Merge drm/drm-next into drm-intel-next-queued

Pull in v4.20-rc3 via drm-next.

Signed-off-by: Jani Nikula <jani.nikula@intel.com>

34 files changed, 1830 insertions, 1084 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 1f2469a0123c..f7045aa47edb 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -74,7 +74,6 @@ config BLK_DEV_BSG
 
 config BLK_DEV_BSGLIB
 	bool "Block layer SG support v4 helper lib"
-	default n
 	select BLK_DEV_BSG
 	select BLK_SCSI_REQUEST
 	help
@@ -107,7 +106,6 @@ config BLK_DEV_ZONED
 config BLK_DEV_THROTTLING
 	bool "Block layer bio throttling support"
 	depends on BLK_CGROUP=y
-	default n
 	---help---
 	Block layer bio throttling support. It can be used to limit
 	the IO rate to a device. IO rate policies are per cgroup and
@@ -119,7 +117,6 @@ config BLK_DEV_THROTTLING
 config BLK_DEV_THROTTLING_LOW
 	bool "Block throttling .low limit interface support (EXPERIMENTAL)"
 	depends on BLK_DEV_THROTTLING
-	default n
 	---help---
 	Add .low limit interface for block throttling. The low limit is a best
 	effort limit to prioritize cgroups. Depending on the setting, the limit
@@ -130,7 +127,6 @@ config BLK_DEV_THROTTLING_LOW
 
 config BLK_CMDLINE_PARSER
 	bool "Block device command line partition parser"
-	default n
 	---help---
 	Enabling this option allows you to specify the partition layout from
 	the kernel boot args.  This is typically of use for embedded devices
@@ -141,7 +137,6 @@ config BLK_CMDLINE_PARSER
 
 config BLK_WBT
 	bool "Enable support for block device writeback throttling"
-	default n
 	---help---
 	Enabling this option enables the block layer to throttle buffered
 	background writeback from the VM, making it more smooth and having
@@ -152,7 +147,6 @@ config BLK_WBT
 config BLK_CGROUP_IOLATENCY
 	bool "Enable support for latency based cgroup IO protection"
 	depends on BLK_CGROUP=y
-	default n
 	---help---
 	Enabling this option enables the .latency interface for IO throttling.
 	The IO controller will attempt to maintain average IO latencies below
@@ -163,7 +157,6 @@ config BLK_CGROUP_IOLATENCY
 
 config BLK_WBT_SQ
 	bool "Single queue writeback throttling"
-	default n
 	depends on BLK_WBT
 	---help---
 	Enable writeback throttling by default on legacy single queue devices
@@ -228,4 +221,7 @@ config BLK_MQ_RDMA
 	depends on BLOCK && INFINIBAND
 	default y
 
+config BLK_PM
+	def_bool BLOCK && PM
+
 source block/Kconfig.iosched
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index a4a8914bf7a4..f95a48b0d7b2 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -36,7 +36,6 @@ config IOSCHED_CFQ
 config CFQ_GROUP_IOSCHED
 	bool "CFQ Group Scheduling support"
 	depends on IOSCHED_CFQ && BLK_CGROUP
-	default n
 	---help---
 	  Enable group IO scheduling in CFQ.
 
@@ -82,7 +81,6 @@ config MQ_IOSCHED_KYBER
 
 config IOSCHED_BFQ
 	tristate "BFQ I/O scheduler"
-	default n
 	---help---
 	BFQ I/O scheduler for BLK-MQ. BFQ distributes the bandwidth of
 	of the device among all processes according to their weights,
@@ -94,7 +92,6 @@ config IOSCHED_BFQ
 config BFQ_GROUP_IOSCHED
        bool "BFQ hierarchical scheduling support"
        depends on IOSCHED_BFQ && BLK_CGROUP
-       default n
        ---help---
 
        Enable hierarchical scheduling in BFQ, using the blkio
diff --git a/block/Makefile b/block/Makefile
index 572b33f32c07..27eac600474f 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -37,3 +37,4 @@ obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
 obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o
 obj-$(CONFIG_BLK_DEBUG_FS_ZONED)+= blk-mq-debugfs-zoned.o
 obj-$(CONFIG_BLK_SED_OPAL)	+= sed-opal.o
+obj-$(CONFIG_BLK_PM)		+= blk-pm.o
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 653100fb719e..3a27d31fcda6 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -624,12 +624,13 @@ void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 }
 
