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

Pull networking updates from David Miller:
 "Highlights (1721 non-merge commits, this has to be a record of some
  sort):

   1) Add 'random' mode to team driver, from Jiri Pirko and Eric
      Dumazet.

   2) Make it so that any driver that supports configuration of multiple
      MAC addresses can provide the forwarding database add and del
      calls by providing a default implementation and hooking that up if
      the driver doesn't have an explicit set of handlers.  From Vlad
      Yasevich.

   3) Support GSO segmentation over tunnels and other encapsulating
      devices such as VXLAN, from Pravin B Shelar.

   4) Support L2 GRE tunnels in the flow dissector, from Michael Dalton.

   5) Implement Tail Loss Probe (TLP) detection in TCP, from Nandita
      Dukkipati.

   6) In the PHY layer, allow supporting wake-on-lan in situations where
      the PHY registers have to be written for it to be configured.

      Use it to support wake-on-lan in mv643xx_eth.

      From Michael Stapelberg.

   7) Significantly improve firewire IPV6 support, from YOSHIFUJI
      Hideaki.

   8) Allow multiple packets to be sent in a single transmission using
      network coding in batman-adv, from Martin Hundebøll.

   9) Add support for T5 cxgb4 chips, from Santosh Rastapur.

  10) Generalize the VXLAN forwarding tables so that there is more
      flexibility in configurating various aspects of the endpoints.
      From David Stevens.

  11) Support RSS and TSO in hardware over GRE tunnels in bxn2x driver,
      from Dmitry Kravkov.

  12) Zero copy support in nfnelink_queue, from Eric Dumazet and Pablo
      Neira Ayuso.

  13) Start adding networking selftests.

  14) In situations of overload on the same AF_PACKET fanout socket, or
      per-cpu packet receive queue, minimize drop by distributing the
      load to other cpus/fanouts.  From Willem de Bruijn and Eric
      Dumazet.

  15) Add support for new payload offset BPF instruction, from Daniel
      Borkmann.

  16) Convert several drivers over to mdoule_platform_driver(), from
      Sachin Kamat.

  17) Provide a minimal BPF JIT image disassembler userspace tool, from
      Daniel Borkmann.

  18) Rewrite F-RTO implementation in TCP to match the final
      specification of it in RFC4138 and RFC5682.  From Yuchung Cheng.

  19) Provide netlink socket diag of netlink sockets ("Yo dawg, I hear
      you like netlink, so I implemented netlink dumping of netlink
      sockets.") From Andrey Vagin.

  20) Remove ugly passing of rtnetlink attributes into rtnl_doit
      functions, from Thomas Graf.

  21) Allow userspace to be able to see if a configuration change occurs
      in the middle of an address or device list dump, from Nicolas
      Dichtel.

  22) Support RFC3168 ECN protection for ipv6 fragments, from Hannes
      Frederic Sowa.

  23) Increase accuracy of packet length used by packet scheduler, from
      Jason Wang.

  24) Beginning set of changes to make ipv4/ipv6 fragment handling more
      scalable and less susceptible to overload and locking contention,
      from Jesper Dangaard Brouer.

  25) Get rid of using non-type-safe NLMSG_* macros and use nlmsg_*()
      instead.  From Hong Zhiguo.

  26) Optimize route usage in IPVS by avoiding reference counting where
      possible, from Julian Anastasov.

  27) Convert IPVS schedulers to RCU, also from Julian Anastasov.

  28) Support cpu fanouts in xt_NFQUEUE netfilter target, from Holger
      Eitzenberger.

  29) Network namespace support for nf_log, ebt_log, xt_LOG, ipt_ULOG,
      nfnetlink_log, and nfnetlink_queue.  From Gao feng.

  30) Implement RFC3168 ECN protection, from Hannes Frederic Sowa.

  31) Support several new r8169 chips, from Hayes Wang.

  32) Support tokenized interface identifiers in ipv6, from Daniel
      Borkmann.

  33) Use usbnet_link_change() helper in USB net driver, from Ming Lei.

  34) Add 802.1ad vlan offload support, from Patrick McHardy.

  35) Support mmap() based netlink communication, also from Patrick
      McHardy.

  36) Support HW timestamping in mlx4 driver, from Amir Vadai.

  37) Rationalize AF_PACKET packet timestamping when transmitting, from
      Willem de Bruijn and Daniel Borkmann.

  38) Bring parity to what's provided by /proc/net/packet socket dumping
      and the info provided by netlink socket dumping of AF_PACKET
      sockets.  From Nicolas Dichtel.

  39) Fix peeking beyond zero sized SKBs in AF_UNIX, from Benjamin
      Poirier"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits)
  filter: fix va_list build error
  af_unix: fix a fatal race with bit fields
  bnx2x: Prevent memory leak when cnic is absent
  bnx2x: correct reading of speed capabilities
  net: sctp: attribute printl with __printf for gcc fmt checks
  netlink: kconfig: move mmap i/o into netlink kconfig
  netpoll: convert mutex into a semaphore
  netlink: Fix skb ref counting.
  net_sched: act_ipt forward compat with xtables
  mlx4_en: fix a build error on 32bit arches
  Revert "bnx2x: allow nvram test to run when device is down"
  bridge: avoid OOPS if root port not found
  drivers: net: cpsw: fix kernel warn on cpsw irq enable
  sh_eth: use random MAC address if no valid one supplied
  3c509.c: call SET_NETDEV_DEV for all device types (ISA/ISAPnP/EISA)
  tg3: fix to append hardware time stamping flags
  unix/stream: fix peeking with an offset larger than data in queue
  unix/dgram: fix peeking with an offset larger than data in queue
  unix/dgram: peek beyond 0-sized skbs
  openvswitch: Remove unneeded ovs_netdev_get_ifindex()
  ...

8 files changed, 648 insertions, 223 deletions

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 29aff55f2eea..234ce6f07544 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2011 Emulex
+ * Copyright (C) 2005 - 2013 Emulex
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -214,6 +214,7 @@ struct be_tx_stats {
 };
 
 struct be_tx_obj {
+	u32 db_offset;
 	struct be_queue_info q;
 	struct be_queue_info cq;
 	/* Remember the skbs that were transmitted */
@@ -292,7 +293,7 @@ struct be_drv_stats {
 	u32 rx_in_range_errors;
 	u32 rx_out_range_errors;
 	u32 rx_frame_too_long;
-	u32 rx_address_mismatch_drops;
+	u32 rx_address_filtered;
 	u32 rx_dropped_too_small;
 	u32 rx_dropped_too_short;
 	u32 rx_dropped_header_too_small;
@@ -328,6 +329,7 @@ enum vf_state {
 #define BE_FLAGS_WORKER_SCHEDULED		(1 << 3)
 #define BE_UC_PMAC_COUNT		30
 #define BE_VF_UC_PMAC_COUNT		2
+#define BE_FLAGS_QNQ_ASYNC_EVT_RCVD		(1 << 11)
 
 struct phy_info {
 	u8 transceiver;
@@ -434,6 +436,8 @@ struct be_adapter {
 	u8 wol_cap;
 	bool wol;
 	u32 uc_macs;		/* Count of secondary UC MAC programmed */
+	u16 asic_rev;
+	u16 qnq_vid;
 	u32 msg_enable;
 	int be_get_temp_freq;
 	u16 max_mcast_mac;
@@ -445,6 +449,7 @@ struct be_adapter {
 	u16 max_event_queues;
 	u32 if_cap_flags;
 	u8 pf_number;
+	u64 rss_flags;
 };
 
 #define be_physfn(adapter)		(!adapter->virtfn)
@@ -648,6 +653,11 @@ static inline bool be_is_wol_excluded(struct be_adapter *adapter)
 	}
 }
 
+static inline int qnq_async_evt_rcvd(struct be_adapter *adapter)
+{
+	return adapter->flags & BE_FLAGS_QNQ_ASYNC_EVT_RCVD;
+}
+
 extern void be_cq_notify(struct be_adapter *adapter, u16 qid, bool arm,
 		u16 num_popped);
 extern void be_link_status_update(struct be_adapter *adapter, u8 link_status);
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 3c9b4f12e3e5..25d3290b8cac 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2011 Emulex
+ * Copyright (C) 2005 - 2013 Emulex
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -263,6 +263,27 @@ static void be_async_grp5_evt_process(struct be_adapter *adapter,
 	}
 }
 
+static void be_async_dbg_evt_process(struct be_adapter *adapter,
+		u32 trailer, struct be_mcc_compl *cmp)
+{
+	u8 event_type = 0;
+	struct be_async_event_qnq *evt = (struct be_async_event_qnq *) cmp;
+
+	event_type = (trailer >> ASYNC_TRAILER_EVENT_TYPE_SHIFT) &
+		ASYNC_TRAILER_EVENT_TYPE_MASK;
+
+	switch (event_type) {
+	case ASYNC_DEBUG_EVENT_TYPE_QNQ:
+		if (evt->valid)
+			adapter->qnq_vid = le16_to_cpu(evt->vlan_tag);
+		adapter->flags |= BE_FLAGS_QNQ_ASYNC_EVT_RCVD;
+	break;
+	default:
+		dev_warn(&adapter->pdev->dev, "Unknown debug event\n");
+	break;
+	}
+}
+
 static inline bool is_link_state_evt(u32 trailer)
 {
 	return ((trailer >> ASYNC_TRAILER_EVENT_CODE_SHIFT) &
@@ -277,6 +298,13 @@ static inline bool is_grp5_evt(u32 trailer)
 				ASYNC_EVENT_CODE_GRP_5);
 }
 
