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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

10 files changed, 461 insertions, 46 deletions

diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index 4a02e618e318..4cacce5d2b16 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -263,6 +263,8 @@ struct nicvf_drv_stats {
 	struct u64_stats_sync   syncp;
 };
 
+struct cavium_ptp;
+
 struct nicvf {
 	struct nicvf		*pnicvf;
 	struct net_device	*netdev;
@@ -312,6 +314,33 @@ struct nicvf {
 	struct tasklet_struct	qs_err_task;
 	struct work_struct	reset_task;
 
+	/* PTP timestamp */
+	struct cavium_ptp	*ptp_clock;
+	/* Inbound timestamping is on */
+	bool			hw_rx_tstamp;
+	/* When the packet that requires timestamping is sent, hardware inserts
+	 * two entries to the completion queue.  First is the regular
+	 * CQE_TYPE_SEND entry that signals that the packet was sent.
+	 * The second is CQE_TYPE_SEND_PTP that contains the actual timestamp
+	 * for that packet.
+	 * `ptp_skb` is initialized in the handler for the CQE_TYPE_SEND
+	 * entry and is used and zeroed in the handler for the CQE_TYPE_SEND_PTP
+	 * entry.
+	 * So `ptp_skb` is used to hold the pointer to the packet between
+	 * the calls to CQE_TYPE_SEND and CQE_TYPE_SEND_PTP handlers.
+	 */
+	struct sk_buff		*ptp_skb;
+	/* `tx_ptp_skbs` is set when the hardware is sending a packet that
+	 * requires timestamping.  Cavium hardware can not process more than one
+	 * such packet at once so this is set each time the driver submits
+	 * a packet that requires timestamping to the send queue and clears
+	 * each time it receives the entry on the completion queue saying
+	 * that such packet was sent.
+	 * So `tx_ptp_skbs` prevents driver from submitting more than one
+	 * packet that requires timestamping to the hardware for transmitting.
+	 */
+	atomic_t		tx_ptp_skbs;
+
 	/* Interrupt coalescing settings */
 	u32			cq_coalesce_usecs;
 	u32			msg_enable;
@@ -371,6 +400,7 @@ struct nicvf {
 #define	NIC_MBOX_MSG_LOOPBACK		0x16	/* Set interface in loopback */
 #define	NIC_MBOX_MSG_RESET_STAT_COUNTER 0x17	/* Reset statistics counters */
 #define	NIC_MBOX_MSG_PFC		0x18	/* Pause frame control */
+#define	NIC_MBOX_MSG_PTP_CFG		0x19	/* HW packet timestamp */
 #define	NIC_MBOX_MSG_CFG_DONE		0xF0	/* VF configuration done */
 #define	NIC_MBOX_MSG_SHUTDOWN		0xF1	/* VF is being shutdown */
 
@@ -521,6 +551,11 @@ struct pfc {
 	u8    fc_tx;
 };
 
+struct set_ptp {
+	u8    msg;
+	bool  enable;
+};
+
 /* 128 bit shared memory between PF and each VF */
 union nic_mbx {
 	struct { u8 msg; }	msg;
@@ -540,6 +575,7 @@ union nic_mbx {
 	struct set_loopback	lbk;
 	struct reset_stat_cfg	reset_stat;
 	struct pfc		pfc;
+	struct set_ptp		ptp;
 };
 
 #define NIC_NODE_ID_MASK	0x03
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 8f1dd55b3e08..7ff66a8194e2 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -18,7 +18,7 @@
 #include "q_struct.h"
 #include "thunder_bgx.h"
 
-#define DRV_NAME	"thunder-nic"
+#define DRV_NAME	"nicpf"
 #define DRV_VERSION	"1.0"
 
 struct hw_info {
@@ -426,13 +426,22 @@ static void nic_init_hw(struct nicpf *nic)
 	/* Enable backpressure */
 	nic_reg_write(nic, NIC_PF_BP_CFG, (1ULL << 6) | 0x03);
 
-	/* TNS and TNS bypass modes are present only on 88xx */
+	/* TNS and TNS bypass modes are present only on 88xx
+	 * Also offset of this CSR has changed in 81xx and 83xx.
+	 */
 	if (nic->pdev->subsystem_device == PCI_SUBSYS_DEVID_88XX_NIC_PF) {
 		/* Disable TNS mode on both interfaces */
 		nic_reg_write(nic, NIC_PF_INTF_0_1_SEND_CFG,
-			      (NIC_TNS_BYPASS_MODE << 7) | BGX0_BLOCK);
+			      (NIC_TNS_BYPASS_MODE << 7) |
+			      BGX0_BLOCK | (1ULL << 16));
 		nic_reg_write(nic, NIC_PF_INTF_0_1_SEND_CFG | (1 << 8),
-			      (NIC_TNS_BYPASS_MODE << 7) | BGX1_BLOCK);
+			      (NIC_TNS_BYPASS_MODE << 7) |
+			      BGX1_BLOCK | (1ULL << 16));
+	} else {
+		/* Configure timestamp generation timeout to 10us */
+		for (i = 0; i < nic->hw->bgx_cnt; i++)
+			nic_reg_write(nic, NIC_PF_INTFX_SEND_CFG | (i << 3),
+				      (1ULL << 16));
 	}
 
 	nic_reg_write(nic, NIC_PF_INTF_0_1_BP_CFG,
@@ -880,6 +889,44 @@ static void nic_pause_frame(struct nicpf *nic, int vf, struct pfc *cfg)
 	}
 }
 
+/* Enable or disable HW timestamping by BGX for pkts received on a LMAC */
+static void nic_config_timestamp(struct nicpf *nic, int vf, struct set_ptp *ptp)
+{
+	struct pkind_cfg *pkind;
+	u8 lmac, bgx_idx;
+	u64 pkind_val, pkind_idx;
+
+	if (vf >= nic->num_vf_en)
+		return;
+
+	bgx_idx = 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]);
+
+	pkind_idx = lmac + bgx_idx * MAX_LMAC_PER_BGX;
+	pkind_val = nic_reg_read(nic, NIC_PF_PKIND_0_15_CFG | (pkind_idx << 3));
+	pkind = (struct pkind_cfg *)&pkind_val;
+
+	if (ptp->enable && !pkind->hdr_sl) {
+		/* Skiplen to exclude 8byte timestamp while parsing pkt
+		 * If not configured, will result in L2 errors.
+		 */
+		pkind->hdr_sl = 4;
+		/* Adjust max packet length allowed */
+		pkind->maxlen += (pkind->hdr_sl * 2);
+		bgx_config_timestamping(nic->node, bgx_idx, lmac, true);
+		nic_reg_write(nic, NIC_PF_RX_ETYPE_0_7 | (1 << 3),
+			      (ETYPE_ALG_ENDPARSE << 16) | ETH_P_1588);
+	} else if (!ptp->enable && pkind->hdr_sl) {
+		pkind->maxlen -= (pkind->hdr_sl * 2);
+		pkind->hdr_sl = 0;
+		bgx_config_timestamping(nic->node, bgx_idx, lmac, false);
+		nic_reg_write(nic, NIC_PF_RX_ETYPE_0_7 | (1 << 3),
+			      (ETYPE_ALG_SKIP << 16) | ETH_P_8021Q);
+	}
+
+	nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG | (pkind_idx << 3), pkind_val);
+}
+
 /* Interrupt handler to handle mailbox messages from VFs */
 static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 {
@@ -1022,6 +1069,9 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 	case NIC_MBOX_MSG_PFC:
 		nic_pause_frame(nic, vf, &mbx.pfc);
 		goto unlock;
+	case NIC_MBOX_MSG_PTP_CFG:
+		nic_config_timestamp(nic, vf, &mbx.ptp);
+		break;
 	default:
 		dev_err(&nic->pdev->dev,
 			"Invalid msg from VF%d, msg 0x%x\n", vf, mbx.msg.msg);
diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h
index 80d46337cf29..a16c48a1ebb2 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_reg.h
+++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h
@@ -99,6 +99,7 @@
 #define   NIC_PF_ECC3_DBE_INT_W1S		(0x2708)
 #define   NIC_PF_ECC3_DBE_ENA_W1C		(0x2710)
 #define   NIC_PF_ECC3_DBE_ENA_W1S		(0x2718)
+#define   NIC_PF_INTFX_SEND_CFG			(0x4000)
 #define   NIC_PF_MCAM_0_191_ENA			(0x100000)
 #define   NIC_PF_MCAM_0_191_M_0_5_DATA		(0x110000)
 #define   NIC_PF_MCAM_CTRL			(0x120000)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index b9ece9cbf98b..5603f5ab1fee 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -9,14 +9,16 @@
 /* ETHTOOL Support for VNIC_VF Device*/
 
 #include <linux/pci.h>
+#include <linux/net_tstamp.h>
 
 #include "nic_reg.h"
 #include "nic.h"
 #include "nicvf_queues.h"
 #include "q_struct.h"
 #include "thunder_bgx.h"
+#include "../common/cavium_ptp.h"
 
-#define DRV_NAME	"thunder-nicvf"
+#define DRV_NAME	"nicvf"
 #define DRV_VERSION     "1.0"
 
 struct nicvf_stat {
@@ -824,6 +826,31 @@ static int nicvf_set_pauseparam(struct net_device *dev,
 	return 0;
 }
 
+static int nicvf_get_ts_info(struct net_device *netdev,
+			     struct ethtool_ts_info *info)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+
+	if (!nic->ptp_clock)
+		return ethtool_op_get_ts_info(netdev, info);
+
+	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+				SOF_TIMESTAMPING_RX_SOFTWARE |
+				SOF_TIMESTAMPING_SOFTWARE |
+				SOF_TIMESTAMPING_TX_HARDWARE |
+				SOF_TIMESTAMPING_RX_HARDWARE |
+				SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	info->phc_index = cavium_ptp_clock_index(nic->ptp_clock);
+
+	info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON);
+
+	info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
+			   (1 << HWTSTAMP_FILTER_ALL);
+
+	return 0;
+}
+
 static const struct ethtool_ops nicvf_ethtool_ops = {
 	.get_link		= nicvf_get_link,
 	.get_drvinfo		= nicvf_get_drvinfo,
@@ -847,7 +874,7 @@ static const struct ethtool_ops nicvf_ethtool_ops = {
 	.set_channels		= nicvf_set_channels,
 	.get_pauseparam         = nicvf_get_pauseparam,
 	.set_pauseparam         = nicvf_set_pauseparam,
-	.get_ts_info		= ethtool_op_get_ts_info,
+	.get_ts_info		= nicvf_get_ts_info,
 	.get_link_ksettings	= nicvf_get_link_ksettings,
 };
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index a063c36c4c58..b68cde9f17d2 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -20,13 +20,15 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/filter.h>
+#include <linux/net_tstamp.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"
 
 /* Supported devices */
@@ -65,6 +67,11 @@ module_param(cpi_alg, int, S_IRUGO);
 MODULE_PARM_DESC(cpi_alg,
 		 "PFC algorithm (0=none, 1=VLAN, 2=VLAN16, 3=IP Diffserv)");
 
+struct nicvf_xdp_tx {
+	u64 dma_addr;
+	u8  qidx;
+};
+
 static inline u8 nicvf_netdev_qidx(struct nicvf *nic, u8 qidx)
 {
 	if (nic->sqs_mode)
@@ -500,14 +507,29 @@ static int nicvf_init_resources(struct nicvf *nic)
 	return 0;
 }
 
+static void nicvf_unmap_page(struct nicvf *nic, struct page *page, u64 dma_addr)
+{
+	/* Check if it's a recycled page, if not unmap the DMA mapping.
+	 * Recycled page holds an extra reference.
+	 */
+	if (page_ref_count(page) == 1) {
+		dma_addr &= PAGE_MASK;
+		dma_unmap_page_attrs(&nic->pdev->dev, dma_addr,
+				     RCV_FRAG_LEN + XDP_HEADROOM,
+				     DMA_FROM_DEVICE,
+				     DMA_ATTR_SKIP_CPU_SYNC);
+	}
+}
+
 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)
 {
 	struct xdp_buff xdp;
 	struct page *page;
+	struct nicvf_xdp_tx *xdp_tx = NULL;
 	u32 action;
-	u16 len, offset = 0;
+	u16 len, err, offset = 0;
 	u64 dma_addr, cpu_addr;
 	void *orig_data;
 
@@ -521,10 +543,11 @@ 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_hard_start = page_address(page) + RCV_BUF_HEADROOM;
 	xdp.data = (void *)cpu_addr;
 	xdp_set_data_meta_invalid(&xdp);
 	xdp.data_end = xdp.data + len;
+	xdp.rxq = &rq->xdp_rxq;
 	orig_data = xdp.data;
 
 	rcu_read_lock();
@@ -540,18 +563,7 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
 
 	switch (action) {
 	case XDP_PASS:
-		/* Check if it's a recycled page, if not
-		 * unmap the DMA mapping.
-		 *
-		 * Recycled page holds an extra reference.
-		 */
-		if (page_ref_count(page) == 1) {
-			dma_addr &= PAGE_MASK;
-			dma_unmap_page_attrs(&nic->pdev->dev, dma_addr,
-					     RCV_FRAG_LEN + XDP_PACKET_HEADROOM,
-					     DMA_FROM_DEVICE,
-					     DMA_ATTR_SKIP_CPU_SYNC);
-		}
+		nicvf_unmap_page(nic, page, dma_addr);
 
 		/* Build SKB and pass on packet to network stack */
 		*skb = build_skb(xdp.data,
@@ -564,6 +576,20 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
 	case XDP_TX:
 		nicvf_xdp_sq_append_pkt(nic, sq, (u64)xdp.data, dma_addr, len);
 		return true;
+	case XDP_REDIRECT:
+		/* Save DMA address for use while transmitting */
+		xdp_tx = (struct nicvf_xdp_tx *)page_address(page);
+		xdp_tx->dma_addr = dma_addr;
+		xdp_tx->qidx = nicvf_netdev_qidx(nic, cqe_rx->rq_idx);
+
+		err = xdp_do_redirect(nic->pnicvf->netdev, &xdp, prog);
+		if (!err)
+			return true;
+
+		/* Free the page on error */
+		nicvf_unmap_page(nic, page, dma_addr);
+		put_page(page);
+		break;
 	default:
 		bpf_warn_invalid_xdp_action(action);
 		/* fall through */
@@ -571,24 +597,51 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
 		trace_xdp_exception(nic->netdev, prog, action);
 		/* fall through */
 	case XDP_DROP:
-		/* Check if it's a recycled page, if not
-		 * unmap the DMA mapping.
-		 *
-		 * Recycled page holds an extra reference.
-		 */
-		if (page_ref_count(page) == 1) {
-			dma_addr &= PAGE_MASK;
-			dma_unmap_page_attrs(&nic->pdev->dev, dma_addr,
-					     RCV_FRAG_LEN + XDP_PACKET_HEADROOM,
-					     DMA_FROM_DEVICE,
-					     DMA_ATTR_SKIP_CPU_SYNC);
-		}
+		nicvf_unmap_page(nic, page, dma_addr);
 		put_page(page);
 		return true;
 	}
 	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,
@@ -645,7 +698,12 @@ 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
@@ -684,9 +742,25 @@ 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);
@@ -712,7 +786,7 @@ 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,
@@ -734,6 +808,7 @@ 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);
@@ -769,6 +844,7 @@ 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);
@@ -799,7 +875,7 @@ 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:
@@ -808,10 +884,12 @@ 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;
 		}
@@ -1307,12 +1385,28 @@ 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 = {};
@@ -1382,6 +1476,12 @@ 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);
@@ -1764,6 +1864,117 @@ static int nicvf_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 	}
 }
 
