Merge branch 'mvpp2-add-RSS-support'

Maxime Chevallier says:

====================
net: mvpp2: add RSS support

This series adds support for RSS on PPv2. There already was some code to
handle the RSS tables, but the driver was missing all the classification
steps required to actually use these tables.

RSS is used through the classifier, using at least 2 lookups :
 - One using the C2 engine, a TCAM engine that match the packet based on
   some header extracted fields, assigns the default rx queue for that
   packet and tag it for RSS
 - One using the C3Hx engine, which computes the hash that's used to perform
   the lookup in the RSS table.

Since RSS spreads the load across CPUs, we need to make sure that packets
from the same flow are always assigned the same rx queue, to prevent
re-ordering.

This series therefore adds a classification step based on the Header Parser,
that separate ingress traffic into 52 flows, based on some L2, L3 and L4
parameters.

Patches 1 and 2 fix some header issues, from the driver splitting

Patches 3 to 7 make sure the correct receive queue setup is used for RSS

Patches 8 to 14 deal with the way we handle the RSS tables

Patch 15 implement basic classifier configuration, by using it to assign the
default receive queue

Patch 16 implement the ingress traffic splitting into multiple flows

Patch 17 adds RSS support, by using the needed classification steps

Patch 18 adds the required ethtool ops to configure the flow hash parameters

This was tested on MacchiatoBin, giving some nice performance improvements
using ip forwarding (going from 5Gbps to 9.6Gbps total throughput).

RSS is disabled by default.
====================

Signed-off-by: David S. Miller <[email protected]>

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

@@ -73,9 +73,9 @@
 #define     MVPP22_RSS_INDEX_TABLE_ENTRY(idx)	(idx)
 #define     MVPP22_RSS_INDEX_TABLE(idx)		((idx) << 8)
 #define     MVPP22_RSS_INDEX_QUEUE(idx)		((idx) << 16)
-#define MVPP22_RSS_TABLE_ENTRY			0x1508
-#define MVPP22_RSS_TABLE			0x1510
+#define MVPP22_RXQ2RSS_TABLE			0x1504
 #define     MVPP22_RSS_TABLE_POINTER(p)		(p)
+#define MVPP22_RSS_TABLE_ENTRY			0x1508
 #define MVPP22_RSS_WIDTH			0x150c
 
 /* Classifier Registers */
@@ -87,18 +87,58 @@
 #define     MVPP2_CLS_LKP_INDEX_WAY_OFFS	6
 #define MVPP2_CLS_LKP_TBL_REG			0x1818
 #define     MVPP2_CLS_LKP_TBL_RXQ_MASK		0xff
+#define     MVPP2_CLS_LKP_FLOW_PTR(flow)	((flow) << 16)
 #define     MVPP2_CLS_LKP_TBL_LOOKUP_EN_MASK	BIT(25)
 #define MVPP2_CLS_FLOW_INDEX_REG		0x1820
 #define MVPP2_CLS_FLOW_TBL0_REG			0x1824
+#define     MVPP2_CLS_FLOW_TBL0_LAST		BIT(0)
+#define     MVPP2_CLS_FLOW_TBL0_ENG_MASK	0x7
+#define     MVPP2_CLS_FLOW_TBL0_OFFS		1
+#define     MVPP2_CLS_FLOW_TBL0_ENG(x)		((x) << 1)
+#define     MVPP2_CLS_FLOW_TBL0_PORT_ID_MASK	0xff
+#define     MVPP2_CLS_FLOW_TBL0_PORT_ID(port)	((port) << 4)
+#define     MVPP2_CLS_FLOW_TBL0_PORT_ID_SEL	BIT(23)
 #define MVPP2_CLS_FLOW_TBL1_REG			0x1828
+#define     MVPP2_CLS_FLOW_TBL1_N_FIELDS_MASK	0x7
+#define     MVPP2_CLS_FLOW_TBL1_N_FIELDS(x)	(x)
+#define     MVPP2_CLS_FLOW_TBL1_PRIO_MASK	0x3f
+#define     MVPP2_CLS_FLOW_TBL1_PRIO(x)		((x) << 9)
+#define     MVPP2_CLS_FLOW_TBL1_SEQ_MASK	0x7
+#define     MVPP2_CLS_FLOW_TBL1_SEQ(x)		((x) << 15)
 #define MVPP2_CLS_FLOW_TBL2_REG			0x182c
+#define     MVPP2_CLS_FLOW_TBL2_FLD_MASK	0x3f
+#define     MVPP2_CLS_FLOW_TBL2_FLD_OFFS(n)	((n) * 6)
+#define     MVPP2_CLS_FLOW_TBL2_FLD(n, x)	((x) << ((n) * 6))
 #define MVPP2_CLS_OVERSIZE_RXQ_LOW_REG(port)	(0x1980 + ((port) * 4))
 #define     MVPP2_CLS_OVERSIZE_RXQ_LOW_BITS	3
 #define     MVPP2_CLS_OVERSIZE_RXQ_LOW_MASK	0x7
 #define MVPP2_CLS_SWFWD_P2HQ_REG(port)		(0x19b0 + ((port) * 4))
 #define MVPP2_CLS_SWFWD_PCTRL_REG		0x19d0
 #define     MVPP2_CLS_SWFWD_PCTRL_MASK(port)	(1 << (port))
 