+static inline bool is_dbg_evt(u32 trailer)
+{
+	return (((trailer >> ASYNC_TRAILER_EVENT_CODE_SHIFT) &
+		ASYNC_TRAILER_EVENT_CODE_MASK) ==
+				ASYNC_EVENT_CODE_QNQ);
+}
+
 static struct be_mcc_compl *be_mcc_compl_get(struct be_adapter *adapter)
 {
 	struct be_queue_info *mcc_cq = &adapter->mcc_obj.cq;
@@ -325,6 +353,9 @@ int be_process_mcc(struct be_adapter *adapter)
 			else if (is_grp5_evt(compl->flags))
 				be_async_grp5_evt_process(adapter,
 				compl->flags, compl);
+			else if (is_dbg_evt(compl->flags))
+				be_async_dbg_evt_process(adapter,
+				compl->flags, compl);
 		} else if (compl->flags & CQE_FLAGS_COMPLETED_MASK) {
 				status = be_mcc_compl_process(adapter, compl);
 				atomic_dec(&mcc_obj->q.used);
@@ -687,10 +718,8 @@ static struct be_mcc_wrb *wrb_from_mccq(struct be_adapter *adapter)
 	if (!mccq->created)
 		return NULL;
 
-	if (atomic_read(&mccq->used) >= mccq->len) {
-		dev_err(&adapter->pdev->dev, "Out of MCCQ wrbs\n");
+	if (atomic_read(&mccq->used) >= mccq->len)
 		return NULL;
-	}
 
 	wrb = queue_head_node(mccq);
 	queue_head_inc(mccq);
@@ -1022,6 +1051,7 @@ int be_cmd_mccq_ext_create(struct be_adapter *adapter,
 
 	/* Subscribe to Link State and Group 5 Events(bits 1 and 5 set) */
 	req->async_event_bitmap[0] = cpu_to_le32(0x00000022);
+	req->async_event_bitmap[0] |= cpu_to_le32(1 << ASYNC_EVENT_CODE_QNQ);
 	be_dws_cpu_to_le(ctxt, sizeof(req->context));
 
 	be_cmd_page_addrs_prepare(req->pages, ARRAY_SIZE(req->pages), q_mem);
@@ -1095,15 +1125,14 @@ int be_cmd_mccq_create(struct be_adapter *adapter,
 	return status;
 }
 
-int be_cmd_txq_create(struct be_adapter *adapter,
-			struct be_queue_info *txq,
-			struct be_queue_info *cq)
+int be_cmd_txq_create(struct be_adapter *adapter, struct be_tx_obj *txo)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_eth_tx_create *req;
+	struct be_queue_info *txq = &txo->q;
+	struct be_queue_info *cq = &txo->cq;
 	struct be_dma_mem *q_mem = &txq->dma_mem;
-	void *ctxt;
-	int status;
+	int status, ver = 0;
 
 	spin_lock_bh(&adapter->mcc_lock);
 
@@ -1114,34 +1143,37 @@ int be_cmd_txq_create(struct be_adapter *adapter,
 	}
 
 	req = embedded_payload(wrb);
-	ctxt = &req->context;
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ETH,
 		OPCODE_ETH_TX_CREATE, sizeof(*req), wrb, NULL);
 
 	if (lancer_chip(adapter)) {
 		req->hdr.version = 1;
-		AMAP_SET_BITS(struct amap_tx_context, if_id, ctxt,
-					adapter->if_handle);
+		req->if_id = cpu_to_le16(adapter->if_handle);
+	} else if (BEx_chip(adapter)) {
+		if (adapter->function_caps & BE_FUNCTION_CAPS_SUPER_NIC)
+			req->hdr.version = 2;
+	} else { /* For SH */
+		req->hdr.version = 2;
 	}
 
 	req->num_pages = PAGES_4K_SPANNED(q_mem->va, q_mem->size);
 	req->ulp_num = BE_ULP1_NUM;
 	req->type = BE_ETH_TX_RING_TYPE_STANDARD;
-
-	AMAP_SET_BITS(struct amap_tx_context, tx_ring_size, ctxt,
-		be_encoded_q_len(txq->len));
-	AMAP_SET_BITS(struct amap_tx_context, ctx_valid, ctxt, 1);
-	AMAP_SET_BITS(struct amap_tx_context, cq_id_send, ctxt, cq->id);
-
-	be_dws_cpu_to_le(ctxt, sizeof(req->context));
-
+	req->cq_id = cpu_to_le16(cq->id);
+	req->queue_size = be_encoded_q_len(txq->len);
 	be_cmd_page_addrs_prepare(req->pages, ARRAY_SIZE(req->pages), q_mem);
 
+	ver = req->hdr.version;
+
 	status = be_mcc_notify_wait(adapter);
 	if (!status) {
 		struct be_cmd_resp_eth_tx_create *resp = embedded_payload(wrb);
 		txq->id = le16_to_cpu(resp->cid);
+		if (ver == 2)
+			txo->db_offset = le32_to_cpu(resp->db_offset);
+		else
+			txo->db_offset = DB_TXULP1_OFFSET;
 		txq->created = true;
 	}
 
@@ -1834,7 +1866,7 @@ err:
 
 /* Uses mbox */
 int be_cmd_query_fw_cfg(struct be_adapter *adapter, u32 *port_num,
-		u32 *mode, u32 *caps)
+			u32 *mode, u32 *caps, u16 *asic_rev)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_query_fw_cfg *req;
@@ -1855,6 +1887,7 @@ int be_cmd_query_fw_cfg(struct be_adapter *adapter, u32 *port_num,
 		*port_num = le32_to_cpu(resp->phys_port);
 		*mode = le32_to_cpu(resp->function_mode);
 		*caps = le32_to_cpu(resp->function_caps);
+		*asic_rev = le32_to_cpu(resp->asic_revision) & 0xFF;
 	}
 
 	mutex_unlock(&adapter->mbox_lock);
@@ -1897,7 +1930,8 @@ int be_cmd_reset_function(struct be_adapter *adapter)
 	return status;
 }
 
-int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable, u16 table_size)
+int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable,
+			u32 rss_hash_opts, u16 table_size)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_rss_config *req;
@@ -1916,16 +1950,12 @@ int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable, u16 table_size)
 		OPCODE_ETH_RSS_CONFIG, sizeof(*req), wrb, NULL);
 
 	req->if_id = cpu_to_le32(adapter->if_handle);
-	req->enable_rss = cpu_to_le16(RSS_ENABLE_TCP_IPV4 | RSS_ENABLE_IPV4 |
-				      RSS_ENABLE_TCP_IPV6 | RSS_ENABLE_IPV6);
+	req->enable_rss = cpu_to_le16(rss_hash_opts);
+	req->cpu_table_size_log2 = cpu_to_le16(fls(table_size) - 1);
 
-	if (lancer_chip(adapter) || skyhawk_chip(adapter)) {
+	if (lancer_chip(adapter) || skyhawk_chip(adapter))
 		req->hdr.version = 1;
-		req->enable_rss |= cpu_to_le16(RSS_ENABLE_UDP_IPV4 |
-					       RSS_ENABLE_UDP_IPV6);
-	}
 
-	req->cpu_table_size_log2 = cpu_to_le16(fls(table_size) - 1);
 	memcpy(req->cpu_table, rsstable, table_size);
 	memcpy(req->hash, myhash, sizeof(myhash));
 	be_dws_cpu_to_le(req->hash, sizeof(req->hash));
@@ -2343,7 +2373,6 @@ int be_cmd_get_seeprom_data(struct be_adapter *adapter,
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_seeprom_read *req;
-	struct be_sge *sge;
 	int status;
 
 	spin_lock_bh(&adapter->mcc_lock);
@@ -2354,7 +2383,6 @@ int be_cmd_get_seeprom_data(struct be_adapter *adapter,
 		goto err;
 	}
 	req = nonemb_cmd->va;
-	sge = nonembedded_sgl(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
 			OPCODE_COMMON_SEEPROM_READ, sizeof(*req), wrb,
@@ -2461,6 +2489,9 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter)
 	struct mgmt_controller_attrib *attribs;
 	struct be_dma_mem attribs_cmd;
 
+	if (mutex_lock_interruptible(&adapter->mbox_lock))
+		return -1;
+
 	memset(&attribs_cmd, 0, sizeof(struct be_dma_mem));
 	attribs_cmd.size = sizeof(struct be_cmd_resp_cntl_attribs);
 	attribs_cmd.va = pci_alloc_consistent(adapter->pdev, attribs_cmd.size,
@@ -2468,12 +2499,10 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter)
 	if (!attribs_cmd.va) {
 		dev_err(&adapter->pdev->dev,
 				"Memory allocation failure\n");
-		return -ENOMEM;
+		status = -ENOMEM;
+		goto err;
 	}
 
-	if (mutex_lock_interruptible(&adapter->mbox_lock))
-		return -1;
-
 	wrb = wrb_from_mbox(adapter);
 	if (!wrb) {
 		status = -EBUSY;
@@ -2493,8 +2522,9 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter)
 
 err:
 	mutex_unlock(&adapter->mbox_lock);
-	pci_free_consistent(adapter->pdev, attribs_cmd.size, attribs_cmd.va,
-					attribs_cmd.dma);
+	if (attribs_cmd.va)
+		pci_free_consistent(adapter->pdev, attribs_cmd.size,
+				    attribs_cmd.va, attribs_cmd.dma);
 	return status;
 }
 
@@ -2667,10 +2697,8 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 	cmd.size = sizeof(struct be_cmd_req_set_mac_list);
 	cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size,
 			&cmd.dma, GFP_KERNEL);
-	if (!cmd.va) {
-		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
+	if (!cmd.va)
 		return -ENOMEM;
-	}
 
 	spin_lock_bh(&adapter->mcc_lock);
 
@@ -2794,6 +2822,9 @@ int be_cmd_get_acpi_wol_cap(struct be_adapter *adapter)
 			    CMD_SUBSYSTEM_ETH))
 		return -EPERM;
 
+	if (mutex_lock_interruptible(&adapter->mbox_lock))
+		return -1;
+
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_acpi_wol_magic_config_v1);
 	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size,
@@ -2801,12 +2832,10 @@ int be_cmd_get_acpi_wol_cap(struct be_adapter *adapter)
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev,
 				"Memory allocation failure\n");
-		return -ENOMEM;
+		status = -ENOMEM;
+		goto err;
 	}
 
