[PATCH v1 net-next 0/2] net: tc: dsa: Implement offload of matchall for bridged DSA ports

[PATCH v1 net-next 0/2] net: tc: dsa: Implement offload of matchall for bridged DSA ports

[Mattias Forsblad]

Greetings,

This series implements offloading of tc matchall filter to HW
for bridged DSA ports.

Background
When using a non-VLAN filtering bridge we want to be able to drop
traffic directed to the CPU port so that the CPU doesn't get unnecessary loaded.
This is specially important when we have disabled learning on user ports.

A sample configuration could be something like this:

       br0
      /   \
   swp0   swp1

ip link add dev br0 type bridge stp_state 0 vlan_filtering 0
ip link set swp0 master br0
ip link set swp1 master br0
ip link set swp0 type bridge_slave learning off
ip link set swp1 type bridge_slave learning off
ip link set swp0 up
ip link set swp1 up
ip link set br0 up

After discussions here: https://lore.kernel.org/netdev/YjMo9xyoycXgSWXS@shredder/
it was advised to use tc to set an ingress filter that could then
be offloaded to HW, like so:

tc qdisc add dev br0 clsact
tc filter add dev br0 ingress pref 1 proto all matchall action drop

Limitations
If there is tc rules on a bridge and all the ports leave the bridge
and then joins the bridge again, the indirect framwork doesn't seem
to reoffload them at join. The tc rules need to be torn down and
re-added.

The first part of this serie uses the flow indirect framework to
setup monitoring of tc qdisc and filters added to a bridge.
The second part offloads the matchall filter to HW for Marvell
switches.

RFC -> v1: Monitor bridge join/leave and re-evaluate offloading (Vladimir Oltean)

Mattias Forsblad (2):
  net: tc: dsa: Add the matchall filter with drop action for bridged DSA
    ports.
  net: dsa: Implement tc offloading for drop target.

 drivers/net/dsa/mv88e6xxx/chip.c |  23 +++-
 include/net/dsa.h                |  14 ++
 net/dsa/dsa2.c                   |   5 +
 net/dsa/dsa_priv.h               |   3 +
 net/dsa/port.c                   |   2 +
 net/dsa/slave.c                  | 221 ++++++++++++++++++++++++++++++-
 6 files changed, 264 insertions(+), 4 deletions(-)

-- 
2.25.1

[PATCH v1 net-next 1/2] net: tc: dsa: Add the matchall filter with drop action for bridged DSA ports.

[Mattias Forsblad]

Use the flow indirect framework on bridged DSA ports to be
able to set up offloading of matchall filter with drop target.

Signed-off-by: Mattias Forsblad <mattias.forsblad@gmail.com>
---
 include/net/dsa.h  |  14 +++
 net/dsa/dsa2.c     |   5 +
 net/dsa/dsa_priv.h |   3 +
 net/dsa/port.c     |   2 +
 net/dsa/slave.c    | 221 ++++++++++++++++++++++++++++++++++++++++++++-
 5 files changed, 242 insertions(+), 3 deletions(-)

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 934958fda962..0ddfce552002 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -171,6 +171,9 @@ struct dsa_switch_tree {
 
 	/* Track the largest switch index within a tree */
 	unsigned int last_switch;
+
+	/* For tc indirect bookkeeping */
+	struct list_head tc_indr_block_list;
 };
 
 /* LAG IDs are one-based, the dst->lags array is zero-based */
@@ -212,6 +215,7 @@ static inline int dsa_lag_id(struct dsa_switch_tree *dst,
 enum dsa_port_mall_action_type {
 	DSA_PORT_MALL_MIRROR,
 	DSA_PORT_MALL_POLICER,
+	DSA_PORT_MALL_DROP,
 };
 
 /* TC mirroring entry */
@@ -220,6 +224,11 @@ struct dsa_mall_mirror_tc_entry {
 	bool ingress;
 };
 
