Merge branch 'dsa-changes-for-multiple-cpu-ports-part-1'

Vladimir Oltean says:

====================
DSA changes for multiple CPU ports (part 1)

I am trying to enable the second internal port pair from the NXP LS1028A
Felix switch for DSA-tagged traffic via "ocelot-8021q". This series
represents part 1 (of an unknown number) of that effort.

It does some preparation work, like managing host flooding in DSA via a
dedicated method, and removing the CPU port as argument from the tagging
protocol change procedure.

In terms of driver-specific changes, it reworks the 2 tag protocol
implementations in the Felix driver to have a structured data format.
It enables host flooding towards all tag_8021q CPU ports. It dynamically
updates the tag_8021q CPU port used for traps. It also fixes a bug
introduced by a previous refactoring/oversimplification commit in
net-next.
====================

Link: https://lore.kernel.org/r/20220511095020.562461-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/dsa/mv88e6xxx/chip.c

@@ -6329,11 +6329,12 @@ static enum dsa_tag_protocol mv88e6xxx_get_tag_protocol(struct dsa_switch *ds,
 	return chip->tag_protocol;
 }
 
-static int mv88e6xxx_change_tag_protocol(struct dsa_switch *ds, int port,
+static int mv88e6xxx_change_tag_protocol(struct dsa_switch *ds,
 					 enum dsa_tag_protocol proto)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
 	enum dsa_tag_protocol old_protocol;
+	struct dsa_port *cpu_dp;
 	int err;
 
 	switch (proto) {
@@ -6358,11 +6359,24 @@ static int mv88e6xxx_change_tag_protocol(struct dsa_switch *ds, int port,
 	chip->tag_protocol = proto;
 
 	mv88e6xxx_reg_lock(chip);
-	err = mv88e6xxx_setup_port_mode(chip, port);
+	dsa_switch_for_each_cpu_port(cpu_dp, ds) {
+		err = mv88e6xxx_setup_port_mode(chip, cpu_dp->index);
+		if (err) {
+			mv88e6xxx_reg_unlock(chip);
+			goto unwind;
+		}
+	}
 	mv88e6xxx_reg_unlock(chip);
 
-	if (err)
+	return 0;
-		chip->tag_protocol = old_protocol;
+
+unwind:
+	chip->tag_protocol = old_protocol;
+
+	mv88e6xxx_reg_lock(chip);
+	dsa_switch_for_each_cpu_port_continue_reverse(cpu_dp, ds)
+		mv88e6xxx_setup_port_mode(chip, cpu_dp->index);
+	mv88e6xxx_reg_unlock(chip);
 
 	return err;
 }

drivers/net/dsa/ocelot/felix.c

@@ -42,43 +42,6 @@ static struct net_device *felix_classify_db(struct dsa_db db)
 	}
 }
 
-static void felix_migrate_pgid_bit(struct dsa_switch *ds, int from, int to,
-				   int pgid)
-{
-	struct ocelot *ocelot = ds->priv;
-	bool on;
-	u32 val;
-
-	val = ocelot_read_rix(ocelot, ANA_PGID_PGID, pgid);
-	on = !!(val & BIT(from));
-	val &= ~BIT(from);
-	if (on)
-		val |= BIT(to);
-	else
-		val &= ~BIT(to);
-
-	ocelot_write_rix(ocelot, val, ANA_PGID_PGID, pgid);
-}
-
-static void felix_migrate_flood_to_npi_port(struct dsa_switch *ds, int port)
-{
-	struct ocelot *ocelot = ds->priv;
-
-	felix_migrate_pgid_bit(ds, port, ocelot->num_phys_ports, PGID_UC);
-	felix_migrate_pgid_bit(ds, port, ocelot->num_phys_ports, PGID_MC);
-	felix_migrate_pgid_bit(ds, port, ocelot->num_phys_ports, PGID_BC);
-}
-
-static void
-felix_migrate_flood_to_tag_8021q_port(struct dsa_switch *ds, int port)
-{
-	struct ocelot *ocelot = ds->priv;
-
-	felix_migrate_pgid_bit(ds, ocelot->num_phys_ports, port, PGID_UC);
-	felix_migrate_pgid_bit(ds, ocelot->num_phys_ports, port, PGID_MC);
-	felix_migrate_pgid_bit(ds, ocelot->num_phys_ports, port, PGID_BC);
-}
-
 /* Set up VCAP ES0 rules for pushing a tag_8021q VLAN towards the CPU such that
  * the tagger can perform RX source port identification.
  */
@@ -313,6 +276,21 @@ static void felix_8021q_cpu_port_deinit(struct ocelot *ocelot, int port)
 	mutex_unlock(&ocelot->fwd_domain_lock);
 }
 
+static int felix_trap_get_cpu_port(struct dsa_switch *ds,
+				   const struct ocelot_vcap_filter *trap)
+{
+	struct dsa_port *dp;
+	int first_port;
+
+	if (WARN_ON(!trap->ingress_port_mask))
+		return -1;
+
+	first_port = __ffs(trap->ingress_port_mask);
+	dp = dsa_to_port(ds, first_port);
+
+	return dp->cpu_dp->index;
+}
+
 /* On switches with no extraction IRQ wired, trapped packets need to be
  * replicated over Ethernet as well, otherwise we'd get no notification of
  * their arrival when using the ocelot-8021q tagging protocol.
@@ -326,19 +304,12 @@ static int felix_update_trapping_destinations(struct dsa_switch *ds,
 	struct ocelot_vcap_filter *trap;
 	enum ocelot_mask_mode mask_mode;
 	unsigned long port_mask;
-	struct dsa_port *dp;
 	bool cpu_copy_ena;
-	int cpu = -1, err;
+	int err;
 
 	if (!felix->info->quirk_no_xtr_irq)
 		return 0;
 
-	/* Figure out the current CPU port */
-	dsa_switch_for_each_cpu_port(dp, ds) {
-		cpu = dp->index;
-		break;
-	}
-
 	/* We are sure that "cpu" was found, otherwise
 	 * dsa_tree_setup_default_cpu() would have failed earlier.
 	 */
@@ -356,7 +327,7 @@ static int felix_update_trapping_destinations(struct dsa_switch *ds,
 			 * port module.
 			 */
 			mask_mode = OCELOT_MASK_MODE_REDIRECT;
-			port_mask = BIT(cpu);
+			port_mask = BIT(felix_trap_get_cpu_port(ds, trap));
 			cpu_copy_ena = !!trap->take_ts;
 		} else {
 			/* Trap packets only to the CPU port module, which is
@@ -384,90 +355,6 @@ static int felix_update_trapping_destinations(struct dsa_switch *ds,
 	return 0;
 }
 
-static int felix_setup_tag_8021q(struct dsa_switch *ds, int cpu)
-{
-	struct ocelot *ocelot = ds->priv;
-	struct dsa_port *dp;
-	int err;
-
-	felix_8021q_cpu_port_init(ocelot, cpu);
-
-	dsa_switch_for_each_available_port(dp, ds) {
-		/* This overwrites ocelot_init():
-		 * Do not forward BPDU frames to the CPU port module,
-		 * for 2 reasons:
-		 * - When these packets are injected from the tag_8021q
-		 *   CPU port, we want them to go out, not loop back
-		 *   into the system.
-		 * - STP traffic ingressing on a user port should go to
-		 *   the tag_8021q CPU port, not to the hardware CPU
-		 *   port module.
-		 */
-		ocelot_write_gix(ocelot,
-				 ANA_PORT_CPU_FWD_BPDU_CFG_BPDU_REDIR_ENA(0),
-				 ANA_PORT_CPU_FWD_BPDU_CFG, dp->index);
-	}
-
-	err = dsa_tag_8021q_register(ds, htons(ETH_P_8021AD));
-	if (err)
-		return err;
-
-	err = ocelot_migrate_mdbs(ocelot, BIT(ocelot->num_phys_ports),
-				  BIT(cpu));
-	if (err)
-		goto out_tag_8021q_unregister;
-
-	felix_migrate_flood_to_tag_8021q_port(ds, cpu);
-
-	err = felix_update_trapping_destinations(ds, true);
-	if (err)
-		goto out_migrate_flood;
-
-	/* The ownership of the CPU port module's queues might have just been
-	 * transferred to the tag_8021q tagger from the NPI-based tagger.
-	 * So there might still be all sorts of crap in the queues. On the
-	 * other hand, the MMIO-based matching of PTP frames is very brittle,
-	 * so we need to be careful that there are no extra frames to be
-	 * dequeued over MMIO, since we would never know to discard them.
-	 */
-	ocelot_drain_cpu_queue(ocelot, 0);
-
-	return 0;
-
-out_migrate_flood:
-	felix_migrate_flood_to_npi_port(ds, cpu);
-	ocelot_migrate_mdbs(ocelot, BIT(cpu), BIT(ocelot->num_phys_ports));
-out_tag_8021q_unregister:
-	dsa_tag_8021q_unregister(ds);
-	return err;
-}
-
-static void felix_teardown_tag_8021q(struct dsa_switch *ds, int cpu)
-{
-	struct ocelot *ocelot = ds->priv;
-	struct dsa_port *dp;
-	int err;
-
-	err = felix_update_trapping_destinations(ds, false);
-	if (err)
-		dev_err(ds->dev, "felix_teardown_mmio_filtering returned %d",
-			err);
-
-	dsa_tag_8021q_unregister(ds);
-
-	dsa_switch_for_each_available_port(dp, ds) {
-		/* Restore the logic from ocelot_init:
-		 * do not forward BPDU frames to the front ports.
-		 */
-		ocelot_write_gix(ocelot,
-				 ANA_PORT_CPU_FWD_BPDU_CFG_BPDU_REDIR_ENA(0xffff),
-				 ANA_PORT_CPU_FWD_BPDU_CFG,
-				 dp->index);
-	}
-
-	felix_8021q_cpu_port_deinit(ocelot, cpu);
-}
-
 /* The CPU port module is connected to the Node Processor Interface (NPI). This
  * is the mode through which frames can be injected from and extracted to an
  * external CPU, over Ethernet. In NXP SoCs, the "external CPU" is the ARM CPU
@@ -511,117 +398,249 @@ static void felix_npi_port_deinit(struct ocelot *ocelot, int port)
 	ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, 1);
 }
 
