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

All conflicts were simple overlapping changes except perhaps
for the Thunder driver.

That driver has a change_mtu method explicitly for sending
a message to the hardware.  If that fails it returns an
error.

Normally a driver doesn't need an ndo_change_mtu method becuase those
are usually just range changes, which are now handled generically.
But since this extra operation is needed in the Thunder driver, it has
to stay.

However, if the message send fails we have to restore the original
MTU before the change because the entire call chain expects that if
an error is thrown by ndo_change_mtu then the MTU did not change.
Therefore code is added to nicvf_change_mtu to remember the original
MTU, and to restore it upon nicvf_update_hw_max_frs() failue.

Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index 95d8b3e..abc9f2a 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -460,7 +460,7 @@ static void arc_emac_set_rx_mode(struct net_device *ndev)
 		if (ndev->flags & IFF_ALLMULTI) {
 			arc_reg_set(priv, R_LAFL, ~0);
 			arc_reg_set(priv, R_LAFH, ~0);
-		} else {
+		} else if (ndev->flags & IFF_MULTICAST) {
 			struct netdev_hw_addr *ha;
 			unsigned int filter[2] = { 0, 0 };
 			int bit;
@@ -472,6 +472,9 @@ static void arc_emac_set_rx_mode(struct net_device *ndev)
 
 			arc_reg_set(priv, R_LAFL, filter[0]);
 			arc_reg_set(priv, R_LAFH, filter[1]);
+		} else {
+			arc_reg_set(priv, R_LAFL, 0);
+			arc_reg_set(priv, R_LAFH, 0);
 		}
 	}
 }
@@ -764,8 +767,6 @@ int arc_emac_probe(struct net_device *ndev, int interface)
 	ndev->netdev_ops = &arc_emac_netdev_ops;
 	ndev->ethtool_ops = &arc_emac_ethtool_ops;
 	ndev->watchdog_timeo = TX_TIMEOUT;
-	/* FIXME :: no multicast support yet */
-	ndev->flags &= ~IFF_MULTICAST;
 
 	priv = netdev_priv(ndev);
 	priv->dev = dev;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 7401c90..8c7bdbe 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4929,6 +4929,10 @@ static void bnxt_del_napi(struct bnxt *bp)
 		napi_hash_del(&bnapi->napi);
 		netif_napi_del(&bnapi->napi);
 	}
+	/* We called napi_hash_del() before netif_napi_del(), we need
+	 * to respect an RCU grace period before freeing napi structures.
+	 */
+	synchronize_net();
 }
 
 static void bnxt_init_napi(struct bnxt *bp)
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 654b5bf..0e489bb 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -2846,6 +2846,12 @@ static int at91ether_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		lp->skb_length = skb->len;
 		lp->skb_physaddr = dma_map_single(NULL, skb->data, skb->len,
 							DMA_TO_DEVICE);
+		if (dma_mapping_error(NULL, lp->skb_physaddr)) {
+			dev_kfree_skb_any(skb);
+			dev->stats.tx_dropped++;
+			netdev_err(dev, "%s: DMA mapping error\n", __func__);
+			return NETDEV_TX_OK;
+		}
 
 		/* Set address of the data in the Transmit Address register */
 		macb_writel(lp, TAR, lp->skb_physaddr);
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index 3042610..86bd93c 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -47,7 +47,7 @@
 
 /* Min/Max packet size */
 #define	NIC_HW_MIN_FRS			64
-#define	NIC_HW_MAX_FRS			9200 /* 9216 max packet including FCS */
+#define	NIC_HW_MAX_FRS			9190 /* Excluding L2 header and FCS */
 
 /* Max pkinds */
 #define	NIC_MAX_PKIND			16
@@ -178,11 +178,11 @@ enum tx_stats_reg_offset {
 
 struct nicvf_hw_stats {
 	u64 rx_bytes;
+	u64 rx_frames;
 	u64 rx_ucast_frames;
 	u64 rx_bcast_frames;
 	u64 rx_mcast_frames;
-	u64 rx_fcs_errors;
-	u64 rx_l2_errors;
+	u64 rx_drops;
 	u64 rx_drop_red;
 	u64 rx_drop_red_bytes;
 	u64 rx_drop_overrun;
@@ -191,6 +191,19 @@ struct nicvf_hw_stats {
 	u64 rx_drop_mcast;
 	u64 rx_drop_l3_bcast;
 	u64 rx_drop_l3_mcast;
+	u64 rx_fcs_errors;
+	u64 rx_l2_errors;
+
+	u64 tx_bytes;
+	u64 tx_frames;
+	u64 tx_ucast_frames;
+	u64 tx_bcast_frames;
+	u64 tx_mcast_frames;
+	u64 tx_drops;
+};
+
+struct nicvf_drv_stats {
+	/* CQE Rx errs */
 	u64 rx_bgx_truncated_pkts;
 	u64 rx_jabber_errs;
 	u64 rx_fcs_errs;
@@ -216,34 +229,30 @@ struct nicvf_hw_stats {
 	u64 rx_l4_pclp;
 	u64 rx_truncated_pkts;
 
-	u64 tx_bytes_ok;
-	u64 tx_ucast_frames_ok;
-	u64 tx_bcast_frames_ok;
-	u64 tx_mcast_frames_ok;
-	u64 tx_drops;
-};
+	/* CQE Tx errs */
+	u64 tx_desc_fault;
+	u64 tx_hdr_cons_err;
+	u64 tx_subdesc_err;
+	u64 tx_max_size_exceeded;
+	u64 tx_imm_size_oflow;
+	u64 tx_data_seq_err;
+	u64 tx_mem_seq_err;
+	u64 tx_lock_viol;
+	u64 tx_data_fault;
+	u64 tx_tstmp_conflict;
+	u64 tx_tstmp_timeout;
+	u64 tx_mem_fault;
+	u64 tx_csum_overlap;
+	u64 tx_csum_overflow;
 
-struct nicvf_drv_stats {
-	/* Rx */
-	u64 rx_frames_ok;
-	u64 rx_frames_64;
-	u64 rx_frames_127;
-	u64 rx_frames_255;
-	u64 rx_frames_511;
-	u64 rx_frames_1023;
-	u64 rx_frames_1518;
-	u64 rx_frames_jumbo;
-	u64 rx_drops;
-
+	/* driver debug stats */
 	u64 rcv_buffer_alloc_failures;
-
-	/* Tx */
-	u64 tx_frames_ok;
-	u64 tx_drops;
 	u64 tx_tso;
 	u64 tx_timeout;
 	u64 txq_stop;
 	u64 txq_wake;
+
+	struct u64_stats_sync   syncp;
 };
 
 struct nicvf {
@@ -282,7 +291,6 @@ struct nicvf {
 
 	u8			node;
 	u8			cpi_alg;
-	u16			mtu;
 	bool			link_up;
 	u8			duplex;
 	u32			speed;
@@ -298,7 +306,7 @@ struct nicvf {
 
 	/* Stats */
 	struct nicvf_hw_stats   hw_stats;
-	struct nicvf_drv_stats  drv_stats;
+	struct nicvf_drv_stats  __percpu *drv_stats;
 	struct bgx_stats	bgx_stats;
 
 	/* MSI-X  */
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 2bbf4cb..6677b96 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -11,6 +11,7 @@
 #include <linux/pci.h>
 #include <linux/etherdevice.h>
 #include <linux/of.h>
+#include <linux/if_vlan.h>
 
 #include "nic_reg.h"
 #include "nic.h"
@@ -260,18 +261,31 @@ static void nic_get_bgx_stats(struct nicpf *nic, struct bgx_stats_msg *bgx)
 /* Update hardware min/max frame size */
 static int nic_update_hw_frs(struct nicpf *nic, int new_frs, int vf)
 {
-	if ((new_frs > NIC_HW_MAX_FRS) || (new_frs < NIC_HW_MIN_FRS)) {
-		dev_err(&nic->pdev->dev,
-			"Invalid MTU setting from VF%d rejected, should be between %d and %d\n",
-			   vf, NIC_HW_MIN_FRS, NIC_HW_MAX_FRS);
-		return 1;
-	}
-	new_frs += ETH_HLEN;
-	if (new_frs <= nic->pkind.maxlen)
-		return 0;
+	int bgx, lmac, lmac_cnt;
+	u64 lmac_credits;
 
-	nic->pkind.maxlen = new_frs;
-	nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG, *(u64 *)&nic->pkind);
+	if ((new_frs > NIC_HW_MAX_FRS) || (new_frs < NIC_HW_MIN_FRS))
+		return 1;
+
+	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]);
+	lmac += bgx * MAX_LMAC_PER_BGX;
+
+	new_frs += VLAN_ETH_HLEN + ETH_FCS_LEN + 4;
+
+	/* Update corresponding LMAC credits */
+	lmac_cnt = bgx_get_lmac_count(nic->node, bgx);
+	lmac_credits = nic_reg_read(nic, NIC_PF_LMAC_0_7_CREDIT + (lmac * 8));
+	lmac_credits &= ~(0xFFFFFULL << 12);
+	lmac_credits |= (((((48 * 1024) / lmac_cnt) - new_frs) / 16) << 12);
+	nic_reg_write(nic, NIC_PF_LMAC_0_7_CREDIT + (lmac * 8), lmac_credits);
+
+	/* Enforce MTU in HW
+	 * This config is supported only from 88xx pass 2.0 onwards.
+	 */
+	if (!pass1_silicon(nic->pdev))
+		nic_reg_write(nic,
+			      NIC_PF_LMAC_0_7_CFG2 + (lmac * 8), new_frs);
 	return 0;
 }
 
@@ -464,7 +478,7 @@ static int nic_init_hw(struct nicpf *nic)
 
 	/* PKIND configuration */
 	nic->pkind.minlen = 0;
-	nic->pkind.maxlen = NIC_HW_MAX_FRS + ETH_HLEN;
+	nic->pkind.maxlen = NIC_HW_MAX_FRS + VLAN_ETH_HLEN + ETH_FCS_LEN + 4;
 	nic->pkind.lenerr_en = 1;
 	nic->pkind.rx_hdr = 0;
 	nic->pkind.hdr_sl = 0;
@@ -837,6 +851,7 @@ static int nic_reset_stat_counters(struct nicpf *nic,
 			nic_reg_write(nic, reg_addr, 0);
 		}
 	}
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h
index edf779f..80d4633 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_reg.h
+++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h
@@ -106,6 +106,7 @@
 #define   NIC_PF_MPI_0_2047_CFG			(0x210000)
 #define   NIC_PF_RSSI_0_4097_RQ			(0x220000)
 #define   NIC_PF_LMAC_0_7_CFG			(0x240000)
+#define   NIC_PF_LMAC_0_7_CFG2			(0x240100)
 #define   NIC_PF_LMAC_0_7_SW_XOFF		(0x242000)
 #define   NIC_PF_LMAC_0_7_CREDIT		(0x244000)
 #define   NIC_PF_CHAN_0_255_TX_CFG		(0x400000)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index ad4fddb..432bf6b 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -36,11 +36,11 @@ struct nicvf_stat {
 
 static const struct nicvf_stat nicvf_hw_stats[] = {
 	NICVF_HW_STAT(rx_bytes),
+	NICVF_HW_STAT(rx_frames),
 	NICVF_HW_STAT(rx_ucast_frames),
 	NICVF_HW_STAT(rx_bcast_frames),
 	NICVF_HW_STAT(rx_mcast_frames),
-	NICVF_HW_STAT(rx_fcs_errors),
-	NICVF_HW_STAT(rx_l2_errors),
+	NICVF_HW_STAT(rx_drops),
 	NICVF_HW_STAT(rx_drop_red),
 	NICVF_HW_STAT(rx_drop_red_bytes),
 	NICVF_HW_STAT(rx_drop_overrun),
@@ -49,50 +49,59 @@ static const struct nicvf_stat nicvf_hw_stats[] = {
 	NICVF_HW_STAT(rx_drop_mcast),
 	NICVF_HW_STAT(rx_drop_l3_bcast),
 	NICVF_HW_STAT(rx_drop_l3_mcast),
-	NICVF_HW_STAT(rx_bgx_truncated_pkts),
-	NICVF_HW_STAT(rx_jabber_errs),
-	NICVF_HW_STAT(rx_fcs_errs),
-	NICVF_HW_STAT(rx_bgx_errs),
-	NICVF_HW_STAT(rx_prel2_errs),
-	NICVF_HW_STAT(rx_l2_hdr_malformed),
-	NICVF_HW_STAT(rx_oversize),
-	NICVF_HW_STAT(rx_undersize),
-	NICVF_HW_STAT(rx_l2_len_mismatch),
-	NICVF_HW_STAT(rx_l2_pclp),
-	NICVF_HW_STAT(rx_ip_ver_errs),
-	NICVF_HW_STAT(rx_ip_csum_errs),
-	NICVF_HW_STAT(rx_ip_hdr_malformed),
-	NICVF_HW_STAT(rx_ip_payload_malformed),
-	NICVF_HW_STAT(rx_ip_ttl_errs),
-	NICVF_HW_STAT(rx_l3_pclp),
-	NICVF_HW_STAT(rx_l4_malformed),
-	NICVF_HW_STAT(rx_l4_csum_errs),
-	NICVF_HW_STAT(rx_udp_len_errs),
-	NICVF_HW_STAT(rx_l4_port_errs),
-	NICVF_HW_STAT(rx_tcp_flag_errs),
-	NICVF_HW_STAT(rx_tcp_offset_errs),
-	NICVF_HW_STAT(rx_l4_pclp),
-	NICVF_HW_STAT(rx_truncated_pkts),
-	NICVF_HW_STAT(tx_bytes_ok),
-	NICVF_HW_STAT(tx_ucast_frames_ok),
-	NICVF_HW_STAT(tx_bcast_frames_ok),
-	NICVF_HW_STAT(tx_mcast_frames_ok),
+	NICVF_HW_STAT(rx_fcs_errors),
+	NICVF_HW_STAT(rx_l2_errors),
+	NICVF_HW_STAT(tx_bytes),
+	NICVF_HW_STAT(tx_frames),
+	NICVF_HW_STAT(tx_ucast_frames),
+	NICVF_HW_STAT(tx_bcast_frames),
+	NICVF_HW_STAT(tx_mcast_frames),
+	NICVF_HW_STAT(tx_drops),
 };
 
 static const struct nicvf_stat nicvf_drv_stats[] = {
-	NICVF_DRV_STAT(rx_frames_ok),
-	NICVF_DRV_STAT(rx_frames_64),
-	NICVF_DRV_STAT(rx_frames_127),
-	NICVF_DRV_STAT(rx_frames_255),
-	NICVF_DRV_STAT(rx_frames_511),
-	NICVF_DRV_STAT(rx_frames_1023),
-	NICVF_DRV_STAT(rx_frames_1518),
-	NICVF_DRV_STAT(rx_frames_jumbo),
-	NICVF_DRV_STAT(rx_drops),
+	NICVF_DRV_STAT(rx_bgx_truncated_pkts),
+	NICVF_DRV_STAT(rx_jabber_errs),
+	NICVF_DRV_STAT(rx_fcs_errs),
+	NICVF_DRV_STAT(rx_bgx_errs),
+	NICVF_DRV_STAT(rx_prel2_errs),
+	NICVF_DRV_STAT(rx_l2_hdr_malformed),
+	NICVF_DRV_STAT(rx_oversize),
+	NICVF_DRV_STAT(rx_undersize),
+	NICVF_DRV_STAT(rx_l2_len_mismatch),
+	NICVF_DRV_STAT(rx_l2_pclp),
+	NICVF_DRV_STAT(rx_ip_ver_errs),
+	NICVF_DRV_STAT(rx_ip_csum_errs),
+	NICVF_DRV_STAT(rx_ip_hdr_malformed),
+	NICVF_DRV_STAT(rx_ip_payload_malformed),
+	NICVF_DRV_STAT(rx_ip_ttl_errs),
+	NICVF_DRV_STAT(rx_l3_pclp),
+	NICVF_DRV_STAT(rx_l4_malformed),
+	NICVF_DRV_STAT(rx_l4_csum_errs),
+	NICVF_DRV_STAT(rx_udp_len_errs),
+	NICVF_DRV_STAT(rx_l4_port_errs),
+	NICVF_DRV_STAT(rx_tcp_flag_errs),
+	NICVF_DRV_STAT(rx_tcp_offset_errs),
+	NICVF_DRV_STAT(rx_l4_pclp),
+	NICVF_DRV_STAT(rx_truncated_pkts),
+
+	NICVF_DRV_STAT(tx_desc_fault),
+	NICVF_DRV_STAT(tx_hdr_cons_err),
+	NICVF_DRV_STAT(tx_subdesc_err),
+	NICVF_DRV_STAT(tx_max_size_exceeded),
+	NICVF_DRV_STAT(tx_imm_size_oflow),
+	NICVF_DRV_STAT(tx_data_seq_err),
+	NICVF_DRV_STAT(tx_mem_seq_err),
+	NICVF_DRV_STAT(tx_lock_viol),
+	NICVF_DRV_STAT(tx_data_fault),
+	NICVF_DRV_STAT(tx_tstmp_conflict),
+	NICVF_DRV_STAT(tx_tstmp_timeout),
+	NICVF_DRV_STAT(tx_mem_fault),
+	NICVF_DRV_STAT(tx_csum_overlap),
+	NICVF_DRV_STAT(tx_csum_overflow),
+
 	NICVF_DRV_STAT(rcv_buffer_alloc_failures),
-	NICVF_DRV_STAT(tx_frames_ok),
 	NICVF_DRV_STAT(tx_tso),
-	NICVF_DRV_STAT(tx_drops),
 	NICVF_DRV_STAT(tx_timeout),
 	NICVF_DRV_STAT(txq_stop),
 	NICVF_DRV_STAT(txq_wake),
@@ -278,8 +287,8 @@ static void nicvf_get_ethtool_stats(struct net_device *netdev,
 				    struct ethtool_stats *stats, u64 *data)
 {
 	struct nicvf *nic = netdev_priv(netdev);
-	int stat;
-	int sqs;
+	int stat, tmp_stats;
+	int sqs, cpu;
 
 	nicvf_update_stats(nic);
 
@@ -289,9 +298,13 @@ static void nicvf_get_ethtool_stats(struct net_device *netdev,
 	for (stat = 0; stat < nicvf_n_hw_stats; stat++)
 		*(data++) = ((u64 *)&nic->hw_stats)
 				[nicvf_hw_stats[stat].index];
-	for (stat = 0; stat < nicvf_n_drv_stats; stat++)
-		*(data++) = ((u64 *)&nic->drv_stats)
-				[nicvf_drv_stats[stat].index];
+	for (stat = 0; stat < nicvf_n_drv_stats; stat++) {
+		tmp_stats = 0;
+		for_each_possible_cpu(cpu)
+			tmp_stats += ((u64 *)per_cpu_ptr(nic->drv_stats, cpu))
+				     [nicvf_drv_stats[stat].index];
+		*(data++) = tmp_stats;
+	}
 
 	nicvf_get_qset_stats(nic, stats, &data);
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index b192712..7c2c373 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -69,25 +69,6 @@ static inline u8 nicvf_netdev_qidx(struct nicvf *nic, u8 qidx)
 		return qidx;
 }
 
-static inline void nicvf_set_rx_frame_cnt(struct nicvf *nic,
-					  struct sk_buff *skb)
-{
-	if (skb->len <= 64)
-		nic->drv_stats.rx_frames_64++;
-	else if (skb->len <= 127)
-		nic->drv_stats.rx_frames_127++;
-	else if (skb->len <= 255)
-		nic->drv_stats.rx_frames_255++;
-	else if (skb->len <= 511)
-		nic->drv_stats.rx_frames_511++;
-	else if (skb->len <= 1023)
-		nic->drv_stats.rx_frames_1023++;
-	else if (skb->len <= 1518)
-		nic->drv_stats.rx_frames_1518++;
-	else
-		nic->drv_stats.rx_frames_jumbo++;
-}
-
 /* The Cavium ThunderX network controller can *only* be found in SoCs
  * containing the ThunderX ARM64 CPU implementation.  All accesses to the device
  * registers on this platform are implicitly strongly ordered with respect
@@ -492,9 +473,6 @@ int nicvf_set_real_num_queues(struct net_device *netdev,
 static int nicvf_init_resources(struct nicvf *nic)
 {
 	int err;
-	union nic_mbx mbx = {};
-
-	mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE;
 
 	/* Enable Qset */
 	nicvf_qset_config(nic, true);
@@ -507,14 +485,10 @@ static int nicvf_init_resources(struct nicvf *nic)
 		return err;
 	}
 
-	/* Send VF config done msg to PF */
-	nicvf_write_to_mbx(nic, &mbx);
-
 	return 0;
 }
 
 static void nicvf_snd_pkt_handler(struct net_device *netdev,
-				  struct cmp_queue *cq,
 				  struct cqe_send_t *cqe_tx,
 				  int cqe_type, int budget,
 				  unsigned int *tx_pkts, unsigned int *tx_bytes)
@@ -536,7 +510,7 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev,
 		   __func__, cqe_tx->sq_qs, cqe_tx->sq_idx,
 		   cqe_tx->sqe_ptr, hdr->subdesc_cnt);
 
-	nicvf_check_cqe_tx_errs(nic, cq, cqe_tx);
+	nicvf_check_cqe_tx_errs(nic, cqe_tx);
 	skb = (struct sk_buff *)sq->skbuff[cqe_tx->sqe_ptr];
 	if (skb) {
 		/* Check for dummy descriptor used for HW TSO offload on 88xx */
@@ -630,8 +604,6 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 		return;
 	}
 
-	nicvf_set_rx_frame_cnt(nic, skb);
-
 	nicvf_set_rxhash(netdev, cqe_rx, skb);
 
 	skb_record_rx_queue(skb, rq_idx);
@@ -703,7 +675,7 @@ static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
 			work_done++;
 		break;
 		case CQE_TYPE_SEND:
-			nicvf_snd_pkt_handler(netdev, cq,
+			nicvf_snd_pkt_handler(netdev,
 					      (void *)cq_desc, CQE_TYPE_SEND,
 					      budget, &tx_pkts, &tx_bytes);
 			tx_done++;
@@ -740,7 +712,7 @@ static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
 		nic = nic->pnicvf;
 		if (netif_tx_queue_stopped(txq) && netif_carrier_ok(netdev)) {
 			netif_tx_start_queue(txq);
-			nic->drv_stats.txq_wake++;
+			this_cpu_inc(nic->drv_stats->txq_wake);
 			if (netif_msg_tx_err(nic))
 				netdev_warn(netdev,
 					    "%s: Transmit queue wakeup SQ%d\n",
@@ -1084,7 +1056,7 @@ static netdev_tx_t nicvf_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	if (!netif_tx_queue_stopped(txq) && !nicvf_sq_append_skb(nic, skb)) {
 		netif_tx_stop_queue(txq);
-		nic->drv_stats.txq_stop++;
+		this_cpu_inc(nic->drv_stats->txq_stop);
 		if (netif_msg_tx_err(nic))
 			netdev_warn(netdev,
 				    "%s: Transmit ring full, stopping SQ%d\n",
@@ -1189,14 +1161,24 @@ int nicvf_stop(struct net_device *netdev)
 	return 0;
 }
 
+static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu)
+{
+	union nic_mbx mbx = {};
+
+	mbx.frs.msg = NIC_MBOX_MSG_SET_MAX_FRS;
+	mbx.frs.max_frs = mtu;
+	mbx.frs.vf_id = nic->vf_id;
+
+	return nicvf_send_msg_to_pf(nic, &mbx);
+}
+
 int nicvf_open(struct net_device *netdev)
 {
-	int err, qidx;
+	int cpu, err, qidx;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct queue_set *qs = nic->qs;
 	struct nicvf_cq_poll *cq_poll = NULL;
-
-	nic->mtu = netdev->mtu;
+	union nic_mbx mbx = {};
 
 	netif_carrier_off(netdev);
 
@@ -1248,9 +1230,17 @@ int nicvf_open(struct net_device *netdev)
 	if (nic->sqs_mode)
 		nicvf_get_primary_vf_struct(nic);
 
-	/* Configure receive side scaling */
-	if (!nic->sqs_mode)
+	/* Configure receive side scaling and MTU */
+	if (!nic->sqs_mode) {
 		nicvf_rss_init(nic);
+		if (nicvf_update_hw_max_frs(nic, netdev->mtu))
+			goto cleanup;
+
+		/* Clear percpu stats */
+		for_each_possible_cpu(cpu)
+			memset(per_cpu_ptr(nic->drv_stats, cpu), 0,
+			       sizeof(struct nicvf_drv_stats));
+	}
 
 	err = nicvf_register_interrupts(nic);
 	if (err)
@@ -1276,8 +1266,9 @@ int nicvf_open(struct net_device *netdev)
 	for (qidx = 0; qidx < qs->rbdr_cnt; qidx++)
 		nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx);
 
-	nic->drv_stats.txq_stop = 0;
-	nic->drv_stats.txq_wake = 0;
+	/* Send VF config done msg to PF */
+	mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE;
+	nicvf_write_to_mbx(nic, &mbx);
 
 	return 0;
 cleanup:
@@ -1297,25 +1288,20 @@ int nicvf_open(struct net_device *netdev)
 	return err;
 }
 
-static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu)
-{
-	union nic_mbx mbx = {};
-
-	mbx.frs.msg = NIC_MBOX_MSG_SET_MAX_FRS;
-	mbx.frs.max_frs = mtu;
-	mbx.frs.vf_id = nic->vf_id;
-
-	return nicvf_send_msg_to_pf(nic, &mbx);
-}
-
 static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct nicvf *nic = netdev_priv(netdev);
+	int orig_mtu = netdev->mtu;
 
-	if (nicvf_update_hw_max_frs(nic, new_mtu))
-		return -EINVAL;
 	netdev->mtu = new_mtu;
-	nic->mtu = new_mtu;
+
+	if (!netif_running(netdev))
+		return 0;
+
+	if (nicvf_update_hw_max_frs(nic, new_mtu)) {
+		netdev->mtu = orig_mtu;
+		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -1373,9 +1359,10 @@ void nicvf_update_lmac_stats(struct nicvf *nic)
 
 void nicvf_update_stats(struct nicvf *nic)
 {
-	int qidx;
+	int qidx, cpu;
+	u64 tmp_stats = 0;
 	struct nicvf_hw_stats *stats = &nic->hw_stats;
-	struct nicvf_drv_stats *drv_stats = &nic->drv_stats;
+	struct nicvf_drv_stats *drv_stats;
 	struct queue_set *qs = nic->qs;
 
 #define GET_RX_STATS(reg) \
@@ -1398,21 +1385,33 @@ void nicvf_update_stats(struct nicvf *nic)
 	stats->rx_drop_l3_bcast = GET_RX_STATS(RX_DRP_L3BCAST);
 	stats->rx_drop_l3_mcast = GET_RX_STATS(RX_DRP_L3MCAST);
 
-	stats->tx_bytes_ok = GET_TX_STATS(TX_OCTS);
-	stats->tx_ucast_frames_ok = GET_TX_STATS(TX_UCAST);
-	stats->tx_bcast_frames_ok = GET_TX_STATS(TX_BCAST);
-	stats->tx_mcast_frames_ok = GET_TX_STATS(TX_MCAST);
+	stats->tx_bytes = GET_TX_STATS(TX_OCTS);
+	stats->tx_ucast_frames = GET_TX_STATS(TX_UCAST);
+	stats->tx_bcast_frames = GET_TX_STATS(TX_BCAST);
+	stats->tx_mcast_frames = GET_TX_STATS(TX_MCAST);
 	stats->tx_drops = GET_TX_STATS(TX_DROP);
 
-	drv_stats->tx_frames_ok = stats->tx_ucast_frames_ok +
-				  stats->tx_bcast_frames_ok +
-				  stats->tx_mcast_frames_ok;
-	drv_stats->rx_frames_ok = stats->rx_ucast_frames +
-				  stats->rx_bcast_frames +
-				  stats->rx_mcast_frames;
-	drv_stats->rx_drops = stats->rx_drop_red +
-			      stats->rx_drop_overrun;
-	drv_stats->tx_drops = stats->tx_drops;
+	/* On T88 pass 2.0, the dummy SQE added for TSO notification
+	 * via CQE has 'dont_send' set. Hence HW drops the pkt pointed
+	 * pointed by dummy SQE and results in tx_drops counter being
+	 * incremented. Subtracting it from tx_tso counter will give
+	 * exact tx_drops counter.
+	 */
+	if (nic->t88 && nic->hw_tso) {
+		for_each_possible_cpu(cpu) {
+			drv_stats = per_cpu_ptr(nic->drv_stats, cpu);
+			tmp_stats += drv_stats->tx_tso;
+		}
+		stats->tx_drops = tmp_stats - stats->tx_drops;
+	}
+	stats->tx_frames = stats->tx_ucast_frames +
+			   stats->tx_bcast_frames +
+			   stats->tx_mcast_frames;
+	stats->rx_frames = stats->rx_ucast_frames +
+			   stats->rx_bcast_frames +
+			   stats->rx_mcast_frames;
+	stats->rx_drops = stats->rx_drop_red +
+			  stats->rx_drop_overrun;
 
 	/* Update RQ and SQ stats */
 	for (qidx = 0; qidx < qs->rq_cnt; qidx++)
@@ -1426,18 +1425,17 @@ static struct rtnl_link_stats64 *nicvf_get_stats64(struct net_device *netdev,
 {
 	struct nicvf *nic = netdev_priv(netdev);
 	struct nicvf_hw_stats *hw_stats = &nic->hw_stats;
-	struct nicvf_drv_stats *drv_stats = &nic->drv_stats;
 
 	nicvf_update_stats(nic);
 
 	stats->rx_bytes = hw_stats->rx_bytes;
-	stats->rx_packets = drv_stats->rx_frames_ok;
-	stats->rx_dropped = drv_stats->rx_drops;
+	stats->rx_packets = hw_stats->rx_frames;
+	stats->rx_dropped = hw_stats->rx_drops;
 	stats->multicast = hw_stats->rx_mcast_frames;
 
-	stats->tx_bytes = hw_stats->tx_bytes_ok;
-	stats->tx_packets = drv_stats->tx_frames_ok;
-	stats->tx_dropped = drv_stats->tx_drops;
+	stats->tx_bytes = hw_stats->tx_bytes;
+	stats->tx_packets = hw_stats->tx_frames;
+	stats->tx_dropped = hw_stats->tx_drops;
 
 	return stats;
 }
@@ -1450,7 +1448,7 @@ static void nicvf_tx_timeout(struct net_device *dev)
 		netdev_warn(dev, "%s: Transmit timed out, resetting\n",
 			    dev->name);
 
-	nic->drv_stats.tx_timeout++;
+	this_cpu_inc(nic->drv_stats->tx_timeout);
 	schedule_work(&nic->reset_task);
 }
 
@@ -1584,6 +1582,12 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_free_netdev;
 	}
 
+	nic->drv_stats = netdev_alloc_pcpu_stats(struct nicvf_drv_stats);
+	if (!nic->drv_stats) {
+		err = -ENOMEM;
+		goto err_free_netdev;
+	}
+
 	err = nicvf_set_qset_resources(nic);
 	if (err)
 		goto err_free_netdev;
@@ -1646,6 +1650,8 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	nicvf_unregister_interrupts(nic);
 err_free_netdev:
 	pci_set_drvdata(pdev, NULL);
+	if (nic->drv_stats)
+		free_percpu(nic->drv_stats);
 	free_netdev(netdev);
 err_release_regions:
 	pci_release_regions(pdev);
@@ -1673,6 +1679,8 @@ static void nicvf_remove(struct pci_dev *pdev)
 		unregister_netdev(pnetdev);
 	nicvf_unregister_interrupts(nic);
 	pci_set_drvdata(pdev, NULL);
+	if (nic->drv_stats)
+		free_percpu(nic->drv_stats);
 	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 a4fc501..747ef08 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -104,7 +104,8 @@ static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp,
 		nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN,
 					   order);
 		if (!nic->rb_page) {
-			nic->drv_stats.rcv_buffer_alloc_failures++;
+			this_cpu_inc(nic->pnicvf->drv_stats->
+				     rcv_buffer_alloc_failures);
 			return -ENOMEM;
 		}
 		nic->rb_page_offset = 0;
@@ -270,7 +271,8 @@ static void nicvf_refill_rbdr(struct nicvf *nic, gfp_t gfp)
 			      rbdr_idx, new_rb);
 next_rbdr:
 	/* Re-enable RBDR interrupts only if buffer allocation is success */
-	if (!nic->rb_alloc_fail && rbdr->enable)
+	if (!nic->rb_alloc_fail && rbdr->enable &&
+	    netif_running(nic->pnicvf->netdev))
 		nicvf_enable_intr(nic, NICVF_INTR_RBDR, rbdr_idx);
 
 	if (rbdr_idx)
@@ -361,6 +363,8 @@ static int nicvf_init_snd_queue(struct nicvf *nic,
 
 static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
 {
+	struct sk_buff *skb;
+
 	if (!sq)
 		return;
 	if (!sq->dmem.base)
@@ -371,6 +375,15 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
 				  sq->dmem.q_len * TSO_HEADER_SIZE,
 				  sq->tso_hdrs, sq->tso_hdrs_phys);
 
+	/* Free pending skbs in the queue */
+	smp_rmb();
+	while (sq->head != sq->tail) {
+		skb = (struct sk_buff *)sq->skbuff[sq->head];
+		if (skb)
+			dev_kfree_skb_any(skb);
+		sq->head++;
+		sq->head &= (sq->dmem.q_len - 1);
+	}
 	kfree(sq->skbuff);
 	nicvf_free_q_desc_mem(nic, &sq->dmem);
 }
@@ -483,9 +496,12 @@ static void nicvf_reset_rcv_queue_stats(struct nicvf *nic)
 {
 	union nic_mbx mbx = {};
 
-	/* Reset all RXQ's stats */
+	/* Reset all RQ/SQ and VF stats */
 	mbx.reset_stat.msg = NIC_MBOX_MSG_RESET_STAT_COUNTER;
+	mbx.reset_stat.rx_stat_mask = 0x3FFF;
+	mbx.reset_stat.tx_stat_mask = 0x1F;
 	mbx.reset_stat.rq_stat_mask = 0xFFFF;
+	mbx.reset_stat.sq_stat_mask = 0xFFFF;
 	nicvf_send_msg_to_pf(nic, &mbx);
 }
 
@@ -538,9 +554,12 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs,
 	mbx.rq.cfg = (1ULL << 62) | (RQ_CQ_DROP << 8);
 	nicvf_send_msg_to_pf(nic, &mbx);
 
-	nicvf_queue_reg_write(nic, NIC_QSET_RQ_GEN_CFG, 0, 0x00);
-	if (!nic->sqs_mode)
+	if (!nic->sqs_mode && (qidx == 0)) {
+		/* Enable checking L3/L4 length and TCP/UDP checksums */
+		nicvf_queue_reg_write(nic, NIC_QSET_RQ_GEN_CFG, 0,
+				      (BIT(24) | BIT(23) | BIT(21)));
 		nicvf_config_vlan_stripping(nic, nic->netdev->features);
+	}
 
 	/* Enable Receive queue */
 	memset(&rq_cfg, 0, sizeof(struct rq_cfg));
@@ -1029,7 +1048,7 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry,
 		hdr->tso_max_paysize = skb_shinfo(skb)->gso_size;
 		/* For non-tunneled pkts, point this to L2 ethertype */
 		hdr->inner_l3_offset = skb_network_offset(skb) - 2;
-		nic->drv_stats.tx_tso++;
+		this_cpu_inc(nic->pnicvf->drv_stats->tx_tso);
 	}
 }
 
@@ -1161,7 +1180,7 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq,
 
 	nicvf_sq_doorbell(nic, skb, sq_num, desc_cnt);
 
-	nic->drv_stats.tx_tso++;
+	this_cpu_inc(nic->pnicvf->drv_stats->tx_tso);
 	return 1;
 }
 
@@ -1422,8 +1441,6 @@ void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx)
 /* Check for errors in the receive cmp.queue entry */
 int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 {
-	struct nicvf_hw_stats *stats = &nic->hw_stats;
-
 	if (!cqe_rx->err_level && !cqe_rx->err_opcode)
 		return 0;
 
