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

Pull networking updates from David Miller:
 "Highlights:

   - Gustavo A. R. Silva keeps working on the implicit switch fallthru
     changes.

   - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
     Luca Coelho.

   - Re-enable ASPM in r8169, from Kai-Heng Feng.

   - Add virtual XFRM interfaces, which avoids all of the limitations of
     existing IPSEC tunnels. From Steffen Klassert.

   - Convert GRO over to use a hash table, so that when we have many
     flows active we don't traverse a long list during accumluation.

   - Many new self tests for routing, TC, tunnels, etc. Too many
     contributors to mention them all, but I'm really happy to keep
     seeing this stuff.

   - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.

   - Lots of cleanups and fixes in L2TP code from Guillaume Nault.

   - Add IPSEC offload support to netdevsim, from Shannon Nelson.

   - Add support for slotting with non-uniform distribution to netem
     packet scheduler, from Yousuk Seung.

   - Add UDP GSO support to mlx5e, from Boris Pismenny.

   - Support offloading of Team LAG in NFP, from John Hurley.

   - Allow to configure TX queue selection based upon RX queue, from
     Amritha Nambiar.

   - Support ethtool ring size configuration in aquantia, from Anton
     Mikaev.

   - Support DSCP and flowlabel per-transport in SCTP, from Xin Long.

   - Support list based batching and stack traversal of SKBs, this is
     very exciting work. From Edward Cree.

   - Busyloop optimizations in vhost_net, from Toshiaki Makita.

   - Introduce the ETF qdisc, which allows time based transmissions. IGB
     can offload this in hardware. From Vinicius Costa Gomes.

   - Add parameter support to devlink, from Moshe Shemesh.

   - Several multiplication and division optimizations for BPF JIT in
     nfp driver, from Jiong Wang.

   - Lots of prepatory work to make more of the packet scheduler layer
     lockless, when possible, from Vlad Buslov.

   - Add ACK filter and NAT awareness to sch_cake packet scheduler, from
     Toke Høiland-Jørgensen.

   - Support regions and region snapshots in devlink, from Alex Vesker.

   - Allow to attach XDP programs to both HW and SW at the same time on
     a given device, with initial support in nfp. From Jakub Kicinski.

   - Add TLS RX offload and support in mlx5, from Ilya Lesokhin.

   - Use PHYLIB in r8169 driver, from Heiner Kallweit.

   - All sorts of changes to support Spectrum 2 in mlxsw driver, from
     Ido Schimmel.

   - PTP support in mv88e6xxx DSA driver, from Andrew Lunn.

   - Make TCP_USER_TIMEOUT socket option more accurate, from Jon
     Maxwell.

   - Support for templates in packet scheduler classifier, from Jiri
     Pirko.

   - IPV6 support in RDS, from Ka-Cheong Poon.

   - Native tproxy support in nf_tables, from Máté Eckl.

   - Maintain IP fragment queue in an rbtree, but optimize properly for
     in-order frags. From Peter Oskolkov.

   - Improvde handling of ACKs on hole repairs, from Yuchung Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
  bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
  hv/netvsc: Fix NULL dereference at single queue mode fallback
  net: filter: mark expected switch fall-through
  xen-netfront: fix warn message as irq device name has '/'
  cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
  net: dsa: mv88e6xxx: missing unlock on error path
  rds: fix building with IPV6=m
  inet/connection_sock: prefer _THIS_IP_ to current_text_addr
  net: dsa: mv88e6xxx: bitwise vs logical bug
  net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
  ieee802154: hwsim: using right kind of iteration
  net: hns3: Add vlan filter setting by ethtool command -K
  net: hns3: Set tx ring' tc info when netdev is up
  net: hns3: Remove tx ring BD len register in hns3_enet
  net: hns3: Fix desc num set to default when setting channel
  net: hns3: Fix for phy link issue when using marvell phy driver
  net: hns3: Fix for information of phydev lost problem when down/up
  net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
  net: hns3: Add support for serdes loopback selftest
  bnxt_en: take coredump_record structure off stack
  ...

51 files changed, 3690 insertions, 1310 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 2545296a0c08..37a551436e4a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -3,10 +3,11 @@
 #
 
 config MLX5_CORE
-	tristate "Mellanox Technologies ConnectX-4 and Connect-IB core driver"
+	tristate "Mellanox 5th generation network adapters (ConnectX series) core driver"
 	depends on MAY_USE_DEVLINK
 	depends on PCI
 	imply PTP_1588_CLOCK
+	imply VXLAN
 	default n
 	---help---
 	  Core driver for low level functionality of the ConnectX-4 and
@@ -27,7 +28,7 @@ config MLX5_FPGA
           sandbox-specific client drivers.
 
 config MLX5_CORE_EN
-	bool "Mellanox Technologies ConnectX-4 Ethernet support"
+	bool "Mellanox 5th generation network adapters (ConnectX series) Ethernet support"
 	depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE
 	depends on IPV6=y || IPV6=n || MLX5_CORE=m
 	select PAGE_POOL
@@ -35,6 +36,24 @@ config MLX5_CORE_EN
 	---help---
 	  Ethernet support in Mellanox Technologies ConnectX-4 NIC.
 
+config MLX5_EN_ARFS
+	bool "Mellanox MLX5 ethernet accelerated receive flow steering (ARFS) support"
+	depends on MLX5_CORE_EN && RFS_ACCEL
+	default y
+	---help---
+	  Mellanox MLX5 ethernet hardware-accelerated receive flow steering support,
+	  Enables ethernet netdevice arfs support and ntuple filtering.
+
+config MLX5_EN_RXNFC
+	bool "Mellanox MLX5 ethernet rx nfc flow steering support"
+	depends on MLX5_CORE_EN
+	default y
+	---help---
+	  Mellanox MLX5 ethernet rx nfc flow steering support
+	  Enables ethtool receive network flow classification, which allows user defined
+	  flow rules to direct traffic into arbitrary rx queue via ethtool set/get_rxnfc
+	  API.
+
 config MLX5_MPFS
         bool "Mellanox Technologies MLX5 MPFS support"
         depends on MLX5_CORE_EN
@@ -69,7 +88,7 @@ config MLX5_CORE_EN_DCB
 	  If unsure, set to Y
 
 config MLX5_CORE_IPOIB
-	bool "Mellanox Technologies ConnectX-4 IPoIB offloads support"
+	bool "Mellanox 5th generation network adapters (connectX series) IPoIB offloads support"
 	depends on MLX5_CORE_EN
 	default n
 	---help---
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 9efbf193ad5a..d324a3884462 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -1,33 +1,61 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_MLX5_CORE)		+= mlx5_core.o
+#
+# Makefile for Mellanox 5th generation network adapters
+# (ConnectX series) core & netdev driver
+#
+
 subdir-ccflags-y += -I$(src)
 
+obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
+
+#
+# mlx5 core basic
+#
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \
 		mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
-		fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o lib/clock.o \
-		diag/fs_tracepoint.o
-
-mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o
-
-mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
-		fpga/ipsec.o fpga/tls.o
+		fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o  \
+		diag/fs_tracepoint.o diag/fw_tracer.o
 
+#
+# Netdev basic
+#
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
-		en_tx.o en_rx.o en_dim.o en_txrx.o en_stats.o vxlan.o \
-		en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o
-
-mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
-
-mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o en_rep.o en_tc.o
+		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
+		en_selftest.o en/port.o
+
+#
+# Netdev extra
+#
+mlx5_core-$(CONFIG_MLX5_EN_ARFS)     += en_arfs.o
+mlx5_core-$(CONFIG_MLX5_EN_RXNFC)    += en_fs_ethtool.o
+mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o
+
+#
+# Core extra
+#
+mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o
+mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
+mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
+mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
+
+#
+# Ipoib netdev
+#
+mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib_vlan.o
 
-mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) +=  en_dcbnl.o en/port_buffer.o
+#
+# Accelerations & FPGA
+#
+mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o
 
-mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib_vlan.o
+mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
+				 fpga/ipsec.o fpga/tls.o
 
 mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \
-		en_accel/ipsec_stats.o
+				     en_accel/ipsec_stats.o
 
-mlx5_core-$(CONFIG_MLX5_EN_TLS) +=  en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o
+mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o
 
 CFLAGS_tracepoint.o := -I$(src)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/accel.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/accel.h
new file mode 100644
index 000000000000..c13260467750
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/accel.h
@@ -0,0 +1,37 @@
+#ifndef __MLX5E_ACCEL_H__
+#define __MLX5E_ACCEL_H__
+
+#ifdef CONFIG_MLX5_ACCEL
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include "en.h"
+
+static inline bool is_metadata_hdr_valid(struct sk_buff *skb)
+{
+	__be16 *ethtype;
+
+	if (unlikely(skb->len < ETH_HLEN + MLX5E_METADATA_ETHER_LEN))
+		return false;
+	ethtype = (__be16 *)(skb->data + ETH_ALEN * 2);
+	if (*ethtype != cpu_to_be16(MLX5E_METADATA_ETHER_TYPE))
+		return false;
+	return true;
+}
+
+static inline void remove_metadata_hdr(struct sk_buff *skb)
+{
+	struct ethhdr *old_eth;
+	struct ethhdr *new_eth;
+
+	/* Remove the metadata from the buffer */
+	old_eth = (struct ethhdr *)skb->data;
+	new_eth = (struct ethhdr *)(skb->data + MLX5E_METADATA_ETHER_LEN);
+	memmove(new_eth, old_eth, 2 * ETH_ALEN);
+	/* Ethertype is already in its new place */
+	skb_pull_inline(skb, MLX5E_METADATA_ETHER_LEN);
+}
+
+#endif /* CONFIG_MLX5_ACCEL */
+
+#endif /* __MLX5E_EN_ACCEL_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
index 77ac19f38cbe..da7bd26368f9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
@@ -37,17 +37,26 @@
 #include "mlx5_core.h"
 #include "fpga/tls.h"
 
-int mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
-			       struct tls_crypto_info *crypto_info,
-			       u32 start_offload_tcp_sn, u32 *p_swid)
+int mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+			    struct tls_crypto_info *crypto_info,
+			    u32 start_offload_tcp_sn, u32 *p_swid,
+			    bool direction_sx)
 {
-	return mlx5_fpga_tls_add_tx_flow(mdev, flow, crypto_info,
-					 start_offload_tcp_sn, p_swid);
+	return mlx5_fpga_tls_add_flow(mdev, flow, crypto_info,
+				      start_offload_tcp_sn, p_swid,
+				      direction_sx);
 }
 
-void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid)
+void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+			     bool direction_sx)
 {
-	mlx5_fpga_tls_del_tx_flow(mdev, swid, GFP_KERNEL);
+	mlx5_fpga_tls_del_flow(mdev, swid, GFP_KERNEL, direction_sx);
+}
+
+int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
+			     u64 rcd_sn)
+{
+	return mlx5_fpga_tls_resync_rx(mdev, handle, seq, rcd_sn);
 }
 
 bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
index 6f9c9f446ecc..def4093ebfae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
@@ -60,10 +60,14 @@ struct mlx5_ifc_tls_flow_bits {
 	u8         reserved_at_2[0x1e];
 };
 
-int mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
-			       struct tls_crypto_info *crypto_info,
-			       u32 start_offload_tcp_sn, u32 *p_swid);
-void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid);
+int mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+			    struct tls_crypto_info *crypto_info,
+			    u32 start_offload_tcp_sn, u32 *p_swid,
+			    bool direction_sx);
+void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+			     bool direction_sx);
+int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
+			     u64 rcd_sn);
 bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev);
 u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev);
 int mlx5_accel_tls_init(struct mlx5_core_dev *mdev);
@@ -72,10 +76,14 @@ void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev);
 #else
 
 static inline int
-mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
-			   struct tls_crypto_info *crypto_info,
-			   u32 start_offload_tcp_sn, u32 *p_swid) { return 0; }
-static inline void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid) { }
+mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+			struct tls_crypto_info *crypto_info,
+			u32 start_offload_tcp_sn, u32 *p_swid,
+			bool direction_sx) { return -ENOTSUPP; }
+static inline void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+					   bool direction_sx) { }
+static inline int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle,
+					   u32 seq, u64 rcd_sn) { return 0; }
 static inline bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev) { return false; }
 static inline u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev) { return 0; }
 static inline int mlx5_accel_tls_init(struct mlx5_core_dev *mdev) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 384c1fa49081..fe4ac40dbade 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -211,7 +211,7 @@ static void poll_timeout(struct mlx5_cmd_work_ent *ent)
 			ent->ret = 0;
 			return;
 		}
-		usleep_range(5000, 10000);
+		cond_resched();
 	} while (time_before(jiffies, poll_end));
 
 	ent->ret = -ETIMEDOUT;
@@ -278,6 +278,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_DESTROY_PSV:
 	case MLX5_CMD_OP_DESTROY_SRQ:
 	case MLX5_CMD_OP_DESTROY_XRC_SRQ:
+	case MLX5_CMD_OP_DESTROY_XRQ:
 	case MLX5_CMD_OP_DESTROY_DCT:
 	case MLX5_CMD_OP_DEALLOC_Q_COUNTER:
 	case MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT:
@@ -310,6 +311,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_DEALLOC_ENCAP_HEADER:
 	case MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT:
 	case MLX5_CMD_OP_FPGA_DESTROY_QP:
+	case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -346,6 +348,9 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_CREATE_XRC_SRQ:
 	case MLX5_CMD_OP_QUERY_XRC_SRQ:
 	case MLX5_CMD_OP_ARM_XRC_SRQ:
+	case MLX5_CMD_OP_CREATE_XRQ:
+	case MLX5_CMD_OP_QUERY_XRQ:
+	case MLX5_CMD_OP_ARM_XRQ:
 	case MLX5_CMD_OP_CREATE_DCT:
 	case MLX5_CMD_OP_DRAIN_DCT:
 	case MLX5_CMD_OP_QUERY_DCT:
@@ -427,6 +432,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_FPGA_MODIFY_QP:
 	case MLX5_CMD_OP_FPGA_QUERY_QP:
 	case MLX5_CMD_OP_FPGA_QUERY_QP_COUNTERS:
+	case MLX5_CMD_OP_CREATE_GENERAL_OBJECT:
 		*status = MLX5_DRIVER_STATUS_ABORTED;
 		*synd = MLX5_DRIVER_SYND;
 		return -EIO;
@@ -452,6 +458,7 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(SET_HCA_CAP);
 	MLX5_COMMAND_STR_CASE(QUERY_ISSI);
 	MLX5_COMMAND_STR_CASE(SET_ISSI);
+	MLX5_COMMAND_STR_CASE(SET_DRIVER_VERSION);
 	MLX5_COMMAND_STR_CASE(CREATE_MKEY);
 	MLX5_COMMAND_STR_CASE(QUERY_MKEY);
 	MLX5_COMMAND_STR_CASE(DESTROY_MKEY);
@@ -599,6 +606,12 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(FPGA_QUERY_QP);
 	MLX5_COMMAND_STR_CASE(FPGA_QUERY_QP_COUNTERS);
 	MLX5_COMMAND_STR_CASE(FPGA_DESTROY_QP);
+	MLX5_COMMAND_STR_CASE(CREATE_XRQ);
+	MLX5_COMMAND_STR_CASE(DESTROY_XRQ);
+	MLX5_COMMAND_STR_CASE(QUERY_XRQ);
+	MLX5_COMMAND_STR_CASE(ARM_XRQ);
+	MLX5_COMMAND_STR_CASE(CREATE_GENERAL_OBJECT);
+	MLX5_COMMAND_STR_CASE(DESTROY_GENERAL_OBJECT);
 	default: return "unknown command opcode";
 	}
 }
@@ -677,7 +690,7 @@ struct mlx5_ifc_mbox_out_bits {
 
 struct mlx5_ifc_mbox_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_at_10[0x10];
+	u8         uid[0x10];
 
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
@@ -697,6 +710,7 @@ static int mlx5_cmd_check(struct mlx5_core_dev *dev, void *in, void *out)
 	u8  status;
 	u16 opcode;
 	u16 op_mod;
+	u16 uid;
 
 	mlx5_cmd_mbox_status(out, &status, &syndrome);
 	if (!status)
@@ -704,8 +718,15 @@ static int mlx5_cmd_check(struct mlx5_core_dev *dev, void *in, void *out)
 
 	opcode = MLX5_GET(mbox_in, in, opcode);
 	op_mod = MLX5_GET(mbox_in, in, op_mod);
+	uid    = MLX5_GET(mbox_in, in, uid);
 
-	mlx5_core_err(dev,
+	if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY)
+		mlx5_core_err_rl(dev,
+			"%s(0x%x) op_mod(0x%x) failed, status %s(0x%x), syndrome (0x%x)\n",
+			mlx5_command_str(opcode), opcode, op_mod,
+			cmd_status_str(status), status, syndrome);
+	else
+		mlx5_core_dbg(dev,
 		      "%s(0x%x) op_mod(0x%x) failed, status %s(0x%x), syndrome (0x%x)\n",
 		      mlx5_command_str(opcode),
 		      opcode, op_mod,
@@ -1022,7 +1043,10 @@ static ssize_t dbg_write(struct file *filp, const char __user *buf,
 	if (!dbg->in_msg || !dbg->out_msg)
 		return -ENOMEM;
 
-	if (copy_from_user(lbuf, buf, sizeof(lbuf)))
+	if (count < sizeof(lbuf) - 1)
+		return -EINVAL;
+
+	if (copy_from_user(lbuf, buf, sizeof(lbuf) - 1))
 		return -EFAULT;
 
 	lbuf[sizeof(lbuf) - 1] = 0;
@@ -1226,21 +1250,12 @@ static ssize_t data_read(struct file *filp, char __user *buf, size_t count,
 {
 	struct mlx5_core_dev *dev = filp->private_data;
 	struct mlx5_cmd_debug *dbg = &dev->cmd.dbg;
-	int copy;
-
-	if (*pos)
-		return 0;
 
 	if (!dbg->out_msg)
 		return -ENOMEM;
 
-	copy = min_t(int, count, dbg->outlen);
-	if (copy_to_user(buf, dbg->out_msg, copy))
-		return -EFAULT;
-
-	*pos += copy;
-
-	return copy;
+	return simple_read_from_buffer(buf, count, pos, dbg->out_msg,
+				       dbg->outlen);
 }
 
 static const struct file_operations dfops = {
@@ -1258,19 +1273,11 @@ static ssize_t outlen_read(struct file *filp, char __user *buf, size_t count,
 	char outlen[8];
 	int err;
 
-	if (*pos)
-		return 0;
-
 	err = snprintf(outlen, sizeof(outlen), "%d", dbg->outlen);
 	if (err < 0)
 		return err;
 
-	if (copy_to_user(buf, &outlen, err))
-		return -EFAULT;
-
-	*pos += err;
-
-	return err;
+	return simple_read_from_buffer(buf, count, pos, outlen, err);
 }
 
 static ssize_t outlen_write(struct file *filp, const char __user *buf,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 413080a312a7..90fabd612b6c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -150,22 +150,13 @@ static ssize_t average_read(struct file *filp, char __user *buf, size_t count,
 	int ret;
 	char tbuf[22];
 
-	if (*pos)
-		return 0;
-
 	stats = filp->private_data;
 	spin_lock_irq(&stats->lock);
 	if (stats->n)
 		field = div64_u64(stats->sum, stats->n);
 	spin_unlock_irq(&stats->lock);
 	ret = snprintf(tbuf, sizeof(tbuf), "%llu\n", field);
-	if (ret > 0) {
-		if (copy_to_user(buf, tbuf, ret))
-			return -EFAULT;
-	}
-
-	*pos += ret;
-	return ret;
+	return simple_read_from_buffer(buf, count, pos, tbuf, ret);
 }
 
 static ssize_t average_write(struct file *filp, const char __user *buf,
@@ -442,9 +433,6 @@ static ssize_t dbg_read(struct file *filp, char __user *buf, size_t count,
 	u64 field;
 	int ret;
 
-	if (*pos)
-		return 0;
-
 	desc = filp->private_data;
 	d = (void *)(desc - desc->i) - sizeof(*d);
 	switch (d->type) {
@@ -470,13 +458,7 @@ static ssize_t dbg_read(struct file *filp, char __user *buf, size_t count,
 	else
 		ret = snprintf(tbuf, sizeof(tbuf), "0x%llx\n", field);
 
-	if (ret > 0) {
-		if (copy_to_user(buf, tbuf, ret))
-			return -EFAULT;
-	}
-
-	*pos += ret;
-	return ret;
+	return simple_read_from_buffer(buf, count, pos, tbuf, ret);
 }
 
 static const struct file_operations fops = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
index 09f178a3fcab..0240aee9189e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
@@ -138,6 +138,8 @@ TRACE_EVENT(mlx5_fs_del_fg,
 	{MLX5_FLOW_CONTEXT_ACTION_MOD_HDR,	 "MOD_HDR"},\
 	{MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH,	 "VLAN_PUSH"},\
 	{MLX5_FLOW_CONTEXT_ACTION_VLAN_POP,	 "VLAN_POP"},\
+	{MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2,	 "VLAN_PUSH_2"},\
+	{MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2,	 "VLAN_POP_2"},\
 	{MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO, "NEXT_PRIO"}
 