-	if (mutex_lock_interruptible(&adapter->mbox_lock))
-		return -1;
-
 	wrb = wrb_from_mbox(adapter);
 	if (!wrb) {
 		status = -EBUSY;
@@ -2837,7 +2866,8 @@ int be_cmd_get_acpi_wol_cap(struct be_adapter *adapter)
 	}
 err:
 	mutex_unlock(&adapter->mbox_lock);
-	pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+	if (cmd.va)
+		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
 	return status;
 
 }
@@ -2942,14 +2972,15 @@ static struct be_nic_resource_desc *be_get_nic_desc(u8 *buf, u32 desc_count,
 	int i;
 
 	for (i = 0; i < desc_count; i++) {
-		desc->desc_len = RESOURCE_DESC_SIZE;
+		desc->desc_len = desc->desc_len ? : RESOURCE_DESC_SIZE;
 		if (((void *)desc + desc->desc_len) >
 		    (void *)(buf + max_buf_size)) {
 			desc = NULL;
 			break;
 		}
 
-		if (desc->desc_type == NIC_RESOURCE_DESC_TYPE_ID)
+		if (desc->desc_type == NIC_RESOURCE_DESC_TYPE_V0 ||
+		    desc->desc_type == NIC_RESOURCE_DESC_TYPE_V1)
 			break;
 
 		desc = (void *)desc + desc->desc_len;
@@ -2969,16 +3000,18 @@ int be_cmd_get_func_config(struct be_adapter *adapter)
 	int status;
 	struct be_dma_mem cmd;
 
+	if (mutex_lock_interruptible(&adapter->mbox_lock))
+		return -1;
+
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_get_func_config);
 	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size,
 				      &cmd.dma);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
-		return -ENOMEM;
+		status = -ENOMEM;
+		goto err;
 	}
-	if (mutex_lock_interruptible(&adapter->mbox_lock))
-		return -1;
 
 	wrb = wrb_from_mbox(adapter);
 	if (!wrb) {
@@ -2992,6 +3025,9 @@ int be_cmd_get_func_config(struct be_adapter *adapter)
 			       OPCODE_COMMON_GET_FUNC_CONFIG,
 			       cmd.size, wrb, &cmd);
 
+	if (skyhawk_chip(adapter))
+		req->hdr.version = 1;
+
 	status = be_mbox_notify_wait(adapter);
 	if (!status) {
 		struct be_cmd_resp_get_func_config *resp = cmd.va;
@@ -3018,28 +3054,46 @@ int be_cmd_get_func_config(struct be_adapter *adapter)
 	}
 err:
 	mutex_unlock(&adapter->mbox_lock);
-	pci_free_consistent(adapter->pdev, cmd.size,
-			    cmd.va, cmd.dma);
+	if (cmd.va)
+		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
 	return status;
 }
 
- /* Uses sync mcc */
-int be_cmd_get_profile_config(struct be_adapter *adapter, u32 *cap_flags,
-			      u8 domain)
+/* Uses mbox */
+int be_cmd_get_profile_config_mbox(struct be_adapter *adapter,
+				   u8 domain, struct be_dma_mem *cmd)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_get_profile_config *req;
 	int status;
-	struct be_dma_mem cmd;
 
-	memset(&cmd, 0, sizeof(struct be_dma_mem));
-	cmd.size = sizeof(struct be_cmd_resp_get_profile_config);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size,
-				      &cmd.dma);
-	if (!cmd.va) {
-		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
-		return -ENOMEM;
-	}
+	if (mutex_lock_interruptible(&adapter->mbox_lock))
+		return -1;
+	wrb = wrb_from_mbox(adapter);
+
+	req = cmd->va;
+	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+			       OPCODE_COMMON_GET_PROFILE_CONFIG,
+			       cmd->size, wrb, cmd);
+
+	req->type = ACTIVE_PROFILE_TYPE;
+	req->hdr.domain = domain;
+	if (!lancer_chip(adapter))
+		req->hdr.version = 1;
+
+	status = be_mbox_notify_wait(adapter);
+
+	mutex_unlock(&adapter->mbox_lock);
+	return status;
+}
+
+/* Uses sync mcc */
+int be_cmd_get_profile_config_mccq(struct be_adapter *adapter,
+				   u8 domain, struct be_dma_mem *cmd)
+{
+	struct be_mcc_wrb *wrb;
+	struct be_cmd_req_get_profile_config *req;
+	int status;
 
 	spin_lock_bh(&adapter->mcc_lock);
 
@@ -3049,16 +3103,47 @@ int be_cmd_get_profile_config(struct be_adapter *adapter, u32 *cap_flags,
 		goto err;
 	}
 
-	req = cmd.va;
-
+	req = cmd->va;
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
 			       OPCODE_COMMON_GET_PROFILE_CONFIG,
-			       cmd.size, wrb, &cmd);
+			       cmd->size, wrb, cmd);
 
 	req->type = ACTIVE_PROFILE_TYPE;
 	req->hdr.domain = domain;
+	if (!lancer_chip(adapter))
+		req->hdr.version = 1;
 
 	status = be_mcc_notify_wait(adapter);
+
+err:
+	spin_unlock_bh(&adapter->mcc_lock);
+	return status;
+}
+
+/* Uses sync mcc, if MCCQ is already created otherwise mbox */
+int be_cmd_get_profile_config(struct be_adapter *adapter, u32 *cap_flags,
+			      u16 *txq_count, u8 domain)
+{
+	struct be_queue_info *mccq = &adapter->mcc_obj.q;
+	struct be_dma_mem cmd;
+	int status;
+
+	memset(&cmd, 0, sizeof(struct be_dma_mem));
+	if (!lancer_chip(adapter))
+		cmd.size = sizeof(struct be_cmd_resp_get_profile_config_v1);
+	else
+		cmd.size = sizeof(struct be_cmd_resp_get_profile_config);
+	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size,
+				      &cmd.dma);
+	if (!cmd.va) {
+		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
+		return -ENOMEM;
+	}
+
+	if (!mccq->created)
+		status = be_cmd_get_profile_config_mbox(adapter, domain, &cmd);
+	else
+		status = be_cmd_get_profile_config_mccq(adapter, domain, &cmd);
 	if (!status) {
 		struct be_cmd_resp_get_profile_config *resp = cmd.va;
 		u32 desc_count = le32_to_cpu(resp->desc_count);
@@ -3071,12 +3156,15 @@ int be_cmd_get_profile_config(struct be_adapter *adapter, u32 *cap_flags,
 			status = -EINVAL;
 			goto err;
 		}
-		*cap_flags = le32_to_cpu(desc->cap_flags);
+		if (cap_flags)
+			*cap_flags = le32_to_cpu(desc->cap_flags);
+		if (txq_count)
+			*txq_count = le32_to_cpu(desc->txq_count);
 	}
 err:
-	spin_unlock_bh(&adapter->mcc_lock);
-	pci_free_consistent(adapter->pdev, cmd.size,
-			    cmd.va, cmd.dma);
+	if (cmd.va)
+		pci_free_consistent(adapter->pdev, cmd.size,
+				    cmd.va, cmd.dma);
 	return status;
 }
 
@@ -3105,7 +3193,7 @@ int be_cmd_set_profile_config(struct be_adapter *adapter, u32 bps,
 	req->hdr.domain = domain;
 	req->desc_count = cpu_to_le32(1);
 
-	req->nic_desc.desc_type = NIC_RESOURCE_DESC_TYPE_ID;
+	req->nic_desc.desc_type = NIC_RESOURCE_DESC_TYPE_V0;
 	req->nic_desc.desc_len = RESOURCE_DESC_SIZE;
 	req->nic_desc.flags = (1 << QUN) | (1 << IMM) | (1 << NOSV);
 	req->nic_desc.pf_num = adapter->pf_number;
@@ -3202,6 +3290,31 @@ err:
 	return status;
 }
 
+int be_cmd_intr_set(struct be_adapter *adapter, bool intr_enable)
+{
+	struct be_mcc_wrb *wrb;
+	struct be_cmd_req_intr_set *req;
+	int status;
+
+	if (mutex_lock_interruptible(&adapter->mbox_lock))
+		return -1;
+
+	wrb = wrb_from_mbox(adapter);
+
+	req = embedded_payload(wrb);
+
+	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+			       OPCODE_COMMON_SET_INTERRUPT_ENABLE, sizeof(*req),
+			       wrb, NULL);
+
+	req->intr_enabled = intr_enable;
+
+	status = be_mbox_notify_wait(adapter);
+
+	mutex_unlock(&adapter->mbox_lock);
+	return status;
+}
+
 int be_roce_mcc_cmd(void *netdev_handle, void *wrb_payload,
 			int wrb_payload_size, u16 *cmd_status, u16 *ext_status)
 {
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index 96970860c915..a855668e0cc5 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2011 Emulex
+ * Copyright (C) 2005 - 2013 Emulex
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -84,6 +84,9 @@ struct be_mcc_compl {
 #define ASYNC_EVENT_QOS_SPEED		0x1
 #define ASYNC_EVENT_COS_PRIORITY	0x2
 #define ASYNC_EVENT_PVID_STATE		0x3
+#define ASYNC_EVENT_CODE_QNQ		0x6
+#define ASYNC_DEBUG_EVENT_TYPE_QNQ	1
+
 struct be_async_event_trailer {
 	u32 code;
 };
@@ -144,6 +147,16 @@ struct be_async_event_grp5_pvid_state {
 	struct be_async_event_trailer trailer;
 } __packed;
 
