Merge branch 'Allow-unknown-unicast-traffic-to-CPU-for-Felix-DSA'

Vladimir Oltean says:

====================
Allow unknown unicast traffic to CPU for Felix DSA

This is the continuation of the previous "[PATCH net-next] net: mscc:
ocelot: Workaround to allow traffic to CPU in standalone mode":

https://www.spinics.net/lists/netdev/msg631067.html

Following the feedback received from Allan Nielsen, the Ocelot and Felix
drivers were made to use the CPU port module in the same way (patch 1),
and Felix was made to additionally allow unknown unicast frames towards
the CPU port module (patch 2).
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 121 insertions, 49 deletions

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index c0acd7dc7f48..69546383a382 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -516,12 +516,22 @@ static int felix_setup(struct dsa_switch *ds)
 	for (port = 0; port < ds->num_ports; port++) {
 		ocelot_init_port(ocelot, port);
 
+		/* Bring up the CPU port module and configure the NPI port */
 		if (dsa_is_cpu_port(ds, port))
-			ocelot_set_cpu_port(ocelot, port,
-					    OCELOT_TAG_PREFIX_NONE,
-					    OCELOT_TAG_PREFIX_LONG);
+			ocelot_configure_cpu(ocelot, port,
+					     OCELOT_TAG_PREFIX_NONE,
+					     OCELOT_TAG_PREFIX_LONG);
 	}
 
+	/* Include the CPU port module in the forwarding mask for unknown
+	 * unicast - the hardware default value for ANA_FLOODING_FLD_UNICAST
+	 * excludes BIT(ocelot->num_phys_ports), and so does ocelot_init, since
+	 * Ocelot relies on whitelisting MAC addresses towards PGID_CPU.
+	 */
+	ocelot_write_rix(ocelot,
+			 ANA_PGID_PGID_PGID(GENMASK(ocelot->num_phys_ports, 0)),
+			 ANA_PGID_PGID, PGID_UC);
+
 	/* It looks like the MAC/PCS interrupt register - PM0_IEVENT (0x8040)
 	 * isn't instantiated for the Felix PF.
 	 * In-band AN may take a few ms to complete, so we need to poll.
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index ac4cf34d3af5..06f9d013f807 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1413,7 +1413,7 @@ void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state)
 	 * a source for the other ports.
 	 */
 	for (p = 0; p < ocelot->num_phys_ports; p++) {
-		if (p == ocelot->cpu || (ocelot->bridge_fwd_mask & BIT(p))) {
+		if (ocelot->bridge_fwd_mask & BIT(p)) {
 			unsigned long mask = ocelot->bridge_fwd_mask & ~BIT(p);
 
 			for (i = 0; i < ocelot->num_phys_ports; i++) {
@@ -1428,18 +1428,10 @@ void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state)
 				}
 			}
 
-			/* Avoid the NPI port from looping back to itself */
-			if (p != ocelot->cpu)
-				mask |= BIT(ocelot->cpu);
-
 			ocelot_write_rix(ocelot, mask,
 					 ANA_PGID_PGID, PGID_SRC + p);
 		} else {
-			/* Only the CPU port, this is compatible with link
-			 * aggregation.
-			 */
-			ocelot_write_rix(ocelot,
-					 BIT(ocelot->cpu),
+			ocelot_write_rix(ocelot, 0,
 					 ANA_PGID_PGID, PGID_SRC + p);
 		}
 	}
@@ -2308,27 +2300,34 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port,
 }
 EXPORT_SYMBOL(ocelot_probe_port);
 
-void ocelot_set_cpu_port(struct ocelot *ocelot, int cpu,
-			 enum ocelot_tag_prefix injection,
-			 enum ocelot_tag_prefix extraction)
+/* Configure and enable the CPU port module, which is a set of queues.
+ * If @npi contains a valid port index, 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.
+ */
+void ocelot_configure_cpu(struct ocelot *ocelot, int npi,
+			  enum ocelot_tag_prefix injection,
+			  enum ocelot_tag_prefix extraction)
 {
-	/* Configure and enable the CPU port. */
+	int cpu = ocelot->num_phys_ports;
+
+	/* The unicast destination PGID for the CPU port module is unused */
 	ocelot_write_rix(ocelot, 0, ANA_PGID_PGID, cpu);
+	/* Instead set up a multicast destination PGID for traffic copied to
+	 * the CPU. Whitelisted MAC addresses like the port netdevice MAC
+	 * addresses will be copied to the CPU via this PGID.
+	 */
 	ocelot_write_rix(ocelot, BIT(cpu), ANA_PGID_PGID, PGID_CPU);
 	ocelot_write_gix(ocelot, ANA_PORT_PORT_CFG_RECV_ENA |
 			 ANA_PORT_PORT_CFG_PORTID_VAL(cpu),
 			 ANA_PORT_PORT_CFG, cpu);
 
