bnx2x: use FW 7.8.17

Update appropriate HSI files and adapt driver accordingly.
Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
Signed-off-by: Yuval Mintz <yuvalmin@broadcom.com>
Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/broadcom/bnx2x/bnx2x.h

@@ -729,7 +729,7 @@ struct bnx2x_fastpath {
 #define SKB_CS(skb)		(*(u16 *)(skb_transport_header(skb) + \
 					  skb->csum_offset))
 
-#define pbd_tcp_flags(skb)	(ntohl(tcp_flag_word(tcp_hdr(skb)))>>16 & 0xff)
+#define pbd_tcp_flags(tcp_hdr)	(ntohl(tcp_flag_word(tcp_hdr))>>16 & 0xff)
 
 #define XMIT_PLAIN			0
 #define XMIT_CSUM_V4			0x1

drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c

@@ -3086,11 +3086,11 @@ int bnx2x_poll(struct napi_struct *napi, int budget)
  * to ease the pain of our fellow microcode engineers
  * we use one mapping for both BDs
  */
-static noinline u16 bnx2x_tx_split(struct bnx2x *bp,
+static u16 bnx2x_tx_split(struct bnx2x *bp,
 			  struct bnx2x_fp_txdata *txdata,
 			  struct sw_tx_bd *tx_buf,
 			  struct eth_tx_start_bd **tx_bd, u16 hlen,
-				   u16 bd_prod, int nbd)
+			  u16 bd_prod)
 {
 	struct eth_tx_start_bd *h_tx_bd = *tx_bd;
 	struct eth_tx_bd *d_tx_bd;
@@ -3098,11 +3098,10 @@ static noinline u16 bnx2x_tx_split(struct bnx2x *bp,
 	int old_len = le16_to_cpu(h_tx_bd->nbytes);
 
 	/* first fix first BD */
-	h_tx_bd->nbd = cpu_to_le16(nbd);
 	h_tx_bd->nbytes = cpu_to_le16(hlen);
 
-	DP(NETIF_MSG_TX_QUEUED,	"TSO split header size is %d (%x:%x) nbd %d\n",
-	   h_tx_bd->nbytes, h_tx_bd->addr_hi, h_tx_bd->addr_lo, h_tx_bd->nbd);
+	DP(NETIF_MSG_TX_QUEUED,	"TSO split header size is %d (%x:%x)\n",
+	   h_tx_bd->nbytes, h_tx_bd->addr_hi, h_tx_bd->addr_lo);
 
 	/* now get a new data BD
 	 * (after the pbd) and fill it */
@@ -3131,7 +3130,7 @@ static noinline u16 bnx2x_tx_split(struct bnx2x *bp,
 
 #define bswab32(b32) ((__force __le32) swab32((__force __u32) (b32)))
 #define bswab16(b16) ((__force __le16) swab16((__force __u16) (b16)))
-static inline __le16 bnx2x_csum_fix(unsigned char *t_header, u16 csum, s8 fix)
+static __le16 bnx2x_csum_fix(unsigned char *t_header, u16 csum, s8 fix)
 {
 	__sum16 tsum = (__force __sum16) csum;
 
@@ -3146,7 +3145,7 @@ static inline __le16 bnx2x_csum_fix(unsigned char *t_header, u16 csum, s8 fix)
 	return bswab16(tsum);
 }
 
-static inline u32 bnx2x_xmit_type(struct bnx2x *bp, struct sk_buff *skb)
+static u32 bnx2x_xmit_type(struct bnx2x *bp, struct sk_buff *skb)
 {
 	u32 rc;
 
@@ -3254,7 +3253,7 @@ static int bnx2x_pkt_req_lin(struct bnx2x *bp, struct sk_buff *skb,
 }
 #endif
 
-static inline void bnx2x_set_pbd_gso_e2(struct sk_buff *skb, u32 *parsing_data,
+static void bnx2x_set_pbd_gso_e2(struct sk_buff *skb, u32 *parsing_data,
 				 u32 xmit_type)
 {
 	*parsing_data |= (skb_shinfo(skb)->gso_size <<
@@ -3272,13 +3271,13 @@ static inline void bnx2x_set_pbd_gso_e2(struct sk_buff *skb, u32 *parsing_data,
  * @pbd:	parse BD
  * @xmit_type:	xmit flags
  */
-static inline void bnx2x_set_pbd_gso(struct sk_buff *skb,
+static void bnx2x_set_pbd_gso(struct sk_buff *skb,
 			      struct eth_tx_parse_bd_e1x *pbd,
 			      u32 xmit_type)
 {
 	pbd->lso_mss = cpu_to_le16(skb_shinfo(skb)->gso_size);
 	pbd->tcp_send_seq = bswab32(tcp_hdr(skb)->seq);
-	pbd->tcp_flags = pbd_tcp_flags(skb);
+	pbd->tcp_flags = pbd_tcp_flags(tcp_hdr(skb));
 