+/* TC drop entry */
+struct dsa_mall_drop_tc_entry {
+	bool enable;
+};
+
 /* TC port policer entry */
 struct dsa_mall_policer_tc_entry {
 	u32 burst;
@@ -234,6 +243,7 @@ struct dsa_mall_tc_entry {
 	union {
 		struct dsa_mall_mirror_tc_entry mirror;
 		struct dsa_mall_policer_tc_entry policer;
+		struct dsa_mall_drop_tc_entry drop;
 	};
 };
 
@@ -241,6 +251,8 @@ struct dsa_bridge {
 	struct net_device *dev;
 	unsigned int num;
 	bool tx_fwd_offload;
+	u8 local_rcv:1;
+	u8 local_rcv_effective:1;
 	refcount_t refcount;
 };
 
@@ -1034,6 +1046,8 @@ struct dsa_switch_ops {
 	int	(*port_policer_add)(struct dsa_switch *ds, int port,
 				    struct dsa_mall_policer_tc_entry *policer);
 	void	(*port_policer_del)(struct dsa_switch *ds, int port);
+	int	(*bridge_local_rcv)(struct dsa_switch *ds, int port,
+				    struct dsa_mall_drop_tc_entry *drop);
 	int	(*port_setup_tc)(struct dsa_switch *ds, int port,
 				 enum tc_setup_type type, void *type_data);
 
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index ca6af86964bc..e87ceb841a70 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -247,6 +247,9 @@ static struct dsa_switch_tree *dsa_tree_alloc(int index)
 	INIT_LIST_HEAD(&dst->list);
 	list_add_tail(&dst->list, &dsa_tree_list);
 
+	INIT_LIST_HEAD(&dst->tc_indr_block_list);
+	dsa_setup_bridge_tc_indr(dst);
+
 	kref_init(&dst->refcount);
 
 	return dst;
@@ -254,6 +257,8 @@ static struct dsa_switch_tree *dsa_tree_alloc(int index)
 
 static void dsa_tree_free(struct dsa_switch_tree *dst)
 {
+	dsa_cleanup_bridge_tc_indr(dst);
+
 	if (dst->tag_ops)
 		dsa_tag_driver_put(dst->tag_ops);
 	list_del(&dst->list);
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 5d3f4a67dce1..456bcbe730ba 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -320,6 +320,9 @@ void dsa_slave_setup_tagger(struct net_device *slave);
 int dsa_slave_change_mtu(struct net_device *dev, int new_mtu);
 int dsa_slave_manage_vlan_filtering(struct net_device *dev,
 				    bool vlan_filtering);
+int dsa_setup_bridge_tc_indr(struct dsa_switch_tree *dst);
+void dsa_cleanup_bridge_tc_indr(struct dsa_switch_tree *dst);
+bool dsa_slave_dev_check(const struct net_device *dev);
 
 static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev)
 {
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 32d472a82241..0c4522cc9eae 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -361,6 +361,8 @@ static int dsa_port_bridge_create(struct dsa_port *dp,
 	refcount_set(&bridge->refcount, 1);
 
 	bridge->dev = br;
+	bridge->local_rcv = 1;
+	bridge->local_rcv_effective = 1;
 
 	bridge->num = dsa_bridge_num_get(br, ds->max_num_bridges);
 	if (ds->max_num_bridges && !bridge->num) {
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 41c69a6e7854..596d377c3ff8 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1246,6 +1246,67 @@ dsa_slave_add_cls_matchall_mirred(struct net_device *dev,
 	return err;
 }
 