 /*
- * Tell whether there are active queues or groups with differentiated weights.
+ * Tell whether there are active queues with different weights or
+ * active groups.
  */
-static bool bfq_differentiated_weights(struct bfq_data *bfqd)
+static bool bfq_varied_queue_weights_or_active_groups(struct bfq_data *bfqd)
 {
 	/*
-	 * For weights to differ, at least one of the trees must contain
+	 * For queue weights to differ, queue_weights_tree must contain
 	 * at least two nodes.
 	 */
 	return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
@@ -637,9 +638,7 @@ static bool bfq_differentiated_weights(struct bfq_data *bfqd)
 		 bfqd->queue_weights_tree.rb_node->rb_right)
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
 	       ) ||
-	       (!RB_EMPTY_ROOT(&bfqd->group_weights_tree) &&
-		(bfqd->group_weights_tree.rb_node->rb_left ||
-		 bfqd->group_weights_tree.rb_node->rb_right)
+		(bfqd->num_active_groups > 0
 #endif
 	       );
 }
@@ -657,26 +656,25 @@ static bool bfq_differentiated_weights(struct bfq_data *bfqd)
  * 3) all active groups at the same level in the groups tree have the same
  *    number of children.
  *
- * Unfortunately, keeping the necessary state for evaluating exactly the
- * above symmetry conditions would be quite complex and time-consuming.
- * Therefore this function evaluates, instead, the following stronger
- * sub-conditions, for which it is much easier to maintain the needed
- * state:
+ * Unfortunately, keeping the necessary state for evaluating exactly
+ * the last two symmetry sub-conditions above would be quite complex
+ * and time consuming.  Therefore this function evaluates, instead,
+ * only the following stronger two sub-conditions, for which it is
+ * much easier to maintain the needed state:
  * 1) all active queues have the same weight,
- * 2) all active groups have the same weight,
- * 3) all active groups have at most one active child each.
- * In particular, the last two conditions are always true if hierarchical
- * support and the cgroups interface are not enabled, thus no state needs
- * to be maintained in this case.
+ * 2) there are no active groups.
+ * In particular, the last condition is always true if hierarchical
+ * support or the cgroups interface are not enabled, thus no state
+ * needs to be maintained in this case.
  */
 static bool bfq_symmetric_scenario(struct bfq_data *bfqd)
 {
-	return !bfq_differentiated_weights(bfqd);
+	return !bfq_varied_queue_weights_or_active_groups(bfqd);
 }
 
 /*
  * If the weight-counter tree passed as input contains no counter for
- * the weight of the input entity, then add that counter; otherwise just
+ * the weight of the input queue, then add that counter; otherwise just
  * increment the existing counter.
  *
  * Note that weight-counter trees contain few nodes in mostly symmetric
@@ -687,25 +685,25 @@ static bool bfq_symmetric_scenario(struct bfq_data *bfqd)
  * In most scenarios, the rate at which nodes are created/destroyed
  * should be low too.
  */
-void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
+void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 			  struct rb_root *root)
 {
+	struct bfq_entity *entity = &bfqq->entity;
 	struct rb_node **new = &(root->rb_node), *parent = NULL;
 
 	/*
-	 * Do not insert if the entity is already associated with a
+	 * Do not insert if the queue is already associated with a
 	 * counter, which happens if:
-	 *   1) the entity is associated with a queue,
-	 *   2) a request arrival has caused the queue to become both
+	 *   1) a request arrival has caused the queue to become both
 	 *      non-weight-raised, and hence change its weight, and
 	 *      backlogged; in this respect, each of the two events
 	 *      causes an invocation of this function,
-	 *   3) this is the invocation of this function caused by the
+	 *   2) this is the invocation of this function caused by the
 	 *      second event. This second invocation is actually useless,
 	 *      and we handle this fact by exiting immediately. More
 	 *      efficient or clearer solutions might possibly be adopted.
 	 */
-	if (entity->weight_counter)
+	if (bfqq->weight_counter)
 		return;
 
 	while (*new) {
@@ -715,7 +713,7 @@ void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
 		parent = *new;
 
 		if (entity->weight == __counter->weight) {
-			entity->weight_counter = __counter;
+			bfqq->weight_counter = __counter;
 			goto inc_counter;
 		}
 		if (entity->weight < __counter->weight)
@@ -724,66 +722,67 @@ void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
 			new = &((*new)->rb_right);
 	}
 