+/* async event indicating outer VLAN tag in QnQ */
+struct be_async_event_qnq {
+	u8 valid;	/* Indicates if outer VLAN is valid */
+	u8 rsvd0;
+	u16 vlan_tag;
+	u32 event_tag;
+	u8 rsvd1[4];
+	struct be_async_event_trailer trailer;
+} __packed;
+
 struct be_mcc_mailbox {
 	struct be_mcc_wrb wrb;
 	struct be_mcc_compl compl;
@@ -188,6 +201,7 @@ struct be_mcc_mailbox {
 #define OPCODE_COMMON_GET_BEACON_STATE			70
 #define OPCODE_COMMON_READ_TRANSRECV_DATA		73
 #define OPCODE_COMMON_GET_PORT_NAME			77
+#define OPCODE_COMMON_SET_INTERRUPT_ENABLE		89
 #define OPCODE_COMMON_GET_PHY_DETAILS			102
 #define OPCODE_COMMON_SET_DRIVER_FUNCTION_CAP		103
 #define OPCODE_COMMON_GET_CNTL_ADDITIONAL_ATTRIBUTES	121
@@ -473,46 +487,27 @@ struct be_cmd_resp_mcc_create {
 #define BE_ETH_TX_RING_TYPE_STANDARD    	2
 #define BE_ULP1_NUM				1
 
-/* Pseudo amap definition in which each bit of the actual structure is defined
- * as a byte: used to calculate offset/shift/mask of each field */
-struct amap_tx_context {
-	u8 if_id[16];		/* dword 0 */
-	u8 tx_ring_size[4];	/* dword 0 */
-	u8 rsvd1[26];		/* dword 0 */
-	u8 pci_func_id[8];	/* dword 1 */
-	u8 rsvd2[9];		/* dword 1 */
-	u8 ctx_valid;		/* dword 1 */
-	u8 cq_id_send[16];	/* dword 2 */
-	u8 rsvd3[16];		/* dword 2 */
-	u8 rsvd4[32];		/* dword 3 */
-	u8 rsvd5[32];		/* dword 4 */
-	u8 rsvd6[32];		/* dword 5 */
-	u8 rsvd7[32];		/* dword 6 */
-	u8 rsvd8[32];		/* dword 7 */
-	u8 rsvd9[32];		/* dword 8 */
-	u8 rsvd10[32];		/* dword 9 */
-	u8 rsvd11[32];		/* dword 10 */
-	u8 rsvd12[32];		/* dword 11 */
-	u8 rsvd13[32];		/* dword 12 */
-	u8 rsvd14[32];		/* dword 13 */
-	u8 rsvd15[32];		/* dword 14 */
-	u8 rsvd16[32];		/* dword 15 */
-} __packed;
-
 struct be_cmd_req_eth_tx_create {
 	struct be_cmd_req_hdr hdr;
 	u8 num_pages;
 	u8 ulp_num;
-	u8 type;
-	u8 bound_port;
-	u8 context[sizeof(struct amap_tx_context) / 8];
+	u16 type;
+	u16 if_id;
+	u8 queue_size;
+	u8 rsvd0;
+	u32 rsvd1;
+	u16 cq_id;
+	u16 rsvd2;
+	u32 rsvd3[13];
 	struct phys_addr pages[8];
 } __packed;
 
 struct be_cmd_resp_eth_tx_create {
 	struct be_cmd_resp_hdr hdr;
 	u16 cid;
-	u16 rsvd0;
+	u16 rid;
+	u32 db_offset;
+	u32 rsvd0[4];
 } __packed;
 
 /******************** Create RxQ ***************************/
@@ -608,8 +603,8 @@ struct be_port_rxf_stats_v0 {
 	u32 rx_in_range_errors;	/* dword 10*/
 	u32 rx_out_range_errors;	/* dword 11*/
 	u32 rx_frame_too_long;	/* dword 12*/
-	u32 rx_address_mismatch_drops;	/* dword 13*/
-	u32 rx_vlan_mismatch_drops;	/* dword 14*/
+	u32 rx_address_filtered;	/* dword 13*/
+	u32 rx_vlan_filtered;	/* dword 14*/
 	u32 rx_dropped_too_small;	/* dword 15*/
 	u32 rx_dropped_too_short;	/* dword 16*/
 	u32 rx_dropped_header_too_small;	/* dword 17*/
@@ -815,8 +810,8 @@ struct lancer_pport_stats {
 	u32 rx_control_frames_unknown_opcode_hi;
 	u32 rx_in_range_errors;
 	u32 rx_out_of_range_errors;
-	u32 rx_address_mismatch_drops;
-	u32 rx_vlan_mismatch_drops;
+	u32 rx_address_filtered;
+	u32 rx_vlan_filtered;
 	u32 rx_dropped_too_small;
 	u32 rx_dropped_too_short;
 	u32 rx_dropped_header_too_small;
@@ -1066,7 +1061,6 @@ struct be_cmd_resp_modify_eq_delay {
 } __packed;
 
 /******************** Get FW Config *******************/
-#define BE_FUNCTION_CAPS_RSS			0x2
 /* The HW can come up in either of the following multi-channel modes
  * based on the skew/IPL.
  */
@@ -1109,6 +1103,9 @@ struct be_cmd_resp_query_fw_cfg {
 #define RSS_ENABLE_UDP_IPV4			0x10
 #define RSS_ENABLE_UDP_IPV6			0x20
 
+#define L3_RSS_FLAGS				(RXH_IP_DST | RXH_IP_SRC)
+#define L4_RSS_FLAGS				(RXH_L4_B_0_1 | RXH_L4_B_2_3)
+
 struct be_cmd_req_rss_config {
 	struct be_cmd_req_hdr hdr;
 	u32 if_id;
@@ -1592,7 +1589,7 @@ struct be_port_rxf_stats_v1 {
 	u32 rx_in_range_errors;
 	u32 rx_out_range_errors;
 	u32 rx_frame_too_long;
-	u32 rx_address_mismatch_drops;
+	u32 rx_address_filtered;
 	u32 rx_dropped_too_small;
 	u32 rx_dropped_too_short;
 	u32 rx_dropped_header_too_small;
@@ -1706,9 +1703,11 @@ struct be_cmd_req_set_ext_fat_caps {
 	struct be_fat_conf_params set_params;
 };
 
-#define RESOURCE_DESC_SIZE			72
-#define NIC_RESOURCE_DESC_TYPE_ID		0x41
+#define RESOURCE_DESC_SIZE			88
+#define NIC_RESOURCE_DESC_TYPE_V0		0x41
+#define NIC_RESOURCE_DESC_TYPE_V1		0x51
 #define MAX_RESOURCE_DESC			4
+#define MAX_RESOURCE_DESC_V1			32
 
 /* QOS unit number */
 #define QUN					4
@@ -1755,7 +1754,7 @@ struct be_cmd_req_get_func_config {
 };
 
 struct be_cmd_resp_get_func_config {
-	struct be_cmd_req_hdr hdr;
+	struct be_cmd_resp_hdr hdr;
 	u32 desc_count;
 	u8 func_param[MAX_RESOURCE_DESC * RESOURCE_DESC_SIZE];
 };
@@ -1774,6 +1773,12 @@ struct be_cmd_resp_get_profile_config {
 	u8 func_param[MAX_RESOURCE_DESC * RESOURCE_DESC_SIZE];
 };
 
+struct be_cmd_resp_get_profile_config_v1 {
+	struct be_cmd_req_hdr hdr;
+	u32 desc_count;
+	u8 func_param[MAX_RESOURCE_DESC_V1 * RESOURCE_DESC_SIZE];
+};
+
 struct be_cmd_req_set_profile_config {
 	struct be_cmd_req_hdr hdr;
 	u32 rsvd;
@@ -1791,6 +1796,12 @@ struct be_cmd_enable_disable_vf {
 	u8 rsvd[3];
 };
 
+struct be_cmd_req_intr_set {
+	struct be_cmd_req_hdr hdr;
+	u8 intr_enabled;
+	u8 rsvd[3];
+};
+
 static inline bool check_privilege(struct be_adapter *adapter, u32 flags)
 {
 	return flags & adapter->cmd_privileges ? true : false;
@@ -1834,8 +1845,7 @@ extern int be_cmd_mccq_create(struct be_adapter *adapter,
 			struct be_queue_info *mccq,
 			struct be_queue_info *cq);
 extern int be_cmd_txq_create(struct be_adapter *adapter,
-			struct be_queue_info *txq,
-			struct be_queue_info *cq);
+			struct be_tx_obj *txo);
 extern int be_cmd_rxq_create(struct be_adapter *adapter,
 			struct be_queue_info *rxq, u16 cq_id,
 			u16 frag_size, u32 if_id, u32 rss, u8 *rss_id);
@@ -1862,11 +1872,11 @@ extern int be_cmd_set_flow_control(struct be_adapter *adapter,
 			u32 tx_fc, u32 rx_fc);
 extern int be_cmd_get_flow_control(struct be_adapter *adapter,
 			u32 *tx_fc, u32 *rx_fc);
-extern int be_cmd_query_fw_cfg(struct be_adapter *adapter,
-			u32 *port_num, u32 *function_mode, u32 *function_caps);
+extern int be_cmd_query_fw_cfg(struct be_adapter *adapter, u32 *port_num,
+			u32 *function_mode, u32 *function_caps, u16 *asic_rev);
 extern int be_cmd_reset_function(struct be_adapter *adapter);
 extern int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable,
-			u16 table_size);
+			     u32 rss_hash_opts, u16 table_size);
 extern int be_process_mcc(struct be_adapter *adapter);
 extern int be_cmd_set_beacon_state(struct be_adapter *adapter,
 			u8 port_num, u8 beacon, u8 status, u8 state);
@@ -1931,10 +1941,11 @@ extern int lancer_test_and_set_rdy_state(struct be_adapter *adapter);
 extern int be_cmd_query_port_name(struct be_adapter *adapter, u8 *port_name);
 extern int be_cmd_get_func_config(struct be_adapter *adapter);
 extern int be_cmd_get_profile_config(struct be_adapter *adapter, u32 *cap_flags,
-				     u8 domain);
+				     u16 *txq_count, u8 domain);
 