+static int dsa_slave_bridge_foreign_if_check(struct net_device *dev,
+					     struct dsa_mall_drop_tc_entry *drop)
+{
+	struct net_device *lower_dev;
+	struct dsa_port *dp = NULL;
+	bool foreign_if = false;
+	struct list_head *iter;
+
+	/* Check port types in this bridge */
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		if (dsa_slave_dev_check(lower_dev))
+			dp = dsa_slave_to_port(lower_dev);
+		else
+			foreign_if = true;
+	}
+
+	/* Offload only if we have requested it and the bridge only
+	 * contains dsa ports
+	 */
+	if (!dp || !dp->bridge)
+		return 0;
+
+	if (!foreign_if)
+		dp->bridge->local_rcv_effective = dp->bridge->local_rcv;
+	else
+		dp->bridge->local_rcv_effective = 1;
+
+	return dp->ds->ops->bridge_local_rcv(dp->ds, dp->index, drop);
+}
+
+static int
+dsa_slave_add_cls_matchall_drop(struct net_device *dev,
+				struct tc_cls_matchall_offload *cls,
+				bool ingress)
+{
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_mall_tc_entry *mall_tc_entry;
+	struct dsa_mall_drop_tc_entry *drop;
+	struct dsa_switch *ds = dp->ds;
+	int err;
+
+	if (!ds->ops->bridge_local_rcv)
+		return -EOPNOTSUPP;
+
+	mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL);
+	if (!mall_tc_entry)
+		return -ENOMEM;
+
+	mall_tc_entry->cookie = cls->cookie;
+	mall_tc_entry->type = DSA_PORT_MALL_DROP;
+	drop = &mall_tc_entry->drop;
+	drop->enable = true;
+	dp->bridge->local_rcv = 0;
+	dsa_slave_bridge_foreign_if_check(dp->bridge->dev, drop);
+
+	list_add_tail(&mall_tc_entry->list, &p->mall_tc_list);
+
+	return err;
+}
+
 static int
 dsa_slave_add_cls_matchall_police(struct net_device *dev,
 				  struct tc_cls_matchall_offload *cls,
@@ -1320,6 +1381,9 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev,
 	else if (flow_offload_has_one_action(&cls->rule->action) &&
 		 cls->rule->action.entries[0].id == FLOW_ACTION_POLICE)
 		err = dsa_slave_add_cls_matchall_police(dev, cls, ingress);
+	else if (flow_offload_has_one_action(&cls->rule->action) &&
+		 cls->rule->action.entries[0].id == FLOW_ACTION_DROP)
+		err = dsa_slave_add_cls_matchall_drop(dev, cls, ingress);
 
 	return err;
 }
@@ -1347,6 +1411,13 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev,
 		if (ds->ops->port_policer_del)
 			ds->ops->port_policer_del(ds, dp->index);
 		break;
+	case DSA_PORT_MALL_DROP:
+		if (!dp->bridge)
+			return;
+		dp->bridge->local_rcv = 1;
+		mall_tc_entry->drop.enable = false;
+		dsa_slave_bridge_foreign_if_check(dp->bridge->dev, &mall_tc_entry->drop);
+		break;
 	default:
 		WARN_ON(1);
 	}
@@ -1430,7 +1501,8 @@ static int dsa_slave_setup_tc_cls_flower(struct net_device *dev,
 	}
 }
 
-static int dsa_slave_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+static int dsa_slave_setup_tc_block_cb(enum tc_setup_type type,
+				       void *cls,
 				       void *cb_priv, bool ingress)
 {
 	struct net_device *dev = cb_priv;
@@ -1440,9 +1512,9 @@ static int dsa_slave_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 
 	switch (type) {
 	case TC_SETUP_CLSMATCHALL:
-		return dsa_slave_setup_tc_cls_matchall(dev, type_data, ingress);
+		return dsa_slave_setup_tc_cls_matchall(dev, cls, ingress);
 	case TC_SETUP_CLSFLOWER:
-		return dsa_slave_setup_tc_cls_flower(dev, type_data, ingress);
+		return dsa_slave_setup_tc_cls_flower(dev, cls, ingress);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1514,6 +1586,133 @@ static int dsa_slave_setup_ft_block(struct dsa_switch *ds, int port,
 	return master->netdev_ops->ndo_setup_tc(master, TC_SETUP_FT, type_data);
 }
 