 TRACE_EVENT(mlx5_fs_set_fte,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
new file mode 100644
index 000000000000..d4ec93bde4de
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -0,0 +1,947 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#define CREATE_TRACE_POINTS
+#include "fw_tracer.h"
+#include "fw_tracer_tracepoint.h"
+
+static int mlx5_query_mtrc_caps(struct mlx5_fw_tracer *tracer)
+{
+	u32 *string_db_base_address_out = tracer->str_db.base_address_out;
+	u32 *string_db_size_out = tracer->str_db.size_out;
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 out[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+	void *mtrc_cap_sp;
+	int err, i;
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
+				   MLX5_REG_MTRC_CAP, 0, 0);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Error reading tracer caps %d\n",
+			       err);
+		return err;
+	}
+
+	if (!MLX5_GET(mtrc_cap, out, trace_to_memory)) {
+		mlx5_core_dbg(dev, "FWTracer: Device does not support logging traces to memory\n");
+		return -ENOTSUPP;
+	}
+
+	tracer->trc_ver = MLX5_GET(mtrc_cap, out, trc_ver);
+	tracer->str_db.first_string_trace =
+			MLX5_GET(mtrc_cap, out, first_string_trace);
+	tracer->str_db.num_string_trace =
+			MLX5_GET(mtrc_cap, out, num_string_trace);
+	tracer->str_db.num_string_db = MLX5_GET(mtrc_cap, out, num_string_db);
+	tracer->owner = !!MLX5_GET(mtrc_cap, out, trace_owner);
+
+	for (i = 0; i < tracer->str_db.num_string_db; i++) {
+		mtrc_cap_sp = MLX5_ADDR_OF(mtrc_cap, out, string_db_param[i]);
+		string_db_base_address_out[i] = MLX5_GET(mtrc_string_db_param,
+							 mtrc_cap_sp,
+							 string_db_base_address);
+		string_db_size_out[i] = MLX5_GET(mtrc_string_db_param,
+						 mtrc_cap_sp, string_db_size);
+	}
+
+	return err;
+}
+
+static int mlx5_set_mtrc_caps_trace_owner(struct mlx5_fw_tracer *tracer,
+					  u32 *out, u32 out_size,
+					  u8 trace_owner)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 in[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+
+	MLX5_SET(mtrc_cap, in, trace_owner, trace_owner);
+
+	return mlx5_core_access_reg(dev, in, sizeof(in), out, out_size,
+				    MLX5_REG_MTRC_CAP, 0, 1);
+}
+
+static int mlx5_fw_tracer_ownership_acquire(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 out[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+	int err;
+
+	err = mlx5_set_mtrc_caps_trace_owner(tracer, out, sizeof(out),
+					     MLX5_FW_TRACER_ACQUIRE_OWNERSHIP);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Acquire tracer ownership failed %d\n",
+			       err);
+		return err;
+	}
+
+	tracer->owner = !!MLX5_GET(mtrc_cap, out, trace_owner);
+
+	if (!tracer->owner)
+		return -EBUSY;
+
+	return 0;
+}
+
+static void mlx5_fw_tracer_ownership_release(struct mlx5_fw_tracer *tracer)
+{
+	u32 out[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+
+	mlx5_set_mtrc_caps_trace_owner(tracer, out, sizeof(out),
+				       MLX5_FW_TRACER_RELEASE_OWNERSHIP);
+	tracer->owner = false;
+}
+
+static int mlx5_fw_tracer_create_log_buf(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	struct device *ddev = &dev->pdev->dev;
+	dma_addr_t dma;
+	void *buff;
+	gfp_t gfp;
+	int err;
+
+	tracer->buff.size = TRACE_BUFFER_SIZE_BYTE;
+
+	gfp = GFP_KERNEL | __GFP_ZERO;
+	buff = (void *)__get_free_pages(gfp,
+					get_order(tracer->buff.size));
+	if (!buff) {
+		err = -ENOMEM;
+		mlx5_core_warn(dev, "FWTracer: Failed to allocate pages, %d\n", err);
+		return err;
+	}
+	tracer->buff.log_buf = buff;
+
+	dma = dma_map_single(ddev, buff, tracer->buff.size, DMA_FROM_DEVICE);
+	if (dma_mapping_error(ddev, dma)) {
+		mlx5_core_warn(dev, "FWTracer: Unable to map DMA: %d\n",
+			       dma_mapping_error(ddev, dma));
+		err = -ENOMEM;
+		goto free_pages;
+	}
+	tracer->buff.dma = dma;
+
+	return 0;
+
+free_pages:
+	free_pages((unsigned long)tracer->buff.log_buf, get_order(tracer->buff.size));
+
+	return err;
+}
+
+static void mlx5_fw_tracer_destroy_log_buf(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	struct device *ddev = &dev->pdev->dev;
+
+	if (!tracer->buff.log_buf)
+		return;
+
+	dma_unmap_single(ddev, tracer->buff.dma, tracer->buff.size, DMA_FROM_DEVICE);
+	free_pages((unsigned long)tracer->buff.log_buf, get_order(tracer->buff.size));
+}
+
+static int mlx5_fw_tracer_create_mkey(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	int err, inlen, i;
+	__be64 *mtt;
+	void *mkc;
+	u32 *in;
+
+	inlen = MLX5_ST_SZ_BYTES(create_mkey_in) +
+			sizeof(*mtt) * round_up(TRACER_BUFFER_PAGE_NUM, 2);
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(create_mkey_in, in, translations_octword_actual_size,
+		 DIV_ROUND_UP(TRACER_BUFFER_PAGE_NUM, 2));
+	mtt = (u64 *)MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt);
+	for (i = 0 ; i < TRACER_BUFFER_PAGE_NUM ; i++)
+		mtt[i] = cpu_to_be64(tracer->buff.dma + i * PAGE_SIZE);
+
+	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
+	MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_MTT);
+	MLX5_SET(mkc, mkc, lr, 1);
+	MLX5_SET(mkc, mkc, lw, 1);
+	MLX5_SET(mkc, mkc, pd, tracer->buff.pdn);
+	MLX5_SET(mkc, mkc, bsf_octword_size, 0);
+	MLX5_SET(mkc, mkc, qpn, 0xffffff);
+	MLX5_SET(mkc, mkc, log_page_size, PAGE_SHIFT);
+	MLX5_SET(mkc, mkc, translations_octword_size,
+		 DIV_ROUND_UP(TRACER_BUFFER_PAGE_NUM, 2));
+	MLX5_SET64(mkc, mkc, start_addr, tracer->buff.dma);
+	MLX5_SET64(mkc, mkc, len, tracer->buff.size);
+	err = mlx5_core_create_mkey(dev, &tracer->buff.mkey, in, inlen);
+	if (err)
+		mlx5_core_warn(dev, "FWTracer: Failed to create mkey, %d\n", err);
+
+	kvfree(in);
+
+	return err;
+}
+
+static void mlx5_fw_tracer_free_strings_db(struct mlx5_fw_tracer *tracer)
+{
+	u32 num_string_db = tracer->str_db.num_string_db;
+	int i;
+
+	for (i = 0; i < num_string_db; i++) {
+		kfree(tracer->str_db.buffer[i]);
+		tracer->str_db.buffer[i] = NULL;
+	}
+}
+
+static int mlx5_fw_tracer_allocate_strings_db(struct mlx5_fw_tracer *tracer)
+{
+	u32 *string_db_size_out = tracer->str_db.size_out;
+	u32 num_string_db = tracer->str_db.num_string_db;
+	int i;
+
+	for (i = 0; i < num_string_db; i++) {
+		tracer->str_db.buffer[i] = kzalloc(string_db_size_out[i], GFP_KERNEL);
+		if (!tracer->str_db.buffer[i])
+			goto free_strings_db;
+	}
+
+	return 0;
+
+free_strings_db:
+	mlx5_fw_tracer_free_strings_db(tracer);
+	return -ENOMEM;
+}
+
+static void mlx5_tracer_read_strings_db(struct work_struct *work)
+{
+	struct mlx5_fw_tracer *tracer = container_of(work, struct mlx5_fw_tracer,
+						     read_fw_strings_work);
+	u32 num_of_reads, num_string_db = tracer->str_db.num_string_db;
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 in[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+	u32 leftovers, offset;
+	int err = 0, i, j;
+	u32 *out, outlen;
+	void *out_value;
+
+	outlen = MLX5_ST_SZ_BYTES(mtrc_stdb) + STRINGS_DB_READ_SIZE_BYTES;
+	out = kzalloc(outlen, GFP_KERNEL);
+	if (!out) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < num_string_db; i++) {
+		offset = 0;
+		MLX5_SET(mtrc_stdb, in, string_db_index, i);
+		num_of_reads = tracer->str_db.size_out[i] /
+				STRINGS_DB_READ_SIZE_BYTES;
+		leftovers = (tracer->str_db.size_out[i] %
+				STRINGS_DB_READ_SIZE_BYTES) /
+					STRINGS_DB_LEFTOVER_SIZE_BYTES;
+
+		MLX5_SET(mtrc_stdb, in, read_size, STRINGS_DB_READ_SIZE_BYTES);
+		for (j = 0; j < num_of_reads; j++) {
+			MLX5_SET(mtrc_stdb, in, start_offset, offset);
+
+			err = mlx5_core_access_reg(dev, in, sizeof(in), out,
+						   outlen, MLX5_REG_MTRC_STDB,
+						   0, 1);
+			if (err) {
+				mlx5_core_dbg(dev, "FWTracer: Failed to read strings DB %d\n",
+					      err);
+				goto out_free;
+			}
+
+			out_value = MLX5_ADDR_OF(mtrc_stdb, out, string_db_data);
+			memcpy(tracer->str_db.buffer[i] + offset, out_value,
+			       STRINGS_DB_READ_SIZE_BYTES);
+			offset += STRINGS_DB_READ_SIZE_BYTES;
+		}
+
+		/* Strings database is aligned to 64, need to read leftovers*/
+		MLX5_SET(mtrc_stdb, in, read_size,
+			 STRINGS_DB_LEFTOVER_SIZE_BYTES);
+		for (j = 0; j < leftovers; j++) {
+			MLX5_SET(mtrc_stdb, in, start_offset, offset);
+
+			err = mlx5_core_access_reg(dev, in, sizeof(in), out,
+						   outlen, MLX5_REG_MTRC_STDB,
+						   0, 1);
+			if (err) {
+				mlx5_core_dbg(dev, "FWTracer: Failed to read strings DB %d\n",
+					      err);
+				goto out_free;
+			}
+
+			out_value = MLX5_ADDR_OF(mtrc_stdb, out, string_db_data);
+			memcpy(tracer->str_db.buffer[i] + offset, out_value,
+			       STRINGS_DB_LEFTOVER_SIZE_BYTES);
+			offset += STRINGS_DB_LEFTOVER_SIZE_BYTES;
+		}
+	}
+
+	tracer->str_db.loaded = true;
+
+out_free:
+	kfree(out);
+out:
+	return;
+}
+
+static void mlx5_fw_tracer_arm(struct mlx5_core_dev *dev)
+{
+	u32 out[MLX5_ST_SZ_DW(mtrc_ctrl)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mtrc_ctrl)] = {0};
+	int err;
+
+	MLX5_SET(mtrc_ctrl, in, arm_event, 1);
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
+				   MLX5_REG_MTRC_CTRL, 0, 1);
+	if (err)
+		mlx5_core_warn(dev, "FWTracer: Failed to arm tracer event %d\n", err);
+}
+
+static const char *VAL_PARM		= "%llx";
+static const char *REPLACE_64_VAL_PARM	= "%x%x";
+static const char *PARAM_CHAR		= "%";
+
+static int mlx5_tracer_message_hash(u32 message_id)
+{
+	return jhash_1word(message_id, 0) & (MESSAGE_HASH_SIZE - 1);
+}
+
+static struct tracer_string_format *mlx5_tracer_message_insert(struct mlx5_fw_tracer *tracer,
+							       struct tracer_event *tracer_event)
+{
+	struct hlist_head *head =
+		&tracer->hash[mlx5_tracer_message_hash(tracer_event->string_event.tmsn)];
+	struct tracer_string_format *cur_string;
+
+	cur_string = kzalloc(sizeof(*cur_string), GFP_KERNEL);
+	if (!cur_string)
+		return NULL;
+
+	hlist_add_head(&cur_string->hlist, head);
+
+	return cur_string;
+}
+
+static struct tracer_string_format *mlx5_tracer_get_string(struct mlx5_fw_tracer *tracer,
+							   struct tracer_event *tracer_event)
+{
+	struct tracer_string_format *cur_string;
+	u32 str_ptr, offset;
+	int i;
+
+	str_ptr = tracer_event->string_event.string_param;
+
+	for (i = 0; i < tracer->str_db.num_string_db; i++) {
+		if (str_ptr > tracer->str_db.base_address_out[i] &&
+		    str_ptr < tracer->str_db.base_address_out[i] +
+		    tracer->str_db.size_out[i]) {
+			offset = str_ptr - tracer->str_db.base_address_out[i];
+			/* add it to the hash */
+			cur_string = mlx5_tracer_message_insert(tracer, tracer_event);
+			if (!cur_string)
+				return NULL;
+			cur_string->string = (char *)(tracer->str_db.buffer[i] +
+							offset);
+			return cur_string;
+		}
+	}
+
+	return NULL;
+}
+
+static void mlx5_tracer_clean_message(struct tracer_string_format *str_frmt)
+{
+	hlist_del(&str_frmt->hlist);
+	kfree(str_frmt);
+}
+
+static int mlx5_tracer_get_num_of_params(char *str)
+{
+	char *substr, *pstr = str;
+	int num_of_params = 0;
+
+	/* replace %llx with %x%x */
+	substr = strstr(pstr, VAL_PARM);
+	while (substr) {
+		memcpy(substr, REPLACE_64_VAL_PARM, 4);
+		pstr = substr;
+		substr = strstr(pstr, VAL_PARM);
+	}
+
+	/* count all the % characters */
+	substr = strstr(str, PARAM_CHAR);
+	while (substr) {
+		num_of_params += 1;
+		str = substr + 1;
+		substr = strstr(str, PARAM_CHAR);
+	}
+
+	return num_of_params;
+}
+
+static struct tracer_string_format *mlx5_tracer_message_find(struct hlist_head *head,
+							     u8 event_id, u32 tmsn)
+{
+	struct tracer_string_format *message;
+
+	hlist_for_each_entry(message, head, hlist)
+		if (message->event_id == event_id && message->tmsn == tmsn)
+			return message;
+
+	return NULL;
+}
+
+static struct tracer_string_format *mlx5_tracer_message_get(struct mlx5_fw_tracer *tracer,
+							    struct tracer_event *tracer_event)
+{
+	struct hlist_head *head =
+		&tracer->hash[mlx5_tracer_message_hash(tracer_event->string_event.tmsn)];
+
+	return mlx5_tracer_message_find(head, tracer_event->event_id, tracer_event->string_event.tmsn);
+}
+
+static void poll_trace(struct mlx5_fw_tracer *tracer,
+		       struct tracer_event *tracer_event, u64 *trace)
+{
+	u32 timestamp_low, timestamp_mid, timestamp_high, urts;
+
+	tracer_event->event_id = MLX5_GET(tracer_event, trace, event_id);
+	tracer_event->lost_event = MLX5_GET(tracer_event, trace, lost);
+
+	switch (tracer_event->event_id) {
+	case TRACER_EVENT_TYPE_TIMESTAMP:
+		tracer_event->type = TRACER_EVENT_TYPE_TIMESTAMP;
+		urts = MLX5_GET(tracer_timestamp_event, trace, urts);
+		if (tracer->trc_ver == 0)
+			tracer_event->timestamp_event.unreliable = !!(urts >> 2);
+		else
+			tracer_event->timestamp_event.unreliable = !!(urts & 1);
+
+		timestamp_low = MLX5_GET(tracer_timestamp_event,
+					 trace, timestamp7_0);
+		timestamp_mid = MLX5_GET(tracer_timestamp_event,
+					 trace, timestamp39_8);
+		timestamp_high = MLX5_GET(tracer_timestamp_event,
+					  trace, timestamp52_40);
+
+		tracer_event->timestamp_event.timestamp =
+				((u64)timestamp_high << 40) |
+				((u64)timestamp_mid << 8) |
+				(u64)timestamp_low;
+		break;
+	default:
+		if (tracer_event->event_id >= tracer->str_db.first_string_trace ||
+		    tracer_event->event_id <= tracer->str_db.first_string_trace +
+					      tracer->str_db.num_string_trace) {
+			tracer_event->type = TRACER_EVENT_TYPE_STRING;
+			tracer_event->string_event.timestamp =
+				MLX5_GET(tracer_string_event, trace, timestamp);
+			tracer_event->string_event.string_param =
+				MLX5_GET(tracer_string_event, trace, string_param);
+			tracer_event->string_event.tmsn =
+				MLX5_GET(tracer_string_event, trace, tmsn);
+			tracer_event->string_event.tdsn =
+				MLX5_GET(tracer_string_event, trace, tdsn);
+		} else {
+			tracer_event->type = TRACER_EVENT_TYPE_UNRECOGNIZED;
+		}
+		break;
+	}
+}
+
+static u64 get_block_timestamp(struct mlx5_fw_tracer *tracer, u64 *ts_event)
+{
+	struct tracer_event tracer_event;
+	u8 event_id;
+
+	event_id = MLX5_GET(tracer_event, ts_event, event_id);
+
+	if (event_id == TRACER_EVENT_TYPE_TIMESTAMP)
+		poll_trace(tracer, &tracer_event, ts_event);
+	else
+		tracer_event.timestamp_event.timestamp = 0;
+
+	return tracer_event.timestamp_event.timestamp;
+}
+
+static void mlx5_fw_tracer_clean_print_hash(struct mlx5_fw_tracer *tracer)
+{
+	struct tracer_string_format *str_frmt;
+	struct hlist_node *n;
+	int i;
+
+	for (i = 0; i < MESSAGE_HASH_SIZE; i++) {
+		hlist_for_each_entry_safe(str_frmt, n, &tracer->hash[i], hlist)
+			mlx5_tracer_clean_message(str_frmt);
+	}
+}
+
+static void mlx5_fw_tracer_clean_ready_list(struct mlx5_fw_tracer *tracer)
+{
+	struct tracer_string_format *str_frmt, *tmp_str;
+
+	list_for_each_entry_safe(str_frmt, tmp_str, &tracer->ready_strings_list,
+				 list)
+		list_del(&str_frmt->list);
+}
+
+static void mlx5_tracer_print_trace(struct tracer_string_format *str_frmt,
+				    struct mlx5_core_dev *dev,
+				    u64 trace_timestamp)
+{
+	char	tmp[512];
+
+	snprintf(tmp, sizeof(tmp), str_frmt->string,
+		 str_frmt->params[0],
+		 str_frmt->params[1],
+		 str_frmt->params[2],
+		 str_frmt->params[3],
+		 str_frmt->params[4],
+		 str_frmt->params[5],
+		 str_frmt->params[6]);
+
+	trace_mlx5_fw(dev->tracer, trace_timestamp, str_frmt->lost,
+		      str_frmt->event_id, tmp);
+
+	/* remove it from hash */
+	mlx5_tracer_clean_message(str_frmt);
+}
+
+static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer,
+					   struct tracer_event *tracer_event)
+{
+	struct tracer_string_format *cur_string;
+
+	if (tracer_event->string_event.tdsn == 0) {
+		cur_string = mlx5_tracer_get_string(tracer, tracer_event);
+		if (!cur_string)
+			return -1;
+
+		cur_string->num_of_params = mlx5_tracer_get_num_of_params(cur_string->string);
+		cur_string->last_param_num = 0;
+		cur_string->event_id = tracer_event->event_id;
+		cur_string->tmsn = tracer_event->string_event.tmsn;
+		cur_string->timestamp = tracer_event->string_event.timestamp;
+		cur_string->lost = tracer_event->lost_event;
+		if (cur_string->num_of_params == 0) /* trace with no params */
+			list_add_tail(&cur_string->list, &tracer->ready_strings_list);
+	} else {
+		cur_string = mlx5_tracer_message_get(tracer, tracer_event);
+		if (!cur_string) {
+			pr_debug("%s Got string event for unknown string tdsm: %d\n",
+				 __func__, tracer_event->string_event.tmsn);
+			return -1;
+		}
+		cur_string->last_param_num += 1;
+		if (cur_string->last_param_num > TRACER_MAX_PARAMS) {
+			pr_debug("%s Number of params exceeds the max (%d)\n",
+				 __func__, TRACER_MAX_PARAMS);
+			list_add_tail(&cur_string->list, &tracer->ready_strings_list);
+			return 0;
+		}
+		/* keep the new parameter */
+		cur_string->params[cur_string->last_param_num - 1] =
+			tracer_event->string_event.string_param;
+		if (cur_string->last_param_num == cur_string->num_of_params)
+			list_add_tail(&cur_string->list, &tracer->ready_strings_list);
+	}
+
+	return 0;
+}
+
+static void mlx5_tracer_handle_timestamp_trace(struct mlx5_fw_tracer *tracer,
+					       struct tracer_event *tracer_event)
+{
+	struct tracer_timestamp_event timestamp_event =
+						tracer_event->timestamp_event;
+	struct tracer_string_format *str_frmt, *tmp_str;
+	struct mlx5_core_dev *dev = tracer->dev;
+	u64 trace_timestamp;
+
+	list_for_each_entry_safe(str_frmt, tmp_str, &tracer->ready_strings_list, list) {
+		list_del(&str_frmt->list);
+		if (str_frmt->timestamp < (timestamp_event.timestamp & MASK_6_0))
+			trace_timestamp = (timestamp_event.timestamp & MASK_52_7) |
+					  (str_frmt->timestamp & MASK_6_0);
+		else
+			trace_timestamp = ((timestamp_event.timestamp & MASK_52_7) - 1) |
+					  (str_frmt->timestamp & MASK_6_0);
+
+		mlx5_tracer_print_trace(str_frmt, dev, trace_timestamp);
+	}
+}
+
+static int mlx5_tracer_handle_trace(struct mlx5_fw_tracer *tracer,
+				    struct tracer_event *tracer_event)
+{
+	if (tracer_event->type == TRACER_EVENT_TYPE_STRING) {
+		mlx5_tracer_handle_string_trace(tracer, tracer_event);
+	} else if (tracer_event->type == TRACER_EVENT_TYPE_TIMESTAMP) {
+		if (!tracer_event->timestamp_event.unreliable)
+			mlx5_tracer_handle_timestamp_trace(tracer, tracer_event);
+	} else {
+		pr_debug("%s Got unrecognised type %d for parsing, exiting..\n",
+			 __func__, tracer_event->type);
+	}
+	return 0;
+}
+
+static void mlx5_fw_tracer_handle_traces(struct work_struct *work)
+{
+	struct mlx5_fw_tracer *tracer =
+			container_of(work, struct mlx5_fw_tracer, handle_traces_work);
+	u64 block_timestamp, last_block_timestamp, tmp_trace_block[TRACES_PER_BLOCK];
+	u32 block_count, start_offset, prev_start_offset, prev_consumer_index;
+	u32 trace_event_size = MLX5_ST_SZ_BYTES(tracer_event);
+	struct mlx5_core_dev *dev = tracer->dev;
+	struct tracer_event tracer_event;
+	int i;
+
+	mlx5_core_dbg(dev, "FWTracer: Handle Trace event, owner=(%d)\n", tracer->owner);
+	if (!tracer->owner)
+		return;
+
+	block_count = tracer->buff.size / TRACER_BLOCK_SIZE_BYTE;
+	start_offset = tracer->buff.consumer_index * TRACER_BLOCK_SIZE_BYTE;
+
+	/* Copy the block to local buffer to avoid HW override while being processed*/
+	memcpy(tmp_trace_block, tracer->buff.log_buf + start_offset,
+	       TRACER_BLOCK_SIZE_BYTE);
+
+	block_timestamp =
+		get_block_timestamp(tracer, &tmp_trace_block[TRACES_PER_BLOCK - 1]);
+
+	while (block_timestamp > tracer->last_timestamp) {
+		/* Check block override if its not the first block */
+		if (!tracer->last_timestamp) {
+			u64 *ts_event;
+			/* To avoid block override be the HW in case of buffer
+			 * wraparound, the time stamp of the previous block
+			 * should be compared to the last timestamp handled
+			 * by the driver.
+			 */
+			prev_consumer_index =
+				(tracer->buff.consumer_index - 1) & (block_count - 1);
+			prev_start_offset = prev_consumer_index * TRACER_BLOCK_SIZE_BYTE;
+
+			ts_event = tracer->buff.log_buf + prev_start_offset +
+				   (TRACES_PER_BLOCK - 1) * trace_event_size;
+			last_block_timestamp = get_block_timestamp(tracer, ts_event);
+			/* If previous timestamp different from last stored
+			 * timestamp then there is a good chance that the
+			 * current buffer is overwritten and therefore should
+			 * not be parsed.
+			 */
+			if (tracer->last_timestamp != last_block_timestamp) {
+				mlx5_core_warn(dev, "FWTracer: Events were lost\n");
+				tracer->last_timestamp = block_timestamp;
+				tracer->buff.consumer_index =
+					(tracer->buff.consumer_index + 1) & (block_count - 1);
+				break;
+			}
+		}
+
+		/* Parse events */
+		for (i = 0; i < TRACES_PER_BLOCK ; i++) {
+			poll_trace(tracer, &tracer_event, &tmp_trace_block[i]);
+			mlx5_tracer_handle_trace(tracer, &tracer_event);
+		}
+
+		tracer->buff.consumer_index =
+			(tracer->buff.consumer_index + 1) & (block_count - 1);
+
+		tracer->last_timestamp = block_timestamp;
+		start_offset = tracer->buff.consumer_index * TRACER_BLOCK_SIZE_BYTE;
+		memcpy(tmp_trace_block, tracer->buff.log_buf + start_offset,
+		       TRACER_BLOCK_SIZE_BYTE);
+		block_timestamp = get_block_timestamp(tracer,
+						      &tmp_trace_block[TRACES_PER_BLOCK - 1]);
+	}
+
+	mlx5_fw_tracer_arm(dev);
+}
+
+static int mlx5_fw_tracer_set_mtrc_conf(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 out[MLX5_ST_SZ_DW(mtrc_conf)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mtrc_conf)] = {0};
+	int err;
+
+	MLX5_SET(mtrc_conf, in, trace_mode, TRACE_TO_MEMORY);
+	MLX5_SET(mtrc_conf, in, log_trace_buffer_size,
+		 ilog2(TRACER_BUFFER_PAGE_NUM));
+	MLX5_SET(mtrc_conf, in, trace_mkey, tracer->buff.mkey.key);
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
+				   MLX5_REG_MTRC_CONF, 0, 1);
+	if (err)
+		mlx5_core_warn(dev, "FWTracer: Failed to set tracer configurations %d\n", err);
+
+	return err;
+}
+
+static int mlx5_fw_tracer_set_mtrc_ctrl(struct mlx5_fw_tracer *tracer, u8 status, u8 arm)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 out[MLX5_ST_SZ_DW(mtrc_ctrl)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mtrc_ctrl)] = {0};
+	int err;
+
+	MLX5_SET(mtrc_ctrl, in, modify_field_select, TRACE_STATUS);
+	MLX5_SET(mtrc_ctrl, in, trace_status, status);
+	MLX5_SET(mtrc_ctrl, in, arm_event, arm);
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
+				   MLX5_REG_MTRC_CTRL, 0, 1);
+
+	if (!err && status)
+		tracer->last_timestamp = 0;
+
+	return err;
+}
+
+static int mlx5_fw_tracer_start(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	int err;
+
+	err = mlx5_fw_tracer_ownership_acquire(tracer);
+	if (err) {
+		mlx5_core_dbg(dev, "FWTracer: Ownership was not granted %d\n", err);
+		/* Don't fail since ownership can be acquired on a later FW event */
+		return 0;
+	}
+
+	err = mlx5_fw_tracer_set_mtrc_conf(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Failed to set tracer configuration %d\n", err);
+		goto release_ownership;
+	}
+
+	/* enable tracer & trace events */
+	err = mlx5_fw_tracer_set_mtrc_ctrl(tracer, 1, 1);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Failed to enable tracer %d\n", err);
+		goto release_ownership;
+	}
+
+	mlx5_core_dbg(dev, "FWTracer: Ownership granted and active\n");
+	return 0;
+
+release_ownership:
+	mlx5_fw_tracer_ownership_release(tracer);
+	return err;
+}
+
+static void mlx5_fw_tracer_ownership_change(struct work_struct *work)
+{
+	struct mlx5_fw_tracer *tracer =
+		container_of(work, struct mlx5_fw_tracer, ownership_change_work);
+
+	mlx5_core_dbg(tracer->dev, "FWTracer: ownership changed, current=(%d)\n", tracer->owner);
+	if (tracer->owner) {
+		tracer->owner = false;
+		tracer->buff.consumer_index = 0;
+		return;
+	}
+
+	mlx5_fw_tracer_start(tracer);
+}
+
+/* Create software resources (Buffers, etc ..) */
+struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_tracer *tracer = NULL;
+	int err;
+
+	if (!MLX5_CAP_MCAM_REG(dev, tracer_registers)) {
+		mlx5_core_dbg(dev, "FWTracer: Tracer capability not present\n");
+		return NULL;
+	}
+
+	tracer = kzalloc(sizeof(*tracer), GFP_KERNEL);
+	if (!tracer)
+		return ERR_PTR(-ENOMEM);
+
+	tracer->work_queue = create_singlethread_workqueue("mlx5_fw_tracer");
+	if (!tracer->work_queue) {
+		err = -ENOMEM;
+		goto free_tracer;
+	}
+
+	tracer->dev = dev;
+
+	INIT_LIST_HEAD(&tracer->ready_strings_list);
+	INIT_WORK(&tracer->ownership_change_work, mlx5_fw_tracer_ownership_change);
+	INIT_WORK(&tracer->read_fw_strings_work, mlx5_tracer_read_strings_db);
+	INIT_WORK(&tracer->handle_traces_work, mlx5_fw_tracer_handle_traces);
+
+
+	err = mlx5_query_mtrc_caps(tracer);
+	if (err) {
+		mlx5_core_dbg(dev, "FWTracer: Failed to query capabilities %d\n", err);
+		goto destroy_workqueue;
+	}
+
+	err = mlx5_fw_tracer_create_log_buf(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Create log buffer failed %d\n", err);
+		goto destroy_workqueue;
+	}
+
+	err = mlx5_fw_tracer_allocate_strings_db(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Allocate strings database failed %d\n", err);
+		goto free_log_buf;
+	}
+
+	mlx5_core_dbg(dev, "FWTracer: Tracer created\n");
+
+	return tracer;
+
+free_log_buf:
+	mlx5_fw_tracer_destroy_log_buf(tracer);
+destroy_workqueue:
+	tracer->dev = NULL;
+	destroy_workqueue(tracer->work_queue);
+free_tracer:
+	kfree(tracer);
+	return ERR_PTR(err);
+}
+
+/* Create HW resources + start tracer
+ * must be called before Async EQ is created
+ */
+int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev;
+	int err;
+
+	if (IS_ERR_OR_NULL(tracer))
+		return 0;
+
+	dev = tracer->dev;
+
+	if (!tracer->str_db.loaded)
+		queue_work(tracer->work_queue, &tracer->read_fw_strings_work);
+
+	err = mlx5_core_alloc_pd(dev, &tracer->buff.pdn);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Failed to allocate PD %d\n", err);
+		return err;
+	}
+
+	err = mlx5_fw_tracer_create_mkey(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Failed to create mkey %d\n", err);
+		goto err_dealloc_pd;
+	}
+
+	mlx5_fw_tracer_start(tracer);
+
+	return 0;
+
+err_dealloc_pd:
+	mlx5_core_dealloc_pd(dev, tracer->buff.pdn);
+	return err;
+}
+
+/* Stop tracer + Cleanup HW resources
+ * must be called after Async EQ is destroyed
+ */
+void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
+{
+	if (IS_ERR_OR_NULL(tracer))
+		return;
+
+	mlx5_core_dbg(tracer->dev, "FWTracer: Cleanup, is owner ? (%d)\n",
+		      tracer->owner);
+
+	cancel_work_sync(&tracer->ownership_change_work);
+	cancel_work_sync(&tracer->handle_traces_work);
+
+	if (tracer->owner)
+		mlx5_fw_tracer_ownership_release(tracer);
+
+	mlx5_core_destroy_mkey(tracer->dev, &tracer->buff.mkey);
+	mlx5_core_dealloc_pd(tracer->dev, tracer->buff.pdn);
+}
+
+/* Free software resources (Buffers, etc ..) */
+void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
+{
+	if (IS_ERR_OR_NULL(tracer))
+		return;
+
+	mlx5_core_dbg(tracer->dev, "FWTracer: Destroy\n");
+
+	cancel_work_sync(&tracer->read_fw_strings_work);
+	mlx5_fw_tracer_clean_ready_list(tracer);
+	mlx5_fw_tracer_clean_print_hash(tracer);
+	mlx5_fw_tracer_free_strings_db(tracer);
+	mlx5_fw_tracer_destroy_log_buf(tracer);
+	flush_workqueue(tracer->work_queue);
+	destroy_workqueue(tracer->work_queue);
+	kfree(tracer);
+}
+
+void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
+{
+	struct mlx5_fw_tracer *tracer = dev->tracer;
+
+	if (!tracer)
+		return;
+
+	switch (eqe->sub_type) {
+	case MLX5_TRACER_SUBTYPE_OWNERSHIP_CHANGE:
+		if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state))
+			queue_work(tracer->work_queue, &tracer->ownership_change_work);
+		break;
+	case MLX5_TRACER_SUBTYPE_TRACES_AVAILABLE:
+		if (likely(tracer->str_db.loaded))
+			queue_work(tracer->work_queue, &tracer->handle_traces_work);
+		break;
+	default:
+		mlx5_core_dbg(dev, "FWTracer: Event with unrecognized subtype: sub_type %d\n",
+			      eqe->sub_type);
+	}
+}
+
+EXPORT_TRACEPOINT_SYMBOL(mlx5_fw);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
new file mode 100644
index 000000000000..0347f2dd5cee
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
@@ -0,0 +1,175 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef __LIB_TRACER_H__
+#define __LIB_TRACER_H__
+
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+
+#define STRINGS_DB_SECTIONS_NUM 8
+#define STRINGS_DB_READ_SIZE_BYTES 256
+#define STRINGS_DB_LEFTOVER_SIZE_BYTES 64
+#define TRACER_BUFFER_PAGE_NUM 64
+#define TRACER_BUFFER_CHUNK 4096
+#define TRACE_BUFFER_SIZE_BYTE (TRACER_BUFFER_PAGE_NUM * TRACER_BUFFER_CHUNK)
+
+#define TRACER_BLOCK_SIZE_BYTE 256
+#define TRACES_PER_BLOCK 32
+
+#define TRACER_MAX_PARAMS 7
+#define MESSAGE_HASH_BITS 6
+#define MESSAGE_HASH_SIZE BIT(MESSAGE_HASH_BITS)
+
+#define MASK_52_7 (0x1FFFFFFFFFFF80)
+#define MASK_6_0  (0x7F)
+
+struct mlx5_fw_tracer {
+	struct mlx5_core_dev *dev;
+	bool owner;
+	u8   trc_ver;
+	struct workqueue_struct *work_queue;
+	struct work_struct ownership_change_work;
+	struct work_struct read_fw_strings_work;
+
+	/* Strings DB */
+	struct {
+		u8 first_string_trace;
+		u8 num_string_trace;
+		u32 num_string_db;
+		u32 base_address_out[STRINGS_DB_SECTIONS_NUM];
+		u32 size_out[STRINGS_DB_SECTIONS_NUM];
+		void *buffer[STRINGS_DB_SECTIONS_NUM];
+		bool loaded;
+	} str_db;
+
+	/* Log Buffer */
+	struct {
+		u32 pdn;
+		void *log_buf;
+		dma_addr_t dma;
+		u32 size;
+		struct mlx5_core_mkey mkey;
+		u32 consumer_index;
+	} buff;
+
+	u64 last_timestamp;
+	struct work_struct handle_traces_work;
+	struct hlist_head hash[MESSAGE_HASH_SIZE];
+	struct list_head ready_strings_list;
+};
+
+struct tracer_string_format {
+	char *string;
+	int params[TRACER_MAX_PARAMS];
+	int num_of_params;
+	int last_param_num;
+	u8 event_id;
+	u32 tmsn;
+	struct hlist_node hlist;
+	struct list_head list;
+	u32 timestamp;
+	bool lost;
+};
+
+enum mlx5_fw_tracer_ownership_state {
+	MLX5_FW_TRACER_RELEASE_OWNERSHIP,
+	MLX5_FW_TRACER_ACQUIRE_OWNERSHIP,
+};
+
+enum tracer_ctrl_fields_select {
+	TRACE_STATUS = 1 << 0,
+};
+
+enum tracer_event_type {
+	TRACER_EVENT_TYPE_STRING,
+	TRACER_EVENT_TYPE_TIMESTAMP = 0xFF,
+	TRACER_EVENT_TYPE_UNRECOGNIZED,
+};
+
+enum tracing_mode {
+	TRACE_TO_MEMORY = 1 << 0,
+};
+
+struct tracer_timestamp_event {
+	u64        timestamp;
+	u8         unreliable;
+};
+
+struct tracer_string_event {
+	u32        timestamp;
+	u32        tmsn;
+	u32        tdsn;
+	u32        string_param;
+};
+
+struct tracer_event {
+	bool      lost_event;
+	u32       type;
+	u8        event_id;
+	union {
+		struct tracer_string_event string_event;
+		struct tracer_timestamp_event timestamp_event;
+	};
+};
+
+struct mlx5_ifc_tracer_event_bits {
+	u8         lost[0x1];
+	u8         timestamp[0x7];
+	u8         event_id[0x8];
+	u8         event_data[0x30];
+};
+
+struct mlx5_ifc_tracer_string_event_bits {
+	u8         lost[0x1];
+	u8         timestamp[0x7];
+	u8         event_id[0x8];
+	u8         tmsn[0xd];
+	u8         tdsn[0x3];
+	u8         string_param[0x20];
+};
+
+struct mlx5_ifc_tracer_timestamp_event_bits {
+	u8         timestamp7_0[0x8];
+	u8         event_id[0x8];
+	u8         urts[0x3];
+	u8         timestamp52_40[0xd];
+	u8         timestamp39_8[0x20];
+};
+
+struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev);
+int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer);
+void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer);
+void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer);
+void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h
new file mode 100644
index 000000000000..83f90e9aff45
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h
@@ -0,0 +1,78 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#if !defined(__LIB_TRACER_TRACEPOINT_H__) || defined(TRACE_HEADER_MULTI_READ)
+#define __LIB_TRACER_TRACEPOINT_H__
+
+#include <linux/tracepoint.h>
+#include "fw_tracer.h"
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mlx5
+
+/* Tracepoint for FWTracer messages: */
+TRACE_EVENT(mlx5_fw,
+	TP_PROTO(const struct mlx5_fw_tracer *tracer, u64 trace_timestamp,
+		 bool lost, u8 event_id, const char *msg),
+
+	TP_ARGS(tracer, trace_timestamp, lost, event_id, msg),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name(&tracer->dev->pdev->dev))
+		__field(u64, trace_timestamp)
+		__field(bool, lost)
+		__field(u8, event_id)
+		__string(msg, msg)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name(&tracer->dev->pdev->dev));
+		__entry->trace_timestamp = trace_timestamp;
+		__entry->lost = lost;
+		__entry->event_id = event_id;
+		__assign_str(msg, msg);
+	),
+
+	TP_printk("%s [0x%llx] %d [0x%x] %s",
+		  __get_str(dev_name),
+		  __entry->trace_timestamp,
+		  __entry->lost, __entry->event_id,
+		  __get_str(msg))
+);
+
+#endif
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH ./diag
+#define TRACE_INCLUDE_FILE fw_tracer_tracepoint
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 405236cf0b04..db2cfcd21d43 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -52,6 +52,7 @@
 #include "wq.h"
 #include "mlx5_core.h"
 #include "en_stats.h"
+#include "en/fs.h"
 
 struct page_pool;
 
@@ -137,7 +138,6 @@ struct page_pool;
 #define MLX5E_MAX_NUM_CHANNELS         (MLX5E_INDIR_RQT_SIZE >> 1)
 #define MLX5E_MAX_NUM_SQS              (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC)
 #define MLX5E_TX_CQ_POLL_BUDGET        128
-#define MLX5E_UPDATE_STATS_INTERVAL    200 /* msecs */
 #define MLX5E_SQ_RECOVER_MIN_INTERVAL  500 /* msecs */
 
 #define MLX5E_UMR_WQE_INLINE_SZ \
@@ -148,10 +148,6 @@ struct page_pool;
 	(DIV_ROUND_UP(MLX5E_UMR_WQE_INLINE_SZ, MLX5_SEND_WQE_BB))
 #define MLX5E_ICOSQ_MAX_WQEBBS MLX5E_UMR_WQEBBS
 
-#define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
-#define MLX5E_XDP_TX_DS_COUNT \
-	((sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) + 1 /* SG DS */)
-
 #define MLX5E_NUM_MAIN_GROUPS 9
 
 #define MLX5E_MSG_LEVEL			NETIF_MSG_LINK
@@ -349,6 +345,7 @@ enum {
 	MLX5E_SQ_STATE_IPSEC,
 	MLX5E_SQ_STATE_AM,
 	MLX5E_SQ_STATE_TLS,
+	MLX5E_SQ_STATE_REDIRECT,
 };
 
 struct mlx5e_sq_wqe_info {
@@ -369,16 +366,14 @@ struct mlx5e_txqsq {
 
 	struct mlx5e_cq            cq;
 
-	/* write@xmit, read@completion */
-	struct {
-		struct mlx5e_sq_dma       *dma_fifo;
-		struct mlx5e_tx_wqe_info  *wqe_info;
-	} db;
-
 	/* read only */
 	struct mlx5_wq_cyc         wq;
 	u32                        dma_fifo_mask;
 	struct mlx5e_sq_stats     *stats;
+	struct {
+		struct mlx5e_sq_dma       *dma_fifo;
+		struct mlx5e_tx_wqe_info  *wqe_info;
+	} db;
 	void __iomem              *uar_map;
 	struct netdev_queue       *txq;
 	u32                        sqn;
@@ -400,30 +395,43 @@ struct mlx5e_txqsq {
 	} recover;
 } ____cacheline_aligned_in_smp;
 
