Merge branch 'fix/kconfig' into for-linus

5 files changed, 429 insertions, 243 deletions

diff --git a/drivers/net/benet/be.h b/drivers/net/benet/be.h
index a7db870d1641..c85768cd1b18 100644
--- a/drivers/net/benet/be.h
+++ b/drivers/net/benet/be.h
@@ -20,7 +20,6 @@
 
 #include <linux/pci.h>
 #include <linux/etherdevice.h>
-#include <linux/version.h>
 #include <linux/delay.h>
 #include <net/tcp.h>
 #include <net/ip.h>
@@ -87,6 +86,7 @@ static inline char *nic_name(struct pci_dev *pdev)
 
 #define MAX_RSS_QS		4	/* BE limit is 4 queues/port */
 #define MAX_RX_QS		(MAX_RSS_QS + 1) /* RSS qs + 1 def Rx */
+#define MAX_TX_QS		8
 #define BE_MAX_MSIX_VECTORS	(MAX_RX_QS + 1)/* RX + TX */
 #define BE_NAPI_WEIGHT		64
 #define MAX_RX_POST 		BE_NAPI_WEIGHT /* Frags posted at a time */
@@ -170,7 +170,6 @@ struct be_tx_stats {
 	u32 be_tx_reqs;		/* number of TX requests initiated */
 	u32 be_tx_stops;	/* number of times TX Q was stopped */
 	u32 be_tx_wrbs;		/* number of tx WRBs used */
-	u32 be_tx_events;	/* number of tx completion events  */
 	u32 be_tx_compl;	/* number of tx completion entries processed */
 	ulong be_tx_jiffies;
 	u64 be_tx_bytes;
@@ -184,6 +183,7 @@ struct be_tx_obj {
 	struct be_queue_info cq;
 	/* Remember the skbs that were transmitted */
 	struct sk_buff *sent_skb_list[TX_Q_LEN];
+	struct be_tx_stats stats;
 };
 
 /* Struct to remember the pages posted for rx frags */
@@ -199,6 +199,7 @@ struct be_rx_stats {
 	u32 rx_polls;	/* number of times NAPI called poll function */
 	u32 rx_events;	/* number of ucast rx completion events  */
 	u32 rx_compl;	/* number of rx completion entries processed */
+	ulong rx_dropped; /* number of skb allocation errors */
 	ulong rx_jiffies;
 	u64 rx_bytes;
 	u64 rx_bytes_prev;
@@ -319,8 +320,8 @@ struct be_adapter {
 
 	/* TX Rings */
 	struct be_eq_obj tx_eq;
-	struct be_tx_obj tx_obj;
-	struct be_tx_stats tx_stats;
+	struct be_tx_obj tx_obj[MAX_TX_QS];
+	u8 num_tx_qs;
 
 	u32 cache_line_break[8];
 
@@ -332,7 +333,6 @@ struct be_adapter {
 	u8 eq_next_idx;
 	struct be_drv_stats drv_stats;
 
-	struct vlan_group *vlan_grp;
 	u16 vlans_added;
 	u16 max_vlans;	/* Number of vlans supported */
 	u8 vlan_tag[VLAN_N_VID];
@@ -391,7 +391,7 @@ struct be_adapter {
 extern const struct ethtool_ops be_ethtool_ops;
 
 #define msix_enabled(adapter)		(adapter->num_msix_vec > 0)
-#define tx_stats(adapter)		(&adapter->tx_stats)
+#define tx_stats(txo)			(&txo->stats)
 #define rx_stats(rxo)			(&rxo->stats)
 
 #define BE_SET_NETDEV_OPS(netdev, ops)	(netdev->netdev_ops = ops)
@@ -405,6 +405,10 @@ extern const struct ethtool_ops be_ethtool_ops;
 	for (i = 0, rxo = &adapter->rx_obj[i+1]; i < (adapter->num_rx_qs - 1);\
 		i++, rxo++)
 
+#define for_all_tx_queues(adapter, txo, i)				\
+	for (i = 0, txo = &adapter->tx_obj[i]; i < adapter->num_tx_qs;	\
+		i++, txo++)
+
 #define PAGE_SHIFT_4K		12
 #define PAGE_SIZE_4K		(1 << PAGE_SHIFT_4K)
 
diff --git a/drivers/net/benet/be_cmds.c b/drivers/net/benet/be_cmds.c
index 81654ae16c63..054fa67bc4e3 100644
--- a/drivers/net/benet/be_cmds.c
+++ b/drivers/net/benet/be_cmds.c
@@ -106,14 +106,24 @@ static int be_mcc_compl_process(struct be_adapter *adapter,
 			netdev_stats_update(adapter);
 			adapter->stats_cmd_sent = false;
 		}
-	} else if ((compl_status != MCC_STATUS_NOT_SUPPORTED) &&
-		   (compl->tag0 != OPCODE_COMMON_NTWK_MAC_QUERY)) {
-		extd_status = (compl->status >> CQE_STATUS_EXTD_SHIFT) &
-				CQE_STATUS_EXTD_MASK;
-		dev_warn(&adapter->pdev->dev,
-		"Error in cmd completion - opcode %d, compl %d, extd %d\n",
-			compl->tag0, compl_status, extd_status);
+	} else {
+		if (compl_status == MCC_STATUS_NOT_SUPPORTED ||
+			compl_status == MCC_STATUS_ILLEGAL_REQUEST)
+			goto done;
+
+		if (compl_status == MCC_STATUS_UNAUTHORIZED_REQUEST) {
+			dev_warn(&adapter->pdev->dev, "This domain(VM) is not "
+				"permitted to execute this cmd (opcode %d)\n",
+				compl->tag0);
+		} else {
+			extd_status = (compl->status >> CQE_STATUS_EXTD_SHIFT) &
+					CQE_STATUS_EXTD_MASK;
+			dev_err(&adapter->pdev->dev, "Cmd (opcode %d) failed:"
+				"status %d, extd-status %d\n",
+				compl->tag0, compl_status, extd_status);
+		}
 	}
+done:
 	return compl_status;
 }
 
@@ -799,12 +809,12 @@ static u32 be_encoded_q_len(int q_len)
 	return len_encoded;
 }
 
-int be_cmd_mccq_create(struct be_adapter *adapter,
+int be_cmd_mccq_ext_create(struct be_adapter *adapter,
 			struct be_queue_info *mccq,
 			struct be_queue_info *cq)
 {
 	struct be_mcc_wrb *wrb;
-	struct be_cmd_req_mcc_create *req;
+	struct be_cmd_req_mcc_ext_create *req;
 	struct be_dma_mem *q_mem = &mccq->dma_mem;
 	void *ctxt;
 	int status;
@@ -859,6 +869,67 @@ int be_cmd_mccq_create(struct be_adapter *adapter,
 	return status;
 }
 
+int be_cmd_mccq_org_create(struct be_adapter *adapter,
+			struct be_queue_info *mccq,
+			struct be_queue_info *cq)
+{
+	struct be_mcc_wrb *wrb;
+	struct be_cmd_req_mcc_create *req;
+	struct be_dma_mem *q_mem = &mccq->dma_mem;
+	void *ctxt;
+	int status;
+
+	if (mutex_lock_interruptible(&adapter->mbox_lock))
+		return -1;
+
+	wrb = wrb_from_mbox(adapter);
+	req = embedded_payload(wrb);
+	ctxt = &req->context;
+
+	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0,
+			OPCODE_COMMON_MCC_CREATE);
+
+	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+			OPCODE_COMMON_MCC_CREATE, sizeof(*req));
+
+	req->num_pages = cpu_to_le16(PAGES_4K_SPANNED(q_mem->va, q_mem->size));
+
+	AMAP_SET_BITS(struct amap_mcc_context_be, valid, ctxt, 1);
+	AMAP_SET_BITS(struct amap_mcc_context_be, ring_size, ctxt,
+			be_encoded_q_len(mccq->len));
+	AMAP_SET_BITS(struct amap_mcc_context_be, cq_id, ctxt, cq->id);
+
+	be_dws_cpu_to_le(ctxt, sizeof(req->context));
+
+	be_cmd_page_addrs_prepare(req->pages, ARRAY_SIZE(req->pages), q_mem);
+
+	status = be_mbox_notify_wait(adapter);
+	if (!status) {
+		struct be_cmd_resp_mcc_create *resp = embedded_payload(wrb);
+		mccq->id = le16_to_cpu(resp->id);
+		mccq->created = true;
+	}
+
+	mutex_unlock(&adapter->mbox_lock);
+	return status;
+}
+
+int be_cmd_mccq_create(struct be_adapter *adapter,
+			struct be_queue_info *mccq,
+			struct be_queue_info *cq)
+{
+	int status;
+
+	status = be_cmd_mccq_ext_create(adapter, mccq, cq);
+	if (status && !lancer_chip(adapter)) {
+		dev_warn(&adapter->pdev->dev, "Upgrade to F/W ver 2.102.235.0 "
+			"or newer to avoid conflicting priorities between NIC "
+			"and FCoE traffic");
+		status = be_cmd_mccq_org_create(adapter, mccq, cq);
+	}
+	return status;
+}
+
 int be_cmd_txq_create(struct be_adapter *adapter,
 			struct be_queue_info *txq,
 			struct be_queue_info *cq)
@@ -913,7 +984,7 @@ int be_cmd_txq_create(struct be_adapter *adapter,
 	return status;
 }
 
-/* Uses mbox */
+/* Uses MCC */
 int be_cmd_rxq_create(struct be_adapter *adapter,
 		struct be_queue_info *rxq, u16 cq_id, u16 frag_size,
 		u16 max_frame_size, u32 if_id, u32 rss, u8 *rss_id)
@@ -923,10 +994,13 @@ int be_cmd_rxq_create(struct be_adapter *adapter,
 	struct be_dma_mem *q_mem = &rxq->dma_mem;
 	int status;
 
-	if (mutex_lock_interruptible(&adapter->mbox_lock))
-		return -1;
+	spin_lock_bh(&adapter->mcc_lock);
 
-	wrb = wrb_from_mbox(adapter);
+	wrb = wrb_from_mccq(adapter);
+	if (!wrb) {
+		status = -EBUSY;
+		goto err;
+	}
 	req = embedded_payload(wrb);
 
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0,
@@ -943,7 +1017,7 @@ int be_cmd_rxq_create(struct be_adapter *adapter,
 	req->max_frame_size = cpu_to_le16(max_frame_size);
 	req->rss_queue = cpu_to_le32(rss);
 
-	status = be_mbox_notify_wait(adapter);
+	status = be_mcc_notify_wait(adapter);
 	if (!status) {
 		struct be_cmd_resp_eth_rx_create *resp = embedded_payload(wrb);
 		rxq->id = le16_to_cpu(resp->id);
@@ -951,8 +1025,8 @@ int be_cmd_rxq_create(struct be_adapter *adapter,
 		*rss_id = resp->rss_id;
 	}
 
-	mutex_unlock(&adapter->mbox_lock);
-
+err:
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1007,9 +1081,40 @@ int be_cmd_q_destroy(struct be_adapter *adapter, struct be_queue_info *q,
 	req->id = cpu_to_le16(q->id);
 
 	status = be_mbox_notify_wait(adapter);
+	if (!status)
+		q->created = false;
 
 	mutex_unlock(&adapter->mbox_lock);
+	return status;
+}
+
+/* Uses MCC */
+int be_cmd_rxq_destroy(struct be_adapter *adapter, struct be_queue_info *q)
+{
+	struct be_mcc_wrb *wrb;
+	struct be_cmd_req_q_destroy *req;
+	int status;
 
+	spin_lock_bh(&adapter->mcc_lock);
+
+	wrb = wrb_from_mccq(adapter);
+	if (!wrb) {
+		status = -EBUSY;
+		goto err;
+	}
+	req = embedded_payload(wrb);
+
+	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, OPCODE_ETH_RX_DESTROY);
+	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ETH, OPCODE_ETH_RX_DESTROY,
+		sizeof(*req));
+	req->id = cpu_to_le16(q->id);
+
+	status = be_mcc_notify_wait(adapter);
+	if (!status)
+		q->created = false;
+
+err:
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2273,8 +2378,7 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter)
 
 	status = be_mbox_notify_wait(adapter);
 	if (!status) {
-		attribs = (struct mgmt_controller_attrib *)( attribs_cmd.va +
-					sizeof(struct be_cmd_resp_hdr));
+		attribs = attribs_cmd.va + sizeof(struct be_cmd_resp_hdr);
 		adapter->hba_port_num = attribs->hba_attribs.phy_port;
 	}
 
@@ -2286,7 +2390,7 @@ err:
 }
 
 /* Uses mbox */
-int be_cmd_check_native_mode(struct be_adapter *adapter)
+int be_cmd_req_native_mode(struct be_adapter *adapter)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_set_func_cap *req;
diff --git a/drivers/net/benet/be_cmds.h b/drivers/net/benet/be_cmds.h
index 8148cc66cbe9..8e4d48824fe9 100644
--- a/drivers/net/benet/be_cmds.h
+++ b/drivers/net/benet/be_cmds.h
@@ -51,17 +51,12 @@ struct be_mcc_wrb {
 
 /* Completion Status */
 enum {
-	MCC_STATUS_SUCCESS = 0x0,
-/* The client does not have sufficient privileges to execute the command */
-	MCC_STATUS_INSUFFICIENT_PRIVILEGES = 0x1,
-/* A parameter in the command was invalid. */
-	MCC_STATUS_INVALID_PARAMETER = 0x2,
-/* There are insufficient chip resources to execute the command */
-	MCC_STATUS_INSUFFICIENT_RESOURCES = 0x3,
-/* The command is completing because the queue was getting flushed */
-	MCC_STATUS_QUEUE_FLUSHING = 0x4,
-/* The command is completing with a DMA error */
-	MCC_STATUS_DMA_FAILED = 0x5,
+	MCC_STATUS_SUCCESS = 0,
+	MCC_STATUS_FAILED = 1,
+	MCC_STATUS_ILLEGAL_REQUEST = 2,
+	MCC_STATUS_ILLEGAL_FIELD = 3,
+	MCC_STATUS_INSUFFICIENT_BUFFER = 4,
+	MCC_STATUS_UNAUTHORIZED_REQUEST = 5,
 	MCC_STATUS_NOT_SUPPORTED = 66
 };
 