+static LIST_HEAD(dsa_slave_block_indr_cb_list);
+
+struct dsa_slave_indr_block_cb_priv {
+	struct dsa_switch_tree *dst;
+	struct net_device *bridge;
+	struct list_head list;
+};
+
+static int dsa_slave_setup_bridge_block_cb(enum tc_setup_type type,
+					   void *type_data,
+					   void *cb_priv)
+{
+	struct dsa_slave_indr_block_cb_priv *priv = cb_priv;
+	struct tc_cls_matchall_offload *cls;
+	struct dsa_port *dp;
+	int ret = 0;
+
+	cls = (struct tc_cls_matchall_offload *)type_data;
+	list_for_each_entry(dp, &priv->dst->ports, list) {
+		if (!dp->bridge || !dp->slave)
+			continue;
+
+		if (dp->bridge->dev != priv->bridge)
+			continue;
+
+		ret += dsa_slave_setup_tc_block_cb(type, cls, dp->slave, true);
+	}
+
+	return ret;
+}
+
+static struct dsa_slave_indr_block_cb_priv *
+dsa_slave_tc_indr_block_cb_lookup(struct dsa_switch_tree *dst, struct net_device *netdev)
+{
+	struct dsa_slave_indr_block_cb_priv *cb_priv;
+
+	list_for_each_entry(cb_priv, &dst->tc_indr_block_list, list)
+		if (cb_priv->bridge == netdev)
+			return cb_priv;
+
+	return NULL;
+}
+
+static void dsa_slave_setup_tc_indr_rel(void *cb_priv)
+{
+	struct dsa_slave_indr_block_cb_priv *priv = cb_priv;
+
+	list_del(&priv->list);
+	kfree(priv);
+}
+
+static int
+dsa_slave_setup_bridge_tc_indr_block(struct net_device *netdev, struct Qdisc *sch,
+				     struct dsa_switch_tree *dst,
+				     struct flow_block_offload *f, void *data,
+				     void (*cleanup)(struct flow_block_cb *block_cb))
+{
+	struct dsa_slave_indr_block_cb_priv *cb_priv;
+	struct flow_block_cb *block_cb;
+
+	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case FLOW_BLOCK_BIND:
+		cb_priv = kmalloc(sizeof(*cb_priv), GFP_KERNEL);
+		if (!cb_priv)
+			return -ENOMEM;
+
+		cb_priv->bridge = netdev;
+		cb_priv->dst = dst;
+		list_add(&cb_priv->list, &dst->tc_indr_block_list);
+
+		block_cb = flow_indr_block_cb_alloc(dsa_slave_setup_bridge_block_cb,
+						    cb_priv, cb_priv,
+						    dsa_slave_setup_tc_indr_rel, f,
+						    netdev, sch, data, cb_priv, cleanup);
+		if (IS_ERR(block_cb)) {
+			list_del(&cb_priv->list);
+			kfree(cb_priv);
+			return PTR_ERR(block_cb);
+		}
+
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &dsa_slave_block_indr_cb_list);
+		break;
+	case FLOW_BLOCK_UNBIND:
+		cb_priv = dsa_slave_tc_indr_block_cb_lookup(dst, netdev);
+		if (!cb_priv)
+			return -ENOENT;
+
+		block_cb = flow_block_cb_lookup(f->block,
+						dsa_slave_setup_bridge_block_cb,
+						cb_priv);
+		if (!block_cb)
+			return -ENOENT;
+
+		flow_indr_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int dsa_slave_setup_bridge_tc_indr_cb(struct net_device *netdev, struct Qdisc *sch,
+					     void *cb_priv,
+					     enum tc_setup_type type, void *type_data,
+					     void *data,
+					     void (*cleanup)(struct flow_block_cb *block_cb))
+{
+	if (!netdev || !netif_is_bridge_master(netdev))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return dsa_slave_setup_bridge_tc_indr_block(netdev, sch, cb_priv,
+						     type_data, data, cleanup);
+	default:
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
 static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			      void *type_data)
 {
@@ -1535,6 +1734,17 @@ static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	return ds->ops->port_setup_tc(ds, dp->index, type, type_data);
 }
 
