bnx2x: Split the FP structure

This patch moves some fields out of the FP structure to different structures, in
order to minimize size of contigiuous memory allocated.

Signed-off-by: Barak Witkowski <barak@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 234517f..25d46c1 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -549,34 +549,23 @@
 				rx_calls;
 
 	/* TPA related */
-	struct bnx2x_agg_info	tpa_info[ETH_MAX_AGGREGATION_QUEUES_E1H_E2];
+	struct bnx2x_agg_info	*tpa_info;
 	u8			disable_tpa;
 #ifdef BNX2X_STOP_ON_ERROR
 	u64			tpa_queue_used;
 #endif
-
-	struct tstorm_per_queue_stats old_tclient;
-	struct ustorm_per_queue_stats old_uclient;
-	struct xstorm_per_queue_stats old_xclient;
-	struct bnx2x_eth_q_stats eth_q_stats;
-	struct bnx2x_eth_q_stats_old eth_q_stats_old;
-
 	/* The size is calculated using the following:
 	     sizeof name field from netdev structure +
 	     4 ('-Xx-' string) +
 	     4 (for the digits and to make it DWORD aligned) */
 #define FP_NAME_SIZE		(sizeof(((struct net_device *)0)->name) + 8)
 	char			name[FP_NAME_SIZE];
-
-	/* MACs object */
-	struct bnx2x_vlan_mac_obj mac_obj;
-
-	/* Queue State object */
-	struct bnx2x_queue_sp_obj q_obj;
-
 };
 
-#define bnx2x_fp(bp, nr, var)		(bp->fp[nr].var)
+#define bnx2x_fp(bp, nr, var)	((bp)->fp[(nr)].var)
+#define bnx2x_sp_obj(bp, fp)	((bp)->sp_objs[(fp)->index])
+#define bnx2x_fp_stats(bp, fp)	(&((bp)->fp_stats[(fp)->index]))
+#define bnx2x_fp_qstats(bp, fp)	(&((bp)->fp_stats[(fp)->index].eth_q_stats))
 
 /* Use 2500 as a mini-jumbo MTU for FCoE */
 #define BNX2X_FCOE_MINI_JUMBO_MTU	2500
@@ -587,6 +576,8 @@
 				 FCOE_IDX_OFFSET)
 #define bnx2x_fcoe_fp(bp)	(&bp->fp[FCOE_IDX(bp)])
 #define bnx2x_fcoe(bp, var)	(bnx2x_fcoe_fp(bp)->var)
+#define bnx2x_fcoe_inner_sp_obj(bp)	(&bp->sp_objs[FCOE_IDX(bp)])
+#define bnx2x_fcoe_sp_obj(bp, var)	(bnx2x_fcoe_inner_sp_obj(bp)->var)
 #define bnx2x_fcoe_tx(bp, var)	(bnx2x_fcoe_fp(bp)-> \
 						txdata_ptr[FIRST_TX_COS_INDEX] \
 						->var)
@@ -1187,11 +1178,29 @@
 	struct list_head list;
 };
 
+struct bnx2x_sp_objs {
+	/* MACs object */
+	struct bnx2x_vlan_mac_obj mac_obj;
+
+	/* Queue State object */
+	struct bnx2x_queue_sp_obj q_obj;
+};
+
+struct bnx2x_fp_stats {
+	struct tstorm_per_queue_stats old_tclient;
+	struct ustorm_per_queue_stats old_uclient;
+	struct xstorm_per_queue_stats old_xclient;
+	struct bnx2x_eth_q_stats eth_q_stats;
+	struct bnx2x_eth_q_stats_old eth_q_stats_old;
+};
+
 struct bnx2x {
 	/* Fields used in the tx and intr/napi performance paths
 	 * are grouped together in the beginning of the structure
 	 */
 	struct bnx2x_fastpath	*fp;
+	struct bnx2x_sp_objs	*sp_objs;
+	struct bnx2x_fp_stats	*fp_stats;
 	struct bnx2x_fp_txdata	*bnx2x_txq;
 	int			bnx2x_txq_size;
 	void __iomem		*regview;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index cdd9ca4..413b665 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -47,6 +47,10 @@
 {
 	struct bnx2x_fastpath *from_fp = &bp->fp[from];
 	struct bnx2x_fastpath *to_fp = &bp->fp[to];
+	struct bnx2x_sp_objs *from_sp_objs = &bp->sp_objs[from];
+	struct bnx2x_sp_objs *to_sp_objs = &bp->sp_objs[to];
+	struct bnx2x_fp_stats *from_fp_stats = &bp->fp_stats[from];
+	struct bnx2x_fp_stats *to_fp_stats = &bp->fp_stats[to];
 	int old_max_eth_txqs, new_max_eth_txqs;
 	int old_txdata_index = 0, new_txdata_index = 0;
 
