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

Three conflicts, one of which, for marvell10g.c is non-trivial and
requires some follow-up from Heiner or someone else.

The issue is that Heiner converted the marvell10g driver over to
use the generic c45 code as much as possible.

However, in 'net' a bug fix appeared which makes sure that a new
local mask (MDIO_AN_10GBT_CTRL_ADV_NBT_MASK) with value 0x01e0
is cleared.

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

17 files changed, 215 insertions, 181 deletions

diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index a7337a6d507d..d99317b3d891 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -1335,13 +1335,11 @@ static int atl2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct net_device *netdev;
 	struct atl2_adapter *adapter;
-	static int cards_found;
+	static int cards_found = 0;
 	unsigned long mmio_start;
 	int mmio_len;
 	int err;
 
-	cards_found = 0;
-
 	err = pci_enable_device(pdev);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index a9edf946d3bf..42fe9e0cceec 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3907,7 +3907,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 			if (len)
 				break;
 			/* on first few passes, just barely sleep */
-			if (i < DFLT_HWRM_CMD_TIMEOUT)
+			if (i < HWRM_SHORT_TIMEOUT_COUNTER)
 				usleep_range(HWRM_SHORT_MIN_TIMEOUT,
 					     HWRM_SHORT_MAX_TIMEOUT);
 			else
@@ -3930,7 +3930,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 			dma_rmb();
 			if (*valid)
 				break;
-			udelay(1);
+			usleep_range(1, 5);
 		}
 
 		if (j >= HWRM_VALID_BIT_DELAY_USEC) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index ecbe7d28a723..cf81ace7a6e6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -581,7 +581,7 @@ struct nqe_cn {
 	(HWRM_SHORT_TIMEOUT_COUNTER * HWRM_SHORT_MIN_TIMEOUT +		\
 	 ((n) - HWRM_SHORT_TIMEOUT_COUNTER) * HWRM_MIN_TIMEOUT))
 
-#define HWRM_VALID_BIT_DELAY_USEC	20
+#define HWRM_VALID_BIT_DELAY_USEC	150
 
 #define BNXT_HWRM_CHNL_CHIMP	0
 #define BNXT_HWRM_CHNL_KONG	1
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index f4d81765221e..62636c1ed141 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -271,7 +271,7 @@ struct xcast_addr_list {
 };
 
 struct nicvf_work {
-	struct delayed_work    work;
+	struct work_struct     work;
 	u8                     mode;
 	struct xcast_addr_list *mc;
 };
@@ -327,7 +327,11 @@ struct nicvf {
 	struct nicvf_work       rx_mode_work;
 	/* spinlock to protect workqueue arguments from concurrent access */
 	spinlock_t              rx_mode_wq_lock;
-
+	/* workqueue for handling kernel ndo_set_rx_mode() calls */
+	struct workqueue_struct *nicvf_rx_mode_wq;
+	/* mutex to protect VF's mailbox contents from concurrent access */
+	struct mutex            rx_mode_mtx;
+	struct delayed_work	link_change_work;
 	/* PTP timestamp */
 	struct cavium_ptp	*ptp_clock;
 	/* Inbound timestamping is on */
@@ -575,10 +579,8 @@ struct set_ptp {
 
 struct xcast {
 	u8    msg;
-	union {
-		u8    mode;
-		u64   mac;
-	} data;
+	u8    mode;
+	u64   mac:48;
 };
 
 /* 128 bit shared memory between PF and each VF */
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 6c8dcb65ff03..c90252829ed3 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -57,14 +57,8 @@ struct nicpf {
 #define	NIC_GET_BGX_FROM_VF_LMAC_MAP(map)	((map >> 4) & 0xF)
 #define	NIC_GET_LMAC_FROM_VF_LMAC_MAP(map)	(map & 0xF)
 	u8			*vf_lmac_map;
-	struct delayed_work     dwork;
-	struct workqueue_struct *check_link;
-	u8			*link;
-	u8			*duplex;
-	u32			*speed;
 	u16			cpi_base[MAX_NUM_VFS_SUPPORTED];
 	u16			rssi_base[MAX_NUM_VFS_SUPPORTED];
-	bool			mbx_lock[MAX_NUM_VFS_SUPPORTED];
 
 	/* MSI-X */
 	u8			num_vec;
@@ -929,6 +923,35 @@ static void nic_config_timestamp(struct nicpf *nic, int vf, struct set_ptp *ptp)
 	nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG | (pkind_idx << 3), pkind_val);
 }
 
