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

Several cases of overlapping changes, as well as one instance
(vxlan) of a bug fix in 'net' overlapping with code movement
in 'net-next'.

Signed-off-by: David S. Miller <davem@davemloft.net>

48 files changed, 398 insertions, 254 deletions

diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 7b881edc0b0a..d81fceddbe0e 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -2455,7 +2455,7 @@ boomerang_interrupt(int irq, void *dev_id)
 					int i;
 					pci_unmap_single(VORTEX_PCI(vp),
 							le32_to_cpu(vp->tx_ring[entry].frag[0].addr),
-							le32_to_cpu(vp->tx_ring[entry].frag[0].length),
+							le32_to_cpu(vp->tx_ring[entry].frag[0].length)&0xFFF,
 							PCI_DMA_TODEVICE);
 
 					for (i=1; i<=skb_shinfo(skb)->nr_frags; i++)
diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
index 17472851674f..f749e4d389eb 100644
--- a/drivers/net/ethernet/altera/altera_tse_main.c
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -193,7 +193,6 @@ static void altera_tse_mdio_destroy(struct net_device *dev)
 			    priv->mdio->id);
 
 	mdiobus_unregister(priv->mdio);
-	kfree(priv->mdio->irq);
 	mdiobus_free(priv->mdio);
 	priv->mdio = NULL;
 }
diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index f71ab2647a3b..08a23e6b60e9 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -1460,7 +1460,19 @@ static int nb8800_probe(struct platform_device *pdev)
 		goto err_disable_clk;
 	}
 
-	priv->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
+	if (of_phy_is_fixed_link(pdev->dev.of_node)) {
+		ret = of_phy_register_fixed_link(pdev->dev.of_node);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "bad fixed-link spec\n");
+			goto err_free_bus;
+		}
+		priv->phy_node = of_node_get(pdev->dev.of_node);
+	}
+
+	if (!priv->phy_node)
+		priv->phy_node = of_parse_phandle(pdev->dev.of_node,
+						  "phy-handle", 0);
+
 	if (!priv->phy_node) {
 		dev_err(&pdev->dev, "no PHY specified\n");
 		ret = -ENODEV;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
index 04523d41b873..f8b810313094 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
@@ -4901,9 +4901,9 @@ struct c2s_pri_trans_table_entry {
  * cfc delete event data
  */
 struct cfc_del_event_data {
-	u32 cid;
-	u32 reserved0;
-	u32 reserved1;
+	__le32 cid;
+	__le32 reserved0;
+	__le32 reserved1;
 };
 
 
@@ -5119,15 +5119,9 @@ struct vf_pf_channel_zone_trigger {
  * zone that triggers the in-bound interrupt
  */
 struct trigger_vf_zone {
-#if defined(__BIG_ENDIAN)
-	u16 reserved1;
-	u8 reserved0;
-	struct vf_pf_channel_zone_trigger vf_pf_channel;
-#elif defined(__LITTLE_ENDIAN)
 	struct vf_pf_channel_zone_trigger vf_pf_channel;
 	u8 reserved0;
 	u16 reserved1;
-#endif
 	u32 reserved2;
 };
 
@@ -5212,9 +5206,9 @@ struct e2_integ_data {
  * set mac event data
  */
 struct eth_event_data {
-	u32 echo;
-	u32 reserved0;
-	u32 reserved1;
+	__le32 echo;
+	__le32 reserved0;
+	__le32 reserved1;
 };
 
 
@@ -5224,9 +5218,9 @@ struct eth_event_data {
 struct vf_pf_event_data {
 	u8 vf_id;
 	u8 reserved0;
-	u16 reserved1;
-	u32 msg_addr_lo;
-	u32 msg_addr_hi;
+	__le16 reserved1;
+	__le32 msg_addr_lo;
+	__le32 msg_addr_hi;
 };
 
 /*
@@ -5235,9 +5229,9 @@ struct vf_pf_event_data {
 struct vf_flr_event_data {
 	u8 vf_id;
 	u8 reserved0;
-	u16 reserved1;
-	u32 reserved2;
-	u32 reserved3;
+	__le16 reserved1;
+	__le32 reserved2;
+	__le32 reserved3;
 };
 
 /*
@@ -5246,9 +5240,9 @@ struct vf_flr_event_data {
 struct malicious_vf_event_data {
 	u8 vf_id;
 	u8 err_id;
-	u16 reserved1;
-	u32 reserved2;
-	u32 reserved3;
+	__le16 reserved1;
+	__le32 reserved2;
+	__le32 reserved3;
 };
 
 /*
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 5c95d0c3b076..b597c32275aa 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -5282,14 +5282,14 @@ static void bnx2x_handle_classification_eqe(struct bnx2x *bp,
 {
 	unsigned long ramrod_flags = 0;
 	int rc = 0;
-	u32 cid = elem->message.data.eth_event.echo & BNX2X_SWCID_MASK;
+	u32 echo = le32_to_cpu(elem->message.data.eth_event.echo);
+	u32 cid = echo & BNX2X_SWCID_MASK;
 	struct bnx2x_vlan_mac_obj *vlan_mac_obj;
 
 	/* Always push next commands out, don't wait here */
 	__set_bit(RAMROD_CONT, &ramrod_flags);
 
-	switch (le32_to_cpu((__force __le32)elem->message.data.eth_event.echo)
-			    >> BNX2X_SWCID_SHIFT) {
+	switch (echo >> BNX2X_SWCID_SHIFT) {
 	case BNX2X_FILTER_MAC_PENDING:
 		DP(BNX2X_MSG_SP, "Got SETUP_MAC completions\n");
 		if (CNIC_LOADED(bp) && (cid == BNX2X_ISCSI_ETH_CID(bp)))
@@ -5310,8 +5310,7 @@ static void bnx2x_handle_classification_eqe(struct bnx2x *bp,
 		bnx2x_handle_mcast_eqe(bp);
 		return;
 	default:
-		BNX2X_ERR("Unsupported classification command: %d\n",
-			  elem->message.data.eth_event.echo);
+		BNX2X_ERR("Unsupported classification command: 0x%x\n", echo);
 		return;
 	}
 
@@ -5480,9 +5479,6 @@ static void bnx2x_eq_int(struct bnx2x *bp)
 			goto next_spqe;
 		}
 
-		/* elem CID originates from FW; actually LE */
-		cid = SW_CID((__force __le32)
-			     elem->message.data.cfc_del_event.cid);
 		opcode = elem->message.opcode;
 
 		/* handle eq element */
@@ -5505,6 +5501,10 @@ static void bnx2x_eq_int(struct bnx2x *bp)
 			 * we may want to verify here that the bp state is
 			 * HALTING
 			 */
+
+			/* elem CID originates from FW; actually LE */
+			cid = SW_CID(elem->message.data.cfc_del_event.cid);
+
 			DP(BNX2X_MSG_SP,
 			   "got delete ramrod for MULTI[%d]\n", cid);
 
@@ -5598,10 +5598,8 @@ static void bnx2x_eq_int(struct bnx2x *bp)
 		      BNX2X_STATE_OPENING_WAIT4_PORT):
 		case (EVENT_RING_OPCODE_RSS_UPDATE_RULES |
 		      BNX2X_STATE_CLOSING_WAIT4_HALT):
-			cid = elem->message.data.eth_event.echo &
-				BNX2X_SWCID_MASK;
 			DP(BNX2X_MSG_SP, "got RSS_UPDATE ramrod. CID %d\n",
-			   cid);
+			   SW_CID(elem->message.data.eth_event.echo));
 			rss_raw->clear_pending(rss_raw);
 			break;
 
@@ -5686,7 +5684,7 @@ static void bnx2x_sp_task(struct work_struct *work)
 		if (status & BNX2X_DEF_SB_IDX) {
 			struct bnx2x_fastpath *fp = bnx2x_fcoe_fp(bp);
 
-		if (FCOE_INIT(bp) &&
+			if (FCOE_INIT(bp) &&
 			    (bnx2x_has_rx_work(fp) || bnx2x_has_tx_work(fp))) {
 				/* Prevent local bottom-halves from running as
 				 * we are going to change the local NAPI list.
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 9d027348cd09..632daff117d3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -1672,11 +1672,12 @@ void bnx2x_vf_handle_classification_eqe(struct bnx2x *bp,
 {
 	unsigned long ramrod_flags = 0;
 	int rc = 0;
+	u32 echo = le32_to_cpu(elem->message.data.eth_event.echo);
 
 	/* Always push next commands out, don't wait here */
 	set_bit(RAMROD_CONT, &ramrod_flags);
 
-	switch (elem->message.data.eth_event.echo >> BNX2X_SWCID_SHIFT) {
+	switch (echo >> BNX2X_SWCID_SHIFT) {
 	case BNX2X_FILTER_MAC_PENDING:
 		rc = vfq->mac_obj.complete(bp, &vfq->mac_obj, elem,
 					   &ramrod_flags);
@@ -1686,8 +1687,7 @@ void bnx2x_vf_handle_classification_eqe(struct bnx2x *bp,
 					    &ramrod_flags);
 		break;
 	default:
-		BNX2X_ERR("Unsupported classification command: %d\n",
-			  elem->message.data.eth_event.echo);
+		BNX2X_ERR("Unsupported classification command: 0x%x\n", echo);
 		return;
 	}
 	if (rc < 0)
@@ -1747,16 +1747,14 @@ int bnx2x_iov_eq_sp_event(struct bnx2x *bp, union event_ring_elem *elem)
 
 	switch (opcode) {
 	case EVENT_RING_OPCODE_CFC_DEL:
-		cid = SW_CID((__force __le32)
-			     elem->message.data.cfc_del_event.cid);
+		cid = SW_CID(elem->message.data.cfc_del_event.cid);
 		DP(BNX2X_MSG_IOV, "checking cfc-del comp cid=%d\n", cid);
 		break;
 	case EVENT_RING_OPCODE_CLASSIFICATION_RULES:
 	case EVENT_RING_OPCODE_MULTICAST_RULES:
 	case EVENT_RING_OPCODE_FILTERS_RULES:
 	case EVENT_RING_OPCODE_RSS_UPDATE_RULES:
-		cid = (elem->message.data.eth_event.echo &
-		       BNX2X_SWCID_MASK);
+		cid = SW_CID(elem->message.data.eth_event.echo);
 		DP(BNX2X_MSG_IOV, "checking filtering comp cid=%d\n", cid);
 		break;
 	case EVENT_RING_OPCODE_VF_FLR:
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 1374e5394a79..bfae300cf25f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -2187,8 +2187,10 @@ void bnx2x_vf_mbx_schedule(struct bnx2x *bp,
 
