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

Pull networking fixes from David Miller:
 "This pull request is dedicated to the upcoming snowpocalypse parts 2
  and 3 in the Pacific Northwest:

   1) Drop profiles are broken because some drivers use dev_kfree_skb*
      instead of dev_consume_skb*, from Yang Wei.

   2) Fix IWLWIFI kconfig deps, from Luca Coelho.

   3) Fix percpu maps updating in bpftool, from Paolo Abeni.

   4) Missing station release in batman-adv, from Felix Fietkau.

   5) Fix some networking compat ioctl bugs, from Johannes Berg.

   6) ucc_geth must reset the BQL queue state when stopping the device,
      from Mathias Thore.

   7) Several XDP bug fixes in virtio_net from Toshiaki Makita.

   8) TSO packets must be sent always on queue 0 in stmmac, from Jose
      Abreu.

   9) Fix socket refcounting bug in RDS, from Eric Dumazet.

  10) Handle sparse cpu allocations in bpf selftests, from Martynas
      Pumputis.

  11) Make sure mgmt frames have enough tailroom in mac80211, from Felix
      Feitkau.

  12) Use safe list walking in sctp_sendmsg() asoc list traversal, from
      Greg Kroah-Hartman.

  13) Make DCCP's ccid_hc_[rt]x_parse_options always check for NULL
      ccid, from Eric Dumazet.

  14) Need to reload WoL password into bcmsysport device after deep
      sleeps, from Florian Fainelli.

  15) Remove filter from mask before freeing in cls_flower, from Petr
      Machata.

  16) Missing release and use after free in error paths of s390 qeth
      code, from Julian Wiedmann.

  17) Fix lockdep false positive in dsa code, from Marc Zyngier.

  18) Fix counting of ATU violations in mv88e6xxx, from Andrew Lunn.

  19) Fix EQ firmware assert in qed driver, from Manish Chopra.

  20) Don't default Caivum PTP to Y in kconfig, from Bjorn Helgaas"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (116 commits)
  net: dsa: b53: Fix for failure when irq is not defined in dt
  sit: check if IPv6 enabled before calling ip6_err_gen_icmpv6_unreach()
  geneve: should not call rt6_lookup() when ipv6 was disabled
  net: Don't default Cavium PTP driver to 'y'
  net: broadcom: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: via-velocity: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: tehuti: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: sun: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: fsl_ucc_hdlc: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: fec_mpc52xx: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: smsc: epic100: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: dscc4: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: tulip: de2104x: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: defxx: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net/mlx5e: Don't overwrite pedit action when multiple pedit used
  net/mlx5e: Update hw flows when encap source mac changed
  qed*: Advance drivers version to 8.37.0.20
  qed: Change verbosity for coalescing message.
  qede: Fix system crash on configuring channels.
  qed: Consider TX tcs while deriving the max num_queues for PF.
  ...

34 files changed, 155 insertions, 80 deletions

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index f9521d0274b7..28c9b0bdf2f6 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -520,7 +520,6 @@ static void bcm_sysport_get_wol(struct net_device *dev,
 				struct ethtool_wolinfo *wol)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
-	u32 reg;
 
 	wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER;
 	wol->wolopts = priv->wolopts;
@@ -528,11 +527,7 @@ static void bcm_sysport_get_wol(struct net_device *dev,
 	if (!(priv->wolopts & WAKE_MAGICSECURE))
 		return;
 
-	/* Return the programmed SecureOn password */
-	reg = umac_readl(priv, UMAC_PSW_MS);
-	put_unaligned_be16(reg, &wol->sopass[0]);
-	reg = umac_readl(priv, UMAC_PSW_LS);
-	put_unaligned_be32(reg, &wol->sopass[2]);
+	memcpy(wol->sopass, priv->sopass, sizeof(priv->sopass));
 }
 
 static int bcm_sysport_set_wol(struct net_device *dev,
@@ -548,13 +543,8 @@ static int bcm_sysport_set_wol(struct net_device *dev,
 	if (wol->wolopts & ~supported)
 		return -EINVAL;
 