 	if (xmit_type & XMIT_GSO_V4) {
 		pbd->ip_id = bswab16(ip_hdr(skb)->id);
@@ -3305,15 +3304,15 @@ static inline void bnx2x_set_pbd_gso(struct sk_buff *skb,
  * @parsing_data:	data to be updated
  * @xmit_type:		xmit flags
  *
- * 57712 related
+ * 57712/578xx related
  */
-static inline  u8 bnx2x_set_pbd_csum_e2(struct bnx2x *bp, struct sk_buff *skb,
+static u8 bnx2x_set_pbd_csum_e2(struct bnx2x *bp, struct sk_buff *skb,
 				u32 *parsing_data, u32 xmit_type)
 {
 	*parsing_data |=
 		((((u8 *)skb_transport_header(skb) - skb->data) >> 1) <<
-		ETH_TX_PARSE_BD_E2_TCP_HDR_START_OFFSET_W_SHIFT) &
-		ETH_TX_PARSE_BD_E2_TCP_HDR_START_OFFSET_W;
+		ETH_TX_PARSE_BD_E2_L4_HDR_START_OFFSET_W_SHIFT) &
+		ETH_TX_PARSE_BD_E2_L4_HDR_START_OFFSET_W;
 
 	if (xmit_type & XMIT_CSUM_TCP) {
 		*parsing_data |= ((tcp_hdrlen(skb) / 4) <<
@@ -3328,17 +3327,14 @@ static inline  u8 bnx2x_set_pbd_csum_e2(struct bnx2x *bp, struct sk_buff *skb,
 	return skb_transport_header(skb) + sizeof(struct udphdr) - skb->data;
 }
 
-static inline void bnx2x_set_sbd_csum(struct bnx2x *bp, struct sk_buff *skb,
-	struct eth_tx_start_bd *tx_start_bd, u32 xmit_type)
+static void bnx2x_set_sbd_csum(struct bnx2x *bp, struct sk_buff *skb,
+			       struct eth_tx_start_bd *tx_start_bd,
+			       u32 xmit_type)
 {
 	tx_start_bd->bd_flags.as_bitfield |= ETH_TX_BD_FLAGS_L4_CSUM;
 
-	if (xmit_type & XMIT_CSUM_V4)
-		tx_start_bd->bd_flags.as_bitfield |=
-					ETH_TX_BD_FLAGS_IP_CSUM;
-	else
-		tx_start_bd->bd_flags.as_bitfield |=
-					ETH_TX_BD_FLAGS_IPV6;
+	if (xmit_type & XMIT_CSUM_V6)
+		tx_start_bd->bd_flags.as_bitfield |= ETH_TX_BD_FLAGS_IPV6;
 
 	if (!(xmit_type & XMIT_CSUM_TCP))
 		tx_start_bd->bd_flags.as_bitfield |= ETH_TX_BD_FLAGS_IS_UDP;
@@ -3352,7 +3348,7 @@ static inline void bnx2x_set_sbd_csum(struct bnx2x *bp, struct sk_buff *skb,
  * @pbd:	parse BD to be updated
  * @xmit_type:	xmit flags
  */
-static inline u8 bnx2x_set_pbd_csum(struct bnx2x *bp, struct sk_buff *skb,
+static u8 bnx2x_set_pbd_csum(struct bnx2x *bp, struct sk_buff *skb,
 			     struct eth_tx_parse_bd_e1x *pbd,
 			     u32 xmit_type)
 {
@@ -3482,7 +3478,7 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			mac_type = MULTICAST_ADDRESS;
 	}
 
-#if (MAX_SKB_FRAGS >= MAX_FETCH_BD - 3)
+#if (MAX_SKB_FRAGS >= MAX_FETCH_BD - BDS_PER_TX_PKT)
 	/* First, check if we need to linearize the skb (due to FW
 	   restrictions). No need to check fragmentation if page size > 8K
 	   (there will be no violation to FW restrictions) */
@@ -3530,12 +3526,9 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	first_bd = tx_start_bd;
 
 	tx_start_bd->bd_flags.as_bitfield = ETH_TX_BD_FLAGS_START_BD;
-	SET_FLAG(tx_start_bd->general_data,
-		 ETH_TX_START_BD_PARSE_NBDS,
-		 0);
 
