net: mvpp2: prs: improve ipv4 parse flow

Patch didn't fix any issue, just improve parse flow
and align ipv4 parse flow with ipv6 parse flow.

Currently ipv4 kenguru parser first check IP protocol(TCP/UDP)
and then destination IP address.
Patch introduce reverse ipv4 parse, first destination IP address parsed
and only then IP protocol.
This would allow extend capability for packet L4 parsing and align ipv4
parsing flow with ipv6.
Suggested-by: Liron Himi <liron@marvell.com>
Signed-off-by: Stefan Chulski <stefanc@marvell.com>
Link: https://lore.kernel.org/r/1610289059-14962-1-git-send-email-stefanc@marvell.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c

@@ -914,15 +914,15 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto,
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP4);
 	pe.index = tid;
 
-	/* Set next lu to IPv4 */
-	mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_IP4);
-	mvpp2_prs_sram_shift_set(&pe, 12, MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD);
+	/* Finished: go to flowid generation */
+	mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_FLOWS);
+	mvpp2_prs_sram_bits_set(&pe, MVPP2_PRS_SRAM_LU_GEN_BIT, 1);
+
 	/* Set L4 offset */
 	mvpp2_prs_sram_offset_set(&pe, MVPP2_PRS_SRAM_UDF_TYPE_L4,
 				  sizeof(struct iphdr) - 4,
 				  MVPP2_PRS_SRAM_OP_SEL_UDF_ADD);
-	mvpp2_prs_sram_ai_update(&pe, MVPP2_PRS_IPV4_DIP_AI_BIT,
-				 MVPP2_PRS_IPV4_DIP_AI_BIT);
+	mvpp2_prs_sram_ai_update(&pe, 0, MVPP2_PRS_IPV4_DIP_AI_BIT);
 	mvpp2_prs_sram_ri_update(&pe, ri, ri_mask | MVPP2_PRS_RI_IP_FRAG_MASK);
 
 	mvpp2_prs_tcam_data_byte_set(&pe, 2, 0x00,
@@ -931,7 +931,8 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto,
 				     MVPP2_PRS_TCAM_PROTO_MASK);
 
 	mvpp2_prs_tcam_data_byte_set(&pe, 5, proto, MVPP2_PRS_TCAM_PROTO_MASK);
-	mvpp2_prs_tcam_ai_update(&pe, 0, MVPP2_PRS_IPV4_DIP_AI_BIT);
+	mvpp2_prs_tcam_ai_update(&pe, MVPP2_PRS_IPV4_DIP_AI_BIT,
+				 MVPP2_PRS_IPV4_DIP_AI_BIT);
 	/* Unmask all ports */
 	mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK);
 
@@ -999,12 +1000,17 @@ static int mvpp2_prs_ip4_cast(struct mvpp2 *priv, unsigned short l3_cast)
 		return -EINVAL;
 	}
 
-	/* Finished: go to flowid generation */
-	mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_FLOWS);
-	mvpp2_prs_sram_bits_set(&pe, MVPP2_PRS_SRAM_LU_GEN_BIT, 1);
+	/* Go again to ipv4 */
+	mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_IP4);
 
-	mvpp2_prs_tcam_ai_update(&pe, MVPP2_PRS_IPV4_DIP_AI_BIT,
+	mvpp2_prs_sram_ai_update(&pe, MVPP2_PRS_IPV4_DIP_AI_BIT,
 				 MVPP2_PRS_IPV4_DIP_AI_BIT);
+
+	/* Shift back to IPv4 proto */
+	mvpp2_prs_sram_shift_set(&pe, -12, MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD);
+
+	mvpp2_prs_tcam_ai_update(&pe, 0, MVPP2_PRS_IPV4_DIP_AI_BIT);
+
 	/* Unmask all ports */
 	mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK);
 