-static int felix_setup_tag_npi(struct dsa_switch *ds, int cpu)
+static int felix_tag_npi_setup(struct dsa_switch *ds)
 {
+	struct dsa_port *dp, *first_cpu_dp = NULL;
 	struct ocelot *ocelot = ds->priv;
-	int err;
 
-	err = ocelot_migrate_mdbs(ocelot, BIT(cpu),
+	dsa_switch_for_each_user_port(dp, ds) {
-				  BIT(ocelot->num_phys_ports));
+		if (first_cpu_dp && dp->cpu_dp != first_cpu_dp) {
-	if (err)
+			dev_err(ds->dev, "Multiple NPI ports not supported\n");
-		return err;
+			return -EINVAL;
+		}
 
-	felix_migrate_flood_to_npi_port(ds, cpu);
+		first_cpu_dp = dp->cpu_dp;
+	}
 
-	felix_npi_port_init(ocelot, cpu);
+	if (!first_cpu_dp)
+		return -EINVAL;
+
+	felix_npi_port_init(ocelot, first_cpu_dp->index);
 
 	return 0;
 }
 
-static void felix_teardown_tag_npi(struct dsa_switch *ds, int cpu)
+static void felix_tag_npi_teardown(struct dsa_switch *ds)
 {
 	struct ocelot *ocelot = ds->priv;
 
-	felix_npi_port_deinit(ocelot, cpu);
+	felix_npi_port_deinit(ocelot, ocelot->npi);
 }
 
-static int felix_set_tag_protocol(struct dsa_switch *ds, int cpu,
+static unsigned long felix_tag_npi_get_host_fwd_mask(struct dsa_switch *ds)
-				  enum dsa_tag_protocol proto)
 {
+	struct ocelot *ocelot = ds->priv;
+
+	return BIT(ocelot->num_phys_ports);
+}
+
+static const struct felix_tag_proto_ops felix_tag_npi_proto_ops = {
+	.setup			= felix_tag_npi_setup,
+	.teardown		= felix_tag_npi_teardown,
+	.get_host_fwd_mask	= felix_tag_npi_get_host_fwd_mask,
+};
+
+static int felix_tag_8021q_setup(struct dsa_switch *ds)
+{
+	struct ocelot *ocelot = ds->priv;
+	struct dsa_port *dp, *cpu_dp;
 	int err;
 
-	switch (proto) {
+	err = dsa_tag_8021q_register(ds, htons(ETH_P_8021AD));
-	case DSA_TAG_PROTO_SEVILLE:
+	if (err)
-	case DSA_TAG_PROTO_OCELOT:
+		return err;
-		err = felix_setup_tag_npi(ds, cpu);
+
+	dsa_switch_for_each_cpu_port(cpu_dp, ds) {
+		felix_8021q_cpu_port_init(ocelot, cpu_dp->index);
+
+		/* TODO we could support multiple CPU ports in tag_8021q mode */
 		break;
-	case DSA_TAG_PROTO_OCELOT_8021Q:
-		err = felix_setup_tag_8021q(ds, cpu);
-		break;
-	default:
-		err = -EPROTONOSUPPORT;
 	}
 
-	return err;
+	dsa_switch_for_each_available_port(dp, ds) {
+		/* This overwrites ocelot_init():
+		 * Do not forward BPDU frames to the CPU port module,
+		 * for 2 reasons:
+		 * - When these packets are injected from the tag_8021q
+		 *   CPU port, we want them to go out, not loop back
+		 *   into the system.
+		 * - STP traffic ingressing on a user port should go to
+		 *   the tag_8021q CPU port, not to the hardware CPU
+		 *   port module.
+		 */
+		ocelot_write_gix(ocelot,
+				 ANA_PORT_CPU_FWD_BPDU_CFG_BPDU_REDIR_ENA(0),
+				 ANA_PORT_CPU_FWD_BPDU_CFG, dp->index);
+	}
+
+	/* The ownership of the CPU port module's queues might have just been
+	 * transferred to the tag_8021q tagger from the NPI-based tagger.
+	 * So there might still be all sorts of crap in the queues. On the
+	 * other hand, the MMIO-based matching of PTP frames is very brittle,
+	 * so we need to be careful that there are no extra frames to be
+	 * dequeued over MMIO, since we would never know to discard them.
+	 */
+	ocelot_drain_cpu_queue(ocelot, 0);
+
+	return 0;
 }
 