+struct mlx5e_dma_info {
+	struct page     *page;
+	dma_addr_t      addr;
+};
+
+struct mlx5e_xdp_info {
+	struct xdp_frame      *xdpf;
+	dma_addr_t            dma_addr;
+	struct mlx5e_dma_info di;
+};
+
 struct mlx5e_xdpsq {
 	/* data path */
 
-	/* dirtied @rx completion */
+	/* dirtied @completion */
 	u16                        cc;
-	u16                        pc;
+	bool                       redirect_flush;
 
-	struct mlx5e_cq            cq;
+	/* dirtied @xmit */
+	u16                        pc ____cacheline_aligned_in_smp;
+	bool                       doorbell;
 
-	/* write@xmit, read@completion */
-	struct {
-		struct mlx5e_dma_info     *di;
-		bool                       doorbell;
-		bool                       redirect_flush;
-	} db;
+	struct mlx5e_cq            cq;
 
 	/* read only */
 	struct mlx5_wq_cyc         wq;
+	struct mlx5e_xdpsq_stats  *stats;
+	struct {
+		struct mlx5e_xdp_info     *xdpi;
+	} db;
 	void __iomem              *uar_map;
 	u32                        sqn;
 	struct device             *pdev;
 	__be32                     mkey_be;
 	u8                         min_inline_mode;
 	unsigned long              state;
+	unsigned int               hw_mtu;
 
 	/* control path */
 	struct mlx5_wq_ctrl        wq_ctrl;
@@ -460,11 +468,6 @@ mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n)
 	return (mlx5_wq_cyc_ctr2ix(wq, cc - pc) >= n) || (cc == pc);
 }
 
-struct mlx5e_dma_info {
-	struct page	*page;
-	dma_addr_t	addr;
-};
-
 struct mlx5e_wqe_frag_info {
 	struct mlx5e_dma_info *di;
 	u32 offset;
@@ -567,7 +570,6 @@ struct mlx5e_rq {
 
 	/* XDP */
 	struct bpf_prog       *xdp_prog;
-	unsigned int           hw_mtu;
 	struct mlx5e_xdpsq     xdpsq;
 	DECLARE_BITMAP(flags, 8);
 	struct page_pool      *page_pool;
@@ -596,6 +598,9 @@ struct mlx5e_channel {
 	__be32                     mkey_be;
 	u8                         num_tc;
 
+	/* XDP_REDIRECT */
+	struct mlx5e_xdpsq         xdpsq;
+
 	/* data path - accessed per napi poll */
 	struct irq_desc *irq_desc;
 	struct mlx5e_ch_stats     *stats;
@@ -618,159 +623,16 @@ struct mlx5e_channel_stats {
 	struct mlx5e_ch_stats ch;
 	struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC];
 	struct mlx5e_rq_stats rq;
+	struct mlx5e_xdpsq_stats rq_xdpsq;
+	struct mlx5e_xdpsq_stats xdpsq;
 } ____cacheline_aligned_in_smp;
 
-enum mlx5e_traffic_types {
-	MLX5E_TT_IPV4_TCP,
-	MLX5E_TT_IPV6_TCP,
-	MLX5E_TT_IPV4_UDP,
-	MLX5E_TT_IPV6_UDP,
-	MLX5E_TT_IPV4_IPSEC_AH,
-	MLX5E_TT_IPV6_IPSEC_AH,
-	MLX5E_TT_IPV4_IPSEC_ESP,
-	MLX5E_TT_IPV6_IPSEC_ESP,
-	MLX5E_TT_IPV4,
-	MLX5E_TT_IPV6,
-	MLX5E_TT_ANY,
-	MLX5E_NUM_TT,
-	MLX5E_NUM_INDIR_TIRS = MLX5E_TT_ANY,
-};
-
-enum mlx5e_tunnel_types {
-	MLX5E_TT_IPV4_GRE,
-	MLX5E_TT_IPV6_GRE,
-	MLX5E_NUM_TUNNEL_TT,
-};
-
 enum {
 	MLX5E_STATE_ASYNC_EVENTS_ENABLED,
 	MLX5E_STATE_OPENED,
 	MLX5E_STATE_DESTROYING,
 };
 
-struct mlx5e_vxlan_db {
-	spinlock_t			lock; /* protect vxlan table */
-	struct radix_tree_root		tree;
-};
-
-struct mlx5e_l2_rule {
-	u8  addr[ETH_ALEN + 2];
-	struct mlx5_flow_handle *rule;
-};
-
-struct mlx5e_flow_table {
-	int num_groups;
-	struct mlx5_flow_table *t;
-	struct mlx5_flow_group **g;
-};
-
-#define MLX5E_L2_ADDR_HASH_SIZE BIT(BITS_PER_BYTE)
-
-struct mlx5e_tc_table {
-	struct mlx5_flow_table		*t;
-
-	struct rhashtable               ht;
-
-	DECLARE_HASHTABLE(mod_hdr_tbl, 8);
-	DECLARE_HASHTABLE(hairpin_tbl, 8);
-};
-
-struct mlx5e_vlan_table {
-	struct mlx5e_flow_table		ft;
-	DECLARE_BITMAP(active_cvlans, VLAN_N_VID);
-	DECLARE_BITMAP(active_svlans, VLAN_N_VID);
-	struct mlx5_flow_handle	*active_cvlans_rule[VLAN_N_VID];
-	struct mlx5_flow_handle	*active_svlans_rule[VLAN_N_VID];
-	struct mlx5_flow_handle	*untagged_rule;
-	struct mlx5_flow_handle	*any_cvlan_rule;
-	struct mlx5_flow_handle	*any_svlan_rule;
-	bool			cvlan_filter_disabled;
-};
-
-struct mlx5e_l2_table {
-	struct mlx5e_flow_table    ft;
-	struct hlist_head          netdev_uc[MLX5E_L2_ADDR_HASH_SIZE];
-	struct hlist_head          netdev_mc[MLX5E_L2_ADDR_HASH_SIZE];
-	struct mlx5e_l2_rule	   broadcast;
-	struct mlx5e_l2_rule	   allmulti;
-	struct mlx5e_l2_rule	   promisc;
-	bool                       broadcast_enabled;
-	bool                       allmulti_enabled;
-	bool                       promisc_enabled;
-};
-
-/* L3/L4 traffic type classifier */
-struct mlx5e_ttc_table {
-	struct mlx5e_flow_table  ft;
-	struct mlx5_flow_handle	 *rules[MLX5E_NUM_TT];
-	struct mlx5_flow_handle  *tunnel_rules[MLX5E_NUM_TUNNEL_TT];
-};
-
-#define ARFS_HASH_SHIFT BITS_PER_BYTE
-#define ARFS_HASH_SIZE BIT(BITS_PER_BYTE)
-struct arfs_table {
-	struct mlx5e_flow_table  ft;
-	struct mlx5_flow_handle	 *default_rule;
-	struct hlist_head	 rules_hash[ARFS_HASH_SIZE];
-};
-
-enum  arfs_type {
-	ARFS_IPV4_TCP,
-	ARFS_IPV6_TCP,
-	ARFS_IPV4_UDP,
-	ARFS_IPV6_UDP,
-	ARFS_NUM_TYPES,
-};
-
-struct mlx5e_arfs_tables {
-	struct arfs_table arfs_tables[ARFS_NUM_TYPES];
-	/* Protect aRFS rules list */
-	spinlock_t                     arfs_lock;
-	struct list_head               rules;
-	int                            last_filter_id;
-	struct workqueue_struct        *wq;
-};
-
-/* NIC prio FTS */
-enum {
-	MLX5E_VLAN_FT_LEVEL = 0,
-	MLX5E_L2_FT_LEVEL,
-	MLX5E_TTC_FT_LEVEL,
-	MLX5E_INNER_TTC_FT_LEVEL,
-	MLX5E_ARFS_FT_LEVEL
-};
-
-enum {
-	MLX5E_TC_FT_LEVEL = 0,
-	MLX5E_TC_TTC_FT_LEVEL,
-};
-
-struct mlx5e_ethtool_table {
-	struct mlx5_flow_table *ft;
-	int                    num_rules;
-};
-
-#define ETHTOOL_NUM_L3_L4_FTS 7
-#define ETHTOOL_NUM_L2_FTS 4
-
-struct mlx5e_ethtool_steering {
-	struct mlx5e_ethtool_table      l3_l4_ft[ETHTOOL_NUM_L3_L4_FTS];
-	struct mlx5e_ethtool_table      l2_ft[ETHTOOL_NUM_L2_FTS];
-	struct list_head                rules;
-	int                             tot_num_rules;
-};
-
-struct mlx5e_flow_steering {
-	struct mlx5_flow_namespace      *ns;
-	struct mlx5e_ethtool_steering   ethtool;
-	struct mlx5e_tc_table           tc;
-	struct mlx5e_vlan_table         vlan;
-	struct mlx5e_l2_table           l2;
-	struct mlx5e_ttc_table          ttc;
-	struct mlx5e_ttc_table          inner_ttc;
-	struct mlx5e_arfs_tables        arfs;
-};
-
 struct mlx5e_rqt {
 	u32              rqtn;
 	bool		 enabled;
@@ -810,7 +672,6 @@ struct mlx5e_priv {
 	u32                        tx_rates[MLX5E_MAX_NUM_SQS];
 
 	struct mlx5e_flow_steering fs;
-	struct mlx5e_vxlan_db      vxlan;
 
 	struct workqueue_struct    *wq;
 	struct work_struct         update_carrier_work;
@@ -864,7 +725,8 @@ struct mlx5e_profile {
 void mlx5e_build_ptys2ethtool_map(void);
 
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv, select_queue_fallback_t fallback);
+		       struct net_device *sb_dev,
+		       select_queue_fallback_t fallback);
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
 netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 			  struct mlx5e_tx_wqe *wqe, u16 pi);
@@ -874,14 +736,13 @@ void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
 int mlx5e_napi_poll(struct napi_struct *napi, int budget);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
-bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
 void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq);
-void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq);
 
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev);
 bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev,
 				struct mlx5e_params *params);
 
+void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info);
 void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
 			bool recycle);
 void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
@@ -890,7 +751,6 @@ bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
 bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq);
 void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
-void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi);
 struct sk_buff *
 mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 				u16 cqe_bcnt, u32 head_offset, u32 page_idx);
@@ -906,23 +766,10 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 
 void mlx5e_update_stats(struct mlx5e_priv *priv);
 
-int mlx5e_create_flow_steering(struct mlx5e_priv *priv);
-void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv);
 void mlx5e_init_l2_addr(struct mlx5e_priv *priv);
-void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft);
 int mlx5e_self_test_num(struct mlx5e_priv *priv);
 void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest,
 		     u64 *buf);
-int mlx5e_ethtool_get_flow(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
-			   int location);
-int mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv,
-				struct ethtool_rxnfc *info, u32 *rule_locs);
-int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
-			       struct ethtool_rx_flow_spec *fs);
-int mlx5e_ethtool_flow_remove(struct mlx5e_priv *priv,
-			      int location);
-void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv);
-void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv);
 void mlx5e_set_rx_mode_work(struct work_struct *work);
 
 int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr);
@@ -933,8 +780,6 @@ int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto,
 			  u16 vid);
 int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto,
 			   u16 vid);
-void mlx5e_enable_cvlan_filter(struct mlx5e_priv *priv);
-void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv);
 void mlx5e_timestamp_init(struct mlx5e_priv *priv);
 
 struct mlx5e_redirect_rqt_param {
@@ -1051,32 +896,6 @@ void mlx5e_dcbnl_init_app(struct mlx5e_priv *priv);
 void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv);
 #endif
 
-#ifndef CONFIG_RFS_ACCEL
-static inline int mlx5e_arfs_create_tables(struct mlx5e_priv *priv)
-{
-	return 0;
-}
-
-static inline void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv) {}
-
-static inline int mlx5e_arfs_enable(struct mlx5e_priv *priv)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int mlx5e_arfs_disable(struct mlx5e_priv *priv)
-{
-	return -EOPNOTSUPP;
-}
-#else
-int mlx5e_arfs_create_tables(struct mlx5e_priv *priv);
-void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv);
-int mlx5e_arfs_enable(struct mlx5e_priv *priv);
-int mlx5e_arfs_disable(struct mlx5e_priv *priv);
-int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
-			u16 rxq_index, u32 flow_id);
-#endif
-
 int mlx5e_create_tir(struct mlx5_core_dev *mdev,
 		     struct mlx5e_tir *tir, u32 *in, int inlen);
 void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
@@ -1097,27 +916,6 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv);
 void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv);
 void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
 
-struct ttc_params {
-	struct mlx5_flow_table_attr ft_attr;
-	u32 any_tt_tirn;
-	u32 indir_tirn[MLX5E_NUM_INDIR_TIRS];
-	struct mlx5e_ttc_table *inner_ttc;
-};
-
-void mlx5e_set_ttc_basic_params(struct mlx5e_priv *priv, struct ttc_params *ttc_params);
-void mlx5e_set_ttc_ft_params(struct ttc_params *ttc_params);
-void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params);
-
-int mlx5e_create_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
-			   struct mlx5e_ttc_table *ttc);
-void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv,
-			     struct mlx5e_ttc_table *ttc);
-
-int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
-				 struct mlx5e_ttc_table *ttc);
-void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv,
-				   struct mlx5e_ttc_table *ttc);
-
 int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
 		     u32 underlay_qpn, u32 *tisn);
 void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
new file mode 100644
index 000000000000..bbf69e859b78
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -0,0 +1,210 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#ifndef __MLX5E_FLOW_STEER_H__
+#define __MLX5E_FLOW_STEER_H__
+
+enum {
+	MLX5E_TC_FT_LEVEL = 0,
+	MLX5E_TC_TTC_FT_LEVEL,
+};
+
+struct mlx5e_tc_table {
+	struct mlx5_flow_table		*t;
+
+	struct rhashtable               ht;
+
+	DECLARE_HASHTABLE(mod_hdr_tbl, 8);
+	DECLARE_HASHTABLE(hairpin_tbl, 8);
+};
+
+struct mlx5e_flow_table {
+	int num_groups;
+	struct mlx5_flow_table *t;
+	struct mlx5_flow_group **g;
+};
+
+struct mlx5e_l2_rule {
+	u8  addr[ETH_ALEN + 2];
+	struct mlx5_flow_handle *rule;
+};
+
+#define MLX5E_L2_ADDR_HASH_SIZE BIT(BITS_PER_BYTE)
+
+struct mlx5e_vlan_table {
+	struct mlx5e_flow_table		ft;
+	DECLARE_BITMAP(active_cvlans, VLAN_N_VID);
+	DECLARE_BITMAP(active_svlans, VLAN_N_VID);
+	struct mlx5_flow_handle	*active_cvlans_rule[VLAN_N_VID];
+	struct mlx5_flow_handle	*active_svlans_rule[VLAN_N_VID];
+	struct mlx5_flow_handle	*untagged_rule;
+	struct mlx5_flow_handle	*any_cvlan_rule;
+	struct mlx5_flow_handle	*any_svlan_rule;
+	bool			cvlan_filter_disabled;
+};
+
+struct mlx5e_l2_table {
+	struct mlx5e_flow_table    ft;
+	struct hlist_head          netdev_uc[MLX5E_L2_ADDR_HASH_SIZE];
+	struct hlist_head          netdev_mc[MLX5E_L2_ADDR_HASH_SIZE];
+	struct mlx5e_l2_rule	   broadcast;
+	struct mlx5e_l2_rule	   allmulti;
+	struct mlx5e_l2_rule	   promisc;
+	bool                       broadcast_enabled;
+	bool                       allmulti_enabled;
+	bool                       promisc_enabled;
+};
+
+enum mlx5e_traffic_types {
+	MLX5E_TT_IPV4_TCP,
+	MLX5E_TT_IPV6_TCP,
+	MLX5E_TT_IPV4_UDP,
+	MLX5E_TT_IPV6_UDP,
+	MLX5E_TT_IPV4_IPSEC_AH,
+	MLX5E_TT_IPV6_IPSEC_AH,
+	MLX5E_TT_IPV4_IPSEC_ESP,
+	MLX5E_TT_IPV6_IPSEC_ESP,
+	MLX5E_TT_IPV4,
+	MLX5E_TT_IPV6,
+	MLX5E_TT_ANY,
+	MLX5E_NUM_TT,
+	MLX5E_NUM_INDIR_TIRS = MLX5E_TT_ANY,
+};
+
+enum mlx5e_tunnel_types {
+	MLX5E_TT_IPV4_GRE,
+	MLX5E_TT_IPV6_GRE,
+	MLX5E_NUM_TUNNEL_TT,
+};
+
+/* L3/L4 traffic type classifier */
+struct mlx5e_ttc_table {
+	struct mlx5e_flow_table  ft;
+	struct mlx5_flow_handle	 *rules[MLX5E_NUM_TT];
+	struct mlx5_flow_handle  *tunnel_rules[MLX5E_NUM_TUNNEL_TT];
+};
+
+/* NIC prio FTS */
+enum {
+	MLX5E_VLAN_FT_LEVEL = 0,
+	MLX5E_L2_FT_LEVEL,
+	MLX5E_TTC_FT_LEVEL,
+	MLX5E_INNER_TTC_FT_LEVEL,
+#ifdef CONFIG_MLX5_EN_ARFS
+	MLX5E_ARFS_FT_LEVEL
+#endif
+};
+
+#ifdef CONFIG_MLX5_EN_RXNFC
+
+struct mlx5e_ethtool_table {
+	struct mlx5_flow_table *ft;
+	int                    num_rules;
+};
+
+#define ETHTOOL_NUM_L3_L4_FTS 7
+#define ETHTOOL_NUM_L2_FTS 4
+
+struct mlx5e_ethtool_steering {
+	struct mlx5e_ethtool_table      l3_l4_ft[ETHTOOL_NUM_L3_L4_FTS];
+	struct mlx5e_ethtool_table      l2_ft[ETHTOOL_NUM_L2_FTS];
+	struct list_head                rules;
+	int                             tot_num_rules;
+};
+
+void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv);
+void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv);
+int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd);
+int mlx5e_get_rxnfc(struct net_device *dev,
+		    struct ethtool_rxnfc *info, u32 *rule_locs);
+#else
+static inline void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv)    { }
+static inline void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv) { }
+#endif /* CONFIG_MLX5_EN_RXNFC */
+
+#ifdef CONFIG_MLX5_EN_ARFS
+#define ARFS_HASH_SHIFT BITS_PER_BYTE
+#define ARFS_HASH_SIZE BIT(BITS_PER_BYTE)
+
+struct arfs_table {
+	struct mlx5e_flow_table  ft;
+	struct mlx5_flow_handle	 *default_rule;
+	struct hlist_head	 rules_hash[ARFS_HASH_SIZE];
+};
+
+enum  arfs_type {
+	ARFS_IPV4_TCP,
+	ARFS_IPV6_TCP,
+	ARFS_IPV4_UDP,
+	ARFS_IPV6_UDP,
+	ARFS_NUM_TYPES,
+};
+
+struct mlx5e_arfs_tables {
+	struct arfs_table arfs_tables[ARFS_NUM_TYPES];
+	/* Protect aRFS rules list */
+	spinlock_t                     arfs_lock;
+	struct list_head               rules;
+	int                            last_filter_id;
+	struct workqueue_struct        *wq;
+};
+
+int mlx5e_arfs_create_tables(struct mlx5e_priv *priv);
+void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv);
+int mlx5e_arfs_enable(struct mlx5e_priv *priv);
+int mlx5e_arfs_disable(struct mlx5e_priv *priv);
+int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
+			u16 rxq_index, u32 flow_id);
+#else
+static inline int mlx5e_arfs_create_tables(struct mlx5e_priv *priv) { return 0; }
+static inline void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv) {}
+static inline int mlx5e_arfs_enable(struct mlx5e_priv *priv) { return -EOPNOTSUPP; }
+static inline int mlx5e_arfs_disable(struct mlx5e_priv *priv) {	return -EOPNOTSUPP; }
+#endif
+
+struct mlx5e_flow_steering {
+	struct mlx5_flow_namespace      *ns;
+#ifdef CONFIG_MLX5_EN_RXNFC
+	struct mlx5e_ethtool_steering   ethtool;
+#endif
+	struct mlx5e_tc_table           tc;
+	struct mlx5e_vlan_table         vlan;
+	struct mlx5e_l2_table           l2;
+	struct mlx5e_ttc_table          ttc;
+	struct mlx5e_ttc_table          inner_ttc;
+#ifdef CONFIG_MLX5_EN_ARFS
+	struct mlx5e_arfs_tables        arfs;
+#endif
+};
+
+struct ttc_params {
+	struct mlx5_flow_table_attr ft_attr;
+	u32 any_tt_tirn;
+	u32 indir_tirn[MLX5E_NUM_INDIR_TIRS];
+	struct mlx5e_ttc_table *inner_ttc;
+};
+
+void mlx5e_set_ttc_basic_params(struct mlx5e_priv *priv, struct ttc_params *ttc_params);
+void mlx5e_set_ttc_ft_params(struct ttc_params *ttc_params);
+void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params);
+
+int mlx5e_create_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
+			   struct mlx5e_ttc_table *ttc);
+void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv,
+			     struct mlx5e_ttc_table *ttc);
+
+int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
+				 struct mlx5e_ttc_table *ttc);
+void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv,
+				   struct mlx5e_ttc_table *ttc);
+
+void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft);
+
+void mlx5e_enable_cvlan_filter(struct mlx5e_priv *priv);
+void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv);
+
+int mlx5e_create_flow_steering(struct mlx5e_priv *priv);
+void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv);
+
+#endif /* __MLX5E_FLOW_STEER_H__ */
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
new file mode 100644
index 000000000000..ad6d471d00dd
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -0,0 +1,307 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/bpf_trace.h>
+#include "en/xdp.h"
+
+static inline bool
+mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di,
+		    struct xdp_buff *xdp)
+{
+	struct mlx5e_xdp_info xdpi;
+
+	xdpi.xdpf = convert_to_xdp_frame(xdp);
+	if (unlikely(!xdpi.xdpf))
+		return false;
+	xdpi.dma_addr = di->addr + (xdpi.xdpf->data - (void *)xdpi.xdpf);
+	dma_sync_single_for_device(sq->pdev, xdpi.dma_addr,
+				   xdpi.xdpf->len, PCI_DMA_TODEVICE);
+	xdpi.di = *di;
+
+	return mlx5e_xmit_xdp_frame(sq, &xdpi);
+}
+
+/* returns true if packet was consumed by xdp */
+bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
+		      void *va, u16 *rx_headroom, u32 *len)
+{
+	struct bpf_prog *prog = READ_ONCE(rq->xdp_prog);
+	struct xdp_buff xdp;
+	u32 act;
+	int err;
+
+	if (!prog)
+		return false;
+
+	xdp.data = va + *rx_headroom;
+	xdp_set_data_meta_invalid(&xdp);
+	xdp.data_end = xdp.data + *len;
+	xdp.data_hard_start = va;
+	xdp.rxq = &rq->xdp_rxq;
+
+	act = bpf_prog_run_xdp(prog, &xdp);
+	switch (act) {
+	case XDP_PASS:
+		*rx_headroom = xdp.data - xdp.data_hard_start;
+		*len = xdp.data_end - xdp.data;
+		return false;
+	case XDP_TX:
+		if (unlikely(!mlx5e_xmit_xdp_buff(&rq->xdpsq, di, &xdp)))
+			goto xdp_abort;
+		__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
+		return true;
+	case XDP_REDIRECT:
+		/* When XDP enabled then page-refcnt==1 here */
+		err = xdp_do_redirect(rq->netdev, &xdp, prog);
+		if (unlikely(err))
+			goto xdp_abort;
+		__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags);
+		rq->xdpsq.redirect_flush = true;
+		mlx5e_page_dma_unmap(rq, di);
+		rq->stats->xdp_redirect++;
+		return true;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+		/* fall through */
+	case XDP_ABORTED:
+xdp_abort:
+		trace_xdp_exception(rq->netdev, prog, act);
+		/* fall through */
+	case XDP_DROP:
+		rq->stats->xdp_drop++;
+		return true;
+	}
+}
+
+bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
+{
+	struct mlx5_wq_cyc       *wq   = &sq->wq;
+	u16                       pi   = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
+
+	struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
+	struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
+	struct mlx5_wqe_data_seg *dseg = wqe->data;
+
+	struct xdp_frame *xdpf = xdpi->xdpf;
+	dma_addr_t dma_addr  = xdpi->dma_addr;
+	unsigned int dma_len = xdpf->len;
+
+	struct mlx5e_xdpsq_stats *stats = sq->stats;
+
+	prefetchw(wqe);
+
+	if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE || sq->hw_mtu < dma_len)) {
+		stats->err++;
+		return false;
+	}
+
+	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) {
+		if (sq->doorbell) {
+			/* SQ is full, ring doorbell */
+			mlx5e_xmit_xdp_doorbell(sq);
+			sq->doorbell = false;
+		}
+		stats->full++;
+		return false;
+	}
+
+	cseg->fm_ce_se = 0;
+
+	/* copy the inline part if required */
+	if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
+		memcpy(eseg->inline_hdr.start, xdpf->data, MLX5E_XDP_MIN_INLINE);
+		eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE);
+		dma_len  -= MLX5E_XDP_MIN_INLINE;
+		dma_addr += MLX5E_XDP_MIN_INLINE;
+		dseg++;
+	}
+
+	/* write the dma part */
+	dseg->addr       = cpu_to_be64(dma_addr);
+	dseg->byte_count = cpu_to_be32(dma_len);
+
+	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND);
+
+	/* move page to reference to sq responsibility,
+	 * and mark so it's not put back in page-cache.
+	 */
+	sq->db.xdpi[pi] = *xdpi;
+	sq->pc++;
+
+	sq->doorbell = true;
+
+	stats->xmit++;
+	return true;
+}
+
+bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
+{
+	struct mlx5e_xdpsq *sq;
+	struct mlx5_cqe64 *cqe;
+	struct mlx5e_rq *rq;
+	bool is_redirect;
+	u16 sqcc;
+	int i;
+
+	sq = container_of(cq, struct mlx5e_xdpsq, cq);
+
+	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
+		return false;
+
+	cqe = mlx5_cqwq_get_cqe(&cq->wq);
+	if (!cqe)
+		return false;
+
+	is_redirect = test_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state);
+	rq = container_of(sq, struct mlx5e_rq, xdpsq);
+
+	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
+	 * otherwise a cq overrun may occur
+	 */
+	sqcc = sq->cc;
+
+	i = 0;
+	do {
+		u16 wqe_counter;
+		bool last_wqe;
+
+		mlx5_cqwq_pop(&cq->wq);
+
+		wqe_counter = be16_to_cpu(cqe->wqe_counter);
+
+		do {
+			u16 ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
+			struct mlx5e_xdp_info *xdpi = &sq->db.xdpi[ci];
+
+			last_wqe = (sqcc == wqe_counter);
+			sqcc++;
+
+			if (is_redirect) {
+				xdp_return_frame(xdpi->xdpf);
+				dma_unmap_single(sq->pdev, xdpi->dma_addr,
+						 xdpi->xdpf->len, DMA_TO_DEVICE);
+			} else {
+				/* Recycle RX page */
+				mlx5e_page_release(rq, &xdpi->di, true);
+			}
+		} while (!last_wqe);
+	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
+
+	sq->stats->cqes += i;
+
+	mlx5_cqwq_update_db_record(&cq->wq);
+
+	/* ensure cq space is freed before enabling more cqes */
+	wmb();
+
+	sq->cc = sqcc;
+	return (i == MLX5E_TX_CQ_POLL_BUDGET);
+}
+
+void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
+{
+	struct mlx5e_rq *rq;
+	bool is_redirect;
+
+	is_redirect = test_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state);
+	rq = is_redirect ? NULL : container_of(sq, struct mlx5e_rq, xdpsq);
+
+	while (sq->cc != sq->pc) {
+		u16 ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
+		struct mlx5e_xdp_info *xdpi = &sq->db.xdpi[ci];
+
+		sq->cc++;
+
+		if (is_redirect) {
+			xdp_return_frame(xdpi->xdpf);
+			dma_unmap_single(sq->pdev, xdpi->dma_addr,
+					 xdpi->xdpf->len, DMA_TO_DEVICE);
+		} else {
+			/* Recycle RX page */
+			mlx5e_page_release(rq, &xdpi->di, false);
+		}
+	}
+}
+
+int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
+		   u32 flags)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_xdpsq *sq;
+	int drops = 0;
+	int sq_num;
+	int i;
+
+	if (unlikely(!test_bit(MLX5E_STATE_OPENED, &priv->state)))
+		return -ENETDOWN;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	sq_num = smp_processor_id();
+
+	if (unlikely(sq_num >= priv->channels.num))
+		return -ENXIO;
+
+	sq = &priv->channels.c[sq_num]->xdpsq;
+
+	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
+		return -ENETDOWN;
+
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *xdpf = frames[i];
+		struct mlx5e_xdp_info xdpi;
+
+		xdpi.dma_addr = dma_map_single(sq->pdev, xdpf->data, xdpf->len,
+					       DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(sq->pdev, xdpi.dma_addr))) {
+			xdp_return_frame_rx_napi(xdpf);
+			drops++;
+			continue;
+		}
+
+		xdpi.xdpf = xdpf;
+
+		if (unlikely(!mlx5e_xmit_xdp_frame(sq, &xdpi))) {
+			dma_unmap_single(sq->pdev, xdpi.dma_addr,
+					 xdpf->len, DMA_TO_DEVICE);
+			xdp_return_frame_rx_napi(xdpf);
+			drops++;
+		}
+	}
+
+	if (flags & XDP_XMIT_FLUSH)
+		mlx5e_xmit_xdp_doorbell(sq);
+
+	return n - drops;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
new file mode 100644
index 000000000000..6dfab045925f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef __MLX5_EN_XDP_H__
+#define __MLX5_EN_XDP_H__
+
+#include "en.h"
+
+#define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \
+				 MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM)))
+#define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
+#define MLX5E_XDP_TX_DS_COUNT \
+	((sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) + 1 /* SG DS */)
+
+bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
+		      void *va, u16 *rx_headroom, u32 *len);
+bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
+void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq);
+
+bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi);
+int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
+		   u32 flags);
+
+static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
+{
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	struct mlx5e_tx_wqe *wqe;
+	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc - 1); /* last pi */
+
+	wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
+
+	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &wqe->ctrl);
+}
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index f20074dbef32..1dd225380a66 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -34,19 +34,26 @@
 #ifndef __MLX5E_EN_ACCEL_H__
 #define __MLX5E_EN_ACCEL_H__
 
-#ifdef CONFIG_MLX5_ACCEL
-
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/tls_rxtx.h"
 #include "en.h"
 
-static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb,
-						    struct mlx5e_txqsq *sq,
-						    struct net_device *dev,
-						    struct mlx5e_tx_wqe **wqe,
-						    u16 *pi)
+static inline void
+mlx5e_udp_gso_handle_tx_skb(struct sk_buff *skb)
+{
+	int payload_len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr);
+
+	udp_hdr(skb)->len = htons(payload_len);
+}
+
+static inline struct sk_buff *
+mlx5e_accel_handle_tx(struct sk_buff *skb,
+		      struct mlx5e_txqsq *sq,
+		      struct net_device *dev,
+		      struct mlx5e_tx_wqe **wqe,
+		      u16 *pi)
 {
 #ifdef CONFIG_MLX5_EN_TLS
 	if (test_bit(MLX5E_SQ_STATE_TLS, &sq->state)) {
@@ -64,9 +71,10 @@ static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb,
 	}
 #endif
 