@@ -1435,76 +1452,76 @@ int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 
 	switch (cqe_rx->err_opcode) {
 	case CQ_RX_ERROP_RE_PARTIAL:
-		stats->rx_bgx_truncated_pkts++;
+		this_cpu_inc(nic->drv_stats->rx_bgx_truncated_pkts);
 		break;
 	case CQ_RX_ERROP_RE_JABBER:
-		stats->rx_jabber_errs++;
+		this_cpu_inc(nic->drv_stats->rx_jabber_errs);
 		break;
 	case CQ_RX_ERROP_RE_FCS:
-		stats->rx_fcs_errs++;
+		this_cpu_inc(nic->drv_stats->rx_fcs_errs);
 		break;
 	case CQ_RX_ERROP_RE_RX_CTL:
-		stats->rx_bgx_errs++;
+		this_cpu_inc(nic->drv_stats->rx_bgx_errs);
 		break;
 	case CQ_RX_ERROP_PREL2_ERR:
-		stats->rx_prel2_errs++;
+		this_cpu_inc(nic->drv_stats->rx_prel2_errs);
 		break;
 	case CQ_RX_ERROP_L2_MAL:
-		stats->rx_l2_hdr_malformed++;
+		this_cpu_inc(nic->drv_stats->rx_l2_hdr_malformed);
 		break;
 	case CQ_RX_ERROP_L2_OVERSIZE:
-		stats->rx_oversize++;
+		this_cpu_inc(nic->drv_stats->rx_oversize);
 		break;
 	case CQ_RX_ERROP_L2_UNDERSIZE:
-		stats->rx_undersize++;
+		this_cpu_inc(nic->drv_stats->rx_undersize);
 		break;
 	case CQ_RX_ERROP_L2_LENMISM:
-		stats->rx_l2_len_mismatch++;
+		this_cpu_inc(nic->drv_stats->rx_l2_len_mismatch);
 		break;
 	case CQ_RX_ERROP_L2_PCLP:
-		stats->rx_l2_pclp++;
+		this_cpu_inc(nic->drv_stats->rx_l2_pclp);
 		break;
 	case CQ_RX_ERROP_IP_NOT:
-		stats->rx_ip_ver_errs++;
+		this_cpu_inc(nic->drv_stats->rx_ip_ver_errs);
 		break;
 	case CQ_RX_ERROP_IP_CSUM_ERR:
-		stats->rx_ip_csum_errs++;
+		this_cpu_inc(nic->drv_stats->rx_ip_csum_errs);
 		break;
 	case CQ_RX_ERROP_IP_MAL:
-		stats->rx_ip_hdr_malformed++;
+		this_cpu_inc(nic->drv_stats->rx_ip_hdr_malformed);
 		break;
 	case CQ_RX_ERROP_IP_MALD:
-		stats->rx_ip_payload_malformed++;
+		this_cpu_inc(nic->drv_stats->rx_ip_payload_malformed);
 		break;
 	case CQ_RX_ERROP_IP_HOP:
-		stats->rx_ip_ttl_errs++;
+		this_cpu_inc(nic->drv_stats->rx_ip_ttl_errs);
 		break;
 	case CQ_RX_ERROP_L3_PCLP:
-		stats->rx_l3_pclp++;
+		this_cpu_inc(nic->drv_stats->rx_l3_pclp);
 		break;
 	case CQ_RX_ERROP_L4_MAL:
-		stats->rx_l4_malformed++;
+		this_cpu_inc(nic->drv_stats->rx_l4_malformed);
 		break;
 	case CQ_RX_ERROP_L4_CHK:
-		stats->rx_l4_csum_errs++;
+		this_cpu_inc(nic->drv_stats->rx_l4_csum_errs);
 		break;
 	case CQ_RX_ERROP_UDP_LEN:
-		stats->rx_udp_len_errs++;
+		this_cpu_inc(nic->drv_stats->rx_udp_len_errs);
 		break;
 	case CQ_RX_ERROP_L4_PORT:
-		stats->rx_l4_port_errs++;
+		this_cpu_inc(nic->drv_stats->rx_l4_port_errs);
 		break;
 	case CQ_RX_ERROP_TCP_FLAG:
-		stats->rx_tcp_flag_errs++;
+		this_cpu_inc(nic->drv_stats->rx_tcp_flag_errs);
 		break;
 	case CQ_RX_ERROP_TCP_OFFSET:
-		stats->rx_tcp_offset_errs++;
+		this_cpu_inc(nic->drv_stats->rx_tcp_offset_errs);
 		break;
 	case CQ_RX_ERROP_L4_PCLP:
-		stats->rx_l4_pclp++;
+		this_cpu_inc(nic->drv_stats->rx_l4_pclp);
 		break;
 	case CQ_RX_ERROP_RBDR_TRUNC:
-		stats->rx_truncated_pkts++;
+		this_cpu_inc(nic->drv_stats->rx_truncated_pkts);
 		break;
 	}
 
@@ -1512,53 +1529,52 @@ int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 }
 
 /* Check for errors in the send cmp.queue entry */
-int nicvf_check_cqe_tx_errs(struct nicvf *nic,
-			    struct cmp_queue *cq, struct cqe_send_t *cqe_tx)
+int nicvf_check_cqe_tx_errs(struct nicvf *nic, struct cqe_send_t *cqe_tx)
 {
-	struct cmp_queue_stats *stats = &cq->stats;
-
 	switch (cqe_tx->send_status) {
 	case CQ_TX_ERROP_GOOD:
-		stats->tx.good++;
 		return 0;
 	case CQ_TX_ERROP_DESC_FAULT:
-		stats->tx.desc_fault++;
+		this_cpu_inc(nic->drv_stats->tx_desc_fault);
 		break;
 	case CQ_TX_ERROP_HDR_CONS_ERR:
-		stats->tx.hdr_cons_err++;
+		this_cpu_inc(nic->drv_stats->tx_hdr_cons_err);
 		break;
 	case CQ_TX_ERROP_SUBDC_ERR:
-		stats->tx.subdesc_err++;
+		this_cpu_inc(nic->drv_stats->tx_subdesc_err);
+		break;
+	case CQ_TX_ERROP_MAX_SIZE_VIOL:
+		this_cpu_inc(nic->drv_stats->tx_max_size_exceeded);
 		break;
 	case CQ_TX_ERROP_IMM_SIZE_OFLOW:
-		stats->tx.imm_size_oflow++;
+		this_cpu_inc(nic->drv_stats->tx_imm_size_oflow);
 		break;
 	case CQ_TX_ERROP_DATA_SEQUENCE_ERR:
-		stats->tx.data_seq_err++;
+		this_cpu_inc(nic->drv_stats->tx_data_seq_err);
 		break;
 	case CQ_TX_ERROP_MEM_SEQUENCE_ERR:
-		stats->tx.mem_seq_err++;
+		this_cpu_inc(nic->drv_stats->tx_mem_seq_err);
 		break;
 	case CQ_TX_ERROP_LOCK_VIOL:
-		stats->tx.lock_viol++;
+		this_cpu_inc(nic->drv_stats->tx_lock_viol);
 		break;
 	case CQ_TX_ERROP_DATA_FAULT:
-		stats->tx.data_fault++;
+		this_cpu_inc(nic->drv_stats->tx_data_fault);
 		break;
 	case CQ_TX_ERROP_TSTMP_CONFLICT:
-		stats->tx.tstmp_conflict++;
+		this_cpu_inc(nic->drv_stats->tx_tstmp_conflict);
 		break;
 	case CQ_TX_ERROP_TSTMP_TIMEOUT:
-		stats->tx.tstmp_timeout++;
+		this_cpu_inc(nic->drv_stats->tx_tstmp_timeout);
 		break;
 	case CQ_TX_ERROP_MEM_FAULT:
-		stats->tx.mem_fault++;
+		this_cpu_inc(nic->drv_stats->tx_mem_fault);
 		break;
 	case CQ_TX_ERROP_CK_OVERLAP:
-		stats->tx.csum_overlap++;
+		this_cpu_inc(nic->drv_stats->tx_csum_overlap);
 		break;
 	case CQ_TX_ERROP_CK_OFLOW:
-		stats->tx.csum_overflow++;
+		this_cpu_inc(nic->drv_stats->tx_csum_overflow);
 		break;
 	}
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index 869f338..2e3c940 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -158,6 +158,7 @@ enum CQ_TX_ERROP_E {
 	CQ_TX_ERROP_DESC_FAULT = 0x10,
 	CQ_TX_ERROP_HDR_CONS_ERR = 0x11,
 	CQ_TX_ERROP_SUBDC_ERR = 0x12,
+	CQ_TX_ERROP_MAX_SIZE_VIOL = 0x13,
 	CQ_TX_ERROP_IMM_SIZE_OFLOW = 0x80,
 	CQ_TX_ERROP_DATA_SEQUENCE_ERR = 0x81,
 	CQ_TX_ERROP_MEM_SEQUENCE_ERR = 0x82,
@@ -171,25 +172,6 @@ enum CQ_TX_ERROP_E {
 	CQ_TX_ERROP_ENUM_LAST = 0x8a,
 };
 
-struct cmp_queue_stats {
-	struct tx_stats {
-		u64 good;
-		u64 desc_fault;
-		u64 hdr_cons_err;
-		u64 subdesc_err;
-		u64 imm_size_oflow;
-		u64 data_seq_err;
-		u64 mem_seq_err;
-		u64 lock_viol;
-		u64 data_fault;
-		u64 tstmp_conflict;
-		u64 tstmp_timeout;
-		u64 mem_fault;
-		u64 csum_overlap;
-		u64 csum_overflow;
-	} tx;
-} ____cacheline_aligned_in_smp;
-
 enum RQ_SQ_STATS {
 	RQ_SQ_STATS_OCTS,
 	RQ_SQ_STATS_PKTS,
@@ -241,7 +223,6 @@ struct cmp_queue {
 	spinlock_t	lock;  /* lock to serialize processing CQEs */
 	void		*desc;
 	struct q_desc_mem   dmem;
-	struct cmp_queue_stats	stats;
 	int		irq;
 } ____cacheline_aligned_in_smp;
 
@@ -336,6 +317,5 @@ u64  nicvf_queue_reg_read(struct nicvf *nic,
 void nicvf_update_rq_stats(struct nicvf *nic, int rq_idx);
 void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx);
 int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx);
-int nicvf_check_cqe_tx_errs(struct nicvf *nic,
-			    struct cmp_queue *cq, struct cqe_send_t *cqe_tx);
+int nicvf_check_cqe_tx_errs(struct nicvf *nic, struct cqe_send_t *cqe_tx);
 #endif /* NICVF_QUEUES_H */
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 8bbaedb..050e21f 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -1242,8 +1242,8 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_read_config_word(pdev, PCI_DEVICE_ID, &sdevid);
 	if (sdevid != PCI_DEVICE_ID_THUNDER_RGX) {
-		bgx->bgx_id =
-		    (pci_resource_start(pdev, PCI_CFG_REG_BAR_NUM) >> 24) & 1;
+		bgx->bgx_id = (pci_resource_start(pdev,
+			PCI_CFG_REG_BAR_NUM) >> 24) & BGX_ID_MASK;
 		bgx->bgx_id += nic_get_node_id(pdev) * MAX_BGX_PER_NODE;
 		bgx->max_lmac = MAX_LMAC_PER_BGX;
 		bgx_vnic[bgx->bgx_id] = bgx;
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index d59c71e..01cc7c8 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -28,6 +28,8 @@
 #define    MAX_DMAC_PER_LMAC			8
 #define    MAX_FRAME_SIZE			9216
 
+#define	   BGX_ID_MASK				0x3
+
 #define    MAX_DMAC_PER_LMAC_TNS_BYPASS_MODE	2
 
 /* Registers */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index b7d0753..9f60647 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -2997,7 +2997,6 @@ void free_rspq_fl(struct adapter *adap, struct sge_rspq *rq,
 		   rq->cntxt_id, fl_id, 0xffff);
 	dma_free_coherent(adap->pdev_dev, (rq->size + 1) * rq->iqe_len,
 			  rq->desc, rq->phys_addr);
-	napi_hash_del(&rq->napi);
 	netif_napi_del(&rq->napi);
 	rq->netdev = NULL;
 	rq->cntxt_id = rq->abs_id = 0;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 3f6152c..7e1633b 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -2796,7 +2796,6 @@ static void be_evt_queues_destroy(struct be_adapter *adapter)
 		if (eqo->q.created) {
 			be_eq_clean(eqo);
 			be_cmd_q_destroy(adapter, &eqo->q, QTYPE_EQ);
-			napi_hash_del(&eqo->napi);
 			netif_napi_del(&eqo->napi);
 			free_cpumask_var(eqo->affinity_mask);
 		}
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index aa60f4d..b60ad0e 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -5218,6 +5218,19 @@ static SIMPLE_DEV_PM_OPS(sky2_pm_ops, sky2_suspend, sky2_resume);
 
 static void sky2_shutdown(struct pci_dev *pdev)
 {
+	struct sky2_hw *hw = pci_get_drvdata(pdev);
+	int port;
+
+	for (port = 0; port < hw->ports; port++) {
+		struct net_device *ndev = hw->dev[port];
+
+		rtnl_lock();
+		if (netif_running(ndev)) {
+			dev_close(ndev);
+			netif_device_detach(ndev);
+		}
+		rtnl_unlock();
+	}
 	sky2_suspend(&pdev->dev);
 	pci_wake_from_d3(pdev, device_may_wakeup(&pdev->dev));
 	pci_set_power_state(pdev, PCI_D3hot);
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 6e9fcc3..d37e32d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -118,7 +118,7 @@
 config DWMAC_STM32
 	tristate "STM32 DWMAC support"
 	default ARCH_STM32
-	depends on OF && HAS_IOMEM
+	depends on OF && HAS_IOMEM && (ARCH_STM32 || COMPILE_TEST)
 	select MFD_SYSCON
 	---help---
 	  Support for ethernet controller on STM32 SOCs.
diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
index 2920e2e..489ef14 100644
--- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
@@ -63,8 +63,8 @@
 #define TSE_PCS_SGMII_LINK_TIMER_0			0x0D40
 #define TSE_PCS_SGMII_LINK_TIMER_1			0x0003
 #define TSE_PCS_SW_RESET_TIMEOUT			100
-#define TSE_PCS_USE_SGMII_AN_MASK			BIT(2)
-#define TSE_PCS_USE_SGMII_ENA				BIT(1)
+#define TSE_PCS_USE_SGMII_AN_MASK			BIT(1)
+#define TSE_PCS_USE_SGMII_ENA				BIT(0)
 