@@ -434,6 +429,14 @@ struct be_cmd_req_mcc_create {
 	struct be_cmd_req_hdr hdr;
 	u16 num_pages;
 	u16 cq_id;
+	u8 context[sizeof(struct amap_mcc_context_be) / 8];
+	struct phys_addr pages[8];
+} __packed;
+
+struct be_cmd_req_mcc_ext_create {
+	struct be_cmd_req_hdr hdr;
+	u16 num_pages;
+	u16 cq_id;
 	u32 async_event_bitmap[1];
 	u8 context[sizeof(struct amap_mcc_context_be) / 8];
 	struct phys_addr pages[8];
@@ -1479,6 +1482,8 @@ extern int be_cmd_rxq_create(struct be_adapter *adapter,
 			u32 rss, u8 *rss_id);
 extern int be_cmd_q_destroy(struct be_adapter *adapter, struct be_queue_info *q,
 			int type);
+extern int be_cmd_rxq_destroy(struct be_adapter *adapter,
+			struct be_queue_info *q);
 extern int be_cmd_link_status_query(struct be_adapter *adapter,
 			bool *link_up, u8 *mac_speed, u16 *link_speed, u32 dom);
 extern int be_cmd_reset(struct be_adapter *adapter);
@@ -1540,7 +1545,7 @@ extern int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain);
 extern void be_detect_dump_ue(struct be_adapter *adapter);
 extern int be_cmd_get_die_temperature(struct be_adapter *adapter);
 extern int be_cmd_get_cntl_attributes(struct be_adapter *adapter);
-extern int be_cmd_check_native_mode(struct be_adapter *adapter);
+extern int be_cmd_req_native_mode(struct be_adapter *adapter);
 extern int be_cmd_get_reg_len(struct be_adapter *adapter, u32 *log_size);
 extern void be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf);
 
diff --git a/drivers/net/benet/be_ethtool.c b/drivers/net/benet/be_ethtool.c
index facfe3ca5c40..7fd8130d86ea 100644
--- a/drivers/net/benet/be_ethtool.c
+++ b/drivers/net/benet/be_ethtool.c
@@ -52,12 +52,7 @@ static const struct be_ethtool_stat et_stats[] = {
 	{NETSTAT_INFO(tx_errors)},
 	{NETSTAT_INFO(rx_dropped)},
 	{NETSTAT_INFO(tx_dropped)},
-	{DRVSTAT_TX_INFO(be_tx_rate)},
-	{DRVSTAT_TX_INFO(be_tx_reqs)},
-	{DRVSTAT_TX_INFO(be_tx_wrbs)},
-	{DRVSTAT_TX_INFO(be_tx_stops)},
-	{DRVSTAT_TX_INFO(be_tx_events)},
-	{DRVSTAT_TX_INFO(be_tx_compl)},
+	{DRVSTAT_INFO(be_tx_events)},
 	{DRVSTAT_INFO(rx_crc_errors)},
 	{DRVSTAT_INFO(rx_alignment_symbol_errors)},
 	{DRVSTAT_INFO(rx_pause_frames)},
@@ -107,10 +102,21 @@ static const struct be_ethtool_stat et_rx_stats[] = {
 	{DRVSTAT_RX_INFO(rx_compl)},
 	{DRVSTAT_RX_INFO(rx_mcast_pkts)},
 	{DRVSTAT_RX_INFO(rx_post_fail)},
+	{DRVSTAT_RX_INFO(rx_dropped)},
 	{ERXSTAT_INFO(rx_drops_no_fragments)}
 };
 #define ETHTOOL_RXSTATS_NUM (ARRAY_SIZE(et_rx_stats))
 
+/* Stats related to multi TX queues */
+static const struct be_ethtool_stat et_tx_stats[] = {
+	{DRVSTAT_TX_INFO(be_tx_rate)},
+	{DRVSTAT_TX_INFO(be_tx_reqs)},
+	{DRVSTAT_TX_INFO(be_tx_wrbs)},
+	{DRVSTAT_TX_INFO(be_tx_stops)},
+	{DRVSTAT_TX_INFO(be_tx_compl)}
+};
+#define ETHTOOL_TXSTATS_NUM (ARRAY_SIZE(et_tx_stats))
+
 static const char et_self_tests[][ETH_GSTRING_LEN] = {
 	"MAC Loopback test",
 	"PHY Loopback test",
@@ -253,17 +259,15 @@ be_get_ethtool_stats(struct net_device *netdev,
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	struct be_rx_obj *rxo;
+	struct be_tx_obj *txo;
 	void *p = NULL;
-	int i, j;
+	int i, j, base;
 
 	for (i = 0; i < ETHTOOL_STATS_NUM; i++) {
 		switch (et_stats[i].type) {
 		case NETSTAT:
 			p = &netdev->stats;
 			break;
-		case DRVSTAT_TX:
-			p = &adapter->tx_stats;
-			break;
 		case DRVSTAT:
 			p = &adapter->drv_stats;
 			break;
@@ -274,6 +278,7 @@ be_get_ethtool_stats(struct net_device *netdev,
 				*(u64 *)p: *(u32 *)p;
 	}
 
+	base = ETHTOOL_STATS_NUM;
 	for_all_rx_queues(adapter, rxo, j) {
 		for (i = 0; i < ETHTOOL_RXSTATS_NUM; i++) {
 			switch (et_rx_stats[i].type) {
@@ -285,11 +290,21 @@ be_get_ethtool_stats(struct net_device *netdev,
 								rxo->q.id;
 				break;
 			}
-			data[ETHTOOL_STATS_NUM + j * ETHTOOL_RXSTATS_NUM + i] =
+			data[base + j * ETHTOOL_RXSTATS_NUM + i] =
 				(et_rx_stats[i].size == sizeof(u64)) ?
 					*(u64 *)p: *(u32 *)p;
 		}
 	}
+
+	base = ETHTOOL_STATS_NUM + adapter->num_rx_qs * ETHTOOL_RXSTATS_NUM;
+	for_all_tx_queues(adapter, txo, j) {
+		for (i = 0; i < ETHTOOL_TXSTATS_NUM; i++) {
+			p = (u8 *)&txo->stats + et_tx_stats[i].offset;
+			data[base + j * ETHTOOL_TXSTATS_NUM + i] =
+				(et_tx_stats[i].size == sizeof(u64)) ?
+					*(u64 *)p: *(u32 *)p;
+		}
+	}
 }
 
 static void
@@ -312,6 +327,13 @@ be_get_stat_strings(struct net_device *netdev, uint32_t stringset,
 				data += ETH_GSTRING_LEN;
 			}
 		}
+		for (i = 0; i < adapter->num_tx_qs; i++) {
+			for (j = 0; j < ETHTOOL_TXSTATS_NUM; j++) {
+				sprintf(data, "txq%d: %s", i,
+					et_tx_stats[j].desc);
+				data += ETH_GSTRING_LEN;
+			}
+		}
 		break;
 	case ETH_SS_TEST:
 		for (i = 0; i < ETHTOOL_TESTS_NUM; i++) {
@@ -331,7 +353,8 @@ static int be_get_sset_count(struct net_device *netdev, int stringset)
 		return ETHTOOL_TESTS_NUM;
 	case ETH_SS_STATS:
 		return ETHTOOL_STATS_NUM +
-			adapter->num_rx_qs * ETHTOOL_RXSTATS_NUM;
+			adapter->num_rx_qs * ETHTOOL_RXSTATS_NUM +
+			adapter->num_tx_qs * ETHTOOL_TXSTATS_NUM;
 	default:
 		return -EINVAL;
 	}
@@ -386,7 +409,7 @@ static int be_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 		}
 		status = be_cmd_get_phy_info(adapter, &phy_cmd);
 		if (!status) {
-			resp = (struct be_cmd_resp_get_phy_info *) phy_cmd.va;
+			resp = phy_cmd.va;
 			intf_type = le16_to_cpu(resp->interface_type);
 
 			switch (intf_type) {
@@ -457,10 +480,10 @@ be_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring)
 	struct be_adapter *adapter = netdev_priv(netdev);
 
 	ring->rx_max_pending = adapter->rx_obj[0].q.len;
-	ring->tx_max_pending = adapter->tx_obj.q.len;
+	ring->tx_max_pending = adapter->tx_obj[0].q.len;
 