-	entity->weight_counter = kzalloc(sizeof(struct bfq_weight_counter),
-					 GFP_ATOMIC);
+	bfqq->weight_counter = kzalloc(sizeof(struct bfq_weight_counter),
+				       GFP_ATOMIC);
 
 	/*
 	 * In the unlucky event of an allocation failure, we just
-	 * exit. This will cause the weight of entity to not be
-	 * considered in bfq_differentiated_weights, which, in its
-	 * turn, causes the scenario to be deemed wrongly symmetric in
-	 * case entity's weight would have been the only weight making
-	 * the scenario asymmetric. On the bright side, no unbalance
-	 * will however occur when entity becomes inactive again (the
-	 * invocation of this function is triggered by an activation
-	 * of entity). In fact, bfq_weights_tree_remove does nothing
-	 * if !entity->weight_counter.
+	 * exit. This will cause the weight of queue to not be
+	 * considered in bfq_varied_queue_weights_or_active_groups,
+	 * which, in its turn, causes the scenario to be deemed
+	 * wrongly symmetric in case bfqq's weight would have been
+	 * the only weight making the scenario asymmetric.  On the
+	 * bright side, no unbalance will however occur when bfqq
+	 * becomes inactive again (the invocation of this function
+	 * is triggered by an activation of queue).  In fact,
+	 * bfq_weights_tree_remove does nothing if
+	 * !bfqq->weight_counter.
 	 */
-	if (unlikely(!entity->weight_counter))
+	if (unlikely(!bfqq->weight_counter))
 		return;
 
-	entity->weight_counter->weight = entity->weight;
-	rb_link_node(&entity->weight_counter->weights_node, parent, new);
-	rb_insert_color(&entity->weight_counter->weights_node, root);
+	bfqq->weight_counter->weight = entity->weight;
+	rb_link_node(&bfqq->weight_counter->weights_node, parent, new);
+	rb_insert_color(&bfqq->weight_counter->weights_node, root);
 
 inc_counter:
-	entity->weight_counter->num_active++;
+	bfqq->weight_counter->num_active++;
 }
 
 /*
- * Decrement the weight counter associated with the entity, and, if the
+ * Decrement the weight counter associated with the queue, and, if the
  * counter reaches 0, remove the counter from the tree.
  * See the comments to the function bfq_weights_tree_add() for considerations
  * about overhead.
  */
 void __bfq_weights_tree_remove(struct bfq_data *bfqd,
-			       struct bfq_entity *entity,
+			       struct bfq_queue *bfqq,
 			       struct rb_root *root)
 {
-	if (!entity->weight_counter)
+	if (!bfqq->weight_counter)
 		return;
 
-	entity->weight_counter->num_active--;
-	if (entity->weight_counter->num_active > 0)
+	bfqq->weight_counter->num_active--;
+	if (bfqq->weight_counter->num_active > 0)
 		goto reset_entity_pointer;
 
-	rb_erase(&entity->weight_counter->weights_node, root);
-	kfree(entity->weight_counter);
+	rb_erase(&bfqq->weight_counter->weights_node, root);
+	kfree(bfqq->weight_counter);
 
 reset_entity_pointer:
-	entity->weight_counter = NULL;
+	bfqq->weight_counter = NULL;
 }
 
 /*
- * Invoke __bfq_weights_tree_remove on bfqq and all its inactive
- * parent entities.
+ * Invoke __bfq_weights_tree_remove on bfqq and decrement the number
+ * of active groups for each queue's inactive parent entity.
  */
 void bfq_weights_tree_remove(struct bfq_data *bfqd,
 			     struct bfq_queue *bfqq)
 {
 	struct bfq_entity *entity = bfqq->entity.parent;
 
