1 files changed, 100 insertions, 82 deletions

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 436b6ca6b175..6a7a26b6cec1 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -128,7 +128,7 @@ BFQ_BFQQ_FNS(busy);
 BFQ_BFQQ_FNS(wait_request);
 BFQ_BFQQ_FNS(non_blocking_wait_rq);
 BFQ_BFQQ_FNS(fifo_expire);
-BFQ_BFQQ_FNS(idle_window);
+BFQ_BFQQ_FNS(has_short_ttime);
 BFQ_BFQQ_FNS(sync);
 BFQ_BFQQ_FNS(IO_bound);
 BFQ_BFQQ_FNS(in_large_burst);
@@ -731,10 +731,10 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 	unsigned int old_wr_coeff = bfqq->wr_coeff;
 	bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq);
 
-	if (bic->saved_idle_window)
-		bfq_mark_bfqq_idle_window(bfqq);
+	if (bic->saved_has_short_ttime)
+		bfq_mark_bfqq_has_short_ttime(bfqq);
 	else
-		bfq_clear_bfqq_idle_window(bfqq);
+		bfq_clear_bfqq_has_short_ttime(bfqq);
 
 	if (bic->saved_IO_bound)
 		bfq_mark_bfqq_IO_bound(bfqq);
@@ -2012,7 +2012,7 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 		return;
 
 	bic->saved_ttime = bfqq->ttime;
-	bic->saved_idle_window = bfq_bfqq_idle_window(bfqq);
+	bic->saved_has_short_ttime = bfq_bfqq_has_short_ttime(bfqq);
 	bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
 	bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
 	bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
@@ -3038,8 +3038,8 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
 	}
 
 	bfq_log_bfqq(bfqd, bfqq,
-		"expire (%d, slow %d, num_disp %d, idle_win %d)", reason,
-		slow, bfqq->dispatched, bfq_bfqq_idle_window(bfqq));
+		"expire (%d, slow %d, num_disp %d, short_ttime %d)", reason,
+		slow, bfqq->dispatched, bfq_bfqq_has_short_ttime(bfqq));
 
 	/*
 	 * Increase, decrease or leave budget unchanged according to
@@ -3114,7 +3114,10 @@ static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
 static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
 {
 	struct bfq_data *bfqd = bfqq->bfqd;
-	bool idling_boosts_thr, idling_boosts_thr_without_issues,
+	bool rot_without_queueing =
+		!blk_queue_nonrot(bfqd->queue) && !bfqd->hw_tag,
+		bfqq_sequential_and_IO_bound,
+		idling_boosts_thr, idling_boosts_thr_without_issues,
 		idling_needed_for_service_guarantees,
 		asymmetric_scenario;
 
@@ -3122,27 +3125,45 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
 		return true;
 
 	/*
+	 * Idling is performed only if slice_idle > 0. In addition, we
+	 * do not idle if
+	 * (a) bfqq is async
+	 * (b) bfqq is in the idle io prio class: in this case we do
+	 * not idle because we want to minimize the bandwidth that
+	 * queues in this class can steal to higher-priority queues
+	 */
+	if (bfqd->bfq_slice_idle == 0 || !bfq_bfqq_sync(bfqq) ||
+	    bfq_class_idle(bfqq))
+		return false;
+
+	bfqq_sequential_and_IO_bound = !BFQQ_SEEKY(bfqq) &&
+		bfq_bfqq_IO_bound(bfqq) && bfq_bfqq_has_short_ttime(bfqq);
+
+	/*
 	 * The next variable takes into account the cases where idling
 	 * boosts the throughput.
 	 *
 	 * The value of the variable is computed considering, first, that
 	 * idling is virtually always beneficial for the throughput if:
-	 * (a) the device is not NCQ-capable, or
-	 * (b) regardless of the presence of NCQ, the device is rotational
-	 *     and the request pattern for bfqq is I/O-bound and sequential.
+	 * (a) the device is not NCQ-capable and rotational, or
+	 * (b) regardless of the presence of NCQ, the device is rotational and
+	 *     the request pattern for bfqq is I/O-bound and sequential, or
+	 * (c) regardless of whether it is rotational, the device is
+	 *     not NCQ-capable and the request pattern for bfqq is
+	 *     I/O-bound and sequential.
 	 *
 	 * Secondly, and in contrast to the above item (b), idling an
 	 * NCQ-capable flash-based device would not boost the
 	 * throughput even with sequential I/O; rather it would lower
 	 * the throughput in proportion to how fast the device
 	 * is. Accordingly, the next variable is true if any of the
-	 * above conditions (a) and (b) is true, and, in particular,
-	 * happens to be false if bfqd is an NCQ-capable flash-based
-	 * device.
+	 * above conditions (a), (b) or (c) is true, and, in
+	 * particular, happens to be false if bfqd is an NCQ-capable
+	 * flash-based device.
 	 */
-	idling_boosts_thr = !bfqd->hw_tag ||
-		(!blk_queue_nonrot(bfqd->queue) && bfq_bfqq_IO_bound(bfqq) &&
-		 bfq_bfqq_idle_window(bfqq));
+	idling_boosts_thr = rot_without_queueing ||
+		((!blk_queue_nonrot(bfqd->queue) || !bfqd->hw_tag) &&
+		 bfqq_sequential_and_IO_bound);
 