-	/* Program the SecureOn password */
-	if (wol->wolopts & WAKE_MAGICSECURE) {
-		umac_writel(priv, get_unaligned_be16(&wol->sopass[0]),
-			    UMAC_PSW_MS);
-		umac_writel(priv, get_unaligned_be32(&wol->sopass[2]),
-			    UMAC_PSW_LS);
-	}
+	if (wol->wolopts & WAKE_MAGICSECURE)
+		memcpy(priv->sopass, wol->sopass, sizeof(priv->sopass));
 
 	/* Flag the device and relevant IRQ as wakeup capable */
 	if (wol->wolopts) {
@@ -2649,13 +2639,18 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv)
 	unsigned int index, i = 0;
 	u32 reg;
 
-	/* Password has already been programmed */
 	reg = umac_readl(priv, UMAC_MPD_CTRL);
 	if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE))
 		reg |= MPD_EN;
 	reg &= ~PSW_EN;
-	if (priv->wolopts & WAKE_MAGICSECURE)
+	if (priv->wolopts & WAKE_MAGICSECURE) {
+		/* Program the SecureOn password */
+		umac_writel(priv, get_unaligned_be16(&priv->sopass[0]),
+			    UMAC_PSW_MS);
+		umac_writel(priv, get_unaligned_be32(&priv->sopass[2]),
+			    UMAC_PSW_LS);
 		reg |= PSW_EN;
+	}
 	umac_writel(priv, reg, UMAC_MPD_CTRL);
 
 	if (priv->wolopts & WAKE_FILTER) {
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index 0887e6356649..0b192fea9c5d 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -12,6 +12,7 @@
 #define __BCM_SYSPORT_H
 
 #include <linux/bitmap.h>
+#include <linux/ethtool.h>
 #include <linux/if_vlan.h>
 #include <linux/net_dim.h>
 
@@ -778,6 +779,7 @@ struct bcm_sysport_priv {
 	unsigned int		crc_fwd:1;
 	u16			rev;
 	u32			wolopts;
+	u8			sopass[SOPASS_MAX];
 	unsigned int		wol_irq_disabled:1;
 
 	/* MIB related fields */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6a512871176b..8bc7e495b027 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4973,12 +4973,18 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
 		struct bnxt_ring_struct *ring = &cpr->cp_ring_struct;
 		u32 map_idx = ring->map_idx;
+		unsigned int vector;
 
+		vector = bp->irq_tbl[map_idx].vector;
+		disable_irq_nosync(vector);
 		rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx);
-		if (rc)
+		if (rc) {
+			enable_irq(vector);
 			goto err_out;
+		}
 		bnxt_set_db(bp, &cpr->cp_db, type, map_idx, ring->fw_ring_id);
 		bnxt_db_nq(bp, &cpr->cp_db, cpr->cp_raw_cons);
+		enable_irq(vector);
 		bp->grp_info[i].cp_fw_ring_id = ring->fw_ring_id;
 
 		if (!i) {
diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c
index 5db9f4158e62..134ae2862efa 100644
--- a/drivers/net/ethernet/broadcom/sb1250-mac.c
+++ b/drivers/net/ethernet/broadcom/sb1250-mac.c
@@ -1288,7 +1288,7 @@ static void sbdma_tx_process(struct sbmac_softc *sc, struct sbmacdma *d,
 		 * for transmits, we just free buffers.
 		 */
 
-		dev_kfree_skb_irq(sb);
+		dev_consume_skb_irq(sb);
 
