796 files changed, 49703 insertions, 20336 deletions

diff --git a/Documentation/ABI/testing/sysfs-class-net-qmi b/Documentation/ABI/testing/sysfs-class-net-qmi
index fa5a00bb1143..7122d6264c49 100644
--- a/Documentation/ABI/testing/sysfs-class-net-qmi
+++ b/Documentation/ABI/testing/sysfs-class-net-qmi
@@ -21,3 +21,30 @@ Description:
 		is responsible for coordination of driver and firmware
 		link framing mode, changing this setting to 'Y' if the
 		firmware is configured for 'raw-ip' mode.
+
+What:		/sys/class/net/<iface>/qmi/add_mux
+Date:		March 2017
+KernelVersion:	4.11
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		Unsigned integer.
+
+		Write a number ranging from 1 to 127 to add a qmap mux
+		based network device, supported by recent Qualcomm based
+		modems.
+
+		The network device will be called qmimux.
+
+		Userspace is in charge of managing the qmux network device
+		activation and data stream setup on the modem side by
+		using the proper QMI protocol requests.
+
+What:		/sys/class/net/<iface>/qmi/del_mux
+Date:		March 2017
+KernelVersion:	4.11
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		Unsigned integer.
+
+		Write a number ranging from 1 to 127 to delete a previously
+		created qmap mux based network device.
diff --git a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
index 10587bdadbbe..26c77d985faf 100644
--- a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
+++ b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
@@ -2,11 +2,14 @@
 
 Required properties:
 - compatible: should contain one of "brcm,genet-v1", "brcm,genet-v2",
-  "brcm,genet-v3", "brcm,genet-v4".
+  "brcm,genet-v3", "brcm,genet-v4", "brcm,genet-v5".
 - reg: address and length of the register set for the device
-- interrupts: must be two cells, the first cell is the general purpose
-  interrupt line, while the second cell is the interrupt for the ring
-  RX and TX queues operating in ring mode
+- interrupts and/or interrupts-extended: must be two cells, the first cell
+  is the general purpose interrupt line, while the second cell is the
+  interrupt for the ring RX and TX queues operating in ring mode.  An
+  optional third interrupt cell for Wake-on-LAN can be specified.
+  See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
+  for information on the property specifics.
 - phy-mode: see ethernet.txt file in the same directory
 - #address-cells: should be 1
 - #size-cells: should be 1
@@ -29,15 +32,15 @@ Optional properties:
 
 Required child nodes:
 
-- mdio bus node: this node should always be present regarless of the PHY
+- mdio bus node: this node should always be present regardless of the PHY
   configuration of the GENET instance
 
 MDIO bus node required properties:
 
 - compatible: should contain one of "brcm,genet-mdio-v1", "brcm,genet-mdio-v2"
-  "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", the version has to match the
-  parent node compatible property (e.g: brcm,genet-v4 pairs with
-  brcm,genet-mdio-v4)
+  "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", "brcm,genet-mdio-v5", the version
+  has to match the parent node compatible property (e.g: brcm,genet-v4 pairs
+  with brcm,genet-mdio-v4)
 - reg: address and length relative to the parent node base register address
 - #address-cells: address cell for MDIO bus addressing, should be 1
 - #size-cells: size of the cells for MDIO bus addressing, should be 0
diff --git a/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt b/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt
index ab0bb4247d14..4648948f7c3b 100644
--- a/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt
+++ b/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt
@@ -2,8 +2,9 @@
 
 Required properties:
 - compatible: should one from "brcm,genet-mdio-v1", "brcm,genet-mdio-v2",
-  "brcm,genet-mdio-v3", "brcm,genet-mdio-v4" or "brcm,unimac-mdio"
-- reg: address and length of the regsiter set for the device, first one is the
+  "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", "brcm,genet-mdio-v5" or
+  "brcm,unimac-mdio"
+- reg: address and length of the register set for the device, first one is the
   base register, and the second one is optional and for indirect accesses to
   larger than 16-bits MDIO transactions
 - reg-names: name(s) of the register must be "mdio" and optional "mdio_indir_rw"
diff --git a/Documentation/devicetree/bindings/net/can/holt_hi311x.txt b/Documentation/devicetree/bindings/net/can/holt_hi311x.txt
new file mode 100644
index 000000000000..23aa94eab207
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/holt_hi311x.txt
@@ -0,0 +1,24 @@
+* Holt HI-311X stand-alone CAN controller device tree bindings
+
+Required properties:
+ - compatible: Should be one of the following:
+   - "holt,hi3110" for HI-3110
+ - reg: SPI chip select.
+ - clocks: The clock feeding the CAN controller.
+ - interrupt-parent: The parent interrupt controller.
+ - interrupts: Should contain IRQ line for the CAN controller.
+
+Optional properties:
+ - vdd-supply: Regulator that powers the CAN controller.
+ - xceiver-supply: Regulator that powers the CAN transceiver.
+
+Example:
+	can0: can@1 {
+		compatible = "holt,hi3110";
+		reg = <1>;
+		clocks = <&clk32m>;
+		interrupt-parent = <&gpio4>;
+		interrupts = <13 IRQ_TYPE_EDGE_RISING>;
+		vdd-supply = <&reg5v0>;
+		xceiver-supply = <&reg5v0>;
+	};
diff --git a/Documentation/devicetree/bindings/net/can/ti_hecc.txt b/Documentation/devicetree/bindings/net/can/ti_hecc.txt
new file mode 100644
index 000000000000..e0f0a7cfe329
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/ti_hecc.txt
@@ -0,0 +1,32 @@
+Texas Instruments High End CAN Controller (HECC)
+================================================
+
+This file provides information, what the device node
+for the hecc interface contains.
+
+Required properties:
+- compatible: "ti,am3517-hecc"
+- reg: addresses and lengths of the register spaces for 'hecc', 'hecc-ram'
+       and 'mbx'
+- reg-names :"hecc", "hecc-ram", "mbx"
+- interrupts: interrupt mapping for the hecc interrupts sources
+- clocks: clock phandles (see clock bindings for details)
+
+Optional properties:
+- ti,use-hecc1int: if provided configures HECC to produce all interrupts
+		   on HECC1INT interrupt line. By default HECC0INT interrupt
+		   line will be used.
+- xceiver-supply: regulator that powers the CAN transceiver
+
+Example:
+
+For am3517evm board:
+	hecc: can@5c050000 {
+		compatible = "ti,am3517-hecc";
+		reg = <0x5c050000 0x80>,
+		      <0x5c053000 0x180>,
+		      <0x5c052000 0x200>;
+		reg-names = "hecc", "hecc-ram", "mbx";
+		interrupts = <24>;
+		clocks = <&hecc_ck>;
+	};
diff --git a/Documentation/devicetree/bindings/net/marvell-pp2.txt b/Documentation/devicetree/bindings/net/marvell-pp2.txt
index 4754364df4c6..6b4956beff8c 100644
--- a/Documentation/devicetree/bindings/net/marvell-pp2.txt
+++ b/Documentation/devicetree/bindings/net/marvell-pp2.txt
@@ -1,17 +1,28 @@
-* Marvell Armada 375 Ethernet Controller (PPv2)
+* Marvell Armada 375 Ethernet Controller (PPv2.1)
+  Marvell Armada 7K/8K Ethernet Controller (PPv2.2)
 
 Required properties:
 
-- compatible: should be "marvell,armada-375-pp2"
+- compatible: should be one of:
+    "marvell,armada-375-pp2"
+    "marvell,armada-7k-pp2"
 - reg: addresses and length of the register sets for the device.
-  Must contain the following register sets:
+  For "marvell,armada-375-pp2", must contain the following register
+  sets:
 	- common controller registers
 	- LMS registers
-  In addition, at least one port register set is required.
-- clocks: a pointer to the reference clocks for this device, consequently:
-	- main controller clock
-	- GOP clock
-- clock-names: names of used clocks, must be "pp_clk" and "gop_clk".
+	- one register area per Ethernet port
+  For "marvell,armada-7k-pp2", must contain the following register
+  sets:
+	- packet processor registers
+	- networking interfaces registers
+
+- clocks: pointers to the reference clocks for this device, consequently:
+	- main controller clock (for both armada-375-pp2 and armada-7k-pp2)
+	- GOP clock (for both armada-375-pp2 and armada-7k-pp2)
+	- MG clock (only for armada-7k-pp2)
+- clock-names: names of used clocks, must be "pp_clk", "gop_clk" and
+  "mg_clk" (the latter only for armada-7k-pp2).
 
 The ethernet ports are represented by subnodes. At least one port is
 required.
@@ -19,8 +30,10 @@ required.
 Required properties (port):
 
 - interrupts: interrupt for the port
-- port-id: should be '0' or '1' for ethernet ports, and '2' for the
-           loopback port
+- port-id: ID of the port from the MAC point of view
+- gop-port-id: only for marvell,armada-7k-pp2, ID of the port from the
+  GOP (Group Of Ports) point of view. This ID is used to index the
+  per-port registers in the second register area.
 - phy-mode: See ethernet.txt file in the same directory
 
 Optional properties (port):
@@ -29,7 +42,7 @@ Optional properties (port):
 - phy: a phandle to a phy node defining the PHY address (as the reg
   property, a single integer).
 
-Example:
+Example for marvell,armada-375-pp2:
 
 ethernet@f0000 {
 	compatible = "marvell,armada-375-pp2";
@@ -57,3 +70,30 @@ ethernet@f0000 {
 		phy-mode = "gmii";
 	};
 };
+
+Example for marvell,armada-7k-pp2:
+
+cpm_ethernet: ethernet@0 {
+	compatible = "marvell,armada-7k-pp22";
+	reg = <0x0 0x100000>, <0x129000 0xb000>;
+	clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>, <&cpm_syscon0 1 5>;
+	clock-names = "pp_clk", "gop_clk", "gp_clk";
+
+	eth0: eth0 {
+		interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
+		port-id = <0>;
+		gop-port-id = <0>;
+	};
+
+	eth1: eth1 {
+		interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
+		port-id = <1>;
+		gop-port-id = <2>;
+	};
+
+	eth2: eth2 {
+		interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
+		port-id = <2>;
+		gop-port-id = <3>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt
index d3bfc2b30fb5..f652b0c384ce 100644
--- a/Documentation/devicetree/bindings/net/stmmac.txt
+++ b/Documentation/devicetree/bindings/net/stmmac.txt
@@ -28,9 +28,9 @@ Optional properties:
   clocks may be specified in derived bindings.
 - clock-names: One name for each entry in the clocks property, the
   first one should be "stmmaceth" and the second one should be "pclk".
-- clk_ptp_ref: this is the PTP reference clock; in case of the PTP is
-  available this clock is used for programming the Timestamp Addend Register.
-  If not passed then the system clock will be used and this is fine on some
+- ptp_ref: this is the PTP reference clock; in case of the PTP is available
+  this clock is used for programming the Timestamp Addend Register. If not
+  passed then the system clock will be used and this is fine on some
   platforms.
 - tx-fifo-depth: See ethernet.txt file in the same directory
 - rx-fifo-depth: See ethernet.txt file in the same directory
@@ -72,7 +72,45 @@ Optional properties:
 	- snps,mb: mixed-burst
 	- snps,rb: rebuild INCRx Burst
 - mdio: with compatible = "snps,dwmac-mdio", create and register mdio bus.
-
+- Multiple RX Queues parameters: below the list of all the parameters to
+				 configure the multiple RX queues:
+	- snps,rx-queues-to-use: number of RX queues to be used in the driver
+	- Choose one of these RX scheduling algorithms:
+		- snps,rx-sched-sp: Strict priority
+		- snps,rx-sched-wsp: Weighted Strict priority
+	- For each RX queue
+		- Choose one of these modes:
+			- snps,dcb-algorithm: Queue to be enabled as DCB
+			- snps,avb-algorithm: Queue to be enabled as AVB
+		- snps,map-to-dma-channel: Channel to map
+		- Specifiy specific packet routing:
+			- snps,route-avcp: AV Untagged Control packets
+			- snps,route-ptp: PTP Packets
+			- snps,route-dcbcp: DCB Control Packets
+			- snps,route-up: Untagged Packets
+			- snps,route-multi-broad: Multicast & Broadcast Packets
+		- snps,priority: RX queue priority (Range: 0x0 to 0xF)
+- Multiple TX Queues parameters: below the list of all the parameters to
+				 configure the multiple TX queues:
+	- snps,tx-queues-to-use: number of TX queues to be used in the driver
+	- Choose one of these TX scheduling algorithms:
+		- snps,tx-sched-wrr: Weighted Round Robin
+		- snps,tx-sched-wfq: Weighted Fair Queuing
+		- snps,tx-sched-dwrr: Deficit Weighted Round Robin
+		- snps,tx-sched-sp: Strict priority
+	- For each TX queue
+		- snps,weight: TX queue weight (if using a DCB weight algorithm)
+		- Choose one of these modes:
+			- snps,dcb-algorithm: TX queue will be working in DCB
+			- snps,avb-algorithm: TX queue will be working in AVB
+			  [Attention] Queue 0 is reserved for legacy traffic
+			  and so no AVB is available in this queue.
+		- Configure Credit Base Shaper (if AVB Mode selected):
+			- snps,send_slope: enable Low Power Interface
+			- snps,idle_slope: unlock on WoL
+			- snps,high_credit: max write outstanding req. limit
+			- snps,low_credit: max read outstanding req. limit
+		- snps,priority: TX queue priority (Range: 0x0 to 0xF)
 Examples:
 
 	stmmac_axi_setup: stmmac-axi-config {
@@ -81,6 +119,35 @@ Examples:
 		snps,blen = <256 128 64 32 0 0 0>;
 	};
 
+	mtl_rx_setup: rx-queues-config {
+		snps,rx-queues-to-use = <1>;
+		snps,rx-sched-sp;
+		queue0 {
+			snps,dcb-algorithm;
+			snps,map-to-dma-channel = <0x0>;
+			snps,priority = <0x0>;
+		};
+	};
+
+	mtl_tx_setup: tx-queues-config {
+		snps,tx-queues-to-use = <2>;
+		snps,tx-sched-wrr;
+		queue0 {
+			snps,weight = <0x10>;
+			snps,dcb-algorithm;
+			snps,priority = <0x0>;
+		};
+
+		queue1 {
+			snps,avb-algorithm;
+			snps,send_slope = <0x1000>;
+			snps,idle_slope = <0x1000>;
+			snps,high_credit = <0x3E800>;
+			snps,low_credit = <0xFFC18000>;
+			snps,priority = <0x1>;
+		};
+	};
+
 	gmac0: ethernet@e0800000 {
 		compatible = "st,spear600-gmac";
 		reg = <0xe0800000 0x8000>;
@@ -104,4 +171,6 @@ Examples:
 			phy1: ethernet-phy@0 {
 			};
 		};
+		snps,mtl-rx-config = <&mtl_rx_setup>;
+		snps,mtl-tx-config = <&mtl_tx_setup>;
 	};
diff --git a/Documentation/networking/i40e.txt b/Documentation/networking/i40e.txt
index a251bf4fe9c9..57e616ed10b0 100644
--- a/Documentation/networking/i40e.txt
+++ b/Documentation/networking/i40e.txt
@@ -63,6 +63,78 @@ Additional Configurations
   The latest release of ethtool can be found from
   https://www.kernel.org/pub/software/network/ethtool
 
+
+  Flow Director n-ntuple traffic filters (FDir)
+  ---------------------------------------------
+  The driver utilizes the ethtool interface for configuring ntuple filters,
+  via "ethtool -N <device> <filter>".
+
+  The sctp4, ip4, udp4, and tcp4 flow types are supported with the standard
+  fields including src-ip, dst-ip, src-port and dst-port. The driver only
+  supports fully enabling or fully masking the fields, so use of the mask
+  fields for partial matches is not supported.
+
+  Additionally, the driver supports using the action to specify filters for a
+  Virtual Function. You can specify the action as a 64bit value, where the
+  lower 32 bits represents the queue number, while the next 8 bits represent
+  which VF. Note that 0 is the PF, so the VF identifier is offset by 1. For
+  example:
+
+    ... action 0x800000002 ...
+
+  Would indicate to direct traffic for Virtual Function 7 (8 minus 1) on queue
+  2 of that VF.
+
+  The driver also supports using the user-defined field to specify 2 bytes of
+  arbitrary data to match within the packet payload in addition to the regular
+  fields. The data is specified in the lower 32bits of the user-def field in
+  the following way:
+
+  +----------------------------+---------------------------+
+  | 31    28    24    20    16 | 15    12     8     4     0|
+  +----------------------------+---------------------------+
+  | offset into packet payload |  2 bytes of flexible data |
+  +----------------------------+---------------------------+
+
+  As an example,
+
+    ... user-def 0x4FFFF ....
+
+  means to match the value 0xFFFF 4 bytes into the packet payload. Note that
+  the offset is based on the beginning of the payload, and not the beginning
+  of the packet. Thus
+
+    flow-type tcp4 ... user-def 0x8BEAF ....
+
+  would match TCP/IPv4 packets which have the value 0xBEAF 8bytes into the
+  TCP/IPv4 payload.
+
+  For ICMP, the hardware parses the ICMP header as 4 bytes of header and 4
+  bytes of payload, so if you want to match an ICMP frames payload you may need
+  to add 4 to the offset in order to match the data.
+
+  Furthermore, the offset can only be up to a value of 64, as the hardware
+  will only read up to 64 bytes of data from the payload. It must also be even
+  as the flexible data is 2 bytes long and must be aligned to byte 0 of the
+  packet payload.
+
+  When programming filters, the hardware is limited to using a single input
+  set for each flow type. This means that it is an error to program two
+  different filters with the same type that don't match on the same fields.
+  Thus the second of the following two commands will fail:
+
+    ethtool -N <device> flow-type tcp4 src-ip 192.168.0.7 action 5
+    ethtool -N <device> flow-type tcp4 dst-ip 192.168.15.18 action 1
+
+  This is because the first filter will be accepted and reprogram the input
+  set for TCPv4 filters, but the second filter will be unable to reprogram the
+  input set until all the conflicting TCPv4 filters are first removed.
+
+  Note that the user-defined flexible offset is also considered part of the
+  input set and cannot be programmed separately for multiple filters of the
+  same type. However, the flexible data is not part of the input set and
+  multiple filters may use the same offset but match against different data.
+
   Data Center Bridging (DCB)
   --------------------------
   DCB configuration is not currently supported.
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index ab0230461377..b1c6500e7a8d 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -73,6 +73,14 @@ fib_multipath_use_neigh - BOOLEAN
 	0 - disabled
 	1 - enabled
 
+fib_multipath_hash_policy - INTEGER
+	Controls which hash policy to use for multipath routes. Only valid
+	for kernels built with CONFIG_IP_ROUTE_MULTIPATH enabled.
+	Default: 0 (Layer 3)
+	Possible values:
+	0 - Layer 3
+	1 - Layer 4
+
 route/max_size - INTEGER
 	Maximum number of routes allowed in the kernel.  Increase
 	this when using large numbers of interfaces and/or routes.
@@ -640,11 +648,6 @@ tcp_tso_win_divisor - INTEGER
 	building larger TSO frames.
 	Default: 3
 
-tcp_tw_recycle - BOOLEAN
-	Enable fast recycling TIME-WAIT sockets. Default value is 0.
-	It should not be changed without advice/request of technical
-	experts.
-
 tcp_tw_reuse - BOOLEAN
 	Allow to reuse TIME-WAIT sockets for new connections when it is
 	safe from protocol viewpoint. Default value is 0.
@@ -853,12 +856,21 @@ ip_dynaddr - BOOLEAN
 ip_early_demux - BOOLEAN
 	Optimize input packet processing down to one demux for
 	certain kinds of local sockets.  Currently we only do this
-	for established TCP sockets.
+	for established TCP and connected UDP sockets.
 
 	It may add an additional cost for pure routing workloads that
 	reduces overall throughput, in such case you should disable it.
 	Default: 1
 
+tcp_early_demux - BOOLEAN
+	Enable early demux for established TCP sockets.
+	Default: 1
+
+udp_early_demux - BOOLEAN
+	Enable early demux for connected UDP sockets. Disable this if
+	your system could experience more unconnected load.
+	Default: 1
+
 icmp_echo_ignore_all - BOOLEAN
 	If set non-zero, then the kernel will ignore all ICMP ECHO
 	requests sent to it.
@@ -1458,11 +1470,20 @@ accept_ra_pinfo - BOOLEAN
 	Functional default: enabled if accept_ra is enabled.
 			    disabled if accept_ra is disabled.
 
+accept_ra_rt_info_min_plen - INTEGER
+	Minimum prefix length of Route Information in RA.
+
+	Route Information w/ prefix smaller than this variable shall
+	be ignored.
+
+	Functional default: 0 if accept_ra_rtr_pref is enabled.
+			    -1 if accept_ra_rtr_pref is disabled.
+
 accept_ra_rt_info_max_plen - INTEGER
 	Maximum prefix length of Route Information in RA.
 
-	Route Information w/ prefix larger than or equal to this
-	variable shall be ignored.
+	Route Information w/ prefix larger than this variable shall
+	be ignored.
 
 	Functional default: 0 if accept_ra_rtr_pref is enabled.
 			    -1 if accept_ra_rtr_pref is disabled.
diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt
index e6b1c025fdd8..056898685d40 100644
--- a/Documentation/networking/ipvs-sysctl.txt
+++ b/Documentation/networking/ipvs-sysctl.txt
@@ -175,6 +175,14 @@ nat_icmp_send - BOOLEAN
         for VS/NAT when the load balancer receives packets from real
         servers but the connection entries don't exist.
 
+pmtu_disc - BOOLEAN
+	0 - disabled
+	not 0 - enabled (default)
+
+	By default, reject with FRAG_NEEDED all DF packets that exceed
+	the PMTU, irrespective of the forwarding method. For TUN method
+	the flag can be disabled to fragment such packets.
+
 secure_tcp - INTEGER
         0  - disabled (default)
 
@@ -185,15 +193,59 @@ secure_tcp - INTEGER
         The value definition is the same as that of drop_entry and
         drop_packet.
 
-sync_threshold - INTEGER
-        default 3
+sync_threshold - vector of 2 INTEGERs: sync_threshold, sync_period
+	default 3 50
+
+	It sets synchronization threshold, which is the minimum number
+	of incoming packets that a connection needs to receive before
+	the connection will be synchronized. A connection will be
+	synchronized, every time the number of its incoming packets
+	modulus sync_period equals the threshold. The range of the
+	threshold is from 0 to sync_period.
+
+	When sync_period and sync_refresh_period are 0, send sync only
+	for state changes or only once when pkts matches sync_threshold
+
+sync_refresh_period - UNSIGNED INTEGER
+	default 0
+
+	In seconds, difference in reported connection timer that triggers
+	new sync message. It can be used to avoid sync messages for the
+	specified period (or half of the connection timeout if it is lower)
+	if connection state is not changed since last sync.
+
+	This is useful for normal connections with high traffic to reduce
+	sync rate. Additionally, retry sync_retries times with period of
+	sync_refresh_period/8.
+
+sync_retries - INTEGER
+	default 0
+
+	Defines sync retries with period of sync_refresh_period/8. Useful
+	to protect against loss of sync messages. The range of the
+	sync_retries is from 0 to 3.
+
+sync_qlen_max - UNSIGNED LONG
+
+	Hard limit for queued sync messages that are not sent yet. It
+	defaults to 1/32 of the memory pages but actually represents
+	number of messages. It will protect us from allocating large
+	parts of memory when the sending rate is lower than the queuing
+	rate.
+
+sync_sock_size - INTEGER
+	default 0
+
+	Configuration of SNDBUF (master) or RCVBUF (slave) socket limit.
+	Default value is 0 (preserve system defaults).
+
+sync_ports - INTEGER
+	default 1
 
-        It sets synchronization threshold, which is the minimum number
-        of incoming packets that a connection needs to receive before
-        the connection will be synchronized. A connection will be
-        synchronized, every time the number of its incoming packets
-        modulus 50 equals the threshold. The range of the threshold is
-        from 0 to 49.
+	The number of threads that master and backup servers can use for
+	sync traffic. Every thread will use single UDP port, thread 0 will
+	use the default port 8848 while last thread will use port
+	8848+sync_ports-1.
 
 snat_reroute - BOOLEAN
 	0 - disabled
diff --git a/Documentation/networking/mpls-sysctl.txt b/Documentation/networking/mpls-sysctl.txt
index 15d8d16934fd..2f24a1912a48 100644
--- a/Documentation/networking/mpls-sysctl.txt
+++ b/Documentation/networking/mpls-sysctl.txt
@@ -19,6 +19,25 @@ platform_labels - INTEGER
 	Possible values: 0 - 1048575
 	Default: 0
 
+ip_ttl_propagate - BOOL
+	Control whether TTL is propagated from the IPv4/IPv6 header to
+	the MPLS header on imposing labels and propagated from the
+	MPLS header to the IPv4/IPv6 header on popping the last label.
+
+	If disabled, the MPLS transport network will appear as a
+	single hop to transit traffic.
+
+	0 - disabled / RFC 3443 [Short] Pipe Model
+	1 - enabled / RFC 3443 Uniform Model (default)
+
+default_ttl - BOOL
+	Default TTL value to use for MPLS packets where it cannot be
+	propagated from an IP header, either because one isn't present
+	or ip_ttl_propagate has been disabled.
+
+	Possible values: 1 - 255
+	Default: 255
+
 conf/<interface>/input - BOOL
 	Control whether packets can be input on this interface.
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 882ea01b4efe..5397f54af5fc 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -896,12 +896,19 @@ F:	arch/arm64/boot/dts/apm/
 APPLIED MICRO (APM) X-GENE SOC ETHERNET DRIVER
 M:	Iyappan Subramanian <isubramanian@apm.com>
 M:	Keyur Chudgar <kchudgar@apm.com>
+M:	Quan Nguyen <qnguyen@apm.com>
 S:	Supported
 F:	drivers/net/ethernet/apm/xgene/
 F:	drivers/net/phy/mdio-xgene.c
 F:	Documentation/devicetree/bindings/net/apm-xgene-enet.txt
 F:	Documentation/devicetree/bindings/net/apm-xgene-mdio.txt
 
+APPLIED MICRO (APM) X-GENE SOC ETHERNET (V2) DRIVER
+M:	Iyappan Subramanian <isubramanian@apm.com>
+M:	Keyur Chudgar <kchudgar@apm.com>
+S:	Supported
+F:	drivers/net/ethernet/apm/xgene-v2/
+
 APPLIED MICRO (APM) X-GENE SOC PMU
 M:	Tai Nguyen <ttnguyen@apm.com>
 S:	Supported
@@ -11064,6 +11071,12 @@ F:	include/linux/dma/dw.h
 F:	include/linux/platform_data/dma-dw.h
 F:	drivers/dma/dw/
 
+SYNOPSYS DESIGNWARE ENTERPRISE ETHERNET DRIVER
+M:	Jie Deng <jiedeng@synopsys.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	drivers/net/ethernet/synopsys/
+
 SYNOPSYS DESIGNWARE I2C DRIVER
 M:	Jarkko Nikula <jarkko.nikula@linux.intel.com>
 R:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index afc901b7a6f6..1bb8cac61a28 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -99,4 +99,8 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h
index 5a650426f357..f824eeb0f2e4 100644
--- a/arch/avr32/include/uapi/asm/socket.h
+++ b/arch/avr32/include/uapi/asm/socket.h
@@ -92,4 +92,8 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
 #endif /* _UAPI__ASM_AVR32_SOCKET_H */
diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h
index 81e03530ed39..a8ad9bebfc47 100644
--- a/arch/frv/include/uapi/asm/socket.h
+++ b/arch/frv/include/uapi/asm/socket.h
@@ -92,5 +92,9 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
 #endif /* _ASM_SOCKET_H */
 
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index 57feb0c1f7d7..6af3253e4209 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -101,4 +101,8 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
 #endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h
index 5853f8e92c20..e98b6bb897c0 100644
--- a/arch/m32r/include/uapi/asm/socket.h
+++ b/arch/m32r/include/uapi/asm/socket.h
@@ -92,4 +92,8 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
 #endif /* _ASM_M32R_SOCKET_H */
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 566ecdcb5b4b..ae2b62e39d4d 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -110,4 +110,8 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h
index 0e12527c4b0e..e4ac1843ee01 100644
--- a/arch/mn10300/include/uapi/asm/socket.h
+++ b/arch/mn10300/include/uapi/asm/socket.h
@@ -92,4 +92,8 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 7a109b73ddf7..f754c793e82a 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -91,4 +91,8 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	0x402F
 
+#define SO_MEMINFO		0x4030
+
+#define SO_INCOMING_NAPI_ID	0x4031
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h
index 44583a52f882..5f84af7dcb2e 100644
--- a/arch/powerpc/include/uapi/asm/socket.h
+++ b/arch/powerpc/include/uapi/asm/socket.h
@@ -99,4 +99,8 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
 #endif	/* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index b24a64cbfeb1..25ac4960e707 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -98,4 +98,8 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define	SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index a25dc32f5d6a..b05513acd589 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -88,6 +88,10 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	0x0038
 
+#define SO_MEMINFO		0x0039
+
+#define SO_INCOMING_NAPI_ID	0x003a
+
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION		0x5001
 #define SO_SECURITY_ENCRYPTION_TRANSPORT	0x5002
diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
index 9fdbe1fe0473..786606c81edd 100644
--- a/arch/xtensa/include/uapi/asm/socket.h
+++ b/arch/xtensa/include/uapi/asm/socket.h
@@ -103,4 +103,8 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
 #endif	/* _XTENSA_SOCKET_H */
diff --git a/drivers/atm/ambassador.c b/drivers/atm/ambassador.c
index 4a610795b585..906705e5f776 100644
--- a/drivers/atm/ambassador.c
+++ b/drivers/atm/ambassador.c
@@ -2267,9 +2267,8 @@ static int amb_probe(struct pci_dev *pci_dev,
 	dev->atm_dev->ci_range.vpi_bits = NUM_VPI_BITS;
 	dev->atm_dev->ci_range.vci_bits = NUM_VCI_BITS;
 
-	init_timer(&dev->housekeeping);
-	dev->housekeeping.function = do_housekeeping;
-	dev->housekeeping.data = (unsigned long) dev;
+	setup_timer(&dev->housekeeping, do_housekeeping,
+		    (unsigned long)dev);
 	mod_timer(&dev->housekeeping, jiffies);
 
 	// enable host interrupts
diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index 08e054507d0b..a6a9dd4d0eef 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -344,7 +344,7 @@ config BT_WILINK
 
 config BT_QCOMSMD
 	tristate "Qualcomm SMD based HCI support"
-	depends on QCOM_SMD || (COMPILE_TEST && QCOM_SMD=n)
+	depends on RPMSG || (COMPILE_TEST && RPMSG=n)
 	depends on QCOM_WCNSS_CTRL || (COMPILE_TEST && QCOM_WCNSS_CTRL=n)
 	select BT_QCA
 	help
diff --git a/drivers/bluetooth/btqcomsmd.c b/drivers/bluetooth/btqcomsmd.c
index 8d4868af9bbd..ef730c173d4b 100644
--- a/drivers/bluetooth/btqcomsmd.c
+++ b/drivers/bluetooth/btqcomsmd.c
@@ -14,7 +14,7 @@
 
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
 #include <linux/soc/qcom/wcnss_ctrl.h>
 #include <linux/platform_device.h>
 
@@ -26,8 +26,8 @@
 struct btqcomsmd {
 	struct hci_dev *hdev;
 
-	struct qcom_smd_channel *acl_channel;
-	struct qcom_smd_channel *cmd_channel;
+	struct rpmsg_endpoint *acl_channel;
+	struct rpmsg_endpoint *cmd_channel;
 };
 
 static int btqcomsmd_recv(struct hci_dev *hdev, unsigned int type,
@@ -48,19 +48,19 @@ static int btqcomsmd_recv(struct hci_dev *hdev, unsigned int type,
 	return hci_recv_frame(hdev, skb);
 }
 
-static int btqcomsmd_acl_callback(struct qcom_smd_channel *channel,
-				  const void *data, size_t count)
+static int btqcomsmd_acl_callback(struct rpmsg_device *rpdev, void *data,
+				  int count, void *priv, u32 addr)
 {
-	struct btqcomsmd *btq = qcom_smd_get_drvdata(channel);
+	struct btqcomsmd *btq = priv;
 
 	btq->hdev->stat.byte_rx += count;
 	return btqcomsmd_recv(btq->hdev, HCI_ACLDATA_PKT, data, count);
 }
 
-static int btqcomsmd_cmd_callback(struct qcom_smd_channel *channel,
-				  const void *data, size_t count)
+static int btqcomsmd_cmd_callback(struct rpmsg_device *rpdev, void *data,
+				  int count, void *priv, u32 addr)
 {
-	struct btqcomsmd *btq = qcom_smd_get_drvdata(channel);
+	struct btqcomsmd *btq = priv;
 
 	return btqcomsmd_recv(btq->hdev, HCI_EVENT_PKT, data, count);
 }
@@ -72,12 +72,12 @@ static int btqcomsmd_send(struct hci_dev *hdev, struct sk_buff *skb)
 
 	switch (hci_skb_pkt_type(skb)) {
 	case HCI_ACLDATA_PKT:
-		ret = qcom_smd_send(btq->acl_channel, skb->data, skb->len);
+		ret = rpmsg_send(btq->acl_channel, skb->data, skb->len);
 		hdev->stat.acl_tx++;
 		hdev->stat.byte_tx += skb->len;
 		break;
 	case HCI_COMMAND_PKT:
-		ret = qcom_smd_send(btq->cmd_channel, skb->data, skb->len);
+		ret = rpmsg_send(btq->cmd_channel, skb->data, skb->len);
 		hdev->stat.cmd_tx++;
 		break;
 	default:
@@ -114,18 +114,15 @@ static int btqcomsmd_probe(struct platform_device *pdev)
 	wcnss = dev_get_drvdata(pdev->dev.parent);
 
 	btq->acl_channel = qcom_wcnss_open_channel(wcnss, "APPS_RIVA_BT_ACL",
-						   btqcomsmd_acl_callback);
+						   btqcomsmd_acl_callback, btq);
 	if (IS_ERR(btq->acl_channel))
 		return PTR_ERR(btq->acl_channel);
 
 	btq->cmd_channel = qcom_wcnss_open_channel(wcnss, "APPS_RIVA_BT_CMD",
-						   btqcomsmd_cmd_callback);
+						   btqcomsmd_cmd_callback, btq);
 	if (IS_ERR(btq->cmd_channel))
 		return PTR_ERR(btq->cmd_channel);
 
-	qcom_smd_set_drvdata(btq->acl_channel, btq);
-	qcom_smd_set_drvdata(btq->cmd_channel, btq);
-
 	hdev = hci_alloc_dev();
 	if (!hdev)
 		return -ENOMEM;
@@ -158,6 +155,9 @@ static int btqcomsmd_remove(struct platform_device *pdev)
 	hci_unregister_dev(btq->hdev);
 	hci_free_dev(btq->hdev);
 
+	rpmsg_destroy_ept(btq->cmd_channel);
+	rpmsg_destroy_ept(btq->acl_channel);
+
 	return 0;
 }
 
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 87799e81af97..c3f1a9e33cef 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -32,6 +32,8 @@
 
 #include "hyperv_vmbus.h"
 
+#define VMBUS_PKT_TRAILER	8
+
 /*
  * When we write to the ring buffer, check if the host needs to
  * be signaled. Here is the details of this protocol:
@@ -336,6 +338,12 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
 	return 0;
 }
 
+static inline void
+init_cached_read_index(struct hv_ring_buffer_info *rbi)
+{
+	rbi->cached_read_index = rbi->ring_buffer->read_index;
+}
+
 int hv_ringbuffer_read(struct vmbus_channel *channel,
 		       void *buffer, u32 buflen, u32 *buffer_actual_len,
 		       u64 *requestid, bool raw)
@@ -366,7 +374,8 @@ int hv_ringbuffer_read(struct vmbus_channel *channel,
 		return ret;
 	}
 
-	init_cached_read_index(channel);
+	init_cached_read_index(inring_info);
+
 	next_read_location = hv_get_next_read_location(inring_info);
 	next_read_location = hv_copyfrom_ringbuffer(inring_info, &desc,
 						    sizeof(desc),
@@ -410,3 +419,86 @@ int hv_ringbuffer_read(struct vmbus_channel *channel,
 
 	return ret;
 }
+
+/*
+ * Determine number of bytes available in ring buffer after
+ * the current iterator (priv_read_index) location.
+ *
+ * This is similar to hv_get_bytes_to_read but with private
+ * read index instead.
+ */
+static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi)
+{
+	u32 priv_read_loc = rbi->priv_read_index;
+	u32 write_loc = READ_ONCE(rbi->ring_buffer->write_index);
+
+	if (write_loc >= priv_read_loc)
+		return write_loc - priv_read_loc;
+	else
+		return (rbi->ring_datasize - priv_read_loc) + write_loc;
+}
+
+/*
+ * Get first vmbus packet from ring buffer after read_index
+ *
+ * If ring buffer is empty, returns NULL and no other action needed.
+ */
+struct vmpacket_descriptor *hv_pkt_iter_first(struct vmbus_channel *channel)
+{
+	struct hv_ring_buffer_info *rbi = &channel->inbound;
+
+	/* set state for later hv_signal_on_read() */
+	init_cached_read_index(rbi);
+
+	if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor))
+		return NULL;
+
+	return hv_get_ring_buffer(rbi) + rbi->priv_read_index;
+}
+EXPORT_SYMBOL_GPL(hv_pkt_iter_first);
+
+/*
+ * Get next vmbus packet from ring buffer.
+ *
+ * Advances the current location (priv_read_index) and checks for more
+ * data. If the end of the ring buffer is reached, then return NULL.
+ */
+struct vmpacket_descriptor *
+__hv_pkt_iter_next(struct vmbus_channel *channel,
+		   const struct vmpacket_descriptor *desc)
+{
+	struct hv_ring_buffer_info *rbi = &channel->inbound;
+	u32 packetlen = desc->len8 << 3;
+	u32 dsize = rbi->ring_datasize;
+
+	/* bump offset to next potential packet */
+	rbi->priv_read_index += packetlen + VMBUS_PKT_TRAILER;
+	if (rbi->priv_read_index >= dsize)
+		rbi->priv_read_index -= dsize;
+
+	/* more data? */
+	if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor))
+		return NULL;
+	else
+		return hv_get_ring_buffer(rbi) + rbi->priv_read_index;
+}
+EXPORT_SYMBOL_GPL(__hv_pkt_iter_next);
+
+/*
+ * Update host ring buffer after iterating over packets.
+ */
+void hv_pkt_iter_close(struct vmbus_channel *channel)
+{
+	struct hv_ring_buffer_info *rbi = &channel->inbound;
+
+	/*
+	 * Make sure all reads are done before we update the read index since
+	 * the writer may start writing to the read area once the read index
+	 * is updated.
+	 */
+	virt_rmb();
+	rbi->ring_buffer->read_index = rbi->priv_read_index;
+
+	hv_signal_on_read(channel);
+}
+EXPORT_SYMBOL_GPL(hv_pkt_iter_close);
diff --git a/drivers/infiniband/hw/nes/nes.h b/drivers/infiniband/hw/nes/nes.h
index 85acd0843b50..3f9e56e8b379 100644
--- a/drivers/infiniband/hw/nes/nes.h
+++ b/drivers/infiniband/hw/nes/nes.h
@@ -36,6 +36,7 @@
 
 #include <linux/netdevice.h>
 #include <linux/inetdevice.h>
+#include <linux/interrupt.h>
 #include <linux/spinlock.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index b9b47e5cc8b3..ced0461d6e9f 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -587,9 +587,8 @@ void qedr_affiliated_event(void *context, u8 e_code, void *fw_handle)
 #define EVENT_TYPE_CQ		1
 #define EVENT_TYPE_QP		2
 	struct qedr_dev *dev = (struct qedr_dev *)context;
-	union event_ring_data *data = fw_handle;
-	u64 roce_handle64 = ((u64)data->roce_handle.hi << 32) +
-			    data->roce_handle.lo;
+	struct regpair *async_handle = (struct regpair *)fw_handle;
+	u64 roce_handle64 = ((u64) async_handle->hi << 32) + async_handle->lo;
 	u8 event_type = EVENT_TYPE_NOT_DEFINED;
 	struct ib_event event;
 	struct ib_cq *ibcq;
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index bb32e4792ec9..5cb9195513bd 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -38,7 +38,8 @@
 #include <linux/qed/qed_chain.h>
 #include <linux/qed/qed_roce_if.h>
 #include <linux/qed/qede_roce.h>
-#include "qedr_hsi.h"
+#include <linux/qed/roce_common.h>
+#include "qedr_hsi_rdma.h"
 
 #define QEDR_MODULE_VERSION	"8.10.10.0"
 #define QEDR_NODE_DESC "QLogic 579xx RoCE HCA"
diff --git a/drivers/infiniband/hw/qedr/qedr_cm.c b/drivers/infiniband/hw/qedr/qedr_cm.c
index 699632893dd9..a6280ce3e2a5 100644
--- a/drivers/infiniband/hw/qedr/qedr_cm.c
+++ b/drivers/infiniband/hw/qedr/qedr_cm.c
@@ -43,14 +43,11 @@
 #include <rdma/ib_addr.h>
 #include <rdma/ib_cache.h>
 
-#include "qedr_hsi.h"
 #include <linux/qed/qed_if.h>
 #include <linux/qed/qed_roce_if.h>
 #include "qedr.h"
-#include "qedr_hsi.h"
 #include "verbs.h"
 #include <rdma/qedr-abi.h>
-#include "qedr_hsi.h"
 #include "qedr_cm.h"
 
 void qedr_inc_sw_gsi_cons(struct qedr_qp_hwq_info *info)
diff --git a/drivers/infiniband/hw/qedr/qedr_hsi.h b/drivers/infiniband/hw/qedr/qedr_hsi.h
deleted file mode 100644
index 66d27521373f..000000000000
--- a/drivers/infiniband/hw/qedr/qedr_hsi.h
+++ /dev/null
@@ -1,56 +0,0 @@
-/* QLogic qedr NIC Driver
- * Copyright (c) 2015-2016  QLogic Corporation
- *
- * 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 __QED_HSI_ROCE__
-#define __QED_HSI_ROCE__
-
-#include <linux/qed/common_hsi.h>
-#include <linux/qed/roce_common.h>
-#include "qedr_hsi_rdma.h"
-
-/* Affiliated asynchronous events / errors enumeration */
-enum roce_async_events_type {
-	ROCE_ASYNC_EVENT_NONE = 0,
-	ROCE_ASYNC_EVENT_COMM_EST = 1,
-	ROCE_ASYNC_EVENT_SQ_DRAINED,
-	ROCE_ASYNC_EVENT_SRQ_LIMIT,
-	ROCE_ASYNC_EVENT_LAST_WQE_REACHED,
-	ROCE_ASYNC_EVENT_CQ_ERR,
-	ROCE_ASYNC_EVENT_LOCAL_INVALID_REQUEST_ERR,
-	ROCE_ASYNC_EVENT_LOCAL_CATASTROPHIC_ERR,
-	ROCE_ASYNC_EVENT_LOCAL_ACCESS_ERR,
-	ROCE_ASYNC_EVENT_QP_CATASTROPHIC_ERR,
-	ROCE_ASYNC_EVENT_CQ_OVERFLOW_ERR,
-	ROCE_ASYNC_EVENT_SRQ_EMPTY,
-	MAX_ROCE_ASYNC_EVENTS_TYPE
-};
-
-#endif /* __QED_HSI_ROCE__ */
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 6b3bb32803bd..2091902848e6 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -43,7 +43,8 @@
 #include <rdma/ib_addr.h>
 #include <rdma/ib_cache.h>
 
-#include "qedr_hsi.h"
+#include <linux/qed/common_hsi.h>
+#include "qedr_hsi_rdma.h"
 #include <linux/qed/qed_if.h>
 #include "qedr.h"
 #include "verbs.h"
diff --git a/drivers/isdn/divert/isdn_divert.c b/drivers/isdn/divert/isdn_divert.c
index 50749a70c5ca..060d357f107f 100644
--- a/drivers/isdn/divert/isdn_divert.c
+++ b/drivers/isdn/divert/isdn_divert.c
@@ -157,10 +157,8 @@ int cf_command(int drvid, int mode,
 	/* allocate mem for information struct */
 	if (!(cs = kmalloc(sizeof(struct call_struc), GFP_ATOMIC)))
 		return (-ENOMEM); /* no memory */
-	init_timer(&cs->timer);
+	setup_timer(&cs->timer, deflect_timer_expire, (ulong)cs);
 	cs->info[0] = '\0';
-	cs->timer.function = deflect_timer_expire;
-	cs->timer.data = (ulong) cs; /* pointer to own structure */
 	cs->ics.driver = drvid;
 	cs->ics.command = ISDN_CMD_PROT_IO; /* protocol specific io */
 	cs->ics.arg = DSS1_CMD_INVOKE; /* invoke supplementary service */
@@ -452,10 +450,9 @@ static int isdn_divert_icall(isdn_ctrl *ic)
 					return (0); /* no external deflection needed */
 			if (!(cs = kmalloc(sizeof(struct call_struc), GFP_ATOMIC)))
 				return (0); /* no memory */
-			init_timer(&cs->timer);
+			setup_timer(&cs->timer, deflect_timer_expire,
+				    (ulong)cs);
 			cs->info[0] = '\0';
-			cs->timer.function = deflect_timer_expire;
-			cs->timer.data = (ulong) cs; /* pointer to own structure */
 
 			cs->ics = *ic; /* copy incoming data */
 			if (!cs->ics.parm.setup.phone[0]) strcpy(cs->ics.parm.setup.phone, "0");
diff --git a/drivers/isdn/hardware/eicon/divasi.c b/drivers/isdn/hardware/eicon/divasi.c
index cb88090f9cea..c61049585cbd 100644
--- a/drivers/isdn/hardware/eicon/divasi.c
+++ b/drivers/isdn/hardware/eicon/divasi.c
@@ -300,9 +300,8 @@ static int um_idi_open_adapter(struct file *file, int adapter_nr)
 	p_os = (diva_um_idi_os_context_t *) diva_um_id_get_os_context(e);
 	init_waitqueue_head(&p_os->read_wait);
 	init_waitqueue_head(&p_os->close_wait);
-	init_timer(&p_os->diva_timer_id);
-	p_os->diva_timer_id.function = (void *) diva_um_timer_function;
-	p_os->diva_timer_id.data = (unsigned long) p_os;
+	setup_timer(&p_os->diva_timer_id, (void *)diva_um_timer_function,
+		    (unsigned long)p_os);
 	p_os->aborted = 0;
 	p_os->adapter_nr = adapter_nr;
 	return (1);
diff --git a/drivers/isdn/hardware/mISDN/Kconfig b/drivers/isdn/hardware/mISDN/Kconfig
index 09df54fc1fef..fda912b0833f 100644
--- a/drivers/isdn/hardware/mISDN/Kconfig
+++ b/drivers/isdn/hardware/mISDN/Kconfig
@@ -13,7 +13,7 @@ config MISDN_HFCPCI
 
 config MISDN_HFCMULTI
 	tristate "Support for HFC multiport cards (HFC-4S/8S/E1)"
-	depends on PCI || 8xx
+	depends on PCI || CPM1
 	depends on MISDN
 	help
 	  Enable support for cards with Cologne Chip AG's HFC multiport
@@ -27,8 +27,8 @@ config MISDN_HFCMULTI_8xx
 	bool "Support for XHFC embedded board in HFC multiport driver"
 	depends on MISDN
 	depends on MISDN_HFCMULTI
-	depends on 8xx
-	default 8xx
+	depends on CPM1
+	default CPM1
 	help
 	  Enable support for the XHFC embedded solution from Speech Design.
 
diff --git a/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h b/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h
index 0eafe9f04fca..8a254747768e 100644
--- a/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h
+++ b/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h
@@ -6,7 +6,7 @@
  *
  */
 
-#include <asm/8xx_immap.h>
+#include <asm/cpm1.h>
 
 /* Change this to the value used by your board */
 #ifndef IMAP_ADDR
diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c
index 480c2d7794eb..961c07ee47b7 100644
--- a/drivers/isdn/hardware/mISDN/hfcmulti.c
+++ b/drivers/isdn/hardware/mISDN/hfcmulti.c
@@ -3878,9 +3878,8 @@ hfcmulti_initmode(struct dchannel *dch)
 		if (hc->dnum[pt]) {
 			mode_hfcmulti(hc, dch->slot, dch->dev.D.protocol,
 				      -1, 0, -1, 0);
-			dch->timer.function = (void *) hfcmulti_dbusy_timer;
-			dch->timer.data = (long) dch;
-			init_timer(&dch->timer);
+			setup_timer(&dch->timer, (void *)hfcmulti_dbusy_timer,
+				    (long)dch);
 		}
 		for (i = 1; i <= 31; i++) {
 			if (!((1 << i) & hc->bmask[pt])) /* skip unused chan */
@@ -3986,9 +3985,8 @@ hfcmulti_initmode(struct dchannel *dch)
 		hc->chan[i].slot_rx = -1;
 		hc->chan[i].conf = -1;
 		mode_hfcmulti(hc, i, dch->dev.D.protocol, -1, 0, -1, 0);
-		dch->timer.function = (void *) hfcmulti_dbusy_timer;
-		dch->timer.data = (long) dch;
-		init_timer(&dch->timer);
+		setup_timer(&dch->timer, (void *)hfcmulti_dbusy_timer,
+			    (long)dch);
 		hc->chan[i - 2].slot_tx = -1;
 		hc->chan[i - 2].slot_rx = -1;
 		hc->chan[i - 2].conf = -1;
diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c
index ff48da61c94c..5dc246d71c16 100644
--- a/drivers/isdn/hardware/mISDN/hfcpci.c
+++ b/drivers/isdn/hardware/mISDN/hfcpci.c
@@ -1717,9 +1717,8 @@ static void
 inithfcpci(struct hfc_pci *hc)
 {
 	printk(KERN_DEBUG "inithfcpci: entered\n");
-	hc->dch.timer.function = (void *) hfcpci_dbusy_timer;
-	hc->dch.timer.data = (long) &hc->dch;
-	init_timer(&hc->dch.timer);
+	setup_timer(&hc->dch.timer, (void *)hfcpci_dbusy_timer,
+		    (long)&hc->dch);
 	hc->chanlimit = 2;
 	mode_hfcpci(&hc->bch[0], 1, -1);
 	mode_hfcpci(&hc->bch[1], 2, -1);
@@ -2044,9 +2043,7 @@ setup_hw(struct hfc_pci *hc)
 	Write_hfc(hc, HFCPCI_INT_M1, hc->hw.int_m1);
 	/* At this point the needed PCI config is done */
 	/* fifos are still not enabled */
-	hc->hw.timer.function = (void *) hfcpci_Timer;
-	hc->hw.timer.data = (long) hc;
-	init_timer(&hc->hw.timer);
+	setup_timer(&hc->hw.timer, (void *)hfcpci_Timer, (long)hc);
 	/* default PCM master */
 	test_and_set_bit(HFC_CFG_MASTER, &hc->cfg);
 	return 0;
diff --git a/drivers/isdn/hardware/mISDN/mISDNipac.c b/drivers/isdn/hardware/mISDN/mISDNipac.c
index 77dec28ba874..6742b0dc0821 100644
--- a/drivers/isdn/hardware/mISDN/mISDNipac.c
+++ b/drivers/isdn/hardware/mISDN/mISDNipac.c
@@ -796,9 +796,8 @@ isac_init(struct isac_hw *isac)
 	}
 	isac->mon_tx = NULL;
 	isac->mon_rx = NULL;
-	isac->dch.timer.function = (void *) dbusy_timer_handler;
-	isac->dch.timer.data = (long)isac;
-	init_timer(&isac->dch.timer);
+	setup_timer(&isac->dch.timer, (void *)dbusy_timer_handler,
+		    (long)isac);
 	isac->mocr = 0xaa;
 	if (isac->type & IPAC_TYPE_ISACX) {
 		/* Disable all IRQ */
diff --git a/drivers/isdn/hardware/mISDN/mISDNisar.c b/drivers/isdn/hardware/mISDN/mISDNisar.c
index feafa91c2ed9..5b078591b6ee 100644
--- a/drivers/isdn/hardware/mISDN/mISDNisar.c
+++ b/drivers/isdn/hardware/mISDN/mISDNisar.c
@@ -1635,13 +1635,11 @@ init_isar(struct isar_hw *isar)
 	}
 	if (isar->version != 1)
 		return -EINVAL;
-	isar->ch[0].ftimer.function = &ftimer_handler;
-	isar->ch[0].ftimer.data = (long)&isar->ch[0];
-	init_timer(&isar->ch[0].ftimer);
+	setup_timer(&isar->ch[0].ftimer, &ftimer_handler,
+		    (long)&isar->ch[0]);
 	test_and_set_bit(FLG_INITIALIZED, &isar->ch[0].bch.Flags);
-	isar->ch[1].ftimer.function = &ftimer_handler;
-	isar->ch[1].ftimer.data = (long)&isar->ch[1];
-	init_timer(&isar->ch[1].ftimer);
+	setup_timer(&isar->ch[1].ftimer, &ftimer_handler,
+		    (long)&isar->ch[1]);
 	test_and_set_bit(FLG_INITIALIZED, &isar->ch[1].bch.Flags);
 	return 0;
 }
diff --git a/drivers/isdn/hardware/mISDN/w6692.c b/drivers/isdn/hardware/mISDN/w6692.c
index 3b067ea656bd..3052c836b89f 100644
--- a/drivers/isdn/hardware/mISDN/w6692.c
+++ b/drivers/isdn/hardware/mISDN/w6692.c
@@ -852,9 +852,8 @@ static void initW6692(struct w6692_hw *card)
 {
 	u8	val;
 
-	card->dch.timer.function = (void *)dbusy_timer_handler;
-	card->dch.timer.data = (u_long)&card->dch;
-	init_timer(&card->dch.timer);
+	setup_timer(&card->dch.timer, (void *)dbusy_timer_handler,
+		    (u_long)&card->dch);
 	w6692_mode(&card->bc[0], ISDN_P_NONE);
 	w6692_mode(&card->bc[1], ISDN_P_NONE);
 	WriteW6692(card, W_D_CTL, 0x00);
diff --git a/drivers/isdn/hisax/amd7930_fn.c b/drivers/isdn/hisax/amd7930_fn.c
index 36817e0a0b94..3a4c2f9e19e9 100644
--- a/drivers/isdn/hisax/amd7930_fn.c
+++ b/drivers/isdn/hisax/amd7930_fn.c
@@ -789,7 +789,5 @@ void Amd7930_init(struct IsdnCardState *cs)
 void setup_Amd7930(struct IsdnCardState *cs)
 {
 	INIT_WORK(&cs->tqueue, Amd7930_bh);
-	cs->dbusytimer.function = (void *) dbusy_timer_handler;
-	cs->dbusytimer.data = (long) cs;
-	init_timer(&cs->dbusytimer);
+	setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs);
 }
diff --git a/drivers/isdn/hisax/arcofi.c b/drivers/isdn/hisax/arcofi.c
index 29ec2dfbd155..9826bad49e2c 100644
--- a/drivers/isdn/hisax/arcofi.c
+++ b/drivers/isdn/hisax/arcofi.c
@@ -125,9 +125,7 @@ clear_arcofi(struct IsdnCardState *cs) {
 
 void
 init_arcofi(struct IsdnCardState *cs) {
-	cs->dc.isac.arcofitimer.function = (void *) arcofi_timer;
-	cs->dc.isac.arcofitimer.data = (long) cs;
-	init_timer(&cs->dc.isac.arcofitimer);
+	setup_timer(&cs->dc.isac.arcofitimer, (void *)arcofi_timer, (long)cs);
 	init_waitqueue_head(&cs->dc.isac.arcofi_wait);
 	test_and_set_bit(HW_ARCOFI, &cs->HW_Flags);
 }
diff --git a/drivers/isdn/hisax/diva.c b/drivers/isdn/hisax/diva.c
index 4fc90de68d18..079336e593f9 100644
--- a/drivers/isdn/hisax/diva.c
+++ b/drivers/isdn/hisax/diva.c
@@ -976,9 +976,8 @@ static int setup_diva_common(struct IsdnCardState *cs)
 		printk(KERN_INFO "Diva: IPACX Design Id: %x\n",
 		       MemReadISAC_IPACX(cs, IPACX_ID) & 0x3F);
 	} else { /* DIVA 2.0 */
-		cs->hw.diva.tl.function = (void *) diva_led_handler;
-		cs->hw.diva.tl.data = (long) cs;
-		init_timer(&cs->hw.diva.tl);
+		setup_timer(&cs->hw.diva.tl, (void *)diva_led_handler,
+			    (long)cs);
 		cs->readisac  = &ReadISAC;
 		cs->writeisac = &WriteISAC;
 		cs->readisacfifo  = &ReadISACfifo;
diff --git a/drivers/isdn/hisax/elsa.c b/drivers/isdn/hisax/elsa.c
index d8ef64da26f1..03bc5d504e22 100644
--- a/drivers/isdn/hisax/elsa.c
+++ b/drivers/isdn/hisax/elsa.c
@@ -1147,9 +1147,7 @@ static int setup_elsa_common(struct IsdnCard *card)
 	init_arcofi(cs);
 #endif
 	setup_isac(cs);
-	cs->hw.elsa.tl.function = (void *) elsa_led_handler;
-	cs->hw.elsa.tl.data = (long) cs;
-	init_timer(&cs->hw.elsa.tl);
+	setup_timer(&cs->hw.elsa.tl, (void *)elsa_led_handler, (long)cs);
 	/* Teste Timer */
 	if (cs->hw.elsa.timer) {
 		byteout(cs->hw.elsa.trig, 0xff);
diff --git a/drivers/isdn/hisax/fsm.c b/drivers/isdn/hisax/fsm.c
index c7a94713e9ec..d63266fa8cbd 100644
--- a/drivers/isdn/hisax/fsm.c
+++ b/drivers/isdn/hisax/fsm.c
@@ -98,13 +98,11 @@ void
 FsmInitTimer(struct FsmInst *fi, struct FsmTimer *ft)
 {
 	ft->fi = fi;
-	ft->tl.function = (void *) FsmExpireTimer;
-	ft->tl.data = (long) ft;
 #if FSM_TIMER_DEBUG
 	if (ft->fi->debug)
 		ft->fi->printdebug(ft->fi, "FsmInitTimer %lx", (long) ft);
 #endif
-	init_timer(&ft->tl);
+	setup_timer(&ft->tl, (void *)FsmExpireTimer, (long)ft);
 }
 
 void
diff --git a/drivers/isdn/hisax/hfc4s8s_l1.c b/drivers/isdn/hisax/hfc4s8s_l1.c
index e034ed847ff3..90f051ce0259 100644
--- a/drivers/isdn/hisax/hfc4s8s_l1.c
+++ b/drivers/isdn/hisax/hfc4s8s_l1.c
@@ -1396,9 +1396,8 @@ setup_instance(hfc4s8s_hw *hw)
 		l1p = hw->l1 + i;
 		spin_lock_init(&l1p->lock);
 		l1p->hw = hw;
-		l1p->l1_timer.function = (void *) hfc_l1_timer;
-		l1p->l1_timer.data = (long) (l1p);
-		init_timer(&l1p->l1_timer);
+		setup_timer(&l1p->l1_timer, (void *)hfc_l1_timer,
+			    (long)(l1p));
 		l1p->st_num = i;
 		skb_queue_head_init(&l1p->d_tx_queue);
 		l1p->d_if.ifc.priv = hw->l1 + i;
diff --git a/drivers/isdn/hisax/hfc_2bds0.c b/drivers/isdn/hisax/hfc_2bds0.c
index a756e5cb6871..ad8597a1a07e 100644
--- a/drivers/isdn/hisax/hfc_2bds0.c
+++ b/drivers/isdn/hisax/hfc_2bds0.c
@@ -1073,8 +1073,6 @@ set_cs_func(struct IsdnCardState *cs)
 	cs->writeisacfifo = &dummyf;
 	cs->BC_Read_Reg = &ReadReg;
 	cs->BC_Write_Reg = &WriteReg;
-	cs->dbusytimer.function = (void *) hfc_dbusy_timer;
-	cs->dbusytimer.data = (long) cs;
-	init_timer(&cs->dbusytimer);
+	setup_timer(&cs->dbusytimer, (void *)hfc_dbusy_timer, (long)cs);
 	INIT_WORK(&cs->tqueue, hfcd_bh);
 }
diff --git a/drivers/isdn/hisax/hfc_pci.c b/drivers/isdn/hisax/hfc_pci.c
index 90449e1e91e5..f9ca35cc32b1 100644
--- a/drivers/isdn/hisax/hfc_pci.c
+++ b/drivers/isdn/hisax/hfc_pci.c
@@ -1582,9 +1582,7 @@ inithfcpci(struct IsdnCardState *cs)
 	cs->bcs[1].BC_SetStack = setstack_2b;
 	cs->bcs[0].BC_Close = close_hfcpci;
 	cs->bcs[1].BC_Close = close_hfcpci;
-	cs->dbusytimer.function = (void *) hfcpci_dbusy_timer;
-	cs->dbusytimer.data = (long) cs;
-	init_timer(&cs->dbusytimer);
+	setup_timer(&cs->dbusytimer, (void *)hfcpci_dbusy_timer, (long)cs);
 	mode_hfcpci(cs->bcs, 0, 0);
 	mode_hfcpci(cs->bcs + 1, 0, 1);
 }
@@ -1746,9 +1744,7 @@ setup_hfcpci(struct IsdnCard *card)
 	cs->BC_Write_Reg = NULL;
 	cs->irq_func = &hfcpci_interrupt;
 	cs->irq_flags |= IRQF_SHARED;
-	cs->hw.hfcpci.timer.function = (void *) hfcpci_Timer;
-	cs->hw.hfcpci.timer.data = (long) cs;
-	init_timer(&cs->hw.hfcpci.timer);
+	setup_timer(&cs->hw.hfcpci.timer, (void *)hfcpci_Timer, (long)cs);
 	cs->cardmsg = &hfcpci_card_msg;
 	cs->auxcmd = &hfcpci_auxcmd;
 
diff --git a/drivers/isdn/hisax/hfc_sx.c b/drivers/isdn/hisax/hfc_sx.c
index 13b2151c10f5..3aef8e1a90e4 100644
--- a/drivers/isdn/hisax/hfc_sx.c
+++ b/drivers/isdn/hisax/hfc_sx.c
@@ -1495,9 +1495,7 @@ int setup_hfcsx(struct IsdnCard *card)
 	} else
 		return (0);	/* no valid card type */
 
-	cs->dbusytimer.function = (void *) hfcsx_dbusy_timer;
-	cs->dbusytimer.data = (long) cs;
-	init_timer(&cs->dbusytimer);
+	setup_timer(&cs->dbusytimer, (void *)hfcsx_dbusy_timer, (long)cs);
 	INIT_WORK(&cs->tqueue, hfcsx_bh);
 	cs->readisac = NULL;
 	cs->writeisac = NULL;
@@ -1507,11 +1505,9 @@ int setup_hfcsx(struct IsdnCard *card)
 	cs->BC_Write_Reg = NULL;
 	cs->irq_func = &hfcsx_interrupt;
 
-	cs->hw.hfcsx.timer.function = (void *) hfcsx_Timer;
-	cs->hw.hfcsx.timer.data = (long) cs;
 	cs->hw.hfcsx.b_fifo_size = 0; /* fifo size still unknown */
 	cs->hw.hfcsx.cirm = ccd_sp_irqtab[cs->irq & 0xF]; /* RAM not evaluated */
-	init_timer(&cs->hw.hfcsx.timer);
+	setup_timer(&cs->hw.hfcsx.timer, (void *)hfcsx_Timer, (long)cs);
 
 	reset_hfcsx(cs);
 	cs->cardmsg = &hfcsx_card_msg;
diff --git a/drivers/isdn/hisax/hfc_usb.c b/drivers/isdn/hisax/hfc_usb.c
index 678bd5224bc3..6dbd1f1da14f 100644
--- a/drivers/isdn/hisax/hfc_usb.c
+++ b/drivers/isdn/hisax/hfc_usb.c
@@ -1165,14 +1165,10 @@ hfc_usb_init(hfcusb_data *hfc)
 	hfc->old_led_state = 0;
 
 	/* init the t3 timer */
-	init_timer(&hfc->t3_timer);
-	hfc->t3_timer.data = (long) hfc;
-	hfc->t3_timer.function = (void *) l1_timer_expire_t3;
+	setup_timer(&hfc->t3_timer, (void *)l1_timer_expire_t3, (long)hfc);
 
 	/* init the t4 timer */
-	init_timer(&hfc->t4_timer);
-	hfc->t4_timer.data = (long) hfc;
-	hfc->t4_timer.function = (void *) l1_timer_expire_t4;
+	setup_timer(&hfc->t4_timer, (void *)l1_timer_expire_t4, (long)hfc);
 
 	/* init the background machinery for control requests */
 	hfc->ctrl_read.bRequestType = 0xc0;
diff --git a/drivers/isdn/hisax/hfcscard.c b/drivers/isdn/hisax/hfcscard.c
index 394da646e97b..467287096918 100644
--- a/drivers/isdn/hisax/hfcscard.c
+++ b/drivers/isdn/hisax/hfcscard.c
@@ -253,9 +253,7 @@ int setup_hfcs(struct IsdnCard *card)
 		outb(0x57, cs->hw.hfcD.addr | 1);
 	}
 	set_cs_func(cs);
-	cs->hw.hfcD.timer.function = (void *) hfcs_Timer;
-	cs->hw.hfcD.timer.data = (long) cs;
-	init_timer(&cs->hw.hfcD.timer);
+	setup_timer(&cs->hw.hfcD.timer, (void *)hfcs_Timer, (long)cs);
 	cs->cardmsg = &hfcs_card_msg;
 	cs->irq_func = &hfcs_interrupt;
 	return (1);
diff --git a/drivers/isdn/hisax/icc.c b/drivers/isdn/hisax/icc.c
index 96d1df05044f..c7c3797a817e 100644
--- a/drivers/isdn/hisax/icc.c
+++ b/drivers/isdn/hisax/icc.c
@@ -676,7 +676,5 @@ clear_pending_icc_ints(struct IsdnCardState *cs)
 void setup_icc(struct IsdnCardState *cs)
 {
 	INIT_WORK(&cs->tqueue, icc_bh);
-	cs->dbusytimer.function = (void *) dbusy_timer_handler;
-	cs->dbusytimer.data = (long) cs;
-	init_timer(&cs->dbusytimer);
+	setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs);
 }
diff --git a/drivers/isdn/hisax/ipacx.c b/drivers/isdn/hisax/ipacx.c
index 9cc26b40a437..43effe7082ed 100644
--- a/drivers/isdn/hisax/ipacx.c
+++ b/drivers/isdn/hisax/ipacx.c
@@ -424,9 +424,7 @@ dch_init(struct IsdnCardState *cs)
 
 	cs->setstack_d      = dch_setstack;
 
-	cs->dbusytimer.function = (void *) dbusy_timer_handler;
-	cs->dbusytimer.data = (long) cs;
-	init_timer(&cs->dbusytimer);
+	setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs);
 
 	cs->writeisac(cs, IPACX_TR_CONF0, 0x00);  // clear LDD
 	cs->writeisac(cs, IPACX_TR_CONF2, 0x00);  // enable transmitter
diff --git a/drivers/isdn/hisax/isac.c b/drivers/isdn/hisax/isac.c
index df7e05ca8f9c..4273b4548825 100644
--- a/drivers/isdn/hisax/isac.c
+++ b/drivers/isdn/hisax/isac.c
@@ -677,7 +677,5 @@ void clear_pending_isac_ints(struct IsdnCardState *cs)
 void setup_isac(struct IsdnCardState *cs)
 {
 	INIT_WORK(&cs->tqueue, isac_bh);
-	cs->dbusytimer.function = (void *) dbusy_timer_handler;
-	cs->dbusytimer.data = (long) cs;
-	init_timer(&cs->dbusytimer);
+	setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs);
 }
diff --git a/drivers/isdn/hisax/isar.c b/drivers/isdn/hisax/isar.c
index f4956c73aa11..0dc60b287c4b 100644
--- a/drivers/isdn/hisax/isar.c
+++ b/drivers/isdn/hisax/isar.c
@@ -1902,10 +1902,8 @@ void initisar(struct IsdnCardState *cs)
 	cs->bcs[1].BC_SetStack = setstack_isar;
 	cs->bcs[0].BC_Close = close_isarstate;
 	cs->bcs[1].BC_Close = close_isarstate;
-	cs->bcs[0].hw.isar.ftimer.function = (void *) ftimer_handler;
-	cs->bcs[0].hw.isar.ftimer.data = (long) &cs->bcs[0];
-	init_timer(&cs->bcs[0].hw.isar.ftimer);
-	cs->bcs[1].hw.isar.ftimer.function = (void *) ftimer_handler;
-	cs->bcs[1].hw.isar.ftimer.data = (long) &cs->bcs[1];
-	init_timer(&cs->bcs[1].hw.isar.ftimer);
+	setup_timer(&cs->bcs[0].hw.isar.ftimer, (void *)ftimer_handler,
+		    (long)&cs->bcs[0]);
+	setup_timer(&cs->bcs[1].hw.isar.ftimer, (void *)ftimer_handler,
+		    (long)&cs->bcs[1]);
 }
diff --git a/drivers/isdn/hisax/isdnl3.c b/drivers/isdn/hisax/isdnl3.c
index c754706f83cd..569ce52c567b 100644
--- a/drivers/isdn/hisax/isdnl3.c
+++ b/drivers/isdn/hisax/isdnl3.c
@@ -169,9 +169,7 @@ void
 L3InitTimer(struct l3_process *pc, struct L3Timer *t)
 {
 	t->pc = pc;
-	t->tl.function = (void *) L3ExpireTimer;
-	t->tl.data = (long) t;
-	init_timer(&t->tl);
+	setup_timer(&t->tl, (void *)L3ExpireTimer, (long)t);
 }
 
 void
diff --git a/drivers/isdn/hisax/teleint.c b/drivers/isdn/hisax/teleint.c
index bf647545c70c..950399f066ef 100644
--- a/drivers/isdn/hisax/teleint.c
+++ b/drivers/isdn/hisax/teleint.c
@@ -278,9 +278,7 @@ int setup_TeleInt(struct IsdnCard *card)
 	cs->bcs[0].hw.hfc.send = NULL;
 	cs->bcs[1].hw.hfc.send = NULL;
 	cs->hw.hfc.fifosize = 7 * 1024 + 512;
-	cs->hw.hfc.timer.function = (void *) TeleInt_Timer;
-	cs->hw.hfc.timer.data = (long) cs;
-	init_timer(&cs->hw.hfc.timer);
+	setup_timer(&cs->hw.hfc.timer, (void *)TeleInt_Timer, (long)cs);
 	if (!request_region(cs->hw.hfc.addr, 2, "TeleInt isdn")) {
 		printk(KERN_WARNING
 		       "HiSax: TeleInt config port %x-%x already in use\n",
diff --git a/drivers/isdn/hisax/w6692.c b/drivers/isdn/hisax/w6692.c
index a85895585d90..c99f0ec58a01 100644
--- a/drivers/isdn/hisax/w6692.c
+++ b/drivers/isdn/hisax/w6692.c
@@ -901,9 +901,8 @@ static void initW6692(struct IsdnCardState *cs, int part)
 	if (part & 1) {
 		cs->setstack_d = setstack_W6692;
 		cs->DC_Close = DC_Close_W6692;
-		cs->dbusytimer.function = (void *) dbusy_timer_handler;
-		cs->dbusytimer.data = (long) cs;
-		init_timer(&cs->dbusytimer);
+		setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler,
+			    (long)cs);
 		resetW6692(cs);
 		ph_command(cs, W_L1CMD_RST);
 		cs->dc.w6692.ph_state = W_L1CMD_RST;
diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index 9c1e8adaf4fc..d07dd5196ffc 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -2370,9 +2370,8 @@ static struct ippp_ccp_reset_state *isdn_ppp_ccp_reset_alloc_state(struct ippp_s
 		rs->state = CCPResetIdle;
 		rs->is = is;
 		rs->id = id;
-		init_timer(&rs->timer);
-		rs->timer.data = (unsigned long)rs;
-		rs->timer.function = isdn_ppp_ccp_timer_callback;
+		setup_timer(&rs->timer, isdn_ppp_ccp_timer_callback,
+			    (unsigned long)rs);
 		is->reset->rs[id] = rs;
 	}
 	return rs;
diff --git a/drivers/isdn/i4l/isdn_tty.c b/drivers/isdn/i4l/isdn_tty.c
index 1b169559a240..ddd8207e4e54 100644
--- a/drivers/isdn/i4l/isdn_tty.c
+++ b/drivers/isdn/i4l/isdn_tty.c
@@ -1812,9 +1812,8 @@ isdn_tty_modem_init(void)
 		info->isdn_channel = -1;
 		info->drv_index = -1;
 		info->xmit_size = ISDN_SERIAL_XMIT_SIZE;
-		init_timer(&info->nc_timer);
-		info->nc_timer.function = isdn_tty_modem_do_ncarrier;
-		info->nc_timer.data = (unsigned long) info;
+		setup_timer(&info->nc_timer, isdn_tty_modem_do_ncarrier,
+			    (unsigned long)info);
 		skb_queue_head_init(&info->xmit_queue);
 #ifdef CONFIG_ISDN_AUDIO
 		skb_queue_head_init(&info->dtmf_queue);
diff --git a/drivers/isdn/mISDN/dsp_core.c b/drivers/isdn/mISDN/dsp_core.c
index 9b85295aa657..880e9d367a39 100644
--- a/drivers/isdn/mISDN/dsp_core.c
+++ b/drivers/isdn/mISDN/dsp_core.c
@@ -1092,9 +1092,7 @@ dspcreate(struct channel_req *crq)
 	ndsp->pcm_bank_tx = -1;
 	ndsp->hfc_conf = -1; /* current conference number */
 	/* set tone timer */
-	ndsp->tone.tl.function = (void *)dsp_tone_timeout;
-	ndsp->tone.tl.data = (long) ndsp;
-	init_timer(&ndsp->tone.tl);
+	setup_timer(&ndsp->tone.tl, (void *)dsp_tone_timeout, (long)ndsp);
 
 	if (dtmfthreshold < 20 || dtmfthreshold > 500)
 		dtmfthreshold = 200;
diff --git a/drivers/isdn/mISDN/fsm.c b/drivers/isdn/mISDN/fsm.c
index 26477d48bbda..78fc5d5e9051 100644
--- a/drivers/isdn/mISDN/fsm.c
+++ b/drivers/isdn/mISDN/fsm.c
@@ -110,13 +110,11 @@ void
 mISDN_FsmInitTimer(struct FsmInst *fi, struct FsmTimer *ft)
 {
 	ft->fi = fi;
-	ft->tl.function = (void *) FsmExpireTimer;
-	ft->tl.data = (long) ft;
 #if FSM_TIMER_DEBUG
 	if (ft->fi->debug)
 		ft->fi->printdebug(ft->fi, "mISDN_FsmInitTimer %lx", (long) ft);
 #endif
-	init_timer(&ft->tl);
+	setup_timer(&ft->tl, (void *)FsmExpireTimer, (long)ft);
 }
 EXPORT_SYMBOL(mISDN_FsmInitTimer);
 
diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c
index 6ceca7db62ad..6be2041248d3 100644
--- a/drivers/isdn/mISDN/l1oip_core.c
+++ b/drivers/isdn/mISDN/l1oip_core.c
@@ -1443,9 +1443,7 @@ init_card(struct l1oip *hc, int pri, int bundle)
 	hc->keep_tl.expires = jiffies + 2 * HZ; /* two seconds first time */
 	add_timer(&hc->keep_tl);
 
-	hc->timeout_tl.function = (void *)l1oip_timeout;
-	hc->timeout_tl.data = (ulong)hc;
-	init_timer(&hc->timeout_tl);
+	setup_timer(&hc->timeout_tl, (void *)l1oip_timeout, (ulong)hc);
 	hc->timeout_on = 0; /* state that we have timer off */
 
 	return 0;
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 98ed4d96987c..57fc47ad5ab3 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -18,7 +18,7 @@ obj-$(CONFIG_MII) += mii.o
 obj-$(CONFIG_MDIO) += mdio.o
 obj-$(CONFIG_NET) += Space.o loopback.o
 obj-$(CONFIG_NETCONSOLE) += netconsole.o
-obj-$(CONFIG_PHYLIB) += phy/
+obj-y += phy/
 obj-$(CONFIG_RIONET) += rionet.o
 obj-$(CONFIG_NET_TEAM) += team/
 obj-$(CONFIG_TUN) += tun.o
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index edc70ffad660..c5fd4259da33 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -92,6 +92,7 @@ enum ad_link_speed_type {
 	AD_LINK_SPEED_2500MBPS,
 	AD_LINK_SPEED_10000MBPS,
 	AD_LINK_SPEED_20000MBPS,
+	AD_LINK_SPEED_25000MBPS,
 	AD_LINK_SPEED_40000MBPS,
 	AD_LINK_SPEED_56000MBPS,
 	AD_LINK_SPEED_100000MBPS,
@@ -260,6 +261,7 @@ static inline int __check_agg_selection_timer(struct port *port)
  *     %AD_LINK_SPEED_2500MBPS,
  *     %AD_LINK_SPEED_10000MBPS
  *     %AD_LINK_SPEED_20000MBPS
+ *     %AD_LINK_SPEED_25000MBPS
  *     %AD_LINK_SPEED_40000MBPS
  *     %AD_LINK_SPEED_56000MBPS
  *     %AD_LINK_SPEED_100000MBPS
@@ -302,6 +304,10 @@ static u16 __get_link_speed(struct port *port)
 			speed = AD_LINK_SPEED_20000MBPS;
 			break;
 
+		case SPEED_25000:
+			speed = AD_LINK_SPEED_25000MBPS;
+			break;
+
 		case SPEED_40000:
 			speed = AD_LINK_SPEED_40000MBPS;
 			break;
@@ -707,6 +713,9 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator)
 		case AD_LINK_SPEED_20000MBPS:
 			bandwidth = nports * 20000;
 			break;
+		case AD_LINK_SPEED_25000MBPS:
+			bandwidth = nports * 25000;
+			break;
 		case AD_LINK_SPEED_40000MBPS:
 			bandwidth = nports * 40000;
 			break;
@@ -1052,8 +1061,7 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port)
 		port->sm_rx_state = AD_RX_INITIALIZE;
 		port->sm_vars |= AD_PORT_CHURNED;
 	/* check if port is not enabled */
-	} else if (!(port->sm_vars & AD_PORT_BEGIN)
-		 && !port->is_enabled && !(port->sm_vars & AD_PORT_MOVED))
+	} else if (!(port->sm_vars & AD_PORT_BEGIN) && !port->is_enabled)
 		port->sm_rx_state = AD_RX_PORT_DISABLED;
 	/* check if new lacpdu arrived */
 	else if (lacpdu && ((port->sm_rx_state == AD_RX_EXPIRED) ||
@@ -1081,11 +1089,8 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port)
 			/* if no lacpdu arrived and no timer is on */
 			switch (port->sm_rx_state) {
 			case AD_RX_PORT_DISABLED:
-				if (port->sm_vars & AD_PORT_MOVED)
-					port->sm_rx_state = AD_RX_INITIALIZE;
-				else if (port->is_enabled
-					 && (port->sm_vars
-					     & AD_PORT_LACP_ENABLED))
+				if (port->is_enabled &&
+				    (port->sm_vars & AD_PORT_LACP_ENABLED))
 					port->sm_rx_state = AD_RX_EXPIRED;
 				else if (port->is_enabled
 					 && ((port->sm_vars
@@ -1115,7 +1120,6 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port)
 			port->sm_vars &= ~AD_PORT_SELECTED;
 			__record_default(port);
 			port->actor_oper_port_state &= ~AD_STATE_EXPIRED;
-			port->sm_vars &= ~AD_PORT_MOVED;
 			port->sm_rx_state = AD_RX_PORT_DISABLED;
 
 			/* Fall Through */
@@ -2442,9 +2446,9 @@ void bond_3ad_adapter_speed_duplex_changed(struct slave *slave)
 
 	spin_lock_bh(&slave->bond->mode_lock);
 	ad_update_actor_keys(port, false);
+	spin_unlock_bh(&slave->bond->mode_lock);
 	netdev_dbg(slave->bond->dev, "Port %d slave %s changed speed/duplex\n",
 		   port->actor_port_number, slave->dev->name);
-	spin_unlock_bh(&slave->bond->mode_lock);
 }
 
 /**
@@ -2488,12 +2492,12 @@ void bond_3ad_handle_link_change(struct slave *slave, char link)
 	agg = __get_first_agg(port);
 	ad_agg_selection_logic(agg, &dummy);
 
+	spin_unlock_bh(&slave->bond->mode_lock);
+
 	netdev_dbg(slave->bond->dev, "Port %d changed link status to %s\n",
 		   port->actor_port_number,
 		   link == BOND_LINK_UP ? "UP" : "DOWN");
 
-	spin_unlock_bh(&slave->bond->mode_lock);
-
 	/* RTNL is held and mode_lock is released so it's safe
 	 * to update slave_array here.
 	 */
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index c80b023092dd..7d7a3cec149a 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -687,7 +687,8 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 		/* the arp must be sent on the selected rx channel */
 		tx_slave = rlb_choose_channel(skb, bond);
 		if (tx_slave)
-			ether_addr_copy(arp->mac_src, tx_slave->dev->dev_addr);
+			bond_hw_addr_copy(arp->mac_src, tx_slave->dev->dev_addr,
+					  tx_slave->dev->addr_len);
 		netdev_dbg(bond->dev, "Server sent ARP Reply packet\n");
 	} else if (arp->op_code == htons(ARPOP_REQUEST)) {
 		/* Create an entry in the rx_hashtbl for this client as a
@@ -1017,22 +1018,23 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
 	rcu_read_unlock();
 }
 
-static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[])
+static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[],
+				  unsigned int len)
 {
 	struct net_device *dev = slave->dev;
-	struct sockaddr s_addr;
+	struct sockaddr_storage ss;
 
 	if (BOND_MODE(slave->bond) == BOND_MODE_TLB) {
-		memcpy(dev->dev_addr, addr, dev->addr_len);
+		memcpy(dev->dev_addr, addr, len);
 		return 0;
 	}
 
 	/* for rlb each slave must have a unique hw mac addresses so that
 	 * each slave will receive packets destined to a different mac
 	 */
-	memcpy(s_addr.sa_data, addr, dev->addr_len);
-	s_addr.sa_family = dev->type;
-	if (dev_set_mac_address(dev, &s_addr)) {
+	memcpy(ss.__data, addr, len);
+	ss.ss_family = dev->type;
+	if (dev_set_mac_address(dev, (struct sockaddr *)&ss)) {
 		netdev_err(slave->bond->dev, "dev_set_mac_address of dev %s failed! ALB mode requires that the base driver support setting the hw address also when the network device's interface is open\n",
 			   dev->name);
 		return -EOPNOTSUPP;
@@ -1046,11 +1048,14 @@ static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[])
  */
 static void alb_swap_mac_addr(struct slave *slave1, struct slave *slave2)
 {
-	u8 tmp_mac_addr[ETH_ALEN];
+	u8 tmp_mac_addr[MAX_ADDR_LEN];
 
-	ether_addr_copy(tmp_mac_addr, slave1->dev->dev_addr);
-	alb_set_slave_mac_addr(slave1, slave2->dev->dev_addr);
-	alb_set_slave_mac_addr(slave2, tmp_mac_addr);
+	bond_hw_addr_copy(tmp_mac_addr, slave1->dev->dev_addr,
+			  slave1->dev->addr_len);
+	alb_set_slave_mac_addr(slave1, slave2->dev->dev_addr,
+			       slave2->dev->addr_len);
+	alb_set_slave_mac_addr(slave2, tmp_mac_addr,
+			       slave1->dev->addr_len);
 
 }
 
@@ -1177,7 +1182,8 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav
 		/* Try setting slave mac to bond address and fall-through
 		 * to code handling that situation below...
 		 */
-		alb_set_slave_mac_addr(slave, bond->dev->dev_addr);
+		alb_set_slave_mac_addr(slave, bond->dev->dev_addr,
+				       bond->dev->addr_len);
 	}
 
 	/* The slave's address is equal to the address of the bond.
@@ -1202,7 +1208,8 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav
 	}
 
 	if (free_mac_slave) {
-		alb_set_slave_mac_addr(slave, free_mac_slave->perm_hwaddr);
+		alb_set_slave_mac_addr(slave, free_mac_slave->perm_hwaddr,
+				       free_mac_slave->dev->addr_len);
 
 		netdev_warn(bond->dev, "the hw address of slave %s is in use by the bond; giving it the hw address of %s\n",
 			    slave->dev->name, free_mac_slave->dev->name);
@@ -1234,8 +1241,8 @@ static int alb_set_mac_address(struct bonding *bond, void *addr)
 {
 	struct slave *slave, *rollback_slave;
 	struct list_head *iter;
-	struct sockaddr sa;
-	char tmp_addr[ETH_ALEN];
+	struct sockaddr_storage ss;
+	char tmp_addr[MAX_ADDR_LEN];
 	int res;
 
 	if (bond->alb_info.rlb_enabled)
@@ -1243,12 +1250,14 @@ static int alb_set_mac_address(struct bonding *bond, void *addr)
 
 	bond_for_each_slave(bond, slave, iter) {
 		/* save net_device's current hw address */
-		ether_addr_copy(tmp_addr, slave->dev->dev_addr);
+		bond_hw_addr_copy(tmp_addr, slave->dev->dev_addr,
+				  slave->dev->addr_len);
 
 		res = dev_set_mac_address(slave->dev, addr);
 
 		/* restore net_device's hw address */
-		ether_addr_copy(slave->dev->dev_addr, tmp_addr);
+		bond_hw_addr_copy(slave->dev->dev_addr, tmp_addr,
+				  slave->dev->addr_len);
 
 		if (res)
 			goto unwind;
@@ -1257,16 +1266,19 @@ static int alb_set_mac_address(struct bonding *bond, void *addr)
 	return 0;
 
 unwind:
-	memcpy(sa.sa_data, bond->dev->dev_addr, bond->dev->addr_len);
-	sa.sa_family = bond->dev->type;
+	memcpy(ss.__data, bond->dev->dev_addr, bond->dev->addr_len);
+	ss.ss_family = bond->dev->type;
 
 	/* unwind from head to the slave that failed */
 	bond_for_each_slave(bond, rollback_slave, iter) {
 		if (rollback_slave == slave)
 			break;
-		ether_addr_copy(tmp_addr, rollback_slave->dev->dev_addr);
-		dev_set_mac_address(rollback_slave->dev, &sa);
-		ether_addr_copy(rollback_slave->dev->dev_addr, tmp_addr);
+		bond_hw_addr_copy(tmp_addr, rollback_slave->dev->dev_addr,
+				  rollback_slave->dev->addr_len);
+		dev_set_mac_address(rollback_slave->dev,
+				    (struct sockaddr *)&ss);
+		bond_hw_addr_copy(rollback_slave->dev->dev_addr, tmp_addr,
+				  rollback_slave->dev->addr_len);
 	}
 
 	return res;
@@ -1582,7 +1594,8 @@ int bond_alb_init_slave(struct bonding *bond, struct slave *slave)
 {
 	int res;
 
-	res = alb_set_slave_mac_addr(slave, slave->perm_hwaddr);
+	res = alb_set_slave_mac_addr(slave, slave->perm_hwaddr,
+				     slave->dev->addr_len);
 	if (res)
 		return res;
 
@@ -1696,17 +1709,20 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
 	 * and thus filter bond->dev_addr's packets, so force bond's mac
 	 */
 	if (BOND_MODE(bond) == BOND_MODE_TLB) {
-		struct sockaddr sa;
-		u8 tmp_addr[ETH_ALEN];
+		struct sockaddr_storage ss;
+		u8 tmp_addr[MAX_ADDR_LEN];
 
-		ether_addr_copy(tmp_addr, new_slave->dev->dev_addr);
+		bond_hw_addr_copy(tmp_addr, new_slave->dev->dev_addr,
+				  new_slave->dev->addr_len);
 
-		memcpy(sa.sa_data, bond->dev->dev_addr, bond->dev->addr_len);
-		sa.sa_family = bond->dev->type;
+		bond_hw_addr_copy(ss.__data, bond->dev->dev_addr,
+				  bond->dev->addr_len);
+		ss.ss_family = bond->dev->type;
 		/* we don't care if it can't change its mac, best effort */
-		dev_set_mac_address(new_slave->dev, &sa);
+		dev_set_mac_address(new_slave->dev, (struct sockaddr *)&ss);
 
-		ether_addr_copy(new_slave->dev->dev_addr, tmp_addr);
+		bond_hw_addr_copy(new_slave->dev->dev_addr, tmp_addr,
+				  new_slave->dev->addr_len);
 	}
 
 	/* curr_active_slave must be set before calling alb_swap_mac_addr */
@@ -1716,7 +1732,8 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
 		alb_fasten_mac_swap(bond, swap_slave, new_slave);
 	} else {
 		/* set the new_slave to the bond mac address */
-		alb_set_slave_mac_addr(new_slave, bond->dev->dev_addr);
+		alb_set_slave_mac_addr(new_slave, bond->dev->dev_addr,
+				       bond->dev->addr_len);
 		alb_send_learning_packets(new_slave, bond->dev->dev_addr,
 					  false);
 	}
@@ -1726,19 +1743,19 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
 int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct sockaddr *sa = addr;
+	struct sockaddr_storage *ss = addr;
 	struct slave *curr_active;
 	struct slave *swap_slave;
 	int res;
 
-	if (!is_valid_ether_addr(sa->sa_data))
+	if (!is_valid_ether_addr(ss->__data))
 		return -EADDRNOTAVAIL;
 
 	res = alb_set_mac_address(bond, addr);
 	if (res)
 		return res;
 
-	memcpy(bond_dev->dev_addr, sa->sa_data, bond_dev->addr_len);
+	bond_hw_addr_copy(bond_dev->dev_addr, ss->__data, bond_dev->addr_len);
 
 	/* If there is no curr_active_slave there is nothing else to do.
 	 * Otherwise we'll need to pass the new address to it and handle
@@ -1754,7 +1771,8 @@ int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr)
 		alb_swap_mac_addr(swap_slave, curr_active);
 		alb_fasten_mac_swap(bond, swap_slave, curr_active);
 	} else {
-		alb_set_slave_mac_addr(curr_active, bond_dev->dev_addr);
+		alb_set_slave_mac_addr(curr_active, bond_dev->dev_addr,
+				       bond_dev->addr_len);
 
 		alb_send_learning_packets(curr_active,
 					  bond_dev->dev_addr, false);
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 8a4ba8b88e52..aba7352906a5 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -201,12 +201,6 @@ atomic_t netpoll_block_tx = ATOMIC_INIT(0);
 
 unsigned int bond_net_id __read_mostly;
 
-static __be32 arp_target[BOND_MAX_ARP_TARGETS];
-static int arp_ip_count;
-static int bond_mode	= BOND_MODE_ROUNDROBIN;
-static int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
-static int lacp_fast;
-
 /*-------------------------- Forward declarations ---------------------------*/
 
 static int bond_init(struct net_device *bond_dev);
@@ -371,9 +365,10 @@ down:
 /* Get link speed and duplex from the slave's base driver
  * using ethtool. If for some reason the call fails or the
  * values are invalid, set speed and duplex to -1,
- * and return.
+ * and return. Return 1 if speed or duplex settings are
+ * UNKNOWN; 0 otherwise.
  */
-static void bond_update_speed_duplex(struct slave *slave)
+static int bond_update_speed_duplex(struct slave *slave)
 {
 	struct net_device *slave_dev = slave->dev;
 	struct ethtool_link_ksettings ecmd;
@@ -384,23 +379,21 @@ static void bond_update_speed_duplex(struct slave *slave)
 
 	res = __ethtool_get_link_ksettings(slave_dev, &ecmd);
 	if (res < 0)
-		return;
-
+		return 1;
 	if (ecmd.base.speed == 0 || ecmd.base.speed == ((__u32)-1))
-		return;
-
+		return 1;
 	switch (ecmd.base.duplex) {
 	case DUPLEX_FULL:
 	case DUPLEX_HALF:
 		break;
 	default:
-		return;
+		return 1;
 	}
 
 	slave->speed = ecmd.base.speed;
 	slave->duplex = ecmd.base.duplex;
 
-	return;
+	return 0;
 }
 
 const char *bond_slave_link_status(s8 link)
@@ -652,8 +645,8 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 				  struct slave *new_active,
 				  struct slave *old_active)
 {
-	u8 tmp_mac[ETH_ALEN];
-	struct sockaddr saddr;
+	u8 tmp_mac[MAX_ADDR_LEN];
+	struct sockaddr_storage ss;
 	int rv;
 
 	switch (bond->params.fail_over_mac) {
@@ -673,16 +666,20 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 			old_active = bond_get_old_active(bond, new_active);
 
 		if (old_active) {
-			ether_addr_copy(tmp_mac, new_active->dev->dev_addr);
-			ether_addr_copy(saddr.sa_data,
-					old_active->dev->dev_addr);
-			saddr.sa_family = new_active->dev->type;
+			bond_hw_addr_copy(tmp_mac, new_active->dev->dev_addr,
+					  new_active->dev->addr_len);
+			bond_hw_addr_copy(ss.__data,
+					  old_active->dev->dev_addr,
+					  old_active->dev->addr_len);
+			ss.ss_family = new_active->dev->type;
 		} else {
-			ether_addr_copy(saddr.sa_data, bond->dev->dev_addr);
-			saddr.sa_family = bond->dev->type;
+			bond_hw_addr_copy(ss.__data, bond->dev->dev_addr,
+					  bond->dev->addr_len);
+			ss.ss_family = bond->dev->type;
 		}
 
-		rv = dev_set_mac_address(new_active->dev, &saddr);
+		rv = dev_set_mac_address(new_active->dev,
+					 (struct sockaddr *)&ss);
 		if (rv) {
 			netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
 				   -rv, new_active->dev->name);
@@ -692,10 +689,12 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 		if (!old_active)
 			goto out;
 
-		ether_addr_copy(saddr.sa_data, tmp_mac);
-		saddr.sa_family = old_active->dev->type;
+		bond_hw_addr_copy(ss.__data, tmp_mac,
+				  new_active->dev->addr_len);
+		ss.ss_family = old_active->dev->type;
 
-		rv = dev_set_mac_address(old_active->dev, &saddr);
+		rv = dev_set_mac_address(old_active->dev,
+					 (struct sockaddr *)&ss);
 		if (rv)
 			netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
 				   -rv, new_active->dev->name);
@@ -1191,7 +1190,8 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 			kfree_skb(skb);
 			return RX_HANDLER_CONSUMED;
 		}
-		ether_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr);
+		bond_hw_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr,
+				  bond->dev->addr_len);
 	}
 
 	return ret;
@@ -1330,7 +1330,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 	const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
 	struct slave *new_slave = NULL, *prev_slave;
-	struct sockaddr addr;
+	struct sockaddr_storage ss;
 	int link_reporting;
 	int res = 0, i;
 
@@ -1481,16 +1481,17 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	 * that need it, and for restoring it upon release, and then
 	 * set it to the master's address
 	 */
-	ether_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr);
+	bond_hw_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr,
+			  slave_dev->addr_len);
 
 	if (!bond->params.fail_over_mac ||
 	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 		/* Set slave to master's mac address.  The application already
 		 * set the master's mac address to that of the first slave
 		 */
-		memcpy(addr.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
-		addr.sa_family = slave_dev->type;
-		res = dev_set_mac_address(slave_dev, &addr);
+		memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
+		ss.ss_family = slave_dev->type;
+		res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss);
 		if (res) {
 			netdev_dbg(bond_dev, "Error %d calling set_mac_address\n", res);
 			goto err_restore_mtu;
@@ -1565,7 +1566,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	new_slave->delay = 0;
 	new_slave->link_failure_count = 0;
 
-	bond_update_speed_duplex(new_slave);
+	if (bond_update_speed_duplex(new_slave))
+		new_slave->link = BOND_LINK_DOWN;
 
 	new_slave->last_rx = jiffies -
 		(msecs_to_jiffies(bond->params.arp_interval) + 1);
@@ -1773,9 +1775,10 @@ err_restore_mac:
 		 * MAC if this slave's MAC is in use by the bond, or at
 		 * least print a warning.
 		 */
-		ether_addr_copy(addr.sa_data, new_slave->perm_hwaddr);
-		addr.sa_family = slave_dev->type;
-		dev_set_mac_address(slave_dev, &addr);
+		bond_hw_addr_copy(ss.__data, new_slave->perm_hwaddr,
+				  new_slave->dev->addr_len);
+		ss.ss_family = slave_dev->type;
+		dev_set_mac_address(slave_dev, (struct sockaddr *)&ss);
 	}
 
 err_restore_mtu:
@@ -1818,7 +1821,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave, *oldcurrent;
-	struct sockaddr addr;
+	struct sockaddr_storage ss;
 	int old_flags = bond_dev->flags;
 	netdev_features_t old_features = bond_dev->features;
 
@@ -1953,9 +1956,10 @@ static int __bond_release_one(struct net_device *bond_dev,
 	if (bond->params.fail_over_mac != BOND_FOM_ACTIVE ||
 	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 		/* restore original ("permanent") mac address */
-		ether_addr_copy(addr.sa_data, slave->perm_hwaddr);
-		addr.sa_family = slave_dev->type;
-		dev_set_mac_address(slave_dev, &addr);
+		bond_hw_addr_copy(ss.__data, slave->perm_hwaddr,
+				  slave->dev->addr_len);
+		ss.ss_family = slave_dev->type;
+		dev_set_mac_address(slave_dev, (struct sockaddr *)&ss);
 	}
 
 	dev_set_mtu(slave_dev, slave->original_mtu);
@@ -2039,8 +2043,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 			if (link_state)
 				continue;
 
-			bond_set_slave_link_state(slave, BOND_LINK_FAIL,
-						  BOND_SLAVE_NOTIFY_LATER);
+			bond_propose_link_state(slave, BOND_LINK_FAIL);
 			slave->delay = bond->params.downdelay;
 			if (slave->delay) {
 				netdev_info(bond->dev, "link status down for %sinterface %s, disabling it in %d ms\n",
@@ -2055,8 +2058,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 		case BOND_LINK_FAIL:
 			if (link_state) {
 				/* recovered before downdelay expired */
-				bond_set_slave_link_state(slave, BOND_LINK_UP,
-							  BOND_SLAVE_NOTIFY_LATER);
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				slave->last_link_up = jiffies;
 				netdev_info(bond->dev, "link status up again after %d ms for interface %s\n",
 					    (bond->params.downdelay - slave->delay) *
@@ -2078,8 +2080,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 			if (!link_state)
 				continue;
 
-			bond_set_slave_link_state(slave, BOND_LINK_BACK,
-						  BOND_SLAVE_NOTIFY_LATER);
+			bond_propose_link_state(slave, BOND_LINK_BACK);
 			slave->delay = bond->params.updelay;
 
 			if (slave->delay) {
@@ -2092,9 +2093,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 			/*FALLTHRU*/
 		case BOND_LINK_BACK:
 			if (!link_state) {
-				bond_set_slave_link_state(slave,
-							  BOND_LINK_DOWN,
-							  BOND_SLAVE_NOTIFY_LATER);
+				bond_propose_link_state(slave, BOND_LINK_DOWN);
 				netdev_info(bond->dev, "link status down again after %d ms for interface %s\n",
 					    (bond->params.updelay - slave->delay) *
 					    bond->params.miimon,
@@ -2132,7 +2131,13 @@ static void bond_miimon_commit(struct bonding *bond)
 			continue;
 
 		case BOND_LINK_UP:
-			bond_update_speed_duplex(slave);
+			if (bond_update_speed_duplex(slave)) {
+				slave->link = BOND_LINK_DOWN;
+				netdev_warn(bond->dev,
+					    "failed to get link speed/duplex for %s\n",
+					    slave->dev->name);
+				continue;
+			}
 			bond_set_slave_link_state(slave, BOND_LINK_UP,
 						  BOND_SLAVE_NOTIFY_NOW);
 			slave->last_link_up = jiffies;
@@ -2231,6 +2236,8 @@ static void bond_mii_monitor(struct work_struct *work)
 					    mii_work.work);
 	bool should_notify_peers = false;
 	unsigned long delay;
+	struct slave *slave;
+	struct list_head *iter;
 
 	delay = msecs_to_jiffies(bond->params.miimon);
 
@@ -2251,6 +2258,9 @@ static void bond_mii_monitor(struct work_struct *work)
 			goto re_arm;
 		}
 
+		bond_for_each_slave(bond, slave, iter) {
+			bond_commit_link_state(slave, BOND_SLAVE_NOTIFY_LATER);
+		}
 		bond_miimon_commit(bond);
 
 		rtnl_unlock();	/* might sleep, hold no other locks */
@@ -2575,10 +2585,8 @@ static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
  * arp is transmitted to generate traffic. see activebackup_arp_monitor for
  * arp monitoring in active backup mode.
  */
-static void bond_loadbalance_arp_mon(struct work_struct *work)
+static void bond_loadbalance_arp_mon(struct bonding *bond)
 {
-	struct bonding *bond = container_of(work, struct bonding,
-					    arp_work.work);
 	struct slave *slave, *oldcurrent;
 	struct list_head *iter;
 	int do_failover = 0, slave_state_changed = 0;
@@ -2916,10 +2924,8 @@ check_state:
 	return should_notify_rtnl;
 }
 
-static void bond_activebackup_arp_mon(struct work_struct *work)
+static void bond_activebackup_arp_mon(struct bonding *bond)
 {
-	struct bonding *bond = container_of(work, struct bonding,
-					    arp_work.work);
 	bool should_notify_peers = false;
 	bool should_notify_rtnl = false;
 	int delta_in_ticks;
@@ -2972,6 +2978,17 @@ re_arm:
 	}
 }
 
+static void bond_arp_monitor(struct work_struct *work)
+{
+	struct bonding *bond = container_of(work, struct bonding,
+					    arp_work.work);
+
+	if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
+		bond_activebackup_arp_mon(bond);
+	else
+		bond_loadbalance_arp_mon(bond);
+}
+
 /*-------------------------- netdev event handling --------------------------*/
 
 /* Change device name */
@@ -3228,10 +3245,7 @@ static void bond_work_init_all(struct bonding *bond)
 			  bond_resend_igmp_join_requests_delayed);
 	INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor);
 	INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor);
-	if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
-		INIT_DELAYED_WORK(&bond->arp_work, bond_activebackup_arp_mon);
-	else
-		INIT_DELAYED_WORK(&bond->arp_work, bond_loadbalance_arp_mon);
+	INIT_DELAYED_WORK(&bond->arp_work, bond_arp_monitor);
 	INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler);
 	INIT_DELAYED_WORK(&bond->slave_arr_work, bond_slave_arr_handler);
 }
@@ -3266,8 +3280,6 @@ static int bond_open(struct net_device *bond_dev)
 		}
 	}
 
-	bond_work_init_all(bond);
-
 	if (bond_is_lb(bond)) {
 		/* bond_alb_initialize must be called before the timer
 		 * is started.
@@ -3327,12 +3339,17 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res,
 	for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) {
 		u64 nv = new[i];
 		u64 ov = old[i];
+		s64 delta = nv - ov;
 
 		/* detects if this particular field is 32bit only */
 		if (((nv | ov) >> 32) == 0)
-			res[i] += (u32)nv - (u32)ov;
-		else
-			res[i] += nv - ov;
+			delta = (s64)(s32)((u32)nv - (u32)ov);
+
+		/* filter anomalies, some drivers reset their stats
+		 * at down/up events.
+		 */
+		if (delta > 0)
+			res[i] += delta;
 	}
 }
 
@@ -3619,7 +3636,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave, *rollback_slave;
-	struct sockaddr *sa = addr, tmp_sa;
+	struct sockaddr_storage *ss = addr, tmp_ss;
 	struct list_head *iter;
 	int res = 0;
 
@@ -3636,7 +3653,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 	    BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
 		return 0;
 
-	if (!is_valid_ether_addr(sa->sa_data))
+	if (!is_valid_ether_addr(ss->__data))
 		return -EADDRNOTAVAIL;
 
 	bond_for_each_slave(bond, slave, iter) {
@@ -3655,12 +3672,12 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 	}
 
 	/* success */
-	memcpy(bond_dev->dev_addr, sa->sa_data, bond_dev->addr_len);
+	memcpy(bond_dev->dev_addr, ss->__data, bond_dev->addr_len);
 	return 0;
 
 unwind:
-	memcpy(tmp_sa.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
-	tmp_sa.sa_family = bond_dev->type;
+	memcpy(tmp_ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
+	tmp_ss.ss_family = bond_dev->type;
 
 	/* unwind from head to the slave that failed */
 	bond_for_each_slave(bond, rollback_slave, iter) {
@@ -3669,7 +3686,8 @@ unwind:
 		if (rollback_slave == slave)
 			break;
 
-		tmp_res = dev_set_mac_address(rollback_slave->dev, &tmp_sa);
+		tmp_res = dev_set_mac_address(rollback_slave->dev,
+					      (struct sockaddr *)&tmp_ss);
 		if (tmp_res) {
 			netdev_dbg(bond_dev, "unwind err %d dev %s\n",
 				   tmp_res, rollback_slave->dev->name);
@@ -4252,6 +4270,12 @@ static int bond_check_params(struct bond_params *params)
 	int arp_all_targets_value;
 	u16 ad_actor_sys_prio = 0;
 	u16 ad_user_port_key = 0;
+	__be32 arp_target[BOND_MAX_ARP_TARGETS];
+	int arp_ip_count;
+	int bond_mode	= BOND_MODE_ROUNDROBIN;
+	int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
+	int lacp_fast = 0;
+	int tlb_dynamic_lb = 0;
 
 	/* Convert string parameters. */
 	if (mode) {
@@ -4564,6 +4588,17 @@ static int bond_check_params(struct bond_params *params)
 	}
 	ad_user_port_key = valptr->value;
 
+	if (bond_mode == BOND_MODE_TLB) {
+		bond_opt_initstr(&newval, "default");
+		valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB),
+					&newval);
+		if (!valptr) {
+			pr_err("Error: No tlb_dynamic_lb default value");
+			return -EINVAL;
+		}
+		tlb_dynamic_lb = valptr->value;
+	}
+
 	if (lp_interval == 0) {
 		pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n",
 			INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL);
@@ -4591,7 +4626,7 @@ static int bond_check_params(struct bond_params *params)
 	params->min_links = min_links;
 	params->lp_interval = lp_interval;
 	params->packets_per_slave = packets_per_slave;
-	params->tlb_dynamic_lb = 1; /* Default value */
+	params->tlb_dynamic_lb = tlb_dynamic_lb;
 	params->ad_actor_sys_prio = ad_actor_sys_prio;
 	eth_zero_addr(params->ad_actor_system);
 	params->ad_user_port_key = ad_user_port_key;
@@ -4687,6 +4722,8 @@ int bond_create(struct net *net, const char *name)
 
 	netif_carrier_off(bond_dev);
 
+	bond_work_init_all(bond);
+
 	rtnl_unlock();
 	if (res < 0)
 		bond_destructor(bond_dev);
diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c
index f514fe5e80a5..d8d4ada034b7 100644
--- a/drivers/net/bonding/bond_procfs.c
+++ b/drivers/net/bonding/bond_procfs.c
@@ -183,7 +183,8 @@ static void bond_info_show_slave(struct seq_file *seq,
 	seq_printf(seq, "Link Failure Count: %u\n",
 		   slave->link_failure_count);
 
-	seq_printf(seq, "Permanent HW addr: %pM\n", slave->perm_hwaddr);
+	seq_printf(seq, "Permanent HW addr: %*phC\n",
+		   slave->dev->addr_len, slave->perm_hwaddr);
 	seq_printf(seq, "Slave queue ID: %d\n", slave->queue_id);
 
 	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
diff --git a/drivers/net/can/spi/Kconfig b/drivers/net/can/spi/Kconfig
index 148cae5871a6..8f2e0dd7b756 100644
--- a/drivers/net/can/spi/Kconfig
+++ b/drivers/net/can/spi/Kconfig
@@ -1,6 +1,12 @@
 menu "CAN SPI interfaces"
 	depends on SPI
 
+config CAN_HI311X
+	tristate "Holt HI311x SPI CAN controllers"
+	depends on CAN_DEV && SPI && HAS_DMA
+	---help---
+	  Driver for the Holt HI311x SPI CAN controllers.
+
 config CAN_MCP251X
 	tristate "Microchip MCP251x SPI CAN controllers"
 	depends on HAS_DMA
diff --git a/drivers/net/can/spi/Makefile b/drivers/net/can/spi/Makefile
index 0e86040cdd8c..f59fa3731073 100644
--- a/drivers/net/can/spi/Makefile
+++ b/drivers/net/can/spi/Makefile
@@ -3,4 +3,5 @@
 #
 
 
+obj-$(CONFIG_CAN_HI311X)	+= hi311x.o
 obj-$(CONFIG_CAN_MCP251X)	+= mcp251x.o
diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c
new file mode 100644
index 000000000000..5590c559a8ca
--- /dev/null
+++ b/drivers/net/can/spi/hi311x.c
@@ -0,0 +1,1076 @@
+/* CAN bus driver for Holt HI3110 CAN Controller with SPI Interface
+ *
+ * Copyright(C) Timesys Corporation 2016
+ *
+ * Based on Microchip 251x CAN Controller (mcp251x) Linux kernel driver
+ * Copyright 2009 Christian Pellegrin EVOL S.r.l.
+ * Copyright 2007 Raymarine UK, Ltd. All Rights Reserved.
+ * Copyright 2006 Arcom Control Systems Ltd.
+ *
+ * Based on CAN bus driver for the CCAN controller written by
+ * - Sascha Hauer, Marc Kleine-Budde, Pengutronix
+ * - Simon Kallweit, intefo AG
+ * Copyright 2007
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/can/core.h>
+#include <linux/can/dev.h>
+#include <linux/can/led.h>
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/freezer.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+#include <linux/spi/spi.h>
+#include <linux/uaccess.h>
+
+#define HI3110_MASTER_RESET 0x56
+#define HI3110_READ_CTRL0 0xD2
+#define HI3110_READ_CTRL1 0xD4
+#define HI3110_READ_STATF 0xE2
+#define HI3110_WRITE_CTRL0 0x14
+#define HI3110_WRITE_CTRL1 0x16
+#define HI3110_WRITE_INTE 0x1C
+#define HI3110_WRITE_BTR0 0x18
+#define HI3110_WRITE_BTR1 0x1A
+#define HI3110_READ_BTR0 0xD6
+#define HI3110_READ_BTR1 0xD8
+#define HI3110_READ_INTF 0xDE
+#define HI3110_READ_ERR 0xDC
+#define HI3110_READ_FIFO_WOTIME 0x48
+#define HI3110_WRITE_FIFO 0x12
+#define HI3110_READ_MESSTAT 0xDA
+#define HI3110_READ_REC 0xEA
+#define HI3110_READ_TEC 0xEC
+
+#define HI3110_CTRL0_MODE_MASK (7 << 5)
+#define HI3110_CTRL0_NORMAL_MODE (0 << 5)
+#define HI3110_CTRL0_LOOPBACK_MODE (1 << 5)
+#define HI3110_CTRL0_MONITOR_MODE (2 << 5)
+#define HI3110_CTRL0_SLEEP_MODE (3 << 5)
+#define HI3110_CTRL0_INIT_MODE (4 << 5)
+
+#define HI3110_CTRL1_TXEN BIT(7)
+
+#define HI3110_INT_RXTMP BIT(7)
+#define HI3110_INT_RXFIFO BIT(6)
+#define HI3110_INT_TXCPLT BIT(5)
+#define HI3110_INT_BUSERR BIT(4)
+#define HI3110_INT_MCHG BIT(3)
+#define HI3110_INT_WAKEUP BIT(2)
+#define HI3110_INT_F1MESS BIT(1)
+#define HI3110_INT_F0MESS BIT(0)
+
+#define HI3110_ERR_BUSOFF BIT(7)
+#define HI3110_ERR_TXERRP BIT(6)
+#define HI3110_ERR_RXERRP BIT(5)
+#define HI3110_ERR_BITERR BIT(4)
+#define HI3110_ERR_FRMERR BIT(3)
+#define HI3110_ERR_CRCERR BIT(2)
+#define HI3110_ERR_ACKERR BIT(1)
+#define HI3110_ERR_STUFERR BIT(0)
+#define HI3110_ERR_PROTOCOL_MASK (0x1F)
+#define HI3110_ERR_PASSIVE_MASK (0x60)
+
+#define HI3110_STAT_RXFMTY BIT(1)
+#define HI3110_STAT_BUSOFF BIT(2)
+#define HI3110_STAT_ERRP BIT(3)
+#define HI3110_STAT_ERRW BIT(4)
+
+#define HI3110_BTR0_SJW_SHIFT 6
+#define HI3110_BTR0_BRP_SHIFT 0
+
+#define HI3110_BTR1_SAMP_3PERBIT (1 << 7)
+#define HI3110_BTR1_SAMP_1PERBIT (0 << 7)
+#define HI3110_BTR1_TSEG2_SHIFT 4
+#define HI3110_BTR1_TSEG1_SHIFT 0
+
+#define HI3110_FIFO_WOTIME_TAG_OFF 0
+#define HI3110_FIFO_WOTIME_ID_OFF 1
+#define HI3110_FIFO_WOTIME_DLC_OFF 5
+#define HI3110_FIFO_WOTIME_DAT_OFF 6
+
+#define HI3110_FIFO_WOTIME_TAG_IDE BIT(7)
+#define HI3110_FIFO_WOTIME_ID_RTR BIT(0)
+
+#define HI3110_FIFO_TAG_OFF 0
+#define HI3110_FIFO_ID_OFF 1
+#define HI3110_FIFO_STD_DLC_OFF 3
+#define HI3110_FIFO_STD_DATA_OFF 4
+#define HI3110_FIFO_EXT_DLC_OFF 5
+#define HI3110_FIFO_EXT_DATA_OFF 6
+
+#define HI3110_CAN_MAX_DATA_LEN 8
+#define HI3110_RX_BUF_LEN 15
+#define HI3110_TX_STD_BUF_LEN 12
+#define HI3110_TX_EXT_BUF_LEN 14
+#define HI3110_CAN_FRAME_MAX_BITS 128
+#define HI3110_EFF_FLAGS 0x18 /* IDE + SRR */
+
+#define HI3110_TX_ECHO_SKB_MAX 1
+
+#define HI3110_OST_DELAY_MS (10)
+
+#define DEVICE_NAME "hi3110"
+
+static int hi3110_enable_dma = 1; /* Enable SPI DMA. Default: 1 (On) */
+module_param(hi3110_enable_dma, int, 0444);
+MODULE_PARM_DESC(hi3110_enable_dma, "Enable SPI DMA. Default: 1 (On)");
+
+static const struct can_bittiming_const hi3110_bittiming_const = {
+	.name = DEVICE_NAME,
+	.tseg1_min = 2,
+	.tseg1_max = 16,
+	.tseg2_min = 2,
+	.tseg2_max = 8,
+	.sjw_max = 4,
+	.brp_min = 1,
+	.brp_max = 64,
+	.brp_inc = 1,
+};
+
+enum hi3110_model {
+	CAN_HI3110_HI3110 = 0x3110,
+};
+
+struct hi3110_priv {
+	struct can_priv can;
+	struct net_device *net;
+	struct spi_device *spi;
+	enum hi3110_model model;
+
+	struct mutex hi3110_lock; /* SPI device lock */
+
+	u8 *spi_tx_buf;
+	u8 *spi_rx_buf;
+	dma_addr_t spi_tx_dma;
+	dma_addr_t spi_rx_dma;
+
+	struct sk_buff *tx_skb;
+	int tx_len;
+
+	struct workqueue_struct *wq;
+	struct work_struct tx_work;
+	struct work_struct restart_work;
+
+	int force_quit;
+	int after_suspend;
+#define HI3110_AFTER_SUSPEND_UP 1
+#define HI3110_AFTER_SUSPEND_DOWN 2
+#define HI3110_AFTER_SUSPEND_POWER 4
+#define HI3110_AFTER_SUSPEND_RESTART 8
+	int restart_tx;
+	struct regulator *power;
+	struct regulator *transceiver;
+	struct clk *clk;
+};
+
+static void hi3110_clean(struct net_device *net)
+{
+	struct hi3110_priv *priv = netdev_priv(net);
+
+	if (priv->tx_skb || priv->tx_len)
+		net->stats.tx_errors++;
+	if (priv->tx_skb)
+		dev_kfree_skb(priv->tx_skb);
+	if (priv->tx_len)
+		can_free_echo_skb(priv->net, 0);
+	priv->tx_skb = NULL;
+	priv->tx_len = 0;
+}
+
+/* Note about handling of error return of hi3110_spi_trans: accessing
+ * registers via SPI is not really different conceptually than using
+ * normal I/O assembler instructions, although it's much more
+ * complicated from a practical POV. So it's not advisable to always
+ * check the return value of this function. Imagine that every
+ * read{b,l}, write{b,l} and friends would be bracketed in "if ( < 0)
+ * error();", it would be a great mess (well there are some situation
+ * when exception handling C++ like could be useful after all). So we
+ * just check that transfers are OK at the beginning of our
+ * conversation with the chip and to avoid doing really nasty things
+ * (like injecting bogus packets in the network stack).
+ */
+static int hi3110_spi_trans(struct spi_device *spi, int len)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+	struct spi_transfer t = {
+		.tx_buf = priv->spi_tx_buf,
+		.rx_buf = priv->spi_rx_buf,
+		.len = len,
+		.cs_change = 0,
+	};
+	struct spi_message m;
+	int ret;
+
+	spi_message_init(&m);
+
+	if (hi3110_enable_dma) {
+		t.tx_dma = priv->spi_tx_dma;
+		t.rx_dma = priv->spi_rx_dma;
+		m.is_dma_mapped = 1;
+	}
+
+	spi_message_add_tail(&t, &m);
+
+	ret = spi_sync(spi, &m);
+
+	if (ret)
+		dev_err(&spi->dev, "spi transfer failed: ret = %d\n", ret);
+	return ret;
+}
+
+static u8 hi3110_cmd(struct spi_device *spi, u8 command)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+
+	priv->spi_tx_buf[0] = command;
+	dev_dbg(&spi->dev, "hi3110_cmd: %02X\n", command);
+
+	return hi3110_spi_trans(spi, 1);
+}
+
+static u8 hi3110_read(struct spi_device *spi, u8 command)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+	u8 val = 0;
+
+	priv->spi_tx_buf[0] = command;
+	hi3110_spi_trans(spi, 2);
+	val = priv->spi_rx_buf[1];
+
+	return val;
+}
+
+static void hi3110_write(struct spi_device *spi, u8 reg, u8 val)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+
+	priv->spi_tx_buf[0] = reg;
+	priv->spi_tx_buf[1] = val;
+	hi3110_spi_trans(spi, 2);
+}
+
+static void hi3110_hw_tx_frame(struct spi_device *spi, u8 *buf, int len)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+
+	priv->spi_tx_buf[0] = HI3110_WRITE_FIFO;
+	memcpy(priv->spi_tx_buf + 1, buf, len);
+	hi3110_spi_trans(spi, len + 1);
+}
+
+static void hi3110_hw_tx(struct spi_device *spi, struct can_frame *frame)
+{
+	u8 buf[HI3110_TX_EXT_BUF_LEN];
+
+	buf[HI3110_FIFO_TAG_OFF] = 0;
+
+	if (frame->can_id & CAN_EFF_FLAG) {
+		/* Extended frame */
+		buf[HI3110_FIFO_ID_OFF] = (frame->can_id & CAN_EFF_MASK) >> 21;
+		buf[HI3110_FIFO_ID_OFF + 1] =
+			(((frame->can_id & CAN_EFF_MASK) >> 13) & 0xe0) |
+			HI3110_EFF_FLAGS |
+			(((frame->can_id & CAN_EFF_MASK) >> 15) & 0x07);
+		buf[HI3110_FIFO_ID_OFF + 2] =
+			(frame->can_id & CAN_EFF_MASK) >> 7;
+		buf[HI3110_FIFO_ID_OFF + 3] =
+			((frame->can_id & CAN_EFF_MASK) << 1) |
+			((frame->can_id & CAN_RTR_FLAG) ? 1 : 0);
+
+		buf[HI3110_FIFO_EXT_DLC_OFF] = frame->can_dlc;
+
+		memcpy(buf + HI3110_FIFO_EXT_DATA_OFF,
+		       frame->data, frame->can_dlc);
+
+		hi3110_hw_tx_frame(spi, buf, HI3110_TX_EXT_BUF_LEN -
+				   (HI3110_CAN_MAX_DATA_LEN - frame->can_dlc));
+	} else {
+		/* Standard frame */
+		buf[HI3110_FIFO_ID_OFF] =   (frame->can_id & CAN_SFF_MASK) >> 3;
+		buf[HI3110_FIFO_ID_OFF + 1] =
+			((frame->can_id & CAN_SFF_MASK) << 5) |
+			((frame->can_id & CAN_RTR_FLAG) ? (1 << 4) : 0);
+
+		buf[HI3110_FIFO_STD_DLC_OFF] = frame->can_dlc;
+
+		memcpy(buf + HI3110_FIFO_STD_DATA_OFF,
+		       frame->data, frame->can_dlc);
+
+		hi3110_hw_tx_frame(spi, buf, HI3110_TX_STD_BUF_LEN -
+				   (HI3110_CAN_MAX_DATA_LEN - frame->can_dlc));
+	}
+}
+
+static void hi3110_hw_rx_frame(struct spi_device *spi, u8 *buf)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+
+	priv->spi_tx_buf[0] = HI3110_READ_FIFO_WOTIME;
+	hi3110_spi_trans(spi, HI3110_RX_BUF_LEN);
+	memcpy(buf, priv->spi_rx_buf + 1, HI3110_RX_BUF_LEN - 1);
+}
+
+static void hi3110_hw_rx(struct spi_device *spi)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+	struct sk_buff *skb;
+	struct can_frame *frame;
+	u8 buf[HI3110_RX_BUF_LEN - 1];
+
+	skb = alloc_can_skb(priv->net, &frame);
+	if (!skb) {
+		priv->net->stats.rx_dropped++;
+		return;
+	}
+
+	hi3110_hw_rx_frame(spi, buf);
+	if (buf[HI3110_FIFO_WOTIME_TAG_OFF] & HI3110_FIFO_WOTIME_TAG_IDE) {
+		/* IDE is recessive (1), indicating extended 29-bit frame */
+		frame->can_id = CAN_EFF_FLAG;
+		frame->can_id |=
+			(buf[HI3110_FIFO_WOTIME_ID_OFF] << 21) |
+			(((buf[HI3110_FIFO_WOTIME_ID_OFF + 1] & 0xE0) >> 5) << 18) |
+			((buf[HI3110_FIFO_WOTIME_ID_OFF + 1] & 0x07) << 15) |
+			(buf[HI3110_FIFO_WOTIME_ID_OFF + 2] << 7) |
+			(buf[HI3110_FIFO_WOTIME_ID_OFF + 3] >> 1);
+	} else {
+		/* IDE is dominant (0), frame indicating standard 11-bit */
+		frame->can_id =
+			(buf[HI3110_FIFO_WOTIME_ID_OFF] << 3) |
+			((buf[HI3110_FIFO_WOTIME_ID_OFF + 1] & 0xE0) >> 5);
+	}
+
+	/* Data length */
+	frame->can_dlc = get_can_dlc(buf[HI3110_FIFO_WOTIME_DLC_OFF] & 0x0F);
+
+	if (buf[HI3110_FIFO_WOTIME_ID_OFF + 3] & HI3110_FIFO_WOTIME_ID_RTR)
+		frame->can_id |= CAN_RTR_FLAG;
+	else
+		memcpy(frame->data, buf + HI3110_FIFO_WOTIME_DAT_OFF,
+		       frame->can_dlc);
+
+	priv->net->stats.rx_packets++;
+	priv->net->stats.rx_bytes += frame->can_dlc;
+
+	can_led_event(priv->net, CAN_LED_EVENT_RX);
+
+	netif_rx_ni(skb);
+}
+
+static void hi3110_hw_sleep(struct spi_device *spi)
+{
+	hi3110_write(spi, HI3110_WRITE_CTRL0, HI3110_CTRL0_SLEEP_MODE);
+}
+
+static netdev_tx_t hi3110_hard_start_xmit(struct sk_buff *skb,
+					  struct net_device *net)
+{
+	struct hi3110_priv *priv = netdev_priv(net);
+	struct spi_device *spi = priv->spi;
+
+	if (priv->tx_skb || priv->tx_len) {
+		dev_err(&spi->dev, "hard_xmit called while tx busy\n");
+		return NETDEV_TX_BUSY;
+	}
+
+	if (can_dropped_invalid_skb(net, skb))
+		return NETDEV_TX_OK;
+
+	netif_stop_queue(net);
+	priv->tx_skb = skb;
+	queue_work(priv->wq, &priv->tx_work);
+
+	return NETDEV_TX_OK;
+}
+
+static int hi3110_do_set_mode(struct net_device *net, enum can_mode mode)
+{
+	struct hi3110_priv *priv = netdev_priv(net);
+
+	switch (mode) {
+	case CAN_MODE_START:
+		hi3110_clean(net);
+		/* We have to delay work since SPI I/O may sleep */
+		priv->can.state = CAN_STATE_ERROR_ACTIVE;
+		priv->restart_tx = 1;
+		if (priv->can.restart_ms == 0)
+			priv->after_suspend = HI3110_AFTER_SUSPEND_RESTART;
+		queue_work(priv->wq, &priv->restart_work);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int hi3110_get_berr_counter(const struct net_device *net,
+				   struct can_berr_counter *bec)
+{
+	struct hi3110_priv *priv = netdev_priv(net);
+	struct spi_device *spi = priv->spi;
+
+	bec->txerr = hi3110_read(spi, HI3110_READ_TEC);
+	bec->rxerr = hi3110_read(spi, HI3110_READ_REC);
+
+	return 0;
+}
+
+static int hi3110_set_normal_mode(struct spi_device *spi)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+	u8 reg = 0;
+
+	hi3110_write(spi, HI3110_WRITE_INTE, HI3110_INT_BUSERR |
+		     HI3110_INT_RXFIFO | HI3110_INT_TXCPLT);
+
+	/* Enable TX */
+	hi3110_write(spi, HI3110_WRITE_CTRL1, HI3110_CTRL1_TXEN);
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)
+		reg = HI3110_CTRL0_LOOPBACK_MODE;
+	else if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+		reg = HI3110_CTRL0_MONITOR_MODE;
+	else
+		reg = HI3110_CTRL0_NORMAL_MODE;
+
+	hi3110_write(spi, HI3110_WRITE_CTRL0, reg);
+
+	/* Wait for the device to enter the mode */
+	mdelay(HI3110_OST_DELAY_MS);
+	reg = hi3110_read(spi, HI3110_READ_CTRL0);
+	if ((reg & HI3110_CTRL0_MODE_MASK) != reg)
+		return -EBUSY;
+
+	priv->can.state = CAN_STATE_ERROR_ACTIVE;
+	return 0;
+}
+
+static int hi3110_do_set_bittiming(struct net_device *net)
+{
+	struct hi3110_priv *priv = netdev_priv(net);
+	struct can_bittiming *bt = &priv->can.bittiming;
+	struct spi_device *spi = priv->spi;
+
+	hi3110_write(spi, HI3110_WRITE_BTR0,
+		     ((bt->sjw - 1) << HI3110_BTR0_SJW_SHIFT) |
+		     ((bt->brp - 1) << HI3110_BTR0_BRP_SHIFT));
+
+	hi3110_write(spi, HI3110_WRITE_BTR1,
+		     (priv->can.ctrlmode &
+		      CAN_CTRLMODE_3_SAMPLES ?
+		      HI3110_BTR1_SAMP_3PERBIT : HI3110_BTR1_SAMP_1PERBIT) |
+		     ((bt->phase_seg1 + bt->prop_seg - 1)
+		      << HI3110_BTR1_TSEG1_SHIFT) |
+		     ((bt->phase_seg2 - 1) << HI3110_BTR1_TSEG2_SHIFT));
+
+	dev_dbg(&spi->dev, "BT: 0x%02x 0x%02x\n",
+		hi3110_read(spi, HI3110_READ_BTR0),
+		hi3110_read(spi, HI3110_READ_BTR1));
+
+	return 0;
+}
+
+static int hi3110_setup(struct net_device *net)
+{
+	hi3110_do_set_bittiming(net);
+	return 0;
+}
+
+static int hi3110_hw_reset(struct spi_device *spi)
+{
+	u8 reg;
+	int ret;
+
+	/* Wait for oscillator startup timer after power up */
+	mdelay(HI3110_OST_DELAY_MS);
+
+	ret = hi3110_cmd(spi, HI3110_MASTER_RESET);
+	if (ret)
+		return ret;
+
+	/* Wait for oscillator startup timer after reset */
+	mdelay(HI3110_OST_DELAY_MS);
+
+	reg = hi3110_read(spi, HI3110_READ_CTRL0);
+	if ((reg & HI3110_CTRL0_MODE_MASK) != HI3110_CTRL0_INIT_MODE)
+		return -ENODEV;
+
+	/* As per the datasheet it appears the error flags are
+	 * not cleared on reset. Explicitly clear them by performing a read
+	 */
+	hi3110_read(spi, HI3110_READ_ERR);
+
+	return 0;
+}
+
+static int hi3110_hw_probe(struct spi_device *spi)
+{
+	u8 statf;
+
+	hi3110_hw_reset(spi);
+
+	/* Confirm correct operation by checking against reset values
+	 * in datasheet
+	 */
+	statf = hi3110_read(spi, HI3110_READ_STATF);
+
+	dev_dbg(&spi->dev, "statf: %02X\n", statf);
+
+	if (statf != 0x82)
+		return -ENODEV;
+
+	return 0;
+}
+
+static int hi3110_power_enable(struct regulator *reg, int enable)
+{
+	if (IS_ERR_OR_NULL(reg))
+		return 0;
+
+	if (enable)
+		return regulator_enable(reg);
+	else
+		return regulator_disable(reg);
+}
+
+static int hi3110_stop(struct net_device *net)
+{
+	struct hi3110_priv *priv = netdev_priv(net);
+	struct spi_device *spi = priv->spi;
+
+	close_candev(net);
+
+	priv->force_quit = 1;
+	free_irq(spi->irq, priv);
+	destroy_workqueue(priv->wq);
+	priv->wq = NULL;
+
+	mutex_lock(&priv->hi3110_lock);
+
+	/* Disable transmit, interrupts and clear flags */
+	hi3110_write(spi, HI3110_WRITE_CTRL1, 0x0);
+	hi3110_write(spi, HI3110_WRITE_INTE, 0x0);
+	hi3110_read(spi, HI3110_READ_INTF);
+
+	hi3110_clean(net);
+
+	hi3110_hw_sleep(spi);
+
+	hi3110_power_enable(priv->transceiver, 0);
+
+	priv->can.state = CAN_STATE_STOPPED;
+
+	mutex_unlock(&priv->hi3110_lock);
+
+	can_led_event(net, CAN_LED_EVENT_STOP);
+
+	return 0;
+}
+
+static void hi3110_tx_work_handler(struct work_struct *ws)
+{
+	struct hi3110_priv *priv = container_of(ws, struct hi3110_priv,
+						tx_work);
+	struct spi_device *spi = priv->spi;
+	struct net_device *net = priv->net;
+	struct can_frame *frame;
+
+	mutex_lock(&priv->hi3110_lock);
+	if (priv->tx_skb) {
+		if (priv->can.state == CAN_STATE_BUS_OFF) {
+			hi3110_clean(net);
+		} else {
+			frame = (struct can_frame *)priv->tx_skb->data;
+			hi3110_hw_tx(spi, frame);
+			priv->tx_len = 1 + frame->can_dlc;
+			can_put_echo_skb(priv->tx_skb, net, 0);
+			priv->tx_skb = NULL;
+		}
+	}
+	mutex_unlock(&priv->hi3110_lock);
+}
+
+static void hi3110_restart_work_handler(struct work_struct *ws)
+{
+	struct hi3110_priv *priv = container_of(ws, struct hi3110_priv,
+						restart_work);
+	struct spi_device *spi = priv->spi;
+	struct net_device *net = priv->net;
+
+	mutex_lock(&priv->hi3110_lock);
+	if (priv->after_suspend) {
+		hi3110_hw_reset(spi);
+		hi3110_setup(net);
+		if (priv->after_suspend & HI3110_AFTER_SUSPEND_RESTART) {
+			hi3110_set_normal_mode(spi);
+		} else if (priv->after_suspend & HI3110_AFTER_SUSPEND_UP) {
+			netif_device_attach(net);
+			hi3110_clean(net);
+			hi3110_set_normal_mode(spi);
+			netif_wake_queue(net);
+		} else {
+			hi3110_hw_sleep(spi);
+		}
+		priv->after_suspend = 0;
+		priv->force_quit = 0;
+	}
+
+	if (priv->restart_tx) {
+		priv->restart_tx = 0;
+		hi3110_hw_reset(spi);
+		hi3110_setup(net);
+		hi3110_clean(net);
+		hi3110_set_normal_mode(spi);
+		netif_wake_queue(net);
+	}
+	mutex_unlock(&priv->hi3110_lock);
+}
+
+static irqreturn_t hi3110_can_ist(int irq, void *dev_id)
+{
+	struct hi3110_priv *priv = dev_id;
+	struct spi_device *spi = priv->spi;
+	struct net_device *net = priv->net;
+
+	mutex_lock(&priv->hi3110_lock);
+
+	while (!priv->force_quit) {
+		enum can_state new_state;
+		u8 intf, eflag, statf;
+
+		while (!(HI3110_STAT_RXFMTY &
+			 (statf = hi3110_read(spi, HI3110_READ_STATF)))) {
+			hi3110_hw_rx(spi);
+		}
+
+		intf = hi3110_read(spi, HI3110_READ_INTF);
+		eflag = hi3110_read(spi, HI3110_READ_ERR);
+		/* Update can state */
+		if (eflag & HI3110_ERR_BUSOFF)
+			new_state = CAN_STATE_BUS_OFF;
+		else if (eflag & HI3110_ERR_PASSIVE_MASK)
+			new_state = CAN_STATE_ERROR_PASSIVE;
+		else if (statf & HI3110_STAT_ERRW)
+			new_state = CAN_STATE_ERROR_WARNING;
+		else
+			new_state = CAN_STATE_ERROR_ACTIVE;
+
+		if (new_state != priv->can.state) {
+			struct can_frame *cf;
+			struct sk_buff *skb;
+			enum can_state rx_state, tx_state;
+			u8 rxerr, txerr;
+
+			skb = alloc_can_err_skb(net, &cf);
+			if (!skb)
+				break;
+
+			txerr = hi3110_read(spi, HI3110_READ_TEC);
+			rxerr = hi3110_read(spi, HI3110_READ_REC);
+			cf->data[6] = txerr;
+			cf->data[7] = rxerr;
+			tx_state = txerr >= rxerr ? new_state : 0;
+			rx_state = txerr <= rxerr ? new_state : 0;
+			can_change_state(net, cf, tx_state, rx_state);
+			netif_rx_ni(skb);
+
+			if (new_state == CAN_STATE_BUS_OFF) {
+				can_bus_off(net);
+				if (priv->can.restart_ms == 0) {
+					priv->force_quit = 1;
+					hi3110_hw_sleep(spi);
+					break;
+				}
+			}
+		}
+
+		/* Update bus errors */
+		if ((intf & HI3110_INT_BUSERR) &&
+		    (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)) {
+			struct can_frame *cf;
+			struct sk_buff *skb;
+
+			/* Check for protocol errors */
+			if (eflag & HI3110_ERR_PROTOCOL_MASK) {
+				skb = alloc_can_err_skb(net, &cf);
+				if (!skb)
+					break;
+
+				cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR;
+				priv->can.can_stats.bus_error++;
+				priv->net->stats.rx_errors++;
+				if (eflag & HI3110_ERR_BITERR)
+					cf->data[2] |= CAN_ERR_PROT_BIT;
+				else if (eflag & HI3110_ERR_FRMERR)
+					cf->data[2] |= CAN_ERR_PROT_FORM;
+				else if (eflag & HI3110_ERR_STUFERR)
+					cf->data[2] |= CAN_ERR_PROT_STUFF;
+				else if (eflag & HI3110_ERR_CRCERR)
+					cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ;
+				else if (eflag & HI3110_ERR_ACKERR)
+					cf->data[3] |= CAN_ERR_PROT_LOC_ACK;
+
+				cf->data[6] = hi3110_read(spi, HI3110_READ_TEC);
+				cf->data[7] = hi3110_read(spi, HI3110_READ_REC);
+				netdev_dbg(priv->net, "Bus Error\n");
+				netif_rx_ni(skb);
+			}
+		}
+
+		if (intf == 0)
+			break;
+
+		if (intf & HI3110_INT_TXCPLT) {
+			net->stats.tx_packets++;
+			net->stats.tx_bytes += priv->tx_len - 1;
+			can_led_event(net, CAN_LED_EVENT_TX);
+			if (priv->tx_len) {
+				can_get_echo_skb(net, 0);
+				priv->tx_len = 0;
+			}
+			netif_wake_queue(net);
+		}
+	}
+	mutex_unlock(&priv->hi3110_lock);
+	return IRQ_HANDLED;
+}
+
+static int hi3110_open(struct net_device *net)
+{
+	struct hi3110_priv *priv = netdev_priv(net);
+	struct spi_device *spi = priv->spi;
+	unsigned long flags = IRQF_ONESHOT | IRQF_TRIGGER_RISING;
+	int ret;
+
+	ret = open_candev(net);
+	if (ret)
+		return ret;
+
+	mutex_lock(&priv->hi3110_lock);
+	hi3110_power_enable(priv->transceiver, 1);
+
+	priv->force_quit = 0;
+	priv->tx_skb = NULL;
+	priv->tx_len = 0;
+
+	ret = request_threaded_irq(spi->irq, NULL, hi3110_can_ist,
+				   flags, DEVICE_NAME, priv);
+	if (ret) {
+		dev_err(&spi->dev, "failed to acquire irq %d\n", spi->irq);
+		goto out_close;
+	}
+
+	priv->wq = alloc_workqueue("hi3110_wq", WQ_FREEZABLE | WQ_MEM_RECLAIM,
+				   0);
+	if (!priv->wq) {
+		ret = -ENOMEM;
+		goto out_free_irq;
+	}
+	INIT_WORK(&priv->tx_work, hi3110_tx_work_handler);
+	INIT_WORK(&priv->restart_work, hi3110_restart_work_handler);
+
+	ret = hi3110_hw_reset(spi);
+	if (ret)
+		goto out_free_wq;
+
+	ret = hi3110_setup(net);
+	if (ret)
+		goto out_free_wq;
+
+	ret = hi3110_set_normal_mode(spi);
+	if (ret)
+		goto out_free_wq;
+
+	can_led_event(net, CAN_LED_EVENT_OPEN);
+	netif_wake_queue(net);
+	mutex_unlock(&priv->hi3110_lock);
+
+	return 0;
+
+ out_free_wq:
+	destroy_workqueue(priv->wq);
+ out_free_irq:
+	free_irq(spi->irq, priv);
+	hi3110_hw_sleep(spi);
+ out_close:
+	hi3110_power_enable(priv->transceiver, 0);
+	close_candev(net);
+	mutex_unlock(&priv->hi3110_lock);
+	return ret;
+}
+
+static const struct net_device_ops hi3110_netdev_ops = {
+	.ndo_open = hi3110_open,
+	.ndo_stop = hi3110_stop,
+	.ndo_start_xmit = hi3110_hard_start_xmit,
+};
+
+static const struct of_device_id hi3110_of_match[] = {
+	{
+		.compatible	= "holt,hi3110",
+		.data		= (void *)CAN_HI3110_HI3110,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, hi3110_of_match);
+
+static const struct spi_device_id hi3110_id_table[] = {
+	{
+		.name		= "hi3110",
+		.driver_data	= (kernel_ulong_t)CAN_HI3110_HI3110,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, hi3110_id_table);
+
+static int hi3110_can_probe(struct spi_device *spi)
+{
+	const struct of_device_id *of_id = of_match_device(hi3110_of_match,
+							   &spi->dev);
+	struct net_device *net;
+	struct hi3110_priv *priv;
+	struct clk *clk;
+	int freq, ret;
+
+	clk = devm_clk_get(&spi->dev, NULL);
+	if (IS_ERR(clk)) {
+		dev_err(&spi->dev, "no CAN clock source defined\n");
+		return PTR_ERR(clk);
+	}
+	freq = clk_get_rate(clk);
+
+	/* Sanity check */
+	if (freq > 40000000)
+		return -ERANGE;
+
+	/* Allocate can/net device */
+	net = alloc_candev(sizeof(struct hi3110_priv), HI3110_TX_ECHO_SKB_MAX);
+	if (!net)
+		return -ENOMEM;
+
+	if (!IS_ERR(clk)) {
+		ret = clk_prepare_enable(clk);
+		if (ret)
+			goto out_free;
+	}
+
+	net->netdev_ops = &hi3110_netdev_ops;
+	net->flags |= IFF_ECHO;
+
+	priv = netdev_priv(net);
+	priv->can.bittiming_const = &hi3110_bittiming_const;
+	priv->can.do_set_mode = hi3110_do_set_mode;
+	priv->can.do_get_berr_counter = hi3110_get_berr_counter;
+	priv->can.clock.freq = freq / 2;
+	priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES |
+		CAN_CTRLMODE_LOOPBACK |
+		CAN_CTRLMODE_LISTENONLY |
+		CAN_CTRLMODE_BERR_REPORTING;
+
+	if (of_id)
+		priv->model = (enum hi3110_model)of_id->data;
+	else
+		priv->model = spi_get_device_id(spi)->driver_data;
+	priv->net = net;
+	priv->clk = clk;
+
+	spi_set_drvdata(spi, priv);
+
+	/* Configure the SPI bus */
+	spi->bits_per_word = 8;
+	ret = spi_setup(spi);
+	if (ret)
+		goto out_clk;
+
+	priv->power = devm_regulator_get_optional(&spi->dev, "vdd");
+	priv->transceiver = devm_regulator_get_optional(&spi->dev, "xceiver");
+	if ((PTR_ERR(priv->power) == -EPROBE_DEFER) ||
+	    (PTR_ERR(priv->transceiver) == -EPROBE_DEFER)) {
+		ret = -EPROBE_DEFER;
+		goto out_clk;
+	}
+
+	ret = hi3110_power_enable(priv->power, 1);
+	if (ret)
+		goto out_clk;
+
+	priv->spi = spi;
+	mutex_init(&priv->hi3110_lock);
+
+	/* If requested, allocate DMA buffers */
+	if (hi3110_enable_dma) {
+		spi->dev.coherent_dma_mask = ~0;
+
+		/* Minimum coherent DMA allocation is PAGE_SIZE, so allocate
+		 * that much and share it between Tx and Rx DMA buffers.
+		 */
+		priv->spi_tx_buf = dmam_alloc_coherent(&spi->dev,
+						       PAGE_SIZE,
+						       &priv->spi_tx_dma,
+						       GFP_DMA);
+
+		if (priv->spi_tx_buf) {
+			priv->spi_rx_buf = (priv->spi_tx_buf + (PAGE_SIZE / 2));
+			priv->spi_rx_dma = (dma_addr_t)(priv->spi_tx_dma +
+							(PAGE_SIZE / 2));
+		} else {
+			/* Fall back to non-DMA */
+			hi3110_enable_dma = 0;
+		}
+	}
+
+	/* Allocate non-DMA buffers */
+	if (!hi3110_enable_dma) {
+		priv->spi_tx_buf = devm_kzalloc(&spi->dev, HI3110_RX_BUF_LEN,
+						GFP_KERNEL);
+		if (!priv->spi_tx_buf) {
+			ret = -ENOMEM;
+			goto error_probe;
+		}
+		priv->spi_rx_buf = devm_kzalloc(&spi->dev, HI3110_RX_BUF_LEN,
+						GFP_KERNEL);
+
+		if (!priv->spi_rx_buf) {
+			ret = -ENOMEM;
+			goto error_probe;
+		}
+	}
+
+	SET_NETDEV_DEV(net, &spi->dev);
+
+	ret = hi3110_hw_probe(spi);
+	if (ret) {
+		if (ret == -ENODEV)
+			dev_err(&spi->dev, "Cannot initialize %x. Wrong wiring?\n",
+				priv->model);
+		goto error_probe;
+	}
+	hi3110_hw_sleep(spi);
+
+	ret = register_candev(net);
+	if (ret)
+		goto error_probe;
+
+	devm_can_led_init(net);
+	netdev_info(net, "%x successfully initialized.\n", priv->model);
+
+	return 0;
+
+ error_probe:
+	hi3110_power_enable(priv->power, 0);
+
+ out_clk:
+	if (!IS_ERR(clk))
+		clk_disable_unprepare(clk);
+
+ out_free:
+	free_candev(net);
+
+	dev_err(&spi->dev, "Probe failed, err=%d\n", -ret);
+	return ret;
+}
+
+static int hi3110_can_remove(struct spi_device *spi)
+{
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+	struct net_device *net = priv->net;
+
+	unregister_candev(net);
+
+	hi3110_power_enable(priv->power, 0);
+
+	if (!IS_ERR(priv->clk))
+		clk_disable_unprepare(priv->clk);
+
+	free_candev(net);
+
+	return 0;
+}
+
+static int __maybe_unused hi3110_can_suspend(struct device *dev)
+{
+	struct spi_device *spi = to_spi_device(dev);
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+	struct net_device *net = priv->net;
+
+	priv->force_quit = 1;
+	disable_irq(spi->irq);
+
+	/* Note: at this point neither IST nor workqueues are running.
+	 * open/stop cannot be called anyway so locking is not needed
+	 */
+	if (netif_running(net)) {
+		netif_device_detach(net);
+
+		hi3110_hw_sleep(spi);
+		hi3110_power_enable(priv->transceiver, 0);
+		priv->after_suspend = HI3110_AFTER_SUSPEND_UP;
+	} else {
+		priv->after_suspend = HI3110_AFTER_SUSPEND_DOWN;
+	}
+
+	if (!IS_ERR_OR_NULL(priv->power)) {
+		regulator_disable(priv->power);
+		priv->after_suspend |= HI3110_AFTER_SUSPEND_POWER;
+	}
+
+	return 0;
+}
+
+static int __maybe_unused hi3110_can_resume(struct device *dev)
+{
+	struct spi_device *spi = to_spi_device(dev);
+	struct hi3110_priv *priv = spi_get_drvdata(spi);
+
+	if (priv->after_suspend & HI3110_AFTER_SUSPEND_POWER)
+		hi3110_power_enable(priv->power, 1);
+
+	if (priv->after_suspend & HI3110_AFTER_SUSPEND_UP) {
+		hi3110_power_enable(priv->transceiver, 1);
+		queue_work(priv->wq, &priv->restart_work);
+	} else {
+		priv->after_suspend = 0;
+	}
+
+	priv->force_quit = 0;
+	enable_irq(spi->irq);
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(hi3110_can_pm_ops, hi3110_can_suspend, hi3110_can_resume);
+
+static struct spi_driver hi3110_can_driver = {
+	.driver = {
+		.name = DEVICE_NAME,
+		.of_match_table = hi3110_of_match,
+		.pm = &hi3110_can_pm_ops,
+	},
+	.id_table = hi3110_id_table,
+	.probe = hi3110_can_probe,
+	.remove = hi3110_can_remove,
+};
+
+module_spi_driver(hi3110_can_driver);
+
+MODULE_AUTHOR("Akshay Bhat <akshay.bhat@timesys.com>");
+MODULE_AUTHOR("Casey Fitzpatrick <casey.fitzpatrick@timesys.com>");
+MODULE_DESCRIPTION("Holt HI-3110 CAN driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 6749b1829469..b8aac538275c 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -17,25 +17,6 @@
  *
  */
 
-/*
- * Your platform definitions should specify module ram offsets and interrupt
- * number to use as follows:
- *
- * static struct ti_hecc_platform_data am3517_evm_hecc_pdata = {
- *         .scc_hecc_offset        = 0,
- *         .scc_ram_offset         = 0x3000,
- *         .hecc_ram_offset        = 0x3000,
- *         .mbx_offset             = 0x2000,
- *         .int_line               = 0,
- *         .revision               = 1,
- *         .transceiver_switch     = hecc_phy_control,
- * };
- *
- * Please see include/linux/can/platform/ti_hecc.h for description of
- * above fields.
- *
- */
-
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -46,11 +27,13 @@
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/regulator/consumer.h>
 
 #include <linux/can/dev.h>
 #include <linux/can/error.h>
 #include <linux/can/led.h>
-#include <linux/can/platform/ti_hecc.h>
 
 #define DRV_NAME "ti_hecc"
 #define HECC_MODULE_VERSION     "0.7"
@@ -214,15 +197,14 @@ struct ti_hecc_priv {
 	struct net_device *ndev;
 	struct clk *clk;
 	void __iomem *base;
-	u32 scc_ram_offset;
-	u32 hecc_ram_offset;
-	u32 mbx_offset;
-	u32 int_line;
+	void __iomem *hecc_ram;
+	void __iomem *mbx;
+	bool use_hecc1int;
 	spinlock_t mbx_lock; /* CANME register needs protection */
 	u32 tx_head;
 	u32 tx_tail;
 	u32 rx_next;
-	void (*transceiver_switch)(int);
+	struct regulator *reg_xceiver;
 };
 
 static inline int get_tx_head_mb(struct ti_hecc_priv *priv)
@@ -242,20 +224,18 @@ static inline int get_tx_head_prio(struct ti_hecc_priv *priv)
 
 static inline void hecc_write_lam(struct ti_hecc_priv *priv, u32 mbxno, u32 val)
 {
-	__raw_writel(val, priv->base + priv->hecc_ram_offset + mbxno * 4);
+	__raw_writel(val, priv->hecc_ram + mbxno * 4);
 }
 
 static inline void hecc_write_mbx(struct ti_hecc_priv *priv, u32 mbxno,
 	u32 reg, u32 val)
 {
-	__raw_writel(val, priv->base + priv->mbx_offset + mbxno * 0x10 +
-			reg);
+	__raw_writel(val, priv->mbx + mbxno * 0x10 + reg);
 }
 
 static inline u32 hecc_read_mbx(struct ti_hecc_priv *priv, u32 mbxno, u32 reg)
 {
-	return __raw_readl(priv->base + priv->mbx_offset + mbxno * 0x10 +
-			reg);
+	return __raw_readl(priv->mbx + mbxno * 0x10 + reg);
 }
 
 static inline void hecc_write(struct ti_hecc_priv *priv, u32 reg, u32 val)
@@ -311,11 +291,16 @@ static int ti_hecc_set_btc(struct ti_hecc_priv *priv)
 	return 0;
 }
 
-static void ti_hecc_transceiver_switch(const struct ti_hecc_priv *priv,
-					int on)
+static int ti_hecc_transceiver_switch(const struct ti_hecc_priv *priv,
+				      int on)
 {
-	if (priv->transceiver_switch)
-		priv->transceiver_switch(on);
+	if (!priv->reg_xceiver)
+		return 0;
+
+	if (on)
+		return regulator_enable(priv->reg_xceiver);
+	else
+		return regulator_disable(priv->reg_xceiver);
 }
 
 static void ti_hecc_reset(struct net_device *ndev)
@@ -409,7 +394,7 @@ static void ti_hecc_start(struct net_device *ndev)
 
 	/* Prevent message over-write & Enable interrupts */
 	hecc_write(priv, HECC_CANOPC, HECC_SET_REG);
-	if (priv->int_line) {
+	if (priv->use_hecc1int) {
 		hecc_write(priv, HECC_CANMIL, HECC_SET_REG);
 		hecc_write(priv, HECC_CANGIM, HECC_CANGIM_DEF_MASK |
 			HECC_CANGIM_I1EN | HECC_CANGIM_SIL);
@@ -760,7 +745,7 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
 	unsigned long ack, flags;
 
 	int_status = hecc_read(priv,
-		(priv->int_line) ? HECC_CANGIF1 : HECC_CANGIF0);
+		(priv->use_hecc1int) ? HECC_CANGIF1 : HECC_CANGIF0);
 
 	if (!int_status)
 		return IRQ_NONE;
@@ -806,7 +791,7 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
 	}
 
 	/* clear all interrupt conditions - read back to avoid spurious ints */
-	if (priv->int_line) {
+	if (priv->use_hecc1int) {
 		hecc_write(priv, HECC_CANGIF1, HECC_SET_REG);
 		int_status = hecc_read(priv, HECC_CANGIF1);
 	} else {
@@ -872,58 +857,87 @@ static const struct net_device_ops ti_hecc_netdev_ops = {
 	.ndo_change_mtu		= can_change_mtu,
 };
 
+static const struct of_device_id ti_hecc_dt_ids[] = {
+	{
+		.compatible = "ti,am3517-hecc",
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ti_hecc_dt_ids);
+
 static int ti_hecc_probe(struct platform_device *pdev)
 {
 	struct net_device *ndev = (struct net_device *)0;
 	struct ti_hecc_priv *priv;
-	struct ti_hecc_platform_data *pdata;
-	struct resource *mem, *irq;
-	void __iomem *addr;
+	struct device_node *np = pdev->dev.of_node;
+	struct resource *res, *irq;
+	struct regulator *reg_xceiver;
 	int err = -ENODEV;
 
-	pdata = dev_get_platdata(&pdev->dev);
-	if (!pdata) {
-		dev_err(&pdev->dev, "No platform data\n");
-		goto probe_exit;
+	if (!IS_ENABLED(CONFIG_OF) || !np)
+		return -EINVAL;
+
+	reg_xceiver = devm_regulator_get(&pdev->dev, "xceiver");
+	if (PTR_ERR(reg_xceiver) == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+	else if (IS_ERR(reg_xceiver))
+		reg_xceiver = NULL;
+
+	ndev = alloc_candev(sizeof(struct ti_hecc_priv), HECC_MAX_TX_MBOX);
+	if (!ndev) {
+		dev_err(&pdev->dev, "alloc_candev failed\n");
+		return -ENOMEM;
 	}
+	priv = netdev_priv(ndev);
 
-	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!mem) {
-		dev_err(&pdev->dev, "No mem resources\n");
-		goto probe_exit;
+	/* handle hecc memory */
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "hecc");
+	if (!res) {
+		dev_err(&pdev->dev, "can't get IORESOURCE_MEM hecc\n");
+		return -EINVAL;
 	}
-	irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (!irq) {
-		dev_err(&pdev->dev, "No irq resource\n");
-		goto probe_exit;
+
+	priv->base = devm_ioremap_resource(&pdev->dev, res);
+	if (!priv->base) {
+		dev_err(&pdev->dev, "hecc ioremap failed\n");
+		return -ENOMEM;
 	}
-	if (!request_mem_region(mem->start, resource_size(mem), pdev->name)) {
-		dev_err(&pdev->dev, "HECC region already claimed\n");
-		err = -EBUSY;
-		goto probe_exit;
+
+	/* handle hecc-ram memory */
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "hecc-ram");
+	if (!res) {
+		dev_err(&pdev->dev, "can't get IORESOURCE_MEM hecc-ram\n");
+		return -EINVAL;
 	}
-	addr = ioremap(mem->start, resource_size(mem));
-	if (!addr) {
-		dev_err(&pdev->dev, "ioremap failed\n");
-		err = -ENOMEM;
-		goto probe_exit_free_region;
+
+	priv->hecc_ram = devm_ioremap_resource(&pdev->dev, res);
+	if (!priv->hecc_ram) {
+		dev_err(&pdev->dev, "hecc-ram ioremap failed\n");
+		return -ENOMEM;
 	}
 
-	ndev = alloc_candev(sizeof(struct ti_hecc_priv), HECC_MAX_TX_MBOX);
-	if (!ndev) {
-		dev_err(&pdev->dev, "alloc_candev failed\n");
-		err = -ENOMEM;
-		goto probe_exit_iounmap;
+	/* handle mbx memory */
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mbx");
+	if (!res) {
+		dev_err(&pdev->dev, "can't get IORESOURCE_MEM mbx\n");
+		return -EINVAL;
+	}
+
+	priv->mbx = devm_ioremap_resource(&pdev->dev, res);
+	if (!priv->mbx) {
+		dev_err(&pdev->dev, "mbx ioremap failed\n");
+		return -ENOMEM;
+	}
+
+	irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!irq) {
+		dev_err(&pdev->dev, "No irq resource\n");
+		goto probe_exit;
 	}
 
-	priv = netdev_priv(ndev);
 	priv->ndev = ndev;
-	priv->base = addr;
-	priv->scc_ram_offset = pdata->scc_ram_offset;
-	priv->hecc_ram_offset = pdata->hecc_ram_offset;
-	priv->mbx_offset = pdata->mbx_offset;
-	priv->int_line = pdata->int_line;
-	priv->transceiver_switch = pdata->transceiver_switch;
+	priv->reg_xceiver = reg_xceiver;
+	priv->use_hecc1int = of_property_read_bool(np, "ti,use-hecc1int");
 
 	priv->can.bittiming_const = &ti_hecc_bittiming_const;
 	priv->can.do_set_mode = ti_hecc_do_set_mode;
@@ -971,32 +985,23 @@ probe_exit_clk:
 	clk_put(priv->clk);
 probe_exit_candev:
 	free_candev(ndev);
-probe_exit_iounmap:
-	iounmap(addr);
-probe_exit_free_region:
-	release_mem_region(mem->start, resource_size(mem));
 probe_exit:
 	return err;
 }
 
 static int ti_hecc_remove(struct platform_device *pdev)
 {
-	struct resource *res;
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct ti_hecc_priv *priv = netdev_priv(ndev);
 
 	unregister_candev(ndev);
 	clk_disable_unprepare(priv->clk);
 	clk_put(priv->clk);
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	iounmap(priv->base);
-	release_mem_region(res->start, resource_size(res));
 	free_candev(ndev);
 
 	return 0;
 }
 
-
 #ifdef CONFIG_PM
 static int ti_hecc_suspend(struct platform_device *pdev, pm_message_t state)
 {
@@ -1045,6 +1050,7 @@ static int ti_hecc_resume(struct platform_device *pdev)
 static struct platform_driver ti_hecc_driver = {
 	.driver = {
 		.name    = DRV_NAME,
+		.of_match_table = ti_hecc_dt_ids,
 	},
 	.probe = ti_hecc_probe,
 	.remove = ti_hecc_remove,
diff --git a/drivers/net/cris/eth_v10.c b/drivers/net/cris/eth_v10.c
index 91c876a0a647..da020418a652 100644
--- a/drivers/net/cris/eth_v10.c
+++ b/drivers/net/cris/eth_v10.c
@@ -1412,31 +1412,39 @@ e100_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	return rc;
 }
 
-static int e100_get_settings(struct net_device *dev,
-			     struct ethtool_cmd *cmd)
+static int e100_get_link_ksettings(struct net_device *dev,
+				   struct ethtool_link_ksettings *cmd)
 {
 	struct net_local *np = netdev_priv(dev);
+	u32 supported;
 	int err;
 
 	spin_lock_irq(&np->lock);
-	err = mii_ethtool_gset(&np->mii_if, cmd);
+	err = mii_ethtool_get_link_ksettings(&np->mii_if, cmd);
 	spin_unlock_irq(&np->lock);
 
 	/* The PHY may support 1000baseT, but the Etrax100 does not.  */
-	cmd->supported &= ~(SUPPORTED_1000baseT_Half
-			    | SUPPORTED_1000baseT_Full);
+	ethtool_convert_link_mode_to_legacy_u32(&supported,
+						cmd->link_modes.supported);
+
+	supported &= ~(SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full);
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+
 	return err;
 }
 
-static int e100_set_settings(struct net_device *dev,
-			     struct ethtool_cmd *ecmd)
+static int e100_set_link_ksettings(struct net_device *dev,
+				   const struct ethtool_link_ksettings *ecmd)
 {
-	if (ecmd->autoneg == AUTONEG_ENABLE) {
+	if (ecmd->base.autoneg == AUTONEG_ENABLE) {
 		e100_set_duplex(dev, autoneg);
 		e100_set_speed(dev, 0);
 	} else {
-		e100_set_duplex(dev, ecmd->duplex == DUPLEX_HALF ? half : full);
-		e100_set_speed(dev, ecmd->speed == SPEED_10 ? 10: 100);
+		e100_set_duplex(dev, ecmd->base.duplex == DUPLEX_HALF ?
+				half : full);
+		e100_set_speed(dev, ecmd->base.speed == SPEED_10 ? 10 : 100);
 	}
 
 	return 0;
@@ -1459,11 +1467,11 @@ static int e100_nway_reset(struct net_device *dev)
 }
 
 static const struct ethtool_ops e100_ethtool_ops = {
-	.get_settings	= e100_get_settings,
-	.set_settings	= e100_set_settings,
 	.get_drvinfo	= e100_get_drvinfo,
 	.nway_reset	= e100_nway_reset,
 	.get_link	= ethtool_op_get_link,
+	.get_link_ksettings	= e100_get_link_ksettings,
+	.set_link_ksettings	= e100_set_link_ksettings,
 };
 
 static int
diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 065984670ff1..ba2e655eec19 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -11,7 +11,7 @@ config NET_DSA_MV88E6060
 
 config NET_DSA_BCM_SF2
 	tristate "Broadcom Starfighter 2 Ethernet switch support"
-	depends on HAS_IOMEM && NET_DSA
+	depends on HAS_IOMEM && NET_DSA && OF_MDIO
 	select NET_DSA_TAG_BRCM
 	select FIXED_PHY
 	select BCM7XXX_PHY
@@ -34,4 +34,12 @@ config NET_DSA_QCA8K
 	  This enables support for the Qualcomm Atheros QCA8K Ethernet
 	  switch chips.
 
+config NET_DSA_LOOP
+	tristate "DSA mock-up Ethernet switch chip support"
+	depends on NET_DSA
+	select FIXED_PHY
+	---help---
+	  This enables support for a fake mock-up switch chip which
+	  exercises the DSA APIs.
+
 endmenu
diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile
index a3c941632217..5c8830991041 100644
--- a/drivers/net/dsa/Makefile
+++ b/drivers/net/dsa/Makefile
@@ -2,6 +2,6 @@ obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o
 obj-$(CONFIG_NET_DSA_BCM_SF2)	+= bcm-sf2.o
 bcm-sf2-objs			:= bcm_sf2.o bcm_sf2_cfp.o
 obj-$(CONFIG_NET_DSA_QCA8K)	+= qca8k.o
-
 obj-y				+= b53/
 obj-y				+= mv88e6xxx/
+obj-$(CONFIG_NET_DSA_LOOP)	+= dsa_loop.o dsa_loop_bdinfo.o
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 346dd9a1232d..2fb32d67065f 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -10,10 +10,11 @@
  */
 
 #include <linux/list.h>
-#include <net/dsa.h>
 #include <linux/ethtool.h>
 #include <linux/if_ether.h>
 #include <linux/in.h>
+#include <linux/netdevice.h>
+#include <net/dsa.h>
 #include <linux/bitmap.h>
 
 #include "bcm_sf2.h"
diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
new file mode 100644
index 000000000000..bc5acc15edbf
--- /dev/null
+++ b/drivers/net/dsa/dsa_loop.c
@@ -0,0 +1,328 @@
+/*
+ * Distributed Switch Architecture loopback driver
+ *
+ * Copyright (C) 2016, Florian Fainelli <f.fainelli@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/platform_device.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+#include <linux/phy_fixed.h>
+#include <linux/export.h>
+#include <linux/workqueue.h>
+#include <linux/module.h>
+#include <linux/if_bridge.h>
+#include <net/switchdev.h>
+#include <net/dsa.h>
+
+#include "dsa_loop.h"
+
+struct dsa_loop_vlan {
+	u16 members;
+	u16 untagged;
+};
+
+#define DSA_LOOP_VLANS	5
+
+struct dsa_loop_priv {
+	struct mii_bus	*bus;
+	unsigned int	port_base;
+	struct dsa_loop_vlan vlans[DSA_LOOP_VLANS];
+	struct net_device *netdev;
+	u16 pvid;
+};
+
+static struct phy_device *phydevs[PHY_MAX_ADDR];
+
+static enum dsa_tag_protocol dsa_loop_get_protocol(struct dsa_switch *ds)
+{
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	return DSA_TAG_PROTO_NONE;
+}
+
+static int dsa_loop_setup(struct dsa_switch *ds)
+{
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	return 0;
+}
+
+static int dsa_loop_set_addr(struct dsa_switch *ds, u8 *addr)
+{
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	return 0;
+}
+
+static int dsa_loop_phy_read(struct dsa_switch *ds, int port, int regnum)
+{
+	struct dsa_loop_priv *ps = ds->priv;
+	struct mii_bus *bus = ps->bus;
+
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	return mdiobus_read_nested(bus, ps->port_base + port, regnum);
+}
+
+static int dsa_loop_phy_write(struct dsa_switch *ds, int port,
+			      int regnum, u16 value)
+{
+	struct dsa_loop_priv *ps = ds->priv;
+	struct mii_bus *bus = ps->bus;
+
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	return mdiobus_write_nested(bus, ps->port_base + port, regnum, value);
+}
+
+static int dsa_loop_port_bridge_join(struct dsa_switch *ds, int port,
+				     struct net_device *bridge)
+{
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	return 0;
+}
+
+static void dsa_loop_port_bridge_leave(struct dsa_switch *ds, int port,
+				       struct net_device *bridge)
+{
+	dev_dbg(ds->dev, "%s\n", __func__);
+}
+
+static void dsa_loop_port_stp_state_set(struct dsa_switch *ds, int port,
+					u8 state)
+{
+	dev_dbg(ds->dev, "%s\n", __func__);
+}
+
+static int dsa_loop_port_vlan_filtering(struct dsa_switch *ds, int port,
+					bool vlan_filtering)
+{
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	return 0;
+}
+
+static int dsa_loop_port_vlan_prepare(struct dsa_switch *ds, int port,
+				      const struct switchdev_obj_port_vlan *vlan,
+				      struct switchdev_trans *trans)
+{
+	struct dsa_loop_priv *ps = ds->priv;
+	struct mii_bus *bus = ps->bus;
+
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	/* Just do a sleeping operation to make lockdep checks effective */
+	mdiobus_read(bus, ps->port_base + port, MII_BMSR);
+
+	if (vlan->vid_end > DSA_LOOP_VLANS)
+		return -ERANGE;
+
+	return 0;
+}
+
+static void dsa_loop_port_vlan_add(struct dsa_switch *ds, int port,
+				   const struct switchdev_obj_port_vlan *vlan,
+				   struct switchdev_trans *trans)
+{
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
+	struct dsa_loop_priv *ps = ds->priv;
+	struct mii_bus *bus = ps->bus;
+	struct dsa_loop_vlan *vl;
+	u16 vid;
+
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	/* Just do a sleeping operation to make lockdep checks effective */
+	mdiobus_read(bus, ps->port_base + port, MII_BMSR);
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		vl = &ps->vlans[vid];
+
+		vl->members |= BIT(port);
+		if (untagged)
+			vl->untagged |= BIT(port);
+		else
+			vl->untagged &= ~BIT(port);
+	}
+
+	if (pvid)
+		ps->pvid = vid;
+}
+
+static int dsa_loop_port_vlan_del(struct dsa_switch *ds, int port,
+				  const struct switchdev_obj_port_vlan *vlan)
+{
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	struct dsa_loop_priv *ps = ds->priv;
+	struct mii_bus *bus = ps->bus;
+	struct dsa_loop_vlan *vl;
+	u16 vid, pvid;
+
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	/* Just do a sleeping operation to make lockdep checks effective */
+	mdiobus_read(bus, ps->port_base + port, MII_BMSR);
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		vl = &ps->vlans[vid];
+
+		vl->members &= ~BIT(port);
+		if (untagged)
+			vl->untagged &= ~BIT(port);
+
+		if (pvid == vid)
+			pvid = 1;
+	}
+	ps->pvid = pvid;
+
+	return 0;
+}
+
+static int dsa_loop_port_vlan_dump(struct dsa_switch *ds, int port,
+				   struct switchdev_obj_port_vlan *vlan,
+				   int (*cb)(struct switchdev_obj *obj))
+{
+	struct dsa_loop_priv *ps = ds->priv;
+	struct mii_bus *bus = ps->bus;
+	struct dsa_loop_vlan *vl;
+	u16 vid, vid_start = 0;
+	int err;
+
+	dev_dbg(ds->dev, "%s\n", __func__);
+
+	/* Just do a sleeping operation to make lockdep checks effective */
+	mdiobus_read(bus, ps->port_base + port, MII_BMSR);
+
+	for (vid = vid_start; vid < DSA_LOOP_VLANS; vid++) {
+		vl = &ps->vlans[vid];
+
+		if (!(vl->members & BIT(port)))
+			continue;
+
+		vlan->vid_begin = vlan->vid_end = vid;
+		vlan->flags = 0;
+
+		if (vl->untagged & BIT(port))
+			vlan->flags |= BRIDGE_VLAN_INFO_UNTAGGED;
+		if (ps->pvid == vid)
+			vlan->flags |= BRIDGE_VLAN_INFO_PVID;
+
+		err = cb(&vlan->obj);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+static struct dsa_switch_ops dsa_loop_driver = {
+	.get_tag_protocol	= dsa_loop_get_protocol,
+	.setup			= dsa_loop_setup,
+	.set_addr		= dsa_loop_set_addr,
+	.phy_read		= dsa_loop_phy_read,
+	.phy_write		= dsa_loop_phy_write,
+	.port_bridge_join	= dsa_loop_port_bridge_join,
+	.port_bridge_leave	= dsa_loop_port_bridge_leave,
+	.port_stp_state_set	= dsa_loop_port_stp_state_set,
+	.port_vlan_filtering	= dsa_loop_port_vlan_filtering,
+	.port_vlan_prepare	= dsa_loop_port_vlan_prepare,
+	.port_vlan_add		= dsa_loop_port_vlan_add,
+	.port_vlan_del		= dsa_loop_port_vlan_del,
+	.port_vlan_dump		= dsa_loop_port_vlan_dump,
+};
+
+static int dsa_loop_drv_probe(struct mdio_device *mdiodev)
+{
+	struct dsa_loop_pdata *pdata = mdiodev->dev.platform_data;
+	struct dsa_loop_priv *ps;
+	struct dsa_switch *ds;
+
+	if (!pdata)
+		return -ENODEV;
+
+	dev_info(&mdiodev->dev, "%s: 0x%0x\n",
+		 pdata->name, pdata->enabled_ports);
+
+	ds = dsa_switch_alloc(&mdiodev->dev, DSA_MAX_PORTS);
+	if (!ds)
+		return -ENOMEM;
+
+	ps = devm_kzalloc(&mdiodev->dev, sizeof(*ps), GFP_KERNEL);
+	ps->netdev = dev_get_by_name(&init_net, pdata->netdev);
+	if (!ps->netdev)
+		return -EPROBE_DEFER;
+
+	pdata->cd.netdev[DSA_LOOP_CPU_PORT] = &ps->netdev->dev;
+
+	ds->dev = &mdiodev->dev;
+	ds->ops = &dsa_loop_driver;
+	ds->priv = ps;
+	ps->bus = mdiodev->bus;
+
+	dev_set_drvdata(&mdiodev->dev, ds);
+
+	return dsa_register_switch(ds, ds->dev);
+}
+
+static void dsa_loop_drv_remove(struct mdio_device *mdiodev)
+{
+	struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev);
+	struct dsa_loop_priv *ps = ds->priv;
+
+	dsa_unregister_switch(ds);
+	dev_put(ps->netdev);
+}
+
+static struct mdio_driver dsa_loop_drv = {
+	.mdiodrv.driver	= {
+		.name	= "dsa-loop",
+	},
+	.probe	= dsa_loop_drv_probe,
+	.remove	= dsa_loop_drv_remove,
+};
+
+#define NUM_FIXED_PHYS	(DSA_LOOP_NUM_PORTS - 2)
+
+static void unregister_fixed_phys(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < NUM_FIXED_PHYS; i++)
+		if (phydevs[i])
+			fixed_phy_unregister(phydevs[i]);
+}
+
+static int __init dsa_loop_init(void)
+{
+	struct fixed_phy_status status = {
+		.link = 1,
+		.speed = SPEED_100,
+		.duplex = DUPLEX_FULL,
+	};
+	unsigned int i;
+
+	for (i = 0; i < NUM_FIXED_PHYS; i++)
+		phydevs[i] = fixed_phy_register(PHY_POLL, &status, -1, NULL);
+
+	return mdio_driver_register(&dsa_loop_drv);
+}
+module_init(dsa_loop_init);
+
+static void __exit dsa_loop_exit(void)
+{
+	mdio_driver_unregister(&dsa_loop_drv);
+	unregister_fixed_phys();
+}
+module_exit(dsa_loop_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Florian Fainelli");
+MODULE_DESCRIPTION("DSA loopback driver");
diff --git a/drivers/net/dsa/dsa_loop.h b/drivers/net/dsa/dsa_loop.h
new file mode 100644
index 000000000000..dc396877fc95
--- /dev/null
+++ b/drivers/net/dsa/dsa_loop.h
@@ -0,0 +1,19 @@
+#ifndef __DSA_LOOP_H
+#define __DSA_LOOP_H
+
+struct dsa_chip_data;
+
+struct dsa_loop_pdata {
+	/* Must be first, such that dsa_register_switch() can access this
+	 * without gory pointer manipulations
+	 */
+	struct dsa_chip_data cd;
+	const char *name;
+	unsigned int enabled_ports;
+	const char *netdev;
+};
+
+#define DSA_LOOP_NUM_PORTS	6
+#define DSA_LOOP_CPU_PORT	(DSA_LOOP_NUM_PORTS - 1)
+
+#endif /* __DSA_LOOP_H */
diff --git a/drivers/net/dsa/dsa_loop_bdinfo.c b/drivers/net/dsa/dsa_loop_bdinfo.c
new file mode 100644
index 000000000000..fb8d5dc71013
--- /dev/null
+++ b/drivers/net/dsa/dsa_loop_bdinfo.c
@@ -0,0 +1,34 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/phy.h>
+#include <net/dsa.h>
+
+#include "dsa_loop.h"
+
+static struct dsa_loop_pdata dsa_loop_pdata = {
+	.cd = {
+		.port_names[0] = "lan1",
+		.port_names[1] = "lan2",
+		.port_names[2] = "lan3",
+		.port_names[3] = "lan4",
+		.port_names[DSA_LOOP_CPU_PORT] = "cpu",
+	},
+	.name = "DSA mockup driver",
+	.enabled_ports = 0x1f,
+	.netdev = "eth0",
+};
+
+static const struct mdio_board_info bdinfo = {
+	.bus_id	= "fixed-0",
+	.modalias = "dsa-loop",
+	.mdio_addr = 31,
+	.platform_data = &dsa_loop_pdata,
+};
+
+static int __init dsa_loop_bdinfo_init(void)
+{
+	return mdiobus_register_board_info(&bdinfo, 1);
+}
+arch_initcall(dsa_loop_bdinfo_init)
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/dsa/mv88e6xxx/Makefile b/drivers/net/dsa/mv88e6xxx/Makefile
index c36be318de1a..31d37a90cec7 100644
--- a/drivers/net/dsa/mv88e6xxx/Makefile
+++ b/drivers/net/dsa/mv88e6xxx/Makefile
@@ -1,5 +1,6 @@
 obj-$(CONFIG_NET_DSA_MV88E6XXX) += mv88e6xxx.o
 mv88e6xxx-objs := chip.o
 mv88e6xxx-objs += global1.o
+mv88e6xxx-objs += global1_atu.o
 mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_GLOBAL2) += global2.o
 mv88e6xxx-objs += port.o
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 03dc886ed3d6..44ba8cff5631 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -8,6 +8,9 @@
  *
  * Copyright (c) 2016 Andrew Lunn <andrew@lunn.ch>
  *
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
@@ -687,11 +690,6 @@ static bool mv88e6xxx_6165_family(struct mv88e6xxx_chip *chip)
 	return chip->info->family == MV88E6XXX_FAMILY_6165;
 }
 
-static bool mv88e6xxx_6320_family(struct mv88e6xxx_chip *chip)
-{
-	return chip->info->family == MV88E6XXX_FAMILY_6320;
-}
-
 static bool mv88e6xxx_6341_family(struct mv88e6xxx_chip *chip)
 {
 	return chip->info->family == MV88E6XXX_FAMILY_6341;
@@ -1066,11 +1064,6 @@ static void mv88e6xxx_get_regs(struct dsa_switch *ds, int port,
 	mutex_unlock(&chip->reg_lock);
 }
 
-static int _mv88e6xxx_atu_wait(struct mv88e6xxx_chip *chip)
-{
-	return mv88e6xxx_g1_wait(chip, GLOBAL_ATU_OP, GLOBAL_ATU_OP_BUSY);
-}
-
 static int mv88e6xxx_get_eee(struct dsa_switch *ds, int port,
 			     struct ethtool_eee *e)
 {
@@ -1130,143 +1123,42 @@ out:
 	return err;
 }
 
-static int _mv88e6xxx_atu_cmd(struct mv88e6xxx_chip *chip, u16 fid, u16 cmd)
-{
-	u16 val;
-	int err;
-
-	if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_G1_ATU_FID)) {
-		err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_FID, fid);
-		if (err)
-			return err;
-	} else if (mv88e6xxx_num_databases(chip) == 256) {
-		/* ATU DBNum[7:4] are located in ATU Control 15:12 */
-		err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val);
-		if (err)
-			return err;
-
-		err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL,
-					 (val & 0xfff) | ((fid << 8) & 0xf000));
-		if (err)
-			return err;
-
-		/* ATU DBNum[3:0] are located in ATU Operation 3:0 */
-		cmd |= fid & 0xf;
-	}
-
-	err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_OP, cmd);
-	if (err)
-		return err;
-
-	return _mv88e6xxx_atu_wait(chip);
-}
-
-static int _mv88e6xxx_atu_data_write(struct mv88e6xxx_chip *chip,
-				     struct mv88e6xxx_atu_entry *entry)
-{
-	u16 data = entry->state & GLOBAL_ATU_DATA_STATE_MASK;
-
-	if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) {
-		unsigned int mask, shift;
-
-		if (entry->trunk) {
-			data |= GLOBAL_ATU_DATA_TRUNK;
-			mask = GLOBAL_ATU_DATA_TRUNK_ID_MASK;
-			shift = GLOBAL_ATU_DATA_TRUNK_ID_SHIFT;
-		} else {
-			mask = GLOBAL_ATU_DATA_PORT_VECTOR_MASK;
-			shift = GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT;
-		}
-
-		data |= (entry->portv_trunkid << shift) & mask;
-	}
-
-	return mv88e6xxx_g1_write(chip, GLOBAL_ATU_DATA, data);
-}
-
-static int _mv88e6xxx_atu_flush_move(struct mv88e6xxx_chip *chip,
-				     struct mv88e6xxx_atu_entry *entry,
-				     bool static_too)
+static u16 mv88e6xxx_port_vlan(struct mv88e6xxx_chip *chip, int dev, int port)
 {
-	int op;
-	int err;
-
-	err = _mv88e6xxx_atu_wait(chip);
-	if (err)
-		return err;
-
-	err = _mv88e6xxx_atu_data_write(chip, entry);
-	if (err)
-		return err;
-
-	if (entry->fid) {
-		op = static_too ? GLOBAL_ATU_OP_FLUSH_MOVE_ALL_DB :
-			GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC_DB;
-	} else {
-		op = static_too ? GLOBAL_ATU_OP_FLUSH_MOVE_ALL :
-			GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC;
-	}
-
-	return _mv88e6xxx_atu_cmd(chip, entry->fid, op);
-}
-
-static int _mv88e6xxx_atu_flush(struct mv88e6xxx_chip *chip,
-				u16 fid, bool static_too)
-{
-	struct mv88e6xxx_atu_entry entry = {
-		.fid = fid,
-		.state = 0, /* EntryState bits must be 0 */
-	};
+	struct dsa_switch *ds = NULL;
+	struct net_device *br;
+	u16 pvlan;
+	int i;
 
-	return _mv88e6xxx_atu_flush_move(chip, &entry, static_too);
-}
+	if (dev < DSA_MAX_SWITCHES)
+		ds = chip->ds->dst->ds[dev];
 
-static int _mv88e6xxx_atu_move(struct mv88e6xxx_chip *chip, u16 fid,
-			       int from_port, int to_port, bool static_too)
-{
-	struct mv88e6xxx_atu_entry entry = {
-		.trunk = false,
-		.fid = fid,
-	};
+	/* Prevent frames from unknown switch or port */
+	if (!ds || port >= ds->num_ports)
+		return 0;
 
-	/* EntryState bits must be 0xF */
-	entry.state = GLOBAL_ATU_DATA_STATE_MASK;
+	/* Frames from DSA links and CPU ports can egress any local port */
+	if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))
+		return mv88e6xxx_port_mask(chip);
 
-	/* ToPort and FromPort are respectively in PortVec bits 7:4 and 3:0 */
-	entry.portv_trunkid = (to_port & 0x0f) << 4;
-	entry.portv_trunkid |= from_port & 0x0f;
+	br = ds->ports[port].bridge_dev;
+	pvlan = 0;
 
-	return _mv88e6xxx_atu_flush_move(chip, &entry, static_too);
-}
+	/* Frames from user ports can egress any local DSA links and CPU ports,
+	 * as well as any local member of their bridge group.
+	 */
+	for (i = 0; i < mv88e6xxx_num_ports(chip); ++i)
+		if (dsa_is_cpu_port(chip->ds, i) ||
+		    dsa_is_dsa_port(chip->ds, i) ||
+		    (br && chip->ds->ports[i].bridge_dev == br))
+			pvlan |= BIT(i);
 
-static int _mv88e6xxx_atu_remove(struct mv88e6xxx_chip *chip, u16 fid,
-				 int port, bool static_too)
-{
-	/* Destination port 0xF means remove the entries */
-	return _mv88e6xxx_atu_move(chip, fid, port, 0x0f, static_too);
+	return pvlan;
 }
 
-static int _mv88e6xxx_port_based_vlan_map(struct mv88e6xxx_chip *chip, int port)
+static int mv88e6xxx_port_vlan_map(struct mv88e6xxx_chip *chip, int port)
 {
-	struct dsa_switch *ds = chip->ds;
-	struct net_device *bridge = ds->ports[port].bridge_dev;
-	u16 output_ports = 0;
-	int i;
-
-	/* allow CPU port or DSA link(s) to send frames to every port */
-	if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) {
-		output_ports = ~0;
-	} else {
-		for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
-			/* allow sending frames to every group member */
-			if (bridge && ds->ports[i].bridge_dev == bridge)
-				output_ports |= BIT(i);
-
-			/* allow sending frames to CPU port and DSA link(s) */
-			if (dsa_is_cpu_port(ds, i) || dsa_is_dsa_port(ds, i))
-				output_ports |= BIT(i);
-		}
-	}
+	u16 output_ports = mv88e6xxx_port_vlan(chip, chip->ds->index, port);
 
 	/* prevent frames from going back out of the port they came in on */
 	output_ports &= ~BIT(port);
@@ -1306,13 +1198,68 @@ static void mv88e6xxx_port_stp_state_set(struct dsa_switch *ds, int port,
 		netdev_err(ds->ports[port].netdev, "failed to update state\n");
 }
 
+static int mv88e6xxx_atu_setup(struct mv88e6xxx_chip *chip)
+{
+	int err;
+
+	err = mv88e6xxx_g1_atu_flush(chip, 0, true);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_g1_atu_set_learn2all(chip, true);
+	if (err)
+		return err;
+
+	return mv88e6xxx_g1_atu_set_age_time(chip, 300000);
+}
+
+static int mv88e6xxx_pvt_map(struct mv88e6xxx_chip *chip, int dev, int port)
+{
+	u16 pvlan = 0;
+
+	if (!mv88e6xxx_has_pvt(chip))
+		return -EOPNOTSUPP;
+
+	/* Skip the local source device, which uses in-chip port VLAN */
+	if (dev != chip->ds->index)
+		pvlan = mv88e6xxx_port_vlan(chip, dev, port);
+
+	return mv88e6xxx_g2_pvt_write(chip, dev, port, pvlan);
+}
+
+static int mv88e6xxx_pvt_setup(struct mv88e6xxx_chip *chip)
+{
+	int dev, port;
+	int err;
+
+	if (!mv88e6xxx_has_pvt(chip))
+		return 0;
+
+	/* Clear 5 Bit Port for usage with Marvell Link Street devices:
+	 * use 4 bits for the Src_Port/Src_Trunk and 5 bits for the Src_Dev.
+	 */
+	err = mv88e6xxx_g2_misc_4_bit_port(chip);
+	if (err)
+		return err;
+
+	for (dev = 0; dev < MV88E6XXX_MAX_PVT_SWITCHES; ++dev) {
+		for (port = 0; port < MV88E6XXX_MAX_PVT_PORTS; ++port) {
+			err = mv88e6xxx_pvt_map(chip, dev, port);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
 static void mv88e6xxx_port_fast_age(struct dsa_switch *ds, int port)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
 	int err;
 
 	mutex_lock(&chip->reg_lock);
-	err = _mv88e6xxx_atu_remove(chip, 0, port, false);
+	err = mv88e6xxx_g1_atu_remove(chip, 0, port, false);
 	mutex_unlock(&chip->reg_lock);
 
 	if (err)
@@ -1662,7 +1609,7 @@ loadpurge:
 	return _mv88e6xxx_vtu_cmd(chip, GLOBAL_VTU_OP_STU_LOAD_PURGE);
 }
 
-static int _mv88e6xxx_fid_new(struct mv88e6xxx_chip *chip, u16 *fid)
+static int mv88e6xxx_atu_new(struct mv88e6xxx_chip *chip, u16 *fid)
 {
 	DECLARE_BITMAP(fid_bitmap, MV88E6XXX_N_FID);
 	struct mv88e6xxx_vtu_entry vlan;
@@ -1703,7 +1650,7 @@ static int _mv88e6xxx_fid_new(struct mv88e6xxx_chip *chip, u16 *fid)
 		return -ENOSPC;
 
 	/* Clear the database */
-	return _mv88e6xxx_atu_flush(chip, *fid, true);
+	return mv88e6xxx_g1_atu_flush(chip, *fid, true);
 }
 
 static int _mv88e6xxx_vtu_new(struct mv88e6xxx_chip *chip, u16 vid,
@@ -1716,7 +1663,7 @@ static int _mv88e6xxx_vtu_new(struct mv88e6xxx_chip *chip, u16 vid,
 	};
 	int i, err;
 
-	err = _mv88e6xxx_fid_new(chip, &vlan.fid);
+	err = mv88e6xxx_atu_new(chip, &vlan.fid);
 	if (err)
 		return err;
 
@@ -1964,7 +1911,7 @@ static int _mv88e6xxx_port_vlan_del(struct mv88e6xxx_chip *chip,
 	if (err)
 		return err;
 
-	return _mv88e6xxx_atu_remove(chip, vlan.fid, port, false);
+	return mv88e6xxx_g1_atu_remove(chip, vlan.fid, port, false);
 }
 
 static int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port,
@@ -2001,96 +1948,6 @@ unlock:
 	return err;
 }
 
-static int _mv88e6xxx_atu_mac_write(struct mv88e6xxx_chip *chip,
-				    const unsigned char *addr)
-{
-	int i, err;
-
-	for (i = 0; i < 3; i++) {
-		err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_MAC_01 + i,
-					 (addr[i * 2] << 8) | addr[i * 2 + 1]);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static int _mv88e6xxx_atu_mac_read(struct mv88e6xxx_chip *chip,
-				   unsigned char *addr)
-{
-	u16 val;
-	int i, err;
-
-	for (i = 0; i < 3; i++) {
-		err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_MAC_01 + i, &val);
-		if (err)
-			return err;
-
-		addr[i * 2] = val >> 8;
-		addr[i * 2 + 1] = val & 0xff;
-	}
-
-	return 0;
-}
-
-static int _mv88e6xxx_atu_load(struct mv88e6xxx_chip *chip,
-			       struct mv88e6xxx_atu_entry *entry)
-{
-	int ret;
-
-	ret = _mv88e6xxx_atu_wait(chip);
-	if (ret < 0)
-		return ret;
-
-	ret = _mv88e6xxx_atu_mac_write(chip, entry->mac);
-	if (ret < 0)
-		return ret;
-
-	ret = _mv88e6xxx_atu_data_write(chip, entry);
-	if (ret < 0)
-		return ret;
-
-	return _mv88e6xxx_atu_cmd(chip, entry->fid, GLOBAL_ATU_OP_LOAD_DB);
-}
-
-static int _mv88e6xxx_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid,
-				  struct mv88e6xxx_atu_entry *entry);
-
-static int mv88e6xxx_atu_get(struct mv88e6xxx_chip *chip, int fid,
-			     const u8 *addr, struct mv88e6xxx_atu_entry *entry)
-{
-	struct mv88e6xxx_atu_entry next;
-	int err;
-
-	memcpy(next.mac, addr, ETH_ALEN);
-	eth_addr_dec(next.mac);
-
-	err = _mv88e6xxx_atu_mac_write(chip, next.mac);
-	if (err)
-		return err;
-
-	do {
-		err = _mv88e6xxx_atu_getnext(chip, fid, &next);
-		if (err)
-			return err;
-
-		if (next.state == GLOBAL_ATU_DATA_STATE_UNUSED)
-			break;
-
-		if (ether_addr_equal(next.mac, addr)) {
-			*entry = next;
-			return 0;
-		}
-	} while (ether_addr_greater(addr, next.mac));
-
-	memset(entry, 0, sizeof(*entry));
-	entry->fid = fid;
-	ether_addr_copy(entry->mac, addr);
-
-	return 0;
-}
-
 static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
 					const unsigned char *addr, u16 vid,
 					u8 state)
@@ -2107,21 +1964,32 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
 	if (err)
 		return err;
 
-	err = mv88e6xxx_atu_get(chip, vlan.fid, addr, &entry);
+	entry.state = GLOBAL_ATU_DATA_STATE_UNUSED;
+	ether_addr_copy(entry.mac, addr);
+	eth_addr_dec(entry.mac);
+
+	err = mv88e6xxx_g1_atu_getnext(chip, vlan.fid, &entry);
 	if (err)
 		return err;
 
+	/* Initialize a fresh ATU entry if it isn't found */
+	if (entry.state == GLOBAL_ATU_DATA_STATE_UNUSED ||
+	    !ether_addr_equal(entry.mac, addr)) {
+		memset(&entry, 0, sizeof(entry));
+		ether_addr_copy(entry.mac, addr);
+	}
+
 	/* Purge the ATU entry only if no port is using it anymore */
 	if (state == GLOBAL_ATU_DATA_STATE_UNUSED) {
-		entry.portv_trunkid &= ~BIT(port);
-		if (!entry.portv_trunkid)
+		entry.portvec &= ~BIT(port);
+		if (!entry.portvec)
 			entry.state = GLOBAL_ATU_DATA_STATE_UNUSED;
 	} else {
-		entry.portv_trunkid |= BIT(port);
+		entry.portvec |= BIT(port);
 		entry.state = state;
 	}
 
-	return _mv88e6xxx_atu_load(chip, &entry);
+	return mv88e6xxx_g1_atu_loadpurge(chip, vlan.fid, &entry);
 }
 
 static int mv88e6xxx_port_fdb_prepare(struct dsa_switch *ds, int port,
@@ -2161,75 +2029,26 @@ static int mv88e6xxx_port_fdb_del(struct dsa_switch *ds, int port,
 	return err;
 }
 
-static int _mv88e6xxx_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid,
-				  struct mv88e6xxx_atu_entry *entry)
-{
-	struct mv88e6xxx_atu_entry next = { 0 };
-	u16 val;
-	int err;
-
-	next.fid = fid;
-
-	err = _mv88e6xxx_atu_wait(chip);
-	if (err)
-		return err;
-
-	err = _mv88e6xxx_atu_cmd(chip, fid, GLOBAL_ATU_OP_GET_NEXT_DB);
-	if (err)
-		return err;
-
-	err = _mv88e6xxx_atu_mac_read(chip, next.mac);
-	if (err)
-		return err;
-
-	err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_DATA, &val);
-	if (err)
-		return err;
-
-	next.state = val & GLOBAL_ATU_DATA_STATE_MASK;
-	if (next.state != GLOBAL_ATU_DATA_STATE_UNUSED) {
-		unsigned int mask, shift;
-
-		if (val & GLOBAL_ATU_DATA_TRUNK) {
-			next.trunk = true;
-			mask = GLOBAL_ATU_DATA_TRUNK_ID_MASK;
-			shift = GLOBAL_ATU_DATA_TRUNK_ID_SHIFT;
-		} else {
-			next.trunk = false;
-			mask = GLOBAL_ATU_DATA_PORT_VECTOR_MASK;
-			shift = GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT;
-		}
-
-		next.portv_trunkid = (val & mask) >> shift;
-	}
-
-	*entry = next;
-	return 0;
-}
-
 static int mv88e6xxx_port_db_dump_fid(struct mv88e6xxx_chip *chip,
 				      u16 fid, u16 vid, int port,
 				      struct switchdev_obj *obj,
 				      int (*cb)(struct switchdev_obj *obj))
 {
-	struct mv88e6xxx_atu_entry addr = {
-		.mac = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
-	};
+	struct mv88e6xxx_atu_entry addr;
 	int err;
 
-	err = _mv88e6xxx_atu_mac_write(chip, addr.mac);
-	if (err)
-		return err;
+	addr.state = GLOBAL_ATU_DATA_STATE_UNUSED;
+	eth_broadcast_addr(addr.mac);
 
 	do {
-		err = _mv88e6xxx_atu_getnext(chip, fid, &addr);
+		err = mv88e6xxx_g1_atu_getnext(chip, fid, &addr);
 		if (err)
 			return err;
 
 		if (addr.state == GLOBAL_ATU_DATA_STATE_UNUSED)
 			break;
 
-		if (addr.trunk || (addr.portv_trunkid & BIT(port)) == 0)
+		if (addr.trunk || (addr.portvec & BIT(port)) == 0)
 			continue;
 
 		if (obj->id == SWITCHDEV_OBJ_ID_PORT_FDB) {
@@ -2321,23 +2140,52 @@ static int mv88e6xxx_port_fdb_dump(struct dsa_switch *ds, int port,
 	return err;
 }
 
-static int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port,
-				      struct net_device *br)
+static int mv88e6xxx_bridge_map(struct mv88e6xxx_chip *chip,
+				struct net_device *br)
 {
-	struct mv88e6xxx_chip *chip = ds->priv;
-	int i, err = 0;
-
-	mutex_lock(&chip->reg_lock);
+	struct dsa_switch *ds;
+	int port;
+	int dev;
+	int err;
 
-	/* Remap each port's VLANTable */
-	for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
-		if (ds->ports[i].bridge_dev == br) {
-			err = _mv88e6xxx_port_based_vlan_map(chip, i);
+	/* Remap the Port VLAN of each local bridge group member */
+	for (port = 0; port < mv88e6xxx_num_ports(chip); ++port) {
+		if (chip->ds->ports[port].bridge_dev == br) {
+			err = mv88e6xxx_port_vlan_map(chip, port);
 			if (err)
-				break;
+				return err;
 		}
 	}
 
+	if (!mv88e6xxx_has_pvt(chip))
+		return 0;
+
+	/* Remap the Port VLAN of each cross-chip bridge group member */
+	for (dev = 0; dev < DSA_MAX_SWITCHES; ++dev) {
+		ds = chip->ds->dst->ds[dev];
+		if (!ds)
+			break;
+
+		for (port = 0; port < ds->num_ports; ++port) {
+			if (ds->ports[port].bridge_dev == br) {
+				err = mv88e6xxx_pvt_map(chip, dev, port);
+				if (err)
+					return err;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port,
+				      struct net_device *br)
+{
+	struct mv88e6xxx_chip *chip = ds->priv;
+	int err;
+
+	mutex_lock(&chip->reg_lock);
+	err = mv88e6xxx_bridge_map(chip, br);
 	mutex_unlock(&chip->reg_lock);
 
 	return err;
@@ -2347,17 +2195,41 @@ static void mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port,
 					struct net_device *br)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
-	int i;
 
 	mutex_lock(&chip->reg_lock);
+	if (mv88e6xxx_bridge_map(chip, br) ||
+	    mv88e6xxx_port_vlan_map(chip, port))
+		dev_err(ds->dev, "failed to remap in-chip Port VLAN\n");
+	mutex_unlock(&chip->reg_lock);
+}
 
-	/* Remap each port's VLANTable */
-	for (i = 0; i < mv88e6xxx_num_ports(chip); ++i)
-		if (i == port || ds->ports[i].bridge_dev == br)
-			if (_mv88e6xxx_port_based_vlan_map(chip, i))
-				netdev_warn(ds->ports[i].netdev,
-					    "failed to remap\n");
+static int mv88e6xxx_crosschip_bridge_join(struct dsa_switch *ds, int dev,
+					   int port, struct net_device *br)
+{
+	struct mv88e6xxx_chip *chip = ds->priv;
+	int err;
+
+	if (!mv88e6xxx_has_pvt(chip))
+		return 0;
 
+	mutex_lock(&chip->reg_lock);
+	err = mv88e6xxx_pvt_map(chip, dev, port);
+	mutex_unlock(&chip->reg_lock);
+
+	return err;
+}
+
+static void mv88e6xxx_crosschip_bridge_leave(struct dsa_switch *ds, int dev,
+					     int port, struct net_device *br)
+{
+	struct mv88e6xxx_chip *chip = ds->priv;
+
+	if (!mv88e6xxx_has_pvt(chip))
+		return;
+
+	mutex_lock(&chip->reg_lock);
+	if (mv88e6xxx_pvt_map(chip, dev, port))
+		dev_err(ds->dev, "failed to remap cross-chip Port VLAN\n");
 	mutex_unlock(&chip->reg_lock);
 }
 
@@ -2433,70 +2305,85 @@ static int mv88e6xxx_serdes_power_on(struct mv88e6xxx_chip *chip)
 	return err;
 }
 
-static int mv88e6xxx_setup_port_dsa(struct mv88e6xxx_chip *chip, int port,
-				    int upstream_port)
+static int mv88e6xxx_set_port_mode(struct mv88e6xxx_chip *chip, int port,
+				   enum mv88e6xxx_frame_mode frame, u16 egress,
+				   u16 etype)
 {
 	int err;
 
-	err = chip->info->ops->port_set_frame_mode(
-		chip, port, MV88E6XXX_FRAME_MODE_DSA);
+	if (!chip->info->ops->port_set_frame_mode)
+		return -EOPNOTSUPP;
+
+	err = mv88e6xxx_port_set_egress_mode(chip, port, egress);
 	if (err)
 		return err;
 
-	return chip->info->ops->port_set_egress_unknowns(
-		chip, port, port == upstream_port);
+	err = chip->info->ops->port_set_frame_mode(chip, port, frame);
+	if (err)
+		return err;
+
+	if (chip->info->ops->port_set_ether_type)
+		return chip->info->ops->port_set_ether_type(chip, port, etype);
+
+	return 0;
 }
 
-static int mv88e6xxx_setup_port_cpu(struct mv88e6xxx_chip *chip, int port)
+static int mv88e6xxx_set_port_mode_normal(struct mv88e6xxx_chip *chip, int port)
 {
-	int err;
+	return mv88e6xxx_set_port_mode(chip, port, MV88E6XXX_FRAME_MODE_NORMAL,
+				       PORT_CONTROL_EGRESS_UNMODIFIED,
+				       PORT_ETH_TYPE_DEFAULT);
+}
 
-	switch (chip->info->tag_protocol) {
-	case DSA_TAG_PROTO_EDSA:
-		err = chip->info->ops->port_set_frame_mode(
-			chip, port, MV88E6XXX_FRAME_MODE_ETHERTYPE);
-		if (err)
-			return err;
+static int mv88e6xxx_set_port_mode_dsa(struct mv88e6xxx_chip *chip, int port)
+{
+	return mv88e6xxx_set_port_mode(chip, port, MV88E6XXX_FRAME_MODE_DSA,
+				       PORT_CONTROL_EGRESS_UNMODIFIED,
+				       PORT_ETH_TYPE_DEFAULT);
+}
 
-		err = mv88e6xxx_port_set_egress_mode(
-			chip, port, PORT_CONTROL_EGRESS_ADD_TAG);
-		if (err)
-			return err;
+static int mv88e6xxx_set_port_mode_edsa(struct mv88e6xxx_chip *chip, int port)
+{
+	return mv88e6xxx_set_port_mode(chip, port,
+				       MV88E6XXX_FRAME_MODE_ETHERTYPE,
+				       PORT_CONTROL_EGRESS_ADD_TAG, ETH_P_EDSA);
+}
 
-		if (chip->info->ops->port_set_ether_type)
-			err = chip->info->ops->port_set_ether_type(
-				chip, port, ETH_P_EDSA);
-		break;
+static int mv88e6xxx_setup_port_mode(struct mv88e6xxx_chip *chip, int port)
+{
+	if (dsa_is_dsa_port(chip->ds, port))
+		return mv88e6xxx_set_port_mode_dsa(chip, port);
 
-	case DSA_TAG_PROTO_DSA:
-		err = chip->info->ops->port_set_frame_mode(
-			chip, port, MV88E6XXX_FRAME_MODE_DSA);
-		if (err)
-			return err;
+	if (dsa_is_normal_port(chip->ds, port))
+		return mv88e6xxx_set_port_mode_normal(chip, port);
 
-		err = mv88e6xxx_port_set_egress_mode(
-			chip, port, PORT_CONTROL_EGRESS_UNMODIFIED);
-		break;
-	default:
-		err = -EINVAL;
-	}
+	/* Setup CPU port mode depending on its supported tag format */
+	if (chip->info->tag_protocol == DSA_TAG_PROTO_DSA)
+		return mv88e6xxx_set_port_mode_dsa(chip, port);
 
-	if (err)
-		return err;
+	if (chip->info->tag_protocol == DSA_TAG_PROTO_EDSA)
+		return mv88e6xxx_set_port_mode_edsa(chip, port);
 
-	return chip->info->ops->port_set_egress_unknowns(chip, port, true);
+	return -EINVAL;
 }
 
-static int mv88e6xxx_setup_port_normal(struct mv88e6xxx_chip *chip, int port)
+static int mv88e6xxx_setup_message_port(struct mv88e6xxx_chip *chip, int port)
 {
-	int err;
+	bool message = dsa_is_dsa_port(chip->ds, port);
 
-	err = chip->info->ops->port_set_frame_mode(
-		chip, port, MV88E6XXX_FRAME_MODE_NORMAL);
-	if (err)
-		return err;
+	return mv88e6xxx_port_set_message_port(chip, port, message);
+}
 
-	return chip->info->ops->port_set_egress_unknowns(chip, port, false);
+static int mv88e6xxx_setup_egress_floods(struct mv88e6xxx_chip *chip, int port)
+{
+	bool flood = port == dsa_upstream_port(chip->ds);
+
+	/* Upstream ports flood frames with unknown unicast or multicast DA */
+	if (chip->info->ops->port_set_egress_floods)
+		return chip->info->ops->port_set_egress_floods(chip, port,
+							       flood, flood);
+
+	return 0;
 }
 
 static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
@@ -2541,14 +2428,11 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
 	if (err)
 		return err;
 
-	if (dsa_is_cpu_port(ds, port)) {
-		err = mv88e6xxx_setup_port_cpu(chip, port);
-	} else if (dsa_is_dsa_port(ds, port)) {
-		err = mv88e6xxx_setup_port_dsa(chip, port,
-					       dsa_upstream_port(ds));
-	} else {
-		err = mv88e6xxx_setup_port_normal(chip, port);
-	}
+	err = mv88e6xxx_setup_port_mode(chip, port);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_setup_egress_floods(chip, port);
 	if (err)
 		return err;
 
@@ -2623,20 +2507,14 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
 			return err;
 	}
 
-	if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) ||
-	    mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) ||
-	    mv88e6xxx_6320_family(chip) || mv88e6xxx_6341_family(chip)) {
-		/* Port ATU control: disable limiting the number of
-		 * address database entries that this port is allowed
-		 * to use.
-		 */
-		err = mv88e6xxx_port_write(chip, port, PORT_ATU_CONTROL,
-					   0x0000);
-		/* Priority Override: disable DA, SA and VTU priority
-		 * override.
-		 */
-		err = mv88e6xxx_port_write(chip, port, PORT_PRI_OVERRIDE,
-					   0x0000);
+	if (chip->info->ops->port_disable_learn_limit) {
+		err = chip->info->ops->port_disable_learn_limit(chip, port);
+		if (err)
+			return err;
+	}
+
+	if (chip->info->ops->port_disable_pri_override) {
+		err = chip->info->ops->port_disable_pri_override(chip, port);
 		if (err)
 			return err;
 	}
@@ -2653,10 +2531,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
 			return err;
 	}
 
-	/* Port Control 1: disable trunking, disable sending
-	 * learning messages to this port.
-	 */
-	err = mv88e6xxx_port_write(chip, port, PORT_CONTROL_1, 0x0000);
+	err = mv88e6xxx_setup_message_port(chip, port);
 	if (err)
 		return err;
 
@@ -2668,7 +2543,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
 	if (err)
 		return err;
 
-	err = _mv88e6xxx_port_based_vlan_map(chip, port);
+	err = mv88e6xxx_port_vlan_map(chip, port);
 	if (err)
 		return err;
 
@@ -2697,33 +2572,6 @@ static int mv88e6xxx_g1_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr)
 	return 0;
 }
 
-static int mv88e6xxx_g1_set_age_time(struct mv88e6xxx_chip *chip,
-				     unsigned int msecs)
-{
-	const unsigned int coeff = chip->info->age_time_coeff;
-	const unsigned int min = 0x01 * coeff;
-	const unsigned int max = 0xff * coeff;
-	u8 age_time;
-	u16 val;
-	int err;
-
-	if (msecs < min || msecs > max)
-		return -ERANGE;
-
-	/* Round to nearest multiple of coeff */
-	age_time = (msecs + coeff / 2) / coeff;
-
-	err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val);
-	if (err)
-		return err;
-
-	/* AgeTime is 11:4 bits */
-	val &= ~0xff0;
-	val |= age_time << 4;
-
-	return mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val);
-}
-
 static int mv88e6xxx_set_ageing_time(struct dsa_switch *ds,
 				     unsigned int ageing_time)
 {
@@ -2731,7 +2579,7 @@ static int mv88e6xxx_set_ageing_time(struct dsa_switch *ds,
 	int err;
 
 	mutex_lock(&chip->reg_lock);
-	err = mv88e6xxx_g1_set_age_time(chip, ageing_time);
+	err = mv88e6xxx_g1_atu_set_age_time(chip, ageing_time);
 	mutex_unlock(&chip->reg_lock);
 
 	return err;
@@ -2774,24 +2622,6 @@ static int mv88e6xxx_g1_setup(struct mv88e6xxx_chip *chip)
 	if (err < 0)
 		return err;
 
-	/* Set the default address aging time to 5 minutes, and
-	 * enable address learn messages to be sent to all message
-	 * ports.
-	 */
-	err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL,
-				 GLOBAL_ATU_CONTROL_LEARN2ALL);
-	if (err)
-		return err;
-
-	err = mv88e6xxx_g1_set_age_time(chip, 300000);
-	if (err)
-		return err;
-
-	/* Clear all ATU entries */
-	err = _mv88e6xxx_atu_flush(chip, 0, true);
-	if (err)
-		return err;
-
 	/* Configure the IP ToS mapping registers. */
 	err = mv88e6xxx_g1_write(chip, GLOBAL_IP_PRI_0, 0x0000);
 	if (err)
@@ -2872,6 +2702,14 @@ static int mv88e6xxx_setup(struct dsa_switch *ds)
 			goto unlock;
 	}
 
+	err = mv88e6xxx_pvt_setup(chip);
+	if (err)
+		goto unlock;
+
+	err = mv88e6xxx_atu_setup(chip);
+	if (err)
+		goto unlock;
+
 	/* Some generations have the configuration of sending reserved
 	 * management frames to the CPU in global2, others in
 	 * global1. Hence it does not fit the two setup functions
@@ -3101,10 +2939,12 @@ static const struct mv88e6xxx_ops mv88e6085_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3127,7 +2967,7 @@ static const struct mv88e6xxx_ops mv88e6095_ops = {
 	.port_set_duplex = mv88e6xxx_port_set_duplex,
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_set_frame_mode = mv88e6085_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6095_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6185_port_set_egress_floods,
 	.port_set_upstream_port = mv88e6095_port_set_upstream_port,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3149,11 +2989,13 @@ static const struct mv88e6xxx_ops mv88e6097_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3174,7 +3016,9 @@ static const struct mv88e6xxx_ops mv88e6123_ops = {
 	.port_set_duplex = mv88e6xxx_port_set_duplex,
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_set_frame_mode = mv88e6085_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6085_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3196,7 +3040,7 @@ static const struct mv88e6xxx_ops mv88e6131_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6095_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6185_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_set_upstream_port = mv88e6095_port_set_upstream_port,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
@@ -3215,6 +3059,37 @@ static const struct mv88e6xxx_ops mv88e6131_ops = {
 	.reset = mv88e6185_g1_reset,
 };
 
+static const struct mv88e6xxx_ops mv88e6141_ops = {
+	/* MV88E6XXX_FAMILY_6341 */
+	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
+	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
+	.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
+	.phy_read = mv88e6xxx_g2_smi_phy_read,
+	.phy_write = mv88e6xxx_g2_smi_phy_write,
+	.port_set_link = mv88e6xxx_port_set_link,
+	.port_set_duplex = mv88e6xxx_port_set_duplex,
+	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
+	.port_set_speed = mv88e6390_port_set_speed,
+	.port_tag_remap = mv88e6095_port_tag_remap,
+	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
+	.port_set_ether_type = mv88e6351_port_set_ether_type,
+	.port_jumbo_config = mv88e6165_port_jumbo_config,
+	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
+	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.stats_snapshot = mv88e6390_g1_stats_snapshot,
+	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
+	.stats_get_strings = mv88e6320_stats_get_strings,
+	.stats_get_stats = mv88e6390_stats_get_stats,
+	.g1_set_cpu_port = mv88e6390_g1_set_cpu_port,
+	.g1_set_egress_port = mv88e6390_g1_set_egress_port,
+	.watchdog_ops = &mv88e6390_watchdog_ops,
+	.mgmt_rsvd2cpu =  mv88e6390_g1_mgmt_rsvd2cpu,
+	.reset = mv88e6352_g1_reset,
+};
+
 static const struct mv88e6xxx_ops mv88e6161_ops = {
 	/* MV88E6XXX_FAMILY_6165 */
 	.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
@@ -3225,11 +3100,13 @@ static const struct mv88e6xxx_ops mv88e6161_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3249,6 +3126,8 @@ static const struct mv88e6xxx_ops mv88e6165_ops = {
 	.port_set_link = mv88e6xxx_port_set_link,
 	.port_set_duplex = mv88e6xxx_port_set_duplex,
 	.port_set_speed = mv88e6185_port_set_speed,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3271,11 +3150,13 @@ static const struct mv88e6xxx_ops mv88e6171_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3300,11 +3181,13 @@ static const struct mv88e6xxx_ops mv88e6172_ops = {
 	.port_set_speed = mv88e6352_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3327,11 +3210,13 @@ static const struct mv88e6xxx_ops mv88e6175_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3356,11 +3241,13 @@ static const struct mv88e6xxx_ops mv88e6176_ops = {
 	.port_set_speed = mv88e6352_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3381,7 +3268,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = {
 	.port_set_duplex = mv88e6xxx_port_set_duplex,
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_set_frame_mode = mv88e6085_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6095_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6185_port_set_egress_floods,
 	.port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting,
 	.port_set_upstream_port = mv88e6095_port_set_upstream_port,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
@@ -3410,9 +3297,11 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
 	.port_set_speed = mv88e6390_port_set_speed,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_pause_config = mv88e6390_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3438,9 +3327,11 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	.port_set_speed = mv88e6390x_port_set_speed,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_pause_config = mv88e6390_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3466,9 +3357,11 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
 	.port_set_speed = mv88e6390_port_set_speed,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_pause_config = mv88e6390_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3494,11 +3387,13 @@ static const struct mv88e6xxx_ops mv88e6240_ops = {
 	.port_set_speed = mv88e6352_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3523,10 +3418,12 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.port_set_speed = mv88e6390_port_set_speed,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_pause_config = mv88e6390_port_pause_config,
 	.port_set_cmode = mv88e6390x_port_set_cmode,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3551,11 +3448,13 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
 	.stats_get_strings = mv88e6320_stats_get_strings,
@@ -3578,11 +3477,13 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
 	.stats_get_strings = mv88e6320_stats_get_strings,
@@ -3592,6 +3493,37 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.reset = mv88e6352_g1_reset,
 };
 
+static const struct mv88e6xxx_ops mv88e6341_ops = {
+	/* MV88E6XXX_FAMILY_6341 */
+	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
+	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
+	.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
+	.phy_read = mv88e6xxx_g2_smi_phy_read,
+	.phy_write = mv88e6xxx_g2_smi_phy_write,
+	.port_set_link = mv88e6xxx_port_set_link,
+	.port_set_duplex = mv88e6xxx_port_set_duplex,
+	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
+	.port_set_speed = mv88e6390_port_set_speed,
+	.port_tag_remap = mv88e6095_port_tag_remap,
+	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
+	.port_set_ether_type = mv88e6351_port_set_ether_type,
+	.port_jumbo_config = mv88e6165_port_jumbo_config,
+	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
+	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.stats_snapshot = mv88e6390_g1_stats_snapshot,
+	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
+	.stats_get_strings = mv88e6320_stats_get_strings,
+	.stats_get_stats = mv88e6390_stats_get_stats,
+	.g1_set_cpu_port = mv88e6390_g1_set_cpu_port,
+	.g1_set_egress_port = mv88e6390_g1_set_egress_port,
+	.watchdog_ops = &mv88e6390_watchdog_ops,
+	.mgmt_rsvd2cpu =  mv88e6390_g1_mgmt_rsvd2cpu,
+	.reset = mv88e6352_g1_reset,
+};
+
 static const struct mv88e6xxx_ops mv88e6350_ops = {
 	/* MV88E6XXX_FAMILY_6351 */
 	.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
@@ -3603,11 +3535,13 @@ static const struct mv88e6xxx_ops mv88e6350_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3630,11 +3564,13 @@ static const struct mv88e6xxx_ops mv88e6351_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3659,11 +3595,13 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
 	.port_set_speed = mv88e6352_port_set_speed,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6097_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3675,64 +3613,6 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
 	.reset = mv88e6352_g1_reset,
 };
 
-static const struct mv88e6xxx_ops mv88e6141_ops = {
-	/* MV88E6XXX_FAMILY_6341 */
-	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
-	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
-	.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
-	.phy_read = mv88e6xxx_g2_smi_phy_read,
-	.phy_write = mv88e6xxx_g2_smi_phy_write,
-	.port_set_link = mv88e6xxx_port_set_link,
-	.port_set_duplex = mv88e6xxx_port_set_duplex,
-	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
-	.port_set_speed = mv88e6390_port_set_speed,
-	.port_tag_remap = mv88e6095_port_tag_remap,
-	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
-	.port_set_ether_type = mv88e6351_port_set_ether_type,
-	.port_jumbo_config = mv88e6165_port_jumbo_config,
-	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
-	.port_pause_config = mv88e6097_port_pause_config,
-	.stats_snapshot = mv88e6390_g1_stats_snapshot,
-	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
-	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6390_stats_get_stats,
-	.g1_set_cpu_port = mv88e6390_g1_set_cpu_port,
-	.g1_set_egress_port = mv88e6390_g1_set_egress_port,
-	.watchdog_ops = &mv88e6390_watchdog_ops,
-	.mgmt_rsvd2cpu =  mv88e6390_g1_mgmt_rsvd2cpu,
-	.reset = mv88e6352_g1_reset,
-};
-
-static const struct mv88e6xxx_ops mv88e6341_ops = {
-	/* MV88E6XXX_FAMILY_6341 */
-	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
-	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
-	.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
-	.phy_read = mv88e6xxx_g2_smi_phy_read,
-	.phy_write = mv88e6xxx_g2_smi_phy_write,
-	.port_set_link = mv88e6xxx_port_set_link,
-	.port_set_duplex = mv88e6xxx_port_set_duplex,
-	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
-	.port_set_speed = mv88e6390_port_set_speed,
-	.port_tag_remap = mv88e6095_port_tag_remap,
-	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
-	.port_set_ether_type = mv88e6351_port_set_ether_type,
-	.port_jumbo_config = mv88e6165_port_jumbo_config,
-	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
-	.port_pause_config = mv88e6097_port_pause_config,
-	.stats_snapshot = mv88e6390_g1_stats_snapshot,
-	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
-	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6390_stats_get_stats,
-	.g1_set_cpu_port = mv88e6390_g1_set_cpu_port,
-	.g1_set_egress_port = mv88e6390_g1_set_egress_port,
-	.watchdog_ops = &mv88e6390_watchdog_ops,
-	.mgmt_rsvd2cpu =  mv88e6390_g1_mgmt_rsvd2cpu,
-	.reset = mv88e6352_g1_reset,
-};
-
 static const struct mv88e6xxx_ops mv88e6390_ops = {
 	/* MV88E6XXX_FAMILY_6390 */
 	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
@@ -3746,12 +3626,14 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 	.port_set_speed = mv88e6390_port_set_speed,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6390_port_pause_config,
 	.port_set_cmode = mv88e6390x_port_set_cmode,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3777,11 +3659,13 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.port_set_speed = mv88e6390x_port_set_speed,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6390_port_pause_config,
+	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3794,50 +3678,6 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.reset = mv88e6352_g1_reset,
 };
 
-static const struct mv88e6xxx_ops mv88e6391_ops = {
-	/* MV88E6XXX_FAMILY_6390 */
-	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
-	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
-	.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
-	.phy_read = mv88e6xxx_g2_smi_phy_read,
-	.phy_write = mv88e6xxx_g2_smi_phy_write,
-	.port_set_link = mv88e6xxx_port_set_link,
-	.port_set_duplex = mv88e6xxx_port_set_duplex,
-	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
-	.port_set_speed = mv88e6390_port_set_speed,
-	.port_tag_remap = mv88e6390_port_tag_remap,
-	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
-	.port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
-	.port_set_ether_type = mv88e6351_port_set_ether_type,
-	.port_pause_config = mv88e6390_port_pause_config,
-	.stats_snapshot = mv88e6390_g1_stats_snapshot,
-	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
-	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
-	.stats_get_strings = mv88e6320_stats_get_strings,
-	.stats_get_stats = mv88e6390_stats_get_stats,
-	.g1_set_cpu_port = mv88e6390_g1_set_cpu_port,
-	.g1_set_egress_port = mv88e6390_g1_set_egress_port,
-	.watchdog_ops = &mv88e6390_watchdog_ops,
-	.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
-	.reset = mv88e6352_g1_reset,
-};
-
-static int mv88e6xxx_verify_madatory_ops(struct mv88e6xxx_chip *chip,
-					 const struct mv88e6xxx_ops *ops)
-{
-	if (!ops->port_set_frame_mode) {
-		dev_err(chip->dev, "Missing port_set_frame_mode");
-		return -EINVAL;
-	}
-
-	if (!ops->port_set_egress_unknowns) {
-		dev_err(chip->dev, "Missing port_set_egress_mode");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 	[MV88E6085] = {
 		.prod_num = PORT_SWITCH_ID_PROD_NUM_6085,
@@ -3849,6 +3689,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 8,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6097,
 		.ops = &mv88e6085_ops,
@@ -3864,6 +3706,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 8,
+		.atu_move_port_mask = 0xf,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6095,
 		.ops = &mv88e6095_ops,
@@ -3879,6 +3722,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 8,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6097,
 		.ops = &mv88e6097_ops,
@@ -3894,6 +3739,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6165,
 		.ops = &mv88e6123_ops,
@@ -3909,11 +3756,28 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6185,
 		.ops = &mv88e6131_ops,
 	},
 
+	[MV88E6141] = {
+		.prod_num = PORT_SWITCH_ID_PROD_NUM_6141,
+		.family = MV88E6XXX_FAMILY_6341,
+		.name = "Marvell 88E6341",
+		.num_databases = 4096,
+		.num_ports = 6,
+		.port_base_addr = 0x10,
+		.global1_addr = 0x1b,
+		.age_time_coeff = 3750,
+		.atu_move_port_mask = 0x1f,
+		.pvt = true,
+		.tag_protocol = DSA_TAG_PROTO_EDSA,
+		.flags = MV88E6XXX_FLAGS_FAMILY_6341,
+		.ops = &mv88e6141_ops,
+	},
+
 	[MV88E6161] = {
 		.prod_num = PORT_SWITCH_ID_PROD_NUM_6161,
 		.family = MV88E6XXX_FAMILY_6165,
@@ -3924,6 +3788,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6165,
 		.ops = &mv88e6161_ops,
@@ -3939,6 +3805,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6165,
 		.ops = &mv88e6165_ops,
@@ -3954,6 +3822,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6351,
 		.ops = &mv88e6171_ops,
@@ -3969,6 +3839,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6352,
 		.ops = &mv88e6172_ops,
@@ -3984,6 +3856,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6351,
 		.ops = &mv88e6175_ops,
@@ -3999,6 +3873,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6352,
 		.ops = &mv88e6176_ops,
@@ -4014,6 +3890,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 8,
+		.atu_move_port_mask = 0xf,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6185,
 		.ops = &mv88e6185_ops,
@@ -4030,6 +3907,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.age_time_coeff = 3750,
 		.g1_irqs = 9,
+		.pvt = true,
+		.atu_move_port_mask = 0x1f,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6390,
 		.ops = &mv88e6190_ops,
 	},
@@ -4044,6 +3923,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 3750,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0x1f,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6390,
 		.ops = &mv88e6190x_ops,
@@ -4059,9 +3940,11 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 3750,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0x1f,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6390,
-		.ops = &mv88e6391_ops,
+		.ops = &mv88e6191_ops,
 	},
 
 	[MV88E6240] = {
@@ -4074,6 +3957,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6352,
 		.ops = &mv88e6240_ops,
@@ -4089,6 +3974,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 3750,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0x1f,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6390,
 		.ops = &mv88e6290_ops,
@@ -4104,6 +3991,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 8,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6320,
 		.ops = &mv88e6320_ops,
@@ -4119,25 +4008,12 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 8,
+		.atu_move_port_mask = 0xf,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6320,
 		.ops = &mv88e6321_ops,
 	},
 
-	[MV88E6141] = {
-		.prod_num = PORT_SWITCH_ID_PROD_NUM_6141,
-		.family = MV88E6XXX_FAMILY_6341,
-		.name = "Marvell 88E6341",
-		.num_databases = 4096,
-		.num_ports = 6,
-		.port_base_addr = 0x10,
-		.global1_addr = 0x1b,
-		.age_time_coeff = 3750,
-		.tag_protocol = DSA_TAG_PROTO_EDSA,
-		.flags = MV88E6XXX_FLAGS_FAMILY_6341,
-		.ops = &mv88e6141_ops,
-	},
-
 	[MV88E6341] = {
 		.prod_num = PORT_SWITCH_ID_PROD_NUM_6341,
 		.family = MV88E6XXX_FAMILY_6341,
@@ -4147,6 +4023,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.port_base_addr = 0x10,
 		.global1_addr = 0x1b,
 		.age_time_coeff = 3750,
+		.atu_move_port_mask = 0x1f,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6341,
 		.ops = &mv88e6341_ops,
@@ -4162,6 +4040,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6351,
 		.ops = &mv88e6350_ops,
@@ -4177,6 +4057,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6351,
 		.ops = &mv88e6351_ops,
@@ -4192,6 +4074,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 15000,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6352,
 		.ops = &mv88e6352_ops,
@@ -4206,6 +4090,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 3750,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0x1f,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6390,
 		.ops = &mv88e6390_ops,
@@ -4220,6 +4106,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.age_time_coeff = 3750,
 		.g1_irqs = 9,
+		.atu_move_port_mask = 0x1f,
+		.pvt = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6390,
 		.ops = &mv88e6390x_ops,
@@ -4455,6 +4343,8 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = {
 	.port_mdb_add           = mv88e6xxx_port_mdb_add,
 	.port_mdb_del           = mv88e6xxx_port_mdb_del,
 	.port_mdb_dump          = mv88e6xxx_port_mdb_dump,
+	.crosschip_bridge_join	= mv88e6xxx_crosschip_bridge_join,
+	.crosschip_bridge_leave	= mv88e6xxx_crosschip_bridge_leave,
 };
 
 static struct dsa_switch_driver mv88e6xxx_switch_drv = {
@@ -4466,12 +4356,14 @@ static int mv88e6xxx_register_switch(struct mv88e6xxx_chip *chip)
 	struct device *dev = chip->dev;
 	struct dsa_switch *ds;
 
-	ds = dsa_switch_alloc(dev, DSA_MAX_PORTS);
+	ds = dsa_switch_alloc(dev, mv88e6xxx_num_ports(chip));
 	if (!ds)
 		return -ENOMEM;
 
 	ds->priv = chip;
 	ds->ops = &mv88e6xxx_switch_ops;
+	ds->ageing_time_min = chip->info->age_time_coeff;
+	ds->ageing_time_max = chip->info->age_time_coeff * U8_MAX;
 
 	dev_set_drvdata(dev, ds);
 
@@ -4502,10 +4394,6 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 
 	chip->info = compat_info;
 
-	err = mv88e6xxx_verify_madatory_ops(chip, chip->info->ops);
-	if (err)
-		return err;
-
 	err = mv88e6xxx_smi_init(chip, mdiodev->bus, mdiodev->addr);
 	if (err)
 		return err;
diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c
index 75af86a7fad8..39825837a1c9 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.c
+++ b/drivers/net/dsa/mv88e6xxx/global1.c
@@ -3,7 +3,8 @@
  *
  * Copyright (c) 2008 Marvell Semiconductor
  *
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h
index 1aec7382c02d..e30cbe480d5b 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.h
+++ b/drivers/net/dsa/mv88e6xxx/global1.h
@@ -3,7 +3,8 @@
  *
  * Copyright (c) 2008 Marvell Semiconductor
  *
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -38,4 +39,15 @@ int mv88e6095_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port);
 int mv88e6390_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port);
 int mv88e6390_g1_mgmt_rsvd2cpu(struct mv88e6xxx_chip *chip);
 
+int mv88e6xxx_g1_atu_set_learn2all(struct mv88e6xxx_chip *chip, bool learn2all);
+int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip,
+				  unsigned int msecs);
+int mv88e6xxx_g1_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid,
+			     struct mv88e6xxx_atu_entry *entry);
+int mv88e6xxx_g1_atu_loadpurge(struct mv88e6xxx_chip *chip, u16 fid,
+			       struct mv88e6xxx_atu_entry *entry);
+int mv88e6xxx_g1_atu_flush(struct mv88e6xxx_chip *chip, u16 fid, bool all);
+int mv88e6xxx_g1_atu_remove(struct mv88e6xxx_chip *chip, u16 fid, int port,
+			    bool all);
+
 #endif /* _MV88E6XXX_GLOBAL1_H */
diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c
new file mode 100644
index 000000000000..fa7e7db5171b
--- /dev/null
+++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c
@@ -0,0 +1,305 @@
+/*
+ * Marvell 88E6xxx Address Translation Unit (ATU) support
+ *
+ * Copyright (c) 2008 Marvell Semiconductor
+ * Copyright (c) 2017 Savoir-faire Linux, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "mv88e6xxx.h"
+#include "global1.h"
+
+/* Offset 0x01: ATU FID Register */
+
+static int mv88e6xxx_g1_atu_fid_write(struct mv88e6xxx_chip *chip, u16 fid)
+{
+	return mv88e6xxx_g1_write(chip, GLOBAL_ATU_FID, fid & 0xfff);
+}
+
+/* Offset 0x0A: ATU Control Register */
+
+int mv88e6xxx_g1_atu_set_learn2all(struct mv88e6xxx_chip *chip, bool learn2all)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val);
+	if (err)
+		return err;
+
+	if (learn2all)
+		val |= GLOBAL_ATU_CONTROL_LEARN2ALL;
+	else
+		val &= ~GLOBAL_ATU_CONTROL_LEARN2ALL;
+
+	return mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val);
+}
+
+int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip,
+				  unsigned int msecs)
+{
+	const unsigned int coeff = chip->info->age_time_coeff;
+	const unsigned int min = 0x01 * coeff;
+	const unsigned int max = 0xff * coeff;
+	u8 age_time;
+	u16 val;
+	int err;
+
+	if (msecs < min || msecs > max)
+		return -ERANGE;
+
+	/* Round to nearest multiple of coeff */
+	age_time = (msecs + coeff / 2) / coeff;
+
+	err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val);
+	if (err)
+		return err;
+
+	/* AgeTime is 11:4 bits */
+	val &= ~0xff0;
+	val |= age_time << 4;
+
+	err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val);
+	if (err)
+		return err;
+
+	dev_dbg(chip->dev, "AgeTime set to 0x%02x (%d ms)\n", age_time,
+		age_time * coeff);
+
+	return 0;
+}
+
+/* Offset 0x0B: ATU Operation Register */
+
+static int mv88e6xxx_g1_atu_op_wait(struct mv88e6xxx_chip *chip)
+{
+	return mv88e6xxx_g1_wait(chip, GLOBAL_ATU_OP, GLOBAL_ATU_OP_BUSY);
+}
+
+static int mv88e6xxx_g1_atu_op(struct mv88e6xxx_chip *chip, u16 fid, u16 op)
+{
+	u16 val;
+	int err;
+
+	/* FID bits are dispatched all around gradually as more are supported */
+	if (mv88e6xxx_num_databases(chip) > 256) {
+		err = mv88e6xxx_g1_atu_fid_write(chip, fid);
+		if (err)
+			return err;
+	} else {
+		if (mv88e6xxx_num_databases(chip) > 16) {
+			/* ATU DBNum[7:4] are located in ATU Control 15:12 */
+			err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val);
+			if (err)
+				return err;
+
+			val = (val & 0x0fff) | ((fid << 8) & 0xf000);
+			err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val);
+			if (err)
+				return err;
+		}
+
+		/* ATU DBNum[3:0] are located in ATU Operation 3:0 */
+		op |= fid & 0xf;
+	}
+
+	err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_OP, op);
+	if (err)
+		return err;
+
+	return mv88e6xxx_g1_atu_op_wait(chip);
+}
+
+/* Offset 0x0C: ATU Data Register */
+
+static int mv88e6xxx_g1_atu_data_read(struct mv88e6xxx_chip *chip,
+				      struct mv88e6xxx_atu_entry *entry)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_DATA, &val);
+	if (err)
+		return err;
+
+	entry->state = val & 0xf;
+	if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) {
+		entry->trunk = !!(val & GLOBAL_ATU_DATA_TRUNK);
+		entry->portvec = (val >> 4) & mv88e6xxx_port_mask(chip);
+	}
+
+	return 0;
+}
+
+static int mv88e6xxx_g1_atu_data_write(struct mv88e6xxx_chip *chip,
+				       struct mv88e6xxx_atu_entry *entry)
+{
+	u16 data = entry->state & 0xf;
+
+	if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) {
+		if (entry->trunk)
+			data |= GLOBAL_ATU_DATA_TRUNK;
+
+		data |= (entry->portvec & mv88e6xxx_port_mask(chip)) << 4;
+	}
+
+	return mv88e6xxx_g1_write(chip, GLOBAL_ATU_DATA, data);
+}
+
+/* Offset 0x0D: ATU MAC Address Register Bytes 0 & 1
+ * Offset 0x0E: ATU MAC Address Register Bytes 2 & 3
+ * Offset 0x0F: ATU MAC Address Register Bytes 4 & 5
+ */
+
+static int mv88e6xxx_g1_atu_mac_read(struct mv88e6xxx_chip *chip,
+				     struct mv88e6xxx_atu_entry *entry)
+{
+	u16 val;
+	int i, err;
+
+	for (i = 0; i < 3; i++) {
+		err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_MAC_01 + i, &val);
+		if (err)
+			return err;
+
+		entry->mac[i * 2] = val >> 8;
+		entry->mac[i * 2 + 1] = val & 0xff;
+	}
+
+	return 0;
+}
+
+static int mv88e6xxx_g1_atu_mac_write(struct mv88e6xxx_chip *chip,
+				      struct mv88e6xxx_atu_entry *entry)
+{
+	u16 val;
+	int i, err;
+
+	for (i = 0; i < 3; i++) {
+		val = (entry->mac[i * 2] << 8) | entry->mac[i * 2 + 1];
+		err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_MAC_01 + i, val);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/* Address Translation Unit operations */
+
+int mv88e6xxx_g1_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid,
+			     struct mv88e6xxx_atu_entry *entry)
+{
+	int err;
+
+	err = mv88e6xxx_g1_atu_op_wait(chip);
+	if (err)
+		return err;
+
+	/* Write the MAC address to iterate from only once */
+	if (entry->state == GLOBAL_ATU_DATA_STATE_UNUSED) {
+		err = mv88e6xxx_g1_atu_mac_write(chip, entry);
+		if (err)
+			return err;
+	}
+
+	err = mv88e6xxx_g1_atu_op(chip, fid, GLOBAL_ATU_OP_GET_NEXT_DB);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_g1_atu_data_read(chip, entry);
+	if (err)
+		return err;
+
+	return mv88e6xxx_g1_atu_mac_read(chip, entry);
+}
+
+int mv88e6xxx_g1_atu_loadpurge(struct mv88e6xxx_chip *chip, u16 fid,
+			       struct mv88e6xxx_atu_entry *entry)
+{
+	int err;
+
+	err = mv88e6xxx_g1_atu_op_wait(chip);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_g1_atu_mac_write(chip, entry);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_g1_atu_data_write(chip, entry);
+	if (err)
+		return err;
+
+	return mv88e6xxx_g1_atu_op(chip, fid, GLOBAL_ATU_OP_LOAD_DB);
+}
+
+static int mv88e6xxx_g1_atu_flushmove(struct mv88e6xxx_chip *chip, u16 fid,
+				      struct mv88e6xxx_atu_entry *entry,
+				      bool all)
+{
+	u16 op;
+	int err;
+
+	err = mv88e6xxx_g1_atu_op_wait(chip);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_g1_atu_data_write(chip, entry);
+	if (err)
+		return err;
+
+	/* Flush/Move all or non-static entries from all or a given database */
+	if (all && fid)
+		op = GLOBAL_ATU_OP_FLUSH_MOVE_ALL_DB;
+	else if (fid)
+		op = GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC_DB;
+	else if (all)
+		op = GLOBAL_ATU_OP_FLUSH_MOVE_ALL;
+	else
+		op = GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC;
+
+	return mv88e6xxx_g1_atu_op(chip, fid, op);
+}
+
+int mv88e6xxx_g1_atu_flush(struct mv88e6xxx_chip *chip, u16 fid, bool all)
+{
+	struct mv88e6xxx_atu_entry entry = {
+		.state = 0, /* Null EntryState means Flush */
+	};
+
+	return mv88e6xxx_g1_atu_flushmove(chip, fid, &entry, all);
+}
+
+static int mv88e6xxx_g1_atu_move(struct mv88e6xxx_chip *chip, u16 fid,
+				 int from_port, int to_port, bool all)
+{
+	struct mv88e6xxx_atu_entry entry = { 0 };
+	unsigned long mask;
+	int shift;
+
+	if (!chip->info->atu_move_port_mask)
+		return -EOPNOTSUPP;
+
+	mask = chip->info->atu_move_port_mask;
+	shift = bitmap_weight(&mask, 16);
+
+	entry.state = 0xf, /* Full EntryState means Move */
+	entry.portvec = from_port & mask;
+	entry.portvec |= (to_port & mask) << shift;
+
+	return mv88e6xxx_g1_atu_flushmove(chip, fid, &entry, all);
+}
+
+int mv88e6xxx_g1_atu_remove(struct mv88e6xxx_chip *chip, u16 fid, int port,
+			    bool all)
+{
+	int from_port = port;
+	int to_port = chip->info->atu_move_port_mask;
+
+	return mv88e6xxx_g1_atu_move(chip, fid, from_port, to_port, all);
+}
diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c
index 8f15bc7b1f5f..7c6bc33a9516 100644
--- a/drivers/net/dsa/mv88e6xxx/global2.c
+++ b/drivers/net/dsa/mv88e6xxx/global2.c
@@ -4,7 +4,8 @@
  *
  * Copyright (c) 2008 Marvell Semiconductor
  *
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -12,6 +13,7 @@
  * (at your option) any later version.
  */
 
+#include <linux/interrupt.h>
 #include <linux/irqdomain.h>
 #include "mv88e6xxx.h"
 #include "global2.h"
@@ -170,6 +172,50 @@ static int mv88e6xxx_g2_clear_irl(struct mv88e6xxx_chip *chip)
 	return err;
 }
 
+/* Offset 0x0B: Cross-chip Port VLAN (Addr) Register
+ * Offset 0x0C: Cross-chip Port VLAN Data Register
+ */
+
+static int mv88e6xxx_g2_pvt_op_wait(struct mv88e6xxx_chip *chip)
+{
+	return mv88e6xxx_g2_wait(chip, GLOBAL2_PVT_ADDR, GLOBAL2_PVT_ADDR_BUSY);
+}
+
+static int mv88e6xxx_g2_pvt_op(struct mv88e6xxx_chip *chip, int src_dev,
+			       int src_port, u16 op)
+{
+	int err;
+
+	/* 9-bit Cross-chip PVT pointer: with GLOBAL2_MISC_5_BIT_PORT cleared,
+	 * source device is 5-bit, source port is 4-bit.
+	 */
+	op |= (src_dev & 0x1f) << 4;
+	op |= (src_port & 0xf);
+
+	err = mv88e6xxx_g2_write(chip, GLOBAL2_PVT_ADDR, op);
+	if (err)
+		return err;
+
+	return mv88e6xxx_g2_pvt_op_wait(chip);
+}
+
+int mv88e6xxx_g2_pvt_write(struct mv88e6xxx_chip *chip, int src_dev,
+			   int src_port, u16 data)
+{
+	int err;
+
+	err = mv88e6xxx_g2_pvt_op_wait(chip);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_g2_write(chip, GLOBAL2_PVT_DATA, data);
+	if (err)
+		return err;
+
+	return mv88e6xxx_g2_pvt_op(chip, src_dev, src_port,
+				   GLOBAL2_PVT_ADDR_OP_WRITE_PVLAN);
+}
+
 /* Offset 0x0D: Switch MAC/WoL/WoF register */
 
 static int mv88e6xxx_g2_switch_mac_write(struct mv88e6xxx_chip *chip,
@@ -782,6 +828,31 @@ static int mv88e6xxx_g2_watchdog_setup(struct mv88e6xxx_chip *chip)
 	return err;
 }
 
+/* Offset 0x1D: Misc Register */
+
+static int mv88e6xxx_g2_misc_5_bit_port(struct mv88e6xxx_chip *chip,
+					bool port_5_bit)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_g2_read(chip, GLOBAL2_MISC, &val);
+	if (err)
+		return err;
+
+	if (port_5_bit)
+		val |= GLOBAL2_MISC_5_BIT_PORT;
+	else
+		val &= ~GLOBAL2_MISC_5_BIT_PORT;
+
+	return mv88e6xxx_g2_write(chip, GLOBAL2_MISC, val);
+}
+
+int mv88e6xxx_g2_misc_4_bit_port(struct mv88e6xxx_chip *chip)
+{
+	return mv88e6xxx_g2_misc_5_bit_port(chip, false);
+}
+
 static void mv88e6xxx_g2_irq_mask(struct irq_data *d)
 {
 	struct mv88e6xxx_chip *chip = irq_data_get_irq_chip_data(d);
@@ -964,14 +1035,6 @@ int mv88e6xxx_g2_setup(struct mv88e6xxx_chip *chip)
 				return err;
 	}
 
-	if (mv88e6xxx_has(chip, MV88E6XXX_FLAGS_PVT)) {
-		/* Initialize Cross-chip Port VLAN Table to reset defaults */
-		err = mv88e6xxx_g2_write(chip, GLOBAL2_PVT_ADDR,
-					 GLOBAL2_PVT_ADDR_OP_INIT_ONES);
-		if (err)
-			return err;
-	}
-
 	if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_G2_POT)) {
 		/* Clear the priority override table. */
 		err = mv88e6xxx_g2_clear_pot(chip);
diff --git a/drivers/net/dsa/mv88e6xxx/global2.h b/drivers/net/dsa/mv88e6xxx/global2.h
index a8b2f9486a4a..96046bb12ca1 100644
--- a/drivers/net/dsa/mv88e6xxx/global2.h
+++ b/drivers/net/dsa/mv88e6xxx/global2.h
@@ -3,7 +3,8 @@
  *
  * Copyright (c) 2008 Marvell Semiconductor
  *
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -41,6 +42,10 @@ int mv88e6xxx_g2_get_eeprom16(struct mv88e6xxx_chip *chip,
 int mv88e6xxx_g2_set_eeprom16(struct mv88e6xxx_chip *chip,
 			      struct ethtool_eeprom *eeprom, u8 *data);
 
+int mv88e6xxx_g2_pvt_write(struct mv88e6xxx_chip *chip, int src_dev,
+			   int src_port, u16 data);
+int mv88e6xxx_g2_misc_4_bit_port(struct mv88e6xxx_chip *chip);
+
 int mv88e6xxx_g2_setup(struct mv88e6xxx_chip *chip);
 int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip);
 void mv88e6xxx_g2_irq_free(struct mv88e6xxx_chip *chip);
@@ -109,6 +114,17 @@ static inline int mv88e6xxx_g2_set_eeprom16(struct mv88e6xxx_chip *chip,
 	return -EOPNOTSUPP;
 }
 
+int mv88e6xxx_g2_pvt_write(struct mv88e6xxx_chip *chip, int src_dev,
+			   int src_port, u16 data)
+{
+	return -EOPNOTSUPP;
+}
+
+int mv88e6xxx_g2_misc_4_bit_port(struct mv88e6xxx_chip *chip)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int mv88e6xxx_g2_setup(struct mv88e6xxx_chip *chip)
 {
 	return -EOPNOTSUPP;
diff --git a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h
index 6033f2f6260a..c8f54986996b 100644
--- a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h
+++ b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h
@@ -16,6 +16,7 @@
 #include <linux/irq.h>
 #include <linux/gpio/consumer.h>
 #include <linux/phy.h>
+#include <net/dsa.h>
 
 #ifndef UINT64_MAX
 #define UINT64_MAX		(u64)(~((u64)0))
@@ -132,18 +133,19 @@
 #define PORT_CONTROL_TAG_IF_BOTH	BIT(6)
 #define PORT_CONTROL_USE_IP		BIT(5)
 #define PORT_CONTROL_USE_TAG		BIT(4)
-#define PORT_CONTROL_FORWARD_UNKNOWN_MC	BIT(3)
 #define PORT_CONTROL_FORWARD_UNKNOWN	BIT(2)
-#define PORT_CONTROL_NOT_EGRESS_UNKNOWN_DA		(0x0 << 2)
-#define PORT_CONTROL_NOT_EGRESS_UNKNOWN_MULTICAST_DA	(0x1 << 2)
-#define PORT_CONTROL_NOT_EGRESS_UNKNOWN_UNITCAST_DA	(0x2 << 2)
-#define PORT_CONTROL_EGRESS_ALL_UNKNOWN_DA		(0x3 << 2)
+#define PORT_CONTROL_EGRESS_FLOODS_MASK			(0x3 << 2)
+#define PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_DA	(0x0 << 2)
+#define PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_MC_DA	(0x1 << 2)
+#define PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_UC_DA	(0x2 << 2)
+#define PORT_CONTROL_EGRESS_FLOODS_ALL_UNKNOWN_DA	(0x3 << 2)
 #define PORT_CONTROL_STATE_MASK		0x03
 #define PORT_CONTROL_STATE_DISABLED	0x00
 #define PORT_CONTROL_STATE_BLOCKING	0x01
 #define PORT_CONTROL_STATE_LEARNING	0x02
 #define PORT_CONTROL_STATE_FORWARDING	0x03
 #define PORT_CONTROL_1		0x05
+#define PORT_CONTROL_1_MESSAGE_PORT	BIT(15)
 #define PORT_CONTROL_1_FID_11_4_MASK	(0xff << 0)
 #define PORT_BASE_VLAN		0x06
 #define PORT_BASE_VLAN_FID_3_0_MASK	(0xf << 12)
@@ -166,7 +168,6 @@
 #define PORT_CONTROL_2_DISCARD_UNTAGGED	BIT(8)
 #define PORT_CONTROL_2_MAP_DA		BIT(7)
 #define PORT_CONTROL_2_DEFAULT_FORWARD	BIT(6)
-#define PORT_CONTROL_2_FORWARD_UNKNOWN	BIT(6)
 #define PORT_CONTROL_2_EGRESS_MONITOR	BIT(5)
 #define PORT_CONTROL_2_INGRESS_MONITOR	BIT(4)
 #define PORT_CONTROL_2_UPSTREAM_MASK	0x0f
@@ -181,6 +182,7 @@
 #define PORT_ATU_CONTROL	0x0c
 #define PORT_PRI_OVERRIDE	0x0d
 #define PORT_ETH_TYPE		0x0f
+#define PORT_ETH_TYPE_DEFAULT	0x9100
 #define PORT_IN_DISCARD_LO	0x10
 #define PORT_IN_DISCARD_HI	0x11
 #define PORT_IN_FILTERED	0x12
@@ -437,9 +439,14 @@
 #define GLOBAL2_WDOG_FORCE_IRQ			BIT(0)
 #define GLOBAL2_QOS_WEIGHT	0x1c
 #define GLOBAL2_MISC		0x1d
+#define GLOBAL2_MISC_5_BIT_PORT	BIT(14)
 
 #define MV88E6XXX_N_FID		4096
 
+/* PVT limits for 4-bit port and 5-bit switch */
+#define MV88E6XXX_MAX_PVT_SWITCHES	32
+#define MV88E6XXX_MAX_PVT_PORTS		16
+
 enum mv88e6xxx_frame_mode {
 	MV88E6XXX_FRAME_MODE_NORMAL,
 	MV88E6XXX_FRAME_MODE_DSA,
@@ -525,8 +532,6 @@ enum mv88e6xxx_cap {
 	MV88E6XXX_CAP_G2_MGMT_EN_0X,	/* (0x03) MGMT Enable Register 0x */
 	MV88E6XXX_CAP_G2_IRL_CMD,	/* (0x09) Ingress Rate Command */
 	MV88E6XXX_CAP_G2_IRL_DATA,	/* (0x0a) Ingress Rate Data */
-	MV88E6XXX_CAP_G2_PVT_ADDR,	/* (0x0b) Cross Chip Port VLAN Addr */
-	MV88E6XXX_CAP_G2_PVT_DATA,	/* (0x0c) Cross Chip Port VLAN Data */
 	MV88E6XXX_CAP_G2_POT,		/* (0x0f) Priority Override Table */
 
 	/* Per VLAN Spanning Tree Unit (STU).
@@ -551,7 +556,6 @@ enum mv88e6xxx_cap {
 
 #define MV88E6XXX_FLAG_SERDES		BIT_ULL(MV88E6XXX_CAP_SERDES)
 
-#define MV88E6XXX_FLAG_G1_ATU_FID	BIT_ULL(MV88E6XXX_CAP_G1_ATU_FID)
 #define MV88E6XXX_FLAG_G1_VTU_FID	BIT_ULL(MV88E6XXX_CAP_G1_VTU_FID)
 
 #define MV88E6XXX_FLAG_GLOBAL2		BIT_ULL(MV88E6XXX_CAP_GLOBAL2)
@@ -560,8 +564,6 @@ enum mv88e6xxx_cap {
 #define MV88E6XXX_FLAG_G2_MGMT_EN_0X	BIT_ULL(MV88E6XXX_CAP_G2_MGMT_EN_0X)
 #define MV88E6XXX_FLAG_G2_IRL_CMD	BIT_ULL(MV88E6XXX_CAP_G2_IRL_CMD)
 #define MV88E6XXX_FLAG_G2_IRL_DATA	BIT_ULL(MV88E6XXX_CAP_G2_IRL_DATA)
-#define MV88E6XXX_FLAG_G2_PVT_ADDR	BIT_ULL(MV88E6XXX_CAP_G2_PVT_ADDR)
-#define MV88E6XXX_FLAG_G2_PVT_DATA	BIT_ULL(MV88E6XXX_CAP_G2_PVT_DATA)
 #define MV88E6XXX_FLAG_G2_POT		BIT_ULL(MV88E6XXX_CAP_G2_POT)
 
 #define MV88E6XXX_FLAG_STU		BIT_ULL(MV88E6XXX_CAP_STU)
@@ -577,11 +579,6 @@ enum mv88e6xxx_cap {
 	(MV88E6XXX_FLAG_SMI_CMD |	\
 	 MV88E6XXX_FLAG_SMI_DATA)
 
-/* Cross-chip Port VLAN Table */
-#define MV88E6XXX_FLAGS_PVT		\
-	(MV88E6XXX_FLAG_G2_PVT_ADDR |	\
-	 MV88E6XXX_FLAG_G2_PVT_DATA)
-
 /* Fiber/SERDES Registers at SMI address F, page 1 */
 #define MV88E6XXX_FLAGS_SERDES		\
 	(MV88E6XXX_FLAG_PHY_PAGE |	\
@@ -594,8 +591,7 @@ enum mv88e6xxx_cap {
 	 MV88E6XXX_FLAGS_MULTI_CHIP)
 
 #define MV88E6XXX_FLAGS_FAMILY_6097	\
-	(MV88E6XXX_FLAG_G1_ATU_FID |	\
-	 MV88E6XXX_FLAG_G1_VTU_FID |	\
+	(MV88E6XXX_FLAG_G1_VTU_FID |	\
 	 MV88E6XXX_FLAG_GLOBAL2 |	\
 	 MV88E6XXX_FLAG_G2_INT |        \
 	 MV88E6XXX_FLAG_G2_MGMT_EN_2X |	\
@@ -604,12 +600,10 @@ enum mv88e6xxx_cap {
 	 MV88E6XXX_FLAG_STU |		\
 	 MV88E6XXX_FLAG_VTU |		\
 	 MV88E6XXX_FLAGS_IRL |		\
-	 MV88E6XXX_FLAGS_MULTI_CHIP |	\
-	 MV88E6XXX_FLAGS_PVT)
+	 MV88E6XXX_FLAGS_MULTI_CHIP)
 
 #define MV88E6XXX_FLAGS_FAMILY_6165	\
-	(MV88E6XXX_FLAG_G1_ATU_FID |	\
-	 MV88E6XXX_FLAG_G1_VTU_FID |	\
+	(MV88E6XXX_FLAG_G1_VTU_FID |	\
 	 MV88E6XXX_FLAG_GLOBAL2 |	\
 	 MV88E6XXX_FLAG_G2_INT |	\
 	 MV88E6XXX_FLAG_G2_MGMT_EN_2X |	\
@@ -618,8 +612,7 @@ enum mv88e6xxx_cap {
 	 MV88E6XXX_FLAG_STU |		\
 	 MV88E6XXX_FLAG_VTU |		\
 	 MV88E6XXX_FLAGS_IRL |		\
-	 MV88E6XXX_FLAGS_MULTI_CHIP |	\
-	 MV88E6XXX_FLAGS_PVT)
+	 MV88E6XXX_FLAGS_MULTI_CHIP)
 
 #define MV88E6XXX_FLAGS_FAMILY_6185	\
 	(MV88E6XXX_FLAG_GLOBAL2 |	\
@@ -636,12 +629,10 @@ enum mv88e6xxx_cap {
 	 MV88E6XXX_FLAG_G2_POT |	\
 	 MV88E6XXX_FLAG_VTU |		\
 	 MV88E6XXX_FLAGS_IRL |		\
-	 MV88E6XXX_FLAGS_MULTI_CHIP |	\
-	 MV88E6XXX_FLAGS_PVT)
+	 MV88E6XXX_FLAGS_MULTI_CHIP)
 
 #define MV88E6XXX_FLAGS_FAMILY_6341	\
 	(MV88E6XXX_FLAG_EEE |		\
-	 MV88E6XXX_FLAG_G1_ATU_FID |	\
 	 MV88E6XXX_FLAG_G1_VTU_FID |	\
 	 MV88E6XXX_FLAG_GLOBAL2 |	\
 	 MV88E6XXX_FLAG_G2_INT |	\
@@ -650,12 +641,10 @@ enum mv88e6xxx_cap {
 	 MV88E6XXX_FLAG_VTU |		\
 	 MV88E6XXX_FLAGS_IRL |		\
 	 MV88E6XXX_FLAGS_MULTI_CHIP |	\
-	 MV88E6XXX_FLAGS_PVT |		\
 	 MV88E6XXX_FLAGS_SERDES)
 
 #define MV88E6XXX_FLAGS_FAMILY_6351	\
-	(MV88E6XXX_FLAG_G1_ATU_FID |	\
-	 MV88E6XXX_FLAG_G1_VTU_FID |	\
+	(MV88E6XXX_FLAG_G1_VTU_FID |	\
 	 MV88E6XXX_FLAG_GLOBAL2 |	\
 	 MV88E6XXX_FLAG_G2_INT |	\
 	 MV88E6XXX_FLAG_G2_MGMT_EN_2X |	\
@@ -664,12 +653,10 @@ enum mv88e6xxx_cap {
 	 MV88E6XXX_FLAG_STU |		\
 	 MV88E6XXX_FLAG_VTU |		\
 	 MV88E6XXX_FLAGS_IRL |		\
-	 MV88E6XXX_FLAGS_MULTI_CHIP |	\
-	 MV88E6XXX_FLAGS_PVT)
+	 MV88E6XXX_FLAGS_MULTI_CHIP)
 
 #define MV88E6XXX_FLAGS_FAMILY_6352	\
 	(MV88E6XXX_FLAG_EEE |		\
-	 MV88E6XXX_FLAG_G1_ATU_FID |	\
 	 MV88E6XXX_FLAG_G1_VTU_FID |	\
 	 MV88E6XXX_FLAG_GLOBAL2 |	\
 	 MV88E6XXX_FLAG_G2_INT |	\
@@ -680,7 +667,6 @@ enum mv88e6xxx_cap {
 	 MV88E6XXX_FLAG_VTU |		\
 	 MV88E6XXX_FLAGS_IRL |		\
 	 MV88E6XXX_FLAGS_MULTI_CHIP |	\
-	 MV88E6XXX_FLAGS_PVT |		\
 	 MV88E6XXX_FLAGS_SERDES)
 
 #define MV88E6XXX_FLAGS_FAMILY_6390	\
@@ -690,8 +676,7 @@ enum mv88e6xxx_cap {
 	 MV88E6XXX_FLAG_STU |		\
 	 MV88E6XXX_FLAG_VTU |		\
 	 MV88E6XXX_FLAGS_IRL |		\
-	 MV88E6XXX_FLAGS_MULTI_CHIP |	\
-	 MV88E6XXX_FLAGS_PVT)
+	 MV88E6XXX_FLAGS_MULTI_CHIP)
 
 struct mv88e6xxx_ops;
 
@@ -705,16 +690,21 @@ struct mv88e6xxx_info {
 	unsigned int global1_addr;
 	unsigned int age_time_coeff;
 	unsigned int g1_irqs;
+	bool pvt;
 	enum dsa_tag_protocol tag_protocol;
 	unsigned long long flags;
+
+	/* Mask for FromPort and ToPort value of PortVec used in ATU Move
+	 * operation. 0 means that the ATU Move operation is not supported.
+	 */
+	u8 atu_move_port_mask;
 	const struct mv88e6xxx_ops *ops;
 };
 
 struct mv88e6xxx_atu_entry {
-	u16	fid;
 	u8	state;
 	bool	trunk;
-	u16	portv_trunkid;
+	u16	portvec;
 	u8	mac[ETH_ALEN];
 };
 
@@ -864,14 +854,16 @@ struct mv88e6xxx_ops {
 
 	int (*port_set_frame_mode)(struct mv88e6xxx_chip *chip, int port,
 				   enum mv88e6xxx_frame_mode mode);
-	int (*port_set_egress_unknowns)(struct mv88e6xxx_chip *chip, int port,
-					bool on);
+	int (*port_set_egress_floods)(struct mv88e6xxx_chip *chip, int port,
+				      bool unicast, bool multicast);
 	int (*port_set_ether_type)(struct mv88e6xxx_chip *chip, int port,
 				   u16 etype);
 	int (*port_jumbo_config)(struct mv88e6xxx_chip *chip, int port);
 
 	int (*port_egress_rate_limiting)(struct mv88e6xxx_chip *chip, int port);
 	int (*port_pause_config)(struct mv88e6xxx_chip *chip, int port);
+	int (*port_disable_learn_limit)(struct mv88e6xxx_chip *chip, int port);
+	int (*port_disable_pri_override)(struct mv88e6xxx_chip *chip, int port);
 
 	/* CMODE control what PHY mode the MAC will use, eg. SGMII, RGMII, etc.
 	 * Some chips allow this to be configured on specific ports.
@@ -934,6 +926,11 @@ static inline bool mv88e6xxx_has(struct mv88e6xxx_chip *chip,
 	return (chip->info->flags & flags) == flags;
 }
 
+static inline bool mv88e6xxx_has_pvt(struct mv88e6xxx_chip *chip)
+{
+	return chip->info->pvt;
+}
+
 static inline unsigned int mv88e6xxx_num_databases(struct mv88e6xxx_chip *chip)
 {
 	return chip->info->num_databases;
@@ -944,6 +941,11 @@ static inline unsigned int mv88e6xxx_num_ports(struct mv88e6xxx_chip *chip)
 	return chip->info->num_ports;
 }
 
+static inline u16 mv88e6xxx_port_mask(struct mv88e6xxx_chip *chip)
+{
+	return GENMASK(mv88e6xxx_num_ports(chip) - 1, 0);
+}
+
 int mv88e6xxx_read(struct mv88e6xxx_chip *chip, int addr, int reg, u16 *val);
 int mv88e6xxx_write(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val);
 int mv88e6xxx_update(struct mv88e6xxx_chip *chip, int addr, int reg,
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index 8875784c4718..548a956637ee 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -3,7 +3,8 @@
  *
  * Copyright (c) 2008 Marvell Semiconductor
  *
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -497,8 +498,8 @@ int mv88e6351_port_set_frame_mode(struct mv88e6xxx_chip *chip, int port,
 	return mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg);
 }
 
-int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
-				       bool on)
+static int mv88e6185_port_set_forward_unknown(struct mv88e6xxx_chip *chip,
+					      int port, bool unicast)
 {
 	int err;
 	u16 reg;
@@ -507,7 +508,7 @@ int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
 	if (err)
 		return err;
 
-	if (on)
+	if (unicast)
 		reg |= PORT_CONTROL_FORWARD_UNKNOWN;
 	else
 		reg &= ~PORT_CONTROL_FORWARD_UNKNOWN;
@@ -515,8 +516,8 @@ int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
 	return mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg);
 }
 
-int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
-				       bool on)
+int mv88e6352_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port,
+				     bool unicast, bool multicast)
 {
 	int err;
 	u16 reg;
@@ -525,21 +526,45 @@ int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
 	if (err)
 		return err;
 
-	if (on)
-		reg |= PORT_CONTROL_EGRESS_ALL_UNKNOWN_DA;
+	reg &= ~PORT_CONTROL_EGRESS_FLOODS_MASK;
+
+	if (unicast && multicast)
+		reg |= PORT_CONTROL_EGRESS_FLOODS_ALL_UNKNOWN_DA;
+	else if (unicast)
+		reg |= PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_MC_DA;
+	else if (multicast)
+		reg |= PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_UC_DA;
 	else
-		reg &= ~PORT_CONTROL_EGRESS_ALL_UNKNOWN_DA;
+		reg |= PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_DA;
 
 	return mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg);
 }
 
 /* Offset 0x05: Port Control 1 */
 
+int mv88e6xxx_port_set_message_port(struct mv88e6xxx_chip *chip, int port,
+				    bool message_port)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_port_read(chip, port, PORT_CONTROL_1, &val);
+	if (err)
+		return err;
+
+	if (message_port)
+		val |= PORT_CONTROL_1_MESSAGE_PORT;
+	else
+		val &= ~PORT_CONTROL_1_MESSAGE_PORT;
+
+	return mv88e6xxx_port_write(chip, port, PORT_CONTROL_1, val);
+}
+
 /* Offset 0x06: Port Based VLAN Map */
 
 int mv88e6xxx_port_set_vlan_map(struct mv88e6xxx_chip *chip, int port, u16 map)
 {
-	const u16 mask = GENMASK(mv88e6xxx_num_ports(chip) - 1, 0);
+	const u16 mask = mv88e6xxx_port_mask(chip);
 	u16 reg;
 	int err;
 
@@ -672,8 +697,8 @@ static const char * const mv88e6xxx_port_8021q_mode_names[] = {
 	[PORT_CONTROL_2_8021Q_SECURE] = "Secure",
 };
 
-int mv88e6095_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
-				       bool on)
+static int mv88e6185_port_set_default_forward(struct mv88e6xxx_chip *chip,
+					      int port, bool multicast)
 {
 	int err;
 	u16 reg;
@@ -682,14 +707,26 @@ int mv88e6095_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
 	if (err)
 		return err;
 
-	if (on)
-		reg |= PORT_CONTROL_2_FORWARD_UNKNOWN;
+	if (multicast)
+		reg |= PORT_CONTROL_2_DEFAULT_FORWARD;
 	else
-		reg &= ~PORT_CONTROL_2_FORWARD_UNKNOWN;
+		reg &= ~PORT_CONTROL_2_DEFAULT_FORWARD;
 
 	return mv88e6xxx_port_write(chip, port, PORT_CONTROL_2, reg);
 }
 
+int mv88e6185_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port,
+				     bool unicast, bool multicast)
+{
+	int err;
+
+	err = mv88e6185_port_set_forward_unknown(chip, port, unicast);
+	if (err)
+		return err;
+
+	return mv88e6185_port_set_default_forward(chip, port, multicast);
+}
+
 int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port,
 				     int upstream_port)
 {
@@ -769,6 +806,20 @@ int mv88e6097_port_egress_rate_limiting(struct mv88e6xxx_chip *chip, int port)
 	return mv88e6xxx_port_write(chip, port, PORT_RATE_CONTROL, 0x0001);
 }
 
+/* Offset 0x0C: Port ATU Control */
+
+int mv88e6xxx_port_disable_learn_limit(struct mv88e6xxx_chip *chip, int port)
+{
+	return mv88e6xxx_port_write(chip, port, PORT_ATU_CONTROL, 0);
+}
+
+/* Offset 0x0D: (Priority) Override Register */
+
+int mv88e6xxx_port_disable_pri_override(struct mv88e6xxx_chip *chip, int port)
+{
+	return mv88e6xxx_port_write(chip, port, PORT_PRI_OVERRIDE, 0);
+}
+
 /* Offset 0x0f: Port Ether type */
 
 int mv88e6351_port_set_ether_type(struct mv88e6xxx_chip *chip, int port,
diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h
index c83cbb3f4491..86f40887b6d2 100644
--- a/drivers/net/dsa/mv88e6xxx/port.h
+++ b/drivers/net/dsa/mv88e6xxx/port.h
@@ -3,7 +3,8 @@
  *
  * Copyright (c) 2008 Marvell Semiconductor
  *
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -56,14 +57,14 @@ int mv88e6085_port_set_frame_mode(struct mv88e6xxx_chip *chip, int port,
 				  enum mv88e6xxx_frame_mode mode);
 int mv88e6351_port_set_frame_mode(struct mv88e6xxx_chip *chip, int port,
 				  enum mv88e6xxx_frame_mode mode);
-int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
-				       bool on);
-int mv88e6095_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
-				       bool on);
-int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
-				       bool on);
+int mv88e6185_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port,
+				     bool unicast, bool multicast);
+int mv88e6352_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port,
+				     bool unicast, bool multicast);
 int mv88e6351_port_set_ether_type(struct mv88e6xxx_chip *chip, int port,
 				  u16 etype);
+int mv88e6xxx_port_set_message_port(struct mv88e6xxx_chip *chip, int port,
+				    bool message_port);
 int mv88e6165_port_jumbo_config(struct mv88e6xxx_chip *chip, int port);
 int mv88e6095_port_egress_rate_limiting(struct mv88e6xxx_chip *chip, int port);
 int mv88e6097_port_egress_rate_limiting(struct mv88e6xxx_chip *chip, int port);
@@ -75,4 +76,8 @@ int mv88e6xxx_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode);
 int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port);
 int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port,
 				     int upstream_port);
+
+int mv88e6xxx_port_disable_learn_limit(struct mv88e6xxx_chip *chip, int port);
+int mv88e6xxx_port_disable_pri_override(struct mv88e6xxx_chip *chip, int port);
+
 #endif /* _MV88E6XXX_PORT_H */
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index 2c80611b94ae..149244aac20a 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -35,6 +35,7 @@
 #include <linux/init.h>
 #include <linux/moduleparam.h>
 #include <linux/rtnetlink.h>
+#include <linux/net_tstamp.h>
 #include <net/rtnetlink.h>
 #include <linux/u64_stats_sync.h>
 
@@ -125,6 +126,7 @@ static netdev_tx_t dummy_xmit(struct sk_buff *skb, struct net_device *dev)
 	dstats->tx_bytes += skb->len;
 	u64_stats_update_end(&dstats->syncp);
 
+	skb_tx_timestamp(skb);
 	dev_kfree_skb(skb);
 	return NETDEV_TX_OK;
 }
@@ -304,8 +306,21 @@ static void dummy_get_drvinfo(struct net_device *dev,
 	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
 }
 
