net/sched: Introduce tc block netdev tracking infra

This commit makes tc blocks track which ports have been added to them.
And, with that, we'll be able to use this new information to send
packets to the block's ports. Which will be done in the patch #3 of this
series.

Suggested-by: Jiri Pirko <jiri@nvidia.com>
Co-developed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Co-developed-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Author: vbnogueira

include/net/sch_generic.h

@@ -19,6 +19,7 @@
 #include <net/gen_stats.h>
 #include <net/rtnetlink.h>
 #include <net/flow_offload.h>
+#include <linux/xarray.h>
 
 struct Qdisc_ops;
 struct qdisc_walker;
@@ -456,6 +457,7 @@ struct tcf_chain {
 };
 
 struct tcf_block {
+	struct xarray ports; /* datapath accessible */
 	/* Lock protects tcf_block and lifetime-management data of chains
 	 * attached to the block (refcnt, action_refcnt, explicitly_created).
 	 */

net/sched/cls_api.c

@@ -531,6 +531,7 @@ static void tcf_block_destroy(struct tcf_block *block)
 {
 	mutex_destroy(&block->lock);
 	mutex_destroy(&block->proto_destroy_lock);
+	xa_destroy(&block->ports);
 	kfree_rcu(block, rcu);
 }
 
@@ -1002,6 +1003,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
 	refcount_set(&block->refcnt, 1);
 	block->net = net;
 	block->index = block_index;
+	xa_init(&block->ports);
 
 	/* Don't store q pointer for blocks which are shared */
 	if (!tcf_block_shared(block))

net/sched/sch_api.c

@@ -1180,6 +1180,43 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 	return 0;
 }
 
+static int qdisc_block_add_dev(struct Qdisc *sch, struct net_device *dev,
+			       struct netlink_ext_ack *extack)
+{
+	const struct Qdisc_class_ops *cl_ops = sch->ops->cl_ops;
+	struct tcf_block *block;
+	int err;
+
+	block = cl_ops->tcf_block(sch, TC_H_MIN_INGRESS, NULL);
+	if (block) {
+		err = xa_insert(&block->ports, dev->ifindex, dev, GFP_KERNEL);
+		if (err) {
+			NL_SET_ERR_MSG(extack,
+				       "ingress block dev insert failed");
+			return err;
+		}
+	}
+
+	block = cl_ops->tcf_block(sch, TC_H_MIN_EGRESS, NULL);
+	if (block) {
+		err = xa_insert(&block->ports, dev->ifindex, dev, GFP_KERNEL);
+		if (err) {
+			NL_SET_ERR_MSG(extack,
+				       "Egress block dev insert failed");
+			goto err_out;
+		}
+	}
+
+	return 0;
+
+err_out:
+	block = cl_ops->tcf_block(sch, TC_H_MIN_INGRESS, NULL);
+	if (block)
+		xa_erase(&block->ports, dev->ifindex);
+
+	return err;
+}
+
 static int qdisc_block_indexes_set(struct Qdisc *sch, struct nlattr **tca,
 				   struct netlink_ext_ack *extack)
 {
@@ -1350,6 +1387,10 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
 	qdisc_hash_add(sch, false);
 	trace_qdisc_create(ops, dev, parent);
 
+	err = qdisc_block_add_dev(sch, dev, extack);
+	if (err)
+		goto err_out4;
+
 	return sch;
 
 err_out4:

net/sched/sch_generic.c

@@ -1051,6 +1051,9 @@ static void qdisc_free_cb(struct rcu_head *head)
 static void __qdisc_destroy(struct Qdisc *qdisc)
 {
 	const struct Qdisc_ops  *ops = qdisc->ops;
+	struct net_device *dev = qdisc_dev(qdisc);
+	const struct Qdisc_class_ops *cops;
+	struct tcf_block *block;
 
 #ifdef CONFIG_NET_SCHED
 	qdisc_hash_del(qdisc);
@@ -1061,11 +1064,24 @@ static void __qdisc_destroy(struct Qdisc *qdisc)
 
 	qdisc_reset(qdisc);
 
+	cops = ops->cl_ops;
+	if (ops->ingress_block_get) {
+		block = cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL);
+		if (block)
+			xa_erase(&block->ports, dev->ifindex);
+	}
+
+	if (ops->egress_block_get) {
+		block = cops->tcf_block(qdisc, TC_H_MIN_EGRESS, NULL);
+		if (block)
+			xa_erase(&block->ports, dev->ifindex);
+	}
+
 	if (ops->destroy)
 		ops->destroy(qdisc);
 
 	module_put(ops->owner);
-	netdev_put(qdisc_dev(qdisc), &qdisc->dev_tracker);
+	netdev_put(dev, &qdisc->dev_tracker);
 
 	trace_qdisc_destroy(qdisc);