@@ -57,6 +61,12 @@
 	memcpy(to_fp, from_fp, sizeof(*to_fp));
 	to_fp->index = to;
 
+	/* move sp_objs contents as well, as their indices match fp ones */
+	memcpy(to_sp_objs, from_sp_objs, sizeof(*to_sp_objs));
+
+	/* move fp_stats contents as well, as their indices match fp ones */
+	memcpy(to_fp_stats, from_fp_stats, sizeof(*to_fp_stats));
+
 	/* Update txdata pointers in fp and move txdata content accordingly:
 	 * Each fp consumes 'max_cos' txdata structures, so the index should be
 	 * decremented by max_cos x delta.
@@ -500,7 +510,7 @@
 		   where we are and drop the whole packet */
 		err = bnx2x_alloc_rx_sge(bp, fp, sge_idx);
 		if (unlikely(err)) {
-			fp->eth_q_stats.rx_skb_alloc_failed++;
+			bnx2x_fp_qstats(bp, fp)->rx_skb_alloc_failed++;
 			return err;
 		}
 
@@ -605,7 +615,7 @@
 	/* drop the packet and keep the buffer in the bin */
 	DP(NETIF_MSG_RX_STATUS,
 	   "Failed to allocate or map a new skb - dropping packet!\n");
-	fp->eth_q_stats.rx_skb_alloc_failed++;
+	bnx2x_fp_stats(bp, fp)->eth_q_stats.rx_skb_alloc_failed++;
 }
 
 static int bnx2x_alloc_rx_data(struct bnx2x *bp,
@@ -638,8 +648,10 @@
 	return 0;
 }
 
-static void bnx2x_csum_validate(struct sk_buff *skb, union eth_rx_cqe *cqe,
-				struct bnx2x_fastpath *fp)
+static
+void bnx2x_csum_validate(struct sk_buff *skb, union eth_rx_cqe *cqe,
+				 struct bnx2x_fastpath *fp,
+				 struct bnx2x_eth_q_stats *qstats)
 {
 	/* Do nothing if no IP/L4 csum validation was done */
 
@@ -653,7 +665,7 @@
 	if (cqe->fast_path_cqe.type_error_flags &
 	    (ETH_FAST_PATH_RX_CQE_IP_BAD_XSUM_FLG |
 	     ETH_FAST_PATH_RX_CQE_L4_BAD_XSUM_FLG))
-		fp->eth_q_stats.hw_csum_err++;
+		qstats->hw_csum_err++;
 	else
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 }
@@ -797,7 +809,7 @@
 			DP(NETIF_MSG_RX_ERR | NETIF_MSG_RX_STATUS,
 			   "ERROR  flags %x  rx packet %u\n",
 			   cqe_fp_flags, sw_comp_cons);
-			fp->eth_q_stats.rx_err_discard_pkt++;
+			bnx2x_fp_qstats(bp, fp)->rx_err_discard_pkt++;
 			goto reuse_rx;
 		}
 