+static int dummy_get_ts_info(struct net_device *dev,
+			      struct ethtool_ts_info *ts_info)
+{
+	ts_info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+				   SOF_TIMESTAMPING_RX_SOFTWARE |
+				   SOF_TIMESTAMPING_SOFTWARE;
+
+	ts_info->phc_index = -1;
+
+	return 0;
+};
+
 static const struct ethtool_ops dummy_ethtool_ops = {
 	.get_drvinfo            = dummy_get_drvinfo,
+	.get_ts_info		= dummy_get_ts_info,
 };
 
 static void dummy_free_netdev(struct net_device *dev)
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 8c08f9deef92..edae15ac0e98 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -180,5 +180,6 @@ source "drivers/net/ethernet/via/Kconfig"
 source "drivers/net/ethernet/wiznet/Kconfig"
 source "drivers/net/ethernet/xilinx/Kconfig"
 source "drivers/net/ethernet/xircom/Kconfig"
+source "drivers/net/ethernet/synopsys/Kconfig"
 
 endif # ETHERNET
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 26dce5bf2c18..bf7f4502cabc 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -91,3 +91,4 @@ obj-$(CONFIG_NET_VENDOR_VIA) += via/
 obj-$(CONFIG_NET_VENDOR_WIZNET) += wiznet/
 obj-$(CONFIG_NET_VENDOR_XILINX) += xilinx/
 obj-$(CONFIG_NET_VENDOR_XIRCOM) += xircom/
+obj-$(CONFIG_NET_VENDOR_SYNOPSYS) += synopsys/
diff --git a/drivers/net/ethernet/adi/bfin_mac.h b/drivers/net/ethernet/adi/bfin_mac.h
index 8c3b56198e4b..4ad5b9be3f84 100644
--- a/drivers/net/ethernet/adi/bfin_mac.h
+++ b/drivers/net/ethernet/adi/bfin_mac.h
@@ -68,13 +68,6 @@ struct net_dma_desc_tx {
 };
 
 struct bfin_mac_local {
-	/*
-	 * these are things that the kernel wants me to keep, so users
-	 * can find out semi-useless statistics of how well the card is
-	 * performing
-	 */
-	struct net_device_stats stats;
-
 	spinlock_t lock;
 
 	int wol;		/* Wake On Lan */
diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c
index 9f7422ada704..d8e133ced7b8 100644
--- a/drivers/net/ethernet/aeroflex/greth.c
+++ b/drivers/net/ethernet/aeroflex/greth.c
@@ -34,6 +34,7 @@
 #include <linux/crc32.h>
 #include <linux/mii.h>
 #include <linux/of_device.h>
+#include <linux/of_net.h>
 #include <linux/of_platform.h>
 #include <linux/slab.h>
 #include <asm/cacheflush.h>
@@ -1454,11 +1455,10 @@ static int greth_of_probe(struct platform_device *ofdev)
 			break;
 	}
 	if (i == 6) {
-		const unsigned char *addr;
-		int len;
-		addr = of_get_property(ofdev->dev.of_node, "local-mac-address",
-					&len);
-		if (addr != NULL && len == 6) {
+		const u8 *addr;
+
+		addr = of_get_mac_address(ofdev->dev.of_node);
+		if (addr) {
 			for (i = 0; i < 6; i++)
 				macaddr[i] = (unsigned int) addr[i];
 		} else {
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index a713abd9d03e..c772420fa41c 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -118,6 +118,7 @@
 #include <linux/spinlock.h>
 #include <linux/tcp.h>
 #include <linux/if_vlan.h>
+#include <linux/interrupt.h>
 #include <net/busy_poll.h>
 #include <linux/clk.h>
 #include <linux/if_ether.h>
@@ -1854,7 +1855,8 @@ static int xgbe_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
 	if (tc_to_netdev->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
-	tc = tc_to_netdev->tc;
+	tc_to_netdev->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+	tc = tc_to_netdev->mqprio->num_tc;
 
 	if (tc > pdata->hw_feat.tc_cnt)
 		return -EINVAL;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
index 0c7088a426e9..417bdb5982a9 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
@@ -115,6 +115,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/interrupt.h>
 #include <linux/kmod.h>
 #include <linux/delay.h>
 #include <linux/completion.h>
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 4c5b90eea4af..b672d9249539 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -114,6 +114,7 @@
  *     THE POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/kmod.h>
 #include <linux/mdio.h>
diff --git a/drivers/net/ethernet/apm/Kconfig b/drivers/net/ethernet/apm/Kconfig
index ec63d706d464..59efe5b145dd 100644
--- a/drivers/net/ethernet/apm/Kconfig
+++ b/drivers/net/ethernet/apm/Kconfig
@@ -1 +1,2 @@
 source "drivers/net/ethernet/apm/xgene/Kconfig"
+source "drivers/net/ethernet/apm/xgene-v2/Kconfig"
diff --git a/drivers/net/ethernet/apm/Makefile b/drivers/net/ethernet/apm/Makefile
index 65ce32ad1b2c..946b2a4c882d 100644
--- a/drivers/net/ethernet/apm/Makefile
+++ b/drivers/net/ethernet/apm/Makefile
@@ -3,3 +3,4 @@
 #
 
 obj-$(CONFIG_NET_XGENE) += xgene/
+obj-$(CONFIG_NET_XGENE_V2) += xgene-v2/
diff --git a/drivers/net/ethernet/apm/xgene-v2/Kconfig b/drivers/net/ethernet/apm/xgene-v2/Kconfig
new file mode 100644
index 000000000000..1205861b6318
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/Kconfig
@@ -0,0 +1,11 @@
+config NET_XGENE_V2
+	tristate "APM X-Gene SoC Ethernet-v2 Driver"
+	depends on HAS_DMA
+	depends on ARCH_XGENE || COMPILE_TEST
+	help
+	  This is the Ethernet driver for the on-chip ethernet interface
+	  which uses a linked list of DMA descriptor architecture (v2) for
+	  APM X-Gene SoCs.
+
+	  To compile this driver as a module, choose M here. This module will
+	  be called xgene-enet-v2.
diff --git a/drivers/net/ethernet/apm/xgene-v2/Makefile b/drivers/net/ethernet/apm/xgene-v2/Makefile
new file mode 100644
index 000000000000..f16a2b3dde8b
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/Makefile
@@ -0,0 +1,6 @@
+#
+# Makefile for APM X-Gene Ethernet v2 driver
+#
+
+xgene-enet-v2-objs := main.o mac.o enet.o ring.o mdio.o ethtool.o
+obj-$(CONFIG_NET_XGENE_V2) += xgene-enet-v2.o
diff --git a/drivers/net/ethernet/apm/xgene-v2/enet.c b/drivers/net/ethernet/apm/xgene-v2/enet.c
new file mode 100644
index 000000000000..5998da014923
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/enet.c
@@ -0,0 +1,83 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+void xge_wr_csr(struct xge_pdata *pdata, u32 offset, u32 val)
+{
+	void __iomem *addr = pdata->resources.base_addr + offset;
+
+	iowrite32(val, addr);
+}
+
+u32 xge_rd_csr(struct xge_pdata *pdata, u32 offset)
+{
+	void __iomem *addr = pdata->resources.base_addr + offset;
+
+	return ioread32(addr);
+}
+
+int xge_port_reset(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	u32 data, wait = 10;
+
+	xge_wr_csr(pdata, ENET_CLKEN, 0x3);
+	xge_wr_csr(pdata, ENET_SRST, 0xf);
+	xge_wr_csr(pdata, ENET_SRST, 0);
+	xge_wr_csr(pdata, CFG_MEM_RAM_SHUTDOWN, 1);
+	xge_wr_csr(pdata, CFG_MEM_RAM_SHUTDOWN, 0);
+
+	do {
+		usleep_range(100, 110);
+		data = xge_rd_csr(pdata, BLOCK_MEM_RDY);
+	} while (data != MEM_RDY && wait--);
+
+	if (data != MEM_RDY) {
+		dev_err(dev, "ECC init failed: %x\n", data);
+		return -ETIMEDOUT;
+	}
+
+	xge_wr_csr(pdata, ENET_SHIM, DEVM_ARAUX_COH | DEVM_AWAUX_COH);
+
+	return 0;
+}
+
+static void xge_traffic_resume(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+
+	xge_wr_csr(pdata, CFG_FORCE_LINK_STATUS_EN, 1);
+	xge_wr_csr(pdata, FORCE_LINK_STATUS, 1);
+
+	xge_wr_csr(pdata, CFG_LINK_AGGR_RESUME, 1);
+	xge_wr_csr(pdata, RX_DV_GATE_REG, 1);
+}
+
+void xge_port_init(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+
+	pdata->phy_speed = SPEED_1000;
+	xge_mac_init(pdata);
+	xge_traffic_resume(ndev);
+}
diff --git a/drivers/net/ethernet/apm/xgene-v2/enet.h b/drivers/net/ethernet/apm/xgene-v2/enet.h
new file mode 100644
index 000000000000..3fd36dc66a23
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/enet.h
@@ -0,0 +1,45 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __XGENE_ENET_V2_ENET_H__
+#define __XGENE_ENET_V2_ENET_H__
+
+#define ENET_CLKEN		0xc008
+#define ENET_SRST		0xc000
+#define ENET_SHIM		0xc010
+#define CFG_MEM_RAM_SHUTDOWN	0xd070
+#define BLOCK_MEM_RDY		0xd074
+
+#define MEM_RDY			0xffffffff
+#define DEVM_ARAUX_COH		BIT(19)
+#define DEVM_AWAUX_COH		BIT(3)
+
+#define CFG_FORCE_LINK_STATUS_EN	0x229c
+#define FORCE_LINK_STATUS		0x22a0
+#define CFG_LINK_AGGR_RESUME		0x27c8
+#define RX_DV_GATE_REG			0x2dfc
+
+void xge_wr_csr(struct xge_pdata *pdata, u32 offset, u32 val);
+u32 xge_rd_csr(struct xge_pdata *pdata, u32 offset);
+int xge_port_reset(struct net_device *ndev);
+void xge_port_init(struct net_device *ndev);
+
+#endif  /* __XGENE_ENET_V2_ENET__H__ */
diff --git a/drivers/net/ethernet/apm/xgene-v2/ethtool.c b/drivers/net/ethernet/apm/xgene-v2/ethtool.c
new file mode 100644
index 000000000000..0c426f55ffdb
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/ethtool.c
@@ -0,0 +1,121 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+struct xge_gstrings_stats {
+	char name[ETH_GSTRING_LEN];
+	int offset;
+};
+
+#define XGE_STAT(m)		{ #m, offsetof(struct xge_pdata, stats.m) }
+
+static const struct xge_gstrings_stats gstrings_stats[] = {
+	XGE_STAT(rx_packets),
+	XGE_STAT(tx_packets),
+	XGE_STAT(rx_bytes),
+	XGE_STAT(tx_bytes),
+	XGE_STAT(rx_errors)
+};
+
+#define XGE_STATS_LEN		ARRAY_SIZE(gstrings_stats)
+
+static void xge_get_drvinfo(struct net_device *ndev,
+			    struct ethtool_drvinfo *info)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct platform_device *pdev = pdata->pdev;
+
+	strcpy(info->driver, "xgene-enet-v2");
+	strcpy(info->version, XGENE_ENET_V2_VERSION);
+	snprintf(info->fw_version, ETHTOOL_FWVERS_LEN, "N/A");
+	sprintf(info->bus_info, "%s", pdev->name);
+}
+
+static void xge_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
+{
+	u8 *p = data;
+	int i;
+
+	if (stringset != ETH_SS_STATS)
+		return;
+
+	for (i = 0; i < XGE_STATS_LEN; i++) {
+		memcpy(p, gstrings_stats[i].name, ETH_GSTRING_LEN);
+		p += ETH_GSTRING_LEN;
+	}
+}
+
+static int xge_get_sset_count(struct net_device *ndev, int sset)
+{
+	if (sset != ETH_SS_STATS)
+		return -EINVAL;
+
+	return XGE_STATS_LEN;
+}
+
+static void xge_get_ethtool_stats(struct net_device *ndev,
+				  struct ethtool_stats *dummy,
+				  u64 *data)
+{
+	void *pdata = netdev_priv(ndev);
+	int i;
+
+	for (i = 0; i < XGE_STATS_LEN; i++)
+		*data++ = *(u64 *)(pdata + gstrings_stats[i].offset);
+}
+
+static int xge_get_link_ksettings(struct net_device *ndev,
+				  struct ethtool_link_ksettings *cmd)
+{
+	struct phy_device *phydev = ndev->phydev;
+
+	if (!phydev)
+		return -ENODEV;
+
+	return phy_ethtool_ksettings_get(phydev, cmd);
+}
+
+static int xge_set_link_ksettings(struct net_device *ndev,
+				  const struct ethtool_link_ksettings *cmd)
+{
+	struct phy_device *phydev = ndev->phydev;
+
+	if (!phydev)
+		return -ENODEV;
+
+	return phy_ethtool_ksettings_set(phydev, cmd);
+}
+
+static const struct ethtool_ops xge_ethtool_ops = {
+	.get_drvinfo = xge_get_drvinfo,
+	.get_link = ethtool_op_get_link,
+	.get_strings = xge_get_strings,
+	.get_sset_count = xge_get_sset_count,
+	.get_ethtool_stats = xge_get_ethtool_stats,
+	.get_link_ksettings = xge_get_link_ksettings,
+	.set_link_ksettings = xge_set_link_ksettings,
+};
+
+void xge_set_ethtool_ops(struct net_device *ndev)
+{
+	ndev->ethtool_ops = &xge_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.c b/drivers/net/ethernet/apm/xgene-v2/mac.c
new file mode 100644
index 000000000000..ee431e397e57
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/mac.c
@@ -0,0 +1,116 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+void xge_mac_reset(struct xge_pdata *pdata)
+{
+	xge_wr_csr(pdata, MAC_CONFIG_1, SOFT_RESET);
+	xge_wr_csr(pdata, MAC_CONFIG_1, 0);
+}
+
+void xge_mac_set_speed(struct xge_pdata *pdata)
+{
+	u32 icm0, icm2, ecm0, mc2;
+	u32 intf_ctrl, rgmii;
+
+	icm0 = xge_rd_csr(pdata, ICM_CONFIG0_REG_0);
+	icm2 = xge_rd_csr(pdata, ICM_CONFIG2_REG_0);
+	ecm0 = xge_rd_csr(pdata, ECM_CONFIG0_REG_0);
+	rgmii = xge_rd_csr(pdata, RGMII_REG_0);
+	mc2 = xge_rd_csr(pdata, MAC_CONFIG_2);
+	intf_ctrl = xge_rd_csr(pdata, INTERFACE_CONTROL);
+	icm2 |= CFG_WAITASYNCRD_EN;
+
+	switch (pdata->phy_speed) {
+	case SPEED_10:
+		SET_REG_BITS(&mc2, INTF_MODE, 1);
+		SET_REG_BITS(&intf_ctrl, HD_MODE, 0);
+		SET_REG_BITS(&icm0, CFG_MACMODE, 0);
+		SET_REG_BITS(&icm2, CFG_WAITASYNCRD, 500);
+		SET_REG_BIT(&rgmii, CFG_SPEED_125, 0);
+		break;
+	case SPEED_100:
+		SET_REG_BITS(&mc2, INTF_MODE, 1);
+		SET_REG_BITS(&intf_ctrl, HD_MODE, 1);
+		SET_REG_BITS(&icm0, CFG_MACMODE, 1);
+		SET_REG_BITS(&icm2, CFG_WAITASYNCRD, 80);
+		SET_REG_BIT(&rgmii, CFG_SPEED_125, 0);
+		break;
+	default:
+		SET_REG_BITS(&mc2, INTF_MODE, 2);
+		SET_REG_BITS(&intf_ctrl, HD_MODE, 2);
+		SET_REG_BITS(&icm0, CFG_MACMODE, 2);
+		SET_REG_BITS(&icm2, CFG_WAITASYNCRD, 16);
+		SET_REG_BIT(&rgmii, CFG_SPEED_125, 1);
+		break;
+	}
+
+	mc2 |= FULL_DUPLEX | CRC_EN | PAD_CRC;
+	SET_REG_BITS(&ecm0, CFG_WFIFOFULLTHR, 0x32);
+
+	xge_wr_csr(pdata, MAC_CONFIG_2, mc2);
+	xge_wr_csr(pdata, INTERFACE_CONTROL, intf_ctrl);
+	xge_wr_csr(pdata, RGMII_REG_0, rgmii);
+	xge_wr_csr(pdata, ICM_CONFIG0_REG_0, icm0);
+	xge_wr_csr(pdata, ICM_CONFIG2_REG_0, icm2);
+	xge_wr_csr(pdata, ECM_CONFIG0_REG_0, ecm0);
+}
+
+void xge_mac_set_station_addr(struct xge_pdata *pdata)
+{
+	u8 *dev_addr = pdata->ndev->dev_addr;
+	u32 addr0, addr1;
+
+	addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) |
+		(dev_addr[1] << 8) | dev_addr[0];
+	addr1 = (dev_addr[5] << 24) | (dev_addr[4] << 16);
+
+	xge_wr_csr(pdata, STATION_ADDR0, addr0);
+	xge_wr_csr(pdata, STATION_ADDR1, addr1);
+}
+
+void xge_mac_init(struct xge_pdata *pdata)
+{
+	xge_mac_reset(pdata);
+	xge_mac_set_speed(pdata);
+	xge_mac_set_station_addr(pdata);
+}
+
+void xge_mac_enable(struct xge_pdata *pdata)
+{
+	u32 data;
+
+	data = xge_rd_csr(pdata, MAC_CONFIG_1);
+	data |= TX_EN | RX_EN;
+	xge_wr_csr(pdata, MAC_CONFIG_1, data);
+
+	data = xge_rd_csr(pdata, MAC_CONFIG_1);
+}
+
+void xge_mac_disable(struct xge_pdata *pdata)
+{
+	u32 data;
+
+	data = xge_rd_csr(pdata, MAC_CONFIG_1);
+	data &= ~(TX_EN | RX_EN);
+	xge_wr_csr(pdata, MAC_CONFIG_1, data);
+}
diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.h b/drivers/net/ethernet/apm/xgene-v2/mac.h
new file mode 100644
index 000000000000..18a9c9d8a5e5
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/mac.h
@@ -0,0 +1,110 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __XGENE_ENET_V2_MAC_H__
+#define __XGENE_ENET_V2_MAC_H__
+
+/* Register offsets */
+#define MAC_CONFIG_1		0xa000
+#define MAC_CONFIG_2		0xa004
+#define MII_MGMT_CONFIG		0xa020
+#define MII_MGMT_COMMAND	0xa024
+#define MII_MGMT_ADDRESS	0xa028
+#define MII_MGMT_CONTROL	0xa02c
+#define MII_MGMT_STATUS		0xa030
+#define MII_MGMT_INDICATORS	0xa034
+#define INTERFACE_CONTROL	0xa038
+#define STATION_ADDR0		0xa040
+#define STATION_ADDR1		0xa044
+#define RBYT			0xa09c
+#define RPKT			0xa0a0
+#define RFCS			0xa0a4
+
+#define RGMII_REG_0		0x27e0
+#define ICM_CONFIG0_REG_0	0x2c00
+#define ICM_CONFIG2_REG_0	0x2c08
+#define ECM_CONFIG0_REG_0	0x2d00
+
+/* Register fields */
+#define SOFT_RESET		BIT(31)
+#define TX_EN			BIT(0)
+#define RX_EN			BIT(2)
+#define PAD_CRC			BIT(2)
+#define CRC_EN			BIT(1)
+#define FULL_DUPLEX		BIT(0)
+
+#define INTF_MODE_POS		8
+#define INTF_MODE_LEN		2
+#define HD_MODE_POS		25
+#define HD_MODE_LEN		2
+#define CFG_MACMODE_POS		18
+#define CFG_MACMODE_LEN		2
+#define CFG_WAITASYNCRD_POS	0
+#define CFG_WAITASYNCRD_LEN	16
+#define CFG_SPEED_125_POS	24
+#define CFG_WFIFOFULLTHR_POS	0
+#define CFG_WFIFOFULLTHR_LEN	7
+#define MGMT_CLOCK_SEL_POS	0
+#define MGMT_CLOCK_SEL_LEN	3
+#define PHY_ADDR_POS		8
+#define PHY_ADDR_LEN		5
+#define REG_ADDR_POS		0
+#define REG_ADDR_LEN		5
+#define MII_MGMT_BUSY		BIT(0)
+#define MII_READ_CYCLE		BIT(0)
+#define CFG_WAITASYNCRD_EN	BIT(16)
+
+static inline void xgene_set_reg_bits(u32 *var, int pos, int len, u32 val)
+{
+	u32 mask = GENMASK(pos + len, pos);
+
+	*var &= ~mask;
+	*var |= ((val << pos) & mask);
+}
+
+static inline u32 xgene_get_reg_bits(u32 var, int pos, int len)
+{
+	u32 mask = GENMASK(pos + len, pos);
+
+	return (var & mask) >> pos;
+}
+
+#define SET_REG_BITS(var, field, val)					\
+	xgene_set_reg_bits(var, field ## _POS, field ## _LEN, val)
+
+#define SET_REG_BIT(var, field, val)					\
+	xgene_set_reg_bits(var, field ## _POS, 1, val)
+
+#define GET_REG_BITS(var, field)					\
+	xgene_get_reg_bits(var, field ## _POS, field ## _LEN)
+
+#define GET_REG_BIT(var, field)		((var) & (field))
+
+struct xge_pdata;
+
+void xge_mac_reset(struct xge_pdata *pdata);
+void xge_mac_set_speed(struct xge_pdata *pdata);
+void xge_mac_enable(struct xge_pdata *pdata);
+void xge_mac_disable(struct xge_pdata *pdata);
+void xge_mac_init(struct xge_pdata *pdata);
+void xge_mac_set_station_addr(struct xge_pdata *pdata);
+
+#endif /* __XGENE_ENET_V2_MAC_H__ */
diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c
new file mode 100644
index 000000000000..0f2ad50f3bd7
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/main.c
@@ -0,0 +1,759 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+static const struct acpi_device_id xge_acpi_match[];
+
+static int xge_get_resources(struct xge_pdata *pdata)
+{
+	struct platform_device *pdev;
+	struct net_device *ndev;
+	int phy_mode, ret = 0;
+	struct resource *res;
+	struct device *dev;
+
+	pdev = pdata->pdev;
+	dev = &pdev->dev;
+	ndev = pdata->ndev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(dev, "Resource enet_csr not defined\n");
+		return -ENODEV;
+	}
+
+	pdata->resources.base_addr = devm_ioremap(dev, res->start,
+						  resource_size(res));
+	if (!pdata->resources.base_addr) {
+		dev_err(dev, "Unable to retrieve ENET Port CSR region\n");
+		return -ENOMEM;
+	}
+
+	if (!device_get_mac_address(dev, ndev->dev_addr, ETH_ALEN))
+		eth_hw_addr_random(ndev);
+
+	memcpy(ndev->perm_addr, ndev->dev_addr, ndev->addr_len);
+
+	phy_mode = device_get_phy_mode(dev);
+	if (phy_mode < 0) {
+		dev_err(dev, "Unable to get phy-connection-type\n");
+		return phy_mode;
+	}
+	pdata->resources.phy_mode = phy_mode;
+
+	if (pdata->resources.phy_mode != PHY_INTERFACE_MODE_RGMII) {
+		dev_err(dev, "Incorrect phy-connection-type specified\n");
+		return -ENODEV;
+	}
+
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0) {
+		dev_err(dev, "Unable to get irq\n");
+		return ret;
+	}
+	pdata->resources.irq = ret;
+
+	return 0;
+}
+
+static int xge_refill_buffers(struct net_device *ndev, u32 nbuf)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct xge_desc_ring *ring = pdata->rx_ring;
+	const u8 slots = XGENE_ENET_NUM_DESC - 1;
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_raw_desc *raw_desc;
+	u64 addr_lo, addr_hi;
+	u8 tail = ring->tail;
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+	u16 len;
+	int i;
+
+	for (i = 0; i < nbuf; i++) {
+		raw_desc = &ring->raw_desc[tail];
+
+		len = XGENE_ENET_STD_MTU;
+		skb = netdev_alloc_skb(ndev, len);
+		if (unlikely(!skb))
+			return -ENOMEM;
+
+		dma_addr = dma_map_single(dev, skb->data, len, DMA_FROM_DEVICE);
+		if (dma_mapping_error(dev, dma_addr)) {
+			netdev_err(ndev, "DMA mapping error\n");
+			dev_kfree_skb_any(skb);
+			return -EINVAL;
+		}
+
+		ring->pkt_info[tail].skb = skb;
+		ring->pkt_info[tail].dma_addr = dma_addr;
+
+		addr_hi = GET_BITS(NEXT_DESC_ADDRH, le64_to_cpu(raw_desc->m1));
+		addr_lo = GET_BITS(NEXT_DESC_ADDRL, le64_to_cpu(raw_desc->m1));
+		raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, addr_lo) |
+					   SET_BITS(NEXT_DESC_ADDRH, addr_hi) |
+					   SET_BITS(PKT_ADDRH,
+						    upper_32_bits(dma_addr)));
+
+		dma_wmb();
+		raw_desc->m0 = cpu_to_le64(SET_BITS(PKT_ADDRL, dma_addr) |
+					   SET_BITS(E, 1));
+		tail = (tail + 1) & slots;
+	}
+
+	ring->tail = tail;
+
+	return 0;
+}
+
+static int xge_init_hw(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	int ret;
+
+	ret = xge_port_reset(ndev);
+	if (ret)
+		return ret;
+
+	xge_port_init(ndev);
+	pdata->nbufs = NUM_BUFS;
+
+	return 0;
+}
+
+static irqreturn_t xge_irq(const int irq, void *data)
+{
+	struct xge_pdata *pdata = data;
+
+	if (napi_schedule_prep(&pdata->napi)) {
+		xge_intr_disable(pdata);
+		__napi_schedule(&pdata->napi);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int xge_request_irq(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	int ret;
+
+	snprintf(pdata->irq_name, IRQ_ID_SIZE, "%s", ndev->name);
+
+	ret = request_irq(pdata->resources.irq, xge_irq, 0, pdata->irq_name,
+			  pdata);
+	if (ret)
+		netdev_err(ndev, "Failed to request irq %s\n", pdata->irq_name);
+
+	return ret;
+}
+
+static void xge_free_irq(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+
+	free_irq(pdata->resources.irq, pdata);
+}
+
+static bool is_tx_slot_available(struct xge_raw_desc *raw_desc)
+{
+	if (GET_BITS(E, le64_to_cpu(raw_desc->m0)) &&
+	    (GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0)) == SLOT_EMPTY))
+		return true;
+
+	return false;
+}
+
+static netdev_tx_t xge_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_desc_ring *tx_ring;
+	struct xge_raw_desc *raw_desc;
+	static dma_addr_t dma_addr;
+	u64 addr_lo, addr_hi;
+	void *pkt_buf;
+	u8 tail;
+	u16 len;
+
+	tx_ring = pdata->tx_ring;
+	tail = tx_ring->tail;
+	len = skb_headlen(skb);
+	raw_desc = &tx_ring->raw_desc[tail];
+
+	if (!is_tx_slot_available(raw_desc)) {
+		netif_stop_queue(ndev);
+		return NETDEV_TX_BUSY;
+	}
+
+	/* Packet buffers should be 64B aligned */
+	pkt_buf = dma_zalloc_coherent(dev, XGENE_ENET_STD_MTU, &dma_addr,
+				      GFP_ATOMIC);
+	if (unlikely(!pkt_buf)) {
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+	memcpy(pkt_buf, skb->data, len);
+
+	addr_hi = GET_BITS(NEXT_DESC_ADDRH, le64_to_cpu(raw_desc->m1));
+	addr_lo = GET_BITS(NEXT_DESC_ADDRL, le64_to_cpu(raw_desc->m1));
+	raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, addr_lo) |
+				   SET_BITS(NEXT_DESC_ADDRH, addr_hi) |
+				   SET_BITS(PKT_ADDRH,
+					    upper_32_bits(dma_addr)));
+
+	tx_ring->pkt_info[tail].skb = skb;
+	tx_ring->pkt_info[tail].dma_addr = dma_addr;
+	tx_ring->pkt_info[tail].pkt_buf = pkt_buf;
+
+	dma_wmb();
+
+	raw_desc->m0 = cpu_to_le64(SET_BITS(PKT_ADDRL, dma_addr) |
+				   SET_BITS(PKT_SIZE, len) |
+				   SET_BITS(E, 0));
+	skb_tx_timestamp(skb);
+	xge_wr_csr(pdata, DMATXCTRL, 1);
+
+	tx_ring->tail = (tail + 1) & (XGENE_ENET_NUM_DESC - 1);
+
+	return NETDEV_TX_OK;
+}
+
+static bool is_tx_hw_done(struct xge_raw_desc *raw_desc)
+{
+	if (GET_BITS(E, le64_to_cpu(raw_desc->m0)) &&
+	    !GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0)))
+		return true;
+
+	return false;
+}
+
+static void xge_txc_poll(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_desc_ring *tx_ring;
+	struct xge_raw_desc *raw_desc;
+	dma_addr_t dma_addr;
+	struct sk_buff *skb;
+	void *pkt_buf;
+	u32 data;
+	u8 head;
+
+	tx_ring = pdata->tx_ring;
+	head = tx_ring->head;
+
+	data = xge_rd_csr(pdata, DMATXSTATUS);
+	if (!GET_BITS(TXPKTCOUNT, data))
+		return;
+
+	while (1) {
+		raw_desc = &tx_ring->raw_desc[head];
+
+		if (!is_tx_hw_done(raw_desc))
+			break;
+
+		dma_rmb();
+
+		skb = tx_ring->pkt_info[head].skb;
+		dma_addr = tx_ring->pkt_info[head].dma_addr;
+		pkt_buf = tx_ring->pkt_info[head].pkt_buf;
+		pdata->stats.tx_packets++;
+		pdata->stats.tx_bytes += skb->len;
+		dma_free_coherent(dev, XGENE_ENET_STD_MTU, pkt_buf, dma_addr);
+		dev_kfree_skb_any(skb);
+
+		/* clear pktstart address and pktsize */
+		raw_desc->m0 = cpu_to_le64(SET_BITS(E, 1) |
+					   SET_BITS(PKT_SIZE, SLOT_EMPTY));
+		xge_wr_csr(pdata, DMATXSTATUS, 1);
+
+		head = (head + 1) & (XGENE_ENET_NUM_DESC - 1);
+	}
+
+	if (netif_queue_stopped(ndev))
+		netif_wake_queue(ndev);
+
+	tx_ring->head = head;
+}
+
+static int xge_rx_poll(struct net_device *ndev, unsigned int budget)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_desc_ring *rx_ring;
+	struct xge_raw_desc *raw_desc;
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+	int processed = 0;
+	u8 head, rx_error;
+	int i, ret;
+	u32 data;
+	u16 len;
+
+	rx_ring = pdata->rx_ring;
+	head = rx_ring->head;
+
+	data = xge_rd_csr(pdata, DMARXSTATUS);
+	if (!GET_BITS(RXPKTCOUNT, data))
+		return 0;
+
+	for (i = 0; i < budget; i++) {
+		raw_desc = &rx_ring->raw_desc[head];
+
+		if (GET_BITS(E, le64_to_cpu(raw_desc->m0)))
+			break;
+
+		dma_rmb();
+
+		skb = rx_ring->pkt_info[head].skb;
+		rx_ring->pkt_info[head].skb = NULL;
+		dma_addr = rx_ring->pkt_info[head].dma_addr;
+		len = GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0));
+		dma_unmap_single(dev, dma_addr, XGENE_ENET_STD_MTU,
+				 DMA_FROM_DEVICE);
+
+		rx_error = GET_BITS(D, le64_to_cpu(raw_desc->m2));
+		if (unlikely(rx_error)) {
+			pdata->stats.rx_errors++;
+			dev_kfree_skb_any(skb);
+			goto out;
+		}
+
+		skb_put(skb, len);
+		skb->protocol = eth_type_trans(skb, ndev);
+
+		pdata->stats.rx_packets++;
+		pdata->stats.rx_bytes += len;
+		napi_gro_receive(&pdata->napi, skb);
+out:
+		ret = xge_refill_buffers(ndev, 1);
+		xge_wr_csr(pdata, DMARXSTATUS, 1);
+		xge_wr_csr(pdata, DMARXCTRL, 1);
+
+		if (ret)
+			break;
+
+		head = (head + 1) & (XGENE_ENET_NUM_DESC - 1);
+		processed++;
+	}
+
+	rx_ring->head = head;
+
+	return processed;
+}
+
+static void xge_delete_desc_ring(struct net_device *ndev,
+				 struct xge_desc_ring *ring)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	u16 size;
+
+	if (!ring)
+		return;
+
+	size = XGENE_ENET_DESC_SIZE * XGENE_ENET_NUM_DESC;
+	if (ring->desc_addr)
+		dma_free_coherent(dev, size, ring->desc_addr, ring->dma_addr);
+
+	kfree(ring->pkt_info);
+	kfree(ring);
+}
+
+static void xge_free_buffers(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct xge_desc_ring *ring = pdata->rx_ring;
+	struct device *dev = &pdata->pdev->dev;
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+	int i;
+
+	for (i = 0; i < XGENE_ENET_NUM_DESC; i++) {
+		skb = ring->pkt_info[i].skb;
+		dma_addr = ring->pkt_info[i].dma_addr;
+
+		if (!skb)
+			continue;
+
+		dma_unmap_single(dev, dma_addr, XGENE_ENET_STD_MTU,
+				 DMA_FROM_DEVICE);
+		dev_kfree_skb_any(skb);
+	}
+}
+
+static void xge_delete_desc_rings(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+
+	xge_txc_poll(ndev);
+	xge_delete_desc_ring(ndev, pdata->tx_ring);
+
+	xge_rx_poll(ndev, 64);
+	xge_free_buffers(ndev);
+	xge_delete_desc_ring(ndev, pdata->rx_ring);
+}
+
+static struct xge_desc_ring *xge_create_desc_ring(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_desc_ring *ring;
+	u16 size;
+
+	ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+	if (!ring)
+		return NULL;
+
+	ring->ndev = ndev;
+
+	size = XGENE_ENET_DESC_SIZE * XGENE_ENET_NUM_DESC;
+	ring->desc_addr = dma_zalloc_coherent(dev, size, &ring->dma_addr,
+					      GFP_KERNEL);
+	if (!ring->desc_addr)
+		goto err;
+
+	ring->pkt_info = kcalloc(XGENE_ENET_NUM_DESC, sizeof(*ring->pkt_info),
+				 GFP_KERNEL);
+	if (!ring->pkt_info)
+		goto err;
+
+	xge_setup_desc(ring);
+
+	return ring;
+
+err:
+	xge_delete_desc_ring(ndev, ring);
+
+	return NULL;
+}
+
+static int xge_create_desc_rings(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct xge_desc_ring *ring;
+	int ret;
+
+	/* create tx ring */
+	ring = xge_create_desc_ring(ndev);
+	if (!ring)
+		goto err;
+
+	pdata->tx_ring = ring;
+	xge_update_tx_desc_addr(pdata);
+
+	/* create rx ring */
+	ring = xge_create_desc_ring(ndev);
+	if (!ring)
+		goto err;
+
+	pdata->rx_ring = ring;
+	xge_update_rx_desc_addr(pdata);
+
+	ret = xge_refill_buffers(ndev, XGENE_ENET_NUM_DESC);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	xge_delete_desc_rings(ndev);
+
+	return -ENOMEM;
+}
+
+static int xge_open(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	int ret;
+
+	ret = xge_create_desc_rings(ndev);
+	if (ret)
+		return ret;
+
+	napi_enable(&pdata->napi);
+	ret = xge_request_irq(ndev);
+	if (ret)
+		return ret;
+
+	xge_intr_enable(pdata);
+	xge_wr_csr(pdata, DMARXCTRL, 1);
+
+	phy_start(ndev->phydev);
+	xge_mac_enable(pdata);
+	netif_start_queue(ndev);
+
+	return 0;
+}
+
+static int xge_close(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+
+	netif_stop_queue(ndev);
+	xge_mac_disable(pdata);
+	phy_stop(ndev->phydev);
+
+	xge_intr_disable(pdata);
+	xge_free_irq(ndev);
+	napi_disable(&pdata->napi);
+	xge_delete_desc_rings(ndev);
+
+	return 0;
+}
+
+static int xge_napi(struct napi_struct *napi, const int budget)
+{
+	struct net_device *ndev = napi->dev;
+	struct xge_pdata *pdata;
+	int processed;
+
+	pdata = netdev_priv(ndev);
+
+	xge_txc_poll(ndev);
+	processed = xge_rx_poll(ndev, budget);
+
+	if (processed < budget) {
+		napi_complete_done(napi, processed);
+		xge_intr_enable(pdata);
+	}
+
+	return processed;
+}
+
+static int xge_set_mac_addr(struct net_device *ndev, void *addr)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	int ret;
+
+	ret = eth_mac_addr(ndev, addr);
+	if (ret)
+		return ret;
+
+	xge_mac_set_station_addr(pdata);
+
+	return 0;
+}
+
+static bool is_tx_pending(struct xge_raw_desc *raw_desc)
+{
+	if (!GET_BITS(E, le64_to_cpu(raw_desc->m0)))
+		return true;
+
+	return false;
+}
+
+static void xge_free_pending_skb(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct xge_desc_ring *tx_ring;
+	struct xge_raw_desc *raw_desc;
+	dma_addr_t dma_addr;
+	struct sk_buff *skb;
+	void *pkt_buf;
+	int i;
+
+	tx_ring = pdata->tx_ring;
+
+	for (i = 0; i < XGENE_ENET_NUM_DESC; i++) {
+		raw_desc = &tx_ring->raw_desc[i];
+
+		if (!is_tx_pending(raw_desc))
+			continue;
+
+		skb = tx_ring->pkt_info[i].skb;
+		dma_addr = tx_ring->pkt_info[i].dma_addr;
+		pkt_buf = tx_ring->pkt_info[i].pkt_buf;
+		dma_free_coherent(dev, XGENE_ENET_STD_MTU, pkt_buf, dma_addr);
+		dev_kfree_skb_any(skb);
+	}
+}
+
+static void xge_timeout(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+
+	rtnl_lock();
+
+	if (!netif_running(ndev))
+		goto out;
+
+	netif_stop_queue(ndev);
+	xge_intr_disable(pdata);
+	napi_disable(&pdata->napi);
+
+	xge_wr_csr(pdata, DMATXCTRL, 0);
+	xge_txc_poll(ndev);
+	xge_free_pending_skb(ndev);
+	xge_wr_csr(pdata, DMATXSTATUS, ~0U);
+
+	xge_setup_desc(pdata->tx_ring);
+	xge_update_tx_desc_addr(pdata);
+	xge_mac_init(pdata);
+
+	napi_enable(&pdata->napi);
+	xge_intr_enable(pdata);
+	xge_mac_enable(pdata);
+	netif_start_queue(ndev);
+
+out:
+	rtnl_unlock();
+}
+
+static void xge_get_stats64(struct net_device *ndev,
+			    struct rtnl_link_stats64 *storage)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct xge_stats *stats = &pdata->stats;
+
+	storage->tx_packets += stats->tx_packets;
+	storage->tx_bytes += stats->tx_bytes;
+
+	storage->rx_packets += stats->rx_packets;
+	storage->rx_bytes += stats->rx_bytes;
+	storage->rx_errors += stats->rx_errors;
+}
+
+static const struct net_device_ops xgene_ndev_ops = {
+	.ndo_open = xge_open,
+	.ndo_stop = xge_close,
+	.ndo_start_xmit = xge_start_xmit,
+	.ndo_set_mac_address = xge_set_mac_addr,
+	.ndo_tx_timeout = xge_timeout,
+	.ndo_get_stats64 = xge_get_stats64,
+};
+
+static int xge_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct net_device *ndev;
+	struct xge_pdata *pdata;
+	int ret;
+
+	ndev = alloc_etherdev(sizeof(*pdata));
+	if (!ndev)
+		return -ENOMEM;
+
+	pdata = netdev_priv(ndev);
+
+	pdata->pdev = pdev;
+	pdata->ndev = ndev;
+	SET_NETDEV_DEV(ndev, dev);
+	platform_set_drvdata(pdev, pdata);
+	ndev->netdev_ops = &xgene_ndev_ops;
+
+	ndev->features |= NETIF_F_GSO |
+			  NETIF_F_GRO;
+
+	ret = xge_get_resources(pdata);
+	if (ret)
+		goto err;
+
+	ndev->hw_features = ndev->features;
+	xge_set_ethtool_ops(ndev);
+
+	ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64));
+	if (ret) {
+		netdev_err(ndev, "No usable DMA configuration\n");
+		goto err;
+	}
+
+	ret = xge_init_hw(ndev);
+	if (ret)
+		goto err;
+
+	ret = xge_mdio_config(ndev);
+	if (ret)
+		goto err;
+
+	netif_napi_add(ndev, &pdata->napi, xge_napi, NAPI_POLL_WEIGHT);
+
+	ret = register_netdev(ndev);
+	if (ret) {
+		netdev_err(ndev, "Failed to register netdev\n");
+		goto err;
+	}
+
+	return 0;
+
+err:
+	free_netdev(ndev);
+
+	return ret;
+}
+
+static int xge_remove(struct platform_device *pdev)
+{
+	struct xge_pdata *pdata;
+	struct net_device *ndev;
+
+	pdata = platform_get_drvdata(pdev);
+	ndev = pdata->ndev;
+
+	rtnl_lock();
+	if (netif_running(ndev))
+		dev_close(ndev);
+	rtnl_unlock();
+
+	xge_mdio_remove(ndev);
+	unregister_netdev(ndev);
+	free_netdev(ndev);
+
+	return 0;
+}
+
+static void xge_shutdown(struct platform_device *pdev)
+{
+	struct xge_pdata *pdata;
+
+	pdata = platform_get_drvdata(pdev);
+	if (!pdata)
+		return;
+
+	if (!pdata->ndev)
+		return;
+
+	xge_remove(pdev);
+}
+
+static const struct acpi_device_id xge_acpi_match[] = {
+	{ "APMC0D80" },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, xge_acpi_match);
+
+static struct platform_driver xge_driver = {
+	.driver = {
+		   .name = "xgene-enet-v2",
+		   .acpi_match_table = ACPI_PTR(xge_acpi_match),
+	},
+	.probe = xge_probe,
+	.remove = xge_remove,
+	.shutdown = xge_shutdown,
+};
+module_platform_driver(xge_driver);
+
+MODULE_DESCRIPTION("APM X-Gene SoC Ethernet v2 driver");
+MODULE_AUTHOR("Iyappan Subramanian <isubramanian@apm.com>");
+MODULE_VERSION(XGENE_ENET_V2_VERSION);
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/apm/xgene-v2/main.h b/drivers/net/ethernet/apm/xgene-v2/main.h
new file mode 100644
index 000000000000..db1178e82a0a
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/main.h
@@ -0,0 +1,80 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __XGENE_ENET_V2_MAIN_H__
+#define __XGENE_ENET_V2_MAIN_H__
+
+#include <linux/acpi.h>
+#include <linux/clk.h>
+#include <linux/efi.h>
+#include <linux/if_vlan.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/of_net.h>
+#include <linux/of_mdio.h>
+#include <linux/prefetch.h>
+#include <linux/phy.h>
+#include <net/ip.h>
+#include "mac.h"
+#include "enet.h"
+#include "ring.h"
+
+#define XGENE_ENET_V2_VERSION	"v1.0"
+#define XGENE_ENET_STD_MTU	1536
+#define XGENE_ENET_MIN_FRAME	60
+#define IRQ_ID_SIZE             16
+
+struct xge_resource {
+	void __iomem *base_addr;
+	int phy_mode;
+	u32 irq;
+};
+
+struct xge_stats {
+	u64 tx_packets;
+	u64 tx_bytes;
+	u64 rx_packets;
+	u64 rx_bytes;
+	u64 rx_errors;
+};
+
+/* ethernet private data */
+struct xge_pdata {
+	struct xge_resource resources;
+	struct xge_desc_ring *tx_ring;
+	struct xge_desc_ring *rx_ring;
+	struct platform_device *pdev;
+	char irq_name[IRQ_ID_SIZE];
+	struct mii_bus *mdio_bus;
+	struct net_device *ndev;
+	struct napi_struct napi;
+	struct xge_stats stats;
+	int phy_speed;
+	u8 nbufs;
+};
+
+int xge_mdio_config(struct net_device *ndev);
+void xge_mdio_remove(struct net_device *ndev);
+void xge_set_ethtool_ops(struct net_device *ndev);
+
+#endif /* __XGENE_ENET_V2_MAIN_H__ */
diff --git a/drivers/net/ethernet/apm/xgene-v2/mdio.c b/drivers/net/ethernet/apm/xgene-v2/mdio.c
new file mode 100644
index 000000000000..a583c6a9a5ea
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/mdio.c
@@ -0,0 +1,167 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+static int xge_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 data)
+{
+	struct xge_pdata *pdata = bus->priv;
+	u32 done, val = 0;
+	u8 wait = 10;
+
+	SET_REG_BITS(&val, PHY_ADDR, phy_id);
+	SET_REG_BITS(&val, REG_ADDR, reg);
+	xge_wr_csr(pdata, MII_MGMT_ADDRESS, val);
+
+	xge_wr_csr(pdata, MII_MGMT_CONTROL, data);
+	do {
+		usleep_range(5, 10);
+		done = xge_rd_csr(pdata, MII_MGMT_INDICATORS);
+	} while ((done & MII_MGMT_BUSY) && wait--);
+
+	if (done & MII_MGMT_BUSY) {
+		dev_err(&bus->dev, "MII_MGMT write failed\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static int xge_mdio_read(struct mii_bus *bus, int phy_id, int reg)
+{
+	struct xge_pdata *pdata = bus->priv;
+	u32 data, done, val = 0;
+	u8 wait = 10;
+
+	SET_REG_BITS(&val, PHY_ADDR, phy_id);
+	SET_REG_BITS(&val, REG_ADDR, reg);
+	xge_wr_csr(pdata, MII_MGMT_ADDRESS, val);
+
+	xge_wr_csr(pdata, MII_MGMT_COMMAND, MII_READ_CYCLE);
+	do {
+		usleep_range(5, 10);
+		done = xge_rd_csr(pdata, MII_MGMT_INDICATORS);
+	} while ((done & MII_MGMT_BUSY) && wait--);
+
+	if (done & MII_MGMT_BUSY) {
+		dev_err(&bus->dev, "MII_MGMT read failed\n");
+		return -ETIMEDOUT;
+	}
+
+	data = xge_rd_csr(pdata, MII_MGMT_STATUS);
+	xge_wr_csr(pdata, MII_MGMT_COMMAND, 0);
+
+	return data;
+}
+
+static void xge_adjust_link(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct phy_device *phydev = ndev->phydev;
+
+	if (phydev->link) {
+		if (pdata->phy_speed != phydev->speed) {
+			pdata->phy_speed = phydev->speed;
+			xge_mac_set_speed(pdata);
+			xge_mac_enable(pdata);
+			phy_print_status(phydev);
+		}
+	} else {
+		if (pdata->phy_speed != SPEED_UNKNOWN) {
+			pdata->phy_speed = SPEED_UNKNOWN;
+			xge_mac_disable(pdata);
+			phy_print_status(phydev);
+		}
+	}
+}
+
+void xge_mdio_remove(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct mii_bus *mdio_bus = pdata->mdio_bus;
+
+	if (ndev->phydev)
+		phy_disconnect(ndev->phydev);
+
+	if (mdio_bus->state == MDIOBUS_REGISTERED)
+		mdiobus_unregister(mdio_bus);
+
+	mdiobus_free(mdio_bus);
+}
+
+int xge_mdio_config(struct net_device *ndev)
+{
+	struct xge_pdata *pdata = netdev_priv(ndev);
+	struct device *dev = &pdata->pdev->dev;
+	struct mii_bus *mdio_bus;
+	struct phy_device *phydev;
+	int ret;
+
+	mdio_bus = mdiobus_alloc();
+	if (!mdio_bus)
+		return -ENOMEM;
+
+	mdio_bus->name = "APM X-Gene Ethernet (v2) MDIO Bus";
+	mdio_bus->read = xge_mdio_read;
+	mdio_bus->write = xge_mdio_write;
+	mdio_bus->priv = pdata;
+	mdio_bus->parent = dev;
+	snprintf(mdio_bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(dev));
+	pdata->mdio_bus = mdio_bus;
+
+	mdio_bus->phy_mask = 0x1;
+	ret = mdiobus_register(mdio_bus);
+	if (ret)
+		goto err;
+
+	phydev = phy_find_first(mdio_bus);
+	if (!phydev) {
+		dev_err(dev, "no PHY found\n");
+		goto err;
+	}
+	phydev = phy_connect(ndev, phydev_name(phydev),
+			     &xge_adjust_link,
+			     pdata->resources.phy_mode);
+
+	if (IS_ERR(phydev)) {
+		netdev_err(ndev, "Could not attach to PHY\n");
+		ret = PTR_ERR(phydev);
+		goto err;
+	}
+
+	phydev->supported &= ~(SUPPORTED_10baseT_Half |
+			       SUPPORTED_10baseT_Full |
+			       SUPPORTED_100baseT_Half |
+			       SUPPORTED_100baseT_Full |
+			       SUPPORTED_1000baseT_Half |
+			       SUPPORTED_AUI |
+			       SUPPORTED_MII |
+			       SUPPORTED_FIBRE |
+			       SUPPORTED_BNC);
+	phydev->advertising = phydev->supported;
+	pdata->phy_speed = SPEED_UNKNOWN;
+
+	return 0;
+err:
+	xge_mdio_remove(ndev);
+
+	return ret;
+}
diff --git a/drivers/net/ethernet/apm/xgene-v2/ring.c b/drivers/net/ethernet/apm/xgene-v2/ring.c
new file mode 100644
index 000000000000..38810828f8f0
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/ring.c
@@ -0,0 +1,81 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+/* create circular linked list of descriptors */
+void xge_setup_desc(struct xge_desc_ring *ring)
+{
+	struct xge_raw_desc *raw_desc;
+	dma_addr_t dma_h, next_dma;
+	u16 offset;
+	int i;
+
+	for (i = 0; i < XGENE_ENET_NUM_DESC; i++) {
+		raw_desc = &ring->raw_desc[i];
+
+		offset = (i + 1) & (XGENE_ENET_NUM_DESC - 1);
+		next_dma = ring->dma_addr + (offset * XGENE_ENET_DESC_SIZE);
+
+		raw_desc->m0 = cpu_to_le64(SET_BITS(E, 1) |
+					   SET_BITS(PKT_SIZE, SLOT_EMPTY));
+		dma_h = upper_32_bits(next_dma);
+		raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, next_dma) |
+					   SET_BITS(NEXT_DESC_ADDRH, dma_h));
+	}
+}
+
+void xge_update_tx_desc_addr(struct xge_pdata *pdata)
+{
+	struct xge_desc_ring *ring = pdata->tx_ring;
+	dma_addr_t dma_addr = ring->dma_addr;
+
+	xge_wr_csr(pdata, DMATXDESCL, dma_addr);
+	xge_wr_csr(pdata, DMATXDESCH, upper_32_bits(dma_addr));
+
+	ring->head = 0;
+	ring->tail = 0;
+}
+
+void xge_update_rx_desc_addr(struct xge_pdata *pdata)
+{
+	struct xge_desc_ring *ring = pdata->rx_ring;
+	dma_addr_t dma_addr = ring->dma_addr;
+
+	xge_wr_csr(pdata, DMARXDESCL, dma_addr);
+	xge_wr_csr(pdata, DMARXDESCH, upper_32_bits(dma_addr));
+
+	ring->head = 0;
+	ring->tail = 0;
+}
+
+void xge_intr_enable(struct xge_pdata *pdata)
+{
+	u32 data;
+
+	data = RX_PKT_RCVD | TX_PKT_SENT;
+	xge_wr_csr(pdata, DMAINTRMASK, data);
+}
+
+void xge_intr_disable(struct xge_pdata *pdata)
+{
+	xge_wr_csr(pdata, DMAINTRMASK, 0);
+}
diff --git a/drivers/net/ethernet/apm/xgene-v2/ring.h b/drivers/net/ethernet/apm/xgene-v2/ring.h
new file mode 100644
index 000000000000..abc8c9a84954
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/ring.h
@@ -0,0 +1,119 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ *	      Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __XGENE_ENET_V2_RING_H__
+#define __XGENE_ENET_V2_RING_H__
+
+#define XGENE_ENET_DESC_SIZE	64
+#define XGENE_ENET_NUM_DESC	256
+#define NUM_BUFS		8
+#define SLOT_EMPTY		0xfff
+
+#define DMATXCTRL		0xa180
+#define DMATXDESCL		0xa184
+#define DMATXDESCH		0xa1a0
+#define DMATXSTATUS		0xa188
+#define DMARXCTRL		0xa18c
+#define DMARXDESCL		0xa190
+#define DMARXDESCH		0xa1a4
+#define DMARXSTATUS		0xa194
+#define DMAINTRMASK		0xa198
+#define DMAINTERRUPT		0xa19c
+
+#define D_POS			62
+#define D_LEN			2
+#define E_POS			63
+#define E_LEN			1
+#define PKT_ADDRL_POS		0
+#define PKT_ADDRL_LEN		32
+#define PKT_ADDRH_POS		32
+#define PKT_ADDRH_LEN		10
+#define PKT_SIZE_POS		32
+#define PKT_SIZE_LEN		12
+#define NEXT_DESC_ADDRL_POS	0
+#define NEXT_DESC_ADDRL_LEN	32
+#define NEXT_DESC_ADDRH_POS	48
+#define NEXT_DESC_ADDRH_LEN	10
+
+#define TXPKTCOUNT_POS		16
+#define TXPKTCOUNT_LEN		8
+#define RXPKTCOUNT_POS		16
+#define RXPKTCOUNT_LEN		8
+
+#define TX_PKT_SENT		BIT(0)
+#define TX_BUS_ERROR		BIT(3)
+#define RX_PKT_RCVD		BIT(4)
+#define RX_BUS_ERROR		BIT(7)
+#define RXSTATUS_RXPKTRCVD	BIT(0)
+
+struct xge_raw_desc {
+	__le64 m0;
+	__le64 m1;
+	__le64 m2;
+	__le64 m3;
+	__le64 m4;
+	__le64 m5;
+	__le64 m6;
+	__le64 m7;
+};
+
+struct pkt_info {
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+	void *pkt_buf;
+};
+
+/* software context of a descriptor ring */
+struct xge_desc_ring {
+	struct net_device *ndev;
+	dma_addr_t dma_addr;
+	u8 head;
+	u8 tail;
+	union {
+		void *desc_addr;
+		struct xge_raw_desc *raw_desc;
+	};
+	struct pkt_info (*pkt_info);
+};
+
+static inline u64 xge_set_desc_bits(int pos, int len, u64 val)
+{
+	return (val & ((1ULL << len) - 1)) << pos;
+}
+
+static inline u64 xge_get_desc_bits(int pos, int len, u64 src)
+{
+	return (src >> pos) & ((1ULL << len) - 1);
+}
+
+#define SET_BITS(field, val) \
+		xge_set_desc_bits(field ## _POS, field ## _LEN, val)
+
+#define GET_BITS(field, src) \
+		xge_get_desc_bits(field ## _POS, field ## _LEN, src)
+
+void xge_setup_desc(struct xge_desc_ring *ring);
+void xge_update_tx_desc_addr(struct xge_pdata *pdata);
+void xge_update_rx_desc_addr(struct xge_pdata *pdata);
+void xge_intr_enable(struct xge_pdata *pdata);
+void xge_intr_disable(struct xge_pdata *pdata);
+
+#endif  /* __XGENE_ENET_V2_RING_H__ */
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
index 06e681697c17..2a835e07adfb 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
@@ -494,7 +494,7 @@ static void xgene_gmac_set_speed(struct xgene_enet_pdata *pdata)
 		break;
 	}
 
-	mc2 |= FULL_DUPLEX2 | PAD_CRC;
+	mc2 |= FULL_DUPLEX2 | PAD_CRC | LENGTH_CHK;
 	xgene_enet_wr_mcx_mac(pdata, MAC_CONFIG_2_ADDR, mc2);
 	xgene_enet_wr_mcx_mac(pdata, INTERFACE_CONTROL_ADDR, intf_ctl);
 	xgene_enet_wr_csr(pdata, RGMII_REG_0_ADDR, rgmii);
@@ -623,6 +623,7 @@ static void xgene_enet_cle_bypass(struct xgene_enet_pdata *pdata,
 	xgene_enet_rd_csr(pdata, CLE_BYPASS_REG0_0_ADDR, &cb);
 	cb |= CFG_CLE_BYPASS_EN0;
 	CFG_CLE_IP_PROTOCOL0_SET(&cb, 3);
+	CFG_CLE_IP_HDR_LEN_SET(&cb, 0);
 	xgene_enet_wr_csr(pdata, CLE_BYPASS_REG0_0_ADDR, cb);
 
 	xgene_enet_rd_csr(pdata, CLE_BYPASS_REG1_0_ADDR, &cb);
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
index 5f83037bb96b..d250bfe94d24 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
@@ -163,6 +163,7 @@ enum xgene_enet_rm {
 #define CFG_RXCLK_MUXSEL0_SET(dst, val)	xgene_set_bits(dst, val, 26, 3)
 
 #define CFG_CLE_IP_PROTOCOL0_SET(dst, val)	xgene_set_bits(dst, val, 16, 2)
+#define CFG_CLE_IP_HDR_LEN_SET(dst, val)	xgene_set_bits(dst, val, 8, 5)
 #define CFG_CLE_DSTQID0_SET(dst, val)		xgene_set_bits(dst, val, 0, 12)
 #define CFG_CLE_FPSEL0_SET(dst, val)		xgene_set_bits(dst, val, 16, 4)
 #define CFG_CLE_NXTFPSEL0_SET(dst, val)		xgene_set_bits(dst, val, 20, 4)
@@ -215,6 +216,7 @@ enum xgene_enet_rm {
 #define ENET_GHD_MODE			BIT(26)
 #define FULL_DUPLEX2			BIT(0)
 #define PAD_CRC				BIT(2)
+#define LENGTH_CHK			BIT(4)
 #define SCAN_AUTO_INCR			BIT(5)
 #define TBYT_ADDR			0x38
 #define TPKT_ADDR			0x39
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index b3568c453b14..5f37ed3506d5 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -601,14 +601,24 @@ static netdev_tx_t xgene_enet_start_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 }
 
-static void xgene_enet_skip_csum(struct sk_buff *skb)
+static void xgene_enet_rx_csum(struct sk_buff *skb)
 {
+	struct net_device *ndev = skb->dev;
 	struct iphdr *iph = ip_hdr(skb);
 
-	if (!ip_is_fragment(iph) ||
-	    (iph->protocol != IPPROTO_TCP && iph->protocol != IPPROTO_UDP)) {
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-	}
+	if (!(ndev->features & NETIF_F_RXCSUM))
+		return;
+
+	if (skb->protocol != htons(ETH_P_IP))
+		return;
+
+	if (ip_is_fragment(iph))
+		return;
+
+	if (iph->protocol != IPPROTO_TCP && iph->protocol != IPPROTO_UDP)
+		return;
+
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
 }
 
 static void xgene_enet_free_pagepool(struct xgene_enet_desc_ring *buf_pool,
@@ -648,12 +658,24 @@ static void xgene_enet_free_pagepool(struct xgene_enet_desc_ring *buf_pool,
 	buf_pool->head = head;
 }
 
+/* Errata 10GE_8 and ENET_11 - allow packet with length <=64B */
+static bool xgene_enet_errata_10GE_8(struct sk_buff *skb, u32 len, u8 status)
+{
+	if (status == INGRESS_PKT_LEN && len == ETHER_MIN_PACKET) {
+		if (ntohs(eth_hdr(skb)->h_proto) < 46)
+			return true;
+	}
+
+	return false;
+}
+
 static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring,
 			       struct xgene_enet_raw_desc *raw_desc,
 			       struct xgene_enet_raw_desc *exp_desc)
 {
 	struct xgene_enet_desc_ring *buf_pool, *page_pool;
 	u32 datalen, frag_size, skb_index;
+	struct xgene_enet_pdata *pdata;
 	struct net_device *ndev;
 	dma_addr_t dma_addr;
 	struct sk_buff *skb;
@@ -666,6 +688,7 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring,
 	bool nv;
 
 	ndev = rx_ring->ndev;
+	pdata = netdev_priv(ndev);
 	dev = ndev_to_dev(rx_ring->ndev);
 	buf_pool = rx_ring->buf_pool;
 	page_pool = rx_ring->page_pool;
@@ -676,30 +699,29 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring,
 	skb = buf_pool->rx_skb[skb_index];
 	buf_pool->rx_skb[skb_index] = NULL;
 
+	datalen = xgene_enet_get_data_len(le64_to_cpu(raw_desc->m1));
+	skb_put(skb, datalen);
+	prefetch(skb->data - NET_IP_ALIGN);
+	skb->protocol = eth_type_trans(skb, ndev);
+
 	/* checking for error */
-	status = (GET_VAL(ELERR, le64_to_cpu(raw_desc->m0)) << LERR_LEN) ||
+	status = (GET_VAL(ELERR, le64_to_cpu(raw_desc->m0)) << LERR_LEN) |
 		  GET_VAL(LERR, le64_to_cpu(raw_desc->m0));
-	if (unlikely(status > 2)) {
-		dev_kfree_skb_any(skb);
-		xgene_enet_free_pagepool(page_pool, raw_desc, exp_desc);
-		xgene_enet_parse_error(rx_ring, netdev_priv(rx_ring->ndev),
-				       status);
-		ret = -EIO;
-		goto out;
+	if (unlikely(status)) {
+		if (!xgene_enet_errata_10GE_8(skb, datalen, status)) {
+			dev_kfree_skb_any(skb);
+			xgene_enet_free_pagepool(page_pool, raw_desc, exp_desc);
+			xgene_enet_parse_error(rx_ring, pdata, status);
+			goto out;
+		}
 	}
 
-	/* strip off CRC as HW isn't doing this */
-	datalen = xgene_enet_get_data_len(le64_to_cpu(raw_desc->m1));
-
 	nv = GET_VAL(NV, le64_to_cpu(raw_desc->m0));
-	if (!nv)
+	if (!nv) {
+		/* strip off CRC as HW isn't doing this */
 		datalen -= 4;
-
-	skb_put(skb, datalen);
-	prefetch(skb->data - NET_IP_ALIGN);
-
-	if (!nv)
 		goto skip_jumbo;
+	}
 
 	slots = page_pool->slots - 1;
 	head = page_pool->head;
@@ -728,11 +750,7 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring,
 
 skip_jumbo:
 	skb_checksum_none_assert(skb);
-	skb->protocol = eth_type_trans(skb, ndev);
-	if (likely((ndev->features & NETIF_F_IP_CSUM) &&
-		   skb->protocol == htons(ETH_P_IP))) {
-		xgene_enet_skip_csum(skb);
-	}
+	xgene_enet_rx_csum(skb);
 
 	rx_ring->rx_packets++;
 	rx_ring->rx_bytes += datalen;
@@ -2039,7 +2057,7 @@ static int xgene_enet_probe(struct platform_device *pdev)
 	xgene_enet_setup_ops(pdata);
 
 	if (pdata->phy_mode == PHY_INTERFACE_MODE_XGMII) {
-		ndev->features |= NETIF_F_TSO;
+		ndev->features |= NETIF_F_TSO | NETIF_F_RXCSUM;
 		spin_lock_init(&pdata->mss_lock);
 	}
 	ndev->hw_features = ndev->features;
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
index 52571741da9f..0d4be2425ebc 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
@@ -41,6 +41,7 @@
 #include "../../../phy/mdio-xgene.h"
 
 #define XGENE_DRV_VERSION	"v1.0"
+#define ETHER_MIN_PACKET	64
 #define XGENE_ENET_STD_MTU	1536
 #define XGENE_ENET_MAX_MTU	9600
 #define SKB_BUFFER_SIZE		(XGENE_ENET_STD_MTU - NET_IP_ALIGN)
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
index ece19e6d68e3..423240c97d39 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
@@ -341,8 +341,15 @@ static void xgene_xgmac_init(struct xgene_enet_pdata *pdata)
 
 	xgene_enet_rd_csr(pdata, XG_RSIF_CONFIG_REG_ADDR, &data);
 	data |= CFG_RSIF_FPBUFF_TIMEOUT_EN;
+	/* Errata 10GE_1 - FIFO threshold default value incorrect */
+	RSIF_CLE_BUFF_THRESH_SET(&data, XG_RSIF_CLE_BUFF_THRESH);
 	xgene_enet_wr_csr(pdata, XG_RSIF_CONFIG_REG_ADDR, data);
 
+	/* Errata 10GE_1 - FIFO threshold default value incorrect */
+	xgene_enet_rd_csr(pdata, XG_RSIF_CONFIG1_REG_ADDR, &data);
+	RSIF_PLC_CLE_BUFF_THRESH_SET(&data, XG_RSIF_PLC_CLE_BUFF_THRESH);
+	xgene_enet_wr_csr(pdata, XG_RSIF_CONFIG1_REG_ADDR, data);
+
 	xgene_enet_rd_csr(pdata, XG_ENET_SPARE_CFG_REG_ADDR, &data);
 	data |= BIT(12);
 	xgene_enet_wr_csr(pdata, XG_ENET_SPARE_CFG_REG_ADDR, data);
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h
index 03b847ad8937..e644a429ebf4 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h
@@ -65,6 +65,11 @@
 #define XG_DEF_PAUSE_THRES		0x390
 #define XG_DEF_PAUSE_OFF_THRES		0x2c0
 #define XG_RSIF_CONFIG_REG_ADDR		0x00a0
+#define XG_RSIF_CLE_BUFF_THRESH                0x3
+#define RSIF_CLE_BUFF_THRESH_SET(dst, val)     xgene_set_bits(dst, val, 0, 3)
+#define XG_RSIF_CONFIG1_REG_ADDR       0x00b8
+#define XG_RSIF_PLC_CLE_BUFF_THRESH    0x1
+#define RSIF_PLC_CLE_BUFF_THRESH_SET(dst, val) xgene_set_bits(dst, val, 0, 2)
 #define XCLE_BYPASS_REG0_ADDR           0x0160
 #define XCLE_BYPASS_REG1_ADDR           0x0164
 #define XG_CFG_BYPASS_ADDR		0x0204
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 940fb24bba21..96413808c726 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -109,7 +109,6 @@ config TIGON3
 	tristate "Broadcom Tigon3 support"
 	depends on PCI
 	select PHYLIB
-	select HWMON
 	imply PTP_1588_CLOCK
 	---help---
 	  This driver supports Broadcom Tigon3 based gigabit Ethernet cards.
@@ -117,6 +116,13 @@ config TIGON3
 	  To compile this driver as a module, choose M here: the module
 	  will be called tg3.  This is recommended.
 
+config TIGON3_HWMON
+	bool "Broadcom Tigon3 HWMON support"
+	default y
+	depends on TIGON3 && HWMON && !(TIGON3=y && HWMON=m)
+	---help---
+	  Say Y if you want to expose the thermal sensor on Tigon3 devices.
+
 config BNX2X
 	tristate "Broadcom NetXtremeII 10Gb support"
 	depends on PCI
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index a68d4889f5db..099b374c1b17 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -22,6 +22,7 @@
 #include <linux/of_mdio.h>
 #include <linux/phy.h>
 #include <linux/phy_fixed.h>
+#include <net/dsa.h>
 #include <net/ip.h>
 #include <net/ipv6.h>
 
@@ -284,6 +285,7 @@ static const struct bcm_sysport_stats bcm_sysport_gstrings_stats[] = {
 	STAT_MIB_SOFT("alloc_rx_buff_failed", mib.alloc_rx_buff_failed),
 	STAT_MIB_SOFT("rx_dma_failed", mib.rx_dma_failed),
 	STAT_MIB_SOFT("tx_dma_failed", mib.tx_dma_failed),
+	/* Per TX-queue statistics are dynamically appended */
 };
 
 #define BCM_SYSPORT_STATS_LEN	ARRAY_SIZE(bcm_sysport_gstrings_stats)
@@ -338,7 +340,8 @@ static int bcm_sysport_get_sset_count(struct net_device *dev, int string_set)
 				continue;
 			j++;
 		}
-		return j;
+		/* Include per-queue statistics */
+		return j + dev->num_tx_queues * NUM_SYSPORT_TXQ_STAT;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -349,6 +352,7 @@ static void bcm_sysport_get_strings(struct net_device *dev,
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	const struct bcm_sysport_stats *s;
+	char buf[128];
 	int i, j;
 
 	switch (stringset) {
@@ -363,6 +367,18 @@ static void bcm_sysport_get_strings(struct net_device *dev,
 			       ETH_GSTRING_LEN);
 			j++;
 		}
+
+		for (i = 0; i < dev->num_tx_queues; i++) {
+			snprintf(buf, sizeof(buf), "txq%d_packets", i);
+			memcpy(data + j * ETH_GSTRING_LEN, buf,
+			       ETH_GSTRING_LEN);
+			j++;
+
+			snprintf(buf, sizeof(buf), "txq%d_bytes", i);
+			memcpy(data + j * ETH_GSTRING_LEN, buf,
+			       ETH_GSTRING_LEN);
+			j++;
+		}
 		break;
 	default:
 		break;
@@ -418,6 +434,7 @@ static void bcm_sysport_get_stats(struct net_device *dev,
 				  struct ethtool_stats *stats, u64 *data)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	struct bcm_sysport_tx_ring *ring;
 	int i, j;
 
 	if (netif_running(dev))
@@ -436,6 +453,22 @@ static void bcm_sysport_get_stats(struct net_device *dev,
 		data[j] = *(unsigned long *)p;
 		j++;
 	}
+
+	/* For SYSTEMPORT Lite since we have holes in our statistics, j would
+	 * be equal to BCM_SYSPORT_STATS_LEN at the end of the loop, but it
+	 * needs to point to how many total statistics we have minus the
+	 * number of per TX queue statistics
+	 */
+	j = bcm_sysport_get_sset_count(dev, ETH_SS_STATS) -
+	    dev->num_tx_queues * NUM_SYSPORT_TXQ_STAT;
+
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		ring = &priv->tx_rings[i];
+		data[j] = ring->packets;
+		j++;
+		data[j] = ring->bytes;
+		j++;
+	}
 }
 
 static void bcm_sysport_get_wol(struct net_device *dev,
@@ -637,6 +670,9 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 	u16 len, status;
 	struct bcm_rsb *rsb;
 
+	/* Clear status before servicing to reduce spurious interrupts */
+	intrl2_0_writel(priv, INTRL2_0_RDMA_MBDONE, INTRL2_CPU_CLEAR);
+
 	/* Determine how much we should process since last call, SYSTEMPORT Lite
 	 * groups the producer and consumer indexes into the same 32-bit
 	 * which we access using RDMA_CONS_INDEX
@@ -647,11 +683,7 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 		p_index = rdma_readl(priv, RDMA_CONS_INDEX);
 	p_index &= RDMA_PROD_INDEX_MASK;
 
-	if (p_index < priv->rx_c_index)
-		to_process = (RDMA_CONS_INDEX_MASK + 1) -
-			priv->rx_c_index + p_index;
-	else
-		to_process = p_index - priv->rx_c_index;
+	to_process = (p_index - priv->rx_c_index) & RDMA_CONS_INDEX_MASK;
 
 	netif_dbg(priv, rx_status, ndev,
 		  "p_index=%d rx_c_index=%d to_process=%d\n",
@@ -746,26 +778,26 @@ next:
 	return processed;
 }
 
-static void bcm_sysport_tx_reclaim_one(struct bcm_sysport_priv *priv,
+static void bcm_sysport_tx_reclaim_one(struct bcm_sysport_tx_ring *ring,
 				       struct bcm_sysport_cb *cb,
 				       unsigned int *bytes_compl,
 				       unsigned int *pkts_compl)
 {
+	struct bcm_sysport_priv *priv = ring->priv;
 	struct device *kdev = &priv->pdev->dev;
-	struct net_device *ndev = priv->netdev;
 
 	if (cb->skb) {
-		ndev->stats.tx_bytes += cb->skb->len;
+		ring->bytes += cb->skb->len;
 		*bytes_compl += cb->skb->len;
 		dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr),
 				 dma_unmap_len(cb, dma_len),
 				 DMA_TO_DEVICE);
-		ndev->stats.tx_packets++;
+		ring->packets++;
 		(*pkts_compl)++;
 		bcm_sysport_free_cb(cb);
 	/* SKB fragment */
 	} else if (dma_unmap_addr(cb, dma_addr)) {
-		ndev->stats.tx_bytes += dma_unmap_len(cb, dma_len);
+		ring->bytes += dma_unmap_len(cb, dma_len);
 		dma_unmap_page(kdev, dma_unmap_addr(cb, dma_addr),
 			       dma_unmap_len(cb, dma_len), DMA_TO_DEVICE);
 		dma_unmap_addr_set(cb, dma_addr, 0);
@@ -782,6 +814,13 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 	struct bcm_sysport_cb *cb;
 	u32 hw_ind;
 
+	/* Clear status before servicing to reduce spurious interrupts */
+	if (!ring->priv->is_lite)
+		intrl2_1_writel(ring->priv, BIT(ring->index), INTRL2_CPU_CLEAR);
+	else
+		intrl2_0_writel(ring->priv, BIT(ring->index +
+				INTRL2_0_TDMA_MBDONE_SHIFT), INTRL2_CPU_CLEAR);
+
 	/* Compute how many descriptors have been processed since last call */
 	hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index));
 	c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK;
@@ -803,7 +842,7 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 
 	while (last_tx_cn-- > 0) {
 		cb = ring->cbs + last_c_index;
-		bcm_sysport_tx_reclaim_one(priv, cb, &bytes_compl, &pkts_compl);
+		bcm_sysport_tx_reclaim_one(ring, cb, &bytes_compl, &pkts_compl);
 
 		ring->desc_count++;
 		last_c_index++;
@@ -1632,6 +1671,24 @@ static int bcm_sysport_change_mac(struct net_device *dev, void *p)
 	return 0;
 }
 
+static struct net_device_stats *bcm_sysport_get_nstats(struct net_device *dev)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	unsigned long tx_bytes = 0, tx_packets = 0;
+	struct bcm_sysport_tx_ring *ring;
+	unsigned int q;
+
+	for (q = 0; q < dev->num_tx_queues; q++) {
+		ring = &priv->tx_rings[q];
+		tx_bytes += ring->bytes;
+		tx_packets += ring->packets;
+	}
+
+	dev->stats.tx_bytes = tx_bytes;
+	dev->stats.tx_packets = tx_packets;
+	return &dev->stats;
+}
+
 static void bcm_sysport_netif_start(struct net_device *dev)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
@@ -1893,6 +1950,7 @@ static const struct net_device_ops bcm_sysport_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= bcm_sysport_poll_controller,
 #endif
+	.ndo_get_stats		= bcm_sysport_get_nstats,
 };
 
 #define REV_FMT	"v%2x.%02x"
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index 863ddd7870b7..77a51c167a69 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -647,6 +647,9 @@ enum bcm_sysport_stat_type {
 	.reg_offset = ofs, \
 }
 
+/* TX bytes and packets */
+#define NUM_SYSPORT_TXQ_STAT	2
+
 struct bcm_sysport_stats {
 	char stat_string[ETH_GSTRING_LEN];
 	int stat_sizeof;
@@ -690,6 +693,8 @@ struct bcm_sysport_tx_ring {
 	struct bcm_sysport_cb *cbs;	/* Transmit control blocks */
 	struct dma_desc	*desc_cpu;	/* CPU view of the descriptor */
 	struct bcm_sysport_priv *priv;	/* private context backpointer */
+	unsigned long	packets;	/* packets statistics */
+	unsigned long	bytes;		/* bytes statistics */
 };
 
 /* Driver private structure */
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c
index d59cfcc4c4d5..6322594ab260 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c
@@ -11,6 +11,7 @@
 #include <linux/bcma/bcma.h>
 #include <linux/brcmphy.h>
 #include <linux/etherdevice.h>
+#include <linux/of_net.h>
 #include "bgmac.h"
 
 static inline bool bgmac_is_bcm4707_family(struct bcma_device *core)
@@ -114,7 +115,7 @@ static int bgmac_probe(struct bcma_device *core)
 	struct ssb_sprom *sprom = &core->bus->sprom;
 	struct mii_bus *mii_bus;
 	struct bgmac *bgmac;
-	u8 *mac;
+	const u8 *mac = NULL;
 	int err;
 
 	bgmac = bgmac_alloc(&core->dev);
@@ -127,21 +128,27 @@ static int bgmac_probe(struct bcma_device *core)
 
 	bcma_set_drvdata(core, bgmac);
 
-	switch (core->core_unit) {
-	case 0:
-		mac = sprom->et0mac;
-		break;
-	case 1:
-		mac = sprom->et1mac;
-		break;
-	case 2:
-		mac = sprom->et2mac;
-		break;
-	default:
-		dev_err(bgmac->dev, "Unsupported core_unit %d\n",
-			core->core_unit);
-		err = -ENOTSUPP;
-		goto err;
+	if (bgmac->dev->of_node)
+		mac = of_get_mac_address(bgmac->dev->of_node);
+
+	/* If no MAC address assigned via device tree, check SPROM */
+	if (!mac) {
+		switch (core->core_unit) {
+		case 0:
+			mac = sprom->et0mac;
+			break;
+		case 1:
+			mac = sprom->et1mac;
+			break;
+		case 2:
+			mac = sprom->et2mac;
+			break;
+		default:
+			dev_err(bgmac->dev, "Unsupported core_unit %d\n",
+				core->core_unit);
+			err = -ENOTSUPP;
+			goto err;
+		}
 	}
 
 	ether_addr_copy(bgmac->net_dev->dev_addr, mac);
@@ -192,36 +199,50 @@ static int bgmac_probe(struct bcma_device *core)
 		goto err1;
 	}
 
-	bgmac->has_robosw = !!(core->bus->sprom.boardflags_lo &
-			       BGMAC_BFL_ENETROBO);
+	bgmac->has_robosw = !!(sprom->boardflags_lo & BGMAC_BFL_ENETROBO);
 	if (bgmac->has_robosw)
 		dev_warn(bgmac->dev, "Support for Roboswitch not implemented\n");
 
-	if (core->bus->sprom.boardflags_lo & BGMAC_BFL_ENETADM)
+	if (sprom->boardflags_lo & BGMAC_BFL_ENETADM)
 		dev_warn(bgmac->dev, "Support for ADMtek ethernet switch not implemented\n");
 
 	/* Feature Flags */
-	switch (core->bus->chipinfo.id) {
+	switch (ci->id) {
+	/* BCM 471X/535X family */
+	case BCMA_CHIP_ID_BCM4716:
+		bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
+		/* fallthrough */
+	case BCMA_CHIP_ID_BCM47162:
+		bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL2;
+		bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK;
+		break;
 	case BCMA_CHIP_ID_BCM5357:
+	case BCMA_CHIP_ID_BCM53572:
 		bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK;
 		bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
 		bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1;
 		bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY;
-		if (core->bus->chipinfo.pkg == BCMA_PKG_ID_BCM47186) {
-			bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED;
+		if (ci->pkg == BCMA_PKG_ID_BCM47188 ||
+		    ci->pkg == BCMA_PKG_ID_BCM47186) {
 			bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII;
+			bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED;
 		}
-		if (core->bus->chipinfo.pkg == BCMA_PKG_ID_BCM5358)
+		if (ci->pkg == BCMA_PKG_ID_BCM5358)
 			bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_EPHYRMII;
 		break;
-	case BCMA_CHIP_ID_BCM53572:
-		bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK;
+	case BCMA_CHIP_ID_BCM53573:
 		bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
-		bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1;
-		bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY;
-		if (core->bus->chipinfo.pkg == BCMA_PKG_ID_BCM47188) {
-			bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII;
+		bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK;
+		if (ci->pkg == BCMA_PKG_ID_BCM47189)
 			bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED;
+		if (core->core_unit == 0) {
+			bgmac->feature_flags |= BGMAC_FEAT_CC4_IF_SW_TYPE;
+			if (ci->pkg == BCMA_PKG_ID_BCM47189)
+				bgmac->feature_flags |=
+					BGMAC_FEAT_CC4_IF_SW_TYPE_RGMII;
+		} else if (core->core_unit == 1) {
+			bgmac->feature_flags |= BGMAC_FEAT_IRQ_ID_OOB_6;
+			bgmac->feature_flags |= BGMAC_FEAT_CC7_IF_TYPE_RGMII;
 		}
 		break;
 	case BCMA_CHIP_ID_BCM4749:
@@ -229,18 +250,11 @@ static int bgmac_probe(struct bcma_device *core)
 		bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
 		bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1;
 		bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY;
-		if (core->bus->chipinfo.pkg == 10) {
+		if (ci->pkg == 10) {
 			bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII;
 			bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED;
 		}
 		break;
-	case BCMA_CHIP_ID_BCM4716:
-		bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
-		/* fallthrough */
-	case BCMA_CHIP_ID_BCM47162:
-		bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL2;
-		bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK;
-		break;
 	/* bcm4707_family */
 	case BCMA_CHIP_ID_BCM4707:
 	case BCMA_CHIP_ID_BCM47094:
@@ -249,21 +263,6 @@ static int bgmac_probe(struct bcma_device *core)
 		bgmac->feature_flags |= BGMAC_FEAT_NO_RESET;
 		bgmac->feature_flags |= BGMAC_FEAT_FORCE_SPEED_2500;
 		break;
-	case BCMA_CHIP_ID_BCM53573:
-		bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
-		bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK;
-		if (ci->pkg == BCMA_PKG_ID_BCM47189)
-			bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED;
-		if (core->core_unit == 0) {
-			bgmac->feature_flags |= BGMAC_FEAT_CC4_IF_SW_TYPE;
-			if (ci->pkg == BCMA_PKG_ID_BCM47189)
-				bgmac->feature_flags |=
-					BGMAC_FEAT_CC4_IF_SW_TYPE_RGMII;
-		} else if (core->core_unit == 1) {
-			bgmac->feature_flags |= BGMAC_FEAT_IRQ_ID_OOB_6;
-			bgmac->feature_flags |= BGMAC_FEAT_CC7_IF_TYPE_RGMII;
-		}
-		break;
 	default:
 		bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
 		bgmac->feature_flags |= BGMAC_FEAT_SET_RXQ_CLK;
diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c
index da1b8b225eb9..73aca97a96bc 100644
--- a/drivers/net/ethernet/broadcom/bgmac-platform.c
+++ b/drivers/net/ethernet/broadcom/bgmac-platform.c
@@ -21,8 +21,12 @@
 #include <linux/of_net.h>
 #include "bgmac.h"
 
+#define NICPM_PADRING_CFG		0x00000004
 #define NICPM_IOMUX_CTRL		0x00000008
 
+#define NICPM_PADRING_CFG_INIT_VAL	0x74000000
+#define NICPM_IOMUX_CTRL_INIT_VAL_AX	0x21880000
+
 #define NICPM_IOMUX_CTRL_INIT_VAL	0x3196e000
 #define NICPM_IOMUX_CTRL_SPD_SHIFT	10
 #define NICPM_IOMUX_CTRL_SPD_10M	0
@@ -113,6 +117,10 @@ static void bgmac_nicpm_speed_set(struct net_device *net_dev)
 	if (!bgmac->plat.nicpm_base)
 		return;
 
+	/* SET RGMII IO CONFIG */
+	writel(NICPM_PADRING_CFG_INIT_VAL,
+	       bgmac->plat.nicpm_base + NICPM_PADRING_CFG);
+
 	val = NICPM_IOMUX_CTRL_INIT_VAL;
 	switch (bgmac->net_dev->phydev->speed) {
 	default:
@@ -244,6 +252,31 @@ static int bgmac_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM
+static int bgmac_suspend(struct device *dev)
+{
+	struct bgmac *bgmac = dev_get_drvdata(dev);
+
+	return bgmac_enet_suspend(bgmac);
+}
+
+static int bgmac_resume(struct device *dev)
+{
+	struct bgmac *bgmac = dev_get_drvdata(dev);
+
+	return bgmac_enet_resume(bgmac);
+}
+
+static const struct dev_pm_ops bgmac_pm_ops = {
+	.suspend = bgmac_suspend,
+	.resume = bgmac_resume
+};
+
+#define BGMAC_PM_OPS (&bgmac_pm_ops)
+#else
+#define BGMAC_PM_OPS NULL
+#endif /* CONFIG_PM */
+
 static const struct of_device_id bgmac_of_enet_match[] = {
 	{.compatible = "brcm,amac",},
 	{.compatible = "brcm,nsp-amac",},
@@ -257,6 +290,7 @@ static struct platform_driver bgmac_enet_driver = {
 	.driver = {
 		.name  = "bgmac-enet",
 		.of_match_table = bgmac_of_enet_match,
+		.pm = BGMAC_PM_OPS
 	},
 	.probe = bgmac_probe,
 	.remove = bgmac_remove,
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index fd66fca00e01..ba4d2e145bb9 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -11,6 +11,7 @@
 
 #include <linux/bcma/bcma.h>
 #include <linux/etherdevice.h>
+#include <linux/interrupt.h>
 #include <linux/bcm47xx_nvram.h>
 #include <linux/phy.h>
 #include <linux/phy_fixed.h>
@@ -1480,6 +1481,7 @@ int bgmac_enet_probe(struct bgmac *bgmac)
 
 	net_dev->irq = bgmac->irq;
 	SET_NETDEV_DEV(net_dev, bgmac->dev);
+	dev_set_drvdata(bgmac->dev, bgmac);
 
 	if (!is_valid_ether_addr(net_dev->dev_addr)) {
 		dev_err(bgmac->dev, "Invalid MAC addr: %pM\n",
@@ -1552,5 +1554,55 @@ void bgmac_enet_remove(struct bgmac *bgmac)
 }
 EXPORT_SYMBOL_GPL(bgmac_enet_remove);
 
+int bgmac_enet_suspend(struct bgmac *bgmac)
+{
+	if (!netif_running(bgmac->net_dev))
+		return 0;
+
+	phy_stop(bgmac->net_dev->phydev);
+
+	netif_stop_queue(bgmac->net_dev);
+
+	napi_disable(&bgmac->napi);
+
+	netif_tx_lock(bgmac->net_dev);
+	netif_device_detach(bgmac->net_dev);
+	netif_tx_unlock(bgmac->net_dev);
+
+	bgmac_chip_intrs_off(bgmac);
+	bgmac_chip_reset(bgmac);
+	bgmac_dma_cleanup(bgmac);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bgmac_enet_suspend);
+
+int bgmac_enet_resume(struct bgmac *bgmac)
+{
+	int rc;
+
+	if (!netif_running(bgmac->net_dev))
+		return 0;
+
+	rc = bgmac_dma_init(bgmac);
+	if (rc)
+		return rc;
+
+	bgmac_chip_init(bgmac);
+
+	napi_enable(&bgmac->napi);
+
+	netif_tx_lock(bgmac->net_dev);
+	netif_device_attach(bgmac->net_dev);
+	netif_tx_unlock(bgmac->net_dev);
+
+	netif_start_queue(bgmac->net_dev);
+
+	phy_start(bgmac->net_dev->phydev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bgmac_enet_resume);
+
 MODULE_AUTHOR("Rafał Miłecki");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h
index 6d1c6ff1ed96..c1818766c501 100644
--- a/drivers/net/ethernet/broadcom/bgmac.h
+++ b/drivers/net/ethernet/broadcom/bgmac.h
@@ -402,7 +402,7 @@
 
 #define BGMAC_WEIGHT	64
 
-#define ETHER_MAX_LEN   1518
+#define ETHER_MAX_LEN	(ETH_FRAME_LEN + ETH_FCS_LEN)
 
 /* Feature Flags */
 #define BGMAC_FEAT_TX_MASK_SETUP	BIT(0)
@@ -537,6 +537,8 @@ int bgmac_enet_probe(struct bgmac *bgmac);
 void bgmac_enet_remove(struct bgmac *bgmac);
 void bgmac_adjust_link(struct net_device *net_dev);
 int bgmac_phy_connect_direct(struct bgmac *bgmac);
+int bgmac_enet_suspend(struct bgmac *bgmac);
+int bgmac_enet_resume(struct bgmac *bgmac);
 
 struct mii_bus *bcma_mdio_mii_register(struct bgmac *bgmac);
 void bcma_mdio_mii_unregister(struct mii_bus *mii_bus);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 9e8c06130c09..ad3e0631877e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -4277,7 +4277,10 @@ int __bnx2x_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
 {
 	if (tc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
-	return bnx2x_setup_tc(dev, tc->tc);
+
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+	return bnx2x_setup_tc(dev, tc->mqprio->num_tc);
 }
 
 /* called with rtnl_lock */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 1f1e54ba0ecb..129b8101b932 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4549,6 +4549,9 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		pf->max_tx_wm_flows = le32_to_cpu(resp->max_tx_wm_flows);
 		pf->max_rx_em_flows = le32_to_cpu(resp->max_rx_em_flows);
 		pf->max_rx_wm_flows = le32_to_cpu(resp->max_rx_wm_flows);
+		if (resp->flags &
+		    cpu_to_le32(FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED))
+			bp->flags |= BNXT_FLAG_WOL_CAP;
 	} else {
 #ifdef CONFIG_BNXT_SRIOV
 		struct bnxt_vf_info *vf = &bp->vf;
@@ -5198,9 +5201,10 @@ static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
 {
 #if defined(CONFIG_BNXT_SRIOV)
 	if (BNXT_VF(bp))
-		return bp->vf.max_irqs;
+		return min_t(unsigned int, bp->vf.max_irqs,
+			     bp->vf.max_cp_rings);
 #endif
-	return bp->pf.max_irqs;
+	return min_t(unsigned int, bp->pf.max_irqs, bp->pf.max_cp_rings);
 }
 
 void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs)
@@ -5857,6 +5861,76 @@ static int bnxt_hwrm_port_led_qcaps(struct bnxt *bp)
 	return 0;
 }
 
+int bnxt_hwrm_alloc_wol_fltr(struct bnxt *bp)
+{
+	struct hwrm_wol_filter_alloc_input req = {0};
+	struct hwrm_wol_filter_alloc_output *resp = bp->hwrm_cmd_resp_addr;
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_WOL_FILTER_ALLOC, -1, -1);
+	req.port_id = cpu_to_le16(bp->pf.port_id);
+	req.wol_type = WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT;
+	req.enables = cpu_to_le32(WOL_FILTER_ALLOC_REQ_ENABLES_MAC_ADDRESS);
+	memcpy(req.mac_address, bp->dev->dev_addr, ETH_ALEN);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
+		bp->wol_filter_id = resp->wol_filter_id;
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
+int bnxt_hwrm_free_wol_fltr(struct bnxt *bp)
+{
+	struct hwrm_wol_filter_free_input req = {0};
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_WOL_FILTER_FREE, -1, -1);
+	req.port_id = cpu_to_le16(bp->pf.port_id);
+	req.enables = cpu_to_le32(WOL_FILTER_FREE_REQ_ENABLES_WOL_FILTER_ID);
+	req.wol_filter_id = bp->wol_filter_id;
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	return rc;
+}
+
+static u16 bnxt_hwrm_get_wol_fltrs(struct bnxt *bp, u16 handle)
+{
+	struct hwrm_wol_filter_qcfg_input req = {0};
+	struct hwrm_wol_filter_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
+	u16 next_handle = 0;
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_WOL_FILTER_QCFG, -1, -1);
+	req.port_id = cpu_to_le16(bp->pf.port_id);
+	req.handle = cpu_to_le16(handle);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc) {
+		next_handle = le16_to_cpu(resp->next_handle);
+		if (next_handle != 0) {
+			if (resp->wol_type ==
+			    WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT) {
+				bp->wol = 1;
+				bp->wol_filter_id = resp->wol_filter_id;
+			}
+		}
+	}
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return next_handle;
+}
+
+static void bnxt_get_wol_settings(struct bnxt *bp)
+{
+	u16 handle = 0;
+
+	if (!BNXT_PF(bp) || !(bp->flags & BNXT_FLAG_WOL_CAP))
+		return;
+
+	do {
+		handle = bnxt_hwrm_get_wol_fltrs(bp, handle);
+	} while (handle && handle != 0xffff);
+}
+
 static bool bnxt_eee_config_ok(struct bnxt *bp)
 {
 	struct ethtool_eee *eee = &bp->eee;
@@ -6042,6 +6116,43 @@ int bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	return rc;
 }
 
+/* rtnl_lock held, open the NIC half way by allocating all resources, but
+ * NAPI, IRQ, and TX are not enabled.  This is mainly used for offline
+ * self tests.
+ */
+int bnxt_half_open_nic(struct bnxt *bp)
+{
+	int rc = 0;
+
+	rc = bnxt_alloc_mem(bp, false);
+	if (rc) {
+		netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);
+		goto half_open_err;
+	}
+	rc = bnxt_init_nic(bp, false);
+	if (rc) {
+		netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc);
+		goto half_open_err;
+	}
+	return 0;
+
+half_open_err:
+	bnxt_free_skbs(bp);
+	bnxt_free_mem(bp, false);
+	dev_close(bp->dev);
+	return rc;
+}
+
+/* rtnl_lock held, this call can only be made after a previous successful
+ * call to bnxt_half_open_nic().
+ */
+void bnxt_half_close_nic(struct bnxt *bp)
+{
+	bnxt_hwrm_resource_free(bp, false, false);
+	bnxt_free_skbs(bp);
+	bnxt_free_mem(bp, false);
+}
+
 static int bnxt_open(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
@@ -6923,7 +7034,9 @@ static int bnxt_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
 	if (ntc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
-	return bnxt_setup_mq_tc(dev, ntc->tc);
+	ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+	return bnxt_setup_mq_tc(dev, ntc->mqprio->num_tc);
 }
 
 #ifdef CONFIG_RFS_ACCEL
@@ -7224,6 +7337,7 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	bnxt_clear_int_mode(bp);
 	bnxt_hwrm_func_drv_unrgtr(bp);
 	bnxt_free_hwrm_resources(bp);
+	bnxt_ethtool_free(bp);
 	bnxt_dcb_free(bp);
 	kfree(bp->edev);
 	bp->edev = NULL;
@@ -7546,6 +7660,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	bnxt_hwrm_func_qcfg(bp);
 	bnxt_hwrm_port_led_qcaps(bp);
+	bnxt_ethtool_init(bp);
 
 	bnxt_set_rx_skb_mode(bp, false);
 	bnxt_set_tpa_flags(bp);
@@ -7591,6 +7706,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err_pci_clean;
 
+	bnxt_get_wol_settings(bp);
+	if (bp->flags & BNXT_FLAG_WOL_CAP)
+		device_set_wakeup_enable(&pdev->dev, bp->wol);
+	else
+		device_set_wakeup_capable(&pdev->dev, false);
+
 	rc = register_netdev(dev);
 	if (rc)
 		goto init_err_clr_int;
@@ -7614,6 +7735,88 @@ init_err_free:
 	return rc;
 }
 
+static void bnxt_shutdown(struct pci_dev *pdev)
+{
+	struct net_device *dev = pci_get_drvdata(pdev);
+	struct bnxt *bp;
+
+	if (!dev)
+		return;
+
+	rtnl_lock();
+	bp = netdev_priv(dev);
+	if (!bp)
+		goto shutdown_exit;
+
+	if (netif_running(dev))
+		dev_close(dev);
+
+	if (system_state == SYSTEM_POWER_OFF) {
+		bnxt_clear_int_mode(bp);
+		pci_wake_from_d3(pdev, bp->wol);
+		pci_set_power_state(pdev, PCI_D3hot);
+	}
+
+shutdown_exit:
+	rtnl_unlock();
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int bnxt_suspend(struct device *device)
+{
+	struct pci_dev *pdev = to_pci_dev(device);
+	struct net_device *dev = pci_get_drvdata(pdev);
+	struct bnxt *bp = netdev_priv(dev);
+	int rc = 0;
+
+	rtnl_lock();
+	if (netif_running(dev)) {
+		netif_device_detach(dev);
+		rc = bnxt_close(dev);
+	}
+	bnxt_hwrm_func_drv_unrgtr(bp);
+	rtnl_unlock();
+	return rc;
+}
+
+static int bnxt_resume(struct device *device)
+{
+	struct pci_dev *pdev = to_pci_dev(device);
+	struct net_device *dev = pci_get_drvdata(pdev);
+	struct bnxt *bp = netdev_priv(dev);
+	int rc = 0;
+
+	rtnl_lock();
+	if (bnxt_hwrm_ver_get(bp) || bnxt_hwrm_func_drv_rgtr(bp)) {
+		rc = -ENODEV;
+		goto resume_exit;
+	}
+	rc = bnxt_hwrm_func_reset(bp);
+	if (rc) {
+		rc = -EBUSY;
+		goto resume_exit;
+	}
+	bnxt_get_wol_settings(bp);
+	if (netif_running(dev)) {
+		rc = bnxt_open(dev);
+		if (!rc)
+			netif_device_attach(dev);
+	}
+
+resume_exit:
+	rtnl_unlock();
+	return rc;
+}
+
+static SIMPLE_DEV_PM_OPS(bnxt_pm_ops, bnxt_suspend, bnxt_resume);
+#define BNXT_PM_OPS (&bnxt_pm_ops)
+
+#else
+
+#define BNXT_PM_OPS NULL
+
+#endif /* CONFIG_PM_SLEEP */
+
 /**
  * bnxt_io_error_detected - called when PCI error is detected
  * @pdev: Pointer to PCI device
@@ -7730,6 +7933,8 @@ static struct pci_driver bnxt_pci_driver = {
 	.id_table	= bnxt_pci_tbl,
 	.probe		= bnxt_init_one,
 	.remove		= bnxt_remove_one,
+	.shutdown	= bnxt_shutdown,
+	.driver.pm	= BNXT_PM_OPS,
 	.err_handler	= &bnxt_err_handler,
 #if defined(CONFIG_BNXT_SRIOV)
 	.sriov_configure = bnxt_sriov_configure,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index c7a5b84a5cb2..c9a1688a65de 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -18,6 +18,8 @@
 #define DRV_VER_MIN	7
 #define DRV_VER_UPD	0
 
+#include <linux/interrupt.h>
+
 struct tx_bd {
 	__le32 tx_bd_len_flags_type;
 	#define TX_BD_TYPE					(0x3f << 0)
@@ -424,8 +426,6 @@ struct rx_tpa_end_cmp_ext {
 
 #define BNXT_MIN_PKT_SIZE	52
 
-#define BNXT_NUM_TESTS(bp)	0
-
 #define BNXT_DEFAULT_RX_RING_SIZE	511
 #define BNXT_DEFAULT_TX_RING_SIZE	511
 
@@ -909,6 +909,14 @@ struct bnxt_led_info {
 	__le16	led_color_caps;
 };
 
+#define BNXT_MAX_TEST	8
+
+struct bnxt_test_info {
+	u8 offline_mask;
+	u16 timeout;
+	char string[BNXT_MAX_TEST][ETH_GSTRING_LEN];
+};
+
 #define BNXT_GRCPF_REG_WINDOW_BASE_OUT	0x400
 #define BNXT_CAG_REG_LEGACY_INT_STATUS	0x4014
 #define BNXT_CAG_REG_BASE		0x300000
@@ -987,6 +995,7 @@ struct bnxt {
 	#define BNXT_FLAG_UDP_RSS_CAP	0x800
 	#define BNXT_FLAG_EEE_CAP	0x1000
 	#define BNXT_FLAG_NEW_RSS_CAP	0x2000
+	#define BNXT_FLAG_WOL_CAP	0x4000
 	#define BNXT_FLAG_ROCEV1_CAP	0x8000
 	#define BNXT_FLAG_ROCEV2_CAP	0x10000
 	#define BNXT_FLAG_ROCE_CAP	(BNXT_FLAG_ROCEV1_CAP |	\
@@ -1178,6 +1187,12 @@ struct bnxt {
 	u32			lpi_tmr_lo;
 	u32			lpi_tmr_hi;
 
+	u8			num_tests;
+	struct bnxt_test_info	*test_info;
+
+	u8			wol_filter_id;
+	u8			wol;
+
 	u8			num_leds;
 	struct bnxt_led_info	leds[BNXT_MAX_LED];
 
@@ -1236,8 +1251,12 @@ void bnxt_tx_disable(struct bnxt *bp);
 void bnxt_tx_enable(struct bnxt *bp);
 int bnxt_hwrm_set_pause(struct bnxt *);
 int bnxt_hwrm_set_link_setting(struct bnxt *, bool, bool);
+int bnxt_hwrm_alloc_wol_fltr(struct bnxt *bp);
+int bnxt_hwrm_free_wol_fltr(struct bnxt *bp);
 int bnxt_hwrm_fw_set_time(struct bnxt *);
 int bnxt_open_nic(struct bnxt *, bool, bool);
+int bnxt_half_open_nic(struct bnxt *bp);
+void bnxt_half_close_nic(struct bnxt *bp);
 int bnxt_close_nic(struct bnxt *, bool, bool);
 int bnxt_reserve_rings(struct bnxt *bp, int tx, int rx, int tcs, int tx_xdp);
 int bnxt_setup_mq_tc(struct net_device *dev, u8 tc);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 6903a873f072..848ecf212b8f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1,6 +1,7 @@
 /* Broadcom NetXtreme-C/E network driver.
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
+ * Copyright (c) 2016-2017 Broadcom Limited
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -17,6 +18,7 @@
 #include <linux/firmware.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
+#include "bnxt_xdp.h"
 #include "bnxt_ethtool.h"
 #include "bnxt_nvm_defs.h"	/* NVRAM content constant and structure defs */
 #include "bnxt_fw_hdr.h"	/* Firmware hdr constant and structure defs */
@@ -209,6 +211,10 @@ static int bnxt_get_sset_count(struct net_device *dev, int sset)
 
 		return num_stats;
 	}
+	case ETH_SS_TEST:
+		if (!bp->num_tests)
+			return -EOPNOTSUPP;
+		return bp->num_tests;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -306,6 +312,11 @@ static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
 			}
 		}
 		break;
+	case ETH_SS_TEST:
+		if (bp->num_tests)
+			memcpy(buf, bp->test_info->string,
+			       bp->num_tests * ETH_GSTRING_LEN);
+		break;
 	default:
 		netdev_err(bp->dev, "bnxt_get_strings invalid request %x\n",
 			   stringset);
@@ -824,7 +835,7 @@ static void bnxt_get_drvinfo(struct net_device *dev,
 			sizeof(info->fw_version));
 	strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info));
 	info->n_stats = BNXT_NUM_STATS * bp->cp_nr_rings;
-	info->testinfo_len = BNXT_NUM_TESTS(bp);
+	info->testinfo_len = bp->num_tests;
 	/* TODO CHIMP_FW: eeprom dump details */
 	info->eedump_len = 0;
 	/* TODO CHIMP FW: reg dump details */
@@ -832,6 +843,45 @@ static void bnxt_get_drvinfo(struct net_device *dev,
 	kfree(pkglog);
 }
 
+static void bnxt_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	wol->supported = 0;
+	wol->wolopts = 0;
+	memset(&wol->sopass, 0, sizeof(wol->sopass));
+	if (bp->flags & BNXT_FLAG_WOL_CAP) {
+		wol->supported = WAKE_MAGIC;
+		if (bp->wol)
+			wol->wolopts = WAKE_MAGIC;
+	}
+}
+
+static int bnxt_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	if (wol->wolopts & ~WAKE_MAGIC)
+		return -EINVAL;
+
+	if (wol->wolopts & WAKE_MAGIC) {
+		if (!(bp->flags & BNXT_FLAG_WOL_CAP))
+			return -EINVAL;
+		if (!bp->wol) {
+			if (bnxt_hwrm_alloc_wol_fltr(bp))
+				return -EBUSY;
+			bp->wol = 1;
+		}
+	} else {
+		if (bp->wol) {
+			if (bnxt_hwrm_free_wol_fltr(bp))
+				return -EBUSY;
+			bp->wol = 0;
+		}
+	}
+	return 0;
+}
+
 u32 _bnxt_fw_to_ethtool_adv_spds(u16 fw_speeds, u8 fw_pause)
 {
 	u32 speed_mask = 0;
@@ -2128,12 +2178,372 @@ static int bnxt_set_phys_id(struct net_device *dev,
 	return rc;
 }
 
+static int bnxt_hwrm_selftest_irq(struct bnxt *bp, u16 cmpl_ring)
+{
+	struct hwrm_selftest_irq_input req = {0};
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_SELFTEST_IRQ, cmpl_ring, -1);
+	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
+static int bnxt_test_irq(struct bnxt *bp)
+{
+	int i;
+
+	for (i = 0; i < bp->cp_nr_rings; i++) {
+		u16 cmpl_ring = bp->grp_info[i].cp_fw_ring_id;
+		int rc;
+
+		rc = bnxt_hwrm_selftest_irq(bp, cmpl_ring);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
+static int bnxt_hwrm_mac_loopback(struct bnxt *bp, bool enable)
+{
+	struct hwrm_port_mac_cfg_input req = {0};
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_MAC_CFG, -1, -1);
+
+	req.enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_LPBK);
+	if (enable)
+		req.lpbk = PORT_MAC_CFG_REQ_LPBK_LOCAL;
+	else
+		req.lpbk = PORT_MAC_CFG_REQ_LPBK_NONE;
+	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
+static int bnxt_disable_an_for_lpbk(struct bnxt *bp,
+				    struct hwrm_port_phy_cfg_input *req)
+{
+	struct bnxt_link_info *link_info = &bp->link_info;
+	u16 fw_advertising = link_info->advertising;
+	u16 fw_speed;
+	int rc;
+
+	if (!link_info->autoneg)
+		return 0;
+
+	fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_1GB;
+	if (netif_carrier_ok(bp->dev))
+		fw_speed = bp->link_info.link_speed;
+	else if (fw_advertising & BNXT_LINK_SPEED_MSK_10GB)
+		fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10GB;
+	else if (fw_advertising & BNXT_LINK_SPEED_MSK_25GB)
+		fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_25GB;
+	else if (fw_advertising & BNXT_LINK_SPEED_MSK_40GB)
+		fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_40GB;
+	else if (fw_advertising & BNXT_LINK_SPEED_MSK_50GB)
+		fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_50GB;
+
+	req->force_link_speed = cpu_to_le16(fw_speed);
+	req->flags |= cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_FORCE |
+				  PORT_PHY_CFG_REQ_FLAGS_RESET_PHY);
+	rc = hwrm_send_message(bp, req, sizeof(*req), HWRM_CMD_TIMEOUT);
+	req->flags = 0;
+	req->force_link_speed = cpu_to_le16(0);
+	return rc;
+}
+
+static int bnxt_hwrm_phy_loopback(struct bnxt *bp, bool enable)
+{
+	struct hwrm_port_phy_cfg_input req = {0};
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_CFG, -1, -1);
+
+	if (enable) {
+		bnxt_disable_an_for_lpbk(bp, &req);
+		req.lpbk = PORT_PHY_CFG_REQ_LPBK_LOCAL;
+	} else {
+		req.lpbk = PORT_PHY_CFG_REQ_LPBK_NONE;
+	}
+	req.enables = cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_LPBK);
+	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
+static int bnxt_rx_loopback(struct bnxt *bp, struct bnxt_napi *bnapi,
+			    u32 raw_cons, int pkt_size)
+{
+	struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
+	struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
+	struct bnxt_sw_rx_bd *rx_buf;
+	struct rx_cmp *rxcmp;
+	u16 cp_cons, cons;
+	u8 *data;
+	u32 len;
+	int i;
+
+	cp_cons = RING_CMP(raw_cons);
+	rxcmp = (struct rx_cmp *)
+		&cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)];
+	cons = rxcmp->rx_cmp_opaque;
+	rx_buf = &rxr->rx_buf_ring[cons];
+	data = rx_buf->data_ptr;
+	len = le32_to_cpu(rxcmp->rx_cmp_len_flags_type) >> RX_CMP_LEN_SHIFT;
+	if (len != pkt_size)
+		return -EIO;
+	i = ETH_ALEN;
+	if (!ether_addr_equal(data + i, bnapi->bp->dev->dev_addr))
+		return -EIO;
+	i += ETH_ALEN;
+	for (  ; i < pkt_size; i++) {
+		if (data[i] != (u8)(i & 0xff))
+			return -EIO;
+	}
+	return 0;
+}
+
+static int bnxt_poll_loopback(struct bnxt *bp, int pkt_size)
+{
+	struct bnxt_napi *bnapi = bp->bnapi[0];
+	struct bnxt_cp_ring_info *cpr;
+	struct tx_cmp *txcmp;
+	int rc = -EIO;
+	u32 raw_cons;
+	u32 cons;
+	int i;
+
+	cpr = &bnapi->cp_ring;
+	raw_cons = cpr->cp_raw_cons;
+	for (i = 0; i < 200; i++) {
+		cons = RING_CMP(raw_cons);
+		txcmp = &cpr->cp_desc_ring[CP_RING(cons)][CP_IDX(cons)];
+
+		if (!TX_CMP_VALID(txcmp, raw_cons)) {
+			udelay(5);
+			continue;
+		}
+
+		/* The valid test of the entry must be done first before
+		 * reading any further.
+		 */
+		dma_rmb();
+		if (TX_CMP_TYPE(txcmp) == CMP_TYPE_RX_L2_CMP) {
+			rc = bnxt_rx_loopback(bp, bnapi, raw_cons, pkt_size);
+			raw_cons = NEXT_RAW_CMP(raw_cons);
+			raw_cons = NEXT_RAW_CMP(raw_cons);
+			break;
+		}
+		raw_cons = NEXT_RAW_CMP(raw_cons);
+	}
+	cpr->cp_raw_cons = raw_cons;
+	return rc;
+}
+
+static int bnxt_run_loopback(struct bnxt *bp)
+{
+	struct bnxt_tx_ring_info *txr = &bp->tx_ring[0];
+	int pkt_size, i = 0;
+	struct sk_buff *skb;
+	dma_addr_t map;
+	u8 *data;
+	int rc;
+
+	pkt_size = min(bp->dev->mtu + ETH_HLEN, bp->rx_copy_thresh);
+	skb = netdev_alloc_skb(bp->dev, pkt_size);
+	if (!skb)
+		return -ENOMEM;
+	data = skb_put(skb, pkt_size);
+	eth_broadcast_addr(data);
+	i += ETH_ALEN;
+	ether_addr_copy(&data[i], bp->dev->dev_addr);
+	i += ETH_ALEN;
+	for ( ; i < pkt_size; i++)
+		data[i] = (u8)(i & 0xff);
+
+	map = dma_map_single(&bp->pdev->dev, skb->data, pkt_size,
+			     PCI_DMA_TODEVICE);
+	if (dma_mapping_error(&bp->pdev->dev, map)) {
+		dev_kfree_skb(skb);
+		return -EIO;
+	}
+	bnxt_xmit_xdp(bp, txr, map, pkt_size, 0);
+
+	/* Sync BD data before updating doorbell */
+	wmb();
+
+	writel(DB_KEY_TX | txr->tx_prod, txr->tx_doorbell);
+	writel(DB_KEY_TX | txr->tx_prod, txr->tx_doorbell);
+	rc = bnxt_poll_loopback(bp, pkt_size);
+
+	dma_unmap_single(&bp->pdev->dev, map, pkt_size, PCI_DMA_TODEVICE);
+	dev_kfree_skb(skb);
+	return rc;
+}
+
+static int bnxt_run_fw_tests(struct bnxt *bp, u8 test_mask, u8 *test_results)
+{
+	struct hwrm_selftest_exec_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_selftest_exec_input req = {0};
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_SELFTEST_EXEC, -1, -1);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	resp->test_success = 0;
+	req.flags = test_mask;
+	rc = _hwrm_send_message(bp, &req, sizeof(req), bp->test_info->timeout);
+	*test_results = resp->test_success;
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
+#define BNXT_DRV_TESTS			3
+#define BNXT_MACLPBK_TEST_IDX		(bp->num_tests - BNXT_DRV_TESTS)
+#define BNXT_PHYLPBK_TEST_IDX		(BNXT_MACLPBK_TEST_IDX + 1)
+#define BNXT_IRQ_TEST_IDX		(BNXT_MACLPBK_TEST_IDX + 2)
+
+static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
+			   u64 *buf)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	bool offline = false;
+	u8 test_results = 0;
+	u8 test_mask = 0;
+	int rc, i;
+
+	if (!bp->num_tests || !BNXT_SINGLE_PF(bp))
+		return;
+	memset(buf, 0, sizeof(u64) * bp->num_tests);
+	if (!netif_running(dev)) {
+		etest->flags |= ETH_TEST_FL_FAILED;
+		return;
+	}
+
+	if (etest->flags & ETH_TEST_FL_OFFLINE) {
+		if (bp->pf.active_vfs) {
+			etest->flags |= ETH_TEST_FL_FAILED;
+			netdev_warn(dev, "Offline tests cannot be run with active VFs\n");
+			return;
+		}
+		offline = true;
+	}
+
+	for (i = 0; i < bp->num_tests - BNXT_DRV_TESTS; i++) {
+		u8 bit_val = 1 << i;
+
+		if (!(bp->test_info->offline_mask & bit_val))
+			test_mask |= bit_val;
+		else if (offline)
+			test_mask |= bit_val;
+	}
+	if (!offline) {
+		bnxt_run_fw_tests(bp, test_mask, &test_results);
+	} else {
+		rc = bnxt_close_nic(bp, false, false);
+		if (rc)
+			return;
+		bnxt_run_fw_tests(bp, test_mask, &test_results);
+
+		buf[BNXT_MACLPBK_TEST_IDX] = 1;
+		bnxt_hwrm_mac_loopback(bp, true);
+		msleep(250);
+		rc = bnxt_half_open_nic(bp);
+		if (rc) {
+			bnxt_hwrm_mac_loopback(bp, false);
+			etest->flags |= ETH_TEST_FL_FAILED;
+			return;
+		}
+		if (bnxt_run_loopback(bp))
+			etest->flags |= ETH_TEST_FL_FAILED;
+		else
+			buf[BNXT_MACLPBK_TEST_IDX] = 0;
+
+		bnxt_hwrm_mac_loopback(bp, false);
+		bnxt_hwrm_phy_loopback(bp, true);
+		msleep(1000);
+		if (bnxt_run_loopback(bp)) {
+			buf[BNXT_PHYLPBK_TEST_IDX] = 1;
+			etest->flags |= ETH_TEST_FL_FAILED;
+		}
+		bnxt_hwrm_phy_loopback(bp, false);
+		bnxt_half_close_nic(bp);
+		bnxt_open_nic(bp, false, true);
+	}
+	if (bnxt_test_irq(bp)) {
+		buf[BNXT_IRQ_TEST_IDX] = 1;
+		etest->flags |= ETH_TEST_FL_FAILED;
+	}
+	for (i = 0; i < bp->num_tests - BNXT_DRV_TESTS; i++) {
+		u8 bit_val = 1 << i;
+
+		if ((test_mask & bit_val) && !(test_results & bit_val)) {
+			buf[i] = 1;
+			etest->flags |= ETH_TEST_FL_FAILED;
+		}
+	}
+}
+
+void bnxt_ethtool_init(struct bnxt *bp)
+{
+	struct hwrm_selftest_qlist_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_selftest_qlist_input req = {0};
+	struct bnxt_test_info *test_info;
+	int i, rc;
+
+	if (bp->hwrm_spec_code < 0x10704 || !BNXT_SINGLE_PF(bp))
+		return;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_SELFTEST_QLIST, -1, -1);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		goto ethtool_init_exit;
+
+	test_info = kzalloc(sizeof(*bp->test_info), GFP_KERNEL);
+	if (!test_info)
+		goto ethtool_init_exit;
+
+	bp->test_info = test_info;
+	bp->num_tests = resp->num_tests + BNXT_DRV_TESTS;
+	if (bp->num_tests > BNXT_MAX_TEST)
+		bp->num_tests = BNXT_MAX_TEST;
+
+	test_info->offline_mask = resp->offline_tests;
+	test_info->timeout = le16_to_cpu(resp->test_timeout);
+	if (!test_info->timeout)
+		test_info->timeout = HWRM_CMD_TIMEOUT;
+	for (i = 0; i < bp->num_tests; i++) {
+		char *str = test_info->string[i];
+		char *fw_str = resp->test0_name + i * 32;
+
+		if (i == BNXT_MACLPBK_TEST_IDX) {
+			strcpy(str, "Mac loopback test (offline)");
+		} else if (i == BNXT_PHYLPBK_TEST_IDX) {
+			strcpy(str, "Phy loopback test (offline)");
+		} else if (i == BNXT_IRQ_TEST_IDX) {
+			strcpy(str, "Interrupt_test (offline)");
+		} else {
+			strlcpy(str, fw_str, ETH_GSTRING_LEN);
+			strncat(str, " test", ETH_GSTRING_LEN - strlen(str));
+			if (test_info->offline_mask & (1 << i))
+				strncat(str, " (offline)",
+					ETH_GSTRING_LEN - strlen(str));
+			else
+				strncat(str, " (online)",
+					ETH_GSTRING_LEN - strlen(str));
+		}
+	}
+
+ethtool_init_exit:
+	mutex_unlock(&bp->hwrm_cmd_lock);
+}
+
+void bnxt_ethtool_free(struct bnxt *bp)
+{
+	kfree(bp->test_info);
+	bp->test_info = NULL;
+}
+
 const struct ethtool_ops bnxt_ethtool_ops = {
 	.get_link_ksettings	= bnxt_get_link_ksettings,
 	.set_link_ksettings	= bnxt_set_link_ksettings,
 	.get_pauseparam		= bnxt_get_pauseparam,
 	.set_pauseparam		= bnxt_set_pauseparam,
 	.get_drvinfo		= bnxt_get_drvinfo,
+	.get_wol		= bnxt_get_wol,
+	.set_wol		= bnxt_set_wol,
 	.get_coalesce		= bnxt_get_coalesce,
 	.set_coalesce		= bnxt_set_coalesce,
 	.get_msglevel		= bnxt_get_msglevel,
@@ -2161,4 +2571,5 @@ const struct ethtool_ops bnxt_ethtool_ops = {
 	.get_module_eeprom	= bnxt_get_module_eeprom,
 	.nway_reset		= bnxt_nway_reset,
 	.set_phys_id		= bnxt_set_phys_id,
+	.self_test		= bnxt_self_test,
 };
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
index ed1e555292e9..f1bc90b6fb5b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
@@ -1,6 +1,7 @@
 /* Broadcom NetXtreme-C/E network driver.
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
+ * Copyright (c) 2016-2017 Broadcom Limited
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -38,5 +39,7 @@ extern const struct ethtool_ops bnxt_ethtool_ops;
 u32 _bnxt_fw_to_ethtool_adv_spds(u16, u8);
 u32 bnxt_fw_to_ethtool_speed(u16);
 u16 bnxt_get_fw_auto_link_speeds(u32);
+void bnxt_ethtool_init(struct bnxt *bp);
+void bnxt_ethtool_free(struct bnxt *bp);
 
 #endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 6e275c23d68b..7dc71bb95837 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -11,19 +11,21 @@
 #ifndef BNXT_HSI_H
 #define BNXT_HSI_H
 
-/* HSI and HWRM Specification 1.7.0 */
+/* HSI and HWRM Specification 1.7.6 */
 #define HWRM_VERSION_MAJOR	1
 #define HWRM_VERSION_MINOR	7
-#define HWRM_VERSION_UPDATE	0
+#define HWRM_VERSION_UPDATE	6
 
-#define HWRM_VERSION_STR	"1.7.0"
+#define HWRM_VERSION_RSVD	2 /* non-zero means beta version */
+
+#define HWRM_VERSION_STR	"1.7.6.2"
 /*
  * Following is the signature for HWRM message field that indicates not
  * applicable (All F's). Need to cast it the size of the field if needed.
  */
 #define HWRM_NA_SIGNATURE	((__le32)(-1))
 #define HWRM_MAX_REQ_LEN    (128)  /* hwrm_func_buf_rgtr */
-#define HWRM_MAX_RESP_LEN    (176)  /* hwrm_func_qstats */
+#define HWRM_MAX_RESP_LEN    (248)  /* hwrm_selftest_qlist */
 #define HW_HASH_INDEX_SIZE      0x80    /* 7 bit indirection table index. */
 #define HW_HASH_KEY_SIZE	40
 #define HWRM_RESP_VALID_KEY      1 /* valid key for HWRM response */
@@ -571,9 +573,10 @@ struct hwrm_ver_get_output {
 	__le16 max_req_win_len;
 	__le16 max_resp_len;
 	__le16 def_req_timeout;
+	u8 init_pending;
+	#define VER_GET_RESP_INIT_PENDING_DEV_NOT_RDY		    0x1UL
 	u8 unused_0;
 	u8 unused_1;
-	u8 unused_2;
 	u8 valid;
 };
 
@@ -809,6 +812,8 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_FLAGS_OOB_WOL_BMP_ENABLED	    0x2UL
 	#define FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED	    0x4UL
 	#define FUNC_QCFG_RESP_FLAGS_STD_TX_RING_MODE_ENABLED      0x8UL
+	#define FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED	    0x10UL
+	#define FUNC_QCFG_RESP_FLAGS_MULTI_HOST			    0x20UL
 	u8 mac_address[6];
 	__le16 pci_id;
 	__le16 alloc_rsscos_ctx;
@@ -827,10 +832,12 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5	   0x3UL
 	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR2_0	   0x4UL
 	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_UNKNOWN	   0xffUL
-	u8 unused_0;
+	u8 port_pf_cnt;
+	#define FUNC_QCFG_RESP_PORT_PF_CNT_UNAVAIL		   0x0UL
 	__le16 dflt_vnic_id;
-	u8 unused_1;
-	u8 unused_2;
+	u8 host_cnt;
+	#define FUNC_QCFG_RESP_HOST_CNT_UNAVAIL		   0x0UL
+	u8 unused_0;
 	__le32 min_bw;
 	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_MASK		    0xfffffffUL
 	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_SFT		    0
@@ -867,12 +874,12 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_EVB_MODE_NO_EVB			   0x0UL
 	#define FUNC_QCFG_RESP_EVB_MODE_VEB			   0x1UL
 	#define FUNC_QCFG_RESP_EVB_MODE_VEPA			   0x2UL
-	u8 unused_3;
+	u8 unused_1;
 	__le16 alloc_vfs;
 	__le32 alloc_mcast_filters;
 	__le32 alloc_hw_ring_grps;
 	__le16 alloc_sp_tx_rings;
-	u8 unused_4;
+	u8 unused_2;
 	u8 valid;
 };
 
@@ -888,16 +895,13 @@ struct hwrm_func_cfg_input {
 	u8 unused_0;
 	u8 unused_1;
 	__le32 flags;
-	#define FUNC_CFG_REQ_FLAGS_PROM_MODE			    0x1UL
-	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK		    0x2UL
-	#define FUNC_CFG_REQ_FLAGS_SRC_IP_ADDR_CHECK		    0x4UL
-	#define FUNC_CFG_REQ_FLAGS_VLAN_PRI_MATCH		    0x8UL
-	#define FUNC_CFG_REQ_FLAGS_DFLT_PRI_NOMATCH		    0x10UL
-	#define FUNC_CFG_REQ_FLAGS_DISABLE_PAUSE		    0x20UL
-	#define FUNC_CFG_REQ_FLAGS_DISABLE_STP			    0x40UL
-	#define FUNC_CFG_REQ_FLAGS_DISABLE_LLDP		    0x80UL
-	#define FUNC_CFG_REQ_FLAGS_DISABLE_PTPV2		    0x100UL
-	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE		    0x200UL
+	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE      0x1UL
+	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE       0x2UL
+	#define FUNC_CFG_REQ_FLAGS_RSVD_MASK			    0x1fcUL
+	#define FUNC_CFG_REQ_FLAGS_RSVD_SFT			    2
+	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_ENABLE	    0x200UL
+	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_DISABLE	    0x400UL
+	#define FUNC_CFG_REQ_FLAGS_VIRT_MAC_PERSIST		    0x800UL
 	__le32 enables;
 	#define FUNC_CFG_REQ_ENABLES_MTU			    0x1UL
 	#define FUNC_CFG_REQ_ENABLES_MRU			    0x2UL
@@ -1013,7 +1017,7 @@ struct hwrm_func_qstats_output {
 	__le64 tx_ucast_pkts;
 	__le64 tx_mcast_pkts;
 	__le64 tx_bcast_pkts;
-	__le64 tx_err_pkts;
+	__le64 tx_discard_pkts;
 	__le64 tx_drop_pkts;
 	__le64 tx_ucast_bytes;
 	__le64 tx_mcast_bytes;
@@ -1021,7 +1025,7 @@ struct hwrm_func_qstats_output {
 	__le64 rx_ucast_pkts;
 	__le64 rx_mcast_pkts;
 	__le64 rx_bcast_pkts;
-	__le64 rx_err_pkts;
+	__le64 rx_discard_pkts;
 	__le64 rx_drop_pkts;
 	__le64 rx_ucast_bytes;
 	__le64 rx_mcast_bytes;
@@ -4743,25 +4747,72 @@ struct hwrm_temp_monitor_query_output {
 	u8 valid;
 };
 
-/* hwrm_nvm_read */
-/* Input (40 bytes) */
-struct hwrm_nvm_read_input {
+/* hwrm_wol_filter_alloc */
+/* Input (64 bytes) */
+struct hwrm_wol_filter_alloc_input {
 	__le16 req_type;
 	__le16 cmpl_ring;
 	__le16 seq_id;
 	__le16 target_id;
 	__le64 resp_addr;
-	__le64 host_dest_addr;
-	__le16 dir_idx;
+	__le32 flags;
+	__le32 enables;
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_MAC_ADDRESS	    0x1UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_OFFSET	    0x2UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_BUF_SIZE      0x4UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_BUF_ADDR      0x8UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_MASK_ADDR     0x10UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_MASK_SIZE     0x20UL
+	__le16 port_id;
+	u8 wol_type;
+	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT		   0x0UL
+	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_BMP		   0x1UL
+	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_INVALID		   0xffUL
 	u8 unused_0;
-	u8 unused_1;
-	__le32 offset;
-	__le32 len;
+	__le32 unused_1;
+	u8 mac_address[6];
+	__le16 pattern_offset;
+	__le16 pattern_buf_size;
+	__le16 pattern_mask_size;
 	__le32 unused_2;
+	__le64 pattern_buf_addr;
+	__le64 pattern_mask_addr;
 };
 
 /* Output (16 bytes) */
-struct hwrm_nvm_read_output {
+struct hwrm_wol_filter_alloc_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	u8 wol_filter_id;
+	u8 unused_0;
+	__le16 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 unused_4;
+	u8 valid;
+};
+
+/* hwrm_wol_filter_free */
+/* Input (32 bytes) */
+struct hwrm_wol_filter_free_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le32 flags;
+	#define WOL_FILTER_FREE_REQ_FLAGS_FREE_ALL_WOL_FILTERS     0x1UL
+	__le32 enables;
+	#define WOL_FILTER_FREE_REQ_ENABLES_WOL_FILTER_ID	    0x1UL
+	__le16 port_id;
+	u8 wol_filter_id;
+	u8 unused_0[5];
+};
+
+/* Output (16 bytes) */
+struct hwrm_wol_filter_free_output {
 	__le16 error_code;
 	__le16 req_type;
 	__le16 seq_id;
@@ -4773,21 +4824,107 @@ struct hwrm_nvm_read_output {
 	u8 valid;
 };
 
-/* hwrm_nvm_raw_dump */
-/* Input (32 bytes) */
-struct hwrm_nvm_raw_dump_input {
+/* hwrm_wol_filter_qcfg */
+/* Input (56 bytes) */
+struct hwrm_wol_filter_qcfg_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le16 port_id;
+	__le16 handle;
+	__le32 unused_0;
+	__le64 pattern_buf_addr;
+	__le16 pattern_buf_size;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3[3];
+	u8 unused_4;
+	__le64 pattern_mask_addr;
+	__le16 pattern_mask_size;
+	__le16 unused_5[3];
+};
+
+/* Output (32 bytes) */
+struct hwrm_wol_filter_qcfg_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le16 next_handle;
+	u8 wol_filter_id;
+	u8 wol_type;
+	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_MAGICPKT		   0x0UL
+	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_BMP		   0x1UL
+	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_INVALID		   0xffUL
+	__le32 unused_0;
+	u8 mac_address[6];
+	__le16 pattern_offset;
+	__le16 pattern_size;
+	__le16 pattern_mask_size;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
+/* hwrm_wol_reason_qcfg */
+/* Input (40 bytes) */
+struct hwrm_wol_reason_qcfg_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le16 port_id;
+	u8 unused_0;
+	u8 unused_1;
+	u8 unused_2[3];
+	u8 unused_3;
+	__le64 wol_pkt_buf_addr;
+	__le16 wol_pkt_buf_size;
+	__le16 unused_4[3];
+};
+
+/* Output (16 bytes) */
+struct hwrm_wol_reason_qcfg_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	u8 wol_filter_id;
+	u8 wol_reason;
+	#define WOL_REASON_QCFG_RESP_WOL_REASON_MAGICPKT	   0x0UL
+	#define WOL_REASON_QCFG_RESP_WOL_REASON_BMP		   0x1UL
+	#define WOL_REASON_QCFG_RESP_WOL_REASON_INVALID	   0xffUL
+	u8 wol_pkt_len;
+	u8 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
+/* hwrm_nvm_read */
+/* Input (40 bytes) */
+struct hwrm_nvm_read_input {
 	__le16 req_type;
 	__le16 cmpl_ring;
 	__le16 seq_id;
 	__le16 target_id;
 	__le64 resp_addr;
 	__le64 host_dest_addr;
+	__le16 dir_idx;
+	u8 unused_0;
+	u8 unused_1;
 	__le32 offset;
 	__le32 len;
+	__le32 unused_2;
 };
 
 /* Output (16 bytes) */
-struct hwrm_nvm_raw_dump_output {
+struct hwrm_nvm_read_output {
 	__le16 error_code;
 	__le16 req_type;
 	__le16 seq_id;
@@ -4881,6 +5018,15 @@ struct hwrm_nvm_write_output {
 	u8 valid;
 };
 
+/* Command specific Error Codes (8 bytes) */
+struct hwrm_nvm_write_cmd_err {
+	u8 code;
+	#define NVM_WRITE_CMD_ERR_CODE_UNKNOWN			   0x0UL
+	#define NVM_WRITE_CMD_ERR_CODE_FRAG_ERR		   0x1UL
+	#define NVM_WRITE_CMD_ERR_CODE_NO_SPACE		   0x2UL
+	u8 unused_0[7];
+};
+
 /* hwrm_nvm_modify */
 /* Input (40 bytes) */
 struct hwrm_nvm_modify_input {
@@ -5112,6 +5258,100 @@ struct hwrm_nvm_install_update_cmd_err {
 	u8 unused_0[7];
 };
 
+/* hwrm_selftest_qlist */
+/* Input (16 bytes) */
+struct hwrm_selftest_qlist_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+};
+
+/* Output (248 bytes) */
+struct hwrm_selftest_qlist_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	u8 num_tests;
+	u8 available_tests;
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_NVM_TEST       0x1UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_LINK_TEST      0x2UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_REGISTER_TEST  0x4UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_MEMORY_TEST    0x8UL
+	u8 offline_tests;
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_NVM_TEST	    0x1UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_LINK_TEST	    0x2UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_REGISTER_TEST    0x4UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_MEMORY_TEST      0x8UL
+	u8 unused_0;
+	__le16 test_timeout;
+	u8 unused_1;
+	u8 unused_2;
+	char test0_name[32];
+	char test1_name[32];
+	char test2_name[32];
+	char test3_name[32];
+	char test4_name[32];
+	char test5_name[32];
+	char test6_name[32];
+	char test7_name[32];
+};
+
+/* hwrm_selftest_exec */
+/* Input (24 bytes) */
+struct hwrm_selftest_exec_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	u8 flags;
+	#define SELFTEST_EXEC_REQ_FLAGS_NVM_TEST		    0x1UL
+	#define SELFTEST_EXEC_REQ_FLAGS_LINK_TEST		    0x2UL
+	#define SELFTEST_EXEC_REQ_FLAGS_REGISTER_TEST		    0x4UL
+	#define SELFTEST_EXEC_REQ_FLAGS_MEMORY_TEST		    0x8UL
+	u8 unused_0[7];
+};
+
+/* Output (16 bytes) */
+struct hwrm_selftest_exec_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	u8 requested_tests;
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_NVM_TEST	    0x1UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_LINK_TEST       0x2UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_REGISTER_TEST   0x4UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_MEMORY_TEST     0x8UL
+	u8 test_success;
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_NVM_TEST	    0x1UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_LINK_TEST	    0x2UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_REGISTER_TEST      0x4UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_MEMORY_TEST	    0x8UL
+	__le16 unused_0[3];
+};
+
+/* hwrm_selftest_irq */
+/* Input (16 bytes) */
+struct hwrm_selftest_irq_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+};
+
+/* Output (8 bytes) */
+struct hwrm_selftest_irq_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+};
+
 /* Hardware Resource Manager Specification */
 /* Input (16 bytes) */
 struct input {
@@ -5130,6 +5370,16 @@ struct output {
 	__le16 resp_len;
 };
 
+/* Short Command Structure (16 bytes) */
+struct hwrm_short_input {
+	__le16 req_type;
+	__le16 signature;
+	#define SHORT_REQ_SIGNATURE_SHORT_CMD			   0x4321UL
+	__le16 unused_0;
+	__le16 size;
+	__le64 req_addr;
+};
+
 /* Command numbering (8 bytes) */
 struct cmd_nums {
 	__le16 req_type;
@@ -5252,11 +5502,15 @@ struct cmd_nums {
 	#define HWRM_CFA_FLOW_FLUSH				   (0x105UL)
 	#define HWRM_CFA_FLOW_STATS				   (0x106UL)
 	#define HWRM_CFA_FLOW_INFO				   (0x107UL)
+	#define HWRM_SELFTEST_QLIST				   (0x200UL)
+	#define HWRM_SELFTEST_EXEC				   (0x201UL)
+	#define HWRM_SELFTEST_IRQ				   (0x202UL)
 	#define HWRM_DBG_READ_DIRECT				   (0xff10UL)
 	#define HWRM_DBG_READ_INDIRECT				   (0xff11UL)
 	#define HWRM_DBG_WRITE_DIRECT				   (0xff12UL)
 	#define HWRM_DBG_WRITE_INDIRECT			   (0xff13UL)
 	#define HWRM_DBG_DUMP					   (0xff14UL)
+	#define HWRM_NVM_FACTORY_DEFAULTS			   (0xffeeUL)
 	#define HWRM_NVM_VALIDATE_OPTION			   (0xffefUL)
 	#define HWRM_NVM_FLUSH					   (0xfff0UL)
 	#define HWRM_NVM_GET_VARIABLE				   (0xfff1UL)
@@ -5464,6 +5718,7 @@ struct hwrm_struct_hdr {
 	#define STRUCT_HDR_STRUCT_ID_DCBX_FEATURE_STATE	   0x422UL
 	#define STRUCT_HDR_STRUCT_ID_LLDP_GENERIC		   0x424UL
 	#define STRUCT_HDR_STRUCT_ID_LLDP_DEVICE		   0x426UL
+	#define STRUCT_HDR_STRUCT_ID_AFM_OPAQUE		   0x1UL
 	#define STRUCT_HDR_STRUCT_ID_PORT_DESCRIPTION		   0xaUL
 	__le16 len;
 	u8 version;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 0b8cd7443843..f89353175e6b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -1,6 +1,7 @@
 /* Broadcom NetXtreme-C/E network driver.
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
+ * Copyright (c) 2016-2017 Broadcom Limited
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -84,6 +85,9 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting)
 	u32 func_flags;
 	int rc;
 
+	if (bp->hwrm_spec_code < 0x10701)
+		return -ENOTSUPP;
+
 	rc = bnxt_vf_ndo_prep(bp, vf_id);
 	if (rc)
 		return rc;
@@ -96,9 +100,9 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting)
 
 	func_flags = vf->func_flags;
 	if (setting)
-		func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK;
+		func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE;
 	else
-		func_flags &= ~FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK;
+		func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE;
 	/*TODO: if the driver supports VLAN filter on guest VLAN,
 	 * the spoof check should also include vlan anti-spoofing
 	 */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h
index 1ab72e4820af..dbc8d977fc5a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h
@@ -1,6 +1,7 @@
 /* Broadcom NetXtreme-C/E network driver.
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
+ * Copyright (c) 2016-2017 Broadcom Limited
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 899c30fb5188..9dae32756767 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -19,11 +19,10 @@
 #include "bnxt.h"
 #include "bnxt_xdp.h"
 
-static void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
-			  dma_addr_t mapping, u32 len, u16 rx_prod)
+void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+		   dma_addr_t mapping, u32 len, u16 rx_prod)
 {
 	struct bnxt_sw_tx_bd *tx_buf;
-	struct tx_bd_ext *txbd1;
 	struct tx_bd *txbd;
 	u32 flags;
 	u16 prod;
@@ -33,23 +32,13 @@ static void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 	tx_buf->rx_prod = rx_prod;
 
 	txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
-	flags = (len << TX_BD_LEN_SHIFT) | TX_BD_TYPE_LONG_TX_BD |
-		(2 << TX_BD_FLAGS_BD_CNT_SHIFT) | TX_BD_FLAGS_COAL_NOW |
+	flags = (len << TX_BD_LEN_SHIFT) | (1 << TX_BD_FLAGS_BD_CNT_SHIFT) |
 		TX_BD_FLAGS_PACKET_END | bnxt_lhint_arr[len >> 9];
 	txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
 	txbd->tx_bd_opaque = prod;
 	txbd->tx_bd_haddr = cpu_to_le64(mapping);
 
 	prod = NEXT_TX(prod);
-	txbd1 = (struct tx_bd_ext *)
-		&txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
-
-	txbd1->tx_bd_hsize_lflags = cpu_to_le32(0);
-	txbd1->tx_bd_mss = cpu_to_le32(0);
-	txbd1->tx_bd_cfa_action = cpu_to_le32(0);
-	txbd1->tx_bd_cfa_meta = cpu_to_le32(0);
-
-	prod = NEXT_TX(prod);
 	txr->tx_prod = prod;
 }
 
@@ -66,7 +55,6 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 	for (i = 0; i < nr_pkts; i++) {
 		last_tx_cons = tx_cons;
 		tx_cons = NEXT_TX(tx_cons);
-		tx_cons = NEXT_TX(tx_cons);
 	}
 	txr->tx_cons = tx_cons;
 	if (bnxt_tx_avail(bp, txr) == bp->tx_ring_size) {
@@ -133,7 +121,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		return false;
 
 	case XDP_TX:
-		if (tx_avail < 2) {
+		if (tx_avail < 1) {
 			trace_xdp_exception(bp->dev, xdp_prog, act);
 			bnxt_reuse_rx_data(rxr, cons, page);
 			return true;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
index b529f2c5355b..12a5ad66b564 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -10,6 +10,8 @@
 #ifndef BNXT_XDP_H
 #define BNXT_XDP_H
 
+void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+		   dma_addr_t mapping, u32 len, u16 rx_prod);
 void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts);
 bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		 struct page *page, u8 **data_ptr, unsigned int *len,
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 365895ed3c3e..a205a9ff9e17 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -621,7 +621,7 @@ static int bcmgenet_set_coalesce(struct net_device *dev,
 
 	/* GENET TDMA hardware does not support a configurable timeout, but will
 	 * always generate an interrupt either after MBDONE packets have been
-	 * transmitted, or when the ring is emtpy.
+	 * transmitted, or when the ring is empty.
 	 */
 	if (ec->tx_coalesce_usecs || ec->tx_coalesce_usecs_high ||
 	    ec->tx_coalesce_usecs_irq || ec->tx_coalesce_usecs_low)
@@ -707,6 +707,19 @@ struct bcmgenet_stats {
 	.reg_offset = offset, \
 }
 
+#define STAT_GENET_Q(num) \
+	STAT_GENET_SOFT_MIB("txq" __stringify(num) "_packets", \
+			tx_rings[num].packets), \
+	STAT_GENET_SOFT_MIB("txq" __stringify(num) "_bytes", \
+			tx_rings[num].bytes), \
+	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_bytes", \
+			rx_rings[num].bytes),	 \
+	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_packets", \
+			rx_rings[num].packets), \
+	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_errors", \
+			rx_rings[num].errors), \
+	STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_dropped", \
+			rx_rings[num].dropped)
 
 /* There is a 0xC gap between the end of RX and beginning of TX stats and then
  * between the end of TX stats and the beginning of the RX RUNT
@@ -801,6 +814,12 @@ static const struct bcmgenet_stats bcmgenet_gstrings_stats[] = {
 	STAT_GENET_SOFT_MIB("alloc_rx_buff_failed", mib.alloc_rx_buff_failed),
 	STAT_GENET_SOFT_MIB("rx_dma_failed", mib.rx_dma_failed),
 	STAT_GENET_SOFT_MIB("tx_dma_failed", mib.tx_dma_failed),
+	/* Per TX queues */
+	STAT_GENET_Q(0),
+	STAT_GENET_Q(1),
+	STAT_GENET_Q(2),
+	STAT_GENET_Q(3),
+	STAT_GENET_Q(16),
 };
 
 #define BCMGENET_STATS_LEN	ARRAY_SIZE(bcmgenet_gstrings_stats)
@@ -1078,8 +1097,17 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv,
 		/* Power down LED */
 		if (priv->hw_params->flags & GENET_HAS_EXT) {
 			reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
-			reg |= (EXT_PWR_DOWN_PHY |
-				EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS);
+			if (GENET_IS_V5(priv))
+				reg |= EXT_PWR_DOWN_PHY_EN |
+				       EXT_PWR_DOWN_PHY_RD |
+				       EXT_PWR_DOWN_PHY_SD |
+				       EXT_PWR_DOWN_PHY_RX |
+				       EXT_PWR_DOWN_PHY_TX |
+				       EXT_IDDQ_GLBL_PWR;
+			else
+				reg |= EXT_PWR_DOWN_PHY;
+
+			reg |= (EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS);
 			bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
 
 			bcmgenet_phy_power_set(priv->dev, false);
@@ -1104,12 +1132,34 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 
 	switch (mode) {
 	case GENET_POWER_PASSIVE:
-		reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_PHY |
-				EXT_PWR_DOWN_BIAS);
-		/* fallthrough */
+		reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS);
+		if (GENET_IS_V5(priv)) {
+			reg &= ~(EXT_PWR_DOWN_PHY_EN |
+				 EXT_PWR_DOWN_PHY_RD |
+				 EXT_PWR_DOWN_PHY_SD |
+				 EXT_PWR_DOWN_PHY_RX |
+				 EXT_PWR_DOWN_PHY_TX |
+				 EXT_IDDQ_GLBL_PWR);
+			reg |=   EXT_PHY_RESET;
+			bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
+			mdelay(1);
+
+			reg &=  ~EXT_PHY_RESET;
+		} else {
+			reg &= ~EXT_PWR_DOWN_PHY;
+			reg |= EXT_PWR_DN_EN_LD;
+		}
+		bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
+		bcmgenet_phy_power_set(priv->dev, true);
+		bcmgenet_mii_reset(priv->dev);
+		break;
+
 	case GENET_POWER_CABLE_SENSE:
 		/* enable APD */
-		reg |= EXT_PWR_DN_EN_LD;
+		if (!GENET_IS_V5(priv)) {
+			reg |= EXT_PWR_DN_EN_LD;
+			bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
+		}
 		break;
 	case GENET_POWER_WOL_MAGIC:
 		bcmgenet_wol_power_up_cfg(priv, mode);
@@ -1117,39 +1167,20 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 	default:
 		break;
 	}
-
-	bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
-	if (mode == GENET_POWER_PASSIVE) {
-		bcmgenet_phy_power_set(priv->dev, true);
-		bcmgenet_mii_reset(priv->dev);
-	}
 }
 
 /* ioctl handle special commands that are not present in ethtool. */
 static int bcmgenet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	int val = 0;
 
 	if (!netif_running(dev))
 		return -EINVAL;
 
-	switch (cmd) {
-	case SIOCGMIIPHY:
-	case SIOCGMIIREG:
-	case SIOCSMIIREG:
-		if (!priv->phydev)
-			val = -ENODEV;
-		else
-			val = phy_mii_ioctl(priv->phydev, rq, cmd);
-		break;
-
-	default:
-		val = -EINVAL;
-		break;
-	}
+	if (!priv->phydev)
+		return -ENODEV;
 
-	return val;
+	return phy_mii_ioctl(priv->phydev, rq, cmd);
 }
 
 static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv,
@@ -1240,14 +1271,18 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 	unsigned int txbds_ready;
 	unsigned int txbds_processed = 0;
 
-	/* Compute how many buffers are transmitted since last xmit call */
-	c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX);
-	c_index &= DMA_C_INDEX_MASK;
-
-	if (likely(c_index >= ring->c_index))
-		txbds_ready = c_index - ring->c_index;
+	/* Clear status before servicing to reduce spurious interrupts */
+	if (ring->index == DESC_INDEX)
+		bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_TXDMA_DONE,
+					 INTRL2_CPU_CLEAR);
 	else
-		txbds_ready = (DMA_C_INDEX_MASK + 1) - ring->c_index + c_index;
+		bcmgenet_intrl2_1_writel(priv, (1 << ring->index),
+					 INTRL2_CPU_CLEAR);
+
+	/* Compute how many buffers are transmitted since last xmit call */
+	c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX)
+		& DMA_C_INDEX_MASK;
+	txbds_ready = (c_index - ring->c_index) & DMA_C_INDEX_MASK;
 
 	netif_dbg(priv, tx_done, dev,
 		  "%s ring=%d old_c_index=%u c_index=%u txbds_ready=%u\n",
@@ -1280,15 +1315,15 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 	}
 
 	ring->free_bds += txbds_processed;
-	ring->c_index = (ring->c_index + txbds_processed) & DMA_C_INDEX_MASK;
+	ring->c_index = c_index;
 
-	dev->stats.tx_packets += pkts_compl;
-	dev->stats.tx_bytes += bytes_compl;
+	ring->packets += pkts_compl;
+	ring->bytes += bytes_compl;
 
 	netdev_tx_completed_queue(netdev_get_tx_queue(dev, ring->queue),
 				  pkts_compl, bytes_compl);
 
-	return pkts_compl;
+	return txbds_processed;
 }
 
 static unsigned int bcmgenet_tx_reclaim(struct net_device *dev,
@@ -1657,18 +1692,28 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 	unsigned long dma_flag;
 	int len;
 	unsigned int rxpktprocessed = 0, rxpkttoprocess;
-	unsigned int p_index;
+	unsigned int p_index, mask;
 	unsigned int discards;
 	unsigned int chksum_ok = 0;
 
+	/* Clear status before servicing to reduce spurious interrupts */
+	if (ring->index == DESC_INDEX) {
+		bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_RXDMA_DONE,
+					 INTRL2_CPU_CLEAR);
+	} else {
+		mask = 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index);
+		bcmgenet_intrl2_1_writel(priv,
+					 mask,
+					 INTRL2_CPU_CLEAR);
+	}
+
 	p_index = bcmgenet_rdma_ring_readl(priv, ring->index, RDMA_PROD_INDEX);
 
 	discards = (p_index >> DMA_P_INDEX_DISCARD_CNT_SHIFT) &
 		   DMA_P_INDEX_DISCARD_CNT_MASK;
 	if (discards > ring->old_discards) {
 		discards = discards - ring->old_discards;
-		dev->stats.rx_missed_errors += discards;
-		dev->stats.rx_errors += discards;
+		ring->errors += discards;
 		ring->old_discards += discards;
 
 		/* Clear HW register when we reach 75% of maximum 0xFFFF */
@@ -1680,12 +1725,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 	}
 
 	p_index &= DMA_P_INDEX_MASK;
-
-	if (likely(p_index >= ring->c_index))
-		rxpkttoprocess = p_index - ring->c_index;
-	else
-		rxpkttoprocess = (DMA_C_INDEX_MASK + 1) - ring->c_index +
-				 p_index;
+	rxpkttoprocess = (p_index - ring->c_index) & DMA_C_INDEX_MASK;
 
 	netif_dbg(priv, rx_status, dev,
 		  "RDMA: rxpkttoprocess=%d\n", rxpkttoprocess);
@@ -1696,7 +1736,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		skb = bcmgenet_rx_refill(priv, cb);
 
 		if (unlikely(!skb)) {
-			dev->stats.rx_dropped++;
+			ring->dropped++;
 			goto next;
 		}
 
@@ -1724,7 +1764,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		if (unlikely(!(dma_flag & DMA_EOP) || !(dma_flag & DMA_SOP))) {
 			netif_err(priv, rx_status, dev,
 				  "dropping fragmented packet!\n");
-			dev->stats.rx_errors++;
+			ring->errors++;
 			dev_kfree_skb_any(skb);
 			goto next;
 		}
@@ -1773,8 +1813,8 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 
 		/*Finish setting up the received SKB and send it to the kernel*/
 		skb->protocol = eth_type_trans(skb, priv->dev);
-		dev->stats.rx_packets++;
-		dev->stats.rx_bytes += len;
+		ring->packets++;
+		ring->bytes += len;
 		if (dma_flag & DMA_RX_MULT)
 			dev->stats.multicast++;
 
@@ -1912,10 +1952,8 @@ static void bcmgenet_intr_disable(struct bcmgenet_priv *priv)
 	/* Mask all interrupts.*/
 	bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET);
 	bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR);
-	bcmgenet_intrl2_0_writel(priv, 0, INTRL2_CPU_MASK_CLEAR);
 	bcmgenet_intrl2_1_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET);
 	bcmgenet_intrl2_1_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR);
-	bcmgenet_intrl2_1_writel(priv, 0, INTRL2_CPU_MASK_CLEAR);
 }
 
 static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv)
@@ -1942,8 +1980,6 @@ static int init_umac(struct bcmgenet_priv *priv)
 	int ret;
 	u32 reg;
 	u32 int0_enable = 0;
-	u32 int1_enable = 0;
-	int i;
 
 	dev_dbg(&priv->pdev->dev, "bcmgenet: init_umac\n");
 
@@ -1970,12 +2006,6 @@ static int init_umac(struct bcmgenet_priv *priv)
 
 	bcmgenet_intr_disable(priv);
 
-	/* Enable Rx default queue 16 interrupts */
-	int0_enable |= UMAC_IRQ_RXDMA_DONE;
-
-	/* Enable Tx default queue 16 interrupts */
-	int0_enable |= UMAC_IRQ_TXDMA_DONE;
-
 	/* Configure backpressure vectors for MoCA */
 	if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
 		reg = bcmgenet_bp_mc_get(priv);
@@ -1993,18 +2023,8 @@ static int init_umac(struct bcmgenet_priv *priv)
 	if (priv->hw_params->flags & GENET_HAS_MDIO_INTR)
 		int0_enable |= (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR);
 
-	/* Enable Rx priority queue interrupts */
-	for (i = 0; i < priv->hw_params->rx_queues; ++i)
-		int1_enable |= (1 << (UMAC_IRQ1_RX_INTR_SHIFT + i));
-
-	/* Enable Tx priority queue interrupts */
-	for (i = 0; i < priv->hw_params->tx_queues; ++i)
-		int1_enable |= (1 << i);
-
 	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
-	bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
 
-	/* Enable rx/tx engine.*/
 	dev_dbg(kdev, "done init umac\n");
 
 	return 0;
@@ -2136,22 +2156,33 @@ static void bcmgenet_init_tx_napi(struct bcmgenet_priv *priv)
 static void bcmgenet_enable_tx_napi(struct bcmgenet_priv *priv)
 {
 	unsigned int i;
+	u32 int0_enable = UMAC_IRQ_TXDMA_DONE;
+	u32 int1_enable = 0;
 	struct bcmgenet_tx_ring *ring;
 
 	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		napi_enable(&ring->napi);
+		int1_enable |= (1 << i);
 	}
 
 	ring = &priv->tx_rings[DESC_INDEX];
 	napi_enable(&ring->napi);
+
+	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
+	bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
 }
 
 static void bcmgenet_disable_tx_napi(struct bcmgenet_priv *priv)
 {
 	unsigned int i;
+	u32 int0_disable = UMAC_IRQ_TXDMA_DONE;
+	u32 int1_disable = 0xffff;
 	struct bcmgenet_tx_ring *ring;
 
+	bcmgenet_intrl2_0_writel(priv, int0_disable, INTRL2_CPU_MASK_SET);
+	bcmgenet_intrl2_1_writel(priv, int1_disable, INTRL2_CPU_MASK_SET);
+
 	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		napi_disable(&ring->napi);
@@ -2264,22 +2295,33 @@ static void bcmgenet_init_rx_napi(struct bcmgenet_priv *priv)
 static void bcmgenet_enable_rx_napi(struct bcmgenet_priv *priv)
 {
 	unsigned int i;
+	u32 int0_enable = UMAC_IRQ_RXDMA_DONE;
+	u32 int1_enable = 0;
 	struct bcmgenet_rx_ring *ring;
 
 	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		napi_enable(&ring->napi);
+		int1_enable |= (1 << (UMAC_IRQ1_RX_INTR_SHIFT + i));
 	}
 
 	ring = &priv->rx_rings[DESC_INDEX];
 	napi_enable(&ring->napi);
+
+	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
+	bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
 }
 
 static void bcmgenet_disable_rx_napi(struct bcmgenet_priv *priv)
 {
 	unsigned int i;
+	u32 int0_disable = UMAC_IRQ_RXDMA_DONE;
+	u32 int1_disable = 0xffff << UMAC_IRQ1_RX_INTR_SHIFT;
 	struct bcmgenet_rx_ring *ring;
 
+	bcmgenet_intrl2_0_writel(priv, int0_disable, INTRL2_CPU_MASK_SET);
+	bcmgenet_intrl2_1_writel(priv, int1_disable, INTRL2_CPU_MASK_SET);
+
 	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		napi_disable(&ring->napi);
@@ -2634,6 +2676,15 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 		}
 	}
 
+	if (priv->irq0_stat & (UMAC_IRQ_PHY_DET_R |
+				UMAC_IRQ_PHY_DET_F |
+				UMAC_IRQ_LINK_EVENT |
+				UMAC_IRQ_HFB_SM |
+				UMAC_IRQ_HFB_MM)) {
+		/* all other interested interrupts handled in bottom half */
+		schedule_work(&priv->bcmgenet_irq_work);
+	}
+
 	if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) &&
 		status & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) {
 		wake_up(&priv->wq);
@@ -2921,7 +2972,7 @@ static int bcmgenet_close(struct net_device *dev)
 	if (ret)
 		return ret;
 
-	/* Disable MAC transmit. TX DMA disabled have to done before this */
+	/* Disable MAC transmit. TX DMA disabled must be done before this */
 	umac_enable_set(priv, CMD_TX_EN, false);
 
 	/* tx reclaim */
@@ -3101,6 +3152,48 @@ static int bcmgenet_set_mac_addr(struct net_device *dev, void *p)
 	return 0;
 }
 
+static struct net_device_stats *bcmgenet_get_stats(struct net_device *dev)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	unsigned long tx_bytes = 0, tx_packets = 0;
+	unsigned long rx_bytes = 0, rx_packets = 0;
+	unsigned long rx_errors = 0, rx_dropped = 0;
+	struct bcmgenet_tx_ring *tx_ring;
+	struct bcmgenet_rx_ring *rx_ring;
+	unsigned int q;
+
+	for (q = 0; q < priv->hw_params->tx_queues; q++) {
+		tx_ring = &priv->tx_rings[q];
+		tx_bytes += tx_ring->bytes;
+		tx_packets += tx_ring->packets;
+	}
+	tx_ring = &priv->tx_rings[DESC_INDEX];
+	tx_bytes += tx_ring->bytes;
+	tx_packets += tx_ring->packets;
+
+	for (q = 0; q < priv->hw_params->rx_queues; q++) {
+		rx_ring = &priv->rx_rings[q];
+
+		rx_bytes += rx_ring->bytes;
+		rx_packets += rx_ring->packets;
+		rx_errors += rx_ring->errors;
+		rx_dropped += rx_ring->dropped;
+	}
+	rx_ring = &priv->rx_rings[DESC_INDEX];
+	rx_bytes += rx_ring->bytes;
+	rx_packets += rx_ring->packets;
+	rx_errors += rx_ring->errors;
+	rx_dropped += rx_ring->dropped;
+
+	dev->stats.tx_bytes = tx_bytes;
+	dev->stats.tx_packets = tx_packets;
+	dev->stats.rx_bytes = rx_bytes;
+	dev->stats.rx_packets = rx_packets;
+	dev->stats.rx_errors = rx_errors;
+	dev->stats.rx_missed_errors = rx_errors;
+	return &dev->stats;
+}
+
 static const struct net_device_ops bcmgenet_netdev_ops = {
 	.ndo_open		= bcmgenet_open,
 	.ndo_stop		= bcmgenet_close,
@@ -3113,6 +3206,7 @@ static const struct net_device_ops bcmgenet_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= bcmgenet_poll_controller,
 #endif
+	.ndo_get_stats		= bcmgenet_get_stats,
 };
 
 /* Array of GENET hardware parameters/characteristics */
@@ -3186,6 +3280,25 @@ static struct bcmgenet_hw_params bcmgenet_hw_params[] = {
 		.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
 			 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
 	},
+	[GENET_V5] = {
+		.tx_queues = 4,
+		.tx_bds_per_q = 32,
+		.rx_queues = 0,
+		.rx_bds_per_q = 0,
+		.bp_in_en_shift = 17,
+		.bp_in_mask = 0x1ffff,
+		.hfb_filter_cnt = 48,
+		.hfb_filter_size = 128,
+		.qtag_mask = 0x3F,
+		.tbuf_offset = 0x0600,
+		.hfb_offset = 0x8000,
+		.hfb_reg_offset = 0xfc00,
+		.rdma_offset = 0x2000,
+		.tdma_offset = 0x4000,
+		.words_per_bd = 3,
+		.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
+			 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
+	},
 };
 
 /* Infer hardware parameters from the detected GENET version */
@@ -3196,26 +3309,22 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
 	u8 major;
 	u16 gphy_rev;
 
-	if (GENET_IS_V4(priv)) {
+	if (GENET_IS_V5(priv) || GENET_IS_V4(priv)) {
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
 		genet_dma_ring_regs = genet_dma_ring_regs_v4;
 		priv->dma_rx_chk_bit = DMA_RX_CHK_V3PLUS;
-		priv->version = GENET_V4;
 	} else if (GENET_IS_V3(priv)) {
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
 		genet_dma_ring_regs = genet_dma_ring_regs_v123;
 		priv->dma_rx_chk_bit = DMA_RX_CHK_V3PLUS;
-		priv->version = GENET_V3;
 	} else if (GENET_IS_V2(priv)) {
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v2;
 		genet_dma_ring_regs = genet_dma_ring_regs_v123;
 		priv->dma_rx_chk_bit = DMA_RX_CHK_V12;
-		priv->version = GENET_V2;
 	} else if (GENET_IS_V1(priv)) {
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v1;
 		genet_dma_ring_regs = genet_dma_ring_regs_v123;
 		priv->dma_rx_chk_bit = DMA_RX_CHK_V12;
-		priv->version = GENET_V1;
 	}
 
 	/* enum genet_version starts at 1 */
@@ -3225,7 +3334,9 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
 	/* Read GENET HW version */
 	reg = bcmgenet_sys_readl(priv, SYS_REV_CTRL);
 	major = (reg >> 24 & 0x0f);
-	if (major == 5)
+	if (major == 6)
+		major = 5;
+	else if (major == 5)
 		major = 4;
 	else if (major == 0)
 		major = 1;
@@ -3253,19 +3364,25 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
 	 */
 	gphy_rev = reg & 0xffff;
 
+	if (GENET_IS_V5(priv)) {
+		/* The EPHY revision should come from the MDIO registers of
+		 * the PHY not from GENET.
+		 */
+		if (gphy_rev != 0) {
+			pr_warn("GENET is reporting EPHY revision: 0x%04x\n",
+				gphy_rev);
+		}
 	/* This is reserved so should require special treatment */
-	if (gphy_rev == 0 || gphy_rev == 0x01ff) {
+	} else if (gphy_rev == 0 || gphy_rev == 0x01ff) {
 		pr_warn("Invalid GPHY revision detected: 0x%04x\n", gphy_rev);
 		return;
-	}
-
 	/* This is the good old scheme, just GPHY major, no minor nor patch */
-	if ((gphy_rev & 0xf0) != 0)
+	} else if ((gphy_rev & 0xf0) != 0) {
 		priv->gphy_rev = gphy_rev << 8;
-
 	/* This is the new scheme, GPHY major rolls over with 0x10 = rev G0 */
-	else if ((gphy_rev & 0xff00) != 0)
+	} else if ((gphy_rev & 0xff00) != 0) {
 		priv->gphy_rev = gphy_rev;
+	}
 
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
 	if (!(params->flags & GENET_HAS_40BITS))
@@ -3295,6 +3412,7 @@ static const struct of_device_id bcmgenet_match[] = {
 	{ .compatible = "brcm,genet-v2", .data = (void *)GENET_V2 },
 	{ .compatible = "brcm,genet-v3", .data = (void *)GENET_V3 },
 	{ .compatible = "brcm,genet-v4", .data = (void *)GENET_V4 },
+	{ .compatible = "brcm,genet-v5", .data = (void *)GENET_V5 },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, bcmgenet_match);
@@ -3493,7 +3611,7 @@ static int bcmgenet_suspend(struct device *d)
 	if (ret)
 		return ret;
 
-	/* Disable MAC transmit. TX DMA disabled have to done before this */
+	/* Disable MAC transmit. TX DMA disabled must be done before this */
 	umac_enable_set(priv, CMD_TX_EN, false);
 
 	/* tx reclaim */
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index db7f289d65ae..efd07020b89f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -355,8 +355,14 @@ struct bcmgenet_mib_counters {
 #define  EXT_PWR_DN_EN_LD		(1 << 3)
 #define  EXT_ENERGY_DET			(1 << 4)
 #define  EXT_IDDQ_FROM_PHY		(1 << 5)
+#define  EXT_IDDQ_GLBL_PWR		(1 << 7)
 #define  EXT_PHY_RESET			(1 << 8)
 #define  EXT_ENERGY_DET_MASK		(1 << 12)
+#define  EXT_PWR_DOWN_PHY_TX		(1 << 16)
+#define  EXT_PWR_DOWN_PHY_RX		(1 << 17)
+#define  EXT_PWR_DOWN_PHY_SD		(1 << 18)
+#define  EXT_PWR_DOWN_PHY_RD		(1 << 19)
+#define  EXT_PWR_DOWN_PHY_EN		(1 << 20)
 
 #define EXT_RGMII_OOB_CTRL		0x0C
 #define  RGMII_LINK			(1 << 4)
@@ -499,13 +505,15 @@ enum bcmgenet_version {
 	GENET_V1 = 1,
 	GENET_V2,
 	GENET_V3,
-	GENET_V4
+	GENET_V4,
+	GENET_V5
 };
 
 #define GENET_IS_V1(p)	((p)->version == GENET_V1)
 #define GENET_IS_V2(p)	((p)->version == GENET_V2)
 #define GENET_IS_V3(p)	((p)->version == GENET_V3)
 #define GENET_IS_V4(p)	((p)->version == GENET_V4)
+#define GENET_IS_V5(p)	((p)->version == GENET_V5)
 
 /* Hardware flags */
 #define GENET_HAS_40BITS	(1 << 0)
@@ -544,6 +552,8 @@ struct bcmgenet_skb_cb {
 struct bcmgenet_tx_ring {
 	spinlock_t	lock;		/* ring lock */
 	struct napi_struct napi;	/* NAPI per tx queue */
+	unsigned long	packets;
+	unsigned long	bytes;
 	unsigned int	index;		/* ring index */
 	unsigned int	queue;		/* queue index */
 	struct enet_cb	*cbs;		/* tx ring buffer control block*/
@@ -562,6 +572,10 @@ struct bcmgenet_tx_ring {
 
 struct bcmgenet_rx_ring {
 	struct napi_struct napi;	/* Rx NAPI struct */
+	unsigned long	bytes;
+	unsigned long	packets;
+	unsigned long	errors;
+	unsigned long	dropped;
 	unsigned int	index;		/* Rx ring index */
 	struct enet_cb	*cbs;		/* Rx ring buffer control block */
 	unsigned int	size;		/* Rx ring size */
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index b97122926d3a..2fbd027f0148 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -1,7 +1,7 @@
 /*
  * Broadcom GENET (Gigabit Ethernet) Wake-on-LAN support
  *
- * Copyright (c) 2014 Broadcom Corporation
+ * Copyright (c) 2014-2017 Broadcom
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -127,7 +127,6 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 				enum bcmgenet_power_mode mode)
 {
 	struct net_device *dev = priv->dev;
-	u32 cpu_mask_clear;
 	int retries = 0;
 	u32 reg;
 
@@ -173,18 +172,12 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 		bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
 	}
 
-	/* Enable the MPD interrupt */
-	cpu_mask_clear = UMAC_IRQ_MPD_R;
-
-	bcmgenet_intrl2_0_writel(priv, cpu_mask_clear, INTRL2_CPU_MASK_CLEAR);
-
 	return 0;
 }
 
 void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 			       enum bcmgenet_power_mode mode)
 {
-	u32 cpu_mask_set;
 	u32 reg;
 
 	if (mode != GENET_POWER_WOL_MAGIC) {
@@ -201,10 +194,4 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 	reg &= ~CMD_CRC_FWD;
 	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	priv->crc_fwd_en = 0;
-
-	/* Stop monitoring magic packet IRQ */
-	cpu_mask_set = UMAC_IRQ_MPD_R;
-
-	/* Stop monitoring magic packet IRQ */
-	bcmgenet_intrl2_0_writel(priv, cpu_mask_set, INTRL2_CPU_MASK_SET);
 }
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 2f9281936f0e..285676f8da6b 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -1,7 +1,7 @@
 /*
  * Broadcom GENET MDIO routines
  *
- * Copyright (c) 2014 Broadcom Corporation
+ * Copyright (c) 2014-2017 Broadcom
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -195,39 +195,43 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
 	u32 reg = 0;
 
 	/* EXT_GPHY_CTRL is only valid for GENETv4 and onward */
-	if (!GENET_IS_V4(priv))
-		return;
-
-	reg = bcmgenet_ext_readl(priv, EXT_GPHY_CTRL);
-	if (enable) {
-		reg &= ~EXT_CK25_DIS;
-		bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
-		mdelay(1);
-
-		reg &= ~(EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN);
-		reg |= EXT_GPHY_RESET;
+	if (GENET_IS_V4(priv)) {
+		reg = bcmgenet_ext_readl(priv, EXT_GPHY_CTRL);
+		if (enable) {
+			reg &= ~EXT_CK25_DIS;
+			bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
+			mdelay(1);
+
+			reg &= ~(EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN);
+			reg |= EXT_GPHY_RESET;
+			bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
+			mdelay(1);
+
+			reg &= ~EXT_GPHY_RESET;
+		} else {
+			reg |= EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN |
+			       EXT_GPHY_RESET;
+			bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
+			mdelay(1);
+			reg |= EXT_CK25_DIS;
+		}
 		bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
-		mdelay(1);
-
-		reg &= ~EXT_GPHY_RESET;
+		udelay(60);
 	} else {
-		reg |= EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN | EXT_GPHY_RESET;
-		bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
 		mdelay(1);
-		reg |= EXT_CK25_DIS;
 	}
-	bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
-	udelay(60);
 }
 
 static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
 {
 	u32 reg;
 
-	/* Speed settings are set in bcmgenet_mii_setup() */
-	reg = bcmgenet_sys_readl(priv, SYS_PORT_CTRL);
-	reg |= LED_ACT_SOURCE_MAC;
-	bcmgenet_sys_writel(priv, reg, SYS_PORT_CTRL);
+	if (!GENET_IS_V5(priv)) {
+		/* Speed settings are set in bcmgenet_mii_setup() */
+		reg = bcmgenet_sys_readl(priv, SYS_PORT_CTRL);
+		reg |= LED_ACT_SOURCE_MAC;
+		bcmgenet_sys_writel(priv, reg, SYS_PORT_CTRL);
+	}
 
 	if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET)
 		fixed_phy_set_link_update(priv->phydev,
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 30d1eb9ebec9..f395b951f5e7 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -825,6 +825,7 @@ static int tg3_ape_event_lock(struct tg3 *tp, u32 timeout_us)
 	return timeout_us ? 0 : -EBUSY;
 }
 
+#ifdef CONFIG_TIGON3_HWMON
 static int tg3_ape_wait_for_event(struct tg3 *tp, u32 timeout_us)
 {
 	u32 i, apedata;
@@ -904,6 +905,7 @@ static int tg3_ape_scratchpad_read(struct tg3 *tp, u32 *data, u32 base_off,
 
 	return 0;
 }
+#endif
 
 static int tg3_ape_send_event(struct tg3 *tp, u32 event)
 {
@@ -10744,6 +10746,7 @@ static int tg3_init_hw(struct tg3 *tp, bool reset_phy)
 	return tg3_reset_hw(tp, reset_phy);
 }
 
+#ifdef CONFIG_TIGON3_HWMON
 static void tg3_sd_scan_scratchpad(struct tg3 *tp, struct tg3_ocir *ocir)
 {
 	int i;
@@ -10826,6 +10829,10 @@ static void tg3_hwmon_open(struct tg3 *tp)
 		dev_err(&pdev->dev, "Cannot register hwmon device, aborting\n");
 	}
 }
+#else
+static inline void tg3_hwmon_close(struct tg3 *tp) { }
+static inline void tg3_hwmon_open(struct tg3 *tp) { }
+#endif /* CONFIG_TIGON3_HWMON */
 
 
 #define TG3_STAT_ADD32(PSTAT, REG) \
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h
index 2fedd91f3df8..dee604651ba7 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h
@@ -43,6 +43,8 @@ struct octeon_cn23xx_pf {
 	struct octeon_config *conf;
 };
 
+#define CN23XX_SLI_DEF_BP			0x40
+
 int setup_cn23xx_octeon_pf_device(struct octeon_device *oct);
 
 int validate_cn23xx_pf_config_info(struct octeon_device *oct,
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index f629c2fe04a4..08676df6cef0 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -26,6 +26,9 @@
 #include "octeon_main.h"
 #include "octeon_network.h"
 
+/* OOM task polling interval */
+#define LIO_OOM_POLL_INTERVAL_MS 250
+
 int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1)
 {
 	struct lio *lio = GET_LIO(netdev);
@@ -131,11 +134,20 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr)
 
 	case OCTNET_CMD_CHANGE_MACADDR:
 		mac = ((u8 *)&nctrl->udd[0]) + 2;
-		netif_info(lio, probe, lio->netdev,
-			   "MACAddr changed to %2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x\n",
-			   mac[0], mac[1],
-			   mac[2], mac[3],
-			   mac[4], mac[5]);
+		if (nctrl->ncmd.s.param1) {
+			/* vfidx is 0 based, but vf_num (param1) is 1 based */
+			int vfidx = nctrl->ncmd.s.param1 - 1;
+			bool mac_is_admin_assigned = nctrl->ncmd.s.param2;
+
+			if (mac_is_admin_assigned)
+				netif_info(lio, probe, lio->netdev,
+					   "MAC Address %pM is configured for VF %d\n",
+					   mac, vfidx);
+		} else {
+			netif_info(lio, probe, lio->netdev,
+				   " MACAddr changed to %pM\n",
+				   mac);
+		}
 		break;
 
 	case OCTNET_CMD_CHANGE_MTU:
@@ -284,3 +296,56 @@ void octeon_pf_changed_vf_macaddr(struct octeon_device *oct, u8 *mac)
 	 * the PF did that already
 	 */
 }
+
+static void octnet_poll_check_rxq_oom_status(struct work_struct *work)
+{
+	struct cavium_wk *wk = (struct cavium_wk *)work;
+	struct lio *lio = (struct lio *)wk->ctxptr;
+	struct octeon_device *oct = lio->oct_dev;
+	struct octeon_droq *droq;
+	int q, q_no = 0;
+
+	if (ifstate_check(lio, LIO_IFSTATE_RUNNING)) {
+		for (q = 0; q < lio->linfo.num_rxpciq; q++) {
+			q_no = lio->linfo.rxpciq[q].s.q_no;
+			droq = oct->droq[q_no];
+			if (!droq)
+				continue;
+			octeon_droq_check_oom(droq);
+		}
+	}
+	queue_delayed_work(lio->rxq_status_wq.wq,
+			   &lio->rxq_status_wq.wk.work,
+			   msecs_to_jiffies(LIO_OOM_POLL_INTERVAL_MS));
+}
+
+int setup_rx_oom_poll_fn(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+
+	lio->rxq_status_wq.wq = alloc_workqueue("rxq-oom-status",
+						WQ_MEM_RECLAIM, 0);
+	if (!lio->rxq_status_wq.wq) {
+		dev_err(&oct->pci_dev->dev, "unable to create cavium rxq oom status wq\n");
+		return -ENOMEM;
+	}
+	INIT_DELAYED_WORK(&lio->rxq_status_wq.wk.work,
+			  octnet_poll_check_rxq_oom_status);
+	lio->rxq_status_wq.wk.ctxptr = lio;
+	queue_delayed_work(lio->rxq_status_wq.wq,
+			   &lio->rxq_status_wq.wk.work,
+			   msecs_to_jiffies(LIO_OOM_POLL_INTERVAL_MS));
+	return 0;
+}
+
+void cleanup_rx_oom_poll_fn(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+
+	if (lio->rxq_status_wq.wq) {
+		cancel_delayed_work_sync(&lio->rxq_status_wq.wk.work);
+		flush_workqueue(lio->rxq_status_wq.wq);
+		destroy_workqueue(lio->rxq_status_wq.wq);
+	}
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
index 50384cede8be..dab10c7e4443 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
@@ -33,6 +33,19 @@
 
 static int octnet_get_link_stats(struct net_device *netdev);
 
+struct oct_intrmod_context {
+	int octeon_id;
+	wait_queue_head_t wc;
+	int cond;
+	int status;
+};
+
+struct oct_intrmod_resp {
+	u64     rh;
+	struct oct_intrmod_cfg intrmod;
+	u64     status;
+};
+
 struct oct_mdio_cmd_context {
 	int octeon_id;
 	wait_queue_head_t wc;
@@ -213,17 +226,23 @@ static int lio_get_link_ksettings(struct net_device *netdev,
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
 	struct oct_link_info *linfo;
-	u32 supported, advertising;
+	u32 supported = 0, advertising = 0;
 
 	linfo = &lio->linfo;
 
 	if (linfo->link.s.if_mode == INTERFACE_MODE_XAUI ||
 	    linfo->link.s.if_mode == INTERFACE_MODE_RXAUI ||
+	    linfo->link.s.if_mode == INTERFACE_MODE_XLAUI ||
 	    linfo->link.s.if_mode == INTERFACE_MODE_XFI) {
 		ecmd->base.port = PORT_FIBRE;
-		supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE |
-			     SUPPORTED_Pause);
-		advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_Pause);
+
+		if (linfo->link.s.speed == SPEED_10000) {
+			supported = SUPPORTED_10000baseT_Full;
+			advertising = ADVERTISED_10000baseT_Full;
+		}
+
+		supported |= SUPPORTED_FIBRE | SUPPORTED_Pause;
+		advertising |= ADVERTISED_Pause;
 		ethtool_convert_legacy_u32_to_link_mode(
 			ecmd->link_modes.supported, supported);
 		ethtool_convert_legacy_u32_to_link_mode(
@@ -1292,95 +1311,103 @@ static int lio_vf_get_sset_count(struct net_device *netdev, int sset)
 	}
 }
 
-static int lio_get_intr_coalesce(struct net_device *netdev,
-				 struct ethtool_coalesce *intr_coal)
+/* Callback function for intrmod */
+static void octnet_intrmod_callback(struct octeon_device *oct_dev,
+				    u32 status,
+				    void *ptr)
 {
-	struct lio *lio = GET_LIO(netdev);
-	struct octeon_device *oct = lio->oct_dev;
-	struct octeon_instr_queue *iq;
-	struct oct_intrmod_cfg *intrmod_cfg;
+	struct octeon_soft_command *sc = (struct octeon_soft_command *)ptr;
+	struct oct_intrmod_context *ctx;
 
-	intrmod_cfg = &oct->intrmod;
+	ctx  = (struct oct_intrmod_context *)sc->ctxptr;
 
-	switch (oct->chip_id) {
-	case OCTEON_CN23XX_PF_VID:
-	case OCTEON_CN23XX_VF_VID:
-		if (!intrmod_cfg->rx_enable) {
-			intr_coal->rx_coalesce_usecs = intrmod_cfg->rx_usecs;
-			intr_coal->rx_max_coalesced_frames =
-				intrmod_cfg->rx_frames;
-		}
-		if (!intrmod_cfg->tx_enable)
-			intr_coal->tx_max_coalesced_frames =
-				intrmod_cfg->tx_frames;
-		break;
-	case OCTEON_CN68XX:
-	case OCTEON_CN66XX: {
-		struct octeon_cn6xxx *cn6xxx =
-			(struct octeon_cn6xxx *)oct->chip;
+	ctx->status = status;
 
-		if (!intrmod_cfg->rx_enable) {
-			intr_coal->rx_coalesce_usecs =
-				CFG_GET_OQ_INTR_TIME(cn6xxx->conf);
-			intr_coal->rx_max_coalesced_frames =
-				CFG_GET_OQ_INTR_PKT(cn6xxx->conf);
-		}
-		iq = oct->instr_queue[lio->linfo.txpciq[0].s.q_no];
-		intr_coal->tx_max_coalesced_frames = iq->fill_threshold;
-		break;
-	}
-	default:
-		netif_info(lio, drv, lio->netdev, "Unknown Chip !!\n");
+	oct_dev = lio_get_device(ctx->octeon_id);
+
+	WRITE_ONCE(ctx->cond, 1);
+
+	/* This barrier is required to be sure that the response has been
+	 * written fully before waking up the handler
+	 */
+	wmb();
+
+	wake_up_interruptible(&ctx->wc);
+}
+
+/*  get interrupt moderation parameters */
+static int octnet_get_intrmod_cfg(struct lio *lio,
+				  struct oct_intrmod_cfg *intr_cfg)
+{
+	struct octeon_soft_command *sc;
+	struct oct_intrmod_context *ctx;
+	struct oct_intrmod_resp *resp;
+	int retval;
+	struct octeon_device *oct_dev = lio->oct_dev;
+
+	/* Alloc soft command */
+	sc = (struct octeon_soft_command *)
+		octeon_alloc_soft_command(oct_dev,
+					  0,
+					  sizeof(struct oct_intrmod_resp),
+					  sizeof(struct oct_intrmod_context));
+
+	if (!sc)
+		return -ENOMEM;
+
+	resp = (struct oct_intrmod_resp *)sc->virtrptr;
+	memset(resp, 0, sizeof(struct oct_intrmod_resp));
+
+	ctx = (struct oct_intrmod_context *)sc->ctxptr;
+	memset(ctx, 0, sizeof(struct oct_intrmod_context));
+	WRITE_ONCE(ctx->cond, 0);
+	ctx->octeon_id = lio_get_device_id(oct_dev);
+	init_waitqueue_head(&ctx->wc);
+
+	sc->iq_no = lio->linfo.txpciq[0].s.q_no;
+
+	octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC,
+				    OPCODE_NIC_INTRMOD_PARAMS, 0, 0, 0);
+
+	sc->callback = octnet_intrmod_callback;
+	sc->callback_arg = sc;
+	sc->wait_time = 1000;
+
+	retval = octeon_send_soft_command(oct_dev, sc);
+	if (retval == IQ_SEND_FAILED) {
+		octeon_free_soft_command(oct_dev, sc);
 		return -EINVAL;
 	}
-	if (intrmod_cfg->rx_enable) {
-		intr_coal->use_adaptive_rx_coalesce =
-			intrmod_cfg->rx_enable;
-		intr_coal->rate_sample_interval =
-			intrmod_cfg->check_intrvl;
-		intr_coal->pkt_rate_high =
-			intrmod_cfg->maxpkt_ratethr;
-		intr_coal->pkt_rate_low =
-			intrmod_cfg->minpkt_ratethr;
-		intr_coal->rx_max_coalesced_frames_high =
-			intrmod_cfg->rx_maxcnt_trigger;
-		intr_coal->rx_coalesce_usecs_high =
-			intrmod_cfg->rx_maxtmr_trigger;
-		intr_coal->rx_coalesce_usecs_low =
-			intrmod_cfg->rx_mintmr_trigger;
-		intr_coal->rx_max_coalesced_frames_low =
-		    intrmod_cfg->rx_mincnt_trigger;
+
+	/* Sleep on a wait queue till the cond flag indicates that the
+	 * response arrived or timed-out.
+	 */
+	if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR) {
+		dev_err(&oct_dev->pci_dev->dev, "Wait interrupted\n");
+		goto intrmod_info_wait_intr;
 	}
-	if ((OCTEON_CN23XX_PF(oct) || OCTEON_CN23XX_VF(oct)) &&
-	    (intrmod_cfg->tx_enable)) {
-		intr_coal->use_adaptive_tx_coalesce = intrmod_cfg->tx_enable;
-		intr_coal->tx_max_coalesced_frames_high =
-		    intrmod_cfg->tx_maxcnt_trigger;
-		intr_coal->tx_max_coalesced_frames_low =
-		    intrmod_cfg->tx_mincnt_trigger;
+
+	retval = ctx->status || resp->status;
+	if (retval) {
+		dev_err(&oct_dev->pci_dev->dev,
+			"Get interrupt moderation parameters failed\n");
+		goto intrmod_info_wait_fail;
 	}
-	return 0;
-}
 
-/* Callback function for intrmod */
-static void octnet_intrmod_callback(struct octeon_device *oct_dev,
-				    u32 status,
-				    void *ptr)
-{
-	struct oct_intrmod_cmd *cmd = ptr;
-	struct octeon_soft_command *sc = cmd->sc;
+	octeon_swap_8B_data((u64 *)&resp->intrmod,
+			    (sizeof(struct oct_intrmod_cfg)) / 8);
+	memcpy(intr_cfg, &resp->intrmod, sizeof(struct oct_intrmod_cfg));
+	octeon_free_soft_command(oct_dev, sc);
 
-	oct_dev = cmd->oct_dev;
+	return 0;
 
-	if (status)
-		dev_err(&oct_dev->pci_dev->dev, "intrmod config failed. Status: %llx\n",
-			CVM_CAST64(status));
-	else
-		dev_info(&oct_dev->pci_dev->dev,
-			 "Rx-Adaptive Interrupt moderation enabled:%llx\n",
-			 oct_dev->intrmod.rx_enable);
+intrmod_info_wait_fail:
 
 	octeon_free_soft_command(oct_dev, sc);
+
+intrmod_info_wait_intr:
+
+	return -ENODEV;
 }
 
 /*  Configure interrupt moderation parameters */
@@ -1388,7 +1415,7 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
 				  struct oct_intrmod_cfg *intr_cfg)
 {
 	struct octeon_soft_command *sc;
-	struct oct_intrmod_cmd *cmd;
+	struct oct_intrmod_context *ctx;
 	struct oct_intrmod_cfg *cfg;
 	int retval;
 	struct octeon_device *oct_dev = lio->oct_dev;
@@ -1398,19 +1425,21 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
 		octeon_alloc_soft_command(oct_dev,
 					  sizeof(struct oct_intrmod_cfg),
 					  0,
-					  sizeof(struct oct_intrmod_cmd));
+					  sizeof(struct oct_intrmod_context));
 
 	if (!sc)
 		return -ENOMEM;
 
-	cmd = (struct oct_intrmod_cmd *)sc->ctxptr;
+	ctx = (struct oct_intrmod_context *)sc->ctxptr;
+
+	WRITE_ONCE(ctx->cond, 0);
+	ctx->octeon_id = lio_get_device_id(oct_dev);
+	init_waitqueue_head(&ctx->wc);
+
 	cfg = (struct oct_intrmod_cfg *)sc->virtdptr;
 
 	memcpy(cfg, intr_cfg, sizeof(struct oct_intrmod_cfg));
 	octeon_swap_8B_data((u64 *)cfg, (sizeof(struct oct_intrmod_cfg)) / 8);
-	cmd->sc = sc;
-	cmd->cfg = cfg;
-	cmd->oct_dev = oct_dev;
 
 	sc->iq_no = lio->linfo.txpciq[0].s.q_no;
 
@@ -1418,7 +1447,7 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
 				    OPCODE_NIC_INTRMOD_CFG, 0, 0, 0);
 
 	sc->callback = octnet_intrmod_callback;
-	sc->callback_arg = cmd;
+	sc->callback_arg = sc;
 	sc->wait_time = 1000;
 
 	retval = octeon_send_soft_command(oct_dev, sc);
@@ -1427,7 +1456,29 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
 		return -EINVAL;
 	}
 
-	return 0;
+	/* Sleep on a wait queue till the cond flag indicates that the
+	 * response arrived or timed-out.
+	 */
+	if (sleep_cond(&ctx->wc, &ctx->cond) != -EINTR) {
+		retval = ctx->status;
+		if (retval)
+			dev_err(&oct_dev->pci_dev->dev,
+				"intrmod config failed. Status: %llx\n",
+				CVM_CAST64(retval));
+		else
+			dev_info(&oct_dev->pci_dev->dev,
+				 "Rx-Adaptive Interrupt moderation %s\n",
+				 (intr_cfg->rx_enable) ?
+				 "enabled" : "disabled");
+
+		octeon_free_soft_command(oct_dev, sc);
+
+		return ((retval) ? -ENODEV : 0);
+	}
+
+	dev_err(&oct_dev->pci_dev->dev, "iq/oq config failed\n");
+
+	return -EINTR;
 }
 
 static void
@@ -1584,80 +1635,106 @@ static int octnet_get_link_stats(struct net_device *netdev)
 	return 0;
 }
 
-/* Enable/Disable auto interrupt Moderation */
-static int oct_cfg_adaptive_intr(struct lio *lio, struct ethtool_coalesce
-				 *intr_coal)
+static int lio_get_intr_coalesce(struct net_device *netdev,
+				 struct ethtool_coalesce *intr_coal)
 {
-	int ret = 0;
+	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
-	struct oct_intrmod_cfg *intrmod_cfg;
-
-	intrmod_cfg = &oct->intrmod;
-
-	if (oct->intrmod.rx_enable || oct->intrmod.tx_enable) {
-		if (intr_coal->rate_sample_interval)
-			intrmod_cfg->check_intrvl =
-				intr_coal->rate_sample_interval;
-		else
-			intrmod_cfg->check_intrvl =
-				LIO_INTRMOD_CHECK_INTERVAL;
+	struct octeon_instr_queue *iq;
+	struct oct_intrmod_cfg intrmod_cfg;
 
-		if (intr_coal->pkt_rate_high)
-			intrmod_cfg->maxpkt_ratethr =
-				intr_coal->pkt_rate_high;
-		else
-			intrmod_cfg->maxpkt_ratethr =
-				LIO_INTRMOD_MAXPKT_RATETHR;
+	if (octnet_get_intrmod_cfg(lio, &intrmod_cfg))
+		return -ENODEV;
 
-		if (intr_coal->pkt_rate_low)
-			intrmod_cfg->minpkt_ratethr =
-				intr_coal->pkt_rate_low;
-		else
-			intrmod_cfg->minpkt_ratethr =
-				LIO_INTRMOD_MINPKT_RATETHR;
+	switch (oct->chip_id) {
+	case OCTEON_CN23XX_PF_VID:
+	case OCTEON_CN23XX_VF_VID: {
+		if (!intrmod_cfg.rx_enable) {
+			intr_coal->rx_coalesce_usecs = oct->rx_coalesce_usecs;
+			intr_coal->rx_max_coalesced_frames =
+				oct->rx_max_coalesced_frames;
+		}
+		if (!intrmod_cfg.tx_enable)
+			intr_coal->tx_max_coalesced_frames =
+				oct->tx_max_coalesced_frames;
+		break;
 	}
-	if (oct->intrmod.rx_enable) {
-		if (intr_coal->rx_max_coalesced_frames_high)
-			intrmod_cfg->rx_maxcnt_trigger =
-				intr_coal->rx_max_coalesced_frames_high;
-		else
-			intrmod_cfg->rx_maxcnt_trigger =
-				LIO_INTRMOD_RXMAXCNT_TRIGGER;
+	case OCTEON_CN68XX:
+	case OCTEON_CN66XX: {
+		struct octeon_cn6xxx *cn6xxx =
+			(struct octeon_cn6xxx *)oct->chip;
 
-		if (intr_coal->rx_coalesce_usecs_high)
-			intrmod_cfg->rx_maxtmr_trigger =
-				intr_coal->rx_coalesce_usecs_high;
-		else
-			intrmod_cfg->rx_maxtmr_trigger =
-				LIO_INTRMOD_RXMAXTMR_TRIGGER;
+		if (!intrmod_cfg.rx_enable) {
+			intr_coal->rx_coalesce_usecs =
+				CFG_GET_OQ_INTR_TIME(cn6xxx->conf);
+			intr_coal->rx_max_coalesced_frames =
+				CFG_GET_OQ_INTR_PKT(cn6xxx->conf);
+		}
+		iq = oct->instr_queue[lio->linfo.txpciq[0].s.q_no];
+		intr_coal->tx_max_coalesced_frames = iq->fill_threshold;
+		break;
+	}
+	default:
+		netif_info(lio, drv, lio->netdev, "Unknown Chip !!\n");
+		return -EINVAL;
+	}
+	if (intrmod_cfg.rx_enable) {
+		intr_coal->use_adaptive_rx_coalesce =
+			intrmod_cfg.rx_enable;
+		intr_coal->rate_sample_interval =
+			intrmod_cfg.check_intrvl;
+		intr_coal->pkt_rate_high =
+			intrmod_cfg.maxpkt_ratethr;
+		intr_coal->pkt_rate_low =
+			intrmod_cfg.minpkt_ratethr;
+		intr_coal->rx_max_coalesced_frames_high =
+			intrmod_cfg.rx_maxcnt_trigger;
+		intr_coal->rx_coalesce_usecs_high =
+			intrmod_cfg.rx_maxtmr_trigger;
+		intr_coal->rx_coalesce_usecs_low =
+			intrmod_cfg.rx_mintmr_trigger;
+		intr_coal->rx_max_coalesced_frames_low =
+			intrmod_cfg.rx_mincnt_trigger;
+	}
+	if ((OCTEON_CN23XX_PF(oct) || OCTEON_CN23XX_VF(oct)) &&
+	    (intrmod_cfg.tx_enable)) {
+		intr_coal->use_adaptive_tx_coalesce =
+			intrmod_cfg.tx_enable;
+		intr_coal->tx_max_coalesced_frames_high =
+			intrmod_cfg.tx_maxcnt_trigger;
+		intr_coal->tx_max_coalesced_frames_low =
+			intrmod_cfg.tx_mincnt_trigger;
+	}
+	return 0;
+}
 
-		if (intr_coal->rx_coalesce_usecs_low)
-			intrmod_cfg->rx_mintmr_trigger =
-				intr_coal->rx_coalesce_usecs_low;
-		else
-			intrmod_cfg->rx_mintmr_trigger =
-				LIO_INTRMOD_RXMINTMR_TRIGGER;
+/* Enable/Disable auto interrupt Moderation */
+static int oct_cfg_adaptive_intr(struct lio *lio,
+				 struct oct_intrmod_cfg *intrmod_cfg,
+				 struct ethtool_coalesce *intr_coal)
+{
+	int ret = 0;
 
-		if (intr_coal->rx_max_coalesced_frames_low)
-			intrmod_cfg->rx_mincnt_trigger =
-				intr_coal->rx_max_coalesced_frames_low;
-		else
-			intrmod_cfg->rx_mincnt_trigger =
-				LIO_INTRMOD_RXMINCNT_TRIGGER;
+	if (intrmod_cfg->rx_enable || intrmod_cfg->tx_enable) {
+		intrmod_cfg->check_intrvl = intr_coal->rate_sample_interval;
+		intrmod_cfg->maxpkt_ratethr = intr_coal->pkt_rate_high;
+		intrmod_cfg->minpkt_ratethr = intr_coal->pkt_rate_low;
 	}
-	if (oct->intrmod.tx_enable) {
-		if (intr_coal->tx_max_coalesced_frames_high)
-			intrmod_cfg->tx_maxcnt_trigger =
-				intr_coal->tx_max_coalesced_frames_high;
-		else
-			intrmod_cfg->tx_maxcnt_trigger =
-				LIO_INTRMOD_TXMAXCNT_TRIGGER;
-		if (intr_coal->tx_max_coalesced_frames_low)
-			intrmod_cfg->tx_mincnt_trigger =
-				intr_coal->tx_max_coalesced_frames_low;
-		else
-			intrmod_cfg->tx_mincnt_trigger =
-				LIO_INTRMOD_TXMINCNT_TRIGGER;
+	if (intrmod_cfg->rx_enable) {
+		intrmod_cfg->rx_maxcnt_trigger =
+			intr_coal->rx_max_coalesced_frames_high;
+		intrmod_cfg->rx_maxtmr_trigger =
+			intr_coal->rx_coalesce_usecs_high;
+		intrmod_cfg->rx_mintmr_trigger =
+			intr_coal->rx_coalesce_usecs_low;
+		intrmod_cfg->rx_mincnt_trigger =
+			intr_coal->rx_max_coalesced_frames_low;
+	}
+	if (intrmod_cfg->tx_enable) {
+		intrmod_cfg->tx_maxcnt_trigger =
+			intr_coal->tx_max_coalesced_frames_high;
+		intrmod_cfg->tx_mincnt_trigger =
+			intr_coal->tx_max_coalesced_frames_low;
 	}
 
 	ret = octnet_set_intrmod_cfg(lio, intrmod_cfg);
@@ -1666,7 +1743,9 @@ static int oct_cfg_adaptive_intr(struct lio *lio, struct ethtool_coalesce
 }
 
 static int
-oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
+oct_cfg_rx_intrcnt(struct lio *lio,
+		   struct oct_intrmod_cfg *intrmod,
+		   struct ethtool_coalesce *intr_coal)
 {
 	struct octeon_device *oct = lio->oct_dev;
 	u32 rx_max_coalesced_frames;
@@ -1692,7 +1771,7 @@ oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
 		int q_no;
 
 		if (!intr_coal->rx_max_coalesced_frames)
-			rx_max_coalesced_frames = oct->intrmod.rx_frames;
+			rx_max_coalesced_frames = intrmod->rx_frames;
 		else
 			rx_max_coalesced_frames =
 			    intr_coal->rx_max_coalesced_frames;
@@ -1703,17 +1782,18 @@ oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
 			    (octeon_read_csr64(
 				 oct, CN23XX_SLI_OQ_PKT_INT_LEVELS(q_no)) &
 			     (0x3fffff00000000UL)) |
-				rx_max_coalesced_frames);
+				(rx_max_coalesced_frames - 1));
 			/*consider setting resend bit*/
 		}
-		oct->intrmod.rx_frames = rx_max_coalesced_frames;
+		intrmod->rx_frames = rx_max_coalesced_frames;
+		oct->rx_max_coalesced_frames = rx_max_coalesced_frames;
 		break;
 	}
 	case OCTEON_CN23XX_VF_VID: {
 		int q_no;
 
 		if (!intr_coal->rx_max_coalesced_frames)
-			rx_max_coalesced_frames = oct->intrmod.rx_frames;
+			rx_max_coalesced_frames = intrmod->rx_frames;
 		else
 			rx_max_coalesced_frames =
 			    intr_coal->rx_max_coalesced_frames;
@@ -1724,9 +1804,10 @@ oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
 				 oct, CN23XX_VF_SLI_OQ_PKT_INT_LEVELS(q_no)) &
 			     (0x3fffff00000000UL)) |
 				rx_max_coalesced_frames);
-			/* consider writing to resend bit here */
+			/*consider writing to resend bit here*/
 		}
-		oct->intrmod.rx_frames = rx_max_coalesced_frames;
+		intrmod->rx_frames = rx_max_coalesced_frames;
+		oct->rx_max_coalesced_frames = rx_max_coalesced_frames;
 		break;
 	}
 	default:
@@ -1736,6 +1817,7 @@ oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
 }
 
 static int oct_cfg_rx_intrtime(struct lio *lio,
+			       struct oct_intrmod_cfg *intrmod,
 			       struct ethtool_coalesce *intr_coal)
 {
 	struct octeon_device *oct = lio->oct_dev;
@@ -1766,7 +1848,7 @@ static int oct_cfg_rx_intrtime(struct lio *lio,
 		int q_no;
 
 		if (!intr_coal->rx_coalesce_usecs)
-			rx_coalesce_usecs = oct->intrmod.rx_usecs;
+			rx_coalesce_usecs = intrmod->rx_usecs;
 		else
 			rx_coalesce_usecs = intr_coal->rx_coalesce_usecs;
 		time_threshold =
@@ -1775,11 +1857,12 @@ static int oct_cfg_rx_intrtime(struct lio *lio,
 			q_no += oct->sriov_info.pf_srn;
 			octeon_write_csr64(oct,
 					   CN23XX_SLI_OQ_PKT_INT_LEVELS(q_no),
-					   (oct->intrmod.rx_frames |
-					    (time_threshold << 32)));
+					   (intrmod->rx_frames |
+					    ((u64)time_threshold << 32)));
 			/*consider writing to resend bit here*/
 		}
-		oct->intrmod.rx_usecs = rx_coalesce_usecs;
+		intrmod->rx_usecs = rx_coalesce_usecs;
+		oct->rx_coalesce_usecs = rx_coalesce_usecs;
 		break;
 	}
 	case OCTEON_CN23XX_VF_VID: {
@@ -1787,7 +1870,7 @@ static int oct_cfg_rx_intrtime(struct lio *lio,
 		int q_no;
 
 		if (!intr_coal->rx_coalesce_usecs)
-			rx_coalesce_usecs = oct->intrmod.rx_usecs;
+			rx_coalesce_usecs = intrmod->rx_usecs;
 		else
 			rx_coalesce_usecs = intr_coal->rx_coalesce_usecs;
 
@@ -1796,11 +1879,12 @@ static int oct_cfg_rx_intrtime(struct lio *lio,
 		for (q_no = 0; q_no < oct->num_oqs; q_no++) {
 			octeon_write_csr64(
 				oct, CN23XX_VF_SLI_OQ_PKT_INT_LEVELS(q_no),
-				(oct->intrmod.rx_frames |
-				 (time_threshold << 32)));
-			/* consider setting resend bit */
+				(intrmod->rx_frames |
+				 ((u64)time_threshold << 32)));
+			/*consider setting resend bit*/
 		}
-		oct->intrmod.rx_usecs = rx_coalesce_usecs;
+		intrmod->rx_usecs = rx_coalesce_usecs;
+		oct->rx_coalesce_usecs = rx_coalesce_usecs;
 		break;
 	}
 	default:
@@ -1811,8 +1895,9 @@ static int oct_cfg_rx_intrtime(struct lio *lio,
 }
 
 static int
-oct_cfg_tx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal
-		   __attribute__((unused)))
+oct_cfg_tx_intrcnt(struct lio *lio,
+		   struct oct_intrmod_cfg *intrmod,
+		   struct ethtool_coalesce *intr_coal)
 {
 	struct octeon_device *oct = lio->oct_dev;
 	u32 iq_intr_pkt;
@@ -1839,12 +1924,13 @@ oct_cfg_tx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal
 			val = readq(inst_cnt_reg);
 			/*clear wmark and count.dont want to write count back*/
 			val = (val & 0xFFFF000000000000ULL) |
-			      ((u64)iq_intr_pkt
+			      ((u64)(iq_intr_pkt - 1)
 			       << CN23XX_PKT_IN_DONE_WMARK_BIT_POS);
 			writeq(val, inst_cnt_reg);
 			/*consider setting resend bit*/
 		}
-		oct->intrmod.tx_frames = iq_intr_pkt;
+		intrmod->tx_frames = iq_intr_pkt;
+		oct->tx_max_coalesced_frames = iq_intr_pkt;
 		break;
 	}
 	default:
@@ -1859,6 +1945,7 @@ static int lio_set_intr_coalesce(struct net_device *netdev,
 	struct lio *lio = GET_LIO(netdev);
 	int ret;
 	struct octeon_device *oct = lio->oct_dev;
+	struct oct_intrmod_cfg intrmod = {0};
 	u32 j, q_no;
 	int db_max, db_min;
 
@@ -1877,8 +1964,8 @@ static int lio_set_intr_coalesce(struct net_device *netdev,
 		} else {
 			dev_err(&oct->pci_dev->dev,
 				"LIQUIDIO: Invalid tx-frames:%d. Range is min:%d max:%d\n",
-				intr_coal->tx_max_coalesced_frames, db_min,
-				db_max);
+				intr_coal->tx_max_coalesced_frames,
+				db_min, db_max);
 			return -EINVAL;
 		}
 		break;
@@ -1889,24 +1976,36 @@ static int lio_set_intr_coalesce(struct net_device *netdev,
 		return -EINVAL;
 	}
 
-	oct->intrmod.rx_enable = intr_coal->use_adaptive_rx_coalesce ? 1 : 0;
-	oct->intrmod.tx_enable = intr_coal->use_adaptive_tx_coalesce ? 1 : 0;
+	intrmod.rx_enable = intr_coal->use_adaptive_rx_coalesce ? 1 : 0;
+	intrmod.tx_enable = intr_coal->use_adaptive_tx_coalesce ? 1 : 0;
+	intrmod.rx_frames = CFG_GET_OQ_INTR_PKT(octeon_get_conf(oct));
+	intrmod.rx_usecs = CFG_GET_OQ_INTR_TIME(octeon_get_conf(oct));
+	intrmod.tx_frames = CFG_GET_IQ_INTR_PKT(octeon_get_conf(oct));
 
-	ret = oct_cfg_adaptive_intr(lio, intr_coal);
+	ret = oct_cfg_adaptive_intr(lio, &intrmod, intr_coal);
 
 	if (!intr_coal->use_adaptive_rx_coalesce) {
-		ret = oct_cfg_rx_intrtime(lio, intr_coal);
+		ret = oct_cfg_rx_intrtime(lio, &intrmod, intr_coal);
 		if (ret)
 			goto ret_intrmod;
 
-		ret = oct_cfg_rx_intrcnt(lio, intr_coal);
+		ret = oct_cfg_rx_intrcnt(lio, &intrmod, intr_coal);
 		if (ret)
 			goto ret_intrmod;
+	} else {
+		oct->rx_coalesce_usecs =
+			CFG_GET_OQ_INTR_TIME(octeon_get_conf(oct));
+		oct->rx_max_coalesced_frames =
+			CFG_GET_OQ_INTR_PKT(octeon_get_conf(oct));
 	}
+
 	if (!intr_coal->use_adaptive_tx_coalesce) {
-		ret = oct_cfg_tx_intrcnt(lio, intr_coal);
+		ret = oct_cfg_tx_intrcnt(lio, &intrmod, intr_coal);
 		if (ret)
 			goto ret_intrmod;
+	} else {
+		oct->tx_max_coalesced_frames =
+			CFG_GET_IQ_INTR_PKT(octeon_get_conf(oct));
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 92f46b1375c3..a8426d3d05d0 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -16,6 +16,7 @@
  * NONINFRINGEMENT.  See the GNU General Public License for more details.
  ***********************************************************************/
 #include <linux/module.h>
+#include <linux/interrupt.h>
 #include <linux/pci.h>
 #include <linux/firmware.h>
 #include <net/vxlan.h>
@@ -60,12 +61,6 @@ MODULE_PARM_DESC(fw_type, "Type of firmware to be loaded. Default \"nic\"");
 
 static int ptp_enable = 1;
 
-/* Bit mask values for lio->ifstate */
-#define   LIO_IFSTATE_DROQ_OPS             0x01
-#define   LIO_IFSTATE_REGISTERED           0x02
-#define   LIO_IFSTATE_RUNNING              0x04
-#define   LIO_IFSTATE_RX_TIMESTAMP_ENABLED 0x08
-
 /* Polling interval for determining when NIC application is alive */
 #define LIQUIDIO_STARTER_POLL_INTERVAL_MS 100
 
@@ -531,36 +526,6 @@ static void liquidio_deinit_pci(void)
 }
 
 /**
- * \brief check interface state
- * @param lio per-network private data
- * @param state_flag flag state to check
- */
-static inline int ifstate_check(struct lio *lio, int state_flag)
-{
-	return atomic_read(&lio->ifstate) & state_flag;
-}
-
-/**
- * \brief set interface state
- * @param lio per-network private data
- * @param state_flag flag state to set
- */
-static inline void ifstate_set(struct lio *lio, int state_flag)
-{
-	atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) | state_flag));
-}
-
-/**
- * \brief clear interface state
- * @param lio per-network private data
- * @param state_flag flag state to clear
- */
-static inline void ifstate_reset(struct lio *lio, int state_flag)
-{
-	atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) & ~(state_flag)));
-}
-
-/**
  * \brief Stop Tx queues
  * @param netdev network device
  */
@@ -748,7 +713,8 @@ static void delete_glists(struct lio *lio)
 				kfree(g);
 		} while (g);
 
-		if (lio->glists_virt_base && lio->glists_virt_base[i]) {
+		if (lio->glists_virt_base && lio->glists_virt_base[i] &&
+		    lio->glists_dma_base && lio->glists_dma_base[i]) {
 			lio_dma_free(lio->oct_dev,
 				     lio->glist_entry_size * lio->tx_qsize,
 				     lio->glists_virt_base[i],
@@ -805,7 +771,7 @@ static int setup_glists(struct octeon_device *oct, struct lio *lio, int num_iqs)
 	}
 
 	for (i = 0; i < num_iqs; i++) {
-		int numa_node = cpu_to_node(i % num_online_cpus());
+		int numa_node = dev_to_node(&oct->pci_dev->dev);
 
 		spin_lock_init(&lio->glist_lock[i]);
 
@@ -967,14 +933,13 @@ static void update_txq_status(struct octeon_device *oct, int iq_num)
 			INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq_num,
 						  tx_restart, 1);
 			netif_wake_subqueue(netdev, iq->q_index);
-		} else {
-			if (!octnet_iq_is_full(oct, lio->txq)) {
-				INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev,
-							  lio->txq,
-							  tx_restart, 1);
-				wake_q(netdev, lio->txq);
-			}
 		}
+	} else if (netif_queue_stopped(netdev) &&
+		   lio->linfo.link.s.link_up &&
+		   (!octnet_iq_is_full(oct, lio->txq))) {
+		INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev,
+					  lio->txq, tx_restart, 1);
+		netif_wake_queue(netdev);
 	}
 }
 
@@ -1084,16 +1049,35 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 	int i;
 	int num_ioq_vectors;
 	int num_alloc_ioq_vectors;
+	char *queue_irq_names = NULL;
+	char *aux_irq_name = NULL;
 
 	if (OCTEON_CN23XX_PF(oct) && oct->msix_on) {
 		oct->num_msix_irqs = oct->sriov_info.num_pf_rings;
 		/* one non ioq interrupt for handling sli_mac_pf_int_sum */
 		oct->num_msix_irqs += 1;
 
+		/* allocate storage for the names assigned to each irq */
+		oct->irq_name_storage =
+			kcalloc((MAX_IOQ_INTERRUPTS_PER_PF + 1), INTRNAMSIZ,
+				GFP_KERNEL);
+		if (!oct->irq_name_storage) {
+			dev_err(&oct->pci_dev->dev, "Irq name storage alloc failed...\n");
+			return -ENOMEM;
+		}
+
+		queue_irq_names = oct->irq_name_storage;
+		aux_irq_name = &queue_irq_names
+				[IRQ_NAME_OFF(MAX_IOQ_INTERRUPTS_PER_PF)];
+
 		oct->msix_entries = kcalloc(
 		    oct->num_msix_irqs, sizeof(struct msix_entry), GFP_KERNEL);
-		if (!oct->msix_entries)
-			return 1;
+		if (!oct->msix_entries) {
+			dev_err(&oct->pci_dev->dev, "Memory Alloc failed...\n");
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
+			return -ENOMEM;
+		}
 
 		msix_entries = (struct msix_entry *)oct->msix_entries;
 		/*Assumption is that pf msix vectors start from pf srn to pf to
@@ -1111,7 +1095,9 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 			dev_err(&oct->pci_dev->dev, "unable to Allocate MSI-X interrupts\n");
 			kfree(oct->msix_entries);
 			oct->msix_entries = NULL;
-			return 1;
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
+			return num_alloc_ioq_vectors;
 		}
 		dev_dbg(&oct->pci_dev->dev, "OCTEON: Enough MSI-X interrupts are allocated...\n");
 
@@ -1119,9 +1105,12 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 
 		/** For PF, there is one non-ioq interrupt handler */
 		num_ioq_vectors -= 1;
+
+		snprintf(aux_irq_name, INTRNAMSIZ,
+			 "LiquidIO%u-pf%u-aux", oct->octeon_id, oct->pf_num);
 		irqret = request_irq(msix_entries[num_ioq_vectors].vector,
-				     liquidio_legacy_intr_handler, 0, "octeon",
-				     oct);
+				     liquidio_legacy_intr_handler, 0,
+				     aux_irq_name, oct);
 		if (irqret) {
 			dev_err(&oct->pci_dev->dev,
 				"OCTEON: Request_irq failed for MSIX interrupt Error: %d\n",
@@ -1129,13 +1118,20 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 			pci_disable_msix(oct->pci_dev);
 			kfree(oct->msix_entries);
 			oct->msix_entries = NULL;
-			return 1;
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
+			return irqret;
 		}
 
 		for (i = 0; i < num_ioq_vectors; i++) {
+			snprintf(&queue_irq_names[IRQ_NAME_OFF(i)], INTRNAMSIZ,
+				 "LiquidIO%u-pf%u-rxtx-%u",
+				 oct->octeon_id, oct->pf_num, i);
+
 			irqret = request_irq(msix_entries[i].vector,
 					     liquidio_msix_intr_handler, 0,
-					     "octeon", &oct->ioq_vector[i]);
+					     &queue_irq_names[IRQ_NAME_OFF(i)],
+					     &oct->ioq_vector[i]);
 			if (irqret) {
 				dev_err(&oct->pci_dev->dev,
 					"OCTEON: Request_irq failed for MSIX interrupt Error: %d\n",
@@ -1155,7 +1151,9 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 				pci_disable_msix(oct->pci_dev);
 				kfree(oct->msix_entries);
 				oct->msix_entries = NULL;
-				return 1;
+				kfree(oct->irq_name_storage);
+				oct->irq_name_storage = NULL;
+				return irqret;
 			}
 			oct->ioq_vector[i].vector = msix_entries[i].vector;
 			/* assign the cpu mask for this msix interrupt vector */
@@ -1173,15 +1171,29 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 		else
 			oct->flags |= LIO_FLAG_MSI_ENABLED;
 
+		/* allocate storage for the names assigned to the irq */
+		oct->irq_name_storage = kcalloc(1, INTRNAMSIZ, GFP_KERNEL);
+		if (!oct->irq_name_storage)
+			return -ENOMEM;
+
+		queue_irq_names = oct->irq_name_storage;
+
+		snprintf(&queue_irq_names[IRQ_NAME_OFF(0)], INTRNAMSIZ,
+			 "LiquidIO%u-pf%u-rxtx-%u",
+			 oct->octeon_id, oct->pf_num, 0);
+
 		irqret = request_irq(oct->pci_dev->irq,
-				     liquidio_legacy_intr_handler, IRQF_SHARED,
-				     "octeon", oct);
+				     liquidio_legacy_intr_handler,
+				     IRQF_SHARED,
+				     &queue_irq_names[IRQ_NAME_OFF(0)], oct);
 		if (irqret) {
 			if (oct->flags & LIO_FLAG_MSI_ENABLED)
 				pci_disable_msi(oct->pci_dev);
 			dev_err(&oct->pci_dev->dev, "Request IRQ failed with code: %d\n",
 				irqret);
-			return 1;
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
+			return irqret;
 		}
 	}
 	return 0;
@@ -1369,6 +1381,12 @@ liquidio_probe(struct pci_dev *pdev,
 	return 0;
 }
 
+static bool fw_type_is_none(void)
+{
+	return strncmp(fw_type, LIO_FW_NAME_TYPE_NONE,
+		       sizeof(LIO_FW_NAME_TYPE_NONE)) == 0;
+}
+
 /**
  *\brief Destroy resources associated with octeon device
  * @param pdev PCI device structure
@@ -1449,6 +1467,9 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 				pci_disable_msi(oct->pci_dev);
 		}
 
+		kfree(oct->irq_name_storage);
+		oct->irq_name_storage = NULL;
+
 	/* fallthrough */
 	case OCT_DEV_MSIX_ALLOC_VECTOR_DONE:
 		if (OCTEON_CN23XX_PF(oct))
@@ -1508,9 +1529,12 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 
 		/* fallthrough */
 	case OCT_DEV_PCI_MAP_DONE:
-		/* Soft reset the octeon device before exiting */
-		if ((!OCTEON_CN23XX_PF(oct)) || !oct->octeon_id)
-			oct->fn_list.soft_reset(oct);
+		if (!fw_type_is_none()) {
+			/* Soft reset the octeon device before exiting */
+			if (!OCTEON_CN23XX_PF(oct) ||
+			    (OCTEON_CN23XX_PF(oct) && !oct->octeon_id))
+				oct->fn_list.soft_reset(oct);
+		}
 
 		octeon_unmap_pci_barx(oct, 0);
 		octeon_unmap_pci_barx(oct, 1);
@@ -1643,6 +1667,15 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
 	if (atomic_read(&lio->ifstate) & LIO_IFSTATE_RUNNING)
 		liquidio_stop(netdev);
 
+	if (fw_type_is_none()) {
+		struct octnic_ctrl_pkt nctrl;
+
+		memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+		nctrl.ncmd.s.cmd = OCTNET_CMD_RESET_PF;
+		nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
+		octnet_send_nic_ctrl_pkt(oct, &nctrl);
+	}
+
 	if (oct->props[lio->ifidx].napi_enabled == 1) {
 		list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list)
 			napi_disable(napi);
@@ -1658,6 +1691,8 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
 
 	cleanup_link_status_change_wq(netdev);
 
+	cleanup_rx_oom_poll_fn(netdev);
+
 	delete_glists(lio);
 
 	free_netdev(netdev);
@@ -2126,8 +2161,7 @@ static int load_firmware(struct octeon_device *oct)
 	char fw_name[LIO_MAX_FW_FILENAME_LEN];
 	char *tmp_fw_type;
 
-	if (strncmp(fw_type, LIO_FW_NAME_TYPE_NONE,
-		    sizeof(LIO_FW_NAME_TYPE_NONE)) == 0) {
+	if (fw_type_is_none()) {
 		dev_info(&oct->pci_dev->dev, "Skipping firmware load\n");
 		return ret;
 	}
@@ -2211,8 +2245,8 @@ static void if_cfg_callback(struct octeon_device *oct,
 
 	oct = lio_get_device(ctx->octeon_id);
 	if (resp->status)
-		dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: %llx\n",
-			CVM_CAST64(resp->status));
+		dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: 0x%llx (0x%08x)\n",
+			CVM_CAST64(resp->status), status);
 	WRITE_ONCE(ctx->cond, 1);
 
 	snprintf(oct->fw_info.liquidio_firmware_version, 32, "%s",
@@ -2437,8 +2471,11 @@ static int liquidio_napi_poll(struct napi_struct *napi, int budget)
 	/* Flush the instruction queue */
 	iq = oct->instr_queue[iq_no];
 	if (iq) {
-		/* Process iq buffers with in the budget limits */
-		tx_done = octeon_flush_iq(oct, iq, budget);
+		if (atomic_read(&iq->instr_pending))
+			/* Process iq buffers with in the budget limits */
+			tx_done = octeon_flush_iq(oct, iq, budget);
+		else
+			tx_done = 1;
 		/* Update iq read-index rather than waiting for next interrupt.
 		 * Return back if tx_done is false.
 		 */
@@ -2555,6 +2592,15 @@ static inline int setup_io_queues(struct octeon_device *octeon_dev,
 				__func__);
 			return 1;
 		}
+
+		if (octeon_dev->ioq_vector) {
+			struct octeon_ioq_vector *ioq_vector;
+
+			ioq_vector = &octeon_dev->ioq_vector[q];
+			netif_set_xps_queue(netdev,
+					    &ioq_vector->affinity_mask,
+					    ioq_vector->iq_index);
+		}
 	}
 
 	return 0;
@@ -3596,7 +3642,8 @@ static int __liquidio_set_vf_mac(struct net_device *netdev, int vfidx,
 	nctrl.ncmd.s.param2 = (is_admin_assigned ? 1 : 0);
 	nctrl.ncmd.s.more = 1;
 	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
-	nctrl.cb_fn = 0;
+	nctrl.netpndev = (u64)netdev;
+	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
 	nctrl.wait_time = LIO_CMD_WAIT_TM;
 
 	nctrl.udd[0] = 0;
@@ -4122,6 +4169,9 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 		if (setup_link_status_change_wq(netdev))
 			goto setup_nic_dev_fail;
 
+		if (setup_rx_oom_poll_fn(netdev))
+			goto setup_nic_dev_fail;
+
 		/* Register the network device with the OS */
 		if (register_netdev(netdev)) {
 			dev_err(&octeon_dev->pci_dev->dev, "Device registration failed\n");
@@ -4271,7 +4321,6 @@ static int liquidio_enable_sriov(struct pci_dev *dev, int num_vfs)
  */
 static int liquidio_init_nic_module(struct octeon_device *oct)
 {
-	struct oct_intrmod_cfg *intrmod_cfg;
 	int i, retval = 0;
 	int num_nic_ports = CFG_GET_NUM_NIC_PORTS(octeon_get_conf(oct));
 
@@ -4296,22 +4345,6 @@ static int liquidio_init_nic_module(struct octeon_device *oct)
 
 	liquidio_ptp_init(oct);
 
-	/* Initialize interrupt moderation params */
-	intrmod_cfg = &((struct octeon_device *)oct)->intrmod;
-	intrmod_cfg->rx_enable = 1;
-	intrmod_cfg->check_intrvl = LIO_INTRMOD_CHECK_INTERVAL;
-	intrmod_cfg->maxpkt_ratethr = LIO_INTRMOD_MAXPKT_RATETHR;
-	intrmod_cfg->minpkt_ratethr = LIO_INTRMOD_MINPKT_RATETHR;
-	intrmod_cfg->rx_maxcnt_trigger = LIO_INTRMOD_RXMAXCNT_TRIGGER;
-	intrmod_cfg->rx_maxtmr_trigger = LIO_INTRMOD_RXMAXTMR_TRIGGER;
-	intrmod_cfg->rx_mintmr_trigger = LIO_INTRMOD_RXMINTMR_TRIGGER;
-	intrmod_cfg->rx_mincnt_trigger = LIO_INTRMOD_RXMINCNT_TRIGGER;
-	intrmod_cfg->tx_enable = 1;
-	intrmod_cfg->tx_maxcnt_trigger = LIO_INTRMOD_TXMAXCNT_TRIGGER;
-	intrmod_cfg->tx_mincnt_trigger = LIO_INTRMOD_TXMINCNT_TRIGGER;
-	intrmod_cfg->rx_frames = CFG_GET_OQ_INTR_PKT(octeon_get_conf(oct));
-	intrmod_cfg->rx_usecs = CFG_GET_OQ_INTR_TIME(octeon_get_conf(oct));
-	intrmod_cfg->tx_frames = CFG_GET_IQ_INTR_PKT(octeon_get_conf(oct));
 	dev_dbg(&oct->pci_dev->dev, "Network interfaces ready\n");
 
 	return retval;
@@ -4447,14 +4480,16 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
 	if (OCTEON_CN23XX_PF(octeon_dev)) {
 		if (!cn23xx_fw_loaded(octeon_dev)) {
 			fw_loaded = 0;
-			/* Do a soft reset of the Octeon device. */
-			if (octeon_dev->fn_list.soft_reset(octeon_dev))
-				return 1;
-			/* things might have changed */
-			if (!cn23xx_fw_loaded(octeon_dev))
-				fw_loaded = 0;
-			else
-				fw_loaded = 1;
+			if (!fw_type_is_none()) {
+				/* Do a soft reset of the Octeon device. */
+				if (octeon_dev->fn_list.soft_reset(octeon_dev))
+					return 1;
+				/* things might have changed */
+				if (!cn23xx_fw_loaded(octeon_dev))
+					fw_loaded = 0;
+				else
+					fw_loaded = 1;
+			}
 		} else {
 			fw_loaded = 1;
 		}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index 7b83be4ce1fe..174d748b5928 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -16,6 +16,7 @@
  * NONINFRINGEMENT.  See the GNU General Public License for more details.
  ***********************************************************************/
 #include <linux/module.h>
+#include <linux/interrupt.h>
 #include <linux/pci.h>
 #include <net/vxlan.h>
 #include "liquidio_common.h"
@@ -39,12 +40,6 @@ MODULE_PARM_DESC(debug, "NETIF_MSG debug bits");
 
 #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
 
-/* Bit mask values for lio->ifstate */
-#define   LIO_IFSTATE_DROQ_OPS             0x01
-#define   LIO_IFSTATE_REGISTERED           0x02
-#define   LIO_IFSTATE_RUNNING              0x04
-#define   LIO_IFSTATE_RX_TIMESTAMP_ENABLED 0x08
-
 struct liquidio_if_cfg_context {
 	int octeon_id;
 
@@ -336,36 +331,6 @@ static struct pci_driver liquidio_vf_pci_driver = {
 };
 
 /**
- * \brief check interface state
- * @param lio per-network private data
- * @param state_flag flag state to check
- */
-static int ifstate_check(struct lio *lio, int state_flag)
-{
-	return atomic_read(&lio->ifstate) & state_flag;
-}
-
-/**
- * \brief set interface state
- * @param lio per-network private data
- * @param state_flag flag state to set
- */
-static void ifstate_set(struct lio *lio, int state_flag)
-{
-	atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) | state_flag));
-}
-
-/**
- * \brief clear interface state
- * @param lio per-network private data
- * @param state_flag flag state to clear
- */
-static void ifstate_reset(struct lio *lio, int state_flag)
-{
-	atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) & ~(state_flag)));
-}
-
-/**
  * \brief Stop Tx queues
  * @param netdev network device
  */
@@ -506,7 +471,8 @@ static void delete_glists(struct lio *lio)
 				kfree(g);
 		} while (g);
 
-		if (lio->glists_virt_base && lio->glists_virt_base[i]) {
+		if (lio->glists_virt_base && lio->glists_virt_base[i] &&
+		    lio->glists_dma_base && lio->glists_dma_base[i]) {
 			lio_dma_free(lio->oct_dev,
 				     lio->glist_entry_size * lio->tx_qsize,
 				     lio->glists_virt_base[i],
@@ -722,13 +688,12 @@ static void update_txq_status(struct octeon_device *oct, int iq_num)
 			netif_wake_subqueue(netdev, iq->q_index);
 			INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq_num,
 						  tx_restart, 1);
-		} else {
-			if (!octnet_iq_is_full(oct, lio->txq)) {
-				INCR_INSTRQUEUE_PKT_COUNT(
-				    lio->oct_dev, lio->txq, tx_restart, 1);
-				wake_q(netdev, lio->txq);
-			}
 		}
+	} else if (netif_queue_stopped(netdev) && lio->linfo.link.s.link_up &&
+		   (!octnet_iq_is_full(oct, lio->txq))) {
+		INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev,
+					  lio->txq, tx_restart, 1);
+		netif_wake_queue(netdev);
 	}
 }
 
@@ -780,6 +745,7 @@ liquidio_msix_intr_handler(int irq __attribute__((unused)), void *dev)
 static int octeon_setup_interrupt(struct octeon_device *oct)
 {
 	struct msix_entry *msix_entries;
+	char *queue_irq_names = NULL;
 	int num_alloc_ioq_vectors;
 	int num_ioq_vectors;
 	int irqret;
@@ -788,10 +754,25 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 	if (oct->msix_on) {
 		oct->num_msix_irqs = oct->sriov_info.rings_per_vf;
 
+		/* allocate storage for the names assigned to each irq */
+		oct->irq_name_storage =
+			kcalloc(MAX_IOQ_INTERRUPTS_PER_VF, INTRNAMSIZ,
+				GFP_KERNEL);
+		if (!oct->irq_name_storage) {
+			dev_err(&oct->pci_dev->dev, "Irq name storage alloc failed...\n");
+			return -ENOMEM;
+		}
+
+		queue_irq_names = oct->irq_name_storage;
+
 		oct->msix_entries = kcalloc(
 		    oct->num_msix_irqs, sizeof(struct msix_entry), GFP_KERNEL);
-		if (!oct->msix_entries)
-			return 1;
+		if (!oct->msix_entries) {
+			dev_err(&oct->pci_dev->dev, "Memory Alloc failed...\n");
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
+			return -ENOMEM;
+		}
 
 		msix_entries = (struct msix_entry *)oct->msix_entries;
 
@@ -805,16 +786,23 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 			dev_err(&oct->pci_dev->dev, "unable to Allocate MSI-X interrupts\n");
 			kfree(oct->msix_entries);
 			oct->msix_entries = NULL;
-			return 1;
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
+			return num_alloc_ioq_vectors;
 		}
 		dev_dbg(&oct->pci_dev->dev, "OCTEON: Enough MSI-X interrupts are allocated...\n");
 
 		num_ioq_vectors = oct->num_msix_irqs;
 
 		for (i = 0; i < num_ioq_vectors; i++) {
+			snprintf(&queue_irq_names[IRQ_NAME_OFF(i)], INTRNAMSIZ,
+				 "LiquidIO%u-vf%u-rxtx-%u",
+				 oct->octeon_id, oct->vf_num, i);
+
 			irqret = request_irq(msix_entries[i].vector,
 					     liquidio_msix_intr_handler, 0,
-					     "octeon", &oct->ioq_vector[i]);
+					     &queue_irq_names[IRQ_NAME_OFF(i)],
+					     &oct->ioq_vector[i]);
 			if (irqret) {
 				dev_err(&oct->pci_dev->dev,
 					"OCTEON: Request_irq failed for MSIX interrupt Error: %d\n",
@@ -830,7 +818,9 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
 				pci_disable_msix(oct->pci_dev);
 				kfree(oct->msix_entries);
 				oct->msix_entries = NULL;
-				return 1;
+				kfree(oct->irq_name_storage);
+				oct->irq_name_storage = NULL;
+				return irqret;
 			}
 			oct->ioq_vector[i].vector = msix_entries[i].vector;
 			/* assign the cpu mask for this msix interrupt vector */
@@ -975,6 +965,8 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 			pci_disable_msix(oct->pci_dev);
 			kfree(oct->msix_entries);
 			oct->msix_entries = NULL;
+			kfree(oct->irq_name_storage);
+			oct->irq_name_storage = NULL;
 		}
 		/* Soft reset the octeon device before exiting */
 		if (oct->pci_dev->reset_fn)
@@ -1163,6 +1155,8 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
 	if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED)
 		unregister_netdev(netdev);
 
+	cleanup_rx_oom_poll_fn(netdev);
+
 	cleanup_link_status_change_wq(netdev);
 
 	delete_glists(lio);
@@ -1642,8 +1636,12 @@ static int liquidio_napi_poll(struct napi_struct *napi, int budget)
 	/* Flush the instruction queue */
 	iq = oct->instr_queue[iq_no];
 	if (iq) {
-		/* Process iq buffers with in the budget limits */
-		tx_done = octeon_flush_iq(oct, iq, budget);
+		if (atomic_read(&iq->instr_pending))
+			/* Process iq buffers with in the budget limits */
+			tx_done = octeon_flush_iq(oct, iq, budget);
+		else
+			tx_done = 1;
+
 		/* Update iq read-index rather than waiting for next interrupt.
 		 * Return back if tx_done is false.
 		 */
@@ -3003,6 +3001,9 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 		if (setup_link_status_change_wq(netdev))
 			goto setup_nic_dev_fail;
 
+		if (setup_rx_oom_poll_fn(netdev))
+			goto setup_nic_dev_fail;
+
 		/* Register the network device with the OS */
 		if (register_netdev(netdev)) {
 			dev_err(&octeon_dev->pci_dev->dev, "Device registration failed\n");
@@ -3057,7 +3058,6 @@ setup_nic_wait_intr:
  */
 static int liquidio_init_nic_module(struct octeon_device *oct)
 {
-	struct oct_intrmod_cfg *intrmod_cfg;
 	int num_nic_ports = 1;
 	int i, retval = 0;
 
@@ -3079,22 +3079,6 @@ static int liquidio_init_nic_module(struct octeon_device *oct)
 		goto octnet_init_failure;
 	}
 
-	/* Initialize interrupt moderation params */
-	intrmod_cfg = &((struct octeon_device *)oct)->intrmod;
-	intrmod_cfg->rx_enable = 1;
-	intrmod_cfg->check_intrvl = LIO_INTRMOD_CHECK_INTERVAL;
-	intrmod_cfg->maxpkt_ratethr = LIO_INTRMOD_MAXPKT_RATETHR;
-	intrmod_cfg->minpkt_ratethr = LIO_INTRMOD_MINPKT_RATETHR;
-	intrmod_cfg->rx_maxcnt_trigger = LIO_INTRMOD_RXMAXCNT_TRIGGER;
-	intrmod_cfg->rx_maxtmr_trigger = LIO_INTRMOD_RXMAXTMR_TRIGGER;
-	intrmod_cfg->rx_mintmr_trigger = LIO_INTRMOD_RXMINTMR_TRIGGER;
-	intrmod_cfg->rx_mincnt_trigger = LIO_INTRMOD_RXMINCNT_TRIGGER;
-	intrmod_cfg->tx_enable = 1;
-	intrmod_cfg->tx_maxcnt_trigger = LIO_INTRMOD_TXMAXCNT_TRIGGER;
-	intrmod_cfg->tx_mincnt_trigger = LIO_INTRMOD_TXMINCNT_TRIGGER;
-	intrmod_cfg->rx_frames = CFG_GET_OQ_INTR_PKT(octeon_get_conf(oct));
-	intrmod_cfg->rx_usecs = CFG_GET_OQ_INTR_TIME(octeon_get_conf(oct));
-	intrmod_cfg->tx_frames = CFG_GET_IQ_INTR_PKT(octeon_get_conf(oct));
 	dev_dbg(&oct->pci_dev->dev, "Network interfaces ready\n");
 
 	return retval;
diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
index 294c6f3c6b48..8ea2323d8d67 100644
--- a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
+++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
@@ -27,7 +27,7 @@
 
 #define LIQUIDIO_PACKAGE ""
 #define LIQUIDIO_BASE_MAJOR_VERSION 1
-#define LIQUIDIO_BASE_MINOR_VERSION 4
+#define LIQUIDIO_BASE_MINOR_VERSION 5
 #define LIQUIDIO_BASE_MICRO_VERSION 1
 #define LIQUIDIO_BASE_VERSION   __stringify(LIQUIDIO_BASE_MAJOR_VERSION) "." \
 				__stringify(LIQUIDIO_BASE_MINOR_VERSION)
@@ -83,6 +83,7 @@ enum octeon_tag_type {
 #define OPCODE_NIC_INTRMOD_CFG         0x08
 #define OPCODE_NIC_IF_CFG              0x09
 #define OPCODE_NIC_VF_DRV_NOTICE       0x0A
+#define OPCODE_NIC_INTRMOD_PARAMS      0x0B
 #define VF_DRV_LOADED                  1
 #define VF_DRV_REMOVED                -1
 #define VF_DRV_MACADDR_CHANGED         2
@@ -100,6 +101,11 @@ enum octeon_tag_type {
 
 #define BYTES_PER_DHLEN_UNIT        8
 #define MAX_REG_CNT                 2000000U
+#define INTRNAMSIZ                  32
+#define IRQ_NAME_OFF(i)             ((i) * INTRNAMSIZ)
+#define MAX_IOQ_INTERRUPTS_PER_PF   (64 * 2)
+#define MAX_IOQ_INTERRUPTS_PER_VF   (8 * 2)
+
 
 static inline u32 incr_index(u32 index, u32 count, u32 max)
 {
@@ -181,6 +187,7 @@ static inline void add_sg_size(struct octeon_sg_entry *sg_entry,
 #define   OCTNET_CMD_Q                0
 
 /* NIC Command types */
+#define   OCTNET_CMD_RESET_PF         0x0
 #define   OCTNET_CMD_CHANGE_MTU       0x1
 #define   OCTNET_CMD_CHANGE_MACADDR   0x2
 #define   OCTNET_CMD_CHANGE_DEVFLAGS  0x3
@@ -845,29 +852,6 @@ struct oct_mdio_cmd {
 
 #define OCT_LINK_STATS_SIZE   (sizeof(struct oct_link_stats))
 
-/* intrmod: max. packet rate threshold */
-#define LIO_INTRMOD_MAXPKT_RATETHR	196608
-/* intrmod: min. packet rate threshold */
-#define LIO_INTRMOD_MINPKT_RATETHR	9216
-/* intrmod: max. packets to trigger interrupt */
-#define LIO_INTRMOD_RXMAXCNT_TRIGGER	384
-/* intrmod: min. packets to trigger interrupt */
-#define LIO_INTRMOD_RXMINCNT_TRIGGER	0
-/* intrmod: max. time to trigger interrupt */
-#define LIO_INTRMOD_RXMAXTMR_TRIGGER	128
-/* 66xx:intrmod: min. time to trigger interrupt
- * (value of 1 is optimum for TCP_RR)
- */
-#define LIO_INTRMOD_RXMINTMR_TRIGGER	1
-
-/* intrmod: max. packets to trigger interrupt */
-#define LIO_INTRMOD_TXMAXCNT_TRIGGER	64
-/* intrmod: min. packets to trigger interrupt */
-#define LIO_INTRMOD_TXMINCNT_TRIGGER	0
-
-/* intrmod: poll interval in seconds */
-#define LIO_INTRMOD_CHECK_INTERVAL  1
-
 struct oct_intrmod_cfg {
 	u64 rx_enable;
 	u64 tx_enable;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index 9675ffbf25e6..e21b477d0159 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -793,7 +793,7 @@ int octeon_setup_instr_queues(struct octeon_device *oct)
 	u32 num_descs = 0;
 	u32 iq_no = 0;
 	union oct_txpciq txpciq;
-	int numa_node = cpu_to_node(iq_no % num_online_cpus());
+	int numa_node = dev_to_node(&oct->pci_dev->dev);
 
 	if (OCTEON_CN6XXX(oct))
 		num_descs =
@@ -837,7 +837,7 @@ int octeon_setup_output_queues(struct octeon_device *oct)
 	u32 num_descs = 0;
 	u32 desc_size = 0;
 	u32 oq_no = 0;
-	int numa_node = cpu_to_node(oq_no % num_online_cpus());
+	int numa_node = dev_to_node(&oct->pci_dev->dev);
 
 	if (OCTEON_CN6XXX(oct)) {
 		num_descs =
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
index c301a3852482..dab35bfa4612 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -453,9 +453,6 @@ struct octeon_device {
 	/** List of dispatch functions */
 	struct octeon_dispatch_list dispatch;
 
-	/* Interrupt Moderation */
-	struct oct_intrmod_cfg intrmod;
-
 	u32 int_status;
 
 	u64 droq_intr;
@@ -517,6 +514,9 @@ struct octeon_device {
 
 	void *msix_entries;
 
+	/* when requesting IRQs, the names are stored here */
+	void *irq_name_storage;
+
 	struct octeon_sriov_info sriov_info;
 
 	struct octeon_pf_vf_hs_word pfvf_hsword;
@@ -538,6 +538,10 @@ struct octeon_device {
 	u32 priv_flags;
 
 	void *watchdog_task;
+
+	u32 rx_coalesce_usecs;
+	u32 rx_max_coalesced_frames;
+	u32 tx_max_coalesced_frames;
 };
 
 #define  OCT_DRV_ONLINE 1
@@ -551,12 +555,6 @@ struct octeon_device {
 #define CHIP_CONF(oct, TYPE)             \
 	(((struct octeon_ ## TYPE  *)((oct)->chip))->conf)
 
-struct oct_intrmod_cmd {
-	struct octeon_device *oct_dev;
-	struct octeon_soft_command *sc;
-	struct oct_intrmod_cfg *cfg;
-};
-
 /*------------------ Function Prototypes ----------------------*/
 
 /** Initialize device list memory */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
index 79f809479af6..286be5539cef 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
@@ -226,8 +226,7 @@ int octeon_init_droq(struct octeon_device *oct,
 	struct octeon_droq *droq;
 	u32 desc_ring_size = 0, c_num_descs = 0, c_buf_size = 0;
 	u32 c_pkts_per_intr = 0, c_refill_threshold = 0;
-	int orig_node = dev_to_node(&oct->pci_dev->dev);
-	int numa_node = cpu_to_node(q_no % num_online_cpus());
+	int numa_node = dev_to_node(&oct->pci_dev->dev);
 
 	dev_dbg(&oct->pci_dev->dev, "%s[%d]\n", __func__, q_no);
 
@@ -267,13 +266,8 @@ int octeon_init_droq(struct octeon_device *oct,
 	droq->buffer_size = c_buf_size;
 
 	desc_ring_size = droq->max_count * OCT_DROQ_DESC_SIZE;
-	set_dev_node(&oct->pci_dev->dev, numa_node);
 	droq->desc_ring = lio_dma_alloc(oct, desc_ring_size,
 					(dma_addr_t *)&droq->desc_ring_dma);
-	set_dev_node(&oct->pci_dev->dev, orig_node);
-	if (!droq->desc_ring)
-		droq->desc_ring = lio_dma_alloc(oct, desc_ring_size,
-					(dma_addr_t *)&droq->desc_ring_dma);
 
 	if (!droq->desc_ring) {
 		dev_err(&oct->pci_dev->dev,
@@ -519,6 +513,32 @@ octeon_droq_refill(struct octeon_device *octeon_dev, struct octeon_droq *droq)
 	return desc_refilled;
 }
 
+/** check if we can allocate packets to get out of oom.
+ *  @param  droq - Droq being checked.
+ *  @return does not return anything
+ */
+void octeon_droq_check_oom(struct octeon_droq *droq)
+{
+	int desc_refilled;
+	struct octeon_device *oct = droq->oct_dev;
+
+	if (readl(droq->pkts_credit_reg) <= CN23XX_SLI_DEF_BP) {
+		spin_lock_bh(&droq->lock);
+		desc_refilled = octeon_droq_refill(oct, droq);
+		if (desc_refilled) {
+			/* Flush the droq descriptor data to memory to be sure
+			 * that when we update the credits the data in memory
+			 * is accurate.
+			 */
+			wmb();
+			writel(desc_refilled, droq->pkts_credit_reg);
+			/* make sure mmio write completes */
+			mmiowb();
+		}
+		spin_unlock_bh(&droq->lock);
+	}
+}
+
 static inline u32
 octeon_droq_get_bufcount(u32 buf_size, u32 total_len)
 {
@@ -970,7 +990,7 @@ int octeon_create_droq(struct octeon_device *oct,
 		       u32 desc_size, void *app_ctx)
 {
 	struct octeon_droq *droq;
-	int numa_node = cpu_to_node(q_no % num_online_cpus());
+	int numa_node = dev_to_node(&oct->pci_dev->dev);
 
 	if (oct->droq[q_no]) {
 		dev_dbg(&oct->pci_dev->dev, "Droq already in use. Cannot create droq %d again\n",
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
index 6982c0af5ecc..9781577115e7 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
@@ -426,4 +426,6 @@ int octeon_droq_process_packets(struct octeon_device *oct,
 int octeon_process_droq_poll_cmd(struct octeon_device *oct, u32 q_no,
 				 int cmd, u32 arg);
 
+void octeon_droq_check_oom(struct octeon_droq *droq);
+
 #endif	/*__OCTEON_DROQ_H__ */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
index 4608a5af35a3..5063a12613e5 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
@@ -152,7 +152,7 @@ struct octeon_instr_queue {
 	struct oct_iq_stats stats;
 
 	/** DMA mapped base address of the input descriptor ring. */
-	u64 base_addr_dma;
+	dma_addr_t base_addr_dma;
 
 	/** Application context */
 	void *app_ctx;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
index eef2a1e8a7e3..454ec0ca56ab 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
@@ -28,6 +28,12 @@
 #define LIO_MAX_MTU_SIZE (OCTNET_MAX_FRM_SIZE - OCTNET_FRM_HEADER_SIZE)
 #define LIO_MIN_MTU_SIZE ETH_MIN_MTU
 
+/* Bit mask values for lio->ifstate */
+#define   LIO_IFSTATE_DROQ_OPS             0x01
+#define   LIO_IFSTATE_REGISTERED           0x02
+#define   LIO_IFSTATE_RUNNING              0x04
+#define   LIO_IFSTATE_RX_TIMESTAMP_ENABLED 0x08
+
 struct oct_nic_stats_resp {
 	u64     rh;
 	struct oct_link_stats stats;
@@ -123,6 +129,9 @@ struct lio {
 	/* work queue for  txq status */
 	struct cavium_wq	txq_status_wq;
 
+	/* work queue for  rxq oom status */
+	struct cavium_wq	rxq_status_wq;
+
 	/* work queue for  link status */
 	struct cavium_wq	link_status_wq;
 
@@ -146,6 +155,10 @@ struct lio {
  */
 int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1);
 
+int setup_rx_oom_poll_fn(struct net_device *netdev);
+
+void cleanup_rx_oom_poll_fn(struct net_device *netdev);
+
 /**
  * \brief Link control command completion callback
  * @param nctrl_ptr pointer to control packet structure
@@ -438,4 +451,34 @@ static inline void octeon_fast_packet_next(struct octeon_droq *droq,
 	       get_rbd(droq->recv_buf_list[idx].buffer), copy_len);
 }
 
+/**
+ * \brief check interface state
+ * @param lio per-network private data
+ * @param state_flag flag state to check
+ */
+static inline int ifstate_check(struct lio *lio, int state_flag)
+{
+	return atomic_read(&lio->ifstate) & state_flag;
+}
+
+/**
+ * \brief set interface state
+ * @param lio per-network private data
+ * @param state_flag flag state to set
+ */
+static inline void ifstate_set(struct lio *lio, int state_flag)
+{
+	atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) | state_flag));
+}
+
+/**
+ * \brief clear interface state
+ * @param lio per-network private data
+ * @param state_flag flag state to clear
+ */
+static inline void ifstate_reset(struct lio *lio, int state_flag)
+{
+	atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) & ~(state_flag)));
+}
+
 #endif
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index 707bc15adec6..261f448f9de2 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -62,8 +62,7 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 	u32 iq_no = (u32)txpciq.s.q_no;
 	u32 q_size;
 	struct cavium_wq *db_wq;
-	int orig_node = dev_to_node(&oct->pci_dev->dev);
-	int numa_node = cpu_to_node(iq_no % num_online_cpus());
+	int numa_node = dev_to_node(&oct->pci_dev->dev);
 
 	if (OCTEON_CN6XXX(oct))
 		conf = &(CFG_GET_IQ_CFG(CHIP_CONF(oct, cn6xxx)));
@@ -91,13 +90,7 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 
 	iq->oct_dev = oct;
 
-	set_dev_node(&oct->pci_dev->dev, numa_node);
-	iq->base_addr = lio_dma_alloc(oct, q_size,
-				      (dma_addr_t *)&iq->base_addr_dma);
-	set_dev_node(&oct->pci_dev->dev, orig_node);
-	if (!iq->base_addr)
-		iq->base_addr = lio_dma_alloc(oct, q_size,
-					      (dma_addr_t *)&iq->base_addr_dma);
+	iq->base_addr = lio_dma_alloc(oct, q_size, &iq->base_addr_dma);
 	if (!iq->base_addr) {
 		dev_err(&oct->pci_dev->dev, "Cannot allocate memory for instr queue %d\n",
 			iq_no);
@@ -211,7 +204,7 @@ int octeon_setup_iq(struct octeon_device *oct,
 		    void *app_ctx)
 {
 	u32 iq_no = (u32)txpciq.s.q_no;
-	int numa_node = cpu_to_node(iq_no % num_online_cpus());
+	int numa_node = dev_to_node(&oct->pci_dev->dev);
 
 	if (oct->instr_queue[iq_no]) {
 		dev_dbg(&oct->pci_dev->dev, "IQ is in use. Cannot create the IQ: %d again\n",
diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.c b/drivers/net/ethernet/cavium/liquidio/response_manager.c
index 2fbaae96b505..3d691c69f74d 100644
--- a/drivers/net/ethernet/cavium/liquidio/response_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/response_manager.c
@@ -69,50 +69,53 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev,
 	int resp_to_process = MAX_ORD_REQS_TO_PROCESS;
 	u32 status;
 	u64 status64;
-	struct octeon_instr_rdp *rdp;
-	u64 rptr;
 
 	ordered_sc_list = &octeon_dev->response_list[OCTEON_ORDERED_SC_LIST];
 
 	do {
 		spin_lock_bh(&ordered_sc_list->lock);
 
-		if (ordered_sc_list->head.next == &ordered_sc_list->head) {
+		if (list_empty(&ordered_sc_list->head)) {
 			spin_unlock_bh(&ordered_sc_list->lock);
 			return 1;
 		}
 
-		sc = (struct octeon_soft_command *)ordered_sc_list->
-		    head.next;
-		if (OCTEON_CN23XX_PF(octeon_dev) ||
-		    OCTEON_CN23XX_VF(octeon_dev)) {
-			rdp = (struct octeon_instr_rdp *)&sc->cmd.cmd3.rdp;
-			rptr = sc->cmd.cmd3.rptr;
-		} else {
-			rdp = (struct octeon_instr_rdp *)&sc->cmd.cmd2.rdp;
-			rptr = sc->cmd.cmd2.rptr;
-		}
+		sc = list_first_entry(&ordered_sc_list->head,
+				      struct octeon_soft_command, node);
 
 		status = OCTEON_REQUEST_PENDING;
 
 		/* check if octeon has finished DMA'ing a response
 		 * to where rptr is pointing to
 		 */
-		dma_sync_single_for_cpu(&octeon_dev->pci_dev->dev,
-					rptr, rdp->rlen,
-					DMA_FROM_DEVICE);
 		status64 = *sc->status_word;
 
 		if (status64 != COMPLETION_WORD_INIT) {
+			/* This logic ensures that all 64b have been written.
+			 * 1. check byte 0 for non-FF
+			 * 2. if non-FF, then swap result from BE to host order
+			 * 3. check byte 7 (swapped to 0) for non-FF
+			 * 4. if non-FF, use the low 32-bit status code
+			 * 5. if either byte 0 or byte 7 is FF, don't use status
+			 */
 			if ((status64 & 0xff) != 0xff) {
 				octeon_swap_8B_data(&status64, 1);
 				if (((status64 & 0xff) != 0xff)) {
-					status = (u32)(status64 &
-						       0xffffffffULL);
+					/* retrieve 16-bit firmware status */
+					status = (u32)(status64 & 0xffffULL);
+					if (status) {
+						status =
+						  FIRMWARE_STATUS_CODE(status);
+					} else {
+						/* i.e. no error */
+						status = OCTEON_REQUEST_DONE;
+					}
 				}
 			}
 		} else if (force_quit || (sc->timeout &&
 			time_after(jiffies, (unsigned long)sc->timeout))) {
+			dev_err(&octeon_dev->pci_dev->dev, "%s: cmd failed, timeout (%ld, %ld)\n",
+				__func__, (long)jiffies, (long)sc->timeout);
 			status = OCTEON_REQUEST_TIMEOUT;
 		}
 
diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.h b/drivers/net/ethernet/cavium/liquidio/response_manager.h
index cbb2d84e8932..9169c2815dba 100644
--- a/drivers/net/ethernet/cavium/liquidio/response_manager.h
+++ b/drivers/net/ethernet/cavium/liquidio/response_manager.h
@@ -78,6 +78,8 @@ enum {
 
 /*------------   Error codes used by host driver   -----------------*/
 #define DRIVER_MAJOR_ERROR_CODE           0x0000
+/*------   Error codes used by firmware (bits 15..0 set by firmware */
+#define FIRMWARE_MAJOR_ERROR_CODE         0x0001
 
 /**  A value of 0x00000000 indicates no error i.e. success */
 #define DRIVER_ERROR_NONE                 0x00000000
@@ -116,6 +118,9 @@ enum {
 
 };
 
+#define FIRMWARE_STATUS_CODE(status) \
+	((FIRMWARE_MAJOR_ERROR_CODE << 16) | (status))
+
 /** Initialize the response lists. The number of response lists to create is
  * given by count.
  * @param octeon_dev      - the octeon device structure.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 87000cd39737..0de8eb72325c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -6369,7 +6369,6 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
 	unsigned int stat_len = cache_line_size > 64 ? 128 : 64;
 	unsigned int fl_align = cache_line_size < 32 ? 32 : cache_line_size;
 	unsigned int fl_align_log = fls(fl_align) - 1;
-	unsigned int ingpad;
 
 	t4_write_reg(adap, SGE_HOST_PAGE_SIZE_A,
 		     HOSTPAGESIZEPF0_V(sge_hps) |
@@ -6389,6 +6388,10 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
 						  INGPADBOUNDARY_SHIFT_X) |
 				 EGRSTATUSPAGESIZE_V(stat_len != 64));
 	} else {
+		unsigned int pack_align;
+		unsigned int ingpad, ingpack;
+		unsigned int pcie_cap;
+
 		/* T5 introduced the separation of the Free List Padding and
 		 * Packing Boundaries.  Thus, we can select a smaller Padding
 		 * Boundary to avoid uselessly chewing up PCIe Link and Memory
@@ -6401,27 +6404,62 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
 		 * Size (the minimum unit of transfer to/from Memory).  If we
 		 * have a Padding Boundary which is smaller than the Memory
 		 * Line Size, that'll involve a Read-Modify-Write cycle on the
-		 * Memory Controller which is never good.  For T5 the smallest
-		 * Padding Boundary which we can select is 32 bytes which is
-		 * larger than any known Memory Controller Line Size so we'll
-		 * use that.
-		 *
-		 * T5 has a different interpretation of the "0" value for the
-		 * Packing Boundary.  This corresponds to 16 bytes instead of
-		 * the expected 32 bytes.  We never have a Packing Boundary
-		 * less than 32 bytes so we can't use that special value but
-		 * on the other hand, if we wanted 32 bytes, the best we can
-		 * really do is 64 bytes.
-		*/
-		if (fl_align <= 32) {
+		 * Memory Controller which is never good.
+		 */
+
+		/* We want the Packing Boundary to be based on the Cache Line
+		 * Size in order to help avoid False Sharing performance
+		 * issues between CPUs, etc.  We also want the Packing
+		 * Boundary to incorporate the PCI-E Maximum Payload Size.  We
+		 * get best performance when the Packing Boundary is a
+		 * multiple of the Maximum Payload Size.
+		 */
+		pack_align = fl_align;
+		pcie_cap = pci_find_capability(adap->pdev, PCI_CAP_ID_EXP);
+		if (pcie_cap) {
+			unsigned int mps, mps_log;
+			u16 devctl;
+
+			/* The PCIe Device Control Maximum Payload Size field
+			 * [bits 7:5] encodes sizes as powers of 2 starting at
+			 * 128 bytes.
+			 */
+			pci_read_config_word(adap->pdev,
+					     pcie_cap + PCI_EXP_DEVCTL,
+					     &devctl);
+			mps_log = ((devctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5) + 7;
+			mps = 1 << mps_log;
+			if (mps > pack_align)
+				pack_align = mps;
+		}
+
+		/* N.B. T5/T6 have a crazy special interpretation of the "0"
+		 * value for the Packing Boundary.  This corresponds to 16
+		 * bytes instead of the expected 32 bytes.  So if we want 32
+		 * bytes, the best we can really do is 64 bytes ...
+		 */
+		if (pack_align <= 16) {
+			ingpack = INGPACKBOUNDARY_16B_X;
+			fl_align = 16;
+		} else if (pack_align == 32) {
+			ingpack = INGPACKBOUNDARY_64B_X;
 			fl_align = 64;
-			fl_align_log = 6;
+		} else {
+			unsigned int pack_align_log = fls(pack_align) - 1;
+
+			ingpack = pack_align_log - INGPACKBOUNDARY_SHIFT_X;
+			fl_align = pack_align;
 		}
 
+		/* Use the smallest Ingress Padding which isn't smaller than
+		 * the Memory Controller Read/Write Size.  We'll take that as
+		 * being 8 bytes since we don't know of any system with a
+		 * wider Memory Controller Bus Width.
+		 */
 		if (is_t5(adap->params.chip))
-			ingpad = INGPCIEBOUNDARY_32B_X;
+			ingpad = INGPADBOUNDARY_32B_X;
 		else
-			ingpad = T6_INGPADBOUNDARY_32B_X;
+			ingpad = T6_INGPADBOUNDARY_8B_X;
 
 		t4_set_reg_field(adap, SGE_CONTROL_A,
 				 INGPADBOUNDARY_V(INGPADBOUNDARY_M) |
@@ -6430,8 +6468,7 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
 				 EGRSTATUSPAGESIZE_V(stat_len != 64));
 		t4_set_reg_field(adap, SGE_CONTROL2_A,
 				 INGPACKBOUNDARY_V(INGPACKBOUNDARY_M),
-				 INGPACKBOUNDARY_V(fl_align_log -
-						   INGPACKBOUNDARY_SHIFT_X));
+				 INGPACKBOUNDARY_V(ingpack));
 	}
 	/*
 	 * Adjust various SGE Free List Host Buffer Sizes.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
index 36cf3073ca37..f6558cbfc54e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
@@ -54,11 +54,15 @@
 #define INGPADBOUNDARY_SHIFT_X		5
 
 #define T6_INGPADBOUNDARY_SHIFT_X	3
+#define T6_INGPADBOUNDARY_8B_X		0
 #define T6_INGPADBOUNDARY_32B_X		2
 
+#define INGPADBOUNDARY_32B_X		0
+
 /* CONTROL2 register */
 #define INGPACKBOUNDARY_SHIFT_X		5
 #define INGPACKBOUNDARY_16B_X		0
+#define INGPACKBOUNDARY_64B_X		1
 
 /* GTS register */
 #define SGE_TIMERREGS			6
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 23d82748f52b..e863ba74d005 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -1148,14 +1148,14 @@ static int ethoc_probe(struct platform_device *pdev)
 
 	/* Allow the platform setup code to pass in a MAC address. */
 	if (pdata) {
-		memcpy(netdev->dev_addr, pdata->hwaddr, IFHWADDRLEN);
+		ether_addr_copy(netdev->dev_addr, pdata->hwaddr);
 		priv->phy_id = pdata->phy_id;
 	} else {
 		const void *mac;
 
 		mac = of_get_mac_address(pdev->dev.of_node);
 		if (mac)
-			memcpy(netdev->dev_addr, mac, IFHWADDRLEN);
+			ether_addr_copy(netdev->dev_addr, mac);
 		priv->phy_id = -1;
 	}
 
diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c
index f819843e2bae..659f1ad37e96 100644
--- a/drivers/net/ethernet/ezchip/nps_enet.c
+++ b/drivers/net/ethernet/ezchip/nps_enet.c
@@ -16,6 +16,7 @@
 
 #include <linux/module.h>
 #include <linux/etherdevice.h>
+#include <linux/interrupt.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_net.h>
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index e2ca107f9d94..9a520e4f0df9 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -137,6 +137,13 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms");
 /* L4 Type field: TCP */
 #define FM_L4_PARSE_RESULT_TCP	0x20
 
+/* FD status field indicating whether the FM Parser has attempted to validate
+ * the L4 csum of the frame.
+ * Note that having this bit set doesn't necessarily imply that the checksum
+ * is valid. One would have to check the parse results to find that out.
+ */
+#define FM_FD_STAT_L4CV         0x00000004
+
 #define DPAA_SGT_MAX_ENTRIES 16 /* maximum number of entries in SG Table */
 #define DPAA_BUFF_RELEASE_MAX 8 /* maximum number of buffers released at once */
 
@@ -235,6 +242,7 @@ static int dpaa_netdev_init(struct net_device *net_dev,
 	 * For conformity, we'll still declare GSO explicitly.
 	 */
 	net_dev->features |= NETIF_F_GSO;
+	net_dev->features |= NETIF_F_RXCSUM;
 
 	net_dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	/* we do not want shared skbs on TX */
@@ -334,6 +342,45 @@ static void dpaa_get_stats64(struct net_device *net_dev,
 	}
 }
 
+static int dpaa_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto,
+			 struct tc_to_netdev *tc)
+{
+	struct dpaa_priv *priv = netdev_priv(net_dev);
+	u8 num_tc;
+	int i;
+
+	if (tc->type != TC_SETUP_MQPRIO)
+		return -EINVAL;
+
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+	num_tc = tc->mqprio->num_tc;
+
+	if (num_tc == priv->num_tc)
+		return 0;
+
+	if (!num_tc) {
+		netdev_reset_tc(net_dev);
+		goto out;
+	}
+
+	if (num_tc > DPAA_TC_NUM) {
+		netdev_err(net_dev, "Too many traffic classes: max %d supported.\n",
+			   DPAA_TC_NUM);
+		return -EINVAL;
+	}
+
+	netdev_set_num_tc(net_dev, num_tc);
+
+	for (i = 0; i < num_tc; i++)
+		netdev_set_tc_queue(net_dev, i, DPAA_TC_TXQ_NUM,
+				    i * DPAA_TC_TXQ_NUM);
+
+out:
+	priv->num_tc = num_tc ? : 1;
+	netif_set_real_num_tx_queues(net_dev, priv->num_tc * DPAA_TC_TXQ_NUM);
+	return 0;
+}
+
 static struct mac_device *dpaa_mac_dev_get(struct platform_device *pdev)
 {
 	struct platform_device *of_dev;
@@ -557,16 +604,18 @@ static void dpaa_bps_free(struct dpaa_priv *priv)
 
 /* Use multiple WQs for FQ assignment:
  *	- Tx Confirmation queues go to WQ1.
- *	- Rx Error and Tx Error queues go to WQ2 (giving them a better chance
- *	  to be scheduled, in case there are many more FQs in WQ3).
- *	- Rx Default and Tx queues go to WQ3 (no differentiation between
- *	  Rx and Tx traffic).
+ *	- Rx Error and Tx Error queues go to WQ5 (giving them a better chance
+ *	  to be scheduled, in case there are many more FQs in WQ6).
+ *	- Rx Default goes to WQ6.
+ *	- Tx queues go to different WQs depending on their priority. Equal
+ *	  chunks of NR_CPUS queues go to WQ6 (lowest priority), WQ2, WQ1 and
+ *	  WQ0 (highest priority).
  * This ensures that Tx-confirmed buffers are timely released. In particular,
  * it avoids congestion on the Tx Confirm FQs, which can pile up PFDRs if they
  * are greatly outnumbered by other FQs in the system, while
  * dequeue scheduling is round-robin.
  */
-static inline void dpaa_assign_wq(struct dpaa_fq *fq)
+static inline void dpaa_assign_wq(struct dpaa_fq *fq, int idx)
 {
 	switch (fq->fq_type) {
 	case FQ_TYPE_TX_CONFIRM:
@@ -575,11 +624,33 @@ static inline void dpaa_assign_wq(struct dpaa_fq *fq)
 		break;
 	case FQ_TYPE_RX_ERROR:
 	case FQ_TYPE_TX_ERROR:
-		fq->wq = 2;
+		fq->wq = 5;
 		break;
 	case FQ_TYPE_RX_DEFAULT:
+		fq->wq = 6;
+		break;
 	case FQ_TYPE_TX:
-		fq->wq = 3;
+		switch (idx / DPAA_TC_TXQ_NUM) {
+		case 0:
+			/* Low priority (best effort) */
+			fq->wq = 6;
+			break;
+		case 1:
+			/* Medium priority */
+			fq->wq = 2;
+			break;
+		case 2:
+			/* High priority */
+			fq->wq = 1;
+			break;
+		case 3:
+			/* Very high priority */
+			fq->wq = 0;
+			break;
+		default:
+			WARN(1, "Too many TX FQs: more than %d!\n",
+			     DPAA_ETH_TXQ_NUM);
+		}
 		break;
 	default:
 		WARN(1, "Invalid FQ type %d for FQID %d!\n",
@@ -607,7 +678,7 @@ static struct dpaa_fq *dpaa_fq_alloc(struct device *dev,
 	}
 
 	for (i = 0; i < count; i++)
-		dpaa_assign_wq(dpaa_fq + i);
+		dpaa_assign_wq(dpaa_fq + i, i);
 
 	return dpaa_fq;
 }
@@ -903,7 +974,7 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable)
 		 * Tx Confirmation FQs.
 		 */
 		if (dpaa_fq->fq_type == FQ_TYPE_TX_CONFIRM)
-			initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_HOLDACTIVE);
+			initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_AVOIDBLOCK);
 
 		/* FQ placement */
 		initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_DESTWQ);
@@ -985,7 +1056,8 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable)
 		/* Initialization common to all ingress queues */
 		if (dpaa_fq->flags & QMAN_FQ_FLAG_NO_ENQUEUE) {
 			initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_CONTEXTA);
-			initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_HOLDACTIVE);
+			initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_HOLDACTIVE |
+						QM_FQCTRL_CTXASTASHING);
 			initfq.fqd.context_a.stashing.exclusive =
 				QM_STASHING_EXCL_DATA | QM_STASHING_EXCL_CTX |
 				QM_STASHING_EXCL_ANNOTATION;
@@ -1055,9 +1127,9 @@ static int dpaa_fq_free(struct device *dev, struct list_head *list)
 	return err;
 }
 
-static void dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq,
-				  struct dpaa_fq *defq,
-				  struct dpaa_buffer_layout *buf_layout)
+static int dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq,
+				 struct dpaa_fq *defq,
+				 struct dpaa_buffer_layout *buf_layout)
 {
 	struct fman_buffer_prefix_content buf_prefix_content;
 	struct fman_port_params params;
@@ -1076,23 +1148,29 @@ static void dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq,
 	params.specific_params.non_rx_params.dflt_fqid = defq->fqid;
 
 	err = fman_port_config(port, &params);
-	if (err)
+	if (err) {
 		pr_err("%s: fman_port_config failed\n", __func__);
+		return err;
+	}
 
 	err = fman_port_cfg_buf_prefix_content(port, &buf_prefix_content);
-	if (err)
+	if (err) {
 		pr_err("%s: fman_port_cfg_buf_prefix_content failed\n",
 		       __func__);
+		return err;
+	}
 
 	err = fman_port_init(port);
 	if (err)
 		pr_err("%s: fm_port_init failed\n", __func__);
+
+	return err;
 }
 
-static void dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps,
-				  size_t count, struct dpaa_fq *errq,
-				  struct dpaa_fq *defq,
-				  struct dpaa_buffer_layout *buf_layout)
+static int dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps,
+				 size_t count, struct dpaa_fq *errq,
+				 struct dpaa_fq *defq,
+				 struct dpaa_buffer_layout *buf_layout)
 {
 	struct fman_buffer_prefix_content buf_prefix_content;
 	struct fman_port_rx_params *rx_p;
@@ -1120,32 +1198,44 @@ static void dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps,
 	}
 
 	err = fman_port_config(port, &params);
-	if (err)
+	if (err) {
 		pr_err("%s: fman_port_config failed\n", __func__);
+		return err;
+	}
 
 	err = fman_port_cfg_buf_prefix_content(port, &buf_prefix_content);
-	if (err)
+	if (err) {
 		pr_err("%s: fman_port_cfg_buf_prefix_content failed\n",
 		       __func__);
+		return err;
+	}
 
 	err = fman_port_init(port);
 	if (err)
 		pr_err("%s: fm_port_init failed\n", __func__);
+
+	return err;
 }
 
-static void dpaa_eth_init_ports(struct mac_device *mac_dev,
-				struct dpaa_bp **bps, size_t count,
-				struct fm_port_fqs *port_fqs,
-				struct dpaa_buffer_layout *buf_layout,
-				struct device *dev)
+static int dpaa_eth_init_ports(struct mac_device *mac_dev,
+			       struct dpaa_bp **bps, size_t count,
+			       struct fm_port_fqs *port_fqs,
+			       struct dpaa_buffer_layout *buf_layout,
+			       struct device *dev)
 {
 	struct fman_port *rxport = mac_dev->port[RX];
 	struct fman_port *txport = mac_dev->port[TX];
+	int err;
+
+	err = dpaa_eth_init_tx_port(txport, port_fqs->tx_errq,
+				    port_fqs->tx_defq, &buf_layout[TX]);
+	if (err)
+		return err;
+
+	err = dpaa_eth_init_rx_port(rxport, bps, count, port_fqs->rx_errq,
+				    port_fqs->rx_defq, &buf_layout[RX]);
 
-	dpaa_eth_init_tx_port(txport, port_fqs->tx_errq,
-			      port_fqs->tx_defq, &buf_layout[TX]);
-	dpaa_eth_init_rx_port(rxport, bps, count, port_fqs->rx_errq,
-			      port_fqs->rx_defq, &buf_layout[RX]);
+	return err;
 }
 
 static int dpaa_bman_release(const struct dpaa_bp *dpaa_bp,
@@ -1526,6 +1616,23 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv,
 	return skb;
 }
 
+static u8 rx_csum_offload(const struct dpaa_priv *priv, const struct qm_fd *fd)
+{
+	/* The parser has run and performed L4 checksum validation.
+	 * We know there were no parser errors (and implicitly no
+	 * L4 csum error), otherwise we wouldn't be here.
+	 */
+	if ((priv->net_dev->features & NETIF_F_RXCSUM) &&
+	    (be32_to_cpu(fd->status) & FM_FD_STAT_L4CV))
+		return CHECKSUM_UNNECESSARY;
+
+	/* We're here because either the parser didn't run or the L4 checksum
+	 * was not verified. This may include the case of a UDP frame with
+	 * checksum zero or an L4 proto other than TCP/UDP
+	 */
+	return CHECKSUM_NONE;
+}
+
 /* Build a linear skb around the received buffer.
  * We are guaranteed there is enough room at the end of the data buffer to
  * accommodate the shared info area of the skb.
@@ -1556,7 +1663,7 @@ static struct sk_buff *contig_fd_to_skb(const struct dpaa_priv *priv,
 	skb_reserve(skb, fd_off);
 	skb_put(skb, qm_fd_get_length(fd));
 
-	skb->ip_summed = CHECKSUM_NONE;
+	skb->ip_summed = rx_csum_offload(priv, fd);
 
 	return skb;
 
@@ -1616,7 +1723,7 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv,
 			if (WARN_ON(unlikely(!skb)))
 				goto free_buffers;
 
-			skb->ip_summed = CHECKSUM_NONE;
+			skb->ip_summed = rx_csum_offload(priv, fd);
 
 			/* Make sure forwarded skbs will have enough space
 			 * on Tx, if extra headers are added.
@@ -2093,7 +2200,7 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal,
 	dma_addr_t addr = qm_fd_addr(fd);
 	enum qm_fd_format fd_format;
 	struct net_device *net_dev;
-	u32 fd_status = fd->status;
+	u32 fd_status;
 	struct dpaa_bp *dpaa_bp;
 	struct dpaa_priv *priv;
 	unsigned int skb_len;
@@ -2350,6 +2457,7 @@ static const struct net_device_ops dpaa_ops = {
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_set_rx_mode = dpaa_set_rx_mode,
 	.ndo_do_ioctl = dpaa_ioctl,
+	.ndo_setup_tc = dpaa_setup_tc,
 };
 
 static int dpaa_napi_add(struct net_device *net_dev)
@@ -2624,8 +2732,10 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 	priv->rx_headroom = dpaa_get_headroom(&priv->buf_layout[RX]);
 
 	/* All real interfaces need their ports initialized */
-	dpaa_eth_init_ports(mac_dev, dpaa_bps, DPAA_BPS_NUM, &port_fqs,
-			    &priv->buf_layout[0], dev);
+	err = dpaa_eth_init_ports(mac_dev, dpaa_bps, DPAA_BPS_NUM, &port_fqs,
+				  &priv->buf_layout[0], dev);
+	if (err)
+		goto init_ports_failed;
 
 	priv->percpu_priv = devm_alloc_percpu(dev, *priv->percpu_priv);
 	if (!priv->percpu_priv) {
@@ -2638,6 +2748,9 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 		memset(percpu_priv, 0, sizeof(*percpu_priv));
 	}
 
+	priv->num_tc = 1;
+	netif_set_real_num_tx_queues(net_dev, priv->num_tc * DPAA_TC_TXQ_NUM);
+
 	/* Initialize NAPI */
 	err = dpaa_napi_add(net_dev);
 	if (err < 0)
@@ -2658,6 +2771,7 @@ netdev_init_failed:
 napi_add_failed:
 	dpaa_napi_del(net_dev);
 alloc_percpu_failed:
+init_ports_failed:
 	dpaa_fq_free(dev, &priv->dpaa_fq_list);
 fq_alloc_failed:
 	qman_delete_cgr_safe(&priv->ingress_cgr);
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
index 1f9aebf3f3c5..9941a7866ebe 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
@@ -39,7 +39,12 @@
 #include "mac.h"
 #include "dpaa_eth_trace.h"
 
-#define DPAA_ETH_TXQ_NUM	NR_CPUS
+/* Number of prioritised traffic classes */
+#define DPAA_TC_NUM		4
+/* Number of Tx queues per traffic class */
+#define DPAA_TC_TXQ_NUM		NR_CPUS
+/* Total number of Tx queues */
+#define DPAA_ETH_TXQ_NUM	(DPAA_TC_NUM * DPAA_TC_TXQ_NUM)
 
 #define DPAA_BPS_NUM 3 /* number of bpools per interface */
 
@@ -152,6 +157,7 @@ struct dpaa_priv {
 	u16 channel;
 	struct list_head dpaa_fq_list;
 
+	u8 num_tc;
 	u32 msg_enable;	/* net_device message level */
 
 	struct {
diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c
index f60845f0c6ca..4aefe2438969 100644
--- a/drivers/net/ethernet/freescale/fman/fman.c
+++ b/drivers/net/ethernet/freescale/fman/fman.c
@@ -59,6 +59,7 @@
 #define DMA_OFFSET		0x000C2000
 #define FPM_OFFSET		0x000C3000
 #define IMEM_OFFSET		0x000C4000
+#define HWP_OFFSET		0x000C7000
 #define CGP_OFFSET		0x000DB000
 
 /* Exceptions bit map */
@@ -218,6 +219,9 @@
 
 #define QMI_GS_HALT_NOT_BUSY		0x00000002
 
+/* HWP defines */
+#define HWP_RPIMAC_PEN			0x00000001
+
 /* IRAM defines */
 #define IRAM_IADD_AIE			0x80000000
 #define IRAM_READY			0x80000000
@@ -475,6 +479,12 @@ struct fman_dma_regs {
 	u32 res00e0[0x400 - 56];
 };
 
+struct fman_hwp_regs {
+	u32 res0000[0x844 / 4];		/* 0x000..0x843 */
+	u32 fmprrpimac;	/* FM Parser Internal memory access control */
+	u32 res[(0x1000 - 0x848) / 4];	/* 0x848..0xFFF */
+};
+
 /* Structure that holds current FMan state.
  * Used for saving run time information.
  */
@@ -606,6 +616,7 @@ struct fman {
 	struct fman_bmi_regs __iomem *bmi_regs;
 	struct fman_qmi_regs __iomem *qmi_regs;
 	struct fman_dma_regs __iomem *dma_regs;
+	struct fman_hwp_regs __iomem *hwp_regs;
 	fman_exceptions_cb *exception_cb;
 	fman_bus_error_cb *bus_error_cb;
 	/* Spinlock for FMan use */
@@ -999,6 +1010,12 @@ static void qmi_init(struct fman_qmi_regs __iomem *qmi_rg,
 	iowrite32be(tmp_reg, &qmi_rg->fmqm_ien);
 }
 
+static void hwp_init(struct fman_hwp_regs __iomem *hwp_rg)
+{
+	/* enable HW Parser */
+	iowrite32be(HWP_RPIMAC_PEN, &hwp_rg->fmprrpimac);
+}
+
 static int enable(struct fman *fman, struct fman_cfg *cfg)
 {
 	u32 cfg_reg = 0;
@@ -1195,7 +1212,7 @@ static int fill_soc_specific_params(struct fman_state_struct *state)
 		state->max_num_of_open_dmas	= 32;
 		state->fm_port_num_of_cg	= 256;
 		state->num_of_rx_ports	= 6;
-		state->total_fifo_size	= 122 * 1024;
+		state->total_fifo_size	= 136 * 1024;
 		break;
 
 	case 2:
@@ -1793,6 +1810,7 @@ static int fman_config(struct fman *fman)
 	fman->bmi_regs = base_addr + BMI_OFFSET;
 	fman->qmi_regs = base_addr + QMI_OFFSET;
 	fman->dma_regs = base_addr + DMA_OFFSET;
+	fman->hwp_regs = base_addr + HWP_OFFSET;
 	fman->base_addr = base_addr;
 
 	spin_lock_init(&fman->spinlock);
@@ -2062,6 +2080,9 @@ static int fman_init(struct fman *fman)
 	/* Init QMI Registers */
 	qmi_init(fman->qmi_regs, fman->cfg);
 
+	/* Init HW Parser */
+	hwp_init(fman->hwp_regs);
+
 	err = enable(fman, cfg);
 	if (err != 0)
 		return err;
diff --git a/drivers/net/ethernet/freescale/fman/fman.h b/drivers/net/ethernet/freescale/fman/fman.h
index 57aae8d17d77..f53e1473dbcc 100644
--- a/drivers/net/ethernet/freescale/fman/fman.h
+++ b/drivers/net/ethernet/freescale/fman/fman.h
@@ -134,14 +134,14 @@ enum fman_exceptions {
 struct fman_prs_result {
 	u8 lpid;		/* Logical port id */
 	u8 shimr;		/* Shim header result  */
-	u16 l2r;		/* Layer 2 result */
-	u16 l3r;		/* Layer 3 result */
+	__be16 l2r;		/* Layer 2 result */
+	__be16 l3r;		/* Layer 3 result */
 	u8 l4r;		/* Layer 4 result */
 	u8 cplan;		/* Classification plan id */
-	u16 nxthdr;		/* Next Header  */
-	u16 cksum;		/* Running-sum */
+	__be16 nxthdr;		/* Next Header  */
+	__be16 cksum;		/* Running-sum */
 	/* Flags&fragment-offset field of the last IP-header */
-	u16 flags_frag_off;
+	__be16 flags_frag_off;
 	/* Routing type field of a IPV6 routing extension header */
 	u8 route_type;
 	/* Routing Extension Header Present; last bit is IP valid */
diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
index 84ea130eed36..98bba10fc38c 100644
--- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c
+++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
@@ -381,6 +381,9 @@ static int init(struct dtsec_regs __iomem *regs, struct dtsec_cfg *cfg,
 
 	/* check RGMII support */
 	if (iface == PHY_INTERFACE_MODE_RGMII ||
+	    iface == PHY_INTERFACE_MODE_RGMII_ID ||
+	    iface == PHY_INTERFACE_MODE_RGMII_RXID ||
+	    iface == PHY_INTERFACE_MODE_RGMII_TXID ||
 	    iface == PHY_INTERFACE_MODE_RMII)
 		if (tmp & DTSEC_ID2_INT_REDUCED_OFF)
 			return -EINVAL;
@@ -390,7 +393,10 @@ static int init(struct dtsec_regs __iomem *regs, struct dtsec_cfg *cfg,
 		if (tmp & DTSEC_ID2_INT_REDUCED_OFF)
 			return -EINVAL;
 
-	is_rgmii = iface == PHY_INTERFACE_MODE_RGMII;
+	is_rgmii = iface == PHY_INTERFACE_MODE_RGMII ||
+		   iface == PHY_INTERFACE_MODE_RGMII_ID ||
+		   iface == PHY_INTERFACE_MODE_RGMII_RXID ||
+		   iface == PHY_INTERFACE_MODE_RGMII_TXID;
 	is_sgmii = iface == PHY_INTERFACE_MODE_SGMII;
 	is_qsgmii = iface == PHY_INTERFACE_MODE_QSGMII;
 
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index cd6a53eaf161..c0296880feba 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -443,7 +443,10 @@ static int init(struct memac_regs __iomem *regs, struct memac_cfg *cfg,
 		break;
 	default:
 		tmp |= IF_MODE_GMII;
-		if (phy_if == PHY_INTERFACE_MODE_RGMII)
+		if (phy_if == PHY_INTERFACE_MODE_RGMII ||
+		    phy_if == PHY_INTERFACE_MODE_RGMII_ID ||
+		    phy_if == PHY_INTERFACE_MODE_RGMII_RXID ||
+		    phy_if == PHY_INTERFACE_MODE_RGMII_TXID)
 			tmp |= IF_MODE_RGMII | IF_MODE_RGMII_AUTO;
 	}
 	iowrite32be(tmp, &regs->if_mode);
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.h b/drivers/net/ethernet/freescale/fman/fman_memac.h
index 173d8e0fd716..c4a66469a907 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.h
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.h
@@ -36,6 +36,7 @@
 #include "fman_mac.h"
 
 #include <linux/netdevice.h>
+#include <linux/phy_fixed.h>
 
 struct fman_mac *memac_config(struct fman_mac_params *params);
 int memac_set_promiscuous(struct fman_mac *memac, bool new_val);
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index 9f3bb50a2365..57bf44fa16a1 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -62,6 +62,7 @@
 
 #define BMI_PORT_REGS_OFFSET				0
 #define QMI_PORT_REGS_OFFSET				0x400
+#define HWP_PORT_REGS_OFFSET				0x800
 
 /* Default values */
 #define DFLT_PORT_BUFFER_PREFIX_CONTEXT_DATA_ALIGN		\
@@ -182,7 +183,7 @@
 #define NIA_ENG_BMI					0x00500000
 #define NIA_ENG_QMI_ENQ					0x00540000
 #define NIA_ENG_QMI_DEQ					0x00580000
-
+#define NIA_ENG_HWP					0x00440000
 #define NIA_BMI_AC_ENQ_FRAME				0x00000002
 #define NIA_BMI_AC_TX_RELEASE				0x000002C0
 #define NIA_BMI_AC_RELEASE				0x000000C0
@@ -317,6 +318,19 @@ struct fman_port_qmi_regs {
 	u32 fmqm_pndcc;		/* PortID n Dequeue Confirm Counter */
 };
 
