net: mvpp2: add an RSS classification step for each flow

One of the classification action that can be performed is to compute a
hash of the packet header based on some header fields, and lookup a RSS
table based on this hash to determine the final RxQ.

This is done by adding one lookup entry per flow per port, so that we
can configure the hash generation parameters for each flow and each
port.

There are 2 possible engines that can be used for RSS hash generation :

 - C3HA, that generates a hash based on up to 4 header-extracted fields
 - C3HB, that does the same as c3HA, but also includes L4 info in the hash

There are a lot of fields that can be extracted from the header. For now,
we only use the ones that we can configure using ethtool :
 - DST MAC address
 - L3 info
 - Source IP
 - Destination IP
 - Source port
 - Destination port

The C3HB engine is selected when we use L4 fields (src/dst port).

               Header parser          Dec table
 Ingress pkt  +-------------+ flow id +----------------------------+
------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag  |
              +-------------+         |TCP IPv4 w/o VLAN, not frag |
                                      |TCP IPv4 w/ VLAN, frag      |--+
                                      |etc.                        |  |
                                      +----------------------------+  |
                                                                      |
                                            Flow table                |
  +---------+   +------------+         +--------------------------+   |
  | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup        |   |
  +---------+   +------------+         |         C3 lookup port 0 |   |
                 |         |           |         C3 lookup port 1 |   |
         +-----------+ +-------------+ |         ...              |   |
         | C2 engine | | C3H engines | | flow 1: C2 lookup        |<--+
         +-----------+ +-------------+ |         C3 lookup port 0 |
                                       |         ...              |
                                       | ...                      |
                                       | flow 51 : C2 lookup      |
                                       |           ...            |
                                       +--------------------------+

The C2 engine also gains the role of enabling and disabling the RSS
table lookup for this packet.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c

@@ -325,6 +325,16 @@ static struct mvpp2_cls_flow cls_flows[MVPP2_N_FLOWS] = {
 		       0, 0),
 };
 
+static void mvpp2_cls_flow_read(struct mvpp2 *priv, int index,
+				struct mvpp2_cls_flow_entry *fe)
+{
+	fe->index = index;
+	mvpp2_write(priv, MVPP2_CLS_FLOW_INDEX_REG, index);
+	fe->data[0] = mvpp2_read(priv, MVPP2_CLS_FLOW_TBL0_REG);
+	fe->data[1] = mvpp2_read(priv, MVPP2_CLS_FLOW_TBL1_REG);
+	fe->data[2] = mvpp2_read(priv, MVPP2_CLS_FLOW_TBL2_REG);
+}
+
 /* Update classification flow table registers */
 static void mvpp2_cls_flow_write(struct mvpp2 *priv,
 				 struct mvpp2_cls_flow_entry *fe)
@@ -346,6 +356,34 @@ static void mvpp2_cls_lookup_write(struct mvpp2 *priv,
 	mvpp2_write(priv, MVPP2_CLS_LKP_TBL_REG, le->data);
 }
 
+/* Operations on flow entry */
+static int mvpp2_cls_flow_hek_num_get(struct mvpp2_cls_flow_entry *fe)
+{
+	return fe->data[1] & MVPP2_CLS_FLOW_TBL1_N_FIELDS_MASK;
+}
+
+static void mvpp2_cls_flow_hek_num_set(struct mvpp2_cls_flow_entry *fe,
+				       int num_of_fields)
+{
+	fe->data[1] &= ~MVPP2_CLS_FLOW_TBL1_N_FIELDS_MASK;
+	fe->data[1] |= MVPP2_CLS_FLOW_TBL1_N_FIELDS(num_of_fields);
+}
+
+static int mvpp2_cls_flow_hek_get(struct mvpp2_cls_flow_entry *fe,
+				  int field_index)
+{
+	return (fe->data[2] >> MVPP2_CLS_FLOW_TBL2_FLD_OFFS(field_index)) &
+		MVPP2_CLS_FLOW_TBL2_FLD_MASK;
+}
+
+static void mvpp2_cls_flow_hek_set(struct mvpp2_cls_flow_entry *fe,
+				   int field_index, int field_id)
+{
+	fe->data[2] &= ~MVPP2_CLS_FLOW_TBL2_FLD(field_index,
+						MVPP2_CLS_FLOW_TBL2_FLD_MASK);
+	fe->data[2] |= MVPP2_CLS_FLOW_TBL2_FLD(field_index, field_id);
+}
+
 static void mvpp2_cls_flow_eng_set(struct mvpp2_cls_flow_entry *fe,
 				   int engine)
 {
@@ -430,15 +468,93 @@ static void mvpp2_cls_flow_init(struct mvpp2 *priv, struct mvpp2_cls_flow *flow)
 
 	mvpp2_cls_flow_eng_set(&fe, MVPP22_CLS_ENGINE_C2);
 	mvpp2_cls_flow_port_id_sel(&fe, true);
-	mvpp2_cls_flow_last_set(&fe, 1);
+	mvpp2_cls_flow_last_set(&fe, 0);
 	mvpp2_cls_flow_pri_set(&fe, 0);
-	mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_LAST);
+	mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_FIRST1);
 