+/* Get BGX LMAC link status and update corresponding VF
+ * if there is a change, valid only if internal L2 switch
+ * is not present otherwise VF link is always treated as up
+ */
+static void nic_link_status_get(struct nicpf *nic, u8 vf)
+{
+	union nic_mbx mbx = {};
+	struct bgx_link_status link;
+	u8 bgx, lmac;
+
+	mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE;
+
+	/* Get BGX, LMAC indices for the VF */
+	bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+	lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+
+	/* Get interface link status */
+	bgx_get_lmac_link_state(nic->node, bgx, lmac, &link);
+
+	/* Send a mbox message to VF with current link status */
+	mbx.link_status.link_up = link.link_up;
+	mbx.link_status.duplex = link.duplex;
+	mbx.link_status.speed = link.speed;
+	mbx.link_status.mac_type = link.mac_type;
+
+	/* reply with link status */
+	nic_send_msg_to_vf(nic, vf, &mbx);
+}
+
 /* Interrupt handler to handle mailbox messages from VFs */
 static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 {
@@ -941,8 +964,6 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 	int i;
 	int ret = 0;
 
-	nic->mbx_lock[vf] = true;
-
 	mbx_addr = nic_get_mbx_addr(vf);
 	mbx_data = (u64 *)&mbx;
 
@@ -957,12 +978,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 	switch (mbx.msg.msg) {
 	case NIC_MBOX_MSG_READY:
 		nic_mbx_send_ready(nic, vf);
-		if (vf < nic->num_vf_en) {
-			nic->link[vf] = 0;
-			nic->duplex[vf] = 0;
-			nic->speed[vf] = 0;
-		}
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_QS_CFG:
 		reg_addr = NIC_PF_QSET_0_127_CFG |
 			   (mbx.qs.num << NIC_QS_ID_SHIFT);
@@ -1031,7 +1047,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 		break;
 	case NIC_MBOX_MSG_RSS_SIZE:
 		nic_send_rss_size(nic, vf);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_RSS_CFG:
 	case NIC_MBOX_MSG_RSS_CFG_CONT:
 		nic_config_rss(nic, &mbx.rss_cfg);
@@ -1039,7 +1055,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 	case NIC_MBOX_MSG_CFG_DONE:
 		/* Last message of VF config msg sequence */
 		nic_enable_vf(nic, vf, true);
-		goto unlock;
+		break;
 	case NIC_MBOX_MSG_SHUTDOWN:
 		/* First msg in VF teardown sequence */
 		if (vf >= nic->num_vf_en)
@@ -1049,19 +1065,19 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 		break;
 	case NIC_MBOX_MSG_ALLOC_SQS:
 		nic_alloc_sqs(nic, &mbx.sqs_alloc);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_NICVF_PTR:
 		nic->nicvf[vf] = mbx.nicvf.nicvf;
 		break;
 	case NIC_MBOX_MSG_PNICVF_PTR:
 		nic_send_pnicvf(nic, vf);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_SNICVF_PTR:
 		nic_send_snicvf(nic, &mbx.nicvf);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_BGX_STATS:
 		nic_get_bgx_stats(nic, &mbx.bgx_stats);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_LOOPBACK:
 		ret = nic_config_loopback(nic, &mbx.lbk);
 		break;
@@ -1070,7 +1086,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 		break;
 	case NIC_MBOX_MSG_PFC:
 		nic_pause_frame(nic, vf, &mbx.pfc);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_PTP_CFG:
 		nic_config_timestamp(nic, vf, &mbx.ptp);
 		break;
@@ -1094,7 +1110,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
 		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
 		bgx_set_dmac_cam_filter(nic->node, bgx, lmac,
-					mbx.xcast.data.mac,
+					mbx.xcast.mac,
 					vf < NIC_VF_PER_MBX_REG ? vf :
 					vf - NIC_VF_PER_MBX_REG);
 		break;
@@ -1106,8 +1122,15 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 		}
 		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
 		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
-		bgx_set_xcast_mode(nic->node, bgx, lmac, mbx.xcast.data.mode);
+		bgx_set_xcast_mode(nic->node, bgx, lmac, mbx.xcast.mode);
 		break;
+	case NIC_MBOX_MSG_BGX_LINK_CHANGE:
+		if (vf >= nic->num_vf_en) {
+			ret = -1; /* NACK */
+			break;
+		}
+		nic_link_status_get(nic, vf);
+		return;
 	default:
 		dev_err(&nic->pdev->dev,
 			"Invalid msg from VF%d, msg 0x%x\n", vf, mbx.msg.msg);
@@ -1121,8 +1144,6 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 			mbx.msg.msg, vf);
 		nic_mbx_send_nack(nic, vf);
 	}
-unlock:
-	nic->mbx_lock[vf] = false;
 }
 