+#define HWP_HXS_COUNT 16
+#define HWP_HXS_PHE_REPORT 0x00000800
+#define HWP_HXS_PCAC_PSTAT 0x00000100
+#define HWP_HXS_PCAC_PSTOP 0x00000001
+struct fman_port_hwp_regs {
+	struct {
+		u32 ssa; /* Soft Sequence Attachment */
+		u32 lcv; /* Line-up Enable Confirmation Mask */
+	} pmda[HWP_HXS_COUNT]; /* Parse Memory Direct Access Registers */
+	u32 reserved080[(0x3f8 - 0x080) / 4]; /* (0x080-0x3f7) */
+	u32 fmpr_pcac; /* Configuration Access Control */
+};
+
 /* QMI dequeue prefetch modes */
 enum fman_port_deq_prefetch {
 	FMAN_PORT_DEQ_NO_PREFETCH, /* No prefetch mode */
@@ -436,6 +450,7 @@ struct fman_port {
 
 	union fman_port_bmi_regs __iomem *bmi_regs;
 	struct fman_port_qmi_regs __iomem *qmi_regs;
+	struct fman_port_hwp_regs __iomem *hwp_regs;
 
 	struct fman_sp_buffer_offsets buffer_offsets;
 
@@ -521,9 +536,12 @@ static int init_bmi_rx(struct fman_port *port)
 	/* NIA */
 	tmp = (u32)cfg->rx_fd_bits << BMI_NEXT_ENG_FD_BITS_SHIFT;
 
-	tmp |= NIA_ENG_BMI | NIA_BMI_AC_ENQ_FRAME;
+	tmp |= NIA_ENG_HWP;
 	iowrite32be(tmp, &regs->fmbm_rfne);
 
+	/* Parser Next Engine NIA */
+	iowrite32be(NIA_ENG_BMI | NIA_BMI_AC_ENQ_FRAME, &regs->fmbm_rfpne);
+
 	/* Enqueue NIA */
 	iowrite32be(NIA_ENG_QMI_ENQ | NIA_ORDER_RESTOR, &regs->fmbm_rfene);
 
@@ -665,6 +683,50 @@ static int init_qmi(struct fman_port *port)
 	return 0;
 }
 
+static void stop_port_hwp(struct fman_port *port)
+{
+	struct fman_port_hwp_regs __iomem *regs = port->hwp_regs;
+	int cnt = 100;
+
+	iowrite32be(HWP_HXS_PCAC_PSTOP, &regs->fmpr_pcac);
+
+	while (cnt-- > 0 &&
+	       (ioread32be(&regs->fmpr_pcac) & HWP_HXS_PCAC_PSTAT))
+		udelay(10);
+	if (!cnt)
+		pr_err("Timeout stopping HW Parser\n");
+}
+
+static void start_port_hwp(struct fman_port *port)
+{
+	struct fman_port_hwp_regs __iomem *regs = port->hwp_regs;
+	int cnt = 100;
+
+	iowrite32be(0, &regs->fmpr_pcac);
+
+	while (cnt-- > 0 &&
+	       !(ioread32be(&regs->fmpr_pcac) & HWP_HXS_PCAC_PSTAT))
+		udelay(10);
+	if (!cnt)
+		pr_err("Timeout starting HW Parser\n");
+}
+
+static void init_hwp(struct fman_port *port)
+{
+	struct fman_port_hwp_regs __iomem *regs = port->hwp_regs;
+	int i;
+
+	stop_port_hwp(port);
+
+	for (i = 0; i < HWP_HXS_COUNT; i++) {
+		/* enable HXS error reporting into FD[STATUS] PHE */
+		iowrite32be(0x00000000, &regs->pmda[i].ssa);
+		iowrite32be(0xffffffff, &regs->pmda[i].lcv);
+	}
+
+	start_port_hwp(port);
+}
+
 static int init(struct fman_port *port)
 {
 	int err;
@@ -673,6 +735,8 @@ static int init(struct fman_port *port)
 	switch (port->port_type) {
 	case FMAN_PORT_TYPE_RX:
 		err = init_bmi_rx(port);
+		if (!err)
+			init_hwp(port);
 		break;
 	case FMAN_PORT_TYPE_TX:
 		err = init_bmi_tx(port);
@@ -686,7 +750,8 @@ static int init(struct fman_port *port)
 
 	/* Init QMI registers */
 	err = init_qmi(port);
-	return err;
+	if (err)
+		return err;
 
 	return 0;
 }
@@ -1247,7 +1312,7 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params)
 	/* Allocate the FM driver's parameters structure */
 	port->cfg = kzalloc(sizeof(*port->cfg), GFP_KERNEL);
 	if (!port->cfg)
-		goto err_params;
+		return -EINVAL;
 
 	/* Initialize FM port parameters which will be kept by the driver */
 	port->port_type = port->dts_params.type;
@@ -1276,6 +1341,7 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params)
 	/* set memory map pointers */
 	port->bmi_regs = base_addr + BMI_PORT_REGS_OFFSET;
 	port->qmi_regs = base_addr + QMI_PORT_REGS_OFFSET;
+	port->hwp_regs = base_addr + HWP_PORT_REGS_OFFSET;
 
 	port->max_frame_length = DFLT_PORT_MAX_FRAME_LENGTH;
 	/* resource distribution. */
@@ -1327,8 +1393,6 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params)
 
 err_port_cfg:
 	kfree(port->cfg);
-err_params:
-	kfree(port);
 	return -EINVAL;
 }
 EXPORT_SYMBOL(fman_port_config);
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
index db9c0bcf54cd..1fc27c97e3b2 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
@@ -38,12 +38,6 @@
 #include <asm/irq.h>
 #include <linux/uaccess.h>
 
-#ifdef CONFIG_8xx
-#include <asm/8xx_immap.h>
-#include <asm/pgtable.h>
-#include <asm/cpm1.h>
-#endif
-
 #include "fs_enet.h"
 #include "fec.h"
 
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
index 96d44cf44fe0..64300ac13e02 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
@@ -37,12 +37,6 @@
 #include <asm/irq.h>
 #include <linux/uaccess.h>
 
-#ifdef CONFIG_8xx
-#include <asm/8xx_immap.h>
-#include <asm/pgtable.h>
-#include <asm/cpm1.h>
-#endif
-
 #include "fs_enet.h"
 
 /*************************************************/
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c
index b6ed818f78ff..9d9b6e6dd988 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.c
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c
@@ -9,9 +9,9 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
+#include <linux/of.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
-
 #include "hnae.h"
 
 #define cls_to_ae_dev(dev) container_of(dev, struct hnae_ae_dev, cls_dev)
@@ -57,11 +57,15 @@ static int hnae_alloc_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb)
 
 static void hnae_free_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb)
 {
+	if (unlikely(!cb->priv))
+		return;
+
 	if (cb->type == DESC_TYPE_SKB)
 		dev_kfree_skb_any((struct sk_buff *)cb->priv);
 	else if (unlikely(is_rx_ring(ring)))
 		put_page((struct page *)cb->priv);
-	memset(cb, 0, sizeof(*cb));
+
+	cb->priv = NULL;
 }
 
 static int hnae_map_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb)
@@ -197,6 +201,7 @@ hnae_init_ring(struct hnae_queue *q, struct hnae_ring *ring, int flags)
 
 	ring->q = q;
 	ring->flags = flags;
+	spin_lock_init(&ring->lock);
 	assert(!ring->desc && !ring->desc_cb && !ring->desc_dma_addr);
 
 	/* not matter for tx or rx ring, the ntc and ntc start from 0 */
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index 8016854796fb..04211ac73b36 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -67,6 +67,8 @@ do { \
 #define AE_IS_VER1(ver) ((ver) == AE_VERSION_1)
 #define AE_NAME_SIZE 16
 
+#define BD_SIZE_2048_MAX_MTU   6000
+
 /* some said the RX and TX RCB format should not be the same in the future. But
  * it is the same now...
  */
@@ -101,7 +103,6 @@ enum hnae_led_state {
 #define HNS_RX_FLAG_L4ID_TCP 0x1
 #define HNS_RX_FLAG_L4ID_SCTP 0x3
 
-
 #define HNS_TXD_ASID_S 0
 #define HNS_TXD_ASID_M (0xff << HNS_TXD_ASID_S)
 #define HNS_TXD_BUFNUM_S 8
@@ -273,6 +274,9 @@ struct hnae_ring {
 	/* statistic */
 	struct ring_stats stats;
 
+	/* ring lock for poll one */
+	spinlock_t lock;
+
 	dma_addr_t desc_dma_addr;
 	u32 buf_size;       /* size for hnae_desc->addr, preset by AE */
 	u16 desc_num;       /* total number of desc */
@@ -483,11 +487,11 @@ struct hnae_ae_ops {
 			      u32 auto_neg, u32 rx_en, u32 tx_en);
 	void (*get_coalesce_usecs)(struct hnae_handle *handle,
 				   u32 *tx_usecs, u32 *rx_usecs);
-	void (*get_rx_max_coalesced_frames)(struct hnae_handle *handle,
-					    u32 *tx_frames, u32 *rx_frames);
+	void (*get_max_coalesced_frames)(struct hnae_handle *handle,
+					 u32 *tx_frames, u32 *rx_frames);
 	int (*set_coalesce_usecs)(struct hnae_handle *handle, u32 timeout);
 	int (*set_coalesce_frames)(struct hnae_handle *handle,
-				   u32 coalesce_frames);
+				   u32 tx_frames, u32 rx_frames);
 	void (*get_coalesce_range)(struct hnae_handle *handle,
 				   u32 *tx_frames_low, u32 *rx_frames_low,
 				   u32 *tx_frames_high, u32 *rx_frames_high,
@@ -646,6 +650,41 @@ static inline void hnae_reuse_buffer(struct hnae_ring *ring, int i)
 	ring->desc[i].rx.ipoff_bnum_pid_flag = 0;
 }
 
+/* when reinit buffer size, we should reinit buffer description */
+static inline void hnae_reinit_all_ring_desc(struct hnae_handle *h)
+{
+	int i, j;
+	struct hnae_ring *ring;
+
+	for (i = 0; i < h->q_num; i++) {
+		ring = &h->qs[i]->rx_ring;
+		for (j = 0; j < ring->desc_num; j++)
+			ring->desc[j].addr = cpu_to_le64(ring->desc_cb[j].dma);
+	}
+
+	wmb();	/* commit all data before submit */
+}
+
+/* when reinit buffer size, we should reinit page offset */
+static inline void hnae_reinit_all_ring_page_off(struct hnae_handle *h)
+{
+	int i, j;
+	struct hnae_ring *ring;
+
+	for (i = 0; i < h->q_num; i++) {
+		ring = &h->qs[i]->rx_ring;
+		for (j = 0; j < ring->desc_num; j++) {
+			ring->desc_cb[j].page_offset = 0;
+			if (ring->desc[j].addr !=
+			    cpu_to_le64(ring->desc_cb[j].dma))
+				ring->desc[j].addr =
+					cpu_to_le64(ring->desc_cb[j].dma);
+		}
+	}
+
+	wmb();	/* commit all data before submit */
+}
+
 #define hnae_set_field(origin, mask, shift, val) \
 	do { \
 		(origin) &= (~(mask)); \
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
index 0a9cdf00b31a..ff864a187d5a 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
@@ -267,8 +267,32 @@ static int hns_ae_clr_multicast(struct hnae_handle *handle)
 static int hns_ae_set_mtu(struct hnae_handle *handle, int new_mtu)
 {
 	struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle);
+	struct hnae_queue *q;
+	u32 rx_buf_size;
+	int i, ret;
+
+	/* when buf_size is 2048, max mtu is 6K for rx ring max bd num is 3. */
+	if (!AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver)) {
+		if (new_mtu <= BD_SIZE_2048_MAX_MTU)
+			rx_buf_size = 2048;
+		else
+			rx_buf_size = 4096;
+	} else {
+		rx_buf_size = mac_cb->dsaf_dev->buf_size;
+	}
+
+	ret = hns_mac_set_mtu(mac_cb, new_mtu, rx_buf_size);
 
-	return hns_mac_set_mtu(mac_cb, new_mtu);
+	if (!ret) {
+		/* reinit ring buf_size */
+		for (i = 0; i < handle->q_num; i++) {
+			q = handle->qs[i];
+			q->rx_ring.buf_size = rx_buf_size;
+			hns_rcb_set_rx_ring_bs(q, rx_buf_size);
+		}
+	}
+
+	return ret;
 }
 
 static void hns_ae_set_tso_stats(struct hnae_handle *handle, int enable)
@@ -463,15 +487,21 @@ static void hns_ae_get_coalesce_usecs(struct hnae_handle *handle,
 					       ring_pair->port_id_in_comm);
 }
 
-static void hns_ae_get_rx_max_coalesced_frames(struct hnae_handle *handle,
-					       u32 *tx_frames, u32 *rx_frames)
+static void hns_ae_get_max_coalesced_frames(struct hnae_handle *handle,
+					    u32 *tx_frames, u32 *rx_frames)
 {
 	struct ring_pair_cb *ring_pair =
 		container_of(handle->qs[0], struct ring_pair_cb, q);
+	struct dsaf_device *dsaf_dev = hns_ae_get_dsaf_dev(handle->dev);
 
-	*tx_frames = hns_rcb_get_coalesced_frames(ring_pair->rcb_common,
-						  ring_pair->port_id_in_comm);
-	*rx_frames = hns_rcb_get_coalesced_frames(ring_pair->rcb_common,
+	if (AE_IS_VER1(dsaf_dev->dsaf_ver) ||
+	    handle->port_type == HNAE_PORT_DEBUG)
+		*tx_frames = hns_rcb_get_rx_coalesced_frames(
+			ring_pair->rcb_common, ring_pair->port_id_in_comm);
+	else
+		*tx_frames = hns_rcb_get_tx_coalesced_frames(
+			ring_pair->rcb_common, ring_pair->port_id_in_comm);
+	*rx_frames = hns_rcb_get_rx_coalesced_frames(ring_pair->rcb_common,
 						  ring_pair->port_id_in_comm);
 }
 
@@ -485,15 +515,34 @@ static int hns_ae_set_coalesce_usecs(struct hnae_handle *handle,
 		ring_pair->rcb_common, ring_pair->port_id_in_comm, timeout);
 }
 
-static int  hns_ae_set_coalesce_frames(struct hnae_handle *handle,
-				       u32 coalesce_frames)
+static int hns_ae_set_coalesce_frames(struct hnae_handle *handle,
+				      u32 tx_frames, u32 rx_frames)
 {
+	int ret;
 	struct ring_pair_cb *ring_pair =
 		container_of(handle->qs[0], struct ring_pair_cb, q);
+	struct dsaf_device *dsaf_dev = hns_ae_get_dsaf_dev(handle->dev);
 
-	return hns_rcb_set_coalesced_frames(
-		ring_pair->rcb_common,
-		ring_pair->port_id_in_comm, coalesce_frames);
+	if (AE_IS_VER1(dsaf_dev->dsaf_ver) ||
+	    handle->port_type == HNAE_PORT_DEBUG) {
+		if (tx_frames != rx_frames)
+			return -EINVAL;
+		return hns_rcb_set_rx_coalesced_frames(
+			ring_pair->rcb_common,
+			ring_pair->port_id_in_comm, rx_frames);
+	} else {
+		if (tx_frames != 1)
+			return -EINVAL;
+		ret = hns_rcb_set_tx_coalesced_frames(
+			ring_pair->rcb_common,
+			ring_pair->port_id_in_comm, tx_frames);
+		if (ret)
+			return ret;
+
+		return hns_rcb_set_rx_coalesced_frames(
+			ring_pair->rcb_common,
+			ring_pair->port_id_in_comm, rx_frames);
+	}
 }
 
 static void hns_ae_get_coalesce_range(struct hnae_handle *handle,
@@ -504,20 +553,27 @@ static void hns_ae_get_coalesce_range(struct hnae_handle *handle,
 {
 	struct dsaf_device *dsaf_dev;
 
+	assert(handle);
+
 	dsaf_dev = hns_ae_get_dsaf_dev(handle->dev);
 
-	*tx_frames_low  = HNS_RCB_MIN_COALESCED_FRAMES;
-	*rx_frames_low  = HNS_RCB_MIN_COALESCED_FRAMES;
-	*tx_frames_high =
-		(dsaf_dev->desc_num - 1 > HNS_RCB_MAX_COALESCED_FRAMES) ?
-		HNS_RCB_MAX_COALESCED_FRAMES : dsaf_dev->desc_num - 1;
-	*rx_frames_high =
-		(dsaf_dev->desc_num - 1 > HNS_RCB_MAX_COALESCED_FRAMES) ?
-		 HNS_RCB_MAX_COALESCED_FRAMES : dsaf_dev->desc_num - 1;
-	*tx_usecs_low   = 0;
-	*rx_usecs_low   = 0;
-	*tx_usecs_high  = HNS_RCB_MAX_COALESCED_USECS;
-	*rx_usecs_high  = HNS_RCB_MAX_COALESCED_USECS;
+	*tx_frames_low  = HNS_RCB_TX_FRAMES_LOW;
+	*rx_frames_low  = HNS_RCB_RX_FRAMES_LOW;
+
+	if (AE_IS_VER1(dsaf_dev->dsaf_ver) ||
+	    handle->port_type == HNAE_PORT_DEBUG)
+		*tx_frames_high =
+			(dsaf_dev->desc_num - 1 > HNS_RCB_TX_FRAMES_HIGH) ?
+			HNS_RCB_TX_FRAMES_HIGH : dsaf_dev->desc_num - 1;
+	else
+		*tx_frames_high = 1;
+
+	*rx_frames_high = (dsaf_dev->desc_num - 1 > HNS_RCB_RX_FRAMES_HIGH) ?
+		HNS_RCB_RX_FRAMES_HIGH : dsaf_dev->desc_num - 1;
+	*tx_usecs_low   = HNS_RCB_TX_USECS_LOW;
+	*rx_usecs_low   = HNS_RCB_RX_USECS_LOW;
+	*tx_usecs_high  = HNS_RCB_TX_USECS_HIGH;
+	*rx_usecs_high  = HNS_RCB_RX_USECS_HIGH;
 }
 
 void hns_ae_update_stats(struct hnae_handle *handle,
@@ -802,8 +858,9 @@ static int hns_ae_get_rss(struct hnae_handle *handle, u32 *indir, u8 *key,
 		memcpy(key, ppe_cb->rss_key, HNS_PPEV2_RSS_KEY_SIZE);
 
 	/* update the current hash->queue mappings from the shadow RSS table */
-	memcpy(indir, ppe_cb->rss_indir_table,
-	       HNS_PPEV2_RSS_IND_TBL_SIZE * sizeof(*indir));
+	if (indir)
+		memcpy(indir, ppe_cb->rss_indir_table,
+		       HNS_PPEV2_RSS_IND_TBL_SIZE  * sizeof(*indir));
 
 	return 0;
 }
@@ -814,15 +871,19 @@ static int hns_ae_set_rss(struct hnae_handle *handle, const u32 *indir,
 	struct hns_ppe_cb *ppe_cb = hns_get_ppe_cb(handle);
 
 	/* set the RSS Hash Key if specififed by the user */
-	if (key)
-		hns_ppe_set_rss_key(ppe_cb, (u32 *)key);
+	if (key) {
+		memcpy(ppe_cb->rss_key, key, HNS_PPEV2_RSS_KEY_SIZE);
+		hns_ppe_set_rss_key(ppe_cb, ppe_cb->rss_key);
+	}
 
-	/* update the shadow RSS table with user specified qids */
-	memcpy(ppe_cb->rss_indir_table, indir,
-	       HNS_PPEV2_RSS_IND_TBL_SIZE * sizeof(*indir));
+	if (indir) {
+		/* update the shadow RSS table with user specified qids */
+		memcpy(ppe_cb->rss_indir_table, indir,
+		       HNS_PPEV2_RSS_IND_TBL_SIZE  * sizeof(*indir));
 
-	/* now update the hardware */
-	hns_ppe_set_indir_table(ppe_cb, ppe_cb->rss_indir_table);
+		/* now update the hardware */
+		hns_ppe_set_indir_table(ppe_cb, ppe_cb->rss_indir_table);
+	}
 
 	return 0;
 }
@@ -846,7 +907,7 @@ static struct hnae_ae_ops hns_dsaf_ops = {
 	.get_autoneg = hns_ae_get_autoneg,
 	.set_pauseparam = hns_ae_set_pauseparam,
 	.get_coalesce_usecs = hns_ae_get_coalesce_usecs,
-	.get_rx_max_coalesced_frames = hns_ae_get_rx_max_coalesced_frames,
+	.get_max_coalesced_frames = hns_ae_get_max_coalesced_frames,
 	.set_coalesce_usecs = hns_ae_set_coalesce_usecs,
 	.set_coalesce_frames = hns_ae_set_coalesce_frames,
 	.get_coalesce_range = hns_ae_get_coalesce_range,
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
index 3382441fe7b5..74bd260ca02a 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
@@ -86,12 +86,11 @@ static void hns_gmac_disable(void *mac_drv, enum mac_commom_mode mode)
 		dsaf_set_dev_bit(drv, GMAC_PORT_EN_REG, GMAC_PORT_RX_EN_B, 0);
 }
 
-/**
-*hns_gmac_get_en - get port enable
-*@mac_drv:mac device
-*@rx:rx enable
-*@tx:tx enable
-*/
+/* hns_gmac_get_en - get port enable
+ * @mac_drv:mac device
+ * @rx:rx enable
+ * @tx:tx enable
+ */
 static void hns_gmac_get_en(void *mac_drv, u32 *rx, u32 *tx)
 {
 	struct mac_driver *drv = (struct mac_driver *)mac_drv;
@@ -148,6 +147,17 @@ static void hns_gmac_config_max_frame_length(void *mac_drv, u16 newval)
 			   GMAC_MAX_FRM_SIZE_S, newval);
 }
 
+static void hns_gmac_config_pad_and_crc(void *mac_drv, u8 newval)
+{
+	u32 tx_ctrl;
+	struct mac_driver *drv = (struct mac_driver *)mac_drv;
+
+	tx_ctrl = dsaf_read_dev(drv, GMAC_TRANSMIT_CONTROL_REG);
+	dsaf_set_bit(tx_ctrl, GMAC_TX_PAD_EN_B, !!newval);
+	dsaf_set_bit(tx_ctrl, GMAC_TX_CRC_ADD_B, !!newval);
+	dsaf_write_dev(drv, GMAC_TRANSMIT_CONTROL_REG, tx_ctrl);
+}
+
 static void hns_gmac_config_an_mode(void *mac_drv, u8 newval)
 {
 	struct mac_driver *drv = (struct mac_driver *)mac_drv;
@@ -250,7 +260,6 @@ static void hns_gmac_get_pausefrm_cfg(void *mac_drv, u32 *rx_pause_en,
 static int hns_gmac_adjust_link(void *mac_drv, enum mac_speed speed,
 				u32 full_duplex)
 {
-	u32 tx_ctrl;
 	struct mac_driver *drv = (struct mac_driver *)mac_drv;
 
 	dsaf_set_dev_bit(drv, GMAC_DUPLEX_TYPE_REG,
@@ -279,14 +288,6 @@ static int hns_gmac_adjust_link(void *mac_drv, enum mac_speed speed,
 		return -EINVAL;
 	}
 
-	tx_ctrl = dsaf_read_dev(drv, GMAC_TRANSMIT_CONTROL_REG);
-	dsaf_set_bit(tx_ctrl, GMAC_TX_PAD_EN_B, 1);
-	dsaf_set_bit(tx_ctrl, GMAC_TX_CRC_ADD_B, 1);
-	dsaf_write_dev(drv, GMAC_TRANSMIT_CONTROL_REG, tx_ctrl);
-
-	dsaf_set_dev_bit(drv, GMAC_MODE_CHANGE_EN_REG,
-			 GMAC_MODE_CHANGE_EB_B, 1);
-
 	return 0;
 }
 
@@ -325,6 +326,17 @@ static void hns_gmac_init(void *mac_drv)
 	hns_gmac_tx_loop_pkt_dis(mac_drv);
 	if (drv->mac_cb->mac_type == HNAE_PORT_DEBUG)
 		hns_gmac_set_uc_match(mac_drv, 0);
+
+	hns_gmac_config_pad_and_crc(mac_drv, 1);
+
+	dsaf_set_dev_bit(drv, GMAC_MODE_CHANGE_EN_REG,
+			 GMAC_MODE_CHANGE_EB_B, 1);
+
+	/* reduce gmac tx water line to avoid gmac hang-up
+	 * in speed 100M and duplex half.
+	 */
+	dsaf_set_dev_field(drv, GMAC_TX_WATER_LINE_REG, GMAC_TX_WATER_LINE_MASK,
+			   GMAC_TX_WATER_LINE_SHIFT, 8);
 }
 
 void hns_gmac_update_stats(void *mac_drv)
@@ -453,24 +465,6 @@ static int hns_gmac_config_loopback(void *mac_drv, enum hnae_loop loop_mode,
 	return 0;
 }
 
-static void hns_gmac_config_pad_and_crc(void *mac_drv, u8 newval)
-{
-	u32 tx_ctrl;
-	struct mac_driver *drv = (struct mac_driver *)mac_drv;
-
-	tx_ctrl = dsaf_read_dev(drv, GMAC_TRANSMIT_CONTROL_REG);
-	dsaf_set_bit(tx_ctrl, GMAC_TX_PAD_EN_B, !!newval);
-	dsaf_set_bit(tx_ctrl, GMAC_TX_CRC_ADD_B, !!newval);
-	dsaf_write_dev(drv, GMAC_TRANSMIT_CONTROL_REG, tx_ctrl);
-}
-
-static void hns_gmac_get_id(void *mac_drv, u8 *mac_id)
-{
-	struct mac_driver *drv = (struct mac_driver *)mac_drv;
-
-	*mac_id = drv->mac_id;
-}
-
 static void hns_gmac_get_info(void *mac_drv, struct mac_info *mac_info)
 {
 	enum hns_gmac_duplex_mdoe duplex;
@@ -712,7 +706,6 @@ void *hns_gmac_config(struct hns_mac_cb *mac_cb, struct mac_params *mac_param)
 	mac_drv->config_pad_and_crc = hns_gmac_config_pad_and_crc;
 	mac_drv->config_half_duplex = hns_gmac_set_duplex_type;
 	mac_drv->set_rx_ignore_pause_frames = hns_gmac_set_rx_auto_pause_frames;
-	mac_drv->mac_get_id = hns_gmac_get_id;
 	mac_drv->get_info = hns_gmac_get_info;
 	mac_drv->autoneg_stat = hns_gmac_autoneg_stat;
 	mac_drv->get_pause_enable = hns_gmac_get_pausefrm_cfg;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index bdd8cdd732fb..0c1f56e58074 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -335,44 +335,6 @@ int hns_mac_set_multi(struct hns_mac_cb *mac_cb,
 	return 0;
 }
 
-/**
- *hns_mac_del_mac - delete mac address into dsaf table,can't delete the same
- *                  address twice
- *@net_dev: net device
- *@vfn :   vf lan
- *@mac : mac address
- *return status
- */
-int hns_mac_del_mac(struct hns_mac_cb *mac_cb, u32 vfn, char *mac)
-{
-	struct mac_entry_idx *old_mac;
-	struct dsaf_device *dsaf_dev;
-	u32 ret;
-
-	dsaf_dev = mac_cb->dsaf_dev;
-
-	if (vfn < DSAF_MAX_VM_NUM) {
-		old_mac = &mac_cb->addr_entry_idx[vfn];
-	} else {
-		dev_err(mac_cb->dev,
-			"vf queue is too large, %s mac%d queue = %#x!\n",
-			mac_cb->dsaf_dev->ae_dev.name, mac_cb->mac_id, vfn);
-		return -EINVAL;
-	}
-
-	if (dsaf_dev) {
-		ret = hns_dsaf_del_mac_entry(dsaf_dev, old_mac->vlan_id,
-					     mac_cb->mac_id, old_mac->addr);
-		if (ret)
-			return ret;
-
-		if (memcmp(old_mac->addr, mac, sizeof(old_mac->addr)) == 0)
-			old_mac->valid = 0;
-	}
-
-	return 0;
-}
-
 int hns_mac_clr_multicast(struct hns_mac_cb *mac_cb, int vfn)
 {
 	struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev;
@@ -494,10 +456,9 @@ void hns_mac_reset(struct hns_mac_cb *mac_cb)
 	}
 }
 
-int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu)
+int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu, u32 buf_size)
 {
 	struct mac_driver *drv = hns_mac_get_drv(mac_cb);
-	u32 buf_size = mac_cb->dsaf_dev->buf_size;
 	u32 new_frm = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
 	u32 max_frm = AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver) ?
 			MAC_MAX_MTU : MAC_MAX_MTU_V2;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
index 2bb3d1e93c64..24dfba53a0f2 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
@@ -373,8 +373,6 @@ struct mac_driver {
 	void (*set_rx_ignore_pause_frames)(void *mac_drv, u32 enable);
 	/* config rx mode for promiscuous*/
 	void (*set_promiscuous)(void *mac_drv, u8 enable);
-	/* get mac id */
-	void (*mac_get_id)(void *mac_drv, u8 *mac_id);
 	void (*mac_pausefrm_cfg)(void *mac_drv, u32 rx_en, u32 tx_en);
 
 	void (*autoneg_stat)(void *mac_drv, u32 *enable);
@@ -436,7 +434,6 @@ int hns_mac_set_multi(struct hns_mac_cb *mac_cb,
 int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vm, bool enable);
 void hns_mac_start(struct hns_mac_cb *mac_cb);
 void hns_mac_stop(struct hns_mac_cb *mac_cb);
-int hns_mac_del_mac(struct hns_mac_cb *mac_cb, u32 vfn, char *mac);
 void hns_mac_uninit(struct dsaf_device *dsaf_dev);
 void hns_mac_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex);
 void hns_mac_reset(struct hns_mac_cb *mac_cb);
@@ -444,7 +441,7 @@ void hns_mac_get_autoneg(struct hns_mac_cb *mac_cb, u32 *auto_neg);
 void hns_mac_get_pauseparam(struct hns_mac_cb *mac_cb, u32 *rx_en, u32 *tx_en);
 int hns_mac_set_autoneg(struct hns_mac_cb *mac_cb, u8 enable);
 int hns_mac_set_pauseparam(struct hns_mac_cb *mac_cb, u32 rx_en, u32 tx_en);
-int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu);
+int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu, u32 buf_size);
 int hns_mac_get_port_info(struct hns_mac_cb *mac_cb,
 			  u8 *auto_neg, u16 *speed, u8 *duplex);
 int hns_mac_config_mac_loopback(struct hns_mac_cb *mac_cb,
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 403ea9db6dbd..e0bc79ea3d88 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -510,10 +510,10 @@ static void hns_dsafv2_sbm_bp_wl_cfg(struct dsaf_device *dsaf_dev)
 		o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg);
 		dsaf_set_field(o_sbm_bp_cfg,
 			       DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_M,
-			       DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_S, 48);
+			       DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_S, 55);
 		dsaf_set_field(o_sbm_bp_cfg,
 			       DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_M,
-			       DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_S, 80);
+			       DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_S, 110);
 		dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg);
 
 		/* for no enable pfc mode */
@@ -521,10 +521,10 @@ static void hns_dsafv2_sbm_bp_wl_cfg(struct dsaf_device *dsaf_dev)
 		o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg);
 		dsaf_set_field(o_sbm_bp_cfg,
 			       DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_M,
-			       DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_S, 192);
+			       DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_S, 128);
 		dsaf_set_field(o_sbm_bp_cfg,
 			       DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_M,
-			       DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_S, 240);
+			       DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_S, 192);
 		dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg);
 	}
 
@@ -1648,87 +1648,6 @@ int hns_dsaf_rm_mac_addr(
 				      mac_entry->addr);
 }
 
-/**
- * hns_dsaf_set_mac_mc_entry - set mac mc-entry
- * @dsaf_dev: dsa fabric device struct pointer
- * @mac_entry: mc-mac entry
- */
-int hns_dsaf_set_mac_mc_entry(
-	struct dsaf_device *dsaf_dev,
-	struct dsaf_drv_mac_multi_dest_entry *mac_entry)
-{
-	u16 entry_index = DSAF_INVALID_ENTRY_IDX;
-	struct dsaf_drv_tbl_tcam_key mac_key;
-	struct dsaf_tbl_tcam_mcast_cfg mac_data;
-	struct dsaf_drv_priv *priv =
-	    (struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev);
-	struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl;
-	struct dsaf_drv_tbl_tcam_key tmp_mac_key;
-	struct dsaf_tbl_tcam_data tcam_data;
-
-	/* mac addr check */
-	if (MAC_IS_ALL_ZEROS(mac_entry->addr)) {
-		dev_err(dsaf_dev->dev, "set uc %s Mac %pM err!\n",
-			dsaf_dev->ae_dev.name, mac_entry->addr);
-		return -EINVAL;
-	}
-
-	/*config key */
-	hns_dsaf_set_mac_key(dsaf_dev, &mac_key,
-			     mac_entry->in_vlan_id,
-			     mac_entry->in_port_num, mac_entry->addr);
-
-	/* entry ie exist? */
-	entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key);
-	if (entry_index == DSAF_INVALID_ENTRY_IDX) {
-		/*if hasnot, find enpty entry*/
-		entry_index = hns_dsaf_find_empty_mac_entry(dsaf_dev);
-		if (entry_index == DSAF_INVALID_ENTRY_IDX) {
-			/*if hasnot empty, error*/
-			dev_err(dsaf_dev->dev,
-				"set_uc_entry failed, %s Mac key(%#x:%#x)\n",
-				dsaf_dev->ae_dev.name,
-				mac_key.high.val, mac_key.low.val);
-			return -EINVAL;
-		}
-
-		/* config hardware entry */
-		memset(mac_data.tbl_mcast_port_msk,
-		       0, sizeof(mac_data.tbl_mcast_port_msk));
-	} else {
-		/* config hardware entry */
-		hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data,
-				     &mac_data);
-
-		tmp_mac_key.high.val =
-			le32_to_cpu(tcam_data.tbl_tcam_data_high);
-		tmp_mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
-	}
-	mac_data.tbl_mcast_old_en = 0;
-	mac_data.tbl_mcast_item_vld = 1;
-	dsaf_set_field(mac_data.tbl_mcast_port_msk[0],
-		       0x3F, 0, mac_entry->port_mask[0]);
-
-	dev_dbg(dsaf_dev->dev,
-		"set_uc_entry, %s key(%#x:%#x) entry_index%d\n",
-		dsaf_dev->ae_dev.name, mac_key.high.val,
-		mac_key.low.val, entry_index);
-
-	tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
-	tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
-
-	hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index, &tcam_data, NULL,
-			     &mac_data);
-
-	/* config software entry */
-	soft_mac_entry += entry_index;
-	soft_mac_entry->index = entry_index;
-	soft_mac_entry->tcam_key.high.val = mac_key.high.val;
-	soft_mac_entry->tcam_key.low.val = mac_key.low.val;
-
-	return 0;
-}
-
 static void hns_dsaf_mc_mask_bit_clear(char *dst, const char *src)
 {
 	u16 *a = (u16 *)dst;
@@ -2090,166 +2009,6 @@ int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev, u8 mac_id,
 	return ret;
 }
 
-/**
- * hns_dsaf_get_mac_uc_entry - get mac uc entry
- * @dsaf_dev: dsa fabric device struct pointer
- * @mac_entry: mac entry
- */
-int hns_dsaf_get_mac_uc_entry(struct dsaf_device *dsaf_dev,
-			      struct dsaf_drv_mac_single_dest_entry *mac_entry)
-{
-	u16 entry_index = DSAF_INVALID_ENTRY_IDX;
-	struct dsaf_drv_tbl_tcam_key mac_key;
-
-	struct dsaf_tbl_tcam_ucast_cfg mac_data;
-	struct dsaf_tbl_tcam_data tcam_data;
-
-	/* check macaddr */
-	if (MAC_IS_ALL_ZEROS(mac_entry->addr) ||
-	    MAC_IS_BROADCAST(mac_entry->addr)) {
-		dev_err(dsaf_dev->dev, "get_entry failed,addr %pM\n",
-			mac_entry->addr);
-		return -EINVAL;
-	}
-
-	/*config key */
-	hns_dsaf_set_mac_key(dsaf_dev, &mac_key, mac_entry->in_vlan_id,
-			     mac_entry->in_port_num, mac_entry->addr);
-
-	/*check exist? */
-	entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key);
-	if (entry_index == DSAF_INVALID_ENTRY_IDX) {
-		/*find none, error */
-		dev_err(dsaf_dev->dev,
-			"get_uc_entry failed, %s Mac key(%#x:%#x)\n",
-			dsaf_dev->ae_dev.name,
-			mac_key.high.val, mac_key.low.val);
-		return -EINVAL;
-	}
-	dev_dbg(dsaf_dev->dev,
-		"get_uc_entry, %s Mac key(%#x:%#x) entry_index%d\n",
-		dsaf_dev->ae_dev.name, mac_key.high.val,
-		mac_key.low.val, entry_index);
-
-	/* read entry */
-	hns_dsaf_tcam_uc_get(dsaf_dev, entry_index, &tcam_data, &mac_data);
-
-	mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
-	mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
-
-	mac_entry->port_num = mac_data.tbl_ucast_out_port;
-
-	return 0;
-}
-
-/**
- * hns_dsaf_get_mac_mc_entry - get mac mc entry
- * @dsaf_dev: dsa fabric device struct pointer
- * @mac_entry: mac entry
- */
-int hns_dsaf_get_mac_mc_entry(struct dsaf_device *dsaf_dev,
-			      struct dsaf_drv_mac_multi_dest_entry *mac_entry)
-{
-	u16 entry_index = DSAF_INVALID_ENTRY_IDX;
-	struct dsaf_drv_tbl_tcam_key mac_key;
-
-	struct dsaf_tbl_tcam_mcast_cfg mac_data;
-	struct dsaf_tbl_tcam_data tcam_data;
-
-	/*check mac addr */
-	if (MAC_IS_ALL_ZEROS(mac_entry->addr) ||
-	    MAC_IS_BROADCAST(mac_entry->addr)) {
-		dev_err(dsaf_dev->dev, "get_entry failed,addr %pM\n",
-			mac_entry->addr);
-		return -EINVAL;
-	}
-
-	/*config key */
-	hns_dsaf_set_mac_key(dsaf_dev, &mac_key, mac_entry->in_vlan_id,
-			     mac_entry->in_port_num, mac_entry->addr);
-
-	/*check exist? */
-	entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key);
-	if (entry_index == DSAF_INVALID_ENTRY_IDX) {
-		/* find none, error */
-		dev_err(dsaf_dev->dev,
-			"get_mac_uc_entry failed, %s Mac key(%#x:%#x)\n",
-			dsaf_dev->ae_dev.name, mac_key.high.val,
-			mac_key.low.val);
-		return -EINVAL;
-	}
-	dev_dbg(dsaf_dev->dev,
-		"get_mac_uc_entry, %s Mac key(%#x:%#x) entry_index%d\n",
-		dsaf_dev->ae_dev.name, mac_key.high.val,
-		mac_key.low.val, entry_index);
-
-	/*read entry */
-	hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data, &mac_data);
-
-	mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
-	mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
-
-	mac_entry->port_mask[0] = mac_data.tbl_mcast_port_msk[0] & 0x3F;
-	return 0;
-}
-
-/**
- * hns_dsaf_get_mac_entry_by_index - get mac entry by tab index
- * @dsaf_dev: dsa fabric device struct pointer
- * @entry_index: tab entry index
- * @mac_entry: mac entry
- */
-int hns_dsaf_get_mac_entry_by_index(
-	struct dsaf_device *dsaf_dev,
-	u16 entry_index, struct dsaf_drv_mac_multi_dest_entry *mac_entry)
-{
-	struct dsaf_drv_tbl_tcam_key mac_key;
-
-	struct dsaf_tbl_tcam_mcast_cfg mac_data;
-	struct dsaf_tbl_tcam_ucast_cfg mac_uc_data;
-	struct dsaf_tbl_tcam_data tcam_data;
-	char mac_addr[ETH_ALEN] = {0};
-
-	if (entry_index >= dsaf_dev->tcam_max_num) {
-		/* find none, del error */
-		dev_err(dsaf_dev->dev, "get_uc_entry failed, %s\n",
-			dsaf_dev->ae_dev.name);
-		return -EINVAL;
-	}
-
-	/* mc entry, do read opt */
-	hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data, &mac_data);
-
-	mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
-	mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
-
-	mac_entry->port_mask[0] = mac_data.tbl_mcast_port_msk[0] & 0x3F;
-
-	/***get mac addr*/
-	mac_addr[0] = mac_key.high.bits.mac_0;
-	mac_addr[1] = mac_key.high.bits.mac_1;
-	mac_addr[2] = mac_key.high.bits.mac_2;
-	mac_addr[3] = mac_key.high.bits.mac_3;
-	mac_addr[4] = mac_key.low.bits.mac_4;
-	mac_addr[5] = mac_key.low.bits.mac_5;
-	/**is mc or uc*/
-	if (MAC_IS_MULTICAST((u8 *)mac_addr) ||
-	    MAC_IS_L3_MULTICAST((u8 *)mac_addr)) {
-		/**mc donot do*/
-	} else {
-		/*is not mc, just uc... */
-		hns_dsaf_tcam_uc_get(dsaf_dev, entry_index, &tcam_data,
-				     &mac_uc_data);
-
-		mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
-		mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
-
-		mac_entry->port_mask[0] = (1 << mac_uc_data.tbl_ucast_out_port);
-	}
-
-	return 0;
-}
-
 static struct dsaf_device *hns_dsaf_alloc_dev(struct device *dev,
 					      size_t sizeof_priv)
 {
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
index cef6bf46ae93..4507e8222683 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
@@ -68,7 +68,7 @@ enum dsaf_roce_qos_sl {
 };
 
 #define DSAF_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset))))
-#define HNS_DSAF_IS_DEBUG(dev) (dev->dsaf_mode == DSAF_MODE_DISABLE_SP)
+#define HNS_DSAF_IS_DEBUG(dev) ((dev)->dsaf_mode == DSAF_MODE_DISABLE_SP)
 
 enum hal_dsaf_mode {
 	HRD_DSAF_NO_DSAF_MODE	= 0x0,
@@ -429,23 +429,12 @@ static inline struct hnae_vf_cb *hns_ae_get_vf_cb(
 
 int hns_dsaf_set_mac_uc_entry(struct dsaf_device *dsaf_dev,
 			      struct dsaf_drv_mac_single_dest_entry *mac_entry);
-int hns_dsaf_set_mac_mc_entry(struct dsaf_device *dsaf_dev,
-			      struct dsaf_drv_mac_multi_dest_entry *mac_entry);
 int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
 			     struct dsaf_drv_mac_single_dest_entry *mac_entry);
 int hns_dsaf_del_mac_entry(struct dsaf_device *dsaf_dev, u16 vlan_id,
 			   u8 in_port_num, u8 *addr);
 int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
 			     struct dsaf_drv_mac_single_dest_entry *mac_entry);
-int hns_dsaf_get_mac_uc_entry(struct dsaf_device *dsaf_dev,
-			      struct dsaf_drv_mac_single_dest_entry *mac_entry);
-int hns_dsaf_get_mac_mc_entry(struct dsaf_device *dsaf_dev,
-			      struct dsaf_drv_mac_multi_dest_entry *mac_entry);
-int hns_dsaf_get_mac_entry_by_index(
-	struct dsaf_device *dsaf_dev,
-	u16 entry_index,
-	struct dsaf_drv_mac_multi_dest_entry *mac_entry);
-
 void hns_dsaf_fix_mac_mode(struct hns_mac_cb *mac_cb);
 
 int hns_dsaf_ae_init(struct dsaf_device *dsaf_dev);
@@ -475,5 +464,4 @@ int hns_dsaf_rm_mac_addr(
 int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev,
 			     u8 mac_id, u8 port_num);
 
-
 #endif /* __HNS_DSAF_MAIN_H__ */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
index 6ea872287307..eba406bea52f 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
@@ -496,17 +496,17 @@ void hns_ppe_get_stats(struct hns_ppe_cb *ppe_cb, u64 *data)
  */
 int hns_ppe_init(struct dsaf_device *dsaf_dev)
 {
-	int i, k;
 	int ret;
+	int i;
 
 	for (i = 0; i < HNS_PPE_COM_NUM; i++) {
 		ret = hns_ppe_common_get_cfg(dsaf_dev, i);
 		if (ret)
-			goto get_ppe_cfg_fail;
+			goto get_cfg_fail;
 
 		ret = hns_rcb_common_get_cfg(dsaf_dev, i);
 		if (ret)
-			goto get_rcb_cfg_fail;
+			goto get_cfg_fail;
 
 		hns_ppe_get_cfg(dsaf_dev->ppe_common[i]);
 
@@ -518,13 +518,12 @@ int hns_ppe_init(struct dsaf_device *dsaf_dev)
 
 	return 0;
 
-get_rcb_cfg_fail:
-	hns_ppe_common_free_cfg(dsaf_dev, i);
-get_ppe_cfg_fail:
-	for (k = i - 1; k >= 0; k--) {
-		hns_rcb_common_free_cfg(dsaf_dev, k);
-		hns_ppe_common_free_cfg(dsaf_dev, k);
+get_cfg_fail:
+	for (i = 0; i < HNS_PPE_COM_NUM; i++) {
+		hns_rcb_common_free_cfg(dsaf_dev, i);
+		hns_ppe_common_free_cfg(dsaf_dev, i);
 	}
+
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
index f0ed80d6ef9c..c20a0f4f8f02 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
@@ -32,6 +32,9 @@
 #define RCB_RESET_WAIT_TIMES 30
 #define RCB_RESET_TRY_TIMES 10
 
+/* Because default mtu is 1500, rcb buffer size is set to 2048 enough */
+#define RCB_DEFAULT_BUFFER_SIZE 2048
+
 /**
  *hns_rcb_wait_fbd_clean - clean fbd
  *@qs: ring struct pointer array
@@ -192,6 +195,30 @@ void hns_rcb_common_init_commit_hw(struct rcb_common_cb *rcb_common)
 	wmb();	/* Sync point after breakpoint */
 }
 
+/* hns_rcb_set_tx_ring_bs - init rcb ring buf size regester
+ *@q: hnae_queue
+ *@buf_size: buffer size set to hw
+ */
+void hns_rcb_set_tx_ring_bs(struct hnae_queue *q, u32 buf_size)
+{
+	u32 bd_size_type = hns_rcb_buf_size2type(buf_size);
+
+	dsaf_write_dev(q, RCB_RING_TX_RING_BD_LEN_REG,
+		       bd_size_type);
+}
+
+/* hns_rcb_set_rx_ring_bs - init rcb ring buf size regester
+ *@q: hnae_queue
+ *@buf_size: buffer size set to hw
+ */
+void hns_rcb_set_rx_ring_bs(struct hnae_queue *q, u32 buf_size)
+{
+	u32 bd_size_type = hns_rcb_buf_size2type(buf_size);
+
+	dsaf_write_dev(q, RCB_RING_RX_RING_BD_LEN_REG,
+		       bd_size_type);
+}
+
 /**
  *hns_rcb_ring_init - init rcb ring
  *@ring_pair: ring pair control block
@@ -200,8 +227,6 @@ void hns_rcb_common_init_commit_hw(struct rcb_common_cb *rcb_common)
 static void hns_rcb_ring_init(struct ring_pair_cb *ring_pair, int ring_type)
 {
 	struct hnae_queue *q = &ring_pair->q;
-	struct rcb_common_cb *rcb_common = ring_pair->rcb_common;
-	u32 bd_size_type = rcb_common->dsaf_dev->buf_size_type;
 	struct hnae_ring *ring =
 		(ring_type == RX_RING) ? &q->rx_ring : &q->tx_ring;
 	dma_addr_t dma = ring->desc_dma_addr;
@@ -212,8 +237,8 @@ static void hns_rcb_ring_init(struct ring_pair_cb *ring_pair, int ring_type)
 		dsaf_write_dev(q, RCB_RING_RX_RING_BASEADDR_H_REG,
 			       (u32)((dma >> 31) >> 1));
 
-		dsaf_write_dev(q, RCB_RING_RX_RING_BD_LEN_REG,
-			       bd_size_type);
+		hns_rcb_set_rx_ring_bs(q, ring->buf_size);
+
 		dsaf_write_dev(q, RCB_RING_RX_RING_BD_NUM_REG,
 			       ring_pair->port_id_in_comm);
 		dsaf_write_dev(q, RCB_RING_RX_RING_PKTLINE_REG,
@@ -224,12 +249,12 @@ static void hns_rcb_ring_init(struct ring_pair_cb *ring_pair, int ring_type)
 		dsaf_write_dev(q, RCB_RING_TX_RING_BASEADDR_H_REG,
 			       (u32)((dma >> 31) >> 1));
 
-		dsaf_write_dev(q, RCB_RING_TX_RING_BD_LEN_REG,
-			       bd_size_type);
+		hns_rcb_set_tx_ring_bs(q, ring->buf_size);
+
 		dsaf_write_dev(q, RCB_RING_TX_RING_BD_NUM_REG,
 			       ring_pair->port_id_in_comm);
 		dsaf_write_dev(q, RCB_RING_TX_RING_PKTLINE_REG,
-			       ring_pair->port_id_in_comm);
+			ring_pair->port_id_in_comm + HNS_RCB_TX_PKTLINE_OFFSET);
 	}
 }
 
@@ -259,13 +284,27 @@ static void hns_rcb_set_port_desc_cnt(struct rcb_common_cb *rcb_common,
 static void hns_rcb_set_port_timeout(
 	struct rcb_common_cb *rcb_common, u32 port_idx, u32 timeout)
 {
-	if (AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver))
+	if (AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver)) {
 		dsaf_write_dev(rcb_common, RCB_CFG_OVERTIME_REG,
 			       timeout * HNS_RCB_CLK_FREQ_MHZ);
-	else
+	} else if (!HNS_DSAF_IS_DEBUG(rcb_common->dsaf_dev)) {
+		if (timeout > HNS_RCB_DEF_GAP_TIME_USECS)
+			dsaf_write_dev(rcb_common,
+				       RCB_PORT_INT_GAPTIME_REG + port_idx * 4,
+				       HNS_RCB_DEF_GAP_TIME_USECS);
+		else
+			dsaf_write_dev(rcb_common,
+				       RCB_PORT_INT_GAPTIME_REG + port_idx * 4,
+				       timeout);
+
+		dsaf_write_dev(rcb_common,
+			       RCB_PORT_CFG_OVERTIME_REG + port_idx * 4,
+			       timeout);
+	} else {
 		dsaf_write_dev(rcb_common,
 			       RCB_PORT_CFG_OVERTIME_REG + port_idx * 4,
 			       timeout);
+	}
 }
 
 static int hns_rcb_common_get_port_num(struct rcb_common_cb *rcb_common)
@@ -327,8 +366,12 @@ int hns_rcb_common_init_hw(struct rcb_common_cb *rcb_common)
 
 	for (i = 0; i < port_num; i++) {
 		hns_rcb_set_port_desc_cnt(rcb_common, i, rcb_common->desc_num);
-		(void)hns_rcb_set_coalesced_frames(
-			rcb_common, i, HNS_RCB_DEF_COALESCED_FRAMES);
+		hns_rcb_set_rx_coalesced_frames(
+			rcb_common, i, HNS_RCB_DEF_RX_COALESCED_FRAMES);
+		if (!AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver) &&
+		    !HNS_DSAF_IS_DEBUG(rcb_common->dsaf_dev))
+			hns_rcb_set_tx_coalesced_frames(
+				rcb_common, i, HNS_RCB_DEF_TX_COALESCED_FRAMES);
 		hns_rcb_set_port_timeout(
 			rcb_common, i, HNS_RCB_DEF_COALESCED_USECS);
 	}
@@ -380,7 +423,6 @@ static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type)
 	struct hnae_ring *ring;
 	struct rcb_common_cb *rcb_common;
 	struct ring_pair_cb *ring_pair_cb;
-	u32 buf_size;
 	u16 desc_num, mdnum_ppkt;
 	bool irq_idx, is_ver1;
 
@@ -401,7 +443,6 @@ static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type)
 	}
 
 	rcb_common = ring_pair_cb->rcb_common;
-	buf_size = rcb_common->dsaf_dev->buf_size;
 	desc_num = rcb_common->dsaf_dev->desc_num;
 
 	ring->desc = NULL;
@@ -410,7 +451,7 @@ static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type)
 	ring->irq = ring_pair_cb->virq[irq_idx];
 	ring->desc_dma_addr = 0;
 
-	ring->buf_size = buf_size;
+	ring->buf_size = RCB_DEFAULT_BUFFER_SIZE;
 	ring->desc_num = desc_num;
 	ring->max_desc_num_per_pkt = mdnum_ppkt;
 	ring->max_raw_data_sz_per_desc = HNS_RCB_MAX_PKT_SIZE;
@@ -430,7 +471,6 @@ static void hns_rcb_ring_pair_get_cfg(struct ring_pair_cb *ring_pair_cb)
 static int hns_rcb_get_port_in_comm(
 	struct rcb_common_cb *rcb_common, int ring_idx)
 {
-
 	return ring_idx / (rcb_common->max_q_per_vf * rcb_common->max_vfn);
 }
 
@@ -484,19 +524,35 @@ void hns_rcb_get_cfg(struct rcb_common_cb *rcb_common)
 }
 
 /**
- *hns_rcb_get_coalesced_frames - get rcb port coalesced frames
+ *hns_rcb_get_rx_coalesced_frames - get rcb port rx coalesced frames
  *@rcb_common: rcb_common device
  *@port_idx:port id in comm
  *
  *Returns: coalesced_frames
  */
-u32 hns_rcb_get_coalesced_frames(
+u32 hns_rcb_get_rx_coalesced_frames(
 	struct rcb_common_cb *rcb_common, u32 port_idx)
 {
 	return dsaf_read_dev(rcb_common, RCB_CFG_PKTLINE_REG + port_idx * 4);
 }
 
 /**
+ *hns_rcb_get_tx_coalesced_frames - get rcb port tx coalesced frames
+ *@rcb_common: rcb_common device
+ *@port_idx:port id in comm
+ *
+ *Returns: coalesced_frames
+ */
+u32 hns_rcb_get_tx_coalesced_frames(
+	struct rcb_common_cb *rcb_common, u32 port_idx)
+{
+	u64 reg;
+
+	reg = RCB_CFG_PKTLINE_REG + (port_idx + HNS_RCB_TX_PKTLINE_OFFSET) * 4;
+	return dsaf_read_dev(rcb_common, reg);
+}
+
+/**
  *hns_rcb_get_coalesce_usecs - get rcb port coalesced time_out
  *@rcb_common: rcb_common device
  *@port_idx:port id in comm
@@ -538,33 +594,47 @@ int hns_rcb_set_coalesce_usecs(
 			return -EINVAL;
 		}
 	}
-	if (timeout > HNS_RCB_MAX_COALESCED_USECS) {
+	if (timeout > HNS_RCB_MAX_COALESCED_USECS || timeout == 0) {
 		dev_err(rcb_common->dsaf_dev->dev,
-			"error: coalesce_usecs setting supports 0~1023us\n");
+			"error: coalesce_usecs setting supports 1~1023us\n");
 		return -EINVAL;
 	}
+	hns_rcb_set_port_timeout(rcb_common, port_idx, timeout);
+	return 0;
+}
 
-	if (!AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver)) {
-		if (timeout == 0)
-			/* set timeout to 0, Disable gap time */
-			dsaf_set_reg_field(rcb_common->io_base,
-					   RCB_INT_GAP_TIME_REG + port_idx * 4,
-					   PPE_INT_GAPTIME_M, PPE_INT_GAPTIME_B,
-					   0);
-		else
-			/* set timeout non 0, restore gap time to 1 */
-			dsaf_set_reg_field(rcb_common->io_base,
-					   RCB_INT_GAP_TIME_REG + port_idx * 4,
-					   PPE_INT_GAPTIME_M, PPE_INT_GAPTIME_B,
-					   1);
+/**
+ *hns_rcb_set_tx_coalesced_frames - set rcb coalesced frames
+ *@rcb_common: rcb_common device
+ *@port_idx:port id in comm
+ *@coalesced_frames:tx/rx BD num for coalesced frames
+ *
+ * Returns:
+ * Zero for success, or an error code in case of failure
+ */
+int hns_rcb_set_tx_coalesced_frames(
+	struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames)
+{
+	u32 old_waterline =
+		hns_rcb_get_tx_coalesced_frames(rcb_common, port_idx);
+	u64 reg;
+
+	if (coalesced_frames == old_waterline)
+		return 0;
+
+	if (coalesced_frames != 1) {
+		dev_err(rcb_common->dsaf_dev->dev,
+			"error: not support tx coalesce_frames setting!\n");
+		return -EINVAL;
 	}
 
-	hns_rcb_set_port_timeout(rcb_common, port_idx, timeout);
+	reg = RCB_CFG_PKTLINE_REG + (port_idx + HNS_RCB_TX_PKTLINE_OFFSET) * 4;
+	dsaf_write_dev(rcb_common, reg,	coalesced_frames);
 	return 0;
 }
 
 /**
- *hns_rcb_set_coalesced_frames - set rcb coalesced frames
+ *hns_rcb_set_rx_coalesced_frames - set rcb rx coalesced frames
  *@rcb_common: rcb_common device
  *@port_idx:port id in comm
  *@coalesced_frames:tx/rx BD num for coalesced frames
@@ -572,10 +642,11 @@ int hns_rcb_set_coalesce_usecs(
  * Returns:
  * Zero for success, or an error code in case of failure
  */
-int hns_rcb_set_coalesced_frames(
+int hns_rcb_set_rx_coalesced_frames(
 	struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames)
 {
-	u32 old_waterline = hns_rcb_get_coalesced_frames(rcb_common, port_idx);
+	u32 old_waterline =
+		hns_rcb_get_rx_coalesced_frames(rcb_common, port_idx);
 
 	if (coalesced_frames == old_waterline)
 		return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
index 99b4e1ba0a94..a664ee88ab45 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
@@ -35,12 +35,23 @@ struct rcb_common_cb;
 
 #define HNS_RCB_REG_OFFSET			0x10000
 
+#define HNS_RCB_TX_FRAMES_LOW		1
+#define HNS_RCB_RX_FRAMES_LOW		1
+#define HNS_RCB_TX_FRAMES_HIGH		1023
+#define HNS_RCB_RX_FRAMES_HIGH		1023
+#define HNS_RCB_TX_USECS_LOW		1
+#define HNS_RCB_RX_USECS_LOW		1
+#define HNS_RCB_TX_USECS_HIGH		1023
+#define HNS_RCB_RX_USECS_HIGH		1023
 #define HNS_RCB_MAX_COALESCED_FRAMES		1023
 #define HNS_RCB_MIN_COALESCED_FRAMES		1
-#define HNS_RCB_DEF_COALESCED_FRAMES		50
+#define HNS_RCB_DEF_RX_COALESCED_FRAMES		50
+#define HNS_RCB_DEF_TX_COALESCED_FRAMES		1
 #define HNS_RCB_CLK_FREQ_MHZ			350
 #define HNS_RCB_MAX_COALESCED_USECS		0x3ff
-#define HNS_RCB_DEF_COALESCED_USECS		50
+#define HNS_RCB_DEF_COALESCED_USECS		30
+#define HNS_RCB_DEF_GAP_TIME_USECS		20
+#define HNS_RCB_TX_PKTLINE_OFFSET		8
 
 #define HNS_RCB_COMMON_ENDIAN			1
 
@@ -125,13 +136,17 @@ void hns_rcbv2_int_clr_hw(struct hnae_queue *q, u32 flag);
 void hns_rcb_init_hw(struct ring_pair_cb *ring);
 void hns_rcb_reset_ring_hw(struct hnae_queue *q);
 void hns_rcb_wait_fbd_clean(struct hnae_queue **qs, int q_num, u32 flag);
-u32 hns_rcb_get_coalesced_frames(
+u32 hns_rcb_get_rx_coalesced_frames(
+	struct rcb_common_cb *rcb_common, u32 port_idx);
+u32 hns_rcb_get_tx_coalesced_frames(
 	struct rcb_common_cb *rcb_common, u32 port_idx);
 u32 hns_rcb_get_coalesce_usecs(
 	struct rcb_common_cb *rcb_common, u32 port_idx);
 int hns_rcb_set_coalesce_usecs(
 	struct rcb_common_cb *rcb_common, u32 port_idx, u32 timeout);
-int hns_rcb_set_coalesced_frames(
+int hns_rcb_set_rx_coalesced_frames(
+	struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames);
+int hns_rcb_set_tx_coalesced_frames(
 	struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames);
 void hns_rcb_update_stats(struct hnae_queue *queue);
 
@@ -146,4 +161,7 @@ int hns_rcb_get_ring_regs_count(void);
 void hns_rcb_get_ring_regs(struct hnae_queue *queue, void *data);
 
 void hns_rcb_get_strings(int stringset, u8 *data, int index);
+void hns_rcb_set_rx_ring_bs(struct hnae_queue *q, u32 buf_size);
+void hns_rcb_set_tx_ring_bs(struct hnae_queue *q, u32 buf_size);
+
 #endif /* _HNS_DSAF_RCB_H */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index 8fa18fc17cd2..46a52d9bb196 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -421,7 +421,7 @@
 #define RCB_CFG_OVERTIME_REG			0x9300
 #define RCB_CFG_PKTLINE_INT_NUM_REG		0x9304
 #define RCB_CFG_OVERTIME_INT_NUM_REG		0x9308
-#define RCB_INT_GAP_TIME_REG			0x9400
+#define RCB_PORT_INT_GAPTIME_REG		0x9400
 #define RCB_PORT_CFG_OVERTIME_REG		0x9430
 
 #define RCB_RING_RX_RING_BASEADDR_L_REG		0x00000
@@ -466,6 +466,7 @@
 
 #define GMAC_DUPLEX_TYPE_REG			0x0008UL
 #define GMAC_FD_FC_TYPE_REG			0x000CUL
+#define GMAC_TX_WATER_LINE_REG			0x0010UL
 #define GMAC_FC_TX_TIMER_REG			0x001CUL
 #define GMAC_FD_FC_ADDR_LOW_REG			0x0020UL
 #define GMAC_FD_FC_ADDR_HIGH_REG		0x0024UL
@@ -912,6 +913,9 @@
 
 #define GMAC_DUPLEX_TYPE_B 0
 
+#define GMAC_TX_WATER_LINE_MASK		((1UL << 8) - 1)
+#define GMAC_TX_WATER_LINE_SHIFT	0
+
 #define GMAC_FC_TX_TIMER_S 0
 #define GMAC_FC_TX_TIMER_M 0xffff
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
index aae830a93050..37a2fc35148f 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
@@ -300,18 +300,6 @@ static void hns_xgmac_set_tx_auto_pause_frames(void *mac_drv, u16 enable)
 }
 
 /**
- *hns_xgmac_get_id - get xgmac port id
- *@mac_drv: mac driver
- *@newval:xgmac max frame length
- */
-static void hns_xgmac_get_id(void *mac_drv, u8 *mac_id)
-{
-	struct mac_driver *drv = (struct mac_driver *)mac_drv;
-
-	*mac_id = drv->mac_id;
-}
-
-/**
  *hns_xgmac_config_max_frame_length - set xgmac max frame length
  *@mac_drv: mac driver
  *@newval:xgmac max frame length
@@ -833,7 +821,6 @@ void *hns_xgmac_config(struct hns_mac_cb *mac_cb, struct mac_params *mac_param)
 	mac_drv->config_half_duplex = NULL;
 	mac_drv->set_rx_ignore_pause_frames =
 		hns_xgmac_set_rx_ignore_pause_frames;
-	mac_drv->mac_get_id = hns_xgmac_get_id;
 	mac_drv->mac_free = hns_xgmac_free;
 	mac_drv->adjust_link = NULL;
 	mac_drv->set_tx_auto_pause_frames = hns_xgmac_set_tx_auto_pause_frames;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index fca37e2c7f01..c6700b91a2df 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -512,7 +512,8 @@ static void hns_nic_reuse_page(struct sk_buff *skb, int i,
 	int last_offset;
 	bool twobufs;
 
-	twobufs = ((PAGE_SIZE < 8192) && hnae_buf_size(ring) == HNS_BUFFER_SIZE_2048);
+	twobufs = ((PAGE_SIZE < 8192) &&
+		hnae_buf_size(ring) == HNS_BUFFER_SIZE_2048);
 
 	desc = &ring->desc[ring->next_to_clean];
 	size = le16_to_cpu(desc->rx.size);
@@ -859,7 +860,7 @@ out:
 	return recv_pkts;
 }
 
-static void hns_nic_rx_fini_pro(struct hns_nic_ring_data *ring_data)
+static bool hns_nic_rx_fini_pro(struct hns_nic_ring_data *ring_data)
 {
 	struct hnae_ring *ring = ring_data->ring;
 	int num = 0;
@@ -873,22 +874,23 @@ static void hns_nic_rx_fini_pro(struct hns_nic_ring_data *ring_data)
 		ring_data->ring->q->handle->dev->ops->toggle_ring_irq(
 			ring_data->ring, 1);
 
-		napi_schedule(&ring_data->napi);
+		return false;
+	} else {
+		return true;
 	}
 }
 
-static void hns_nic_rx_fini_pro_v2(struct hns_nic_ring_data *ring_data)
+static bool hns_nic_rx_fini_pro_v2(struct hns_nic_ring_data *ring_data)
 {
 	struct hnae_ring *ring = ring_data->ring;
-	int num = 0;
+	int num;
 
 	num = readl_relaxed(ring->io_base + RCB_REG_FBDNUM);
 
-	if (num == 0)
-		ring_data->ring->q->handle->dev->ops->toggle_ring_irq(
-			ring, 0);
+	if (!num)
+		return true;
 	else
-		napi_schedule(&ring_data->napi);
+		return false;
 }
 
 static inline void hns_nic_reclaim_one_desc(struct hnae_ring *ring,
@@ -921,12 +923,13 @@ static int is_valid_clean_head(struct hnae_ring *ring, int h)
 
 /* netif_tx_lock will turn down the performance, set only when necessary */
 #ifdef CONFIG_NET_POLL_CONTROLLER
-#define NETIF_TX_LOCK(ndev) netif_tx_lock(ndev)
-#define NETIF_TX_UNLOCK(ndev) netif_tx_unlock(ndev)
+#define NETIF_TX_LOCK(ring) spin_lock(&(ring)->lock)
+#define NETIF_TX_UNLOCK(ring) spin_unlock(&(ring)->lock)
 #else
-#define NETIF_TX_LOCK(ndev)
-#define NETIF_TX_UNLOCK(ndev)
+#define NETIF_TX_LOCK(ring)
+#define NETIF_TX_UNLOCK(ring)
 #endif
+
 /* reclaim all desc in one budget
  * return error or number of desc left
  */
@@ -940,13 +943,13 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 	int head;
 	int bytes, pkts;
 
-	NETIF_TX_LOCK(ndev);
+	NETIF_TX_LOCK(ring);
 
 	head = readl_relaxed(ring->io_base + RCB_REG_HEAD);
 	rmb(); /* make sure head is ready before touch any data */
 
 	if (is_ring_empty(ring) || head == ring->next_to_clean) {
-		NETIF_TX_UNLOCK(ndev);
+		NETIF_TX_UNLOCK(ring);
 		return 0; /* no data to poll */
 	}
 
@@ -954,7 +957,7 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 		netdev_err(ndev, "wrong head (%d, %d-%d)\n", head,
 			   ring->next_to_use, ring->next_to_clean);
 		ring->stats.io_err_cnt++;
-		NETIF_TX_UNLOCK(ndev);
+		NETIF_TX_UNLOCK(ring);
 		return -EIO;
 	}
 
@@ -966,7 +969,7 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 		prefetch(&ring->desc_cb[ring->next_to_clean]);
 	}
 
-	NETIF_TX_UNLOCK(ndev);
+	NETIF_TX_UNLOCK(ring);
 
 	dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index);
 	netdev_tx_completed_queue(dev_queue, pkts, bytes);
@@ -989,7 +992,7 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 	return 0;
 }
 
-static void hns_nic_tx_fini_pro(struct hns_nic_ring_data *ring_data)
+static bool hns_nic_tx_fini_pro(struct hns_nic_ring_data *ring_data)
 {
 	struct hnae_ring *ring = ring_data->ring;
 	int head;
@@ -1002,20 +1005,21 @@ static void hns_nic_tx_fini_pro(struct hns_nic_ring_data *ring_data)
 		ring_data->ring->q->handle->dev->ops->toggle_ring_irq(
 			ring_data->ring, 1);
 
-		napi_schedule(&ring_data->napi);
+		return false;
+	} else {
+		return true;
 	}
 }
 
-static void hns_nic_tx_fini_pro_v2(struct hns_nic_ring_data *ring_data)
+static bool hns_nic_tx_fini_pro_v2(struct hns_nic_ring_data *ring_data)
 {
 	struct hnae_ring *ring = ring_data->ring;
 	int head = readl_relaxed(ring->io_base + RCB_REG_HEAD);
 
 	if (head == ring->next_to_clean)
-		ring_data->ring->q->handle->dev->ops->toggle_ring_irq(
-			ring, 0);
+		return true;
 	else
-		napi_schedule(&ring_data->napi);
+		return false;
 }
 
 static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
@@ -1026,7 +1030,7 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
 	int head;
 	int bytes, pkts;
 
-	NETIF_TX_LOCK(ndev);
+	NETIF_TX_LOCK(ring);
 
 	head = ring->next_to_use; /* ntu :soft setted ring position*/
 	bytes = 0;
@@ -1034,7 +1038,7 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
 	while (head != ring->next_to_clean)
 		hns_nic_reclaim_one_desc(ring, &bytes, &pkts);
 
-	NETIF_TX_UNLOCK(ndev);
+	NETIF_TX_UNLOCK(ring);
 
 	dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index);
 	netdev_tx_reset_queue(dev_queue);
@@ -1042,15 +1046,23 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
 
 static int hns_nic_common_poll(struct napi_struct *napi, int budget)
 {
+	int clean_complete = 0;
 	struct hns_nic_ring_data *ring_data =
 		container_of(napi, struct hns_nic_ring_data, napi);
-	int clean_complete = ring_data->poll_one(
-				ring_data, budget, ring_data->ex_process);
+	struct hnae_ring *ring = ring_data->ring;
 
-	if (clean_complete >= 0 && clean_complete < budget) {
-		napi_complete(napi);
-		ring_data->fini_process(ring_data);
-		return 0;
+try_again:
+	clean_complete += ring_data->poll_one(
+				ring_data, budget - clean_complete,
+				ring_data->ex_process);
+
+	if (clean_complete < budget) {
+		if (ring_data->fini_process(ring_data)) {
+			napi_complete(napi);
+			ring->q->handle->dev->ops->toggle_ring_irq(ring, 0);
+		} else {
+			goto try_again;
+		}
 	}
 
 	return clean_complete;
@@ -1196,54 +1208,31 @@ static void hns_nic_ring_close(struct net_device *netdev, int idx)
 	napi_disable(&priv->ring_data[idx].napi);
 }
 
-static void hns_set_irq_affinity(struct hns_nic_priv *priv)
+static int hns_nic_init_affinity_mask(int q_num, int ring_idx,
+				      struct hnae_ring *ring, cpumask_t *mask)
 {
-	struct hnae_handle *h = priv->ae_handle;
-	struct hns_nic_ring_data *rd;
-	int i;
 	int cpu;
-	cpumask_var_t mask;
-
-	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
-		return;
 
-	/*diffrent irq banlance for 16core and 32core*/
-	if (h->q_num == num_possible_cpus()) {
-		for (i = 0; i < h->q_num * 2; i++) {
-			rd = &priv->ring_data[i];
-			if (cpu_online(rd->queue_index)) {
-				cpumask_clear(mask);
-				cpu = rd->queue_index;
-				cpumask_set_cpu(cpu, mask);
-				(void)irq_set_affinity_hint(rd->ring->irq,
-							    mask);
-			}
-		}
+	/* Diffrent irq banlance between 16core and 32core.
+	 * The cpu mask set by ring index according to the ring flag
+	 * which indicate the ring is tx or rx.
+	 */
+	if (q_num == num_possible_cpus()) {
+		if (is_tx_ring(ring))
+			cpu = ring_idx;
+		else
+			cpu = ring_idx - q_num;
 	} else {
-		for (i = 0; i < h->q_num; i++) {
-			rd = &priv->ring_data[i];
-			if (cpu_online(rd->queue_index * 2)) {
-				cpumask_clear(mask);
-				cpu = rd->queue_index * 2;
-				cpumask_set_cpu(cpu, mask);
-				(void)irq_set_affinity_hint(rd->ring->irq,
-							    mask);
-			}
-		}
-
-		for (i = h->q_num; i < h->q_num * 2; i++) {
-			rd = &priv->ring_data[i];
-			if (cpu_online(rd->queue_index * 2 + 1)) {
-				cpumask_clear(mask);
-				cpu = rd->queue_index * 2 + 1;
-				cpumask_set_cpu(cpu, mask);
-				(void)irq_set_affinity_hint(rd->ring->irq,
-							    mask);
-			}
-		}
+		if (is_tx_ring(ring))
+			cpu = ring_idx * 2;
+		else
+			cpu = (ring_idx - q_num) * 2 + 1;
 	}
 
-	free_cpumask_var(mask);
+	cpumask_clear(mask);
+	cpumask_set_cpu(cpu, mask);
+
+	return cpu;
 }
 
 static int hns_nic_init_irq(struct hns_nic_priv *priv)
@@ -1252,6 +1241,7 @@ static int hns_nic_init_irq(struct hns_nic_priv *priv)
 	struct hns_nic_ring_data *rd;
 	int i;
 	int ret;
+	int cpu;
 
 	for (i = 0; i < h->q_num * 2; i++) {
 		rd = &priv->ring_data[i];
@@ -1261,7 +1251,7 @@ static int hns_nic_init_irq(struct hns_nic_priv *priv)
 
 		snprintf(rd->ring->ring_name, RCB_RING_NAME_LEN,
 			 "%s-%s%d", priv->netdev->name,
-			 (i < h->q_num ? "tx" : "rx"), rd->queue_index);
+			 (is_tx_ring(rd->ring) ? "tx" : "rx"), rd->queue_index);
 
 		rd->ring->ring_name[RCB_RING_NAME_LEN - 1] = '\0';
 
@@ -1273,12 +1263,17 @@ static int hns_nic_init_irq(struct hns_nic_priv *priv)
 			return ret;
 		}
 		disable_irq(rd->ring->irq);
+
+		cpu = hns_nic_init_affinity_mask(h->q_num, i,
+						 rd->ring, &rd->mask);
+
+		if (cpu_online(cpu))
+			irq_set_affinity_hint(rd->ring->irq,
+					      &rd->mask);
+
 		rd->ring->irq_init_flag = RCB_IRQ_INITED;
 	}
 
-	/*set cpu affinity*/
-	hns_set_irq_affinity(priv);
-
 	return 0;
 }
 
@@ -1487,32 +1482,259 @@ static netdev_tx_t hns_nic_net_xmit(struct sk_buff *skb,
 	return (netdev_tx_t)ret;
 }
 
+static void hns_nic_drop_rx_fetch(struct hns_nic_ring_data *ring_data,
+				  struct sk_buff *skb)
+{
+	dev_kfree_skb_any(skb);
+}
+
+#define HNS_LB_TX_RING	0
+static struct sk_buff *hns_assemble_skb(struct net_device *ndev)
+{
+	struct sk_buff *skb;
+	struct ethhdr *ethhdr;
+	int frame_len;
+
+	/* allocate test skb */
+	skb = alloc_skb(64, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	skb_put(skb, 64);
+	skb->dev = ndev;
+	memset(skb->data, 0xFF, skb->len);
+
+	/* must be tcp/ip package */
+	ethhdr = (struct ethhdr *)skb->data;
+	ethhdr->h_proto = htons(ETH_P_IP);
+
+	frame_len = skb->len & (~1ul);
+	memset(&skb->data[frame_len / 2], 0xAA,
+	       frame_len / 2 - 1);
+
+	skb->queue_mapping = HNS_LB_TX_RING;
+
+	return skb;
+}
+
+static int hns_enable_serdes_lb(struct net_device *ndev)
+{
+	struct hns_nic_priv *priv = netdev_priv(ndev);
+	struct hnae_handle *h = priv->ae_handle;
+	struct hnae_ae_ops *ops = h->dev->ops;
+	int speed, duplex;
+	int ret;
+
+	ret = ops->set_loopback(h, MAC_INTERNALLOOP_SERDES, 1);
+	if (ret)
+		return ret;
+
+	ret = ops->start ? ops->start(h) : 0;
+	if (ret)
+		return ret;
+
+	/* link adjust duplex*/
+	if (h->phy_if != PHY_INTERFACE_MODE_XGMII)
+		speed = 1000;
+	else
+		speed = 10000;
+	duplex = 1;
+
+	ops->adjust_link(h, speed, duplex);
+
+	/* wait h/w ready */
+	mdelay(300);
+
+	return 0;
+}
+
+static void hns_disable_serdes_lb(struct net_device *ndev)
+{
+	struct hns_nic_priv *priv = netdev_priv(ndev);
+	struct hnae_handle *h = priv->ae_handle;
+	struct hnae_ae_ops *ops = h->dev->ops;
+
+	ops->stop(h);
+	ops->set_loopback(h, MAC_INTERNALLOOP_SERDES, 0);
+}
+
+/**
+ *hns_nic_clear_all_rx_fetch - clear the chip fetched descriptions. The
+ *function as follows:
+ *    1. if one rx ring has found the page_offset is not equal 0 between head
+ *       and tail, it means that the chip fetched the wrong descs for the ring
+ *       which buffer size is 4096.
+ *    2. we set the chip serdes loopback and set rss indirection to the ring.
+ *    3. construct 64-bytes ip broadcast packages, wait the associated rx ring
+ *       recieving all packages and it will fetch new descriptions.
+ *    4. recover to the original state.
+ *
+ *@ndev: net device
+ */
+static int hns_nic_clear_all_rx_fetch(struct net_device *ndev)
+{
+	struct hns_nic_priv *priv = netdev_priv(ndev);
+	struct hnae_handle *h = priv->ae_handle;
+	struct hnae_ae_ops *ops = h->dev->ops;
+	struct hns_nic_ring_data *rd;
+	struct hnae_ring *ring;
+	struct sk_buff *skb;
+	u32 *org_indir;
+	u32 *cur_indir;
+	int indir_size;
+	int head, tail;
+	int fetch_num;
+	int i, j;
+	bool found;
+	int retry_times;
+	int ret = 0;
+
+	/* alloc indir memory */
+	indir_size = ops->get_rss_indir_size(h) * sizeof(*org_indir);
+	org_indir = kzalloc(indir_size, GFP_KERNEL);
+	if (!org_indir)
+		return -ENOMEM;
+
+	/* store the orginal indirection */
+	ops->get_rss(h, org_indir, NULL, NULL);
+
+	cur_indir = kzalloc(indir_size, GFP_KERNEL);
+	if (!cur_indir) {
+		ret = -ENOMEM;
+		goto cur_indir_alloc_err;
+	}
+
+	/* set loopback */
+	if (hns_enable_serdes_lb(ndev)) {
+		ret = -EINVAL;
+		goto enable_serdes_lb_err;
+	}
+
+	/* foreach every rx ring to clear fetch desc */
+	for (i = 0; i < h->q_num; i++) {
+		ring = &h->qs[i]->rx_ring;
+		head = readl_relaxed(ring->io_base + RCB_REG_HEAD);
+		tail = readl_relaxed(ring->io_base + RCB_REG_TAIL);
+		found = false;
+		fetch_num = ring_dist(ring, head, tail);
+
+		while (head != tail) {
+			if (ring->desc_cb[head].page_offset != 0) {
+				found = true;
+				break;
+			}
+
+			head++;
+			if (head == ring->desc_num)
+				head = 0;
+		}
+
+		if (found) {
+			for (j = 0; j < indir_size / sizeof(*org_indir); j++)
+				cur_indir[j] = i;
+			ops->set_rss(h, cur_indir, NULL, 0);
+
+			for (j = 0; j < fetch_num; j++) {
+				/* alloc one skb and init */
+				skb = hns_assemble_skb(ndev);
+				if (!skb)
+					goto out;
+				rd = &tx_ring_data(priv, skb->queue_mapping);
+				hns_nic_net_xmit_hw(ndev, skb, rd);
+
+				retry_times = 0;
+				while (retry_times++ < 10) {
+					mdelay(10);
+					/* clean rx */
+					rd = &rx_ring_data(priv, i);
+					if (rd->poll_one(rd, fetch_num,
+							 hns_nic_drop_rx_fetch))
+						break;
+				}
+
+				retry_times = 0;
+				while (retry_times++ < 10) {
+					mdelay(10);
+					/* clean tx ring 0 send package */
+					rd = &tx_ring_data(priv,
+							   HNS_LB_TX_RING);
+					if (rd->poll_one(rd, fetch_num, NULL))
+						break;
+				}
+			}
+		}
+	}
+
+out:
+	/* restore everything */
+	ops->set_rss(h, org_indir, NULL, 0);
+	hns_disable_serdes_lb(ndev);
+enable_serdes_lb_err:
+	kfree(cur_indir);
+cur_indir_alloc_err:
+	kfree(org_indir);
+
+	return ret;
+}
+
 static int hns_nic_change_mtu(struct net_device *ndev, int new_mtu)
 {
 	struct hns_nic_priv *priv = netdev_priv(ndev);
 	struct hnae_handle *h = priv->ae_handle;
+	bool if_running = netif_running(ndev);
 	int ret;
 
+	/* MTU < 68 is an error and causes problems on some kernels */
+	if (new_mtu < 68)
+		return -EINVAL;
+
+	/* MTU no change */
+	if (new_mtu == ndev->mtu)
+		return 0;
+
 	if (!h->dev->ops->set_mtu)
 		return -ENOTSUPP;
 
-	if (netif_running(ndev)) {
+	if (if_running) {
 		(void)hns_nic_net_stop(ndev);
 		msleep(100);
+	}
 
-		ret = h->dev->ops->set_mtu(h, new_mtu);
-		if (ret)
-			netdev_err(ndev, "set mtu fail, return value %d\n",
-				   ret);
+	if (priv->enet_ver != AE_VERSION_1 &&
+	    ndev->mtu <= BD_SIZE_2048_MAX_MTU &&
+	    new_mtu > BD_SIZE_2048_MAX_MTU) {
+		/* update desc */
+		hnae_reinit_all_ring_desc(h);
 
-		if (hns_nic_net_open(ndev))
-			netdev_err(ndev, "hns net open fail\n");
-	} else {
-		ret = h->dev->ops->set_mtu(h, new_mtu);
+		/* clear the package which the chip has fetched */
+		ret = hns_nic_clear_all_rx_fetch(ndev);
+
+		/* the page offset must be consist with desc */
+		hnae_reinit_all_ring_page_off(h);
+
+		if (ret) {
+			netdev_err(ndev, "clear the fetched desc fail\n");
+			goto out;
+		}
+	}
+
+	ret = h->dev->ops->set_mtu(h, new_mtu);
+	if (ret) {
+		netdev_err(ndev, "set mtu fail, return value %d\n",
+			   ret);
+		goto out;
 	}
 
-	if (!ret)
-		ndev->mtu = new_mtu;
+	/* finally, set new mtu to netdevice */
+	ndev->mtu = new_mtu;
+
+out:
+	if (if_running) {
+		if (hns_nic_net_open(ndev)) {
+			netdev_err(ndev, "hns net open fail\n");
+			ret = -EINVAL;
+		}
+	}
 
 	return ret;
 }
@@ -1791,7 +2013,7 @@ static void hns_nic_reset_subtask(struct hns_nic_priv *priv)
 static void hns_nic_service_event_complete(struct hns_nic_priv *priv)
 {
 	WARN_ON(!test_bit(NIC_STATE_SERVICE_SCHED, &priv->state));
-
+	/* make sure to commit the things */
 	smp_mb__before_atomic();
 	clear_bit(NIC_STATE_SERVICE_SCHED, &priv->state);
 }
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.h b/drivers/net/ethernet/hisilicon/hns/hns_enet.h
index 5b412de350aa..1b83232082b2 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.h
@@ -37,10 +37,11 @@ enum hns_nic_state {
 struct hns_nic_ring_data {
 	struct hnae_ring *ring;
 	struct napi_struct napi;
+	cpumask_t mask; /* affinity mask */
 	int queue_index;
 	int (*poll_one)(struct hns_nic_ring_data *, int, void *);
 	void (*ex_process)(struct hns_nic_ring_data *, struct sk_buff *);
-	void (*fini_process)(struct hns_nic_ring_data *);
+	bool (*fini_process)(struct hns_nic_ring_data *);
 };
 
 /* compatible the difference between two versions */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 3ac2183dbd21..b8fab149690f 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -146,7 +146,7 @@ static int hns_nic_get_link_ksettings(struct net_device *net_dev,
 
 	/* When there is no phy, autoneg is off. */
 	cmd->base.autoneg = false;
-	cmd->base.cmd = speed;
+	cmd->base.speed = speed;
 	cmd->base.duplex = duplex;
 
 	if (net_dev->phydev)
@@ -764,14 +764,14 @@ static int hns_get_coalesce(struct net_device *net_dev,
 	ec->use_adaptive_tx_coalesce = 1;
 
 	if ((!ops->get_coalesce_usecs) ||
-	    (!ops->get_rx_max_coalesced_frames))
+	    (!ops->get_max_coalesced_frames))
 		return -ESRCH;
 
 	ops->get_coalesce_usecs(priv->ae_handle,
 					&ec->tx_coalesce_usecs,
 					&ec->rx_coalesce_usecs);
 
-	ops->get_rx_max_coalesced_frames(
+	ops->get_max_coalesced_frames(
 		priv->ae_handle,
 		&ec->tx_max_coalesced_frames,
 		&ec->rx_max_coalesced_frames);
@@ -801,30 +801,28 @@ static int hns_set_coalesce(struct net_device *net_dev,
 {
 	struct hns_nic_priv *priv = netdev_priv(net_dev);
 	struct hnae_ae_ops *ops;
-	int ret;
+	int rc1, rc2;
 
 	ops = priv->ae_handle->dev->ops;
 
 	if (ec->tx_coalesce_usecs != ec->rx_coalesce_usecs)
 		return -EINVAL;
 
-	if (ec->rx_max_coalesced_frames != ec->tx_max_coalesced_frames)
-		return -EINVAL;
-
 	if ((!ops->set_coalesce_usecs) ||
 	    (!ops->set_coalesce_frames))
 		return -ESRCH;
 
-	ret = ops->set_coalesce_usecs(priv->ae_handle,
+	rc1 = ops->set_coalesce_usecs(priv->ae_handle,
 				      ec->rx_coalesce_usecs);
-	if (ret)
-		return ret;
 
-	ret = ops->set_coalesce_frames(
-		priv->ae_handle,
-		ec->rx_max_coalesced_frames);
+	rc2 = ops->set_coalesce_frames(priv->ae_handle,
+				       ec->tx_max_coalesced_frames,
+				       ec->rx_max_coalesced_frames);
 
-	return ret;
+	if (rc1 || rc2)
+		return -EINVAL;
+
+	return 0;
 }
 
 /**
@@ -1253,12 +1251,10 @@ hns_set_rss(struct net_device *netdev, const u32 *indir, const u8 *key,
 
 	ops = priv->ae_handle->dev->ops;
 
-	/* currently hfunc can only be Toeplitz hash */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) {
+		netdev_err(netdev, "Invalid hfunc!\n");
 		return -EOPNOTSUPP;
-	if (!indir)
-		return 0;
+	}
 
 	return ops->set_rss(priv->ae_handle, indir, key, hfunc);
 }
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index 501eb2090ca6..e5221d95afe1 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -23,17 +23,9 @@
 #include <linux/phy.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
-#include <linux/spinlock_types.h>
 
 #define MDIO_DRV_NAME "Hi-HNS_MDIO"
 #define MDIO_BUS_NAME "Hisilicon MII Bus"
-#define MDIO_DRV_VERSION "1.3.0"
-#define MDIO_COPYRIGHT "Copyright(c) 2015 Huawei Corporation."
-#define MDIO_DRV_STRING MDIO_BUS_NAME
-#define MDIO_DEFAULT_DEVICE_DESCR MDIO_BUS_NAME
-
-#define MDIO_CTL_DEV_ADDR(x)	(x & 0x1f)
-#define MDIO_CTL_PORT_ADDR(x)	((x & 0x1f) << 5)
 
 #define MDIO_TIMEOUT			1000000
 
@@ -64,9 +56,7 @@ struct hns_mdio_device {
 #define MDIO_CMD_DEVAD_S	0
 #define MDIO_CMD_PRTAD_M	0x1f
 #define MDIO_CMD_PRTAD_S	5
-#define MDIO_CMD_OP_M		0x3
 #define MDIO_CMD_OP_S		10
-#define MDIO_CMD_ST_M		0x3
 #define MDIO_CMD_ST_S		12
 #define MDIO_CMD_START_B	14
 
@@ -185,18 +175,20 @@ static int mdio_sc_cfg_reg_write(struct hns_mdio_device *mdio_dev,
 static int hns_mdio_wait_ready(struct mii_bus *bus)
 {
 	struct hns_mdio_device *mdio_dev = bus->priv;
+	u32 cmd_reg_value;
 	int i;
-	u32 cmd_reg_value = 1;
 
 	/* waitting for MDIO_COMMAND_REG 's mdio_start==0 */
 	/* after that can do read or write*/
-	for (i = 0; cmd_reg_value; i++) {
+	for (i = 0; i < MDIO_TIMEOUT; i++) {
 		cmd_reg_value = MDIO_GET_REG_BIT(mdio_dev,
 						 MDIO_COMMAND_REG,
 						 MDIO_CMD_START_B);
-		if (i == MDIO_TIMEOUT)
-			return -ETIMEDOUT;
+		if (!cmd_reg_value)
+			break;
 	}
+	if ((i == MDIO_TIMEOUT) && cmd_reg_value)
+		return -ETIMEDOUT;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/ibm/emac/Makefile b/drivers/net/ethernet/ibm/emac/Makefile
index eba21835d90d..98768ba0955a 100644
--- a/drivers/net/ethernet/ibm/emac/Makefile
+++ b/drivers/net/ethernet/ibm/emac/Makefile
@@ -8,4 +8,3 @@ ibm_emac-y := mal.o core.o phy.o
 ibm_emac-$(CONFIG_IBM_EMAC_ZMII) += zmii.o
 ibm_emac-$(CONFIG_IBM_EMAC_RGMII) += rgmii.o
 ibm_emac-$(CONFIG_IBM_EMAC_TAH) += tah.o
-ibm_emac-$(CONFIG_IBM_EMAC_DEBUG) += debug.o
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index c44036d5761a..0f9cd92fdc5e 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -3173,8 +3173,6 @@ static int emac_probe(struct platform_device *ofdev)
 		printk("%s: found %s PHY (0x%02x)\n", ndev->name,
 		       dev->phy.def->name, dev->phy.address);
 
-	emac_dbg_register(dev);
-
 	/* Life is good */
 	return 0;
 
@@ -3243,7 +3241,6 @@ static int emac_remove(struct platform_device *ofdev)
 	mal_unregister_commac(dev->mal, &dev->commac);
 	emac_put_deps(dev);
 
-	emac_dbg_unregister(dev);
 	iounmap(dev->emacp);
 
 	if (dev->wol_irq)
@@ -3326,9 +3323,6 @@ static int __init emac_init(void)
 
 	printk(KERN_INFO DRV_DESC ", version " DRV_VERSION "\n");
 
-	/* Init debug stuff */
-	emac_init_debug();
-
 	/* Build EMAC boot list */
 	emac_make_bootlist();
 
@@ -3373,7 +3367,6 @@ static void __exit emac_exit(void)
 	rgmii_exit();
 	zmii_exit();
 	mal_exit();
-	emac_fini_debug();
 
 	/* Destroy EMAC boot list */
 	for (i = 0; i < EMAC_BOOT_LIST_SIZE; i++)
diff --git a/drivers/net/ethernet/ibm/emac/debug.c b/drivers/net/ethernet/ibm/emac/debug.c
deleted file mode 100644
index a559f326bf63..000000000000
--- a/drivers/net/ethernet/ibm/emac/debug.c
+++ /dev/null
@@ -1,270 +0,0 @@
-/*
- * drivers/net/ethernet/ibm/emac/debug.c
- *
- * Driver for PowerPC 4xx on-chip ethernet controller, debug print routines.
- *
- * Copyright 2007 Benjamin Herrenschmidt, IBM Corp.
- *                <benh@kernel.crashing.org>
- *
- * Based on the arch/ppc version of the driver:
- *
- * Copyright (c) 2004, 2005 Zultys Technologies
- * Eugene Surovegin <eugene.surovegin@zultys.com> or <ebs@ebshome.net>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- */
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/netdevice.h>
-#include <linux/sysrq.h>
-#include <asm/io.h>
-
-#include "core.h"
-
-static DEFINE_SPINLOCK(emac_dbg_lock);
-
-static void emac_desc_dump(struct emac_instance *p)
-{
-	int i;
-	printk("** EMAC %s TX BDs **\n"
-	       " tx_cnt = %d tx_slot = %d ack_slot = %d\n",
-	       p->ofdev->dev.of_node->full_name,
-	       p->tx_cnt, p->tx_slot, p->ack_slot);
-	for (i = 0; i < NUM_TX_BUFF / 2; ++i)
-		printk
-		    ("bd[%2d] 0x%08x %c 0x%04x %4u - bd[%2d] 0x%08x %c 0x%04x %4u\n",
-		     i, p->tx_desc[i].data_ptr, p->tx_skb[i] ? 'V' : ' ',
-		     p->tx_desc[i].ctrl, p->tx_desc[i].data_len,
-		     NUM_TX_BUFF / 2 + i,
-		     p->tx_desc[NUM_TX_BUFF / 2 + i].data_ptr,
-		     p->tx_skb[NUM_TX_BUFF / 2 + i] ? 'V' : ' ',
-		     p->tx_desc[NUM_TX_BUFF / 2 + i].ctrl,
-		     p->tx_desc[NUM_TX_BUFF / 2 + i].data_len);
-
-	printk("** EMAC %s RX BDs **\n"
-	       " rx_slot = %d flags = 0x%lx rx_skb_size = %d rx_sync_size = %d\n"
-	       " rx_sg_skb = 0x%p\n",
-	       p->ofdev->dev.of_node->full_name,
-	       p->rx_slot, p->commac.flags, p->rx_skb_size,
-	       p->rx_sync_size, p->rx_sg_skb);
-	for (i = 0; i < NUM_RX_BUFF / 2; ++i)
-		printk
-		    ("bd[%2d] 0x%08x %c 0x%04x %4u - bd[%2d] 0x%08x %c 0x%04x %4u\n",
-		     i, p->rx_desc[i].data_ptr, p->rx_skb[i] ? 'V' : ' ',
-		     p->rx_desc[i].ctrl, p->rx_desc[i].data_len,
-		     NUM_RX_BUFF / 2 + i,
-		     p->rx_desc[NUM_RX_BUFF / 2 + i].data_ptr,
-		     p->rx_skb[NUM_RX_BUFF / 2 + i] ? 'V' : ' ',
-		     p->rx_desc[NUM_RX_BUFF / 2 + i].ctrl,
-		     p->rx_desc[NUM_RX_BUFF / 2 + i].data_len);
-}
-
-static void emac_mac_dump(struct emac_instance *dev)
-{
-	struct emac_regs __iomem *p = dev->emacp;
-	const int xaht_regs = EMAC_XAHT_REGS(dev);
-	u32 *gaht_base = emac_gaht_base(dev);
-	u32 *iaht_base = emac_iaht_base(dev);
-	int emac4sync = emac_has_feature(dev, EMAC_FTR_EMAC4SYNC);
-	int n;
-
-	printk("** EMAC %s registers **\n"
-	       "MR0 = 0x%08x MR1 = 0x%08x TMR0 = 0x%08x TMR1 = 0x%08x\n"
-	       "RMR = 0x%08x ISR = 0x%08x ISER = 0x%08x\n"
-	       "IAR = %04x%08x VTPID = 0x%04x VTCI = 0x%04x\n",
-	       dev->ofdev->dev.of_node->full_name,
-	       in_be32(&p->mr0), in_be32(&p->mr1),
-	       in_be32(&p->tmr0), in_be32(&p->tmr1),
-	       in_be32(&p->rmr), in_be32(&p->isr), in_be32(&p->iser),
-	       in_be32(&p->iahr), in_be32(&p->ialr), in_be32(&p->vtpid),
-	       in_be32(&p->vtci)
-	       );
-
-	if (emac4sync)
-		printk("MAR = %04x%08x MMAR = %04x%08x\n",
-		       in_be32(&p->u0.emac4sync.mahr),
-		       in_be32(&p->u0.emac4sync.malr),
-		       in_be32(&p->u0.emac4sync.mmahr),
-		       in_be32(&p->u0.emac4sync.mmalr)
-		       );
-
-	for (n = 0; n < xaht_regs; n++)
-		printk("IAHT%02d = 0x%08x\n", n + 1, in_be32(iaht_base + n));
-
-	for (n = 0; n < xaht_regs; n++)
-		printk("GAHT%02d = 0x%08x\n", n + 1, in_be32(gaht_base + n));
-
-	printk("LSA = %04x%08x IPGVR = 0x%04x\n"
-	       "STACR = 0x%08x TRTR = 0x%08x RWMR = 0x%08x\n"
-	       "OCTX = 0x%08x OCRX = 0x%08x\n",
-	       in_be32(&p->lsah), in_be32(&p->lsal), in_be32(&p->ipgvr),
-	       in_be32(&p->stacr), in_be32(&p->trtr), in_be32(&p->rwmr),
-	       in_be32(&p->octx), in_be32(&p->ocrx)
-	       );
-
-	if (!emac4sync) {
-		printk("IPCR = 0x%08x\n",
-		       in_be32(&p->u1.emac4.ipcr)
-		       );
-	} else {
-		printk("REVID = 0x%08x TPC = 0x%08x\n",
-		       in_be32(&p->u1.emac4sync.revid),
-		       in_be32(&p->u1.emac4sync.tpc)
-		       );
-	}
-
-	emac_desc_dump(dev);
-}
-
-static void emac_mal_dump(struct mal_instance *mal)
-{
-	int i;
-
-	printk("** MAL %s Registers **\n"
-	       "CFG = 0x%08x ESR = 0x%08x IER = 0x%08x\n"
-	       "TX|CASR = 0x%08x CARR = 0x%08x EOBISR = 0x%08x DEIR = 0x%08x\n"
-	       "RX|CASR = 0x%08x CARR = 0x%08x EOBISR = 0x%08x DEIR = 0x%08x\n",
-	       mal->ofdev->dev.of_node->full_name,
-	       get_mal_dcrn(mal, MAL_CFG), get_mal_dcrn(mal, MAL_ESR),
-	       get_mal_dcrn(mal, MAL_IER),
-	       get_mal_dcrn(mal, MAL_TXCASR), get_mal_dcrn(mal, MAL_TXCARR),
-	       get_mal_dcrn(mal, MAL_TXEOBISR), get_mal_dcrn(mal, MAL_TXDEIR),
-	       get_mal_dcrn(mal, MAL_RXCASR), get_mal_dcrn(mal, MAL_RXCARR),
-	       get_mal_dcrn(mal, MAL_RXEOBISR), get_mal_dcrn(mal, MAL_RXDEIR)
-	    );
-
-	printk("TX|");
-	for (i = 0; i < mal->num_tx_chans; ++i) {
-		if (i && !(i % 4))
-			printk("\n   ");
-		printk("CTP%d = 0x%08x ", i, get_mal_dcrn(mal, MAL_TXCTPR(i)));
-	}
-	printk("\nRX|");
-	for (i = 0; i < mal->num_rx_chans; ++i) {
-		if (i && !(i % 4))
-			printk("\n   ");
-		printk("CTP%d = 0x%08x ", i, get_mal_dcrn(mal, MAL_RXCTPR(i)));
-	}
-	printk("\n   ");
-	for (i = 0; i < mal->num_rx_chans; ++i) {
-		u32 r = get_mal_dcrn(mal, MAL_RCBS(i));
-		if (i && !(i % 3))
-			printk("\n   ");
-		printk("RCBS%d = 0x%08x (%d) ", i, r, r * 16);
-	}
-	printk("\n");
-}
-
-static struct emac_instance *__emacs[4];
-static struct mal_instance *__mals[1];
-
-void emac_dbg_register(struct emac_instance *dev)
-{
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&emac_dbg_lock, flags);
-	for (i = 0; i < ARRAY_SIZE(__emacs); i++)
-		if (__emacs[i] == NULL) {
-			__emacs[i] = dev;
-			break;
-		}
-	spin_unlock_irqrestore(&emac_dbg_lock, flags);
-}
-
-void emac_dbg_unregister(struct emac_instance *dev)
-{
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&emac_dbg_lock, flags);
-	for (i = 0; i < ARRAY_SIZE(__emacs); i++)
-		if (__emacs[i] == dev) {
-			__emacs[i] = NULL;
-			break;
-		}
-	spin_unlock_irqrestore(&emac_dbg_lock, flags);
-}
-
-void mal_dbg_register(struct mal_instance *mal)
-{
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&emac_dbg_lock, flags);
-	for (i = 0; i < ARRAY_SIZE(__mals); i++)
-		if (__mals[i] == NULL) {
-			__mals[i] = mal;
-			break;
-		}
-	spin_unlock_irqrestore(&emac_dbg_lock, flags);
-}
-
-void mal_dbg_unregister(struct mal_instance *mal)
-{
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&emac_dbg_lock, flags);
-	for (i = 0; i < ARRAY_SIZE(__mals); i++)
-		if (__mals[i] == mal) {
-			__mals[i] = NULL;
-			break;
-		}
-	spin_unlock_irqrestore(&emac_dbg_lock, flags);
-}
-
-void emac_dbg_dump_all(void)
-{
-	unsigned int i;
-	unsigned long flags;
-
-	spin_lock_irqsave(&emac_dbg_lock, flags);
-
-	for (i = 0; i < ARRAY_SIZE(__mals); ++i)
-		if (__mals[i])
-			emac_mal_dump(__mals[i]);
-
-	for (i = 0; i < ARRAY_SIZE(__emacs); ++i)
-		if (__emacs[i])
-			emac_mac_dump(__emacs[i]);
-
-	spin_unlock_irqrestore(&emac_dbg_lock, flags);
-}
-
-#if defined(CONFIG_MAGIC_SYSRQ)
-static void emac_sysrq_handler(int key)
-{
-	emac_dbg_dump_all();
-}
-
-static struct sysrq_key_op emac_sysrq_op = {
-	.handler = emac_sysrq_handler,
-	.help_msg = "emac(c)",
-	.action_msg = "Show EMAC(s) status",
-};
-
-int __init emac_init_debug(void)
-{
-	return register_sysrq_key('c', &emac_sysrq_op);
-}
-
-void __exit emac_fini_debug(void)
-{
-	unregister_sysrq_key('c', &emac_sysrq_op);
-}
-
-#else
-int __init emac_init_debug(void)
-{
-	return 0;
-}
-void __exit emac_fini_debug(void)
-{
-}
-#endif				/* CONFIG_MAGIC_SYSRQ */
diff --git a/drivers/net/ethernet/ibm/emac/debug.h b/drivers/net/ethernet/ibm/emac/debug.h
index 9c45efe4c8fe..5bdfc174a07e 100644
--- a/drivers/net/ethernet/ibm/emac/debug.h
+++ b/drivers/net/ethernet/ibm/emac/debug.h
@@ -25,32 +25,9 @@
 #include "core.h"
 
 #if defined(CONFIG_IBM_EMAC_DEBUG)
-
-struct emac_instance;
-struct mal_instance;
-
-void emac_dbg_register(struct emac_instance *dev);
-void emac_dbg_unregister(struct emac_instance *dev);
-void mal_dbg_register(struct mal_instance *mal);
-void mal_dbg_unregister(struct mal_instance *mal);
-int emac_init_debug(void) __init;
-void emac_fini_debug(void) __exit;
-void emac_dbg_dump_all(void);
-
 # define DBG_LEVEL		1
-
 #else
-
-# define emac_dbg_register(x)	do { } while(0)
-# define emac_dbg_unregister(x)	do { } while(0)
-# define mal_dbg_register(x)	do { } while(0)
-# define mal_dbg_unregister(x)	do { } while(0)
-# define emac_init_debug()	do { } while(0)
-# define emac_fini_debug()	do { } while(0)
-# define emac_dbg_dump_all()	do { } while(0)
-
 # define DBG_LEVEL		0
-
 #endif
 
 #define EMAC_DBG(d, name, fmt, arg...) \
diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c
index cd3227b088b7..91b1a558f37d 100644
--- a/drivers/net/ethernet/ibm/emac/mal.c
+++ b/drivers/net/ethernet/ibm/emac/mal.c
@@ -695,8 +695,6 @@ static int mal_probe(struct platform_device *ofdev)
 	wmb();
 	platform_set_drvdata(ofdev, mal);
 
-	mal_dbg_register(mal);
-
 	return 0;
 
  fail6:
@@ -740,8 +738,6 @@ static int mal_remove(struct platform_device *ofdev)
 
 	mal_reset(mal);
 
-	mal_dbg_unregister(mal);
-
 	dma_free_coherent(&ofdev->dev,
 			  sizeof(struct mal_descriptor) *
 			  (NUM_TX_BUFF * mal->num_tx_chans +
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index 7acda04d034e..ed8780cca982 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -146,7 +146,6 @@ struct ibmveth_adapter {
     struct vio_dev *vdev;
     struct net_device *netdev;
     struct napi_struct napi;
-    struct net_device_stats stats;
     unsigned int mcastFilterSize;
     void * buffer_list_addr;
     void * filter_list_addr;
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index b23d6545f835..7ba43cfadf3a 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -65,7 +65,6 @@
 #include <linux/irq.h>
 #include <linux/kthread.h>
 #include <linux/seq_file.h>
-#include <linux/debugfs.h>
 #include <linux/interrupt.h>
 #include <net/net_namespace.h>
 #include <asm/hvcall.h>
@@ -89,7 +88,6 @@ MODULE_VERSION(IBMVNIC_DRIVER_VERSION);
 static int ibmvnic_version = IBMVNIC_INITIAL_VERSION;
 static int ibmvnic_remove(struct vio_dev *);
 static void release_sub_crqs(struct ibmvnic_adapter *);
-static void release_sub_crqs_no_irqs(struct ibmvnic_adapter *);
 static int ibmvnic_reset_crq(struct ibmvnic_adapter *);
 static int ibmvnic_send_crq_init(struct ibmvnic_adapter *);
 static int ibmvnic_reenable_crq_queue(struct ibmvnic_adapter *);
@@ -110,6 +108,11 @@ static int ibmvnic_poll(struct napi_struct *napi, int data);
 static void send_map_query(struct ibmvnic_adapter *adapter);
 static void send_request_map(struct ibmvnic_adapter *, dma_addr_t, __be32, u8);
 static void send_request_unmap(struct ibmvnic_adapter *, u8);
+static void send_login(struct ibmvnic_adapter *adapter);
+static void send_cap_queries(struct ibmvnic_adapter *adapter);
+static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter);
+static int ibmvnic_init(struct ibmvnic_adapter *);
+static void release_crq_queue(struct ibmvnic_adapter *);
 
 struct ibmvnic_stat {
 	char name[ETH_GSTRING_LEN];
@@ -159,21 +162,6 @@ static long h_reg_sub_crq(unsigned long unit_address, unsigned long token,
 	return rc;
 }
 
-/* net_device_ops functions */
-
-static void init_rx_pool(struct ibmvnic_adapter *adapter,
-			 struct ibmvnic_rx_pool *rx_pool, int num, int index,
-			 int buff_size, int active)
-{
-	netdev_dbg(adapter->netdev,
-		   "Initializing rx_pool %d, %d buffs, %d bytes each\n",
-		   index, num, buff_size);
-	rx_pool->size = num;
-	rx_pool->index = index;
-	rx_pool->buff_size = buff_size;
-	rx_pool->active = active;
-}
-
 static int alloc_long_term_buff(struct ibmvnic_adapter *adapter,
 				struct ibmvnic_long_term_buff *ltb, int size)
 {
@@ -202,47 +190,14 @@ static void free_long_term_buff(struct ibmvnic_adapter *adapter,
 {
 	struct device *dev = &adapter->vdev->dev;
 
+	if (!ltb->buff)
+		return;
+
 	dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr);
 	if (!adapter->failover)
 		send_request_unmap(adapter, ltb->map_id);
 }
 
-static int alloc_rx_pool(struct ibmvnic_adapter *adapter,
-			 struct ibmvnic_rx_pool *pool)
-{
-	struct device *dev = &adapter->vdev->dev;
-	int i;
-
-	pool->free_map = kcalloc(pool->size, sizeof(int), GFP_KERNEL);
-	if (!pool->free_map)
-		return -ENOMEM;
-
-	pool->rx_buff = kcalloc(pool->size, sizeof(struct ibmvnic_rx_buff),
-				GFP_KERNEL);
-
-	if (!pool->rx_buff) {
-		dev_err(dev, "Couldn't alloc rx buffers\n");
-		kfree(pool->free_map);
-		return -ENOMEM;
-	}
-
-	if (alloc_long_term_buff(adapter, &pool->long_term_buff,
-				 pool->size * pool->buff_size)) {
-		kfree(pool->free_map);
-		kfree(pool->rx_buff);
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < pool->size; ++i)
-		pool->free_map[i] = i;
-
-	atomic_set(&pool->available, 0);
-	pool->next_alloc = 0;
-	pool->next_free = 0;
-
-	return 0;
-}
-
 static void replenish_rx_pool(struct ibmvnic_adapter *adapter,
 			      struct ibmvnic_rx_pool *pool)
 {
@@ -347,93 +302,195 @@ static void replenish_pools(struct ibmvnic_adapter *adapter)
 	}
 }
 
-static void free_rx_pool(struct ibmvnic_adapter *adapter,
-			 struct ibmvnic_rx_pool *pool)
+static void release_stats_token(struct ibmvnic_adapter *adapter)
 {
-	int i;
+	struct device *dev = &adapter->vdev->dev;
 
-	kfree(pool->free_map);
-	pool->free_map = NULL;
+	if (!adapter->stats_token)
+		return;
+
+	dma_unmap_single(dev, adapter->stats_token,
+			 sizeof(struct ibmvnic_statistics),
+			 DMA_FROM_DEVICE);
+	adapter->stats_token = 0;
+}
 
-	if (!pool->rx_buff)
+static int init_stats_token(struct ibmvnic_adapter *adapter)
+{
+	struct device *dev = &adapter->vdev->dev;
+	dma_addr_t stok;
+
+	stok = dma_map_single(dev, &adapter->stats,
+			      sizeof(struct ibmvnic_statistics),
+			      DMA_FROM_DEVICE);
+	if (dma_mapping_error(dev, stok)) {
+		dev_err(dev, "Couldn't map stats buffer\n");
+		return -1;
+	}
+
+	adapter->stats_token = stok;
+	return 0;
+}
+
+static void release_rx_pools(struct ibmvnic_adapter *adapter)
+{
+	struct ibmvnic_rx_pool *rx_pool;
+	int rx_scrqs;
+	int i, j;
+
+	if (!adapter->rx_pool)
 		return;
 
-	for (i = 0; i < pool->size; i++) {
-		if (pool->rx_buff[i].skb) {
-			dev_kfree_skb_any(pool->rx_buff[i].skb);
-			pool->rx_buff[i].skb = NULL;
+	rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
+	for (i = 0; i < rx_scrqs; i++) {
+		rx_pool = &adapter->rx_pool[i];
+
+		kfree(rx_pool->free_map);
+		free_long_term_buff(adapter, &rx_pool->long_term_buff);
+
+		if (!rx_pool->rx_buff)
+		continue;
+
+		for (j = 0; j < rx_pool->size; j++) {
+			if (rx_pool->rx_buff[j].skb) {
+				dev_kfree_skb_any(rx_pool->rx_buff[i].skb);
+				rx_pool->rx_buff[i].skb = NULL;
+			}
 		}
+
+		kfree(rx_pool->rx_buff);
 	}
-	kfree(pool->rx_buff);
-	pool->rx_buff = NULL;
+
+	kfree(adapter->rx_pool);
+	adapter->rx_pool = NULL;
 }
 
-static int ibmvnic_open(struct net_device *netdev)
+static int init_rx_pools(struct net_device *netdev)
 {
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
 	struct device *dev = &adapter->vdev->dev;
-	struct ibmvnic_tx_pool *tx_pool;
-	union ibmvnic_crq crq;
+	struct ibmvnic_rx_pool *rx_pool;
 	int rxadd_subcrqs;
 	u64 *size_array;
-	int tx_subcrqs;
 	int i, j;
 
 	rxadd_subcrqs =
-	    be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
-	tx_subcrqs =
-	    be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
+		be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
 	size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
-				  be32_to_cpu(adapter->login_rsp_buf->
-					      off_rxadd_buff_size));
-	adapter->map_id = 1;
-	adapter->napi = kcalloc(adapter->req_rx_queues,
-				sizeof(struct napi_struct), GFP_KERNEL);
-	if (!adapter->napi)
-		goto alloc_napi_failed;
-	for (i = 0; i < adapter->req_rx_queues; i++) {
-		netif_napi_add(netdev, &adapter->napi[i], ibmvnic_poll,
-			       NAPI_POLL_WEIGHT);
-		napi_enable(&adapter->napi[i]);
+		be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size));
+
+	adapter->rx_pool = kcalloc(rxadd_subcrqs,
+				   sizeof(struct ibmvnic_rx_pool),
+				   GFP_KERNEL);
+	if (!adapter->rx_pool) {
+		dev_err(dev, "Failed to allocate rx pools\n");
+		return -1;
 	}
-	adapter->rx_pool =
-	    kcalloc(rxadd_subcrqs, sizeof(struct ibmvnic_rx_pool), GFP_KERNEL);
 
-	if (!adapter->rx_pool)
-		goto rx_pool_arr_alloc_failed;
-	send_map_query(adapter);
 	for (i = 0; i < rxadd_subcrqs; i++) {
-		init_rx_pool(adapter, &adapter->rx_pool[i],
-			     adapter->req_rx_add_entries_per_subcrq, i,
-			     be64_to_cpu(size_array[i]), 1);
-		if (alloc_rx_pool(adapter, &adapter->rx_pool[i])) {
-			dev_err(dev, "Couldn't alloc rx pool\n");
-			goto rx_pool_alloc_failed;
+		rx_pool = &adapter->rx_pool[i];
+
+		netdev_dbg(adapter->netdev,
+			   "Initializing rx_pool %d, %lld buffs, %lld bytes each\n",
+			   i, adapter->req_rx_add_entries_per_subcrq,
+			   be64_to_cpu(size_array[i]));
+
+		rx_pool->size = adapter->req_rx_add_entries_per_subcrq;
+		rx_pool->index = i;
+		rx_pool->buff_size = be64_to_cpu(size_array[i]);
+		rx_pool->active = 1;
+
+		rx_pool->free_map = kcalloc(rx_pool->size, sizeof(int),
+					    GFP_KERNEL);
+		if (!rx_pool->free_map) {
+			release_rx_pools(adapter);
+			return -1;
+		}
+
+		rx_pool->rx_buff = kcalloc(rx_pool->size,
+					   sizeof(struct ibmvnic_rx_buff),
+					   GFP_KERNEL);
+		if (!rx_pool->rx_buff) {
+			dev_err(dev, "Couldn't alloc rx buffers\n");
+			release_rx_pools(adapter);
+			return -1;
+		}
+
+		if (alloc_long_term_buff(adapter, &rx_pool->long_term_buff,
+					 rx_pool->size * rx_pool->buff_size)) {
+			release_rx_pools(adapter);
+			return -1;
 		}
+
+		for (j = 0; j < rx_pool->size; ++j)
+			rx_pool->free_map[j] = j;
+
+		atomic_set(&rx_pool->available, 0);
+		rx_pool->next_alloc = 0;
+		rx_pool->next_free = 0;
 	}
-	adapter->tx_pool =
-	    kcalloc(tx_subcrqs, sizeof(struct ibmvnic_tx_pool), GFP_KERNEL);
+
+	return 0;
+}
+
+static void release_tx_pools(struct ibmvnic_adapter *adapter)
+{
+	struct ibmvnic_tx_pool *tx_pool;
+	int i, tx_scrqs;
 
 	if (!adapter->tx_pool)
-		goto tx_pool_arr_alloc_failed;
+		return;
+
+	tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
+	for (i = 0; i < tx_scrqs; i++) {
+		tx_pool = &adapter->tx_pool[i];
+		kfree(tx_pool->tx_buff);
+		free_long_term_buff(adapter, &tx_pool->long_term_buff);
+		kfree(tx_pool->free_map);
+	}
+
+	kfree(adapter->tx_pool);
+	adapter->tx_pool = NULL;
+}
+
+static int init_tx_pools(struct net_device *netdev)
+{
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+	struct device *dev = &adapter->vdev->dev;
+	struct ibmvnic_tx_pool *tx_pool;
+	int tx_subcrqs;
+	int i, j;
+
+	tx_subcrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
+	adapter->tx_pool = kcalloc(tx_subcrqs,
+				   sizeof(struct ibmvnic_tx_pool), GFP_KERNEL);
+	if (!adapter->tx_pool)
+		return -1;
+
 	for (i = 0; i < tx_subcrqs; i++) {
 		tx_pool = &adapter->tx_pool[i];
-		tx_pool->tx_buff =
-		    kcalloc(adapter->req_tx_entries_per_subcrq,
-			    sizeof(struct ibmvnic_tx_buff), GFP_KERNEL);
-		if (!tx_pool->tx_buff)
-			goto tx_pool_alloc_failed;
+		tx_pool->tx_buff = kcalloc(adapter->req_tx_entries_per_subcrq,
+					   sizeof(struct ibmvnic_tx_buff),
+					   GFP_KERNEL);
+		if (!tx_pool->tx_buff) {
+			dev_err(dev, "tx pool buffer allocation failed\n");
+			release_tx_pools(adapter);
+			return -1;
+		}
 
 		if (alloc_long_term_buff(adapter, &tx_pool->long_term_buff,
 					 adapter->req_tx_entries_per_subcrq *
-					 adapter->req_mtu))
-			goto tx_ltb_alloc_failed;
+					 adapter->req_mtu)) {
+			release_tx_pools(adapter);
+			return -1;
+		}
 
-		tx_pool->free_map =
-		    kcalloc(adapter->req_tx_entries_per_subcrq,
-			    sizeof(int), GFP_KERNEL);
-		if (!tx_pool->free_map)
-			goto tx_fm_alloc_failed;
+		tx_pool->free_map = kcalloc(adapter->req_tx_entries_per_subcrq,
+					    sizeof(int), GFP_KERNEL);
+		if (!tx_pool->free_map) {
+			release_tx_pools(adapter);
+			return -1;
+		}
 
 		for (j = 0; j < adapter->req_tx_entries_per_subcrq; j++)
 			tx_pool->free_map[j] = j;
@@ -441,20 +498,153 @@ static int ibmvnic_open(struct net_device *netdev)
 		tx_pool->consumer_index = 0;
 		tx_pool->producer_index = 0;
 	}
-	adapter->bounce_buffer_size =
-	    (netdev->mtu + ETH_HLEN - 1) / PAGE_SIZE + 1;
-	adapter->bounce_buffer = kmalloc(adapter->bounce_buffer_size,
-					 GFP_KERNEL);
+
+	return 0;
+}
+
+static void release_bounce_buffer(struct ibmvnic_adapter *adapter)
+{
+	struct device *dev = &adapter->vdev->dev;
+
 	if (!adapter->bounce_buffer)
-		goto bounce_alloc_failed;
+		return;
 
-	adapter->bounce_buffer_dma = dma_map_single(dev, adapter->bounce_buffer,
-						    adapter->bounce_buffer_size,
-						    DMA_TO_DEVICE);
-	if (dma_mapping_error(dev, adapter->bounce_buffer_dma)) {
-		dev_err(dev, "Couldn't map tx bounce buffer\n");
-		goto bounce_map_failed;
+	if (!dma_mapping_error(dev, adapter->bounce_buffer_dma)) {
+		dma_unmap_single(dev, adapter->bounce_buffer_dma,
+				 adapter->bounce_buffer_size,
+				 DMA_BIDIRECTIONAL);
+		adapter->bounce_buffer_dma = DMA_ERROR_CODE;
+	}
+
+	kfree(adapter->bounce_buffer);
+	adapter->bounce_buffer = NULL;
+}
+
+static int init_bounce_buffer(struct net_device *netdev)
+{
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+	struct device *dev = &adapter->vdev->dev;
+	char *buf;
+	int buf_sz;
+	dma_addr_t map_addr;
+
+	buf_sz = (netdev->mtu + ETH_HLEN - 1) / PAGE_SIZE + 1;
+	buf = kmalloc(adapter->bounce_buffer_size, GFP_KERNEL);
+	if (!buf)
+		return -1;
+
+	map_addr = dma_map_single(dev, buf, buf_sz, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, map_addr)) {
+		dev_err(dev, "Couldn't map bounce buffer\n");
+		kfree(buf);
+		return -1;
+	}
+
+	adapter->bounce_buffer = buf;
+	adapter->bounce_buffer_size = buf_sz;
+	adapter->bounce_buffer_dma = map_addr;
+	return 0;
+}
+
+static int ibmvnic_login(struct net_device *netdev)
+{
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+	unsigned long timeout = msecs_to_jiffies(30000);
+	struct device *dev = &adapter->vdev->dev;
+
+	do {
+		if (adapter->renegotiate) {
+			adapter->renegotiate = false;
+			release_sub_crqs(adapter);
+
+			reinit_completion(&adapter->init_done);
+			send_cap_queries(adapter);
+			if (!wait_for_completion_timeout(&adapter->init_done,
+							 timeout)) {
+				dev_err(dev, "Capabilities query timeout\n");
+				return -1;
+			}
+		}
+
+		reinit_completion(&adapter->init_done);
+		send_login(adapter);
+		if (!wait_for_completion_timeout(&adapter->init_done,
+						 timeout)) {
+			dev_err(dev, "Login timeout\n");
+			return -1;
+		}
+	} while (adapter->renegotiate);
+
+	return 0;
+}
+
+static void release_resources(struct ibmvnic_adapter *adapter)
+{
+	release_bounce_buffer(adapter);
+	release_tx_pools(adapter);
+	release_rx_pools(adapter);
+
+	release_sub_crqs(adapter);
+	release_crq_queue(adapter);
+
+	release_stats_token(adapter);
+}
+
+static int ibmvnic_open(struct net_device *netdev)
+{
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+	struct device *dev = &adapter->vdev->dev;
+	union ibmvnic_crq crq;
+	int rc = 0;
+	int i;
+
+	if (adapter->is_closed) {
+		rc = ibmvnic_init(adapter);
+		if (rc)
+			return rc;
 	}
+
+	rc = ibmvnic_login(netdev);
+	if (rc)
+		return rc;
+
+	rc = netif_set_real_num_tx_queues(netdev, adapter->req_tx_queues);
+	if (rc) {
+		dev_err(dev, "failed to set the number of tx queues\n");
+		return -1;
+	}
+
+	rc = init_sub_crq_irqs(adapter);
+	if (rc) {
+		dev_err(dev, "failed to initialize sub crq irqs\n");
+		return -1;
+	}
+
+	adapter->map_id = 1;
+	adapter->napi = kcalloc(adapter->req_rx_queues,
+				sizeof(struct napi_struct), GFP_KERNEL);
+	if (!adapter->napi)
+		goto ibmvnic_open_fail;
+	for (i = 0; i < adapter->req_rx_queues; i++) {
+		netif_napi_add(netdev, &adapter->napi[i], ibmvnic_poll,
+			       NAPI_POLL_WEIGHT);
+		napi_enable(&adapter->napi[i]);
+	}
+
+	send_map_query(adapter);
+
+	rc = init_rx_pools(netdev);
+	if (rc)
+		goto ibmvnic_open_fail;
+
+	rc = init_tx_pools(netdev);
+	if (rc)
+		goto ibmvnic_open_fail;
+
+	rc = init_bounce_buffer(netdev);
+	if (rc)
+		goto ibmvnic_open_fail;
+
 	replenish_pools(adapter);
 
 	/* We're ready to receive frames, enable the sub-crq interrupts and
@@ -473,48 +663,20 @@ static int ibmvnic_open(struct net_device *netdev)
 	ibmvnic_send_crq(adapter, &crq);
 
 	netif_tx_start_all_queues(netdev);
+	adapter->is_closed = false;
 
 	return 0;
 
-bounce_map_failed:
-	kfree(adapter->bounce_buffer);
-bounce_alloc_failed:
-	i = tx_subcrqs - 1;
-	kfree(adapter->tx_pool[i].free_map);
-tx_fm_alloc_failed:
-	free_long_term_buff(adapter, &adapter->tx_pool[i].long_term_buff);
-tx_ltb_alloc_failed:
-	kfree(adapter->tx_pool[i].tx_buff);
-tx_pool_alloc_failed:
-	for (j = 0; j < i; j++) {
-		kfree(adapter->tx_pool[j].tx_buff);
-		free_long_term_buff(adapter,
-				    &adapter->tx_pool[j].long_term_buff);
-		kfree(adapter->tx_pool[j].free_map);
-	}
-	kfree(adapter->tx_pool);
-	adapter->tx_pool = NULL;
-tx_pool_arr_alloc_failed:
-	i = rxadd_subcrqs;
-rx_pool_alloc_failed:
-	for (j = 0; j < i; j++) {
-		free_rx_pool(adapter, &adapter->rx_pool[j]);
-		free_long_term_buff(adapter,
-				    &adapter->rx_pool[j].long_term_buff);
-	}
-	kfree(adapter->rx_pool);
-	adapter->rx_pool = NULL;
-rx_pool_arr_alloc_failed:
+ibmvnic_open_fail:
 	for (i = 0; i < adapter->req_rx_queues; i++)
 		napi_disable(&adapter->napi[i]);
-alloc_napi_failed:
+	release_resources(adapter);
 	return -ENOMEM;
 }
 
 static int ibmvnic_close(struct net_device *netdev)
 {
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
-	struct device *dev = &adapter->vdev->dev;
 	union ibmvnic_crq crq;
 	int i;
 
@@ -526,45 +688,16 @@ static int ibmvnic_close(struct net_device *netdev)
 	if (!adapter->failover)
 		netif_tx_stop_all_queues(netdev);
 
-	if (adapter->bounce_buffer) {
-		if (!dma_mapping_error(dev, adapter->bounce_buffer_dma)) {
-			dma_unmap_single(&adapter->vdev->dev,
-					 adapter->bounce_buffer_dma,
-					 adapter->bounce_buffer_size,
-					 DMA_BIDIRECTIONAL);
-			adapter->bounce_buffer_dma = DMA_ERROR_CODE;
-		}
-		kfree(adapter->bounce_buffer);
-		adapter->bounce_buffer = NULL;
-	}
-
 	memset(&crq, 0, sizeof(crq));
 	crq.logical_link_state.first = IBMVNIC_CRQ_CMD;
 	crq.logical_link_state.cmd = LOGICAL_LINK_STATE;
 	crq.logical_link_state.link_state = IBMVNIC_LOGICAL_LNK_DN;
 	ibmvnic_send_crq(adapter, &crq);
 
-	for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
-	     i++) {
-		kfree(adapter->tx_pool[i].tx_buff);
-		free_long_term_buff(adapter,
-				    &adapter->tx_pool[i].long_term_buff);
-		kfree(adapter->tx_pool[i].free_map);
-	}
-	kfree(adapter->tx_pool);
-	adapter->tx_pool = NULL;
-
-	for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
-	     i++) {
-		free_rx_pool(adapter, &adapter->rx_pool[i]);
-		free_long_term_buff(adapter,
-				    &adapter->rx_pool[i].long_term_buff);
-	}
-	kfree(adapter->rx_pool);
-	adapter->rx_pool = NULL;
+	release_resources(adapter);
 
+	adapter->is_closed = true;
 	adapter->closing = false;
-
 	return 0;
 }
 
@@ -1249,49 +1382,40 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter)
 	int i;
 
 	if (adapter->tx_scrq) {
-		for (i = 0; i < adapter->req_tx_queues; i++)
-			if (adapter->tx_scrq[i]) {
+		for (i = 0; i < adapter->req_tx_queues; i++) {
+			if (!adapter->tx_scrq[i])
+				continue;
+
+			if (adapter->tx_scrq[i]->irq) {
 				free_irq(adapter->tx_scrq[i]->irq,
 					 adapter->tx_scrq[i]);
 				irq_dispose_mapping(adapter->tx_scrq[i]->irq);
-				release_sub_crq_queue(adapter,
-						      adapter->tx_scrq[i]);
+				adapter->tx_scrq[i]->irq = 0;
 			}
+
+			release_sub_crq_queue(adapter, adapter->tx_scrq[i]);
+		}
+
 		kfree(adapter->tx_scrq);
 		adapter->tx_scrq = NULL;
 	}
 
 	if (adapter->rx_scrq) {
-		for (i = 0; i < adapter->req_rx_queues; i++)
-			if (adapter->rx_scrq[i]) {
+		for (i = 0; i < adapter->req_rx_queues; i++) {
+			if (!adapter->rx_scrq[i])
+				continue;
+
+			if (adapter->rx_scrq[i]->irq) {
 				free_irq(adapter->rx_scrq[i]->irq,
 					 adapter->rx_scrq[i]);
 				irq_dispose_mapping(adapter->rx_scrq[i]->irq);
-				release_sub_crq_queue(adapter,
-						      adapter->rx_scrq[i]);
+				adapter->rx_scrq[i]->irq = 0;
 			}
-		kfree(adapter->rx_scrq);
-		adapter->rx_scrq = NULL;
-	}
-}
 
-static void release_sub_crqs_no_irqs(struct ibmvnic_adapter *adapter)
-{
-	int i;
-
-	if (adapter->tx_scrq) {
-		for (i = 0; i < adapter->req_tx_queues; i++)
-			if (adapter->tx_scrq[i])
-				release_sub_crq_queue(adapter,
-						      adapter->tx_scrq[i]);
-		adapter->tx_scrq = NULL;
-	}
+			release_sub_crq_queue(adapter, adapter->rx_scrq[i]);
+		}
 
-	if (adapter->rx_scrq) {
-		for (i = 0; i < adapter->req_rx_queues; i++)
-			if (adapter->rx_scrq[i])
-				release_sub_crq_queue(adapter,
-						      adapter->rx_scrq[i]);
+		kfree(adapter->rx_scrq);
 		adapter->rx_scrq = NULL;
 	}
 }
@@ -1487,7 +1611,7 @@ req_tx_irq_failed:
 		free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]);
 		irq_dispose_mapping(adapter->rx_scrq[j]->irq);
 	}
-	release_sub_crqs_no_irqs(adapter);
+	release_sub_crqs(adapter);
 	return rc;
 }
 
@@ -2242,57 +2366,6 @@ static void handle_error_info_rsp(union ibmvnic_crq *crq,
 	kfree(error_buff);
 }
 
-static void handle_dump_size_rsp(union ibmvnic_crq *crq,
-				 struct ibmvnic_adapter *adapter)
-{
-	int len = be32_to_cpu(crq->request_dump_size_rsp.len);
-	struct ibmvnic_inflight_cmd *inflight_cmd;
-	struct device *dev = &adapter->vdev->dev;
-	union ibmvnic_crq newcrq;
-	unsigned long flags;
-
-	/* allocate and map buffer */
-	adapter->dump_data = kmalloc(len, GFP_KERNEL);
-	if (!adapter->dump_data) {
-		complete(&adapter->fw_done);
-		return;
-	}
-
-	adapter->dump_data_token = dma_map_single(dev, adapter->dump_data, len,
-						  DMA_FROM_DEVICE);
-
-	if (dma_mapping_error(dev, adapter->dump_data_token)) {
-		if (!firmware_has_feature(FW_FEATURE_CMO))
-			dev_err(dev, "Couldn't map dump data\n");
-		kfree(adapter->dump_data);
-		complete(&adapter->fw_done);
-		return;
-	}
-
-	inflight_cmd = kmalloc(sizeof(*inflight_cmd), GFP_ATOMIC);
-	if (!inflight_cmd) {
-		dma_unmap_single(dev, adapter->dump_data_token, len,
-				 DMA_FROM_DEVICE);
-		kfree(adapter->dump_data);
-		complete(&adapter->fw_done);
-		return;
-	}
-
-	memset(&newcrq, 0, sizeof(newcrq));
-	newcrq.request_dump.first = IBMVNIC_CRQ_CMD;
-	newcrq.request_dump.cmd = REQUEST_DUMP;
-	newcrq.request_dump.ioba = cpu_to_be32(adapter->dump_data_token);
-	newcrq.request_dump.len = cpu_to_be32(adapter->dump_data_size);
-
-	memcpy(&inflight_cmd->crq, &newcrq, sizeof(newcrq));
-
-	spin_lock_irqsave(&adapter->inflight_lock, flags);
-	list_add_tail(&inflight_cmd->list, &adapter->inflight);
-	spin_unlock_irqrestore(&adapter->inflight_lock, flags);
-
-	ibmvnic_send_crq(adapter, &newcrq);
-}
-
 static void handle_error_indication(union ibmvnic_crq *crq,
 				    struct ibmvnic_adapter *adapter)
 {
@@ -2428,7 +2501,7 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq,
 			 *req_value,
 			 (long int)be64_to_cpu(crq->request_capability_rsp.
 					       number), name);
-		release_sub_crqs_no_irqs(adapter);
+		release_sub_crqs(adapter);
 		*req_value = be64_to_cpu(crq->request_capability_rsp.number);
 		init_sub_crqs(adapter, 1);
 		return;
@@ -2473,7 +2546,6 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
 	struct device *dev = &adapter->vdev->dev;
 	struct ibmvnic_login_rsp_buffer *login_rsp = adapter->login_rsp_buf;
 	struct ibmvnic_login_buffer *login = adapter->login_buf;
-	union ibmvnic_crq crq;
 	int i;
 
 	dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz,
@@ -2508,11 +2580,6 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
 	}
 	complete(&adapter->init_done);
 
-	memset(&crq, 0, sizeof(crq));
-	crq.request_ras_comp_num.first = IBMVNIC_CRQ_CMD;
-	crq.request_ras_comp_num.cmd = REQUEST_RAS_COMP_NUM;
-	ibmvnic_send_crq(adapter, &crq);
-
 	return 0;
 }
 
@@ -2748,476 +2815,6 @@ out:
 	}
 }
 
-static void handle_control_ras_rsp(union ibmvnic_crq *crq,
-				   struct ibmvnic_adapter *adapter)
-{
-	u8 correlator = crq->control_ras_rsp.correlator;
-	struct device *dev = &adapter->vdev->dev;
-	bool found = false;
-	int i;
-
-	if (crq->control_ras_rsp.rc.code) {
-		dev_warn(dev, "Control ras failed rc=%d\n",
-			 crq->control_ras_rsp.rc.code);
-		return;
-	}
-
-	for (i = 0; i < adapter->ras_comp_num; i++) {
-		if (adapter->ras_comps[i].correlator == correlator) {
-			found = true;
-			break;
-		}
-	}
-
-	if (!found) {
-		dev_warn(dev, "Correlator not found on control_ras_rsp\n");
-		return;
-	}
-
-	switch (crq->control_ras_rsp.op) {
-	case IBMVNIC_TRACE_LEVEL:
-		adapter->ras_comps[i].trace_level = crq->control_ras.level;
-		break;
-	case IBMVNIC_ERROR_LEVEL:
-		adapter->ras_comps[i].error_check_level =
-		    crq->control_ras.level;
-		break;
-	case IBMVNIC_TRACE_PAUSE:
-		adapter->ras_comp_int[i].paused = 1;
-		break;
-	case IBMVNIC_TRACE_RESUME:
-		adapter->ras_comp_int[i].paused = 0;
-		break;
-	case IBMVNIC_TRACE_ON:
-		adapter->ras_comps[i].trace_on = 1;
-		break;
-	case IBMVNIC_TRACE_OFF:
-		adapter->ras_comps[i].trace_on = 0;
-		break;
-	case IBMVNIC_CHG_TRACE_BUFF_SZ:
-		/* trace_buff_sz is 3 bytes, stuff it into an int */
-		((u8 *)(&adapter->ras_comps[i].trace_buff_size))[0] = 0;
-		((u8 *)(&adapter->ras_comps[i].trace_buff_size))[1] =
-		    crq->control_ras_rsp.trace_buff_sz[0];
-		((u8 *)(&adapter->ras_comps[i].trace_buff_size))[2] =
-		    crq->control_ras_rsp.trace_buff_sz[1];
-		((u8 *)(&adapter->ras_comps[i].trace_buff_size))[3] =
-		    crq->control_ras_rsp.trace_buff_sz[2];
-		break;
-	default:
-		dev_err(dev, "invalid op %d on control_ras_rsp",
-			crq->control_ras_rsp.op);
-	}
-}
-
-static ssize_t trace_read(struct file *file, char __user *user_buf, size_t len,
-			  loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	struct device *dev = &adapter->vdev->dev;
-	struct ibmvnic_fw_trace_entry *trace;
-	int num = ras_comp_int->num;
-	union ibmvnic_crq crq;
-	dma_addr_t trace_tok;
-
-	if (*ppos >= be32_to_cpu(adapter->ras_comps[num].trace_buff_size))
-		return 0;
-
-	trace =
-	    dma_alloc_coherent(dev,
-			       be32_to_cpu(adapter->ras_comps[num].
-					   trace_buff_size), &trace_tok,
-			       GFP_KERNEL);
-	if (!trace) {
-		dev_err(dev, "Couldn't alloc trace buffer\n");
-		return 0;
-	}
-
-	memset(&crq, 0, sizeof(crq));
-	crq.collect_fw_trace.first = IBMVNIC_CRQ_CMD;
-	crq.collect_fw_trace.cmd = COLLECT_FW_TRACE;
-	crq.collect_fw_trace.correlator = adapter->ras_comps[num].correlator;
-	crq.collect_fw_trace.ioba = cpu_to_be32(trace_tok);
-	crq.collect_fw_trace.len = adapter->ras_comps[num].trace_buff_size;
-
-	init_completion(&adapter->fw_done);
-	ibmvnic_send_crq(adapter, &crq);
-	wait_for_completion(&adapter->fw_done);
-
-	if (*ppos + len > be32_to_cpu(adapter->ras_comps[num].trace_buff_size))
-		len =
-		    be32_to_cpu(adapter->ras_comps[num].trace_buff_size) -
-		    *ppos;
-
-	copy_to_user(user_buf, &((u8 *)trace)[*ppos], len);
-
-	dma_free_coherent(dev,
-			  be32_to_cpu(adapter->ras_comps[num].trace_buff_size),
-			  trace, trace_tok);
-	*ppos += len;
-	return len;
-}
-
-static const struct file_operations trace_ops = {
-	.owner		= THIS_MODULE,
-	.open		= simple_open,
-	.read		= trace_read,
-};
-
-static ssize_t paused_read(struct file *file, char __user *user_buf, size_t len,
-			   loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	int num = ras_comp_int->num;
-	char buff[5]; /*  1 or 0 plus \n and \0 */
-	int size;
-
-	size = sprintf(buff, "%d\n", adapter->ras_comp_int[num].paused);
-
-	if (*ppos >= size)
-		return 0;
-
-	copy_to_user(user_buf, buff, size);
-	*ppos += size;
-	return size;
-}
-
-static ssize_t paused_write(struct file *file, const char __user *user_buf,
-			    size_t len, loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	int num = ras_comp_int->num;
-	union ibmvnic_crq crq;
-	unsigned long val;
-	char buff[9]; /* decimal max int plus \n and \0 */
-
-	copy_from_user(buff, user_buf, sizeof(buff));
-	val = kstrtoul(buff, 10, NULL);
-
-	adapter->ras_comp_int[num].paused = val ? 1 : 0;
-
-	memset(&crq, 0, sizeof(crq));
-	crq.control_ras.first = IBMVNIC_CRQ_CMD;
-	crq.control_ras.cmd = CONTROL_RAS;
-	crq.control_ras.correlator = adapter->ras_comps[num].correlator;
-	crq.control_ras.op = val ? IBMVNIC_TRACE_PAUSE : IBMVNIC_TRACE_RESUME;
-	ibmvnic_send_crq(adapter, &crq);
-
-	return len;
-}
-
-static const struct file_operations paused_ops = {
-	.owner		= THIS_MODULE,
-	.open		= simple_open,
-	.read		= paused_read,
-	.write		= paused_write,
-};
-
-static ssize_t tracing_read(struct file *file, char __user *user_buf,
-			    size_t len, loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	int num = ras_comp_int->num;
-	char buff[5]; /*  1 or 0 plus \n and \0 */
-	int size;
-
-	size = sprintf(buff, "%d\n", adapter->ras_comps[num].trace_on);
-
-	if (*ppos >= size)
-		return 0;
-
-	copy_to_user(user_buf, buff, size);
-	*ppos += size;
-	return size;
-}
-
-static ssize_t tracing_write(struct file *file, const char __user *user_buf,
-			     size_t len, loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	int num = ras_comp_int->num;
-	union ibmvnic_crq crq;
-	unsigned long val;
-	char buff[9]; /* decimal max int plus \n and \0 */
-
-	copy_from_user(buff, user_buf, sizeof(buff));
-	val = kstrtoul(buff, 10, NULL);
-
-	memset(&crq, 0, sizeof(crq));
-	crq.control_ras.first = IBMVNIC_CRQ_CMD;
-	crq.control_ras.cmd = CONTROL_RAS;
-	crq.control_ras.correlator = adapter->ras_comps[num].correlator;
-	crq.control_ras.op = val ? IBMVNIC_TRACE_ON : IBMVNIC_TRACE_OFF;
-
-	return len;
-}
-
-static const struct file_operations tracing_ops = {
-	.owner		= THIS_MODULE,
-	.open		= simple_open,
-	.read		= tracing_read,
-	.write		= tracing_write,
-};
-
-static ssize_t error_level_read(struct file *file, char __user *user_buf,
-				size_t len, loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	int num = ras_comp_int->num;
-	char buff[5]; /* decimal max char plus \n and \0 */
-	int size;
-
-	size = sprintf(buff, "%d\n", adapter->ras_comps[num].error_check_level);
-
-	if (*ppos >= size)
-		return 0;
-
-	copy_to_user(user_buf, buff, size);
-	*ppos += size;
-	return size;
-}
-
-static ssize_t error_level_write(struct file *file, const char __user *user_buf,
-				 size_t len, loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	int num = ras_comp_int->num;
-	union ibmvnic_crq crq;
-	unsigned long val;
-	char buff[9]; /* decimal max int plus \n and \0 */
-
-	copy_from_user(buff, user_buf, sizeof(buff));
-	val = kstrtoul(buff, 10, NULL);
-
-	if (val > 9)
-		val = 9;
-
-	memset(&crq, 0, sizeof(crq));
-	crq.control_ras.first = IBMVNIC_CRQ_CMD;
-	crq.control_ras.cmd = CONTROL_RAS;
-	crq.control_ras.correlator = adapter->ras_comps[num].correlator;
-	crq.control_ras.op = IBMVNIC_ERROR_LEVEL;
-	crq.control_ras.level = val;
-	ibmvnic_send_crq(adapter, &crq);
-
-	return len;
-}
-
-static const struct file_operations error_level_ops = {
-	.owner		= THIS_MODULE,
-	.open		= simple_open,
-	.read		= error_level_read,
-	.write		= error_level_write,
-};
-
-static ssize_t trace_level_read(struct file *file, char __user *user_buf,
-				size_t len, loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	int num = ras_comp_int->num;
-	char buff[5]; /* decimal max char plus \n and \0 */
-	int size;
-
-	size = sprintf(buff, "%d\n", adapter->ras_comps[num].trace_level);
-	if (*ppos >= size)
-		return 0;
-
-	copy_to_user(user_buf, buff, size);
-	*ppos += size;
-	return size;
-}
-
-static ssize_t trace_level_write(struct file *file, const char __user *user_buf,
-				 size_t len, loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	union ibmvnic_crq crq;
-	unsigned long val;
-	char buff[9]; /* decimal max int plus \n and \0 */
-
-	copy_from_user(buff, user_buf, sizeof(buff));
-	val = kstrtoul(buff, 10, NULL);
-	if (val > 9)
-		val = 9;
-
-	memset(&crq, 0, sizeof(crq));
-	crq.control_ras.first = IBMVNIC_CRQ_CMD;
-	crq.control_ras.cmd = CONTROL_RAS;
-	crq.control_ras.correlator =
-	    adapter->ras_comps[ras_comp_int->num].correlator;
-	crq.control_ras.op = IBMVNIC_TRACE_LEVEL;
-	crq.control_ras.level = val;
-	ibmvnic_send_crq(adapter, &crq);
-
-	return len;
-}
-
-static const struct file_operations trace_level_ops = {
-	.owner		= THIS_MODULE,
-	.open		= simple_open,
-	.read		= trace_level_read,
-	.write		= trace_level_write,
-};
-
-static ssize_t trace_buff_size_read(struct file *file, char __user *user_buf,
-				    size_t len, loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	int num = ras_comp_int->num;
-	char buff[9]; /* decimal max int plus \n and \0 */
-	int size;
-
-	size = sprintf(buff, "%d\n", adapter->ras_comps[num].trace_buff_size);
-	if (*ppos >= size)
-		return 0;
-
-	copy_to_user(user_buf, buff, size);
-	*ppos += size;
-	return size;
-}
-
-static ssize_t trace_buff_size_write(struct file *file,
-				     const char __user *user_buf, size_t len,
-				     loff_t *ppos)
-{
-	struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
-	struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
-	union ibmvnic_crq crq;
-	unsigned long val;
-	char buff[9]; /* decimal max int plus \n and \0 */
-
-	copy_from_user(buff, user_buf, sizeof(buff));
-	val = kstrtoul(buff, 10, NULL);
-
-	memset(&crq, 0, sizeof(crq));
-	crq.control_ras.first = IBMVNIC_CRQ_CMD;
-	crq.control_ras.cmd = CONTROL_RAS;
-	crq.control_ras.correlator =
-	    adapter->ras_comps[ras_comp_int->num].correlator;
-	crq.control_ras.op = IBMVNIC_CHG_TRACE_BUFF_SZ;
-	/* trace_buff_sz is 3 bytes, stuff an int into it */
-	crq.control_ras.trace_buff_sz[0] = ((u8 *)(&val))[5];
-	crq.control_ras.trace_buff_sz[1] = ((u8 *)(&val))[6];
-	crq.control_ras.trace_buff_sz[2] = ((u8 *)(&val))[7];
-	ibmvnic_send_crq(adapter, &crq);
-
-	return len;
-}
-
-static const struct file_operations trace_size_ops = {
-	.owner		= THIS_MODULE,
-	.open		= simple_open,
-	.read		= trace_buff_size_read,
-	.write		= trace_buff_size_write,
-};
-
-static void handle_request_ras_comps_rsp(union ibmvnic_crq *crq,
-					 struct ibmvnic_adapter *adapter)
-{
-	struct device *dev = &adapter->vdev->dev;
-	struct dentry *dir_ent;
-	struct dentry *ent;
-	int i;
-
-	debugfs_remove_recursive(adapter->ras_comps_ent);
-
-	adapter->ras_comps_ent = debugfs_create_dir("ras_comps",
-						    adapter->debugfs_dir);
-	if (!adapter->ras_comps_ent || IS_ERR(adapter->ras_comps_ent)) {
-		dev_info(dev, "debugfs create ras_comps dir failed\n");
-		return;
-	}
-
-	for (i = 0; i < adapter->ras_comp_num; i++) {
-		dir_ent = debugfs_create_dir(adapter->ras_comps[i].name,
-					     adapter->ras_comps_ent);
-		if (!dir_ent || IS_ERR(dir_ent)) {
-			dev_info(dev, "debugfs create %s dir failed\n",
-				 adapter->ras_comps[i].name);
-			continue;
-		}
-
-		adapter->ras_comp_int[i].adapter = adapter;
-		adapter->ras_comp_int[i].num = i;
-		adapter->ras_comp_int[i].desc_blob.data =
-		    &adapter->ras_comps[i].description;
-		adapter->ras_comp_int[i].desc_blob.size =
-		    sizeof(adapter->ras_comps[i].description);
-
-		/* Don't need to remember the dentry's because the debugfs dir
-		 * gets removed recursively
-		 */
-		ent = debugfs_create_blob("description", S_IRUGO, dir_ent,
-					  &adapter->ras_comp_int[i].desc_blob);
-		ent = debugfs_create_file("trace_buf_size", S_IRUGO | S_IWUSR,
-					  dir_ent, &adapter->ras_comp_int[i],
-					  &trace_size_ops);
-		ent = debugfs_create_file("trace_level",
-					  S_IRUGO |
-					  (adapter->ras_comps[i].trace_level !=
-					   0xFF  ? S_IWUSR : 0),
-					   dir_ent, &adapter->ras_comp_int[i],
-					   &trace_level_ops);
-		ent = debugfs_create_file("error_level",
-					  S_IRUGO |
-					  (adapter->
-					   ras_comps[i].error_check_level !=
-					   0xFF ? S_IWUSR : 0),
-					  dir_ent, &adapter->ras_comp_int[i],
-					  &trace_level_ops);
-		ent = debugfs_create_file("tracing", S_IRUGO | S_IWUSR,
-					  dir_ent, &adapter->ras_comp_int[i],
-					  &tracing_ops);
-		ent = debugfs_create_file("paused", S_IRUGO | S_IWUSR,
-					  dir_ent, &adapter->ras_comp_int[i],
-					  &paused_ops);
-		ent = debugfs_create_file("trace", S_IRUGO, dir_ent,
-					  &adapter->ras_comp_int[i],
-					  &trace_ops);
-	}
-}
-
-static void handle_request_ras_comp_num_rsp(union ibmvnic_crq *crq,
-					    struct ibmvnic_adapter *adapter)
-{
-	int len = adapter->ras_comp_num * sizeof(struct ibmvnic_fw_component);
-	struct device *dev = &adapter->vdev->dev;
-	union ibmvnic_crq newcrq;
-
-	adapter->ras_comps = dma_alloc_coherent(dev, len,
-						&adapter->ras_comps_tok,
-						GFP_KERNEL);
-	if (!adapter->ras_comps) {
-		if (!firmware_has_feature(FW_FEATURE_CMO))
-			dev_err(dev, "Couldn't alloc fw comps buffer\n");
-		return;
-	}
-
-	adapter->ras_comp_int = kmalloc(adapter->ras_comp_num *
-					sizeof(struct ibmvnic_fw_comp_internal),
-					GFP_KERNEL);
-	if (!adapter->ras_comp_int)
-		dma_free_coherent(dev, len, adapter->ras_comps,
-				  adapter->ras_comps_tok);
-
-	memset(&newcrq, 0, sizeof(newcrq));
-	newcrq.request_ras_comps.first = IBMVNIC_CRQ_CMD;
-	newcrq.request_ras_comps.cmd = REQUEST_RAS_COMPS;
-	newcrq.request_ras_comps.ioba = cpu_to_be32(adapter->ras_comps_tok);
-	newcrq.request_ras_comps.len = cpu_to_be32(len);
-	ibmvnic_send_crq(adapter, &newcrq);
-}
-
 static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter)
 {
 	struct ibmvnic_inflight_cmd *inflight_cmd, *tmp1;
@@ -3239,9 +2836,6 @@ static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter)
 			kfree(adapter->login_rsp_buf);
 			kfree(adapter->login_buf);
 			break;
-		case REQUEST_DUMP:
-			complete(&adapter->fw_done);
-			break;
 		case REQUEST_ERROR_INFO:
 			spin_lock_irqsave(&adapter->error_list_lock, flags2);
 			list_for_each_entry_safe(error_buff, tmp2,
@@ -3401,14 +2995,6 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 		netdev_dbg(netdev, "Got Statistics Response\n");
 		complete(&adapter->stats_done);
 		break;
-	case REQUEST_DUMP_SIZE_RSP:
-		netdev_dbg(netdev, "Got Request Dump Size Response\n");
-		handle_dump_size_rsp(crq, adapter);
-		break;
-	case REQUEST_DUMP_RSP:
-		netdev_dbg(netdev, "Got Request Dump Response\n");
-		complete(&adapter->fw_done);
-		break;
 	case QUERY_IP_OFFLOAD_RSP:
 		netdev_dbg(netdev, "Got Query IP offload Response\n");
 		handle_query_ip_offload_rsp(adapter);
@@ -3421,26 +3007,7 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 		dma_unmap_single(dev, adapter->ip_offload_ctrl_tok,
 				 sizeof(adapter->ip_offload_ctrl),
 				 DMA_TO_DEVICE);
-		/* We're done with the queries, perform the login */
-		send_login(adapter);
-		break;
-	case REQUEST_RAS_COMP_NUM_RSP:
-		netdev_dbg(netdev, "Got Request RAS Comp Num Response\n");
-		if (crq->request_ras_comp_num_rsp.rc.code == 10) {
-			netdev_dbg(netdev, "Request RAS Comp Num not supported\n");
-			break;
-		}
-		adapter->ras_comp_num =
-		    be32_to_cpu(crq->request_ras_comp_num_rsp.num_components);
-		handle_request_ras_comp_num_rsp(crq, adapter);
-		break;
-	case REQUEST_RAS_COMPS_RSP:
-		netdev_dbg(netdev, "Got Request RAS Comps Response\n");
-		handle_request_ras_comps_rsp(crq, adapter);
-		break;
-	case CONTROL_RAS_RSP:
-		netdev_dbg(netdev, "Got Control RAS Response\n");
-		handle_control_ras_rsp(crq, adapter);
+		complete(&adapter->init_done);
 		break;
 	case COLLECT_FW_TRACE_RSP:
 		netdev_dbg(netdev, "Got Collect firmware trace Response\n");
@@ -3547,12 +3114,15 @@ static int ibmvnic_reset_crq(struct ibmvnic_adapter *adapter)
 	return rc;
 }
 
-static void ibmvnic_release_crq_queue(struct ibmvnic_adapter *adapter)
+static void release_crq_queue(struct ibmvnic_adapter *adapter)
 {
 	struct ibmvnic_crq_queue *crq = &adapter->crq;
 	struct vio_dev *vdev = adapter->vdev;
 	long rc;
 
+	if (!crq->msgs)
+		return;
+
 	netdev_dbg(adapter->netdev, "Releasing CRQ\n");
 	free_irq(vdev->irq, adapter);
 	tasklet_kill(&adapter->tasklet);
@@ -3563,15 +3133,19 @@ static void ibmvnic_release_crq_queue(struct ibmvnic_adapter *adapter)
 	dma_unmap_single(&vdev->dev, crq->msg_token, PAGE_SIZE,
 			 DMA_BIDIRECTIONAL);
 	free_page((unsigned long)crq->msgs);
+	crq->msgs = NULL;
 }
 
-static int ibmvnic_init_crq_queue(struct ibmvnic_adapter *adapter)
+static int init_crq_queue(struct ibmvnic_adapter *adapter)
 {
 	struct ibmvnic_crq_queue *crq = &adapter->crq;
 	struct device *dev = &adapter->vdev->dev;
 	struct vio_dev *vdev = adapter->vdev;
 	int rc, retrc = -ENOMEM;
 
+	if (crq->msgs)
+		return 0;
+
 	crq->msgs = (union ibmvnic_crq *)get_zeroed_page(GFP_KERNEL);
 	/* Should we allocate more than one page? */
 
@@ -3633,48 +3207,10 @@ reg_crq_failed:
 	dma_unmap_single(dev, crq->msg_token, PAGE_SIZE, DMA_BIDIRECTIONAL);
 map_failed:
 	free_page((unsigned long)crq->msgs);
+	crq->msgs = NULL;
 	return retrc;
 }
 
-/* debugfs for dump */
-static int ibmvnic_dump_show(struct seq_file *seq, void *v)
-{
-	struct net_device *netdev = seq->private;
-	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
-	struct device *dev = &adapter->vdev->dev;
-	union ibmvnic_crq crq;
-
-	memset(&crq, 0, sizeof(crq));
-	crq.request_dump_size.first = IBMVNIC_CRQ_CMD;
-	crq.request_dump_size.cmd = REQUEST_DUMP_SIZE;
-
-	init_completion(&adapter->fw_done);
-	ibmvnic_send_crq(adapter, &crq);
-	wait_for_completion(&adapter->fw_done);
-
-	seq_write(seq, adapter->dump_data, adapter->dump_data_size);
-
-	dma_unmap_single(dev, adapter->dump_data_token, adapter->dump_data_size,
-			 DMA_BIDIRECTIONAL);
-
-	kfree(adapter->dump_data);
-
-	return 0;
-}
-
-static int ibmvnic_dump_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ibmvnic_dump_show, inode->i_private);
-}
-
-static const struct file_operations ibmvnic_dump_ops = {
-	.owner          = THIS_MODULE,
-	.open           = ibmvnic_dump_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release        = single_release,
-};
-
 static void handle_crq_init_rsp(struct work_struct *work)
 {
 	struct ibmvnic_adapter *adapter = container_of(work,
@@ -3702,26 +3238,6 @@ static void handle_crq_init_rsp(struct work_struct *work)
 		goto task_failed;
 	}
 
-	do {
-		if (adapter->renegotiate) {
-			adapter->renegotiate = false;
-			release_sub_crqs_no_irqs(adapter);
-
-			reinit_completion(&adapter->init_done);
-			send_cap_queries(adapter);
-			if (!wait_for_completion_timeout(&adapter->init_done,
-							 timeout)) {
-				dev_err(dev, "Passive init timeout\n");
-				goto task_failed;
-			}
-		}
-	} while (adapter->renegotiate);
-	rc = init_sub_crq_irqs(adapter);
-
-	if (rc)
-		goto task_failed;
-
-	netdev->real_num_tx_queues = adapter->req_tx_queues;
 	netdev->mtu = adapter->req_mtu - ETH_HLEN;
 
 	if (adapter->failover) {
@@ -3753,14 +3269,40 @@ task_failed:
 	dev_err(dev, "Passive initialization was not successful\n");
 }
 
-static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
+static int ibmvnic_init(struct ibmvnic_adapter *adapter)
 {
+	struct device *dev = &adapter->vdev->dev;
 	unsigned long timeout = msecs_to_jiffies(30000);
+	int rc;
+
+	rc = init_crq_queue(adapter);
+	if (rc) {
+		dev_err(dev, "Couldn't initialize crq. rc=%d\n", rc);
+		return rc;
+	}
+
+	rc = init_stats_token(adapter);
+	if (rc) {
+		release_crq_queue(adapter);
+		return rc;
+	}
+
+	init_completion(&adapter->init_done);
+	ibmvnic_send_crq_init(adapter);
+	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
+		dev_err(dev, "Initialization sequence timed out\n");
+		release_crq_queue(adapter);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
+{
 	struct ibmvnic_adapter *adapter;
 	struct net_device *netdev;
 	unsigned char *mac_addr_p;
-	struct dentry *ent;
-	char buf[17]; /* debugfs name buf */
 	int rc;
 
 	dev_dbg(&dev->dev, "entering ibmvnic_probe for UA 0x%x\n",
@@ -3798,118 +3340,36 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 
 	spin_lock_init(&adapter->stats_lock);
 
-	rc = ibmvnic_init_crq_queue(adapter);
-	if (rc) {
-		dev_err(&dev->dev, "Couldn't initialize crq. rc=%d\n", rc);
-		goto free_netdev;
-	}
-
 	INIT_LIST_HEAD(&adapter->errors);
 	INIT_LIST_HEAD(&adapter->inflight);
 	spin_lock_init(&adapter->error_list_lock);
 	spin_lock_init(&adapter->inflight_lock);
 
-	adapter->stats_token = dma_map_single(&dev->dev, &adapter->stats,
-					      sizeof(struct ibmvnic_statistics),
-					      DMA_FROM_DEVICE);
-	if (dma_mapping_error(&dev->dev, adapter->stats_token)) {
-		if (!firmware_has_feature(FW_FEATURE_CMO))
-			dev_err(&dev->dev, "Couldn't map stats buffer\n");
-		rc = -ENOMEM;
-		goto free_crq;
-	}
-
-	snprintf(buf, sizeof(buf), "ibmvnic_%x", dev->unit_address);
-	ent = debugfs_create_dir(buf, NULL);
-	if (!ent || IS_ERR(ent)) {
-		dev_info(&dev->dev, "debugfs create directory failed\n");
-		adapter->debugfs_dir = NULL;
-	} else {
-		adapter->debugfs_dir = ent;
-		ent = debugfs_create_file("dump", S_IRUGO, adapter->debugfs_dir,
-					  netdev, &ibmvnic_dump_ops);
-		if (!ent || IS_ERR(ent)) {
-			dev_info(&dev->dev,
-				 "debugfs create dump file failed\n");
-			adapter->debugfs_dump = NULL;
-		} else {
-			adapter->debugfs_dump = ent;
-		}
-	}
-
-	init_completion(&adapter->init_done);
-	ibmvnic_send_crq_init(adapter);
-	if (!wait_for_completion_timeout(&adapter->init_done, timeout))
-		return 0;
-
-	do {
-		if (adapter->renegotiate) {
-			adapter->renegotiate = false;
-			release_sub_crqs_no_irqs(adapter);
-
-			reinit_completion(&adapter->init_done);
-			send_cap_queries(adapter);
-			if (!wait_for_completion_timeout(&adapter->init_done,
-							 timeout))
-				return 0;
-		}
-	} while (adapter->renegotiate);
-
-	rc = init_sub_crq_irqs(adapter);
+	rc = ibmvnic_init(adapter);
 	if (rc) {
-		dev_err(&dev->dev, "failed to initialize sub crq irqs\n");
-		goto free_debugfs;
+		free_netdev(netdev);
+		return rc;
 	}
 
-	netdev->real_num_tx_queues = adapter->req_tx_queues;
 	netdev->mtu = adapter->req_mtu - ETH_HLEN;
+	adapter->is_closed = false;
 
 	rc = register_netdev(netdev);
 	if (rc) {
 		dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc);
-		goto free_sub_crqs;
+		free_netdev(netdev);
+		return rc;
 	}
 	dev_info(&dev->dev, "ibmvnic registered\n");
 
 	return 0;
-
-free_sub_crqs:
-	release_sub_crqs(adapter);
-free_debugfs:
-	if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir))
-		debugfs_remove_recursive(adapter->debugfs_dir);
-free_crq:
-	ibmvnic_release_crq_queue(adapter);
-free_netdev:
-	free_netdev(netdev);
-	return rc;
 }
 
 static int ibmvnic_remove(struct vio_dev *dev)
 {
 	struct net_device *netdev = dev_get_drvdata(&dev->dev);
-	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
 
 	unregister_netdev(netdev);
-
-	release_sub_crqs(adapter);
-
-	ibmvnic_release_crq_queue(adapter);
-
-	if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir))
-		debugfs_remove_recursive(adapter->debugfs_dir);
-
-	dma_unmap_single(&dev->dev, adapter->stats_token,
-			 sizeof(struct ibmvnic_statistics), DMA_FROM_DEVICE);
-
-	if (adapter->ras_comps)
-		dma_free_coherent(&dev->dev,
-				  adapter->ras_comp_num *
-				  sizeof(struct ibmvnic_fw_component),
-				  adapter->ras_comps, adapter->ras_comps_tok);
-
-	kfree(adapter->ras_comp_int);
-
 	free_netdev(netdev);
 	dev_set_drvdata(&dev->dev, NULL);
 
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 1993b42666f7..b0d0b890d033 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -772,20 +772,10 @@ enum ibmvnic_commands {
 	ERROR_INDICATION = 0x08,
 	REQUEST_ERROR_INFO = 0x09,
 	REQUEST_ERROR_RSP = 0x89,
-	REQUEST_DUMP_SIZE = 0x0A,
-	REQUEST_DUMP_SIZE_RSP = 0x8A,
-	REQUEST_DUMP = 0x0B,
-	REQUEST_DUMP_RSP = 0x8B,
 	LOGICAL_LINK_STATE = 0x0C,
 	LOGICAL_LINK_STATE_RSP = 0x8C,
 	REQUEST_STATISTICS = 0x0D,
 	REQUEST_STATISTICS_RSP = 0x8D,
-	REQUEST_RAS_COMP_NUM = 0x0E,
-	REQUEST_RAS_COMP_NUM_RSP = 0x8E,
-	REQUEST_RAS_COMPS = 0x0F,
-	REQUEST_RAS_COMPS_RSP = 0x8F,
-	CONTROL_RAS = 0x10,
-	CONTROL_RAS_RSP = 0x90,
 	COLLECT_FW_TRACE = 0x11,
 	COLLECT_FW_TRACE_RSP = 0x91,
 	LINK_STATE_INDICATION = 0x12,
@@ -806,8 +796,6 @@ enum ibmvnic_commands {
 	ACL_CHANGE_INDICATION = 0x1A,
 	ACL_QUERY = 0x1B,
 	ACL_QUERY_RSP = 0x9B,
-	REQUEST_DEBUG_STATS = 0x1C,
-	REQUEST_DEBUG_STATS_RSP = 0x9C,
 	QUERY_MAP = 0x1D,
 	QUERY_MAP_RSP = 0x9D,
 	REQUEST_MAP = 0x1E,
@@ -925,13 +913,6 @@ struct ibmvnic_error_buff {
 	__be32 error_id;
 };
 
-struct ibmvnic_fw_comp_internal {
-	struct ibmvnic_adapter *adapter;
-	int num;
-	struct debugfs_blob_wrapper desc_blob;
-	int paused;
-};
-
 struct ibmvnic_inflight_cmd {
 	union ibmvnic_crq crq;
 	struct list_head list;
@@ -953,7 +934,6 @@ struct ibmvnic_adapter {
 	dma_addr_t bounce_buffer_dma;
 
 	/* Statistics */
-	struct net_device_stats net_stats;
 	struct ibmvnic_statistics stats;
 	dma_addr_t stats_token;
 	struct completion stats_done;
@@ -996,18 +976,7 @@ struct ibmvnic_adapter {
 	struct list_head errors;
 	spinlock_t error_list_lock;
 
-	/* debugfs */
-	struct dentry *debugfs_dir;
-	struct dentry *debugfs_dump;
 	struct completion fw_done;
-	char *dump_data;
-	dma_addr_t dump_data_token;
-	int dump_data_size;
-	int ras_comp_num;
-	struct ibmvnic_fw_component *ras_comps;
-	struct ibmvnic_fw_comp_internal *ras_comp_int;
-	dma_addr_t ras_comps_tok;
-	struct dentry *ras_comps_ent;
 
 	/* in-flight commands that allocate and/or map memory*/
 	struct list_head inflight;
@@ -1052,4 +1021,5 @@ struct ibmvnic_adapter {
 	struct work_struct ibmvnic_xport;
 	struct tasklet_struct tasklet;
 	bool failover;
+	bool is_closed;
 };
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 1349b45f014d..1542a2158e96 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -235,17 +235,6 @@ config I40E_DCB
 
 	  If unsure, say N.
 
-config I40E_FCOE
-	bool "Fibre Channel over Ethernet (FCoE)"
-	default n
-	depends on I40E && DCB && FCOE
-	---help---
-	  Say Y here if you want to use Fibre Channel over Ethernet (FCoE)
-	  in the driver. This will create new netdev for exclusive FCoE
-	  use with XL710 FCoE offloads enabled.
-
-	  If unsure, say N.
-
 config I40EVF
 	tristate "Intel(R) XL710 X710 Virtual Function Ethernet support"
 	depends on PCI_MSI
diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
index 975eeb885ca2..ec8aa4562cc9 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
@@ -103,104 +103,104 @@ static const char e1000_gstrings_test[][ETH_GSTRING_LEN] = {
 
 #define E1000_TEST_LEN	ARRAY_SIZE(e1000_gstrings_test)
 
-static int e1000_get_settings(struct net_device *netdev,
-			      struct ethtool_cmd *ecmd)
+static int e1000_get_link_ksettings(struct net_device *netdev,
+				    struct ethtool_link_ksettings *cmd)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
+	u32 supported, advertising;
 
 	if (hw->media_type == e1000_media_type_copper) {
-		ecmd->supported = (SUPPORTED_10baseT_Half |
-				   SUPPORTED_10baseT_Full |
-				   SUPPORTED_100baseT_Half |
-				   SUPPORTED_100baseT_Full |
-				   SUPPORTED_1000baseT_Full|
-				   SUPPORTED_Autoneg |
-				   SUPPORTED_TP);
-		ecmd->advertising = ADVERTISED_TP;
+		supported = (SUPPORTED_10baseT_Half |
+			     SUPPORTED_10baseT_Full |
+			     SUPPORTED_100baseT_Half |
+			     SUPPORTED_100baseT_Full |
+			     SUPPORTED_1000baseT_Full|
+			     SUPPORTED_Autoneg |
+			     SUPPORTED_TP);
+		advertising = ADVERTISED_TP;
 
 		if (hw->autoneg == 1) {
-			ecmd->advertising |= ADVERTISED_Autoneg;
+			advertising |= ADVERTISED_Autoneg;
 			/* the e1000 autoneg seems to match ethtool nicely */
-			ecmd->advertising |= hw->autoneg_advertised;
+			advertising |= hw->autoneg_advertised;
 		}
 
-		ecmd->port = PORT_TP;
-		ecmd->phy_address = hw->phy_addr;
-
-		if (hw->mac_type == e1000_82543)
-			ecmd->transceiver = XCVR_EXTERNAL;
-		else
-			ecmd->transceiver = XCVR_INTERNAL;
-
+		cmd->base.port = PORT_TP;
+		cmd->base.phy_address = hw->phy_addr;
 	} else {
-		ecmd->supported   = (SUPPORTED_1000baseT_Full |
-				     SUPPORTED_FIBRE |
-				     SUPPORTED_Autoneg);
+		supported   = (SUPPORTED_1000baseT_Full |
+			       SUPPORTED_FIBRE |
+			       SUPPORTED_Autoneg);
 
-		ecmd->advertising = (ADVERTISED_1000baseT_Full |
-				     ADVERTISED_FIBRE |
-				     ADVERTISED_Autoneg);
+		advertising = (ADVERTISED_1000baseT_Full |
+			       ADVERTISED_FIBRE |
+			       ADVERTISED_Autoneg);
 
-		ecmd->port = PORT_FIBRE;
-
-		if (hw->mac_type >= e1000_82545)
-			ecmd->transceiver = XCVR_INTERNAL;
-		else
-			ecmd->transceiver = XCVR_EXTERNAL;
+		cmd->base.port = PORT_FIBRE;
 	}
 
 	if (er32(STATUS) & E1000_STATUS_LU) {
 		e1000_get_speed_and_duplex(hw, &adapter->link_speed,
 					   &adapter->link_duplex);
-		ethtool_cmd_speed_set(ecmd, adapter->link_speed);
+		cmd->base.speed = adapter->link_speed;
 
 		/* unfortunately FULL_DUPLEX != DUPLEX_FULL
 		 * and HALF_DUPLEX != DUPLEX_HALF
 		 */
 		if (adapter->link_duplex == FULL_DUPLEX)
-			ecmd->duplex = DUPLEX_FULL;
+			cmd->base.duplex = DUPLEX_FULL;
 		else
-			ecmd->duplex = DUPLEX_HALF;
+			cmd->base.duplex = DUPLEX_HALF;
 	} else {
-		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
-		ecmd->duplex = DUPLEX_UNKNOWN;
+		cmd->base.speed = SPEED_UNKNOWN;
+		cmd->base.duplex = DUPLEX_UNKNOWN;
 	}
 
-	ecmd->autoneg = ((hw->media_type == e1000_media_type_fiber) ||
+	cmd->base.autoneg = ((hw->media_type == e1000_media_type_fiber) ||
 			 hw->autoneg) ? AUTONEG_ENABLE : AUTONEG_DISABLE;
 
 	/* MDI-X => 1; MDI => 0 */
 	if ((hw->media_type == e1000_media_type_copper) &&
 	    netif_carrier_ok(netdev))
-		ecmd->eth_tp_mdix = (!!adapter->phy_info.mdix_mode ?
+		cmd->base.eth_tp_mdix = (!!adapter->phy_info.mdix_mode ?
 				     ETH_TP_MDI_X : ETH_TP_MDI);
 	else
-		ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID;
+		cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID;
 
 	if (hw->mdix == AUTO_ALL_MODES)
-		ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
+		cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
 	else
-		ecmd->eth_tp_mdix_ctrl = hw->mdix;
+		cmd->base.eth_tp_mdix_ctrl = hw->mdix;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
+
 	return 0;
 }
 
-static int e1000_set_settings(struct net_device *netdev,
-			      struct ethtool_cmd *ecmd)
+static int e1000_set_link_ksettings(struct net_device *netdev,
+				    const struct ethtool_link_ksettings *cmd)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
+	u32 advertising;
+
+	ethtool_convert_link_mode_to_legacy_u32(&advertising,
+						cmd->link_modes.advertising);
 
 	/* MDI setting is only allowed when autoneg enabled because
 	 * some hardware doesn't allow MDI setting when speed or
 	 * duplex is forced.
 	 */
-	if (ecmd->eth_tp_mdix_ctrl) {
+	if (cmd->base.eth_tp_mdix_ctrl) {
 		if (hw->media_type != e1000_media_type_copper)
 			return -EOPNOTSUPP;
 
-		if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
-		    (ecmd->autoneg != AUTONEG_ENABLE)) {
+		if ((cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
+		    (cmd->base.autoneg != AUTONEG_ENABLE)) {
 			e_err(drv, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
 			return -EINVAL;
 		}
@@ -209,32 +209,31 @@ static int e1000_set_settings(struct net_device *netdev,
 	while (test_and_set_bit(__E1000_RESETTING, &adapter->flags))
 		msleep(1);
 
-	if (ecmd->autoneg == AUTONEG_ENABLE) {
+	if (cmd->base.autoneg == AUTONEG_ENABLE) {
 		hw->autoneg = 1;
 		if (hw->media_type == e1000_media_type_fiber)
 			hw->autoneg_advertised = ADVERTISED_1000baseT_Full |
-				     ADVERTISED_FIBRE |
-				     ADVERTISED_Autoneg;
+						 ADVERTISED_FIBRE |
+						 ADVERTISED_Autoneg;
 		else
-			hw->autoneg_advertised = ecmd->advertising |
+			hw->autoneg_advertised = advertising |
 						 ADVERTISED_TP |
 						 ADVERTISED_Autoneg;
-		ecmd->advertising = hw->autoneg_advertised;
 	} else {
-		u32 speed = ethtool_cmd_speed(ecmd);
+		u32 speed = cmd->base.speed;
 		/* calling this overrides forced MDI setting */
-		if (e1000_set_spd_dplx(adapter, speed, ecmd->duplex)) {
+		if (e1000_set_spd_dplx(adapter, speed, cmd->base.duplex)) {
 			clear_bit(__E1000_RESETTING, &adapter->flags);
 			return -EINVAL;
 		}
 	}
 
 	/* MDI-X => 2; MDI => 1; Auto => 3 */
-	if (ecmd->eth_tp_mdix_ctrl) {
-		if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+	if (cmd->base.eth_tp_mdix_ctrl) {
+		if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
 			hw->mdix = AUTO_ALL_MODES;
 		else
-			hw->mdix = ecmd->eth_tp_mdix_ctrl;
+			hw->mdix = cmd->base.eth_tp_mdix_ctrl;
 	}
 
 	/* reset the link */
@@ -1875,8 +1874,6 @@ static void e1000_get_strings(struct net_device *netdev, u32 stringset,
 }
 
 static const struct ethtool_ops e1000_ethtool_ops = {
-	.get_settings		= e1000_get_settings,
-	.set_settings		= e1000_set_settings,
 	.get_drvinfo		= e1000_get_drvinfo,
 	.get_regs_len		= e1000_get_regs_len,
 	.get_regs		= e1000_get_regs,
@@ -1901,6 +1898,8 @@ static const struct ethtool_ops e1000_ethtool_ops = {
 	.get_coalesce		= e1000_get_coalesce,
 	.set_coalesce		= e1000_set_coalesce,
 	.get_ts_info		= ethtool_op_get_ts_info,
+	.get_link_ksettings	= e1000_get_link_ksettings,
+	.set_link_ksettings	= e1000_set_link_ksettings,
 };
 
 void e1000_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index 7aff68a4a4df..e70b1ebff60d 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -117,55 +117,52 @@ static const char e1000_gstrings_test[][ETH_GSTRING_LEN] = {
 
 #define E1000_TEST_LEN ARRAY_SIZE(e1000_gstrings_test)
 
-static int e1000_get_settings(struct net_device *netdev,
-			      struct ethtool_cmd *ecmd)
+static int e1000_get_link_ksettings(struct net_device *netdev,
+				    struct ethtool_link_ksettings *cmd)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
-	u32 speed;
+	u32 speed, supported, advertising;
 
 	if (hw->phy.media_type == e1000_media_type_copper) {
-		ecmd->supported = (SUPPORTED_10baseT_Half |
-				   SUPPORTED_10baseT_Full |
-				   SUPPORTED_100baseT_Half |
-				   SUPPORTED_100baseT_Full |
-				   SUPPORTED_1000baseT_Full |
-				   SUPPORTED_Autoneg |
-				   SUPPORTED_TP);
+		supported = (SUPPORTED_10baseT_Half |
+			     SUPPORTED_10baseT_Full |
+			     SUPPORTED_100baseT_Half |
+			     SUPPORTED_100baseT_Full |
+			     SUPPORTED_1000baseT_Full |
+			     SUPPORTED_Autoneg |
+			     SUPPORTED_TP);
 		if (hw->phy.type == e1000_phy_ife)
-			ecmd->supported &= ~SUPPORTED_1000baseT_Full;
-		ecmd->advertising = ADVERTISED_TP;
+			supported &= ~SUPPORTED_1000baseT_Full;
+		advertising = ADVERTISED_TP;
 
 		if (hw->mac.autoneg == 1) {
-			ecmd->advertising |= ADVERTISED_Autoneg;
+			advertising |= ADVERTISED_Autoneg;
 			/* the e1000 autoneg seems to match ethtool nicely */
-			ecmd->advertising |= hw->phy.autoneg_advertised;
+			advertising |= hw->phy.autoneg_advertised;
 		}
 
-		ecmd->port = PORT_TP;
-		ecmd->phy_address = hw->phy.addr;
-		ecmd->transceiver = XCVR_INTERNAL;
-
+		cmd->base.port = PORT_TP;
+		cmd->base.phy_address = hw->phy.addr;
 	} else {
-		ecmd->supported   = (SUPPORTED_1000baseT_Full |
-				     SUPPORTED_FIBRE |
-				     SUPPORTED_Autoneg);
+		supported   = (SUPPORTED_1000baseT_Full |
+			       SUPPORTED_FIBRE |
+			       SUPPORTED_Autoneg);
 
-		ecmd->advertising = (ADVERTISED_1000baseT_Full |
-				     ADVERTISED_FIBRE |
-				     ADVERTISED_Autoneg);
+		advertising = (ADVERTISED_1000baseT_Full |
+			       ADVERTISED_FIBRE |
+			       ADVERTISED_Autoneg);
 
-		ecmd->port = PORT_FIBRE;
-		ecmd->transceiver = XCVR_EXTERNAL;
+		cmd->base.port = PORT_FIBRE;
 	}
 
 	speed = SPEED_UNKNOWN;
-	ecmd->duplex = DUPLEX_UNKNOWN;
+	cmd->base.duplex = DUPLEX_UNKNOWN;
 
 	if (netif_running(netdev)) {
 		if (netif_carrier_ok(netdev)) {
 			speed = adapter->link_speed;
-			ecmd->duplex = adapter->link_duplex - 1;
+			cmd->base.duplex = adapter->link_duplex - 1;
 		}
 	} else if (!pm_runtime_suspended(netdev->dev.parent)) {
 		u32 status = er32(STATUS);
@@ -179,30 +176,36 @@ static int e1000_get_settings(struct net_device *netdev,
 				speed = SPEED_10;
 
 			if (status & E1000_STATUS_FD)
-				ecmd->duplex = DUPLEX_FULL;
+				cmd->base.duplex = DUPLEX_FULL;
 			else
-				ecmd->duplex = DUPLEX_HALF;
+				cmd->base.duplex = DUPLEX_HALF;
 		}
 	}
 
-	ethtool_cmd_speed_set(ecmd, speed);
-	ecmd->autoneg = ((hw->phy.media_type == e1000_media_type_fiber) ||
+	cmd->base.speed = speed;
+	cmd->base.autoneg = ((hw->phy.media_type == e1000_media_type_fiber) ||
 			 hw->mac.autoneg) ? AUTONEG_ENABLE : AUTONEG_DISABLE;
 
 	/* MDI-X => 2; MDI =>1; Invalid =>0 */
 	if ((hw->phy.media_type == e1000_media_type_copper) &&
 	    netif_carrier_ok(netdev))
-		ecmd->eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X : ETH_TP_MDI;
+		cmd->base.eth_tp_mdix = hw->phy.is_mdix ?
+			ETH_TP_MDI_X : ETH_TP_MDI;
 	else
-		ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID;
+		cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID;
 
 	if (hw->phy.mdix == AUTO_ALL_MODES)
-		ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
+		cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
 	else
-		ecmd->eth_tp_mdix_ctrl = hw->phy.mdix;
+		cmd->base.eth_tp_mdix_ctrl = hw->phy.mdix;
 
 	if (hw->phy.media_type != e1000_media_type_copper)
-		ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_INVALID;
+		cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_INVALID;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 
 	return 0;
 }
@@ -262,12 +265,16 @@ err_inval:
 	return -EINVAL;
 }
 
-static int e1000_set_settings(struct net_device *netdev,
-			      struct ethtool_cmd *ecmd)
+static int e1000_set_link_ksettings(struct net_device *netdev,
+				    const struct ethtool_link_ksettings *cmd)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
 	int ret_val = 0;
+	u32 advertising;
+
+	ethtool_convert_link_mode_to_legacy_u32(&advertising,
+						cmd->link_modes.advertising);
 
 	pm_runtime_get_sync(netdev->dev.parent);
 
@@ -285,14 +292,14 @@ static int e1000_set_settings(struct net_device *netdev,
 	 * some hardware doesn't allow MDI setting when speed or
 	 * duplex is forced.
 	 */
-	if (ecmd->eth_tp_mdix_ctrl) {
+	if (cmd->base.eth_tp_mdix_ctrl) {
 		if (hw->phy.media_type != e1000_media_type_copper) {
 			ret_val = -EOPNOTSUPP;
 			goto out;
 		}
 
-		if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
-		    (ecmd->autoneg != AUTONEG_ENABLE)) {
+		if ((cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
+		    (cmd->base.autoneg != AUTONEG_ENABLE)) {
 			e_err("forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
 			ret_val = -EINVAL;
 			goto out;
@@ -302,35 +309,35 @@ static int e1000_set_settings(struct net_device *netdev,
 	while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
 		usleep_range(1000, 2000);
 
-	if (ecmd->autoneg == AUTONEG_ENABLE) {
+	if (cmd->base.autoneg == AUTONEG_ENABLE) {
 		hw->mac.autoneg = 1;
 		if (hw->phy.media_type == e1000_media_type_fiber)
 			hw->phy.autoneg_advertised = ADVERTISED_1000baseT_Full |
 			    ADVERTISED_FIBRE | ADVERTISED_Autoneg;
 		else
-			hw->phy.autoneg_advertised = ecmd->advertising |
+			hw->phy.autoneg_advertised = advertising |
 			    ADVERTISED_TP | ADVERTISED_Autoneg;
-		ecmd->advertising = hw->phy.autoneg_advertised;
+		advertising = hw->phy.autoneg_advertised;
 		if (adapter->fc_autoneg)
 			hw->fc.requested_mode = e1000_fc_default;
 	} else {
-		u32 speed = ethtool_cmd_speed(ecmd);
+		u32 speed = cmd->base.speed;
 		/* calling this overrides forced MDI setting */
-		if (e1000_set_spd_dplx(adapter, speed, ecmd->duplex)) {
+		if (e1000_set_spd_dplx(adapter, speed, cmd->base.duplex)) {
 			ret_val = -EINVAL;
 			goto out;
 		}
 	}
 
 	/* MDI-X => 2; MDI => 1; Auto => 3 */
-	if (ecmd->eth_tp_mdix_ctrl) {
+	if (cmd->base.eth_tp_mdix_ctrl) {
 		/* fix up the value for auto (3 => 0) as zero is mapped
 		 * internally to auto
 		 */
-		if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+		if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
 			hw->phy.mdix = AUTO_ALL_MODES;
 		else
-			hw->phy.mdix = ecmd->eth_tp_mdix_ctrl;
+			hw->phy.mdix = cmd->base.eth_tp_mdix_ctrl;
 	}
 
 	/* reset the link */
@@ -2313,8 +2320,6 @@ static int e1000e_get_ts_info(struct net_device *netdev,
 }
 
 static const struct ethtool_ops e1000_ethtool_ops = {
-	.get_settings		= e1000_get_settings,
-	.set_settings		= e1000_set_settings,
 	.get_drvinfo		= e1000_get_drvinfo,
 	.get_regs_len		= e1000_get_regs_len,
 	.get_regs		= e1000_get_regs,
@@ -2342,6 +2347,8 @@ static const struct ethtool_ops e1000_ethtool_ops = {
 	.get_ts_info		= e1000e_get_ts_info,
 	.get_eee		= e1000e_get_eee,
 	.set_eee		= e1000e_set_eee,
+	.get_link_ksettings	= e1000_get_link_ksettings,
+	.set_link_ksettings	= e1000_set_link_ksettings,
 };
 
 void e1000e_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
index 01db688cf539..72481670478c 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -1226,7 +1226,9 @@ static int __fm10k_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
 	if (tc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
-	return fm10k_setup_tc(dev, tc->tc);
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+	return fm10k_setup_tc(dev, tc->mqprio->num_tc);
 }
 
 static void fm10k_assign_l2_accel(struct fm10k_intfc *interface,
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index e372a5823480..60d9b6aaf63a 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/interrupt.h>
 #include <linux/aer.h>
 
 #include "fm10k.h"
diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile
index 3b3c63e54ed6..4f454d364d0d 100644
--- a/drivers/net/ethernet/intel/i40e/Makefile
+++ b/drivers/net/ethernet/intel/i40e/Makefile
@@ -45,4 +45,3 @@ i40e-objs := i40e_main.o \
 	i40e_virtchnl_pf.o
 
 i40e-$(CONFIG_I40E_DCB) += i40e_dcb.o i40e_dcb_nl.o
-i40e-$(CONFIG_I40E_FCOE) += i40e_fcoe.o
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 82d8040fa418..421ea57128d3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -56,9 +56,6 @@
 #include <linux/ptp_clock_kernel.h>
 #include "i40e_type.h"
 #include "i40e_prototype.h"
-#ifdef I40E_FCOE
-#include "i40e_fcoe.h"
-#endif
 #include "i40e_client.h"
 #include "i40e_virtchnl.h"
 #include "i40e_virtchnl_pf.h"
@@ -85,10 +82,6 @@
 		(((pf)->flags & I40E_FLAG_128_QP_RSS_CAPABLE) ? 128 : 64)
 #define I40E_FDIR_RING			0
 #define I40E_FDIR_RING_COUNT		32
-#ifdef I40E_FCOE
-#define I40E_DEFAULT_FCOE		8 /* default number of QPs for FCoE */
-#define I40E_MINIMUM_FCOE		1 /* minimum number of QPs for FCoE */
-#endif /* I40E_FCOE */
 #define I40E_MAX_AQ_BUF_SIZE		4096
 #define I40E_AQ_LEN			256
 #define I40E_AQ_WORK_LIMIT		66 /* max number of VFs + a little */
@@ -98,14 +91,6 @@
 #define I40E_QUEUE_WAIT_RETRY_LIMIT	10
 #define I40E_INT_NAME_STR_LEN		(IFNAMSIZ + 16)
 
-/* Ethtool Private Flags */
-#define I40E_PRIV_FLAGS_MFP_FLAG		BIT(0)
-#define I40E_PRIV_FLAGS_LINKPOLL_FLAG		BIT(1)
-#define I40E_PRIV_FLAGS_FD_ATR			BIT(2)
-#define I40E_PRIV_FLAGS_VEB_STATS		BIT(3)
-#define I40E_PRIV_FLAGS_HW_ATR_EVICT		BIT(4)
-#define I40E_PRIV_FLAGS_TRUE_PROMISC_SUPPORT	BIT(5)
-
 #define I40E_NVM_VERSION_LO_SHIFT	0
 #define I40E_NVM_VERSION_LO_MASK	(0xff << I40E_NVM_VERSION_LO_SHIFT)
 #define I40E_NVM_VERSION_HI_SHIFT	12
@@ -202,17 +187,32 @@ enum i40e_fd_stat_idx {
 #define I40E_FD_ATR_TUNNEL_STAT_IDX(pf_id) \
 			(I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_ATR_TUNNEL)
 
+/* The following structure contains the data parsed from the user-defined
+ * field of the ethtool_rx_flow_spec structure.
+ */
+struct i40e_rx_flow_userdef {
+	bool flex_filter;
+	u16 flex_word;
+	u16 flex_offset;
+};
+
 struct i40e_fdir_filter {
 	struct hlist_node fdir_node;
 	/* filter ipnut set */
 	u8 flow_type;
 	u8 ip4_proto;
 	/* TX packet view of src and dst */
-	__be32 dst_ip[4];
-	__be32 src_ip[4];
+	__be32 dst_ip;
+	__be32 src_ip;
 	__be16 src_port;
 	__be16 dst_port;
 	__be32 sctp_v_tag;
+
+	/* Flexible data to match within the packet payload */
+	__be16 flex_word;
+	u16 flex_offset;
+	bool flex_filter;
+
 	/* filter control */
 	u16 q_index;
 	u8  flex_off;
@@ -244,10 +244,80 @@ struct i40e_tc_configuration {
 };
 
 struct i40e_udp_port_config {
-	__be16 index;
+	/* AdminQ command interface expects port number in Host byte order */
+	u16 index;
 	u8 type;
 };
 
+/* macros related to FLX_PIT */
+#define I40E_FLEX_SET_FSIZE(fsize) (((fsize) << \
+				    I40E_PRTQF_FLX_PIT_FSIZE_SHIFT) & \
+				    I40E_PRTQF_FLX_PIT_FSIZE_MASK)
+#define I40E_FLEX_SET_DST_WORD(dst) (((dst) << \
+				     I40E_PRTQF_FLX_PIT_DEST_OFF_SHIFT) & \
+				     I40E_PRTQF_FLX_PIT_DEST_OFF_MASK)
+#define I40E_FLEX_SET_SRC_WORD(src) (((src) << \
+				     I40E_PRTQF_FLX_PIT_SOURCE_OFF_SHIFT) & \
+				     I40E_PRTQF_FLX_PIT_SOURCE_OFF_MASK)
+#define I40E_FLEX_PREP_VAL(dst, fsize, src) (I40E_FLEX_SET_DST_WORD(dst) | \
+					     I40E_FLEX_SET_FSIZE(fsize) | \
+					     I40E_FLEX_SET_SRC_WORD(src))
+
+#define I40E_FLEX_PIT_GET_SRC(flex) (((flex) & \
+				     I40E_PRTQF_FLX_PIT_SOURCE_OFF_MASK) >> \
+				     I40E_PRTQF_FLX_PIT_SOURCE_OFF_SHIFT)
+#define I40E_FLEX_PIT_GET_DST(flex) (((flex) & \
+				     I40E_PRTQF_FLX_PIT_DEST_OFF_MASK) >> \
+				     I40E_PRTQF_FLX_PIT_DEST_OFF_SHIFT)
+#define I40E_FLEX_PIT_GET_FSIZE(flex) (((flex) & \
+				       I40E_PRTQF_FLX_PIT_FSIZE_MASK) >> \
+				       I40E_PRTQF_FLX_PIT_FSIZE_SHIFT)
+
+#define I40E_MAX_FLEX_SRC_OFFSET 0x1F
+
+/* macros related to GLQF_ORT */
+#define I40E_ORT_SET_IDX(idx)		(((idx) << \
+					  I40E_GLQF_ORT_PIT_INDX_SHIFT) & \
+					 I40E_GLQF_ORT_PIT_INDX_MASK)
+
+#define I40E_ORT_SET_COUNT(count)	(((count) << \
+					  I40E_GLQF_ORT_FIELD_CNT_SHIFT) & \
+					 I40E_GLQF_ORT_FIELD_CNT_MASK)
+
+#define I40E_ORT_SET_PAYLOAD(payload)	(((payload) << \
+					  I40E_GLQF_ORT_FLX_PAYLOAD_SHIFT) & \
+					 I40E_GLQF_ORT_FLX_PAYLOAD_MASK)
+
+#define I40E_ORT_PREP_VAL(idx, count, payload) (I40E_ORT_SET_IDX(idx) | \
+						I40E_ORT_SET_COUNT(count) | \
+						I40E_ORT_SET_PAYLOAD(payload))
+
+#define I40E_L3_GLQF_ORT_IDX		34
+#define I40E_L4_GLQF_ORT_IDX		35
+
+/* Flex PIT register index */
+#define I40E_FLEX_PIT_IDX_START_L2	0
+#define I40E_FLEX_PIT_IDX_START_L3	3
+#define I40E_FLEX_PIT_IDX_START_L4	6
+
+#define I40E_FLEX_PIT_TABLE_SIZE	3
+
+#define I40E_FLEX_DEST_UNUSED		63
+
+#define I40E_FLEX_INDEX_ENTRIES		8
+
+/* Flex MASK to disable all flexible entries */
+#define I40E_FLEX_INPUT_MASK	(I40E_FLEX_50_MASK | I40E_FLEX_51_MASK | \
+				 I40E_FLEX_52_MASK | I40E_FLEX_53_MASK | \
+				 I40E_FLEX_54_MASK | I40E_FLEX_55_MASK | \
+				 I40E_FLEX_56_MASK | I40E_FLEX_57_MASK)
+
+struct i40e_flex_pit {
+	struct list_head list;
+	u16 src_offset;
+	u8 pit_index;
+};
+
 /* struct that defines the Ethernet device */
 struct i40e_pf {
 	struct pci_dev *pdev;
@@ -262,10 +332,6 @@ struct i40e_pf {
 	u16 num_vmdq_msix;         /* num queue vectors per vmdq pool */
 	u16 num_req_vfs;           /* num VFs requested for this VF */
 	u16 num_vf_qps;            /* num queue pairs per VF */
-#ifdef I40E_FCOE
-	u16 num_fcoe_qps;          /* num fcoe queues this PF has set up */
-	u16 num_fcoe_msix;         /* num queue vectors per fcoe pool */
-#endif /* I40E_FCOE */
 	u16 num_lan_qps;           /* num lan queues this PF has set up */
 	u16 num_lan_msix;          /* num queue vectors for the base PF vsi */
 	u16 num_fdsb_msix;         /* num queue vectors for sideband Fdir */
@@ -285,7 +351,23 @@ struct i40e_pf {
 	u32 fd_flush_cnt;
 	u32 fd_add_err;
 	u32 fd_atr_cnt;
-	u32 fd_tcp_rule;
+
+	/* Book-keeping of side-band filter count per flow-type.
+	 * This is used to detect and handle input set changes for
+	 * respective flow-type.
+	 */
+	u16 fd_tcp4_filter_cnt;
+	u16 fd_udp4_filter_cnt;
+	u16 fd_sctp4_filter_cnt;
+	u16 fd_ip4_filter_cnt;
+
+	/* Flexible filter table values that need to be programmed into
+	 * hardware, which expects L3 and L4 to be programmed separately. We
+	 * need to ensure that the values are in ascended order and don't have
+	 * duplicates, so we track each L3 and L4 values in separate lists.
+	 */
+	struct list_head l3_flex_pit_list;
+	struct list_head l4_flex_pit_list;
 
 	struct i40e_udp_port_config udp_ports[I40E_MAX_PF_UDP_OFFLOAD_PORTS];
 	u16 pending_udp_bitmap;
@@ -307,12 +389,8 @@ struct i40e_pf {
 #define I40E_FLAG_MSIX_ENABLED			BIT_ULL(3)
 #define I40E_FLAG_RSS_ENABLED			BIT_ULL(6)
 #define I40E_FLAG_VMDQ_ENABLED			BIT_ULL(7)
-#define I40E_FLAG_FDIR_REQUIRES_REINIT		BIT_ULL(8)
 #define I40E_FLAG_NEED_LINK_UPDATE		BIT_ULL(9)
 #define I40E_FLAG_IWARP_ENABLED			BIT_ULL(10)
-#ifdef I40E_FCOE
-#define I40E_FLAG_FCOE_ENABLED			BIT_ULL(11)
-#endif /* I40E_FCOE */
 #define I40E_FLAG_CLEAN_ADMINQ			BIT_ULL(14)
 #define I40E_FLAG_FILTER_SYNC			BIT_ULL(15)
 #define I40E_FLAG_SERVICE_CLIENT_REQUESTED	BIT_ULL(16)
@@ -348,16 +426,20 @@ struct i40e_pf {
 #define I40E_FLAG_TRUE_PROMISC_SUPPORT		BIT_ULL(51)
 #define I40E_FLAG_HAVE_CRT_RETIMER		BIT_ULL(52)
 #define I40E_FLAG_PTP_L4_CAPABLE		BIT_ULL(53)
-#define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE		BIT_ULL(54)
+#define I40E_FLAG_CLIENT_RESET			BIT_ULL(54)
 #define I40E_FLAG_TEMP_LINK_POLLING		BIT_ULL(55)
+#define I40E_FLAG_CLIENT_L2_CHANGE		BIT_ULL(56)
+#define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE		BIT_ULL(57)
+#define I40E_FLAG_LEGACY_RX			BIT_ULL(58)
+
+	/* Tracks features that are disabled due to hw limitations.
+	 * If a bit is set here, it means that the corresponding
+	 * bit in the 'flags' field is cleared i.e that feature
+	 * is disabled
+	 */
+	u64 hw_disabled_flags;
 
-	/* tracks features that get auto disabled by errors */
-	u64 auto_disable_flags;
-
-#ifdef I40E_FCOE
-	struct i40e_fcoe fcoe;
-
-#endif /* I40E_FCOE */
+	struct i40e_client_instance *cinst;
 	bool stat_offsets_loaded;
 	struct i40e_hw_port_stats stats;
 	struct i40e_hw_port_stats stats_offsets;
@@ -412,8 +494,6 @@ struct i40e_pf {
 	 */
 	u16 dcbx_cap;
 
-	u32 fcoe_hmc_filt_num;
-	u32 fcoe_hmc_cntx_num;
 	struct i40e_filter_control_settings filter_settings;
 
 	struct ptp_clock *ptp_clock;
@@ -533,11 +613,6 @@ struct i40e_vsi {
 	struct rtnl_link_stats64 net_stats_offsets;
 	struct i40e_eth_stats eth_stats;
 	struct i40e_eth_stats eth_stats_offsets;
-#ifdef I40E_FCOE
-	struct i40e_fcoe_stats fcoe_stats;
-	struct i40e_fcoe_stats fcoe_stats_offsets;
-	bool fcoe_stat_offsets_loaded;
-#endif
 	u32 tx_restart;
 	u32 tx_busy;
 	u64 tx_linearize;
@@ -719,6 +794,43 @@ static inline int i40e_get_fd_cnt_all(struct i40e_pf *pf)
 	return pf->hw.fdir_shared_filter_count + pf->fdir_pf_filter_count;
 }
 
+/**
+ * i40e_read_fd_input_set - reads value of flow director input set register
+ * @pf: pointer to the PF struct
+ * @addr: register addr
+ *
+ * This function reads value of flow director input set register
+ * specified by 'addr' (which is specific to flow-type)
+ **/
+static inline u64 i40e_read_fd_input_set(struct i40e_pf *pf, u16 addr)
+{
+	u64 val;
+
+	val = i40e_read_rx_ctl(&pf->hw, I40E_PRTQF_FD_INSET(addr, 1));
+	val <<= 32;
+	val += i40e_read_rx_ctl(&pf->hw, I40E_PRTQF_FD_INSET(addr, 0));
+
+	return val;
+}
+
+/**
+ * i40e_write_fd_input_set - writes value into flow director input set register
+ * @pf: pointer to the PF struct
+ * @addr: register addr
+ * @val: value to be written
+ *
+ * This function writes specified value to the register specified by 'addr'.
+ * This register is input set register based on flow-type.
+ **/
+static inline void i40e_write_fd_input_set(struct i40e_pf *pf,
+					   u16 addr, u64 val)
+{
+	i40e_write_rx_ctl(&pf->hw, I40E_PRTQF_FD_INSET(addr, 1),
+			  (u32)(val >> 32));
+	i40e_write_rx_ctl(&pf->hw, I40E_PRTQF_FD_INSET(addr, 0),
+			  (u32)(val & 0xFFFFFFFFULL));
+}
+
 /* needed by i40e_ethtool.c */
 int i40e_up(struct i40e_vsi *vsi);
 void i40e_down(struct i40e_vsi *vsi);
@@ -773,11 +885,6 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi);
 struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 				u16 uplink, u32 param1);
 int i40e_vsi_release(struct i40e_vsi *vsi);
-#ifdef I40E_FCOE
-void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
-			      struct i40e_vsi_context *ctxt,
-			      u8 enabled_tc, bool is_add);
-#endif
 void i40e_service_event_schedule(struct i40e_pf *pf);
 void i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id,
 				  u8 *msg, u16 len);
@@ -813,8 +920,7 @@ void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi);
 void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset);
 void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs);
 void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id);
-int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id,
-			   enum i40e_client_type type);
+int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id);
 /**
  * i40e_irq_dynamic_enable - Enable default interrupt generation settings
  * @vsi: pointer to a vsi
@@ -838,20 +944,7 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector)
 
 void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf);
 void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba);
-#ifdef I40E_FCOE
-void i40e_get_netdev_stats_struct(struct net_device *netdev,
-				  struct rtnl_link_stats64 *storage);
-int i40e_set_mac(struct net_device *netdev, void *p);
-void i40e_set_rx_mode(struct net_device *netdev);
-#endif
 int i40e_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd);
-#ifdef I40E_FCOE
-void i40e_tx_timeout(struct net_device *netdev);
-int i40e_vlan_rx_add_vid(struct net_device *netdev,
-			 __always_unused __be16 proto, u16 vid);
-int i40e_vlan_rx_kill_vid(struct net_device *netdev,
-			  __always_unused __be16 proto, u16 vid);
-#endif
 int i40e_open(struct net_device *netdev);
 int i40e_close(struct net_device *netdev);
 int i40e_vsi_open(struct i40e_vsi *vsi);
@@ -865,25 +958,6 @@ struct i40e_mac_filter *i40e_add_mac_filter(struct i40e_vsi *vsi,
 int i40e_del_mac_filter(struct i40e_vsi *vsi, const u8 *macaddr);
 bool i40e_is_vsi_in_vlan(struct i40e_vsi *vsi);
 struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, const u8 *macaddr);
-#ifdef I40E_FCOE
-int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
-		    struct tc_to_netdev *tc);
-void i40e_netpoll(struct net_device *netdev);
-int i40e_fcoe_enable(struct net_device *netdev);
-int i40e_fcoe_disable(struct net_device *netdev);
-int i40e_fcoe_vsi_init(struct i40e_vsi *vsi, struct i40e_vsi_context *ctxt);
-u8 i40e_get_fcoe_tc_map(struct i40e_pf *pf);
-void i40e_fcoe_config_netdev(struct net_device *netdev, struct i40e_vsi *vsi);
-void i40e_fcoe_vsi_setup(struct i40e_pf *pf);
-void i40e_init_pf_fcoe(struct i40e_pf *pf);
-int i40e_fcoe_setup_ddp_resources(struct i40e_vsi *vsi);
-void i40e_fcoe_free_ddp_resources(struct i40e_vsi *vsi);
-int i40e_fcoe_handle_offload(struct i40e_ring *rx_ring,
-			     union i40e_rx_desc *rx_desc,
-			     struct sk_buff *skb);
-void i40e_fcoe_handle_status(struct i40e_ring *rx_ring,
-			     union i40e_rx_desc *rx_desc, u8 prog_id);
-#endif /* I40E_FCOE */
 void i40e_vlan_stripping_enable(struct i40e_vsi *vsi);
 #ifdef CONFIG_I40E_DCB
 void i40e_dcbnl_flush_apps(struct i40e_pf *pf,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 451f48b7540a..251074c677c4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -132,6 +132,10 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_list_func_capabilities	= 0x000A,
 	i40e_aqc_opc_list_dev_capabilities	= 0x000B,
 
+	/* Proxy commands */
+	i40e_aqc_opc_set_proxy_config		= 0x0104,
+	i40e_aqc_opc_set_ns_proxy_table_entry	= 0x0105,
+
 	/* LAA */
 	i40e_aqc_opc_mac_address_read	= 0x0107,
 	i40e_aqc_opc_mac_address_write	= 0x0108,
@@ -139,6 +143,10 @@ enum i40e_admin_queue_opc {
 	/* PXE */
 	i40e_aqc_opc_clear_pxe_mode	= 0x0110,
 
+	/* WoL commands */
+	i40e_aqc_opc_set_wol_filter	= 0x0120,
+	i40e_aqc_opc_get_wake_reason	= 0x0121,
+
 	/* internal switch commands */
 	i40e_aqc_opc_get_switch_config		= 0x0200,
 	i40e_aqc_opc_add_statistics		= 0x0201,
@@ -177,6 +185,7 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_remove_control_packet_filter	= 0x025B,
 	i40e_aqc_opc_add_cloud_filters		= 0x025C,
 	i40e_aqc_opc_remove_cloud_filters	= 0x025D,
+	i40e_aqc_opc_clear_wol_switch_filters	= 0x025E,
 
 	i40e_aqc_opc_add_mirror_rule	= 0x0260,
 	i40e_aqc_opc_delete_mirror_rule	= 0x0261,
@@ -563,6 +572,56 @@ struct i40e_aqc_clear_pxe {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe);
 
+/* Set WoL Filter (0x0120) */
+
+struct i40e_aqc_set_wol_filter {
+	__le16 filter_index;
+#define I40E_AQC_MAX_NUM_WOL_FILTERS	8
+#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT	15
+#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK	(0x1 << \
+		I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT)
+
+#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT		0
+#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK	(0x7 << \
+		I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT)
+	__le16 cmd_flags;
+#define I40E_AQC_SET_WOL_FILTER				0x8000
+#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL		0x4000
+#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR		0
+#define I40E_AQC_SET_WOL_FILTER_ACTION_SET		1
+	__le16 valid_flags;
+#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID		0x8000
+#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID	0x4000
+	u8 reserved[2];
+	__le32	address_high;
+	__le32	address_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter);
+
+struct i40e_aqc_set_wol_filter_data {
+	u8 filter[128];
+	u8 mask[16];
+};
+
+I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data);
+
+/* Get Wake Reason (0x0121) */
+
+struct i40e_aqc_get_wake_reason_completion {
+	u8 reserved_1[2];
+	__le16 wake_reason;
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT	0
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \
+		I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT)
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT	8
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK	(0xFF << \
+		I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT)
+	u8 reserved_2[12];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion);
+
 /* Switch configuration commands (0x02xx) */
 
 /* Used by many indirect commands that only pass an seid and a buffer in the
@@ -645,6 +704,8 @@ struct i40e_aqc_set_port_parameters {
 #define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS	2 /* must set! */
 #define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA	4
 	__le16	bad_frame_vsi;
+#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT	0x0
+#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK	0x3FF
 	__le16	default_seid;        /* reserved for command */
 	u8	reserved[10];
 };
@@ -696,6 +757,7 @@ I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp);
 /* Set Switch Configuration (direct 0x0205) */
 struct i40e_aqc_set_switch_config {
 	__le16	flags;
+/* flags used for both fields below */
 #define I40E_AQ_SET_SWITCH_CFG_PROMISC		0x0001
 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER	0x0002
 	__le16	valid_flags;
@@ -1844,11 +1906,12 @@ struct i40e_aqc_get_link_status {
 #define I40E_AQ_CONFIG_FEC_RS_ENA	0x02
 #define I40E_AQ_CONFIG_CRC_ENA		0x04
 #define I40E_AQ_CONFIG_PACING_MASK	0x78
-	u8	external_power_ability;
+	u8	power_desc;
 #define I40E_AQ_LINK_POWER_CLASS_1	0x00
 #define I40E_AQ_LINK_POWER_CLASS_2	0x01
 #define I40E_AQ_LINK_POWER_CLASS_3	0x02
 #define I40E_AQ_LINK_POWER_CLASS_4	0x03
+#define I40E_AQ_PWR_CLASS_MASK		0x03
 	u8	reserved[4];
 };
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index d570219efd9f..191028b1489b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -32,16 +32,10 @@
 #include "i40e_client.h"
 
 static const char i40e_client_interface_version_str[] = I40E_CLIENT_VERSION_STR;
-
+static struct i40e_client *registered_client;
 static LIST_HEAD(i40e_devices);
 static DEFINE_MUTEX(i40e_device_mutex);
 
-static LIST_HEAD(i40e_clients);
-static DEFINE_MUTEX(i40e_client_mutex);
-
-static LIST_HEAD(i40e_client_instances);
-static DEFINE_MUTEX(i40e_client_instance_mutex);
-
 static int i40e_client_virtchnl_send(struct i40e_info *ldev,
 				     struct i40e_client *client,
 				     u32 vf_id, u8 *msg, u16 len);
@@ -67,28 +61,6 @@ static struct i40e_ops i40e_lan_ops = {
 };
 
 /**
- * i40e_client_type_to_vsi_type - convert client type to vsi type
- * @client_type: the i40e_client type
- *
- * returns the related vsi type value
- **/
-static
-enum i40e_vsi_type i40e_client_type_to_vsi_type(enum i40e_client_type type)
-{
-	switch (type) {
-	case I40E_CLIENT_IWARP:
-		return I40E_VSI_IWARP;
-
-	case I40E_CLIENT_VMDQ2:
-		return I40E_VSI_VMDQ2;
-
-	default:
-		pr_err("i40e: Client type unknown\n");
-		return I40E_VSI_TYPE_UNKNOWN;
-	}
-}
-
-/**
  * i40e_client_get_params - Get the params that can change at runtime
  * @vsi: the VSI with the message
  * @param: clinet param struct
@@ -134,31 +106,22 @@ int i40e_client_get_params(struct i40e_vsi *vsi, struct i40e_params *params)
 void
 i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len)
 {
-	struct i40e_client_instance *cdev;
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_client_instance *cdev = pf->cinst;
 
-	if (!vsi)
+	if (!cdev || !cdev->client)
+		return;
+	if (!cdev->client->ops || !cdev->client->ops->virtchnl_receive) {
+		dev_dbg(&pf->pdev->dev,
+			"Cannot locate client instance virtual channel receive routine\n");
+		return;
+	}
+	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
+		dev_dbg(&pf->pdev->dev, "Client is not open, abort virtchnl_receive\n");
 		return;
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry(cdev, &i40e_client_instances, list) {
-		if (cdev->lan_info.pf == vsi->back) {
-			if (!cdev->client ||
-			    !cdev->client->ops ||
-			    !cdev->client->ops->virtchnl_receive) {
-				dev_dbg(&vsi->back->pdev->dev,
-					"Cannot locate client instance virtual channel receive routine\n");
-				continue;
-			}
-			if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
-				      &cdev->state)) {
-				dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort virtchnl_receive\n");
-				continue;
-			}
-			cdev->client->ops->virtchnl_receive(&cdev->lan_info,
-							    cdev->client,
-							    vf_id, msg, len);
-		}
 	}
-	mutex_unlock(&i40e_client_instance_mutex);
+	cdev->client->ops->virtchnl_receive(&cdev->lan_info, cdev->client,
+					    vf_id, msg, len);
 }
 
 /**
@@ -169,39 +132,30 @@ i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len)
  **/
 void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi)
 {
-	struct i40e_client_instance *cdev;
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_client_instance *cdev = pf->cinst;
 	struct i40e_params params;
 
-	if (!vsi)
+	if (!cdev || !cdev->client)
 		return;
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry(cdev, &i40e_client_instances, list) {
-		if (cdev->lan_info.pf == vsi->back) {
-			if (!cdev->client ||
-			    !cdev->client->ops ||
-			    !cdev->client->ops->l2_param_change) {
-				dev_dbg(&vsi->back->pdev->dev,
-					"Cannot locate client instance l2_param_change routine\n");
-				continue;
-			}
+	if (!cdev->client->ops || !cdev->client->ops->l2_param_change) {
+		dev_dbg(&vsi->back->pdev->dev,
+			"Cannot locate client instance l2_param_change routine\n");
+		return;
+	}
+	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
+		dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort l2 param change\n");
+		return;
+	}
 	memset(&params, 0, sizeof(params));
 	i40e_client_get_params(vsi, &params);
-			if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
-				      &cdev->state)) {
-				dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort l2 param change\n");
-				continue;
-			}
-			cdev->lan_info.params = params;
-			cdev->client->ops->l2_param_change(&cdev->lan_info,
-							   cdev->client,
-							   &params);
-		}
-	}
-	mutex_unlock(&i40e_client_instance_mutex);
+	memcpy(&cdev->lan_info.params, &params, sizeof(struct i40e_params));
+	cdev->client->ops->l2_param_change(&cdev->lan_info, cdev->client,
+					   &params);
 }
 
 /**
- * i40e_client_release_qvlist
+ * i40e_client_release_qvlist - release MSI-X vector mapping for client
  * @ldev: pointer to L2 context.
  *
  **/
@@ -237,26 +191,19 @@ static void i40e_client_release_qvlist(struct i40e_info *ldev)
  **/
 void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset)
 {
-	struct i40e_client_instance *cdev;
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_client_instance *cdev = pf->cinst;
 
-	if (!vsi)
+	if (!cdev || !cdev->client)
+		return;
+	if (!cdev->client->ops || !cdev->client->ops->close) {
+		dev_dbg(&vsi->back->pdev->dev,
+			"Cannot locate client instance close routine\n");
 		return;
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry(cdev, &i40e_client_instances, list) {
-		if (cdev->lan_info.netdev == vsi->netdev) {
-			if (!cdev->client ||
-			    !cdev->client->ops || !cdev->client->ops->close) {
-				dev_dbg(&vsi->back->pdev->dev,
-					"Cannot locate client instance close routine\n");
-				continue;
-			}
-			cdev->client->ops->close(&cdev->lan_info, cdev->client,
-						 reset);
-			clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
-			i40e_client_release_qvlist(&cdev->lan_info);
-		}
 	}
-	mutex_unlock(&i40e_client_instance_mutex);
+	cdev->client->ops->close(&cdev->lan_info, cdev->client, reset);
+	clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
+	i40e_client_release_qvlist(&cdev->lan_info);
 }
 
 /**
@@ -268,30 +215,20 @@ void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset)
  **/
 void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id)
 {
-	struct i40e_client_instance *cdev;
+	struct i40e_client_instance *cdev = pf->cinst;
 
-	if (!pf)
+	if (!cdev || !cdev->client)
+		return;
+	if (!cdev->client->ops || !cdev->client->ops->vf_reset) {
+		dev_dbg(&pf->pdev->dev,
+			"Cannot locate client instance VF reset routine\n");
 		return;
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry(cdev, &i40e_client_instances, list) {
-		if (cdev->lan_info.pf == pf) {
-			if (!cdev->client ||
-			    !cdev->client->ops ||
-			    !cdev->client->ops->vf_reset) {
-				dev_dbg(&pf->pdev->dev,
-					"Cannot locate client instance VF reset routine\n");
-				continue;
-			}
-			if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
-				      &cdev->state)) {
-				dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-reset\n");
-				continue;
-			}
-			cdev->client->ops->vf_reset(&cdev->lan_info,
-						    cdev->client, vf_id);
-		}
 	}
-	mutex_unlock(&i40e_client_instance_mutex);
+	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,  &cdev->state)) {
+		dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-reset\n");
+		return;
+	}
+	cdev->client->ops->vf_reset(&cdev->lan_info, cdev->client, vf_id);
 }
 
 /**
@@ -303,30 +240,21 @@ void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id)
  **/
 void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs)
 {
-	struct i40e_client_instance *cdev;
+	struct i40e_client_instance *cdev = pf->cinst;
 
-	if (!pf)
+	if (!cdev || !cdev->client)
+		return;
+	if (!cdev->client->ops || !cdev->client->ops->vf_enable) {
+		dev_dbg(&pf->pdev->dev,
+			"Cannot locate client instance VF enable routine\n");
+		return;
+	}
+	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
+		      &cdev->state)) {
+		dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-enable\n");
 		return;
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry(cdev, &i40e_client_instances, list) {
-		if (cdev->lan_info.pf == pf) {
-			if (!cdev->client ||
-			    !cdev->client->ops ||
-			    !cdev->client->ops->vf_enable) {
-				dev_dbg(&pf->pdev->dev,
-					"Cannot locate client instance VF enable routine\n");
-				continue;
-			}
-			if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
-				      &cdev->state)) {
-				dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-enable\n");
-				continue;
-			}
-			cdev->client->ops->vf_enable(&cdev->lan_info,
-						     cdev->client, num_vfs);
-		}
 	}
-	mutex_unlock(&i40e_client_instance_mutex);
+	cdev->client->ops->vf_enable(&cdev->lan_info, cdev->client, num_vfs);
 }
 
 /**
@@ -337,37 +265,25 @@ void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs)
  * If there is a client of the specified type attached to this PF, call
  * its vf_capable routine
  **/
-int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id,
-			   enum i40e_client_type type)
+int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id)
 {
-	struct i40e_client_instance *cdev;
+	struct i40e_client_instance *cdev = pf->cinst;
 	int capable = false;
 
-	if (!pf)
-		return false;
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry(cdev, &i40e_client_instances, list) {
-		if (cdev->lan_info.pf == pf) {
-			if (!cdev->client ||
-			    !cdev->client->ops ||
-			    !cdev->client->ops->vf_capable ||
-			    !(cdev->client->type == type)) {
-				dev_dbg(&pf->pdev->dev,
-					"Cannot locate client instance VF capability routine\n");
-				continue;
-			}
-			if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
-				      &cdev->state)) {
-				dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-capable\n");
-				continue;
-			}
-			capable = cdev->client->ops->vf_capable(&cdev->lan_info,
-								cdev->client,
-								vf_id);
-			break;
-		}
+	if (!cdev || !cdev->client)
+		goto out;
+	if (!cdev->client->ops || !cdev->client->ops->vf_capable) {
+		dev_info(&pf->pdev->dev,
+			 "Cannot locate client instance VF capability routine\n");
+		goto out;
 	}
-	mutex_unlock(&i40e_client_instance_mutex);
+	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state))
+		goto out;
+
+	capable = cdev->client->ops->vf_capable(&cdev->lan_info,
+						cdev->client,
+						vf_id);
+out:
 	return capable;
 }
 
@@ -377,27 +293,19 @@ int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id,
  * @client: pointer to a client struct in the client list.
  * @existing: if there was already an existing instance
  *
- * Returns cdev ptr on success or if already exists, NULL on failure
  **/
-static
-struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf,
-						     struct i40e_client *client,
-						     bool *existing)
+static void i40e_client_add_instance(struct i40e_pf *pf)
 {
-	struct i40e_client_instance *cdev;
+	struct i40e_client_instance *cdev = NULL;
 	struct netdev_hw_addr *mac = NULL;
 	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry(cdev, &i40e_client_instances, list) {
-		if ((cdev->lan_info.pf == pf) && (cdev->client == client)) {
-			*existing = true;
-			goto out;
-		}
-	}
+	if (!registered_client || pf->cinst)
+		return;
+
 	cdev = kzalloc(sizeof(*cdev), GFP_KERNEL);
 	if (!cdev)
-		goto out;
+		return;
 
 	cdev->lan_info.pf = (void *)pf;
 	cdev->lan_info.netdev = vsi->netdev;
@@ -417,7 +325,7 @@ struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf,
 	if (i40e_client_get_params(vsi, &cdev->lan_info.params)) {
 		kfree(cdev);
 		cdev = NULL;
-		goto out;
+		return;
 	}
 
 	cdev->lan_info.msix_count = pf->num_iwarp_msix;
@@ -430,41 +338,20 @@ struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf,
 	else
 		dev_err(&pf->pdev->dev, "MAC address list is empty!\n");
 
-	cdev->client = client;
-	INIT_LIST_HEAD(&cdev->list);
-	list_add(&cdev->list, &i40e_client_instances);
-out:
-	mutex_unlock(&i40e_client_instance_mutex);
-	return cdev;
+	cdev->client = registered_client;
+	pf->cinst = cdev;
 }
 
 /**
  * i40e_client_del_instance - removes a client instance from the list
  * @pf: pointer to the board struct
  *
- * Returns 0 on success or non-0 on error
  **/
 static
-int i40e_client_del_instance(struct i40e_pf *pf, struct i40e_client *client)
+void i40e_client_del_instance(struct i40e_pf *pf)
 {
-	struct i40e_client_instance *cdev, *tmp;
-	int ret = -ENODEV;
-
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry_safe(cdev, tmp, &i40e_client_instances, list) {
-		if ((cdev->lan_info.pf != pf) || (cdev->client != client))
-			continue;
-
-		dev_info(&pf->pdev->dev, "Deleted instance of Client %s, of dev %d bus=0x%02x func=0x%02x)\n",
-			 client->name, pf->hw.pf_id,
-			 pf->hw.bus.device, pf->hw.bus.func);
-		list_del(&cdev->list);
-		kfree(cdev);
-		ret = 0;
-		break;
-	}
-	mutex_unlock(&i40e_client_instance_mutex);
-	return ret;
+	kfree(pf->cinst);
+	pf->cinst = NULL;
 }
 
 /**
@@ -473,67 +360,50 @@ int i40e_client_del_instance(struct i40e_pf *pf, struct i40e_client *client)
  **/
 void i40e_client_subtask(struct i40e_pf *pf)
 {
+	struct i40e_client *client = registered_client;
 	struct i40e_client_instance *cdev;
-	struct i40e_client *client;
-	bool existing = false;
+	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 	int ret = 0;
 
 	if (!(pf->flags & I40E_FLAG_SERVICE_CLIENT_REQUESTED))
 		return;
 	pf->flags &= ~I40E_FLAG_SERVICE_CLIENT_REQUESTED;
+	cdev = pf->cinst;
 
 	/* If we're down or resetting, just bail */
 	if (test_bit(__I40E_DOWN, &pf->state) ||
 	    test_bit(__I40E_CONFIG_BUSY, &pf->state))
 		return;
 
-	/* Check client state and instantiate client if client registered */
-	mutex_lock(&i40e_client_mutex);
-	list_for_each_entry(client, &i40e_clients, list) {
-		/* first check client is registered */
-		if (!test_bit(__I40E_CLIENT_REGISTERED, &client->state))
-			continue;
-
-		/* Do we also need the LAN VSI to be up, to create instance */
-		if (!(client->flags & I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE)) {
-			/* check if L2 VSI is up, if not we are not ready */
-			if (test_bit(__I40E_DOWN, &pf->vsi[pf->lan_vsi]->state))
-				continue;
-		} else {
-			dev_warn(&pf->pdev->dev, "This client %s is being instantiated at probe\n",
-				 client->name);
-		}
-
-		/* Add the client instance to the instance list */
-		cdev = i40e_client_add_instance(pf, client, &existing);
-		if (!cdev)
-			continue;
-
-		if (!existing) {
-			dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x dev=0x%02x func=0x%02x\n",
-				 client->name, pf->hw.pf_id,
-				 pf->hw.bus.bus_id, pf->hw.bus.device,
-				 pf->hw.bus.func);
-		}
+	if (!client || !cdev)
+		return;
 
-		mutex_lock(&i40e_client_instance_mutex);
-		if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
-			      &cdev->state)) {
-			/* Send an Open request to the client */
-			if (client->ops && client->ops->open)
-				ret = client->ops->open(&cdev->lan_info,
-							client);
-			if (!ret) {
-				set_bit(__I40E_CLIENT_INSTANCE_OPENED,
-					&cdev->state);
-			} else {
-				/* remove client instance */
-				i40e_client_del_instance(pf, client);
+	/* Here we handle client opens. If the client is down, but
+	 * the netdev is up, then open the client.
+	 */
+	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
+		if (!test_bit(__I40E_DOWN, &vsi->state) &&
+		    client->ops && client->ops->open) {
+			set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
+			ret = client->ops->open(&cdev->lan_info, client);
+			if (ret) {
+				/* Remove failed client instance */
+				clear_bit(__I40E_CLIENT_INSTANCE_OPENED,
+					  &cdev->state);
+				i40e_client_del_instance(pf);
 			}
 		}
-		mutex_unlock(&i40e_client_instance_mutex);
+	} else {
+	/* Likewise for client close. If the client is up, but the netdev
+	 * is down, then close the client.
+	 */
+		if (test_bit(__I40E_DOWN, &vsi->state) &&
+		    client->ops && client->ops->close) {
+			clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
+			client->ops->close(&cdev->lan_info, client, false);
+			i40e_client_release_qvlist(&cdev->lan_info);
+		}
 	}
-	mutex_unlock(&i40e_client_mutex);
 }
 
 /**
@@ -601,7 +471,6 @@ int i40e_lan_del_device(struct i40e_pf *pf)
 			break;
 		}
 	}
-
 	mutex_unlock(&i40e_device_mutex);
 	return ret;
 }
@@ -610,22 +479,24 @@ int i40e_lan_del_device(struct i40e_pf *pf)
  * i40e_client_release - release client specific resources
  * @client: pointer to the registered client
  *
- * Return 0 on success or < 0 on error
  **/
-static int i40e_client_release(struct i40e_client *client)
+static void i40e_client_release(struct i40e_client *client)
 {
-	struct i40e_client_instance *cdev, *tmp;
+	struct i40e_client_instance *cdev;
+	struct i40e_device *ldev;
 	struct i40e_pf *pf;
-	int ret = 0;
 
-	LIST_HEAD(cdevs_tmp);
-
-	mutex_lock(&i40e_client_instance_mutex);
-	list_for_each_entry_safe(cdev, tmp, &i40e_client_instances, list) {
-		if (strncmp(cdev->client->name, client->name,
-			    I40E_CLIENT_STR_LENGTH))
+	mutex_lock(&i40e_device_mutex);
+	list_for_each_entry(ldev, &i40e_devices, list) {
+		pf = ldev->pf;
+		cdev = pf->cinst;
+		if (!cdev)
 			continue;
-		pf = (struct i40e_pf *)cdev->lan_info.pf;
+
+		while (test_and_set_bit(__I40E_SERVICE_SCHED,
+					&pf->state))
+			usleep_range(500, 1000);
+
 		if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
 			if (client->ops && client->ops->close)
 				client->ops->close(&cdev->lan_info, client,
@@ -637,18 +508,13 @@ static int i40e_client_release(struct i40e_client *client)
 				 "Client %s instance for PF id %d closed\n",
 				 client->name, pf->hw.pf_id);
 		}
-		/* delete the client instance from the list */
-		list_move(&cdev->list, &cdevs_tmp);
+		/* delete the client instance */
+		i40e_client_del_instance(pf);
 		dev_info(&pf->pdev->dev, "Deleted client instance of Client %s\n",
 			 client->name);
+		clear_bit(__I40E_SERVICE_SCHED, &pf->state);
 	}
-	mutex_unlock(&i40e_client_instance_mutex);
-
-	/* free the client device and release its vsi */
-	list_for_each_entry_safe(cdev, tmp, &cdevs_tmp, list) {
-		kfree(cdev);
-	}
-	return ret;
+	mutex_unlock(&i40e_device_mutex);
 }
 
 /**
@@ -664,6 +530,7 @@ static void i40e_client_prepare(struct i40e_client *client)
 	mutex_lock(&i40e_device_mutex);
 	list_for_each_entry(ldev, &i40e_devices, list) {
 		pf = ldev->pf;
+		i40e_client_add_instance(pf);
 		/* Start the client subtask */
 		pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED;
 		i40e_service_event_schedule(pf);
@@ -792,8 +659,8 @@ static void i40e_client_request_reset(struct i40e_info *ldev,
 		break;
 	default:
 		dev_warn(&pf->pdev->dev,
-			 "Client %s instance for PF id %d request an unsupported reset: %d.\n",
-			 client->name, pf->hw.pf_id, reset_level);
+			 "Client for PF id %d requested an unsupported reset: %d.\n",
+			 pf->hw.pf_id, reset_level);
 		break;
 	}
 
@@ -852,8 +719,8 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev,
 	} else {
 		update = false;
 		dev_warn(&pf->pdev->dev,
-			 "Client %s instance for PF id %d request an unsupported Config: %x.\n",
-			 client->name, pf->hw.pf_id, flag);
+			 "Client for PF id %d request an unsupported Config: %x.\n",
+			 pf->hw.pf_id, flag);
 	}
 
 	if (update) {
@@ -878,7 +745,6 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev,
 int i40e_register_client(struct i40e_client *client)
 {
 	int ret = 0;
-	enum i40e_vsi_type vsi_type;
 
 	if (!client) {
 		ret = -EIO;
@@ -891,11 +757,9 @@ int i40e_register_client(struct i40e_client *client)
 		goto out;
 	}
 
-	mutex_lock(&i40e_client_mutex);
-	if (i40e_client_is_registered(client)) {
+	if (registered_client) {
 		pr_info("i40e: Client %s has already been registered!\n",
 			client->name);
-		mutex_unlock(&i40e_client_mutex);
 		ret = -EEXIST;
 		goto out;
 	}
@@ -908,22 +772,11 @@ int i40e_register_client(struct i40e_client *client)
 			client->version.major, client->version.minor,
 			client->version.build,
 			i40e_client_interface_version_str);
-		mutex_unlock(&i40e_client_mutex);
 		ret = -EIO;
 		goto out;
 	}
 
-	vsi_type = i40e_client_type_to_vsi_type(client->type);
-	if (vsi_type == I40E_VSI_TYPE_UNKNOWN) {
-		pr_info("i40e: Failed to register client %s due to unknown client type %d\n",
-			client->name, client->type);
-		mutex_unlock(&i40e_client_mutex);
-		ret = -EIO;
-		goto out;
-	}
-	list_add(&client->list, &i40e_clients);
-	set_bit(__I40E_CLIENT_REGISTERED, &client->state);
-	mutex_unlock(&i40e_client_mutex);
+	registered_client = client;
 
 	i40e_client_prepare(client);
 
@@ -943,29 +796,21 @@ int i40e_unregister_client(struct i40e_client *client)
 {
 	int ret = 0;
 
-	/* When a unregister request comes through we would have to send
-	 * a close for each of the client instances that were opened.
-	 * client_release function is called to handle this.
-	 */
-	mutex_lock(&i40e_client_mutex);
-	if (!client || i40e_client_release(client)) {
-		ret = -EIO;
-		goto out;
-	}
-
-	/* TODO: check if device is in reset, or if that matters? */
-	if (!i40e_client_is_registered(client)) {
+	if (registered_client != client) {
 		pr_info("i40e: Client %s has not been registered\n",
 			client->name);
 		ret = -ENODEV;
 		goto out;
 	}
-	clear_bit(__I40E_CLIENT_REGISTERED, &client->state);
-	list_del(&client->list);
-	pr_info("i40e: Unregistered client %s with return code %d\n",
-		client->name, ret);
+	registered_client = NULL;
+	/* When a unregister request comes through we would have to send
+	 * a close for each of the client instances that were opened.
+	 * client_release function is called to handle this.
+	 */
+	i40e_client_release(client);
+
+	pr_info("i40e: Unregistered client %s\n", client->name);
 out:
-	mutex_unlock(&i40e_client_mutex);
 	return ret;
 }
 EXPORT_SYMBOL(i40e_unregister_client);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.h b/drivers/net/ethernet/intel/i40e/i40e_client.h
index 528bd79b05fe..15b21a5315b5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.h
@@ -57,11 +57,6 @@ enum i40e_client_instance_state {
 	__I40E_CLIENT_INSTANCE_OPENED,
 };
 
-enum i40e_client_type {
-	I40E_CLIENT_IWARP,
-	I40E_CLIENT_VMDQ2
-};
-
 struct i40e_ops;
 struct i40e_client;
 
@@ -214,7 +209,8 @@ struct i40e_client {
 	u32 flags;
 #define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE	BIT(0)
 #define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS	BIT(2)
-	enum i40e_client_type type;
+	u8 type;
+#define I40E_CLIENT_IWARP 0
 	const struct i40e_client_ops *ops; /* client ops provided by the client */
 };
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index ece57d6a6e23..f9db95aa3a20 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1088,33 +1088,6 @@ void i40e_pre_tx_queue_cfg(struct i40e_hw *hw, u32 queue, bool enable)
 
 	wr32(hw, I40E_GLLAN_TXPRE_QDIS(reg_block), reg_val);
 }
-#ifdef I40E_FCOE
-
-/**
- * i40e_get_san_mac_addr - get SAN MAC address
- * @hw: pointer to the HW structure
- * @mac_addr: pointer to SAN MAC address
- *
- * Reads the adapter's SAN MAC address from NVM
- **/
-i40e_status i40e_get_san_mac_addr(struct i40e_hw *hw, u8 *mac_addr)
-{
-	struct i40e_aqc_mac_address_read_data addrs;
-	i40e_status status;
-	u16 flags = 0;
-
-	status = i40e_aq_mac_address_read(hw, &flags, &addrs, NULL);
-	if (status)
-		return status;
-
-	if (flags & I40E_AQC_SAN_ADDR_VALID)
-		ether_addr_copy(mac_addr, addrs.pf_san_mac);
-	else
-		status = I40E_ERR_INVALID_MAC_ADDR;
-
-	return status;
-}
-#endif
 
 /**
  *  i40e_read_pba_string - Reads part number string from EEPROM
@@ -4990,7 +4963,9 @@ u32 i40e_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr)
 	int retry = 5;
 	u32 val = 0;
 
-	use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5);
+	use_register = (((hw->aq.api_maj_ver == 1) &&
+			(hw->aq.api_min_ver < 5)) ||
+			(hw->mac.type == I40E_MAC_X722));
 	if (!use_register) {
 do_retry:
 		status = i40e_aq_rx_ctl_read_register(hw, reg_addr, &val, NULL);
@@ -5049,7 +5024,9 @@ void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val)
 	bool use_register;
 	int retry = 5;
 
-	use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5);
+	use_register = (((hw->aq.api_maj_ver == 1) &&
+			(hw->aq.api_min_ver < 5)) ||
+			(hw->mac.type == I40E_MAC_X722));
 	if (!use_register) {
 do_retry:
 		status = i40e_aq_rx_ctl_write_register(hw, reg_addr,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 267ad2588255..c5f68cc1edcd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -484,25 +484,6 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
 			 vsi->bw_ets_limit_credits[i],
 			 vsi->bw_ets_max_quanta[i]);
 	}
-#ifdef I40E_FCOE
-	if (vsi->type == I40E_VSI_FCOE) {
-		dev_info(&pf->pdev->dev,
-			 "    fcoe_stats: rx_packets = %llu, rx_dwords = %llu, rx_dropped = %llu\n",
-			 vsi->fcoe_stats.rx_fcoe_packets,
-			 vsi->fcoe_stats.rx_fcoe_dwords,
-			 vsi->fcoe_stats.rx_fcoe_dropped);
-		dev_info(&pf->pdev->dev,
-			 "    fcoe_stats: tx_packets = %llu, tx_dwords = %llu\n",
-			 vsi->fcoe_stats.tx_fcoe_packets,
-			 vsi->fcoe_stats.tx_fcoe_dwords);
-		dev_info(&pf->pdev->dev,
-			 "    fcoe_stats: bad_crc = %llu, last_error = %llu\n",
-			 vsi->fcoe_stats.fcoe_bad_fccrc,
-			 vsi->fcoe_stats.fcoe_last_error);
-		dev_info(&pf->pdev->dev, "    fcoe_stats: ddp_count = %llu\n",
-			 vsi->fcoe_stats.fcoe_ddp_count);
-	}
-#endif
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index a22e26200bcc..c0c1a0cdaa5b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -162,19 +162,6 @@ static const struct i40e_stats i40e_gstrings_stats[] = {
 	I40E_PF_STAT("rx_lpi_count", stats.rx_lpi_count),
 };
 
-#ifdef I40E_FCOE
-static const struct i40e_stats i40e_gstrings_fcoe_stats[] = {
-	I40E_VSI_STAT("fcoe_bad_fccrc", fcoe_stats.fcoe_bad_fccrc),
-	I40E_VSI_STAT("rx_fcoe_dropped", fcoe_stats.rx_fcoe_dropped),
-	I40E_VSI_STAT("rx_fcoe_packets", fcoe_stats.rx_fcoe_packets),
-	I40E_VSI_STAT("rx_fcoe_dwords", fcoe_stats.rx_fcoe_dwords),
-	I40E_VSI_STAT("fcoe_ddp_count", fcoe_stats.fcoe_ddp_count),
-	I40E_VSI_STAT("fcoe_last_error", fcoe_stats.fcoe_last_error),
-	I40E_VSI_STAT("tx_fcoe_packets", fcoe_stats.tx_fcoe_packets),
-	I40E_VSI_STAT("tx_fcoe_dwords", fcoe_stats.tx_fcoe_dwords),
-};
-
-#endif /* I40E_FCOE */
 #define I40E_QUEUE_STATS_LEN(n) \
 	(((struct i40e_netdev_priv *)netdev_priv((n)))->vsi->num_queue_pairs \
 	    * 2 /* Tx and Rx together */                                     \
@@ -182,17 +169,9 @@ static const struct i40e_stats i40e_gstrings_fcoe_stats[] = {
 #define I40E_GLOBAL_STATS_LEN	ARRAY_SIZE(i40e_gstrings_stats)
 #define I40E_NETDEV_STATS_LEN   ARRAY_SIZE(i40e_gstrings_net_stats)
 #define I40E_MISC_STATS_LEN	ARRAY_SIZE(i40e_gstrings_misc_stats)
-#ifdef I40E_FCOE
-#define I40E_FCOE_STATS_LEN	ARRAY_SIZE(i40e_gstrings_fcoe_stats)
-#define I40E_VSI_STATS_LEN(n)	(I40E_NETDEV_STATS_LEN + \
-				 I40E_FCOE_STATS_LEN + \
-				 I40E_MISC_STATS_LEN + \
-				 I40E_QUEUE_STATS_LEN((n)))
-#else
 #define I40E_VSI_STATS_LEN(n)   (I40E_NETDEV_STATS_LEN + \
 				 I40E_MISC_STATS_LEN + \
 				 I40E_QUEUE_STATS_LEN((n)))
-#endif /* I40E_FCOE */
 #define I40E_PFC_STATS_LEN ( \
 		(FIELD_SIZEOF(struct i40e_pf, stats.priority_xoff_rx) + \
 		 FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_rx) + \
@@ -228,22 +207,37 @@ static const char i40e_gstrings_test[][ETH_GSTRING_LEN] = {
 
 #define I40E_TEST_LEN (sizeof(i40e_gstrings_test) / ETH_GSTRING_LEN)
 
-static const char i40e_priv_flags_strings[][ETH_GSTRING_LEN] = {
-	"MFP",
-	"LinkPolling",
-	"flow-director-atr",
-	"veb-stats",
-	"hw-atr-eviction",
+struct i40e_priv_flags {
+	char flag_string[ETH_GSTRING_LEN];
+	u64 flag;
+	bool read_only;
+};
+
+#define I40E_PRIV_FLAG(_name, _flag, _read_only) { \
+	.flag_string = _name, \
+	.flag = _flag, \
+	.read_only = _read_only, \
+}
+
+static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = {
+	/* NOTE: MFP setting cannot be changed */
+	I40E_PRIV_FLAG("MFP", I40E_FLAG_MFP_ENABLED, 1),
+	I40E_PRIV_FLAG("LinkPolling", I40E_FLAG_LINK_POLLING_ENABLED, 0),
+	I40E_PRIV_FLAG("flow-director-atr", I40E_FLAG_FD_ATR_ENABLED, 0),
+	I40E_PRIV_FLAG("veb-stats", I40E_FLAG_VEB_STATS_ENABLED, 0),
+	I40E_PRIV_FLAG("hw-atr-eviction", I40E_FLAG_HW_ATR_EVICT_CAPABLE, 0),
+	I40E_PRIV_FLAG("legacy-rx", I40E_FLAG_LEGACY_RX, 0),
 };
 
-#define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_priv_flags_strings)
+#define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags)
 
 /* Private flags with a global effect, restricted to PF 0 */
-static const char i40e_gl_priv_flags_strings[][ETH_GSTRING_LEN] = {
-	"vf-true-promisc-support",
+static const struct i40e_priv_flags i40e_gl_gstrings_priv_flags[] = {
+	I40E_PRIV_FLAG("vf-true-promisc-support",
+		       I40E_FLAG_TRUE_PROMISC_SUPPORT, 0),
 };
 
-#define I40E_GL_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gl_priv_flags_strings)
+#define I40E_GL_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gl_gstrings_priv_flags)
 
 /**
  * i40e_partition_setting_complaint - generic complaint for MFP restriction
@@ -387,7 +381,7 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported,
  *
  **/
 static void i40e_get_settings_link_up(struct i40e_hw *hw,
-				      struct ethtool_cmd *ecmd,
+				      struct ethtool_link_ksettings *cmd,
 				      struct net_device *netdev,
 				      struct i40e_pf *pf)
 {
@@ -395,90 +389,96 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 	u32 link_speed = hw_link_info->link_speed;
 	u32 e_advertising = 0x0;
 	u32 e_supported = 0x0;
+	u32 supported, advertising;
+
+	ethtool_convert_link_mode_to_legacy_u32(&supported,
+						cmd->link_modes.supported);
+	ethtool_convert_link_mode_to_legacy_u32(&advertising,
+						cmd->link_modes.advertising);
 
 	/* Initialize supported and advertised settings based on phy settings */
 	switch (hw_link_info->phy_type) {
 	case I40E_PHY_TYPE_40GBASE_CR4:
 	case I40E_PHY_TYPE_40GBASE_CR4_CU:
-		ecmd->supported = SUPPORTED_Autoneg |
-				  SUPPORTED_40000baseCR4_Full;
-		ecmd->advertising = ADVERTISED_Autoneg |
-				    ADVERTISED_40000baseCR4_Full;
+		supported = SUPPORTED_Autoneg |
+			    SUPPORTED_40000baseCR4_Full;
+		advertising = ADVERTISED_Autoneg |
+			      ADVERTISED_40000baseCR4_Full;
 		break;
 	case I40E_PHY_TYPE_XLAUI:
 	case I40E_PHY_TYPE_XLPPI:
 	case I40E_PHY_TYPE_40GBASE_AOC:
-		ecmd->supported = SUPPORTED_40000baseCR4_Full;
+		supported = SUPPORTED_40000baseCR4_Full;
 		break;
 	case I40E_PHY_TYPE_40GBASE_SR4:
-		ecmd->supported = SUPPORTED_40000baseSR4_Full;
+		supported = SUPPORTED_40000baseSR4_Full;
 		break;
 	case I40E_PHY_TYPE_40GBASE_LR4:
-		ecmd->supported = SUPPORTED_40000baseLR4_Full;
+		supported = SUPPORTED_40000baseLR4_Full;
 		break;
 	case I40E_PHY_TYPE_10GBASE_SR:
 	case I40E_PHY_TYPE_10GBASE_LR:
 	case I40E_PHY_TYPE_1000BASE_SX:
 	case I40E_PHY_TYPE_1000BASE_LX:
-		ecmd->supported = SUPPORTED_10000baseT_Full;
+		supported = SUPPORTED_10000baseT_Full;
 		if (hw_link_info->module_type[2] &
 		    I40E_MODULE_TYPE_1000BASE_SX ||
 		    hw_link_info->module_type[2] &
 		    I40E_MODULE_TYPE_1000BASE_LX) {
-			ecmd->supported |= SUPPORTED_1000baseT_Full;
+			supported |= SUPPORTED_1000baseT_Full;
 			if (hw_link_info->requested_speeds &
 			    I40E_LINK_SPEED_1GB)
-				ecmd->advertising |= ADVERTISED_1000baseT_Full;
+				advertising |= ADVERTISED_1000baseT_Full;
 		}
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
-			ecmd->advertising |= ADVERTISED_10000baseT_Full;
+			advertising |= ADVERTISED_10000baseT_Full;
 		break;
 	case I40E_PHY_TYPE_10GBASE_T:
 	case I40E_PHY_TYPE_1000BASE_T:
 	case I40E_PHY_TYPE_100BASE_TX:
-		ecmd->supported = SUPPORTED_Autoneg |
-				  SUPPORTED_10000baseT_Full |
-				  SUPPORTED_1000baseT_Full |
-				  SUPPORTED_100baseT_Full;
-		ecmd->advertising = ADVERTISED_Autoneg;
+		supported = SUPPORTED_Autoneg |
+			    SUPPORTED_10000baseT_Full |
+			    SUPPORTED_1000baseT_Full |
+			    SUPPORTED_100baseT_Full;
+		advertising = ADVERTISED_Autoneg;
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
-			ecmd->advertising |= ADVERTISED_10000baseT_Full;
+			advertising |= ADVERTISED_10000baseT_Full;
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
-			ecmd->advertising |= ADVERTISED_1000baseT_Full;
+			advertising |= ADVERTISED_1000baseT_Full;
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB)
-			ecmd->advertising |= ADVERTISED_100baseT_Full;
+			advertising |= ADVERTISED_100baseT_Full;
 		break;
 	case I40E_PHY_TYPE_1000BASE_T_OPTICAL:
-		ecmd->supported = SUPPORTED_Autoneg |
-				  SUPPORTED_1000baseT_Full;
-		ecmd->advertising = ADVERTISED_Autoneg |
-				    ADVERTISED_1000baseT_Full;
+		supported = SUPPORTED_Autoneg |
+			    SUPPORTED_1000baseT_Full;
+		advertising = ADVERTISED_Autoneg |
+			      ADVERTISED_1000baseT_Full;
 		break;
 	case I40E_PHY_TYPE_10GBASE_CR1_CU:
 	case I40E_PHY_TYPE_10GBASE_CR1:
-		ecmd->supported = SUPPORTED_Autoneg |
-				  SUPPORTED_10000baseT_Full;
-		ecmd->advertising = ADVERTISED_Autoneg |
-				    ADVERTISED_10000baseT_Full;
+		supported = SUPPORTED_Autoneg |
+			    SUPPORTED_10000baseT_Full;
+		advertising = ADVERTISED_Autoneg |
+			      ADVERTISED_10000baseT_Full;
 		break;
 	case I40E_PHY_TYPE_XAUI:
 	case I40E_PHY_TYPE_XFI:
 	case I40E_PHY_TYPE_SFI:
 	case I40E_PHY_TYPE_10GBASE_SFPP_CU:
 	case I40E_PHY_TYPE_10GBASE_AOC:
-		ecmd->supported = SUPPORTED_10000baseT_Full;
-		ecmd->advertising = SUPPORTED_10000baseT_Full;
+		supported = SUPPORTED_10000baseT_Full;
+		advertising = SUPPORTED_10000baseT_Full;
 		break;
 	case I40E_PHY_TYPE_SGMII:
-		ecmd->supported = SUPPORTED_Autoneg |
-				  SUPPORTED_1000baseT_Full;
+		supported = SUPPORTED_Autoneg |
+			    SUPPORTED_1000baseT_Full;
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
-			ecmd->advertising |= ADVERTISED_1000baseT_Full;
+			advertising |= ADVERTISED_1000baseT_Full;
 		if (pf->flags & I40E_FLAG_100M_SGMII_CAPABLE) {
-			ecmd->supported |= SUPPORTED_100baseT_Full;
+			supported |= SUPPORTED_100baseT_Full;
 			if (hw_link_info->requested_speeds &
 			    I40E_LINK_SPEED_100MB)
-				ecmd->advertising |= ADVERTISED_100baseT_Full;
+				advertising |= ADVERTISED_100baseT_Full;
 		}
 		break;
 	case I40E_PHY_TYPE_40GBASE_KR4:
@@ -486,25 +486,25 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 	case I40E_PHY_TYPE_10GBASE_KR:
 	case I40E_PHY_TYPE_10GBASE_KX4:
 	case I40E_PHY_TYPE_1000BASE_KX:
-		ecmd->supported |= SUPPORTED_40000baseKR4_Full |
-				   SUPPORTED_20000baseKR2_Full |
-				   SUPPORTED_10000baseKR_Full |
-				   SUPPORTED_10000baseKX4_Full |
-				   SUPPORTED_1000baseKX_Full |
-				   SUPPORTED_Autoneg;
-		ecmd->advertising |= ADVERTISED_40000baseKR4_Full |
-				     ADVERTISED_20000baseKR2_Full |
-				     ADVERTISED_10000baseKR_Full |
-				     ADVERTISED_10000baseKX4_Full |
-				     ADVERTISED_1000baseKX_Full |
-				     ADVERTISED_Autoneg;
+		supported |= SUPPORTED_40000baseKR4_Full |
+			     SUPPORTED_20000baseKR2_Full |
+			     SUPPORTED_10000baseKR_Full |
+			     SUPPORTED_10000baseKX4_Full |
+			     SUPPORTED_1000baseKX_Full |
+			     SUPPORTED_Autoneg;
+		advertising |= ADVERTISED_40000baseKR4_Full |
+			       ADVERTISED_20000baseKR2_Full |
+			       ADVERTISED_10000baseKR_Full |
+			       ADVERTISED_10000baseKX4_Full |
+			       ADVERTISED_1000baseKX_Full |
+			       ADVERTISED_Autoneg;
 		break;
 	case I40E_PHY_TYPE_25GBASE_KR:
 	case I40E_PHY_TYPE_25GBASE_CR:
 	case I40E_PHY_TYPE_25GBASE_SR:
 	case I40E_PHY_TYPE_25GBASE_LR:
-		ecmd->supported = SUPPORTED_Autoneg;
-		ecmd->advertising = ADVERTISED_Autoneg;
+		supported = SUPPORTED_Autoneg;
+		advertising = ADVERTISED_Autoneg;
 		/* TODO: add speeds when ethtool is ready to support*/
 		break;
 	default:
@@ -520,38 +520,43 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 	i40e_phy_type_to_ethtool(pf, &e_supported,
 				 &e_advertising);
 
-	ecmd->supported = ecmd->supported & e_supported;
-	ecmd->advertising = ecmd->advertising & e_advertising;
+	supported = supported & e_supported;
+	advertising = advertising & e_advertising;
 
 	/* Set speed and duplex */
 	switch (link_speed) {
 	case I40E_LINK_SPEED_40GB:
-		ethtool_cmd_speed_set(ecmd, SPEED_40000);
+		cmd->base.speed = SPEED_40000;
 		break;
 	case I40E_LINK_SPEED_25GB:
 #ifdef SPEED_25000
-		ethtool_cmd_speed_set(ecmd, SPEED_25000);
+		cmd->base.speed = SPEED_25000;
 #else
 		netdev_info(netdev,
 			    "Speed is 25G, display not supported by this version of ethtool.\n");
 #endif
 		break;
 	case I40E_LINK_SPEED_20GB:
-		ethtool_cmd_speed_set(ecmd, SPEED_20000);
+		cmd->base.speed = SPEED_20000;
 		break;
 	case I40E_LINK_SPEED_10GB:
-		ethtool_cmd_speed_set(ecmd, SPEED_10000);
+		cmd->base.speed = SPEED_10000;
 		break;
 	case I40E_LINK_SPEED_1GB:
-		ethtool_cmd_speed_set(ecmd, SPEED_1000);
+		cmd->base.speed = SPEED_1000;
 		break;
 	case I40E_LINK_SPEED_100MB:
-		ethtool_cmd_speed_set(ecmd, SPEED_100);
+		cmd->base.speed = SPEED_100;
 		break;
 	default:
 		break;
 	}
-	ecmd->duplex = DUPLEX_FULL;
+	cmd->base.duplex = DUPLEX_FULL;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 }
 
 /**
@@ -562,18 +567,24 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
  * Reports link settings that can be determined when link is down
  **/
 static void i40e_get_settings_link_down(struct i40e_hw *hw,
-					struct ethtool_cmd *ecmd,
+					struct ethtool_link_ksettings *cmd,
 					struct i40e_pf *pf)
 {
+	u32 supported, advertising;
+
 	/* link is down and the driver needs to fall back on
 	 * supported phy types to figure out what info to display
 	 */
-	i40e_phy_type_to_ethtool(pf, &ecmd->supported,
-				 &ecmd->advertising);
+	i40e_phy_type_to_ethtool(pf, &supported, &advertising);
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 
 	/* With no link speed and duplex are unknown */
-	ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
-	ecmd->duplex = DUPLEX_UNKNOWN;
+	cmd->base.speed = SPEED_UNKNOWN;
+	cmd->base.duplex = DUPLEX_UNKNOWN;
 }
 
 /**
@@ -583,74 +594,85 @@ static void i40e_get_settings_link_down(struct i40e_hw *hw,
  *
  * Reports speed/duplex settings based on media_type
  **/
-static int i40e_get_settings(struct net_device *netdev,
-			     struct ethtool_cmd *ecmd)
+static int i40e_get_link_ksettings(struct net_device *netdev,
+				   struct ethtool_link_ksettings *cmd)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
 	struct i40e_hw *hw = &pf->hw;
 	struct i40e_link_status *hw_link_info = &hw->phy.link_info;
 	bool link_up = hw_link_info->link_info & I40E_AQ_LINK_UP;
+	u32 advertising;
 
 	if (link_up)
-		i40e_get_settings_link_up(hw, ecmd, netdev, pf);
+		i40e_get_settings_link_up(hw, cmd, netdev, pf);
 	else
-		i40e_get_settings_link_down(hw, ecmd, pf);
+		i40e_get_settings_link_down(hw, cmd, pf);
 
 	/* Now set the settings that don't rely on link being up/down */
 	/* Set autoneg settings */
-	ecmd->autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ?
+	cmd->base.autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ?
 			  AUTONEG_ENABLE : AUTONEG_DISABLE);
 
 	switch (hw->phy.media_type) {
 	case I40E_MEDIA_TYPE_BACKPLANE:
-		ecmd->supported |= SUPPORTED_Autoneg |
-				   SUPPORTED_Backplane;
-		ecmd->advertising |= ADVERTISED_Autoneg |
-				     ADVERTISED_Backplane;
-		ecmd->port = PORT_NONE;
+		ethtool_link_ksettings_add_link_mode(cmd, supported,
+						     Autoneg);
+		ethtool_link_ksettings_add_link_mode(cmd, supported,
+						     Backplane);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Autoneg);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Backplane);
+		cmd->base.port = PORT_NONE;
 		break;
 	case I40E_MEDIA_TYPE_BASET:
-		ecmd->supported |= SUPPORTED_TP;
-		ecmd->advertising |= ADVERTISED_TP;
-		ecmd->port = PORT_TP;
+		ethtool_link_ksettings_add_link_mode(cmd, supported, TP);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising, TP);
+		cmd->base.port = PORT_TP;
 		break;
 	case I40E_MEDIA_TYPE_DA:
 	case I40E_MEDIA_TYPE_CX4:
-		ecmd->supported |= SUPPORTED_FIBRE;
-		ecmd->advertising |= ADVERTISED_FIBRE;
-		ecmd->port = PORT_DA;
+		ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE);
+		cmd->base.port = PORT_DA;
 		break;
 	case I40E_MEDIA_TYPE_FIBER:
-		ecmd->supported |= SUPPORTED_FIBRE;
-		ecmd->port = PORT_FIBRE;
+		ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+		cmd->base.port = PORT_FIBRE;
 		break;
 	case I40E_MEDIA_TYPE_UNKNOWN:
 	default:
-		ecmd->port = PORT_OTHER;
+		cmd->base.port = PORT_OTHER;
 		break;
 	}
 
-	/* Set transceiver */
-	ecmd->transceiver = XCVR_EXTERNAL;
-
 	/* Set flow control settings */
-	ecmd->supported |= SUPPORTED_Pause;
+	ethtool_link_ksettings_add_link_mode(cmd, supported, Pause);
 
 	switch (hw->fc.requested_mode) {
 	case I40E_FC_FULL:
-		ecmd->advertising |= ADVERTISED_Pause;
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Pause);
 		break;
 	case I40E_FC_TX_PAUSE:
-		ecmd->advertising |= ADVERTISED_Asym_Pause;
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Asym_Pause);
 		break;
 	case I40E_FC_RX_PAUSE:
-		ecmd->advertising |= (ADVERTISED_Pause |
-				      ADVERTISED_Asym_Pause);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Pause);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Asym_Pause);
 		break;
 	default:
-		ecmd->advertising &= ~(ADVERTISED_Pause |
-				       ADVERTISED_Asym_Pause);
+		ethtool_convert_link_mode_to_legacy_u32(
+			&advertising, cmd->link_modes.advertising);
+
+		advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause);
+
+		ethtool_convert_legacy_u32_to_link_mode(
+			cmd->link_modes.advertising, advertising);
 		break;
 	}
 
@@ -664,8 +686,8 @@ static int i40e_get_settings(struct net_device *netdev,
  *
  * Set speed/duplex per media_types advertised/forced
  **/
-static int i40e_set_settings(struct net_device *netdev,
-			     struct ethtool_cmd *ecmd)
+static int i40e_set_link_ksettings(struct net_device *netdev,
+				   const struct ethtool_link_ksettings *cmd)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_aq_get_phy_abilities_resp abilities;
@@ -673,12 +695,14 @@ static int i40e_set_settings(struct net_device *netdev,
 	struct i40e_pf *pf = np->vsi->back;
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_hw *hw = &pf->hw;
-	struct ethtool_cmd safe_ecmd;
+	struct ethtool_link_ksettings safe_cmd;
+	struct ethtool_link_ksettings copy_cmd;
 	i40e_status status = 0;
 	bool change = false;
 	int err = 0;
-	u8 autoneg;
+	u32 autoneg;
 	u32 advertise;
+	u32 tmp;
 
 	/* Changing port settings is not supported if this isn't the
 	 * port's controlling PF
@@ -706,23 +730,31 @@ static int i40e_set_settings(struct net_device *netdev,
 		return -EOPNOTSUPP;
 	}
 
+	/* copy the cmd to copy_cmd to avoid modifying the origin */
+	memcpy(&copy_cmd, cmd, sizeof(struct ethtool_link_ksettings));
+
 	/* get our own copy of the bits to check against */
-	memset(&safe_ecmd, 0, sizeof(struct ethtool_cmd));
-	i40e_get_settings(netdev, &safe_ecmd);
+	memset(&safe_cmd, 0, sizeof(struct ethtool_link_ksettings));
+	i40e_get_link_ksettings(netdev, &safe_cmd);
 
-	/* save autoneg and speed out of ecmd */
-	autoneg = ecmd->autoneg;
-	advertise = ecmd->advertising;
+	/* save autoneg and speed out of cmd */
+	autoneg = cmd->base.autoneg;
+	ethtool_convert_link_mode_to_legacy_u32(&advertise,
+						cmd->link_modes.advertising);
 
 	/* set autoneg and speed back to what they currently are */
-	ecmd->autoneg = safe_ecmd.autoneg;
-	ecmd->advertising = safe_ecmd.advertising;
+	copy_cmd.base.autoneg = safe_cmd.base.autoneg;
+	ethtool_convert_link_mode_to_legacy_u32(
+		&tmp, safe_cmd.link_modes.advertising);
+	ethtool_convert_legacy_u32_to_link_mode(
+		copy_cmd.link_modes.advertising, tmp);
+
+	copy_cmd.base.cmd = safe_cmd.base.cmd;
 
-	ecmd->cmd = safe_ecmd.cmd;
-	/* If ecmd and safe_ecmd are not the same now, then they are
+	/* If copy_cmd and safe_cmd are not the same now, then they are
 	 * trying to set something that we do not support
 	 */
-	if (memcmp(ecmd, &safe_ecmd, sizeof(struct ethtool_cmd)))
+	if (memcmp(&copy_cmd, &safe_cmd, sizeof(struct ethtool_link_ksettings)))
 		return -EOPNOTSUPP;
 
 	while (test_bit(__I40E_CONFIG_BUSY, &vsi->state))
@@ -745,7 +777,8 @@ static int i40e_set_settings(struct net_device *netdev,
 		/* If autoneg was not already enabled */
 		if (!(hw->phy.link_info.an_info & I40E_AQ_AN_COMPLETED)) {
 			/* If autoneg is not supported, return error */
-			if (!(safe_ecmd.supported & SUPPORTED_Autoneg)) {
+			if (!ethtool_link_ksettings_test_link_mode(
+				    &safe_cmd, supported, Autoneg)) {
 				netdev_info(netdev, "Autoneg not supported on this phy\n");
 				return -EINVAL;
 			}
@@ -760,7 +793,8 @@ static int i40e_set_settings(struct net_device *netdev,
 			/* If autoneg is supported 10GBASE_T is the only PHY
 			 * that can disable it, so otherwise return error
 			 */
-			if (safe_ecmd.supported & SUPPORTED_Autoneg &&
+			if (ethtool_link_ksettings_test_link_mode(
+				    &safe_cmd, supported, Autoneg) &&
 			    hw->phy.link_info.phy_type !=
 			    I40E_PHY_TYPE_10GBASE_T) {
 				netdev_info(netdev, "Autoneg cannot be disabled on this phy\n");
@@ -773,7 +807,9 @@ static int i40e_set_settings(struct net_device *netdev,
 		}
 	}
 
-	if (advertise & ~safe_ecmd.supported)
+	ethtool_convert_link_mode_to_legacy_u32(&tmp,
+						safe_cmd.link_modes.supported);
+	if (advertise & ~tmp)
 		return -EINVAL;
 
 	if (advertise & ADVERTISED_100baseT_Full)
@@ -1165,6 +1201,11 @@ static int i40e_get_eeprom_len(struct net_device *netdev)
 	struct i40e_hw *hw = &np->vsi->back->hw;
 	u32 val;
 
+#define X722_EEPROM_SCOPE_LIMIT 0x5B9FFF
+	if (hw->mac.type == I40E_MAC_X722) {
+		val = X722_EEPROM_SCOPE_LIMIT + 1;
+		return val;
+	}
 	val = (rd32(hw, I40E_GLPCI_LBARCTRL)
 		& I40E_GLPCI_LBARCTRL_FL_SIZE_MASK)
 		>> I40E_GLPCI_LBARCTRL_FL_SIZE_SHIFT;
@@ -1483,13 +1524,6 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 		data[i++] = (i40e_gstrings_misc_stats[j].sizeof_stat ==
 			    sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
 	}
-#ifdef I40E_FCOE
-	for (j = 0; j < I40E_FCOE_STATS_LEN; j++) {
-		p = (char *)vsi + i40e_gstrings_fcoe_stats[j].stat_offset;
-		data[i++] = (i40e_gstrings_fcoe_stats[j].sizeof_stat ==
-			sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
-	}
-#endif
 	rcu_read_lock();
 	for (j = 0; j < vsi->num_queue_pairs; j++) {
 		tx_ring = ACCESS_ONCE(vsi->tx_rings[j]);
@@ -1577,13 +1611,6 @@ static void i40e_get_strings(struct net_device *netdev, u32 stringset,
 				 i40e_gstrings_misc_stats[i].stat_string);
 			p += ETH_GSTRING_LEN;
 		}
-#ifdef I40E_FCOE
-		for (i = 0; i < I40E_FCOE_STATS_LEN; i++) {
-			snprintf(p, ETH_GSTRING_LEN, "%s",
-				 i40e_gstrings_fcoe_stats[i].stat_string);
-			p += ETH_GSTRING_LEN;
-		}
-#endif
 		for (i = 0; i < vsi->num_queue_pairs; i++) {
 			snprintf(p, ETH_GSTRING_LEN, "tx-%d.tx_packets", i);
 			p += ETH_GSTRING_LEN;
@@ -1648,12 +1675,18 @@ static void i40e_get_strings(struct net_device *netdev, u32 stringset,
 		/* BUG_ON(p - data != I40E_STATS_LEN * ETH_GSTRING_LEN); */
 		break;
 	case ETH_SS_PRIV_FLAGS:
-		memcpy(data, i40e_priv_flags_strings,
-		       I40E_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN);
-		data += I40E_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN;
-		if (pf->hw.pf_id == 0)
-			memcpy(data, i40e_gl_priv_flags_strings,
-			       I40E_GL_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN);
+		for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) {
+			snprintf(p, ETH_GSTRING_LEN, "%s",
+				 i40e_gstrings_priv_flags[i].flag_string);
+			p += ETH_GSTRING_LEN;
+		}
+		if (pf->hw.pf_id != 0)
+			break;
+		for (i = 0; i < I40E_GL_PRIV_FLAGS_STR_LEN; i++) {
+			snprintf(p, ETH_GSTRING_LEN, "%s",
+				 i40e_gl_gstrings_priv_flags[i].flag_string);
+			p += ETH_GSTRING_LEN;
+		}
 		break;
 	default:
 		break;
@@ -2285,6 +2318,102 @@ static int i40e_get_rss_hash_opts(struct i40e_pf *pf, struct ethtool_rxnfc *cmd)
 }
 
 /**
+ * i40e_check_mask - Check whether a mask field is set
+ * @mask: the full mask value
+ * @field; mask of the field to check
+ *
+ * If the given mask is fully set, return positive value. If the mask for the
+ * field is fully unset, return zero. Otherwise return a negative error code.
+ **/
+static int i40e_check_mask(u64 mask, u64 field)
+{
+	u64 value = mask & field;
+
+	if (value == field)
+		return 1;
+	else if (!value)
+		return 0;
+	else
+		return -1;
+}
+
+/**
+ * i40e_parse_rx_flow_user_data - Deconstruct user-defined data
+ * @fsp: pointer to rx flow specification
+ * @data: pointer to userdef data structure for storage
+ *
+ * Read the user-defined data and deconstruct the value into a structure. No
+ * other code should read the user-defined data, so as to ensure that every
+ * place consistently reads the value correctly.
+ *
+ * The user-defined field is a 64bit Big Endian format value, which we
+ * deconstruct by reading bits or bit fields from it. Single bit flags shall
+ * be defined starting from the highest bits, while small bit field values
+ * shall be defined starting from the lowest bits.
+ *
+ * Returns 0 if the data is valid, and non-zero if the userdef data is invalid
+ * and the filter should be rejected. The data structure will always be
+ * modified even if FLOW_EXT is not set.
+ *
+ **/
+static int i40e_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp,
+					struct i40e_rx_flow_userdef *data)
+{
+	u64 value, mask;
+	int valid;
+
+	/* Zero memory first so it's always consistent. */
+	memset(data, 0, sizeof(*data));
+
+	if (!(fsp->flow_type & FLOW_EXT))
+		return 0;
+
+	value = be64_to_cpu(*((__be64 *)fsp->h_ext.data));
+	mask = be64_to_cpu(*((__be64 *)fsp->m_ext.data));
+
+#define I40E_USERDEF_FLEX_WORD		GENMASK_ULL(15, 0)
+#define I40E_USERDEF_FLEX_OFFSET	GENMASK_ULL(31, 16)
+#define I40E_USERDEF_FLEX_FILTER	GENMASK_ULL(31, 0)
+
+	valid = i40e_check_mask(mask, I40E_USERDEF_FLEX_FILTER);
+	if (valid < 0) {
+		return -EINVAL;
+	} else if (valid) {
+		data->flex_word = value & I40E_USERDEF_FLEX_WORD;
+		data->flex_offset =
+			(value & I40E_USERDEF_FLEX_OFFSET) >> 16;
+		data->flex_filter = true;
+	}
+
+	return 0;
+}
+
+/**
+ * i40e_fill_rx_flow_user_data - Fill in user-defined data field
+ * @fsp: pointer to rx_flow specification
+ *
+ * Reads the userdef data structure and properly fills in the user defined
+ * fields of the rx_flow_spec.
+ **/
+static void i40e_fill_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp,
+					struct i40e_rx_flow_userdef *data)
+{
+	u64 value = 0, mask = 0;
+
+	if (data->flex_filter) {
+		value |= data->flex_word;
+		value |= (u64)data->flex_offset << 16;
+		mask |= I40E_USERDEF_FLEX_FILTER;
+	}
+
+	if (value || mask)
+		fsp->flow_type |= FLOW_EXT;
+
+	*((__be64 *)fsp->h_ext.data) = cpu_to_be64(value);
+	*((__be64 *)fsp->m_ext.data) = cpu_to_be64(mask);
+}
+
+/**
  * i40e_get_ethtool_fdir_all - Populates the rule count of a command
  * @pf: Pointer to the physical function struct
  * @cmd: The command to get or set Rx flow classification rules
@@ -2335,8 +2464,11 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf,
 {
 	struct ethtool_rx_flow_spec *fsp =
 			(struct ethtool_rx_flow_spec *)&cmd->fs;
+	struct i40e_rx_flow_userdef userdef = {0};
 	struct i40e_fdir_filter *rule = NULL;
 	struct hlist_node *node2;
+	u64 input_set;
+	u16 index;
 
 	hlist_for_each_entry_safe(rule, node2,
 				  &pf->fdir_filter_list, fdir_node) {
@@ -2359,8 +2491,48 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf,
 	 */
 	fsp->h_u.tcp_ip4_spec.psrc = rule->dst_port;
 	fsp->h_u.tcp_ip4_spec.pdst = rule->src_port;
-	fsp->h_u.tcp_ip4_spec.ip4src = rule->dst_ip[0];
-	fsp->h_u.tcp_ip4_spec.ip4dst = rule->src_ip[0];
+	fsp->h_u.tcp_ip4_spec.ip4src = rule->dst_ip;
+	fsp->h_u.tcp_ip4_spec.ip4dst = rule->src_ip;
+
+	switch (rule->flow_type) {
+	case SCTP_V4_FLOW:
+		index = I40E_FILTER_PCTYPE_NONF_IPV4_SCTP;
+		break;
+	case TCP_V4_FLOW:
+		index = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+		break;
+	case UDP_V4_FLOW:
+		index = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
+		break;
+	case IP_USER_FLOW:
+		index = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER;
+		break;
+	default:
+		/* If we have stored a filter with a flow type not listed here
+		 * it is almost certainly a driver bug. WARN(), and then
+		 * assign the input_set as if all fields are enabled to avoid
+		 * reading unassigned memory.
+		 */
+		WARN(1, "Missing input set index for flow_type %d\n",
+		     rule->flow_type);
+		input_set = 0xFFFFFFFFFFFFFFFFULL;
+		goto no_input_set;
+	}
+
+	input_set = i40e_read_fd_input_set(pf, index);
+
+no_input_set:
+	if (input_set & I40E_L3_SRC_MASK)
+		fsp->m_u.tcp_ip4_spec.ip4src = htonl(0xFFFF);
+
+	if (input_set & I40E_L3_DST_MASK)
+		fsp->m_u.tcp_ip4_spec.ip4dst = htonl(0xFFFF);
+
+	if (input_set & I40E_L4_SRC_MASK)
+		fsp->m_u.tcp_ip4_spec.psrc = htons(0xFFFFFFFF);
+
+	if (input_set & I40E_L4_DST_MASK)
+		fsp->m_u.tcp_ip4_spec.pdst = htons(0xFFFFFFFF);
 
 	if (rule->dest_ctl == I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET)
 		fsp->ring_cookie = RX_CLS_FLOW_DISC;
@@ -2372,11 +2544,24 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf,
 
 		vsi = i40e_find_vsi_from_id(pf, rule->dest_vsi);
 		if (vsi && vsi->type == I40E_VSI_SRIOV) {
-			fsp->h_ext.data[1] = htonl(vsi->vf_id);
-			fsp->m_ext.data[1] = htonl(0x1);
+			/* VFs are zero-indexed by the driver, but ethtool
+			 * expects them to be one-indexed, so add one here
+			 */
+			u64 ring_vf = vsi->vf_id + 1;
+
+			ring_vf <<= ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF;
+			fsp->ring_cookie |= ring_vf;
 		}
 	}
 
+	if (rule->flex_filter) {
+		userdef.flex_filter = true;
+		userdef.flex_word = be16_to_cpu(rule->flex_word);
+		userdef.flex_offset = rule->flex_offset;
+	}
+
+	i40e_fill_rx_flow_user_data(fsp, &userdef);
+
 	return 0;
 }
 
@@ -2574,24 +2759,6 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 }
 
 /**
- * i40e_match_fdir_input_set - Match a new filter against an existing one
- * @rule: The filter already added
- * @input: The new filter to comapre against
- *
- * Returns true if the two input set match
- **/
-static bool i40e_match_fdir_input_set(struct i40e_fdir_filter *rule,
-				      struct i40e_fdir_filter *input)
-{
-	if ((rule->dst_ip[0] != input->dst_ip[0]) ||
-	    (rule->src_ip[0] != input->src_ip[0]) ||
-	    (rule->dst_port != input->dst_port) ||
-	    (rule->src_port != input->src_port))
-		return false;
-	return true;
-}
-
-/**
  * i40e_update_ethtool_fdir_entry - Updates the fdir filter entry
  * @vsi: Pointer to the targeted VSI
  * @input: The filter to update or NULL to indicate deletion
@@ -2626,22 +2793,22 @@ static int i40e_update_ethtool_fdir_entry(struct i40e_vsi *vsi,
 
 	/* if there is an old rule occupying our place remove it */
 	if (rule && (rule->fd_id == sw_idx)) {
-		if (input && !i40e_match_fdir_input_set(rule, input))
-			err = i40e_add_del_fdir(vsi, rule, false);
-		else if (!input)
-			err = i40e_add_del_fdir(vsi, rule, false);
+		/* Remove this rule, since we're either deleting it, or
+		 * replacing it.
+		 */
+		err = i40e_add_del_fdir(vsi, rule, false);
 		hlist_del(&rule->fdir_node);
 		kfree(rule);
 		pf->fdir_pf_active_filters--;
 	}
 
-	/* If no input this was a delete, err should be 0 if a rule was
-	 * successfully found and removed from the list else -EINVAL
+	/* If we weren't given an input, this is a delete, so just return the
+	 * error code indicating if there was an entry at the requested slot
 	 */
 	if (!input)
 		return err;
 
-	/* initialize node and set software index */
+	/* Otherwise, install the new rule as requested */
 	INIT_HLIST_NODE(&input->fdir_node);
 
 	/* add filter to the list */
@@ -2658,6 +2825,69 @@ static int i40e_update_ethtool_fdir_entry(struct i40e_vsi *vsi,
 }
 
 /**
+ * i40e_prune_flex_pit_list - Cleanup unused entries in FLX_PIT table
+ * @pf: pointer to PF structure
+ *
+ * This function searches the list of filters and determines which FLX_PIT
+ * entries are still required. It will prune any entries which are no longer
+ * in use after the deletion.
+ **/
+static void i40e_prune_flex_pit_list(struct i40e_pf *pf)
+{
+	struct i40e_flex_pit *entry, *tmp;
+	struct i40e_fdir_filter *rule;
+
+	/* First, we'll check the l3 table */
+	list_for_each_entry_safe(entry, tmp, &pf->l3_flex_pit_list, list) {
+		bool found = false;
+
+		hlist_for_each_entry(rule, &pf->fdir_filter_list, fdir_node) {
+			if (rule->flow_type != IP_USER_FLOW)
+				continue;
+			if (rule->flex_filter &&
+			    rule->flex_offset == entry->src_offset) {
+				found = true;
+				break;
+			}
+		}
+
+		/* If we didn't find the filter, then we can prune this entry
+		 * from the list.
+		 */
+		if (!found) {
+			list_del(&entry->list);
+			kfree(entry);
+		}
+	}
+
+	/* Followed by the L4 table */
+	list_for_each_entry_safe(entry, tmp, &pf->l4_flex_pit_list, list) {
+		bool found = false;
+
+		hlist_for_each_entry(rule, &pf->fdir_filter_list, fdir_node) {
+			/* Skip this filter if it's L3, since we already
+			 * checked those in the above loop
+			 */
+			if (rule->flow_type == IP_USER_FLOW)
+				continue;
+			if (rule->flex_filter &&
+			    rule->flex_offset == entry->src_offset) {
+				found = true;
+				break;
+			}
+		}
+
+		/* If we didn't find the filter, then we can prune this entry
+		 * from the list.
+		 */
+		if (!found) {
+			list_del(&entry->list);
+			kfree(entry);
+		}
+	}
+}
+
+/**
  * i40e_del_fdir_entry - Deletes a Flow Director filter entry
  * @vsi: Pointer to the targeted VSI
  * @cmd: The command to get or set Rx flow classification rules
@@ -2684,11 +2914,691 @@ static int i40e_del_fdir_entry(struct i40e_vsi *vsi,
 
 	ret = i40e_update_ethtool_fdir_entry(vsi, NULL, fsp->location, cmd);
 
+	i40e_prune_flex_pit_list(pf);
+
 	i40e_fdir_check_and_reenable(pf);
 	return ret;
 }
 
 /**
+ * i40e_unused_pit_index - Find an unused PIT index for given list
+ * @pf: the PF data structure
+ *
+ * Find the first unused flexible PIT index entry. We search both the L3 and
+ * L4 flexible PIT lists so that the returned index is unique and unused by
+ * either currently programmed L3 or L4 filters. We use a bit field as storage
+ * to track which indexes are already used.
+ **/
+static u8 i40e_unused_pit_index(struct i40e_pf *pf)
+{
+	unsigned long available_index = 0xFF;
+	struct i40e_flex_pit *entry;
+
+	/* We need to make sure that the new index isn't in use by either L3
+	 * or L4 filters so that IP_USER_FLOW filters can program both L3 and
+	 * L4 to use the same index.
+	 */
+
+	list_for_each_entry(entry, &pf->l4_flex_pit_list, list)
+		clear_bit(entry->pit_index, &available_index);
+
+	list_for_each_entry(entry, &pf->l3_flex_pit_list, list)
+		clear_bit(entry->pit_index, &available_index);
+
+	return find_first_bit(&available_index, 8);
+}
+
+/**
+ * i40e_find_flex_offset - Find an existing flex src_offset
+ * @flex_pit_list: L3 or L4 flex PIT list
+ * @src_offset: new src_offset to find
+ *
+ * Searches the flex_pit_list for an existing offset. If no offset is
+ * currently programmed, then this will return an ERR_PTR if there is no space
+ * to add a new offset, otherwise it returns NULL.
+ **/
+static
+struct i40e_flex_pit *i40e_find_flex_offset(struct list_head *flex_pit_list,
+					    u16 src_offset)
+{
+	struct i40e_flex_pit *entry;
+	int size = 0;
+
+	/* Search for the src_offset first. If we find a matching entry
+	 * already programmed, we can simply re-use it.
+	 */
+	list_for_each_entry(entry, flex_pit_list, list) {
+		size++;
+		if (entry->src_offset == src_offset)
+			return entry;
+	}
+
+	/* If we haven't found an entry yet, then the provided src offset has
+	 * not yet been programmed. We will program the src offset later on,
+	 * but we need to indicate whether there is enough space to do so
+	 * here. We'll make use of ERR_PTR for this purpose.
+	 */
+	if (size >= I40E_FLEX_PIT_TABLE_SIZE)
+		return ERR_PTR(-ENOSPC);
+
+	return NULL;
+}
+
+/**
+ * i40e_add_flex_offset - Add src_offset to flex PIT table list
+ * @flex_pit_list: L3 or L4 flex PIT list
+ * @src_offset: new src_offset to add
+ * @pit_index: the PIT index to program
+ *
+ * This function programs the new src_offset to the list. It is expected that
+ * i40e_find_flex_offset has already been tried and returned NULL, indicating
+ * that this offset is not programmed, and that the list has enough space to
+ * store another offset.
+ *
+ * Returns 0 on success, and negative value on error.
+ **/
+static int i40e_add_flex_offset(struct list_head *flex_pit_list,
+				u16 src_offset,
+				u8 pit_index)
+{
+	struct i40e_flex_pit *new_pit, *entry;
+
+	new_pit = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!new_pit)
+		return -ENOMEM;
+
+	new_pit->src_offset = src_offset;
+	new_pit->pit_index = pit_index;
+
+	/* We need to insert this item such that the list is sorted by
+	 * src_offset in ascending order.
+	 */
+	list_for_each_entry(entry, flex_pit_list, list) {
+		if (new_pit->src_offset < entry->src_offset) {
+			list_add_tail(&new_pit->list, &entry->list);
+			return 0;
+		}
+
+		/* If we found an entry with our offset already programmed we
+		 * can simply return here, after freeing the memory. However,
+		 * if the pit_index does not match we need to report an error.
+		 */
+		if (new_pit->src_offset == entry->src_offset) {
+			int err = 0;
+
+			/* If the PIT index is not the same we can't re-use
+			 * the entry, so we must report an error.
+			 */
+			if (new_pit->pit_index != entry->pit_index)
+				err = -EINVAL;
+
+			kfree(new_pit);
+			return err;
+		}
+	}
+
+	/* If we reached here, then we haven't yet added the item. This means
+	 * that we should add the item at the end of the list.
+	 */
+	list_add_tail(&new_pit->list, flex_pit_list);
+	return 0;
+}
+
+/**
+ * __i40e_reprogram_flex_pit - Re-program specific FLX_PIT table
+ * @pf: Pointer to the PF structure
+ * @flex_pit_list: list of flexible src offsets in use
+ * #flex_pit_start: index to first entry for this section of the table
+ *
+ * In order to handle flexible data, the hardware uses a table of values
+ * called the FLX_PIT table. This table is used to indicate which sections of
+ * the input correspond to what PIT index values. Unfortunately, hardware is
+ * very restrictive about programming this table. Entries must be ordered by
+ * src_offset in ascending order, without duplicates. Additionally, unused
+ * entries must be set to the unused index value, and must have valid size and
+ * length according to the src_offset ordering.
+ *
+ * This function will reprogram the FLX_PIT register from a book-keeping
+ * structure that we guarantee is already ordered correctly, and has no more
+ * than 3 entries.
+ *
+ * To make things easier, we only support flexible values of one word length,
+ * rather than allowing variable length flexible values.
+ **/
+static void __i40e_reprogram_flex_pit(struct i40e_pf *pf,
+				      struct list_head *flex_pit_list,
+				      int flex_pit_start)
+{
+	struct i40e_flex_pit *entry = NULL;
+	u16 last_offset = 0;
+	int i = 0, j = 0;
+
+	/* First, loop over the list of flex PIT entries, and reprogram the
+	 * registers.
+	 */
+	list_for_each_entry(entry, flex_pit_list, list) {
+		/* We have to be careful when programming values for the
+		 * largest SRC_OFFSET value. It is possible that adding
+		 * additional empty values at the end would overflow the space
+		 * for the SRC_OFFSET in the FLX_PIT register. To avoid this,
+		 * we check here and add the empty values prior to adding the
+		 * largest value.
+		 *
+		 * To determine this, we will use a loop from i+1 to 3, which
+		 * will determine whether the unused entries would have valid
+		 * SRC_OFFSET. Note that there cannot be extra entries past
+		 * this value, because the only valid values would have been
+		 * larger than I40E_MAX_FLEX_SRC_OFFSET, and thus would not
+		 * have been added to the list in the first place.
+		 */
+		for (j = i + 1; j < 3; j++) {
+			u16 offset = entry->src_offset + j;
+			int index = flex_pit_start + i;
+			u32 value = I40E_FLEX_PREP_VAL(I40E_FLEX_DEST_UNUSED,
+						       1,
+						       offset - 3);
+
+			if (offset > I40E_MAX_FLEX_SRC_OFFSET) {
+				i40e_write_rx_ctl(&pf->hw,
+						  I40E_PRTQF_FLX_PIT(index),
+						  value);
+				i++;
+			}
+		}
+
+		/* Now, we can program the actual value into the table */
+		i40e_write_rx_ctl(&pf->hw,
+				  I40E_PRTQF_FLX_PIT(flex_pit_start + i),
+				  I40E_FLEX_PREP_VAL(entry->pit_index + 50,
+						     1,
+						     entry->src_offset));
+		i++;
+	}
+
+	/* In order to program the last entries in the table, we need to
+	 * determine the valid offset. If the list is empty, we'll just start
+	 * with 0. Otherwise, we'll start with the last item offset and add 1.
+	 * This ensures that all entries have valid sizes. If we don't do this
+	 * correctly, the hardware will disable flexible field parsing.
+	 */
+	if (!list_empty(flex_pit_list))
+		last_offset = list_prev_entry(entry, list)->src_offset + 1;
+
+	for (; i < 3; i++, last_offset++) {
+		i40e_write_rx_ctl(&pf->hw,
+				  I40E_PRTQF_FLX_PIT(flex_pit_start + i),
+				  I40E_FLEX_PREP_VAL(I40E_FLEX_DEST_UNUSED,
+						     1,
+						     last_offset));
+	}
+}
+
+/**
+ * i40e_reprogram_flex_pit - Reprogram all FLX_PIT tables after input set change
+ * @pf: pointer to the PF structure
+ *
+ * This function reprograms both the L3 and L4 FLX_PIT tables. See the
+ * internal helper function for implementation details.
+ **/
+static void i40e_reprogram_flex_pit(struct i40e_pf *pf)
+{
+	__i40e_reprogram_flex_pit(pf, &pf->l3_flex_pit_list,
+				  I40E_FLEX_PIT_IDX_START_L3);
+
+	__i40e_reprogram_flex_pit(pf, &pf->l4_flex_pit_list,
+				  I40E_FLEX_PIT_IDX_START_L4);
+
+	/* We also need to program the L3 and L4 GLQF ORT register */
+	i40e_write_rx_ctl(&pf->hw,
+			  I40E_GLQF_ORT(I40E_L3_GLQF_ORT_IDX),
+			  I40E_ORT_PREP_VAL(I40E_FLEX_PIT_IDX_START_L3,
+					    3, 1));
+
+	i40e_write_rx_ctl(&pf->hw,
+			  I40E_GLQF_ORT(I40E_L4_GLQF_ORT_IDX),
+			  I40E_ORT_PREP_VAL(I40E_FLEX_PIT_IDX_START_L4,
+					    3, 1));
+}
+
+/**
+ * i40e_flow_str - Converts a flow_type into a human readable string
+ * @flow_type: the flow type from a flow specification
+ *
+ * Currently only flow types we support are included here, and the string
+ * value attempts to match what ethtool would use to configure this flow type.
+ **/
+static const char *i40e_flow_str(struct ethtool_rx_flow_spec *fsp)
+{
+	switch (fsp->flow_type & ~FLOW_EXT) {
+	case TCP_V4_FLOW:
+		return "tcp4";
+	case UDP_V4_FLOW:
+		return "udp4";
+	case SCTP_V4_FLOW:
+		return "sctp4";
+	case IP_USER_FLOW:
+		return "ip4";
+	default:
+		return "unknown";
+	}
+}
+
+/**
+ * i40e_pit_index_to_mask - Return the FLEX mask for a given PIT index
+ * @pit_index: PIT index to convert
+ *
+ * Returns the mask for a given PIT index. Will return 0 if the pit_index is
+ * of range.
+ **/
+static u64 i40e_pit_index_to_mask(int pit_index)
+{
+	switch (pit_index) {
+	case 0:
+		return I40E_FLEX_50_MASK;
+	case 1:
+		return I40E_FLEX_51_MASK;
+	case 2:
+		return I40E_FLEX_52_MASK;
+	case 3:
+		return I40E_FLEX_53_MASK;
+	case 4:
+		return I40E_FLEX_54_MASK;
+	case 5:
+		return I40E_FLEX_55_MASK;
+	case 6:
+		return I40E_FLEX_56_MASK;
+	case 7:
+		return I40E_FLEX_57_MASK;
+	default:
+		return 0;
+	}
+}
+
+/**
+ * i40e_print_input_set - Show changes between two input sets
+ * @vsi: the vsi being configured
+ * @old: the old input set
+ * @new: the new input set
+ *
+ * Print the difference between old and new input sets by showing which series
+ * of words are toggled on or off. Only displays the bits we actually support
+ * changing.
+ **/
+static void i40e_print_input_set(struct i40e_vsi *vsi, u64 old, u64 new)
+{
+	struct i40e_pf *pf = vsi->back;
+	bool old_value, new_value;
+	int i;
+
+	old_value = !!(old & I40E_L3_SRC_MASK);
+	new_value = !!(new & I40E_L3_SRC_MASK);
+	if (old_value != new_value)
+		netif_info(pf, drv, vsi->netdev, "L3 source address: %s -> %s\n",
+			   old_value ? "ON" : "OFF",
+			   new_value ? "ON" : "OFF");
+
+	old_value = !!(old & I40E_L3_DST_MASK);
+	new_value = !!(new & I40E_L3_DST_MASK);
+	if (old_value != new_value)
+		netif_info(pf, drv, vsi->netdev, "L3 destination address: %s -> %s\n",
+			   old_value ? "ON" : "OFF",
+			   new_value ? "ON" : "OFF");
+
+	old_value = !!(old & I40E_L4_SRC_MASK);
+	new_value = !!(new & I40E_L4_SRC_MASK);
+	if (old_value != new_value)
+		netif_info(pf, drv, vsi->netdev, "L4 source port: %s -> %s\n",
+			   old_value ? "ON" : "OFF",
+			   new_value ? "ON" : "OFF");
+
+	old_value = !!(old & I40E_L4_DST_MASK);
+	new_value = !!(new & I40E_L4_DST_MASK);
+	if (old_value != new_value)
+		netif_info(pf, drv, vsi->netdev, "L4 destination port: %s -> %s\n",
+			   old_value ? "ON" : "OFF",
+			   new_value ? "ON" : "OFF");
+
+	old_value = !!(old & I40E_VERIFY_TAG_MASK);
+	new_value = !!(new & I40E_VERIFY_TAG_MASK);
+	if (old_value != new_value)
+		netif_info(pf, drv, vsi->netdev, "SCTP verification tag: %s -> %s\n",
+			   old_value ? "ON" : "OFF",
+			   new_value ? "ON" : "OFF");
+
+	/* Show change of flexible filter entries */
+	for (i = 0; i < I40E_FLEX_INDEX_ENTRIES; i++) {
+		u64 flex_mask = i40e_pit_index_to_mask(i);
+
+		old_value = !!(old & flex_mask);
+		new_value = !!(new & flex_mask);
+		if (old_value != new_value)
+			netif_info(pf, drv, vsi->netdev, "FLEX index %d: %s -> %s\n",
+				   i,
+				   old_value ? "ON" : "OFF",
+				   new_value ? "ON" : "OFF");
+	}
+
+	netif_info(pf, drv, vsi->netdev, "  Current input set: %0llx\n",
+		   old);
+	netif_info(pf, drv, vsi->netdev, "Requested input set: %0llx\n",
+		   new);
+}
+
+/**
+ * i40e_check_fdir_input_set - Check that a given rx_flow_spec mask is valid
+ * @vsi: pointer to the targeted VSI
+ * @fsp: pointer to Rx flow specification
+ * @userdef: userdefined data from flow specification
+ *
+ * Ensures that a given ethtool_rx_flow_spec has a valid mask. Some support
+ * for partial matches exists with a few limitations. First, hardware only
+ * supports masking by word boundary (2 bytes) and not per individual bit.
+ * Second, hardware is limited to using one mask for a flow type and cannot
+ * use a separate mask for each filter.
+ *
+ * To support these limitations, if we already have a configured filter for
+ * the specified type, this function enforces that new filters of the type
+ * match the configured input set. Otherwise, if we do not have a filter of
+ * the specified type, we allow the input set to be updated to match the
+ * desired filter.
+ *
+ * To help ensure that administrators understand why filters weren't displayed
+ * as supported, we print a diagnostic message displaying how the input set
+ * would change and warning to delete the preexisting filters if required.
+ *
+ * Returns 0 on successful input set match, and a negative return code on
+ * failure.
+ **/
+static int i40e_check_fdir_input_set(struct i40e_vsi *vsi,
+				     struct ethtool_rx_flow_spec *fsp,
+				     struct i40e_rx_flow_userdef *userdef)
+{
+	struct i40e_pf *pf = vsi->back;
+	struct ethtool_tcpip4_spec *tcp_ip4_spec;
+	struct ethtool_usrip4_spec *usr_ip4_spec;
+	u64 current_mask, new_mask;
+	bool new_flex_offset = false;
+	bool flex_l3 = false;
+	u16 *fdir_filter_count;
+	u16 index, src_offset = 0;
+	u8 pit_index = 0;
+	int err;
+
+	switch (fsp->flow_type & ~FLOW_EXT) {
+	case SCTP_V4_FLOW:
+		index = I40E_FILTER_PCTYPE_NONF_IPV4_SCTP;
+		fdir_filter_count = &pf->fd_sctp4_filter_cnt;
+		break;
+	case TCP_V4_FLOW:
+		index = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+		fdir_filter_count = &pf->fd_tcp4_filter_cnt;
+		break;
+	case UDP_V4_FLOW:
+		index = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
+		fdir_filter_count = &pf->fd_udp4_filter_cnt;
+		break;
+	case IP_USER_FLOW:
+		index = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER;
+		fdir_filter_count = &pf->fd_ip4_filter_cnt;
+		flex_l3 = true;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	/* Read the current input set from register memory. */
+	current_mask = i40e_read_fd_input_set(pf, index);
+	new_mask = current_mask;
+
+	/* Determine, if any, the required changes to the input set in order
+	 * to support the provided mask.
+	 *
+	 * Hardware only supports masking at word (2 byte) granularity and does
+	 * not support full bitwise masking. This implementation simplifies
+	 * even further and only supports fully enabled or fully disabled
+	 * masks for each field, even though we could split the ip4src and
+	 * ip4dst fields.
+	 */
+	switch (fsp->flow_type & ~FLOW_EXT) {
+	case SCTP_V4_FLOW:
+		new_mask &= ~I40E_VERIFY_TAG_MASK;
+		/* Fall through */
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+		tcp_ip4_spec = &fsp->m_u.tcp_ip4_spec;
+
+		/* IPv4 source address */
+		if (tcp_ip4_spec->ip4src == htonl(0xFFFFFFFF))
+			new_mask |= I40E_L3_SRC_MASK;
+		else if (!tcp_ip4_spec->ip4src)
+			new_mask &= ~I40E_L3_SRC_MASK;
+		else
+			return -EOPNOTSUPP;
+
+		/* IPv4 destination address */
+		if (tcp_ip4_spec->ip4dst == htonl(0xFFFFFFFF))
+			new_mask |= I40E_L3_DST_MASK;
+		else if (!tcp_ip4_spec->ip4dst)
+			new_mask &= ~I40E_L3_DST_MASK;
+		else
+			return -EOPNOTSUPP;
+
+		/* L4 source port */
+		if (tcp_ip4_spec->psrc == htons(0xFFFF))
+			new_mask |= I40E_L4_SRC_MASK;
+		else if (!tcp_ip4_spec->psrc)
+			new_mask &= ~I40E_L4_SRC_MASK;
+		else
+			return -EOPNOTSUPP;
+
+		/* L4 destination port */
+		if (tcp_ip4_spec->pdst == htons(0xFFFF))
+			new_mask |= I40E_L4_DST_MASK;
+		else if (!tcp_ip4_spec->pdst)
+			new_mask &= ~I40E_L4_DST_MASK;
+		else
+			return -EOPNOTSUPP;
+
+		/* Filtering on Type of Service is not supported. */
+		if (tcp_ip4_spec->tos)
+			return -EOPNOTSUPP;
+
+		break;
+	case IP_USER_FLOW:
+		usr_ip4_spec = &fsp->m_u.usr_ip4_spec;
+
+		/* IPv4 source address */
+		if (usr_ip4_spec->ip4src == htonl(0xFFFFFFFF))
+			new_mask |= I40E_L3_SRC_MASK;
+		else if (!usr_ip4_spec->ip4src)
+			new_mask &= ~I40E_L3_SRC_MASK;
+		else
+			return -EOPNOTSUPP;
+
+		/* IPv4 destination address */
+		if (usr_ip4_spec->ip4dst == htonl(0xFFFFFFFF))
+			new_mask |= I40E_L3_DST_MASK;
+		else if (!usr_ip4_spec->ip4dst)
+			new_mask &= ~I40E_L3_DST_MASK;
+		else
+			return -EOPNOTSUPP;
+
+		/* First 4 bytes of L4 header */
+		if (usr_ip4_spec->l4_4_bytes == htonl(0xFFFFFFFF))
+			new_mask |= I40E_L4_SRC_MASK | I40E_L4_DST_MASK;
+		else if (!usr_ip4_spec->l4_4_bytes)
+			new_mask &= ~(I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
+		else
+			return -EOPNOTSUPP;
+
+		/* Filtering on Type of Service is not supported. */
+		if (usr_ip4_spec->tos)
+			return -EOPNOTSUPP;
+
+		/* Filtering on IP version is not supported */
+		if (usr_ip4_spec->ip_ver)
+			return -EINVAL;
+
+		/* Filtering on L4 protocol is not supported */
+		if (usr_ip4_spec->proto)
+			return -EINVAL;
+
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	/* First, clear all flexible filter entries */
+	new_mask &= ~I40E_FLEX_INPUT_MASK;
+
+	/* If we have a flexible filter, try to add this offset to the correct
+	 * flexible filter PIT list. Once finished, we can update the mask.
+	 * If the src_offset changed, we will get a new mask value which will
+	 * trigger an input set change.
+	 */
+	if (userdef->flex_filter) {
+		struct i40e_flex_pit *l3_flex_pit = NULL, *flex_pit = NULL;
+
+		/* Flexible offset must be even, since the flexible payload
+		 * must be aligned on 2-byte boundary.
+		 */
+		if (userdef->flex_offset & 0x1) {
+			dev_warn(&pf->pdev->dev,
+				 "Flexible data offset must be 2-byte aligned\n");
+			return -EINVAL;
+		}
+
+		src_offset = userdef->flex_offset >> 1;
+
+		/* FLX_PIT source offset value is only so large */
+		if (src_offset > I40E_MAX_FLEX_SRC_OFFSET) {
+			dev_warn(&pf->pdev->dev,
+				 "Flexible data must reside within first 64 bytes of the packet payload\n");
+			return -EINVAL;
+		}
+
+		/* See if this offset has already been programmed. If we get
+		 * an ERR_PTR, then the filter is not safe to add. Otherwise,
+		 * if we get a NULL pointer, this means we will need to add
+		 * the offset.
+		 */
+		flex_pit = i40e_find_flex_offset(&pf->l4_flex_pit_list,
+						 src_offset);
+		if (IS_ERR(flex_pit))
+			return PTR_ERR(flex_pit);
+
+		/* IP_USER_FLOW filters match both L4 (ICMP) and L3 (unknown)
+		 * packet types, and thus we need to program both L3 and L4
+		 * flexible values. These must have identical flexible index,
+		 * as otherwise we can't correctly program the input set. So
+		 * we'll find both an L3 and L4 index and make sure they are
+		 * the same.
+		 */
+		if (flex_l3) {
+			l3_flex_pit =
+				i40e_find_flex_offset(&pf->l3_flex_pit_list,
+						      src_offset);
+			if (IS_ERR(l3_flex_pit))
+				return PTR_ERR(l3_flex_pit);
+
+			if (flex_pit) {
+				/* If we already had a matching L4 entry, we
+				 * need to make sure that the L3 entry we
+				 * obtained uses the same index.
+				 */
+				if (l3_flex_pit) {
+					if (l3_flex_pit->pit_index !=
+					    flex_pit->pit_index) {
+						return -EINVAL;
+					}
+				} else {
+					new_flex_offset = true;
+				}
+			} else {
+				flex_pit = l3_flex_pit;
+			}
+		}
+
+		/* If we didn't find an existing flex offset, we need to
+		 * program a new one. However, we don't immediately program it
+		 * here because we will wait to program until after we check
+		 * that it is safe to change the input set.
+		 */
+		if (!flex_pit) {
+			new_flex_offset = true;
+			pit_index = i40e_unused_pit_index(pf);
+		} else {
+			pit_index = flex_pit->pit_index;
+		}
+
+		/* Update the mask with the new offset */
+		new_mask |= i40e_pit_index_to_mask(pit_index);
+	}
+
+	/* If the mask and flexible filter offsets for this filter match the
+	 * currently programmed values we don't need any input set change, so
+	 * this filter is safe to install.
+	 */
+	if (new_mask == current_mask && !new_flex_offset)
+		return 0;
+
+	netif_info(pf, drv, vsi->netdev, "Input set change requested for %s flows:\n",
+		   i40e_flow_str(fsp));
+	i40e_print_input_set(vsi, current_mask, new_mask);
+	if (new_flex_offset) {
+		netif_info(pf, drv, vsi->netdev, "FLEX index %d: Offset -> %d",
+			   pit_index, src_offset);
+	}
+
+	/* Hardware input sets are global across multiple ports, so even the
+	 * main port cannot change them when in MFP mode as this would impact
+	 * any filters on the other ports.
+	 */
+	if (pf->flags & I40E_FLAG_MFP_ENABLED) {
+		netif_err(pf, drv, vsi->netdev, "Cannot change Flow Director input sets while MFP is enabled\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* This filter requires us to update the input set. However, hardware
+	 * only supports one input set per flow type, and does not support
+	 * separate masks for each filter. This means that we can only support
+	 * a single mask for all filters of a specific type.
+	 *
+	 * If we have preexisting filters, they obviously depend on the
+	 * current programmed input set. Display a diagnostic message in this
+	 * case explaining why the filter could not be accepted.
+	 */
+	if (*fdir_filter_count) {
+		netif_err(pf, drv, vsi->netdev, "Cannot change input set for %s flows until %d preexisting filters are removed\n",
+			  i40e_flow_str(fsp),
+			  *fdir_filter_count);
+		return -EOPNOTSUPP;
+	}
+
+	i40e_write_fd_input_set(pf, index, new_mask);
+
+	/* Add the new offset and update table, if necessary */
+	if (new_flex_offset) {
+		err = i40e_add_flex_offset(&pf->l4_flex_pit_list, src_offset,
+					   pit_index);
+		if (err)
+			return err;
+
+		if (flex_l3) {
+			err = i40e_add_flex_offset(&pf->l3_flex_pit_list,
+						   src_offset,
+						   pit_index);
+			if (err)
+				return err;
+		}
+
+		i40e_reprogram_flex_pit(pf);
+	}
+
+	return 0;
+}
+
+/**
  * i40e_add_fdir_ethtool - Add/Remove Flow Director filters
  * @vsi: pointer to the targeted VSI
  * @cmd: command to get or set RX flow classification rules
@@ -2699,11 +3609,13 @@ static int i40e_del_fdir_entry(struct i40e_vsi *vsi,
 static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 				 struct ethtool_rxnfc *cmd)
 {
+	struct i40e_rx_flow_userdef userdef;
 	struct ethtool_rx_flow_spec *fsp;
 	struct i40e_fdir_filter *input;
+	u16 dest_vsi = 0, q_index = 0;
 	struct i40e_pf *pf;
 	int ret = -EINVAL;
-	u16 vf_id;
+	u8 dest_ctl;
 
 	if (!vsi)
 		return -EINVAL;
@@ -2712,7 +3624,7 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 	if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
 		return -EOPNOTSUPP;
 
-	if (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)
+	if (pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED)
 		return -ENOSPC;
 
 	if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) ||
@@ -2724,14 +3636,49 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 
 	fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
 
+	/* Parse the user-defined field */
+	if (i40e_parse_rx_flow_user_data(fsp, &userdef))
+		return -EINVAL;
+
+	/* Extended MAC field is not supported */
+	if (fsp->flow_type & FLOW_MAC_EXT)
+		return -EINVAL;
+
+	ret = i40e_check_fdir_input_set(vsi, fsp, &userdef);
+	if (ret)
+		return ret;
+
 	if (fsp->location >= (pf->hw.func_caps.fd_filters_best_effort +
 			      pf->hw.func_caps.fd_filters_guaranteed)) {
 		return -EINVAL;
 	}
 
-	if ((fsp->ring_cookie != RX_CLS_FLOW_DISC) &&
-	    (fsp->ring_cookie >= vsi->num_queue_pairs))
-		return -EINVAL;
+	/* ring_cookie is either the drop index, or is a mask of the queue
+	 * index and VF id we wish to target.
+	 */
+	if (fsp->ring_cookie == RX_CLS_FLOW_DISC) {
+		dest_ctl = I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET;
+	} else {
+		u32 ring = ethtool_get_flow_spec_ring(fsp->ring_cookie);
+		u8 vf = ethtool_get_flow_spec_ring_vf(fsp->ring_cookie);
+
+		if (!vf) {
+			if (ring >= vsi->num_queue_pairs)
+				return -EINVAL;
+			dest_vsi = vsi->id;
+		} else {
+			/* VFs are zero-indexed, so we subtract one here */
+			vf--;
+
+			if (vf >= pf->num_alloc_vfs)
+				return -EINVAL;
+			if (ring >= pf->vf[vf].num_queue_pairs)
+				return -EINVAL;
+			dest_vsi = pf->vf[vf].lan_vsi_id;
+		}
+		dest_ctl = I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX;
+		q_index = ring;
+	}
 
 	input = kzalloc(sizeof(*input), GFP_KERNEL);
 
@@ -2739,20 +3686,14 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 		return -ENOMEM;
 
 	input->fd_id = fsp->location;
-
-	if (fsp->ring_cookie == RX_CLS_FLOW_DISC)
-		input->dest_ctl = I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET;
-	else
-		input->dest_ctl =
-			     I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX;
-
-	input->q_index = fsp->ring_cookie;
-	input->flex_off = 0;
-	input->pctype = 0;
-	input->dest_vsi = vsi->id;
+	input->q_index = q_index;
+	input->dest_vsi = dest_vsi;
+	input->dest_ctl = dest_ctl;
 	input->fd_status = I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID;
 	input->cnt_index  = I40E_FD_SB_STAT_IDX(pf->hw.pf_id);
-	input->flow_type = fsp->flow_type;
+	input->dst_ip = fsp->h_u.tcp_ip4_spec.ip4src;
+	input->src_ip = fsp->h_u.tcp_ip4_spec.ip4dst;
+	input->flow_type = fsp->flow_type & ~FLOW_EXT;
 	input->ip4_proto = fsp->h_u.usr_ip4_spec.proto;
 
 	/* Reverse the src and dest notion, since the HW expects them to be from
@@ -2760,33 +3701,29 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 	 */
 	input->dst_port = fsp->h_u.tcp_ip4_spec.psrc;
 	input->src_port = fsp->h_u.tcp_ip4_spec.pdst;
-	input->dst_ip[0] = fsp->h_u.tcp_ip4_spec.ip4src;
-	input->src_ip[0] = fsp->h_u.tcp_ip4_spec.ip4dst;
-
-	if (ntohl(fsp->m_ext.data[1])) {
-		vf_id = ntohl(fsp->h_ext.data[1]);
-		if (vf_id >= pf->num_alloc_vfs) {
-			netif_info(pf, drv, vsi->netdev,
-				   "Invalid VF id %d\n", vf_id);
-			goto free_input;
-		}
-		/* Find vsi id from vf id and override dest vsi */
-		input->dest_vsi = pf->vf[vf_id].lan_vsi_id;
-		if (input->q_index >= pf->vf[vf_id].num_queue_pairs) {
-			netif_info(pf, drv, vsi->netdev,
-				   "Invalid queue id %d for VF %d\n",
-				   input->q_index, vf_id);
-			goto free_input;
-		}
+	input->dst_ip = fsp->h_u.tcp_ip4_spec.ip4src;
+	input->src_ip = fsp->h_u.tcp_ip4_spec.ip4dst;
+
+	if (userdef.flex_filter) {
+		input->flex_filter = true;
+		input->flex_word = cpu_to_be16(userdef.flex_word);
+		input->flex_offset = userdef.flex_offset;
 	}
 
 	ret = i40e_add_del_fdir(vsi, input, true);
-free_input:
 	if (ret)
-		kfree(input);
-	else
-		i40e_update_ethtool_fdir_entry(vsi, input, fsp->location, NULL);
+		goto free_input;
+
+	/* Add the input filter to the fdir_input_list, possibly replacing
+	 * a previous filter. Do not free the input structure after adding it
+	 * to the list as this would cause a use-after-free bug.
+	 */
+	i40e_update_ethtool_fdir_entry(vsi, input, fsp->location, NULL);
 
+	return 0;
+
+free_input:
+	kfree(input);
 	return ret;
 }
 
@@ -3036,7 +3973,7 @@ static int i40e_set_rxfh(struct net_device *netdev, const u32 *indir,
  * @dev: network interface device structure
  *
  * The get string set count and the string set should be matched for each
- * flag returned.  Add new strings for each flag to the i40e_priv_flags_strings
+ * flag returned.  Add new strings for each flag to the i40e_gstrings_priv_flags
  * array.
  *
  * Returns a u32 bitmap of flags.
@@ -3046,19 +3983,27 @@ static u32 i40e_get_priv_flags(struct net_device *dev)
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
-	u32 ret_flags = 0;
+	u32 i, j, ret_flags = 0;
+
+	for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) {
+		const struct i40e_priv_flags *priv_flags;
+
+		priv_flags = &i40e_gstrings_priv_flags[i];
+
+		if (priv_flags->flag & pf->flags)
+			ret_flags |= BIT(i);
+	}
+
+	if (pf->hw.pf_id != 0)
+		return ret_flags;
+
+	for (j = 0; j < I40E_GL_PRIV_FLAGS_STR_LEN; j++) {
+		const struct i40e_priv_flags *priv_flags;
 
-	ret_flags |= pf->flags & I40E_FLAG_LINK_POLLING_ENABLED ?
-		I40E_PRIV_FLAGS_LINKPOLL_FLAG : 0;
-	ret_flags |= pf->flags & I40E_FLAG_FD_ATR_ENABLED ?
-		I40E_PRIV_FLAGS_FD_ATR : 0;
-	ret_flags |= pf->flags & I40E_FLAG_VEB_STATS_ENABLED ?
-		I40E_PRIV_FLAGS_VEB_STATS : 0;
-	ret_flags |= pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE ?
-		0 : I40E_PRIV_FLAGS_HW_ATR_EVICT;
-	if (pf->hw.pf_id == 0) {
-		ret_flags |= pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT ?
-			I40E_PRIV_FLAGS_TRUE_PROMISC_SUPPORT : 0;
+		priv_flags = &i40e_gl_gstrings_priv_flags[j];
+
+		if (priv_flags->flag & pf->flags)
+			ret_flags |= BIT(i + j);
 	}
 
 	return ret_flags;
@@ -3074,54 +4019,66 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
-	u16 sw_flags = 0, valid_flags = 0;
-	bool reset_required = false;
-	bool promisc_change = false;
-	int ret;
+	u64 changed_flags;
+	u32 i, j;
 
-	/* NOTE: MFP is not settable */
+	changed_flags = pf->flags;
 
-	if (flags & I40E_PRIV_FLAGS_LINKPOLL_FLAG)
-		pf->flags |= I40E_FLAG_LINK_POLLING_ENABLED;
-	else
-		pf->flags &= ~I40E_FLAG_LINK_POLLING_ENABLED;
+	for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) {
+		const struct i40e_priv_flags *priv_flags;
 
-	/* allow the user to control the state of the Flow
-	 * Director ATR (Application Targeted Routing) feature
-	 * of the driver
+		priv_flags = &i40e_gstrings_priv_flags[i];
+
+		if (priv_flags->read_only)
+			continue;
+
+		if (flags & BIT(i))
+			pf->flags |= priv_flags->flag;
+		else
+			pf->flags &= ~(priv_flags->flag);
+	}
+
+	if (pf->hw.pf_id != 0)
+		goto flags_complete;
+
+	for (j = 0; j < I40E_GL_PRIV_FLAGS_STR_LEN; j++) {
+		const struct i40e_priv_flags *priv_flags;
+
+		priv_flags = &i40e_gl_gstrings_priv_flags[j];
+
+		if (priv_flags->read_only)
+			continue;
+
+		if (flags & BIT(i + j))
+			pf->flags |= priv_flags->flag;
+		else
+			pf->flags &= ~(priv_flags->flag);
+	}
+
+flags_complete:
+	/* check for flags that changed */
+	changed_flags ^= pf->flags;
+
+	/* Process any additional changes needed as a result of flag changes.
+	 * The changed_flags value reflects the list of bits that were
+	 * changed in the code above.
 	 */
-	if (flags & I40E_PRIV_FLAGS_FD_ATR) {
-		pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
-	} else {
-		pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED;
-		pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
 
-		/* flush current ATR settings */
+	/* Flush current ATR settings if ATR was disabled */
+	if ((changed_flags & I40E_FLAG_FD_ATR_ENABLED) &&
+	    !(pf->flags & I40E_FLAG_FD_ATR_ENABLED)) {
+		pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED;
 		set_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
 	}
 
-	if ((flags & I40E_PRIV_FLAGS_VEB_STATS) &&
-	    !(pf->flags & I40E_FLAG_VEB_STATS_ENABLED)) {
-		pf->flags |= I40E_FLAG_VEB_STATS_ENABLED;
-		reset_required = true;
-	} else if (!(flags & I40E_PRIV_FLAGS_VEB_STATS) &&
-		   (pf->flags & I40E_FLAG_VEB_STATS_ENABLED)) {
-		pf->flags &= ~I40E_FLAG_VEB_STATS_ENABLED;
-		reset_required = true;
-	}
-
-	if (pf->hw.pf_id == 0) {
-		if ((flags & I40E_PRIV_FLAGS_TRUE_PROMISC_SUPPORT) &&
-		    !(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT)) {
-			pf->flags |= I40E_FLAG_TRUE_PROMISC_SUPPORT;
-			promisc_change = true;
-		} else if (!(flags & I40E_PRIV_FLAGS_TRUE_PROMISC_SUPPORT) &&
-			   (pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT)) {
-			pf->flags &= ~I40E_FLAG_TRUE_PROMISC_SUPPORT;
-			promisc_change = true;
-		}
-	}
-	if (promisc_change) {
+	/* Only allow ATR evict on hardware that is capable of handling it */
+	if (pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)
+		pf->flags &= ~I40E_FLAG_HW_ATR_EVICT_CAPABLE;
+
+	if (changed_flags & I40E_FLAG_TRUE_PROMISC_SUPPORT) {
+		u16 sw_flags = 0, valid_flags = 0;
+		int ret;
+
 		if (!(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT))
 			sw_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
 		valid_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
@@ -3137,22 +4094,17 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
 		}
 	}
 
-	if ((flags & I40E_PRIV_FLAGS_HW_ATR_EVICT) &&
-	    (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))
-		pf->auto_disable_flags &= ~I40E_FLAG_HW_ATR_EVICT_CAPABLE;
-	else
-		pf->auto_disable_flags |= I40E_FLAG_HW_ATR_EVICT_CAPABLE;
-
-	/* if needed, issue reset to cause things to take effect */
-	if (reset_required)
+	/* Issue reset to cause things to take effect, as additional bits
+	 * are added we will need to create a mask of bits requiring reset
+	 */
+	if ((changed_flags & I40E_FLAG_VEB_STATS_ENABLED) ||
+	    ((changed_flags & I40E_FLAG_LEGACY_RX) && netif_running(dev)))
 		i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED));
 
 	return 0;
 }
 
 static const struct ethtool_ops i40e_ethtool_ops = {
-	.get_settings		= i40e_get_settings,
-	.set_settings		= i40e_set_settings,
 	.get_drvinfo		= i40e_get_drvinfo,
 	.get_regs_len		= i40e_get_regs_len,
 	.get_regs		= i40e_get_regs,
@@ -3189,6 +4141,8 @@ static const struct ethtool_ops i40e_ethtool_ops = {
 	.set_priv_flags		= i40e_set_priv_flags,
 	.get_per_queue_coalesce	= i40e_get_per_queue_coalesce,
 	.set_per_queue_coalesce	= i40e_set_per_queue_coalesce,
+	.get_link_ksettings	= i40e_get_link_ksettings,
+	.set_link_ksettings	= i40e_set_link_ksettings,
 };
 
 void i40e_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 82a95cc2c8ee..703444e92964 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -39,9 +39,9 @@ static const char i40e_driver_string[] =
 
 #define DRV_KERN "-k"
 
-#define DRV_VERSION_MAJOR 1
-#define DRV_VERSION_MINOR 6
-#define DRV_VERSION_BUILD 27
+#define DRV_VERSION_MAJOR 2
+#define DRV_VERSION_MINOR 1
+#define DRV_VERSION_BUILD 7
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
@@ -299,11 +299,7 @@ void i40e_service_event_schedule(struct i40e_pf *pf)
  * device is munged, not just the one netdev port, so go for the full
  * reset.
  **/
-#ifdef I40E_FCOE
-void i40e_tx_timeout(struct net_device *netdev)
-#else
 static void i40e_tx_timeout(struct net_device *netdev)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -408,10 +404,7 @@ struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi)
  * Returns the address of the device statistics structure.
  * The statistics are actually updated from the service task.
  **/
-#ifndef I40E_FCOE
-static
-#endif
-void i40e_get_netdev_stats_struct(struct net_device *netdev,
+static void i40e_get_netdev_stats_struct(struct net_device *netdev,
 				  struct rtnl_link_stats64 *stats)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
@@ -723,55 +716,6 @@ static void i40e_update_veb_stats(struct i40e_veb *veb)
 	veb->stat_offsets_loaded = true;
 }
 
-#ifdef I40E_FCOE
-/**
- * i40e_update_fcoe_stats - Update FCoE-specific ethernet statistics counters.
- * @vsi: the VSI that is capable of doing FCoE
- **/
-static void i40e_update_fcoe_stats(struct i40e_vsi *vsi)
-{
-	struct i40e_pf *pf = vsi->back;
-	struct i40e_hw *hw = &pf->hw;
-	struct i40e_fcoe_stats *ofs;
-	struct i40e_fcoe_stats *fs;     /* device's eth stats */
-	int idx;
-
-	if (vsi->type != I40E_VSI_FCOE)
-		return;
-
-	idx = hw->pf_id + I40E_FCOE_PF_STAT_OFFSET;
-	fs = &vsi->fcoe_stats;
-	ofs = &vsi->fcoe_stats_offsets;
-
-	i40e_stat_update32(hw, I40E_GL_FCOEPRC(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->rx_fcoe_packets, &fs->rx_fcoe_packets);
-	i40e_stat_update48(hw, I40E_GL_FCOEDWRCH(idx), I40E_GL_FCOEDWRCL(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->rx_fcoe_dwords, &fs->rx_fcoe_dwords);
-	i40e_stat_update32(hw, I40E_GL_FCOERPDC(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->rx_fcoe_dropped, &fs->rx_fcoe_dropped);
-	i40e_stat_update32(hw, I40E_GL_FCOEPTC(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->tx_fcoe_packets, &fs->tx_fcoe_packets);
-	i40e_stat_update48(hw, I40E_GL_FCOEDWTCH(idx), I40E_GL_FCOEDWTCL(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->tx_fcoe_dwords, &fs->tx_fcoe_dwords);
-	i40e_stat_update32(hw, I40E_GL_FCOECRC(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->fcoe_bad_fccrc, &fs->fcoe_bad_fccrc);
-	i40e_stat_update32(hw, I40E_GL_FCOELAST(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->fcoe_last_error, &fs->fcoe_last_error);
-	i40e_stat_update32(hw, I40E_GL_FCOEDDPC(idx),
-			   vsi->fcoe_stat_offsets_loaded,
-			   &ofs->fcoe_ddp_count, &fs->fcoe_ddp_count);
-
-	vsi->fcoe_stat_offsets_loaded = true;
-}
-
-#endif
 /**
  * i40e_update_vsi_stats - Update the vsi statistics counters.
  * @vsi: the VSI to be updated
@@ -1101,13 +1045,13 @@ static void i40e_update_pf_stats(struct i40e_pf *pf)
 			   &osd->rx_lpi_count, &nsd->rx_lpi_count);
 
 	if (pf->flags & I40E_FLAG_FD_SB_ENABLED &&
-	    !(pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED))
+	    !(pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED))
 		nsd->fd_sb_status = true;
 	else
 		nsd->fd_sb_status = false;
 
 	if (pf->flags & I40E_FLAG_FD_ATR_ENABLED &&
-	    !(pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED))
+	    !(pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED))
 		nsd->fd_atr_status = true;
 	else
 		nsd->fd_atr_status = false;
@@ -1129,9 +1073,6 @@ void i40e_update_stats(struct i40e_vsi *vsi)
 		i40e_update_pf_stats(pf);
 
 	i40e_update_vsi_stats(vsi);
-#ifdef I40E_FCOE
-	i40e_update_fcoe_stats(vsi);
-#endif
 }
 
 /**
@@ -1562,11 +1503,7 @@ int i40e_del_mac_filter(struct i40e_vsi *vsi, const u8 *macaddr)
  *
  * Returns 0 on success, negative on failure
  **/
-#ifdef I40E_FCOE
-int i40e_set_mac(struct net_device *netdev, void *p)
-#else
 static int i40e_set_mac(struct net_device *netdev, void *p)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -1626,17 +1563,10 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
  *
  * Setup VSI queue mapping for enabled traffic classes.
  **/
-#ifdef I40E_FCOE
-void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
-			      struct i40e_vsi_context *ctxt,
-			      u8 enabled_tc,
-			      bool is_add)
-#else
 static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 				     struct i40e_vsi_context *ctxt,
 				     u8 enabled_tc,
 				     bool is_add)
-#endif
 {
 	struct i40e_pf *pf = vsi->back;
 	u16 sections = 0;
@@ -1686,11 +1616,6 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 				qcount = min_t(int, pf->alloc_rss_size,
 					       num_tc_qps);
 				break;
-#ifdef I40E_FCOE
-			case I40E_VSI_FCOE:
-				qcount = num_tc_qps;
-				break;
-#endif
 			case I40E_VSI_FDIR:
 			case I40E_VSI_SRIOV:
 			case I40E_VSI_VMDQ2:
@@ -1800,11 +1725,7 @@ static int i40e_addr_unsync(struct net_device *netdev, const u8 *addr)
  * i40e_set_rx_mode - NDO callback to set the netdev filters
  * @netdev: network interface device structure
  **/
-#ifdef I40E_FCOE
-void i40e_set_rx_mode(struct net_device *netdev)
-#else
 static void i40e_set_rx_mode(struct net_device *netdev)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -1883,19 +1804,12 @@ static void i40e_undo_add_filter_entries(struct i40e_vsi *vsi,
 static
 struct i40e_new_mac_filter *i40e_next_filter(struct i40e_new_mac_filter *next)
 {
-	while (next) {
-		next = hlist_entry(next->hlist.next,
-				   typeof(struct i40e_new_mac_filter),
-				   hlist);
-
-		/* keep going if we found a broadcast filter */
-		if (next && is_broadcast_ether_addr(next->f->macaddr))
-			continue;
-
-		break;
+	hlist_for_each_entry_continue(next, hlist) {
+		if (!is_broadcast_ether_addr(next->f->macaddr))
+			return next;
 	}
 
-	return next;
+	return NULL;
 }
 
 /**
@@ -2487,13 +2401,15 @@ static int i40e_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
 
 	netdev_info(netdev, "changing MTU from %d to %d\n",
 		    netdev->mtu, new_mtu);
 	netdev->mtu = new_mtu;
 	if (netif_running(netdev))
 		i40e_vsi_reinit_locked(vsi);
-	i40e_notify_client_of_l2_param_changes(vsi);
+	pf->flags |= (I40E_FLAG_SERVICE_CLIENT_REQUESTED |
+		      I40E_FLAG_CLIENT_L2_CHANGE);
 	return 0;
 }
 
@@ -2707,13 +2623,8 @@ void i40e_vsi_kill_vlan(struct i40e_vsi *vsi, u16 vid)
  *
  * net_device_ops implementation for adding vlan ids
  **/
-#ifdef I40E_FCOE
-int i40e_vlan_rx_add_vid(struct net_device *netdev,
-			 __always_unused __be16 proto, u16 vid)
-#else
 static int i40e_vlan_rx_add_vid(struct net_device *netdev,
 				__always_unused __be16 proto, u16 vid)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -2744,13 +2655,8 @@ static int i40e_vlan_rx_add_vid(struct net_device *netdev,
  *
  * net_device_ops implementation for removing vlan ids
  **/
-#ifdef I40E_FCOE
-int i40e_vlan_rx_kill_vid(struct net_device *netdev,
-			  __always_unused __be16 proto, u16 vid)
-#else
 static int i40e_vlan_rx_kill_vid(struct net_device *netdev,
 				 __always_unused __be16 proto, u16 vid)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -2920,9 +2826,6 @@ static int i40e_vsi_setup_rx_resources(struct i40e_vsi *vsi)
 
 	for (i = 0; i < vsi->num_queue_pairs && !err; i++)
 		err = i40e_setup_rx_descriptors(vsi->rx_rings[i]);
-#ifdef I40E_FCOE
-	i40e_fcoe_setup_ddp_resources(vsi);
-#endif
 	return err;
 }
 
@@ -2942,9 +2845,6 @@ static void i40e_vsi_free_rx_resources(struct i40e_vsi *vsi)
 	for (i = 0; i < vsi->num_queue_pairs; i++)
 		if (vsi->rx_rings[i] && vsi->rx_rings[i]->desc)
 			i40e_free_rx_resources(vsi->rx_rings[i]);
-#ifdef I40E_FCOE
-	i40e_fcoe_free_ddp_resources(vsi);
-#endif
 }
 
 /**
@@ -3015,9 +2915,6 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring)
 	tx_ctx.qlen = ring->count;
 	tx_ctx.fd_ena = !!(vsi->back->flags & (I40E_FLAG_FD_SB_ENABLED |
 					       I40E_FLAG_FD_ATR_ENABLED));
-#ifdef I40E_FCOE
-	tx_ctx.fc_ena = (vsi->type == I40E_VSI_FCOE);
-#endif
 	tx_ctx.timesync_ena = !!(vsi->back->flags & I40E_FLAG_PTP);
 	/* FDIR VSI tx ring can still use RS bit and writebacks */
 	if (vsi->type != I40E_VSI_FDIR)
@@ -3098,7 +2995,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 
 	ring->rx_buf_len = vsi->rx_buf_len;
 
-	rx_ctx.dbuff = ring->rx_buf_len >> I40E_RXQ_CTX_DBUFF_SHIFT;
+	rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len,
+				    BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
 
 	rx_ctx.base = (ring->dma / 128);
 	rx_ctx.qlen = ring->count;
@@ -3120,9 +3018,6 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	rx_ctx.l2tsel = 1;
 	/* this controls whether VLAN is stripped from inner headers */
 	rx_ctx.showiv = 0;
-#ifdef I40E_FCOE
-	rx_ctx.fc_ena = (vsi->type == I40E_VSI_FCOE);
-#endif
 	/* set the prefena field to 1 because the manual says to */
 	rx_ctx.prefena = 1;
 
@@ -3181,27 +3076,19 @@ static int i40e_vsi_configure_rx(struct i40e_vsi *vsi)
 	int err = 0;
 	u16 i;
 
-	if (vsi->netdev && (vsi->netdev->mtu > ETH_DATA_LEN))
-		vsi->max_frame = vsi->netdev->mtu + ETH_HLEN
-			       + ETH_FCS_LEN + VLAN_HLEN;
-	else
-		vsi->max_frame = I40E_RXBUFFER_2048;
-
-	vsi->rx_buf_len = I40E_RXBUFFER_2048;
-
-#ifdef I40E_FCOE
-	/* setup rx buffer for FCoE */
-	if ((vsi->type == I40E_VSI_FCOE) &&
-	    (vsi->back->flags & I40E_FLAG_FCOE_ENABLED)) {
-		vsi->rx_buf_len = I40E_RXBUFFER_3072;
-		vsi->max_frame = I40E_RXBUFFER_3072;
+	if (!vsi->netdev || (vsi->back->flags & I40E_FLAG_LEGACY_RX)) {
+		vsi->max_frame = I40E_MAX_RXBUFFER;
+		vsi->rx_buf_len = I40E_RXBUFFER_2048;
+#if (PAGE_SIZE < 8192)
+	} else if (vsi->netdev->mtu <= ETH_DATA_LEN) {
+		vsi->max_frame = I40E_RXBUFFER_1536 - NET_IP_ALIGN;
+		vsi->rx_buf_len = I40E_RXBUFFER_1536 - NET_IP_ALIGN;
+#endif
+	} else {
+		vsi->max_frame = I40E_MAX_RXBUFFER;
+		vsi->rx_buf_len = I40E_RXBUFFER_2048;
 	}
 
-#endif /* I40E_FCOE */
-	/* round up for the chip's needs */
-	vsi->rx_buf_len = ALIGN(vsi->rx_buf_len,
-				BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
-
 	/* set up individual rings */
 	for (i = 0; i < vsi->num_queue_pairs && !err; i++)
 		err = i40e_configure_rx_ring(vsi->rx_rings[i]);
@@ -3281,6 +3168,12 @@ static void i40e_fdir_filter_restore(struct i40e_vsi *vsi)
 	if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
 		return;
 
+	/* Reset FDir counters as we're replaying all existing filters */
+	pf->fd_tcp4_filter_cnt = 0;
+	pf->fd_udp4_filter_cnt = 0;
+	pf->fd_sctp4_filter_cnt = 0;
+	pf->fd_ip4_filter_cnt = 0;
+
 	hlist_for_each_entry_safe(filter, node,
 				  &pf->fdir_filter_list, fdir_node) {
 		i40e_add_del_fdir(vsi, filter, true);
@@ -3993,11 +3886,7 @@ static int i40e_vsi_request_irq(struct i40e_vsi *vsi, char *basename)
  * This is used by netconsole to send skbs without having to re-enable
  * interrupts.  It's not called while the normal interrupt routine is executing.
  **/
-#ifdef I40E_FCOE
-void i40e_netpoll(struct net_device *netdev)
-#else
 static void i40e_netpoll(struct net_device *netdev)
-#endif
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -4100,8 +3989,6 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable)
 		}
 	}
 
-	if (hw->revision_id == 0)
-		mdelay(50);
 	return ret;
 }
 
@@ -4180,6 +4067,12 @@ static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable)
 		}
 	}
 
+	/* Due to HW errata, on Rx disable only, the register can indicate done
+	 * before it really is. Needs 50ms to be sure
+	 */
+	if (!enable)
+		mdelay(50);
+
 	return ret;
 }
 
@@ -4471,17 +4364,16 @@ static void i40e_napi_disable_all(struct i40e_vsi *vsi)
  **/
 static void i40e_vsi_close(struct i40e_vsi *vsi)
 {
-	bool reset = false;
-
+	struct i40e_pf *pf = vsi->back;
 	if (!test_and_set_bit(__I40E_DOWN, &vsi->state))
 		i40e_down(vsi);
 	i40e_vsi_free_irq(vsi);
 	i40e_vsi_free_tx_resources(vsi);
 	i40e_vsi_free_rx_resources(vsi);
 	vsi->current_netdev_flags = 0;
-	if (test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
-		reset = true;
-	i40e_notify_client_of_netdev_close(vsi, reset);
+	pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED;
+	if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state))
+		pf->flags |=  I40E_FLAG_CLIENT_RESET;
 }
 
 /**
@@ -4493,14 +4385,6 @@ static void i40e_quiesce_vsi(struct i40e_vsi *vsi)
 	if (test_bit(__I40E_DOWN, &vsi->state))
 		return;
 
-	/* No need to disable FCoE VSI when Tx suspended */
-	if ((test_bit(__I40E_PORT_TX_SUSPENDED, &vsi->back->state)) &&
-	    vsi->type == I40E_VSI_FCOE) {
-		dev_dbg(&vsi->back->pdev->dev,
-			 "VSI seid %d skipping FCoE VSI disable\n", vsi->seid);
-		return;
-	}
-
 	set_bit(__I40E_NEEDS_RESTART, &vsi->state);
 	if (vsi->netdev && netif_running(vsi->netdev))
 		vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
@@ -4603,8 +4487,7 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf)
 	int v, ret = 0;
 
 	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
-		/* No need to wait for FCoE VSI queues */
-		if (pf->vsi[v] && pf->vsi[v]->type != I40E_VSI_FCOE) {
+		if (pf->vsi[v]) {
 			ret = i40e_vsi_wait_queues_disabled(pf->vsi[v]);
 			if (ret)
 				break;
@@ -5228,20 +5111,12 @@ static void i40e_dcb_reconfigure(struct i40e_pf *pf)
 			continue;
 
 		/* - Enable all TCs for the LAN VSI
-#ifdef I40E_FCOE
-		 * - For FCoE VSI only enable the TC configured
-		 *   as per the APP TLV
-#endif
 		 * - For all others keep them at TC0 for now
 		 */
 		if (v == pf->lan_vsi)
 			tc_map = i40e_pf_get_tc_map(pf);
 		else
 			tc_map = I40E_DEFAULT_TRAFFIC_CLASS;
-#ifdef I40E_FCOE
-		if (pf->vsi[v]->type == I40E_VSI_FCOE)
-			tc_map = i40e_get_fcoe_tc_map(pf);
-#endif /* #ifdef I40E_FCOE */
 
 		ret = i40e_vsi_config_tc(pf->vsi[v], tc_map);
 		if (ret) {
@@ -5308,10 +5183,6 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 		    (hw->dcbx_status == I40E_DCBX_STATUS_DISABLED)) {
 			dev_info(&pf->pdev->dev,
 				 "DCBX offload is not supported or is disabled for this PF.\n");
-
-			if (pf->flags & I40E_FLAG_MFP_ENABLED)
-				goto out;
-
 		} else {
 			/* When status is not DISABLED then DCBX in FW */
 			pf->dcbx_cap = DCB_CAP_DCBX_LLD_MANAGED |
@@ -5472,13 +5343,8 @@ static int i40e_up_complete(struct i40e_vsi *vsi)
 	/* replay FDIR SB filters */
 	if (vsi->type == I40E_VSI_FDIR) {
 		/* reset fd counters */
-		pf->fd_add_err = pf->fd_atr_cnt = 0;
-		if (pf->fd_tcp_rule > 0) {
-			pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
-			if (I40E_DEBUG_FD & pf->hw.debug_mask)
-				dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 exist\n");
-			pf->fd_tcp_rule = 0;
-		}
+		pf->fd_add_err = 0;
+		pf->fd_atr_cnt = 0;
 		i40e_fdir_filter_restore(vsi);
 	}
 
@@ -5550,8 +5416,6 @@ void i40e_down(struct i40e_vsi *vsi)
 		i40e_clean_rx_ring(vsi->rx_rings[i]);
 	}
 
-	i40e_notify_client_of_netdev_close(vsi, false);
-
 }
 
 /**
@@ -5612,17 +5476,15 @@ exit:
 	return ret;
 }
 
-#ifdef I40E_FCOE
-int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
-		    struct tc_to_netdev *tc)
-#else
 static int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
 			   struct tc_to_netdev *tc)
-#endif
 {
-	if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO)
+	if (tc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
-	return i40e_setup_tc(netdev, tc->tc);
+
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+	return i40e_setup_tc(netdev, tc->mqprio->num_tc);
 }
 
 /**
@@ -5753,6 +5615,7 @@ err_setup_tx:
 static void i40e_fdir_filter_exit(struct i40e_pf *pf)
 {
 	struct i40e_fdir_filter *filter;
+	struct i40e_flex_pit *pit_entry, *tmp;
 	struct hlist_node *node2;
 
 	hlist_for_each_entry_safe(filter, node2,
@@ -5760,7 +5623,43 @@ static void i40e_fdir_filter_exit(struct i40e_pf *pf)
 		hlist_del(&filter->fdir_node);
 		kfree(filter);
 	}
+
+	list_for_each_entry_safe(pit_entry, tmp, &pf->l3_flex_pit_list, list) {
+		list_del(&pit_entry->list);
+		kfree(pit_entry);
+	}
+	INIT_LIST_HEAD(&pf->l3_flex_pit_list);
+
+	list_for_each_entry_safe(pit_entry, tmp, &pf->l4_flex_pit_list, list) {
+		list_del(&pit_entry->list);
+		kfree(pit_entry);
+	}
+	INIT_LIST_HEAD(&pf->l4_flex_pit_list);
+
 	pf->fdir_pf_active_filters = 0;
+	pf->fd_tcp4_filter_cnt = 0;
+	pf->fd_udp4_filter_cnt = 0;
+	pf->fd_sctp4_filter_cnt = 0;
+	pf->fd_ip4_filter_cnt = 0;
+
+	/* Reprogram the default input set for TCP/IPv4 */
+	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_TCP,
+				I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
+				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
+
+	/* Reprogram the default input set for UDP/IPv4 */
+	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_UDP,
+				I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
+				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
+
+	/* Reprogram the default input set for SCTP/IPv4 */
+	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_SCTP,
+				I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
+				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
+
+	/* Reprogram the default input set for Other/IPv4 */
+	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_OTHER,
+				I40E_L3_SRC_MASK | I40E_L3_DST_MASK);
 }
 
 /**
@@ -6029,8 +5928,8 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 		i40e_service_event_schedule(pf);
 	} else {
 		i40e_pf_unquiesce_all_vsi(pf);
-		/* Notify the client for the DCB changes */
-		i40e_notify_client_of_l2_param_changes(pf->vsi[pf->lan_vsi]);
+	pf->flags |= (I40E_FLAG_SERVICE_CLIENT_REQUESTED |
+		      I40E_FLAG_CLIENT_L2_CHANGE);
 	}
 
 exit:
@@ -6152,8 +6051,8 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
 	    (pf->fd_add_err == 0) ||
 	    (i40e_get_current_atr_cnt(pf) < pf->fd_atr_cnt)) {
 		if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
-		    (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) {
-			pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED;
+		    (pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED)) {
+			pf->hw_disabled_flags &= ~I40E_FLAG_FD_SB_ENABLED;
 			if (I40E_DEBUG_FD & pf->hw.debug_mask)
 				dev_info(&pf->pdev->dev, "FD Sideband/ntuple is being enabled since we have space in the table now\n");
 		}
@@ -6164,9 +6063,9 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
 	 */
 	if (fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM * 2)) {
 		if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
-		    (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED) &&
-		    (pf->fd_tcp_rule == 0)) {
-			pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
+		    (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED) &&
+		    (pf->fd_tcp4_filter_cnt == 0)) {
+			pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
 			if (I40E_DEBUG_FD & pf->hw.debug_mask)
 				dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table and there are no conflicting ntuple rules\n");
 		}
@@ -6218,7 +6117,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf)
 	}
 
 	pf->fd_flush_timestamp = jiffies;
-	pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
+	pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED;
 	/* flush all filters */
 	wr32(&pf->hw, I40E_PFQF_CTL_1,
 	     I40E_PFQF_CTL_1_CLEARFDTABLE_MASK);
@@ -6237,8 +6136,8 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf)
 	} else {
 		/* replay sideband filters */
 		i40e_fdir_filter_restore(pf->vsi[pf->lan_vsi]);
-		if (!disable_atr)
-			pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
+		if (!disable_atr && !pf->fd_tcp4_filter_cnt)
+			pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
 		clear_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
 		if (I40E_DEBUG_FD & pf->hw.debug_mask)
 			dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n");
@@ -6291,9 +6190,6 @@ static void i40e_vsi_link_event(struct i40e_vsi *vsi, bool link_up)
 
 	switch (vsi->type) {
 	case I40E_VSI_MAIN:
-#ifdef I40E_FCOE
-	case I40E_VSI_FCOE:
-#endif
 		if (!vsi->netdev || !vsi->netdev_registered)
 			break;
 
@@ -6635,9 +6531,11 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
 				 opcode);
 			break;
 		}
-	} while (pending && (i++ < pf->adminq_work_limit));
+	} while (i++ < pf->adminq_work_limit);
+
+	if (i < pf->adminq_work_limit)
+		clear_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state);
 
-	clear_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state);
 	/* re-enable Admin queue interrupt cause */
 	val = rd32(hw, I40E_PFINT_ICR0_ENA);
 	val |=  I40E_PFINT_ICR0_ENA_ADMINQ_MASK;
@@ -7075,8 +6973,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 		goto end_core_reset;
 
 	ret = i40e_init_lan_hmc(hw, hw->func_caps.num_tx_qp,
-				hw->func_caps.num_rx_qp,
-				pf->fcoe_hmc_cntx_num, pf->fcoe_hmc_filt_num);
+				hw->func_caps.num_rx_qp, 0, 0);
 	if (ret) {
 		dev_info(&pf->pdev->dev, "init_lan_hmc failed: %d\n", ret);
 		goto end_core_reset;
@@ -7095,10 +6992,6 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 		/* Continue without DCB enabled */
 	}
 #endif /* CONFIG_I40E_DCB */
-#ifdef I40E_FCOE
-	i40e_init_pf_fcoe(pf);
-
-#endif
 	/* do basic switch setup */
 	ret = i40e_setup_pf_switch(pf, reinit);
 	if (ret)
@@ -7359,7 +7252,7 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
 {
 	struct i40e_hw *hw = &pf->hw;
 	i40e_status ret;
-	__be16 port;
+	u16 port;
 	int i;
 
 	if (!(pf->flags & I40E_FLAG_UDP_FILTER_SYNC))
@@ -7383,7 +7276,7 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
 					"%s %s port %d, index %d failed, err %s aq_err %s\n",
 					pf->udp_ports[i].type ? "vxlan" : "geneve",
 					port ? "add" : "delete",
-					ntohs(port), i,
+					port, i,
 					i40e_stat_str(&pf->hw, ret),
 					i40e_aq_str(&pf->hw,
 						    pf->hw.aq.asq_last_status));
@@ -7419,7 +7312,18 @@ static void i40e_service_task(struct work_struct *work)
 	i40e_vc_process_vflr_event(pf);
 	i40e_watchdog_subtask(pf);
 	i40e_fdir_reinit_subtask(pf);
-	i40e_client_subtask(pf);
+	if (pf->flags & I40E_FLAG_CLIENT_RESET) {
+		/* Client subtask will reopen next time through. */
+		i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], true);
+		pf->flags &= ~I40E_FLAG_CLIENT_RESET;
+	} else {
+		i40e_client_subtask(pf);
+		if (pf->flags & I40E_FLAG_CLIENT_L2_CHANGE) {
+			i40e_notify_client_of_l2_param_changes(
+							pf->vsi[pf->lan_vsi]);
+			pf->flags &= ~I40E_FLAG_CLIENT_L2_CHANGE;
+		}
+	}
 	i40e_sync_filters_subtask(pf);
 	i40e_sync_udp_filters_subtask(pf);
 	i40e_clean_adminq_subtask(pf);
@@ -7492,15 +7396,6 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi)
 				      I40E_REQ_DESCRIPTOR_MULTIPLE);
 		break;
 
-#ifdef I40E_FCOE
-	case I40E_VSI_FCOE:
-		vsi->alloc_queue_pairs = pf->num_fcoe_qps;
-		vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
-				      I40E_REQ_DESCRIPTOR_MULTIPLE);
-		vsi->num_q_vectors = pf->num_fcoe_msix;
-		break;
-
-#endif /* I40E_FCOE */
 	default:
 		WARN_ON(1);
 		return -ENODATA;
@@ -7817,6 +7712,7 @@ static int i40e_reserve_msix_vectors(struct i40e_pf *pf, int vectors)
 static int i40e_init_msix(struct i40e_pf *pf)
 {
 	struct i40e_hw *hw = &pf->hw;
+	int cpus, extra_vectors;
 	int vectors_left;
 	int v_budget, i;
 	int v_actual;
@@ -7835,9 +7731,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 	 *	- assumes symmetric Tx/Rx pairing
 	 *   - The number of VMDq pairs
 	 *   - The CPU count within the NUMA node if iWARP is enabled
-#ifdef I40E_FCOE
-	 *   - The number of FCOE qps.
-#endif
 	 * Once we count this up, try the request.
 	 *
 	 * If we can't get what we want, we'll simplify to nearly nothing
@@ -7852,10 +7745,16 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		vectors_left--;
 	}
 
-	/* reserve vectors for the main PF traffic queues */
-	pf->num_lan_msix = min_t(int, num_online_cpus(), vectors_left);
+	/* reserve some vectors for the main PF traffic queues. Initially we
+	 * only reserve at most 50% of the available vectors, in the case that
+	 * the number of online CPUs is large. This ensures that we can enable
+	 * extra features as well. Once we've enabled the other features, we
+	 * will use any remaining vectors to reach as close as we can to the
+	 * number of online CPUs.
+	 */
+	cpus = num_online_cpus();
+	pf->num_lan_msix = min_t(int, cpus, vectors_left / 2);
 	vectors_left -= pf->num_lan_msix;
-	v_budget += pf->num_lan_msix;
 
 	/* reserve one vector for sideband flow director */
 	if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
@@ -7868,20 +7767,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		}
 	}
 
-#ifdef I40E_FCOE
-	/* can we reserve enough for FCoE? */
-	if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
-		if (!vectors_left)
-			pf->num_fcoe_msix = 0;
-		else if (vectors_left >= pf->num_fcoe_qps)
-			pf->num_fcoe_msix = pf->num_fcoe_qps;
-		else
-			pf->num_fcoe_msix = 1;
-		v_budget += pf->num_fcoe_msix;
-		vectors_left -= pf->num_fcoe_msix;
-	}
-
-#endif
 	/* can we reserve enough for iWARP? */
 	if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
 		iwarp_requested = pf->num_iwarp_msix;
@@ -7918,6 +7803,23 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		}
 	}
 
+	/* On systems with a large number of SMP cores, we previously limited
+	 * the number of vectors for num_lan_msix to be at most 50% of the
+	 * available vectors, to allow for other features. Now, we add back
+	 * the remaining vectors. However, we ensure that the total
+	 * num_lan_msix will not exceed num_online_cpus(). To do this, we
+	 * calculate the number of vectors we can add without going over the
+	 * cap of CPUs. For systems with a small number of CPUs this will be
+	 * zero.
+	 */
+	extra_vectors = min_t(int, cpus - pf->num_lan_msix, vectors_left);
+	pf->num_lan_msix += extra_vectors;
+	vectors_left -= extra_vectors;
+
+	WARN(vectors_left < 0,
+	     "Calculation of remaining vectors underflowed. This is an accounting bug when determining total MSI-X vectors.\n");
+
+	v_budget += pf->num_lan_msix;
 	pf->msix_entries = kcalloc(v_budget, sizeof(struct msix_entry),
 				   GFP_KERNEL);
 	if (!pf->msix_entries)
@@ -7958,10 +7860,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		pf->num_vmdq_msix = 1;    /* force VMDqs to only one vector */
 		pf->num_vmdq_vsis = 1;
 		pf->num_vmdq_qps = 1;
-#ifdef I40E_FCOE
-		pf->num_fcoe_qps = 0;
-		pf->num_fcoe_msix = 0;
-#endif
 
 		/* partition out the remaining vectors */
 		switch (vec) {
@@ -7975,13 +7873,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 			} else {
 				pf->num_lan_msix = 2;
 			}
-#ifdef I40E_FCOE
-			/* give one vector to FCoE */
-			if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
-				pf->num_lan_msix = 1;
-				pf->num_fcoe_msix = 1;
-			}
-#endif
 			break;
 		default:
 			if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
@@ -8001,13 +7892,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 			       (vec - (pf->num_iwarp_msix + pf->num_vmdq_vsis)),
 							      pf->num_lan_msix);
 			pf->num_lan_qps = pf->num_lan_msix;
-#ifdef I40E_FCOE
-			/* give one vector to FCoE */
-			if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
-				pf->num_fcoe_msix = 1;
-				vec--;
-			}
-#endif
 			break;
 		}
 	}
@@ -8028,13 +7912,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		dev_info(&pf->pdev->dev, "IWARP disabled, not enough MSI-X vectors\n");
 		pf->flags &= ~I40E_FLAG_IWARP_ENABLED;
 	}
-#ifdef I40E_FCOE
-
-	if ((pf->flags & I40E_FLAG_FCOE_ENABLED) && (pf->num_fcoe_msix == 0)) {
-		dev_info(&pf->pdev->dev, "FCOE disabled, not enough MSI-X vectors\n");
-		pf->flags &= ~I40E_FLAG_FCOE_ENABLED;
-	}
-#endif
 	i40e_debug(&pf->hw, I40E_DEBUG_INIT,
 		   "MSI-X vector distribution: PF %d, VMDq %d, FDSB %d, iWARP %d\n",
 		   pf->num_lan_msix,
@@ -8133,9 +8010,6 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf)
 		if (vectors < 0) {
 			pf->flags &= ~(I40E_FLAG_MSIX_ENABLED	|
 				       I40E_FLAG_IWARP_ENABLED	|
-#ifdef I40E_FCOE
-				       I40E_FLAG_FCOE_ENABLED	|
-#endif
 				       I40E_FLAG_RSS_ENABLED	|
 				       I40E_FLAG_DCB_CAPABLE	|
 				       I40E_FLAG_DCB_ENABLED	|
@@ -8368,13 +8242,10 @@ static int i40e_config_rss_reg(struct i40e_vsi *vsi, const u8 *seed,
 
 		if (vsi->type == I40E_VSI_MAIN) {
 			for (i = 0; i <= I40E_PFQF_HKEY_MAX_INDEX; i++)
-				i40e_write_rx_ctl(hw, I40E_PFQF_HKEY(i),
-						  seed_dw[i]);
+				wr32(hw, I40E_PFQF_HKEY(i), seed_dw[i]);
 		} else if (vsi->type == I40E_VSI_SRIOV) {
 			for (i = 0; i <= I40E_VFQF_HKEY1_MAX_INDEX; i++)
-				i40e_write_rx_ctl(hw,
-						  I40E_VFQF_HKEY1(i, vf_id),
-						  seed_dw[i]);
+				wr32(hw, I40E_VFQF_HKEY1(i, vf_id), seed_dw[i]);
 		} else {
 			dev_err(&pf->pdev->dev, "Cannot set RSS seed - invalid VSI type\n");
 		}
@@ -8392,9 +8263,7 @@ static int i40e_config_rss_reg(struct i40e_vsi *vsi, const u8 *seed,
 			if (lut_size != I40E_VF_HLUT_ARRAY_SIZE)
 				return -EINVAL;
 			for (i = 0; i <= I40E_VFQF_HLUT_MAX_INDEX; i++)
-				i40e_write_rx_ctl(hw,
-						  I40E_VFQF_HLUT1(i, vf_id),
-						  lut_dw[i]);
+				wr32(hw, I40E_VFQF_HLUT1(i, vf_id), lut_dw[i]);
 		} else {
 			dev_err(&pf->pdev->dev, "Cannot set RSS LUT - invalid VSI type\n");
 		}
@@ -8522,9 +8391,12 @@ static int i40e_pf_config_rss(struct i40e_pf *pf)
 	i40e_write_rx_ctl(hw, I40E_PFQF_CTL_0, reg_val);
 
 	/* Determine the RSS size of the VSI */
-	if (!vsi->rss_size)
-		vsi->rss_size = min_t(int, pf->alloc_rss_size,
-				      vsi->num_queue_pairs);
+	if (!vsi->rss_size) {
+		u16 qcount;
+
+		qcount = vsi->num_queue_pairs / vsi->tc_config.numtc;
+		vsi->rss_size = min_t(int, pf->alloc_rss_size, qcount);
+	}
 	if (!vsi->rss_size)
 		return -EINVAL;
 
@@ -8570,6 +8442,8 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
 	new_rss_size = min_t(int, queue_count, pf->rss_size_max);
 
 	if (queue_count != vsi->num_queue_pairs) {
+		u16 qcount;
+
 		vsi->req_queue_pairs = queue_count;
 		i40e_prep_for_reset(pf);
 
@@ -8587,8 +8461,8 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
 		}
 
 		/* Reset vsi->rss_size, as number of enabled queues changed */
-		vsi->rss_size = min_t(int, pf->alloc_rss_size,
-				      vsi->num_queue_pairs);
+		qcount = vsi->num_queue_pairs / vsi->tc_config.numtc;
+		vsi->rss_size = min_t(int, pf->alloc_rss_size, qcount);
 
 		i40e_pf_config_rss(pf);
 	}
@@ -8821,10 +8695,6 @@ static int i40e_sw_init(struct i40e_pf *pf)
 		pf->num_iwarp_msix = (int)num_online_cpus() + 1;
 	}
 
-#ifdef I40E_FCOE
-	i40e_init_pf_fcoe(pf);
-
-#endif /* I40E_FCOE */
 #ifdef CONFIG_PCI_IOV
 	if (pf->hw.func_caps.num_vfs && pf->hw.partition_id == 1) {
 		pf->num_vf_qps = I40E_DEFAULT_QUEUES_PER_VF;
@@ -8851,9 +8721,9 @@ static int i40e_sw_init(struct i40e_pf *pf)
 		    (pf->hw.aq.api_min_ver > 4))) {
 		/* Supported in FW API version higher than 1.4 */
 		pf->flags |= I40E_FLAG_GENEVE_OFFLOAD_CAPABLE;
-		pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
+		pf->hw_disabled_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
 	} else {
-		pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
+		pf->hw_disabled_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
 	}
 
 	pf->eeprom_version = 0xDEAD;
@@ -8914,14 +8784,14 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features)
 			i40e_fdir_filter_exit(pf);
 		}
 		pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
-		pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED;
+		pf->hw_disabled_flags &= ~I40E_FLAG_FD_SB_ENABLED;
 		/* reset fd counters */
-		pf->fd_add_err = pf->fd_atr_cnt = pf->fd_tcp_rule = 0;
-		pf->fdir_pf_active_filters = 0;
+		pf->fd_add_err = 0;
+		pf->fd_atr_cnt = 0;
 		/* if ATR was auto disabled it can be re-enabled. */
 		if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
-		    (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) {
-			pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
+		    (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED)) {
+			pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
 			if (I40E_DEBUG_FD & pf->hw.debug_mask)
 				dev_info(&pf->pdev->dev, "ATR re-enabled.\n");
 		}
@@ -8990,7 +8860,7 @@ static int i40e_set_features(struct net_device *netdev,
  *
  * Returns the index number or I40E_MAX_PF_UDP_OFFLOAD_PORTS if port not found
  **/
-static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, __be16 port)
+static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, u16 port)
 {
 	u8 i;
 
@@ -9013,7 +8883,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev,
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
-	__be16 port = ti->port;
+	u16 port = ntohs(ti->port);
 	u8 next_idx;
 	u8 idx;
 
@@ -9021,8 +8891,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev,
 
 	/* Check if port already exists */
 	if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		netdev_info(netdev, "port %d already offloaded\n",
-			    ntohs(port));
+		netdev_info(netdev, "port %d already offloaded\n", port);
 		return;
 	}
 
@@ -9031,7 +8900,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev,
 
 	if (next_idx == I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
 		netdev_info(netdev, "maximum number of offloaded UDP ports reached, not adding port %d\n",
-			    ntohs(port));
+			    port);
 		return;
 	}
 
@@ -9065,7 +8934,7 @@ static void i40e_udp_tunnel_del(struct net_device *netdev,
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
-	__be16 port = ti->port;
+	u16 port = ntohs(ti->port);
 	u8 idx;
 
 	idx = i40e_get_udp_port_idx(pf, port);
@@ -9097,7 +8966,7 @@ static void i40e_udp_tunnel_del(struct net_device *netdev,
 	return;
 not_found:
 	netdev_warn(netdev, "UDP port %d was not found, not deleting\n",
-		    ntohs(port));
+		    port);
 }
 
 static int i40e_get_phys_port_id(struct net_device *netdev,
@@ -9352,10 +9221,6 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_poll_controller	= i40e_netpoll,
 #endif
 	.ndo_setup_tc		= __i40e_setup_tc,
-#ifdef I40E_FCOE
-	.ndo_fcoe_enable	= i40e_fcoe_enable,
-	.ndo_fcoe_disable	= i40e_fcoe_disable,
-#endif
 	.ndo_set_features	= i40e_set_features,
 	.ndo_set_vf_mac		= i40e_ndo_set_vf_mac,
 	.ndo_set_vf_vlan	= i40e_ndo_set_vf_port_vlan,
@@ -9440,10 +9305,10 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	if (vsi->type == I40E_VSI_MAIN) {
 		SET_NETDEV_DEV(netdev, &pf->pdev->dev);
 		ether_addr_copy(mac_addr, hw->mac.perm_addr);
-		/* The following steps are necessary to prevent reception
-		 * of tagged packets - some older NVM configurations load a
-		 * default a MAC-VLAN filter that accepts any tagged packet
-		 * which must be replaced by a normal filter.
+		/* The following steps are necessary to properly keep track of
+		 * MAC-VLAN filters loaded into firmware - first we remove
+		 * filter that is automatically generated by firmware and then
+		 * add new filter both to the driver hash table and firmware.
 		 */
 		i40e_rm_default_mac_filter(vsi, mac_addr);
 		spin_lock_bh(&vsi->mac_filter_hash_lock);
@@ -9489,9 +9354,6 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	netdev->netdev_ops = &i40e_netdev_ops;
 	netdev->watchdog_timeo = 5 * HZ;
 	i40e_set_ethtool_ops(netdev);
-#ifdef I40E_FCOE
-	i40e_fcoe_config_netdev(netdev, vsi);
-#endif
 
 	/* MTU range: 68 - 9706 */
 	netdev->min_mtu = ETH_MIN_MTU;
@@ -9715,16 +9577,6 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 		i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, true);
 		break;
 
-#ifdef I40E_FCOE
-	case I40E_VSI_FCOE:
-		ret = i40e_fcoe_vsi_init(vsi, &ctxt);
-		if (ret) {
-			dev_info(&pf->pdev->dev, "failed to initialize FCoE VSI\n");
-			return ret;
-		}
-		break;
-
-#endif /* I40E_FCOE */
 	case I40E_VSI_IWARP:
 		/* send down message to iWARP */
 		break;
@@ -10141,7 +9993,6 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 			}
 		}
 	case I40E_VSI_VMDQ2:
-	case I40E_VSI_FCOE:
 		ret = i40e_config_netdev(vsi);
 		if (ret)
 			goto err_netdev;
@@ -10801,9 +10652,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 	int queues_left;
 
 	pf->num_lan_qps = 0;
-#ifdef I40E_FCOE
-	pf->num_fcoe_qps = 0;
-#endif
 
 	/* Find the max queues to be put into basic use.  We'll always be
 	 * using TC0, whether or not DCB is running, and TC0 will get the
@@ -10820,9 +10668,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 		/* make sure all the fancies are disabled */
 		pf->flags &= ~(I40E_FLAG_RSS_ENABLED	|
 			       I40E_FLAG_IWARP_ENABLED	|
-#ifdef I40E_FCOE
-			       I40E_FLAG_FCOE_ENABLED	|
-#endif
 			       I40E_FLAG_FD_SB_ENABLED	|
 			       I40E_FLAG_FD_ATR_ENABLED	|
 			       I40E_FLAG_DCB_CAPABLE	|
@@ -10839,9 +10684,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 
 		pf->flags &= ~(I40E_FLAG_RSS_ENABLED	|
 			       I40E_FLAG_IWARP_ENABLED	|
-#ifdef I40E_FCOE
-			       I40E_FLAG_FCOE_ENABLED	|
-#endif
 			       I40E_FLAG_FD_SB_ENABLED	|
 			       I40E_FLAG_FD_ATR_ENABLED	|
 			       I40E_FLAG_DCB_ENABLED	|
@@ -10862,22 +10704,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 		queues_left -= pf->num_lan_qps;
 	}
 
-#ifdef I40E_FCOE
-	if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
-		if (I40E_DEFAULT_FCOE <= queues_left) {
-			pf->num_fcoe_qps = I40E_DEFAULT_FCOE;
-		} else if (I40E_MINIMUM_FCOE <= queues_left) {
-			pf->num_fcoe_qps = I40E_MINIMUM_FCOE;
-		} else {
-			pf->num_fcoe_qps = 0;
-			pf->flags &= ~I40E_FLAG_FCOE_ENABLED;
-			dev_info(&pf->pdev->dev, "not enough queues for FCoE. FCoE feature will be disabled\n");
-		}
-
-		queues_left -= pf->num_fcoe_qps;
-	}
-
-#endif
 	if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
 		if (queues_left > 1) {
 			queues_left -= 1; /* save 1 queue for FD */
@@ -10909,9 +10735,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 		pf->num_lan_qps, pf->alloc_rss_size, pf->num_req_vfs,
 		pf->num_vf_qps, pf->num_vmdq_vsis, pf->num_vmdq_qps,
 		queues_left);
-#ifdef I40E_FCOE
-	dev_dbg(&pf->pdev->dev, "fcoe queues = %d\n", pf->num_fcoe_qps);
-#endif
 }
 
 /**
@@ -10978,10 +10801,6 @@ static void i40e_print_features(struct i40e_pf *pf)
 	i += snprintf(&buf[i], REMAIN(i), " Geneve");
 	if (pf->flags & I40E_FLAG_PTP)
 		i += snprintf(&buf[i], REMAIN(i), " PTP");
-#ifdef I40E_FCOE
-	if (pf->flags & I40E_FLAG_FCOE_ENABLED)
-		i += snprintf(&buf[i], REMAIN(i), " FCOE");
-#endif
 	if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED)
 		i += snprintf(&buf[i], REMAIN(i), " VEB");
 	else
@@ -11098,6 +10917,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	hw->bus.bus_id = pdev->bus->number;
 	pf->instance = pfs_found;
 
+	INIT_LIST_HEAD(&pf->l3_flex_pit_list);
+	INIT_LIST_HEAD(&pf->l4_flex_pit_list);
+
 	/* set up the locks for the AQ, do this only once in probe
 	 * and destroy them only once in remove
 	 */
@@ -11196,8 +11018,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	err = i40e_init_lan_hmc(hw, hw->func_caps.num_tx_qp,
-				hw->func_caps.num_rx_qp,
-				pf->fcoe_hmc_cntx_num, pf->fcoe_hmc_filt_num);
+				hw->func_caps.num_rx_qp, 0, 0);
 	if (err) {
 		dev_info(&pdev->dev, "init_lan_hmc failed: %d\n", err);
 		goto err_init_lan_hmc;
@@ -11232,18 +11053,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	i40e_get_port_mac_addr(hw, hw->mac.port_addr);
 	if (is_valid_ether_addr(hw->mac.port_addr))
 		pf->flags |= I40E_FLAG_PORT_ID_VALID;
-#ifdef I40E_FCOE
-	err = i40e_get_san_mac_addr(hw, hw->mac.san_addr);
-	if (err)
-		dev_info(&pdev->dev,
-			 "(non-fatal) SAN MAC retrieval failed: %d\n", err);
-	if (!is_valid_ether_addr(hw->mac.san_addr)) {
-		dev_warn(&pdev->dev, "invalid SAN MAC address %pM, falling back to LAN MAC\n",
-			 hw->mac.san_addr);
-		ether_addr_copy(hw->mac.san_addr, hw->mac.addr);
-	}
-	dev_info(&pf->pdev->dev, "SAN MAC: %pM\n", hw->mac.san_addr);
-#endif /* I40E_FCOE */
 
 	pci_set_drvdata(pdev, pf);
 	pci_save_state(pdev);
@@ -11439,11 +11248,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_info(&pdev->dev, "Failed to add PF to client API service list: %d\n",
 			 err);
 
-#ifdef I40E_FCOE
-	/* create FCoE interface */
-	i40e_fcoe_vsi_setup(pf);
-
-#endif
 #define PCI_SPEED_SIZE 8
 #define PCI_WIDTH_SIZE 8
 	/* Devices on the IOSF bus do not have this information
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 38ee18f11124..800bd55d0159 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -292,14 +292,14 @@ i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset,
 {
 	enum i40e_status_code ret_code = 0;
 
-	if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) {
-		ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
-		if (!ret_code) {
+	ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
+	if (!ret_code) {
+		if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) {
 			ret_code = i40e_read_nvm_word_aq(hw, offset, data);
-			i40e_release_nvm(hw);
+		} else {
+			ret_code = i40e_read_nvm_word_srctl(hw, offset, data);
 		}
-	} else {
-		ret_code = i40e_read_nvm_word_srctl(hw, offset, data);
+		i40e_release_nvm(hw);
 	}
 	return ret_code;
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
index fea81ed065db..80e66da6b145 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_osdep.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
@@ -78,7 +78,4 @@ do {								\
 } while (0)
 
 typedef enum i40e_status_code i40e_status;
-#ifdef CONFIG_I40E_FCOE
-#define I40E_FCOE
-#endif
 #endif /* _I40E_OSDEP_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index 2551fc827444..dfc5e5901be5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -304,9 +304,6 @@ i40e_status i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num,
 				 u32 pba_num_size);
 i40e_status i40e_validate_mac_addr(u8 *mac_addr);
 void i40e_pre_tx_queue_cfg(struct i40e_hw *hw, u32 queue, bool enable);
-#ifdef I40E_FCOE
-i40e_status i40e_get_san_mac_addr(struct i40e_hw *hw, u8 *mac_addr);
-#endif
 /* prototype for functions used for NVM access */
 i40e_status i40e_init_nvm(struct i40e_hw *hw);
 i40e_status i40e_acquire_nvm(struct i40e_hw *hw,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 97d46058d71d..ebffca0cefac 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -71,6 +71,9 @@ static void i40e_fdir(struct i40e_ring *tx_ring,
 	flex_ptype |= I40E_TXD_FLTR_QW0_PCTYPE_MASK &
 		      (fdata->pctype << I40E_TXD_FLTR_QW0_PCTYPE_SHIFT);
 
+	flex_ptype |= I40E_TXD_FLTR_QW0_PCTYPE_MASK &
+		      (fdata->flex_offset << I40E_TXD_FLTR_QW0_FLEXOFF_SHIFT);
+
 	/* Use LAN VSI Id if not programmed by user */
 	flex_ptype |= I40E_TXD_FLTR_QW0_DEST_VSI_MASK &
 		      ((u32)(fdata->dest_vsi ? : pf->vsi[pf->lan_vsi]->id) <<
@@ -203,7 +206,6 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi,
 	struct i40e_pf *pf = vsi->back;
 	struct udphdr *udp;
 	struct iphdr *ip;
-	bool err = false;
 	u8 *raw_packet;
 	int ret;
 	static char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0,
@@ -219,18 +221,28 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi,
 	udp = (struct udphdr *)(raw_packet + IP_HEADER_OFFSET
 	      + sizeof(struct iphdr));
 
-	ip->daddr = fd_data->dst_ip[0];
+	ip->daddr = fd_data->dst_ip;
 	udp->dest = fd_data->dst_port;
-	ip->saddr = fd_data->src_ip[0];
+	ip->saddr = fd_data->src_ip;
 	udp->source = fd_data->src_port;
 
+	if (fd_data->flex_filter) {
+		u8 *payload = raw_packet + I40E_UDPIP_DUMMY_PACKET_LEN;
+		__be16 pattern = fd_data->flex_word;
+		u16 off = fd_data->flex_offset;
+
+		*((__force __be16 *)(payload + off)) = pattern;
+	}
+
 	fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
 	ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n",
 			 fd_data->pctype, fd_data->fd_id, ret);
-		err = true;
+		/* Free the packet buffer since it wasn't added to the ring */
+		kfree(raw_packet);
+		return -EOPNOTSUPP;
 	} else if (I40E_DEBUG_FD & pf->hw.debug_mask) {
 		if (add)
 			dev_info(&pf->pdev->dev,
@@ -241,10 +253,13 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi,
 				 "Filter deleted for PCTYPE %d loc = %d\n",
 				 fd_data->pctype, fd_data->fd_id);
 	}
-	if (err)
-		kfree(raw_packet);
 
-	return err ? -EOPNOTSUPP : 0;
+	if (add)
+		pf->fd_udp4_filter_cnt++;
+	else
+		pf->fd_udp4_filter_cnt--;
+
+	return 0;
 }
 
 #define I40E_TCPIP_DUMMY_PACKET_LEN 54
@@ -263,7 +278,6 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
 	struct i40e_pf *pf = vsi->back;
 	struct tcphdr *tcp;
 	struct iphdr *ip;
-	bool err = false;
 	u8 *raw_packet;
 	int ret;
 	/* Dummy packet */
@@ -281,39 +295,116 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
 	tcp = (struct tcphdr *)(raw_packet + IP_HEADER_OFFSET
 	      + sizeof(struct iphdr));
 
-	ip->daddr = fd_data->dst_ip[0];
+	ip->daddr = fd_data->dst_ip;
 	tcp->dest = fd_data->dst_port;
-	ip->saddr = fd_data->src_ip[0];
+	ip->saddr = fd_data->src_ip;
 	tcp->source = fd_data->src_port;
 
+	if (fd_data->flex_filter) {
+		u8 *payload = raw_packet + I40E_TCPIP_DUMMY_PACKET_LEN;
+		__be16 pattern = fd_data->flex_word;
+		u16 off = fd_data->flex_offset;
+
+		*((__force __be16 *)(payload + off)) = pattern;
+	}
+
+	fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+	ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
+	if (ret) {
+		dev_info(&pf->pdev->dev,
+			 "PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n",
+			 fd_data->pctype, fd_data->fd_id, ret);
+		/* Free the packet buffer since it wasn't added to the ring */
+		kfree(raw_packet);
+		return -EOPNOTSUPP;
+	} else if (I40E_DEBUG_FD & pf->hw.debug_mask) {
+		if (add)
+			dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d loc = %d)\n",
+				 fd_data->pctype, fd_data->fd_id);
+		else
+			dev_info(&pf->pdev->dev,
+				 "Filter deleted for PCTYPE %d loc = %d\n",
+				 fd_data->pctype, fd_data->fd_id);
+	}
+
 	if (add) {
-		pf->fd_tcp_rule++;
+		pf->fd_tcp4_filter_cnt++;
 		if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
 		    I40E_DEBUG_FD & pf->hw.debug_mask)
 			dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n");
-		pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
+		pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED;
 	} else {
-		pf->fd_tcp_rule = (pf->fd_tcp_rule > 0) ?
-				  (pf->fd_tcp_rule - 1) : 0;
-		if (pf->fd_tcp_rule == 0) {
+		pf->fd_tcp4_filter_cnt--;
+		if (pf->fd_tcp4_filter_cnt == 0) {
 			if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
 			    I40E_DEBUG_FD & pf->hw.debug_mask)
 				dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n");
-			pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
+			pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
 		}
 	}
 
-	fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
-	ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
+	return 0;
+}
 
+#define I40E_SCTPIP_DUMMY_PACKET_LEN 46
+/**
+ * i40e_add_del_fdir_sctpv4 - Add/Remove SCTPv4 Flow Director filters for
+ * a specific flow spec
+ * @vsi: pointer to the targeted VSI
+ * @fd_data: the flow director data required for the FDir descriptor
+ * @add: true adds a filter, false removes it
+ *
+ * Returns 0 if the filters were successfully added or removed
+ **/
+static int i40e_add_del_fdir_sctpv4(struct i40e_vsi *vsi,
+				    struct i40e_fdir_filter *fd_data,
+				    bool add)
+{
+	struct i40e_pf *pf = vsi->back;
+	struct sctphdr *sctp;
+	struct iphdr *ip;
+	u8 *raw_packet;
+	int ret;
+	/* Dummy packet */
+	static char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0,
+		0x45, 0, 0, 0x20, 0, 0, 0x40, 0, 0x40, 0x84, 0, 0, 0, 0, 0, 0,
+		0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
+
+	raw_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_SIZE, GFP_KERNEL);
+	if (!raw_packet)
+		return -ENOMEM;
+	memcpy(raw_packet, packet, I40E_SCTPIP_DUMMY_PACKET_LEN);
+
+	ip = (struct iphdr *)(raw_packet + IP_HEADER_OFFSET);
+	sctp = (struct sctphdr *)(raw_packet + IP_HEADER_OFFSET
+	      + sizeof(struct iphdr));
+
+	ip->daddr = fd_data->dst_ip;
+	sctp->dest = fd_data->dst_port;
+	ip->saddr = fd_data->src_ip;
+	sctp->source = fd_data->src_port;
+
+	if (fd_data->flex_filter) {
+		u8 *payload = raw_packet + I40E_SCTPIP_DUMMY_PACKET_LEN;
+		__be16 pattern = fd_data->flex_word;
+		u16 off = fd_data->flex_offset;
+
+		*((__force __be16 *)(payload + off)) = pattern;
+	}
+
+	fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_SCTP;
+	ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
 	if (ret) {
 		dev_info(&pf->pdev->dev,
 			 "PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n",
 			 fd_data->pctype, fd_data->fd_id, ret);
-		err = true;
+		/* Free the packet buffer since it wasn't added to the ring */
+		kfree(raw_packet);
+		return -EOPNOTSUPP;
 	} else if (I40E_DEBUG_FD & pf->hw.debug_mask) {
 		if (add)
-			dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d loc = %d)\n",
+			dev_info(&pf->pdev->dev,
+				 "Filter OK for PCTYPE %d loc = %d\n",
 				 fd_data->pctype, fd_data->fd_id);
 		else
 			dev_info(&pf->pdev->dev,
@@ -321,10 +412,12 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
 				 fd_data->pctype, fd_data->fd_id);
 	}
 
-	if (err)
-		kfree(raw_packet);
+	if (add)
+		pf->fd_sctp4_filter_cnt++;
+	else
+		pf->fd_sctp4_filter_cnt--;
 
-	return err ? -EOPNOTSUPP : 0;
+	return 0;
 }
 
 #define I40E_IP_DUMMY_PACKET_LEN 34
@@ -343,7 +436,6 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi,
 {
 	struct i40e_pf *pf = vsi->back;
 	struct iphdr *ip;
-	bool err = false;
 	u8 *raw_packet;
 	int ret;
 	int i;
@@ -359,18 +451,29 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi,
 		memcpy(raw_packet, packet, I40E_IP_DUMMY_PACKET_LEN);
 		ip = (struct iphdr *)(raw_packet + IP_HEADER_OFFSET);
 
-		ip->saddr = fd_data->src_ip[0];
-		ip->daddr = fd_data->dst_ip[0];
+		ip->saddr = fd_data->src_ip;
+		ip->daddr = fd_data->dst_ip;
 		ip->protocol = 0;
 
+		if (fd_data->flex_filter) {
+			u8 *payload = raw_packet + I40E_IP_DUMMY_PACKET_LEN;
+			__be16 pattern = fd_data->flex_word;
+			u16 off = fd_data->flex_offset;
+
+			*((__force __be16 *)(payload + off)) = pattern;
+		}
+
 		fd_data->pctype = i;
 		ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
-
 		if (ret) {
 			dev_info(&pf->pdev->dev,
 				 "PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n",
 				 fd_data->pctype, fd_data->fd_id, ret);
-			err = true;
+			/* The packet buffer wasn't added to the ring so we
+			 * need to free it now.
+			 */
+			kfree(raw_packet);
+			return -EOPNOTSUPP;
 		} else if (I40E_DEBUG_FD & pf->hw.debug_mask) {
 			if (add)
 				dev_info(&pf->pdev->dev,
@@ -383,10 +486,12 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi,
 		}
 	}
 
-	if (err)
-		kfree(raw_packet);
+	if (add)
+		pf->fd_ip4_filter_cnt++;
+	else
+		pf->fd_ip4_filter_cnt--;
 
-	return err ? -EOPNOTSUPP : 0;
+	return 0;
 }
 
 /**
@@ -409,6 +514,9 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi,
 	case UDP_V4_FLOW:
 		ret = i40e_add_del_fdir_udpv4(vsi, input, add);
 		break;
+	case SCTP_V4_FLOW:
+		ret = i40e_add_del_fdir_sctpv4(vsi, input, add);
+		break;
 	case IP_USER_FLOW:
 		switch (input->ip4_proto) {
 		case IPPROTO_TCP:
@@ -417,6 +525,9 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi,
 		case IPPROTO_UDP:
 			ret = i40e_add_del_fdir_udpv4(vsi, input, add);
 			break;
+		case IPPROTO_SCTP:
+			ret = i40e_add_del_fdir_sctpv4(vsi, input, add);
+			break;
 		case IPPROTO_IP:
 			ret = i40e_add_del_fdir_ipv4(vsi, input, add);
 			break;
@@ -484,8 +595,8 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring,
 		pf->fd_atr_cnt = i40e_get_current_atr_cnt(pf);
 
 		if ((rx_desc->wb.qword0.hi_dword.fd_id == 0) &&
-		    (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) {
-			pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
+		    (pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED)) {
+			pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED;
 			set_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
 		}
 
@@ -498,11 +609,11 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring,
 		 */
 		if (fcnt_prog >= (fcnt_avail - I40E_FDIR_BUFFER_FULL_MARGIN)) {
 			if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
-			    !(pf->auto_disable_flags &
+			    !(pf->hw_disabled_flags &
 				     I40E_FLAG_FD_SB_ENABLED)) {
 				if (I40E_DEBUG_FD & pf->hw.debug_mask)
 					dev_warn(&pdev->dev, "FD filter space full, new ntuple rules will not be added\n");
-				pf->auto_disable_flags |=
+				pf->hw_disabled_flags |=
 							I40E_FLAG_FD_SB_ENABLED;
 			}
 		}
@@ -951,11 +1062,6 @@ static void i40e_clean_programming_status(struct i40e_ring *rx_ring,
 
 	if (id == I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS)
 		i40e_fd_handle_status(rx_ring, rx_desc, id);
-#ifdef I40E_FCOE
-	else if ((id == I40E_RX_PROG_STATUS_DESC_FCOE_CTXT_PROG_STATUS) ||
-		 (id == I40E_RX_PROG_STATUS_DESC_FCOE_CTXT_INVL_STATUS))
-		i40e_fcoe_handle_status(rx_ring, rx_desc, id);
-#endif
 }
 
 /**
@@ -1010,7 +1116,6 @@ err:
  **/
 void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 {
-	struct device *dev = rx_ring->dev;
 	unsigned long bi_size;
 	u16 i;
 
@@ -1030,8 +1135,21 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 		if (!rx_bi->page)
 			continue;
 
-		dma_unmap_page(dev, rx_bi->dma, PAGE_SIZE, DMA_FROM_DEVICE);
-		__free_pages(rx_bi->page, 0);
+		/* Invalidate cache lines that may have been written to by
+		 * device so that we avoid corrupting memory.
+		 */
+		dma_sync_single_range_for_cpu(rx_ring->dev,
+					      rx_bi->dma,
+					      rx_bi->page_offset,
+					      I40E_RXBUFFER_2048,
+					      DMA_FROM_DEVICE);
+
+		/* free resources associated with mapping */
+		dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma,
+				     PAGE_SIZE,
+				     DMA_FROM_DEVICE,
+				     I40E_RX_DMA_ATTR);
+		__page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias);
 
 		rx_bi->page = NULL;
 		rx_bi->page_offset = 0;
@@ -1159,7 +1277,10 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
 	}
 
 	/* map page for use */
-	dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	dma = dma_map_page_attrs(rx_ring->dev, page, 0,
+				 PAGE_SIZE,
+				 DMA_FROM_DEVICE,
+				 I40E_RX_DMA_ATTR);
 
 	/* if mapping failed free memory back to system since
 	 * there isn't much point in holding memory we can't use
@@ -1174,6 +1295,9 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
 	bi->page = page;
 	bi->page_offset = 0;
 
+	/* initialize pagecnt_bias to 1 representing we fully own page */
+	bi->pagecnt_bias = 1;
+
 	return true;
 }
 
@@ -1219,6 +1343,12 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
 		if (!i40e_alloc_mapped_page(rx_ring, bi))
 			goto no_buffers;
 
+		/* sync the buffer for use by the device */
+		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+						 bi->page_offset,
+						 I40E_RXBUFFER_2048,
+						 DMA_FROM_DEVICE);
+
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
@@ -1259,8 +1389,6 @@ no_buffers:
  * @vsi: the VSI we care about
  * @skb: skb currently being received and modified
  * @rx_desc: the receive descriptor
- *
- * skb->protocol must be set before this function is called
  **/
 static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 				    struct sk_buff *skb,
@@ -1422,12 +1550,12 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring,
 
 	i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
 
-	/* modifies the skb - consumes the enet header */
-	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
-
 	i40e_rx_checksum(rx_ring->vsi, skb, rx_desc);
 
 	skb_record_rx_queue(skb, rx_ring->queue_index);
+
+	/* modifies the skb - consumes the enet header */
+	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 }
 
 /**
@@ -1472,7 +1600,10 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring,
 	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
 
 	/* transfer page from old buffer to new buffer */
-	*new_buff = *old_buff;
+	new_buff->dma		= old_buff->dma;
+	new_buff->page		= old_buff->page;
+	new_buff->page_offset	= old_buff->page_offset;
+	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
 }
 
 /**
@@ -1493,8 +1624,6 @@ static inline bool i40e_page_is_reusable(struct page *page)
  * the adapter for another receive
  *
  * @rx_buffer: buffer containing the page
- * @page: page address from rx_buffer
- * @truesize: actual size of the buffer in this page
  *
  * If page is reusable, rx_buffer->page_offset is adjusted to point to
  * an unused region in the page.
@@ -1517,13 +1646,13 @@ static inline bool i40e_page_is_reusable(struct page *page)
  *
  * In either case, if the page is reusable its refcount is increased.
  **/
-static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
-				   struct page *page,
-				   const unsigned int truesize)
+static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer)
 {
 #if (PAGE_SIZE >= 8192)
 	unsigned int last_offset = PAGE_SIZE - I40E_RXBUFFER_2048;
 #endif
+	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
+	struct page *page = rx_buffer->page;
 
 	/* Is any reuse possible? */
 	if (unlikely(!i40e_page_is_reusable(page)))
@@ -1531,21 +1660,21 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
 
 #if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
-	if (unlikely(page_count(page) != 1))
+	if (unlikely((page_count(page) - pagecnt_bias) > 1))
 		return false;
-
-	/* flip page offset to other buffer */
-	rx_buffer->page_offset ^= truesize;
 #else
-	/* move offset up to the next cache line */
-	rx_buffer->page_offset += truesize;
-
 	if (rx_buffer->page_offset > last_offset)
 		return false;
 #endif
 
-	/* Inc ref count on page before passing it up to the stack */
-	get_page(page);
+	/* If we have drained the page fragment pool we need to update
+	 * the pagecnt_bias and page count so that we fully restock the
+	 * number of references the driver holds.
+	 */
+	if (unlikely(!pagecnt_bias)) {
+		page_ref_add(page, USHRT_MAX);
+		rx_buffer->pagecnt_bias = USHRT_MAX;
+	}
 
 	return true;
 }
@@ -1554,145 +1683,155 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
  * i40e_add_rx_frag - Add contents of Rx buffer to sk_buff
  * @rx_ring: rx descriptor ring to transact packets on
  * @rx_buffer: buffer containing page to add
- * @size: packet length from rx_desc
  * @skb: sk_buff to place the data into
+ * @size: packet length from rx_desc
  *
  * This function will add the data contained in rx_buffer->page to the skb.
- * This is done either through a direct copy if the data in the buffer is
- * less than the skb header size, otherwise it will just attach the page as
- * a frag to the skb.
+ * It will just attach the page as a frag to the skb.
  *
- * The function will then update the page offset if necessary and return
- * true if the buffer can be reused by the adapter.
+ * The function will then update the page offset.
  **/
-static bool i40e_add_rx_frag(struct i40e_ring *rx_ring,
+static void i40e_add_rx_frag(struct i40e_ring *rx_ring,
 			     struct i40e_rx_buffer *rx_buffer,
-			     unsigned int size,
-			     struct sk_buff *skb)
+			     struct sk_buff *skb,
+			     unsigned int size)
 {
-	struct page *page = rx_buffer->page;
-	unsigned char *va = page_address(page) + rx_buffer->page_offset;
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = I40E_RXBUFFER_2048;
 #else
-	unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
+	unsigned int truesize = SKB_DATA_ALIGN(size);
 #endif
-	unsigned int pull_len;
-
-	if (unlikely(skb_is_nonlinear(skb)))
-		goto add_tail_frag;
 
-	/* will the data fit in the skb we allocated? if so, just
-	 * copy it as it is pretty small anyway
-	 */
-	if (size <= I40E_RX_HDR_SIZE) {
-		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
+			rx_buffer->page_offset, size, truesize);
 
-		/* page is reusable, we can reuse buffer as-is */
-		if (likely(i40e_page_is_reusable(page)))
-			return true;
-
-		/* this page cannot be reused so discard it */
-		__free_pages(page, 0);
-		return false;
-	}
+	/* page is being used so we must update the page offset */
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
+}
 
-	/* we need the header to contain the greater of either
-	 * ETH_HLEN or 60 bytes if the skb->len is less than
-	 * 60 for skb_pad.
-	 */
-	pull_len = eth_get_headlen(va, I40E_RX_HDR_SIZE);
+/**
+ * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @size: size of buffer to add to skb
+ *
+ * This function will pull an Rx buffer from the ring and synchronize it
+ * for use by the CPU.
+ */
+static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
+						 const unsigned int size)
+{
+	struct i40e_rx_buffer *rx_buffer;
 
-	/* align pull length to size of long to optimize
-	 * memcpy performance
-	 */
-	memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
+	rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
+	prefetchw(rx_buffer->page);
 
-	/* update all of the pointers */
-	va += pull_len;
-	size -= pull_len;
+	/* we are reusing so sync this buffer for CPU use */
+	dma_sync_single_range_for_cpu(rx_ring->dev,
+				      rx_buffer->dma,
+				      rx_buffer->page_offset,
+				      size,
+				      DMA_FROM_DEVICE);
 
-add_tail_frag:
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
-			(unsigned long)va & ~PAGE_MASK, size, truesize);
+	/* We have pulled a buffer for use, so decrement pagecnt_bias */
+	rx_buffer->pagecnt_bias--;
 
-	return i40e_can_reuse_rx_page(rx_buffer, page, truesize);
+	return rx_buffer;
 }
 
 /**
- * i40e_fetch_rx_buffer - Allocate skb and populate it
+ * i40e_construct_skb - Allocate skb and populate it
  * @rx_ring: rx descriptor ring to transact packets on
- * @rx_desc: descriptor containing info written by hardware
+ * @rx_buffer: rx buffer to pull data from
+ * @size: size of buffer to add to skb
  *
- * This function allocates an skb on the fly, and populates it with the page
- * data from the current receive descriptor, taking care to set up the skb
- * correctly, as well as handling calling the page recycle function if
- * necessary.
+ * This function allocates an skb.  It then populates it with the page
+ * data from the current receive descriptor, taking care to set up the
+ * skb correctly.
  */
-static inline
-struct sk_buff *i40e_fetch_rx_buffer(struct i40e_ring *rx_ring,
-				     union i40e_rx_desc *rx_desc,
-				     struct sk_buff *skb)
+static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
+					  struct i40e_rx_buffer *rx_buffer,
+					  unsigned int size)
 {
-	u64 local_status_error_len =
-		le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-	unsigned int size =
-		(local_status_error_len & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
-		I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
-	struct i40e_rx_buffer *rx_buffer;
-	struct page *page;
-
-	rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
-	page = rx_buffer->page;
-	prefetchw(page);
-
-	if (likely(!skb)) {
-		void *page_addr = page_address(page) + rx_buffer->page_offset;
+	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = I40E_RXBUFFER_2048;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(size);
+#endif
+	unsigned int headlen;
+	struct sk_buff *skb;
 
-		/* prefetch first cache line of first page */
-		prefetch(page_addr);
+	/* prefetch first cache line of first page */
+	prefetch(va);
 #if L1_CACHE_BYTES < 128
-		prefetch(page_addr + L1_CACHE_BYTES);
+	prefetch(va + L1_CACHE_BYTES);
 #endif
 
-		/* allocate a skb to store the frags */
-		skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
-				       I40E_RX_HDR_SIZE,
-				       GFP_ATOMIC | __GFP_NOWARN);
-		if (unlikely(!skb)) {
-			rx_ring->rx_stats.alloc_buff_failed++;
-			return NULL;
-		}
+	/* allocate a skb to store the frags */
+	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
+			       I40E_RX_HDR_SIZE,
+			       GFP_ATOMIC | __GFP_NOWARN);
+	if (unlikely(!skb))
+		return NULL;
 
-		/* we will be copying header into skb->data in
-		 * pskb_may_pull so it is in our interest to prefetch
-		 * it now to avoid a possible cache miss
-		 */
-		prefetchw(skb->data);
+	/* Determine available headroom for copy */
+	headlen = size;
+	if (headlen > I40E_RX_HDR_SIZE)
+		headlen = eth_get_headlen(va, I40E_RX_HDR_SIZE);
+
+	/* align pull length to size of long to optimize memcpy performance */
+	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
+
+	/* update all of the pointers */
+	size -= headlen;
+	if (size) {
+		skb_add_rx_frag(skb, 0, rx_buffer->page,
+				rx_buffer->page_offset + headlen,
+				size, truesize);
+
+		/* buffer is used by skb, update page_offset */
+#if (PAGE_SIZE < 8192)
+		rx_buffer->page_offset ^= truesize;
+#else
+		rx_buffer->page_offset += truesize;
+#endif
+	} else {
+		/* buffer is unused, reset bias back to rx_buffer */
+		rx_buffer->pagecnt_bias++;
 	}
 
-	/* we are reusing so sync this buffer for CPU use */
-	dma_sync_single_range_for_cpu(rx_ring->dev,
-				      rx_buffer->dma,
-				      rx_buffer->page_offset,
-				      size,
-				      DMA_FROM_DEVICE);
+	return skb;
+}
 
-	/* pull page into skb */
-	if (i40e_add_rx_frag(rx_ring, rx_buffer, size, skb)) {
+/**
+ * i40e_put_rx_buffer - Clean up used buffer and either recycle or free
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_buffer: rx buffer to pull data from
+ *
+ * This function will clean up the contents of the rx_buffer.  It will
+ * either recycle the bufer or unmap it and free the associated resources.
+ */
+static void i40e_put_rx_buffer(struct i40e_ring *rx_ring,
+			       struct i40e_rx_buffer *rx_buffer)
+{
+	if (i40e_can_reuse_rx_page(rx_buffer)) {
 		/* hand second half of page back to the ring */
 		i40e_reuse_rx_page(rx_ring, rx_buffer);
 		rx_ring->rx_stats.page_reuse_count++;
 	} else {
 		/* we are not reusing the buffer so unmap it */
-		dma_unmap_page(rx_ring->dev, rx_buffer->dma, PAGE_SIZE,
-			       DMA_FROM_DEVICE);
+		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, PAGE_SIZE,
+				     DMA_FROM_DEVICE, I40E_RX_DMA_ATTR);
+		__page_frag_cache_drain(rx_buffer->page,
+					rx_buffer->pagecnt_bias);
 	}
 
 	/* clear contents of buffer_info */
 	rx_buffer->page = NULL;
-
-	return skb;
 }
 
 /**
@@ -1753,7 +1892,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	bool failure = false;
 
 	while (likely(total_rx_packets < budget)) {
+		struct i40e_rx_buffer *rx_buffer;
 		union i40e_rx_desc *rx_desc;
+		unsigned int size;
 		u16 vlan_tag;
 		u8 rx_ptype;
 		u64 qword;
@@ -1770,22 +1911,36 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		/* status_error_len will always be zero for unused descriptors
 		 * because it's cleared in cleanup, and overlaps with hdr_addr
 		 * which is always zero because packet split isn't used, if the
-		 * hardware wrote DD then it will be non-zero
+		 * hardware wrote DD then the length will be non-zero
 		 */
-		if (!i40e_test_staterr(rx_desc,
-				       BIT(I40E_RX_DESC_STATUS_DD_SHIFT)))
+		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+		size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
+		       I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
+		if (!size)
 			break;
 
 		/* This memory barrier is needed to keep us from reading
-		 * any other fields out of the rx_desc until we know the
-		 * DD bit is set.
+		 * any other fields out of the rx_desc until we have
+		 * verified the descriptor has been written back.
 		 */
 		dma_rmb();
 
-		skb = i40e_fetch_rx_buffer(rx_ring, rx_desc, skb);
-		if (!skb)
+		rx_buffer = i40e_get_rx_buffer(rx_ring, size);
+
+		/* retrieve a buffer from the ring */
+		if (skb)
+			i40e_add_rx_frag(rx_ring, rx_buffer, skb, size);
+		else
+			skb = i40e_construct_skb(rx_ring, rx_buffer, size);
+
+		/* exit if we failed to retrieve a buffer */
+		if (!skb) {
+			rx_ring->rx_stats.alloc_buff_failed++;
+			rx_buffer->pagecnt_bias++;
 			break;
+		}
 
+		i40e_put_rx_buffer(rx_ring, rx_buffer);
 		cleaned_count++;
 
 		if (i40e_is_non_eop(rx_ring, rx_desc, skb))
@@ -1798,6 +1953,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		 */
 		if (unlikely(i40e_test_staterr(rx_desc, BIT(I40E_RXD_QW1_ERROR_SHIFT)))) {
 			dev_kfree_skb_any(skb);
+			skb = NULL;
 			continue;
 		}
 
@@ -1816,15 +1972,6 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		/* populate checksum, VLAN, and protocol */
 		i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
 
-#ifdef I40E_FCOE
-		if (unlikely(
-		    i40e_rx_is_fcoe(rx_ptype) &&
-		    !i40e_fcoe_handle_offload(rx_ring, rx_desc, skb))) {
-			dev_kfree_skb_any(skb);
-			continue;
-		}
-#endif
-
 		vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ?
 			   le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0;
 
@@ -2079,7 +2226,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	if (!(pf->flags & I40E_FLAG_FD_ATR_ENABLED))
 		return;
 
-	if ((pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED))
+	if ((pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED))
 		return;
 
 	/* if sampling is disabled do nothing */
@@ -2113,10 +2260,10 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	th = (struct tcphdr *)(hdr.network + hlen);
 
 	/* Due to lack of space, no more new filters can be programmed */
-	if (th->syn && (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED))
+	if (th->syn && (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED))
 		return;
 	if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) &&
-	    (!(pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) {
+	    (!(pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) {
 		/* HW ATR eviction will take care of removing filters on FIN
 		 * and RST packets.
 		 */
@@ -2179,7 +2326,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 			I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
 
 	if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) &&
-	    (!(pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)))
+	    (!(pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)))
 		dtype_cmd |= I40E_TXD_FLTR_QW1_ATR_MASK;
 
 	fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype);
@@ -2200,15 +2347,9 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
  * Returns error code indicate the frame should be dropped upon error and the
  * otherwise  returns 0 to indicate the flags has been set properly.
  **/
-#ifdef I40E_FCOE
-inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
-				      struct i40e_ring *tx_ring,
-				      u32 *flags)
-#else
 static inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
 					     struct i40e_ring *tx_ring,
 					     u32 *flags)
-#endif
 {
 	__be16 protocol = skb->protocol;
 	u32  tx_flags = 0;
@@ -2716,15 +2857,9 @@ bool __i40e_chk_linearize(struct sk_buff *skb)
  * @td_cmd:   the command field in the descriptor
  * @td_offset: offset for checksum or crc
  **/
-#ifdef I40E_FCOE
-inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
-			struct i40e_tx_buffer *first, u32 tx_flags,
-			const u8 hdr_len, u32 td_cmd, u32 td_offset)
-#else
 static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 			       struct i40e_tx_buffer *first, u32 tx_flags,
 			       const u8 hdr_len, u32 td_cmd, u32 td_offset)
-#endif
 {
 	unsigned int data_len = skb->data_len;
 	unsigned int size = skb_headlen(skb);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index f80979025c01..d6609deace57 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -117,10 +117,8 @@ enum i40e_dyn_idx_t {
 
 /* Supported Rx Buffer Sizes (a multiple of 128) */
 #define I40E_RXBUFFER_256   256
+#define I40E_RXBUFFER_1536  1536  /* 128B aligned standard Ethernet frame */
 #define I40E_RXBUFFER_2048  2048
-#define I40E_RXBUFFER_3072  3072   /* For FCoE MTU of 2158 */
-#define I40E_RXBUFFER_4096  4096
-#define I40E_RXBUFFER_8192  8192
 #define I40E_MAX_RXBUFFER   9728  /* largest size for single descriptor */
 
 /* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we
@@ -133,6 +131,9 @@ enum i40e_dyn_idx_t {
 #define I40E_RX_HDR_SIZE I40E_RXBUFFER_256
 #define i40e_rx_desc i40e_32byte_rx_desc
 
+#define I40E_RX_DMA_ATTR \
+	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
 /**
  * i40e_test_staterr - tests bits in Rx descriptor status and error fields
  * @rx_desc: pointer to receive descriptor (in le64 format)
@@ -255,7 +256,12 @@ struct i40e_tx_buffer {
 struct i40e_rx_buffer {
 	dma_addr_t dma;
 	struct page *page;
-	unsigned int page_offset;
+#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
+	__u32 page_offset;
+#else
+	__u16 page_offset;
+#endif
+	__u16 pagecnt_bias;
 };
 
 struct i40e_queue_stats {
@@ -393,13 +399,6 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring);
 void i40e_free_tx_resources(struct i40e_ring *tx_ring);
 void i40e_free_rx_resources(struct i40e_ring *rx_ring);
 int i40e_napi_poll(struct napi_struct *napi, int budget);
-#ifdef I40E_FCOE
-void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
-		 struct i40e_tx_buffer *first, u32 tx_flags,
-		 const u8 hdr_len, u32 td_cmd, u32 td_offset);
-int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
-			       struct i40e_ring *tx_ring, u32 *flags);
-#endif
 void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector);
 u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw);
 int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
@@ -483,16 +482,6 @@ static inline bool i40e_chk_linearize(struct sk_buff *skb, int count)
 }
 
 /**
- * i40e_rx_is_fcoe - returns true if the Rx packet type is FCoE
- * @ptype: the packet type field from Rx descriptor write-back
- **/
-static inline bool i40e_rx_is_fcoe(u16 ptype)
-{
-	return (ptype >= I40E_RX_PTYPE_L2_FCOE_PAY3) &&
-	       (ptype <= I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER);
-}
-
-/**
  * txring_txq - Find the netdev Tx ring based on the i40e Tx ring
  * @ring: Tx ring to find the netdev equivalent of
  **/
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 939f9fdc8f85..9200f2d9c752 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -1213,25 +1213,6 @@ struct i40e_veb_tc_stats {
 	u64 tc_tx_bytes[I40E_MAX_TRAFFIC_CLASS];
 };
 
-#ifdef I40E_FCOE
-/* Statistics collected per function for FCoE */
-struct i40e_fcoe_stats {
-	u64 rx_fcoe_packets;		/* fcoeprc */
-	u64 rx_fcoe_dwords;		/* focedwrc */
-	u64 rx_fcoe_dropped;		/* fcoerpdc */
-	u64 tx_fcoe_packets;		/* fcoeptc */
-	u64 tx_fcoe_dwords;		/* focedwtc */
-	u64 fcoe_bad_fccrc;		/* fcoecrc */
-	u64 fcoe_last_error;		/* fcoelast */
-	u64 fcoe_ddp_count;		/* fcoeddpc */
-};
-
-/* offset to per function FCoE statistics block */
-#define I40E_FCOE_VF_STAT_OFFSET	0
-#define I40E_FCOE_PF_STAT_OFFSET	128
-#define I40E_FCOE_STAT_MAX		(I40E_FCOE_PF_STAT_OFFSET + I40E_MAX_PF)
-
-#endif
 /* Statistics collected by the MAC */
 struct i40e_hw_port_stats {
 	/* eth stats collected by the port */
@@ -1319,125 +1300,6 @@ struct i40e_hw_port_stats {
 
 #define I40E_SRRD_SRCTL_ATTEMPTS	100000
 
-#ifdef I40E_FCOE
-/* FCoE Tx context descriptor - Use the i40e_tx_context_desc struct */
-
-enum i40E_fcoe_tx_ctx_desc_cmd_bits {
-	I40E_FCOE_TX_CTX_DESC_OPCODE_SINGLE_SEND	= 0x00, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_OPCODE_TSO_FC_CLASS2	= 0x01, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_OPCODE_TSO_FC_CLASS3	= 0x05, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_OPCODE_ETSO_FC_CLASS2	= 0x02, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_OPCODE_ETSO_FC_CLASS3	= 0x06, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_OPCODE_DWO_FC_CLASS2	= 0x03, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_OPCODE_DWO_FC_CLASS3	= 0x07, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_OPCODE_DDP_CTX_INVL	= 0x08, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_OPCODE_DWO_CTX_INVL	= 0x09, /* 4 BITS */
-	I40E_FCOE_TX_CTX_DESC_RELOFF			= 0x10,
-	I40E_FCOE_TX_CTX_DESC_CLRSEQ			= 0x20,
-	I40E_FCOE_TX_CTX_DESC_DIFENA			= 0x40,
-	I40E_FCOE_TX_CTX_DESC_IL2TAG2			= 0x80
-};
-
-/* FCoE DDP Context descriptor */
-struct i40e_fcoe_ddp_context_desc {
-	__le64 rsvd;
-	__le64 type_cmd_foff_lsize;
-};
-
-#define I40E_FCOE_DDP_CTX_QW1_DTYPE_SHIFT	0
-#define I40E_FCOE_DDP_CTX_QW1_DTYPE_MASK	(0xFULL << \
-					I40E_FCOE_DDP_CTX_QW1_DTYPE_SHIFT)
-
-#define I40E_FCOE_DDP_CTX_QW1_CMD_SHIFT	4
-#define I40E_FCOE_DDP_CTX_QW1_CMD_MASK	(0xFULL << \
-					 I40E_FCOE_DDP_CTX_QW1_CMD_SHIFT)
-
-enum i40e_fcoe_ddp_ctx_desc_cmd_bits {
-	I40E_FCOE_DDP_CTX_DESC_BSIZE_512B	= 0x00, /* 2 BITS */
-	I40E_FCOE_DDP_CTX_DESC_BSIZE_4K		= 0x01, /* 2 BITS */
-	I40E_FCOE_DDP_CTX_DESC_BSIZE_8K		= 0x02, /* 2 BITS */
-	I40E_FCOE_DDP_CTX_DESC_BSIZE_16K	= 0x03, /* 2 BITS */
-	I40E_FCOE_DDP_CTX_DESC_DIFENA		= 0x04, /* 1 BIT  */
-	I40E_FCOE_DDP_CTX_DESC_LASTSEQH		= 0x08, /* 1 BIT  */
-};
-
-#define I40E_FCOE_DDP_CTX_QW1_FOFF_SHIFT	16
-#define I40E_FCOE_DDP_CTX_QW1_FOFF_MASK	(0x3FFFULL << \
-					 I40E_FCOE_DDP_CTX_QW1_FOFF_SHIFT)
-
-#define I40E_FCOE_DDP_CTX_QW1_LSIZE_SHIFT	32
-#define I40E_FCOE_DDP_CTX_QW1_LSIZE_MASK	(0x3FFFULL << \
-					I40E_FCOE_DDP_CTX_QW1_LSIZE_SHIFT)
-
-/* FCoE DDP/DWO Queue Context descriptor */
-struct i40e_fcoe_queue_context_desc {
-	__le64 dmaindx_fbase;           /* 0:11 DMAINDX, 12:63 FBASE */
-	__le64 flen_tph;                /* 0:12 FLEN, 13:15 TPH */
-};
-
-#define I40E_FCOE_QUEUE_CTX_QW0_DMAINDX_SHIFT	0
-#define I40E_FCOE_QUEUE_CTX_QW0_DMAINDX_MASK	(0xFFFULL << \
-					I40E_FCOE_QUEUE_CTX_QW0_DMAINDX_SHIFT)
-
-#define I40E_FCOE_QUEUE_CTX_QW0_FBASE_SHIFT	12
-#define I40E_FCOE_QUEUE_CTX_QW0_FBASE_MASK	(0xFFFFFFFFFFFFFULL << \
-					I40E_FCOE_QUEUE_CTX_QW0_FBASE_SHIFT)
-
-#define I40E_FCOE_QUEUE_CTX_QW1_FLEN_SHIFT	0
-#define I40E_FCOE_QUEUE_CTX_QW1_FLEN_MASK	(0x1FFFULL << \
-					I40E_FCOE_QUEUE_CTX_QW1_FLEN_SHIFT)
-
-#define I40E_FCOE_QUEUE_CTX_QW1_TPH_SHIFT	13
-#define I40E_FCOE_QUEUE_CTX_QW1_TPH_MASK	(0x7ULL << \
-					I40E_FCOE_QUEUE_CTX_QW1_FLEN_SHIFT)
-
-enum i40e_fcoe_queue_ctx_desc_tph_bits {
-	I40E_FCOE_QUEUE_CTX_DESC_TPHRDESC	= 0x1,
-	I40E_FCOE_QUEUE_CTX_DESC_TPHDATA	= 0x2
-};
-
-#define I40E_FCOE_QUEUE_CTX_QW1_RECIPE_SHIFT	30
-#define I40E_FCOE_QUEUE_CTX_QW1_RECIPE_MASK	(0x3ULL << \
-					I40E_FCOE_QUEUE_CTX_QW1_RECIPE_SHIFT)
-
-/* FCoE DDP/DWO Filter Context descriptor */
-struct i40e_fcoe_filter_context_desc {
-	__le32 param;
-	__le16 seqn;
-
-	/* 48:51(0:3) RSVD, 52:63(4:15) DMAINDX */
-	__le16 rsvd_dmaindx;
-
-	/* 0:7 FLAGS, 8:52 RSVD, 53:63 LANQ */
-	__le64 flags_rsvd_lanq;
-};
-
-#define I40E_FCOE_FILTER_CTX_QW0_DMAINDX_SHIFT	4
-#define I40E_FCOE_FILTER_CTX_QW0_DMAINDX_MASK	(0xFFF << \
-					I40E_FCOE_FILTER_CTX_QW0_DMAINDX_SHIFT)
-
-enum i40e_fcoe_filter_ctx_desc_flags_bits {
-	I40E_FCOE_FILTER_CTX_DESC_CTYP_DDP	= 0x00,
-	I40E_FCOE_FILTER_CTX_DESC_CTYP_DWO	= 0x01,
-	I40E_FCOE_FILTER_CTX_DESC_ENODE_INIT	= 0x00,
-	I40E_FCOE_FILTER_CTX_DESC_ENODE_RSP	= 0x02,
-	I40E_FCOE_FILTER_CTX_DESC_FC_CLASS2	= 0x00,
-	I40E_FCOE_FILTER_CTX_DESC_FC_CLASS3	= 0x04
-};
-
-#define I40E_FCOE_FILTER_CTX_QW1_FLAGS_SHIFT	0
-#define I40E_FCOE_FILTER_CTX_QW1_FLAGS_MASK	(0xFFULL << \
-					I40E_FCOE_FILTER_CTX_QW1_FLAGS_SHIFT)
-
-#define I40E_FCOE_FILTER_CTX_QW1_PCTYPE_SHIFT     8
-#define I40E_FCOE_FILTER_CTX_QW1_PCTYPE_MASK      (0x3FULL << \
-			I40E_FCOE_FILTER_CTX_QW1_PCTYPE_SHIFT)
-
-#define I40E_FCOE_FILTER_CTX_QW1_LANQINDX_SHIFT     53
-#define I40E_FCOE_FILTER_CTX_QW1_LANQINDX_MASK      (0x7FFULL << \
-			I40E_FCOE_FILTER_CTX_QW1_LANQINDX_SHIFT)
-
-#endif /* I40E_FCOE */
 enum i40e_switch_element_types {
 	I40E_SWITCH_ELEMENT_TYPE_MAC	= 1,
 	I40E_SWITCH_ELEMENT_TYPE_PF	= 2,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 78460c52b7c4..d526940ff951 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -702,10 +702,8 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
 			dev_info(&pf->pdev->dev,
 				 "Could not allocate VF broadcast filter\n");
 		spin_unlock_bh(&vsi->mac_filter_hash_lock);
-		i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id),
-				  (u32)hena);
-		i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id),
-				  (u32)(hena >> 32));
+		wr32(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)hena);
+		wr32(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id), (u32)(hena >> 32));
 	}
 
 	/* program mac filter */
@@ -811,6 +809,11 @@ static void i40e_free_vf_res(struct i40e_vf *vf)
 	u32 reg_idx, reg;
 	int i, msix_vf;
 
+	/* Start by disabling VF's configuration API to prevent the OS from
+	 * accessing the VF's VSI after it's freed / invalidated.
+	 */
+	clear_bit(I40E_VF_STAT_INIT, &vf->vf_states);
+
 	/* free vsi & disconnect it from the parent uplink */
 	if (vf->lan_vsi_idx) {
 		i40e_vsi_release(pf->vsi[vf->lan_vsi_idx]);
@@ -850,7 +853,6 @@ static void i40e_free_vf_res(struct i40e_vf *vf)
 	/* reset some of the state variables keeping track of the resources */
 	vf->num_queue_pairs = 0;
 	vf->vf_states = 0;
-	clear_bit(I40E_VF_STAT_INIT, &vf->vf_states);
 }
 
 /**
@@ -941,6 +943,14 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
 	/* warn the VF */
 	clear_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states);
 
+	/* Disable VF's configuration API during reset. The flag is re-enabled
+	 * in i40e_alloc_vf_res(), when it's safe again to access VF's VSI.
+	 * It's normally disabled in i40e_free_vf_res(), but it's safer
+	 * to do it earlier to give some time to finish to any VF config
+	 * functions that may still be running at this point.
+	 */
+	clear_bit(I40E_VF_STAT_INIT, &vf->vf_states);
+
 	/* In the case of a VFLR, the HW has already reset the VF and we
 	 * just need to clean up, so don't hit the VFRTRIG register.
 	 */
@@ -984,11 +994,6 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
 	if (!rsd)
 		dev_err(&pf->pdev->dev, "VF reset check timeout on VF %d\n",
 			vf->vf_id);
-	wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_COMPLETED);
-	/* clear the reset bit in the VPGEN_VFRTRIG reg */
-	reg = rd32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id));
-	reg &= ~I40E_VPGEN_VFRTRIG_VFSWR_MASK;
-	wr32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id), reg);
 
 	/* On initial reset, we won't have any queues */
 	if (vf->lan_vsi_idx == 0)
@@ -996,8 +1001,24 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
 
 	i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]);
 complete_reset:
-	/* reallocate VF resources to reset the VSI state */
+	/* free VF resources to begin resetting the VSI state */
 	i40e_free_vf_res(vf);
+
+	/* Enable hardware by clearing the reset bit in the VPGEN_VFRTRIG reg.
+	 * By doing this we allow HW to access VF memory at any point. If we
+	 * did it any sooner, HW could access memory while it was being freed
+	 * in i40e_free_vf_res(), causing an IOMMU fault.
+	 *
+	 * On the other hand, this needs to be done ASAP, because the VF driver
+	 * is waiting for this to happen and may report a timeout. It's
+	 * harmless, but it gets logged into Guest OS kernel log, so best avoid
+	 * it.
+	 */
+	reg = rd32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id));
+	reg &= ~I40E_VPGEN_VFRTRIG_VFSWR_MASK;
+	wr32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id), reg);
+
+	/* reallocate VF resources to finish resetting the VSI state */
 	if (!i40e_alloc_vf_res(vf)) {
 		int abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id;
 		i40e_enable_vf_mappings(vf);
@@ -1008,7 +1029,11 @@ complete_reset:
 			i40e_notify_client_of_vf_reset(pf, abs_vf_id);
 		vf->num_vlan = 0;
 	}
-	/* tell the VF the reset is done */
+
+	/* Tell the VF driver the reset is done. This needs to be done only
+	 * after VF has been fully initialized, because the VF driver may
+	 * request resources immediately after setting this flag.
+	 */
 	wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_VFACTIVE);
 
 	i40e_flush(hw);
@@ -1359,7 +1384,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 	if (!vsi->info.pvid)
 		vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_VLAN;
 
-	if (i40e_vf_client_capable(pf, vf->vf_id, I40E_CLIENT_IWARP) &&
+	if (i40e_vf_client_capable(pf, vf->vf_id) &&
 	    (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_IWARP)) {
 		vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_IWARP;
 		set_bit(I40E_VF_STAT_IWARPENA, &vf->vf_states);
@@ -1853,7 +1878,7 @@ error_param:
 }
 
 /* If the VF is not trusted restrict the number of MAC/VLAN it can program */
-#define I40E_VC_MAX_MAC_ADDR_PER_VF 8
+#define I40E_VC_MAX_MAC_ADDR_PER_VF 12
 #define I40E_VC_MAX_VLAN_PER_VF 8
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index 4012d069939a..37af437daa5d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -87,7 +87,6 @@ struct i40e_vf {
 	u16 stag;
 
 	struct i40e_virtchnl_ether_addr default_lan_addr;
-	struct i40e_virtchnl_ether_addr default_fcoe_addr;
 	u16 port_vlan_id;
 	bool pf_set_mac;	/* The VMM admin set the VF MAC address */
 	bool trusted;
diff --git a/drivers/net/ethernet/intel/i40evf/Makefile b/drivers/net/ethernet/intel/i40evf/Makefile
index 3a423836a565..827c7a6ed0ba 100644
--- a/drivers/net/ethernet/intel/i40evf/Makefile
+++ b/drivers/net/ethernet/intel/i40evf/Makefile
@@ -32,5 +32,5 @@
 obj-$(CONFIG_I40EVF) += i40evf.o
 
 i40evf-objs :=	i40evf_main.o i40evf_ethtool.o i40evf_virtchnl.o \
-		i40e_txrx.o i40e_common.o i40e_adminq.o
+		i40e_txrx.o i40e_common.o i40e_adminq.o i40evf_client.o
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
index eeb9864bc5b1..c28cb8f27243 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
@@ -132,6 +132,10 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_list_func_capabilities	= 0x000A,
 	i40e_aqc_opc_list_dev_capabilities	= 0x000B,
 
+	/* Proxy commands */
+	i40e_aqc_opc_set_proxy_config		= 0x0104,
+	i40e_aqc_opc_set_ns_proxy_table_entry	= 0x0105,
+
 	/* LAA */
 	i40e_aqc_opc_mac_address_read	= 0x0107,
 	i40e_aqc_opc_mac_address_write	= 0x0108,
@@ -139,6 +143,10 @@ enum i40e_admin_queue_opc {
 	/* PXE */
 	i40e_aqc_opc_clear_pxe_mode	= 0x0110,
 
+	/* WoL commands */
+	i40e_aqc_opc_set_wol_filter	= 0x0120,
+	i40e_aqc_opc_get_wake_reason	= 0x0121,
+
 	/* internal switch commands */
 	i40e_aqc_opc_get_switch_config		= 0x0200,
 	i40e_aqc_opc_add_statistics		= 0x0201,
@@ -177,6 +185,7 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_remove_control_packet_filter	= 0x025B,
 	i40e_aqc_opc_add_cloud_filters		= 0x025C,
 	i40e_aqc_opc_remove_cloud_filters	= 0x025D,
+	i40e_aqc_opc_clear_wol_switch_filters	= 0x025E,
 
 	i40e_aqc_opc_add_mirror_rule	= 0x0260,
 	i40e_aqc_opc_delete_mirror_rule	= 0x0261,
@@ -558,6 +567,56 @@ struct i40e_aqc_clear_pxe {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe);
 
+/* Set WoL Filter (0x0120) */
+
+struct i40e_aqc_set_wol_filter {
+	__le16 filter_index;
+#define I40E_AQC_MAX_NUM_WOL_FILTERS	8
+#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT	15
+#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK	(0x1 << \
+		I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT)
+
+#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT		0
+#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK	(0x7 << \
+		I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT)
+	__le16 cmd_flags;
+#define I40E_AQC_SET_WOL_FILTER				0x8000
+#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL		0x4000
+#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR		0
+#define I40E_AQC_SET_WOL_FILTER_ACTION_SET		1
+	__le16 valid_flags;
+#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID		0x8000
+#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID	0x4000
+	u8 reserved[2];
+	__le32	address_high;
+	__le32	address_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter);
+
+struct i40e_aqc_set_wol_filter_data {
+	u8 filter[128];
+	u8 mask[16];
+};
+
+I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data);
+
+/* Get Wake Reason (0x0121) */
+
+struct i40e_aqc_get_wake_reason_completion {
+	u8 reserved_1[2];
+	__le16 wake_reason;
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT	0
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \
+		I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT)
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT	8
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK	(0xFF << \
+		I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT)
+	u8 reserved_2[12];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion);
+
 /* Switch configuration commands (0x02xx) */
 
 /* Used by many indirect commands that only pass an seid and a buffer in the
@@ -640,6 +699,8 @@ struct i40e_aqc_set_port_parameters {
 #define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS	2 /* must set! */
 #define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA	4
 	__le16	bad_frame_vsi;
+#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT	0x0
+#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK	0x3FF
 	__le16	default_seid;        /* reserved for command */
 	u8	reserved[10];
 };
@@ -691,6 +752,7 @@ I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp);
 /* Set Switch Configuration (direct 0x0205) */
 struct i40e_aqc_set_switch_config {
 	__le16	flags;
+/* flags used for both fields below */
 #define I40E_AQ_SET_SWITCH_CFG_PROMISC		0x0001
 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER	0x0002
 	__le16	valid_flags;
@@ -1839,11 +1901,12 @@ struct i40e_aqc_get_link_status {
 #define I40E_AQ_CONFIG_FEC_RS_ENA	0x02
 #define I40E_AQ_CONFIG_CRC_ENA		0x04
 #define I40E_AQ_CONFIG_PACING_MASK	0x78
-	u8	external_power_ability;
+	u8	power_desc;
 #define I40E_AQ_LINK_POWER_CLASS_1	0x00
 #define I40E_AQ_LINK_POWER_CLASS_2	0x01
 #define I40E_AQ_LINK_POWER_CLASS_3	0x02
 #define I40E_AQ_LINK_POWER_CLASS_4	0x03
+#define I40E_AQ_PWR_CLASS_MASK		0x03
 	u8	reserved[4];
 };
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c
index 89dfdbca13db..626fbf1ead4d 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c
@@ -958,7 +958,9 @@ u32 i40evf_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr)
 	int retry = 5;
 	u32 val = 0;
 
-	use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5);
+	use_register = (((hw->aq.api_maj_ver == 1) &&
+			(hw->aq.api_min_ver < 5)) ||
+			(hw->mac.type == I40E_MAC_X722));
 	if (!use_register) {
 do_retry:
 		status = i40evf_aq_rx_ctl_read_register(hw, reg_addr,
@@ -1019,7 +1021,9 @@ void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val)
 	bool use_register;
 	int retry = 5;
 
-	use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5);
+	use_register = (((hw->aq.api_maj_ver == 1) &&
+			(hw->aq.api_min_ver < 5)) ||
+			(hw->mac.type == I40E_MAC_X722));
 	if (!use_register) {
 do_retry:
 		status = i40evf_aq_rx_ctl_write_register(hw, reg_addr,
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index c91fcf43ccbc..95e383af41c4 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -137,10 +137,7 @@ u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw)
 {
 	u32 head, tail;
 
-	if (!in_sw)
-		head = i40e_get_head(ring);
-	else
-		head = ring->next_to_clean;
+	head = ring->next_to_clean;
 	tail = readl(ring->tail);
 
 	if (head != tail)
@@ -165,7 +162,6 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 {
 	u16 i = tx_ring->next_to_clean;
 	struct i40e_tx_buffer *tx_buf;
-	struct i40e_tx_desc *tx_head;
 	struct i40e_tx_desc *tx_desc;
 	unsigned int total_bytes = 0, total_packets = 0;
 	unsigned int budget = vsi->work_limit;
@@ -174,8 +170,6 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 	tx_desc = I40E_TX_DESC(tx_ring, i);
 	i -= tx_ring->count;
 
-	tx_head = I40E_TX_DESC(tx_ring, i40e_get_head(tx_ring));
-
 	do {
 		struct i40e_tx_desc *eop_desc = tx_buf->next_to_watch;
 
@@ -186,8 +180,9 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		/* prevent any other reads prior to eop_desc */
 		read_barrier_depends();
 
-		/* we have caught up to head, no work left to do */
-		if (tx_head == tx_desc)
+		/* if the descriptor isn't done, no work yet to do */
+		if (!(eop_desc->cmd_type_offset_bsz &
+		      cpu_to_le64(I40E_TX_DESC_DTYPE_DESC_DONE)))
 			break;
 
 		/* clear next_to_watch to prevent false hangs */
@@ -464,10 +459,6 @@ int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring)
 
 	/* round up to nearest 4K */
 	tx_ring->size = tx_ring->count * sizeof(struct i40e_tx_desc);
-	/* add u32 for head writeback, align after this takes care of
-	 * guaranteeing this is at least one cache line in size
-	 */
-	tx_ring->size += sizeof(u32);
 	tx_ring->size = ALIGN(tx_ring->size, 4096);
 	tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size,
 					   &tx_ring->dma, GFP_KERNEL);
@@ -493,7 +484,6 @@ err:
  **/
 void i40evf_clean_rx_ring(struct i40e_ring *rx_ring)
 {
-	struct device *dev = rx_ring->dev;
 	unsigned long bi_size;
 	u16 i;
 
@@ -513,8 +503,21 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring)
 		if (!rx_bi->page)
 			continue;
 
-		dma_unmap_page(dev, rx_bi->dma, PAGE_SIZE, DMA_FROM_DEVICE);
-		__free_pages(rx_bi->page, 0);
+		/* Invalidate cache lines that may have been written to by
+		 * device so that we avoid corrupting memory.
+		 */
+		dma_sync_single_range_for_cpu(rx_ring->dev,
+					      rx_bi->dma,
+					      rx_bi->page_offset,
+					      I40E_RXBUFFER_2048,
+					      DMA_FROM_DEVICE);
+
+		/* free resources associated with mapping */
+		dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma,
+				     PAGE_SIZE,
+				     DMA_FROM_DEVICE,
+				     I40E_RX_DMA_ATTR);
+		__page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias);
 
 		rx_bi->page = NULL;
 		rx_bi->page_offset = 0;
@@ -642,7 +645,10 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
 	}
 
 	/* map page for use */
-	dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	dma = dma_map_page_attrs(rx_ring->dev, page, 0,
+				 PAGE_SIZE,
+				 DMA_FROM_DEVICE,
+				 I40E_RX_DMA_ATTR);
 
 	/* if mapping failed free memory back to system since
 	 * there isn't much point in holding memory we can't use
@@ -657,6 +663,9 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
 	bi->page = page;
 	bi->page_offset = 0;
 
+	/* initialize pagecnt_bias to 1 representing we fully own page */
+	bi->pagecnt_bias = 1;
+
 	return true;
 }
 
@@ -702,6 +711,12 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
 		if (!i40e_alloc_mapped_page(rx_ring, bi))
 			goto no_buffers;
 
+		/* sync the buffer for use by the device */
+		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+						 bi->page_offset,
+						 I40E_RXBUFFER_2048,
+						 DMA_FROM_DEVICE);
+
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
@@ -742,8 +757,6 @@ no_buffers:
  * @vsi: the VSI we care about
  * @skb: skb currently being received and modified
  * @rx_desc: the receive descriptor
- *
- * skb->protocol must be set before this function is called
  **/
 static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 				    struct sk_buff *skb,
@@ -895,12 +908,12 @@ void i40evf_process_skb_fields(struct i40e_ring *rx_ring,
 {
 	i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
 
-	/* modifies the skb - consumes the enet header */
-	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
-
 	i40e_rx_checksum(rx_ring->vsi, skb, rx_desc);
 
 	skb_record_rx_queue(skb, rx_ring->queue_index);
+
+	/* modifies the skb - consumes the enet header */
+	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 }
 
 /**
@@ -945,7 +958,10 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring,
 	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
 
 	/* transfer page from old buffer to new buffer */
-	*new_buff = *old_buff;
+	new_buff->dma		= old_buff->dma;
+	new_buff->page		= old_buff->page;
+	new_buff->page_offset	= old_buff->page_offset;
+	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
 }
 
 /**
@@ -966,8 +982,6 @@ static inline bool i40e_page_is_reusable(struct page *page)
  * the adapter for another receive
  *
  * @rx_buffer: buffer containing the page
- * @page: page address from rx_buffer
- * @truesize: actual size of the buffer in this page
  *
  * If page is reusable, rx_buffer->page_offset is adjusted to point to
  * an unused region in the page.
@@ -990,13 +1004,13 @@ static inline bool i40e_page_is_reusable(struct page *page)
  *
  * In either case, if the page is reusable its refcount is increased.
  **/
-static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
-				   struct page *page,
-				   const unsigned int truesize)
+static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer)
 {
 #if (PAGE_SIZE >= 8192)
 	unsigned int last_offset = PAGE_SIZE - I40E_RXBUFFER_2048;
 #endif
+	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
+	struct page *page = rx_buffer->page;
 
 	/* Is any reuse possible? */
 	if (unlikely(!i40e_page_is_reusable(page)))
@@ -1004,21 +1018,21 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
 
 #if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
-	if (unlikely(page_count(page) != 1))
+	if (unlikely((page_count(page) - pagecnt_bias) > 1))
 		return false;
-
-	/* flip page offset to other buffer */
-	rx_buffer->page_offset ^= truesize;
 #else
-	/* move offset up to the next cache line */
-	rx_buffer->page_offset += truesize;
-
 	if (rx_buffer->page_offset > last_offset)
 		return false;
 #endif
 
-	/* Inc ref count on page before passing it up to the stack */
-	get_page(page);
+	/* If we have drained the page fragment pool we need to update
+	 * the pagecnt_bias and page count so that we fully restock the
+	 * number of references the driver holds.
+	 */
+	if (unlikely(!pagecnt_bias)) {
+		page_ref_add(page, USHRT_MAX);
+		rx_buffer->pagecnt_bias = USHRT_MAX;
+	}
 
 	return true;
 }
@@ -1027,145 +1041,155 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
  * i40e_add_rx_frag - Add contents of Rx buffer to sk_buff
  * @rx_ring: rx descriptor ring to transact packets on
  * @rx_buffer: buffer containing page to add
- * @size: packet length from rx_desc
  * @skb: sk_buff to place the data into
+ * @size: packet length from rx_desc
  *
  * This function will add the data contained in rx_buffer->page to the skb.
- * This is done either through a direct copy if the data in the buffer is
- * less than the skb header size, otherwise it will just attach the page as
- * a frag to the skb.
+ * It will just attach the page as a frag to the skb.
  *
- * The function will then update the page offset if necessary and return
- * true if the buffer can be reused by the adapter.
+ * The function will then update the page offset.
  **/
-static bool i40e_add_rx_frag(struct i40e_ring *rx_ring,
+static void i40e_add_rx_frag(struct i40e_ring *rx_ring,
 			     struct i40e_rx_buffer *rx_buffer,
-			     unsigned int size,
-			     struct sk_buff *skb)
+			     struct sk_buff *skb,
+			     unsigned int size)
 {
-	struct page *page = rx_buffer->page;
-	unsigned char *va = page_address(page) + rx_buffer->page_offset;
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = I40E_RXBUFFER_2048;
 #else
-	unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
+	unsigned int truesize = SKB_DATA_ALIGN(size);
 #endif
-	unsigned int pull_len;
-
-	if (unlikely(skb_is_nonlinear(skb)))
-		goto add_tail_frag;
 
-	/* will the data fit in the skb we allocated? if so, just
-	 * copy it as it is pretty small anyway
-	 */
-	if (size <= I40E_RX_HDR_SIZE) {
-		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
+			rx_buffer->page_offset, size, truesize);
 
-		/* page is reusable, we can reuse buffer as-is */
-		if (likely(i40e_page_is_reusable(page)))
-			return true;
-
-		/* this page cannot be reused so discard it */
-		__free_pages(page, 0);
-		return false;
-	}
+	/* page is being used so we must update the page offset */
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
+}
 
-	/* we need the header to contain the greater of either
-	 * ETH_HLEN or 60 bytes if the skb->len is less than
-	 * 60 for skb_pad.
-	 */
-	pull_len = eth_get_headlen(va, I40E_RX_HDR_SIZE);
+/**
+ * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @size: size of buffer to add to skb
+ *
+ * This function will pull an Rx buffer from the ring and synchronize it
+ * for use by the CPU.
+ */
+static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
+						 const unsigned int size)
+{
+	struct i40e_rx_buffer *rx_buffer;
 
-	/* align pull length to size of long to optimize
-	 * memcpy performance
-	 */
-	memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
+	rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
+	prefetchw(rx_buffer->page);
 
-	/* update all of the pointers */
-	va += pull_len;
-	size -= pull_len;
+	/* we are reusing so sync this buffer for CPU use */
+	dma_sync_single_range_for_cpu(rx_ring->dev,
+				      rx_buffer->dma,
+				      rx_buffer->page_offset,
+				      size,
+				      DMA_FROM_DEVICE);
 
-add_tail_frag:
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
-			(unsigned long)va & ~PAGE_MASK, size, truesize);
+	/* We have pulled a buffer for use, so decrement pagecnt_bias */
+	rx_buffer->pagecnt_bias--;
 
-	return i40e_can_reuse_rx_page(rx_buffer, page, truesize);
+	return rx_buffer;
 }
 
 /**
- * i40evf_fetch_rx_buffer - Allocate skb and populate it
+ * i40e_construct_skb - Allocate skb and populate it
  * @rx_ring: rx descriptor ring to transact packets on
- * @rx_desc: descriptor containing info written by hardware
+ * @rx_buffer: rx buffer to pull data from
+ * @size: size of buffer to add to skb
  *
- * This function allocates an skb on the fly, and populates it with the page
- * data from the current receive descriptor, taking care to set up the skb
- * correctly, as well as handling calling the page recycle function if
- * necessary.
+ * This function allocates an skb.  It then populates it with the page
+ * data from the current receive descriptor, taking care to set up the
+ * skb correctly.
  */
-static inline
-struct sk_buff *i40evf_fetch_rx_buffer(struct i40e_ring *rx_ring,
-				       union i40e_rx_desc *rx_desc,
-				       struct sk_buff *skb)
+static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
+					  struct i40e_rx_buffer *rx_buffer,
+					  unsigned int size)
 {
-	u64 local_status_error_len =
-		le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-	unsigned int size =
-		(local_status_error_len & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
-		I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
-	struct i40e_rx_buffer *rx_buffer;
-	struct page *page;
-
-	rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
-	page = rx_buffer->page;
-	prefetchw(page);
-
-	if (likely(!skb)) {
-		void *page_addr = page_address(page) + rx_buffer->page_offset;
+	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = I40E_RXBUFFER_2048;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(size);
+#endif
+	unsigned int headlen;
+	struct sk_buff *skb;
 
-		/* prefetch first cache line of first page */
-		prefetch(page_addr);
+	/* prefetch first cache line of first page */
+	prefetch(va);
 #if L1_CACHE_BYTES < 128
-		prefetch(page_addr + L1_CACHE_BYTES);
+	prefetch(va + L1_CACHE_BYTES);
 #endif
 
-		/* allocate a skb to store the frags */
-		skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
-				       I40E_RX_HDR_SIZE,
-				       GFP_ATOMIC | __GFP_NOWARN);
-		if (unlikely(!skb)) {
-			rx_ring->rx_stats.alloc_buff_failed++;
-			return NULL;
-		}
+	/* allocate a skb to store the frags */
+	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
+			       I40E_RX_HDR_SIZE,
+			       GFP_ATOMIC | __GFP_NOWARN);
+	if (unlikely(!skb))
+		return NULL;
 
-		/* we will be copying header into skb->data in
-		 * pskb_may_pull so it is in our interest to prefetch
-		 * it now to avoid a possible cache miss
-		 */
-		prefetchw(skb->data);
+	/* Determine available headroom for copy */
+	headlen = size;
+	if (headlen > I40E_RX_HDR_SIZE)
+		headlen = eth_get_headlen(va, I40E_RX_HDR_SIZE);
+
+	/* align pull length to size of long to optimize memcpy performance */
+	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
+
+	/* update all of the pointers */
+	size -= headlen;
+	if (size) {
+		skb_add_rx_frag(skb, 0, rx_buffer->page,
+				rx_buffer->page_offset + headlen,
+				size, truesize);
+
+		/* buffer is used by skb, update page_offset */
+#if (PAGE_SIZE < 8192)
+		rx_buffer->page_offset ^= truesize;
+#else
+		rx_buffer->page_offset += truesize;
+#endif
+	} else {
+		/* buffer is unused, reset bias back to rx_buffer */
+		rx_buffer->pagecnt_bias++;
 	}
 
-	/* we are reusing so sync this buffer for CPU use */
-	dma_sync_single_range_for_cpu(rx_ring->dev,
-				      rx_buffer->dma,
-				      rx_buffer->page_offset,
-				      size,
-				      DMA_FROM_DEVICE);
+	return skb;
+}
 
-	/* pull page into skb */
-	if (i40e_add_rx_frag(rx_ring, rx_buffer, size, skb)) {
+/**
+ * i40e_put_rx_buffer - Clean up used buffer and either recycle or free
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_buffer: rx buffer to pull data from
+ *
+ * This function will clean up the contents of the rx_buffer.  It will
+ * either recycle the bufer or unmap it and free the associated resources.
+ */
+static void i40e_put_rx_buffer(struct i40e_ring *rx_ring,
+			       struct i40e_rx_buffer *rx_buffer)
+{
+	if (i40e_can_reuse_rx_page(rx_buffer)) {
 		/* hand second half of page back to the ring */
 		i40e_reuse_rx_page(rx_ring, rx_buffer);
 		rx_ring->rx_stats.page_reuse_count++;
 	} else {
 		/* we are not reusing the buffer so unmap it */
-		dma_unmap_page(rx_ring->dev, rx_buffer->dma, PAGE_SIZE,
-			       DMA_FROM_DEVICE);
+		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, PAGE_SIZE,
+				     DMA_FROM_DEVICE, I40E_RX_DMA_ATTR);
+		__page_frag_cache_drain(rx_buffer->page,
+					rx_buffer->pagecnt_bias);
 	}
 
 	/* clear contents of buffer_info */
 	rx_buffer->page = NULL;
-
-	return skb;
 }
 
 /**
@@ -1221,7 +1245,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	bool failure = false;
 
 	while (likely(total_rx_packets < budget)) {
+		struct i40e_rx_buffer *rx_buffer;
 		union i40e_rx_desc *rx_desc;
+		unsigned int size;
 		u16 vlan_tag;
 		u8 rx_ptype;
 		u64 qword;
@@ -1238,22 +1264,36 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		/* status_error_len will always be zero for unused descriptors
 		 * because it's cleared in cleanup, and overlaps with hdr_addr
 		 * which is always zero because packet split isn't used, if the
-		 * hardware wrote DD then it will be non-zero
+		 * hardware wrote DD then the length will be non-zero
 		 */
-		if (!i40e_test_staterr(rx_desc,
-				       BIT(I40E_RX_DESC_STATUS_DD_SHIFT)))
+		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+		size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
+		       I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
+		if (!size)
 			break;
 
 		/* This memory barrier is needed to keep us from reading
-		 * any other fields out of the rx_desc until we know the
-		 * DD bit is set.
+		 * any other fields out of the rx_desc until we have
+		 * verified the descriptor has been written back.
 		 */
 		dma_rmb();
 
-		skb = i40evf_fetch_rx_buffer(rx_ring, rx_desc, skb);
-		if (!skb)
+		rx_buffer = i40e_get_rx_buffer(rx_ring, size);
+
+		/* retrieve a buffer from the ring */
+		if (skb)
+			i40e_add_rx_frag(rx_ring, rx_buffer, skb, size);
+		else
+			skb = i40e_construct_skb(rx_ring, rx_buffer, size);
+
+		/* exit if we failed to retrieve a buffer */
+		if (!skb) {
+			rx_ring->rx_stats.alloc_buff_failed++;
+			rx_buffer->pagecnt_bias++;
 			break;
+		}
 
+		i40e_put_rx_buffer(rx_ring, rx_buffer);
 		cleaned_count++;
 
 		if (i40e_is_non_eop(rx_ring, rx_desc, skb))
@@ -1266,6 +1306,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		 */
 		if (unlikely(i40e_test_staterr(rx_desc, BIT(I40E_RXD_QW1_ERROR_SHIFT)))) {
 			dev_kfree_skb_any(skb);
+			skb = NULL;
 			continue;
 		}
 
@@ -1980,7 +2021,6 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	u16 i = tx_ring->next_to_use;
 	u32 td_tag = 0;
 	dma_addr_t dma;
-	u16 desc_count = 1;
 
 	if (tx_flags & I40E_TX_FLAGS_HW_VLAN) {
 		td_cmd |= I40E_TX_DESC_CMD_IL2TAG1;
@@ -2016,7 +2056,6 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 			tx_desc++;
 			i++;
-			desc_count++;
 
 			if (i == tx_ring->count) {
 				tx_desc = I40E_TX_DESC(tx_ring, 0);
@@ -2038,7 +2077,6 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 		tx_desc++;
 		i++;
-		desc_count++;
 
 		if (i == tx_ring->count) {
 			tx_desc = I40E_TX_DESC(tx_ring, 0);
@@ -2064,46 +2102,8 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 	i40e_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
-	/* write last descriptor with EOP bit */
-	td_cmd |= I40E_TX_DESC_CMD_EOP;
-
-	/* We can OR these values together as they both are checked against
-	 * 4 below and at this point desc_count will be used as a boolean value
-	 * after this if/else block.
-	 */
-	desc_count |= ++tx_ring->packet_stride;
-
-	/* Algorithm to optimize tail and RS bit setting:
-	 * if queue is stopped
-	 *	mark RS bit
-	 *	reset packet counter
-	 * else if xmit_more is supported and is true
-	 *	advance packet counter to 4
-	 *	reset desc_count to 0
-	 *
-	 * if desc_count >= 4
-	 *	mark RS bit
-	 *	reset packet counter
-	 * if desc_count > 0
-	 *	update tail
-	 *
-	 * Note: If there are less than 4 descriptors
-	 * pending and interrupts were disabled the service task will
-	 * trigger a force WB.
-	 */
-	if (netif_xmit_stopped(txring_txq(tx_ring))) {
-		goto do_rs;
-	} else if (skb->xmit_more) {
-		/* set stride to arm on next packet and reset desc_count */
-		tx_ring->packet_stride = WB_STRIDE;
-		desc_count = 0;
-	} else if (desc_count >= WB_STRIDE) {
-do_rs:
-		/* write last descriptor with RS bit set */
-		td_cmd |= I40E_TX_DESC_CMD_RS;
-		tx_ring->packet_stride = 0;
-	}
-
+	/* write last descriptor with RS and EOP bits */
+	td_cmd |= I40E_TXD_CMD;
 	tx_desc->cmd_type_offset_bsz =
 			build_ctob(td_cmd, td_offset, size, td_tag);
 
@@ -2119,7 +2119,7 @@ do_rs:
 	first->next_to_watch = tx_desc;
 
 	/* notify HW of packet */
-	if (desc_count) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index 8274ba68bd32..3bb4d732e467 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -104,10 +104,8 @@ enum i40e_dyn_idx_t {
 
 /* Supported Rx Buffer Sizes (a multiple of 128) */
 #define I40E_RXBUFFER_256   256
+#define I40E_RXBUFFER_1536  1536  /* 128B aligned standard Ethernet frame */
 #define I40E_RXBUFFER_2048  2048
-#define I40E_RXBUFFER_3072  3072   /* For FCoE MTU of 2158 */
-#define I40E_RXBUFFER_4096  4096
-#define I40E_RXBUFFER_8192  8192
 #define I40E_MAX_RXBUFFER   9728  /* largest size for single descriptor */
 
 /* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we
@@ -120,6 +118,9 @@ enum i40e_dyn_idx_t {
 #define I40E_RX_HDR_SIZE I40E_RXBUFFER_256
 #define i40e_rx_desc i40e_32byte_rx_desc
 
+#define I40E_RX_DMA_ATTR \
+	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
 /**
  * i40e_test_staterr - tests bits in Rx descriptor status and error fields
  * @rx_desc: pointer to receive descriptor (in le64 format)
@@ -241,7 +242,12 @@ struct i40e_tx_buffer {
 struct i40e_rx_buffer {
 	dma_addr_t dma;
 	struct page *page;
-	unsigned int page_offset;
+#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
+	__u32 page_offset;
+#else
+	__u16 page_offset;
+#endif
+	__u16 pagecnt_bias;
 };
 
 struct i40e_queue_stats {
@@ -385,20 +391,6 @@ int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
 bool __i40evf_chk_linearize(struct sk_buff *skb);
 
 /**
- * i40e_get_head - Retrieve head from head writeback
- * @tx_ring: Tx ring to fetch head of
- *
- * Returns value of Tx ring head based on value stored
- * in head write-back location
- **/
-static inline u32 i40e_get_head(struct i40e_ring *tx_ring)
-{
-	void *head = (struct i40e_tx_desc *)tx_ring->desc + tx_ring->count;
-
-	return le32_to_cpu(*(volatile __le32 *)head);
-}
-
-/**
  * i40e_xmit_descriptor_count - calculate number of Tx descriptors needed
  * @skb:     send buffer
  * @tx_ring: ring to send buffer on
@@ -460,19 +452,7 @@ static inline bool i40e_chk_linearize(struct sk_buff *skb, int count)
 	/* we can support up to 8 data buffers for a single send */
 	return count != I40E_MAX_BUFFER_TXD;
 }
-
-/**
- * i40e_rx_is_fcoe - returns true if the Rx packet type is FCoE
- * @ptype: the packet type field from Rx descriptor write-back
- **/
-static inline bool i40e_rx_is_fcoe(u16 ptype)
-{
-	return (ptype >= I40E_RX_PTYPE_L2_FCOE_PAY3) &&
-	       (ptype <= I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER);
-}
-
 /**
- * txring_txq - Find the netdev Tx ring based on the i40e Tx ring
  * @ring: Tx ring to find the netdev equivalent of
  **/
 static inline struct netdev_queue *txring_txq(const struct i40e_ring *ring)
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h
index d38a2b2aea2b..f431fbc4a3e7 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h
@@ -81,7 +81,9 @@ enum i40e_virtchnl_ops {
 	I40E_VIRTCHNL_OP_GET_STATS = 15,
 	I40E_VIRTCHNL_OP_FCOE = 16,
 	I40E_VIRTCHNL_OP_EVENT = 17, /* must ALWAYS be 17 */
+	I40E_VIRTCHNL_OP_IWARP = 20,
 	I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP = 21,
+	I40E_VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP = 22,
 	I40E_VIRTCHNL_OP_CONFIG_RSS_KEY = 23,
 	I40E_VIRTCHNL_OP_CONFIG_RSS_LUT = 24,
 	I40E_VIRTCHNL_OP_GET_RSS_HENA_CAPS = 25,
@@ -393,6 +395,37 @@ struct i40e_virtchnl_pf_event {
 	int severity;
 };
 
+/* I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP
+ * VF uses this message to request PF to map IWARP vectors to IWARP queues.
+ * The request for this originates from the VF IWARP driver through
+ * a client interface between VF LAN and VF IWARP driver.
+ * A vector could have an AEQ and CEQ attached to it although
+ * there is a single AEQ per VF IWARP instance in which case
+ * most vectors will have an INVALID_IDX for aeq and valid idx for ceq.
+ * There will never be a case where there will be multiple CEQs attached
+ * to a single vector.
+ * PF configures interrupt mapping and returns status.
+ */
+
+/* HW does not define a type value for AEQ; only for RX/TX and CEQ.
+ * In order for us to keep the interface simple, SW will define a
+ * unique type value for AEQ.
+ */
+#define I40E_QUEUE_TYPE_PE_AEQ  0x80
+#define I40E_QUEUE_INVALID_IDX  0xFFFF
+
+struct i40e_virtchnl_iwarp_qv_info {
+	u32 v_idx; /* msix_vector */
+	u16 ceq_idx;
+	u16 aeq_idx;
+	u8 itr_idx;
+};
+
+struct i40e_virtchnl_iwarp_qvlist_info {
+	u32 num_vectors;
+	struct i40e_virtchnl_iwarp_qv_info qv_info[1];
+};
+
 /* VF reset states - these are written into the RSTAT register:
  * I40E_VFGEN_RSTAT1 on the PF
  * I40E_VFGEN_RSTAT on the VF
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h
index 00c42d803276..d61ecf655091 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf.h
+++ b/drivers/net/ethernet/intel/i40evf/i40evf.h
@@ -60,6 +60,7 @@ struct i40e_vsi {
 	int base_vector;
 	u16 work_limit;
 	u16 qs_handle;
+	void *priv;     /* client driver data reference. */
 };
 
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
@@ -71,10 +72,6 @@ struct i40e_vsi {
 #define I40EVF_MAX_RXD		4096
 #define I40EVF_MIN_RXD		64
 #define I40EVF_REQ_DESCRIPTOR_MULTIPLE	32
-
-/* Supported Rx Buffer Sizes */
-#define I40EVF_RXBUFFER_2048	2048
-#define I40EVF_MAX_RXBUFFER	16384  /* largest size for single descriptor */
 #define I40EVF_MAX_AQ_BUF_SIZE	4096
 #define I40EVF_AQ_LEN		32
 #define I40EVF_AQ_MAX_ERR	20 /* times to try before resetting AQ */
@@ -169,6 +166,7 @@ enum i40evf_state_t {
 
 enum i40evf_critical_section_t {
 	__I40EVF_IN_CRITICAL_TASK,	/* cannot be interrupted */
+	__I40EVF_IN_CLIENT_TASK,
 };
 /* make common code happy */
 #define __I40E_DOWN __I40EVF_DOWN
@@ -178,6 +176,7 @@ struct i40evf_adapter {
 	struct timer_list watchdog_timer;
 	struct work_struct reset_task;
 	struct work_struct adminq_task;
+	struct delayed_work client_task;
 	struct delayed_work init_task;
 	struct i40e_q_vector *q_vectors;
 	struct list_head vlan_filter_list;
@@ -195,7 +194,10 @@ struct i40evf_adapter {
 	u64 hw_csum_rx_error;
 	u32 rx_desc_count;
 	int num_msix_vectors;
+	int num_iwarp_msix;
+	int iwarp_base_vector;
 	u32 client_pending;
+	struct i40e_client_instance *cinst;
 	struct msix_entry *msix_entries;
 
 	u32 flags;
@@ -211,8 +213,12 @@ struct i40evf_adapter {
 #define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE	BIT(12)
 #define I40EVF_FLAG_ADDR_SET_BY_PF		BIT(13)
 #define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED	BIT(14)
-#define I40EVF_FLAG_PROMISC_ON			BIT(15)
-#define I40EVF_FLAG_ALLMULTI_ON			BIT(16)
+#define I40EVF_FLAG_CLIENT_NEEDS_OPEN		BIT(15)
+#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE		BIT(16)
+#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS	BIT(17)
+#define I40EVF_FLAG_PROMISC_ON			BIT(18)
+#define I40EVF_FLAG_ALLMULTI_ON			BIT(19)
+#define I40EVF_FLAG_LEGACY_RX			BIT(20)
 /* duplicates for common code */
 #define I40E_FLAG_FDIR_ATR_ENABLED		0
 #define I40E_FLAG_DCB_ENABLED			0
@@ -220,6 +226,7 @@ struct i40evf_adapter {
 #define I40E_FLAG_RX_CSUM_ENABLED		I40EVF_FLAG_RX_CSUM_ENABLED
 #define I40E_FLAG_WB_ON_ITR_CAPABLE		I40EVF_FLAG_WB_ON_ITR_CAPABLE
 #define I40E_FLAG_OUTER_UDP_CSUM_CAPABLE	I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE
+#define I40E_FLAG_LEGACY_RX			I40EVF_FLAG_LEGACY_RX
 	/* flags for admin queue service task */
 	u32 aq_required;
 #define I40EVF_FLAG_AQ_ENABLE_QUEUES		BIT(0)
@@ -258,10 +265,11 @@ struct i40evf_adapter {
 	bool link_up;
 	enum i40e_aq_link_speed link_speed;
 	enum i40e_virtchnl_ops current_op;
-#define CLIENT_ENABLED(_a) ((_a)->vf_res ? \
+#define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \
 			    (_a)->vf_res->vf_offload_flags & \
 				I40E_VIRTCHNL_VF_OFFLOAD_IWARP : \
 			    0)
+#define CLIENT_ENABLED(_a) ((_a)->cinst)
 /* RSS by the PF should be preferred over RSS via other methods. */
 #define RSS_PF(_a) ((_a)->vf_res->vf_offload_flags & \
 		    I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF)
@@ -292,6 +300,12 @@ struct i40evf_adapter {
 
 /* Ethtool Private Flags */
 
+/* lan device */
+struct i40e_device {
+	struct list_head list;
+	struct i40evf_adapter *vf;
+};
+
 /* needed by i40evf_ethtool.c */
 extern char i40evf_driver_name[];
 extern const char i40evf_driver_version[];
@@ -337,4 +351,11 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 				enum i40e_virtchnl_ops v_opcode,
 				i40e_status v_retval, u8 *msg, u16 msglen);
 int i40evf_config_rss(struct i40evf_adapter *adapter);
+int i40evf_lan_add_device(struct i40evf_adapter *adapter);
+int i40evf_lan_del_device(struct i40evf_adapter *adapter);
+void i40evf_client_subtask(struct i40evf_adapter *adapter);
+void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len);
+void i40evf_notify_client_l2_params(struct i40e_vsi *vsi);
+void i40evf_notify_client_open(struct i40e_vsi *vsi);
+void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset);
 #endif /* _I40EVF_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.c b/drivers/net/ethernet/intel/i40evf/i40evf_client.c
new file mode 100644
index 000000000000..ee737680a0e9
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_client.c
@@ -0,0 +1,564 @@
+#include <linux/list.h>
+#include <linux/errno.h>
+
+#include "i40evf.h"
+#include "i40e_prototype.h"
+#include "i40evf_client.h"
+
+static
+const char i40evf_client_interface_version_str[] = I40EVF_CLIENT_VERSION_STR;
+static struct i40e_client *vf_registered_client;
+static LIST_HEAD(i40evf_devices);
+static DEFINE_MUTEX(i40evf_device_mutex);
+
+static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev,
+				       struct i40e_client *client,
+				       u8 *msg, u16 len);
+
+static int i40evf_client_setup_qvlist(struct i40e_info *ldev,
+				      struct i40e_client *client,
+				      struct i40e_qvlist_info *qvlist_info);
+
+static struct i40e_ops i40evf_lan_ops = {
+	.virtchnl_send = i40evf_client_virtchnl_send,
+	.setup_qvlist = i40evf_client_setup_qvlist,
+};
+
+/**
+ * i40evf_notify_client_message - call the client message receive callback
+ * @vsi: the VSI associated with this client
+ * @msg: message buffer
+ * @len: length of message
+ *
+ * If there is a client to this VSI, call the client
+ **/
+void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len)
+{
+	struct i40e_client_instance *cinst;
+
+	if (!vsi)
+		return;
+
+	cinst = vsi->back->cinst;
+	if (!cinst || !cinst->client || !cinst->client->ops ||
+	    !cinst->client->ops->virtchnl_receive) {
+		dev_dbg(&vsi->back->pdev->dev,
+			"Cannot locate client instance virtchnl_receive function\n");
+		return;
+	}
+	cinst->client->ops->virtchnl_receive(&cinst->lan_info,  cinst->client,
+					     msg, len);
+}
+
+/**
+ * i40evf_notify_client_l2_params - call the client notify callback
+ * @vsi: the VSI with l2 param changes
+ *
+ * If there is a client to this VSI, call the client
+ **/
+void i40evf_notify_client_l2_params(struct i40e_vsi *vsi)
+{
+	struct i40e_client_instance *cinst;
+	struct i40e_params params;
+
+	if (!vsi)
+		return;
+
+	cinst = vsi->back->cinst;
+	memset(&params, 0, sizeof(params));
+	params.mtu = vsi->netdev->mtu;
+	params.link_up = vsi->back->link_up;
+	params.qos.prio_qos[0].qs_handle = vsi->qs_handle;
+
+	if (!cinst || !cinst->client || !cinst->client->ops ||
+	    !cinst->client->ops->l2_param_change) {
+		dev_dbg(&vsi->back->pdev->dev,
+			"Cannot locate client instance l2_param_change function\n");
+		return;
+	}
+	cinst->client->ops->l2_param_change(&cinst->lan_info, cinst->client,
+					    &params);
+}
+
+/**
+ * i40evf_notify_client_open - call the client open callback
+ * @vsi: the VSI with netdev opened
+ *
+ * If there is a client to this netdev, call the client with open
+ **/
+void i40evf_notify_client_open(struct i40e_vsi *vsi)
+{
+	struct i40evf_adapter *adapter = vsi->back;
+	struct i40e_client_instance *cinst = adapter->cinst;
+	int ret;
+
+	if (!cinst || !cinst->client || !cinst->client->ops ||
+	    !cinst->client->ops->open) {
+		dev_dbg(&vsi->back->pdev->dev,
+			"Cannot locate client instance open function\n");
+		return;
+	}
+	if (!(test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state))) {
+		ret = cinst->client->ops->open(&cinst->lan_info, cinst->client);
+		if (!ret)
+			set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state);
+	}
+}
+
+/**
+ * i40evf_client_release_qvlist - send a message to the PF to release iwarp qv map
+ * @ldev: pointer to L2 context.
+ *
+ * Return 0 on success or < 0 on error
+ **/
+static int i40evf_client_release_qvlist(struct i40e_info *ldev)
+{
+	struct i40evf_adapter *adapter = ldev->vf;
+	i40e_status err;
+
+	if (adapter->aq_required)
+		return -EAGAIN;
+
+	err = i40e_aq_send_msg_to_pf(&adapter->hw,
+			I40E_VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP,
+			I40E_SUCCESS, NULL, 0, NULL);
+
+	if (err)
+		dev_err(&adapter->pdev->dev,
+			"Unable to send iWarp vector release message to PF, error %d, aq status %d\n",
+			err, adapter->hw.aq.asq_last_status);
+
+	return err;
+}
+
+/**
+ * i40evf_notify_client_close - call the client close callback
+ * @vsi: the VSI with netdev closed
+ * @reset: true when close called due to reset pending
+ *
+ * If there is a client to this netdev, call the client with close
+ **/
+void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset)
+{
+	struct i40evf_adapter *adapter = vsi->back;
+	struct i40e_client_instance *cinst = adapter->cinst;
+
+	if (!cinst || !cinst->client || !cinst->client->ops ||
+	    !cinst->client->ops->close) {
+		dev_dbg(&vsi->back->pdev->dev,
+			"Cannot locate client instance close function\n");
+		return;
+	}
+	cinst->client->ops->close(&cinst->lan_info, cinst->client, reset);
+	i40evf_client_release_qvlist(&cinst->lan_info);
+	clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state);
+}
+
+/**
+ * i40evf_client_add_instance - add a client instance to the instance list
+ * @adapter: pointer to the board struct
+ * @client: pointer to a client struct in the client list.
+ *
+ * Returns cinst ptr on success, NULL on failure
+ **/
+static struct i40e_client_instance *
+i40evf_client_add_instance(struct i40evf_adapter *adapter)
+{
+	struct i40e_client_instance *cinst = NULL;
+	struct netdev_hw_addr *mac = NULL;
+	struct i40e_vsi *vsi = &adapter->vsi;
+	int i;
+
+	if (!vf_registered_client)
+		goto out;
+
+	if (adapter->cinst) {
+		cinst = adapter->cinst;
+		goto out;
+	}
+
+	cinst = kzalloc(sizeof(*cinst), GFP_KERNEL);
+	if (!cinst)
+		goto out;
+
+	cinst->lan_info.vf = (void *)adapter;
+	cinst->lan_info.netdev = vsi->netdev;
+	cinst->lan_info.pcidev = adapter->pdev;
+	cinst->lan_info.fid = 0;
+	cinst->lan_info.ftype = I40E_CLIENT_FTYPE_VF;
+	cinst->lan_info.hw_addr = adapter->hw.hw_addr;
+	cinst->lan_info.ops = &i40evf_lan_ops;
+	cinst->lan_info.version.major = I40EVF_CLIENT_VERSION_MAJOR;
+	cinst->lan_info.version.minor = I40EVF_CLIENT_VERSION_MINOR;
+	cinst->lan_info.version.build = I40EVF_CLIENT_VERSION_BUILD;
+	set_bit(__I40E_CLIENT_INSTANCE_NONE, &cinst->state);
+
+	cinst->lan_info.msix_count = adapter->num_iwarp_msix;
+	cinst->lan_info.msix_entries =
+			&adapter->msix_entries[adapter->iwarp_base_vector];
+
+	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
+		cinst->lan_info.params.qos.prio_qos[i].tc = 0;
+		cinst->lan_info.params.qos.prio_qos[i].qs_handle =
+								vsi->qs_handle;
+	}
+
+	mac = list_first_entry(&cinst->lan_info.netdev->dev_addrs.list,
+			       struct netdev_hw_addr, list);
+	if (mac)
+		ether_addr_copy(cinst->lan_info.lanmac, mac->addr);
+	else
+		dev_err(&adapter->pdev->dev, "MAC address list is empty!\n");
+
+	cinst->client = vf_registered_client;
+	adapter->cinst = cinst;
+out:
+	return cinst;
+}
+
+/**
+ * i40evf_client_del_instance - removes a client instance from the list
+ * @adapter: pointer to the board struct
+ * @client: pointer to the client struct
+ *
+ **/
+static
+void i40evf_client_del_instance(struct i40evf_adapter *adapter)
+{
+	kfree(adapter->cinst);
+	adapter->cinst = NULL;
+}
+
+/**
+ * i40evf_client_subtask - client maintenance work
+ * @adapter: board private structure
+ **/
+void i40evf_client_subtask(struct i40evf_adapter *adapter)
+{
+	struct i40e_client *client = vf_registered_client;
+	struct i40e_client_instance *cinst;
+	int ret = 0;
+
+	if (adapter->state < __I40EVF_DOWN)
+		return;
+
+	/* first check client is registered */
+	if (!client)
+		return;
+
+	/* Add the client instance to the instance list */
+	cinst = i40evf_client_add_instance(adapter);
+	if (!cinst)
+		return;
+
+	dev_info(&adapter->pdev->dev, "Added instance of Client %s\n",
+		 client->name);
+
+	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) {
+		/* Send an Open request to the client */
+
+		if (client->ops && client->ops->open)
+			ret = client->ops->open(&cinst->lan_info, client);
+		if (!ret)
+			set_bit(__I40E_CLIENT_INSTANCE_OPENED,
+				&cinst->state);
+		else
+			/* remove client instance */
+			i40evf_client_del_instance(adapter);
+	}
+}
+
+/**
+ * i40evf_lan_add_device - add a lan device struct to the list of lan devices
+ * @adapter: pointer to the board struct
+ *
+ * Returns 0 on success or none 0 on error
+ **/
+int i40evf_lan_add_device(struct i40evf_adapter *adapter)
+{
+	struct i40e_device *ldev;
+	int ret = 0;
+
+	mutex_lock(&i40evf_device_mutex);
+	list_for_each_entry(ldev, &i40evf_devices, list) {
+		if (ldev->vf == adapter) {
+			ret = -EEXIST;
+			goto out;
+		}
+	}
+	ldev = kzalloc(sizeof(*ldev), GFP_KERNEL);
+	if (!ldev) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	ldev->vf = adapter;
+	INIT_LIST_HEAD(&ldev->list);
+	list_add(&ldev->list, &i40evf_devices);
+	dev_info(&adapter->pdev->dev, "Added LAN device bus=0x%02x dev=0x%02x func=0x%02x\n",
+		 adapter->hw.bus.bus_id, adapter->hw.bus.device,
+		 adapter->hw.bus.func);
+
+	/* Since in some cases register may have happened before a device gets
+	 * added, we can schedule a subtask to go initiate the clients.
+	 */
+	adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
+
+out:
+	mutex_unlock(&i40evf_device_mutex);
+	return ret;
+}
+
+/**
+ * i40evf_lan_del_device - removes a lan device from the device list
+ * @adapter: pointer to the board struct
+ *
+ * Returns 0 on success or non-0 on error
+ **/
+int i40evf_lan_del_device(struct i40evf_adapter *adapter)
+{
+	struct i40e_device *ldev, *tmp;
+	int ret = -ENODEV;
+
+	mutex_lock(&i40evf_device_mutex);
+	list_for_each_entry_safe(ldev, tmp, &i40evf_devices, list) {
+		if (ldev->vf == adapter) {
+			dev_info(&adapter->pdev->dev,
+				 "Deleted LAN device bus=0x%02x dev=0x%02x func=0x%02x\n",
+				 adapter->hw.bus.bus_id, adapter->hw.bus.device,
+				 adapter->hw.bus.func);
+			list_del(&ldev->list);
+			kfree(ldev);
+			ret = 0;
+			break;
+		}
+	}
+
+	mutex_unlock(&i40evf_device_mutex);
+	return ret;
+}
+
+/**
+ * i40evf_client_release - release client specific resources
+ * @client: pointer to the registered client
+ *
+ **/
+static void i40evf_client_release(struct i40e_client *client)
+{
+	struct i40e_client_instance *cinst;
+	struct i40e_device *ldev;
+	struct i40evf_adapter *adapter;
+
+	mutex_lock(&i40evf_device_mutex);
+	list_for_each_entry(ldev, &i40evf_devices, list) {
+		adapter = ldev->vf;
+		cinst = adapter->cinst;
+		if (!cinst)
+			continue;
+		if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) {
+			if (client->ops && client->ops->close)
+				client->ops->close(&cinst->lan_info, client,
+						   false);
+			i40evf_client_release_qvlist(&cinst->lan_info);
+			clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state);
+
+			dev_warn(&adapter->pdev->dev,
+				 "Client %s instance closed\n", client->name);
+		}
+		/* delete the client instance */
+		i40evf_client_del_instance(adapter);
+		dev_info(&adapter->pdev->dev, "Deleted client instance of Client %s\n",
+			 client->name);
+	}
+	mutex_unlock(&i40evf_device_mutex);
+}
+
+/**
+ * i40evf_client_prepare - prepare client specific resources
+ * @client: pointer to the registered client
+ *
+ **/
+static void i40evf_client_prepare(struct i40e_client *client)
+{
+	struct i40e_device *ldev;
+	struct i40evf_adapter *adapter;
+
+	mutex_lock(&i40evf_device_mutex);
+	list_for_each_entry(ldev, &i40evf_devices, list) {
+		adapter = ldev->vf;
+		/* Signal the watchdog to service the client */
+		adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
+	}
+	mutex_unlock(&i40evf_device_mutex);
+}
+
+/**
+ * i40evf_client_virtchnl_send - send a message to the PF instance
+ * @ldev: pointer to L2 context.
+ * @client: Client pointer.
+ * @msg: pointer to message buffer
+ * @len: message length
+ *
+ * Return 0 on success or < 0 on error
+ **/
+static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev,
+				       struct i40e_client *client,
+				       u8 *msg, u16 len)
+{
+	struct i40evf_adapter *adapter = ldev->vf;
+	i40e_status err;
+
+	if (adapter->aq_required)
+		return -EAGAIN;
+
+	err = i40e_aq_send_msg_to_pf(&adapter->hw, I40E_VIRTCHNL_OP_IWARP,
+				     I40E_SUCCESS, msg, len, NULL);
+	if (err)
+		dev_err(&adapter->pdev->dev, "Unable to send iWarp message to PF, error %d, aq status %d\n",
+			err, adapter->hw.aq.asq_last_status);
+
+	return err;
+}
+
+/**
+ * i40evf_client_setup_qvlist - send a message to the PF to setup iwarp qv map
+ * @ldev: pointer to L2 context.
+ * @client: Client pointer.
+ * @qv_info: queue and vector list
+ *
+ * Return 0 on success or < 0 on error
+ **/
+static int i40evf_client_setup_qvlist(struct i40e_info *ldev,
+				      struct i40e_client *client,
+				      struct i40e_qvlist_info *qvlist_info)
+{
+	struct i40e_virtchnl_iwarp_qvlist_info *v_qvlist_info;
+	struct i40evf_adapter *adapter = ldev->vf;
+	struct i40e_qv_info *qv_info;
+	i40e_status err;
+	u32 v_idx, i;
+	u32 msg_size;
+
+	if (adapter->aq_required)
+		return -EAGAIN;
+
+	/* A quick check on whether the vectors belong to the client */
+	for (i = 0; i < qvlist_info->num_vectors; i++) {
+		qv_info = &qvlist_info->qv_info[i];
+		if (!qv_info)
+			continue;
+		v_idx = qv_info->v_idx;
+		if ((v_idx >=
+		    (adapter->iwarp_base_vector + adapter->num_iwarp_msix)) ||
+		    (v_idx < adapter->iwarp_base_vector))
+			return -EINVAL;
+	}
+
+	v_qvlist_info = (struct i40e_virtchnl_iwarp_qvlist_info *)qvlist_info;
+	msg_size = sizeof(struct i40e_virtchnl_iwarp_qvlist_info) +
+			(sizeof(struct i40e_virtchnl_iwarp_qv_info) *
+			(v_qvlist_info->num_vectors - 1));
+
+	adapter->client_pending |= BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP);
+	err = i40e_aq_send_msg_to_pf(&adapter->hw,
+			I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP,
+			I40E_SUCCESS, (u8 *)v_qvlist_info, msg_size, NULL);
+
+	if (err) {
+		dev_err(&adapter->pdev->dev,
+			"Unable to send iWarp vector config message to PF, error %d, aq status %d\n",
+			err, adapter->hw.aq.asq_last_status);
+		goto out;
+	}
+
+	err = -EBUSY;
+	for (i = 0; i < 5; i++) {
+		msleep(100);
+		if (!(adapter->client_pending &
+		      BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP))) {
+			err = 0;
+			break;
+		}
+	}
+out:
+	return err;
+}
+
+/**
+ * i40evf_register_client - Register a i40e client driver with the L2 driver
+ * @client: pointer to the i40e_client struct
+ *
+ * Returns 0 on success or non-0 on error
+ **/
+int i40evf_register_client(struct i40e_client *client)
+{
+	int ret = 0;
+
+	if (!client) {
+		ret = -EIO;
+		goto out;
+	}
+
+	if (strlen(client->name) == 0) {
+		pr_info("i40evf: Failed to register client with no name\n");
+		ret = -EIO;
+		goto out;
+	}
+
+	if (vf_registered_client) {
+		pr_info("i40evf: Client %s has already been registered!\n",
+			client->name);
+		ret = -EEXIST;
+		goto out;
+	}
+
+	if ((client->version.major != I40EVF_CLIENT_VERSION_MAJOR) ||
+	    (client->version.minor != I40EVF_CLIENT_VERSION_MINOR)) {
+		pr_info("i40evf: Failed to register client %s due to mismatched client interface version\n",
+			client->name);
+		pr_info("Client is using version: %02d.%02d.%02d while LAN driver supports %s\n",
+			client->version.major, client->version.minor,
+			client->version.build,
+			i40evf_client_interface_version_str);
+		ret = -EIO;
+		goto out;
+	}
+
+	vf_registered_client = client;
+
+	i40evf_client_prepare(client);
+
+	pr_info("i40evf: Registered client %s with return code %d\n",
+		client->name, ret);
+out:
+	return ret;
+}
+EXPORT_SYMBOL(i40evf_register_client);
+
+/**
+ * i40evf_unregister_client - Unregister a i40e client driver with the L2 driver
+ * @client: pointer to the i40e_client struct
+ *
+ * Returns 0 on success or non-0 on error
+ **/
+int i40evf_unregister_client(struct i40e_client *client)
+{
+	int ret = 0;
+
+	/* When a unregister request comes through we would have to send
+	 * a close for each of the client instances that were opened.
+	 * client_release function is called to handle this.
+	 */
+	i40evf_client_release(client);
+
+	if (vf_registered_client != client) {
+		pr_info("i40evf: Client %s has not been registered\n",
+			client->name);
+		ret = -ENODEV;
+		goto out;
+	}
+	vf_registered_client = NULL;
+	pr_info("i40evf: Unregistered client %s\n", client->name);
+out:
+	return ret;
+}
+EXPORT_SYMBOL(i40evf_unregister_client);
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.h b/drivers/net/ethernet/intel/i40evf/i40evf_client.h
new file mode 100644
index 000000000000..7d283c7506a5
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_client.h
@@ -0,0 +1,166 @@
+#ifndef _I40E_CLIENT_H_
+#define _I40E_CLIENT_H_
+
+#define I40EVF_CLIENT_STR_LENGTH 10
+
+/* Client interface version should be updated anytime there is a change in the
+ * existing APIs or data structures.
+ */
+#define I40EVF_CLIENT_VERSION_MAJOR 0
+#define I40EVF_CLIENT_VERSION_MINOR 01
+#define I40EVF_CLIENT_VERSION_BUILD 00
+#define I40EVF_CLIENT_VERSION_STR     \
+	__stringify(I40EVF_CLIENT_VERSION_MAJOR) "." \
+	__stringify(I40EVF_CLIENT_VERSION_MINOR) "." \
+	__stringify(I40EVF_CLIENT_VERSION_BUILD)
+
+struct i40e_client_version {
+	u8 major;
+	u8 minor;
+	u8 build;
+	u8 rsvd;
+};
+
+enum i40e_client_state {
+	__I40E_CLIENT_NULL,
+	__I40E_CLIENT_REGISTERED
+};
+
+enum i40e_client_instance_state {
+	__I40E_CLIENT_INSTANCE_NONE,
+	__I40E_CLIENT_INSTANCE_OPENED,
+};
+
+struct i40e_ops;
+struct i40e_client;
+
+/* HW does not define a type value for AEQ; only for RX/TX and CEQ.
+ * In order for us to keep the interface simple, SW will define a
+ * unique type value for AEQ.
+ */
+#define I40E_QUEUE_TYPE_PE_AEQ  0x80
+#define I40E_QUEUE_INVALID_IDX	0xFFFF
+
+struct i40e_qv_info {
+	u32 v_idx; /* msix_vector */
+	u16 ceq_idx;
+	u16 aeq_idx;
+	u8 itr_idx;
+};
+
+struct i40e_qvlist_info {
+	u32 num_vectors;
+	struct i40e_qv_info qv_info[1];
+};
+
+#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF
+
+/* set of LAN parameters useful for clients managed by LAN */
+
+/* Struct to hold per priority info */
+struct i40e_prio_qos_params {
+	u16 qs_handle; /* qs handle for prio */
+	u8 tc; /* TC mapped to prio */
+	u8 reserved;
+};
+
+#define I40E_CLIENT_MAX_USER_PRIORITY        8
+/* Struct to hold Client QoS */
+struct i40e_qos_params {
+	struct i40e_prio_qos_params prio_qos[I40E_CLIENT_MAX_USER_PRIORITY];
+};
+
+struct i40e_params {
+	struct i40e_qos_params qos;
+	u16 mtu;
+	u16 link_up; /* boolean */
+};
+
+/* Structure to hold LAN device info for a client device */
+struct i40e_info {
+	struct i40e_client_version version;
+	u8 lanmac[6];
+	struct net_device *netdev;
+	struct pci_dev *pcidev;
+	u8 __iomem *hw_addr;
+	u8 fid;	/* function id, PF id or VF id */
+#define I40E_CLIENT_FTYPE_PF 0
+#define I40E_CLIENT_FTYPE_VF 1
+	u8 ftype; /* function type, PF or VF */
+	void *vf; /* cast to i40evf_adapter */
+
+	/* All L2 params that could change during the life span of the device
+	 * and needs to be communicated to the client when they change
+	 */
+	struct i40e_params params;
+	struct i40e_ops *ops;
+
+	u16 msix_count;	 /* number of msix vectors*/
+	/* Array down below will be dynamically allocated based on msix_count */
+	struct msix_entry *msix_entries;
+	u16 itr_index; /* Which ITR index the PE driver is suppose to use */
+};
+
+struct i40e_ops {
+	/* setup_q_vector_list enables queues with a particular vector */
+	int (*setup_qvlist)(struct i40e_info *ldev, struct i40e_client *client,
+			    struct i40e_qvlist_info *qv_info);
+
+	u32 (*virtchnl_send)(struct i40e_info *ldev, struct i40e_client *client,
+			     u8 *msg, u16 len);
+
+	/* If the PE Engine is unresponsive, RDMA driver can request a reset.*/
+	void (*request_reset)(struct i40e_info *ldev,
+			      struct i40e_client *client);
+};
+
+struct i40e_client_ops {
+	/* Should be called from register_client() or whenever the driver is
+	 * ready to create a specific client instance.
+	 */
+	int (*open)(struct i40e_info *ldev, struct i40e_client *client);
+
+	/* Should be closed when netdev is unavailable or when unregister
+	 * call comes in. If the close happens due to a reset, set the reset
+	 * bit to true.
+	 */
+	void (*close)(struct i40e_info *ldev, struct i40e_client *client,
+		      bool reset);
+
+	/* called when some l2 managed parameters changes - mss */
+	void (*l2_param_change)(struct i40e_info *ldev,
+				struct i40e_client *client,
+				struct i40e_params *params);
+
+	/* called when a message is received from the PF */
+	int (*virtchnl_receive)(struct i40e_info *ldev,
+				struct i40e_client *client,
+				u8 *msg, u16 len);
+};
+
+/* Client device */
+struct i40e_client_instance {
+	struct list_head list;
+	struct i40e_info lan_info;
+	struct i40e_client *client;
+	unsigned long  state;
+};
+
+struct i40e_client {
+	struct list_head list;		/* list of registered clients */
+	char name[I40EVF_CLIENT_STR_LENGTH];
+	struct i40e_client_version version;
+	unsigned long state;		/* client state */
+	atomic_t ref_cnt;  /* Count of all the client devices of this kind */
+	u32 flags;
+#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE	BIT(0)
+#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS	BIT(2)
+	u8 type;
+#define I40E_CLIENT_IWARP 0
+	struct i40e_client_ops *ops;	/* client ops provided by the client */
+};
+
+/* used by clients */
+int i40evf_register_client(struct i40e_client *client);
+int i40evf_unregister_client(struct i40e_client *client);
+#endif /* _I40E_CLIENT_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
index 272d600c1ed0..9bb2cc7dd4e4 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
@@ -63,52 +63,74 @@ static const struct i40evf_stats i40evf_gstrings_stats[] = {
 #define I40EVF_STATS_LEN(_dev) \
 	(I40EVF_GLOBAL_STATS_LEN + I40EVF_QUEUE_STATS_LEN(_dev))
 
+/* For now we have one and only one private flag and it is only defined
+ * when we have support for the SKIP_CPU_SYNC DMA attribute.  Instead
+ * of leaving all this code sitting around empty we will strip it unless
+ * our one private flag is actually available.
+ */
+struct i40evf_priv_flags {
+	char flag_string[ETH_GSTRING_LEN];
+	u32 flag;
+	bool read_only;
+};
+
+#define I40EVF_PRIV_FLAG(_name, _flag, _read_only) { \
+	.flag_string = _name, \
+	.flag = _flag, \
+	.read_only = _read_only, \
+}
+
+static const struct i40evf_priv_flags i40evf_gstrings_priv_flags[] = {
+	I40EVF_PRIV_FLAG("legacy-rx", I40EVF_FLAG_LEGACY_RX, 0),
+};
+
+#define I40EVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40evf_gstrings_priv_flags)
+
 /**
- * i40evf_get_settings - Get Link Speed and Duplex settings
+ * i40evf_get_link_ksettings - Get Link Speed and Duplex settings
  * @netdev: network interface device structure
- * @ecmd: ethtool command
+ * @cmd: ethtool command
  *
  * Reports speed/duplex settings. Because this is a VF, we don't know what
  * kind of link we really have, so we fake it.
  **/
-static int i40evf_get_settings(struct net_device *netdev,
-			       struct ethtool_cmd *ecmd)
+static int i40evf_get_link_ksettings(struct net_device *netdev,
+				     struct ethtool_link_ksettings *cmd)
 {
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 
-	ecmd->supported = 0;
-	ecmd->autoneg = AUTONEG_DISABLE;
-	ecmd->transceiver = XCVR_DUMMY1;
-	ecmd->port = PORT_NONE;
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	cmd->base.autoneg = AUTONEG_DISABLE;
+	cmd->base.port = PORT_NONE;
 	/* Set speed and duplex */
 	switch (adapter->link_speed) {
 	case I40E_LINK_SPEED_40GB:
-		ethtool_cmd_speed_set(ecmd, SPEED_40000);
+		cmd->base.speed = SPEED_40000;
 		break;
 	case I40E_LINK_SPEED_25GB:
 #ifdef SPEED_25000
-		ethtool_cmd_speed_set(ecmd, SPEED_25000);
+		cmd->base.speed = SPEED_25000;
 #else
 		netdev_info(netdev,
 			    "Speed is 25G, display not supported by this version of ethtool.\n");
 #endif
 		break;
 	case I40E_LINK_SPEED_20GB:
-		ethtool_cmd_speed_set(ecmd, SPEED_20000);
+		cmd->base.speed = SPEED_20000;
 		break;
 	case I40E_LINK_SPEED_10GB:
-		ethtool_cmd_speed_set(ecmd, SPEED_10000);
+		cmd->base.speed = SPEED_10000;
 		break;
 	case I40E_LINK_SPEED_1GB:
-		ethtool_cmd_speed_set(ecmd, SPEED_1000);
+		cmd->base.speed = SPEED_1000;
 		break;
 	case I40E_LINK_SPEED_100MB:
-		ethtool_cmd_speed_set(ecmd, SPEED_100);
+		cmd->base.speed = SPEED_100;
 		break;
 	default:
 		break;
 	}
-	ecmd->duplex = DUPLEX_FULL;
+	cmd->base.duplex = DUPLEX_FULL;
 
 	return 0;
 }
@@ -125,6 +147,8 @@ static int i40evf_get_sset_count(struct net_device *netdev, int sset)
 {
 	if (sset == ETH_SS_STATS)
 		return I40EVF_STATS_LEN(netdev);
+	else if (sset == ETH_SS_PRIV_FLAGS)
+		return I40EVF_PRIV_FLAGS_STR_LEN;
 	else
 		return -EINVAL;
 }
@@ -190,7 +214,83 @@ static void i40evf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 			snprintf(p, ETH_GSTRING_LEN, "rx-%u.bytes", i);
 			p += ETH_GSTRING_LEN;
 		}
+	} else if (sset == ETH_SS_PRIV_FLAGS) {
+		for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) {
+			snprintf(p, ETH_GSTRING_LEN, "%s",
+				 i40evf_gstrings_priv_flags[i].flag_string);
+			p += ETH_GSTRING_LEN;
+		}
+	}
+}
+
+/**
+ * i40evf_get_priv_flags - report device private flags
+ * @dev: network interface device structure
+ *
+ * The get string set count and the string set should be matched for each
+ * flag returned.  Add new strings for each flag to the i40e_gstrings_priv_flags
+ * array.
+ *
+ * Returns a u32 bitmap of flags.
+ **/
+static u32 i40evf_get_priv_flags(struct net_device *netdev)
+{
+	struct i40evf_adapter *adapter = netdev_priv(netdev);
+	u32 i, ret_flags = 0;
+
+	for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) {
+		const struct i40evf_priv_flags *priv_flags;
+
+		priv_flags = &i40evf_gstrings_priv_flags[i];
+
+		if (priv_flags->flag & adapter->flags)
+			ret_flags |= BIT(i);
+	}
+
+	return ret_flags;
+}
+
+/**
+ * i40evf_set_priv_flags - set private flags
+ * @dev: network interface device structure
+ * @flags: bit flags to be set
+ **/
+static int i40evf_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+	struct i40evf_adapter *adapter = netdev_priv(netdev);
+	u64 changed_flags;
+	u32 i;
+
+	changed_flags = adapter->flags;
+
+	for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) {
+		const struct i40evf_priv_flags *priv_flags;
+
+		priv_flags = &i40evf_gstrings_priv_flags[i];
+
+		if (priv_flags->read_only)
+			continue;
+
+		if (flags & BIT(i))
+			adapter->flags |= priv_flags->flag;
+		else
+			adapter->flags &= ~(priv_flags->flag);
+	}
+
+	/* check for flags that changed */
+	changed_flags ^= adapter->flags;
+
+	/* Process any additional changes needed as a result of flag changes. */
+
+	/* issue a reset to force legacy-rx change to take effect */
+	if (changed_flags & I40EVF_FLAG_LEGACY_RX) {
+		if (netif_running(netdev)) {
+			adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
+			schedule_work(&adapter->reset_task);
+		}
 	}
+
+	return 0;
 }
 
 /**
@@ -239,6 +339,7 @@ static void i40evf_get_drvinfo(struct net_device *netdev,
 	strlcpy(drvinfo->version, i40evf_driver_version, 32);
 	strlcpy(drvinfo->fw_version, "N/A", 4);
 	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+	drvinfo->n_priv_flags = I40EVF_PRIV_FLAGS_STR_LEN;
 }
 
 /**
@@ -643,7 +744,6 @@ static int i40evf_set_rxfh(struct net_device *netdev, const u32 *indir,
 }
 
 static const struct ethtool_ops i40evf_ethtool_ops = {
-	.get_settings		= i40evf_get_settings,
 	.get_drvinfo		= i40evf_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_ringparam		= i40evf_get_ringparam,
@@ -651,6 +751,8 @@ static const struct ethtool_ops i40evf_ethtool_ops = {
 	.get_strings		= i40evf_get_strings,
 	.get_ethtool_stats	= i40evf_get_ethtool_stats,
 	.get_sset_count		= i40evf_get_sset_count,
+	.get_priv_flags		= i40evf_get_priv_flags,
+	.set_priv_flags		= i40evf_set_priv_flags,
 	.get_msglevel		= i40evf_get_msglevel,
 	.set_msglevel		= i40evf_set_msglevel,
 	.get_coalesce		= i40evf_get_coalesce,
@@ -663,6 +765,7 @@ static const struct ethtool_ops i40evf_ethtool_ops = {
 	.set_rxfh		= i40evf_set_rxfh,
 	.get_channels		= i40evf_get_channels,
 	.get_rxfh_key_size	= i40evf_get_rxfh_key_size,
+	.get_link_ksettings	= i40evf_get_link_ksettings,
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index f35dcaac5bb7..fb2811c23024 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -26,6 +26,7 @@
 
 #include "i40evf.h"
 #include "i40e_prototype.h"
+#include "i40evf_client.h"
 static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter);
 static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter);
 static int i40evf_close(struct net_device *netdev);
@@ -36,9 +37,9 @@ static const char i40evf_driver_string[] =
 
 #define DRV_KERN "-k"
 
-#define DRV_VERSION_MAJOR 1
-#define DRV_VERSION_MINOR 6
-#define DRV_VERSION_BUILD 27
+#define DRV_VERSION_MAJOR 2
+#define DRV_VERSION_MINOR 1
+#define DRV_VERSION_BUILD 7
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD) \
@@ -685,12 +686,26 @@ static void i40evf_configure_tx(struct i40evf_adapter *adapter)
  **/
 static void i40evf_configure_rx(struct i40evf_adapter *adapter)
 {
+	unsigned int rx_buf_len = I40E_RXBUFFER_2048;
+	struct net_device *netdev = adapter->netdev;
 	struct i40e_hw *hw = &adapter->hw;
 	int i;
 
+	/* Legacy Rx will always default to a 2048 buffer size. */
+#if (PAGE_SIZE < 8192)
+	if (!(adapter->flags & I40EVF_FLAG_LEGACY_RX)) {
+		/* We use a 1536 buffer size for configurations with
+		 * standard Ethernet mtu.  On x86 this gives us enough room
+		 * for shared info and 192 bytes of padding.
+		 */
+		if (netdev->mtu <= ETH_DATA_LEN)
+			rx_buf_len = I40E_RXBUFFER_1536 - NET_IP_ALIGN;
+	}
+#endif
+
 	for (i = 0; i < adapter->num_active_queues; i++) {
 		adapter->rx_rings[i].tail = hw->hw_addr + I40E_QRX_TAIL1(i);
-		adapter->rx_rings[i].rx_buf_len = I40EVF_RXBUFFER_2048;
+		adapter->rx_rings[i].rx_buf_len = rx_buf_len;
 	}
 }
 
@@ -1058,6 +1073,8 @@ static void i40evf_up_complete(struct i40evf_adapter *adapter)
 	i40evf_napi_enable_all(adapter);
 
 	adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_QUEUES;
+	if (CLIENT_ENABLED(adapter))
+		adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_OPEN;
 	mod_timer_pending(&adapter->watchdog_timer, jiffies + 1);
 }
 
@@ -1685,6 +1702,7 @@ static void i40evf_watchdog_task(struct work_struct *work)
 		i40evf_set_promiscuous(adapter, 0);
 		goto watchdog_done;
 	}
+	schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5));
 
 	if (adapter->state == __I40EVF_RUNNING)
 		i40evf_request_stats(adapter);
@@ -1773,10 +1791,17 @@ static void i40evf_reset_task(struct work_struct *work)
 	u32 reg_val;
 	int i = 0, err;
 
-	while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK,
+	while (test_and_set_bit(__I40EVF_IN_CLIENT_TASK,
 				&adapter->crit_section))
 		usleep_range(500, 1000);
-
+	if (CLIENT_ENABLED(adapter)) {
+		adapter->flags &= ~(I40EVF_FLAG_CLIENT_NEEDS_OPEN |
+				    I40EVF_FLAG_CLIENT_NEEDS_CLOSE |
+				    I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS |
+				    I40EVF_FLAG_SERVICE_CLIENT_REQUESTED);
+		cancel_delayed_work_sync(&adapter->client_task);
+		i40evf_notify_client_close(&adapter->vsi, true);
+	}
 	i40evf_misc_irq_disable(adapter);
 	if (adapter->flags & I40EVF_FLAG_RESET_NEEDED) {
 		adapter->flags &= ~I40EVF_FLAG_RESET_NEEDED;
@@ -1819,6 +1844,7 @@ static void i40evf_reset_task(struct work_struct *work)
 		dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n",
 			reg_val);
 		i40evf_disable_vf(adapter);
+		clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);
 		return; /* Do not attempt to reinit. It's dead, Jim. */
 	}
 
@@ -1861,9 +1887,8 @@ continue_reset:
 	}
 	adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER;
 	adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER;
-	/* Open RDMA Client again */
-	adapter->aq_required |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
 	clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);
 	i40evf_misc_irq_enable(adapter);
 
 	mod_timer(&adapter->watchdog_timer, jiffies + 2);
@@ -1980,6 +2005,48 @@ out:
 }
 
 /**
+ * i40evf_client_task - worker thread to perform client work
+ * @work: pointer to work_struct containing our data
+ *
+ * This task handles client interactions. Because client calls can be
+ * reentrant, we can't handle them in the watchdog.
+ **/
+static void i40evf_client_task(struct work_struct *work)
+{
+	struct i40evf_adapter *adapter =
+		container_of(work, struct i40evf_adapter, client_task.work);
+
+	/* If we can't get the client bit, just give up. We'll be rescheduled
+	 * later.
+	 */
+
+	if (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section))
+		return;
+
+	if (adapter->flags & I40EVF_FLAG_SERVICE_CLIENT_REQUESTED) {
+		i40evf_client_subtask(adapter);
+		adapter->flags &= ~I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
+		goto out;
+	}
+	if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_CLOSE) {
+		i40evf_notify_client_close(&adapter->vsi, false);
+		adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_CLOSE;
+		goto out;
+	}
+	if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_OPEN) {
+		i40evf_notify_client_open(&adapter->vsi);
+		adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_OPEN;
+		goto out;
+	}
+	if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS) {
+		i40evf_notify_client_l2_params(&adapter->vsi);
+		adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS;
+	}
+out:
+	clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);
+}
+
+/**
  * i40evf_free_all_tx_resources - Free Tx Resources for All Queues
  * @adapter: board private structure
  *
@@ -2148,6 +2215,8 @@ static int i40evf_close(struct net_device *netdev)
 
 
 	set_bit(__I40E_DOWN, &adapter->vsi.state);
+	if (CLIENT_ENABLED(adapter))
+		adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_CLOSE;
 
 	i40evf_down(adapter);
 	adapter->state = __I40EVF_DOWN_PENDING;
@@ -2188,6 +2257,10 @@ static int i40evf_change_mtu(struct net_device *netdev, int new_mtu)
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 
 	netdev->mtu = new_mtu;
+	if (CLIENT_ENABLED(adapter)) {
+		i40evf_notify_client_l2_params(&adapter->vsi);
+		adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
+	}
 	adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
 	schedule_work(&adapter->reset_task);
 
@@ -2581,6 +2654,12 @@ static void i40evf_init_task(struct work_struct *work)
 	adapter->netdev_registered = true;
 
 	netif_tx_stop_all_queues(netdev);
+	if (CLIENT_ALLOWED(adapter)) {
+		err = i40evf_lan_add_device(adapter);
+		if (err)
+			dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n",
+				 err);
+	}
 
 	dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr);
 	if (netdev->features & NETIF_F_GRO)
@@ -2745,6 +2824,7 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	INIT_WORK(&adapter->reset_task, i40evf_reset_task);
 	INIT_WORK(&adapter->adminq_task, i40evf_adminq_task);
 	INIT_WORK(&adapter->watchdog_task, i40evf_watchdog_task);
+	INIT_DELAYED_WORK(&adapter->client_task, i40evf_client_task);
 	INIT_DELAYED_WORK(&adapter->init_task, i40evf_init_task);
 	schedule_delayed_work(&adapter->init_task,
 			      msecs_to_jiffies(5 * (pdev->devfn & 0x07)));
@@ -2857,14 +2937,21 @@ static void i40evf_remove(struct pci_dev *pdev)
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 	struct i40evf_mac_filter *f, *ftmp;
 	struct i40e_hw *hw = &adapter->hw;
+	int err;
 
 	cancel_delayed_work_sync(&adapter->init_task);
 	cancel_work_sync(&adapter->reset_task);
-
+	cancel_delayed_work_sync(&adapter->client_task);
 	if (adapter->netdev_registered) {
 		unregister_netdev(netdev);
 		adapter->netdev_registered = false;
 	}
+	if (CLIENT_ALLOWED(adapter)) {
+		err = i40evf_lan_del_device(adapter);
+		if (err)
+			dev_warn(&pdev->dev, "Failed to delete client device: %d\n",
+				 err);
+	}
 
 	/* Shut down all the garbage mashers on the detention level */
 	adapter->state = __I40EVF_REMOVE;
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
index bee58af390e1..032be8d3928a 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
@@ -26,6 +26,7 @@
 
 #include "i40evf.h"
 #include "i40e_prototype.h"
+#include "i40evf_client.h"
 
 /* busy wait delay in msec */
 #define I40EVF_BUSY_WAIT_DELAY 10
@@ -233,7 +234,7 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter)
 	struct i40e_virtchnl_vsi_queue_config_info *vqci;
 	struct i40e_virtchnl_queue_pair_info *vqpi;
 	int pairs = adapter->num_active_queues;
-	int i, len;
+	int i, len, max_frame = I40E_MAX_RXBUFFER;
 
 	if (adapter->current_op != I40E_VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -248,6 +249,11 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter)
 	if (!vqci)
 		return;
 
+	/* Limit maximum frame size when jumbo frames is not enabled */
+	if (!(adapter->flags & I40EVF_FLAG_LEGACY_RX) &&
+	    (adapter->netdev->mtu <= ETH_DATA_LEN))
+		max_frame = I40E_RXBUFFER_1536 - NET_IP_ALIGN;
+
 	vqci->vsi_id = adapter->vsi_res->vsi_id;
 	vqci->num_queue_pairs = pairs;
 	vqpi = vqci->qpair;
@@ -259,17 +265,14 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter)
 		vqpi->txq.queue_id = i;
 		vqpi->txq.ring_len = adapter->tx_rings[i].count;
 		vqpi->txq.dma_ring_addr = adapter->tx_rings[i].dma;
-		vqpi->txq.headwb_enabled = 1;
-		vqpi->txq.dma_headwb_addr = vqpi->txq.dma_ring_addr +
-		    (vqpi->txq.ring_len * sizeof(struct i40e_tx_desc));
-
 		vqpi->rxq.vsi_id = vqci->vsi_id;
 		vqpi->rxq.queue_id = i;
 		vqpi->rxq.ring_len = adapter->rx_rings[i].count;
 		vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma;
-		vqpi->rxq.max_pkt_size = adapter->netdev->mtu
-					+ ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN;
-		vqpi->rxq.databuffer_size = adapter->rx_rings[i].rx_buf_len;
+		vqpi->rxq.max_pkt_size = max_frame;
+		vqpi->rxq.databuffer_size =
+			ALIGN(adapter->rx_rings[i].rx_buf_len,
+			      BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
 		vqpi++;
 	}
 
@@ -999,6 +1002,16 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 		if (v_opcode != adapter->current_op)
 			return;
 		break;
+	case I40E_VIRTCHNL_OP_IWARP:
+		/* Gobble zero-length replies from the PF. They indicate that
+		 * a previous message was received OK, and the client doesn't
+		 * care about that.
+		 */
+		if (msglen && CLIENT_ENABLED(adapter))
+			i40evf_notify_client_message(&adapter->vsi,
+						     msg, msglen);
+		break;
+
 	case I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP:
 		adapter->client_pending &=
 				~(BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP));
@@ -1014,7 +1027,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 		}
 		break;
 	default:
-		if (v_opcode != adapter->current_op)
+		if (adapter->current_op && (v_opcode != adapter->current_op))
 			dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n",
 				 adapter->current_op, v_opcode);
 		break;
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index acbc3abe2ddd..dc6e2980718f 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -142,12 +142,24 @@ struct vf_data_storage {
 /* Supported Rx Buffer Sizes */
 #define IGB_RXBUFFER_256	256
 #define IGB_RXBUFFER_2048	2048
+#define IGB_RXBUFFER_3072	3072
 #define IGB_RX_HDR_LEN		IGB_RXBUFFER_256
-#define IGB_RX_BUFSZ		IGB_RXBUFFER_2048
+#define IGB_TS_HDR_LEN		16
+
+#define IGB_SKB_PAD		(NET_SKB_PAD + NET_IP_ALIGN)
+#if (PAGE_SIZE < 8192)
+#define IGB_MAX_FRAME_BUILD_SKB \
+	(SKB_WITH_OVERHEAD(IGB_RXBUFFER_2048) - IGB_SKB_PAD - IGB_TS_HDR_LEN)
+#else
+#define IGB_MAX_FRAME_BUILD_SKB (IGB_RXBUFFER_2048 - IGB_TS_HDR_LEN)
+#endif
 
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
 #define IGB_RX_BUFFER_WRITE	16 /* Must be power of 2 */
 
+#define IGB_RX_DMA_ATTR \
+	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
 #define AUTO_ALL_MODES		0
 #define IGB_EEPROM_APME		0x0400
 
@@ -301,12 +313,51 @@ struct igb_q_vector {
 };
 
 enum e1000_ring_flags_t {
+	IGB_RING_FLAG_RX_3K_BUFFER,
+	IGB_RING_FLAG_RX_BUILD_SKB_ENABLED,
 	IGB_RING_FLAG_RX_SCTP_CSUM,
 	IGB_RING_FLAG_RX_LB_VLAN_BSWAP,
 	IGB_RING_FLAG_TX_CTX_IDX,
 	IGB_RING_FLAG_TX_DETECT_HANG
 };
 
+#define ring_uses_large_buffer(ring) \
+	test_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags)
+#define set_ring_uses_large_buffer(ring) \
+	set_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags)
+#define clear_ring_uses_large_buffer(ring) \
+	clear_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags)
+
+#define ring_uses_build_skb(ring) \
+	test_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags)
+#define set_ring_build_skb_enabled(ring) \
+	set_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags)
+#define clear_ring_build_skb_enabled(ring) \
+	clear_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags)
+
+static inline unsigned int igb_rx_bufsz(struct igb_ring *ring)
+{
+#if (PAGE_SIZE < 8192)
+	if (ring_uses_large_buffer(ring))
+		return IGB_RXBUFFER_3072;
+
+	if (ring_uses_build_skb(ring))
+		return IGB_MAX_FRAME_BUILD_SKB + IGB_TS_HDR_LEN;
+#endif
+	return IGB_RXBUFFER_2048;
+}
+
+static inline unsigned int igb_rx_pg_order(struct igb_ring *ring)
+{
+#if (PAGE_SIZE < 8192)
+	if (ring_uses_large_buffer(ring))
+		return 1;
+#endif
+	return 0;
+}
+
+#define igb_rx_pg_size(_ring) (PAGE_SIZE << igb_rx_pg_order(_ring))
+
 #define IGB_TXD_DCMD (E1000_ADVTXD_DCMD_EOP | E1000_ADVTXD_DCMD_RS)
 
 #define IGB_RX_DESC(R, i)	\
@@ -545,6 +596,7 @@ struct igb_adapter {
 #define IGB_FLAG_HAS_MSIX		BIT(13)
 #define IGB_FLAG_EEE			BIT(14)
 #define IGB_FLAG_VLAN_PROMISC		BIT(15)
+#define IGB_FLAG_RX_LEGACY		BIT(16)
 
 /* Media Auto Sense */
 #define IGB_MAS_ENABLE_0		0X0001
@@ -558,7 +610,6 @@ struct igb_adapter {
 #define IGB_DMCTLX_DCFLUSH_DIS	0x80000000  /* Disable DMA Coal Flush */
 
 #define IGB_82576_TSYNC_SHIFT	19
-#define IGB_TS_HDR_LEN		16
 enum e1000_state_t {
 	__IGB_TESTING,
 	__IGB_RESETTING,
@@ -591,7 +642,6 @@ void igb_configure_rx_ring(struct igb_adapter *, struct igb_ring *);
 void igb_setup_tctl(struct igb_adapter *);
 void igb_setup_rctl(struct igb_adapter *);
 netdev_tx_t igb_xmit_frame_ring(struct sk_buff *, struct igb_ring *);
-void igb_unmap_and_free_tx_resource(struct igb_ring *, struct igb_tx_buffer *);
 void igb_alloc_rx_buffers(struct igb_ring *, u16);
 void igb_update_stats(struct igb_adapter *, struct rtnl_link_stats64 *);
 bool igb_has_link(struct igb_adapter *adapter);
@@ -604,7 +654,7 @@ void igb_ptp_reset(struct igb_adapter *adapter);
 void igb_ptp_suspend(struct igb_adapter *adapter);
 void igb_ptp_rx_hang(struct igb_adapter *adapter);
 void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb);
-void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, unsigned char *va,
+void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 			 struct sk_buff *skb);
 int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
 int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 737b664d004c..0efb62db6efd 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -144,7 +144,15 @@ static const char igb_gstrings_test[][ETH_GSTRING_LEN] = {
 };
 #define IGB_TEST_LEN (sizeof(igb_gstrings_test) / ETH_GSTRING_LEN)
 
-static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+static const char igb_priv_flags_strings[][ETH_GSTRING_LEN] = {
+#define IGB_PRIV_FLAGS_LEGACY_RX	BIT(0)
+	"legacy-rx",
+};
+
+#define IGB_PRIV_FLAGS_STR_LEN ARRAY_SIZE(igb_priv_flags_strings)
+
+static int igb_get_link_ksettings(struct net_device *netdev,
+				  struct ethtool_link_ksettings *cmd)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
@@ -152,76 +160,73 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 	struct e1000_sfp_flags *eth_flags = &dev_spec->eth_flags;
 	u32 status;
 	u32 speed;
+	u32 supported, advertising;
 
 	status = rd32(E1000_STATUS);
 	if (hw->phy.media_type == e1000_media_type_copper) {
 
-		ecmd->supported = (SUPPORTED_10baseT_Half |
-				   SUPPORTED_10baseT_Full |
-				   SUPPORTED_100baseT_Half |
-				   SUPPORTED_100baseT_Full |
-				   SUPPORTED_1000baseT_Full|
-				   SUPPORTED_Autoneg |
-				   SUPPORTED_TP |
-				   SUPPORTED_Pause);
-		ecmd->advertising = ADVERTISED_TP;
+		supported = (SUPPORTED_10baseT_Half |
+			     SUPPORTED_10baseT_Full |
+			     SUPPORTED_100baseT_Half |
+			     SUPPORTED_100baseT_Full |
+			     SUPPORTED_1000baseT_Full|
+			     SUPPORTED_Autoneg |
+			     SUPPORTED_TP |
+			     SUPPORTED_Pause);
+		advertising = ADVERTISED_TP;
 
 		if (hw->mac.autoneg == 1) {
-			ecmd->advertising |= ADVERTISED_Autoneg;
+			advertising |= ADVERTISED_Autoneg;
 			/* the e1000 autoneg seems to match ethtool nicely */
-			ecmd->advertising |= hw->phy.autoneg_advertised;
+			advertising |= hw->phy.autoneg_advertised;
 		}
 
-		ecmd->port = PORT_TP;
-		ecmd->phy_address = hw->phy.addr;
-		ecmd->transceiver = XCVR_INTERNAL;
+		cmd->base.port = PORT_TP;
+		cmd->base.phy_address = hw->phy.addr;
 	} else {
-		ecmd->supported = (SUPPORTED_FIBRE |
-				   SUPPORTED_1000baseKX_Full |
-				   SUPPORTED_Autoneg |
-				   SUPPORTED_Pause);
-		ecmd->advertising = (ADVERTISED_FIBRE |
-				     ADVERTISED_1000baseKX_Full);
+		supported = (SUPPORTED_FIBRE |
+			     SUPPORTED_1000baseKX_Full |
+			     SUPPORTED_Autoneg |
+			     SUPPORTED_Pause);
+		advertising = (ADVERTISED_FIBRE |
+			       ADVERTISED_1000baseKX_Full);
 		if (hw->mac.type == e1000_i354) {
 			if ((hw->device_id ==
 			     E1000_DEV_ID_I354_BACKPLANE_2_5GBPS) &&
 			    !(status & E1000_STATUS_2P5_SKU_OVER)) {
-				ecmd->supported |= SUPPORTED_2500baseX_Full;
-				ecmd->supported &=
-					~SUPPORTED_1000baseKX_Full;
-				ecmd->advertising |= ADVERTISED_2500baseX_Full;
-				ecmd->advertising &=
-					~ADVERTISED_1000baseKX_Full;
+				supported |= SUPPORTED_2500baseX_Full;
+				supported &= ~SUPPORTED_1000baseKX_Full;
+				advertising |= ADVERTISED_2500baseX_Full;
+				advertising &= ~ADVERTISED_1000baseKX_Full;
 			}
 		}
 		if (eth_flags->e100_base_fx) {
-			ecmd->supported |= SUPPORTED_100baseT_Full;
-			ecmd->advertising |= ADVERTISED_100baseT_Full;
+			supported |= SUPPORTED_100baseT_Full;
+			advertising |= ADVERTISED_100baseT_Full;
 		}
 		if (hw->mac.autoneg == 1)
-			ecmd->advertising |= ADVERTISED_Autoneg;
+			advertising |= ADVERTISED_Autoneg;
 
-		ecmd->port = PORT_FIBRE;
-		ecmd->transceiver = XCVR_EXTERNAL;
+		cmd->base.port = PORT_FIBRE;
 	}
 	if (hw->mac.autoneg != 1)
-		ecmd->advertising &= ~(ADVERTISED_Pause |
-				       ADVERTISED_Asym_Pause);
+		advertising &= ~(ADVERTISED_Pause |
+				 ADVERTISED_Asym_Pause);
 
 	switch (hw->fc.requested_mode) {
 	case e1000_fc_full:
-		ecmd->advertising |= ADVERTISED_Pause;
+		advertising |= ADVERTISED_Pause;
 		break;
 	case e1000_fc_rx_pause:
-		ecmd->advertising |= (ADVERTISED_Pause |
-				      ADVERTISED_Asym_Pause);
+		advertising |= (ADVERTISED_Pause |
+				ADVERTISED_Asym_Pause);
 		break;
 	case e1000_fc_tx_pause:
-		ecmd->advertising |=  ADVERTISED_Asym_Pause;
+		advertising |=  ADVERTISED_Asym_Pause;
 		break;
 	default:
-		ecmd->advertising &= ~(ADVERTISED_Pause |
-				       ADVERTISED_Asym_Pause);
+		advertising &= ~(ADVERTISED_Pause |
+				 ADVERTISED_Asym_Pause);
 	}
 	if (status & E1000_STATUS_LU) {
 		if ((status & E1000_STATUS_2P5_SKU) &&
@@ -236,39 +241,46 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 		}
 		if ((status & E1000_STATUS_FD) ||
 		    hw->phy.media_type != e1000_media_type_copper)
-			ecmd->duplex = DUPLEX_FULL;
+			cmd->base.duplex = DUPLEX_FULL;
 		else
-			ecmd->duplex = DUPLEX_HALF;
+			cmd->base.duplex = DUPLEX_HALF;
 	} else {
 		speed = SPEED_UNKNOWN;
-		ecmd->duplex = DUPLEX_UNKNOWN;
+		cmd->base.duplex = DUPLEX_UNKNOWN;
 	}
-	ethtool_cmd_speed_set(ecmd, speed);
+	cmd->base.speed = speed;
 	if ((hw->phy.media_type == e1000_media_type_fiber) ||
 	    hw->mac.autoneg)
-		ecmd->autoneg = AUTONEG_ENABLE;
+		cmd->base.autoneg = AUTONEG_ENABLE;
 	else
-		ecmd->autoneg = AUTONEG_DISABLE;
+		cmd->base.autoneg = AUTONEG_DISABLE;
 
 	/* MDI-X => 2; MDI =>1; Invalid =>0 */
 	if (hw->phy.media_type == e1000_media_type_copper)
-		ecmd->eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X :
+		cmd->base.eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X :
 						      ETH_TP_MDI;
 	else
-		ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID;
+		cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID;
 
 	if (hw->phy.mdix == AUTO_ALL_MODES)
-		ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
+		cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
 	else
-		ecmd->eth_tp_mdix_ctrl = hw->phy.mdix;
+		cmd->base.eth_tp_mdix_ctrl = hw->phy.mdix;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 
 	return 0;
 }
 
-static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+static int igb_set_link_ksettings(struct net_device *netdev,
+				  const struct ethtool_link_ksettings *cmd)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
+	u32 advertising;
 
 	/* When SoL/IDER sessions are active, autoneg/speed/duplex
 	 * cannot be changed
@@ -283,12 +295,12 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 	 * some hardware doesn't allow MDI setting when speed or
 	 * duplex is forced.
 	 */
-	if (ecmd->eth_tp_mdix_ctrl) {
+	if (cmd->base.eth_tp_mdix_ctrl) {
 		if (hw->phy.media_type != e1000_media_type_copper)
 			return -EOPNOTSUPP;
 
-		if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
-		    (ecmd->autoneg != AUTONEG_ENABLE)) {
+		if ((cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
+		    (cmd->base.autoneg != AUTONEG_ENABLE)) {
 			dev_err(&adapter->pdev->dev, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
 			return -EINVAL;
 		}
@@ -297,10 +309,13 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 	while (test_and_set_bit(__IGB_RESETTING, &adapter->state))
 		usleep_range(1000, 2000);
 
-	if (ecmd->autoneg == AUTONEG_ENABLE) {
+	ethtool_convert_link_mode_to_legacy_u32(&advertising,
+						cmd->link_modes.advertising);
+
+	if (cmd->base.autoneg == AUTONEG_ENABLE) {
 		hw->mac.autoneg = 1;
 		if (hw->phy.media_type == e1000_media_type_fiber) {
-			hw->phy.autoneg_advertised = ecmd->advertising |
+			hw->phy.autoneg_advertised = advertising |
 						     ADVERTISED_FIBRE |
 						     ADVERTISED_Autoneg;
 			switch (adapter->link_speed) {
@@ -320,31 +335,31 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 				break;
 			}
 		} else {
-			hw->phy.autoneg_advertised = ecmd->advertising |
+			hw->phy.autoneg_advertised = advertising |
 						     ADVERTISED_TP |
 						     ADVERTISED_Autoneg;
 		}
-		ecmd->advertising = hw->phy.autoneg_advertised;
+		advertising = hw->phy.autoneg_advertised;
 		if (adapter->fc_autoneg)
 			hw->fc.requested_mode = e1000_fc_default;
 	} else {
-		u32 speed = ethtool_cmd_speed(ecmd);
+		u32 speed = cmd->base.speed;
 		/* calling this overrides forced MDI setting */
-		if (igb_set_spd_dplx(adapter, speed, ecmd->duplex)) {
+		if (igb_set_spd_dplx(adapter, speed, cmd->base.duplex)) {
 			clear_bit(__IGB_RESETTING, &adapter->state);
 			return -EINVAL;
 		}
 	}
 
 	/* MDI-X => 2; MDI => 1; Auto => 3 */
-	if (ecmd->eth_tp_mdix_ctrl) {
+	if (cmd->base.eth_tp_mdix_ctrl) {
 		/* fix up the value for auto (3 => 0) as zero is mapped
 		 * internally to auto
 		 */
-		if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+		if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
 			hw->phy.mdix = AUTO_ALL_MODES;
 		else
-			hw->phy.mdix = ecmd->eth_tp_mdix_ctrl;
+			hw->phy.mdix = cmd->base.eth_tp_mdix_ctrl;
 	}
 
 	/* reset the link */
@@ -852,6 +867,8 @@ static void igb_get_drvinfo(struct net_device *netdev,
 		sizeof(drvinfo->fw_version));
 	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
 		sizeof(drvinfo->bus_info));
+
+	drvinfo->n_priv_flags = IGB_PRIV_FLAGS_STR_LEN;
 }
 
 static void igb_get_ringparam(struct net_device *netdev,
@@ -1811,14 +1828,14 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
 	tx_ntc = tx_ring->next_to_clean;
 	rx_desc = IGB_RX_DESC(rx_ring, rx_ntc);
 
-	while (igb_test_staterr(rx_desc, E1000_RXD_STAT_DD)) {
+	while (rx_desc->wb.upper.length) {
 		/* check Rx buffer */
 		rx_buffer_info = &rx_ring->rx_buffer_info[rx_ntc];
 
 		/* sync Rx buffer for CPU read */
 		dma_sync_single_for_cpu(rx_ring->dev,
 					rx_buffer_info->dma,
-					IGB_RX_BUFSZ,
+					size,
 					DMA_FROM_DEVICE);
 
 		/* verify contents of skb */
@@ -1828,12 +1845,21 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
 		/* sync Rx buffer for device write */
 		dma_sync_single_for_device(rx_ring->dev,
 					   rx_buffer_info->dma,
-					   IGB_RX_BUFSZ,
+					   size,
 					   DMA_FROM_DEVICE);
 
 		/* unmap buffer on Tx side */
 		tx_buffer_info = &tx_ring->tx_buffer_info[tx_ntc];
-		igb_unmap_and_free_tx_resource(tx_ring, tx_buffer_info);
+
+		/* Free all the Tx ring sk_buffs */
+		dev_kfree_skb_any(tx_buffer_info->skb);
+
+		/* unmap skb header data */
+		dma_unmap_single(tx_ring->dev,
+				 dma_unmap_addr(tx_buffer_info, dma),
+				 dma_unmap_len(tx_buffer_info, len),
+				 DMA_TO_DEVICE);
+		dma_unmap_len_set(tx_buffer_info, len, 0);
 
 		/* increment Rx/Tx next to clean counters */
 		rx_ntc++;
@@ -2271,6 +2297,8 @@ static int igb_get_sset_count(struct net_device *netdev, int sset)
 		return IGB_STATS_LEN;
 	case ETH_SS_TEST:
 		return IGB_TEST_LEN;
+	case ETH_SS_PRIV_FLAGS:
+		return IGB_PRIV_FLAGS_STR_LEN;
 	default:
 		return -ENOTSUPP;
 	}
@@ -2376,6 +2404,10 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 		}
 		/* BUG_ON(p - data != IGB_STATS_LEN * ETH_GSTRING_LEN); */
 		break;
+	case ETH_SS_PRIV_FLAGS:
+		memcpy(data, igb_priv_flags_strings,
+		       IGB_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN);
+		break;
 	}
 }
 
@@ -3388,9 +3420,38 @@ static int igb_set_channels(struct net_device *netdev,
 	return 0;
 }
 
+static u32 igb_get_priv_flags(struct net_device *netdev)
+{
+	struct igb_adapter *adapter = netdev_priv(netdev);
+	u32 priv_flags = 0;
+
+	if (adapter->flags & IGB_FLAG_RX_LEGACY)
+		priv_flags |= IGB_PRIV_FLAGS_LEGACY_RX;
+
+	return priv_flags;
+}
+
+static int igb_set_priv_flags(struct net_device *netdev, u32 priv_flags)
+{
+	struct igb_adapter *adapter = netdev_priv(netdev);
+	unsigned int flags = adapter->flags;
+
+	flags &= ~IGB_FLAG_RX_LEGACY;
+	if (priv_flags & IGB_PRIV_FLAGS_LEGACY_RX)
+		flags |= IGB_FLAG_RX_LEGACY;
+
+	if (flags != adapter->flags) {
+		adapter->flags = flags;
+
+		/* reset interface to repopulate queues */
+		if (netif_running(netdev))
+			igb_reinit_locked(adapter);
+	}
+
+	return 0;
+}
+
 static const struct ethtool_ops igb_ethtool_ops = {
-	.get_settings		= igb_get_settings,
-	.set_settings		= igb_set_settings,
 	.get_drvinfo		= igb_get_drvinfo,
 	.get_regs_len		= igb_get_regs_len,
 	.get_regs		= igb_get_regs,
@@ -3426,8 +3487,12 @@ static const struct ethtool_ops igb_ethtool_ops = {
 	.set_rxfh		= igb_set_rxfh,
 	.get_channels		= igb_get_channels,
 	.set_channels		= igb_set_channels,
+	.get_priv_flags		= igb_get_priv_flags,
+	.set_priv_flags		= igb_set_priv_flags,
 	.begin			= igb_ethtool_begin,
 	.complete		= igb_ethtool_complete,
+	.get_link_ksettings	= igb_get_link_ksettings,
+	.set_link_ksettings	= igb_set_link_ksettings,
 };
 
 void igb_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index be456bae8169..26a821fcd220 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -554,7 +554,7 @@ rx_ring_summary:
 					  16, 1,
 					  page_address(buffer_info->page) +
 						      buffer_info->page_offset,
-					  IGB_RX_BUFSZ, true);
+					  igb_rx_bufsz(rx_ring), true);
 				}
 			}
 		}
@@ -3293,7 +3293,7 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring)
 
 	size = sizeof(struct igb_tx_buffer) * tx_ring->count;
 
-	tx_ring->tx_buffer_info = vzalloc(size);
+	tx_ring->tx_buffer_info = vmalloc(size);
 	if (!tx_ring->tx_buffer_info)
 		goto err;
 
@@ -3404,6 +3404,10 @@ void igb_configure_tx_ring(struct igb_adapter *adapter,
 	txdctl |= IGB_TX_HTHRESH << 8;
 	txdctl |= IGB_TX_WTHRESH << 16;
 
+	/* reinitialize tx_buffer_info */
+	memset(ring->tx_buffer_info, 0,
+	       sizeof(struct igb_tx_buffer) * ring->count);
+
 	txdctl |= E1000_TXDCTL_QUEUE_ENABLE;
 	wr32(E1000_TXDCTL(reg_idx), txdctl);
 }
@@ -3435,7 +3439,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring)
 
 	size = sizeof(struct igb_rx_buffer) * rx_ring->count;
 
-	rx_ring->rx_buffer_info = vzalloc(size);
+	rx_ring->rx_buffer_info = vmalloc(size);
 	if (!rx_ring->rx_buffer_info)
 		goto err;
 
@@ -3720,6 +3724,7 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 			   struct igb_ring *ring)
 {
 	struct e1000_hw *hw = &adapter->hw;
+	union e1000_adv_rx_desc *rx_desc;
 	u64 rdba = ring->dma;
 	int reg_idx = ring->reg_idx;
 	u32 srrctl = 0, rxdctl = 0;
@@ -3741,7 +3746,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 
 	/* set descriptor configuration */
 	srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
-	srrctl |= IGB_RX_BUFSZ >> E1000_SRRCTL_BSIZEPKT_SHIFT;
+	if (ring_uses_large_buffer(ring))
+		srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
+	else
+		srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
 	srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF;
 	if (hw->mac.type >= e1000_82580)
 		srrctl |= E1000_SRRCTL_TIMESTAMP;
@@ -3758,11 +3766,39 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 	rxdctl |= IGB_RX_HTHRESH << 8;
 	rxdctl |= IGB_RX_WTHRESH << 16;
 
+	/* initialize rx_buffer_info */
+	memset(ring->rx_buffer_info, 0,
+	       sizeof(struct igb_rx_buffer) * ring->count);
+
+	/* initialize Rx descriptor 0 */
+	rx_desc = IGB_RX_DESC(ring, 0);
+	rx_desc->wb.upper.length = 0;
+
 	/* enable receive descriptor fetching */
 	rxdctl |= E1000_RXDCTL_QUEUE_ENABLE;
 	wr32(E1000_RXDCTL(reg_idx), rxdctl);
 }
 
+static void igb_set_rx_buffer_len(struct igb_adapter *adapter,
+				  struct igb_ring *rx_ring)
+{
+	/* set build_skb and buffer size flags */
+	clear_ring_build_skb_enabled(rx_ring);
+	clear_ring_uses_large_buffer(rx_ring);
+
+	if (adapter->flags & IGB_FLAG_RX_LEGACY)
+		return;
+
+	set_ring_build_skb_enabled(rx_ring);
+
+#if (PAGE_SIZE < 8192)
+	if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB)
+		return;
+
+	set_ring_uses_large_buffer(rx_ring);
+#endif
+}
+
 /**
  *  igb_configure_rx - Configure receive Unit after Reset
  *  @adapter: board private structure
@@ -3780,8 +3816,12 @@ static void igb_configure_rx(struct igb_adapter *adapter)
 	/* Setup the HW Rx Head and Tail Descriptor Pointers and
 	 * the Base and Length of the Rx Descriptor Ring
 	 */
-	for (i = 0; i < adapter->num_rx_queues; i++)
-		igb_configure_rx_ring(adapter, adapter->rx_ring[i]);
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		struct igb_ring *rx_ring = adapter->rx_ring[i];
+
+		igb_set_rx_buffer_len(adapter, rx_ring);
+		igb_configure_rx_ring(adapter, rx_ring);
+	}
 }
 
 /**
@@ -3822,55 +3862,63 @@ static void igb_free_all_tx_resources(struct igb_adapter *adapter)
 			igb_free_tx_resources(adapter->tx_ring[i]);
 }
 
-void igb_unmap_and_free_tx_resource(struct igb_ring *ring,
-				    struct igb_tx_buffer *tx_buffer)
-{
-	if (tx_buffer->skb) {
-		dev_kfree_skb_any(tx_buffer->skb);
-		if (dma_unmap_len(tx_buffer, len))
-			dma_unmap_single(ring->dev,
-					 dma_unmap_addr(tx_buffer, dma),
-					 dma_unmap_len(tx_buffer, len),
-					 DMA_TO_DEVICE);
-	} else if (dma_unmap_len(tx_buffer, len)) {
-		dma_unmap_page(ring->dev,
-			       dma_unmap_addr(tx_buffer, dma),
-			       dma_unmap_len(tx_buffer, len),
-			       DMA_TO_DEVICE);
-	}
-	tx_buffer->next_to_watch = NULL;
-	tx_buffer->skb = NULL;
-	dma_unmap_len_set(tx_buffer, len, 0);
-	/* buffer_info must be completely set up in the transmit path */
-}
-
 /**
  *  igb_clean_tx_ring - Free Tx Buffers
  *  @tx_ring: ring to be cleaned
  **/
 static void igb_clean_tx_ring(struct igb_ring *tx_ring)
 {
-	struct igb_tx_buffer *buffer_info;
-	unsigned long size;
-	u16 i;
+	u16 i = tx_ring->next_to_clean;
+	struct igb_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i];
 
-	if (!tx_ring->tx_buffer_info)
-		return;
-	/* Free all the Tx ring sk_buffs */
+	while (i != tx_ring->next_to_use) {
+		union e1000_adv_tx_desc *eop_desc, *tx_desc;
 
-	for (i = 0; i < tx_ring->count; i++) {
-		buffer_info = &tx_ring->tx_buffer_info[i];
-		igb_unmap_and_free_tx_resource(tx_ring, buffer_info);
-	}
+		/* Free all the Tx ring sk_buffs */
+		dev_kfree_skb_any(tx_buffer->skb);
 
-	netdev_tx_reset_queue(txring_txq(tx_ring));
+		/* unmap skb header data */
+		dma_unmap_single(tx_ring->dev,
+				 dma_unmap_addr(tx_buffer, dma),
+				 dma_unmap_len(tx_buffer, len),
+				 DMA_TO_DEVICE);
 
-	size = sizeof(struct igb_tx_buffer) * tx_ring->count;
-	memset(tx_ring->tx_buffer_info, 0, size);
+		/* check for eop_desc to determine the end of the packet */
+		eop_desc = tx_buffer->next_to_watch;
+		tx_desc = IGB_TX_DESC(tx_ring, i);
+
+		/* unmap remaining buffers */
+		while (tx_desc != eop_desc) {
+			tx_buffer++;
+			tx_desc++;
+			i++;
+			if (unlikely(i == tx_ring->count)) {
+				i = 0;
+				tx_buffer = tx_ring->tx_buffer_info;
+				tx_desc = IGB_TX_DESC(tx_ring, 0);
+			}
+
+			/* unmap any remaining paged data */
+			if (dma_unmap_len(tx_buffer, len))
+				dma_unmap_page(tx_ring->dev,
+					       dma_unmap_addr(tx_buffer, dma),
+					       dma_unmap_len(tx_buffer, len),
+					       DMA_TO_DEVICE);
+		}
 
-	/* Zero out the descriptor ring */
-	memset(tx_ring->desc, 0, tx_ring->size);
+		/* move us one more past the eop_desc for start of next pkt */
+		tx_buffer++;
+		i++;
+		if (unlikely(i == tx_ring->count)) {
+			i = 0;
+			tx_buffer = tx_ring->tx_buffer_info;
+		}
+	}
 
+	/* reset BQL for queue */
+	netdev_tx_reset_queue(txring_txq(tx_ring));
+
+	/* reset next_to_use and next_to_clean */
 	tx_ring->next_to_use = 0;
 	tx_ring->next_to_clean = 0;
 }
@@ -3932,50 +3980,39 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter)
  **/
 static void igb_clean_rx_ring(struct igb_ring *rx_ring)
 {
-	unsigned long size;
-	u16 i;
+	u16 i = rx_ring->next_to_clean;
 
 	if (rx_ring->skb)
 		dev_kfree_skb(rx_ring->skb);
 	rx_ring->skb = NULL;
 
-	if (!rx_ring->rx_buffer_info)
-		return;
-
 	/* Free all the Rx ring sk_buffs */
-	for (i = 0; i < rx_ring->count; i++) {
+	while (i != rx_ring->next_to_alloc) {
 		struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i];
 
-		if (!buffer_info->page)
-			continue;
-
 		/* Invalidate cache lines that may have been written to by
 		 * device so that we avoid corrupting memory.
 		 */
 		dma_sync_single_range_for_cpu(rx_ring->dev,
 					      buffer_info->dma,
 					      buffer_info->page_offset,
-					      IGB_RX_BUFSZ,
+					      igb_rx_bufsz(rx_ring),
 					      DMA_FROM_DEVICE);
 
 		/* free resources associated with mapping */
 		dma_unmap_page_attrs(rx_ring->dev,
 				     buffer_info->dma,
-				     PAGE_SIZE,
+				     igb_rx_pg_size(rx_ring),
 				     DMA_FROM_DEVICE,
-				     DMA_ATTR_SKIP_CPU_SYNC);
+				     IGB_RX_DMA_ATTR);
 		__page_frag_cache_drain(buffer_info->page,
 					buffer_info->pagecnt_bias);
 
-		buffer_info->page = NULL;
+		i++;
+		if (i == rx_ring->count)
+			i = 0;
 	}
 
-	size = sizeof(struct igb_rx_buffer) * rx_ring->count;
-	memset(rx_ring->rx_buffer_info, 0, size);
-
-	/* Zero out the descriptor ring */
-	memset(rx_ring->desc, 0, rx_ring->size);
-
 	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
@@ -4240,7 +4277,7 @@ static void igb_set_rx_mode(struct net_device *netdev)
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
 	unsigned int vfn = adapter->vfs_allocated_count;
-	u32 rctl = 0, vmolr = 0;
+	u32 rctl = 0, vmolr = 0, rlpml = MAX_JUMBO_FRAME_SIZE;
 	int count;
 
 	/* Check for Promiscuous and All Multicast modes */
@@ -4298,6 +4335,14 @@ static void igb_set_rx_mode(struct net_device *netdev)
 				     E1000_RCTL_VFE);
 	wr32(E1000_RCTL, rctl);
 
+#if (PAGE_SIZE < 8192)
+	if (!adapter->vfs_allocated_count) {
+		if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB)
+			rlpml = IGB_MAX_FRAME_BUILD_SKB;
+	}
+#endif
+	wr32(E1000_RLPML, rlpml);
+
 	/* In order to support SR-IOV and eventually VMDq it is necessary to set
 	 * the VMOLR to enable the appropriate modes.  Without this workaround
 	 * we will have issues with VLAN tag stripping not being done for frames
@@ -4312,12 +4357,17 @@ static void igb_set_rx_mode(struct net_device *netdev)
 	vmolr |= rd32(E1000_VMOLR(vfn)) &
 		 ~(E1000_VMOLR_ROPE | E1000_VMOLR_MPME | E1000_VMOLR_ROMPE);
 
-	/* enable Rx jumbo frames, no need for restriction */
+	/* enable Rx jumbo frames, restrict as needed to support build_skb */
 	vmolr &= ~E1000_VMOLR_RLPML_MASK;
-	vmolr |= MAX_JUMBO_FRAME_SIZE | E1000_VMOLR_LPE;
+#if (PAGE_SIZE < 8192)
+	if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB)
+		vmolr |= IGB_MAX_FRAME_BUILD_SKB;
+	else
+#endif
+		vmolr |= MAX_JUMBO_FRAME_SIZE;
+	vmolr |= E1000_VMOLR_LPE;
 
 	wr32(E1000_VMOLR(vfn), vmolr);
-	wr32(E1000_RLPML, MAX_JUMBO_FRAME_SIZE);
 
 	igb_restore_vf_multicasts(adapter);
 }
@@ -5256,18 +5306,32 @@ static void igb_tx_map(struct igb_ring *tx_ring,
 
 dma_error:
 	dev_err(tx_ring->dev, "TX DMA map failed\n");
+	tx_buffer = &tx_ring->tx_buffer_info[i];
 
 	/* clear dma mappings for failed tx_buffer_info map */
-	for (;;) {
+	while (tx_buffer != first) {
+		if (dma_unmap_len(tx_buffer, len))
+			dma_unmap_page(tx_ring->dev,
+				       dma_unmap_addr(tx_buffer, dma),
+				       dma_unmap_len(tx_buffer, len),
+				       DMA_TO_DEVICE);
+		dma_unmap_len_set(tx_buffer, len, 0);
+
+		if (i--)
+			i += tx_ring->count;
 		tx_buffer = &tx_ring->tx_buffer_info[i];
-		igb_unmap_and_free_tx_resource(tx_ring, tx_buffer);
-		if (tx_buffer == first)
-			break;
-		if (i == 0)
-			i = tx_ring->count;
-		i--;
 	}
 
+	if (dma_unmap_len(tx_buffer, len))
+		dma_unmap_single(tx_ring->dev,
+				 dma_unmap_addr(tx_buffer, dma),
+				 dma_unmap_len(tx_buffer, len),
+				 DMA_TO_DEVICE);
+	dma_unmap_len_set(tx_buffer, len, 0);
+
+	dev_kfree_skb_any(tx_buffer->skb);
+	tx_buffer->skb = NULL;
+
 	tx_ring->next_to_use = i;
 }
 
@@ -5339,7 +5403,8 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 
 out_drop:
-	igb_unmap_and_free_tx_resource(tx_ring, first);
+	dev_kfree_skb_any(first->skb);
+	first->skb = NULL;
 
 	return NETDEV_TX_OK;
 }
@@ -6686,7 +6751,6 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget)
 				 DMA_TO_DEVICE);
 
 		/* clear tx_buffer data */
-		tx_buffer->skb = NULL;
 		dma_unmap_len_set(tx_buffer, len, 0);
 
 		/* clear last DMA location and unmap remaining buffers */
@@ -6822,8 +6886,14 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring,
 	nta++;
 	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
 
-	/* transfer page from old buffer to new buffer */
-	*new_buff = *old_buff;
+	/* Transfer page from old buffer to new buffer.
+	 * Move each member individually to avoid possible store
+	 * forwarding stalls.
+	 */
+	new_buff->dma		= old_buff->dma;
+	new_buff->page		= old_buff->page;
+	new_buff->page_offset	= old_buff->page_offset;
+	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
 }
 
 static inline bool igb_page_is_reserved(struct page *page)
@@ -6831,11 +6901,10 @@ static inline bool igb_page_is_reserved(struct page *page)
 	return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page);
 }
 
-static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
-				  struct page *page,
-				  unsigned int truesize)
+static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer)
 {
-	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias--;
+	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
+	struct page *page = rx_buffer->page;
 
 	/* avoid re-using remote pages */
 	if (unlikely(igb_page_is_reserved(page)))
@@ -6843,16 +6912,13 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
 
 #if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
-	if (unlikely(page_ref_count(page) != pagecnt_bias))
+	if (unlikely((page_ref_count(page) - pagecnt_bias) > 1))
 		return false;
-
-	/* flip page offset to other buffer */
-	rx_buffer->page_offset ^= IGB_RX_BUFSZ;
 #else
-	/* move offset up to the next cache line */
-	rx_buffer->page_offset += truesize;
+#define IGB_LAST_OFFSET \
+	(SKB_WITH_OVERHEAD(PAGE_SIZE) - IGB_RXBUFFER_2048)
 
-	if (rx_buffer->page_offset > (PAGE_SIZE - IGB_RX_BUFSZ))
+	if (rx_buffer->page_offset > IGB_LAST_OFFSET)
 		return false;
 #endif
 
@@ -6860,7 +6926,7 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
 	 * the pagecnt_bias and page count so that we fully restock the
 	 * number of references the driver holds.
 	 */
-	if (unlikely(pagecnt_bias == 1)) {
+	if (unlikely(!pagecnt_bias)) {
 		page_ref_add(page, USHRT_MAX);
 		rx_buffer->pagecnt_bias = USHRT_MAX;
 	}
@@ -6872,34 +6938,56 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
  *  igb_add_rx_frag - Add contents of Rx buffer to sk_buff
  *  @rx_ring: rx descriptor ring to transact packets on
  *  @rx_buffer: buffer containing page to add
- *  @rx_desc: descriptor containing length of buffer written by hardware
  *  @skb: sk_buff to place the data into
+ *  @size: size of buffer to be added
  *
  *  This function will add the data contained in rx_buffer->page to the skb.
- *  This is done either through a direct copy if the data in the buffer is
- *  less than the skb header size, otherwise it will just attach the page as
- *  a frag to the skb.
- *
- *  The function will then update the page offset if necessary and return
- *  true if the buffer can be reused by the adapter.
  **/
-static bool igb_add_rx_frag(struct igb_ring *rx_ring,
+static void igb_add_rx_frag(struct igb_ring *rx_ring,
 			    struct igb_rx_buffer *rx_buffer,
-			    unsigned int size,
-			    union e1000_adv_rx_desc *rx_desc,
-			    struct sk_buff *skb)
+			    struct sk_buff *skb,
+			    unsigned int size)
 {
-	struct page *page = rx_buffer->page;
-	unsigned char *va = page_address(page) + rx_buffer->page_offset;
 #if (PAGE_SIZE < 8192)
-	unsigned int truesize = IGB_RX_BUFSZ;
+	unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
+#else
+	unsigned int truesize = ring_uses_build_skb(rx_ring) ?
+				SKB_DATA_ALIGN(IGB_SKB_PAD + size) :
+				SKB_DATA_ALIGN(size);
+#endif
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
+			rx_buffer->page_offset, size, truesize);
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
+}
+
+static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
+					 struct igb_rx_buffer *rx_buffer,
+					 union e1000_adv_rx_desc *rx_desc,
+					 unsigned int size)
+{
+	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
 #else
 	unsigned int truesize = SKB_DATA_ALIGN(size);
 #endif
-	unsigned int pull_len;
+	unsigned int headlen;
+	struct sk_buff *skb;
 
-	if (unlikely(skb_is_nonlinear(skb)))
-		goto add_tail_frag;
+	/* prefetch first cache line of first page */
+	prefetch(va);
+#if L1_CACHE_BYTES < 128
+	prefetch(va + L1_CACHE_BYTES);
+#endif
+
+	/* allocate a skb to store the frags */
+	skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN);
+	if (unlikely(!skb))
+		return NULL;
 
 	if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) {
 		igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb);
@@ -6907,95 +6995,73 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring,
 		size -= IGB_TS_HDR_LEN;
 	}
 
-	if (likely(size <= IGB_RX_HDR_LEN)) {
-		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
-
-		/* page is not reserved, we can reuse buffer as-is */
-		if (likely(!igb_page_is_reserved(page)))
-			return true;
-
-		/* this page cannot be reused so discard it */
-		return false;
-	}
-
-	/* we need the header to contain the greater of either ETH_HLEN or
-	 * 60 bytes if the skb->len is less than 60 for skb_pad.
-	 */
-	pull_len = eth_get_headlen(va, IGB_RX_HDR_LEN);
+	/* Determine available headroom for copy */
+	headlen = size;
+	if (headlen > IGB_RX_HDR_LEN)
+		headlen = eth_get_headlen(va, IGB_RX_HDR_LEN);
 
 	/* align pull length to size of long to optimize memcpy performance */
-	memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
+	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
 
 	/* update all of the pointers */
-	va += pull_len;
-	size -= pull_len;
-
-add_tail_frag:
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
-			(unsigned long)va & ~PAGE_MASK, size, truesize);
+	size -= headlen;
+	if (size) {
+		skb_add_rx_frag(skb, 0, rx_buffer->page,
+				(va + headlen) - page_address(rx_buffer->page),
+				size, truesize);
+#if (PAGE_SIZE < 8192)
+		rx_buffer->page_offset ^= truesize;
+#else
+		rx_buffer->page_offset += truesize;
+#endif
+	} else {
+		rx_buffer->pagecnt_bias++;
+	}
 
-	return igb_can_reuse_rx_page(rx_buffer, page, truesize);
+	return skb;
 }
 
-static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring,
-					   union e1000_adv_rx_desc *rx_desc,
-					   struct sk_buff *skb)
+static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring,
+				     struct igb_rx_buffer *rx_buffer,
+				     union e1000_adv_rx_desc *rx_desc,
+				     unsigned int size)
 {
-	unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
-	struct igb_rx_buffer *rx_buffer;
-	struct page *page;
-
-	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
-	page = rx_buffer->page;
-	prefetchw(page);
-
-	/* we are reusing so sync this buffer for CPU use */
-	dma_sync_single_range_for_cpu(rx_ring->dev,
-				      rx_buffer->dma,
-				      rx_buffer->page_offset,
-				      size,
-				      DMA_FROM_DEVICE);
-
-	if (likely(!skb)) {
-		void *page_addr = page_address(page) +
-				  rx_buffer->page_offset;
+	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
+				SKB_DATA_ALIGN(IGB_SKB_PAD + size);
+#endif
+	struct sk_buff *skb;
 
-		/* prefetch first cache line of first page */
-		prefetch(page_addr);
+	/* prefetch first cache line of first page */
+	prefetch(va);
 #if L1_CACHE_BYTES < 128
-		prefetch(page_addr + L1_CACHE_BYTES);
+	prefetch(va + L1_CACHE_BYTES);
 #endif
 
-		/* allocate a skb to store the frags */
-		skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN);
-		if (unlikely(!skb)) {
-			rx_ring->rx_stats.alloc_failed++;
-			return NULL;
-		}
+	/* build an skb around the page buffer */
+	skb = build_skb(va - IGB_SKB_PAD, truesize);
+	if (unlikely(!skb))
+		return NULL;
 
-		/* we will be copying header into skb->data in
-		 * pskb_may_pull so it is in our interest to prefetch
-		 * it now to avoid a possible cache miss
-		 */
-		prefetchw(skb->data);
-	}
+	/* update pointers within the skb to store the data */
+	skb_reserve(skb, IGB_SKB_PAD);
+	__skb_put(skb, size);
 
-	/* pull page into skb */
-	if (igb_add_rx_frag(rx_ring, rx_buffer, size, rx_desc, skb)) {
-		/* hand second half of page back to the ring */
-		igb_reuse_rx_page(rx_ring, rx_buffer);
-	} else {
-		/* We are not reusing the buffer so unmap it and free
-		 * any references we are holding to it
-		 */
-		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
-				     PAGE_SIZE, DMA_FROM_DEVICE,
-				     DMA_ATTR_SKIP_CPU_SYNC);
-		__page_frag_cache_drain(page, rx_buffer->pagecnt_bias);
+	/* pull timestamp out of packet data */
+	if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
+		igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb);
+		__skb_pull(skb, IGB_TS_HDR_LEN);
 	}
 
-	/* clear contents of rx_buffer */
-	rx_buffer->page = NULL;
+	/* update buffer offset */
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
 
 	return skb;
 }
@@ -7154,6 +7220,47 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring,
 	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 }
 
+static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring,
+					       const unsigned int size)
+{
+	struct igb_rx_buffer *rx_buffer;
+
+	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
+	prefetchw(rx_buffer->page);
+
+	/* we are reusing so sync this buffer for CPU use */
+	dma_sync_single_range_for_cpu(rx_ring->dev,
+				      rx_buffer->dma,
+				      rx_buffer->page_offset,
+				      size,
+				      DMA_FROM_DEVICE);
+
+	rx_buffer->pagecnt_bias--;
+
+	return rx_buffer;
+}
+
+static void igb_put_rx_buffer(struct igb_ring *rx_ring,
+			      struct igb_rx_buffer *rx_buffer)
+{
+	if (igb_can_reuse_rx_page(rx_buffer)) {
+		/* hand second half of page back to the ring */
+		igb_reuse_rx_page(rx_ring, rx_buffer);
+	} else {
+		/* We are not reusing the buffer so unmap it and free
+		 * any references we are holding to it
+		 */
+		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
+				     igb_rx_pg_size(rx_ring), DMA_FROM_DEVICE,
+				     IGB_RX_DMA_ATTR);
+		__page_frag_cache_drain(rx_buffer->page,
+					rx_buffer->pagecnt_bias);
+	}
+
+	/* clear contents of rx_buffer */
+	rx_buffer->page = NULL;
+}
+
 static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 {
 	struct igb_ring *rx_ring = q_vector->rx.ring;
@@ -7163,6 +7270,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 
 	while (likely(total_packets < budget)) {
 		union e1000_adv_rx_desc *rx_desc;
+		struct igb_rx_buffer *rx_buffer;
+		unsigned int size;
 
 		/* return some buffers to hardware, one at a time is too slow */
 		if (cleaned_count >= IGB_RX_BUFFER_WRITE) {
@@ -7171,8 +7280,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 		}
 
 		rx_desc = IGB_RX_DESC(rx_ring, rx_ring->next_to_clean);
-
-		if (!rx_desc->wb.upper.status_error)
+		size = le16_to_cpu(rx_desc->wb.upper.length);
+		if (!size)
 			break;
 
 		/* This memory barrier is needed to keep us from reading
@@ -7181,13 +7290,25 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 		 */
 		dma_rmb();
 
+		rx_buffer = igb_get_rx_buffer(rx_ring, size);
+
 		/* retrieve a buffer from the ring */
-		skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb);
+		if (skb)
+			igb_add_rx_frag(rx_ring, rx_buffer, skb, size);
+		else if (ring_uses_build_skb(rx_ring))
+			skb = igb_build_skb(rx_ring, rx_buffer, rx_desc, size);
+		else
+			skb = igb_construct_skb(rx_ring, rx_buffer,
+						rx_desc, size);
 
 		/* exit if we failed to retrieve a buffer */
-		if (!skb)
+		if (!skb) {
+			rx_ring->rx_stats.alloc_failed++;
+			rx_buffer->pagecnt_bias++;
 			break;
+		}
 
+		igb_put_rx_buffer(rx_ring, rx_buffer);
 		cleaned_count++;
 
 		/* fetch next buffer in frame if non-eop */
@@ -7231,6 +7352,11 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 	return total_packets;
 }
 
+static inline unsigned int igb_rx_offset(struct igb_ring *rx_ring)
+{
+	return ring_uses_build_skb(rx_ring) ? IGB_SKB_PAD : 0;
+}
+
 static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 				  struct igb_rx_buffer *bi)
 {
@@ -7242,21 +7368,23 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 		return true;
 
 	/* alloc new page for storage */
-	page = dev_alloc_page();
+	page = dev_alloc_pages(igb_rx_pg_order(rx_ring));
 	if (unlikely(!page)) {
 		rx_ring->rx_stats.alloc_failed++;
 		return false;
 	}
 
 	/* map page for use */
-	dma = dma_map_page_attrs(rx_ring->dev, page, 0, PAGE_SIZE,
-				 DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+	dma = dma_map_page_attrs(rx_ring->dev, page, 0,
+				 igb_rx_pg_size(rx_ring),
+				 DMA_FROM_DEVICE,
+				 IGB_RX_DMA_ATTR);
 
 	/* if mapping failed free memory back to system since
 	 * there isn't much point in holding memory we can't use
 	 */
 	if (dma_mapping_error(rx_ring->dev, dma)) {
-		__free_page(page);
+		__free_pages(page, igb_rx_pg_order(rx_ring));
 
 		rx_ring->rx_stats.alloc_failed++;
 		return false;
@@ -7264,7 +7392,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 
 	bi->dma = dma;
 	bi->page = page;
-	bi->page_offset = 0;
+	bi->page_offset = igb_rx_offset(rx_ring);
 	bi->pagecnt_bias = 1;
 
 	return true;
@@ -7279,6 +7407,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
 	union e1000_adv_rx_desc *rx_desc;
 	struct igb_rx_buffer *bi;
 	u16 i = rx_ring->next_to_use;
+	u16 bufsz;
 
 	/* nothing to do */
 	if (!cleaned_count)
@@ -7288,14 +7417,15 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
 	bi = &rx_ring->rx_buffer_info[i];
 	i -= rx_ring->count;
 
+	bufsz = igb_rx_bufsz(rx_ring);
+
 	do {
 		if (!igb_alloc_mapped_page(rx_ring, bi))
 			break;
 
 		/* sync the buffer for use by the device */
 		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
-						 bi->page_offset,
-						 IGB_RX_BUFSZ,
+						 bi->page_offset, bufsz,
 						 DMA_FROM_DEVICE);
 
 		/* Refresh the desc even if buffer_addrs didn't change
@@ -7312,8 +7442,8 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
 			i -= rx_ring->count;
 		}
 
-		/* clear the status bits for the next_to_use descriptor */
-		rx_desc->wb.upper.status_error = 0;
+		/* clear the length for the next_to_use descriptor */
+		rx_desc->wb.upper.length = 0;
 
 		cleaned_count--;
 	} while (cleaned_count);
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index c4477552ce9e..7a3fd4d74592 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -764,8 +764,7 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
  * incoming frame.  The value is stored in little endian format starting on
  * byte 8.
  **/
-void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector,
-			 unsigned char *va,
+void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 			 struct sk_buff *skb)
 {
 	__le64 *regval = (__le64 *)va;
diff --git a/drivers/net/ethernet/intel/igbvf/ethtool.c b/drivers/net/ethernet/intel/igbvf/ethtool.c
index 8dea1b1367ef..34faa113a8a0 100644
--- a/drivers/net/ethernet/intel/igbvf/ethtool.c
+++ b/drivers/net/ethernet/intel/igbvf/ethtool.c
@@ -71,45 +71,45 @@ static const char igbvf_gstrings_test[][ETH_GSTRING_LEN] = {
 
 #define IGBVF_TEST_LEN ARRAY_SIZE(igbvf_gstrings_test)
 
-static int igbvf_get_settings(struct net_device *netdev,
-			      struct ethtool_cmd *ecmd)
+static int igbvf_get_link_ksettings(struct net_device *netdev,
+				    struct ethtool_link_ksettings *cmd)
 {
 	struct igbvf_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
 	u32 status;
 
-	ecmd->supported   = SUPPORTED_1000baseT_Full;
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full);
+	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full);
 
