--- zzzz-none-000/linux-3.10.107/net/sched/sch_api.c	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/net/sched/sch_api.c	2021-02-04 17:41:59.000000000 +0000
@@ -135,7 +135,7 @@
 
 static struct Qdisc_ops *qdisc_base;
 
-/* Register/uregister queueing discipline */
+/* Register/unregister queueing discipline */
 
 int register_qdisc(struct Qdisc_ops *qops)
 {
@@ -200,8 +200,61 @@
 }
 EXPORT_SYMBOL(unregister_qdisc);
 
+/* Get default qdisc if not otherwise specified */
+void qdisc_get_default(char *name, size_t len)
+{
+	read_lock(&qdisc_mod_lock);
+	strlcpy(name, default_qdisc_ops->id, len);
+	read_unlock(&qdisc_mod_lock);
+}
+
+static struct Qdisc_ops *qdisc_lookup_default(const char *name)
+{
+	struct Qdisc_ops *q = NULL;
+
+	for (q = qdisc_base; q; q = q->next) {
+		if (!strcmp(name, q->id)) {
+			if (!try_module_get(q->owner))
+				q = NULL;
+			break;
+		}
+	}
+
+	return q;
+}
+
+/* Set new default qdisc to use */
+int qdisc_set_default(const char *name)
+{
+	const struct Qdisc_ops *ops;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	write_lock(&qdisc_mod_lock);
+	ops = qdisc_lookup_default(name);
+	if (!ops) {
+		/* Not found, drop lock and try to load module */
+		write_unlock(&qdisc_mod_lock);
+		request_module("sch_%s", name);
+		write_lock(&qdisc_mod_lock);
+
+		ops = qdisc_lookup_default(name);
+	}
+
+	if (ops) {
+		/* Set new default */
+		module_put(default_qdisc_ops->owner);
+		default_qdisc_ops = ops;
+	}
+	write_unlock(&qdisc_mod_lock);
+
+	return ops ? 0 : -ENOENT;
+}
+
 /* We know handle. Find qdisc among all qdisc's attached to device
-   (root qdisc, all its children, children of children etc.)
+ * (root qdisc, all its children, children of children etc.)
+ * Note: caller either uses rtnl or rcu_read_lock()
  */
 
 static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
@@ -212,23 +265,31 @@
 	    root->handle == handle)
 		return root;
 
-	list_for_each_entry(q, &root->list, list) {
+	list_for_each_entry_rcu(q, &root->list, list) {
 		if (q->handle == handle)
 			return q;
 	}
 	return NULL;
 }
 
-static void qdisc_list_add(struct Qdisc *q)
+void qdisc_list_add(struct Qdisc *q)
 {
-	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
-		list_add_tail(&q->list, &qdisc_dev(q)->qdisc->list);
+	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
+		struct Qdisc *root = qdisc_dev(q)->qdisc;
+
+		WARN_ON_ONCE(root == &noop_qdisc);
+		ASSERT_RTNL();
+		list_add_tail_rcu(&q->list, &root->list);
+	}
 }
+EXPORT_SYMBOL(qdisc_list_add);
 
 void qdisc_list_del(struct Qdisc *q)
 {
-	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
-		list_del(&q->list);
+	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
+		ASSERT_RTNL();
+		list_del_rcu(&q->list);
+	}
 }
 EXPORT_SYMBOL(qdisc_list_del);
 
@@ -247,6 +308,7 @@
 out:
 	return q;
 }
+EXPORT_SYMBOL(qdisc_lookup);
 
 static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid)
 {
@@ -267,7 +329,7 @@
 
 /* Find queueing discipline by name */
 
-static struct Qdisc_ops *qdisc_lookup_ops(struct nlattr *kind)
+struct Qdisc_ops *qdisc_lookup_ops(struct nlattr *kind)
 {
 	struct Qdisc_ops *q = NULL;
 
@@ -284,6 +346,7 @@
 	}
 	return q;
 }
+EXPORT_SYMBOL(qdisc_lookup_ops);
 
 /* The linklayer setting were not transferred from iproute2, in older
  * versions, and the rate tables lookup systems have been dropped in
@@ -506,7 +569,7 @@
 }
 EXPORT_SYMBOL(__qdisc_calculate_pkt_len);
 
-void qdisc_warn_nonwc(char *txt, struct Qdisc *qdisc)
+void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc)
 {
 	if (!(qdisc->flags & TCQ_F_WARN_NONWC)) {
 		pr_warn("%s: %s qdisc %X: is non-work-conserving?\n",
@@ -521,31 +584,34 @@
 	struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog,
 						 timer);
 