-	__bfq_weights_tree_remove(bfqd, &bfqq->entity,
+	__bfq_weights_tree_remove(bfqd, bfqq,
 				  &bfqd->queue_weights_tree);
 
 	for_each_entity(entity) {
@@ -797,17 +796,13 @@ void bfq_weights_tree_remove(struct bfq_data *bfqd,
 			 * next_in_service for details on why
 			 * in_service_entity must be checked too).
 			 *
-			 * As a consequence, the weight of entity is
-			 * not to be removed. In addition, if entity
-			 * is active, then its parent entities are
-			 * active as well, and thus their weights are
-			 * not to be removed either. In the end, this
-			 * loop must stop here.
+			 * As a consequence, its parent entities are
+			 * active as well, and thus this loop must
+			 * stop here.
 			 */
 			break;
 		}
-		__bfq_weights_tree_remove(bfqd, entity,
-					  &bfqd->group_weights_tree);
+		bfqd->num_active_groups--;
 	}
 }
 
@@ -3182,6 +3177,13 @@ static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
 		    jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
 }
 
+static bool bfq_bfqq_injectable(struct bfq_queue *bfqq)
+{
+	return BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 &&
+		blk_queue_nonrot(bfqq->bfqd->queue) &&
+		bfqq->bfqd->hw_tag;
+}
+
 /**
  * bfq_bfqq_expire - expire a queue.
  * @bfqd: device owning the queue.
@@ -3291,6 +3293,8 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
 	if (ref == 1) /* bfqq is gone, no more actions on it */
 		return;
 