 		/*
 		 * .. and advance to the next buffer.
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index 5f03199a3acf..05f4a3b21e29 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -54,7 +54,6 @@ config CAVIUM_PTP
 	tristate "Cavium PTP coprocessor as PTP clock"
 	depends on 64BIT && PCI
 	imply PTP_1588_CLOCK
-	default y
 	---help---
 	  This driver adds support for the Precision Time Protocol Clocks and
 	  Timestamping coprocessor (PTP) found on Cavium processors.
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 60641e202534..9a7f70db20c7 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -1434,7 +1434,8 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
 		 * csum is correct or is zero.
 		 */
 		if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc &&
-		    tcp_udp_csum_ok && ipv4_csum_ok && outer_csum_ok) {
+		    tcp_udp_csum_ok && outer_csum_ok &&
+		    (ipv4_csum_ok || ipv6)) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 			skb->csum_level = encap;
 		}
diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c
index 13430f75496c..f1a2da15dd0a 100644
--- a/drivers/net/ethernet/dec/tulip/de2104x.c
+++ b/drivers/net/ethernet/dec/tulip/de2104x.c
@@ -585,7 +585,7 @@ static void de_tx (struct de_private *de)
 				netif_dbg(de, tx_done, de->dev,
 					  "tx done, slot %d\n", tx_tail);
 			}
-			dev_kfree_skb_irq(skb);
+			dev_consume_skb_irq(skb);
 		}
 
 next:
diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c
index b90bab72efdb..c1968b3ecec8 100644
--- a/drivers/net/ethernet/freescale/fec_mpc52xx.c
+++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c
@@ -369,7 +369,7 @@ static irqreturn_t mpc52xx_fec_tx_interrupt(int irq, void *dev_id)
 		dma_unmap_single(dev->dev.parent, bd->skb_pa, skb->len,
 				 DMA_TO_DEVICE);
 
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 	}
 	spin_unlock(&priv->lock);
 
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index c3d539e209ed..eb3e65e8868f 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -1879,6 +1879,8 @@ static void ucc_geth_free_tx(struct ucc_geth_private *ugeth)
 	u16 i, j;
 	u8 __iomem *bd;
 
+	netdev_reset_queue(ugeth->ndev);
+
 	ug_info = ugeth->ug_info;
 	uf_info = &ug_info->uf_info;
 
diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index 04fd1f135011..654ac534b10e 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -152,8 +152,10 @@ static void skge_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 	memset(p, 0, regs->len);
 	memcpy_fromio(p, io, B3_RAM_ADDR);
 
-	memcpy_fromio(p + B3_RI_WTO_R1, io + B3_RI_WTO_R1,
-		      regs->len - B3_RI_WTO_R1);
+	if (regs->len > B3_RI_WTO_R1) {
+		memcpy_fromio(p + B3_RI_WTO_R1, io + B3_RI_WTO_R1,
+			      regs->len - B3_RI_WTO_R1);
+	}
 }
 
 /* Wake on Lan only supported on Yukon chips with rev 1 or above */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 046948ead152..f3c7ab6faea5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -256,6 +256,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 	e->m_neigh.family = n->ops->family;
 	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
 	e->out_dev = out_dev;
+	e->route_dev = route_dev;
 
 	/* It's important to add the neigh to the hash table before checking
 	 * the neigh validity state. So if we'll get a notification, in case the
@@ -369,6 +370,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 	e->m_neigh.family = n->ops->family;
 	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
 	e->out_dev = out_dev;
+	e->route_dev = route_dev;
 
 	/* It's importent to add the neigh to the hash table before checking
 	 * the neigh validity state. So if we'll get a notification, in case the
@@ -612,16 +614,18 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev,
 		       struct mlx5_flow_spec *spec,
 		       struct tc_cls_flower_offload *f,
 		       void *headers_c,
-		       void *headers_v)
+		       void *headers_v, u8 *match_level)
 {
 	int tunnel_type;
 	int err = 0;
 
 	tunnel_type = mlx5e_tc_tun_get_type(filter_dev);
 	if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
+		*match_level = MLX5_MATCH_L4;
 		err = mlx5e_tc_tun_parse_vxlan(priv, spec, f,
 					       headers_c, headers_v);
 	} else if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) {
+		*match_level = MLX5_MATCH_L3;
 		err = mlx5e_tc_tun_parse_gretap(priv, spec, f,
 						headers_c, headers_v);
 	} else {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
index 706ce7bf15e7..b63f15de899d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
@@ -39,6 +39,6 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev,
 		       struct mlx5_flow_spec *spec,
 		       struct tc_cls_flower_offload *f,
 		       void *headers_c,
-		       void *headers_v);
+		       void *headers_v, u8 *match_level);
 
 #endif //__MLX5_EN_TC_TUNNEL_H__
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index f2573c2d2b5c..ef9e472daffb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -596,6 +596,10 @@ static void mlx5e_rep_update_flows(struct mlx5e_priv *priv,
 	if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) {
 		ether_addr_copy(e->h_dest, ha);
 		ether_addr_copy(eth->h_dest, ha);
+		/* Update the encap source mac, in case that we delete
+		 * the flows when encap source mac changed.
+		 */
+		ether_addr_copy(eth->h_source, e->route_dev->dev_addr);
 
 		mlx5e_tc_encap_flows_add(priv, e);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index edd722824697..36eafc877e6b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -148,6 +148,7 @@ struct mlx5e_encap_entry {
 	unsigned char h_dest[ETH_ALEN];	/* destination eth addr	*/
 
 	struct net_device *out_dev;
+	struct net_device *route_dev;
 	int tunnel_type;
 	int tunnel_hlen;
 	int reformat_type;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index cae6c6d48984..b5c1b039375a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -128,6 +128,7 @@ struct mlx5e_tc_flow_parse_attr {
 	struct net_device *filter_dev;
 	struct mlx5_flow_spec spec;
 	int num_mod_hdr_actions;
+	int max_mod_hdr_actions;
 	void *mod_hdr_actions;
 	int mirred_ifindex[MLX5_MAX_FLOW_FWD_VPORTS];
 };
@@ -1302,7 +1303,7 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
 static int parse_tunnel_attr(struct mlx5e_priv *priv,
 			     struct mlx5_flow_spec *spec,
 			     struct tc_cls_flower_offload *f,
-			     struct net_device *filter_dev)
+			     struct net_device *filter_dev, u8 *match_level)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
 	void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
@@ -1317,7 +1318,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 	int err = 0;
 
 	err = mlx5e_tc_tun_parse(filter_dev, priv, spec, f,
-				 headers_c, headers_v);
+				 headers_c, headers_v, match_level);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "failed to parse tunnel attributes");
@@ -1426,7 +1427,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			      struct mlx5_flow_spec *spec,
 			      struct tc_cls_flower_offload *f,
 			      struct net_device *filter_dev,
-			      u8 *match_level)
+			      u8 *match_level, u8 *tunnel_match_level)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
 	void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
@@ -1477,7 +1478,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		switch (key->addr_type) {
 		case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
 		case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
-			if (parse_tunnel_attr(priv, spec, f, filter_dev))
+			if (parse_tunnel_attr(priv, spec, f, filter_dev, tunnel_match_level))
 				return -EOPNOTSUPP;
 			break;
 		default:
@@ -1826,11 +1827,11 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
 	struct mlx5_core_dev *dev = priv->mdev;
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	u8 match_level, tunnel_match_level = MLX5_MATCH_NONE;
 	struct mlx5_eswitch_rep *rep;
-	u8 match_level;
 	int err;
 
-	err = __parse_cls_flower(priv, spec, f, filter_dev, &match_level);
+	err = __parse_cls_flower(priv, spec, f, filter_dev, &match_level, &tunnel_match_level);
 
 	if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) {
 		rep = rpriv->rep;
@@ -1846,10 +1847,12 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
 		}
 	}
 
-	if (flow->flags & MLX5E_TC_FLOW_ESWITCH)
+	if (flow->flags & MLX5E_TC_FLOW_ESWITCH) {
 		flow->esw_attr->match_level = match_level;
-	else
+		flow->esw_attr->tunnel_match_level = tunnel_match_level;
+	} else {
 		flow->nic_attr->match_level = match_level;
+	}
 
 	return err;
 }
@@ -1934,9 +1937,9 @@ static struct mlx5_fields fields[] = {
 	OFFLOAD(UDP_DPORT, 2, udp.dest,   0),
 };
 