+/* Classifier C2 engine Registers */
+#define MVPP22_CLS_C2_TCAM_IDX			0x1b00
+#define MVPP22_CLS_C2_TCAM_DATA0		0x1b10
+#define MVPP22_CLS_C2_TCAM_DATA1		0x1b14
+#define MVPP22_CLS_C2_TCAM_DATA2		0x1b18
+#define MVPP22_CLS_C2_TCAM_DATA3		0x1b1c
+#define MVPP22_CLS_C2_TCAM_DATA4		0x1b20
+#define     MVPP22_CLS_C2_PORT_ID(port)		((port) << 8)
+#define MVPP22_CLS_C2_ACT			0x1b60
+#define     MVPP22_CLS_C2_ACT_RSS_EN(act)	(((act) & 0x3) << 19)
+#define     MVPP22_CLS_C2_ACT_FWD(act)		(((act) & 0x7) << 13)
+#define     MVPP22_CLS_C2_ACT_QHIGH(act)	(((act) & 0x3) << 11)
+#define     MVPP22_CLS_C2_ACT_QLOW(act)		(((act) & 0x3) << 9)
+#define MVPP22_CLS_C2_ATTR0			0x1b64
+#define     MVPP22_CLS_C2_ATTR0_QHIGH(qh)	(((qh) & 0x1f) << 24)
+#define     MVPP22_CLS_C2_ATTR0_QHIGH_MASK	0x1f
+#define     MVPP22_CLS_C2_ATTR0_QLOW(ql)	(((ql) & 0x7) << 21)
+#define     MVPP22_CLS_C2_ATTR0_QLOW_MASK	0x7
+#define MVPP22_CLS_C2_ATTR1			0x1b68
+#define MVPP22_CLS_C2_ATTR2			0x1b6c
+#define     MVPP22_CLS_C2_ATTR2_RSS_EN		BIT(30)
+#define MVPP22_CLS_C2_ATTR3			0x1b70
+
 /* Descriptor Manager Top Registers */
 #define MVPP2_RXQ_NUM_REG			0x2040
 #define MVPP2_RXQ_DESC_ADDR_REG			0x2044
@@ -500,7 +540,7 @@
 #define MVPP2_MAX_SKB_DESCS		(MVPP2_MAX_TSO_SEGS * 2 + MAX_SKB_FRAGS)
 
 /* Dfault number of RXQs in use */
-#define MVPP2_DEFAULT_RXQ		4
+#define MVPP2_DEFAULT_RXQ		1
 
 /* Max number of Rx descriptors */
 #define MVPP2_MAX_RXD_MAX		1024
@@ -557,6 +597,9 @@
 #define MVPP2_BIT_TO_WORD(bit)		((bit) / 32)
 #define MVPP2_BIT_IN_WORD(bit)		((bit) % 32)
 
+/* RSS constants */
+#define MVPP22_RSS_TABLE_ENTRIES	32
+
 /* IPv6 max L3 address size */
 #define MVPP2_MAX_L3_ADDR_SIZE		16
 
@@ -798,6 +841,9 @@ struct mvpp2_port {
 	bool has_tx_irqs;
 
 	u32 tx_time_coal;
+
+	/* RSS indirection table */
+	u32 indir[MVPP22_RSS_TABLE_ENTRIES];
 };
 
 /* The mvpp2_tx_desc and mvpp2_rx_desc structures describe the