Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Support ipv6 checksum offload in sunvnet driver, from Shannon
    Nelson.

 2) Move to RB-tree instead of custom AVL code in inetpeer, from Eric
    Dumazet.

 3) Allow generic XDP to work on virtual devices, from John Fastabend.

 4) Add bpf device maps and XDP_REDIRECT, which can be used to build
    arbitrary switching frameworks using XDP. From John Fastabend.

 5) Remove UFO offloads from the tree, gave us little other than bugs.

 6) Remove the IPSEC flow cache, from Florian Westphal.

 7) Support ipv6 route offload in mlxsw driver.

 8) Support VF representors in bnxt_en, from Sathya Perla.

 9) Add support for forward error correction modes to ethtool, from
    Vidya Sagar Ravipati.

10) Add time filter for packet scheduler action dumping, from Jamal Hadi
    Salim.

11) Extend the zerocopy sendmsg() used by virtio and tap to regular
    sockets via MSG_ZEROCOPY. From Willem de Bruijn.

12) Significantly rework value tracking in the BPF verifier, from Edward
    Cree.

13) Add new jump instructions to eBPF, from Daniel Borkmann.

14) Rework rtnetlink plumbing so that operations can be run without
    taking the RTNL semaphore. From Florian Westphal.

15) Support XDP in tap driver, from Jason Wang.

16) Add 32-bit eBPF JIT for ARM, from Shubham Bansal.

17) Add Huawei hinic ethernet driver.

18) Allow to report MD5 keys in TCP inet_diag dumps, from Ivan
    Delalande.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1780 commits)
  i40e: point wb_desc at the nvm_wb_desc during i40e_read_nvm_aq
  i40e: avoid NVM acquire deadlock during NVM update
  drivers: net: xgene: Remove return statement from void function
  drivers: net: xgene: Configure tx/rx delay for ACPI
  drivers: net: xgene: Read tx/rx delay for ACPI
  rocker: fix kcalloc parameter order
  rds: Fix non-atomic operation on shared flag variable
  net: sched: don't use GFP_KERNEL under spin lock
  vhost_net: correctly check tx avail during rx busy polling
  net: mdio-mux: add mdio_mux parameter to mdio_mux_init()
  rxrpc: Make service connection lookup always check for retry
  net: stmmac: Delete dead code for MDIO registration
  gianfar: Fix Tx flow control deactivation
  cxgb4: Ignore MPS_TX_INT_CAUSE[Bubble] for T6
  cxgb4: Fix pause frame count in t4_get_port_stats
  cxgb4: fix memory leak
  tun: rename generic_xdp to skb_xdp
  tun: reserve extra headroom only when XDP is set
  net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
  net: dsa: bcm_sf2: Advertise number of egress queues
  ...

1 files changed, 725 insertions, 3 deletions

diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index adde7745d069..23f6b60030c5 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -165,9 +165,6 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr)
 		/* If command is successful, change the MTU. */
 		netif_info(lio, probe, lio->netdev, "MTU Changed from %d to %d\n",
 			   netdev->mtu, nctrl->ncmd.s.param1);
-		dev_info(&oct->pci_dev->dev, "%s MTU Changed from %d to %d\n",
-			 netdev->name, netdev->mtu,
-			 nctrl->ncmd.s.param1);
 		netdev->mtu = nctrl->ncmd.s.param1;
 		queue_delayed_work(lio->link_status_wq.wq,
 				   &lio->link_status_wq.wk.work, 0);
@@ -275,6 +272,11 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr)
 		netif_info(lio, probe, lio->netdev, "Set RX/TX flow control parameters\n");
 		break;
 