 	/*
 	 * The value of the next variable,
@@ -3313,16 +3334,13 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
 		asymmetric_scenario && !bfq_bfqq_in_large_burst(bfqq);
 
 	/*
-	 * We have now all the components we need to compute the return
-	 * value of the function, which is true only if both the following
-	 * conditions hold:
-	 * 1) bfqq is sync, because idling make sense only for sync queues;
-	 * 2) idling either boosts the throughput (without issues), or
-	 *    is necessary to preserve service guarantees.
+	 * We have now all the components we need to compute the
+	 * return value of the function, which is true only if idling
+	 * either boosts the throughput (without issues), or is
+	 * necessary to preserve service guarantees.
 	 */
-	return bfq_bfqq_sync(bfqq) &&
-		(idling_boosts_thr_without_issues ||
-		 idling_needed_for_service_guarantees);
+	return idling_boosts_thr_without_issues ||
+		idling_needed_for_service_guarantees;
 }
 
 /*
@@ -3338,10 +3356,7 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
  */
 static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
 {
-	struct bfq_data *bfqd = bfqq->bfqd;
-
-	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfqd->bfq_slice_idle != 0 &&
-	       bfq_bfqq_may_idle(bfqq);
+	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_may_idle(bfqq);
 }
 
 /*
@@ -3783,7 +3798,6 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
 	case IOPRIO_CLASS_IDLE:
 		bfqq->new_ioprio_class = IOPRIO_CLASS_IDLE;
 		bfqq->new_ioprio = 7;
-		bfq_clear_bfqq_idle_window(bfqq);
 		break;
 	}
 
@@ -3843,8 +3857,14 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		bfq_set_next_ioprio_data(bfqq, bic);
 
 	if (is_sync) {
+		/*
+		 * No need to mark as has_short_ttime if in
+		 * idle_class, because no device idling is performed
+		 * for queues in idle class
+		 */
 		if (!bfq_class_idle(bfqq))
-			bfq_mark_bfqq_idle_window(bfqq);
+			/* tentatively mark as has_short_ttime */
+			bfq_mark_bfqq_has_short_ttime(bfqq);
 		bfq_mark_bfqq_sync(bfqq);
 		bfq_mark_bfqq_just_created(bfqq);
 	} else
@@ -3985,18 +4005,19 @@ bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		 blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT);
 }
 
-/*
- * Disable idle window if the process thinks too long or seeks so much that
- * it doesn't matter.
- */
-static void bfq_update_idle_window(struct bfq_data *bfqd,
-				   struct bfq_queue *bfqq,
-				   struct bfq_io_cq *bic)
+static void bfq_update_has_short_ttime(struct bfq_data *bfqd,
+				       struct bfq_queue *bfqq,
+				       struct bfq_io_cq *bic)
 {
-	int enable_idle;
+	bool has_short_ttime = true;
 
