Merge branch 'felix-dsa-driver-fixes'

Vladimir Oltean says:

====================
Felix DSA driver fixes

This is an assorted collection of fixes for issues seen on the NXP
LS1028A switch.

- PTP packet drops due to switch congestion result in catastrophic
  damage to the driver's state
- loops are not blocked by STP if using the ocelot-8021q tagger
- driver uses the wrong CPU port when two of them are defined in DT
- module autoloading is broken* with both tagging protocol drivers
  (ocelot and ocelot-8021q)

Changes in v2:
- Stop printing that we aren't going to take TX timestamps if we don't
  have TX timestamping anyway, and we are just carrying PTP frames for a
  cascaded DSA switch.
- Shorten the deferred xmit kthread name so that it fits the 16
  character limit (TASK_COMM_LEN)
====================

Link: https://lore.kernel.org/r/20211012114044.2526146-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/dsa/ocelot/felix.c

@@ -266,12 +266,12 @@ static void felix_8021q_cpu_port_deinit(struct ocelot *ocelot, int port)
  */
 static int felix_setup_mmio_filtering(struct felix *felix)
 {
-	unsigned long user_ports = 0, cpu_ports = 0;
+	unsigned long user_ports = dsa_user_ports(felix->ds);
 	struct ocelot_vcap_filter *redirect_rule;
 	struct ocelot_vcap_filter *tagging_rule;
 	struct ocelot *ocelot = &felix->ocelot;
 	struct dsa_switch *ds = felix->ds;
-	int port, ret;
+	int cpu = -1, port, ret;
 
 	tagging_rule = kzalloc(sizeof(struct ocelot_vcap_filter), GFP_KERNEL);
 	if (!tagging_rule)
@@ -284,12 +284,15 @@ static int felix_setup_mmio_filtering(struct felix *felix)
 	}
 
 	for (port = 0; port < ocelot->num_phys_ports; port++) {
-		if (dsa_is_user_port(ds, port))
-			user_ports |= BIT(port);
-		if (dsa_is_cpu_port(ds, port))
-			cpu_ports |= BIT(port);
+		if (dsa_is_cpu_port(ds, port)) {
+			cpu = port;
+			break;
+		}
 	}
 
+	if (cpu < 0)
+		return -EINVAL;
+
 	tagging_rule->key_type = OCELOT_VCAP_KEY_ETYPE;
 	*(__be16 *)tagging_rule->key.etype.etype.value = htons(ETH_P_1588);
 	*(__be16 *)tagging_rule->key.etype.etype.mask = htons(0xffff);
@@ -325,7 +328,7 @@ static int felix_setup_mmio_filtering(struct felix *felix)
 		 * the CPU port module
 		 */
 		redirect_rule->action.mask_mode = OCELOT_MASK_MODE_REDIRECT;
-		redirect_rule->action.port_mask = cpu_ports;
+		redirect_rule->action.port_mask = BIT(cpu);
 	} else {
 		/* Trap PTP packets only to the CPU port module (which is
 		 * redirected to the NPI port)
@@ -1074,6 +1077,101 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 	return 0;
 }
 
+static void ocelot_port_purge_txtstamp_skb(struct ocelot *ocelot, int port,
+					   struct sk_buff *skb)
+{
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	struct sk_buff *clone = OCELOT_SKB_CB(skb)->clone;
+	struct sk_buff *skb_match = NULL, *skb_tmp;
+	unsigned long flags;
+
+	if (!clone)
+		return;
+
+	spin_lock_irqsave(&ocelot_port->tx_skbs.lock, flags);
+
+	skb_queue_walk_safe(&ocelot_port->tx_skbs, skb, skb_tmp) {
+		if (skb != clone)
+			continue;
+		__skb_unlink(skb, &ocelot_port->tx_skbs);
+		skb_match = skb;
+		break;
+	}
+
+	spin_unlock_irqrestore(&ocelot_port->tx_skbs.lock, flags);
+
+	WARN_ONCE(!skb_match,
+		  "Could not find skb clone in TX timestamping list\n");
+}
+
+#define work_to_xmit_work(w) \
+		container_of((w), struct felix_deferred_xmit_work, work)
+
+static void felix_port_deferred_xmit(struct kthread_work *work)
+{
+	struct felix_deferred_xmit_work *xmit_work = work_to_xmit_work(work);
+	struct dsa_switch *ds = xmit_work->dp->ds;
+	struct sk_buff *skb = xmit_work->skb;
+	u32 rew_op = ocelot_ptp_rew_op(skb);
+	struct ocelot *ocelot = ds->priv;
+	int port = xmit_work->dp->index;
+	int retries = 10;
+
+	do {
+		if (ocelot_can_inject(ocelot, 0))
+			break;
+
+		cpu_relax();
+	} while (--retries);
+
+	if (!retries) {
+		dev_err(ocelot->dev, "port %d failed to inject skb\n",
+			port);
+		ocelot_port_purge_txtstamp_skb(ocelot, port, skb);
+		kfree_skb(skb);
+		return;
+	}
+
+	ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb);
+
+	consume_skb(skb);
+	kfree(xmit_work);
+}
+
+static int felix_port_setup_tagger_data(struct dsa_switch *ds, int port)
+{
+	struct dsa_port *dp = dsa_to_port(ds, port);
+	struct ocelot *ocelot = ds->priv;
+	struct felix *felix = ocelot_to_felix(ocelot);
+	struct felix_port *felix_port;
+
+	if (!dsa_port_is_user(dp))
+		return 0;
+
+	felix_port = kzalloc(sizeof(*felix_port), GFP_KERNEL);
+	if (!felix_port)
+		return -ENOMEM;
+
+	felix_port->xmit_worker = felix->xmit_worker;
+	felix_port->xmit_work_fn = felix_port_deferred_xmit;
+
+	dp->priv = felix_port;
+
+	return 0;
+}
+
+static void felix_port_teardown_tagger_data(struct dsa_switch *ds, int port)
+{
+	struct dsa_port *dp = dsa_to_port(ds, port);
+	struct felix_port *felix_port = dp->priv;
+
+	if (!felix_port)
+		return;
+
+	dp->priv = NULL;
+	kfree(felix_port);
+}
+
 /* Hardware initialization done here so that we can allocate structures with
  * devm without fear of dsa_register_switch returning -EPROBE_DEFER and causing
  * us to allocate structures twice (leak memory) and map PCI memory twice
@@ -1102,6 +1200,12 @@ static int felix_setup(struct dsa_switch *ds)
 		}
 	}
 