+	bfqq->injected_service = 0;
+
 	/* mark bfqq as waiting a request only if a bic still points to it */
 	if (!bfq_bfqq_busy(bfqq) &&
 	    reason != BFQQE_BUDGET_TIMEOUT &&
@@ -3497,9 +3501,11 @@ static bool bfq_better_to_idle(struct bfq_queue *bfqq)
 	 * symmetric scenario where:
 	 * (i)  each of these processes must get the same throughput as
 	 *      the others;
-	 * (ii) all these processes have the same I/O pattern
-		(either sequential or random).
-	 * In fact, in such a scenario, the drive will tend to treat
+	 * (ii) the I/O of each process has the same properties, in
+	 *      terms of locality (sequential or random), direction
+	 *      (reads or writes), request sizes, greediness
+	 *      (from I/O-bound to sporadic), and so on.
+	 * In fact, in such a scenario, the drive tends to treat
 	 * the requests of each of these processes in about the same
 	 * way as the requests of the others, and thus to provide
 	 * each of these processes with about the same throughput
@@ -3508,18 +3514,50 @@ static bool bfq_better_to_idle(struct bfq_queue *bfqq)
 	 * certainly needed to guarantee that bfqq receives its
 	 * assigned fraction of the device throughput (see [1] for
 	 * details).
+	 * The problem is that idling may significantly reduce
+	 * throughput with certain combinations of types of I/O and
+	 * devices. An important example is sync random I/O, on flash
+	 * storage with command queueing. So, unless bfqq falls in the
+	 * above cases where idling also boosts throughput, it would
+	 * be important to check conditions (i) and (ii) accurately,
+	 * so as to avoid idling when not strictly needed for service
+	 * guarantees.
+	 *
+	 * Unfortunately, it is extremely difficult to thoroughly
+	 * check condition (ii). And, in case there are active groups,
+	 * it becomes very difficult to check condition (i) too. In
+	 * fact, if there are active groups, then, for condition (i)
+	 * to become false, it is enough that an active group contains
+	 * more active processes or sub-groups than some other active
+	 * group. We address this issue with the following bi-modal
+	 * behavior, implemented in the function
+	 * bfq_symmetric_scenario().
 	 *
-	 * We address this issue by controlling, actually, only the
-	 * symmetry sub-condition (i), i.e., provided that
-	 * sub-condition (i) holds, idling is not performed,
-	 * regardless of whether sub-condition (ii) holds. In other
-	 * words, only if sub-condition (i) holds, then idling is
+	 * If there are active groups, then the scenario is tagged as
+	 * asymmetric, conservatively, without checking any of the
+	 * conditions (i) and (ii). So the device is idled for bfqq.
+	 * This behavior matches also the fact that groups are created
+	 * exactly if controlling I/O (to preserve bandwidth and
+	 * latency guarantees) is a primary concern.
+	 *
+	 * On the opposite end, if there are no active groups, then
+	 * only condition (i) is actually controlled, i.e., provided
+	 * that condition (i) holds, idling is not performed,
+	 * regardless of whether condition (ii) holds. In other words,
+	 * only if condition (i) does not hold, then idling is
 	 * allowed, and the device tends to be prevented from queueing
-	 * many requests, possibly of several processes. The reason
-	 * for not controlling also sub-condition (ii) is that we
-	 * exploit preemption to preserve guarantees in case of
-	 * symmetric scenarios, even if (ii) does not hold, as
-	 * explained in the next two paragraphs.
+	 * many requests, possibly of several processes. Since there
+	 * are no active groups, then, to control condition (i) it is
+	 * enough to check whether all active queues have the same
+	 * weight.
+	 *
+	 * Not checking condition (ii) evidently exposes bfqq to the
+	 * risk of getting less throughput than its fair share.
+	 * However, for queues with the same weight, a further
+	 * mechanism, preemption, mitigates or even eliminates this
+	 * problem. And it does so without consequences on overall
+	 * throughput. This mechanism and its benefits are explained
+	 * in the next three paragraphs.
 	 *
 	 * Even if a queue, say Q, is expired when it remains idle, Q
 	 * can still preempt the new in-service queue if the next
@@ -3533,11 +3571,7 @@ static bool bfq_better_to_idle(struct bfq_queue *bfqq)
 	 * idling allows the internal queues of the device to contain
 	 * many requests, and thus to reorder requests, we can rather
 	 * safely assume that the internal scheduler still preserves a
-	 * minimum of mid-term fairness. The motivation for using
-	 * preemption instead of idling is that, by not idling,
-	 * service guarantees are preserved without minimally
-	 * sacrificing throughput. In other words, both a high
-	 * throughput and its desired distribution are obtained.
+	 * minimum of mid-term fairness.
 	 *
 	 * More precisely, this preemption-based, idleless approach
 	 * provides fairness in terms of IOPS, and not sectors per
@@ -3556,22 +3590,27 @@ static bool bfq_better_to_idle(struct bfq_queue *bfqq)
 	 * 1024/8 times as high as the service received by the other
 	 * queue.
 	 *
-	 * On the other hand, device idling is performed, and thus
-	 * pure sector-domain guarantees are provided, for the
-	 * following queues, which are likely to need stronger
-	 * throughput guarantees: weight-raised queues, and queues
-	 * with a higher weight than other queues. When such queues
-	 * are active, sub-condition (i) is false, which triggers
-	 * device idling.
+	 * The motivation for using preemption instead of idling (for
+	 * queues with the same weight) is that, by not idling,
+	 * service guarantees are preserved (completely or at least in
+	 * part) without minimally sacrificing throughput. And, if
+	 * there is no active group, then the primary expectation for
+	 * this device is probably a high throughput.
 	 *
-	 * According to the above considerations, the next variable is
-	 * true (only) if sub-condition (i) holds. To compute the
-	 * value of this variable, we not only use the return value of
-	 * the function bfq_symmetric_scenario(), but also check
-	 * whether bfqq is being weight-raised, because
-	 * bfq_symmetric_scenario() does not take into account also
-	 * weight-raised queues (see comments on
-	 * bfq_weights_tree_add()).
+	 * We are now left only with explaining the additional
+	 * compound condition that is checked below for deciding
+	 * whether the scenario is asymmetric. To explain this
+	 * compound condition, we need to add that the function
+	 * bfq_symmetric_scenario checks the weights of only
+	 * non-weight-raised queues, for efficiency reasons (see
+	 * comments on bfq_weights_tree_add()). Then the fact that
+	 * bfqq is weight-raised is checked explicitly here. More
+	 * precisely, the compound condition below takes into account
+	 * also the fact that, even if bfqq is being weight-raised,
+	 * the scenario is still symmetric if all active queues happen
+	 * to be weight-raised. Actually, we should be even more
+	 * precise here, and differentiate between interactive weight
+	 * raising and soft real-time weight raising.
 	 *
 	 * As a side note, it is worth considering that the above
 	 * device-idling countermeasures may however fail in the
@@ -3583,7 +3622,8 @@ static bool bfq_better_to_idle(struct bfq_queue *bfqq)
 	 * to let requests be served in the desired order until all
 	 * the requests already queued in the device have been served.
 	 */
-	asymmetric_scenario = bfqq->wr_coeff > 1 ||
+	asymmetric_scenario = (bfqq->wr_coeff > 1 &&
+			       bfqd->wr_busy_queues < bfqd->busy_queues) ||
 		!bfq_symmetric_scenario(bfqd);
 