 	ring->rx_pending = atomic_read(&adapter->rx_obj[0].q.used);
-	ring->tx_pending = atomic_read(&adapter->tx_obj.q.used);
+	ring->tx_pending = atomic_read(&adapter->tx_obj[0].q.used);
 }
 
 static void
@@ -690,7 +713,7 @@ be_read_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
 	status = be_cmd_get_seeprom_data(adapter, &eeprom_cmd);
 
 	if (!status) {
-		resp = (struct be_cmd_resp_seeprom_read *) eeprom_cmd.va;
+		resp = eeprom_cmd.va;
 		memcpy(data, resp->seeprom_data + eeprom->offset, eeprom->len);
 	}
 	dma_free_coherent(&adapter->pdev->dev, eeprom_cmd.size, eeprom_cmd.va,
diff --git a/drivers/net/benet/be_main.c b/drivers/net/benet/be_main.c
index a485f7fdaf37..c411bb1845fd 100644
--- a/drivers/net/benet/be_main.c
+++ b/drivers/net/benet/be_main.c
@@ -33,10 +33,6 @@ module_param(num_vfs, uint, S_IRUGO);
 MODULE_PARM_DESC(rx_frag_size, "Size of a fragment that holds rcvd data.");
 MODULE_PARM_DESC(num_vfs, "Number of PCI VFs to initialize");
 
-static bool multi_rxq = true;
-module_param(multi_rxq, bool, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(multi_rxq, "Multi Rx Queue support. Enabled by default");
-
 static DEFINE_PCI_DEVICE_TABLE(be_dev_ids) = {
 	{ PCI_DEVICE(BE_VENDOR_ID, BE_DEVICE_ID1) },
 	{ PCI_DEVICE(BE_VENDOR_ID, BE_DEVICE_ID2) },
@@ -48,7 +44,7 @@ static DEFINE_PCI_DEVICE_TABLE(be_dev_ids) = {
 };
 MODULE_DEVICE_TABLE(pci, be_dev_ids);
 /* UE Status Low CSR */
-static char *ue_status_low_desc[] = {
+static const char * const ue_status_low_desc[] = {
 	"CEV",
 	"CTX",
 	"DBUF",
@@ -83,7 +79,7 @@ static char *ue_status_low_desc[] = {
 	"MPU_INTPEND"
 };
 /* UE Status High CSR */
-static char *ue_status_hi_desc[] = {
+static const char * const ue_status_hi_desc[] = {
 	"LPCMEMHOST",
 	"MGMT_MAC",
 	"PCS0ONLINE",
@@ -107,7 +103,7 @@ static char *ue_status_hi_desc[] = {
 	"HOST7",
 	"HOST8",
 	"HOST9",
-	"NETC"
+	"NETC",
 	"Unknown",
 	"Unknown",
 	"Unknown",
@@ -362,8 +358,8 @@ static void populate_lancer_stats(struct be_adapter *adapter)
 	drvs->rx_priority_pause_frames = 0;
 	drvs->pmem_fifo_overflow_drop = 0;
 	drvs->rx_pause_frames =
-		make_64bit_val(pport_stats->rx_pause_frames_lo,
-				 pport_stats->rx_pause_frames_hi);
+		make_64bit_val(pport_stats->rx_pause_frames_hi,
+				 pport_stats->rx_pause_frames_lo);
 	drvs->rx_crc_errors = make_64bit_val(pport_stats->rx_crc_errors_hi,
 						pport_stats->rx_crc_errors_lo);
 	drvs->rx_control_frames =
@@ -427,31 +423,40 @@ void netdev_stats_update(struct be_adapter *adapter)
 	struct be_drv_stats *drvs = &adapter->drv_stats;
 	struct net_device_stats *dev_stats = &adapter->netdev->stats;
 	struct be_rx_obj *rxo;
+	struct be_tx_obj *txo;
+	unsigned long pkts = 0, bytes = 0, mcast = 0, drops = 0;
 	int i;
 
-	memset(dev_stats, 0, sizeof(*dev_stats));
 	for_all_rx_queues(adapter, rxo, i) {
-		dev_stats->rx_packets += rx_stats(rxo)->rx_pkts;
-		dev_stats->rx_bytes += rx_stats(rxo)->rx_bytes;
-		dev_stats->multicast += rx_stats(rxo)->rx_mcast_pkts;
+		pkts += rx_stats(rxo)->rx_pkts;
+		bytes += rx_stats(rxo)->rx_bytes;
+		mcast += rx_stats(rxo)->rx_mcast_pkts;
+		drops += rx_stats(rxo)->rx_dropped;
 		/*  no space in linux buffers: best possible approximation */
 		if (adapter->generation == BE_GEN3) {
 			if (!(lancer_chip(adapter))) {
-				struct be_erx_stats_v1 *erx_stats =
+				struct be_erx_stats_v1 *erx =
 					be_erx_stats_from_cmd(adapter);
-				dev_stats->rx_dropped +=
-				erx_stats->rx_drops_no_fragments[rxo->q.id];
+				drops += erx->rx_drops_no_fragments[rxo->q.id];
 			}
 		} else {
-			struct be_erx_stats_v0 *erx_stats =
+			struct be_erx_stats_v0 *erx =
 					be_erx_stats_from_cmd(adapter);
-			dev_stats->rx_dropped +=
-				erx_stats->rx_drops_no_fragments[rxo->q.id];
+			drops += erx->rx_drops_no_fragments[rxo->q.id];
 		}
 	}
+	dev_stats->rx_packets = pkts;
+	dev_stats->rx_bytes = bytes;
+	dev_stats->multicast = mcast;
+	dev_stats->rx_dropped = drops;
 
-	dev_stats->tx_packets = tx_stats(adapter)->be_tx_pkts;
-	dev_stats->tx_bytes = tx_stats(adapter)->be_tx_bytes;
+	pkts = bytes = 0;
+	for_all_tx_queues(adapter, txo, i) {
+		pkts += tx_stats(txo)->be_tx_pkts;
+		bytes += tx_stats(txo)->be_tx_bytes;
+	}
+	dev_stats->tx_packets = pkts;
+	dev_stats->tx_bytes = bytes;
 
 	/* bad pkts received */
 	dev_stats->rx_errors = drvs->rx_crc_errors +
@@ -554,9 +559,9 @@ static u32 be_calc_rate(u64 bytes, unsigned long ticks)
 	return rate;
 }
 
-static void be_tx_rate_update(struct be_adapter *adapter)
+static void be_tx_rate_update(struct be_tx_obj *txo)
 {
-	struct be_tx_stats *stats = tx_stats(adapter);
+	struct be_tx_stats *stats = tx_stats(txo);
 	ulong now = jiffies;
 
 	/* Wrapped around? */
@@ -575,10 +580,11 @@ static void be_tx_rate_update(struct be_adapter *adapter)
 	}
 }
 
-static void be_tx_stats_update(struct be_adapter *adapter,
+static void be_tx_stats_update(struct be_tx_obj *txo,
 			u32 wrb_cnt, u32 copied, u32 gso_segs, bool stopped)
 {
-	struct be_tx_stats *stats = tx_stats(adapter);
+	struct be_tx_stats *stats = tx_stats(txo);
+
 	stats->be_tx_reqs++;
 	stats->be_tx_wrbs += wrb_cnt;
 	stats->be_tx_bytes += copied;
@@ -648,7 +654,7 @@ static void wrb_fill_hdr(struct be_adapter *adapter, struct be_eth_hdr_wrb *hdr,
 			AMAP_SET_BITS(struct amap_eth_hdr_wrb, udpcs, hdr, 1);
 	}
 