-	/* header nbd */
-	SET_FLAG(tx_start_bd->general_data, ETH_TX_START_BD_HDR_NBDS, 1);
+	/* header nbd: indirectly zero other flags! */
+	tx_start_bd->general_data = 1 << ETH_TX_START_BD_HDR_NBDS_SHIFT;
 
 	/* remember the first BD of the packet */
 	tx_buf->first_bd = txdata->tx_bd_prod;
@@ -3555,18 +3548,15 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		/* when transmitting in a vf, start bd must hold the ethertype
 		 * for fw to enforce it
 		 */
-#ifndef BNX2X_STOP_ON_ERROR
-		if (IS_VF(bp)) {
-#endif
+		if (IS_VF(bp))
 			tx_start_bd->vlan_or_ethertype =
 				cpu_to_le16(ntohs(eth->h_proto));
-#ifndef BNX2X_STOP_ON_ERROR
-		} else {
+		else
 			/* used by FW for packet accounting */
 			tx_start_bd->vlan_or_ethertype = cpu_to_le16(pkt_prod);
 	}
-#endif
-	}
+
+	nbd = 2; /* start_bd + pbd + frags (updated when pages are mapped) */
 
 	/* turn on parsing and get a BD */
 	bd_prod = TX_BD(NEXT_TX_IDX(bd_prod));
@@ -3579,21 +3569,22 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		memset(pbd_e2, 0, sizeof(struct eth_tx_parse_bd_e2));
 		/* Set PBD in checksum offload case */
 		if (xmit_type & XMIT_CSUM)
+			/* Set PBD in checksum offload case w/o encapsulation */
 			hlen = bnx2x_set_pbd_csum_e2(bp, skb,
 						     &pbd_e2_parsing_data,
 						     xmit_type);
 
-		if (IS_MF_SI(bp) || IS_VF(bp)) {
-			/* fill in the MAC addresses in the PBD - for local
-			 * switching
-			 */
-			bnx2x_set_fw_mac_addr(&pbd_e2->src_mac_addr_hi,
-					      &pbd_e2->src_mac_addr_mid,
-					      &pbd_e2->src_mac_addr_lo,
+		/* Add the macs to the parsing BD this is a vf */
+		if (IS_VF(bp)) {
+			/* override GRE parameters in BD */
+			bnx2x_set_fw_mac_addr(&pbd_e2->data.mac_addr.src_hi,
+					      &pbd_e2->data.mac_addr.src_mid,
+					      &pbd_e2->data.mac_addr.src_lo,
 					      eth->h_source);
-			bnx2x_set_fw_mac_addr(&pbd_e2->dst_mac_addr_hi,
-					      &pbd_e2->dst_mac_addr_mid,
-					      &pbd_e2->dst_mac_addr_lo,
+
+			bnx2x_set_fw_mac_addr(&pbd_e2->data.mac_addr.dst_hi,
+					      &pbd_e2->data.mac_addr.dst_mid,
+					      &pbd_e2->data.mac_addr.dst_lo,
 					      eth->h_dest);
 		}
 
@@ -3615,14 +3606,13 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Setup the data pointer of the first BD of the packet */
 	tx_start_bd->addr_hi = cpu_to_le32(U64_HI(mapping));
 	tx_start_bd->addr_lo = cpu_to_le32(U64_LO(mapping));
-	nbd = 2; /* start_bd + pbd + frags (updated when pages are mapped) */
 	tx_start_bd->nbytes = cpu_to_le16(skb_headlen(skb));
 	pkt_size = tx_start_bd->nbytes;
 
 	DP(NETIF_MSG_TX_QUEUED,
-	   "first bd @%p  addr (%x:%x)  nbd %d  nbytes %d  flags %x  vlan %x\n",
+	   "first bd @%p  addr (%x:%x)  nbytes %d  flags %x  vlan %x\n",
 	   tx_start_bd, tx_start_bd->addr_hi, tx_start_bd->addr_lo,
-	   le16_to_cpu(tx_start_bd->nbd), le16_to_cpu(tx_start_bd->nbytes),
+	   le16_to_cpu(tx_start_bd->nbytes),
 	   tx_start_bd->bd_flags.as_bitfield,
 	   le16_to_cpu(tx_start_bd->vlan_or_ethertype));
 