 #define SGMII_ADAPTER_CTRL_REG				0x00
 #define SGMII_ADAPTER_DISABLE				0x0001
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index d3292c4a..6d2de4e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -120,14 +120,17 @@ struct stmmac_extra_stats {
 	unsigned long ip_csum_bypassed;
 	unsigned long ipv4_pkt_rcvd;
 	unsigned long ipv6_pkt_rcvd;
-	unsigned long rx_msg_type_ext_no_ptp;
-	unsigned long rx_msg_type_sync;
-	unsigned long rx_msg_type_follow_up;
-	unsigned long rx_msg_type_delay_req;
-	unsigned long rx_msg_type_delay_resp;
-	unsigned long rx_msg_type_pdelay_req;
-	unsigned long rx_msg_type_pdelay_resp;
-	unsigned long rx_msg_type_pdelay_follow_up;
+	unsigned long no_ptp_rx_msg_type_ext;
+	unsigned long ptp_rx_msg_type_sync;
+	unsigned long ptp_rx_msg_type_follow_up;
+	unsigned long ptp_rx_msg_type_delay_req;
+	unsigned long ptp_rx_msg_type_delay_resp;
+	unsigned long ptp_rx_msg_type_pdelay_req;
+	unsigned long ptp_rx_msg_type_pdelay_resp;
+	unsigned long ptp_rx_msg_type_pdelay_follow_up;
+	unsigned long ptp_rx_msg_type_announce;
+	unsigned long ptp_rx_msg_type_management;
+	unsigned long ptp_rx_msg_pkt_reserved_type;
 	unsigned long ptp_frame_type;
 	unsigned long ptp_ver;
 	unsigned long timestamp_dropped;
@@ -482,11 +485,12 @@ struct stmmac_ops {
 /* PTP and HW Timer helpers */
 struct stmmac_hwtimestamp {
 	void (*config_hw_tstamping) (void __iomem *ioaddr, u32 data);
-	u32 (*config_sub_second_increment) (void __iomem *ioaddr, u32 clk_rate);
+	u32 (*config_sub_second_increment)(void __iomem *ioaddr, u32 ptp_clock,
+					   int gmac4);
 	int (*init_systime) (void __iomem *ioaddr, u32 sec, u32 nsec);
 	int (*config_addend) (void __iomem *ioaddr, u32 addend);
 	int (*adjust_systime) (void __iomem *ioaddr, u32 sec, u32 nsec,
-			       int add_sub);
+			       int add_sub, int gmac4);
 	 u64(*get_systime) (void __iomem *ioaddr);
 };
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/descs.h b/drivers/net/ethernet/stmicro/stmmac/descs.h
index 4000af4..faeeef7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/descs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/descs.h
@@ -155,14 +155,18 @@
 #define	ERDES4_L3_L4_FILT_NO_MATCH_MASK	GENMASK(27, 26)
 
 /* Extended RDES4 message type definitions */
-#define RDES_EXT_NO_PTP			0
-#define RDES_EXT_SYNC			1
-#define RDES_EXT_FOLLOW_UP		2
-#define RDES_EXT_DELAY_REQ		3
-#define RDES_EXT_DELAY_RESP		4
-#define RDES_EXT_PDELAY_REQ		5
-#define RDES_EXT_PDELAY_RESP		6
-#define RDES_EXT_PDELAY_FOLLOW_UP	7
+#define RDES_EXT_NO_PTP			0x0
+#define RDES_EXT_SYNC			0x1
+#define RDES_EXT_FOLLOW_UP		0x2
+#define RDES_EXT_DELAY_REQ		0x3
+#define RDES_EXT_DELAY_RESP		0x4
+#define RDES_EXT_PDELAY_REQ		0x5
+#define RDES_EXT_PDELAY_RESP		0x6
+#define RDES_EXT_PDELAY_FOLLOW_UP	0x7
+#define RDES_PTP_ANNOUNCE		0x8
+#define RDES_PTP_MANAGEMENT		0x9
+#define RDES_PTP_SIGNALING		0xa
+#define RDES_PTP_PKT_RESERVED_TYPE	0xf
 
 /* Basic descriptor structure for normal and alternate descriptors */
 struct dma_desc {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index bec72d3..a340fc8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -123,22 +123,29 @@ static int dwmac4_wrback_get_rx_status(void *data, struct stmmac_extra_stats *x,
 		x->ipv4_pkt_rcvd++;
 	if (rdes1 & RDES1_IPV6_HEADER)
 		x->ipv6_pkt_rcvd++;
-	if (message_type == RDES_EXT_SYNC)
-		x->rx_msg_type_sync++;
+
+	if (message_type == RDES_EXT_NO_PTP)
+		x->no_ptp_rx_msg_type_ext++;
+	else if (message_type == RDES_EXT_SYNC)
+		x->ptp_rx_msg_type_sync++;
 	else if (message_type == RDES_EXT_FOLLOW_UP)
-		x->rx_msg_type_follow_up++;
+		x->ptp_rx_msg_type_follow_up++;
 	else if (message_type == RDES_EXT_DELAY_REQ)
-		x->rx_msg_type_delay_req++;
+		x->ptp_rx_msg_type_delay_req++;
 	else if (message_type == RDES_EXT_DELAY_RESP)
-		x->rx_msg_type_delay_resp++;
+		x->ptp_rx_msg_type_delay_resp++;
 	else if (message_type == RDES_EXT_PDELAY_REQ)
-		x->rx_msg_type_pdelay_req++;
+		x->ptp_rx_msg_type_pdelay_req++;
 	else if (message_type == RDES_EXT_PDELAY_RESP)
-		x->rx_msg_type_pdelay_resp++;
+		x->ptp_rx_msg_type_pdelay_resp++;
 	else if (message_type == RDES_EXT_PDELAY_FOLLOW_UP)
-		x->rx_msg_type_pdelay_follow_up++;
-	else
-		x->rx_msg_type_ext_no_ptp++;
+		x->ptp_rx_msg_type_pdelay_follow_up++;
+	else if (message_type == RDES_PTP_ANNOUNCE)
+		x->ptp_rx_msg_type_announce++;
+	else if (message_type == RDES_PTP_MANAGEMENT)
+		x->ptp_rx_msg_type_management++;
+	else if (message_type == RDES_PTP_PKT_RESERVED_TYPE)
+		x->ptp_rx_msg_pkt_reserved_type++;
 
 	if (rdes1 & RDES1_PTP_PACKET_TYPE)
 		x->ptp_frame_type++;
@@ -205,14 +212,18 @@ static void dwmac4_rd_enable_tx_timestamp(struct dma_desc *p)
 
 static int dwmac4_wrback_get_tx_timestamp_status(struct dma_desc *p)
 {
-	return (le32_to_cpu(p->des3) & TDES3_TIMESTAMP_STATUS)
-		>> TDES3_TIMESTAMP_STATUS_SHIFT;
+	/* Context type from W/B descriptor must be zero */
+	if (le32_to_cpu(p->des3) & TDES3_CONTEXT_TYPE)
+		return -EINVAL;
+
+	/* Tx Timestamp Status is 1 so des0 and des1'll have valid values */
+	if (le32_to_cpu(p->des3) & TDES3_TIMESTAMP_STATUS)
+		return 0;
+
+	return 1;
 }
 
-/*  NOTE: For RX CTX bit has to be checked before
- *  HAVE a specific function for TX and another one for RX
- */
-static u64 dwmac4_wrback_get_timestamp(void *desc, u32 ats)
+static inline u64 dwmac4_get_timestamp(void *desc, u32 ats)
 {
 	struct dma_desc *p = (struct dma_desc *)desc;
 	u64 ns;
@@ -224,12 +235,54 @@ static u64 dwmac4_wrback_get_timestamp(void *desc, u32 ats)
 	return ns;
 }
 
-static int dwmac4_context_get_rx_timestamp_status(void *desc, u32 ats)
+static int dwmac4_rx_check_timestamp(void *desc)
 {
 	struct dma_desc *p = (struct dma_desc *)desc;
+	u32 own, ctxt;
+	int ret = 1;
 
-	return (le32_to_cpu(p->des1) & RDES1_TIMESTAMP_AVAILABLE)
-		>> RDES1_TIMESTAMP_AVAILABLE_SHIFT;
+	own = p->des3 & RDES3_OWN;
+	ctxt = ((p->des3 & RDES3_CONTEXT_DESCRIPTOR)
+		>> RDES3_CONTEXT_DESCRIPTOR_SHIFT);
+
+	if (likely(!own && ctxt)) {
+		if ((p->des0 == 0xffffffff) && (p->des1 == 0xffffffff))
+			/* Corrupted value */
+			ret = -EINVAL;
+		else
+			/* A valid Timestamp is ready to be read */
+			ret = 0;
+	}
+
+	/* Timestamp not ready */
+	return ret;
+}
+
+static int dwmac4_wrback_get_rx_timestamp_status(void *desc, u32 ats)
+{
+	struct dma_desc *p = (struct dma_desc *)desc;
+	int ret = -EINVAL;
+
+	/* Get the status from normal w/b descriptor */
+	if (likely(p->des3 & TDES3_RS1V)) {
+		if (likely(le32_to_cpu(p->des1) & RDES1_TIMESTAMP_AVAILABLE)) {
+			int i = 0;
+
+			/* Check if timestamp is OK from context descriptor */
+			do {
+				ret = dwmac4_rx_check_timestamp(desc);
+				if (ret < 0)
+					goto exit;
+				i++;
+
+			} while ((ret == 1) || (i < 10));
+
+			if (i == 10)
+				ret = -EBUSY;
+		}
+	}
+exit:
+	return ret;
 }
 
 static void dwmac4_rd_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
@@ -375,8 +428,8 @@ const struct stmmac_desc_ops dwmac4_desc_ops = {
 	.get_rx_frame_len = dwmac4_wrback_get_rx_frame_len,
 	.enable_tx_timestamp = dwmac4_rd_enable_tx_timestamp,
 	.get_tx_timestamp_status = dwmac4_wrback_get_tx_timestamp_status,
-	.get_timestamp = dwmac4_wrback_get_timestamp,
-	.get_rx_timestamp_status = dwmac4_context_get_rx_timestamp_status,
+	.get_rx_timestamp_status = dwmac4_wrback_get_rx_timestamp_status,
+	.get_timestamp = dwmac4_get_timestamp,
 	.set_tx_ic = dwmac4_rd_set_tx_ic,
 	.prepare_tx_desc = dwmac4_rd_prepare_tx_desc,
 	.prepare_tso_tx_desc = dwmac4_rd_prepare_tso_tx_desc,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
index 0902a2e..9736c50 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
@@ -59,10 +59,13 @@
 #define TDES3_CTXT_TCMSSV		BIT(26)
 
 /* TDES3 Common */
+#define	TDES3_RS1V			BIT(26)
+#define	TDES3_RS1V_SHIFT		26
 #define TDES3_LAST_DESCRIPTOR		BIT(28)
 #define TDES3_LAST_DESCRIPTOR_SHIFT	28
 #define TDES3_FIRST_DESCRIPTOR		BIT(29)
 #define TDES3_CONTEXT_TYPE		BIT(30)
+#define	TDES3_CONTEXT_TYPE_SHIFT	30
 
 /* TDS3 use for both format (read and write back) */
 #define TDES3_OWN			BIT(31)
@@ -117,6 +120,7 @@
 #define RDES3_LAST_DESCRIPTOR		BIT(28)
 #define RDES3_FIRST_DESCRIPTOR		BIT(29)
 #define RDES3_CONTEXT_DESCRIPTOR	BIT(30)
+#define RDES3_CONTEXT_DESCRIPTOR_SHIFT	30
 
 /* RDES3 (read format) */
 #define RDES3_BUFFER1_VALID_ADDR	BIT(24)
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 8295aa9..ce97e52 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -150,22 +150,30 @@ static void enh_desc_get_ext_status(void *data, struct stmmac_extra_stats *x,
 			x->ipv4_pkt_rcvd++;
 		if (rdes4 & ERDES4_IPV6_PKT_RCVD)
 			x->ipv6_pkt_rcvd++;
-		if (message_type == RDES_EXT_SYNC)
-			x->rx_msg_type_sync++;
+
+		if (message_type == RDES_EXT_NO_PTP)
+			x->no_ptp_rx_msg_type_ext++;
+		else if (message_type == RDES_EXT_SYNC)
+			x->ptp_rx_msg_type_sync++;
 		else if (message_type == RDES_EXT_FOLLOW_UP)
-			x->rx_msg_type_follow_up++;
+			x->ptp_rx_msg_type_follow_up++;
 		else if (message_type == RDES_EXT_DELAY_REQ)
-			x->rx_msg_type_delay_req++;
+			x->ptp_rx_msg_type_delay_req++;
 		else if (message_type == RDES_EXT_DELAY_RESP)
-			x->rx_msg_type_delay_resp++;
+			x->ptp_rx_msg_type_delay_resp++;
 		else if (message_type == RDES_EXT_PDELAY_REQ)
-			x->rx_msg_type_pdelay_req++;
+			x->ptp_rx_msg_type_pdelay_req++;
 		else if (message_type == RDES_EXT_PDELAY_RESP)
-			x->rx_msg_type_pdelay_resp++;
+			x->ptp_rx_msg_type_pdelay_resp++;
 		else if (message_type == RDES_EXT_PDELAY_FOLLOW_UP)
-			x->rx_msg_type_pdelay_follow_up++;
-		else
-			x->rx_msg_type_ext_no_ptp++;
+			x->ptp_rx_msg_type_pdelay_follow_up++;
+		else if (message_type == RDES_PTP_ANNOUNCE)
+			x->ptp_rx_msg_type_announce++;
+		else if (message_type == RDES_PTP_MANAGEMENT)
+			x->ptp_rx_msg_type_management++;
+		else if (message_type == RDES_PTP_PKT_RESERVED_TYPE)
+			x->ptp_rx_msg_pkt_reserved_type++;
+
 		if (rdes4 & ERDES4_PTP_FRAME_TYPE)
 			x->ptp_frame_type++;
 		if (rdes4 & ERDES4_PTP_VER)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 758b4e2..dbacb80 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -128,6 +128,7 @@ struct stmmac_priv {
 	int irq_wake;
 	spinlock_t ptp_lock;
 	void __iomem *mmcaddr;
+	void __iomem *ptpaddr;
 	u32 rx_tail_addr;
 	u32 tx_tail_addr;
 	u32 mss;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 0290d52..d5a8122 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -115,14 +115,17 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = {
 	STMMAC_STAT(ip_csum_bypassed),
 	STMMAC_STAT(ipv4_pkt_rcvd),
 	STMMAC_STAT(ipv6_pkt_rcvd),
-	STMMAC_STAT(rx_msg_type_ext_no_ptp),
-	STMMAC_STAT(rx_msg_type_sync),
-	STMMAC_STAT(rx_msg_type_follow_up),
-	STMMAC_STAT(rx_msg_type_delay_req),
-	STMMAC_STAT(rx_msg_type_delay_resp),
-	STMMAC_STAT(rx_msg_type_pdelay_req),
-	STMMAC_STAT(rx_msg_type_pdelay_resp),
-	STMMAC_STAT(rx_msg_type_pdelay_follow_up),
+	STMMAC_STAT(no_ptp_rx_msg_type_ext),
+	STMMAC_STAT(ptp_rx_msg_type_sync),
+	STMMAC_STAT(ptp_rx_msg_type_follow_up),
+	STMMAC_STAT(ptp_rx_msg_type_delay_req),
+	STMMAC_STAT(ptp_rx_msg_type_delay_resp),
+	STMMAC_STAT(ptp_rx_msg_type_pdelay_req),
+	STMMAC_STAT(ptp_rx_msg_type_pdelay_resp),
+	STMMAC_STAT(ptp_rx_msg_type_pdelay_follow_up),
+	STMMAC_STAT(ptp_rx_msg_type_announce),
+	STMMAC_STAT(ptp_rx_msg_type_management),
+	STMMAC_STAT(ptp_rx_msg_pkt_reserved_type),
 	STMMAC_STAT(ptp_frame_type),
 	STMMAC_STAT(ptp_ver),
 	STMMAC_STAT(timestamp_dropped),
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index a77f689..10d6059 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -34,21 +34,29 @@ static void stmmac_config_hw_tstamping(void __iomem *ioaddr, u32 data)
 }
 
 static u32 stmmac_config_sub_second_increment(void __iomem *ioaddr,
-					      u32 ptp_clock)
+					      u32 ptp_clock, int gmac4)
 {
 	u32 value = readl(ioaddr + PTP_TCR);
 	unsigned long data;
 
-	/* Convert the ptp_clock to nano second
-	 * formula = (2/ptp_clock) * 1000000000
-	 * where, ptp_clock = 50MHz.
+	/* For GMAC3.x, 4.x versions, convert the ptp_clock to nano second
+	 *	formula = (1/ptp_clock) * 1000000000
+	 * where ptp_clock is 50MHz if fine method is used to update system
 	 */
-	data = (2000000000ULL / ptp_clock);
+	if (value & PTP_TCR_TSCFUPDT)
+		data = (1000000000ULL / 50000000);
+	else
+		data = (1000000000ULL / ptp_clock);
 
 	/* 0.465ns accuracy */
 	if (!(value & PTP_TCR_TSCTRLSSR))
 		data = (data * 1000) / 465;
 
+	data &= PTP_SSIR_SSINC_MASK;
+
+	if (gmac4)
+		data = data << GMAC4_PTP_SSIR_SSINC_SHIFT;
+
 	writel(data, ioaddr + PTP_SSIR);
 
 	return data;
@@ -104,14 +112,30 @@ static int stmmac_config_addend(void __iomem *ioaddr, u32 addend)
 }
 
 static int stmmac_adjust_systime(void __iomem *ioaddr, u32 sec, u32 nsec,
-				 int add_sub)
+				 int add_sub, int gmac4)
 {
 	u32 value;
 	int limit;
 
+	if (add_sub) {
+		/* If the new sec value needs to be subtracted with
+		 * the system time, then MAC_STSUR reg should be
+		 * programmed with (2^32 – <new_sec_value>)
+		 */
+		if (gmac4)
+			sec = (100000000ULL - sec);
+
+		value = readl(ioaddr + PTP_TCR);
+		if (value & PTP_TCR_TSCTRLSSR)
+			nsec = (PTP_DIGITAL_ROLLOVER_MODE - nsec);
+		else
+			nsec = (PTP_BINARY_ROLLOVER_MODE - nsec);
+	}
+
 	writel(sec, ioaddr + PTP_STSUR);
-	writel(((add_sub << PTP_STNSUR_ADDSUB_SHIFT) | nsec),
-		ioaddr + PTP_STNSUR);
+	value = (add_sub << PTP_STNSUR_ADDSUB_SHIFT) | nsec;
+	writel(value, ioaddr + PTP_STNSUR);
+
 	/* issue command to initialize the system time value */
 	value = readl(ioaddr + PTP_TCR);
 	value |= PTP_TCR_TSUPDT;
@@ -134,8 +158,9 @@ static u64 stmmac_get_systime(void __iomem *ioaddr)
 {
 	u64 ns;
 
+	/* Get the TSSS value */
 	ns = readl(ioaddr + PTP_STNSR);
-	/* convert sec time value to nanosecond */
+	/* Get the TSS and convert sec time value to nanosecond */
 	ns += readl(ioaddr + PTP_STSR) * 1000000000ULL;
 
 	return ns;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index fbd1cd7..29557d2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -342,18 +342,17 @@ bool stmmac_eee_init(struct stmmac_priv *priv)
 
 /* stmmac_get_tx_hwtstamp - get HW TX timestamps
  * @priv: driver private structure
- * @entry : descriptor index to be used.
+ * @p : descriptor pointer
  * @skb : the socket buffer
  * Description :
  * This function will read timestamp from the descriptor & pass it to stack.
  * and also perform some sanity checks.
  */
 static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv,
-				   unsigned int entry, struct sk_buff *skb)
+				   struct dma_desc *p, struct sk_buff *skb)
 {
 	struct skb_shared_hwtstamps shhwtstamp;
 	u64 ns;
-	void *desc = NULL;
 
 	if (!priv->hwts_tx_en)
 		return;
@@ -362,58 +361,55 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv,
 	if (likely(!skb || !(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)))
 		return;
 
-	if (priv->adv_ts)
-		desc = (priv->dma_etx + entry);
-	else
-		desc = (priv->dma_tx + entry);
-
 	/* check tx tstamp status */
-	if (!priv->hw->desc->get_tx_timestamp_status((struct dma_desc *)desc))
-		return;
+	if (!priv->hw->desc->get_tx_timestamp_status(p)) {
+		/* get the valid tstamp */
+		ns = priv->hw->desc->get_timestamp(p, priv->adv_ts);
 
-	/* get the valid tstamp */
-	ns = priv->hw->desc->get_timestamp(desc, priv->adv_ts);
+		memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps));
+		shhwtstamp.hwtstamp = ns_to_ktime(ns);
 
-	memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps));
-	shhwtstamp.hwtstamp = ns_to_ktime(ns);
-	/* pass tstamp to stack */
-	skb_tstamp_tx(skb, &shhwtstamp);
+		netdev_info(priv->dev, "get valid TX hw timestamp %llu\n", ns);
+		/* pass tstamp to stack */
+		skb_tstamp_tx(skb, &shhwtstamp);
+	}
 
 	return;
 }
 
 /* stmmac_get_rx_hwtstamp - get HW RX timestamps
  * @priv: driver private structure
- * @entry : descriptor index to be used.
+ * @p : descriptor pointer
+ * @np : next descriptor pointer
  * @skb : the socket buffer
  * Description :
  * This function will read received packet's timestamp from the descriptor
  * and pass it to stack. It also perform some sanity checks.
  */
-static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv,
-				   unsigned int entry, struct sk_buff *skb)
+static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p,
+				   struct dma_desc *np, struct sk_buff *skb)
 {
 	struct skb_shared_hwtstamps *shhwtstamp = NULL;
 	u64 ns;
-	void *desc = NULL;
 
 	if (!priv->hwts_rx_en)
 		return;
 
-	if (priv->adv_ts)
-		desc = (priv->dma_erx + entry);
-	else
-		desc = (priv->dma_rx + entry);
+	/* Check if timestamp is available */
+	if (!priv->hw->desc->get_rx_timestamp_status(p, priv->adv_ts)) {
+		/* For GMAC4, the valid timestamp is from CTX next desc. */
+		if (priv->plat->has_gmac4)
+			ns = priv->hw->desc->get_timestamp(np, priv->adv_ts);
+		else
+			ns = priv->hw->desc->get_timestamp(p, priv->adv_ts);
 
-	/* exit if rx tstamp is not valid */
-	if (!priv->hw->desc->get_rx_timestamp_status(desc, priv->adv_ts))
-		return;
-
-	/* get valid tstamp */
-	ns = priv->hw->desc->get_timestamp(desc, priv->adv_ts);
-	shhwtstamp = skb_hwtstamps(skb);
-	memset(shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps));
-	shhwtstamp->hwtstamp = ns_to_ktime(ns);
+		netdev_info(priv->dev, "get valid RX hw timestamp %llu\n", ns);
+		shhwtstamp = skb_hwtstamps(skb);
+		memset(shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps));
+		shhwtstamp->hwtstamp = ns_to_ktime(ns);
+	} else  {
+		netdev_err(priv->dev, "cannot get RX hw timestamp\n");
+	}
 }
 
 /**
@@ -600,17 +596,18 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 	priv->hwts_tx_en = config.tx_type == HWTSTAMP_TX_ON;
 
 	if (!priv->hwts_tx_en && !priv->hwts_rx_en)
-		priv->hw->ptp->config_hw_tstamping(priv->ioaddr, 0);
+		priv->hw->ptp->config_hw_tstamping(priv->ptpaddr, 0);
 	else {
 		value = (PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | PTP_TCR_TSCTRLSSR |
 			 tstamp_all | ptp_v2 | ptp_over_ethernet |
 			 ptp_over_ipv6_udp | ptp_over_ipv4_udp | ts_event_en |
 			 ts_master_en | snap_type_sel);
-		priv->hw->ptp->config_hw_tstamping(priv->ioaddr, value);
+		priv->hw->ptp->config_hw_tstamping(priv->ptpaddr, value);
 