 extern int be_cmd_set_profile_config(struct be_adapter *adapter, u32 bps,
 				     u8 domain);
 extern int be_cmd_get_if_id(struct be_adapter *adapter,
 			    struct be_vf_cfg *vf_cfg, int vf_num);
 extern int be_cmd_enable_vf(struct be_adapter *adapter, u8 domain);
+extern int be_cmd_intr_set(struct be_adapter *adapter, bool intr_enable);
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 76b302f30c87..5733cde88e2c 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2011 Emulex
+ * Copyright (C) 2005 - 2013 Emulex
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -54,7 +54,7 @@ static const struct be_ethtool_stat et_stats[] = {
 	/* Received packets dropped when they don't pass the unicast or
 	 * multicast address filtering.
 	 */
-	{DRVSTAT_INFO(rx_address_mismatch_drops)},
+	{DRVSTAT_INFO(rx_address_filtered)},
 	/* Received packets dropped when IP packet length field is less than
 	 * the IP header length field.
 	 */
@@ -680,7 +680,8 @@ be_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 
 	if (be_is_wol_supported(adapter)) {
 		wol->supported |= WAKE_MAGIC;
-		wol->wolopts |= WAKE_MAGIC;
+		if (adapter->wol)
+			wol->wolopts |= WAKE_MAGIC;
 	} else
 		wol->wolopts = 0;
 	memset(&wol->sopass, 0, sizeof(wol->sopass));
@@ -719,10 +720,8 @@ be_test_ddr_dma(struct be_adapter *adapter)
 	ddrdma_cmd.size = sizeof(struct be_cmd_req_ddrdma_test);
 	ddrdma_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, ddrdma_cmd.size,
 					   &ddrdma_cmd.dma, GFP_KERNEL);
-	if (!ddrdma_cmd.va) {
-		dev_err(&adapter->pdev->dev, "Memory allocation failure\n");
+	if (!ddrdma_cmd.va)
 		return -ENOMEM;
-	}
 
 	for (i = 0; i < 2; i++) {
 		ret = be_cmd_ddr_dma_test(adapter, pattern[i],
@@ -757,6 +756,12 @@ be_self_test(struct net_device *netdev, struct ethtool_test *test, u64 *data)
 	int status;
 	u8 link_status = 0;
 
+	if (adapter->function_caps & BE_FUNCTION_CAPS_SUPER_NIC) {
+		dev_err(&adapter->pdev->dev, "Self test not supported\n");
+		test->flags |= ETH_TEST_FL_FAILED;
+		return;
+	}
+
 	memset(data, 0, sizeof(u64) * ETHTOOL_TESTS_NUM);
 
 	if (test->flags & ETH_TEST_FL_OFFLINE) {
@@ -845,11 +850,8 @@ be_read_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
 	eeprom_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, eeprom_cmd.size,
 					   &eeprom_cmd.dma, GFP_KERNEL);
 
-	if (!eeprom_cmd.va) {
-		dev_err(&adapter->pdev->dev,
-			"Memory allocation failure. Could not read eeprom\n");
+	if (!eeprom_cmd.va)
 		return -ENOMEM;
-	}
 
 	status = be_cmd_get_seeprom_data(adapter, &eeprom_cmd);
 
@@ -939,6 +941,159 @@ static void be_set_msg_level(struct net_device *netdev, u32 level)
 	return;
 }
 
+static u64 be_get_rss_hash_opts(struct be_adapter *adapter, u64 flow_type)
+{
+	u64 data = 0;
+
+	switch (flow_type) {
+	case TCP_V4_FLOW:
+		if (adapter->rss_flags & RSS_ENABLE_IPV4)
+			data |= RXH_IP_DST | RXH_IP_SRC;
+		if (adapter->rss_flags & RSS_ENABLE_TCP_IPV4)
+			data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		break;
+	case UDP_V4_FLOW:
+		if (adapter->rss_flags & RSS_ENABLE_IPV4)
+			data |= RXH_IP_DST | RXH_IP_SRC;
+		if (adapter->rss_flags & RSS_ENABLE_UDP_IPV4)
+			data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		break;
+	case TCP_V6_FLOW:
+		if (adapter->rss_flags & RSS_ENABLE_IPV6)
+			data |= RXH_IP_DST | RXH_IP_SRC;
+		if (adapter->rss_flags & RSS_ENABLE_TCP_IPV6)
+			data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		break;
+	case UDP_V6_FLOW:
+		if (adapter->rss_flags & RSS_ENABLE_IPV6)
+			data |= RXH_IP_DST | RXH_IP_SRC;
+		if (adapter->rss_flags & RSS_ENABLE_UDP_IPV6)
+			data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		break;
+	}
+
+	return data;
+}
+
+static int be_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
+		      u32 *rule_locs)
+{
+	struct be_adapter *adapter = netdev_priv(netdev);
+
+	if (!be_multi_rxq(adapter)) {
+		dev_info(&adapter->pdev->dev,
+			 "ethtool::get_rxnfc: RX flow hashing is disabled\n");
+		return -EINVAL;
+	}
+
+	switch (cmd->cmd) {
+	case ETHTOOL_GRXFH:
+		cmd->data = be_get_rss_hash_opts(adapter, cmd->flow_type);
+		break;
+	case ETHTOOL_GRXRINGS:
+		cmd->data = adapter->num_rx_qs - 1;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int be_set_rss_hash_opts(struct be_adapter *adapter,
+				struct ethtool_rxnfc *cmd)
+{
+	struct be_rx_obj *rxo;
+	int status = 0, i, j;
+	u8 rsstable[128];
+	u32 rss_flags = adapter->rss_flags;
+
+	if (cmd->data != L3_RSS_FLAGS &&
+	    cmd->data != (L3_RSS_FLAGS | L4_RSS_FLAGS))
+		return -EINVAL;
+
+	switch (cmd->flow_type) {
+	case TCP_V4_FLOW:
+		if (cmd->data == L3_RSS_FLAGS)
+			rss_flags &= ~RSS_ENABLE_TCP_IPV4;
+		else if (cmd->data == (L3_RSS_FLAGS | L4_RSS_FLAGS))
+			rss_flags |= RSS_ENABLE_IPV4 |
+					RSS_ENABLE_TCP_IPV4;
+		break;
+	case TCP_V6_FLOW:
+		if (cmd->data == L3_RSS_FLAGS)
+			rss_flags &= ~RSS_ENABLE_TCP_IPV6;
+		else if (cmd->data == (L3_RSS_FLAGS | L4_RSS_FLAGS))
+			rss_flags |= RSS_ENABLE_IPV6 |
+					RSS_ENABLE_TCP_IPV6;
+		break;
+	case UDP_V4_FLOW:
+		if ((cmd->data == (L3_RSS_FLAGS | L4_RSS_FLAGS)) &&
+		    BEx_chip(adapter))
+			return -EINVAL;
+
+		if (cmd->data == L3_RSS_FLAGS)
+			rss_flags &= ~RSS_ENABLE_UDP_IPV4;
+		else if (cmd->data == (L3_RSS_FLAGS | L4_RSS_FLAGS))
+			rss_flags |= RSS_ENABLE_IPV4 |
+					RSS_ENABLE_UDP_IPV4;
+		break;
+	case UDP_V6_FLOW:
+		if ((cmd->data == (L3_RSS_FLAGS | L4_RSS_FLAGS)) &&
+		    BEx_chip(adapter))
+			return -EINVAL;
+
+		if (cmd->data == L3_RSS_FLAGS)
+			rss_flags &= ~RSS_ENABLE_UDP_IPV6;
+		else if (cmd->data == (L3_RSS_FLAGS | L4_RSS_FLAGS))
+			rss_flags |= RSS_ENABLE_IPV6 |
+					RSS_ENABLE_UDP_IPV6;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (rss_flags == adapter->rss_flags)
+		return status;
+
+	if (be_multi_rxq(adapter)) {
+		for (j = 0; j < 128; j += adapter->num_rx_qs - 1) {
+			for_all_rss_queues(adapter, rxo, i) {
+				if ((j + i) >= 128)
+					break;
+				rsstable[j + i] = rxo->rss_id;
+			}
+		}
+	}
+	status = be_cmd_rss_config(adapter, rsstable, rss_flags, 128);
+	if (!status)
+		adapter->rss_flags = rss_flags;
+
+	return status;
+}
+
+static int be_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
+{
+	struct be_adapter *adapter = netdev_priv(netdev);
+	int status = 0;
+
+	if (!be_multi_rxq(adapter)) {
+		dev_err(&adapter->pdev->dev,
+			"ethtool::set_rxnfc: RX flow hashing is disabled\n");
+		return -EINVAL;
+	}
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXFH:
+		status = be_set_rss_hash_opts(adapter, cmd);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return status;
+}
+
 const struct ethtool_ops be_ethtool_ops = {
 	.get_settings = be_get_settings,
 	.get_drvinfo = be_get_drvinfo,
@@ -962,4 +1117,6 @@ const struct ethtool_ops be_ethtool_ops = {
 	.get_regs = be_get_regs,
 	.flash_device = be_do_flash,
 	.self_test = be_self_test,
+	.get_rxnfc = be_get_rxnfc,
+	.set_rxnfc = be_set_rxnfc,
 };
diff --git a/drivers/net/ethernet/emulex/benet/be_hw.h b/drivers/net/ethernet/emulex/benet/be_hw.h
index 62dc220695f7..3c1099b47f2a 100644
--- a/drivers/net/ethernet/emulex/benet/be_hw.h
+++ b/drivers/net/ethernet/emulex/benet/be_hw.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2011 Emulex
+ * Copyright (C) 2005 - 2013 Emulex
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -72,6 +72,10 @@
  */
 #define MEMBAR_CTRL_INT_CTRL_HOSTINTR_MASK	(1 << 29) /* bit 29 */
 
+/********* PCI Function Capability *********/
+#define BE_FUNCTION_CAPS_RSS			0x2
+#define BE_FUNCTION_CAPS_SUPER_NIC		0x40
+
 /********* Power management (WOL) **********/
 #define PCICFG_PM_CONTROL_OFFSET		0x44
 #define PCICFG_PM_CONTROL_MASK			0x108	/* bits 3 & 8 */
@@ -495,7 +499,8 @@ struct flash_file_hdr_g3 {
 	u32 antidote;
 	u32 num_imgs;
 	u8 build[24];
-	u8 rsvd[32];
+	u8 asic_type_rev;
+	u8 rsvd[31];
 };
 
 struct flash_section_hdr {
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 2886c9b63f90..4babc8a4a543 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2011 Emulex
+ * Copyright (C) 2005 - 2013 Emulex
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -146,20 +146,16 @@ static int be_queue_alloc(struct be_adapter *adapter, struct be_queue_info *q,
 	q->entry_size = entry_size;
 	mem->size = len * entry_size;
 	mem->va = dma_alloc_coherent(&adapter->pdev->dev, mem->size, &mem->dma,
-				     GFP_KERNEL);
+				     GFP_KERNEL | __GFP_ZERO);
 	if (!mem->va)
 		return -ENOMEM;
-	memset(mem->va, 0, mem->size);
 	return 0;
 }
 