-	/* If the CPU port is a physical port, set up the port in Node
-	 * Processor Interface (NPI) mode. This is the mode through which
-	 * frames can be injected from and extracted to an external CPU.
-	 * Only one port can be an NPI at the same time.
-	 */
-	if (cpu < ocelot->num_phys_ports) {
+	if (npi >= 0 && npi < ocelot->num_phys_ports) {
 		int mtu = VLAN_ETH_FRAME_LEN + OCELOT_TAG_LEN;
 
 		ocelot_write(ocelot, QSYS_EXT_CPU_CFG_EXT_CPUQ_MSK_M |
-			     QSYS_EXT_CPU_CFG_EXT_CPU_PORT(cpu),
+			     QSYS_EXT_CPU_CFG_EXT_CPU_PORT(npi),
 			     QSYS_EXT_CPU_CFG);
 
 		if (injection == OCELOT_TAG_PREFIX_SHORT)
@@ -2336,14 +2335,27 @@ void ocelot_set_cpu_port(struct ocelot *ocelot, int cpu,
 		else if (injection == OCELOT_TAG_PREFIX_LONG)
 			mtu += OCELOT_LONG_PREFIX_LEN;
 
-		ocelot_port_set_mtu(ocelot, cpu, mtu);
+		ocelot_port_set_mtu(ocelot, npi, mtu);
+
+		/* Enable NPI port */
+		ocelot_write_rix(ocelot,
+				 QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE |
+				 QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG(1) |
+				 QSYS_SWITCH_PORT_MODE_PORT_ENA,
+				 QSYS_SWITCH_PORT_MODE, npi);
+		/* NPI port Injection/Extraction configuration */
+		ocelot_write_rix(ocelot,
+				 SYS_PORT_MODE_INCL_XTR_HDR(extraction) |
+				 SYS_PORT_MODE_INCL_INJ_HDR(injection),
+				 SYS_PORT_MODE, npi);
 	}
 
-	/* CPU port Injection/Extraction configuration */
+	/* Enable CPU port module */
 	ocelot_write_rix(ocelot, QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE |
 			 QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG(1) |
 			 QSYS_SWITCH_PORT_MODE_PORT_ENA,
 			 QSYS_SWITCH_PORT_MODE, cpu);
+	/* CPU port Injection/Extraction configuration */
 	ocelot_write_rix(ocelot, SYS_PORT_MODE_INCL_XTR_HDR(extraction) |
 			 SYS_PORT_MODE_INCL_INJ_HDR(injection),
 			 SYS_PORT_MODE, cpu);
@@ -2353,10 +2365,8 @@ void ocelot_set_cpu_port(struct ocelot *ocelot, int cpu,
 				 ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
 				 ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1),
 			 ANA_PORT_VLAN_CFG, cpu);
-
-	ocelot->cpu = cpu;
 }
-EXPORT_SYMBOL(ocelot_set_cpu_port);
+EXPORT_SYMBOL(ocelot_configure_cpu);
 
 int ocelot_init(struct ocelot *ocelot)
 {
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index 04372ba72fec..e34ef8380eb3 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -28,16 +28,6 @@
 #include "ocelot_tc.h"
 #include "ocelot_ptp.h"
 
-#define PGID_AGGR    64
-#define PGID_SRC     80
-
-/* Reserved PGIDs */
-#define PGID_CPU     (PGID_AGGR - 5)
-#define PGID_UC      (PGID_AGGR - 4)
-#define PGID_MC      (PGID_AGGR - 3)
-#define PGID_MCIPV4  (PGID_AGGR - 2)
-#define PGID_MCIPV6  (PGID_AGGR - 1)
-
 #define OCELOT_BUFFER_CELL_SZ 60
 
 #define OCELOT_STATS_CHECK_DELAY (2 * HZ)
diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index c343ca5276ef..0ac9fbf77a01 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -453,8 +453,6 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		ocelot->ptp = 1;
 	}
 
-	ocelot->num_cpu_ports = 1; /* 1 port on the switch, two groups */
-
 	ports = of_get_child_by_name(np, "ethernet-ports");
 	if (!ports) {
 		dev_err(&pdev->dev, "no ethernet-ports child node found\n");
@@ -471,8 +469,9 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 	ocelot->vcap = vsc7514_vcap_props;
 
 	ocelot_init(ocelot);
-	ocelot_set_cpu_port(ocelot, ocelot->num_phys_ports,
-			    OCELOT_TAG_PREFIX_NONE, OCELOT_TAG_PREFIX_NONE);
+	/* No NPI port */
+	ocelot_configure_cpu(ocelot, -1, OCELOT_TAG_PREFIX_NONE,
+			     OCELOT_TAG_PREFIX_NONE);
 
 	for_each_available_child_of_node(ports, portnp) {
 		struct ocelot_port_private *priv;
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 5b037f976245..007b584cc431 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -11,6 +11,66 @@
 #include <linux/regmap.h>
 #include <net/dsa.h>
 