-	ecmd->advertising = ADVERTISED_1000baseT_Full;
-
-	ecmd->port = -1;
-	ecmd->transceiver = XCVR_DUMMY1;
+	cmd->base.port = -1;
 
 	status = er32(STATUS);
 	if (status & E1000_STATUS_LU) {
 		if (status & E1000_STATUS_SPEED_1000)
-			ethtool_cmd_speed_set(ecmd, SPEED_1000);
+			cmd->base.speed = SPEED_1000;
 		else if (status & E1000_STATUS_SPEED_100)
-			ethtool_cmd_speed_set(ecmd, SPEED_100);
+			cmd->base.speed = SPEED_100;
 		else
-			ethtool_cmd_speed_set(ecmd, SPEED_10);
+			cmd->base.speed = SPEED_10;
 
 		if (status & E1000_STATUS_FD)
-			ecmd->duplex = DUPLEX_FULL;
+			cmd->base.duplex = DUPLEX_FULL;
 		else
-			ecmd->duplex = DUPLEX_HALF;
+			cmd->base.duplex = DUPLEX_HALF;
 	} else {
-		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
-		ecmd->duplex = DUPLEX_UNKNOWN;
+		cmd->base.speed = SPEED_UNKNOWN;
+		cmd->base.duplex = DUPLEX_UNKNOWN;
 	}
 
-	ecmd->autoneg = AUTONEG_DISABLE;
+	cmd->base.autoneg = AUTONEG_DISABLE;
 
 	return 0;
 }
 
-static int igbvf_set_settings(struct net_device *netdev,
-			      struct ethtool_cmd *ecmd)
+static int igbvf_set_link_ksettings(struct net_device *netdev,
+				    const struct ethtool_link_ksettings *cmd)
 {
 	return -EOPNOTSUPP;
 }
@@ -443,8 +443,6 @@ static void igbvf_get_strings(struct net_device *netdev, u32 stringset,
 }
 
 static const struct ethtool_ops igbvf_ethtool_ops = {
-	.get_settings		= igbvf_get_settings,
-	.set_settings		= igbvf_set_settings,
 	.get_drvinfo		= igbvf_get_drvinfo,
 	.get_regs_len		= igbvf_get_regs_len,
 	.get_regs		= igbvf_get_regs,
@@ -467,6 +465,8 @@ static const struct ethtool_ops igbvf_ethtool_ops = {
 	.get_ethtool_stats	= igbvf_get_ethtool_stats,
 	.get_coalesce		= igbvf_get_coalesce,
 	.set_coalesce		= igbvf_set_coalesce,
+	.get_link_ksettings	= igbvf_get_link_ksettings,
+	.set_link_ksettings	= igbvf_set_link_ksettings,
 };
 
 void igbvf_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
index e5d72559cca9..d10a0d242dda 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
@@ -94,24 +94,30 @@ static struct ixgb_stats ixgb_gstrings_stats[] = {
 #define IXGB_STATS_LEN	ARRAY_SIZE(ixgb_gstrings_stats)
 
 static int
-ixgb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+ixgb_get_link_ksettings(struct net_device *netdev,
+			struct ethtool_link_ksettings *cmd)
 {
 	struct ixgb_adapter *adapter = netdev_priv(netdev);
 
-	ecmd->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE);
-	ecmd->advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_FIBRE);
-	ecmd->port = PORT_FIBRE;
-	ecmd->transceiver = XCVR_EXTERNAL;
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+
+	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 10000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE);
+
+	cmd->base.port = PORT_FIBRE;
 
 	if (netif_carrier_ok(adapter->netdev)) {
-		ethtool_cmd_speed_set(ecmd, SPEED_10000);
-		ecmd->duplex = DUPLEX_FULL;
+		cmd->base.speed = SPEED_10000;
+		cmd->base.duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
-		ecmd->duplex = DUPLEX_UNKNOWN;
+		cmd->base.speed = SPEED_UNKNOWN;
+		cmd->base.duplex = DUPLEX_UNKNOWN;
 	}
 
-	ecmd->autoneg = AUTONEG_DISABLE;
+	cmd->base.autoneg = AUTONEG_DISABLE;
 	return 0;
 }
 
@@ -126,13 +132,14 @@ void ixgb_set_speed_duplex(struct net_device *netdev)
 }
 
 static int
-ixgb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+ixgb_set_link_ksettings(struct net_device *netdev,
+			const struct ethtool_link_ksettings *cmd)
 {
 	struct ixgb_adapter *adapter = netdev_priv(netdev);
-	u32 speed = ethtool_cmd_speed(ecmd);
+	u32 speed = cmd->base.speed;
 
-	if (ecmd->autoneg == AUTONEG_ENABLE ||
-	    (speed + ecmd->duplex != SPEED_10000 + DUPLEX_FULL))
+	if (cmd->base.autoneg == AUTONEG_ENABLE ||
+	    (speed + cmd->base.duplex != SPEED_10000 + DUPLEX_FULL))
 		return -EINVAL;
 
 	if (netif_running(adapter->netdev)) {
@@ -630,8 +637,6 @@ ixgb_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 }
 
 static const struct ethtool_ops ixgb_ethtool_ops = {
-	.get_settings = ixgb_get_settings,
-	.set_settings = ixgb_set_settings,
 	.get_drvinfo = ixgb_get_drvinfo,
 	.get_regs_len = ixgb_get_regs_len,
 	.get_regs = ixgb_get_regs,
@@ -649,6 +654,8 @@ static const struct ethtool_ops ixgb_ethtool_ops = {
 	.set_phys_id = ixgb_set_phys_id,
 	.get_sset_count = ixgb_get_sset_count,
 	.get_ethtool_stats = ixgb_get_ethtool_stats,
+	.get_link_ksettings = ixgb_get_link_ksettings,
+	.set_link_ksettings = ixgb_set_link_ksettings,
 };
 
 void ixgb_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 90fa5bf23d1b..0da0752fedef 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -186,60 +186,62 @@ static u32 ixgbe_get_supported_10gtypes(struct ixgbe_hw *hw)
 	}
 }
 
-static int ixgbe_get_settings(struct net_device *netdev,
-			      struct ethtool_cmd *ecmd)
+static int ixgbe_get_link_ksettings(struct net_device *netdev,
+				    struct ethtool_link_ksettings *cmd)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	ixgbe_link_speed supported_link;
 	bool autoneg = false;
+	u32 supported, advertising;
+
+	ethtool_convert_link_mode_to_legacy_u32(&supported,
+						cmd->link_modes.supported);
 
 	hw->mac.ops.get_link_capabilities(hw, &supported_link, &autoneg);
 
 	/* set the supported link speeds */
 	if (supported_link & IXGBE_LINK_SPEED_10GB_FULL)
-		ecmd->supported |= ixgbe_get_supported_10gtypes(hw);
+		supported |= ixgbe_get_supported_10gtypes(hw);
 	if (supported_link & IXGBE_LINK_SPEED_1GB_FULL)
-		ecmd->supported |= (ixgbe_isbackplane(hw->phy.media_type)) ?
+		supported |= (ixgbe_isbackplane(hw->phy.media_type)) ?
 				   SUPPORTED_1000baseKX_Full :
 				   SUPPORTED_1000baseT_Full;
 	if (supported_link & IXGBE_LINK_SPEED_100_FULL)
-		ecmd->supported |= SUPPORTED_100baseT_Full;
+		supported |= SUPPORTED_100baseT_Full;
 	if (supported_link & IXGBE_LINK_SPEED_10_FULL)
-		ecmd->supported |= SUPPORTED_10baseT_Full;
+		supported |= SUPPORTED_10baseT_Full;
 
 	/* default advertised speed if phy.autoneg_advertised isn't set */
-	ecmd->advertising = ecmd->supported;
+	advertising = supported;
 	/* set the advertised speeds */
 	if (hw->phy.autoneg_advertised) {
-		ecmd->advertising = 0;
+		advertising = 0;
 		if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10_FULL)
-			ecmd->advertising |= ADVERTISED_10baseT_Full;
+			advertising |= ADVERTISED_10baseT_Full;
 		if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL)
-			ecmd->advertising |= ADVERTISED_100baseT_Full;
+			advertising |= ADVERTISED_100baseT_Full;
 		if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL)
-			ecmd->advertising |= ecmd->supported & ADVRTSD_MSK_10G;
+			advertising |= supported & ADVRTSD_MSK_10G;
 		if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) {
-			if (ecmd->supported & SUPPORTED_1000baseKX_Full)
-				ecmd->advertising |= ADVERTISED_1000baseKX_Full;
+			if (supported & SUPPORTED_1000baseKX_Full)
+				advertising |= ADVERTISED_1000baseKX_Full;
 			else
-				ecmd->advertising |= ADVERTISED_1000baseT_Full;
+				advertising |= ADVERTISED_1000baseT_Full;
 		}
 	} else {
 		if (hw->phy.multispeed_fiber && !autoneg) {
 			if (supported_link & IXGBE_LINK_SPEED_10GB_FULL)
-				ecmd->advertising = ADVERTISED_10000baseT_Full;
+				advertising = ADVERTISED_10000baseT_Full;
 		}
 	}
 
 	if (autoneg) {
-		ecmd->supported |= SUPPORTED_Autoneg;
-		ecmd->advertising |= ADVERTISED_Autoneg;
-		ecmd->autoneg = AUTONEG_ENABLE;
+		supported |= SUPPORTED_Autoneg;
+		advertising |= ADVERTISED_Autoneg;
+		cmd->base.autoneg = AUTONEG_ENABLE;
 	} else
-		ecmd->autoneg = AUTONEG_DISABLE;
-
-	ecmd->transceiver = XCVR_EXTERNAL;
+		cmd->base.autoneg = AUTONEG_DISABLE;
 
 	/* Determine the remaining settings based on the PHY type. */
 	switch (adapter->hw.phy.type) {
@@ -248,14 +250,14 @@ static int ixgbe_get_settings(struct net_device *netdev,
 	case ixgbe_phy_x550em_ext_t:
 	case ixgbe_phy_fw:
 	case ixgbe_phy_cu_unknown:
-		ecmd->supported |= SUPPORTED_TP;
-		ecmd->advertising |= ADVERTISED_TP;
-		ecmd->port = PORT_TP;
+		supported |= SUPPORTED_TP;
+		advertising |= ADVERTISED_TP;
+		cmd->base.port = PORT_TP;
 		break;
 	case ixgbe_phy_qt:
-		ecmd->supported |= SUPPORTED_FIBRE;
-		ecmd->advertising |= ADVERTISED_FIBRE;
-		ecmd->port = PORT_FIBRE;
+		supported |= SUPPORTED_FIBRE;
+		advertising |= ADVERTISED_FIBRE;
+		cmd->base.port = PORT_FIBRE;
 		break;
 	case ixgbe_phy_nl:
 	case ixgbe_phy_sfp_passive_tyco:
@@ -273,9 +275,9 @@ static int ixgbe_get_settings(struct net_device *netdev,
 		case ixgbe_sfp_type_da_cu:
 		case ixgbe_sfp_type_da_cu_core0:
 		case ixgbe_sfp_type_da_cu_core1:
-			ecmd->supported |= SUPPORTED_FIBRE;
-			ecmd->advertising |= ADVERTISED_FIBRE;
-			ecmd->port = PORT_DA;
+			supported |= SUPPORTED_FIBRE;
+			advertising |= ADVERTISED_FIBRE;
+			cmd->base.port = PORT_DA;
 			break;
 		case ixgbe_sfp_type_sr:
 		case ixgbe_sfp_type_lr:
@@ -285,102 +287,113 @@ static int ixgbe_get_settings(struct net_device *netdev,
 		case ixgbe_sfp_type_1g_sx_core1:
 		case ixgbe_sfp_type_1g_lx_core0:
 		case ixgbe_sfp_type_1g_lx_core1:
-			ecmd->supported |= SUPPORTED_FIBRE;
-			ecmd->advertising |= ADVERTISED_FIBRE;
-			ecmd->port = PORT_FIBRE;
+			supported |= SUPPORTED_FIBRE;
+			advertising |= ADVERTISED_FIBRE;
+			cmd->base.port = PORT_FIBRE;
 			break;
 		case ixgbe_sfp_type_not_present:
-			ecmd->supported |= SUPPORTED_FIBRE;
-			ecmd->advertising |= ADVERTISED_FIBRE;
-			ecmd->port = PORT_NONE;
+			supported |= SUPPORTED_FIBRE;
+			advertising |= ADVERTISED_FIBRE;
+			cmd->base.port = PORT_NONE;
 			break;
 		case ixgbe_sfp_type_1g_cu_core0:
 		case ixgbe_sfp_type_1g_cu_core1:
-			ecmd->supported |= SUPPORTED_TP;
-			ecmd->advertising |= ADVERTISED_TP;
-			ecmd->port = PORT_TP;
+			supported |= SUPPORTED_TP;
+			advertising |= ADVERTISED_TP;
+			cmd->base.port = PORT_TP;
 			break;
 		case ixgbe_sfp_type_unknown:
 		default:
-			ecmd->supported |= SUPPORTED_FIBRE;
-			ecmd->advertising |= ADVERTISED_FIBRE;
-			ecmd->port = PORT_OTHER;
+			supported |= SUPPORTED_FIBRE;
+			advertising |= ADVERTISED_FIBRE;
+			cmd->base.port = PORT_OTHER;
 			break;
 		}
 		break;
 	case ixgbe_phy_xaui:
-		ecmd->supported |= SUPPORTED_FIBRE;
-		ecmd->advertising |= ADVERTISED_FIBRE;
-		ecmd->port = PORT_NONE;
+		supported |= SUPPORTED_FIBRE;
+		advertising |= ADVERTISED_FIBRE;
+		cmd->base.port = PORT_NONE;
 		break;
 	case ixgbe_phy_unknown:
 	case ixgbe_phy_generic:
 	case ixgbe_phy_sfp_unsupported:
 	default:
-		ecmd->supported |= SUPPORTED_FIBRE;
-		ecmd->advertising |= ADVERTISED_FIBRE;
-		ecmd->port = PORT_OTHER;
+		supported |= SUPPORTED_FIBRE;
+		advertising |= ADVERTISED_FIBRE;
+		cmd->base.port = PORT_OTHER;
 		break;
 	}
 
 	/* Indicate pause support */
-	ecmd->supported |= SUPPORTED_Pause;
+	supported |= SUPPORTED_Pause;
 
 	switch (hw->fc.requested_mode) {
 	case ixgbe_fc_full:
-		ecmd->advertising |= ADVERTISED_Pause;
+		advertising |= ADVERTISED_Pause;
 		break;
 	case ixgbe_fc_rx_pause:
-		ecmd->advertising |= ADVERTISED_Pause |
+		advertising |= ADVERTISED_Pause |
 				     ADVERTISED_Asym_Pause;
 		break;
 	case ixgbe_fc_tx_pause:
-		ecmd->advertising |= ADVERTISED_Asym_Pause;
+		advertising |= ADVERTISED_Asym_Pause;
 		break;
 	default:
-		ecmd->advertising &= ~(ADVERTISED_Pause |
+		advertising &= ~(ADVERTISED_Pause |
 				       ADVERTISED_Asym_Pause);
 	}
 
 	if (netif_carrier_ok(netdev)) {
 		switch (adapter->link_speed) {
 		case IXGBE_LINK_SPEED_10GB_FULL:
-			ethtool_cmd_speed_set(ecmd, SPEED_10000);
+			cmd->base.speed = SPEED_10000;
 			break;
 		case IXGBE_LINK_SPEED_5GB_FULL:
-			ethtool_cmd_speed_set(ecmd, SPEED_5000);
+			cmd->base.speed = SPEED_5000;
 			break;
 		case IXGBE_LINK_SPEED_2_5GB_FULL:
-			ethtool_cmd_speed_set(ecmd, SPEED_2500);
+			cmd->base.speed = SPEED_2500;
 			break;
 		case IXGBE_LINK_SPEED_1GB_FULL:
-			ethtool_cmd_speed_set(ecmd, SPEED_1000);
+			cmd->base.speed = SPEED_1000;
 			break;
 		case IXGBE_LINK_SPEED_100_FULL:
-			ethtool_cmd_speed_set(ecmd, SPEED_100);
+			cmd->base.speed = SPEED_100;
 			break;
 		case IXGBE_LINK_SPEED_10_FULL:
-			ethtool_cmd_speed_set(ecmd, SPEED_10);
+			cmd->base.speed = SPEED_10;
 			break;
 		default:
 			break;
 		}
-		ecmd->duplex = DUPLEX_FULL;
+		cmd->base.duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
-		ecmd->duplex = DUPLEX_UNKNOWN;
+		cmd->base.speed = SPEED_UNKNOWN;
+		cmd->base.duplex = DUPLEX_UNKNOWN;
 	}
 
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
+
 	return 0;
 }
 
-static int ixgbe_set_settings(struct net_device *netdev,
-			      struct ethtool_cmd *ecmd)
+static int ixgbe_set_link_ksettings(struct net_device *netdev,
+				    const struct ethtool_link_ksettings *cmd)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 advertised, old;
 	s32 err = 0;
+	u32 supported, advertising;
+
+	ethtool_convert_link_mode_to_legacy_u32(&supported,
+						cmd->link_modes.supported);
+	ethtool_convert_link_mode_to_legacy_u32(&advertising,
+						cmd->link_modes.advertising);
 
 	if ((hw->phy.media_type == ixgbe_media_type_copper) ||
 	    (hw->phy.multispeed_fiber)) {
@@ -388,12 +401,12 @@ static int ixgbe_set_settings(struct net_device *netdev,
 		 * this function does not support duplex forcing, but can
 		 * limit the advertising of the adapter to the specified speed
 		 */
-		if (ecmd->advertising & ~ecmd->supported)
+		if (advertising & ~supported)
 			return -EINVAL;
 
 		/* only allow one speed at a time if no autoneg */
-		if (!ecmd->autoneg && hw->phy.multispeed_fiber) {
-			if (ecmd->advertising ==
+		if (!cmd->base.autoneg && hw->phy.multispeed_fiber) {
+			if (advertising ==
 			    (ADVERTISED_10000baseT_Full |
 			     ADVERTISED_1000baseT_Full))
 				return -EINVAL;
@@ -401,16 +414,16 @@ static int ixgbe_set_settings(struct net_device *netdev,
 
 		old = hw->phy.autoneg_advertised;
 		advertised = 0;
-		if (ecmd->advertising & ADVERTISED_10000baseT_Full)
+		if (advertising & ADVERTISED_10000baseT_Full)
 			advertised |= IXGBE_LINK_SPEED_10GB_FULL;
 
-		if (ecmd->advertising & ADVERTISED_1000baseT_Full)
+		if (advertising & ADVERTISED_1000baseT_Full)
 			advertised |= IXGBE_LINK_SPEED_1GB_FULL;
 
-		if (ecmd->advertising & ADVERTISED_100baseT_Full)
+		if (advertising & ADVERTISED_100baseT_Full)
 			advertised |= IXGBE_LINK_SPEED_100_FULL;
 
-		if (ecmd->advertising & ADVERTISED_10baseT_Full)
+		if (advertising & ADVERTISED_10baseT_Full)
 			advertised |= IXGBE_LINK_SPEED_10_FULL;
 
 		if (old == advertised)
@@ -428,10 +441,11 @@ static int ixgbe_set_settings(struct net_device *netdev,
 		clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state);
 	} else {
 		/* in this case we currently only support 10Gb/FULL */
-		u32 speed = ethtool_cmd_speed(ecmd);
-		if ((ecmd->autoneg == AUTONEG_ENABLE) ||
-		    (ecmd->advertising != ADVERTISED_10000baseT_Full) ||
-		    (speed + ecmd->duplex != SPEED_10000 + DUPLEX_FULL))
+		u32 speed = cmd->base.speed;
+
+		if ((cmd->base.autoneg == AUTONEG_ENABLE) ||
+		    (advertising != ADVERTISED_10000baseT_Full) ||
+		    (speed + cmd->base.duplex != SPEED_10000 + DUPLEX_FULL))
 			return -EINVAL;
 	}
 
@@ -3402,8 +3416,6 @@ static int ixgbe_set_priv_flags(struct net_device *netdev, u32 priv_flags)
 }
 
 static const struct ethtool_ops ixgbe_ethtool_ops = {
-	.get_settings           = ixgbe_get_settings,
-	.set_settings           = ixgbe_set_settings,
 	.get_drvinfo            = ixgbe_get_drvinfo,
 	.get_regs_len           = ixgbe_get_regs_len,
 	.get_regs               = ixgbe_get_regs,
@@ -3442,6 +3454,8 @@ static const struct ethtool_ops ixgbe_ethtool_ops = {
 	.get_ts_info		= ixgbe_get_ts_info,
 	.get_module_info	= ixgbe_get_module_info,
 	.get_module_eeprom	= ixgbe_get_module_eeprom,
+	.get_link_ksettings     = ixgbe_get_link_ksettings,
+	.set_link_ksettings     = ixgbe_set_link_ksettings,
 };
 
 void ixgbe_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a7a430a7be2c..852a2e7e25ed 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2122,7 +2122,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 	prefetch(va + L1_CACHE_BYTES);
 #endif
 
-	/* build an skb to around the page buffer */
+	/* build an skb around the page buffer */
 	skb = build_skb(va - IXGBE_SKB_PAD, truesize);
 	if (unlikely(!skb))
 		return NULL;
@@ -8948,7 +8948,9 @@ static int __ixgbe_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
 	if (tc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
-	return ixgbe_setup_tc(dev, tc->tc);
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+	return ixgbe_setup_tc(dev, tc->mqprio->num_tc);
 }
 
 #ifdef CONFIG_PCI_IOV
diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index d2555e8b947e..da6fb825afea 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -82,13 +82,13 @@ config MVNETA_BM
 	  that all dependencies are met.
 
 config MVPP2
-	tristate "Marvell Armada 375 network interface support"
+	tristate "Marvell Armada 375/7K/8K network interface support"
 	depends on ARCH_MVEBU || COMPILE_TEST
 	depends on HAS_DMA
 	select MVMDIO
 	---help---
 	  This driver supports the network interface units in the
-	  Marvell ARMADA 375 SoC.
+	  Marvell ARMADA 375, 7K and 8K SoCs.
 
 config PXA168_ETH
 	tristate "Marvell pxa168 ethernet support"
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 61dd4462411c..34a3686d2ce6 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -431,6 +431,7 @@ struct mvneta_port {
 	/* Flags for special SoC configurations */
 	bool neta_armada3700;
 	u16 rx_offset_correction;
+	const struct mbus_dram_target_info *dram_target_info;
 };
 
 /* The mvneta_tx_desc and mvneta_rx_desc structures describe the
@@ -4098,6 +4099,8 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
 		break;
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		ctrl |= MVNETA_GMAC2_PORT_RGMII;
 		break;
 	default:
@@ -4118,7 +4121,6 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
 /* Device initialization routine */
 static int mvneta_probe(struct platform_device *pdev)
 {
-	const struct mbus_dram_target_info *dram_target_info;
 	struct resource *res;
 	struct device_node *dn = pdev->dev.of_node;
 	struct device_node *phy_node;
@@ -4267,13 +4269,13 @@ static int mvneta_probe(struct platform_device *pdev)
 
 	pp->tx_csum_limit = tx_csum_limit;
 
-	dram_target_info = mv_mbus_dram_info();
+	pp->dram_target_info = mv_mbus_dram_info();
 	/* Armada3700 requires setting default configuration of Mbus
 	 * windows, however without using filled mbus_dram_target_info
 	 * structure.
 	 */
-	if (dram_target_info || pp->neta_armada3700)
-		mvneta_conf_mbus_windows(pp, dram_target_info);
+	if (pp->dram_target_info || pp->neta_armada3700)
+		mvneta_conf_mbus_windows(pp, pp->dram_target_info);
 
 	pp->tx_ring_size = MVNETA_MAX_TXD;
 	pp->rx_ring_size = MVNETA_MAX_RXD;
@@ -4405,6 +4407,61 @@ static int mvneta_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int mvneta_suspend(struct device *device)
+{
+	struct net_device *dev = dev_get_drvdata(device);
+	struct mvneta_port *pp = netdev_priv(dev);
+
+	if (netif_running(dev))
+		mvneta_stop(dev);
+	netif_device_detach(dev);
+	clk_disable_unprepare(pp->clk_bus);
+	clk_disable_unprepare(pp->clk);
+	return 0;
+}
+
+static int mvneta_resume(struct device *device)
+{
+	struct platform_device *pdev = to_platform_device(device);
+	struct net_device *dev = dev_get_drvdata(device);
+	struct mvneta_port *pp = netdev_priv(dev);
+	int err;
+
+	clk_prepare_enable(pp->clk);
+	if (!IS_ERR(pp->clk_bus))
+		clk_prepare_enable(pp->clk_bus);
+	if (pp->dram_target_info || pp->neta_armada3700)
+		mvneta_conf_mbus_windows(pp, pp->dram_target_info);
+	if (pp->bm_priv) {
+		err = mvneta_bm_port_init(pdev, pp);
+		if (err < 0) {
+			dev_info(&pdev->dev, "use SW buffer management\n");
+			pp->bm_priv = NULL;
+		}
+	}
+	mvneta_defaults_set(pp);
+	err = mvneta_port_power_up(pp, pp->phy_interface);
+	if (err < 0) {
+		dev_err(device, "can't power up port\n");
+		return err;
+	}
+
+	if (pp->use_inband_status)
+		mvneta_fixed_link_update(pp, dev->phydev);
+
+	netif_device_attach(dev);
+	if (netif_running(dev)) {
+		mvneta_open(dev);
+		mvneta_set_rx_mode(dev);
+	}
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(mvneta_pm_ops, mvneta_suspend, mvneta_resume);
+
 static const struct of_device_id mvneta_match[] = {
 	{ .compatible = "marvell,armada-370-neta" },
 	{ .compatible = "marvell,armada-xp-neta" },
@@ -4419,6 +4476,7 @@ static struct platform_driver mvneta_driver = {
 	.driver = {
 		.name = MVNETA_DRIVER_NAME,
 		.of_match_table = mvneta_match,
+		.pm = &mvneta_pm_ops,
 	},
 };
 
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index d00421b9ffea..af5bfa13d976 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -25,6 +25,7 @@
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/of_address.h>
+#include <linux/of_device.h>
 #include <linux/phy.h>
 #include <linux/clk.h>
 #include <linux/hrtimer.h>
@@ -49,9 +50,11 @@
 #define     MVPP2_SNOOP_PKT_SIZE_MASK		0x1ff
 #define     MVPP2_SNOOP_BUF_HDR_MASK		BIT(9)
 #define     MVPP2_RXQ_POOL_SHORT_OFFS		20
-#define     MVPP2_RXQ_POOL_SHORT_MASK		0x700000
+#define     MVPP21_RXQ_POOL_SHORT_MASK		0x700000
+#define     MVPP22_RXQ_POOL_SHORT_MASK		0xf00000
 #define     MVPP2_RXQ_POOL_LONG_OFFS		24
-#define     MVPP2_RXQ_POOL_LONG_MASK		0x7000000
+#define     MVPP21_RXQ_POOL_LONG_MASK		0x7000000
+#define     MVPP22_RXQ_POOL_LONG_MASK		0xf000000
 #define     MVPP2_RXQ_PACKET_OFFSET_OFFS	28
 #define     MVPP2_RXQ_PACKET_OFFSET_MASK	0x70000000
 #define     MVPP2_RXQ_DISABLE_MASK		BIT(31)
@@ -99,6 +102,7 @@
 /* Descriptor Manager Top Registers */
 #define MVPP2_RXQ_NUM_REG			0x2040
 #define MVPP2_RXQ_DESC_ADDR_REG			0x2044
+#define     MVPP22_DESC_ADDR_OFFS		8
 #define MVPP2_RXQ_DESC_SIZE_REG			0x2048
 #define     MVPP2_RXQ_DESC_SIZE_MASK		0x3ff0
 #define MVPP2_RXQ_STATUS_UPDATE_REG(rxq)	(0x3000 + 4 * (rxq))
@@ -117,9 +121,6 @@
 #define MVPP2_TXQ_DESC_SIZE_REG			0x2088
 #define     MVPP2_TXQ_DESC_SIZE_MASK		0x3ff0
 #define MVPP2_AGGR_TXQ_UPDATE_REG		0x2090
-#define MVPP2_TXQ_THRESH_REG			0x2094
-#define     MVPP2_TRANSMITTED_THRESH_OFFSET	16
-#define     MVPP2_TRANSMITTED_THRESH_MASK	0x3fff0000
 #define MVPP2_TXQ_INDEX_REG			0x2098
 #define MVPP2_TXQ_PREF_BUF_REG			0x209c
 #define     MVPP2_PREF_BUF_PTR(desc)		((desc) & 0xfff)
@@ -140,6 +141,7 @@
 #define MVPP2_TXQ_RSVD_CLR_REG			0x20b8
 #define     MVPP2_TXQ_RSVD_CLR_OFFSET		16
 #define MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu)	(0x2100 + 4 * (cpu))
+#define     MVPP22_AGGR_TXQ_DESC_ADDR_OFFS	8
 #define MVPP2_AGGR_TXQ_DESC_SIZE_REG(cpu)	(0x2140 + 4 * (cpu))
 #define     MVPP2_AGGR_TXQ_DESC_SIZE_MASK	0x3ff0
 #define MVPP2_AGGR_TXQ_STATUS_REG(cpu)		(0x2180 + 4 * (cpu))
@@ -152,10 +154,52 @@
 #define MVPP2_WIN_REMAP(w)			(0x4040 + ((w) << 2))
 #define MVPP2_BASE_ADDR_ENABLE			0x4060
 
+/* AXI Bridge Registers */
+#define MVPP22_AXI_BM_WR_ATTR_REG		0x4100
+#define MVPP22_AXI_BM_RD_ATTR_REG		0x4104
+#define MVPP22_AXI_AGGRQ_DESCR_RD_ATTR_REG	0x4110
+#define MVPP22_AXI_TXQ_DESCR_WR_ATTR_REG	0x4114
+#define MVPP22_AXI_TXQ_DESCR_RD_ATTR_REG	0x4118
+#define MVPP22_AXI_RXQ_DESCR_WR_ATTR_REG	0x411c
+#define MVPP22_AXI_RX_DATA_WR_ATTR_REG		0x4120
+#define MVPP22_AXI_TX_DATA_RD_ATTR_REG		0x4130
+#define MVPP22_AXI_RD_NORMAL_CODE_REG		0x4150
+#define MVPP22_AXI_RD_SNOOP_CODE_REG		0x4154
+#define MVPP22_AXI_WR_NORMAL_CODE_REG		0x4160
+#define MVPP22_AXI_WR_SNOOP_CODE_REG		0x4164
+
+/* Values for AXI Bridge registers */
+#define MVPP22_AXI_ATTR_CACHE_OFFS		0
+#define MVPP22_AXI_ATTR_DOMAIN_OFFS		12
+
+#define MVPP22_AXI_CODE_CACHE_OFFS		0
+#define MVPP22_AXI_CODE_DOMAIN_OFFS		4
+
+#define MVPP22_AXI_CODE_CACHE_NON_CACHE		0x3
+#define MVPP22_AXI_CODE_CACHE_WR_CACHE		0x7
+#define MVPP22_AXI_CODE_CACHE_RD_CACHE		0xb
+
+#define MVPP22_AXI_CODE_DOMAIN_OUTER_DOM	2
+#define MVPP22_AXI_CODE_DOMAIN_SYSTEM		3
+
 /* Interrupt Cause and Mask registers */
 #define MVPP2_ISR_RX_THRESHOLD_REG(rxq)		(0x5200 + 4 * (rxq))
 #define     MVPP2_MAX_ISR_RX_THRESHOLD		0xfffff0
-#define MVPP2_ISR_RXQ_GROUP_REG(rxq)		(0x5400 + 4 * (rxq))
+#define MVPP21_ISR_RXQ_GROUP_REG(rxq)		(0x5400 + 4 * (rxq))
+
+#define MVPP22_ISR_RXQ_GROUP_INDEX_REG          0x5400
+#define MVPP22_ISR_RXQ_GROUP_INDEX_SUBGROUP_MASK 0xf
+#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_MASK   0x380
+#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET 7
+
+#define MVPP22_ISR_RXQ_GROUP_INDEX_SUBGROUP_MASK 0xf
+#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_MASK   0x380
+
+#define MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG     0x5404
+#define MVPP22_ISR_RXQ_SUB_GROUP_STARTQ_MASK    0x1f
+#define MVPP22_ISR_RXQ_SUB_GROUP_SIZE_MASK      0xf00
+#define MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET    8
+
 #define MVPP2_ISR_ENABLE_REG(port)		(0x5420 + 4 * (port))
 #define     MVPP2_ISR_ENABLE_INTERRUPT(mask)	((mask) & 0xffff)
 #define     MVPP2_ISR_DISABLE_INTERRUPT(mask)	(((mask) << 16) & 0xffff0000)
@@ -210,14 +254,19 @@
 #define MVPP2_BM_PHY_ALLOC_REG(pool)		(0x6400 + ((pool) * 4))
 #define     MVPP2_BM_PHY_ALLOC_GRNTD_MASK	BIT(0)
 #define MVPP2_BM_VIRT_ALLOC_REG			0x6440
+#define MVPP22_BM_ADDR_HIGH_ALLOC		0x6444
+#define     MVPP22_BM_ADDR_HIGH_PHYS_MASK	0xff
+#define     MVPP22_BM_ADDR_HIGH_VIRT_MASK	0xff00
+#define     MVPP22_BM_ADDR_HIGH_VIRT_SHIFT	8
 #define MVPP2_BM_PHY_RLS_REG(pool)		(0x6480 + ((pool) * 4))
 #define     MVPP2_BM_PHY_RLS_MC_BUFF_MASK	BIT(0)
 #define     MVPP2_BM_PHY_RLS_PRIO_EN_MASK	BIT(1)
 #define     MVPP2_BM_PHY_RLS_GRNTD_MASK		BIT(2)
 #define MVPP2_BM_VIRT_RLS_REG			0x64c0
-#define MVPP2_BM_MC_RLS_REG			0x64c4
-#define     MVPP2_BM_MC_ID_MASK			0xfff
-#define     MVPP2_BM_FORCE_RELEASE_MASK		BIT(12)
+#define MVPP22_BM_ADDR_HIGH_RLS_REG		0x64c4
+#define     MVPP22_BM_ADDR_HIGH_PHYS_RLS_MASK	0xff
+#define	    MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK	0xff00
+#define     MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT	8
 
 /* TX Scheduler registers */
 #define MVPP2_TXP_SCHED_PORT_INDEX_REG		0x8000
@@ -287,6 +336,24 @@
 #define      MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK	0x1fc0
 #define      MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(v)	(((v) << 6) & \
 					MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK)
+#define MVPP22_GMAC_CTRL_4_REG			0x90
+#define      MVPP22_CTRL4_EXT_PIN_GMII_SEL	BIT(0)
+#define      MVPP22_CTRL4_DP_CLK_SEL		BIT(5)
+#define      MVPP22_CTRL4_SYNC_BYPASS		BIT(6)
+#define      MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE	BIT(7)
+
+/* Per-port XGMAC registers. PPv2.2 only, only for GOP port 0,
+ * relative to port->base.
+ */
+#define MVPP22_XLG_CTRL3_REG			0x11c
+#define      MVPP22_XLG_CTRL3_MACMODESELECT_MASK	(7 << 13)
+#define      MVPP22_XLG_CTRL3_MACMODESELECT_GMAC	(0 << 13)
+
+/* SMI registers. PPv2.2 only, relative to priv->iface_base. */
+#define MVPP22_SMI_MISC_CFG_REG			0x1204
+#define      MVPP22_SMI_POLLING_EN		BIT(10)
+
+#define MVPP22_GMAC_BASE(port)		(0x7000 + (port) * 0x1000 + 0xe00)
 
 #define MVPP2_CAUSE_TXQ_SENT_DESC_ALL_MASK	0xff
 
@@ -335,15 +402,9 @@
 /* Maximum number of TXQs used by single port */
 #define MVPP2_MAX_TXQ			8
 
-/* Maximum number of RXQs used by single port */
-#define MVPP2_MAX_RXQ			8
-
 /* Dfault number of RXQs in use */
 #define MVPP2_DEFAULT_RXQ		4
 
-/* Total number of RXQs available to all ports */
-#define MVPP2_RXQ_TOTAL_NUM		(MVPP2_MAX_PORTS * MVPP2_MAX_RXQ)
-
 /* Max number of Rx descriptors */
 #define MVPP2_MAX_RXD			128
 
@@ -615,6 +676,11 @@ enum mvpp2_prs_l3_cast {
  */
 #define MVPP2_BM_SHORT_PKT_SIZE		MVPP2_RX_MAX_PKT_SIZE(512)
 
+#define MVPP21_ADDR_SPACE_SZ		0
+#define MVPP22_ADDR_SPACE_SZ		SZ_64K
+
+#define MVPP2_MAX_CPUS			4
+
 enum mvpp2_bm_type {
 	MVPP2_BM_FREE,
 	MVPP2_BM_SWF_LONG,
@@ -626,12 +692,19 @@ enum mvpp2_bm_type {
 /* Shared Packet Processor resources */
 struct mvpp2 {
 	/* Shared registers' base addresses */
-	void __iomem *base;
 	void __iomem *lms_base;
+	void __iomem *iface_base;
+
+	/* On PPv2.2, each CPU can access the base register through a
+	 * separate address space, each 64 KB apart from each
+	 * other.
+	 */
+	void __iomem *cpu_base[MVPP2_MAX_CPUS];
 
 	/* Common clocks */
 	struct clk *pp_clk;
 	struct clk *gop_clk;
+	struct clk *mg_clk;
 
 	/* List of pointers to port structures */
 	struct mvpp2_port **port_list;
@@ -649,6 +722,12 @@ struct mvpp2 {
 
 	/* Tclk value */
 	u32 tclk;
+
+	/* HW version */
+	enum { MVPP21, MVPP22 } hw_version;
+
+	/* Maximum number of RXQs per port */
+	unsigned int max_port_rxqs;
 };
 
 struct mvpp2_pcpu_stats {
@@ -670,6 +749,11 @@ struct mvpp2_port_pcpu {
 struct mvpp2_port {
 	u8 id;
 
+	/* Index of the port from the "group of ports" complex point
+	 * of view
+	 */
+	int gop_id;
+
 	int irq;
 
 	struct mvpp2 *priv;
@@ -741,22 +825,24 @@ struct mvpp2_port {
 #define MVPP2_RXD_L3_IP6		BIT(30)
 #define MVPP2_RXD_BUF_HDR		BIT(31)
 
-struct mvpp2_tx_desc {
+/* HW TX descriptor for PPv2.1 */
+struct mvpp21_tx_desc {
 	u32 command;		/* Options used by HW for packet transmitting.*/
 	u8  packet_offset;	/* the offset from the buffer beginning	*/
 	u8  phys_txq;		/* destination queue ID			*/
 	u16 data_size;		/* data size of transmitted packet in bytes */
-	u32 buf_phys_addr;	/* physical addr of transmitted buffer	*/
+	u32 buf_dma_addr;	/* physical addr of transmitted buffer	*/
 	u32 buf_cookie;		/* cookie for access to TX buffer in tx path */
 	u32 reserved1[3];	/* hw_cmd (for future use, BM, PON, PNC) */
 	u32 reserved2;		/* reserved (for future use)		*/
 };
 
-struct mvpp2_rx_desc {
+/* HW RX descriptor for PPv2.1 */
+struct mvpp21_rx_desc {
 	u32 status;		/* info about received packet		*/
 	u16 reserved1;		/* parser_info (for future use, PnC)	*/
 	u16 data_size;		/* size of received packet in bytes	*/
-	u32 buf_phys_addr;	/* physical address of the buffer	*/
+	u32 buf_dma_addr;	/* physical address of the buffer	*/
 	u32 buf_cookie;		/* cookie for access to RX buffer in rx path */
 	u16 reserved2;		/* gem_port_id (for future use, PON)	*/
 	u16 reserved3;		/* csum_l4 (for future use, PnC)	*/
@@ -767,12 +853,51 @@ struct mvpp2_rx_desc {
 	u32 reserved8;
 };
 
+/* HW TX descriptor for PPv2.2 */
+struct mvpp22_tx_desc {
+	u32 command;
+	u8  packet_offset;
+	u8  phys_txq;
+	u16 data_size;
+	u64 reserved1;
+	u64 buf_dma_addr_ptp;
+	u64 buf_cookie_misc;
+};
+
+/* HW RX descriptor for PPv2.2 */
+struct mvpp22_rx_desc {
+	u32 status;
+	u16 reserved1;
+	u16 data_size;
+	u32 reserved2;
+	u32 reserved3;
+	u64 buf_dma_addr_key_hash;
+	u64 buf_cookie_misc;
+};
+
+/* Opaque type used by the driver to manipulate the HW TX and RX
+ * descriptors
+ */
+struct mvpp2_tx_desc {
+	union {
+		struct mvpp21_tx_desc pp21;
+		struct mvpp22_tx_desc pp22;
+	};
+};
+
+struct mvpp2_rx_desc {
+	union {
+		struct mvpp21_rx_desc pp21;
+		struct mvpp22_rx_desc pp22;
+	};
+};
+
 struct mvpp2_txq_pcpu_buf {
 	/* Transmitted SKB */
 	struct sk_buff *skb;
 
 	/* Physical address of transmitted buffer */
-	dma_addr_t phys;
+	dma_addr_t dma;
 
 	/* Size transmitted */
 	size_t size;
@@ -825,7 +950,7 @@ struct mvpp2_tx_queue {
 	struct mvpp2_tx_desc *descs;
 
 	/* DMA address of the Tx DMA descriptors array */
-	dma_addr_t descs_phys;
+	dma_addr_t descs_dma;
 
 	/* Index of the last Tx DMA descriptor */
 	int last_desc;
@@ -848,7 +973,7 @@ struct mvpp2_rx_queue {
 	struct mvpp2_rx_desc *descs;
 
 	/* DMA address of the RX DMA descriptors array */
-	dma_addr_t descs_phys;
+	dma_addr_t descs_dma;
 
 	/* Index of the last RX DMA descriptor */
 	int last_desc;
@@ -912,6 +1037,8 @@ struct mvpp2_bm_pool {
 
 	/* Buffer Pointers Pool External (BPPE) size */
 	int size;
+	/* BPPE size in bytes */
+	int size_bytes;
 	/* Number of buffers for this pool */
 	int buf_num;
 	/* Pool buffer size */
@@ -922,29 +1049,13 @@ struct mvpp2_bm_pool {
 
 	/* BPPE virtual base address */
 	u32 *virt_addr;
-	/* BPPE physical base address */
-	dma_addr_t phys_addr;
+	/* BPPE DMA base address */
+	dma_addr_t dma_addr;
 
 	/* Ports using BM pool */
 	u32 port_map;
 };
 
-struct mvpp2_buff_hdr {
-	u32 next_buff_phys_addr;
-	u32 next_buff_virt_addr;
-	u16 byte_count;
-	u16 info;
-	u8  reserved1;		/* bm_qset (for future use, BM)		*/
-};
-
-/* Buffer header info bits */
-#define MVPP2_B_HDR_INFO_MC_ID_MASK	0xfff
-#define MVPP2_B_HDR_INFO_MC_ID(info)	((info) & MVPP2_B_HDR_INFO_MC_ID_MASK)
-#define MVPP2_B_HDR_INFO_LAST_OFFS	12
-#define MVPP2_B_HDR_INFO_LAST_MASK	BIT(12)
-#define MVPP2_B_HDR_INFO_IS_LAST(info) \
-	   ((info & MVPP2_B_HDR_INFO_LAST_MASK) >> MVPP2_B_HDR_INFO_LAST_OFFS)
-
 /* Static declaractions */
 
 /* Number of RXQs used by single port */
@@ -959,12 +1070,177 @@ static int txq_number = MVPP2_MAX_TXQ;
 
 static void mvpp2_write(struct mvpp2 *priv, u32 offset, u32 data)
 {
-	writel(data, priv->base + offset);
+	writel(data, priv->cpu_base[0] + offset);
 }
 
 static u32 mvpp2_read(struct mvpp2 *priv, u32 offset)
 {
-	return readl(priv->base + offset);
+	return readl(priv->cpu_base[0] + offset);
+}
+
+/* These accessors should be used to access:
+ *
+ * - per-CPU registers, where each CPU has its own copy of the
+ *   register.
+ *
+ *   MVPP2_BM_VIRT_ALLOC_REG
+ *   MVPP2_BM_ADDR_HIGH_ALLOC
+ *   MVPP22_BM_ADDR_HIGH_RLS_REG
+ *   MVPP2_BM_VIRT_RLS_REG
+ *   MVPP2_ISR_RX_TX_CAUSE_REG
+ *   MVPP2_ISR_RX_TX_MASK_REG
+ *   MVPP2_TXQ_NUM_REG
+ *   MVPP2_AGGR_TXQ_UPDATE_REG
+ *   MVPP2_TXQ_RSVD_REQ_REG
+ *   MVPP2_TXQ_RSVD_RSLT_REG
+ *   MVPP2_TXQ_SENT_REG
+ *   MVPP2_RXQ_NUM_REG
+ *
+ * - global registers that must be accessed through a specific CPU
+ *   window, because they are related to an access to a per-CPU
+ *   register
+ *
+ *   MVPP2_BM_PHY_ALLOC_REG    (related to MVPP2_BM_VIRT_ALLOC_REG)
+ *   MVPP2_BM_PHY_RLS_REG      (related to MVPP2_BM_VIRT_RLS_REG)
+ *   MVPP2_RXQ_THRESH_REG      (related to MVPP2_RXQ_NUM_REG)
+ *   MVPP2_RXQ_DESC_ADDR_REG   (related to MVPP2_RXQ_NUM_REG)
+ *   MVPP2_RXQ_DESC_SIZE_REG   (related to MVPP2_RXQ_NUM_REG)
+ *   MVPP2_RXQ_INDEX_REG       (related to MVPP2_RXQ_NUM_REG)
+ *   MVPP2_TXQ_PENDING_REG     (related to MVPP2_TXQ_NUM_REG)
+ *   MVPP2_TXQ_DESC_ADDR_REG   (related to MVPP2_TXQ_NUM_REG)
+ *   MVPP2_TXQ_DESC_SIZE_REG   (related to MVPP2_TXQ_NUM_REG)
+ *   MVPP2_TXQ_INDEX_REG       (related to MVPP2_TXQ_NUM_REG)
+ *   MVPP2_TXQ_PENDING_REG     (related to MVPP2_TXQ_NUM_REG)
+ *   MVPP2_TXQ_PREF_BUF_REG    (related to MVPP2_TXQ_NUM_REG)
+ *   MVPP2_TXQ_PREF_BUF_REG    (related to MVPP2_TXQ_NUM_REG)
+ */
+static void mvpp2_percpu_write(struct mvpp2 *priv, int cpu,
+			       u32 offset, u32 data)
+{
+	writel(data, priv->cpu_base[cpu] + offset);
+}
+
+static u32 mvpp2_percpu_read(struct mvpp2 *priv, int cpu,
+			     u32 offset)
+{
+	return readl(priv->cpu_base[cpu] + offset);
+}
+
+static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port,
+					    struct mvpp2_tx_desc *tx_desc)
+{
+	if (port->priv->hw_version == MVPP21)
+		return tx_desc->pp21.buf_dma_addr;
+	else
+		return tx_desc->pp22.buf_dma_addr_ptp & GENMASK_ULL(40, 0);
+}
+
+static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
+				      struct mvpp2_tx_desc *tx_desc,
+				      dma_addr_t dma_addr)
+{
+	if (port->priv->hw_version == MVPP21) {
+		tx_desc->pp21.buf_dma_addr = dma_addr;
+	} else {
+		u64 val = (u64)dma_addr;
+
+		tx_desc->pp22.buf_dma_addr_ptp &= ~GENMASK_ULL(40, 0);
+		tx_desc->pp22.buf_dma_addr_ptp |= val;
+	}
+}
+
+static size_t mvpp2_txdesc_size_get(struct mvpp2_port *port,
+				    struct mvpp2_tx_desc *tx_desc)
+{
+	if (port->priv->hw_version == MVPP21)
+		return tx_desc->pp21.data_size;
+	else
+		return tx_desc->pp22.data_size;
+}
+
+static void mvpp2_txdesc_size_set(struct mvpp2_port *port,
+				  struct mvpp2_tx_desc *tx_desc,
+				  size_t size)
+{
+	if (port->priv->hw_version == MVPP21)
+		tx_desc->pp21.data_size = size;
+	else
+		tx_desc->pp22.data_size = size;
+}
+
+static void mvpp2_txdesc_txq_set(struct mvpp2_port *port,
+				 struct mvpp2_tx_desc *tx_desc,
+				 unsigned int txq)
+{
+	if (port->priv->hw_version == MVPP21)
+		tx_desc->pp21.phys_txq = txq;
+	else
+		tx_desc->pp22.phys_txq = txq;
+}
+
+static void mvpp2_txdesc_cmd_set(struct mvpp2_port *port,
+				 struct mvpp2_tx_desc *tx_desc,
+				 unsigned int command)
+{
+	if (port->priv->hw_version == MVPP21)
+		tx_desc->pp21.command = command;
+	else
+		tx_desc->pp22.command = command;
+}
+
+static void mvpp2_txdesc_offset_set(struct mvpp2_port *port,
+				    struct mvpp2_tx_desc *tx_desc,
+				    unsigned int offset)
+{
+	if (port->priv->hw_version == MVPP21)
+		tx_desc->pp21.packet_offset = offset;
+	else
+		tx_desc->pp22.packet_offset = offset;
+}
+
+static unsigned int mvpp2_txdesc_offset_get(struct mvpp2_port *port,
+					    struct mvpp2_tx_desc *tx_desc)
+{
+	if (port->priv->hw_version == MVPP21)
+		return tx_desc->pp21.packet_offset;
+	else
+		return tx_desc->pp22.packet_offset;
+}
+
+static dma_addr_t mvpp2_rxdesc_dma_addr_get(struct mvpp2_port *port,
+					    struct mvpp2_rx_desc *rx_desc)
+{
+	if (port->priv->hw_version == MVPP21)
+		return rx_desc->pp21.buf_dma_addr;
+	else
+		return rx_desc->pp22.buf_dma_addr_key_hash & GENMASK_ULL(40, 0);
+}
+
+static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port,
+					     struct mvpp2_rx_desc *rx_desc)
+{
+	if (port->priv->hw_version == MVPP21)
+		return rx_desc->pp21.buf_cookie;
+	else
+		return rx_desc->pp22.buf_cookie_misc & GENMASK_ULL(40, 0);
+}
+
+static size_t mvpp2_rxdesc_size_get(struct mvpp2_port *port,
+				    struct mvpp2_rx_desc *rx_desc)
+{
+	if (port->priv->hw_version == MVPP21)
+		return rx_desc->pp21.data_size;
+	else
+		return rx_desc->pp22.data_size;
+}
+
+static u32 mvpp2_rxdesc_status_get(struct mvpp2_port *port,
+				   struct mvpp2_rx_desc *rx_desc)
+{
+	if (port->priv->hw_version == MVPP21)
+		return rx_desc->pp21.status;
+	else
+		return rx_desc->pp22.status;
 }
 
 static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu)
@@ -974,15 +1250,17 @@ static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu)
 		txq_pcpu->txq_get_index = 0;
 }
 
-static void mvpp2_txq_inc_put(struct mvpp2_txq_pcpu *txq_pcpu,
+static void mvpp2_txq_inc_put(struct mvpp2_port *port,
+			      struct mvpp2_txq_pcpu *txq_pcpu,
 			      struct sk_buff *skb,
 			      struct mvpp2_tx_desc *tx_desc)
 {
 	struct mvpp2_txq_pcpu_buf *tx_buf =
 		txq_pcpu->buffs + txq_pcpu->txq_put_index;
 	tx_buf->skb = skb;
-	tx_buf->size = tx_desc->data_size;
-	tx_buf->phys = tx_desc->buf_phys_addr + tx_desc->packet_offset;
+	tx_buf->size = mvpp2_txdesc_size_get(port, tx_desc);
+	tx_buf->dma = mvpp2_txdesc_dma_addr_get(port, tx_desc) +
+		mvpp2_txdesc_offset_get(port, tx_desc);
 	txq_pcpu->txq_put_index++;
 	if (txq_pcpu->txq_put_index == txq_pcpu->size)
 		txq_pcpu->txq_put_index = 0;
@@ -3378,27 +3656,39 @@ static int mvpp2_bm_pool_create(struct platform_device *pdev,
 				struct mvpp2 *priv,
 				struct mvpp2_bm_pool *bm_pool, int size)
 {
-	int size_bytes;
 	u32 val;
 
-	size_bytes = sizeof(u32) * size;
-	bm_pool->virt_addr = dma_alloc_coherent(&pdev->dev, size_bytes,
-						&bm_pool->phys_addr,
+	/* Number of buffer pointers must be a multiple of 16, as per
+	 * hardware constraints
+	 */
+	if (!IS_ALIGNED(size, 16))
+		return -EINVAL;
+
+	/* PPv2.1 needs 8 bytes per buffer pointer, PPv2.2 needs 16
+	 * bytes per buffer pointer
+	 */
+	if (priv->hw_version == MVPP21)
+		bm_pool->size_bytes = 2 * sizeof(u32) * size;
+	else
+		bm_pool->size_bytes = 2 * sizeof(u64) * size;
+
+	bm_pool->virt_addr = dma_alloc_coherent(&pdev->dev, bm_pool->size_bytes,
+						&bm_pool->dma_addr,
 						GFP_KERNEL);
 	if (!bm_pool->virt_addr)
 		return -ENOMEM;
 
 	if (!IS_ALIGNED((unsigned long)bm_pool->virt_addr,
 			MVPP2_BM_POOL_PTR_ALIGN)) {
-		dma_free_coherent(&pdev->dev, size_bytes, bm_pool->virt_addr,
-				  bm_pool->phys_addr);
+		dma_free_coherent(&pdev->dev, bm_pool->size_bytes,
+				  bm_pool->virt_addr, bm_pool->dma_addr);
 		dev_err(&pdev->dev, "BM pool %d is not %d bytes aligned\n",
 			bm_pool->id, MVPP2_BM_POOL_PTR_ALIGN);
 		return -ENOMEM;
 	}
 
 	mvpp2_write(priv, MVPP2_BM_POOL_BASE_REG(bm_pool->id),
-		    bm_pool->phys_addr);
+		    lower_32_bits(bm_pool->dma_addr));
 	mvpp2_write(priv, MVPP2_BM_POOL_SIZE_REG(bm_pool->id), size);
 
 	val = mvpp2_read(priv, MVPP2_BM_POOL_CTRL_REG(bm_pool->id));
@@ -3426,6 +3716,34 @@ static void mvpp2_bm_pool_bufsize_set(struct mvpp2 *priv,
 	mvpp2_write(priv, MVPP2_POOL_BUF_SIZE_REG(bm_pool->id), val);
 }
 
+static void mvpp2_bm_bufs_get_addrs(struct device *dev, struct mvpp2 *priv,
+				    struct mvpp2_bm_pool *bm_pool,
+				    dma_addr_t *dma_addr,
+				    phys_addr_t *phys_addr)
+{
+	int cpu = smp_processor_id();
+
+	*dma_addr = mvpp2_percpu_read(priv, cpu,
+				      MVPP2_BM_PHY_ALLOC_REG(bm_pool->id));
+	*phys_addr = mvpp2_percpu_read(priv, cpu, MVPP2_BM_VIRT_ALLOC_REG);
+
+	if (priv->hw_version == MVPP22) {
+		u32 val;
+		u32 dma_addr_highbits, phys_addr_highbits;
+
+		val = mvpp2_percpu_read(priv, cpu, MVPP22_BM_ADDR_HIGH_ALLOC);
+		dma_addr_highbits = (val & MVPP22_BM_ADDR_HIGH_PHYS_MASK);
+		phys_addr_highbits = (val & MVPP22_BM_ADDR_HIGH_VIRT_MASK) >>
+			MVPP22_BM_ADDR_HIGH_VIRT_SHIFT;
+
+		if (sizeof(dma_addr_t) == 8)
+			*dma_addr |= (u64)dma_addr_highbits << 32;
+
+		if (sizeof(phys_addr_t) == 8)
+			*phys_addr |= (u64)phys_addr_highbits << 32;
+	}
+}
+
 /* Free all buffers from the pool */
 static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv,
 			       struct mvpp2_bm_pool *bm_pool)
@@ -3433,21 +3751,21 @@ static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv,
 	int i;
 
 	for (i = 0; i < bm_pool->buf_num; i++) {
-		dma_addr_t buf_phys_addr;
-		unsigned long vaddr;
+		dma_addr_t buf_dma_addr;
+		phys_addr_t buf_phys_addr;
+		void *data;
 
-		/* Get buffer virtual address (indirect access) */
-		buf_phys_addr = mvpp2_read(priv,
-					   MVPP2_BM_PHY_ALLOC_REG(bm_pool->id));
-		vaddr = mvpp2_read(priv, MVPP2_BM_VIRT_ALLOC_REG);
+		mvpp2_bm_bufs_get_addrs(dev, priv, bm_pool,
+					&buf_dma_addr, &buf_phys_addr);
 
-		dma_unmap_single(dev, buf_phys_addr,
+		dma_unmap_single(dev, buf_dma_addr,
 				 bm_pool->buf_size, DMA_FROM_DEVICE);
 
-		if (!vaddr)
+		data = (void *)phys_to_virt(buf_phys_addr);
+		if (!data)
 			break;
 
-		mvpp2_frag_free(bm_pool, (void *)vaddr);
+		mvpp2_frag_free(bm_pool, data);
 	}
 
 	/* Update BM driver with number of buffers removed from pool */
@@ -3471,9 +3789,9 @@ static int mvpp2_bm_pool_destroy(struct platform_device *pdev,
 	val |= MVPP2_BM_STOP_MASK;
 	mvpp2_write(priv, MVPP2_BM_POOL_CTRL_REG(bm_pool->id), val);
 
-	dma_free_coherent(&pdev->dev, sizeof(u32) * bm_pool->size,
+	dma_free_coherent(&pdev->dev, bm_pool->size_bytes,
 			  bm_pool->virt_addr,
-			  bm_pool->phys_addr);
+			  bm_pool->dma_addr);
 	return 0;
 }
 
@@ -3529,17 +3847,20 @@ static int mvpp2_bm_init(struct platform_device *pdev, struct mvpp2 *priv)
 static void mvpp2_rxq_long_pool_set(struct mvpp2_port *port,
 				    int lrxq, int long_pool)
 {
-	u32 val;
+	u32 val, mask;
 	int prxq;
 
 	/* Get queue physical ID */
 	prxq = port->rxqs[lrxq]->id;
 
-	val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq));
-	val &= ~MVPP2_RXQ_POOL_LONG_MASK;
-	val |= ((long_pool << MVPP2_RXQ_POOL_LONG_OFFS) &
-		    MVPP2_RXQ_POOL_LONG_MASK);
+	if (port->priv->hw_version == MVPP21)
+		mask = MVPP21_RXQ_POOL_LONG_MASK;
+	else
+		mask = MVPP22_RXQ_POOL_LONG_MASK;
 
+	val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq));
+	val &= ~mask;
+	val |= (long_pool << MVPP2_RXQ_POOL_LONG_OFFS) & mask;
 	mvpp2_write(port->priv, MVPP2_RXQ_CONFIG_REG(prxq), val);
 }
 
@@ -3547,40 +3868,45 @@ static void mvpp2_rxq_long_pool_set(struct mvpp2_port *port,
 static void mvpp2_rxq_short_pool_set(struct mvpp2_port *port,
 				     int lrxq, int short_pool)
 {
-	u32 val;
+	u32 val, mask;
 	int prxq;
 
 	/* Get queue physical ID */
 	prxq = port->rxqs[lrxq]->id;
 
-	val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq));
-	val &= ~MVPP2_RXQ_POOL_SHORT_MASK;
-	val |= ((short_pool << MVPP2_RXQ_POOL_SHORT_OFFS) &
-		    MVPP2_RXQ_POOL_SHORT_MASK);
+	if (port->priv->hw_version == MVPP21)
+		mask = MVPP21_RXQ_POOL_SHORT_MASK;
+	else
+		mask = MVPP22_RXQ_POOL_SHORT_MASK;
 
+	val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq));
+	val &= ~mask;
+	val |= (short_pool << MVPP2_RXQ_POOL_SHORT_OFFS) & mask;
 	mvpp2_write(port->priv, MVPP2_RXQ_CONFIG_REG(prxq), val);
 }
 
 static void *mvpp2_buf_alloc(struct mvpp2_port *port,
 			     struct mvpp2_bm_pool *bm_pool,
-			     dma_addr_t *buf_phys_addr,
+			     dma_addr_t *buf_dma_addr,
+			     phys_addr_t *buf_phys_addr,
 			     gfp_t gfp_mask)
 {
-	dma_addr_t phys_addr;
+	dma_addr_t dma_addr;
 	void *data;
 
 	data = mvpp2_frag_alloc(bm_pool);
 	if (!data)
 		return NULL;
 
-	phys_addr = dma_map_single(port->dev->dev.parent, data,
-				   MVPP2_RX_BUF_SIZE(bm_pool->pkt_size),
-				    DMA_FROM_DEVICE);
-	if (unlikely(dma_mapping_error(port->dev->dev.parent, phys_addr))) {
+	dma_addr = dma_map_single(port->dev->dev.parent, data,
+				  MVPP2_RX_BUF_SIZE(bm_pool->pkt_size),
+				  DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(port->dev->dev.parent, dma_addr))) {
 		mvpp2_frag_free(bm_pool, data);
 		return NULL;
 	}
-	*buf_phys_addr = phys_addr;
+	*buf_dma_addr = dma_addr;
+	*buf_phys_addr = virt_to_phys(data);
 
 	return data;
 }
@@ -3604,37 +3930,46 @@ static inline int mvpp2_bm_cookie_pool_get(unsigned long cookie)
 
 /* Release buffer to BM */
 static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool,
-				     dma_addr_t buf_phys_addr,
-				     unsigned long buf_virt_addr)
+				     dma_addr_t buf_dma_addr,
+				     phys_addr_t buf_phys_addr)
 {
-	mvpp2_write(port->priv, MVPP2_BM_VIRT_RLS_REG, buf_virt_addr);
-	mvpp2_write(port->priv, MVPP2_BM_PHY_RLS_REG(pool), buf_phys_addr);
-}
+	int cpu = smp_processor_id();
 
-/* Release multicast buffer */
-static void mvpp2_bm_pool_mc_put(struct mvpp2_port *port, int pool,
-				 dma_addr_t buf_phys_addr,
-				 unsigned long buf_virt_addr,
-				 int mc_id)
-{
-	u32 val = 0;
+	if (port->priv->hw_version == MVPP22) {
+		u32 val = 0;
+
+		if (sizeof(dma_addr_t) == 8)
+			val |= upper_32_bits(buf_dma_addr) &
+				MVPP22_BM_ADDR_HIGH_PHYS_RLS_MASK;
+
+		if (sizeof(phys_addr_t) == 8)
+			val |= (upper_32_bits(buf_phys_addr)
+				<< MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT) &
+				MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK;
 
-	val |= (mc_id & MVPP2_BM_MC_ID_MASK);
-	mvpp2_write(port->priv, MVPP2_BM_MC_RLS_REG, val);
+		mvpp2_percpu_write(port->priv, cpu,
+				   MVPP22_BM_ADDR_HIGH_RLS_REG, val);
+	}
 
-	mvpp2_bm_pool_put(port, pool,
-			  buf_phys_addr | MVPP2_BM_PHY_RLS_MC_BUFF_MASK,
-			  buf_virt_addr);
+	/* MVPP2_BM_VIRT_RLS_REG is not interpreted by HW, and simply
+	 * returned in the "cookie" field of the RX
+	 * descriptor. Instead of storing the virtual address, we
+	 * store the physical address
+	 */
+	mvpp2_percpu_write(port->priv, cpu,
+			   MVPP2_BM_VIRT_RLS_REG, buf_phys_addr);
+	mvpp2_percpu_write(port->priv, cpu,
+			   MVPP2_BM_PHY_RLS_REG(pool), buf_dma_addr);
 }
 
 /* Refill BM pool */
 static void mvpp2_pool_refill(struct mvpp2_port *port, u32 bm,
-			      dma_addr_t phys_addr,
-			      unsigned long cookie)
+			      dma_addr_t dma_addr,
+			      phys_addr_t phys_addr)
 {
 	int pool = mvpp2_bm_cookie_pool_get(bm);
 
-	mvpp2_bm_pool_put(port, pool, phys_addr, cookie);
+	mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr);
 }
 
 /* Allocate buffers for the pool */
@@ -3642,7 +3977,8 @@ static int mvpp2_bm_bufs_add(struct mvpp2_port *port,
 			     struct mvpp2_bm_pool *bm_pool, int buf_num)
 {
 	int i, buf_size, total_size;
-	dma_addr_t phys_addr;
+	dma_addr_t dma_addr;
+	phys_addr_t phys_addr;
 	void *buf;
 
 	buf_size = MVPP2_RX_BUF_SIZE(bm_pool->pkt_size);
@@ -3657,12 +3993,13 @@ static int mvpp2_bm_bufs_add(struct mvpp2_port *port,
 	}
 
 	for (i = 0; i < buf_num; i++) {
-		buf = mvpp2_buf_alloc(port, bm_pool, &phys_addr, GFP_KERNEL);
+		buf = mvpp2_buf_alloc(port, bm_pool, &dma_addr,
+				      &phys_addr, GFP_KERNEL);
 		if (!buf)
 			break;
 
-		mvpp2_bm_pool_put(port, bm_pool->id, phys_addr,
-				  (unsigned long)buf);
+		mvpp2_bm_pool_put(port, bm_pool->id, dma_addr,
+				  phys_addr);
 	}
 
 	/* Update BM driver with number of buffers added to pool */
@@ -3830,7 +4167,8 @@ static void mvpp2_interrupts_mask(void *arg)
 {
 	struct mvpp2_port *port = arg;
 
-	mvpp2_write(port->priv, MVPP2_ISR_RX_TX_MASK_REG(port->id), 0);
+	mvpp2_percpu_write(port->priv, smp_processor_id(),
+			   MVPP2_ISR_RX_TX_MASK_REG(port->id), 0);
 }
 
 /* Unmask the current CPU's Rx/Tx interrupts */
@@ -3838,17 +4176,46 @@ static void mvpp2_interrupts_unmask(void *arg)
 {
 	struct mvpp2_port *port = arg;
 
-	mvpp2_write(port->priv, MVPP2_ISR_RX_TX_MASK_REG(port->id),
-		    (MVPP2_CAUSE_MISC_SUM_MASK |
-		     MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK));
+	mvpp2_percpu_write(port->priv, smp_processor_id(),
+			   MVPP2_ISR_RX_TX_MASK_REG(port->id),
+			   (MVPP2_CAUSE_MISC_SUM_MASK |
+			    MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK));
 }
 
 /* Port configuration routines */
 
+static void mvpp22_port_mii_set(struct mvpp2_port *port)
+{
+	u32 val;
+
+	return;
+
+	/* Only GOP port 0 has an XLG MAC */
+	if (port->gop_id == 0) {
+		val = readl(port->base + MVPP22_XLG_CTRL3_REG);
+		val &= ~MVPP22_XLG_CTRL3_MACMODESELECT_MASK;
+		val |= MVPP22_XLG_CTRL3_MACMODESELECT_GMAC;
+		writel(val, port->base + MVPP22_XLG_CTRL3_REG);
+	}
+
+	val = readl(port->base + MVPP22_GMAC_CTRL_4_REG);
+	if (port->phy_interface == PHY_INTERFACE_MODE_RGMII)
+		val |= MVPP22_CTRL4_EXT_PIN_GMII_SEL;
+	else
+		val &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL;
+	val &= ~MVPP22_CTRL4_DP_CLK_SEL;
+	val |= MVPP22_CTRL4_SYNC_BYPASS;
+	val |= MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
+	writel(val, port->base + MVPP22_GMAC_CTRL_4_REG);
+}
+
 static void mvpp2_port_mii_set(struct mvpp2_port *port)
 {
 	u32 val;
 
+	if (port->priv->hw_version == MVPP22)
+		mvpp22_port_mii_set(port);
+
 	val = readl(port->base + MVPP2_GMAC_CTRL_2_REG);
 
 	switch (port->phy_interface) {
@@ -3952,16 +4319,18 @@ static void mvpp2_defaults_set(struct mvpp2_port *port)
 {
 	int tx_port_num, val, queue, ptxq, lrxq;
 
-	/* Configure port to loopback if needed */
-	if (port->flags & MVPP2_F_LOOPBACK)
-		mvpp2_port_loopback_set(port);
+	if (port->priv->hw_version == MVPP21) {
+		/* Configure port to loopback if needed */
+		if (port->flags & MVPP2_F_LOOPBACK)
+			mvpp2_port_loopback_set(port);
 
-	/* Update TX FIFO MIN Threshold */
-	val = readl(port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG);
-	val &= ~MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK;
-	/* Min. TX threshold must be less than minimal packet length */
-	val |= MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(64 - 4 - 2);
-	writel(val, port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG);
+		/* Update TX FIFO MIN Threshold */
+		val = readl(port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG);
+		val &= ~MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK;
+		/* Min. TX threshold must be less than minimal packet length */
+		val |= MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(64 - 4 - 2);
+		writel(val, port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG);
+	}
 
 	/* Disable Legacy WRR, Disable EJP, Release from reset */
 	tx_port_num = mvpp2_egress_port(port);
@@ -4149,11 +4518,15 @@ static void mvpp2_rxq_offset_set(struct mvpp2_port *port,
 }
 
 /* Obtain BM cookie information from descriptor */
-static u32 mvpp2_bm_cookie_build(struct mvpp2_rx_desc *rx_desc)
+static u32 mvpp2_bm_cookie_build(struct mvpp2_port *port,
+				 struct mvpp2_rx_desc *rx_desc)
 {
-	int pool = (rx_desc->status & MVPP2_RXD_BM_POOL_ID_MASK) >>
-		   MVPP2_RXD_BM_POOL_ID_OFFS;
 	int cpu = smp_processor_id();
+	int pool;
+
+	pool = (mvpp2_rxdesc_status_get(port, rx_desc) &
+		MVPP2_RXD_BM_POOL_ID_MASK) >>
+		MVPP2_RXD_BM_POOL_ID_OFFS;
 
 	return ((pool & 0xFF) << MVPP2_BM_COOKIE_POOL_OFFS) |
 	       ((cpu & 0xFF) << MVPP2_BM_COOKIE_CPU_OFFS);
@@ -4161,18 +4534,6 @@ static u32 mvpp2_bm_cookie_build(struct mvpp2_rx_desc *rx_desc)
 
 /* Tx descriptors helper methods */
 
-/* Get number of Tx descriptors waiting to be transmitted by HW */
-static int mvpp2_txq_pend_desc_num_get(struct mvpp2_port *port,
-				       struct mvpp2_tx_queue *txq)
-{
-	u32 val;
-
-	mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id);
-	val = mvpp2_read(port->priv, MVPP2_TXQ_PENDING_REG);
-
-	return val & MVPP2_TXQ_PENDING_MASK;
-}
-
 /* Get pointer to next Tx descriptor to be processed (send) by HW */
 static struct mvpp2_tx_desc *
 mvpp2_txq_next_desc_get(struct mvpp2_tx_queue *txq)
@@ -4187,7 +4548,8 @@ mvpp2_txq_next_desc_get(struct mvpp2_tx_queue *txq)
 static void mvpp2_aggr_txq_pend_desc_add(struct mvpp2_port *port, int pending)
 {
 	/* aggregated access - relevant TXQ number is written in TX desc */
-	mvpp2_write(port->priv, MVPP2_AGGR_TXQ_UPDATE_REG, pending);
+	mvpp2_percpu_write(port->priv, smp_processor_id(),
+			   MVPP2_AGGR_TXQ_UPDATE_REG, pending);
 }
 
 
@@ -4216,11 +4578,12 @@ static int mvpp2_txq_alloc_reserved_desc(struct mvpp2 *priv,
 					 struct mvpp2_tx_queue *txq, int num)
 {
 	u32 val;
+	int cpu = smp_processor_id();
 
 	val = (txq->id << MVPP2_TXQ_RSVD_REQ_Q_OFFSET) | num;
-	mvpp2_write(priv, MVPP2_TXQ_RSVD_REQ_REG, val);
+	mvpp2_percpu_write(priv, cpu, MVPP2_TXQ_RSVD_REQ_REG, val);
 
-	val = mvpp2_read(priv, MVPP2_TXQ_RSVD_RSLT_REG);
+	val = mvpp2_percpu_read(priv, cpu, MVPP2_TXQ_RSVD_RSLT_REG);
 
 	return val & MVPP2_TXQ_RSVD_RSLT_MASK;
 }
@@ -4321,7 +4684,8 @@ static inline int mvpp2_txq_sent_desc_proc(struct mvpp2_port *port,
 	u32 val;
 
 	/* Reading status reg resets transmitted descriptor counter */
-	val = mvpp2_read(port->priv, MVPP2_TXQ_SENT_REG(txq->id));
+	val = mvpp2_percpu_read(port->priv, smp_processor_id(),
+				MVPP2_TXQ_SENT_REG(txq->id));
 
 	return (val & MVPP2_TRANSMITTED_COUNT_MASK) >>
 		MVPP2_TRANSMITTED_COUNT_OFFSET;
@@ -4335,7 +4699,8 @@ static void mvpp2_txq_sent_counter_clear(void *arg)
 	for (queue = 0; queue < txq_number; queue++) {
 		int id = port->txqs[queue]->id;
 
-		mvpp2_read(port->priv, MVPP2_TXQ_SENT_REG(id));
+		mvpp2_percpu_read(port->priv, smp_processor_id(),
+				  MVPP2_TXQ_SENT_REG(id));
 	}
 }
 
@@ -4394,12 +4759,14 @@ static void mvpp2_txp_max_tx_size_set(struct mvpp2_port *port)
 static void mvpp2_rx_pkts_coal_set(struct mvpp2_port *port,
 				   struct mvpp2_rx_queue *rxq)
 {
+	int cpu = smp_processor_id();
+
 	if (rxq->pkts_coal > MVPP2_OCCUPIED_THRESH_MASK)
 		rxq->pkts_coal = MVPP2_OCCUPIED_THRESH_MASK;
 
-	mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id);
-	mvpp2_write(port->priv, MVPP2_RXQ_THRESH_REG,
-		    rxq->pkts_coal);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_THRESH_REG,
+			   rxq->pkts_coal);
 }
 
 static u32 mvpp2_usec_to_cycles(u32 usec, unsigned long clk_hz)
@@ -4449,7 +4816,7 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port,
 		struct mvpp2_txq_pcpu_buf *tx_buf =
 			txq_pcpu->buffs + txq_pcpu->txq_get_index;
 
-		dma_unmap_single(port->dev->dev.parent, tx_buf->phys,
+		dma_unmap_single(port->dev->dev.parent, tx_buf->dma,
 				 tx_buf->size, DMA_TO_DEVICE);
 		if (tx_buf->skb)
 			dev_kfree_skb_any(tx_buf->skb);
@@ -4527,10 +4894,12 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev,
 			       int desc_num, int cpu,
 			       struct mvpp2 *priv)
 {
+	u32 txq_dma;
+
 	/* Allocate memory for TX descriptors */
 	aggr_txq->descs = dma_alloc_coherent(&pdev->dev,
 				desc_num * MVPP2_DESC_ALIGNED_SIZE,
-				&aggr_txq->descs_phys, GFP_KERNEL);
+				&aggr_txq->descs_dma, GFP_KERNEL);
 	if (!aggr_txq->descs)
 		return -ENOMEM;
 
@@ -4540,10 +4909,16 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev,
 	aggr_txq->next_desc_to_proc = mvpp2_read(priv,
 						 MVPP2_AGGR_TXQ_INDEX_REG(cpu));
 
-	/* Set Tx descriptors queue starting address */
-	/* indirect access */
-	mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu),
-		    aggr_txq->descs_phys);
+	/* Set Tx descriptors queue starting address indirect
+	 * access
+	 */
+	if (priv->hw_version == MVPP21)
+		txq_dma = aggr_txq->descs_dma;
+	else
+		txq_dma = aggr_txq->descs_dma >>
+			MVPP22_AGGR_TXQ_DESC_ADDR_OFFS;
+
+	mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu), txq_dma);
 	mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_SIZE_REG(cpu), desc_num);
 
 	return 0;
@@ -4554,12 +4929,15 @@ static int mvpp2_rxq_init(struct mvpp2_port *port,
 			  struct mvpp2_rx_queue *rxq)
 
 {
+	u32 rxq_dma;
+	int cpu;
+
 	rxq->size = port->rx_ring_size;
 
 	/* Allocate memory for RX descriptors */
 	rxq->descs = dma_alloc_coherent(port->dev->dev.parent,
 					rxq->size * MVPP2_DESC_ALIGNED_SIZE,
-					&rxq->descs_phys, GFP_KERNEL);
+					&rxq->descs_dma, GFP_KERNEL);
 	if (!rxq->descs)
 		return -ENOMEM;
 
@@ -4569,10 +4947,15 @@ static int mvpp2_rxq_init(struct mvpp2_port *port,
 	mvpp2_write(port->priv, MVPP2_RXQ_STATUS_REG(rxq->id), 0);
 
 	/* Set Rx descriptors queue starting address - indirect access */
-	mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id);
-	mvpp2_write(port->priv, MVPP2_RXQ_DESC_ADDR_REG, rxq->descs_phys);
-	mvpp2_write(port->priv, MVPP2_RXQ_DESC_SIZE_REG, rxq->size);
-	mvpp2_write(port->priv, MVPP2_RXQ_INDEX_REG, 0);
+	cpu = smp_processor_id();
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id);
+	if (port->priv->hw_version == MVPP21)
+		rxq_dma = rxq->descs_dma;
+	else
+		rxq_dma = rxq->descs_dma >> MVPP22_DESC_ADDR_OFFS;
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_ADDR_REG, rxq_dma);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_SIZE_REG, rxq->size);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_INDEX_REG, 0);
 
 	/* Set Offset */
 	mvpp2_rxq_offset_set(port, rxq->id, NET_SKB_PAD);
@@ -4599,10 +4982,11 @@ static void mvpp2_rxq_drop_pkts(struct mvpp2_port *port,
 
 	for (i = 0; i < rx_received; i++) {
 		struct mvpp2_rx_desc *rx_desc = mvpp2_rxq_next_desc_get(rxq);
-		u32 bm = mvpp2_bm_cookie_build(rx_desc);
+		u32 bm = mvpp2_bm_cookie_build(port, rx_desc);
 
-		mvpp2_pool_refill(port, bm, rx_desc->buf_phys_addr,
-				  rx_desc->buf_cookie);
+		mvpp2_pool_refill(port, bm,
+				  mvpp2_rxdesc_dma_addr_get(port, rx_desc),
+				  mvpp2_rxdesc_cookie_get(port, rx_desc));
 	}
 	mvpp2_rxq_status_update(port, rxq->id, rx_received, rx_received);
 }
@@ -4611,26 +4995,29 @@ static void mvpp2_rxq_drop_pkts(struct mvpp2_port *port,
 static void mvpp2_rxq_deinit(struct mvpp2_port *port,
 			     struct mvpp2_rx_queue *rxq)
 {
+	int cpu;
+
 	mvpp2_rxq_drop_pkts(port, rxq);
 
 	if (rxq->descs)
 		dma_free_coherent(port->dev->dev.parent,
 				  rxq->size * MVPP2_DESC_ALIGNED_SIZE,
 				  rxq->descs,
-				  rxq->descs_phys);
+				  rxq->descs_dma);
 
 	rxq->descs             = NULL;
 	rxq->last_desc         = 0;
 	rxq->next_desc_to_proc = 0;
-	rxq->descs_phys        = 0;
+	rxq->descs_dma         = 0;
 
 	/* Clear Rx descriptors queue starting address and size;
 	 * free descriptor number
 	 */
 	mvpp2_write(port->priv, MVPP2_RXQ_STATUS_REG(rxq->id), 0);
-	mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id);
-	mvpp2_write(port->priv, MVPP2_RXQ_DESC_ADDR_REG, 0);
-	mvpp2_write(port->priv, MVPP2_RXQ_DESC_SIZE_REG, 0);
+	cpu = smp_processor_id();
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_ADDR_REG, 0);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_SIZE_REG, 0);
 }
 
 /* Create and initialize a Tx queue */
@@ -4646,23 +5033,25 @@ static int mvpp2_txq_init(struct mvpp2_port *port,
 	/* Allocate memory for Tx descriptors */
 	txq->descs = dma_alloc_coherent(port->dev->dev.parent,
 				txq->size * MVPP2_DESC_ALIGNED_SIZE,
-				&txq->descs_phys, GFP_KERNEL);
+				&txq->descs_dma, GFP_KERNEL);
 	if (!txq->descs)
 		return -ENOMEM;
 
 	txq->last_desc = txq->size - 1;
 
 	/* Set Tx descriptors queue starting address - indirect access */
-	mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id);
-	mvpp2_write(port->priv, MVPP2_TXQ_DESC_ADDR_REG, txq->descs_phys);
-	mvpp2_write(port->priv, MVPP2_TXQ_DESC_SIZE_REG, txq->size &
-					     MVPP2_TXQ_DESC_SIZE_MASK);
-	mvpp2_write(port->priv, MVPP2_TXQ_INDEX_REG, 0);
-	mvpp2_write(port->priv, MVPP2_TXQ_RSVD_CLR_REG,
-		    txq->id << MVPP2_TXQ_RSVD_CLR_OFFSET);
-	val = mvpp2_read(port->priv, MVPP2_TXQ_PENDING_REG);
+	cpu = smp_processor_id();
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_ADDR_REG,
+			   txq->descs_dma);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_SIZE_REG,
+			   txq->size & MVPP2_TXQ_DESC_SIZE_MASK);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_INDEX_REG, 0);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_RSVD_CLR_REG,
+			   txq->id << MVPP2_TXQ_RSVD_CLR_OFFSET);
+	val = mvpp2_percpu_read(port->priv, cpu, MVPP2_TXQ_PENDING_REG);
 	val &= ~MVPP2_TXQ_PENDING_MASK;
-	mvpp2_write(port->priv, MVPP2_TXQ_PENDING_REG, val);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PENDING_REG, val);
 
 	/* Calculate base address in prefetch buffer. We reserve 16 descriptors
 	 * for each existing TXQ.
@@ -4673,9 +5062,9 @@ static int mvpp2_txq_init(struct mvpp2_port *port,
 	desc = (port->id * MVPP2_MAX_TXQ * desc_per_txq) +
 	       (txq->log_id * desc_per_txq);
 
-	mvpp2_write(port->priv, MVPP2_TXQ_PREF_BUF_REG,
-		    MVPP2_PREF_BUF_PTR(desc) | MVPP2_PREF_BUF_SIZE_16 |
-		    MVPP2_PREF_BUF_THRESH(desc_per_txq/2));
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG,
+			   MVPP2_PREF_BUF_PTR(desc) | MVPP2_PREF_BUF_SIZE_16 |
+			   MVPP2_PREF_BUF_THRESH(desc_per_txq / 2));
 
 	/* WRR / EJP configuration - indirect access */
 	tx_port_num = mvpp2_egress_port(port);
@@ -4716,7 +5105,7 @@ error:
 
 	dma_free_coherent(port->dev->dev.parent,
 			  txq->size * MVPP2_DESC_ALIGNED_SIZE,
-			  txq->descs, txq->descs_phys);
+			  txq->descs, txq->descs_dma);
 
 	return -ENOMEM;
 }
@@ -4736,20 +5125,21 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port,
 	if (txq->descs)
 		dma_free_coherent(port->dev->dev.parent,
 				  txq->size * MVPP2_DESC_ALIGNED_SIZE,
-				  txq->descs, txq->descs_phys);
+				  txq->descs, txq->descs_dma);
 
 	txq->descs             = NULL;
 	txq->last_desc         = 0;
 	txq->next_desc_to_proc = 0;
-	txq->descs_phys        = 0;
+	txq->descs_dma         = 0;
 
 	/* Set minimum bandwidth for disabled TXQs */
 	mvpp2_write(port->priv, MVPP2_TXQ_SCHED_TOKEN_CNTR_REG(txq->id), 0);
 
 	/* Set Tx descriptors queue starting address and size */
-	mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id);
-	mvpp2_write(port->priv, MVPP2_TXQ_DESC_ADDR_REG, 0);
-	mvpp2_write(port->priv, MVPP2_TXQ_DESC_SIZE_REG, 0);
+	cpu = smp_processor_id();
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_ADDR_REG, 0);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_SIZE_REG, 0);
 }
 
 /* Cleanup Tx ports */
@@ -4759,10 +5149,11 @@ static void mvpp2_txq_clean(struct mvpp2_port *port, struct mvpp2_tx_queue *txq)
 	int delay, pending, cpu;
 	u32 val;
 
-	mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id);
-	val = mvpp2_read(port->priv, MVPP2_TXQ_PREF_BUF_REG);
+	cpu = smp_processor_id();
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id);
+	val = mvpp2_percpu_read(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG);
 	val |= MVPP2_TXQ_DRAIN_EN_MASK;
-	mvpp2_write(port->priv, MVPP2_TXQ_PREF_BUF_REG, val);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, val);
 
 	/* The napi queue has been stopped so wait for all packets
 	 * to be transmitted.
@@ -4778,11 +5169,13 @@ static void mvpp2_txq_clean(struct mvpp2_port *port, struct mvpp2_tx_queue *txq)
 		mdelay(1);
 		delay++;
 
-		pending = mvpp2_txq_pend_desc_num_get(port, txq);
+		pending = mvpp2_percpu_read(port->priv, cpu,
+					    MVPP2_TXQ_PENDING_REG);
+		pending &= MVPP2_TXQ_PENDING_MASK;
 	} while (pending);
 
 	val &= ~MVPP2_TXQ_DRAIN_EN_MASK;
-	mvpp2_write(port->priv, MVPP2_TXQ_PREF_BUF_REG, val);
+	mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, val);
 
 	for_each_present_cpu(cpu) {
 		txq_pcpu = per_cpu_ptr(txq->pcpu, cpu);
@@ -4991,20 +5384,21 @@ static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer)
 static void mvpp2_rx_error(struct mvpp2_port *port,
 			   struct mvpp2_rx_desc *rx_desc)
 {
-	u32 status = rx_desc->status;
+	u32 status = mvpp2_rxdesc_status_get(port, rx_desc);
+	size_t sz = mvpp2_rxdesc_size_get(port, rx_desc);
 
 	switch (status & MVPP2_RXD_ERR_CODE_MASK) {
 	case MVPP2_RXD_ERR_CRC:
-		netdev_err(port->dev, "bad rx status %08x (crc error), size=%d\n",
-			   status, rx_desc->data_size);
+		netdev_err(port->dev, "bad rx status %08x (crc error), size=%zu\n",
+			   status, sz);
 		break;
 	case MVPP2_RXD_ERR_OVERRUN:
-		netdev_err(port->dev, "bad rx status %08x (overrun error), size=%d\n",
-			   status, rx_desc->data_size);
+		netdev_err(port->dev, "bad rx status %08x (overrun error), size=%zu\n",
+			   status, sz);
 		break;
 	case MVPP2_RXD_ERR_RESOURCE:
-		netdev_err(port->dev, "bad rx status %08x (resource error), size=%d\n",
-			   status, rx_desc->data_size);
+		netdev_err(port->dev, "bad rx status %08x (resource error), size=%zu\n",
+			   status, sz);
 		break;
 	}
 }
@@ -5031,15 +5425,17 @@ static void mvpp2_rx_csum(struct mvpp2_port *port, u32 status,
 static int mvpp2_rx_refill(struct mvpp2_port *port,
 			   struct mvpp2_bm_pool *bm_pool, u32 bm)
 {
-	dma_addr_t phys_addr;
+	dma_addr_t dma_addr;
+	phys_addr_t phys_addr;
 	void *buf;
 
 	/* No recycle or too many buffers are in use, so allocate a new skb */
-	buf = mvpp2_buf_alloc(port, bm_pool, &phys_addr, GFP_ATOMIC);
+	buf = mvpp2_buf_alloc(port, bm_pool, &dma_addr, &phys_addr,
+			      GFP_ATOMIC);
 	if (!buf)
 		return -ENOMEM;
 
-	mvpp2_pool_refill(port, bm, phys_addr, (unsigned long)buf);
+	mvpp2_pool_refill(port, bm, dma_addr, phys_addr);
 
 	return 0;
 }
@@ -5075,43 +5471,6 @@ static u32 mvpp2_skb_tx_csum(struct mvpp2_port *port, struct sk_buff *skb)
 	return MVPP2_TXD_L4_CSUM_NOT | MVPP2_TXD_IP_CSUM_DISABLE;
 }
 
-static void mvpp2_buff_hdr_rx(struct mvpp2_port *port,
-			      struct mvpp2_rx_desc *rx_desc)
-{
-	struct mvpp2_buff_hdr *buff_hdr;
-	struct sk_buff *skb;
-	u32 rx_status = rx_desc->status;
-	dma_addr_t buff_phys_addr;
-	unsigned long buff_virt_addr;
-	dma_addr_t buff_phys_addr_next;
-	unsigned long buff_virt_addr_next;
-	int mc_id;
-	int pool_id;
-
-	pool_id = (rx_status & MVPP2_RXD_BM_POOL_ID_MASK) >>
-		   MVPP2_RXD_BM_POOL_ID_OFFS;
-	buff_phys_addr = rx_desc->buf_phys_addr;
-	buff_virt_addr = rx_desc->buf_cookie;
-
-	do {
-		skb = (struct sk_buff *)buff_virt_addr;
-		buff_hdr = (struct mvpp2_buff_hdr *)skb->head;
-
-		mc_id = MVPP2_B_HDR_INFO_MC_ID(buff_hdr->info);
-
-		buff_phys_addr_next = buff_hdr->next_buff_phys_addr;
-		buff_virt_addr_next = buff_hdr->next_buff_virt_addr;
-
-		/* Release buffer */
-		mvpp2_bm_pool_mc_put(port, pool_id, buff_phys_addr,
-				     buff_virt_addr, mc_id);
-
-		buff_phys_addr = buff_phys_addr_next;
-		buff_virt_addr = buff_virt_addr_next;
-
-	} while (!MVPP2_B_HDR_INFO_IS_LAST(buff_hdr->info));
-}
-
 /* Main rx processing */
 static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
 		    struct mvpp2_rx_queue *rxq)
@@ -5132,25 +5491,23 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
 		struct mvpp2_bm_pool *bm_pool;
 		struct sk_buff *skb;
 		unsigned int frag_size;
-		dma_addr_t phys_addr;
+		dma_addr_t dma_addr;
+		phys_addr_t phys_addr;
 		u32 bm, rx_status;
 		int pool, rx_bytes, err;
 		void *data;
 
 		rx_done++;
-		rx_status = rx_desc->status;
-		rx_bytes = rx_desc->data_size - MVPP2_MH_SIZE;
-		phys_addr = rx_desc->buf_phys_addr;
-		data = (void *)(uintptr_t)rx_desc->buf_cookie;
-
-		bm = mvpp2_bm_cookie_build(rx_desc);
+		rx_status = mvpp2_rxdesc_status_get(port, rx_desc);
+		rx_bytes = mvpp2_rxdesc_size_get(port, rx_desc);
+		rx_bytes -= MVPP2_MH_SIZE;
+		dma_addr = mvpp2_rxdesc_dma_addr_get(port, rx_desc);
+		phys_addr = mvpp2_rxdesc_cookie_get(port, rx_desc);
+		data = (void *)phys_to_virt(phys_addr);
+
+		bm = mvpp2_bm_cookie_build(port, rx_desc);
 		pool = mvpp2_bm_cookie_pool_get(bm);
 		bm_pool = &port->priv->bm_pools[pool];
-		/* Check if buffer header is used */
-		if (rx_status & MVPP2_RXD_BUF_HDR) {
-			mvpp2_buff_hdr_rx(port, rx_desc);
-			continue;
-		}
 
 		/* In case of an error, release the requested buffer pointer
 		 * to the Buffer Manager. This request process is controlled
@@ -5162,9 +5519,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
 			dev->stats.rx_errors++;
 			mvpp2_rx_error(port, rx_desc);
 			/* Return the buffer to the pool */
-
-			mvpp2_pool_refill(port, bm, rx_desc->buf_phys_addr,
-					  rx_desc->buf_cookie);
+			mvpp2_pool_refill(port, bm, dma_addr, phys_addr);
 			continue;
 		}
 
@@ -5185,7 +5540,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
 			goto err_drop_frame;
 		}
 
-		dma_unmap_single(dev->dev.parent, phys_addr,
+		dma_unmap_single(dev->dev.parent, dma_addr,
 				 bm_pool->buf_size, DMA_FROM_DEVICE);
 
 		rcvd_pkts++;
@@ -5216,11 +5571,15 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
 }
 
 static inline void
-tx_desc_unmap_put(struct device *dev, struct mvpp2_tx_queue *txq,
+tx_desc_unmap_put(struct mvpp2_port *port, struct mvpp2_tx_queue *txq,
 		  struct mvpp2_tx_desc *desc)
 {
-	dma_unmap_single(dev, desc->buf_phys_addr,
-			 desc->data_size, DMA_TO_DEVICE);
+	dma_addr_t buf_dma_addr =
+		mvpp2_txdesc_dma_addr_get(port, desc);
+	size_t buf_sz =
+		mvpp2_txdesc_size_get(port, desc);
+	dma_unmap_single(port->dev->dev.parent, buf_dma_addr,
+			 buf_sz, DMA_TO_DEVICE);
 	mvpp2_txq_desc_put(txq);
 }
 
@@ -5232,35 +5591,38 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb,
 	struct mvpp2_txq_pcpu *txq_pcpu = this_cpu_ptr(txq->pcpu);
 	struct mvpp2_tx_desc *tx_desc;
 	int i;
-	dma_addr_t buf_phys_addr;
+	dma_addr_t buf_dma_addr;
 
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 		void *addr = page_address(frag->page.p) + frag->page_offset;
 
 		tx_desc = mvpp2_txq_next_desc_get(aggr_txq);
-		tx_desc->phys_txq = txq->id;
-		tx_desc->data_size = frag->size;
+		mvpp2_txdesc_txq_set(port, tx_desc, txq->id);
+		mvpp2_txdesc_size_set(port, tx_desc, frag->size);
 
-		buf_phys_addr = dma_map_single(port->dev->dev.parent, addr,
-					       tx_desc->data_size,
+		buf_dma_addr = dma_map_single(port->dev->dev.parent, addr,
+					       frag->size,
 					       DMA_TO_DEVICE);
-		if (dma_mapping_error(port->dev->dev.parent, buf_phys_addr)) {
+		if (dma_mapping_error(port->dev->dev.parent, buf_dma_addr)) {
 			mvpp2_txq_desc_put(txq);
 			goto error;
 		}
 
-		tx_desc->packet_offset = buf_phys_addr & MVPP2_TX_DESC_ALIGN;
-		tx_desc->buf_phys_addr = buf_phys_addr & (~MVPP2_TX_DESC_ALIGN);
+		mvpp2_txdesc_offset_set(port, tx_desc,
+					buf_dma_addr & MVPP2_TX_DESC_ALIGN);
+		mvpp2_txdesc_dma_addr_set(port, tx_desc,
+					  buf_dma_addr & ~MVPP2_TX_DESC_ALIGN);
 
 		if (i == (skb_shinfo(skb)->nr_frags - 1)) {
 			/* Last descriptor */
-			tx_desc->command = MVPP2_TXD_L_DESC;
-			mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc);
+			mvpp2_txdesc_cmd_set(port, tx_desc,
+					     MVPP2_TXD_L_DESC);
+			mvpp2_txq_inc_put(port, txq_pcpu, skb, tx_desc);
 		} else {
 			/* Descriptor in the middle: Not First, Not Last */
-			tx_desc->command = 0;
-			mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc);
+			mvpp2_txdesc_cmd_set(port, tx_desc, 0);
+			mvpp2_txq_inc_put(port, txq_pcpu, NULL, tx_desc);
 		}
 	}
 
@@ -5272,7 +5634,7 @@ error:
 	 */
 	for (i = i - 1; i >= 0; i--) {
 		tx_desc = txq->descs + i;
-		tx_desc_unmap_put(port->dev->dev.parent, txq, tx_desc);
+		tx_desc_unmap_put(port, txq, tx_desc);
 	}
 
 	return -ENOMEM;
@@ -5285,7 +5647,7 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev)
 	struct mvpp2_tx_queue *txq, *aggr_txq;
 	struct mvpp2_txq_pcpu *txq_pcpu;
 	struct mvpp2_tx_desc *tx_desc;
-	dma_addr_t buf_phys_addr;
+	dma_addr_t buf_dma_addr;
 	int frags = 0;
 	u16 txq_id;
 	u32 tx_cmd;
@@ -5307,35 +5669,38 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev)
 
 	/* Get a descriptor for the first part of the packet */
 	tx_desc = mvpp2_txq_next_desc_get(aggr_txq);
-	tx_desc->phys_txq = txq->id;
-	tx_desc->data_size = skb_headlen(skb);
+	mvpp2_txdesc_txq_set(port, tx_desc, txq->id);
+	mvpp2_txdesc_size_set(port, tx_desc, skb_headlen(skb));
 
-	buf_phys_addr = dma_map_single(dev->dev.parent, skb->data,
-				       tx_desc->data_size, DMA_TO_DEVICE);
-	if (unlikely(dma_mapping_error(dev->dev.parent, buf_phys_addr))) {
+	buf_dma_addr = dma_map_single(dev->dev.parent, skb->data,
+				      skb_headlen(skb), DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(dev->dev.parent, buf_dma_addr))) {
 		mvpp2_txq_desc_put(txq);
 		frags = 0;
 		goto out;
 	}
-	tx_desc->packet_offset = buf_phys_addr & MVPP2_TX_DESC_ALIGN;
-	tx_desc->buf_phys_addr = buf_phys_addr & ~MVPP2_TX_DESC_ALIGN;
+
+	mvpp2_txdesc_offset_set(port, tx_desc,
+				buf_dma_addr & MVPP2_TX_DESC_ALIGN);
+	mvpp2_txdesc_dma_addr_set(port, tx_desc,
+				  buf_dma_addr & ~MVPP2_TX_DESC_ALIGN);
 
 	tx_cmd = mvpp2_skb_tx_csum(port, skb);
 
 	if (frags == 1) {
 		/* First and Last descriptor */
 		tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_L_DESC;
-		tx_desc->command = tx_cmd;
-		mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc);
+		mvpp2_txdesc_cmd_set(port, tx_desc, tx_cmd);
+		mvpp2_txq_inc_put(port, txq_pcpu, skb, tx_desc);
 	} else {
 		/* First but not Last */
 		tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_PADDING_DISABLE;
-		tx_desc->command = tx_cmd;
-		mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc);
+		mvpp2_txdesc_cmd_set(port, tx_desc, tx_cmd);
+		mvpp2_txq_inc_put(port, txq_pcpu, NULL, tx_desc);
 
 		/* Continue with other skb fragments */
 		if (mvpp2_tx_frag_process(port, skb, aggr_txq, txq)) {
-			tx_desc_unmap_put(port->dev->dev.parent, txq, tx_desc);
+			tx_desc_unmap_put(port, txq, tx_desc);
 			frags = 0;
 			goto out;
 		}
@@ -5396,6 +5761,7 @@ static int mvpp2_poll(struct napi_struct *napi, int budget)
 	u32 cause_rx_tx, cause_rx, cause_misc;
 	int rx_done = 0;
 	struct mvpp2_port *port = netdev_priv(napi->dev);
+	int cpu = smp_processor_id();
 
 	/* Rx/Tx cause register
 	 *
@@ -5407,8 +5773,8 @@ static int mvpp2_poll(struct napi_struct *napi, int budget)
 	 *
 	 * Each CPU has its own Rx/Tx cause register
 	 */
-	cause_rx_tx = mvpp2_read(port->priv,
-				 MVPP2_ISR_RX_TX_CAUSE_REG(port->id));
+	cause_rx_tx = mvpp2_percpu_read(port->priv, cpu,
+					MVPP2_ISR_RX_TX_CAUSE_REG(port->id));
 	cause_rx_tx &= ~MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK;
 	cause_misc = cause_rx_tx & MVPP2_CAUSE_MISC_SUM_MASK;
 
@@ -5417,8 +5783,9 @@ static int mvpp2_poll(struct napi_struct *napi, int budget)
 
 		/* Clear the cause register */
 		mvpp2_write(port->priv, MVPP2_ISR_MISC_CAUSE_REG, 0);
-		mvpp2_write(port->priv, MVPP2_ISR_RX_TX_CAUSE_REG(port->id),
-			    cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK);
+		mvpp2_percpu_write(port->priv, cpu,
+				   MVPP2_ISR_RX_TX_CAUSE_REG(port->id),
+				   cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK);
 	}
 
 	cause_rx = cause_rx_tx & MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK;
@@ -5530,7 +5897,7 @@ static int mvpp2_check_ringparam_valid(struct net_device *dev,
 	return 0;
 }
 
-static void mvpp2_get_mac_address(struct mvpp2_port *port, unsigned char *addr)
+static void mvpp21_get_mac_address(struct mvpp2_port *port, unsigned char *addr)
 {
 	u32 mac_addr_l, mac_addr_m, mac_addr_h;
 
@@ -5975,16 +6342,6 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = {
 	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
-/* Driver initialization */
-
-static void mvpp2_port_power_up(struct mvpp2_port *port)
-{
-	mvpp2_port_mii_set(port);
-	mvpp2_port_periodic_xon_disable(port);
-	mvpp2_port_fc_adv_enable(port);
-	mvpp2_port_reset(port);
-}
-
 /* Initialize port HW */
 static int mvpp2_port_init(struct mvpp2_port *port)
 {
@@ -5993,7 +6350,8 @@ static int mvpp2_port_init(struct mvpp2_port *port)
 	struct mvpp2_txq_pcpu *txq_pcpu;
 	int queue, cpu, err;
 
-	if (port->first_rxq + rxq_number > MVPP2_RXQ_TOTAL_NUM)
+	if (port->first_rxq + rxq_number >
+	    MVPP2_MAX_PORTS * priv->max_port_rxqs)
 		return -EINVAL;
 
 	/* Disable port */
@@ -6061,7 +6419,18 @@ static int mvpp2_port_init(struct mvpp2_port *port)
 	}
 
 	/* Configure Rx queue group interrupt for this port */
-	mvpp2_write(priv, MVPP2_ISR_RXQ_GROUP_REG(port->id), rxq_number);
+	if (priv->hw_version == MVPP21) {
+		mvpp2_write(priv, MVPP21_ISR_RXQ_GROUP_REG(port->id),
+			    rxq_number);
+	} else {
+		u32 val;
+
+		val = (port->id << MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET);
+		mvpp2_write(priv, MVPP22_ISR_RXQ_GROUP_INDEX_REG, val);
+
+		val = (rxq_number << MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET);
+		mvpp2_write(priv, MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG, val);
+	}
 
 	/* Create Rx descriptor rings */
 	for (queue = 0; queue < rxq_number; queue++) {
@@ -6103,8 +6472,7 @@ err_free_percpu:
 /* Ports initialization */
 static int mvpp2_port_probe(struct platform_device *pdev,
 			    struct device_node *port_node,
-			    struct mvpp2 *priv,
-			    int *next_first_rxq)
+			    struct mvpp2 *priv)
 {
 	struct device_node *phy_node;
 	struct mvpp2_port *port;
@@ -6117,7 +6485,6 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	u32 id;
 	int features;
 	int phy_mode;
-	int priv_common_regs_num = 2;
 	int err, i, cpu;
 
 	dev = alloc_etherdev_mqs(sizeof(struct mvpp2_port), txq_number,
@@ -6163,16 +6530,30 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 
 	port->priv = priv;
 	port->id = id;
-	port->first_rxq = *next_first_rxq;
+	if (priv->hw_version == MVPP21)
+		port->first_rxq = port->id * rxq_number;
+	else
+		port->first_rxq = port->id * priv->max_port_rxqs;
+
 	port->phy_node = phy_node;
 	port->phy_interface = phy_mode;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM,
-				    priv_common_regs_num + id);
-	port->base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(port->base)) {
-		err = PTR_ERR(port->base);
-		goto err_free_irq;
+	if (priv->hw_version == MVPP21) {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 2 + id);
+		port->base = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(port->base)) {
+			err = PTR_ERR(port->base);
+			goto err_free_irq;
+		}
+	} else {
+		if (of_property_read_u32(port_node, "gop-port-id",
+					 &port->gop_id)) {
+			err = -EINVAL;
+			dev_err(&pdev->dev, "missing gop-port-id value\n");
+			goto err_free_irq;
+		}
+
+		port->base = priv->iface_base + MVPP22_GMAC_BASE(port->gop_id);
 	}
 
 	/* Alloc per-cpu stats */
@@ -6187,7 +6568,8 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 		mac_from = "device tree";
 		ether_addr_copy(dev->dev_addr, dt_mac_addr);
 	} else {
-		mvpp2_get_mac_address(port, hw_mac_addr);
+		if (priv->hw_version == MVPP21)
+			mvpp21_get_mac_address(port, hw_mac_addr);
 		if (is_valid_ether_addr(hw_mac_addr)) {
 			mac_from = "hardware";
 			ether_addr_copy(dev->dev_addr, hw_mac_addr);
@@ -6207,7 +6589,14 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 		dev_err(&pdev->dev, "failed to init port %d\n", id);
 		goto err_free_stats;
 	}
-	mvpp2_port_power_up(port);
+
+	mvpp2_port_mii_set(port);
+	mvpp2_port_periodic_xon_disable(port);
+
+	if (priv->hw_version == MVPP21)
+		mvpp2_port_fc_adv_enable(port);
+
+	mvpp2_port_reset(port);
 
 	port->pcpu = alloc_percpu(struct mvpp2_port_pcpu);
 	if (!port->pcpu) {
@@ -6245,8 +6634,6 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	}
 	netdev_info(dev, "Using %s mac address %pM\n", mac_from, dev->dev_addr);
 
-	/* Increment the first Rx queue number to be used by the next port */
-	*next_first_rxq += rxq_number;
 	priv->port_list[id] = port;
 	return 0;
 
@@ -6330,6 +6717,60 @@ static void mvpp2_rx_fifo_init(struct mvpp2 *priv)
 	mvpp2_write(priv, MVPP2_RX_FIFO_INIT_REG, 0x1);
 }
 
+static void mvpp2_axi_init(struct mvpp2 *priv)
+{
+	u32 val, rdval, wrval;
+
+	mvpp2_write(priv, MVPP22_BM_ADDR_HIGH_RLS_REG, 0x0);
+
+	/* AXI Bridge Configuration */
+
+	rdval = MVPP22_AXI_CODE_CACHE_RD_CACHE
+		<< MVPP22_AXI_ATTR_CACHE_OFFS;
+	rdval |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM
+		<< MVPP22_AXI_ATTR_DOMAIN_OFFS;
+
+	wrval = MVPP22_AXI_CODE_CACHE_WR_CACHE
+		<< MVPP22_AXI_ATTR_CACHE_OFFS;
+	wrval |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM
+		<< MVPP22_AXI_ATTR_DOMAIN_OFFS;
+
+	/* BM */
+	mvpp2_write(priv, MVPP22_AXI_BM_WR_ATTR_REG, wrval);
+	mvpp2_write(priv, MVPP22_AXI_BM_RD_ATTR_REG, rdval);
+
+	/* Descriptors */
+	mvpp2_write(priv, MVPP22_AXI_AGGRQ_DESCR_RD_ATTR_REG, rdval);
+	mvpp2_write(priv, MVPP22_AXI_TXQ_DESCR_WR_ATTR_REG, wrval);
+	mvpp2_write(priv, MVPP22_AXI_TXQ_DESCR_RD_ATTR_REG, rdval);
+	mvpp2_write(priv, MVPP22_AXI_RXQ_DESCR_WR_ATTR_REG, wrval);
+
+	/* Buffer Data */
+	mvpp2_write(priv, MVPP22_AXI_TX_DATA_RD_ATTR_REG, rdval);
+	mvpp2_write(priv, MVPP22_AXI_RX_DATA_WR_ATTR_REG, wrval);
+
+	val = MVPP22_AXI_CODE_CACHE_NON_CACHE
+		<< MVPP22_AXI_CODE_CACHE_OFFS;
+	val |= MVPP22_AXI_CODE_DOMAIN_SYSTEM
+		<< MVPP22_AXI_CODE_DOMAIN_OFFS;
+	mvpp2_write(priv, MVPP22_AXI_RD_NORMAL_CODE_REG, val);
+	mvpp2_write(priv, MVPP22_AXI_WR_NORMAL_CODE_REG, val);
+
+	val = MVPP22_AXI_CODE_CACHE_RD_CACHE
+		<< MVPP22_AXI_CODE_CACHE_OFFS;
+	val |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM
+		<< MVPP22_AXI_CODE_DOMAIN_OFFS;
+
+	mvpp2_write(priv, MVPP22_AXI_RD_SNOOP_CODE_REG, val);
+
+	val = MVPP22_AXI_CODE_CACHE_WR_CACHE
+		<< MVPP22_AXI_CODE_CACHE_OFFS;
+	val |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM
+		<< MVPP22_AXI_CODE_DOMAIN_OFFS;
+
+	mvpp2_write(priv, MVPP22_AXI_WR_SNOOP_CODE_REG, val);
+}
+
 /* Initialize network controller common part HW */
 static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv)
 {
@@ -6338,7 +6779,7 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv)
 	u32 val;
 
 	/* Checks for hardware constraints */
-	if (rxq_number % 4 || (rxq_number > MVPP2_MAX_RXQ) ||
+	if (rxq_number % 4 || (rxq_number > priv->max_port_rxqs) ||
 	    (txq_number > MVPP2_MAX_TXQ)) {
 		dev_err(&pdev->dev, "invalid queue size parameter\n");
 		return -EINVAL;
@@ -6349,10 +6790,19 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv)
 	if (dram_target_info)
 		mvpp2_conf_mbus_windows(dram_target_info, priv);
 
+	if (priv->hw_version == MVPP22)
+		mvpp2_axi_init(priv);
+
 	/* Disable HW PHY polling */
-	val = readl(priv->lms_base + MVPP2_PHY_AN_CFG0_REG);
-	val |= MVPP2_PHY_AN_STOP_SMI0_MASK;
-	writel(val, priv->lms_base + MVPP2_PHY_AN_CFG0_REG);
+	if (priv->hw_version == MVPP21) {
+		val = readl(priv->lms_base + MVPP2_PHY_AN_CFG0_REG);
+		val |= MVPP2_PHY_AN_STOP_SMI0_MASK;
+		writel(val, priv->lms_base + MVPP2_PHY_AN_CFG0_REG);
+	} else {
+		val = readl(priv->iface_base + MVPP22_SMI_MISC_CFG_REG);
+		val &= ~MVPP22_SMI_POLLING_EN;
+		writel(val, priv->iface_base + MVPP22_SMI_MISC_CFG_REG);
+	}
 
 	/* Allocate and initialize aggregated TXQs */
 	priv->aggr_txqs = devm_kcalloc(&pdev->dev, num_present_cpus(),
@@ -6374,11 +6824,25 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv)
 	mvpp2_rx_fifo_init(priv);
 
 	/* Reset Rx queue group interrupt configuration */
-	for (i = 0; i < MVPP2_MAX_PORTS; i++)
-		mvpp2_write(priv, MVPP2_ISR_RXQ_GROUP_REG(i), rxq_number);
+	for (i = 0; i < MVPP2_MAX_PORTS; i++) {
+		if (priv->hw_version == MVPP21) {
+			mvpp2_write(priv, MVPP21_ISR_RXQ_GROUP_REG(i),
+				    rxq_number);
+			continue;
+		} else {
+			u32 val;
+
+			val = (i << MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET);
+			mvpp2_write(priv, MVPP22_ISR_RXQ_GROUP_INDEX_REG, val);
 
-	writel(MVPP2_EXT_GLOBAL_CTRL_DEFAULT,
-	       priv->lms_base + MVPP2_MNG_EXTENDED_GLOBAL_CTRL_REG);
+			val = (rxq_number << MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET);
+			mvpp2_write(priv, MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG, val);
+		}
+	}
+
+	if (priv->hw_version == MVPP21)
+		writel(MVPP2_EXT_GLOBAL_CTRL_DEFAULT,
+		       priv->lms_base + MVPP2_MNG_EXTENDED_GLOBAL_CTRL_REG);
 
 	/* Allow cache snoop when transmiting packets */
 	mvpp2_write(priv, MVPP2_TX_SNOOP_REG, 0x1);
@@ -6405,22 +6869,46 @@ static int mvpp2_probe(struct platform_device *pdev)
 	struct device_node *port_node;
 	struct mvpp2 *priv;
 	struct resource *res;
-	int port_count, first_rxq;
+	void __iomem *base;
+	int port_count, cpu;
 	int err;
 
 	priv = devm_kzalloc(&pdev->dev, sizeof(struct mvpp2), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
+	priv->hw_version =
+		(unsigned long)of_device_get_match_data(&pdev->dev);
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(priv->base))
-		return PTR_ERR(priv->base);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	if (priv->hw_version == MVPP21) {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+		priv->lms_base = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(priv->lms_base))
+			return PTR_ERR(priv->lms_base);
+	} else {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+		priv->iface_base = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(priv->iface_base))
+			return PTR_ERR(priv->iface_base);
+	}
+
+	for_each_present_cpu(cpu) {
+		u32 addr_space_sz;
+
+		addr_space_sz = (priv->hw_version == MVPP21 ?
+				 MVPP21_ADDR_SPACE_SZ : MVPP22_ADDR_SPACE_SZ);
+		priv->cpu_base[cpu] = base + cpu * addr_space_sz;
+	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	priv->lms_base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(priv->lms_base))
-		return PTR_ERR(priv->lms_base);
+	if (priv->hw_version == MVPP21)
+		priv->max_port_rxqs = 8;
+	else
+		priv->max_port_rxqs = 32;
 
 	priv->pp_clk = devm_clk_get(&pdev->dev, "pp_clk");
 	if (IS_ERR(priv->pp_clk))
@@ -6438,21 +6926,47 @@ static int mvpp2_probe(struct platform_device *pdev)
 	if (err < 0)
 		goto err_pp_clk;
 
+	if (priv->hw_version == MVPP22) {
+		priv->mg_clk = devm_clk_get(&pdev->dev, "mg_clk");
+		if (IS_ERR(priv->mg_clk)) {
+			err = PTR_ERR(priv->mg_clk);
+			goto err_gop_clk;
+		}
+
+		err = clk_prepare_enable(priv->mg_clk);
+		if (err < 0)
+			goto err_gop_clk;
+	}
+
 	/* Get system's tclk rate */
 	priv->tclk = clk_get_rate(priv->pp_clk);
 
+	if (priv->hw_version == MVPP22) {
+		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(40));
+		if (err)
+			goto err_mg_clk;
+		/* Sadly, the BM pools all share the same register to
+		 * store the high 32 bits of their address. So they
+		 * must all have the same high 32 bits, which forces
+		 * us to restrict coherent memory to DMA_BIT_MASK(32).
+		 */
+		err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
+		if (err)
+			goto err_mg_clk;
+	}
+
 	/* Initialize network controller */
 	err = mvpp2_init(pdev, priv);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to initialize controller\n");
-		goto err_gop_clk;
+		goto err_mg_clk;
 	}
 
 	port_count = of_get_available_child_count(dn);
 	if (port_count == 0) {
 		dev_err(&pdev->dev, "no ports enabled\n");
 		err = -ENODEV;
-		goto err_gop_clk;
+		goto err_mg_clk;
 	}
 
 	priv->port_list = devm_kcalloc(&pdev->dev, port_count,
@@ -6460,20 +6974,22 @@ static int mvpp2_probe(struct platform_device *pdev)
 				      GFP_KERNEL);
 	if (!priv->port_list) {
 		err = -ENOMEM;
-		goto err_gop_clk;
+		goto err_mg_clk;
 	}
 
 	/* Initialize ports */
-	first_rxq = 0;
 	for_each_available_child_of_node(dn, port_node) {
-		err = mvpp2_port_probe(pdev, port_node, priv, &first_rxq);
+		err = mvpp2_port_probe(pdev, port_node, priv);
 		if (err < 0)
-			goto err_gop_clk;
+			goto err_mg_clk;
 	}
 
 	platform_set_drvdata(pdev, priv);
 	return 0;
 
+err_mg_clk:
+	if (priv->hw_version == MVPP22)
+		clk_disable_unprepare(priv->mg_clk);
 err_gop_clk:
 	clk_disable_unprepare(priv->gop_clk);
 err_pp_clk:
@@ -6506,9 +7022,10 @@ static int mvpp2_remove(struct platform_device *pdev)
 		dma_free_coherent(&pdev->dev,
 				  MVPP2_AGGR_TXQ_SIZE * MVPP2_DESC_ALIGNED_SIZE,
 				  aggr_txq->descs,
-				  aggr_txq->descs_phys);
+				  aggr_txq->descs_dma);
 	}
 
+	clk_disable_unprepare(priv->mg_clk);
 	clk_disable_unprepare(priv->pp_clk);
 	clk_disable_unprepare(priv->gop_clk);
 
@@ -6516,7 +7033,14 @@ static int mvpp2_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id mvpp2_match[] = {
-	{ .compatible = "marvell,armada-375-pp2" },
+	{
+		.compatible = "marvell,armada-375-pp2",
+		.data = (void *)MVPP21,
+	},
+	{
+		.compatible = "marvell,armada-7k-pp22",
+		.data = (void *)MVPP22,
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, mvpp2_match);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 9e757684816d..bf6317eca2f6 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -1908,10 +1908,9 @@ static int __init mtk_init(struct net_device *dev)
 
 	/* If the mac address is invalid, use random mac address  */
 	if (!is_valid_ether_addr(dev->dev_addr)) {
-		random_ether_addr(dev->dev_addr);
+		eth_hw_addr_random(dev);
 		dev_err(eth->dev, "generated random MAC address %pM\n",
 			dev->dev_addr);
-		dev->addr_assign_type = NET_ADDR_RANDOM;
 	}
 
 	return mtk_phy_connect(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index c4d714fcc7da..ffbcb27c05e5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -117,7 +117,7 @@ static const char main_strings[][ETH_GSTRING_LEN] = {
 	/* port statistics */
 	"tso_packets",
 	"xmit_more",
-	"queue_stopped", "wake_queue", "tx_timeout", "rx_alloc_failed",
+	"queue_stopped", "wake_queue", "tx_timeout", "rx_alloc_pages",
 	"rx_csum_good", "rx_csum_none", "rx_csum_complete", "tx_chksum_offload",
 
 	/* pf statistics */
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 61420473fe5f..94fab20ef146 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -92,7 +92,9 @@ static int __mlx4_en_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
 	if (tc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
-	return mlx4_en_setup_tc(dev, tc->tc);
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+	return mlx4_en_setup_tc(dev, tc->mqprio->num_tc);
 }
 
 #ifdef CONFIG_RFS_ACCEL
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 9166d90e7328..e0eb695318e6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -213,6 +213,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	priv->port_stats.rx_chksum_good = 0;
 	priv->port_stats.rx_chksum_none = 0;
 	priv->port_stats.rx_chksum_complete = 0;
+	priv->port_stats.rx_alloc_pages = 0;
 	priv->xdp_stats.rx_xdp_drop    = 0;
 	priv->xdp_stats.rx_xdp_tx      = 0;
 	priv->xdp_stats.rx_xdp_tx_full = 0;
@@ -223,6 +224,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 		priv->port_stats.rx_chksum_good += READ_ONCE(ring->csum_ok);
 		priv->port_stats.rx_chksum_none += READ_ONCE(ring->csum_none);
 		priv->port_stats.rx_chksum_complete += READ_ONCE(ring->csum_complete);
+		priv->port_stats.rx_alloc_pages += READ_ONCE(ring->rx_alloc_pages);
 		priv->xdp_stats.rx_xdp_drop	+= READ_ONCE(ring->xdp_drop);
 		priv->xdp_stats.rx_xdp_tx	+= READ_ONCE(ring->xdp_tx);
 		priv->xdp_stats.rx_xdp_tx_full	+= READ_ONCE(ring->xdp_tx_full);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 867292880c07..aa074e57ce06 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -50,173 +50,62 @@
 
 #include "mlx4_en.h"
 
-static int mlx4_alloc_pages(struct mlx4_en_priv *priv,
-			    struct mlx4_en_rx_alloc *page_alloc,
-			    const struct mlx4_en_frag_info *frag_info,
-			    gfp_t _gfp)
+static int mlx4_alloc_page(struct mlx4_en_priv *priv,
+			   struct mlx4_en_rx_alloc *frag,
+			   gfp_t gfp)
 {
-	int order;
 	struct page *page;
 	dma_addr_t dma;
 
-	for (order = frag_info->order; ;) {
-		gfp_t gfp = _gfp;
-
-		if (order)
-			gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NOMEMALLOC;
-		page = alloc_pages(gfp, order);
-		if (likely(page))
-			break;
-		if (--order < 0 ||
-		    ((PAGE_SIZE << order) < frag_info->frag_size))
-			return -ENOMEM;
-	}
-	dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE << order,
-			   frag_info->dma_dir);
+	page = alloc_page(gfp);
+	if (unlikely(!page))
+		return -ENOMEM;
+	dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE, priv->dma_dir);
 	if (unlikely(dma_mapping_error(priv->ddev, dma))) {
-		put_page(page);
+		__free_page(page);
 		return -ENOMEM;
 	}
-	page_alloc->page_size = PAGE_SIZE << order;
-	page_alloc->page = page;
-	page_alloc->dma = dma;
-	page_alloc->page_offset = 0;
-	/* Not doing get_page() for each frag is a big win
-	 * on asymetric workloads. Note we can not use atomic_set().
-	 */
-	page_ref_add(page, page_alloc->page_size / frag_info->frag_stride - 1);
+	frag->page = page;
+	frag->dma = dma;
+	frag->page_offset = priv->rx_headroom;
 	return 0;
 }
 
 static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv,
+			       struct mlx4_en_rx_ring *ring,
 			       struct mlx4_en_rx_desc *rx_desc,
 			       struct mlx4_en_rx_alloc *frags,
-			       struct mlx4_en_rx_alloc *ring_alloc,
 			       gfp_t gfp)
 {
-	struct mlx4_en_rx_alloc page_alloc[MLX4_EN_MAX_RX_FRAGS];
-	const struct mlx4_en_frag_info *frag_info;
-	struct page *page;
 	int i;
 
-	for (i = 0; i < priv->num_frags; i++) {
-		frag_info = &priv->frag_info[i];
-		page_alloc[i] = ring_alloc[i];
-		page_alloc[i].page_offset += frag_info->frag_stride;
-
-		if (page_alloc[i].page_offset + frag_info->frag_stride <=
-		    ring_alloc[i].page_size)
-			continue;
-
-		if (unlikely(mlx4_alloc_pages(priv, &page_alloc[i],
-					      frag_info, gfp)))
-			goto out;
-	}
-
-	for (i = 0; i < priv->num_frags; i++) {
-		frags[i] = ring_alloc[i];
-		frags[i].page_offset += priv->frag_info[i].rx_headroom;
-		rx_desc->data[i].addr = cpu_to_be64(frags[i].dma +
-						    frags[i].page_offset);
-		ring_alloc[i] = page_alloc[i];
-	}
-
-	return 0;
-
-out:
-	while (i--) {
-		if (page_alloc[i].page != ring_alloc[i].page) {
-			dma_unmap_page(priv->ddev, page_alloc[i].dma,
-				page_alloc[i].page_size,
-				priv->frag_info[i].dma_dir);
-			page = page_alloc[i].page;
-			/* Revert changes done by mlx4_alloc_pages */
-			page_ref_sub(page, page_alloc[i].page_size /
-					   priv->frag_info[i].frag_stride - 1);
-			put_page(page);
+	for (i = 0; i < priv->num_frags; i++, frags++) {
+		if (!frags->page) {
+			if (mlx4_alloc_page(priv, frags, gfp))
+				return -ENOMEM;
+			ring->rx_alloc_pages++;
 		}
-	}
-	return -ENOMEM;
-}
-
-static void mlx4_en_free_frag(struct mlx4_en_priv *priv,
-			      struct mlx4_en_rx_alloc *frags,
-			      int i)
-{
-	const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i];
-	u32 next_frag_end = frags[i].page_offset + 2 * frag_info->frag_stride;
-
-
-	if (next_frag_end > frags[i].page_size)
-		dma_unmap_page(priv->ddev, frags[i].dma, frags[i].page_size,
-			       frag_info->dma_dir);
-
-	if (frags[i].page)
-		put_page(frags[i].page);
-}
-
-static int mlx4_en_init_allocator(struct mlx4_en_priv *priv,
-				  struct mlx4_en_rx_ring *ring)
-{
-	int i;
-	struct mlx4_en_rx_alloc *page_alloc;
-
-	for (i = 0; i < priv->num_frags; i++) {
-		const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i];
-
-		if (mlx4_alloc_pages(priv, &ring->page_alloc[i],
-				     frag_info, GFP_KERNEL | __GFP_COLD))
-			goto out;
-
-		en_dbg(DRV, priv, "  frag %d allocator: - size:%d frags:%d\n",
-		       i, ring->page_alloc[i].page_size,
-		       page_ref_count(ring->page_alloc[i].page));
+		rx_desc->data[i].addr = cpu_to_be64(frags->dma +
+						    frags->page_offset);
 	}
 	return 0;
-
-out:
-	while (i--) {
-		struct page *page;
-
-		page_alloc = &ring->page_alloc[i];
-		dma_unmap_page(priv->ddev, page_alloc->dma,
-			       page_alloc->page_size,
-			       priv->frag_info[i].dma_dir);
-		page = page_alloc->page;
-		/* Revert changes done by mlx4_alloc_pages */
-		page_ref_sub(page, page_alloc->page_size /
-				   priv->frag_info[i].frag_stride - 1);
-		put_page(page);
-		page_alloc->page = NULL;
-	}
-	return -ENOMEM;
 }
 
-static void mlx4_en_destroy_allocator(struct mlx4_en_priv *priv,
-				      struct mlx4_en_rx_ring *ring)
+static void mlx4_en_free_frag(const struct mlx4_en_priv *priv,
+			      struct mlx4_en_rx_alloc *frag)
 {
-	struct mlx4_en_rx_alloc *page_alloc;
-	int i;
-
-	for (i = 0; i < priv->num_frags; i++) {
-		const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i];
-
-		page_alloc = &ring->page_alloc[i];
-		en_dbg(DRV, priv, "Freeing allocator:%d count:%d\n",
-		       i, page_count(page_alloc->page));
-
-		dma_unmap_page(priv->ddev, page_alloc->dma,
-				page_alloc->page_size, frag_info->dma_dir);
-		while (page_alloc->page_offset + frag_info->frag_stride <
-		       page_alloc->page_size) {
-			put_page(page_alloc->page);
-			page_alloc->page_offset += frag_info->frag_stride;
-		}
-		page_alloc->page = NULL;
+	if (frag->page) {
+		dma_unmap_page(priv->ddev, frag->dma,
+			       PAGE_SIZE, priv->dma_dir);
+		__free_page(frag->page);
 	}
+	/* We need to clear all fields, otherwise a change of priv->log_rx_info
+	 * could lead to see garbage later in frag->page.
+	 */
+	memset(frag, 0, sizeof(*frag));
 }
 
-static void mlx4_en_init_rx_desc(struct mlx4_en_priv *priv,
+static void mlx4_en_init_rx_desc(const struct mlx4_en_priv *priv,
 				 struct mlx4_en_rx_ring *ring, int index)
 {
 	struct mlx4_en_rx_desc *rx_desc = ring->buf + ring->stride * index;
@@ -248,18 +137,23 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
 	struct mlx4_en_rx_desc *rx_desc = ring->buf + (index * ring->stride);
 	struct mlx4_en_rx_alloc *frags = ring->rx_info +
 					(index << priv->log_rx_info);
-
 	if (ring->page_cache.index > 0) {
-		frags[0] = ring->page_cache.buf[--ring->page_cache.index];
-		rx_desc->data[0].addr = cpu_to_be64(frags[0].dma +
-						    frags[0].page_offset);
+		/* XDP uses a single page per frame */
+		if (!frags->page) {
+			ring->page_cache.index--;
+			frags->page = ring->page_cache.buf[ring->page_cache.index].page;
+			frags->dma  = ring->page_cache.buf[ring->page_cache.index].dma;
+		}
+		frags->page_offset = XDP_PACKET_HEADROOM;
+		rx_desc->data[0].addr = cpu_to_be64(frags->dma +
+						    XDP_PACKET_HEADROOM);
 		return 0;
 	}
 
-	return mlx4_en_alloc_frags(priv, rx_desc, frags, ring->page_alloc, gfp);
+	return mlx4_en_alloc_frags(priv, ring, rx_desc, frags, gfp);
 }
 
-static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring)
+static bool mlx4_en_is_ring_empty(const struct mlx4_en_rx_ring *ring)
 {
 	return ring->prod == ring->cons;
 }
@@ -269,7 +163,8 @@ static inline void mlx4_en_update_rx_prod_db(struct mlx4_en_rx_ring *ring)
 	*ring->wqres.db.db = cpu_to_be32(ring->prod & 0xffff);
 }
 
-static void mlx4_en_free_rx_desc(struct mlx4_en_priv *priv,
+/* slow path */
+static void mlx4_en_free_rx_desc(const struct mlx4_en_priv *priv,
 				 struct mlx4_en_rx_ring *ring,
 				 int index)
 {
@@ -279,7 +174,7 @@ static void mlx4_en_free_rx_desc(struct mlx4_en_priv *priv,
 	frags = ring->rx_info + (index << priv->log_rx_info);
 	for (nr = 0; nr < priv->num_frags; nr++) {
 		en_dbg(DRV, priv, "Freeing fragment:%d\n", nr);
-		mlx4_en_free_frag(priv, frags, nr);
+		mlx4_en_free_frag(priv, frags + nr);
 	}
 }
 
@@ -335,12 +230,12 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv,
 	       ring->cons, ring->prod);
 
 	/* Unmap and free Rx buffers */
-	while (!mlx4_en_is_ring_empty(ring)) {
-		index = ring->cons & ring->size_mask;
+	for (index = 0; index < ring->size; index++) {
 		en_dbg(DRV, priv, "Processing descriptor:%d\n", index);
 		mlx4_en_free_rx_desc(priv, ring, index);
-		++ring->cons;
 	}
+	ring->cons = 0;
+	ring->prod = 0;
 }
 
 void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev)
@@ -392,9 +287,9 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 
 	tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *
 					sizeof(struct mlx4_en_rx_alloc));
-	ring->rx_info = vmalloc_node(tmp, node);
+	ring->rx_info = vzalloc_node(tmp, node);
 	if (!ring->rx_info) {
-		ring->rx_info = vmalloc(tmp);
+		ring->rx_info = vzalloc(tmp);
 		if (!ring->rx_info) {
 			err = -ENOMEM;
 			goto err_ring;
@@ -464,16 +359,6 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv)
 		/* Initialize all descriptors */
 		for (i = 0; i < ring->size; i++)
 			mlx4_en_init_rx_desc(priv, ring, i);
-
-		/* Initialize page allocators */
-		err = mlx4_en_init_allocator(priv, ring);
-		if (err) {
-			en_err(priv, "Failed initializing ring allocator\n");
-			if (ring->stride <= TXBB_SIZE)
-				ring->buf -= TXBB_SIZE;
-			ring_ind--;
-			goto err_allocator;
-		}
 	}
 	err = mlx4_en_fill_rx_buffers(priv);
 	if (err)
@@ -493,11 +378,9 @@ err_buffers:
 		mlx4_en_free_rx_buf(priv, priv->rx_ring[ring_ind]);
 
 	ring_ind = priv->rx_ring_num - 1;
-err_allocator:
 	while (ring_ind >= 0) {
 		if (priv->rx_ring[ring_ind]->stride <= TXBB_SIZE)
 			priv->rx_ring[ring_ind]->buf -= TXBB_SIZE;
-		mlx4_en_destroy_allocator(priv, priv->rx_ring[ring_ind]);
 		ring_ind--;
 	}
 	return err;
@@ -537,7 +420,9 @@ bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
 	if (cache->index >= MLX4_EN_CACHE_SIZE)
 		return false;
 
-	cache->buf[cache->index++] = *frame;
+	cache->buf[cache->index].page = frame->page;
+	cache->buf[cache->index].dma = frame->dma;
+	cache->index++;
 	return true;
 }
 
@@ -567,136 +452,91 @@ void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv,
 	int i;
 
 	for (i = 0; i < ring->page_cache.index; i++) {
-		struct mlx4_en_rx_alloc *frame = &ring->page_cache.buf[i];
-
-		dma_unmap_page(priv->ddev, frame->dma, frame->page_size,
-			       priv->frag_info[0].dma_dir);
-		put_page(frame->page);
+		dma_unmap_page(priv->ddev, ring->page_cache.buf[i].dma,
+			       PAGE_SIZE, priv->dma_dir);
+		put_page(ring->page_cache.buf[i].page);
 	}
 	ring->page_cache.index = 0;
 	mlx4_en_free_rx_buf(priv, ring);
 	if (ring->stride <= TXBB_SIZE)
 		ring->buf -= TXBB_SIZE;
-	mlx4_en_destroy_allocator(priv, ring);
 }
 
 
 static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
-				    struct mlx4_en_rx_desc *rx_desc,
 				    struct mlx4_en_rx_alloc *frags,
 				    struct sk_buff *skb,
 				    int length)
 {
-	struct skb_frag_struct *skb_frags_rx = skb_shinfo(skb)->frags;
-	struct mlx4_en_frag_info *frag_info;
-	int nr;
+	const struct mlx4_en_frag_info *frag_info = priv->frag_info;
+	unsigned int truesize = 0;
+	int nr, frag_size;
+	struct page *page;
 	dma_addr_t dma;
+	bool release;
 
 	/* Collect used fragments while replacing them in the HW descriptors */
-	for (nr = 0; nr < priv->num_frags; nr++) {
-		frag_info = &priv->frag_info[nr];
-		if (length <= frag_info->frag_prefix_size)
-			break;
-		if (unlikely(!frags[nr].page))
+	for (nr = 0;; frags++) {
+		frag_size = min_t(int, length, frag_info->frag_size);
+
+		page = frags->page;
+		if (unlikely(!page))
 			goto fail;
 
-		dma = be64_to_cpu(rx_desc->data[nr].addr);
-		dma_sync_single_for_cpu(priv->ddev, dma, frag_info->frag_size,
-					DMA_FROM_DEVICE);
+		dma = frags->dma;
+		dma_sync_single_range_for_cpu(priv->ddev, dma, frags->page_offset,
+					      frag_size, priv->dma_dir);
+
+		__skb_fill_page_desc(skb, nr, page, frags->page_offset,
+				     frag_size);
 
-		__skb_fill_page_desc(skb, nr, frags[nr].page,
-				     frags[nr].page_offset,
-				     frag_info->frag_size);
+		truesize += frag_info->frag_stride;
+		if (frag_info->frag_stride == PAGE_SIZE / 2) {
+			frags->page_offset ^= PAGE_SIZE / 2;
+			release = page_count(page) != 1 ||
+				  page_is_pfmemalloc(page) ||
+				  page_to_nid(page) != numa_mem_id();
+		} else {
+			u32 sz_align = ALIGN(frag_size, SMP_CACHE_BYTES);
 
-		skb->truesize += frag_info->frag_stride;
-		frags[nr].page = NULL;
+			frags->page_offset += sz_align;
+			release = frags->page_offset + frag_info->frag_size > PAGE_SIZE;
+		}
+		if (release) {
+			dma_unmap_page(priv->ddev, dma, PAGE_SIZE, priv->dma_dir);
+			frags->page = NULL;
+		} else {
+			page_ref_inc(page);
+		}
+
+		nr++;
+		length -= frag_size;
+		if (!length)
+			break;
+		frag_info++;
 	}
-	/* Adjust size of last fragment to match actual length */
-	if (nr > 0)
-		skb_frag_size_set(&skb_frags_rx[nr - 1],
-			length - priv->frag_info[nr - 1].frag_prefix_size);
+	skb->truesize += truesize;
 	return nr;
 
 fail:
 	while (nr > 0) {
 		nr--;
-		__skb_frag_unref(&skb_frags_rx[nr]);
+		__skb_frag_unref(skb_shinfo(skb)->frags + nr);
 	}
 	return 0;
 }
 
-
-static struct sk_buff *mlx4_en_rx_skb(struct mlx4_en_priv *priv,
-				      struct mlx4_en_rx_desc *rx_desc,
-				      struct mlx4_en_rx_alloc *frags,
-				      unsigned int length)
-{
-	struct sk_buff *skb;
-	void *va;
-	int used_frags;
-	dma_addr_t dma;
-
-	skb = netdev_alloc_skb(priv->dev, SMALL_PACKET_SIZE + NET_IP_ALIGN);
-	if (unlikely(!skb)) {
-		en_dbg(RX_ERR, priv, "Failed allocating skb\n");
-		return NULL;
-	}
-	skb_reserve(skb, NET_IP_ALIGN);
-	skb->len = length;
-
-	/* Get pointer to first fragment so we could copy the headers into the
-	 * (linear part of the) skb */
-	va = page_address(frags[0].page) + frags[0].page_offset;
-
-	if (length <= SMALL_PACKET_SIZE) {
-		/* We are copying all relevant data to the skb - temporarily
-		 * sync buffers for the copy */
-		dma = be64_to_cpu(rx_desc->data[0].addr);
-		dma_sync_single_for_cpu(priv->ddev, dma, length,
-					DMA_FROM_DEVICE);
-		skb_copy_to_linear_data(skb, va, length);
-		skb->tail += length;
-	} else {
-		unsigned int pull_len;
-
-		/* Move relevant fragments to skb */
-		used_frags = mlx4_en_complete_rx_desc(priv, rx_desc, frags,
-							skb, length);
-		if (unlikely(!used_frags)) {
-			kfree_skb(skb);
-			return NULL;
-		}
-		skb_shinfo(skb)->nr_frags = used_frags;
-
-		pull_len = eth_get_headlen(va, SMALL_PACKET_SIZE);
-		/* Copy headers into the skb linear buffer */
-		memcpy(skb->data, va, pull_len);
-		skb->tail += pull_len;
-
-		/* Skip headers in first fragment */
-		skb_shinfo(skb)->frags[0].page_offset += pull_len;
-
-		/* Adjust size of first fragment */
-		skb_frag_size_sub(&skb_shinfo(skb)->frags[0], pull_len);
-		skb->data_len = length - pull_len;
-	}
-	return skb;
-}
-
-static void validate_loopback(struct mlx4_en_priv *priv, struct sk_buff *skb)
+static void validate_loopback(struct mlx4_en_priv *priv, void *va)
 {
+	const unsigned char *data = va + ETH_HLEN;
 	int i;
-	int offset = ETH_HLEN;
 
-	for (i = 0; i < MLX4_LOOPBACK_TEST_PAYLOAD; i++, offset++) {
-		if (*(skb->data + offset) != (unsigned char) (i & 0xff))
-			goto out_loopback;
+	for (i = 0; i < MLX4_LOOPBACK_TEST_PAYLOAD; i++) {
+		if (data[i] != (unsigned char)i)
+			return;
 	}
 	/* Loopback found */
 	priv->loopback_ok = 1;
-
-out_loopback:
-	dev_kfree_skb_any(skb);
 }
 
 static bool mlx4_en_refill_rx_buffers(struct mlx4_en_priv *priv,
@@ -801,7 +641,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	struct mlx4_cqe *cqe;
 	struct mlx4_en_rx_ring *ring = priv->rx_ring[cq->ring];
 	struct mlx4_en_rx_alloc *frags;
-	struct mlx4_en_rx_desc *rx_desc;
 	struct bpf_prog *xdp_prog;
 	int doorbell_pending;
 	struct sk_buff *skb;
@@ -834,10 +673,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	/* Process all completed CQEs */
 	while (XNOR(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK,
 		    cq->mcq.cons_index & cq->size)) {
+		void *va;
 
 		frags = ring->rx_info + (index << priv->log_rx_info);
-		rx_desc = ring->buf + (index << ring->log_stride);
-
+		va = page_address(frags[0].page) + frags[0].page_offset;
 		/*
 		 * make sure we read the CQE after we read the ownership bit
 		 */
@@ -860,16 +699,14 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 		 * and not performing the selftest or flb disabled
 		 */
 		if (priv->flags & MLX4_EN_FLAG_RX_FILTER_NEEDED) {
-			struct ethhdr *ethh;
+			const struct ethhdr *ethh = va;
 			dma_addr_t dma;
 			/* Get pointer to first fragment since we haven't
 			 * skb yet and cast it to ethhdr struct
 			 */
-			dma = be64_to_cpu(rx_desc->data[0].addr);
+			dma = frags[0].dma + frags[0].page_offset;
 			dma_sync_single_for_cpu(priv->ddev, dma, sizeof(*ethh),
 						DMA_FROM_DEVICE);
-			ethh = (struct ethhdr *)(page_address(frags[0].page) +
-						 frags[0].page_offset);
 
 			if (is_multicast_ether_addr(ethh->h_dest)) {
 				struct mlx4_mac_entry *entry;
@@ -887,13 +724,16 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			}
 		}
 
+		if (unlikely(priv->validate_loopback)) {
+			validate_loopback(priv, va);
+			goto next;
+		}
+
 		/*
 		 * Packet is OK - process it.
 		 */
 		length = be32_to_cpu(cqe->byte_cnt);
 		length -= ring->fcs_del;
-		l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
-			(cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
 
 		/* A bpf program gets first chance to drop the packet. It may
 		 * read bytes but not past the end of the frag.
@@ -904,13 +744,13 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			void *orig_data;
 			u32 act;
 
-			dma = be64_to_cpu(rx_desc->data[0].addr);
+			dma = frags[0].dma + frags[0].page_offset;
 			dma_sync_single_for_cpu(priv->ddev, dma,
 						priv->frag_info[0].frag_size,
 						DMA_FROM_DEVICE);
 
-			xdp.data_hard_start = page_address(frags[0].page);
-			xdp.data = xdp.data_hard_start + frags[0].page_offset;
+			xdp.data_hard_start = va - frags[0].page_offset;
+			xdp.data = va;
 			xdp.data_end = xdp.data + length;
 			orig_data = xdp.data;
 
@@ -920,6 +760,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 				length = xdp.data_end - xdp.data;
 				frags[0].page_offset = xdp.data -
 					xdp.data_hard_start;
+				va = xdp.data;
 			}
 
 			switch (act) {
@@ -928,8 +769,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			case XDP_TX:
 				if (likely(!mlx4_en_xmit_frame(ring, frags, dev,
 							length, cq->ring,
-							&doorbell_pending)))
-					goto consumed;
+							&doorbell_pending))) {
+					frags[0].page = NULL;
+					goto next;
+				}
 				trace_xdp_exception(dev, xdp_prog, act);
 				goto xdp_drop_no_cnt; /* Drop on xmit failure */
 			default:
@@ -939,8 +782,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			case XDP_DROP:
 				ring->xdp_drop++;
 xdp_drop_no_cnt:
-				if (likely(mlx4_en_rx_recycle(ring, frags)))
-					goto consumed;
 				goto next;
 			}
 		}
@@ -948,129 +789,51 @@ xdp_drop_no_cnt:
 		ring->bytes += length;
 		ring->packets++;
 
+		skb = napi_get_frags(&cq->napi);
+		if (!skb)
+			goto next;
+
+		if (unlikely(ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL)) {
+			timestamp = mlx4_en_get_cqe_ts(cqe);
+			mlx4_en_fill_hwtstamps(mdev, skb_hwtstamps(skb),
+					       timestamp);
+		}
+		skb_record_rx_queue(skb, cq->ring);
+
 		if (likely(dev->features & NETIF_F_RXCSUM)) {
 			if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
 						      MLX4_CQE_STATUS_UDP)) {
 				if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) &&
 				    cqe->checksum == cpu_to_be16(0xffff)) {
 					ip_summed = CHECKSUM_UNNECESSARY;
+					l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
+						(cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
+					if (l2_tunnel)
+						skb->csum_level = 1;
 					ring->csum_ok++;
 				} else {
-					ip_summed = CHECKSUM_NONE;
-					ring->csum_none++;
+					goto csum_none;
 				}
 			} else {
 				if (priv->flags & MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP &&
 				    (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4 |
 							       MLX4_CQE_STATUS_IPV6))) {
-					ip_summed = CHECKSUM_COMPLETE;
-					ring->csum_complete++;
+					if (check_csum(cqe, skb, va, dev->features)) {
+						goto csum_none;
+					} else {
+						ip_summed = CHECKSUM_COMPLETE;
+						ring->csum_complete++;
+					}
 				} else {
-					ip_summed = CHECKSUM_NONE;
-					ring->csum_none++;
+					goto csum_none;
 				}
 			}
 		} else {
+csum_none:
 			ip_summed = CHECKSUM_NONE;
 			ring->csum_none++;
 		}
-
-		/* This packet is eligible for GRO if it is:
-		 * - DIX Ethernet (type interpretation)
-		 * - TCP/IP (v4)
-		 * - without IP options
-		 * - not an IP fragment
-		 */
-		if (dev->features & NETIF_F_GRO) {
-			struct sk_buff *gro_skb = napi_get_frags(&cq->napi);
-			if (!gro_skb)
-				goto next;
-
-			nr = mlx4_en_complete_rx_desc(priv,
-				rx_desc, frags, gro_skb,
-				length);
-			if (!nr)
-				goto next;
-
-			if (ip_summed == CHECKSUM_COMPLETE) {
-				void *va = skb_frag_address(skb_shinfo(gro_skb)->frags);
-				if (check_csum(cqe, gro_skb, va,
-					       dev->features)) {
-					ip_summed = CHECKSUM_NONE;
-					ring->csum_none++;
-					ring->csum_complete--;
-				}
-			}
-
-			skb_shinfo(gro_skb)->nr_frags = nr;
-			gro_skb->len = length;
-			gro_skb->data_len = length;
-			gro_skb->ip_summed = ip_summed;
-
-			if (l2_tunnel && ip_summed == CHECKSUM_UNNECESSARY)
-				gro_skb->csum_level = 1;
-
-			if ((cqe->vlan_my_qpn &
-			    cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK)) &&
-			    (dev->features & NETIF_F_HW_VLAN_CTAG_RX)) {
-				u16 vid = be16_to_cpu(cqe->sl_vid);
-
-				__vlan_hwaccel_put_tag(gro_skb, htons(ETH_P_8021Q), vid);
-			} else if ((be32_to_cpu(cqe->vlan_my_qpn) &
-				  MLX4_CQE_SVLAN_PRESENT_MASK) &&
-				 (dev->features & NETIF_F_HW_VLAN_STAG_RX)) {
-				__vlan_hwaccel_put_tag(gro_skb,
-						       htons(ETH_P_8021AD),
-						       be16_to_cpu(cqe->sl_vid));
-			}
-
-			if (dev->features & NETIF_F_RXHASH)
-				skb_set_hash(gro_skb,
-					     be32_to_cpu(cqe->immed_rss_invalid),
-					     (ip_summed == CHECKSUM_UNNECESSARY) ?
-						PKT_HASH_TYPE_L4 :
-						PKT_HASH_TYPE_L3);
-
-			skb_record_rx_queue(gro_skb, cq->ring);
-
-			if (ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL) {
-				timestamp = mlx4_en_get_cqe_ts(cqe);
-				mlx4_en_fill_hwtstamps(mdev,
-						       skb_hwtstamps(gro_skb),
-						       timestamp);
-			}
-
-			napi_gro_frags(&cq->napi);
-			goto next;
-		}
-
-		/* GRO not possible, complete processing here */
-		skb = mlx4_en_rx_skb(priv, rx_desc, frags, length);
-		if (unlikely(!skb)) {
-			ring->dropped++;
-			goto next;
-		}
-
-		if (unlikely(priv->validate_loopback)) {
-			validate_loopback(priv, skb);
-			goto next;
-		}
-
-		if (ip_summed == CHECKSUM_COMPLETE) {
-			if (check_csum(cqe, skb, skb->data, dev->features)) {
-				ip_summed = CHECKSUM_NONE;
-				ring->csum_complete--;
-				ring->csum_none++;
-			}
-		}
-
 		skb->ip_summed = ip_summed;
-		skb->protocol = eth_type_trans(skb, dev);
-		skb_record_rx_queue(skb, cq->ring);
-
-		if (l2_tunnel && ip_summed == CHECKSUM_UNNECESSARY)
-			skb->csum_level = 1;
-
 		if (dev->features & NETIF_F_RXHASH)
 			skb_set_hash(skb,
 				     be32_to_cpu(cqe->immed_rss_invalid),
@@ -1078,36 +841,36 @@ xdp_drop_no_cnt:
 					PKT_HASH_TYPE_L4 :
 					PKT_HASH_TYPE_L3);
 
-		if ((be32_to_cpu(cqe->vlan_my_qpn) &
-		    MLX4_CQE_CVLAN_PRESENT_MASK) &&
+
+		if ((cqe->vlan_my_qpn &
+		     cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK)) &&
 		    (dev->features & NETIF_F_HW_VLAN_CTAG_RX))
-			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), be16_to_cpu(cqe->sl_vid));
-		else if ((be32_to_cpu(cqe->vlan_my_qpn) &
-			  MLX4_CQE_SVLAN_PRESENT_MASK) &&
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+					       be16_to_cpu(cqe->sl_vid));
+		else if ((cqe->vlan_my_qpn &
+			  cpu_to_be32(MLX4_CQE_SVLAN_PRESENT_MASK)) &&
 			 (dev->features & NETIF_F_HW_VLAN_STAG_RX))
 			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021AD),
 					       be16_to_cpu(cqe->sl_vid));
 
-		if (ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL) {
-			timestamp = mlx4_en_get_cqe_ts(cqe);
-			mlx4_en_fill_hwtstamps(mdev, skb_hwtstamps(skb),
-					       timestamp);
+		nr = mlx4_en_complete_rx_desc(priv, frags, skb, length);
+		if (likely(nr)) {
+			skb_shinfo(skb)->nr_frags = nr;
+			skb->len = length;
+			skb->data_len = length;
+			napi_gro_frags(&cq->napi);
+		} else {
+			skb->vlan_tci = 0;
+			skb_clear_hash(skb);
 		}
-
-		napi_gro_receive(&cq->napi, skb);
 next:
-		for (nr = 0; nr < priv->num_frags; nr++)
-			mlx4_en_free_frag(priv, frags, nr);
-
-consumed:
 		++cq->mcq.cons_index;
 		index = (cq->mcq.cons_index) & ring->size_mask;
 		cqe = mlx4_en_get_cqe(cq->buf, index, priv->cqe_size) + factor;
 		if (++polled == budget)
-			goto out;
+			break;
 	}
 
-out:
 	rcu_read_unlock();
 
 	if (polled) {
@@ -1178,13 +941,6 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
 	return done;
 }
 
-static const int frag_sizes[] = {
-	FRAG_SZ0,
-	FRAG_SZ1,
-	FRAG_SZ2,
-	FRAG_SZ3
-};
-
 void mlx4_en_calc_rx_buf(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
@@ -1195,33 +951,43 @@ void mlx4_en_calc_rx_buf(struct net_device *dev)
 	 * This only works when num_frags == 1.
 	 */
 	if (priv->tx_ring_num[TX_XDP]) {
-		priv->frag_info[0].order = 0;
 		priv->frag_info[0].frag_size = eff_mtu;
-		priv->frag_info[0].frag_prefix_size = 0;
 		/* This will gain efficient xdp frame recycling at the
 		 * expense of more costly truesize accounting
 		 */
 		priv->frag_info[0].frag_stride = PAGE_SIZE;
-		priv->frag_info[0].dma_dir = PCI_DMA_BIDIRECTIONAL;
-		priv->frag_info[0].rx_headroom = XDP_PACKET_HEADROOM;
+		priv->dma_dir = PCI_DMA_BIDIRECTIONAL;
+		priv->rx_headroom = XDP_PACKET_HEADROOM;
 		i = 1;
 	} else {
-		int buf_size = 0;
+		int frag_size_max = 2048, buf_size = 0;
+
+		/* should not happen, right ? */
+		if (eff_mtu > PAGE_SIZE + (MLX4_EN_MAX_RX_FRAGS - 1) * 2048)
+			frag_size_max = PAGE_SIZE;
 
 		while (buf_size < eff_mtu) {
-			priv->frag_info[i].order = MLX4_EN_ALLOC_PREFER_ORDER;
-			priv->frag_info[i].frag_size =
-				(eff_mtu > buf_size + frag_sizes[i]) ?
-					frag_sizes[i] : eff_mtu - buf_size;
-			priv->frag_info[i].frag_prefix_size = buf_size;
-			priv->frag_info[i].frag_stride =
-				ALIGN(priv->frag_info[i].frag_size,
-				      SMP_CACHE_BYTES);
-			priv->frag_info[i].dma_dir = PCI_DMA_FROMDEVICE;
-			priv->frag_info[i].rx_headroom = 0;
-			buf_size += priv->frag_info[i].frag_size;
+			int frag_stride, frag_size = eff_mtu - buf_size;
+			int pad, nb;
+
+			if (i < MLX4_EN_MAX_RX_FRAGS - 1)
+				frag_size = min(frag_size, frag_size_max);
+
+			priv->frag_info[i].frag_size = frag_size;
+			frag_stride = ALIGN(frag_size, SMP_CACHE_BYTES);
+			/* We can only pack 2 1536-bytes frames in on 4K page
+			 * Therefore, each frame would consume more bytes (truesize)
+			 */
+			nb = PAGE_SIZE / frag_stride;
+			pad = (PAGE_SIZE - nb * frag_stride) / nb;
+			pad &= ~(SMP_CACHE_BYTES - 1);
+			priv->frag_info[i].frag_stride = frag_stride + pad;
+
+			buf_size += frag_size;
 			i++;
 		}
+		priv->dma_dir = PCI_DMA_FROMDEVICE;
+		priv->rx_headroom = 0;
 	}
 
 	priv->num_frags = i;
@@ -1232,10 +998,9 @@ void mlx4_en_calc_rx_buf(struct net_device *dev)
 	       eff_mtu, priv->num_frags);
 	for (i = 0; i < priv->num_frags; i++) {
 		en_err(priv,
-		       "  frag:%d - size:%d prefix:%d stride:%d\n",
+		       "  frag:%d - size:%d stride:%d\n",
 		       i,
 		       priv->frag_info[i].frag_size,
-		       priv->frag_info[i].frag_prefix_size,
 		       priv->frag_info[i].frag_stride);
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
index 95290e1fc9fe..17112faafbcc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
@@ -81,14 +81,11 @@ static int mlx4_en_test_loopback(struct mlx4_en_priv *priv)
 {
 	u32 loopback_ok = 0;
 	int i;
-	bool gro_enabled;
 
         priv->loopback_ok = 0;
 	priv->validate_loopback = 1;
-	gro_enabled = priv->dev->features & NETIF_F_GRO;
 
 	mlx4_en_update_loopback_state(priv->dev, priv->dev->features);
-	priv->dev->features &= ~NETIF_F_GRO;
 
 	/* xmit */
 	if (mlx4_en_test_loopback_xmit(priv)) {
@@ -111,9 +108,6 @@ mlx4_en_test_loopback_exit:
 
 	priv->validate_loopback = 0;
 
-	if (gro_enabled)
-		priv->dev->features |= NETIF_F_GRO;
-
 	mlx4_en_update_loopback_state(priv->dev, priv->dev->features);
 	return !loopback_ok;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 3ed42199d3f1..e0c5ffb3e3a6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -354,13 +354,11 @@ u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
 	struct mlx4_en_rx_alloc frame = {
 		.page = tx_info->page,
 		.dma = tx_info->map0_dma,
-		.page_offset = XDP_PACKET_HEADROOM,
-		.page_size = PAGE_SIZE,
 	};
 
 	if (!mlx4_en_rx_recycle(ring->recycle_ring, &frame)) {
 		dma_unmap_page(priv->ddev, tx_info->map0_dma,
-			       PAGE_SIZE, priv->frag_info[0].dma_dir);
+			       PAGE_SIZE, priv->dma_dir);
 		put_page(tx_info->page);
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 3629ce11a68b..39f401aa3047 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -102,17 +102,6 @@
 /* Use the maximum between 16384 and a single page */
 #define MLX4_EN_ALLOC_SIZE	PAGE_ALIGN(16384)
 
-#define MLX4_EN_ALLOC_PREFER_ORDER min_t(int, get_order(32768),		\
-					 PAGE_ALLOC_COSTLY_ORDER)
-
-/* Receive fragment sizes; we use at most 3 fragments (for 9600 byte MTU
- * and 4K allocations) */
-enum {
-	FRAG_SZ0 = 1536 - NET_IP_ALIGN,
-	FRAG_SZ1 = 4096,
-	FRAG_SZ2 = 4096,
-	FRAG_SZ3 = MLX4_EN_ALLOC_SIZE
-};
 #define MLX4_EN_MAX_RX_FRAGS	4
 
 /* Maximum ring sizes */
@@ -264,13 +253,16 @@ struct mlx4_en_rx_alloc {
 	struct page	*page;
 	dma_addr_t	dma;
 	u32		page_offset;
-	u32		page_size;
 };
 
 #define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT)
+
 struct mlx4_en_page_cache {
 	u32 index;
-	struct mlx4_en_rx_alloc buf[MLX4_EN_CACHE_SIZE];
+	struct {
+		struct page	*page;
+		dma_addr_t	dma;
+	} buf[MLX4_EN_CACHE_SIZE];
 };
 
 struct mlx4_en_priv;
@@ -335,7 +327,6 @@ struct mlx4_en_rx_desc {
 
 struct mlx4_en_rx_ring {
 	struct mlx4_hwq_resources wqres;
-	struct mlx4_en_rx_alloc page_alloc[MLX4_EN_MAX_RX_FRAGS];
 	u32 size ;	/* number of Rx descs*/
 	u32 actual_size;
 	u32 size_mask;
@@ -355,6 +346,7 @@ struct mlx4_en_rx_ring {
 	unsigned long csum_ok;
 	unsigned long csum_none;
 	unsigned long csum_complete;
+	unsigned long rx_alloc_pages;
 	unsigned long xdp_drop;
 	unsigned long xdp_tx;
 	unsigned long xdp_tx_full;
@@ -472,11 +464,7 @@ struct mlx4_en_mc_list {
 
 struct mlx4_en_frag_info {
 	u16 frag_size;
-	u16 frag_prefix_size;
 	u32 frag_stride;
-	enum dma_data_direction dma_dir;
-	u16 order;
-	u16 rx_headroom;
 };
 
 #ifdef CONFIG_MLX4_EN_DCB
@@ -584,8 +572,10 @@ struct mlx4_en_priv {
 	u32 rx_ring_num;
 	u32 rx_skb_size;
 	struct mlx4_en_frag_info frag_info[MLX4_EN_MAX_RX_FRAGS];
-	u16 num_frags;
-	u16 log_rx_info;
+	u8 num_frags;
+	u8 log_rx_info;
+	u8 dma_dir;
+	u16 rx_headroom;
 
 	struct mlx4_en_tx_ring **tx_ring[MLX4_EN_NUM_TX_TYPES];
 	struct mlx4_en_rx_ring *rx_ring[MAX_RX_RINGS];
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
index 48641cb0367f..926f3c3f3665 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
@@ -37,7 +37,7 @@ struct mlx4_en_port_stats {
 	unsigned long queue_stopped;
 	unsigned long wake_queue;
 	unsigned long tx_timeout;
-	unsigned long rx_alloc_failed;
+	unsigned long rx_alloc_pages;
 	unsigned long rx_chksum_good;
 	unsigned long rx_chksum_none;
 	unsigned long rx_chksum_complete;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index a380353a78c2..5bdaf3d545b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -279,6 +279,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_DESTROY_XRC_SRQ:
 	case MLX5_CMD_OP_DESTROY_DCT:
 	case MLX5_CMD_OP_DEALLOC_Q_COUNTER:
+	case MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT:
+	case MLX5_CMD_OP_DESTROY_QOS_PARA_VPORT:
 	case MLX5_CMD_OP_DEALLOC_PD:
 	case MLX5_CMD_OP_DEALLOC_UAR:
 	case MLX5_CMD_OP_DETACH_FROM_MCG:
@@ -305,8 +307,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY:
 	case MLX5_CMD_OP_SET_FLOW_TABLE_ROOT:
 	case MLX5_CMD_OP_DEALLOC_ENCAP_HEADER:
-	case MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT:
-	case MLX5_CMD_OP_DESTROY_QOS_PARA_VPORT:
+	case MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -363,6 +364,10 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_QUERY_Q_COUNTER:
 	case MLX5_CMD_OP_SET_RATE_LIMIT:
 	case MLX5_CMD_OP_QUERY_RATE_LIMIT:
+	case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT:
+	case MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT:
+	case MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT:
+	case MLX5_CMD_OP_CREATE_QOS_PARA_VPORT:
 	case MLX5_CMD_OP_ALLOC_PD:
 	case MLX5_CMD_OP_ALLOC_UAR:
 	case MLX5_CMD_OP_CONFIG_INT_MODERATION:
@@ -414,10 +419,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_ALLOC_FLOW_COUNTER:
 	case MLX5_CMD_OP_QUERY_FLOW_COUNTER:
 	case MLX5_CMD_OP_ALLOC_ENCAP_HEADER:
-	case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT:
-	case MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT:
-	case MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT:
-	case MLX5_CMD_OP_CREATE_QOS_PARA_VPORT:
+	case MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT:
 		*status = MLX5_DRIVER_STATUS_ABORTED;
 		*synd = MLX5_DRIVER_SYND;
 		return -EIO;
@@ -501,6 +503,12 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(SET_RATE_LIMIT);
 	MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT);
+	MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT);
+	MLX5_COMMAND_STR_CASE(DESTROY_SCHEDULING_ELEMENT);
+	MLX5_COMMAND_STR_CASE(QUERY_SCHEDULING_ELEMENT);
+	MLX5_COMMAND_STR_CASE(MODIFY_SCHEDULING_ELEMENT);
+	MLX5_COMMAND_STR_CASE(CREATE_QOS_PARA_VPORT);
+	MLX5_COMMAND_STR_CASE(DESTROY_QOS_PARA_VPORT);
 	MLX5_COMMAND_STR_CASE(ALLOC_PD);
 	MLX5_COMMAND_STR_CASE(DEALLOC_PD);
 	MLX5_COMMAND_STR_CASE(ALLOC_UAR);
@@ -576,12 +584,8 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(MODIFY_FLOW_TABLE);
 	MLX5_COMMAND_STR_CASE(ALLOC_ENCAP_HEADER);
 	MLX5_COMMAND_STR_CASE(DEALLOC_ENCAP_HEADER);
-	MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT);
-	MLX5_COMMAND_STR_CASE(DESTROY_SCHEDULING_ELEMENT);
-	MLX5_COMMAND_STR_CASE(QUERY_SCHEDULING_ELEMENT);
-	MLX5_COMMAND_STR_CASE(MODIFY_SCHEDULING_ELEMENT);
-	MLX5_COMMAND_STR_CASE(CREATE_QOS_PARA_VPORT);
-	MLX5_COMMAND_STR_CASE(DESTROY_QOS_PARA_VPORT);
+	MLX5_COMMAND_STR_CASE(ALLOC_MODIFY_HEADER_CONTEXT);
+	MLX5_COMMAND_STR_CASE(DEALLOC_MODIFY_HEADER_CONTEXT);
 	default: return "unknown command opcode";
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index dc52053128bc..150fb52a0737 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -111,18 +111,13 @@
 #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_BF_BUDGET             16
 
 #define MLX5E_ICOSQ_MAX_WQEBBS \
 	(DIV_ROUND_UP(sizeof(struct mlx5e_umr_wqe), MLX5_SEND_WQE_BB))
 
 #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
-#define MLX5E_XDP_IHS_DS_COUNT \
-	DIV_ROUND_UP(MLX5E_XDP_MIN_INLINE - 2, MLX5_SEND_WQE_DS)
 #define MLX5E_XDP_TX_DS_COUNT \
 	((sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) + 1 /* SG DS */)
-#define MLX5E_XDP_TX_WQEBBS \
-	DIV_ROUND_UP(MLX5E_XDP_TX_DS_COUNT, MLX5_SEND_WQEBB_NUM_DS)
 
 #define MLX5E_NUM_MAIN_GROUPS 9
 
@@ -187,15 +182,15 @@ enum mlx5e_priv_flag {
 	MLX5E_PFLAG_RX_CQE_COMPRESS = (1 << 1),
 };
 
-#define MLX5E_SET_PFLAG(priv, pflag, enable)			\
+#define MLX5E_SET_PFLAG(params, pflag, enable)			\
 	do {							\
 		if (enable)					\
-			(priv)->params.pflags |= (pflag);	\
+			(params)->pflags |= (pflag);		\
 		else						\
-			(priv)->params.pflags &= ~(pflag);	\
+			(params)->pflags &= ~(pflag);		\
 	} while (0)
 
-#define MLX5E_GET_PFLAG(priv, pflag) (!!((priv)->params.pflags & (pflag)))
+#define MLX5E_GET_PFLAG(params, pflag) (!!((params)->pflags & (pflag)))
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 #define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */
@@ -218,7 +213,6 @@ struct mlx5e_params {
 	bool rx_cqe_compress_def;
 	struct mlx5e_cq_moder rx_cq_moderation;
 	struct mlx5e_cq_moder tx_cq_moderation;
-	u16 min_rx_wqes;
 	bool lro_en;
 	u32 lro_wqe_sz;
 	u16 tx_max_inline;
@@ -230,6 +224,7 @@ struct mlx5e_params {
 	bool rx_am_enabled;
 	u32 lro_timeout;
 	u32 pflags;
+	struct bpf_prog *xdp_prog;
 };
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
@@ -285,7 +280,6 @@ struct mlx5e_cq {
 	struct napi_struct        *napi;
 	struct mlx5_core_cq        mcq;
 	struct mlx5e_channel      *channel;
-	struct mlx5e_priv         *priv;
 
 	/* cqe decompression */
 	struct mlx5_cqe64          title;
@@ -295,22 +289,163 @@ struct mlx5e_cq {
 	u16                        decmprs_wqe_counter;
 
 	/* control */
+	struct mlx5_core_dev      *mdev;
 	struct mlx5_frag_wq_ctrl   wq_ctrl;
 } ____cacheline_aligned_in_smp;
 
-struct mlx5e_rq;
-typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq *rq,
-				       struct mlx5_cqe64 *cqe);
-typedef int (*mlx5e_fp_alloc_wqe)(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe,
-				  u16 ix);
+struct mlx5e_tx_wqe_info {
+	u32 num_bytes;
+	u8  num_wqebbs;
+	u8  num_dma;
+};
 
-typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq *rq, u16 ix);
+enum mlx5e_dma_map_type {
+	MLX5E_DMA_MAP_SINGLE,
+	MLX5E_DMA_MAP_PAGE
+};
+
+struct mlx5e_sq_dma {
+	dma_addr_t              addr;
+	u32                     size;
+	enum mlx5e_dma_map_type type;
+};
+
+enum {
+	MLX5E_SQ_STATE_ENABLED,
+};
+
+struct mlx5e_sq_wqe_info {
+	u8  opcode;
+	u8  num_wqebbs;
+};
+
+struct mlx5e_txqsq {
+	/* data path */
+
+	/* dirtied @completion */
+	u16                        cc;
+	u32                        dma_fifo_cc;
+
+	/* dirtied @xmit */
+	u16                        pc ____cacheline_aligned_in_smp;
+	u32                        dma_fifo_pc;
+	struct mlx5e_sq_stats      stats;
+
+	struct mlx5e_cq            cq;
+
+	/* write@xmit, read@completion */
+	struct {
+		struct sk_buff           **skb;
+		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;
+	void __iomem              *uar_map;
+	struct netdev_queue       *txq;
+	u32                        sqn;
+	u16                        max_inline;
+	u8                         min_inline_mode;
+	u16                        edge;
+	struct device             *pdev;
+	struct mlx5e_tstamp       *tstamp;
+	__be32                     mkey_be;
+	unsigned long              state;
+
+	/* control path */
+	struct mlx5_wq_ctrl        wq_ctrl;
+	struct mlx5e_channel      *channel;
+	int                        txq_ix;
+	u32                        rate_limit;
+} ____cacheline_aligned_in_smp;
+
+struct mlx5e_xdpsq {
+	/* data path */
+
+	/* dirtied @rx completion */
+	u16                        cc;
+	u16                        pc;
+
+	struct mlx5e_cq            cq;
+
+	/* write@xmit, read@completion */
+	struct {
+		struct mlx5e_dma_info     *di;
+		bool                       doorbell;
+	} db;
+
+	/* read only */
+	struct mlx5_wq_cyc         wq;
+	void __iomem              *uar_map;
+	u32                        sqn;
+	struct device             *pdev;
+	__be32                     mkey_be;
+	u8                         min_inline_mode;
+	unsigned long              state;
+
+	/* control path */
+	struct mlx5_wq_ctrl        wq_ctrl;
+	struct mlx5e_channel      *channel;
+} ____cacheline_aligned_in_smp;
+
+struct mlx5e_icosq {
+	/* data path */
+
+	/* dirtied @completion */
+	u16                        cc;
+
+	/* dirtied @xmit */
+	u16                        pc ____cacheline_aligned_in_smp;
+	u32                        dma_fifo_pc;
+	u16                        prev_cc;
+
+	struct mlx5e_cq            cq;
+
+	/* write@xmit, read@completion */
+	struct {
+		struct mlx5e_sq_wqe_info *ico_wqe;
+	} db;
+
+	/* read only */
+	struct mlx5_wq_cyc         wq;
+	void __iomem              *uar_map;
+	u32                        sqn;
+	u16                        edge;
+	struct device             *pdev;
+	__be32                     mkey_be;
+	unsigned long              state;
+
+	/* control path */
+	struct mlx5_wq_ctrl        wq_ctrl;
+	struct mlx5e_channel      *channel;
+} ____cacheline_aligned_in_smp;
+
+static inline bool
+mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n)
+{
+	return (((wq->sz_m1 & (cc - pc)) >= n) || (cc == pc));
+}
 
 struct mlx5e_dma_info {
 	struct page	*page;
 	dma_addr_t	addr;
 };
 
+struct mlx5e_umr_dma_info {
+	__be64                *mtt;
+	dma_addr_t             mtt_addr;
+	struct mlx5e_dma_info  dma_info[MLX5_MPWRQ_PAGES_PER_WQE];
+	struct mlx5e_umr_wqe   wqe;
+};
+
+struct mlx5e_mpw_info {
+	struct mlx5e_umr_dma_info umr;
+	u16 consumed_strides;
+	u16 skbs_frags[MLX5_MPWRQ_PAGES_PER_WQE];
+};
+
 struct mlx5e_rx_am_stats {
 	int ppms; /* packets per msec */
 	int epms; /* events per msec */
@@ -347,6 +482,11 @@ struct mlx5e_page_cache {
 	struct mlx5e_dma_info page_cache[MLX5E_CACHE_SIZE];
 };
 
+struct mlx5e_rq;
+typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq*, struct mlx5_cqe64*);
+typedef int (*mlx5e_fp_alloc_wqe)(struct mlx5e_rq*, struct mlx5e_rx_wqe*, u16);
+typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq*, u16);
+
 struct mlx5e_rq {
 	/* data path */
 	struct mlx5_wq_ll      wq;
@@ -381,7 +521,10 @@ struct mlx5e_rq {
 	u16                    rx_headroom;
 
 	struct mlx5e_rx_am     am; /* Adaptive Moderation */
+
+	/* XDP */
 	struct bpf_prog       *xdp_prog;
+	struct mlx5e_xdpsq     xdpsq;
 
 	/* control */
 	struct mlx5_wq_ctrl    wq_ctrl;
@@ -390,118 +533,10 @@ struct mlx5e_rq {
 	u32                    mpwqe_num_strides;
 	u32                    rqn;
 	struct mlx5e_channel  *channel;
-	struct mlx5e_priv     *priv;
+	struct mlx5_core_dev  *mdev;
 	struct mlx5_core_mkey  umr_mkey;
 } ____cacheline_aligned_in_smp;
 
-struct mlx5e_umr_dma_info {
-	__be64                *mtt;
-	dma_addr_t             mtt_addr;
-	struct mlx5e_dma_info  dma_info[MLX5_MPWRQ_PAGES_PER_WQE];
-	struct mlx5e_umr_wqe   wqe;
-};
-
-struct mlx5e_mpw_info {
-	struct mlx5e_umr_dma_info umr;
-	u16 consumed_strides;
-	u16 skbs_frags[MLX5_MPWRQ_PAGES_PER_WQE];
-};
-
-struct mlx5e_tx_wqe_info {
-	u32 num_bytes;
-	u8  num_wqebbs;
-	u8  num_dma;
-};
-
-enum mlx5e_dma_map_type {
-	MLX5E_DMA_MAP_SINGLE,
-	MLX5E_DMA_MAP_PAGE
-};
-
-struct mlx5e_sq_dma {
-	dma_addr_t              addr;
-	u32                     size;
-	enum mlx5e_dma_map_type type;
-};
-
-enum {
-	MLX5E_SQ_STATE_ENABLED,
-	MLX5E_SQ_STATE_BF_ENABLE,
-};
-
-struct mlx5e_sq_wqe_info {
-	u8  opcode;
-	u8  num_wqebbs;
-};
-
-enum mlx5e_sq_type {
-	MLX5E_SQ_TXQ,
-	MLX5E_SQ_ICO,
-	MLX5E_SQ_XDP
-};
-
-struct mlx5e_sq {
-	/* data path */
-
-	/* dirtied @completion */
-	u16                        cc;
-	u32                        dma_fifo_cc;
-
-	/* dirtied @xmit */
-	u16                        pc ____cacheline_aligned_in_smp;
-	u32                        dma_fifo_pc;
-	u16                        bf_offset;
-	u16                        prev_cc;
-	u8                         bf_budget;
-	struct mlx5e_sq_stats      stats;
-
-	struct mlx5e_cq            cq;
-
-	/* pointers to per tx element info: write@xmit, read@completion */
-	union {
-		struct {
-			struct sk_buff           **skb;
-			struct mlx5e_sq_dma       *dma_fifo;
-			struct mlx5e_tx_wqe_info  *wqe_info;
-		} txq;
-		struct mlx5e_sq_wqe_info *ico_wqe;
-		struct {
-			struct mlx5e_sq_wqe_info  *wqe_info;
-			struct mlx5e_dma_info     *di;
-			bool                       doorbell;
-		} xdp;
-	} db;
-
-	/* read only */
-	struct mlx5_wq_cyc         wq;
-	u32                        dma_fifo_mask;
-	void __iomem              *uar_map;
-	struct netdev_queue       *txq;
-	u32                        sqn;
-	u16                        bf_buf_size;
-	u16                        max_inline;
-	u8                         min_inline_mode;
-	u16                        edge;
-	struct device             *pdev;
-	struct mlx5e_tstamp       *tstamp;
-	__be32                     mkey_be;
-	unsigned long              state;
-
-	/* control path */
-	struct mlx5_wq_ctrl        wq_ctrl;
-	struct mlx5_sq_bfreg	   bfreg;
-	struct mlx5e_channel      *channel;
-	int                        tc;
-	u32                        rate_limit;
-	u8                         type;
-} ____cacheline_aligned_in_smp;
-
-static inline bool mlx5e_sq_has_room_for(struct mlx5e_sq *sq, u16 n)
-{
-	return (((sq->wq.sz_m1 & (sq->cc - sq->pc)) >= n) ||
-		(sq->cc  == sq->pc));
-}
-
 enum channel_flags {
 	MLX5E_CHANNEL_NAPI_SCHED = 1,
 };
@@ -509,9 +544,8 @@ enum channel_flags {
 struct mlx5e_channel {
 	/* data path */
 	struct mlx5e_rq            rq;
-	struct mlx5e_sq            xdp_sq;
-	struct mlx5e_sq            sq[MLX5E_MAX_NUM_TC];
-	struct mlx5e_sq            icosq;   /* internal control operations */
+	struct mlx5e_txqsq         sq[MLX5E_MAX_NUM_TC];
+	struct mlx5e_icosq         icosq;   /* internal control operations */
 	bool                       xdp;
 	struct napi_struct         napi;
 	struct device             *pdev;
@@ -522,10 +556,18 @@ struct mlx5e_channel {
 
 	/* control */
 	struct mlx5e_priv         *priv;
+	struct mlx5_core_dev      *mdev;
+	struct mlx5e_tstamp       *tstamp;
 	int                        ix;
 	int                        cpu;
 };
 
+struct mlx5e_channels {
+	struct mlx5e_channel **c;
+	unsigned int           num;
+	struct mlx5e_params    params;
+};
+
 enum mlx5e_traffic_types {
 	MLX5E_TT_IPV4_TCP,
 	MLX5E_TT_IPV6_TCP,
@@ -675,34 +717,17 @@ enum {
 	MLX5E_NIC_PRIO
 };
 
-struct mlx5e_profile {
-	void	(*init)(struct mlx5_core_dev *mdev,
-			struct net_device *netdev,
-			const struct mlx5e_profile *profile, void *ppriv);
-	void	(*cleanup)(struct mlx5e_priv *priv);
-	int	(*init_rx)(struct mlx5e_priv *priv);
-	void	(*cleanup_rx)(struct mlx5e_priv *priv);
-	int	(*init_tx)(struct mlx5e_priv *priv);
-	void	(*cleanup_tx)(struct mlx5e_priv *priv);
-	void	(*enable)(struct mlx5e_priv *priv);
-	void	(*disable)(struct mlx5e_priv *priv);
-	void	(*update_stats)(struct mlx5e_priv *priv);
-	int	(*max_nch)(struct mlx5_core_dev *mdev);
-	int	max_tc;
-};
-
 struct mlx5e_priv {
 	/* priv data path fields - start */
-	struct mlx5e_sq            **txq_to_sq_map;
-	int channeltc_to_txq_map[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC];
-	struct bpf_prog *xdp_prog;
+	struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC];
+	int channel_tc2txq[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC];
 	/* priv data path fields - end */
 
 	unsigned long              state;
 	struct mutex               state_lock; /* Protects Interface state */
 	struct mlx5e_rq            drop_rq;
 
-	struct mlx5e_channel     **channel;
+	struct mlx5e_channels      channels;
 	u32                        tisn[MLX5E_MAX_NUM_TC];
 	struct mlx5e_rqt           indir_rqt;
 	struct mlx5e_tir           indir_tir[MLX5E_NUM_INDIR_TIRS];
@@ -712,7 +737,6 @@ struct mlx5e_priv {
 	struct mlx5e_flow_steering fs;
 	struct mlx5e_vxlan_db      vxlan;
 
-	struct mlx5e_params        params;
 	struct workqueue_struct    *wq;
 	struct work_struct         update_carrier_work;
 	struct work_struct         set_rx_mode_work;
@@ -732,9 +756,24 @@ struct mlx5e_priv {
 	void                      *ppriv;
 };
 
+struct mlx5e_profile {
+	void	(*init)(struct mlx5_core_dev *mdev,
+			struct net_device *netdev,
+			const struct mlx5e_profile *profile, void *ppriv);
+	void	(*cleanup)(struct mlx5e_priv *priv);
+	int	(*init_rx)(struct mlx5e_priv *priv);
+	void	(*cleanup_rx)(struct mlx5e_priv *priv);
+	int	(*init_tx)(struct mlx5e_priv *priv);
+	void	(*cleanup_tx)(struct mlx5e_priv *priv);
+	void	(*enable)(struct mlx5e_priv *priv);
+	void	(*disable)(struct mlx5e_priv *priv);
+	void	(*update_stats)(struct mlx5e_priv *priv);
+	int	(*max_nch)(struct mlx5_core_dev *mdev);
+	int	max_tc;
+};
+
 void mlx5e_build_ptys2ethtool_map(void);
 
-void mlx5e_send_nop(struct mlx5e_sq *sq, bool notify_hw);
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 		       void *accel_priv, select_queue_fallback_t fallback);
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
@@ -744,7 +783,9 @@ 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);
-void mlx5e_free_sq_descs(struct mlx5e_sq *sq);
+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);
 
 void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
 			bool recycle);
@@ -792,7 +833,7 @@ void mlx5e_pps_event_handler(struct mlx5e_priv *priv,
 			     struct ptp_clock_event *event);
 int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr);
 int mlx5e_hwstamp_get(struct net_device *dev, struct ifreq *ifr);
-void mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val);
+int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val);
 
 int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto,
 			  u16 vid);
@@ -801,14 +842,40 @@ int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto,
 void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv);
 void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv);
 
-int mlx5e_modify_rqs_vsd(struct mlx5e_priv *priv, bool vsd);
+int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd);
 
-int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, int ix);
-void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc,
-				    enum mlx5e_traffic_types tt);
+struct mlx5e_redirect_rqt_param {
+	bool is_rss;
+	union {
+		u32 rqn; /* Direct RQN (Non-RSS) */
+		struct {
+			u8 hfunc;
+			struct mlx5e_channels *channels;
+		} rss; /* RSS data */
+	};
+};
+
+int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz,
+		       struct mlx5e_redirect_rqt_param rrp);
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
+				    enum mlx5e_traffic_types tt,
+				    void *tirc);
 
 int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);
+
+int mlx5e_open_channels(struct mlx5e_priv *priv,
+			struct mlx5e_channels *chs);
+void mlx5e_close_channels(struct mlx5e_channels *chs);
+
+/* Function pointer to be used to modify WH settings while
+ * switching channels
+ */
+typedef int (*mlx5e_fp_hw_modify)(struct mlx5e_priv *priv);
+void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
+				struct mlx5e_channels *new_chs,
+				mlx5e_fp_hw_modify hw_modify);
+
 void mlx5e_build_default_indir_rqt(struct mlx5_core_dev *mdev,
 				   u32 *indirection_rqt, int len,
 				   int num_channels);
@@ -816,30 +883,43 @@ int mlx5e_get_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 
 void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params,
 				 u8 cq_period_mode);
-void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type);
+void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev,
+			      struct mlx5e_params *params, u8 rq_type);
 
-static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq,
-				      struct mlx5_wqe_ctrl_seg *ctrl, int bf_sz)
+static inline
+struct mlx5e_tx_wqe *mlx5e_post_nop(struct mlx5_wq_cyc *wq, u32 sqn, u16 *pc)
 {
-	u16 ofst = sq->bf_offset;
+	u16                         pi   = *pc & wq->sz_m1;
+	struct mlx5e_tx_wqe        *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
+	struct mlx5_wqe_ctrl_seg   *cseg = &wqe->ctrl;
+
+	memset(cseg, 0, sizeof(*cseg));
+
+	cseg->opmod_idx_opcode = cpu_to_be32((*pc << 8) | MLX5_OPCODE_NOP);
+	cseg->qpn_ds           = cpu_to_be32((sqn << 8) | 0x01);
+
+	(*pc)++;
 
+	return wqe;
+}
+
+static inline
+void mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc,
+		     void __iomem *uar_map,
+		     struct mlx5_wqe_ctrl_seg *ctrl)
+{
+	ctrl->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
 	/* ensure wqe is visible to device before updating doorbell record */
 	dma_wmb();
 
-	*sq->wq.db = cpu_to_be32(sq->pc);
+	*wq->db = cpu_to_be32(pc);
 
 	/* ensure doorbell record is visible to device before ringing the
 	 * doorbell
 	 */
 	wmb();
-	if (bf_sz)
-		__iowrite64_copy(sq->uar_map + ofst, ctrl, bf_sz);
-	else
-		mlx5_write64((__be32 *)ctrl, sq->uar_map + ofst, NULL);
-	/* flush the write-combining mapped buffer */
-	wmb();
 
-	sq->bf_offset ^= sq->bf_buf_size;
+	mlx5_write64((__be32 *)ctrl, uar_map, NULL);
 }
 
 static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
@@ -895,8 +975,7 @@ void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
 		       struct mlx5e_tir *tir);
 int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev);
 void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
-int mlx5e_refresh_tirs_self_loopback(struct mlx5_core_dev *mdev,
-				     bool enable_uc_lb);
+int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb);
 
 struct mlx5_eswitch_rep;
 int mlx5e_vport_rep_load(struct mlx5_eswitch *esw,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 68419a01db36..c4e9cc79f5c7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -174,13 +174,9 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv,
 				 enum arfs_type type)
 {
 	struct arfs_table *arfs_t = &priv->fs.arfs.arfs_tables[type];
-	struct mlx5_flow_act flow_act = {
-		.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
-		.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
-		.encap_id = 0,
-	};
-	struct mlx5_flow_destination dest;
 	struct mlx5e_tir *tir = priv->indir_tir;
+	struct mlx5_flow_destination dest;
+	MLX5_DECLARE_FLOW_ACT(flow_act);
 	struct mlx5_flow_spec *spec;
 	int err = 0;
 
@@ -469,15 +465,11 @@ static struct arfs_table *arfs_get_table(struct mlx5e_arfs_tables *arfs,
 static struct mlx5_flow_handle *arfs_add_rule(struct mlx5e_priv *priv,
 					      struct arfs_rule *arfs_rule)
 {
-	struct mlx5_flow_act flow_act = {
-		.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
-		.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
-		.encap_id = 0,
-	};
 	struct mlx5e_arfs_tables *arfs = &priv->fs.arfs;
 	struct arfs_tuple *tuple = &arfs_rule->tuple;
 	struct mlx5_flow_handle *rule = NULL;
 	struct mlx5_flow_destination dest;
+	MLX5_DECLARE_FLOW_ACT(flow_act);
 	struct arfs_table *arfs_table;
 	struct mlx5_flow_spec *spec;
 	struct mlx5_flow_table *ft;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index 37e66eef6fb5..e706a87fc8b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -90,6 +90,7 @@ int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct hwtstamp_config config;
+	int err;
 
 	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
 		return -EOPNOTSUPP;
@@ -111,7 +112,7 @@ int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
 	switch (config.rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		/* Reset CQE compression to Admin default */
-		mlx5e_modify_rx_cqe_compression_locked(priv, priv->params.rx_cqe_compress_def);
+		mlx5e_modify_rx_cqe_compression_locked(priv, priv->channels.params.rx_cqe_compress_def);
 		break;
 	case HWTSTAMP_FILTER_ALL:
 	case HWTSTAMP_FILTER_SOME:
@@ -129,7 +130,12 @@ int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 		/* Disable CQE compression */
 		netdev_warn(dev, "Disabling cqe compression");
-		mlx5e_modify_rx_cqe_compression_locked(priv, false);
+		err = mlx5e_modify_rx_cqe_compression_locked(priv, false);
+		if (err) {
+			netdev_err(dev, "Failed disabling cqe compression err=%d\n", err);
+			mutex_unlock(&priv->state_lock);
+			return err;
+		}
 		config.rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index bd898d8deda0..f1f17f7a3cd0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -107,10 +107,18 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 		goto err_dealloc_transport_domain;
 	}
 
+	err = mlx5_alloc_bfreg(mdev, &res->bfreg, false, false);
+	if (err) {
+		mlx5_core_err(mdev, "alloc bfreg failed, %d\n", err);
+		goto err_destroy_mkey;
+	}
+
 	INIT_LIST_HEAD(&mdev->mlx5e_res.td.tirs_list);
 
 	return 0;
 
+err_destroy_mkey:
+	mlx5_core_destroy_mkey(mdev, &res->mkey);
 err_dealloc_transport_domain:
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
 err_dealloc_pd:
@@ -122,23 +130,26 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
 {
 	struct mlx5e_resources *res = &mdev->mlx5e_res;
 
+	mlx5_free_bfreg(mdev, &res->bfreg);
 	mlx5_core_destroy_mkey(mdev, &res->mkey);
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
 	mlx5_core_dealloc_pd(mdev, res->pdn);
 }
 
-int mlx5e_refresh_tirs_self_loopback(struct mlx5_core_dev *mdev,
-				     bool enable_uc_lb)
+int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 {
+	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_tir *tir;
-	void *in;
+	int err  = -ENOMEM;
+	u32 tirn = 0;
 	int inlen;
-	int err = 0;
+	void *in;
+
 
 	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
 	in = mlx5_vzalloc(inlen);
 	if (!in)
-		return -ENOMEM;
+		goto out;
 
 	if (enable_uc_lb)
 		MLX5_SET(modify_tir_in, in, ctx.self_lb_block,
@@ -147,13 +158,16 @@ int mlx5e_refresh_tirs_self_loopback(struct mlx5_core_dev *mdev,
 	MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
 
 	list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) {
-		err = mlx5_core_modify_tir(mdev, tir->tirn, in, inlen);
+		tirn = tir->tirn;
+		err = mlx5_core_modify_tir(mdev, tirn, in, inlen);
 		if (err)
 			goto out;
 	}
 
 out:
 	kvfree(in);
+	if (err)
+		netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index a004a5a1a4c2..af039b6c0799 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -152,12 +152,9 @@ static bool mlx5e_query_global_pause_combined(struct mlx5e_priv *priv)
 }
 
 #define MLX5E_NUM_Q_CNTRS(priv) (NUM_Q_COUNTERS * (!!priv->q_counter))
-#define MLX5E_NUM_RQ_STATS(priv) \
-	(NUM_RQ_STATS * priv->params.num_channels * \
-	 test_bit(MLX5E_STATE_OPENED, &priv->state))
+#define MLX5E_NUM_RQ_STATS(priv) (NUM_RQ_STATS * (priv)->channels.num)
 #define MLX5E_NUM_SQ_STATS(priv) \
-	(NUM_SQ_STATS * priv->params.num_channels * priv->params.num_tc * \
-	 test_bit(MLX5E_STATE_OPENED, &priv->state))
+	(NUM_SQ_STATS * (priv)->channels.num * (priv)->channels.params.num_tc)
 #define MLX5E_NUM_PFC_COUNTERS(priv) \
 	((mlx5e_query_global_pause_combined(priv) + hweight8(mlx5e_query_pfc_combined(priv))) * \
 	  NUM_PPORT_PER_PRIO_PFC_COUNTERS)
@@ -262,17 +259,17 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data)
 		return;
 
 	/* per channel counters */
-	for (i = 0; i < priv->params.num_channels; i++)
+	for (i = 0; i < priv->channels.num; i++)
 		for (j = 0; j < NUM_RQ_STATS; j++)
 			sprintf(data + (idx++) * ETH_GSTRING_LEN,
 				rq_stats_desc[j].format, i);
 
-	for (tc = 0; tc < priv->params.num_tc; tc++)
-		for (i = 0; i < priv->params.num_channels; i++)
+	for (tc = 0; tc < priv->channels.params.num_tc; tc++)
+		for (i = 0; i < priv->channels.num; i++)
 			for (j = 0; j < NUM_SQ_STATS; j++)
 				sprintf(data + (idx++) * ETH_GSTRING_LEN,
 					sq_stats_desc[j].format,
-					priv->channeltc_to_txq_map[i][tc]);
+					priv->channel_tc2txq[i][tc]);
 }
 
 static void mlx5e_get_strings(struct net_device *dev,
@@ -303,6 +300,7 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
 				    struct ethtool_stats *stats, u64 *data)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_channels *channels;
 	struct mlx5_priv *mlx5_priv;
 	int i, j, tc, prio, idx = 0;
 	unsigned long pfc_combined;
@@ -313,6 +311,7 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
 	mutex_lock(&priv->state_lock);
 	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
 		mlx5e_update_stats(priv);
+	channels = &priv->channels;
 	mutex_unlock(&priv->state_lock);
 
 	for (i = 0; i < NUM_SW_COUNTERS; i++)
@@ -382,16 +381,16 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
 		return;
 
 	/* per channel counters */
-	for (i = 0; i < priv->params.num_channels; i++)
+	for (i = 0; i < channels->num; i++)
 		for (j = 0; j < NUM_RQ_STATS; j++)
 			data[idx++] =
-			       MLX5E_READ_CTR64_CPU(&priv->channel[i]->rq.stats,
+			       MLX5E_READ_CTR64_CPU(&channels->c[i]->rq.stats,
 						    rq_stats_desc, j);
 
-	for (tc = 0; tc < priv->params.num_tc; tc++)
-		for (i = 0; i < priv->params.num_channels; i++)
+	for (tc = 0; tc < priv->channels.params.num_tc; tc++)
+		for (i = 0; i < channels->num; i++)
 			for (j = 0; j < NUM_SQ_STATS; j++)
-				data[idx++] = MLX5E_READ_CTR64_CPU(&priv->channel[i]->sq[tc].stats,
+				data[idx++] = MLX5E_READ_CTR64_CPU(&channels->c[i]->sq[tc].stats,
 								   sq_stats_desc, j);
 }
 
@@ -406,8 +405,8 @@ static u32 mlx5e_rx_wqes_to_packets(struct mlx5e_priv *priv, int rq_wq_type,
 	if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
 		return num_wqe;
 
-	stride_size = 1 << priv->params.mpwqe_log_stride_sz;
-	num_strides = 1 << priv->params.mpwqe_log_num_strides;
+	stride_size = 1 << priv->channels.params.mpwqe_log_stride_sz;
+	num_strides = 1 << priv->channels.params.mpwqe_log_num_strides;
 	wqe_size = stride_size * num_strides;
 
 	packets_per_wqe = wqe_size /
@@ -427,8 +426,8 @@ static u32 mlx5e_packets_to_rx_wqes(struct mlx5e_priv *priv, int rq_wq_type,
 	if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
 		return num_packets;
 
-	stride_size = 1 << priv->params.mpwqe_log_stride_sz;
-	num_strides = 1 << priv->params.mpwqe_log_num_strides;
+	stride_size = 1 << priv->channels.params.mpwqe_log_stride_sz;
+	num_strides = 1 << priv->channels.params.mpwqe_log_num_strides;
 	wqe_size = stride_size * num_strides;
 
 	num_packets = (1 << order_base_2(num_packets));
@@ -443,26 +442,25 @@ static void mlx5e_get_ringparam(struct net_device *dev,
 				struct ethtool_ringparam *param)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	int rq_wq_type = priv->params.rq_wq_type;
+	int rq_wq_type = priv->channels.params.rq_wq_type;
 
 	param->rx_max_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
 							 1 << mlx5_max_log_rq_size(rq_wq_type));
 	param->tx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE;
 	param->rx_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
-						     1 << priv->params.log_rq_size);
-	param->tx_pending     = 1 << priv->params.log_sq_size;
+						     1 << priv->channels.params.log_rq_size);
+	param->tx_pending     = 1 << priv->channels.params.log_sq_size;
 }
 
 static int mlx5e_set_ringparam(struct net_device *dev,
 			       struct ethtool_ringparam *param)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	bool was_opened;
-	int rq_wq_type = priv->params.rq_wq_type;
+	int rq_wq_type = priv->channels.params.rq_wq_type;
+	struct mlx5e_channels new_channels = {};
 	u32 rx_pending_wqes;
 	u32 min_rq_size;
 	u32 max_rq_size;
-	u16 min_rx_wqes;
 	u8 log_rq_size;
 	u8 log_sq_size;
 	u32 num_mtts;
@@ -500,7 +498,7 @@ static int mlx5e_set_ringparam(struct net_device *dev,
 	}
 
 	num_mtts = MLX5E_REQUIRED_MTTS(rx_pending_wqes);
-	if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
+	if (priv->channels.params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
 	    !MLX5E_VALID_NUM_MTTS(num_mtts)) {
 		netdev_info(dev, "%s: rx_pending (%d) request can't be satisfied, try to reduce.\n",
 			    __func__, param->rx_pending);
@@ -522,26 +520,29 @@ static int mlx5e_set_ringparam(struct net_device *dev,
 
 	log_rq_size = order_base_2(rx_pending_wqes);
 	log_sq_size = order_base_2(param->tx_pending);
-	min_rx_wqes = mlx5_min_rx_wqes(rq_wq_type, rx_pending_wqes);
 
-	if (log_rq_size == priv->params.log_rq_size &&
-	    log_sq_size == priv->params.log_sq_size &&
-	    min_rx_wqes == priv->params.min_rx_wqes)
+	if (log_rq_size == priv->channels.params.log_rq_size &&
+	    log_sq_size == priv->channels.params.log_sq_size)
 		return 0;
 
 	mutex_lock(&priv->state_lock);
 
-	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (was_opened)
-		mlx5e_close_locked(dev);
+	new_channels.params = priv->channels.params;
+	new_channels.params.log_rq_size = log_rq_size;
+	new_channels.params.log_sq_size = log_sq_size;
 
-	priv->params.log_rq_size = log_rq_size;
-	priv->params.log_sq_size = log_sq_size;
-	priv->params.min_rx_wqes = min_rx_wqes;
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		priv->channels.params = new_channels.params;
+		goto unlock;
+	}
+
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err)
+		goto unlock;
 
-	if (was_opened)
-		err = mlx5e_open_locked(dev);
+	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
 
+unlock:
 	mutex_unlock(&priv->state_lock);
 
 	return err;
@@ -553,7 +554,7 @@ static void mlx5e_get_channels(struct net_device *dev,
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
 	ch->max_combined   = priv->profile->max_nch(priv->mdev);
-	ch->combined_count = priv->params.num_channels;
+	ch->combined_count = priv->channels.params.num_channels;
 }
 
 static int mlx5e_set_channels(struct net_device *dev,
@@ -561,8 +562,8 @@ static int mlx5e_set_channels(struct net_device *dev,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	unsigned int count = ch->combined_count;
+	struct mlx5e_channels new_channels = {};
 	bool arfs_enabled;
-	bool was_opened;
 	int err = 0;
 
 	if (!count) {
@@ -571,27 +572,32 @@ static int mlx5e_set_channels(struct net_device *dev,
 		return -EINVAL;
 	}
 
-	if (priv->params.num_channels == count)
+	if (priv->channels.params.num_channels == count)
 		return 0;
 
 	mutex_lock(&priv->state_lock);
 
-	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (was_opened)
-		mlx5e_close_locked(dev);
+	new_channels.params = priv->channels.params;
+	new_channels.params.num_channels = count;
+	mlx5e_build_default_indir_rqt(priv->mdev, new_channels.params.indirection_rqt,
+				      MLX5E_INDIR_RQT_SIZE, count);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		priv->channels.params = new_channels.params;
+		goto out;
+	}
+
+	/* Create fresh channels with new parameters */
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err)
+		goto out;
 
 	arfs_enabled = dev->features & NETIF_F_NTUPLE;
 	if (arfs_enabled)
 		mlx5e_arfs_disable(priv);
 
-	priv->params.num_channels = count;
-	mlx5e_build_default_indir_rqt(priv->mdev, priv->params.indirection_rqt,
-				      MLX5E_INDIR_RQT_SIZE, count);
-
-	if (was_opened)
-		err = mlx5e_open_locked(dev);
-	if (err)
-		goto out;
+	/* Switch to new channels, set new parameters and close old ones */
+	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
 
 	if (arfs_enabled) {
 		err = mlx5e_arfs_enable(priv);
@@ -614,49 +620,24 @@ static int mlx5e_get_coalesce(struct net_device *netdev,
 	if (!MLX5_CAP_GEN(priv->mdev, cq_moderation))
 		return -EOPNOTSUPP;
 
-	coal->rx_coalesce_usecs       = priv->params.rx_cq_moderation.usec;
-	coal->rx_max_coalesced_frames = priv->params.rx_cq_moderation.pkts;
-	coal->tx_coalesce_usecs       = priv->params.tx_cq_moderation.usec;
-	coal->tx_max_coalesced_frames = priv->params.tx_cq_moderation.pkts;
-	coal->use_adaptive_rx_coalesce = priv->params.rx_am_enabled;
+	coal->rx_coalesce_usecs       = priv->channels.params.rx_cq_moderation.usec;
+	coal->rx_max_coalesced_frames = priv->channels.params.rx_cq_moderation.pkts;
+	coal->tx_coalesce_usecs       = priv->channels.params.tx_cq_moderation.usec;
+	coal->tx_max_coalesced_frames = priv->channels.params.tx_cq_moderation.pkts;
+	coal->use_adaptive_rx_coalesce = priv->channels.params.rx_am_enabled;
 
 	return 0;
 }
 
-static int mlx5e_set_coalesce(struct net_device *netdev,
-			      struct ethtool_coalesce *coal)
+static void
+mlx5e_set_priv_channels_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal)
 {
-	struct mlx5e_priv *priv    = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5e_channel *c;
-	bool restart =
-		!!coal->use_adaptive_rx_coalesce != priv->params.rx_am_enabled;
-	bool was_opened;
-	int err = 0;
 	int tc;
 	int i;
 
-	if (!MLX5_CAP_GEN(mdev, cq_moderation))
-		return -EOPNOTSUPP;
-
-	mutex_lock(&priv->state_lock);
-
-	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (was_opened && restart) {
-		mlx5e_close_locked(netdev);
-		priv->params.rx_am_enabled = !!coal->use_adaptive_rx_coalesce;
-	}
-
-	priv->params.tx_cq_moderation.usec = coal->tx_coalesce_usecs;
-	priv->params.tx_cq_moderation.pkts = coal->tx_max_coalesced_frames;
-	priv->params.rx_cq_moderation.usec = coal->rx_coalesce_usecs;
-	priv->params.rx_cq_moderation.pkts = coal->rx_max_coalesced_frames;
-
-	if (!was_opened || restart)
-		goto out;
-
-	for (i = 0; i < priv->params.num_channels; ++i) {
-		c = priv->channel[i];
+	for (i = 0; i < priv->channels.num; ++i) {
+		struct mlx5e_channel *c = priv->channels.c[i];
 
 		for (tc = 0; tc < c->num_tc; tc++) {
 			mlx5_core_modify_cq_moderation(mdev,
@@ -669,11 +650,50 @@ static int mlx5e_set_coalesce(struct net_device *netdev,
 					       coal->rx_coalesce_usecs,
 					       coal->rx_max_coalesced_frames);
 	}
+}
 
-out:
-	if (was_opened && restart)
-		err = mlx5e_open_locked(netdev);
+static int mlx5e_set_coalesce(struct net_device *netdev,
+			      struct ethtool_coalesce *coal)
+{
+	struct mlx5e_priv *priv    = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_channels new_channels = {};
+	int err = 0;
+	bool reset;
+
+	if (!MLX5_CAP_GEN(mdev, cq_moderation))
+		return -EOPNOTSUPP;
+
+	mutex_lock(&priv->state_lock);
+	new_channels.params = priv->channels.params;
+
+	new_channels.params.tx_cq_moderation.usec = coal->tx_coalesce_usecs;
+	new_channels.params.tx_cq_moderation.pkts = coal->tx_max_coalesced_frames;
+	new_channels.params.rx_cq_moderation.usec = coal->rx_coalesce_usecs;
+	new_channels.params.rx_cq_moderation.pkts = coal->rx_max_coalesced_frames;
+	new_channels.params.rx_am_enabled         = !!coal->use_adaptive_rx_coalesce;
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		priv->channels.params = new_channels.params;
+		goto out;
+	}
+	/* we are opened */
+
+	reset = !!coal->use_adaptive_rx_coalesce != priv->channels.params.rx_am_enabled;
+	if (!reset) {
+		mlx5e_set_priv_channels_coalesce(priv, coal);
+		priv->channels.params = new_channels.params;
+		goto out;
+	}
+
+	/* open fresh channels with new coal parameters */
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err)
+		goto out;
+
+	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
 
+out:
 	mutex_unlock(&priv->state_lock);
 	return err;
 }
@@ -968,7 +988,7 @@ static u32 mlx5e_get_rxfh_key_size(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	return sizeof(priv->params.toeplitz_hash_key);
+	return sizeof(priv->channels.params.toeplitz_hash_key);
 }
 
 static u32 mlx5e_get_rxfh_indir_size(struct net_device *netdev)
@@ -982,15 +1002,15 @@ static int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
 	if (indir)
-		memcpy(indir, priv->params.indirection_rqt,
-		       sizeof(priv->params.indirection_rqt));
+		memcpy(indir, priv->channels.params.indirection_rqt,
+		       sizeof(priv->channels.params.indirection_rqt));
 
 	if (key)
-		memcpy(key, priv->params.toeplitz_hash_key,
-		       sizeof(priv->params.toeplitz_hash_key));
+		memcpy(key, priv->channels.params.toeplitz_hash_key,
+		       sizeof(priv->channels.params.toeplitz_hash_key));
 
 	if (hfunc)
-		*hfunc = priv->params.rss_hfunc;
+		*hfunc = priv->channels.params.rss_hfunc;
 
 	return 0;
 }
@@ -1006,7 +1026,7 @@ static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
 		memset(tirc, 0, ctxlen);
-		mlx5e_build_indir_tir_ctx_hash(priv, tirc, tt);
+		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc);
 		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
 	}
 }
@@ -1030,25 +1050,37 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 
 	mutex_lock(&priv->state_lock);
 
-	if (indir) {
-		u32 rqtn = priv->indir_rqt.rqtn;
-
-		memcpy(priv->params.indirection_rqt, indir,
-		       sizeof(priv->params.indirection_rqt));
-		mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, 0);
-	}
-
 	if (hfunc != ETH_RSS_HASH_NO_CHANGE &&
-	    hfunc != priv->params.rss_hfunc) {
-		priv->params.rss_hfunc = hfunc;
+	    hfunc != priv->channels.params.rss_hfunc) {
+		priv->channels.params.rss_hfunc = hfunc;
 		hash_changed = true;
 	}
 
+	if (indir) {
+		memcpy(priv->channels.params.indirection_rqt, indir,
+		       sizeof(priv->channels.params.indirection_rqt));
+
+		if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+			u32 rqtn = priv->indir_rqt.rqtn;
+			struct mlx5e_redirect_rqt_param rrp = {
+				.is_rss = true,
+				{
+					.rss = {
+						.hfunc = priv->channels.params.rss_hfunc,
+						.channels  = &priv->channels,
+					},
+				},
+			};
+
+			mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp);
+		}
+	}
+
 	if (key) {
-		memcpy(priv->params.toeplitz_hash_key, key,
-		       sizeof(priv->params.toeplitz_hash_key));
+		memcpy(priv->channels.params.toeplitz_hash_key, key,
+		       sizeof(priv->channels.params.toeplitz_hash_key));
 		hash_changed = hash_changed ||
-			       priv->params.rss_hfunc == ETH_RSS_HASH_TOP;
+			       priv->channels.params.rss_hfunc == ETH_RSS_HASH_TOP;
 	}
 
 	if (hash_changed)
@@ -1069,7 +1101,7 @@ static int mlx5e_get_rxnfc(struct net_device *netdev,
 
 	switch (info->cmd) {
 	case ETHTOOL_GRXRINGS:
-		info->data = priv->params.num_channels;
+		info->data = priv->channels.params.num_channels;
 		break;
 	case ETHTOOL_GRXCLSRLCNT:
 		info->rule_cnt = priv->fs.ethtool.tot_num_rules;
@@ -1097,7 +1129,7 @@ static int mlx5e_get_tunable(struct net_device *dev,
 
 	switch (tuna->id) {
 	case ETHTOOL_TX_COPYBREAK:
-		*(u32 *)data = priv->params.tx_max_inline;
+		*(u32 *)data = priv->channels.params.tx_max_inline;
 		break;
 	default:
 		err = -EINVAL;
@@ -1113,9 +1145,11 @@ static int mlx5e_set_tunable(struct net_device *dev,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
-	bool was_opened;
-	u32 val;
+	struct mlx5e_channels new_channels = {};
 	int err = 0;
+	u32 val;
+
+	mutex_lock(&priv->state_lock);
 
 	switch (tuna->id) {
 	case ETHTOOL_TX_COPYBREAK:
@@ -1125,24 +1159,26 @@ static int mlx5e_set_tunable(struct net_device *dev,
 			break;
 		}
 
-		mutex_lock(&priv->state_lock);
+		new_channels.params = priv->channels.params;
+		new_channels.params.tx_max_inline = val;
 
-		was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-		if (was_opened)
-			mlx5e_close_locked(dev);
-
-		priv->params.tx_max_inline = val;
+		if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+			priv->channels.params = new_channels.params;
+			break;
+		}
 
-		if (was_opened)
-			err = mlx5e_open_locked(dev);
+		err = mlx5e_open_channels(priv, &new_channels);
+		if (err)
+			break;
+		mlx5e_switch_priv_channels(priv, &new_channels, NULL);
 
-		mutex_unlock(&priv->state_lock);
 		break;
 	default:
 		err = -EINVAL;
 		break;
 	}
 
+	mutex_unlock(&priv->state_lock);
 	return err;
 }
 
@@ -1442,15 +1478,15 @@ static int set_pflag_rx_cqe_based_moder(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_channels new_channels = {};
 	bool rx_mode_changed;
 	u8 rx_cq_period_mode;
 	int err = 0;
-	bool reset;
 
 	rx_cq_period_mode = enable ?
 		MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
 		MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
-	rx_mode_changed = rx_cq_period_mode != priv->params.rx_cq_period_mode;
+	rx_mode_changed = rx_cq_period_mode != priv->channels.params.rx_cq_period_mode;
 
 	if (rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE &&
 	    !MLX5_CAP_GEN(mdev, cq_period_start_from_cqe))
@@ -1459,16 +1495,51 @@ static int set_pflag_rx_cqe_based_moder(struct net_device *netdev, bool enable)
 	if (!rx_mode_changed)
 		return 0;
 
-	reset = test_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (reset)
-		mlx5e_close_locked(netdev);
+	new_channels.params = priv->channels.params;
+	mlx5e_set_rx_cq_mode_params(&new_channels.params, rx_cq_period_mode);
 
-	mlx5e_set_rx_cq_mode_params(&priv->params, rx_cq_period_mode);
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		priv->channels.params = new_channels.params;
+		return 0;
+	}
 
-	if (reset)
-		err = mlx5e_open_locked(netdev);
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err)
+		return err;
 
-	return err;
+	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+	return 0;
+}
+
+int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val)
+{
+	bool curr_val = MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS);
+	struct mlx5e_channels new_channels = {};
+	int err = 0;
+
+	if (!MLX5_CAP_GEN(priv->mdev, cqe_compression))
+		return new_val ? -EOPNOTSUPP : 0;
+
+	if (curr_val == new_val)
+		return 0;
+
+	new_channels.params = priv->channels.params;
+	MLX5E_SET_PFLAG(&new_channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS, new_val);
+
+	mlx5e_set_rq_type_params(priv->mdev, &new_channels.params,
+				 new_channels.params.rq_wq_type);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		priv->channels.params = new_channels.params;
+		return 0;
+	}
+
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err)
+		return err;
+
+	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+	return 0;
 }
 
 static int set_pflag_rx_cqe_compress(struct net_device *netdev,
@@ -1486,8 +1557,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev,
 	}
 
 	mlx5e_modify_rx_cqe_compression_locked(priv, enable);
-	priv->params.rx_cqe_compress_def = enable;
-	mlx5e_set_rq_type_params(priv, priv->params.rq_wq_type);
+	priv->channels.params.rx_cqe_compress_def = enable;
 
 	return 0;
 }
@@ -1499,7 +1569,7 @@ static int mlx5e_handle_pflag(struct net_device *netdev,
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	bool enable = !!(wanted_flags & flag);
-	u32 changes = wanted_flags ^ priv->params.pflags;
+	u32 changes = wanted_flags ^ priv->channels.params.pflags;
 	int err;
 
 	if (!(changes & flag))
@@ -1512,7 +1582,7 @@ static int mlx5e_handle_pflag(struct net_device *netdev,
 		return err;
 	}
 
-	MLX5E_SET_PFLAG(priv, flag, enable);
+	MLX5E_SET_PFLAG(&priv->channels.params, flag, enable);
 	return 0;
 }
 
@@ -1541,7 +1611,7 @@ static u32 mlx5e_get_priv_flags(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	return priv->params.pflags;
+	return priv->channels.params.pflags;
 }
 
 static int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index f2762e45c8ae..5376d69a6b1a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -159,14 +159,10 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv,
 				 enum mlx5e_vlan_rule_type rule_type,
 				 u16 vid, struct mlx5_flow_spec *spec)
 {
-	struct mlx5_flow_act flow_act = {
-		.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
-		.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
-		.encap_id = 0,
-	};
 	struct mlx5_flow_table *ft = priv->fs.vlan.ft.t;
 	struct mlx5_flow_destination dest;
 	struct mlx5_flow_handle **rule_p;
+	MLX5_DECLARE_FLOW_ACT(flow_act);
 	int err = 0;
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
@@ -659,11 +655,7 @@ mlx5e_generate_ttc_rule(struct mlx5e_priv *priv,
 			u16 etype,
 			u8 proto)
 {
-	struct mlx5_flow_act flow_act = {
-		.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
-		.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
-		.encap_id = 0,
-	};
+	MLX5_DECLARE_FLOW_ACT(flow_act);
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_spec *spec;
 	int err = 0;
@@ -848,13 +840,9 @@ static void mlx5e_del_l2_flow_rule(struct mlx5e_priv *priv,
 static int mlx5e_add_l2_flow_rule(struct mlx5e_priv *priv,
 				  struct mlx5e_l2_rule *ai, int type)
 {
-	struct mlx5_flow_act flow_act = {
-		.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
-		.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
-		.encap_id = 0,
-	};
 	struct mlx5_flow_table *ft = priv->fs.l2.ft.t;
 	struct mlx5_flow_destination dest;
+	MLX5_DECLARE_FLOW_ACT(flow_act);
 	struct mlx5_flow_spec *spec;
 	int err = 0;
 	u8 *mc_dmac;
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 d55fff0ba388..e73c97fea55c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -390,7 +390,7 @@ static int validate_flow(struct mlx5e_priv *priv,
 	if (fs->location >= MAX_NUM_OF_ETHTOOL_RULES)
 		return -EINVAL;
 
-	if (fs->ring_cookie >= priv->params.num_channels &&
+	if (fs->ring_cookie >= priv->channels.params.num_channels &&
 	    fs->ring_cookie != RX_CLS_FLOW_DISC)
 		return -EINVAL;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 66c133757a5e..ec389b1b51cb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -44,15 +44,11 @@
 struct mlx5e_rq_param {
 	u32			rqc[MLX5_ST_SZ_DW(rqc)];
 	struct mlx5_wq_param	wq;
-	bool			am_enabled;
 };
 
 struct mlx5e_sq_param {
 	u32                        sqc[MLX5_ST_SZ_DW(sqc)];
 	struct mlx5_wq_param       wq;
-	u16                        max_inline;
-	u8                         min_inline_mode;
-	enum mlx5e_sq_type         type;
 };
 
 struct mlx5e_cq_param {
@@ -79,49 +75,47 @@ static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 		MLX5_CAP_ETH(mdev, reg_umr_sq);
 }
 
-void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type)
+void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev,
+			      struct mlx5e_params *params, u8 rq_type)
 {
-	priv->params.rq_wq_type = rq_type;
-	priv->params.lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
-	switch (priv->params.rq_wq_type) {
+	params->rq_wq_type = rq_type;
+	params->lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
+	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		priv->params.log_rq_size = is_kdump_kernel() ?
+		params->log_rq_size = is_kdump_kernel() ?
 			MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW :
 			MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW;
-		priv->params.mpwqe_log_stride_sz =
-			MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS) ?
-			MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(priv->mdev) :
-			MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(priv->mdev);
-		priv->params.mpwqe_log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ -
-			priv->params.mpwqe_log_stride_sz;
+		params->mpwqe_log_stride_sz =
+			MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS) ?
+			MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) :
+			MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev);
+		params->mpwqe_log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ -
+			params->mpwqe_log_stride_sz;
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
-		priv->params.log_rq_size = is_kdump_kernel() ?
+		params->log_rq_size = is_kdump_kernel() ?
 			MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
 			MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
 
 		/* Extra room needed for build_skb */
-		priv->params.lro_wqe_sz -= MLX5_RX_HEADROOM +
+		params->lro_wqe_sz -= MLX5_RX_HEADROOM +
 			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	}
-	priv->params.min_rx_wqes = mlx5_min_rx_wqes(priv->params.rq_wq_type,
-					       BIT(priv->params.log_rq_size));
 
-	mlx5_core_info(priv->mdev,
-		       "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n",
-		       priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ,
-		       BIT(priv->params.log_rq_size),
-		       BIT(priv->params.mpwqe_log_stride_sz),
-		       MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS));
+	mlx5_core_info(mdev, "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n",
+		       params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ,
+		       BIT(params->log_rq_size),
+		       BIT(params->mpwqe_log_stride_sz),
+		       MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
 }
 
-static void mlx5e_set_rq_priv_params(struct mlx5e_priv *priv)
+static void mlx5e_set_rq_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
 {
-	u8 rq_type = mlx5e_check_fragmented_striding_rq_cap(priv->mdev) &&
-		    !priv->xdp_prog ?
+	u8 rq_type = mlx5e_check_fragmented_striding_rq_cap(mdev) &&
+		    !params->xdp_prog ?
 		    MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ :
 		    MLX5_WQ_TYPE_LINKED_LIST;
-	mlx5e_set_rq_type_params(priv, rq_type);
+	mlx5e_set_rq_type_params(mdev, params, rq_type);
 }
 
 static void mlx5e_update_carrier(struct mlx5e_priv *priv)
@@ -181,8 +175,10 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 	int i, j;
 
 	memset(s, 0, sizeof(*s));
-	for (i = 0; i < priv->params.num_channels; i++) {
-		rq_stats = &priv->channel[i]->rq.stats;
+	for (i = 0; i < priv->channels.num; i++) {
+		struct mlx5e_channel *c = priv->channels.c[i];
+
+		rq_stats = &c->rq.stats;
 
 		s->rx_packets	+= rq_stats->packets;
 		s->rx_bytes	+= rq_stats->bytes;
@@ -204,8 +200,8 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 		s->rx_cache_empty += rq_stats->cache_empty;
 		s->rx_cache_busy  += rq_stats->cache_busy;
 
-		for (j = 0; j < priv->params.num_tc; j++) {
-			sq_stats = &priv->channel[i]->sq[j].stats;
+		for (j = 0; j < priv->channels.params.num_tc; j++) {
+			sq_stats = &c->sq[j].stats;
 
 			s->tx_packets		+= sq_stats->packets;
 			s->tx_bytes		+= sq_stats->bytes;
@@ -402,8 +398,10 @@ static inline int mlx5e_get_wqe_mtt_sz(void)
 		     MLX5_UMR_MTT_ALIGNMENT);
 }
 
-static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, struct mlx5e_sq *sq,
-				       struct mlx5e_umr_wqe *wqe, u16 ix)
+static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
+				       struct mlx5e_icosq *sq,
+				       struct mlx5e_umr_wqe *wqe,
+				       u16 ix)
 {
 	struct mlx5_wqe_ctrl_seg      *cseg = &wqe->ctrl;
 	struct mlx5_wqe_umr_ctrl_seg *ucseg = &wqe->uctrl;
@@ -493,11 +491,10 @@ static void mlx5e_rq_free_mpwqe_info(struct mlx5e_rq *rq)
 	kfree(rq->mpwqe.info);
 }
 
-static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv,
+static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
 				 u64 npages, u8 page_shift,
 				 struct mlx5_core_mkey *umr_mkey)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
 	int inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
 	void *mkc;
 	u32 *in;
@@ -531,21 +528,20 @@ static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv,
 	return err;
 }
 
-static int mlx5e_create_rq_umr_mkey(struct mlx5e_rq *rq)
+static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq *rq)
 {
-	struct mlx5e_priv *priv = rq->priv;
-	u64 num_mtts = MLX5E_REQUIRED_MTTS(BIT(priv->params.log_rq_size));
+	u64 num_mtts = MLX5E_REQUIRED_MTTS(mlx5_wq_ll_get_size(&rq->wq));
 
-	return mlx5e_create_umr_mkey(priv, num_mtts, PAGE_SHIFT, &rq->umr_mkey);
+	return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey);
 }
 
-static int mlx5e_create_rq(struct mlx5e_channel *c,
-			   struct mlx5e_rq_param *param,
-			   struct mlx5e_rq *rq)
+static int mlx5e_alloc_rq(struct mlx5e_channel *c,
+			  struct mlx5e_params *params,
+			  struct mlx5e_rq_param *rqp,
+			  struct mlx5e_rq *rq)
 {
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
-	void *rqc = param->rqc;
+	struct mlx5_core_dev *mdev = c->mdev;
+	void *rqc = rqp->rqc;
 	void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq);
 	u32 byte_count;
 	u32 frag_sz;
@@ -554,9 +550,9 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 	int err;
 	int i;
 
-	param->wq.db_numa_node = cpu_to_node(c->cpu);
+	rqp->wq.db_numa_node = cpu_to_node(c->cpu);
 
-	err = mlx5_wq_ll_create(mdev, &param->wq, rqc_wq, &rq->wq,
+	err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->wq,
 				&rq->wq_ctrl);
 	if (err)
 		return err;
@@ -565,15 +561,15 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 
 	wq_sz = mlx5_wq_ll_get_size(&rq->wq);
 
-	rq->wq_type = priv->params.rq_wq_type;
+	rq->wq_type = params->rq_wq_type;
 	rq->pdev    = c->pdev;
 	rq->netdev  = c->netdev;
-	rq->tstamp  = &priv->tstamp;
+	rq->tstamp  = c->tstamp;
 	rq->channel = c;
 	rq->ix      = c->ix;
-	rq->priv    = c->priv;
+	rq->mdev    = mdev;
 
-	rq->xdp_prog = priv->xdp_prog ? bpf_prog_inc(priv->xdp_prog) : NULL;
+	rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
 	if (IS_ERR(rq->xdp_prog)) {
 		err = PTR_ERR(rq->xdp_prog);
 		rq->xdp_prog = NULL;
@@ -588,9 +584,9 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 		rq->rx_headroom = MLX5_RX_HEADROOM;
 	}
 
-	switch (priv->params.rq_wq_type) {
+	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		if (mlx5e_is_vf_vport_rep(priv)) {
+		if (mlx5e_is_vf_vport_rep(c->priv)) {
 			err = -EINVAL;
 			goto err_rq_wq_destroy;
 		}
@@ -599,13 +595,13 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 		rq->alloc_wqe = mlx5e_alloc_rx_mpwqe;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
 
-		rq->mpwqe_stride_sz = BIT(priv->params.mpwqe_log_stride_sz);
-		rq->mpwqe_num_strides = BIT(priv->params.mpwqe_log_num_strides);
+		rq->mpwqe_stride_sz = BIT(params->mpwqe_log_stride_sz);
+		rq->mpwqe_num_strides = BIT(params->mpwqe_log_num_strides);
 
 		rq->buff.wqe_sz = rq->mpwqe_stride_sz * rq->mpwqe_num_strides;
 		byte_count = rq->buff.wqe_sz;
 
-		err = mlx5e_create_rq_umr_mkey(rq);
+		err = mlx5e_create_rq_umr_mkey(mdev, rq);
 		if (err)
 			goto err_rq_wq_destroy;
 		rq->mkey_be = cpu_to_be32(rq->umr_mkey.key);
@@ -622,7 +618,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 			goto err_rq_wq_destroy;
 		}
 
-		if (mlx5e_is_vf_vport_rep(priv))
+		if (mlx5e_is_vf_vport_rep(c->priv))
 			rq->handle_rx_cqe = mlx5e_handle_rx_cqe_rep;
 		else
 			rq->handle_rx_cqe = mlx5e_handle_rx_cqe;
@@ -630,9 +626,9 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 		rq->alloc_wqe = mlx5e_alloc_rx_wqe;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
 
-		rq->buff.wqe_sz = (priv->params.lro_en) ?
-				priv->params.lro_wqe_sz :
-				MLX5E_SW2HW_MTU(priv->netdev->mtu);
+		rq->buff.wqe_sz = params->lro_en  ?
+				params->lro_wqe_sz :
+				MLX5E_SW2HW_MTU(c->netdev->mtu);
 		byte_count = rq->buff.wqe_sz;
 
 		/* calc the required page order */
@@ -656,8 +652,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 	}
 
 	INIT_WORK(&rq->am.work, mlx5e_rx_am_work);
-	rq->am.mode = priv->params.rx_cq_period_mode;
-
+	rq->am.mode = params->rx_cq_period_mode;
 	rq->page_cache.head = 0;
 	rq->page_cache.tail = 0;
 
@@ -674,7 +669,7 @@ err_rq_wq_destroy:
 	return err;
 }
 
-static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
+static void mlx5e_free_rq(struct mlx5e_rq *rq)
 {
 	int i;
 
@@ -684,7 +679,7 @@ static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		mlx5e_rq_free_mpwqe_info(rq);
-		mlx5_core_destroy_mkey(rq->priv->mdev, &rq->umr_mkey);
+		mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
 		kfree(rq->dma_info);
@@ -699,10 +694,10 @@ static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
 	mlx5_wq_destroy(&rq->wq_ctrl);
 }
 
-static int mlx5e_enable_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param)
+static int mlx5e_create_rq(struct mlx5e_rq *rq,
+			   struct mlx5e_rq_param *param)
 {
-	struct mlx5e_priv *priv = rq->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_core_dev *mdev = rq->mdev;
 
 	void *in;
 	void *rqc;
@@ -723,7 +718,6 @@ static int mlx5e_enable_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param)
 
 	MLX5_SET(rqc,  rqc, cqn,		rq->cq.mcq.cqn);
 	MLX5_SET(rqc,  rqc, state,		MLX5_RQC_STATE_RST);
-	MLX5_SET(rqc,  rqc, vsd, priv->params.vlan_strip_disable);
 	MLX5_SET(wq,   wq,  log_wq_pg_sz,	rq->wq_ctrl.buf.page_shift -
 						MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(wq, wq,  dbr_addr,		rq->wq_ctrl.db.dma);
@@ -742,8 +736,7 @@ static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state,
 				 int next_state)
 {
 	struct mlx5e_channel *c = rq->channel;
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_core_dev *mdev = c->mdev;
 
 	void *in;
 	void *rqc;
@@ -770,9 +763,7 @@ static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state,
 static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd)
 {
 	struct mlx5e_channel *c = rq->channel;
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
-
+	struct mlx5_core_dev *mdev = c->mdev;
 	void *in;
 	void *rqc;
 	int inlen;
@@ -798,25 +789,28 @@ static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd)
 	return err;
 }
 
-static void mlx5e_disable_rq(struct mlx5e_rq *rq)
+static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
 {
-	mlx5_core_destroy_rq(rq->priv->mdev, rq->rqn);
+	mlx5_core_destroy_rq(rq->mdev, rq->rqn);
 }
 
 static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq)
 {
 	unsigned long exp_time = jiffies + msecs_to_jiffies(20000);
 	struct mlx5e_channel *c = rq->channel;
-	struct mlx5e_priv *priv = c->priv;
+
 	struct mlx5_wq_ll *wq = &rq->wq;
+	u16 min_wqes = mlx5_min_rx_wqes(rq->wq_type, mlx5_wq_ll_get_size(wq));
 
 	while (time_before(jiffies, exp_time)) {
-		if (wq->cur_sz >= priv->params.min_rx_wqes)
+		if (wq->cur_sz >= min_wqes)
 			return 0;
 
 		msleep(20);
 	}
 
+	netdev_warn(c->netdev, "Failed to get min RX wqes on RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n",
+		    rq->rqn, wq->cur_sz, min_wqes);
 	return -ETIMEDOUT;
 }
 
@@ -842,83 +836,128 @@ static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 }
 
 static int mlx5e_open_rq(struct mlx5e_channel *c,
+			 struct mlx5e_params *params,
 			 struct mlx5e_rq_param *param,
 			 struct mlx5e_rq *rq)
 {
-	struct mlx5e_sq *sq = &c->icosq;
-	u16 pi = sq->pc & sq->wq.sz_m1;
 	int err;
 
-	err = mlx5e_create_rq(c, param, rq);
+	err = mlx5e_alloc_rq(c, params, param, rq);
 	if (err)
 		return err;
 
-	err = mlx5e_enable_rq(rq, param);
+	err = mlx5e_create_rq(rq, param);
 	if (err)
-		goto err_destroy_rq;
+		goto err_free_rq;
 
-	set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
 	err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY);
 	if (err)
-		goto err_disable_rq;
+		goto err_destroy_rq;
 
-	if (param->am_enabled)
+	if (params->rx_am_enabled)
 		set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
 
-	sq->db.ico_wqe[pi].opcode     = MLX5_OPCODE_NOP;
-	sq->db.ico_wqe[pi].num_wqebbs = 1;
-	mlx5e_send_nop(sq, true); /* trigger mlx5e_post_rx_wqes() */
-
 	return 0;
 
-err_disable_rq:
-	clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
-	mlx5e_disable_rq(rq);
 err_destroy_rq:
 	mlx5e_destroy_rq(rq);
+err_free_rq:
+	mlx5e_free_rq(rq);
 
 	return err;
 }
 
-static void mlx5e_close_rq(struct mlx5e_rq *rq)
+static void mlx5e_activate_rq(struct mlx5e_rq *rq)
+{
+	struct mlx5e_icosq *sq = &rq->channel->icosq;
+	u16 pi = sq->pc & sq->wq.sz_m1;
+	struct mlx5e_tx_wqe *nopwqe;
+
+	set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
+	sq->db.ico_wqe[pi].opcode     = MLX5_OPCODE_NOP;
+	sq->db.ico_wqe[pi].num_wqebbs = 1;
+	nopwqe = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc);
+	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &nopwqe->ctrl);
+}
+
+static void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
 {
 	clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
 	napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */
-	cancel_work_sync(&rq->am.work);
+}
 
-	mlx5e_disable_rq(rq);
-	mlx5e_free_rx_descs(rq);
+static void mlx5e_close_rq(struct mlx5e_rq *rq)
+{
+	cancel_work_sync(&rq->am.work);
 	mlx5e_destroy_rq(rq);
+	mlx5e_free_rx_descs(rq);
+	mlx5e_free_rq(rq);
 }
 
-static void mlx5e_free_sq_xdp_db(struct mlx5e_sq *sq)
+static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq)
 {
-	kfree(sq->db.xdp.di);
-	kfree(sq->db.xdp.wqe_info);
+	kfree(sq->db.di);
 }
 
-static int mlx5e_alloc_sq_xdp_db(struct mlx5e_sq *sq, int numa)
+static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 {
 	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
-	sq->db.xdp.di = kzalloc_node(sizeof(*sq->db.xdp.di) * wq_sz,
+	sq->db.di = kzalloc_node(sizeof(*sq->db.di) * wq_sz,
 				     GFP_KERNEL, numa);
-	sq->db.xdp.wqe_info = kzalloc_node(sizeof(*sq->db.xdp.wqe_info) * wq_sz,
-					   GFP_KERNEL, numa);
-	if (!sq->db.xdp.di || !sq->db.xdp.wqe_info) {
-		mlx5e_free_sq_xdp_db(sq);
+	if (!sq->db.di) {
+		mlx5e_free_xdpsq_db(sq);
 		return -ENOMEM;
 	}
 
 	return 0;
 }
 
-static void mlx5e_free_sq_ico_db(struct mlx5e_sq *sq)
+static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
+			     struct mlx5e_params *params,
+			     struct mlx5e_sq_param *param,
+			     struct mlx5e_xdpsq *sq)
+{
+	void *sqc_wq               = MLX5_ADDR_OF(sqc, param->sqc, wq);
+	struct mlx5_core_dev *mdev = c->mdev;
+	int err;
+
+	sq->pdev      = c->pdev;
+	sq->mkey_be   = c->mkey_be;
+	sq->channel   = c;
+	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
+	sq->min_inline_mode = params->tx_min_inline_mode;
+
+	param->wq.db_numa_node = cpu_to_node(c->cpu);
+	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
+	if (err)
+		return err;
+	sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
+
+	err = mlx5e_alloc_xdpsq_db(sq, cpu_to_node(c->cpu));
+	if (err)
+		goto err_sq_wq_destroy;
+
+	return 0;
+
+err_sq_wq_destroy:
+	mlx5_wq_destroy(&sq->wq_ctrl);
+
+	return err;
+}
+
+static void mlx5e_free_xdpsq(struct mlx5e_xdpsq *sq)
+{
+	mlx5e_free_xdpsq_db(sq);
+	mlx5_wq_destroy(&sq->wq_ctrl);
+}
+
+static void mlx5e_free_icosq_db(struct mlx5e_icosq *sq)
 {
 	kfree(sq->db.ico_wqe);
 }
 
-static int mlx5e_alloc_sq_ico_db(struct mlx5e_sq *sq, int numa)
+static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa)
 {
 	u8 wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
@@ -930,155 +969,131 @@ static int mlx5e_alloc_sq_ico_db(struct mlx5e_sq *sq, int numa)
 	return 0;
 }
 
-static void mlx5e_free_sq_txq_db(struct mlx5e_sq *sq)
+static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
+			     struct mlx5e_sq_param *param,
+			     struct mlx5e_icosq *sq)
 {
-	kfree(sq->db.txq.wqe_info);
-	kfree(sq->db.txq.dma_fifo);
-	kfree(sq->db.txq.skb);
-}
+	void *sqc_wq               = MLX5_ADDR_OF(sqc, param->sqc, wq);
+	struct mlx5_core_dev *mdev = c->mdev;
+	int err;
 
-static int mlx5e_alloc_sq_txq_db(struct mlx5e_sq *sq, int numa)
-{
-	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
-	int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
+	sq->pdev      = c->pdev;
+	sq->mkey_be   = c->mkey_be;
+	sq->channel   = c;
+	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 
-	sq->db.txq.skb = kzalloc_node(wq_sz * sizeof(*sq->db.txq.skb),
-				      GFP_KERNEL, numa);
-	sq->db.txq.dma_fifo = kzalloc_node(df_sz * sizeof(*sq->db.txq.dma_fifo),
-					   GFP_KERNEL, numa);
-	sq->db.txq.wqe_info = kzalloc_node(wq_sz * sizeof(*sq->db.txq.wqe_info),
-					   GFP_KERNEL, numa);
-	if (!sq->db.txq.skb || !sq->db.txq.dma_fifo || !sq->db.txq.wqe_info) {
-		mlx5e_free_sq_txq_db(sq);
-		return -ENOMEM;
-	}
+	param->wq.db_numa_node = cpu_to_node(c->cpu);
+	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
+	if (err)
+		return err;
+	sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
 
-	sq->dma_fifo_mask = df_sz - 1;
+	err = mlx5e_alloc_icosq_db(sq, cpu_to_node(c->cpu));
+	if (err)
+		goto err_sq_wq_destroy;
+
+	sq->edge = (sq->wq.sz_m1 + 1) - MLX5E_ICOSQ_MAX_WQEBBS;
 
 	return 0;
+
+err_sq_wq_destroy:
+	mlx5_wq_destroy(&sq->wq_ctrl);
+
+	return err;
 }
 
-static void mlx5e_free_sq_db(struct mlx5e_sq *sq)
+static void mlx5e_free_icosq(struct mlx5e_icosq *sq)
 {
-	switch (sq->type) {
-	case MLX5E_SQ_TXQ:
-		mlx5e_free_sq_txq_db(sq);
-		break;
-	case MLX5E_SQ_ICO:
-		mlx5e_free_sq_ico_db(sq);
-		break;
-	case MLX5E_SQ_XDP:
-		mlx5e_free_sq_xdp_db(sq);
-		break;
-	}
+	mlx5e_free_icosq_db(sq);
+	mlx5_wq_destroy(&sq->wq_ctrl);
 }
 
-static int mlx5e_alloc_sq_db(struct mlx5e_sq *sq, int numa)
+static void mlx5e_free_txqsq_db(struct mlx5e_txqsq *sq)
 {
-	switch (sq->type) {
-	case MLX5E_SQ_TXQ:
-		return mlx5e_alloc_sq_txq_db(sq, numa);
-	case MLX5E_SQ_ICO:
-		return mlx5e_alloc_sq_ico_db(sq, numa);
-	case MLX5E_SQ_XDP:
-		return mlx5e_alloc_sq_xdp_db(sq, numa);
-	}
-
-	return 0;
+	kfree(sq->db.wqe_info);
+	kfree(sq->db.dma_fifo);
+	kfree(sq->db.skb);
 }
 
-static int mlx5e_sq_get_max_wqebbs(u8 sq_type)
+static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
 {
-	switch (sq_type) {
-	case MLX5E_SQ_ICO:
-		return MLX5E_ICOSQ_MAX_WQEBBS;
-	case MLX5E_SQ_XDP:
-		return MLX5E_XDP_TX_WQEBBS;
+	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
+	int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
+
+	sq->db.skb = kzalloc_node(wq_sz * sizeof(*sq->db.skb),
+				      GFP_KERNEL, numa);
+	sq->db.dma_fifo = kzalloc_node(df_sz * sizeof(*sq->db.dma_fifo),
+					   GFP_KERNEL, numa);
+	sq->db.wqe_info = kzalloc_node(wq_sz * sizeof(*sq->db.wqe_info),
+					   GFP_KERNEL, numa);
+	if (!sq->db.skb || !sq->db.dma_fifo || !sq->db.wqe_info) {
+		mlx5e_free_txqsq_db(sq);
+		return -ENOMEM;
 	}
-	return MLX5_SEND_WQE_MAX_WQEBBS;
+
+	sq->dma_fifo_mask = df_sz - 1;
+
+	return 0;
 }
 
-static int mlx5e_create_sq(struct mlx5e_channel *c,
-			   int tc,
-			   struct mlx5e_sq_param *param,
-			   struct mlx5e_sq *sq)
+static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
+			     int txq_ix,
+			     struct mlx5e_params *params,
+			     struct mlx5e_sq_param *param,
+			     struct mlx5e_txqsq *sq)
 {
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
-
-	void *sqc = param->sqc;
-	void *sqc_wq = MLX5_ADDR_OF(sqc, sqc, wq);
+	void *sqc_wq               = MLX5_ADDR_OF(sqc, param->sqc, wq);
+	struct mlx5_core_dev *mdev = c->mdev;
 	int err;
 
-	sq->type      = param->type;
 	sq->pdev      = c->pdev;
-	sq->tstamp    = &priv->tstamp;
+	sq->tstamp    = c->tstamp;
 	sq->mkey_be   = c->mkey_be;
 	sq->channel   = c;
-	sq->tc        = tc;
+	sq->txq_ix    = txq_ix;
+	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
+	sq->max_inline      = params->tx_max_inline;
+	sq->min_inline_mode = params->tx_min_inline_mode;
 
-	err = mlx5_alloc_bfreg(mdev, &sq->bfreg, MLX5_CAP_GEN(mdev, bf), false);
-	if (err)
-		return err;
-
-	sq->uar_map = sq->bfreg.map;
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
-
-	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq,
-				 &sq->wq_ctrl);
+	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
 	if (err)
-		goto err_unmap_free_uar;
-
-	sq->wq.db       = &sq->wq.db[MLX5_SND_DBR];
-	if (sq->bfreg.wc)
-		set_bit(MLX5E_SQ_STATE_BF_ENABLE, &sq->state);
-
-	sq->bf_buf_size = (1 << MLX5_CAP_GEN(mdev, log_bf_reg_size)) / 2;
-	sq->max_inline  = param->max_inline;
-	sq->min_inline_mode = param->min_inline_mode;
+		return err;
+	sq->wq.db    = &sq->wq.db[MLX5_SND_DBR];
 
-	err = mlx5e_alloc_sq_db(sq, cpu_to_node(c->cpu));
+	err = mlx5e_alloc_txqsq_db(sq, cpu_to_node(c->cpu));
 	if (err)
 		goto err_sq_wq_destroy;
 
-	if (sq->type == MLX5E_SQ_TXQ) {
-		int txq_ix;
-
-		txq_ix = c->ix + tc * priv->params.num_channels;
-		sq->txq = netdev_get_tx_queue(priv->netdev, txq_ix);
-		priv->txq_to_sq_map[txq_ix] = sq;
-	}
-
-	sq->edge = (sq->wq.sz_m1 + 1) - mlx5e_sq_get_max_wqebbs(sq->type);
-	sq->bf_budget = MLX5E_SQ_BF_BUDGET;
+	sq->edge = (sq->wq.sz_m1 + 1) - MLX5_SEND_WQE_MAX_WQEBBS;
 
 	return 0;
 
 err_sq_wq_destroy:
 	mlx5_wq_destroy(&sq->wq_ctrl);
 
-err_unmap_free_uar:
-	mlx5_free_bfreg(mdev, &sq->bfreg);
-
 	return err;
 }
 
-static void mlx5e_destroy_sq(struct mlx5e_sq *sq)
+static void mlx5e_free_txqsq(struct mlx5e_txqsq *sq)
 {
-	struct mlx5e_channel *c = sq->channel;
-	struct mlx5e_priv *priv = c->priv;
-
-	mlx5e_free_sq_db(sq);
+	mlx5e_free_txqsq_db(sq);
 	mlx5_wq_destroy(&sq->wq_ctrl);
-	mlx5_free_bfreg(priv->mdev, &sq->bfreg);
 }
 
-static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param)
-{
-	struct mlx5e_channel *c = sq->channel;
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
+struct mlx5e_create_sq_param {
+	struct mlx5_wq_ctrl        *wq_ctrl;
+	u32                         cqn;
+	u32                         tisn;
+	u8                          tis_lst_sz;
+	u8                          min_inline_mode;
+};
 
+static int mlx5e_create_sq(struct mlx5_core_dev *mdev,
+			   struct mlx5e_sq_param *param,
+			   struct mlx5e_create_sq_param *csp,
+			   u32 *sqn)
+{
 	void *in;
 	void *sqc;
 	void *wq;
@@ -1086,7 +1101,7 @@ static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param)
 	int err;
 
 	inlen = MLX5_ST_SZ_BYTES(create_sq_in) +
-		sizeof(u64) * sq->wq_ctrl.buf.npages;
+		sizeof(u64) * csp->wq_ctrl->buf.npages;
 	in = mlx5_vzalloc(inlen);
 	if (!in)
 		return -ENOMEM;
@@ -1095,40 +1110,40 @@ static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param)
 	wq = MLX5_ADDR_OF(sqc, sqc, wq);
 
 	memcpy(sqc, param->sqc, sizeof(param->sqc));
-
-	MLX5_SET(sqc,  sqc, tis_num_0, param->type == MLX5E_SQ_ICO ?
-				       0 : priv->tisn[sq->tc]);
-	MLX5_SET(sqc,  sqc, cqn,		sq->cq.mcq.cqn);
+	MLX5_SET(sqc,  sqc, tis_lst_sz, csp->tis_lst_sz);
+	MLX5_SET(sqc,  sqc, tis_num_0, csp->tisn);
+	MLX5_SET(sqc,  sqc, cqn, csp->cqn);
 
 	if (MLX5_CAP_ETH(mdev, wqe_inline_mode) == MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
-		MLX5_SET(sqc,  sqc, min_wqe_inline_mode, sq->min_inline_mode);
+		MLX5_SET(sqc,  sqc, min_wqe_inline_mode, csp->min_inline_mode);
 
-	MLX5_SET(sqc,  sqc, state,		MLX5_SQC_STATE_RST);
-	MLX5_SET(sqc,  sqc, tis_lst_sz, param->type == MLX5E_SQ_ICO ? 0 : 1);
+	MLX5_SET(sqc,  sqc, state, MLX5_SQC_STATE_RST);
 
 	MLX5_SET(wq,   wq, wq_type,       MLX5_WQ_TYPE_CYCLIC);
-	MLX5_SET(wq,   wq, uar_page,      sq->bfreg.index);
-	MLX5_SET(wq,   wq, log_wq_pg_sz,  sq->wq_ctrl.buf.page_shift -
+	MLX5_SET(wq,   wq, uar_page,      mdev->mlx5e_res.bfreg.index);
+	MLX5_SET(wq,   wq, log_wq_pg_sz,  csp->wq_ctrl->buf.page_shift -
 					  MLX5_ADAPTER_PAGE_SHIFT);
-	MLX5_SET64(wq, wq, dbr_addr,      sq->wq_ctrl.db.dma);
+	MLX5_SET64(wq, wq, dbr_addr,      csp->wq_ctrl->db.dma);
 
-	mlx5_fill_page_array(&sq->wq_ctrl.buf,
-			     (__be64 *)MLX5_ADDR_OF(wq, wq, pas));
+	mlx5_fill_page_array(&csp->wq_ctrl->buf, (__be64 *)MLX5_ADDR_OF(wq, wq, pas));
 
-	err = mlx5_core_create_sq(mdev, in, inlen, &sq->sqn);
+	err = mlx5_core_create_sq(mdev, in, inlen, sqn);
 
 	kvfree(in);
 
 	return err;
 }
 
-static int mlx5e_modify_sq(struct mlx5e_sq *sq, int curr_state,
-			   int next_state, bool update_rl, int rl_index)
-{
-	struct mlx5e_channel *c = sq->channel;
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
+struct mlx5e_modify_sq_param {
+	int curr_state;
+	int next_state;
+	bool rl_update;
+	int rl_index;
+};
 
+static int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
+			   struct mlx5e_modify_sq_param *p)
+{
 	void *in;
 	void *sqc;
 	int inlen;
@@ -1141,68 +1156,94 @@ static int mlx5e_modify_sq(struct mlx5e_sq *sq, int curr_state,
 
 	sqc = MLX5_ADDR_OF(modify_sq_in, in, ctx);
 
-	MLX5_SET(modify_sq_in, in, sq_state, curr_state);
-	MLX5_SET(sqc, sqc, state, next_state);
-	if (update_rl && next_state == MLX5_SQC_STATE_RDY) {
+	MLX5_SET(modify_sq_in, in, sq_state, p->curr_state);
+	MLX5_SET(sqc, sqc, state, p->next_state);
+	if (p->rl_update && p->next_state == MLX5_SQC_STATE_RDY) {
 		MLX5_SET64(modify_sq_in, in, modify_bitmask, 1);
-		MLX5_SET(sqc,  sqc, packet_pacing_rate_limit_index, rl_index);
+		MLX5_SET(sqc,  sqc, packet_pacing_rate_limit_index, p->rl_index);
 	}
 
-	err = mlx5_core_modify_sq(mdev, sq->sqn, in, inlen);
+	err = mlx5_core_modify_sq(mdev, sqn, in, inlen);
 
 	kvfree(in);
 
 	return err;
 }
 
-static void mlx5e_disable_sq(struct mlx5e_sq *sq)
+static void mlx5e_destroy_sq(struct mlx5_core_dev *mdev, u32 sqn)
 {
-	struct mlx5e_channel *c = sq->channel;
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
-
-	mlx5_core_destroy_sq(mdev, sq->sqn);
-	if (sq->rate_limit)
-		mlx5_rl_remove_rate(mdev, sq->rate_limit);
+	mlx5_core_destroy_sq(mdev, sqn);
 }
 
-static int mlx5e_open_sq(struct mlx5e_channel *c,
-			 int tc,
-			 struct mlx5e_sq_param *param,
-			 struct mlx5e_sq *sq)
+static int mlx5e_create_sq_rdy(struct mlx5_core_dev *mdev,
+			       struct mlx5e_sq_param *param,
+			       struct mlx5e_create_sq_param *csp,
+			       u32 *sqn)
 {
+	struct mlx5e_modify_sq_param msp = {0};
 	int err;
 
-	err = mlx5e_create_sq(c, tc, param, sq);
+	err = mlx5e_create_sq(mdev, param, csp, sqn);
 	if (err)
 		return err;
 
-	err = mlx5e_enable_sq(sq, param);
+	msp.curr_state = MLX5_SQC_STATE_RST;
+	msp.next_state = MLX5_SQC_STATE_RDY;
+	err = mlx5e_modify_sq(mdev, *sqn, &msp);
 	if (err)
-		goto err_destroy_sq;
+		mlx5e_destroy_sq(mdev, *sqn);
 
-	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-	err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RST, MLX5_SQC_STATE_RDY,
-			      false, 0);
+	return err;
+}
+
+static int mlx5e_set_sq_maxrate(struct net_device *dev,
+				struct mlx5e_txqsq *sq, u32 rate);
+
+static int mlx5e_open_txqsq(struct mlx5e_channel *c,
+			    u32 tisn,
+			    int txq_ix,
+			    struct mlx5e_params *params,
+			    struct mlx5e_sq_param *param,
+			    struct mlx5e_txqsq *sq)
+{
+	struct mlx5e_create_sq_param csp = {};
+	u32 tx_rate;
+	int err;
+
+	err = mlx5e_alloc_txqsq(c, txq_ix, params, param, sq);
 	if (err)
-		goto err_disable_sq;
+		return err;
 
-	if (sq->txq) {
-		netdev_tx_reset_queue(sq->txq);
-		netif_tx_start_queue(sq->txq);
-	}
+	csp.tisn            = tisn;
+	csp.tis_lst_sz      = 1;
+	csp.cqn             = sq->cq.mcq.cqn;
+	csp.wq_ctrl         = &sq->wq_ctrl;
+	csp.min_inline_mode = sq->min_inline_mode;
+	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
+	if (err)
+		goto err_free_txqsq;
+
+	tx_rate = c->priv->tx_rates[sq->txq_ix];
+	if (tx_rate)
+		mlx5e_set_sq_maxrate(c->netdev, sq, tx_rate);
 
 	return 0;
 
-err_disable_sq:
+err_free_txqsq:
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-	mlx5e_disable_sq(sq);
-err_destroy_sq:
-	mlx5e_destroy_sq(sq);
+	mlx5e_free_txqsq(sq);
 
 	return err;
 }
 
+static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
+{
+	sq->txq = netdev_get_tx_queue(sq->channel->netdev, sq->txq_ix);
+	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+	netdev_tx_reset_queue(sq->txq);
+	netif_tx_start_queue(sq->txq);
+}
+
 static inline void netif_tx_disable_queue(struct netdev_queue *txq)
 {
 	__netif_tx_lock_bh(txq);
@@ -1210,33 +1251,148 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq)
 	__netif_tx_unlock_bh(txq);
 }
 
-static void mlx5e_close_sq(struct mlx5e_sq *sq)
+static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq)
 {
+	struct mlx5e_channel *c = sq->channel;
+
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 	/* prevent netif_tx_wake_queue */
-	napi_synchronize(&sq->channel->napi);
+	napi_synchronize(&c->napi);
 
-	if (sq->txq) {
-		netif_tx_disable_queue(sq->txq);
+	netif_tx_disable_queue(sq->txq);
 
-		/* last doorbell out, godspeed .. */
-		if (mlx5e_sq_has_room_for(sq, 1)) {
-			sq->db.txq.skb[(sq->pc & sq->wq.sz_m1)] = NULL;
-			mlx5e_send_nop(sq, true);
-		}
+	/* last doorbell out, godspeed .. */
+	if (mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1)) {
+		struct mlx5e_tx_wqe *nop;
+
+		sq->db.skb[(sq->pc & sq->wq.sz_m1)] = NULL;
+		nop = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc);
+		mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &nop->ctrl);
 	}
+}
+
+static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq)
+{
+	struct mlx5e_channel *c = sq->channel;
+	struct mlx5_core_dev *mdev = c->mdev;
 
-	mlx5e_disable_sq(sq);
-	mlx5e_free_sq_descs(sq);
-	mlx5e_destroy_sq(sq);
+	mlx5e_destroy_sq(mdev, sq->sqn);
+	if (sq->rate_limit)
+		mlx5_rl_remove_rate(mdev, sq->rate_limit);
+	mlx5e_free_txqsq_descs(sq);
+	mlx5e_free_txqsq(sq);
 }
 
-static int mlx5e_create_cq(struct mlx5e_channel *c,
-			   struct mlx5e_cq_param *param,
-			   struct mlx5e_cq *cq)
+static int mlx5e_open_icosq(struct mlx5e_channel *c,
+			    struct mlx5e_params *params,
+			    struct mlx5e_sq_param *param,
+			    struct mlx5e_icosq *sq)
 {
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_create_sq_param csp = {};
+	int err;
+
+	err = mlx5e_alloc_icosq(c, param, sq);
+	if (err)
+		return err;
+
+	csp.cqn             = sq->cq.mcq.cqn;
+	csp.wq_ctrl         = &sq->wq_ctrl;
+	csp.min_inline_mode = params->tx_min_inline_mode;
+	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
+	if (err)
+		goto err_free_icosq;
+
+	return 0;
+
+err_free_icosq:
+	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+	mlx5e_free_icosq(sq);
+
+	return err;
+}
+
+static void mlx5e_close_icosq(struct mlx5e_icosq *sq)
+{
+	struct mlx5e_channel *c = sq->channel;
+
+	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+	napi_synchronize(&c->napi);
+
+	mlx5e_destroy_sq(c->mdev, sq->sqn);
+	mlx5e_free_icosq(sq);
+}
+
+static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
+			    struct mlx5e_params *params,
+			    struct mlx5e_sq_param *param,
+			    struct mlx5e_xdpsq *sq)
+{
+	unsigned int ds_cnt = MLX5E_XDP_TX_DS_COUNT;
+	struct mlx5e_create_sq_param csp = {};
+	unsigned int inline_hdr_sz = 0;
+	int err;
+	int i;
+
+	err = mlx5e_alloc_xdpsq(c, params, param, sq);
+	if (err)
+		return err;
+
+	csp.tis_lst_sz      = 1;
+	csp.tisn            = c->priv->tisn[0]; /* tc = 0 */
+	csp.cqn             = sq->cq.mcq.cqn;
+	csp.wq_ctrl         = &sq->wq_ctrl;
+	csp.min_inline_mode = sq->min_inline_mode;
+	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
+	if (err)
+		goto err_free_xdpsq;
+
+	if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
+		inline_hdr_sz = MLX5E_XDP_MIN_INLINE;
+		ds_cnt++;
+	}
+
+	/* Pre initialize fixed WQE fields */
+	for (i = 0; i < mlx5_wq_cyc_get_size(&sq->wq); i++) {
+		struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(&sq->wq, i);
+		struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
+		struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
+		struct mlx5_wqe_data_seg *dseg;
+
+		cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
+		eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
+
+		dseg = (struct mlx5_wqe_data_seg *)cseg + (ds_cnt - 1);
+		dseg->lkey = sq->mkey_be;
+	}
+
+	return 0;
+
+err_free_xdpsq:
+	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+	mlx5e_free_xdpsq(sq);
+
+	return err;
+}
+
+static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq)
+{
+	struct mlx5e_channel *c = sq->channel;
+
+	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+	napi_synchronize(&c->napi);
+
+	mlx5e_destroy_sq(c->mdev, sq->sqn);
+	mlx5e_free_xdpsq_descs(sq);
+	mlx5e_free_xdpsq(sq);
+}
+
+static int mlx5e_alloc_cq(struct mlx5e_channel *c,
+			  struct mlx5e_cq_param *param,
+			  struct mlx5e_cq *cq)
+{
+	struct mlx5_core_dev *mdev = c->mdev;
 	struct mlx5_core_cq *mcq = &cq->mcq;
 	int eqn_not_used;
 	unsigned int irqn;
@@ -1273,20 +1429,19 @@ static int mlx5e_create_cq(struct mlx5e_channel *c,
 	}
 
 	cq->channel = c;
-	cq->priv = priv;
+	cq->mdev = mdev;
 
 	return 0;
 }
 
-static void mlx5e_destroy_cq(struct mlx5e_cq *cq)
+static void mlx5e_free_cq(struct mlx5e_cq *cq)
 {
 	mlx5_cqwq_destroy(&cq->wq_ctrl);
 }
 
-static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
+static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 {
-	struct mlx5e_priv *priv = cq->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_core_dev *mdev = cq->mdev;
 	struct mlx5_core_cq *mcq = &cq->mcq;
 
 	void *in;
@@ -1330,47 +1485,41 @@ static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 	return 0;
 }
 
-static void mlx5e_disable_cq(struct mlx5e_cq *cq)
+static void mlx5e_destroy_cq(struct mlx5e_cq *cq)
 {
-	struct mlx5e_priv *priv = cq->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
-
-	mlx5_core_destroy_cq(mdev, &cq->mcq);
+	mlx5_core_destroy_cq(cq->mdev, &cq->mcq);
 }
 
 static int mlx5e_open_cq(struct mlx5e_channel *c,
+			 struct mlx5e_cq_moder moder,
 			 struct mlx5e_cq_param *param,
-			 struct mlx5e_cq *cq,
-			 struct mlx5e_cq_moder moderation)
+			 struct mlx5e_cq *cq)
 {
+	struct mlx5_core_dev *mdev = c->mdev;
 	int err;
-	struct mlx5e_priv *priv = c->priv;
-	struct mlx5_core_dev *mdev = priv->mdev;
 
-	err = mlx5e_create_cq(c, param, cq);
+	err = mlx5e_alloc_cq(c, param, cq);
 	if (err)
 		return err;
 
-	err = mlx5e_enable_cq(cq, param);
+	err = mlx5e_create_cq(cq, param);
 	if (err)
-		goto err_destroy_cq;
+		goto err_free_cq;
 
 	if (MLX5_CAP_GEN(mdev, cq_moderation))
-		mlx5_core_modify_cq_moderation(mdev, &cq->mcq,
-					       moderation.usec,
-					       moderation.pkts);
+		mlx5_core_modify_cq_moderation(mdev, &cq->mcq, moder.usec, moder.pkts);
 	return 0;
 
-err_destroy_cq:
-	mlx5e_destroy_cq(cq);
+err_free_cq:
+	mlx5e_free_cq(cq);
 
 	return err;
 }
 
 static void mlx5e_close_cq(struct mlx5e_cq *cq)
 {
-	mlx5e_disable_cq(cq);
 	mlx5e_destroy_cq(cq);
+	mlx5e_free_cq(cq);
 }
 
 static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
@@ -1379,15 +1528,15 @@ static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
 }
 
 static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
+			     struct mlx5e_params *params,
 			     struct mlx5e_channel_param *cparam)
 {
-	struct mlx5e_priv *priv = c->priv;
 	int err;
 	int tc;
 
 	for (tc = 0; tc < c->num_tc; tc++) {
-		err = mlx5e_open_cq(c, &cparam->tx_cq, &c->sq[tc].cq,
-				    priv->params.tx_cq_moderation);
+		err = mlx5e_open_cq(c, params->tx_cq_moderation,
+				    &cparam->tx_cq, &c->sq[tc].cq);
 		if (err)
 			goto err_close_tx_cqs;
 	}
@@ -1410,13 +1559,17 @@ static void mlx5e_close_tx_cqs(struct mlx5e_channel *c)
 }
 
 static int mlx5e_open_sqs(struct mlx5e_channel *c,
+			  struct mlx5e_params *params,
 			  struct mlx5e_channel_param *cparam)
 {
 	int err;
 	int tc;
 
-	for (tc = 0; tc < c->num_tc; tc++) {
-		err = mlx5e_open_sq(c, tc, &cparam->sq, &c->sq[tc]);
+	for (tc = 0; tc < params->num_tc; tc++) {
+		int txq_ix = c->ix + tc * params->num_channels;
+
+		err = mlx5e_open_txqsq(c, c->priv->tisn[tc], txq_ix,
+				       params, &cparam->sq, &c->sq[tc]);
 		if (err)
 			goto err_close_sqs;
 	}
@@ -1425,7 +1578,7 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c,
 
 err_close_sqs:
 	for (tc--; tc >= 0; tc--)
-		mlx5e_close_sq(&c->sq[tc]);
+		mlx5e_close_txqsq(&c->sq[tc]);
 
 	return err;
 }
@@ -1435,23 +1588,15 @@ static void mlx5e_close_sqs(struct mlx5e_channel *c)
 	int tc;
 
 	for (tc = 0; tc < c->num_tc; tc++)
-		mlx5e_close_sq(&c->sq[tc]);
-}
-
-static void mlx5e_build_channeltc_to_txq_map(struct mlx5e_priv *priv, int ix)
-{
-	int i;
-
-	for (i = 0; i < priv->profile->max_tc; i++)
-		priv->channeltc_to_txq_map[ix][i] =
-			ix + i * priv->params.num_channels;
+		mlx5e_close_txqsq(&c->sq[tc]);
 }
 
 static int mlx5e_set_sq_maxrate(struct net_device *dev,
-				struct mlx5e_sq *sq, u32 rate)
+				struct mlx5e_txqsq *sq, u32 rate)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_modify_sq_param msp = {0};
 	u16 rl_index = 0;
 	int err;
 
@@ -1474,8 +1619,11 @@ static int mlx5e_set_sq_maxrate(struct net_device *dev,
 		}
 	}
 
-	err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY,
-			      MLX5_SQC_STATE_RDY, true, rl_index);
+	msp.curr_state = MLX5_SQC_STATE_RDY;
+	msp.next_state = MLX5_SQC_STATE_RDY;
+	msp.rl_index   = rl_index;
+	msp.rl_update  = true;
+	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
 	if (err) {
 		netdev_err(dev, "Failed configuring rate %u: %d\n",
 			   rate, err);
@@ -1493,7 +1641,7 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5e_sq *sq = priv->txq_to_sq_map[index];
+	struct mlx5e_txqsq *sq = priv->txq2sq[index];
 	int err = 0;
 
 	if (!mlx5_rl_is_supported(mdev)) {
@@ -1529,105 +1677,86 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
 }
 
 static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
+			      struct mlx5e_params *params,
 			      struct mlx5e_channel_param *cparam,
 			      struct mlx5e_channel **cp)
 {
-	struct mlx5e_cq_moder icosq_cq_moder = {0, 0};
+	struct mlx5e_cq_moder icocq_moder = {0, 0};
 	struct net_device *netdev = priv->netdev;
-	struct mlx5e_cq_moder rx_cq_profile;
 	int cpu = mlx5e_get_cpu(priv, ix);
 	struct mlx5e_channel *c;
-	struct mlx5e_sq *sq;
 	int err;
-	int i;
 
 	c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
 	if (!c)
 		return -ENOMEM;
 
 	c->priv     = priv;
+	c->mdev     = priv->mdev;
+	c->tstamp   = &priv->tstamp;
 	c->ix       = ix;
 	c->cpu      = cpu;
 	c->pdev     = &priv->mdev->pdev->dev;
 	c->netdev   = priv->netdev;
 	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
-	c->num_tc   = priv->params.num_tc;
-	c->xdp      = !!priv->xdp_prog;
-
-	if (priv->params.rx_am_enabled)
-		rx_cq_profile = mlx5e_am_get_def_profile(priv->params.rx_cq_period_mode);
-	else
-		rx_cq_profile = priv->params.rx_cq_moderation;
-
-	mlx5e_build_channeltc_to_txq_map(priv, ix);
+	c->num_tc   = params->num_tc;
+	c->xdp      = !!params->xdp_prog;
 
 	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
 
-	err = mlx5e_open_cq(c, &cparam->icosq_cq, &c->icosq.cq, icosq_cq_moder);
+	err = mlx5e_open_cq(c, icocq_moder, &cparam->icosq_cq, &c->icosq.cq);
 	if (err)
 		goto err_napi_del;
 
-	err = mlx5e_open_tx_cqs(c, cparam);
+	err = mlx5e_open_tx_cqs(c, params, cparam);
 	if (err)
 		goto err_close_icosq_cq;
 
-	err = mlx5e_open_cq(c, &cparam->rx_cq, &c->rq.cq,
-			    rx_cq_profile);
+	err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rx_cq, &c->rq.cq);
 	if (err)
 		goto err_close_tx_cqs;
 
 	/* XDP SQ CQ params are same as normal TXQ sq CQ params */
-	err = c->xdp ? mlx5e_open_cq(c, &cparam->tx_cq, &c->xdp_sq.cq,
-				     priv->params.tx_cq_moderation) : 0;
+	err = c->xdp ? mlx5e_open_cq(c, params->tx_cq_moderation,
+				     &cparam->tx_cq, &c->rq.xdpsq.cq) : 0;
 	if (err)
 		goto err_close_rx_cq;
 
 	napi_enable(&c->napi);
 
-	err = mlx5e_open_sq(c, 0, &cparam->icosq, &c->icosq);
+	err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq);
 	if (err)
 		goto err_disable_napi;
 
-	err = mlx5e_open_sqs(c, cparam);
+	err = mlx5e_open_sqs(c, params, cparam);
 	if (err)
 		goto err_close_icosq;
 
-	for (i = 0; i < priv->params.num_tc; i++) {
-		u32 txq_ix = priv->channeltc_to_txq_map[ix][i];
-
-		if (priv->tx_rates[txq_ix]) {
-			sq = priv->txq_to_sq_map[txq_ix];
-			mlx5e_set_sq_maxrate(priv->netdev, sq,
-					     priv->tx_rates[txq_ix]);
-		}
-	}
-
-	err = c->xdp ? mlx5e_open_sq(c, 0, &cparam->xdp_sq, &c->xdp_sq) : 0;
+	err = c->xdp ? mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->rq.xdpsq) : 0;
 	if (err)
 		goto err_close_sqs;
 
-	err = mlx5e_open_rq(c, &cparam->rq, &c->rq);
+	err = mlx5e_open_rq(c, params, &cparam->rq, &c->rq);
 	if (err)
 		goto err_close_xdp_sq;
 
-	netif_set_xps_queue(netdev, get_cpu_mask(c->cpu), ix);
 	*cp = c;
 
 	return 0;
 err_close_xdp_sq:
 	if (c->xdp)
-		mlx5e_close_sq(&c->xdp_sq);
+		mlx5e_close_xdpsq(&c->rq.xdpsq);
 
 err_close_sqs:
 	mlx5e_close_sqs(c);
 
 err_close_icosq:
-	mlx5e_close_sq(&c->icosq);
+	mlx5e_close_icosq(&c->icosq);
 
 err_disable_napi:
 	napi_disable(&c->napi);
 	if (c->xdp)
-		mlx5e_close_cq(&c->xdp_sq.cq);
+		mlx5e_close_cq(&c->rq.xdpsq.cq);
 
 err_close_rx_cq:
 	mlx5e_close_cq(&c->rq.cq);
@@ -1645,16 +1774,35 @@ err_napi_del:
 	return err;
 }
 
+static void mlx5e_activate_channel(struct mlx5e_channel *c)
+{
+	int tc;
+
+	for (tc = 0; tc < c->num_tc; tc++)
+		mlx5e_activate_txqsq(&c->sq[tc]);
+	mlx5e_activate_rq(&c->rq);
+	netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix);
+}
+
+static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
+{
+	int tc;
+
+	mlx5e_deactivate_rq(&c->rq);
+	for (tc = 0; tc < c->num_tc; tc++)
+		mlx5e_deactivate_txqsq(&c->sq[tc]);
+}
+
 static void mlx5e_close_channel(struct mlx5e_channel *c)
 {
 	mlx5e_close_rq(&c->rq);
 	if (c->xdp)
-		mlx5e_close_sq(&c->xdp_sq);
+		mlx5e_close_xdpsq(&c->rq.xdpsq);
 	mlx5e_close_sqs(c);
-	mlx5e_close_sq(&c->icosq);
+	mlx5e_close_icosq(&c->icosq);
 	napi_disable(&c->napi);
 	if (c->xdp)
-		mlx5e_close_cq(&c->xdp_sq.cq);
+		mlx5e_close_cq(&c->rq.xdpsq.cq);
 	mlx5e_close_cq(&c->rq.cq);
 	mlx5e_close_tx_cqs(c);
 	mlx5e_close_cq(&c->icosq.cq);
@@ -1664,17 +1812,16 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
 }
 
 static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
+				 struct mlx5e_params *params,
 				 struct mlx5e_rq_param *param)
 {
 	void *rqc = param->rqc;
 	void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
 
-	switch (priv->params.rq_wq_type) {
+	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		MLX5_SET(wq, wq, log_wqe_num_of_strides,
-			 priv->params.mpwqe_log_num_strides - 9);
-		MLX5_SET(wq, wq, log_wqe_stride_size,
-			 priv->params.mpwqe_log_stride_sz - 6);
+		MLX5_SET(wq, wq, log_wqe_num_of_strides, params->mpwqe_log_num_strides - 9);
+		MLX5_SET(wq, wq, log_wqe_stride_size, params->mpwqe_log_stride_sz - 6);
 		MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
@@ -1683,14 +1830,13 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 
 	MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
 	MLX5_SET(wq, wq, log_wq_stride,    ilog2(sizeof(struct mlx5e_rx_wqe)));
-	MLX5_SET(wq, wq, log_wq_sz,        priv->params.log_rq_size);
+	MLX5_SET(wq, wq, log_wq_sz,        params->log_rq_size);
 	MLX5_SET(wq, wq, pd,               priv->mdev->mlx5e_res.pdn);
 	MLX5_SET(rqc, rqc, counter_set_id, priv->q_counter);
+	MLX5_SET(rqc, rqc, vsd,            params->vlan_strip_disable);
 
 	param->wq.buf_numa_node = dev_to_node(&priv->mdev->pdev->dev);
 	param->wq.linear = 1;
-
-	param->am_enabled = priv->params.rx_am_enabled;
 }
 
 static void mlx5e_build_drop_rq_param(struct mlx5e_rq_param *param)
@@ -1715,17 +1861,14 @@ static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
 }
 
 static void mlx5e_build_sq_param(struct mlx5e_priv *priv,
+				 struct mlx5e_params *params,
 				 struct mlx5e_sq_param *param)
 {
 	void *sqc = param->sqc;
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
 
 	mlx5e_build_sq_param_common(priv, param);
-	MLX5_SET(wq, wq, log_wq_sz,     priv->params.log_sq_size);
-
-	param->max_inline = priv->params.tx_max_inline;
-	param->min_inline_mode = priv->params.tx_min_inline_mode;
-	param->type = MLX5E_SQ_TXQ;
+	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
 }
 
 static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv,
@@ -1737,37 +1880,40 @@ static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv,
 }
 
 static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
+				    struct mlx5e_params *params,
 				    struct mlx5e_cq_param *param)
 {
 	void *cqc = param->cqc;
 	u8 log_cq_size;
 
-	switch (priv->params.rq_wq_type) {
+	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		log_cq_size = priv->params.log_rq_size +
-			priv->params.mpwqe_log_num_strides;
+		log_cq_size = params->log_rq_size + params->mpwqe_log_num_strides;
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
-		log_cq_size = priv->params.log_rq_size;
+		log_cq_size = params->log_rq_size;
 	}
 
 	MLX5_SET(cqc, cqc, log_cq_size, log_cq_size);
-	if (MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS)) {
+	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)) {
 		MLX5_SET(cqc, cqc, mini_cqe_res_format, MLX5_CQE_FORMAT_CSUM);
 		MLX5_SET(cqc, cqc, cqe_comp_en, 1);
 	}
 
 	mlx5e_build_common_cq_param(priv, param);
 
-	param->cq_period_mode = priv->params.rx_cq_period_mode;
+	if (params->rx_am_enabled)
+		params->rx_cq_moderation =
+			mlx5e_am_get_def_profile(params->rx_cq_period_mode);
 }
 
 static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
+				    struct mlx5e_params *params,
 				    struct mlx5e_cq_param *param)
 {
 	void *cqc = param->cqc;
 
-	MLX5_SET(cqc, cqc, log_cq_size, priv->params.log_sq_size);
+	MLX5_SET(cqc, cqc, log_cq_size, params->log_sq_size);
 
 	mlx5e_build_common_cq_param(priv, param);
 
@@ -1775,8 +1921,8 @@ static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
 }
 
 static void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
-				     struct mlx5e_cq_param *param,
-				     u8 log_wq_size)
+				     u8 log_wq_size,
+				     struct mlx5e_cq_param *param)
 {
 	void *cqc = param->cqc;
 
@@ -1788,8 +1934,8 @@ static void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
 }
 
 static void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
-				    struct mlx5e_sq_param *param,
-				    u8 log_wq_size)
+				    u8 log_wq_size,
+				    struct mlx5e_sq_param *param)
 {
 	void *sqc = param->sqc;
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
@@ -1798,162 +1944,119 @@ static void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
 
 	MLX5_SET(wq, wq, log_wq_sz, log_wq_size);
 	MLX5_SET(sqc, sqc, reg_umr, MLX5_CAP_ETH(priv->mdev, reg_umr_sq));
-
-	param->type = MLX5E_SQ_ICO;
 }
 
 static void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
+				    struct mlx5e_params *params,
 				    struct mlx5e_sq_param *param)
 {
 	void *sqc = param->sqc;
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
 
 	mlx5e_build_sq_param_common(priv, param);
-	MLX5_SET(wq, wq, log_wq_sz,     priv->params.log_sq_size);
-
-	param->max_inline = priv->params.tx_max_inline;
-	param->min_inline_mode = priv->params.tx_min_inline_mode;
-	param->type = MLX5E_SQ_XDP;
+	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
 }
 
-static void mlx5e_build_channel_param(struct mlx5e_priv *priv, struct mlx5e_channel_param *cparam)
+static void mlx5e_build_channel_param(struct mlx5e_priv *priv,
+				      struct mlx5e_params *params,
+				      struct mlx5e_channel_param *cparam)
 {
 	u8 icosq_log_wq_sz = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
 