@@ -1425,8 +1431,9 @@ static int mvpp2_prs_etype_init(struct mvpp2 *priv)
 	mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_IP4);
 	mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP4,
 				 MVPP2_PRS_RI_L3_PROTO_MASK);
-	/* Skip eth_type + 4 bytes of IP header */
-	mvpp2_prs_sram_shift_set(&pe, MVPP2_ETH_TYPE_LEN + 4,
+	/* goto ipv4 dest-address (skip eth_type + IP-header-size - 4) */
+	mvpp2_prs_sram_shift_set(&pe, MVPP2_ETH_TYPE_LEN +
+				 sizeof(struct iphdr) - 4,
 				 MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD);
 	/* Set L3 offset */
 	mvpp2_prs_sram_offset_set(&pe, MVPP2_PRS_SRAM_UDF_TYPE_L3,
@@ -1630,8 +1637,9 @@ static int mvpp2_prs_pppoe_init(struct mvpp2 *priv)
 	mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_IP4);
 	mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP4_OPT,
 				 MVPP2_PRS_RI_L3_PROTO_MASK);
-	/* Skip eth_type + 4 bytes of IP header */
-	mvpp2_prs_sram_shift_set(&pe, MVPP2_ETH_TYPE_LEN + 4,
+	/* goto ipv4 dest-address (skip eth_type + IP-header-size - 4) */
+	mvpp2_prs_sram_shift_set(&pe, MVPP2_ETH_TYPE_LEN +
+				 sizeof(struct iphdr) - 4,
 				 MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD);
 	/* Set L3 offset */
 	mvpp2_prs_sram_offset_set(&pe, MVPP2_PRS_SRAM_UDF_TYPE_L3,
@@ -1761,19 +1769,20 @@ static int mvpp2_prs_ip4_init(struct mvpp2 *priv)
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP4);
 	pe.index = MVPP2_PE_IP4_PROTO_UN;
 
-	/* Set next lu to IPv4 */
-	mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_IP4);
-	mvpp2_prs_sram_shift_set(&pe, 12, MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD);
+	/* Finished: go to flowid generation */
+	mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_FLOWS);
+	mvpp2_prs_sram_bits_set(&pe, MVPP2_PRS_SRAM_LU_GEN_BIT, 1);
+
 	/* Set L4 offset */
 	mvpp2_prs_sram_offset_set(&pe, MVPP2_PRS_SRAM_UDF_TYPE_L4,
 				  sizeof(struct iphdr) - 4,
 				  MVPP2_PRS_SRAM_OP_SEL_UDF_ADD);
-	mvpp2_prs_sram_ai_update(&pe, MVPP2_PRS_IPV4_DIP_AI_BIT,
-				 MVPP2_PRS_IPV4_DIP_AI_BIT);
+	mvpp2_prs_sram_ai_update(&pe, 0, MVPP2_PRS_IPV4_DIP_AI_BIT);
 	mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L4_OTHER,
 				 MVPP2_PRS_RI_L4_PROTO_MASK);
 
-	mvpp2_prs_tcam_ai_update(&pe, 0, MVPP2_PRS_IPV4_DIP_AI_BIT);
+	mvpp2_prs_tcam_ai_update(&pe, MVPP2_PRS_IPV4_DIP_AI_BIT,
+				 MVPP2_PRS_IPV4_DIP_AI_BIT);
 	/* Unmask all ports */
 	mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK);
 
@@ -1786,14 +1795,19 @@ static int mvpp2_prs_ip4_init(struct mvpp2 *priv)
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_IP4);
 	pe.index = MVPP2_PE_IP4_ADDR_UN;
 
-	/* Finished: go to flowid generation */
-	mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_FLOWS);
-	mvpp2_prs_sram_bits_set(&pe, MVPP2_PRS_SRAM_LU_GEN_BIT, 1);
+	/* Go again to ipv4 */
+	mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_IP4);
+
+	mvpp2_prs_sram_ai_update(&pe, MVPP2_PRS_IPV4_DIP_AI_BIT,
+				 MVPP2_PRS_IPV4_DIP_AI_BIT);
+
+	/* Shift back to IPv4 proto */
+	mvpp2_prs_sram_shift_set(&pe, -12, MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD);
+
 	mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_UCAST,
 				 MVPP2_PRS_RI_L3_ADDR_MASK);
+	mvpp2_prs_tcam_ai_update(&pe, 0, MVPP2_PRS_IPV4_DIP_AI_BIT);
 
-	mvpp2_prs_tcam_ai_update(&pe, MVPP2_PRS_IPV4_DIP_AI_BIT,
-				 MVPP2_PRS_IPV4_DIP_AI_BIT);
 	/* Unmask all ports */
 	mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK);