1 files changed, 441 insertions, 92 deletions

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 49b80da51ba7..0b6e30a8feb0 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2015 Cavium, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2 of the GNU General Public License
- * as published by the Free Software Foundation.
  */
 
 #include <linux/module.h>
@@ -20,15 +17,25 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/filter.h>
+#include <linux/net_tstamp.h>
+#include <linux/workqueue.h>
 
 #include "nic_reg.h"
 #include "nic.h"
 #include "nicvf_queues.h"
 #include "thunder_bgx.h"
+#include "../common/cavium_ptp.h"
 
-#define DRV_NAME	"thunder-nicvf"
+#define DRV_NAME	"nicvf"
 #define DRV_VERSION	"1.0"
 
+/* NOTE: Packets bigger than 1530 are split across multiple pages and XDP needs
+ * the buffer to be contiguous. Allow XDP to be set up only if we don't exceed
+ * this value, keeping headroom for the 14 byte Ethernet header and two
+ * VLAN tags (for QinQ)
+ */
+#define MAX_XDP_MTU	(1530 - ETH_HLEN - VLAN_HLEN * 2)
+
 /* Supported devices */
 static const struct pci_device_id nicvf_id_table[] = {
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM,
@@ -61,7 +68,7 @@ module_param(debug, int, 0644);
 MODULE_PARM_DESC(debug, "Debug message level bitmap");
 
 static int cpi_alg = CPI_ALG_NONE;
-module_param(cpi_alg, int, S_IRUGO);
+module_param(cpi_alg, int, 0444);
 MODULE_PARM_DESC(cpi_alg,
 		 "PFC algorithm (0=none, 1=VLAN, 2=VLAN16, 3=IP Diffserv)");
 
@@ -119,34 +126,39 @@ static void nicvf_write_to_mbx(struct nicvf *nic, union nic_mbx *mbx)
 
 int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx)
 {
-	int timeout = NIC_MBOX_MSG_TIMEOUT;
-	int sleep = 10;
+	unsigned long timeout;
+	int ret = 0;
+
+	mutex_lock(&nic->rx_mode_mtx);
 
 	nic->pf_acked = false;
 	nic->pf_nacked = false;
 
 	nicvf_write_to_mbx(nic, mbx);
 
+	timeout = jiffies + msecs_to_jiffies(NIC_MBOX_MSG_TIMEOUT);
 	/* Wait for previous message to be acked, timeout 2sec */
 	while (!nic->pf_acked) {
 		if (nic->pf_nacked) {
 			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);
+		usleep_range(8000, 10000);
 		if (nic->pf_acked)
 			break;
-		timeout -= sleep;
-		if (!timeout) {
+		if (time_after(jiffies, timeout)) {
 			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
@@ -166,6 +178,17 @@ 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)
@@ -198,8 +221,7 @@ static void  nicvf_handle_mbx_intr(struct nicvf *nic)
 		nic->tns_mode = mbx.nic_cfg.tns_mode & 0x7F;
 		nic->node = mbx.nic_cfg.node_id;
 		if (!nic->set_mac_pending)
-			ether_addr_copy(nic->netdev->dev_addr,
-					mbx.nic_cfg.mac_addr);
+			eth_hw_addr_set(nic->netdev, mbx.nic_cfg.mac_addr);
 		nic->sqs_mode = mbx.nic_cfg.sqs_mode;
 		nic->loopback_supported = mbx.nic_cfg.loopback_supported;
 		nic->link_up = false;
@@ -222,21 +244,24 @@ 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:
@@ -502,8 +527,9 @@ static int nicvf_init_resources(struct nicvf *nic)
 
 static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
 				struct cqe_rx_t *cqe_rx, struct snd_queue *sq,
-				struct sk_buff **skb)
+				struct rcv_queue *rq, struct sk_buff **skb)
 {
+	unsigned char *hard_start, *data;
 	struct xdp_buff xdp;
 	struct page *page;
 	u32 action;
@@ -521,18 +547,18 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
 	cpu_addr = (u64)phys_to_virt(cpu_addr);
 	page = virt_to_page((void *)cpu_addr);
 
-	xdp.data_hard_start = page_address(page);
-	xdp.data = (void *)cpu_addr;
-	xdp.data_end = xdp.data + len;
+	xdp_init_buff(&xdp, RCV_FRAG_LEN + XDP_PACKET_HEADROOM,
+		      &rq->xdp_rxq);
+	hard_start = page_address(page);
+	data = (unsigned char *)cpu_addr;
+	xdp_prepare_buff(&xdp, hard_start, data - hard_start, len, false);
 	orig_data = xdp.data;
 
-	rcu_read_lock();
 	action = bpf_prog_run_xdp(prog, &xdp);
-	rcu_read_unlock();
 
+	len = xdp.data_end - xdp.data;
 	/* Check if XDP program has changed headers */
 	if (orig_data != xdp.data) {
-		len = xdp.data_end - xdp.data;
 		offset = orig_data - xdp.data;
 		dma_addr -= offset;
 	}
@@ -564,9 +590,11 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
 		nicvf_xdp_sq_append_pkt(nic, sq, (u64)xdp.data, dma_addr, len);
 		return true;
 	default:
-		bpf_warn_invalid_xdp_action(action);
+		bpf_warn_invalid_xdp_action(nic->netdev, prog, action);
+		fallthrough;
 	case XDP_ABORTED:
 		trace_xdp_exception(nic->netdev, prog, action);
+		fallthrough;
 	case XDP_DROP:
 		/* Check if it's a recycled page, if not
 		 * unmap the DMA mapping.
@@ -586,6 +614,44 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
 	return false;
 }
 
+static void nicvf_snd_ptp_handler(struct net_device *netdev,
+				  struct cqe_send_t *cqe_tx)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+	struct skb_shared_hwtstamps ts;
+	u64 ns;
+
+	nic = nic->pnicvf;
+
+	/* Sync for 'ptp_skb' */
+	smp_rmb();
+
+	/* New timestamp request can be queued now */
+	atomic_set(&nic->tx_ptp_skbs, 0);
+
+	/* Check for timestamp requested skb */
+	if (!nic->ptp_skb)
+		return;
+
+	/* Check if timestamping is timedout, which is set to 10us */
+	if (cqe_tx->send_status == CQ_TX_ERROP_TSTMP_TIMEOUT ||
+	    cqe_tx->send_status == CQ_TX_ERROP_TSTMP_CONFLICT)
+		goto no_tstamp;
+
+	/* Get the timestamp */
+	memset(&ts, 0, sizeof(ts));
+	ns = cavium_ptp_tstamp2time(nic->ptp_clock, cqe_tx->ptp_timestamp);
+	ts.hwtstamp = ns_to_ktime(ns);
+	skb_tstamp_tx(nic->ptp_skb, &ts);
+
+no_tstamp:
+	/* Free the original skb */
+	dev_kfree_skb_any(nic->ptp_skb);
+	nic->ptp_skb = NULL;
+	/* Sync 'ptp_skb' */
+	smp_wmb();
+}
+
 static void nicvf_snd_pkt_handler(struct net_device *netdev,
 				  struct cqe_send_t *cqe_tx,
 				  int budget, int *subdesc_cnt,
@@ -642,7 +708,12 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev,
 		prefetch(skb);
 		(*tx_pkts)++;
 		*tx_bytes += skb->len;
-		napi_consume_skb(skb, budget);
+		/* If timestamp is requested for this skb, don't free it */
+		if (skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS &&
+		    !nic->pnicvf->ptp_skb)
+			nic->pnicvf->ptp_skb = skb;
+		else
+			napi_consume_skb(skb, budget);
 		sq->skbuff[cqe_tx->sqe_ptr] = (u64)NULL;
 	} else {
 		/* In case of SW TSO on 88xx, only last segment will have
@@ -681,9 +752,25 @@ static inline void nicvf_set_rxhash(struct net_device *netdev,
 	skb_set_hash(skb, hash, hash_type);
 }
 