@@ -810,7 +822,7 @@
 			if (skb == NULL) {
 				DP(NETIF_MSG_RX_ERR | NETIF_MSG_RX_STATUS,
 				   "ERROR  packet dropped because of alloc failure\n");
-				fp->eth_q_stats.rx_skb_alloc_failed++;
+				bnx2x_fp_qstats(bp, fp)->rx_skb_alloc_failed++;
 				goto reuse_rx;
 			}
 			memcpy(skb->data, data + pad, len);
@@ -824,14 +836,15 @@
 				skb = build_skb(data, 0);
 				if (unlikely(!skb)) {
 					kfree(data);
-					fp->eth_q_stats.rx_skb_alloc_failed++;
+					bnx2x_fp_qstats(bp, fp)->
+							rx_skb_alloc_failed++;
 					goto next_rx;
 				}
 				skb_reserve(skb, pad);
 			} else {
 				DP(NETIF_MSG_RX_ERR | NETIF_MSG_RX_STATUS,
 				   "ERROR  packet dropped because of alloc failure\n");
-				fp->eth_q_stats.rx_skb_alloc_failed++;
+				bnx2x_fp_qstats(bp, fp)->rx_skb_alloc_failed++;
 reuse_rx:
 				bnx2x_reuse_rx_data(fp, bd_cons, bd_prod);
 				goto next_rx;
@@ -847,8 +860,8 @@
 		skb_checksum_none_assert(skb);
 
 		if (bp->dev->features & NETIF_F_RXCSUM)
-			bnx2x_csum_validate(skb, cqe, fp);
-
+			bnx2x_csum_validate(skb, cqe, fp,
+					    bnx2x_fp_qstats(bp, fp));
 
 		skb_record_rx_queue(skb, fp->rx_queue);
 
@@ -1780,7 +1793,7 @@
 	int rc;
 	unsigned long ramrod_flags = 0, vlan_mac_flags = 0;
 	struct bnx2x_mcast_ramrod_params rparam = {NULL};
-	struct bnx2x_vlan_mac_obj *mac_obj = &bp->fp->mac_obj;
+	struct bnx2x_vlan_mac_obj *mac_obj = &bp->sp_objs->mac_obj;
 
 	/***************** Cleanup MACs' object first *************************/
 
@@ -1791,7 +1804,7 @@
 
 	/* Clean ETH primary MAC */
 	__set_bit(BNX2X_ETH_MAC, &vlan_mac_flags);
-	rc = mac_obj->delete_all(bp, &bp->fp->mac_obj, &vlan_mac_flags,
+	rc = mac_obj->delete_all(bp, &bp->sp_objs->mac_obj, &vlan_mac_flags,
 				 &ramrod_flags);
 	if (rc != 0)
 		BNX2X_ERR("Failed to clean ETH MACs: %d\n", rc);
@@ -1877,12 +1890,16 @@
 static void bnx2x_bz_fp(struct bnx2x *bp, int index)
 {
 	struct bnx2x_fastpath *fp = &bp->fp[index];
+	struct bnx2x_fp_stats *fp_stats = &bp->fp_stats[index];
+
 	int cos;
 	struct napi_struct orig_napi = fp->napi;
+	struct bnx2x_agg_info *orig_tpa_info = fp->tpa_info;
 	/* bzero bnx2x_fastpath contents */
-	if (bp->stats_init)
+	if (bp->stats_init) {
+		memset(fp->tpa_info, 0, sizeof(*fp->tpa_info));
 		memset(fp, 0, sizeof(*fp));
-	else {
+	} else {
 		/* Keep Queue statistics */
 		struct bnx2x_eth_q_stats *tmp_eth_q_stats;
 		struct bnx2x_eth_q_stats_old *tmp_eth_q_stats_old;
@@ -1890,26 +1907,27 @@
 		tmp_eth_q_stats = kzalloc(sizeof(struct bnx2x_eth_q_stats),
 					  GFP_KERNEL);
 		if (tmp_eth_q_stats)
-			memcpy(tmp_eth_q_stats, &fp->eth_q_stats,
+			memcpy(tmp_eth_q_stats, &fp_stats->eth_q_stats,
 			       sizeof(struct bnx2x_eth_q_stats));
 
 		tmp_eth_q_stats_old =
 			kzalloc(sizeof(struct bnx2x_eth_q_stats_old),
 				GFP_KERNEL);
 		if (tmp_eth_q_stats_old)
-			memcpy(tmp_eth_q_stats_old, &fp->eth_q_stats_old,
+			memcpy(tmp_eth_q_stats_old, &fp_stats->eth_q_stats_old,
 			       sizeof(struct bnx2x_eth_q_stats_old));
 