+	case OCTNET_CMD_QUEUE_COUNT_CTL:
+		netif_info(lio, probe, lio->netdev, "Queue count updated to %d\n",
+			   nctrl->ncmd.s.param1);
+		break;
+
 	default:
 		dev_err(&oct->pci_dev->dev, "%s Unknown cmd %d\n", __func__,
 			nctrl->ncmd.s.cmd);
@@ -364,3 +366,723 @@ void cleanup_rx_oom_poll_fn(struct net_device *netdev)
 		destroy_workqueue(lio->rxq_status_wq.wq);
 	}
 }
+
+/* Runs in interrupt context. */
+static void lio_update_txq_status(struct octeon_device *oct, int iq_num)
+{
+	struct octeon_instr_queue *iq = oct->instr_queue[iq_num];
+	struct net_device *netdev;
+	struct lio *lio;
+
+	netdev = oct->props[iq->ifidx].netdev;
+
+	/* This is needed because the first IQ does not have
+	 * a netdev associated with it.
+	 */
+	if (!netdev)
+		return;
+
+	lio = GET_LIO(netdev);
+	if (netif_is_multiqueue(netdev)) {
+		if (__netif_subqueue_stopped(netdev, iq->q_index) &&
+		    lio->linfo.link.s.link_up &&
+		    (!octnet_iq_is_full(oct, iq_num))) {
+			netif_wake_subqueue(netdev, iq->q_index);
+			INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq_num,
+						  tx_restart, 1);
+		}
+	} else if (netif_queue_stopped(netdev) &&
+		   lio->linfo.link.s.link_up &&
+		   (!octnet_iq_is_full(oct, lio->txq))) {
+		INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, lio->txq,
+					  tx_restart, 1);
+		netif_wake_queue(netdev);
+	}
+}
+
+/**
+ * \brief Setup output queue
+ * @param oct octeon device
+ * @param q_no which queue
+ * @param num_descs how many descriptors
+ * @param desc_size size of each descriptor
+ * @param app_ctx application context
+ */
+static int octeon_setup_droq(struct octeon_device *oct, int q_no, int num_descs,
+			     int desc_size, void *app_ctx)
+{
+	int ret_val;
+
+	dev_dbg(&oct->pci_dev->dev, "Creating Droq: %d\n", q_no);
+	/* droq creation and local register settings. */
+	ret_val = octeon_create_droq(oct, q_no, num_descs, desc_size, app_ctx);
+	if (ret_val < 0)
+		return ret_val;
+
+	if (ret_val == 1) {
+		dev_dbg(&oct->pci_dev->dev, "Using default droq %d\n", q_no);
+		return 0;
+	}
+
+	/* Enable the droq queues */
+	octeon_set_droq_pkt_op(oct, q_no, 1);
+
+	/* Send Credit for Octeon Output queues. Credits are always
+	 * sent after the output queue is enabled.
+	 */
+	writel(oct->droq[q_no]->max_count, oct->droq[q_no]->pkts_credit_reg);
+
+	return ret_val;
+}
+
+/** Routine to push packets arriving on Octeon interface upto network layer.
+ * @param oct_id   - octeon device id.
+ * @param skbuff   - skbuff struct to be passed to network layer.
+ * @param len      - size of total data received.
+ * @param rh       - Control header associated with the packet
+ * @param param    - additional control data with the packet
+ * @param arg      - farg registered in droq_ops
+ */
+static void
+liquidio_push_packet(u32 octeon_id __attribute__((unused)),
+		     void *skbuff,
+		     u32 len,
+		     union octeon_rh *rh,
+		     void *param,
+		     void *arg)
+{
+	struct net_device *netdev = (struct net_device *)arg;