+/* Port Group IDs (PGID) are masks of destination ports.
+ *
+ * For L2 forwarding, the switch performs 3 lookups in the PGID table for each
+ * frame, and forwards the frame to the ports that are present in the logical
+ * AND of all 3 PGIDs.
+ *
+ * These PGID lookups are:
+ * - In one of PGID[0-63]: for the destination masks. There are 2 paths by
+ *   which the switch selects a destination PGID:
+ *     - The {DMAC, VID} is present in the MAC table. In that case, the
+ *       destination PGID is given by the DEST_IDX field of the MAC table entry
+ *       that matched.
+ *     - The {DMAC, VID} is not present in the MAC table (it is unknown). The
+ *       frame is disseminated as being either unicast, multicast or broadcast,
+ *       and according to that, the destination PGID is chosen as being the
+ *       value contained by ANA_FLOODING_FLD_UNICAST,
+ *       ANA_FLOODING_FLD_MULTICAST or ANA_FLOODING_FLD_BROADCAST.
+ *   The destination PGID can be an unicast set: the first PGIDs, 0 to
+ *   ocelot->num_phys_ports - 1, or a multicast set: the PGIDs from
+ *   ocelot->num_phys_ports to 63. By convention, a unicast PGID corresponds to
+ *   a physical port and has a single bit set in the destination ports mask:
+ *   that corresponding to the port number itself. In contrast, a multicast
+ *   PGID will have potentially more than one single bit set in the destination
+ *   ports mask.
+ * - In one of PGID[64-79]: for the aggregation mask. The switch classifier
+ *   dissects each frame and generates a 4-bit Link Aggregation Code which is
+ *   used for this second PGID table lookup. The goal of link aggregation is to
+ *   hash multiple flows within the same LAG on to different destination ports.
+ *   The first lookup will result in a PGID with all the LAG members present in
+ *   the destination ports mask, and the second lookup, by Link Aggregation
+ *   Code, will ensure that each flow gets forwarded only to a single port out
+ *   of that mask (there are no duplicates).
+ * - In one of PGID[80-90]: for the source mask. The third time, the PGID table
+ *   is indexed with the ingress port (plus 80). These PGIDs answer the
+ *   question "is port i allowed to forward traffic to port j?" If yes, then
+ *   BIT(j) of PGID 80+i will be found set. The third PGID lookup can be used
+ *   to enforce the L2 forwarding matrix imposed by e.g. a Linux bridge.
+ */
+
+/* Reserve some destination PGIDs at the end of the range:
+ * PGID_CPU: used for whitelisting certain MAC addresses, such as the addresses
+ *           of the switch port net devices, towards the CPU port module.
+ * PGID_UC: the flooding destinations for unknown unicast traffic.
+ * PGID_MC: the flooding destinations for broadcast and non-IP multicast
+ *          traffic.
+ * PGID_MCIPV4: the flooding destinations for IPv4 multicast traffic.
+ * PGID_MCIPV6: the flooding destinations for IPv6 multicast traffic.
+ */
+#define PGID_CPU			59
+#define PGID_UC				60
+#define PGID_MC				61
+#define PGID_MCIPV4			62
+#define PGID_MCIPV6			63
+
+/* Aggregation PGIDs, one per Link Aggregation Code */
+#define PGID_AGGR			64
+
+/* Source PGIDs, one per physical port */
+#define PGID_SRC			80
+
 #define IFH_INJ_BYPASS			BIT(31)
 #define IFH_INJ_POP_CNT_DISABLE		(3 << 28)
 
@@ -451,9 +511,11 @@ struct ocelot {
 	/* Keep track of the vlan port masks */
 	u32				vlan_mask[VLAN_N_VID];
 
+	/* In tables like ANA:PORT and the ANA:PGID:PGID mask,
+	 * the CPU is located after the physical ports (at the
+	 * num_phys_ports index).
+	 */
 	u8				num_phys_ports;
-	u8				num_cpu_ports;
-	u8				cpu;
 
 	u32				*lags;
 
@@ -508,9 +570,9 @@ void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg,
 int ocelot_regfields_init(struct ocelot *ocelot,
 			  const struct reg_field *const regfields);
 struct regmap *ocelot_regmap_init(struct ocelot *ocelot, struct resource *res);
-void ocelot_set_cpu_port(struct ocelot *ocelot, int cpu,
-			 enum ocelot_tag_prefix injection,
-			 enum ocelot_tag_prefix extraction);
+void ocelot_configure_cpu(struct ocelot *ocelot, int npi,
+			  enum ocelot_tag_prefix injection,
+			  enum ocelot_tag_prefix extraction);
 int ocelot_init(struct ocelot *ocelot);
 void ocelot_deinit(struct ocelot *ocelot);
 void ocelot_init_port(struct ocelot *ocelot, int port);
diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c
index 8e3e7283d430..59de1315100f 100644
--- a/net/dsa/tag_ocelot.c
+++ b/net/dsa/tag_ocelot.c
@@ -153,7 +153,8 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb,
 
 	memset(injection, 0, OCELOT_TAG_LEN);
 
-	src = dsa_upstream_port(ds, port);
+	/* Set the source port as the CPU port module and not the NPI port */
+	src = ocelot->num_phys_ports;
 	dest = BIT(port);
 	bypass = true;
 	qos_class = skb->priority;