 	/* Update VFDB with current message and schedule its handling */
 	mutex_lock(&BP_VFDB(bp)->event_mutex);
-	BP_VF_MBX(bp, vf_idx)->vf_addr_hi = vfpf_event->msg_addr_hi;
-	BP_VF_MBX(bp, vf_idx)->vf_addr_lo = vfpf_event->msg_addr_lo;
+	BP_VF_MBX(bp, vf_idx)->vf_addr_hi =
+		le32_to_cpu(vfpf_event->msg_addr_hi);
+	BP_VF_MBX(bp, vf_idx)->vf_addr_lo =
+		le32_to_cpu(vfpf_event->msg_addr_lo);
 	BP_VFDB(bp)->event_occur |= (1ULL << vf_idx);
 	mutex_unlock(&BP_VFDB(bp)->event_mutex);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index ce6b075842ee..4dfc25f042e8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -248,7 +248,8 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		tx_push1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags);
 		tx_push1->tx_bd_cfa_action = cpu_to_le32(cfa_action);
 
-		end = PTR_ALIGN(pdata + length + 1, 8) - 1;
+		end = pdata + length;
+		end = PTR_ALIGN(end, 8) - 1;
 		*end = 0;
 
 		skb_copy_from_linear_data(skb, pdata, len);
diff --git a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
index 04b0d16b210e..95bc470ae441 100644
--- a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
+++ b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
@@ -987,7 +987,7 @@ bna_rxf_ucast_cfg_apply(struct bna_rxf *rxf)
 	if (!list_empty(&rxf->ucast_pending_add_q)) {
 		mac = list_first_entry(&rxf->ucast_pending_add_q,
 				       struct bna_mac, qe);
-		list_add_tail(&mac->qe, &rxf->ucast_active_q);
+		list_move_tail(&mac->qe, &rxf->ucast_active_q);
 		bna_bfi_ucast_req(rxf, mac, BFI_ENET_H2I_MAC_UCAST_ADD_REQ);
 		return 1;
 	}
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index 00cc9156abbb..092f097a5943 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -116,6 +116,15 @@
 #define NIC_PF_INTR_ID_MBOX0		8
 #define NIC_PF_INTR_ID_MBOX1		9
 
+/* Minimum FIFO level before all packets for the CQ are dropped
+ *
+ * This value ensures that once a packet has been "accepted"
+ * for reception it will not get dropped due to non-availability
+ * of CQ descriptor. An errata in HW mandates this value to be
+ * atleast 0x100.
+ */
+#define NICPF_CQM_MIN_DROP_LEVEL       0x100
+
 /* Global timer for CQ timer thresh interrupts
  * Calculated for SCLK of 700Mhz
  * value written should be a 1/16th of what is expected
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 4dded90076c8..95f17f8cadac 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -304,6 +304,7 @@ static void nic_set_lmac_vf_mapping(struct nicpf *nic)
 static void nic_init_hw(struct nicpf *nic)
 {
 	int i;
+	u64 cqm_cfg;
 
 	/* Enable NIC HW block */
 	nic_reg_write(nic, NIC_PF_CFG, 0x3);
@@ -340,6 +341,11 @@ static void nic_init_hw(struct nicpf *nic)
 	/* Enable VLAN ethertype matching and stripping */
 	nic_reg_write(nic, NIC_PF_RX_ETYPE_0_7,
 		      (2 << 19) | (ETYPE_ALG_VLAN_STRIP << 16) | ETH_P_8021Q);
+
+	/* Check if HW expected value is higher (could be in future chips) */
+	cqm_cfg = nic_reg_read(nic, NIC_PF_CQM_CFG);
+	if (cqm_cfg < NICPF_CQM_MIN_DROP_LEVEL)
+		nic_reg_write(nic, NIC_PF_CQM_CFG, NICPF_CQM_MIN_DROP_LEVEL);
 }
 
 /* Channel parse index configuration */
diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h
index dd536be20193..afb10e326b4f 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_reg.h
+++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h
@@ -21,7 +21,7 @@
 #define   NIC_PF_TCP_TIMER			(0x0060)
 #define   NIC_PF_BP_CFG				(0x0080)
 #define   NIC_PF_RRM_CFG			(0x0088)
-#define   NIC_PF_CQM_CF				(0x00A0)
+#define   NIC_PF_CQM_CFG			(0x00A0)
 #define   NIC_PF_CNM_CF				(0x00A8)
 #define   NIC_PF_CNM_STATUS			(0x00B0)
 #define   NIC_PF_CQ_AVG_CFG			(0x00C0)
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index ee584c59ff62..fe3763df3f13 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -545,6 +545,7 @@ struct be_adapter {
 	struct delayed_work be_err_detection_work;
 	u8 recovery_retries;
 	u8 err_flags;
+	bool pcicfg_mapped;	/* pcicfg obtained via pci_iomap() */
 	u32 flags;
 	u32 cmd_privileges;
 	/* Ethtool knobs and info */
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index 0b9f741f31af..d8540ae95e5a 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -666,10 +666,13 @@ enum be_if_flags {
 					 BE_IF_FLAGS_VLAN_PROMISCUOUS |\
 					 BE_IF_FLAGS_MCAST_PROMISCUOUS)
 
-#define BE_IF_EN_FLAGS	(BE_IF_FLAGS_BROADCAST | BE_IF_FLAGS_PASS_L3L4_ERRORS |\
-			BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_UNTAGGED)
+#define BE_IF_FILT_FLAGS_BASIC (BE_IF_FLAGS_BROADCAST | \
+				BE_IF_FLAGS_PASS_L3L4_ERRORS | \
+				BE_IF_FLAGS_UNTAGGED)
 
-#define BE_IF_ALL_FILT_FLAGS	(BE_IF_EN_FLAGS | BE_IF_FLAGS_ALL_PROMISCUOUS)
+#define BE_IF_ALL_FILT_FLAGS	(BE_IF_FILT_FLAGS_BASIC | \
+				 BE_IF_FLAGS_MULTICAST | \
+				 BE_IF_FLAGS_ALL_PROMISCUOUS)
 
 /* An RX interface is an object with one or more MAC addresses and
  * filtering capabilities. */
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 17422b20a8ec..536686476369 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -125,6 +125,11 @@ static const char * const ue_status_hi_desc[] = {
 	"Unknown"
 };
 
+#define BE_VF_IF_EN_FLAGS	(BE_IF_FLAGS_UNTAGGED | \
+				 BE_IF_FLAGS_BROADCAST | \
+				 BE_IF_FLAGS_MULTICAST | \
+				 BE_IF_FLAGS_PASS_L3L4_ERRORS)
+
 static void be_queue_free(struct be_adapter *adapter, struct be_queue_info *q)
 {
 	struct be_dma_mem *mem = &q->dma_mem;
@@ -3558,7 +3563,7 @@ static int be_enable_if_filters(struct be_adapter *adapter)
 {
 	int status;
 
-	status = be_cmd_rx_filter(adapter, BE_IF_EN_FLAGS, ON);
+	status = be_cmd_rx_filter(adapter, BE_IF_FILT_FLAGS_BASIC, ON);
 	if (status)
 		return status;
 
@@ -3875,8 +3880,7 @@ static int be_vfs_if_create(struct be_adapter *adapter)
 	int status;
 
 	/* If a FW profile exists, then cap_flags are updated */
-	cap_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
-		    BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS;
+	cap_flags = BE_VF_IF_EN_FLAGS;
 
 	for_all_vfs(adapter, vf_cfg, vf) {
 		if (!BE3_chip(adapter)) {
@@ -3892,10 +3896,8 @@ static int be_vfs_if_create(struct be_adapter *adapter)
 			}
 		}
 
-		en_flags = cap_flags & (BE_IF_FLAGS_UNTAGGED |
-					BE_IF_FLAGS_BROADCAST |
-					BE_IF_FLAGS_MULTICAST |
-					BE_IF_FLAGS_PASS_L3L4_ERRORS);
+		/* PF should enable IF flags during proxy if_create call */
+		en_flags = cap_flags & BE_VF_IF_EN_FLAGS;
 		status = be_cmd_if_create(adapter, cap_flags, en_flags,
 					  &vf_cfg->if_handle, vf + 1);
 		if (status)
@@ -5040,6 +5042,8 @@ static void be_unmap_pci_bars(struct be_adapter *adapter)
 		pci_iounmap(adapter->pdev, adapter->csr);
 	if (adapter->db)
 		pci_iounmap(adapter->pdev, adapter->db);
+	if (adapter->pcicfg && adapter->pcicfg_mapped)
+		pci_iounmap(adapter->pdev, adapter->pcicfg);
 }
 
 static int db_bar(struct be_adapter *adapter)
@@ -5091,8 +5095,10 @@ static int be_map_pci_bars(struct be_adapter *adapter)
 			if (!addr)
 				goto pci_map_err;
 			adapter->pcicfg = addr;
+			adapter->pcicfg_mapped = true;
 		} else {
 			adapter->pcicfg = adapter->db + SRIOV_VF_PCICFG_OFFSET;
+			adapter->pcicfg_mapped = false;
 		}
 	}
 
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 62fa136554ac..41b010645100 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -1265,7 +1265,6 @@ static int ethoc_remove(struct platform_device *pdev)
 
 		if (priv->mdio) {
 			mdiobus_unregister(priv->mdio);
-			kfree(priv->mdio->irq);
 			mdiobus_free(priv->mdio);
 		}
 		if (priv->clk)
diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c
index 623aa1c8ebc6..79a210aaf0bb 100644
--- a/drivers/net/ethernet/freescale/fman/fman.c
+++ b/drivers/net/ethernet/freescale/fman/fman.c
@@ -2791,6 +2791,8 @@ static struct fman *read_dts_node(struct platform_device *of_dev)
 		goto fman_free;
 	}
 
+	fman->dev = &of_dev->dev;
+
 	return fman;
 
 fman_node_put:
@@ -2845,8 +2847,6 @@ static int fman_probe(struct platform_device *of_dev)
 
 	dev_set_drvdata(dev, fman);
 
-	fman->dev = dev;
-
 	dev_dbg(dev, "FMan%d probed\n", fman->dts_params.id);
 
 	return 0;
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index a01e5a32b631..08c041548300 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -1111,8 +1111,10 @@ static void __gfar_detect_errata_85xx(struct gfar_private *priv)
 
 	if ((SVR_SOC_VER(svr) == SVR_8548) && (SVR_REV(svr) == 0x20))
 		priv->errata |= GFAR_ERRATA_12;
+	/* P2020/P1010 Rev 1; MPC8548 Rev 2 */
 	if (((SVR_SOC_VER(svr) == SVR_P2020) && (SVR_REV(svr) < 0x20)) ||
-	    ((SVR_SOC_VER(svr) == SVR_P2010) && (SVR_REV(svr) < 0x20)))
+	    ((SVR_SOC_VER(svr) == SVR_P2010) && (SVR_REV(svr) < 0x20)) ||
+	    ((SVR_SOC_VER(svr) == SVR_8548) && (SVR_REV(svr) < 0x31)))
 		priv->errata |= GFAR_ERRATA_76; /* aka eTSEC 20 */
 }
 #endif
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index 74beb1867230..4ccc032633c4 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -25,6 +25,7 @@ config HIX5HD2_GMAC
 
 config HIP04_ETH
 	tristate "HISILICON P04 Ethernet support"
+	depends on HAS_IOMEM	# For MFD_SYSCON
 	select MARVELL_PHY
 	select MFD_SYSCON
 	select HNS_MDIO
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
index a0070d0e740d..d4f92ed322d6 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
@@ -675,8 +675,12 @@ static int hns_ae_config_loopback(struct hnae_handle *handle,
 {
 	int ret;
 	struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle);
+	struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle);
 
 	switch (loop) {
+	case MAC_INTERNALLOOP_PHY:
+		ret = 0;
+		break;
 	case MAC_INTERNALLOOP_SERDES:
 		ret = hns_mac_config_sds_loopback(vf_cb->mac_cb, en);
 		break;
@@ -686,6 +690,10 @@ static int hns_ae_config_loopback(struct hnae_handle *handle,
 	default:
 		ret = -EINVAL;
 	}
+
+	if (!ret)
+		hns_dsaf_set_inner_lb(mac_cb->dsaf_dev, mac_cb->mac_id, en);
+
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 9439f04962e1..38fc5be3870c 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -230,6 +230,30 @@ static void hns_dsaf_mix_def_qid_cfg(struct dsaf_device *dsaf_dev)
 	}
 }
 
+static void hns_dsaf_inner_qid_cfg(struct dsaf_device *dsaf_dev)
+{
+	u16 max_q_per_vf, max_vfn;
+	u32 q_id, q_num_per_port;
+	u32 mac_id;
+
+	if (AE_IS_VER1(dsaf_dev->dsaf_ver))
+		return;
+
+	hns_rcb_get_queue_mode(dsaf_dev->dsaf_mode,
+			       HNS_DSAF_COMM_SERVICE_NW_IDX,
+			       &max_vfn, &max_q_per_vf);
+	q_num_per_port = max_vfn * max_q_per_vf;
+
+	for (mac_id = 0, q_id = 0; mac_id < DSAF_SERVICE_NW_NUM; mac_id++) {
+		dsaf_set_dev_field(dsaf_dev,
+				   DSAFV2_SERDES_LBK_0_REG + 4 * mac_id,
+				   DSAFV2_SERDES_LBK_QID_M,
+				   DSAFV2_SERDES_LBK_QID_S,
+				   q_id);
+		q_id += q_num_per_port;
+	}
+}
+
 /**
  * hns_dsaf_sw_port_type_cfg - cfg sw type
  * @dsaf_id: dsa fabric id
@@ -691,6 +715,16 @@ void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en)
 	dsaf_set_dev_bit(dsaf_dev, DSAF_CFG_0_REG, DSAF_CFG_MIX_MODE_S, !!en);
 }
 
+void hns_dsaf_set_inner_lb(struct dsaf_device *dsaf_dev, u32 mac_id, u32 en)
+{
+	if (AE_IS_VER1(dsaf_dev->dsaf_ver) ||
+	    dsaf_dev->mac_cb[mac_id].mac_type == HNAE_PORT_DEBUG)
+		return;
+
+	dsaf_set_dev_bit(dsaf_dev, DSAFV2_SERDES_LBK_0_REG + 4 * mac_id,
+			 DSAFV2_SERDES_LBK_EN_B, !!en);
+}
+
 /**
  * hns_dsaf_tbl_stat_en - tbl
  * @dsaf_id: dsa fabric id
@@ -1022,6 +1056,9 @@ static void hns_dsaf_comm_init(struct dsaf_device *dsaf_dev)
 	/* set promisc def queue id */
 	hns_dsaf_mix_def_qid_cfg(dsaf_dev);
 
+	/* set inner loopback queue id */
+	hns_dsaf_inner_qid_cfg(dsaf_dev);
+
 	/* in non switch mode, set all port to access mode */
 	hns_dsaf_sw_port_type_cfg(dsaf_dev, DSAF_SW_PORT_TYPE_NON_VLAN);
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
index 40205b910f80..5fea226efaf3 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
@@ -417,5 +417,6 @@ void hns_dsaf_get_strings(int stringset, u8 *data, int port);
 void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data);
 int hns_dsaf_get_regs_count(void);
 void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en);
+void hns_dsaf_set_inner_lb(struct dsaf_device *dsaf_dev, u32 mac_id, u32 en);
 
 #endif /* __HNS_DSAF_MAIN_H__ */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index f0c4f9b09d5b..60d695daa471 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -134,6 +134,7 @@
 #define DSAF_XGE_INT_STS_0_REG		0x1C0
 #define DSAF_PPE_INT_STS_0_REG		0x1E0
 #define DSAF_ROCEE_INT_STS_0_REG	0x200
+#define DSAFV2_SERDES_LBK_0_REG         0x220
 #define DSAF_PPE_QID_CFG_0_REG		0x300
 #define DSAF_SW_PORT_TYPE_0_REG		0x320
 #define DSAF_STP_PORT_TYPE_0_REG	0x340
@@ -857,6 +858,10 @@
 #define PPEV2_CFG_RSS_TBL_4N3_S	24
 #define PPEV2_CFG_RSS_TBL_4N3_M	(((1UL << 5) - 1) << PPEV2_CFG_RSS_TBL_4N3_S)
 
+#define DSAFV2_SERDES_LBK_EN_B  8
+#define DSAFV2_SERDES_LBK_QID_S 0
+#define DSAFV2_SERDES_LBK_QID_M	(((1UL << 8) - 1) << DSAFV2_SERDES_LBK_QID_S)
+
 #define PPE_CNT_CLR_CE_B	0
 #define PPE_CNT_CLR_SNAP_EN_B	1
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 3df22840fcd1..3c4a3bc31a89 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -295,8 +295,10 @@ static int __lb_setup(struct net_device *ndev,
 
 	switch (loop) {
 	case MAC_INTERNALLOOP_PHY:
-		if ((phy_dev) && (!phy_dev->is_c45))
+		if ((phy_dev) && (!phy_dev->is_c45)) {
 			ret = hns_nic_config_phy_loopback(phy_dev, 0x1);
+			ret |= h->dev->ops->set_loopback(h, loop, 0x1);
+		}
 		break;
 	case MAC_INTERNALLOOP_MAC:
 		if ((h->dev->ops->set_loopback) &&
@@ -376,6 +378,7 @@ static void __lb_other_process(struct hns_nic_ring_data *ring_data,
 			       struct sk_buff *skb)
 {
 	struct net_device *ndev;
+	struct hns_nic_priv *priv;
 	struct hnae_ring *ring;
 	struct netdev_queue *dev_queue;
 	struct sk_buff *new_skb;
@@ -385,8 +388,17 @@ static void __lb_other_process(struct hns_nic_ring_data *ring_data,
 	char buff[33]; /* 32B data and the last character '\0' */
 
 	if (!ring_data) { /* Just for doing create frame*/
+		ndev = skb->dev;
+		priv = netdev_priv(ndev);
+
 		frame_size = skb->len;
 		memset(skb->data, 0xFF, frame_size);
+		if ((!AE_IS_VER1(priv->enet_ver)) &&
+		    (priv->ae_handle->port_type == HNAE_PORT_SERVICE)) {
+			memcpy(skb->data, ndev->dev_addr, 6);
+			skb->data[5] += 0x1f;
+		}
+
 		frame_size &= ~1ul;
 		memset(&skb->data[frame_size / 2], 0xAA, frame_size / 2 - 1);
 		memset(&skb->data[frame_size / 2 + 10], 0xBE,
@@ -486,6 +498,7 @@ static int __lb_run_test(struct net_device *ndev,
 
 	/* place data into test skb */
 	(void)skb_put(skb, size);
+	skb->dev = ndev;
 	__lb_other_process(NULL, skb);
 	skb->queue_mapping = NIC_LB_TEST_RING_ID;
 
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 335417b4756b..ebe60719e489 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1166,7 +1166,10 @@ map_failed:
 	if (!firmware_has_feature(FW_FEATURE_CMO))
 		netdev_err(netdev, "tx: unable to map xmit buffer\n");
 	adapter->tx_map_failed++;
-	skb_linearize(skb);
+	if (skb_linearize(skb)) {
+		netdev->stats.tx_dropped++;
+		goto out;
+	}
 	force_bounce = 1;
 	goto retry_bounce;
 }
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 7d6570843723..6e9e16eee5d0 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1348,44 +1348,44 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
 	crq.request_capability.cmd = REQUEST_CAPABILITY;
 
 	crq.request_capability.capability = cpu_to_be16(REQ_TX_QUEUES);
-	crq.request_capability.number = cpu_to_be32(adapter->req_tx_queues);
+	crq.request_capability.number = cpu_to_be64(adapter->req_tx_queues);
 	ibmvnic_send_crq(adapter, &crq);
 
 	crq.request_capability.capability = cpu_to_be16(REQ_RX_QUEUES);
-	crq.request_capability.number = cpu_to_be32(adapter->req_rx_queues);
+	crq.request_capability.number = cpu_to_be64(adapter->req_rx_queues);
 	ibmvnic_send_crq(adapter, &crq);
 
 	crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_QUEUES);
-	crq.request_capability.number = cpu_to_be32(adapter->req_rx_add_queues);
+	crq.request_capability.number = cpu_to_be64(adapter->req_rx_add_queues);
 	ibmvnic_send_crq(adapter, &crq);
 
 	crq.request_capability.capability =
 	    cpu_to_be16(REQ_TX_ENTRIES_PER_SUBCRQ);
 	crq.request_capability.number =
-	    cpu_to_be32(adapter->req_tx_entries_per_subcrq);
+	    cpu_to_be64(adapter->req_tx_entries_per_subcrq);
 	ibmvnic_send_crq(adapter, &crq);
 
 	crq.request_capability.capability =
 	    cpu_to_be16(REQ_RX_ADD_ENTRIES_PER_SUBCRQ);
 	crq.request_capability.number =
-	    cpu_to_be32(adapter->req_rx_add_entries_per_subcrq);
+	    cpu_to_be64(adapter->req_rx_add_entries_per_subcrq);
 	ibmvnic_send_crq(adapter, &crq);
 
 	crq.request_capability.capability = cpu_to_be16(REQ_MTU);
-	crq.request_capability.number = cpu_to_be32(adapter->req_mtu);
+	crq.request_capability.number = cpu_to_be64(adapter->req_mtu);
 	ibmvnic_send_crq(adapter, &crq);
 
 	if (adapter->netdev->flags & IFF_PROMISC) {
 		if (adapter->promisc_supported) {
 			crq.request_capability.capability =
 			    cpu_to_be16(PROMISC_REQUESTED);
-			crq.request_capability.number = cpu_to_be32(1);
+			crq.request_capability.number = cpu_to_be64(1);
 			ibmvnic_send_crq(adapter, &crq);
 		}
 	} else {
 		crq.request_capability.capability =
 		    cpu_to_be16(PROMISC_REQUESTED);
-		crq.request_capability.number = cpu_to_be32(0);
+		crq.request_capability.number = cpu_to_be64(0);
 		ibmvnic_send_crq(adapter, &crq);
 	}
 
@@ -2312,93 +2312,93 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq,
 	switch (be16_to_cpu(crq->query_capability.capability)) {
 	case MIN_TX_QUEUES:
 		adapter->min_tx_queues =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "min_tx_queues = %lld\n",
 			   adapter->min_tx_queues);
 		break;
 	case MIN_RX_QUEUES:
 		adapter->min_rx_queues =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "min_rx_queues = %lld\n",
 			   adapter->min_rx_queues);
 		break;
 	case MIN_RX_ADD_QUEUES:
 		adapter->min_rx_add_queues =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "min_rx_add_queues = %lld\n",
 			   adapter->min_rx_add_queues);
 		break;
 	case MAX_TX_QUEUES:
 		adapter->max_tx_queues =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "max_tx_queues = %lld\n",
 			   adapter->max_tx_queues);
 		break;
 	case MAX_RX_QUEUES:
 		adapter->max_rx_queues =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "max_rx_queues = %lld\n",
 			   adapter->max_rx_queues);
 		break;
 	case MAX_RX_ADD_QUEUES:
 		adapter->max_rx_add_queues =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "max_rx_add_queues = %lld\n",
 			   adapter->max_rx_add_queues);
 		break;
 	case MIN_TX_ENTRIES_PER_SUBCRQ:
 		adapter->min_tx_entries_per_subcrq =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "min_tx_entries_per_subcrq = %lld\n",
 			   adapter->min_tx_entries_per_subcrq);
 		break;
 	case MIN_RX_ADD_ENTRIES_PER_SUBCRQ:
 		adapter->min_rx_add_entries_per_subcrq =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "min_rx_add_entrs_per_subcrq = %lld\n",
 			   adapter->min_rx_add_entries_per_subcrq);
 		break;
 	case MAX_TX_ENTRIES_PER_SUBCRQ:
 		adapter->max_tx_entries_per_subcrq =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "max_tx_entries_per_subcrq = %lld\n",
 			   adapter->max_tx_entries_per_subcrq);
 		break;
 	case MAX_RX_ADD_ENTRIES_PER_SUBCRQ:
 		adapter->max_rx_add_entries_per_subcrq =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "max_rx_add_entrs_per_subcrq = %lld\n",
 			   adapter->max_rx_add_entries_per_subcrq);
 		break;
 	case TCP_IP_OFFLOAD:
 		adapter->tcp_ip_offload =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "tcp_ip_offload = %lld\n",
 			   adapter->tcp_ip_offload);
 		break;
 	case PROMISC_SUPPORTED:
 		adapter->promisc_supported =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "promisc_supported = %lld\n",
 			   adapter->promisc_supported);
 		break;
 	case MIN_MTU:
-		adapter->min_mtu = be32_to_cpu(crq->query_capability.number);
+		adapter->min_mtu = be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "min_mtu = %lld\n", adapter->min_mtu);
 		break;
 	case MAX_MTU:
-		adapter->max_mtu = be32_to_cpu(crq->query_capability.number);
+		adapter->max_mtu = be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "max_mtu = %lld\n", adapter->max_mtu);
 		break;
 	case MAX_MULTICAST_FILTERS:
 		adapter->max_multicast_filters =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "max_multicast_filters = %lld\n",
 			   adapter->max_multicast_filters);
 		break;
 	case VLAN_HEADER_INSERTION:
 		adapter->vlan_header_insertion =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		if (adapter->vlan_header_insertion)
 			netdev->features |= NETIF_F_HW_VLAN_STAG_TX;
 		netdev_dbg(netdev, "vlan_header_insertion = %lld\n",
@@ -2406,43 +2406,43 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq,
 		break;
 	case MAX_TX_SG_ENTRIES:
 		adapter->max_tx_sg_entries =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "max_tx_sg_entries = %lld\n",
 			   adapter->max_tx_sg_entries);
 		break;
 	case RX_SG_SUPPORTED:
 		adapter->rx_sg_supported =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "rx_sg_supported = %lld\n",
 			   adapter->rx_sg_supported);
 		break;
 	case OPT_TX_COMP_SUB_QUEUES:
 		adapter->opt_tx_comp_sub_queues =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "opt_tx_comp_sub_queues = %lld\n",
 			   adapter->opt_tx_comp_sub_queues);
 		break;
 	case OPT_RX_COMP_QUEUES:
 		adapter->opt_rx_comp_queues =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "opt_rx_comp_queues = %lld\n",
 			   adapter->opt_rx_comp_queues);
 		break;
 	case OPT_RX_BUFADD_Q_PER_RX_COMP_Q:
 		adapter->opt_rx_bufadd_q_per_rx_comp_q =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "opt_rx_bufadd_q_per_rx_comp_q = %lld\n",
 			   adapter->opt_rx_bufadd_q_per_rx_comp_q);
 		break;
 	case OPT_TX_ENTRIES_PER_SUBCRQ:
 		adapter->opt_tx_entries_per_subcrq =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "opt_tx_entries_per_subcrq = %lld\n",
 			   adapter->opt_tx_entries_per_subcrq);
 		break;
 	case OPT_RXBA_ENTRIES_PER_SUBCRQ:
 		adapter->opt_rxba_entries_per_subcrq =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "opt_rxba_entries_per_subcrq = %lld\n",
 			   adapter->opt_rxba_entries_per_subcrq);
 		break;
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 1242925ad34c..1a9993cc79b5 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -319,10 +319,8 @@ struct ibmvnic_capability {
 	u8 first;
 	u8 cmd;
 	__be16 capability; /* one of ibmvnic_capabilities */
+	__be64 number;
 	struct ibmvnic_rc rc;
-	__be32 number; /*FIX: should be __be64, but I'm getting the least
-			* significant word first
-			*/
 } __packed __aligned(8);
 
 struct ibmvnic_login {
diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index b1de7afd4116..3ddf657bc10b 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -270,11 +270,17 @@ jme_reset_mac_processor(struct jme_adapter *jme)
 }
 
 static inline void
-jme_clear_pm(struct jme_adapter *jme)
+jme_clear_pm_enable_wol(struct jme_adapter *jme)
 {
 	jwrite32(jme, JME_PMCS, PMCS_STMASK | jme->reg_pmcs);
 }
 