+	struct octeon_droq *droq =
+	    container_of(param, struct octeon_droq, napi);
+	struct sk_buff *skb = (struct sk_buff *)skbuff;
+	struct skb_shared_hwtstamps *shhwtstamps;
+	struct napi_struct *napi = param;
+	u16 vtag = 0;
+	u32 r_dh_off;
+	u64 ns;
+
+	if (netdev) {
+		struct lio *lio = GET_LIO(netdev);
+		struct octeon_device *oct = lio->oct_dev;
+		int packet_was_received;
+
+		/* Do not proceed if the interface is not in RUNNING state. */
+		if (!ifstate_check(lio, LIO_IFSTATE_RUNNING)) {
+			recv_buffer_free(skb);
+			droq->stats.rx_dropped++;
+			return;
+		}
+
+		skb->dev = netdev;
+
+		skb_record_rx_queue(skb, droq->q_no);
+		if (likely(len > MIN_SKB_SIZE)) {
+			struct octeon_skb_page_info *pg_info;
+			unsigned char *va;
+
+			pg_info = ((struct octeon_skb_page_info *)(skb->cb));
+			if (pg_info->page) {
+				/* For Paged allocation use the frags */
+				va = page_address(pg_info->page) +
+					pg_info->page_offset;
+				memcpy(skb->data, va, MIN_SKB_SIZE);
+				skb_put(skb, MIN_SKB_SIZE);
+				skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+						pg_info->page,
+						pg_info->page_offset +
+						MIN_SKB_SIZE,
+						len - MIN_SKB_SIZE,
+						LIO_RXBUFFER_SZ);
+			}
+		} else {
+			struct octeon_skb_page_info *pg_info =
+				((struct octeon_skb_page_info *)(skb->cb));
+			skb_copy_to_linear_data(skb, page_address(pg_info->page)
+						+ pg_info->page_offset, len);
+			skb_put(skb, len);
+			put_page(pg_info->page);
+		}
+
+		r_dh_off = (rh->r_dh.len - 1) * BYTES_PER_DHLEN_UNIT;
+
+		if (oct->ptp_enable) {
+			if (rh->r_dh.has_hwtstamp) {
+				/* timestamp is included from the hardware at
+				 * the beginning of the packet.
+				 */
+				if (ifstate_check
+					(lio,
+					 LIO_IFSTATE_RX_TIMESTAMP_ENABLED)) {
+					/* Nanoseconds are in the first 64-bits
+					 * of the packet.
+					 */
+					memcpy(&ns, (skb->data + r_dh_off),
+					       sizeof(ns));
+					r_dh_off -= BYTES_PER_DHLEN_UNIT;
+					shhwtstamps = skb_hwtstamps(skb);
+					shhwtstamps->hwtstamp =
+						ns_to_ktime(ns +
+							    lio->ptp_adjust);
+				}
+			}
+		}
+
+		if (rh->r_dh.has_hash) {
+			__be32 *hash_be = (__be32 *)(skb->data + r_dh_off);
+			u32 hash = be32_to_cpu(*hash_be);
+
+			skb_set_hash(skb, hash, PKT_HASH_TYPE_L4);
+			r_dh_off -= BYTES_PER_DHLEN_UNIT;
+		}
+
+		skb_pull(skb, rh->r_dh.len * BYTES_PER_DHLEN_UNIT);
+		skb->protocol = eth_type_trans(skb, skb->dev);
+
+		if ((netdev->features & NETIF_F_RXCSUM) &&
+		    (((rh->r_dh.encap_on) &&
+		      (rh->r_dh.csum_verified & CNNIC_TUN_CSUM_VERIFIED)) ||
+		     (!(rh->r_dh.encap_on) &&
+		      (rh->r_dh.csum_verified & CNNIC_CSUM_VERIFIED))))
+			/* checksum has already been verified */
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+		else
+			skb->ip_summed = CHECKSUM_NONE;
+
+		/* Setting Encapsulation field on basis of status received
+		 * from the firmware
+		 */
+		if (rh->r_dh.encap_on) {
+			skb->encapsulation = 1;