+static inline void nicvf_set_rxtstamp(struct nicvf *nic, struct sk_buff *skb)
+{
+	u64 ns;
+
+	if (!nic->ptp_clock || !nic->hw_rx_tstamp)
+		return;
+
+	/* The first 8 bytes is the timestamp */
+	ns = cavium_ptp_tstamp2time(nic->ptp_clock,
+				    be64_to_cpu(*(__be64 *)skb->data));
+	skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(ns);
+
+	__skb_pull(skb, 8);
+}
+
 static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 				  struct napi_struct *napi,
-				  struct cqe_rx_t *cqe_rx, struct snd_queue *sq)
+				  struct cqe_rx_t *cqe_rx,
+				  struct snd_queue *sq, struct rcv_queue *rq)
 {
 	struct sk_buff *skb = NULL;
 	struct nicvf *nic = netdev_priv(netdev);
@@ -709,7 +796,7 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 	/* For XDP, ignore pkts spanning multiple pages */
 	if (nic->xdp_prog && (cqe_rx->rb_cnt == 1)) {
 		/* Packet consumed by XDP */
-		if (nicvf_xdp_rx(snic, nic->xdp_prog, cqe_rx, sq, &skb))
+		if (nicvf_xdp_rx(snic, nic->xdp_prog, cqe_rx, sq, rq, &skb))
 			return;
 	} else {
 		skb = nicvf_get_rcv_skb(snic, cqe_rx,
@@ -731,6 +818,7 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 		return;
 	}
 
+	nicvf_set_rxtstamp(nic, skb);
 	nicvf_set_rxhash(netdev, cqe_rx, skb);
 
 	skb_record_rx_queue(skb, rq_idx);
@@ -766,6 +854,7 @@ static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
 	struct cqe_rx_t *cq_desc;
 	struct netdev_queue *txq;
 	struct snd_queue *sq = &qs->sq[cq_idx];
+	struct rcv_queue *rq = &qs->rq[cq_idx];
 	unsigned int tx_pkts = 0, tx_bytes = 0, txq_idx;
 
 	spin_lock_bh(&cq->lock);
@@ -796,7 +885,7 @@ loop:
 
 		switch (cq_desc->cqe_type) {
 		case CQE_TYPE_RX:
-			nicvf_rcv_pkt_handler(netdev, napi, cq_desc, sq);
+			nicvf_rcv_pkt_handler(netdev, napi, cq_desc, sq, rq);
 			work_done++;
 		break;
 		case CQE_TYPE_SEND:
@@ -805,10 +894,12 @@ loop:
 					      &tx_pkts, &tx_bytes);
 			tx_done++;
 		break;
+		case CQE_TYPE_SEND_PTP:
+			nicvf_snd_ptp_handler(netdev, (void *)cq_desc);
+		break;
 		case CQE_TYPE_INVALID:
 		case CQE_TYPE_RX_SPLIT:
 		case CQE_TYPE_RX_TCP:
-		case CQE_TYPE_SEND_PTP:
 			/* Ignore for now */
 		break;
 		}
@@ -891,9 +982,9 @@ static int nicvf_poll(struct napi_struct *napi, int budget)
  *
  * As of now only CQ errors are handled
  */
-static void nicvf_handle_qs_err(unsigned long data)
+static void nicvf_handle_qs_err(struct tasklet_struct *t)
 {
-	struct nicvf *nic = (struct nicvf *)data;
+	struct nicvf *nic = from_tasklet(nic, t, qs_err_task);
 	struct queue_set *qs = nic->qs;
 	int qidx;
 	u64 status;
@@ -1132,7 +1223,7 @@ static int nicvf_register_misc_interrupt(struct nicvf *nic)
 	if (ret < 0) {
 		netdev_err(nic->netdev,
 			   "Req for #%d msix vectors failed\n", nic->num_vec);
-		return 1;
+		return ret;
 	}
 
 	sprintf(nic->irq_name[irq], "%s Mbox", "NICVF");
@@ -1151,7 +1242,7 @@ static int nicvf_register_misc_interrupt(struct nicvf *nic)
 	if (!nicvf_check_pf_ready(nic)) {
 		nicvf_disable_intr(nic, NICVF_INTR_MBOX, 0);
 		nicvf_unregister_interrupts(nic);
-		return 1;
+		return -EIO;
 	}
 
 	return 0;
@@ -1238,6 +1329,12 @@ int nicvf_stop(struct net_device *netdev)
 	struct nicvf_cq_poll *cq_poll = NULL;
 	union nic_mbx mbx = {};
 