+	rcu_read_lock();
 	qdisc_unthrottled(wd->qdisc);
 	__netif_schedule(qdisc_root(wd->qdisc));
+	rcu_read_unlock();
 
 	return HRTIMER_NORESTART;
 }
 
 void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc)
 {
-	hrtimer_init(&wd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer_init(&wd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
 	wd->timer.function = qdisc_watchdog;
 	wd->qdisc = qdisc;
 }
 EXPORT_SYMBOL(qdisc_watchdog_init);
 
-void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires)
+void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires, bool throttle)
 {
 	if (test_bit(__QDISC_STATE_DEACTIVATED,
 		     &qdisc_root_sleeping(wd->qdisc)->state))
 		return;
 
-	qdisc_throttled(wd->qdisc);
+	if (throttle)
+		qdisc_throttled(wd->qdisc);
 
 	hrtimer_start(&wd->timer,
 		      ns_to_ktime(expires),
-		      HRTIMER_MODE_ABS);
+		      HRTIMER_MODE_ABS_PINNED);
 }
 EXPORT_SYMBOL(qdisc_watchdog_schedule_ns);
 
@@ -680,22 +746,29 @@
 	return 0;
 }
 
-void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
+void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n,
+			       unsigned int len)
 {
 	const struct Qdisc_class_ops *cops;
 	unsigned long cl;
 	u32 parentid;
+	int drops;
 
-	if (n == 0)
+	if (n == 0 && len == 0)
 		return;
+	drops = max_t(int, n, 0);
+	rcu_read_lock();
 	while ((parentid = sch->parent)) {
 		if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS))
-			return;
+			break;
 
+		if (sch->flags & TCQ_F_NOPARENT)
+			break;
+		/* TODO: perform the search on a per txq basis */
 		sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid));
 		if (sch == NULL) {
-			WARN_ON(parentid != TC_H_ROOT);
-			return;
+			WARN_ON_ONCE(parentid != TC_H_ROOT);
+			break;
 		}
 		cops = sch->ops->cl_ops;
 		if (cops->qlen_notify) {
@@ -704,9 +777,12 @@
 			cops->put(sch, cl);
 		}
 		sch->q.qlen -= n;
+		sch->qstats.backlog -= len;
+		__qdisc_qstats_drop(sch, drops);
 	}
+	rcu_read_unlock();
 }
-EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
+EXPORT_SYMBOL(qdisc_tree_reduce_backlog);
 
 static void notify_and_destroy(struct net *net, struct sk_buff *skb,
 			       struct nlmsghdr *n, u32 clid,
@@ -884,6 +960,17 @@
 	sch->handle = handle;
 
 	if (!ops->init || (err = ops->init(sch, tca[TCA_OPTIONS])) == 0) {
+		if (qdisc_is_percpu_stats(sch)) {
+			sch->cpu_bstats =
+				netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
+			if (!sch->cpu_bstats)
+				goto err_out4;
+
+			sch->cpu_qstats = alloc_percpu(struct gnet_stats_queue);
+			if (!sch->cpu_qstats)
+				goto err_out4;
+		}
+
 		if (tca[TCA_STAB]) {
 			stab = qdisc_get_stab(tca[TCA_STAB]);
 			if (IS_ERR(stab)) {
@@ -906,8 +993,11 @@
 			else
 				root_lock = qdisc_lock(sch);
 
-			err = gen_new_estimator(&sch->bstats, &sch->rate_est,
-						root_lock, tca[TCA_RATE]);
+			err = gen_new_estimator(&sch->bstats,
+						sch->cpu_bstats,
+						&sch->rate_est,
+						root_lock,
+						tca[TCA_RATE]);
 			if (err)
 				goto err_out4;
 		}
@@ -926,6 +1016,8 @@
 	return NULL;
 
 err_out4:
+	free_percpu(sch->cpu_bstats);
+	free_percpu(sch->cpu_qstats);
 	/*
 	 * Any broken qdiscs that would require a ops->reset() here?
 	 * The qdisc was never in action so it shouldn't be necessary.
@@ -964,9 +1056,11 @@
 		   because change can't be undone. */
 		if (sch->flags & TCQ_F_MQROOT)
 			goto out;
-		gen_replace_estimator(&sch->bstats, &sch->rate_est,
-					    qdisc_root_sleeping_lock(sch),
-					    tca[TCA_RATE]);
+		gen_replace_estimator(&sch->bstats,
+				      sch->cpu_bstats,
+				      &sch->rate_est,
+				      qdisc_root_sleeping_lock(sch),
+				      tca[TCA_RATE]);
 	}
 out:
 	return 0;
@@ -1026,7 +1120,8 @@
 	struct Qdisc *p = NULL;
 	int err;
 