-static void be_intr_set(struct be_adapter *adapter, bool enable)
+static void be_reg_intr_set(struct be_adapter *adapter, bool enable)
 {
 	u32 reg, enabled;
 
-	if (adapter->eeh_error)
-		return;
-
 	pci_read_config_dword(adapter->pdev, PCICFG_MEMBAR_CTRL_INT_CTRL_OFFSET,
 				&reg);
 	enabled = reg & MEMBAR_CTRL_INT_CTRL_HOSTINTR_MASK;
@@ -175,6 +171,22 @@ static void be_intr_set(struct be_adapter *adapter, bool enable)
 			PCICFG_MEMBAR_CTRL_INT_CTRL_OFFSET, reg);
 }
 
+static void be_intr_set(struct be_adapter *adapter, bool enable)
+{
+	int status = 0;
+
+	/* On lancer interrupts can't be controlled via this register */
+	if (lancer_chip(adapter))
+		return;
+
+	if (adapter->eeh_error)
+		return;
+
+	status = be_cmd_intr_set(adapter, enable);
+	if (status)
+		be_reg_intr_set(adapter, enable);
+}
+
 static void be_rxq_notify(struct be_adapter *adapter, u16 qid, u16 posted)
 {
 	u32 val = 0;
@@ -185,14 +197,15 @@ static void be_rxq_notify(struct be_adapter *adapter, u16 qid, u16 posted)
 	iowrite32(val, adapter->db + DB_RQ_OFFSET);
 }
 
-static void be_txq_notify(struct be_adapter *adapter, u16 qid, u16 posted)
+static void be_txq_notify(struct be_adapter *adapter, struct be_tx_obj *txo,
+			  u16 posted)
 {
 	u32 val = 0;
-	val |= qid & DB_TXULP_RING_ID_MASK;
+	val |= txo->q.id & DB_TXULP_RING_ID_MASK;
 	val |= (posted & DB_TXULP_NUM_POSTED_MASK) << DB_TXULP_NUM_POSTED_SHIFT;
 
 	wmb();
-	iowrite32(val, adapter->db + DB_TXULP1_OFFSET);
+	iowrite32(val, adapter->db + txo->db_offset);
 }
 
 static void be_eq_notify(struct be_adapter *adapter, u16 qid,
@@ -340,9 +353,9 @@ static void populate_be_v0_stats(struct be_adapter *adapter)
 	drvs->rx_input_fifo_overflow_drop = port_stats->rx_input_fifo_overflow;
 	drvs->rx_dropped_header_too_small =
 		port_stats->rx_dropped_header_too_small;
-	drvs->rx_address_mismatch_drops =
-					port_stats->rx_address_mismatch_drops +
-					port_stats->rx_vlan_mismatch_drops;
+	drvs->rx_address_filtered =
+					port_stats->rx_address_filtered +
+					port_stats->rx_vlan_filtered;
 	drvs->rx_alignment_symbol_errors =
 		port_stats->rx_alignment_symbol_errors;
 
@@ -391,7 +404,7 @@ static void populate_be_v1_stats(struct be_adapter *adapter)
 		port_stats->rx_dropped_header_too_small;
 	drvs->rx_input_fifo_overflow_drop =
 		port_stats->rx_input_fifo_overflow_drop;
-	drvs->rx_address_mismatch_drops = port_stats->rx_address_mismatch_drops;
+	drvs->rx_address_filtered = port_stats->rx_address_filtered;
 	drvs->rx_alignment_symbol_errors =
 		port_stats->rx_alignment_symbol_errors;
 	drvs->rxpp_fifo_overflow_drop = port_stats->rxpp_fifo_overflow_drop;
@@ -432,9 +445,9 @@ static void populate_lancer_stats(struct be_adapter *adapter)
 	drvs->rx_dropped_header_too_small =
 				pport_stats->rx_dropped_header_too_small;
 	drvs->rx_input_fifo_overflow_drop = pport_stats->rx_fifo_overflow;
-	drvs->rx_address_mismatch_drops =
-					pport_stats->rx_address_mismatch_drops +
-					pport_stats->rx_vlan_mismatch_drops;
+	drvs->rx_address_filtered =
+					pport_stats->rx_address_filtered +
+					pport_stats->rx_vlan_filtered;
 	drvs->rx_alignment_symbol_errors = pport_stats->rx_symbol_errors_lo;
 	drvs->rxpp_fifo_overflow_drop = pport_stats->rx_fifo_overflow;
 	drvs->tx_pauseframes = pport_stats->tx_pause_frames_lo;
@@ -626,13 +639,8 @@ static inline u16 be_get_tx_vlan_tag(struct be_adapter *adapter,
 	return vlan_tag;
 }
 
-static int be_vlan_tag_chk(struct be_adapter *adapter, struct sk_buff *skb)
-{
-	return vlan_tx_tag_present(skb) || adapter->pvid;
-}
-
 static void wrb_fill_hdr(struct be_adapter *adapter, struct be_eth_hdr_wrb *hdr,
-		struct sk_buff *skb, u32 wrb_cnt, u32 len)
+		struct sk_buff *skb, u32 wrb_cnt, u32 len, bool skip_hw_vlan)
 {
 	u16 vlan_tag;
 
@@ -659,8 +667,9 @@ static void wrb_fill_hdr(struct be_adapter *adapter, struct be_eth_hdr_wrb *hdr,
 		AMAP_SET_BITS(struct amap_eth_hdr_wrb, vlan_tag, hdr, vlan_tag);
 	}
 
+	/* To skip HW VLAN tagging: evt = 1, compl = 0 */
+	AMAP_SET_BITS(struct amap_eth_hdr_wrb, complete, hdr, !skip_hw_vlan);
 	AMAP_SET_BITS(struct amap_eth_hdr_wrb, event, hdr, 1);
-	AMAP_SET_BITS(struct amap_eth_hdr_wrb, complete, hdr, 1);
 	AMAP_SET_BITS(struct amap_eth_hdr_wrb, num_wrb, hdr, wrb_cnt);
 	AMAP_SET_BITS(struct amap_eth_hdr_wrb, len, hdr, len);
 }
@@ -683,7 +692,8 @@ static void unmap_tx_frag(struct device *dev, struct be_eth_wrb *wrb,
 }
 
 static int make_tx_wrbs(struct be_adapter *adapter, struct be_queue_info *txq,
-		struct sk_buff *skb, u32 wrb_cnt, bool dummy_wrb)
+		struct sk_buff *skb, u32 wrb_cnt, bool dummy_wrb,
+		bool skip_hw_vlan)
 {
 	dma_addr_t busaddr;
 	int i, copied = 0;
@@ -732,7 +742,7 @@ static int make_tx_wrbs(struct be_adapter *adapter, struct be_queue_info *txq,
 		queue_head_inc(txq);
 	}
 
-	wrb_fill_hdr(adapter, hdr, first_skb, wrb_cnt, copied);
+	wrb_fill_hdr(adapter, hdr, first_skb, wrb_cnt, copied, skip_hw_vlan);
 	be_dws_cpu_to_le(hdr, sizeof(*hdr));
 
 	return copied;
@@ -749,7 +759,8 @@ dma_err:
 }
 
 static struct sk_buff *be_insert_vlan_in_pkt(struct be_adapter *adapter,
-					     struct sk_buff *skb)
+					     struct sk_buff *skb,
+					     bool *skip_hw_vlan)
 {
 	u16 vlan_tag = 0;
 
@@ -759,14 +770,72 @@ static struct sk_buff *be_insert_vlan_in_pkt(struct be_adapter *adapter,
 
 	if (vlan_tx_tag_present(skb)) {
 		vlan_tag = be_get_tx_vlan_tag(adapter, skb);
-		skb = __vlan_put_tag(skb, vlan_tag);
+		skb = __vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
 		if (skb)
 			skb->vlan_tci = 0;
 	}
 
+	if (qnq_async_evt_rcvd(adapter) && adapter->pvid) {
+		if (!vlan_tag)
+			vlan_tag = adapter->pvid;
+		if (skip_hw_vlan)
+			*skip_hw_vlan = true;
+	}
+
+	if (vlan_tag) {
+		skb = __vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
+		if (unlikely(!skb))
+			return skb;
+
+		skb->vlan_tci = 0;
+	}
+
+	/* Insert the outer VLAN, if any */
+	if (adapter->qnq_vid) {
+		vlan_tag = adapter->qnq_vid;
+		skb = __vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
+		if (unlikely(!skb))
+			return skb;
+		if (skip_hw_vlan)
+			*skip_hw_vlan = true;
+	}
+
 	return skb;
 }
 