-	mlx5e_build_rq_param(priv, &cparam->rq);
-	mlx5e_build_sq_param(priv, &cparam->sq);
-	mlx5e_build_xdpsq_param(priv, &cparam->xdp_sq);
-	mlx5e_build_icosq_param(priv, &cparam->icosq, icosq_log_wq_sz);
-	mlx5e_build_rx_cq_param(priv, &cparam->rx_cq);
-	mlx5e_build_tx_cq_param(priv, &cparam->tx_cq);
-	mlx5e_build_ico_cq_param(priv, &cparam->icosq_cq, icosq_log_wq_sz);
+	mlx5e_build_rq_param(priv, params, &cparam->rq);
+	mlx5e_build_sq_param(priv, params, &cparam->sq);
+	mlx5e_build_xdpsq_param(priv, params, &cparam->xdp_sq);
+	mlx5e_build_icosq_param(priv, icosq_log_wq_sz, &cparam->icosq);
+	mlx5e_build_rx_cq_param(priv, params, &cparam->rx_cq);
+	mlx5e_build_tx_cq_param(priv, params, &cparam->tx_cq);
+	mlx5e_build_ico_cq_param(priv, icosq_log_wq_sz, &cparam->icosq_cq);
 }
 
-static int mlx5e_open_channels(struct mlx5e_priv *priv)
+int mlx5e_open_channels(struct mlx5e_priv *priv,
+			struct mlx5e_channels *chs)
 {
 	struct mlx5e_channel_param *cparam;
-	int nch = priv->params.num_channels;
 	int err = -ENOMEM;
 	int i;
-	int j;
 
-	priv->channel = kcalloc(nch, sizeof(struct mlx5e_channel *),
-				GFP_KERNEL);
-
-	priv->txq_to_sq_map = kcalloc(nch * priv->params.num_tc,
-				      sizeof(struct mlx5e_sq *), GFP_KERNEL);
+	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);
+	if (!chs->c || !cparam)
+		goto err_free;
 
-	if (!priv->channel || !priv->txq_to_sq_map || !cparam)
-		goto err_free_txq_to_sq_map;
-
-	mlx5e_build_channel_param(priv, cparam);
-
-	for (i = 0; i < nch; i++) {
-		err = mlx5e_open_channel(priv, i, cparam, &priv->channel[i]);
-		if (err)
-			goto err_close_channels;
-	}
-
-	for (j = 0; j < nch; j++) {
-		err = mlx5e_wait_for_min_rx_wqes(&priv->channel[j]->rq);
+	mlx5e_build_channel_param(priv, &chs->params, cparam);
+	for (i = 0; i < chs->num; i++) {
+		err = mlx5e_open_channel(priv, i, &chs->params, cparam, &chs->c[i]);
 		if (err)
 			goto err_close_channels;
 	}
 
-	/* FIXME: This is a W/A for tx timeout watch dog false alarm when
-	 * polling for inactive tx queues.
-	 */
-	netif_tx_start_all_queues(priv->netdev);
-
 	kfree(cparam);
 	return 0;
 
 err_close_channels:
 	for (i--; i >= 0; i--)
-		mlx5e_close_channel(priv->channel[i]);
+		mlx5e_close_channel(chs->c[i]);
 
-err_free_txq_to_sq_map:
-	kfree(priv->txq_to_sq_map);
-	kfree(priv->channel);
+err_free:
+	kfree(chs->c);
 	kfree(cparam);
-
+	chs->num = 0;
 	return err;
 }
 
-static void mlx5e_close_channels(struct mlx5e_priv *priv)
+static void mlx5e_activate_channels(struct mlx5e_channels *chs)
 {
 	int i;
 
-	/* FIXME: This is a W/A only for tx timeout watch dog false alarm when
-	 * polling for inactive tx queues.
-	 */
-	netif_tx_stop_all_queues(priv->netdev);
-	netif_tx_disable(priv->netdev);
-
-	for (i = 0; i < priv->params.num_channels; i++)
-		mlx5e_close_channel(priv->channel[i]);
-
-	kfree(priv->txq_to_sq_map);
-	kfree(priv->channel);
-}
-
-static int mlx5e_rx_hash_fn(int hfunc)
-{
-	return (hfunc == ETH_RSS_HASH_TOP) ?
-	       MLX5_RX_HASH_FN_TOEPLITZ :
-	       MLX5_RX_HASH_FN_INVERTED_XOR8;
+	for (i = 0; i < chs->num; i++)
+		mlx5e_activate_channel(chs->c[i]);
 }
 
-static int mlx5e_bits_invert(unsigned long a, int size)
+static int mlx5e_wait_channels_min_rx_wqes(struct mlx5e_channels *chs)
 {
-	int inv = 0;
+	int err = 0;
 	int i;
 
-	for (i = 0; i < size; i++)
-		inv |= (test_bit(size - i - 1, &a) ? 1 : 0) << i;
+	for (i = 0; i < chs->num; i++) {
+		err = mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq);
+		if (err)
+			break;
+	}
 
-	return inv;
+	return err;
 }
 
-static void mlx5e_fill_indir_rqt_rqns(struct mlx5e_priv *priv, void *rqtc)
+static void mlx5e_deactivate_channels(struct mlx5e_channels *chs)
 {
 	int i;
 
-	for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++) {
-		int ix = i;
-		u32 rqn;
-
-		if (priv->params.rss_hfunc == ETH_RSS_HASH_XOR)
-			ix = mlx5e_bits_invert(i, MLX5E_LOG_INDIR_RQT_SIZE);
-
-		ix = priv->params.indirection_rqt[ix];
-		rqn = test_bit(MLX5E_STATE_OPENED, &priv->state) ?
-				priv->channel[ix]->rq.rqn :
-				priv->drop_rq.rqn;
-		MLX5_SET(rqtc, rqtc, rq_num[i], rqn);
-	}
+	for (i = 0; i < chs->num; i++)
+		mlx5e_deactivate_channel(chs->c[i]);
 }
 
-static void mlx5e_fill_direct_rqt_rqn(struct mlx5e_priv *priv, void *rqtc,
-				      int ix)
+void mlx5e_close_channels(struct mlx5e_channels *chs)
 {
-	u32 rqn = test_bit(MLX5E_STATE_OPENED, &priv->state) ?
-			priv->channel[ix]->rq.rqn :
-			priv->drop_rq.rqn;
+	int i;
 
-	MLX5_SET(rqtc, rqtc, rq_num[0], rqn);
+	for (i = 0; i < chs->num; i++)
+		mlx5e_close_channel(chs->c[i]);
+
+	kfree(chs->c);
+	chs->num = 0;
 }
 
-static int mlx5e_create_rqt(struct mlx5e_priv *priv, int sz,
-			    int ix, struct mlx5e_rqt *rqt)
+static int
+mlx5e_create_rqt(struct mlx5e_priv *priv, int sz, struct mlx5e_rqt *rqt)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	void *rqtc;
 	int inlen;
 	int err;
 	u32 *in;
+	int i;
 
 	inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * sz;
 	in = mlx5_vzalloc(inlen);
@@ -1965,10 +2068,8 @@ static int mlx5e_create_rqt(struct mlx5e_priv *priv, int sz,
 	MLX5_SET(rqtc, rqtc, rqt_actual_size, sz);
 	MLX5_SET(rqtc, rqtc, rqt_max_size, sz);
 
-	if (sz > 1) /* RSS */
-		mlx5e_fill_indir_rqt_rqns(priv, rqtc);
-	else
-		mlx5e_fill_direct_rqt_rqn(priv, rqtc, ix);
+	for (i = 0; i < sz; i++)
+		MLX5_SET(rqtc, rqtc, rq_num[i], priv->drop_rq.rqn);
 
 	err = mlx5_core_create_rqt(mdev, in, inlen, &rqt->rqtn);
 	if (!err)
@@ -1988,7 +2089,7 @@ static int mlx5e_create_indirect_rqts(struct mlx5e_priv *priv)
 {
 	struct mlx5e_rqt *rqt = &priv->indir_rqt;
 
-	return mlx5e_create_rqt(priv, MLX5E_INDIR_RQT_SIZE, 0, rqt);
+	return mlx5e_create_rqt(priv, MLX5E_INDIR_RQT_SIZE, rqt);
 }
 
 int mlx5e_create_direct_rqts(struct mlx5e_priv *priv)
@@ -1999,7 +2100,7 @@ int mlx5e_create_direct_rqts(struct mlx5e_priv *priv)
 
 	for (ix = 0; ix < priv->profile->max_nch(priv->mdev); ix++) {
 		rqt = &priv->direct_tir[ix].rqt;
-		err = mlx5e_create_rqt(priv, 1 /*size */, ix, rqt);
+		err = mlx5e_create_rqt(priv, 1 /*size */, rqt);
 		if (err)
 			goto err_destroy_rqts;
 	}
@@ -2013,7 +2114,49 @@ err_destroy_rqts:
 	return err;
 }
 
-int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, int ix)
+static int mlx5e_rx_hash_fn(int hfunc)
+{
+	return (hfunc == ETH_RSS_HASH_TOP) ?
+	       MLX5_RX_HASH_FN_TOEPLITZ :
+	       MLX5_RX_HASH_FN_INVERTED_XOR8;
+}
+
+static int mlx5e_bits_invert(unsigned long a, int size)
+{
+	int inv = 0;
+	int i;
+
+	for (i = 0; i < size; i++)
+		inv |= (test_bit(size - i - 1, &a) ? 1 : 0) << i;
+
+	return inv;
+}
+
+static void mlx5e_fill_rqt_rqns(struct mlx5e_priv *priv, int sz,
+				struct mlx5e_redirect_rqt_param rrp, void *rqtc)
+{
+	int i;
+
+	for (i = 0; i < sz; i++) {
+		u32 rqn;
+
+		if (rrp.is_rss) {
+			int ix = i;
+
+			if (rrp.rss.hfunc == ETH_RSS_HASH_XOR)
+				ix = mlx5e_bits_invert(i, ilog2(sz));
+
+			ix = priv->channels.params.indirection_rqt[ix];
+			rqn = rrp.rss.channels->c[ix]->rq.rqn;
+		} else {
+			rqn = rrp.rqn;
+		}
+		MLX5_SET(rqtc, rqtc, rq_num[i], rqn);
+	}
+}
+
+int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz,
+		       struct mlx5e_redirect_rqt_param rrp)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	void *rqtc;
@@ -2029,41 +2172,86 @@ int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, int ix)
 	rqtc = MLX5_ADDR_OF(modify_rqt_in, in, ctx);
 
 	MLX5_SET(rqtc, rqtc, rqt_actual_size, sz);
-	if (sz > 1) /* RSS */
-		mlx5e_fill_indir_rqt_rqns(priv, rqtc);
-	else
-		mlx5e_fill_direct_rqt_rqn(priv, rqtc, ix);
-
 	MLX5_SET(modify_rqt_in, in, bitmask.rqn_list, 1);
-
+	mlx5e_fill_rqt_rqns(priv, sz, rrp, rqtc);
 	err = mlx5_core_modify_rqt(mdev, rqtn, in, inlen);
 
 	kvfree(in);
-
 	return err;
 }
 
-static void mlx5e_redirect_rqts(struct mlx5e_priv *priv)
+static u32 mlx5e_get_direct_rqn(struct mlx5e_priv *priv, int ix,
+				struct mlx5e_redirect_rqt_param rrp)
+{
+	if (!rrp.is_rss)
+		return rrp.rqn;
+
+	if (ix >= rrp.rss.channels->num)
+		return priv->drop_rq.rqn;
+
+	return rrp.rss.channels->c[ix]->rq.rqn;
+}
+
+static void mlx5e_redirect_rqts(struct mlx5e_priv *priv,
+				struct mlx5e_redirect_rqt_param rrp)
 {
 	u32 rqtn;
 	int ix;
 
 	if (priv->indir_rqt.enabled) {
+		/* RSS RQ table */
 		rqtn = priv->indir_rqt.rqtn;
-		mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, 0);
+		mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp);
 	}
 
-	for (ix = 0; ix < priv->params.num_channels; ix++) {
+	for (ix = 0; ix < priv->profile->max_nch(priv->mdev); ix++) {
+		struct mlx5e_redirect_rqt_param direct_rrp = {
+			.is_rss = false,
+			{
+				.rqn    = mlx5e_get_direct_rqn(priv, ix, rrp)
+			},
+		};
+
+		/* Direct RQ Tables */
 		if (!priv->direct_tir[ix].rqt.enabled)
 			continue;
+
 		rqtn = priv->direct_tir[ix].rqt.rqtn;
-		mlx5e_redirect_rqt(priv, rqtn, 1, ix);
+		mlx5e_redirect_rqt(priv, rqtn, 1, direct_rrp);
 	}
 }
 
-static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv)
+static void mlx5e_redirect_rqts_to_channels(struct mlx5e_priv *priv,
+					    struct mlx5e_channels *chs)
+{
+	struct mlx5e_redirect_rqt_param rrp = {
+		.is_rss        = true,
+		{
+			.rss = {
+				.channels  = chs,
+				.hfunc     = chs->params.rss_hfunc,
+			}
+		},
+	};
+
+	mlx5e_redirect_rqts(priv, rrp);
+}
+
+static void mlx5e_redirect_rqts_to_drop(struct mlx5e_priv *priv)
 {
-	if (!priv->params.lro_en)
+	struct mlx5e_redirect_rqt_param drop_rrp = {
+		.is_rss = false,
+		{
+			.rqn = priv->drop_rq.rqn,
+		},
+	};
+
+	mlx5e_redirect_rqts(priv, drop_rrp);
+}
+
+static void mlx5e_build_tir_ctx_lro(struct mlx5e_params *params, void *tirc)
+{
+	if (!params->lro_en)
 		return;
 
 #define ROUGH_MAX_L2_L3_HDR_SZ 256
@@ -2072,13 +2260,13 @@ static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv)
 		 MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO |
 		 MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO);
 	MLX5_SET(tirc, tirc, lro_max_ip_payload_size,
-		 (priv->params.lro_wqe_sz -
-		  ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
-	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, priv->params.lro_timeout);
+		 (params->lro_wqe_sz - ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
+	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, params->lro_timeout);
 }
 
-void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc,
-				    enum mlx5e_traffic_types tt)
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
+				    enum mlx5e_traffic_types tt,
+				    void *tirc)
 {
 	void *hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
 
@@ -2094,16 +2282,15 @@ void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc,
 				 MLX5_HASH_FIELD_SEL_DST_IP   |\
 				 MLX5_HASH_FIELD_SEL_IPSEC_SPI)
 
-	MLX5_SET(tirc, tirc, rx_hash_fn,
-		 mlx5e_rx_hash_fn(priv->params.rss_hfunc));
-	if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) {
+	MLX5_SET(tirc, tirc, rx_hash_fn, mlx5e_rx_hash_fn(params->rss_hfunc));
+	if (params->rss_hfunc == ETH_RSS_HASH_TOP) {
 		void *rss_key = MLX5_ADDR_OF(tirc, tirc,
 					     rx_hash_toeplitz_key);
 		size_t len = MLX5_FLD_SZ_BYTES(tirc,
 					       rx_hash_toeplitz_key);
 
 		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
-		memcpy(rss_key, priv->params.toeplitz_hash_key, len);
+		memcpy(rss_key, params->toeplitz_hash_key, len);
 	}
 
 	switch (tt) {
@@ -2208,7 +2395,7 @@ static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv)
 	MLX5_SET(modify_tir_in, in, bitmask.lro, 1);
 	tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
 
-	mlx5e_build_tir_ctx_lro(tirc, priv);
+	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
 		err = mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in,
@@ -2258,9 +2445,9 @@ static void mlx5e_query_mtu(struct mlx5e_priv *priv, u16 *mtu)
 	*mtu = MLX5E_HW2SW_MTU(hw_mtu);
 }
 
-static int mlx5e_set_dev_port_mtu(struct net_device *netdev)
+static int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct net_device *netdev = priv->netdev;
 	u16 mtu;
 	int err;
 
@@ -2280,8 +2467,8 @@ static int mlx5e_set_dev_port_mtu(struct net_device *netdev)
 static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	int nch = priv->params.num_channels;
-	int ntc = priv->params.num_tc;
+	int nch = priv->channels.params.num_channels;
+	int ntc = priv->channels.params.num_tc;
 	int tc;
 
 	netdev_reset_tc(netdev);
@@ -2298,53 +2485,112 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 		netdev_set_tc_queue(netdev, tc, nch, 0);
 }
 
+static void mlx5e_build_channels_tx_maps(struct mlx5e_priv *priv)
+{
+	struct mlx5e_channel *c;
+	struct mlx5e_txqsq *sq;
+	int i, tc;
+
+	for (i = 0; i < priv->channels.num; i++)
+		for (tc = 0; tc < priv->profile->max_tc; tc++)
+			priv->channel_tc2txq[i][tc] = i + tc * priv->channels.num;
+
+	for (i = 0; i < priv->channels.num; i++) {
+		c = priv->channels.c[i];
+		for (tc = 0; tc < c->num_tc; tc++) {
+			sq = &c->sq[tc];
+			priv->txq2sq[sq->txq_ix] = sq;
+		}
+	}
+}
+
+static void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
+{
+	int num_txqs = priv->channels.num * priv->channels.params.num_tc;
+	struct net_device *netdev = priv->netdev;
+
+	mlx5e_netdev_set_tcs(netdev);
+	if (netdev->real_num_tx_queues != num_txqs)
+		netif_set_real_num_tx_queues(netdev, num_txqs);
+	if (netdev->real_num_rx_queues != priv->channels.num)
+		netif_set_real_num_rx_queues(netdev, priv->channels.num);
+
+	mlx5e_build_channels_tx_maps(priv);
+	mlx5e_activate_channels(&priv->channels);
+	netif_tx_start_all_queues(priv->netdev);
+
+	if (MLX5_CAP_GEN(priv->mdev, vport_group_manager))
+		mlx5e_add_sqs_fwd_rules(priv);
+
+	mlx5e_wait_channels_min_rx_wqes(&priv->channels);
+	mlx5e_redirect_rqts_to_channels(priv, &priv->channels);
+}
+
+static void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
+{
+	mlx5e_redirect_rqts_to_drop(priv);
+
+	if (MLX5_CAP_GEN(priv->mdev, vport_group_manager))
+		mlx5e_remove_sqs_fwd_rules(priv);
+
+	/* FIXME: This is a W/A only for tx timeout watch dog false alarm when
+	 * polling for inactive tx queues.
+	 */
+	netif_tx_stop_all_queues(priv->netdev);
+	netif_tx_disable(priv->netdev);
+	mlx5e_deactivate_channels(&priv->channels);
+}
+
+void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
+				struct mlx5e_channels *new_chs,
+				mlx5e_fp_hw_modify hw_modify)
+{
+	struct net_device *netdev = priv->netdev;
+	int new_num_txqs;
+
+	new_num_txqs = new_chs->num * new_chs->params.num_tc;
+
+	netif_carrier_off(netdev);
+
+	if (new_num_txqs < netdev->real_num_tx_queues)
+		netif_set_real_num_tx_queues(netdev, new_num_txqs);
+
+	mlx5e_deactivate_priv_channels(priv);
+	mlx5e_close_channels(&priv->channels);
+
+	priv->channels = *new_chs;
+
+	/* New channels are ready to roll, modify HW settings if needed */
+	if (hw_modify)
+		hw_modify(priv);
+
+	mlx5e_refresh_tirs(priv, false);
+	mlx5e_activate_priv_channels(priv);
+
+	mlx5e_update_carrier(priv);
+}
+
 int mlx5e_open_locked(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5_core_dev *mdev = priv->mdev;
-	int num_txqs;
 	int err;
 
 	set_bit(MLX5E_STATE_OPENED, &priv->state);
 
-	mlx5e_netdev_set_tcs(netdev);
-
-	num_txqs = priv->params.num_channels * priv->params.num_tc;
-	netif_set_real_num_tx_queues(netdev, num_txqs);
-	netif_set_real_num_rx_queues(netdev, priv->params.num_channels);
-
-	err = mlx5e_open_channels(priv);
-	if (err) {
-		netdev_err(netdev, "%s: mlx5e_open_channels failed, %d\n",
-			   __func__, err);
+	err = mlx5e_open_channels(priv, &priv->channels);
+	if (err)
 		goto err_clear_state_opened_flag;
-	}
-
-	err = mlx5e_refresh_tirs_self_loopback(priv->mdev, false);
-	if (err) {
-		netdev_err(netdev, "%s: mlx5e_refresh_tirs_self_loopback_enable failed, %d\n",
-			   __func__, err);
-		goto err_close_channels;
-	}
 
-	mlx5e_redirect_rqts(priv);
+	mlx5e_refresh_tirs(priv, false);
+	mlx5e_activate_priv_channels(priv);
 	mlx5e_update_carrier(priv);
 	mlx5e_timestamp_init(priv);
-#ifdef CONFIG_RFS_ACCEL
-	priv->netdev->rx_cpu_rmap = priv->mdev->rmap;
-#endif
+
 	if (priv->profile->update_stats)
 		queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
 
-	if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
-		err = mlx5e_add_sqs_fwd_rules(priv);
-		if (err)
-			goto err_close_channels;
-	}
 	return 0;
 
-err_close_channels:
-	mlx5e_close_channels(priv);
 err_clear_state_opened_flag:
 	clear_bit(MLX5E_STATE_OPENED, &priv->state);
 	return err;
@@ -2365,7 +2611,6 @@ int mlx5e_open(struct net_device *netdev)
 int mlx5e_close_locked(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5_core_dev *mdev = priv->mdev;
 
 	/* May already be CLOSED in case a previous configuration operation
 	 * (e.g RX/TX queue size change) that involves close&open failed.
@@ -2375,13 +2620,10 @@ int mlx5e_close_locked(struct net_device *netdev)
 
 	clear_bit(MLX5E_STATE_OPENED, &priv->state);
 
-	if (MLX5_CAP_GEN(mdev, vport_group_manager))
-		mlx5e_remove_sqs_fwd_rules(priv);
-
 	mlx5e_timestamp_cleanup(priv);
 	netif_carrier_off(priv->netdev);
-	mlx5e_redirect_rqts(priv);
-	mlx5e_close_channels(priv);
+	mlx5e_deactivate_priv_channels(priv);
+	mlx5e_close_channels(&priv->channels);
 
 	return 0;
 }
@@ -2401,11 +2643,10 @@ int mlx5e_close(struct net_device *netdev)
 	return err;
 }
 
-static int mlx5e_create_drop_rq(struct mlx5e_priv *priv,
-				struct mlx5e_rq *rq,
-				struct mlx5e_rq_param *param)
+static int mlx5e_alloc_drop_rq(struct mlx5_core_dev *mdev,
+			       struct mlx5e_rq *rq,
+			       struct mlx5e_rq_param *param)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
 	void *rqc = param->rqc;
 	void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq);
 	int err;
@@ -2417,16 +2658,15 @@ static int mlx5e_create_drop_rq(struct mlx5e_priv *priv,
 	if (err)
 		return err;
 
-	rq->priv = priv;
+	rq->mdev = mdev;
 
 	return 0;
 }
 
-static int mlx5e_create_drop_cq(struct mlx5e_priv *priv,
-				struct mlx5e_cq *cq,
-				struct mlx5e_cq_param *param)
+static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev,
+			       struct mlx5e_cq *cq,
+			       struct mlx5e_cq_param *param)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_core_cq *mcq = &cq->mcq;
 	int eqn_not_used;
 	unsigned int irqn;
@@ -2449,59 +2689,57 @@ static int mlx5e_create_drop_cq(struct mlx5e_priv *priv,
 	mcq->event      = mlx5e_cq_error_event;
 	mcq->irqn       = irqn;
 
-	cq->priv = priv;
+	cq->mdev = mdev;
 
 	return 0;
 }
 
-static int mlx5e_open_drop_rq(struct mlx5e_priv *priv)
+static int mlx5e_open_drop_rq(struct mlx5_core_dev *mdev,
+			      struct mlx5e_rq *drop_rq)
 {
-	struct mlx5e_cq_param cq_param;
-	struct mlx5e_rq_param rq_param;
-	struct mlx5e_rq *rq = &priv->drop_rq;
-	struct mlx5e_cq *cq = &priv->drop_rq.cq;
+	struct mlx5e_cq_param cq_param = {};
+	struct mlx5e_rq_param rq_param = {};
+	struct mlx5e_cq *cq = &drop_rq->cq;
 	int err;
 
-	memset(&cq_param, 0, sizeof(cq_param));
-	memset(&rq_param, 0, sizeof(rq_param));
 	mlx5e_build_drop_rq_param(&rq_param);
 
-	err = mlx5e_create_drop_cq(priv, cq, &cq_param);
+	err = mlx5e_alloc_drop_cq(mdev, cq, &cq_param);
 	if (err)
 		return err;
 
-	err = mlx5e_enable_cq(cq, &cq_param);
+	err = mlx5e_create_cq(cq, &cq_param);
 	if (err)
-		goto err_destroy_cq;
+		goto err_free_cq;
 
-	err = mlx5e_create_drop_rq(priv, rq, &rq_param);
+	err = mlx5e_alloc_drop_rq(mdev, drop_rq, &rq_param);
 	if (err)
-		goto err_disable_cq;
+		goto err_destroy_cq;
 
-	err = mlx5e_enable_rq(rq, &rq_param);
+	err = mlx5e_create_rq(drop_rq, &rq_param);
 	if (err)
-		goto err_destroy_rq;
+		goto err_free_rq;
 
 	return 0;
 
-err_destroy_rq:
-	mlx5e_destroy_rq(&priv->drop_rq);
-
-err_disable_cq:
-	mlx5e_disable_cq(&priv->drop_rq.cq);
+err_free_rq:
+	mlx5e_free_rq(drop_rq);
 
 err_destroy_cq:
-	mlx5e_destroy_cq(&priv->drop_rq.cq);
+	mlx5e_destroy_cq(cq);
+
+err_free_cq:
+	mlx5e_free_cq(cq);
 
 	return err;
 }
 
-static void mlx5e_close_drop_rq(struct mlx5e_priv *priv)
+static void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq)
 {
-	mlx5e_disable_rq(&priv->drop_rq);
-	mlx5e_destroy_rq(&priv->drop_rq);
-	mlx5e_disable_cq(&priv->drop_rq.cq);
-	mlx5e_destroy_cq(&priv->drop_rq.cq);
+	mlx5e_destroy_rq(drop_rq);
+	mlx5e_free_rq(drop_rq);
+	mlx5e_destroy_cq(&drop_rq->cq);
+	mlx5e_free_cq(&drop_rq->cq);
 }
 
 static int mlx5e_create_tis(struct mlx5e_priv *priv, int tc)
@@ -2552,24 +2790,24 @@ void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
 		mlx5e_destroy_tis(priv, tc);
 }
 
-static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
-				      enum mlx5e_traffic_types tt)
+static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv,
+				      enum mlx5e_traffic_types tt,
+				      u32 *tirc)
 {
 	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
 
-	mlx5e_build_tir_ctx_lro(tirc, priv);
+	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
 
 	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
 	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
-	mlx5e_build_indir_tir_ctx_hash(priv, tirc, tt);
+	mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc);
 }
 
-static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
-				       u32 rqtn)
+static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 rqtn, u32 *tirc)
 {
 	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
 
-	mlx5e_build_tir_ctx_lro(tirc, priv);
+	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
 
 	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
 	MLX5_SET(tirc, tirc, indirect_table, rqtn);
@@ -2594,7 +2832,7 @@ static int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv)
 		memset(in, 0, inlen);
 		tir = &priv->indir_tir[tt];
 		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
-		mlx5e_build_indir_tir_ctx(priv, tirc, tt);
+		mlx5e_build_indir_tir_ctx(priv, tt, tirc);
 		err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
 		if (err)
 			goto err_destroy_tirs;
@@ -2632,8 +2870,7 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv)
 		memset(in, 0, inlen);
 		tir = &priv->direct_tir[ix];
 		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
-		mlx5e_build_direct_tir_ctx(priv, tirc,
-					   priv->direct_tir[ix].rqt.rqtn);
+		mlx5e_build_direct_tir_ctx(priv, priv->direct_tir[ix].rqt.rqtn, tirc);
 		err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
 		if (err)
 			goto err_destroy_ch_tirs;
@@ -2669,16 +2906,13 @@ void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv)
 		mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[i]);
 }
 
-int mlx5e_modify_rqs_vsd(struct mlx5e_priv *priv, bool vsd)
+int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd)
 {
 	int err = 0;
 	int i;
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		return 0;
-
-	for (i = 0; i < priv->params.num_channels; i++) {
-		err = mlx5e_modify_rq_vsd(&priv->channel[i]->rq, vsd);
+	for (i = 0; i < chs->num; i++) {
+		err = mlx5e_modify_rq_vsd(&chs->c[i]->rq, vsd);
 		if (err)
 			return err;
 	}
@@ -2689,7 +2923,7 @@ int mlx5e_modify_rqs_vsd(struct mlx5e_priv *priv, bool vsd)
 static int mlx5e_setup_tc(struct net_device *netdev, u8 tc)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	bool was_opened;
+	struct mlx5e_channels new_channels = {};
 	int err = 0;
 
 	if (tc && tc != MLX5E_MAX_NUM_TC)
@@ -2697,17 +2931,21 @@ static int mlx5e_setup_tc(struct net_device *netdev, u8 tc)
 
 	mutex_lock(&priv->state_lock);
 
-	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (was_opened)
-		mlx5e_close_locked(priv->netdev);
+	new_channels.params = priv->channels.params;
+	new_channels.params.num_tc = tc ? tc : 1;
 
-	priv->params.num_tc = tc ? tc : 1;
+	if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		priv->channels.params = new_channels.params;
+		goto out;
+	}
 
-	if (was_opened)
-		err = mlx5e_open_locked(priv->netdev);
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err)
+		goto out;
 
+	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+out:
 	mutex_unlock(&priv->state_lock);
-
 	return err;
 }
 
@@ -2737,7 +2975,9 @@ mqprio:
 	if (tc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
-	return mlx5e_setup_tc(dev, tc->tc);
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+	return mlx5e_setup_tc(dev, tc->mqprio->num_tc);
 }
 
 static void
@@ -2822,26 +3062,31 @@ typedef int (*mlx5e_feature_handler)(struct net_device *netdev, bool enable);
 static int set_feature_lro(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	bool was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-	int err;
+	struct mlx5e_channels new_channels = {};
+	int err = 0;
+	bool reset;
 
 	mutex_lock(&priv->state_lock);
 
-	if (was_opened && (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST))
-		mlx5e_close_locked(priv->netdev);
+	reset = (priv->channels.params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST);
+	reset = reset && test_bit(MLX5E_STATE_OPENED, &priv->state);
 
-	priv->params.lro_en = enable;
-	err = mlx5e_modify_tirs_lro(priv);
-	if (err) {
-		netdev_err(netdev, "lro modify failed, %d\n", err);
-		priv->params.lro_en = !enable;
+	new_channels.params = priv->channels.params;
+	new_channels.params.lro_en = enable;
+
+	if (!reset) {
+		priv->channels.params = new_channels.params;
+		err = mlx5e_modify_tirs_lro(priv);
+		goto out;
 	}
 
-	if (was_opened && (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST))
-		mlx5e_open_locked(priv->netdev);
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err)
+		goto out;
 
+	mlx5e_switch_priv_channels(priv, &new_channels, mlx5e_modify_tirs_lro);
+out:
 	mutex_unlock(&priv->state_lock);
-
 	return err;
 }
 
@@ -2881,15 +3126,19 @@ static int set_feature_rx_all(struct net_device *netdev, bool enable)
 static int set_feature_rx_vlan(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	int err;
+	int err = 0;
 
 	mutex_lock(&priv->state_lock);
 
-	priv->params.vlan_strip_disable = !enable;
-	err = mlx5e_modify_rqs_vsd(priv, !enable);
+	priv->channels.params.vlan_strip_disable = !enable;
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto unlock;
+
+	err = mlx5e_modify_channels_vsd(&priv->channels, !enable);
 	if (err)
-		priv->params.vlan_strip_disable = enable;
+		priv->channels.params.vlan_strip_disable = enable;
 
+unlock:
 	mutex_unlock(&priv->state_lock);
 
 	return err;
@@ -2960,28 +3209,38 @@ static int mlx5e_set_features(struct net_device *netdev,
 static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	bool was_opened;
+	struct mlx5e_channels new_channels = {};
+	int curr_mtu;
 	int err = 0;
 	bool reset;
 
 	mutex_lock(&priv->state_lock);
 
-	reset = !priv->params.lro_en &&
-		(priv->params.rq_wq_type !=
+	reset = !priv->channels.params.lro_en &&
+		(priv->channels.params.rq_wq_type !=
 		 MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
 
-	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (was_opened && reset)
-		mlx5e_close_locked(netdev);
+	reset = reset && test_bit(MLX5E_STATE_OPENED, &priv->state);
 
+	curr_mtu    = netdev->mtu;
 	netdev->mtu = new_mtu;
-	mlx5e_set_dev_port_mtu(netdev);
 
-	if (was_opened && reset)
-		err = mlx5e_open_locked(netdev);
+	if (!reset) {
+		mlx5e_set_dev_port_mtu(priv);
+		goto out;
+	}
 
-	mutex_unlock(&priv->state_lock);
+	new_channels.params = priv->channels.params;
+	err = mlx5e_open_channels(priv, &new_channels);
+	if (err) {
+		netdev->mtu = curr_mtu;
+		goto out;
+	}
 
+	mlx5e_switch_priv_channels(priv, &new_channels, mlx5e_set_dev_port_mtu);
+
+out:
+	mutex_unlock(&priv->state_lock);
 	return err;
 }
 
@@ -3186,8 +3445,8 @@ static void mlx5e_tx_timeout(struct net_device *dev)
 
 	netdev_err(dev, "TX timeout detected\n");
 
-	for (i = 0; i < priv->params.num_channels * priv->params.num_tc; i++) {
-		struct mlx5e_sq *sq = priv->txq_to_sq_map[i];
+	for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; i++) {
+		struct mlx5e_txqsq *sq = priv->txq2sq[i];
 
 		if (!netif_xmit_stopped(netdev_get_tx_queue(dev, i)))
 			continue;
@@ -3219,7 +3478,7 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 
 	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
 	/* no need for full reset when exchanging programs */
-	reset = (!priv->xdp_prog || !prog);
+	reset = (!priv->channels.params.xdp_prog || !prog);
 
 	if (was_opened && reset)
 		mlx5e_close_locked(netdev);
@@ -3227,7 +3486,7 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 		/* num_channels is invariant here, so we can take the
 		 * batched reference right upfront.
 		 */
-		prog = bpf_prog_add(prog, priv->params.num_channels);
+		prog = bpf_prog_add(prog, priv->channels.num);
 		if (IS_ERR(prog)) {
 			err = PTR_ERR(prog);
 			goto unlock;
@@ -3237,12 +3496,12 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	/* exchange programs, extra prog reference we got from caller
 	 * as long as we don't fail from this point onwards.
 	 */
-	old_prog = xchg(&priv->xdp_prog, prog);
+	old_prog = xchg(&priv->channels.params.xdp_prog, prog);
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
 	if (reset) /* change RQ type according to priv->xdp_prog */
-		mlx5e_set_rq_priv_params(priv);
+		mlx5e_set_rq_params(priv->mdev, &priv->channels.params);
 
 	if (was_opened && reset)
 		mlx5e_open_locked(netdev);
@@ -3253,8 +3512,8 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	/* exchanging programs w/o reset, we update ref counts on behalf
 	 * of the channels RQs here.
 	 */
-	for (i = 0; i < priv->params.num_channels; i++) {
-		struct mlx5e_channel *c = priv->channel[i];
+	for (i = 0; i < priv->channels.num; i++) {
+		struct mlx5e_channel *c = priv->channels.c[i];
 
 		clear_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state);
 		napi_synchronize(&c->napi);
@@ -3280,7 +3539,7 @@ static bool mlx5e_xdp_attached(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
-	return !!priv->xdp_prog;
+	return !!priv->channels.params.xdp_prog;
 }
 
 static int mlx5e_xdp(struct net_device *dev, struct netdev_xdp *xdp)
@@ -3303,10 +3562,12 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_xdp *xdp)
 static void mlx5e_netpoll(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_channels *chs = &priv->channels;
+
 	int i;
 
-	for (i = 0; i < priv->params.num_channels; i++)
-		napi_schedule(&priv->channel[i]->napi);
+	for (i = 0; i < chs->num; i++)
+		napi_schedule(&chs->c[i]->napi);
 }
 #endif
 
@@ -3475,6 +3736,9 @@ void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
 	if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE)
 		params->rx_cq_moderation.usec =
 			MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE;
+
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_BASED_MODER,
+			params->rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
 }
 
 u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout)
@@ -3489,75 +3753,79 @@ u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout)
 	return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]);
 }
 
-static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
-					struct net_device *netdev,
-					const struct mlx5e_profile *profile,
-					void *ppriv)
+static void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
+				   struct mlx5e_params *params,
+				   u16 max_channels)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
+	u8 cq_period_mode = 0;
 	u32 link_speed = 0;
 	u32 pci_bw = 0;
-	u8 cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
-					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
-					 MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 
-	priv->mdev                         = mdev;
-	priv->netdev                       = netdev;
-	priv->params.num_channels          = profile->max_nch(mdev);
-	priv->profile                      = profile;
-	priv->ppriv                        = ppriv;
+	params->num_channels = max_channels;
+	params->num_tc       = 1;
 
-	priv->params.lro_timeout =
-		mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
-
-	priv->params.log_sq_size = is_kdump_kernel() ?
+	/* SQ */
+	params->log_sq_size = is_kdump_kernel() ?
 		MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE :
 		MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
 
 	/* set CQE compression */
-	priv->params.rx_cqe_compress_def = false;
+	params->rx_cqe_compress_def = false;
 	if (MLX5_CAP_GEN(mdev, cqe_compression) &&
-	    MLX5_CAP_GEN(mdev, vport_group_manager)) {
+	     MLX5_CAP_GEN(mdev, vport_group_manager)) {
 		mlx5e_get_max_linkspeed(mdev, &link_speed);
 		mlx5e_get_pci_bw(mdev, &pci_bw);
 		mlx5_core_dbg(mdev, "Max link speed = %d, PCI BW = %d\n",
-			      link_speed, pci_bw);
-		priv->params.rx_cqe_compress_def =
-			cqe_compress_heuristic(link_speed, pci_bw);
+			       link_speed, pci_bw);
+		params->rx_cqe_compress_def = cqe_compress_heuristic(link_speed, pci_bw);
 	}
-
-	MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS,
-			priv->params.rx_cqe_compress_def);
-
-	mlx5e_set_rq_priv_params(priv);
-	if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
-		priv->params.lro_en = true;
-
-	priv->params.rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
-	mlx5e_set_rx_cq_mode_params(&priv->params, cq_period_mode);
-
-	priv->params.tx_cq_moderation.usec =
-		MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC;
-	priv->params.tx_cq_moderation.pkts =
-		MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
-	priv->params.tx_max_inline         = mlx5e_get_max_inline_cap(mdev);
-	mlx5_query_min_inline(mdev, &priv->params.tx_min_inline_mode);
-	if (priv->params.tx_min_inline_mode == MLX5_INLINE_MODE_NONE &&
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS, params->rx_cqe_compress_def);
+
+	/* RQ */
+	mlx5e_set_rq_params(mdev, params);
+
+	/* HW LRO */
+	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+		params->lro_en = true;
+	params->lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
+
+	/* CQ moderation params */
+	cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
+			MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
+			MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
+	params->rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
+
+	params->tx_cq_moderation.usec = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC;
+	params->tx_cq_moderation.pkts = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
+
+	/* TX inline */
+	params->tx_max_inline = mlx5e_get_max_inline_cap(mdev);
+	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
+	if (params->tx_min_inline_mode == MLX5_INLINE_MODE_NONE &&
 	    !MLX5_CAP_ETH(mdev, wqe_vlan_insert))
-		priv->params.tx_min_inline_mode = MLX5_INLINE_MODE_L2;
+		params->tx_min_inline_mode = MLX5_INLINE_MODE_L2;
 
-	priv->params.num_tc                = 1;
-	priv->params.rss_hfunc             = ETH_RSS_HASH_XOR;
+	/* RSS */
+	params->rss_hfunc = ETH_RSS_HASH_XOR;
+	netdev_rss_key_fill(params->toeplitz_hash_key, sizeof(params->toeplitz_hash_key));
+	mlx5e_build_default_indir_rqt(mdev, params->indirection_rqt,
+				      MLX5E_INDIR_RQT_SIZE, max_channels);
+}
 
-	netdev_rss_key_fill(priv->params.toeplitz_hash_key,
-			    sizeof(priv->params.toeplitz_hash_key));
+static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
+					struct net_device *netdev,
+					const struct mlx5e_profile *profile,
+					void *ppriv)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	mlx5e_build_default_indir_rqt(mdev, priv->params.indirection_rqt,
-				      MLX5E_INDIR_RQT_SIZE, profile->max_nch(mdev));
+	priv->mdev        = mdev;
+	priv->netdev      = netdev;
+	priv->profile     = profile;
+	priv->ppriv       = ppriv;
 
-	/* Initialize pflags */
-	MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_BASED_MODER,
-			priv->params.rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
+	mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev));
 
 	mutex_init(&priv->state_lock);
 
@@ -3643,7 +3911,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 		netdev->hw_features |= NETIF_F_RXALL;
 
 	netdev->features          = netdev->hw_features;
-	if (!priv->params.lro_en)
+	if (!priv->channels.params.lro_en)
 		netdev->features  &= ~NETIF_F_LRO;
 
 	if (fcs_enabled)
@@ -3708,8 +3976,8 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 {
 	mlx5e_vxlan_cleanup(priv);
 
-	if (priv->xdp_prog)
-		bpf_prog_put(priv->xdp_prog);
+	if (priv->channels.params.xdp_prog)
+		bpf_prog_put(priv->channels.params.xdp_prog);
 }
 
 static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
@@ -3872,6 +4140,10 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
 		return NULL;
 	}
 
+#ifdef CONFIG_RFS_ACCEL
+	netdev->rx_cpu_rmap = mdev->rmap;
+#endif
+
 	profile->init(mdev, netdev, profile, ppriv);
 
 	netif_carrier_off(netdev);
@@ -3906,7 +4178,7 @@ int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
 	if (err)
 		goto out;
 
-	err = mlx5e_open_drop_rq(priv);
+	err = mlx5e_open_drop_rq(mdev, &priv->drop_rq);
 	if (err) {
 		mlx5_core_err(mdev, "open drop rq failed, %d\n", err);
 		goto err_cleanup_tx;
@@ -3925,7 +4197,7 @@ int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
 	mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1);
 	netdev->max_mtu = MLX5E_HW2SW_MTU(max_mtu);
 
-	mlx5e_set_dev_port_mtu(netdev);
+	mlx5e_set_dev_port_mtu(priv);
 
 	if (profile->enable)
 		profile->enable(priv);
@@ -3939,7 +4211,7 @@ int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
 	return 0;
 
 err_close_drop_rq:
-	mlx5e_close_drop_rq(priv);
+	mlx5e_close_drop_rq(&priv->drop_rq);
 
 err_cleanup_tx:
 	profile->cleanup_tx(priv);
@@ -4003,7 +4275,7 @@ void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
 
 	mlx5e_destroy_q_counter(priv);
 	profile->cleanup_rx(priv);
-	mlx5e_close_drop_rq(priv);
+	mlx5e_close_drop_rq(&priv->drop_rq);
 	profile->cleanup_tx(priv);
 	cancel_delayed_work_sync(&priv->update_stats_work);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index f621373bd7a5..53db5ec2c122 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -102,14 +102,16 @@ static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv)
 	int i, j;
 
 	memset(s, 0, sizeof(*s));
-	for (i = 0; i < priv->params.num_channels; i++) {
-		rq_stats = &priv->channel[i]->rq.stats;
+	for (i = 0; i < priv->channels.num; i++) {
+		struct mlx5e_channel *c = priv->channels.c[i];
+
+		rq_stats = &c->rq.stats;
 
 		s->rx_packets	+= rq_stats->packets;
 		s->rx_bytes	+= rq_stats->bytes;
 
-		for (j = 0; j < priv->params.num_tc; j++) {
-			sq_stats = &priv->channel[i]->sq[j].stats;
+		for (j = 0; j < priv->channels.params.num_tc; j++) {
+			sq_stats = &c->sq[j].stats;
 
 			s->tx_packets		+= sq_stats->packets;
 			s->tx_bytes		+= sq_stats->bytes;
@@ -187,22 +189,26 @@ int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv)
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5_eswitch_rep *rep = priv->ppriv;
 	struct mlx5e_channel *c;
-	int n, tc, err, num_sqs = 0;
+	int n, tc, num_sqs = 0;
+	int err = -ENOMEM;
 	u16 *sqs;
 
-	sqs = kcalloc(priv->params.num_channels * priv->params.num_tc, sizeof(u16), GFP_KERNEL);
+	sqs = kcalloc(priv->channels.num * priv->channels.params.num_tc, sizeof(u16), GFP_KERNEL);
 	if (!sqs)
-		return -ENOMEM;
+		goto out;
 
-	for (n = 0; n < priv->params.num_channels; n++) {
-		c = priv->channel[n];
+	for (n = 0; n < priv->channels.num; n++) {
+		c = priv->channels.c[n];
 		for (tc = 0; tc < c->num_tc; tc++)
 			sqs[num_sqs++] = c->sq[tc].sqn;
 	}
 
 	err = mlx5_eswitch_sqs2vport_start(esw, rep, sqs, num_sqs);
-
 	kfree(sqs);
+
+out:
+	if (err)
+		netdev_warn(priv->netdev, "Failed to add SQs FWD rules %d\n", err);
 	return err;
 }
 
@@ -397,42 +403,23 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = {
 	.ndo_get_offload_stats	 = mlx5e_get_offload_stats,
 };
 
-static void mlx5e_build_rep_netdev_priv(struct mlx5_core_dev *mdev,
-					struct net_device *netdev,
-					const struct mlx5e_profile *profile,
-					void *ppriv)
+static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
+				   struct mlx5e_params *params)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
 	u8 cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
 					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
 					 MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 
-	priv->params.log_sq_size           =
-		MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
-	priv->params.rq_wq_type = MLX5_WQ_TYPE_LINKED_LIST;
-	priv->params.log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
-
-	priv->params.min_rx_wqes = mlx5_min_rx_wqes(priv->params.rq_wq_type,
-					    BIT(priv->params.log_rq_size));
-
-	priv->params.rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
-	mlx5e_set_rx_cq_mode_params(&priv->params, cq_period_mode);
+	params->log_sq_size = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+	params->rq_wq_type  = MLX5_WQ_TYPE_LINKED_LIST;
+	params->log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
 
-	priv->params.tx_max_inline         = mlx5e_get_max_inline_cap(mdev);
-	priv->params.num_tc                = 1;
+	params->rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
 
-	priv->params.lro_wqe_sz            =
-		MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
-
-	priv->mdev                         = mdev;
-	priv->netdev                       = netdev;
-	priv->params.num_channels          = profile->max_nch(mdev);
-	priv->profile                      = profile;
-	priv->ppriv                        = ppriv;
-
-	mutex_init(&priv->state_lock);
-
-	INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work);
+	params->tx_max_inline         = mlx5e_get_max_inline_cap(mdev);
+	params->num_tc                = 1;
+	params->lro_wqe_sz            = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
 }
 
 static void mlx5e_build_rep_netdev(struct net_device *netdev)
@@ -458,7 +445,19 @@ static void mlx5e_init_rep(struct mlx5_core_dev *mdev,
 			   const struct mlx5e_profile *profile,
 			   void *ppriv)
 {
-	mlx5e_build_rep_netdev_priv(mdev, netdev, profile, ppriv);
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	priv->mdev                         = mdev;
+	priv->netdev                       = netdev;
+	priv->profile                      = profile;
+	priv->ppriv                        = ppriv;
+
+	mutex_init(&priv->state_lock);
+
+	INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work);
+
+	priv->channels.params.num_channels = profile->max_nch(mdev);
+	mlx5e_build_rep_params(mdev, &priv->channels.params);
 	mlx5e_build_rep_netdev(netdev);
 }
 
@@ -503,7 +502,7 @@ err_del_flow_rule:
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv);
 err_destroy_direct_rqts:
-	for (i = 0; i < priv->params.num_channels; i++)
+	for (i = 0; i < priv->channels.params.num_channels; i++)
 		mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
 	return err;
 }
@@ -516,7 +515,7 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 	mlx5e_tc_cleanup(priv);
 	mlx5_del_flow_rules(rep->vport_rx_rule);
 	mlx5e_destroy_direct_tirs(priv);
-	for (i = 0; i < priv->params.num_channels; i++)
+	for (i = 0; i < priv->channels.params.num_channels; i++)
 		mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index bafcb349a50c..1a9532b31635 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -156,28 +156,6 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq,
 	return mlx5e_decompress_cqes_cont(rq, cq, 1, budget_rem) - 1;
 }
 
-void mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val)
-{
-	bool was_opened;
-
-	if (!MLX5_CAP_GEN(priv->mdev, cqe_compression))
-		return;
-
-	if (MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS) == val)
-		return;
-
-	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (was_opened)
-		mlx5e_close_locked(priv->netdev);
-
-	MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS, val);
-	mlx5e_set_rq_type_params(priv, priv->params.rq_wq_type);
-
-	if (was_opened)
-		mlx5e_open_locked(priv->netdev);
-
-}
-
 #define RQ_PAGE_SIZE(rq) ((1 << rq->buff.page_order) << PAGE_SHIFT)
 
 static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq,
@@ -331,7 +309,7 @@ mlx5e_copy_skb_header_mpwqe(struct device *pdev,
 static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
 {
 	struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
-	struct mlx5e_sq *sq = &rq->channel->icosq;
+	struct mlx5e_icosq *sq = &rq->channel->icosq;
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	struct mlx5e_umr_wqe *wqe;
 	u8 num_wqebbs = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_BB);
@@ -341,7 +319,7 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
 	while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) {
 		sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
 		sq->db.ico_wqe[pi].num_wqebbs = 1;
-		mlx5e_send_nop(sq, false);
+		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
 	}
 
 	wqe = mlx5_wq_cyc_get_wqe(wq, pi);
@@ -353,7 +331,7 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
 	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
 	sq->db.ico_wqe[pi].num_wqebbs = num_wqebbs;
 	sq->pc += num_wqebbs;
-	mlx5e_tx_notify_hw(sq, &wqe->ctrl, 0);
+	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &wqe->ctrl);
 }
 
 static int mlx5e_alloc_rx_umr_mpwqe(struct mlx5e_rq *rq,
@@ -637,37 +615,36 @@ 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_sq *sq)
+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 = (sq->pc - MLX5E_XDP_TX_WQEBBS) & wq->sz_m1; /* last pi */
+	u16 pi = (sq->pc - 1) & wq->sz_m1; /* last pi */
 
 	wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
 
-	wqe->ctrl.fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
-	mlx5e_tx_notify_hw(sq, &wqe->ctrl, 0);
+	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_sq          *sq   = &rq->channel->xdp_sq;
+	struct mlx5e_xdpsq       *sq   = &rq->xdpsq;
 	struct mlx5_wq_cyc       *wq   = &sq->wq;
-	u16                      pi    = sq->pc & wq->sz_m1;
+	u16                       pi   = sq->pc & wq->sz_m1;
 	struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
-	struct mlx5e_sq_wqe_info *wi   = &sq->db.xdp.wqe_info[pi];
 
 	struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
 	struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
 	struct mlx5_wqe_data_seg *dseg;
-	u8 ds_cnt = MLX5E_XDP_TX_DS_COUNT;
 
 	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;
 
+	prefetchw(wqe);
+
 	if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE ||
 		     MLX5E_SW2HW_MTU(rq->netdev->mtu) < dma_len)) {
 		rq->stats.xdp_drop++;
@@ -675,48 +652,42 @@ static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq,
 		return false;
 	}
 
-	if (unlikely(!mlx5e_sq_has_room_for(sq, MLX5E_XDP_TX_WQEBBS))) {
-		if (sq->db.xdp.doorbell) {
+	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.xdp.doorbell = false;
+			sq->db.doorbell = false;
 		}
 		rq->stats.xdp_tx_full++;
 		mlx5e_page_release(rq, di, true);
 		return false;
 	}
 
-	dma_sync_single_for_device(sq->pdev, dma_addr, dma_len,
-				   PCI_DMA_TODEVICE);
+	dma_sync_single_for_device(sq->pdev, dma_addr, dma_len, PCI_DMA_TODEVICE);
 
-	memset(wqe, 0, sizeof(*wqe));
+	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;
-
-		ds_cnt   += MLX5E_XDP_IHS_DS_COUNT;
 		dseg++;
 	}
 
 	/* write the dma part */
 	dseg->addr       = cpu_to_be64(dma_addr);
 	dseg->byte_count = cpu_to_be32(dma_len);
-	dseg->lkey       = sq->mkey_be;
 
 	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND);
-	cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
 
-	sq->db.xdp.di[pi] = *di;
-	wi->opcode     = MLX5_OPCODE_SEND;
-	wi->num_wqebbs = MLX5E_XDP_TX_WQEBBS;
-	sq->pc += MLX5E_XDP_TX_WQEBBS;
+	sq->db.di[pi] = *di;
+	sq->pc++;
 
-	sq->db.xdp.doorbell = true;
+	sq->db.doorbell = true;
 	rq->stats.xdp_tx++;
 	return true;
 }
@@ -950,7 +921,7 @@ mpwrq_cqe_out:
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 {
 	struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
-	struct mlx5e_sq *xdp_sq = &rq->channel->xdp_sq;
+	struct mlx5e_xdpsq *xdpsq = &rq->xdpsq;
 	int work_done = 0;
 
 	if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
@@ -977,9 +948,9 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 		rq->handle_rx_cqe(rq, cqe);
 	}
 
-	if (xdp_sq->db.xdp.doorbell) {
-		mlx5e_xmit_xdp_doorbell(xdp_sq);
-		xdp_sq->db.xdp.doorbell = false;
+	if (xdpsq->db.doorbell) {
+		mlx5e_xmit_xdp_doorbell(xdpsq);
+		xdpsq->db.doorbell = false;
 	}
 
 	mlx5_cqwq_update_db_record(&cq->wq);
@@ -989,3 +960,74 @@ 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 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;
+
+	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;
+
+	for (i = 0; i < MLX5E_TX_CQ_POLL_BUDGET; i++) {
+		struct mlx5_cqe64 *cqe;
+		u16 wqe_counter;
+		bool last_wqe;
+
+		cqe = mlx5e_get_cqe(cq);
+		if (!cqe)
+			break;
+
+		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 = sqcc & sq->wq.sz_m1;
+			di = &sq->db.di[ci];
+
+			sqcc++;
+			/* Recycle RX page */
+			mlx5e_page_release(rq, di, true);
+		} while (!last_wqe);
+	}
+
+	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 = sq->cc & sq->wq.sz_m1;
+		di = &sq->db.di[ci];
+		sq->cc++;
+
+		mlx5e_page_release(rq, di, false);
+	}
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
index cbfac06b7ffd..02dd3a95ed8f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
@@ -293,7 +293,7 @@ void mlx5e_rx_am_work(struct work_struct *work)
 	struct mlx5e_rq *rq = container_of(am, struct mlx5e_rq, am);
 	struct mlx5e_cq_moder cur_profile = profile[am->mode][am->profile_ix];
 
-	mlx5_core_modify_cq_moderation(rq->priv->mdev, &rq->cq.mcq,
+	mlx5_core_modify_cq_moderation(rq->mdev, &rq->cq.mcq,
 				       cur_profile.usec, cur_profile.pkts);
 
 	am->state = MLX5E_AM_START_MEASURE;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 5621dcfda4f1..5225f2226a67 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -236,12 +236,9 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv,
 {
 	int err = 0;
 
-	err = mlx5e_refresh_tirs_self_loopback(priv->mdev, true);
-	if (err) {
-		netdev_err(priv->netdev,
-			   "\tFailed to enable UC loopback err(%d)\n", err);
+	err = mlx5e_refresh_tirs(priv, true);
+	if (err)
 		return err;
-	}
 
 	lbtp->loopback_ok = false;
 	init_completion(&lbtp->comp);
@@ -258,7 +255,7 @@ static void mlx5e_test_loopback_cleanup(struct mlx5e_priv *priv,
 					struct mlx5e_lbt_priv *lbtp)
 {
 	dev_remove_pack(&lbtp->pt);
-	mlx5e_refresh_tirs_self_loopback(priv->mdev, false);
+	mlx5e_refresh_tirs(priv, false);
 }
 
 #define MLX5E_LB_VERIFY_TIMEOUT (msecs_to_jiffies(200))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index fade7233dac5..9dec11c00a49 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -42,14 +42,22 @@
 #include <net/tc_act/tc_mirred.h>
 #include <net/tc_act/tc_vlan.h>
 #include <net/tc_act/tc_tunnel_key.h>
+#include <net/tc_act/tc_pedit.h>
 #include <net/vxlan.h>
 #include "en.h"
 #include "en_tc.h"
 #include "eswitch.h"
 #include "vxlan.h"
 
+struct mlx5_nic_flow_attr {
+	u32 action;
+	u32 flow_tag;
+	u32 mod_hdr_id;
+};
+
 enum {
 	MLX5E_TC_FLOW_ESWITCH	= BIT(0),
+	MLX5E_TC_FLOW_NIC	= BIT(1),
 };
 
 struct mlx5e_tc_flow {
@@ -58,7 +66,16 @@ struct mlx5e_tc_flow {
 	u8			flags;
 	struct mlx5_flow_handle *rule;
 	struct list_head	encap; /* flows sharing the same encap */
-	struct mlx5_esw_flow_attr *attr;
+	union {
+		struct mlx5_esw_flow_attr esw_attr[0];
+		struct mlx5_nic_flow_attr nic_attr[0];
+	};
+};
+
+struct mlx5e_tc_flow_parse_attr {
+	struct mlx5_flow_spec spec;
+	int num_mod_hdr_actions;
+	void *mod_hdr_actions;
 };
 
 enum {
@@ -71,24 +88,26 @@ enum {
 
 static struct mlx5_flow_handle *
 mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
-		      struct mlx5_flow_spec *spec,
-		      u32 action, u32 flow_tag)
+		      struct mlx5e_tc_flow_parse_attr *parse_attr,
+		      struct mlx5e_tc_flow *flow)
 {
+	struct mlx5_nic_flow_attr *attr = flow->nic_attr;
 	struct mlx5_core_dev *dev = priv->mdev;
-	struct mlx5_flow_destination dest = { 0 };
+	struct mlx5_flow_destination dest = {};
 	struct mlx5_flow_act flow_act = {
-		.action = action,
-		.flow_tag = flow_tag,
+		.action = attr->action,
+		.flow_tag = attr->flow_tag,
 		.encap_id = 0,
 	};
 	struct mlx5_fc *counter = NULL;
 	struct mlx5_flow_handle *rule;
 	bool table_created = false;
+	int err;
 
-	if (action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
 		dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 		dest.ft = priv->fs.vlan.ft.t;
-	} else if (action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+	} else if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
 		counter = mlx5_fc_create(dev, true);
 		if (IS_ERR(counter))
 			return ERR_CAST(counter);
@@ -97,6 +116,19 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
 		dest.counter = counter;
 	}
 
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
+		err = mlx5_modify_header_alloc(dev, MLX5_FLOW_NAMESPACE_KERNEL,
+					       parse_attr->num_mod_hdr_actions,
+					       parse_attr->mod_hdr_actions,
+					       &attr->mod_hdr_id);
+		flow_act.modify_id = attr->mod_hdr_id;
+		kfree(parse_attr->mod_hdr_actions);
+		if (err) {
+			rule = ERR_PTR(err);
+			goto err_create_mod_hdr_id;
+		}
+	}
+
 	if (IS_ERR_OR_NULL(priv->fs.tc.t)) {
 		priv->fs.tc.t =
 			mlx5_create_auto_grouped_flow_table(priv->fs.ns,
@@ -114,8 +146,9 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
 		table_created = true;
 	}
 
-	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-	rule = mlx5_add_flow_rules(priv->fs.tc.t, spec, &flow_act, &dest, 1);
+	parse_attr->spec.match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	rule = mlx5_add_flow_rules(priv->fs.tc.t, &parse_attr->spec,
+				   &flow_act, &dest, 1);
 
 	if (IS_ERR(rule))
 		goto err_add_rule;
@@ -128,6 +161,10 @@ err_add_rule:
 		priv->fs.tc.t = NULL;
 	}
 err_create_ft:
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+		mlx5_modify_header_dealloc(priv->mdev,
+					   attr->mod_hdr_id);
+err_create_mod_hdr_id:
 	mlx5_fc_destroy(dev, counter);
 
 	return rule;
@@ -138,47 +175,85 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv,
 {
 	struct mlx5_fc *counter = NULL;
 
-	if (!IS_ERR(flow->rule)) {
-		counter = mlx5_flow_rule_counter(flow->rule);
-		mlx5_del_flow_rules(flow->rule);
-		mlx5_fc_destroy(priv->mdev, counter);
-	}
+	counter = mlx5_flow_rule_counter(flow->rule);
+	mlx5_del_flow_rules(flow->rule);
+	mlx5_fc_destroy(priv->mdev, counter);
 
 	if (!mlx5e_tc_num_filters(priv) && (priv->fs.tc.t)) {
 		mlx5_destroy_flow_table(priv->fs.tc.t);
 		priv->fs.tc.t = NULL;
 	}
+
+	if (flow->nic_attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+		mlx5_modify_header_dealloc(priv->mdev,
+					   flow->nic_attr->mod_hdr_id);
 }
 
+static void mlx5e_detach_encap(struct mlx5e_priv *priv,
+			       struct mlx5e_tc_flow *flow);
+
 static struct mlx5_flow_handle *
 mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
-		      struct mlx5_flow_spec *spec,
-		      struct mlx5_esw_flow_attr *attr)
+		      struct mlx5e_tc_flow_parse_attr *parse_attr,
+		      struct mlx5e_tc_flow *flow)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
+	struct mlx5_flow_handle *rule;
 	int err;
 
 	err = mlx5_eswitch_add_vlan_action(esw, attr);
-	if (err)
-		return ERR_PTR(err);
+	if (err) {
+		rule = ERR_PTR(err);
+		goto err_add_vlan;
+	}
 
-	return mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
-}
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
+		err = mlx5_modify_header_alloc(priv->mdev, MLX5_FLOW_NAMESPACE_FDB,
+					       parse_attr->num_mod_hdr_actions,
+					       parse_attr->mod_hdr_actions,
+					       &attr->mod_hdr_id);
+		kfree(parse_attr->mod_hdr_actions);
+		if (err) {
+			rule = ERR_PTR(err);
+			goto err_mod_hdr;
+		}
+	}
 
-static void mlx5e_detach_encap(struct mlx5e_priv *priv,
-			       struct mlx5e_tc_flow *flow);
+	rule = mlx5_eswitch_add_offloaded_rule(esw, &parse_attr->spec, attr);
+	if (IS_ERR(rule))
+		goto err_add_rule;
+
+	return rule;
+
+err_add_rule:
+	if (flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+		mlx5_modify_header_dealloc(priv->mdev,
+					   attr->mod_hdr_id);
+err_mod_hdr:
+	mlx5_eswitch_del_vlan_action(esw, attr);
+err_add_vlan:
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
+		mlx5e_detach_encap(priv, flow);
+	return rule;
+}
 
 static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 				  struct mlx5e_tc_flow *flow)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
 
-	mlx5_eswitch_del_offloaded_rule(esw, flow->rule, flow->attr);
+	mlx5_eswitch_del_offloaded_rule(esw, flow->rule, flow->esw_attr);
 
-	mlx5_eswitch_del_vlan_action(esw, flow->attr);
+	mlx5_eswitch_del_vlan_action(esw, flow->esw_attr);
 
-	if (flow->attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
+	if (flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
 		mlx5e_detach_encap(priv, flow);
+
+	if (flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+		mlx5_modify_header_dealloc(priv->mdev,
+					   attr->mod_hdr_id);
 }
 
 static void mlx5e_detach_encap(struct mlx5e_priv *priv,
@@ -200,10 +275,6 @@ static void mlx5e_detach_encap(struct mlx5e_priv *priv,
 	}
 }
 
-/* we get here also when setting rule to the FW failed, etc. It means that the
- * flow rule itself might not exist, but some offloading related to the actions
- * should be cleaned.
- */
 static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
 			      struct mlx5e_tc_flow *flow)
 {
@@ -650,29 +721,313 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
 	return err;
 }
 
+struct pedit_headers {
+	struct ethhdr  eth;
+	struct iphdr   ip4;
+	struct ipv6hdr ip6;
+	struct tcphdr  tcp;
+	struct udphdr  udp;
+};
+
+static int pedit_header_offsets[] = {
+	[TCA_PEDIT_KEY_EX_HDR_TYPE_ETH] = offsetof(struct pedit_headers, eth),
+	[TCA_PEDIT_KEY_EX_HDR_TYPE_IP4] = offsetof(struct pedit_headers, ip4),
+	[TCA_PEDIT_KEY_EX_HDR_TYPE_IP6] = offsetof(struct pedit_headers, ip6),
+	[TCA_PEDIT_KEY_EX_HDR_TYPE_TCP] = offsetof(struct pedit_headers, tcp),
+	[TCA_PEDIT_KEY_EX_HDR_TYPE_UDP] = offsetof(struct pedit_headers, udp),
+};
+
+#define pedit_header(_ph, _htype) ((void *)(_ph) + pedit_header_offsets[_htype])
+
+static int set_pedit_val(u8 hdr_type, u32 mask, u32 val, u32 offset,
+			 struct pedit_headers *masks,
+			 struct pedit_headers *vals)
+{
+	u32 *curr_pmask, *curr_pval;
+
+	if (hdr_type >= __PEDIT_HDR_TYPE_MAX)
+		goto out_err;
+
+	curr_pmask = (u32 *)(pedit_header(masks, hdr_type) + offset);
+	curr_pval  = (u32 *)(pedit_header(vals, hdr_type) + offset);
+
+	if (*curr_pmask & mask)  /* disallow acting twice on the same location */
+		goto out_err;
+
+	*curr_pmask |= mask;
+	*curr_pval  |= (val & mask);
+
+	return 0;
+
+out_err:
+	return -EOPNOTSUPP;
+}
+
+struct mlx5_fields {
+	u8  field;
+	u8  size;
+	u32 offset;
+};
+
+static struct mlx5_fields fields[] = {
+	{MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16, 4, offsetof(struct pedit_headers, eth.h_dest[0])},
+	{MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0,  2, offsetof(struct pedit_headers, eth.h_dest[4])},
+	{MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16, 4, offsetof(struct pedit_headers, eth.h_source[0])},
+	{MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0,  2, offsetof(struct pedit_headers, eth.h_source[4])},
+	{MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE,  2, offsetof(struct pedit_headers, eth.h_proto)},
+
+	{MLX5_ACTION_IN_FIELD_OUT_IP_DSCP, 1, offsetof(struct pedit_headers, ip4.tos)},
+	{MLX5_ACTION_IN_FIELD_OUT_IP_TTL,  1, offsetof(struct pedit_headers, ip4.ttl)},
+	{MLX5_ACTION_IN_FIELD_OUT_SIPV4,   4, offsetof(struct pedit_headers, ip4.saddr)},
+	{MLX5_ACTION_IN_FIELD_OUT_DIPV4,   4, offsetof(struct pedit_headers, ip4.daddr)},
+
+	{MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96, 4, offsetof(struct pedit_headers, ip6.saddr.s6_addr32[0])},
+	{MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64,  4, offsetof(struct pedit_headers, ip6.saddr.s6_addr32[1])},
+	{MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32,  4, offsetof(struct pedit_headers, ip6.saddr.s6_addr32[2])},
+	{MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0,   4, offsetof(struct pedit_headers, ip6.saddr.s6_addr32[3])},
+	{MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96, 4, offsetof(struct pedit_headers, ip6.daddr.s6_addr32[0])},
+	{MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64,  4, offsetof(struct pedit_headers, ip6.daddr.s6_addr32[1])},
+	{MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32,  4, offsetof(struct pedit_headers, ip6.daddr.s6_addr32[2])},
+	{MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0,   4, offsetof(struct pedit_headers, ip6.daddr.s6_addr32[3])},
+
+	{MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT, 2, offsetof(struct pedit_headers, tcp.source)},
+	{MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT, 2, offsetof(struct pedit_headers, tcp.dest)},
+	{MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS, 1, offsetof(struct pedit_headers, tcp.ack_seq) + 5},
+
+	{MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT, 2, offsetof(struct pedit_headers, udp.source)},
+	{MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT, 2, offsetof(struct pedit_headers, udp.dest)},
+};
+
+/* On input attr->num_mod_hdr_actions tells how many HW actions can be parsed at
+ * max from the SW pedit action. On success, it says how many HW actions were
+ * actually parsed.
+ */
+static int offload_pedit_fields(struct pedit_headers *masks,
+				struct pedit_headers *vals,
+				struct mlx5e_tc_flow_parse_attr *parse_attr)
+{
+	struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals;
+	int i, action_size, nactions, max_actions, first, last;
+	void *s_masks_p, *a_masks_p, *vals_p;
+	u32 s_mask, a_mask, val;
+	struct mlx5_fields *f;
+	u8 cmd, field_bsize;
+	unsigned long mask;
+	void *action;
+
+	set_masks = &masks[TCA_PEDIT_KEY_EX_CMD_SET];
+	add_masks = &masks[TCA_PEDIT_KEY_EX_CMD_ADD];
+	set_vals = &vals[TCA_PEDIT_KEY_EX_CMD_SET];
+	add_vals = &vals[TCA_PEDIT_KEY_EX_CMD_ADD];
+
+	action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
+	action = parse_attr->mod_hdr_actions;
+	max_actions = parse_attr->num_mod_hdr_actions;
+	nactions = 0;
+
+	for (i = 0; i < ARRAY_SIZE(fields); i++) {
+		f = &fields[i];
+		/* avoid seeing bits set from previous iterations */
+		s_mask = a_mask = mask = val = 0;
+
+		s_masks_p = (void *)set_masks + f->offset;
+		a_masks_p = (void *)add_masks + f->offset;
+
+		memcpy(&s_mask, s_masks_p, f->size);
+		memcpy(&a_mask, a_masks_p, f->size);
+
+		if (!s_mask && !a_mask) /* nothing to offload here */
+			continue;
+
+		if (s_mask && a_mask) {
+			printk(KERN_WARNING "mlx5: can't set and add to the same HW field (%x)\n", f->field);
+			return -EOPNOTSUPP;
+		}
+
+		if (nactions == max_actions) {
+			printk(KERN_WARNING "mlx5: parsed %d pedit actions, can't do more\n", nactions);
+			return -EOPNOTSUPP;
+		}
+
+		if (s_mask) {
+			cmd  = MLX5_ACTION_TYPE_SET;
+			mask = s_mask;
+			vals_p = (void *)set_vals + f->offset;
+			/* clear to denote we consumed this field */
+			memset(s_masks_p, 0, f->size);
+		} else {
+			cmd  = MLX5_ACTION_TYPE_ADD;
+			mask = a_mask;
+			vals_p = (void *)add_vals + f->offset;
+			/* clear to denote we consumed this field */
+			memset(a_masks_p, 0, f->size);
+		}
+
+		memcpy(&val, vals_p, f->size);
+
+		field_bsize = f->size * BITS_PER_BYTE;
+		first = find_first_bit(&mask, field_bsize);
+		last  = find_last_bit(&mask, field_bsize);
+		if (first > 0 || last != (field_bsize - 1)) {
+			printk(KERN_WARNING "mlx5: partial rewrite (mask %lx) is currently not offloaded\n",
+			       mask);
+			return -EOPNOTSUPP;
+		}
+
+		MLX5_SET(set_action_in, action, action_type, cmd);
+		MLX5_SET(set_action_in, action, field, f->field);
+
+		if (cmd == MLX5_ACTION_TYPE_SET) {
+			MLX5_SET(set_action_in, action, offset, 0);
+			/* length is num of bits to be written, zero means length of 32 */
+			MLX5_SET(set_action_in, action, length, field_bsize);
+		}
+
+		if (field_bsize == 32)
+			MLX5_SET(set_action_in, action, data, ntohl(val));
+		else if (field_bsize == 16)
+			MLX5_SET(set_action_in, action, data, ntohs(val));
+		else if (field_bsize == 8)
+			MLX5_SET(set_action_in, action, data, val);
+
+		action += action_size;
+		nactions++;
+	}
+
+	parse_attr->num_mod_hdr_actions = nactions;
+	return 0;
+}
+
+static int alloc_mod_hdr_actions(struct mlx5e_priv *priv,
+				 const struct tc_action *a, int namespace,
+				 struct mlx5e_tc_flow_parse_attr *parse_attr)
+{
+	int nkeys, action_size, max_actions;
+
+	nkeys = tcf_pedit_nkeys(a);
+	action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
+
+	if (namespace == MLX5_FLOW_NAMESPACE_FDB) /* FDB offloading */
+		max_actions = MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, max_modify_header_actions);
+	else /* namespace is MLX5_FLOW_NAMESPACE_KERNEL - NIC offloading */
+		max_actions = MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, max_modify_header_actions);
+
+	/* can get up to crazingly 16 HW actions in 32 bits pedit SW key */
+	max_actions = min(max_actions, nkeys * 16);
+
+	parse_attr->mod_hdr_actions = kcalloc(max_actions, action_size, GFP_KERNEL);
+	if (!parse_attr->mod_hdr_actions)
+		return -ENOMEM;
+
+	parse_attr->num_mod_hdr_actions = max_actions;
+	return 0;
+}
+
+static const struct pedit_headers zero_masks = {};
+
+static int parse_tc_pedit_action(struct mlx5e_priv *priv,
+				 const struct tc_action *a, int namespace,
+				 struct mlx5e_tc_flow_parse_attr *parse_attr)
+{
+	struct pedit_headers masks[__PEDIT_CMD_MAX], vals[__PEDIT_CMD_MAX], *cmd_masks;
+	int nkeys, i, err = -EOPNOTSUPP;
+	u32 mask, val, offset;
+	u8 cmd, htype;
+
+	nkeys = tcf_pedit_nkeys(a);
+
+	memset(masks, 0, sizeof(struct pedit_headers) * __PEDIT_CMD_MAX);
+	memset(vals,  0, sizeof(struct pedit_headers) * __PEDIT_CMD_MAX);
+
+	for (i = 0; i < nkeys; i++) {
+		htype = tcf_pedit_htype(a, i);
+		cmd = tcf_pedit_cmd(a, i);
+		err = -EOPNOTSUPP; /* can't be all optimistic */
+
+		if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK) {
+			printk(KERN_WARNING "mlx5: legacy pedit isn't offloaded\n");
+			goto out_err;
+		}
+
+		if (cmd != TCA_PEDIT_KEY_EX_CMD_SET && cmd != TCA_PEDIT_KEY_EX_CMD_ADD) {
+			printk(KERN_WARNING "mlx5: pedit cmd %d isn't offloaded\n", cmd);
+			goto out_err;
+		}
+
+		mask = tcf_pedit_mask(a, i);
+		val = tcf_pedit_val(a, i);
+		offset = tcf_pedit_offset(a, i);
+
+		err = set_pedit_val(htype, ~mask, val, offset, &masks[cmd], &vals[cmd]);
+		if (err)
+			goto out_err;
+	}
+
+	err = alloc_mod_hdr_actions(priv, a, namespace, parse_attr);
+	if (err)
+		goto out_err;
+
+	err = offload_pedit_fields(masks, vals, parse_attr);
+	if (err < 0)
+		goto out_dealloc_parsed_actions;
+
+	for (cmd = 0; cmd < __PEDIT_CMD_MAX; cmd++) {
+		cmd_masks = &masks[cmd];
+		if (memcmp(cmd_masks, &zero_masks, sizeof(zero_masks))) {
+			printk(KERN_WARNING "mlx5: attempt to offload an unsupported field (cmd %d)\n",
+			       cmd);
+			print_hex_dump(KERN_WARNING, "mask: ", DUMP_PREFIX_ADDRESS,
+				       16, 1, cmd_masks, sizeof(zero_masks), true);
+			err = -EOPNOTSUPP;
+			goto out_dealloc_parsed_actions;
+		}
+	}
+
+	return 0;
+
+out_dealloc_parsed_actions:
+	kfree(parse_attr->mod_hdr_actions);
+out_err:
+	return err;
+}
+
 static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
-				u32 *action, u32 *flow_tag)
+				struct mlx5e_tc_flow_parse_attr *parse_attr,
+				struct mlx5e_tc_flow *flow)
 {
+	struct mlx5_nic_flow_attr *attr = flow->nic_attr;
 	const struct tc_action *a;
 	LIST_HEAD(actions);
+	int err;
 
 	if (tc_no_actions(exts))
 		return -EINVAL;
 
-	*flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
-	*action = 0;
+	attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
+	attr->action = 0;
 
 	tcf_exts_to_list(exts, &actions);
 	list_for_each_entry(a, &actions, list) {
 		/* Only support a single action per rule */
-		if (*action)
+		if (attr->action)
 			return -EINVAL;
 
 		if (is_tcf_gact_shot(a)) {
-			*action |= MLX5_FLOW_CONTEXT_ACTION_DROP;
+			attr->action |= MLX5_FLOW_CONTEXT_ACTION_DROP;
 			if (MLX5_CAP_FLOWTABLE(priv->mdev,
 					       flow_table_properties_nic_receive.flow_counter))
-				*action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
+				attr->action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
+			continue;
+		}
+
+		if (is_tcf_pedit(a)) {
+			err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_KERNEL,
+						    parse_attr);
+			if (err)
+				return err;
+
+			attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
+					MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 			continue;
 		}
 
@@ -685,8 +1040,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				return -EINVAL;
 			}
 
-			*flow_tag = mark;
-			*action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+			attr->flow_tag = mark;
+			attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 			continue;
 		}
 
@@ -1071,9 +1426,10 @@ out_err:
 }
 
 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)
 {
-	struct mlx5_esw_flow_attr *attr = flow->attr;
+	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
 	struct ip_tunnel_info *info = NULL;
 	const struct tc_action *a;
 	LIST_HEAD(actions);
@@ -1094,6 +1450,16 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 			continue;
 		}
 
+		if (is_tcf_pedit(a)) {
+			err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_FDB,
+						    parse_attr);
+			if (err)
+				return err;
+
+			attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+			continue;
+		}
+
 		if (is_tcf_mirred_egress_redirect(a)) {
 			int ifindex = tcf_mirred_ifindex(a);
 			struct net_device *out_dev;
@@ -1163,22 +1529,24 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
 			   struct tc_cls_flower_offload *f)
 {
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5e_tc_table *tc = &priv->fs.tc;
-	int err, attr_size = 0;
-	u32 flow_tag, action;
 	struct mlx5e_tc_flow *flow;
-	struct mlx5_flow_spec *spec;
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	int attr_size, err = 0;
 	u8 flow_flags = 0;
 
 	if (esw && esw->mode == SRIOV_OFFLOADS) {
 		flow_flags = MLX5E_TC_FLOW_ESWITCH;
 		attr_size  = sizeof(struct mlx5_esw_flow_attr);
+	} else {
+		flow_flags = MLX5E_TC_FLOW_NIC;
+		attr_size  = sizeof(struct mlx5_nic_flow_attr);
 	}
 
 	flow = kzalloc(sizeof(*flow) + attr_size, GFP_KERNEL);
-	spec = mlx5_vzalloc(sizeof(*spec));
-	if (!spec || !flow) {
+	parse_attr = mlx5_vzalloc(sizeof(*parse_attr));
+	if (!parse_attr || !flow) {
 		err = -ENOMEM;
 		goto err_free;
 	}
@@ -1186,26 +1554,25 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
 	flow->cookie = f->cookie;
 	flow->flags = flow_flags;
 
-	err = parse_cls_flower(priv, flow, spec, f);
+	err = parse_cls_flower(priv, flow, &parse_attr->spec, f);
 	if (err < 0)
 		goto err_free;
 
 	if (flow->flags & MLX5E_TC_FLOW_ESWITCH) {
-		flow->attr  = (struct mlx5_esw_flow_attr *)(flow + 1);
-		err = parse_tc_fdb_actions(priv, f->exts, flow);
+		err = parse_tc_fdb_actions(priv, f->exts, parse_attr, flow);
 		if (err < 0)
 			goto err_free;
-		flow->rule = mlx5e_tc_add_fdb_flow(priv, spec, flow->attr);
+		flow->rule = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow);
 	} else {
-		err = parse_tc_nic_actions(priv, f->exts, &action, &flow_tag);
+		err = parse_tc_nic_actions(priv, f->exts, parse_attr, flow);
 		if (err < 0)
 			goto err_free;
-		flow->rule = mlx5e_tc_add_nic_flow(priv, spec, action, flow_tag);
+		flow->rule = mlx5e_tc_add_nic_flow(priv, parse_attr, flow);
 	}
 
 	if (IS_ERR(flow->rule)) {
 		err = PTR_ERR(flow->rule);
-		goto err_del_rule;
+		goto err_free;
 	}
 
 	err = rhashtable_insert_fast(&tc->ht, &flow->node,
@@ -1221,7 +1588,7 @@ err_del_rule:
 err_free:
 	kfree(flow);
 out:
-	kvfree(spec);
+	kvfree(parse_attr);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 57f5e2d7ebd1..5bbc313e70c5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -38,29 +38,6 @@
 #define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\
 			    MLX5E_SQ_NOPS_ROOM)
 
-void mlx5e_send_nop(struct mlx5e_sq *sq, bool notify_hw)
-{
-	struct mlx5_wq_cyc                *wq  = &sq->wq;
-
-	u16 pi = sq->pc & wq->sz_m1;
-	struct mlx5e_tx_wqe              *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
-
-	struct mlx5_wqe_ctrl_seg         *cseg = &wqe->ctrl;
-
-	memset(cseg, 0, sizeof(*cseg));
-
-	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_NOP);
-	cseg->qpn_ds           = cpu_to_be32((sq->sqn << 8) | 0x01);
-
-	sq->pc++;
-	sq->stats.nop++;
-
-	if (notify_hw) {
-		cseg->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
-		mlx5e_tx_notify_hw(sq, &wqe->ctrl, 0);
-	}
-}
-
 static inline void mlx5e_tx_dma_unmap(struct device *pdev,
 				      struct mlx5e_sq_dma *dma)
 {
@@ -76,25 +53,25 @@ static inline void mlx5e_tx_dma_unmap(struct device *pdev,
 	}
 }
 
-static inline void mlx5e_dma_push(struct mlx5e_sq *sq,
+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.txq.dma_fifo[i].addr = addr;
-	sq->db.txq.dma_fifo[i].size = size;
-	sq->db.txq.dma_fifo[i].type = map_type;
+	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++;
 }
 
-static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_sq *sq, u32 i)
+static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_txqsq *sq, u32 i)
 {
-	return &sq->db.txq.dma_fifo[i & sq->dma_fifo_mask];
+	return &sq->db.dma_fifo[i & sq->dma_fifo_mask];
 }
 
-static void mlx5e_dma_unmap_wqe_err(struct mlx5e_sq *sq, u8 num_dma)
+static void mlx5e_dma_unmap_wqe_err(struct mlx5e_txqsq *sq, u8 num_dma)
 {
 	int i;
 
@@ -111,6 +88,7 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	int channel_ix = fallback(dev, skb);
+	u16 num_channels;
 	int up = 0;
 
 	if (!netdev_get_num_tc(dev))
@@ -122,11 +100,11 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 	/* channel_ix can be larger than num_channels since
 	 * dev->num_real_tx_queues = num_channels * num_tc
 	 */
-	if (channel_ix >= priv->params.num_channels)
-		channel_ix = reciprocal_scale(channel_ix,
-					      priv->params.num_channels);
+	num_channels = priv->channels.params.num_channels;
+	if (channel_ix >= num_channels)
+		channel_ix = reciprocal_scale(channel_ix, num_channels);
 
-	return priv->channeltc_to_txq_map[channel_ix][up];
+	return priv->channel_tc2txq[channel_ix][up];
 }
 
 static inline int mlx5e_skb_l2_header_offset(struct sk_buff *skb)
@@ -175,25 +153,6 @@ static inline unsigned int mlx5e_calc_min_inline(enum mlx5_inline_modes mode,
 	}
 }
 
-static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq,
-					    struct sk_buff *skb, bool bf)
-{
-	/* Some NIC TX decisions, e.g loopback, are based on the packet
-	 * headers and occur before the data gather.
-	 * Therefore these headers must be copied into the WQE
-	 */
-	if (bf) {
-		u16 ihs = skb_headlen(skb);
-
-		if (skb_vlan_tag_present(skb))
-			ihs += VLAN_HLEN;
-
-		if (ihs <= sq->max_inline)
-			return skb_headlen(skb);
-	}
-	return mlx5e_calc_min_inline(sq->min_inline_mode, skb);
-}
-
 static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data,
 					    unsigned int *skb_len,
 					    unsigned int len)
@@ -218,13 +177,13 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs,
 	mlx5e_tx_skb_pull_inline(skb_data, skb_len, cpy2_sz);
 }
 
-static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
+static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb)
 {
 	struct mlx5_wq_cyc       *wq   = &sq->wq;
 
 	u16 pi = sq->pc & wq->sz_m1;
 	struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
-	struct mlx5e_tx_wqe_info *wi   = &sq->db.txq.wqe_info[pi];
+	struct mlx5e_tx_wqe_info *wi   = &sq->db.wqe_info[pi];
 
 	struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
 	struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
@@ -235,7 +194,6 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 	u8  opcode = MLX5_OPCODE_SEND;
 	dma_addr_t dma_addr = 0;
 	unsigned int num_bytes;
-	bool bf = false;
 	u16 headlen;
 	u16 ds_cnt;
 	u16 ihs;
@@ -255,11 +213,6 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 	} else
 		sq->stats.csum_none++;
 
-	if (sq->cc != sq->prev_cc) {
-		sq->prev_cc = sq->cc;
-		sq->bf_budget = (sq->cc == sq->pc) ? MLX5E_SQ_BF_BUDGET : 0;
-	}
-
 	if (skb_is_gso(skb)) {
 		eseg->mss    = cpu_to_be16(skb_shinfo(skb)->gso_size);
 		opcode       = MLX5_OPCODE_LSO;
@@ -277,10 +230,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 		sq->stats.packets += skb_shinfo(skb)->gso_segs;
 		num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
 	} else {
-		bf = sq->bf_budget &&
-		     !skb->xmit_more &&
-		     !skb_shinfo(skb)->nr_frags;
-		ihs = mlx5e_get_inline_hdr_size(sq, skb, bf);
+		ihs = mlx5e_calc_min_inline(sq->min_inline_mode, skb);
 		sq->stats.packets++;
 		num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
 	}
@@ -349,7 +299,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | opcode);
 	cseg->qpn_ds           = cpu_to_be32((sq->sqn << 8) | ds_cnt);
 
-	sq->db.txq.skb[pi] = skb;
+	sq->db.skb[pi] = skb;
 
 	wi->num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
 	sq->pc += wi->num_wqebbs;
@@ -359,31 +309,23 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 
-	if (unlikely(!mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM))) {
+	if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc,
+					     MLX5E_SQ_STOP_ROOM))) {
 		netif_tx_stop_queue(sq->txq);
 		sq->stats.stopped++;
 	}
 
 	sq->stats.xmit_more += skb->xmit_more;
-	if (!skb->xmit_more || netif_xmit_stopped(sq->txq)) {
-		int bf_sz = 0;
-
-		if (bf && test_bit(MLX5E_SQ_STATE_BF_ENABLE, &sq->state))
-			bf_sz = wi->num_wqebbs << 3;
-
-		cseg->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
-		mlx5e_tx_notify_hw(sq, &wqe->ctrl, bf_sz);
-	}
+	if (!skb->xmit_more || netif_xmit_stopped(sq->txq))
+		mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg);
 
 	/* fill sq edge with nops to avoid wqe wrap around */
 	while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) {
-		sq->db.txq.skb[pi] = NULL;
-		mlx5e_send_nop(sq, false);
+		sq->db.skb[pi] = NULL;
+		mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc);
+		sq->stats.nop++;
 	}
 
-	if (bf)
-		sq->bf_budget--;
-
 	return NETDEV_TX_OK;
 
 dma_unmap_wqe_err:
@@ -398,21 +340,21 @@ dma_unmap_wqe_err:
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_sq *sq = priv->txq_to_sq_map[skb_get_queue_mapping(skb)];
+	struct mlx5e_txqsq *sq = priv->txq2sq[skb_get_queue_mapping(skb)];
 
 	return mlx5e_sq_xmit(sq, skb);
 }
 
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 {
-	struct mlx5e_sq *sq;
+	struct mlx5e_txqsq *sq;
 	u32 dma_fifo_cc;
 	u32 nbytes;
 	u16 npkts;
 	u16 sqcc;
 	int i;
 
-	sq = container_of(cq, struct mlx5e_sq, cq);
+	sq = container_of(cq, struct mlx5e_txqsq, cq);
 
 	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
 		return false;
@@ -450,8 +392,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 			last_wqe = (sqcc == wqe_counter);
 
 			ci = sqcc & sq->wq.sz_m1;
-			skb = sq->db.txq.skb[ci];
-			wi = &sq->db.txq.wqe_info[ci];
+			skb = sq->db.skb[ci];
+			wi = &sq->db.wqe_info[ci];
 
 			if (unlikely(!skb)) { /* nop */
 				sqcc++;
@@ -492,7 +434,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 	netdev_tx_completed_queue(sq->txq, npkts, nbytes);
 
 	if (netif_tx_queue_stopped(sq->txq) &&
-	    mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM)) {
+	    mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, MLX5E_SQ_STOP_ROOM)) {
 		netif_tx_wake_queue(sq->txq);
 		sq->stats.wake++;
 	}
@@ -500,7 +442,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 	return (i == MLX5E_TX_CQ_POLL_BUDGET);
 }
 
-static void mlx5e_free_txq_sq_descs(struct mlx5e_sq *sq)
+void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 {
 	struct mlx5e_tx_wqe_info *wi;
 	struct sk_buff *skb;
@@ -509,8 +451,8 @@ static void mlx5e_free_txq_sq_descs(struct mlx5e_sq *sq)
 
 	while (sq->cc != sq->pc) {
 		ci = sq->cc & sq->wq.sz_m1;
-		skb = sq->db.txq.skb[ci];
-		wi = &sq->db.txq.wqe_info[ci];
+		skb = sq->db.skb[ci];
+		wi = &sq->db.wqe_info[ci];
 
 		if (!skb) { /* nop */
 			sq->cc++;
@@ -528,37 +470,3 @@ static void mlx5e_free_txq_sq_descs(struct mlx5e_sq *sq)
 		sq->cc += wi->num_wqebbs;
 	}
 }
-
-static void mlx5e_free_xdp_sq_descs(struct mlx5e_sq *sq)
-{
-	struct mlx5e_sq_wqe_info *wi;
-	struct mlx5e_dma_info *di;
-	u16 ci;
-
-	while (sq->cc != sq->pc) {
-		ci = sq->cc & sq->wq.sz_m1;
-		di = &sq->db.xdp.di[ci];
-		wi = &sq->db.xdp.wqe_info[ci];
-
-		if (wi->opcode == MLX5_OPCODE_NOP) {
-			sq->cc++;
-			continue;
-		}
-
-		sq->cc += wi->num_wqebbs;
-
-		mlx5e_page_release(&sq->channel->rq, di, false);
-	}
-}
-
-void mlx5e_free_sq_descs(struct mlx5e_sq *sq)
-{
-	switch (sq->type) {
-	case MLX5E_SQ_TXQ:
-		mlx5e_free_txq_sq_descs(sq);
-		break;
-	case MLX5E_SQ_XDP:
-		mlx5e_free_xdp_sq_descs(sq);
-		break;
-	}
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index e5c12a732aa1..43729ec35dfc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -44,14 +44,14 @@ struct mlx5_cqe64 *mlx5e_get_cqe(struct mlx5e_cq *cq)
 		return NULL;
 
 	/* ensure cqe content is read after cqe ownership bit */
-	rmb();
+	dma_rmb();
 
 	return cqe;
 }
 
 static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 {
-	struct mlx5e_sq *sq = container_of(cq, struct mlx5e_sq, cq);
+	struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq);
 	struct mlx5_wq_cyc *wq;
 	struct mlx5_cqe64 *cqe;
 	u16 sqcc;
@@ -105,66 +105,6 @@ static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 	sq->cc = sqcc;
 }
 
-static inline bool mlx5e_poll_xdp_tx_cq(struct mlx5e_cq *cq)
-{
-	struct mlx5e_sq *sq;
-	u16 sqcc;
-	int i;
-
-	sq = container_of(cq, struct mlx5e_sq, cq);
-
-	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
-		return false;
-
-	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
-	 * otherwise a cq overrun may occur
-	 */
-	sqcc = sq->cc;
-
-	for (i = 0; i < MLX5E_TX_CQ_POLL_BUDGET; i++) {
-		struct mlx5_cqe64 *cqe;
-		u16 wqe_counter;
-		bool last_wqe;
-
-		cqe = mlx5e_get_cqe(cq);
-		if (!cqe)
-			break;
-
-		mlx5_cqwq_pop(&cq->wq);
-
-		wqe_counter = be16_to_cpu(cqe->wqe_counter);
-
-		do {
-			struct mlx5e_sq_wqe_info *wi;
-			struct mlx5e_dma_info *di;
-			u16 ci;
-
-			last_wqe = (sqcc == wqe_counter);
-
-			ci = sqcc & sq->wq.sz_m1;
-			di = &sq->db.xdp.di[ci];
-			wi = &sq->db.xdp.wqe_info[ci];
-
-			if (unlikely(wi->opcode == MLX5_OPCODE_NOP)) {
-				sqcc++;
-				continue;
-			}
-
-			sqcc += wi->num_wqebbs;
-			/* Recycle RX page */
-			mlx5e_page_release(&sq->channel->rq, di, true);
-		} while (!last_wqe);
-	}
-
-	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);
-}
-
 int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel,
@@ -178,12 +118,12 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	for (i = 0; i < c->num_tc; i++)
 		busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget);
 
+	if (c->xdp)
+		busy |= mlx5e_poll_xdpsq_cq(&c->rq.xdpsq.cq);
+
 	work_done = mlx5e_poll_rx_cq(&c->rq.cq, budget);
 	busy |= work_done == budget;
 
-	if (c->xdp)
-		busy |= mlx5e_poll_xdp_tx_cq(&c->xdp_sq.cq);
-
 	mlx5e_poll_ico_cq(&c->icosq.cq);
 
 	busy |= mlx5e_post_rx_wqes(&c->rq);
@@ -224,8 +164,7 @@ void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event)
 {
 	struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
 	struct mlx5e_channel *c = cq->channel;
-	struct mlx5e_priv *priv = c->priv;
-	struct net_device *netdev = priv->netdev;
+	struct net_device *netdev = c->netdev;
 
 	netdev_err(netdev, "%s: cqn=0x%.6x event=0x%.2x\n",
 		   __func__, mcq->cqn, event);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index ad329b1680b4..1f56ed9f5a6f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -285,8 +285,8 @@ enum {
 	SET_VLAN_INSERT	= BIT(1)
 };
 
-#define MLX5_FLOW_CONTEXT_ACTION_VLAN_POP  0x40
-#define MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH 0x80
+#define MLX5_FLOW_CONTEXT_ACTION_VLAN_POP  0x4000
+#define MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH 0x8000
 
 struct mlx5_encap_entry {
 	struct hlist_node encap_hlist;
@@ -308,6 +308,7 @@ struct mlx5_esw_flow_attr {
 	u16	vlan;
 	bool	vlan_handled;
 	struct mlx5_encap_entry *encap;
+	u32	mod_hdr_id;
 };
 
 int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 307ec6c5fd3b..fff962dac8e3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -68,8 +68,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 	}
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
 		counter = mlx5_fc_create(esw->dev, true);
-		if (IS_ERR(counter))
-			return ERR_CAST(counter);
+		if (IS_ERR(counter)) {
+			rule = ERR_CAST(counter);
+			goto err_counter_alloc;
+		}
 		dest[i].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
 		dest[i].counter = counter;
 		i++;
@@ -86,17 +88,25 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP)
 		spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS;
 
-	if (attr->encap)
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+		flow_act.modify_id = attr->mod_hdr_id;
+
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
 		flow_act.encap_id = attr->encap->encap_id;
 
 	rule = mlx5_add_flow_rules((struct mlx5_flow_table *)esw->fdb_table.fdb,
 				   spec, &flow_act, dest, i);
 	if (IS_ERR(rule))
-		mlx5_fc_destroy(esw->dev, counter);
+		goto err_add_rule;
 	else
 		esw->offloads.num_flows++;
 
 	return rule;
+
+err_add_rule:
+	mlx5_fc_destroy(esw->dev, counter);
+err_counter_alloc:
+	return rule;
 }
 
 void
@@ -106,12 +116,10 @@ mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw,
 {
 	struct mlx5_fc *counter = NULL;
 
-	if (!IS_ERR(rule)) {
-		counter = mlx5_flow_rule_counter(rule);
-		mlx5_del_flow_rules(rule);
-		mlx5_fc_destroy(esw->dev, counter);
-		esw->offloads.num_flows--;
-	}
+	counter = mlx5_flow_rule_counter(rule);
+	mlx5_del_flow_rules(rule);
+	mlx5_fc_destroy(esw->dev, counter);
+	esw->offloads.num_flows--;
 }
 
 static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index b64a781c7e85..c6178ea1a461 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -249,6 +249,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	MLX5_SET(flow_context, in_flow_context, flow_tag, fte->flow_tag);
 	MLX5_SET(flow_context, in_flow_context, action, fte->action);
 	MLX5_SET(flow_context, in_flow_context, encap_id, fte->encap_id);
+	MLX5_SET(flow_context, in_flow_context, modify_header_id, fte->modify_id);
 	in_match_value = MLX5_ADDR_OF(flow_context, in_flow_context,
 				      match_value);
 	memcpy(in_match_value, &fte->val, MLX5_ST_SZ_BYTES(fte_match_param));
@@ -515,3 +516,69 @@ void mlx5_encap_dealloc(struct mlx5_core_dev *dev, u32 encap_id)
 
 	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
+
+int mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
+			     u8 namespace, u8 num_actions,
+			     void *modify_actions, u32 *modify_header_id)
+{
+	u32 out[MLX5_ST_SZ_DW(alloc_modify_header_context_out)];
+	int max_actions, actions_size, inlen, err;
+	void *actions_in;
+	u8 table_type;
+	u32 *in;
+
+	switch (namespace) {
+	case MLX5_FLOW_NAMESPACE_FDB:
+		max_actions = MLX5_CAP_ESW_FLOWTABLE_FDB(dev, max_modify_header_actions);
+		table_type = FS_FT_FDB;
+		break;
+	case MLX5_FLOW_NAMESPACE_KERNEL:
+		max_actions = MLX5_CAP_FLOWTABLE_NIC_RX(dev, max_modify_header_actions);
+		table_type = FS_FT_NIC_RX;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if (num_actions > max_actions) {
+		mlx5_core_warn(dev, "too many modify header actions %d, max supported %d\n",
+			       num_actions, max_actions);
+		return -EOPNOTSUPP;
+	}
+
+	actions_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto) * num_actions;
+	inlen = MLX5_ST_SZ_BYTES(alloc_modify_header_context_in) + actions_size;
+
+	in = kzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(alloc_modify_header_context_in, in, opcode,
+		 MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT);
+	MLX5_SET(alloc_modify_header_context_in, in, table_type, table_type);
+	MLX5_SET(alloc_modify_header_context_in, in, num_of_actions, num_actions);
+
+	actions_in = MLX5_ADDR_OF(alloc_modify_header_context_in, in, actions);
+	memcpy(actions_in, modify_actions, actions_size);
+
+	memset(out, 0, sizeof(out));
+	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+
+	*modify_header_id = MLX5_GET(alloc_modify_header_context_out, out, modify_header_id);
+	kfree(in);
+	return err;
+}
+
+void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id)
+{
+	u32 in[MLX5_ST_SZ_DW(dealloc_modify_header_context_in)];
+	u32 out[MLX5_ST_SZ_DW(dealloc_modify_header_context_out)];
+
+	memset(in, 0, sizeof(in));
+	MLX5_SET(dealloc_modify_header_context_in, in, opcode,
+		 MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT);
+	MLX5_SET(dealloc_modify_header_context_in, in, modify_header_id,
+		 modify_header_id);
+
+	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index ded27bb9a3b6..27ff815600f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -476,6 +476,7 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_act *flow_act,
 	fte->index = index;
 	fte->action = flow_act->action;
 	fte->encap_id = flow_act->encap_id;
+	fte->modify_id = flow_act->modify_id;
 
 	return fte;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 8e668c63f69e..03af2e7989f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -152,6 +152,7 @@ struct fs_fte {
 	u32				index;
 	u32				action;
 	u32				encap_id;
+	u32				modify_id;
 	enum fs_fte_status		status;
 	struct mlx5_fc			*counter;
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index b3dabe6e8836..fbc6e9e9e305 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -141,6 +141,11 @@ int mlx5_encap_alloc(struct mlx5_core_dev *dev,
 		     u32 *encap_id);
 void mlx5_encap_dealloc(struct mlx5_core_dev *dev, u32 encap_id);
 
+int mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
+			     u8 namespace, u8 num_actions,
+			     void *modify_actions, u32 *modify_header_id);
+void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id);
+
 bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv);
 
 int mlx5_query_mtpps(struct mlx5_core_dev *dev, u32 *mtpps, u32 mtpps_size);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 6b6c30deee83..2fb8c6585ac7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -15,7 +15,8 @@ obj-$(CONFIG_MLXSW_SPECTRUM)	+= mlxsw_spectrum.o
 mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_switchdev.o spectrum_router.o \
 				   spectrum_kvdl.o spectrum_acl_tcam.o \
-				   spectrum_acl.o spectrum_flower.o
+				   spectrum_acl.o spectrum_flower.o \
+				   spectrum_cnt.o spectrum_dpipe.o
 mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB)	+= spectrum_dcb.o
 obj-$(CONFIG_MLXSW_MINIMAL)	+= mlxsw_minimal.o
 mlxsw_minimal-objs		:= minimal.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
index a1b48421648a..479511cf79bc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
@@ -1043,13 +1043,6 @@ MLXSW_ITEM32(cmd_mbox, sw2hw_cq, cv, 0x00, 28, 4);
  */
 MLXSW_ITEM32(cmd_mbox, sw2hw_cq, c_eqn, 0x00, 24, 1);
 
-/* cmd_mbox_sw2hw_cq_oi
- * When set, overrun ignore is enabled. When set, updates of
- * CQ consumer counter (poll for completion) or Request completion
- * notifications (Arm CQ) DoorBells should not be rung on that CQ.
- */
-MLXSW_ITEM32(cmd_mbox, sw2hw_cq, oi, 0x00, 12, 1);
-
 /* cmd_mbox_sw2hw_cq_st
  * Event delivery state machine
  * 0x0 - FIRED
@@ -1132,11 +1125,6 @@ static inline int mlxsw_cmd_sw2hw_eq(struct mlxsw_core *mlxsw_core,
  */
 MLXSW_ITEM32(cmd_mbox, sw2hw_eq, int_msix, 0x00, 24, 1);
 
-/* cmd_mbox_sw2hw_eq_oi
- * When set, overrun ignore is enabled.
- */
-MLXSW_ITEM32(cmd_mbox, sw2hw_eq, oi, 0x00, 12, 1);
-
 /* cmd_mbox_sw2hw_eq_st
  * Event delivery state machine
  * 0x0 - FIRED
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index a4c07841aaf6..affe84eb4bff 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -40,9 +40,6 @@
 #include <linux/export.h>
 #include <linux/err.h>
 #include <linux/if_link.h>
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-#include <linux/u64_stats_sync.h>
 #include <linux/netdevice.h>
 #include <linux/completion.h>
 #include <linux/skbuff.h>
@@ -74,23 +71,9 @@ static DEFINE_SPINLOCK(mlxsw_core_driver_list_lock);
 
 static const char mlxsw_core_driver_name[] = "mlxsw_core";
 
-static struct dentry *mlxsw_core_dbg_root;
-
 static struct workqueue_struct *mlxsw_wq;
 static struct workqueue_struct *mlxsw_owq;
 
-struct mlxsw_core_pcpu_stats {
-	u64			trap_rx_packets[MLXSW_TRAP_ID_MAX];
-	u64			trap_rx_bytes[MLXSW_TRAP_ID_MAX];
-	u64			port_rx_packets[MLXSW_PORT_MAX_PORTS];
-	u64			port_rx_bytes[MLXSW_PORT_MAX_PORTS];
-	struct u64_stats_sync	syncp;
-	u32			trap_rx_dropped[MLXSW_TRAP_ID_MAX];
-	u32			port_rx_dropped[MLXSW_PORT_MAX_PORTS];
-	u32			trap_rx_invalid;
-	u32			port_rx_invalid;
-};
-
 struct mlxsw_core_port {
 	struct devlink_port devlink_port;
 	void *port_driver_priv;
@@ -121,23 +104,48 @@ struct mlxsw_core {
 		spinlock_t trans_list_lock; /* protects trans_list writes */
 		bool use_emad;
 	} emad;
-	struct mlxsw_core_pcpu_stats __percpu *pcpu_stats;
-	struct dentry *dbg_dir;
-	struct {
-		struct debugfs_blob_wrapper vsd_blob;
-		struct debugfs_blob_wrapper psid_blob;
-	} dbg;
 	struct {
 		u8 *mapping; /* lag_id+port_index to local_port mapping */
 	} lag;
 	struct mlxsw_res res;
 	struct mlxsw_hwmon *hwmon;
 	struct mlxsw_thermal *thermal;
-	struct mlxsw_core_port ports[MLXSW_PORT_MAX_PORTS];
+	struct mlxsw_core_port *ports;
+	unsigned int max_ports;
 	unsigned long driver_priv[0];
 	/* driver_priv has to be always the last item */
 };
 
+#define MLXSW_PORT_MAX_PORTS_DEFAULT	0x40
+
+static int mlxsw_ports_init(struct mlxsw_core *mlxsw_core)
+{
+	/* Switch ports are numbered from 1 to queried value */
+	if (MLXSW_CORE_RES_VALID(mlxsw_core, MAX_SYSTEM_PORT))
+		mlxsw_core->max_ports = MLXSW_CORE_RES_GET(mlxsw_core,
+							   MAX_SYSTEM_PORT) + 1;
+	else
+		mlxsw_core->max_ports = MLXSW_PORT_MAX_PORTS_DEFAULT + 1;
+
+	mlxsw_core->ports = kcalloc(mlxsw_core->max_ports,
+				    sizeof(struct mlxsw_core_port), GFP_KERNEL);
+	if (!mlxsw_core->ports)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void mlxsw_ports_fini(struct mlxsw_core *mlxsw_core)
+{
+	kfree(mlxsw_core->ports);
+}
+
+unsigned int mlxsw_core_max_ports(const struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_core->max_ports;
+}
+EXPORT_SYMBOL(mlxsw_core_max_ports);
+
 void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core)
 {
 	return mlxsw_core->driver_priv;
@@ -703,91 +711,6 @@ err_out:
  * Core functions
  *****************/
 
-static int mlxsw_core_rx_stats_dbg_read(struct seq_file *file, void *data)
-{
-	struct mlxsw_core *mlxsw_core = file->private;
-	struct mlxsw_core_pcpu_stats *p;
-	u64 rx_packets, rx_bytes;
-	u64 tmp_rx_packets, tmp_rx_bytes;
-	u32 rx_dropped, rx_invalid;
-	unsigned int start;
-	int i;
-	int j;
-	static const char hdr[] =
-		"     NUM   RX_PACKETS     RX_BYTES RX_DROPPED\n";
-
-	seq_printf(file, hdr);
-	for (i = 0; i < MLXSW_TRAP_ID_MAX; i++) {
-		rx_packets = 0;
-		rx_bytes = 0;
-		rx_dropped = 0;
-		for_each_possible_cpu(j) {
-			p = per_cpu_ptr(mlxsw_core->pcpu_stats, j);
-			do {
-				start = u64_stats_fetch_begin(&p->syncp);
-				tmp_rx_packets = p->trap_rx_packets[i];
-				tmp_rx_bytes = p->trap_rx_bytes[i];
-			} while (u64_stats_fetch_retry(&p->syncp, start));
-
-			rx_packets += tmp_rx_packets;
-			rx_bytes += tmp_rx_bytes;
-			rx_dropped += p->trap_rx_dropped[i];
-		}
-		seq_printf(file, "trap %3d %12llu %12llu %10u\n",
-			   i, rx_packets, rx_bytes, rx_dropped);
-	}
-	rx_invalid = 0;
-	for_each_possible_cpu(j) {
-		p = per_cpu_ptr(mlxsw_core->pcpu_stats, j);
-		rx_invalid += p->trap_rx_invalid;
-	}
-	seq_printf(file, "trap INV                           %10u\n",
-		   rx_invalid);
-
-	for (i = 0; i < MLXSW_PORT_MAX_PORTS; i++) {
-		rx_packets = 0;
-		rx_bytes = 0;
-		rx_dropped = 0;
-		for_each_possible_cpu(j) {
-			p = per_cpu_ptr(mlxsw_core->pcpu_stats, j);
-			do {
-				start = u64_stats_fetch_begin(&p->syncp);
-				tmp_rx_packets = p->port_rx_packets[i];
-				tmp_rx_bytes = p->port_rx_bytes[i];
-			} while (u64_stats_fetch_retry(&p->syncp, start));
-
-			rx_packets += tmp_rx_packets;
-			rx_bytes += tmp_rx_bytes;
-			rx_dropped += p->port_rx_dropped[i];
-		}
-		seq_printf(file, "port %3d %12llu %12llu %10u\n",
-			   i, rx_packets, rx_bytes, rx_dropped);
-	}
-	rx_invalid = 0;
-	for_each_possible_cpu(j) {
-		p = per_cpu_ptr(mlxsw_core->pcpu_stats, j);
-		rx_invalid += p->port_rx_invalid;
-	}
-	seq_printf(file, "port INV                           %10u\n",
-		   rx_invalid);
-	return 0;
-}
-
-static int mlxsw_core_rx_stats_dbg_open(struct inode *inode, struct file *f)
-{
-	struct mlxsw_core *mlxsw_core = inode->i_private;
-
-	return single_open(f, mlxsw_core_rx_stats_dbg_read, mlxsw_core);
-}
-
-static const struct file_operations mlxsw_core_rx_stats_dbg_ops = {
-	.owner = THIS_MODULE,
-	.open = mlxsw_core_rx_stats_dbg_open,
-	.release = single_release,
-	.read = seq_read,
-	.llseek = seq_lseek
-};
-
 int mlxsw_core_driver_register(struct mlxsw_driver *mlxsw_driver)
 {
 	spin_lock(&mlxsw_core_driver_list_lock);
@@ -835,39 +758,13 @@ static void mlxsw_core_driver_put(const char *kind)
 	spin_unlock(&mlxsw_core_driver_list_lock);
 }
 
-static int mlxsw_core_debugfs_init(struct mlxsw_core *mlxsw_core)
-{
-	const struct mlxsw_bus_info *bus_info = mlxsw_core->bus_info;
-
-	mlxsw_core->dbg_dir = debugfs_create_dir(bus_info->device_name,
-						 mlxsw_core_dbg_root);
-	if (!mlxsw_core->dbg_dir)
-		return -ENOMEM;
-	debugfs_create_file("rx_stats", S_IRUGO, mlxsw_core->dbg_dir,
-			    mlxsw_core, &mlxsw_core_rx_stats_dbg_ops);
-	mlxsw_core->dbg.vsd_blob.data = (void *) &bus_info->vsd;
-	mlxsw_core->dbg.vsd_blob.size = sizeof(bus_info->vsd);
-	debugfs_create_blob("vsd", S_IRUGO, mlxsw_core->dbg_dir,
-			    &mlxsw_core->dbg.vsd_blob);
-	mlxsw_core->dbg.psid_blob.data = (void *) &bus_info->psid;
-	mlxsw_core->dbg.psid_blob.size = sizeof(bus_info->psid);
-	debugfs_create_blob("psid", S_IRUGO, mlxsw_core->dbg_dir,
-			    &mlxsw_core->dbg.psid_blob);
-	return 0;
-}
-
-static void mlxsw_core_debugfs_fini(struct mlxsw_core *mlxsw_core)
-{
-	debugfs_remove_recursive(mlxsw_core->dbg_dir);
-}
-
 static int mlxsw_devlink_port_split(struct devlink *devlink,
 				    unsigned int port_index,
 				    unsigned int count)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
 
-	if (port_index >= MLXSW_PORT_MAX_PORTS)
+	if (port_index >= mlxsw_core->max_ports)
 		return -EINVAL;
 	if (!mlxsw_core->driver->port_split)
 		return -EOPNOTSUPP;
@@ -879,7 +776,7 @@ static int mlxsw_devlink_port_unsplit(struct devlink *devlink,
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
 
-	if (port_index >= MLXSW_PORT_MAX_PORTS)
+	if (port_index >= mlxsw_core->max_ports)
 		return -EINVAL;
 	if (!mlxsw_core->driver->port_unsplit)
 		return -EOPNOTSUPP;
@@ -1101,18 +998,15 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	mlxsw_core->bus_priv = bus_priv;
 	mlxsw_core->bus_info = mlxsw_bus_info;
 
-	mlxsw_core->pcpu_stats =
-		netdev_alloc_pcpu_stats(struct mlxsw_core_pcpu_stats);
-	if (!mlxsw_core->pcpu_stats) {
-		err = -ENOMEM;
-		goto err_alloc_stats;
-	}
-
 	err = mlxsw_bus->init(bus_priv, mlxsw_core, mlxsw_driver->profile,
 			      &mlxsw_core->res);
 	if (err)
 		goto err_bus_init;
 
+	err = mlxsw_ports_init(mlxsw_core);
+	if (err)
+		goto err_ports_init;
+
 	if (MLXSW_CORE_RES_VALID(mlxsw_core, MAX_LAG) &&
 	    MLXSW_CORE_RES_VALID(mlxsw_core, MAX_LAG_MEMBERS)) {
 		alloc_size = sizeof(u8) *
@@ -1148,15 +1042,8 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 			goto err_driver_init;
 	}
 
-	err = mlxsw_core_debugfs_init(mlxsw_core);
-	if (err)
-		goto err_debugfs_init;
-
 	return 0;
 
-err_debugfs_init:
-	if (mlxsw_core->driver->fini)
-		mlxsw_core->driver->fini(mlxsw_core);
 err_driver_init:
 	mlxsw_thermal_fini(mlxsw_core->thermal);
 err_thermal_init:
@@ -1167,10 +1054,10 @@ err_devlink_register:
 err_emad_init:
 	kfree(mlxsw_core->lag.mapping);
 err_alloc_lag_mapping:
+	mlxsw_ports_fini(mlxsw_core);
+err_ports_init:
 	mlxsw_bus->fini(bus_priv);
 err_bus_init:
-	free_percpu(mlxsw_core->pcpu_stats);
-err_alloc_stats:
 	devlink_free(devlink);
 err_devlink_alloc:
 	mlxsw_core_driver_put(device_kind);
@@ -1183,15 +1070,14 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core)
 	const char *device_kind = mlxsw_core->bus_info->device_kind;
 	struct devlink *devlink = priv_to_devlink(mlxsw_core);
 
-	mlxsw_core_debugfs_fini(mlxsw_core);
 	if (mlxsw_core->driver->fini)
 		mlxsw_core->driver->fini(mlxsw_core);
 	mlxsw_thermal_fini(mlxsw_core->thermal);
 	devlink_unregister(devlink);
 	mlxsw_emad_fini(mlxsw_core);
 	kfree(mlxsw_core->lag.mapping);
+	mlxsw_ports_fini(mlxsw_core);
 	mlxsw_core->bus->fini(mlxsw_core->bus_priv);
-	free_percpu(mlxsw_core->pcpu_stats);
 	devlink_free(devlink);
 	mlxsw_core_driver_put(device_kind);
 }
@@ -1639,7 +1525,6 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 {
 	struct mlxsw_rx_listener_item *rxl_item;
 	const struct mlxsw_rx_listener *rxl;
-	struct mlxsw_core_pcpu_stats *pcpu_stats;
 	u8 local_port;
 	bool found = false;
 
@@ -1661,7 +1546,7 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 			    __func__, local_port, rx_info->trap_id);
 
 	if ((rx_info->trap_id >= MLXSW_TRAP_ID_MAX) ||
-	    (local_port >= MLXSW_PORT_MAX_PORTS))
+	    (local_port >= mlxsw_core->max_ports))
 		goto drop;
 
 	rcu_read_lock();
@@ -1678,26 +1563,10 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 	if (!found)
 		goto drop;
 
-	pcpu_stats = this_cpu_ptr(mlxsw_core->pcpu_stats);
-	u64_stats_update_begin(&pcpu_stats->syncp);
-	pcpu_stats->port_rx_packets[local_port]++;
-	pcpu_stats->port_rx_bytes[local_port] += skb->len;
-	pcpu_stats->trap_rx_packets[rx_info->trap_id]++;
-	pcpu_stats->trap_rx_bytes[rx_info->trap_id] += skb->len;
-	u64_stats_update_end(&pcpu_stats->syncp);
-
 	rxl->func(skb, local_port, rxl_item->priv);
 	return;
 
 drop:
-	if (rx_info->trap_id >= MLXSW_TRAP_ID_MAX)
-		this_cpu_inc(mlxsw_core->pcpu_stats->trap_rx_invalid);
-	else
-		this_cpu_inc(mlxsw_core->pcpu_stats->trap_rx_dropped[rx_info->trap_id]);
-	if (local_port >= MLXSW_PORT_MAX_PORTS)
-		this_cpu_inc(mlxsw_core->pcpu_stats->port_rx_invalid);
-	else
-		this_cpu_inc(mlxsw_core->pcpu_stats->port_rx_dropped[local_port]);
 	dev_kfree_skb(skb);
 }
 EXPORT_SYMBOL(mlxsw_core_skb_receive);
@@ -1926,15 +1795,8 @@ static int __init mlxsw_core_module_init(void)
 		err = -ENOMEM;
 		goto err_alloc_ordered_workqueue;
 	}
-	mlxsw_core_dbg_root = debugfs_create_dir(mlxsw_core_driver_name, NULL);
-	if (!mlxsw_core_dbg_root) {
-		err = -ENOMEM;
-		goto err_debugfs_create_dir;
-	}
 	return 0;
 
-err_debugfs_create_dir:
-	destroy_workqueue(mlxsw_owq);
 err_alloc_ordered_workqueue:
 	destroy_workqueue(mlxsw_wq);
 	return err;
@@ -1942,7 +1804,6 @@ err_alloc_ordered_workqueue:
 
 static void __exit mlxsw_core_module_exit(void)
 {
-	debugfs_remove_recursive(mlxsw_core_dbg_root);
 	destroy_workqueue(mlxsw_owq);
 	destroy_workqueue(mlxsw_wq);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index cf38cf9027f8..7fb35395adf5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -57,6 +57,8 @@ struct mlxsw_driver;
 struct mlxsw_bus;
 struct mlxsw_bus_info;
 
+unsigned int mlxsw_core_max_ports(const struct mlxsw_core *mlxsw_core);
+
 void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core);
 
 int mlxsw_core_driver_register(struct mlxsw_driver *mlxsw_driver);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index 5f337715a4da..a984c361926c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -567,6 +567,89 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block,
 	return oneact + MLXSW_AFA_PAYLOAD_OFFSET;
 }
 
+/* VLAN Action
+ * -----------
+ * VLAN action is used for manipulating VLANs. It can be used to implement QinQ,
+ * VLAN translation, change of PCP bits of the VLAN tag, push, pop as swap VLANs
+ * and more.
+ */
+
+#define MLXSW_AFA_VLAN_CODE 0x02
+#define MLXSW_AFA_VLAN_SIZE 1
+
+enum mlxsw_afa_vlan_vlan_tag_cmd {
+	MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP,
+	MLXSW_AFA_VLAN_VLAN_TAG_CMD_PUSH_TAG,
+	MLXSW_AFA_VLAN_VLAN_TAG_CMD_POP_TAG,
+};
+
+enum mlxsw_afa_vlan_cmd {
+	MLXSW_AFA_VLAN_CMD_NOP,
+	MLXSW_AFA_VLAN_CMD_SET_OUTER,
+	MLXSW_AFA_VLAN_CMD_SET_INNER,
+	MLXSW_AFA_VLAN_CMD_COPY_OUTER_TO_INNER,
+	MLXSW_AFA_VLAN_CMD_COPY_INNER_TO_OUTER,
+	MLXSW_AFA_VLAN_CMD_SWAP,
+};
+
+/* afa_vlan_vlan_tag_cmd
+ * Tag command: push, pop, nop VLAN header.
+ */
+MLXSW_ITEM32(afa, vlan, vlan_tag_cmd, 0x00, 29, 3);
+
+/* afa_vlan_vid_cmd */
+MLXSW_ITEM32(afa, vlan, vid_cmd, 0x04, 29, 3);
+
+/* afa_vlan_vid */
+MLXSW_ITEM32(afa, vlan, vid, 0x04, 0, 12);
+
+/* afa_vlan_ethertype_cmd */
+MLXSW_ITEM32(afa, vlan, ethertype_cmd, 0x08, 29, 3);
+
+/* afa_vlan_ethertype
+ * Index to EtherTypes in Switch VLAN EtherType Register (SVER).
+ */
+MLXSW_ITEM32(afa, vlan, ethertype, 0x08, 24, 3);
+
+/* afa_vlan_pcp_cmd */
+MLXSW_ITEM32(afa, vlan, pcp_cmd, 0x08, 13, 3);
+
+/* afa_vlan_pcp */
+MLXSW_ITEM32(afa, vlan, pcp, 0x08, 8, 3);
+
+static inline void
+mlxsw_afa_vlan_pack(char *payload,
+		    enum mlxsw_afa_vlan_vlan_tag_cmd vlan_tag_cmd,
+		    enum mlxsw_afa_vlan_cmd vid_cmd, u16 vid,
+		    enum mlxsw_afa_vlan_cmd pcp_cmd, u8 pcp,
+		    enum mlxsw_afa_vlan_cmd ethertype_cmd, u8 ethertype)
+{
+	mlxsw_afa_vlan_vlan_tag_cmd_set(payload, vlan_tag_cmd);
+	mlxsw_afa_vlan_vid_cmd_set(payload, vid_cmd);
+	mlxsw_afa_vlan_vid_set(payload, vid);
+	mlxsw_afa_vlan_pcp_cmd_set(payload, pcp_cmd);
+	mlxsw_afa_vlan_pcp_set(payload, pcp);
+	mlxsw_afa_vlan_ethertype_cmd_set(payload, ethertype_cmd);
+	mlxsw_afa_vlan_ethertype_set(payload, ethertype);
+}
+
+int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
+				       u16 vid, u8 pcp, u8 et)
+{
+	char *act = mlxsw_afa_block_append_action(block,
+						  MLXSW_AFA_VLAN_CODE,
+						  MLXSW_AFA_VLAN_SIZE);
+
+	if (!act)
+		return -ENOBUFS;
+	mlxsw_afa_vlan_pack(act, MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP,
+			    MLXSW_AFA_VLAN_CMD_SET_OUTER, vid,
+			    MLXSW_AFA_VLAN_CMD_SET_OUTER, pcp,
+			    MLXSW_AFA_VLAN_CMD_SET_OUTER, et);
+	return 0;
+}
+EXPORT_SYMBOL(mlxsw_afa_block_append_vlan_modify);
+
 /* Trap / Discard Action
  * ---------------------
  * The Trap / Discard action enables trapping / mirroring packets to the CPU
@@ -677,3 +760,54 @@ err_append_action:
 	return err;
 }
 EXPORT_SYMBOL(mlxsw_afa_block_append_fwd);
+
+/* Policing and Counting Action
+ * ----------------------------
+ * Policing and Counting action is used for binding policer and counter
+ * to ACL rules.
+ */
+
+#define MLXSW_AFA_POLCNT_CODE 0x08
+#define MLXSW_AFA_POLCNT_SIZE 1
+
+enum mlxsw_afa_polcnt_counter_set_type {
+	/* No count */
+	MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_NO_COUNT = 0x00,
+	/* Count packets and bytes */
+	MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03,
+	/* Count only packets */
+	MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS = 0x05,
+};
+
+/* afa_polcnt_counter_set_type
+ * Counter set type for flow counters.
+ */
+MLXSW_ITEM32(afa, polcnt, counter_set_type, 0x04, 24, 8);
+
+/* afa_polcnt_counter_index
+ * Counter index for flow counters.
+ */
+MLXSW_ITEM32(afa, polcnt, counter_index, 0x04, 0, 24);
+
+static inline void
+mlxsw_afa_polcnt_pack(char *payload,
+		      enum mlxsw_afa_polcnt_counter_set_type set_type,
+		      u32 counter_index)
+{
+	mlxsw_afa_polcnt_counter_set_type_set(payload, set_type);
+	mlxsw_afa_polcnt_counter_index_set(payload, counter_index);
+}
+
+int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block,
+				   u32 counter_index)
+{
+	char *act = mlxsw_afa_block_append_action(block,
+						  MLXSW_AFA_POLCNT_CODE,
+						  MLXSW_AFA_POLCNT_SIZE);
+	if (!act)
+		return -ENOBUFS;
+	mlxsw_afa_polcnt_pack(act, MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES,
+			      counter_index);
+	return 0;
+}
+EXPORT_SYMBOL(mlxsw_afa_block_append_counter);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
index 43f78dcfe394..a03362c1ef32 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
@@ -62,5 +62,9 @@ void mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id);
 int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block);
 int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block,
 			       u8 local_port, bool in_port);
+int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
+				       u16 vid, u8 pcp, u8 et);
+int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block,
+				   u32 counter_index);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index e4fcba7c2af2..c75e9141e3ec 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -54,6 +54,8 @@ enum mlxsw_afk_element {
 	MLXSW_AFK_ELEMENT_DST_IP6_LO,
 	MLXSW_AFK_ELEMENT_DST_L4_PORT,
 	MLXSW_AFK_ELEMENT_SRC_L4_PORT,
+	MLXSW_AFK_ELEMENT_VID,
+	MLXSW_AFK_ELEMENT_PCP,
 	MLXSW_AFK_ELEMENT_MAX,
 };
 
@@ -88,7 +90,7 @@ struct mlxsw_afk_element_info {
 	MLXSW_AFK_ELEMENT_INFO(MLXSW_AFK_ELEMENT_TYPE_BUF,			\
 			       _element, _offset, 0, _size)
 
-/* For the purpose of the driver, define a internal storage scratchpad
+/* For the purpose of the driver, define an internal storage scratchpad
  * that will be used to store key/mask values. For each defined element type
  * define an internal storage geometry.
  */
@@ -98,6 +100,8 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = {
 	MLXSW_AFK_ELEMENT_INFO_BUF(SMAC, 0x0A, 6),
 	MLXSW_AFK_ELEMENT_INFO_U32(ETHERTYPE, 0x00, 0, 16),
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_PROTO, 0x10, 0, 8),
+	MLXSW_AFK_ELEMENT_INFO_U32(VID, 0x10, 8, 12),
+	MLXSW_AFK_ELEMENT_INFO_U32(PCP, 0x10, 20, 3),
 	MLXSW_AFK_ELEMENT_INFO_U32(SRC_IP4, 0x18, 0, 32),
 	MLXSW_AFK_ELEMENT_INFO_U32(DST_IP4, 0x1C, 0, 32),
 	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_HI, 0x18, 8),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index a223c85dfde0..eaa3e3bf5a2b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -44,8 +44,6 @@
 #include <linux/skbuff.h>
 #include <linux/if_vlan.h>
 #include <linux/log2.h>
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
 #include <linux/string.h>
 
 #include "pci_hw.h"
@@ -57,8 +55,6 @@
 
 static const char mlxsw_pci_driver_name[] = "mlxsw_pci";
 
-static struct dentry *mlxsw_pci_dbg_root;
-
 #define mlxsw_pci_write32(mlxsw_pci, reg, val) \
 	iowrite32be(val, (mlxsw_pci)->hw_addr + (MLXSW_PCI_ ## reg))
 #define mlxsw_pci_read32(mlxsw_pci, reg) \
@@ -71,21 +67,6 @@ enum mlxsw_pci_queue_type {
 	MLXSW_PCI_QUEUE_TYPE_EQ,
 };
 
-static const char *mlxsw_pci_queue_type_str(enum mlxsw_pci_queue_type q_type)
-{
-	switch (q_type) {
-	case MLXSW_PCI_QUEUE_TYPE_SDQ:
-		return "sdq";
-	case MLXSW_PCI_QUEUE_TYPE_RDQ:
-		return "rdq";
-	case MLXSW_PCI_QUEUE_TYPE_CQ:
-		return "cq";
-	case MLXSW_PCI_QUEUE_TYPE_EQ:
-		return "eq";
-	}
-	BUG();
-}
-
 #define MLXSW_PCI_QUEUE_TYPE_COUNT	4
 
 static const u16 mlxsw_pci_doorbell_type_offset[] = {
@@ -174,7 +155,6 @@ struct mlxsw_pci {
 		} comp;
 	} cmd;
 	struct mlxsw_bus_info bus_info;
-	struct dentry *dbg_dir;
 };
 
 static void mlxsw_pci_queue_tasklet_schedule(struct mlxsw_pci_queue *q)
@@ -261,21 +241,11 @@ static u8 mlxsw_pci_sdq_count(struct mlxsw_pci *mlxsw_pci)
 	return __mlxsw_pci_queue_count(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_SDQ);
 }
 
-static u8 mlxsw_pci_rdq_count(struct mlxsw_pci *mlxsw_pci)
-{
-	return __mlxsw_pci_queue_count(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_RDQ);
-}
-
 static u8 mlxsw_pci_cq_count(struct mlxsw_pci *mlxsw_pci)
 {
 	return __mlxsw_pci_queue_count(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_CQ);
 }
 
-static u8 mlxsw_pci_eq_count(struct mlxsw_pci *mlxsw_pci)
-{
-	return __mlxsw_pci_queue_count(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_EQ);
-}
-
 static struct mlxsw_pci_queue *
 __mlxsw_pci_queue_get(struct mlxsw_pci *mlxsw_pci,
 		      enum mlxsw_pci_queue_type q_type, u8 q_num)
@@ -390,26 +360,6 @@ static void mlxsw_pci_sdq_fini(struct mlxsw_pci *mlxsw_pci,
 	mlxsw_cmd_hw2sw_sdq(mlxsw_pci->core, q->num);
 }
 
-static int mlxsw_pci_sdq_dbg_read(struct seq_file *file, void *data)
-{
-	struct mlxsw_pci *mlxsw_pci = dev_get_drvdata(file->private);
-	struct mlxsw_pci_queue *q;
-	int i;
-	static const char hdr[] =
-		"NUM PROD_COUNT CONS_COUNT COUNT\n";
-
-	seq_printf(file, hdr);
-	for (i = 0; i < mlxsw_pci_sdq_count(mlxsw_pci); i++) {
-		q = mlxsw_pci_sdq_get(mlxsw_pci, i);
-		spin_lock_bh(&q->lock);
-		seq_printf(file, "%3d %10d %10d %5d\n",
-			   i, q->producer_counter, q->consumer_counter,
-			   q->count);
-		spin_unlock_bh(&q->lock);
-	}
-	return 0;
-}
-
 static int mlxsw_pci_wqe_frag_map(struct mlxsw_pci *mlxsw_pci, char *wqe,
 				  int index, char *frag_data, size_t frag_len,
 				  int direction)
@@ -544,26 +494,6 @@ static void mlxsw_pci_rdq_fini(struct mlxsw_pci *mlxsw_pci,
 	}
 }
 
-static int mlxsw_pci_rdq_dbg_read(struct seq_file *file, void *data)
-{
-	struct mlxsw_pci *mlxsw_pci = dev_get_drvdata(file->private);
-	struct mlxsw_pci_queue *q;
-	int i;
-	static const char hdr[] =
-		"NUM PROD_COUNT CONS_COUNT COUNT\n";
-
-	seq_printf(file, hdr);
-	for (i = 0; i < mlxsw_pci_rdq_count(mlxsw_pci); i++) {
-		q = mlxsw_pci_rdq_get(mlxsw_pci, i);
-		spin_lock_bh(&q->lock);
-		seq_printf(file, "%3d %10d %10d %5d\n",
-			   i, q->producer_counter, q->consumer_counter,
-			   q->count);
-		spin_unlock_bh(&q->lock);
-	}
-	return 0;
-}
-
 static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 			     struct mlxsw_pci_queue *q)
 {
@@ -580,7 +510,6 @@ static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 
 	mlxsw_cmd_mbox_sw2hw_cq_cv_set(mbox, 0); /* CQE ver 0 */
 	mlxsw_cmd_mbox_sw2hw_cq_c_eqn_set(mbox, MLXSW_PCI_EQ_COMP_NUM);
-	mlxsw_cmd_mbox_sw2hw_cq_oi_set(mbox, 0);
 	mlxsw_cmd_mbox_sw2hw_cq_st_set(mbox, 0);
 	mlxsw_cmd_mbox_sw2hw_cq_log_cq_size_set(mbox, ilog2(q->count));
 	for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) {
@@ -602,27 +531,6 @@ static void mlxsw_pci_cq_fini(struct mlxsw_pci *mlxsw_pci,
 	mlxsw_cmd_hw2sw_cq(mlxsw_pci->core, q->num);
 }
 
-static int mlxsw_pci_cq_dbg_read(struct seq_file *file, void *data)
-{
-	struct mlxsw_pci *mlxsw_pci = dev_get_drvdata(file->private);
-
-	struct mlxsw_pci_queue *q;
-	int i;
-	static const char hdr[] =
-		"NUM CONS_INDEX  SDQ_COUNT  RDQ_COUNT COUNT\n";
-
-	seq_printf(file, hdr);
-	for (i = 0; i < mlxsw_pci_cq_count(mlxsw_pci); i++) {
-		q = mlxsw_pci_cq_get(mlxsw_pci, i);
-		spin_lock_bh(&q->lock);
-		seq_printf(file, "%3d %10d %10d %10d %5d\n",
-			   i, q->consumer_counter, q->u.cq.comp_sdq_count,
-			   q->u.cq.comp_rdq_count, q->count);
-		spin_unlock_bh(&q->lock);
-	}
-	return 0;
-}
-
 static void mlxsw_pci_cqe_sdq_handle(struct mlxsw_pci *mlxsw_pci,
 				     struct mlxsw_pci_queue *q,
 				     u16 consumer_counter_limit,
@@ -755,7 +663,6 @@ static int mlxsw_pci_eq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 	}
 
 	mlxsw_cmd_mbox_sw2hw_eq_int_msix_set(mbox, 1); /* MSI-X used */
-	mlxsw_cmd_mbox_sw2hw_eq_oi_set(mbox, 0);
 	mlxsw_cmd_mbox_sw2hw_eq_st_set(mbox, 1); /* armed */
 	mlxsw_cmd_mbox_sw2hw_eq_log_eq_size_set(mbox, ilog2(q->count));
 	for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) {
@@ -777,27 +684,6 @@ static void mlxsw_pci_eq_fini(struct mlxsw_pci *mlxsw_pci,
 	mlxsw_cmd_hw2sw_eq(mlxsw_pci->core, q->num);
 }
 
-static int mlxsw_pci_eq_dbg_read(struct seq_file *file, void *data)
-{
-	struct mlxsw_pci *mlxsw_pci = dev_get_drvdata(file->private);
-	struct mlxsw_pci_queue *q;
-	int i;
-	static const char hdr[] =
-		"NUM CONS_COUNT     EV_CMD    EV_COMP   EV_OTHER COUNT\n";
-
-	seq_printf(file, hdr);
-	for (i = 0; i < mlxsw_pci_eq_count(mlxsw_pci); i++) {
-		q = mlxsw_pci_eq_get(mlxsw_pci, i);
-		spin_lock_bh(&q->lock);
-		seq_printf(file, "%3d %10d %10d %10d %10d %5d\n",
-			   i, q->consumer_counter, q->u.eq.ev_cmd_count,
-			   q->u.eq.ev_comp_count, q->u.eq.ev_other_count,
-			   q->count);
-		spin_unlock_bh(&q->lock);
-	}
-	return 0;
-}
-
 static void mlxsw_pci_eq_cmd_event(struct mlxsw_pci *mlxsw_pci, char *eqe)
 {
 	mlxsw_pci->cmd.comp.status = mlxsw_pci_eqe_cmd_status_get(eqe);
@@ -868,7 +754,6 @@ struct mlxsw_pci_queue_ops {
 	void (*fini)(struct mlxsw_pci *mlxsw_pci,
 		     struct mlxsw_pci_queue *q);
 	void (*tasklet)(unsigned long data);
-	int (*dbg_read)(struct seq_file *s, void *data);
 	u16 elem_count;
 	u8 elem_size;
 };
@@ -877,7 +762,6 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_sdq_ops = {
 	.type		= MLXSW_PCI_QUEUE_TYPE_SDQ,
 	.init		= mlxsw_pci_sdq_init,
 	.fini		= mlxsw_pci_sdq_fini,
-	.dbg_read	= mlxsw_pci_sdq_dbg_read,
 	.elem_count	= MLXSW_PCI_WQE_COUNT,
 	.elem_size	= MLXSW_PCI_WQE_SIZE,
 };
@@ -886,7 +770,6 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_rdq_ops = {
 	.type		= MLXSW_PCI_QUEUE_TYPE_RDQ,
 	.init		= mlxsw_pci_rdq_init,
 	.fini		= mlxsw_pci_rdq_fini,
-	.dbg_read	= mlxsw_pci_rdq_dbg_read,
 	.elem_count	= MLXSW_PCI_WQE_COUNT,
 	.elem_size	= MLXSW_PCI_WQE_SIZE
 };
@@ -896,7 +779,6 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_cq_ops = {
 	.init		= mlxsw_pci_cq_init,
 	.fini		= mlxsw_pci_cq_fini,
 	.tasklet	= mlxsw_pci_cq_tasklet,
-	.dbg_read	= mlxsw_pci_cq_dbg_read,
 	.elem_count	= MLXSW_PCI_CQE_COUNT,
 	.elem_size	= MLXSW_PCI_CQE_SIZE
 };
@@ -906,7 +788,6 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_eq_ops = {
 	.init		= mlxsw_pci_eq_init,
 	.fini		= mlxsw_pci_eq_fini,
 	.tasklet	= mlxsw_pci_eq_tasklet,
-	.dbg_read	= mlxsw_pci_eq_dbg_read,
 	.elem_count	= MLXSW_PCI_EQE_COUNT,
 	.elem_size	= MLXSW_PCI_EQE_SIZE
 };
@@ -984,9 +865,7 @@ static int mlxsw_pci_queue_group_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 				      const struct mlxsw_pci_queue_ops *q_ops,
 				      u8 num_qs)
 {
-	struct pci_dev *pdev = mlxsw_pci->pdev;
 	struct mlxsw_pci_queue_type_group *queue_group;
-	char tmp[16];
 	int i;
 	int err;
 
@@ -1003,10 +882,6 @@ static int mlxsw_pci_queue_group_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 	}
 	queue_group->count = num_qs;
 
-	sprintf(tmp, "%s_stats", mlxsw_pci_queue_type_str(q_ops->type));
-	debugfs_create_devm_seqfile(&pdev->dev, tmp, mlxsw_pci->dbg_dir,
-				    q_ops->dbg_read);
-
 	return 0;
 
 err_queue_init:
@@ -1852,14 +1727,6 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mlxsw_pci->bus_info.device_name = pci_name(mlxsw_pci->pdev);
 	mlxsw_pci->bus_info.dev = &pdev->dev;
 
-	mlxsw_pci->dbg_dir = debugfs_create_dir(mlxsw_pci->bus_info.device_name,
-						mlxsw_pci_dbg_root);
-	if (!mlxsw_pci->dbg_dir) {
-		dev_err(&pdev->dev, "Failed to create debugfs dir\n");
-		err = -ENOMEM;
-		goto err_dbg_create_dir;
-	}
-
 	err = mlxsw_core_bus_device_register(&mlxsw_pci->bus_info,
 					     &mlxsw_pci_bus, mlxsw_pci);
 	if (err) {
@@ -1870,8 +1737,6 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	return 0;
 
 err_bus_device_register:
-	debugfs_remove_recursive(mlxsw_pci->dbg_dir);
-err_dbg_create_dir:
 	pci_disable_msix(mlxsw_pci->pdev);
 err_msix_init:
 err_sw_reset:
@@ -1892,7 +1757,6 @@ static void mlxsw_pci_remove(struct pci_dev *pdev)
 	struct mlxsw_pci *mlxsw_pci = pci_get_drvdata(pdev);
 
 	mlxsw_core_bus_device_unregister(mlxsw_pci->core);
-	debugfs_remove_recursive(mlxsw_pci->dbg_dir);
 	pci_disable_msix(mlxsw_pci->pdev);
 	iounmap(mlxsw_pci->hw_addr);
 	pci_release_regions(mlxsw_pci->pdev);
@@ -1916,15 +1780,11 @@ EXPORT_SYMBOL(mlxsw_pci_driver_unregister);
 
 static int __init mlxsw_pci_module_init(void)
 {
-	mlxsw_pci_dbg_root = debugfs_create_dir(mlxsw_pci_driver_name, NULL);
-	if (!mlxsw_pci_dbg_root)
-		return -ENOMEM;
 	return 0;
 }
 
 static void __exit mlxsw_pci_module_exit(void)
 {
-	debugfs_remove_recursive(mlxsw_pci_dbg_root);
 }
 
 module_init(mlxsw_pci_module_init);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h
index 3d42146473b3..c580abba8d34 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/port.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/port.h
@@ -49,20 +49,12 @@
 
 #define MLXSW_PORT_MID			0xd000
 
-#define MLXSW_PORT_MAX_PHY_PORTS	0x40
-#define MLXSW_PORT_MAX_PORTS		(MLXSW_PORT_MAX_PHY_PORTS + 1)
-
 #define MLXSW_PORT_MAX_IB_PHY_PORTS	36
 #define MLXSW_PORT_MAX_IB_PORTS		(MLXSW_PORT_MAX_IB_PHY_PORTS + 1)
 
-#define MLXSW_PORT_DEVID_BITS_OFFSET	10
-#define MLXSW_PORT_PHY_BITS_OFFSET	4
-#define MLXSW_PORT_PHY_BITS_MASK	(MLXSW_PORT_MAX_PHY_PORTS - 1)
-
 #define MLXSW_PORT_CPU_PORT		0x0
-#define MLXSW_PORT_ROUTER_PORT		(MLXSW_PORT_MAX_PHY_PORTS + 2)
 
-#define MLXSW_PORT_DONT_CARE		(MLXSW_PORT_MAX_PORTS)
+#define MLXSW_PORT_DONT_CARE		0xFF
 
 #define MLXSW_PORT_MODULE_MAX_WIDTH	4
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index d9616daf8a70..83b277c8090e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -4125,6 +4125,60 @@ MLXSW_ITEM32(reg, ritr, sp_if_system_port, 0x08, 0, 16);
  */
 MLXSW_ITEM32(reg, ritr, sp_if_vid, 0x18, 0, 12);
 
+/* Shared between ingress/egress */
+enum mlxsw_reg_ritr_counter_set_type {
+	/* No Count. */
+	MLXSW_REG_RITR_COUNTER_SET_TYPE_NO_COUNT = 0x0,
+	/* Basic. Used for router interfaces, counting the following:
+	 *	- Error and Discard counters.
+	 *	- Unicast, Multicast and Broadcast counters. Sharing the
+	 *	  same set of counters for the different type of traffic
+	 *	  (IPv4, IPv6 and mpls).
+	 */
+	MLXSW_REG_RITR_COUNTER_SET_TYPE_BASIC = 0x9,
+};
+
+/* reg_ritr_ingress_counter_index
+ * Counter Index for flow counter.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, ingress_counter_index, 0x38, 0, 24);
+
+/* reg_ritr_ingress_counter_set_type
+ * Igress Counter Set Type for router interface counter.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, ingress_counter_set_type, 0x38, 24, 8);
+
+/* reg_ritr_egress_counter_index
+ * Counter Index for flow counter.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, egress_counter_index, 0x3C, 0, 24);
+
+/* reg_ritr_egress_counter_set_type
+ * Egress Counter Set Type for router interface counter.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, egress_counter_set_type, 0x3C, 24, 8);
+
+static inline void mlxsw_reg_ritr_counter_pack(char *payload, u32 index,
+					       bool enable, bool egress)
+{
+	enum mlxsw_reg_ritr_counter_set_type set_type;
+
+	if (enable)
+		set_type = MLXSW_REG_RITR_COUNTER_SET_TYPE_BASIC;
+	else
+		set_type = MLXSW_REG_RITR_COUNTER_SET_TYPE_NO_COUNT;
+	mlxsw_reg_ritr_egress_counter_set_type_set(payload, set_type);
+
+	if (egress)
+		mlxsw_reg_ritr_egress_counter_index_set(payload, index);
+	else
+		mlxsw_reg_ritr_ingress_counter_index_set(payload, index);
+}
+
 static inline void mlxsw_reg_ritr_rif_pack(char *payload, u16 rif)
 {
 	MLXSW_REG_ZERO(ritr, payload);
@@ -4141,7 +4195,8 @@ static inline void mlxsw_reg_ritr_sp_if_pack(char *payload, bool lag,
 
 static inline void mlxsw_reg_ritr_pack(char *payload, bool enable,
 				       enum mlxsw_reg_ritr_if_type type,
-				       u16 rif, u16 mtu, const char *mac)
+				       u16 rif, u16 vr_id, u16 mtu,
+				       const char *mac)
 {
 	bool op = enable ? MLXSW_REG_RITR_RIF_CREATE : MLXSW_REG_RITR_RIF_DEL;
 
@@ -4153,6 +4208,7 @@ static inline void mlxsw_reg_ritr_pack(char *payload, bool enable,
 	mlxsw_reg_ritr_rif_set(payload, rif);
 	mlxsw_reg_ritr_ipv4_fe_set(payload, 1);
 	mlxsw_reg_ritr_lb_en_set(payload, 1);
+	mlxsw_reg_ritr_virtual_router_set(payload, vr_id);
 	mlxsw_reg_ritr_mtu_set(payload, mtu);
 	mlxsw_reg_ritr_if_mac_memcpy_to(payload, mac);
 }
@@ -4285,6 +4341,129 @@ static inline void mlxsw_reg_ratr_eth_entry_pack(char *payload,
 	mlxsw_reg_ratr_eth_destination_mac_memcpy_to(payload, dest_mac);
 }
 
+/* RICNT - Router Interface Counter Register
+ * -----------------------------------------
+ * The RICNT register retrieves per port performance counters
+ */
+#define MLXSW_REG_RICNT_ID 0x800B
+#define MLXSW_REG_RICNT_LEN 0x100
+
+MLXSW_REG_DEFINE(ricnt, MLXSW_REG_RICNT_ID, MLXSW_REG_RICNT_LEN);
+
+/* reg_ricnt_counter_index
+ * Counter index
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ricnt, counter_index, 0x04, 0, 24);
+
+enum mlxsw_reg_ricnt_counter_set_type {
+	/* No Count. */
+	MLXSW_REG_RICNT_COUNTER_SET_TYPE_NO_COUNT = 0x00,
+	/* Basic. Used for router interfaces, counting the following:
+	 *	- Error and Discard counters.
+	 *	- Unicast, Multicast and Broadcast counters. Sharing the
+	 *	  same set of counters for the different type of traffic
+	 *	  (IPv4, IPv6 and mpls).
+	 */
+	MLXSW_REG_RICNT_COUNTER_SET_TYPE_BASIC = 0x09,
+};
+
+/* reg_ricnt_counter_set_type
+ * Counter Set Type for router interface counter
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ricnt, counter_set_type, 0x04, 24, 8);
+
+enum mlxsw_reg_ricnt_opcode {
+	/* Nop. Supported only for read access*/
+	MLXSW_REG_RICNT_OPCODE_NOP = 0x00,
+	/* Clear. Setting the clr bit will reset the counter value for
+	 * all counters of the specified Router Interface.
+	 */
+	MLXSW_REG_RICNT_OPCODE_CLEAR = 0x08,
+};
+
+/* reg_ricnt_opcode
+ * Opcode
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ricnt, op, 0x00, 28, 4);
+
+/* reg_ricnt_good_unicast_packets
+ * good unicast packets.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_unicast_packets, 0x08, 0, 64);
+
+/* reg_ricnt_good_multicast_packets
+ * good multicast packets.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_multicast_packets, 0x10, 0, 64);
+
+/* reg_ricnt_good_broadcast_packets
+ * good broadcast packets
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_broadcast_packets, 0x18, 0, 64);
+
+/* reg_ricnt_good_unicast_bytes
+ * A count of L3 data and padding octets not including L2 headers
+ * for good unicast frames.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_unicast_bytes, 0x20, 0, 64);
+
+/* reg_ricnt_good_multicast_bytes
+ * A count of L3 data and padding octets not including L2 headers
+ * for good multicast frames.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_multicast_bytes, 0x28, 0, 64);
+
+/* reg_ritr_good_broadcast_bytes
+ * A count of L3 data and padding octets not including L2 headers
+ * for good broadcast frames.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_broadcast_bytes, 0x30, 0, 64);
+
+/* reg_ricnt_error_packets
+ * A count of errored frames that do not pass the router checks.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, error_packets, 0x38, 0, 64);
+
+/* reg_ricnt_discrad_packets
+ * A count of non-errored frames that do not pass the router checks.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, discard_packets, 0x40, 0, 64);
+
+/* reg_ricnt_error_bytes
+ * A count of L3 data and padding octets not including L2 headers
+ * for errored frames.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, error_bytes, 0x48, 0, 64);
+
+/* reg_ricnt_discard_bytes
+ * A count of L3 data and padding octets not including L2 headers
+ * for non-errored frames that do not pass the router checks.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, discard_bytes, 0x50, 0, 64);
+
+static inline void mlxsw_reg_ricnt_pack(char *payload, u32 index,
+					enum mlxsw_reg_ricnt_opcode op)
+{
+	MLXSW_REG_ZERO(ricnt, payload);
+	mlxsw_reg_ricnt_op_set(payload, op);
+	mlxsw_reg_ricnt_counter_index_set(payload, index);
+	mlxsw_reg_ricnt_counter_set_type_set(payload,
+					     MLXSW_REG_RICNT_COUNTER_SET_TYPE_BASIC);
+}
+
 /* RALTA - Router Algorithmic LPM Tree Allocation Register
  * -------------------------------------------------------
  * RALTA is used to allocate the LPM trees of the SHSPM method.
@@ -5504,6 +5683,70 @@ static inline void mlxsw_reg_mpsc_pack(char *payload, u8 local_port, bool e,
 	mlxsw_reg_mpsc_rate_set(payload, rate);
 }
 
+/* MGPC - Monitoring General Purpose Counter Set Register
+ * The MGPC register retrieves and sets the General Purpose Counter Set.
+ */
+#define MLXSW_REG_MGPC_ID 0x9081
+#define MLXSW_REG_MGPC_LEN 0x18
+
+MLXSW_REG_DEFINE(mgpc, MLXSW_REG_MGPC_ID, MLXSW_REG_MGPC_LEN);
+
+enum mlxsw_reg_mgpc_counter_set_type {
+	/* No count */
+	MLXSW_REG_MGPC_COUNTER_SET_TYPE_NO_COUT = 0x00,
+	/* Count packets and bytes */
+	MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03,
+	/* Count only packets */
+	MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS = 0x05,
+};
+
+/* reg_mgpc_counter_set_type
+ * Counter set type.
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, mgpc, counter_set_type, 0x00, 24, 8);
+
+/* reg_mgpc_counter_index
+ * Counter index.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, mgpc, counter_index, 0x00, 0, 24);
+
+enum mlxsw_reg_mgpc_opcode {
+	/* Nop */
+	MLXSW_REG_MGPC_OPCODE_NOP = 0x00,
+	/* Clear counters */
+	MLXSW_REG_MGPC_OPCODE_CLEAR = 0x08,
+};
+
+/* reg_mgpc_opcode
+ * Opcode.
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, mgpc, opcode, 0x04, 28, 4);
+
+/* reg_mgpc_byte_counter
+ * Byte counter value.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, mgpc, byte_counter, 0x08, 0, 64);
+
+/* reg_mgpc_packet_counter
+ * Packet counter value.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, mgpc, packet_counter, 0x10, 0, 64);
+
+static inline void mlxsw_reg_mgpc_pack(char *payload, u32 counter_index,
+				       enum mlxsw_reg_mgpc_opcode opcode,
+				       enum mlxsw_reg_mgpc_counter_set_type set_type)
+{
+	MLXSW_REG_ZERO(mgpc, payload);
+	mlxsw_reg_mgpc_counter_index_set(payload, counter_index);
+	mlxsw_reg_mgpc_counter_set_type_set(payload, set_type);
+	mlxsw_reg_mgpc_opcode_set(payload, opcode);
+}
+
 /* SBPR - Shared Buffer Pools Register
  * -----------------------------------
  * The SBPR configures and retrieves the shared buffer pools and configuration.
@@ -5960,6 +6203,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(rgcr),
 	MLXSW_REG(ritr),
 	MLXSW_REG(ratr),
+	MLXSW_REG(ricnt),
 	MLXSW_REG(ralta),
 	MLXSW_REG(ralst),
 	MLXSW_REG(raltb),
@@ -5977,6 +6221,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(mpar),
 	MLXSW_REG(mlcr),
 	MLXSW_REG(mpsc),
+	MLXSW_REG(mgpc),
 	MLXSW_REG(sbpr),
 	MLXSW_REG(sbcm),
 	MLXSW_REG(sbpm),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h
index bce8c2e00630..9556d934714b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/resources.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h
@@ -43,11 +43,15 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE,
 	MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE,
 	MLXSW_RES_ID_MAX_TRAP_GROUPS,
+	MLXSW_RES_ID_COUNTER_POOL_SIZE,
 	MLXSW_RES_ID_MAX_SPAN,
+	MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES,
+	MLXSW_RES_ID_COUNTER_SIZE_ROUTER_BASIC,
 	MLXSW_RES_ID_MAX_SYSTEM_PORT,
 	MLXSW_RES_ID_MAX_LAG,
 	MLXSW_RES_ID_MAX_LAG_MEMBERS,
 	MLXSW_RES_ID_MAX_BUFFER_SIZE,
+	MLXSW_RES_ID_CELL_SIZE,
 	MLXSW_RES_ID_ACL_MAX_TCAM_REGIONS,
 	MLXSW_RES_ID_ACL_MAX_TCAM_RULES,
 	MLXSW_RES_ID_ACL_MAX_REGIONS,
@@ -59,6 +63,7 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_MAX_CPU_POLICERS,
 	MLXSW_RES_ID_MAX_VRS,
 	MLXSW_RES_ID_MAX_RIFS,
+	MLXSW_RES_ID_MAX_LPM_TREES,
 
 	/* Internal resources.
 	 * Determined by the SW, not queried from the HW.
@@ -75,11 +80,15 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE] = 0x1002,
 	[MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE] = 0x1003,
 	[MLXSW_RES_ID_MAX_TRAP_GROUPS] = 0x2201,
+	[MLXSW_RES_ID_COUNTER_POOL_SIZE] = 0x2410,
 	[MLXSW_RES_ID_MAX_SPAN] = 0x2420,
+	[MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES] = 0x2443,
+	[MLXSW_RES_ID_COUNTER_SIZE_ROUTER_BASIC] = 0x2449,
 	[MLXSW_RES_ID_MAX_SYSTEM_PORT] = 0x2502,
 	[MLXSW_RES_ID_MAX_LAG] = 0x2520,
 	[MLXSW_RES_ID_MAX_LAG_MEMBERS] = 0x2521,
 	[MLXSW_RES_ID_MAX_BUFFER_SIZE] = 0x2802,	/* Bytes */
+	[MLXSW_RES_ID_CELL_SIZE] = 0x2803,	/* Bytes */
 	[MLXSW_RES_ID_ACL_MAX_TCAM_REGIONS] = 0x2901,
 	[MLXSW_RES_ID_ACL_MAX_TCAM_RULES] = 0x2902,
 	[MLXSW_RES_ID_ACL_MAX_REGIONS] = 0x2903,
@@ -91,6 +100,7 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_MAX_CPU_POLICERS] = 0x2A13,
 	[MLXSW_RES_ID_MAX_VRS] = 0x2C01,
 	[MLXSW_RES_ID_MAX_RIFS] = 0x2C02,
+	[MLXSW_RES_ID_MAX_LPM_TREES] = 0x2C30,
 };
 
 struct mlxsw_res {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 16484f24b7db..b031f09bf4e6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -66,6 +66,8 @@
 #include "port.h"
 #include "trap.h"
 #include "txheader.h"
+#include "spectrum_cnt.h"
+#include "spectrum_dpipe.h"
 
 static const char mlxsw_sp_driver_name[] = "mlxsw_spectrum";
 static const char mlxsw_sp_driver_version[] = "1.0";
@@ -138,6 +140,60 @@ MLXSW_ITEM32(tx, hdr, fid, 0x08, 0, 16);
  */
 MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4);
 
+int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp,
+			      unsigned int counter_index, u64 *packets,
+			      u64 *bytes)
+{
+	char mgpc_pl[MLXSW_REG_MGPC_LEN];
+	int err;
+
+	mlxsw_reg_mgpc_pack(mgpc_pl, counter_index, MLXSW_REG_MGPC_OPCODE_NOP,
+			    MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(mgpc), mgpc_pl);
+	if (err)
+		return err;
+	*packets = mlxsw_reg_mgpc_packet_counter_get(mgpc_pl);
+	*bytes = mlxsw_reg_mgpc_byte_counter_get(mgpc_pl);
+	return 0;
+}
+
+static int mlxsw_sp_flow_counter_clear(struct mlxsw_sp *mlxsw_sp,
+				       unsigned int counter_index)
+{
+	char mgpc_pl[MLXSW_REG_MGPC_LEN];
+
+	mlxsw_reg_mgpc_pack(mgpc_pl, counter_index, MLXSW_REG_MGPC_OPCODE_CLEAR,
+			    MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mgpc), mgpc_pl);
+}
+
+int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+				unsigned int *p_counter_index)
+{
+	int err;
+
+	err = mlxsw_sp_counter_alloc(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_FLOW,
+				     p_counter_index);
+	if (err)
+		return err;
+	err = mlxsw_sp_flow_counter_clear(mlxsw_sp, *p_counter_index);
+	if (err)
+		goto err_counter_clear;
+	return 0;
+
+err_counter_clear:
+	mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_FLOW,
+			      *p_counter_index);
+	return err;
+}
+
+void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp,
+				unsigned int counter_index)
+{
+	 mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_FLOW,
+			       counter_index);
+}
+
 static void mlxsw_sp_txhdr_construct(struct sk_buff *skb,
 				     const struct mlxsw_tx_info *tx_info)
 {
@@ -304,9 +360,10 @@ static bool mlxsw_sp_span_is_egress_mirror(struct mlxsw_sp_port *port)
 	return false;
 }
 
-static int mlxsw_sp_span_mtu_to_buffsize(int mtu)
+static int mlxsw_sp_span_mtu_to_buffsize(const struct mlxsw_sp *mlxsw_sp,
+					 int mtu)
 {
-	return MLXSW_SP_BYTES_TO_CELLS(mtu * 5 / 2) + 1;
+	return mlxsw_sp_bytes_cells(mlxsw_sp, mtu * 5 / 2) + 1;
 }
 
 static int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu)
@@ -319,8 +376,9 @@ static int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu)
 	 * updated according to the mtu value
 	 */
 	if (mlxsw_sp_span_is_egress_mirror(port)) {
-		mlxsw_reg_sbib_pack(sbib_pl, port->local_port,
-				    mlxsw_sp_span_mtu_to_buffsize(mtu));
+		u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp, mtu);
+
+		mlxsw_reg_sbib_pack(sbib_pl, port->local_port, buffsize);
 		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
 		if (err) {
 			netdev_err(port->dev, "Could not update shared buffer for mirroring\n");
@@ -357,8 +415,10 @@ mlxsw_sp_span_inspected_port_bind(struct mlxsw_sp_port *port,
 
 	/* if it is an egress SPAN, bind a shared buffer to it */
 	if (type == MLXSW_SP_SPAN_EGRESS) {
-		mlxsw_reg_sbib_pack(sbib_pl, port->local_port,
-				    mlxsw_sp_span_mtu_to_buffsize(port->dev->mtu));
+		u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp,
+							     port->dev->mtu);
+
+		mlxsw_reg_sbib_pack(sbib_pl, port->local_port, buffsize);
 		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
 		if (err) {
 			netdev_err(port->dev, "Could not create shared buffer for mirroring\n");
@@ -745,19 +805,47 @@ static int mlxsw_sp_port_set_mac_address(struct net_device *dev, void *p)
 	return 0;
 }
 
-static void mlxsw_sp_pg_buf_pack(char *pbmc_pl, int pg_index, int mtu,
-				 bool pause_en, bool pfc_en, u16 delay)
+static u16 mlxsw_sp_pg_buf_threshold_get(const struct mlxsw_sp *mlxsw_sp,
+					 int mtu)
 {
-	u16 pg_size = 2 * MLXSW_SP_BYTES_TO_CELLS(mtu);
+	return 2 * mlxsw_sp_bytes_cells(mlxsw_sp, mtu);
+}
 
-	delay = pfc_en ? mlxsw_sp_pfc_delay_get(mtu, delay) :
-			 MLXSW_SP_PAUSE_DELAY;
+#define MLXSW_SP_CELL_FACTOR 2	/* 2 * cell_size / (IPG + cell_size + 1) */
+
+static u16 mlxsw_sp_pfc_delay_get(const struct mlxsw_sp *mlxsw_sp, int mtu,
+				  u16 delay)
+{
+	delay = mlxsw_sp_bytes_cells(mlxsw_sp, DIV_ROUND_UP(delay,
+							    BITS_PER_BYTE));
+	return MLXSW_SP_CELL_FACTOR * delay + mlxsw_sp_bytes_cells(mlxsw_sp,
+								   mtu);
+}
 
-	if (pause_en || pfc_en)
-		mlxsw_reg_pbmc_lossless_buffer_pack(pbmc_pl, pg_index,
-						    pg_size + delay, pg_size);
+/* Maximum delay buffer needed in case of PAUSE frames, in bytes.
+ * Assumes 100m cable and maximum MTU.
+ */
+#define MLXSW_SP_PAUSE_DELAY 58752
+
+static u16 mlxsw_sp_pg_buf_delay_get(const struct mlxsw_sp *mlxsw_sp, int mtu,
+				     u16 delay, bool pfc, bool pause)
+{
+	if (pfc)
+		return mlxsw_sp_pfc_delay_get(mlxsw_sp, mtu, delay);
+	else if (pause)
+		return mlxsw_sp_bytes_cells(mlxsw_sp, MLXSW_SP_PAUSE_DELAY);
 	else
-		mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, pg_index, pg_size);
+		return 0;
+}
+
+static void mlxsw_sp_pg_buf_pack(char *pbmc_pl, int index, u16 size, u16 thres,
+				 bool lossy)
+{
+	if (lossy)
+		mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, index, size);
+	else
+		mlxsw_reg_pbmc_lossless_buffer_pack(pbmc_pl, index, size,
+						    thres);
 }
 
 int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
@@ -778,6 +866,8 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
 		bool configure = false;
 		bool pfc = false;
+		bool lossy;
+		u16 thres;
 
 		for (j = 0; j < IEEE_8021QAZ_MAX_TCS; j++) {
 			if (prio_tc[j] == i) {
@@ -789,7 +879,12 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 
 		if (!configure)
 			continue;
-		mlxsw_sp_pg_buf_pack(pbmc_pl, i, mtu, pause_en, pfc, delay);
+
+		lossy = !(pfc || pause_en);
+		thres = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu);
+		delay = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, pfc,
+						  pause_en);
+		mlxsw_sp_pg_buf_pack(pbmc_pl, i, thres + delay, thres, lossy);
 	}
 
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
@@ -1368,7 +1463,7 @@ static int mlxsw_sp_setup_tc(struct net_device *dev, u32 handle,
 						       tc->cls_mall);
 			return 0;
 		default:
-			return -EINVAL;
+			return -EOPNOTSUPP;
 		}
 	case TC_SETUP_CLSFLOWER:
 		switch (tc->cls_flower->command) {
@@ -1379,6 +1474,9 @@ static int mlxsw_sp_setup_tc(struct net_device *dev, u32 handle,
 			mlxsw_sp_flower_destroy(mlxsw_sp_port, ingress,
 						tc->cls_flower);
 			return 0;
+		case TC_CLSFLOWER_STATS:
+			return mlxsw_sp_flower_stats(mlxsw_sp_port, ingress,
+						     tc->cls_flower);
 		default:
 			return -EOPNOTSUPP;
 		}
@@ -1492,6 +1590,7 @@ err_port_pause_configure:
 struct mlxsw_sp_port_hw_stats {
 	char str[ETH_GSTRING_LEN];
 	u64 (*getter)(const char *payload);
+	bool cells_bytes;
 };
 
 static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_stats[] = {
@@ -1612,17 +1711,11 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_prio_stats[] = {
 
 #define MLXSW_SP_PORT_HW_PRIO_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_prio_stats)
 
-static u64 mlxsw_reg_ppcnt_tc_transmit_queue_bytes_get(const char *ppcnt_pl)
-{
-	u64 transmit_queue = mlxsw_reg_ppcnt_tc_transmit_queue_get(ppcnt_pl);
-
-	return MLXSW_SP_CELLS_TO_BYTES(transmit_queue);
-}
-
 static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_tc_stats[] = {
 	{
 		.str = "tc_transmit_queue_tc",
-		.getter = mlxsw_reg_ppcnt_tc_transmit_queue_bytes_get,
+		.getter = mlxsw_reg_ppcnt_tc_transmit_queue_get,
+		.cells_bytes = true,
 	},
 	{
 		.str = "tc_no_buffer_discard_uc_tc",
@@ -1734,6 +1827,8 @@ static void __mlxsw_sp_port_get_stats(struct net_device *dev,
 				      enum mlxsw_reg_ppcnt_grp grp, int prio,
 				      u64 *data, int data_index)
 {
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_port_hw_stats *hw_stats;
 	char ppcnt_pl[MLXSW_REG_PPCNT_LEN];
 	int i, len;
@@ -1743,8 +1838,13 @@ static void __mlxsw_sp_port_get_stats(struct net_device *dev,
 	if (err)
 		return;
 	mlxsw_sp_port_get_stats_raw(dev, grp, prio, ppcnt_pl);
-	for (i = 0; i < len; i++)
+	for (i = 0; i < len; i++) {
 		data[data_index + i] = hw_stats[i].getter(ppcnt_pl);
+		if (!hw_stats[i].cells_bytes)
+			continue;
+		data[data_index + i] = mlxsw_sp_cells_bytes(mlxsw_sp,
+							    data[data_index + i]);
+	}
 }
 
 static void mlxsw_sp_port_get_stats(struct net_device *dev,
@@ -2537,25 +2637,33 @@ static void mlxsw_sp_ports_remove(struct mlxsw_sp *mlxsw_sp)
 {
 	int i;
 
-	for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++)
+	for (i = 1; i < mlxsw_core_max_ports(mlxsw_sp->core); i++)
 		if (mlxsw_sp_port_created(mlxsw_sp, i))
 			mlxsw_sp_port_remove(mlxsw_sp, i);
+	kfree(mlxsw_sp->port_to_module);
 	kfree(mlxsw_sp->ports);
 }
 
 static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
 {
+	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
 	u8 module, width, lane;
 	size_t alloc_size;
 	int i;
 	int err;
 
-	alloc_size = sizeof(struct mlxsw_sp_port *) * MLXSW_PORT_MAX_PORTS;
+	alloc_size = sizeof(struct mlxsw_sp_port *) * max_ports;
 	mlxsw_sp->ports = kzalloc(alloc_size, GFP_KERNEL);
 	if (!mlxsw_sp->ports)
 		return -ENOMEM;
 
-	for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++) {
+	mlxsw_sp->port_to_module = kcalloc(max_ports, sizeof(u8), GFP_KERNEL);
+	if (!mlxsw_sp->port_to_module) {
+		err = -ENOMEM;
+		goto err_port_to_module_alloc;
+	}
+
+	for (i = 1; i < max_ports; i++) {
 		err = mlxsw_sp_port_module_info_get(mlxsw_sp, i, &module,
 						    &width, &lane);
 		if (err)
@@ -2575,6 +2683,8 @@ err_port_module_info_get:
 	for (i--; i >= 1; i--)
 		if (mlxsw_sp_port_created(mlxsw_sp, i))
 			mlxsw_sp_port_remove(mlxsw_sp, i);
+	kfree(mlxsw_sp->port_to_module);
+err_port_to_module_alloc:
 	kfree(mlxsw_sp->ports);
 	return err;
 }
@@ -3224,6 +3334,18 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 		goto err_acl_init;
 	}
 
+	err = mlxsw_sp_counter_pool_init(mlxsw_sp);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to init counter pool\n");
+		goto err_counter_pool_init;
+	}
+
+	err = mlxsw_sp_dpipe_init(mlxsw_sp);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to init pipeline debug\n");
+		goto err_dpipe_init;
+	}
+
 	err = mlxsw_sp_ports_create(mlxsw_sp);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to create ports\n");
@@ -3233,6 +3355,10 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 	return 0;
 
 err_ports_create:
+	mlxsw_sp_dpipe_fini(mlxsw_sp);
+err_dpipe_init:
+	mlxsw_sp_counter_pool_fini(mlxsw_sp);
+err_counter_pool_init:
 	mlxsw_sp_acl_fini(mlxsw_sp);
 err_acl_init:
 	mlxsw_sp_span_fini(mlxsw_sp);
@@ -3255,6 +3381,8 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 
 	mlxsw_sp_ports_remove(mlxsw_sp);
+	mlxsw_sp_dpipe_fini(mlxsw_sp);
+	mlxsw_sp_counter_pool_fini(mlxsw_sp);
 	mlxsw_sp_acl_fini(mlxsw_sp);
 	mlxsw_sp_span_fini(mlxsw_sp);
 	mlxsw_sp_router_fini(mlxsw_sp);
@@ -3326,13 +3454,13 @@ bool mlxsw_sp_port_dev_check(const struct net_device *dev)
 	return dev->netdev_ops == &mlxsw_sp_port_netdev_ops;
 }
 
-static int mlxsw_lower_dev_walk(struct net_device *lower_dev, void *data)
+static int mlxsw_sp_lower_dev_walk(struct net_device *lower_dev, void *data)
 {
-	struct mlxsw_sp_port **port = data;
+	struct mlxsw_sp_port **p_mlxsw_sp_port = data;
 	int ret = 0;
 
 	if (mlxsw_sp_port_dev_check(lower_dev)) {
-		*port = netdev_priv(lower_dev);
+		*p_mlxsw_sp_port = netdev_priv(lower_dev);
 		ret = 1;
 	}
 
@@ -3341,18 +3469,18 @@ static int mlxsw_lower_dev_walk(struct net_device *lower_dev, void *data)
 
 static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev)
 {
-	struct mlxsw_sp_port *port;
+	struct mlxsw_sp_port *mlxsw_sp_port;
 
 	if (mlxsw_sp_port_dev_check(dev))
 		return netdev_priv(dev);
 
-	port = NULL;
-	netdev_walk_all_lower_dev(dev, mlxsw_lower_dev_walk, &port);
+	mlxsw_sp_port = NULL;
+	netdev_walk_all_lower_dev(dev, mlxsw_sp_lower_dev_walk, &mlxsw_sp_port);
 
-	return port;
+	return mlxsw_sp_port;
 }
 
-static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev)
+struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port;
 
@@ -3362,15 +3490,16 @@ static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev)
 
 static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev)
 {
-	struct mlxsw_sp_port *port;
+	struct mlxsw_sp_port *mlxsw_sp_port;
 
 	if (mlxsw_sp_port_dev_check(dev))
 		return netdev_priv(dev);
 
-	port = NULL;
-	netdev_walk_all_lower_dev_rcu(dev, mlxsw_lower_dev_walk, &port);
+	mlxsw_sp_port = NULL;
+	netdev_walk_all_lower_dev_rcu(dev, mlxsw_sp_lower_dev_walk,
+				      &mlxsw_sp_port);
 
-	return port;
+	return mlxsw_sp_port;
 }
 
 struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev)
@@ -3390,546 +3519,6 @@ void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port)
 	dev_put(mlxsw_sp_port->dev);
 }
 
-static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *r,
-				       unsigned long event)
-{
-	switch (event) {
-	case NETDEV_UP:
-		if (!r)
-			return true;
-		r->ref_count++;
-		return false;
-	case NETDEV_DOWN:
-		if (r && --r->ref_count == 0)
-			return true;
-		/* It is possible we already removed the RIF ourselves
-		 * if it was assigned to a netdev that is now a bridge
-		 * or LAG slave.
-		 */
-		return false;
-	}
-
-	return false;
-}
-
-static int mlxsw_sp_avail_rif_get(struct mlxsw_sp *mlxsw_sp)
-{
-	int i;
-
-	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
-		if (!mlxsw_sp->rifs[i])
-			return i;
-
-	return MLXSW_SP_INVALID_RIF;
-}
-
-static void mlxsw_sp_vport_rif_sp_attr_get(struct mlxsw_sp_port *mlxsw_sp_vport,
-					   bool *p_lagged, u16 *p_system_port)
-{
-	u8 local_port = mlxsw_sp_vport->local_port;
-
-	*p_lagged = mlxsw_sp_vport->lagged;
-	*p_system_port = *p_lagged ? mlxsw_sp_vport->lag_id : local_port;
-}
-
-static int mlxsw_sp_vport_rif_sp_op(struct mlxsw_sp_port *mlxsw_sp_vport,
-				    struct net_device *l3_dev, u16 rif,
-				    bool create)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
-	bool lagged = mlxsw_sp_vport->lagged;
-	char ritr_pl[MLXSW_REG_RITR_LEN];
-	u16 system_port;
-
-	mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif,
-			    l3_dev->mtu, l3_dev->dev_addr);
-
-	mlxsw_sp_vport_rif_sp_attr_get(mlxsw_sp_vport, &lagged, &system_port);
-	mlxsw_reg_ritr_sp_if_pack(ritr_pl, lagged, system_port,
-				  mlxsw_sp_vport_vid_get(mlxsw_sp_vport));
-
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-}
-
-static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport);
-
-static struct mlxsw_sp_fid *
-mlxsw_sp_rfid_alloc(u16 fid, struct net_device *l3_dev)
-{
-	struct mlxsw_sp_fid *f;
-
-	f = kzalloc(sizeof(*f), GFP_KERNEL);
-	if (!f)
-		return NULL;
-
-	f->leave = mlxsw_sp_vport_rif_sp_leave;
-	f->ref_count = 0;
-	f->dev = l3_dev;
-	f->fid = fid;
-
-	return f;
-}
-
-static struct mlxsw_sp_rif *
-mlxsw_sp_rif_alloc(u16 rif, struct net_device *l3_dev, struct mlxsw_sp_fid *f)
-{
-	struct mlxsw_sp_rif *r;
-
-	r = kzalloc(sizeof(*r), GFP_KERNEL);
-	if (!r)
-		return NULL;
-
-	INIT_LIST_HEAD(&r->nexthop_list);
-	INIT_LIST_HEAD(&r->neigh_list);
-	ether_addr_copy(r->addr, l3_dev->dev_addr);
-	r->mtu = l3_dev->mtu;
-	r->ref_count = 1;
-	r->dev = l3_dev;
-	r->rif = rif;
-	r->f = f;
-
-	return r;
-}
-
-static struct mlxsw_sp_rif *
-mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport,
-			     struct net_device *l3_dev)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
-	struct mlxsw_sp_fid *f;
-	struct mlxsw_sp_rif *r;
-	u16 fid, rif;
-	int err;
-
-	rif = mlxsw_sp_avail_rif_get(mlxsw_sp);
-	if (rif == MLXSW_SP_INVALID_RIF)
-		return ERR_PTR(-ERANGE);
-
-	err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, true);
-	if (err)
-		return ERR_PTR(err);
-
-	fid = mlxsw_sp_rif_sp_to_fid(rif);
-	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, true);
-	if (err)
-		goto err_rif_fdb_op;
-
-	f = mlxsw_sp_rfid_alloc(fid, l3_dev);
-	if (!f) {
-		err = -ENOMEM;
-		goto err_rfid_alloc;
-	}
-
-	r = mlxsw_sp_rif_alloc(rif, l3_dev, f);
-	if (!r) {
-		err = -ENOMEM;
-		goto err_rif_alloc;
-	}
-
-	f->r = r;
-	mlxsw_sp->rifs[rif] = r;
-
-	return r;
-
-err_rif_alloc:
-	kfree(f);
-err_rfid_alloc:
-	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false);
-err_rif_fdb_op:
-	mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false);
-	return ERR_PTR(err);
-}
-
-static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport,
-					  struct mlxsw_sp_rif *r)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
-	struct net_device *l3_dev = r->dev;
-	struct mlxsw_sp_fid *f = r->f;
-	u16 fid = f->fid;
-	u16 rif = r->rif;
-
-	mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r);
-
-	mlxsw_sp->rifs[rif] = NULL;
-	f->r = NULL;
-
-	kfree(r);
-
-	kfree(f);
-
-	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false);
-
-	mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false);
-}
-
-static int mlxsw_sp_vport_rif_sp_join(struct mlxsw_sp_port *mlxsw_sp_vport,
-				      struct net_device *l3_dev)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
-	struct mlxsw_sp_rif *r;
-
-	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
-	if (!r) {
-		r = mlxsw_sp_vport_rif_sp_create(mlxsw_sp_vport, l3_dev);
-		if (IS_ERR(r))
-			return PTR_ERR(r);
-	}
-
-	mlxsw_sp_vport_fid_set(mlxsw_sp_vport, r->f);
-	r->f->ref_count++;
-
-	netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", r->f->fid);
-
-	return 0;
-}
-
-static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport)
-{
-	struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
-
-	netdev_dbg(mlxsw_sp_vport->dev, "Left FID=%d\n", f->fid);
-
-	mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL);
-	if (--f->ref_count == 0)
-		mlxsw_sp_vport_rif_sp_destroy(mlxsw_sp_vport, f->r);
-}
-
-static int mlxsw_sp_inetaddr_vport_event(struct net_device *l3_dev,
-					 struct net_device *port_dev,
-					 unsigned long event, u16 vid)
-{
-	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(port_dev);
-	struct mlxsw_sp_port *mlxsw_sp_vport;
-
-	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
-	if (WARN_ON(!mlxsw_sp_vport))
-		return -EINVAL;
-
-	switch (event) {
-	case NETDEV_UP:
-		return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, l3_dev);
-	case NETDEV_DOWN:
-		mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport);
-		break;
-	}
-
-	return 0;
-}
-
-static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev,
-					unsigned long event)
-{
-	if (netif_is_bridge_port(port_dev) || netif_is_lag_port(port_dev))
-		return 0;
-
-	return mlxsw_sp_inetaddr_vport_event(port_dev, port_dev, event, 1);
-}
-
-static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev,
-					 struct net_device *lag_dev,
-					 unsigned long event, u16 vid)
-{
-	struct net_device *port_dev;
-	struct list_head *iter;
-	int err;
-
-	netdev_for_each_lower_dev(lag_dev, port_dev, iter) {
-		if (mlxsw_sp_port_dev_check(port_dev)) {
-			err = mlxsw_sp_inetaddr_vport_event(l3_dev, port_dev,
-							    event, vid);
-			if (err)
-				return err;
-		}
-	}
-
-	return 0;
-}
-
-static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev,
-				       unsigned long event)
-{
-	if (netif_is_bridge_port(lag_dev))
-		return 0;
-
-	return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1);
-}
-
-static struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp,
-						    struct net_device *l3_dev)
-{
-	u16 fid;
-
-	if (is_vlan_dev(l3_dev))
-		fid = vlan_dev_vlan_id(l3_dev);
-	else if (mlxsw_sp->master_bridge.dev == l3_dev)
-		fid = 1;
-	else
-		return mlxsw_sp_vfid_find(mlxsw_sp, l3_dev);
-
-	return mlxsw_sp_fid_find(mlxsw_sp, fid);
-}
-
-static enum mlxsw_flood_table_type mlxsw_sp_flood_table_type_get(u16 fid)
-{
-	return mlxsw_sp_fid_is_vfid(fid) ? MLXSW_REG_SFGC_TABLE_TYPE_FID :
-	       MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST;
-}
-
-static u16 mlxsw_sp_flood_table_index_get(u16 fid)
-{
-	return mlxsw_sp_fid_is_vfid(fid) ? mlxsw_sp_fid_to_vfid(fid) : fid;
-}
-
-static int mlxsw_sp_router_port_flood_set(struct mlxsw_sp *mlxsw_sp, u16 fid,
-					  bool set)
-{
-	enum mlxsw_flood_table_type table_type;
-	char *sftr_pl;
-	u16 index;
-	int err;
-
-	sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL);
-	if (!sftr_pl)
-		return -ENOMEM;
-
-	table_type = mlxsw_sp_flood_table_type_get(fid);
-	index = mlxsw_sp_flood_table_index_get(fid);
-	mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BC, index, table_type,
-			    1, MLXSW_PORT_ROUTER_PORT, set);
-	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl);
-
-	kfree(sftr_pl);
-	return err;
-}
-
-static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid)
-{
-	if (mlxsw_sp_fid_is_vfid(fid))
-		return MLXSW_REG_RITR_FID_IF;
-	else
-		return MLXSW_REG_RITR_VLAN_IF;
-}
-
-static int mlxsw_sp_rif_bridge_op(struct mlxsw_sp *mlxsw_sp,
-				  struct net_device *l3_dev,
-				  u16 fid, u16 rif,
-				  bool create)
-{
-	enum mlxsw_reg_ritr_if_type rif_type;
-	char ritr_pl[MLXSW_REG_RITR_LEN];
-
-	rif_type = mlxsw_sp_rif_type_get(fid);
-	mlxsw_reg_ritr_pack(ritr_pl, create, rif_type, rif, l3_dev->mtu,
-			    l3_dev->dev_addr);
-	mlxsw_reg_ritr_fid_set(ritr_pl, rif_type, fid);
-
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-}
-
-static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp,
-				      struct net_device *l3_dev,
-				      struct mlxsw_sp_fid *f)
-{
-	struct mlxsw_sp_rif *r;
-	u16 rif;
-	int err;
-
-	rif = mlxsw_sp_avail_rif_get(mlxsw_sp);
-	if (rif == MLXSW_SP_INVALID_RIF)
-		return -ERANGE;
-
-	err = mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, true);
-	if (err)
-		return err;
-
-	err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true);
-	if (err)
-		goto err_rif_bridge_op;
-
-	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true);
-	if (err)
-		goto err_rif_fdb_op;
-
-	r = mlxsw_sp_rif_alloc(rif, l3_dev, f);
-	if (!r) {
-		err = -ENOMEM;
-		goto err_rif_alloc;
-	}
-
-	f->r = r;
-	mlxsw_sp->rifs[rif] = r;
-
-	netdev_dbg(l3_dev, "RIF=%d created\n", rif);
-
-	return 0;
-
-err_rif_alloc:
-	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false);
-err_rif_fdb_op:
-	mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false);
-err_rif_bridge_op:
-	mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false);
-	return err;
-}
-
-void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp,
-				 struct mlxsw_sp_rif *r)
-{
-	struct net_device *l3_dev = r->dev;
-	struct mlxsw_sp_fid *f = r->f;
-	u16 rif = r->rif;
-
-	mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r);
-
-	mlxsw_sp->rifs[rif] = NULL;
-	f->r = NULL;
-
-	kfree(r);
-
-	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false);
-
-	mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false);
-
-	mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false);
-
-	netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif);
-}
-
-static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev,
-					  struct net_device *br_dev,
-					  unsigned long event)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev);
-	struct mlxsw_sp_fid *f;
-
-	/* FID can either be an actual FID if the L3 device is the
-	 * VLAN-aware bridge or a VLAN device on top. Otherwise, the
-	 * L3 device is a VLAN-unaware bridge and we get a vFID.
-	 */
-	f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev);
-	if (WARN_ON(!f))
-		return -EINVAL;
-
-	switch (event) {
-	case NETDEV_UP:
-		return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f);
-	case NETDEV_DOWN:
-		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r);
-		break;
-	}
-
-	return 0;
-}
-
-static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
-					unsigned long event)
-{
-	struct net_device *real_dev = vlan_dev_real_dev(vlan_dev);
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev);
-	u16 vid = vlan_dev_vlan_id(vlan_dev);
-
-	if (mlxsw_sp_port_dev_check(real_dev))
-		return mlxsw_sp_inetaddr_vport_event(vlan_dev, real_dev, event,
-						     vid);
-	else if (netif_is_lag_master(real_dev))
-		return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event,
-						     vid);
-	else if (netif_is_bridge_master(real_dev) &&
-		 mlxsw_sp->master_bridge.dev == real_dev)
-		return mlxsw_sp_inetaddr_bridge_event(vlan_dev, real_dev,
-						      event);
-
-	return 0;
-}
-
-static int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
-				   unsigned long event, void *ptr)
-{
-	struct in_ifaddr *ifa = (struct in_ifaddr *) ptr;
-	struct net_device *dev = ifa->ifa_dev->dev;
-	struct mlxsw_sp *mlxsw_sp;
-	struct mlxsw_sp_rif *r;
-	int err = 0;
-
-	mlxsw_sp = mlxsw_sp_lower_get(dev);
-	if (!mlxsw_sp)
-		goto out;
-
-	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
-	if (!mlxsw_sp_rif_should_config(r, event))
-		goto out;
-
-	if (mlxsw_sp_port_dev_check(dev))
-		err = mlxsw_sp_inetaddr_port_event(dev, event);
-	else if (netif_is_lag_master(dev))
-		err = mlxsw_sp_inetaddr_lag_event(dev, event);
-	else if (netif_is_bridge_master(dev))
-		err = mlxsw_sp_inetaddr_bridge_event(dev, dev, event);
-	else if (is_vlan_dev(dev))
-		err = mlxsw_sp_inetaddr_vlan_event(dev, event);
-
-out:
-	return notifier_from_errno(err);
-}
-
-static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif,
-			     const char *mac, int mtu)
-{
-	char ritr_pl[MLXSW_REG_RITR_LEN];
-	int err;
-
-	mlxsw_reg_ritr_rif_pack(ritr_pl, rif);
-	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-	if (err)
-		return err;
-
-	mlxsw_reg_ritr_mtu_set(ritr_pl, mtu);
-	mlxsw_reg_ritr_if_mac_memcpy_to(ritr_pl, mac);
-	mlxsw_reg_ritr_op_set(ritr_pl, MLXSW_REG_RITR_RIF_CREATE);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-}
-
-static int mlxsw_sp_netdevice_router_port_event(struct net_device *dev)
-{
-	struct mlxsw_sp *mlxsw_sp;
-	struct mlxsw_sp_rif *r;
-	int err;
-
-	mlxsw_sp = mlxsw_sp_lower_get(dev);
-	if (!mlxsw_sp)
-		return 0;
-
-	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
-	if (!r)
-		return 0;
-
-	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, false);
-	if (err)
-		return err;
-
-	err = mlxsw_sp_rif_edit(mlxsw_sp, r->rif, dev->dev_addr, dev->mtu);
-	if (err)
-		goto err_rif_edit;
-
-	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, dev->dev_addr, r->f->fid, true);
-	if (err)
-		goto err_rif_fdb_op;
-
-	ether_addr_copy(r->addr, dev->dev_addr);
-	r->mtu = dev->mtu;
-
-	netdev_dbg(dev, "Updated RIF=%d\n", r->rif);
-
-	return 0;
-
-err_rif_fdb_op:
-	mlxsw_sp_rif_edit(mlxsw_sp, r->rif, r->addr, r->mtu);
-err_rif_edit:
-	mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, true);
-	return err;
-}
-
 static bool mlxsw_sp_lag_port_fid_member(struct mlxsw_sp_port *lag_port,
 					 u16 fid)
 {
@@ -4220,7 +3809,7 @@ static int mlxsw_sp_port_lag_index_get(struct mlxsw_sp *mlxsw_sp,
 
 static void
 mlxsw_sp_port_pvid_vport_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
-				  u16 lag_id)
+				  struct net_device *lag_dev, u16 lag_id)
 {
 	struct mlxsw_sp_port *mlxsw_sp_vport;
 	struct mlxsw_sp_fid *f;
@@ -4238,6 +3827,7 @@ mlxsw_sp_port_pvid_vport_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	mlxsw_sp_vport->lag_id = lag_id;
 	mlxsw_sp_vport->lagged = 1;
+	mlxsw_sp_vport->dev = lag_dev;
 }
 
 static void
@@ -4254,6 +3844,7 @@ mlxsw_sp_port_pvid_vport_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port)
 	if (f)
 		f->leave(mlxsw_sp_vport);
 
+	mlxsw_sp_vport->dev = mlxsw_sp_port->dev;
 	mlxsw_sp_vport->lagged = 0;
 }
 
@@ -4293,7 +3884,7 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_port->lagged = 1;
 	lag->ref_count++;
 
-	mlxsw_sp_port_pvid_vport_lag_join(mlxsw_sp_port, lag_id);
+	mlxsw_sp_port_pvid_vport_lag_join(mlxsw_sp_port, lag_dev, lag_id);
 
 	return 0;
 
@@ -4421,7 +4012,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
 		upper_dev = info->upper_dev;
 		if (!is_vlan_dev(upper_dev) &&
 		    !netif_is_lag_master(upper_dev) &&
-		    !netif_is_bridge_master(upper_dev))
+		    !netif_is_bridge_master(upper_dev) &&
+		    !netif_is_l3_master(upper_dev))
 			return -EINVAL;
 		if (!info->linking)
 			break;
@@ -4461,6 +4053,11 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
 			else
 				mlxsw_sp_port_lag_leave(mlxsw_sp_port,
 							upper_dev);
+		} else if (netif_is_l3_master(upper_dev)) {
+			if (info->linking)
+				err = mlxsw_sp_port_vrf_join(mlxsw_sp_port);
+			else
+				mlxsw_sp_port_vrf_leave(mlxsw_sp_port);
 		} else {
 			err = -EINVAL;
 			WARN_ON(1);
@@ -4552,8 +4149,8 @@ static void mlxsw_sp_master_bridge_vlan_unlink(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_fid *f;
 
 	f = mlxsw_sp_fid_find(mlxsw_sp, fid);
-	if (f && f->r)
-		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r);
+	if (f && f->rif)
+		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif);
 	if (f && --f->ref_count == 0)
 		mlxsw_sp_fid_destroy(mlxsw_sp, f);
 }
@@ -4564,33 +4161,46 @@ static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev,
 	struct netdev_notifier_changeupper_info *info;
 	struct net_device *upper_dev;
 	struct mlxsw_sp *mlxsw_sp;
-	int err;
+	int err = 0;
 
 	mlxsw_sp = mlxsw_sp_lower_get(br_dev);
 	if (!mlxsw_sp)
 		return 0;
-	if (br_dev != mlxsw_sp->master_bridge.dev)
-		return 0;
 
 	info = ptr;
 
 	switch (event) {
+	case NETDEV_PRECHANGEUPPER:
+		upper_dev = info->upper_dev;
+		if (!is_vlan_dev(upper_dev) && !netif_is_l3_master(upper_dev))
+			return -EINVAL;
+		if (is_vlan_dev(upper_dev) &&
+		    br_dev != mlxsw_sp->master_bridge.dev)
+			return -EINVAL;
+		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
-		if (!is_vlan_dev(upper_dev))
-			break;
-		if (info->linking) {
-			err = mlxsw_sp_master_bridge_vlan_link(mlxsw_sp,
-							       upper_dev);
-			if (err)
-				return err;
+		if (is_vlan_dev(upper_dev)) {
+			if (info->linking)
+				err = mlxsw_sp_master_bridge_vlan_link(mlxsw_sp,
+								       upper_dev);
+			else
+				mlxsw_sp_master_bridge_vlan_unlink(mlxsw_sp,
+								   upper_dev);
+		} else if (netif_is_l3_master(upper_dev)) {
+			if (info->linking)
+				err = mlxsw_sp_bridge_vrf_join(mlxsw_sp,
+							       br_dev);
+			else
+				mlxsw_sp_bridge_vrf_leave(mlxsw_sp, br_dev);
 		} else {
-			mlxsw_sp_master_bridge_vlan_unlink(mlxsw_sp, upper_dev);
+			err = -EINVAL;
+			WARN_ON(1);
 		}
 		break;
 	}
 
-	return 0;
+	return err;
 }
 
 static u16 mlxsw_sp_avail_vfid_get(const struct mlxsw_sp *mlxsw_sp)
@@ -4657,8 +4267,8 @@ static void mlxsw_sp_vfid_destroy(struct mlxsw_sp *mlxsw_sp,
 	clear_bit(vfid, mlxsw_sp->vfids.mapped);
 	list_del(&f->list);
 
-	if (f->r)
-		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r);
+	if (f->rif)
+		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif);
 
 	kfree(f);
 
@@ -4810,33 +4420,43 @@ static int mlxsw_sp_netdevice_vport_event(struct net_device *dev,
 	int err = 0;
 
 	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
+	if (!mlxsw_sp_vport)
+		return 0;
 
 	switch (event) {
 	case NETDEV_PRECHANGEUPPER:
 		upper_dev = info->upper_dev;
-		if (!netif_is_bridge_master(upper_dev))
+		if (!netif_is_bridge_master(upper_dev) &&
+		    !netif_is_l3_master(upper_dev))
 			return -EINVAL;
 		if (!info->linking)
 			break;
 		/* We can't have multiple VLAN interfaces configured on
 		 * the same port and being members in the same bridge.
 		 */
-		if (!mlxsw_sp_port_master_bridge_check(mlxsw_sp_port,
+		if (netif_is_bridge_master(upper_dev) &&
+		    !mlxsw_sp_port_master_bridge_check(mlxsw_sp_port,
 						       upper_dev))
 			return -EINVAL;
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
-		if (info->linking) {
-			if (WARN_ON(!mlxsw_sp_vport))
-				return -EINVAL;
-			err = mlxsw_sp_vport_bridge_join(mlxsw_sp_vport,
-							 upper_dev);
+		if (netif_is_bridge_master(upper_dev)) {
+			if (info->linking)
+				err = mlxsw_sp_vport_bridge_join(mlxsw_sp_vport,
+								 upper_dev);
+			else
+				mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport);
+		} else if (netif_is_l3_master(upper_dev)) {
+			if (info->linking)
+				err = mlxsw_sp_vport_vrf_join(mlxsw_sp_vport);
+			else
+				mlxsw_sp_vport_vrf_leave(mlxsw_sp_vport);
 		} else {
-			if (!mlxsw_sp_vport)
-				return 0;
-			mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport);
+			err = -EINVAL;
+			WARN_ON(1);
 		}
+		break;
 	}
 
 	return err;
@@ -4862,6 +4482,47 @@ static int mlxsw_sp_netdevice_lag_vport_event(struct net_device *lag_dev,
 	return 0;
 }
 
+static int mlxsw_sp_netdevice_bridge_vlan_event(struct net_device *vlan_dev,
+						unsigned long event, void *ptr)
+{
+	struct netdev_notifier_changeupper_info *info;
+	struct mlxsw_sp *mlxsw_sp;
+	int err = 0;
+
+	mlxsw_sp = mlxsw_sp_lower_get(vlan_dev);
+	if (!mlxsw_sp)
+		return 0;
+
+	info = ptr;
+
+	switch (event) {
+	case NETDEV_PRECHANGEUPPER:
+		/* VLAN devices are only allowed on top of the
+		 * VLAN-aware bridge.
+		 */
+		if (WARN_ON(vlan_dev_real_dev(vlan_dev) !=
+			    mlxsw_sp->master_bridge.dev))
+			return -EINVAL;
+		if (!netif_is_l3_master(info->upper_dev))
+			return -EINVAL;
+		break;
+	case NETDEV_CHANGEUPPER:
+		if (netif_is_l3_master(info->upper_dev)) {
+			if (info->linking)
+				err = mlxsw_sp_bridge_vrf_join(mlxsw_sp,
+							       vlan_dev);
+			else
+				mlxsw_sp_bridge_vrf_leave(mlxsw_sp, vlan_dev);
+		} else {
+			err = -EINVAL;
+			WARN_ON(1);
+		}
+		break;
+	}
+
+	return err;
+}
+
 static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
 					 unsigned long event, void *ptr)
 {
@@ -4874,6 +4535,9 @@ static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
 	else if (netif_is_lag_master(real_dev))
 		return mlxsw_sp_netdevice_lag_vport_event(real_dev, event, ptr,
 							  vid);
+	else if (netif_is_bridge_master(real_dev))
+		return mlxsw_sp_netdevice_bridge_vlan_event(vlan_dev, event,
+							    ptr);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 13ec85e7c392..c245e4c3d9ad 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -58,40 +58,18 @@
 #define MLXSW_SP_VFID_MAX 1024	/* Bridged VLAN interfaces */
 
 #define MLXSW_SP_RFID_BASE 15360
-#define MLXSW_SP_INVALID_RIF 0xffff
 
 #define MLXSW_SP_MID_MAX 7000
 
 #define MLXSW_SP_PORTS_PER_CLUSTER_MAX 4
 
-#define MLXSW_SP_LPM_TREE_MIN 2 /* trees 0 and 1 are reserved */
-#define MLXSW_SP_LPM_TREE_MAX 22
-#define MLXSW_SP_LPM_TREE_COUNT (MLXSW_SP_LPM_TREE_MAX - MLXSW_SP_LPM_TREE_MIN)
-
 #define MLXSW_SP_PORT_BASE_SPEED 25000	/* Mb/s */
 
-#define MLXSW_SP_BYTES_PER_CELL 96
-
-#define MLXSW_SP_BYTES_TO_CELLS(b) DIV_ROUND_UP(b, MLXSW_SP_BYTES_PER_CELL)
-#define MLXSW_SP_CELLS_TO_BYTES(c) (c * MLXSW_SP_BYTES_PER_CELL)
-
 #define MLXSW_SP_KVD_LINEAR_SIZE 65536 /* entries */
 #define MLXSW_SP_KVD_GRANULARITY 128
 
-/* Maximum delay buffer needed in case of PAUSE frames, in cells.
- * Assumes 100m cable and maximum MTU.
- */
-#define MLXSW_SP_PAUSE_DELAY 612
-
-#define MLXSW_SP_CELL_FACTOR 2	/* 2 * cell_size / (IPG + cell_size + 1) */
-
-static inline u16 mlxsw_sp_pfc_delay_get(int mtu, u16 delay)
-{
-	delay = MLXSW_SP_BYTES_TO_CELLS(DIV_ROUND_UP(delay, BITS_PER_BYTE));
-	return MLXSW_SP_CELL_FACTOR * delay + MLXSW_SP_BYTES_TO_CELLS(mtu);
-}
-
 struct mlxsw_sp_port;
+struct mlxsw_sp_rif;
 
 struct mlxsw_sp_upper {
 	struct net_device *dev;
@@ -103,21 +81,10 @@ struct mlxsw_sp_fid {
 	struct list_head list;
 	unsigned int ref_count;
 	struct net_device *dev;
-	struct mlxsw_sp_rif *r;
+	struct mlxsw_sp_rif *rif;
 	u16 fid;
 };
 
-struct mlxsw_sp_rif {
-	struct list_head nexthop_list;
-	struct list_head neigh_list;
-	struct net_device *dev;
-	unsigned int ref_count;
-	struct mlxsw_sp_fid *f;
-	unsigned char addr[ETH_ALEN];
-	int mtu;
-	u16 rif;
-};
-
 struct mlxsw_sp_mid {
 	struct list_head list;
 	unsigned char addr[ETH_ALEN];
@@ -141,16 +108,6 @@ static inline bool mlxsw_sp_fid_is_vfid(u16 fid)
 	return fid >= MLXSW_SP_VFID_BASE && fid < MLXSW_SP_RFID_BASE;
 }
 
-static inline bool mlxsw_sp_fid_is_rfid(u16 fid)
-{
-	return fid >= MLXSW_SP_RFID_BASE;
-}
-
-static inline u16 mlxsw_sp_rif_sp_to_fid(u16 rif)
-{
-	return MLXSW_SP_RFID_BASE + rif;
-}
-
 struct mlxsw_sp_sb_pr {
 	enum mlxsw_reg_sbpr_mode mode;
 	u32 size;
@@ -177,12 +134,15 @@ struct mlxsw_sp_sb_pm {
 #define MLXSW_SP_SB_POOL_COUNT	4
 #define MLXSW_SP_SB_TC_COUNT	8
 
+struct mlxsw_sp_sb_port {
+	struct mlxsw_sp_sb_cm cms[2][MLXSW_SP_SB_TC_COUNT];
+	struct mlxsw_sp_sb_pm pms[2][MLXSW_SP_SB_POOL_COUNT];
+};
+
 struct mlxsw_sp_sb {
 	struct mlxsw_sp_sb_pr prs[2][MLXSW_SP_SB_POOL_COUNT];
-	struct {
-		struct mlxsw_sp_sb_cm cms[2][MLXSW_SP_SB_TC_COUNT];
-		struct mlxsw_sp_sb_pm pms[2][MLXSW_SP_SB_POOL_COUNT];
-	} ports[MLXSW_PORT_MAX_PORTS];
+	struct mlxsw_sp_sb_port *ports;
+	u32 cell_size;
 };
 
 #define MLXSW_SP_PREFIX_COUNT (sizeof(struct in6_addr) * BITS_PER_BYTE)
@@ -207,11 +167,9 @@ struct mlxsw_sp_fib;
 
 struct mlxsw_sp_vr {
 	u16 id; /* virtual router ID */
-	bool used;
-	enum mlxsw_sp_l3proto proto;
 	u32 tb_id; /* kernel fib table id */
-	struct mlxsw_sp_lpm_tree *lpm_tree;
-	struct mlxsw_sp_fib *fib;
+	unsigned int rif_count;
+	struct mlxsw_sp_fib *fib4;
 };
 
 enum mlxsw_sp_span_type {
@@ -253,12 +211,15 @@ struct mlxsw_sp_port_mall_tc_entry {
 };
 
 struct mlxsw_sp_router {
-	struct mlxsw_sp_lpm_tree lpm_trees[MLXSW_SP_LPM_TREE_COUNT];
 	struct mlxsw_sp_vr *vrs;
 	struct rhashtable neigh_ht;
 	struct rhashtable nexthop_group_ht;
 	struct rhashtable nexthop_ht;
 	struct {
+		struct mlxsw_sp_lpm_tree *trees;
+		unsigned int tree_count;
+	} lpm;
+	struct {
 		struct delayed_work dw;
 		unsigned long interval;	/* ms */
 	} neighs_update;
@@ -269,6 +230,7 @@ struct mlxsw_sp_router {
 };
 
 struct mlxsw_sp_acl;
+struct mlxsw_sp_counter_pool;
 
 struct mlxsw_sp {
 	struct {
@@ -296,7 +258,7 @@ struct mlxsw_sp {
 	u32 ageing_time;
 	struct mlxsw_sp_upper master_bridge;
 	struct mlxsw_sp_upper *lags;
-	u8 port_to_module[MLXSW_PORT_MAX_PORTS];
+	u8 *port_to_module;
 	struct mlxsw_sp_sb sb;
 	struct mlxsw_sp_router router;
 	struct mlxsw_sp_acl *acl;
@@ -304,6 +266,7 @@ struct mlxsw_sp {
 		DECLARE_BITMAP(usage, MLXSW_SP_KVD_LINEAR_SIZE);
 	} kvdl;
 
+	struct mlxsw_sp_counter_pool *counter_pool;
 	struct {
 		struct mlxsw_sp_span_entry *entries;
 		int entries_count;
@@ -317,6 +280,18 @@ mlxsw_sp_lag_get(struct mlxsw_sp *mlxsw_sp, u16 lag_id)
 	return &mlxsw_sp->lags[lag_id];
 }
 
+static inline u32 mlxsw_sp_cells_bytes(const struct mlxsw_sp *mlxsw_sp,
+				       u32 cells)
+{
+	return mlxsw_sp->sb.cell_size * cells;
+}
+
+static inline u32 mlxsw_sp_bytes_cells(const struct mlxsw_sp *mlxsw_sp,
+				       u32 bytes)
+{
+	return DIV_ROUND_UP(bytes, mlxsw_sp->sb.cell_size);
+}
+
 struct mlxsw_sp_port_pcpu_stats {
 	u64			rx_packets;
 	u64			rx_bytes;
@@ -386,6 +361,7 @@ struct mlxsw_sp_port {
 };
 
 bool mlxsw_sp_port_dev_check(const struct net_device *dev);
+struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev);
 struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev);
 void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port);
 
@@ -497,19 +473,6 @@ mlxsw_sp_vfid_find(const struct mlxsw_sp *mlxsw_sp,
 	return NULL;
 }
 
-static inline struct mlxsw_sp_rif *
-mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
-			 const struct net_device *dev)
-{
-	int i;
-
-	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
-		if (mlxsw_sp->rifs[i] && mlxsw_sp->rifs[i]->dev == dev)
-			return mlxsw_sp->rifs[i];
-
-	return NULL;
-}
-
 enum mlxsw_sp_flood_table {
 	MLXSW_SP_FLOOD_TABLE_UC,
 	MLXSW_SP_FLOOD_TABLE_BC,
@@ -570,8 +533,6 @@ int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid,
 			bool adding);
 struct mlxsw_sp_fid *mlxsw_sp_fid_create(struct mlxsw_sp *mlxsw_sp, u16 fid);
 void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f);
-void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp,
-				 struct mlxsw_sp_rif *r);
 int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port,
 			  enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index,
 			  bool dwrr, u8 dwrr_weight);
@@ -608,10 +569,22 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp);
 int mlxsw_sp_router_netevent_event(struct notifier_block *unused,
 				   unsigned long event, void *ptr);
-void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
-				   struct mlxsw_sp_rif *r);
-
-int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count);
+int mlxsw_sp_netdevice_router_port_event(struct net_device *dev);
+int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
+			    unsigned long event, void *ptr);
+void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_rif *rif);
+int mlxsw_sp_vport_vrf_join(struct mlxsw_sp_port *mlxsw_sp_vport);
+void mlxsw_sp_vport_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_vport);
+int mlxsw_sp_port_vrf_join(struct mlxsw_sp_port *mlxsw_sp_port);
+void mlxsw_sp_port_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_port);
+int mlxsw_sp_bridge_vrf_join(struct mlxsw_sp *mlxsw_sp,
+			     struct net_device *l3_dev);
+void mlxsw_sp_bridge_vrf_leave(struct mlxsw_sp *mlxsw_sp,
+			       struct net_device *l3_dev);
+
+int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
+			u32 *p_entry_index);
 void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index);
 
 struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl);
@@ -620,6 +593,8 @@ struct mlxsw_sp_acl_rule_info {
 	unsigned int priority;
 	struct mlxsw_afk_element_values values;
 	struct mlxsw_afa_block *act_block;
+	unsigned int counter_index;
+	bool counter_valid;
 };
 
 enum mlxsw_sp_acl_profile {
@@ -639,6 +614,8 @@ struct mlxsw_sp_acl_profile_ops {
 			void *ruleset_priv, void *rule_priv,
 			struct mlxsw_sp_acl_rule_info *rulei);
 	void (*rule_del)(struct mlxsw_sp *mlxsw_sp, void *rule_priv);
+	int (*rule_activity_get)(struct mlxsw_sp *mlxsw_sp, void *rule_priv,
+				 bool *activity);
 };
 
 struct mlxsw_sp_acl_ops {
@@ -679,6 +656,11 @@ int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei);
 int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_rule_info *rulei,
 			       struct net_device *out_dev);
+int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_rule_info *rulei,
+				u32 action, u16 vid, u16 proto, u8 prio);
+int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_rule_info *rulei);
 
 struct mlxsw_sp_acl_rule;
 
@@ -698,6 +680,9 @@ mlxsw_sp_acl_rule_lookup(struct mlxsw_sp *mlxsw_sp,
 			 unsigned long cookie);
 struct mlxsw_sp_acl_rule_info *
 mlxsw_sp_acl_rule_rulei(struct mlxsw_sp_acl_rule *rule);
+int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_rule *rule,
+				u64 *packets, u64 *bytes, u64 *last_use);
 
 int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp);
@@ -708,5 +693,14 @@ int mlxsw_sp_flower_replace(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress,
 			    __be16 protocol, struct tc_cls_flower_offload *f);
 void mlxsw_sp_flower_destroy(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress,
 			     struct tc_cls_flower_offload *f);
+int mlxsw_sp_flower_stats(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress,
+			  struct tc_cls_flower_offload *f);
+int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp,
+			      unsigned int counter_index, u64 *packets,
+			      u64 *bytes);
+int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+				unsigned int *p_counter_index);
+void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp,
+				unsigned int counter_index);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 8a18b3aa70dc..d3b791f69f5b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -39,6 +39,7 @@
 #include <linux/string.h>
 #include <linux/rhashtable.h>
 #include <linux/netdevice.h>
+#include <net/tc_act/tc_vlan.h>
 
 #include "reg.h"
 #include "core.h"
@@ -49,10 +50,17 @@
 #include "spectrum_acl_flex_keys.h"
 
 struct mlxsw_sp_acl {
+	struct mlxsw_sp *mlxsw_sp;
 	struct mlxsw_afk *afk;
 	struct mlxsw_afa *afa;
 	const struct mlxsw_sp_acl_ops *ops;
 	struct rhashtable ruleset_ht;
+	struct list_head rules;
+	struct {
+		struct delayed_work dw;
+		unsigned long interval;	/* ms */
+#define MLXSW_SP_ACL_RULE_ACTIVITY_UPDATE_PERIOD_MS 1000
+	} rule_activity_update;
 	unsigned long priv[0];
 	/* priv has to be always the last item */
 };
@@ -79,9 +87,13 @@ struct mlxsw_sp_acl_ruleset {
 
 struct mlxsw_sp_acl_rule {
 	struct rhash_head ht_node; /* Member of rule HT */
+	struct list_head list;
 	unsigned long cookie; /* HT key */
 	struct mlxsw_sp_acl_ruleset *ruleset;
 	struct mlxsw_sp_acl_rule_info *rulei;
+	u64 last_used;
+	u64 last_packets;
+	u64 last_bytes;
 	unsigned long priv[0];
 	/* priv has to be always the last item */
 };
@@ -237,6 +249,27 @@ void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_acl_ruleset_ref_dec(mlxsw_sp, ruleset);
 }
 
+static int
+mlxsw_sp_acl_rulei_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_rule_info *rulei)
+{
+	int err;
+
+	err = mlxsw_sp_flow_counter_alloc(mlxsw_sp, &rulei->counter_index);
+	if (err)
+		return err;
+	rulei->counter_valid = true;
+	return 0;
+}
+
+static void
+mlxsw_sp_acl_rulei_counter_free(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_rule_info *rulei)
+{
+	rulei->counter_valid = false;
+	mlxsw_sp_flow_counter_free(mlxsw_sp, rulei->counter_index);
+}
+
 struct mlxsw_sp_acl_rule_info *
 mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl)
 {
@@ -335,6 +368,41 @@ int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
 					  local_port, in_port);
 }
 
+int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_rule_info *rulei,
+				u32 action, u16 vid, u16 proto, u8 prio)
+{
+	u8 ethertype;
+
+	if (action == TCA_VLAN_ACT_MODIFY) {
+		switch (proto) {
+		case ETH_P_8021Q:
+			ethertype = 0;
+			break;
+		case ETH_P_8021AD:
+			ethertype = 1;
+			break;
+		default:
+			dev_err(mlxsw_sp->bus_info->dev, "Unsupported VLAN protocol %#04x\n",
+				proto);
+			return -EINVAL;
+		}
+
+		return mlxsw_afa_block_append_vlan_modify(rulei->act_block,
+							  vid, prio, ethertype);
+	} else {
+		dev_err(mlxsw_sp->bus_info->dev, "Unsupported VLAN action\n");
+		return -EINVAL;
+	}
+}
+
+int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_rule_info *rulei)
+{
+	return mlxsw_afa_block_append_counter(rulei->act_block,
+					      rulei->counter_index);
+}
+
 struct mlxsw_sp_acl_rule *
 mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_ruleset *ruleset,
@@ -358,8 +426,14 @@ mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 		err = PTR_ERR(rule->rulei);
 		goto err_rulei_create;
 	}
+
+	err = mlxsw_sp_acl_rulei_counter_alloc(mlxsw_sp, rule->rulei);
+	if (err)
+		goto err_counter_alloc;
 	return rule;
 
+err_counter_alloc:
+	mlxsw_sp_acl_rulei_destroy(rule->rulei);
 err_rulei_create:
 	kfree(rule);
 err_alloc:
@@ -372,6 +446,7 @@ void mlxsw_sp_acl_rule_destroy(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset;
 
+	mlxsw_sp_acl_rulei_counter_free(mlxsw_sp, rule->rulei);
 	mlxsw_sp_acl_rulei_destroy(rule->rulei);
 	kfree(rule);
 	mlxsw_sp_acl_ruleset_ref_dec(mlxsw_sp, ruleset);
@@ -393,6 +468,7 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_rhashtable_insert;
 
+	list_add_tail(&rule->list, &mlxsw_sp->acl->rules);
 	return 0;
 
 err_rhashtable_insert:
@@ -406,6 +482,7 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset;
 	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
 
+	list_del(&rule->list);
 	rhashtable_remove_fast(&ruleset->rule_ht, &rule->ht_node,
 			       mlxsw_sp_acl_rule_ht_params);
 	ops->rule_del(mlxsw_sp, rule->priv);
@@ -426,6 +503,90 @@ mlxsw_sp_acl_rule_rulei(struct mlxsw_sp_acl_rule *rule)
 	return rule->rulei;
 }
 
+static int mlxsw_sp_acl_rule_activity_update(struct mlxsw_sp *mlxsw_sp,
+					     struct mlxsw_sp_acl_rule *rule)
+{
+	struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset;
+	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
+	bool active;
+	int err;
+
+	err = ops->rule_activity_get(mlxsw_sp, rule->priv, &active);
+	if (err)
+		return err;
+	if (active)
+		rule->last_used = jiffies;
+	return 0;
+}
+
+static int mlxsw_sp_acl_rules_activity_update(struct mlxsw_sp_acl *acl)
+{
+	struct mlxsw_sp_acl_rule *rule;
+	int err;
+
+	/* Protect internal structures from changes */
+	rtnl_lock();
+	list_for_each_entry(rule, &acl->rules, list) {
+		err = mlxsw_sp_acl_rule_activity_update(acl->mlxsw_sp,
+							rule);
+		if (err)
+			goto err_rule_update;
+	}
+	rtnl_unlock();
+	return 0;
+
+err_rule_update:
+	rtnl_unlock();
+	return err;
+}
+
+static void mlxsw_sp_acl_rule_activity_work_schedule(struct mlxsw_sp_acl *acl)
+{
+	unsigned long interval = acl->rule_activity_update.interval;
+
+	mlxsw_core_schedule_dw(&acl->rule_activity_update.dw,
+			       msecs_to_jiffies(interval));
+}
+
+static void mlxsw_sp_acl_rul_activity_update_work(struct work_struct *work)
+{
+	struct mlxsw_sp_acl *acl = container_of(work, struct mlxsw_sp_acl,
+						rule_activity_update.dw.work);
+	int err;
+
+	err = mlxsw_sp_acl_rules_activity_update(acl);
+	if (err)
+		dev_err(acl->mlxsw_sp->bus_info->dev, "Could not update acl activity");
+
+	mlxsw_sp_acl_rule_activity_work_schedule(acl);
+}
+
+int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_rule *rule,
+				u64 *packets, u64 *bytes, u64 *last_use)
+
+{
+	struct mlxsw_sp_acl_rule_info *rulei;
+	u64 current_packets;
+	u64 current_bytes;
+	int err;
+
+	rulei = mlxsw_sp_acl_rule_rulei(rule);
+	err = mlxsw_sp_flow_counter_get(mlxsw_sp, rulei->counter_index,
+					&current_packets, &current_bytes);
+	if (err)
+		return err;
+
+	*packets = current_packets - rule->last_packets;
+	*bytes = current_bytes - rule->last_bytes;
+	*last_use = rule->last_used;
+
+	rule->last_bytes = current_bytes;
+	rule->last_packets = current_packets;
+
+	return 0;
+}
+
 #define MLXSW_SP_KDVL_ACT_EXT_SIZE 1
 
 static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
@@ -434,7 +595,6 @@ static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
 	struct mlxsw_sp *mlxsw_sp = priv;
 	char pefa_pl[MLXSW_REG_PEFA_LEN];
 	u32 kvdl_index;
-	int ret;
 	int err;
 
 	/* The first action set of a TCAM entry is stored directly in TCAM,
@@ -443,10 +603,10 @@ static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
 	if (is_first)
 		return 0;
 
-	ret = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KDVL_ACT_EXT_SIZE);
-	if (ret < 0)
-		return ret;
-	kvdl_index = ret;
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KDVL_ACT_EXT_SIZE,
+				  &kvdl_index);
+	if (err)
+		return err;
 	mlxsw_reg_pefa_pack(pefa_pl, kvdl_index, enc_actions);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pefa), pefa_pl);
 	if (err)
@@ -475,13 +635,11 @@ static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
 	struct mlxsw_sp *mlxsw_sp = priv;
 	char ppbs_pl[MLXSW_REG_PPBS_LEN];
 	u32 kvdl_index;
-	int ret;
 	int err;
 
-	ret = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1);
-	if (ret < 0)
-		return ret;
-	kvdl_index = ret;
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1, &kvdl_index);
+	if (err)
+		return err;
 	mlxsw_reg_ppbs_pack(ppbs_pl, kvdl_index, local_port);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ppbs), ppbs_pl);
 	if (err)
@@ -518,7 +676,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 	if (!acl)
 		return -ENOMEM;
 	mlxsw_sp->acl = acl;
-
+	acl->mlxsw_sp = mlxsw_sp;
 	acl->afk = mlxsw_afk_create(MLXSW_CORE_RES_GET(mlxsw_sp->core,
 						       ACL_FLEX_KEYS),
 				    mlxsw_sp_afk_blocks,
@@ -541,11 +699,18 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 	if (err)
 		goto err_rhashtable_init;
 
+	INIT_LIST_HEAD(&acl->rules);
 	err = acl_ops->init(mlxsw_sp, acl->priv);
 	if (err)
 		goto err_acl_ops_init;
 
 	acl->ops = acl_ops;
+
+	/* Create the delayed work for the rule activity_update */
+	INIT_DELAYED_WORK(&acl->rule_activity_update.dw,
+			  mlxsw_sp_acl_rul_activity_update_work);
+	acl->rule_activity_update.interval = MLXSW_SP_ACL_RULE_ACTIVITY_UPDATE_PERIOD_MS;
+	mlxsw_core_schedule_dw(&acl->rule_activity_update.dw, 0);
 	return 0;
 
 err_acl_ops_init:
@@ -564,7 +729,9 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp)
 	struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
 	const struct mlxsw_sp_acl_ops *acl_ops = acl->ops;
 
+	cancel_delayed_work_sync(&mlxsw_sp->acl->rule_activity_update.dw);
 	acl_ops->fini(mlxsw_sp, acl->priv);
+	WARN_ON(!list_empty(&acl->rules));
 	rhashtable_destroy(&acl->ruleset_ht);
 	mlxsw_afa_destroy(acl->afa);
 	mlxsw_afk_destroy(acl->afk);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
index 82b81cf7f4a7..af7b7bad48df 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
@@ -39,11 +39,15 @@
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_dmac[] = {
 	MLXSW_AFK_ELEMENT_INST_BUF(DMAC, 0x00, 6),
+	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
 	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac[] = {
 	MLXSW_AFK_ELEMENT_INST_BUF(SMAC, 0x00, 6),
+	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
 	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
 };
 
@@ -65,6 +69,8 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_dip[] = {
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_ex[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x00, 0, 12),
+	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 29, 3),
 	MLXSW_AFK_ELEMENT_INST_U32(SRC_L4_PORT, 0x08, 0, 16),
 	MLXSW_AFK_ELEMENT_INST_U32(DST_L4_PORT, 0x0C, 0, 16),
 };
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index 7382832215fa..3a24289979d9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -561,6 +561,24 @@ mlxsw_sp_acl_tcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
 }
 
+static int
+mlxsw_sp_acl_tcam_region_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
+					    struct mlxsw_sp_acl_tcam_region *region,
+					    unsigned int offset,
+					    bool *activity)
+{
+	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
+	int err;
+
+	mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_QUERY_CLEAR_ON_READ,
+			     region->tcam_region_info, offset);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+	if (err)
+		return err;
+	*activity = mlxsw_reg_ptce2_a_get(ptce2_pl);
+	return 0;
+}
+
 #define MLXSW_SP_ACL_TCAM_CATCHALL_PRIO (~0U)
 
 static int
@@ -940,6 +958,19 @@ static void mlxsw_sp_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk);
 }
 
+static int
+mlxsw_sp_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_acl_tcam_entry *entry,
+				     bool *activity)
+{
+	struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk;
+	struct mlxsw_sp_acl_tcam_region *region = chunk->region;
+
+	return mlxsw_sp_acl_tcam_region_entry_activity_get(mlxsw_sp, region,
+							   entry->parman_item.index,
+							   activity);
+}
+
 static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = {
 	MLXSW_AFK_ELEMENT_SRC_SYS_PORT,
 	MLXSW_AFK_ELEMENT_DMAC,
@@ -950,6 +981,8 @@ static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = {
 	MLXSW_AFK_ELEMENT_DST_IP4,
 	MLXSW_AFK_ELEMENT_DST_L4_PORT,
 	MLXSW_AFK_ELEMENT_SRC_L4_PORT,
+	MLXSW_AFK_ELEMENT_VID,
+	MLXSW_AFK_ELEMENT_PCP,
 };
 
 static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv6[] = {
@@ -1046,6 +1079,16 @@ mlxsw_sp_acl_tcam_flower_rule_del(struct mlxsw_sp *mlxsw_sp, void *rule_priv)
 	mlxsw_sp_acl_tcam_entry_del(mlxsw_sp, &rule->entry);
 }
 
+static int
+mlxsw_sp_acl_tcam_flower_rule_activity_get(struct mlxsw_sp *mlxsw_sp,
+					   void *rule_priv, bool *activity)
+{
+	struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv;
+
+	return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, &rule->entry,
+						    activity);
+}
+
 static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = {
 	.ruleset_priv_size	= sizeof(struct mlxsw_sp_acl_tcam_flower_ruleset),
 	.ruleset_add		= mlxsw_sp_acl_tcam_flower_ruleset_add,
@@ -1055,6 +1098,7 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = {
 	.rule_priv_size		= sizeof(struct mlxsw_sp_acl_tcam_flower_rule),
 	.rule_add		= mlxsw_sp_acl_tcam_flower_rule_add,
 	.rule_del		= mlxsw_sp_acl_tcam_flower_rule_del,
+	.rule_activity_get	= mlxsw_sp_acl_tcam_flower_rule_activity_get,
 };
 
 static const struct mlxsw_sp_acl_profile_ops *
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index a7468262f118..997189cfe7fd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -162,8 +162,8 @@ static int mlxsw_sp_sb_pm_occ_query(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 }
 
 static const u16 mlxsw_sp_pbs[] = {
-	[0] = 2 * MLXSW_SP_BYTES_TO_CELLS(ETH_FRAME_LEN),
-	[9] = 2 * MLXSW_SP_BYTES_TO_CELLS(MLXSW_PORT_MAX_MTU),
+	[0] = 2 * ETH_FRAME_LEN,
+	[9] = 2 * MLXSW_PORT_MAX_MTU,
 };
 
 #define MLXSW_SP_PBS_LEN ARRAY_SIZE(mlxsw_sp_pbs)
@@ -171,20 +171,22 @@ static const u16 mlxsw_sp_pbs[] = {
 
 static int mlxsw_sp_port_pb_init(struct mlxsw_sp_port *mlxsw_sp_port)
 {
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char pbmc_pl[MLXSW_REG_PBMC_LEN];
 	int i;
 
 	mlxsw_reg_pbmc_pack(pbmc_pl, mlxsw_sp_port->local_port,
 			    0xffff, 0xffff / 2);
 	for (i = 0; i < MLXSW_SP_PBS_LEN; i++) {
+		u16 size = mlxsw_sp_bytes_cells(mlxsw_sp, mlxsw_sp_pbs[i]);
+
 		if (i == MLXSW_SP_PB_UNUSED)
 			continue;
-		mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, i, mlxsw_sp_pbs[i]);
+		mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, i, size);
 	}
 	mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl,
 					 MLXSW_REG_PBMC_PORT_SHARED_BUF_IDX, 0);
-	return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core,
-			       MLXSW_REG(pbmc), pbmc_pl);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
 }
 
 static int mlxsw_sp_port_pb_prio_init(struct mlxsw_sp_port *mlxsw_sp_port)
@@ -209,11 +211,25 @@ static int mlxsw_sp_port_headroom_init(struct mlxsw_sp_port *mlxsw_sp_port)
 	return mlxsw_sp_port_pb_prio_init(mlxsw_sp_port);
 }
 
-#define MLXSW_SP_SB_PR_INGRESS_SIZE				\
-	(15000000 - (2 * 20000 * MLXSW_PORT_MAX_PORTS))
+static int mlxsw_sp_sb_ports_init(struct mlxsw_sp *mlxsw_sp)
+{
+	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
+
+	mlxsw_sp->sb.ports = kcalloc(max_ports, sizeof(struct mlxsw_sp_sb_port),
+				     GFP_KERNEL);
+	if (!mlxsw_sp->sb.ports)
+		return -ENOMEM;
+	return 0;
+}
+
+static void mlxsw_sp_sb_ports_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	kfree(mlxsw_sp->sb.ports);
+}
+
+#define MLXSW_SP_SB_PR_INGRESS_SIZE	12440000
 #define MLXSW_SP_SB_PR_INGRESS_MNG_SIZE (200 * 1000)
-#define MLXSW_SP_SB_PR_EGRESS_SIZE				\
-	(14000000 - (8 * 1500 * MLXSW_PORT_MAX_PORTS))
+#define MLXSW_SP_SB_PR_EGRESS_SIZE	13232000
 
 #define MLXSW_SP_SB_PR(_mode, _size)	\
 	{				\
@@ -223,18 +239,17 @@ static int mlxsw_sp_port_headroom_init(struct mlxsw_sp_port *mlxsw_sp_port)
 
 static const struct mlxsw_sp_sb_pr mlxsw_sp_sb_prs_ingress[] = {
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
-		       MLXSW_SP_BYTES_TO_CELLS(MLXSW_SP_SB_PR_INGRESS_SIZE)),
+		       MLXSW_SP_SB_PR_INGRESS_SIZE),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
-		       MLXSW_SP_BYTES_TO_CELLS(MLXSW_SP_SB_PR_INGRESS_MNG_SIZE)),
+		       MLXSW_SP_SB_PR_INGRESS_MNG_SIZE),
 };
 
 #define MLXSW_SP_SB_PRS_INGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_prs_ingress)
 
 static const struct mlxsw_sp_sb_pr mlxsw_sp_sb_prs_egress[] = {
-	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
-		       MLXSW_SP_BYTES_TO_CELLS(MLXSW_SP_SB_PR_EGRESS_SIZE)),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, MLXSW_SP_SB_PR_EGRESS_SIZE),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
@@ -251,11 +266,9 @@ static int __mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	for (i = 0; i < prs_len; i++) {
-		const struct mlxsw_sp_sb_pr *pr;
+		u32 size = mlxsw_sp_bytes_cells(mlxsw_sp, prs[i].size);
 
-		pr = &prs[i];
-		err = mlxsw_sp_sb_pr_write(mlxsw_sp, i, dir,
-					   pr->mode, pr->size);
+		err = mlxsw_sp_sb_pr_write(mlxsw_sp, i, dir, prs[i].mode, size);
 		if (err)
 			return err;
 	}
@@ -284,7 +297,7 @@ static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp)
 	}
 
 static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_ingress[] = {
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(10000), 8, 0),
+	MLXSW_SP_SB_CM(10000, 8, 0),
 	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
 	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
 	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
@@ -293,20 +306,20 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_ingress[] = {
 	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
 	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
 	MLXSW_SP_SB_CM(0, 0, 0), /* dummy, this PG does not exist */
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(20000), 1, 3),
+	MLXSW_SP_SB_CM(20000, 1, 3),
 };
 
 #define MLXSW_SP_SB_CMS_INGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_cms_ingress)
 
 static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_egress[] = {
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
+	MLXSW_SP_SB_CM(1500, 9, 0),
+	MLXSW_SP_SB_CM(1500, 9, 0),
+	MLXSW_SP_SB_CM(1500, 9, 0),
+	MLXSW_SP_SB_CM(1500, 9, 0),
+	MLXSW_SP_SB_CM(1500, 9, 0),
+	MLXSW_SP_SB_CM(1500, 9, 0),
+	MLXSW_SP_SB_CM(1500, 9, 0),
+	MLXSW_SP_SB_CM(1500, 9, 0),
 	MLXSW_SP_SB_CM(0, 0, 0),
 	MLXSW_SP_SB_CM(0, 0, 0),
 	MLXSW_SP_SB_CM(0, 0, 0),
@@ -330,7 +343,7 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = {
 	MLXSW_SP_CPU_PORT_SB_CM,
 	MLXSW_SP_CPU_PORT_SB_CM,
 	MLXSW_SP_CPU_PORT_SB_CM,
-	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(10000), 0, 0),
+	MLXSW_SP_SB_CM(10000, 0, 0),
 	MLXSW_SP_CPU_PORT_SB_CM,
 	MLXSW_SP_CPU_PORT_SB_CM,
 	MLXSW_SP_CPU_PORT_SB_CM,
@@ -370,13 +383,17 @@ static int __mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 
 	for (i = 0; i < cms_len; i++) {
 		const struct mlxsw_sp_sb_cm *cm;
+		u32 min_buff;
 
 		if (i == 8 && dir == MLXSW_REG_SBXX_DIR_INGRESS)
 			continue; /* PG number 8 does not exist, skip it */
 		cm = &cms[i];
+		/* All pools are initialized using dynamic thresholds,
+		 * therefore 'max_buff' isn't specified in cells.
+		 */
+		min_buff = mlxsw_sp_bytes_cells(mlxsw_sp, cm->min_buff);
 		err = mlxsw_sp_sb_cm_write(mlxsw_sp, local_port, i, dir,
-					   cm->min_buff, cm->max_buff,
-					   cm->pool);
+					   min_buff, cm->max_buff, cm->pool);
 		if (err)
 			return err;
 	}
@@ -484,21 +501,21 @@ struct mlxsw_sp_sb_mm {
 	}
 
 static const struct mlxsw_sp_sb_mm mlxsw_sp_sb_mms[] = {
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
-	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
+	MLXSW_SP_SB_MM(20000, 0xff, 0),
 };
 
 #define MLXSW_SP_SB_MMS_LEN ARRAY_SIZE(mlxsw_sp_sb_mms)
@@ -511,10 +528,15 @@ static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp)
 
 	for (i = 0; i < MLXSW_SP_SB_MMS_LEN; i++) {
 		const struct mlxsw_sp_sb_mm *mc;
+		u32 min_buff;
 
 		mc = &mlxsw_sp_sb_mms[i];
-		mlxsw_reg_sbmm_pack(sbmm_pl, i, mc->min_buff,
-				    mc->max_buff, mc->pool);
+		/* All pools are initialized using dynamic thresholds,
+		 * therefore 'max_buff' isn't specified in cells.
+		 */
+		min_buff = mlxsw_sp_bytes_cells(mlxsw_sp, mc->min_buff);
+		mlxsw_reg_sbmm_pack(sbmm_pl, i, min_buff, mc->max_buff,
+				    mc->pool);
 		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbmm), sbmm_pl);
 		if (err)
 			return err;
@@ -522,32 +544,53 @@ static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp)
 	return 0;
 }
 
-#define MLXSW_SP_SB_SIZE (16 * 1024 * 1024)
-
 int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp)
 {
+	u64 sb_size;
 	int err;
 
-	err = mlxsw_sp_sb_prs_init(mlxsw_sp);
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, CELL_SIZE))
+		return -EIO;
+	mlxsw_sp->sb.cell_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, CELL_SIZE);
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_BUFFER_SIZE))
+		return -EIO;
+	sb_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_BUFFER_SIZE);
+
+	err = mlxsw_sp_sb_ports_init(mlxsw_sp);
 	if (err)
 		return err;
+	err = mlxsw_sp_sb_prs_init(mlxsw_sp);
+	if (err)
+		goto err_sb_prs_init;
 	err = mlxsw_sp_cpu_port_sb_cms_init(mlxsw_sp);
 	if (err)
-		return err;
+		goto err_sb_cpu_port_sb_cms_init;
 	err = mlxsw_sp_sb_mms_init(mlxsw_sp);
 	if (err)
-		return err;
-	return devlink_sb_register(priv_to_devlink(mlxsw_sp->core), 0,
-				   MLXSW_SP_SB_SIZE,
-				   MLXSW_SP_SB_POOL_COUNT,
-				   MLXSW_SP_SB_POOL_COUNT,
-				   MLXSW_SP_SB_TC_COUNT,
-				   MLXSW_SP_SB_TC_COUNT);
+		goto err_sb_mms_init;
+	err = devlink_sb_register(priv_to_devlink(mlxsw_sp->core), 0, sb_size,
+				  MLXSW_SP_SB_POOL_COUNT,
+				  MLXSW_SP_SB_POOL_COUNT,
+				  MLXSW_SP_SB_TC_COUNT,
+				  MLXSW_SP_SB_TC_COUNT);
+	if (err)
+		goto err_devlink_sb_register;
+
+	return 0;
+
+err_devlink_sb_register:
+err_sb_mms_init:
+err_sb_cpu_port_sb_cms_init:
+err_sb_prs_init:
+	mlxsw_sp_sb_ports_fini(mlxsw_sp);
+	return err;
 }
 
 void mlxsw_sp_buffers_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	devlink_sb_unregister(priv_to_devlink(mlxsw_sp->core), 0);
+	mlxsw_sp_sb_ports_fini(mlxsw_sp);
 }
 
 int mlxsw_sp_port_buffers_init(struct mlxsw_sp_port *mlxsw_sp_port)
@@ -596,7 +639,7 @@ int mlxsw_sp_sb_pool_get(struct mlxsw_core *mlxsw_core,
 	struct mlxsw_sp_sb_pr *pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool, dir);
 
 	pool_info->pool_type = (enum devlink_sb_pool_type) dir;
-	pool_info->size = MLXSW_SP_CELLS_TO_BYTES(pr->size);
+	pool_info->size = mlxsw_sp_cells_bytes(mlxsw_sp, pr->size);
 	pool_info->threshold_type = (enum devlink_sb_threshold_type) pr->mode;
 	return 0;
 }
@@ -606,9 +649,9 @@ int mlxsw_sp_sb_pool_set(struct mlxsw_core *mlxsw_core,
 			 enum devlink_sb_threshold_type threshold_type)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	u32 pool_size = mlxsw_sp_bytes_cells(mlxsw_sp, size);
 	u8 pool = pool_get(pool_index);
 	enum mlxsw_reg_sbxx_dir dir = dir_get(pool_index);
-	u32 pool_size = MLXSW_SP_BYTES_TO_CELLS(size);
 	enum mlxsw_reg_sbpr_mode mode;
 
 	if (size > MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_BUFFER_SIZE))
@@ -627,7 +670,7 @@ static u32 mlxsw_sp_sb_threshold_out(struct mlxsw_sp *mlxsw_sp, u8 pool,
 
 	if (pr->mode == MLXSW_REG_SBPR_MODE_DYNAMIC)
 		return max_buff - MLXSW_SP_SB_THRESHOLD_TO_ALPHA_OFFSET;
-	return MLXSW_SP_CELLS_TO_BYTES(max_buff);
+	return mlxsw_sp_cells_bytes(mlxsw_sp, max_buff);
 }
 
 static int mlxsw_sp_sb_threshold_in(struct mlxsw_sp *mlxsw_sp, u8 pool,
@@ -645,7 +688,7 @@ static int mlxsw_sp_sb_threshold_in(struct mlxsw_sp *mlxsw_sp, u8 pool,
 			return -EINVAL;
 		*p_max_buff = val;
 	} else {
-		*p_max_buff = MLXSW_SP_BYTES_TO_CELLS(threshold);
+		*p_max_buff = mlxsw_sp_bytes_cells(mlxsw_sp, threshold);
 	}
 	return 0;
 }
@@ -761,7 +804,7 @@ static void mlxsw_sp_sb_sr_occ_query_cb(struct mlxsw_core *mlxsw_core,
 
 	masked_count = 0;
 	for (local_port = cb_ctx.local_port_1;
-	     local_port < MLXSW_PORT_MAX_PORTS; local_port++) {
+	     local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) {
 		if (!mlxsw_sp->ports[local_port])
 			continue;
 		for (i = 0; i < MLXSW_SP_SB_TC_COUNT; i++) {
@@ -775,7 +818,7 @@ static void mlxsw_sp_sb_sr_occ_query_cb(struct mlxsw_core *mlxsw_core,
 	}
 	masked_count = 0;
 	for (local_port = cb_ctx.local_port_1;
-	     local_port < MLXSW_PORT_MAX_PORTS; local_port++) {
+	     local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) {
 		if (!mlxsw_sp->ports[local_port])
 			continue;
 		for (i = 0; i < MLXSW_SP_SB_TC_COUNT; i++) {
@@ -817,7 +860,7 @@ next_batch:
 		mlxsw_reg_sbsr_pg_buff_mask_set(sbsr_pl, i, 1);
 		mlxsw_reg_sbsr_tclass_mask_set(sbsr_pl, i, 1);
 	}
-	for (; local_port < MLXSW_PORT_MAX_PORTS; local_port++) {
+	for (; local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) {
 		if (!mlxsw_sp->ports[local_port])
 			continue;
 		mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1);
@@ -847,7 +890,7 @@ do_query:
 				    cb_priv);
 	if (err)
 		goto out;
-	if (local_port < MLXSW_PORT_MAX_PORTS)
+	if (local_port < mlxsw_core_max_ports(mlxsw_core))
 		goto next_batch;
 
 out:
@@ -882,7 +925,7 @@ next_batch:
 		mlxsw_reg_sbsr_pg_buff_mask_set(sbsr_pl, i, 1);
 		mlxsw_reg_sbsr_tclass_mask_set(sbsr_pl, i, 1);
 	}
-	for (; local_port < MLXSW_PORT_MAX_PORTS; local_port++) {
+	for (; local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) {
 		if (!mlxsw_sp->ports[local_port])
 			continue;
 		mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1);
@@ -908,7 +951,7 @@ do_query:
 				    &bulk_list, NULL, 0);
 	if (err)
 		goto out;
-	if (local_port < MLXSW_PORT_MAX_PORTS)
+	if (local_port < mlxsw_core_max_ports(mlxsw_core))
 		goto next_batch;
 
 out:
@@ -932,8 +975,8 @@ int mlxsw_sp_sb_occ_port_pool_get(struct mlxsw_core_port *mlxsw_core_port,
 	struct mlxsw_sp_sb_pm *pm = mlxsw_sp_sb_pm_get(mlxsw_sp, local_port,
 						       pool, dir);
 
-	*p_cur = MLXSW_SP_CELLS_TO_BYTES(pm->occ.cur);
-	*p_max = MLXSW_SP_CELLS_TO_BYTES(pm->occ.max);
+	*p_cur = mlxsw_sp_cells_bytes(mlxsw_sp, pm->occ.cur);
+	*p_max = mlxsw_sp_cells_bytes(mlxsw_sp, pm->occ.max);
 	return 0;
 }
 
@@ -951,7 +994,7 @@ int mlxsw_sp_sb_occ_tc_port_bind_get(struct mlxsw_core_port *mlxsw_core_port,
 	struct mlxsw_sp_sb_cm *cm = mlxsw_sp_sb_cm_get(mlxsw_sp, local_port,
 						       pg_buff, dir);
 
-	*p_cur = MLXSW_SP_CELLS_TO_BYTES(cm->occ.cur);
-	*p_max = MLXSW_SP_CELLS_TO_BYTES(cm->occ.max);
+	*p_cur = mlxsw_sp_cells_bytes(mlxsw_sp, cm->occ.cur);
+	*p_max = mlxsw_sp_cells_bytes(mlxsw_sp, cm->occ.max);
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
new file mode 100644
index 000000000000..0f46775e0307
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
@@ -0,0 +1,207 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Arkadi Sharshevsky <arkadis@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+
+#include "spectrum_cnt.h"
+
+#define MLXSW_SP_COUNTER_POOL_BANK_SIZE 4096
+
+struct mlxsw_sp_counter_sub_pool {
+	unsigned int base_index;
+	unsigned int size;
+	unsigned int entry_size;
+	unsigned int bank_count;
+};
+
+struct mlxsw_sp_counter_pool {
+	unsigned int pool_size;
+	unsigned long *usage; /* Usage bitmap */
+	struct mlxsw_sp_counter_sub_pool *sub_pools;
+};
+
+static struct mlxsw_sp_counter_sub_pool mlxsw_sp_counter_sub_pools[] = {
+	[MLXSW_SP_COUNTER_SUB_POOL_FLOW] = {
+		.bank_count = 6,
+	},
+	[MLXSW_SP_COUNTER_SUB_POOL_RIF] = {
+		.bank_count = 2,
+	}
+};
+
+static int mlxsw_sp_counter_pool_validate(struct mlxsw_sp *mlxsw_sp)
+{
+	unsigned int total_bank_config = 0;
+	unsigned int pool_size;
+	int i;
+
+	pool_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, COUNTER_POOL_SIZE);
+	/* Check config is valid, no bank over subscription */
+	for (i = 0; i < ARRAY_SIZE(mlxsw_sp_counter_sub_pools); i++)
+		total_bank_config += mlxsw_sp_counter_sub_pools[i].bank_count;
+	if (total_bank_config > pool_size / MLXSW_SP_COUNTER_POOL_BANK_SIZE + 1)
+		return -EINVAL;
+	return 0;
+}
+
+static int mlxsw_sp_counter_sub_pools_prepare(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_counter_sub_pool *sub_pool;
+
+	/* Prepare generic flow pool*/
+	sub_pool = &mlxsw_sp_counter_sub_pools[MLXSW_SP_COUNTER_SUB_POOL_FLOW];
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, COUNTER_SIZE_PACKETS_BYTES))
+		return -EIO;
+	sub_pool->entry_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+						  COUNTER_SIZE_PACKETS_BYTES);
+	/* Prepare erif pool*/
+	sub_pool = &mlxsw_sp_counter_sub_pools[MLXSW_SP_COUNTER_SUB_POOL_RIF];
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, COUNTER_SIZE_ROUTER_BASIC))
+		return -EIO;
+	sub_pool->entry_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+						  COUNTER_SIZE_ROUTER_BASIC);
+	return 0;
+}
+
+int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_counter_sub_pool *sub_pool;
+	struct mlxsw_sp_counter_pool *pool;
+	unsigned int base_index;
+	unsigned int map_size;
+	int i;
+	int err;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, COUNTER_POOL_SIZE))
+		return -EIO;
+
+	err = mlxsw_sp_counter_pool_validate(mlxsw_sp);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_counter_sub_pools_prepare(mlxsw_sp);
+	if (err)
+		return err;
+
+	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+	if (!pool)
+		return -ENOMEM;
+
+	pool->pool_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, COUNTER_POOL_SIZE);
+	map_size = BITS_TO_LONGS(pool->pool_size) * sizeof(unsigned long);
+
+	pool->usage = kzalloc(map_size, GFP_KERNEL);
+	if (!pool->usage) {
+		err = -ENOMEM;
+		goto err_usage_alloc;
+	}
+
+	pool->sub_pools = mlxsw_sp_counter_sub_pools;
+	/* Allocation is based on bank count which should be
+	 * specified for each sub pool statically.
+	 */
+	base_index = 0;
+	for (i = 0; i < ARRAY_SIZE(mlxsw_sp_counter_sub_pools); i++) {
+		sub_pool = &pool->sub_pools[i];
+		sub_pool->size = sub_pool->bank_count *
+				 MLXSW_SP_COUNTER_POOL_BANK_SIZE;
+		sub_pool->base_index = base_index;
+		base_index += sub_pool->size;
+		/* The last bank can't be fully used */
+		if (sub_pool->base_index + sub_pool->size > pool->pool_size)
+			sub_pool->size = pool->pool_size - sub_pool->base_index;
+	}
+
+	mlxsw_sp->counter_pool = pool;
+	return 0;
+
+err_usage_alloc:
+	kfree(pool);
+	return err;
+}
+
+void mlxsw_sp_counter_pool_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_counter_pool *pool = mlxsw_sp->counter_pool;
+
+	WARN_ON(find_first_bit(pool->usage, pool->pool_size) !=
+			       pool->pool_size);
+	kfree(pool->usage);
+	kfree(pool);
+}
+
+int mlxsw_sp_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+			   enum mlxsw_sp_counter_sub_pool_id sub_pool_id,
+			   unsigned int *p_counter_index)
+{
+	struct mlxsw_sp_counter_pool *pool = mlxsw_sp->counter_pool;
+	struct mlxsw_sp_counter_sub_pool *sub_pool;
+	unsigned int entry_index;
+	unsigned int stop_index;
+	int i;
+
+	sub_pool = &mlxsw_sp_counter_sub_pools[sub_pool_id];
+	stop_index = sub_pool->base_index + sub_pool->size;
+	entry_index = sub_pool->base_index;
+
+	entry_index = find_next_zero_bit(pool->usage, stop_index, entry_index);
+	if (entry_index == stop_index)
+		return -ENOBUFS;
+	/* The sub-pools can contain non-integer number of entries
+	 * so we must check for overflow
+	 */
+	if (entry_index + sub_pool->entry_size > stop_index)
+		return -ENOBUFS;
+	for (i = 0; i < sub_pool->entry_size; i++)
+		__set_bit(entry_index + i, pool->usage);
+
+	*p_counter_index = entry_index;
+	return 0;
+}
+
+void mlxsw_sp_counter_free(struct mlxsw_sp *mlxsw_sp,
+			   enum mlxsw_sp_counter_sub_pool_id sub_pool_id,
+			   unsigned int counter_index)
+{
+	struct mlxsw_sp_counter_pool *pool = mlxsw_sp->counter_pool;
+	struct mlxsw_sp_counter_sub_pool *sub_pool;
+	int i;
+
+	if (WARN_ON(counter_index >= pool->pool_size))
+		return;
+	sub_pool = &mlxsw_sp_counter_sub_pools[sub_pool_id];
+	for (i = 0; i < sub_pool->entry_size; i++)
+		__clear_bit(counter_index + i, pool->usage);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
new file mode 100644
index 000000000000..fd34d0a01073
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
@@ -0,0 +1,54 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Arkadi Sharshevsky <arkdis@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_SPECTRUM_CNT_H
+#define _MLXSW_SPECTRUM_CNT_H
+
+#include "spectrum.h"
+
+enum mlxsw_sp_counter_sub_pool_id {
+	MLXSW_SP_COUNTER_SUB_POOL_FLOW,
+	MLXSW_SP_COUNTER_SUB_POOL_RIF,
+};
+
+int mlxsw_sp_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+			   enum mlxsw_sp_counter_sub_pool_id sub_pool_id,
+			   unsigned int *p_counter_index);
+void mlxsw_sp_counter_free(struct mlxsw_sp *mlxsw_sp,
+			   enum mlxsw_sp_counter_sub_pool_id sub_pool_id,
+			   unsigned int counter_index);
+int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp);
+void mlxsw_sp_counter_pool_fini(struct mlxsw_sp *mlxsw_sp);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
new file mode 100644
index 000000000000..ea56f6ade6b4
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
@@ -0,0 +1,351 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Arkadi Sharshevsky <arakdis@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <net/devlink.h>
+
+#include "spectrum.h"
+#include "spectrum_dpipe.h"
+#include "spectrum_router.h"
+
+enum mlxsw_sp_field_metadata_id {
+	MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT,
+	MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD,
+	MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP,
+};
+
+static struct devlink_dpipe_field mlxsw_sp_dpipe_fields_metadata[] = {
+	{ .name = "erif_port",
+	  .id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT,
+	  .bitwidth = 32,
+	  .mapping_type = DEVLINK_DPIPE_FIELD_MAPPING_TYPE_IFINDEX,
+	},
+	{ .name = "l3_forward",
+	  .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD,
+	  .bitwidth = 1,
+	},
+	{ .name = "l3_drop",
+	  .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP,
+	  .bitwidth = 1,
+	},
+};
+
+enum mlxsw_sp_dpipe_header_id {
+	MLXSW_SP_DPIPE_HEADER_METADATA,
+};
+
+static struct devlink_dpipe_header mlxsw_sp_dpipe_header_metadata = {
+	.name = "mlxsw_meta",
+	.id = MLXSW_SP_DPIPE_HEADER_METADATA,
+	.fields = mlxsw_sp_dpipe_fields_metadata,
+	.fields_count = ARRAY_SIZE(mlxsw_sp_dpipe_fields_metadata),
+};
+
+static struct devlink_dpipe_header *mlxsw_dpipe_headers[] = {
+	&mlxsw_sp_dpipe_header_metadata,
+};
+
+static struct devlink_dpipe_headers mlxsw_sp_dpipe_headers = {
+	.headers = mlxsw_dpipe_headers,
+	.headers_count = ARRAY_SIZE(mlxsw_dpipe_headers),
+};
+
+static int mlxsw_sp_dpipe_table_erif_actions_dump(void *priv,
+						  struct sk_buff *skb)
+{
+	struct devlink_dpipe_action action = {0};
+	int err;
+
+	action.type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+	action.header = &mlxsw_sp_dpipe_header_metadata;
+	action.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD;
+
+	err = devlink_dpipe_action_put(skb, &action);
+	if (err)
+		return err;
+
+	action.type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+	action.header = &mlxsw_sp_dpipe_header_metadata;
+	action.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP;
+
+	return devlink_dpipe_action_put(skb, &action);
+}
+
+static int mlxsw_sp_dpipe_table_erif_matches_dump(void *priv,
+						  struct sk_buff *skb)
+{
+	struct devlink_dpipe_match match = {0};
+
+	match.type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+	match.header = &mlxsw_sp_dpipe_header_metadata;
+	match.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT;
+
+	return devlink_dpipe_match_put(skb, &match);
+}
+
+static void mlxsw_sp_erif_entry_clear(struct devlink_dpipe_entry *entry)
+{
+	unsigned int value_count, value_index;
+	struct devlink_dpipe_value *value;
+
+	value = entry->action_values;
+	value_count = entry->action_values_count;
+	for (value_index = 0; value_index < value_count; value_index++) {
+		kfree(value[value_index].value);
+		kfree(value[value_index].mask);
+	}
+
+	value = entry->match_values;
+	value_count = entry->match_values_count;
+	for (value_index = 0; value_index < value_count; value_index++) {
+		kfree(value[value_index].value);
+		kfree(value[value_index].mask);
+	}
+}
+
+static void
+mlxsw_sp_erif_match_action_prepare(struct devlink_dpipe_match *match,
+				   struct devlink_dpipe_action *action)
+{
+	action->type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+	action->header = &mlxsw_sp_dpipe_header_metadata;
+	action->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD;
+
+	match->type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+	match->header = &mlxsw_sp_dpipe_header_metadata;
+	match->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT;
+}
+
+static int mlxsw_sp_erif_entry_prepare(struct devlink_dpipe_entry *entry,
+				       struct devlink_dpipe_value *match_value,
+				       struct devlink_dpipe_match *match,
+				       struct devlink_dpipe_value *action_value,
+				       struct devlink_dpipe_action *action)
+{
+	entry->match_values = match_value;
+	entry->match_values_count = 1;
+
+	entry->action_values = action_value;
+	entry->action_values_count = 1;
+
+	match_value->match = match;
+	match_value->value_size = sizeof(u32);
+	match_value->value = kmalloc(match_value->value_size, GFP_KERNEL);
+	if (!match_value->value)
+		return -ENOMEM;
+
+	action_value->action = action;
+	action_value->value_size = sizeof(u32);
+	action_value->value = kmalloc(action_value->value_size, GFP_KERNEL);
+	if (!action_value->value)
+		goto err_action_alloc;
+	return 0;
+
+err_action_alloc:
+	kfree(match_value->value);
+	return -ENOMEM;
+}
+
+static int mlxsw_sp_erif_entry_get(struct mlxsw_sp *mlxsw_sp,
+				   struct devlink_dpipe_entry *entry,
+				   struct mlxsw_sp_rif *rif,
+				   bool counters_enabled)
+{
+	u32 *action_value;
+	u32 *rif_value;
+	u64 cnt;
+	int err;
+
+	/* Set Match RIF index */
+	rif_value = entry->match_values->value;
+	*rif_value = mlxsw_sp_rif_index(rif);
+	entry->match_values->mapping_value = mlxsw_sp_rif_dev_ifindex(rif);
+	entry->match_values->mapping_valid = true;
+
+	/* Set Action Forwarding */
+	action_value = entry->action_values->value;
+	*action_value = 1;
+
+	entry->counter_valid = false;
+	entry->counter = 0;
+	if (!counters_enabled)
+		return 0;
+
+	entry->index = mlxsw_sp_rif_index(rif);
+	err = mlxsw_sp_rif_counter_value_get(mlxsw_sp, rif,
+					     MLXSW_SP_RIF_COUNTER_EGRESS,
+					     &cnt);
+	if (!err) {
+		entry->counter = cnt;
+		entry->counter_valid = true;
+	}
+	return 0;
+}
+
+static int
+mlxsw_sp_table_erif_entries_dump(void *priv, bool counters_enabled,
+				 struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+	struct devlink_dpipe_value match_value = {{0}}, action_value = {{0}};
+	struct devlink_dpipe_action action = {0};
+	struct devlink_dpipe_match match = {0};
+	struct devlink_dpipe_entry entry = {0};
+	struct mlxsw_sp *mlxsw_sp = priv;
+	unsigned int rif_count;
+	int i, j;
+	int err;
+
+	mlxsw_sp_erif_match_action_prepare(&match, &action);
+	err = mlxsw_sp_erif_entry_prepare(&entry, &match_value, &match,
+					  &action_value, &action);
+	if (err)
+		return err;
+
+	rif_count = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
+	rtnl_lock();
+	i = 0;
+start_again:
+	err = devlink_dpipe_entry_ctx_prepare(dump_ctx);
+	if (err)
+		return err;
+	j = 0;
+	for (; i < rif_count; i++) {
+		if (!mlxsw_sp->rifs[i])
+			continue;
+		err = mlxsw_sp_erif_entry_get(mlxsw_sp, &entry,
+					      mlxsw_sp->rifs[i],
+					      counters_enabled);
+		if (err)
+			goto err_entry_get;
+		err = devlink_dpipe_entry_ctx_append(dump_ctx, &entry);
+		if (err) {
+			if (err == -EMSGSIZE) {
+				if (!j)
+					goto err_entry_append;
+				break;
+			}
+			goto err_entry_append;
+		}
+		j++;
+	}
+
+	devlink_dpipe_entry_ctx_close(dump_ctx);
+	if (i != rif_count)
+		goto start_again;
+	rtnl_unlock();
+
+	mlxsw_sp_erif_entry_clear(&entry);
+	return 0;
+err_entry_append:
+err_entry_get:
+	rtnl_unlock();
+	mlxsw_sp_erif_entry_clear(&entry);
+	return err;
+}
+
+static int mlxsw_sp_table_erif_counters_update(void *priv, bool enable)
+{
+	struct mlxsw_sp *mlxsw_sp = priv;
+	int i;
+
+	rtnl_lock();
+	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) {
+		if (!mlxsw_sp->rifs[i])
+			continue;
+		if (enable)
+			mlxsw_sp_rif_counter_alloc(mlxsw_sp,
+						   mlxsw_sp->rifs[i],
+						   MLXSW_SP_RIF_COUNTER_EGRESS);
+		else
+			mlxsw_sp_rif_counter_free(mlxsw_sp,
+						  mlxsw_sp->rifs[i],
+						  MLXSW_SP_RIF_COUNTER_EGRESS);
+	}
+	rtnl_unlock();
+	return 0;
+}
+
+static struct devlink_dpipe_table_ops mlxsw_sp_erif_ops = {
+	.matches_dump = mlxsw_sp_dpipe_table_erif_matches_dump,
+	.actions_dump = mlxsw_sp_dpipe_table_erif_actions_dump,
+	.entries_dump = mlxsw_sp_table_erif_entries_dump,
+	.counters_set_update = mlxsw_sp_table_erif_counters_update,
+};
+
+static int mlxsw_sp_dpipe_erif_table_init(struct mlxsw_sp *mlxsw_sp)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	u64 table_size;
+
+	table_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
+	return devlink_dpipe_table_register(devlink,
+					    MLXSW_SP_DPIPE_TABLE_NAME_ERIF,
+					    &mlxsw_sp_erif_ops,
+					    mlxsw_sp, table_size,
+					    false);
+}
+
+static void mlxsw_sp_dpipe_erif_table_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+
+	devlink_dpipe_table_unregister(devlink, MLXSW_SP_DPIPE_TABLE_NAME_ERIF);
+}
+
+int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	int err;
+
+	err = devlink_dpipe_headers_register(devlink,
+					     &mlxsw_sp_dpipe_headers);
+	if (err)
+		return err;
+	err = mlxsw_sp_dpipe_erif_table_init(mlxsw_sp);
+	if (err)
+		goto err_erif_register;
+	return 0;
+
+err_erif_register:
+	devlink_dpipe_headers_unregister(priv_to_devlink(mlxsw_sp->core));
+	return err;
+}
+
+void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+
+	mlxsw_sp_dpipe_erif_table_fini(mlxsw_sp);
+	devlink_dpipe_headers_unregister(devlink);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
new file mode 100644
index 000000000000..d2089298cba3
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
@@ -0,0 +1,43 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Arkadi Sharshevsky <arkadis@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_PIPELINE_H_
+#define _MLXSW_PIPELINE_H_
+
+int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp);
+void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp);
+
+#define MLXSW_SP_DPIPE_TABLE_NAME_ERIF "mlxsw_erif"
+
+#endif /* _MLXSW_PIPELINE_H_*/
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index ae6cccc666e4..3e7a0bcbba72 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -39,6 +39,7 @@
 #include <net/pkt_cls.h>
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
+#include <net/tc_act/tc_vlan.h>
 
 #include "spectrum.h"
 #include "core_acl_flex_keys.h"
@@ -55,6 +56,11 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 	if (tc_no_actions(exts))
 		return 0;
 
+	/* Count action is inserted first */
+	err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei);
+	if (err)
+		return err;
+
 	tcf_exts_to_list(exts, &actions);
 	list_for_each_entry(a, &actions, list) {
 		if (is_tcf_gact_shot(a)) {
@@ -73,6 +79,15 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 							 out_dev);
 			if (err)
 				return err;
+		} else if (is_tcf_vlan(a)) {
+			u16 proto = be16_to_cpu(tcf_vlan_push_proto(a));
+			u32 action = tcf_vlan_action(a);
+			u8 prio = tcf_vlan_push_prio(a);
+			u16 vid = tcf_vlan_push_vid(a);
+
+			return mlxsw_sp_acl_rulei_act_vlan(mlxsw_sp, rulei,
+							   action, vid,
+							   proto, prio);
 		} else {
 			dev_err(mlxsw_sp->bus_info->dev, "Unsupported action\n");
 			return -EOPNOTSUPP;
@@ -173,7 +188,8 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
-	      BIT(FLOW_DISSECTOR_KEY_PORTS))) {
+	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT(FLOW_DISSECTOR_KEY_VLAN))) {
 		dev_err(mlxsw_sp->bus_info->dev, "Unsupported key\n");
 		return -EOPNOTSUPP;
 	}
@@ -234,6 +250,27 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 					       sizeof(key->src));
 	}
 
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_dissector_key_vlan *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_VLAN,
+						  f->key);
+		struct flow_dissector_key_vlan *mask =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_VLAN,
+						  f->mask);
+		if (mask->vlan_id != 0)
+			mlxsw_sp_acl_rulei_keymask_u32(rulei,
+						       MLXSW_AFK_ELEMENT_VID,
+						       key->vlan_id,
+						       mask->vlan_id);
+		if (mask->vlan_priority != 0)
+			mlxsw_sp_acl_rulei_keymask_u32(rulei,
+						       MLXSW_AFK_ELEMENT_PCP,
+						       key->vlan_priority,
+						       mask->vlan_priority);
+	}
+
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS)
 		mlxsw_sp_flower_parse_ipv4(rulei, f);
 
@@ -314,3 +351,47 @@ void mlxsw_sp_flower_destroy(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress,
 
 	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
 }
+
+int mlxsw_sp_flower_stats(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress,
+			  struct tc_cls_flower_offload *f)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_acl_ruleset *ruleset;
+	struct mlxsw_sp_acl_rule *rule;
+	struct tc_action *a;
+	LIST_HEAD(actions);
+	u64 packets;
+	u64 lastuse;
+	u64 bytes;
+	int err;
+
+	ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, mlxsw_sp_port->dev,
+					   ingress,
+					   MLXSW_SP_ACL_PROFILE_FLOWER);
+	if (WARN_ON(IS_ERR(ruleset)))
+		return -EINVAL;
+
+	rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset, f->cookie);
+	if (!rule)
+		return -EINVAL;
+
+	err = mlxsw_sp_acl_rule_get_stats(mlxsw_sp, rule, &packets, &bytes,
+					  &lastuse);
+	if (err)
+		goto err_rule_get_stats;
+
+	preempt_disable();
+
+	tcf_exts_to_list(f->exts, &actions);
+	list_for_each_entry(a, &actions, list)
+		tcf_action_stats_update(a, bytes, packets, lastuse);
+
+	preempt_enable();
+
+	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
+	return 0;
+
+err_rule_get_stats:
+	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
index ac321e8e5c1a..26c26cd30c3d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
@@ -45,7 +45,8 @@
 	(MLXSW_SP_KVD_LINEAR_SIZE - MLXSW_SP_KVDL_CHUNKS_BASE)
 #define MLXSW_SP_CHUNK_MAX 32
 
-int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count)
+int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
+			u32 *p_entry_index)
 {
 	int entry_index;
 	int size;
@@ -72,7 +73,8 @@ int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count)
 
 		for (i = 0; i < type_entries; i++)
 			set_bit(entry_index + i, mlxsw_sp->kvdl.usage);
-		return entry_index;
+		*p_entry_index = entry_index;
+		return 0;
 	}
 	return -ENOBUFS;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index bd8de6b9be71..c70c59181014 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -41,14 +41,184 @@
 #include <linux/in6.h>
 #include <linux/notifier.h>
 #include <linux/inetdevice.h>
+#include <linux/netdevice.h>
 #include <net/netevent.h>
 #include <net/neighbour.h>
 #include <net/arp.h>
 #include <net/ip_fib.h>
+#include <net/fib_rules.h>
+#include <net/l3mdev.h>
 
 #include "spectrum.h"
 #include "core.h"
 #include "reg.h"
+#include "spectrum_cnt.h"
+#include "spectrum_dpipe.h"
+#include "spectrum_router.h"
+
+struct mlxsw_sp_rif {
+	struct list_head nexthop_list;
+	struct list_head neigh_list;
+	struct net_device *dev;
+	struct mlxsw_sp_fid *f;
+	unsigned char addr[ETH_ALEN];
+	int mtu;
+	u16 rif_index;
+	u16 vr_id;
+	unsigned int counter_ingress;
+	bool counter_ingress_valid;
+	unsigned int counter_egress;
+	bool counter_egress_valid;
+};
+
+static unsigned int *
+mlxsw_sp_rif_p_counter_get(struct mlxsw_sp_rif *rif,
+			   enum mlxsw_sp_rif_counter_dir dir)
+{
+	switch (dir) {
+	case MLXSW_SP_RIF_COUNTER_EGRESS:
+		return &rif->counter_egress;
+	case MLXSW_SP_RIF_COUNTER_INGRESS:
+		return &rif->counter_ingress;
+	}
+	return NULL;
+}
+
+static bool
+mlxsw_sp_rif_counter_valid_get(struct mlxsw_sp_rif *rif,
+			       enum mlxsw_sp_rif_counter_dir dir)
+{
+	switch (dir) {
+	case MLXSW_SP_RIF_COUNTER_EGRESS:
+		return rif->counter_egress_valid;
+	case MLXSW_SP_RIF_COUNTER_INGRESS:
+		return rif->counter_ingress_valid;
+	}
+	return false;
+}
+
+static void
+mlxsw_sp_rif_counter_valid_set(struct mlxsw_sp_rif *rif,
+			       enum mlxsw_sp_rif_counter_dir dir,
+			       bool valid)
+{
+	switch (dir) {
+	case MLXSW_SP_RIF_COUNTER_EGRESS:
+		rif->counter_egress_valid = valid;
+		break;
+	case MLXSW_SP_RIF_COUNTER_INGRESS:
+		rif->counter_ingress_valid = valid;
+		break;
+	}
+}
+
+static int mlxsw_sp_rif_counter_edit(struct mlxsw_sp *mlxsw_sp, u16 rif_index,
+				     unsigned int counter_index, bool enable,
+				     enum mlxsw_sp_rif_counter_dir dir)
+{
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+	bool is_egress = false;
+	int err;
+
+	if (dir == MLXSW_SP_RIF_COUNTER_EGRESS)
+		is_egress = true;
+	mlxsw_reg_ritr_rif_pack(ritr_pl, rif_index);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_ritr_counter_pack(ritr_pl, counter_index, enable,
+				    is_egress);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_rif *rif,
+				   enum mlxsw_sp_rif_counter_dir dir, u64 *cnt)
+{
+	char ricnt_pl[MLXSW_REG_RICNT_LEN];
+	unsigned int *p_counter_index;
+	bool valid;
+	int err;
+
+	valid = mlxsw_sp_rif_counter_valid_get(rif, dir);
+	if (!valid)
+		return -EINVAL;
+
+	p_counter_index = mlxsw_sp_rif_p_counter_get(rif, dir);
+	if (!p_counter_index)
+		return -EINVAL;
+	mlxsw_reg_ricnt_pack(ricnt_pl, *p_counter_index,
+			     MLXSW_REG_RICNT_OPCODE_NOP);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ricnt), ricnt_pl);
+	if (err)
+		return err;
+	*cnt = mlxsw_reg_ricnt_good_unicast_packets_get(ricnt_pl);
+	return 0;
+}
+
+static int mlxsw_sp_rif_counter_clear(struct mlxsw_sp *mlxsw_sp,
+				      unsigned int counter_index)
+{
+	char ricnt_pl[MLXSW_REG_RICNT_LEN];
+
+	mlxsw_reg_ricnt_pack(ricnt_pl, counter_index,
+			     MLXSW_REG_RICNT_OPCODE_CLEAR);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ricnt), ricnt_pl);
+}
+
+int mlxsw_sp_rif_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_rif *rif,
+			       enum mlxsw_sp_rif_counter_dir dir)
+{
+	unsigned int *p_counter_index;
+	int err;
+
+	p_counter_index = mlxsw_sp_rif_p_counter_get(rif, dir);
+	if (!p_counter_index)
+		return -EINVAL;
+	err = mlxsw_sp_counter_alloc(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_RIF,
+				     p_counter_index);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_rif_counter_clear(mlxsw_sp, *p_counter_index);
+	if (err)
+		goto err_counter_clear;
+
+	err = mlxsw_sp_rif_counter_edit(mlxsw_sp, rif->rif_index,
+					*p_counter_index, true, dir);
+	if (err)
+		goto err_counter_edit;
+	mlxsw_sp_rif_counter_valid_set(rif, dir, true);
+	return 0;
+
+err_counter_edit:
+err_counter_clear:
+	mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_RIF,
+			      *p_counter_index);
+	return err;
+}
+
+void mlxsw_sp_rif_counter_free(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_rif *rif,
+			       enum mlxsw_sp_rif_counter_dir dir)
+{
+	unsigned int *p_counter_index;
+
+	p_counter_index = mlxsw_sp_rif_p_counter_get(rif, dir);
+	if (WARN_ON(!p_counter_index))
+		return;
+	mlxsw_sp_rif_counter_edit(mlxsw_sp, rif->rif_index,
+				  *p_counter_index, false, dir);
+	mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_RIF,
+			      *p_counter_index);
+	mlxsw_sp_rif_counter_valid_set(rif, dir, false);
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
+			 const struct net_device *dev);
 
 #define mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) \
 	for_each_set_bit(prefix, (prefix_usage)->b, MLXSW_SP_PREFIX_COUNT)
@@ -89,12 +259,6 @@ mlxsw_sp_prefix_usage_cpy(struct mlxsw_sp_prefix_usage *prefix_usage1,
 }
 
 static void
-mlxsw_sp_prefix_usage_zero(struct mlxsw_sp_prefix_usage *prefix_usage)
-{
-	memset(prefix_usage, 0, sizeof(*prefix_usage));
-}
-
-static void
 mlxsw_sp_prefix_usage_set(struct mlxsw_sp_prefix_usage *prefix_usage,
 			  unsigned char prefix_len)
 {
@@ -125,7 +289,7 @@ struct mlxsw_sp_fib_node {
 	struct list_head entry_list;
 	struct list_head list;
 	struct rhash_head ht_node;
-	struct mlxsw_sp_vr *vr;
+	struct mlxsw_sp_fib *fib;
 	struct mlxsw_sp_fib_key key;
 };
 
@@ -149,13 +313,17 @@ struct mlxsw_sp_fib_entry {
 struct mlxsw_sp_fib {
 	struct rhashtable ht;
 	struct list_head node_list;
+	struct mlxsw_sp_vr *vr;
+	struct mlxsw_sp_lpm_tree *lpm_tree;
 	unsigned long prefix_ref_count[MLXSW_SP_PREFIX_COUNT];
 	struct mlxsw_sp_prefix_usage prefix_usage;
+	enum mlxsw_sp_l3proto proto;
 };
 
 static const struct rhashtable_params mlxsw_sp_fib_ht_params;
 
-static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void)
+static struct mlxsw_sp_fib *mlxsw_sp_fib_create(struct mlxsw_sp_vr *vr,
+						enum mlxsw_sp_l3proto proto)
 {
 	struct mlxsw_sp_fib *fib;
 	int err;
@@ -167,6 +335,8 @@ static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void)
 	if (err)
 		goto err_rhashtable_init;
 	INIT_LIST_HEAD(&fib->node_list);
+	fib->proto = proto;
+	fib->vr = vr;
 	return fib;
 
 err_rhashtable_init:
@@ -177,24 +347,21 @@ err_rhashtable_init:
 static void mlxsw_sp_fib_destroy(struct mlxsw_sp_fib *fib)
 {
 	WARN_ON(!list_empty(&fib->node_list));
+	WARN_ON(fib->lpm_tree);
 	rhashtable_destroy(&fib->ht);
 	kfree(fib);
 }
 
 static struct mlxsw_sp_lpm_tree *
-mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp, bool one_reserved)
+mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp)
 {
 	static struct mlxsw_sp_lpm_tree *lpm_tree;
 	int i;
 
-	for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
-		lpm_tree = &mlxsw_sp->router.lpm_trees[i];
-		if (lpm_tree->ref_count == 0) {
-			if (one_reserved)
-				one_reserved = false;
-			else
-				return lpm_tree;
-		}
+	for (i = 0; i < mlxsw_sp->router.lpm.tree_count; i++) {
+		lpm_tree = &mlxsw_sp->router.lpm.trees[i];
+		if (lpm_tree->ref_count == 0)
+			return lpm_tree;
 	}
 	return NULL;
 }
@@ -248,12 +415,12 @@ mlxsw_sp_lpm_tree_left_struct_set(struct mlxsw_sp *mlxsw_sp,
 static struct mlxsw_sp_lpm_tree *
 mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_prefix_usage *prefix_usage,
-			 enum mlxsw_sp_l3proto proto, bool one_reserved)
+			 enum mlxsw_sp_l3proto proto)
 {
 	struct mlxsw_sp_lpm_tree *lpm_tree;
 	int err;
 