+int dsa_setup_bridge_tc_indr(struct dsa_switch_tree *dst)
+{
+	return flow_indr_dev_register(dsa_slave_setup_bridge_tc_indr_cb, dst);
+}
+
+void dsa_cleanup_bridge_tc_indr(struct dsa_switch_tree *dst)
+{
+	flow_indr_dev_unregister(dsa_slave_setup_bridge_tc_indr_cb,
+				 dst, dsa_slave_setup_tc_indr_rel);
+}
+
 static int dsa_slave_get_rxnfc(struct net_device *dev,
 			       struct ethtool_rxnfc *nfc, u32 *rule_locs)
 {
@@ -2718,6 +2928,11 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb,
 		break;
 	}
 	case NETDEV_CHANGEUPPER:
+		struct netdev_notifier_changeupper_info *info = ptr;
+
+		if (netif_is_bridge_master(info->upper_dev))
+			dsa_slave_bridge_foreign_if_check(info->upper_dev, NULL);
+
 		if (dsa_slave_dev_check(dev))
 			return dsa_slave_changeupper(dev, ptr);
 
-- 
2.25.1

[PATCH v1 net-next 2/2] net: dsa: Implement tc offloading for drop target.

[Mattias Forsblad]

Add the ability to handle tc matchall drop HW offloading for Marvell
switches.

Signed-off-by: Mattias Forsblad <mattias.forsblad@gmail.com>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 64f4fdd02902..84e319520d36 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -1436,7 +1436,7 @@ static u16 mv88e6xxx_port_vlan(struct mv88e6xxx_chip *chip, int dev, int port)
 	 * bridge group.
 	 */
 	dsa_switch_for_each_port(other_dp, ds)
-		if (other_dp->type == DSA_PORT_TYPE_CPU ||
+		if ((other_dp->type == DSA_PORT_TYPE_CPU && dp->bridge->local_rcv_effective) ||
 		    other_dp->type == DSA_PORT_TYPE_DSA ||
 		    dsa_port_bridge_same(dp, other_dp))
 			pvlan |= BIT(other_dp->index);
@@ -6439,6 +6439,26 @@ static void mv88e6xxx_port_mirror_del(struct dsa_switch *ds, int port,
 	mutex_unlock(&chip->reg_lock);
 }
 
+static int mv88e6xxx_bridge_local_rcv(struct dsa_switch *ds, int port,
+				      struct dsa_mall_drop_tc_entry *drop)
+{
+	struct mv88e6xxx_chip *chip = ds->priv;
+	struct dsa_port *dp;
+	int err;
+
+	dp = dsa_to_port(ds, port);
+	if (!dp)
+		return -EINVAL;
+
+	mutex_lock(&chip->reg_lock);
+
+	err = mv88e6xxx_bridge_map(chip, *dp->bridge);
+
+	mutex_unlock(&chip->reg_lock);
+
+	return err;
+}
+
 static int mv88e6xxx_port_pre_bridge_flags(struct dsa_switch *ds, int port,
 					   struct switchdev_brport_flags flags,
 					   struct netlink_ext_ack *extack)
@@ -6837,6 +6857,7 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = {
 	.port_mdb_del           = mv88e6xxx_port_mdb_del,
 	.port_mirror_add	= mv88e6xxx_port_mirror_add,
 	.port_mirror_del	= mv88e6xxx_port_mirror_del,
+	.bridge_local_rcv	= mv88e6xxx_bridge_local_rcv,
 	.crosschip_bridge_join	= mv88e6xxx_crosschip_bridge_join,
 	.crosschip_bridge_leave	= mv88e6xxx_crosschip_bridge_leave,
 	.port_hwtstamp_set	= mv88e6xxx_port_hwtstamp_set,
-- 
2.25.1

Re: [PATCH v1 net-next 1/2] net: tc: dsa: Add the matchall filter with drop action for bridged DSA ports.

[Jakub Kicinski]

On Fri,  1 Apr 2022 12:04:17 +0200 Mattias Forsblad wrote:
>  	case NETDEV_CHANGEUPPER:
> +		struct netdev_notifier_changeupper_info *info = ptr;

I don't think C99 has been enabled, yet? You can't declare variables
like this. Please fix and repost on Monday when net-next is actually
opened.