-/* On input attr->num_mod_hdr_actions tells how many HW actions can be parsed at
- * max from the SW pedit action. On success, it says how many HW actions were
- * actually parsed.
+/* On input attr->max_mod_hdr_actions tells how many HW actions can be parsed at
+ * max from the SW pedit action. On success, attr->num_mod_hdr_actions
+ * says how many HW actions were actually parsed.
  */
 static int offload_pedit_fields(struct pedit_headers *masks,
 				struct pedit_headers *vals,
@@ -1960,9 +1963,11 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 	add_vals = &vals[TCA_PEDIT_KEY_EX_CMD_ADD];
 
 	action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
-	action = parse_attr->mod_hdr_actions;
-	max_actions = parse_attr->num_mod_hdr_actions;
-	nactions = 0;
+	action = parse_attr->mod_hdr_actions +
+		 parse_attr->num_mod_hdr_actions * action_size;
+
+	max_actions = parse_attr->max_mod_hdr_actions;
+	nactions = parse_attr->num_mod_hdr_actions;
 
 	for (i = 0; i < ARRAY_SIZE(fields); i++) {
 		f = &fields[i];
@@ -2073,7 +2078,7 @@ static int alloc_mod_hdr_actions(struct mlx5e_priv *priv,
 	if (!parse_attr->mod_hdr_actions)
 		return -ENOMEM;
 
-	parse_attr->num_mod_hdr_actions = max_actions;
+	parse_attr->max_mod_hdr_actions = max_actions;
 	return 0;
 }
 
@@ -2119,9 +2124,11 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv,
 			goto out_err;
 	}
 
-	err = alloc_mod_hdr_actions(priv, a, namespace, parse_attr);
-	if (err)
-		goto out_err;
+	if (!parse_attr->mod_hdr_actions) {
+		err = alloc_mod_hdr_actions(priv, a, namespace, parse_attr);
+		if (err)
+			goto out_err;
+	}
 
 	err = offload_pedit_fields(masks, vals, parse_attr, extack);
 	if (err < 0)
@@ -2179,6 +2186,7 @@ static bool csum_offload_supported(struct mlx5e_priv *priv,
 
 static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 					  struct tcf_exts *exts,
+					  u32 actions,
 					  struct netlink_ext_ack *extack)
 {
 	const struct tc_action *a;
@@ -2188,7 +2196,11 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 	u16 ethertype;
 	int nkeys, i;
 
-	headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers);
+	if (actions & MLX5_FLOW_CONTEXT_ACTION_DECAP)
+		headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, inner_headers);
+	else
+		headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers);
+
 	ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype);
 
 	/* for non-IP we only re-write MACs, so we're okay */
@@ -2245,7 +2257,7 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 
 	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		return modify_header_match_supported(&parse_attr->spec, exts,
-						     extack);
+						     actions, extack);
 
 	return true;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 598ad7e4d5c9..0e55cd1f2e98 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -387,8 +387,14 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
 	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
 	if (unlikely(contig_wqebbs_room < num_wqebbs)) {
+#ifdef CONFIG_MLX5_EN_IPSEC
+		struct mlx5_wqe_eth_seg cur_eth = wqe->eth;
+#endif
 		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
 		mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
+#ifdef CONFIG_MLX5_EN_IPSEC
+		wqe->eth = cur_eth;
+#endif
 	}
 
 	/* fill wqe */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 9c89eea9b2c3..748ff178a1d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -312,6 +312,7 @@ struct mlx5_esw_flow_attr {
 	} dests[MLX5_MAX_FLOW_FWD_VPORTS];
 	u32	mod_hdr_id;
 	u8	match_level;
+	u8	tunnel_match_level;
 	struct mlx5_fc *counter;
 	u32	chain;
 	u16	prio;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 53065b6ae593..d4e6fe5b9300 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -160,14 +160,15 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 		MLX5_SET_TO_ONES(fte_match_set_misc, misc,
 				 source_eswitch_owner_vhca_id);
 
-	if (attr->match_level == MLX5_MATCH_NONE)
-		spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
-	else
-		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS |
-					      MLX5_MATCH_MISC_PARAMETERS;
-
-	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP)
-		spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS;
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) {
+		if (attr->tunnel_match_level != MLX5_MATCH_NONE)
+			spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
+		if (attr->match_level != MLX5_MATCH_NONE)
+			spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS;
+	} else if (attr->match_level != MLX5_MATCH_NONE) {
+		spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
+	}
 
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		flow_act.modify_id = attr->mod_hdr_id;
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 24a90163775e..2d8a77cc156b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -53,7 +53,7 @@
 extern const struct qed_common_ops qed_common_ops_pass;
 
 #define QED_MAJOR_VERSION		8
-#define QED_MINOR_VERSION		33
+#define QED_MINOR_VERSION		37
 #define QED_REVISION_VERSION		0
 #define QED_ENGINEERING_VERSION		20
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index e68ca83ae915..58be1c4c6668 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -2216,7 +2216,7 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev,
 			u16 num_queues = 0;
 
 			/* Since the feature controls only queue-zones,
-			 * make sure we have the contexts [rx, tx, xdp] to
+			 * make sure we have the contexts [rx, xdp, tcs] to
 			 * match.
 			 */
 			for_each_hwfn(cdev, i) {
@@ -2226,7 +2226,8 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev,
 				u16 cids;
 
 				cids = hwfn->pf_params.eth_pf_params.num_cons;
-				num_queues += min_t(u16, l2_queues, cids / 3);
+				cids /= (2 + info->num_tc);
+				num_queues += min_t(u16, l2_queues, cids);
 			}
 
 			/* queues might theoretically be >256, but interrupts'
@@ -2870,7 +2871,8 @@ static int qed_get_coalesce(struct qed_dev *cdev, u16 *coal, void *handle)
 	p_hwfn = p_cid->p_owner;
 	rc = qed_get_queue_coalesce(p_hwfn, coal, handle);
 	if (rc)
-		DP_NOTICE(p_hwfn, "Unable to read queue coalescing\n");
+		DP_VERBOSE(cdev, QED_MSG_DEBUG,
+			   "Unable to read queue coalescing\n");
 
 	return rc;
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h
index 4179c9013fc6..96ab77ae6af5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h
@@ -382,6 +382,7 @@ void qed_consq_setup(struct qed_hwfn *p_hwfn);
  * @param p_hwfn
  */
 void qed_consq_free(struct qed_hwfn *p_hwfn);
+int qed_spq_pend_post(struct qed_hwfn *p_hwfn);
 
 /**
  * @file
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
index 888274fa208b..5a495fda9e9d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
@@ -604,6 +604,9 @@ int qed_sp_pf_update_stag(struct qed_hwfn *p_hwfn)
 
 	p_ent->ramrod.pf_update.update_mf_vlan_flag = true;
 	p_ent->ramrod.pf_update.mf_vlan = cpu_to_le16(p_hwfn->hw_info.ovlan);
+	if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits))
+		p_ent->ramrod.pf_update.mf_vlan |=
+			cpu_to_le16(((u16)p_hwfn->ufp_info.tc << 13));
 
 	return qed_spq_post(p_hwfn, p_ent, NULL);
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index eb88bbc6b193..ba64ff9bedbd 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -397,6 +397,11 @@ int qed_eq_completion(struct qed_hwfn *p_hwfn, void *cookie)
 
 	qed_eq_prod_update(p_hwfn, qed_chain_get_prod_idx(p_chain));
 
+	/* Attempt to post pending requests */
+	spin_lock_bh(&p_hwfn->p_spq->lock);
+	rc = qed_spq_pend_post(p_hwfn);
+	spin_unlock_bh(&p_hwfn->p_spq->lock);
+
 	return rc;
 }
 
@@ -767,7 +772,7 @@ static int qed_spq_post_list(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
-static int qed_spq_pend_post(struct qed_hwfn *p_hwfn)
+int qed_spq_pend_post(struct qed_hwfn *p_hwfn)
 {
 	struct qed_spq *p_spq = p_hwfn->p_spq;
 	struct qed_spq_entry *p_ent = NULL;
@@ -905,7 +910,6 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn,
 	struct qed_spq_entry	*p_ent = NULL;
 	struct qed_spq_entry	*tmp;
 	struct qed_spq_entry	*found = NULL;
-	int			rc;
 
 	if (!p_hwfn)
 		return -EINVAL;
@@ -963,12 +967,7 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn,
 		 */
 		qed_spq_return_entry(p_hwfn, found);
 