+static int nicvf_xdp_xmit(struct net_device *netdev, struct xdp_buff *xdp)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+	struct nicvf *snic = nic;
+	struct nicvf_xdp_tx *xdp_tx;
+	struct snd_queue *sq;
+	struct page *page;
+	int err, qidx;
+
+	if (!netif_running(netdev) || !nic->xdp_prog)
+		return -EINVAL;
+
+	page = virt_to_page(xdp->data);
+	xdp_tx = (struct nicvf_xdp_tx *)page_address(page);
+	qidx = xdp_tx->qidx;
+
+	if (xdp_tx->qidx >= nic->xdp_tx_queues)
+		return -EINVAL;
+
+	/* Get secondary Qset's info */
+	if (xdp_tx->qidx >= MAX_SND_QUEUES_PER_QS) {
+		qidx = xdp_tx->qidx / MAX_SND_QUEUES_PER_QS;
+		snic = (struct nicvf *)nic->snicvf[qidx - 1];
+		if (!snic)
+			return -EINVAL;
+		qidx = xdp_tx->qidx % MAX_SND_QUEUES_PER_QS;
+	}
+
+	sq = &snic->qs->sq[qidx];
+	err = nicvf_xdp_sq_append_pkt(snic, sq, (u64)xdp->data,
+				      xdp_tx->dma_addr,
+				      xdp->data_end - xdp->data);
+	if (err)
+		return -ENOMEM;
+
+	nicvf_xdp_sq_doorbell(snic, sq, qidx);
+	return 0;
+}
+
+static void nicvf_xdp_flush(struct net_device *dev)
+{
+	return;
+}
+
+static int nicvf_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr)
+{
+	struct hwtstamp_config config;
+	struct nicvf *nic = netdev_priv(netdev);
+
+	if (!nic->ptp_clock)
+		return -ENODEV;
+
+	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+		return -EFAULT;
+
+	/* reserved for future extensions */
+	if (config.flags)
+		return -EINVAL;
+
+	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);
+
+	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int nicvf_ioctl(struct net_device *netdev, struct ifreq *req, int cmd)
+{
+	switch (cmd) {
+	case SIOCSHWTSTAMP:
+		return nicvf_config_hwtstamp(netdev, req);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct net_device_ops nicvf_netdev_ops = {
 	.ndo_open		= nicvf_open,
 	.ndo_stop		= nicvf_stop,
@@ -1775,6 +1986,9 @@ static const struct net_device_ops nicvf_netdev_ops = {
 	.ndo_fix_features       = nicvf_fix_features,
 	.ndo_set_features       = nicvf_set_features,
 	.ndo_bpf		= nicvf_xdp,
+	.ndo_xdp_xmit		= nicvf_xdp_xmit,
+	.ndo_xdp_flush          = nicvf_xdp_flush,
+	.ndo_do_ioctl           = nicvf_ioctl,
 };
 
 static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
@@ -1784,6 +1998,16 @@ 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;
+
+	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) {
@@ -1833,6 +2057,12 @@ 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;
 
 	/* MAP VF's configuration registers */
 	nic->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0);
@@ -1946,6 +2176,7 @@ static void nicvf_remove(struct pci_dev *pdev)
 	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);
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index a3d12dbde95b..3eae9ff9b53a 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -204,7 +204,7 @@ static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, struct rbdr *rbdr,
 
 	/* Reserve space for header modifications by BPF program */
 	if (rbdr->is_xdp)
-		buf_len += XDP_PACKET_HEADROOM;
+		buf_len += XDP_HEADROOM;
 
 	/* Check if it's recycled */
 	if (pgcache)
@@ -224,8 +224,9 @@ ret:
 			nic->rb_page = NULL;
 			return -ENOMEM;
 		}
+
 		if (pgcache)
-			pgcache->dma_addr = *rbuf + XDP_PACKET_HEADROOM;
+			pgcache->dma_addr = *rbuf + XDP_HEADROOM;
 		nic->rb_page_offset += buf_len;
 	}
 
@@ -759,6 +760,7 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs,
 
 	if (!rq->enable) {
 		nicvf_reclaim_rcv_queue(nic, qs, qidx);
+		xdp_rxq_info_unreg(&rq->xdp_rxq);
 		return;
 	}
 
@@ -771,6 +773,9 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs,
 	/* all writes of RBDR data to be loaded into L2 Cache as well*/
 	rq->caching = 1;
 