+		memset(fp->tpa_info, 0, sizeof(*fp->tpa_info));
 		memset(fp, 0, sizeof(*fp));
 
 		if (tmp_eth_q_stats) {
-			memcpy(&fp->eth_q_stats, tmp_eth_q_stats,
-				   sizeof(struct bnx2x_eth_q_stats));
+			memcpy(&fp_stats->eth_q_stats, tmp_eth_q_stats,
+			       sizeof(struct bnx2x_eth_q_stats));
 			kfree(tmp_eth_q_stats);
 		}
 
 		if (tmp_eth_q_stats_old) {
-			memcpy(&fp->eth_q_stats_old, tmp_eth_q_stats_old,
+			memcpy(&fp_stats->eth_q_stats_old, tmp_eth_q_stats_old,
 			       sizeof(struct bnx2x_eth_q_stats_old));
 			kfree(tmp_eth_q_stats_old);
 		}
@@ -1918,7 +1936,7 @@
 
 	/* Restore the NAPI object as it has been already initialized */
 	fp->napi = orig_napi;
-
+	fp->tpa_info = orig_tpa_info;
 	fp->bp = bp;
 	fp->index = index;
 	if (IS_ETH_FP(fp))
@@ -2918,7 +2936,7 @@
 
 	if (unlikely(bnx2x_tx_avail(bp, txdata) <
 		     (skb_shinfo(skb)->nr_frags + 3))) {
-		txdata->parent_fp->eth_q_stats.driver_xoff++;
+		bnx2x_fp_qstats(bp, txdata->parent_fp)->driver_xoff++;
 		netif_tx_stop_queue(txq);
 		BNX2X_ERR("BUG! Tx ring full when queue awake!\n");
 		return NETDEV_TX_BUSY;
@@ -3200,7 +3218,7 @@
 		 * fp->bd_tx_cons */
 		smp_mb();
 
-		txdata->parent_fp->eth_q_stats.driver_xoff++;
+		bnx2x_fp_qstats(bp, txdata->parent_fp)->driver_xoff++;
 		if (bnx2x_tx_avail(bp, txdata) >= MAX_SKB_FRAGS + 4)
 			netif_tx_wake_queue(txq);
 	}
@@ -3437,7 +3455,7 @@
 			       cqe_ring_prod);
 	fp->rx_pkt = fp->rx_calls = 0;
 
-	fp->eth_q_stats.rx_skb_alloc_failed += failure_cnt;
+	bnx2x_fp_stats(bp, fp)->eth_q_stats.rx_skb_alloc_failed += failure_cnt;
 
 	return i - failure_cnt;
 }
@@ -3642,7 +3660,10 @@
 
 void bnx2x_free_mem_bp(struct bnx2x *bp)
 {
+	kfree(bp->fp->tpa_info);
 	kfree(bp->fp);
+	kfree(bp->sp_objs);
+	kfree(bp->fp_stats);
 	kfree(bp->bnx2x_txq);
 	kfree(bp->msix_table);
 	kfree(bp->ilt);
@@ -3654,6 +3675,8 @@
 	struct msix_entry *tbl;
 	struct bnx2x_ilt *ilt;
 	int msix_table_size = 0;
+	int fp_array_size;
+	int i;
 
 	/*
 	 * The biggest MSI-X table we might need is as a maximum number of fast
@@ -3662,12 +3685,34 @@
 	msix_table_size = bp->igu_sb_cnt + 1;
 
 	/* fp array: RSS plus CNIC related L2 queues */
-	fp = kcalloc(BNX2X_MAX_RSS_COUNT(bp) + NON_ETH_CONTEXT_USE,
-		     sizeof(*fp), GFP_KERNEL);
+	fp_array_size = BNX2X_MAX_RSS_COUNT(bp) + NON_ETH_CONTEXT_USE;
+	BNX2X_DEV_INFO("fp_array_size %d", fp_array_size);
+
+	fp = kcalloc(fp_array_size, sizeof(*fp), GFP_KERNEL);
 	if (!fp)
 		goto alloc_err;
+	for (i = 0; i < fp_array_size; i++) {
+		fp[i].tpa_info =
+			kcalloc(ETH_MAX_AGGREGATION_QUEUES_E1H_E2,
+				sizeof(struct bnx2x_agg_info), GFP_KERNEL);
+		if (!(fp[i].tpa_info))
+			goto alloc_err;
+	}
+
 	bp->fp = fp;
 