+			skb->csum_level = 1;
+			droq->stats.rx_vxlan++;
+		}
+
+		/* inbound VLAN tag */
+		if ((netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+		    rh->r_dh.vlan) {
+			u16 priority = rh->r_dh.priority;
+			u16 vid = rh->r_dh.vlan;
+
+			vtag = (priority << VLAN_PRIO_SHIFT) | vid;
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vtag);
+		}
+
+		packet_was_received = (napi_gro_receive(napi, skb) != GRO_DROP);
+
+		if (packet_was_received) {
+			droq->stats.rx_bytes_received += len;
+			droq->stats.rx_pkts_received++;
+		} else {
+			droq->stats.rx_dropped++;
+			netif_info(lio, rx_err, lio->netdev,
+				   "droq:%d  error rx_dropped:%llu\n",
+				   droq->q_no, droq->stats.rx_dropped);
+		}
+
+	} else {
+		recv_buffer_free(skb);
+	}
+}
+
+/**
+ * \brief wrapper for calling napi_schedule
+ * @param param parameters to pass to napi_schedule
+ *
+ * Used when scheduling on different CPUs
+ */
+static void napi_schedule_wrapper(void *param)
+{
+	struct napi_struct *napi = param;
+
+	napi_schedule(napi);
+}
+
+/**
+ * \brief callback when receive interrupt occurs and we are in NAPI mode
+ * @param arg pointer to octeon output queue
+ */
+static void liquidio_napi_drv_callback(void *arg)
+{
+	struct octeon_device *oct;
+	struct octeon_droq *droq = arg;
+	int this_cpu = smp_processor_id();
+
+	oct = droq->oct_dev;
+
+	if (OCTEON_CN23XX_PF(oct) || OCTEON_CN23XX_VF(oct) ||
+	    droq->cpu_id == this_cpu) {
+		napi_schedule_irqoff(&droq->napi);
+	} else {
+		call_single_data_t *csd = &droq->csd;
+
+		csd->func = napi_schedule_wrapper;
+		csd->info = &droq->napi;
+		csd->flags = 0;
+
+		smp_call_function_single_async(droq->cpu_id, csd);
+	}
+}
+
+/**
+ * \brief Entry point for NAPI polling
+ * @param napi NAPI structure
+ * @param budget maximum number of items to process
+ */
+static int liquidio_napi_poll(struct napi_struct *napi, int budget)
+{
+	struct octeon_instr_queue *iq;
+	struct octeon_device *oct;
+	struct octeon_droq *droq;
+	int tx_done = 0, iq_no;
+	int work_done;
+
+	droq = container_of(napi, struct octeon_droq, napi);
+	oct = droq->oct_dev;
+	iq_no = droq->q_no;
+
+	/* Handle Droq descriptors */
+	work_done = octeon_process_droq_poll_cmd(oct, droq->q_no,
+						 POLL_EVENT_PROCESS_PKTS,
+						 budget);
+
+	/* Flush the instruction queue */
+	iq = oct->instr_queue[iq_no];
+	if (iq) {
+		/* TODO: move this check to inside octeon_flush_iq,
+		 * once check_db_timeout is removed
+		 */
+		if (atomic_read(&iq->instr_pending))
+			/* Process iq buffers with in the budget limits */
+			tx_done = octeon_flush_iq(oct, iq, budget);
+		else
+			tx_done = 1;
+		/* Update iq read-index rather than waiting for next interrupt.
+		 * Return back if tx_done is false.
+		 */
+		/* sub-queue status update */
+		lio_update_txq_status(oct, iq_no);
+	} else {
+		dev_err(&oct->pci_dev->dev, "%s:  iq (%d) num invalid\n",
+			__func__, iq_no);
+	}
+
+#define MAX_REG_CNT  2000000U
+	/* force enable interrupt if reg cnts are high to avoid wraparound */