+	/* Driver have no proper error path for failed XDP RX-queue info reg */
+	WARN_ON(xdp_rxq_info_reg(&rq->xdp_rxq, nic->netdev, qidx) < 0);
+
 	/* Send a mailbox msg to PF to config RQ */
 	mbx.rq.msg = NIC_MBOX_MSG_RQ_CFG;
 	mbx.rq.qs_num = qs->vnic_id;
@@ -977,6 +982,9 @@ void nicvf_qset_config(struct nicvf *nic, bool enable)
 		qs_cfg->be = 1;
 #endif
 		qs_cfg->vnic = qs->vnic_id;
+		/* Enable Tx timestamping capability */
+		if (nic->ptp_clock)
+			qs_cfg->send_tstmp_ena = 1;
 	}
 	nicvf_send_msg_to_pf(nic, &mbx);
 }
@@ -1236,7 +1244,7 @@ int nicvf_xdp_sq_append_pkt(struct nicvf *nic, struct snd_queue *sq,
 	int qentry;
 
 	if (subdesc_cnt > sq->xdp_free_cnt)
-		return 0;
+		return -1;
 
 	qentry = nicvf_get_sq_desc(sq, subdesc_cnt);
 
@@ -1247,7 +1255,7 @@ int nicvf_xdp_sq_append_pkt(struct nicvf *nic, struct snd_queue *sq,
 
 	sq->xdp_desc_cnt += subdesc_cnt;
 
-	return 1;
+	return 0;
 }
 
 /* Calculate no of SQ subdescriptors needed to transmit all
@@ -1384,6 +1392,29 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry,
 		hdr->inner_l3_offset = skb_network_offset(skb) - 2;
 		this_cpu_inc(nic->pnicvf->drv_stats->tx_tso);
 	}
+
+	/* Check if timestamp is requested */
+	if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
+		skb_tx_timestamp(skb);
+		return;
+	}
+
+	/* Tx timestamping not supported along with TSO, so ignore request */
+	if (skb_shinfo(skb)->gso_size)
+		return;
+
+	/* HW supports only a single outstanding packet to timestamp */
+	if (!atomic_add_unless(&nic->pnicvf->tx_ptp_skbs, 1, 1))
+		return;
+
+	/* Mark the SKB for later reference */
+	skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+
+	/* Finally enable timestamp generation
+	 * Since 'post_cqe' is also set, two CQEs will be posted
+	 * for this packet i.e CQE_TYPE_SEND and CQE_TYPE_SEND_PTP.
+	 */
+	hdr->tstmp = 1;
 }
 
 /* SQ GATHER subdescriptor
@@ -1625,7 +1656,7 @@ static void nicvf_unmap_rcv_buffer(struct nicvf *nic, u64 dma_addr,
 		if (page_ref_count(page) != 1)
 			return;
 
-		len += XDP_PACKET_HEADROOM;
+		len += XDP_HEADROOM;
 		/* Receive buffers in XDP mode are mapped from page start */
 		dma_addr &= PAGE_MASK;
 	}
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index 67d1a3230773..7d1e4e2aaad0 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -11,6 +11,8 @@
 
 #include <linux/netdevice.h>
 #include <linux/iommu.h>
+#include <linux/bpf.h>
+#include <net/xdp.h>
 #include "q_struct.h"
 
 #define MAX_QUEUE_SET			128
@@ -92,6 +94,9 @@
 #define RCV_FRAG_LEN	 (SKB_DATA_ALIGN(DMA_BUFFER_LEN + NET_SKB_PAD) + \
 			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
 
+#define RCV_BUF_HEADROOM	128 /* To store dma address for XDP redirect */
+#define XDP_HEADROOM		(XDP_PACKET_HEADROOM + RCV_BUF_HEADROOM)
+
 #define MAX_CQES_FOR_TX		((SND_QUEUE_LEN / MIN_SQ_DESC_PER_PKT_XMIT) * \
 				 MAX_CQE_PER_PKT_XMIT)
 
@@ -251,6 +256,7 @@ struct rcv_queue {
 	u8		start_qs_rbdr_idx; /* RBDR idx in the above QS */
 	u8		caching;
 	struct		rx_tx_queue_stats stats;
+	struct xdp_rxq_info xdp_rxq;
 } ____cacheline_aligned_in_smp;
 
 struct cmp_queue {
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 5e5c4d7796b8..91d34ea40e2c 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -21,7 +21,7 @@
 #include "nic.h"
 #include "thunder_bgx.h"
 