-static void felix_del_tag_protocol(struct dsa_switch *ds, int cpu,
+static void felix_tag_8021q_teardown(struct dsa_switch *ds)
-				   enum dsa_tag_protocol proto)
 {
-	switch (proto) {
+	struct ocelot *ocelot = ds->priv;
-	case DSA_TAG_PROTO_SEVILLE:
+	struct dsa_port *dp, *cpu_dp;
-	case DSA_TAG_PROTO_OCELOT:
+
-		felix_teardown_tag_npi(ds, cpu);
+	dsa_switch_for_each_available_port(dp, ds) {
-		break;
+		/* Restore the logic from ocelot_init:
-	case DSA_TAG_PROTO_OCELOT_8021Q:
+		 * do not forward BPDU frames to the front ports.
-		felix_teardown_tag_8021q(ds, cpu);
+		 */
-		break;
+		ocelot_write_gix(ocelot,
-	default:
+				 ANA_PORT_CPU_FWD_BPDU_CFG_BPDU_REDIR_ENA(0xffff),
+				 ANA_PORT_CPU_FWD_BPDU_CFG,
+				 dp->index);
+	}
+
+	dsa_switch_for_each_cpu_port(cpu_dp, ds) {
+		felix_8021q_cpu_port_deinit(ocelot, cpu_dp->index);
+
+		/* TODO we could support multiple CPU ports in tag_8021q mode */
 		break;
 	}
+
+	dsa_tag_8021q_unregister(ds);
+}
+
+static unsigned long felix_tag_8021q_get_host_fwd_mask(struct dsa_switch *ds)
+{
+	return dsa_cpu_ports(ds);
+}
+
+static const struct felix_tag_proto_ops felix_tag_8021q_proto_ops = {
+	.setup			= felix_tag_8021q_setup,
+	.teardown		= felix_tag_8021q_teardown,
+	.get_host_fwd_mask	= felix_tag_8021q_get_host_fwd_mask,
+};
+
+static void felix_set_host_flood(struct dsa_switch *ds, unsigned long mask,
+				 bool uc, bool mc, bool bc)
+{
+	struct ocelot *ocelot = ds->priv;
+	unsigned long val;
+
+	val = uc ? mask : 0;
+	ocelot_rmw_rix(ocelot, val, mask, ANA_PGID_PGID, PGID_UC);
+
+	val = mc ? mask : 0;
+	ocelot_rmw_rix(ocelot, val, mask, ANA_PGID_PGID, PGID_MC);
+	ocelot_rmw_rix(ocelot, val, mask, ANA_PGID_PGID, PGID_MCIPV4);
+	ocelot_rmw_rix(ocelot, val, mask, ANA_PGID_PGID, PGID_MCIPV6);
+}
+
+static void
+felix_migrate_host_flood(struct dsa_switch *ds,
+			 const struct felix_tag_proto_ops *proto_ops,
+			 const struct felix_tag_proto_ops *old_proto_ops)
+{
+	struct ocelot *ocelot = ds->priv;
+	struct felix *felix = ocelot_to_felix(ocelot);
+	unsigned long mask;
+
+	if (old_proto_ops) {
+		mask = old_proto_ops->get_host_fwd_mask(ds);
+		felix_set_host_flood(ds, mask, false, false, false);
+	}
+
+	mask = proto_ops->get_host_fwd_mask(ds);
+	felix_set_host_flood(ds, mask, !!felix->host_flood_uc_mask,
+			     !!felix->host_flood_mc_mask, true);
+}
+
+static int felix_migrate_mdbs(struct dsa_switch *ds,
+			      const struct felix_tag_proto_ops *proto_ops,
+			      const struct felix_tag_proto_ops *old_proto_ops)
+{
+	struct ocelot *ocelot = ds->priv;
+	unsigned long from, to;
+
+	if (!old_proto_ops)
+		return 0;
+
+	from = old_proto_ops->get_host_fwd_mask(ds);
+	to = proto_ops->get_host_fwd_mask(ds);
+
+	return ocelot_migrate_mdbs(ocelot, from, to);
+}
+
+/* Configure the shared hardware resources for a transition between
+ * @old_proto_ops and @proto_ops.
+ * Manual migration is needed because as far as DSA is concerned, no change of
+ * the CPU port is taking place here, just of the tagging protocol.
+ */
+static int
+felix_tag_proto_setup_shared(struct dsa_switch *ds,
+			     const struct felix_tag_proto_ops *proto_ops,
+			     const struct felix_tag_proto_ops *old_proto_ops)
+{
+	bool using_tag_8021q = (proto_ops == &felix_tag_8021q_proto_ops);
+	int err;
+
+	err = felix_migrate_mdbs(ds, proto_ops, old_proto_ops);
+	if (err)
+		return err;
+
+	felix_update_trapping_destinations(ds, using_tag_8021q);
+
+	felix_migrate_host_flood(ds, proto_ops, old_proto_ops);
+
+	return 0;
 }
 
 /* This always leaves the switch in a consistent state, because although the
  * tag_8021q setup can fail, the NPI setup can't. So either the change is made,
  * or the restoration is guaranteed to work.
  */
-static int felix_change_tag_protocol(struct dsa_switch *ds, int cpu,
+static int felix_change_tag_protocol(struct dsa_switch *ds,
 				     enum dsa_tag_protocol proto)
 {
+	const struct felix_tag_proto_ops *old_proto_ops, *proto_ops;
 	struct ocelot *ocelot = ds->priv;
 	struct felix *felix = ocelot_to_felix(ocelot);
-	enum dsa_tag_protocol old_proto = felix->tag_proto;
-	bool cpu_port_active = false;
-	struct dsa_port *dp;
 	int err;
 