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+		mlx5e_udp_gso_handle_tx_skb(skb);
+
 	return skb;
 }
 
-#endif /* CONFIG_MLX5_ACCEL */
-
 #endif /* __MLX5E_EN_ACCEL_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index c245d8e78509..128a82b1dbfc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -37,6 +37,7 @@
 
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/ipsec.h"
+#include "accel/accel.h"
 #include "en.h"
 
 enum {
@@ -346,19 +347,12 @@ mlx5e_ipsec_build_sp(struct net_device *netdev, struct sk_buff *skb,
 }
 
 struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev,
-					  struct sk_buff *skb)
+					  struct sk_buff *skb, u32 *cqe_bcnt)
 {
 	struct mlx5e_ipsec_metadata *mdata;
-	struct ethhdr *old_eth;
-	struct ethhdr *new_eth;
 	struct xfrm_state *xs;
-	__be16 *ethtype;
 
-	/* Detect inline metadata */
-	if (skb->len < ETH_HLEN + MLX5E_METADATA_ETHER_LEN)
-		return skb;
-	ethtype = (__be16 *)(skb->data + ETH_ALEN * 2);
-	if (*ethtype != cpu_to_be16(MLX5E_METADATA_ETHER_TYPE))
+	if (!is_metadata_hdr_valid(skb))
 		return skb;
 
 	/* Use the metadata */
@@ -369,12 +363,8 @@ struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev,
 		return NULL;
 	}
 
-	/* Remove the metadata from the buffer */
-	old_eth = (struct ethhdr *)skb->data;
-	new_eth = (struct ethhdr *)(skb->data + MLX5E_METADATA_ETHER_LEN);
-	memmove(new_eth, old_eth, 2 * ETH_ALEN);
-	/* Ethertype is already in its new place */
-	skb_pull_inline(skb, MLX5E_METADATA_ETHER_LEN);
+	remove_metadata_hdr(skb);
+	*cqe_bcnt -= MLX5E_METADATA_ETHER_LEN;
 
 	return skb;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
index 2bfbbef1b054..ca47c0540904 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
@@ -41,7 +41,7 @@
 #include "en.h"
 
 struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev,
-					  struct sk_buff *skb);
+					  struct sk_buff *skb, u32 *cqe_bcnt);
 void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 
 void mlx5e_ipsec_inverse_table_init(void);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
index d167845271c3..eddd7702680b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
@@ -110,9 +110,7 @@ static int mlx5e_tls_add(struct net_device *netdev, struct sock *sk,
 	u32 caps = mlx5_accel_tls_device_caps(mdev);
 	int ret = -ENOMEM;
 	void *flow;
-
-	if (direction != TLS_OFFLOAD_CTX_DIR_TX)
-		return -EINVAL;
+	u32 swid;
 
 	flow = kzalloc(MLX5_ST_SZ_BYTES(tls_flow), GFP_KERNEL);
 	if (!flow)
@@ -122,18 +120,23 @@ static int mlx5e_tls_add(struct net_device *netdev, struct sock *sk,
 	if (ret)
 		goto free_flow;
 
+	ret = mlx5_accel_tls_add_flow(mdev, flow, crypto_info,
+				      start_offload_tcp_sn, &swid,
+				      direction == TLS_OFFLOAD_CTX_DIR_TX);
+	if (ret < 0)
+		goto free_flow;
+
 	if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
-		struct mlx5e_tls_offload_context *tx_ctx =
+		struct mlx5e_tls_offload_context_tx *tx_ctx =
 		    mlx5e_get_tls_tx_context(tls_ctx);
-		u32 swid;
-
-		ret = mlx5_accel_tls_add_tx_flow(mdev, flow, crypto_info,
-						 start_offload_tcp_sn, &swid);
-		if (ret < 0)
-			goto free_flow;
 
 		tx_ctx->swid = htonl(swid);
 		tx_ctx->expected_seq = start_offload_tcp_sn;
+	} else {
+		struct mlx5e_tls_offload_context_rx *rx_ctx =
+		    mlx5e_get_tls_rx_context(tls_ctx);
+
+		rx_ctx->handle = htonl(swid);
 	}
 
 	return 0;
@@ -147,30 +150,60 @@ static void mlx5e_tls_del(struct net_device *netdev,
 			  enum tls_offload_ctx_dir direction)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	unsigned int handle;
 
-	if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
-		u32 swid = ntohl(mlx5e_get_tls_tx_context(tls_ctx)->swid);
+	handle = ntohl((direction == TLS_OFFLOAD_CTX_DIR_TX) ?
+		       mlx5e_get_tls_tx_context(tls_ctx)->swid :
+		       mlx5e_get_tls_rx_context(tls_ctx)->handle);
 
-		mlx5_accel_tls_del_tx_flow(priv->mdev, swid);
-	} else {
-		netdev_err(netdev, "unsupported direction %d\n", direction);
-	}
+	mlx5_accel_tls_del_flow(priv->mdev, handle,
+				direction == TLS_OFFLOAD_CTX_DIR_TX);
+}
+
+static void mlx5e_tls_resync_rx(struct net_device *netdev, struct sock *sk,
+				u32 seq, u64 rcd_sn)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_tls_offload_context_rx *rx_ctx;
+
+	rx_ctx = mlx5e_get_tls_rx_context(tls_ctx);
+
+	netdev_info(netdev, "resyncing seq %d rcd %lld\n", seq,
+		    be64_to_cpu(rcd_sn));
+	mlx5_accel_tls_resync_rx(priv->mdev, rx_ctx->handle, seq, rcd_sn);
+	atomic64_inc(&priv->tls->sw_stats.rx_tls_resync_reply);
 }
 
 static const struct tlsdev_ops mlx5e_tls_ops = {
 	.tls_dev_add = mlx5e_tls_add,
 	.tls_dev_del = mlx5e_tls_del,
+	.tls_dev_resync_rx = mlx5e_tls_resync_rx,
 };
 
 void mlx5e_tls_build_netdev(struct mlx5e_priv *priv)
 {
+	u32 caps = mlx5_accel_tls_device_caps(priv->mdev);
 	struct net_device *netdev = priv->netdev;
 
 	if (!mlx5_accel_is_tls_device(priv->mdev))
 		return;
 
-	netdev->features |= NETIF_F_HW_TLS_TX;
-	netdev->hw_features |= NETIF_F_HW_TLS_TX;
+	if (caps & MLX5_ACCEL_TLS_TX) {
+		netdev->features          |= NETIF_F_HW_TLS_TX;
+		netdev->hw_features       |= NETIF_F_HW_TLS_TX;
+	}
+
+	if (caps & MLX5_ACCEL_TLS_RX) {
+		netdev->features          |= NETIF_F_HW_TLS_RX;
+		netdev->hw_features       |= NETIF_F_HW_TLS_RX;
+	}
+
+	if (!(caps & MLX5_ACCEL_TLS_LRO)) {
+		netdev->features          &= ~NETIF_F_LRO;
+		netdev->hw_features       &= ~NETIF_F_LRO;
+	}
+
 	netdev->tlsdev_ops = &mlx5e_tls_ops;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
index b6162178f621..3f5d72163b56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
@@ -43,25 +43,44 @@ struct mlx5e_tls_sw_stats {
 	atomic64_t tx_tls_drop_resync_alloc;
 	atomic64_t tx_tls_drop_no_sync_data;
 	atomic64_t tx_tls_drop_bypass_required;
+	atomic64_t rx_tls_drop_resync_request;
+	atomic64_t rx_tls_resync_request;
+	atomic64_t rx_tls_resync_reply;
+	atomic64_t rx_tls_auth_fail;
 };
 
 struct mlx5e_tls {
 	struct mlx5e_tls_sw_stats sw_stats;
 };
 
-struct mlx5e_tls_offload_context {
-	struct tls_offload_context base;
+struct mlx5e_tls_offload_context_tx {
+	struct tls_offload_context_tx base;
 	u32 expected_seq;
 	__be32 swid;
 };
 
-static inline struct mlx5e_tls_offload_context *
+static inline struct mlx5e_tls_offload_context_tx *
 mlx5e_get_tls_tx_context(struct tls_context *tls_ctx)
 {
-	BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context) >
-		     TLS_OFFLOAD_CONTEXT_SIZE);
-	return container_of(tls_offload_ctx(tls_ctx),
-			    struct mlx5e_tls_offload_context,
+	BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context_tx) >
+		     TLS_OFFLOAD_CONTEXT_SIZE_TX);
+	return container_of(tls_offload_ctx_tx(tls_ctx),
+			    struct mlx5e_tls_offload_context_tx,
+			    base);
+}
+
+struct mlx5e_tls_offload_context_rx {
+	struct tls_offload_context_rx base;
+	__be32 handle;
+};
+
+static inline struct mlx5e_tls_offload_context_rx *
+mlx5e_get_tls_rx_context(struct tls_context *tls_ctx)
+{
+	BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context_rx) >
+		     TLS_OFFLOAD_CONTEXT_SIZE_RX);
+	return container_of(tls_offload_ctx_rx(tls_ctx),
+			    struct mlx5e_tls_offload_context_rx,
 			    base);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index 15aef71d1957..be137d4a9169 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -33,6 +33,14 @@
 
 #include "en_accel/tls.h"
 #include "en_accel/tls_rxtx.h"
+#include "accel/accel.h"
+
+#include <net/inet6_hashtables.h>
+#include <linux/ipv6.h>
+
+#define SYNDROM_DECRYPTED  0x30
+#define SYNDROM_RESYNC_REQUEST 0x31
+#define SYNDROM_AUTH_FAILED 0x32
 
 #define SYNDROME_OFFLOAD_REQUIRED 32
 #define SYNDROME_SYNC 33
@@ -44,10 +52,26 @@ struct sync_info {
 	skb_frag_t frags[MAX_SKB_FRAGS];
 };
 
-struct mlx5e_tls_metadata {
+struct recv_metadata_content {
+	u8 syndrome;
+	u8 reserved;
+	__be32 sync_seq;
+} __packed;
+
+struct send_metadata_content {
 	/* One byte of syndrome followed by 3 bytes of swid */
 	__be32 syndrome_swid;
 	__be16 first_seq;
+} __packed;
+
+struct mlx5e_tls_metadata {
+	union {
+		/* from fpga to host */
+		struct recv_metadata_content recv;
+		/* from host to fpga */
+		struct send_metadata_content send;
+		unsigned char raw[6];
+	} __packed content;
 	/* packet type ID field	*/
 	__be16 ethertype;
 } __packed;
@@ -68,12 +92,13 @@ static int mlx5e_tls_add_metadata(struct sk_buff *skb, __be32 swid)
 		2 * ETH_ALEN);
 
 	eth->h_proto = cpu_to_be16(MLX5E_METADATA_ETHER_TYPE);
-	pet->syndrome_swid = htonl(SYNDROME_OFFLOAD_REQUIRED << 24) | swid;
+	pet->content.send.syndrome_swid =
+		htonl(SYNDROME_OFFLOAD_REQUIRED << 24) | swid;
 
 	return 0;
 }
 
-static int mlx5e_tls_get_sync_data(struct mlx5e_tls_offload_context *context,
+static int mlx5e_tls_get_sync_data(struct mlx5e_tls_offload_context_tx *context,
 				   u32 tcp_seq, struct sync_info *info)
 {
 	int remaining, i = 0, ret = -EINVAL;
@@ -149,7 +174,7 @@ static void mlx5e_tls_complete_sync_skb(struct sk_buff *skb,
 
 	pet = (struct mlx5e_tls_metadata *)(nskb->data + sizeof(struct ethhdr));
 	memcpy(pet, &syndrome, sizeof(syndrome));
-	pet->first_seq = htons(tcp_seq);
+	pet->content.send.first_seq = htons(tcp_seq);
 
 	/* MLX5 devices don't care about the checksum partial start, offset
 	 * and pseudo header
@@ -161,7 +186,7 @@ static void mlx5e_tls_complete_sync_skb(struct sk_buff *skb,
 }
 
 static struct sk_buff *
-mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context *context,
+mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
 		     struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		     struct mlx5e_tx_wqe **wqe,
 		     u16 *pi,
@@ -239,7 +264,7 @@ struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
 					u16 *pi)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5e_tls_offload_context *context;
+	struct mlx5e_tls_offload_context_tx *context;
 	struct tls_context *tls_ctx;
 	u32 expected_seq;
 	int datalen;
@@ -276,3 +301,83 @@ struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
 out:
 	return skb;
 }
+
+static int tls_update_resync_sn(struct net_device *netdev,
+				struct sk_buff *skb,
+				struct mlx5e_tls_metadata *mdata)
+{
+	struct sock *sk = NULL;
+	struct iphdr *iph;
+	struct tcphdr *th;
+	__be32 seq;
+
+	if (mdata->ethertype != htons(ETH_P_IP))
+		return -EINVAL;
+
+	iph = (struct iphdr *)(mdata + 1);
+
+	th = ((void *)iph) + iph->ihl * 4;
+
+	if (iph->version == 4) {
+		sk = inet_lookup_established(dev_net(netdev), &tcp_hashinfo,
+					     iph->saddr, th->source, iph->daddr,
+					     th->dest, netdev->ifindex);
+#if IS_ENABLED(CONFIG_IPV6)
+	} else {
+		struct ipv6hdr *ipv6h = (struct ipv6hdr *)iph;
+
+		sk = __inet6_lookup_established(dev_net(netdev), &tcp_hashinfo,
+						&ipv6h->saddr, th->source,
+						&ipv6h->daddr, ntohs(th->dest),
+						netdev->ifindex, 0);
+#endif
+	}
+	if (!sk || sk->sk_state == TCP_TIME_WAIT) {
+		struct mlx5e_priv *priv = netdev_priv(netdev);
+
+		atomic64_inc(&priv->tls->sw_stats.rx_tls_drop_resync_request);
+		goto out;
+	}
+
+	skb->sk = sk;
+	skb->destructor = sock_edemux;
+
+	memcpy(&seq, &mdata->content.recv.sync_seq, sizeof(seq));
+	tls_offload_rx_resync_request(sk, seq);
+out:
+	return 0;
+}
+
+void mlx5e_tls_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
+			     u32 *cqe_bcnt)
+{
+	struct mlx5e_tls_metadata *mdata;
+	struct mlx5e_priv *priv;
+
+	if (!is_metadata_hdr_valid(skb))
+		return;
+
+	/* Use the metadata */
+	mdata = (struct mlx5e_tls_metadata *)(skb->data + ETH_HLEN);
+	switch (mdata->content.recv.syndrome) {
+	case SYNDROM_DECRYPTED:
+		skb->decrypted = 1;
+		break;
+	case SYNDROM_RESYNC_REQUEST:
+		tls_update_resync_sn(netdev, skb, mdata);
+		priv = netdev_priv(netdev);
+		atomic64_inc(&priv->tls->sw_stats.rx_tls_resync_request);
+		break;
+	case SYNDROM_AUTH_FAILED:
+		/* Authentication failure will be observed and verified by kTLS */
+		priv = netdev_priv(netdev);
+		atomic64_inc(&priv->tls->sw_stats.rx_tls_auth_fail);
+		break;
+	default:
+		/* Bypass the metadata header to others */
+		return;
+	}
+
+	remove_metadata_hdr(skb);
+	*cqe_bcnt -= MLX5E_METADATA_ETHER_LEN;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
index 405dfd302225..311667ec71b8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
@@ -45,6 +45,9 @@ struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
 					struct mlx5e_tx_wqe **wqe,
 					u16 *pi);
 
+void mlx5e_tls_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
+			     u32 *cqe_bcnt);
+
 #endif /* CONFIG_MLX5_EN_TLS */
 
 #endif /* __MLX5E_TLS_RXTX_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index d258bb679271..45cdde694d20 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -30,8 +30,6 @@
  * SOFTWARE.
  */
 
-#ifdef CONFIG_RFS_ACCEL
-
 #include <linux/hash.h>
 #include <linux/mlx5/fs.h>
 #include <linux/ip.h>
@@ -738,4 +736,4 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	spin_unlock_bh(&arfs->arfs_lock);
 	return arfs_rule->filter_id;
 }
-#endif
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index fffe514ba855..98dd3e0ada72 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -32,6 +32,7 @@
 
 #include "en.h"
 #include "en/port.h"
+#include "lib/clock.h"
 
 void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
 			       struct ethtool_drvinfo *drvinfo)
@@ -969,33 +970,6 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 	return 0;
 }
 
-static int mlx5e_get_rxnfc(struct net_device *netdev,
-			   struct ethtool_rxnfc *info, u32 *rule_locs)
-{
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-	int err = 0;
-
-	switch (info->cmd) {
-	case ETHTOOL_GRXRINGS:
-		info->data = priv->channels.params.num_channels;
-		break;
-	case ETHTOOL_GRXCLSRLCNT:
-		info->rule_cnt = priv->fs.ethtool.tot_num_rules;
-		break;
-	case ETHTOOL_GRXCLSRULE:
-		err = mlx5e_ethtool_get_flow(priv, info, info->fs.location);
-		break;
-	case ETHTOOL_GRXCLSRLALL:
-		err = mlx5e_ethtool_get_all_flows(priv, info, rule_locs);
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		break;
-	}
-
-	return err;
-}
-
 #define MLX5E_PFC_PREVEN_AUTO_TOUT_MSEC		100
 #define MLX5E_PFC_PREVEN_TOUT_MAX_MSEC		8000
 #define MLX5E_PFC_PREVEN_MINOR_PRECENT		85
@@ -1133,10 +1107,10 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 	if (ret)
 		return ret;
 
-	info->phc_index = mdev->clock.ptp ?
-			  ptp_clock_index(mdev->clock.ptp) : -1;
+	info->phc_index = mlx5_clock_get_ptp_index(mdev);
 
-	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
+	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz) ||
+	    info->phc_index == -1)
 		return 0;
 
 	info->so_timestamping |= SOF_TIMESTAMPING_TX_HARDWARE |
@@ -1606,26 +1580,6 @@ static u32 mlx5e_get_priv_flags(struct net_device *netdev)
 	return priv->channels.params.pflags;
 }
 
-static int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
-{
-	int err = 0;
-	struct mlx5e_priv *priv = netdev_priv(dev);
-
-	switch (cmd->cmd) {
-	case ETHTOOL_SRXCLSRLINS:
-		err = mlx5e_ethtool_flow_replace(priv, &cmd->fs);
-		break;
-	case ETHTOOL_SRXCLSRLDEL:
-		err = mlx5e_ethtool_flow_remove(priv, cmd->fs.location);
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		break;
-	}
-
-	return err;
-}
-
 int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
 			       struct ethtool_flash *flash)
 {
@@ -1678,8 +1632,10 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.get_rxfh_indir_size = mlx5e_get_rxfh_indir_size,
 	.get_rxfh          = mlx5e_get_rxfh,
 	.set_rxfh          = mlx5e_set_rxfh,
+#ifdef CONFIG_MLX5_EN_RXNFC
 	.get_rxnfc         = mlx5e_get_rxnfc,
 	.set_rxnfc         = mlx5e_set_rxnfc,
+#endif
 	.flash_device      = mlx5e_flash_device,
 	.get_tunable       = mlx5e_get_tunable,
 	.set_tunable       = mlx5e_set_tunable,
@@ -1696,5 +1652,4 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.self_test         = mlx5e_self_test,
 	.get_msglevel      = mlx5e_get_msglevel,
 	.set_msglevel      = mlx5e_set_msglevel,
-
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index eafc59280ada..75bb981e00b7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -66,11 +66,14 @@ static struct mlx5e_ethtool_table *get_flow_table(struct mlx5e_priv *priv,
 	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
 		max_tuples = ETHTOOL_NUM_L3_L4_FTS;
 		prio = MLX5E_ETHTOOL_L3_L4_PRIO + (max_tuples - num_tuples);
 		eth_ft = &priv->fs.ethtool.l3_l4_ft[prio];
 		break;
 	case IP_USER_FLOW:
+	case IPV6_USER_FLOW:
 		max_tuples = ETHTOOL_NUM_L3_L4_FTS;
 		prio = MLX5E_ETHTOOL_L3_L4_PRIO + (max_tuples - num_tuples);
 		eth_ft = &priv->fs.ethtool.l3_l4_ft[prio];
@@ -115,29 +118,203 @@ static void mask_spec(u8 *mask, u8 *val, size_t size)
 		*((u8 *)val) = *((u8 *)mask) & *((u8 *)val);
 }
 
-static void set_ips(void *outer_headers_v, void *outer_headers_c, __be32 ip4src_m,
-		    __be32 ip4src_v, __be32 ip4dst_m, __be32 ip4dst_v)
+#define MLX5E_FTE_SET(header_p, fld, v)  \
+	MLX5_SET(fte_match_set_lyr_2_4, header_p, fld, v)
+
+#define MLX5E_FTE_ADDR_OF(header_p, fld) \
+	MLX5_ADDR_OF(fte_match_set_lyr_2_4, header_p, fld)
+
+static void
+set_ip4(void *headers_c, void *headers_v, __be32 ip4src_m,
+	__be32 ip4src_v, __be32 ip4dst_m, __be32 ip4dst_v)
 {
 	if (ip4src_m) {
-		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_v,
-				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
+		memcpy(MLX5E_FTE_ADDR_OF(headers_v, src_ipv4_src_ipv6.ipv4_layout.ipv4),
 		       &ip4src_v, sizeof(ip4src_v));
-		memset(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_c,
-				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
+		memset(MLX5E_FTE_ADDR_OF(headers_c, src_ipv4_src_ipv6.ipv4_layout.ipv4),
 		       0xff, sizeof(ip4src_m));
 	}
 	if (ip4dst_m) {
-		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_v,
-				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
+		memcpy(MLX5E_FTE_ADDR_OF(headers_v, dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
 		       &ip4dst_v, sizeof(ip4dst_v));
-		memset(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_c,
-				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
+		memset(MLX5E_FTE_ADDR_OF(headers_c, dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
 		       0xff, sizeof(ip4dst_m));
 	}
-	MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
-		 ethertype, ETH_P_IP);
-	MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
-		 ethertype, 0xffff);
+
+	MLX5E_FTE_SET(headers_c, ethertype, 0xffff);
+	MLX5E_FTE_SET(headers_v, ethertype, ETH_P_IP);
+}
+
+static void
+set_ip6(void *headers_c, void *headers_v, __be32 ip6src_m[4],
+	__be32 ip6src_v[4], __be32 ip6dst_m[4], __be32 ip6dst_v[4])
+{
+	u8 ip6_sz = MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6);
+
+	if (!ipv6_addr_any((struct in6_addr *)ip6src_m)) {
+		memcpy(MLX5E_FTE_ADDR_OF(headers_v, src_ipv4_src_ipv6.ipv6_layout.ipv6),
+		       ip6src_v, ip6_sz);
+		memcpy(MLX5E_FTE_ADDR_OF(headers_c, src_ipv4_src_ipv6.ipv6_layout.ipv6),
+		       ip6src_m, ip6_sz);
+	}
+	if (!ipv6_addr_any((struct in6_addr *)ip6dst_m)) {
+		memcpy(MLX5E_FTE_ADDR_OF(headers_v, dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+		       ip6dst_v, ip6_sz);
+		memcpy(MLX5E_FTE_ADDR_OF(headers_c, dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+		       ip6dst_m, ip6_sz);
+	}
+
+	MLX5E_FTE_SET(headers_c, ethertype, 0xffff);
+	MLX5E_FTE_SET(headers_v, ethertype, ETH_P_IPV6);
+}
+
+static void
+set_tcp(void *headers_c, void *headers_v, __be16 psrc_m, __be16 psrc_v,
+	__be16 pdst_m, __be16 pdst_v)
+{
+	if (psrc_m) {
+		MLX5E_FTE_SET(headers_c, tcp_sport, 0xffff);
+		MLX5E_FTE_SET(headers_v, tcp_sport, ntohs(psrc_v));
+	}
+	if (pdst_m) {
+		MLX5E_FTE_SET(headers_c, tcp_dport, 0xffff);
+		MLX5E_FTE_SET(headers_v, tcp_dport, ntohs(pdst_v));
+	}
+
+	MLX5E_FTE_SET(headers_c, ip_protocol, 0xffff);
+	MLX5E_FTE_SET(headers_v, ip_protocol, IPPROTO_TCP);
+}
+
+static void
+set_udp(void *headers_c, void *headers_v, __be16 psrc_m, __be16 psrc_v,
+	__be16 pdst_m, __be16 pdst_v)
+{
+	if (psrc_m) {
+		MLX5E_FTE_SET(headers_c, udp_sport, 0xffff);
+		MLX5E_FTE_SET(headers_c, udp_sport, ntohs(psrc_v));
+	}
+
+	if (pdst_m) {
+		MLX5E_FTE_SET(headers_c, udp_dport, 0xffff);
+		MLX5E_FTE_SET(headers_v, udp_dport, ntohs(pdst_v));
+	}
+
+	MLX5E_FTE_SET(headers_c, ip_protocol, 0xffff);
+	MLX5E_FTE_SET(headers_v, ip_protocol, IPPROTO_UDP);
+}
+
+static void
+parse_tcp4(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip4_spec *l4_mask = &fs->m_u.tcp_ip4_spec;
+	struct ethtool_tcpip4_spec *l4_val  = &fs->h_u.tcp_ip4_spec;
+
+	set_ip4(headers_c, headers_v, l4_mask->ip4src, l4_val->ip4src,
+		l4_mask->ip4dst, l4_val->ip4dst);
+
+	set_tcp(headers_c, headers_v, l4_mask->psrc, l4_val->psrc,
+		l4_mask->pdst, l4_val->pdst);
+}
+
+static void
+parse_udp4(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip4_spec *l4_mask = &fs->m_u.udp_ip4_spec;
+	struct ethtool_tcpip4_spec *l4_val  = &fs->h_u.udp_ip4_spec;
+
+	set_ip4(headers_c, headers_v, l4_mask->ip4src, l4_val->ip4src,
+		l4_mask->ip4dst, l4_val->ip4dst);
+
+	set_udp(headers_c, headers_v, l4_mask->psrc, l4_val->psrc,
+		l4_mask->pdst, l4_val->pdst);
+}
+
+static void
+parse_ip4(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_usrip4_spec *l3_mask = &fs->m_u.usr_ip4_spec;
+	struct ethtool_usrip4_spec *l3_val  = &fs->h_u.usr_ip4_spec;
+
+	set_ip4(headers_c, headers_v, l3_mask->ip4src, l3_val->ip4src,
+		l3_mask->ip4dst, l3_val->ip4dst);
+
+	if (l3_mask->proto) {
+		MLX5E_FTE_SET(headers_c, ip_protocol, l3_mask->proto);
+		MLX5E_FTE_SET(headers_v, ip_protocol, l3_val->proto);
+	}
+}
+
+static void
+parse_ip6(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_usrip6_spec *l3_mask = &fs->m_u.usr_ip6_spec;
+	struct ethtool_usrip6_spec *l3_val  = &fs->h_u.usr_ip6_spec;
+
+	set_ip6(headers_c, headers_v, l3_mask->ip6src,
+		l3_val->ip6src, l3_mask->ip6dst, l3_val->ip6dst);
+
+	if (l3_mask->l4_proto) {
+		MLX5E_FTE_SET(headers_c, ip_protocol, l3_mask->l4_proto);
+		MLX5E_FTE_SET(headers_v, ip_protocol, l3_val->l4_proto);
+	}
+}
+
+static void
+parse_tcp6(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip6_spec *l4_mask = &fs->m_u.tcp_ip6_spec;
+	struct ethtool_tcpip6_spec *l4_val  = &fs->h_u.tcp_ip6_spec;
+
+	set_ip6(headers_c, headers_v, l4_mask->ip6src,
+		l4_val->ip6src, l4_mask->ip6dst, l4_val->ip6dst);
+
+	set_tcp(headers_c, headers_v, l4_mask->psrc, l4_val->psrc,
+		l4_mask->pdst, l4_val->pdst);
+}
+
+static void
+parse_udp6(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip6_spec *l4_mask = &fs->m_u.udp_ip6_spec;
+	struct ethtool_tcpip6_spec *l4_val  = &fs->h_u.udp_ip6_spec;
+
+	set_ip6(headers_c, headers_v, l4_mask->ip6src,
+		l4_val->ip6src, l4_mask->ip6dst, l4_val->ip6dst);
+
+	set_udp(headers_c, headers_v, l4_mask->psrc, l4_val->psrc,
+		l4_mask->pdst, l4_val->pdst);
+}
+
+static void
+parse_ether(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethhdr *eth_mask = &fs->m_u.ether_spec;
+	struct ethhdr *eth_val = &fs->h_u.ether_spec;
+
+	mask_spec((u8 *)eth_mask, (u8 *)eth_val, sizeof(*eth_mask));
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_c, smac_47_16), eth_mask->h_source);
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_v, smac_47_16), eth_val->h_source);
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_c, dmac_47_16), eth_mask->h_dest);
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_v, dmac_47_16), eth_val->h_dest);
+	MLX5E_FTE_SET(headers_c, ethertype, ntohs(eth_mask->h_proto));
+	MLX5E_FTE_SET(headers_v, ethertype, ntohs(eth_val->h_proto));
+}
+
+static void
+set_cvlan(void *headers_c, void *headers_v, __be16 vlan_tci)
+{
+	MLX5E_FTE_SET(headers_c, cvlan_tag, 1);
+	MLX5E_FTE_SET(headers_v, cvlan_tag, 1);
+	MLX5E_FTE_SET(headers_c, first_vid, 0xfff);
+	MLX5E_FTE_SET(headers_v, first_vid, ntohs(vlan_tci));
+}
+
+static void
+set_dmac(void *headers_c, void *headers_v,
+	 unsigned char m_dest[ETH_ALEN], unsigned char v_dest[ETH_ALEN])
+{
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_c, dmac_47_16), m_dest);
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_v, dmac_47_16), v_dest);
 }
 
 static int set_flow_attrs(u32 *match_c, u32 *match_v,
@@ -148,112 +325,42 @@ static int set_flow_attrs(u32 *match_c, u32 *match_v,
 	void *outer_headers_v = MLX5_ADDR_OF(fte_match_param, match_v,
 					     outer_headers);
 	u32 flow_type = fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT);
-	struct ethtool_tcpip4_spec *l4_mask;
-	struct ethtool_tcpip4_spec *l4_val;
-	struct ethtool_usrip4_spec *l3_mask;
-	struct ethtool_usrip4_spec *l3_val;
-	struct ethhdr *eth_val;
-	struct ethhdr *eth_mask;
 
 	switch (flow_type) {
 	case TCP_V4_FLOW:
-		l4_mask = &fs->m_u.tcp_ip4_spec;
-		l4_val = &fs->h_u.tcp_ip4_spec;
-		set_ips(outer_headers_v, outer_headers_c, l4_mask->ip4src,
-			l4_val->ip4src, l4_mask->ip4dst, l4_val->ip4dst);
-
-		if (l4_mask->psrc) {
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, tcp_sport,
-				 0xffff);
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, tcp_sport,
-				 ntohs(l4_val->psrc));
-		}
-		if (l4_mask->pdst) {
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, tcp_dport,
-				 0xffff);
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, tcp_dport,
-				 ntohs(l4_val->pdst));
-		}
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol,
-			 0xffff);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, ip_protocol,
-			 IPPROTO_TCP);
+		parse_tcp4(outer_headers_c, outer_headers_v, fs);
 		break;
 	case UDP_V4_FLOW:
-		l4_mask = &fs->m_u.tcp_ip4_spec;
-		l4_val = &fs->h_u.tcp_ip4_spec;
-		set_ips(outer_headers_v, outer_headers_c, l4_mask->ip4src,
-			l4_val->ip4src, l4_mask->ip4dst, l4_val->ip4dst);
-
-		if (l4_mask->psrc) {
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, udp_sport,
-				 0xffff);
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, udp_sport,
-				 ntohs(l4_val->psrc));
-		}
-		if (l4_mask->pdst) {
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, udp_dport,
-				 0xffff);
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, udp_dport,
-				 ntohs(l4_val->pdst));
-		}
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol,
-			 0xffff);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, ip_protocol,
-			 IPPROTO_UDP);
+		parse_udp4(outer_headers_c, outer_headers_v, fs);
 		break;
 	case IP_USER_FLOW:
-		l3_mask = &fs->m_u.usr_ip4_spec;
-		l3_val = &fs->h_u.usr_ip4_spec;
-		set_ips(outer_headers_v, outer_headers_c, l3_mask->ip4src,
-			l3_val->ip4src, l3_mask->ip4dst, l3_val->ip4dst);
+		parse_ip4(outer_headers_c, outer_headers_v, fs);
+		break;
+	case TCP_V6_FLOW:
+		parse_tcp6(outer_headers_c, outer_headers_v, fs);
+		break;
+	case UDP_V6_FLOW:
+		parse_udp6(outer_headers_c, outer_headers_v, fs);
+		break;
+	case IPV6_USER_FLOW:
+		parse_ip6(outer_headers_c, outer_headers_v, fs);
 		break;
 	case ETHER_FLOW:
-		eth_mask = &fs->m_u.ether_spec;
-		eth_val = &fs->h_u.ether_spec;
-
-		mask_spec((u8 *)eth_mask, (u8 *)eth_val, sizeof(*eth_mask));
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_c, smac_47_16),
-				eth_mask->h_source);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_v, smac_47_16),
-				eth_val->h_source);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_c, dmac_47_16),
-				eth_mask->h_dest);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_v, dmac_47_16),
-				eth_val->h_dest);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, ethertype,
-			 ntohs(eth_mask->h_proto));
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, ethertype,
-			 ntohs(eth_val->h_proto));
+		parse_ether(outer_headers_c, outer_headers_v, fs);
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	if ((fs->flow_type & FLOW_EXT) &&
-	    (fs->m_ext.vlan_tci & cpu_to_be16(VLAN_VID_MASK))) {
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
-			 cvlan_tag, 1);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
-			 cvlan_tag, 1);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
-			 first_vid, 0xfff);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
-			 first_vid, ntohs(fs->h_ext.vlan_tci));
-	}
+	    (fs->m_ext.vlan_tci & cpu_to_be16(VLAN_VID_MASK)))
+		set_cvlan(outer_headers_c, outer_headers_v, fs->h_ext.vlan_tci);
+
 	if (fs->flow_type & FLOW_MAC_EXT &&
 	    !is_zero_ether_addr(fs->m_ext.h_dest)) {
 		mask_spec(fs->m_ext.h_dest, fs->h_ext.h_dest, ETH_ALEN);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_c, dmac_47_16),
-				fs->m_ext.h_dest);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_v, dmac_47_16),
-				fs->h_ext.h_dest);
+		set_dmac(outer_headers_c, outer_headers_v, fs->m_ext.h_dest,
+			 fs->h_ext.h_dest);
 	}
 
 	return 0;
@@ -379,16 +486,143 @@ static struct mlx5e_ethtool_rule *get_ethtool_rule(struct mlx5e_priv *priv,
 #define all_zeros_or_all_ones(field)		\
 	((field) == 0 || (field) == (__force typeof(field))-1)
 
+static int validate_ethter(struct ethtool_rx_flow_spec *fs)
+{
+	struct ethhdr *eth_mask = &fs->m_u.ether_spec;
+	int ntuples = 0;
+
+	if (!is_zero_ether_addr(eth_mask->h_dest))
+		ntuples++;
+	if (!is_zero_ether_addr(eth_mask->h_source))
+		ntuples++;
+	if (eth_mask->h_proto)
+		ntuples++;
+	return ntuples;
+}
+
+static int validate_tcpudp4(struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip4_spec *l4_mask = &fs->m_u.tcp_ip4_spec;
+	int ntuples = 0;
+
+	if (l4_mask->tos)
+		return -EINVAL;
+
+	if (l4_mask->ip4src) {
+		if (!all_ones(l4_mask->ip4src))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l4_mask->ip4dst) {
+		if (!all_ones(l4_mask->ip4dst))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l4_mask->psrc) {
+		if (!all_ones(l4_mask->psrc))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l4_mask->pdst) {
+		if (!all_ones(l4_mask->pdst))
+			return -EINVAL;
+		ntuples++;
+	}
+	/* Flow is TCP/UDP */
+	return ++ntuples;
+}
+
+static int validate_ip4(struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_usrip4_spec *l3_mask = &fs->m_u.usr_ip4_spec;
+	int ntuples = 0;
+
+	if (l3_mask->l4_4_bytes || l3_mask->tos ||
+	    fs->h_u.usr_ip4_spec.ip_ver != ETH_RX_NFC_IP4)
+		return -EINVAL;
+	if (l3_mask->ip4src) {
+		if (!all_ones(l3_mask->ip4src))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l3_mask->ip4dst) {
+		if (!all_ones(l3_mask->ip4dst))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l3_mask->proto)
+		ntuples++;
+	/* Flow is IPv4 */
+	return ++ntuples;
+}
+
+static int validate_ip6(struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_usrip6_spec *l3_mask = &fs->m_u.usr_ip6_spec;
+	int ntuples = 0;
+
+	if (l3_mask->l4_4_bytes || l3_mask->tclass)
+		return -EINVAL;
+	if (!ipv6_addr_any((struct in6_addr *)l3_mask->ip6src))
+		ntuples++;
+
+	if (!ipv6_addr_any((struct in6_addr *)l3_mask->ip6dst))
+		ntuples++;
+	if (l3_mask->l4_proto)
+		ntuples++;
+	/* Flow is IPv6 */
+	return ++ntuples;
+}
+
+static int validate_tcpudp6(struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip6_spec *l4_mask = &fs->m_u.tcp_ip6_spec;
+	int ntuples = 0;
+
+	if (l4_mask->tclass)
+		return -EINVAL;
+
+	if (!ipv6_addr_any((struct in6_addr *)l4_mask->ip6src))
+		ntuples++;
+
+	if (!ipv6_addr_any((struct in6_addr *)l4_mask->ip6dst))
+		ntuples++;
+
+	if (l4_mask->psrc) {
+		if (!all_ones(l4_mask->psrc))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l4_mask->pdst) {
+		if (!all_ones(l4_mask->pdst))
+			return -EINVAL;
+		ntuples++;
+	}
+	/* Flow is TCP/UDP */
+	return ++ntuples;
+}
+
+static int validate_vlan(struct ethtool_rx_flow_spec *fs)
+{
+	if (fs->m_ext.vlan_etype ||
+	    fs->m_ext.vlan_tci != cpu_to_be16(VLAN_VID_MASK))
+		return -EINVAL;
+
+	if (fs->m_ext.vlan_tci &&
+	    (be16_to_cpu(fs->h_ext.vlan_tci) >= VLAN_N_VID))
+		return -EINVAL;
+
+	return 1;
+}
+
 static int validate_flow(struct mlx5e_priv *priv,
 			 struct ethtool_rx_flow_spec *fs)
 {
-	struct ethtool_tcpip4_spec *l4_mask;
-	struct ethtool_usrip4_spec *l3_mask;
-	struct ethhdr *eth_mask;
 	int num_tuples = 0;
+	int ret = 0;
 
 	if (fs->location >= MAX_NUM_OF_ETHTOOL_RULES)
-		return -EINVAL;
+		return -ENOSPC;
 
 	if (fs->ring_cookie >= priv->channels.params.num_channels &&
 	    fs->ring_cookie != RX_CLS_FLOW_DISC)
@@ -396,73 +630,42 @@ static int validate_flow(struct mlx5e_priv *priv,
 
 	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
 	case ETHER_FLOW:
-		eth_mask = &fs->m_u.ether_spec;
-		if (!is_zero_ether_addr(eth_mask->h_dest))
-			num_tuples++;
-		if (!is_zero_ether_addr(eth_mask->h_source))
-			num_tuples++;
-		if (eth_mask->h_proto)
-			num_tuples++;
+		num_tuples += validate_ethter(fs);
 		break;
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
-		if (fs->m_u.tcp_ip4_spec.tos)
-			return -EINVAL;
-		l4_mask = &fs->m_u.tcp_ip4_spec;
-		if (l4_mask->ip4src) {
-			if (!all_ones(l4_mask->ip4src))
-				return -EINVAL;
-			num_tuples++;
-		}
-		if (l4_mask->ip4dst) {
-			if (!all_ones(l4_mask->ip4dst))
-				return -EINVAL;
-			num_tuples++;
-		}
-		if (l4_mask->psrc) {
-			if (!all_ones(l4_mask->psrc))
-				return -EINVAL;
-			num_tuples++;
-		}
-		if (l4_mask->pdst) {
-			if (!all_ones(l4_mask->pdst))
-				return -EINVAL;
-			num_tuples++;
-		}
-		/* Flow is TCP/UDP */
-		num_tuples++;
+		ret = validate_tcpudp4(fs);
+		if (ret < 0)
+			return ret;
+		num_tuples += ret;
 		break;
 	case IP_USER_FLOW:
-		l3_mask = &fs->m_u.usr_ip4_spec;
-		if (l3_mask->l4_4_bytes || l3_mask->tos || l3_mask->proto ||
-		    fs->h_u.usr_ip4_spec.ip_ver != ETH_RX_NFC_IP4)
-			return -EINVAL;
-		if (l3_mask->ip4src) {
-			if (!all_ones(l3_mask->ip4src))
-				return -EINVAL;
-			num_tuples++;
-		}
-		if (l3_mask->ip4dst) {
-			if (!all_ones(l3_mask->ip4dst))
-				return -EINVAL;
-			num_tuples++;
-		}
-		/* Flow is IPv4 */
-		num_tuples++;
+		ret = validate_ip4(fs);
+		if (ret < 0)
+			return ret;
+		num_tuples += ret;
+		break;
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+		ret = validate_tcpudp6(fs);
+		if (ret < 0)
+			return ret;
+		num_tuples += ret;
+		break;
+	case IPV6_USER_FLOW:
+		ret = validate_ip6(fs);
+		if (ret < 0)
+			return ret;
+		num_tuples += ret;
 		break;
 	default:
-		return -EINVAL;
+		return -ENOTSUPP;
 	}
 	if ((fs->flow_type & FLOW_EXT)) {
-		if (fs->m_ext.vlan_etype ||
-		    (fs->m_ext.vlan_tci != cpu_to_be16(VLAN_VID_MASK)))
-			return -EINVAL;
-
-		if (fs->m_ext.vlan_tci) {
-			if (be16_to_cpu(fs->h_ext.vlan_tci) >= VLAN_N_VID)
-				return -EINVAL;
-		}
-		num_tuples++;
+		ret = validate_vlan(fs);
+		if (ret < 0)
+			return ret;
+		num_tuples += ret;
 	}
 
 	if (fs->flow_type & FLOW_MAC_EXT &&
@@ -472,8 +675,9 @@ static int validate_flow(struct mlx5e_priv *priv,
 	return num_tuples;
 }
 
-int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
-			       struct ethtool_rx_flow_spec *fs)
+static int
+mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
+			   struct ethtool_rx_flow_spec *fs)
 {
 	struct mlx5e_ethtool_table *eth_ft;
 	struct mlx5e_ethtool_rule *eth_rule;
@@ -483,8 +687,9 @@ int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
 
 	num_tuples = validate_flow(priv, fs);
 	if (num_tuples <= 0) {
-		netdev_warn(priv->netdev, "%s: flow is not valid\n",  __func__);
-		return -EINVAL;
+		netdev_warn(priv->netdev, "%s: flow is not valid %d\n",
+			    __func__, num_tuples);
+		return num_tuples;
 	}
 
 	eth_ft = get_flow_table(priv, fs, num_tuples);
@@ -519,8 +724,8 @@ del_ethtool_rule:
 	return err;
 }
 
-int mlx5e_ethtool_flow_remove(struct mlx5e_priv *priv,
-			      int location)
+static int
+mlx5e_ethtool_flow_remove(struct mlx5e_priv *priv, int location)
 {
 	struct mlx5e_ethtool_rule *eth_rule;
 	int err = 0;
@@ -539,8 +744,9 @@ out:
 	return err;
 }
 
-int mlx5e_ethtool_get_flow(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
-			   int location)
+static int
+mlx5e_ethtool_get_flow(struct mlx5e_priv *priv,
+		       struct ethtool_rxnfc *info, int location)
 {
 	struct mlx5e_ethtool_rule *eth_rule;
 
@@ -557,8 +763,9 @@ int mlx5e_ethtool_get_flow(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
 	return -ENOENT;
 }
 
-int mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
-				u32 *rule_locs)
+static int
+mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv,
+			    struct ethtool_rxnfc *info, u32 *rule_locs)
 {
 	int location = 0;
 	int idx = 0;
@@ -587,3 +794,51 @@ void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv)
 {
 	INIT_LIST_HEAD(&priv->fs.ethtool.rules);
 }
+
+int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
+{
+	int err = 0;
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXCLSRLINS:
+		err = mlx5e_ethtool_flow_replace(priv, &cmd->fs);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		err = mlx5e_ethtool_flow_remove(priv, cmd->fs.location);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+int mlx5e_get_rxnfc(struct net_device *dev,
+		    struct ethtool_rxnfc *info, u32 *rule_locs)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	int err = 0;
+
+	switch (info->cmd) {
+	case ETHTOOL_GRXRINGS:
+		info->data = priv->channels.params.num_channels;
+		break;
+	case ETHTOOL_GRXCLSRLCNT:
+		info->rule_cnt = priv->fs.ethtool.tot_num_rules;
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		err = mlx5e_ethtool_get_flow(priv, info, info->fs.location);
+		break;
+	case ETHTOOL_GRXCLSRLALL:
+		err = mlx5e_ethtool_get_all_flows(priv, info, rule_locs);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index c592678ab5f1..5a7939e70190 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -45,8 +45,10 @@
 #include "en_accel/tls.h"
 #include "accel/ipsec.h"
 #include "accel/tls.h"
-#include "vxlan.h"
+#include "lib/vxlan.h"
+#include "lib/clock.h"
 #include "en/port.h"
+#include "en/xdp.h"
 
 struct mlx5e_rq_param {
 	u32			rqc[MLX5_ST_SZ_DW(rqc)];
@@ -96,14 +98,19 @@ bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 
 static u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params)
 {
-	if (!params->xdp_prog) {
-		u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
-		u16 rq_headroom = MLX5_RX_HEADROOM + NET_IP_ALIGN;
+	u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+	u16 linear_rq_headroom = params->xdp_prog ?
+		XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM;
+	u32 frag_sz;
 
-		return MLX5_SKB_FRAG_SZ(rq_headroom + hw_mtu);
-	}
+	linear_rq_headroom += NET_IP_ALIGN;
+
+	frag_sz = MLX5_SKB_FRAG_SZ(linear_rq_headroom + hw_mtu);
+
+	if (params->xdp_prog && frag_sz < PAGE_SIZE)
+		frag_sz = PAGE_SIZE;
 
-	return PAGE_SIZE;
+	return frag_sz;
 }
 
 static u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params)
@@ -222,7 +229,7 @@ static void mlx5e_update_carrier(struct mlx5e_priv *priv)
 	u8 port_state;
 
 	port_state = mlx5_query_vport_state(mdev,
-					    MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT,
+					    MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT,
 					    0);
 
 	if (port_state == VPORT_STATE_UP) {
@@ -270,12 +277,9 @@ void mlx5e_update_stats_work(struct work_struct *work)
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlx5e_priv *priv = container_of(dwork, struct mlx5e_priv,
 					       update_stats_work);
+
 	mutex_lock(&priv->state_lock);
-	if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
-		priv->profile->update_stats(priv);
-		queue_delayed_work(priv->wq, dwork,
-				   msecs_to_jiffies(MLX5E_UPDATE_STATS_INTERVAL));
-	}
+	priv->profile->update_stats(priv);
 	mutex_unlock(&priv->state_lock);
 }
 
@@ -352,8 +356,9 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
 {
 	int wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
 
-	rq->mpwqe.info = kcalloc_node(wq_sz, sizeof(*rq->mpwqe.info),
-				      GFP_KERNEL, cpu_to_node(c->cpu));
+	rq->mpwqe.info = kvzalloc_node(array_size(wq_sz,
+						  sizeof(*rq->mpwqe.info)),
+				       GFP_KERNEL, cpu_to_node(c->cpu));
 	if (!rq->mpwqe.info)
 		return -ENOMEM;
 
@@ -487,7 +492,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	rq->channel = c;
 	rq->ix      = c->ix;
 	rq->mdev    = mdev;
-	rq->hw_mtu  = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	rq->stats   = &c->priv->channel_stats[c->ix].rq;
 
 	rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
@@ -670,7 +674,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 err_free:
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		kfree(rq->mpwqe.info);
+		kvfree(rq->mpwqe.info);
 		mlx5_core_destroy_mkey(mdev, &rq->umr_mkey);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
@@ -702,7 +706,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
 
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		kfree(rq->mpwqe.info);
+		kvfree(rq->mpwqe.info);
 		mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
@@ -879,7 +883,7 @@ static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 
 		/* UMR WQE (if in progress) is always at wq->head */
 		if (rq->mpwqe.umr_in_progress)
-			mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]);
+			rq->dealloc_wqe(rq, wq->head);
 
 		while (!mlx5_wq_ll_is_empty(wq)) {
 			struct mlx5e_rx_wqe_ll *wqe;
@@ -965,16 +969,16 @@ static void mlx5e_close_rq(struct mlx5e_rq *rq)
 
 static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq)
 {
-	kfree(sq->db.di);
+	kvfree(sq->db.xdpi);
 }
 
 static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 {
 	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
-	sq->db.di = kcalloc_node(wq_sz, sizeof(*sq->db.di),
-				     GFP_KERNEL, numa);
-	if (!sq->db.di) {
+	sq->db.xdpi = kvzalloc_node(array_size(wq_sz, sizeof(*sq->db.xdpi)),
+				    GFP_KERNEL, numa);
+	if (!sq->db.xdpi) {
 		mlx5e_free_xdpsq_db(sq);
 		return -ENOMEM;
 	}
@@ -985,7 +989,8 @@ static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 			     struct mlx5e_params *params,
 			     struct mlx5e_sq_param *param,
-			     struct mlx5e_xdpsq *sq)
+			     struct mlx5e_xdpsq *sq,
+			     bool is_redirect)
 {
 	void *sqc_wq               = MLX5_ADDR_OF(sqc, param->sqc, wq);
 	struct mlx5_core_dev *mdev = c->mdev;
@@ -997,6 +1002,10 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 	sq->channel   = c;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
+	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+	sq->stats     = is_redirect ?
+		&c->priv->channel_stats[c->ix].xdpsq :
+		&c->priv->channel_stats[c->ix].rq_xdpsq;
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
@@ -1024,15 +1033,16 @@ static void mlx5e_free_xdpsq(struct mlx5e_xdpsq *sq)
 
 static void mlx5e_free_icosq_db(struct mlx5e_icosq *sq)
 {
-	kfree(sq->db.ico_wqe);
+	kvfree(sq->db.ico_wqe);
 }
 
 static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa)
 {
 	u8 wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
-	sq->db.ico_wqe = kcalloc_node(wq_sz, sizeof(*sq->db.ico_wqe),
-				      GFP_KERNEL, numa);
+	sq->db.ico_wqe = kvzalloc_node(array_size(wq_sz,
+						  sizeof(*sq->db.ico_wqe)),
+				       GFP_KERNEL, numa);
 	if (!sq->db.ico_wqe)
 		return -ENOMEM;
 
@@ -1077,8 +1087,8 @@ static void mlx5e_free_icosq(struct mlx5e_icosq *sq)
 
 static void mlx5e_free_txqsq_db(struct mlx5e_txqsq *sq)
 {
-	kfree(sq->db.wqe_info);
-	kfree(sq->db.dma_fifo);
+	kvfree(sq->db.wqe_info);
+	kvfree(sq->db.dma_fifo);
 }
 
 static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
@@ -1086,10 +1096,12 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
 	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 	int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
 
-	sq->db.dma_fifo = kcalloc_node(df_sz, sizeof(*sq->db.dma_fifo),
-					   GFP_KERNEL, numa);
-	sq->db.wqe_info = kcalloc_node(wq_sz, sizeof(*sq->db.wqe_info),
-					   GFP_KERNEL, numa);
+	sq->db.dma_fifo = kvzalloc_node(array_size(df_sz,
+						   sizeof(*sq->db.dma_fifo)),
+					GFP_KERNEL, numa);
+	sq->db.wqe_info = kvzalloc_node(array_size(wq_sz,
+						   sizeof(*sq->db.wqe_info)),
+					GFP_KERNEL, numa);
 	if (!sq->db.dma_fifo || !sq->db.wqe_info) {
 		mlx5e_free_txqsq_db(sq);
 		return -ENOMEM;
@@ -1523,7 +1535,8 @@ static void mlx5e_close_icosq(struct mlx5e_icosq *sq)
 static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 			    struct mlx5e_params *params,
 			    struct mlx5e_sq_param *param,
-			    struct mlx5e_xdpsq *sq)
+			    struct mlx5e_xdpsq *sq,
+			    bool is_redirect)
 {
 	unsigned int ds_cnt = MLX5E_XDP_TX_DS_COUNT;
 	struct mlx5e_create_sq_param csp = {};
@@ -1531,7 +1544,7 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 	int err;
 	int i;
 
-	err = mlx5e_alloc_xdpsq(c, params, param, sq);
+	err = mlx5e_alloc_xdpsq(c, params, param, sq, is_redirect);
 	if (err)
 		return err;
 
@@ -1540,6 +1553,8 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 	csp.cqn             = sq->cq.mcq.cqn;
 	csp.wq_ctrl         = &sq->wq_ctrl;
 	csp.min_inline_mode = sq->min_inline_mode;
+	if (is_redirect)
+		set_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state);
 	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
 	if (err)
@@ -1893,7 +1908,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	int err;
 	int eqn;
 
-	c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
+	c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
 	if (!c)
 		return -ENOMEM;
 
@@ -1922,10 +1937,14 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	if (err)
 		goto err_close_icosq_cq;
 
-	err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rx_cq, &c->rq.cq);
+	err = mlx5e_open_cq(c, params->tx_cq_moderation, &cparam->tx_cq, &c->xdpsq.cq);
 	if (err)
 		goto err_close_tx_cqs;
 
+	err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rx_cq, &c->rq.cq);
+	if (err)
+		goto err_close_xdp_tx_cqs;
+
 	/* XDP SQ CQ params are same as normal TXQ sq CQ params */
 	err = c->xdp ? mlx5e_open_cq(c, params->tx_cq_moderation,
 				     &cparam->tx_cq, &c->rq.xdpsq.cq) : 0;
@@ -1942,7 +1961,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	if (err)
 		goto err_close_icosq;
 
-	err = c->xdp ? mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->rq.xdpsq) : 0;
+	err = c->xdp ? mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->rq.xdpsq, false) : 0;
 	if (err)
 		goto err_close_sqs;
 
@@ -1950,9 +1969,17 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	if (err)
 		goto err_close_xdp_sq;
 
+	err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->xdpsq, true);
+	if (err)
+		goto err_close_rq;
+
 	*cp = c;
 
 	return 0;
+
+err_close_rq:
+	mlx5e_close_rq(&c->rq);
+
 err_close_xdp_sq:
 	if (c->xdp)
 		mlx5e_close_xdpsq(&c->rq.xdpsq);
@@ -1971,6 +1998,9 @@ err_disable_napi:
 err_close_rx_cq:
 	mlx5e_close_cq(&c->rq.cq);
 
+err_close_xdp_tx_cqs:
+	mlx5e_close_cq(&c->xdpsq.cq);
+
 err_close_tx_cqs:
 	mlx5e_close_tx_cqs(c);
 
@@ -1979,7 +2009,7 @@ err_close_icosq_cq:
 
 err_napi_del:
 	netif_napi_del(&c->napi);
-	kfree(c);
+	kvfree(c);
 
 	return err;
 }
@@ -2005,6 +2035,7 @@ static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
 
 static void mlx5e_close_channel(struct mlx5e_channel *c)
 {
+	mlx5e_close_xdpsq(&c->xdpsq);
 	mlx5e_close_rq(&c->rq);
 	if (c->xdp)
 		mlx5e_close_xdpsq(&c->rq.xdpsq);
@@ -2014,11 +2045,12 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
 	if (c->xdp)
 		mlx5e_close_cq(&c->rq.xdpsq.cq);
 	mlx5e_close_cq(&c->rq.cq);
+	mlx5e_close_cq(&c->xdpsq.cq);
 	mlx5e_close_tx_cqs(c);
 	mlx5e_close_cq(&c->icosq.cq);
 	netif_napi_del(&c->napi);
 
-	kfree(c);
+	kvfree(c);
 }
 
 #define DEFAULT_FRAG_SIZE (2048)
@@ -2276,7 +2308,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 	chs->num = chs->params.num_channels;
 
 	chs->c = kcalloc(chs->num, sizeof(struct mlx5e_channel *), GFP_KERNEL);
-	cparam = kzalloc(sizeof(struct mlx5e_channel_param), GFP_KERNEL);
+	cparam = kvzalloc(sizeof(struct mlx5e_channel_param), GFP_KERNEL);
 	if (!chs->c || !cparam)
 		goto err_free;
 
@@ -2287,7 +2319,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 			goto err_close_channels;
 	}
 
-	kfree(cparam);
+	kvfree(cparam);
 	return 0;
 
 err_close_channels:
@@ -2296,7 +2328,7 @@ err_close_channels:
 
 err_free:
 	kfree(chs->c);
-	kfree(cparam);
+	kvfree(cparam);
 	chs->num = 0;
 	return err;
 }
@@ -2943,7 +2975,7 @@ int mlx5e_open(struct net_device *netdev)
 		mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP);
 	mutex_unlock(&priv->state_lock);
 
-	if (mlx5e_vxlan_allowed(priv->mdev))
+	if (mlx5_vxlan_allowed(priv->mdev->vxlan))
 		udp_tunnel_get_rx_info(netdev);
 
 	return err;
@@ -3371,7 +3403,7 @@ static int mlx5e_setup_tc_block(struct net_device *dev,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, mlx5e_setup_tc_block_cb,
-					     priv, priv);
+					     priv, priv, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, mlx5e_setup_tc_block_cb,
 					priv);
@@ -3405,6 +3437,9 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	struct mlx5e_vport_stats *vstats = &priv->stats.vport;
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
 
+	/* update HW stats in background for next time */
+	queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
+
 	if (mlx5e_is_uplink_rep(priv)) {
 		stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok);
 		stats->rx_bytes   = PPORT_802_3_GET(pstats, a_octets_received_ok);
@@ -3590,7 +3625,7 @@ unlock:
 	return err;
 }
 
-#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_EN_ARFS
 static int set_feature_arfs(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -3645,7 +3680,7 @@ static int mlx5e_set_features(struct net_device *netdev,
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXALL, set_feature_rx_all);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXFCS, set_feature_rx_fcs);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_VLAN_CTAG_RX, set_feature_rx_vlan);
-#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_EN_ARFS
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_NTUPLE, set_feature_arfs);
 #endif
 
@@ -3703,6 +3738,14 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 	new_channels.params = *params;
 	new_channels.params.sw_mtu = new_mtu;
 
+	if (params->xdp_prog &&
+	    !mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
+		netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n",
+			   new_mtu, MLX5E_XDP_MAX_MTU);
+		err = -EINVAL;
+		goto out;
+	}
+
 	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
 		u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params);
 		u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params);
@@ -3740,7 +3783,8 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
 	struct hwtstamp_config config;
 	int err;
 
-	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
+	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz) ||
+	    (mlx5_clock_get_ptp_index(priv->mdev) == -1))
 		return -EOPNOTSUPP;
 
 	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
@@ -3874,9 +3918,9 @@ static int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate,
 static int mlx5_vport_link2ifla(u8 esw_link)
 {
 	switch (esw_link) {
-	case MLX5_ESW_VPORT_ADMIN_STATE_DOWN:
+	case MLX5_VPORT_ADMIN_STATE_DOWN:
 		return IFLA_VF_LINK_STATE_DISABLE;
-	case MLX5_ESW_VPORT_ADMIN_STATE_UP:
+	case MLX5_VPORT_ADMIN_STATE_UP:
 		return IFLA_VF_LINK_STATE_ENABLE;
 	}
 	return IFLA_VF_LINK_STATE_AUTO;
@@ -3886,11 +3930,11 @@ static int mlx5_ifla_link2vport(u8 ifla_link)
 {
 	switch (ifla_link) {
 	case IFLA_VF_LINK_STATE_DISABLE:
-		return MLX5_ESW_VPORT_ADMIN_STATE_DOWN;
+		return MLX5_VPORT_ADMIN_STATE_DOWN;
 	case IFLA_VF_LINK_STATE_ENABLE:
-		return MLX5_ESW_VPORT_ADMIN_STATE_UP;
+		return MLX5_VPORT_ADMIN_STATE_UP;
 	}
-	return MLX5_ESW_VPORT_ADMIN_STATE_AUTO;
+	return MLX5_VPORT_ADMIN_STATE_AUTO;
 }
 
 static int mlx5e_set_vf_link_state(struct net_device *dev, int vf,
@@ -3928,6 +3972,57 @@ static int mlx5e_get_vf_stats(struct net_device *dev,
 }
 #endif
 
+struct mlx5e_vxlan_work {
+	struct work_struct	work;
+	struct mlx5e_priv	*priv;
+	u16			port;
+};
+
+static void mlx5e_vxlan_add_work(struct work_struct *work)
+{
+	struct mlx5e_vxlan_work *vxlan_work =
+		container_of(work, struct mlx5e_vxlan_work, work);
+	struct mlx5e_priv *priv = vxlan_work->priv;
+	u16 port = vxlan_work->port;
+
+	mutex_lock(&priv->state_lock);
+	mlx5_vxlan_add_port(priv->mdev->vxlan, port);
+	mutex_unlock(&priv->state_lock);
+
+	kfree(vxlan_work);
+}
+
+static void mlx5e_vxlan_del_work(struct work_struct *work)
+{
+	struct mlx5e_vxlan_work *vxlan_work =
+		container_of(work, struct mlx5e_vxlan_work, work);
+	struct mlx5e_priv *priv         = vxlan_work->priv;
+	u16 port = vxlan_work->port;
+
+	mutex_lock(&priv->state_lock);
+	mlx5_vxlan_del_port(priv->mdev->vxlan, port);
+	mutex_unlock(&priv->state_lock);
+	kfree(vxlan_work);
+}
+
+static void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, u16 port, int add)
+{
+	struct mlx5e_vxlan_work *vxlan_work;
+
+	vxlan_work = kmalloc(sizeof(*vxlan_work), GFP_ATOMIC);
+	if (!vxlan_work)
+		return;
+
+	if (add)
+		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_add_work);
+	else
+		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_del_work);
+
+	vxlan_work->priv = priv;
+	vxlan_work->port = port;
+	queue_work(priv->wq, &vxlan_work->work);
+}
+
 static void mlx5e_add_vxlan_port(struct net_device *netdev,
 				 struct udp_tunnel_info *ti)
 {
@@ -3936,10 +4031,10 @@ static void mlx5e_add_vxlan_port(struct net_device *netdev,
 	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
 		return;
 
-	if (!mlx5e_vxlan_allowed(priv->mdev))
+	if (!mlx5_vxlan_allowed(priv->mdev->vxlan))
 		return;
 