-	/* Attempt to post pending requests */
-	spin_lock_bh(&p_spq->lock);
-	rc = qed_spq_pend_post(p_hwfn);
-	spin_unlock_bh(&p_spq->lock);
-
-	return rc;
+	return 0;
 }
 
 int qed_consq_alloc(struct qed_hwfn *p_hwfn)
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 613249d1e967..730997b13747 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -56,7 +56,7 @@
 #include <net/tc_act/tc_gact.h>
 
 #define QEDE_MAJOR_VERSION		8
-#define QEDE_MINOR_VERSION		33
+#define QEDE_MINOR_VERSION		37
 #define QEDE_REVISION_VERSION		0
 #define QEDE_ENGINEERING_VERSION	20
 #define DRV_MODULE_VERSION __stringify(QEDE_MAJOR_VERSION) "."	\
@@ -494,6 +494,9 @@ struct qede_reload_args {
 
 /* Datapath functions definition */
 netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev);
+u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb,
+		      struct net_device *sb_dev,
+		      select_queue_fallback_t fallback);
 netdev_features_t qede_features_check(struct sk_buff *skb,
 				      struct net_device *dev,
 				      netdev_features_t features);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index bdf816fe5a16..31b046e24565 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -1695,6 +1695,19 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	return NETDEV_TX_OK;
 }
 
+u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb,
+		      struct net_device *sb_dev,
+		      select_queue_fallback_t fallback)
+{
+	struct qede_dev *edev = netdev_priv(dev);
+	int total_txq;
+
+	total_txq = QEDE_TSS_COUNT(edev) * edev->dev_info.num_tc;
+
+	return QEDE_TSS_COUNT(edev) ?
+		fallback(dev, skb, NULL) % total_txq :  0;
+}
+
 /* 8B udp header + 8B base tunnel header + 32B option length */
 #define QEDE_MAX_TUN_HDR_LEN 48
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 5a74fcbdbc2b..9790f26d17c4 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -631,6 +631,7 @@ static const struct net_device_ops qede_netdev_ops = {
 	.ndo_open = qede_open,
 	.ndo_stop = qede_close,
 	.ndo_start_xmit = qede_start_xmit,
+	.ndo_select_queue = qede_select_queue,
 	.ndo_set_rx_mode = qede_set_rx_mode,
 	.ndo_set_mac_address = qede_set_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
@@ -666,6 +667,7 @@ static const struct net_device_ops qede_netdev_vf_ops = {
 	.ndo_open = qede_open,
 	.ndo_stop = qede_close,
 	.ndo_start_xmit = qede_start_xmit,
+	.ndo_select_queue = qede_select_queue,
 	.ndo_set_rx_mode = qede_set_rx_mode,
 	.ndo_set_mac_address = qede_set_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
@@ -684,6 +686,7 @@ static const struct net_device_ops qede_netdev_vf_xdp_ops = {
 	.ndo_open = qede_open,
 	.ndo_stop = qede_close,
 	.ndo_start_xmit = qede_start_xmit,
+	.ndo_select_queue = qede_select_queue,
 	.ndo_set_rx_mode = qede_set_rx_mode,
 	.ndo_set_mac_address = qede_set_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c
index 15c62c160953..be47d864f8b9 100644
--- a/drivers/net/ethernet/smsc/epic100.c
+++ b/drivers/net/ethernet/smsc/epic100.c
@@ -1037,7 +1037,7 @@ static void epic_tx(struct net_device *dev, struct epic_private *ep)
 		skb = ep->tx_skbuff[entry];
 		pci_unmap_single(ep->pci_dev, ep->tx_ring[entry].bufaddr,
 				 skb->len, PCI_DMA_TODEVICE);
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 		ep->tx_skbuff[entry] = NULL;
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index d1f61c25d82b..5d85742a2be0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -721,8 +721,11 @@ static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv)
 {
 	unsigned long clk = clk_get_rate(priv->plat->stmmac_clk);
 