 	/*
@@ -3629,6 +3669,30 @@ static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
 	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_better_to_idle(bfqq);
 }
 
+static struct bfq_queue *bfq_choose_bfqq_for_injection(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq;
+
+	/*
+	 * A linear search; but, with a high probability, very few
+	 * steps are needed to find a candidate queue, i.e., a queue
+	 * with enough budget left for its next request. In fact:
+	 * - BFQ dynamically updates the budget of every queue so as
+	 *   to accommodate the expected backlog of the queue;
+	 * - if a queue gets all its requests dispatched as injected
+	 *   service, then the queue is removed from the active list
+	 *   (and re-added only if it gets new requests, but with
+	 *   enough budget for its new backlog).
+	 */
+	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
+		if (!RB_EMPTY_ROOT(&bfqq->sort_list) &&
+		    bfq_serv_to_charge(bfqq->next_rq, bfqq) <=
+		    bfq_bfqq_budget_left(bfqq))
+			return bfqq;
+
+	return NULL;
+}
+
 /*
  * Select a queue for service.  If we have a current queue in service,
  * check whether to continue servicing it, or retrieve and set a new one.
@@ -3710,10 +3774,19 @@ check_queue:
 	 * No requests pending. However, if the in-service queue is idling
 	 * for a new request, or has requests waiting for a completion and
 	 * may idle after their completion, then keep it anyway.
+	 *
+	 * Yet, to boost throughput, inject service from other queues if
+	 * possible.
 	 */
 	if (bfq_bfqq_wait_request(bfqq) ||
 	    (bfqq->dispatched != 0 && bfq_better_to_idle(bfqq))) {
-		bfqq = NULL;
+		if (bfq_bfqq_injectable(bfqq) &&
+		    bfqq->injected_service * bfqq->inject_coeff <
+		    bfqq->entity.service * 10)
+			bfqq = bfq_choose_bfqq_for_injection(bfqd);
+		else
+			bfqq = NULL;
+
 		goto keep_queue;
 	}
 
@@ -3803,6 +3876,14 @@ static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd,
 
 	bfq_dispatch_remove(bfqd->queue, rq);
 
+	if (bfqq != bfqd->in_service_queue) {
+		if (likely(bfqd->in_service_queue))
+			bfqd->in_service_queue->injected_service +=
+				bfq_serv_to_charge(rq, bfqq);
+
+		goto return_rq;
+	}
+
 	/*
 	 * If weight raising has to terminate for bfqq, then next
 	 * function causes an immediate update of bfqq's weight,
@@ -3821,13 +3902,12 @@ static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd,
 	 * belongs to CLASS_IDLE and other queues are waiting for
 	 * service.
 	 */
-	if (bfqd->busy_queues > 1 && bfq_class_idle(bfqq))
-		goto expire;
-
-	return rq;
+	if (!(bfqd->busy_queues > 1 && bfq_class_idle(bfqq)))
+		goto return_rq;
 
-expire:
 	bfq_bfqq_expire(bfqd, bfqq, false, BFQQE_BUDGET_EXHAUSTED);
+
+return_rq:
 	return rq;
 }
 
@@ -4232,6 +4312,13 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 			bfq_mark_bfqq_has_short_ttime(bfqq);
 		bfq_mark_bfqq_sync(bfqq);
 		bfq_mark_bfqq_just_created(bfqq);
+		/*
+		 * Aggressively inject a lot of service: up to 90%.
+		 * This coefficient remains constant during bfqq life,
+		 * but this behavior might be changed, after enough
+		 * testing and tuning.
+		 */
+		bfqq->inject_coeff = 1;
 	} else
 		bfq_clear_bfqq_sync(bfqq);
 
@@ -5330,7 +5417,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
 
 	bfqd->queue_weights_tree = RB_ROOT;
-	bfqd->group_weights_tree = RB_ROOT;
+	bfqd->num_active_groups = 0;
 
 	INIT_LIST_HEAD(&bfqd->active_list);
 	INIT_LIST_HEAD(&bfqd->idle_list);
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index a8a2e5aca4d4..77651d817ecd 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -108,15 +108,14 @@ struct bfq_sched_data {
 };
 