+	/* allocate sp objs */
+	bp->sp_objs = kcalloc(fp_array_size, sizeof(struct bnx2x_sp_objs),
+			      GFP_KERNEL);
+	if (!bp->sp_objs)
+		goto alloc_err;
+
+	/* allocate fp_stats */
+	bp->fp_stats = kcalloc(fp_array_size, sizeof(struct bnx2x_fp_stats),
+			       GFP_KERNEL);
+	if (!bp->fp_stats)
+		goto alloc_err;
+
 	/* Allocate memory for the transmission queues array */
 	bp->bnx2x_txq_size = BNX2X_MAX_RSS_COUNT(bp) * BNX2X_MULTI_TX_COS;
 #ifdef BCM_CNIC
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index de79cdf..11afe5d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -981,8 +981,8 @@
 	struct bnx2x *bp = fp->bp;
 
 	/* Configure classification DBs */
-	bnx2x_init_mac_obj(bp, &fp->mac_obj, fp->cl_id, fp->cid,
-			   BP_FUNC(bp), bnx2x_sp(bp, mac_rdata),
+	bnx2x_init_mac_obj(bp, &bnx2x_sp_obj(bp, fp).mac_obj, fp->cl_id,
+			   fp->cid, BP_FUNC(bp), bnx2x_sp(bp, mac_rdata),
 			   bnx2x_sp_mapping(bp, mac_rdata),
 			   BNX2X_FILTER_MAC_PENDING,
 			   &bp->sp_state, obj_type,
@@ -1138,8 +1138,8 @@
 	/* No multi-CoS for FCoE L2 client */
 	BUG_ON(fp->max_cos != 1);
 
-	bnx2x_init_queue_obj(bp, &fp->q_obj, fp->cl_id, &fp->cid, 1,
-			     BP_FUNC(bp), bnx2x_sp(bp, q_rdata),
+	bnx2x_init_queue_obj(bp, &bnx2x_sp_obj(bp, fp).q_obj, fp->cl_id,
+			     &fp->cid, 1, BP_FUNC(bp), bnx2x_sp(bp, q_rdata),
 			     bnx2x_sp_mapping(bp, q_rdata), q_type);
 
 	DP(NETIF_MSG_IFUP,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index b468223..af84ebd 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -2292,7 +2292,7 @@
 		return -ENODEV;
 	}
 
-	params.q_obj = &bp->fp->q_obj;
+	params.q_obj = &bp->sp_objs->q_obj;
 	params.cmd = BNX2X_Q_CMD_EMPTY;
 
 	__set_bit(RAMROD_COMP_WAIT, &params.ramrod_flags);
@@ -2516,7 +2516,7 @@
 
 	if (is_multi(bp)) {
 		for_each_eth_queue(bp, i) {
-			hw_stats = (u32 *)&bp->fp[i].eth_q_stats;
+			hw_stats = (u32 *)&bp->fp_stats[i].eth_q_stats;
 			for (j = 0; j < BNX2X_NUM_Q_STATS; j++) {
 				if (bnx2x_q_stats_arr[j].size == 0) {
 					/* skip this counter */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index c9302d9..dce7056 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -1583,7 +1583,7 @@
 	int cid = SW_CID(rr_cqe->ramrod_cqe.conn_and_cmd_data);
 	int command = CQE_CMD(rr_cqe->ramrod_cqe.conn_and_cmd_data);
 	enum bnx2x_queue_cmd drv_cmd = BNX2X_Q_CMD_MAX;
-	struct bnx2x_queue_sp_obj *q_obj = &fp->q_obj;
+	struct bnx2x_queue_sp_obj *q_obj = &bnx2x_sp_obj(bp, fp).q_obj;
 