-	mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 1);
+	mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 1);
 }
 
 static void mlx5e_del_vxlan_port(struct net_device *netdev,
@@ -3950,10 +4045,10 @@ static void mlx5e_del_vxlan_port(struct net_device *netdev,
 	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
 		return;
 
-	if (!mlx5e_vxlan_allowed(priv->mdev))
+	if (!mlx5_vxlan_allowed(priv->mdev->vxlan))
 		return;
 
-	mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 0);
+	mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 0);
 }
 
 static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
@@ -3984,7 +4079,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
 		port = be16_to_cpu(udph->dest);
 
 		/* Verify if UDP port is being offloaded by HW */
-		if (mlx5e_vxlan_lookup_port(priv, port))
+		if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, port))
 			return features;
 	}
 
@@ -4091,26 +4186,47 @@ static void mlx5e_tx_timeout(struct net_device *dev)
 	queue_work(priv->wq, &priv->tx_timeout_work);
 }
 
+static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
+{
+	struct net_device *netdev = priv->netdev;
+	struct mlx5e_channels new_channels = {};
+
+	if (priv->channels.params.lro_en) {
+		netdev_warn(netdev, "can't set XDP while LRO is on, disable LRO first\n");
+		return -EINVAL;
+	}
+
+	if (MLX5_IPSEC_DEV(priv->mdev)) {
+		netdev_warn(netdev, "can't set XDP with IPSec offload\n");
+		return -EINVAL;
+	}
+
+	new_channels.params = priv->channels.params;
+	new_channels.params.xdp_prog = prog;
+
+	if (!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
+		netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n",
+			    new_channels.params.sw_mtu, MLX5E_XDP_MAX_MTU);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct bpf_prog *old_prog;
-	int err = 0;
 	bool reset, was_opened;
+	int err = 0;
 	int i;
 
 	mutex_lock(&priv->state_lock);
 
-	if ((netdev->features & NETIF_F_LRO) && prog) {
-		netdev_warn(netdev, "can't set XDP while LRO is on, disable LRO first\n");
-		err = -EINVAL;
-		goto unlock;
-	}
-
-	if ((netdev->features & NETIF_F_HW_ESP) && prog) {
-		netdev_warn(netdev, "can't set XDP with IPSec offload\n");
-		err = -EINVAL;
-		goto unlock;
+	if (prog) {
+		err = mlx5e_xdp_allowed(priv, prog);
+		if (err)
+			goto unlock;
 	}
 
 	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
@@ -4193,7 +4309,6 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		return mlx5e_xdp_set(dev, xdp->prog);
 	case XDP_QUERY_PROG:
 		xdp->prog_id = mlx5e_xdp_query(dev);
-		xdp->prog_attached = !!xdp->prog_id;
 		return 0;
 	default:
 		return -EINVAL;
@@ -4235,11 +4350,12 @@ static const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_udp_tunnel_add      = mlx5e_add_vxlan_port,
 	.ndo_udp_tunnel_del      = mlx5e_del_vxlan_port,
 	.ndo_features_check      = mlx5e_features_check,
-#ifdef CONFIG_RFS_ACCEL
-	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
-#endif
 	.ndo_tx_timeout          = mlx5e_tx_timeout,
 	.ndo_bpf		 = mlx5e_xdp,
+	.ndo_xdp_xmit            = mlx5e_xdp_xmit,
+#ifdef CONFIG_MLX5_EN_ARFS
+	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
+#endif
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller     = mlx5e_netpoll,
 #endif
@@ -4535,8 +4651,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	netdev->hw_features      |= NETIF_F_HW_VLAN_STAG_TX;
 
-	if (mlx5e_vxlan_allowed(mdev) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
-		netdev->hw_features     |= NETIF_F_GSO_PARTIAL;
+	if (mlx5_vxlan_allowed(mdev->vxlan) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
 		netdev->hw_enc_features |= NETIF_F_IP_CSUM;
 		netdev->hw_enc_features |= NETIF_F_IPV6_CSUM;
 		netdev->hw_enc_features |= NETIF_F_TSO;
@@ -4544,7 +4659,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 		netdev->hw_enc_features |= NETIF_F_GSO_PARTIAL;
 	}
 
-	if (mlx5e_vxlan_allowed(mdev)) {
+	if (mlx5_vxlan_allowed(mdev->vxlan)) {
 		netdev->hw_features     |= NETIF_F_GSO_UDP_TUNNEL |
 					   NETIF_F_GSO_UDP_TUNNEL_CSUM;
 		netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL |
@@ -4561,6 +4676,11 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 						NETIF_F_GSO_GRE_CSUM;
 	}
 
+	netdev->hw_features	                 |= NETIF_F_GSO_PARTIAL;
+	netdev->gso_partial_features             |= NETIF_F_GSO_UDP_L4;
+	netdev->hw_features                      |= NETIF_F_GSO_UDP_L4;
+	netdev->features                         |= NETIF_F_GSO_UDP_L4;
+
 	mlx5_query_port_fcs(mdev, &fcs_supported, &fcs_enabled);
 
 	if (fcs_supported)
@@ -4585,7 +4705,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	    FT_CAP(identified_miss_table_mode) &&
 	    FT_CAP(flow_table_modify)) {
 		netdev->hw_features      |= NETIF_F_HW_TC;
-#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_EN_ARFS
 		netdev->hw_features	 |= NETIF_F_NTUPLE;
 #endif
 	}
@@ -4650,14 +4770,12 @@ static void mlx5e_nic_init(struct mlx5_core_dev *mdev,
 		mlx5_core_err(mdev, "TLS initialization failed, %d\n", err);
 	mlx5e_build_nic_netdev(netdev);
 	mlx5e_build_tc2txq_maps(priv);
-	mlx5e_vxlan_init(priv);
 }
 
 static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 {
 	mlx5e_tls_cleanup(priv);
 	mlx5e_ipsec_cleanup(priv);
-	mlx5e_vxlan_cleanup(priv);
 }
 
 static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
@@ -4831,7 +4949,7 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
 		return NULL;
 	}
 
-#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_EN_ARFS
 	netdev->rx_cpu_rmap = mdev->rmap;
 #endif
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 2b8040a3cdbd..c9cc9747d21d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -698,8 +698,8 @@ static int mlx5e_rep_open(struct net_device *dev)
 		goto unlock;
 
 	if (!mlx5_modify_vport_admin_state(priv->mdev,
-					   MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
-					   rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP))
+					   MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
+					   rep->vport, MLX5_VPORT_ADMIN_STATE_UP))
 		netif_carrier_on(dev);
 
 unlock:
@@ -716,8 +716,8 @@ static int mlx5e_rep_close(struct net_device *dev)
 
 	mutex_lock(&priv->state_lock);
 	mlx5_modify_vport_admin_state(priv->mdev,
-				      MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
-				      rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
+				      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
+				      rep->vport, MLX5_VPORT_ADMIN_STATE_DOWN);
 	ret = mlx5e_close_locked(dev);
 	mutex_unlock(&priv->state_lock);
 	return ret;
@@ -797,7 +797,7 @@ static int mlx5e_rep_setup_tc_block(struct net_device *dev,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, mlx5e_rep_setup_tc_cb,
-					     priv, priv);
+					     priv, priv, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, mlx5e_rep_setup_tc_cb, priv);
 		return 0;
@@ -897,6 +897,9 @@ mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
+	/* update HW stats in background for next time */
+	queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
+
 	memcpy(stats, &priv->stats.vf_vport, sizeof(*stats));
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index d3a1dd20e41d..15d8ae28c040 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -34,7 +34,6 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/tcp.h>
-#include <linux/bpf_trace.h>
 #include <net/busy_poll.h>
 #include <net/ip6_checksum.h>
 #include <net/page_pool.h>
@@ -44,7 +43,9 @@
 #include "en_rep.h"
 #include "ipoib/ipoib.h"
 #include "en_accel/ipsec_rxtx.h"
+#include "en_accel/tls_rxtx.h"
 #include "lib/clock.h"
+#include "en/xdp.h"
 
 static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
 {
@@ -238,8 +239,7 @@ static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq,
 	return 0;
 }
 
-static void mlx5e_page_dma_unmap(struct mlx5e_rq *rq,
-					struct mlx5e_dma_info *dma_info)
+void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info)
 {
 	dma_unmap_page(rq->pdev, dma_info->addr, PAGE_SIZE, rq->buff.map_dir);
 }
@@ -276,10 +276,11 @@ static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
 }
 
 static inline void mlx5e_put_rx_frag(struct mlx5e_rq *rq,
-				     struct mlx5e_wqe_frag_info *frag)
+				     struct mlx5e_wqe_frag_info *frag,
+				     bool recycle)
 {
 	if (frag->last_in_page)
-		mlx5e_page_release(rq, frag->di, true);
+		mlx5e_page_release(rq, frag->di, recycle);
 }
 
 static inline struct mlx5e_wqe_frag_info *get_frag(struct mlx5e_rq *rq, u16 ix)
@@ -307,25 +308,26 @@ static int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe_cyc *wqe,
 
 free_frags:
 	while (--i >= 0)
-		mlx5e_put_rx_frag(rq, --frag);
+		mlx5e_put_rx_frag(rq, --frag, true);
 
 	return err;
 }
 
 static inline void mlx5e_free_rx_wqe(struct mlx5e_rq *rq,
-				     struct mlx5e_wqe_frag_info *wi)
+				     struct mlx5e_wqe_frag_info *wi,
+				     bool recycle)
 {
 	int i;
 
 	for (i = 0; i < rq->wqe.info.num_frags; i++, wi++)
-		mlx5e_put_rx_frag(rq, wi);
+		mlx5e_put_rx_frag(rq, wi, recycle);
 }
 
 void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
 {
 	struct mlx5e_wqe_frag_info *wi = get_frag(rq, ix);
 
-	mlx5e_free_rx_wqe(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi, false);
 }
 
 static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk)
@@ -395,7 +397,8 @@ mlx5e_copy_skb_header_mpwqe(struct device *pdev,
 	}
 }
 
-void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
+static void
+mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, bool recycle)
 {
 	const bool no_xdp_xmit =
 		bitmap_empty(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
@@ -404,7 +407,7 @@ void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
 
 	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++)
 		if (no_xdp_xmit || !test_bit(i, wi->xdp_xmit_bitmap))
-			mlx5e_page_release(rq, &dma_info[i], true);
+			mlx5e_page_release(rq, &dma_info[i], recycle);
 }
 
 static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
@@ -487,7 +490,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 
 	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
 	sq->pc += MLX5E_UMR_WQEBBS;
-	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &umr_wqe->ctrl);
+	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &umr_wqe->ctrl);
 
 	return 0;
 
@@ -504,8 +507,8 @@ err_unmap:
 void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 {
 	struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
-
-	mlx5e_free_rx_mpwqe(rq, wi);
+	/* Don't recycle, this function is called on rq/netdev close */
+	mlx5e_free_rx_mpwqe(rq, wi, false);
 }
 
 bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
@@ -601,6 +604,8 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 
 	if (!rq->mpwqe.umr_in_progress)
 		mlx5e_alloc_rx_mpwqe(rq, wq->head);
+	else
+		rq->stats->congst_umr += mlx5_wq_ll_missing(wq) > 2;
 
 	return false;
 }
@@ -795,6 +800,11 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 	struct net_device *netdev = rq->netdev;
 
 	skb->mac_len = ETH_HLEN;
+
+#ifdef CONFIG_MLX5_EN_TLS
+	mlx5e_tls_handle_rx_skb(netdev, skb, &cqe_bcnt);
+#endif
+
 	if (lro_num_seg > 1) {
 		mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
 		skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg);
@@ -839,135 +849,6 @@ static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq,
 	mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb);
 }
 
-static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
-{
-	struct mlx5_wq_cyc *wq = &sq->wq;
-	struct mlx5e_tx_wqe *wqe;
-	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc - 1); /* last pi */
-
-	wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
-
-	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &wqe->ctrl);
-}
-
-static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq,
-					struct mlx5e_dma_info *di,
-					const struct xdp_buff *xdp)
-{
-	struct mlx5e_xdpsq       *sq   = &rq->xdpsq;
-	struct mlx5_wq_cyc       *wq   = &sq->wq;
-	u16                       pi   = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-	struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
-
-	struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
-	struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
-	struct mlx5_wqe_data_seg *dseg;
-
-	ptrdiff_t data_offset = xdp->data - xdp->data_hard_start;
-	dma_addr_t dma_addr  = di->addr + data_offset;
-	unsigned int dma_len = xdp->data_end - xdp->data;
-
-	struct mlx5e_rq_stats *stats = rq->stats;
-
-	prefetchw(wqe);
-
-	if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE || rq->hw_mtu < dma_len)) {
-		stats->xdp_drop++;
-		return false;
-	}
-
-	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) {
-		if (sq->db.doorbell) {
-			/* SQ is full, ring doorbell */
-			mlx5e_xmit_xdp_doorbell(sq);
-			sq->db.doorbell = false;
-		}
-		stats->xdp_tx_full++;
-		return false;
-	}
-
-	dma_sync_single_for_device(sq->pdev, dma_addr, dma_len, PCI_DMA_TODEVICE);
-
-	cseg->fm_ce_se = 0;
-
-	dseg = (struct mlx5_wqe_data_seg *)eseg + 1;
-
-	/* copy the inline part if required */
-	if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
-		memcpy(eseg->inline_hdr.start, xdp->data, MLX5E_XDP_MIN_INLINE);
-		eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE);
-		dma_len  -= MLX5E_XDP_MIN_INLINE;
-		dma_addr += MLX5E_XDP_MIN_INLINE;
-		dseg++;
-	}
-
-	/* write the dma part */
-	dseg->addr       = cpu_to_be64(dma_addr);
-	dseg->byte_count = cpu_to_be32(dma_len);
-
-	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND);
-
-	/* move page to reference to sq responsibility,
-	 * and mark so it's not put back in page-cache.
-	 */
-	__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
-	sq->db.di[pi] = *di;
-	sq->pc++;
-
-	sq->db.doorbell = true;
-
-	stats->xdp_tx++;
-	return true;
-}
-
-/* returns true if packet was consumed by xdp */
-static inline bool mlx5e_xdp_handle(struct mlx5e_rq *rq,
-				    struct mlx5e_dma_info *di,
-				    void *va, u16 *rx_headroom, u32 *len)
-{
-	struct bpf_prog *prog = READ_ONCE(rq->xdp_prog);
-	struct xdp_buff xdp;
-	u32 act;
-	int err;
-
-	if (!prog)
-		return false;
-
-	xdp.data = va + *rx_headroom;
-	xdp_set_data_meta_invalid(&xdp);
-	xdp.data_end = xdp.data + *len;
-	xdp.data_hard_start = va;
-	xdp.rxq = &rq->xdp_rxq;
-
-	act = bpf_prog_run_xdp(prog, &xdp);
-	switch (act) {
-	case XDP_PASS:
-		*rx_headroom = xdp.data - xdp.data_hard_start;
-		*len = xdp.data_end - xdp.data;
-		return false;
-	case XDP_TX:
-		if (unlikely(!mlx5e_xmit_xdp_frame(rq, di, &xdp)))
-			trace_xdp_exception(rq->netdev, prog, act);
-		return true;
-	case XDP_REDIRECT:
-		/* When XDP enabled then page-refcnt==1 here */
-		err = xdp_do_redirect(rq->netdev, &xdp, prog);
-		if (!err) {
-			__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags);
-			rq->xdpsq.db.redirect_flush = true;
-			mlx5e_page_dma_unmap(rq, di);
-		}
-		return true;
-	default:
-		bpf_warn_invalid_xdp_action(act);
-	case XDP_ABORTED:
-		trace_xdp_exception(rq->netdev, prog, act);
-	case XDP_DROP:
-		rq->stats->xdp_drop++;
-		return true;
-	}
-}
-
 static inline
 struct sk_buff *mlx5e_build_linear_skb(struct mlx5e_rq *rq, void *va,
 				       u32 frag_size, u16 headroom,
@@ -1105,7 +986,7 @@ void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	napi_gro_receive(rq->cq.napi, skb);
 
 free_wqe:
-	mlx5e_free_rx_wqe(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi, true);
 wq_cyc_pop:
 	mlx5_wq_cyc_pop(wq);
 }
@@ -1147,7 +1028,7 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	napi_gro_receive(rq->cq.napi, skb);
 
 free_wqe:
-	mlx5e_free_rx_wqe(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi, true);
 wq_cyc_pop:
 	mlx5_wq_cyc_pop(wq);
 }
@@ -1218,6 +1099,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 
 	dma_sync_single_range_for_cpu(rq->pdev, di->addr, head_offset,
 				      frag_size, DMA_FROM_DEVICE);
+	prefetchw(va); /* xdp_frame data area */
 	prefetch(data);
 
 	rcu_read_lock();
@@ -1261,7 +1143,10 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	}
 
 	if (unlikely(mpwrq_is_filler_cqe(cqe))) {
-		rq->stats->mpwqe_filler++;
+		struct mlx5e_rq_stats *stats = rq->stats;
+
+		stats->mpwqe_filler_cqes++;
+		stats->mpwqe_filler_strides += cstrides;
 		goto mpwrq_cqe_out;
 	}
 
@@ -1281,7 +1166,7 @@ mpwrq_cqe_out:
 
 	wq  = &rq->mpwqe.wq;
 	wqe = mlx5_wq_ll_get_wqe(wq, wqe_id);
-	mlx5e_free_rx_mpwqe(rq, wi);
+	mlx5e_free_rx_mpwqe(rq, wi, true);
 	mlx5_wq_ll_pop(wq, cqe->wqe_id, &wqe->next.next_wqe_index);
 }
 
@@ -1317,14 +1202,14 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 		rq->handle_rx_cqe(rq, cqe);
 	} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
-	if (xdpsq->db.doorbell) {
+	if (xdpsq->doorbell) {
 		mlx5e_xmit_xdp_doorbell(xdpsq);
-		xdpsq->db.doorbell = false;
+		xdpsq->doorbell = false;
 	}
 
-	if (xdpsq->db.redirect_flush) {
+	if (xdpsq->redirect_flush) {
 		xdp_do_flush_map();
-		xdpsq->db.redirect_flush = false;
+		xdpsq->redirect_flush = false;
 	}
 
 	mlx5_cqwq_update_db_record(&cq->wq);
@@ -1335,78 +1220,6 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	return work_done;
 }
 
-bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
-{
-	struct mlx5e_xdpsq *sq;
-	struct mlx5_cqe64 *cqe;
-	struct mlx5e_rq *rq;
-	u16 sqcc;
-	int i;
-
-	sq = container_of(cq, struct mlx5e_xdpsq, cq);
-
-	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
-		return false;
-
-	cqe = mlx5_cqwq_get_cqe(&cq->wq);
-	if (!cqe)
-		return false;
-
-	rq = container_of(sq, struct mlx5e_rq, xdpsq);
-
-	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
-	 * otherwise a cq overrun may occur
-	 */
-	sqcc = sq->cc;
-
-	i = 0;
-	do {
-		u16 wqe_counter;
-		bool last_wqe;
-
-		mlx5_cqwq_pop(&cq->wq);
-
-		wqe_counter = be16_to_cpu(cqe->wqe_counter);
-
-		do {
-			struct mlx5e_dma_info *di;
-			u16 ci;
-
-			last_wqe = (sqcc == wqe_counter);
-
-			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
-			di = &sq->db.di[ci];
-
-			sqcc++;
-			/* Recycle RX page */
-			mlx5e_page_release(rq, di, true);
-		} while (!last_wqe);
-	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
-
-	mlx5_cqwq_update_db_record(&cq->wq);
-
-	/* ensure cq space is freed before enabling more cqes */
-	wmb();
-
-	sq->cc = sqcc;
-	return (i == MLX5E_TX_CQ_POLL_BUDGET);
-}
-
-void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
-{
-	struct mlx5e_rq *rq = container_of(sq, struct mlx5e_rq, xdpsq);
-	struct mlx5e_dma_info *di;
-	u16 ci;
-
-	while (sq->cc != sq->pc) {
-		ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
-		di = &sq->db.di[ci];
-		sq->cc++;
-
-		mlx5e_page_release(rq, di, false);
-	}
-}
-
 #ifdef CONFIG_MLX5_CORE_IPOIB
 
 #define MLX5_IB_GRH_DGID_OFFSET 24
@@ -1508,7 +1321,7 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	napi_gro_receive(rq->cq.napi, skb);
 
 wq_free_wqe:
-	mlx5e_free_rx_wqe(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi, true);
 	mlx5_wq_cyc_pop(wq);
 }
 
@@ -1531,19 +1344,19 @@ void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt);
 	if (unlikely(!skb)) {
 		/* a DROP, save the page-reuse checks */
-		mlx5e_free_rx_wqe(rq, wi);
+		mlx5e_free_rx_wqe(rq, wi, true);
 		goto wq_cyc_pop;
 	}
-	skb = mlx5e_ipsec_handle_rx_skb(rq->netdev, skb);
+	skb = mlx5e_ipsec_handle_rx_skb(rq->netdev, skb, &cqe_bcnt);
 	if (unlikely(!skb)) {
-		mlx5e_free_rx_wqe(rq, wi);
+		mlx5e_free_rx_wqe(rq, wi, true);
 		goto wq_cyc_pop;
 	}
 
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
 	napi_gro_receive(rq->cq.napi, skb);
 
-	mlx5e_free_rx_wqe(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi, true);
 wq_cyc_pop:
 	mlx5_wq_cyc_pop(wq);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 4d316cc9b008..35ded91203f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -74,7 +74,7 @@ static int mlx5e_test_link_state(struct mlx5e_priv *priv)
 	if (!netif_carrier_ok(priv->netdev))
 		return 1;
 
-	port_state = mlx5_query_vport_state(priv->mdev, MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT, 0);
+	port_state = mlx5_query_vport_state(priv->mdev, MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT, 0);
 	return port_state == VPORT_STATE_UP ? 0 : 1;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 1646859974ce..12fdf5c92b67 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -44,6 +44,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_added_vlan_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_nop) },
 
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) },
@@ -58,8 +59,11 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_redirect) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_xmit) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_none) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) },
@@ -67,10 +71,17 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_recover) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_udp_seg_rem) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_xmit) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_full) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_cqes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_cqes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_strides) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) },
@@ -80,6 +91,11 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_empty) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_congst_umr) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_events) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_aff_change) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_eq_rearm) },
 };
 
@@ -118,6 +134,8 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 	for (i = 0; i < priv->profile->max_nch(priv->mdev); i++) {
 		struct mlx5e_channel_stats *channel_stats =
 			&priv->channel_stats[i];
+		struct mlx5e_xdpsq_stats *xdpsq_red_stats = &channel_stats->xdpsq;
+		struct mlx5e_xdpsq_stats *xdpsq_stats = &channel_stats->rq_xdpsq;
 		struct mlx5e_rq_stats *rq_stats = &channel_stats->rq;
 		struct mlx5e_ch_stats *ch_stats = &channel_stats->ch;
 		int j;
@@ -131,11 +149,15 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_csum_complete += rq_stats->csum_complete;
 		s->rx_csum_unnecessary += rq_stats->csum_unnecessary;
 		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
-		s->rx_xdp_drop += rq_stats->xdp_drop;
-		s->rx_xdp_tx += rq_stats->xdp_tx;
-		s->rx_xdp_tx_full += rq_stats->xdp_tx_full;
+		s->rx_xdp_drop     += rq_stats->xdp_drop;
+		s->rx_xdp_redirect += rq_stats->xdp_redirect;
+		s->rx_xdp_tx_xmit  += xdpsq_stats->xmit;
+		s->rx_xdp_tx_full  += xdpsq_stats->full;
+		s->rx_xdp_tx_err   += xdpsq_stats->err;
+		s->rx_xdp_tx_cqe   += xdpsq_stats->cqes;
 		s->rx_wqe_err   += rq_stats->wqe_err;
-		s->rx_mpwqe_filler += rq_stats->mpwqe_filler;
+		s->rx_mpwqe_filler_cqes    += rq_stats->mpwqe_filler_cqes;
+		s->rx_mpwqe_filler_strides += rq_stats->mpwqe_filler_strides;
 		s->rx_buff_alloc_err += rq_stats->buff_alloc_err;
 		s->rx_cqe_compress_blks += rq_stats->cqe_compress_blks;
 		s->rx_cqe_compress_pkts += rq_stats->cqe_compress_pkts;
@@ -145,7 +167,17 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_cache_empty += rq_stats->cache_empty;
 		s->rx_cache_busy  += rq_stats->cache_busy;
 		s->rx_cache_waive += rq_stats->cache_waive;
-		s->ch_eq_rearm += ch_stats->eq_rearm;
+		s->rx_congst_umr  += rq_stats->congst_umr;
+		s->ch_events      += ch_stats->events;
+		s->ch_poll        += ch_stats->poll;
+		s->ch_arm         += ch_stats->arm;
+		s->ch_aff_change  += ch_stats->aff_change;
+		s->ch_eq_rearm    += ch_stats->eq_rearm;
+		/* xdp redirect */
+		s->tx_xdp_xmit    += xdpsq_red_stats->xmit;
+		s->tx_xdp_full    += xdpsq_red_stats->full;
+		s->tx_xdp_err     += xdpsq_red_stats->err;
+		s->tx_xdp_cqes    += xdpsq_red_stats->cqes;
 
 		for (j = 0; j < priv->max_opened_tc; j++) {
 			struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j];
@@ -157,8 +189,10 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			s->tx_tso_inner_packets	+= sq_stats->tso_inner_packets;
 			s->tx_tso_inner_bytes	+= sq_stats->tso_inner_bytes;
 			s->tx_added_vlan_packets += sq_stats->added_vlan_packets;
+			s->tx_nop               += sq_stats->nop;
 			s->tx_queue_stopped	+= sq_stats->stopped;
 			s->tx_queue_wake	+= sq_stats->wake;
+			s->tx_udp_seg_rem	+= sq_stats->udp_seg_rem;
 			s->tx_queue_dropped	+= sq_stats->dropped;
 			s->tx_cqe_err		+= sq_stats->cqe_err;
 			s->tx_recover		+= sq_stats->recover;
@@ -170,6 +204,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			s->tx_tls_ooo		+= sq_stats->tls_ooo;
 			s->tx_tls_resync_bytes	+= sq_stats->tls_resync_bytes;
 #endif
+			s->tx_cqes		+= sq_stats->cqes;
 		}
 	}
 
@@ -1106,13 +1141,13 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_drop) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_full) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_redirect) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, removed_vlan_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_cqes) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_strides) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
@@ -1122,6 +1157,7 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_empty) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_busy) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, congst_umr) },
 };
 
 static const struct counter_desc sq_stats_desc[] = {
@@ -1140,16 +1176,37 @@ static const struct counter_desc sq_stats_desc[] = {
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, xmit_more) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, recover) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqes) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqe_err) },
 };
 
+static const struct counter_desc rq_xdpsq_stats_desc[] = {
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) },
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) },
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
+};
+
+static const struct counter_desc xdpsq_stats_desc[] = {
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) },
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) },
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
+};
+
 static const struct counter_desc ch_stats_desc[] = {
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, events) },
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, poll) },
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, arm) },
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, aff_change) },
 	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, eq_rearm) },
 };
 
 #define NUM_RQ_STATS			ARRAY_SIZE(rq_stats_desc)
 #define NUM_SQ_STATS			ARRAY_SIZE(sq_stats_desc)
+#define NUM_XDPSQ_STATS			ARRAY_SIZE(xdpsq_stats_desc)
+#define NUM_RQ_XDPSQ_STATS		ARRAY_SIZE(rq_xdpsq_stats_desc)
 #define NUM_CH_STATS			ARRAY_SIZE(ch_stats_desc)
 
 static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv)
@@ -1158,7 +1215,9 @@ static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv)
 
 	return (NUM_RQ_STATS * max_nch) +
 	       (NUM_CH_STATS * max_nch) +
-	       (NUM_SQ_STATS * max_nch * priv->max_opened_tc);
+	       (NUM_SQ_STATS * max_nch * priv->max_opened_tc) +
+	       (NUM_RQ_XDPSQ_STATS * max_nch) +
+	       (NUM_XDPSQ_STATS * max_nch);
 }
 
 static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
@@ -1172,9 +1231,14 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
 			sprintf(data + (idx++) * ETH_GSTRING_LEN,
 				ch_stats_desc[j].format, i);
 
-	for (i = 0; i < max_nch; i++)
+	for (i = 0; i < max_nch; i++) {
 		for (j = 0; j < NUM_RQ_STATS; j++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN, rq_stats_desc[j].format, i);
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				rq_stats_desc[j].format, i);
+		for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++)
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				rq_xdpsq_stats_desc[j].format, i);
+	}
 
 	for (tc = 0; tc < priv->max_opened_tc; tc++)
 		for (i = 0; i < max_nch; i++)
@@ -1183,6 +1247,11 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
 					sq_stats_desc[j].format,
 					priv->channel_tc2txq[i][tc]);
 
+	for (i = 0; i < max_nch; i++)
+		for (j = 0; j < NUM_XDPSQ_STATS; j++)
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				xdpsq_stats_desc[j].format, i);
+
 	return idx;
 }
 
@@ -1198,11 +1267,16 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
 				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].ch,
 						     ch_stats_desc, j);
 
-	for (i = 0; i < max_nch; i++)
+	for (i = 0; i < max_nch; i++) {
 		for (j = 0; j < NUM_RQ_STATS; j++)
 			data[idx++] =
 				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq,
 						     rq_stats_desc, j);
+		for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++)
+			data[idx++] =
+				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq_xdpsq,
+						     rq_xdpsq_stats_desc, j);
+	}
 
 	for (tc = 0; tc < priv->max_opened_tc; tc++)
 		for (i = 0; i < max_nch; i++)
@@ -1211,6 +1285,12 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
 					MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].sq[tc],
 							     sq_stats_desc, j);
 
+	for (i = 0; i < max_nch; i++)
+		for (j = 0; j < NUM_XDPSQ_STATS; j++)
+			data[idx++] =
+				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].xdpsq,
+						     xdpsq_stats_desc, j);
+
 	return idx;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 643153bb3607..a4c035aedd46 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -44,6 +44,8 @@
 #define MLX5E_DECLARE_STAT(type, fld) #fld, offsetof(type, fld)
 #define MLX5E_DECLARE_RX_STAT(type, fld) "rx%d_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_TX_STAT(type, fld) "tx%d_"#fld, offsetof(type, fld)
+#define MLX5E_DECLARE_XDPSQ_STAT(type, fld) "tx%d_xdp_"#fld, offsetof(type, fld)
+#define MLX5E_DECLARE_RQ_XDPSQ_STAT(type, fld) "rx%d_xdp_tx_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_CH_STAT(type, fld) "ch%d_"#fld, offsetof(type, fld)
 
 struct counter_desc {
@@ -61,6 +63,7 @@ struct mlx5e_sw_stats {
 	u64 tx_tso_inner_packets;
 	u64 tx_tso_inner_bytes;
 	u64 tx_added_vlan_packets;
+	u64 tx_nop;
 	u64 rx_lro_packets;
 	u64 rx_lro_bytes;
 	u64 rx_removed_vlan_packets;
@@ -69,8 +72,11 @@ struct mlx5e_sw_stats {
 	u64 rx_csum_complete;
 	u64 rx_csum_unnecessary_inner;
 	u64 rx_xdp_drop;
-	u64 rx_xdp_tx;
+	u64 rx_xdp_redirect;
+	u64 rx_xdp_tx_xmit;
 	u64 rx_xdp_tx_full;
+	u64 rx_xdp_tx_err;
+	u64 rx_xdp_tx_cqe;
 	u64 tx_csum_none;
 	u64 tx_csum_partial;
 	u64 tx_csum_partial_inner;
@@ -78,10 +84,17 @@ struct mlx5e_sw_stats {
 	u64 tx_queue_dropped;
 	u64 tx_xmit_more;
 	u64 tx_recover;
+	u64 tx_cqes;
 	u64 tx_queue_wake;
+	u64 tx_udp_seg_rem;
 	u64 tx_cqe_err;
+	u64 tx_xdp_xmit;
+	u64 tx_xdp_full;
+	u64 tx_xdp_err;
+	u64 tx_xdp_cqes;
 	u64 rx_wqe_err;
-	u64 rx_mpwqe_filler;
+	u64 rx_mpwqe_filler_cqes;
+	u64 rx_mpwqe_filler_strides;
 	u64 rx_buff_alloc_err;
 	u64 rx_cqe_compress_blks;
 	u64 rx_cqe_compress_pkts;
@@ -91,6 +104,11 @@ struct mlx5e_sw_stats {
 	u64 rx_cache_empty;
 	u64 rx_cache_busy;
 	u64 rx_cache_waive;
+	u64 rx_congst_umr;
+	u64 ch_events;
+	u64 ch_poll;
+	u64 ch_arm;
+	u64 ch_aff_change;
 	u64 ch_eq_rearm;
 