 /**
- * struct bfq_weight_counter - counter of the number of all active entities
+ * struct bfq_weight_counter - counter of the number of all active queues
  *                             with a given weight.
  */
 struct bfq_weight_counter {
-	unsigned int weight; /* weight of the entities this counter refers to */
-	unsigned int num_active; /* nr of active entities with this weight */
+	unsigned int weight; /* weight of the queues this counter refers to */
+	unsigned int num_active; /* nr of active queues with this weight */
 	/*
-	 * Weights tree member (see bfq_data's @queue_weights_tree and
-	 * @group_weights_tree)
+	 * Weights tree member (see bfq_data's @queue_weights_tree)
 	 */
 	struct rb_node weights_node;
 };
@@ -151,8 +150,6 @@ struct bfq_weight_counter {
 struct bfq_entity {
 	/* service_tree member */
 	struct rb_node rb_node;
-	/* pointer to the weight counter associated with this entity */
-	struct bfq_weight_counter *weight_counter;
 
 	/*
 	 * Flag, true if the entity is on a tree (either the active or
@@ -266,6 +263,9 @@ struct bfq_queue {
 	/* entity representing this queue in the scheduler */
 	struct bfq_entity entity;
 
+	/* pointer to the weight counter associated with this entity */
+	struct bfq_weight_counter *weight_counter;
+
 	/* maximum budget allowed from the feedback mechanism */
 	int max_budget;
 	/* budget expiration (in jiffies) */
@@ -351,6 +351,32 @@ struct bfq_queue {
 	unsigned long split_time; /* time of last split */
 
 	unsigned long first_IO_time; /* time of first I/O for this queue */
+
+	/* max service rate measured so far */
+	u32 max_service_rate;
+	/*
+	 * Ratio between the service received by bfqq while it is in
+	 * service, and the cumulative service (of requests of other
+	 * queues) that may be injected while bfqq is empty but still
+	 * in service. To increase precision, the coefficient is
+	 * measured in tenths of unit. Here are some example of (1)
+	 * ratios, (2) resulting percentages of service injected
+	 * w.r.t. to the total service dispatched while bfqq is in
+	 * service, and (3) corresponding values of the coefficient:
+	 * 1 (50%) -> 10
+	 * 2 (33%) -> 20
+	 * 10 (9%) -> 100
+	 * 9.9 (9%) -> 99
+	 * 1.5 (40%) -> 15
+	 * 0.5 (66%) -> 5
+	 * 0.1 (90%) -> 1
+	 *
+	 * So, if the coefficient is lower than 10, then
+	 * injected service is more than bfqq service.
+	 */
+	unsigned int inject_coeff;
+	/* amount of service injected in current service slot */
+	unsigned int injected_service;
 };
 
 /**
@@ -423,14 +449,9 @@ struct bfq_data {
 	 */
 	struct rb_root queue_weights_tree;
 	/*
-	 * rbtree of non-queue @bfq_entity weight counters, sorted by
-	 * weight. Used to keep track of whether all @bfq_groups have
-	 * the same weight. The tree contains one counter for each
-	 * distinct weight associated to some active @bfq_group (see
-	 * the comments to the functions bfq_weights_tree_[add|remove]
-	 * for further details).
+	 * number of groups with requests still waiting for completion
 	 */
-	struct rb_root group_weights_tree;
+	unsigned int num_active_groups;
 
 	/*
 	 * Number of bfq_queues containing requests (including the
@@ -825,10 +846,10 @@ struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync);
 void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync);
 struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic);
 void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq);
-void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
+void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 			  struct rb_root *root);
 void __bfq_weights_tree_remove(struct bfq_data *bfqd,
-			       struct bfq_entity *entity,
+			       struct bfq_queue *bfqq,
 			       struct rb_root *root);
 void bfq_weights_tree_remove(struct bfq_data *bfqd,
 			     struct bfq_queue *bfqq);
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index ae52bff43ce4..4b0d5fb69160 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -788,25 +788,23 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
 		new_weight = entity->orig_weight *
 			     (bfqq ? bfqq->wr_coeff : 1);
 		/*
-		 * If the weight of the entity changes, remove the entity
-		 * from its old weight counter (if there is a counter
-		 * associated with the entity), and add it to the counter