 	DP(BNX2X_MSG_SP,
 	   "fp %d  cid %d  got ramrod #%d  state is %x  type is %d\n",
@@ -3035,9 +3035,9 @@
 	memcpy(ether_stat->version, DRV_MODULE_VERSION,
 	       ETH_STAT_INFO_VERSION_LEN - 1);
 
-	bp->fp[0].mac_obj.get_n_elements(bp, &bp->fp[0].mac_obj,
-					 DRV_INFO_ETH_STAT_NUM_MACS_REQUIRED,
-					 ether_stat->mac_local);
+	bp->sp_objs[0].mac_obj.get_n_elements(bp, &bp->sp_objs[0].mac_obj,
+					DRV_INFO_ETH_STAT_NUM_MACS_REQUIRED,
+					ether_stat->mac_local);
 
 	ether_stat->mtu_size = bp->dev->mtu;
 
@@ -4632,7 +4632,7 @@
 			vlan_mac_obj = &bp->iscsi_l2_mac_obj;
 		else
 #endif
-			vlan_mac_obj = &bp->fp[cid].mac_obj;
+			vlan_mac_obj = &bp->sp_objs[cid].mac_obj;
 
 		break;
 	case BNX2X_FILTER_MCAST_PENDING:
@@ -4730,7 +4730,7 @@
 	for_each_eth_queue(bp, q) {
 		/* Set the appropriate Queue object */
 		fp = &bp->fp[q];
-		queue_params.q_obj = &fp->q_obj;
+		queue_params.q_obj = &bnx2x_sp_obj(bp, fp).q_obj;
 
 		/* send the ramrod */
 		rc = bnx2x_queue_state_change(bp, &queue_params);
@@ -4742,7 +4742,7 @@
 #ifdef BCM_CNIC
 	if (!NO_FCOE(bp)) {
 		fp = &bp->fp[FCOE_IDX(bp)];
-		queue_params.q_obj = &fp->q_obj;
+		queue_params.q_obj = &bnx2x_sp_obj(bp, fp).q_obj;
 
 		/* clear pending completion bit */
 		__clear_bit(RAMROD_COMP_WAIT, &queue_params.ramrod_flags);
@@ -4775,10 +4775,10 @@
 	DP(BNX2X_MSG_SP, "retrieving fp from cid %d\n", cid);
 #ifdef BCM_CNIC
 	if (cid == BNX2X_FCOE_ETH_CID(bp))
-		return &bnx2x_fcoe(bp, q_obj);
+		return &bnx2x_fcoe_sp_obj(bp, q_obj);
 	else
 #endif
-		return &bnx2x_fp(bp, CID_TO_FP(cid, bp), q_obj);
+		return &bp->sp_objs[CID_TO_FP(cid, bp)].q_obj;
 }
 
 static void bnx2x_eq_int(struct bnx2x *bp)
@@ -5667,8 +5667,8 @@
 		cids[cos] = fp->txdata_ptr[cos]->cid;
 	}
 
-	bnx2x_init_queue_obj(bp, &fp->q_obj, fp->cl_id, cids, fp->max_cos,
-			     BP_FUNC(bp), bnx2x_sp(bp, q_rdata),
+	bnx2x_init_queue_obj(bp, &bnx2x_sp_obj(bp, fp).q_obj, fp->cl_id, cids,
+			     fp->max_cos, BP_FUNC(bp), bnx2x_sp(bp, q_rdata),
 			     bnx2x_sp_mapping(bp, q_rdata), q_type);
 
 	/**
@@ -7596,8 +7596,8 @@
 
 	__set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
 	/* Eth MAC is set on RSS leading client (fp[0]) */
-	return bnx2x_set_mac_one(bp, bp->dev->dev_addr, &bp->fp->mac_obj, set,
-				 BNX2X_ETH_MAC, &ramrod_flags);
+	return bnx2x_set_mac_one(bp, bp->dev->dev_addr, &bp->sp_objs->mac_obj,
+				 set, BNX2X_ETH_MAC, &ramrod_flags);
 }
 
 int bnx2x_setup_leading(struct bnx2x *bp)
@@ -7877,7 +7877,7 @@
 		bnx2x_ack_sb(bp, fp->igu_sb_id, USTORM_ID, 0,
 			     IGU_INT_ENABLE, 0);
 
