diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index f12669819d1a..d17ed6fb2f70 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -7,6 +7,7 @@
 #include <linux/pkt_sched.h>
 #include <linux/pkt_cls.h>
 #include <linux/percpu.h>
+#include <linux/dynamic_queue_limits.h>
 #include <net/gen_stats.h>
 #include <net/rtnetlink.h>
 
@@ -119,6 +120,21 @@ static inline void qdisc_run_end(struct Qdisc *qdisc)
 	qdisc->__state &= ~__QDISC___STATE_RUNNING;
 }
 
+static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
+{
+	return qdisc->flags & TCQ_F_ONETXQUEUE;
+}
+
+static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq)
+{
+#ifdef CONFIG_BQL
+	/* Non-BQL migrated drivers will return 0, too. */
+	return dql_avail(&txq->dql);
+#else
+	return 0;
+#endif
+}
+
 static inline bool qdisc_is_throttled(const struct Qdisc *qdisc)
 {
 	return test_bit(__QDISC_STATE_THROTTLED, &qdisc->state) ? true : false;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 7c8e5d73d433..c2e87e63b832 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -56,6 +56,41 @@ static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 	return 0;
 }
 
+static struct sk_buff *try_bulk_dequeue_skb(struct Qdisc *q,
+					    struct sk_buff *head_skb,
+					    int bytelimit)
+{
+	struct sk_buff *skb, *tail_skb = head_skb;
+
+	while (bytelimit > 0) {
+		/* For now, don't bulk dequeue GSO (or GSO segmented) pkts */
+		if (tail_skb->next || skb_is_gso(tail_skb))
+			break;
+
+		skb = q->dequeue(q);
+		if (!skb)
+			break;
+
+		bytelimit -= skb->len; /* covers GSO len */
+		skb = validate_xmit_skb(skb, qdisc_dev(q));
+		if (!skb)
+			break;
+
+		/* "skb" can be a skb list after validate call above
+		 * (GSO segmented), but it is okay to append it to
+		 * current tail_skb->next, because next round will exit
+		 * in-case "tail_skb->next" is a skb list.
+		 */
+		tail_skb->next = skb;
+		tail_skb = skb;
+	}
+
+	return head_skb;
+}
+
+/* Note that dequeue_skb can possibly return a SKB list (via skb->next).
+ * A requeued skb (via q->gso_skb) can also be a SKB list.
+ */
 static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
 {
 	struct sk_buff *skb = q->gso_skb;
@@ -70,10 +105,17 @@ static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
 		} else
 			skb = NULL;
 	} else {
-		if (!(q->flags & TCQ_F_ONETXQUEUE) || !netif_xmit_frozen_or_stopped(txq)) {
+		if (!(q->flags & TCQ_F_ONETXQUEUE) ||
+		    !netif_xmit_frozen_or_stopped(txq)) {
+			int bytelimit = qdisc_avail_bulklimit(txq);
+
 			skb = q->dequeue(q);
-			if (skb)
+			if (skb) {
+				bytelimit -= skb->len;
 				skb = validate_xmit_skb(skb, qdisc_dev(q));
+			}
+			if (skb && qdisc_may_bulk(q))
+				skb = try_bulk_dequeue_skb(q, skb, bytelimit);
 		}
 	}