+	felix->xmit_worker = kthread_create_worker(0, "felix_xmit");
+	if (IS_ERR(felix->xmit_worker)) {
+		err = PTR_ERR(felix->xmit_worker);
+		goto out_deinit_timestamp;
+	}
+
 	for (port = 0; port < ds->num_ports; port++) {
 		if (dsa_is_unused_port(ds, port))
 			continue;
@@ -1112,6 +1216,14 @@ static int felix_setup(struct dsa_switch *ds)
 		 * bits of vlan tag.
 		 */
 		felix_port_qos_map_init(ocelot, port);
+
+		err = felix_port_setup_tagger_data(ds, port);
+		if (err) {
+			dev_err(ds->dev,
+				"port %d failed to set up tagger data: %pe\n",
+				port, ERR_PTR(err));
+			goto out_deinit_ports;
+		}
 	}
 
 	err = ocelot_devlink_sb_register(ocelot);
@@ -1126,6 +1238,7 @@ static int felix_setup(struct dsa_switch *ds)
 		 * there's no real point in checking for errors.
 		 */
 		felix_set_tag_protocol(ds, port, felix->tag_proto);
+		break;
 	}
 
 	ds->mtu_enforcement_ingress = true;
@@ -1138,9 +1251,13 @@ static int felix_setup(struct dsa_switch *ds)
 		if (dsa_is_unused_port(ds, port))
 			continue;
 
+		felix_port_teardown_tagger_data(ds, port);
 		ocelot_deinit_port(ocelot, port);
 	}
 
+	kthread_destroy_worker(felix->xmit_worker);
+
+out_deinit_timestamp:
 	ocelot_deinit_timestamp(ocelot);
 	ocelot_deinit(ocelot);
 
@@ -1162,19 +1279,23 @@ static void felix_teardown(struct dsa_switch *ds)
 			continue;
 
 		felix_del_tag_protocol(ds, port, felix->tag_proto);
+		break;
 	}
 
-	ocelot_devlink_sb_unregister(ocelot);
-	ocelot_deinit_timestamp(ocelot);
-	ocelot_deinit(ocelot);
-
 	for (port = 0; port < ocelot->num_phys_ports; port++) {
 		if (dsa_is_unused_port(ds, port))
 			continue;
 
+		felix_port_teardown_tagger_data(ds, port);
 		ocelot_deinit_port(ocelot, port);
 	}
 
+	kthread_destroy_worker(felix->xmit_worker);
+
+	ocelot_devlink_sb_unregister(ocelot);
+	ocelot_deinit_timestamp(ocelot);
+	ocelot_deinit(ocelot);
+
 	if (felix->info->mdio_bus_free)
 		felix->info->mdio_bus_free(ocelot);
 }
@@ -1291,8 +1412,12 @@ static void felix_txtstamp(struct dsa_switch *ds, int port,
 	if (!ocelot->ptp)
 		return;
 
-	if (ocelot_port_txtstamp_request(ocelot, port, skb, &clone))
+	if (ocelot_port_txtstamp_request(ocelot, port, skb, &clone)) {
+		dev_err_ratelimited(ds->dev,
+				    "port %d delivering skb without TX timestamp\n",
+				    port);
 		return;
+	}
 
 	if (clone)
 		OCELOT_SKB_CB(skb)->clone = clone;

drivers/net/dsa/ocelot/felix.h

@@ -62,6 +62,7 @@ struct felix {
 	resource_size_t			switch_base;
 	resource_size_t			imdio_base;
 	enum dsa_tag_protocol		tag_proto;
+	struct kthread_worker		*xmit_worker;
 };
 
 struct net_device *felix_port_to_netdev(struct ocelot *ocelot, int port);