 		/* program Sub Second Increment reg */
 		sec_inc = priv->hw->ptp->config_sub_second_increment(
-			priv->ioaddr, priv->clk_ptp_rate);
+			priv->ptpaddr, priv->clk_ptp_rate,
+			priv->plat->has_gmac4);
 		temp = div_u64(1000000000ULL, sec_inc);
 
 		/* calculate default added value:
@@ -620,14 +617,14 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 		 */
 		temp = (u64)(temp << 32);
 		priv->default_addend = div_u64(temp, priv->clk_ptp_rate);
-		priv->hw->ptp->config_addend(priv->ioaddr,
+		priv->hw->ptp->config_addend(priv->ptpaddr,
 					     priv->default_addend);
 
 		/* initialize system time */
 		ktime_get_real_ts64(&now);
 
 		/* lower 32 bits of tv_sec are safe until y2106 */
-		priv->hw->ptp->init_systime(priv->ioaddr, (u32)now.tv_sec,
+		priv->hw->ptp->init_systime(priv->ptpaddr, (u32)now.tv_sec,
 					    now.tv_nsec);
 	}
 
@@ -1341,7 +1338,7 @@ static void stmmac_tx_clean(struct stmmac_priv *priv)
 				priv->dev->stats.tx_packets++;
 				priv->xstats.tx_pkt_n++;
 			}
-			stmmac_get_tx_hwtstamp(priv, entry, skb);
+			stmmac_get_tx_hwtstamp(priv, p, skb);
 		}
 
 		if (likely(priv->tx_skbuff_dma[entry].buf)) {
@@ -1487,10 +1484,13 @@ static void stmmac_mmc_setup(struct stmmac_priv *priv)
 	unsigned int mode = MMC_CNTRL_RESET_ON_READ | MMC_CNTRL_COUNTER_RESET |
 			    MMC_CNTRL_PRESET | MMC_CNTRL_FULL_HALF_PRESET;
 
-	if (priv->synopsys_id >= DWMAC_CORE_4_00)
+	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+		priv->ptpaddr = priv->ioaddr + PTP_GMAC4_OFFSET;
 		priv->mmcaddr = priv->ioaddr + MMC_GMAC4_OFFSET;
-	else
+	} else {
+		priv->ptpaddr = priv->ioaddr + PTP_GMAC3_X_OFFSET;
 		priv->mmcaddr = priv->ioaddr + MMC_GMAC3_X_OFFSET;
+	}
 
 	dwmac_mmc_intr_all_mask(priv->mmcaddr);
 
@@ -2504,6 +2504,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 	while (count < limit) {
 		int status;
 		struct dma_desc *p;
+		struct dma_desc *np;
 
 		if (priv->extend_desc)
 			p = (struct dma_desc *)(priv->dma_erx + entry);
@@ -2523,9 +2524,11 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 		next_entry = priv->cur_rx;
 
 		if (priv->extend_desc)
-			prefetch(priv->dma_erx + next_entry);
+			np = (struct dma_desc *)(priv->dma_erx + next_entry);
 		else
-			prefetch(priv->dma_rx + next_entry);
+			np = priv->dma_rx + next_entry;
+
+		prefetch(np);
 
 		if ((priv->extend_desc) && (priv->hw->desc->rx_extended_status))
 			priv->hw->desc->rx_extended_status(&priv->dev->stats,
@@ -2635,14 +2638,14 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 						 DMA_FROM_DEVICE);
 			}
 
-			stmmac_get_rx_hwtstamp(priv, entry, skb);
-
 			if (netif_msg_pktdata(priv)) {
 				netdev_dbg(priv->dev, "frame received (%dbytes)",
 					   frame_len);
 				print_pkt(skb->data, frame_len);
 			}
 
+			stmmac_get_rx_hwtstamp(priv, p, np, skb);
+
 			stmmac_rx_vlan(priv->dev, skb);
 
 			skb->protocol = eth_type_trans(skb, priv->dev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index 1477471..3eb281d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -54,7 +54,7 @@ static int stmmac_adjust_freq(struct ptp_clock_info *ptp, s32 ppb)
 
 	spin_lock_irqsave(&priv->ptp_lock, flags);
 
-	priv->hw->ptp->config_addend(priv->ioaddr, addend);
+	priv->hw->ptp->config_addend(priv->ptpaddr, addend);
 
 	spin_unlock_irqrestore(&priv->ptp_lock, flags);
 
@@ -89,7 +89,8 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta)
 
 	spin_lock_irqsave(&priv->ptp_lock, flags);
 
-	priv->hw->ptp->adjust_systime(priv->ioaddr, sec, nsec, neg_adj);
+	priv->hw->ptp->adjust_systime(priv->ptpaddr, sec, nsec, neg_adj,
+				      priv->plat->has_gmac4);
 
 	spin_unlock_irqrestore(&priv->ptp_lock, flags);
 
@@ -114,7 +115,7 @@ static int stmmac_get_time(struct ptp_clock_info *ptp, struct timespec64 *ts)
 
 	spin_lock_irqsave(&priv->ptp_lock, flags);
 
-	ns = priv->hw->ptp->get_systime(priv->ioaddr);
+	ns = priv->hw->ptp->get_systime(priv->ptpaddr);
 
 	spin_unlock_irqrestore(&priv->ptp_lock, flags);
 
@@ -141,7 +142,7 @@ static int stmmac_set_time(struct ptp_clock_info *ptp,
 
 	spin_lock_irqsave(&priv->ptp_lock, flags);
 
-	priv->hw->ptp->init_systime(priv->ioaddr, ts->tv_sec, ts->tv_nsec);
+	priv->hw->ptp->init_systime(priv->ptpaddr, ts->tv_sec, ts->tv_nsec);
 
 	spin_unlock_irqrestore(&priv->ptp_lock, flags);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
index 4535df3..c06938c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
@@ -22,51 +22,53 @@
   Author: Rayagond Kokatanur <rayagond@vayavyalabs.com>
 ******************************************************************************/
 
-#ifndef __STMMAC_PTP_H__
-#define __STMMAC_PTP_H__
+#ifndef	__STMMAC_PTP_H__
+#define	__STMMAC_PTP_H__
+
+#define	PTP_GMAC4_OFFSET	0xb00
+#define	PTP_GMAC3_X_OFFSET	0x700
 
 /* IEEE 1588 PTP register offsets */
-#define PTP_TCR		0x0700	/* Timestamp Control Reg */
-#define PTP_SSIR	0x0704	/* Sub-Second Increment Reg */
-#define PTP_STSR	0x0708	/* System Time – Seconds Regr */
-#define PTP_STNSR	0x070C	/* System Time – Nanoseconds Reg */
-#define PTP_STSUR	0x0710	/* System Time – Seconds Update Reg */
-#define PTP_STNSUR	0x0714	/* System Time – Nanoseconds Update Reg */
-#define PTP_TAR		0x0718	/* Timestamp Addend Reg */
-#define PTP_TTSR	0x071C	/* Target Time Seconds Reg */
-#define PTP_TTNSR	0x0720	/* Target Time Nanoseconds Reg */
-#define	PTP_STHWSR	0x0724	/* System Time - Higher Word Seconds Reg */
-#define PTP_TSR		0x0728	/* Timestamp Status */
+#define	PTP_TCR		0x00	/* Timestamp Control Reg */
+#define	PTP_SSIR	0x04	/* Sub-Second Increment Reg */
+#define	PTP_STSR	0x08	/* System Time – Seconds Regr */
+#define	PTP_STNSR	0x0c	/* System Time – Nanoseconds Reg */
+#define	PTP_STSUR	0x10	/* System Time – Seconds Update Reg */
+#define	PTP_STNSUR	0x14	/* System Time – Nanoseconds Update Reg */
+#define	PTP_TAR		0x18	/* Timestamp Addend Reg */
 
-#define PTP_STNSUR_ADDSUB_SHIFT 31
+#define	PTP_STNSUR_ADDSUB_SHIFT	31
+#define	PTP_DIGITAL_ROLLOVER_MODE	0x3B9ACA00	/* 10e9-1 ns */
+#define	PTP_BINARY_ROLLOVER_MODE	0x80000000	/* ~0.466 ns */
 
-/* PTP TCR defines */
-#define PTP_TCR_TSENA		0x00000001 /* Timestamp Enable */
-#define PTP_TCR_TSCFUPDT	0x00000002 /* Timestamp Fine/Coarse Update */
-#define PTP_TCR_TSINIT		0x00000004 /* Timestamp Initialize */
-#define PTP_TCR_TSUPDT		0x00000008 /* Timestamp Update */
-/* Timestamp Interrupt Trigger Enable */
-#define PTP_TCR_TSTRIG		0x00000010
-#define PTP_TCR_TSADDREG	0x00000020 /* Addend Reg Update */
-#define PTP_TCR_TSENALL		0x00000100 /* Enable Timestamp for All Frames */
-/* Timestamp Digital or Binary Rollover Control */
-#define PTP_TCR_TSCTRLSSR	0x00000200
-
+/* PTP Timestamp control register defines */
+#define	PTP_TCR_TSENA		BIT(0)	/* Timestamp Enable */
+#define	PTP_TCR_TSCFUPDT	BIT(1)	/* Timestamp Fine/Coarse Update */
+#define	PTP_TCR_TSINIT		BIT(2)	/* Timestamp Initialize */
+#define	PTP_TCR_TSUPDT		BIT(3)	/* Timestamp Update */
+#define	PTP_TCR_TSTRIG		BIT(4)	/* Timestamp Interrupt Trigger Enable */
+#define	PTP_TCR_TSADDREG	BIT(5)	/* Addend Reg Update */
+#define	PTP_TCR_TSENALL		BIT(8)	/* Enable Timestamp for All Frames */
+#define	PTP_TCR_TSCTRLSSR	BIT(9)	/* Digital or Binary Rollover Control */
 /* Enable PTP packet Processing for Version 2 Format */
-#define PTP_TCR_TSVER2ENA	0x00000400
+#define	PTP_TCR_TSVER2ENA	BIT(10)
 /* Enable Processing of PTP over Ethernet Frames */
-#define PTP_TCR_TSIPENA		0x00000800
+#define	PTP_TCR_TSIPENA		BIT(11)
 /* Enable Processing of PTP Frames Sent over IPv6-UDP */
-#define PTP_TCR_TSIPV6ENA	0x00001000
+#define	PTP_TCR_TSIPV6ENA	BIT(12)
 /* Enable Processing of PTP Frames Sent over IPv4-UDP */
-#define PTP_TCR_TSIPV4ENA	0x00002000
+#define	PTP_TCR_TSIPV4ENA	BIT(13)
 /* Enable Timestamp Snapshot for Event Messages */
-#define PTP_TCR_TSEVNTENA	0x00004000
+#define	PTP_TCR_TSEVNTENA	BIT(14)
 /* Enable Snapshot for Messages Relevant to Master */
-#define PTP_TCR_TSMSTRENA	0x00008000
+#define	PTP_TCR_TSMSTRENA	BIT(15)
 /* Select PTP packets for Taking Snapshots */
-#define PTP_TCR_SNAPTYPSEL_1	0x00010000
+#define	PTP_TCR_SNAPTYPSEL_1	GENMASK(17, 16)
 /* Enable MAC address for PTP Frame Filtering */
-#define PTP_TCR_TSENMACADDR	0x00040000
+#define	PTP_TCR_TSENMACADDR	BIT(18)
 
-#endif /* __STMMAC_PTP_H__ */
+/* SSIR defines */
+#define	PTP_SSIR_SSINC_MASK		0xff
+#define	GMAC4_PTP_SSIR_SSINC_SHIFT	16
+
+#endif	/* __STMMAC_PTP_H__ */
diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c
index ea89ef3..c4caf48 100644
--- a/drivers/net/ethernet/sun/sunbmac.c
+++ b/drivers/net/ethernet/sun/sunbmac.c
@@ -623,6 +623,7 @@ static int bigmac_init_hw(struct bigmac *bp, int from_irq)
 	void __iomem *gregs        = bp->gregs;
 	void __iomem *cregs        = bp->creg;
 	void __iomem *bregs        = bp->bregs;
+	__u32 bblk_dvma = (__u32)bp->bblock_dvma;
 	unsigned char *e = &bp->dev->dev_addr[0];
 
 	/* Latch current counters into statistics. */
@@ -671,9 +672,9 @@ static int bigmac_init_hw(struct bigmac *bp, int from_irq)
 		    bregs + BMAC_XIFCFG);
 
