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

Pull networking fixes from David Miller:
 "Hopefully the last pull request for this release. Fingers crossed:

   1) Only refcount ESP stats on full sockets, from Martin Willi.

   2) Missing barriers in AF_UNIX, from Al Viro.

   3) RCU protection fixes in ipv6 route code, from Paolo Abeni.

   4) Avoid false positives in untrusted GSO validation, from Willem de
      Bruijn.

   5) Forwarded mesh packets in mac80211 need more tailroom allocated,
      from Felix Fietkau.

   6) Use operstate consistently for linkup in team driver, from George
      Wilkie.

   7) ThunderX bug fixes from Vadim Lomovtsev. Mostly races between VF
      and PF code paths.

   8) Purge ipv6 exceptions during netdevice removal, from Paolo Abeni.

   9) nfp eBPF code gen fixes from Jiong Wang.

  10) bnxt_en firmware timeout fix from Michael Chan.

  11) Use after free in udp/udpv6 error handlers, from Paolo Abeni.

  12) Fix a race in x25_bind triggerable by syzbot, from Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (65 commits)
  net: phy: realtek: Dummy IRQ calls for RTL8366RB
  tcp: repaired skbs must init their tso_segs
  net/x25: fix a race in x25_bind()
  net: dsa: Remove documentation for port_fdb_prepare
  Revert "bridge: do not add port to router list when receives query with source 0.0.0.0"
  selftests: fib_tests: sleep after changing carrier. again.
  net: set static variable an initial value in atl2_probe()
  net: phy: marvell10g: Fix Multi-G advertisement to only advertise 10G
  bpf, doc: add bpf list as secondary entry to maintainers file
  udp: fix possible user after free in error handler
  udpv6: fix possible user after free in error handler
  fou6: fix proto error handler argument type
  udpv6: add the required annotation to mib type
  mdio_bus: Fix use-after-free on device_register fails
  net: Set rtm_table to RT_TABLE_COMPAT for ipv6 for tables > 255
  bnxt_en: Wait longer for the firmware message response to complete.
  bnxt_en: Fix typo in firmware message timeout logic.
  nfp: bpf: fix ALU32 high bits clearance bug
  nfp: bpf: fix code-gen bug on BPF_ALU | BPF_XOR | BPF_K
  Documentation: networking: switchdev: Update port parent ID section
  ...

24 files changed, 250 insertions, 208 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 485462d3087f..537c90c8eb0a 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1183,29 +1183,22 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 		}
 	}
 
-	/* Link-local multicast packets should be passed to the
-	 * stack on the link they arrive as well as pass them to the
-	 * bond-master device. These packets are mostly usable when
-	 * stack receives it with the link on which they arrive
-	 * (e.g. LLDP) they also must be available on master. Some of
-	 * the use cases include (but are not limited to): LLDP agents
-	 * that must be able to operate both on enslaved interfaces as
-	 * well as on bonds themselves; linux bridges that must be able
-	 * to process/pass BPDUs from attached bonds when any kind of
-	 * STP version is enabled on the network.
+	/*
+	 * For packets determined by bond_should_deliver_exact_match() call to
+	 * be suppressed we want to make an exception for link-local packets.
+	 * This is necessary for e.g. LLDP daemons to be able to monitor
+	 * inactive slave links without being forced to bind to them
+	 * explicitly.
+	 *
+	 * At the same time, packets that are passed to the bonding master
+	 * (including link-local ones) can have their originating interface
+	 * determined via PACKET_ORIGDEV socket option.
 	 */
-	if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) {
-		struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
-
-		if (nskb) {
-			nskb->dev = bond->dev;
-			nskb->queue_mapping = 0;
-			netif_rx(nskb);
-		}
-		return RX_HANDLER_PASS;
-	}
-	if (bond_should_deliver_exact_match(skb, slave, bond))
+	if (bond_should_deliver_exact_match(skb, slave, bond)) {
+		if (is_link_local_ether_addr(eth_hdr(skb)->h_dest))
+			return RX_HANDLER_PASS;
 		return RX_HANDLER_EXACT;
+	}
 
 	skb->dev = bond->dev;
 
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index bb41becb6609..31ff1e0d1baa 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 8bc7e495b027..d95730c6e0f2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3903,7 +3903,7 @@ 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
@@ -3926,7 +3926,7 @@ 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 a451796deefe..2fb653e0048d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -582,7 +582,7 @@ 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/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index f52e2c46e6a7..e4ff531db14a 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]);
 	}
 
@@ -11895,6 +11903,14 @@ 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;
 }
 
@@ -11955,8 +11971,13 @@ 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 (unlike