+	if ((work_done < budget && tx_done) ||
+	    (iq && iq->pkt_in_done >= MAX_REG_CNT) ||
+	    (droq->pkt_count >= MAX_REG_CNT)) {
+		tx_done = 1;
+		napi_complete_done(napi, work_done);
+
+		octeon_process_droq_poll_cmd(droq->oct_dev, droq->q_no,
+					     POLL_EVENT_ENABLE_INTR, 0);
+		return 0;
+	}
+
+	return (!tx_done) ? (budget) : (work_done);
+}
+
+/**
+ * \brief Setup input and output queues
+ * @param octeon_dev octeon device
+ * @param ifidx Interface index
+ *
+ * Note: Queues are with respect to the octeon device. Thus
+ * an input queue is for egress packets, and output queues
+ * are for ingress packets.
+ */
+int liquidio_setup_io_queues(struct octeon_device *octeon_dev, int ifidx,
+			     u32 num_iqs, u32 num_oqs)
+{
+	struct octeon_droq_ops droq_ops;
+	struct net_device *netdev;
+	struct octeon_droq *droq;
+	struct napi_struct *napi;
+	int cpu_id_modulus;
+	int num_tx_descs;
+	struct lio *lio;
+	int retval = 0;
+	int q, q_no;
+	int cpu_id;
+
+	netdev = octeon_dev->props[ifidx].netdev;
+
+	lio = GET_LIO(netdev);
+
+	memset(&droq_ops, 0, sizeof(struct octeon_droq_ops));
+
+	droq_ops.fptr = liquidio_push_packet;
+	droq_ops.farg = netdev;
+
+	droq_ops.poll_mode = 1;
+	droq_ops.napi_fn = liquidio_napi_drv_callback;
+	cpu_id = 0;
+	cpu_id_modulus = num_present_cpus();
+
+	/* set up DROQs. */
+	for (q = 0; q < num_oqs; q++) {
+		q_no = lio->linfo.rxpciq[q].s.q_no;
+		dev_dbg(&octeon_dev->pci_dev->dev,
+			"%s index:%d linfo.rxpciq.s.q_no:%d\n",
+			__func__, q, q_no);
+		retval = octeon_setup_droq(
+		    octeon_dev, q_no,
+		    CFG_GET_NUM_RX_DESCS_NIC_IF(octeon_get_conf(octeon_dev),
+						lio->ifidx),
+		    CFG_GET_NUM_RX_BUF_SIZE_NIC_IF(octeon_get_conf(octeon_dev),
+						   lio->ifidx),
+		    NULL);
+		if (retval) {
+			dev_err(&octeon_dev->pci_dev->dev,
+				"%s : Runtime DROQ(RxQ) creation failed.\n",
+				__func__);
+			return 1;
+		}
+
+		droq = octeon_dev->droq[q_no];
+		napi = &droq->napi;
+		dev_dbg(&octeon_dev->pci_dev->dev, "netif_napi_add netdev:%llx oct:%llx\n",
+			(u64)netdev, (u64)octeon_dev);
+		netif_napi_add(netdev, napi, liquidio_napi_poll, 64);
+
+		/* designate a CPU for this droq */
+		droq->cpu_id = cpu_id;
+		cpu_id++;
+		if (cpu_id >= cpu_id_modulus)
+			cpu_id = 0;
+
+		octeon_register_droq_ops(octeon_dev, q_no, &droq_ops);
+	}
+
+	if (OCTEON_CN23XX_PF(octeon_dev) || OCTEON_CN23XX_VF(octeon_dev)) {
+		/* 23XX PF/VF can send/recv control messages (via the first
+		 * PF/VF-owned droq) from the firmware even if the ethX
+		 * interface is down, so that's why poll_mode must be off
+		 * for the first droq.
+		 */
+		octeon_dev->droq[0]->ops.poll_mode = 0;
+	}
+
+	/* set up IQs. */
+	for (q = 0; q < num_iqs; q++) {
+		num_tx_descs = CFG_GET_NUM_TX_DESCS_NIC_IF(
+		    octeon_get_conf(octeon_dev), lio->ifidx);
+		retval = octeon_setup_iq(octeon_dev, ifidx, q,
+					 lio->linfo.txpciq[q], num_tx_descs,
+					 netdev_get_tx_queue(netdev, q));
+		if (retval) {