 	/* Tell the QEC where the ring descriptors are. */
-	sbus_writel(bp->bblock_dvma + bib_offset(be_rxd, 0),
+	sbus_writel(bblk_dvma + bib_offset(be_rxd, 0),
 		    cregs + CREG_RXDS);
-	sbus_writel(bp->bblock_dvma + bib_offset(be_txd, 0),
+	sbus_writel(bblk_dvma + bib_offset(be_txd, 0),
 		    cregs + CREG_TXDS);
 
 	/* Setup the FIFO pointers into QEC local memory. */
diff --git a/drivers/net/ethernet/sun/sunbmac.h b/drivers/net/ethernet/sun/sunbmac.h
index 06dd217..532fc56 100644
--- a/drivers/net/ethernet/sun/sunbmac.h
+++ b/drivers/net/ethernet/sun/sunbmac.h
@@ -291,7 +291,7 @@ struct bigmac {
 	void __iomem	*bregs;	/* BigMAC Registers                   */
 	void __iomem	*tregs;	/* BigMAC Transceiver                 */
 	struct bmac_init_block	*bmac_block;	/* RX and TX descriptors */
-	__u32			 bblock_dvma;	/* RX and TX descriptors */
+	dma_addr_t		bblock_dvma;	/* RX and TX descriptors */
 
 	spinlock_t		lock;
 
diff --git a/drivers/net/ethernet/sun/sunqe.c b/drivers/net/ethernet/sun/sunqe.c
index c5ef711..a6bcdcd 100644
--- a/drivers/net/ethernet/sun/sunqe.c
+++ b/drivers/net/ethernet/sun/sunqe.c
@@ -124,7 +124,7 @@ static void qe_init_rings(struct sunqe *qep)
 {
 	struct qe_init_block *qb = qep->qe_block;
 	struct sunqe_buffers *qbufs = qep->buffers;
-	__u32 qbufs_dvma = qep->buffers_dvma;
+	__u32 qbufs_dvma = (__u32)qep->buffers_dvma;
 	int i;
 
 	qep->rx_new = qep->rx_old = qep->tx_new = qep->tx_old = 0;
@@ -144,6 +144,7 @@ static int qe_init(struct sunqe *qep, int from_irq)
 	void __iomem *mregs = qep->mregs;
 	void __iomem *gregs = qecp->gregs;
 	unsigned char *e = &qep->dev->dev_addr[0];
+	__u32 qblk_dvma = (__u32)qep->qblock_dvma;
 	u32 tmp;
 	int i;
 
@@ -152,8 +153,8 @@ static int qe_init(struct sunqe *qep, int from_irq)
 		return -EAGAIN;
 
 	/* Setup initial rx/tx init block pointers. */
-	sbus_writel(qep->qblock_dvma + qib_offset(qe_rxd, 0), cregs + CREG_RXDS);
-	sbus_writel(qep->qblock_dvma + qib_offset(qe_txd, 0), cregs + CREG_TXDS);
+	sbus_writel(qblk_dvma + qib_offset(qe_rxd, 0), cregs + CREG_RXDS);
+	sbus_writel(qblk_dvma + qib_offset(qe_txd, 0), cregs + CREG_TXDS);
 
 	/* Enable/mask the various irq's. */
 	sbus_writel(0, cregs + CREG_RIMASK);
@@ -413,7 +414,7 @@ static void qe_rx(struct sunqe *qep)
 	struct net_device *dev = qep->dev;
 	struct qe_rxd *this;
 	struct sunqe_buffers *qbufs = qep->buffers;
-	__u32 qbufs_dvma = qep->buffers_dvma;
+	__u32 qbufs_dvma = (__u32)qep->buffers_dvma;
 	int elem = qep->rx_new;
 	u32 flags;
 
@@ -572,7 +573,7 @@ static int qe_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct sunqe *qep = netdev_priv(dev);
 	struct sunqe_buffers *qbufs = qep->buffers;
-	__u32 txbuf_dvma, qbufs_dvma = qep->buffers_dvma;
+	__u32 txbuf_dvma, qbufs_dvma = (__u32)qep->buffers_dvma;
 	unsigned char *txbuf;
 	int len, entry;
 
diff --git a/drivers/net/ethernet/sun/sunqe.h b/drivers/net/ethernet/sun/sunqe.h
index 581781b..ae190b7 100644
--- a/drivers/net/ethernet/sun/sunqe.h
+++ b/drivers/net/ethernet/sun/sunqe.h
@@ -334,12 +334,12 @@ struct sunqe {
 	void __iomem			*qcregs;		/* QEC per-channel Registers   */
 	void __iomem			*mregs;		/* Per-channel MACE Registers  */
 	struct qe_init_block      	*qe_block;	/* RX and TX descriptors       */
-	__u32                      	qblock_dvma;	/* RX and TX descriptors       */
+	dma_addr_t			qblock_dvma;	/* RX and TX descriptors       */
 	spinlock_t			lock;		/* Protects txfull state       */
 	int                        	rx_new, rx_old;	/* RX ring extents	       */
 	int			   	tx_new, tx_old;	/* TX ring extents	       */
 	struct sunqe_buffers		*buffers;	/* CPU visible address.        */
-	__u32				buffers_dvma;	/* DVMA visible address.       */
+	dma_addr_t			buffers_dvma;	/* DVMA visible address.       */
 	struct sunqec			*parent;
 	u8				mconfig;	/* Base MACE mconfig value     */
 	struct platform_device		*op;		/* QE's OF device struct       */
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 39d06e8..da40ea5 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -2373,8 +2373,11 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 			 * to the PHY is the Ethernet MAC DT node.
 			 */
 			ret = of_phy_register_fixed_link(slave_node);
-			if (ret)
+			if (ret) {
+				if (ret != -EPROBE_DEFER)
+					dev_err(&pdev->dev, "failed to register fixed-link phy: %d\n", ret);
 				return ret;
+			}
 			slave_data->phy_node = of_node_get(slave_node);
 		} else if (parp) {
 			u32 phyid;
@@ -2395,6 +2398,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 			}
 			snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
 				 PHY_ID_FMT, mdio->name, phyid);
+			put_device(&mdio->dev);
 		} else {
 			dev_err(&pdev->dev,
 				"No slave[%d] phy_id, phy-handle, or fixed-link property\n",
@@ -2438,6 +2442,46 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 	return 0;
 }
 
+static void cpsw_remove_dt(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	struct cpsw_platform_data *data = &cpsw->data;
+	struct device_node *node = pdev->dev.of_node;
+	struct device_node *slave_node;
+	int i = 0;
+
+	for_each_available_child_of_node(node, slave_node) {
+		struct cpsw_slave_data *slave_data = &data->slave_data[i];
+
+		if (strcmp(slave_node->name, "slave"))
+			continue;
+
+		if (of_phy_is_fixed_link(slave_node)) {
+			struct phy_device *phydev;
+
+			phydev = of_phy_find_device(slave_node);
+			if (phydev) {
+				fixed_phy_unregister(phydev);
+				/* Put references taken by
+				 * of_phy_find_device() and
+				 * of_phy_register_fixed_link().
+				 */
+				phy_device_free(phydev);
+				phy_device_free(phydev);
+			}
+		}
+
+		of_node_put(slave_data->phy_node);
+
+		i++;
+		if (i == data->slaves)
+			break;
+	}
+
+	of_platform_depopulate(&pdev->dev);
+}
+
 static int cpsw_probe_dual_emac(struct cpsw_priv *priv)
 {
 	struct cpsw_common		*cpsw = priv->cpsw;
@@ -2545,6 +2589,9 @@ static int cpsw_probe(struct platform_device *pdev)
 	int irq;
 
 	cpsw = devm_kzalloc(&pdev->dev, sizeof(struct cpsw_common), GFP_KERNEL);
+	if (!cpsw)
+		return -ENOMEM;
+
 	cpsw->dev = &pdev->dev;
 
 	ndev = alloc_etherdev_mq(sizeof(struct cpsw_priv), CPSW_MAX_QUEUES);
@@ -2582,11 +2629,19 @@ static int cpsw_probe(struct platform_device *pdev)
 	/* Select default pin state */
 	pinctrl_pm_select_default_state(&pdev->dev);
 
-	if (cpsw_probe_dt(&cpsw->data, pdev)) {
-		dev_err(&pdev->dev, "cpsw: platform data missing\n");
-		ret = -ENODEV;
+	/* Need to enable clocks with runtime PM api to access module
+	 * registers
+	 */
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(&pdev->dev);
 		goto clean_runtime_disable_ret;
 	}
+
+	ret = cpsw_probe_dt(&cpsw->data, pdev);
+	if (ret)
+		goto clean_dt_ret;
+
 	data = &cpsw->data;
 	cpsw->rx_ch_num = 1;
 	cpsw->tx_ch_num = 1;
@@ -2606,7 +2661,7 @@ static int cpsw_probe(struct platform_device *pdev)
 				    GFP_KERNEL);
 	if (!cpsw->slaves) {
 		ret = -ENOMEM;
-		goto clean_runtime_disable_ret;
+		goto clean_dt_ret;
 	}
 	for (i = 0; i < data->slaves; i++)
 		cpsw->slaves[i].slave_num = i;
@@ -2618,7 +2673,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	if (IS_ERR(clk)) {
 		dev_err(priv->dev, "fck is not found\n");
 		ret = -ENODEV;
-		goto clean_runtime_disable_ret;
+		goto clean_dt_ret;
 	}
 	cpsw->bus_freq_mhz = clk_get_rate(clk) / 1000000;
 
@@ -2626,26 +2681,17 @@ static int cpsw_probe(struct platform_device *pdev)
 	ss_regs = devm_ioremap_resource(&pdev->dev, ss_res);
 	if (IS_ERR(ss_regs)) {
 		ret = PTR_ERR(ss_regs);
-		goto clean_runtime_disable_ret;
+		goto clean_dt_ret;
 	}
 	cpsw->regs = ss_regs;
 
-	/* Need to enable clocks with runtime PM api to access module
-	 * registers
-	 */
-	ret = pm_runtime_get_sync(&pdev->dev);
-	if (ret < 0) {
-		pm_runtime_put_noidle(&pdev->dev);
-		goto clean_runtime_disable_ret;
-	}
 	cpsw->version = readl(&cpsw->regs->id_ver);
-	pm_runtime_put_sync(&pdev->dev);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 	cpsw->wr_regs = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(cpsw->wr_regs)) {
 		ret = PTR_ERR(cpsw->wr_regs);
-		goto clean_runtime_disable_ret;
+		goto clean_dt_ret;
 	}
 
 	memset(&dma_params, 0, sizeof(dma_params));
@@ -2682,7 +2728,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	default:
 		dev_err(priv->dev, "unknown version 0x%08x\n", cpsw->version);
 		ret = -ENODEV;
-		goto clean_runtime_disable_ret;
+		goto clean_dt_ret;
 	}
 	for (i = 0; i < cpsw->data.slaves; i++) {
 		struct cpsw_slave *slave = &cpsw->slaves[i];
@@ -2711,7 +2757,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	if (!cpsw->dma) {
 		dev_err(priv->dev, "error initializing dma\n");
 		ret = -ENOMEM;
-		goto clean_runtime_disable_ret;
+		goto clean_dt_ret;
 	}
 
 	cpsw->txch[0] = cpdma_chan_create(cpsw->dma, 0, cpsw_tx_handler, 0);
@@ -2809,16 +2855,23 @@ static int cpsw_probe(struct platform_device *pdev)
 		ret = cpsw_probe_dual_emac(priv);
 		if (ret) {
 			cpsw_err(priv, probe, "error probe slave 2 emac interface\n");
-			goto clean_ale_ret;
+			goto clean_unregister_netdev_ret;
 		}
 	}
 
+	pm_runtime_put(&pdev->dev);
+
 	return 0;
 
+clean_unregister_netdev_ret:
+	unregister_netdev(ndev);
 clean_ale_ret:
 	cpsw_ale_destroy(cpsw->ale);
 clean_dma_ret:
 	cpdma_ctlr_destroy(cpsw->dma);
+clean_dt_ret:
+	cpsw_remove_dt(pdev);
+	pm_runtime_put_sync(&pdev->dev);
 clean_runtime_disable_ret:
 	pm_runtime_disable(&pdev->dev);
 clean_ndev_ret:
@@ -2844,7 +2897,7 @@ static int cpsw_remove(struct platform_device *pdev)
 
 	cpsw_ale_destroy(cpsw->ale);
 	cpdma_ctlr_destroy(cpsw->dma);
-	of_platform_depopulate(&pdev->dev);
+	cpsw_remove_dt(pdev);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	if (cpsw->data.dual_emac)