-	if (adapter->vlan_grp && vlan_tx_tag_present(skb)) {
+	if (vlan_tx_tag_present(skb)) {
 		AMAP_SET_BITS(struct amap_eth_hdr_wrb, vlan, hdr, 1);
 		vlan_tag = vlan_tx_tag_get(skb);
 		vlan_prio = (vlan_tag & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
@@ -682,14 +688,13 @@ static void unmap_tx_frag(struct device *dev, struct be_eth_wrb *wrb,
 	}
 }
 
-static int make_tx_wrbs(struct be_adapter *adapter,
+static int make_tx_wrbs(struct be_adapter *adapter, struct be_queue_info *txq,
 		struct sk_buff *skb, u32 wrb_cnt, bool dummy_wrb)
 {
 	dma_addr_t busaddr;
 	int i, copied = 0;
 	struct device *dev = &adapter->pdev->dev;
 	struct sk_buff *first_skb = skb;
-	struct be_queue_info *txq = &adapter->tx_obj.q;
 	struct be_eth_wrb *wrb;
 	struct be_eth_hdr_wrb *hdr;
 	bool map_single = false;
@@ -753,19 +758,19 @@ static netdev_tx_t be_xmit(struct sk_buff *skb,
 			struct net_device *netdev)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
-	struct be_tx_obj *tx_obj = &adapter->tx_obj;
-	struct be_queue_info *txq = &tx_obj->q;
+	struct be_tx_obj *txo = &adapter->tx_obj[skb_get_queue_mapping(skb)];
+	struct be_queue_info *txq = &txo->q;
 	u32 wrb_cnt = 0, copied = 0;
 	u32 start = txq->head;
 	bool dummy_wrb, stopped = false;
 
 	wrb_cnt = wrb_cnt_for_skb(adapter, skb, &dummy_wrb);
 
-	copied = make_tx_wrbs(adapter, skb, wrb_cnt, dummy_wrb);
+	copied = make_tx_wrbs(adapter, txq, skb, wrb_cnt, dummy_wrb);
 	if (copied) {
 		/* record the sent skb in the sent_skb table */
-		BUG_ON(tx_obj->sent_skb_list[start]);
-		tx_obj->sent_skb_list[start] = skb;
+		BUG_ON(txo->sent_skb_list[start]);
+		txo->sent_skb_list[start] = skb;
 
 		/* Ensure txq has space for the next skb; Else stop the queue
 		 * *BEFORE* ringing the tx doorbell, so that we serialze the
@@ -774,13 +779,13 @@ static netdev_tx_t be_xmit(struct sk_buff *skb,
 		atomic_add(wrb_cnt, &txq->used);
 		if ((BE_MAX_TX_FRAG_COUNT + atomic_read(&txq->used)) >=
 								txq->len) {
-			netif_stop_queue(netdev);
+			netif_stop_subqueue(netdev, skb_get_queue_mapping(skb));
 			stopped = true;
 		}
 
 		be_txq_notify(adapter, txq->id, wrb_cnt);
 
-		be_tx_stats_update(adapter, wrb_cnt, copied,
+		be_tx_stats_update(txo, wrb_cnt, copied,
 				skb_shinfo(skb)->gso_segs, stopped);
 	} else {
 		txq->head = start;
@@ -842,13 +847,6 @@ static int be_vid_config(struct be_adapter *adapter, bool vf, u32 vf_num)
 	return status;
 }
 
-static void be_vlan_register(struct net_device *netdev, struct vlan_group *grp)
-{
-	struct be_adapter *adapter = netdev_priv(netdev);
-
-	adapter->vlan_grp = grp;
-}
-
 static void be_vlan_add_vid(struct net_device *netdev, u16 vid)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
@@ -867,7 +865,6 @@ static void be_vlan_rem_vid(struct net_device *netdev, u16 vid)
 	struct be_adapter *adapter = netdev_priv(netdev);
 
 	adapter->vlans_added--;
-	vlan_group_set_device(adapter->vlan_grp, vid, NULL);
 
 	if (!be_physfn(adapter))
 		return;
@@ -1177,8 +1174,7 @@ static void be_rx_compl_process(struct be_adapter *adapter,
 
 	skb = netdev_alloc_skb_ip_align(netdev, BE_HDR_LEN);
 	if (unlikely(!skb)) {
-		if (net_ratelimit())
-			dev_warn(&adapter->pdev->dev, "skb alloc failed\n");
+		rxo->stats.rx_dropped++;
 		be_rx_compl_discard(adapter, rxo, rxcp);
 		return;
 	}
@@ -1196,16 +1192,10 @@ static void be_rx_compl_process(struct be_adapter *adapter,
 		skb->rxhash = rxcp->rss_hash;
 
 
-	if (unlikely(rxcp->vlanf)) {
-		if (!adapter->vlan_grp || adapter->vlans_added == 0) {
-			kfree_skb(skb);
-			return;
-		}
-		vlan_hwaccel_receive_skb(skb, adapter->vlan_grp,
-					rxcp->vlan_tag);
-	} else {
-		netif_receive_skb(skb);
-	}
+	if (unlikely(rxcp->vlanf))
+		__vlan_hwaccel_put_tag(skb, rxcp->vlan_tag);
+
+	netif_receive_skb(skb);
 }
 
 /* Process the RX completion indicated by rxcp when GRO is enabled */
@@ -1259,11 +1249,10 @@ static void be_rx_compl_process_gro(struct be_adapter *adapter,
 	if (adapter->netdev->features & NETIF_F_RXHASH)
 		skb->rxhash = rxcp->rss_hash;
 
-	if (likely(!rxcp->vlanf))
-		napi_gro_frags(&eq_obj->napi);
-	else
-		vlan_gro_frags(&eq_obj->napi, adapter->vlan_grp,
-				rxcp->vlan_tag);
+	if (unlikely(rxcp->vlanf))
+		__vlan_hwaccel_put_tag(skb, rxcp->vlan_tag);
+
+	napi_gro_frags(&eq_obj->napi);
 }
 
 static void be_parse_rx_compl_v1(struct be_adapter *adapter,
@@ -1459,11 +1448,12 @@ static struct be_eth_tx_compl *be_tx_compl_get(struct be_queue_info *tx_cq)
 	return txcp;
 }
 
-static u16 be_tx_compl_process(struct be_adapter *adapter, u16 last_index)
+static u16 be_tx_compl_process(struct be_adapter *adapter,
+		struct be_tx_obj *txo, u16 last_index)
 {
-	struct be_queue_info *txq = &adapter->tx_obj.q;
+	struct be_queue_info *txq = &txo->q;
 	struct be_eth_wrb *wrb;
-	struct sk_buff **sent_skbs = adapter->tx_obj.sent_skb_list;
+	struct sk_buff **sent_skbs = txo->sent_skb_list;
 	struct sk_buff *sent_skb;
 	u16 cur_index, num_wrbs = 1; /* account for hdr wrb */
 	bool unmap_skb_hdr = true;
@@ -1504,7 +1494,8 @@ static inline struct be_eq_entry *event_get(struct be_eq_obj *eq_obj)
 }
 
 static int event_handle(struct be_adapter *adapter,
-			struct be_eq_obj *eq_obj)
+			struct be_eq_obj *eq_obj,
+			bool rearm)
 {
 	struct be_eq_entry *eqe;
 	u16 num = 0;
@@ -1517,7 +1508,10 @@ static int event_handle(struct be_adapter *adapter,
 	/* Deal with any spurious interrupts that come
 	 * without events
 	 */
-	be_eq_notify(adapter, eq_obj->q.id, true, true, num);
+	if (!num)
+		rearm = true;
+
+	be_eq_notify(adapter, eq_obj->q.id, rearm, true, num);
 	if (num)
 		napi_schedule(&eq_obj->napi);
 