+			dev_err(&octeon_dev->pci_dev->dev,
+				" %s : Runtime IQ(TxQ) creation failed.\n",
+				__func__);
+			return 1;
+		}
+
+		/* XPS */
+		if (!OCTEON_CN23XX_VF(octeon_dev) && octeon_dev->msix_on &&
+		    octeon_dev->ioq_vector) {
+			struct octeon_ioq_vector    *ioq_vector;
+
+			ioq_vector = &octeon_dev->ioq_vector[q];
+			netif_set_xps_queue(netdev,
+					    &ioq_vector->affinity_mask,
+					    ioq_vector->iq_index);
+		}
+	}
+
+	return 0;
+}
+
+static
+int liquidio_schedule_msix_droq_pkt_handler(struct octeon_droq *droq, u64 ret)
+{
+	struct octeon_device *oct = droq->oct_dev;
+	struct octeon_device_priv *oct_priv =
+	    (struct octeon_device_priv *)oct->priv;
+
+	if (droq->ops.poll_mode) {
+		droq->ops.napi_fn(droq);
+	} else {
+		if (ret & MSIX_PO_INT) {
+			if (OCTEON_CN23XX_VF(oct))
+				dev_err(&oct->pci_dev->dev,
+					"should not come here should not get rx when poll mode = 0 for vf\n");
+			tasklet_schedule(&oct_priv->droq_tasklet);
+			return 1;
+		}
+		/* this will be flushed periodically by check iq db */
+		if (ret & MSIX_PI_INT)
+			return 0;
+	}
+
+	return 0;
+}
+
+irqreturn_t
+liquidio_msix_intr_handler(int irq __attribute__((unused)), void *dev)
+{
+	struct octeon_ioq_vector *ioq_vector = (struct octeon_ioq_vector *)dev;
+	struct octeon_device *oct = ioq_vector->oct_dev;
+	struct octeon_droq *droq = oct->droq[ioq_vector->droq_index];
+	u64 ret;
+
+	ret = oct->fn_list.msix_interrupt_handler(ioq_vector);
+
+	if (ret & MSIX_PO_INT || ret & MSIX_PI_INT)
+		liquidio_schedule_msix_droq_pkt_handler(droq, ret);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * \brief Droq packet processor sceduler
+ * @param oct octeon device
+ */
+static void liquidio_schedule_droq_pkt_handlers(struct octeon_device *oct)
+{
+	struct octeon_device_priv *oct_priv =
+		(struct octeon_device_priv *)oct->priv;
+	struct octeon_droq *droq;
+	u64 oq_no;
+
+	if (oct->int_status & OCT_DEV_INTR_PKT_DATA) {
+		for (oq_no = 0; oq_no < MAX_OCTEON_OUTPUT_QUEUES(oct);
+		     oq_no++) {
+			if (!(oct->droq_intr & BIT_ULL(oq_no)))
+				continue;
+
+			droq = oct->droq[oq_no];
+
+			if (droq->ops.poll_mode) {
+				droq->ops.napi_fn(droq);
+				oct_priv->napi_mask |= (1 << oq_no);
+			} else {
+				tasklet_schedule(&oct_priv->droq_tasklet);
+			}
+		}
+	}
+}
+
+/**
+ * \brief Interrupt handler for octeon
+ * @param irq unused
+ * @param dev octeon device
+ */
+static
+irqreturn_t liquidio_legacy_intr_handler(int irq __attribute__((unused)),
+					 void *dev)
+{
+	struct octeon_device *oct = (struct octeon_device *)dev;
+	irqreturn_t ret;
+
+	/* Disable our interrupts for the duration of ISR */
+	oct->fn_list.disable_interrupt(oct, OCTEON_ALL_INTR);
+
+	ret = oct->fn_list.process_interrupt_regs(oct);
+
+	if (ret == IRQ_HANDLED)
+		liquidio_schedule_droq_pkt_handlers(oct);
+
+	/* Re-enable our interrupts  */
+	if (!(atomic_read(&oct->status) == OCT_DEV_IN_RESET))
+		oct->fn_list.enable_interrupt(oct, OCTEON_ALL_INTR);
+
+	return ret;
+}
+