+static bool be_ipv6_exthdr_check(struct sk_buff *skb)
+{
+	struct ethhdr *eh = (struct ethhdr *)skb->data;
+	u16 offset = ETH_HLEN;
+
+	if (eh->h_proto == htons(ETH_P_IPV6)) {
+		struct ipv6hdr *ip6h = (struct ipv6hdr *)(skb->data + offset);
+
+		offset += sizeof(struct ipv6hdr);
+		if (ip6h->nexthdr != NEXTHDR_TCP &&
+		    ip6h->nexthdr != NEXTHDR_UDP) {
+			struct ipv6_opt_hdr *ehdr =
+				(struct ipv6_opt_hdr *) (skb->data + offset);
+
+			/* offending pkt: 2nd byte following IPv6 hdr is 0xff */
+			if (ehdr->hdrlen == 0xff)
+				return true;
+		}
+	}
+	return false;
+}
+
+static int be_vlan_tag_tx_chk(struct be_adapter *adapter, struct sk_buff *skb)
+{
+	return vlan_tx_tag_present(skb) || adapter->pvid || adapter->qnq_vid;
+}
+
+static int be_ipv6_tx_stall_chk(struct be_adapter *adapter, struct sk_buff *skb)
+{
+	return BE3_chip(adapter) &&
+		be_ipv6_exthdr_check(skb);
+}
+
 static netdev_tx_t be_xmit(struct sk_buff *skb,
 			struct net_device *netdev)
 {
@@ -777,33 +846,64 @@ static netdev_tx_t be_xmit(struct sk_buff *skb,
 	u32 wrb_cnt = 0, copied = 0;
 	u32 start = txq->head, eth_hdr_len;
 	bool dummy_wrb, stopped = false;
+	bool skip_hw_vlan = false;
+	struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
 
 	eth_hdr_len = ntohs(skb->protocol) == ETH_P_8021Q ?
 		VLAN_ETH_HLEN : ETH_HLEN;
 
-	/* HW has a bug which considers padding bytes as legal
-	 * and modifies the IPv4 hdr's 'tot_len' field
+	/* For padded packets, BE HW modifies tot_len field in IP header
+	 * incorrecly when VLAN tag is inserted by HW.
 	 */
-	if (skb->len <= 60 && be_vlan_tag_chk(adapter, skb) &&
-			is_ipv4_pkt(skb)) {
+	if (skb->len <= 60 && vlan_tx_tag_present(skb) && is_ipv4_pkt(skb)) {
 		ip = (struct iphdr *)ip_hdr(skb);
 		pskb_trim(skb, eth_hdr_len + ntohs(ip->tot_len));
 	}
 
+	/* If vlan tag is already inlined in the packet, skip HW VLAN
+	 * tagging in UMC mode
+	 */
+	if ((adapter->function_mode & UMC_ENABLED) &&
+	    veh->h_vlan_proto == htons(ETH_P_8021Q))
+			skip_hw_vlan = true;
+
 	/* HW has a bug wherein it will calculate CSUM for VLAN
 	 * pkts even though it is disabled.
 	 * Manually insert VLAN in pkt.
 	 */
 	if (skb->ip_summed != CHECKSUM_PARTIAL &&
-			be_vlan_tag_chk(adapter, skb)) {
-		skb = be_insert_vlan_in_pkt(adapter, skb);
+			vlan_tx_tag_present(skb)) {
+		skb = be_insert_vlan_in_pkt(adapter, skb, &skip_hw_vlan);
+		if (unlikely(!skb))
+			goto tx_drop;
+	}
+
+	/* HW may lockup when VLAN HW tagging is requested on
+	 * certain ipv6 packets. Drop such pkts if the HW workaround to
+	 * skip HW tagging is not enabled by FW.
+	 */
+	if (unlikely(be_ipv6_tx_stall_chk(adapter, skb) &&
+		     (adapter->pvid || adapter->qnq_vid) &&
+		     !qnq_async_evt_rcvd(adapter)))
+		goto tx_drop;
+
+	/* Manual VLAN tag insertion to prevent:
+	 * ASIC lockup when the ASIC inserts VLAN tag into
+	 * certain ipv6 packets. Insert VLAN tags in driver,
+	 * and set event, completion, vlan bits accordingly
+	 * in the Tx WRB.
+	 */
+	if (be_ipv6_tx_stall_chk(adapter, skb) &&
+	    be_vlan_tag_tx_chk(adapter, skb)) {
+		skb = be_insert_vlan_in_pkt(adapter, skb, &skip_hw_vlan);
 		if (unlikely(!skb))
 			goto tx_drop;
 	}
 
 	wrb_cnt = wrb_cnt_for_skb(adapter, skb, &dummy_wrb);
 
-	copied = make_tx_wrbs(adapter, txq, skb, wrb_cnt, dummy_wrb);
+	copied = make_tx_wrbs(adapter, txq, skb, wrb_cnt, dummy_wrb,
+			      skip_hw_vlan);
 	if (copied) {
 		int gso_segs = skb_shinfo(skb)->gso_segs;
 
@@ -822,7 +922,7 @@ static netdev_tx_t be_xmit(struct sk_buff *skb,
 			stopped = true;
 		}
 
-		be_txq_notify(adapter, txq->id, wrb_cnt);
+		be_txq_notify(adapter, txo, wrb_cnt);
 
 		be_tx_stats_update(txo, wrb_cnt, copied, gso_segs, stopped);
 	} else {
@@ -891,7 +991,7 @@ set_vlan_promisc:
 	return status;
 }
 
-static int be_vlan_add_vid(struct net_device *netdev, u16 vid)
+static int be_vlan_add_vid(struct net_device *netdev, __be16 proto, u16 vid)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	int status = 0;
@@ -917,7 +1017,7 @@ ret:
 	return status;
 }
 
-static int be_vlan_rem_vid(struct net_device *netdev, u16 vid)
+static int be_vlan_rem_vid(struct net_device *netdev, __be16 proto, u16 vid)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	int status = 0;
@@ -1372,7 +1472,7 @@ static void be_rx_compl_process(struct be_rx_obj *rxo,
 
 
 	if (rxcp->vlanf)
-		__vlan_hwaccel_put_tag(skb, rxcp->vlan_tag);
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), rxcp->vlan_tag);
 
 	netif_receive_skb(skb);
 }
@@ -1428,7 +1528,7 @@ void be_rx_compl_process_gro(struct be_rx_obj *rxo, struct napi_struct *napi,
 		skb->rxhash = rxcp->rss_hash;
 
 	if (rxcp->vlanf)
-		__vlan_hwaccel_put_tag(skb, rxcp->vlan_tag);
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), rxcp->vlan_tag);
 
 	napi_gro_frags(napi);
 }
@@ -1958,7 +2058,7 @@ static int be_tx_qs_create(struct be_adapter *adapter)
 		if (status)
 			return status;
 
-		status = be_cmd_txq_create(adapter, &txo->q, &txo->cq);
+		status = be_cmd_txq_create(adapter, txo);
 		if (status)
 			return status;
 	}
@@ -2436,9 +2536,6 @@ static int be_close(struct net_device *netdev)
 
 	be_roce_dev_close(adapter);
 
-	if (!lancer_chip(adapter))
-		be_intr_set(adapter, false);
-
 	for_all_evt_queues(adapter, eqo, i)
 		napi_disable(&eqo->napi);
 
@@ -2500,9 +2597,19 @@ static int be_rx_qs_create(struct be_adapter *adapter)
 				rsstable[j + i] = rxo->rss_id;
 			}
 		}
-		rc = be_cmd_rss_config(adapter, rsstable, 128);
-		if (rc)
+		adapter->rss_flags = RSS_ENABLE_TCP_IPV4 | RSS_ENABLE_IPV4 |
+					RSS_ENABLE_TCP_IPV6 | RSS_ENABLE_IPV6;
+
+		if (!BEx_chip(adapter))
+			adapter->rss_flags |= RSS_ENABLE_UDP_IPV4 |
+						RSS_ENABLE_UDP_IPV6;
+
+		rc = be_cmd_rss_config(adapter, rsstable, adapter->rss_flags,
+				       128);
+		if (rc) {
+			adapter->rss_flags = 0;
 			return rc;
+		}
 	}
 
 	/* First time posting */
@@ -2526,9 +2633,6 @@ static int be_open(struct net_device *netdev)
 
 	be_irq_register(adapter);
 
-	if (!lancer_chip(adapter))
-		be_intr_set(adapter, true);
-
 	for_all_rx_queues(adapter, rxo, i)
 		be_cq_notify(adapter, rxo->cq.id, true, 0);
 
@@ -2563,10 +2667,9 @@ static int be_setup_wol(struct be_adapter *adapter, bool enable)
 
 	cmd.size = sizeof(struct be_cmd_req_acpi_wol_magic_config);
 	cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
-				    GFP_KERNEL);
+				    GFP_KERNEL | __GFP_ZERO);
 	if (cmd.va == NULL)
 		return -1;
-	memset(cmd.va, 0, cmd.size);
 
 	if (enable) {
 		status = pci_write_config_dword(adapter->pdev,
@@ -2714,7 +2817,8 @@ static int be_vfs_if_create(struct be_adapter *adapter)
 
 	for_all_vfs(adapter, vf_cfg, vf) {
 		if (!BE3_chip(adapter))
-			be_cmd_get_profile_config(adapter, &cap_flags, vf + 1);
+			be_cmd_get_profile_config(adapter, &cap_flags,
+						  NULL, vf + 1);
 
 		/* If a FW profile exists, then cap_flags are updated */
 		en_flags = cap_flags & (BE_IF_FLAGS_UNTAGGED |
@@ -2878,11 +2982,14 @@ static void be_get_resources(struct be_adapter *adapter)
 	u16 dev_num_vfs;
 	int pos, status;
 	bool profile_present = false;
+	u16 txq_count = 0;
 
 	if (!BEx_chip(adapter)) {
 		status = be_cmd_get_func_config(adapter);
 		if (!status)
 			profile_present = true;
+	} else if (BE3_chip(adapter) && be_physfn(adapter)) {
+		be_cmd_get_profile_config(adapter, NULL, &txq_count, 0);
 	}
 
 	if (profile_present) {
@@ -2920,7 +3027,9 @@ static void be_get_resources(struct be_adapter *adapter)
 			adapter->max_vlans = BE_NUM_VLANS_SUPPORTED;
 
 		adapter->max_mcast_mac = BE_MAX_MC;
-		adapter->max_tx_queues = MAX_TX_QS;
+		adapter->max_tx_queues = txq_count ? txq_count : MAX_TX_QS;
+		adapter->max_tx_queues = min_t(u16, adapter->max_tx_queues,
+					       MAX_TX_QS);
 		adapter->max_rss_queues = (adapter->be3_native) ?
 					   BE3_MAX_RSS_QS : BE2_MAX_RSS_QS;
 		adapter->max_event_queues = BE3_MAX_RSS_QS;
@@ -2954,7 +3063,8 @@ static int be_get_config(struct be_adapter *adapter)
 
 	status = be_cmd_query_fw_cfg(adapter, &adapter->port_num,
 				     &adapter->function_mode,
-				     &adapter->function_caps);
+				     &adapter->function_caps,
+				     &adapter->asic_rev);
 	if (status)
 		goto err;
 