+static inline void
+jme_clear_pm_disable_wol(struct jme_adapter *jme)
+{
+	jwrite32(jme, JME_PMCS, PMCS_STMASK);
+}
+
 static int
 jme_reload_eeprom(struct jme_adapter *jme)
 {
@@ -1853,7 +1859,7 @@ jme_open(struct net_device *netdev)
 	struct jme_adapter *jme = netdev_priv(netdev);
 	int rc;
 
-	jme_clear_pm(jme);
+	jme_clear_pm_disable_wol(jme);
 	JME_NAPI_ENABLE(jme);
 
 	tasklet_init(&jme->linkch_task, jme_link_change_tasklet,
@@ -1925,11 +1931,11 @@ jme_wait_link(struct jme_adapter *jme)
 static void
 jme_powersave_phy(struct jme_adapter *jme)
 {
-	if (jme->reg_pmcs) {
+	if (jme->reg_pmcs && device_may_wakeup(&jme->pdev->dev)) {
 		jme_set_100m_half(jme);
 		if (jme->reg_pmcs & (PMCS_LFEN | PMCS_LREN))
 			jme_wait_link(jme);
-		jme_clear_pm(jme);
+		jme_clear_pm_enable_wol(jme);
 	} else {
 		jme_phy_off(jme);
 	}
@@ -2646,9 +2652,6 @@ jme_set_wol(struct net_device *netdev,
 	if (wol->wolopts & WAKE_MAGIC)
 		jme->reg_pmcs |= PMCS_MFEN;
 
-	jwrite32(jme, JME_PMCS, jme->reg_pmcs);
-	device_set_wakeup_enable(&jme->pdev->dev, !!(jme->reg_pmcs));
-
 	return 0;
 }
 
@@ -3172,8 +3175,8 @@ jme_init_one(struct pci_dev *pdev,
 	jme->mii_if.mdio_read = jme_mdio_read;
 	jme->mii_if.mdio_write = jme_mdio_write;
 
-	jme_clear_pm(jme);
-	device_set_wakeup_enable(&pdev->dev, true);
+	jme_clear_pm_disable_wol(jme);
+	device_init_wakeup(&pdev->dev, true);
 
 	jme_set_phyfifo_5level(jme);
 	jme->pcirev = pdev->revision;
@@ -3304,7 +3307,7 @@ jme_resume(struct device *dev)
 	if (!netif_running(netdev))
 		return 0;
 
-	jme_clear_pm(jme);
+	jme_clear_pm_disable_wol(jme);
 	jme_phy_on(jme);
 	if (test_bit(JME_FLAG_SSET, &jme->flags))
 		jme_set_settings(netdev, &jme->old_ecmd);
@@ -3312,13 +3315,14 @@ jme_resume(struct device *dev)
 		jme_reset_phy_processor(jme);
 	jme_phy_calibration(jme);
 	jme_phy_setEA(jme);
-	jme_start_irq(jme);
 	netif_device_attach(netdev);
 
 	atomic_inc(&jme->link_changing);
 
 	jme_reset_link(jme);
 
+	jme_start_irq(jme);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 16b26d17c54c..b4b258c8ca47 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2258,7 +2258,7 @@ static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac)
 	struct mlx4_en_dev *mdev = en_priv->mdev;
 	u64 mac_u64 = mlx4_mac_to_u64(mac);
 
-	if (!is_valid_ether_addr(mac))
+	if (is_multicast_ether_addr(mac))
 		return -EINVAL;
 
 	return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac_u64);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index b8a51515e73c..503ec23e84cc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1272,6 +1272,7 @@ err_set_port:
 static int mlx4_mf_bond(struct mlx4_dev *dev)
 {
 	int err = 0;
+	int nvfs;
 	struct mlx4_slaves_pport slaves_port1;
 	struct mlx4_slaves_pport slaves_port2;
 	DECLARE_BITMAP(slaves_port_1_2, MLX4_MFUNC_MAX);
@@ -1288,11 +1289,18 @@ static int mlx4_mf_bond(struct mlx4_dev *dev)
 		return -EINVAL;
 	}
 
+	/* number of virtual functions is number of total functions minus one
+	 * physical function for each port.
+	 */
+	nvfs = bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) +
+		bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1) - 2;
+
 	/* limit on maximum allowed VFs */
-	if ((bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) +
-	    bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1)) >
-	    MAX_MF_BOND_ALLOWED_SLAVES)
+	if (nvfs > MAX_MF_BOND_ALLOWED_SLAVES) {
+		mlx4_warn(dev, "HA mode is not supported for %d VFs (max %d are allowed)\n",
+			  nvfs, MAX_MF_BOND_ALLOWED_SLAVES);
 		return -EINVAL;
+	}
 
 	if (dev->caps.steering_mode != MLX4_STEERING_MODE_DEVICE_MANAGED) {
 		mlx4_warn(dev, "HA mode unsupported for NON DMFS steering\n");
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 787b7bb54d52..211c65087997 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -193,10 +193,10 @@ int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac)
 	if (need_mf_bond) {
 		if (port == 1) {
 			mutex_lock(&table->mutex);
-			mutex_lock(&dup_table->mutex);
+			mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING);
 		} else {
 			mutex_lock(&dup_table->mutex);
-			mutex_lock(&table->mutex);
+			mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING);
 		}
 	} else {
 		mutex_lock(&table->mutex);
@@ -389,10 +389,10 @@ void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac)
 	if (dup) {
 		if (port == 1) {
 			mutex_lock(&table->mutex);
-			mutex_lock(&dup_table->mutex);
+			mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING);
 		} else {
 			mutex_lock(&dup_table->mutex);
-			mutex_lock(&table->mutex);
+			mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING);
 		}
 	} else {
 		mutex_lock(&table->mutex);
@@ -479,10 +479,10 @@ int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac)
 	if (dup) {
 		if (port == 1) {
 			mutex_lock(&table->mutex);
-			mutex_lock(&dup_table->mutex);
+			mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING);
 		} else {
 			mutex_lock(&dup_table->mutex);
-			mutex_lock(&table->mutex);
+			mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING);
 		}
 	} else {
 		mutex_lock(&table->mutex);
@@ -588,10 +588,10 @@ int __mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan,
 	if (need_mf_bond) {
 		if (port == 1) {
 			mutex_lock(&table->mutex);
-			mutex_lock(&dup_table->mutex);
+			mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING);
 		} else {
 			mutex_lock(&dup_table->mutex);
-			mutex_lock(&table->mutex);
+			mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING);
 		}
 	} else {
 		mutex_lock(&table->mutex);
@@ -764,10 +764,10 @@ void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan)
 	if (dup) {
 		if (port == 1) {
 			mutex_lock(&table->mutex);
-			mutex_lock(&dup_table->mutex);
+			mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING);
 		} else {
 			mutex_lock(&dup_table->mutex);
-			mutex_lock(&table->mutex);
+			mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING);
 		}
 	} else {
 		mutex_lock(&table->mutex);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 9c0e80e64b43..dbc2fb89e067 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -237,6 +237,7 @@ struct mlx5e_pport_stats {
 
 static const char rq_stats_strings[][ETH_GSTRING_LEN] = {
 	"packets",
+	"bytes",
 	"csum_none",
 	"csum_sw",
 	"lro_packets",
@@ -246,16 +247,18 @@ static const char rq_stats_strings[][ETH_GSTRING_LEN] = {
 
 struct mlx5e_rq_stats {
 	u64 packets;
+	u64 bytes;
 	u64 csum_none;
 	u64 csum_sw;
 	u64 lro_packets;
 	u64 lro_bytes;
 	u64 wqe_err;
-#define NUM_RQ_STATS 6
+#define NUM_RQ_STATS 7
 };
 
 static const char sq_stats_strings[][ETH_GSTRING_LEN] = {
 	"packets",
+	"bytes",
 	"tso_packets",
 	"tso_bytes",
 	"tso_inner_packets",
@@ -271,6 +274,7 @@ static const char sq_stats_strings[][ETH_GSTRING_LEN] = {
 struct mlx5e_sq_stats {
 	/* commonly accessed in data path */
 	u64 packets;
+	u64 bytes;
 	u64 tso_packets;
 	u64 tso_bytes;
 	u64 tso_inner_packets;
@@ -282,7 +286,7 @@ struct mlx5e_sq_stats {
 	u64 stopped;
 	u64 wake;
 	u64 dropped;
-#define NUM_SQ_STATS 11
+#define NUM_SQ_STATS 12
 };
 
 struct mlx5e_stats {
@@ -328,14 +332,9 @@ enum {
 	MLX5E_RQ_STATE_POST_WQES_ENABLE,
 };
 
-enum cq_flags {
-	MLX5E_CQ_HAS_CQES = 1,
-};
-
 struct mlx5e_cq {
 	/* data path - accessed per cqe */
 	struct mlx5_cqwq           wq;
-	unsigned long              flags;
 
 	/* data path - accessed per napi poll */
 	struct napi_struct        *napi;
@@ -476,6 +475,8 @@ enum mlx5e_traffic_types {
 	MLX5E_NUM_TT,
 };
 