@@ -1563,15 +1557,17 @@ static void be_rx_q_clean(struct be_adapter *adapter, struct be_rx_obj *rxo)
 		memset(page_info, 0, sizeof(*page_info));
 	}
 	BUG_ON(atomic_read(&rxq->used));
+	rxq->tail = rxq->head = 0;
 }
 
-static void be_tx_compl_clean(struct be_adapter *adapter)
+static void be_tx_compl_clean(struct be_adapter *adapter,
+				struct be_tx_obj *txo)
 {
-	struct be_queue_info *tx_cq = &adapter->tx_obj.cq;
-	struct be_queue_info *txq = &adapter->tx_obj.q;
+	struct be_queue_info *tx_cq = &txo->cq;
+	struct be_queue_info *txq = &txo->q;
 	struct be_eth_tx_compl *txcp;
 	u16 end_idx, cmpl = 0, timeo = 0, num_wrbs = 0;
-	struct sk_buff **sent_skbs = adapter->tx_obj.sent_skb_list;
+	struct sk_buff **sent_skbs = txo->sent_skb_list;
 	struct sk_buff *sent_skb;
 	bool dummy_wrb;
 
@@ -1580,7 +1576,7 @@ static void be_tx_compl_clean(struct be_adapter *adapter)
 		while ((txcp = be_tx_compl_get(tx_cq))) {
 			end_idx = AMAP_GET_BITS(struct amap_eth_tx_compl,
 					wrb_index, txcp);
-			num_wrbs += be_tx_compl_process(adapter, end_idx);
+			num_wrbs += be_tx_compl_process(adapter, txo, end_idx);
 			cmpl++;
 		}
 		if (cmpl) {
@@ -1607,7 +1603,7 @@ static void be_tx_compl_clean(struct be_adapter *adapter)
 		index_adv(&end_idx,
 			wrb_cnt_for_skb(adapter, sent_skb, &dummy_wrb) - 1,
 			txq->len);
-		num_wrbs = be_tx_compl_process(adapter, end_idx);
+		num_wrbs = be_tx_compl_process(adapter, txo, end_idx);
 		atomic_sub(num_wrbs, &txq->used);
 	}
 }
@@ -1666,16 +1662,20 @@ err:
 static void be_tx_queues_destroy(struct be_adapter *adapter)
 {
 	struct be_queue_info *q;
+	struct be_tx_obj *txo;
+	u8 i;
 
-	q = &adapter->tx_obj.q;
-	if (q->created)
-		be_cmd_q_destroy(adapter, q, QTYPE_TXQ);
-	be_queue_free(adapter, q);
+	for_all_tx_queues(adapter, txo, i) {
+		q = &txo->q;
+		if (q->created)
+			be_cmd_q_destroy(adapter, q, QTYPE_TXQ);
+		be_queue_free(adapter, q);
 
-	q = &adapter->tx_obj.cq;
-	if (q->created)
-		be_cmd_q_destroy(adapter, q, QTYPE_CQ);
-	be_queue_free(adapter, q);
+		q = &txo->cq;
+		if (q->created)
+			be_cmd_q_destroy(adapter, q, QTYPE_CQ);
+		be_queue_free(adapter, q);
+	}
 
 	/* Clear any residual events */
 	be_eq_clean(adapter, &adapter->tx_eq);
@@ -1686,56 +1686,48 @@ static void be_tx_queues_destroy(struct be_adapter *adapter)
 	be_queue_free(adapter, q);
 }
 
+/* One TX event queue is shared by all TX compl qs */
 static int be_tx_queues_create(struct be_adapter *adapter)
 {
 	struct be_queue_info *eq, *q, *cq;
+	struct be_tx_obj *txo;
+	u8 i;
 
 	adapter->tx_eq.max_eqd = 0;
 	adapter->tx_eq.min_eqd = 0;
 	adapter->tx_eq.cur_eqd = 96;
 	adapter->tx_eq.enable_aic = false;
-	/* Alloc Tx Event queue */
+
 	eq = &adapter->tx_eq.q;
-	if (be_queue_alloc(adapter, eq, EVNT_Q_LEN, sizeof(struct be_eq_entry)))
+	if (be_queue_alloc(adapter, eq, EVNT_Q_LEN,
+		sizeof(struct be_eq_entry)))
 		return -1;
 
-	/* Ask BE to create Tx Event queue */
 	if (be_cmd_eq_create(adapter, eq, adapter->tx_eq.cur_eqd))
-		goto tx_eq_free;
-
+		goto err;
 	adapter->tx_eq.eq_idx = adapter->eq_next_idx++;
 
-
-	/* Alloc TX eth compl queue */
-	cq = &adapter->tx_obj.cq;
-	if (be_queue_alloc(adapter, cq, TX_CQ_LEN,
+	for_all_tx_queues(adapter, txo, i) {
+		cq = &txo->cq;
+		if (be_queue_alloc(adapter, cq, TX_CQ_LEN,
 			sizeof(struct be_eth_tx_compl)))
-		goto tx_eq_destroy;
+			goto err;
 
-	/* Ask BE to create Tx eth compl queue */
-	if (be_cmd_cq_create(adapter, cq, eq, false, false, 3))
-		goto tx_cq_free;
+		if (be_cmd_cq_create(adapter, cq, eq, false, false, 3))
+			goto err;
 
-	/* Alloc TX eth queue */
-	q = &adapter->tx_obj.q;
-	if (be_queue_alloc(adapter, q, TX_Q_LEN, sizeof(struct be_eth_wrb)))
-		goto tx_cq_destroy;
+		q = &txo->q;
+		if (be_queue_alloc(adapter, q, TX_Q_LEN,
+			sizeof(struct be_eth_wrb)))
+			goto err;
 
-	/* Ask BE to create Tx eth queue */
-	if (be_cmd_txq_create(adapter, q, cq))
-		goto tx_q_free;
+		if (be_cmd_txq_create(adapter, q, cq))
+			goto err;
+	}
 	return 0;
 
-tx_q_free:
-	be_queue_free(adapter, q);
-tx_cq_destroy:
-	be_cmd_q_destroy(adapter, cq, QTYPE_CQ);
-tx_cq_free:
-	be_queue_free(adapter, cq);
-tx_eq_destroy:
-	be_cmd_q_destroy(adapter, eq, QTYPE_EQ);
-tx_eq_free:
-	be_queue_free(adapter, eq);
+err:
+	be_tx_queues_destroy(adapter);
 	return -1;
 }
 
@@ -1746,36 +1738,23 @@ static void be_rx_queues_destroy(struct be_adapter *adapter)
 	int i;
 
 	for_all_rx_queues(adapter, rxo, i) {
-		q = &rxo->q;
-		if (q->created) {
-			be_cmd_q_destroy(adapter, q, QTYPE_RXQ);
-			/* After the rxq is invalidated, wait for a grace time
-			 * of 1ms for all dma to end and the flush compl to
-			 * arrive
-			 */
-			mdelay(1);
-			be_rx_q_clean(adapter, rxo);
-		}
-		be_queue_free(adapter, q);
+		be_queue_free(adapter, &rxo->q);
 
 		q = &rxo->cq;
 		if (q->created)
 			be_cmd_q_destroy(adapter, q, QTYPE_CQ);
 		be_queue_free(adapter, q);
 