-	lpm_tree = mlxsw_sp_lpm_tree_find_unused(mlxsw_sp, one_reserved);
+	lpm_tree = mlxsw_sp_lpm_tree_find_unused(mlxsw_sp);
 	if (!lpm_tree)
 		return ERR_PTR(-EBUSY);
 	lpm_tree->proto = proto;
@@ -283,13 +450,13 @@ static int mlxsw_sp_lpm_tree_destroy(struct mlxsw_sp *mlxsw_sp,
 static struct mlxsw_sp_lpm_tree *
 mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp,
 		      struct mlxsw_sp_prefix_usage *prefix_usage,
-		      enum mlxsw_sp_l3proto proto, bool one_reserved)
+		      enum mlxsw_sp_l3proto proto)
 {
 	struct mlxsw_sp_lpm_tree *lpm_tree;
 	int i;
 
-	for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
-		lpm_tree = &mlxsw_sp->router.lpm_trees[i];
+	for (i = 0; i < mlxsw_sp->router.lpm.tree_count; i++) {
+		lpm_tree = &mlxsw_sp->router.lpm.trees[i];
 		if (lpm_tree->ref_count != 0 &&
 		    lpm_tree->proto == proto &&
 		    mlxsw_sp_prefix_usage_eq(&lpm_tree->prefix_usage,
@@ -297,7 +464,7 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp,
 			goto inc_ref_count;
 	}
 	lpm_tree = mlxsw_sp_lpm_tree_create(mlxsw_sp, prefix_usage,
-					    proto, one_reserved);
+					    proto);
 	if (IS_ERR(lpm_tree))
 		return lpm_tree;
 
@@ -314,15 +481,41 @@ static int mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 }
 
-static void mlxsw_sp_lpm_init(struct mlxsw_sp *mlxsw_sp)
+#define MLXSW_SP_LPM_TREE_MIN 2 /* trees 0 and 1 are reserved */
+
+static int mlxsw_sp_lpm_init(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_lpm_tree *lpm_tree;
+	u64 max_trees;
 	int i;
 
-	for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
-		lpm_tree = &mlxsw_sp->router.lpm_trees[i];
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_LPM_TREES))
+		return -EIO;
+
+	max_trees = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_LPM_TREES);
+	mlxsw_sp->router.lpm.tree_count = max_trees - MLXSW_SP_LPM_TREE_MIN;
+	mlxsw_sp->router.lpm.trees = kcalloc(mlxsw_sp->router.lpm.tree_count,
+					     sizeof(struct mlxsw_sp_lpm_tree),
+					     GFP_KERNEL);
+	if (!mlxsw_sp->router.lpm.trees)
+		return -ENOMEM;
+
+	for (i = 0; i < mlxsw_sp->router.lpm.tree_count; i++) {
+		lpm_tree = &mlxsw_sp->router.lpm.trees[i];
 		lpm_tree->id = i + MLXSW_SP_LPM_TREE_MIN;
 	}
+
+	return 0;
+}
+
+static void mlxsw_sp_lpm_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	kfree(mlxsw_sp->router.lpm.trees);
+}
+
+static bool mlxsw_sp_vr_is_used(const struct mlxsw_sp_vr *vr)
+{
+	return !!vr->fib4;
 }
 
 static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp)
@@ -332,31 +525,31 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp)
 
 	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
 		vr = &mlxsw_sp->router.vrs[i];
-		if (!vr->used)
+		if (!mlxsw_sp_vr_is_used(vr))
 			return vr;
 	}
 	return NULL;
 }
 
 static int mlxsw_sp_vr_lpm_tree_bind(struct mlxsw_sp *mlxsw_sp,
-				     struct mlxsw_sp_vr *vr)
+				     const struct mlxsw_sp_fib *fib)
 {
 	char raltb_pl[MLXSW_REG_RALTB_LEN];
 
-	mlxsw_reg_raltb_pack(raltb_pl, vr->id,
-			     (enum mlxsw_reg_ralxx_protocol) vr->proto,
-			     vr->lpm_tree->id);
+	mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id,
+			     (enum mlxsw_reg_ralxx_protocol) fib->proto,
+			     fib->lpm_tree->id);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
 }
 
 static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp,
-				       struct mlxsw_sp_vr *vr)
+				       const struct mlxsw_sp_fib *fib)
 {
 	char raltb_pl[MLXSW_REG_RALTB_LEN];
 
 	/* Bind to tree 0 which is default */
-	mlxsw_reg_raltb_pack(raltb_pl, vr->id,
-			     (enum mlxsw_reg_ralxx_protocol) vr->proto, 0);
+	mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id,
+			     (enum mlxsw_reg_ralxx_protocol) fib->proto, 0);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
 }
 
@@ -369,8 +562,7 @@ static u32 mlxsw_sp_fix_tb_id(u32 tb_id)
 }
 
 static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp,
-					    u32 tb_id,
-					    enum mlxsw_sp_l3proto proto)
+					    u32 tb_id)
 {
 	struct mlxsw_sp_vr *vr;
 	int i;
@@ -379,69 +571,50 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp,
 
 	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
 		vr = &mlxsw_sp->router.vrs[i];
-		if (vr->used && vr->proto == proto && vr->tb_id == tb_id)
+		if (mlxsw_sp_vr_is_used(vr) && vr->tb_id == tb_id)
 			return vr;
 	}
 	return NULL;
 }
 
+static struct mlxsw_sp_fib *mlxsw_sp_vr_fib(const struct mlxsw_sp_vr *vr,
+					    enum mlxsw_sp_l3proto proto)
+{
+	switch (proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		return vr->fib4;
+	case MLXSW_SP_L3_PROTO_IPV6:
+		BUG_ON(1);
+	}
+	return NULL;
+}
+
 static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp,
-					      unsigned char prefix_len,
-					      u32 tb_id,
-					      enum mlxsw_sp_l3proto proto)
+					      u32 tb_id)
 {
-	struct mlxsw_sp_prefix_usage req_prefix_usage;
-	struct mlxsw_sp_lpm_tree *lpm_tree;
 	struct mlxsw_sp_vr *vr;
-	int err;
 
 	vr = mlxsw_sp_vr_find_unused(mlxsw_sp);
 	if (!vr)
 		return ERR_PTR(-EBUSY);
-	vr->fib = mlxsw_sp_fib_create();
-	if (IS_ERR(vr->fib))
-		return ERR_CAST(vr->fib);
-
-	vr->proto = proto;
+	vr->fib4 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV4);
+	if (IS_ERR(vr->fib4))
+		return ERR_CAST(vr->fib4);
 	vr->tb_id = tb_id;
-	mlxsw_sp_prefix_usage_zero(&req_prefix_usage);
-	mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len);
-	lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage,
-					 proto, true);
-	if (IS_ERR(lpm_tree)) {
-		err = PTR_ERR(lpm_tree);
-		goto err_tree_get;
-	}
-	vr->lpm_tree = lpm_tree;
-	err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
-	if (err)
-		goto err_tree_bind;
-
-	vr->used = true;
 	return vr;
-
-err_tree_bind:
-	mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree);
-err_tree_get:
-	mlxsw_sp_fib_destroy(vr->fib);
-
-	return ERR_PTR(err);
 }
 
-static void mlxsw_sp_vr_destroy(struct mlxsw_sp *mlxsw_sp,
-				struct mlxsw_sp_vr *vr)
+static void mlxsw_sp_vr_destroy(struct mlxsw_sp_vr *vr)
 {
-	mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr);
-	mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree);
-	mlxsw_sp_fib_destroy(vr->fib);
-	vr->used = false;
+	mlxsw_sp_fib_destroy(vr->fib4);
+	vr->fib4 = NULL;
 }
 
 static int
-mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
+mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib *fib,
 			   struct mlxsw_sp_prefix_usage *req_prefix_usage)
 {
-	struct mlxsw_sp_lpm_tree *lpm_tree = vr->lpm_tree;
+	struct mlxsw_sp_lpm_tree *lpm_tree = fib->lpm_tree;
 	struct mlxsw_sp_lpm_tree *new_tree;
 	int err;
 
@@ -449,7 +622,7 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
 		return 0;
 
 	new_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage,
-					 vr->proto, false);
+					 fib->proto);
 	if (IS_ERR(new_tree)) {
 		/* We failed to get a tree according to the required
 		 * prefix usage. However, the current tree might be still good
@@ -463,8 +636,8 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
 	}
 
 	/* Prevent packet loss by overwriting existing binding */
-	vr->lpm_tree = new_tree;
-	err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
+	fib->lpm_tree = new_tree;
+	err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib);
 	if (err)
 		goto err_tree_bind;
 	mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree);
@@ -472,53 +645,26 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
 	return 0;
 
 err_tree_bind:
-	vr->lpm_tree = lpm_tree;
+	fib->lpm_tree = lpm_tree;
 	mlxsw_sp_lpm_tree_put(mlxsw_sp, new_tree);
 	return err;
 }
 
-static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp,
-					   unsigned char prefix_len,
-					   u32 tb_id,
-					   enum mlxsw_sp_l3proto proto)
+static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id)
 {
 	struct mlxsw_sp_vr *vr;
-	int err;
 
 	tb_id = mlxsw_sp_fix_tb_id(tb_id);
-	vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id, proto);
-	if (!vr) {
-		vr = mlxsw_sp_vr_create(mlxsw_sp, prefix_len, tb_id, proto);
-		if (IS_ERR(vr))
-			return vr;
-	} else {
-		struct mlxsw_sp_prefix_usage req_prefix_usage;
-
-		mlxsw_sp_prefix_usage_cpy(&req_prefix_usage,
-					  &vr->fib->prefix_usage);
-		mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len);
-		/* Need to replace LPM tree in case new prefix is required. */
-		err = mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr,
-						 &req_prefix_usage);
-		if (err)
-			return ERR_PTR(err);
-	}
+	vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id);
+	if (!vr)
+		vr = mlxsw_sp_vr_create(mlxsw_sp, tb_id);
 	return vr;
 }
 
-static void mlxsw_sp_vr_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr)
+static void mlxsw_sp_vr_put(struct mlxsw_sp_vr *vr)
 {
-	/* Destroy virtual router entity in case the associated FIB is empty
-	 * and allow it to be used for other tables in future. Otherwise,
-	 * check if some prefix usage did not disappear and change tree if
-	 * that is the case. Note that in case new, smaller tree cannot be
-	 * allocated, the original one will be kept being used.
-	 */
-	if (mlxsw_sp_prefix_usage_none(&vr->fib->prefix_usage))
-		mlxsw_sp_vr_destroy(mlxsw_sp, vr);
-	else
-		mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr,
-					   &vr->fib->prefix_usage);
+	if (!vr->rif_count && list_empty(&vr->fib4->node_list))
+		mlxsw_sp_vr_destroy(vr);
 }
 
 static int mlxsw_sp_vrs_init(struct mlxsw_sp *mlxsw_sp)
@@ -627,14 +773,14 @@ static struct mlxsw_sp_neigh_entry *
 mlxsw_sp_neigh_entry_create(struct mlxsw_sp *mlxsw_sp, struct neighbour *n)
 {
 	struct mlxsw_sp_neigh_entry *neigh_entry;
-	struct mlxsw_sp_rif *r;
+	struct mlxsw_sp_rif *rif;
 	int err;
 
-	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev);
-	if (!r)
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev);
+	if (!rif)
 		return ERR_PTR(-EINVAL);
 
-	neigh_entry = mlxsw_sp_neigh_entry_alloc(mlxsw_sp, n, r->rif);
+	neigh_entry = mlxsw_sp_neigh_entry_alloc(mlxsw_sp, n, rif->rif_index);
 	if (!neigh_entry)
 		return ERR_PTR(-ENOMEM);
 
@@ -642,7 +788,7 @@ mlxsw_sp_neigh_entry_create(struct mlxsw_sp *mlxsw_sp, struct neighbour *n)
 	if (err)
 		goto err_neigh_entry_insert;
 
-	list_add(&neigh_entry->rif_list_node, &r->neigh_list);
+	list_add(&neigh_entry->rif_list_node, &rif->neigh_list);
 
 	return neigh_entry;
 
@@ -1050,22 +1196,22 @@ static void mlxsw_sp_neigh_fini(struct mlxsw_sp *mlxsw_sp)
 }
 
 static int mlxsw_sp_neigh_rif_flush(struct mlxsw_sp *mlxsw_sp,
-				    const struct mlxsw_sp_rif *r)
+				    const struct mlxsw_sp_rif *rif)
 {
 	char rauht_pl[MLXSW_REG_RAUHT_LEN];
 
 	mlxsw_reg_rauht_pack(rauht_pl, MLXSW_REG_RAUHT_OP_WRITE_DELETE_ALL,
-			     r->rif, r->addr);
+			     rif->rif_index, rif->addr);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl);
 }
 
 static void mlxsw_sp_neigh_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
-					 struct mlxsw_sp_rif *r)
+					 struct mlxsw_sp_rif *rif)
 {
 	struct mlxsw_sp_neigh_entry *neigh_entry, *tmp;
 
-	mlxsw_sp_neigh_rif_flush(mlxsw_sp, r);
-	list_for_each_entry_safe(neigh_entry, tmp, &r->neigh_list,
+	mlxsw_sp_neigh_rif_flush(mlxsw_sp, rif);
+	list_for_each_entry_safe(neigh_entry, tmp, &rif->neigh_list,
 				 rif_list_node)
 		mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry);
 }
@@ -1082,7 +1228,7 @@ struct mlxsw_sp_nexthop {
 						*/
 	struct rhash_head ht_node;
 	struct mlxsw_sp_nexthop_key key;
-	struct mlxsw_sp_rif *r;
+	struct mlxsw_sp_rif *rif;
 	u8 should_offload:1, /* set indicates this neigh is connected and
 			      * should be put to KVD linear area of this group.
 			      */
@@ -1109,7 +1255,7 @@ struct mlxsw_sp_nexthop_group {
 	u16 ecmp_size;
 	u16 count;
 	struct mlxsw_sp_nexthop nexthops[0];
-#define nh_rif	nexthops[0].r
+#define nh_rif	nexthops[0].rif
 };
 
 static const struct rhashtable_params mlxsw_sp_nexthop_group_ht_params = {
@@ -1171,7 +1317,7 @@ mlxsw_sp_nexthop_lookup(struct mlxsw_sp *mlxsw_sp,
 }
 
 static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp,
-					     struct mlxsw_sp_vr *vr,
+					     const struct mlxsw_sp_fib *fib,
 					     u32 adj_index, u16 ecmp_size,
 					     u32 new_adj_index,
 					     u16 new_ecmp_size)
@@ -1179,8 +1325,8 @@ static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp,
 	char raleu_pl[MLXSW_REG_RALEU_LEN];
 
 	mlxsw_reg_raleu_pack(raleu_pl,
-			     (enum mlxsw_reg_ralxx_protocol) vr->proto, vr->id,
-			     adj_index, ecmp_size, new_adj_index,
+			     (enum mlxsw_reg_ralxx_protocol) fib->proto,
+			     fib->vr->id, adj_index, ecmp_size, new_adj_index,
 			     new_ecmp_size);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raleu), raleu_pl);
 }
@@ -1190,14 +1336,14 @@ static int mlxsw_sp_adj_index_mass_update(struct mlxsw_sp *mlxsw_sp,
 					  u32 old_adj_index, u16 old_ecmp_size)
 {
 	struct mlxsw_sp_fib_entry *fib_entry;
-	struct mlxsw_sp_vr *vr = NULL;
+	struct mlxsw_sp_fib *fib = NULL;
 	int err;
 
 	list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node) {
-		if (vr == fib_entry->fib_node->vr)
+		if (fib == fib_entry->fib_node->fib)
 			continue;
-		vr = fib_entry->fib_node->vr;
-		err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, vr,
+		fib = fib_entry->fib_node->fib;
+		err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, fib,
 							old_adj_index,
 							old_ecmp_size,
 							nh_grp->adj_index,
@@ -1280,7 +1426,6 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 	bool old_adj_index_valid;
 	u32 old_adj_index;
 	u16 old_ecmp_size;
-	int ret;
 	int i;
 	int err;
 
@@ -1318,15 +1463,14 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 		 */
 		goto set_trap;
 
-	ret = mlxsw_sp_kvdl_alloc(mlxsw_sp, ecmp_size);
-	if (ret < 0) {
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, ecmp_size, &adj_index);
+	if (err) {
 		/* We ran out of KVD linear space, just set the
 		 * trap and let everything flow through kernel.
 		 */
 		dev_warn(mlxsw_sp->bus_info->dev, "Failed to allocate KVD linear area for nexthop group.\n");
 		goto set_trap;
 	}
-	adj_index = ret;
 	old_adj_index_valid = nh_grp->adj_index_valid;
 	old_adj_index = nh_grp->adj_index;
 	old_ecmp_size = nh_grp->ecmp_size;
@@ -1399,22 +1543,22 @@ mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp,
 }
 
 static void mlxsw_sp_nexthop_rif_init(struct mlxsw_sp_nexthop *nh,
-				      struct mlxsw_sp_rif *r)
+				      struct mlxsw_sp_rif *rif)
 {
-	if (nh->r)
+	if (nh->rif)
 		return;
 
-	nh->r = r;
-	list_add(&nh->rif_list_node, &r->nexthop_list);
+	nh->rif = rif;
+	list_add(&nh->rif_list_node, &rif->nexthop_list);
 }
 
 static void mlxsw_sp_nexthop_rif_fini(struct mlxsw_sp_nexthop *nh)
 {
-	if (!nh->r)
+	if (!nh->rif)
 		return;
 
 	list_del(&nh->rif_list_node);
-	nh->r = NULL;
+	nh->rif = NULL;
 }
 
 static int mlxsw_sp_nexthop_neigh_init(struct mlxsw_sp *mlxsw_sp,
@@ -1505,7 +1649,7 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp,
 {
 	struct net_device *dev = fib_nh->nh_dev;
 	struct in_device *in_dev;
-	struct mlxsw_sp_rif *r;
+	struct mlxsw_sp_rif *rif;
 	int err;
 
 	nh->nh_grp = nh_grp;
@@ -1514,15 +1658,18 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
+	if (!dev)
+		return 0;
+
 	in_dev = __in_dev_get_rtnl(dev);
 	if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
 	    fib_nh->nh_flags & RTNH_F_LINKDOWN)
 		return 0;
 
-	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
-	if (!r)
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	if (!rif)
 		return 0;
-	mlxsw_sp_nexthop_rif_init(nh, r);
+	mlxsw_sp_nexthop_rif_init(nh, rif);
 
 	err = mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh);
 	if (err)
@@ -1548,7 +1695,7 @@ static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_nexthop_key key;
 	struct mlxsw_sp_nexthop *nh;
-	struct mlxsw_sp_rif *r;
+	struct mlxsw_sp_rif *rif;
 
 	if (mlxsw_sp->router.aborted)
 		return;
@@ -1558,13 +1705,13 @@ static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp,
 	if (WARN_ON_ONCE(!nh))
 		return;
 
-	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, fib_nh->nh_dev);
-	if (!r)
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, fib_nh->nh_dev);
+	if (!rif)
 		return;
 
 	switch (event) {
 	case FIB_EVENT_NH_ADD:
-		mlxsw_sp_nexthop_rif_init(nh, r);
+		mlxsw_sp_nexthop_rif_init(nh, rif);
 		mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh);
 		break;
 	case FIB_EVENT_NH_DEL:
@@ -1577,11 +1724,11 @@ static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp,
 }
 
 static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
-					   struct mlxsw_sp_rif *r)
+					   struct mlxsw_sp_rif *rif)
 {
 	struct mlxsw_sp_nexthop *nh, *tmp;
 
-	list_for_each_entry_safe(nh, tmp, &r->nexthop_list, rif_list_node) {
+	list_for_each_entry_safe(nh, tmp, &rif->nexthop_list, rif_list_node) {
 		mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh);
 		mlxsw_sp_nexthop_rif_fini(nh);
 		mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
@@ -1699,7 +1846,7 @@ static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
 {
 	fib_entry->offloaded = true;
 
-	switch (fib_entry->fib_node->vr->proto) {
+	switch (fib_entry->fib_node->fib->proto) {
 	case MLXSW_SP_L3_PROTO_IPV4:
 		fib_info_offload_inc(fib_entry->nh_group->key.fi);
 		break;
@@ -1711,7 +1858,7 @@ static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
 static void
 mlxsw_sp_fib_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
 {
-	switch (fib_entry->fib_node->vr->proto) {
+	switch (fib_entry->fib_node->fib->proto) {
 	case MLXSW_SP_L3_PROTO_IPV4:
 		fib_info_offload_dec(fib_entry->nh_group->key.fi);
 		break;
@@ -1751,8 +1898,8 @@ static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp,
 					 enum mlxsw_reg_ralue_op op)
 {
 	char ralue_pl[MLXSW_REG_RALUE_LEN];
+	struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib;
 	u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr;
-	struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr;
 	enum mlxsw_reg_ralue_trap_action trap_action;
 	u16 trap_id = 0;
 	u32 adjacency_index = 0;
@@ -1772,8 +1919,8 @@ static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp,
 	}
 
 	mlxsw_reg_ralue_pack4(ralue_pl,
-			      (enum mlxsw_reg_ralxx_protocol) vr->proto, op,
-			      vr->id, fib_entry->fib_node->key.prefix_len,
+			      (enum mlxsw_reg_ralxx_protocol) fib->proto, op,
+			      fib->vr->id, fib_entry->fib_node->key.prefix_len,
 			      *p_dip);
 	mlxsw_reg_ralue_act_remote_pack(ralue_pl, trap_action, trap_id,
 					adjacency_index, ecmp_size);
@@ -1784,27 +1931,28 @@ static int mlxsw_sp_fib_entry_op4_local(struct mlxsw_sp *mlxsw_sp,
 					struct mlxsw_sp_fib_entry *fib_entry,
 					enum mlxsw_reg_ralue_op op)
 {
-	struct mlxsw_sp_rif *r = fib_entry->nh_group->nh_rif;
+	struct mlxsw_sp_rif *rif = fib_entry->nh_group->nh_rif;
+	struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib;
 	enum mlxsw_reg_ralue_trap_action trap_action;
 	char ralue_pl[MLXSW_REG_RALUE_LEN];
 	u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr;
-	struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr;
 	u16 trap_id = 0;
-	u16 rif = 0;
+	u16 rif_index = 0;
 
 	if (mlxsw_sp_fib_entry_should_offload(fib_entry)) {
 		trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP;
-		rif = r->rif;
+		rif_index = rif->rif_index;
 	} else {
 		trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP;
 		trap_id = MLXSW_TRAP_ID_RTR_INGRESS0;
 	}
 
 	mlxsw_reg_ralue_pack4(ralue_pl,
-			      (enum mlxsw_reg_ralxx_protocol) vr->proto, op,
-			      vr->id, fib_entry->fib_node->key.prefix_len,
+			      (enum mlxsw_reg_ralxx_protocol) fib->proto, op,
+			      fib->vr->id, fib_entry->fib_node->key.prefix_len,
 			      *p_dip);
-	mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, rif);
+	mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id,
+				       rif_index);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
 }
 
@@ -1812,13 +1960,13 @@ static int mlxsw_sp_fib_entry_op4_trap(struct mlxsw_sp *mlxsw_sp,
 				       struct mlxsw_sp_fib_entry *fib_entry,
 				       enum mlxsw_reg_ralue_op op)
 {
+	struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib;
 	char ralue_pl[MLXSW_REG_RALUE_LEN];
 	u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr;
-	struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr;
 
 	mlxsw_reg_ralue_pack4(ralue_pl,
-			      (enum mlxsw_reg_ralxx_protocol) vr->proto, op,
-			      vr->id, fib_entry->fib_node->key.prefix_len,
+			      (enum mlxsw_reg_ralxx_protocol) fib->proto, op,
+			      fib->vr->id, fib_entry->fib_node->key.prefix_len,
 			      *p_dip);
 	mlxsw_reg_ralue_act_ip2me_pack(ralue_pl);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
@@ -1845,7 +1993,7 @@ static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp,
 {
 	int err = -EINVAL;
 
-	switch (fib_entry->fib_node->vr->proto) {
+	switch (fib_entry->fib_node->fib->proto) {
 	case MLXSW_SP_L3_PROTO_IPV4:
 		err = mlxsw_sp_fib_entry_op4(mlxsw_sp, fib_entry, op);
 		break;
@@ -1877,17 +2025,29 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp,
 {
 	struct fib_info *fi = fen_info->fi;
 
-	if (fen_info->type == RTN_LOCAL || fen_info->type == RTN_BROADCAST) {
+	switch (fen_info->type) {
+	case RTN_BROADCAST: /* fall through */
+	case RTN_LOCAL:
 		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP;
 		return 0;
-	}
-	if (fen_info->type != RTN_UNICAST)
-		return -EINVAL;
-	if (fi->fib_nh->nh_scope != RT_SCOPE_LINK)
+	case RTN_UNREACHABLE: /* fall through */
+	case RTN_BLACKHOLE: /* fall through */
+	case RTN_PROHIBIT:
+		/* Packets hitting these routes need to be trapped, but
+		 * can do so with a lower priority than packets directed
+		 * at the host, so use action type local instead of trap.
+		 */
 		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
-	else
-		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE;
-	return 0;
+		return 0;
+	case RTN_UNICAST:
+		if (fi->fib_nh->nh_scope != RT_SCOPE_LINK)
+			fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
+		else
+			fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE;
+		return 0;
+	default:
+		return -EINVAL;
+	}
 }
 
 static struct mlxsw_sp_fib_entry *
@@ -1996,7 +2156,7 @@ mlxsw_sp_fib_node_lookup(struct mlxsw_sp_fib *fib, const void *addr,
 }
 
 static struct mlxsw_sp_fib_node *
-mlxsw_sp_fib_node_create(struct mlxsw_sp_vr *vr, const void *addr,
+mlxsw_sp_fib_node_create(struct mlxsw_sp_fib *fib, const void *addr,
 			 size_t addr_len, unsigned char prefix_len)
 {
 	struct mlxsw_sp_fib_node *fib_node;
@@ -2006,18 +2166,15 @@ mlxsw_sp_fib_node_create(struct mlxsw_sp_vr *vr, const void *addr,
 		return NULL;
 
 	INIT_LIST_HEAD(&fib_node->entry_list);
-	list_add(&fib_node->list, &vr->fib->node_list);
+	list_add(&fib_node->list, &fib->node_list);
 	memcpy(fib_node->key.addr, addr, addr_len);
 	fib_node->key.prefix_len = prefix_len;
-	mlxsw_sp_fib_node_insert(vr->fib, fib_node);
-	fib_node->vr = vr;
 
 	return fib_node;
 }
 
 static void mlxsw_sp_fib_node_destroy(struct mlxsw_sp_fib_node *fib_node)
 {
-	mlxsw_sp_fib_node_remove(fib_node->vr->fib, fib_node);
 	list_del(&fib_node->list);
 	WARN_ON(!list_empty(&fib_node->entry_list));
 	kfree(fib_node);
@@ -2034,7 +2191,7 @@ mlxsw_sp_fib_node_entry_is_first(const struct mlxsw_sp_fib_node *fib_node,
 static void mlxsw_sp_fib_node_prefix_inc(struct mlxsw_sp_fib_node *fib_node)
 {
 	unsigned char prefix_len = fib_node->key.prefix_len;
-	struct mlxsw_sp_fib *fib = fib_node->vr->fib;
+	struct mlxsw_sp_fib *fib = fib_node->fib;
 
 	if (fib->prefix_ref_count[prefix_len]++ == 0)
 		mlxsw_sp_prefix_usage_set(&fib->prefix_usage, prefix_len);
@@ -2043,32 +2200,98 @@ static void mlxsw_sp_fib_node_prefix_inc(struct mlxsw_sp_fib_node *fib_node)
 static void mlxsw_sp_fib_node_prefix_dec(struct mlxsw_sp_fib_node *fib_node)
 {
 	unsigned char prefix_len = fib_node->key.prefix_len;
-	struct mlxsw_sp_fib *fib = fib_node->vr->fib;
+	struct mlxsw_sp_fib *fib = fib_node->fib;
 
 	if (--fib->prefix_ref_count[prefix_len] == 0)
 		mlxsw_sp_prefix_usage_clear(&fib->prefix_usage, prefix_len);
 }
 
+static int mlxsw_sp_fib_node_init(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_fib_node *fib_node,
+				  struct mlxsw_sp_fib *fib)
+{
+	struct mlxsw_sp_prefix_usage req_prefix_usage;
+	struct mlxsw_sp_lpm_tree *lpm_tree;
+	int err;
+
+	err = mlxsw_sp_fib_node_insert(fib, fib_node);
+	if (err)
+		return err;
+	fib_node->fib = fib;
+
+	mlxsw_sp_prefix_usage_cpy(&req_prefix_usage, &fib->prefix_usage);
+	mlxsw_sp_prefix_usage_set(&req_prefix_usage, fib_node->key.prefix_len);
+
+	if (!mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) {
+		err = mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, fib,
+						 &req_prefix_usage);
+		if (err)
+			goto err_tree_check;
+	} else {
+		lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage,
+						 fib->proto);
+		if (IS_ERR(lpm_tree))
+			return PTR_ERR(lpm_tree);
+		fib->lpm_tree = lpm_tree;
+		err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib);
+		if (err)
+			goto err_tree_bind;
+	}
+
+	mlxsw_sp_fib_node_prefix_inc(fib_node);
+
+	return 0;
+
+err_tree_bind:
+	fib->lpm_tree = NULL;
+	mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree);
+err_tree_check:
+	fib_node->fib = NULL;
+	mlxsw_sp_fib_node_remove(fib, fib_node);
+	return err;
+}
+
+static void mlxsw_sp_fib_node_fini(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_fib_node *fib_node)
+{
+	struct mlxsw_sp_lpm_tree *lpm_tree = fib_node->fib->lpm_tree;
+	struct mlxsw_sp_fib *fib = fib_node->fib;
+
+	mlxsw_sp_fib_node_prefix_dec(fib_node);
+
+	if (mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) {
+		mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, fib);
+		fib->lpm_tree = NULL;
+		mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree);
+	} else {
+		mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, fib, &fib->prefix_usage);
+	}
+
+	fib_node->fib = NULL;
+	mlxsw_sp_fib_node_remove(fib, fib_node);
+}
+
 static struct mlxsw_sp_fib_node *
 mlxsw_sp_fib4_node_get(struct mlxsw_sp *mlxsw_sp,
 		       const struct fib_entry_notifier_info *fen_info)
 {
 	struct mlxsw_sp_fib_node *fib_node;
+	struct mlxsw_sp_fib *fib;
 	struct mlxsw_sp_vr *vr;
 	int err;
 
-	vr = mlxsw_sp_vr_get(mlxsw_sp, fen_info->dst_len, fen_info->tb_id,
-			     MLXSW_SP_L3_PROTO_IPV4);
+	vr = mlxsw_sp_vr_get(mlxsw_sp, fen_info->tb_id);
 	if (IS_ERR(vr))
 		return ERR_CAST(vr);
+	fib = mlxsw_sp_vr_fib(vr, MLXSW_SP_L3_PROTO_IPV4);
 
-	fib_node = mlxsw_sp_fib_node_lookup(vr->fib, &fen_info->dst,
+	fib_node = mlxsw_sp_fib_node_lookup(fib, &fen_info->dst,
 					    sizeof(fen_info->dst),
 					    fen_info->dst_len);
 	if (fib_node)
 		return fib_node;
 
-	fib_node = mlxsw_sp_fib_node_create(vr, &fen_info->dst,
+	fib_node = mlxsw_sp_fib_node_create(fib, &fen_info->dst,
 					    sizeof(fen_info->dst),
 					    fen_info->dst_len);
 	if (!fib_node) {
@@ -2076,22 +2299,29 @@ mlxsw_sp_fib4_node_get(struct mlxsw_sp *mlxsw_sp,
 		goto err_fib_node_create;
 	}
 
+	err = mlxsw_sp_fib_node_init(mlxsw_sp, fib_node, fib);
+	if (err)
+		goto err_fib_node_init;
+
 	return fib_node;
 
+err_fib_node_init:
+	mlxsw_sp_fib_node_destroy(fib_node);
 err_fib_node_create:
-	mlxsw_sp_vr_put(mlxsw_sp, vr);
+	mlxsw_sp_vr_put(vr);
 	return ERR_PTR(err);
 }
 
 static void mlxsw_sp_fib4_node_put(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_fib_node *fib_node)
 {
-	struct mlxsw_sp_vr *vr = fib_node->vr;
+	struct mlxsw_sp_vr *vr = fib_node->fib->vr;
 
 	if (!list_empty(&fib_node->entry_list))
 		return;
+	mlxsw_sp_fib_node_fini(mlxsw_sp, fib_node);
 	mlxsw_sp_fib_node_destroy(fib_node);
-	mlxsw_sp_vr_put(mlxsw_sp, vr);
+	mlxsw_sp_vr_put(vr);
 }
 
 static struct mlxsw_sp_fib_entry *
@@ -2236,8 +2466,6 @@ static int mlxsw_sp_fib4_node_entry_link(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_fib4_node_entry_add;
 
-	mlxsw_sp_fib_node_prefix_inc(fib_node);
-
 	return 0;
 
 err_fib4_node_entry_add:
@@ -2251,7 +2479,6 @@ mlxsw_sp_fib4_node_entry_unlink(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node;
 
-	mlxsw_sp_fib_node_prefix_dec(fib_node);
 	mlxsw_sp_fib4_node_entry_del(mlxsw_sp, fib_node, fib_entry);
 	mlxsw_sp_fib4_node_list_remove(fib_entry);
 }
@@ -2340,9 +2567,7 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
 {
 	char ralta_pl[MLXSW_REG_RALTA_LEN];
 	char ralst_pl[MLXSW_REG_RALST_LEN];
-	char raltb_pl[MLXSW_REG_RALTB_LEN];
-	char ralue_pl[MLXSW_REG_RALUE_LEN];
-	int err;
+	int i, err;
 
 	mlxsw_reg_ralta_pack(ralta_pl, true, MLXSW_REG_RALXX_PROTOCOL_IPV4,
 			     MLXSW_SP_LPM_TREE_MIN);
@@ -2355,16 +2580,33 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
 	if (err)
 		return err;
 
-	mlxsw_reg_raltb_pack(raltb_pl, 0, MLXSW_REG_RALXX_PROTOCOL_IPV4,
-			     MLXSW_SP_LPM_TREE_MIN);
-	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
-	if (err)
-		return err;
+	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
+		struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[i];
+		char raltb_pl[MLXSW_REG_RALTB_LEN];
+		char ralue_pl[MLXSW_REG_RALUE_LEN];
 
-	mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_SP_L3_PROTO_IPV4,
-			      MLXSW_REG_RALUE_OP_WRITE_WRITE, 0, 0, 0);
-	mlxsw_reg_ralue_act_ip2me_pack(ralue_pl);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
+		if (!mlxsw_sp_vr_is_used(vr))
+			continue;
+
+		mlxsw_reg_raltb_pack(raltb_pl, vr->id,
+				     MLXSW_REG_RALXX_PROTOCOL_IPV4,
+				     MLXSW_SP_LPM_TREE_MIN);
+		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb),
+				      raltb_pl);
+		if (err)
+			return err;
+
+		mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_SP_L3_PROTO_IPV4,
+				      MLXSW_REG_RALUE_OP_WRITE_WRITE, vr->id, 0,
+				      0);
+		mlxsw_reg_ralue_act_ip2me_pack(ralue_pl);
+		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue),
+				      ralue_pl);
+		if (err)
+			return err;
+	}
+
+	return 0;
 }
 
 static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp,
@@ -2390,7 +2632,7 @@ static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp,
 static void mlxsw_sp_fib_node_flush(struct mlxsw_sp *mlxsw_sp,
 				    struct mlxsw_sp_fib_node *fib_node)
 {
-	switch (fib_node->vr->proto) {
+	switch (fib_node->fib->proto) {
 	case MLXSW_SP_L3_PROTO_IPV4:
 		mlxsw_sp_fib4_node_flush(mlxsw_sp, fib_node);
 		break;
@@ -2400,26 +2642,32 @@ static void mlxsw_sp_fib_node_flush(struct mlxsw_sp *mlxsw_sp,
 	}
 }
 
-static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp)
+static void mlxsw_sp_vr_fib_flush(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_vr *vr,
+				  enum mlxsw_sp_l3proto proto)
 {
+	struct mlxsw_sp_fib *fib = mlxsw_sp_vr_fib(vr, proto);
 	struct mlxsw_sp_fib_node *fib_node, *tmp;
-	struct mlxsw_sp_vr *vr;
+
+	list_for_each_entry_safe(fib_node, tmp, &fib->node_list, list) {
+		bool do_break = &tmp->list == &fib->node_list;
+
+		mlxsw_sp_fib_node_flush(mlxsw_sp, fib_node);
+		if (do_break)
+			break;
+	}
+}
+
+static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp)
+{
 	int i;
 
 	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
-		vr = &mlxsw_sp->router.vrs[i];
+		struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[i];
 
-		if (!vr->used)
+		if (!mlxsw_sp_vr_is_used(vr))
 			continue;
-
-		list_for_each_entry_safe(fib_node, tmp, &vr->fib->node_list,
-					 list) {
-			bool do_break = &tmp->list == &vr->fib->node_list;
-
-			mlxsw_sp_fib_node_flush(mlxsw_sp, fib_node);
-			if (do_break)
-				break;
-		}
+		mlxsw_sp_vr_fib_flush(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV4);
 	}
 }
 
@@ -2437,74 +2685,11 @@ static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp)
 		dev_warn(mlxsw_sp->bus_info->dev, "Failed to set abort trap.\n");
 }
 
-static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif)
-{
-	char ritr_pl[MLXSW_REG_RITR_LEN];
-	int err;
-
-	mlxsw_reg_ritr_rif_pack(ritr_pl, rif);
-	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-	if (WARN_ON_ONCE(err))
-		return err;
-
-	mlxsw_reg_ritr_enable_set(ritr_pl, false);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-}
-
-void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
-				   struct mlxsw_sp_rif *r)
-{
-	mlxsw_sp_router_rif_disable(mlxsw_sp, r->rif);
-	mlxsw_sp_nexthop_rif_gone_sync(mlxsw_sp, r);
-	mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, r);
-}
-
-static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
-{
-	char rgcr_pl[MLXSW_REG_RGCR_LEN];
-	u64 max_rifs;
-	int err;
-
-	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_RIFS))
-		return -EIO;
-
-	max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
-	mlxsw_sp->rifs = kcalloc(max_rifs, sizeof(struct mlxsw_sp_rif *),
-				 GFP_KERNEL);
-	if (!mlxsw_sp->rifs)
-		return -ENOMEM;
-
-	mlxsw_reg_rgcr_pack(rgcr_pl, true);
-	mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs);
-	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl);
-	if (err)
-		goto err_rgcr_fail;
-
-	return 0;
-
-err_rgcr_fail:
-	kfree(mlxsw_sp->rifs);
-	return err;
-}
-
-static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
-{
-	char rgcr_pl[MLXSW_REG_RGCR_LEN];
-	int i;
-
-	mlxsw_reg_rgcr_pack(rgcr_pl, false);
-	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl);
-
-	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
-		WARN_ON_ONCE(mlxsw_sp->rifs[i]);
-
-	kfree(mlxsw_sp->rifs);
-}
-
 struct mlxsw_sp_fib_event_work {
 	struct work_struct work;
 	union {
 		struct fib_entry_notifier_info fen_info;
+		struct fib_rule_notifier_info fr_info;
 		struct fib_nh_notifier_info fnh_info;
 	};
 	struct mlxsw_sp *mlxsw_sp;
@@ -2516,6 +2701,7 @@ static void mlxsw_sp_router_fib_event_work(struct work_struct *work)
 	struct mlxsw_sp_fib_event_work *fib_work =
 		container_of(work, struct mlxsw_sp_fib_event_work, work);
 	struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp;
+	struct fib_rule *rule;
 	bool replace, append;
 	int err;
 
@@ -2539,7 +2725,10 @@ static void mlxsw_sp_router_fib_event_work(struct work_struct *work)
 		break;
 	case FIB_EVENT_RULE_ADD: /* fall through */
 	case FIB_EVENT_RULE_DEL:
-		mlxsw_sp_router_fib4_abort(mlxsw_sp);
+		rule = fib_work->fr_info.rule;
+		if (!fib4_rule_default(rule) && !rule->l3mdev)
+			mlxsw_sp_router_fib4_abort(mlxsw_sp);
+		fib_rule_put(rule);
 		break;
 	case FIB_EVENT_NH_ADD: /* fall through */
 	case FIB_EVENT_NH_DEL:
@@ -2582,6 +2771,11 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 		 */
 		fib_info_hold(fib_work->fen_info.fi);
 		break;
+	case FIB_EVENT_RULE_ADD: /* fall through */
+	case FIB_EVENT_RULE_DEL:
+		memcpy(&fib_work->fr_info, ptr, sizeof(fib_work->fr_info));
+		fib_rule_get(fib_work->fr_info.rule);
+		break;
 	case FIB_EVENT_NH_ADD: /* fall through */
 	case FIB_EVENT_NH_DEL:
 		memcpy(&fib_work->fnh_info, ptr, sizeof(fib_work->fnh_info));
@@ -2594,6 +2788,716 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
+static struct mlxsw_sp_rif *
+mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
+			 const struct net_device *dev)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
+		if (mlxsw_sp->rifs[i] && mlxsw_sp->rifs[i]->dev == dev)
+			return mlxsw_sp->rifs[i];
+
+	return NULL;
+}
+
+static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif)
+{
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+	int err;
+
+	mlxsw_reg_ritr_rif_pack(ritr_pl, rif);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+	if (WARN_ON_ONCE(err))
+		return err;
+
+	mlxsw_reg_ritr_enable_set(ritr_pl, false);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
+					  struct mlxsw_sp_rif *rif)
+{
+	mlxsw_sp_router_rif_disable(mlxsw_sp, rif->rif_index);
+	mlxsw_sp_nexthop_rif_gone_sync(mlxsw_sp, rif);
+	mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, rif);
+}
+
+static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *rif,
+				       const struct in_device *in_dev,
+				       unsigned long event)
+{
+	switch (event) {
+	case NETDEV_UP:
+		if (!rif)
+			return true;
+		return false;
+	case NETDEV_DOWN:
+		if (rif && !in_dev->ifa_list &&
+		    !netif_is_l3_slave(rif->dev))
+			return true;
+		/* It is possible we already removed the RIF ourselves
+		 * if it was assigned to a netdev that is now a bridge
+		 * or LAG slave.
+		 */
+		return false;
+	}
+
+	return false;
+}
+
+#define MLXSW_SP_INVALID_INDEX_RIF 0xffff
+static int mlxsw_sp_avail_rif_get(struct mlxsw_sp *mlxsw_sp)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
+		if (!mlxsw_sp->rifs[i])
+			return i;
+
+	return MLXSW_SP_INVALID_INDEX_RIF;
+}
+
+static void mlxsw_sp_vport_rif_sp_attr_get(struct mlxsw_sp_port *mlxsw_sp_vport,
+					   bool *p_lagged, u16 *p_system_port)
+{
+	u8 local_port = mlxsw_sp_vport->local_port;
+
+	*p_lagged = mlxsw_sp_vport->lagged;
+	*p_system_port = *p_lagged ? mlxsw_sp_vport->lag_id : local_port;
+}
+
+static int mlxsw_sp_vport_rif_sp_op(struct mlxsw_sp_port *mlxsw_sp_vport,
+				    u16 vr_id, struct net_device *l3_dev,
+				    u16 rif_index, bool create)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+	bool lagged = mlxsw_sp_vport->lagged;
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+	u16 system_port;
+
+	mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif_index,
+			    vr_id, l3_dev->mtu, l3_dev->dev_addr);
+
+	mlxsw_sp_vport_rif_sp_attr_get(mlxsw_sp_vport, &lagged, &system_port);
+	mlxsw_reg_ritr_sp_if_pack(ritr_pl, lagged, system_port,
+				  mlxsw_sp_vport_vid_get(mlxsw_sp_vport));
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport);
+
+static u16 mlxsw_sp_rif_sp_to_fid(u16 rif_index)
+{
+	return MLXSW_SP_RFID_BASE + rif_index;
+}
+
+static struct mlxsw_sp_fid *
+mlxsw_sp_rfid_alloc(u16 fid, struct net_device *l3_dev)
+{
+	struct mlxsw_sp_fid *f;
+
+	f = kzalloc(sizeof(*f), GFP_KERNEL);
+	if (!f)
+		return NULL;
+
+	f->leave = mlxsw_sp_vport_rif_sp_leave;
+	f->ref_count = 0;
+	f->dev = l3_dev;
+	f->fid = fid;
+
+	return f;
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_rif_alloc(u16 rif_index, u16 vr_id, struct net_device *l3_dev,
+		   struct mlxsw_sp_fid *f)
+{
+	struct mlxsw_sp_rif *rif;
+
+	rif = kzalloc(sizeof(*rif), GFP_KERNEL);
+	if (!rif)
+		return NULL;
+
+	INIT_LIST_HEAD(&rif->nexthop_list);
+	INIT_LIST_HEAD(&rif->neigh_list);
+	ether_addr_copy(rif->addr, l3_dev->dev_addr);
+	rif->mtu = l3_dev->mtu;
+	rif->vr_id = vr_id;
+	rif->dev = l3_dev;
+	rif->rif_index = rif_index;
+	rif->f = f;
+
+	return rif;
+}
+
+u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif)
+{
+	return rif->rif_index;
+}
+
+int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif)
+{
+	return rif->dev->ifindex;
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport,
+			     struct net_device *l3_dev)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+	u32 tb_id = l3mdev_fib_table(l3_dev);
+	struct mlxsw_sp_vr *vr;
+	struct mlxsw_sp_fid *f;
+	struct mlxsw_sp_rif *rif;
+	u16 fid, rif_index;
+	int err;
+
+	rif_index = mlxsw_sp_avail_rif_get(mlxsw_sp);
+	if (rif_index == MLXSW_SP_INVALID_INDEX_RIF)
+		return ERR_PTR(-ERANGE);
+
+	vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN);
+	if (IS_ERR(vr))
+		return ERR_CAST(vr);
+
+	err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev,
+				       rif_index, true);
+	if (err)
+		goto err_vport_rif_sp_op;
+
+	fid = mlxsw_sp_rif_sp_to_fid(rif_index);
+	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, true);
+	if (err)
+		goto err_rif_fdb_op;
+
+	f = mlxsw_sp_rfid_alloc(fid, l3_dev);
+	if (!f) {
+		err = -ENOMEM;
+		goto err_rfid_alloc;
+	}
+
+	rif = mlxsw_sp_rif_alloc(rif_index, vr->id, l3_dev, f);
+	if (!rif) {
+		err = -ENOMEM;
+		goto err_rif_alloc;
+	}
+
+	if (devlink_dpipe_table_counter_enabled(priv_to_devlink(mlxsw_sp->core),
+						MLXSW_SP_DPIPE_TABLE_NAME_ERIF)) {
+		err = mlxsw_sp_rif_counter_alloc(mlxsw_sp, rif,
+						 MLXSW_SP_RIF_COUNTER_EGRESS);
+		if (err)
+			netdev_dbg(mlxsw_sp_vport->dev,
+				   "Counter alloc Failed err=%d\n", err);
+	}
+
+	f->rif = rif;
+	mlxsw_sp->rifs[rif_index] = rif;
+	vr->rif_count++;
+
+	return rif;
+
+err_rif_alloc:
+	kfree(f);
+err_rfid_alloc:
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false);
+err_rif_fdb_op:
+	mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif_index,
+				 false);
+err_vport_rif_sp_op:
+	mlxsw_sp_vr_put(vr);
+	return ERR_PTR(err);
+}
+
+static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport,
+					  struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+	struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[rif->vr_id];
+	struct net_device *l3_dev = rif->dev;
+	struct mlxsw_sp_fid *f = rif->f;
+	u16 rif_index = rif->rif_index;
+	u16 fid = f->fid;
+
+	mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif);
+
+	mlxsw_sp_rif_counter_free(mlxsw_sp, rif, MLXSW_SP_RIF_COUNTER_EGRESS);
+	mlxsw_sp_rif_counter_free(mlxsw_sp, rif, MLXSW_SP_RIF_COUNTER_INGRESS);
+
+	vr->rif_count--;
+	mlxsw_sp->rifs[rif_index] = NULL;
+	f->rif = NULL;
+
+	kfree(rif);
+
+	kfree(f);
+
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false);
+
+	mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif_index,
+				 false);
+	mlxsw_sp_vr_put(vr);
+}
+
+static int mlxsw_sp_vport_rif_sp_join(struct mlxsw_sp_port *mlxsw_sp_vport,
+				      struct net_device *l3_dev)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+	struct mlxsw_sp_rif *rif;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
+	if (!rif) {
+		rif = mlxsw_sp_vport_rif_sp_create(mlxsw_sp_vport, l3_dev);
+		if (IS_ERR(rif))
+			return PTR_ERR(rif);
+	}
+
+	mlxsw_sp_vport_fid_set(mlxsw_sp_vport, rif->f);
+	rif->f->ref_count++;
+
+	netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", rif->f->fid);
+
+	return 0;
+}
+
+static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+	struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+
+	netdev_dbg(mlxsw_sp_vport->dev, "Left FID=%d\n", f->fid);
+
+	mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL);
+	if (--f->ref_count == 0)
+		mlxsw_sp_vport_rif_sp_destroy(mlxsw_sp_vport, f->rif);
+}
+
+static int mlxsw_sp_inetaddr_vport_event(struct net_device *l3_dev,
+					 struct net_device *port_dev,
+					 unsigned long event, u16 vid)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(port_dev);
+	struct mlxsw_sp_port *mlxsw_sp_vport;
+
+	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
+	if (WARN_ON(!mlxsw_sp_vport))
+		return -EINVAL;
+
+	switch (event) {
+	case NETDEV_UP:
+		return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, l3_dev);
+	case NETDEV_DOWN:
+		mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport);
+		break;
+	}
+
+	return 0;
+}
+
+static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev,
+					unsigned long event)
+{
+	if (netif_is_bridge_port(port_dev) || netif_is_lag_port(port_dev))
+		return 0;
+
+	return mlxsw_sp_inetaddr_vport_event(port_dev, port_dev, event, 1);
+}
+
+static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev,
+					 struct net_device *lag_dev,
+					 unsigned long event, u16 vid)
+{
+	struct net_device *port_dev;
+	struct list_head *iter;
+	int err;
+
+	netdev_for_each_lower_dev(lag_dev, port_dev, iter) {
+		if (mlxsw_sp_port_dev_check(port_dev)) {
+			err = mlxsw_sp_inetaddr_vport_event(l3_dev, port_dev,
+							    event, vid);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev,
+				       unsigned long event)
+{
+	if (netif_is_bridge_port(lag_dev))
+		return 0;
+
+	return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1);
+}
+
+static struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp,
+						    struct net_device *l3_dev)
+{
+	u16 fid;
+
+	if (is_vlan_dev(l3_dev))
+		fid = vlan_dev_vlan_id(l3_dev);
+	else if (mlxsw_sp->master_bridge.dev == l3_dev)
+		fid = 1;
+	else
+		return mlxsw_sp_vfid_find(mlxsw_sp, l3_dev);
+
+	return mlxsw_sp_fid_find(mlxsw_sp, fid);
+}
+
+static u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp)
+{
+	return mlxsw_core_max_ports(mlxsw_sp->core) + 1;
+}
+
+static enum mlxsw_flood_table_type mlxsw_sp_flood_table_type_get(u16 fid)
+{
+	return mlxsw_sp_fid_is_vfid(fid) ? MLXSW_REG_SFGC_TABLE_TYPE_FID :
+	       MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST;
+}
+
+static u16 mlxsw_sp_flood_table_index_get(u16 fid)
+{
+	return mlxsw_sp_fid_is_vfid(fid) ? mlxsw_sp_fid_to_vfid(fid) : fid;
+}
+
+static int mlxsw_sp_router_port_flood_set(struct mlxsw_sp *mlxsw_sp, u16 fid,
+					  bool set)
+{
+	u8 router_port = mlxsw_sp_router_port(mlxsw_sp);
+	enum mlxsw_flood_table_type table_type;
+	char *sftr_pl;
+	u16 index;
+	int err;
+
+	sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL);
+	if (!sftr_pl)
+		return -ENOMEM;
+
+	table_type = mlxsw_sp_flood_table_type_get(fid);
+	index = mlxsw_sp_flood_table_index_get(fid);
+	mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BC, index, table_type,
+			    1, router_port, set);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl);
+
+	kfree(sftr_pl);
+	return err;
+}
+
+static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid)
+{
+	if (mlxsw_sp_fid_is_vfid(fid))
+		return MLXSW_REG_RITR_FID_IF;
+	else
+		return MLXSW_REG_RITR_VLAN_IF;
+}
+
+static int mlxsw_sp_rif_bridge_op(struct mlxsw_sp *mlxsw_sp, u16 vr_id,
+				  struct net_device *l3_dev,
+				  u16 fid, u16 rif,
+				  bool create)
+{
+	enum mlxsw_reg_ritr_if_type rif_type;
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+
+	rif_type = mlxsw_sp_rif_type_get(fid);
+	mlxsw_reg_ritr_pack(ritr_pl, create, rif_type, rif, vr_id, l3_dev->mtu,
+			    l3_dev->dev_addr);
+	mlxsw_reg_ritr_fid_set(ritr_pl, rif_type, fid);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp,
+				      struct net_device *l3_dev,
+				      struct mlxsw_sp_fid *f)
+{
+	u32 tb_id = l3mdev_fib_table(l3_dev);
+	struct mlxsw_sp_rif *rif;
+	struct mlxsw_sp_vr *vr;
+	u16 rif_index;
+	int err;
+
+	rif_index = mlxsw_sp_avail_rif_get(mlxsw_sp);
+	if (rif_index == MLXSW_SP_INVALID_INDEX_RIF)
+		return -ERANGE;
+
+	vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN);
+	if (IS_ERR(vr))
+		return PTR_ERR(vr);
+
+	err = mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, true);
+	if (err)
+		goto err_port_flood_set;
+
+	err = mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid,
+				     rif_index, true);
+	if (err)
+		goto err_rif_bridge_op;
+
+	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true);
+	if (err)
+		goto err_rif_fdb_op;
+
+	rif = mlxsw_sp_rif_alloc(rif_index, vr->id, l3_dev, f);
+	if (!rif) {
+		err = -ENOMEM;
+		goto err_rif_alloc;
+	}
+
+	f->rif = rif;
+	mlxsw_sp->rifs[rif_index] = rif;
+	vr->rif_count++;
+
+	netdev_dbg(l3_dev, "RIF=%d created\n", rif_index);
+
+	return 0;
+
+err_rif_alloc:
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false);
+err_rif_fdb_op:
+	mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif_index,
+			       false);
+err_rif_bridge_op:
+	mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false);
+err_port_flood_set:
+	mlxsw_sp_vr_put(vr);
+	return err;
+}
+
+void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[rif->vr_id];
+	struct net_device *l3_dev = rif->dev;
+	struct mlxsw_sp_fid *f = rif->f;
+	u16 rif_index = rif->rif_index;
+
+	mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif);
+
+	vr->rif_count--;
+	mlxsw_sp->rifs[rif_index] = NULL;
+	f->rif = NULL;
+
+	kfree(rif);
+
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false);
+
+	mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif_index,
+			       false);
+
+	mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false);
+
+	mlxsw_sp_vr_put(vr);
+
+	netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif_index);
+}
+
+static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev,
+					  struct net_device *br_dev,
+					  unsigned long event)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev);
+	struct mlxsw_sp_fid *f;
+
+	/* FID can either be an actual FID if the L3 device is the
+	 * VLAN-aware bridge or a VLAN device on top. Otherwise, the
+	 * L3 device is a VLAN-unaware bridge and we get a vFID.
+	 */
+	f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev);
+	if (WARN_ON(!f))
+		return -EINVAL;
+
+	switch (event) {
+	case NETDEV_UP:
+		return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f);
+	case NETDEV_DOWN:
+		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif);
+		break;
+	}
+
+	return 0;
+}
+
+static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
+					unsigned long event)
+{
+	struct net_device *real_dev = vlan_dev_real_dev(vlan_dev);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev);
+	u16 vid = vlan_dev_vlan_id(vlan_dev);
+
+	if (mlxsw_sp_port_dev_check(real_dev))
+		return mlxsw_sp_inetaddr_vport_event(vlan_dev, real_dev, event,
+						     vid);
+	else if (netif_is_lag_master(real_dev))
+		return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event,
+						     vid);
+	else if (netif_is_bridge_master(real_dev) &&
+		 mlxsw_sp->master_bridge.dev == real_dev)
+		return mlxsw_sp_inetaddr_bridge_event(vlan_dev, real_dev,
+						      event);
+
+	return 0;
+}
+
+int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
+			    unsigned long event, void *ptr)
+{
+	struct in_ifaddr *ifa = (struct in_ifaddr *) ptr;
+	struct net_device *dev = ifa->ifa_dev->dev;
+	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_rif *rif;
+	int err = 0;
+
+	mlxsw_sp = mlxsw_sp_lower_get(dev);
+	if (!mlxsw_sp)
+		goto out;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	if (!mlxsw_sp_rif_should_config(rif, ifa->ifa_dev, event))
+		goto out;
+
+	if (mlxsw_sp_port_dev_check(dev))
+		err = mlxsw_sp_inetaddr_port_event(dev, event);
+	else if (netif_is_lag_master(dev))
+		err = mlxsw_sp_inetaddr_lag_event(dev, event);
+	else if (netif_is_bridge_master(dev))
+		err = mlxsw_sp_inetaddr_bridge_event(dev, dev, event);
+	else if (is_vlan_dev(dev))
+		err = mlxsw_sp_inetaddr_vlan_event(dev, event);
+
+out:
+	return notifier_from_errno(err);
+}
+
+static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif_index,
+			     const char *mac, int mtu)
+{
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+	int err;
+
+	mlxsw_reg_ritr_rif_pack(ritr_pl, rif_index);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_ritr_mtu_set(ritr_pl, mtu);
+	mlxsw_reg_ritr_if_mac_memcpy_to(ritr_pl, mac);
+	mlxsw_reg_ritr_op_set(ritr_pl, MLXSW_REG_RITR_RIF_CREATE);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+int mlxsw_sp_netdevice_router_port_event(struct net_device *dev)
+{
+	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_rif *rif;
+	int err;
+
+	mlxsw_sp = mlxsw_sp_lower_get(dev);
+	if (!mlxsw_sp)
+		return 0;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	if (!rif)
+		return 0;
+
+	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, rif->addr, rif->f->fid, false);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_rif_edit(mlxsw_sp, rif->rif_index, dev->dev_addr,
+				dev->mtu);
+	if (err)
+		goto err_rif_edit;
+
+	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, dev->dev_addr, rif->f->fid, true);
+	if (err)
+		goto err_rif_fdb_op;
+
+	ether_addr_copy(rif->addr, dev->dev_addr);
+	rif->mtu = dev->mtu;
+
+	netdev_dbg(dev, "Updated RIF=%d\n", rif->rif_index);
+
+	return 0;
+
+err_rif_fdb_op:
+	mlxsw_sp_rif_edit(mlxsw_sp, rif->rif_index, rif->addr, rif->mtu);
+err_rif_edit:
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, rif->addr, rif->f->fid, true);
+	return err;
+}
+
+int mlxsw_sp_vport_vrf_join(struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+	struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+	struct net_device *dev = mlxsw_sp_vport->dev;
+
+	/* In case vPort already has a RIF, then we need to drop it.
+	 * A new one will be created using the VRF's VR.
+	 */
+	if (f && f->rif)
+		mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport);
+
+	return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, dev);
+}
+
+void mlxsw_sp_vport_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+	mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport);
+}
+
+int mlxsw_sp_port_vrf_join(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	struct mlxsw_sp_port *mlxsw_sp_vport;
+
+	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, 1);
+	if (WARN_ON(!mlxsw_sp_vport))
+		return -EINVAL;
+
+	return mlxsw_sp_vport_vrf_join(mlxsw_sp_vport);
+}
+
+void mlxsw_sp_port_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	struct mlxsw_sp_port *mlxsw_sp_vport;
+
+	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, 1);
+	if (WARN_ON(!mlxsw_sp_vport))
+		return;
+
+	mlxsw_sp_vport_vrf_leave(mlxsw_sp_vport);
+}
+
+int mlxsw_sp_bridge_vrf_join(struct mlxsw_sp *mlxsw_sp,
+			     struct net_device *l3_dev)
+{
+	struct mlxsw_sp_fid *f;
+
+	f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev);
+	if (WARN_ON(!f))
+		return -EINVAL;
+
+	if (f->rif)
+		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif);
+
+	return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f);
+}
+
+void mlxsw_sp_bridge_vrf_leave(struct mlxsw_sp *mlxsw_sp,
+			       struct net_device *l3_dev)
+{
+	struct mlxsw_sp_fid *f;
+
+	f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev);
+	if (WARN_ON(!f))
+		return;
+	mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif);
+}
+
 static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb)
 {
 	struct mlxsw_sp *mlxsw_sp = container_of(nb, struct mlxsw_sp, fib_nb);
@@ -2606,6 +3510,48 @@ static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb)
 	mlxsw_sp_router_fib_flush(mlxsw_sp);
 }
 
+static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
+{
+	char rgcr_pl[MLXSW_REG_RGCR_LEN];
+	u64 max_rifs;
+	int err;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_RIFS))
+		return -EIO;
+
+	max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
+	mlxsw_sp->rifs = kcalloc(max_rifs, sizeof(struct mlxsw_sp_rif *),
+				 GFP_KERNEL);
+	if (!mlxsw_sp->rifs)
+		return -ENOMEM;
+
+	mlxsw_reg_rgcr_pack(rgcr_pl, true);
+	mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl);
+	if (err)
+		goto err_rgcr_fail;
+
+	return 0;
+
+err_rgcr_fail:
+	kfree(mlxsw_sp->rifs);
+	return err;
+}
+
+static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	char rgcr_pl[MLXSW_REG_RGCR_LEN];
+	int i;
+
+	mlxsw_reg_rgcr_pack(rgcr_pl, false);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl);
+
+	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
+		WARN_ON_ONCE(mlxsw_sp->rifs[i]);
+
+	kfree(mlxsw_sp->rifs);
+}
+
 int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 {
 	int err;
@@ -2625,7 +3571,10 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 	if (err)
 		goto err_nexthop_group_ht_init;
 
-	mlxsw_sp_lpm_init(mlxsw_sp);
+	err = mlxsw_sp_lpm_init(mlxsw_sp);
+	if (err)
+		goto err_lpm_init;
+
 	err = mlxsw_sp_vrs_init(mlxsw_sp);
 	if (err)
 		goto err_vrs_init;
@@ -2647,6 +3596,8 @@ err_register_fib_notifier:
 err_neigh_init:
 	mlxsw_sp_vrs_fini(mlxsw_sp);
 err_vrs_init:
+	mlxsw_sp_lpm_fini(mlxsw_sp);
+err_lpm_init:
 	rhashtable_destroy(&mlxsw_sp->router.nexthop_group_ht);
 err_nexthop_group_ht_init:
 	rhashtable_destroy(&mlxsw_sp->router.nexthop_ht);
@@ -2660,6 +3611,7 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
 	unregister_fib_notifier(&mlxsw_sp->fib_nb);
 	mlxsw_sp_neigh_fini(mlxsw_sp);
 	mlxsw_sp_vrs_fini(mlxsw_sp);
+	mlxsw_sp_lpm_fini(mlxsw_sp);
 	rhashtable_destroy(&mlxsw_sp->router.nexthop_group_ht);
 	rhashtable_destroy(&mlxsw_sp->router.nexthop_ht);
 	__mlxsw_sp_router_fini(mlxsw_sp);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
new file mode 100644
index 000000000000..c3095fef6697
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -0,0 +1,58 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Arkadi Sharshevsky <arkadis@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_ROUTER_H_
+#define _MLXSW_ROUTER_H_
+
+#include "spectrum.h"
+
+enum mlxsw_sp_rif_counter_dir {
+	MLXSW_SP_RIF_COUNTER_INGRESS,
+	MLXSW_SP_RIF_COUNTER_EGRESS,
+};
+
+u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif);
+int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif);
+int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_rif *rif,
+				   enum mlxsw_sp_rif_counter_dir dir,
+				   u64 *cnt);
+void mlxsw_sp_rif_counter_free(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_rif *rif,
+			       enum mlxsw_sp_rif_counter_dir dir);
+int mlxsw_sp_rif_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_rif *rif,
+			       enum mlxsw_sp_rif_counter_dir dir);
+
+#endif /* _MLXSW_ROUTER_H_*/
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 598727d578c1..05eaa15ad9d5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -568,8 +568,8 @@ void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f)
 
 	list_del(&f->list);
 
-	if (f->r)
-		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r);
+	if (f->rif)
+		mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif);
 
 	kfree(f);
 
@@ -1012,7 +1012,7 @@ static int mlxsw_sp_port_smid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mid,
 
 	mlxsw_reg_smid_pack(smid_pl, mid, mlxsw_sp_port->local_port, add);
 	if (clear_all_ports) {
-		for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++)
+		for (i = 1; i < mlxsw_core_max_ports(mlxsw_sp->core); i++)
 			if (mlxsw_sp->ports[i])
 				mlxsw_reg_smid_port_mask_set(smid_pl, i, 1);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index ec1e886d4566..3b0f72455681 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -1321,7 +1321,7 @@ static void mlxsw_sx_ports_remove(struct mlxsw_sx *mlxsw_sx)
 {
 	int i;
 
-	for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++)
+	for (i = 1; i < mlxsw_core_max_ports(mlxsw_sx->core); i++)
 		if (mlxsw_sx_port_created(mlxsw_sx, i))
 			mlxsw_sx_port_remove(mlxsw_sx, i);
 	kfree(mlxsw_sx->ports);
@@ -1329,17 +1329,18 @@ static void mlxsw_sx_ports_remove(struct mlxsw_sx *mlxsw_sx)
 
 static int mlxsw_sx_ports_create(struct mlxsw_sx *mlxsw_sx)
 {
+	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sx->core);
 	size_t alloc_size;
 	u8 module, width;
 	int i;
 	int err;
 
-	alloc_size = sizeof(struct mlxsw_sx_port *) * MLXSW_PORT_MAX_PORTS;
+	alloc_size = sizeof(struct mlxsw_sx_port *) * max_ports;
 	mlxsw_sx->ports = kzalloc(alloc_size, GFP_KERNEL);
 	if (!mlxsw_sx->ports)
 		return -ENOMEM;
 
-	for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++) {
+	for (i = 1; i < max_ports; i++) {
 		err = mlxsw_sx_port_module_info_get(mlxsw_sx, i, &module,
 						    &width);
 		if (err)
diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 279ee4612981..20358f87de57 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -212,25 +212,6 @@ static void ks8851_wrreg8(struct ks8851_net *ks, unsigned reg, unsigned val)
 }
 
 /**
- * ks8851_rx_1msg - select whether to use one or two messages for spi read
- * @ks: The device structure
- *
- * Return whether to generate a single message with a tx and rx buffer
- * supplied to spi_sync(), or alternatively send the tx and rx buffers
- * as separate messages.
- *
- * Depending on the hardware in use, a single message may be more efficient
- * on interrupts or work done by the driver.
- *
- * This currently always returns true until we add some per-device data passed
- * from the platform code to specify which mode is better.
- */
-static inline bool ks8851_rx_1msg(struct ks8851_net *ks)
-{
-	return true;
-}
-
-/**
  * ks8851_rdreg - issue read register command and return the data
  * @ks: The device state
  * @op: The register address and byte enables in message format.
@@ -251,14 +232,7 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned op,
 
 	txb[0] = cpu_to_le16(op | KS_SPIOP_RD);
 
-	if (ks8851_rx_1msg(ks)) {
-		msg = &ks->spi_msg1;
-		xfer = &ks->spi_xfer1;
-
-		xfer->tx_buf = txb;
-		xfer->rx_buf = trx;
-		xfer->len = rxl + 2;
-	} else {
+	if (ks->spidev->master->flags & SPI_MASTER_HALF_DUPLEX) {
 		msg = &ks->spi_msg2;
 		xfer = ks->spi_xfer2;
 
@@ -270,15 +244,22 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned op,
 		xfer->tx_buf = NULL;
 		xfer->rx_buf = trx;
 		xfer->len = rxl;
+	} else {
+		msg = &ks->spi_msg1;
+		xfer = &ks->spi_xfer1;
+
+		xfer->tx_buf = txb;
+		xfer->rx_buf = trx;
+		xfer->len = rxl + 2;
 	}
 
 	ret = spi_sync(ks->spidev, msg);
 	if (ret < 0)
 		netdev_err(ks->netdev, "read: spi_sync() failed\n");
-	else if (ks8851_rx_1msg(ks))
-		memcpy(rxb, trx + 2, rxl);
-	else
+	else if (ks->spidev->master->flags & SPI_MASTER_HALF_DUPLEX)
 		memcpy(rxb, trx, rxl);
+	else
+		memcpy(rxb, trx + 2, rxl);
 }
 
 /**
diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile
index 6933afa69df2..4a5d13ef92a4 100644
--- a/drivers/net/ethernet/netronome/nfp/Makefile
+++ b/drivers/net/ethernet/netronome/nfp/Makefile
@@ -6,6 +6,7 @@ nfp-objs := \
 	    nfpcore/nfp_cpplib.o \
 	    nfpcore/nfp_hwinfo.o \
 	    nfpcore/nfp_mip.o \
+	    nfpcore/nfp_mutex.o \
 	    nfpcore/nfp_nffw.o \
 	    nfpcore/nfp_nsp.o \
 	    nfpcore/nfp_nsp_eth.o \
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c
index dedac720fb29..bea2a1a6c211 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c
@@ -48,7 +48,7 @@
 #include "nfpcore/nfp.h"
 #include "nfpcore/nfp_cpp.h"
 #include "nfpcore/nfp_nffw.h"
-#include "nfpcore/nfp_nsp_eth.h"
+#include "nfpcore/nfp_nsp.h"
 
 #include "nfpcore/nfp6000_pcie.h"
 
@@ -385,8 +385,7 @@ static void nfp_pci_remove(struct pci_dev *pdev)
 {
 	struct nfp_pf *pf = pci_get_drvdata(pdev);
 
-	if (!list_empty(&pf->ports))
-		nfp_net_pci_remove(pf);
+	nfp_net_pci_remove(pf);
 
 	nfp_pcie_sriov_disable(pdev);
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.h b/drivers/net/ethernet/netronome/nfp/nfp_main.h
index 39105d0435e9..b57de047b002 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.h
@@ -42,7 +42,9 @@
 #include <linux/list.h>
 #include <linux/types.h>
 #include <linux/msi.h>
+#include <linux/mutex.h>
 #include <linux/pci.h>
+#include <linux/workqueue.h>
 
 struct dentry;
 struct pci_dev;
@@ -64,8 +66,11 @@ struct nfp_eth_table;
  * @fw_loaded:		Is the firmware loaded?
  * @eth_tbl:		NSP ETH table
  * @ddir:		Per-device debugfs directory
- * @num_ports:		Number of adapter ports
+ * @num_ports:		Number of adapter ports app firmware supports
+ * @num_netdevs:	Number of netdevs spawned
  * @ports:		Linked list of port structures (struct nfp_net)
+ * @port_lock:		Protects @ports, @num_ports, @num_netdevs
+ * @port_refresh_work:	Work entry for taking netdevs out
  */
 struct nfp_pf {
 	struct pci_dev *pdev;
@@ -88,7 +93,11 @@ struct nfp_pf {
 	struct dentry *ddir;
 
 	unsigned int num_ports;
+	unsigned int num_netdevs;
+
 	struct list_head ports;
+	struct work_struct port_refresh_work;
+	struct mutex port_lock;
 };
 
 extern struct pci_driver nfp_netvf_pci_driver;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index e614a376b595..052db9208fbb 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -50,14 +50,14 @@
 
 #include "nfp_net_ctrl.h"
 
-#define nn_err(nn, fmt, args...)  netdev_err((nn)->netdev, fmt, ## args)
-#define nn_warn(nn, fmt, args...) netdev_warn((nn)->netdev, fmt, ## args)
-#define nn_info(nn, fmt, args...) netdev_info((nn)->netdev, fmt, ## args)
-#define nn_dbg(nn, fmt, args...)  netdev_dbg((nn)->netdev, fmt, ## args)
-#define nn_warn_ratelimit(nn, fmt, args...)				\
+#define nn_err(nn, fmt, args...)  netdev_err((nn)->dp.netdev, fmt, ## args)
+#define nn_warn(nn, fmt, args...) netdev_warn((nn)->dp.netdev, fmt, ## args)
+#define nn_info(nn, fmt, args...) netdev_info((nn)->dp.netdev, fmt, ## args)
+#define nn_dbg(nn, fmt, args...)  netdev_dbg((nn)->dp.netdev, fmt, ## args)
+#define nn_dp_warn(dp, fmt, args...)					\
 	do {								\
 		if (unlikely(net_ratelimit()))				\
-			netdev_warn((nn)->netdev, fmt, ## args);	\
+			netdev_warn((dp)->netdev, fmt, ## args);	\
 	} while (0)
 
 /* Max time to wait for NFP to respond on updates (in seconds) */
@@ -112,6 +112,7 @@
 
 /* Forward declarations */
 struct nfp_cpp;
+struct nfp_eth_table_port;
 struct nfp_net;
 struct nfp_net_r_vector;
 
@@ -306,17 +307,13 @@ struct nfp_net_rx_buf {
  * @rd_p:       FL/RX ring read pointer (free running)
  * @idx:        Ring index from Linux's perspective
  * @fl_qcidx:   Queue Controller Peripheral (QCP) queue index for the freelist
- * @rx_qcidx:   Queue Controller Peripheral (QCP) queue index for the RX queue
  * @qcp_fl:     Pointer to base of the QCP freelist queue
- * @qcp_rx:     Pointer to base of the QCP RX queue
  * @wr_ptr_add: Accumulated number of buffers to add to QCP write pointer
  *              (used for free list batching)
  * @rxbufs:     Array of transmitted FL/RX buffers
  * @rxds:       Virtual address of FL/RX ring in host memory
  * @dma:        DMA address of the FL/RX ring
  * @size:       Size, in bytes, of the FL/RX ring (needed to free)
- * @bufsz:	Buffer allocation size for convenience of management routines
- *		(NOTE: this is in second cache line, do not use on fast path!)
  */
 struct nfp_net_rx_ring {
 	struct nfp_net_r_vector *r_vec;
@@ -325,20 +322,17 @@ struct nfp_net_rx_ring {
 	u32 wr_p;
 	u32 rd_p;
 
-	u16 idx;
-	u16 wr_ptr_add;
+	u32 idx;
+	u32 wr_ptr_add;
 
 	int fl_qcidx;
-	int rx_qcidx;
 	u8 __iomem *qcp_fl;
-	u8 __iomem *qcp_rx;
 
 	struct nfp_net_rx_buf *rxbufs;
 	struct nfp_net_rx_desc *rxds;
 
 	dma_addr_t dma;
 	unsigned int size;
-	unsigned int bufsz;
 } ____cacheline_aligned;
 
 /**
@@ -433,19 +427,76 @@ struct nfp_stat_pair {
 };
 
 /**
- * struct nfp_net - NFP network device structure
- * @pdev:               Backpointer to PCI device
- * @netdev:             Backpointer to net_device structure
- * @is_vf:              Is the driver attached to a VF?
+ * struct nfp_net_dp - NFP network device datapath data structure
+ * @dev:		Backpointer to struct device
+ * @netdev:		Backpointer to net_device structure
+ * @is_vf:		Is the driver attached to a VF?
  * @bpf_offload_skip_sw:  Offloaded BPF program will not be rerun by cls_bpf
  * @bpf_offload_xdp:	Offloaded BPF program is XDP
- * @ctrl:               Local copy of the control register/word.
- * @fl_bufsz:           Currently configured size of the freelist buffers
+ * @chained_metadata_format:  Firemware will use new metadata format
+ * @rx_dma_dir:		Mapping direction for RX buffers
+ * @rx_dma_off:		Offset at which DMA packets (for XDP headroom)
  * @rx_offset:		Offset in the RX buffers where packet data starts
+ * @ctrl:		Local copy of the control register/word.
+ * @fl_bufsz:		Currently configured size of the freelist buffers
  * @xdp_prog:		Installed XDP program
- * @fw_ver:             Firmware version
+ * @tx_rings:		Array of pre-allocated TX ring structures
+ * @rx_rings:		Array of pre-allocated RX ring structures
+ * @ctrl_bar:		Pointer to mapped control BAR
+ *
+ * @txd_cnt:		Size of the TX ring in number of descriptors
+ * @rxd_cnt:		Size of the RX ring in number of descriptors
+ * @num_r_vecs:		Number of used ring vectors
+ * @num_tx_rings:	Currently configured number of TX rings
+ * @num_stack_tx_rings:	Number of TX rings used by the stack (not XDP)
+ * @num_rx_rings:	Currently configured number of RX rings
+ * @mtu:		Device MTU
+ */
+struct nfp_net_dp {
+	struct device *dev;
+	struct net_device *netdev;
+
+	u8 is_vf:1;
+	u8 bpf_offload_skip_sw:1;
+	u8 bpf_offload_xdp:1;
+	u8 chained_metadata_format:1;
+
+	u8 rx_dma_dir;
+	u8 rx_dma_off;
+
+	u8 rx_offset;
+
+	u32 ctrl;
+	u32 fl_bufsz;
+
+	struct bpf_prog *xdp_prog;
+
+	struct nfp_net_tx_ring *tx_rings;
+	struct nfp_net_rx_ring *rx_rings;
+
+	u8 __iomem *ctrl_bar;
+
+	/* Cold data follows */
+
+	unsigned int txd_cnt;
+	unsigned int rxd_cnt;
+
+	unsigned int num_r_vecs;
+
+	unsigned int num_tx_rings;
+	unsigned int num_stack_tx_rings;
+	unsigned int num_rx_rings;
+
+	unsigned int mtu;
+};
+
+/**
+ * struct nfp_net - NFP network device structure
+ * @dp:			Datapath structure
+ * @fw_ver:		Firmware version
  * @cap:                Capabilities advertised by the Firmware
  * @max_mtu:            Maximum support MTU advertised by the Firmware
+ * @rss_hfunc:		RSS selected hash function
  * @rss_cfg:            RSS configuration
  * @rss_key:            RSS secret key
  * @rss_itbl:           RSS indirection table
@@ -454,17 +505,9 @@ struct nfp_stat_pair {
  * @rx_filter_change:	Jiffies when statistics last changed
  * @rx_filter_stats_timer:  Timer for polling filter offload statistics
  * @rx_filter_lock:	Lock protecting timer state changes (teardown)
+ * @max_r_vecs:		Number of allocated interrupt vectors for RX/TX
  * @max_tx_rings:       Maximum number of TX rings supported by the Firmware
  * @max_rx_rings:       Maximum number of RX rings supported by the Firmware
- * @num_tx_rings:       Currently configured number of TX rings
- * @num_stack_tx_rings:	Number of TX rings used by the stack (not XDP)
- * @num_rx_rings:       Currently configured number of RX rings
- * @txd_cnt:            Size of the TX ring in number of descriptors
- * @rxd_cnt:            Size of the RX ring in number of descriptors
- * @tx_rings:           Array of pre-allocated TX ring structures
- * @rx_rings:           Array of pre-allocated RX ring structures
- * @max_r_vecs:	        Number of allocated interrupt vectors for RX/TX
- * @num_r_vecs:         Number of used ring vectors
  * @r_vecs:             Pre-allocated array of ring vectors
  * @irq_entries:        Pre-allocated array of MSI-X entries
  * @lsc_handler:        Handler for Link State Change interrupt
@@ -480,7 +523,8 @@ struct nfp_stat_pair {
  * @reconfig_sync_present:  Some thread is performing synchronous reconfig
  * @reconfig_timer:	Timer for async reading of reconfig results
  * @link_up:            Is the link up?
- * @link_status_lock:	Protects @link_up and ensures atomicity with BAR reading
+ * @link_changed:	Has link state changes since last port refresh?
+ * @link_status_lock:	Protects @link_* and ensures atomicity with BAR reading
  * @rx_coalesce_usecs:      RX interrupt moderation usecs delay parameter
  * @rx_coalesce_max_frames: RX interrupt moderation frame count parameter
  * @tx_coalesce_usecs:      TX interrupt moderation usecs delay parameter
@@ -488,36 +532,24 @@ struct nfp_stat_pair {
  * @vxlan_ports:	VXLAN ports for RX inner csum offload communicated to HW
  * @vxlan_usecnt:	IPv4/IPv6 VXLAN port use counts
  * @qcp_cfg:            Pointer to QCP queue used for configuration notification
- * @ctrl_bar:           Pointer to mapped control BAR
  * @tx_bar:             Pointer to mapped TX queues
  * @rx_bar:             Pointer to mapped FL/RX queues
  * @debugfs_dir:	Device directory in debugfs
  * @ethtool_dump_flag:	Ethtool dump flag
  * @port_list:		Entry on device port list
+ * @pdev:		Backpointer to PCI device
  * @cpp:		CPP device handle if available
+ * @eth_port:		Translated ETH Table port entry
  */
 struct nfp_net {
-	struct pci_dev *pdev;
-	struct net_device *netdev;
-
-	unsigned is_vf:1;
-	unsigned bpf_offload_skip_sw:1;
-	unsigned bpf_offload_xdp:1;
-
-	u32 ctrl;
-	u32 fl_bufsz;
-
-	u32 rx_offset;
-
-	struct bpf_prog *xdp_prog;
-
-	struct nfp_net_tx_ring *tx_rings;
-	struct nfp_net_rx_ring *rx_rings;
+	struct nfp_net_dp dp;
 
 	struct nfp_net_fw_version fw_ver;
+
 	u32 cap;
 	u32 max_mtu;
 
+	u8 rss_hfunc;
 	u32 rss_cfg;
 	u8 rss_key[NFP_NET_CFG_RSS_KEY_SZ];
 	u8 rss_itbl[NFP_NET_CFG_RSS_ITBL_SZ];
@@ -530,18 +562,10 @@ struct nfp_net {
 	unsigned int max_tx_rings;
 	unsigned int max_rx_rings;
 
-	unsigned int num_tx_rings;
-	unsigned int num_stack_tx_rings;
-	unsigned int num_rx_rings;
-
 	int stride_tx;
 	int stride_rx;
 
-	int txd_cnt;
-	int rxd_cnt;
-
 	unsigned int max_r_vecs;
-	unsigned int num_r_vecs;
 	struct nfp_net_r_vector r_vecs[NFP_NET_MAX_R_VECS];
 	struct msix_entry irq_entries[NFP_NET_MAX_IRQS];
 
@@ -557,6 +581,7 @@ struct nfp_net {
 	u32 me_freq_mhz;
 
 	bool link_up;
+	bool link_changed;
 	spinlock_t link_status_lock;
 
 	spinlock_t reconfig_lock;
@@ -575,7 +600,6 @@ struct nfp_net {
 
 	u8 __iomem *qcp_cfg;
 
-	u8 __iomem *ctrl_bar;
 	u8 __iomem *tx_bar;
 	u8 __iomem *rx_bar;
 
@@ -584,14 +608,10 @@ struct nfp_net {
 
 	struct list_head port_list;
 
+	struct pci_dev *pdev;
 	struct nfp_cpp *cpp;
-};
 
-struct nfp_net_ring_set {
-	unsigned int n_rings;
-	unsigned int mtu;
-	unsigned int dcnt;
-	void *rings;
+	struct nfp_eth_table_port *eth_port;
 };
 
 /* Functions to read/write from/to a BAR
@@ -599,42 +619,42 @@ struct nfp_net_ring_set {
  */
 static inline u16 nn_readb(struct nfp_net *nn, int off)
 {
-	return readb(nn->ctrl_bar + off);
+	return readb(nn->dp.ctrl_bar + off);
 }
 
 static inline void nn_writeb(struct nfp_net *nn, int off, u8 val)
 {
-	writeb(val, nn->ctrl_bar + off);
+	writeb(val, nn->dp.ctrl_bar + off);
 }
 
 static inline u16 nn_readw(struct nfp_net *nn, int off)
 {
-	return readw(nn->ctrl_bar + off);
+	return readw(nn->dp.ctrl_bar + off);
 }
 
 static inline void nn_writew(struct nfp_net *nn, int off, u16 val)
 {
-	writew(val, nn->ctrl_bar + off);
+	writew(val, nn->dp.ctrl_bar + off);
 }
 
 static inline u32 nn_readl(struct nfp_net *nn, int off)
 {
-	return readl(nn->ctrl_bar + off);
+	return readl(nn->dp.ctrl_bar + off);
 }
 
 static inline void nn_writel(struct nfp_net *nn, int off, u32 val)
 {
-	writel(val, nn->ctrl_bar + off);
+	writel(val, nn->dp.ctrl_bar + off);
 }
 
 static inline u64 nn_readq(struct nfp_net *nn, int off)
 {
-	return readq(nn->ctrl_bar + off);
+	return readq(nn->dp.ctrl_bar + off);
 }
 
 static inline void nn_writeq(struct nfp_net *nn, int off, u64 val)
 {
-	writeq(val, nn->ctrl_bar + off);
+	writeq(val, nn->dp.ctrl_bar + off);
 }
 
 /* Flush posted PCI writes by reading something without side effects */
@@ -776,6 +796,7 @@ void nfp_net_netdev_clean(struct net_device *netdev);
 void nfp_net_set_ethtool_ops(struct net_device *netdev);
 void nfp_net_info(struct nfp_net *nn);
 int nfp_net_reconfig(struct nfp_net *nn, u32 update);
+unsigned int nfp_net_rss_key_sz(struct nfp_net *nn);
 void nfp_net_rss_write_itbl(struct nfp_net *nn);
 void nfp_net_rss_write_key(struct nfp_net *nn);
 void nfp_net_coalesce_write_cfg(struct nfp_net *nn);
@@ -787,9 +808,12 @@ void nfp_net_irqs_disable(struct pci_dev *pdev);
 void
 nfp_net_irqs_assign(struct nfp_net *nn, struct msix_entry *irq_entries,
 		    unsigned int n);
-int
-nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog,
-		      struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx);
+
+struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn);
+int nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *new);
+
+bool nfp_net_link_changed_read_clear(struct nfp_net *nn);
+void nfp_net_refresh_port_config(struct nfp_net *nn);
 
 #ifdef CONFIG_NFP_DEBUG
 void nfp_net_debugfs_create(void);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index a41377e26c07..e2197160e4dc 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -41,6 +41,7 @@
  *          Chris Telfer <chris.telfer@netronome.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/module.h>
@@ -66,6 +67,7 @@
 #include <net/pkt_cls.h>
 #include <net/vxlan.h>
 
+#include "nfpcore/nfp_nsp.h"
 #include "nfp_net_ctrl.h"
 #include "nfp_net.h"
 
@@ -83,20 +85,18 @@ void nfp_net_get_fw_version(struct nfp_net_fw_version *fw_ver,
 	put_unaligned_le32(reg, fw_ver);
 }
 
-static dma_addr_t
-nfp_net_dma_map_rx(struct nfp_net *nn, void *frag, unsigned int bufsz,
-		   int direction)
+static dma_addr_t nfp_net_dma_map_rx(struct nfp_net_dp *dp, void *frag)
 {
-	return dma_map_single(&nn->pdev->dev, frag + NFP_NET_RX_BUF_HEADROOM,
-			      bufsz - NFP_NET_RX_BUF_NON_DATA, direction);
+	return dma_map_single(dp->dev, frag + NFP_NET_RX_BUF_HEADROOM,
+			      dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA,
+			      dp->rx_dma_dir);
 }
 
-static void
-nfp_net_dma_unmap_rx(struct nfp_net *nn, dma_addr_t dma_addr,
-		     unsigned int bufsz, int direction)
+static void nfp_net_dma_unmap_rx(struct nfp_net_dp *dp, dma_addr_t dma_addr)
 {
-	dma_unmap_single(&nn->pdev->dev, dma_addr,
-			 bufsz - NFP_NET_RX_BUF_NON_DATA, direction);
+	dma_unmap_single(dp->dev, dma_addr,
+			 dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA,
+			 dp->rx_dma_dir);
 }
 
 /* Firmware reconfig
@@ -327,19 +327,22 @@ void
 nfp_net_irqs_assign(struct nfp_net *nn, struct msix_entry *irq_entries,
 		    unsigned int n)
 {
+	struct nfp_net_dp *dp = &nn->dp;
+
 	nn->max_r_vecs = n - NFP_NET_NON_Q_VECTORS;
-	nn->num_r_vecs = nn->max_r_vecs;
+	dp->num_r_vecs = nn->max_r_vecs;
 
 	memcpy(nn->irq_entries, irq_entries, sizeof(*irq_entries) * n);
 
-	if (nn->num_rx_rings > nn->num_r_vecs ||
-	    nn->num_tx_rings > nn->num_r_vecs)
-		nn_warn(nn, "More rings (%d,%d) than vectors (%d).\n",
-			nn->num_rx_rings, nn->num_tx_rings, nn->num_r_vecs);
+	if (dp->num_rx_rings > dp->num_r_vecs ||
+	    dp->num_tx_rings > dp->num_r_vecs)
+		dev_warn(nn->dp.dev, "More rings (%d,%d) than vectors (%d).\n",
+			 dp->num_rx_rings, dp->num_tx_rings,
+			 dp->num_r_vecs);
 
-	nn->num_rx_rings = min(nn->num_r_vecs, nn->num_rx_rings);
-	nn->num_tx_rings = min(nn->num_r_vecs, nn->num_tx_rings);
-	nn->num_stack_tx_rings = nn->num_tx_rings;
+	dp->num_rx_rings = min(dp->num_r_vecs, dp->num_rx_rings);
+	dp->num_tx_rings = min(dp->num_r_vecs, dp->num_tx_rings);
+	dp->num_stack_tx_rings = dp->num_tx_rings;
 }
 
 /**
@@ -373,6 +376,19 @@ static irqreturn_t nfp_net_irq_rxtx(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+bool nfp_net_link_changed_read_clear(struct nfp_net *nn)
+{
+	unsigned long flags;
+	bool ret;
+
+	spin_lock_irqsave(&nn->link_status_lock, flags);
+	ret = nn->link_changed;
+	nn->link_changed = false;
+	spin_unlock_irqrestore(&nn->link_status_lock, flags);
+
+	return ret;
+}
+
 /**
  * nfp_net_read_link_status() - Reread link status from control BAR
  * @nn:       NFP Network structure
@@ -392,13 +408,14 @@ static void nfp_net_read_link_status(struct nfp_net *nn)
 		goto out;
 
 	nn->link_up = link_up;
+	nn->link_changed = true;
 
 	if (nn->link_up) {
-		netif_carrier_on(nn->netdev);
-		netdev_info(nn->netdev, "NIC Link is Up\n");
+		netif_carrier_on(nn->dp.netdev);
+		netdev_info(nn->dp.netdev, "NIC Link is Up\n");
 	} else {
-		netif_carrier_off(nn->netdev);
-		netdev_info(nn->netdev, "NIC Link is Down\n");
+		netif_carrier_off(nn->dp.netdev);
+		netdev_info(nn->dp.netdev, "NIC Link is Down\n");
 	}
 out:
 	spin_unlock_irqrestore(&nn->link_status_lock, flags);
@@ -476,10 +493,7 @@ nfp_net_rx_ring_init(struct nfp_net_rx_ring *rx_ring,
 	rx_ring->r_vec = r_vec;
 
 	rx_ring->fl_qcidx = rx_ring->idx * nn->stride_rx;
-	rx_ring->rx_qcidx = rx_ring->fl_qcidx + (nn->stride_rx - 1);
-
 	rx_ring->qcp_fl = nn->rx_bar + NFP_QCP_QUEUE_OFF(rx_ring->fl_qcidx);
-	rx_ring->qcp_rx = nn->rx_bar + NFP_QCP_QUEUE_OFF(rx_ring->rx_qcidx);
 }
 
 /**
@@ -530,7 +544,7 @@ nfp_net_aux_irq_request(struct nfp_net *nn, u32 ctrl_offset,
 
 	entry = &nn->irq_entries[vector_idx];
 
-	snprintf(name, name_sz, format, netdev_name(nn->netdev));
+	snprintf(name, name_sz, format, netdev_name(nn->dp.netdev));
 	err = request_irq(entry->vector, handler, 0, name, nn);
 	if (err) {
 		nn_err(nn, "Failed to request IRQ %d (err=%d).\n",
@@ -617,7 +631,6 @@ static void nfp_net_tx_ring_stop(struct netdev_queue *nd_q,
 
 /**
  * nfp_net_tx_tso() - Set up Tx descriptor for LSO
- * @nn:  NFP Net device
  * @r_vec: per-ring structure
  * @txbuf: Pointer to driver soft TX descriptor
  * @txd: Pointer to HW TX descriptor
@@ -626,7 +639,7 @@ static void nfp_net_tx_ring_stop(struct netdev_queue *nd_q,
  * Set up Tx descriptor for LSO, do nothing for non-LSO skbs.
  * Return error on packet header greater than maximum supported LSO header size.
  */
-static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
+static void nfp_net_tx_tso(struct nfp_net_r_vector *r_vec,
 			   struct nfp_net_tx_buf *txbuf,
 			   struct nfp_net_tx_desc *txd, struct sk_buff *skb)
 {
@@ -657,7 +670,7 @@ static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 
 /**
  * nfp_net_tx_csum() - Set TX CSUM offload flags in TX descriptor
- * @nn:  NFP Net device
+ * @dp:  NFP Net data path struct
  * @r_vec: per-ring structure
  * @txbuf: Pointer to driver soft TX descriptor
  * @txd: Pointer to TX descriptor
@@ -666,7 +679,8 @@ static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
  * This function sets the TX checksum flags in the TX descriptor based
  * on the configuration and the protocol of the packet to be transmitted.
  */
-static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
+static void nfp_net_tx_csum(struct nfp_net_dp *dp,
+			    struct nfp_net_r_vector *r_vec,
 			    struct nfp_net_tx_buf *txbuf,
 			    struct nfp_net_tx_desc *txd, struct sk_buff *skb)
 {
@@ -674,7 +688,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 	struct iphdr *iph;
 	u8 l4_hdr;
 
-	if (!(nn->ctrl & NFP_NET_CFG_CTRL_TXCSUM))
+	if (!(dp->ctrl & NFP_NET_CFG_CTRL_TXCSUM))
 		return;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
@@ -693,8 +707,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 	} else if (ipv6h->version == 6) {
 		l4_hdr = ipv6h->nexthdr;
 	} else {
-		nn_warn_ratelimit(nn, "partial checksum but ipv=%x!\n",
-				  iph->version);
+		nn_dp_warn(dp, "partial checksum but ipv=%x!\n", iph->version);
 		return;
 	}
 
@@ -706,8 +719,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 		txd->flags |= PCIE_DESC_TX_UDP_CSUM;
 		break;
 	default:
-		nn_warn_ratelimit(nn, "partial checksum but l4 proto=%x!\n",
-				  l4_hdr);
+		nn_dp_warn(dp, "partial checksum but l4 proto=%x!\n", l4_hdr);
 		return;
 	}
 
@@ -737,28 +749,31 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 	const struct skb_frag_struct *frag;
-	struct nfp_net_r_vector *r_vec;
 	struct nfp_net_tx_desc *txd, txdg;
-	struct nfp_net_tx_buf *txbuf;
 	struct nfp_net_tx_ring *tx_ring;
+	struct nfp_net_r_vector *r_vec;
+	struct nfp_net_tx_buf *txbuf;
 	struct netdev_queue *nd_q;
+	struct nfp_net_dp *dp;
 	dma_addr_t dma_addr;
 	unsigned int fsize;
 	int f, nr_frags;
 	int wr_idx;
 	u16 qidx;
 
+	dp = &nn->dp;
 	qidx = skb_get_queue_mapping(skb);
-	tx_ring = &nn->tx_rings[qidx];
+	tx_ring = &dp->tx_rings[qidx];
 	r_vec = tx_ring->r_vec;
-	nd_q = netdev_get_tx_queue(nn->netdev, qidx);
+	nd_q = netdev_get_tx_queue(dp->netdev, qidx);
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
 
 	if (unlikely(nfp_net_tx_full(tx_ring, nr_frags + 1))) {
-		nn_warn_ratelimit(nn, "TX ring %d busy. wrp=%u rdp=%u\n",
-				  qidx, tx_ring->wr_p, tx_ring->rd_p);
+		nn_dp_warn(dp, "TX ring %d busy. wrp=%u rdp=%u\n",
+			   qidx, tx_ring->wr_p, tx_ring->rd_p);
 		netif_tx_stop_queue(nd_q);
+		nfp_net_tx_xmit_more_flush(tx_ring);
 		u64_stats_update_begin(&r_vec->tx_sync);
 		r_vec->tx_busy++;
 		u64_stats_update_end(&r_vec->tx_sync);
@@ -766,9 +781,9 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 	}
 
 	/* Start with the head skbuf */
-	dma_addr = dma_map_single(&nn->pdev->dev, skb->data, skb_headlen(skb),
+	dma_addr = dma_map_single(dp->dev, skb->data, skb_headlen(skb),
 				  DMA_TO_DEVICE);
-	if (dma_mapping_error(&nn->pdev->dev, dma_addr))
+	if (dma_mapping_error(dp->dev, dma_addr))
 		goto err_free;
 
 	wr_idx = tx_ring->wr_p & (tx_ring->cnt - 1);
@@ -792,11 +807,11 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 	txd->mss = 0;
 	txd->l4_offset = 0;
 
-	nfp_net_tx_tso(nn, r_vec, txbuf, txd, skb);
+	nfp_net_tx_tso(r_vec, txbuf, txd, skb);
 
-	nfp_net_tx_csum(nn, r_vec, txbuf, txd, skb);
+	nfp_net_tx_csum(dp, r_vec, txbuf, txd, skb);
 
-	if (skb_vlan_tag_present(skb) && nn->ctrl & NFP_NET_CFG_CTRL_TXVLAN) {
+	if (skb_vlan_tag_present(skb) && dp->ctrl & NFP_NET_CFG_CTRL_TXVLAN) {
 		txd->flags |= PCIE_DESC_TX_VLAN;
 		txd->vlan = cpu_to_le16(skb_vlan_tag_get(skb));
 	}
@@ -810,9 +825,9 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 			frag = &skb_shinfo(skb)->frags[f];
 			fsize = skb_frag_size(frag);
 
-			dma_addr = skb_frag_dma_map(&nn->pdev->dev, frag, 0,
+			dma_addr = skb_frag_dma_map(dp->dev, frag, 0,
 						    fsize, DMA_TO_DEVICE);
-			if (dma_mapping_error(&nn->pdev->dev, dma_addr))
+			if (dma_mapping_error(dp->dev, dma_addr))
 				goto err_unmap;
 
 			wr_idx = (wr_idx + 1) & (tx_ring->cnt - 1);
@@ -851,8 +866,7 @@ err_unmap:
 	--f;
 	while (f >= 0) {
 		frag = &skb_shinfo(skb)->frags[f];
-		dma_unmap_page(&nn->pdev->dev,
-			       tx_ring->txbufs[wr_idx].dma_addr,
+		dma_unmap_page(dp->dev, tx_ring->txbufs[wr_idx].dma_addr,
 			       skb_frag_size(frag), DMA_TO_DEVICE);
 		tx_ring->txbufs[wr_idx].skb = NULL;
 		tx_ring->txbufs[wr_idx].dma_addr = 0;
@@ -861,13 +875,14 @@ err_unmap:
 		if (wr_idx < 0)
 			wr_idx += tx_ring->cnt;
 	}
-	dma_unmap_single(&nn->pdev->dev, tx_ring->txbufs[wr_idx].dma_addr,
+	dma_unmap_single(dp->dev, tx_ring->txbufs[wr_idx].dma_addr,
 			 skb_headlen(skb), DMA_TO_DEVICE);
 	tx_ring->txbufs[wr_idx].skb = NULL;
 	tx_ring->txbufs[wr_idx].dma_addr = 0;
 	tx_ring->txbufs[wr_idx].fidx = -2;
 err_free:
-	nn_warn_ratelimit(nn, "Failed to map DMA TX buffer\n");
+	nn_dp_warn(dp, "Failed to map DMA TX buffer\n");
+	nfp_net_tx_xmit_more_flush(tx_ring);
 	u64_stats_update_begin(&r_vec->tx_sync);
 	r_vec->tx_errors++;
 	u64_stats_update_end(&r_vec->tx_sync);
@@ -884,7 +899,7 @@ err_free:
 static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
+	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
 	const struct skb_frag_struct *frag;
 	struct netdev_queue *nd_q;
 	u32 done_pkts = 0, done_bytes = 0;
@@ -918,8 +933,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 
 		if (fidx == -1) {
 			/* unmap head */
-			dma_unmap_single(&nn->pdev->dev,
-					 tx_ring->txbufs[idx].dma_addr,
+			dma_unmap_single(dp->dev, tx_ring->txbufs[idx].dma_addr,
 					 skb_headlen(skb), DMA_TO_DEVICE);
 
 			done_pkts += tx_ring->txbufs[idx].pkt_cnt;
@@ -927,8 +941,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 		} else {
 			/* unmap fragment */
 			frag = &skb_shinfo(skb)->frags[fidx];
-			dma_unmap_page(&nn->pdev->dev,
-				       tx_ring->txbufs[idx].dma_addr,
+			dma_unmap_page(dp->dev, tx_ring->txbufs[idx].dma_addr,
 				       skb_frag_size(frag), DMA_TO_DEVICE);
 		}
 
@@ -948,7 +961,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 	r_vec->tx_pkts += done_pkts;
 	u64_stats_update_end(&r_vec->tx_sync);
 
-	nd_q = netdev_get_tx_queue(nn->netdev, tx_ring->idx);
+	nd_q = netdev_get_tx_queue(dp->netdev, tx_ring->idx);
 	netdev_tx_completed_queue(nd_q, done_pkts, done_bytes);
 	if (nfp_net_tx_ring_should_wake(tx_ring)) {
 		/* Make sure TX thread will see updated tx_ring->rd_p */
@@ -966,7 +979,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
+	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
 	u32 done_pkts = 0, done_bytes = 0;
 	int idx, todo;
 	u32 qcp_rd_p;
@@ -989,8 +1002,7 @@ static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring)
 		if (!tx_ring->txbufs[idx].frag)
 			continue;
 
-		nfp_net_dma_unmap_rx(nn, tx_ring->txbufs[idx].dma_addr,
-				     nn->fl_bufsz, DMA_BIDIRECTIONAL);
+		nfp_net_dma_unmap_rx(dp, tx_ring->txbufs[idx].dma_addr);
 		__free_page(virt_to_page(tx_ring->txbufs[idx].frag));
 
 		done_pkts++;
@@ -1015,17 +1027,16 @@ static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring)
 
 /**
  * nfp_net_tx_ring_reset() - Free any untransmitted buffers and reset pointers
- * @nn:		NFP Net device
+ * @dp:		NFP Net data path struct
  * @tx_ring:	TX ring structure
  *
  * Assumes that the device is stopped
  */
 static void
-nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
+nfp_net_tx_ring_reset(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
 	const struct skb_frag_struct *frag;
-	struct pci_dev *pdev = nn->pdev;
 	struct netdev_queue *nd_q;
 
 	while (tx_ring->rd_p != tx_ring->wr_p) {
@@ -1036,8 +1047,7 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
 		tx_buf = &tx_ring->txbufs[idx];
 
 		if (tx_ring == r_vec->xdp_ring) {
-			nfp_net_dma_unmap_rx(nn, tx_buf->dma_addr,
-					     nn->fl_bufsz, DMA_BIDIRECTIONAL);
+			nfp_net_dma_unmap_rx(dp, tx_buf->dma_addr);
 			__free_page(virt_to_page(tx_ring->txbufs[idx].frag));
 		} else {
 			struct sk_buff *skb = tx_ring->txbufs[idx].skb;
@@ -1045,13 +1055,13 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
 
 			if (tx_buf->fidx == -1) {
 				/* unmap head */
-				dma_unmap_single(&pdev->dev, tx_buf->dma_addr,
+				dma_unmap_single(dp->dev, tx_buf->dma_addr,
 						 skb_headlen(skb),
 						 DMA_TO_DEVICE);
 			} else {
 				/* unmap fragment */
 				frag = &skb_shinfo(skb)->frags[tx_buf->fidx];
-				dma_unmap_page(&pdev->dev, tx_buf->dma_addr,
+				dma_unmap_page(dp->dev, tx_buf->dma_addr,
 					       skb_frag_size(frag),
 					       DMA_TO_DEVICE);
 			}
@@ -1078,7 +1088,7 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
 	if (tx_ring == r_vec->xdp_ring)
 		return;
 
-	nd_q = netdev_get_tx_queue(nn->netdev, tx_ring->idx);
+	nd_q = netdev_get_tx_queue(dp->netdev, tx_ring->idx);
 	netdev_tx_reset_queue(nd_q);
 }
 
@@ -1087,7 +1097,7 @@ static void nfp_net_tx_timeout(struct net_device *netdev)
 	struct nfp_net *nn = netdev_priv(netdev);
 	int i;
 
-	for (i = 0; i < nn->netdev->real_num_tx_queues; i++) {
+	for (i = 0; i < nn->dp.netdev->real_num_tx_queues; i++) {
 		if (!netif_tx_queue_stopped(netdev_get_tx_queue(netdev, i)))
 			continue;
 		nn_warn(nn, "TX timeout on ring: %d\n", i);
@@ -1098,16 +1108,17 @@ static void nfp_net_tx_timeout(struct net_device *netdev)
 /* Receive processing
  */
 static unsigned int
-nfp_net_calc_fl_bufsz(struct nfp_net *nn, unsigned int mtu)
+nfp_net_calc_fl_bufsz(struct nfp_net_dp *dp)
 {
 	unsigned int fl_bufsz;
 
 	fl_bufsz = NFP_NET_RX_BUF_HEADROOM;
-	if (nn->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
+	fl_bufsz += dp->rx_dma_off;
+	if (dp->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
 		fl_bufsz += NFP_NET_MAX_PREPEND;
 	else
-		fl_bufsz += nn->rx_offset;
-	fl_bufsz += ETH_HLEN + VLAN_HLEN * 2 + mtu;
+		fl_bufsz += dp->rx_offset;
+	fl_bufsz += ETH_HLEN + VLAN_HLEN * 2 + dp->mtu;
 
 	fl_bufsz = SKB_DATA_ALIGN(fl_bufsz);
 	fl_bufsz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
@@ -1126,62 +1137,56 @@ nfp_net_free_frag(void *frag, bool xdp)
 
 /**
  * nfp_net_rx_alloc_one() - Allocate and map page frag for RX
+ * @dp:		NFP Net data path struct
  * @rx_ring:	RX ring structure of the skb
  * @dma_addr:	Pointer to storage for DMA address (output param)
- * @fl_bufsz:	size of freelist buffers
- * @xdp:	Whether XDP is enabled
  *
  * This function will allcate a new page frag, map it for DMA.
  *
  * Return: allocated page frag or NULL on failure.
  */
 static void *
-nfp_net_rx_alloc_one(struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr,
-		     unsigned int fl_bufsz, bool xdp)
+nfp_net_rx_alloc_one(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring,
+		     dma_addr_t *dma_addr)
 {
-	struct nfp_net *nn = rx_ring->r_vec->nfp_net;
-	int direction;
 	void *frag;
 
-	if (!xdp)
-		frag = netdev_alloc_frag(fl_bufsz);
+	if (!dp->xdp_prog)
+		frag = netdev_alloc_frag(dp->fl_bufsz);
 	else
 		frag = page_address(alloc_page(GFP_KERNEL | __GFP_COLD));
 	if (!frag) {
-		nn_warn_ratelimit(nn, "Failed to alloc receive page frag\n");
+		nn_dp_warn(dp, "Failed to alloc receive page frag\n");
 		return NULL;
 	}
 
-	direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
-
-	*dma_addr = nfp_net_dma_map_rx(nn, frag, fl_bufsz, direction);
-	if (dma_mapping_error(&nn->pdev->dev, *dma_addr)) {
-		nfp_net_free_frag(frag, xdp);
-		nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n");
+	*dma_addr = nfp_net_dma_map_rx(dp, frag);
+	if (dma_mapping_error(dp->dev, *dma_addr)) {
+		nfp_net_free_frag(frag, dp->xdp_prog);
+		nn_dp_warn(dp, "Failed to map DMA RX buffer\n");
 		return NULL;
 	}
 
 	return frag;
 }
 
-static void *
-nfp_net_napi_alloc_one(struct nfp_net *nn, int direction, dma_addr_t *dma_addr)
+static void *nfp_net_napi_alloc_one(struct nfp_net_dp *dp, dma_addr_t *dma_addr)
 {
 	void *frag;
 
-	if (!nn->xdp_prog)
-		frag = napi_alloc_frag(nn->fl_bufsz);
+	if (!dp->xdp_prog)
+		frag = napi_alloc_frag(dp->fl_bufsz);
 	else
 		frag = page_address(alloc_page(GFP_ATOMIC | __GFP_COLD));
 	if (!frag) {
-		nn_warn_ratelimit(nn, "Failed to alloc receive page frag\n");
+		nn_dp_warn(dp, "Failed to alloc receive page frag\n");
 		return NULL;
 	}
 
-	*dma_addr = nfp_net_dma_map_rx(nn, frag, nn->fl_bufsz, direction);
-	if (dma_mapping_error(&nn->pdev->dev, *dma_addr)) {
-		nfp_net_free_frag(frag, nn->xdp_prog);
-		nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n");
+	*dma_addr = nfp_net_dma_map_rx(dp, frag);
+	if (dma_mapping_error(dp->dev, *dma_addr)) {
+		nfp_net_free_frag(frag, dp->xdp_prog);
+		nn_dp_warn(dp, "Failed to map DMA RX buffer\n");
 		return NULL;
 	}
 
@@ -1190,11 +1195,13 @@ nfp_net_napi_alloc_one(struct nfp_net *nn, int direction, dma_addr_t *dma_addr)
 
 /**
  * nfp_net_rx_give_one() - Put mapped skb on the software and hardware rings
+ * @dp:		NFP Net data path struct
  * @rx_ring:	RX ring structure
  * @frag:	page fragment buffer
  * @dma_addr:	DMA address of skb mapping
  */
-static void nfp_net_rx_give_one(struct nfp_net_rx_ring *rx_ring,
+static void nfp_net_rx_give_one(const struct nfp_net_dp *dp,
+				struct nfp_net_rx_ring *rx_ring,
 				void *frag, dma_addr_t dma_addr)
 {
 	unsigned int wr_idx;
@@ -1208,7 +1215,8 @@ static void nfp_net_rx_give_one(struct nfp_net_rx_ring *rx_ring,
 	/* Fill freelist descriptor */
 	rx_ring->rxds[wr_idx].fld.reserved = 0;
 	rx_ring->rxds[wr_idx].fld.meta_len_dd = 0;
-	nfp_desc_set_dma_addr(&rx_ring->rxds[wr_idx].fld, dma_addr);
+	nfp_desc_set_dma_addr(&rx_ring->rxds[wr_idx].fld,
+			      dma_addr + dp->rx_dma_off);
 
 	rx_ring->wr_p++;
 	rx_ring->wr_ptr_add++;
@@ -1249,19 +1257,17 @@ static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring)
 
 /**
  * nfp_net_rx_ring_bufs_free() - Free any buffers currently on the RX ring
- * @nn:		NFP Net device
+ * @dp:		NFP Net data path struct
  * @rx_ring:	RX ring to remove buffers from
- * @xdp:	Whether XDP is enabled
  *
  * Assumes that the device is stopped and buffers are in [0, ring->cnt - 1)
  * entries.  After device is disabled nfp_net_rx_ring_reset() must be called
  * to restore required ring geometry.
  */
 static void
-nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
-			  bool xdp)
+nfp_net_rx_ring_bufs_free(struct nfp_net_dp *dp,
+			  struct nfp_net_rx_ring *rx_ring)
 {
-	int direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
 	unsigned int i;
 
 	for (i = 0; i < rx_ring->cnt - 1; i++) {
@@ -1272,9 +1278,8 @@ nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 		if (!rx_ring->rxbufs[i].frag)
 			continue;
 
-		nfp_net_dma_unmap_rx(nn, rx_ring->rxbufs[i].dma_addr,
-				     rx_ring->bufsz, direction);
-		nfp_net_free_frag(rx_ring->rxbufs[i].frag, xdp);
+		nfp_net_dma_unmap_rx(dp, rx_ring->rxbufs[i].dma_addr);
+		nfp_net_free_frag(rx_ring->rxbufs[i].frag, dp->xdp_prog);
 		rx_ring->rxbufs[i].dma_addr = 0;
 		rx_ring->rxbufs[i].frag = NULL;
 	}
@@ -1282,13 +1287,12 @@ nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 
 /**
  * nfp_net_rx_ring_bufs_alloc() - Fill RX ring with buffers (don't give to FW)
- * @nn:		NFP Net device
+ * @dp:		NFP Net data path struct
  * @rx_ring:	RX ring to remove buffers from
- * @xdp:	Whether XDP is enabled
  */
 static int
-nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
-			   bool xdp)
+nfp_net_rx_ring_bufs_alloc(struct nfp_net_dp *dp,
+			   struct nfp_net_rx_ring *rx_ring)
 {
 	struct nfp_net_rx_buf *rxbufs;
 	unsigned int i;
@@ -1297,10 +1301,9 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 
 	for (i = 0; i < rx_ring->cnt - 1; i++) {
 		rxbufs[i].frag =
-			nfp_net_rx_alloc_one(rx_ring, &rxbufs[i].dma_addr,
-					     rx_ring->bufsz, xdp);
+			nfp_net_rx_alloc_one(dp, rx_ring, &rxbufs[i].dma_addr);
 		if (!rxbufs[i].frag) {
-			nfp_net_rx_ring_bufs_free(nn, rx_ring, xdp);
+			nfp_net_rx_ring_bufs_free(dp, rx_ring);
 			return -ENOMEM;
 		}
 	}
@@ -1310,14 +1313,17 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 
 /**
  * nfp_net_rx_ring_fill_freelist() - Give buffers from the ring to FW
+ * @dp:	     NFP Net data path struct
  * @rx_ring: RX ring to fill
  */
-static void nfp_net_rx_ring_fill_freelist(struct nfp_net_rx_ring *rx_ring)
+static void
+nfp_net_rx_ring_fill_freelist(struct nfp_net_dp *dp,
+			      struct nfp_net_rx_ring *rx_ring)
 {
 	unsigned int i;
 
 	for (i = 0; i < rx_ring->cnt - 1; i++)
-		nfp_net_rx_give_one(rx_ring, rx_ring->rxbufs[i].frag,
+		nfp_net_rx_give_one(dp, rx_ring, rx_ring->rxbufs[i].frag,
 				    rx_ring->rxbufs[i].dma_addr);
 }
 
@@ -1337,17 +1343,18 @@ static int nfp_net_rx_csum_has_errors(u16 flags)
 
 /**
  * nfp_net_rx_csum() - set SKB checksum field based on RX descriptor flags
- * @nn:  NFP Net device
+ * @dp:  NFP Net data path struct
  * @r_vec: per-ring structure
  * @rxd: Pointer to RX descriptor
  * @skb: Pointer to SKB
  */
-static void nfp_net_rx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
+static void nfp_net_rx_csum(struct nfp_net_dp *dp,
+			    struct nfp_net_r_vector *r_vec,
 			    struct nfp_net_rx_desc *rxd, struct sk_buff *skb)
 {
 	skb_checksum_none_assert(skb);
 
-	if (!(nn->netdev->features & NETIF_F_RXCSUM))
+	if (!(dp->netdev->features & NETIF_F_RXCSUM))
 		return;
 
 	if (nfp_net_rx_csum_has_errors(le16_to_cpu(rxd->rxd.flags))) {
@@ -1398,24 +1405,21 @@ static void nfp_net_set_hash(struct net_device *netdev, struct sk_buff *skb,
 
 static void
 nfp_net_set_hash_desc(struct net_device *netdev, struct sk_buff *skb,
-		      struct nfp_net_rx_desc *rxd)
+		      void *data, struct nfp_net_rx_desc *rxd)
 {
-	struct nfp_net_rx_hash *rx_hash;
+	struct nfp_net_rx_hash *rx_hash = data;
 
 	if (!(rxd->rxd.flags & PCIE_DESC_RX_RSS))
 		return;
 
-	rx_hash = (struct nfp_net_rx_hash *)(skb->data - sizeof(*rx_hash));
-
 	nfp_net_set_hash(netdev, skb, get_unaligned_be32(&rx_hash->hash_type),
 			 &rx_hash->hash);
 }
 
 static void *
 nfp_net_parse_meta(struct net_device *netdev, struct sk_buff *skb,
-		   int meta_len)
+		   void *data, int meta_len)
 {
-	u8 *data = skb->data - meta_len;
 	u32 meta_info;
 
 	meta_info = get_unaligned_be32(data);
@@ -1445,8 +1449,9 @@ nfp_net_parse_meta(struct net_device *netdev, struct sk_buff *skb,
 }
 
 static void
-nfp_net_rx_drop(struct nfp_net_r_vector *r_vec, struct nfp_net_rx_ring *rx_ring,
-		struct nfp_net_rx_buf *rxbuf, struct sk_buff *skb)
+nfp_net_rx_drop(const struct nfp_net_dp *dp, struct nfp_net_r_vector *r_vec,
+		struct nfp_net_rx_ring *rx_ring, struct nfp_net_rx_buf *rxbuf,
+		struct sk_buff *skb)
 {
 	u64_stats_update_begin(&r_vec->rx_sync);
 	r_vec->rx_drops++;
@@ -1458,15 +1463,15 @@ nfp_net_rx_drop(struct nfp_net_r_vector *r_vec, struct nfp_net_rx_ring *rx_ring,
 	if (skb && rxbuf && skb->head == rxbuf->frag)
 		page_ref_inc(virt_to_head_page(rxbuf->frag));
 	if (rxbuf)
-		nfp_net_rx_give_one(rx_ring, rxbuf->frag, rxbuf->dma_addr);
+		nfp_net_rx_give_one(dp, rx_ring, rxbuf->frag, rxbuf->dma_addr);
 	if (skb)
 		dev_kfree_skb_any(skb);
 }
 
 static bool
-nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
+nfp_net_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring,
 		   struct nfp_net_tx_ring *tx_ring,
-		   struct nfp_net_rx_buf *rxbuf, unsigned int pkt_off,
+		   struct nfp_net_rx_buf *rxbuf, unsigned int dma_off,
 		   unsigned int pkt_len)
 {
 	struct nfp_net_tx_buf *txbuf;
@@ -1476,16 +1481,16 @@ nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 	int wr_idx;
 
 	if (unlikely(nfp_net_tx_full(tx_ring, 1))) {
-		nfp_net_rx_drop(rx_ring->r_vec, rx_ring, rxbuf, NULL);
+		nfp_net_rx_drop(dp, rx_ring->r_vec, rx_ring, rxbuf, NULL);
 		return false;
 	}
 
-	new_frag = nfp_net_napi_alloc_one(nn, DMA_BIDIRECTIONAL, &new_dma_addr);
+	new_frag = nfp_net_napi_alloc_one(dp, &new_dma_addr);
 	if (unlikely(!new_frag)) {
-		nfp_net_rx_drop(rx_ring->r_vec, rx_ring, rxbuf, NULL);
+		nfp_net_rx_drop(dp, rx_ring->r_vec, rx_ring, rxbuf, NULL);
 		return false;
 	}
-	nfp_net_rx_give_one(rx_ring, new_frag, new_dma_addr);
+	nfp_net_rx_give_one(dp, rx_ring, new_frag, new_dma_addr);
 
 	wr_idx = tx_ring->wr_p & (tx_ring->cnt - 1);
 
@@ -1497,14 +1502,14 @@ nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 	txbuf->pkt_cnt = 1;
 	txbuf->real_len = pkt_len;
 
-	dma_sync_single_for_device(&nn->pdev->dev, rxbuf->dma_addr + pkt_off,
+	dma_sync_single_for_device(dp->dev, rxbuf->dma_addr + dma_off,
 				   pkt_len, DMA_BIDIRECTIONAL);
 
 	/* Build TX descriptor */
 	txd = &tx_ring->txds[wr_idx];
 	txd->offset_eop = PCIE_DESC_TX_EOP;
 	txd->dma_len = cpu_to_le16(pkt_len);
-	nfp_desc_set_dma_addr(txd, rxbuf->dma_addr + pkt_off);
+	nfp_desc_set_dma_addr(txd, rxbuf->dma_addr + dma_off);
 	txd->data_len = cpu_to_le16(pkt_len);
 
 	txd->flags = 0;
@@ -1516,14 +1521,24 @@ nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 	return true;
 }
 
-static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, unsigned int len)
+static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, void *hard_start,
+			   unsigned int *off, unsigned int *len)
 {
 	struct xdp_buff xdp;
+	void *orig_data;
+	int ret;
+
+	xdp.data_hard_start = hard_start;
+	xdp.data = data + *off;
+	xdp.data_end = data + *off + *len;
+
+	orig_data = xdp.data;
+	ret = bpf_prog_run_xdp(prog, &xdp);
 
-	xdp.data = data;
-	xdp.data_end = data + len;
+	*len -= xdp.data - orig_data;
+	*off += xdp.data - orig_data;
 
-	return bpf_prog_run_xdp(prog, &xdp);
+	return ret;
 }
 
 /**
@@ -1540,27 +1555,27 @@ static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, unsigned int len)
 static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 {
 	struct nfp_net_r_vector *r_vec = rx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
+	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
 	struct nfp_net_tx_ring *tx_ring;
 	struct bpf_prog *xdp_prog;
 	unsigned int true_bufsz;
 	struct sk_buff *skb;
 	int pkts_polled = 0;
-	int rx_dma_map_dir;
 	int idx;
 
 	rcu_read_lock();
-	xdp_prog = READ_ONCE(nn->xdp_prog);
-	rx_dma_map_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
-	true_bufsz = xdp_prog ? PAGE_SIZE : nn->fl_bufsz;
+	xdp_prog = READ_ONCE(dp->xdp_prog);
+	true_bufsz = xdp_prog ? PAGE_SIZE : dp->fl_bufsz;
 	tx_ring = r_vec->xdp_ring;
 
 	while (pkts_polled < budget) {
-		unsigned int meta_len, data_len, data_off, pkt_len, pkt_off;
+		unsigned int meta_len, data_len, data_off, pkt_len;
+		u8 meta_prepend[NFP_NET_MAX_PREPEND];
 		struct nfp_net_rx_buf *rxbuf;
 		struct nfp_net_rx_desc *rxd;
 		dma_addr_t new_dma_addr;
 		void *new_frag;
+		u8 *meta;
 
 		idx = rx_ring->rd_p & (rx_ring->cnt - 1);
 
@@ -1593,11 +1608,11 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 		data_len = le16_to_cpu(rxd->rxd.data_len);
 		pkt_len = data_len - meta_len;
 
-		if (nn->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
-			pkt_off = meta_len;
+		if (dp->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
+			data_off = NFP_NET_RX_BUF_HEADROOM + meta_len;
 		else
-			pkt_off = nn->rx_offset;
-		data_off = NFP_NET_RX_BUF_HEADROOM + pkt_off;
+			data_off = NFP_NET_RX_BUF_HEADROOM + dp->rx_offset;
+		data_off += dp->rx_dma_off;
 
 		/* Stats update */
 		u64_stats_update_begin(&r_vec->rx_sync);
@@ -1605,30 +1620,55 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 		r_vec->rx_bytes += pkt_len;
 		u64_stats_update_end(&r_vec->rx_sync);
 
+		/* Pointer to start of metadata */
+		meta = rxbuf->frag + data_off - meta_len;
+
+		if (unlikely(meta_len > NFP_NET_MAX_PREPEND ||
+			     (dp->rx_offset && meta_len > dp->rx_offset))) {
+			nn_dp_warn(dp, "oversized RX packet metadata %u\n",
+				   meta_len);
+			nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, NULL);
+			continue;
+		}
+
 		if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF &&
-				  nn->bpf_offload_xdp)) {
+				  dp->bpf_offload_xdp)) {
+			unsigned int dma_off;
+			void *hard_start;
 			int act;
 
-			dma_sync_single_for_cpu(&nn->pdev->dev,
-						rxbuf->dma_addr + pkt_off,
-						pkt_len, DMA_BIDIRECTIONAL);
-			act = nfp_net_run_xdp(xdp_prog, rxbuf->frag + data_off,
-					      pkt_len);
+			hard_start = rxbuf->frag + NFP_NET_RX_BUF_HEADROOM;
+			dma_off = data_off - NFP_NET_RX_BUF_HEADROOM;
+			dma_sync_single_for_cpu(dp->dev, rxbuf->dma_addr,
+						dma_off + pkt_len,
+						DMA_BIDIRECTIONAL);
+
+			/* Move prepend out of the way */
+			if (xdp_prog->xdp_adjust_head) {
+				memcpy(meta_prepend, meta, meta_len);
+				meta = meta_prepend;
+			}
+
+			act = nfp_net_run_xdp(xdp_prog, rxbuf->frag, hard_start,
+					      &data_off, &pkt_len);
 			switch (act) {
 			case XDP_PASS:
 				break;
 			case XDP_TX:
-				if (unlikely(!nfp_net_tx_xdp_buf(nn, rx_ring,
+				dma_off = data_off - NFP_NET_RX_BUF_HEADROOM;
+				if (unlikely(!nfp_net_tx_xdp_buf(dp, rx_ring,
 								 tx_ring, rxbuf,
-								 pkt_off, pkt_len)))
-					trace_xdp_exception(nn->netdev, xdp_prog, act);
+								 dma_off,
+								 pkt_len)))
+					trace_xdp_exception(dp->netdev,
+							    xdp_prog, act);
 				continue;
 			default:
 				bpf_warn_invalid_xdp_action(act);
 			case XDP_ABORTED:
-				trace_xdp_exception(nn->netdev, xdp_prog, act);
+				trace_xdp_exception(dp->netdev, xdp_prog, act);
 			case XDP_DROP:
-				nfp_net_rx_give_one(rx_ring, rxbuf->frag,
+				nfp_net_rx_give_one(dp, rx_ring, rxbuf->frag,
 						    rxbuf->dma_addr);
 				continue;
 			}
@@ -1636,41 +1676,40 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 
 		skb = build_skb(rxbuf->frag, true_bufsz);
 		if (unlikely(!skb)) {
-			nfp_net_rx_drop(r_vec, rx_ring, rxbuf, NULL);
+			nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, NULL);
 			continue;
 		}
-		new_frag = nfp_net_napi_alloc_one(nn, rx_dma_map_dir,
-						  &new_dma_addr);
+		new_frag = nfp_net_napi_alloc_one(dp, &new_dma_addr);
 		if (unlikely(!new_frag)) {
-			nfp_net_rx_drop(r_vec, rx_ring, rxbuf, skb);
+			nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, skb);
 			continue;
 		}
 
-		nfp_net_dma_unmap_rx(nn, rxbuf->dma_addr, nn->fl_bufsz,
-				     rx_dma_map_dir);
+		nfp_net_dma_unmap_rx(dp, rxbuf->dma_addr);
 
-		nfp_net_rx_give_one(rx_ring, new_frag, new_dma_addr);
+		nfp_net_rx_give_one(dp, rx_ring, new_frag, new_dma_addr);
 
 		skb_reserve(skb, data_off);
 		skb_put(skb, pkt_len);
 
-		if (nn->fw_ver.major <= 3) {
-			nfp_net_set_hash_desc(nn->netdev, skb, rxd);
+		if (!dp->chained_metadata_format) {
+			nfp_net_set_hash_desc(dp->netdev, skb, meta, rxd);
 		} else if (meta_len) {
 			void *end;
 
-			end = nfp_net_parse_meta(nn->netdev, skb, meta_len);
-			if (unlikely(end != skb->data)) {
-				nn_warn_ratelimit(nn, "invalid RX packet metadata\n");
-				nfp_net_rx_drop(r_vec, rx_ring, NULL, skb);
+			end = nfp_net_parse_meta(dp->netdev, skb, meta,
+						 meta_len);
+			if (unlikely(end != meta + meta_len)) {
+				nn_dp_warn(dp, "invalid RX packet metadata\n");
+				nfp_net_rx_drop(dp, r_vec, rx_ring, NULL, skb);
 				continue;
 			}
 		}
 
 		skb_record_rx_queue(skb, rx_ring->idx);
-		skb->protocol = eth_type_trans(skb, nn->netdev);
+		skb->protocol = eth_type_trans(skb, dp->netdev);
 
-		nfp_net_rx_csum(nn, r_vec, rxd, skb);
+		nfp_net_rx_csum(dp, r_vec, rxd, skb);
 
 		if (rxd->rxd.flags & PCIE_DESC_RX_VLAN)
 			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
@@ -1707,10 +1746,9 @@ static int nfp_net_poll(struct napi_struct *napi, int budget)
 			nfp_net_xdp_complete(r_vec->xdp_ring);
 	}
 
-	if (pkts_polled < budget) {
-		napi_complete_done(napi, pkts_polled);
-		nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry);
-	}
+	if (pkts_polled < budget)
+		if (napi_complete_done(napi, pkts_polled))
+			nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry);
 
 	return pkts_polled;
 }
@@ -1725,13 +1763,12 @@ static int nfp_net_poll(struct napi_struct *napi, int budget)
 static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
-	struct pci_dev *pdev = nn->pdev;
+	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
 
 	kfree(tx_ring->txbufs);
 
 	if (tx_ring->txds)
-		dma_free_coherent(&pdev->dev, tx_ring->size,
+		dma_free_coherent(dp->dev, tx_ring->size,
 				  tx_ring->txds, tx_ring->dma);
 
 	tx_ring->cnt = 0;
@@ -1743,24 +1780,23 @@ static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring)
 
 /**
  * nfp_net_tx_ring_alloc() - Allocate resource for a TX ring
+ * @dp:        NFP Net data path struct
  * @tx_ring:   TX Ring structure to allocate
- * @cnt:       Ring buffer count
  * @is_xdp:    True if ring will be used for XDP
  *
  * Return: 0 on success, negative errno otherwise.
  */
 static int
-nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp)
+nfp_net_tx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring,
+		      bool is_xdp)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
-	struct pci_dev *pdev = nn->pdev;
 	int sz;
 
-	tx_ring->cnt = cnt;
+	tx_ring->cnt = dp->txd_cnt;
 
 	tx_ring->size = sizeof(*tx_ring->txds) * tx_ring->cnt;
-	tx_ring->txds = dma_zalloc_coherent(&pdev->dev, tx_ring->size,
+	tx_ring->txds = dma_zalloc_coherent(dp->dev, tx_ring->size,
 					    &tx_ring->dma, GFP_KERNEL);
 	if (!tx_ring->txds)
 		goto err_alloc;
@@ -1771,14 +1807,9 @@ nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp)
 		goto err_alloc;
 
 	if (!is_xdp)
-		netif_set_xps_queue(nn->netdev, &r_vec->affinity_mask,
+		netif_set_xps_queue(dp->netdev, &r_vec->affinity_mask,
 				    tx_ring->idx);
 
-	nn_dbg(nn, "TxQ%02d: QCidx=%02d cnt=%d dma=%#llx host=%p %s\n",
-	       tx_ring->idx, tx_ring->qcidx,
-	       tx_ring->cnt, (unsigned long long)tx_ring->dma, tx_ring->txds,
-	       is_xdp ? "XDP" : "");
-
 	return 0;
 
 err_alloc:
@@ -1786,62 +1817,45 @@ err_alloc:
 	return -ENOMEM;
 }
 
-static struct nfp_net_tx_ring *
-nfp_net_tx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s,
-			    unsigned int num_stack_tx_rings)
+static int nfp_net_tx_rings_prepare(struct nfp_net *nn, struct nfp_net_dp *dp)
 {
-	struct nfp_net_tx_ring *rings;
 	unsigned int r;
 
-	rings = kcalloc(s->n_rings, sizeof(*rings), GFP_KERNEL);
-	if (!rings)
-		return NULL;
+	dp->tx_rings = kcalloc(dp->num_tx_rings, sizeof(*dp->tx_rings),
+			       GFP_KERNEL);
+	if (!dp->tx_rings)
+		return -ENOMEM;
 
-	for (r = 0; r < s->n_rings; r++) {
+	for (r = 0; r < dp->num_tx_rings; r++) {
 		int bias = 0;
 
-		if (r >= num_stack_tx_rings)
-			bias = num_stack_tx_rings;
+		if (r >= dp->num_stack_tx_rings)
+			bias = dp->num_stack_tx_rings;
 
-		nfp_net_tx_ring_init(&rings[r], &nn->r_vecs[r - bias], r);
+		nfp_net_tx_ring_init(&dp->tx_rings[r], &nn->r_vecs[r - bias],
+				     r);
 
-		if (nfp_net_tx_ring_alloc(&rings[r], s->dcnt, bias))
+		if (nfp_net_tx_ring_alloc(dp, &dp->tx_rings[r], bias))
 			goto err_free_prev;
 	}
 
-	return s->rings = rings;
+	return 0;
 
 err_free_prev:
 	while (r--)
-		nfp_net_tx_ring_free(&rings[r]);
-	kfree(rings);
-	return NULL;
-}
-
-static void
-nfp_net_tx_ring_set_swap(struct nfp_net *nn, struct nfp_net_ring_set *s)
-{
-	struct nfp_net_ring_set new = *s;
-
-	s->dcnt = nn->txd_cnt;
-	s->rings = nn->tx_rings;
-	s->n_rings = nn->num_tx_rings;
-
-	nn->txd_cnt = new.dcnt;
-	nn->tx_rings = new.rings;
-	nn->num_tx_rings = new.n_rings;
+		nfp_net_tx_ring_free(&dp->tx_rings[r]);
+	kfree(dp->tx_rings);
+	return -ENOMEM;
 }
 
-static void
-nfp_net_tx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s)
+static void nfp_net_tx_rings_free(struct nfp_net_dp *dp)
 {
-	struct nfp_net_tx_ring *rings = s->rings;
 	unsigned int r;
 
-	for (r = 0; r < s->n_rings; r++)
-		nfp_net_tx_ring_free(&rings[r]);
+	for (r = 0; r < dp->num_tx_rings; r++)
+		nfp_net_tx_ring_free(&dp->tx_rings[r]);
 
-	kfree(rings);
+	kfree(dp->tx_rings);
 }
 
 /**
@@ -1851,13 +1865,12 @@ nfp_net_tx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s)
 static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring)
 {
 	struct nfp_net_r_vector *r_vec = rx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
-	struct pci_dev *pdev = nn->pdev;
+	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
 
 	kfree(rx_ring->rxbufs);
 
 	if (rx_ring->rxds)
-		dma_free_coherent(&pdev->dev, rx_ring->size,
+		dma_free_coherent(dp->dev, rx_ring->size,
 				  rx_ring->rxds, rx_ring->dma);
 
 	rx_ring->cnt = 0;
@@ -1869,26 +1882,19 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring)
 
 /**
  * nfp_net_rx_ring_alloc() - Allocate resource for a RX ring
+ * @dp:	      NFP Net data path struct
  * @rx_ring:  RX ring to allocate
- * @fl_bufsz: Size of buffers to allocate
- * @cnt:      Ring buffer count
  *
  * Return: 0 on success, negative errno otherwise.
  */
 static int
-nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz,
-		      u32 cnt)
+nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring)
 {
-	struct nfp_net_r_vector *r_vec = rx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
-	struct pci_dev *pdev = nn->pdev;
 	int sz;
 
-	rx_ring->cnt = cnt;
-	rx_ring->bufsz = fl_bufsz;
-
+	rx_ring->cnt = dp->rxd_cnt;
 	rx_ring->size = sizeof(*rx_ring->rxds) * rx_ring->cnt;
-	rx_ring->rxds = dma_zalloc_coherent(&pdev->dev, rx_ring->size,
+	rx_ring->rxds = dma_zalloc_coherent(dp->dev, rx_ring->size,
 					    &rx_ring->dma, GFP_KERNEL);
 	if (!rx_ring->rxds)
 		goto err_alloc;
@@ -1898,10 +1904,6 @@ nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz,
 	if (!rx_ring->rxbufs)
 		goto err_alloc;
 
-	nn_dbg(nn, "RxQ%02d: FlQCidx=%02d RxQCidx=%02d cnt=%d dma=%#llx host=%p\n",
-	       rx_ring->idx, rx_ring->fl_qcidx, rx_ring->rx_qcidx,
-	       rx_ring->cnt, (unsigned long long)rx_ring->dma, rx_ring->rxds);
-
 	return 0;
 
 err_alloc:
@@ -1909,82 +1911,59 @@ err_alloc:
 	return -ENOMEM;
 }
 
-static struct nfp_net_rx_ring *
-nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s,
-			    bool xdp)
+static int nfp_net_rx_rings_prepare(struct nfp_net *nn, struct nfp_net_dp *dp)
 {
-	unsigned int fl_bufsz =	nfp_net_calc_fl_bufsz(nn, s->mtu);
-	struct nfp_net_rx_ring *rings;
 	unsigned int r;
 
-	rings = kcalloc(s->n_rings, sizeof(*rings), GFP_KERNEL);
-	if (!rings)
-		return NULL;
+	dp->rx_rings = kcalloc(dp->num_rx_rings, sizeof(*dp->rx_rings),
+			       GFP_KERNEL);
+	if (!dp->rx_rings)
+		return -ENOMEM;
 
-	for (r = 0; r < s->n_rings; r++) {
-		nfp_net_rx_ring_init(&rings[r], &nn->r_vecs[r], r);
+	for (r = 0; r < dp->num_rx_rings; r++) {
+		nfp_net_rx_ring_init(&dp->rx_rings[r], &nn->r_vecs[r], r);
 
-		if (nfp_net_rx_ring_alloc(&rings[r], fl_bufsz, s->dcnt))
+		if (nfp_net_rx_ring_alloc(dp, &dp->rx_rings[r]))
 			goto err_free_prev;
 
-		if (nfp_net_rx_ring_bufs_alloc(nn, &rings[r], xdp))
+		if (nfp_net_rx_ring_bufs_alloc(dp, &dp->rx_rings[r]))
 			goto err_free_ring;
 	}
 
-	return s->rings = rings;
+	return 0;
 
 err_free_prev:
 	while (r--) {
-		nfp_net_rx_ring_bufs_free(nn, &rings[r], xdp);
+		nfp_net_rx_ring_bufs_free(dp, &dp->rx_rings[r]);
 err_free_ring:
-		nfp_net_rx_ring_free(&rings[r]);
+		nfp_net_rx_ring_free(&dp->rx_rings[r]);
 	}
-	kfree(rings);
-	return NULL;
-}
-
-static void
-nfp_net_rx_ring_set_swap(struct nfp_net *nn, struct nfp_net_ring_set *s)
-{
-	struct nfp_net_ring_set new = *s;
-
-	s->mtu = nn->netdev->mtu;
-	s->dcnt = nn->rxd_cnt;
-	s->rings = nn->rx_rings;
-	s->n_rings = nn->num_rx_rings;
-
-	nn->netdev->mtu = new.mtu;
-	nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, new.mtu);
-	nn->rxd_cnt = new.dcnt;
-	nn->rx_rings = new.rings;
-	nn->num_rx_rings = new.n_rings;
+	kfree(dp->rx_rings);
+	return -ENOMEM;
 }
 
-static void
-nfp_net_rx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s,
-			 bool xdp)
+static void nfp_net_rx_rings_free(struct nfp_net_dp *dp)
 {
-	struct nfp_net_rx_ring *rings = s->rings;
 	unsigned int r;
 
-	for (r = 0; r < s->n_rings; r++) {
-		nfp_net_rx_ring_bufs_free(nn, &rings[r], xdp);
-		nfp_net_rx_ring_free(&rings[r]);
+	for (r = 0; r < dp->num_rx_rings; r++) {
+		nfp_net_rx_ring_bufs_free(dp, &dp->rx_rings[r]);
+		nfp_net_rx_ring_free(&dp->rx_rings[r]);
 	}
 
-	kfree(rings);
+	kfree(dp->rx_rings);
 }
 
 static void
-nfp_net_vector_assign_rings(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
-			    int idx)
+nfp_net_vector_assign_rings(struct nfp_net_dp *dp,
+			    struct nfp_net_r_vector *r_vec, int idx)
 {
-	r_vec->rx_ring = idx < nn->num_rx_rings ? &nn->rx_rings[idx] : NULL;
+	r_vec->rx_ring = idx < dp->num_rx_rings ? &dp->rx_rings[idx] : NULL;
 	r_vec->tx_ring =
-		idx < nn->num_stack_tx_rings ? &nn->tx_rings[idx] : NULL;
+		idx < dp->num_stack_tx_rings ? &dp->tx_rings[idx] : NULL;
 
-	r_vec->xdp_ring = idx < nn->num_tx_rings - nn->num_stack_tx_rings ?
-		&nn->tx_rings[nn->num_stack_tx_rings + idx] : NULL;
+	r_vec->xdp_ring = idx < dp->num_tx_rings - dp->num_stack_tx_rings ?
+		&dp->tx_rings[dp->num_stack_tx_rings + idx] : NULL;
 }
 
 static int
@@ -1994,11 +1973,11 @@ nfp_net_prepare_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 	int err;
 
 	/* Setup NAPI */
-	netif_napi_add(nn->netdev, &r_vec->napi,
+	netif_napi_add(nn->dp.netdev, &r_vec->napi,
 		       nfp_net_poll, NAPI_POLL_WEIGHT);
 
 	snprintf(r_vec->name, sizeof(r_vec->name),
-		 "%s-rxtx-%d", nn->netdev->name, idx);
+		 "%s-rxtx-%d", nn->dp.netdev->name, idx);
 	err = request_irq(r_vec->irq_vector, r_vec->handler, 0, r_vec->name,
 			  r_vec);
 	if (err) {
@@ -2045,7 +2024,7 @@ void nfp_net_rss_write_key(struct nfp_net *nn)
 {
 	int i;
 
-	for (i = 0; i < NFP_NET_CFG_RSS_KEY_SZ; i += 4)
+	for (i = 0; i < nfp_net_rss_key_sz(nn); i += 4)
 		nn_writel(nn, NFP_NET_CFG_RSS_KEY + i,
 			  get_unaligned_le32(nn->rss_key + i));
 }
@@ -2069,13 +2048,13 @@ void nfp_net_coalesce_write_cfg(struct nfp_net *nn)
 	/* copy RX interrupt coalesce parameters */
 	value = (nn->rx_coalesce_max_frames << 16) |
 		(factor * nn->rx_coalesce_usecs);
-	for (i = 0; i < nn->num_rx_rings; i++)
+	for (i = 0; i < nn->dp.num_rx_rings; i++)
 		nn_writel(nn, NFP_NET_CFG_RXR_IRQ_MOD(i), value);
 
 	/* copy TX interrupt coalesce parameters */
 	value = (nn->tx_coalesce_max_frames << 16) |
 		(factor * nn->tx_coalesce_usecs);
-	for (i = 0; i < nn->num_tx_rings; i++)
+	for (i = 0; i < nn->dp.num_tx_rings; i++)
 		nn_writel(nn, NFP_NET_CFG_TXR_IRQ_MOD(i), value);
 }
 
@@ -2090,9 +2069,9 @@ void nfp_net_coalesce_write_cfg(struct nfp_net *nn)
 static void nfp_net_write_mac_addr(struct nfp_net *nn)
 {
 	nn_writel(nn, NFP_NET_CFG_MACADDR + 0,
-		  get_unaligned_be32(nn->netdev->dev_addr));
+		  get_unaligned_be32(nn->dp.netdev->dev_addr));
 	nn_writew(nn, NFP_NET_CFG_MACADDR + 6,
-		  get_unaligned_be16(nn->netdev->dev_addr + 4));
+		  get_unaligned_be16(nn->dp.netdev->dev_addr + 4));
 }
 
 static void nfp_net_vec_clear_ring_data(struct nfp_net *nn, unsigned int idx)
@@ -2116,7 +2095,7 @@ static void nfp_net_clear_config_and_disable(struct nfp_net *nn)
 	unsigned int r;
 	int err;
 
-	new_ctrl = nn->ctrl;
+	new_ctrl = nn->dp.ctrl;
 	new_ctrl &= ~NFP_NET_CFG_CTRL_ENABLE;
 	update = NFP_NET_CFG_UPDATE_GEN;
 	update |= NFP_NET_CFG_UPDATE_MSIX;
@@ -2133,14 +2112,14 @@ static void nfp_net_clear_config_and_disable(struct nfp_net *nn)
 	if (err)
 		nn_err(nn, "Could not disable device: %d\n", err);
 
-	for (r = 0; r < nn->num_rx_rings; r++)
-		nfp_net_rx_ring_reset(&nn->rx_rings[r]);
-	for (r = 0; r < nn->num_tx_rings; r++)
-		nfp_net_tx_ring_reset(nn, &nn->tx_rings[r]);
-	for (r = 0; r < nn->num_r_vecs; r++)
+	for (r = 0; r < nn->dp.num_rx_rings; r++)
+		nfp_net_rx_ring_reset(&nn->dp.rx_rings[r]);
+	for (r = 0; r < nn->dp.num_tx_rings; r++)
+		nfp_net_tx_ring_reset(&nn->dp, &nn->dp.tx_rings[r]);
+	for (r = 0; r < nn->dp.num_r_vecs; r++)
 		nfp_net_vec_clear_ring_data(nn, r);
 
-	nn->ctrl = new_ctrl;
+	nn->dp.ctrl = new_ctrl;
 }
 
 static void
@@ -2162,13 +2141,17 @@ nfp_net_tx_ring_hw_cfg_write(struct nfp_net *nn,
 	nn_writeb(nn, NFP_NET_CFG_TXR_VEC(idx), tx_ring->r_vec->irq_entry);
 }
 
-static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
+/**
+ * nfp_net_set_config_and_enable() - Write control BAR and enable NFP
+ * @nn:      NFP Net device to reconfigure
+ */
+static int nfp_net_set_config_and_enable(struct nfp_net *nn)
 {
 	u32 new_ctrl, update = 0;
 	unsigned int r;
 	int err;
 
-	new_ctrl = nn->ctrl;
+	new_ctrl = nn->dp.ctrl;
 
 	if (nn->cap & NFP_NET_CFG_CTRL_RSS) {
 		nfp_net_rss_write_key(nn);
@@ -2184,22 +2167,22 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
 		update |= NFP_NET_CFG_UPDATE_IRQMOD;
 	}
 
-	for (r = 0; r < nn->num_tx_rings; r++)
-		nfp_net_tx_ring_hw_cfg_write(nn, &nn->tx_rings[r], r);
-	for (r = 0; r < nn->num_rx_rings; r++)
-		nfp_net_rx_ring_hw_cfg_write(nn, &nn->rx_rings[r], r);
+	for (r = 0; r < nn->dp.num_tx_rings; r++)
+		nfp_net_tx_ring_hw_cfg_write(nn, &nn->dp.tx_rings[r], r);
+	for (r = 0; r < nn->dp.num_rx_rings; r++)
+		nfp_net_rx_ring_hw_cfg_write(nn, &nn->dp.rx_rings[r], r);
 
-	nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, nn->num_tx_rings == 64 ?
-		  0xffffffffffffffffULL : ((u64)1 << nn->num_tx_rings) - 1);
+	nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, nn->dp.num_tx_rings == 64 ?
+		  0xffffffffffffffffULL : ((u64)1 << nn->dp.num_tx_rings) - 1);
 
-	nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, nn->num_rx_rings == 64 ?
-		  0xffffffffffffffffULL : ((u64)1 << nn->num_rx_rings) - 1);
+	nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, nn->dp.num_rx_rings == 64 ?
+		  0xffffffffffffffffULL : ((u64)1 << nn->dp.num_rx_rings) - 1);
 
 	nfp_net_write_mac_addr(nn);
 
-	nn_writel(nn, NFP_NET_CFG_MTU, nn->netdev->mtu);
+	nn_writel(nn, NFP_NET_CFG_MTU, nn->dp.netdev->mtu);
 	nn_writel(nn, NFP_NET_CFG_FLBUFSZ,
-		  nn->fl_bufsz - NFP_NET_RX_BUF_NON_DATA);
+		  nn->dp.fl_bufsz - NFP_NET_RX_BUF_NON_DATA);
 
 	/* Enable device */
 	new_ctrl |= NFP_NET_CFG_CTRL_ENABLE;
@@ -2211,37 +2194,26 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
 
 	nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl);
 	err = nfp_net_reconfig(nn, update);
+	if (err) {
+		nfp_net_clear_config_and_disable(nn);
+		return err;
+	}
 
-	nn->ctrl = new_ctrl;
+	nn->dp.ctrl = new_ctrl;
 
-	for (r = 0; r < nn->num_rx_rings; r++)
-		nfp_net_rx_ring_fill_freelist(&nn->rx_rings[r]);
+	for (r = 0; r < nn->dp.num_rx_rings; r++)
+		nfp_net_rx_ring_fill_freelist(&nn->dp, &nn->dp.rx_rings[r]);
 
 	/* Since reconfiguration requests while NFP is down are ignored we
 	 * have to wipe the entire VXLAN configuration and reinitialize it.
 	 */
-	if (nn->ctrl & NFP_NET_CFG_CTRL_VXLAN) {
+	if (nn->dp.ctrl & NFP_NET_CFG_CTRL_VXLAN) {
 		memset(&nn->vxlan_ports, 0, sizeof(nn->vxlan_ports));
 		memset(&nn->vxlan_usecnt, 0, sizeof(nn->vxlan_usecnt));
-		udp_tunnel_get_rx_info(nn->netdev);
+		udp_tunnel_get_rx_info(nn->dp.netdev);
 	}
 
-	return err;
-}
-
-/**
- * nfp_net_set_config_and_enable() - Write control BAR and enable NFP
- * @nn:      NFP Net device to reconfigure
- */
-static int nfp_net_set_config_and_enable(struct nfp_net *nn)
-{
-	int err;
-
-	err = __nfp_net_set_config_and_enable(nn);
-	if (err)
-		nfp_net_clear_config_and_disable(nn);
-
-	return err;
+	return 0;
 }
 
 /**
@@ -2252,12 +2224,12 @@ static void nfp_net_open_stack(struct nfp_net *nn)
 {
 	unsigned int r;
 
-	for (r = 0; r < nn->num_r_vecs; r++) {
+	for (r = 0; r < nn->dp.num_r_vecs; r++) {
 		napi_enable(&nn->r_vecs[r].napi);
 		enable_irq(nn->r_vecs[r].irq_vector);
 	}
 
-	netif_tx_wake_all_queues(nn->netdev);
+	netif_tx_wake_all_queues(nn->dp.netdev);
 
 	enable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
 	nfp_net_read_link_status(nn);
@@ -2266,22 +2238,8 @@ static void nfp_net_open_stack(struct nfp_net *nn)
 static int nfp_net_netdev_open(struct net_device *netdev)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
-	struct nfp_net_ring_set rx = {
-		.n_rings = nn->num_rx_rings,
-		.mtu = nn->netdev->mtu,
-		.dcnt = nn->rxd_cnt,
-	};
-	struct nfp_net_ring_set tx = {
-		.n_rings = nn->num_tx_rings,
-		.dcnt = nn->txd_cnt,
-	};
 	int err, r;
 
-	if (nn->ctrl & NFP_NET_CFG_CTRL_ENABLE) {
-		nn_err(nn, "Dev is already enabled: 0x%08x\n", nn->ctrl);
-		return -EBUSY;
-	}
-
 	/* Step 1: Allocate resources for rings and the like
 	 * - Request interrupts
 	 * - Allocate RX and TX ring resources
@@ -2299,33 +2257,28 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 		goto err_free_exn;
 	disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
 
-	for (r = 0; r < nn->num_r_vecs; r++) {
+	for (r = 0; r < nn->dp.num_r_vecs; r++) {
 		err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r);
 		if (err)
 			goto err_cleanup_vec_p;
 	}
 
-	nn->rx_rings = nfp_net_rx_ring_set_prepare(nn, &rx, nn->xdp_prog);
-	if (!nn->rx_rings) {
-		err = -ENOMEM;
+	err = nfp_net_rx_rings_prepare(nn, &nn->dp);
+	if (err)
 		goto err_cleanup_vec;
-	}
 
-	nn->tx_rings = nfp_net_tx_ring_set_prepare(nn, &tx,
-						   nn->num_stack_tx_rings);
-	if (!nn->tx_rings) {
-		err = -ENOMEM;
+	err = nfp_net_tx_rings_prepare(nn, &nn->dp);
+	if (err)
 		goto err_free_rx_rings;
-	}
 
 	for (r = 0; r < nn->max_r_vecs; r++)
-		nfp_net_vector_assign_rings(nn, &nn->r_vecs[r], r);
+		nfp_net_vector_assign_rings(&nn->dp, &nn->r_vecs[r], r);
 
-	err = netif_set_real_num_tx_queues(netdev, nn->num_stack_tx_rings);
+	err = netif_set_real_num_tx_queues(netdev, nn->dp.num_stack_tx_rings);
 	if (err)
 		goto err_free_rings;
 
-	err = netif_set_real_num_rx_queues(netdev, nn->num_rx_rings);
+	err = netif_set_real_num_rx_queues(netdev, nn->dp.num_rx_rings);
 	if (err)
 		goto err_free_rings;
 
@@ -2351,11 +2304,11 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 	return 0;
 
 err_free_rings:
-	nfp_net_tx_ring_set_free(nn, &tx);
+	nfp_net_tx_rings_free(&nn->dp);
 err_free_rx_rings:
-	nfp_net_rx_ring_set_free(nn, &rx, nn->xdp_prog);
+	nfp_net_rx_rings_free(&nn->dp);
 err_cleanup_vec:
-	r = nn->num_r_vecs;
+	r = nn->dp.num_r_vecs;
 err_cleanup_vec_p:
 	while (r--)
 		nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
@@ -2374,15 +2327,15 @@ static void nfp_net_close_stack(struct nfp_net *nn)
 	unsigned int r;
 
 	disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
-	netif_carrier_off(nn->netdev);
+	netif_carrier_off(nn->dp.netdev);
 	nn->link_up = false;
 
-	for (r = 0; r < nn->num_r_vecs; r++) {
+	for (r = 0; r < nn->dp.num_r_vecs; r++) {
 		disable_irq(nn->r_vecs[r].irq_vector);
 		napi_disable(&nn->r_vecs[r].napi);
 	}
 
-	netif_tx_disable(nn->netdev);
+	netif_tx_disable(nn->dp.netdev);
 }
 
 /**
@@ -2393,17 +2346,17 @@ static void nfp_net_close_free_all(struct nfp_net *nn)
 {
 	unsigned int r;
 
-	for (r = 0; r < nn->num_rx_rings; r++) {
-		nfp_net_rx_ring_bufs_free(nn, &nn->rx_rings[r], nn->xdp_prog);
-		nfp_net_rx_ring_free(&nn->rx_rings[r]);
+	for (r = 0; r < nn->dp.num_rx_rings; r++) {
+		nfp_net_rx_ring_bufs_free(&nn->dp, &nn->dp.rx_rings[r]);
+		nfp_net_rx_ring_free(&nn->dp.rx_rings[r]);
 	}
-	for (r = 0; r < nn->num_tx_rings; r++)
-		nfp_net_tx_ring_free(&nn->tx_rings[r]);
-	for (r = 0; r < nn->num_r_vecs; r++)
+	for (r = 0; r < nn->dp.num_tx_rings; r++)
+		nfp_net_tx_ring_free(&nn->dp.tx_rings[r]);
+	for (r = 0; r < nn->dp.num_r_vecs; r++)
 		nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
 
-	kfree(nn->rx_rings);
-	kfree(nn->tx_rings);
+	kfree(nn->dp.rx_rings);
+	kfree(nn->dp.tx_rings);
 
 	nfp_net_aux_irq_free(nn, NFP_NET_CFG_LSC, NFP_NET_IRQ_LSC_IDX);
 	nfp_net_aux_irq_free(nn, NFP_NET_CFG_EXN, NFP_NET_IRQ_EXN_IDX);
@@ -2417,11 +2370,6 @@ static int nfp_net_netdev_close(struct net_device *netdev)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 
-	if (!(nn->ctrl & NFP_NET_CFG_CTRL_ENABLE)) {
-		nn_err(nn, "Dev is not up: 0x%08x\n", nn->ctrl);
-		return 0;
-	}
-
 	/* Step 1: Disable RX and TX rings from the Linux kernel perspective
 	 */
 	nfp_net_close_stack(nn);
@@ -2443,7 +2391,7 @@ static void nfp_net_set_rx_mode(struct net_device *netdev)
 	struct nfp_net *nn = netdev_priv(netdev);
 	u32 new_ctrl;
 
-	new_ctrl = nn->ctrl;
+	new_ctrl = nn->dp.ctrl;
 
 	if (netdev->flags & IFF_PROMISC) {
 		if (nn->cap & NFP_NET_CFG_CTRL_PROMISC)
@@ -2454,13 +2402,13 @@ static void nfp_net_set_rx_mode(struct net_device *netdev)
 		new_ctrl &= ~NFP_NET_CFG_CTRL_PROMISC;
 	}
 
-	if (new_ctrl == nn->ctrl)
+	if (new_ctrl == nn->dp.ctrl)
 		return;
 
 	nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl);
 	nfp_net_reconfig_post(nn, NFP_NET_CFG_UPDATE_GEN);
 
-	nn->ctrl = new_ctrl;
+	nn->dp.ctrl = new_ctrl;
 }
 
 static void nfp_net_rss_init_itbl(struct nfp_net *nn)
@@ -2469,61 +2417,76 @@ static void nfp_net_rss_init_itbl(struct nfp_net *nn)
 
 	for (i = 0; i < sizeof(nn->rss_itbl); i++)
 		nn->rss_itbl[i] =
-			ethtool_rxfh_indir_default(i, nn->num_rx_rings);
+			ethtool_rxfh_indir_default(i, nn->dp.num_rx_rings);
 }
 
-static int
-nfp_net_ring_swap_enable(struct nfp_net *nn, unsigned int *num_vecs,
-			 unsigned int *stack_tx_rings,
-			 struct bpf_prog **xdp_prog,
-			 struct nfp_net_ring_set *rx,
-			 struct nfp_net_ring_set *tx)
+static void nfp_net_dp_swap(struct nfp_net *nn, struct nfp_net_dp *dp)
+{
+	struct nfp_net_dp new_dp = *dp;
+
+	*dp = nn->dp;
+	nn->dp = new_dp;
+
+	nn->dp.netdev->mtu = new_dp.mtu;
+
+	if (!netif_is_rxfh_configured(nn->dp.netdev))
+		nfp_net_rss_init_itbl(nn);
+}
+
+static int nfp_net_dp_swap_enable(struct nfp_net *nn, struct nfp_net_dp *dp)
 {
 	unsigned int r;
 	int err;
 
-	if (rx)
-		nfp_net_rx_ring_set_swap(nn, rx);
-	if (tx)
-		nfp_net_tx_ring_set_swap(nn, tx);
-
-	swap(*num_vecs, nn->num_r_vecs);
-	swap(*stack_tx_rings, nn->num_stack_tx_rings);
-	*xdp_prog = xchg(&nn->xdp_prog, *xdp_prog);
+	nfp_net_dp_swap(nn, dp);
 
 	for (r = 0; r <	nn->max_r_vecs; r++)
-		nfp_net_vector_assign_rings(nn, &nn->r_vecs[r], r);
-
-	if (!netif_is_rxfh_configured(nn->netdev))
-		nfp_net_rss_init_itbl(nn);
+		nfp_net_vector_assign_rings(&nn->dp, &nn->r_vecs[r], r);
 
-	err = netif_set_real_num_rx_queues(nn->netdev,
-					   nn->num_rx_rings);
+	err = netif_set_real_num_rx_queues(nn->dp.netdev, nn->dp.num_rx_rings);
 	if (err)
 		return err;
 
-	if (nn->netdev->real_num_tx_queues != nn->num_stack_tx_rings) {
-		err = netif_set_real_num_tx_queues(nn->netdev,
-						   nn->num_stack_tx_rings);
+	if (nn->dp.netdev->real_num_tx_queues != nn->dp.num_stack_tx_rings) {
+		err = netif_set_real_num_tx_queues(nn->dp.netdev,
+						   nn->dp.num_stack_tx_rings);
 		if (err)
 			return err;
 	}
 
-	return __nfp_net_set_config_and_enable(nn);
+	return nfp_net_set_config_and_enable(nn);
 }
 
-static int
-nfp_net_check_config(struct nfp_net *nn, struct bpf_prog *xdp_prog,
-		     struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx)
+struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn)
+{
+	struct nfp_net_dp *new;
+
+	new = kmalloc(sizeof(*new), GFP_KERNEL);
+	if (!new)
+		return NULL;
+
+	*new = nn->dp;
+
+	/* Clear things which need to be recomputed */
+	new->fl_bufsz = 0;
+	new->tx_rings = NULL;
+	new->rx_rings = NULL;
+	new->num_r_vecs = 0;
+	new->num_stack_tx_rings = 0;
+
+	return new;
+}
+
+static int nfp_net_check_config(struct nfp_net *nn, struct nfp_net_dp *dp)
 {
 	/* XDP-enabled tests */
-	if (!xdp_prog)
+	if (!dp->xdp_prog)
 		return 0;
-	if (rx && nfp_net_calc_fl_bufsz(nn, rx->mtu) > PAGE_SIZE) {
+	if (dp->fl_bufsz > PAGE_SIZE) {
 		nn_warn(nn, "MTU too large w/ XDP enabled\n");
 		return -EINVAL;
 	}
-	if (tx && tx->n_rings > nn->max_tx_rings) {
+	if (dp->num_tx_rings > nn->max_tx_rings) {
 		nn_warn(nn, "Insufficient number of TX rings w/ XDP enabled\n");
 		return -EINVAL;
 	}
@@ -2531,119 +2494,94 @@ nfp_net_check_config(struct nfp_net *nn, struct bpf_prog *xdp_prog,
 	return 0;
 }
 
-static void
-nfp_net_ring_reconfig_down(struct nfp_net *nn, struct bpf_prog **xdp_prog,
-			   struct nfp_net_ring_set *rx,
-			   struct nfp_net_ring_set *tx,
-			   unsigned int stack_tx_rings, unsigned int num_vecs)
-{
-	nn->netdev->mtu = rx ? rx->mtu : nn->netdev->mtu;
-	nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, nn->netdev->mtu);
-	nn->rxd_cnt = rx ? rx->dcnt : nn->rxd_cnt;
-	nn->txd_cnt = tx ? tx->dcnt : nn->txd_cnt;
-	nn->num_rx_rings = rx ? rx->n_rings : nn->num_rx_rings;
-	nn->num_tx_rings = tx ? tx->n_rings : nn->num_tx_rings;
-	nn->num_stack_tx_rings = stack_tx_rings;
-	nn->num_r_vecs = num_vecs;
-	*xdp_prog = xchg(&nn->xdp_prog, *xdp_prog);
-
-	if (!netif_is_rxfh_configured(nn->netdev))
-		nfp_net_rss_init_itbl(nn);
-}
-
-int
-nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog,
-		      struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx)
+int nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp)
 {
-	unsigned int stack_tx_rings, num_vecs, r;
-	int err;
+	int r, err;
 
-	stack_tx_rings = tx ? tx->n_rings : nn->num_tx_rings;
-	if (*xdp_prog)
-		stack_tx_rings -= rx ? rx->n_rings : nn->num_rx_rings;
+	dp->fl_bufsz = nfp_net_calc_fl_bufsz(dp);
 
-	num_vecs = max(rx ? rx->n_rings : nn->num_rx_rings, stack_tx_rings);
+	dp->num_stack_tx_rings = dp->num_tx_rings;
+	if (dp->xdp_prog)
+		dp->num_stack_tx_rings -= dp->num_rx_rings;
 
-	err = nfp_net_check_config(nn, *xdp_prog, rx, tx);
+	dp->num_r_vecs = max(dp->num_rx_rings, dp->num_stack_tx_rings);
+
+	err = nfp_net_check_config(nn, dp);
 	if (err)
-		return err;
+		goto exit_free_dp;
 
-	if (!netif_running(nn->netdev)) {
-		nfp_net_ring_reconfig_down(nn, xdp_prog, rx, tx,
-					   stack_tx_rings, num_vecs);
-		return 0;
+	if (!netif_running(dp->netdev)) {
+		nfp_net_dp_swap(nn, dp);
+		err = 0;
+		goto exit_free_dp;
 	}
 
 	/* Prepare new rings */
-	for (r = nn->num_r_vecs; r < num_vecs; r++) {
+	for (r = nn->dp.num_r_vecs; r < dp->num_r_vecs; r++) {
 		err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r);
 		if (err) {
-			num_vecs = r;
+			dp->num_r_vecs = r;
 			goto err_cleanup_vecs;
 		}
 	}
-	if (rx) {
-		if (!nfp_net_rx_ring_set_prepare(nn, rx, *xdp_prog)) {
-			err = -ENOMEM;
-			goto err_cleanup_vecs;
-		}
-	}
-	if (tx) {
-		if (!nfp_net_tx_ring_set_prepare(nn, tx, stack_tx_rings)) {
-			err = -ENOMEM;
-			goto err_free_rx;
-		}
-	}
+
+	err = nfp_net_rx_rings_prepare(nn, dp);
+	if (err)
+		goto err_cleanup_vecs;
+
+	err = nfp_net_tx_rings_prepare(nn, dp);
+	if (err)
+		goto err_free_rx;
 
 	/* Stop device, swap in new rings, try to start the firmware */
 	nfp_net_close_stack(nn);
 	nfp_net_clear_config_and_disable(nn);
 
-	err = nfp_net_ring_swap_enable(nn, &num_vecs, &stack_tx_rings,
-				       xdp_prog, rx, tx);
+	err = nfp_net_dp_swap_enable(nn, dp);
 	if (err) {
 		int err2;
 
 		nfp_net_clear_config_and_disable(nn);
 
 		/* Try with old configuration and old rings */
-		err2 = nfp_net_ring_swap_enable(nn, &num_vecs, &stack_tx_rings,
-						xdp_prog, rx, tx);
+		err2 = nfp_net_dp_swap_enable(nn, dp);
 		if (err2)
 			nn_err(nn, "Can't restore ring config - FW communication failed (%d,%d)\n",
 			       err, err2);
 	}
-	for (r = num_vecs - 1; r >= nn->num_r_vecs; r--)
+	for (r = dp->num_r_vecs - 1; r >= nn->dp.num_r_vecs; r--)
 		nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
 
-	if (rx)
-		nfp_net_rx_ring_set_free(nn, rx, *xdp_prog);
-	if (tx)
-		nfp_net_tx_ring_set_free(nn, tx);
+	nfp_net_rx_rings_free(dp);
+	nfp_net_tx_rings_free(dp);
 
 	nfp_net_open_stack(nn);
+exit_free_dp:
+	kfree(dp);
 
 	return err;
 
 err_free_rx:
-	if (rx)
-		nfp_net_rx_ring_set_free(nn, rx, *xdp_prog);
+	nfp_net_rx_rings_free(dp);
 err_cleanup_vecs:
-	for (r = num_vecs - 1; r >= nn->num_r_vecs; r--)
+	for (r = dp->num_r_vecs - 1; r >= nn->dp.num_r_vecs; r--)
 		nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
+	kfree(dp);
 	return err;
 }
 
 static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
-	struct nfp_net_ring_set rx = {
-		.n_rings = nn->num_rx_rings,
-		.mtu = new_mtu,
-		.dcnt = nn->rxd_cnt,
-	};
+	struct nfp_net_dp *dp;
+
+	dp = nfp_net_clone_dp(nn);
+	if (!dp)
+		return -ENOMEM;
 
-	return nfp_net_ring_reconfig(nn, &nn->xdp_prog, &rx, NULL);
+	dp->mtu = new_mtu;
+
+	return nfp_net_ring_reconfig(nn, dp);
 }
 
 static void nfp_net_stat64(struct net_device *netdev,
@@ -2652,7 +2590,7 @@ static void nfp_net_stat64(struct net_device *netdev,
 	struct nfp_net *nn = netdev_priv(netdev);
 	int r;
 
-	for (r = 0; r < nn->num_r_vecs; r++) {
+	for (r = 0; r < nn->dp.num_r_vecs; r++) {
 		struct nfp_net_r_vector *r_vec = &nn->r_vecs[r];
 		u64 data[3];
 		unsigned int start;
@@ -2699,7 +2637,7 @@ nfp_net_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
 		return -ENOTSUPP;
 
 	if (tc->type == TC_SETUP_CLSBPF && nfp_net_ebpf_capable(nn)) {
-		if (!nn->bpf_offload_xdp)
+		if (!nn->dp.bpf_offload_xdp)
 			return nfp_net_bpf_offload(nn, tc->cls_bpf);
 		else
 			return -EBUSY;
@@ -2718,7 +2656,7 @@ static int nfp_net_set_features(struct net_device *netdev,
 
 	/* Assume this is not called with features we have not advertised */
 
-	new_ctrl = nn->ctrl;
+	new_ctrl = nn->dp.ctrl;
 
 	if (changed & NETIF_F_RXCSUM) {
 		if (features & NETIF_F_RXCSUM)
@@ -2762,7 +2700,7 @@ static int nfp_net_set_features(struct net_device *netdev,
 			new_ctrl &= ~NFP_NET_CFG_CTRL_GATHER;
 	}
 
-	if (changed & NETIF_F_HW_TC && nn->ctrl & NFP_NET_CFG_CTRL_BPF) {
+	if (changed & NETIF_F_HW_TC && nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) {
 		nn_err(nn, "Cannot disable HW TC offload while in use\n");
 		return -EBUSY;
 	}
@@ -2770,16 +2708,16 @@ static int nfp_net_set_features(struct net_device *netdev,
 	nn_dbg(nn, "Feature change 0x%llx -> 0x%llx (changed=0x%llx)\n",
 	       netdev->features, features, changed);
 
-	if (new_ctrl == nn->ctrl)
+	if (new_ctrl == nn->dp.ctrl)
 		return 0;
 
-	nn_dbg(nn, "NIC ctrl: 0x%x -> 0x%x\n", nn->ctrl, new_ctrl);
+	nn_dbg(nn, "NIC ctrl: 0x%x -> 0x%x\n", nn->dp.ctrl, new_ctrl);
 	nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl);
 	err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN);
 	if (err)
 		return err;
 
-	nn->ctrl = new_ctrl;
+	nn->dp.ctrl = new_ctrl;
 
 	return 0;
 }
@@ -2830,6 +2768,26 @@ nfp_net_features_check(struct sk_buff *skb, struct net_device *dev,
 	return features;
 }
 
+static int
+nfp_net_get_phys_port_name(struct net_device *netdev, char *name, size_t len)
+{
+	struct nfp_net *nn = netdev_priv(netdev);
+	int err;
+
+	if (!nn->eth_port)
+		return -EOPNOTSUPP;
+
+	if (!nn->eth_port->is_split)
+		err = snprintf(name, len, "p%d", nn->eth_port->label_port);
+	else
+		err = snprintf(name, len, "p%ds%d", nn->eth_port->label_port,
+			       nn->eth_port->label_subport);
+	if (err >= len)
+		return -EINVAL;
+
+	return 0;
+}
+
 /**
  * nfp_net_set_vxlan_port() - set vxlan port in SW and reconfigure HW
  * @nn:   NFP Net device to reconfigure
@@ -2842,7 +2800,7 @@ static void nfp_net_set_vxlan_port(struct nfp_net *nn, int idx, __be16 port)
 
 	nn->vxlan_ports[idx] = port;
 
-	if (!(nn->ctrl & NFP_NET_CFG_CTRL_VXLAN))
+	if (!(nn->dp.ctrl & NFP_NET_CFG_CTRL_VXLAN))
 		return;
 
 	BUILD_BUG_ON(NFP_NET_N_VXLAN_PORTS & 1);
@@ -2921,8 +2879,8 @@ static int nfp_net_xdp_offload(struct nfp_net *nn, struct bpf_prog *prog)
 	if (!nfp_net_ebpf_capable(nn))
 		return -EINVAL;
 
-	if (nn->ctrl & NFP_NET_CFG_CTRL_BPF) {
-		if (!nn->bpf_offload_xdp)
+	if (nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) {
+		if (!nn->dp.bpf_offload_xdp)
 			return prog ? -EBUSY : 0;
 		cmd.command = prog ? TC_CLSBPF_REPLACE : TC_CLSBPF_DESTROY;
 	} else {
@@ -2935,48 +2893,47 @@ static int nfp_net_xdp_offload(struct nfp_net *nn, struct bpf_prog *prog)
 	/* Stop offload if replace not possible */
 	if (ret && cmd.command == TC_CLSBPF_REPLACE)
 		nfp_net_xdp_offload(nn, NULL);
-	nn->bpf_offload_xdp = prog && !ret;
+	nn->dp.bpf_offload_xdp = prog && !ret;
 	return ret;
 }
 
 static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog)
 {
-	struct nfp_net_ring_set rx = {
-		.n_rings = nn->num_rx_rings,
-		.mtu = nn->netdev->mtu,
-		.dcnt = nn->rxd_cnt,
-	};
-	struct nfp_net_ring_set tx = {
-		.n_rings = nn->num_tx_rings,
-		.dcnt = nn->txd_cnt,
-	};
+	struct bpf_prog *old_prog = nn->dp.xdp_prog;
+	struct nfp_net_dp *dp;
 	int err;
 
-	if (prog && prog->xdp_adjust_head) {
-		nn_err(nn, "Does not support bpf_xdp_adjust_head()\n");
-		return -EOPNOTSUPP;
-	}
-	if (!prog && !nn->xdp_prog)
+	if (!prog && !nn->dp.xdp_prog)
 		return 0;
-	if (prog && nn->xdp_prog) {
-		prog = xchg(&nn->xdp_prog, prog);
+	if (prog && nn->dp.xdp_prog) {
+		prog = xchg(&nn->dp.xdp_prog, prog);
 		bpf_prog_put(prog);
-		nfp_net_xdp_offload(nn, nn->xdp_prog);
+		nfp_net_xdp_offload(nn, nn->dp.xdp_prog);
 		return 0;
 	}
 
-	tx.n_rings += prog ? nn->num_rx_rings : -nn->num_rx_rings;
+	dp = nfp_net_clone_dp(nn);
+	if (!dp)
+		return -ENOMEM;
+
+	dp->xdp_prog = prog;
+	dp->num_tx_rings += prog ? nn->dp.num_rx_rings : -nn->dp.num_rx_rings;
+	dp->rx_dma_dir = prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
+	if (prog)
+		dp->rx_dma_off = XDP_PACKET_HEADROOM -
+			(nn->dp.rx_offset ?: NFP_NET_MAX_PREPEND);
+	else
+		dp->rx_dma_off = 0;
 
 	/* We need RX reconfig to remap the buffers (BIDIR vs FROM_DEV) */
-	err = nfp_net_ring_reconfig(nn, &prog, &rx, &tx);
+	err = nfp_net_ring_reconfig(nn, dp);
 	if (err)
 		return err;
 
-	/* @prog got swapped and is now the old one */
-	if (prog)
-		bpf_prog_put(prog);
+	if (old_prog)
+		bpf_prog_put(old_prog);
 
-	nfp_net_xdp_offload(nn, nn->xdp_prog);
+	nfp_net_xdp_offload(nn, nn->dp.xdp_prog);
 
 	return 0;
 }
@@ -2989,7 +2946,7 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_xdp *xdp)
 	case XDP_SETUP_PROG:
 		return nfp_net_xdp_setup(nn, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!nn->xdp_prog;
+		xdp->prog_attached = !!nn->dp.xdp_prog;
 		return 0;
 	default:
 		return -EINVAL;
@@ -3008,6 +2965,7 @@ static const struct net_device_ops nfp_net_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_set_features	= nfp_net_set_features,
 	.ndo_features_check	= nfp_net_features_check,
+	.ndo_get_phys_port_name	= nfp_net_get_phys_port_name,
 	.ndo_udp_tunnel_add	= nfp_net_add_vxlan_port,
 	.ndo_udp_tunnel_del	= nfp_net_del_vxlan_port,
 	.ndo_xdp		= nfp_net_xdp,
@@ -3020,9 +2978,9 @@ static const struct net_device_ops nfp_net_netdev_ops = {
 void nfp_net_info(struct nfp_net *nn)
 {
 	nn_info(nn, "Netronome NFP-6xxx %sNetdev: TxQs=%d/%d RxQs=%d/%d\n",
-		nn->is_vf ? "VF " : "",
-		nn->num_tx_rings, nn->max_tx_rings,
-		nn->num_rx_rings, nn->max_rx_rings);
+		nn->dp.is_vf ? "VF " : "",
+		nn->dp.num_tx_rings, nn->max_tx_rings,
+		nn->dp.num_rx_rings, nn->max_rx_rings);
 	nn_info(nn, "VER: %d.%d.%d.%d, Maximum supported MTU: %d\n",
 		nn->fw_ver.resv, nn->fw_ver.class,
 		nn->fw_ver.major, nn->fw_ver.minor,
@@ -3074,21 +3032,24 @@ struct nfp_net *nfp_net_netdev_alloc(struct pci_dev *pdev,
 	SET_NETDEV_DEV(netdev, &pdev->dev);
 	nn = netdev_priv(netdev);
 
-	nn->netdev = netdev;
+	nn->dp.netdev = netdev;
+	nn->dp.dev = &pdev->dev;
 	nn->pdev = pdev;
 
 	nn->max_tx_rings = max_tx_rings;
 	nn->max_rx_rings = max_rx_rings;
 
-	nn->num_tx_rings = min_t(unsigned int, max_tx_rings, num_online_cpus());
-	nn->num_rx_rings = min_t(unsigned int, max_rx_rings,
+	nn->dp.num_tx_rings = min_t(unsigned int,
+				    max_tx_rings, num_online_cpus());
+	nn->dp.num_rx_rings = min_t(unsigned int, max_rx_rings,
 				 netif_get_num_default_rss_queues());
 
-	nn->num_r_vecs = max(nn->num_tx_rings, nn->num_rx_rings);
-	nn->num_r_vecs = min_t(unsigned int, nn->num_r_vecs, num_online_cpus());
+	nn->dp.num_r_vecs = max(nn->dp.num_tx_rings, nn->dp.num_rx_rings);
+	nn->dp.num_r_vecs = min_t(unsigned int,
+				  nn->dp.num_r_vecs, num_online_cpus());
 
-	nn->txd_cnt = NFP_NET_TX_DESCS_DEFAULT;
-	nn->rxd_cnt = NFP_NET_RX_DESCS_DEFAULT;
+	nn->dp.txd_cnt = NFP_NET_TX_DESCS_DEFAULT;
+	nn->dp.rxd_cnt = NFP_NET_RX_DESCS_DEFAULT;
 
 	spin_lock_init(&nn->reconfig_lock);
 	spin_lock_init(&nn->rx_filter_lock);
@@ -3108,7 +3069,28 @@ struct nfp_net *nfp_net_netdev_alloc(struct pci_dev *pdev,
  */
 void nfp_net_netdev_free(struct nfp_net *nn)
 {
-	free_netdev(nn->netdev);
+	free_netdev(nn->dp.netdev);
+}
+
+/**
+ * nfp_net_rss_key_sz() - Get current size of the RSS key
+ * @nn:		NFP Net device instance
+ *
+ * Return: size of the RSS key for currently selected hash function.
+ */
+unsigned int nfp_net_rss_key_sz(struct nfp_net *nn)
+{
+	switch (nn->rss_hfunc) {
+	case ETH_RSS_HASH_TOP:
+		return NFP_NET_CFG_RSS_KEY_SZ;
+	case ETH_RSS_HASH_XOR:
+		return 0;
+	case ETH_RSS_HASH_CRC32:
+		return 4;
+	}
+
+	nn_warn(nn, "Unknown hash function: %u\n", nn->rss_hfunc);
+	return 0;
 }
 
 /**
@@ -3117,14 +3099,32 @@ void nfp_net_netdev_free(struct nfp_net *nn)
  */
 static void nfp_net_rss_init(struct nfp_net *nn)
 {
-	netdev_rss_key_fill(nn->rss_key, NFP_NET_CFG_RSS_KEY_SZ);
+	unsigned long func_bit, rss_cap_hfunc;
+	u32 reg;
+
+	/* Read the RSS function capability and select first supported func */
+	reg = nn_readl(nn, NFP_NET_CFG_RSS_CAP);
+	rss_cap_hfunc =	FIELD_GET(NFP_NET_CFG_RSS_CAP_HFUNC, reg);
+	if (!rss_cap_hfunc)
+		rss_cap_hfunc =	FIELD_GET(NFP_NET_CFG_RSS_CAP_HFUNC,
+					  NFP_NET_CFG_RSS_TOEPLITZ);
+
+	func_bit = find_first_bit(&rss_cap_hfunc, NFP_NET_CFG_RSS_HFUNCS);
+	if (func_bit == NFP_NET_CFG_RSS_HFUNCS) {
+		dev_warn(nn->dp.dev,
+			 "Bad RSS config, defaulting to Toeplitz hash\n");
+		func_bit = ETH_RSS_HASH_TOP_BIT;
+	}
+	nn->rss_hfunc = 1 << func_bit;
+
+	netdev_rss_key_fill(nn->rss_key, nfp_net_rss_key_sz(nn));
 
 	nfp_net_rss_init_itbl(nn);
 
 	/* Enable IPv4/IPv6 TCP by default */
 	nn->rss_cfg = NFP_NET_CFG_RSS_IPV4_TCP |
 		      NFP_NET_CFG_RSS_IPV6_TCP |
-		      NFP_NET_CFG_RSS_TOEPLITZ |
+		      FIELD_PREP(NFP_NET_CFG_RSS_HFUNC, nn->rss_hfunc) |
 		      NFP_NET_CFG_RSS_MASK;
 }
 
@@ -3151,6 +3151,17 @@ int nfp_net_netdev_init(struct net_device *netdev)
 	struct nfp_net *nn = netdev_priv(netdev);
 	int err;
 
+	/* XDP calls for 256 byte packet headroom which wouldn't fit in a u8.
+	 * We, however, reuse the metadata prepend space for XDP buffers which
+	 * is at least 1 byte long and as long as XDP headroom doesn't increase
+	 * above 256 the *extra* XDP headroom will fit on 8 bits.
+	 */
+	BUILD_BUG_ON(XDP_PACKET_HEADROOM > 256);
+
+	nn->dp.chained_metadata_format = nn->fw_ver.major > 3;
+
+	nn->dp.rx_dma_dir = DMA_FROM_DEVICE;
+
 	/* Get some of the read-only fields from the BAR */
 	nn->cap = nn_readl(nn, NFP_NET_CFG_CAP);
 	nn->max_mtu = nn_readl(nn, NFP_NET_CFG_MAX_MTU);
@@ -3158,17 +3169,26 @@ int nfp_net_netdev_init(struct net_device *netdev)
 	nfp_net_write_mac_addr(nn);
 
 	/* Determine RX packet/metadata boundary offset */
-	if (nn->fw_ver.major >= 2)
-		nn->rx_offset = nn_readl(nn, NFP_NET_CFG_RX_OFFSET);
-	else
-		nn->rx_offset = NFP_NET_RX_OFFSET;
+	if (nn->fw_ver.major >= 2) {
+		u32 reg;
+
+		reg = nn_readl(nn, NFP_NET_CFG_RX_OFFSET);
+		if (reg > NFP_NET_MAX_PREPEND) {
+			nn_err(nn, "Invalid rx offset: %d\n", reg);
+			return -EINVAL;
+		}
+		nn->dp.rx_offset = reg;
+	} else {
+		nn->dp.rx_offset = NFP_NET_RX_OFFSET;
+	}
 
 	/* Set default MTU and Freelist buffer size */
 	if (nn->max_mtu < NFP_NET_DEFAULT_MTU)
 		netdev->mtu = nn->max_mtu;
 	else
 		netdev->mtu = NFP_NET_DEFAULT_MTU;
-	nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, netdev->mtu);
+	nn->dp.mtu = netdev->mtu;
+	nn->dp.fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp);
 
 	/* Advertise/enable offloads based on capabilities
 	 *
@@ -3179,31 +3199,31 @@ int nfp_net_netdev_init(struct net_device *netdev)
 	netdev->hw_features = NETIF_F_HIGHDMA;
 	if (nn->cap & NFP_NET_CFG_CTRL_RXCSUM) {
 		netdev->hw_features |= NETIF_F_RXCSUM;
-		nn->ctrl |= NFP_NET_CFG_CTRL_RXCSUM;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_RXCSUM;
 	}
 	if (nn->cap & NFP_NET_CFG_CTRL_TXCSUM) {
 		netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
-		nn->ctrl |= NFP_NET_CFG_CTRL_TXCSUM;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_TXCSUM;
 	}
 	if (nn->cap & NFP_NET_CFG_CTRL_GATHER) {
 		netdev->hw_features |= NETIF_F_SG;
-		nn->ctrl |= NFP_NET_CFG_CTRL_GATHER;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_GATHER;
 	}
 	if ((nn->cap & NFP_NET_CFG_CTRL_LSO) && nn->fw_ver.major > 2) {
 		netdev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6;
-		nn->ctrl |= NFP_NET_CFG_CTRL_LSO;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_LSO;
 	}
 	if (nn->cap & NFP_NET_CFG_CTRL_RSS) {
 		netdev->hw_features |= NETIF_F_RXHASH;
 		nfp_net_rss_init(nn);
-		nn->ctrl |= NFP_NET_CFG_CTRL_RSS;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_RSS;
 	}
 	if (nn->cap & NFP_NET_CFG_CTRL_VXLAN &&
 	    nn->cap & NFP_NET_CFG_CTRL_NVGRE) {
 		if (nn->cap & NFP_NET_CFG_CTRL_LSO)
 			netdev->hw_features |= NETIF_F_GSO_GRE |
 					       NETIF_F_GSO_UDP_TUNNEL;
-		nn->ctrl |= NFP_NET_CFG_CTRL_VXLAN | NFP_NET_CFG_CTRL_NVGRE;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_VXLAN | NFP_NET_CFG_CTRL_NVGRE;
 
 		netdev->hw_enc_features = netdev->hw_features;
 	}
@@ -3212,11 +3232,11 @@ int nfp_net_netdev_init(struct net_device *netdev)
 
 	if (nn->cap & NFP_NET_CFG_CTRL_RXVLAN) {
 		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
-		nn->ctrl |= NFP_NET_CFG_CTRL_RXVLAN;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_RXVLAN;
 	}
 	if (nn->cap & NFP_NET_CFG_CTRL_TXVLAN) {
 		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX;
-		nn->ctrl |= NFP_NET_CFG_CTRL_TXVLAN;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_TXVLAN;
 	}
 
 	netdev->features = netdev->hw_features;
@@ -3229,14 +3249,14 @@ int nfp_net_netdev_init(struct net_device *netdev)
 
 	/* Allow L2 Broadcast and Multicast through by default, if supported */
 	if (nn->cap & NFP_NET_CFG_CTRL_L2BC)
-		nn->ctrl |= NFP_NET_CFG_CTRL_L2BC;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_L2BC;
 	if (nn->cap & NFP_NET_CFG_CTRL_L2MC)
-		nn->ctrl |= NFP_NET_CFG_CTRL_L2MC;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_L2MC;
 
 	/* Allow IRQ moderation, if supported */
 	if (nn->cap & NFP_NET_CFG_CTRL_IRQMOD) {
 		nfp_net_irqmod_init(nn);
-		nn->ctrl |= NFP_NET_CFG_CTRL_IRQMOD;
+		nn->dp.ctrl |= NFP_NET_CFG_CTRL_IRQMOD;
 	}
 
 	/* Stash the re-configuration queue away.  First odd queue in TX Bar */
@@ -3275,10 +3295,10 @@ void nfp_net_netdev_clean(struct net_device *netdev)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 
-	unregister_netdev(nn->netdev);
+	unregister_netdev(nn->dp.netdev);
 
-	if (nn->xdp_prog)
-		bpf_prog_put(nn->xdp_prog);
-	if (nn->bpf_offload_xdp)
+	if (nn->dp.xdp_prog)
+		bpf_prog_put(nn->dp.xdp_prog);
+	if (nn->dp.bpf_offload_xdp)
 		nfp_net_xdp_offload(nn, NULL);
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
index 385ba355c965..d04ccc9f6116 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015 Netronome Systems, Inc.
+ * Copyright (C) 2015-2017 Netronome Systems, Inc.
  *
  * This software is dual licensed under the GNU General License Version 2,
  * June 1991 as shown in the file COPYING in the top-level directory of this
@@ -177,6 +177,19 @@
 #define   NFP_NET_CFG_VERSION_MINOR(x)    (((x) & 0xff) <<  0)
 #define NFP_NET_CFG_STS                 0x0034
 #define   NFP_NET_CFG_STS_LINK            (0x1 << 0) /* Link up or down */
+/* Link rate */
+#define   NFP_NET_CFG_STS_LINK_RATE_SHIFT 1
+#define   NFP_NET_CFG_STS_LINK_RATE_MASK  0xF
+#define   NFP_NET_CFG_STS_LINK_RATE       \
+	(NFP_NET_CFG_STS_LINK_RATE_MASK << NFP_NET_CFG_STS_LINK_RATE_SHIFT)
+#define   NFP_NET_CFG_STS_LINK_RATE_UNSUPPORTED   0
+#define   NFP_NET_CFG_STS_LINK_RATE_UNKNOWN       1
+#define   NFP_NET_CFG_STS_LINK_RATE_1G            2
+#define   NFP_NET_CFG_STS_LINK_RATE_10G           3
+#define   NFP_NET_CFG_STS_LINK_RATE_25G           4
+#define   NFP_NET_CFG_STS_LINK_RATE_40G           5
+#define   NFP_NET_CFG_STS_LINK_RATE_50G           6
+#define   NFP_NET_CFG_STS_LINK_RATE_100G          7
 #define NFP_NET_CFG_CAP                 0x0038
 #define NFP_NET_CFG_MAX_TXRINGS         0x003c
 #define NFP_NET_CFG_MAX_RXRINGS         0x0040
@@ -192,6 +205,14 @@
 #define NFP_NET_CFG_RX_OFFSET_DYNAMIC		0	/* Prepend mode */
 
 /**
+ * RSS capabilities
+ * @NFP_NET_CFG_RSS_CAP_HFUNC:	supported hash functions (same bits as
+ *				@NFP_NET_CFG_RSS_HFUNC)
+ */
+#define NFP_NET_CFG_RSS_CAP		0x0054
+#define   NFP_NET_CFG_RSS_CAP_HFUNC	  0xff000000
+
+/**
  * VXLAN/UDP encap configuration
  * @NFP_NET_CFG_VXLAN_PORT:	Base address of table of tunnels' UDP dst ports
  * @NFP_NET_CFG_VXLAN_SZ:	Size of the UDP port table in bytes
@@ -249,7 +270,11 @@
 #define   NFP_NET_CFG_RSS_IPV4_UDP        (1 << 11) /* RSS for IPv4/UDP */
 #define   NFP_NET_CFG_RSS_IPV6_TCP        (1 << 12) /* RSS for IPv6/TCP */
 #define   NFP_NET_CFG_RSS_IPV6_UDP        (1 << 13) /* RSS for IPv6/UDP */
+#define   NFP_NET_CFG_RSS_HFUNC		  0xff000000
 #define   NFP_NET_CFG_RSS_TOEPLITZ        (1 << 24) /* Use Toeplitz hash */
+#define   NFP_NET_CFG_RSS_XOR		  (1 << 25) /* Use XOR as hash */
+#define   NFP_NET_CFG_RSS_CRC32		  (1 << 26) /* Use CRC32 as hash */
+#define   NFP_NET_CFG_RSS_HFUNCS	  3
 #define NFP_NET_CFG_RSS_KEY             (NFP_NET_CFG_RSS_BASE + 0x4)
 #define NFP_NET_CFG_RSS_KEY_SZ          0x28
 #define NFP_NET_CFG_RSS_ITBL            (NFP_NET_CFG_RSS_BASE + 0x4 + \
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
index 6e9372a18375..4077c59bf782 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
@@ -40,9 +40,9 @@ static struct dentry *nfp_dir;
 
 static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
 {
-	int fl_rd_p, fl_wr_p, rx_rd_p, rx_wr_p, rxd_cnt;
 	struct nfp_net_r_vector *r_vec = file->private;
 	struct nfp_net_rx_ring *rx_ring;
+	int fl_rd_p, fl_wr_p, rxd_cnt;
 	struct nfp_net_rx_desc *rxd;
 	struct nfp_net *nn;
 	void *frag;
@@ -54,19 +54,18 @@ static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
 		goto out;
 	nn = r_vec->nfp_net;
 	rx_ring = r_vec->rx_ring;
-	if (!netif_running(nn->netdev))
+	if (!netif_running(nn->dp.netdev))
 		goto out;
 
 	rxd_cnt = rx_ring->cnt;
 
 	fl_rd_p = nfp_qcp_rd_ptr_read(rx_ring->qcp_fl);
 	fl_wr_p = nfp_qcp_wr_ptr_read(rx_ring->qcp_fl);
-	rx_rd_p = nfp_qcp_rd_ptr_read(rx_ring->qcp_rx);
-	rx_wr_p = nfp_qcp_wr_ptr_read(rx_ring->qcp_rx);
 
-	seq_printf(file, "RX[%02d]: H_RD=%d H_WR=%d FL_RD=%d FL_WR=%d RX_RD=%d RX_WR=%d\n",
-		   rx_ring->idx, rx_ring->rd_p, rx_ring->wr_p,
-		   fl_rd_p, fl_wr_p, rx_rd_p, rx_wr_p);
+	seq_printf(file, "RX[%02d,%02d]: cnt=%d dma=%pad host=%p   H_RD=%d H_WR=%d FL_RD=%d FL_WR=%d\n",
+		   rx_ring->idx, rx_ring->fl_qcidx,
+		   rx_ring->cnt, &rx_ring->dma, rx_ring->rxds,
+		   rx_ring->rd_p, rx_ring->wr_p, fl_rd_p, fl_wr_p);
 
 	for (i = 0; i < rxd_cnt; i++) {
 		rxd = &rx_ring->rxds[i];
@@ -89,10 +88,6 @@ static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
 			seq_puts(file, " FL_RD");
 		if (i == fl_wr_p % rxd_cnt)
 			seq_puts(file, " FL_WR");
-		if (i == rx_rd_p % rxd_cnt)
-			seq_puts(file, " RX_RD");
-		if (i == rx_wr_p % rxd_cnt)
-			seq_puts(file, " RX_WR");
 
 		seq_putc(file, '\n');
 	}
@@ -143,7 +138,7 @@ static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data)
 	if (!r_vec->nfp_net || !tx_ring)
 		goto out;
 	nn = r_vec->nfp_net;
-	if (!netif_running(nn->netdev))
+	if (!netif_running(nn->dp.netdev))
 		goto out;
 
 	txd_cnt = tx_ring->cnt;
@@ -151,8 +146,11 @@ static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data)
 	d_rd_p = nfp_qcp_rd_ptr_read(tx_ring->qcp_q);
 	d_wr_p = nfp_qcp_wr_ptr_read(tx_ring->qcp_q);
 
-	seq_printf(file, "TX[%02d]: H_RD=%d H_WR=%d D_RD=%d D_WR=%d\n",
-		   tx_ring->idx, tx_ring->rd_p, tx_ring->wr_p, d_rd_p, d_wr_p);
+	seq_printf(file, "TX[%02d,%02d%s]: cnt=%d dma=%pad host=%p   H_RD=%d H_WR=%d D_RD=%d D_WR=%d\n",
+		   tx_ring->idx, tx_ring->qcidx,
+		   tx_ring == r_vec->tx_ring ? "" : "xdp",
+		   tx_ring->cnt, &tx_ring->dma, tx_ring->txds,
+		   tx_ring->rd_p, tx_ring->wr_p, d_rd_p, d_wr_p);
 
 	for (i = 0; i < txd_cnt; i++) {
 		txd = &tx_ring->txds[i];
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 2649f7523c81..3328041ec290 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -40,6 +40,7 @@
  *          Brad Petrus <brad.petrus@netronome.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
@@ -48,6 +49,7 @@
 #include <linux/ethtool.h>
 
 #include "nfpcore/nfp.h"
+#include "nfpcore/nfp_nsp.h"
 #include "nfp_net_ctrl.h"
 #include "nfp_net.h"
 
@@ -126,9 +128,9 @@ static const struct _nfp_net_et_stats nfp_net_et_stats[] = {
 };
 
 #define NN_ET_GLOBAL_STATS_LEN ARRAY_SIZE(nfp_net_et_stats)
-#define NN_ET_RVEC_STATS_LEN (nn->num_r_vecs * 3)
+#define NN_ET_RVEC_STATS_LEN (nn->dp.num_r_vecs * 3)
 #define NN_ET_RVEC_GATHER_STATS 7
-#define NN_ET_QUEUE_STATS_LEN ((nn->num_tx_rings + nn->num_rx_rings) * 2)
+#define NN_ET_QUEUE_STATS_LEN ((nn->dp.num_tx_rings + nn->dp.num_rx_rings) * 2)
 #define NN_ET_STATS_LEN (NN_ET_GLOBAL_STATS_LEN + NN_ET_RVEC_GATHER_STATS + \
 			 NN_ET_RVEC_STATS_LEN + NN_ET_QUEUE_STATS_LEN)
 
@@ -172,6 +174,114 @@ static void nfp_net_get_drvinfo(struct net_device *netdev,
 	drvinfo->regdump_len = NFP_NET_CFG_BAR_SZ;
 }
 
+/**
+ * nfp_net_get_link_ksettings - Get Link Speed settings
+ * @netdev:	network interface device structure
+ * @cmd:	ethtool command
+ *
+ * Reports speed settings based on info in the BAR provided by the fw.
+ */
+static int
+nfp_net_get_link_ksettings(struct net_device *netdev,
+			   struct ethtool_link_ksettings *cmd)
+{
+	static const u32 ls_to_ethtool[] = {
+		[NFP_NET_CFG_STS_LINK_RATE_UNSUPPORTED]	= 0,
+		[NFP_NET_CFG_STS_LINK_RATE_UNKNOWN]	= SPEED_UNKNOWN,
+		[NFP_NET_CFG_STS_LINK_RATE_1G]		= SPEED_1000,
+		[NFP_NET_CFG_STS_LINK_RATE_10G]		= SPEED_10000,
+		[NFP_NET_CFG_STS_LINK_RATE_25G]		= SPEED_25000,
+		[NFP_NET_CFG_STS_LINK_RATE_40G]		= SPEED_40000,
+		[NFP_NET_CFG_STS_LINK_RATE_50G]		= SPEED_50000,
+		[NFP_NET_CFG_STS_LINK_RATE_100G]	= SPEED_100000,
+	};
+	struct nfp_net *nn = netdev_priv(netdev);
+	u32 sts, ls;
+
+	ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+	cmd->base.port = PORT_OTHER;
+	cmd->base.speed = SPEED_UNKNOWN;
+	cmd->base.duplex = DUPLEX_UNKNOWN;
+
+	if (nn->eth_port)
+		cmd->base.autoneg = nn->eth_port->aneg != NFP_ANEG_DISABLED ?
+			AUTONEG_ENABLE : AUTONEG_DISABLE;
+
+	if (!netif_carrier_ok(netdev))
+		return 0;
+
+	/* Use link speed from ETH table if available, otherwise try the BAR */
+	if (nn->eth_port && nfp_net_link_changed_read_clear(nn))
+		nfp_net_refresh_port_config(nn);
+	/* Separate if - on FW error the port could've disappeared from table */
+	if (nn->eth_port) {
+		cmd->base.port = nn->eth_port->port_type;
+		cmd->base.speed = nn->eth_port->speed;
+		cmd->base.duplex = DUPLEX_FULL;
+		return 0;
+	}
+
+	sts = nn_readl(nn, NFP_NET_CFG_STS);
+
+	ls = FIELD_GET(NFP_NET_CFG_STS_LINK_RATE, sts);
+	if (ls == NFP_NET_CFG_STS_LINK_RATE_UNSUPPORTED)
+		return -EOPNOTSUPP;
+
+	if (ls == NFP_NET_CFG_STS_LINK_RATE_UNKNOWN ||
+	    ls >= ARRAY_SIZE(ls_to_ethtool))
+		return 0;
+
+	cmd->base.speed = ls_to_ethtool[sts];
+	cmd->base.duplex = DUPLEX_FULL;
+
+	return 0;
+}
+
+static int
+nfp_net_set_link_ksettings(struct net_device *netdev,
+			   const struct ethtool_link_ksettings *cmd)
+{
+	struct nfp_net *nn = netdev_priv(netdev);
+	struct nfp_nsp *nsp;
+	int err;
+
+	if (!nn->eth_port)
+		return -EOPNOTSUPP;
+
+	if (netif_running(netdev)) {
+		nn_warn(nn, "Changing settings not allowed on an active interface. It may cause the port to be disabled until reboot.\n");
+		return -EBUSY;
+	}
+
+	nsp = nfp_eth_config_start(nn->cpp, nn->eth_port->index);
+	if (IS_ERR(nsp))
+		return PTR_ERR(nsp);
+
+	err = __nfp_eth_set_aneg(nsp, cmd->base.autoneg == AUTONEG_ENABLE ?
+				 NFP_ANEG_AUTO : NFP_ANEG_DISABLED);
+	if (err)
+		goto err_bad_set;
+	if (cmd->base.speed != SPEED_UNKNOWN) {
+		u32 speed = cmd->base.speed / nn->eth_port->lanes;
+
+		err = __nfp_eth_set_speed(nsp, speed);
+		if (err)
+			goto err_bad_set;
+	}
+
+	err = nfp_eth_config_commit_end(nsp);
+	if (err > 0)
+		return 0; /* no change */
+
+	nfp_net_refresh_port_config(nn);
+
+	return err;
+
+err_bad_set:
+	nfp_eth_config_cleanup_end(nsp);
+	return err;
+}
+
 static void nfp_net_get_ringparam(struct net_device *netdev,
 				  struct ethtool_ringparam *ring)
 {
@@ -179,30 +289,22 @@ static void nfp_net_get_ringparam(struct net_device *netdev,
 
 	ring->rx_max_pending = NFP_NET_MAX_RX_DESCS;
 	ring->tx_max_pending = NFP_NET_MAX_TX_DESCS;
-	ring->rx_pending = nn->rxd_cnt;
-	ring->tx_pending = nn->txd_cnt;
+	ring->rx_pending = nn->dp.rxd_cnt;
+	ring->tx_pending = nn->dp.txd_cnt;
 }
 
 static int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt)
 {
-	struct nfp_net_ring_set *reconfig_rx = NULL, *reconfig_tx = NULL;
-	struct nfp_net_ring_set rx = {
-		.n_rings = nn->num_rx_rings,
-		.mtu = nn->netdev->mtu,
-		.dcnt = rxd_cnt,
-	};
-	struct nfp_net_ring_set tx = {
-		.n_rings = nn->num_tx_rings,
-		.dcnt = txd_cnt,
-	};
+	struct nfp_net_dp *dp;
 
-	if (nn->rxd_cnt != rxd_cnt)
-		reconfig_rx = &rx;
-	if (nn->txd_cnt != txd_cnt)
-		reconfig_tx = &tx;
+	dp = nfp_net_clone_dp(nn);
+	if (!dp)
+		return -ENOMEM;
 
-	return nfp_net_ring_reconfig(nn, &nn->xdp_prog,
-				     reconfig_rx, reconfig_tx);
+	dp->rxd_cnt = rxd_cnt;
+	dp->txd_cnt = txd_cnt;
+
+	return nfp_net_ring_reconfig(nn, dp);
 }
 
 static int nfp_net_set_ringparam(struct net_device *netdev,
@@ -223,11 +325,11 @@ static int nfp_net_set_ringparam(struct net_device *netdev,
 	    txd_cnt < NFP_NET_MIN_TX_DESCS || txd_cnt > NFP_NET_MAX_TX_DESCS)
 		return -EINVAL;
 
-	if (nn->rxd_cnt == rxd_cnt && nn->txd_cnt == txd_cnt)
+	if (nn->dp.rxd_cnt == rxd_cnt && nn->dp.txd_cnt == txd_cnt)
 		return 0;
 
 	nn_dbg(nn, "Change ring size: RxQ %u->%u, TxQ %u->%u\n",
-	       nn->rxd_cnt, rxd_cnt, nn->txd_cnt, txd_cnt);
+	       nn->dp.rxd_cnt, rxd_cnt, nn->dp.txd_cnt, txd_cnt);
 
 	return nfp_net_set_ring_size(nn, rxd_cnt, txd_cnt);
 }
@@ -245,7 +347,7 @@ static void nfp_net_get_strings(struct net_device *netdev,
 			memcpy(p, nfp_net_et_stats[i].name, ETH_GSTRING_LEN);
 			p += ETH_GSTRING_LEN;
 		}
-		for (i = 0; i < nn->num_r_vecs; i++) {
+		for (i = 0; i < nn->dp.num_r_vecs; i++) {
 			sprintf(p, "rvec_%u_rx_pkts", i);
 			p += ETH_GSTRING_LEN;
 			sprintf(p, "rvec_%u_tx_pkts", i);
@@ -267,13 +369,13 @@ static void nfp_net_get_strings(struct net_device *netdev,
 		p += ETH_GSTRING_LEN;
 		strncpy(p, "tx_lso", ETH_GSTRING_LEN);
 		p += ETH_GSTRING_LEN;
-		for (i = 0; i < nn->num_tx_rings; i++) {
+		for (i = 0; i < nn->dp.num_tx_rings; i++) {
 			sprintf(p, "txq_%u_pkts", i);
 			p += ETH_GSTRING_LEN;
 			sprintf(p, "txq_%u_bytes", i);
 			p += ETH_GSTRING_LEN;
 		}
-		for (i = 0; i < nn->num_rx_rings; i++) {
+		for (i = 0; i < nn->dp.num_rx_rings; i++) {
 			sprintf(p, "rxq_%u_pkts", i);
 			p += ETH_GSTRING_LEN;
 			sprintf(p, "rxq_%u_bytes", i);
@@ -306,12 +408,12 @@ static void nfp_net_get_stats(struct net_device *netdev,
 			break;
 
 		case NFP_NET_DEV_ET_STATS:
-			io_p = nn->ctrl_bar + nfp_net_et_stats[i].off;
+			io_p = nn->dp.ctrl_bar + nfp_net_et_stats[i].off;
 			data[i] = readq(io_p);
 			break;
 		}
 	}
-	for (j = 0; j < nn->num_r_vecs; j++) {
+	for (j = 0; j < nn->dp.num_r_vecs; j++) {
 		unsigned int start;
 
 		do {
@@ -337,16 +439,16 @@ static void nfp_net_get_stats(struct net_device *netdev,
 	}
 	for (j = 0; j < NN_ET_RVEC_GATHER_STATS; j++)
 		data[i++] = gathered_stats[j];
-	for (j = 0; j < nn->num_tx_rings; j++) {
-		io_p = nn->ctrl_bar + NFP_NET_CFG_TXR_STATS(j);
+	for (j = 0; j < nn->dp.num_tx_rings; j++) {
+		io_p = nn->dp.ctrl_bar + NFP_NET_CFG_TXR_STATS(j);
 		data[i++] = readq(io_p);
-		io_p = nn->ctrl_bar + NFP_NET_CFG_TXR_STATS(j) + 8;
+		io_p = nn->dp.ctrl_bar + NFP_NET_CFG_TXR_STATS(j) + 8;
 		data[i++] = readq(io_p);
 	}
-	for (j = 0; j < nn->num_rx_rings; j++) {
-		io_p = nn->ctrl_bar + NFP_NET_CFG_RXR_STATS(j);
+	for (j = 0; j < nn->dp.num_rx_rings; j++) {
+		io_p = nn->dp.ctrl_bar + NFP_NET_CFG_RXR_STATS(j);
 		data[i++] = readq(io_p);
-		io_p = nn->ctrl_bar + NFP_NET_CFG_RXR_STATS(j) + 8;
+		io_p = nn->dp.ctrl_bar + NFP_NET_CFG_RXR_STATS(j) + 8;
 		data[i++] = readq(io_p);
 	}
 }
@@ -410,7 +512,7 @@ static int nfp_net_get_rxnfc(struct net_device *netdev,
 
 	switch (cmd->cmd) {
 	case ETHTOOL_GRXRINGS:
-		cmd->data = nn->num_rx_rings;
+		cmd->data = nn->dp.num_rx_rings;
 		return 0;
 	case ETHTOOL_GRXFH:
 		return nfp_net_get_rss_hash_opts(nn, cmd);
@@ -454,13 +556,13 @@ static int nfp_net_set_rss_hash_opt(struct nfp_net *nn,
 		return -EINVAL;
 	}
 
-	new_rss_cfg |= NFP_NET_CFG_RSS_TOEPLITZ;
+	new_rss_cfg |= FIELD_PREP(NFP_NET_CFG_RSS_HFUNC, nn->rss_hfunc);
 	new_rss_cfg |= NFP_NET_CFG_RSS_MASK;
 
 	if (new_rss_cfg == nn->rss_cfg)
 		return 0;
 
-	writel(new_rss_cfg, nn->ctrl_bar + NFP_NET_CFG_RSS_CTRL);
+	writel(new_rss_cfg, nn->dp.ctrl_bar + NFP_NET_CFG_RSS_CTRL);
 	err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_RSS);
 	if (err)
 		return err;
@@ -496,7 +598,12 @@ static u32 nfp_net_get_rxfh_indir_size(struct net_device *netdev)
 
 static u32 nfp_net_get_rxfh_key_size(struct net_device *netdev)
 {
-	return NFP_NET_CFG_RSS_KEY_SZ;
+	struct nfp_net *nn = netdev_priv(netdev);
+
+	if (!(nn->cap & NFP_NET_CFG_CTRL_RSS))
+		return -EOPNOTSUPP;
+
+	return nfp_net_rss_key_sz(nn);
 }
 
 static int nfp_net_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
@@ -512,9 +619,12 @@ static int nfp_net_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 		for (i = 0; i < ARRAY_SIZE(nn->rss_itbl); i++)
 			indir[i] = nn->rss_itbl[i];
 	if (key)
-		memcpy(key, nn->rss_key, NFP_NET_CFG_RSS_KEY_SZ);
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+		memcpy(key, nn->rss_key, nfp_net_rss_key_sz(nn));
+	if (hfunc) {
+		*hfunc = nn->rss_hfunc;
+		if (*hfunc >= 1 << ETH_RSS_HASH_FUNCS_COUNT)
+			*hfunc = ETH_RSS_HASH_UNKNOWN;
+	}
 
 	return 0;
 }
@@ -527,14 +637,14 @@ static int nfp_net_set_rxfh(struct net_device *netdev,
 	int i;
 
 	if (!(nn->cap & NFP_NET_CFG_CTRL_RSS) ||
-	    !(hfunc == ETH_RSS_HASH_NO_CHANGE || hfunc == ETH_RSS_HASH_TOP))
+	    !(hfunc == ETH_RSS_HASH_NO_CHANGE || hfunc == nn->rss_hfunc))
 		return -EOPNOTSUPP;
 
 	if (!key && !indir)
 		return 0;
 
 	if (key) {
-		memcpy(nn->rss_key, key, NFP_NET_CFG_RSS_KEY_SZ);
+		memcpy(nn->rss_key, key, nfp_net_rss_key_sz(nn));
 		nfp_net_rss_write_key(nn);
 	}
 	if (indir) {
@@ -564,7 +674,7 @@ static void nfp_net_get_regs(struct net_device *netdev,
 	regs->version = nn_readl(nn, NFP_NET_CFG_VERSION);
 
 	for (i = 0; i < NFP_NET_CFG_BAR_SZ / sizeof(u32); i++)
-		regs_buf[i] = readl(nn->ctrl_bar + (i * sizeof(u32)));
+		regs_buf[i] = readl(nn->dp.ctrl_bar + (i * sizeof(u32)));
 }
 
 static int nfp_net_get_coalesce(struct net_device *netdev,
@@ -736,16 +846,16 @@ static void nfp_net_get_channels(struct net_device *netdev,
 	struct nfp_net *nn = netdev_priv(netdev);
 	unsigned int num_tx_rings;
 
-	num_tx_rings = nn->num_tx_rings;
-	if (nn->xdp_prog)
-		num_tx_rings -= nn->num_rx_rings;
+	num_tx_rings = nn->dp.num_tx_rings;
+	if (nn->dp.xdp_prog)
+		num_tx_rings -= nn->dp.num_rx_rings;
 
 	channel->max_rx = min(nn->max_rx_rings, nn->max_r_vecs);
 	channel->max_tx = min(nn->max_tx_rings, nn->max_r_vecs);
 	channel->max_combined = min(channel->max_rx, channel->max_tx);
 	channel->max_other = NFP_NET_NON_Q_VECTORS;
-	channel->combined_count = min(nn->num_rx_rings, num_tx_rings);
-	channel->rx_count = nn->num_rx_rings - channel->combined_count;
+	channel->combined_count = min(nn->dp.num_rx_rings, num_tx_rings);
+	channel->rx_count = nn->dp.num_rx_rings - channel->combined_count;
 	channel->tx_count = num_tx_rings - channel->combined_count;
 	channel->other_count = NFP_NET_NON_Q_VECTORS;
 }
@@ -753,29 +863,19 @@ static void nfp_net_get_channels(struct net_device *netdev,
 static int nfp_net_set_num_rings(struct nfp_net *nn, unsigned int total_rx,
 				 unsigned int total_tx)
 {
-	struct nfp_net_ring_set *reconfig_rx = NULL, *reconfig_tx = NULL;
-	struct nfp_net_ring_set rx = {
-		.n_rings = total_rx,
-		.mtu = nn->netdev->mtu,
-		.dcnt = nn->rxd_cnt,
-	};
-	struct nfp_net_ring_set tx = {
-		.n_rings = total_tx,
-		.dcnt = nn->txd_cnt,
-	};
+	struct nfp_net_dp *dp;
 
-	if (nn->num_rx_rings != total_rx)
-		reconfig_rx = &rx;
-	if (nn->num_stack_tx_rings != total_tx ||
-	    (nn->xdp_prog && reconfig_rx))
-		reconfig_tx = &tx;
+	dp = nfp_net_clone_dp(nn);
+	if (!dp)
+		return -ENOMEM;
 
-	/* nfp_net_check_config() will catch tx.n_rings > nn->max_tx_rings */
-	if (nn->xdp_prog)
-		tx.n_rings += total_rx;
+	dp->num_rx_rings = total_rx;
+	dp->num_tx_rings = total_tx;
+	/* nfp_net_check_config() will catch num_tx_rings > nn->max_tx_rings */
+	if (dp->xdp_prog)
+		dp->num_tx_rings += total_rx;
 
-	return nfp_net_ring_reconfig(nn, &nn->xdp_prog,
-				     reconfig_rx, reconfig_tx);
+	return nfp_net_ring_reconfig(nn, dp);
 }
 
 static int nfp_net_set_channels(struct net_device *netdev,
@@ -823,6 +923,8 @@ static const struct ethtool_ops nfp_net_ethtool_ops = {
 	.set_coalesce           = nfp_net_set_coalesce,
 	.get_channels		= nfp_net_get_channels,
 	.set_channels		= nfp_net_set_channels,
+	.get_link_ksettings	= nfp_net_get_link_ksettings,
+	.set_link_ksettings	= nfp_net_set_link_ksettings,
 };
 
 void nfp_net_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
index 3afcdc11480c..3e1f97e88710 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
@@ -47,11 +47,12 @@
 #include <linux/pci_regs.h>
 #include <linux/msi.h>
 #include <linux/random.h>
+#include <linux/rtnetlink.h>
 
 #include "nfpcore/nfp.h"
 #include "nfpcore/nfp_cpp.h"
 #include "nfpcore/nfp_nffw.h"
-#include "nfpcore/nfp_nsp_eth.h"
+#include "nfpcore/nfp_nsp.h"
 #include "nfpcore/nfp6000_pcie.h"
 
 #include "nfp_net_ctrl.h"
@@ -129,61 +130,61 @@ err_area:
 	return (u8 __iomem *)ERR_PTR(err);
 }
 
+/**
+ * nfp_net_get_mac_addr() - Get the MAC address.
+ * @nn:       NFP Network structure
+ * @cpp:      NFP CPP handle
+ * @id:	      NFP port id
+ *
+ * First try to get the MAC address from NSP ETH table. If that
+ * fails try HWInfo.  As a last resort generate a random address.
+ */
 static void
-nfp_net_get_mac_addr_hwinfo(struct nfp_net *nn, struct nfp_cpp *cpp,
-			    unsigned int id)
+nfp_net_get_mac_addr(struct nfp_net *nn, struct nfp_cpp *cpp, unsigned int id)
 {
+	struct nfp_net_dp *dp = &nn->dp;
 	u8 mac_addr[ETH_ALEN];
 	const char *mac_str;
 	char name[32];
 
+	if (nn->eth_port) {
+		ether_addr_copy(dp->netdev->dev_addr, nn->eth_port->mac_addr);
+		ether_addr_copy(dp->netdev->perm_addr, nn->eth_port->mac_addr);
+		return;
+	}
+
 	snprintf(name, sizeof(name), "eth%d.mac", id);
 
 	mac_str = nfp_hwinfo_lookup(cpp, name);
 	if (!mac_str) {
-		dev_warn(&nn->pdev->dev,
-			 "Can't lookup MAC address. Generate\n");
-		eth_hw_addr_random(nn->netdev);
+		dev_warn(dp->dev, "Can't lookup MAC address. Generate\n");
+		eth_hw_addr_random(dp->netdev);
 		return;
 	}
 
 	if (sscanf(mac_str, "%02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx",
 		   &mac_addr[0], &mac_addr[1], &mac_addr[2],
 		   &mac_addr[3], &mac_addr[4], &mac_addr[5]) != 6) {
-		dev_warn(&nn->pdev->dev,
+		dev_warn(dp->dev,
 			 "Can't parse MAC address (%s). Generate.\n", mac_str);
-		eth_hw_addr_random(nn->netdev);
+		eth_hw_addr_random(dp->netdev);
 		return;
 	}
 
-	ether_addr_copy(nn->netdev->dev_addr, mac_addr);
-	ether_addr_copy(nn->netdev->perm_addr, mac_addr);
+	ether_addr_copy(dp->netdev->dev_addr, mac_addr);
+	ether_addr_copy(dp->netdev->perm_addr, mac_addr);
 }
 
-/**
- * nfp_net_get_mac_addr() - Get the MAC address.
- * @nn:       NFP Network structure
- * @pf:	      NFP PF device structure
- * @id:	      NFP port id
- *
- * First try to get the MAC address from NSP ETH table. If that
- * fails try HWInfo.  As a last resort generate a random address.
- */
-static void
-nfp_net_get_mac_addr(struct nfp_net *nn, struct nfp_pf *pf, unsigned int id)
+static struct nfp_eth_table_port *
+nfp_net_find_port(struct nfp_pf *pf, unsigned int id)
 {
 	int i;
 
 	for (i = 0; pf->eth_tbl && i < pf->eth_tbl->count; i++)
-		if (pf->eth_tbl->ports[i].eth_index == id) {
-			const u8 *mac_addr = pf->eth_tbl->ports[i].mac_addr;
+		if (pf->eth_tbl->ports[i].eth_index == id)
+			return &pf->eth_tbl->ports[i];
 
-			ether_addr_copy(nn->netdev->dev_addr, mac_addr);
-			ether_addr_copy(nn->netdev->perm_addr, mac_addr);
-			return;
-		}
-
-	nfp_net_get_mac_addr_hwinfo(nn, pf->cpp, id);
+	return NULL;
 }
 
 static unsigned int nfp_net_pf_get_num_ports(struct nfp_pf *pf)
@@ -282,6 +283,7 @@ static void nfp_net_pf_free_netdevs(struct nfp_pf *pf)
 	while (!list_empty(&pf->ports)) {
 		nn = list_first_entry(&pf->ports, struct nfp_net, port_list);
 		list_del(&nn->port_list);
+		pf->num_netdevs--;
 
 		nfp_net_netdev_free(nn);
 	}
@@ -290,7 +292,8 @@ static void nfp_net_pf_free_netdevs(struct nfp_pf *pf)
 static struct nfp_net *
 nfp_net_pf_alloc_port_netdev(struct nfp_pf *pf, void __iomem *ctrl_bar,
 			     void __iomem *tx_bar, void __iomem *rx_bar,
-			     int stride, struct nfp_net_fw_version *fw_ver)
+			     int stride, struct nfp_net_fw_version *fw_ver,
+			     struct nfp_eth_table_port *eth_port)
 {
 	u32 n_tx_rings, n_rx_rings;
 	struct nfp_net *nn;
@@ -305,12 +308,13 @@ nfp_net_pf_alloc_port_netdev(struct nfp_pf *pf, void __iomem *ctrl_bar,
 
 	nn->cpp = pf->cpp;
 	nn->fw_ver = *fw_ver;
-	nn->ctrl_bar = ctrl_bar;
+	nn->dp.ctrl_bar = ctrl_bar;
 	nn->tx_bar = tx_bar;
 	nn->rx_bar = rx_bar;
-	nn->is_vf = 0;
+	nn->dp.is_vf = 0;
 	nn->stride_rx = stride;
 	nn->stride_tx = stride;
+	nn->eth_port = eth_port;
 
 	return nn;
 }
@@ -322,7 +326,7 @@ nfp_net_pf_init_port_netdev(struct nfp_pf *pf, struct nfp_net *nn,
 	int err;
 
 	/* Get MAC address */
-	nfp_net_get_mac_addr(nn, pf, id);
+	nfp_net_get_mac_addr(nn, pf->cpp, id);
 
 	/* Get ME clock frequency from ctrl BAR
 	 * XXX for now frequency is hardcoded until we figure out how
@@ -330,7 +334,7 @@ nfp_net_pf_init_port_netdev(struct nfp_pf *pf, struct nfp_net *nn,
 	 */
 	nn->me_freq_mhz = 1200;
 
-	err = nfp_net_netdev_init(nn->netdev);
+	err = nfp_net_netdev_init(nn->dp.netdev);
 	if (err)
 		return err;
 
@@ -347,6 +351,7 @@ nfp_net_pf_alloc_netdevs(struct nfp_pf *pf, void __iomem *ctrl_bar,
 			 int stride, struct nfp_net_fw_version *fw_ver)
 {
 	u32 prev_tx_base, prev_rx_base, tgt_tx_base, tgt_rx_base;
+	struct nfp_eth_table_port *eth_port;
 	struct nfp_net *nn;
 	unsigned int i;
 	int err;
@@ -362,17 +367,27 @@ nfp_net_pf_alloc_netdevs(struct nfp_pf *pf, void __iomem *ctrl_bar,
 		prev_tx_base = tgt_tx_base;
 		prev_rx_base = tgt_rx_base;
 
-		nn = nfp_net_pf_alloc_port_netdev(pf, ctrl_bar, tx_bar, rx_bar,
-						  stride, fw_ver);
-		if (IS_ERR(nn)) {
-			err = PTR_ERR(nn);
-			goto err_free_prev;
+		eth_port = nfp_net_find_port(pf, i);
+		if (eth_port && eth_port->override_changed) {
+			nfp_warn(pf->cpp, "Config changed for port #%d, reboot required before port will be operational\n", i);
+		} else {
+			nn = nfp_net_pf_alloc_port_netdev(pf, ctrl_bar, tx_bar,
+							  rx_bar, stride,
+							  fw_ver, eth_port);
+			if (IS_ERR(nn)) {
+				err = PTR_ERR(nn);
+				goto err_free_prev;
+			}
+			list_add_tail(&nn->port_list, &pf->ports);
+			pf->num_netdevs++;
 		}
-		list_add_tail(&nn->port_list, &pf->ports);
 
 		ctrl_bar += NFP_PF_CSR_SLICE_SIZE;
 	}
 
+	if (list_empty(&pf->ports))
+		return -ENODEV;
+
 	return 0;
 
 err_free_prev:
@@ -399,7 +414,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf,
 	/* Get MSI-X vectors */
 	wanted_irqs = 0;
 	list_for_each_entry(nn, &pf->ports, port_list)
-		wanted_irqs += NFP_NET_NON_Q_VECTORS + nn->num_r_vecs;
+		wanted_irqs += NFP_NET_NON_Q_VECTORS + nn->dp.num_r_vecs;
 	pf->irq_entries = kcalloc(wanted_irqs, sizeof(*pf->irq_entries),
 				  GFP_KERNEL);
 	if (!pf->irq_entries) {
@@ -408,7 +423,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf,
 	}
 
 	num_irqs = nfp_net_irqs_alloc(pf->pdev, pf->irq_entries,
-				      NFP_NET_MIN_PORT_IRQS * pf->num_ports,
+				      NFP_NET_MIN_PORT_IRQS * pf->num_netdevs,
 				      wanted_irqs);
 	if (!num_irqs) {
 		nn_warn(nn, "Unable to allocate MSI-X Vectors. Exiting\n");
@@ -418,7 +433,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf,
 
 	/* Distribute IRQs to ports */
 	irqs_left = num_irqs;
-	ports_left = pf->num_ports;
+	ports_left = pf->num_netdevs;
 	list_for_each_entry(nn, &pf->ports, port_list) {
 		unsigned int n;
 
@@ -444,7 +459,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf,
 err_prev_deinit:
 	list_for_each_entry_continue_reverse(nn, &pf->ports, port_list) {
 		nfp_net_debugfs_dir_clean(&nn->debugfs_dir);
-		nfp_net_netdev_clean(nn->netdev);
+		nfp_net_netdev_clean(nn->dp.netdev);
 	}
 	nfp_net_irqs_disable(pf->pdev);
 err_vec_free:
@@ -454,6 +469,82 @@ err_nn_free:
 	return err;
 }
 
+static void nfp_net_pci_remove_finish(struct nfp_pf *pf)
+{
+	nfp_net_debugfs_dir_clean(&pf->ddir);
+
+	nfp_net_irqs_disable(pf->pdev);
+	kfree(pf->irq_entries);
+
+	nfp_cpp_area_release_free(pf->rx_area);
+	nfp_cpp_area_release_free(pf->tx_area);
+	nfp_cpp_area_release_free(pf->ctrl_area);
+}
+
+static void nfp_net_refresh_netdevs(struct work_struct *work)
+{
+	struct nfp_pf *pf = container_of(work, struct nfp_pf,
+					 port_refresh_work);
+	struct nfp_net *nn, *next;
+
+	mutex_lock(&pf->port_lock);
+
+	/* Check for nfp_net_pci_remove() racing against us */
+	if (list_empty(&pf->ports))
+		goto out;
+
+	list_for_each_entry_safe(nn, next, &pf->ports, port_list) {
+		if (!nn->eth_port) {
+			nfp_warn(pf->cpp, "Warning: port %d not present after reconfig\n",
+				 nn->eth_port->eth_index);
+			continue;
+		}
+		if (!nn->eth_port->override_changed)
+			continue;
+
+		nn_warn(nn, "Port config changed, unregistering. Reboot required before port will be operational again.\n");
+
+		nfp_net_debugfs_dir_clean(&nn->debugfs_dir);
+		nfp_net_netdev_clean(nn->dp.netdev);
+
+		list_del(&nn->port_list);
+		pf->num_netdevs--;
+		nfp_net_netdev_free(nn);
+	}
+
+	if (list_empty(&pf->ports))
+		nfp_net_pci_remove_finish(pf);
+out:
+	mutex_unlock(&pf->port_lock);
+}
+
+void nfp_net_refresh_port_config(struct nfp_net *nn)
+{
+	struct nfp_pf *pf = pci_get_drvdata(nn->pdev);
+	struct nfp_eth_table *old_table;
+
+	ASSERT_RTNL();
+
+	old_table = pf->eth_tbl;
+
+	list_for_each_entry(nn, &pf->ports, port_list)
+		nfp_net_link_changed_read_clear(nn);
+
+	pf->eth_tbl = nfp_eth_read_ports(pf->cpp);
+	if (!pf->eth_tbl) {
+		pf->eth_tbl = old_table;
+		nfp_err(pf->cpp, "Error refreshing port config!\n");
+		return;
+	}
+
+	list_for_each_entry(nn, &pf->ports, port_list)
+		nn->eth_port = nfp_net_find_port(pf, nn->eth_port->eth_index);
+
+	kfree(old_table);
+
+	schedule_work(&pf->port_refresh_work);
+}
+
 /*
  * PCI device functions
  */
@@ -467,17 +558,23 @@ int nfp_net_pci_probe(struct nfp_pf *pf)
 	int stride;
 	int err;
 
+	INIT_WORK(&pf->port_refresh_work, nfp_net_refresh_netdevs);
+	mutex_init(&pf->port_lock);
+
 	/* Verify that the board has completed initialization */
 	if (!nfp_is_ready(pf->cpp)) {
 		nfp_err(pf->cpp, "NFP is not ready for NIC operation.\n");
 		return -EINVAL;
 	}
 
+	mutex_lock(&pf->port_lock);
 	pf->num_ports = nfp_net_pf_get_num_ports(pf);
 
 	ctrl_bar = nfp_net_pf_map_ctrl_bar(pf);
-	if (!ctrl_bar)
-		return pf->fw_loaded ? -EINVAL : -EPROBE_DEFER;
+	if (!ctrl_bar) {
+		err = pf->fw_loaded ? -EINVAL : -EPROBE_DEFER;
+		goto err_unlock;
+	}
 
 	nfp_net_get_fw_version(&fw_ver, ctrl_bar);
 	if (fw_ver.resv || fw_ver.class != NFP_NET_CFG_VERSION_CLASS_GENERIC) {
@@ -551,6 +648,8 @@ int nfp_net_pci_probe(struct nfp_pf *pf)
 	if (err)
 		goto err_clean_ddir;
 
+	mutex_unlock(&pf->port_lock);
+
 	return 0;
 
 err_clean_ddir:
@@ -560,6 +659,8 @@ err_unmap_tx:
 	nfp_cpp_area_release_free(pf->tx_area);
 err_ctrl_unmap:
 	nfp_cpp_area_release_free(pf->ctrl_area);
+err_unlock:
+	mutex_unlock(&pf->port_lock);
 	return err;
 }
 
@@ -567,20 +668,21 @@ void nfp_net_pci_remove(struct nfp_pf *pf)
 {
 	struct nfp_net *nn;
 
+	mutex_lock(&pf->port_lock);
+	if (list_empty(&pf->ports))
+		goto out;
+
 	list_for_each_entry(nn, &pf->ports, port_list) {
 		nfp_net_debugfs_dir_clean(&nn->debugfs_dir);
 
-		nfp_net_netdev_clean(nn->netdev);
+		nfp_net_netdev_clean(nn->dp.netdev);
 	}
 
 	nfp_net_pf_free_netdevs(pf);
 
-	nfp_net_debugfs_dir_clean(&pf->ddir);
+	nfp_net_pci_remove_finish(pf);
+out:
+	mutex_unlock(&pf->port_lock);
 
-	nfp_net_irqs_disable(pf->pdev);
-	kfree(pf->irq_entries);
-
-	nfp_cpp_area_release_free(pf->rx_area);
-	nfp_cpp_area_release_free(pf->tx_area);
-	nfp_cpp_area_release_free(pf->ctrl_area);
+	cancel_work_sync(&pf->port_refresh_work);
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c
index 18a851eb3508..b5b6f69d1e0f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c
@@ -58,7 +58,7 @@ void nfp_net_filter_stats_timer(unsigned long data)
 
 	spin_lock_bh(&nn->rx_filter_lock);
 
-	if (nn->ctrl & NFP_NET_CFG_CTRL_BPF)
+	if (nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF)
 		mod_timer(&nn->rx_filter_stats_timer,
 			  jiffies + NFP_NET_STAT_POLL_IVL);
 
@@ -132,7 +132,7 @@ nfp_net_bpf_get_act(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf)
 			return NN_ACT_TC_DROP;
 
 		if (is_tcf_mirred_egress_redirect(a) &&
-		    tcf_mirred_ifindex(a) == nn->netdev->ifindex)
+		    tcf_mirred_ifindex(a) == nn->dp.netdev->ifindex)
 			return NN_ACT_TC_REDIR;
 	}
 
@@ -160,7 +160,7 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn,
 	act = ret;
 
 	max_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
-	if (max_mtu < nn->netdev->mtu) {
+	if (max_mtu < nn->dp.netdev->mtu) {
 		nn_info(nn, "BPF offload not supported with MTU larger than HW packet split boundary\n");
 		return -ENOTSUPP;
 	}
@@ -168,8 +168,7 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn,
 	start_off = nn_readw(nn, NFP_NET_CFG_BPF_START);
 	done_off = nn_readw(nn, NFP_NET_CFG_BPF_DONE);
 
-	*code = dma_zalloc_coherent(&nn->pdev->dev, code_sz, dma_addr,
-				    GFP_KERNEL);
+	*code = dma_zalloc_coherent(nn->dp.dev, code_sz, dma_addr, GFP_KERNEL);
 	if (!*code)
 		return -ENOMEM;
 
@@ -181,7 +180,7 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn,
 	return 0;
 
 out:
-	dma_free_coherent(&nn->pdev->dev, code_sz, *code, *dma_addr);
+	dma_free_coherent(nn->dp.dev, code_sz, *code, *dma_addr);
 	return ret;
 }
 
@@ -194,7 +193,7 @@ nfp_net_bpf_load_and_start(struct nfp_net *nn, u32 tc_flags,
 	u64 bpf_addr = dma_addr;
 	int err;
 
-	nn->bpf_offload_skip_sw = !!(tc_flags & TCA_CLS_FLAGS_SKIP_SW);
+	nn->dp.bpf_offload_skip_sw = !!(tc_flags & TCA_CLS_FLAGS_SKIP_SW);
 
 	if (dense_mode)
 		bpf_addr |= NFP_NET_CFG_BPF_CFG_8CTX;
@@ -208,13 +207,13 @@ nfp_net_bpf_load_and_start(struct nfp_net *nn, u32 tc_flags,
 		nn_err(nn, "FW command error while loading BPF: %d\n", err);
 
 	/* Enable passing packets through BPF function */
-	nn->ctrl |= NFP_NET_CFG_CTRL_BPF;
-	nn_writel(nn, NFP_NET_CFG_CTRL, nn->ctrl);
+	nn->dp.ctrl |= NFP_NET_CFG_CTRL_BPF;
+	nn_writel(nn, NFP_NET_CFG_CTRL, nn->dp.ctrl);
 	err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN);
 	if (err)
 		nn_err(nn, "FW command error while enabling BPF: %d\n", err);
 
-	dma_free_coherent(&nn->pdev->dev, code_sz, code, dma_addr);
+	dma_free_coherent(nn->dp.dev, code_sz, code, dma_addr);
 
 	nfp_net_bpf_stats_reset(nn);
 	mod_timer(&nn->rx_filter_stats_timer, jiffies + NFP_NET_STAT_POLL_IVL);
@@ -222,16 +221,16 @@ nfp_net_bpf_load_and_start(struct nfp_net *nn, u32 tc_flags,
 
 static int nfp_net_bpf_stop(struct nfp_net *nn)
 {
-	if (!(nn->ctrl & NFP_NET_CFG_CTRL_BPF))
+	if (!(nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF))
 		return 0;
 
 	spin_lock_bh(&nn->rx_filter_lock);
-	nn->ctrl &= ~NFP_NET_CFG_CTRL_BPF;
+	nn->dp.ctrl &= ~NFP_NET_CFG_CTRL_BPF;
 	spin_unlock_bh(&nn->rx_filter_lock);
-	nn_writel(nn, NFP_NET_CFG_CTRL, nn->ctrl);
+	nn_writel(nn, NFP_NET_CFG_CTRL, nn->dp.ctrl);
 
 	del_timer_sync(&nn->rx_filter_stats_timer);
-	nn->bpf_offload_skip_sw = 0;
+	nn->dp.bpf_offload_skip_sw = 0;
 
 	return nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN);
 }
@@ -255,7 +254,7 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf)
 		 * frames which didn't have BPF applied in the hardware should
 		 * be fine if software fallback is available, though.
 		 */
-		if (nn->bpf_offload_skip_sw)
+		if (nn->dp.bpf_offload_skip_sw)
 			return -EBUSY;
 
 		err = nfp_net_bpf_offload_prepare(nn, cls_bpf, &res, &code,
@@ -270,7 +269,7 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf)
 		return 0;
 
 	case TC_CLSBPF_ADD:
-		if (nn->ctrl & NFP_NET_CFG_CTRL_BPF)
+		if (nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF)
 			return -EBUSY;
 
 		err = nfp_net_bpf_offload_prepare(nn, cls_bpf, &res, &code,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
index 39407f7cc586..86e61be6f35c 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
@@ -84,12 +84,12 @@ static void nfp_netvf_get_mac_addr(struct nfp_net *nn)
 	put_unaligned_be16(nn_readw(nn, NFP_NET_CFG_MACADDR + 6), &mac_addr[4]);
 
 	if (!is_valid_ether_addr(mac_addr)) {
-		eth_hw_addr_random(nn->netdev);
+		eth_hw_addr_random(nn->dp.netdev);
 		return;
 	}
 
-	ether_addr_copy(nn->netdev->dev_addr, mac_addr);
-	ether_addr_copy(nn->netdev->perm_addr, mac_addr);
+	ether_addr_copy(nn->dp.netdev->dev_addr, mac_addr);
+	ether_addr_copy(nn->dp.netdev->perm_addr, mac_addr);
 }
 
 static int nfp_netvf_pci_probe(struct pci_dev *pdev,
@@ -210,8 +210,8 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
 	vf->nn = nn;
 
 	nn->fw_ver = fw_ver;
-	nn->ctrl_bar = ctrl_bar;
-	nn->is_vf = 1;
+	nn->dp.ctrl_bar = ctrl_bar;
+	nn->dp.is_vf = 1;
 	nn->stride_tx = stride;
 	nn->stride_rx = stride;
 
@@ -268,7 +268,8 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
 
 	num_irqs = nfp_net_irqs_alloc(pdev, vf->irq_entries,
 				      NFP_NET_MIN_PORT_IRQS,
-				      NFP_NET_NON_Q_VECTORS + nn->num_r_vecs);
+				      NFP_NET_NON_Q_VECTORS +
+				      nn->dp.num_r_vecs);
 	if (!num_irqs) {
 		nn_warn(nn, "Unable to allocate MSI-X Vectors. Exiting\n");
 		err = -EIO;
@@ -282,7 +283,7 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
 	 */
 	nn->me_freq_mhz = 1200;
 
-	err = nfp_net_netdev_init(nn->netdev);
+	err = nfp_net_netdev_init(nn->dp.netdev);
 	if (err)
 		goto err_irqs_disable;
 
@@ -327,7 +328,7 @@ static void nfp_netvf_pci_remove(struct pci_dev *pdev)
 	nfp_net_debugfs_dir_clean(&nn->debugfs_dir);
 	nfp_net_debugfs_dir_clean(&vf->ddir);
 
-	nfp_net_netdev_clean(nn->netdev);
+	nfp_net_netdev_clean(nn->dp.netdev);
 
 	nfp_net_irqs_disable(pdev);
 
@@ -337,7 +338,7 @@ static void nfp_netvf_pci_remove(struct pci_dev *pdev)
 	} else {
 		iounmap(vf->q_bar);
 	}
-	iounmap(nn->ctrl_bar);
+	iounmap(nn->dp.ctrl_bar);
 
 	nfp_net_netdev_free(nn);
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h
index 42cb720b696d..8afef7593f13 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h
@@ -48,32 +48,25 @@
 
 const char *nfp_hwinfo_lookup(struct nfp_cpp *cpp, const char *lookup);
 
-/* Implemented in nfp_nsp.c */
+/* Implemented in nfp_nsp.c, low level functions */
 
 struct nfp_nsp;
-struct firmware;
-
-struct nfp_nsp *nfp_nsp_open(struct nfp_cpp *cpp);
-void nfp_nsp_close(struct nfp_nsp *state);
-u16 nfp_nsp_get_abi_ver_major(struct nfp_nsp *state);
-u16 nfp_nsp_get_abi_ver_minor(struct nfp_nsp *state);
-int nfp_nsp_wait(struct nfp_nsp *state);
-int nfp_nsp_device_soft_reset(struct nfp_nsp *state);
-int nfp_nsp_load_fw(struct nfp_nsp *state, const struct firmware *fw);
+
+struct nfp_cpp *nfp_nsp_cpp(struct nfp_nsp *state);
+bool nfp_nsp_config_modified(struct nfp_nsp *state);
+void nfp_nsp_config_set_modified(struct nfp_nsp *state, bool modified);
+void *nfp_nsp_config_entries(struct nfp_nsp *state);
+unsigned int nfp_nsp_config_idx(struct nfp_nsp *state);
+void nfp_nsp_config_set_state(struct nfp_nsp *state, void *entries,
+			      unsigned int idx);
+void nfp_nsp_config_clear_state(struct nfp_nsp *state);
 int nfp_nsp_read_eth_table(struct nfp_nsp *state, void *buf, unsigned int size);
 int nfp_nsp_write_eth_table(struct nfp_nsp *state,
 			    const void *buf, unsigned int size);
 
 /* Implemented in nfp_resource.c */
 
-#define NFP_RESOURCE_TBL_TARGET		NFP_CPP_TARGET_MU
-#define NFP_RESOURCE_TBL_BASE		0x8100000000ULL
-
-/* NFP Resource Table self-identifier */
-#define NFP_RESOURCE_TBL_NAME		"nfp.res"
-#define NFP_RESOURCE_TBL_KEY		0x00000000 /* Special key for entry 0 */
-
-/* All other keys are CRC32-POSIX of the 8-byte identification string */
+/* All keys are CRC32-POSIX of the 8-byte identification string */
 
 /* ARM/PCI vNIC Interfaces 0..3 */
 #define NFP_RESOURCE_VNIC_PCI_0		"vnic.p0"
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
index 15cc3e77cf6a..43dc68e01274 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
@@ -217,7 +217,7 @@ static resource_size_t nfp_bar_resource_start(struct nfp_bar *bar)
 #define TARGET_WIDTH_64    8
 
 static int
-compute_bar(struct nfp6000_pcie *nfp, struct nfp_bar *bar,
+compute_bar(const struct nfp6000_pcie *nfp, const struct nfp_bar *bar,
 	    u32 *bar_config, u64 *bar_base,
 	    int tgt, int act, int tok, u64 offset, size_t size, int width)
 {
@@ -410,35 +410,36 @@ find_matching_bar(struct nfp6000_pcie *nfp,
 
 /* Return EAGAIN if no resource is available */
 static int
-find_unused_bar_noblock(struct nfp6000_pcie *nfp,
+find_unused_bar_noblock(const struct nfp6000_pcie *nfp,
 			int tgt, int act, int tok,
 			u64 offset, size_t size, int width)
 {
-	int n, invalid = 0;
+	int n, busy = 0;
 
 	for (n = 0; n < nfp->bars; n++) {
-		struct nfp_bar *bar = &nfp->bar[n];
+		const struct nfp_bar *bar = &nfp->bar[n];
 		int err;
 
-		if (bar->bitsize == 0) {
-			invalid++;
-			continue;
-		}
-
-		if (atomic_read(&bar->refcnt) != 0)
+		if (!bar->bitsize)
 			continue;
 
 		/* Just check to see if we can make it fit... */
 		err = compute_bar(nfp, bar, NULL, NULL,
 				  tgt, act, tok, offset, size, width);
+		if (err)
+			continue;
 
-		if (err < 0)
-			invalid++;
-		else
+		if (!atomic_read(&bar->refcnt))
 			return n;
+
+		busy++;
 	}
 
-	return (n == invalid) ? -EINVAL : -EAGAIN;
+	if (WARN(!busy, "No suitable BAR found for request tgt:0x%x act:0x%x tok:0x%x off:0x%llx size:%zd width:%d\n",
+		 tgt, act, tok, offset, size, width))
+		return -EINVAL;
+
+	return -EAGAIN;
 }
 
 static int
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
index 40108e66c654..e2abba4c3a3f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
@@ -65,39 +65,49 @@ struct nfp_cpp_resource {
 	u64 end;
 };
 
-struct nfp_cpp_mutex {
-	struct list_head list;
-	struct nfp_cpp *cpp;
-	int target;
-	u16 usage;
-	u16 depth;
-	unsigned long long address;
-	u32 key;
-};
-
+/**
+ * struct nfp_cpp - main nfpcore device structure
+ * Following fields are read-only after probe() exits or netdevs are spawned.
+ * @dev:		embedded device structure
+ * @op:			low-level implementation ops
+ * @priv:		private data of the low-level implementation
+ * @model:		chip model
+ * @interface:		chip interface id we are using to reach it
+ * @serial:		chip serial number
+ * @imb_cat_table:	CPP Mapping Table
+ *
+ * Following fields can be used only in probe() or with rtnl held:
+ * @hwinfo:		HWInfo database fetched from the device
+ * @rtsym:		firmware run time symbols
+ *
+ * Following fields use explicit locking:
+ * @resource_list:	NFP CPP resource list
+ * @resource_lock:	protects @resource_list
+ *
+ * @area_cache_list:	cached areas for cpp/xpb read/write speed up
+ * @area_cache_mutex:	protects @area_cache_list
+ *
+ * @waitq:		area wait queue
+ */
 struct nfp_cpp {
 	struct device dev;
 
-	void *priv; /* Private data of the low-level implementation */
+	void *priv;
 
 	u32 model;
 	u16 interface;
 	u8 serial[NFP_SERIAL_LEN];
 
 	const struct nfp_cpp_operations *op;
-	struct list_head resource_list;	/* NFP CPP resource list */
-	struct list_head mutex_cache;	/* Mutex cache */
+	struct list_head resource_list;
 	rwlock_t resource_lock;
 	wait_queue_head_t waitq;
 
-	/* NFP6000 CPP Mapping Table */
 	u32 imb_cat_table[16];
 
-	/* Cached areas for cpp/xpb readl/writel speedups */
-	struct mutex area_cache_mutex;  /* Lock for the area cache */
+	struct mutex area_cache_mutex;
 	struct list_head area_cache_list;
 
-	/* Cached information */
 	void *hwinfo;
 	void *rtsym;
 };
@@ -187,24 +197,6 @@ void nfp_cpp_free(struct nfp_cpp *cpp)
 {
 	struct nfp_cpp_area_cache *cache, *ctmp;
 	struct nfp_cpp_resource *res, *rtmp;
-	struct nfp_cpp_mutex *mutex, *mtmp;
-
-	/* There should be no mutexes in the cache at this point. */
-	WARN_ON(!list_empty(&cpp->mutex_cache));
-	/* .. but if there are, unlock them and complain. */
-	list_for_each_entry_safe(mutex, mtmp, &cpp->mutex_cache, list) {
-		dev_err(cpp->dev.parent, "Dangling mutex: @%d::0x%llx, %d locks held by %d owners\n",
-			mutex->target, (unsigned long long)mutex->address,
-			mutex->depth, mutex->usage);
-
-		/* Forcing an unlock */
-		mutex->depth = 1;
-		nfp_cpp_mutex_unlock(mutex);
-
-		/* Forcing a free */
-		mutex->usage = 1;
-		nfp_cpp_mutex_free(mutex);
-	}
 
 	/* Remove all caches */
 	list_for_each_entry_safe(cache, ctmp, &cpp->area_cache_list, entry) {
@@ -419,9 +411,43 @@ nfp_cpp_area_alloc(struct nfp_cpp *cpp, u32 dest,
  */
 void nfp_cpp_area_free(struct nfp_cpp_area *area)
 {
+	if (atomic_read(&area->refcount))
+		nfp_warn(area->cpp, "Warning: freeing busy area\n");
 	nfp_cpp_area_put(area);
 }
 
+static bool nfp_cpp_area_acquire_try(struct nfp_cpp_area *area, int *status)
+{
+	*status = area->cpp->op->area_acquire(area);
+
+	return *status != -EAGAIN;
+}
+
+static int __nfp_cpp_area_acquire(struct nfp_cpp_area *area)
+{
+	int err, status;
+
+	if (atomic_inc_return(&area->refcount) > 1)
+		return 0;
+
+	if (!area->cpp->op->area_acquire)
+		return 0;
+
+	err = wait_event_interruptible(area->cpp->waitq,
+				       nfp_cpp_area_acquire_try(area, &status));
+	if (!err)
+		err = status;
+	if (err) {
+		nfp_warn(area->cpp, "Warning: area wait failed: %d\n", err);
+		atomic_dec(&area->refcount);
+		return err;
+	}
+
+	nfp_cpp_area_get(area);
+
+	return 0;
+}
+
 /**
  * nfp_cpp_area_acquire() - lock down a CPP area for access
  * @area:	CPP area handle
@@ -433,27 +459,13 @@ void nfp_cpp_area_free(struct nfp_cpp_area *area)
  */
 int nfp_cpp_area_acquire(struct nfp_cpp_area *area)
 {
-	mutex_lock(&area->mutex);
-	if (atomic_inc_return(&area->refcount) == 1) {
-		int (*a_a)(struct nfp_cpp_area *);
-
-		a_a = area->cpp->op->area_acquire;
-		if (a_a) {
-			int err;
+	int ret;
 
-			wait_event_interruptible(area->cpp->waitq,
-						 (err = a_a(area)) != -EAGAIN);
-			if (err < 0) {
-				atomic_dec(&area->refcount);
-				mutex_unlock(&area->mutex);
-				return err;
-			}
-		}
-	}
+	mutex_lock(&area->mutex);
+	ret = __nfp_cpp_area_acquire(area);
 	mutex_unlock(&area->mutex);
 
-	nfp_cpp_area_get(area);
-	return 0;
+	return ret;
 }
 
 /**
@@ -829,10 +841,7 @@ area_cache_get(struct nfp_cpp *cpp, u32 id,
 	 * the need for special case code below when
 	 * checking against available cache size.
 	 */
-	if (length == 0)
-		return NULL;
-
-	if (list_empty(&cpp->area_cache_list) || id == 0)
+	if (length == 0 || id == 0)
 		return NULL;
 
 	/* Remap from cpp_island to cpp_target */
@@ -840,10 +849,15 @@ area_cache_get(struct nfp_cpp *cpp, u32 id,
 	if (err < 0)
 		return NULL;
 
-	addr += *offset;
-
 	mutex_lock(&cpp->area_cache_mutex);
 
+	if (list_empty(&cpp->area_cache_list)) {
+		mutex_unlock(&cpp->area_cache_mutex);
+		return NULL;
+	}
+
+	addr += *offset;
+
 	/* See if we have a match */
 	list_for_each_entry(cache, &cpp->area_cache_list, entry) {
 		if (id == cache->id &&
@@ -937,12 +951,14 @@ int nfp_cpp_read(struct nfp_cpp *cpp, u32 destination,
 			return -ENOMEM;
 
 		err = nfp_cpp_area_acquire(area);
-		if (err)
-			goto out;
+		if (err) {
+			nfp_cpp_area_free(area);
+			return err;
+		}
 	}
 
 	err = nfp_cpp_area_read(area, offset, kernel_vaddr, length);
-out:
+
 	if (cache)
 		area_cache_put(cpp, cache);
 	else
@@ -979,13 +995,14 @@ int nfp_cpp_write(struct nfp_cpp *cpp, u32 destination,
 			return -ENOMEM;
 
 		err = nfp_cpp_area_acquire(area);
-		if (err)
-			goto out;
+		if (err) {
+			nfp_cpp_area_free(area);
+			return err;
+		}
 	}
 
 	err = nfp_cpp_area_write(area, offset, kernel_vaddr, length);
 
-out:
 	if (cache)
 		area_cache_put(cpp, cache);
 	else
@@ -1127,7 +1144,6 @@ nfp_cpp_from_operations(const struct nfp_cpp_operations *ops,
 	rwlock_init(&cpp->resource_lock);
 	init_waitqueue_head(&cpp->waitq);
 	lockdep_set_class(&cpp->resource_lock, &nfp_cpp_resource_lock_key);
-	INIT_LIST_HEAD(&cpp->mutex_cache);
 	INIT_LIST_HEAD(&cpp->resource_list);
 	INIT_LIST_HEAD(&cpp->area_cache_list);
 	mutex_init(&cpp->area_cache_mutex);
@@ -1425,322 +1441,3 @@ void *nfp_cpp_explicit_priv(struct nfp_cpp_explicit *cpp_explicit)
 {
 	return &cpp_explicit[1];
 }
-
-/* THIS FUNCTION IS NOT EXPORTED */
-static u32 nfp_mutex_locked(u16 interface)
-{
-	return (u32)interface << 16 | 0x000f;
-}
-
-static u32 nfp_mutex_unlocked(u16 interface)
-{
-	return (u32)interface << 16 | 0x0000;
-}
-
-static bool nfp_mutex_is_locked(u32 val)
-{
-	return (val & 0xffff) == 0x000f;
-}
-
-static bool nfp_mutex_is_unlocked(u32 val)
-{
-	return (val & 0xffff) == 0000;
-}
-
-/* If you need more than 65536 recursive locks, please rethink your code. */
-#define MUTEX_DEPTH_MAX         0xffff
-
-static int
-nfp_cpp_mutex_validate(u16 interface, int *target, unsigned long long address)
-{
-	/* Not permitted on invalid interfaces */
-	if (NFP_CPP_INTERFACE_TYPE_of(interface) ==
-	    NFP_CPP_INTERFACE_TYPE_INVALID)
-		return -EINVAL;
-
-	/* Address must be 64-bit aligned */
-	if (address & 7)
-		return -EINVAL;
-
-	if (*target != NFP_CPP_TARGET_MU)
-		return -EINVAL;
-
-	return 0;
-}
-
-/**
- * nfp_cpp_mutex_init() - Initialize a mutex location
- * @cpp:	NFP CPP handle
- * @target:	NFP CPP target ID (ie NFP_CPP_TARGET_CLS or NFP_CPP_TARGET_MU)
- * @address:	Offset into the address space of the NFP CPP target ID
- * @key:	Unique 32-bit value for this mutex
- *
- * The CPP target:address must point to a 64-bit aligned location, and
- * will initialize 64 bits of data at the location.
- *
- * This creates the initial mutex state, as locked by this
- * nfp_cpp_interface().
- *
- * This function should only be called when setting up
- * the initial lock state upon boot-up of the system.
- *
- * Return: 0 on success, or -errno on failure
- */
-int nfp_cpp_mutex_init(struct nfp_cpp *cpp,
-		       int target, unsigned long long address, u32 key)
-{
-	const u32 muw = NFP_CPP_ID(target, 4, 0);    /* atomic_write */
-	u16 interface = nfp_cpp_interface(cpp);
-	int err;
-
-	err = nfp_cpp_mutex_validate(interface, &target, address);
-	if (err)
-		return err;
-
-	err = nfp_cpp_writel(cpp, muw, address + 4, key);
-	if (err)
-		return err;
-
-	err = nfp_cpp_writel(cpp, muw, address, nfp_mutex_locked(interface));
-	if (err)
-		return err;
-
-	return 0;
-}
-
-/**
- * nfp_cpp_mutex_alloc() - Create a mutex handle
- * @cpp:	NFP CPP handle
- * @target:	NFP CPP target ID (ie NFP_CPP_TARGET_CLS or NFP_CPP_TARGET_MU)
- * @address:	Offset into the address space of the NFP CPP target ID
- * @key:	32-bit unique key (must match the key at this location)
- *
- * The CPP target:address must point to a 64-bit aligned location, and
- * reserve 64 bits of data at the location for use by the handle.
- *
- * Only target/address pairs that point to entities that support the
- * MU Atomic Engine's CmpAndSwap32 command are supported.
- *
- * Return:	A non-NULL struct nfp_cpp_mutex * on success, NULL on failure.
- */
-struct nfp_cpp_mutex *nfp_cpp_mutex_alloc(struct nfp_cpp *cpp, int target,
-					  unsigned long long address, u32 key)
-{
-	const u32 mur = NFP_CPP_ID(target, 3, 0);    /* atomic_read */
-	u16 interface = nfp_cpp_interface(cpp);
-	struct nfp_cpp_mutex *mutex;
-	int err;
-	u32 tmp;
-
-	err = nfp_cpp_mutex_validate(interface, &target, address);
-	if (err)
-		return NULL;
-
-	/* Look for mutex on cache list */
-	list_for_each_entry(mutex, &cpp->mutex_cache, list) {
-		if (mutex->target == target && mutex->address == address) {
-			mutex->usage++;
-			return mutex;
-		}
-	}
-
-	err = nfp_cpp_readl(cpp, mur, address + 4, &tmp);
-	if (err < 0)
-		return NULL;
-
-	if (tmp != key)
-		return NULL;
-
-	mutex = kzalloc(sizeof(*mutex), GFP_KERNEL);
-	if (!mutex)
-		return NULL;
-
-	mutex->cpp = cpp;
-	mutex->target = target;
-	mutex->address = address;
-	mutex->key = key;
-	mutex->depth = 0;
-	mutex->usage = 1;
-
-	/* Add mutex to cache list */
-	list_add(&mutex->list, &cpp->mutex_cache);
-
-	return mutex;
-}
-
-/**
- * nfp_cpp_mutex_free() - Free a mutex handle - does not alter the lock state
- * @mutex:	NFP CPP Mutex handle
- */
-void nfp_cpp_mutex_free(struct nfp_cpp_mutex *mutex)
-{
-	if (--mutex->usage)
-		return;
-
-	/* Remove mutex from cache */
-	list_del(&mutex->list);
-	kfree(mutex);
-}
-
-/**
- * nfp_cpp_mutex_lock() - Lock a mutex handle, using the NFP MU Atomic Engine
- * @mutex:	NFP CPP Mutex handle
- *
- * Return: 0 on success, or -errno on failure
- */
-int nfp_cpp_mutex_lock(struct nfp_cpp_mutex *mutex)
-{
-	unsigned long warn_at = jiffies + 15 * HZ;
-	unsigned int timeout_ms = 1;
-	int err;
-
-	/* We can't use a waitqueue here, because the unlocker
-	 * might be on a separate CPU.
-	 *
-	 * So just wait for now.
-	 */
-	for (;;) {
-		err = nfp_cpp_mutex_trylock(mutex);
-		if (err != -EBUSY)
-			break;
-
-		err = msleep_interruptible(timeout_ms);
-		if (err != 0)
-			return -ERESTARTSYS;
-
-		if (time_is_before_eq_jiffies(warn_at)) {
-			warn_at = jiffies + 60 * HZ;
-			dev_warn(mutex->cpp->dev.parent,
-				 "Warning: waiting for NFP mutex [usage:%hd depth:%hd target:%d addr:%llx key:%08x]\n",
-				 mutex->usage, mutex->depth,
-				 mutex->target, mutex->address, mutex->key);
-		}
-	}
-
-	return err;
-}
-
-/**
- * nfp_cpp_mutex_unlock() - Unlock a mutex handle, using the MU Atomic Engine
- * @mutex:	NFP CPP Mutex handle
- *
- * Return: 0 on success, or -errno on failure
- */
-int nfp_cpp_mutex_unlock(struct nfp_cpp_mutex *mutex)
-{
-	const u32 muw = NFP_CPP_ID(mutex->target, 4, 0);    /* atomic_write */
-	const u32 mur = NFP_CPP_ID(mutex->target, 3, 0);    /* atomic_read */
-	struct nfp_cpp *cpp = mutex->cpp;
-	u32 key, value;
-	u16 interface;
-	int err;
-
-	interface = nfp_cpp_interface(cpp);
-
-	if (mutex->depth > 1) {
-		mutex->depth--;
-		return 0;
-	}
-
-	err = nfp_cpp_readl(mutex->cpp, mur, mutex->address + 4, &key);
-	if (err < 0)
-		return err;
-
-	if (key != mutex->key)
-		return -EPERM;
-
-	err = nfp_cpp_readl(mutex->cpp, mur, mutex->address, &value);
-	if (err < 0)
-		return err;
-
-	if (value != nfp_mutex_locked(interface))
-		return -EACCES;
-
-	err = nfp_cpp_writel(cpp, muw, mutex->address,
-			     nfp_mutex_unlocked(interface));
-	if (err < 0)
-		return err;
-
-	mutex->depth = 0;
-	return 0;
-}
-
-/**
- * nfp_cpp_mutex_trylock() - Attempt to lock a mutex handle
- * @mutex:	NFP CPP Mutex handle
- *
- * Return:      0 if the lock succeeded, -errno on failure
- */
-int nfp_cpp_mutex_trylock(struct nfp_cpp_mutex *mutex)
-{
-	const u32 muw = NFP_CPP_ID(mutex->target, 4, 0);    /* atomic_write */
-	const u32 mus = NFP_CPP_ID(mutex->target, 5, 3);    /* test_set_imm */
-	const u32 mur = NFP_CPP_ID(mutex->target, 3, 0);    /* atomic_read */
-	struct nfp_cpp *cpp = mutex->cpp;
-	u32 key, value, tmp;
-	int err;
-
-	if (mutex->depth > 0) {
-		if (mutex->depth == MUTEX_DEPTH_MAX)
-			return -E2BIG;
-		mutex->depth++;
-		return 0;
-	}
-
-	/* Verify that the lock marker is not damaged */
-	err = nfp_cpp_readl(cpp, mur, mutex->address + 4, &key);
-	if (err < 0)
-		return err;
-
-	if (key != mutex->key)
-		return -EPERM;
-
-	/* Compare against the unlocked state, and if true,
-	 * write the interface id into the top 16 bits, and
-	 * mark as locked.
-	 */
-	value = nfp_mutex_locked(nfp_cpp_interface(cpp));
-
-	/* We use test_set_imm here, as it implies a read
-	 * of the current state, and sets the bits in the
-	 * bytemask of the command to 1s. Since the mutex
-	 * is guaranteed to be 64-bit aligned, the bytemask
-	 * of this 32-bit command is ensured to be 8'b00001111,
-	 * which implies that the lower 4 bits will be set to
-	 * ones regardless of the initial state.
-	 *
-	 * Since this is a 'Readback' operation, with no Pull
-	 * data, we can treat this as a normal Push (read)
-	 * atomic, which returns the original value.
-	 */
-	err = nfp_cpp_readl(cpp, mus, mutex->address, &tmp);
-	if (err < 0)
-		return err;
-
-	/* Was it unlocked? */
-	if (nfp_mutex_is_unlocked(tmp)) {
-		/* The read value can only be 0x....0000 in the unlocked state.
-		 * If there was another contending for this lock, then
-		 * the lock state would be 0x....000f
-		 */
-
-		/* Write our owner ID into the lock
-		 * While not strictly necessary, this helps with
-		 * debug and bookkeeping.
-		 */
-		err = nfp_cpp_writel(cpp, muw, mutex->address, value);
-		if (err < 0)
-			return err;
-
-		mutex->depth = 1;
-		return 0;
-	}
-
-	/* Already locked by us? Success! */
-	if (tmp == value) {
-		mutex->depth = 1;
-		return 0;
-	}
-
-	return nfp_mutex_is_locked(tmp) ? -EBUSY : -EINVAL;
-}
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c
new file mode 100644
index 000000000000..8a99c189efa8
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c
@@ -0,0 +1,345 @@
+/*
+ * Copyright (C) 2015-2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below.  You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      1. Redistributions of source code must retain the above
+ *         copyright notice, this list of conditions and the following
+ *         disclaimer.
+ *
+ *      2. 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/delay.h>
+#include <linux/device.h>
+#include <linux/jiffies.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+
+#include "nfp_cpp.h"
+#include "nfp6000/nfp6000.h"
+
+struct nfp_cpp_mutex {
+	struct nfp_cpp *cpp;
+	int target;
+	u16 depth;
+	unsigned long long address;
+	u32 key;
+};
+
+static u32 nfp_mutex_locked(u16 interface)
+{
+	return (u32)interface << 16 | 0x000f;
+}
+
+static u32 nfp_mutex_unlocked(u16 interface)
+{
+	return (u32)interface << 16 | 0x0000;
+}
+
+static bool nfp_mutex_is_locked(u32 val)
+{
+	return (val & 0xffff) == 0x000f;
+}
+
+static bool nfp_mutex_is_unlocked(u32 val)
+{
+	return (val & 0xffff) == 0000;
+}
+
+/* If you need more than 65536 recursive locks, please rethink your code. */
+#define NFP_MUTEX_DEPTH_MAX         0xffff
+
+static int
+nfp_cpp_mutex_validate(u16 interface, int *target, unsigned long long address)
+{
+	/* Not permitted on invalid interfaces */
+	if (NFP_CPP_INTERFACE_TYPE_of(interface) ==
+	    NFP_CPP_INTERFACE_TYPE_INVALID)
+		return -EINVAL;
+
+	/* Address must be 64-bit aligned */
+	if (address & 7)
+		return -EINVAL;
+
+	if (*target != NFP_CPP_TARGET_MU)
+		return -EINVAL;
+
+	return 0;
+}
+
+/**
+ * nfp_cpp_mutex_init() - Initialize a mutex location
+ * @cpp:	NFP CPP handle
+ * @target:	NFP CPP target ID (ie NFP_CPP_TARGET_CLS or NFP_CPP_TARGET_MU)
+ * @address:	Offset into the address space of the NFP CPP target ID
+ * @key:	Unique 32-bit value for this mutex
+ *
+ * The CPP target:address must point to a 64-bit aligned location, and
+ * will initialize 64 bits of data at the location.
+ *
+ * This creates the initial mutex state, as locked by this
+ * nfp_cpp_interface().
+ *
+ * This function should only be called when setting up
+ * the initial lock state upon boot-up of the system.
+ *
+ * Return: 0 on success, or -errno on failure
+ */
+int nfp_cpp_mutex_init(struct nfp_cpp *cpp,
+		       int target, unsigned long long address, u32 key)
+{
+	const u32 muw = NFP_CPP_ID(target, 4, 0);    /* atomic_write */
+	u16 interface = nfp_cpp_interface(cpp);
+	int err;
+
+	err = nfp_cpp_mutex_validate(interface, &target, address);
+	if (err)
+		return err;
+
+	err = nfp_cpp_writel(cpp, muw, address + 4, key);
+	if (err)
+		return err;
+
+	err = nfp_cpp_writel(cpp, muw, address, nfp_mutex_locked(interface));
+	if (err)
+		return err;
+
+	return 0;
+}
+
+/**
+ * nfp_cpp_mutex_alloc() - Create a mutex handle
+ * @cpp:	NFP CPP handle
+ * @target:	NFP CPP target ID (ie NFP_CPP_TARGET_CLS or NFP_CPP_TARGET_MU)
+ * @address:	Offset into the address space of the NFP CPP target ID
+ * @key:	32-bit unique key (must match the key at this location)
+ *
+ * The CPP target:address must point to a 64-bit aligned location, and
+ * reserve 64 bits of data at the location for use by the handle.
+ *
+ * Only target/address pairs that point to entities that support the
+ * MU Atomic Engine's CmpAndSwap32 command are supported.
+ *
+ * Return:	A non-NULL struct nfp_cpp_mutex * on success, NULL on failure.
+ */
+struct nfp_cpp_mutex *nfp_cpp_mutex_alloc(struct nfp_cpp *cpp, int target,
+					  unsigned long long address, u32 key)
+{
+	const u32 mur = NFP_CPP_ID(target, 3, 0);    /* atomic_read */
+	u16 interface = nfp_cpp_interface(cpp);
+	struct nfp_cpp_mutex *mutex;
+	int err;
+	u32 tmp;
+
+	err = nfp_cpp_mutex_validate(interface, &target, address);
+	if (err)
+		return NULL;
+
+	err = nfp_cpp_readl(cpp, mur, address + 4, &tmp);
+	if (err < 0)
+		return NULL;
+
+	if (tmp != key)
+		return NULL;
+
+	mutex = kzalloc(sizeof(*mutex), GFP_KERNEL);
+	if (!mutex)
+		return NULL;
+
+	mutex->cpp = cpp;
+	mutex->target = target;
+	mutex->address = address;
+	mutex->key = key;
+	mutex->depth = 0;
+
+	return mutex;
+}
+
+/**
+ * nfp_cpp_mutex_free() - Free a mutex handle - does not alter the lock state
+ * @mutex:	NFP CPP Mutex handle
+ */
+void nfp_cpp_mutex_free(struct nfp_cpp_mutex *mutex)
+{
+	kfree(mutex);
+}
+
+/**
+ * nfp_cpp_mutex_lock() - Lock a mutex handle, using the NFP MU Atomic Engine
+ * @mutex:	NFP CPP Mutex handle
+ *
+ * Return: 0 on success, or -errno on failure
+ */
+int nfp_cpp_mutex_lock(struct nfp_cpp_mutex *mutex)
+{
+	unsigned long warn_at = jiffies + 15 * HZ;
+	unsigned int timeout_ms = 1;
+	int err;
+
+	/* We can't use a waitqueue here, because the unlocker
+	 * might be on a separate CPU.
+	 *
+	 * So just wait for now.
+	 */
+	for (;;) {
+		err = nfp_cpp_mutex_trylock(mutex);
+		if (err != -EBUSY)
+			break;
+
+		err = msleep_interruptible(timeout_ms);
+		if (err != 0)
+			return -ERESTARTSYS;
+
+		if (time_is_before_eq_jiffies(warn_at)) {
+			warn_at = jiffies + 60 * HZ;
+			nfp_warn(mutex->cpp,
+				 "Warning: waiting for NFP mutex [depth:%hd target:%d addr:%llx key:%08x]\n",
+				 mutex->depth,
+				 mutex->target, mutex->address, mutex->key);
+		}
+	}
+
+	return err;
+}
+
+/**
+ * nfp_cpp_mutex_unlock() - Unlock a mutex handle, using the MU Atomic Engine
+ * @mutex:	NFP CPP Mutex handle
+ *
+ * Return: 0 on success, or -errno on failure
+ */
+int nfp_cpp_mutex_unlock(struct nfp_cpp_mutex *mutex)
+{
+	const u32 muw = NFP_CPP_ID(mutex->target, 4, 0);    /* atomic_write */
+	const u32 mur = NFP_CPP_ID(mutex->target, 3, 0);    /* atomic_read */
+	struct nfp_cpp *cpp = mutex->cpp;
+	u32 key, value;
+	u16 interface;
+	int err;
+
+	interface = nfp_cpp_interface(cpp);
+
+	if (mutex->depth > 1) {
+		mutex->depth--;
+		return 0;
+	}
+
+	err = nfp_cpp_readl(mutex->cpp, mur, mutex->address + 4, &key);
+	if (err < 0)
+		return err;
+
+	if (key != mutex->key)
+		return -EPERM;
+
+	err = nfp_cpp_readl(mutex->cpp, mur, mutex->address, &value);
+	if (err < 0)
+		return err;
+
+	if (value != nfp_mutex_locked(interface))
+		return -EACCES;
+
+	err = nfp_cpp_writel(cpp, muw, mutex->address,
+			     nfp_mutex_unlocked(interface));
+	if (err < 0)
+		return err;
+
+	mutex->depth = 0;
+	return 0;
+}
+
+/**
+ * nfp_cpp_mutex_trylock() - Attempt to lock a mutex handle
+ * @mutex:	NFP CPP Mutex handle
+ *
+ * Return:      0 if the lock succeeded, -errno on failure
+ */
+int nfp_cpp_mutex_trylock(struct nfp_cpp_mutex *mutex)
+{
+	const u32 muw = NFP_CPP_ID(mutex->target, 4, 0);    /* atomic_write */
+	const u32 mus = NFP_CPP_ID(mutex->target, 5, 3);    /* test_set_imm */
+	const u32 mur = NFP_CPP_ID(mutex->target, 3, 0);    /* atomic_read */
+	struct nfp_cpp *cpp = mutex->cpp;
+	u32 key, value, tmp;
+	int err;
+
+	if (mutex->depth > 0) {
+		if (mutex->depth == NFP_MUTEX_DEPTH_MAX)
+			return -E2BIG;
+		mutex->depth++;
+		return 0;
+	}
+
+	/* Verify that the lock marker is not damaged */
+	err = nfp_cpp_readl(cpp, mur, mutex->address + 4, &key);
+	if (err < 0)
+		return err;
+
+	if (key != mutex->key)
+		return -EPERM;
+
+	/* Compare against the unlocked state, and if true,
+	 * write the interface id into the top 16 bits, and
+	 * mark as locked.
+	 */
+	value = nfp_mutex_locked(nfp_cpp_interface(cpp));
+
+	/* We use test_set_imm here, as it implies a read
+	 * of the current state, and sets the bits in the
+	 * bytemask of the command to 1s. Since the mutex
+	 * is guaranteed to be 64-bit aligned, the bytemask
+	 * of this 32-bit command is ensured to be 8'b00001111,
+	 * which implies that the lower 4 bits will be set to
+	 * ones regardless of the initial state.
+	 *
+	 * Since this is a 'Readback' operation, with no Pull
+	 * data, we can treat this as a normal Push (read)
+	 * atomic, which returns the original value.
+	 */
+	err = nfp_cpp_readl(cpp, mus, mutex->address, &tmp);
+	if (err < 0)
+		return err;
+
+	/* Was it unlocked? */
+	if (nfp_mutex_is_unlocked(tmp)) {
+		/* The read value can only be 0x....0000 in the unlocked state.
+		 * If there was another contending for this lock, then
+		 * the lock state would be 0x....000f
+		 */
+
+		/* Write our owner ID into the lock
+		 * While not strictly necessary, this helps with
+		 * debug and bookkeeping.
+		 */
+		err = nfp_cpp_writel(cpp, muw, mutex->address, value);
+		if (err < 0)
+			return err;
+
+		mutex->depth = 1;
+		return 0;
+	}
+
+	return nfp_mutex_is_locked(tmp) ? -EBUSY : -EINVAL;
+}
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
index 34c50987c377..4635f42e15b0 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
@@ -49,6 +49,7 @@
 