 	/* Add all ports */
 	for (i = 0; i < MVPP2_MAX_PORTS; i++)
 		mvpp2_cls_flow_port_add(&fe, BIT(i));
 
 	mvpp2_cls_flow_write(priv, &fe);
+
+	/* C3Hx lookups */
+	for (i = 0; i < MVPP2_MAX_PORTS; i++) {
+		memset(&fe, 0, sizeof(fe));
+		fe.index = MVPP2_PORT_FLOW_HASH_ENTRY(i, flow->flow_id);
+
+		mvpp2_cls_flow_port_id_sel(&fe, true);
+		mvpp2_cls_flow_pri_set(&fe, i + 1);
+		mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_MIDDLE);
+		mvpp2_cls_flow_port_add(&fe, BIT(i));
+
+		mvpp2_cls_flow_write(priv, &fe);
+	}
+
+	/* Update the last entry */
+	mvpp2_cls_flow_last_set(&fe, 1);
+	mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_LAST);
+
+	mvpp2_cls_flow_write(priv, &fe);
+}
+
+/* Adds a field to the Header Extracted Key generation parameters*/
+static int mvpp2_flow_add_hek_field(struct mvpp2_cls_flow_entry *fe,
+				    u32 field_id)
+{
+	int nb_fields = mvpp2_cls_flow_hek_num_get(fe);
+
+	if (nb_fields == MVPP2_FLOW_N_FIELDS)
+		return -EINVAL;
+
+	mvpp2_cls_flow_hek_set(fe, nb_fields, field_id);
+
+	mvpp2_cls_flow_hek_num_set(fe, nb_fields + 1);
+
+	return 0;
+}
+
+static int mvpp2_flow_set_hek_fields(struct mvpp2_cls_flow_entry *fe,
+				     unsigned long hash_opts)
+{
+	u32 field_id;
+	int i;
+
+	/* Clear old fields */
+	mvpp2_cls_flow_hek_num_set(fe, 0);
+	fe->data[2] = 0;
+
+	for_each_set_bit(i, &hash_opts, MVPP22_CLS_HEK_N_FIELDS) {
+		switch (BIT(i)) {
+		case MVPP22_CLS_HEK_OPT_VLAN:
+			field_id = MVPP22_CLS_FIELD_VLAN;
+			break;
+		case MVPP22_CLS_HEK_OPT_IP4SA:
+			field_id = MVPP22_CLS_FIELD_IP4SA;
+			break;
+		case MVPP22_CLS_HEK_OPT_IP4DA:
+			field_id = MVPP22_CLS_FIELD_IP4DA;
+			break;
+		case MVPP22_CLS_HEK_OPT_IP6SA:
+			field_id = MVPP22_CLS_FIELD_IP6SA;
+			break;
+		case MVPP22_CLS_HEK_OPT_IP6DA:
+			field_id = MVPP22_CLS_FIELD_IP6DA;
+			break;
+		case MVPP22_CLS_HEK_OPT_L4SIP:
+			field_id = MVPP22_CLS_FIELD_L4SIP;
+			break;
+		case MVPP22_CLS_HEK_OPT_L4DIP:
+			field_id = MVPP22_CLS_FIELD_L4DIP;
+			break;
+		default:
+			return -EINVAL;
+		}
+		if (mvpp2_flow_add_hek_field(fe, field_id))
+			return -EINVAL;
+	}
+
+	return 0;
 }
 
 struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow)
@@ -449,6 +565,104 @@ struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow)
 	return &cls_flows[flow];
 }
 