 static irqreturn_t nic_mbx_intr_handler(int irq, void *nic_irq)
@@ -1270,52 +1291,6 @@ static int nic_sriov_init(struct pci_dev *pdev, struct nicpf *nic)
 	return 0;
 }
 
-/* Poll for BGX LMAC link status and update corresponding VF
- * if there is a change, valid only if internal L2 switch
- * is not present otherwise VF link is always treated as up
- */
-static void nic_poll_for_link(struct work_struct *work)
-{
-	union nic_mbx mbx = {};
-	struct nicpf *nic;
-	struct bgx_link_status link;
-	u8 vf, bgx, lmac;
-
-	nic = container_of(work, struct nicpf, dwork.work);
-
-	mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE;
-
-	for (vf = 0; vf < nic->num_vf_en; vf++) {
-		/* Poll only if VF is UP */
-		if (!nic->vf_enabled[vf])
-			continue;
-
-		/* Get BGX, LMAC indices for the VF */
-		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
-		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
-		/* Get interface link status */
-		bgx_get_lmac_link_state(nic->node, bgx, lmac, &link);
-
-		/* Inform VF only if link status changed */
-		if (nic->link[vf] == link.link_up)
-			continue;
-
-		if (!nic->mbx_lock[vf]) {
-			nic->link[vf] = link.link_up;
-			nic->duplex[vf] = link.duplex;
-			nic->speed[vf] = link.speed;
-
-			/* Send a mbox message to VF with current link status */
-			mbx.link_status.link_up = link.link_up;
-			mbx.link_status.duplex = link.duplex;
-			mbx.link_status.speed = link.speed;
-			mbx.link_status.mac_type = link.mac_type;
-			nic_send_msg_to_vf(nic, vf, &mbx);
-		}
-	}
-	queue_delayed_work(nic->check_link, &nic->dwork, HZ * 2);
-}
-
 static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct device *dev = &pdev->dev;
@@ -1384,18 +1359,6 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!nic->vf_lmac_map)
 		goto err_release_regions;
 
-	nic->link = devm_kmalloc_array(dev, max_lmac, sizeof(u8), GFP_KERNEL);
-	if (!nic->link)
-		goto err_release_regions;
-
-	nic->duplex = devm_kmalloc_array(dev, max_lmac, sizeof(u8), GFP_KERNEL);
-	if (!nic->duplex)
-		goto err_release_regions;
-
-	nic->speed = devm_kmalloc_array(dev, max_lmac, sizeof(u32), GFP_KERNEL);
-	if (!nic->speed)
-		goto err_release_regions;
-
 	/* Initialize hardware */
 	nic_init_hw(nic);
 
@@ -1411,22 +1374,8 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto err_unregister_interrupts;
 
-	/* Register a physical link status poll fn() */
-	nic->check_link = alloc_workqueue("check_link_status",
-					  WQ_UNBOUND | WQ_MEM_RECLAIM, 1);
-	if (!nic->check_link) {
-		err = -ENOMEM;
-		goto err_disable_sriov;
-	}
-
-	INIT_DELAYED_WORK(&nic->dwork, nic_poll_for_link);
-	queue_delayed_work(nic->check_link, &nic->dwork, 0);
-
 	return 0;
 
-err_disable_sriov:
-	if (nic->flags & NIC_SRIOV_ENABLED)
-		pci_disable_sriov(pdev);
 err_unregister_interrupts:
 	nic_unregister_interrupts(nic);
 err_release_regions:
@@ -1447,12 +1396,6 @@ static void nic_remove(struct pci_dev *pdev)
 	if (nic->flags & NIC_SRIOV_ENABLED)
 		pci_disable_sriov(pdev);
 