+	/* wait till all queued set_rx_mode tasks completes */
+	if (nic->nicvf_rx_mode_wq) {
+		cancel_delayed_work_sync(&nic->link_change_work);
+		drain_workqueue(nic->nicvf_rx_mode_wq);
+	}
+
 	mbx.msg.msg = NIC_MBOX_MSG_SHUTDOWN;
 	nicvf_send_msg_to_pf(nic, &mbx);
 
@@ -1304,12 +1401,28 @@ int nicvf_stop(struct net_device *netdev)
 
 	nicvf_free_cq_poll(nic);
 
+	/* Free any pending SKB saved to receive timestamp */
+	if (nic->ptp_skb) {
+		dev_kfree_skb_any(nic->ptp_skb);
+		nic->ptp_skb = NULL;
+	}
+
 	/* Clear multiqset info */
 	nic->pnicvf = nic;
 
 	return 0;
 }
 
+static int nicvf_config_hw_rx_tstamp(struct nicvf *nic, bool enable)
+{
+	union nic_mbx mbx = {};
+
+	mbx.ptp.msg = NIC_MBOX_MSG_PTP_CFG;
+	mbx.ptp.enable = enable;
+
+	return nicvf_send_msg_to_pf(nic, &mbx);
+}
+
 static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu)
 {
 	union nic_mbx mbx = {};
@@ -1321,13 +1434,28 @@ 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 */
+	if (nic->nicvf_rx_mode_wq)
+		drain_workqueue(nic->nicvf_rx_mode_wq);
 
 	netif_carrier_off(netdev);
 
@@ -1344,8 +1472,7 @@ int nicvf_open(struct net_device *netdev)
 		}
 		cq_poll->cq_idx = qidx;
 		cq_poll->nicvf = nic;
-		netif_napi_add(netdev, &cq_poll->napi, nicvf_poll,
-			       NAPI_POLL_WEIGHT);
+		netif_napi_add(netdev, &cq_poll->napi, nicvf_poll);
 		napi_enable(&cq_poll->napi);
 		nic->napi[qidx] = cq_poll;
 	}
@@ -1362,12 +1489,10 @@ int nicvf_open(struct net_device *netdev)
 	}
 
 	/* Init tasklet for handling Qset err interrupt */
-	tasklet_init(&nic->qs_err_task, nicvf_handle_qs_err,
-		     (unsigned long)nic);
+	tasklet_setup(&nic->qs_err_task, nicvf_handle_qs_err);
 
 	/* Init RBDR tasklet which will refill RBDR */
-	tasklet_init(&nic->rbdr_task, nicvf_rbdr_task,
-		     (unsigned long)nic);
+	tasklet_setup(&nic->rbdr_task, nicvf_rbdr_task);
 	INIT_DELAYED_WORK(&nic->rbdr_work, nicvf_rbdr_work);
 
 	/* Configure CPI alorithm */
@@ -1379,6 +1504,12 @@ int nicvf_open(struct net_device *netdev)
 	if (nic->sqs_mode)
 		nicvf_get_primary_vf_struct(nic);
 
+	/* Configure PTP timestamp */
+	if (nic->ptp_clock)
+		nicvf_config_hw_rx_tstamp(nic, nic->hw_rx_tstamp);
+	atomic_set(&nic->tx_ptp_skbs, 0);
+	nic->ptp_skb = NULL;
+
 	/* Configure receive side scaling and MTU */
 	if (!nic->sqs_mode) {
 		nicvf_rss_init(nic);
@@ -1417,8 +1548,14 @@ 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);
+
+	if (nic->nicvf_rx_mode_wq) {
+		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:
@@ -1441,18 +1578,21 @@ napi_del:
 static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct nicvf *nic = netdev_priv(netdev);
-	int orig_mtu = netdev->mtu;
-
-	netdev->mtu = new_mtu;
-
-	if (!netif_running(netdev))
-		return 0;
 
-	if (nicvf_update_hw_max_frs(nic, new_mtu)) {
-		netdev->mtu = orig_mtu;
+	/* For now just support only the usual MTU sized frames,
+	 * plus some headroom for VLAN, QinQ.
+	 */
+	if (nic->xdp_prog && new_mtu > MAX_XDP_MTU) {
+		netdev_warn(netdev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
+			    netdev->mtu);
 		return -EINVAL;
 	}
 
+	if (netif_running(netdev) && nicvf_update_hw_max_frs(nic, new_mtu))
+		return -EINVAL;
+
+	WRITE_ONCE(netdev->mtu, new_mtu);
+
 	return 0;
 }
 
@@ -1464,7 +1604,7 @@ static int nicvf_set_mac_address(struct net_device *netdev, void *p)
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
-	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
+	eth_hw_addr_set(netdev, addr->sa_data);
 
 	if (nic->pdev->msix_enabled) {
 		if (nicvf_hw_set_mac_addr(nic, netdev))
@@ -1589,7 +1729,7 @@ static void nicvf_get_stats64(struct net_device *netdev,
 
 }
 
-static void nicvf_tx_timeout(struct net_device *dev)
+static void nicvf_tx_timeout(struct net_device *dev, unsigned int txqueue)
 {
 	struct nicvf *nic = netdev_priv(dev);
 
@@ -1689,9 +1829,12 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
 	bool if_up = netif_running(nic->netdev);
 	struct bpf_prog *old_prog;
 	bool bpf_attached = false;
+	int ret = 0;
 
-	/* For now just support only the usual MTU sized frames */
-	if (prog && (dev->mtu > 1500)) {
+	/* For now just support only the usual MTU sized frames,
+	 * plus some headroom for VLAN, QinQ.
+	 */
+	if (prog && dev->mtu > MAX_XDP_MTU) {
 		netdev_warn(dev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
 			    dev->mtu);
 		return -EOPNOTSUPP;
@@ -1721,9 +1864,8 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
 
 	if (nic->xdp_prog) {
 		/* Attach BPF program */
-		nic->xdp_prog = bpf_prog_add(nic->xdp_prog, nic->rx_queues - 1);
-		if (!IS_ERR(nic->xdp_prog))
-			bpf_attached = true;
+		bpf_prog_add(nic->xdp_prog, nic->rx_queues - 1);
+		bpf_attached = true;
 	}
 
 	/* Calculate Tx queues needed for XDP and network stack */
@@ -1735,10 +1877,10 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
 		netif_trans_update(nic->netdev);
 	}
 
-	return 0;
+	return ret;
 }
 
-static int nicvf_xdp(struct net_device *netdev, struct netdev_xdp *xdp)
+static int nicvf_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 {
 	struct nicvf *nic = netdev_priv(netdev);
 
@@ -1752,15 +1894,186 @@ static int nicvf_xdp(struct net_device *netdev, struct netdev_xdp *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return nicvf_xdp_setup(nic, xdp->prog);
-	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!nic->xdp_prog;
-		xdp->prog_id = nic->xdp_prog ? nic->xdp_prog->aux->id : 0;
-		return 0;
 	default:
 		return -EINVAL;
 	}
 }
 