+/* Set the hash generation options for the given traffic flow.
+ * One traffic flow (in the ethtool sense) has multiple classification flows,
+ * to handle specific cases such as fragmentation, or the presence of a
+ * VLAN / DSA Tag.
+ *
+ * Each of these individual flows has different constraints, for example we
+ * can't hash fragmented packets on L4 data (else we would risk having packet
+ * re-ordering), so each classification flows masks the options with their
+ * supported ones.
+ *
+ */
+static int mvpp2_port_rss_hash_opts_set(struct mvpp2_port *port, int flow_type,
+					u16 requested_opts)
+{
+	struct mvpp2_cls_flow_entry fe;
+	struct mvpp2_cls_flow *flow;
+	int i, engine, flow_index;
+	u16 hash_opts;
+
+	for (i = 0; i < MVPP2_N_FLOWS; i++) {
+		flow = mvpp2_cls_flow_get(i);
+		if (!flow)
+			return -EINVAL;
+
+		if (flow->flow_type != flow_type)
+			continue;
+
+		flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(port->id,
+							flow->flow_id);
+
+		mvpp2_cls_flow_read(port->priv, flow_index, &fe);
+
+		hash_opts = flow->supported_hash_opts & requested_opts;
+
+		/* Use C3HB engine to access L4 infos. This adds L4 infos to the
+		 * hash parameters
+		 */
+		if (hash_opts & MVPP22_CLS_HEK_L4_OPTS)
+			engine = MVPP22_CLS_ENGINE_C3HB;
+		else
+			engine = MVPP22_CLS_ENGINE_C3HA;
+
+		if (mvpp2_flow_set_hek_fields(&fe, hash_opts))
+			return -EINVAL;
+
+		mvpp2_cls_flow_eng_set(&fe, engine);
+
+		mvpp2_cls_flow_write(port->priv, &fe);
+	}
+
+	return 0;
+}
+
+u16 mvpp2_flow_get_hek_fields(struct mvpp2_cls_flow_entry *fe)
+{
+	u16 hash_opts = 0;
+	int n_fields, i, field;
+
+	n_fields = mvpp2_cls_flow_hek_num_get(fe);
+
+	for (i = 0; i < n_fields; i++) {
+		field = mvpp2_cls_flow_hek_get(fe, i);
+
+		switch (field) {
+		case MVPP22_CLS_FIELD_MAC_DA:
+			hash_opts |= MVPP22_CLS_HEK_OPT_MAC_DA;
+			break;
+		case MVPP22_CLS_FIELD_VLAN:
+			hash_opts |= MVPP22_CLS_HEK_OPT_VLAN;
+			break;
+		case MVPP22_CLS_FIELD_L3_PROTO:
+			hash_opts |= MVPP22_CLS_HEK_OPT_L3_PROTO;
+			break;
+		case MVPP22_CLS_FIELD_IP4SA:
+			hash_opts |= MVPP22_CLS_HEK_OPT_IP4SA;
+			break;
+		case MVPP22_CLS_FIELD_IP4DA:
+			hash_opts |= MVPP22_CLS_HEK_OPT_IP4DA;
+			break;
+		case MVPP22_CLS_FIELD_IP6SA:
+			hash_opts |= MVPP22_CLS_HEK_OPT_IP6SA;
+			break;
+		case MVPP22_CLS_FIELD_IP6DA:
+			hash_opts |= MVPP22_CLS_HEK_OPT_IP6DA;
+			break;
+		case MVPP22_CLS_FIELD_L4SIP:
+			hash_opts |= MVPP22_CLS_HEK_OPT_L4SIP;
+			break;
+		case MVPP22_CLS_FIELD_L4DIP:
+			hash_opts |= MVPP22_CLS_HEK_OPT_L4DIP;
+			break;
+		default:
+			break;
+		}
+	}
+	return hash_opts;
+}
+
 static void mvpp2_cls_port_init_flows(struct mvpp2 *priv)
 {
 	struct mvpp2_cls_flow *flow;
@@ -485,6 +699,27 @@ static void mvpp2_cls_c2_write(struct mvpp2 *priv,
 	mvpp2_write(priv, MVPP22_CLS_C2_ATTR3, c2->attr[3]);
 }
 
+static void mvpp2_cls_c2_read(struct mvpp2 *priv, int index,
+			      struct mvpp2_cls_c2_entry *c2)
+{
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, index);
+
+	c2->index = index;
+
+	c2->tcam[0] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA0);
+	c2->tcam[1] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA1);
+	c2->tcam[2] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA2);
+	c2->tcam[3] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA3);
+	c2->tcam[4] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA4);
+
+	c2->act = mvpp2_read(priv, MVPP22_CLS_C2_ACT);
+
+	c2->attr[0] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR0);
+	c2->attr[1] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR1);
+	c2->attr[2] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR2);
+	c2->attr[3] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR3);
+}
+
 static void mvpp2_port_c2_cls_init(struct mvpp2_port *port)
 {
 	struct mvpp2_cls_c2_entry c2;
@@ -580,6 +815,38 @@ void mvpp2_cls_port_config(struct mvpp2_port *port)
 	mvpp2_port_c2_cls_init(port);
 }
 