-	/* Don't idle for async or idle io prio class. */
-	if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq))
+	/*
+	 * No need to update has_short_ttime if bfqq is async or in
+	 * idle io prio class, or if bfq_slice_idle is zero, because
+	 * no device idling is performed for bfqq in this case.
+	 */
+	if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq) ||
+	    bfqd->bfq_slice_idle == 0)
 		return;
 
 	/* Idle window just restored, statistics are meaningless. */
@@ -4004,27 +4025,22 @@ static void bfq_update_idle_window(struct bfq_data *bfqd,
 				     bfqd->bfq_wr_min_idle_time))
 		return;
 
-	enable_idle = bfq_bfqq_idle_window(bfqq);
-
+	/* Think time is infinite if no process is linked to
+	 * bfqq. Otherwise check average think time to
+	 * decide whether to mark as has_short_ttime
+	 */
 	if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
-	    bfqd->bfq_slice_idle == 0 ||
-		(bfqd->hw_tag && BFQQ_SEEKY(bfqq) &&
-			bfqq->wr_coeff == 1))
-		enable_idle = 0;
-	else if (bfq_sample_valid(bfqq->ttime.ttime_samples)) {
-		if (bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle &&
-			bfqq->wr_coeff == 1)
-			enable_idle = 0;
-		else
-			enable_idle = 1;
-	}
-	bfq_log_bfqq(bfqd, bfqq, "update_idle_window: enable_idle %d",
-		enable_idle);
+	    (bfq_sample_valid(bfqq->ttime.ttime_samples) &&
+	     bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle))
+		has_short_ttime = false;
 
-	if (enable_idle)
-		bfq_mark_bfqq_idle_window(bfqq);
+	bfq_log_bfqq(bfqd, bfqq, "update_has_short_ttime: has_short_ttime %d",
+		     has_short_ttime);
+
+	if (has_short_ttime)
+		bfq_mark_bfqq_has_short_ttime(bfqq);
 	else
-		bfq_clear_bfqq_idle_window(bfqq);
+		bfq_clear_bfqq_has_short_ttime(bfqq);
 }
 
 /*
@@ -4040,14 +4056,12 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		bfqq->meta_pending++;
 
 	bfq_update_io_thinktime(bfqd, bfqq);
+	bfq_update_has_short_ttime(bfqd, bfqq, bic);
 	bfq_update_io_seektime(bfqd, bfqq, rq);
-	if (bfqq->entity.service > bfq_max_budget(bfqd) / 8 ||
-	    !BFQQ_SEEKY(bfqq))
-		bfq_update_idle_window(bfqd, bfqq, bic);
 
 	bfq_log_bfqq(bfqd, bfqq,
-		     "rq_enqueued: idle_window=%d (seeky %d)",
-		     bfq_bfqq_idle_window(bfqq), BFQQ_SEEKY(bfqq));
+		     "rq_enqueued: has_short_ttime=%d (seeky %d)",
+		     bfq_bfqq_has_short_ttime(bfqq), BFQQ_SEEKY(bfqq));
 
 	bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
 
@@ -4787,16 +4801,13 @@ static ssize_t bfq_var_show(unsigned int var, char *page)
 	return sprintf(page, "%u\n", var);
 }
 
-static ssize_t bfq_var_store(unsigned long *var, const char *page,
-			     size_t count)
+static void bfq_var_store(unsigned long *var, const char *page)
 {
 	unsigned long new_val;
 	int ret = kstrtoul(page, 10, &new_val);
 