+/**
+ * \brief Setup interrupt for octeon device
+ * @param oct octeon device
+ *
+ *  Enable interrupt in Octeon device as given in the PCI interrupt mask.
+ */
+int octeon_setup_interrupt(struct octeon_device *oct, u32 num_ioqs)
+{
+	struct msix_entry *msix_entries;
+	char *queue_irq_names = NULL;
+	int i, num_interrupts = 0;
+	int num_alloc_ioq_vectors;
+	char *aux_irq_name = NULL;
+	int num_ioq_vectors;
+	int irqret, err;
+
+	oct->num_msix_irqs = num_ioqs;
+	if (oct->msix_on) {
+		if (OCTEON_CN23XX_PF(oct)) {
+			num_interrupts = MAX_IOQ_INTERRUPTS_PER_PF + 1;
+
+			/* one non ioq interrupt for handling
+			 * sli_mac_pf_int_sum
+			 */
+			oct->num_msix_irqs += 1;
+		} else if (OCTEON_CN23XX_VF(oct)) {
+			num_interrupts = MAX_IOQ_INTERRUPTS_PER_VF;
+		}
+
+		/* allocate storage for the names assigned to each irq */
+		oct->irq_name_storage =
+			kcalloc(num_interrupts, INTRNAMSIZ, GFP_KERNEL);
+		if (!oct->irq_name_storage) {
+			dev_err(&oct->pci_dev->dev, "Irq name storage alloc failed...\n");
+			return -ENOMEM;
+		}
+
+		queue_irq_names = oct->irq_name_storage;
+
+		if (OCTEON_CN23XX_PF(oct))
+			aux_irq_name = &queue_irq_names
+				[IRQ_NAME_OFF(MAX_IOQ_INTERRUPTS_PER_PF)];
+
+		oct->msix_entries = kcalloc(oct->num_msix_irqs,
+					    sizeof(struct msix_entry),
+					    GFP_KERNEL);
+		if (!oct->msix_entries) {
+			dev_err(&oct->pci_dev->dev, "Memory Alloc failed...\n");
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
+			return -ENOMEM;
+		}
+
+		msix_entries = (struct msix_entry *)oct->msix_entries;
+
+		/*Assumption is that pf msix vectors start from pf srn to pf to
+		 * trs and not from 0. if not change this code
+		 */
+		if (OCTEON_CN23XX_PF(oct)) {
+			for (i = 0; i < oct->num_msix_irqs - 1; i++)
+				msix_entries[i].entry =
+					oct->sriov_info.pf_srn + i;
+
+			msix_entries[oct->num_msix_irqs - 1].entry =
+				oct->sriov_info.trs;
+		} else if (OCTEON_CN23XX_VF(oct)) {
+			for (i = 0; i < oct->num_msix_irqs; i++)
+				msix_entries[i].entry = i;
+		}
+		num_alloc_ioq_vectors = pci_enable_msix_range(
+						oct->pci_dev, msix_entries,
+						oct->num_msix_irqs,
+						oct->num_msix_irqs);
+		if (num_alloc_ioq_vectors < 0) {
+			dev_err(&oct->pci_dev->dev, "unable to Allocate MSI-X interrupts\n");
+			kfree(oct->msix_entries);
+			oct->msix_entries = NULL;
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
+			return num_alloc_ioq_vectors;
+		}
+
+		dev_dbg(&oct->pci_dev->dev, "OCTEON: Enough MSI-X interrupts are allocated...\n");
+
+		num_ioq_vectors = oct->num_msix_irqs;
+		/** For PF, there is one non-ioq interrupt handler */
+		if (OCTEON_CN23XX_PF(oct)) {
+			num_ioq_vectors -= 1;
+
+			snprintf(aux_irq_name, INTRNAMSIZ,
+				 "LiquidIO%u-pf%u-aux", oct->octeon_id,
+				 oct->pf_num);
+			irqret = request_irq(
+					msix_entries[num_ioq_vectors].vector,
+					liquidio_legacy_intr_handler, 0,
+					aux_irq_name, oct);
+			if (irqret) {
+				dev_err(&oct->pci_dev->dev,