+#define IS_HASHING_TT(tt) (tt != MLX5E_TT_ANY)
+
 enum mlx5e_rqt_ix {
 	MLX5E_INDIRECTION_RQT,
 	MLX5E_SINGLE_RQ_RQT,
@@ -646,9 +647,12 @@ void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv);
 void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv);
 
 int mlx5e_redirect_rqt(struct mlx5e_priv *priv, enum mlx5e_rqt_ix rqt_ix);
+void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv);
 
 int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);
+void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len,
+				   int num_channels);
 
 static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq,
 				      struct mlx5e_tx_wqe *wqe, int bf_sz)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index be6543570b2b..2018eebe1531 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -62,10 +62,11 @@ static void mlx5e_timestamp_overflow(struct work_struct *work)
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlx5e_tstamp *tstamp = container_of(dwork, struct mlx5e_tstamp,
 						   overflow_work);
+	unsigned long flags;
 
-	write_lock(&tstamp->lock);
+	write_lock_irqsave(&tstamp->lock, flags);
 	timecounter_read(&tstamp->clock);
-	write_unlock(&tstamp->lock);
+	write_unlock_irqrestore(&tstamp->lock, flags);
 	schedule_delayed_work(&tstamp->overflow_work, tstamp->overflow_period);
 }
 
@@ -136,10 +137,11 @@ static int mlx5e_ptp_settime(struct ptp_clock_info *ptp,
 	struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp,
 						   ptp_info);
 	u64 ns = timespec64_to_ns(ts);
+	unsigned long flags;
 
-	write_lock(&tstamp->lock);
+	write_lock_irqsave(&tstamp->lock, flags);
 	timecounter_init(&tstamp->clock, &tstamp->cycles, ns);
-	write_unlock(&tstamp->lock);
+	write_unlock_irqrestore(&tstamp->lock, flags);
 
 	return 0;
 }
@@ -150,10 +152,11 @@ static int mlx5e_ptp_gettime(struct ptp_clock_info *ptp,
 	struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp,
 						   ptp_info);
 	u64 ns;
+	unsigned long flags;
 
-	write_lock(&tstamp->lock);
+	write_lock_irqsave(&tstamp->lock, flags);
 	ns = timecounter_read(&tstamp->clock);
-	write_unlock(&tstamp->lock);
+	write_unlock_irqrestore(&tstamp->lock, flags);
 
 	*ts = ns_to_timespec64(ns);
 
@@ -164,10 +167,11 @@ static int mlx5e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 {
 	struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp,
 						   ptp_info);
+	unsigned long flags;
 
-	write_lock(&tstamp->lock);
+	write_lock_irqsave(&tstamp->lock, flags);
 	timecounter_adjtime(&tstamp->clock, delta);
-	write_unlock(&tstamp->lock);
+	write_unlock_irqrestore(&tstamp->lock, flags);
 
 	return 0;
 }
@@ -176,6 +180,7 @@ static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
 {
 	u64 adj;
 	u32 diff;
+	unsigned long flags;
 	int neg_adj = 0;
 	struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp,
 						  ptp_info);
@@ -189,11 +194,11 @@ static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
 	adj *= delta;
 	diff = div_u64(adj, 1000000000ULL);
 
-	write_lock(&tstamp->lock);
+	write_lock_irqsave(&tstamp->lock, flags);
 	timecounter_read(&tstamp->clock);
 	tstamp->cycles.mult = neg_adj ? tstamp->nominal_c_mult - diff :
 					tstamp->nominal_c_mult + diff;
-	write_unlock(&tstamp->lock);
+	write_unlock_irqrestore(&tstamp->lock, flags);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 0959656404b3..68834b715f6c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -386,6 +386,8 @@ static int mlx5e_set_channels(struct net_device *dev,
 		mlx5e_close_locked(dev);
 
 	priv->params.num_channels = count;
+	mlx5e_build_default_indir_rqt(priv->params.indirection_rqt,
+				      MLX5E_INDIR_RQT_SIZE, count);
 
 	if (was_opened)
 		err = mlx5e_open_locked(dev);
@@ -716,18 +718,36 @@ static int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	return 0;
 }
 
+static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
+	int i;
+
+	MLX5_SET(modify_tir_in, in, bitmask.hash, 1);
+	mlx5e_build_tir_ctx_hash(tirc, priv);
+
+	for (i = 0; i < MLX5E_NUM_TT; i++)
+		if (IS_HASHING_TT(i))
+			mlx5_core_modify_tir(mdev, priv->tirn[i], in, inlen);
+}
+
 static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 			  const u8 *key, const u8 hfunc)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	bool close_open;
-	int err = 0;
+	int inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
+	void *in;
 
 	if ((hfunc != ETH_RSS_HASH_NO_CHANGE) &&
 	    (hfunc != ETH_RSS_HASH_XOR) &&
 	    (hfunc != ETH_RSS_HASH_TOP))
 		return -EINVAL;
 
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
 	mutex_lock(&priv->state_lock);
 
 	if (indir) {
@@ -736,11 +756,6 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 		mlx5e_redirect_rqt(priv, MLX5E_INDIRECTION_RQT);
 	}
 
-	close_open = (key || (hfunc != ETH_RSS_HASH_NO_CHANGE)) &&
-		     test_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (close_open)
-		mlx5e_close_locked(dev);
-
 	if (key)
 		memcpy(priv->params.toeplitz_hash_key, key,
 		       sizeof(priv->params.toeplitz_hash_key));
@@ -748,12 +763,13 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 	if (hfunc != ETH_RSS_HASH_NO_CHANGE)
 		priv->params.rss_hfunc = hfunc;
 
-	if (close_open)
-		err = mlx5e_open_locked(priv->netdev);
+	mlx5e_modify_tirs_hash(priv, in, inlen);
 
 	mutex_unlock(&priv->state_lock);
 
-	return err;
+	kvfree(in);
+
+	return 0;
 }
 
 static int mlx5e_get_rxnfc(struct net_device *netdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 5063c0e0f8ac..19e5daeaa61d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -143,6 +143,10 @@ void mlx5e_update_stats(struct mlx5e_priv *priv)
 		return;
 
 	/* Collect firts the SW counters and then HW for consistency */
+	s->rx_packets		= 0;
+	s->rx_bytes		= 0;
+	s->tx_packets		= 0;
+	s->tx_bytes		= 0;
 	s->tso_packets		= 0;
 	s->tso_bytes		= 0;
 	s->tso_inner_packets	= 0;
@@ -160,6 +164,8 @@ void mlx5e_update_stats(struct mlx5e_priv *priv)
 	for (i = 0; i < priv->params.num_channels; i++) {
 		rq_stats = &priv->channel[i]->rq.stats;
 
+		s->rx_packets	+= rq_stats->packets;
+		s->rx_bytes	+= rq_stats->bytes;
 		s->lro_packets	+= rq_stats->lro_packets;
 		s->lro_bytes	+= rq_stats->lro_bytes;
 		s->rx_csum_none	+= rq_stats->csum_none;
@@ -169,6 +175,8 @@ void mlx5e_update_stats(struct mlx5e_priv *priv)
 		for (j = 0; j < priv->params.num_tc; j++) {
 			sq_stats = &priv->channel[i]->sq[j].stats;
 
+			s->tx_packets		+= sq_stats->packets;
+			s->tx_bytes		+= sq_stats->bytes;
 			s->tso_packets		+= sq_stats->tso_packets;
 			s->tso_bytes		+= sq_stats->tso_bytes;
 			s->tso_inner_packets	+= sq_stats->tso_inner_packets;
@@ -233,23 +241,6 @@ void mlx5e_update_stats(struct mlx5e_priv *priv)
 	s->tx_broadcast_bytes   =
 		MLX5_GET_CTR(out, transmitted_eth_broadcast.octets);
 
-	s->rx_packets =
-		s->rx_unicast_packets +
-		s->rx_multicast_packets +
-		s->rx_broadcast_packets;
-	s->rx_bytes =
-		s->rx_unicast_bytes +
-		s->rx_multicast_bytes +
-		s->rx_broadcast_bytes;
-	s->tx_packets =
-		s->tx_unicast_packets +
-		s->tx_multicast_packets +
-		s->tx_broadcast_packets;
-	s->tx_bytes =
-		s->tx_unicast_bytes +
-		s->tx_multicast_bytes +
-		s->tx_broadcast_bytes;
-
 	/* Update calculated offload counters */
 	s->tx_csum_offload = s->tx_packets - tx_offload_none - s->tx_csum_inner;
 	s->rx_csum_good    = s->rx_packets - s->rx_csum_none -
@@ -1211,7 +1202,6 @@ static void mlx5e_fill_indir_rqt_rqns(struct mlx5e_priv *priv, void *rqtc)
 			ix = mlx5e_bits_invert(i, MLX5E_LOG_INDIR_RQT_SIZE);
 
 		ix = priv->params.indirection_rqt[ix];
-		ix = ix % priv->params.num_channels;
 		MLX5_SET(rqtc, rqtc, rq_num[i],
 			 test_bit(MLX5E_STATE_OPENED, &priv->state) ?
 			 priv->channel[ix]->rq.rqn :
@@ -1329,7 +1319,22 @@ static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv)
 			      lro_timer_supported_periods[2]));
 }
 
-static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt)
+void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv)
+{
+	MLX5_SET(tirc, tirc, rx_hash_fn,
+		 mlx5e_rx_hash_fn(priv->params.rss_hfunc));
+	if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) {
+		void *rss_key = MLX5_ADDR_OF(tirc, tirc,
+					     rx_hash_toeplitz_key);
+		size_t len = MLX5_FLD_SZ_BYTES(tirc,
+					       rx_hash_toeplitz_key);
+
+		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
+		memcpy(rss_key, priv->params.toeplitz_hash_key, len);
+	}
+}
+
+static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 
@@ -1337,6 +1342,7 @@ static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt)
 	void *tirc;
 	int inlen;
 	int err;
+	int tt;
 
 	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
 	in = mlx5_vzalloc(inlen);
@@ -1348,7 +1354,11 @@ static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt)
 
 	mlx5e_build_tir_ctx_lro(tirc, priv);
 