-	if ((n->nlmsg_type != RTM_GETQDISC) && !netlink_capable(skb, CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETQDISC) &&
+	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
@@ -1093,7 +1188,7 @@
 	struct Qdisc *q, *p;
 	int err;
 
-	if (!netlink_capable(skb, CAP_NET_ADMIN))
+	if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
@@ -1240,12 +1335,16 @@
 static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 			 u32 portid, u32 seq, u16 flags, int event)
 {
+	struct gnet_stats_basic_cpu __percpu *cpu_bstats = NULL;
+	struct gnet_stats_queue __percpu *cpu_qstats = NULL;
 	struct tcmsg *tcm;
 	struct nlmsghdr  *nlh;
 	unsigned char *b = skb_tail_pointer(skb);
 	struct gnet_dump d;
 	struct qdisc_size_table *stab;
+	__u32 qlen;
 
+	cond_resched();
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
 	if (!nlh)
 		goto out_nlmsg_trim;
@@ -1261,7 +1360,7 @@
 		goto nla_put_failure;
 	if (q->ops->dump && q->ops->dump(q, skb) < 0)
 		goto nla_put_failure;
-	q->qstats.qlen = q->q.qlen;
+	qlen = q->q.qlen;
 
 	stab = rtnl_dereference(q->stab);
 	if (stab && qdisc_dump_stab(skb, stab) < 0)
@@ -1274,9 +1373,14 @@
 	if (q->ops->dump_stats && q->ops->dump_stats(q, &d) < 0)
 		goto nla_put_failure;
 
-	if (gnet_stats_copy_basic(&d, &q->bstats) < 0 ||
+	if (qdisc_is_percpu_stats(q)) {
+		cpu_bstats = q->cpu_bstats;
+		cpu_qstats = q->cpu_qstats;
+	}
+
+	if (gnet_stats_copy_basic(&d, cpu_bstats, &q->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(&d, &q->bstats, &q->rate_est) < 0 ||
-	    gnet_stats_copy_queue(&d, &q->qstats) < 0)
+	    gnet_stats_copy_queue(&d, cpu_qstats, &q->qstats, qlen) < 0)
 		goto nla_put_failure;
 
 	if (gnet_stats_finish_copy(&d) < 0)
@@ -1377,9 +1481,9 @@
 	s_idx = cb->args[0];
 	s_q_idx = q_idx = cb->args[1];
 
-	rcu_read_lock();
 	idx = 0;
-	for_each_netdev_rcu(net, dev) {
+	ASSERT_RTNL();
+	for_each_netdev(net, dev) {
 		struct netdev_queue *dev_queue;
 
 		if (idx < s_idx)
@@ -1402,8 +1506,6 @@
 	}
 
 done:
-	rcu_read_unlock();
-
 	cb->args[0] = idx;
 	cb->args[1] = q_idx;
 
@@ -1433,7 +1535,8 @@
 	u32 qid;
 	int err;
 
-	if ((n->nlmsg_type != RTM_GETTCLASS) && !netlink_capable(skb, CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETTCLASS) &&
+	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
@@ -1560,6 +1663,7 @@
 	struct gnet_dump d;
 	const struct Qdisc_class_ops *cl_ops = q->ops->cl_ops;
 
+	cond_resched();
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
 	if (!nlh)
 		goto out_nlmsg_trim;
@@ -1715,74 +1819,67 @@
  * to this qdisc, (optionally) tests for protocol and asks
  * specific classifiers.
  */
-int tc_classify_compat(struct sk_buff *skb, const struct tcf_proto *tp,
-		       struct tcf_result *res)
+int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp,
+		struct tcf_result *res, bool compat_mode)
 {
-	__be16 protocol = skb->protocol;
-	int err;
+	__be16 protocol = tc_skb_protocol(skb);
+#ifdef CONFIG_NET_CLS_ACT
+	const struct tcf_proto *old_tp = tp;
+	int limit = 0;
+
+reclassify:
+#endif
+	for (; tp; tp = rcu_dereference_bh(tp->next)) {
+		int err;
 