-		/* Clear any residual events */
 		q = &rxo->rx_eq.q;
-		if (q->created) {
-			be_eq_clean(adapter, &rxo->rx_eq);
+		if (q->created)
 			be_cmd_q_destroy(adapter, q, QTYPE_EQ);
-		}
 		be_queue_free(adapter, q);
 	}
 }
 
 static u32 be_num_rxqs_want(struct be_adapter *adapter)
 {
-	if (multi_rxq && (adapter->function_caps & BE_FUNCTION_CAPS_RSS) &&
+	if ((adapter->function_caps & BE_FUNCTION_CAPS_RSS) &&
 		!adapter->sriov_enabled && !(adapter->function_mode & 0x400)) {
 		return 1 + MAX_RSS_QS; /* one default non-RSS queue */
 	} else {
@@ -1827,30 +1806,14 @@ static int be_rx_queues_create(struct be_adapter *adapter)
 		rc = be_cmd_cq_create(adapter, cq, eq, false, false, 3);
 		if (rc)
 			goto err;
-		/* Rx Q */
+
+		/* Rx Q - will be created in be_open() */
 		q = &rxo->q;
 		rc = be_queue_alloc(adapter, q, RX_Q_LEN,
 				sizeof(struct be_eth_rx_d));
 		if (rc)
 			goto err;
 
-		rc = be_cmd_rxq_create(adapter, q, cq->id, rx_frag_size,
-			BE_MAX_JUMBO_FRAME_SIZE, adapter->if_handle,
-			(i > 0) ? 1 : 0/* rss enable */, &rxo->rss_id);
-		if (rc)
-			goto err;
-	}
-
-	if (be_multi_rxq(adapter)) {
-		u8 rsstable[MAX_RSS_QS];
-
-		for_all_rss_queues(adapter, rxo, i)
-			rsstable[i] = rxo->rss_id;
-
-		rc = be_cmd_rss_config(adapter, rsstable,
-			adapter->num_rx_qs - 1);
-		if (rc)
-			goto err;
 	}
 
 	return 0;
@@ -1876,10 +1839,10 @@ static irqreturn_t be_intx(int irq, void *dev)
 
 	if (lancer_chip(adapter)) {
 		if (event_peek(&adapter->tx_eq))
-			tx = event_handle(adapter, &adapter->tx_eq);
+			tx = event_handle(adapter, &adapter->tx_eq, false);
 		for_all_rx_queues(adapter, rxo, i) {
 			if (event_peek(&rxo->rx_eq))
-				rx |= event_handle(adapter, &rxo->rx_eq);
+				rx |= event_handle(adapter, &rxo->rx_eq, true);
 		}
 
 		if (!(tx || rx))
@@ -1892,11 +1855,11 @@ static irqreturn_t be_intx(int irq, void *dev)
 			return IRQ_NONE;
 
 		if ((1 << adapter->tx_eq.eq_idx & isr))
-			event_handle(adapter, &adapter->tx_eq);
+			event_handle(adapter, &adapter->tx_eq, false);
 
 		for_all_rx_queues(adapter, rxo, i) {
 			if ((1 << rxo->rx_eq.eq_idx & isr))
-				event_handle(adapter, &rxo->rx_eq);
+				event_handle(adapter, &rxo->rx_eq, true);
 		}
 	}
 
@@ -1908,7 +1871,7 @@ static irqreturn_t be_msix_rx(int irq, void *dev)
 	struct be_rx_obj *rxo = dev;
 	struct be_adapter *adapter = rxo->adapter;
 
-	event_handle(adapter, &rxo->rx_eq);
+	event_handle(adapter, &rxo->rx_eq, true);
 
 	return IRQ_HANDLED;
 }
@@ -1917,7 +1880,7 @@ static irqreturn_t be_msix_tx_mcc(int irq, void *dev)
 {
 	struct be_adapter *adapter = dev;
 
-	event_handle(adapter, &adapter->tx_eq);
+	event_handle(adapter, &adapter->tx_eq, false);
 
 	return IRQ_HANDLED;
 }
@@ -1978,45 +1941,48 @@ static int be_poll_tx_mcc(struct napi_struct *napi, int budget)
 	struct be_eq_obj *tx_eq = container_of(napi, struct be_eq_obj, napi);
 	struct be_adapter *adapter =
 		container_of(tx_eq, struct be_adapter, tx_eq);
-	struct be_queue_info *txq = &adapter->tx_obj.q;
-	struct be_queue_info *tx_cq = &adapter->tx_obj.cq;
+	struct be_tx_obj *txo;
 	struct be_eth_tx_compl *txcp;
-	int tx_compl = 0, mcc_compl, status = 0;
-	u16 end_idx, num_wrbs = 0;
+	int tx_compl, mcc_compl, status = 0;
+	u8 i;
+	u16 num_wrbs;
+
+	for_all_tx_queues(adapter, txo, i) {
+		tx_compl = 0;
+		num_wrbs = 0;
+		while ((txcp = be_tx_compl_get(&txo->cq))) {
+			num_wrbs += be_tx_compl_process(adapter, txo,
+				AMAP_GET_BITS(struct amap_eth_tx_compl,
+					wrb_index, txcp));
+			tx_compl++;
+		}
+		if (tx_compl) {
+			be_cq_notify(adapter, txo->cq.id, true, tx_compl);
 
-	while ((txcp = be_tx_compl_get(tx_cq))) {
-		end_idx = AMAP_GET_BITS(struct amap_eth_tx_compl,
-				wrb_index, txcp);
-		num_wrbs += be_tx_compl_process(adapter, end_idx);
-		tx_compl++;
+			atomic_sub(num_wrbs, &txo->q.used);
+
+			/* As Tx wrbs have been freed up, wake up netdev queue
+			 * if it was stopped due to lack of tx wrbs.  */
+			if (__netif_subqueue_stopped(adapter->netdev, i) &&
+				atomic_read(&txo->q.used) < txo->q.len / 2) {
+				netif_wake_subqueue(adapter->netdev, i);
+			}
+
+			adapter->drv_stats.be_tx_events++;
+			txo->stats.be_tx_compl += tx_compl;
+		}
 	}
 
 	mcc_compl = be_process_mcc(adapter, &status);
 
-	napi_complete(napi);
-
 	if (mcc_compl) {
 		struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
 		be_cq_notify(adapter, mcc_obj->cq.id, true, mcc_compl);
 	}
 
-	if (tx_compl) {
-		be_cq_notify(adapter, adapter->tx_obj.cq.id, true, tx_compl);
-
-		atomic_sub(num_wrbs, &txq->used);
-
-		/* As Tx wrbs have been freed up, wake up netdev queue if
-		 * it was stopped due to lack of tx wrbs.
-		 */
-		if (netif_queue_stopped(adapter->netdev) &&
-			atomic_read(&txq->used) < txq->len / 2) {
-			netif_wake_queue(adapter->netdev);
-		}
-
-		tx_stats(adapter)->be_tx_events++;
-		tx_stats(adapter)->be_tx_compl += tx_compl;
-	}
+	napi_complete(napi);
 
+	be_eq_notify(adapter, tx_eq->q.id, true, false, 0);
 	return 1;
 }
 
@@ -2065,6 +2031,7 @@ static void be_worker(struct work_struct *work)
 	struct be_adapter *adapter =
 		container_of(work, struct be_adapter, work.work);
 	struct be_rx_obj *rxo;
+	struct be_tx_obj *txo;
 	int i;
 
 	if (!adapter->ue_detected && !lancer_chip(adapter))
@@ -2092,7 +2059,9 @@ static void be_worker(struct work_struct *work)
 		else
 			be_cmd_get_stats(adapter, &adapter->stats_cmd);
 	}
-	be_tx_rate_update(adapter);
+
+	for_all_tx_queues(adapter, txo, i)
+		be_tx_rate_update(txo);
 
 	for_all_rx_queues(adapter, rxo, i) {
 		be_rx_rate_update(rxo);
@@ -2290,10 +2259,36 @@ done:
 	adapter->isr_registered = false;
 }
 