-	q_params.q_obj = &fp->q_obj;
+	q_params.q_obj = &bnx2x_sp_obj(bp, fp).q_obj;
 	/* We want to wait for completion in this context */
 	__set_bit(RAMROD_COMP_WAIT, &q_params.ramrod_flags);
 
@@ -7950,7 +7950,7 @@
 
 	DP(NETIF_MSG_IFDOWN, "stopping queue %d cid %d\n", index, fp->cid);
 
-	q_params.q_obj = &fp->q_obj;
+	q_params.q_obj = &bnx2x_sp_obj(bp, fp).q_obj;
 	/* We want to wait for completion in this context */
 	__set_bit(RAMROD_COMP_WAIT, &q_params.ramrod_flags);
 
@@ -8339,12 +8339,13 @@
 	usleep_range(1000, 1000);
 
 	/* Clean all ETH MACs */
-	rc = bnx2x_del_all_macs(bp, &bp->fp[0].mac_obj, BNX2X_ETH_MAC, false);
+	rc = bnx2x_del_all_macs(bp, &bp->sp_objs[0].mac_obj, BNX2X_ETH_MAC,
+				false);
 	if (rc < 0)
 		BNX2X_ERR("Failed to delete all ETH macs: %d\n", rc);
 
 	/* Clean up UC list  */
-	rc = bnx2x_del_all_macs(bp, &bp->fp[0].mac_obj, BNX2X_UC_LIST_MAC,
+	rc = bnx2x_del_all_macs(bp, &bp->sp_objs[0].mac_obj, BNX2X_UC_LIST_MAC,
 				true);
 	if (rc < 0)
 		BNX2X_ERR("Failed to schedule DEL commands for UC MACs list: %d\n",
@@ -11049,7 +11050,7 @@
 	int rc;
 	struct net_device *dev = bp->dev;
 	struct netdev_hw_addr *ha;
-	struct bnx2x_vlan_mac_obj *mac_obj = &bp->fp->mac_obj;
+	struct bnx2x_vlan_mac_obj *mac_obj = &bp->sp_objs->mac_obj;
 	unsigned long ramrod_flags = 0;
 
 	/* First schedule a cleanup up of old configuration */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
index 776b521..514a528 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
@@ -859,17 +859,22 @@
 		struct tstorm_per_queue_stats *tclient =
 			&bp->fw_stats_data->queue_stats[i].
 			tstorm_queue_statistics;
-		struct tstorm_per_queue_stats *old_tclient = &fp->old_tclient;
+		struct tstorm_per_queue_stats *old_tclient =
+			&bnx2x_fp_stats(bp, fp)->old_tclient;
 		struct ustorm_per_queue_stats *uclient =
 			&bp->fw_stats_data->queue_stats[i].
 			ustorm_queue_statistics;
-		struct ustorm_per_queue_stats *old_uclient = &fp->old_uclient;
+		struct ustorm_per_queue_stats *old_uclient =
+			&bnx2x_fp_stats(bp, fp)->old_uclient;
 		struct xstorm_per_queue_stats *xclient =
 			&bp->fw_stats_data->queue_stats[i].
 			xstorm_queue_statistics;
-		struct xstorm_per_queue_stats *old_xclient = &fp->old_xclient;
-		struct bnx2x_eth_q_stats *qstats = &fp->eth_q_stats;
-		struct bnx2x_eth_q_stats_old *qstats_old = &fp->eth_q_stats_old;
+		struct xstorm_per_queue_stats *old_xclient =
+			&bnx2x_fp_stats(bp, fp)->old_xclient;
+		struct bnx2x_eth_q_stats *qstats =
+			&bnx2x_fp_stats(bp, fp)->eth_q_stats;
+		struct bnx2x_eth_q_stats_old *qstats_old =
+			&bnx2x_fp_stats(bp, fp)->eth_q_stats_old;
 
 		u32 diff;
 