-	if (nic->check_link) {
-		/* Destroy work Queue */
-		cancel_delayed_work_sync(&nic->dwork);
-		destroy_workqueue(nic->check_link);
-	}
-
 	nic_unregister_interrupts(nic);
 	pci_release_regions(pdev);
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 88f8a8fa93cd..503cfadff4ac 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -68,9 +68,6 @@ module_param(cpi_alg, int, 0444);
 MODULE_PARM_DESC(cpi_alg,
 		 "PFC algorithm (0=none, 1=VLAN, 2=VLAN16, 3=IP Diffserv)");
 
-/* workqueue for handling kernel ndo_set_rx_mode() calls */
-static struct workqueue_struct *nicvf_rx_mode_wq;
-
 static inline u8 nicvf_netdev_qidx(struct nicvf *nic, u8 qidx)
 {
 	if (nic->sqs_mode)
@@ -127,6 +124,9 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx)
 {
 	int timeout = NIC_MBOX_MSG_TIMEOUT;
 	int sleep = 10;
+	int ret = 0;
+
+	mutex_lock(&nic->rx_mode_mtx);
 
 	nic->pf_acked = false;
 	nic->pf_nacked = false;
@@ -139,7 +139,8 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx)
 			netdev_err(nic->netdev,
 				   "PF NACK to mbox msg 0x%02x from VF%d\n",
 				   (mbx->msg.msg & 0xFF), nic->vf_id);
-			return -EINVAL;
+			ret = -EINVAL;
+			break;
 		}
 		msleep(sleep);
 		if (nic->pf_acked)
@@ -149,10 +150,12 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx)
 			netdev_err(nic->netdev,
 				   "PF didn't ACK to mbox msg 0x%02x from VF%d\n",
 				   (mbx->msg.msg & 0xFF), nic->vf_id);
-			return -EBUSY;
+			ret = -EBUSY;
+			break;
 		}
 	}
-	return 0;
+	mutex_unlock(&nic->rx_mode_mtx);
+	return ret;
 }
 
 /* Checks if VF is able to comminicate with PF
@@ -172,6 +175,17 @@ static int nicvf_check_pf_ready(struct nicvf *nic)
 	return 1;
 }
 
+static void nicvf_send_cfg_done(struct nicvf *nic)
+{
+	union nic_mbx mbx = {};
+
+	mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE;
+	if (nicvf_send_msg_to_pf(nic, &mbx)) {
+		netdev_err(nic->netdev,
+			   "PF didn't respond to CFG DONE msg\n");
+	}
+}
+
 static void nicvf_read_bgx_stats(struct nicvf *nic, struct bgx_stats_msg *bgx)
 {
 	if (bgx->rx)
@@ -228,21 +242,24 @@ static void  nicvf_handle_mbx_intr(struct nicvf *nic)
 		break;
 	case NIC_MBOX_MSG_BGX_LINK_CHANGE:
 		nic->pf_acked = true;
-		nic->link_up = mbx.link_status.link_up;
-		nic->duplex = mbx.link_status.duplex;
-		nic->speed = mbx.link_status.speed;
-		nic->mac_type = mbx.link_status.mac_type;
-		if (nic->link_up) {
-			netdev_info(nic->netdev, "Link is Up %d Mbps %s duplex\n",
-				    nic->speed,
-				    nic->duplex == DUPLEX_FULL ?
-				    "Full" : "Half");
-			netif_carrier_on(nic->netdev);
-			netif_tx_start_all_queues(nic->netdev);
-		} else {
-			netdev_info(nic->netdev, "Link is Down\n");
-			netif_carrier_off(nic->netdev);
-			netif_tx_stop_all_queues(nic->netdev);
+		if (nic->link_up != mbx.link_status.link_up) {
+			nic->link_up = mbx.link_status.link_up;
+			nic->duplex = mbx.link_status.duplex;
+			nic->speed = mbx.link_status.speed;
+			nic->mac_type = mbx.link_status.mac_type;
+			if (nic->link_up) {
+				netdev_info(nic->netdev,
+					    "Link is Up %d Mbps %s duplex\n",
+					    nic->speed,
+					    nic->duplex == DUPLEX_FULL ?
+					    "Full" : "Half");
+				netif_carrier_on(nic->netdev);
+				netif_tx_start_all_queues(nic->netdev);
+			} else {
+				netdev_info(nic->netdev, "Link is Down\n");
+				netif_carrier_off(nic->netdev);
+				netif_tx_stop_all_queues(nic->netdev);
+			}
 		}
 		break;
 	case NIC_MBOX_MSG_ALLOC_SQS:
@@ -1311,6 +1328,11 @@ int nicvf_stop(struct net_device *netdev)
 	struct nicvf_cq_poll *cq_poll = NULL;
 	union nic_mbx mbx = {};
 