 	if (ret == 0)
 		*var = new_val;
-
-	return count;
 }
 
 #define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
@@ -4838,7 +4849,7 @@ __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
 {									\
 	struct bfq_data *bfqd = e->elevator_data;			\
 	unsigned long uninitialized_var(__data);			\
-	int ret = bfq_var_store(&__data, (page), count);		\
+	bfq_var_store(&__data, (page));					\
 	if (__data < (MIN))						\
 		__data = (MIN);						\
 	else if (__data > (MAX))					\
@@ -4849,7 +4860,7 @@ __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
 		*(__PTR) = (u64)__data * NSEC_PER_MSEC;			\
 	else								\
 		*(__PTR) = __data;					\
-	return ret;							\
+	return count;							\
 }
 STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1,
 		INT_MAX, 2);
@@ -4866,13 +4877,13 @@ static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)\
 {									\
 	struct bfq_data *bfqd = e->elevator_data;			\
 	unsigned long uninitialized_var(__data);			\
-	int ret = bfq_var_store(&__data, (page), count);		\
+	bfq_var_store(&__data, (page));					\
 	if (__data < (MIN))						\
 		__data = (MIN);						\
 	else if (__data > (MAX))					\
 		__data = (MAX);						\
 	*(__PTR) = (u64)__data * NSEC_PER_USEC;				\
-	return ret;							\
+	return count;							\
 }
 USEC_STORE_FUNCTION(bfq_slice_idle_us_store, &bfqd->bfq_slice_idle, 0,
 		    UINT_MAX);
@@ -4883,7 +4894,8 @@ static ssize_t bfq_max_budget_store(struct elevator_queue *e,
 {
 	struct bfq_data *bfqd = e->elevator_data;
 	unsigned long uninitialized_var(__data);
-	int ret = bfq_var_store(&__data, (page), count);
+
+	bfq_var_store(&__data, (page));
 
 	if (__data == 0)
 		bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd);
@@ -4895,7 +4907,7 @@ static ssize_t bfq_max_budget_store(struct elevator_queue *e,
 
 	bfqd->bfq_user_max_budget = __data;
 
-	return ret;
+	return count;
 }
 
 /*
@@ -4907,7 +4919,8 @@ static ssize_t bfq_timeout_sync_store(struct elevator_queue *e,
 {
 	struct bfq_data *bfqd = e->elevator_data;
 	unsigned long uninitialized_var(__data);
-	int ret = bfq_var_store(&__data, (page), count);
+
+	bfq_var_store(&__data, (page));
 
 	if (__data < 1)
 		__data = 1;
@@ -4918,7 +4931,7 @@ static ssize_t bfq_timeout_sync_store(struct elevator_queue *e,
 	if (bfqd->bfq_user_max_budget == 0)
 		bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd);
 
-	return ret;
+	return count;
 }
 
 static ssize_t bfq_strict_guarantees_store(struct elevator_queue *e,
@@ -4926,7 +4939,8 @@ static ssize_t bfq_strict_guarantees_store(struct elevator_queue *e,
 {
 	struct bfq_data *bfqd = e->elevator_data;
 	unsigned long uninitialized_var(__data);
-	int ret = bfq_var_store(&__data, (page), count);
+
+	bfq_var_store(&__data, (page));
 
 	if (__data > 1)
 		__data = 1;
@@ -4936,7 +4950,7 @@ static ssize_t bfq_strict_guarantees_store(struct elevator_queue *e,
 
 	bfqd->strict_guarantees = __data;
 
-	return ret;
+	return count;
 }
 
 static ssize_t bfq_low_latency_store(struct elevator_queue *e,
@@ -4944,7 +4958,8 @@ static ssize_t bfq_low_latency_store(struct elevator_queue *e,
 {
 	struct bfq_data *bfqd = e->elevator_data;
 	unsigned long uninitialized_var(__data);
-	int ret = bfq_var_store(&__data, (page), count);
+
+	bfq_var_store(&__data, (page));
 
 	if (__data > 1)
 		__data = 1;
@@ -4952,7 +4967,7 @@ static ssize_t bfq_low_latency_store(struct elevator_queue *e,
 		bfq_end_wr(bfqd);
 	bfqd->low_latency = __data;
 
-	return ret;
+	return count;
 }
 
 #define BFQ_ATTR(name) \
@@ -4998,6 +5013,7 @@ static struct elevator_type iosched_bfq_mq = {
 	.elevator_name =	"bfq",
 	.elevator_owner =	THIS_MODULE,
 };
+MODULE_ALIAS("bfq-iosched");
 
 static int __init bfq_init(void)
 {
@@ -5048,10 +5064,12 @@ static int __init bfq_init(void)
 
 	ret = elv_register(&iosched_bfq_mq);
 	if (ret)
-		goto err_pol_unreg;
+		goto slab_kill;
 
 	return 0;
 
+slab_kill:
+	bfq_slab_kill();
 err_pol_unreg:
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
 	blkcg_policy_unregister(&blkcg_policy_bfq);