+					"Request_irq failed for MSIX interrupt Error: %d\n",
+					irqret);
+				pci_disable_msix(oct->pci_dev);
+				kfree(oct->msix_entries);
+				kfree(oct->irq_name_storage);
+				oct->irq_name_storage = NULL;
+				oct->msix_entries = NULL;
+				return irqret;
+			}
+		}
+		for (i = 0 ; i < num_ioq_vectors ; i++) {
+			if (OCTEON_CN23XX_PF(oct))
+				snprintf(&queue_irq_names[IRQ_NAME_OFF(i)],
+					 INTRNAMSIZ, "LiquidIO%u-pf%u-rxtx-%u",
+					 oct->octeon_id, oct->pf_num, i);
+
+			if (OCTEON_CN23XX_VF(oct))
+				snprintf(&queue_irq_names[IRQ_NAME_OFF(i)],
+					 INTRNAMSIZ, "LiquidIO%u-vf%u-rxtx-%u",
+					 oct->octeon_id, oct->vf_num, i);
+
+			irqret = request_irq(msix_entries[i].vector,
+					     liquidio_msix_intr_handler, 0,
+					     &queue_irq_names[IRQ_NAME_OFF(i)],
+					     &oct->ioq_vector[i]);
+
+			if (irqret) {
+				dev_err(&oct->pci_dev->dev,
+					"Request_irq failed for MSIX interrupt Error: %d\n",
+					irqret);
+				/** Freeing the non-ioq irq vector here . */
+				free_irq(msix_entries[num_ioq_vectors].vector,
+					 oct);
+
+				while (i) {
+					i--;
+					/** clearing affinity mask. */
+					irq_set_affinity_hint(
+						      msix_entries[i].vector,
+						      NULL);
+					free_irq(msix_entries[i].vector,
+						 &oct->ioq_vector[i]);
+				}
+				pci_disable_msix(oct->pci_dev);
+				kfree(oct->msix_entries);
+				kfree(oct->irq_name_storage);
+				oct->irq_name_storage = NULL;
+				oct->msix_entries = NULL;
+				return irqret;
+			}
+			oct->ioq_vector[i].vector = msix_entries[i].vector;
+			/* assign the cpu mask for this msix interrupt vector */
+			irq_set_affinity_hint(msix_entries[i].vector,
+					      &oct->ioq_vector[i].affinity_mask
+					      );
+		}
+		dev_dbg(&oct->pci_dev->dev, "OCTEON[%d]: MSI-X enabled\n",
+			oct->octeon_id);
+	} else {
+		err = pci_enable_msi(oct->pci_dev);
+		if (err)
+			dev_warn(&oct->pci_dev->dev, "Reverting to legacy interrupts. Error: %d\n",
+				 err);
+		else
+			oct->flags |= LIO_FLAG_MSI_ENABLED;
+
+		/* allocate storage for the names assigned to the irq */
+		oct->irq_name_storage = kcalloc(1, INTRNAMSIZ, GFP_KERNEL);
+		if (!oct->irq_name_storage)
+			return -ENOMEM;
+
+		queue_irq_names = oct->irq_name_storage;
+
+		if (OCTEON_CN23XX_PF(oct))
+			snprintf(&queue_irq_names[IRQ_NAME_OFF(0)], INTRNAMSIZ,
+				 "LiquidIO%u-pf%u-rxtx-%u",
+				 oct->octeon_id, oct->pf_num, 0);
+
+		if (OCTEON_CN23XX_VF(oct))
+			snprintf(&queue_irq_names[IRQ_NAME_OFF(0)], INTRNAMSIZ,
+				 "LiquidIO%u-vf%u-rxtx-%u",
+				 oct->octeon_id, oct->vf_num, 0);
+
+		irqret = request_irq(oct->pci_dev->irq,
+				     liquidio_legacy_intr_handler,
+				     IRQF_SHARED,
+				     &queue_irq_names[IRQ_NAME_OFF(0)], oct);
+		if (irqret) {
+			if (oct->flags & LIO_FLAG_MSI_ENABLED)
+				pci_disable_msi(oct->pci_dev);
+			dev_err(&oct->pci_dev->dev, "Request IRQ failed with code: %d\n",
+				irqret);
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
+			return irqret;
+		}
+	}
+	return 0;
+}