-	if (proto != DSA_TAG_PROTO_SEVILLE &&
+	switch (proto) {
-	    proto != DSA_TAG_PROTO_OCELOT &&
+	case DSA_TAG_PROTO_SEVILLE:
-	    proto != DSA_TAG_PROTO_OCELOT_8021Q)
+	case DSA_TAG_PROTO_OCELOT:
+		proto_ops = &felix_tag_npi_proto_ops;
+		break;
+	case DSA_TAG_PROTO_OCELOT_8021Q:
+		proto_ops = &felix_tag_8021q_proto_ops;
+		break;
+	default:
 		return -EPROTONOSUPPORT;
-
-	/* We don't support multiple CPU ports, yet the DT blob may have
-	 * multiple CPU ports defined. The first CPU port is the active one,
-	 * the others are inactive. In this case, DSA will call
-	 * ->change_tag_protocol() multiple times, once per CPU port.
-	 * Since we implement the tagging protocol change towards "ocelot" or
-	 * "seville" as effectively initializing the NPI port, what we are
-	 * doing is effectively changing who the NPI port is to the last @cpu
-	 * argument passed, which is an unused DSA CPU port and not the one
-	 * that should actively pass traffic.
-	 * Suppress DSA's calls on CPU ports that are inactive.
-	 */
-	dsa_switch_for_each_user_port(dp, ds) {
-		if (dp->cpu_dp->index == cpu) {
-			cpu_port_active = true;
-			break;
-		}
 	}
 
-	if (!cpu_port_active)
+	old_proto_ops = felix->tag_proto_ops;
-		return 0;
 
-	felix_del_tag_protocol(ds, cpu, old_proto);
+	err = proto_ops->setup(ds);
+	if (err)
+		goto setup_failed;
 
-	err = felix_set_tag_protocol(ds, cpu, proto);
+	err = felix_tag_proto_setup_shared(ds, proto_ops, old_proto_ops);
-	if (err) {
+	if (err)
-		felix_set_tag_protocol(ds, cpu, old_proto);
+		goto setup_shared_failed;
-		return err;
-	}
 
+	if (old_proto_ops)
+		old_proto_ops->teardown(ds);
+
+	felix->tag_proto_ops = proto_ops;
 	felix->tag_proto = proto;
 
 	return 0;
+
+setup_shared_failed:
+	proto_ops->teardown(ds);
+setup_failed:
+	return err;
 }
 
 static enum dsa_tag_protocol felix_get_tag_protocol(struct dsa_switch *ds,
@@ -634,6 +653,28 @@ static enum dsa_tag_protocol felix_get_tag_protocol(struct dsa_switch *ds,
 	return felix->tag_proto;
 }
 
+static void felix_port_set_host_flood(struct dsa_switch *ds, int port,
+				      bool uc, bool mc)
+{
+	struct ocelot *ocelot = ds->priv;
+	struct felix *felix = ocelot_to_felix(ocelot);
+	unsigned long mask;
+
+	if (uc)
+		felix->host_flood_uc_mask |= BIT(port);
+	else
+		felix->host_flood_uc_mask &= ~BIT(port);
+
+	if (mc)
+		felix->host_flood_mc_mask |= BIT(port);
+	else
+		felix->host_flood_mc_mask &= ~BIT(port);
+
+	mask = felix->tag_proto_ops->get_host_fwd_mask(ds);
+	felix_set_host_flood(ds, mask, !!felix->host_flood_uc_mask,
+			     !!felix->host_flood_mc_mask, true);
+}
+
 static int felix_set_ageing_time(struct dsa_switch *ds,
 				 unsigned int ageing_time)
 {
@@ -668,15 +709,19 @@ static int felix_fdb_add(struct dsa_switch *ds, int port,
 			 struct dsa_db db)
 {
 	struct net_device *bridge_dev = felix_classify_db(db);
+	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct ocelot *ocelot = ds->priv;
 
 	if (IS_ERR(bridge_dev))
 		return PTR_ERR(bridge_dev);
 
-	if (dsa_is_cpu_port(ds, port) && !bridge_dev &&
+	if (dsa_port_is_cpu(dp) && !bridge_dev &&
 	    dsa_fdb_present_in_other_db(ds, port, addr, vid, db))
 		return 0;
 
+	if (dsa_port_is_cpu(dp))
+		port = PGID_CPU;
+
 	return ocelot_fdb_add(ocelot, port, addr, vid, bridge_dev);
 }
 
@@ -685,15 +730,19 @@ static int felix_fdb_del(struct dsa_switch *ds, int port,
 			 struct dsa_db db)
 {
 	struct net_device *bridge_dev = felix_classify_db(db);
+	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct ocelot *ocelot = ds->priv;
 
 	if (IS_ERR(bridge_dev))
 		return PTR_ERR(bridge_dev);
 
-	if (dsa_is_cpu_port(ds, port) && !bridge_dev &&
+	if (dsa_port_is_cpu(dp) && !bridge_dev &&
 	    dsa_fdb_present_in_other_db(ds, port, addr, vid, db))
 		return 0;
 