+static int nicvf_hwtstamp_set(struct net_device *netdev,
+			      struct kernel_hwtstamp_config *config,
+			      struct netlink_ext_ack *extack)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+
+	if (!nic->ptp_clock) {
+		NL_SET_ERR_MSG_MOD(extack, "HW timestamping is not supported");
+		return -ENODEV;
+	}
+
+	switch (config->tx_type) {
+	case HWTSTAMP_TX_OFF:
+	case HWTSTAMP_TX_ON:
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	switch (config->rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		nic->hw_rx_tstamp = false;
+		break;
+	case HWTSTAMP_FILTER_ALL:
+	case HWTSTAMP_FILTER_SOME:
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+		nic->hw_rx_tstamp = true;
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	if (netif_running(netdev))
+		nicvf_config_hw_rx_tstamp(nic, nic->hw_rx_tstamp);
+
+	return 0;
+}
+
+static int nicvf_hwtstamp_get(struct net_device *netdev,
+			      struct kernel_hwtstamp_config *config)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+
+	if (!nic->ptp_clock)
+		return -ENODEV;
+
+	/* TX timestamping is technically always on */
+	config->tx_type = HWTSTAMP_TX_ON;
+	config->rx_filter = nic->hw_rx_tstamp ?
+			    HWTSTAMP_FILTER_ALL :
+			    HWTSTAMP_FILTER_NONE;
+
+	return 0;
+}
+
+static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs,
+				     struct nicvf *nic)
+{
+	union nic_mbx mbx = {};
+	int idx;
+
+	/* From the inside of VM code flow we have only 128 bits memory
+	 * available to send message to host's PF, so send all mc addrs
+	 * one by one, starting from flush command in case if kernel
+	 * requests to configure specific MAC filtering
+	 */
+
+	/* flush DMAC filters and reset RX mode */
+	mbx.xcast.msg = NIC_MBOX_MSG_RESET_XCAST;
+	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.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 */
+	if (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.mac = mc_addrs->mc[idx];
+			if (nicvf_send_msg_to_pf(nic, &mbx) < 0)
+				goto free_mc;
+		}
+	}
+
+	/* and finally set rx mode for PF accordingly */
+	mbx.xcast.msg = NIC_MBOX_MSG_SET_XCAST;
+	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);
+	struct nicvf *nic = container_of(vf_work, struct nicvf, rx_mode_work);
+	u8 mode;
+	struct xcast_addr_list *mc;
+
+	/* Save message data locally to prevent them from
+	 * being overwritten by next ndo_set_rx_mode call().
+	 */
+	spin_lock_bh(&nic->rx_mode_wq_lock);
+	mode = vf_work->mode;
+	mc = vf_work->mc;
+	vf_work->mc = NULL;
+	spin_unlock_bh(&nic->rx_mode_wq_lock);
+
+	__nicvf_set_rx_mode_task(mode, mc, nic);
+}
+
+static void nicvf_set_rx_mode(struct net_device *netdev)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+	struct netdev_hw_addr *ha;
+	struct xcast_addr_list *mc_list = NULL;
+	u8 mode = 0;
+
+	if (netdev->flags & IFF_PROMISC) {
+		mode = BGX_XCAST_BCAST_ACCEPT | BGX_XCAST_MCAST_ACCEPT;
+	} else {
+		if (netdev->flags & IFF_BROADCAST)
+			mode |= BGX_XCAST_BCAST_ACCEPT;
+
+		if (netdev->flags & IFF_ALLMULTI) {
+			mode |= BGX_XCAST_MCAST_ACCEPT;
+		} else if (netdev->flags & IFF_MULTICAST) {
+			mode |= BGX_XCAST_MCAST_FILTER;
+			/* here we need to copy mc addrs */
+			if (netdev_mc_count(netdev)) {
+				mc_list = kmalloc(struct_size(mc_list, mc,
+							      netdev_mc_count(netdev)),
+						  GFP_ATOMIC);
+				if (unlikely(!mc_list))
+					return;
+				mc_list->count = 0;
+				netdev_hw_addr_list_for_each(ha, &netdev->mc) {
+					mc_list->mc[mc_list->count] =
+						ether_addr_to_u64(ha->addr);
+					mc_list->count++;
+				}
+			}
+		}
+	}
+	spin_lock(&nic->rx_mode_wq_lock);
+	kfree(nic->rx_mode_work.mc);
+	nic->rx_mode_work.mc = mc_list;
+	nic->rx_mode_work.mode = mode;
+	queue_work(nic->nicvf_rx_mode_wq, &nic->rx_mode_work.work);
+	spin_unlock(&nic->rx_mode_wq_lock);
+}
+
 static const struct net_device_ops nicvf_netdev_ops = {
 	.ndo_open		= nicvf_open,
 	.ndo_stop		= nicvf_stop,
@@ -1771,7 +2084,10 @@ static const struct net_device_ops nicvf_netdev_ops = {
 	.ndo_tx_timeout         = nicvf_tx_timeout,
 	.ndo_fix_features       = nicvf_fix_features,
 	.ndo_set_features       = nicvf_set_features,
-	.ndo_xdp		= nicvf_xdp,
+	.ndo_bpf		= nicvf_xdp,
+	.ndo_set_rx_mode        = nicvf_set_rx_mode,
+	.ndo_hwtstamp_get	= nicvf_hwtstamp_get,
+	.ndo_hwtstamp_set	= nicvf_hwtstamp_set,
 };
 
 static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
@@ -1781,31 +2097,33 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct nicvf *nic;
 	int    err, qcount;
 	u16    sdevid;
+	struct cavium_ptp *ptp_clock;
 