+	cancel_delayed_work_sync(&nic->link_change_work);
+
+	/* wait till all queued set_rx_mode tasks completes */
+	drain_workqueue(nic->nicvf_rx_mode_wq);
+
 	mbx.msg.msg = NIC_MBOX_MSG_SHUTDOWN;
 	nicvf_send_msg_to_pf(nic, &mbx);
 
@@ -1410,13 +1432,27 @@ static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu)
 	return nicvf_send_msg_to_pf(nic, &mbx);
 }
 
+static void nicvf_link_status_check_task(struct work_struct *work_arg)
+{
+	struct nicvf *nic = container_of(work_arg,
+					 struct nicvf,
+					 link_change_work.work);
+	union nic_mbx mbx = {};
+	mbx.msg.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE;
+	nicvf_send_msg_to_pf(nic, &mbx);
+	queue_delayed_work(nic->nicvf_rx_mode_wq,
+			   &nic->link_change_work, 2 * HZ);
+}
+
 int nicvf_open(struct net_device *netdev)
 {
 	int cpu, err, qidx;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct queue_set *qs = nic->qs;
 	struct nicvf_cq_poll *cq_poll = NULL;
-	union nic_mbx mbx = {};
+
+	/* wait till all queued set_rx_mode tasks completes if any */
+	drain_workqueue(nic->nicvf_rx_mode_wq);
 
 	netif_carrier_off(netdev);
 
@@ -1512,8 +1548,12 @@ int nicvf_open(struct net_device *netdev)
 		nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx);
 
 	/* Send VF config done msg to PF */
-	mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE;
-	nicvf_write_to_mbx(nic, &mbx);
+	nicvf_send_cfg_done(nic);
+
+	INIT_DELAYED_WORK(&nic->link_change_work,
+			  nicvf_link_status_check_task);
+	queue_delayed_work(nic->nicvf_rx_mode_wq,
+			   &nic->link_change_work, 0);
 
 	return 0;
 cleanup:
@@ -1941,15 +1981,17 @@ static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs,
 
 	/* flush DMAC filters and reset RX mode */
 	mbx.xcast.msg = NIC_MBOX_MSG_RESET_XCAST;
-	nicvf_send_msg_to_pf(nic, &mbx);
+	if (nicvf_send_msg_to_pf(nic, &mbx) < 0)
+		goto free_mc;
 
 	if (mode & BGX_XCAST_MCAST_FILTER) {
 		/* once enabling filtering, we need to signal to PF to add
 		 * its' own LMAC to the filter to accept packets for it.
 		 */
 		mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST;
-		mbx.xcast.data.mac = 0;
-		nicvf_send_msg_to_pf(nic, &mbx);
+		mbx.xcast.mac = 0;
+		if (nicvf_send_msg_to_pf(nic, &mbx) < 0)
+			goto free_mc;
 	}
 
 	/* check if we have any specific MACs to be added to PF DMAC filter */
@@ -1957,23 +1999,25 @@ static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs,
 		/* now go through kernel list of MACs and add them one by one */
 		for (idx = 0; idx < mc_addrs->count; idx++) {
 			mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST;
-			mbx.xcast.data.mac = mc_addrs->mc[idx];
-			nicvf_send_msg_to_pf(nic, &mbx);
+			mbx.xcast.mac = mc_addrs->mc[idx];
+			if (nicvf_send_msg_to_pf(nic, &mbx) < 0)
+				goto free_mc;
 		}
-		kfree(mc_addrs);
 	}
 
 	/* and finally set rx mode for PF accordingly */
 	mbx.xcast.msg = NIC_MBOX_MSG_SET_XCAST;
-	mbx.xcast.data.mode = mode;
+	mbx.xcast.mode = mode;
 
 	nicvf_send_msg_to_pf(nic, &mbx);
+free_mc:
+	kfree(mc_addrs);
 }
 
 static void nicvf_set_rx_mode_task(struct work_struct *work_arg)
 {
 	struct nicvf_work *vf_work = container_of(work_arg, struct nicvf_work,
-						  work.work);
+						  work);
 	struct nicvf *nic = container_of(vf_work, struct nicvf, rx_mode_work);
 	u8 mode;
 	struct xcast_addr_list *mc;
@@ -2030,7 +2074,7 @@ static void nicvf_set_rx_mode(struct net_device *netdev)
 	kfree(nic->rx_mode_work.mc);
 	nic->rx_mode_work.mc = mc_list;
 	nic->rx_mode_work.mode = mode;
-	queue_delayed_work(nicvf_rx_mode_wq, &nic->rx_mode_work.work, 0);
+	queue_work(nic->nicvf_rx_mode_wq, &nic->rx_mode_work.work);
 	spin_unlock(&nic->rx_mode_wq_lock);
 }
 