 #ifdef CONFIG_MLX5_EN_TLS
@@ -168,10 +186,10 @@ struct mlx5e_rq_stats {
 	u64 lro_bytes;
 	u64 removed_vlan_packets;
 	u64 xdp_drop;
-	u64 xdp_tx;
-	u64 xdp_tx_full;
+	u64 xdp_redirect;
 	u64 wqe_err;
-	u64 mpwqe_filler;
+	u64 mpwqe_filler_cqes;
+	u64 mpwqe_filler_strides;
 	u64 buff_alloc_err;
 	u64 cqe_compress_blks;
 	u64 cqe_compress_pkts;
@@ -181,6 +199,7 @@ struct mlx5e_rq_stats {
 	u64 cache_empty;
 	u64 cache_busy;
 	u64 cache_waive;
+	u64 congst_umr;
 };
 
 struct mlx5e_sq_stats {
@@ -196,6 +215,7 @@ struct mlx5e_sq_stats {
 	u64 csum_partial_inner;
 	u64 added_vlan_packets;
 	u64 nop;
+	u64 udp_seg_rem;
 #ifdef CONFIG_MLX5_EN_TLS
 	u64 tls_ooo;
 	u64 tls_resync_bytes;
@@ -206,11 +226,24 @@ struct mlx5e_sq_stats {
 	u64 dropped;
 	u64 recover;
 	/* dirtied @completion */
-	u64 wake ____cacheline_aligned_in_smp;
+	u64 cqes ____cacheline_aligned_in_smp;
+	u64 wake;
 	u64 cqe_err;
 };
 
+struct mlx5e_xdpsq_stats {
+	u64 xmit;
+	u64 full;
+	u64 err;
+	/* dirtied @completion */
+	u64 cqes ____cacheline_aligned_in_smp;
+};
+
 struct mlx5e_ch_stats {
+	u64 events;
+	u64 poll;
+	u64 arm;
+	u64 aff_change;
 	u64 eq_rearm;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index dfbcda0d0e08..9131a1376e7d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -50,7 +50,7 @@
 #include "en_rep.h"
 #include "en_tc.h"
 #include "eswitch.h"
-#include "vxlan.h"
+#include "lib/vxlan.h"
 #include "fs_core.h"
 #include "en/port.h"
 
@@ -1032,10 +1032,8 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 		 * dst ip pair
 		 */
 		n = neigh_lookup(tbl, &m_neigh->dst_ip, m_neigh->dev);
-		if (!n) {
-			WARN(1, "The neighbour already freed\n");
+		if (!n)
 			return;
-		}
 
 		neigh_event_send(n, NULL);
 		neigh_release(n);
@@ -1126,16 +1124,12 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 			skb_flow_dissector_target(f->dissector,
 						  FLOW_DISSECTOR_KEY_ENC_PORTS,
 						  f->mask);
-		struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-		struct mlx5e_rep_priv *uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-		struct net_device *up_dev = uplink_rpriv->netdev;
-		struct mlx5e_priv *up_priv = netdev_priv(up_dev);
 
 		/* Full udp dst port must be given */
 		if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst)))
 			goto vxlan_match_offload_err;
 
-		if (mlx5e_vxlan_lookup_port(up_priv, be16_to_cpu(key->dst)) &&
+		if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->dst)) &&
 		    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
 			parse_vxlan_attr(spec, f);
 		else {
@@ -1213,6 +1207,26 @@ vxlan_match_offload_err:
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IPV6);
 	}
 
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_IP)) {
+		struct flow_dissector_key_ip *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_ENC_IP,
+						  f->key);
+		struct flow_dissector_key_ip *mask =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_ENC_IP,
+						  f->mask);
+
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn, mask->tos & 0x3);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, key->tos & 0x3);
+
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp, mask->tos >> 2);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, key->tos  >> 2);
+
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, mask->ttl);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, key->ttl);
+	}
+
 	/* Enforce DMAC when offloading incoming tunneled flows.
 	 * Flow counters require a match on the DMAC.
 	 */
@@ -1237,6 +1251,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 				       outer_headers);
 	void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				       outer_headers);
+	void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    misc_parameters);
+	void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    misc_parameters);
 	u16 addr_type = 0;
 	u8 ip_proto = 0;
 
@@ -1247,6 +1265,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT(FLOW_DISSECTOR_KEY_CVLAN) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
@@ -1256,7 +1275,8 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 	      BIT(FLOW_DISSECTOR_KEY_ENC_PORTS)	|
 	      BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_TCP) |
-	      BIT(FLOW_DISSECTOR_KEY_IP))) {
+	      BIT(FLOW_DISSECTOR_KEY_IP)  |
+	      BIT(FLOW_DISSECTOR_KEY_ENC_IP))) {
 		netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n",
 			    f->dissector->used_keys);
 		return -EOPNOTSUPP;
@@ -1327,9 +1347,18 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			skb_flow_dissector_target(f->dissector,
 						  FLOW_DISSECTOR_KEY_VLAN,
 						  f->mask);
-		if (mask->vlan_id || mask->vlan_priority) {
-			MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
-			MLX5_SET(fte_match_set_lyr_2_4, headers_v, cvlan_tag, 1);
+		if (mask->vlan_id || mask->vlan_priority || mask->vlan_tpid) {
+			if (key->vlan_tpid == htons(ETH_P_8021AD)) {
+				MLX5_SET(fte_match_set_lyr_2_4, headers_c,
+					 svlan_tag, 1);
+				MLX5_SET(fte_match_set_lyr_2_4, headers_v,
+					 svlan_tag, 1);
+			} else {
+				MLX5_SET(fte_match_set_lyr_2_4, headers_c,
+					 cvlan_tag, 1);
+				MLX5_SET(fte_match_set_lyr_2_4, headers_v,
+					 cvlan_tag, 1);
+			}
 
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, mask->vlan_id);
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, key->vlan_id);
@@ -1341,6 +1370,41 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		}
 	}
 
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CVLAN)) {
+		struct flow_dissector_key_vlan *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_CVLAN,
+						  f->key);
+		struct flow_dissector_key_vlan *mask =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_CVLAN,
+						  f->mask);
+		if (mask->vlan_id || mask->vlan_priority || mask->vlan_tpid) {
+			if (key->vlan_tpid == htons(ETH_P_8021AD)) {
+				MLX5_SET(fte_match_set_misc, misc_c,
+					 outer_second_svlan_tag, 1);
+				MLX5_SET(fte_match_set_misc, misc_v,
+					 outer_second_svlan_tag, 1);
+			} else {
+				MLX5_SET(fte_match_set_misc, misc_c,
+					 outer_second_cvlan_tag, 1);
+				MLX5_SET(fte_match_set_misc, misc_v,
+					 outer_second_cvlan_tag, 1);
+			}
+
+			MLX5_SET(fte_match_set_misc, misc_c, outer_second_vid,
+				 mask->vlan_id);
+			MLX5_SET(fte_match_set_misc, misc_v, outer_second_vid,
+				 key->vlan_id);
+			MLX5_SET(fte_match_set_misc, misc_c, outer_second_prio,
+				 mask->vlan_priority);
+			MLX5_SET(fte_match_set_misc, misc_v, outer_second_prio,
+				 key->vlan_priority);
+
+			*match_level = MLX5_MATCH_L2;
+		}
+	}
+
 	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
 		struct flow_dissector_key_basic *key =
 			skb_flow_dissector_target(f->dissector,
@@ -2082,7 +2146,7 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 				   struct net_device **out_dev,
 				   struct flowi4 *fl4,
 				   struct neighbour **out_n,
-				   int *out_ttl)
+				   u8 *out_ttl)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_rep_priv *uplink_rpriv;
@@ -2106,7 +2170,8 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 	else
 		*out_dev = rt->dst.dev;
 
-	*out_ttl = ip4_dst_hoplimit(&rt->dst);
+	if (!(*out_ttl))
+		*out_ttl = ip4_dst_hoplimit(&rt->dst);
 	n = dst_neigh_lookup(&rt->dst, &fl4->daddr);
 	ip_rt_put(rt);
 	if (!n)
@@ -2135,7 +2200,7 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 				   struct net_device **out_dev,
 				   struct flowi6 *fl6,
 				   struct neighbour **out_n,
-				   int *out_ttl)
+				   u8 *out_ttl)
 {
 	struct neighbour *n = NULL;
 	struct dst_entry *dst;
@@ -2150,7 +2215,8 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 	if (ret < 0)
 		return ret;
 
-	*out_ttl = ip6_dst_hoplimit(dst);
+	if (!(*out_ttl))
+		*out_ttl = ip6_dst_hoplimit(dst);
 
 	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
 	/* if the egress device isn't on the same HW e-switch, we use the uplink */
@@ -2174,7 +2240,7 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 static void gen_vxlan_header_ipv4(struct net_device *out_dev,
 				  char buf[], int encap_size,
 				  unsigned char h_dest[ETH_ALEN],
-				  int ttl,
+				  u8 tos, u8 ttl,
 				  __be32 daddr,
 				  __be32 saddr,
 				  __be16 udp_dst_port,
@@ -2194,6 +2260,7 @@ static void gen_vxlan_header_ipv4(struct net_device *out_dev,
 	ip->daddr = daddr;
 	ip->saddr = saddr;
 
+	ip->tos = tos;
 	ip->ttl = ttl;
 	ip->protocol = IPPROTO_UDP;
 	ip->version = 0x4;
@@ -2207,7 +2274,7 @@ static void gen_vxlan_header_ipv4(struct net_device *out_dev,
 static void gen_vxlan_header_ipv6(struct net_device *out_dev,
 				  char buf[], int encap_size,
 				  unsigned char h_dest[ETH_ALEN],
-				  int ttl,
+				  u8 tos, u8 ttl,
 				  struct in6_addr *daddr,
 				  struct in6_addr *saddr,
 				  __be16 udp_dst_port,
@@ -2224,7 +2291,7 @@ static void gen_vxlan_header_ipv6(struct net_device *out_dev,
 	ether_addr_copy(eth->h_source, out_dev->dev_addr);
 	eth->h_proto = htons(ETH_P_IPV6);
 
-	ip6_flow_hdr(ip6h, 0, 0);
+	ip6_flow_hdr(ip6h, tos, 0);
 	/* the HW fills up ipv6 payload len */
 	ip6h->nexthdr     = IPPROTO_UDP;
 	ip6h->hop_limit   = ttl;
@@ -2246,9 +2313,9 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	struct net_device *out_dev;
 	struct neighbour *n = NULL;
 	struct flowi4 fl4 = {};
+	u8 nud_state, tos, ttl;
 	char *encap_header;
-	int ttl, err;
-	u8 nud_state;
+	int err;
 
 	if (max_encap_size < ipv4_encap_size) {
 		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
@@ -2269,6 +2336,10 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 		err = -EOPNOTSUPP;
 		goto free_encap;
 	}
+
+	tos = tun_key->tos;
+	ttl = tun_key->ttl;
+
 	fl4.flowi4_tos = tun_key->tos;
 	fl4.daddr = tun_key->u.ipv4.dst;
 	fl4.saddr = tun_key->u.ipv4.src;
@@ -2303,7 +2374,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	switch (e->tunnel_type) {
 	case MLX5_HEADER_TYPE_VXLAN:
 		gen_vxlan_header_ipv4(out_dev, encap_header,
-				      ipv4_encap_size, e->h_dest, ttl,
+				      ipv4_encap_size, e->h_dest, tos, ttl,
 				      fl4.daddr,
 				      fl4.saddr, tun_key->tp_dst,
 				      tunnel_id_to_key32(tun_key->tun_id));
@@ -2351,9 +2422,9 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 	struct net_device *out_dev;
 	struct neighbour *n = NULL;
 	struct flowi6 fl6 = {};
+	u8 nud_state, tos, ttl;
 	char *encap_header;
-	int err, ttl = 0;
-	u8 nud_state;
+	int err;
 
 	if (max_encap_size < ipv6_encap_size) {
 		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
@@ -2375,6 +2446,9 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 		goto free_encap;
 	}
 
+	tos = tun_key->tos;
+	ttl = tun_key->ttl;
+
 	fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
 	fl6.daddr = tun_key->u.ipv6.dst;
 	fl6.saddr = tun_key->u.ipv6.src;
@@ -2409,7 +2483,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 	switch (e->tunnel_type) {
 	case MLX5_HEADER_TYPE_VXLAN:
 		gen_vxlan_header_ipv6(out_dev, encap_header,
-				      ipv6_encap_size, e->h_dest, ttl,
+				      ipv6_encap_size, e->h_dest, tos, ttl,
 				      &fl6.daddr,
 				      &fl6.saddr, tun_key->tp_dst,
 				      tunnel_id_to_key32(tun_key->tun_id));
@@ -2455,11 +2529,7 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 			      struct mlx5e_tc_flow *flow)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5e_rep_priv *uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw,
-									   REP_ETH);
-	struct net_device *up_dev = uplink_rpriv->netdev;
 	unsigned short family = ip_tunnel_info_af(tun_info);
-	struct mlx5e_priv *up_priv = netdev_priv(up_dev);
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
 	struct ip_tunnel_key *key = &tun_info->key;
 	struct mlx5e_encap_entry *e;
@@ -2479,7 +2549,7 @@ vxlan_encap_offload_err:
 		return -EOPNOTSUPP;
 	}
 
-	if (mlx5e_vxlan_lookup_port(up_priv, be16_to_cpu(key->tp_dst)) &&
+	if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->tp_dst)) &&
 	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) {
 		tunnel_type = MLX5_HEADER_TYPE_VXLAN;
 	} else {
@@ -2535,6 +2605,56 @@ out_err:
 	return err;
 }
 
+static int parse_tc_vlan_action(struct mlx5e_priv *priv,
+				const struct tc_action *a,
+				struct mlx5_esw_flow_attr *attr,
+				u32 *action)
+{
+	u8 vlan_idx = attr->total_vlan;
+
+	if (vlan_idx >= MLX5_FS_VLAN_DEPTH)
+		return -EOPNOTSUPP;
+
+	if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
+		if (vlan_idx) {
+			if (!mlx5_eswitch_vlan_actions_supported(priv->mdev,
+								 MLX5_FS_VLAN_DEPTH))
+				return -EOPNOTSUPP;
+
+			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2;
+		} else {
+			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
+		}
+	} else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
+		attr->vlan_vid[vlan_idx] = tcf_vlan_push_vid(a);
+		attr->vlan_prio[vlan_idx] = tcf_vlan_push_prio(a);
+		attr->vlan_proto[vlan_idx] = tcf_vlan_push_proto(a);
+		if (!attr->vlan_proto[vlan_idx])
+			attr->vlan_proto[vlan_idx] = htons(ETH_P_8021Q);
+
+		if (vlan_idx) {
+			if (!mlx5_eswitch_vlan_actions_supported(priv->mdev,
+								 MLX5_FS_VLAN_DEPTH))
+				return -EOPNOTSUPP;
+
+			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2;
+		} else {
+			if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, 1) &&
+			    (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q) ||
+			     tcf_vlan_push_prio(a)))
+				return -EOPNOTSUPP;
+
+			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
+		}
+	} else { /* action is TCA_VLAN_ACT_MODIFY */
+		return -EOPNOTSUPP;
+	}
+
+	attr->total_vlan = vlan_idx + 1;
+
+	return 0;
+}
+
 static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				struct mlx5e_tc_flow_parse_attr *parse_attr,
 				struct mlx5e_tc_flow *flow)
@@ -2546,6 +2666,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 	LIST_HEAD(actions);
 	bool encap = false;
 	u32 action = 0;
+	int err;
 
 	if (!tcf_exts_has_actions(exts))
 		return -EINVAL;
@@ -2562,8 +2683,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 		}
 
 		if (is_tcf_pedit(a)) {
-			int err;
-
 			err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_FDB,
 						    parse_attr);
 			if (err)
@@ -2630,23 +2749,11 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 		}
 
 		if (is_tcf_vlan(a)) {
-			if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
-				action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
-			} else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
-				action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
-				attr->vlan_vid = tcf_vlan_push_vid(a);
-				if (mlx5_eswitch_vlan_actions_supported(priv->mdev)) {
-					attr->vlan_prio = tcf_vlan_push_prio(a);
-					attr->vlan_proto = tcf_vlan_push_proto(a);
-					if (!attr->vlan_proto)
-						attr->vlan_proto = htons(ETH_P_8021Q);
-				} else if (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q) ||
-					   tcf_vlan_push_prio(a)) {
-					return -EOPNOTSUPP;
-				}
-			} else { /* action is TCA_VLAN_ACT_MODIFY */
-				return -EOPNOTSUPP;
-			}
+			err = parse_tc_vlan_action(priv, a, attr, &action);
+
+			if (err)
+				return err;
+
 			attr->mirror_count = attr->out_count;
 			continue;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index f29deb44bf3b..ae73ea992845 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -66,22 +66,21 @@ static inline void mlx5e_tx_dma_unmap(struct device *pdev,
 	}
 }
 
+static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_txqsq *sq, u32 i)
+{
+	return &sq->db.dma_fifo[i & sq->dma_fifo_mask];
+}
+
 static inline void mlx5e_dma_push(struct mlx5e_txqsq *sq,
 				  dma_addr_t addr,
 				  u32 size,
 				  enum mlx5e_dma_map_type map_type)
 {
-	u32 i = sq->dma_fifo_pc & sq->dma_fifo_mask;
-
-	sq->db.dma_fifo[i].addr = addr;
-	sq->db.dma_fifo[i].size = size;
-	sq->db.dma_fifo[i].type = map_type;
-	sq->dma_fifo_pc++;
-}
+	struct mlx5e_sq_dma *dma = mlx5e_dma_get(sq, sq->dma_fifo_pc++);
 
-static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_txqsq *sq, u32 i)
-{
-	return &sq->db.dma_fifo[i & sq->dma_fifo_mask];
+	dma->addr = addr;
+	dma->size = size;
+	dma->type = map_type;
 }
 
 static void mlx5e_dma_unmap_wqe_err(struct mlx5e_txqsq *sq, u8 num_dma)
@@ -111,10 +110,11 @@ static inline int mlx5e_get_dscp_up(struct mlx5e_priv *priv, struct sk_buff *skb
 #endif
 
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv, select_queue_fallback_t fallback)
+		       struct net_device *sb_dev,
+		       select_queue_fallback_t fallback)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	int channel_ix = fallback(dev, skb);
+	int channel_ix = fallback(dev, skb, NULL);
 	u16 num_channels;
 	int up = 0;
 
@@ -228,7 +228,10 @@ mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb)
 		stats->tso_inner_packets++;
 		stats->tso_inner_bytes += skb->len - ihs;
 	} else {
-		ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+			ihs = skb_transport_offset(skb) + sizeof(struct udphdr);
+		else
+			ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
 		stats->tso_packets++;
 		stats->tso_bytes += skb->len - ihs;
 	}
@@ -443,12 +446,11 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	sq = priv->txq2sq[skb_get_queue_mapping(skb)];
 	mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
 
-#ifdef CONFIG_MLX5_ACCEL
 	/* might send skbs and update wqe and pi */
 	skb = mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi);
 	if (unlikely(!skb))
 		return NETDEV_TX_OK;
-#endif
+
 	return mlx5e_sq_xmit(sq, skb, wqe, pi);
 }
 
@@ -466,6 +468,7 @@ static void mlx5e_dump_error_cqe(struct mlx5e_txqsq *sq,
 
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 {
+	struct mlx5e_sq_stats *stats;
 	struct mlx5e_txqsq *sq;
 	struct mlx5_cqe64 *cqe;
 	u32 dma_fifo_cc;
@@ -483,6 +486,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 	if (!cqe)
 		return false;
 
+	stats = sq->stats;
+
 	npkts = 0;
 	nbytes = 0;
 
@@ -511,7 +516,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 				queue_work(cq->channel->priv->wq,
 					   &sq->recover.recover_work);
 			}
-			sq->stats->cqe_err++;
+			stats->cqe_err++;
 		}
 
 		do {
@@ -556,6 +561,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
+	stats->cqes += i;
+
 	mlx5_cqwq_update_db_record(&cq->wq);
 
 	/* ensure cq space is freed before enabling more cqes */
@@ -571,7 +578,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 				   MLX5E_SQ_STOP_ROOM) &&
 	    !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) {
 		netif_tx_wake_queue(sq->txq);
-		sq->stats->wake++;
+		stats->wake++;
 	}
 
 	return (i == MLX5E_TX_CQ_POLL_BUDGET);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 1b17f682693b..85d517360157 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -32,6 +32,7 @@
 
 #include <linux/irq.h>
 #include "en.h"
+#include "en/xdp.h"
 
 static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c)
 {
@@ -74,13 +75,18 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel,
 					       napi);
+	struct mlx5e_ch_stats *ch_stats = c->stats;
 	bool busy = false;
 	int work_done = 0;
 	int i;
 
+	ch_stats->poll++;
+
 	for (i = 0; i < c->num_tc; i++)
 		busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget);
 
+	busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq);
+
 	if (c->xdp)
 		busy |= mlx5e_poll_xdpsq_cq(&c->rq.xdpsq.cq);
 
@@ -94,6 +100,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	if (busy) {
 		if (likely(mlx5e_channel_no_affinity_change(c)))
 			return budget;
+		ch_stats->aff_change++;
 		if (budget && work_done == budget)
 			work_done--;
 	}
@@ -101,6 +108,8 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	if (unlikely(!napi_complete_done(napi, work_done)))
 		return work_done;
 
+	ch_stats->arm++;
+
 	for (i = 0; i < c->num_tc; i++) {
 		mlx5e_handle_tx_dim(&c->sq[i]);
 		mlx5e_cq_arm(&c->sq[i].cq);
@@ -110,6 +119,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 
 	mlx5e_cq_arm(&c->rq.cq);
 	mlx5e_cq_arm(&c->icosq.cq);
+	mlx5e_cq_arm(&c->xdpsq.cq);
 
 	return work_done;
 }
@@ -118,8 +128,9 @@ void mlx5e_completion_event(struct mlx5_core_cq *mcq)
 {
 	struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
 
-	cq->event_ctr++;
 	napi_schedule(cq->napi);
+	cq->event_ctr++;
+	cq->channel->stats->events++;
 }
 
 void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 406c23862f5f..48864f4988a4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -40,6 +40,8 @@
 #include "mlx5_core.h"
 #include "fpga/core.h"
 #include "eswitch.h"
+#include "lib/clock.h"
+#include "diag/fw_tracer.h"
 
 enum {
 	MLX5_EQE_SIZE		= sizeof(struct mlx5_eqe),
@@ -168,6 +170,8 @@ static const char *eqe_type_str(u8 type)
 		return "MLX5_EVENT_TYPE_FPGA_QP_ERROR";
 	case MLX5_EVENT_TYPE_GENERAL_EVENT:
 		return "MLX5_EVENT_TYPE_GENERAL_EVENT";
+	case MLX5_EVENT_TYPE_DEVICE_TRACER:
+		return "MLX5_EVENT_TYPE_DEVICE_TRACER";
 	default:
 		return "Unrecognized event";
 	}
@@ -576,6 +580,11 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 		case MLX5_EVENT_TYPE_GENERAL_EVENT:
 			general_event_handler(dev, eqe);
 			break;
+
+		case MLX5_EVENT_TYPE_DEVICE_TRACER:
+			mlx5_fw_tracer_event(dev, eqe);
+			break;
+
 		default:
 			mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n",
 				       eqe->type, eq->eqn);
@@ -853,6 +862,9 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 	if (MLX5_CAP_GEN(dev, temp_warn_event))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_TEMP_WARN_EVENT);
 
+	if (MLX5_CAP_MCAM_REG(dev, tracer_registers))
+		async_event_mask |= (1ull << MLX5_EVENT_TYPE_DEVICE_TRACER);
+
 	err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD,
 				 MLX5_NUM_CMD_EQE, 1ull << MLX5_EVENT_TYPE_CMD,
 				 "mlx5_cmd_eq", MLX5_EQ_TYPE_ASYNC);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 40dba9e8af92..2b252cde5cc2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -246,7 +246,7 @@ esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport)
 	return __esw_fdb_set_vport_rule(esw, vport, true, mac_c, mac_v);
 }
 
-static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw, int nvports)
+static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_flow_table_attr ft_attr = {};
@@ -1469,7 +1469,7 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw,
 		return;
 
 	mlx5_modify_vport_admin_state(esw->dev,
-				      MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+				      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
 				      vport_num,
 				      vport->info.link_state);
 	mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, vport->info.mac);
@@ -1582,9 +1582,9 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	esw_vport_disable_qos(esw, vport_num);
 	if (vport_num && esw->mode == SRIOV_LEGACY) {
 		mlx5_modify_vport_admin_state(esw->dev,
-					      MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+					      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
 					      vport_num,
-					      MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
+					      MLX5_VPORT_ADMIN_STATE_DOWN);
 		esw_vport_disable_egress_acl(esw, vport);
 		esw_vport_disable_ingress_acl(esw, vport);
 		esw_vport_destroy_drop_counters(vport);
@@ -1618,7 +1618,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	esw->mode = mode;
 
 	if (mode == SRIOV_LEGACY) {
-		err = esw_create_legacy_fdb_table(esw, nvfs + 1);
+		err = esw_create_legacy_fdb_table(esw);
 	} else {
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
 
@@ -1736,7 +1736,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		struct mlx5_vport *vport = &esw->vports[vport_num];
 
 		vport->vport = vport_num;
-		vport->info.link_state = MLX5_ESW_VPORT_ADMIN_STATE_AUTO;
+		vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
 		vport->dev = dev;
 		INIT_WORK(&vport->vport_change_handler,
 			  esw_vport_change_handler);
@@ -1860,7 +1860,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
 	evport = &esw->vports[vport];
 
 	err = mlx5_modify_vport_admin_state(esw->dev,
-					    MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+					    MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
 					    vport, link_state);
 	if (err) {
 		mlx5_core_warn(esw->dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index b174da2884c5..c17bfcab517c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -38,6 +38,7 @@
 #include <net/devlink.h>
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/eswitch.h>
+#include <linux/mlx5/fs.h>
 #include "lib/mpfs.h"
 
 #ifdef CONFIG_MLX5_ESWITCH
@@ -256,9 +257,10 @@ struct mlx5_esw_flow_attr {
 	int out_count;
 
 	int	action;
-	__be16	vlan_proto;
-	u16	vlan_vid;
-	u8	vlan_prio;
+	__be16	vlan_proto[MLX5_FS_VLAN_DEPTH];
+	u16	vlan_vid[MLX5_FS_VLAN_DEPTH];
+	u8	vlan_prio[MLX5_FS_VLAN_DEPTH];
+	u8	total_vlan;
 	bool	vlan_handled;
 	u32	encap_id;
 	u32	mod_hdr_id;
@@ -282,10 +284,17 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
 int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 				  int vport, u16 vlan, u8 qos, u8 set_flags);
 
-static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev)
+static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev,
+						       u8 vlan_depth)
 {
-	return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, pop_vlan) &&
-	       MLX5_CAP_ESW_FLOWTABLE_FDB(dev, push_vlan);
+	bool ret = MLX5_CAP_ESW_FLOWTABLE_FDB(dev, pop_vlan) &&
+		   MLX5_CAP_ESW_FLOWTABLE_FDB(dev, push_vlan);
+
+	if (vlan_depth == 1)
+		return ret;
+
+	return  ret && MLX5_CAP_ESW_FLOWTABLE_FDB(dev, pop_vlan_2) &&
+		MLX5_CAP_ESW_FLOWTABLE_FDB(dev, push_vlan_2);
 }
 
 #define MLX5_DEBUG_ESWITCH_MASK BIT(3)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 91f1209886ff..f72b5c9dcfe9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -66,13 +66,18 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 
 	flow_act.action = attr->action;
 	/* if per flow vlan pop/push is emulated, don't set that into the firmware */
-	if (!mlx5_eswitch_vlan_actions_supported(esw->dev))
+	if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
 		flow_act.action &= ~(MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH |
 				     MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
 	else if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) {
-		flow_act.vlan.ethtype = ntohs(attr->vlan_proto);
-		flow_act.vlan.vid = attr->vlan_vid;
-		flow_act.vlan.prio = attr->vlan_prio;
+		flow_act.vlan[0].ethtype = ntohs(attr->vlan_proto[0]);
+		flow_act.vlan[0].vid = attr->vlan_vid[0];
+		flow_act.vlan[0].prio = attr->vlan_prio[0];
+		if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) {
+			flow_act.vlan[1].ethtype = ntohs(attr->vlan_proto[1]);
+			flow_act.vlan[1].vid = attr->vlan_vid[1];
+			flow_act.vlan[1].prio = attr->vlan_prio[1];
+		}
 	}
 
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
@@ -266,7 +271,7 @@ static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr,
 	/* protects against (1) setting rules with different vlans to push and
 	 * (2) setting rules w.o vlans (attr->vlan = 0) && w. vlans to push (!= 0)
 	 */
-	if (push && in_rep->vlan_refcount && (in_rep->vlan != attr->vlan_vid))
+	if (push && in_rep->vlan_refcount && (in_rep->vlan != attr->vlan_vid[0]))
 		goto out_notsupp;
 
 	return 0;
@@ -284,7 +289,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
 	int err = 0;
 
 	/* nop if we're on the vlan push/pop non emulation mode */
-	if (mlx5_eswitch_vlan_actions_supported(esw->dev))
+	if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
 		return 0;
 
 	push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH);
@@ -324,11 +329,11 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
 		if (vport->vlan_refcount)
 			goto skip_set_push;
 
-		err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport, attr->vlan_vid, 0,
+		err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport, attr->vlan_vid[0], 0,
 						    SET_VLAN_INSERT | SET_VLAN_STRIP);
 		if (err)
 			goto out;
-		vport->vlan = attr->vlan_vid;
+		vport->vlan = attr->vlan_vid[0];
 skip_set_push:
 		vport->vlan_refcount++;
 	}
@@ -347,7 +352,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
 	int err = 0;
 
 	/* nop if we're on the vlan push/pop non emulation mode */
-	if (mlx5_eswitch_vlan_actions_supported(esw->dev))
+	if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
 		return 0;
 
 	if (!attr->vlan_handled)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
index c9736238604a..5cf5f2a9d51f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
@@ -129,6 +129,7 @@ static void mlx5_fpga_tls_cmd_send(struct mlx5_fpga_device *fdev,
 static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock,
 				    void *ptr)
 {
+	unsigned long flags;
 	int ret;
 