+static void be_rx_queues_clear(struct be_adapter *adapter)
+{
+	struct be_queue_info *q;
+	struct be_rx_obj *rxo;
+	int i;
+
+	for_all_rx_queues(adapter, rxo, i) {
+		q = &rxo->q;
+		if (q->created) {
+			be_cmd_rxq_destroy(adapter, q);
+			/* After the rxq is invalidated, wait for a grace time
+			 * of 1ms for all dma to end and the flush compl to
+			 * arrive
+			 */
+			mdelay(1);
+			be_rx_q_clean(adapter, rxo);
+		}
+
+		/* Clear any residual events */
+		q = &rxo->rx_eq.q;
+		if (q->created)
+			be_eq_clean(adapter, &rxo->rx_eq);
+	}
+}
+
 static int be_close(struct net_device *netdev)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	struct be_rx_obj *rxo;
+	struct be_tx_obj *txo;
 	struct be_eq_obj *tx_eq = &adapter->tx_eq;
 	int vec, i;
 
@@ -2311,10 +2306,11 @@ static int be_close(struct net_device *netdev)
 	napi_disable(&tx_eq->napi);
 
 	if (lancer_chip(adapter)) {
-		be_cq_notify(adapter, adapter->tx_obj.cq.id, false, 0);
 		be_cq_notify(adapter, adapter->mcc_obj.cq.id, false, 0);
 		for_all_rx_queues(adapter, rxo, i)
 			 be_cq_notify(adapter, rxo->cq.id, false, 0);
+		for_all_tx_queues(adapter, txo, i)
+			 be_cq_notify(adapter, txo->cq.id, false, 0);
 	}
 
 	if (msix_enabled(adapter)) {
@@ -2333,8 +2329,43 @@ static int be_close(struct net_device *netdev)
 	/* Wait for all pending tx completions to arrive so that
 	 * all tx skbs are freed.
 	 */
-	be_tx_compl_clean(adapter);
+	for_all_tx_queues(adapter, txo, i)
+		be_tx_compl_clean(adapter, txo);
+
+	be_rx_queues_clear(adapter);
+	return 0;
+}
+
+static int be_rx_queues_setup(struct be_adapter *adapter)
+{
+	struct be_rx_obj *rxo;
+	int rc, i;
+	u8 rsstable[MAX_RSS_QS];
+
+	for_all_rx_queues(adapter, rxo, i) {
+		rc = be_cmd_rxq_create(adapter, &rxo->q, rxo->cq.id,
+			rx_frag_size, BE_MAX_JUMBO_FRAME_SIZE,
+			adapter->if_handle,
+			(i > 0) ? 1 : 0/* rss enable */, &rxo->rss_id);
+		if (rc)
+			return rc;
+	}
+
+	if (be_multi_rxq(adapter)) {
+		for_all_rss_queues(adapter, rxo, i)
+			rsstable[i] = rxo->rss_id;
 
+		rc = be_cmd_rss_config(adapter, rsstable,
+			adapter->num_rx_qs - 1);
+		if (rc)
+			return rc;
+	}
+
+	/* First time posting */
+	for_all_rx_queues(adapter, rxo, i) {
+		be_post_rx_frags(rxo, GFP_KERNEL);
+		napi_enable(&rxo->rx_eq.napi);
+	}
 	return 0;
 }
 
@@ -2348,10 +2379,10 @@ static int be_open(struct net_device *netdev)
 	u8 mac_speed;
 	u16 link_speed;
 
-	for_all_rx_queues(adapter, rxo, i) {
-		be_post_rx_frags(rxo, GFP_KERNEL);
-		napi_enable(&rxo->rx_eq.napi);
-	}
+	status = be_rx_queues_setup(adapter);
+	if (status)
+		goto err;
+
 	napi_enable(&tx_eq->napi);
 
 	be_irq_register(adapter);
@@ -2480,6 +2511,8 @@ static int be_setup(struct be_adapter *adapter)
 	int status;
 	u8 mac[ETH_ALEN];
 
+	be_cmd_req_native_mode(adapter);
+
 	cap_flags = en_flags = BE_IF_FLAGS_UNTAGGED |
 				BE_IF_FLAGS_BROADCAST |
 				BE_IF_FLAGS_MULTICAST;
@@ -2539,6 +2572,9 @@ static int be_setup(struct be_adapter *adapter)
 	if (status != 0)
 		goto tx_qs_destroy;
 
+	/* Allow all priorities by default. A GRP5 evt may modify this */
+	adapter->vlan_prio_bmap = 0xff;
+
 	status = be_mcc_queues_create(adapter);
 	if (status != 0)
 		goto rx_qs_destroy;
@@ -2584,6 +2620,8 @@ static int be_clear(struct be_adapter *adapter)
 
 	be_cmd_if_destroy(adapter, adapter->if_handle,  0);
 
+	adapter->be3_native = 0;
+
 	/* tell fw we're done with firing cmds */
 	be_cmd_fw_clean(adapter);
 	return 0;
@@ -2901,7 +2939,6 @@ static struct net_device_ops be_netdev_ops = {
 	.ndo_set_mac_address	= be_mac_addr_set,
 	.ndo_change_mtu		= be_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_vlan_rx_register	= be_vlan_register,
 	.ndo_vlan_rx_add_vid	= be_vlan_add_vid,
 	.ndo_vlan_rx_kill_vid	= be_vlan_rem_vid,
 	.ndo_set_vf_mac		= be_set_vf_mac,
@@ -2925,12 +2962,9 @@ static void be_netdev_init(struct net_device *netdev)
 	netdev->features |= netdev->hw_features |
 		NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_FILTER;
 
-	netdev->vlan_features |= NETIF_F_SG | NETIF_F_TSO |
+	netdev->vlan_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 |
 		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 
-	if (lancer_chip(adapter))
-		netdev->vlan_features |= NETIF_F_TSO6;
-
 	netdev->flags |= IFF_MULTICAST;
 
 	/* Default settings for Rx and Tx flow control */
@@ -3185,7 +3219,16 @@ static int be_get_config(struct be_adapter *adapter)
 	if (status)
 		return status;
 
-	be_cmd_check_native_mode(adapter);
+	if ((num_vfs && adapter->sriov_enabled) ||
+		(adapter->function_mode & 0x400) ||
+		lancer_chip(adapter) || !be_physfn(adapter)) {
+		adapter->num_tx_qs = 1;
+		netif_set_real_num_tx_queues(adapter->netdev,
+			adapter->num_tx_qs);
+	} else {
+		adapter->num_tx_qs = MAX_TX_QS;
+	}
+
 	return 0;
 }
 
@@ -3288,7 +3331,7 @@ static int __devinit be_probe(struct pci_dev *pdev,
 		goto disable_dev;
 	pci_set_master(pdev);
 
-	netdev = alloc_etherdev(sizeof(struct be_adapter));
+	netdev = alloc_etherdev_mq(sizeof(struct be_adapter), MAX_TX_QS);
 	if (netdev == NULL) {
 		status = -ENOMEM;
 		goto rel_reg;
@@ -3360,6 +3403,12 @@ static int __devinit be_probe(struct pci_dev *pdev,
 	if (status)
 		goto stats_clean;
 
+	/* 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);
+
 	be_msix_enable(adapter);
 
 	INIT_DELAYED_WORK(&adapter->work, be_worker);
@@ -3396,6 +3445,7 @@ static int __devinit be_probe(struct pci_dev *pdev,
 	}
 
 	dev_info(&pdev->dev, "%s port %d\n", nic_name(pdev), adapter->port_num);
+
 	schedule_delayed_work(&adapter->work, msecs_to_jiffies(100));
 	return 0;