@@ -2187,8 +2231,12 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	INIT_WORK(&nic->reset_task, nicvf_reset_task);
 
-	INIT_DELAYED_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task);
+	nic->nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_rx_mode_wq_VF%d",
+							WQ_MEM_RECLAIM,
+							nic->vf_id);
+	INIT_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task);
 	spin_lock_init(&nic->rx_mode_wq_lock);
+	mutex_init(&nic->rx_mode_mtx);
 
 	err = register_netdev(netdev);
 	if (err) {
@@ -2228,13 +2276,15 @@ static void nicvf_remove(struct pci_dev *pdev)
 	nic = netdev_priv(netdev);
 	pnetdev = nic->pnicvf->netdev;
 
-	cancel_delayed_work_sync(&nic->rx_mode_work.work);
-
 	/* Check if this Qset is assigned to different VF.
 	 * If yes, clean primary and all secondary Qsets.
 	 */
 	if (pnetdev && (pnetdev->reg_state == NETREG_REGISTERED))
 		unregister_netdev(pnetdev);
+	if (nic->nicvf_rx_mode_wq) {
+		destroy_workqueue(nic->nicvf_rx_mode_wq);
+		nic->nicvf_rx_mode_wq = NULL;
+	}
 	nicvf_unregister_interrupts(nic);
 	pci_set_drvdata(pdev, NULL);
 	if (nic->drv_stats)
@@ -2261,17 +2311,11 @@ static struct pci_driver nicvf_driver = {
 static int __init nicvf_init_module(void)
 {
 	pr_info("%s, ver %s\n", DRV_NAME, DRV_VERSION);
-	nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_generic",
-						   WQ_MEM_RECLAIM);
 	return pci_register_driver(&nicvf_driver);
 }
 
 static void __exit nicvf_cleanup_module(void)
 {
-	if (nicvf_rx_mode_wq) {
-		destroy_workqueue(nicvf_rx_mode_wq);
-		nicvf_rx_mode_wq = NULL;
-	}
 	pci_unregister_driver(&nicvf_driver);
 }
 
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index e337da6ba2a4..673c57b8023f 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -1217,7 +1217,7 @@ static void bgx_init_hw(struct bgx *bgx)
 
 	/* Disable MAC steering (NCSI traffic) */
 	for (i = 0; i < RX_TRAFFIC_STEER_RULE_COUNT; i++)
-		bgx_reg_write(bgx, 0, BGX_CMR_RX_STREERING + (i * 8), 0x00);
+		bgx_reg_write(bgx, 0, BGX_CMR_RX_STEERING + (i * 8), 0x00);
 }
 