+	if (dsa_port_is_cpu(dp))
+		port = PGID_CPU;
+
 	return ocelot_fdb_del(ocelot, port, addr, vid, bridge_dev);
 }
 
@@ -737,6 +786,9 @@ static int felix_mdb_add(struct dsa_switch *ds, int port,
 	    dsa_mdb_present_in_other_db(ds, port, mdb, db))
 		return 0;
 
+	if (port == ocelot->npi)
+		port = ocelot->num_phys_ports;
+
 	return ocelot_port_mdb_add(ocelot, port, mdb, bridge_dev);
 }
 
@@ -754,6 +806,9 @@ static int felix_mdb_del(struct dsa_switch *ds, int port,
 	    dsa_mdb_present_in_other_db(ds, port, mdb, db))
 		return 0;
 
+	if (port == ocelot->npi)
+		port = ocelot->num_phys_ports;
+
 	return ocelot_port_mdb_del(ocelot, port, mdb, bridge_dev);
 }
 
@@ -780,6 +835,9 @@ static int felix_bridge_flags(struct dsa_switch *ds, int port,
 {
 	struct ocelot *ocelot = ds->priv;
 
+	if (port == ocelot->npi)
+		port = ocelot->num_phys_ports;
+
 	ocelot_port_bridge_flags(ocelot, port, val);
 
 	return 0;
@@ -1293,7 +1351,6 @@ static int felix_setup(struct dsa_switch *ds)
 {
 	struct ocelot *ocelot = ds->priv;
 	struct felix *felix = ocelot_to_felix(ocelot);
-	unsigned long cpu_flood;
 	struct dsa_port *dp;
 	int err;
 
@@ -1327,21 +1384,10 @@ static int felix_setup(struct dsa_switch *ds)
 	if (err)
 		goto out_deinit_ports;
 
-	dsa_switch_for_each_cpu_port(dp, ds) {
+	/* The initial tag protocol is NPI which won't fail during initial
-		/* The initial tag protocol is NPI which always returns 0, so
+	 * setup, there's no real point in checking for errors.
-		 * there's no real point in checking for errors.
+	 */
-		 */
+	felix_change_tag_protocol(ds, felix->tag_proto);
-		felix_set_tag_protocol(ds, dp->index, felix->tag_proto);
-
-		/* Start off with flooding disabled towards the NPI port
-		 * (actually CPU port module).
-		 */
-		cpu_flood = ANA_PGID_PGID_PGID(BIT(ocelot->num_phys_ports));
-		ocelot_rmw_rix(ocelot, 0, cpu_flood, ANA_PGID_PGID, PGID_UC);
-		ocelot_rmw_rix(ocelot, 0, cpu_flood, ANA_PGID_PGID, PGID_MC);
-
-		break;
-	}
 
 	ds->mtu_enforcement_ingress = true;
 	ds->assisted_learning_on_cpu_port = true;
@@ -1370,10 +1416,8 @@ static void felix_teardown(struct dsa_switch *ds)
 	struct felix *felix = ocelot_to_felix(ocelot);
 	struct dsa_port *dp;
 
-	dsa_switch_for_each_cpu_port(dp, ds) {
+	if (felix->tag_proto_ops)
-		felix_del_tag_protocol(ds, dp->index, felix->tag_proto);
+		felix->tag_proto_ops->teardown(ds);
-		break;
-	}
 
 	dsa_switch_for_each_available_port(dp, ds)
 		ocelot_deinit_port(ocelot, dp->index);
@@ -1859,6 +1903,7 @@ const struct dsa_switch_ops felix_switch_ops = {
 	.port_get_dscp_prio		= felix_port_get_dscp_prio,
 	.port_add_dscp_prio		= felix_port_add_dscp_prio,
 	.port_del_dscp_prio		= felix_port_del_dscp_prio,
+	.port_set_host_flood		= felix_port_set_host_flood,
 };
 
 struct net_device *felix_port_to_netdev(struct ocelot *ocelot, int port)

drivers/net/dsa/ocelot/felix.h

@@ -59,6 +59,19 @@ struct felix_info {
 				      struct resource *res);
 };
 
+/* Methods for initializing the hardware resources specific to a tagging
+ * protocol (like the NPI port, for "ocelot" or "seville", or the VCAP TCAMs,
+ * for "ocelot-8021q").
+ * It is important that the resources configured here do not have side effects
+ * for the other tagging protocols. If that is the case, their configuration
+ * needs to go to felix_tag_proto_setup_shared().
+ */
+struct felix_tag_proto_ops {
+	int (*setup)(struct dsa_switch *ds);
+	void (*teardown)(struct dsa_switch *ds);
+	unsigned long (*get_host_fwd_mask)(struct dsa_switch *ds);
+};
+
 extern const struct dsa_switch_ops felix_switch_ops;
 