-	if (!clk)
-		return 0;
+	if (!clk) {
+		clk = priv->plat->clk_ref_rate;
+		if (!clk)
+			return 0;
+	}
 
 	return (usec * (clk / 1000000)) / 256;
 }
@@ -731,8 +734,11 @@ static u32 stmmac_riwt2usec(u32 riwt, struct stmmac_priv *priv)
 {
 	unsigned long clk = clk_get_rate(priv->plat->stmmac_clk);
 
-	if (!clk)
-		return 0;
+	if (!clk) {
+		clk = priv->plat->clk_ref_rate;
+		if (!clk)
+			return 0;
+	}
 
 	return (riwt * 256) / (clk / 1000000);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 5afba69981cf..685d20472358 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3023,10 +3023,22 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	tx_q = &priv->tx_queue[queue];
 
+	if (priv->tx_path_in_lpi_mode)
+		stmmac_disable_eee_mode(priv);
+
 	/* Manage oversized TCP frames for GMAC4 device */
 	if (skb_is_gso(skb) && priv->tso) {
-		if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))
+		if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
+			/*
+			 * There is no way to determine the number of TSO
+			 * capable Queues. Let's use always the Queue 0
+			 * because if TSO is supported then at least this
+			 * one will be capable.
+			 */
+			skb_set_queue_mapping(skb, 0);
+
 			return stmmac_tso_xmit(skb, dev);
+		}
 	}
 
 	if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) {
@@ -3041,9 +3053,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_BUSY;
 	}
 
-	if (priv->tx_path_in_lpi_mode)
-		stmmac_disable_eee_mode(priv);
-
 	entry = tx_q->cur_tx;
 	first_entry = entry;
 	WARN_ON(tx_q->tx_skbuff[first_entry]);
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 7ec4eb74fe21..6fc05c106afc 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -1898,7 +1898,7 @@ static inline void cas_tx_ringN(struct cas *cp, int ring, int limit)
 		cp->net_stats[ring].tx_packets++;
 		cp->net_stats[ring].tx_bytes += skb->len;
 		spin_unlock(&cp->stat_lock[ring]);
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 	}
 	cp->tx_old[ring] = entry;
 
diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c
index 720b7ac77f3b..e9b757b03b56 100644
--- a/drivers/net/ethernet/sun/sunbmac.c
+++ b/drivers/net/ethernet/sun/sunbmac.c
@@ -781,7 +781,7 @@ static void bigmac_tx(struct bigmac *bp)
 
 		DTX(("skb(%p) ", skb));
 		bp->tx_skbs[elem] = NULL;
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 
 		elem = NEXT_TX(elem);
 	}
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index ff641cf30a4e..d007dfeba5c3 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -1962,7 +1962,7 @@ static void happy_meal_tx(struct happy_meal *hp)
 			this = &txbase[elem];
 		}
 
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 		dev->stats.tx_packets++;
 	}
 	hp->tx_old = elem;
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index dc966ddb6d81..b24c11187017 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -1739,7 +1739,7 @@ static void bdx_tx_cleanup(struct bdx_priv *priv)
 		tx_level -= db->rptr->len;	/* '-' koz len is negative */
 
 		/* now should come skb pointer - free it */
-		dev_kfree_skb_irq(db->rptr->addr.skb);
+		dev_consume_skb_irq(db->rptr->addr.skb);
 		bdx_tx_db_inc_rptr(db);
 	}
 
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index 82412691ee66..27f6cf140845 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -1740,7 +1740,7 @@ static void velocity_free_tx_buf(struct velocity_info *vptr,
 		dma_unmap_single(vptr->dev, tdinfo->skb_dma[i],
 				 le16_to_cpu(pktlen), DMA_TO_DEVICE);
 	}
-	dev_kfree_skb_irq(skb);
+	dev_consume_skb_irq(skb);
 	tdinfo->skb = NULL;
 }