 static u8 bgx_get_lane2sds_cfg(struct bgx *bgx, struct lmac *lmac)
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index cbdd20b9ee6f..5cbc54e9eb19 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -60,7 +60,7 @@
 #define  RX_DMACX_CAM_EN			BIT_ULL(48)
 #define  RX_DMACX_CAM_LMACID(x)			(((u64)x) << 49)
 #define  RX_DMAC_COUNT				32
-#define BGX_CMR_RX_STREERING		0x300
+#define BGX_CMR_RX_STEERING		0x300
 #define  RX_TRAFFIC_STEER_RULE_COUNT		8
 #define BGX_CMR_CHAN_MSK_AND		0x450
 #define BGX_CMR_BIST_STATUS		0x460
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index c041f44324db..b3654598a2d5 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -660,6 +660,7 @@ static void uld_init(struct adapter *adap, struct cxgb4_lld_info *lld)
 	lld->cclk_ps = 1000000000 / adap->params.vpd.cclk;
 	lld->udb_density = 1 << adap->params.sge.eq_qpp;
 	lld->ucq_density = 1 << adap->params.sge.iq_qpp;
+	lld->sge_host_page_size = 1 << (adap->params.sge.hps + 10);
 	lld->filt_mode = adap->params.tp.vlan_pri_map;
 	/* MODQ_REQ_MAP sets queues 0-3 to chan 0-3 */
 	for (i = 0; i < NCHAN; i++)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 5fa9a2d5fc4b..21da34a4ca24 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -336,6 +336,7 @@ struct cxgb4_lld_info {
 	unsigned int cclk_ps;                /* Core clock period in psec */
 	unsigned short udb_density;          /* # of user DB/page */
 	unsigned short ucq_density;          /* # of user CQs/page */
+	unsigned int sge_host_page_size;     /* SGE host page size */
 	unsigned short filt_mode;            /* filter optional components */
 	unsigned short tx_modq[NCHAN];       /* maps each tx channel to a */
 					     /* scheduler queue */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 5e74a5127849..da62218eb70a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3289,8 +3289,11 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	     i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)) :
 	     !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
 	if (!ok) {
+		/* Log this in case the user has forgotten to give the kernel
+		 * any buffers, even later in the application.
+		 */
 		dev_info(&vsi->back->pdev->dev,
-			 "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n",
+			 "Failed to allocate some buffers on %sRx ring %d (pf_q %d)\n",
 			 ring->xsk_umem ? "UMEM enabled " : "",
 			 ring->queue_index, pf_q);
 	}
@@ -6725,8 +6728,13 @@ void i40e_down(struct i40e_vsi *vsi)
 
 	for (i = 0; i < vsi->num_queue_pairs; i++) {
 		i40e_clean_tx_ring(vsi->tx_rings[i]);
-		if (i40e_enabled_xdp_vsi(vsi))
+		if (i40e_enabled_xdp_vsi(vsi)) {
+			/* Make sure that in-progress ndo_xdp_xmit
+			 * calls are completed.
+			 */
+			synchronize_rcu();
 			i40e_clean_tx_ring(vsi->xdp_rings[i]);
+		}
 		i40e_clean_rx_ring(vsi->rx_rings[i]);
 	}
 
@@ -11855,6 +11863,14 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi,
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
+	/* Kick start the NAPI context if there is an AF_XDP socket open
+	 * on that queue id. This so that receiving will start.
+	 */
+	if (need_reset && prog)
+		for (i = 0; i < vsi->num_queue_pairs; i++)
+			if (vsi->xdp_rings[i]->xsk_umem)
+				(void)i40e_xsk_async_xmit(vsi->netdev, i);
+
 	return 0;
 }
 
@@ -11915,8 +11931,13 @@ static void i40e_queue_pair_reset_stats(struct i40e_vsi *vsi, int queue_pair)
 static void i40e_queue_pair_clean_rings(struct i40e_vsi *vsi, int queue_pair)
 {
 	i40e_clean_tx_ring(vsi->tx_rings[queue_pair]);
-	if (i40e_enabled_xdp_vsi(vsi))
+	if (i40e_enabled_xdp_vsi(vsi)) {
+		/* Make sure that in-progress ndo_xdp_xmit calls are
+		 * completed.
+		 */
+		synchronize_rcu();
 		i40e_clean_tx_ring(vsi->xdp_rings[queue_pair]);
+	}
 	i40e_clean_rx_ring(vsi->rx_rings[queue_pair]);
 }
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index a7e14e98889f..6c97667d20ef 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -3709,6 +3709,7 @@ int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	unsigned int queue_index = smp_processor_id();
 	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
 	struct i40e_ring *xdp_ring;
 	int drops = 0;
 	int i;
@@ -3716,7 +3717,8 @@ int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	if (test_bit(__I40E_VSI_DOWN, vsi->state))
 		return -ENETDOWN;
 
-	if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs)
+	if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs ||
+	    test_bit(__I40E_CONFIG_BUSY, pf->state))
 		return -ENXIO;
 
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index e190a2c2b9ff..b5c182e688e3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -112,6 +112,11 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 		err = i40e_queue_pair_enable(vsi, qid);
 		if (err)
 			return err;
+
+		/* Kick start the NAPI context so that receiving will start */
+		err = i40e_xsk_async_xmit(vsi->netdev, qid);
+		if (err)
+			return err;
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 38c430b94ae3..a4e7584a50cb 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -3953,8 +3953,11 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter)
 			else
 				mrqc = IXGBE_MRQC_VMDQRSS64EN;
 