-#define DRV_NAME	"thunder-BGX"
+#define DRV_NAME	"thunder_bgx"
 #define DRV_VERSION	"1.0"
 
 struct lmac {
@@ -245,6 +245,35 @@ void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable)
 }
 EXPORT_SYMBOL(bgx_lmac_rx_tx_enable);
 
+/* Enables or disables timestamp insertion by BGX for Rx packets */
+void bgx_config_timestamping(int node, int bgx_idx, int lmacid, bool enable)
+{
+	struct bgx *bgx = get_bgx(node, bgx_idx);
+	struct lmac *lmac;
+	u64 csr_offset, cfg;
+
+	if (!bgx)
+		return;
+
+	lmac = &bgx->lmac[lmacid];
+
+	if (lmac->lmac_type == BGX_MODE_SGMII ||
+	    lmac->lmac_type == BGX_MODE_QSGMII ||
+	    lmac->lmac_type == BGX_MODE_RGMII)
+		csr_offset = BGX_GMP_GMI_RXX_FRM_CTL;
+	else
+		csr_offset = BGX_SMUX_RX_FRM_CTL;
+
+	cfg = bgx_reg_read(bgx, lmacid, csr_offset);
+
+	if (enable)
+		cfg |= BGX_PKT_RX_PTP_EN;
+	else
+		cfg &= ~BGX_PKT_RX_PTP_EN;
+	bgx_reg_write(bgx, lmacid, csr_offset, cfg);
+}
+EXPORT_SYMBOL(bgx_config_timestamping);
+
 void bgx_lmac_get_pfc(int node, int bgx_idx, int lmacid, void *pause)
 {
 	struct pfc *pfc = (struct pfc *)pause;
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index 23acdc5ab896..5a7567d31138 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -122,6 +122,8 @@
 #define  SPU_DBG_CTL_AN_NONCE_MCT_DIS		BIT_ULL(29)
 
 #define BGX_SMUX_RX_INT			0x20000
+#define BGX_SMUX_RX_FRM_CTL		0x20020
+#define  BGX_PKT_RX_PTP_EN			BIT_ULL(12)
 #define BGX_SMUX_RX_JABBER		0x20030
 #define BGX_SMUX_RX_CTL			0x20048
 #define  SMU_RX_CTL_STATUS			(3ull << 0)
@@ -172,6 +174,7 @@
 #define  GMI_PORT_CFG_SPEED_MSB			BIT_ULL(8)
 #define  GMI_PORT_CFG_RX_IDLE			BIT_ULL(12)
 #define  GMI_PORT_CFG_TX_IDLE			BIT_ULL(13)
+#define BGX_GMP_GMI_RXX_FRM_CTL		0x38028
 #define BGX_GMP_GMI_RXX_JABBER		0x38038
 #define BGX_GMP_GMI_TXX_THRESH		0x38210
 #define BGX_GMP_GMI_TXX_APPEND		0x38218
@@ -223,6 +226,7 @@ void bgx_set_lmac_mac(int node, int bgx_idx, int lmacid, const u8 *mac);
 void bgx_get_lmac_link_state(int node, int bgx_idx, int lmacid, void *status);
 void bgx_lmac_internal_loopback(int node, int bgx_idx,
 				int lmac_idx, bool enable);
+void bgx_config_timestamping(int node, int bgx_idx, int lmacid, bool enable);
 void bgx_lmac_get_pfc(int node, int bgx_idx, int lmacid, void *pause);
 void bgx_lmac_set_pfc(int node, int bgx_idx, int lmacid, void *pause);
 
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_xcv.c b/drivers/net/ethernet/cavium/thunder/thunder_xcv.c
index 578c7f8f11bf..2d5e8dab1f70 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_xcv.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_xcv.c
@@ -20,7 +20,7 @@
 #include "nic.h"
 #include "thunder_bgx.h"
 
-#define DRV_NAME	"thunder-xcv"
+#define DRV_NAME	"thunder_xcv"
 #define DRV_VERSION	"1.0"
 
 /* Register offsets */