 /* DSA glue / front-end for struct ocelot */
@@ -71,7 +84,10 @@ struct felix {
 	resource_size_t			switch_base;
 	resource_size_t			imdio_base;
 	enum dsa_tag_protocol		tag_proto;
+	const struct felix_tag_proto_ops *tag_proto_ops;
 	struct kthread_worker		*xmit_worker;
+	unsigned long			host_flood_uc_mask;
+	unsigned long			host_flood_mc_mask;
 };
 
 struct net_device *felix_port_to_netdev(struct ocelot *ocelot, int port);

drivers/net/dsa/realtek/rtl8365mb.c

@@ -1778,7 +1778,7 @@ static int rtl8365mb_cpu_config(struct realtek_priv *priv)
 	return 0;
 }
 
-static int rtl8365mb_change_tag_protocol(struct dsa_switch *ds, int cpu_index,
+static int rtl8365mb_change_tag_protocol(struct dsa_switch *ds,
 					 enum dsa_tag_protocol proto)
 {
 	struct realtek_priv *priv = ds->priv;

drivers/net/ethernet/mscc/ocelot.c

@@ -1349,15 +1349,10 @@ EXPORT_SYMBOL(ocelot_drain_cpu_queue);
 int ocelot_fdb_add(struct ocelot *ocelot, int port, const unsigned char *addr,
 		   u16 vid, const struct net_device *bridge)
 {
-	int pgid = port;
-
-	if (port == ocelot->npi)
-		pgid = PGID_CPU;
-
 	if (!vid)
 		vid = ocelot_vlan_unaware_pvid(ocelot, bridge);
 
-	return ocelot_mact_learn(ocelot, pgid, addr, vid, ENTRYTYPE_LOCKED);
+	return ocelot_mact_learn(ocelot, port, addr, vid, ENTRYTYPE_LOCKED);
 }
 EXPORT_SYMBOL(ocelot_fdb_add);
 
@@ -2344,9 +2339,6 @@ int ocelot_port_mdb_add(struct ocelot *ocelot, int port,
 	struct ocelot_pgid *pgid;
 	u16 vid = mdb->vid;
 
-	if (port == ocelot->npi)
-		port = ocelot->num_phys_ports;
-
 	if (!vid)
 		vid = ocelot_vlan_unaware_pvid(ocelot, bridge);
 
@@ -2404,9 +2396,6 @@ int ocelot_port_mdb_del(struct ocelot *ocelot, int port,
 	struct ocelot_pgid *pgid;
 	u16 vid = mdb->vid;
 
-	if (port == ocelot->npi)
-		port = ocelot->num_phys_ports;
-
 	if (!vid)
 		vid = ocelot_vlan_unaware_pvid(ocelot, bridge);
 
@@ -2954,9 +2943,6 @@ EXPORT_SYMBOL(ocelot_port_pre_bridge_flags);
 void ocelot_port_bridge_flags(struct ocelot *ocelot, int port,
 			      struct switchdev_brport_flags flags)
 {
-	if (port == ocelot->npi)
-		port = ocelot->num_phys_ports;
-
 	if (flags.mask & BR_LEARNING)
 		ocelot_port_set_learning(ocelot, port,
 					 !!(flags.val & BR_LEARNING));

include/net/dsa.h

@@ -579,6 +579,10 @@ static inline bool dsa_is_user_port(struct dsa_switch *ds, int p)
 	dsa_switch_for_each_port((_dp), (_ds)) \
 		if (dsa_port_is_cpu((_dp)))
 
+#define dsa_switch_for_each_cpu_port_continue_reverse(_dp, _ds) \
+	dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \
+		if (dsa_port_is_cpu((_dp)))
+
 static inline u32 dsa_user_ports(struct dsa_switch *ds)
 {
 	struct dsa_port *dp;
@@ -590,6 +594,17 @@ static inline u32 dsa_user_ports(struct dsa_switch *ds)
 	return mask;
 }
 
+static inline u32 dsa_cpu_ports(struct dsa_switch *ds)
+{
+	struct dsa_port *cpu_dp;
+	u32 mask = 0;
+
+	dsa_switch_for_each_cpu_port(cpu_dp, ds)
+		mask |= BIT(cpu_dp->index);
+
+	return mask;
+}
+
 /* Return the local port used to reach an arbitrary switch device */
 static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device)
 {
@@ -792,7 +807,7 @@ struct dsa_switch_ops {
 	enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds,
 						  int port,
 						  enum dsa_tag_protocol mprot);
-	int	(*change_tag_protocol)(struct dsa_switch *ds, int port,
+	int	(*change_tag_protocol)(struct dsa_switch *ds,
 				       enum dsa_tag_protocol proto);
 	/*
 	 * Method for switch drivers to connect to the tagging protocol driver
@@ -967,6 +982,8 @@ struct dsa_switch_ops {
 	int	(*port_bridge_flags)(struct dsa_switch *ds, int port,
 				     struct switchdev_brport_flags flags,
 				     struct netlink_ext_ack *extack);
+	void	(*port_set_host_flood)(struct dsa_switch *ds, int port,
+				       bool uc, bool mc);
 
 	/*
 	 * VLAN support

net/dsa/dsa2.c

@@ -809,22 +809,18 @@ static int dsa_switch_setup_tag_protocol(struct dsa_switch *ds)
 {
 	const struct dsa_device_ops *tag_ops = ds->dst->tag_ops;
 	struct dsa_switch_tree *dst = ds->dst;
-	struct dsa_port *cpu_dp;
 	int err;
 
 	if (tag_ops->proto == dst->default_proto)
 		goto connect;
 