@@ -3635,10 +3625,12 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		tx_start_bd->bd_flags.as_bitfield |= ETH_TX_BD_FLAGS_SW_LSO;
 
-		if (unlikely(skb_headlen(skb) > hlen))
+		if (unlikely(skb_headlen(skb) > hlen)) {
+			nbd++;
 			bd_prod = bnx2x_tx_split(bp, txdata, tx_buf,
 						 &tx_start_bd, hlen,
-						 bd_prod, ++nbd);
+						 bd_prod);
+		}
 		if (!CHIP_IS_E1x(bp))
 			bnx2x_set_pbd_gso_e2(skb, &pbd_e2_parsing_data,
 					     xmit_type);
@@ -3728,9 +3720,13 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (pbd_e2)
 		DP(NETIF_MSG_TX_QUEUED,
 		   "PBD (E2) @%p  dst %x %x %x src %x %x %x parsing_data %x\n",
-		   pbd_e2, pbd_e2->dst_mac_addr_hi, pbd_e2->dst_mac_addr_mid,
-		   pbd_e2->dst_mac_addr_lo, pbd_e2->src_mac_addr_hi,
-		   pbd_e2->src_mac_addr_mid, pbd_e2->src_mac_addr_lo,
+		   pbd_e2,
+		   pbd_e2->data.mac_addr.dst_hi,
+		   pbd_e2->data.mac_addr.dst_mid,
+		   pbd_e2->data.mac_addr.dst_lo,
+		   pbd_e2->data.mac_addr.src_hi,
+		   pbd_e2->data.mac_addr.src_mid,
+		   pbd_e2->data.mac_addr.src_lo,
 		   pbd_e2->parsing_data);
 	DP(NETIF_MSG_TX_QUEUED, "doorbell: nbd %d  bd %u\n", nbd, bd_prod);
 

drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h

@@ -30,31 +30,31 @@
 	* IRO[138].m2) + ((sbId) * IRO[138].m3))
 #define CSTORM_IGU_MODE_OFFSET (IRO[157].base)
 #define CSTORM_ISCSI_CQ_SIZE_OFFSET(pfId) \
-	(IRO[316].base + ((pfId) * IRO[316].m1))
-#define CSTORM_ISCSI_CQ_SQN_SIZE_OFFSET(pfId) \
 	(IRO[317].base + ((pfId) * IRO[317].m1))
+#define CSTORM_ISCSI_CQ_SQN_SIZE_OFFSET(pfId) \
+	(IRO[318].base + ((pfId) * IRO[318].m1))
 #define CSTORM_ISCSI_EQ_CONS_OFFSET(pfId, iscsiEqId) \
-	(IRO[309].base + ((pfId) * IRO[309].m1) + ((iscsiEqId) * IRO[309].m2))
+	(IRO[310].base + ((pfId) * IRO[310].m1) + ((iscsiEqId) * IRO[310].m2))
 #define CSTORM_ISCSI_EQ_NEXT_EQE_ADDR_OFFSET(pfId, iscsiEqId) \
-	(IRO[311].base + ((pfId) * IRO[311].m1) + ((iscsiEqId) * IRO[311].m2))
+	(IRO[312].base + ((pfId) * IRO[312].m1) + ((iscsiEqId) * IRO[312].m2))
 #define CSTORM_ISCSI_EQ_NEXT_PAGE_ADDR_OFFSET(pfId, iscsiEqId) \
-	(IRO[310].base + ((pfId) * IRO[310].m1) + ((iscsiEqId) * IRO[310].m2))
+	(IRO[311].base + ((pfId) * IRO[311].m1) + ((iscsiEqId) * IRO[311].m2))
 #define CSTORM_ISCSI_EQ_NEXT_PAGE_ADDR_VALID_OFFSET(pfId, iscsiEqId) \
-	(IRO[312].base + ((pfId) * IRO[312].m1) + ((iscsiEqId) * IRO[312].m2))
+	(IRO[313].base + ((pfId) * IRO[313].m1) + ((iscsiEqId) * IRO[313].m2))
 #define CSTORM_ISCSI_EQ_PROD_OFFSET(pfId, iscsiEqId) \
-	(IRO[308].base + ((pfId) * IRO[308].m1) + ((iscsiEqId) * IRO[308].m2))
+	(IRO[309].base + ((pfId) * IRO[309].m1) + ((iscsiEqId) * IRO[309].m2))
 #define CSTORM_ISCSI_EQ_SB_INDEX_OFFSET(pfId, iscsiEqId) \
-	(IRO[314].base + ((pfId) * IRO[314].m1) + ((iscsiEqId) * IRO[314].m2))
+	(IRO[315].base + ((pfId) * IRO[315].m1) + ((iscsiEqId) * IRO[315].m2))
 #define CSTORM_ISCSI_EQ_SB_NUM_OFFSET(pfId, iscsiEqId) \
-	(IRO[313].base + ((pfId) * IRO[313].m1) + ((iscsiEqId) * IRO[313].m2))
+	(IRO[314].base + ((pfId) * IRO[314].m1) + ((iscsiEqId) * IRO[314].m2))
 #define CSTORM_ISCSI_HQ_SIZE_OFFSET(pfId) \
-	(IRO[315].base + ((pfId) * IRO[315].m1))
+	(IRO[316].base + ((pfId) * IRO[316].m1))
 #define CSTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfId) \
-	(IRO[307].base + ((pfId) * IRO[307].m1))
+	(IRO[308].base + ((pfId) * IRO[308].m1))
 #define CSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfId) \
-	(IRO[306].base + ((pfId) * IRO[306].m1))
+	(IRO[307].base + ((pfId) * IRO[307].m1))
 #define CSTORM_ISCSI_PAGE_SIZE_OFFSET(pfId) \
-	(IRO[305].base + ((pfId) * IRO[305].m1))
+	(IRO[306].base + ((pfId) * IRO[306].m1))
 #define CSTORM_RECORD_SLOW_PATH_OFFSET(funcId) \
 	(IRO[151].base + ((funcId) * IRO[151].m1))
 #define CSTORM_SP_STATUS_BLOCK_DATA_OFFSET(pfId) \
@@ -114,7 +114,7 @@
 #define TSTORM_ISCSI_RQ_SIZE_OFFSET(pfId) \
 	(IRO[268].base + ((pfId) * IRO[268].m1))
 #define TSTORM_ISCSI_TCP_LOCAL_ADV_WND_OFFSET(pfId) \
-	(IRO[277].base + ((pfId) * IRO[277].m1))
+	(IRO[278].base + ((pfId) * IRO[278].m1))
 #define TSTORM_ISCSI_TCP_VARS_FLAGS_OFFSET(pfId) \
 	(IRO[264].base + ((pfId) * IRO[264].m1))
 #define TSTORM_ISCSI_TCP_VARS_LSB_LOCAL_MAC_ADDR_OFFSET(pfId) \
@@ -136,35 +136,32 @@
 #define USTORM_ASSERT_LIST_INDEX_OFFSET	(IRO[177].base)
 #define USTORM_ASSERT_LIST_OFFSET(assertListEntry) \
 	(IRO[176].base + ((assertListEntry) * IRO[176].m1))
-#define USTORM_CQE_PAGE_NEXT_OFFSET(portId, clientId) \
-	(IRO[205].base + ((portId) * IRO[205].m1) + ((clientId) * \
-	IRO[205].m2))
 #define USTORM_ETH_PAUSE_ENABLED_OFFSET(portId) \
 	(IRO[183].base + ((portId) * IRO[183].m1))
 #define USTORM_FCOE_EQ_PROD_OFFSET(pfId) \
-	(IRO[318].base + ((pfId) * IRO[318].m1))
+	(IRO[319].base + ((pfId) * IRO[319].m1))
 #define USTORM_FUNC_EN_OFFSET(funcId) \
 	(IRO[178].base + ((funcId) * IRO[178].m1))
 #define USTORM_ISCSI_CQ_SIZE_OFFSET(pfId) \
-	(IRO[282].base + ((pfId) * IRO[282].m1))
-#define USTORM_ISCSI_CQ_SQN_SIZE_OFFSET(pfId) \
 	(IRO[283].base + ((pfId) * IRO[283].m1))
+#define USTORM_ISCSI_CQ_SQN_SIZE_OFFSET(pfId) \
+	(IRO[284].base + ((pfId) * IRO[284].m1))