-	for (; tp; tp = tp->next) {
 		if (tp->protocol != protocol &&
 		    tp->protocol != htons(ETH_P_ALL))
 			continue;
-		err = tp->classify(skb, tp, res);
 
-		if (err >= 0) {
+		err = tp->classify(skb, tp, res);
 #ifdef CONFIG_NET_CLS_ACT
-			if (err != TC_ACT_RECLASSIFY && skb->tc_verd)
-				skb->tc_verd = SET_TC_VERD(skb->tc_verd, 0);
+		if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode))
+			goto reset;
 #endif
+		if (err >= 0)
 			return err;
-		}
 	}
-	return -1;
-}
-EXPORT_SYMBOL(tc_classify_compat);
-
-int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp,
-		struct tcf_result *res)
-{
-	int err = 0;
-#ifdef CONFIG_NET_CLS_ACT
-	const struct tcf_proto *otp = tp;
-reclassify:
-#endif
 
-	err = tc_classify_compat(skb, tp, res);
+	return -1;
 #ifdef CONFIG_NET_CLS_ACT
-	if (err == TC_ACT_RECLASSIFY) {
-		u32 verd = G_TC_VERD(skb->tc_verd);
-		tp = otp;
-
-		if (verd++ >= MAX_REC_LOOP) {
-			net_notice_ratelimited("%s: packet reclassify loop rule prio %u protocol %02x\n",
-					       tp->q->ops->id,
-					       tp->prio & 0xffff,
-					       ntohs(tp->protocol));
-			return TC_ACT_SHOT;
-		}
-		skb->tc_verd = SET_TC_VERD(skb->tc_verd, verd);
-		goto reclassify;
+reset:
+	if (unlikely(limit++ >= MAX_REC_LOOP)) {
+		net_notice_ratelimited("%s: reclassify loop, rule prio %u, protocol %02x\n",
+				       tp->q->ops->id, tp->prio & 0xffff,
+				       ntohs(tp->protocol));
+		return TC_ACT_SHOT;
 	}
+
+	tp = old_tp;
+	protocol = tc_skb_protocol(skb);
+	goto reclassify;
 #endif
-	return err;
 }
 EXPORT_SYMBOL(tc_classify);
 
-void tcf_destroy(struct tcf_proto *tp)
+bool tcf_destroy(struct tcf_proto *tp, bool force)
 {
-	tp->ops->destroy(tp);
-	module_put(tp->ops->owner);
-	kfree(tp);
+	if (tp->ops->destroy(tp, force)) {
+		module_put(tp->ops->owner);
+		kfree_rcu(tp, rcu);
+		return true;
+	}
+
+	return false;
 }
 
-void tcf_destroy_chain(struct tcf_proto **fl)
+void tcf_destroy_chain(struct tcf_proto __rcu **fl)
 {
 	struct tcf_proto *tp;
 
-	while ((tp = *fl) != NULL) {
-		*fl = tp->next;
-		tcf_destroy(tp);
+	while ((tp = rtnl_dereference(*fl)) != NULL) {
+		RCU_INIT_POINTER(*fl, tp->next);
+		tcf_destroy(tp, true);
 	}
 }
 EXPORT_SYMBOL(tcf_destroy_chain);
@@ -1790,13 +1887,10 @@
 #ifdef CONFIG_PROC_FS
 static int psched_show(struct seq_file *seq, void *v)
 {
-	struct timespec ts;
-
-	hrtimer_get_res(CLOCK_MONOTONIC, &ts);
 	seq_printf(seq, "%08x %08x %08x %08x\n",
 		   (u32)NSEC_PER_USEC, (u32)PSCHED_TICKS2NS(1),
 		   1000000,
-		   (u32)NSEC_PER_SEC/(u32)ktime_to_ns(timespec_to_ktime(ts)));
+		   (u32)NSEC_PER_SEC / hrtimer_resolution);
 
 	return 0;
 }
@@ -1856,10 +1950,12 @@
 		return err;
 	}
 
+	register_qdisc(&fq_codel_qdisc_ops);
 	register_qdisc(&pfifo_qdisc_ops);
 	register_qdisc(&bfifo_qdisc_ops);
 	register_qdisc(&pfifo_head_drop_qdisc_ops);
 	register_qdisc(&mq_qdisc_ops);
+	register_qdisc(&noqueue_qdisc_ops);
 
 	rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL, NULL);
 	rtnl_register(PF_UNSPEC, RTM_DELQDISC, tc_get_qdisc, NULL, NULL);