+static void mvpp2_rss_port_c2_enable(struct mvpp2_port *port)
+{
+	struct mvpp2_cls_c2_entry c2;
+
+	mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
+
+	c2.attr[2] |= MVPP22_CLS_C2_ATTR2_RSS_EN;
+
+	mvpp2_cls_c2_write(port->priv, &c2);
+}
+
+static void mvpp2_rss_port_c2_disable(struct mvpp2_port *port)
+{
+	struct mvpp2_cls_c2_entry c2;
+
+	mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
+
+	c2.attr[2] &= ~MVPP22_CLS_C2_ATTR2_RSS_EN;
+
+	mvpp2_cls_c2_write(port->priv, &c2);
+}
+
+void mvpp22_rss_enable(struct mvpp2_port *port)
+{
+	mvpp2_rss_port_c2_enable(port);
+}
+
+void mvpp22_rss_disable(struct mvpp2_port *port)
+{
+	mvpp2_rss_port_c2_disable(port);
+}
+
 /* Set CPU queue number for oversize packets */
 void mvpp2_cls_oversize_rxq_set(struct mvpp2_port *port)
 {
@@ -656,4 +923,12 @@ void mvpp22_rss_port_init(struct mvpp2_port *port)
 		port->indir[i] = ethtool_rxfh_indir_default(i, port->nrxqs);
 
 	mvpp22_rss_fill_table(port, port->id);
+
+	/* Configure default flows */
+	mvpp2_port_rss_hash_opts_set(port, IPV4_FLOW, MVPP22_CLS_HEK_IP4_2T);
+	mvpp2_port_rss_hash_opts_set(port, IPV6_FLOW, MVPP22_CLS_HEK_IP6_2T);
+	mvpp2_port_rss_hash_opts_set(port, TCP_V4_FLOW, MVPP22_CLS_HEK_IP4_5T);
+	mvpp2_port_rss_hash_opts_set(port, TCP_V6_FLOW, MVPP22_CLS_HEK_IP6_5T);
+	mvpp2_port_rss_hash_opts_set(port, UDP_V4_FLOW, MVPP22_CLS_HEK_IP4_5T);
+	mvpp2_port_rss_hash_opts_set(port, UDP_V6_FLOW, MVPP22_CLS_HEK_IP6_5T);
 }

drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h

@@ -62,6 +62,18 @@ enum mvpp2_cls_engine {
 #define MVPP22_CLS_HEK_IP6_5T	(MVPP22_CLS_HEK_IP6_2T | \
 				 MVPP22_CLS_HEK_L4_OPTS)
 
+enum mvpp2_cls_field_id {
+	MVPP22_CLS_FIELD_MAC_DA = 0x03,
+	MVPP22_CLS_FIELD_VLAN = 0x06,
+	MVPP22_CLS_FIELD_L3_PROTO = 0x0f,
+	MVPP22_CLS_FIELD_IP4SA = 0x10,
+	MVPP22_CLS_FIELD_IP4DA = 0x11,
+	MVPP22_CLS_FIELD_IP6SA = 0x17,
+	MVPP22_CLS_FIELD_IP6DA = 0x1a,
+	MVPP22_CLS_FIELD_L4SIP = 0x1d,
+	MVPP22_CLS_FIELD_L4DIP = 0x1e,
+};
+
 enum mvpp2_cls_flow_seq {
 	MVPP2_CLS_FLOW_SEQ_NORMAL = 0,
 	MVPP2_CLS_FLOW_SEQ_FIRST1,
@@ -188,6 +200,9 @@ void mvpp22_rss_fill_table(struct mvpp2_port *port, u32 table);
 
 void mvpp22_rss_port_init(struct mvpp2_port *port);
 
+void mvpp22_rss_enable(struct mvpp2_port *port);
+void mvpp22_rss_disable(struct mvpp2_port *port);
+
 void mvpp2_cls_init(struct mvpp2 *priv);
 
 void mvpp2_cls_port_config(struct mvpp2_port *port);

drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c

@@ -3631,6 +3631,13 @@ static int mvpp2_set_features(struct net_device *dev,
 		}
 	}
 
+	if (changed & NETIF_F_RXHASH) {
+		if (features & NETIF_F_RXHASH)
+			mvpp22_rss_enable(port);
+		else
+			mvpp22_rss_disable(port);
+	}
+
 	return 0;
 }
 
@@ -4759,6 +4766,9 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	dev->hw_features |= features | NETIF_F_RXCSUM | NETIF_F_GRO |
 			    NETIF_F_HW_VLAN_CTAG_FILTER;
 
+	if (mvpp22_rss_is_supported())
+		dev->hw_features |= NETIF_F_RXHASH;
+
 	if (port->pool_long->id == MVPP2_BM_JUMBO && port->id != 0) {
 		dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
 		dev->hw_features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);