 #define USTORM_ISCSI_ERROR_BITMAP_OFFSET(pfId) \
-	(IRO[287].base + ((pfId) * IRO[287].m1))
+	(IRO[288].base + ((pfId) * IRO[288].m1))
 #define USTORM_ISCSI_GLOBAL_BUF_PHYS_ADDR_OFFSET(pfId) \
-	(IRO[284].base + ((pfId) * IRO[284].m1))
+	(IRO[285].base + ((pfId) * IRO[285].m1))
 #define USTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfId) \
-	(IRO[280].base + ((pfId) * IRO[280].m1))
+	(IRO[281].base + ((pfId) * IRO[281].m1))
 #define USTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfId) \
-	(IRO[279].base + ((pfId) * IRO[279].m1))
+	(IRO[280].base + ((pfId) * IRO[280].m1))
 #define USTORM_ISCSI_PAGE_SIZE_OFFSET(pfId) \
-	(IRO[278].base + ((pfId) * IRO[278].m1))
+	(IRO[279].base + ((pfId) * IRO[279].m1))
 #define USTORM_ISCSI_R2TQ_SIZE_OFFSET(pfId) \
-	(IRO[281].base + ((pfId) * IRO[281].m1))
+	(IRO[282].base + ((pfId) * IRO[282].m1))
 #define USTORM_ISCSI_RQ_BUFFER_SIZE_OFFSET(pfId) \
-	(IRO[285].base + ((pfId) * IRO[285].m1))
-#define USTORM_ISCSI_RQ_SIZE_OFFSET(pfId) \
 	(IRO[286].base + ((pfId) * IRO[286].m1))
+#define USTORM_ISCSI_RQ_SIZE_OFFSET(pfId) \
+	(IRO[287].base + ((pfId) * IRO[287].m1))
 #define USTORM_MEM_WORKAROUND_ADDRESS_OFFSET(pfId) \
 	(IRO[182].base + ((pfId) * IRO[182].m1))
 #define USTORM_RECORD_SLOW_PATH_OFFSET(funcId) \
@@ -190,39 +187,39 @@
 #define XSTORM_FUNC_EN_OFFSET(funcId) \
 	(IRO[47].base + ((funcId) * IRO[47].m1))
 #define XSTORM_ISCSI_HQ_SIZE_OFFSET(pfId) \
-	(IRO[295].base + ((pfId) * IRO[295].m1))
+	(IRO[296].base + ((pfId) * IRO[296].m1))
 #define XSTORM_ISCSI_LOCAL_MAC_ADDR0_OFFSET(pfId) \
-	(IRO[298].base + ((pfId) * IRO[298].m1))
-#define XSTORM_ISCSI_LOCAL_MAC_ADDR1_OFFSET(pfId) \
 	(IRO[299].base + ((pfId) * IRO[299].m1))
-#define XSTORM_ISCSI_LOCAL_MAC_ADDR2_OFFSET(pfId) \
+#define XSTORM_ISCSI_LOCAL_MAC_ADDR1_OFFSET(pfId) \
 	(IRO[300].base + ((pfId) * IRO[300].m1))
-#define XSTORM_ISCSI_LOCAL_MAC_ADDR3_OFFSET(pfId) \
+#define XSTORM_ISCSI_LOCAL_MAC_ADDR2_OFFSET(pfId) \
 	(IRO[301].base + ((pfId) * IRO[301].m1))
-#define XSTORM_ISCSI_LOCAL_MAC_ADDR4_OFFSET(pfId) \
+#define XSTORM_ISCSI_LOCAL_MAC_ADDR3_OFFSET(pfId) \
 	(IRO[302].base + ((pfId) * IRO[302].m1))
-#define XSTORM_ISCSI_LOCAL_MAC_ADDR5_OFFSET(pfId) \
+#define XSTORM_ISCSI_LOCAL_MAC_ADDR4_OFFSET(pfId) \
 	(IRO[303].base + ((pfId) * IRO[303].m1))
-#define XSTORM_ISCSI_LOCAL_VLAN_OFFSET(pfId) \
+#define XSTORM_ISCSI_LOCAL_MAC_ADDR5_OFFSET(pfId) \
 	(IRO[304].base + ((pfId) * IRO[304].m1))
+#define XSTORM_ISCSI_LOCAL_VLAN_OFFSET(pfId) \
+	(IRO[305].base + ((pfId) * IRO[305].m1))
 #define XSTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfId) \
-	(IRO[294].base + ((pfId) * IRO[294].m1))
+	(IRO[295].base + ((pfId) * IRO[295].m1))
 #define XSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfId) \
-	(IRO[293].base + ((pfId) * IRO[293].m1))
+	(IRO[294].base + ((pfId) * IRO[294].m1))
 #define XSTORM_ISCSI_PAGE_SIZE_OFFSET(pfId) \
-	(IRO[292].base + ((pfId) * IRO[292].m1))
+	(IRO[293].base + ((pfId) * IRO[293].m1))
 #define XSTORM_ISCSI_R2TQ_SIZE_OFFSET(pfId) \
-	(IRO[297].base + ((pfId) * IRO[297].m1))
+	(IRO[298].base + ((pfId) * IRO[298].m1))
 #define XSTORM_ISCSI_SQ_SIZE_OFFSET(pfId) \
-	(IRO[296].base + ((pfId) * IRO[296].m1))
+	(IRO[297].base + ((pfId) * IRO[297].m1))
 #define XSTORM_ISCSI_TCP_VARS_ADV_WND_SCL_OFFSET(pfId) \
-	(IRO[291].base + ((pfId) * IRO[291].m1))
+	(IRO[292].base + ((pfId) * IRO[292].m1))
 #define XSTORM_ISCSI_TCP_VARS_FLAGS_OFFSET(pfId) \
-	(IRO[290].base + ((pfId) * IRO[290].m1))
+	(IRO[291].base + ((pfId) * IRO[291].m1))
 #define XSTORM_ISCSI_TCP_VARS_TOS_OFFSET(pfId) \
-	(IRO[289].base + ((pfId) * IRO[289].m1))
+	(IRO[290].base + ((pfId) * IRO[290].m1))
 #define XSTORM_ISCSI_TCP_VARS_TTL_OFFSET(pfId) \
-	(IRO[288].base + ((pfId) * IRO[288].m1))
+	(IRO[289].base + ((pfId) * IRO[289].m1))
 #define XSTORM_RATE_SHAPING_PER_VN_VARS_OFFSET(pfId) \
 	(IRO[44].base + ((pfId) * IRO[44].m1))
 #define XSTORM_RECORD_SLOW_PATH_OFFSET(funcId) \

drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c

@@ -2961,6 +2961,7 @@ static unsigned long bnx2x_get_common_flags(struct bnx2x *bp,
 	if (zero_stats)
 		__set_bit(BNX2X_Q_FLG_ZERO_STATS, &flags);
 
+	__set_bit(BNX2X_Q_FLG_PCSUM_ON_PKT, &flags);
 
 #ifdef BNX2X_STOP_ON_ERROR
 	__set_bit(BNX2X_Q_FLG_TX_SEC, &flags);

drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c

@@ -476,7 +476,8 @@ static int bnx2x_check_mac_add(struct bnx2x *bp,
 
 	/* Check if a requested MAC already exists */
 	list_for_each_entry(pos, &o->head, link)
-		if (!memcmp(data->mac.mac, pos->u.mac.mac, ETH_ALEN))
+		if (!memcmp(data->mac.mac, pos->u.mac.mac, ETH_ALEN) &&
+		    (data->mac.is_inner_mac == pos->u.mac.is_inner_mac))
 			return -EEXIST;
 
 	return 0;
@@ -509,7 +510,9 @@ static int bnx2x_check_vlan_mac_add(struct bnx2x *bp,
 	list_for_each_entry(pos, &o->head, link)
 		if ((data->vlan_mac.vlan == pos->u.vlan_mac.vlan) &&
 		    (!memcmp(data->vlan_mac.mac, pos->u.vlan_mac.mac,
-			     ETH_ALEN)))
+				  ETH_ALEN)) &&
+		    (data->vlan_mac.is_inner_mac ==
+		     pos->u.vlan_mac.is_inner_mac))
 			return -EEXIST;
 
 	return 0;
@@ -527,7 +530,8 @@ static struct bnx2x_vlan_mac_registry_elem *
 	DP(BNX2X_MSG_SP, "Checking MAC %pM for DEL command\n", data->mac.mac);
 
 	list_for_each_entry(pos, &o->head, link)
-		if (!memcmp(data->mac.mac, pos->u.mac.mac, ETH_ALEN))
+		if ((!memcmp(data->mac.mac, pos->u.mac.mac, ETH_ALEN)) &&
+		    (data->mac.is_inner_mac == pos->u.mac.is_inner_mac))
 			return pos;
 
 	return NULL;
@@ -562,7 +566,9 @@ static struct bnx2x_vlan_mac_registry_elem *
 	list_for_each_entry(pos, &o->head, link)
 		if ((data->vlan_mac.vlan == pos->u.vlan_mac.vlan) &&
 		    (!memcmp(data->vlan_mac.mac, pos->u.vlan_mac.mac,
-			     ETH_ALEN)))
+			     ETH_ALEN)) &&
+		    (data->vlan_mac.is_inner_mac ==
+		     pos->u.vlan_mac.is_inner_mac))
 			return pos;
 
 	return NULL;
@@ -759,6 +765,8 @@ static void bnx2x_set_one_mac_e2(struct bnx2x *bp,
 	bnx2x_set_fw_mac_addr(&rule_entry->mac.mac_msb,
 			      &rule_entry->mac.mac_mid,
 			      &rule_entry->mac.mac_lsb, mac);
+	rule_entry->mac.inner_mac =
+		cpu_to_le16(elem->cmd_data.vlan_mac.u.mac.is_inner_mac);
 