-	dsa_switch_for_each_cpu_port(cpu_dp, ds) {
+	rtnl_lock();
-		rtnl_lock();
+	err = ds->ops->change_tag_protocol(ds, tag_ops->proto);
-		err = ds->ops->change_tag_protocol(ds, cpu_dp->index,
+	rtnl_unlock();
-						   tag_ops->proto);
+	if (err) {
-		rtnl_unlock();
+		dev_err(ds->dev, "Unable to use tag protocol \"%s\": %pe\n",
-		if (err) {
+			tag_ops->name, ERR_PTR(err));
-			dev_err(ds->dev, "Unable to use tag protocol \"%s\": %pe\n",
+		return err;
-				tag_ops->name, ERR_PTR(err));
-			return err;
-		}
 	}
 
 connect:

net/dsa/dsa_priv.h

@@ -291,6 +291,7 @@ int dsa_port_hsr_join(struct dsa_port *dp, struct net_device *hsr);
 void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr);
 int dsa_port_tag_8021q_vlan_add(struct dsa_port *dp, u16 vid, bool broadcast);
 void dsa_port_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid, bool broadcast);
+void dsa_port_set_host_flood(struct dsa_port *dp, bool uc, bool mc);
 
 /* slave.c */
 extern const struct dsa_device_ops notag_netdev_ops;

net/dsa/port.c

@@ -920,6 +920,14 @@ int dsa_port_bridge_flags(struct dsa_port *dp,
 	return 0;
 }
 
+void dsa_port_set_host_flood(struct dsa_port *dp, bool uc, bool mc)
+{
+	struct dsa_switch *ds = dp->ds;
+
+	if (ds->ops->port_set_host_flood)
+		ds->ops->port_set_host_flood(ds, dp->index, uc, mc);
+}
+
 int dsa_port_vlan_msti(struct dsa_port *dp,
 		       const struct switchdev_vlan_msti *msti)
 {

net/dsa/slave.c

@@ -262,37 +262,13 @@ static int dsa_slave_close(struct net_device *dev)
 	return 0;
 }
 
-/* Keep flooding enabled towards this port's CPU port as long as it serves at
+static void dsa_slave_manage_host_flood(struct net_device *dev)
- * least one port in the tree that requires it.
- */
-static void dsa_port_manage_cpu_flood(struct dsa_port *dp)
 {
-	struct switchdev_brport_flags flags = {
+	bool mc = dev->flags & (IFF_PROMISC | IFF_ALLMULTI);
-		.mask = BR_FLOOD | BR_MCAST_FLOOD,
+	struct dsa_port *dp = dsa_slave_to_port(dev);
-	};
+	bool uc = dev->flags & IFF_PROMISC;
-	struct dsa_switch_tree *dst = dp->ds->dst;
-	struct dsa_port *cpu_dp = dp->cpu_dp;
-	struct dsa_port *other_dp;
-	int err;
 
-	list_for_each_entry(other_dp, &dst->ports, list) {
+	dsa_port_set_host_flood(dp, uc, mc);
-		if (!dsa_port_is_user(other_dp))
-			continue;
-
-		if (other_dp->cpu_dp != cpu_dp)
-			continue;
-
-		if (other_dp->slave->flags & IFF_ALLMULTI)
-			flags.val |= BR_MCAST_FLOOD;
-		if (other_dp->slave->flags & IFF_PROMISC)
-			flags.val |= BR_FLOOD | BR_MCAST_FLOOD;
-	}
-
-	err = dsa_port_pre_bridge_flags(dp, flags, NULL);
-	if (err)
-		return;
-
-	dsa_port_bridge_flags(cpu_dp, flags, NULL);
 }
 
 static void dsa_slave_change_rx_flags(struct net_device *dev, int change)
@@ -310,7 +286,7 @@ static void dsa_slave_change_rx_flags(struct net_device *dev, int change)
 
 	if (dsa_switch_supports_uc_filtering(ds) &&
 	    dsa_switch_supports_mc_filtering(ds))
-		dsa_port_manage_cpu_flood(dp);
+		dsa_slave_manage_host_flood(dev);
 }
 
 static void dsa_slave_set_rx_mode(struct net_device *dev)

net/dsa/switch.c

@@ -809,14 +809,12 @@ static int dsa_switch_change_tag_proto(struct dsa_switch *ds,
 
 	ASSERT_RTNL();
 
-	dsa_switch_for_each_cpu_port(cpu_dp, ds) {
+	err = ds->ops->change_tag_protocol(ds, tag_ops->proto);
-		err = ds->ops->change_tag_protocol(ds, cpu_dp->index,
+	if (err)
-						   tag_ops->proto);
+		return err;
-		if (err)
-			return err;
 
+	dsa_switch_for_each_cpu_port(cpu_dp, ds)
 		dsa_port_set_tag_protocol(cpu_dp, tag_ops);
-	}
 
 	/* Now that changing the tag protocol can no longer fail, let's update
 	 * the remaining bits which are "duplicated for faster access", and the