-	err = pci_enable_device(pdev);
-	if (err) {
-		dev_err(dev, "Failed to enable PCI device\n");
-		return err;
+	ptp_clock = cavium_ptp_get();
+	if (IS_ERR(ptp_clock)) {
+		if (PTR_ERR(ptp_clock) == -ENODEV)
+			/* In virtualized environment we proceed without ptp */
+			ptp_clock = NULL;
+		else
+			return PTR_ERR(ptp_clock);
 	}
 
+	err = pci_enable_device(pdev);
+	if (err)
+		return dev_err_probe(dev, err, "Failed to enable PCI device\n");
+
 	err = pci_request_regions(pdev, DRV_NAME);
 	if (err) {
 		dev_err(dev, "PCI request regions failed 0x%x\n", err);
 		goto err_disable_device;
 	}
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(48));
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(48));
 	if (err) {
 		dev_err(dev, "Unable to get usable DMA configuration\n");
 		goto err_release_regions;
 	}
 
-	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(48));
-	if (err) {
-		dev_err(dev, "unable to get 48-bit DMA for consistent allocations\n");
-		goto err_release_regions;
-	}
-
 	qcount = netif_get_num_default_rss_queues();
 
 	/* Restrict multiqset support only for host bound VFs */
@@ -1830,6 +2148,15 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	nic->pdev = pdev;
 	nic->pnicvf = nic;
 	nic->max_queues = qcount;
+	/* If no of CPUs are too low, there won't be any queues left
+	 * for XDP_TX, hence double it.
+	 */
+	if (!nic->t88)
+		nic->max_queues *= 2;
+	nic->ptp_clock = ptp_clock;
+
+	/* Initialize mutex that serializes usage of VF's mailbox */
+	mutex_init(&nic->rx_mode_mtx);
 
 	/* MAP VF's configuration registers */
 	nic->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0);
@@ -1890,16 +2217,32 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	netdev->netdev_ops = &nicvf_netdev_ops;
 	netdev->watchdog_timeo = NICVF_TX_TIMEOUT;
 
+	if (!pass1_silicon(nic->pdev) &&
+	    nic->rx_queues + nic->tx_queues <= nic->max_queues)
+		netdev->xdp_features = NETDEV_XDP_ACT_BASIC;
+
 	/* MTU range: 64 - 9200 */
 	netdev->min_mtu = NIC_HW_MIN_FRS;
 	netdev->max_mtu = NIC_HW_MAX_FRS;
 
 	INIT_WORK(&nic->reset_task, nicvf_reset_task);
 
+	nic->nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_rx_mode_wq_VF%d",
+							WQ_MEM_RECLAIM,
+							nic->vf_id);
+	if (!nic->nicvf_rx_mode_wq) {
+		err = -ENOMEM;
+		dev_err(dev, "Failed to allocate work queue\n");
+		goto err_unregister_interrupts;
+	}
+
+	INIT_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task);
+	spin_lock_init(&nic->rx_mode_wq_lock);
+
 	err = register_netdev(netdev);
 	if (err) {
 		dev_err(dev, "Failed to register netdevice\n");
-		goto err_unregister_interrupts;
+		goto err_destroy_workqueue;
 	}
 
 	nic->msg_enable = debug;
@@ -1908,6 +2251,8 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	return 0;
 
+err_destroy_workqueue:
+	destroy_workqueue(nic->nicvf_rx_mode_wq);
 err_unregister_interrupts:
 	nicvf_unregister_interrupts(nic);
 err_free_netdev:
@@ -1939,10 +2284,15 @@ static void nicvf_remove(struct pci_dev *pdev)
 	 */
 	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)
 		free_percpu(nic->drv_stats);
+	cavium_ptp_put(nic->ptp_clock);
 	free_netdev(netdev);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
@@ -1964,7 +2314,6 @@ static struct pci_driver nicvf_driver = {
 static int __init nicvf_init_module(void)
 {
 	pr_info("%s, ver %s\n", DRV_NAME, DRV_VERSION);
-
 	return pci_register_driver(&nicvf_driver);
 }