-			/* Enable L3/L4 for Tx Switched packets */
-			mrqc |= IXGBE_MRQC_L3L4TXSWEN;
+			/* Enable L3/L4 for Tx Switched packets only for X550,
+			 * older devices do not support this feature
+			 */
+			if (hw->mac.type >= ixgbe_mac_X550)
+				mrqc |= IXGBE_MRQC_L3L4TXSWEN;
 		} else {
 			if (tcs > 4)
 				mrqc = IXGBE_MRQC_RTRSS8TCEN;
@@ -10226,6 +10229,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 	int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	struct bpf_prog *old_prog;
+	bool need_reset;
 
 	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
 		return -EINVAL;
@@ -10248,9 +10252,10 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 		return -ENOMEM;
 
 	old_prog = xchg(&adapter->xdp_prog, prog);
+	need_reset = (!!prog != !!old_prog);
 
 	/* If transitioning XDP modes reconfigure rings */
-	if (!!prog != !!old_prog) {
+	if (need_reset) {
 		int err = ixgbe_setup_tc(dev, adapter->hw_tcs);
 
 		if (err) {
@@ -10266,6 +10271,14 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
+	/* Kick start the NAPI context if there is an AF_XDP socket open
+	 * on that queue id. This so that receiving will start.
+	 */
+	if (need_reset && prog)
+		for (i = 0; i < adapter->num_rx_queues; i++)
+			if (adapter->xdp_ring[i]->xsk_umem)
+				(void)ixgbe_xsk_async_xmit(adapter->netdev, i);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 98870707b51a..bfe95ce0bd7f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -144,11 +144,19 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter,
 		ixgbe_txrx_ring_disable(adapter, qid);
 
 	err = ixgbe_add_xsk_umem(adapter, umem, qid);
+	if (err)
+		return err;
 
-	if (if_running)
+	if (if_running) {
 		ixgbe_txrx_ring_enable(adapter, qid);
 
-	return err;
+		/* Kick start the NAPI context so that receiving will start */
+		err = ixgbe_xsk_async_xmit(adapter->netdev, qid);
+		if (err)
+			return err;
+	}
+
+	return 0;
 }
 
 static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid)
@@ -617,7 +625,8 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 	dma_addr_t dma;
 
 	while (budget-- > 0) {
-		if (unlikely(!ixgbe_desc_unused(xdp_ring))) {
+		if (unlikely(!ixgbe_desc_unused(xdp_ring)) ||
+		    !netif_carrier_ok(xdp_ring->netdev)) {
 			work_done = false;
 			break;
 		}
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index d134d3538f9b..ff275780040f 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2148,7 +2148,7 @@ err_drop_frame:
 			if (unlikely(!skb))
 				goto err_drop_frame_ret_pool;
 
-			dma_sync_single_range_for_cpu(dev->dev.parent,
+			dma_sync_single_range_for_cpu(&pp->bm_priv->pdev->dev,
 			                              rx_desc->buf_phys_addr,
 			                              MVNETA_MH_SIZE + NET_SKB_PAD,
 			                              rx_bytes,
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 4d9d3806908e..f272247d1708 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -1291,15 +1291,10 @@ wrp_alu64_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 
 static int
 wrp_alu32_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
-	      enum alu_op alu_op, bool skip)
+	      enum alu_op alu_op)
 {
 	const struct bpf_insn *insn = &meta->insn;
 
-	if (skip) {
-		meta->flags |= FLAG_INSN_SKIP_NOOP;
-		return 0;
-	}
-
 	wrp_alu_imm(nfp_prog, insn->dst_reg * 2, alu_op, insn->imm);
 	wrp_immed(nfp_prog, reg_both(insn->dst_reg * 2 + 1), 0);
 
@@ -2322,7 +2317,7 @@ static int xor_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int xor_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_XOR, !~meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_XOR);
 }
 
 static int and_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2332,7 +2327,7 @@ static int and_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int and_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_AND, !~meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_AND);
 }
 
 static int or_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2342,7 +2337,7 @@ static int or_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int or_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_OR, !meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_OR);
 }
 
 static int add_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2352,7 +2347,7 @@ static int add_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int add_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_ADD, !meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_ADD);
 }
 
 static int sub_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2362,7 +2357,7 @@ static int sub_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int sub_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB, !meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB);
 }
 
 static int mul_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)