@@ -1052,8 +1057,11 @@
 	nstats->tx_bytes = bnx2x_hilo(&estats->total_bytes_transmitted_hi);
 
 	tmp = estats->mac_discard;
-	for_each_rx_queue(bp, i)
-		tmp += le32_to_cpu(bp->fp[i].old_tclient.checksum_discard);
+	for_each_rx_queue(bp, i) {
+		struct tstorm_per_queue_stats *old_tclient =
+			&bp->fp_stats[i].old_tclient;
+		tmp += le32_to_cpu(old_tclient->checksum_discard);
+	}
 	nstats->rx_dropped = tmp + bp->net_stats_old.rx_dropped;
 
 	nstats->tx_dropped = 0;
@@ -1103,9 +1111,9 @@
 	int i;
 
 	for_each_queue(bp, i) {
-		struct bnx2x_eth_q_stats *qstats = &bp->fp[i].eth_q_stats;
+		struct bnx2x_eth_q_stats *qstats = &bp->fp_stats[i].eth_q_stats;
 		struct bnx2x_eth_q_stats_old *qstats_old =
-						&bp->fp[i].eth_q_stats_old;
+			&bp->fp_stats[i].eth_q_stats_old;
 
 		UPDATE_ESTAT_QSTAT(driver_xoff);
 		UPDATE_ESTAT_QSTAT(rx_err_discard_pkt);
@@ -1483,15 +1491,19 @@
 
 	/* function stats */
 	for_each_queue(bp, i) {
-		struct bnx2x_fastpath *fp = &bp->fp[i];
+		struct bnx2x_fp_stats *fp_stats = &bp->fp_stats[i];
 
-		memset(&fp->old_tclient, 0, sizeof(fp->old_tclient));
-		memset(&fp->old_uclient, 0, sizeof(fp->old_uclient));
-		memset(&fp->old_xclient, 0, sizeof(fp->old_xclient));
+		memset(&fp_stats->old_tclient, 0,
+		       sizeof(fp_stats->old_tclient));
+		memset(&fp_stats->old_uclient, 0,
+		       sizeof(fp_stats->old_uclient));
+		memset(&fp_stats->old_xclient, 0,
+		       sizeof(fp_stats->old_xclient));
 		if (bp->stats_init) {
-			memset(&fp->eth_q_stats, 0, sizeof(fp->eth_q_stats));
-			memset(&fp->eth_q_stats_old, 0,
-			       sizeof(fp->eth_q_stats_old));
+			memset(&fp_stats->eth_q_stats, 0,
+			       sizeof(fp_stats->eth_q_stats));
+			memset(&fp_stats->eth_q_stats_old, 0,
+			       sizeof(fp_stats->eth_q_stats_old));
 		}
 	}
 
@@ -1533,8 +1545,10 @@
 	/* save queue statistics */
 	for_each_eth_queue(bp, i) {
 		struct bnx2x_fastpath *fp = &bp->fp[i];
-		struct bnx2x_eth_q_stats *qstats = &fp->eth_q_stats;
-		struct bnx2x_eth_q_stats_old *qstats_old = &fp->eth_q_stats_old;
+		struct bnx2x_eth_q_stats *qstats =
+			&bnx2x_fp_stats(bp, fp)->eth_q_stats;
+		struct bnx2x_eth_q_stats_old *qstats_old =
+			&bnx2x_fp_stats(bp, fp)->eth_q_stats_old;
 
 		UPDATE_QSTAT_OLD(total_unicast_bytes_received_hi);
 		UPDATE_QSTAT_OLD(total_unicast_bytes_received_lo);
@@ -1590,8 +1604,7 @@
 	memset(afex_stats, 0, sizeof(struct afex_stats));
 
 	for_each_eth_queue(bp, i) {
-		struct bnx2x_fastpath *fp = &bp->fp[i];
-		struct bnx2x_eth_q_stats *qstats = &fp->eth_q_stats;
+		struct bnx2x_eth_q_stats *qstats = &bp->fp_stats[i].eth_q_stats;
 
 		ADD_64(afex_stats->rx_unicast_bytes_hi,
 		       qstats->total_unicast_bytes_received_hi,