 	/* MOVE: Add a rule that will add this MAC to the target Queue */
 	if (cmd == BNX2X_VLAN_MAC_MOVE) {
@@ -775,6 +783,9 @@ static void bnx2x_set_one_mac_e2(struct bnx2x *bp,
 		bnx2x_set_fw_mac_addr(&rule_entry->mac.mac_msb,
 				      &rule_entry->mac.mac_mid,
 				      &rule_entry->mac.mac_lsb, mac);
+		rule_entry->mac.inner_mac =
+			cpu_to_le16(elem->cmd_data.vlan_mac.
+						u.mac.is_inner_mac);
 	}
 
 	/* Set the ramrod data header */
@@ -963,7 +974,8 @@ static void bnx2x_set_one_vlan_mac_e2(struct bnx2x *bp,
 	bnx2x_set_fw_mac_addr(&rule_entry->pair.mac_msb,
 			      &rule_entry->pair.mac_mid,
 			      &rule_entry->pair.mac_lsb, mac);
-
+	rule_entry->pair.inner_mac =
+		cpu_to_le16(elem->cmd_data.vlan_mac.u.vlan_mac.is_inner_mac);
 	/* MOVE: Add a rule that will add this MAC to the target Queue */
 	if (cmd == BNX2X_VLAN_MAC_MOVE) {
 		rule_entry++;
@@ -980,6 +992,9 @@ static void bnx2x_set_one_vlan_mac_e2(struct bnx2x *bp,
 		bnx2x_set_fw_mac_addr(&rule_entry->pair.mac_msb,
 				      &rule_entry->pair.mac_mid,
 				      &rule_entry->pair.mac_lsb, mac);
+		rule_entry->pair.inner_mac =
+			cpu_to_le16(elem->cmd_data.vlan_mac.u.
+						vlan_mac.is_inner_mac);
 	}
 
 	/* Set the ramrod data header */
@@ -4417,6 +4432,10 @@ static void bnx2x_q_fill_init_tx_data(struct bnx2x_queue_sp_obj *o,
 	tx_data->force_default_pri_flg =
 		test_bit(BNX2X_Q_FLG_FORCE_DEFAULT_PRI, flags);
 
+	tx_data->tunnel_non_lso_pcsum_location =
+		test_bit(BNX2X_Q_FLG_PCSUM_ON_PKT, flags) ? PCSUM_ON_PKT :
+								  PCSUM_ON_BD;
+
 	tx_data->tx_status_block_id = params->fw_sb_id;
 	tx_data->tx_sb_index_number = params->sb_cq_index;
 	tx_data->tss_leading_client_id = params->tss_leading_cl_id;

drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h

@@ -100,6 +100,7 @@ struct bnx2x_raw_obj {
 /************************* VLAN-MAC commands related parameters ***************/
 struct bnx2x_mac_ramrod_data {
 	u8 mac[ETH_ALEN];
+	u8 is_inner_mac;
 };
 
 struct bnx2x_vlan_ramrod_data {
@@ -108,6 +109,7 @@ struct bnx2x_vlan_ramrod_data {
 
 struct bnx2x_vlan_mac_ramrod_data {
 	u8 mac[ETH_ALEN];
+	u8 is_inner_mac;
 	u16 vlan;
 };
 
@@ -825,7 +827,8 @@ enum {
 	BNX2X_Q_FLG_TX_SEC,
 	BNX2X_Q_FLG_ANTI_SPOOF,
 	BNX2X_Q_FLG_SILENT_VLAN_REM,
-	BNX2X_Q_FLG_FORCE_DEFAULT_PRI
+	BNX2X_Q_FLG_FORCE_DEFAULT_PRI,
+	BNX2X_Q_FLG_PCSUM_ON_PKT
 };
 
 /* Queue type options: queue type may be a compination of below. */