-	err = mlx5_core_modify_tir(mdev, priv->tirn[tt], in, inlen);
+	for (tt = 0; tt < MLX5E_NUM_TT; tt++) {
+		err = mlx5_core_modify_tir(mdev, priv->tirn[tt], in, inlen);
+		if (err)
+			break;
+	}
 
 	kvfree(in);
 
@@ -1703,17 +1713,7 @@ static void mlx5e_build_tir_ctx(struct mlx5e_priv *priv, u32 *tirc, int tt)
 	default:
 		MLX5_SET(tirc, tirc, indirect_table,
 			 priv->rqtn[MLX5E_INDIRECTION_RQT]);
-		MLX5_SET(tirc, tirc, rx_hash_fn,
-			 mlx5e_rx_hash_fn(priv->params.rss_hfunc));
-		if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) {
-			void *rss_key = MLX5_ADDR_OF(tirc, tirc,
-						     rx_hash_toeplitz_key);
-			size_t len = MLX5_FLD_SZ_BYTES(tirc,
-						       rx_hash_toeplitz_key);
-
-			MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
-			memcpy(rss_key, priv->params.toeplitz_hash_key, len);
-		}
+		mlx5e_build_tir_ctx_hash(tirc, priv);
 		break;
 	}
 
@@ -1950,8 +1950,10 @@ static int mlx5e_set_features(struct net_device *netdev,
 			mlx5e_close_locked(priv->netdev);
 
 		priv->params.lro_en = !!(features & NETIF_F_LRO);
-		mlx5e_modify_tir_lro(priv, MLX5E_TT_IPV4_TCP);
-		mlx5e_modify_tir_lro(priv, MLX5E_TT_IPV6_TCP);
+		err = mlx5e_modify_tirs_lro(priv);
+		if (err)
+			mlx5_core_warn(priv->mdev, "lro modify failed, %d\n",
+				       err);
 
 		if (was_opened)
 			err = mlx5e_open_locked(priv->netdev);
@@ -2253,12 +2255,20 @@ static void mlx5e_ets_init(struct mlx5e_priv *priv)
 }
 #endif
 
+void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len,
+				   int num_channels)
+{
+	int i;
+
+	for (i = 0; i < len; i++)
+		indirection_rqt[i] = i % num_channels;
+}
+
 static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev,
 				    struct net_device *netdev,
 				    int num_channels)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	int i;
 
 	priv->params.log_sq_size           =
 		MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
@@ -2281,8 +2291,8 @@ static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev,
 	netdev_rss_key_fill(priv->params.toeplitz_hash_key,
 			    sizeof(priv->params.toeplitz_hash_key));
 
-	for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++)
-		priv->params.indirection_rqt[i] = i % num_channels;
+	mlx5e_build_default_indir_rqt(priv->params.indirection_rqt,
+				      MLX5E_INDIR_RQT_SIZE, num_channels);
 
 	priv->params.lro_wqe_sz            =
 		MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 519a07f253f9..884ed19cded2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -231,10 +231,6 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
 	int work_done;
 
-	/* avoid accessing cq (dma coherent memory) if not needed */
-	if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags))
-		return 0;
-
 	for (work_done = 0; work_done < budget; work_done++) {
 		struct mlx5e_rx_wqe *wqe;
 		struct mlx5_cqe64 *cqe;
@@ -268,6 +264,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 
 		mlx5e_build_rx_skb(cqe, rq, skb);
 		rq->stats.packets++;
+		rq->stats.bytes += be32_to_cpu(cqe->byte_cnt);
 		napi_gro_receive(cq->napi, skb);
 
 wq_ll_pop:
@@ -280,8 +277,5 @@ wq_ll_pop:
 	/* ensure cq space is freed before enabling more cqes */
 	wmb();
 
-	if (work_done == budget)
-		set_bit(MLX5E_CQ_HAS_CQES, &cq->flags);
-
 	return work_done;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index c34f4f3e9537..94a14f85f70d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -177,6 +177,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 	unsigned int skb_len = skb->len;
 	u8  opcode = MLX5_OPCODE_SEND;
 	dma_addr_t dma_addr = 0;
+	unsigned int num_bytes;
 	bool bf = false;
 	u16 headlen;
 	u16 ds_cnt;
@@ -216,16 +217,17 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 			sq->stats.tso_bytes += skb->len - ihs;
 		}
 
-		wi->num_bytes = skb->len +
-				(skb_shinfo(skb)->gso_segs - 1) * ihs;
+		num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
 	} else {
 		bf = sq->bf_budget &&
 		     !skb->xmit_more &&
 		     !skb_shinfo(skb)->nr_frags;
 		ihs = mlx5e_get_inline_hdr_size(sq, skb, bf);
-		wi->num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
+		num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
 	}
 
+	wi->num_bytes = num_bytes;
+
 	if (skb_vlan_tag_present(skb)) {
 		mlx5e_insert_vlan(eseg->inline_hdr_start, skb, ihs, &skb_data,
 				  &skb_len);
@@ -317,6 +319,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 	sq->bf_budget = bf ? sq->bf_budget - 1 : 0;
 
 	sq->stats.packets++;
+	sq->stats.bytes += num_bytes;
 	return NETDEV_TX_OK;
 
 dma_unmap_wqe_err:
@@ -345,10 +348,6 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq)
 	u16 sqcc;
 	int i;
 
-	/* avoid accessing cq (dma coherent memory) if not needed */
-	if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags))
-		return false;
-
 	sq = container_of(cq, struct mlx5e_sq, cq);
 
 	npkts = 0;
@@ -432,10 +431,6 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq)
 				netif_tx_wake_queue(sq->txq);
 				sq->stats.wake++;
 	}
-	if (i == MLX5E_TX_CQ_POLL_BUDGET) {
-		set_bit(MLX5E_CQ_HAS_CQES, &cq->flags);
-		return true;
-	}
 
-	return false;
+	return (i == MLX5E_TX_CQ_POLL_BUDGET);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 4ac8d716dbdd..66d51a77609e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -88,7 +88,6 @@ void mlx5e_completion_event(struct mlx5_core_cq *mcq)
 {
 	struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
 
-	set_bit(MLX5E_CQ_HAS_CQES, &cq->flags);
 	set_bit(MLX5E_CHANNEL_NAPI_SCHED, &cq->channel->flags);
 	barrier();
 	napi_schedule(cq->napi);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index c071077aafbd..7992c553c1f5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -215,7 +215,7 @@ mlxsw_pci_queue_elem_info_producer_get(struct mlxsw_pci_queue *q)
 {
 	int index = q->producer_counter & (q->count - 1);
 
-	if ((q->producer_counter - q->consumer_counter) == q->count)
+	if ((u16) (q->producer_counter - q->consumer_counter) == q->count)
 		return NULL;
 	return mlxsw_pci_queue_elem_info_get(q, index);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 53487d3eb9f6..4afbc3e9e381 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2592,9 +2592,7 @@ static int mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (mlxsw_sp_port->bridged) {
 		mlxsw_sp_port_active_vlans_del(mlxsw_sp_port);
 		mlxsw_sp_port_bridge_leave(mlxsw_sp_port, false);
-
-		if (lag->ref_count == 1)
-			mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL);
+		mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL);
 	}
 
 	if (lag->ref_count == 1) {
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index 00cfd95ca59d..3e67f451f2ab 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -474,9 +474,9 @@ static int moxart_mac_probe(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	ndev->base_addr = res->start;
 	priv->base = devm_ioremap_resource(p_dev, res);
-	ret = IS_ERR(priv->base);
-	if (ret) {
+	if (IS_ERR(priv->base)) {
 		dev_err(p_dev, "devm_ioremap_resource failed\n");
+		ret = PTR_ERR(priv->base);
 		goto init_fail;
 	}
 
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 689a4a5c8dcf..1ef03939d25f 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -811,7 +811,7 @@ qcaspi_netdev_setup(struct net_device *dev)
 	dev->netdev_ops = &qcaspi_netdev_ops;
 	qcaspi_set_ethtool_ops(dev);
 	dev->watchdog_timeo = QCASPI_TX_TIMEOUT;
-	dev->flags = IFF_MULTICAST;
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->tx_queue_len = 100;
 
 	qca = netdev_priv(dev);
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 537974cfd427..dd2cf3738b73 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -4933,8 +4933,6 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
 		RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST);
 		break;
 	case RTL_GIGA_MAC_VER_40:
-		RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF);
-		break;
 	case RTL_GIGA_MAC_VER_41:
 	case RTL_GIGA_MAC_VER_42:
 	case RTL_GIGA_MAC_VER_43:
@@ -4943,8 +4941,6 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_46:
 	case RTL_GIGA_MAC_VER_47:
 	case RTL_GIGA_MAC_VER_48:
-		RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF);
-		break;
 	case RTL_GIGA_MAC_VER_49:
 	case RTL_GIGA_MAC_VER_50:
 	case RTL_GIGA_MAC_VER_51:
@@ -7730,10 +7726,13 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 	void __iomem *ioaddr = tp->mmio_addr;
+	struct pci_dev *pdev = tp->pci_dev;
 	struct rtl8169_counters *counters = tp->counters;
 	unsigned int start;
 
-	if (netif_running(dev))
+	pm_runtime_get_noresume(&pdev->dev);
+
+	if (netif_running(dev) && pm_runtime_active(&pdev->dev))
 		rtl8169_rx_missed(dev, ioaddr);
 
 	do {
@@ -7761,7 +7760,8 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	 * Fetch additonal counter values missing in stats collected by driver
 	 * from tally counters.
 	 */
-	rtl8169_update_counters(dev);
+	if (pm_runtime_active(&pdev->dev))
+		rtl8169_update_counters(dev);
 