@@ -3215,7 +3325,7 @@ static int be_flash(struct be_adapter *adapter, const u8 *img,
 	return 0;
 }
 
-/* For BE2 and BE3 */
+/* For BE2, BE3 and BE3-R */
 static int be_flash_BEx(struct be_adapter *adapter,
 			 const struct firmware *fw,
 			 struct be_dma_mem *flash_cmd,
@@ -3458,11 +3568,9 @@ static int lancer_fw_download(struct be_adapter *adapter,
 	flash_cmd.size = sizeof(struct lancer_cmd_req_write_object)
 				+ LANCER_FW_DOWNLOAD_CHUNK;
 	flash_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, flash_cmd.size,
-						&flash_cmd.dma, GFP_KERNEL);
+					  &flash_cmd.dma, GFP_KERNEL);
 	if (!flash_cmd.va) {
 		status = -ENOMEM;
-		dev_err(&adapter->pdev->dev,
-			"Memory allocation failure while flashing\n");
 		goto lancer_fw_exit;
 	}
 
@@ -3530,18 +3638,22 @@ lancer_fw_exit:
 
 #define UFI_TYPE2		2
 #define UFI_TYPE3		3
+#define UFI_TYPE3R		10
 #define UFI_TYPE4		4
 static int be_get_ufi_type(struct be_adapter *adapter,
-			   struct flash_file_hdr_g2 *fhdr)
+			   struct flash_file_hdr_g3 *fhdr)
 {
 	if (fhdr == NULL)
 		goto be_get_ufi_exit;
 
 	if (skyhawk_chip(adapter) && fhdr->build[0] == '4')
 		return UFI_TYPE4;
-	else if (BE3_chip(adapter) && fhdr->build[0] == '3')
-		return UFI_TYPE3;
-	else if (BE2_chip(adapter) && fhdr->build[0] == '2')
+	else if (BE3_chip(adapter) && fhdr->build[0] == '3') {
+		if (fhdr->asic_type_rev == 0x10)
+			return UFI_TYPE3R;
+		else
+			return UFI_TYPE3;
+	} else if (BE2_chip(adapter) && fhdr->build[0] == '2')
 		return UFI_TYPE2;
 
 be_get_ufi_exit:
@@ -3552,7 +3664,6 @@ be_get_ufi_exit:
 
 static int be_fw_download(struct be_adapter *adapter, const struct firmware* fw)
 {
-	struct flash_file_hdr_g2 *fhdr;
 	struct flash_file_hdr_g3 *fhdr3;
 	struct image_hdr *img_hdr_ptr = NULL;
 	struct be_dma_mem flash_cmd;
@@ -3564,29 +3675,41 @@ static int be_fw_download(struct be_adapter *adapter, const struct firmware* fw)
 					  &flash_cmd.dma, GFP_KERNEL);
 	if (!flash_cmd.va) {
 		status = -ENOMEM;
-		dev_err(&adapter->pdev->dev,
-			"Memory allocation failure while flashing\n");
 		goto be_fw_exit;
 	}
 
 	p = fw->data;
-	fhdr = (struct flash_file_hdr_g2 *)p;
+	fhdr3 = (struct flash_file_hdr_g3 *)p;
 
-	ufi_type = be_get_ufi_type(adapter, fhdr);
+	ufi_type = be_get_ufi_type(adapter, fhdr3);
 
-	fhdr3 = (struct flash_file_hdr_g3 *)fw->data;
 	num_imgs = le32_to_cpu(fhdr3->num_imgs);
 	for (i = 0; i < num_imgs; i++) {
 		img_hdr_ptr = (struct image_hdr *)(fw->data +
 				(sizeof(struct flash_file_hdr_g3) +
 				 i * sizeof(struct image_hdr)));
 		if (le32_to_cpu(img_hdr_ptr->imageid) == 1) {
-			if (ufi_type == UFI_TYPE4)
+			switch (ufi_type) {
+			case UFI_TYPE4:
 				status = be_flash_skyhawk(adapter, fw,
 							&flash_cmd, num_imgs);
-			else if (ufi_type == UFI_TYPE3)
+				break;
+			case UFI_TYPE3R:
 				status = be_flash_BEx(adapter, fw, &flash_cmd,
 						      num_imgs);
+				break;
+			case UFI_TYPE3:
+				/* Do not flash this ufi on BE3-R cards */
+				if (adapter->asic_rev < 0x10)
+					status = be_flash_BEx(adapter, fw,
+							      &flash_cmd,
+							      num_imgs);
+				else {
+					status = -1;
+					dev_err(&adapter->pdev->dev,
+						"Can't load BE3 UFI on BE3R\n");
+				}
+			}
 		}
 	}
 
@@ -3663,12 +3786,12 @@ static void be_netdev_init(struct net_device *netdev)
 
 	netdev->hw_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 |
 		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |
-		NETIF_F_HW_VLAN_TX;
+		NETIF_F_HW_VLAN_CTAG_TX;
 	if (be_multi_rxq(adapter))
 		netdev->hw_features |= NETIF_F_RXHASH;
 
 	netdev->features |= netdev->hw_features |
-		NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_FILTER;
+		NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER;
 
 	netdev->vlan_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 |
 		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
@@ -3792,12 +3915,13 @@ static int be_ctrl_init(struct be_adapter *adapter)
 
 	rx_filter->size = sizeof(struct be_cmd_req_rx_filter);
 	rx_filter->va = dma_alloc_coherent(&adapter->pdev->dev, rx_filter->size,
-					&rx_filter->dma, GFP_KERNEL);
+					   &rx_filter->dma,
+					   GFP_KERNEL | __GFP_ZERO);
 	if (rx_filter->va == NULL) {
 		status = -ENOMEM;
 		goto free_mbox;
 	}
-	memset(rx_filter->va, 0, rx_filter->size);
+
 	mutex_init(&adapter->mbox_lock);
 	spin_lock_init(&adapter->mcc_lock);
 	spin_lock_init(&adapter->mcc_cq_lock);
@@ -3839,10 +3963,9 @@ static int be_stats_init(struct be_adapter *adapter)
 		cmd->size = sizeof(struct be_cmd_req_get_stats_v1);
 
 	cmd->va = dma_alloc_coherent(&adapter->pdev->dev, cmd->size, &cmd->dma,
-				     GFP_KERNEL);
+				     GFP_KERNEL | __GFP_ZERO);
 	if (cmd->va == NULL)
 		return -1;
-	memset(cmd->va, 0, cmd->size);
 	return 0;
 }
 
@@ -3854,6 +3977,7 @@ static void be_remove(struct pci_dev *pdev)
 		return;
 
 	be_roce_dev_remove(adapter);
+	be_intr_set(adapter, false);
 
 	cancel_delayed_work_sync(&adapter->func_recovery_work);
 
@@ -4108,6 +4232,11 @@ static int be_probe(struct pci_dev *pdev, const struct pci_device_id *pdev_id)
 
 	status = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
 	if (!status) {
+		status = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
+		if (status < 0) {
+			dev_err(&pdev->dev, "dma_set_coherent_mask failed\n");
+			goto free_netdev;
+		}
 		netdev->features |= NETIF_F_HIGHDMA;
 	} else {
 		status = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
@@ -4132,22 +4261,22 @@ static int be_probe(struct pci_dev *pdev, const struct pci_device_id *pdev_id)
 			goto ctrl_clean;
 	}
 
-	/* tell fw we're ready to fire cmds */
-	status = be_cmd_fw_init(adapter);
-	if (status)
-		goto ctrl_clean;
-
 	if (be_reset_required(adapter)) {
 		status = be_cmd_reset_function(adapter);
 		if (status)
 			goto ctrl_clean;
+
+		/* Wait for interrupts to quiesce after an FLR */
+		msleep(100);
 	}
 
-	/* The INTR bit may be set in the card when probed by a kdump kernel
-	 * after a crash.
-	 */
-	if (!lancer_chip(adapter))
-		be_intr_set(adapter, false);
+	/* Allow interrupts for other ULPs running on NIC function */
+	be_intr_set(adapter, true);
+
+	/* tell fw we're ready to fire cmds */
+	status = be_cmd_fw_init(adapter);
+	if (status)
+		goto ctrl_clean;
 
 	status = be_stats_init(adapter);
 	if (status)
@@ -4358,12 +4487,12 @@ static void be_eeh_resume(struct pci_dev *pdev)
 
 	pci_save_state(pdev);
 
-	/* tell fw we're ready to fire cmds */
-	status = be_cmd_fw_init(adapter);
+	status = be_cmd_reset_function(adapter);
 	if (status)
 		goto err;
 
-	status = be_cmd_reset_function(adapter);
+	/* tell fw we're ready to fire cmds */
+	status = be_cmd_fw_init(adapter);
 	if (status)
 		goto err;
 
diff --git a/drivers/net/ethernet/emulex/benet/be_roce.c b/drivers/net/ethernet/emulex/benet/be_roce.c
index 55d32aa0a093..f3d126dcc104 100644
--- a/drivers/net/ethernet/emulex/benet/be_roce.c
+++ b/drivers/net/ethernet/emulex/benet/be_roce.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2011 Emulex
+ * Copyright (C) 2005 - 2013 Emulex
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
diff --git a/drivers/net/ethernet/emulex/benet/be_roce.h b/drivers/net/ethernet/emulex/benet/be_roce.h
index db4ea8081c07..276572998463 100644
--- a/drivers/net/ethernet/emulex/benet/be_roce.h
+++ b/drivers/net/ethernet/emulex/benet/be_roce.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2011 Emulex
+ * Copyright (C) 2005 - 2013 Emulex
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or