 	/* TLS metadata format is 1 byte for syndrome followed
@@ -139,9 +140,9 @@ static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock,
 	BUILD_BUG_ON((SWID_END - 1) & 0xFF000000);
 
 	idr_preload(GFP_KERNEL);
-	spin_lock_irq(idr_spinlock);
+	spin_lock_irqsave(idr_spinlock, flags);
 	ret = idr_alloc(idr, ptr, SWID_START, SWID_END, GFP_ATOMIC);
-	spin_unlock_irq(idr_spinlock);
+	spin_unlock_irqrestore(idr_spinlock, flags);
 	idr_preload_end();
 
 	return ret;
@@ -157,6 +158,13 @@ static void mlx5_fpga_tls_release_swid(struct idr *idr,
 	spin_unlock_irqrestore(idr_spinlock, flags);
 }
 
+static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
+				   struct mlx5_fpga_device *fdev,
+				   struct mlx5_fpga_dma_buf *buf, u8 status)
+{
+	kfree(buf);
+}
+
 struct mlx5_teardown_stream_context {
 	struct mlx5_fpga_tls_command_context cmd;
 	u32 swid;
@@ -178,9 +186,13 @@ mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
 			mlx5_fpga_err(fdev,
 				      "Teardown stream failed with syndrome = %d",
 				      syndrome);
-		else
+		else if (MLX5_GET(tls_cmd, cmd->buf.sg[0].data, direction_sx))
 			mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr,
-						   &fdev->tls->idr_spinlock,
+						   &fdev->tls->tx_idr_spinlock,
+						   ctx->swid);
+		else
+			mlx5_fpga_tls_release_swid(&fdev->tls->rx_idr,
+						   &fdev->tls->rx_idr_spinlock,
 						   ctx->swid);
 	}
 	mlx5_fpga_tls_put_command_ctx(cmd);
@@ -196,6 +208,40 @@ static void mlx5_fpga_tls_flow_to_cmd(void *flow, void *cmd)
 		 MLX5_GET(tls_flow, flow, direction_sx));
 }
 
+int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
+			    u64 rcd_sn)
+{
+	struct mlx5_fpga_dma_buf *buf;
+	int size = sizeof(*buf) + MLX5_TLS_COMMAND_SIZE;
+	void *flow;
+	void *cmd;
+	int ret;
+
+	buf = kzalloc(size, GFP_ATOMIC);
+	if (!buf)
+		return -ENOMEM;
+
+	cmd = (buf + 1);
+
+	rcu_read_lock();
+	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
+	rcu_read_unlock();
+	mlx5_fpga_tls_flow_to_cmd(flow, cmd);
+
+	MLX5_SET(tls_cmd, cmd, swid, ntohl(handle));
+	MLX5_SET64(tls_cmd, cmd, tls_rcd_sn, be64_to_cpu(rcd_sn));
+	MLX5_SET(tls_cmd, cmd, tcp_sn, seq);
+	MLX5_SET(tls_cmd, cmd, command_type, CMD_RESYNC_RX);
+
+	buf->sg[0].data = cmd;
+	buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
+	buf->complete = mlx_tls_kfree_complete;
+
+	ret = mlx5_fpga_sbu_conn_sendmsg(mdev->fpga->tls->conn, buf);
+
+	return ret;
+}
+
 static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 					    void *flow, u32 swid, gfp_t flags)
 {
@@ -223,14 +269,18 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 			       mlx5_fpga_tls_teardown_completion);
 }
 
-void mlx5_fpga_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid,
-			       gfp_t flags)
+void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+			    gfp_t flags, bool direction_sx)
 {
 	struct mlx5_fpga_tls *tls = mdev->fpga->tls;
 	void *flow;
 
 	rcu_read_lock();
-	flow = idr_find(&tls->tx_idr, swid);
+	if (direction_sx)
+		flow = idr_find(&tls->tx_idr, swid);
+	else
+		flow = idr_find(&tls->rx_idr, swid);
+
 	rcu_read_unlock();
 
 	if (!flow) {
@@ -289,9 +339,11 @@ mlx5_fpga_tls_setup_completion(struct mlx5_fpga_conn *conn,
 		 * the command context because we might not have received
 		 * the tx completion yet.
 		 */
-		mlx5_fpga_tls_del_tx_flow(fdev->mdev,
-					  MLX5_GET(tls_cmd, tls_cmd, swid),
-					  GFP_ATOMIC);
+		mlx5_fpga_tls_del_flow(fdev->mdev,
+				       MLX5_GET(tls_cmd, tls_cmd, swid),
+				       GFP_ATOMIC,
+				       MLX5_GET(tls_cmd, tls_cmd,
+						direction_sx));
 	}
 
 	mlx5_fpga_tls_put_command_ctx(cmd);
@@ -415,8 +467,7 @@ int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev)
 	if (err)
 		goto error;
 
-	if (!(tls->caps & (MLX5_ACCEL_TLS_TX | MLX5_ACCEL_TLS_V12 |
-				 MLX5_ACCEL_TLS_AES_GCM128))) {
+	if (!(tls->caps & (MLX5_ACCEL_TLS_V12 | MLX5_ACCEL_TLS_AES_GCM128))) {
 		err = -ENOTSUPP;
 		goto error;
 	}
@@ -438,7 +489,9 @@ int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev)
 	INIT_LIST_HEAD(&tls->pending_cmds);
 
 	idr_init(&tls->tx_idr);
-	spin_lock_init(&tls->idr_spinlock);
+	idr_init(&tls->rx_idr);
+	spin_lock_init(&tls->tx_idr_spinlock);
+	spin_lock_init(&tls->rx_idr_spinlock);
 	fdev->tls = tls;
 	return 0;
 
@@ -500,9 +553,9 @@ static int mlx5_fpga_tls_set_key_material(void *cmd, u32 caps,
 	return 0;
 }
 
-static int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
-				  struct tls_crypto_info *crypto_info, u32 swid,
-				  u32 tcp_sn)
+static int _mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+				   struct tls_crypto_info *crypto_info,
+				   u32 swid, u32 tcp_sn)
 {
 	u32 caps = mlx5_fpga_tls_device_caps(mdev);
 	struct mlx5_setup_stream_context *ctx;
@@ -533,30 +586,42 @@ out:
 	return ret;
 }
 
-int mlx5_fpga_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
-			      struct tls_crypto_info *crypto_info,
-			      u32 start_offload_tcp_sn, u32 *p_swid)
+int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+			   struct tls_crypto_info *crypto_info,
+			   u32 start_offload_tcp_sn, u32 *p_swid,
+			   bool direction_sx)
 {
 	struct mlx5_fpga_tls *tls = mdev->fpga->tls;
 	int ret = -ENOMEM;
 	u32 swid;
 
-	ret = mlx5_fpga_tls_alloc_swid(&tls->tx_idr, &tls->idr_spinlock, flow);
+	if (direction_sx)
+		ret = mlx5_fpga_tls_alloc_swid(&tls->tx_idr,
+					       &tls->tx_idr_spinlock, flow);
+	else
+		ret = mlx5_fpga_tls_alloc_swid(&tls->rx_idr,
+					       &tls->rx_idr_spinlock, flow);
+
 	if (ret < 0)
 		return ret;
 
 	swid = ret;
-	MLX5_SET(tls_flow, flow, direction_sx, 1);
+	MLX5_SET(tls_flow, flow, direction_sx, direction_sx ? 1 : 0);
 
-	ret = mlx5_fpga_tls_add_flow(mdev, flow, crypto_info, swid,
-				     start_offload_tcp_sn);
+	ret = _mlx5_fpga_tls_add_flow(mdev, flow, crypto_info, swid,
+				      start_offload_tcp_sn);
 	if (ret && ret != -EINTR)
 		goto free_swid;
 
 	*p_swid = swid;
 	return 0;
 free_swid:
-	mlx5_fpga_tls_release_swid(&tls->tx_idr, &tls->idr_spinlock, swid);
+	if (direction_sx)
+		mlx5_fpga_tls_release_swid(&tls->tx_idr,
+					   &tls->tx_idr_spinlock, swid);
+	else
+		mlx5_fpga_tls_release_swid(&tls->rx_idr,
+					   &tls->rx_idr_spinlock, swid);
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h
index 800a214e4e49..3b2e37bf76fe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h
@@ -46,15 +46,18 @@ struct mlx5_fpga_tls {
 	struct mlx5_fpga_conn *conn;
 
 	struct idr tx_idr;
-	spinlock_t idr_spinlock; /* protects the IDR */
+	struct idr rx_idr;
+	spinlock_t tx_idr_spinlock; /* protects the IDR */
+	spinlock_t rx_idr_spinlock; /* protects the IDR */
 };
 
-int mlx5_fpga_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
-			      struct tls_crypto_info *crypto_info,
-			      u32 start_offload_tcp_sn, u32 *p_swid);
+int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+			   struct tls_crypto_info *crypto_info,
+			   u32 start_offload_tcp_sn, u32 *p_swid,
+			   bool direction_sx);
 
-void mlx5_fpga_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid,
-			       gfp_t flags);
+void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+			    gfp_t flags, bool direction_sx);
 
 bool mlx5_fpga_is_tls_device(struct mlx5_core_dev *mdev);
 int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev);
@@ -65,4 +68,7 @@ static inline u32 mlx5_fpga_tls_device_caps(struct mlx5_core_dev *mdev)
 	return mdev->fpga->tls->caps;
 }
 
+int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
+			    u64 rcd_sn);
+
 #endif /* __MLX5_FPGA_TLS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 5a00deff5457..6a62b84e57f4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -349,9 +349,15 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 
 	vlan = MLX5_ADDR_OF(flow_context, in_flow_context, push_vlan);
 
-	MLX5_SET(vlan, vlan, ethtype, fte->action.vlan.ethtype);
-	MLX5_SET(vlan, vlan, vid, fte->action.vlan.vid);
-	MLX5_SET(vlan, vlan, prio, fte->action.vlan.prio);
+	MLX5_SET(vlan, vlan, ethtype, fte->action.vlan[0].ethtype);
+	MLX5_SET(vlan, vlan, vid, fte->action.vlan[0].vid);
+	MLX5_SET(vlan, vlan, prio, fte->action.vlan[0].prio);
+
+	vlan = MLX5_ADDR_OF(flow_context, in_flow_context, push_vlan_2);
+
+	MLX5_SET(vlan, vlan, ethtype, fte->action.vlan[1].ethtype);
+	MLX5_SET(vlan, vlan, vid, fte->action.vlan[1].vid);
+	MLX5_SET(vlan, vlan, prio, fte->action.vlan[1].prio);
 
 	in_match_value = MLX5_ADDR_OF(flow_context, in_flow_context,
 				      match_value);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 6ddb2565884d..261cb6aacf12 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1465,7 +1465,9 @@ static bool check_conflicting_actions(u32 action1, u32 action2)
 			     MLX5_FLOW_CONTEXT_ACTION_DECAP |
 			     MLX5_FLOW_CONTEXT_ACTION_MOD_HDR  |
 			     MLX5_FLOW_CONTEXT_ACTION_VLAN_POP |
-			     MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH))
+			     MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH |
+			     MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2 |
+			     MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2))
 		return true;
 
 	return false;
@@ -1824,7 +1826,7 @@ search_again_locked:
 
 	g = alloc_auto_flow_group(ft, spec);
 	if (IS_ERR(g)) {
-		rule = (void *)g;
+		rule = ERR_CAST(g);
 		up_write_ref_node(&ft->node);
 		return rule;
 	}
@@ -1874,7 +1876,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 		    struct mlx5_flow_spec *spec,
 		    struct mlx5_flow_act *flow_act,
 		    struct mlx5_flow_destination *dest,
-		    int dest_num)
+		    int num_dest)
 {
 	struct mlx5_flow_root_namespace *root = find_root(&ft->node);
 	struct mlx5_flow_destination gen_dest = {};
@@ -1887,7 +1889,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 	if (flow_act->action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
 		if (!fwd_next_prio_supported(ft))
 			return ERR_PTR(-EOPNOTSUPP);
-		if (dest_num)
+		if (num_dest)
 			return ERR_PTR(-EINVAL);
 		mutex_lock(&root->chain_lock);
 		next_ft = find_next_chained_ft(prio);
@@ -1895,7 +1897,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 			gen_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 			gen_dest.ft = next_ft;
 			dest = &gen_dest;
-			dest_num = 1;
+			num_dest = 1;
 			flow_act->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 		} else {
 			mutex_unlock(&root->chain_lock);
@@ -1903,7 +1905,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 		}
 	}
 
-	handle = _mlx5_add_flow_rules(ft, spec, flow_act, dest, dest_num);
+	handle = _mlx5_add_flow_rules(ft, spec, flow_act, dest, num_dest);
 
 	if (sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
 		if (!IS_ERR_OR_NULL(handle) &&
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
index a8eecedd46c2..02e2e4575e4f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
@@ -33,8 +33,15 @@
 #ifndef __LIB_CLOCK_H__
 #define __LIB_CLOCK_H__
 
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
 void mlx5_init_clock(struct mlx5_core_dev *mdev);
 void mlx5_cleanup_clock(struct mlx5_core_dev *mdev);
+void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
+
+static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
+{
+	return mdev->clock.ptp ? ptp_clock_index(mdev->clock.ptp) : -1;
+}
 
 static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
 						u64 timestamp)
@@ -48,4 +55,21 @@ static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
 	return ns_to_ktime(nsec);
 }
 
+#else
+static inline void mlx5_init_clock(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe) {}
+
+static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
+{
+	return -1;
+}
+
+static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
+						u64 timestamp)
+{
+	return 0;
+}
+#endif
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
new file mode 100644
index 000000000000..9a8fd762167b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
@@ -0,0 +1,230 @@
+/*
+ * Copyright (c) 2016, Mellanox Technologies, Ltd.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+#include "vxlan.h"
+
+struct mlx5_vxlan {
+	struct mlx5_core_dev		*mdev;
+	spinlock_t			lock; /* protect vxlan table */
+	/* max_num_ports is usuallly 4, 16 buckets is more than enough */
+	DECLARE_HASHTABLE(htable, 4);
+	int				num_ports;
+	struct mutex                    sync_lock; /* sync add/del port HW operations */
+};
+
+struct mlx5_vxlan_port {
+	struct hlist_node hlist;
+	atomic_t refcount;
+	u16 udp_port;
+};
+
+static inline u8 mlx5_vxlan_max_udp_ports(struct mlx5_core_dev *mdev)
+{
+	return MLX5_CAP_ETH(mdev, max_vxlan_udp_ports) ?: 4;
+}
+
+static int mlx5_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port)
+{
+	u32 in[MLX5_ST_SZ_DW(add_vxlan_udp_dport_in)]   = {0};
+	u32 out[MLX5_ST_SZ_DW(add_vxlan_udp_dport_out)] = {0};
+
+	MLX5_SET(add_vxlan_udp_dport_in, in, opcode,
+		 MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT);
+	MLX5_SET(add_vxlan_udp_dport_in, in, vxlan_udp_port, port);
+	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+static int mlx5_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port)
+{
+	u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)]   = {0};
+	u32 out[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_out)] = {0};
+
+	MLX5_SET(delete_vxlan_udp_dport_in, in, opcode,
+		 MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT);
+	MLX5_SET(delete_vxlan_udp_dport_in, in, vxlan_udp_port, port);
+	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+static struct mlx5_vxlan_port*
+mlx5_vxlan_lookup_port_locked(struct mlx5_vxlan *vxlan, u16 port)
+{
+	struct mlx5_vxlan_port *vxlanp;
+
+	hash_for_each_possible(vxlan->htable, vxlanp, hlist, port) {
+		if (vxlanp->udp_port == port)
+			return vxlanp;
+	}
+
+	return NULL;
+}
+
+struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port)
+{
+	struct mlx5_vxlan_port *vxlanp;
+
+	if (!mlx5_vxlan_allowed(vxlan))
+		return NULL;
+
+	spin_lock_bh(&vxlan->lock);
+	vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port);
+	spin_unlock_bh(&vxlan->lock);
+
+	return vxlanp;
+}
+
+int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port)
+{
+	struct mlx5_vxlan_port *vxlanp;
+	int ret = -ENOSPC;
+
+	vxlanp = mlx5_vxlan_lookup_port(vxlan, port);
+	if (vxlanp) {
+		atomic_inc(&vxlanp->refcount);
+		return 0;
+	}
+
+	mutex_lock(&vxlan->sync_lock);
+	if (vxlan->num_ports >= mlx5_vxlan_max_udp_ports(vxlan->mdev)) {
+		mlx5_core_info(vxlan->mdev,
+			       "UDP port (%d) not offloaded, max number of UDP ports (%d) are already offloaded\n",
+			       port, mlx5_vxlan_max_udp_ports(vxlan->mdev));
+		ret = -ENOSPC;
+		goto unlock;
+	}
+
+	ret = mlx5_vxlan_core_add_port_cmd(vxlan->mdev, port);
+	if (ret)
+		goto unlock;
+
+	vxlanp = kzalloc(sizeof(*vxlanp), GFP_KERNEL);
+	if (!vxlanp) {
+		ret = -ENOMEM;
+		goto err_delete_port;
+	}
+
+	vxlanp->udp_port = port;
+	atomic_set(&vxlanp->refcount, 1);
+
+	spin_lock_bh(&vxlan->lock);
+	hash_add(vxlan->htable, &vxlanp->hlist, port);
+	spin_unlock_bh(&vxlan->lock);
+
+	vxlan->num_ports++;
+	mutex_unlock(&vxlan->sync_lock);
+	return 0;
+
+err_delete_port:
+	mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port);
+
+unlock:
+	mutex_unlock(&vxlan->sync_lock);
+	return ret;
+}
+
+int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port)
+{
+	struct mlx5_vxlan_port *vxlanp;
+	bool remove = false;
+	int ret = 0;
+
+	mutex_lock(&vxlan->sync_lock);
+
+	spin_lock_bh(&vxlan->lock);
+	vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port);
+	if (!vxlanp) {
+		ret = -ENOENT;
+		goto out_unlock;
+	}
+
+	if (atomic_dec_and_test(&vxlanp->refcount)) {
+		hash_del(&vxlanp->hlist);
+		remove = true;
+	}
+
+out_unlock:
+	spin_unlock_bh(&vxlan->lock);
+
+	if (remove) {
+		mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port);
+		kfree(vxlanp);
+		vxlan->num_ports--;
+	}
+
+	mutex_unlock(&vxlan->sync_lock);
+
+	return ret;
+}
+
+struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_vxlan *vxlan;
+
+	if (!MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) || !mlx5_core_is_pf(mdev))
+		return ERR_PTR(-ENOTSUPP);
+
+	vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL);
+	if (!vxlan)
+		return ERR_PTR(-ENOMEM);
+
+	vxlan->mdev = mdev;
+	mutex_init(&vxlan->sync_lock);
+	spin_lock_init(&vxlan->lock);
+	hash_init(vxlan->htable);
+
+	/* Hardware adds 4789 by default */
+	mlx5_vxlan_add_port(vxlan, 4789);
+
+	return vxlan;
+}
+
+void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan)
+{
+	struct mlx5_vxlan_port *vxlanp;
+	struct hlist_node *tmp;
+	int bkt;
+
+	if (!mlx5_vxlan_allowed(vxlan))
+		return;
+
+	/* Lockless since we are the only hash table consumers*/
+	hash_for_each_safe(vxlan->htable, bkt, tmp, vxlanp, hlist) {
+		hash_del(&vxlanp->hlist);
+		mlx5_vxlan_core_del_port_cmd(vxlan->mdev, vxlanp->udp_port);
+		kfree(vxlanp);
+	}
+
+	kfree(vxlan);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
index 5ef6ae7d568a..8fb0eb08fa6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
@@ -33,31 +33,32 @@
 #define __MLX5_VXLAN_H__
 
 #include <linux/mlx5/driver.h>
-#include "en.h"
 
-struct mlx5e_vxlan {
-	atomic_t refcount;
-	u16 udp_port;
-};
+struct mlx5_vxlan;
+struct mlx5_vxlan_port;
 
-struct mlx5e_vxlan_work {
-	struct work_struct	work;
-	struct mlx5e_priv	*priv;
-	sa_family_t		sa_family;
-	u16			port;
-};
-
-static inline bool mlx5e_vxlan_allowed(struct mlx5_core_dev *mdev)
+static inline bool mlx5_vxlan_allowed(struct mlx5_vxlan *vxlan)
 {
-	return (MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) &&
-		mlx5_core_is_pf(mdev));
+	/* not allowed reason is encoded in vxlan pointer as error,
+	 * on mlx5_vxlan_create
+	 */
+	return !IS_ERR_OR_NULL(vxlan);
 }
 
-void mlx5e_vxlan_init(struct mlx5e_priv *priv);
-void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv);
-
-void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, sa_family_t sa_family,
-			    u16 port, int add);
-struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port);
+#if IS_ENABLED(CONFIG_VXLAN)
+struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev);
+void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan);
+int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port);
+int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port);
+struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port);
+#else
+static inline struct mlx5_vxlan*
+mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-EOPNOTSUPP); }
+static inline void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { return; }
+static inline int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; }
+static inline int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; }
+static inline struct mx5_vxlan_port*
+mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port) { return NULL; }
+#endif
 
 #endif /* __MLX5_VXLAN_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 615005e63819..cf3e4a659052 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -62,9 +62,11 @@
 #include "accel/ipsec.h"
 #include "accel/tls.h"
 #include "lib/clock.h"
+#include "lib/vxlan.h"
+#include "diag/fw_tracer.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
-MODULE_DESCRIPTION("Mellanox Connect-IB, ConnectX-4 core driver");
+MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_VERSION(DRIVER_VERSION);
 
@@ -321,7 +323,9 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 	struct mlx5_eq_table *table = &priv->eq_table;
-	int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq);
+	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
+		      MLX5_CAP_GEN(dev, max_num_eqs) :
+		      1 << MLX5_CAP_GEN(dev, log_max_eq);
 	int nvec;
 	int err;
 
@@ -960,6 +964,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 
 	mlx5_init_clock(dev);
 
+	dev->vxlan = mlx5_vxlan_create(dev);
+
 	err = mlx5_init_rl_table(dev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to init rate limiting\n");
@@ -990,6 +996,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 		goto err_sriov_cleanup;
 	}
 
+	dev->tracer = mlx5_fw_tracer_create(dev);
+
 	return 0;
 
 err_sriov_cleanup:
@@ -1001,6 +1009,7 @@ err_mpfs_cleanup:
 err_rl_cleanup:
 	mlx5_cleanup_rl_table(dev);
 err_tables_cleanup:
+	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cleanup_mkey_table(dev);
 	mlx5_cleanup_srq_table(dev);
 	mlx5_cleanup_qp_table(dev);
@@ -1015,11 +1024,13 @@ out:
 
 static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 {
+	mlx5_fw_tracer_destroy(dev->tracer);
 	mlx5_fpga_cleanup(dev);
 	mlx5_sriov_cleanup(dev);
 	mlx5_eswitch_cleanup(dev->priv.eswitch);
 	mlx5_mpfs_cleanup(dev);
 	mlx5_cleanup_rl_table(dev);
+	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cleanup_clock(dev);
 	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cleanup_mkey_table(dev);
@@ -1167,10 +1178,16 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_put_uars;
 	}
 
+	err = mlx5_fw_tracer_init(dev->tracer);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to init FW tracer\n");
+		goto err_fw_tracer;
+	}
+
 	err = alloc_comp_eqs(dev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to alloc completion EQs\n");
-		goto err_stop_eqs;
+		goto err_comp_eqs;
 	}
 
 	err = mlx5_irq_set_affinity_hints(dev);
@@ -1252,7 +1269,10 @@ err_fpga_start:
 err_affinity_hints:
 	free_comp_eqs(dev);
 
-err_stop_eqs:
+err_comp_eqs:
+	mlx5_fw_tracer_cleanup(dev->tracer);
+
+err_fw_tracer:
 	mlx5_stop_eqs(dev);
 
 err_put_uars:
@@ -1320,6 +1340,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	mlx5_fpga_device_stop(dev);
 	mlx5_irq_clear_affinity_hints(dev);
 	free_comp_eqs(dev);
+	mlx5_fw_tracer_cleanup(dev->tracer);
 	mlx5_stop_eqs(dev);
 	mlx5_put_uars_page(dev, priv->uar);
 	mlx5_free_irq_vectors(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 023882d9a22e..b4134fa0bba3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -66,6 +66,12 @@ do {									\
 		__func__, __LINE__, current->pid,	\
 	       ##__VA_ARGS__)
 
+#define mlx5_core_err_rl(__dev, format, ...)				\
+	dev_err_ratelimited(&(__dev)->pdev->dev,			\
+			   "%s:%d:(pid %d): " format,			\
+			   __func__, __LINE__, current->pid,		\
+			   ##__VA_ARGS__)
+
 #define mlx5_core_warn(__dev, format, ...)				\
 	dev_warn(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format,	\
 		 __func__, __LINE__, current->pid,			\
@@ -93,7 +99,6 @@ void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
 		     unsigned long param);
 void mlx5_core_page_fault(struct mlx5_core_dev *dev,
 			  struct mlx5_pagefault *pfault);
-void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index f4f02f775c93..0670165afd5f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -146,23 +146,6 @@ int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey,
 }
 EXPORT_SYMBOL(mlx5_core_query_mkey);
 
-int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *_mkey,
-			     u32 *mkey)
-{
-	u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)]   = {0};
-	int err;
-
-	MLX5_SET(query_special_contexts_in, in, opcode,
-		 MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-	if (!err)
-		*mkey = MLX5_GET(query_special_contexts_out, out,
-				 dump_fill_mkey);
-	return err;
-}
-EXPORT_SYMBOL(mlx5_core_dump_fill_mkey);
-
 static inline u32 mlx5_get_psv(u32 *out, int psv_index)
 {
 	switch (psv_index) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 7eecd5b07bb1..b02af317c125 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -62,17 +62,6 @@ u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport)
 
 	return MLX5_GET(query_vport_state_out, out, state);
 }
-EXPORT_SYMBOL_GPL(mlx5_query_vport_state);
-
-u8 mlx5_query_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport)
-{
-	u32 out[MLX5_ST_SZ_DW(query_vport_state_out)] = {0};
-
-	_mlx5_query_vport_state(mdev, opmod, vport, out, sizeof(out));
-
-	return MLX5_GET(query_vport_state_out, out, admin_state);
-}
-EXPORT_SYMBOL_GPL(mlx5_query_vport_admin_state);
 
 int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 				  u16 vport, u8 state)
@@ -90,7 +79,6 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 
 	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 }
-EXPORT_SYMBOL_GPL(mlx5_modify_vport_admin_state);
 
 static int mlx5_query_nic_vport_context(struct mlx5_core_dev *mdev, u16 vport,
 					u32 *out, int outlen)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
deleted file mode 100644
index 2f74953e4561..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ /dev/null
@@ -1,190 +0,0 @@
-/*
- * Copyright (c) 2016, Mellanox Technologies, Ltd.  All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mlx5/driver.h>
-#include "mlx5_core.h"
-#include "vxlan.h"
-
-void mlx5e_vxlan_init(struct mlx5e_priv *priv)
-{
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-
-	spin_lock_init(&vxlan_db->lock);
-	INIT_RADIX_TREE(&vxlan_db->tree, GFP_ATOMIC);
-}
-
-static int mlx5e_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port)
-{
-	u32 in[MLX5_ST_SZ_DW(add_vxlan_udp_dport_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(add_vxlan_udp_dport_out)] = {0};
-
-	MLX5_SET(add_vxlan_udp_dport_in, in, opcode,
-		 MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT);
-	MLX5_SET(add_vxlan_udp_dport_in, in, vxlan_udp_port, port);
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
-}
-
-static int mlx5e_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port)
-{
-	u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_out)] = {0};
-
-	MLX5_SET(delete_vxlan_udp_dport_in, in, opcode,
-		 MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT);
-	MLX5_SET(delete_vxlan_udp_dport_in, in, vxlan_udp_port, port);
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
-}
-
-struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port)
-{
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-	struct mlx5e_vxlan *vxlan;
-
-	spin_lock_bh(&vxlan_db->lock);
-	vxlan = radix_tree_lookup(&vxlan_db->tree, port);
-	spin_unlock_bh(&vxlan_db->lock);
-
-	return vxlan;
-}
-
-static void mlx5e_vxlan_add_port(struct work_struct *work)
-{
-	struct mlx5e_vxlan_work *vxlan_work =
-		container_of(work, struct mlx5e_vxlan_work, work);
-	struct mlx5e_priv *priv = vxlan_work->priv;
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-	u16 port = vxlan_work->port;
-	struct mlx5e_vxlan *vxlan;
-	int err;
-
-	mutex_lock(&priv->state_lock);
-	vxlan = mlx5e_vxlan_lookup_port(priv, port);
-	if (vxlan) {
-		atomic_inc(&vxlan->refcount);
-		goto free_work;
-	}
-
-	if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port))
-		goto free_work;
-
-	vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL);
-	if (!vxlan)
-		goto err_delete_port;
-
-	vxlan->udp_port = port;
-	atomic_set(&vxlan->refcount, 1);
-
-	spin_lock_bh(&vxlan_db->lock);
-	err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan);
-	spin_unlock_bh(&vxlan_db->lock);
-	if (err)
-		goto err_free;
-
-	goto free_work;
-
-err_free:
-	kfree(vxlan);
-err_delete_port:
-	mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
-free_work:
-	mutex_unlock(&priv->state_lock);
-	kfree(vxlan_work);
-}
-
-static void mlx5e_vxlan_del_port(struct work_struct *work)
-{
-	struct mlx5e_vxlan_work *vxlan_work =
-		container_of(work, struct mlx5e_vxlan_work, work);
-	struct mlx5e_priv *priv         = vxlan_work->priv;
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-	u16 port = vxlan_work->port;
-	struct mlx5e_vxlan *vxlan;
-	bool remove = false;
-
-	mutex_lock(&priv->state_lock);
-	spin_lock_bh(&vxlan_db->lock);
-	vxlan = radix_tree_lookup(&vxlan_db->tree, port);
-	if (!vxlan)
-		goto out_unlock;
-
-	if (atomic_dec_and_test(&vxlan->refcount)) {
-		radix_tree_delete(&vxlan_db->tree, port);
-		remove = true;
-	}
-
-out_unlock:
-	spin_unlock_bh(&vxlan_db->lock);
-
-	if (remove) {
-		mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
-		kfree(vxlan);
-	}
-	mutex_unlock(&priv->state_lock);
-	kfree(vxlan_work);
-}
-
-void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, sa_family_t sa_family,
-			    u16 port, int add)
-{
-	struct mlx5e_vxlan_work *vxlan_work;
-
-	vxlan_work = kmalloc(sizeof(*vxlan_work), GFP_ATOMIC);
-	if (!vxlan_work)
-		return;
-
-	if (add)
-		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_add_port);
-	else
-		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_del_port);
-
-	vxlan_work->priv = priv;
-	vxlan_work->port = port;
-	vxlan_work->sa_family = sa_family;
-	queue_work(priv->wq, &vxlan_work->work);
-}
-
-void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv)
-{
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-	struct mlx5e_vxlan *vxlan;
-	unsigned int port = 0;
-
-	/* Lockless since we are the only radix-tree consumers, wq is disabled */
-	while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) {
-		port = vxlan->udp_port;
-		radix_tree_delete(&vxlan_db->tree, port);
-		mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
-		kfree(vxlan);
-	}
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
index 0b47126815b6..2bd4c3184eba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -229,6 +229,11 @@ static inline int mlx5_wq_ll_is_empty(struct mlx5_wq_ll *wq)
 	return !wq->cur_sz;
 }
 
+static inline int mlx5_wq_ll_missing(struct mlx5_wq_ll *wq)
+{
+	return wq->fbc.sz_m1 - wq->cur_sz;
+}
+
 static inline void *mlx5_wq_ll_get_wqe(struct mlx5_wq_ll *wq, u16 ix)
 {
 	return mlx5_frag_buf_get_wqe(&wq->fbc, ix);