 	/*
 	 * Subtract values fetched during initalization.
@@ -7774,6 +7774,8 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	stats->tx_aborted_errors = le16_to_cpu(counters->tx_aborted) -
 		le16_to_cpu(tp->tc_offset.tx_aborted);
 
+	pm_runtime_put_noidle(&pdev->dev);
+
 	return stats;
 }
 
@@ -7853,6 +7855,10 @@ static int rtl8169_runtime_suspend(struct device *device)
 
 	rtl8169_net_suspend(dev);
 
+	/* Update counters before going runtime suspend */
+	rtl8169_rx_missed(dev, tp->mmio_addr);
+	rtl8169_update_counters(dev);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 88656ceb6e29..8f2c4fb4c724 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1708,7 +1708,6 @@ static int ravb_set_gti(struct net_device *ndev)
 static int ravb_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
-	const struct of_device_id *match;
 	struct ravb_private *priv;
 	enum ravb_chip_id chip_id;
 	struct net_device *ndev;
@@ -1740,8 +1739,7 @@ static int ravb_probe(struct platform_device *pdev)
 	ndev->base_addr = res->start;
 	ndev->dma = -1;
 
-	match = of_match_device(of_match_ptr(ravb_match_table), &pdev->dev);
-	chip_id = (enum ravb_chip_id)match->data;
+	chip_id = (enum ravb_chip_id)of_device_get_match_data(&pdev->dev);
 
 	if (chip_id == RCAR_GEN3)
 		irq = platform_get_irq_byname(pdev, "ch22");
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index a2767336b7c5..9c6448915b65 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -3044,15 +3044,11 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
 	mdp->ether_link_active_low = pd->ether_link_active_low;
 
 	/* set cpu data */
-	if (id) {
+	if (id)
 		mdp->cd = (struct sh_eth_cpu_data *)id->driver_data;
-	} else	{
-		const struct of_device_id *match;
+	else
+		mdp->cd = (struct sh_eth_cpu_data *)of_device_get_match_data(&pdev->dev);
 
-		match = of_match_device(of_match_ptr(sh_eth_match_table),
-					&pdev->dev);
-		mdp->cd = (struct sh_eth_cpu_data *)match->data;
-	}
 	mdp->reg_offset = sh_eth_get_register_offset(mdp->cd->register_type);
 	if (!mdp->reg_offset) {
 		dev_err(&pdev->dev, "Unknown register type (%d)\n",
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 0faf16336035..efb54f356a67 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -199,21 +199,12 @@ int stmmac_mdio_register(struct net_device *ndev)
 	struct stmmac_priv *priv = netdev_priv(ndev);
 	struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data;
 	int addr, found;
-	struct device_node *mdio_node = NULL;
-	struct device_node *child_node = NULL;
+	struct device_node *mdio_node = priv->plat->mdio_node;
 
 	if (!mdio_bus_data)
 		return 0;
 
 	if (IS_ENABLED(CONFIG_OF)) {
-		for_each_child_of_node(priv->device->of_node, child_node) {
-			if (of_device_is_compatible(child_node,
-						    "snps,dwmac-mdio")) {
-				mdio_node = child_node;
-				break;
-			}
-		}
-
 		if (mdio_node) {
 			netdev_dbg(ndev, "FOUND MDIO subnode\n");
 		} else {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 9cf181f839fd..dcbd2a1601e8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -146,6 +146,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 	struct device_node *np = pdev->dev.of_node;
 	struct plat_stmmacenet_data *plat;
 	struct stmmac_dma_cfg *dma_cfg;
+	struct device_node *child_node = NULL;
 
 	plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL);
 	if (!plat)
@@ -176,13 +177,19 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 		plat->phy_node = of_node_get(np);
 	}
 
+	for_each_child_of_node(np, child_node)
+		if (of_device_is_compatible(child_node,	"snps,dwmac-mdio")) {
+			plat->mdio_node = child_node;
+			break;
+		}
+
 	/* "snps,phy-addr" is not a standard property. Mark it as deprecated
 	 * and warn of its use. Remove this when phy node support is added.
 	 */
 	if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0)
 		dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n");
 
-	if ((plat->phy_node && !of_phy_is_fixed_link(np)) || plat->phy_bus_name)
+	if ((plat->phy_node && !of_phy_is_fixed_link(np)) || !plat->mdio_node)
 		plat->mdio_bus_data = NULL;
 	else
 		plat->mdio_bus_data =
diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
index fc8bbff2d7e3..af11ed1e0bcc 100644
--- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c
+++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
@@ -426,7 +426,7 @@
 #define DWC_MMC_RXOCTETCOUNT_GB          0x0784
 #define DWC_MMC_RXPACKETCOUNT_GB         0x0780
 
-static int debug = 3;
+static int debug = -1;
 module_param(debug, int, 0);
 MODULE_PARM_DESC(debug, "DWC_eth_qos debug level (0=none,...,16=all)");
 
@@ -650,6 +650,11 @@ struct net_local {
 	u32 mmc_tx_counters_mask;
 
 	struct dwceqos_flowcontrol flowcontrol;
+
+	/* Tracks the intermediate state of phy started but hardware
+	 * init not finished yet.
+	 */
+	bool phy_defer;
 };
 
 static void dwceqos_read_mmc_counters(struct net_local *lp, u32 rx_mask,
@@ -901,6 +906,9 @@ static void dwceqos_adjust_link(struct net_device *ndev)
 	struct phy_device *phydev = lp->phy_dev;
 	int status_change = 0;
 
+	if (lp->phy_defer)
+		return;
+
 	if (phydev->link) {
 		if ((lp->speed != phydev->speed) ||
 		    (lp->duplex != phydev->duplex)) {
@@ -1113,7 +1121,7 @@ static int dwceqos_descriptor_init(struct net_local *lp)
 	/* Allocate DMA descriptors */
 	size = DWCEQOS_RX_DCNT * sizeof(struct dwceqos_dma_desc);
 	lp->rx_descs = dma_alloc_coherent(lp->ndev->dev.parent, size,
-			&lp->rx_descs_addr, 0);
+			&lp->rx_descs_addr, GFP_KERNEL);
 	if (!lp->rx_descs)
 		goto err_out;
 	lp->rx_descs_tail_addr = lp->rx_descs_addr +
@@ -1121,7 +1129,7 @@ static int dwceqos_descriptor_init(struct net_local *lp)
 
 	size = DWCEQOS_TX_DCNT * sizeof(struct dwceqos_dma_desc);
 	lp->tx_descs = dma_alloc_coherent(lp->ndev->dev.parent, size,
-			&lp->tx_descs_addr, 0);
+			&lp->tx_descs_addr, GFP_KERNEL);
 	if (!lp->tx_descs)
 		goto err_out;
 	lp->tx_descs_tail_addr = lp->tx_descs_addr +
@@ -1635,6 +1643,12 @@ static void dwceqos_init_hw(struct net_local *lp)
 	regval = dwceqos_read(lp, REG_DWCEQOS_MAC_CFG);
 	dwceqos_write(lp, REG_DWCEQOS_MAC_CFG,
 		      regval | DWCEQOS_MAC_CFG_TE | DWCEQOS_MAC_CFG_RE);
+
+	lp->phy_defer = false;
+	mutex_lock(&lp->phy_dev->lock);
+	phy_read_status(lp->phy_dev);
+	dwceqos_adjust_link(lp->ndev);
+	mutex_unlock(&lp->phy_dev->lock);
 }
 
 static void dwceqos_tx_reclaim(unsigned long data)
@@ -1880,9 +1894,13 @@ static int dwceqos_open(struct net_device *ndev)
 	}
 	netdev_reset_queue(ndev);
 
+	/* The dwceqos reset state machine requires all phy clocks to complete,
+	 * hence the unusual init order with phy_start first.
+	 */
+	lp->phy_defer = true;
+	phy_start(lp->phy_dev);
 	dwceqos_init_hw(lp);
 	napi_enable(&lp->napi);
-	phy_start(lp->phy_dev);
 
 	netif_start_queue(ndev);
 	tasklet_enable(&lp->tx_bdreclaim_tasklet);
@@ -1915,18 +1933,19 @@ static int dwceqos_stop(struct net_device *ndev)
 {
 	struct net_local *lp = netdev_priv(ndev);
 
-	phy_stop(lp->phy_dev);
-
 	tasklet_disable(&lp->tx_bdreclaim_tasklet);
-	netif_stop_queue(ndev);
 	napi_disable(&lp->napi);
 
-	dwceqos_drain_dma(lp);
+	/* Stop all tx before we drain the tx dma. */
+	netif_tx_lock_bh(lp->ndev);
+	netif_stop_queue(ndev);
+	netif_tx_unlock_bh(lp->ndev);
 
-	netif_tx_lock(lp->ndev);
+	dwceqos_drain_dma(lp);
 	dwceqos_reset_hw(lp);
+	phy_stop(lp->phy_dev);
+
 	dwceqos_descriptor_free(lp);
-	netif_tx_unlock(lp->ndev);
 
 	return 0;
 }
@@ -2178,12 +2197,10 @@ static int dwceqos_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		((trans.initial_descriptor + trans.nr_descriptors) %
 		 DWCEQOS_TX_DCNT));
 
-	dwceqos_tx_finalize(skb, lp, &trans);
-
-	netdev_sent_queue(ndev, skb->len);
-
 	spin_lock_bh(&lp->tx_lock);
 	lp->tx_free -= trans.nr_descriptors;
+	dwceqos_tx_finalize(skb, lp, &trans);
+	netdev_sent_queue(ndev, skb->len);
 	spin_unlock_bh(&lp->tx_lock);
 
 	ndev->trans_start = jiffies;