 #include "nfp.h"
 #include "nfp_cpp.h"
+#include "nfp_nsp.h"
 
 /* Offsets relative to the CSR base */
 #define NSP_STATUS		0x00
@@ -96,6 +97,17 @@ enum nfp_nsp_cmd {
 	__MAX_SPCODE,
 };
 
+static const struct {
+	int code;
+	const char *msg;
+} nsp_errors[] = {
+	{ 6010, "could not map to phy for port" },
+	{ 6011, "not an allowed rate/lanes for port" },
+	{ 6012, "not an allowed rate/lanes for port" },
+	{ 6013, "high/low error, change other port first" },
+	{ 6014, "config not found in flash" },
+};
+
 struct nfp_nsp {
 	struct nfp_cpp *cpp;
 	struct nfp_resource *res;
@@ -103,8 +115,63 @@ struct nfp_nsp {
 		u16 major;
 		u16 minor;
 	} ver;
+
+	/* Eth table config state */
+	bool modified;
+	unsigned int idx;
+	void *entries;
 };
 
+struct nfp_cpp *nfp_nsp_cpp(struct nfp_nsp *state)
+{
+	return state->cpp;
+}
+
+bool nfp_nsp_config_modified(struct nfp_nsp *state)
+{
+	return state->modified;
+}
+
+void nfp_nsp_config_set_modified(struct nfp_nsp *state, bool modified)
+{
+	state->modified = modified;
+}
+
+void *nfp_nsp_config_entries(struct nfp_nsp *state)
+{
+	return state->entries;
+}
+
+unsigned int nfp_nsp_config_idx(struct nfp_nsp *state)
+{
+	return state->idx;
+}
+
+void
+nfp_nsp_config_set_state(struct nfp_nsp *state, void *entries, unsigned int idx)
+{
+	state->entries = entries;
+	state->idx = idx;
+}
+
+void nfp_nsp_config_clear_state(struct nfp_nsp *state)
+{
+	state->entries = NULL;
+	state->idx = 0;
+}
+
+static void nfp_nsp_print_extended_error(struct nfp_nsp *state, u32 ret_val)
+{
+	int i;
+
+	if (!ret_val)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(nsp_errors); i++)
+		if (ret_val == nsp_errors[i].code)
+			nfp_err(state->cpp, "err msg: %s\n", nsp_errors[i].msg);
+}
+
 static int nfp_nsp_check(struct nfp_nsp *state)
 {
 	struct nfp_cpp *cpp = state->cpp;
@@ -209,9 +276,8 @@ nfp_nsp_wait_reg(struct nfp_cpp *cpp, u64 *reg,
 		if ((*reg & mask) == val)
 			return 0;
 
-		err = msleep_interruptible(100);
-		if (err)
-			return err;
+		if (msleep_interruptible(25))
+			return -ERESTARTSYS;
 
 		if (time_after(start_time, wait_until))
 			return -ETIMEDOUT;
@@ -228,7 +294,7 @@ nfp_nsp_wait_reg(struct nfp_cpp *cpp, u64 *reg,
  *
  * Return: 0 for success with no result
  *
- *	 1..255 for NSP completion with a result code
+ *	 positive value for NSP completion with a result code
  *
  *	-EAGAIN if the NSP is not yet present
  *	-ENODEV if the NSP is not a supported model
@@ -239,7 +305,7 @@ nfp_nsp_wait_reg(struct nfp_cpp *cpp, u64 *reg,
 static int nfp_nsp_command(struct nfp_nsp *state, u16 code, u32 option,
 			   u32 buff_cpp, u64 buff_addr)
 {
-	u64 reg, nsp_base, nsp_buffer, nsp_status, nsp_command;
+	u64 reg, ret_val, nsp_base, nsp_buffer, nsp_status, nsp_command;
 	struct nfp_cpp *cpp = state->cpp;
 	u32 nsp_cpp;
 	int err;
@@ -292,18 +358,20 @@ static int nfp_nsp_command(struct nfp_nsp *state, u16 code, u32 option,
 		return err;
 	}
 
+	err = nfp_cpp_readq(cpp, nsp_cpp, nsp_command, &ret_val);
+	if (err < 0)
+		return err;
+	ret_val = FIELD_GET(NSP_COMMAND_OPTION, ret_val);
+
 	err = FIELD_GET(NSP_STATUS_RESULT, reg);
 	if (err) {
-		nfp_warn(cpp, "Result (error) code set: %d command: %d\n",
-			 -err, code);
+		nfp_warn(cpp, "Result (error) code set: %d (%d) command: %d\n",
+			 -err, (int)ret_val, code);
+		nfp_nsp_print_extended_error(state, ret_val);
 		return -err;
 	}
 
-	err = nfp_cpp_readq(cpp, nsp_cpp, nsp_command, &reg);
-	if (err < 0)
-		return err;
-
-	return FIELD_GET(NSP_COMMAND_OPTION, reg);
+	return ret_val;
 }
 
 static int nfp_nsp_command_buf(struct nfp_nsp *nsp, u16 code, u32 option,
@@ -380,9 +448,10 @@ int nfp_nsp_wait(struct nfp_nsp *state)
 		if (err != -EAGAIN)
 			break;
 
-		err = msleep_interruptible(100);
-		if (err)
+		if (msleep_interruptible(25)) {
+			err = -ERESTARTSYS;
 			break;
+		}
 
 		if (time_after(start_time, wait_until)) {
 			err = -ETIMEDOUT;
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h
index edf703d319c8..7d34ff145fd7 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h
@@ -31,12 +31,48 @@
  * SOFTWARE.
  */
 
-#ifndef NSP_NSP_ETH_H
-#define NSP_NSP_ETH_H 1
+#ifndef NSP_NSP_H
+#define NSP_NSP_H 1
 
 #include <linux/types.h>
 #include <linux/if_ether.h>
 
+struct firmware;
+struct nfp_cpp;
+struct nfp_nsp;
+
+struct nfp_nsp *nfp_nsp_open(struct nfp_cpp *cpp);
+void nfp_nsp_close(struct nfp_nsp *state);
+u16 nfp_nsp_get_abi_ver_major(struct nfp_nsp *state);
+u16 nfp_nsp_get_abi_ver_minor(struct nfp_nsp *state);
+int nfp_nsp_wait(struct nfp_nsp *state);
+int nfp_nsp_device_soft_reset(struct nfp_nsp *state);
+int nfp_nsp_load_fw(struct nfp_nsp *state, const struct firmware *fw);
+
+enum nfp_eth_interface {
+	NFP_INTERFACE_NONE	= 0,
+	NFP_INTERFACE_SFP	= 1,
+	NFP_INTERFACE_SFPP	= 10,
+	NFP_INTERFACE_SFP28	= 28,
+	NFP_INTERFACE_QSFP	= 40,
+	NFP_INTERFACE_CXP	= 100,
+	NFP_INTERFACE_QSFP28	= 112,
+};
+
+enum nfp_eth_media {
+	NFP_MEDIA_DAC_PASSIVE = 0,
+	NFP_MEDIA_DAC_ACTIVE,
+	NFP_MEDIA_FIBRE,
+};
+
+enum nfp_eth_aneg {
+	NFP_ANEG_AUTO = 0,
+	NFP_ANEG_SEARCH,
+	NFP_ANEG_25G_CONSORTIUM,
+	NFP_ANEG_25G_IEEE,
+	NFP_ANEG_DISABLED,
+};
+
 /**
  * struct nfp_eth_table - ETH table information
  * @count:	number of table entries
@@ -48,11 +84,19 @@
  * @base:	first channel index (within NBI)
  * @lanes:	number of channels
  * @speed:	interface speed (in Mbps)
+ * @interface:	interface (module) plugged in
+ * @media:	media type of the @interface
+ * @aneg:	auto negotiation mode
  * @mac_addr:	interface MAC address
- * @label:	interface id string
+ * @label_port:	port id
+ * @label_subport:  id of interface within port (for split ports)
  * @enabled:	is enabled?
  * @tx_enabled:	is TX enabled?
  * @rx_enabled:	is RX enabled?
+ * @override_changed: is media reconfig pending?
+ *
+ * @port_type:	one of %PORT_* defines for ethtool
+ * @is_split:	is interface part of a split port
  */
 struct nfp_eth_table {
 	unsigned int count;
@@ -64,18 +108,43 @@ struct nfp_eth_table {
 		unsigned int lanes;
 		unsigned int speed;
 
+		unsigned int interface;
+		enum nfp_eth_media media;
+
+		enum nfp_eth_aneg aneg;
+
 		u8 mac_addr[ETH_ALEN];
-		char label[8];
+
+		u8 label_port;
+		u8 label_subport;
 
 		bool enabled;
 		bool tx_enabled;
 		bool rx_enabled;
+
+		bool override_changed;
+
+		/* Computed fields */
+		u8 port_type;
+
+		bool is_split;
 	} ports[0];
 };
 
 struct nfp_eth_table *nfp_eth_read_ports(struct nfp_cpp *cpp);
 struct nfp_eth_table *
 __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp);
+
 int nfp_eth_set_mod_enable(struct nfp_cpp *cpp, unsigned int idx, bool enable);
+int nfp_eth_set_configured(struct nfp_cpp *cpp, unsigned int idx,
+			   bool configed);
+
+struct nfp_nsp *nfp_eth_config_start(struct nfp_cpp *cpp, unsigned int idx);
+int nfp_eth_config_commit_end(struct nfp_nsp *nsp);
+void nfp_eth_config_cleanup_end(struct nfp_nsp *nsp);
+
+int __nfp_eth_set_aneg(struct nfp_nsp *nsp, enum nfp_eth_aneg mode);
+int __nfp_eth_set_speed(struct nfp_nsp *nsp, unsigned int speed);
+int __nfp_eth_set_split(struct nfp_nsp *nsp, unsigned int lanes);
 
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
index 1ece1f8ae4b3..639438d8313a 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
@@ -43,13 +43,13 @@
 #include <linux/module.h>
 
 #include "nfp.h"
-#include "nfp_nsp_eth.h"
+#include "nfp_nsp.h"
 #include "nfp6000/nfp6000.h"
 
 #define NSP_ETH_NBI_PORT_COUNT		24
 #define NSP_ETH_MAX_COUNT		(2 * NSP_ETH_NBI_PORT_COUNT)
 #define NSP_ETH_TABLE_SIZE		(NSP_ETH_MAX_COUNT *		\
-					 sizeof(struct eth_table_entry))
+					 sizeof(union eth_table_entry))
 
 #define NSP_ETH_PORT_LANES		GENMASK_ULL(3, 0)
 #define NSP_ETH_PORT_INDEX		GENMASK_ULL(15, 8)
@@ -58,14 +58,32 @@
 
 #define NSP_ETH_PORT_LANES_MASK		cpu_to_le64(NSP_ETH_PORT_LANES)
 
+#define NSP_ETH_STATE_CONFIGURED	BIT_ULL(0)
 #define NSP_ETH_STATE_ENABLED		BIT_ULL(1)
 #define NSP_ETH_STATE_TX_ENABLED	BIT_ULL(2)
 #define NSP_ETH_STATE_RX_ENABLED	BIT_ULL(3)
 #define NSP_ETH_STATE_RATE		GENMASK_ULL(11, 8)
+#define NSP_ETH_STATE_INTERFACE		GENMASK_ULL(19, 12)
+#define NSP_ETH_STATE_MEDIA		GENMASK_ULL(21, 20)
+#define NSP_ETH_STATE_OVRD_CHNG		BIT_ULL(22)
+#define NSP_ETH_STATE_ANEG		GENMASK_ULL(25, 23)
 
+#define NSP_ETH_CTRL_CONFIGURED		BIT_ULL(0)
 #define NSP_ETH_CTRL_ENABLED		BIT_ULL(1)
 #define NSP_ETH_CTRL_TX_ENABLED		BIT_ULL(2)
 #define NSP_ETH_CTRL_RX_ENABLED		BIT_ULL(3)
+#define NSP_ETH_CTRL_SET_RATE		BIT_ULL(4)
+#define NSP_ETH_CTRL_SET_LANES		BIT_ULL(5)
+#define NSP_ETH_CTRL_SET_ANEG		BIT_ULL(6)
+
+enum nfp_eth_raw {
+	NSP_ETH_RAW_PORT = 0,
+	NSP_ETH_RAW_STATE,
+	NSP_ETH_RAW_MAC,
+	NSP_ETH_RAW_CONTROL,
+
+	NSP_ETH_NUM_RAW
+};
 
 enum nfp_eth_rate {
 	RATE_INVALID = 0,
@@ -76,29 +94,49 @@ enum nfp_eth_rate {
 	RATE_25G,
 };
 
-struct eth_table_entry {
-	__le64 port;
-	__le64 state;
-	u8 mac_addr[6];
-	u8 resv[2];
-	__le64 control;
+union eth_table_entry {
+	struct {
+		__le64 port;
+		__le64 state;
+		u8 mac_addr[6];
+		u8 resv[2];
+		__le64 control;
+	};
+	__le64 raw[NSP_ETH_NUM_RAW];
+};
+
+static const struct {
+	enum nfp_eth_rate rate;
+	unsigned int speed;
+} nsp_eth_rate_tbl[] = {
+	{ RATE_INVALID,	0, },
+	{ RATE_10M,	SPEED_10, },
+	{ RATE_100M,	SPEED_100, },
+	{ RATE_1G,	SPEED_1000, },
+	{ RATE_10G,	SPEED_10000, },
+	{ RATE_25G,	SPEED_25000, },
 };
 
-static unsigned int nfp_eth_rate(enum nfp_eth_rate rate)
+static unsigned int nfp_eth_rate2speed(enum nfp_eth_rate rate)
 {
-	unsigned int rate_xlate[] = {
-		[RATE_INVALID]		= 0,
-		[RATE_10M]		= SPEED_10,
-		[RATE_100M]		= SPEED_100,
-		[RATE_1G]		= SPEED_1000,
-		[RATE_10G]		= SPEED_10000,
-		[RATE_25G]		= SPEED_25000,
-	};
+	int i;
 
-	if (rate >= ARRAY_SIZE(rate_xlate))
-		return 0;
+	for (i = 0; i < ARRAY_SIZE(nsp_eth_rate_tbl); i++)
+		if (nsp_eth_rate_tbl[i].rate == rate)
+			return nsp_eth_rate_tbl[i].speed;
+
+	return 0;
+}
+
+static unsigned int nfp_eth_speed2rate(unsigned int speed)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nsp_eth_rate_tbl); i++)
+		if (nsp_eth_rate_tbl[i].speed == speed)
+			return nsp_eth_rate_tbl[i].rate;
 
-	return rate_xlate[rate];
+	return RATE_INVALID;
 }
 
 static void nfp_eth_copy_mac_reverse(u8 *dst, const u8 *src)
@@ -110,8 +148,8 @@ static void nfp_eth_copy_mac_reverse(u8 *dst, const u8 *src)
 }
 
 static void
-nfp_eth_port_translate(const struct eth_table_entry *src, unsigned int index,
-		       struct nfp_eth_table_port *dst)
+nfp_eth_port_translate(struct nfp_nsp *nsp, const union eth_table_entry *src,
+		       unsigned int index, struct nfp_eth_table_port *dst)
 {
 	unsigned int rate;
 	u64 port, state;
@@ -129,14 +167,60 @@ nfp_eth_port_translate(const struct eth_table_entry *src, unsigned int index,
 	dst->tx_enabled = FIELD_GET(NSP_ETH_STATE_TX_ENABLED, state);
 	dst->rx_enabled = FIELD_GET(NSP_ETH_STATE_RX_ENABLED, state);
 
-	rate = nfp_eth_rate(FIELD_GET(NSP_ETH_STATE_RATE, state));
+	rate = nfp_eth_rate2speed(FIELD_GET(NSP_ETH_STATE_RATE, state));
 	dst->speed = dst->lanes * rate;
 
+	dst->interface = FIELD_GET(NSP_ETH_STATE_INTERFACE, state);
+	dst->media = FIELD_GET(NSP_ETH_STATE_MEDIA, state);
+
 	nfp_eth_copy_mac_reverse(dst->mac_addr, src->mac_addr);
 
-	snprintf(dst->label, sizeof(dst->label) - 1, "%llu.%llu",
-		 FIELD_GET(NSP_ETH_PORT_PHYLABEL, port),
-		 FIELD_GET(NSP_ETH_PORT_LABEL, port));
+	dst->label_port = FIELD_GET(NSP_ETH_PORT_PHYLABEL, port);
+	dst->label_subport = FIELD_GET(NSP_ETH_PORT_LABEL, port);
+
+	if (nfp_nsp_get_abi_ver_minor(nsp) < 17)
+		return;
+
+	dst->override_changed = FIELD_GET(NSP_ETH_STATE_OVRD_CHNG, state);
+	dst->aneg = FIELD_GET(NSP_ETH_STATE_ANEG, state);
+}
+
+static void
+nfp_eth_mark_split_ports(struct nfp_cpp *cpp, struct nfp_eth_table *table)
+{
+	unsigned int i, j;
+
+	for (i = 0; i < table->count; i++)
+		for (j = 0; j < table->count; j++) {
+			if (i == j)
+				continue;
+			if (table->ports[i].label_port !=
+			    table->ports[j].label_port)
+				continue;
+			if (table->ports[i].label_subport ==
+			    table->ports[j].label_subport)
+				nfp_warn(cpp,
+					 "Port %d subport %d is a duplicate\n",
+					 table->ports[i].label_port,
+					 table->ports[i].label_subport);
+
+			table->ports[i].is_split = true;
+			break;
+		}
+}
+
+static void
+nfp_eth_calc_port_type(struct nfp_cpp *cpp, struct nfp_eth_table_port *entry)
+{
+	if (entry->interface == NFP_INTERFACE_NONE) {
+		entry->port_type = PORT_NONE;
+		return;
+	}
+
+	if (entry->media == NFP_MEDIA_FIBRE)
+		entry->port_type = PORT_FIBRE;
+	else
+		entry->port_type = PORT_DA;
 }
 
 /**
@@ -166,10 +250,9 @@ struct nfp_eth_table *nfp_eth_read_ports(struct nfp_cpp *cpp)
 struct nfp_eth_table *
 __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp)
 {
-	struct eth_table_entry *entries;
+	union eth_table_entry *entries;
 	struct nfp_eth_table *table;
-	unsigned int cnt;
-	int i, j, ret;
+	int i, j, ret, cnt = 0;
 
 	entries = kzalloc(NSP_ETH_TABLE_SIZE, GFP_KERNEL);
 	if (!entries)
@@ -178,93 +261,288 @@ __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp)
 	ret = nfp_nsp_read_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE);
 	if (ret < 0) {
 		nfp_err(cpp, "reading port table failed %d\n", ret);
-		kfree(entries);
-		return NULL;
+		goto err;
 	}
 
-	/* Some versions of flash will give us 0 instead of port count */
-	cnt = ret;
-	if (!cnt) {
-		for (i = 0; i < NSP_ETH_MAX_COUNT; i++)
-			if (entries[i].port & NSP_ETH_PORT_LANES_MASK)
-				cnt++;
+	for (i = 0; i < NSP_ETH_MAX_COUNT; i++)
+		if (entries[i].port & NSP_ETH_PORT_LANES_MASK)
+			cnt++;
+
+	/* Some versions of flash will give us 0 instead of port count.
+	 * For those that give a port count, verify it against the value
+	 * calculated above.
+	 */
+	if (ret && ret != cnt) {
+		nfp_err(cpp, "table entry count reported (%d) does not match entries present (%d)\n",
+			ret, cnt);
+		goto err;
 	}
 
 	table = kzalloc(sizeof(*table) +
 			sizeof(struct nfp_eth_table_port) * cnt, GFP_KERNEL);
-	if (!table) {
-		kfree(entries);
-		return NULL;
-	}
+	if (!table)
+		goto err;
 
 	table->count = cnt;
 	for (i = 0, j = 0; i < NSP_ETH_MAX_COUNT; i++)
 		if (entries[i].port & NSP_ETH_PORT_LANES_MASK)
-			nfp_eth_port_translate(&entries[i], i,
+			nfp_eth_port_translate(nsp, &entries[i], i,
 					       &table->ports[j++]);
 
+	nfp_eth_mark_split_ports(cpp, table);
+	for (i = 0; i < table->count; i++)
+		nfp_eth_calc_port_type(cpp, &table->ports[i]);
+
 	kfree(entries);
 
 	return table;
+
+err:
+	kfree(entries);
+	return NULL;
 }
 
-/**
- * nfp_eth_set_mod_enable() - set PHY module enable control bit
- * @cpp:	NFP CPP handle
- * @idx:	NFP chip-wide port index
- * @enable:	Desired state
- *
- * Enable or disable PHY module (this usually means setting the TX lanes
- * disable bits).
- *
- * Return: 0 or -ERRNO.
- */
-int nfp_eth_set_mod_enable(struct nfp_cpp *cpp, unsigned int idx, bool enable)
+struct nfp_nsp *nfp_eth_config_start(struct nfp_cpp *cpp, unsigned int idx)
 {
-	struct eth_table_entry *entries;
+	union eth_table_entry *entries;
 	struct nfp_nsp *nsp;
-	u64 reg;
 	int ret;
 
 	entries = kzalloc(NSP_ETH_TABLE_SIZE, GFP_KERNEL);
 	if (!entries)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	nsp = nfp_nsp_open(cpp);
 	if (IS_ERR(nsp)) {
 		kfree(entries);
-		return PTR_ERR(nsp);
+		return nsp;
 	}
 
 	ret = nfp_nsp_read_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE);
 	if (ret < 0) {
 		nfp_err(cpp, "reading port table failed %d\n", ret);
-		goto exit_close_nsp;
+		goto err;
 	}
 
 	if (!(entries[idx].port & NSP_ETH_PORT_LANES_MASK)) {
 		nfp_warn(cpp, "trying to set port state on disabled port %d\n",
 			 idx);
-		ret = -EINVAL;
-		goto exit_close_nsp;
+		goto err;
+	}
+
+	nfp_nsp_config_set_state(nsp, entries, idx);
+	return nsp;
+
+err:
+	nfp_nsp_close(nsp);
+	kfree(entries);
+	return ERR_PTR(-EIO);
+}
+
+void nfp_eth_config_cleanup_end(struct nfp_nsp *nsp)
+{
+	union eth_table_entry *entries = nfp_nsp_config_entries(nsp);
+
+	nfp_nsp_config_set_modified(nsp, false);
+	nfp_nsp_config_clear_state(nsp);
+	nfp_nsp_close(nsp);
+	kfree(entries);
+}
+
+/**
+ * nfp_eth_config_commit_end() - perform recorded configuration changes
+ * @nsp:	NFP NSP handle returned from nfp_eth_config_start()
+ *
+ * Perform the configuration which was requested with __nfp_eth_set_*()
+ * helpers and recorded in @nsp state.  If device was already configured
+ * as requested or no __nfp_eth_set_*() operations were made no NSP command
+ * will be performed.
+ *
+ * Return:
+ * 0 - configuration successful;
+ * 1 - no changes were needed;
+ * -ERRNO - configuration failed.
+ */
+int nfp_eth_config_commit_end(struct nfp_nsp *nsp)
+{
+	union eth_table_entry *entries = nfp_nsp_config_entries(nsp);
+	int ret = 1;
+
+	if (nfp_nsp_config_modified(nsp)) {
+		ret = nfp_nsp_write_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE);
+		ret = ret < 0 ? ret : 0;
+	}
+
+	nfp_eth_config_cleanup_end(nsp);
+
+	return ret;
+}
+
+/**
+ * nfp_eth_set_mod_enable() - set PHY module enable control bit
+ * @cpp:	NFP CPP handle
+ * @idx:	NFP chip-wide port index
+ * @enable:	Desired state
+ *
+ * Enable or disable PHY module (this usually means setting the TX lanes
+ * disable bits).
+ *
+ * Return: 0 or -ERRNO.
+ */
+int nfp_eth_set_mod_enable(struct nfp_cpp *cpp, unsigned int idx, bool enable)
+{
+	union eth_table_entry *entries;
+	struct nfp_nsp *nsp;
+	u64 reg;
+
+	nsp = nfp_eth_config_start(cpp, idx);
+	if (IS_ERR(nsp))
+		return PTR_ERR(nsp);
+
+	entries = nfp_nsp_config_entries(nsp);
+
+	/* Check if we are already in requested state */
+	reg = le64_to_cpu(entries[idx].state);
+	if (enable != FIELD_GET(NSP_ETH_CTRL_ENABLED, reg)) {
+		reg = le64_to_cpu(entries[idx].control);
+		reg &= ~NSP_ETH_CTRL_ENABLED;
+		reg |= FIELD_PREP(NSP_ETH_CTRL_ENABLED, enable);
+		entries[idx].control = cpu_to_le64(reg);
+
+		nfp_nsp_config_set_modified(nsp, true);
 	}
 
+	return nfp_eth_config_commit_end(nsp);
+}
+
+/**
+ * nfp_eth_set_configured() - set PHY module configured control bit
+ * @cpp:	NFP CPP handle
+ * @idx:	NFP chip-wide port index
+ * @configed:	Desired state
+ *
+ * Set the ifup/ifdown state on the PHY.
+ *
+ * Return: 0 or -ERRNO.
+ */
+int nfp_eth_set_configured(struct nfp_cpp *cpp, unsigned int idx, bool configed)
+{
+	union eth_table_entry *entries;
+	struct nfp_nsp *nsp;
+	u64 reg;
+
+	nsp = nfp_eth_config_start(cpp, idx);
+	if (IS_ERR(nsp))
+		return PTR_ERR(nsp);
+
+	entries = nfp_nsp_config_entries(nsp);
+
 	/* Check if we are already in requested state */
 	reg = le64_to_cpu(entries[idx].state);
-	if (enable == FIELD_GET(NSP_ETH_CTRL_ENABLED, reg)) {
-		ret = 0;
-		goto exit_close_nsp;
+	if (configed != FIELD_GET(NSP_ETH_STATE_CONFIGURED, reg)) {
+		reg = le64_to_cpu(entries[idx].control);
+		reg &= ~NSP_ETH_CTRL_CONFIGURED;
+		reg |= FIELD_PREP(NSP_ETH_CTRL_CONFIGURED, configed);
+		entries[idx].control = cpu_to_le64(reg);
+
+		nfp_nsp_config_set_modified(nsp, true);
 	}
 
-	reg = le64_to_cpu(entries[idx].control);
-	reg &= ~NSP_ETH_CTRL_ENABLED;
-	reg |= FIELD_PREP(NSP_ETH_CTRL_ENABLED, enable);
-	entries[idx].control = cpu_to_le64(reg);
+	return nfp_eth_config_commit_end(nsp);
+}
 
-	ret = nfp_nsp_write_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE);
-exit_close_nsp:
-	nfp_nsp_close(nsp);
-	kfree(entries);
+/* Force inline, FIELD_* macroes require masks to be compilation-time known */
+static __always_inline int
+nfp_eth_set_bit_config(struct nfp_nsp *nsp, unsigned int raw_idx,
+		       const u64 mask, unsigned int val, const u64 ctrl_bit)
+{
+	union eth_table_entry *entries = nfp_nsp_config_entries(nsp);
+	unsigned int idx = nfp_nsp_config_idx(nsp);
+	u64 reg;
+
+	/* Note: set features were added in ABI 0.14 but the error
+	 *	 codes were initially not populated correctly.
+	 */
+	if (nfp_nsp_get_abi_ver_minor(nsp) < 17) {
+		nfp_err(nfp_nsp_cpp(nsp),
+			"set operations not supported, please update flash\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* Check if we are already in requested state */
+	reg = le64_to_cpu(entries[idx].raw[raw_idx]);
+	if (val == FIELD_GET(mask, reg))
+		return 0;
 
-	return ret < 0 ? ret : 0;
+	reg &= ~mask;
+	reg |= FIELD_PREP(mask, val);
+	entries[idx].raw[raw_idx] = cpu_to_le64(reg);
+
+	entries[idx].control |= cpu_to_le64(ctrl_bit);
+
+	nfp_nsp_config_set_modified(nsp, true);
+
+	return 0;
+}
+
+/**
+ * __nfp_eth_set_aneg() - set PHY autonegotiation control bit
+ * @nsp:	NFP NSP handle returned from nfp_eth_config_start()
+ * @mode:	Desired autonegotiation mode
+ *
+ * Allow/disallow PHY module to advertise/perform autonegotiation.
+ * Will write to hwinfo overrides in the flash (persistent config).
+ *
+ * Return: 0 or -ERRNO.
+ */
+int __nfp_eth_set_aneg(struct nfp_nsp *nsp, enum nfp_eth_aneg mode)
+{
+	return nfp_eth_set_bit_config(nsp, NSP_ETH_RAW_STATE,
+				      NSP_ETH_STATE_ANEG, mode,
+				      NSP_ETH_CTRL_SET_ANEG);
+}
+
+/**
+ * __nfp_eth_set_speed() - set interface speed/rate
+ * @nsp:	NFP NSP handle returned from nfp_eth_config_start()
+ * @speed:	Desired speed (per lane)
+ *
+ * Set lane speed.  Provided @speed value should be subport speed divided
+ * by number of lanes this subport is spanning (i.e. 10000 for 40G, 25000 for
+ * 50G, etc.)
+ * Will write to hwinfo overrides in the flash (persistent config).
+ *
+ * Return: 0 or -ERRNO.
+ */
+int __nfp_eth_set_speed(struct nfp_nsp *nsp, unsigned int speed)
+{
+	enum nfp_eth_rate rate;
+
+	rate = nfp_eth_speed2rate(speed);
+	if (rate == RATE_INVALID) {
+		nfp_warn(nfp_nsp_cpp(nsp),
+			 "could not find matching lane rate for speed %u\n",
+			 speed);
+		return -EINVAL;
+	}
+
+	return nfp_eth_set_bit_config(nsp, NSP_ETH_RAW_STATE,
+				      NSP_ETH_STATE_RATE, rate,
+				      NSP_ETH_CTRL_SET_RATE);
+}
+
+/**
+ * __nfp_eth_set_split() - set interface lane split
+ * @nsp:	NFP NSP handle returned from nfp_eth_config_start()
+ * @lanes:	Desired lanes per port
+ *
+ * Set number of lanes in the port.
+ * Will write to hwinfo overrides in the flash (persistent config).
+ *
+ * Return: 0 or -ERRNO.
+ */
+int __nfp_eth_set_split(struct nfp_nsp *nsp, unsigned int lanes)
+{
+	return nfp_eth_set_bit_config(nsp, NSP_ETH_RAW_PORT, NSP_ETH_PORT_LANES,
+				      lanes, NSP_ETH_CTRL_SET_LANES);
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c
index a2850344f8b4..2d15a7c9d0de 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c
@@ -45,6 +45,13 @@
 #include "nfp_cpp.h"
 #include "nfp6000/nfp6000.h"
 
+#define NFP_RESOURCE_TBL_TARGET		NFP_CPP_TARGET_MU
+#define NFP_RESOURCE_TBL_BASE		0x8100000000ULL
+
+/* NFP Resource Table self-identifier */
+#define NFP_RESOURCE_TBL_NAME		"nfp.res"
+#define NFP_RESOURCE_TBL_KEY		0x00000000 /* Special key for entry 0 */
+
 #define NFP_RESOURCE_ENTRY_NAME_SZ	8
 
 /**
@@ -100,9 +107,11 @@ static int nfp_cpp_resource_find(struct nfp_cpp *cpp, struct nfp_resource *res)
 	strncpy(name_pad, res->name, sizeof(name_pad));
 
 	/* Search for a matching entry */
-	key = NFP_RESOURCE_TBL_KEY;
-	if (memcmp(name_pad, NFP_RESOURCE_TBL_NAME "\0\0\0\0\0\0\0\0", 8))
-		key = crc32_posix(name_pad, sizeof(name_pad));
+	if (!memcmp(name_pad, NFP_RESOURCE_TBL_NAME "\0\0\0\0\0\0\0\0", 8)) {
+		nfp_err(cpp, "Grabbing device lock not supported\n");
+		return -EOPNOTSUPP;
+	}
+	key = crc32_posix(name_pad, sizeof(name_pad));
 
 	for (i = 0; i < NFP_RESOURCE_TBL_ENTRIES; i++) {
 		u64 addr = NFP_RESOURCE_TBL_BASE +
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
index 7b43a3b4abdc..3dd973475125 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
@@ -1375,13 +1375,8 @@ netxen_receive_peg_ready(struct netxen_adapter *adapter)
 
 	} while (--retries);
 
-	if (!retries) {
-		printk(KERN_ERR "Receive Peg initialization not "
-			      "complete, state: 0x%x.\n", val);
-		return -EIO;
-	}
-
-	return 0;
+	pr_err("Receive Peg initialization not complete, state: 0x%x.\n", val);
+	return -EIO;
 }
 
 int netxen_init_firmware(struct netxen_adapter *adapter)
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 00c17fa6545b..d8bcc21a4f69 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -51,7 +51,19 @@
 #include "qed_hsi.h"
 
 extern const struct qed_common_ops qed_common_ops_pass;
-#define DRV_MODULE_VERSION "8.10.10.20"
+
+#define QED_MAJOR_VERSION               8
+#define QED_MINOR_VERSION               10
+#define QED_REVISION_VERSION            10
+#define QED_ENGINEERING_VERSION 21
+
+#define QED_VERSION						 \
+	((QED_MAJOR_VERSION << 24) | (QED_MINOR_VERSION << 16) | \
+	 (QED_REVISION_VERSION << 8) | QED_ENGINEERING_VERSION)
+
+#define STORM_FW_VERSION				       \
+	((FW_MAJOR_VERSION << 24) | (FW_MINOR_VERSION << 16) | \
+	 (FW_REVISION_VERSION << 8) | FW_ENGINEERING_VERSION)
 
 #define MAX_HWFNS_PER_DEVICE    (4)
 #define NAME_SIZE 16
@@ -59,8 +71,6 @@ extern const struct qed_common_ops qed_common_ops_pass;
 
 #define QED_WFQ_UNIT	100
 
-#define ISCSI_BDQ_ID(_port_id) (_port_id)
-#define FCOE_BDQ_ID(_port_id) ((_port_id) + 2)
 #define QED_WID_SIZE            (1024)
 #define QED_PF_DEMS_SIZE        (4)
 
@@ -76,6 +86,15 @@ union qed_mcp_protocol_stats;
 enum qed_mcp_protocol_type;
 
 /* helpers */
+#define QED_MFW_GET_FIELD(name, field) \
+	(((name) & (field ## _MASK)) >> (field ## _SHIFT))
+
+#define QED_MFW_SET_FIELD(name, field, value)				       \
+	do {								       \
+		(name)	&= ~((field ## _MASK) << (field ## _SHIFT));	       \
+		(name)	|= (((value) << (field ## _SHIFT)) & (field ## _MASK));\
+	} while (0)
+
 static inline u32 qed_db_addr(u32 cid, u32 DEMS)
 {
 	u32 db_addr = FIELD_VALUE(DB_LEGACY_ADDR_DEMS, DEMS) |
@@ -198,6 +217,7 @@ enum qed_resources {
 	QED_LL2_QUEUE,
 	QED_CMDQS_CQS,
 	QED_RDMA_STATS_QUEUE,
+	QED_BDQ,
 	QED_MAX_RESC,
 };
 
@@ -219,7 +239,9 @@ enum QED_PORT_MODE {
 	QED_PORT_MODE_DE_4X20G,
 	QED_PORT_MODE_DE_1X40G,
 	QED_PORT_MODE_DE_2X25G,
-	QED_PORT_MODE_DE_1X25G
+	QED_PORT_MODE_DE_1X25G,
+	QED_PORT_MODE_DE_4X25G,
+	QED_PORT_MODE_DE_2X10G,
 };
 
 enum qed_dev_cap {
@@ -249,9 +271,14 @@ struct qed_hw_info {
 				 RESC_NUM(_p_hwfn, resc))
 #define FEAT_NUM(_p_hwfn, resc) ((_p_hwfn)->hw_info.feat_num[resc])
 
-	u8				num_tc;
+	/* Amount of traffic classes HW supports */
+	u8 num_hw_tc;
+
+	/* Amount of TCs which should be active according to DCBx or upper
+	 * layer driver configuration.
+	 */
+	u8 num_active_tc;
 	u8				offload_tc;
-	u8				non_offload_tc;
 
 	u32				concrete_fid;
 	u16				opaque_fid;
@@ -314,15 +341,19 @@ struct qed_qm_info {
 	struct init_qm_port_params	*qm_port_params;
 	u16				start_pq;
 	u8				start_vport;
-	u8				pure_lb_pq;
-	u8				offload_pq;
-	u8				pure_ack_pq;
-	u8 ooo_pq;
-	u8				vf_queues_offset;
+	u16				 pure_lb_pq;
+	u16				offload_pq;
+	u16				low_latency_pq;
+	u16				pure_ack_pq;
+	u16				ooo_pq;
+	u16				first_vf_pq;
+	u16				first_mcos_pq;
+	u16				first_rl_pq;
 	u16				num_pqs;
 	u16				num_vf_pqs;
 	u8				num_vports;
 	u8				max_phys_tcs_per_port;
+	u8				ooo_tc;
 	bool				pf_rl_en;
 	bool				pf_wfq_en;
 	bool				vport_rl_en;
@@ -353,6 +384,12 @@ struct qed_fw_data {
 	u32			init_ops_size;
 };
 
+#define DRV_MODULE_VERSION		      \
+	__stringify(QED_MAJOR_VERSION) "."    \
+	__stringify(QED_MINOR_VERSION) "."    \
+	__stringify(QED_REVISION_VERSION) "." \
+	__stringify(QED_ENGINEERING_VERSION)
+
 struct qed_simd_fp_handler {
 	void	*token;
 	void	(*func)(void *);
@@ -364,7 +401,8 @@ struct qed_hwfn {
 #define IS_LEAD_HWFN(edev)              (!((edev)->my_id))
 	u8				rel_pf_id;      /* Relative to engine*/
 	u8				abs_pf_id;
-#define QED_PATH_ID(_p_hwfn)		((_p_hwfn)->abs_pf_id & 1)
+#define QED_PATH_ID(_p_hwfn) \
+	(QED_IS_K2((_p_hwfn)->cdev) ? 0 : ((_p_hwfn)->abs_pf_id & 1))
 	u8				port_id;
 	bool				b_active;
 
@@ -523,9 +561,7 @@ struct qed_dev {
 	u8	dp_level;
 	char	name[NAME_SIZE];
 
-	u8	type;
-#define QED_DEV_TYPE_BB (0 << 0)
-#define QED_DEV_TYPE_AH BIT(0)
+	enum	qed_dev_type type;
 /* Translate type/revision combo into the proper conditions */
 #define QED_IS_BB(dev)  ((dev)->type == QED_DEV_TYPE_BB)
 #define QED_IS_BB_A0(dev)       (QED_IS_BB(dev) && \
@@ -540,6 +576,9 @@ struct qed_dev {
 
 	u16	vendor_id;
 	u16	device_id;
+#define QED_DEV_ID_MASK		0xff00
+#define QED_DEV_ID_MASK_BB	0x1600
+#define QED_DEV_ID_MASK_AH	0x8000
 
 	u16	chip_num;
 #define CHIP_NUM_MASK                   0xffff
@@ -654,10 +693,16 @@ struct qed_dev {
 	u32 rdma_max_srq_sge;
 };
 
-#define NUM_OF_VFS(dev)         MAX_NUM_VFS_BB
-#define NUM_OF_L2_QUEUES(dev)	MAX_NUM_L2_QUEUES_BB
-#define NUM_OF_SBS(dev)         MAX_SB_PER_PATH_BB
-#define NUM_OF_ENG_PFS(dev)     MAX_NUM_PFS_BB
+#define NUM_OF_VFS(dev)         (QED_IS_BB(dev) ? MAX_NUM_VFS_BB \
+						: MAX_NUM_VFS_K2)
+#define NUM_OF_L2_QUEUES(dev)   (QED_IS_BB(dev) ? MAX_NUM_L2_QUEUES_BB \
+						: MAX_NUM_L2_QUEUES_K2)
+#define NUM_OF_PORTS(dev)       (QED_IS_BB(dev) ? MAX_NUM_PORTS_BB \
+						: MAX_NUM_PORTS_K2)
+#define NUM_OF_SBS(dev)         (QED_IS_BB(dev) ? MAX_SB_PER_PATH_BB \
+						: MAX_SB_PER_PATH_K2)
+#define NUM_OF_ENG_PFS(dev)     (QED_IS_BB(dev) ? MAX_NUM_PFS_BB \
+						: MAX_NUM_PFS_K2)
 
 /**
  * @brief qed_concrete_to_sw_fid - get the sw function id from
@@ -693,6 +738,25 @@ void qed_configure_vp_wfq_on_link_change(struct qed_dev *cdev,
 					 u32 min_pf_rate);
 
 void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+int qed_device_num_engines(struct qed_dev *cdev);
+
+#define QED_LEADING_HWFN(dev)   (&dev->hwfns[0])
+
+/* Flags for indication of required queues */
+#define PQ_FLAGS_RLS    (BIT(0))
+#define PQ_FLAGS_MCOS   (BIT(1))
+#define PQ_FLAGS_LB     (BIT(2))
+#define PQ_FLAGS_OOO    (BIT(3))
+#define PQ_FLAGS_ACK    (BIT(4))
+#define PQ_FLAGS_OFLD   (BIT(5))
+#define PQ_FLAGS_VFS    (BIT(6))
+#define PQ_FLAGS_LLT    (BIT(7))
+
+/* physical queue index for cm context intialization */
+u16 qed_get_cm_pq_idx(struct qed_hwfn *p_hwfn, u32 pq_flags);
+u16 qed_get_cm_pq_idx_mcos(struct qed_hwfn *p_hwfn, u8 tc);
+u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf);
+
 #define QED_LEADING_HWFN(dev)   (&dev->hwfns[0])
 
 /* Other Linux specific common definitions */
@@ -721,5 +785,6 @@ void qed_get_protocol_stats(struct qed_dev *cdev,
 			    enum qed_mcp_protocol_type type,
 			    union qed_mcp_protocol_stats *stats);
 int qed_slowpath_irq_req(struct qed_hwfn *hwfn);
+void qed_slowpath_irq_sync(struct qed_hwfn *p_hwfn);
 
 #endif /* _QED_H */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 7e3a6fed3da6..485b8b22ec7a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -71,8 +71,7 @@
 #define TM_ALIGN        BIT(TM_SHIFT)
 #define TM_ELEM_SIZE    4
 
-/* For RoCE we configure to 64K to cover for RoCE max tasks 256K purpose. */
-#define ILT_DEFAULT_HW_P_SIZE	(IS_ENABLED(CONFIG_QED_RDMA) ? 4 : 3)
+#define ILT_DEFAULT_HW_P_SIZE	4
 
 #define ILT_PAGE_IN_BYTES(hw_p_size)	(1U << ((hw_p_size) + 12))
 #define ILT_CFG_REG(cli, reg)	PSWRQ2_REG_ ## cli ## _ ## reg ## _RT_OFFSET
@@ -242,8 +241,7 @@ struct qed_cxt_mngr {
 static bool src_proto(enum protocol_type type)
 {
 	return type == PROTOCOLID_ISCSI ||
-	       type == PROTOCOLID_FCOE ||
-	       type == PROTOCOLID_ROCE;
+	       type == PROTOCOLID_FCOE;
 }
 
 static bool tm_cid_proto(enum protocol_type type)
@@ -304,16 +302,34 @@ struct qed_tm_iids {
 	u32 per_vf_tids;
 };
 
-static void qed_cxt_tm_iids(struct qed_cxt_mngr *p_mngr,
+static void qed_cxt_tm_iids(struct qed_hwfn *p_hwfn,
+			    struct qed_cxt_mngr *p_mngr,
 			    struct qed_tm_iids *iids)
 {
-	u32 i, j;
-
-	for (i = 0; i < MAX_CONN_TYPES; i++) {
+	bool tm_vf_required = false;
+	bool tm_required = false;
+	int i, j;
+
+	/* Timers is a special case -> we don't count how many cids require
+	 * timers but what's the max cid that will be used by the timer block.
+	 * therefore we traverse in reverse order, and once we hit a protocol
+	 * that requires the timers memory, we'll sum all the protocols up
+	 * to that one.
+	 */
+	for (i = MAX_CONN_TYPES - 1; i >= 0; i--) {
 		struct qed_conn_type_cfg *p_cfg = &p_mngr->conn_cfg[i];
 
-		if (tm_cid_proto(i)) {
+		if (tm_cid_proto(i) || tm_required) {
+			if (p_cfg->cid_count)
+				tm_required = true;
+
 			iids->pf_cids += p_cfg->cid_count;
+		}
+
+		if (tm_cid_proto(i) || tm_vf_required) {
+			if (p_cfg->cids_per_vf)
+				tm_vf_required = true;
+
 			iids->per_vf_cids += p_cfg->cids_per_vf;
 		}
 
@@ -527,7 +543,22 @@ static u32 qed_ilt_get_dynamic_line_cnt(struct qed_hwfn *p_hwfn,
 	return lines_to_skip;
 }
 
-int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
+static struct qed_ilt_client_cfg *qed_cxt_set_cli(struct qed_ilt_client_cfg
+						  *p_cli)
+{
+	p_cli->active = false;
+	p_cli->first.val = 0;
+	p_cli->last.val = 0;
+	return p_cli;
+}
+
+static struct qed_ilt_cli_blk *qed_cxt_set_blk(struct qed_ilt_cli_blk *p_blk)
+{
+	p_blk->total_size = 0;
+	return p_blk;
+}
+
+int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *line_count)
 {
 	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
 	u32 curr_line, total, i, task_size, line;
@@ -551,7 +582,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 		   p_hwfn->my_id, p_hwfn->p_cxt_mngr->pf_start_line);
 
 	/* CDUC */
-	p_cli = &p_mngr->clients[ILT_CLI_CDUC];
+	p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_CDUC]);
+
 	curr_line = p_mngr->pf_start_line;
 
 	/* CDUC PF */
@@ -560,7 +592,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 	/* get the counters for the CDUC and QM clients  */
 	qed_cxt_cdu_iids(p_mngr, &cdu_iids);
 
-	p_blk = &p_cli->pf_blks[CDUC_BLK];
+	p_blk = qed_cxt_set_blk(&p_cli->pf_blks[CDUC_BLK]);
 
 	total = cdu_iids.pf_cids * CONN_CXT_SIZE(p_hwfn);
 
@@ -574,7 +606,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 							       ILT_CLI_CDUC);
 
 	/* CDUC VF */
-	p_blk = &p_cli->vf_blks[CDUC_BLK];
+	p_blk = qed_cxt_set_blk(&p_cli->vf_blks[CDUC_BLK]);
 	total = cdu_iids.per_vf_cids * CONN_CXT_SIZE(p_hwfn);
 
 	qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
@@ -588,7 +620,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 				     ILT_CLI_CDUC);
 
 	/* CDUT PF */
-	p_cli = &p_mngr->clients[ILT_CLI_CDUT];
+	p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_CDUT]);
 	p_cli->first.val = curr_line;
 
 	/* first the 'working' task memory */
@@ -597,7 +629,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 		if (!p_seg || p_seg->count == 0)
 			continue;
 
-		p_blk = &p_cli->pf_blks[CDUT_SEG_BLK(i)];
+		p_blk = qed_cxt_set_blk(&p_cli->pf_blks[CDUT_SEG_BLK(i)]);
 		total = p_seg->count * p_mngr->task_type_size[p_seg->type];
 		qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line, total,
 				     p_mngr->task_type_size[p_seg->type]);
@@ -612,7 +644,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 		if (!p_seg || p_seg->count == 0)
 			continue;
 
-		p_blk = &p_cli->pf_blks[CDUT_FL_SEG_BLK(i, PF)];
+		p_blk =
+		    qed_cxt_set_blk(&p_cli->pf_blks[CDUT_FL_SEG_BLK(i, PF)]);
 
 		if (!p_seg->has_fl_mem) {
 			/* The segment is active (total size pf 'working'
@@ -657,7 +690,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 		/* 'working' memory */
 		total = p_seg->count * p_mngr->task_type_size[p_seg->type];
 
-		p_blk = &p_cli->vf_blks[CDUT_SEG_BLK(0)];
+		p_blk = qed_cxt_set_blk(&p_cli->vf_blks[CDUT_SEG_BLK(0)]);
 		qed_ilt_cli_blk_fill(p_cli, p_blk,
 				     curr_line, total,
 				     p_mngr->task_type_size[p_seg->type]);
@@ -666,7 +699,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 				     ILT_CLI_CDUT);
 
 		/* 'init' memory */
-		p_blk = &p_cli->vf_blks[CDUT_FL_SEG_BLK(0, VF)];
+		p_blk =
+		    qed_cxt_set_blk(&p_cli->vf_blks[CDUT_FL_SEG_BLK(0, VF)]);
 		if (!p_seg->has_fl_mem) {
 			/* see comment above */
 			line = p_cli->vf_blks[CDUT_SEG_BLK(0)].start_line;
@@ -694,8 +728,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 	}
 
 	/* QM */
-	p_cli = &p_mngr->clients[ILT_CLI_QM];
-	p_blk = &p_cli->pf_blks[0];
+	p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_QM]);
+	p_blk = qed_cxt_set_blk(&p_cli->pf_blks[0]);
 
 	qed_cxt_qm_iids(p_hwfn, &qm_iids);
 	total = qed_qm_pf_mem_size(p_hwfn->rel_pf_id, qm_iids.cids,
@@ -719,7 +753,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 	p_cli->pf_total_lines = curr_line - p_blk->start_line;
 
 	/* SRC */
-	p_cli = &p_mngr->clients[ILT_CLI_SRC];
+	p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_SRC]);
 	qed_cxt_src_iids(p_mngr, &src_iids);
 
 	/* Both the PF and VFs searcher connections are stored in the per PF
@@ -733,7 +767,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 
 		total = roundup_pow_of_two(local_max);
 
-		p_blk = &p_cli->pf_blks[0];
+		p_blk = qed_cxt_set_blk(&p_cli->pf_blks[0]);
 		qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
 				     total * sizeof(struct src_ent),
 				     sizeof(struct src_ent));
@@ -744,11 +778,11 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 	}
 
 	/* TM PF */
-	p_cli = &p_mngr->clients[ILT_CLI_TM];
-	qed_cxt_tm_iids(p_mngr, &tm_iids);
+	p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_TM]);
+	qed_cxt_tm_iids(p_hwfn, p_mngr, &tm_iids);
 	total = tm_iids.pf_cids + tm_iids.pf_tids_total;
 	if (total) {
-		p_blk = &p_cli->pf_blks[0];
+		p_blk = qed_cxt_set_blk(&p_cli->pf_blks[0]);
 		qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
 				     total * TM_ELEM_SIZE, TM_ELEM_SIZE);
 
@@ -760,14 +794,14 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 	/* TM VF */
 	total = tm_iids.per_vf_cids + tm_iids.per_vf_tids;
 	if (total) {
-		p_blk = &p_cli->vf_blks[0];
+		p_blk = qed_cxt_set_blk(&p_cli->vf_blks[0]);
 		qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
 				     total * TM_ELEM_SIZE, TM_ELEM_SIZE);
 
 		qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
 				     ILT_CLI_TM);
-		p_cli->pf_total_lines = curr_line - p_blk->start_line;
 
+		p_cli->vf_total_lines = curr_line - p_blk->start_line;
 		for (i = 1; i < p_mngr->vf_count; i++)
 			qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
 					     ILT_CLI_TM);
@@ -777,8 +811,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 	total = qed_cxt_get_srq_count(p_hwfn);
 
 	if (total) {
-		p_cli = &p_mngr->clients[ILT_CLI_TSDM];
-		p_blk = &p_cli->pf_blks[SRQ_BLK];
+		p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_TSDM]);
+		p_blk = qed_cxt_set_blk(&p_cli->pf_blks[SRQ_BLK]);
 		qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
 				     total * SRQ_CXT_SIZE, SRQ_CXT_SIZE);
 
@@ -787,13 +821,50 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
 		p_cli->pf_total_lines = curr_line - p_blk->start_line;
 	}
 
+	*line_count = curr_line - p_hwfn->p_cxt_mngr->pf_start_line;
+
 	if (curr_line - p_hwfn->p_cxt_mngr->pf_start_line >
-	    RESC_NUM(p_hwfn, QED_ILT)) {
-		DP_ERR(p_hwfn, "too many ilt lines...#lines=%d\n",
-		       curr_line - p_hwfn->p_cxt_mngr->pf_start_line);
+	    RESC_NUM(p_hwfn, QED_ILT))
 		return -EINVAL;
+
+	return 0;
+}
+
+u32 qed_cxt_cfg_ilt_compute_excess(struct qed_hwfn *p_hwfn, u32 used_lines)
+{
+	struct qed_ilt_client_cfg *p_cli;
+	u32 excess_lines, available_lines;
+	struct qed_cxt_mngr *p_mngr;
+	u32 ilt_page_size, elem_size;
+	struct qed_tid_seg *p_seg;
+	int i;
+
+	available_lines = RESC_NUM(p_hwfn, QED_ILT);
+	excess_lines = used_lines - available_lines;
+
+	if (!excess_lines)
+		return 0;
+
+	if (p_hwfn->hw_info.personality != QED_PCI_ETH_ROCE)
+		return 0;
+
+	p_mngr = p_hwfn->p_cxt_mngr;
+	p_cli = &p_mngr->clients[ILT_CLI_CDUT];
+	ilt_page_size = ILT_PAGE_IN_BYTES(p_cli->p_size.val);
+
+	for (i = 0; i < NUM_TASK_PF_SEGMENTS; i++) {
+		p_seg = qed_cxt_tid_seg_info(p_hwfn, i);
+		if (!p_seg || p_seg->count == 0)
+			continue;
+
+		elem_size = p_mngr->task_type_size[p_seg->type];
+		if (!elem_size)
+			continue;
+
+		return (ilt_page_size / elem_size) * excess_lines;
 	}
 
+	DP_NOTICE(p_hwfn, "failed computing excess ILT lines\n");
 	return 0;
 }
 
@@ -1127,7 +1198,7 @@ int qed_cxt_mngr_alloc(struct qed_hwfn *p_hwfn)
 	clients[ILT_CLI_TSDM].first.reg = ILT_CFG_REG(TSDM, FIRST_ILT);
 	clients[ILT_CLI_TSDM].last.reg = ILT_CFG_REG(TSDM, LAST_ILT);
 	clients[ILT_CLI_TSDM].p_size.reg = ILT_CFG_REG(TSDM, P_SIZE);
-	/* default ILT page size for all clients is 32K */
+	/* default ILT page size for all clients is 64K */
 	for (i = 0; i < ILT_CLI_MAX; i++)
 		p_mngr->clients[i].p_size.val = ILT_DEFAULT_HW_P_SIZE;
 
@@ -1397,18 +1468,11 @@ void qed_qm_init_pf(struct qed_hwfn *p_hwfn)
 }
 
 /* CM PF */
-static int qed_cm_init_pf(struct qed_hwfn *p_hwfn)
+void qed_cm_init_pf(struct qed_hwfn *p_hwfn)
 {
-	union qed_qm_pq_params pq_params;
-	u16 pq;
-
 	/* XCM pure-LB queue */
-	memset(&pq_params, 0, sizeof(pq_params));
-	pq_params.core.tc = LB_TC;
-	pq = qed_get_qm_pq(p_hwfn, PROTOCOLID_CORE, &pq_params);
-	STORE_RT_REG(p_hwfn, XCM_REG_CON_PHY_Q3_RT_OFFSET, pq);
-
-	return 0;
+	STORE_RT_REG(p_hwfn, XCM_REG_CON_PHY_Q3_RT_OFFSET,
+		     qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LB));
 }
 
 /* DQ PF */
@@ -1640,7 +1704,7 @@ static void qed_tm_init_pf(struct qed_hwfn *p_hwfn)
 	u8 i;
 
 	memset(&tm_iids, 0, sizeof(tm_iids));
-	qed_cxt_tm_iids(p_mngr, &tm_iids);
+	qed_cxt_tm_iids(p_hwfn, p_mngr, &tm_iids);
 
 	/* @@@TBD No pre-scan for now */
 
@@ -1884,13 +1948,12 @@ int qed_cxt_get_cid_info(struct qed_hwfn *p_hwfn, struct qed_cxt_info *p_info)
 }
 
 static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
-				   struct qed_rdma_pf_params *p_params)
+				   struct qed_rdma_pf_params *p_params,
+				   u32 num_tasks)
 {
-	u32 num_cons, num_tasks, num_qps, num_mrs, num_srqs;
+	u32 num_cons, num_qps, num_srqs;
 	enum protocol_type proto;
 
-	num_mrs = min_t(u32, RDMA_MAX_TIDS, p_params->num_mrs);
-	num_tasks = num_mrs;	/* each mr uses a single task id */
 	num_srqs = min_t(u32, 32 * 1024, p_params->num_srqs);
 
 	switch (p_hwfn->hw_info.personality) {
@@ -1919,7 +1982,7 @@ static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
 	}
 }
 
-int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn)
+int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks)
 {
 	/* Set the number of required CORE connections */
 	u32 core_cids = 1; /* SPQ */
@@ -1931,9 +1994,10 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn)
 	switch (p_hwfn->hw_info.personality) {
 	case QED_PCI_ETH_ROCE:
 	{
-		qed_rdma_set_pf_params(p_hwfn,
-				       &p_hwfn->
-				       pf_params.rdma_pf_params);
+			qed_rdma_set_pf_params(p_hwfn,
+					       &p_hwfn->
+					       pf_params.rdma_pf_params,
+					       rdma_tasks);
 		/* no need for break since RoCE coexist with Ethernet */
 	}
 	case QED_PCI_ETH:
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.h b/drivers/net/ethernet/qlogic/qed/qed_cxt.h
index 8b010324268a..f34b2889f4bb 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.h
@@ -105,19 +105,28 @@ u32 qed_cxt_get_proto_cid_count(struct qed_hwfn *p_hwfn,
  * @brief qed_cxt_set_pf_params - Set the PF params for cxt init
  *
  * @param p_hwfn
- *
+ * @param rdma_tasks - requested maximum
  * @return int
  */
-int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn);
+int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks);
 
 /**
  * @brief qed_cxt_cfg_ilt_compute - compute ILT init parameters
  *
  * @param p_hwfn
+ * @param last_line
  *
  * @return int
  */
-int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn);
+int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *last_line);
+
+/**
+ * @brief qed_cxt_cfg_ilt_compute_excess - how many lines can be decreased
+ *
+ * @param p_hwfn
+ * @param used_lines
+ */
+u32 qed_cxt_cfg_ilt_compute_excess(struct qed_hwfn *p_hwfn, u32 used_lines);
 
 /**
  * @brief qed_cxt_mngr_alloc - Allocate and init the context manager struct
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 5bd36a4a8fcd..2fc1fde824bd 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -183,7 +183,7 @@ qed_dcbx_dp_protocol(struct qed_hwfn *p_hwfn, struct qed_dcbx_results *p_data)
 			   "%s info: update %d, enable %d, prio %d, tc %d, num_tc %d\n",
 			   qed_dcbx_app_update[i].name, p_data->arr[id].update,
 			   p_data->arr[id].enable, p_data->arr[id].priority,
-			   p_data->arr[id].tc, p_hwfn->hw_info.num_tc);
+			   p_data->arr[id].tc, p_hwfn->hw_info.num_active_tc);
 	}
 }
 
@@ -204,12 +204,8 @@ qed_dcbx_set_params(struct qed_dcbx_results *p_data,
 	p_data->arr[type].tc = tc;
 
 	/* QM reconf data */
-	if (p_info->personality == personality) {
-		if (personality == QED_PCI_ETH)
-			p_info->non_offload_tc = tc;
-		else
-			p_info->offload_tc = tc;
-	}
+	if (p_info->personality == personality)
+		p_info->offload_tc = tc;
 }
 
 /* Update app protocol data and hw_info fields with the TLV info */
@@ -376,7 +372,9 @@ static int qed_dcbx_process_mib_info(struct qed_hwfn *p_hwfn)
 	if (rc)
 		return rc;
 
-	p_info->num_tc = QED_MFW_GET_FIELD(p_ets->flags, DCBX_ETS_MAX_TCS);
+	p_info->num_active_tc = QED_MFW_GET_FIELD(p_ets->flags,
+						  DCBX_ETS_MAX_TCS);
+	p_hwfn->qm_info.ooo_tc = QED_MFW_GET_FIELD(p_ets->flags, DCBX_OOO_TC);
 	data.pf_id = p_hwfn->rel_pf_id;
 	data.dcbx_enabled = !!dcbx_version;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
index 0fabe97f998d..2eb988fe1298 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
@@ -85,9 +85,6 @@ struct qed_dcbx_app_metadata {
 	enum qed_pci_personality personality;
 };
 
-#define QED_MFW_GET_FIELD(name, field) \
-	(((name) & (field ## _MASK)) >> (field ## _SHIFT))
-
 struct qed_dcbx_info {
 	struct lldp_status_params_s lldp_remote[LLDP_MAX_LLDP_AGENTS];
 	struct lldp_config_params_s lldp_local[LLDP_MAX_LLDP_AGENTS];
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 68f19ca57f96..483241b4b05d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -17,7 +17,6 @@
 
 /* Chip IDs enum */
 enum chip_ids {
-	CHIP_RESERVED,
 	CHIP_BB_B0,
 	CHIP_K2,
 	MAX_CHIP_IDS
@@ -40,6 +39,7 @@ enum mem_groups {
 	MEM_GROUP_BTB_RAM,
 	MEM_GROUP_RDIF_CTX,
 	MEM_GROUP_TDIF_CTX,
+	MEM_GROUP_CFC_MEM,
 	MEM_GROUP_CONN_CFC_MEM,
 	MEM_GROUP_TASK_CFC_MEM,
 	MEM_GROUP_CAU_PI,
@@ -72,6 +72,7 @@ static const char * const s_mem_group_names[] = {
 	"BTB_RAM",
 	"RDIF_CTX",
 	"TDIF_CTX",
+	"CFC_MEM",
 	"CONN_CFC_MEM",
 	"TASK_CFC_MEM",
 	"CAU_PI",
@@ -185,13 +186,16 @@ struct dbg_array {
 	u32 size_in_dwords;
 };
 
+struct chip_platform_defs {
+	u8 num_ports;
+	u8 num_pfs;
+	u8 num_vfs;
+};
+
 /* Chip constant definitions */
 struct chip_defs {
 	const char *name;
-	struct {
-		u8 num_ports;
-		u8 num_pfs;
-	} per_platform[MAX_PLATFORM_IDS];
+	struct chip_platform_defs per_platform[MAX_PLATFORM_IDS];
 };
 
 /* Platform constant definitions */
@@ -405,22 +409,23 @@ struct phy_defs {
 /***************************** Constant Arrays *******************************/
 
 /* Debug arrays */
-static struct dbg_array s_dbg_arrays[MAX_BIN_DBG_BUFFER_TYPE] = { {NULL} };
+static struct dbg_array s_dbg_arrays[MAX_BIN_DBG_BUFFER_TYPE] = { {0} };
 
 /* Chip constant definitions array */
 static struct chip_defs s_chip_defs[MAX_CHIP_IDS] = {
-	{ "reserved", { {0, 0}, {0, 0}, {0, 0}, {0, 0} } },
 	{ "bb_b0",
-	  { {MAX_NUM_PORTS_BB, MAX_NUM_PFS_BB}, {0, 0}, {0, 0}, {0, 0} } },
-	{ "k2", { {MAX_NUM_PORTS_K2, MAX_NUM_PFS_K2}, {0, 0}, {0, 0}, {0, 0} } }
+	  { {MAX_NUM_PORTS_BB, MAX_NUM_PFS_BB, MAX_NUM_VFS_BB}, {0, 0, 0},
+	    {0, 0, 0}, {0, 0, 0} } },
+	{ "k2",
+	  { {MAX_NUM_PORTS_K2, MAX_NUM_PFS_K2, MAX_NUM_VFS_K2}, {0, 0, 0},
+	    {0, 0, 0}, {0, 0, 0} } }
 };
 
 /* Storm constant definitions array */
 static struct storm_defs s_storm_defs[] = {
 	/* Tstorm */
 	{'T', BLOCK_TSEM,
-	 {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT,
-	  DBG_BUS_CLIENT_RBCT}, true,
+	 {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, true,
 	 TSEM_REG_FAST_MEMORY,
 	 TSEM_REG_DBG_FRAME_MODE, TSEM_REG_SLOW_DBG_ACTIVE,
 	 TSEM_REG_SLOW_DBG_MODE, TSEM_REG_DBG_MODE1_CFG,
@@ -432,8 +437,7 @@ static struct storm_defs s_storm_defs[] = {
 	 4, TCM_REG_SM_TASK_CTX},
 	/* Mstorm */
 	{'M', BLOCK_MSEM,
-	 {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT,
-	  DBG_BUS_CLIENT_RBCM}, false,
+	 {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, false,
 	 MSEM_REG_FAST_MEMORY,
 	 MSEM_REG_DBG_FRAME_MODE, MSEM_REG_SLOW_DBG_ACTIVE,
 	 MSEM_REG_SLOW_DBG_MODE, MSEM_REG_DBG_MODE1_CFG,
@@ -445,8 +449,7 @@ static struct storm_defs s_storm_defs[] = {
 	 7, MCM_REG_SM_TASK_CTX},
 	/* Ustorm */
 	{'U', BLOCK_USEM,
-	 {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU,
-	  DBG_BUS_CLIENT_RBCU}, false,
+	 {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, false,
 	 USEM_REG_FAST_MEMORY,
 	 USEM_REG_DBG_FRAME_MODE, USEM_REG_SLOW_DBG_ACTIVE,
 	 USEM_REG_SLOW_DBG_MODE, USEM_REG_DBG_MODE1_CFG,
@@ -458,8 +461,7 @@ static struct storm_defs s_storm_defs[] = {
 	 3, UCM_REG_SM_TASK_CTX},
 	/* Xstorm */
 	{'X', BLOCK_XSEM,
-	 {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX,
-	  DBG_BUS_CLIENT_RBCX}, false,
+	 {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, false,
 	 XSEM_REG_FAST_MEMORY,
 	 XSEM_REG_DBG_FRAME_MODE, XSEM_REG_SLOW_DBG_ACTIVE,
 	 XSEM_REG_SLOW_DBG_MODE, XSEM_REG_DBG_MODE1_CFG,
@@ -471,8 +473,7 @@ static struct storm_defs s_storm_defs[] = {
 	 0, 0},
 	/* Ystorm */
 	{'Y', BLOCK_YSEM,
-	 {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX,
-	  DBG_BUS_CLIENT_RBCY}, false,
+	 {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, false,
 	 YSEM_REG_FAST_MEMORY,
 	 YSEM_REG_DBG_FRAME_MODE, YSEM_REG_SLOW_DBG_ACTIVE,
 	 YSEM_REG_SLOW_DBG_MODE, YSEM_REG_DBG_MODE1_CFG,
@@ -484,8 +485,7 @@ static struct storm_defs s_storm_defs[] = {
 	 12, YCM_REG_SM_TASK_CTX},
 	/* Pstorm */
 	{'P', BLOCK_PSEM,
-	 {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS,
-	  DBG_BUS_CLIENT_RBCS}, true,
+	 {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, true,
 	 PSEM_REG_FAST_MEMORY,
 	 PSEM_REG_DBG_FRAME_MODE, PSEM_REG_SLOW_DBG_ACTIVE,
 	 PSEM_REG_SLOW_DBG_MODE, PSEM_REG_DBG_MODE1_CFG,
@@ -499,8 +499,9 @@ static struct storm_defs s_storm_defs[] = {
 
 /* Block definitions array */
 static struct block_defs block_grc_defs = {
-	"grc", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN},
+	"grc",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN},
 	GRC_REG_DBG_SELECT, GRC_REG_DBG_DWORD_ENABLE,
 	GRC_REG_DBG_SHIFT, GRC_REG_DBG_FORCE_VALID,
 	GRC_REG_DBG_FORCE_FRAME,
@@ -508,29 +509,30 @@ static struct block_defs block_grc_defs = {
 };
 
 static struct block_defs block_miscs_defs = {
-	"miscs", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"miscs", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	false, false, MAX_DBG_RESET_REGS, 0
 };
 
 static struct block_defs block_misc_defs = {
-	"misc", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"misc", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	false, false, MAX_DBG_RESET_REGS, 0
 };
 
 static struct block_defs block_dbu_defs = {
-	"dbu", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"dbu", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	false, false, MAX_DBG_RESET_REGS, 0
 };
 
 static struct block_defs block_pglue_b_defs = {
-	"pglue_b", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH},
+	"pglue_b",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH},
 	PGLUE_B_REG_DBG_SELECT, PGLUE_B_REG_DBG_DWORD_ENABLE,
 	PGLUE_B_REG_DBG_SHIFT, PGLUE_B_REG_DBG_FORCE_VALID,
 	PGLUE_B_REG_DBG_FORCE_FRAME,
@@ -538,8 +540,9 @@ static struct block_defs block_pglue_b_defs = {
 };
 
 static struct block_defs block_cnig_defs = {
-	"cnig", {false, false, true}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW},
+	"cnig",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW},
 	CNIG_REG_DBG_SELECT_K2, CNIG_REG_DBG_DWORD_ENABLE_K2,
 	CNIG_REG_DBG_SHIFT_K2, CNIG_REG_DBG_FORCE_VALID_K2,
 	CNIG_REG_DBG_FORCE_FRAME_K2,
@@ -547,15 +550,16 @@ static struct block_defs block_cnig_defs = {
 };
 
 static struct block_defs block_cpmu_defs = {
-	"cpmu", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"cpmu", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	true, false, DBG_RESET_REG_MISCS_PL_HV, 8
 };
 
 static struct block_defs block_ncsi_defs = {
-	"ncsi", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ},
+	"ncsi",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ},
 	NCSI_REG_DBG_SELECT, NCSI_REG_DBG_DWORD_ENABLE,
 	NCSI_REG_DBG_SHIFT, NCSI_REG_DBG_FORCE_VALID,
 	NCSI_REG_DBG_FORCE_FRAME,
@@ -563,15 +567,16 @@ static struct block_defs block_ncsi_defs = {
 };
 
 static struct block_defs block_opte_defs = {
-	"opte", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"opte", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	true, false, DBG_RESET_REG_MISCS_PL_HV, 4
 };
 
 static struct block_defs block_bmb_defs = {
-	"bmb", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCB},
+	"bmb",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCB},
 	BMB_REG_DBG_SELECT, BMB_REG_DBG_DWORD_ENABLE,
 	BMB_REG_DBG_SHIFT, BMB_REG_DBG_FORCE_VALID,
 	BMB_REG_DBG_FORCE_FRAME,
@@ -579,8 +584,9 @@ static struct block_defs block_bmb_defs = {
 };
 
 static struct block_defs block_pcie_defs = {
-	"pcie", {false, false, true}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
+	"pcie",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
 	PCIE_REG_DBG_COMMON_SELECT, PCIE_REG_DBG_COMMON_DWORD_ENABLE,
 	PCIE_REG_DBG_COMMON_SHIFT, PCIE_REG_DBG_COMMON_FORCE_VALID,
 	PCIE_REG_DBG_COMMON_FORCE_FRAME,
@@ -588,15 +594,16 @@ static struct block_defs block_pcie_defs = {
 };
 
 static struct block_defs block_mcp_defs = {
-	"mcp", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"mcp", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	false, false, MAX_DBG_RESET_REGS, 0
 };
 
 static struct block_defs block_mcp2_defs = {
-	"mcp2", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ},
+	"mcp2",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ},
 	MCP2_REG_DBG_SELECT, MCP2_REG_DBG_DWORD_ENABLE,
 	MCP2_REG_DBG_SHIFT, MCP2_REG_DBG_FORCE_VALID,
 	MCP2_REG_DBG_FORCE_FRAME,
@@ -604,8 +611,9 @@ static struct block_defs block_mcp2_defs = {
 };
 
 static struct block_defs block_pswhst_defs = {
-	"pswhst", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"pswhst",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	PSWHST_REG_DBG_SELECT, PSWHST_REG_DBG_DWORD_ENABLE,
 	PSWHST_REG_DBG_SHIFT, PSWHST_REG_DBG_FORCE_VALID,
 	PSWHST_REG_DBG_FORCE_FRAME,
@@ -613,8 +621,9 @@ static struct block_defs block_pswhst_defs = {
 };
 
 static struct block_defs block_pswhst2_defs = {
-	"pswhst2", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"pswhst2",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	PSWHST2_REG_DBG_SELECT, PSWHST2_REG_DBG_DWORD_ENABLE,
 	PSWHST2_REG_DBG_SHIFT, PSWHST2_REG_DBG_FORCE_VALID,
 	PSWHST2_REG_DBG_FORCE_FRAME,
@@ -622,8 +631,9 @@ static struct block_defs block_pswhst2_defs = {
 };
 
 static struct block_defs block_pswrd_defs = {
-	"pswrd", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"pswrd",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	PSWRD_REG_DBG_SELECT, PSWRD_REG_DBG_DWORD_ENABLE,
 	PSWRD_REG_DBG_SHIFT, PSWRD_REG_DBG_FORCE_VALID,
 	PSWRD_REG_DBG_FORCE_FRAME,
@@ -631,8 +641,9 @@ static struct block_defs block_pswrd_defs = {
 };
 
 static struct block_defs block_pswrd2_defs = {
-	"pswrd2", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"pswrd2",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	PSWRD2_REG_DBG_SELECT, PSWRD2_REG_DBG_DWORD_ENABLE,
 	PSWRD2_REG_DBG_SHIFT, PSWRD2_REG_DBG_FORCE_VALID,
 	PSWRD2_REG_DBG_FORCE_FRAME,
@@ -640,8 +651,9 @@ static struct block_defs block_pswrd2_defs = {
 };
 
 static struct block_defs block_pswwr_defs = {
-	"pswwr", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"pswwr",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	PSWWR_REG_DBG_SELECT, PSWWR_REG_DBG_DWORD_ENABLE,
 	PSWWR_REG_DBG_SHIFT, PSWWR_REG_DBG_FORCE_VALID,
 	PSWWR_REG_DBG_FORCE_FRAME,
@@ -649,15 +661,16 @@ static struct block_defs block_pswwr_defs = {
 };
 
 static struct block_defs block_pswwr2_defs = {
-	"pswwr2", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"pswwr2", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	true, false, DBG_RESET_REG_MISC_PL_HV, 3
 };
 
 static struct block_defs block_pswrq_defs = {
-	"pswrq", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"pswrq",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	PSWRQ_REG_DBG_SELECT, PSWRQ_REG_DBG_DWORD_ENABLE,
 	PSWRQ_REG_DBG_SHIFT, PSWRQ_REG_DBG_FORCE_VALID,
 	PSWRQ_REG_DBG_FORCE_FRAME,
@@ -665,8 +678,9 @@ static struct block_defs block_pswrq_defs = {
 };
 
 static struct block_defs block_pswrq2_defs = {
-	"pswrq2", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"pswrq2",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	PSWRQ2_REG_DBG_SELECT, PSWRQ2_REG_DBG_DWORD_ENABLE,
 	PSWRQ2_REG_DBG_SHIFT, PSWRQ2_REG_DBG_FORCE_VALID,
 	PSWRQ2_REG_DBG_FORCE_FRAME,
@@ -674,8 +688,9 @@ static struct block_defs block_pswrq2_defs = {
 };
 
 static struct block_defs block_pglcs_defs = {
-	"pglcs", {false, false, true}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
+	"pglcs",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
 	PGLCS_REG_DBG_SELECT, PGLCS_REG_DBG_DWORD_ENABLE,
 	PGLCS_REG_DBG_SHIFT, PGLCS_REG_DBG_FORCE_VALID,
 	PGLCS_REG_DBG_FORCE_FRAME,
@@ -683,8 +698,9 @@ static struct block_defs block_pglcs_defs = {
 };
 
 static struct block_defs block_ptu_defs = {
-	"ptu", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"ptu",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	PTU_REG_DBG_SELECT, PTU_REG_DBG_DWORD_ENABLE,
 	PTU_REG_DBG_SHIFT, PTU_REG_DBG_FORCE_VALID,
 	PTU_REG_DBG_FORCE_FRAME,
@@ -692,8 +708,9 @@ static struct block_defs block_ptu_defs = {
 };
 
 static struct block_defs block_dmae_defs = {
-	"dmae", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"dmae",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	DMAE_REG_DBG_SELECT, DMAE_REG_DBG_DWORD_ENABLE,
 	DMAE_REG_DBG_SHIFT, DMAE_REG_DBG_FORCE_VALID,
 	DMAE_REG_DBG_FORCE_FRAME,
@@ -701,8 +718,9 @@ static struct block_defs block_dmae_defs = {
 };
 
 static struct block_defs block_tcm_defs = {
-	"tcm", {true, true, true}, true, DBG_TSTORM_ID,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
+	"tcm",
+	{true, true}, true, DBG_TSTORM_ID,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
 	TCM_REG_DBG_SELECT, TCM_REG_DBG_DWORD_ENABLE,
 	TCM_REG_DBG_SHIFT, TCM_REG_DBG_FORCE_VALID,
 	TCM_REG_DBG_FORCE_FRAME,
@@ -710,8 +728,9 @@ static struct block_defs block_tcm_defs = {
 };
 
 static struct block_defs block_mcm_defs = {
-	"mcm", {true, true, true}, true, DBG_MSTORM_ID,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+	"mcm",
+	{true, true}, true, DBG_MSTORM_ID,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
 	MCM_REG_DBG_SELECT, MCM_REG_DBG_DWORD_ENABLE,
 	MCM_REG_DBG_SHIFT, MCM_REG_DBG_FORCE_VALID,
 	MCM_REG_DBG_FORCE_FRAME,
@@ -719,8 +738,9 @@ static struct block_defs block_mcm_defs = {
 };
 
 static struct block_defs block_ucm_defs = {
-	"ucm", {true, true, true}, true, DBG_USTORM_ID,
-	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
+	"ucm",
+	{true, true}, true, DBG_USTORM_ID,
+	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
 	UCM_REG_DBG_SELECT, UCM_REG_DBG_DWORD_ENABLE,
 	UCM_REG_DBG_SHIFT, UCM_REG_DBG_FORCE_VALID,
 	UCM_REG_DBG_FORCE_FRAME,
@@ -728,8 +748,9 @@ static struct block_defs block_ucm_defs = {
 };
 
 static struct block_defs block_xcm_defs = {
-	"xcm", {true, true, true}, true, DBG_XSTORM_ID,
-	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
+	"xcm",
+	{true, true}, true, DBG_XSTORM_ID,
+	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
 	XCM_REG_DBG_SELECT, XCM_REG_DBG_DWORD_ENABLE,
 	XCM_REG_DBG_SHIFT, XCM_REG_DBG_FORCE_VALID,
 	XCM_REG_DBG_FORCE_FRAME,
@@ -737,8 +758,9 @@ static struct block_defs block_xcm_defs = {
 };
 
 static struct block_defs block_ycm_defs = {
-	"ycm", {true, true, true}, true, DBG_YSTORM_ID,
-	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
+	"ycm",
+	{true, true}, true, DBG_YSTORM_ID,
+	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
 	YCM_REG_DBG_SELECT, YCM_REG_DBG_DWORD_ENABLE,
 	YCM_REG_DBG_SHIFT, YCM_REG_DBG_FORCE_VALID,
 	YCM_REG_DBG_FORCE_FRAME,
@@ -746,8 +768,9 @@ static struct block_defs block_ycm_defs = {
 };
 
 static struct block_defs block_pcm_defs = {
-	"pcm", {true, true, true}, true, DBG_PSTORM_ID,
-	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
+	"pcm",
+	{true, true}, true, DBG_PSTORM_ID,
+	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
 	PCM_REG_DBG_SELECT, PCM_REG_DBG_DWORD_ENABLE,
 	PCM_REG_DBG_SHIFT, PCM_REG_DBG_FORCE_VALID,
 	PCM_REG_DBG_FORCE_FRAME,
@@ -755,8 +778,9 @@ static struct block_defs block_pcm_defs = {
 };
 
 static struct block_defs block_qm_defs = {
-	"qm", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCQ},
+	"qm",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCQ},
 	QM_REG_DBG_SELECT, QM_REG_DBG_DWORD_ENABLE,
 	QM_REG_DBG_SHIFT, QM_REG_DBG_FORCE_VALID,
 	QM_REG_DBG_FORCE_FRAME,
@@ -764,8 +788,9 @@ static struct block_defs block_qm_defs = {
 };
 
 static struct block_defs block_tm_defs = {
-	"tm", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
+	"tm",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
 	TM_REG_DBG_SELECT, TM_REG_DBG_DWORD_ENABLE,
 	TM_REG_DBG_SHIFT, TM_REG_DBG_FORCE_VALID,
 	TM_REG_DBG_FORCE_FRAME,
@@ -773,8 +798,9 @@ static struct block_defs block_tm_defs = {
 };
 
 static struct block_defs block_dorq_defs = {
-	"dorq", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
+	"dorq",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
 	DORQ_REG_DBG_SELECT, DORQ_REG_DBG_DWORD_ENABLE,
 	DORQ_REG_DBG_SHIFT, DORQ_REG_DBG_FORCE_VALID,
 	DORQ_REG_DBG_FORCE_FRAME,
@@ -782,8 +808,9 @@ static struct block_defs block_dorq_defs = {
 };
 
 static struct block_defs block_brb_defs = {
-	"brb", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR},
+	"brb",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR},
 	BRB_REG_DBG_SELECT, BRB_REG_DBG_DWORD_ENABLE,
 	BRB_REG_DBG_SHIFT, BRB_REG_DBG_FORCE_VALID,
 	BRB_REG_DBG_FORCE_FRAME,
@@ -791,8 +818,9 @@ static struct block_defs block_brb_defs = {
 };
 
 static struct block_defs block_src_defs = {
-	"src", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
+	"src",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
 	SRC_REG_DBG_SELECT, SRC_REG_DBG_DWORD_ENABLE,
 	SRC_REG_DBG_SHIFT, SRC_REG_DBG_FORCE_VALID,
 	SRC_REG_DBG_FORCE_FRAME,
@@ -800,8 +828,9 @@ static struct block_defs block_src_defs = {
 };
 
 static struct block_defs block_prs_defs = {
-	"prs", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR},
+	"prs",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR},
 	PRS_REG_DBG_SELECT, PRS_REG_DBG_DWORD_ENABLE,
 	PRS_REG_DBG_SHIFT, PRS_REG_DBG_FORCE_VALID,
 	PRS_REG_DBG_FORCE_FRAME,
@@ -809,8 +838,9 @@ static struct block_defs block_prs_defs = {
 };
 
 static struct block_defs block_tsdm_defs = {
-	"tsdm", {true, true, true}, true, DBG_TSTORM_ID,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
+	"tsdm",
+	{true, true}, true, DBG_TSTORM_ID,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
 	TSDM_REG_DBG_SELECT, TSDM_REG_DBG_DWORD_ENABLE,
 	TSDM_REG_DBG_SHIFT, TSDM_REG_DBG_FORCE_VALID,
 	TSDM_REG_DBG_FORCE_FRAME,
@@ -818,8 +848,9 @@ static struct block_defs block_tsdm_defs = {
 };
 
 static struct block_defs block_msdm_defs = {
-	"msdm", {true, true, true}, true, DBG_MSTORM_ID,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+	"msdm",
+	{true, true}, true, DBG_MSTORM_ID,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
 	MSDM_REG_DBG_SELECT, MSDM_REG_DBG_DWORD_ENABLE,
 	MSDM_REG_DBG_SHIFT, MSDM_REG_DBG_FORCE_VALID,
 	MSDM_REG_DBG_FORCE_FRAME,
@@ -827,8 +858,9 @@ static struct block_defs block_msdm_defs = {
 };
 
 static struct block_defs block_usdm_defs = {
-	"usdm", {true, true, true}, true, DBG_USTORM_ID,
-	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
+	"usdm",
+	{true, true}, true, DBG_USTORM_ID,
+	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
 	USDM_REG_DBG_SELECT, USDM_REG_DBG_DWORD_ENABLE,
 	USDM_REG_DBG_SHIFT, USDM_REG_DBG_FORCE_VALID,
 	USDM_REG_DBG_FORCE_FRAME,
@@ -836,8 +868,9 @@ static struct block_defs block_usdm_defs = {
 };
 
 static struct block_defs block_xsdm_defs = {
-	"xsdm", {true, true, true}, true, DBG_XSTORM_ID,
-	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
+	"xsdm",
+	{true, true}, true, DBG_XSTORM_ID,
+	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
 	XSDM_REG_DBG_SELECT, XSDM_REG_DBG_DWORD_ENABLE,
 	XSDM_REG_DBG_SHIFT, XSDM_REG_DBG_FORCE_VALID,
 	XSDM_REG_DBG_FORCE_FRAME,
@@ -845,8 +878,9 @@ static struct block_defs block_xsdm_defs = {
 };
 
 static struct block_defs block_ysdm_defs = {
-	"ysdm", {true, true, true}, true, DBG_YSTORM_ID,
-	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
+	"ysdm",
+	{true, true}, true, DBG_YSTORM_ID,
+	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
 	YSDM_REG_DBG_SELECT, YSDM_REG_DBG_DWORD_ENABLE,
 	YSDM_REG_DBG_SHIFT, YSDM_REG_DBG_FORCE_VALID,
 	YSDM_REG_DBG_FORCE_FRAME,
@@ -854,8 +888,9 @@ static struct block_defs block_ysdm_defs = {
 };
 
 static struct block_defs block_psdm_defs = {
-	"psdm", {true, true, true}, true, DBG_PSTORM_ID,
-	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
+	"psdm",
+	{true, true}, true, DBG_PSTORM_ID,
+	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
 	PSDM_REG_DBG_SELECT, PSDM_REG_DBG_DWORD_ENABLE,
 	PSDM_REG_DBG_SHIFT, PSDM_REG_DBG_FORCE_VALID,
 	PSDM_REG_DBG_FORCE_FRAME,
@@ -863,8 +898,9 @@ static struct block_defs block_psdm_defs = {
 };
 
 static struct block_defs block_tsem_defs = {
-	"tsem", {true, true, true}, true, DBG_TSTORM_ID,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
+	"tsem",
+	{true, true}, true, DBG_TSTORM_ID,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
 	TSEM_REG_DBG_SELECT, TSEM_REG_DBG_DWORD_ENABLE,
 	TSEM_REG_DBG_SHIFT, TSEM_REG_DBG_FORCE_VALID,
 	TSEM_REG_DBG_FORCE_FRAME,
@@ -872,8 +908,9 @@ static struct block_defs block_tsem_defs = {
 };
 
 static struct block_defs block_msem_defs = {
-	"msem", {true, true, true}, true, DBG_MSTORM_ID,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+	"msem",
+	{true, true}, true, DBG_MSTORM_ID,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
 	MSEM_REG_DBG_SELECT, MSEM_REG_DBG_DWORD_ENABLE,
 	MSEM_REG_DBG_SHIFT, MSEM_REG_DBG_FORCE_VALID,
 	MSEM_REG_DBG_FORCE_FRAME,
@@ -881,8 +918,9 @@ static struct block_defs block_msem_defs = {
 };
 
 static struct block_defs block_usem_defs = {
-	"usem", {true, true, true}, true, DBG_USTORM_ID,
-	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
+	"usem",
+	{true, true}, true, DBG_USTORM_ID,
+	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
 	USEM_REG_DBG_SELECT, USEM_REG_DBG_DWORD_ENABLE,
 	USEM_REG_DBG_SHIFT, USEM_REG_DBG_FORCE_VALID,
 	USEM_REG_DBG_FORCE_FRAME,
@@ -890,8 +928,9 @@ static struct block_defs block_usem_defs = {
 };
 
 static struct block_defs block_xsem_defs = {
-	"xsem", {true, true, true}, true, DBG_XSTORM_ID,
-	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
+	"xsem",
+	{true, true}, true, DBG_XSTORM_ID,
+	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
 	XSEM_REG_DBG_SELECT, XSEM_REG_DBG_DWORD_ENABLE,
 	XSEM_REG_DBG_SHIFT, XSEM_REG_DBG_FORCE_VALID,
 	XSEM_REG_DBG_FORCE_FRAME,
@@ -899,8 +938,9 @@ static struct block_defs block_xsem_defs = {
 };
 
 static struct block_defs block_ysem_defs = {
-	"ysem", {true, true, true}, true, DBG_YSTORM_ID,
-	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
+	"ysem",
+	{true, true}, true, DBG_YSTORM_ID,
+	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
 	YSEM_REG_DBG_SELECT, YSEM_REG_DBG_DWORD_ENABLE,
 	YSEM_REG_DBG_SHIFT, YSEM_REG_DBG_FORCE_VALID,
 	YSEM_REG_DBG_FORCE_FRAME,
@@ -908,8 +948,9 @@ static struct block_defs block_ysem_defs = {
 };
 
 static struct block_defs block_psem_defs = {
-	"psem", {true, true, true}, true, DBG_PSTORM_ID,
-	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
+	"psem",
+	{true, true}, true, DBG_PSTORM_ID,
+	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
 	PSEM_REG_DBG_SELECT, PSEM_REG_DBG_DWORD_ENABLE,
 	PSEM_REG_DBG_SHIFT, PSEM_REG_DBG_FORCE_VALID,
 	PSEM_REG_DBG_FORCE_FRAME,
@@ -917,8 +958,9 @@ static struct block_defs block_psem_defs = {
 };
 
 static struct block_defs block_rss_defs = {
-	"rss", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
+	"rss",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
 	RSS_REG_DBG_SELECT, RSS_REG_DBG_DWORD_ENABLE,
 	RSS_REG_DBG_SHIFT, RSS_REG_DBG_FORCE_VALID,
 	RSS_REG_DBG_FORCE_FRAME,
@@ -926,8 +968,9 @@ static struct block_defs block_rss_defs = {
 };
 
 static struct block_defs block_tmld_defs = {
-	"tmld", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+	"tmld",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
 	TMLD_REG_DBG_SELECT, TMLD_REG_DBG_DWORD_ENABLE,
 	TMLD_REG_DBG_SHIFT, TMLD_REG_DBG_FORCE_VALID,
 	TMLD_REG_DBG_FORCE_FRAME,
@@ -935,8 +978,9 @@ static struct block_defs block_tmld_defs = {
 };
 
 static struct block_defs block_muld_defs = {
-	"muld", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
+	"muld",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
 	MULD_REG_DBG_SELECT, MULD_REG_DBG_DWORD_ENABLE,
 	MULD_REG_DBG_SHIFT, MULD_REG_DBG_FORCE_VALID,
 	MULD_REG_DBG_FORCE_FRAME,
@@ -944,8 +988,9 @@ static struct block_defs block_muld_defs = {
 };
 
 static struct block_defs block_yuld_defs = {
-	"yuld", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
+	"yuld",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
 	YULD_REG_DBG_SELECT, YULD_REG_DBG_DWORD_ENABLE,
 	YULD_REG_DBG_SHIFT, YULD_REG_DBG_FORCE_VALID,
 	YULD_REG_DBG_FORCE_FRAME,
@@ -953,8 +998,9 @@ static struct block_defs block_yuld_defs = {
 };
 
 static struct block_defs block_xyld_defs = {
-	"xyld", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
+	"xyld",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
 	XYLD_REG_DBG_SELECT, XYLD_REG_DBG_DWORD_ENABLE,
 	XYLD_REG_DBG_SHIFT, XYLD_REG_DBG_FORCE_VALID,
 	XYLD_REG_DBG_FORCE_FRAME,
@@ -962,8 +1008,9 @@ static struct block_defs block_xyld_defs = {
 };
 
 static struct block_defs block_prm_defs = {
-	"prm", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+	"prm",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
 	PRM_REG_DBG_SELECT, PRM_REG_DBG_DWORD_ENABLE,
 	PRM_REG_DBG_SHIFT, PRM_REG_DBG_FORCE_VALID,
 	PRM_REG_DBG_FORCE_FRAME,
@@ -971,8 +1018,9 @@ static struct block_defs block_prm_defs = {
 };
 
 static struct block_defs block_pbf_pb1_defs = {
-	"pbf_pb1", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
+	"pbf_pb1",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
 	PBF_PB1_REG_DBG_SELECT, PBF_PB1_REG_DBG_DWORD_ENABLE,
 	PBF_PB1_REG_DBG_SHIFT, PBF_PB1_REG_DBG_FORCE_VALID,
 	PBF_PB1_REG_DBG_FORCE_FRAME,
@@ -981,8 +1029,9 @@ static struct block_defs block_pbf_pb1_defs = {
 };
 
 static struct block_defs block_pbf_pb2_defs = {
-	"pbf_pb2", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
+	"pbf_pb2",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
 	PBF_PB2_REG_DBG_SELECT, PBF_PB2_REG_DBG_DWORD_ENABLE,
 	PBF_PB2_REG_DBG_SHIFT, PBF_PB2_REG_DBG_FORCE_VALID,
 	PBF_PB2_REG_DBG_FORCE_FRAME,
@@ -991,8 +1040,9 @@ static struct block_defs block_pbf_pb2_defs = {
 };
 
 static struct block_defs block_rpb_defs = {
-	"rpb", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+	"rpb",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
 	RPB_REG_DBG_SELECT, RPB_REG_DBG_DWORD_ENABLE,
 	RPB_REG_DBG_SHIFT, RPB_REG_DBG_FORCE_VALID,
 	RPB_REG_DBG_FORCE_FRAME,
@@ -1000,8 +1050,9 @@ static struct block_defs block_rpb_defs = {
 };
 
 static struct block_defs block_btb_defs = {
-	"btb", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCV},
+	"btb",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCV},
 	BTB_REG_DBG_SELECT, BTB_REG_DBG_DWORD_ENABLE,
 	BTB_REG_DBG_SHIFT, BTB_REG_DBG_FORCE_VALID,
 	BTB_REG_DBG_FORCE_FRAME,
@@ -1009,8 +1060,9 @@ static struct block_defs block_btb_defs = {
 };
 
 static struct block_defs block_pbf_defs = {
-	"pbf", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
+	"pbf",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
 	PBF_REG_DBG_SELECT, PBF_REG_DBG_DWORD_ENABLE,
 	PBF_REG_DBG_SHIFT, PBF_REG_DBG_FORCE_VALID,
 	PBF_REG_DBG_FORCE_FRAME,
@@ -1018,8 +1070,9 @@ static struct block_defs block_pbf_defs = {
 };
 
 static struct block_defs block_rdif_defs = {
-	"rdif", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+	"rdif",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
 	RDIF_REG_DBG_SELECT, RDIF_REG_DBG_DWORD_ENABLE,
 	RDIF_REG_DBG_SHIFT, RDIF_REG_DBG_FORCE_VALID,
 	RDIF_REG_DBG_FORCE_FRAME,
@@ -1027,8 +1080,9 @@ static struct block_defs block_rdif_defs = {
 };
 
 static struct block_defs block_tdif_defs = {
-	"tdif", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
+	"tdif",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
 	TDIF_REG_DBG_SELECT, TDIF_REG_DBG_DWORD_ENABLE,
 	TDIF_REG_DBG_SHIFT, TDIF_REG_DBG_FORCE_VALID,
 	TDIF_REG_DBG_FORCE_FRAME,
@@ -1036,8 +1090,9 @@ static struct block_defs block_tdif_defs = {
 };
 
 static struct block_defs block_cdu_defs = {
-	"cdu", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
+	"cdu",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
 	CDU_REG_DBG_SELECT, CDU_REG_DBG_DWORD_ENABLE,
 	CDU_REG_DBG_SHIFT, CDU_REG_DBG_FORCE_VALID,
 	CDU_REG_DBG_FORCE_FRAME,
@@ -1045,8 +1100,9 @@ static struct block_defs block_cdu_defs = {
 };
 
 static struct block_defs block_ccfc_defs = {
-	"ccfc", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
+	"ccfc",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
 	CCFC_REG_DBG_SELECT, CCFC_REG_DBG_DWORD_ENABLE,
 	CCFC_REG_DBG_SHIFT, CCFC_REG_DBG_FORCE_VALID,
 	CCFC_REG_DBG_FORCE_FRAME,
@@ -1054,8 +1110,9 @@ static struct block_defs block_ccfc_defs = {
 };
 
 static struct block_defs block_tcfc_defs = {
-	"tcfc", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
+	"tcfc",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
 	TCFC_REG_DBG_SELECT, TCFC_REG_DBG_DWORD_ENABLE,
 	TCFC_REG_DBG_SHIFT, TCFC_REG_DBG_FORCE_VALID,
 	TCFC_REG_DBG_FORCE_FRAME,
@@ -1063,8 +1120,9 @@ static struct block_defs block_tcfc_defs = {
 };
 
 static struct block_defs block_igu_defs = {
-	"igu", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"igu",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	IGU_REG_DBG_SELECT, IGU_REG_DBG_DWORD_ENABLE,
 	IGU_REG_DBG_SHIFT, IGU_REG_DBG_FORCE_VALID,
 	IGU_REG_DBG_FORCE_FRAME,
@@ -1072,8 +1130,9 @@ static struct block_defs block_igu_defs = {
 };
 
 static struct block_defs block_cau_defs = {
-	"cau", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+	"cau",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
 	CAU_REG_DBG_SELECT, CAU_REG_DBG_DWORD_ENABLE,
 	CAU_REG_DBG_SHIFT, CAU_REG_DBG_FORCE_VALID,
 	CAU_REG_DBG_FORCE_FRAME,
@@ -1081,8 +1140,9 @@ static struct block_defs block_cau_defs = {
 };
 
 static struct block_defs block_umac_defs = {
-	"umac", {false, false, true}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ},
+	"umac",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ},
 	UMAC_REG_DBG_SELECT, UMAC_REG_DBG_DWORD_ENABLE,
 	UMAC_REG_DBG_SHIFT, UMAC_REG_DBG_FORCE_VALID,
 	UMAC_REG_DBG_FORCE_FRAME,
@@ -1090,22 +1150,23 @@ static struct block_defs block_umac_defs = {
 };
 
 static struct block_defs block_xmac_defs = {
-	"xmac", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"xmac", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	false, false, MAX_DBG_RESET_REGS, 0
 };
 
 static struct block_defs block_dbg_defs = {
-	"dbg", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"dbg", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	true, true, DBG_RESET_REG_MISC_PL_PDA_VAUX, 3
 };
 
 static struct block_defs block_nig_defs = {
-	"nig", {true, true, true}, false, 0,
-	{DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN},
+	"nig",
+	{true, true}, false, 0,
+	{DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN},
 	NIG_REG_DBG_SELECT, NIG_REG_DBG_DWORD_ENABLE,
 	NIG_REG_DBG_SHIFT, NIG_REG_DBG_FORCE_VALID,
 	NIG_REG_DBG_FORCE_FRAME,
@@ -1113,8 +1174,9 @@ static struct block_defs block_nig_defs = {
 };
 
 static struct block_defs block_wol_defs = {
-	"wol", {false, false, true}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ},
+	"wol",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ},
 	WOL_REG_DBG_SELECT, WOL_REG_DBG_DWORD_ENABLE,
 	WOL_REG_DBG_SHIFT, WOL_REG_DBG_FORCE_VALID,
 	WOL_REG_DBG_FORCE_FRAME,
@@ -1122,8 +1184,9 @@ static struct block_defs block_wol_defs = {
 };
 
 static struct block_defs block_bmbn_defs = {
-	"bmbn", {false, false, true}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCB},
+	"bmbn",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCB},
 	BMBN_REG_DBG_SELECT, BMBN_REG_DBG_DWORD_ENABLE,
 	BMBN_REG_DBG_SHIFT, BMBN_REG_DBG_FORCE_VALID,
 	BMBN_REG_DBG_FORCE_FRAME,
@@ -1131,15 +1194,16 @@ static struct block_defs block_bmbn_defs = {
 };
 
 static struct block_defs block_ipc_defs = {
-	"ipc", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"ipc", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	true, false, DBG_RESET_REG_MISCS_PL_UA, 8
 };
 
 static struct block_defs block_nwm_defs = {
-	"nwm", {false, false, true}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW},
+	"nwm",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW},
 	NWM_REG_DBG_SELECT, NWM_REG_DBG_DWORD_ENABLE,
 	NWM_REG_DBG_SHIFT, NWM_REG_DBG_FORCE_VALID,
 	NWM_REG_DBG_FORCE_FRAME,
@@ -1147,22 +1211,29 @@ static struct block_defs block_nwm_defs = {
 };
 
 static struct block_defs block_nws_defs = {
-	"nws", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
-	0, 0, 0, 0, 0,
+	"nws",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW},
+	NWS_REG_DBG_SELECT, NWS_REG_DBG_DWORD_ENABLE,
+	NWS_REG_DBG_SHIFT, NWS_REG_DBG_FORCE_VALID,
+	NWS_REG_DBG_FORCE_FRAME,
 	true, false, DBG_RESET_REG_MISCS_PL_HV, 12
 };
 
 static struct block_defs block_ms_defs = {
-	"ms", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
-	0, 0, 0, 0, 0,
+	"ms",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ},
+	MS_REG_DBG_SELECT, MS_REG_DBG_DWORD_ENABLE,
+	MS_REG_DBG_SHIFT, MS_REG_DBG_FORCE_VALID,
+	MS_REG_DBG_FORCE_FRAME,
 	true, false, DBG_RESET_REG_MISCS_PL_HV, 13
 };
 
 static struct block_defs block_phy_pcie_defs = {
-	"phy_pcie", {false, false, true}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
+	"phy_pcie",
+	{false, true}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
 	PCIE_REG_DBG_COMMON_SELECT, PCIE_REG_DBG_COMMON_DWORD_ENABLE,
 	PCIE_REG_DBG_COMMON_SHIFT, PCIE_REG_DBG_COMMON_FORCE_VALID,
 	PCIE_REG_DBG_COMMON_FORCE_FRAME,
@@ -1170,22 +1241,57 @@ static struct block_defs block_phy_pcie_defs = {
 };
 
 static struct block_defs block_led_defs = {
-	"led", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"led", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	0, 0, 0, 0, 0,
+	true, false, DBG_RESET_REG_MISCS_PL_HV, 14
+};
+
+static struct block_defs block_avs_wrap_defs = {
+	"avs_wrap", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	0, 0, 0, 0, 0,
+	true, false, DBG_RESET_REG_MISCS_PL_UA, 11
+};
+
+static struct block_defs block_rgfs_defs = {
+	"rgfs", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
-	true, true, DBG_RESET_REG_MISCS_PL_HV, 14
+	false, false, MAX_DBG_RESET_REGS, 0
+};
+
+static struct block_defs block_tgfs_defs = {
+	"tgfs", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	0, 0, 0, 0, 0,
+	false, false, MAX_DBG_RESET_REGS, 0
+};
+
+static struct block_defs block_ptld_defs = {
+	"ptld", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	0, 0, 0, 0, 0,
+	false, false, MAX_DBG_RESET_REGS, 0
+};
+
+static struct block_defs block_ypld_defs = {
+	"ypld", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	0, 0, 0, 0, 0,
+	false, false, MAX_DBG_RESET_REGS, 0
 };
 
 static struct block_defs block_misc_aeu_defs = {
-	"misc_aeu", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"misc_aeu", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	false, false, MAX_DBG_RESET_REGS, 0
 };
 
 static struct block_defs block_bar0_map_defs = {
-	"bar0_map", {false, false, false}, false, 0,
-	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+	"bar0_map", {false, false}, false, 0,
+	{MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
 	0, 0, 0, 0, 0,
 	false, false, MAX_DBG_RESET_REGS, 0
 };
@@ -1269,6 +1375,11 @@ static struct block_defs *s_block_defs[MAX_BLOCK_ID] = {
 	&block_ms_defs,
 	&block_phy_pcie_defs,
 	&block_led_defs,
+	&block_avs_wrap_defs,
+	&block_rgfs_defs,
+	&block_tgfs_defs,
+	&block_ptld_defs,
+	&block_ypld_defs,
 	&block_misc_aeu_defs,
 	&block_bar0_map_defs,
 };
@@ -1281,65 +1392,67 @@ static struct platform_defs s_platform_defs[] = {
 };
 
 static struct grc_param_defs s_grc_param_defs[] = {
-	{{1, 1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_TSTORM */
-	{{1, 1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_MSTORM */
-	{{1, 1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_USTORM */
-	{{1, 1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_XSTORM */
-	{{1, 1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_YSTORM */
-	{{1, 1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_PSTORM */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_REGS */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_RAM */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_PBUF */
-	{{0, 0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_IOR */
-	{{0, 0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_VFC */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_CM_CTX */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_ILT */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_RSS */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_CAU */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_QM */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_MCP */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_RESERVED */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_CFC */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_IGU */
-	{{0, 0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_BRB */
-	{{0, 0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_BTB */
-	{{0, 0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_BMB */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_NIG */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_MULD */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_PRS */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_DMAE */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_TM */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_SDM */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_DIF */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_STATIC */
-	{{0, 0, 0}, 0, 1, false, 0, 0},	/* DBG_GRC_PARAM_UNSTALL */
-	{{MAX_LCIDS, MAX_LCIDS, MAX_LCIDS}, 1, MAX_LCIDS, false, MAX_LCIDS,
+	{{1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_TSTORM */
+	{{1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_MSTORM */
+	{{1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_USTORM */
+	{{1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_XSTORM */
+	{{1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_YSTORM */
+	{{1, 1}, 0, 1, false, 1, 1},	/* DBG_GRC_PARAM_DUMP_PSTORM */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_REGS */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_RAM */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_PBUF */
+	{{0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_IOR */
+	{{0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_VFC */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_CM_CTX */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_ILT */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_RSS */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_CAU */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_QM */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_MCP */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_RESERVED */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_CFC */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_IGU */
+	{{0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_BRB */
+	{{0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_BTB */
+	{{0, 0}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_BMB */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_NIG */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_MULD */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_PRS */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_DMAE */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_TM */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_SDM */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_DIF */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_STATIC */
+	{{0, 0}, 0, 1, false, 0, 0},	/* DBG_GRC_PARAM_UNSTALL */
+	{{MAX_LCIDS, MAX_LCIDS}, 1, MAX_LCIDS, false, MAX_LCIDS,
 	 MAX_LCIDS},			/* DBG_GRC_PARAM_NUM_LCIDS */
-	{{MAX_LTIDS, MAX_LTIDS, MAX_LTIDS}, 1, MAX_LTIDS, false, MAX_LTIDS,
+	{{MAX_LTIDS, MAX_LTIDS}, 1, MAX_LTIDS, false, MAX_LTIDS,
 	 MAX_LTIDS},			/* DBG_GRC_PARAM_NUM_LTIDS */
-	{{0, 0, 0}, 0, 1, true, 0, 0},	/* DBG_GRC_PARAM_EXCLUDE_ALL */
-	{{0, 0, 0}, 0, 1, true, 0, 0},	/* DBG_GRC_PARAM_CRASH */
-	{{0, 0, 0}, 0, 1, false, 1, 0},	/* DBG_GRC_PARAM_PARITY_SAFE */
-	{{1, 1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_CM */
-	{{1, 1, 1}, 0, 1, false, 0, 1}	/* DBG_GRC_PARAM_DUMP_PHY */
+	{{0, 0}, 0, 1, true, 0, 0},	/* DBG_GRC_PARAM_EXCLUDE_ALL */
+	{{0, 0}, 0, 1, true, 0, 0},	/* DBG_GRC_PARAM_CRASH */
+	{{0, 0}, 0, 1, false, 1, 0},	/* DBG_GRC_PARAM_PARITY_SAFE */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_CM */
+	{{1, 1}, 0, 1, false, 0, 1},	/* DBG_GRC_PARAM_DUMP_PHY */
+	{{0, 0}, 0, 1, false, 0, 0},	/* DBG_GRC_PARAM_NO_MCP */
+	{{0, 0}, 0, 1, false, 0, 0}	/* DBG_GRC_PARAM_NO_FW_VER */
 };
 
 static struct rss_mem_defs s_rss_mem_defs[] = {
 	{ "rss_mem_cid", "rss_cid", 0,
-	  {256, 256, 320},
-	  {32, 32, 32} },
+	  {256, 320},
+	  {32, 32} },
 	{ "rss_mem_key_msb", "rss_key", 1024,
-	  {128, 128, 208},
-	  {256, 256, 256} },
+	  {128, 208},
+	  {256, 256} },
 	{ "rss_mem_key_lsb", "rss_key", 2048,
-	  {128, 128, 208},
-	  {64, 64, 64} },
+	  {128, 208},
+	  {64, 64} },
 	{ "rss_mem_info", "rss_info", 3072,
-	  {128, 128, 208},
-	  {16, 16, 16} },
+	  {128, 208},
+	  {16, 16} },
 	{ "rss_mem_ind", "rss_ind", 4096,
-	  {(128 * 128), (128 * 128), (128 * 208)},
-	  {16, 16, 16} }
+	  {(128 * 128), (128 * 208)},
+	  {16, 16} }
 };
 
 static struct vfc_ram_defs s_vfc_ram_defs[] = {
@@ -1352,32 +1465,32 @@ static struct vfc_ram_defs s_vfc_ram_defs[] = {
 static struct big_ram_defs s_big_ram_defs[] = {
 	{ "BRB", MEM_GROUP_BRB_MEM, MEM_GROUP_BRB_RAM, DBG_GRC_PARAM_DUMP_BRB,
 	  BRB_REG_BIG_RAM_ADDRESS, BRB_REG_BIG_RAM_DATA,
-	  {4800, 4800, 5632} },
+	  {4800, 5632} },
 	{ "BTB", MEM_GROUP_BTB_MEM, MEM_GROUP_BTB_RAM, DBG_GRC_PARAM_DUMP_BTB,
 	  BTB_REG_BIG_RAM_ADDRESS, BTB_REG_BIG_RAM_DATA,
-	  {2880, 2880, 3680} },
+	  {2880, 3680} },
 	{ "BMB", MEM_GROUP_BMB_MEM, MEM_GROUP_BMB_RAM, DBG_GRC_PARAM_DUMP_BMB,
 	  BMB_REG_BIG_RAM_ADDRESS, BMB_REG_BIG_RAM_DATA,
-	  {1152, 1152, 1152} }
+	  {1152, 1152} }
 };
 
 static struct reset_reg_defs s_reset_regs_defs[] = {
 	{ MISCS_REG_RESET_PL_UA, 0x0,
-	  {true, true, true} },		/* DBG_RESET_REG_MISCS_PL_UA */
+	  {true, true} },		/* DBG_RESET_REG_MISCS_PL_UA */
 	{ MISCS_REG_RESET_PL_HV, 0x0,
-	  {true, true, true} },		/* DBG_RESET_REG_MISCS_PL_HV */
+	  {true, true} },		/* DBG_RESET_REG_MISCS_PL_HV */
 	{ MISCS_REG_RESET_PL_HV_2, 0x0,
-	  {false, false, true} },	/* DBG_RESET_REG_MISCS_PL_HV_2 */
+	  {false, true} },	/* DBG_RESET_REG_MISCS_PL_HV_2 */
 	{ MISC_REG_RESET_PL_UA, 0x0,
-	  {true, true, true} },		/* DBG_RESET_REG_MISC_PL_UA */
+	  {true, true} },		/* DBG_RESET_REG_MISC_PL_UA */
 	{ MISC_REG_RESET_PL_HV, 0x0,
-	  {true, true, true} },		/* DBG_RESET_REG_MISC_PL_HV */
+	  {true, true} },		/* DBG_RESET_REG_MISC_PL_HV */
 	{ MISC_REG_RESET_PL_PDA_VMAIN_1, 0x4404040,
-	  {true, true, true} },		/* DBG_RESET_REG_MISC_PL_PDA_VMAIN_1 */
+	  {true, true} },		/* DBG_RESET_REG_MISC_PL_PDA_VMAIN_1 */
 	{ MISC_REG_RESET_PL_PDA_VMAIN_2, 0x7c00007,
-	  {true, true, true} },		/* DBG_RESET_REG_MISC_PL_PDA_VMAIN_2 */
+	  {true, true} },		/* DBG_RESET_REG_MISC_PL_PDA_VMAIN_2 */
 	{ MISC_REG_RESET_PL_PDA_VAUX, 0x2,
-	  {true, true, true} },		/* DBG_RESET_REG_MISC_PL_PDA_VAUX */
+	  {true, true} },		/* DBG_RESET_REG_MISC_PL_PDA_VAUX */
 };
 
 static struct phy_defs s_phy_defs[] = {
@@ -1410,6 +1523,26 @@ static u32 qed_read_unaligned_dword(u8 *buf)
 	return dword;
 }
 
+/* Returns the value of the specified GRC param */
+static u32 qed_grc_get_param(struct qed_hwfn *p_hwfn,
+			     enum dbg_grc_params grc_param)
+{
+	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+
+	return dev_data->grc.param_val[grc_param];
+}
+
+/* Initializes the GRC parameters */
+static void qed_dbg_grc_init_params(struct qed_hwfn *p_hwfn)
+{
+	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+
+	if (!dev_data->grc.params_initialized) {
+		qed_dbg_grc_set_params_default(p_hwfn);
+		dev_data->grc.params_initialized = 1;
+	}
+}
+
 /* Initializes debug data for the specified device */
 static enum dbg_status qed_dbg_dev_init(struct qed_hwfn *p_hwfn,
 					struct qed_ptt *p_ptt)
@@ -1424,13 +1557,17 @@ static enum dbg_status qed_dbg_dev_init(struct qed_hwfn *p_hwfn,
 		dev_data->mode_enable[MODE_K2] = 1;
 	} else if (QED_IS_BB_B0(p_hwfn->cdev)) {
 		dev_data->chip_id = CHIP_BB_B0;
-		dev_data->mode_enable[MODE_BB_B0] = 1;
+		dev_data->mode_enable[MODE_BB] = 1;
 	} else {
 		return DBG_STATUS_UNKNOWN_CHIP;
 	}
 
 	dev_data->platform_id = PLATFORM_ASIC;
 	dev_data->mode_enable[MODE_ASIC] = 1;
+
+	/* Initializes the GRC parameters */
+	qed_dbg_grc_init_params(p_hwfn);
+
 	dev_data->initialized = true;
 	return DBG_STATUS_OK;
 }
@@ -1561,7 +1698,7 @@ static u32 qed_dump_fw_ver_param(struct qed_hwfn *p_hwfn,
 	int printed_chars;
 	u32 offset = 0;
 
-	if (dump) {
+	if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_FW_VER)) {
 		/* Read FW image/version from PRAM in a non-reset SEMI */
 		bool found = false;
 		u8 storm_id;
@@ -1622,7 +1759,7 @@ static u32 qed_dump_mfw_ver_param(struct qed_hwfn *p_hwfn,
 {
 	char mfw_ver_str[16] = EMPTY_FW_VERSION_STR;
 
-	if (dump) {
+	if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_FW_VER)) {
 		u32 global_section_offsize, global_section_addr, mfw_ver;
 		u32 public_data_addr, global_section_offsize_addr;
 		int printed_chars;
@@ -1683,15 +1820,13 @@ static u32 qed_dump_common_global_params(struct qed_hwfn *p_hwfn,
 					 bool dump,
 					 u8 num_specific_global_params)
 {
+	u8 num_params = NUM_COMMON_GLOBAL_PARAMS + num_specific_global_params;
 	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
 	u32 offset = 0;
 
 	/* Find platform string and dump global params section header */
 	offset += qed_dump_section_hdr(dump_buf + offset,
-				       dump,
-				       "global_params",
-				       NUM_COMMON_GLOBAL_PARAMS +
-				       num_specific_global_params);
+				       dump, "global_params", num_params);
 
 	/* Store params */
 	offset += qed_dump_fw_ver_param(p_hwfn, p_ptt, dump_buf + offset, dump);
@@ -1815,37 +1950,6 @@ static bool qed_is_mode_match(struct qed_hwfn *p_hwfn, u16 *modes_buf_offset)
 	}
 }
 
-/* Returns the value of the specified GRC param */
-static u32 qed_grc_get_param(struct qed_hwfn *p_hwfn,
-			     enum dbg_grc_params grc_param)
-{
-	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
-
-	return dev_data->grc.param_val[grc_param];
-}
-
-/* Clear all GRC params */
-static void qed_dbg_grc_clear_params(struct qed_hwfn *p_hwfn)
-{
-	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
-	u32 i;
-
-	for (i = 0; i < MAX_DBG_GRC_PARAMS; i++)
-		dev_data->grc.param_set_by_user[i] = 0;
-}
-
-/* Assign default GRC param values */
-static void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn)
-{
-	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
-	u32 i;
-
-	for (i = 0; i < MAX_DBG_GRC_PARAMS; i++)
-		if (!dev_data->grc.param_set_by_user[i])
-			dev_data->grc.param_val[i] =
-			    s_grc_param_defs[i].default_val[dev_data->chip_id];
-}
-
 /* Returns true if the specified entity (indicated by GRC param) should be
  * included in the dump, false otherwise.
  */
@@ -1971,7 +2075,7 @@ static void qed_grc_unreset_blocks(struct qed_hwfn *p_hwfn,
 	}
 }
 
-/* Returns the attention name offsets of the specified block */
+/* Returns the attention block data of the specified block */
 static const struct dbg_attn_block_type_data *
 qed_get_block_attn_data(enum block_id block_id, enum dbg_attn_type attn_type)
 {
@@ -2040,7 +2144,7 @@ static void qed_grc_clear_all_prty(struct qed_hwfn *p_hwfn,
  * The following parameters are dumped:
  * - 'count' = num_dumped_entries
  * - 'split' = split_type
- * - 'id'i = split_id (dumped only if split_id >= 0)
+ * - 'id' = split_id (dumped only if split_id >= 0)
  * - 'param_name' = param_val (user param, dumped only if param_name != NULL and
  *	param_val != NULL)
  */
@@ -2069,21 +2173,81 @@ static u32 qed_grc_dump_regs_hdr(u32 *dump_buf,
 	return offset;
 }
 
-/* Dumps GRC register/memory. Returns the dumped size in dwords. */
+/* Dumps the GRC registers in the specified address range.
+ * Returns the dumped size in dwords.
+ */
+static u32 qed_grc_dump_addr_range(struct qed_hwfn *p_hwfn,
+				   struct qed_ptt *p_ptt, u32 *dump_buf,
+				   bool dump, u32 addr, u32 len)
+{
+	u32 byte_addr = DWORDS_TO_BYTES(addr), offset = 0, i;
+
+	if (dump)
+		for (i = 0; i < len; i++, byte_addr += BYTES_IN_DWORD, offset++)
+			*(dump_buf + offset) = qed_rd(p_hwfn, p_ptt, byte_addr);
+	else
+		offset += len;
+	return offset;
+}
+
+/* Dumps GRC registers sequence header. Returns the dumped size in dwords. */
+static u32 qed_grc_dump_reg_entry_hdr(u32 *dump_buf, bool dump, u32 addr,
+				      u32 len)
+{
+	if (dump)
+		*dump_buf = addr | (len << REG_DUMP_LEN_SHIFT);
+	return 1;
+}
+
+/* Dumps GRC registers sequence. Returns the dumped size in dwords. */
 static u32 qed_grc_dump_reg_entry(struct qed_hwfn *p_hwfn,
 				  struct qed_ptt *p_ptt, u32 *dump_buf,
 				  bool dump, u32 addr, u32 len)
 {
-	u32 offset = 0, i;
+	u32 offset = 0;
+
+	offset += qed_grc_dump_reg_entry_hdr(dump_buf, dump, addr, len);
+	offset += qed_grc_dump_addr_range(p_hwfn,
+					  p_ptt,
+					  dump_buf + offset, dump, addr, len);
+	return offset;
+}
+
+/* Dumps GRC registers sequence with skip cycle.
+ * Returns the dumped size in dwords.
+ */
+static u32 qed_grc_dump_reg_entry_skip(struct qed_hwfn *p_hwfn,
+				       struct qed_ptt *p_ptt, u32 *dump_buf,
+				       bool dump, u32 addr, u32 total_len,
+				       u32 read_len, u32 skip_len)
+{
+	u32 offset = 0, reg_offset = 0;
 
+	offset += qed_grc_dump_reg_entry_hdr(dump_buf, dump, addr, total_len);
 	if (dump) {
-		*(dump_buf + offset++) = addr | (len << REG_DUMP_LEN_SHIFT);
-		for (i = 0; i < len; i++, addr++, offset++)
-			*(dump_buf + offset) = qed_rd(p_hwfn,
-						      p_ptt,
-						      DWORDS_TO_BYTES(addr));
+		while (reg_offset < total_len) {
+			u32 curr_len = min_t(u32,
+					     read_len,
+					     total_len - reg_offset);
+			offset += qed_grc_dump_addr_range(p_hwfn,
+							  p_ptt,
+							  dump_buf + offset,
+							  dump, addr, curr_len);
+			reg_offset += curr_len;
+			addr += curr_len;
+			if (reg_offset < total_len) {
+				curr_len = min_t(u32,
+						 skip_len,
+						 total_len - skip_len);
+				memset(dump_buf + offset, 0,
+				       DWORDS_TO_BYTES(curr_len));
+				offset += curr_len;
+				reg_offset += curr_len;
+				addr += curr_len;
+			}
+		}
 	} else {
-		offset += len + 1;
+		offset += total_len;
 	}
 
 	return offset;
@@ -2124,14 +2288,17 @@ static u32 qed_grc_dump_regs_entries(struct qed_hwfn *p_hwfn,
 				const struct dbg_dump_reg *reg =
 				    (const struct dbg_dump_reg *)
 				    &input_regs_arr.ptr[input_offset];
+				u32 addr, len;
 
+				addr = GET_FIELD(reg->data,
+						 DBG_DUMP_REG_ADDRESS);
+				len = GET_FIELD(reg->data, DBG_DUMP_REG_LENGTH);
 				offset +=
-					qed_grc_dump_reg_entry(p_hwfn, p_ptt,
-						    dump_buf + offset, dump,
-						    GET_FIELD(reg->data,
-							DBG_DUMP_REG_ADDRESS),
-						    GET_FIELD(reg->data,
-							DBG_DUMP_REG_LENGTH));
+				    qed_grc_dump_reg_entry(p_hwfn, p_ptt,
+							   dump_buf + offset,
+							   dump,
+							   addr,
+							   len);
 				(*num_dumped_reg_entries)++;
 			}
 		} else {
@@ -2194,8 +2361,14 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn,
 				  const char *param_name, const char *param_val)
 {
 	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+	struct chip_platform_defs *p_platform_defs;
 	u32 offset = 0, input_offset = 0;
-	u8 port_id, pf_id;
+	struct chip_defs *p_chip_defs;
+	u8 port_id, pf_id, vf_id;
+	u16 fid;
+
+	p_chip_defs = &s_chip_defs[dev_data->chip_id];
+	p_platform_defs = &p_chip_defs->per_platform[dev_data->platform_id];
 
 	if (dump)
 		DP_VERBOSE(p_hwfn, QED_MSG_DEBUG, "Dumping registers...\n");
@@ -2214,7 +2387,6 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn,
 
 		switch (split_type_id) {
 		case SPLIT_TYPE_NONE:
-		case SPLIT_TYPE_VF:
 			offset += qed_grc_dump_split_data(p_hwfn,
 							  p_ptt,
 							  curr_input_regs_arr,
@@ -2227,10 +2399,7 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn,
 							  param_val);
 			break;
 		case SPLIT_TYPE_PORT:
-			for (port_id = 0;
-			     port_id <
-			     s_chip_defs[dev_data->chip_id].
-			     per_platform[dev_data->platform_id].num_ports;
+			for (port_id = 0; port_id < p_platform_defs->num_ports;
 			     port_id++) {
 				if (dump)
 					qed_port_pretend(p_hwfn, p_ptt,
@@ -2247,20 +2416,48 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn,
 			break;
 		case SPLIT_TYPE_PF:
 		case SPLIT_TYPE_PORT_PF:
-			for (pf_id = 0;
-			     pf_id <
-			     s_chip_defs[dev_data->chip_id].
-			     per_platform[dev_data->platform_id].num_pfs;
+			for (pf_id = 0; pf_id < p_platform_defs->num_pfs;
 			     pf_id++) {
-				if (dump)
-					qed_fid_pretend(p_hwfn, p_ptt, pf_id);
-				offset += qed_grc_dump_split_data(p_hwfn,
-							p_ptt,
-							curr_input_regs_arr,
-							dump_buf + offset,
-							dump, block_enable,
-							"pf", pf_id, param_name,
-							param_val);
+				u8 pfid_shift =
+					PXP_PRETEND_CONCRETE_FID_PFID_SHIFT;
+
+				if (dump) {
+					fid = pf_id << pfid_shift;
+					qed_fid_pretend(p_hwfn, p_ptt, fid);
+				}
+
+				offset +=
+				    qed_grc_dump_split_data(p_hwfn, p_ptt,
+							    curr_input_regs_arr,
+							    dump_buf + offset,
+							    dump, block_enable,
+							    "pf", pf_id,
+							    param_name,
+							    param_val);
+			}
+			break;
+		case SPLIT_TYPE_VF:
+			for (vf_id = 0; vf_id < p_platform_defs->num_vfs;
+			     vf_id++) {
+				u8 vfvalid_shift =
+					PXP_PRETEND_CONCRETE_FID_VFVALID_SHIFT;
+				u8 vfid_shift =
+					PXP_PRETEND_CONCRETE_FID_VFID_SHIFT;
+
+				if (dump) {
+					fid = BIT(vfvalid_shift) |
+					      (vf_id << vfid_shift);
+					qed_fid_pretend(p_hwfn, p_ptt, fid);
+				}
+
+				offset +=
+				    qed_grc_dump_split_data(p_hwfn, p_ptt,
+							    curr_input_regs_arr,
+							    dump_buf + offset,
+							    dump, block_enable,
+							    "vf", vf_id,
+							    param_name,
+							    param_val);
 			}
 			break;
 		default:
@@ -2271,8 +2468,11 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn,
 	}
 
 	/* Pretend to original PF */
-	if (dump)
-		qed_fid_pretend(p_hwfn, p_ptt, p_hwfn->rel_pf_id);
+	if (dump) {
+		fid = p_hwfn->rel_pf_id << PXP_PRETEND_CONCRETE_FID_PFID_SHIFT;
+		qed_fid_pretend(p_hwfn, p_ptt, fid);
+	}
+
 	return offset;
 }
 
@@ -2291,13 +2491,14 @@ static u32 qed_grc_dump_reset_regs(struct qed_hwfn *p_hwfn,
 	/* Write reset registers */
 	for (i = 0; i < MAX_DBG_RESET_REGS; i++) {
 		if (s_reset_regs_defs[i].exists[dev_data->chip_id]) {
+			u32 addr = BYTES_TO_DWORDS(s_reset_regs_defs[i].addr);
+
 			offset += qed_grc_dump_reg_entry(p_hwfn,
 							 p_ptt,
 							 dump_buf + offset,
 							 dump,
-							 BYTES_TO_DWORDS
-							 (s_reset_regs_defs
-							  [i].addr), 1);
+							 addr,
+							 1);
 			num_regs++;
 		}
 	}
@@ -2339,6 +2540,7 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn,
 				&attn_reg_arr[reg_idx];
 			u16 modes_buf_offset;
 			bool eval_mode;
+			u32 addr;
 
 			/* Check mode */
 			eval_mode = GET_FIELD(reg_data->mode.data,
@@ -2349,19 +2551,23 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn,
 			if (!eval_mode ||
 			    qed_is_mode_match(p_hwfn, &modes_buf_offset)) {
 				/* Mode match - read and dump registers */
-				offset += qed_grc_dump_reg_entry(p_hwfn,
-							p_ptt,
-							dump_buf + offset,
-							dump,
-							reg_data->mask_address,
-							1);
-				offset += qed_grc_dump_reg_entry(p_hwfn,
-						p_ptt,
-						dump_buf + offset,
-						dump,
-						GET_FIELD(reg_data->data,
-						    DBG_ATTN_REG_STS_ADDRESS),
-						1);
+				addr = reg_data->mask_address;
+				offset +=
+				    qed_grc_dump_reg_entry(p_hwfn,
+							   p_ptt,
+							   dump_buf + offset,
+							   dump,
+							   addr,
+							   1);
+				addr = GET_FIELD(reg_data->data,
+						 DBG_ATTN_REG_STS_ADDRESS);
+				offset +=
+				    qed_grc_dump_reg_entry(p_hwfn,
+							   p_ptt,
+							   dump_buf + offset,
+							   dump,
+							   addr,
+							   1);
 				num_reg_entries += 2;
 			}
 		}
@@ -2369,18 +2575,21 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn,
 
 	/* Write storm stall status registers */
 	for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) {
+		u32 addr;
+
 		if (dev_data->block_in_reset[s_storm_defs[storm_id].block_id] &&
 		    dump)
 			continue;
 
+		addr =
+		    BYTES_TO_DWORDS(s_storm_defs[storm_id].sem_fast_mem_addr +
+				    SEM_FAST_REG_STALLED);
 		offset += qed_grc_dump_reg_entry(p_hwfn,
-					p_ptt,
-					dump_buf + offset,
-					dump,
-					BYTES_TO_DWORDS(s_storm_defs[storm_id].
-							sem_fast_mem_addr +
-							SEM_FAST_REG_STALLED),
-					1);
+						 p_ptt,
+						 dump_buf + offset,
+						 dump,
+						 addr,
+						 1);
 		num_reg_entries++;
 	}
 
@@ -2392,11 +2601,47 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn,
 	return offset;
 }
 
+/* Dumps registers that can't be represented in the debug arrays */
+static u32 qed_grc_dump_special_regs(struct qed_hwfn *p_hwfn,
+				     struct qed_ptt *p_ptt,
+				     u32 *dump_buf, bool dump)
+{
+	u32 offset = 0, addr;
+
+	offset += qed_grc_dump_regs_hdr(dump_buf,
+					dump, 2, "eng", -1, NULL, NULL);
+
+	/* Dump R/TDIF_REG_DEBUG_ERROR_INFO_SIZE (every 8'th register should be
+	 * skipped).
+	 */
+	addr = BYTES_TO_DWORDS(RDIF_REG_DEBUG_ERROR_INFO);
+	offset += qed_grc_dump_reg_entry_skip(p_hwfn,
+					      p_ptt,
+					      dump_buf + offset,
+					      dump,
+					      addr,
+					      RDIF_REG_DEBUG_ERROR_INFO_SIZE,
+					      7,
+					      1);
+	addr = BYTES_TO_DWORDS(TDIF_REG_DEBUG_ERROR_INFO);
+	offset +=
+	    qed_grc_dump_reg_entry_skip(p_hwfn,
+					p_ptt,
+					dump_buf + offset,
+					dump,
+					addr,
+					TDIF_REG_DEBUG_ERROR_INFO_SIZE,
+					7,
+					1);
+
+	return offset;
+}
+
 /* Dumps a GRC memory header (section and params).
  * The following parameters are dumped:
  * name - name is dumped only if it's not NULL.
- * addr - byte_addr is dumped only if name is NULL.
- * len - dword_len is always dumped.
+ * addr - addr is dumped only if name is NULL.
+ * len - len is always dumped.
  * width - bit_width is dumped if it's not zero.
  * packed - packed=1 is dumped if it's not false.
  * mem_group - mem_group is always dumped.
@@ -2408,8 +2653,8 @@ static u32 qed_grc_dump_mem_hdr(struct qed_hwfn *p_hwfn,
 				u32 *dump_buf,
 				bool dump,
 				const char *name,
-				u32 byte_addr,
-				u32 dword_len,
+				u32 addr,
+				u32 len,
 				u32 bit_width,
 				bool packed,
 				const char *mem_group,
@@ -2419,7 +2664,7 @@ static u32 qed_grc_dump_mem_hdr(struct qed_hwfn *p_hwfn,
 	u32 offset = 0;
 	char buf[64];
 
-	if (!dword_len)
+	if (!len)
 		DP_NOTICE(p_hwfn,
 			  "Unexpected GRC Dump error: dumped memory size must be non-zero\n");
 	if (bit_width)
@@ -2446,20 +2691,21 @@ static u32 qed_grc_dump_mem_hdr(struct qed_hwfn *p_hwfn,
 			DP_VERBOSE(p_hwfn,
 				   QED_MSG_DEBUG,
 				   "Dumping %d registers from %s...\n",
-				   dword_len, buf);
+				   len, buf);
 	} else {
 		/* Dump address */
 		offset += qed_dump_num_param(dump_buf + offset,
-					     dump, "addr", byte_addr);
-		if (dump && dword_len > 64)
+					     dump, "addr",
+					     DWORDS_TO_BYTES(addr));
+		if (dump && len > 64)
 			DP_VERBOSE(p_hwfn,
 				   QED_MSG_DEBUG,
 				   "Dumping %d registers from address 0x%x...\n",
-				   dword_len, byte_addr);
+				   len, (u32)DWORDS_TO_BYTES(addr));
 	}
 
 	/* Dump len */
-	offset += qed_dump_num_param(dump_buf + offset, dump, "len", dword_len);
+	offset += qed_dump_num_param(dump_buf + offset, dump, "len", len);
 
 	/* Dump bit width */
 	if (bit_width)
@@ -2492,8 +2738,8 @@ static u32 qed_grc_dump_mem(struct qed_hwfn *p_hwfn,
 			    u32 *dump_buf,
 			    bool dump,
 			    const char *name,
-			    u32 byte_addr,
-			    u32 dword_len,
+			    u32 addr,
+			    u32 len,
 			    u32 bit_width,
 			    bool packed,
 			    const char *mem_group,
@@ -2505,21 +2751,14 @@ static u32 qed_grc_dump_mem(struct qed_hwfn *p_hwfn,
 				       dump_buf + offset,
 				       dump,
 				       name,
-				       byte_addr,
-				       dword_len,
+				       addr,
+				       len,
 				       bit_width,
 				       packed,
 				       mem_group, is_storm, storm_letter);
-	if (dump) {
-		u32 i;
-
-		for (i = 0; i < dword_len;
-		     i++, byte_addr += BYTES_IN_DWORD, offset++)
-			*(dump_buf + offset) = qed_rd(p_hwfn, p_ptt, byte_addr);
-	} else {
-		offset += dword_len;
-	}
-
+	offset += qed_grc_dump_addr_range(p_hwfn,
+					  p_ptt,
+					  dump_buf + offset, dump, addr, len);
 	return offset;
 }
 
@@ -2575,25 +2814,41 @@ static u32 qed_grc_dump_mem_entries(struct qed_hwfn *p_hwfn,
 			if (qed_grc_is_mem_included(p_hwfn,
 					(enum block_id)cond_hdr->block_id,
 					mem_group_id)) {
-				u32 mem_byte_addr =
-					DWORDS_TO_BYTES(GET_FIELD(mem->dword0,
-							DBG_DUMP_MEM_ADDRESS));
+				u32 mem_addr = GET_FIELD(mem->dword0,
+							 DBG_DUMP_MEM_ADDRESS);
 				u32 mem_len = GET_FIELD(mem->dword1,
 							DBG_DUMP_MEM_LENGTH);
+				enum dbg_grc_params grc_param;
 				char storm_letter = 'a';
 				bool is_storm = false;
 
 				/* Update memory length for CCFC/TCFC memories
 				 * according to number of LCIDs/LTIDs.
 				 */
-				if (mem_group_id == MEM_GROUP_CONN_CFC_MEM)
+				if (mem_group_id == MEM_GROUP_CONN_CFC_MEM) {
+					if (mem_len % MAX_LCIDS != 0) {
+						DP_NOTICE(p_hwfn,
+							  "Invalid CCFC connection memory size\n");
+						return 0;
+					}
+
+					grc_param = DBG_GRC_PARAM_NUM_LCIDS;
 					mem_len = qed_grc_get_param(p_hwfn,
-							DBG_GRC_PARAM_NUM_LCIDS)
-							* (mem_len / MAX_LCIDS);
-				else if (mem_group_id == MEM_GROUP_TASK_CFC_MEM)
+								    grc_param) *
+						  (mem_len / MAX_LCIDS);
+				} else if (mem_group_id ==
+					   MEM_GROUP_TASK_CFC_MEM) {
+					if (mem_len % MAX_LTIDS != 0) {
+						DP_NOTICE(p_hwfn,
+							  "Invalid TCFC task memory size\n");
+						return 0;
+					}
+
+					grc_param = DBG_GRC_PARAM_NUM_LTIDS;
 					mem_len = qed_grc_get_param(p_hwfn,
-							DBG_GRC_PARAM_NUM_LTIDS)
-							* (mem_len / MAX_LTIDS);
+								    grc_param) *
+						  (mem_len / MAX_LTIDS);
+				}
 
 				/* If memory is associated with Storm, update
 				 * Storm details.
@@ -2610,7 +2865,7 @@ static u32 qed_grc_dump_mem_entries(struct qed_hwfn *p_hwfn,
 				/* Dump memory */
 				offset += qed_grc_dump_mem(p_hwfn, p_ptt,
 						dump_buf + offset, dump, NULL,
-						mem_byte_addr, mem_len, 0,
+						mem_addr, mem_len, 0,
 						false,
 						s_mem_group_names[mem_group_id],
 						is_storm, storm_letter);
@@ -2799,29 +3054,31 @@ static u32 qed_grc_dump_iors(struct qed_hwfn *p_hwfn,
 	u32 offset = 0;
 
 	for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) {
-		if (qed_grc_is_storm_included(p_hwfn,
-					      (enum dbg_storms)storm_id)) {
-			for (set_id = 0; set_id < NUM_IOR_SETS; set_id++) {
-				u32 addr =
-				    s_storm_defs[storm_id].sem_fast_mem_addr +
-				    SEM_FAST_REG_STORM_REG_FILE +
-				    DWORDS_TO_BYTES(IOR_SET_OFFSET(set_id));
+		struct storm_defs *storm = &s_storm_defs[storm_id];
 
-				buf[strlen(buf) - 1] = '0' + set_id;
-				offset += qed_grc_dump_mem(p_hwfn,
-							   p_ptt,
-							   dump_buf + offset,
-							   dump,
-							   buf,
-							   addr,
-							   IORS_PER_SET,
-							   32,
-							   false,
-							   "ior",
-							   true,
-							   s_storm_defs
-							   [storm_id].letter);
-			}
+		if (!qed_grc_is_storm_included(p_hwfn,
+					       (enum dbg_storms)storm_id))
+			continue;
+
+		for (set_id = 0; set_id < NUM_IOR_SETS; set_id++) {
+			u32 dwords, addr;
+
+			dwords = storm->sem_fast_mem_addr +
+				 SEM_FAST_REG_STORM_REG_FILE;
+			addr = BYTES_TO_DWORDS(dwords) + IOR_SET_OFFSET(set_id);
+			buf[strlen(buf) - 1] = '0' + set_id;
+			offset += qed_grc_dump_mem(p_hwfn,
+						   p_ptt,
+						   dump_buf + offset,
+						   dump,
+						   buf,
+						   addr,
+						   IORS_PER_SET,
+						   32,
+						   false,
+						   "ior",
+						   true,
+						   storm->letter);
 		}
 	}
 
@@ -2990,34 +3247,39 @@ static u32 qed_grc_dump_rss(struct qed_hwfn *p_hwfn,
 		struct rss_mem_defs *rss_defs = &s_rss_mem_defs[rss_mem_id];
 		u32 num_entries = rss_defs->num_entries[dev_data->chip_id];
 		u32 entry_width = rss_defs->entry_width[dev_data->chip_id];
-		u32 total_size = (num_entries * entry_width) / 32;
+		u32 total_dwords = (num_entries * entry_width) / 32;
+		u32 size = RSS_REG_RSS_RAM_DATA_SIZE;
 		bool packed = (entry_width == 16);
-		u32 addr = rss_defs->addr;
-		u32 i, j;
+		u32 rss_addr = rss_defs->addr;
+		u32 i, addr;
 
 		offset += qed_grc_dump_mem_hdr(p_hwfn,
 					       dump_buf + offset,
 					       dump,
 					       rss_defs->mem_name,
-					       addr,
-					       total_size,
+					       0,
+					       total_dwords,
 					       entry_width,
 					       packed,
 					       rss_defs->type_name, false, 0);
 
 		if (!dump) {
-			offset += total_size;
+			offset += total_dwords;
 			continue;
 		}
 
 		/* Dump RSS data */
-		for (i = 0; i < BYTES_TO_DWORDS(total_size); i++, addr++) {
-			qed_wr(p_hwfn, p_ptt, RSS_REG_RSS_RAM_ADDR, addr);
-			for (j = 0; j < BYTES_IN_DWORD; j++, offset++)
-				*(dump_buf + offset) =
-					qed_rd(p_hwfn, p_ptt,
-					       RSS_REG_RSS_RAM_DATA +
-					       DWORDS_TO_BYTES(j));
+		for (i = 0; i < total_dwords;
+		     i += RSS_REG_RSS_RAM_DATA_SIZE, rss_addr++) {
+			addr = BYTES_TO_DWORDS(RSS_REG_RSS_RAM_DATA);
+			qed_wr(p_hwfn, p_ptt, RSS_REG_RSS_RAM_ADDR, rss_addr);
+				offset += qed_grc_dump_addr_range(p_hwfn,
+								  p_ptt,
+								  dump_buf +
+								  offset,
+								  dump,
+								  addr,
+								  size);
 		}
 	}
 
@@ -3030,19 +3292,19 @@ static u32 qed_grc_dump_big_ram(struct qed_hwfn *p_hwfn,
 				u32 *dump_buf, bool dump, u8 big_ram_id)
 {
 	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+	u32 total_blocks, ram_size, offset = 0, i;
 	char mem_name[12] = "???_BIG_RAM";
 	char type_name[8] = "???_RAM";
-	u32 ram_size, total_blocks;
-	u32 offset = 0, i, j;
+	struct big_ram_defs *big_ram;
 
-	total_blocks =
-		s_big_ram_defs[big_ram_id].num_of_blocks[dev_data->chip_id];
+	big_ram = &s_big_ram_defs[big_ram_id];
+	total_blocks = big_ram->num_of_blocks[dev_data->chip_id];
 	ram_size = total_blocks * BIG_RAM_BLOCK_SIZE_DWORDS;
 
-	strncpy(type_name, s_big_ram_defs[big_ram_id].instance_name,
-		strlen(s_big_ram_defs[big_ram_id].instance_name));
-	strncpy(mem_name, s_big_ram_defs[big_ram_id].instance_name,
-		strlen(s_big_ram_defs[big_ram_id].instance_name));
+	strncpy(type_name, big_ram->instance_name,
+		strlen(big_ram->instance_name));
+	strncpy(mem_name, big_ram->instance_name,
+		strlen(big_ram->instance_name));
 
 	/* Dump memory header */
 	offset += qed_grc_dump_mem_hdr(p_hwfn,
@@ -3059,13 +3321,17 @@ static u32 qed_grc_dump_big_ram(struct qed_hwfn *p_hwfn,
 
 	/* Read and dump Big RAM data */
 	for (i = 0; i < total_blocks / 2; i++) {
-		qed_wr(p_hwfn, p_ptt, s_big_ram_defs[big_ram_id].addr_reg_addr,
-		       i);
-		for (j = 0; j < 2 * BIG_RAM_BLOCK_SIZE_DWORDS; j++, offset++)
-			*(dump_buf + offset) = qed_rd(p_hwfn, p_ptt,
-						s_big_ram_defs[big_ram_id].
-							data_reg_addr +
-						DWORDS_TO_BYTES(j));
+		u32 addr, len;
+
+		qed_wr(p_hwfn, p_ptt, big_ram->addr_reg_addr, i);
+		addr = BYTES_TO_DWORDS(big_ram->data_reg_addr);
+		len = 2 * BIG_RAM_BLOCK_SIZE_DWORDS;
+		offset += qed_grc_dump_addr_range(p_hwfn,
+						  p_ptt,
+						  dump_buf + offset,
+						  dump,
+						  addr,
+						  len);
 	}
 
 	return offset;
@@ -3075,11 +3341,11 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn,
 			    struct qed_ptt *p_ptt, u32 *dump_buf, bool dump)
 {
 	bool block_enable[MAX_BLOCK_ID] = { 0 };
+	u32 offset = 0, addr;
 	bool halted = false;
-	u32 offset = 0;
 
 	/* Halt MCP */
-	if (dump) {
+	if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_MCP)) {
 		halted = !qed_mcp_halt(p_hwfn, p_ptt);
 		if (!halted)
 			DP_NOTICE(p_hwfn, "MCP halt failed!\n");
@@ -3091,7 +3357,7 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn,
 				   dump_buf + offset,
 				   dump,
 				   NULL,
-				   MCP_REG_SCRATCH,
+				   BYTES_TO_DWORDS(MCP_REG_SCRATCH),
 				   MCP_REG_SCRATCH_SIZE,
 				   0, false, "MCP", false, 0);
 
@@ -3101,7 +3367,7 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn,
 				   dump_buf + offset,
 				   dump,
 				   NULL,
-				   MCP_REG_CPU_REG_FILE,
+				   BYTES_TO_DWORDS(MCP_REG_CPU_REG_FILE),
 				   MCP_REG_CPU_REG_FILE_SIZE,
 				   0, false, "MCP", false, 0);
 
@@ -3115,12 +3381,13 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn,
 	/* Dump required non-MCP registers */
 	offset += qed_grc_dump_regs_hdr(dump_buf + offset,
 					dump, 1, "eng", -1, "block", "MCP");
+	addr = BYTES_TO_DWORDS(MISC_REG_SHARED_MEM_ADDR);
 	offset += qed_grc_dump_reg_entry(p_hwfn,
 					 p_ptt,
 					 dump_buf + offset,
 					 dump,
-					 BYTES_TO_DWORDS
-					 (MISC_REG_SHARED_MEM_ADDR), 1);
+					 addr,
+					 1);
 
 	/* Release MCP */
 	if (halted && qed_mcp_resume(p_hwfn, p_ptt))
@@ -3212,7 +3479,7 @@ static u32 qed_grc_dump_static_debug(struct qed_hwfn *p_hwfn,
 {
 	u32 block_dwords = NUM_DBG_BUS_LINES * STATIC_DEBUG_LINE_DWORDS;
 	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
-	u32 offset = 0, block_id, line_id, addr, i;
+	u32 offset = 0, block_id, line_id;
 	struct block_defs *p_block_defs;
 
 	if (dump) {
@@ -3255,6 +3522,8 @@ static u32 qed_grc_dump_static_debug(struct qed_hwfn *p_hwfn,
 		if (dump && !dev_data->block_in_reset[block_id]) {
 			u8 dbg_client_id =
 				p_block_defs->dbg_client_id[dev_data->chip_id];
+			u32 addr = BYTES_TO_DWORDS(DBG_REG_CALENDAR_OUT_DATA);
+			u32 len = STATIC_DEBUG_LINE_DWORDS;
 
 			/* Enable block's client */
 			qed_bus_enable_clients(p_hwfn, p_ptt,
@@ -3270,11 +3539,13 @@ static u32 qed_grc_dump_static_debug(struct qed_hwfn *p_hwfn,
 						    0xf, 0, 0, 0);
 
 				/* Read debug line info */
-				for (i = 0, addr = DBG_REG_CALENDAR_OUT_DATA;
-				     i < STATIC_DEBUG_LINE_DWORDS;
-				     i++, offset++, addr += BYTES_IN_DWORD)
-					dump_buf[offset] = qed_rd(p_hwfn, p_ptt,
-								  addr);
+				offset +=
+				    qed_grc_dump_addr_range(p_hwfn,
+							    p_ptt,
+							    dump_buf + offset,
+							    dump,
+							    addr,
+							    len);
 			}
 
 			/* Disable block's client and debug output */
@@ -3311,14 +3582,8 @@ static enum dbg_status qed_grc_dump(struct qed_hwfn *p_hwfn,
 	u8 i, port_mode = 0;
 	u32 offset = 0;
 
-	/* Check if emulation platform */
 	*num_dumped_dwords = 0;
 
-	/* Fill GRC parameters that were not set by the user with their default
-	 * value.
-	 */
-	qed_dbg_grc_set_params_default(p_hwfn);
-
 	/* Find port mode */
 	if (dump) {
 		switch (qed_rd(p_hwfn, p_ptt, MISC_REG_PORT_MODE)) {
@@ -3370,15 +3635,14 @@ static enum dbg_status qed_grc_dump(struct qed_hwfn *p_hwfn,
 	}
 
 	/* Disable all parities using MFW command */
-	if (dump) {
+	if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_MCP)) {
 		parities_masked = !qed_mcp_mask_parities(p_hwfn, p_ptt, 1);
 		if (!parities_masked) {
+			DP_NOTICE(p_hwfn,
+				  "Failed to mask parities using MFW\n");
 			if (qed_grc_get_param
 			    (p_hwfn, DBG_GRC_PARAM_PARITY_SAFE))
 				return DBG_STATUS_MCP_COULD_NOT_MASK_PRTY;
-			else
-				DP_NOTICE(p_hwfn,
-					  "Failed to mask parities using MFW\n");
 		}
 	}
 
@@ -3409,6 +3673,11 @@ static enum dbg_status qed_grc_dump(struct qed_hwfn *p_hwfn,
 						 offset,
 						 dump,
 						 block_enable, NULL, NULL);
+
+		/* Dump special registers */
+		offset += qed_grc_dump_special_regs(p_hwfn,
+						    p_ptt,
+						    dump_buf + offset, dump);
 	}
 
 	/* Dump memories */
@@ -3583,9 +3852,9 @@ static u32 qed_idle_chk_dump_failure(struct qed_hwfn *p_hwfn,
 			}
 
 			if (mode_match) {
-				u32 grc_addr =
-					DWORDS_TO_BYTES(GET_FIELD(reg->data,
-						DBG_IDLE_CHK_INFO_REG_ADDRESS));
+				u32 addr =
+				    GET_FIELD(reg->data,
+					      DBG_IDLE_CHK_INFO_REG_ADDRESS);
 
 				/* Write register header */
 				struct dbg_idle_chk_result_reg_hdr *reg_hdr =
@@ -3597,16 +3866,19 @@ static u32 qed_idle_chk_dump_failure(struct qed_hwfn *p_hwfn,
 				memset(reg_hdr, 0, sizeof(*reg_hdr));
 				reg_hdr->size = reg->size;
 				SET_FIELD(reg_hdr->data,
-					DBG_IDLE_CHK_RESULT_REG_HDR_REG_ID,
-					rule->num_cond_regs + reg_id);
+					  DBG_IDLE_CHK_RESULT_REG_HDR_REG_ID,
+					  rule->num_cond_regs + reg_id);
 
 				/* Write register values */
-				for (i = 0; i < reg->size;
-				     i++, offset++, grc_addr += 4)
-					dump_buf[offset] =
-						qed_rd(p_hwfn, p_ptt, grc_addr);
-				}
+				offset +=
+				    qed_grc_dump_addr_range(p_hwfn,
+							    p_ptt,
+							    dump_buf + offset,
+							    dump,
+							    addr,
+							    reg->size);
 			}
+		}
 	}
 
 	return offset;
@@ -3621,7 +3893,7 @@ qed_idle_chk_dump_rule_entries(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 {
 	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
 	u32 cond_reg_values[IDLE_CHK_MAX_ENTRIES_SIZE];
-	u32 i, j, offset = 0;
+	u32 i, offset = 0;
 	u16 entry_id;
 	u8 reg_id;
 
@@ -3664,73 +3936,83 @@ qed_idle_chk_dump_rule_entries(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 		if (!check_rule && dump)
 			continue;
 
+		if (!dump) {
+			u32 entry_dump_size =
+				qed_idle_chk_dump_failure(p_hwfn,
+							  p_ptt,
+							  dump_buf + offset,
+							  false,
+							  rule->rule_id,
+							  rule,
+							  0,
+							  NULL);
+
+			offset += num_reg_entries * entry_dump_size;
+			(*num_failing_rules) += num_reg_entries;
+			continue;
+		}
+
 		/* Go over all register entries (number of entries is the same
 		 * for all condition registers).
 		 */
 		for (entry_id = 0; entry_id < num_reg_entries; entry_id++) {
 			/* Read current entry of all condition registers */
-			if (dump) {
-				u32 next_reg_offset = 0;
-
-				for (reg_id = 0;
-				     reg_id < rule->num_cond_regs;
-				     reg_id++) {
-					const struct dbg_idle_chk_cond_reg
-						*reg = &cond_regs[reg_id];
-
-					/* Find GRC address (if it's a memory,
-					 * the address of the specific entry is
-					 * calculated).
-					 */
-					u32 grc_addr =
-					   DWORDS_TO_BYTES(
-						GET_FIELD(reg->data,
-						    DBG_IDLE_CHK_COND_REG_ADDRESS));
-
-					if (reg->num_entries > 1 ||
-					    reg->start_entry > 0) {
-						u32 padded_entry_size =
-							reg->entry_size > 1 ?
-							roundup_pow_of_two
-							(reg->entry_size) : 1;
-
-						grc_addr +=
-							DWORDS_TO_BYTES(
-								(reg->start_entry +
-								entry_id)
-								* padded_entry_size);
-					}
+			u32 next_reg_offset = 0;
 
-					/* Read registers */
-					if (next_reg_offset + reg->entry_size >=
-					    IDLE_CHK_MAX_ENTRIES_SIZE) {
-						DP_NOTICE(p_hwfn,
-							  "idle check registers entry is too large\n");
-						return 0;
-					}
+			for (reg_id = 0; reg_id < rule->num_cond_regs;
+			     reg_id++) {
+				const struct dbg_idle_chk_cond_reg *reg =
+					&cond_regs[reg_id];
 
-					for (j = 0; j < reg->entry_size;
-					     j++, next_reg_offset++,
-					     grc_addr += 4)
-					     cond_reg_values[next_reg_offset] =
-						qed_rd(p_hwfn, p_ptt, grc_addr);
+				/* Find GRC address (if it's a memory,the
+				 * address of the specific entry is calculated).
+				 */
+				u32 addr =
+				    GET_FIELD(reg->data,
+					      DBG_IDLE_CHK_COND_REG_ADDRESS);
+
+				if (reg->num_entries > 1 ||
+				    reg->start_entry > 0) {
+					u32 padded_entry_size =
+					   reg->entry_size > 1 ?
+					   roundup_pow_of_two(reg->entry_size) :
+					   1;
+
+					addr += (reg->start_entry + entry_id) *
+						padded_entry_size;
 				}
+
+				/* Read registers */
+				if (next_reg_offset + reg->entry_size >=
+				    IDLE_CHK_MAX_ENTRIES_SIZE) {
+					DP_NOTICE(p_hwfn,
+						  "idle check registers entry is too large\n");
+					return 0;
+				}
+
+				next_reg_offset +=
+				    qed_grc_dump_addr_range(p_hwfn,
+							    p_ptt,
+							    cond_reg_values +
+							    next_reg_offset,
+							    dump, addr,
+							    reg->entry_size);
 			}
 
 			/* Call rule's condition function - a return value of
 			 * true indicates failure.
 			 */
 			if ((*cond_arr[rule->cond_id])(cond_reg_values,
-						       imm_values) || !dump) {
+						       imm_values)) {
 				offset +=
-					qed_idle_chk_dump_failure(p_hwfn,
-							p_ptt,
-							dump_buf + offset,
-							dump,
-							rule->rule_id,
-							rule,
-							entry_id,
-							cond_reg_values);
+				    qed_idle_chk_dump_failure(p_hwfn,
+							      p_ptt,
+							      dump_buf + offset,
+							      dump,
+							      rule->rule_id,
+							      rule,
+							      entry_id,
+							      cond_reg_values);
 				(*num_failing_rules)++;
 				break;
 			}
@@ -3818,13 +4100,18 @@ static enum dbg_status qed_find_nvram_image(struct qed_hwfn *p_hwfn,
 	struct mcp_file_att file_att;
 
 	/* Call NVRAM get file command */
-	if (qed_mcp_nvm_rd_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_NVM_GET_FILE_ATT,
-			       image_type, &ret_mcp_resp, &ret_mcp_param,
-			       &ret_txn_size, (u32 *)&file_att) != 0)
-		return DBG_STATUS_NVRAM_GET_IMAGE_FAILED;
+	int nvm_result = qed_mcp_nvm_rd_cmd(p_hwfn,
+					    p_ptt,
+					    DRV_MSG_CODE_NVM_GET_FILE_ATT,
+					    image_type,
+					    &ret_mcp_resp,
+					    &ret_mcp_param,
+					    &ret_txn_size,
+					    (u32 *)&file_att);
 
 	/* Check response */
-	if ((ret_mcp_resp & FW_MSG_CODE_MASK) != FW_MSG_CODE_NVM_OK)
+	if (nvm_result ||
+	    (ret_mcp_resp & FW_MSG_CODE_MASK) != FW_MSG_CODE_NVM_OK)
 		return DBG_STATUS_NVRAM_GET_IMAGE_FAILED;
 
 	/* Update return values */
@@ -3944,7 +4231,6 @@ static enum dbg_status qed_mcp_trace_get_meta_info(struct qed_hwfn *p_hwfn,
 	u32 running_mfw_addr =
 		MCP_REG_SCRATCH + SECTION_OFFSET(spad_trace_offsize) +
 		QED_SECTION_SIZE(spad_trace_offsize) + trace_data_size_bytes;
-	enum dbg_status status;
 	u32 nvram_image_type;
 
 	*running_bundle_id = qed_rd(p_hwfn, p_ptt, running_mfw_addr);
@@ -3955,30 +4241,12 @@ static enum dbg_status qed_mcp_trace_get_meta_info(struct qed_hwfn *p_hwfn,
 	nvram_image_type =
 	    (*running_bundle_id ==
 	     DIR_ID_1) ? NVM_TYPE_MFW_TRACE1 : NVM_TYPE_MFW_TRACE2;
-	status = qed_find_nvram_image(p_hwfn,
-				      p_ptt,
-				      nvram_image_type,
-				      trace_meta_offset_bytes,
-				      trace_meta_size_bytes);
-
-	return status;
-}
-
-/* Reads the MCP Trace data from the specified GRC address into the specified
- * buffer.
- */
-static void qed_mcp_trace_read_data(struct qed_hwfn *p_hwfn,
-				    struct qed_ptt *p_ptt,
-				    u32 grc_addr, u32 size_in_dwords, u32 *buf)
-{
-	u32 i;
 
-	DP_VERBOSE(p_hwfn,
-		   QED_MSG_DEBUG,
-		   "mcp_trace_read_data: reading trace data of size %d dwords from GRC address 0x%x\n",
-		   size_in_dwords, grc_addr);
-	for (i = 0; i < size_in_dwords; i++, grc_addr += BYTES_IN_DWORD)
-		buf[i] = qed_rd(p_hwfn, p_ptt, grc_addr);
+	return qed_find_nvram_image(p_hwfn,
+				    p_ptt,
+				    nvram_image_type,
+				    trace_meta_offset_bytes,
+				    trace_meta_size_bytes);
 }
 
 /* Reads the MCP Trace meta data (from NVRAM or buffer) into the specified
@@ -4034,11 +4302,14 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
 					  bool dump, u32 *num_dumped_dwords)
 {
 	u32 trace_data_grc_addr, trace_data_size_bytes, trace_data_size_dwords;
-	u32 trace_meta_size_dwords, running_bundle_id, offset = 0;
-	u32 trace_meta_offset_bytes, trace_meta_size_bytes;
+	u32 trace_meta_size_dwords = 0, running_bundle_id, offset = 0;
+	u32 trace_meta_offset_bytes = 0, trace_meta_size_bytes = 0;
 	enum dbg_status status;
+	bool mcp_access;
 	int halted = 0;
 
+	mcp_access = !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_MCP);
+
 	*num_dumped_dwords = 0;
 
 	/* Get trace data info */
@@ -4060,7 +4331,7 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
 	 * consistent if halt fails, MCP trace is taken anyway, with a small
 	 * risk that it may be corrupt.
 	 */
-	if (dump) {
+	if (dump && mcp_access) {
 		halted = !qed_mcp_halt(p_hwfn, p_ptt);
 		if (!halted)
 			DP_NOTICE(p_hwfn, "MCP halt failed!\n");
@@ -4078,13 +4349,12 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
 				     dump, "size", trace_data_size_dwords);
 
 	/* Read trace data from scratchpad into dump buffer */
-	if (dump)
-		qed_mcp_trace_read_data(p_hwfn,
-					p_ptt,
-					trace_data_grc_addr,
-					trace_data_size_dwords,
-					dump_buf + offset);
-	offset += trace_data_size_dwords;
+	offset += qed_grc_dump_addr_range(p_hwfn,
+					  p_ptt,
+					  dump_buf + offset,
+					  dump,
+					  BYTES_TO_DWORDS(trace_data_grc_addr),
+					  trace_data_size_dwords);
 
 	/* Resume MCP (only if halt succeeded) */
 	if (halted && qed_mcp_resume(p_hwfn, p_ptt) != 0)
@@ -4095,38 +4365,38 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
 				       dump, "mcp_trace_meta", 1);
 
 	/* Read trace meta info */
-	status = qed_mcp_trace_get_meta_info(p_hwfn,
-					     p_ptt,
-					     trace_data_size_bytes,
-					     &running_bundle_id,
-					     &trace_meta_offset_bytes,
-					     &trace_meta_size_bytes);
-	if (status != DBG_STATUS_OK)
-		return status;
+	if (mcp_access) {
+		status = qed_mcp_trace_get_meta_info(p_hwfn,
+						     p_ptt,
+						     trace_data_size_bytes,
+						     &running_bundle_id,
+						     &trace_meta_offset_bytes,
+						     &trace_meta_size_bytes);
+		if (status == DBG_STATUS_OK)
+			trace_meta_size_dwords =
+				BYTES_TO_DWORDS(trace_meta_size_bytes);
+	}
 
-	/* Dump trace meta size param (trace_meta_size_bytes is always
-	 * dword-aligned).
-	 */
-	trace_meta_size_dwords = BYTES_TO_DWORDS(trace_meta_size_bytes);
-	offset += qed_dump_num_param(dump_buf + offset,	dump, "size",
-				     trace_meta_size_dwords);
+	/* Dump trace meta size param */
+	offset += qed_dump_num_param(dump_buf + offset,
+				     dump, "size", trace_meta_size_dwords);
 
 	/* Read trace meta image into dump buffer */
-	if (dump) {
+	if (dump && trace_meta_size_dwords)
 		status = qed_mcp_trace_read_meta(p_hwfn,
-						p_ptt,
-						trace_meta_offset_bytes,
-						trace_meta_size_bytes,
-						dump_buf + offset);
-		if (status != DBG_STATUS_OK)
-			return status;
-	}
-
-	offset += trace_meta_size_dwords;
+						 p_ptt,
+						 trace_meta_offset_bytes,
+						 trace_meta_size_bytes,
+						 dump_buf + offset);
+	if (status == DBG_STATUS_OK)
+		offset += trace_meta_size_dwords;
 
 	*num_dumped_dwords = offset;
 
-	return DBG_STATUS_OK;
+	/* If no mcp access, indicate that the dump doesn't contain the meta
+	 * data from NVRAM.
+	 */
+	return mcp_access ? status : DBG_STATUS_NVRAM_GET_IMAGE_FAILED;
 }
 
 /* Dump GRC FIFO */
@@ -4311,9 +4581,10 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
 			       struct qed_ptt *p_ptt, u32 *dump_buf, bool dump)
 {
 	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+	struct fw_asserts_ram_section *asserts;
 	char storm_letter_str[2] = "?";
 	struct fw_info fw_info;
-	u32 offset = 0, i;
+	u32 offset = 0;
 	u8 storm_id;
 
 	/* Dump global params */
@@ -4323,8 +4594,8 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
 	offset += qed_dump_str_param(dump_buf + offset,
 				     dump, "dump-type", "fw-asserts");
 	for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) {
-		u32 fw_asserts_section_addr, next_list_idx_addr, next_list_idx,
-			last_list_idx, element_addr;
+		u32 fw_asserts_section_addr, next_list_idx_addr, next_list_idx;
+		u32 last_list_idx, addr;
 
 		if (dev_data->block_in_reset[s_storm_defs[storm_id].block_id])
 			continue;
@@ -4332,6 +4603,8 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
 		/* Read FW info for the current Storm */
 		qed_read_fw_info(p_hwfn, p_ptt, storm_id, &fw_info);
 
+		asserts = &fw_info.fw_asserts_section;
+
 		/* Dump FW Asserts section header and params */
 		storm_letter_str[0] = s_storm_defs[storm_id].letter;
 		offset += qed_dump_section_hdr(dump_buf + offset, dump,
@@ -4339,12 +4612,10 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
 		offset += qed_dump_str_param(dump_buf + offset, dump, "storm",
 					     storm_letter_str);
 		offset += qed_dump_num_param(dump_buf + offset, dump, "size",
-					     fw_info.fw_asserts_section.
-					     list_element_dword_size);
+					     asserts->list_element_dword_size);
 
 		if (!dump) {
-			offset += fw_info.fw_asserts_section.
-				  list_element_dword_size;
+			offset += asserts->list_element_dword_size;
 			continue;
 		}
 
@@ -4352,28 +4623,22 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
 		fw_asserts_section_addr =
 			s_storm_defs[storm_id].sem_fast_mem_addr +
 			SEM_FAST_REG_INT_RAM +
-			RAM_LINES_TO_BYTES(fw_info.fw_asserts_section.
-					   section_ram_line_offset);
+			RAM_LINES_TO_BYTES(asserts->section_ram_line_offset);
 		next_list_idx_addr =
 			fw_asserts_section_addr +
-			DWORDS_TO_BYTES(fw_info.fw_asserts_section.
-					list_next_index_dword_offset);
+			DWORDS_TO_BYTES(asserts->list_next_index_dword_offset);
 		next_list_idx = qed_rd(p_hwfn, p_ptt, next_list_idx_addr);
 		last_list_idx = (next_list_idx > 0
 				 ? next_list_idx
-				 : fw_info.fw_asserts_section.list_num_elements)
-				- 1;
-		element_addr =
-			fw_asserts_section_addr +
-			DWORDS_TO_BYTES(fw_info.fw_asserts_section.
-					list_dword_offset) +
-			last_list_idx *
-			DWORDS_TO_BYTES(fw_info.fw_asserts_section.
-					list_element_dword_size);
-		for (i = 0;
-		     i < fw_info.fw_asserts_section.list_element_dword_size;
-		     i++, offset++, element_addr += BYTES_IN_DWORD)
-			dump_buf[offset] = qed_rd(p_hwfn, p_ptt, element_addr);
+				 : asserts->list_num_elements) - 1;
+		addr = BYTES_TO_DWORDS(fw_asserts_section_addr) +
+		       asserts->list_dword_offset +
+		       last_list_idx * asserts->list_element_dword_size;
+		offset +=
+		    qed_grc_dump_addr_range(p_hwfn, p_ptt,
+					    dump_buf + offset,
+					    dump, addr,
+					    asserts->list_element_dword_size);
 	}
 
 	/* Dump last section */
@@ -4386,13 +4651,10 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
 enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr)
 {
 	/* Convert binary data to debug arrays */
-	u32 num_of_buffers = *(u32 *)bin_ptr;
-	struct bin_buffer_hdr *buf_array;
+	struct bin_buffer_hdr *buf_array = (struct bin_buffer_hdr *)bin_ptr;
 	u8 buf_id;
 
-	buf_array = (struct bin_buffer_hdr *)((u32 *)bin_ptr + 1);
-
-	for (buf_id = 0; buf_id < num_of_buffers; buf_id++) {
+	for (buf_id = 0; buf_id < MAX_BIN_DBG_BUFFER_TYPE; buf_id++) {
 		s_dbg_arrays[buf_id].ptr =
 		    (u32 *)(bin_ptr + buf_array[buf_id].offset);
 		s_dbg_arrays[buf_id].size_in_dwords =
@@ -4402,6 +4664,17 @@ enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr)
 	return DBG_STATUS_OK;
 }
 
+/* Assign default GRC param values */
+void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn)
+{
+	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+	u32 i;
+
+	for (i = 0; i < MAX_DBG_GRC_PARAMS; i++)
+		dev_data->grc.param_val[i] =
+		    s_grc_param_defs[i].default_val[dev_data->chip_id];
+}
+
 enum dbg_status qed_dbg_grc_get_dump_buf_size(struct qed_hwfn *p_hwfn,
 					      struct qed_ptt *p_ptt,
 					      u32 *buf_size)
@@ -4441,8 +4714,9 @@ enum dbg_status qed_dbg_grc_dump(struct qed_hwfn *p_hwfn,
 	/* GRC Dump */
 	status = qed_grc_dump(p_hwfn, p_ptt, dump_buf, true, num_dumped_dwords);
 
-	/* Clear all GRC params */
-	qed_dbg_grc_clear_params(p_hwfn);
+	/* Revert GRC params to their default */
+	qed_dbg_grc_set_params_default(p_hwfn);
+
 	return status;
 }
 
@@ -4495,6 +4769,10 @@ enum dbg_status qed_dbg_idle_chk_dump(struct qed_hwfn *p_hwfn,
 
 	/* Idle Check Dump */
 	*num_dumped_dwords = qed_idle_chk_dump(p_hwfn, p_ptt, dump_buf, true);
+
+	/* Revert GRC params to their default */
+	qed_dbg_grc_set_params_default(p_hwfn);
+
 	return DBG_STATUS_OK;
 }
 
@@ -4519,11 +4797,15 @@ enum dbg_status qed_dbg_mcp_trace_dump(struct qed_hwfn *p_hwfn,
 	u32 needed_buf_size_in_dwords;
 	enum dbg_status status;
 
-	status = qed_dbg_mcp_trace_get_dump_buf_size(p_hwfn, p_ptt,
+	/* validate buffer size */
+	status =
+	    qed_dbg_mcp_trace_get_dump_buf_size(p_hwfn, p_ptt,
 						&needed_buf_size_in_dwords);
 
-	if (status != DBG_STATUS_OK)
+	if (status != DBG_STATUS_OK &&
+	    status != DBG_STATUS_NVRAM_GET_IMAGE_FAILED)
 		return status;
+
 	if (buf_size_in_dwords < needed_buf_size_in_dwords)
 		return DBG_STATUS_DUMP_BUF_TOO_SMALL;
 
@@ -4531,8 +4813,13 @@ enum dbg_status qed_dbg_mcp_trace_dump(struct qed_hwfn *p_hwfn,
 	qed_update_blocks_reset_state(p_hwfn, p_ptt);
 
 	/* Perform dump */
-	return qed_mcp_trace_dump(p_hwfn,
-				  p_ptt, dump_buf, true, num_dumped_dwords);
+	status = qed_mcp_trace_dump(p_hwfn,
+				    p_ptt, dump_buf, true, num_dumped_dwords);
+
+	/* Revert GRC params to their default */
+	qed_dbg_grc_set_params_default(p_hwfn);
+
+	return status;
 }
 
 enum dbg_status qed_dbg_reg_fifo_get_dump_buf_size(struct qed_hwfn *p_hwfn,
@@ -4567,8 +4854,14 @@ enum dbg_status qed_dbg_reg_fifo_dump(struct qed_hwfn *p_hwfn,
 
 	/* Update reset state */
 	qed_update_blocks_reset_state(p_hwfn, p_ptt);
-	return qed_reg_fifo_dump(p_hwfn,
-				 p_ptt, dump_buf, true, num_dumped_dwords);
+
+	status = qed_reg_fifo_dump(p_hwfn,
+				   p_ptt, dump_buf, true, num_dumped_dwords);
+
+	/* Revert GRC params to their default */
+	qed_dbg_grc_set_params_default(p_hwfn);
+
+	return status;
 }
 
 enum dbg_status qed_dbg_igu_fifo_get_dump_buf_size(struct qed_hwfn *p_hwfn,
@@ -4603,8 +4896,13 @@ enum dbg_status qed_dbg_igu_fifo_dump(struct qed_hwfn *p_hwfn,
 
 	/* Update reset state */
 	qed_update_blocks_reset_state(p_hwfn, p_ptt);
-	return qed_igu_fifo_dump(p_hwfn,
-				 p_ptt, dump_buf, true, num_dumped_dwords);
+
+	status = qed_igu_fifo_dump(p_hwfn,
+				   p_ptt, dump_buf, true, num_dumped_dwords);
+	/* Revert GRC params to their default */
+	qed_dbg_grc_set_params_default(p_hwfn);
+
+	return status;
 }
 
 enum dbg_status
@@ -4641,9 +4939,16 @@ enum dbg_status qed_dbg_protection_override_dump(struct qed_hwfn *p_hwfn,
 
 	/* Update reset state */
 	qed_update_blocks_reset_state(p_hwfn, p_ptt);
-	return qed_protection_override_dump(p_hwfn,
-					    p_ptt,
-					    dump_buf, true, num_dumped_dwords);
+
+	status = qed_protection_override_dump(p_hwfn,
+					      p_ptt,
+					      dump_buf,
+					      true, num_dumped_dwords);
+
+	/* Revert GRC params to their default */
+	qed_dbg_grc_set_params_default(p_hwfn);
+
+	return status;
 }
 
 enum dbg_status qed_dbg_fw_asserts_get_dump_buf_size(struct qed_hwfn *p_hwfn,
@@ -5045,13 +5350,10 @@ static char s_temp_buf[MAX_MSG_LEN];
 enum dbg_status qed_dbg_user_set_bin_ptr(const u8 * const bin_ptr)
 {
 	/* Convert binary data to debug arrays */
-	u32 num_of_buffers = *(u32 *)bin_ptr;
-	struct bin_buffer_hdr *buf_array;
+	struct bin_buffer_hdr *buf_array = (struct bin_buffer_hdr *)bin_ptr;
 	u8 buf_id;
 
-	buf_array = (struct bin_buffer_hdr *)((u32 *)bin_ptr + 1);
-
-	for (buf_id = 0; buf_id < num_of_buffers; buf_id++) {
+	for (buf_id = 0; buf_id < MAX_BIN_DBG_BUFFER_TYPE; buf_id++) {
 		s_dbg_arrays[buf_id].ptr =
 		    (u32 *)(bin_ptr + buf_array[buf_id].offset);
 		s_dbg_arrays[buf_id].size_in_dwords =
@@ -5874,16 +6176,16 @@ static enum dbg_status qed_parse_reg_fifo_dump(struct qed_hwfn *p_hwfn,
 		results_offset +=
 		    sprintf(qed_get_buf_ptr(results_buf,
 					    results_offset),
-			    "raw: 0x%016llx, address: 0x%07llx, access: %-5s, pf: %2lld, vf: %s, port: %lld, privilege: %-3s, protection: %-12s, master: %-4s, errors: ",
+			    "raw: 0x%016llx, address: 0x%07x, access: %-5s, pf: %2d, vf: %s, port: %d, privilege: %-3s, protection: %-12s, master: %-4s, errors: ",
 			    elements[i].data,
-			    GET_FIELD(elements[i].data,
+			    (u32)GET_FIELD(elements[i].data,
 				      REG_FIFO_ELEMENT_ADDRESS) *
 				      REG_FIFO_ELEMENT_ADDR_FACTOR,
 				      s_access_strs[GET_FIELD(elements[i].data,
 						    REG_FIFO_ELEMENT_ACCESS)],
-			    GET_FIELD(elements[i].data,
-				      REG_FIFO_ELEMENT_PF), vf_str,
-			    GET_FIELD(elements[i].data,
+			    (u32)GET_FIELD(elements[i].data,
+					   REG_FIFO_ELEMENT_PF), vf_str,
+			    (u32)GET_FIELD(elements[i].data,
 				      REG_FIFO_ELEMENT_PORT),
 				      s_privilege_strs[GET_FIELD(elements[i].
 				      data,
@@ -6189,13 +6491,13 @@ qed_parse_protection_override_dump(struct qed_hwfn *p_hwfn,
 		results_offset +=
 		    sprintf(qed_get_buf_ptr(results_buf,
 					    results_offset),
-			    "window %2d, address: 0x%07x, size: %7lld regs, read: %lld, write: %lld, read protection: %-12s, write protection: %-12s\n",
+			    "window %2d, address: 0x%07x, size: %7d regs, read: %d, write: %d, read protection: %-12s, write protection: %-12s\n",
 			    i, address,
-			    GET_FIELD(elements[i].data,
+			    (u32)GET_FIELD(elements[i].data,
 				      PROTECTION_OVERRIDE_ELEMENT_WINDOW_SIZE),
-			    GET_FIELD(elements[i].data,
+			    (u32)GET_FIELD(elements[i].data,
 				      PROTECTION_OVERRIDE_ELEMENT_READ),
-			    GET_FIELD(elements[i].data,
+			    (u32)GET_FIELD(elements[i].data,
 				      PROTECTION_OVERRIDE_ELEMENT_WRITE),
 			    s_protection_strs[GET_FIELD(elements[i].data,
 				PROTECTION_OVERRIDE_ELEMENT_READ_PROTECTION)],
@@ -6508,7 +6810,7 @@ static enum dbg_status qed_dbg_dump(struct qed_hwfn *p_hwfn,
 	 */
 	rc = qed_features_lookup[feature_idx].get_size(p_hwfn, p_ptt,
 						       &buf_size_dwords);
-	if (rc != DBG_STATUS_OK)
+	if (rc != DBG_STATUS_OK && rc != DBG_STATUS_NVRAM_GET_IMAGE_FAILED)
 		return rc;
 	feature->buf_size = buf_size_dwords * sizeof(u32);
 	feature->dump_buf = vmalloc(feature->buf_size);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index e518f914eab1..249878533fd9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -186,195 +186,569 @@ void qed_resc_free(struct qed_dev *cdev)
 	}
 }
 
-static int qed_init_qm_info(struct qed_hwfn *p_hwfn, bool b_sleepable)
+/******************** QM initialization *******************/
+#define ACTIVE_TCS_BMAP 0x9f
+#define ACTIVE_TCS_BMAP_4PORT_K2 0xf
+
+/* determines the physical queue flags for a given PF. */
+static u32 qed_get_pq_flags(struct qed_hwfn *p_hwfn)
 {
-	u8 num_vports, vf_offset = 0, i, vport_id, num_ports, curr_queue = 0;
-	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
-	struct init_qm_port_params *p_qm_port;
-	bool init_rdma_offload_pq = false;
-	bool init_pure_ack_pq = false;
-	bool init_ooo_pq = false;
-	u16 num_pqs, multi_cos_tcs = 1;
-	u8 pf_wfq = qm_info->pf_wfq;
-	u32 pf_rl = qm_info->pf_rl;
-	u16 num_pf_rls = 0;
-	u16 num_vfs = 0;
-
-#ifdef CONFIG_QED_SRIOV
-	if (p_hwfn->cdev->p_iov_info)
-		num_vfs = p_hwfn->cdev->p_iov_info->total_vfs;
-#endif
-	memset(qm_info, 0, sizeof(*qm_info));
+	u32 flags;
 
-	num_pqs = multi_cos_tcs + num_vfs + 1;	/* The '1' is for pure-LB */
-	num_vports = (u8)RESC_NUM(p_hwfn, QED_VPORT);
+	/* common flags */
+	flags = PQ_FLAGS_LB;
 
-	if (p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE) {
-		num_pqs++;	/* for RoCE queue */
-		init_rdma_offload_pq = true;
-		/* we subtract num_vfs because each require a rate limiter,
-		 * and one default rate limiter
-		 */
-		if (p_hwfn->pf_params.rdma_pf_params.enable_dcqcn)
-			num_pf_rls = RESC_NUM(p_hwfn, QED_RL) - num_vfs - 1;
+	/* feature flags */
+	if (IS_QED_SRIOV(p_hwfn->cdev))
+		flags |= PQ_FLAGS_VFS;
 
-		num_pqs += num_pf_rls;
-		qm_info->num_pf_rls = (u8) num_pf_rls;
+	/* protocol flags */
+	switch (p_hwfn->hw_info.personality) {
+	case QED_PCI_ETH:
+		flags |= PQ_FLAGS_MCOS;
+		break;
+	case QED_PCI_FCOE:
+		flags |= PQ_FLAGS_OFLD;
+		break;
+	case QED_PCI_ISCSI:
+		flags |= PQ_FLAGS_ACK | PQ_FLAGS_OOO | PQ_FLAGS_OFLD;
+		break;
+	case QED_PCI_ETH_ROCE:
+		flags |= PQ_FLAGS_MCOS | PQ_FLAGS_OFLD | PQ_FLAGS_LLT;
+		break;
+	default:
+		DP_ERR(p_hwfn,
+		       "unknown personality %d\n", p_hwfn->hw_info.personality);
+		return 0;
 	}
 
-	if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) {
-		num_pqs += 2;	/* for iSCSI pure-ACK / OOO queue */
-		init_pure_ack_pq = true;
-		init_ooo_pq = true;
-	}
+	return flags;
+}
 
-	/* Sanity checking that setup requires legal number of resources */
-	if (num_pqs > RESC_NUM(p_hwfn, QED_PQ)) {
-		DP_ERR(p_hwfn,
-		       "Need too many Physical queues - 0x%04x when only %04x are available\n",
-		       num_pqs, RESC_NUM(p_hwfn, QED_PQ));
-		return -EINVAL;
-	}
+/* Getters for resource amounts necessary for qm initialization */
+u8 qed_init_qm_get_num_tcs(struct qed_hwfn *p_hwfn)
+{
+	return p_hwfn->hw_info.num_hw_tc;
+}
 
-	/* PQs will be arranged as follows: First per-TC PQ then pure-LB quete.
-	 */
-	qm_info->qm_pq_params = kcalloc(num_pqs,
-					sizeof(struct init_qm_pq_params),
-					b_sleepable ? GFP_KERNEL : GFP_ATOMIC);
-	if (!qm_info->qm_pq_params)
-		goto alloc_err;
+u16 qed_init_qm_get_num_vfs(struct qed_hwfn *p_hwfn)
+{
+	return IS_QED_SRIOV(p_hwfn->cdev) ?
+	       p_hwfn->cdev->p_iov_info->total_vfs : 0;
+}
 
-	qm_info->qm_vport_params = kcalloc(num_vports,
-					   sizeof(struct init_qm_vport_params),
-					   b_sleepable ? GFP_KERNEL
-						       : GFP_ATOMIC);
-	if (!qm_info->qm_vport_params)
-		goto alloc_err;
+#define NUM_DEFAULT_RLS 1
 
-	qm_info->qm_port_params = kcalloc(MAX_NUM_PORTS,
-					  sizeof(struct init_qm_port_params),
-					  b_sleepable ? GFP_KERNEL
-						      : GFP_ATOMIC);
-	if (!qm_info->qm_port_params)
-		goto alloc_err;
+u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn)
+{
+	u16 num_pf_rls, num_vfs = qed_init_qm_get_num_vfs(p_hwfn);
 
-	qm_info->wfq_data = kcalloc(num_vports, sizeof(struct qed_wfq_data),
-				    b_sleepable ? GFP_KERNEL : GFP_ATOMIC);
-	if (!qm_info->wfq_data)
-		goto alloc_err;
+	/* num RLs can't exceed resource amount of rls or vports */
+	num_pf_rls = (u16) min_t(u32, RESC_NUM(p_hwfn, QED_RL),
+				 RESC_NUM(p_hwfn, QED_VPORT));
 
-	vport_id = (u8)RESC_START(p_hwfn, QED_VPORT);
+	/* Make sure after we reserve there's something left */
+	if (num_pf_rls < num_vfs + NUM_DEFAULT_RLS)
+		return 0;
 
-	/* First init rate limited queues */
-	for (curr_queue = 0; curr_queue < num_pf_rls; curr_queue++) {
-		qm_info->qm_pq_params[curr_queue].vport_id = vport_id++;
-		qm_info->qm_pq_params[curr_queue].tc_id =
-		    p_hwfn->hw_info.non_offload_tc;
-		qm_info->qm_pq_params[curr_queue].wrr_group = 1;
-		qm_info->qm_pq_params[curr_queue].rl_valid = 1;
-	}
+	/* subtract rls necessary for VFs and one default one for the PF */
+	num_pf_rls -= num_vfs + NUM_DEFAULT_RLS;
 
-	/* First init per-TC PQs */
-	for (i = 0; i < multi_cos_tcs; i++) {
-		struct init_qm_pq_params *params =
-		    &qm_info->qm_pq_params[curr_queue++];
+	return num_pf_rls;
+}
 
-		if (p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE ||
-		    p_hwfn->hw_info.personality == QED_PCI_ETH) {
-			params->vport_id = vport_id;
-			params->tc_id = p_hwfn->hw_info.non_offload_tc;
-			params->wrr_group = 1;
-		} else {
-			params->vport_id = vport_id;
-			params->tc_id = p_hwfn->hw_info.offload_tc;
-			params->wrr_group = 1;
-		}
-	}
+u16 qed_init_qm_get_num_vports(struct qed_hwfn *p_hwfn)
+{
+	u32 pq_flags = qed_get_pq_flags(p_hwfn);
 
-	/* Then init pure-LB PQ */
-	qm_info->pure_lb_pq = curr_queue;
-	qm_info->qm_pq_params[curr_queue].vport_id =
-	    (u8) RESC_START(p_hwfn, QED_VPORT);
-	qm_info->qm_pq_params[curr_queue].tc_id = PURE_LB_TC;
-	qm_info->qm_pq_params[curr_queue].wrr_group = 1;
-	curr_queue++;
-
-	qm_info->offload_pq = 0;
-	if (init_rdma_offload_pq) {
-		qm_info->offload_pq = curr_queue;
-		qm_info->qm_pq_params[curr_queue].vport_id = vport_id;
-		qm_info->qm_pq_params[curr_queue].tc_id =
-		    p_hwfn->hw_info.offload_tc;
-		qm_info->qm_pq_params[curr_queue].wrr_group = 1;
-		curr_queue++;
-	}
-
-	if (init_pure_ack_pq) {
-		qm_info->pure_ack_pq = curr_queue;
-		qm_info->qm_pq_params[curr_queue].vport_id = vport_id;
-		qm_info->qm_pq_params[curr_queue].tc_id =
-		    p_hwfn->hw_info.offload_tc;
-		qm_info->qm_pq_params[curr_queue].wrr_group = 1;
-		curr_queue++;
-	}
-
-	if (init_ooo_pq) {
-		qm_info->ooo_pq = curr_queue;
-		qm_info->qm_pq_params[curr_queue].vport_id = vport_id;
-		qm_info->qm_pq_params[curr_queue].tc_id = DCBX_ISCSI_OOO_TC;
-		qm_info->qm_pq_params[curr_queue].wrr_group = 1;
-		curr_queue++;
-	}
-
-	/* Then init per-VF PQs */
-	vf_offset = curr_queue;
-	for (i = 0; i < num_vfs; i++) {
-		/* First vport is used by the PF */
-		qm_info->qm_pq_params[curr_queue].vport_id = vport_id + i + 1;
-		qm_info->qm_pq_params[curr_queue].tc_id =
-		    p_hwfn->hw_info.non_offload_tc;
-		qm_info->qm_pq_params[curr_queue].wrr_group = 1;
-		qm_info->qm_pq_params[curr_queue].rl_valid = 1;
-		curr_queue++;
-	}
-
-	qm_info->vf_queues_offset = vf_offset;
-	qm_info->num_pqs = num_pqs;
-	qm_info->num_vports = num_vports;
+	/* all pqs share the same vport, except for vfs and pf_rl pqs */
+	return (!!(PQ_FLAGS_RLS & pq_flags)) *
+	       qed_init_qm_get_num_pf_rls(p_hwfn) +
+	       (!!(PQ_FLAGS_VFS & pq_flags)) *
+	       qed_init_qm_get_num_vfs(p_hwfn) + 1;
+}
+
+/* calc amount of PQs according to the requested flags */
+u16 qed_init_qm_get_num_pqs(struct qed_hwfn *p_hwfn)
+{
+	u32 pq_flags = qed_get_pq_flags(p_hwfn);
+
+	return (!!(PQ_FLAGS_RLS & pq_flags)) *
+	       qed_init_qm_get_num_pf_rls(p_hwfn) +
+	       (!!(PQ_FLAGS_MCOS & pq_flags)) *
+	       qed_init_qm_get_num_tcs(p_hwfn) +
+	       (!!(PQ_FLAGS_LB & pq_flags)) + (!!(PQ_FLAGS_OOO & pq_flags)) +
+	       (!!(PQ_FLAGS_ACK & pq_flags)) + (!!(PQ_FLAGS_OFLD & pq_flags)) +
+	       (!!(PQ_FLAGS_LLT & pq_flags)) +
+	       (!!(PQ_FLAGS_VFS & pq_flags)) * qed_init_qm_get_num_vfs(p_hwfn);
+}
+
+/* initialize the top level QM params */
+static void qed_init_qm_params(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+	bool four_port;
+
+	/* pq and vport bases for this PF */
+	qm_info->start_pq = (u16) RESC_START(p_hwfn, QED_PQ);
+	qm_info->start_vport = (u8) RESC_START(p_hwfn, QED_VPORT);
 
+	/* rate limiting and weighted fair queueing are always enabled */
+	qm_info->vport_rl_en = 1;
+	qm_info->vport_wfq_en = 1;
+
+	/* TC config is different for AH 4 port */
+	four_port = p_hwfn->cdev->num_ports_in_engines == MAX_NUM_PORTS_K2;
+
+	/* in AH 4 port we have fewer TCs per port */
+	qm_info->max_phys_tcs_per_port = four_port ? NUM_PHYS_TCS_4PORT_K2 :
+						     NUM_OF_PHYS_TCS;
+
+	/* unless MFW indicated otherwise, ooo_tc == 3 for
+	 * AH 4-port and 4 otherwise.
+	 */
+	if (!qm_info->ooo_tc)
+		qm_info->ooo_tc = four_port ? DCBX_TCP_OOO_K2_4PORT_TC :
+					      DCBX_TCP_OOO_TC;
+}
+
+/* initialize qm vport params */
+static void qed_init_qm_vport_params(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+	u8 i;
+
+	/* all vports participate in weighted fair queueing */
+	for (i = 0; i < qed_init_qm_get_num_vports(p_hwfn); i++)
+		qm_info->qm_vport_params[i].vport_wfq = 1;
+}
+
+/* initialize qm port params */
+static void qed_init_qm_port_params(struct qed_hwfn *p_hwfn)
+{
 	/* Initialize qm port parameters */
-	num_ports = p_hwfn->cdev->num_ports_in_engines;
+	u8 i, active_phys_tcs, num_ports = p_hwfn->cdev->num_ports_in_engines;
+
+	/* indicate how ooo and high pri traffic is dealt with */
+	active_phys_tcs = num_ports == MAX_NUM_PORTS_K2 ?
+			  ACTIVE_TCS_BMAP_4PORT_K2 :
+			  ACTIVE_TCS_BMAP;
+
 	for (i = 0; i < num_ports; i++) {
-		p_qm_port = &qm_info->qm_port_params[i];
+		struct init_qm_port_params *p_qm_port =
+		    &p_hwfn->qm_info.qm_port_params[i];
+
 		p_qm_port->active = 1;
-		if (num_ports == 4)
-			p_qm_port->active_phys_tcs = 0x7;
-		else
-			p_qm_port->active_phys_tcs = 0x9f;
+		p_qm_port->active_phys_tcs = active_phys_tcs;
 		p_qm_port->num_pbf_cmd_lines = PBF_MAX_CMD_LINES / num_ports;
 		p_qm_port->num_btb_blocks = BTB_MAX_BLOCKS / num_ports;
 	}
+}
+
+/* Reset the params which must be reset for qm init. QM init may be called as
+ * a result of flows other than driver load (e.g. dcbx renegotiation). Other
+ * params may be affected by the init but would simply recalculate to the same
+ * values. The allocations made for QM init, ports, vports, pqs and vfqs are not
+ * affected as these amounts stay the same.
+ */
+static void qed_init_qm_reset_params(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+	qm_info->num_pqs = 0;
+	qm_info->num_vports = 0;
+	qm_info->num_pf_rls = 0;
+	qm_info->num_vf_pqs = 0;
+	qm_info->first_vf_pq = 0;
+	qm_info->first_mcos_pq = 0;
+	qm_info->first_rl_pq = 0;
+}
+
+static void qed_init_qm_advance_vport(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+	qm_info->num_vports++;
+
+	if (qm_info->num_vports > qed_init_qm_get_num_vports(p_hwfn))
+		DP_ERR(p_hwfn,
+		       "vport overflow! qm_info->num_vports %d, qm_init_get_num_vports() %d\n",
+		       qm_info->num_vports, qed_init_qm_get_num_vports(p_hwfn));
+}
+
+/* initialize a single pq and manage qm_info resources accounting.
+ * The pq_init_flags param determines whether the PQ is rate limited
+ * (for VF or PF) and whether a new vport is allocated to the pq or not
+ * (i.e. vport will be shared).
+ */
+
+/* flags for pq init */
+#define PQ_INIT_SHARE_VPORT     (1 << 0)
+#define PQ_INIT_PF_RL           (1 << 1)
+#define PQ_INIT_VF_RL           (1 << 2)
+
+/* defines for pq init */
+#define PQ_INIT_DEFAULT_WRR_GROUP       1
+#define PQ_INIT_DEFAULT_TC              0
+#define PQ_INIT_OFLD_TC                 (p_hwfn->hw_info.offload_tc)
+
+static void qed_init_qm_pq(struct qed_hwfn *p_hwfn,
+			   struct qed_qm_info *qm_info,
+			   u8 tc, u32 pq_init_flags)
+{
+	u16 pq_idx = qm_info->num_pqs, max_pq = qed_init_qm_get_num_pqs(p_hwfn);
+
+	if (pq_idx > max_pq)
+		DP_ERR(p_hwfn,
+		       "pq overflow! pq %d, max pq %d\n", pq_idx, max_pq);
+
+	/* init pq params */
+	qm_info->qm_pq_params[pq_idx].vport_id = qm_info->start_vport +
+	    qm_info->num_vports;
+	qm_info->qm_pq_params[pq_idx].tc_id = tc;
+	qm_info->qm_pq_params[pq_idx].wrr_group = PQ_INIT_DEFAULT_WRR_GROUP;
+	qm_info->qm_pq_params[pq_idx].rl_valid =
+	    (pq_init_flags & PQ_INIT_PF_RL || pq_init_flags & PQ_INIT_VF_RL);
+
+	/* qm params accounting */
+	qm_info->num_pqs++;
+	if (!(pq_init_flags & PQ_INIT_SHARE_VPORT))
+		qm_info->num_vports++;
+
+	if (pq_init_flags & PQ_INIT_PF_RL)
+		qm_info->num_pf_rls++;
+
+	if (qm_info->num_vports > qed_init_qm_get_num_vports(p_hwfn))
+		DP_ERR(p_hwfn,
+		       "vport overflow! qm_info->num_vports %d, qm_init_get_num_vports() %d\n",
+		       qm_info->num_vports, qed_init_qm_get_num_vports(p_hwfn));
+
+	if (qm_info->num_pf_rls > qed_init_qm_get_num_pf_rls(p_hwfn))
+		DP_ERR(p_hwfn,
+		       "rl overflow! qm_info->num_pf_rls %d, qm_init_get_num_pf_rls() %d\n",
+		       qm_info->num_pf_rls, qed_init_qm_get_num_pf_rls(p_hwfn));
+}
+
+/* get pq index according to PQ_FLAGS */
+static u16 *qed_init_qm_get_idx_from_flags(struct qed_hwfn *p_hwfn,
+					   u32 pq_flags)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+	/* Can't have multiple flags set here */
+	if (bitmap_weight((unsigned long *)&pq_flags, sizeof(pq_flags)) > 1)
+		goto err;
+
+	switch (pq_flags) {
+	case PQ_FLAGS_RLS:
+		return &qm_info->first_rl_pq;
+	case PQ_FLAGS_MCOS:
+		return &qm_info->first_mcos_pq;
+	case PQ_FLAGS_LB:
+		return &qm_info->pure_lb_pq;
+	case PQ_FLAGS_OOO:
+		return &qm_info->ooo_pq;
+	case PQ_FLAGS_ACK:
+		return &qm_info->pure_ack_pq;
+	case PQ_FLAGS_OFLD:
+		return &qm_info->offload_pq;
+	case PQ_FLAGS_LLT:
+		return &qm_info->low_latency_pq;
+	case PQ_FLAGS_VFS:
+		return &qm_info->first_vf_pq;
+	default:
+		goto err;
+	}
+
+err:
+	DP_ERR(p_hwfn, "BAD pq flags %d\n", pq_flags);
+	return NULL;
+}
+
+/* save pq index in qm info */
+static void qed_init_qm_set_idx(struct qed_hwfn *p_hwfn,
+				u32 pq_flags, u16 pq_val)
+{
+	u16 *base_pq_idx = qed_init_qm_get_idx_from_flags(p_hwfn, pq_flags);
+
+	*base_pq_idx = p_hwfn->qm_info.start_pq + pq_val;
+}
+
+/* get tx pq index, with the PQ TX base already set (ready for context init) */
+u16 qed_get_cm_pq_idx(struct qed_hwfn *p_hwfn, u32 pq_flags)
+{
+	u16 *base_pq_idx = qed_init_qm_get_idx_from_flags(p_hwfn, pq_flags);
+
+	return *base_pq_idx + CM_TX_PQ_BASE;
+}
+
+u16 qed_get_cm_pq_idx_mcos(struct qed_hwfn *p_hwfn, u8 tc)
+{
+	u8 max_tc = qed_init_qm_get_num_tcs(p_hwfn);
+
+	if (tc > max_tc)
+		DP_ERR(p_hwfn, "tc %d must be smaller than %d\n", tc, max_tc);
+
+	return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_MCOS) + tc;
+}
+
+u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf)
+{
+	u16 max_vf = qed_init_qm_get_num_vfs(p_hwfn);
+
+	if (vf > max_vf)
+		DP_ERR(p_hwfn, "vf %d must be smaller than %d\n", vf, max_vf);
+
+	return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_VFS) + vf;
+}
+
+u16 qed_get_cm_pq_idx_rl(struct qed_hwfn *p_hwfn, u8 rl)
+{
+	u16 max_rl = qed_init_qm_get_num_pf_rls(p_hwfn);
+
+	if (rl > max_rl)
+		DP_ERR(p_hwfn, "rl %d must be smaller than %d\n", rl, max_rl);
+
+	return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_RLS) + rl;
+}
+
+/* Functions for creating specific types of pqs */
+static void qed_init_qm_lb_pq(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+	if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_LB))
+		return;
+
+	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_LB, qm_info->num_pqs);
+	qed_init_qm_pq(p_hwfn, qm_info, PURE_LB_TC, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_ooo_pq(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+	if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_OOO))
+		return;
+
+	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_OOO, qm_info->num_pqs);
+	qed_init_qm_pq(p_hwfn, qm_info, qm_info->ooo_tc, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_pure_ack_pq(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+	if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_ACK))
+		return;
+
+	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_ACK, qm_info->num_pqs);
+	qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_offload_pq(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+	if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_OFLD))
+		return;
 
-	qm_info->max_phys_tcs_per_port = NUM_OF_PHYS_TCS;
+	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_OFLD, qm_info->num_pqs);
+	qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+}
 
-	qm_info->start_pq = (u16)RESC_START(p_hwfn, QED_PQ);
+static void qed_init_qm_low_latency_pq(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
 
+	if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_LLT))
+		return;
+
+	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_LLT, qm_info->num_pqs);
+	qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_mcos_pqs(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+	u8 tc_idx;
+
+	if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_MCOS))
+		return;
+
+	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_MCOS, qm_info->num_pqs);
+	for (tc_idx = 0; tc_idx < qed_init_qm_get_num_tcs(p_hwfn); tc_idx++)
+		qed_init_qm_pq(p_hwfn, qm_info, tc_idx, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_vf_pqs(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+	u16 vf_idx, num_vfs = qed_init_qm_get_num_vfs(p_hwfn);
+
+	if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_VFS))
+		return;
+
+	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_VFS, qm_info->num_pqs);
 	qm_info->num_vf_pqs = num_vfs;
-	qm_info->start_vport = (u8) RESC_START(p_hwfn, QED_VPORT);
+	for (vf_idx = 0; vf_idx < num_vfs; vf_idx++)
+		qed_init_qm_pq(p_hwfn,
+			       qm_info, PQ_INIT_DEFAULT_TC, PQ_INIT_VF_RL);
+}
 
-	for (i = 0; i < qm_info->num_vports; i++)
-		qm_info->qm_vport_params[i].vport_wfq = 1;
+static void qed_init_qm_rl_pqs(struct qed_hwfn *p_hwfn)
+{
+	u16 pf_rls_idx, num_pf_rls = qed_init_qm_get_num_pf_rls(p_hwfn);
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
 
-	qm_info->vport_rl_en = 1;
-	qm_info->vport_wfq_en = 1;
-	qm_info->pf_rl = pf_rl;
-	qm_info->pf_wfq = pf_wfq;
+	if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_RLS))
+		return;
+
+	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_RLS, qm_info->num_pqs);
+	for (pf_rls_idx = 0; pf_rls_idx < num_pf_rls; pf_rls_idx++)
+		qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_PF_RL);
+}
+
+static void qed_init_qm_pq_params(struct qed_hwfn *p_hwfn)
+{
+	/* rate limited pqs, must come first (FW assumption) */
+	qed_init_qm_rl_pqs(p_hwfn);
+
+	/* pqs for multi cos */
+	qed_init_qm_mcos_pqs(p_hwfn);
+
+	/* pure loopback pq */
+	qed_init_qm_lb_pq(p_hwfn);
+
+	/* out of order pq */
+	qed_init_qm_ooo_pq(p_hwfn);
+
+	/* pure ack pq */
+	qed_init_qm_pure_ack_pq(p_hwfn);
+
+	/* pq for offloaded protocol */
+	qed_init_qm_offload_pq(p_hwfn);
+
+	/* low latency pq */
+	qed_init_qm_low_latency_pq(p_hwfn);
+
+	/* done sharing vports */
+	qed_init_qm_advance_vport(p_hwfn);
+
+	/* pqs for vfs */
+	qed_init_qm_vf_pqs(p_hwfn);
+}
+
+/* compare values of getters against resources amounts */
+static int qed_init_qm_sanity(struct qed_hwfn *p_hwfn)
+{
+	if (qed_init_qm_get_num_vports(p_hwfn) > RESC_NUM(p_hwfn, QED_VPORT)) {
+		DP_ERR(p_hwfn, "requested amount of vports exceeds resource\n");
+		return -EINVAL;
+	}
+
+	if (qed_init_qm_get_num_pqs(p_hwfn) > RESC_NUM(p_hwfn, QED_PQ)) {
+		DP_ERR(p_hwfn, "requested amount of pqs exceeds resource\n");
+		return -EINVAL;
+	}
 
 	return 0;
+}
 
-alloc_err:
-	qed_qm_info_free(p_hwfn);
-	return -ENOMEM;
+static void qed_dp_init_qm_params(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+	struct init_qm_vport_params *vport;
+	struct init_qm_port_params *port;
+	struct init_qm_pq_params *pq;
+	int i, tc;
+
+	/* top level params */
+	DP_VERBOSE(p_hwfn,
+		   NETIF_MSG_HW,
+		   "qm init top level params: start_pq %d, start_vport %d, pure_lb_pq %d, offload_pq %d, pure_ack_pq %d\n",
+		   qm_info->start_pq,
+		   qm_info->start_vport,
+		   qm_info->pure_lb_pq,
+		   qm_info->offload_pq, qm_info->pure_ack_pq);
+	DP_VERBOSE(p_hwfn,
+		   NETIF_MSG_HW,
+		   "ooo_pq %d, first_vf_pq %d, num_pqs %d, num_vf_pqs %d, num_vports %d, max_phys_tcs_per_port %d\n",
+		   qm_info->ooo_pq,
+		   qm_info->first_vf_pq,
+		   qm_info->num_pqs,
+		   qm_info->num_vf_pqs,
+		   qm_info->num_vports, qm_info->max_phys_tcs_per_port);
+	DP_VERBOSE(p_hwfn,
+		   NETIF_MSG_HW,
+		   "pf_rl_en %d, pf_wfq_en %d, vport_rl_en %d, vport_wfq_en %d, pf_wfq %d, pf_rl %d, num_pf_rls %d, pq_flags %x\n",
+		   qm_info->pf_rl_en,
+		   qm_info->pf_wfq_en,
+		   qm_info->vport_rl_en,
+		   qm_info->vport_wfq_en,
+		   qm_info->pf_wfq,
+		   qm_info->pf_rl,
+		   qm_info->num_pf_rls, qed_get_pq_flags(p_hwfn));
+
+	/* port table */
+	for (i = 0; i < p_hwfn->cdev->num_ports_in_engines; i++) {
+		port = &(qm_info->qm_port_params[i]);
+		DP_VERBOSE(p_hwfn,
+			   NETIF_MSG_HW,
+			   "port idx %d, active %d, active_phys_tcs %d, num_pbf_cmd_lines %d, num_btb_blocks %d, reserved %d\n",
+			   i,
+			   port->active,
+			   port->active_phys_tcs,
+			   port->num_pbf_cmd_lines,
+			   port->num_btb_blocks, port->reserved);
+	}
+
+	/* vport table */
+	for (i = 0; i < qm_info->num_vports; i++) {
+		vport = &(qm_info->qm_vport_params[i]);
+		DP_VERBOSE(p_hwfn,
+			   NETIF_MSG_HW,
+			   "vport idx %d, vport_rl %d, wfq %d, first_tx_pq_id [ ",
+			   qm_info->start_vport + i,
+			   vport->vport_rl, vport->vport_wfq);
+		for (tc = 0; tc < NUM_OF_TCS; tc++)
+			DP_VERBOSE(p_hwfn,
+				   NETIF_MSG_HW,
+				   "%d ", vport->first_tx_pq_id[tc]);
+		DP_VERBOSE(p_hwfn, NETIF_MSG_HW, "]\n");
+	}
+
+	/* pq table */
+	for (i = 0; i < qm_info->num_pqs; i++) {
+		pq = &(qm_info->qm_pq_params[i]);
+		DP_VERBOSE(p_hwfn,
+			   NETIF_MSG_HW,
+			   "pq idx %d, vport_id %d, tc %d, wrr_grp %d, rl_valid %d\n",
+			   qm_info->start_pq + i,
+			   pq->vport_id,
+			   pq->tc_id, pq->wrr_group, pq->rl_valid);
+	}
+}
+
+static void qed_init_qm_info(struct qed_hwfn *p_hwfn)
+{
+	/* reset params required for init run */
+	qed_init_qm_reset_params(p_hwfn);
+
+	/* init QM top level params */
+	qed_init_qm_params(p_hwfn);
+
+	/* init QM port params */
+	qed_init_qm_port_params(p_hwfn);
+
+	/* init QM vport params */
+	qed_init_qm_vport_params(p_hwfn);
+
+	/* init QM physical queue params */
+	qed_init_qm_pq_params(p_hwfn);
+
+	/* display all that init */
+	qed_dp_init_qm_params(p_hwfn);
 }
 
 /* This function reconfigures the QM pf on the fly.
@@ -391,17 +765,8 @@ int qed_qm_reconf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	bool b_rc;
 	int rc;
 
-	/* qm_info is allocated in qed_init_qm_info() which is already called
-	 * from qed_resc_alloc() or previous call of qed_qm_reconf().
-	 * The allocated size may change each init, so we free it before next
-	 * allocation.
-	 */
-	qed_qm_info_free(p_hwfn);
-
 	/* initialize qed's qm data structure */
-	rc = qed_init_qm_info(p_hwfn, false);
-	if (rc)
-		return rc;
+	qed_init_qm_info(p_hwfn);
 
 	/* stop PF's qm queues */
 	spin_lock_bh(&qm_lock);
@@ -434,6 +799,47 @@ int qed_qm_reconf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	return 0;
 }
 
+static int qed_alloc_qm_data(struct qed_hwfn *p_hwfn)
+{
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+	int rc;
+
+	rc = qed_init_qm_sanity(p_hwfn);
+	if (rc)
+		goto alloc_err;
+
+	qm_info->qm_pq_params = kzalloc(sizeof(*qm_info->qm_pq_params) *
+					qed_init_qm_get_num_pqs(p_hwfn),
+					GFP_KERNEL);
+	if (!qm_info->qm_pq_params)
+		goto alloc_err;
+
+	qm_info->qm_vport_params = kzalloc(sizeof(*qm_info->qm_vport_params) *
+					   qed_init_qm_get_num_vports(p_hwfn),
+					   GFP_KERNEL);
+	if (!qm_info->qm_vport_params)
+		goto alloc_err;
+
+	qm_info->qm_port_params = kzalloc(sizeof(qm_info->qm_port_params) *
+					  p_hwfn->cdev->num_ports_in_engines,
+					  GFP_KERNEL);
+	if (!qm_info->qm_port_params)
+		goto alloc_err;
+
+	qm_info->wfq_data = kzalloc(sizeof(*qm_info->wfq_data) *
+				    qed_init_qm_get_num_vports(p_hwfn),
+				    GFP_KERNEL);
+	if (!qm_info->wfq_data)
+		goto alloc_err;
+
+	return 0;
+
+alloc_err:
+	DP_NOTICE(p_hwfn, "Failed to allocate memory for QM params\n");
+	qed_qm_info_free(p_hwfn);
+	return -ENOMEM;
+}
+
 int qed_resc_alloc(struct qed_dev *cdev)
 {
 	struct qed_iscsi_info *p_iscsi_info;
@@ -442,8 +848,10 @@ int qed_resc_alloc(struct qed_dev *cdev)
 #ifdef CONFIG_QED_LL2
 	struct qed_ll2_info *p_ll2_info;
 #endif
+	u32 rdma_tasks, excess_tasks;
 	struct qed_consq *p_consq;
 	struct qed_eq *p_eq;
+	u32 line_count;
 	int i, rc = 0;
 
 	if (IS_VF(cdev))
@@ -465,19 +873,44 @@ int qed_resc_alloc(struct qed_dev *cdev)
 		/* Set the HW cid/tid numbers (in the contest manager)
 		 * Must be done prior to any further computations.
 		 */
-		rc = qed_cxt_set_pf_params(p_hwfn);
+		rc = qed_cxt_set_pf_params(p_hwfn, RDMA_MAX_TIDS);
 		if (rc)
 			goto alloc_err;
 
-		/* Prepare and process QM requirements */
-		rc = qed_init_qm_info(p_hwfn, true);
+		rc = qed_alloc_qm_data(p_hwfn);
 		if (rc)
 			goto alloc_err;
 
+		/* init qm info */
+		qed_init_qm_info(p_hwfn);
+
 		/* Compute the ILT client partition */
-		rc = qed_cxt_cfg_ilt_compute(p_hwfn);
-		if (rc)
-			goto alloc_err;
+		rc = qed_cxt_cfg_ilt_compute(p_hwfn, &line_count);
+		if (rc) {
+			DP_NOTICE(p_hwfn,
+				  "too many ILT lines; re-computing with less lines\n");
+			/* In case there are not enough ILT lines we reduce the
+			 * number of RDMA tasks and re-compute.
+			 */
+			excess_tasks =
+			    qed_cxt_cfg_ilt_compute_excess(p_hwfn, line_count);
+			if (!excess_tasks)
+				goto alloc_err;
+
+			rdma_tasks = RDMA_MAX_TIDS - excess_tasks;
+			rc = qed_cxt_set_pf_params(p_hwfn, rdma_tasks);
+			if (rc)
+				goto alloc_err;
+
+			rc = qed_cxt_cfg_ilt_compute(p_hwfn, &line_count);
+			if (rc) {
+				DP_ERR(p_hwfn,
+				       "failed ILT compute. Requested too many lines: %u\n",
+				       line_count);
+
+				goto alloc_err;
+			}
+		}
 
 		/* CID map / ILT shadow table / T2
 		 * The talbes sizes are determined by the computations above
@@ -674,11 +1107,19 @@ int qed_final_cleanup(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn)
+static int qed_calc_hw_mode(struct qed_hwfn *p_hwfn)
 {
 	int hw_mode = 0;
 
-	hw_mode = (1 << MODE_BB_B0);
+	if (QED_IS_BB_B0(p_hwfn->cdev)) {
+		hw_mode |= 1 << MODE_BB;
+	} else if (QED_IS_AH(p_hwfn->cdev)) {
+		hw_mode |= 1 << MODE_K2;
+	} else {
+		DP_NOTICE(p_hwfn, "Unknown chip type %#x\n",
+			  p_hwfn->cdev->type);
+		return -EINVAL;
+	}
 
 	switch (p_hwfn->cdev->num_ports_in_engines) {
 	case 1:
@@ -693,7 +1134,7 @@ static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn)
 	default:
 		DP_NOTICE(p_hwfn, "num_ports_in_engine = %d not supported\n",
 			  p_hwfn->cdev->num_ports_in_engines);
-		return;
+		return -EINVAL;
 	}
 
 	switch (p_hwfn->cdev->mf_mode) {
@@ -719,6 +1160,8 @@ static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn)
 	DP_VERBOSE(p_hwfn, (NETIF_MSG_PROBE | NETIF_MSG_IFUP),
 		   "Configuring function for hw_mode: 0x%08x\n",
 		   p_hwfn->hw_info.hw_mode);
+
+	return 0;
 }
 
 /* Init run time data for all PFs on an engine. */
@@ -754,10 +1197,10 @@ static int qed_hw_init_common(struct qed_hwfn *p_hwfn,
 	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
 	struct qed_qm_common_rt_init_params params;
 	struct qed_dev *cdev = p_hwfn->cdev;
+	u8 vf_id, max_num_vfs;
 	u16 num_pfs, pf_id;
 	u32 concrete_fid;
 	int rc = 0;
-	u8 vf_id;
 
 	qed_init_cau_rt_data(cdev);
 
@@ -814,7 +1257,8 @@ static int qed_hw_init_common(struct qed_hwfn *p_hwfn,
 		qed_fid_pretend(p_hwfn, p_ptt, p_hwfn->rel_pf_id);
 	}
 
-	for (vf_id = 0; vf_id < MAX_NUM_VFS_BB; vf_id++) {
+	max_num_vfs = QED_IS_AH(cdev) ? MAX_NUM_VFS_K2 : MAX_NUM_VFS_BB;
+	for (vf_id = 0; vf_id < max_num_vfs; vf_id++) {
 		concrete_fid = qed_vfid_to_concrete(p_hwfn, vf_id);
 		qed_fid_pretend(p_hwfn, p_ptt, (u16) concrete_fid);
 		qed_wr(p_hwfn, p_ptt, CCFC_REG_STRONG_ENABLE_VF, 0x1);
@@ -1095,25 +1539,34 @@ static void qed_reset_mb_shadow(struct qed_hwfn *p_hwfn,
 	       p_hwfn->mcp_info->mfw_mb_cur, p_hwfn->mcp_info->mfw_mb_length);
 }
 
-int qed_hw_init(struct qed_dev *cdev,
-		struct qed_tunn_start_params *p_tunn,
-		bool b_hw_start,
-		enum qed_int_mode int_mode,
-		bool allow_npar_tx_switch,
-		const u8 *bin_fw_data)
+static void
+qed_fill_load_req_params(struct qed_load_req_params *p_load_req,
+			 struct qed_drv_load_params *p_drv_load)
 {
+	memset(p_load_req, 0, sizeof(*p_load_req));
+
+	p_load_req->drv_role = p_drv_load->is_crash_kernel ?
+			       QED_DRV_ROLE_KDUMP : QED_DRV_ROLE_OS;
+	p_load_req->timeout_val = p_drv_load->mfw_timeout_val;
+	p_load_req->avoid_eng_reset = p_drv_load->avoid_eng_reset;
+	p_load_req->override_force_load = p_drv_load->override_force_load;
+}
+
+int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
+{
+	struct qed_load_req_params load_req_params;
 	u32 load_code, param, drv_mb_param;
 	bool b_default_mtu = true;
 	struct qed_hwfn *p_hwfn;
 	int rc = 0, mfw_rc, i;
 
-	if ((int_mode == QED_INT_MODE_MSI) && (cdev->num_hwfns > 1)) {
+	if ((p_params->int_mode == QED_INT_MODE_MSI) && (cdev->num_hwfns > 1)) {
 		DP_NOTICE(cdev, "MSI mode is not supported for CMT devices\n");
 		return -EINVAL;
 	}
 
 	if (IS_PF(cdev)) {
-		rc = qed_init_fw_data(cdev, bin_fw_data);
+		rc = qed_init_fw_data(cdev, p_params->bin_fw_data);
 		if (rc)
 			return rc;
 	}
@@ -1135,19 +1588,25 @@ int qed_hw_init(struct qed_dev *cdev,
 		/* Enable DMAE in PXP */
 		rc = qed_change_pci_hwfn(p_hwfn, p_hwfn->p_main_ptt, true);
 
-		qed_calc_hw_mode(p_hwfn);
+		rc = qed_calc_hw_mode(p_hwfn);
+		if (rc)
+			return rc;
 
-		rc = qed_mcp_load_req(p_hwfn, p_hwfn->p_main_ptt, &load_code);
+		qed_fill_load_req_params(&load_req_params,
+					 p_params->p_drv_load_params);
+		rc = qed_mcp_load_req(p_hwfn, p_hwfn->p_main_ptt,
+				      &load_req_params);
 		if (rc) {
-			DP_NOTICE(p_hwfn, "Failed sending LOAD_REQ command\n");
+			DP_NOTICE(p_hwfn, "Failed sending a LOAD_REQ command\n");
 			return rc;
 		}
 
-		qed_reset_mb_shadow(p_hwfn, p_hwfn->p_main_ptt);
-
+		load_code = load_req_params.load_code;
 		DP_VERBOSE(p_hwfn, QED_MSG_SP,
-			   "Load request was sent. Resp:0x%x, Load code: 0x%x\n",
-			   rc, load_code);
+			   "Load request was sent. Load code: 0x%x\n",
+			   load_code);
+
+		qed_reset_mb_shadow(p_hwfn, p_hwfn->p_main_ptt);
 
 		p_hwfn->first_on_engine = (load_code ==
 					   FW_MSG_CODE_DRV_LOAD_ENGINE);
@@ -1168,11 +1627,15 @@ int qed_hw_init(struct qed_dev *cdev,
 		/* Fall into */
 		case FW_MSG_CODE_DRV_LOAD_FUNCTION:
 			rc = qed_hw_init_pf(p_hwfn, p_hwfn->p_main_ptt,
-					    p_tunn, p_hwfn->hw_info.hw_mode,
-					    b_hw_start, int_mode,
-					    allow_npar_tx_switch);
+					    p_params->p_tunn,
+					    p_hwfn->hw_info.hw_mode,
+					    p_params->b_hw_start,
+					    p_params->int_mode,
+					    p_params->allow_npar_tx_switch);
 			break;
 		default:
+			DP_NOTICE(p_hwfn,
+				  "Unexpected load code [0x%08x]", load_code);
 			rc = -EINVAL;
 			break;
 		}
@@ -1212,10 +1675,7 @@ int qed_hw_init(struct qed_dev *cdev,
 
 	if (IS_PF(cdev)) {
 		p_hwfn = QED_LEADING_HWFN(cdev);
-		drv_mb_param = (FW_MAJOR_VERSION << 24) |
-			       (FW_MINOR_VERSION << 16) |
-			       (FW_REVISION_VERSION << 8) |
-			       (FW_ENGINEERING_VERSION);
+		drv_mb_param = STORM_FW_VERSION;
 		rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
 				 DRV_MSG_CODE_OV_UPDATE_STORM_FW_VER,
 				 drv_mb_param, &load_code, &param);
@@ -1290,27 +1750,53 @@ void qed_hw_timers_stop_all(struct qed_dev *cdev)
 
 int qed_hw_stop(struct qed_dev *cdev)
 {
-	int rc = 0, t_rc;
+	struct qed_hwfn *p_hwfn;
+	struct qed_ptt *p_ptt;
+	int rc, rc2 = 0;
 	int j;
 
 	for_each_hwfn(cdev, j) {
-		struct qed_hwfn *p_hwfn = &cdev->hwfns[j];
-		struct qed_ptt *p_ptt = p_hwfn->p_main_ptt;
+		p_hwfn = &cdev->hwfns[j];
+		p_ptt = p_hwfn->p_main_ptt;
 
 		DP_VERBOSE(p_hwfn, NETIF_MSG_IFDOWN, "Stopping hw/fw\n");
 
 		if (IS_VF(cdev)) {
 			qed_vf_pf_int_cleanup(p_hwfn);
+			rc = qed_vf_pf_reset(p_hwfn);
+			if (rc) {
+				DP_NOTICE(p_hwfn,
+					  "qed_vf_pf_reset failed. rc = %d.\n",
+					  rc);
+				rc2 = -EINVAL;
+			}
 			continue;
 		}
 
 		/* mark the hw as uninitialized... */
 		p_hwfn->hw_init_done = false;
 
+		/* Send unload command to MCP */
+		rc = qed_mcp_unload_req(p_hwfn, p_ptt);
+		if (rc) {
+			DP_NOTICE(p_hwfn,
+				  "Failed sending a UNLOAD_REQ command. rc = %d.\n",
+				  rc);
+			rc2 = -EINVAL;
+		}
+
+		qed_slowpath_irq_sync(p_hwfn);
+
+		/* After this point no MFW attentions are expected, e.g. prevent
+		 * race between pf stop and dcbx pf update.
+		 */
 		rc = qed_sp_pf_stop(p_hwfn);
-		if (rc)
+		if (rc) {
 			DP_NOTICE(p_hwfn,
-				  "Failed to close PF against FW. Continue to stop HW to prevent illegal host access by the device\n");
+				  "Failed to close PF against FW [rc = %d]. Continue to stop HW to prevent illegal host access by the device.\n",
+				  rc);
+			rc2 = -EINVAL;
+		}
 
 		qed_wr(p_hwfn, p_ptt,
 		       NIG_REG_RX_LLH_BRB_GATE_DNTFWD_PERPF, 0x1);
@@ -1333,20 +1819,37 @@ int qed_hw_stop(struct qed_dev *cdev)
 
 		/* Need to wait 1ms to guarantee SBs are cleared */
 		usleep_range(1000, 2000);
+
+		/* Disable PF in HW blocks */
+		qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_DB_ENABLE, 0);
+		qed_wr(p_hwfn, p_ptt, QM_REG_PF_EN, 0);
+
+		qed_mcp_unload_done(p_hwfn, p_ptt);
+		if (rc) {
+			DP_NOTICE(p_hwfn,
+				  "Failed sending a UNLOAD_DONE command. rc = %d.\n",
+				  rc);
+			rc2 = -EINVAL;
+		}
 	}
 
 	if (IS_PF(cdev)) {
+		p_hwfn = QED_LEADING_HWFN(cdev);
+		p_ptt = QED_LEADING_HWFN(cdev)->p_main_ptt;
+
 		/* Disable DMAE in PXP - in CMT, this should only be done for
 		 * first hw-function, and only after all transactions have
 		 * stopped for all active hw-functions.
 		 */
-		t_rc = qed_change_pci_hwfn(&cdev->hwfns[0],
-					   cdev->hwfns[0].p_main_ptt, false);
-		if (t_rc != 0)
-			rc = t_rc;
+		rc = qed_change_pci_hwfn(p_hwfn, p_ptt, false);
+		if (rc) {
+			DP_NOTICE(p_hwfn,
+				  "qed_change_pci_hwfn failed. rc = %d.\n", rc);
+			rc2 = -EINVAL;
+		}
 	}
 
-	return rc;
+	return rc2;
 }
 
 void qed_hw_stop_fastpath(struct qed_dev *cdev)
@@ -1391,89 +1894,6 @@ void qed_hw_start_fastpath(struct qed_hwfn *p_hwfn)
 	       NIG_REG_RX_LLH_BRB_GATE_DNTFWD_PERPF, 0x0);
 }
 
-static int qed_reg_assert(struct qed_hwfn *p_hwfn,
-			  struct qed_ptt *p_ptt, u32 reg, bool expected)
-{
-	u32 assert_val = qed_rd(p_hwfn, p_ptt, reg);
-
-	if (assert_val != expected) {
-		DP_NOTICE(p_hwfn, "Value at address 0x%08x != 0x%08x\n",
-			  reg, expected);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-int qed_hw_reset(struct qed_dev *cdev)
-{
-	int rc = 0;
-	u32 unload_resp, unload_param;
-	u32 wol_param;
-	int i;
-
-	switch (cdev->wol_config) {
-	case QED_OV_WOL_DISABLED:
-		wol_param = DRV_MB_PARAM_UNLOAD_WOL_DISABLED;
-		break;
-	case QED_OV_WOL_ENABLED:
-		wol_param = DRV_MB_PARAM_UNLOAD_WOL_ENABLED;
-		break;
-	default:
-		DP_NOTICE(cdev,
-			  "Unknown WoL configuration %02x\n", cdev->wol_config);
-		/* Fallthrough */
-	case QED_OV_WOL_DEFAULT:
-		wol_param = DRV_MB_PARAM_UNLOAD_WOL_MCP;
-	}
-
-	for_each_hwfn(cdev, i) {
-		struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
-
-		if (IS_VF(cdev)) {
-			rc = qed_vf_pf_reset(p_hwfn);
-			if (rc)
-				return rc;
-			continue;
-		}
-
-		DP_VERBOSE(p_hwfn, NETIF_MSG_IFDOWN, "Resetting hw/fw\n");
-
-		/* Check for incorrect states */
-		qed_reg_assert(p_hwfn, p_hwfn->p_main_ptt,
-			       QM_REG_USG_CNT_PF_TX, 0);
-		qed_reg_assert(p_hwfn, p_hwfn->p_main_ptt,
-			       QM_REG_USG_CNT_PF_OTHER, 0);
-
-		/* Disable PF in HW blocks */
-		qed_wr(p_hwfn, p_hwfn->p_main_ptt, DORQ_REG_PF_DB_ENABLE, 0);
-		qed_wr(p_hwfn, p_hwfn->p_main_ptt, QM_REG_PF_EN, 0);
-		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
-		       TCFC_REG_STRONG_ENABLE_PF, 0);
-		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
-		       CCFC_REG_STRONG_ENABLE_PF, 0);
-
-		/* Send unload command to MCP */
-		rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
-				 DRV_MSG_CODE_UNLOAD_REQ, wol_param,
-				 &unload_resp, &unload_param);
-		if (rc) {
-			DP_NOTICE(p_hwfn, "qed_hw_reset: UNLOAD_REQ failed\n");
-			unload_resp = FW_MSG_CODE_DRV_UNLOAD_ENGINE;
-		}
-
-		rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
-				 DRV_MSG_CODE_UNLOAD_DONE,
-				 0, &unload_resp, &unload_param);
-		if (rc) {
-			DP_NOTICE(p_hwfn, "qed_hw_reset: UNLOAD_DONE failed\n");
-			return rc;
-		}
-	}
-
-	return rc;
-}
-
 /* Free hwfn memory and resources acquired in hw_hwfn_prepare */
 static void qed_hw_hwfn_free(struct qed_hwfn *p_hwfn)
 {
@@ -1485,10 +1905,25 @@ static void qed_hw_hwfn_free(struct qed_hwfn *p_hwfn)
 static void qed_hw_hwfn_prepare(struct qed_hwfn *p_hwfn)
 {
 	/* clear indirect access */
-	qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_88_F0, 0);
-	qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_8C_F0, 0);
-	qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_90_F0, 0);
-	qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_94_F0, 0);
+	if (QED_IS_AH(p_hwfn->cdev)) {
+		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+		       PGLUE_B_REG_PGL_ADDR_E8_F0_K2, 0);
+		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+		       PGLUE_B_REG_PGL_ADDR_EC_F0_K2, 0);
+		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+		       PGLUE_B_REG_PGL_ADDR_F0_F0_K2, 0);
+		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+		       PGLUE_B_REG_PGL_ADDR_F4_F0_K2, 0);
+	} else {
+		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+		       PGLUE_B_REG_PGL_ADDR_88_F0_BB, 0);
+		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+		       PGLUE_B_REG_PGL_ADDR_8C_F0_BB, 0);
+		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+		       PGLUE_B_REG_PGL_ADDR_90_F0_BB, 0);
+		qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+		       PGLUE_B_REG_PGL_ADDR_94_F0_BB, 0);
+	}
 
 	/* Clean Previous errors if such exist */
 	qed_wr(p_hwfn, p_hwfn->p_main_ptt,
@@ -1522,7 +1957,7 @@ static void qed_hw_set_feat(struct qed_hwfn *p_hwfn)
 {
 	u32 *feat_num = p_hwfn->hw_info.feat_num;
 	struct qed_sb_cnt_info sb_cnt_info;
-	int num_features = 1;
+	u32 non_l2_sbs = 0;
 
 	if (IS_ENABLED(CONFIG_QED_RDMA) &&
 	    p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE) {
@@ -1530,204 +1965,255 @@ static void qed_hw_set_feat(struct qed_hwfn *p_hwfn)
 		 * the status blocks equally between L2 / RoCE but with
 		 * consideration as to how many l2 queues / cnqs we have.
 		 */
-		num_features++;
-
 		feat_num[QED_RDMA_CNQ] =
-			min_t(u32, RESC_NUM(p_hwfn, QED_SB) / num_features,
+			min_t(u32, RESC_NUM(p_hwfn, QED_SB) / 2,
 			      RESC_NUM(p_hwfn, QED_RDMA_CNQ_RAM));
-	}
 
-	feat_num[QED_PF_L2_QUE] = min_t(u32, RESC_NUM(p_hwfn, QED_SB) /
-						num_features,
-					RESC_NUM(p_hwfn, QED_L2_QUEUE));
+		non_l2_sbs = feat_num[QED_RDMA_CNQ];
+	}
 
-	memset(&sb_cnt_info, 0, sizeof(sb_cnt_info));
-	qed_int_get_num_sbs(p_hwfn, &sb_cnt_info);
-	feat_num[QED_VF_L2_QUE] =
-	    min_t(u32,
-		  RESC_NUM(p_hwfn, QED_L2_QUEUE) -
-		  FEAT_NUM(p_hwfn, QED_PF_L2_QUE), sb_cnt_info.sb_iov_cnt);
+	if (p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE ||
+	    p_hwfn->hw_info.personality == QED_PCI_ETH) {
+		/* Start by allocating VF queues, then PF's */
+		memset(&sb_cnt_info, 0, sizeof(sb_cnt_info));
+		qed_int_get_num_sbs(p_hwfn, &sb_cnt_info);
+		feat_num[QED_VF_L2_QUE] = min_t(u32,
+						RESC_NUM(p_hwfn, QED_L2_QUEUE),
+						sb_cnt_info.sb_iov_cnt);
+		feat_num[QED_PF_L2_QUE] = min_t(u32,
+						RESC_NUM(p_hwfn, QED_SB) -
+						non_l2_sbs,
+						RESC_NUM(p_hwfn,
+							 QED_L2_QUEUE) -
+						FEAT_NUM(p_hwfn,
+							 QED_VF_L2_QUE));
+	}
 
 	DP_VERBOSE(p_hwfn,
 		   NETIF_MSG_PROBE,
-		   "#PF_L2_QUEUES=%d VF_L2_QUEUES=%d #ROCE_CNQ=%d #SBS=%d num_features=%d\n",
+		   "#PF_L2_QUEUES=%d VF_L2_QUEUES=%d #ROCE_CNQ=%d #SBS=%d\n",
 		   (int)FEAT_NUM(p_hwfn, QED_PF_L2_QUE),
 		   (int)FEAT_NUM(p_hwfn, QED_VF_L2_QUE),
 		   (int)FEAT_NUM(p_hwfn, QED_RDMA_CNQ),
-		   RESC_NUM(p_hwfn, QED_SB), num_features);
+		   RESC_NUM(p_hwfn, QED_SB));
 }
 
-static enum resource_id_enum qed_hw_get_mfw_res_id(enum qed_resources res_id)
+const char *qed_hw_get_resc_name(enum qed_resources res_id)
 {
-	enum resource_id_enum mfw_res_id = RESOURCE_NUM_INVALID;
-
 	switch (res_id) {
-	case QED_SB:
-		mfw_res_id = RESOURCE_NUM_SB_E;
-		break;
 	case QED_L2_QUEUE:
-		mfw_res_id = RESOURCE_NUM_L2_QUEUE_E;
-		break;
+		return "L2_QUEUE";
 	case QED_VPORT:
-		mfw_res_id = RESOURCE_NUM_VPORT_E;
-		break;
+		return "VPORT";
 	case QED_RSS_ENG:
-		mfw_res_id = RESOURCE_NUM_RSS_ENGINES_E;
-		break;
+		return "RSS_ENG";
 	case QED_PQ:
-		mfw_res_id = RESOURCE_NUM_PQ_E;
-		break;
+		return "PQ";
 	case QED_RL:
-		mfw_res_id = RESOURCE_NUM_RL_E;
-		break;
+		return "RL";
 	case QED_MAC:
+		return "MAC";
 	case QED_VLAN:
-		/* Each VFC resource can accommodate both a MAC and a VLAN */
-		mfw_res_id = RESOURCE_VFC_FILTER_E;
-		break;
+		return "VLAN";
+	case QED_RDMA_CNQ_RAM:
+		return "RDMA_CNQ_RAM";
 	case QED_ILT:
-		mfw_res_id = RESOURCE_ILT_E;
-		break;
+		return "ILT";
 	case QED_LL2_QUEUE:
-		mfw_res_id = RESOURCE_LL2_QUEUE_E;
-		break;
-	case QED_RDMA_CNQ_RAM:
+		return "LL2_QUEUE";
 	case QED_CMDQS_CQS:
-		/* CNQ/CMDQS are the same resource */
-		mfw_res_id = RESOURCE_CQS_E;
-		break;
+		return "CMDQS_CQS";
 	case QED_RDMA_STATS_QUEUE:
-		mfw_res_id = RESOURCE_RDMA_STATS_QUEUE_E;
-		break;
+		return "RDMA_STATS_QUEUE";
+	case QED_BDQ:
+		return "BDQ";
+	case QED_SB:
+		return "SB";
 	default:
-		break;
+		return "UNKNOWN_RESOURCE";
+	}
+}
+
+static int
+__qed_hw_set_soft_resc_size(struct qed_hwfn *p_hwfn,
+			    struct qed_ptt *p_ptt,
+			    enum qed_resources res_id,
+			    u32 resc_max_val, u32 *p_mcp_resp)
+{
+	int rc;
+
+	rc = qed_mcp_set_resc_max_val(p_hwfn, p_ptt, res_id,
+				      resc_max_val, p_mcp_resp);
+	if (rc) {
+		DP_NOTICE(p_hwfn,
+			  "MFW response failure for a max value setting of resource %d [%s]\n",
+			  res_id, qed_hw_get_resc_name(res_id));
+		return rc;
 	}
 
-	return mfw_res_id;
+	if (*p_mcp_resp != FW_MSG_CODE_RESOURCE_ALLOC_OK)
+		DP_INFO(p_hwfn,
+			"Failed to set the max value of resource %d [%s]. mcp_resp = 0x%08x.\n",
+			res_id, qed_hw_get_resc_name(res_id), *p_mcp_resp);
+
+	return 0;
 }
 
-static u32 qed_hw_get_dflt_resc_num(struct qed_hwfn *p_hwfn,
-				    enum qed_resources res_id)
+static int
+qed_hw_set_soft_resc_size(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	bool b_ah = QED_IS_AH(p_hwfn->cdev);
+	u32 resc_max_val, mcp_resp;
+	u8 res_id;
+	int rc;
+
+	for (res_id = 0; res_id < QED_MAX_RESC; res_id++) {
+		switch (res_id) {
+		case QED_LL2_QUEUE:
+			resc_max_val = MAX_NUM_LL2_RX_QUEUES;
+			break;
+		case QED_RDMA_CNQ_RAM:
+			/* No need for a case for QED_CMDQS_CQS since
+			 * CNQ/CMDQS are the same resource.
+			 */
+			resc_max_val = NUM_OF_CMDQS_CQS;
+			break;
+		case QED_RDMA_STATS_QUEUE:
+			resc_max_val = b_ah ? RDMA_NUM_STATISTIC_COUNTERS_K2
+			    : RDMA_NUM_STATISTIC_COUNTERS_BB;
+			break;
+		case QED_BDQ:
+			resc_max_val = BDQ_NUM_RESOURCES;
+			break;
+		default:
+			continue;
+		}
+
+		rc = __qed_hw_set_soft_resc_size(p_hwfn, p_ptt, res_id,
+						 resc_max_val, &mcp_resp);
+		if (rc)
+			return rc;
+
+		/* There's no point to continue to the next resource if the
+		 * command is not supported by the MFW.
+		 * We do continue if the command is supported but the resource
+		 * is unknown to the MFW. Such a resource will be later
+		 * configured with the default allocation values.
+		 */
+		if (mcp_resp == FW_MSG_CODE_UNSUPPORTED)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static
+int qed_hw_get_dflt_resc(struct qed_hwfn *p_hwfn,
+			 enum qed_resources res_id,
+			 u32 *p_resc_num, u32 *p_resc_start)
 {
 	u8 num_funcs = p_hwfn->num_funcs_on_engine;
+	bool b_ah = QED_IS_AH(p_hwfn->cdev);
 	struct qed_sb_cnt_info sb_cnt_info;
-	u32 dflt_resc_num = 0;
 
 	switch (res_id) {
-	case QED_SB:
-		memset(&sb_cnt_info, 0, sizeof(sb_cnt_info));
-		qed_int_get_num_sbs(p_hwfn, &sb_cnt_info);
-		dflt_resc_num = sb_cnt_info.sb_cnt;
-		break;
 	case QED_L2_QUEUE:
-		dflt_resc_num = MAX_NUM_L2_QUEUES_BB / num_funcs;
+		*p_resc_num = (b_ah ? MAX_NUM_L2_QUEUES_K2 :
+			       MAX_NUM_L2_QUEUES_BB) / num_funcs;
 		break;
 	case QED_VPORT:
-		dflt_resc_num = MAX_NUM_VPORTS_BB / num_funcs;
+		*p_resc_num = (b_ah ? MAX_NUM_VPORTS_K2 :
+			       MAX_NUM_VPORTS_BB) / num_funcs;
 		break;
 	case QED_RSS_ENG:
-		dflt_resc_num = ETH_RSS_ENGINE_NUM_BB / num_funcs;
+		*p_resc_num = (b_ah ? ETH_RSS_ENGINE_NUM_K2 :
+			       ETH_RSS_ENGINE_NUM_BB) / num_funcs;
 		break;
 	case QED_PQ:
-		/* The granularity of the PQs is 8 */
-		dflt_resc_num = MAX_QM_TX_QUEUES_BB / num_funcs;
-		dflt_resc_num &= ~0x7;
+		*p_resc_num = (b_ah ? MAX_QM_TX_QUEUES_K2 :
+			       MAX_QM_TX_QUEUES_BB) / num_funcs;
+		*p_resc_num &= ~0x7;	/* The granularity of the PQs is 8 */
 		break;
 	case QED_RL:
-		dflt_resc_num = MAX_QM_GLOBAL_RLS / num_funcs;
+		*p_resc_num = MAX_QM_GLOBAL_RLS / num_funcs;
 		break;
 	case QED_MAC:
 	case QED_VLAN:
 		/* Each VFC resource can accommodate both a MAC and a VLAN */
-		dflt_resc_num = ETH_NUM_MAC_FILTERS / num_funcs;
+		*p_resc_num = ETH_NUM_MAC_FILTERS / num_funcs;
 		break;
 	case QED_ILT:
-		dflt_resc_num = PXP_NUM_ILT_RECORDS_BB / num_funcs;
+		*p_resc_num = (b_ah ? PXP_NUM_ILT_RECORDS_K2 :
+			       PXP_NUM_ILT_RECORDS_BB) / num_funcs;
 		break;
 	case QED_LL2_QUEUE:
-		dflt_resc_num = MAX_NUM_LL2_RX_QUEUES / num_funcs;
+		*p_resc_num = MAX_NUM_LL2_RX_QUEUES / num_funcs;
 		break;
 	case QED_RDMA_CNQ_RAM:
 	case QED_CMDQS_CQS:
 		/* CNQ/CMDQS are the same resource */
-		dflt_resc_num = NUM_OF_CMDQS_CQS / num_funcs;
+		*p_resc_num = NUM_OF_CMDQS_CQS / num_funcs;
 		break;
 	case QED_RDMA_STATS_QUEUE:
-		dflt_resc_num = RDMA_NUM_STATISTIC_COUNTERS_BB / num_funcs;
+		*p_resc_num = (b_ah ? RDMA_NUM_STATISTIC_COUNTERS_K2 :
+			       RDMA_NUM_STATISTIC_COUNTERS_BB) / num_funcs;
 		break;
-	default:
+	case QED_BDQ:
+		if (p_hwfn->hw_info.personality != QED_PCI_ISCSI &&
+		    p_hwfn->hw_info.personality != QED_PCI_FCOE)
+			*p_resc_num = 0;
+		else
+			*p_resc_num = 1;
 		break;
+	case QED_SB:
+		memset(&sb_cnt_info, 0, sizeof(sb_cnt_info));
+		qed_int_get_num_sbs(p_hwfn, &sb_cnt_info);
+		*p_resc_num = sb_cnt_info.sb_cnt;
+		break;
+	default:
+		return -EINVAL;
 	}
 
-	return dflt_resc_num;
-}
-
-static const char *qed_hw_get_resc_name(enum qed_resources res_id)
-{
 	switch (res_id) {
-	case QED_SB:
-		return "SB";
-	case QED_L2_QUEUE:
-		return "L2_QUEUE";
-	case QED_VPORT:
-		return "VPORT";
-	case QED_RSS_ENG:
-		return "RSS_ENG";
-	case QED_PQ:
-		return "PQ";
-	case QED_RL:
-		return "RL";
-	case QED_MAC:
-		return "MAC";
-	case QED_VLAN:
-		return "VLAN";
-	case QED_RDMA_CNQ_RAM:
-		return "RDMA_CNQ_RAM";
-	case QED_ILT:
-		return "ILT";
-	case QED_LL2_QUEUE:
-		return "LL2_QUEUE";
-	case QED_CMDQS_CQS:
-		return "CMDQS_CQS";
-	case QED_RDMA_STATS_QUEUE:
-		return "RDMA_STATS_QUEUE";
+	case QED_BDQ:
+		if (!*p_resc_num)
+			*p_resc_start = 0;
+		else if (p_hwfn->cdev->num_ports_in_engines == 4)
+			*p_resc_start = p_hwfn->port_id;
+		else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI)
+			*p_resc_start = p_hwfn->port_id;
+		else if (p_hwfn->hw_info.personality == QED_PCI_FCOE)
+			*p_resc_start = p_hwfn->port_id + 2;
+		break;
 	default:
-		return "UNKNOWN_RESOURCE";
+		*p_resc_start = *p_resc_num * p_hwfn->enabled_func_idx;
+		break;
 	}
+
+	return 0;
 }
 
-static int qed_hw_set_resc_info(struct qed_hwfn *p_hwfn,
-				enum qed_resources res_id)
+static int __qed_hw_set_resc_info(struct qed_hwfn *p_hwfn,
+				  enum qed_resources res_id)
 {
-	u32 dflt_resc_num = 0, dflt_resc_start = 0, mcp_resp, mcp_param;
-	u32 *p_resc_num, *p_resc_start;
-	struct resource_info resc_info;
+	u32 dflt_resc_num = 0, dflt_resc_start = 0;
+	u32 mcp_resp, *p_resc_num, *p_resc_start;
 	int rc;
 
 	p_resc_num = &RESC_NUM(p_hwfn, res_id);
 	p_resc_start = &RESC_START(p_hwfn, res_id);
 
-	/* Default values assumes that each function received equal share */
-	dflt_resc_num = qed_hw_get_dflt_resc_num(p_hwfn, res_id);
-	if (!dflt_resc_num) {
+	rc = qed_hw_get_dflt_resc(p_hwfn, res_id, &dflt_resc_num,
+				  &dflt_resc_start);
+	if (rc) {
 		DP_ERR(p_hwfn,
 		       "Failed to get default amount for resource %d [%s]\n",
 		       res_id, qed_hw_get_resc_name(res_id));
-		return -EINVAL;
-	}
-	dflt_resc_start = dflt_resc_num * p_hwfn->enabled_func_idx;
-
-	memset(&resc_info, 0, sizeof(resc_info));
-	resc_info.res_id = qed_hw_get_mfw_res_id(res_id);
-	if (resc_info.res_id == RESOURCE_NUM_INVALID) {
-		DP_ERR(p_hwfn,
-		       "Failed to match resource %d [%s] with the MFW resources\n",
-		       res_id, qed_hw_get_resc_name(res_id));
-		return -EINVAL;
+		return rc;
 	}
 
-	rc = qed_mcp_get_resc_info(p_hwfn, p_hwfn->p_main_ptt, &resc_info,
-				   &mcp_resp, &mcp_param);
+	rc = qed_mcp_get_resc_info(p_hwfn, p_hwfn->p_main_ptt, res_id,
+				   &mcp_resp, p_resc_num, p_resc_start);
 	if (rc) {
 		DP_NOTICE(p_hwfn,
 			  "MFW response failure for an allocation request for resource %d [%s]\n",
@@ -1740,13 +2226,12 @@ static int qed_hw_set_resc_info(struct qed_hwfn *p_hwfn,
 	 * - There is an internal error in the MFW while processing the request
 	 * - The resource ID is unknown to the MFW
 	 */
-	if (mcp_resp != FW_MSG_CODE_RESOURCE_ALLOC_OK &&
-	    mcp_resp != FW_MSG_CODE_RESOURCE_ALLOC_DEPRECATED) {
-		DP_NOTICE(p_hwfn,
-			  "Resource %d [%s]: No allocation info was received [mcp_resp 0x%x]. Applying default values [num %d, start %d].\n",
-			  res_id,
-			  qed_hw_get_resc_name(res_id),
-			  mcp_resp, dflt_resc_num, dflt_resc_start);
+	if (mcp_resp != FW_MSG_CODE_RESOURCE_ALLOC_OK) {
+		DP_INFO(p_hwfn,
+			"Failed to receive allocation info for resource %d [%s]. mcp_resp = 0x%x. Applying default values [%d,%d].\n",
+			res_id,
+			qed_hw_get_resc_name(res_id),
+			mcp_resp, dflt_resc_num, dflt_resc_start);
 		*p_resc_num = dflt_resc_num;
 		*p_resc_start = dflt_resc_start;
 		goto out;
@@ -1754,13 +2239,9 @@ static int qed_hw_set_resc_info(struct qed_hwfn *p_hwfn,
 
 	/* Special handling for status blocks; Would be revised in future */
 	if (res_id == QED_SB) {
-		resc_info.size -= 1;
-		resc_info.offset -= p_hwfn->enabled_func_idx;
+		*p_resc_num -= 1;
+		*p_resc_start -= p_hwfn->enabled_func_idx;
 	}
-
-	*p_resc_num = resc_info.size;
-	*p_resc_start = resc_info.offset;
-
 out:
 	/* PQs have to divide by 8 [that's the HW granularity].
 	 * Reduce number so it would fit.
@@ -1778,19 +2259,88 @@ out:
 	return 0;
 }
 
-static int qed_hw_get_resc(struct qed_hwfn *p_hwfn)
+static int qed_hw_set_resc_info(struct qed_hwfn *p_hwfn)
 {
-	u8 res_id;
 	int rc;
+	u8 res_id;
 
 	for (res_id = 0; res_id < QED_MAX_RESC; res_id++) {
-		rc = qed_hw_set_resc_info(p_hwfn, res_id);
+		rc = __qed_hw_set_resc_info(p_hwfn, res_id);
 		if (rc)
 			return rc;
 	}
 
+	return 0;
+}
+
+#define QED_RESC_ALLOC_LOCK_RETRY_CNT           10
+#define QED_RESC_ALLOC_LOCK_RETRY_INTVL_US      10000	/* 10 msec */
+
+static int qed_hw_get_resc(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_resc_unlock_params resc_unlock_params;
+	struct qed_resc_lock_params resc_lock_params;
+	bool b_ah = QED_IS_AH(p_hwfn->cdev);
+	u8 res_id;
+	int rc;
+
+	/* Setting the max values of the soft resources and the following
+	 * resources allocation queries should be atomic. Since several PFs can
+	 * run in parallel - a resource lock is needed.
+	 * If either the resource lock or resource set value commands are not
+	 * supported - skip the the max values setting, release the lock if
+	 * needed, and proceed to the queries. Other failures, including a
+	 * failure to acquire the lock, will cause this function to fail.
+	 */
+	memset(&resc_lock_params, 0, sizeof(resc_lock_params));
+	resc_lock_params.resource = QED_RESC_LOCK_RESC_ALLOC;
+	resc_lock_params.retry_num = QED_RESC_ALLOC_LOCK_RETRY_CNT;
+	resc_lock_params.retry_interval = QED_RESC_ALLOC_LOCK_RETRY_INTVL_US;
+	resc_lock_params.sleep_b4_retry = true;
+	memset(&resc_unlock_params, 0, sizeof(resc_unlock_params));
+	resc_unlock_params.resource = QED_RESC_LOCK_RESC_ALLOC;
+
+	rc = qed_mcp_resc_lock(p_hwfn, p_ptt, &resc_lock_params);
+	if (rc && rc != -EINVAL) {
+		return rc;
+	} else if (rc == -EINVAL) {
+		DP_INFO(p_hwfn,
+			"Skip the max values setting of the soft resources since the resource lock is not supported by the MFW\n");
+	} else if (!rc && !resc_lock_params.b_granted) {
+		DP_NOTICE(p_hwfn,
+			  "Failed to acquire the resource lock for the resource allocation commands\n");
+		return -EBUSY;
+	} else {
+		rc = qed_hw_set_soft_resc_size(p_hwfn, p_ptt);
+		if (rc && rc != -EINVAL) {
+			DP_NOTICE(p_hwfn,
+				  "Failed to set the max values of the soft resources\n");
+			goto unlock_and_exit;
+		} else if (rc == -EINVAL) {
+			DP_INFO(p_hwfn,
+				"Skip the max values setting of the soft resources since it is not supported by the MFW\n");
+			rc = qed_mcp_resc_unlock(p_hwfn, p_ptt,
+						 &resc_unlock_params);
+			if (rc)
+				DP_INFO(p_hwfn,
+					"Failed to release the resource lock for the resource allocation commands\n");
+		}
+	}
+
+	rc = qed_hw_set_resc_info(p_hwfn);
+	if (rc)
+		goto unlock_and_exit;
+
+	if (resc_lock_params.b_granted && !resc_unlock_params.b_released) {
+		rc = qed_mcp_resc_unlock(p_hwfn, p_ptt, &resc_unlock_params);
+		if (rc)
+			DP_INFO(p_hwfn,
+				"Failed to release the resource lock for the resource allocation commands\n");
+	}
+
 	/* Sanity for ILT */
-	if ((RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_BB)) {
+	if ((b_ah && (RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_K2)) ||
+	    (!b_ah && (RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_BB))) {
 		DP_NOTICE(p_hwfn, "Can't assign ILT pages [%08x,...,%08x]\n",
 			  RESC_START(p_hwfn, QED_ILT),
 			  RESC_END(p_hwfn, QED_ILT) - 1);
@@ -1799,8 +2349,6 @@ static int qed_hw_get_resc(struct qed_hwfn *p_hwfn)
 
 	qed_hw_set_feat(p_hwfn);
 
-	DP_VERBOSE(p_hwfn, NETIF_MSG_PROBE,
-		   "The numbers for each resource are:\n");
 	for (res_id = 0; res_id < QED_MAX_RESC; res_id++)
 		DP_VERBOSE(p_hwfn, NETIF_MSG_PROBE, "%s = %d start = %d\n",
 			   qed_hw_get_resc_name(res_id),
@@ -1808,6 +2356,11 @@ static int qed_hw_get_resc(struct qed_hwfn *p_hwfn)
 			   RESC_START(p_hwfn, res_id));
 
 	return 0;
+
+unlock_and_exit:
+	if (resc_lock_params.b_granted && !resc_unlock_params.b_released)
+		qed_mcp_resc_unlock(p_hwfn, p_ptt, &resc_unlock_params);
+	return rc;
 }
 
 static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
@@ -1860,9 +2413,15 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	case NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X25G:
 		p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_2X25G;
 		break;
+	case NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X10G:
+		p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_2X10G;
+		break;
 	case NVM_CFG1_GLOB_NETWORK_PORT_MODE_1X25G:
 		p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_1X25G;
 		break;
+	case NVM_CFG1_GLOB_NETWORK_PORT_MODE_4X25G:
+		p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_4X25G;
+		break;
 	default:
 		DP_NOTICE(p_hwfn, "Unknown port mode in 0x%08x\n", core_cfg);
 		break;
@@ -1976,8 +2535,9 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	u8 num_funcs, enabled_func_idx = p_hwfn->rel_pf_id;
 	u32 reg_function_hide, tmp, eng_mask, low_pfs_mask;
+	struct qed_dev *cdev = p_hwfn->cdev;
 
-	num_funcs = MAX_NUM_PFS_BB;
+	num_funcs = QED_IS_AH(cdev) ? MAX_NUM_PFS_K2 : MAX_NUM_PFS_BB;
 
 	/* Bit 0 of MISCS_REG_FUNCTION_HIDE indicates whether the bypass values
 	 * in the other bits are selected.
@@ -1990,12 +2550,17 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	reg_function_hide = qed_rd(p_hwfn, p_ptt, MISCS_REG_FUNCTION_HIDE);
 
 	if (reg_function_hide & 0x1) {
-		if (QED_PATH_ID(p_hwfn) && p_hwfn->cdev->num_hwfns == 1) {
-			num_funcs = 0;
-			eng_mask = 0xaaaa;
+		if (QED_IS_BB(cdev)) {
+			if (QED_PATH_ID(p_hwfn) && cdev->num_hwfns == 1) {
+				num_funcs = 0;
+				eng_mask = 0xaaaa;
+			} else {
+				num_funcs = 1;
+				eng_mask = 0x5554;
+			}
 		} else {
 			num_funcs = 1;
-			eng_mask = 0x5554;
+			eng_mask = 0xfffe;
 		}
 
 		/* Get the number of the enabled functions on the engine */
@@ -2027,24 +2592,12 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		   p_hwfn->enabled_func_idx, p_hwfn->num_funcs_on_engine);
 }
 
-static int
-qed_get_hw_info(struct qed_hwfn *p_hwfn,
-		struct qed_ptt *p_ptt,
-		enum qed_pci_personality personality)
+static void qed_hw_info_port_num_bb(struct qed_hwfn *p_hwfn,
+				    struct qed_ptt *p_ptt)
 {
 	u32 port_mode;
-	int rc;
-
-	/* Since all information is common, only first hwfns should do this */
-	if (IS_LEAD_HWFN(p_hwfn)) {
-		rc = qed_iov_hw_info(p_hwfn);
-		if (rc)
-			return rc;
-	}
 
-	/* Read the port mode */
-	port_mode = qed_rd(p_hwfn, p_ptt,
-			   CNIG_REG_NW_PORT_MODE_BB_B0);
+	port_mode = qed_rd(p_hwfn, p_ptt, CNIG_REG_NW_PORT_MODE_BB_B0);
 
 	if (port_mode < 3) {
 		p_hwfn->cdev->num_ports_in_engines = 1;
@@ -2057,6 +2610,54 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn,
 		/* Default num_ports_in_engines to something */
 		p_hwfn->cdev->num_ports_in_engines = 1;
 	}
+}
+
+static void qed_hw_info_port_num_ah(struct qed_hwfn *p_hwfn,
+				    struct qed_ptt *p_ptt)
+{
+	u32 port;
+	int i;
+
+	p_hwfn->cdev->num_ports_in_engines = 0;
+
+	for (i = 0; i < MAX_NUM_PORTS_K2; i++) {
+		port = qed_rd(p_hwfn, p_ptt,
+			      CNIG_REG_NIG_PORT0_CONF_K2 + (i * 4));
+		if (port & 1)
+			p_hwfn->cdev->num_ports_in_engines++;
+	}
+
+	if (!p_hwfn->cdev->num_ports_in_engines) {
+		DP_NOTICE(p_hwfn, "All NIG ports are inactive\n");
+
+		/* Default num_ports_in_engine to something */
+		p_hwfn->cdev->num_ports_in_engines = 1;
+	}
+}
+
+static void qed_hw_info_port_num(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	if (QED_IS_BB(p_hwfn->cdev))
+		qed_hw_info_port_num_bb(p_hwfn, p_ptt);
+	else
+		qed_hw_info_port_num_ah(p_hwfn, p_ptt);
+}
+
+static int
+qed_get_hw_info(struct qed_hwfn *p_hwfn,
+		struct qed_ptt *p_ptt,
+		enum qed_pci_personality personality)
+{
+	int rc;
+
+	/* Since all information is common, only first hwfns should do this */
+	if (IS_LEAD_HWFN(p_hwfn)) {
+		rc = qed_iov_hw_info(p_hwfn);
+		if (rc)
+			return rc;
+	}
+
+	qed_hw_info_port_num(p_hwfn, p_ptt);
 
 	qed_hw_get_nvm_info(p_hwfn, p_ptt);
 
@@ -2085,30 +2686,47 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn,
 		p_hwfn->hw_info.personality = protocol;
 	}
 
+	p_hwfn->hw_info.num_hw_tc = NUM_PHYS_TCS_4PORT_K2;
+	p_hwfn->hw_info.num_active_tc = 1;
+
 	qed_get_num_funcs(p_hwfn, p_ptt);
 
 	if (qed_mcp_is_init(p_hwfn))
 		p_hwfn->hw_info.mtu = p_hwfn->mcp_info->func_info.mtu;
 
-	return qed_hw_get_resc(p_hwfn);
+	return qed_hw_get_resc(p_hwfn, p_ptt);
 }
 
 static int qed_get_dev_info(struct qed_dev *cdev)
 {
 	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	u16 device_id_mask;
 	u32 tmp;
 
 	/* Read Vendor Id / Device Id */
 	pci_read_config_word(cdev->pdev, PCI_VENDOR_ID, &cdev->vendor_id);
 	pci_read_config_word(cdev->pdev, PCI_DEVICE_ID, &cdev->device_id);
 
+	/* Determine type */
+	device_id_mask = cdev->device_id & QED_DEV_ID_MASK;
+	switch (device_id_mask) {
+	case QED_DEV_ID_MASK_BB:
+		cdev->type = QED_DEV_TYPE_BB;
+		break;
+	case QED_DEV_ID_MASK_AH:
+		cdev->type = QED_DEV_TYPE_AH;
+		break;
+	default:
+		DP_NOTICE(p_hwfn, "Unknown device id 0x%x\n", cdev->device_id);
+		return -EBUSY;
+	}
+
 	cdev->chip_num = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt,
 				     MISCS_REG_CHIP_NUM);
 	cdev->chip_rev = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt,
 				     MISCS_REG_CHIP_REV);
 	MASK_FIELD(CHIP_REV, cdev->chip_rev);
 
-	cdev->type = QED_DEV_TYPE_BB;
 	/* Learn number of HW-functions */
 	tmp = qed_rd(p_hwfn, p_hwfn->p_main_ptt,
 		     MISCS_REG_CMT_ENABLED_FOR_PAIR);
@@ -2128,7 +2746,10 @@ static int qed_get_dev_info(struct qed_dev *cdev)
 	MASK_FIELD(CHIP_METAL, cdev->chip_metal);
 
 	DP_INFO(cdev->hwfns,
-		"Chip details - Num: %04x Rev: %04x Bond id: %04x Metal: %04x\n",
+		"Chip details - %s %c%d, Num: %04x Rev: %04x Bond id: %04x Metal: %04x\n",
+		QED_IS_BB(cdev) ? "BB" : "AH",
+		'A' + cdev->chip_rev,
+		(int)cdev->chip_metal,
 		cdev->chip_num, cdev->chip_rev,
 		cdev->chip_bond_id, cdev->chip_metal);
 
@@ -2195,6 +2816,15 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
 		goto err2;
 	}
 
+	/* Sending a mailbox to the MFW should be done after qed_get_hw_info()
+	 * is called as it sets the ports number in an engine.
+	 */
+	if (IS_LEAD_HWFN(p_hwfn)) {
+		rc = qed_mcp_initiate_pf_flr(p_hwfn, p_hwfn->p_main_ptt);
+		if (rc)
+			DP_NOTICE(p_hwfn, "Failed to initiate PF FLR\n");
+	}
+
 	/* Allocate the init RT array and initialize the init-ops engine */
 	rc = qed_init_alloc(p_hwfn);
 	if (rc)
@@ -3363,3 +3993,8 @@ void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	memset(p_hwfn->qm_info.wfq_data, 0,
 	       sizeof(*p_hwfn->qm_info.wfq_data) * p_hwfn->qm_info.num_vports);
 }
+
+int qed_device_num_engines(struct qed_dev *cdev)
+{
+	return QED_IS_BB(cdev) ? 2 : 1;
+}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
index 6812003411cd..2c6637fd7ef6 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
@@ -82,26 +82,63 @@ int qed_resc_alloc(struct qed_dev *cdev);
  */
 void qed_resc_setup(struct qed_dev *cdev);
 
+enum qed_override_force_load {
+	QED_OVERRIDE_FORCE_LOAD_NONE,
+	QED_OVERRIDE_FORCE_LOAD_ALWAYS,
+	QED_OVERRIDE_FORCE_LOAD_NEVER,
+};
+
+struct qed_drv_load_params {
+	/* Indicates whether the driver is running over a crash kernel.
+	 * As part of the load request, this will be used for providing the
+	 * driver role to the MFW.
+	 * In case of a crash kernel over PDA - this should be set to false.
+	 */
+	bool is_crash_kernel;
+
+	/* The timeout value that the MFW should use when locking the engine for
+	 * the driver load process.
+	 * A value of '0' means the default value, and '255' means no timeout.
+	 */
+	u8 mfw_timeout_val;
+#define QED_LOAD_REQ_LOCK_TO_DEFAULT    0
+#define QED_LOAD_REQ_LOCK_TO_NONE       255
+
+	/* Avoid engine reset when first PF loads on it */
+	bool avoid_eng_reset;
+
+	/* Allow overriding the default force load behavior */
+	enum qed_override_force_load override_force_load;
+};
+
+struct qed_hw_init_params {
+	/* Tunneling parameters */
+	struct qed_tunn_start_params *p_tunn;
+
+	bool b_hw_start;
+
+	/* Interrupt mode [msix, inta, etc.] to use */
+	enum qed_int_mode int_mode;
+
+	/* NPAR tx switching to be used for vports for tx-switching */
+	bool allow_npar_tx_switch;
+
+	/* Binary fw data pointer in binary fw file */
+	const u8 *bin_fw_data;
+
+	/* Driver load parameters */
+	struct qed_drv_load_params *p_drv_load_params;
+};
+
 /**
  * @brief qed_hw_init -
  *
  * @param cdev
- * @param p_tunn
- * @param b_hw_start
- * @param int_mode - interrupt mode [msix, inta, etc.] to use.
- * @param allow_npar_tx_switch - npar tx switching to be used
- *	  for vports configured for tx-switching.
- * @param bin_fw_data - binary fw data pointer in binary fw file.
- *			Pass NULL if not using binary fw file.
+ * @param p_params
  *
  * @return int
  */
-int qed_hw_init(struct qed_dev *cdev,
-		struct qed_tunn_start_params *p_tunn,
-		bool b_hw_start,
-		enum qed_int_mode int_mode,
-		bool allow_npar_tx_switch,
-		const u8 *bin_fw_data);
+int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params);
 
 /**
  * @brief qed_hw_timers_stop_all - stop the timers HW block
@@ -140,14 +177,6 @@ void qed_hw_stop_fastpath(struct qed_dev *cdev);
  */
 void qed_hw_start_fastpath(struct qed_hwfn *p_hwfn);
 
-/**
- * @brief qed_hw_reset -
- *
- * @param cdev
- *
- * @return int
- */
-int qed_hw_reset(struct qed_dev *cdev);
 
 /**
  * @brief qed_hw_prepare -
@@ -441,4 +470,6 @@ int qed_set_rxq_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
  */
 int qed_set_txq_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 			 u16 coalesce, u8 qid, u16 sb_id);
+
+const char *qed_hw_get_resc_name(enum qed_resources res_id);
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
index cbc81412174f..f4b95345d1a5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
@@ -191,7 +191,7 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn,
 	p_data->q_params.cq_sb_pi = fcoe_pf_params->gl_rq_pi;
 	p_data->q_params.cmdq_sb_pi = fcoe_pf_params->gl_cmd_pi;
 
-	p_data->q_params.bdq_resource_id = FCOE_BDQ_ID(p_hwfn->port_id);
+	p_data->q_params.bdq_resource_id = (u8)RESC_START(p_hwfn, QED_BDQ);
 
 	DMA_REGPAIR_LE(p_data->q_params.bdq_pbl_base_address[BDQ_ID_RQ],
 		       fcoe_pf_params->bdq_pbl_base_addr[BDQ_ID_RQ]);
@@ -241,7 +241,7 @@ qed_sp_fcoe_conn_offload(struct qed_hwfn *p_hwfn,
 	struct fcoe_conn_offload_ramrod_data *p_data;
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
-	u16 pq_id = 0, tmp;
+	u16 physical_q0, tmp;
 	int rc;
 
 	/* Get SPQ entry */
@@ -261,9 +261,9 @@ qed_sp_fcoe_conn_offload(struct qed_hwfn *p_hwfn,
 	p_data = &p_ramrod->offload_ramrod_data;
 
 	/* Transmission PQ is the first of the PF */
-	pq_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_FCOE, NULL);
-	p_conn->physical_q0 = cpu_to_le16(pq_id);
-	p_data->physical_q0 = cpu_to_le16(pq_id);
+	physical_q0 = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+	p_conn->physical_q0 = cpu_to_le16(physical_q0);
+	p_data->physical_q0 = cpu_to_le16(physical_q0);
 
 	p_data->conn_id = cpu_to_le16(p_conn->conn_id);
 	DMA_REGPAIR_LE(p_data->sq_pbl_addr, p_conn->sq_pbl_addr);
@@ -512,19 +512,31 @@ static void __iomem *qed_fcoe_get_db_addr(struct qed_hwfn *p_hwfn, u32 cid)
 static void __iomem *qed_fcoe_get_primary_bdq_prod(struct qed_hwfn *p_hwfn,
 						   u8 bdq_id)
 {
-	u8 bdq_function_id = FCOE_BDQ_ID(p_hwfn->port_id);
-
-	return (u8 __iomem *)p_hwfn->regview + GTT_BAR0_MAP_REG_MSDM_RAM +
-	       MSTORM_SCSI_BDQ_EXT_PROD_OFFSET(bdq_function_id, bdq_id);
+	if (RESC_NUM(p_hwfn, QED_BDQ)) {
+		return (u8 __iomem *)p_hwfn->regview +
+		       GTT_BAR0_MAP_REG_MSDM_RAM +
+		       MSTORM_SCSI_BDQ_EXT_PROD_OFFSET(RESC_START(p_hwfn,
+								  QED_BDQ),
+						       bdq_id);
+	} else {
+		DP_NOTICE(p_hwfn, "BDQ is not allocated!\n");
+		return NULL;
+	}
 }
 
 static void __iomem *qed_fcoe_get_secondary_bdq_prod(struct qed_hwfn *p_hwfn,
 						     u8 bdq_id)
 {
-	u8 bdq_function_id = FCOE_BDQ_ID(p_hwfn->port_id);
-
-	return (u8 __iomem *)p_hwfn->regview + GTT_BAR0_MAP_REG_TSDM_RAM +
-	       TSTORM_SCSI_BDQ_EXT_PROD_OFFSET(bdq_function_id, bdq_id);
+	if (RESC_NUM(p_hwfn, QED_BDQ)) {
+		return (u8 __iomem *)p_hwfn->regview +
+		       GTT_BAR0_MAP_REG_TSDM_RAM +
+		       TSTORM_SCSI_BDQ_EXT_PROD_OFFSET(RESC_START(p_hwfn,
+								  QED_BDQ),
+						       bdq_id);
+	} else {
+		DP_NOTICE(p_hwfn, "BDQ is not allocated!\n");
+		return NULL;
+	}
 }
 
 struct qed_fcoe_info *qed_fcoe_alloc(struct qed_hwfn *p_hwfn)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 37c2bfb663bb..815c4ec5b458 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -574,6 +574,7 @@ enum core_event_opcode {
 	CORE_EVENT_TX_QUEUE_STOP,
 	CORE_EVENT_RX_QUEUE_START,
 	CORE_EVENT_RX_QUEUE_STOP,
+	CORE_EVENT_RX_QUEUE_FLUSH,
 	MAX_CORE_EVENT_OPCODE
 };
 
@@ -625,6 +626,7 @@ enum core_ramrod_cmd_id {
 	CORE_RAMROD_TX_QUEUE_START,
 	CORE_RAMROD_RX_QUEUE_STOP,
 	CORE_RAMROD_TX_QUEUE_STOP,
+	CORE_RAMROD_RX_QUEUE_FLUSH,
 	MAX_CORE_RAMROD_CMD_ID
 };
 
@@ -698,7 +700,8 @@ struct core_rx_slow_path_cqe {
 	u8 type;
 	u8 ramrod_cmd_id;
 	__le16 echo;
-	__le32 reserved1[7];
+	struct core_rx_cqe_opaque_data opaque_data;
+	__le32 reserved1[5];
 };
 
 union core_rx_cqe_union {
@@ -735,45 +738,46 @@ struct core_rx_stop_ramrod_data {
 	__le16 reserved2[2];
 };
 
-struct core_tx_bd_flags {
-	u8 as_bitfield;
-#define CORE_TX_BD_FLAGS_FORCE_VLAN_MODE_MASK	0x1
-#define CORE_TX_BD_FLAGS_FORCE_VLAN_MODE_SHIFT	0
-#define CORE_TX_BD_FLAGS_VLAN_INSERTION_MASK	0x1
-#define CORE_TX_BD_FLAGS_VLAN_INSERTION_SHIFT	1
-#define CORE_TX_BD_FLAGS_START_BD_MASK	0x1
-#define CORE_TX_BD_FLAGS_START_BD_SHIFT	2
-#define CORE_TX_BD_FLAGS_IP_CSUM_MASK	0x1
-#define CORE_TX_BD_FLAGS_IP_CSUM_SHIFT	3
-#define CORE_TX_BD_FLAGS_L4_CSUM_MASK	0x1
-#define CORE_TX_BD_FLAGS_L4_CSUM_SHIFT	4
-#define CORE_TX_BD_FLAGS_IPV6_EXT_MASK	0x1
-#define CORE_TX_BD_FLAGS_IPV6_EXT_SHIFT	5
-#define CORE_TX_BD_FLAGS_L4_PROTOCOL_MASK	0x1
-#define CORE_TX_BD_FLAGS_L4_PROTOCOL_SHIFT	6
-#define CORE_TX_BD_FLAGS_L4_PSEUDO_CSUM_MODE_MASK	0x1
-#define CORE_TX_BD_FLAGS_L4_PSEUDO_CSUM_MODE_SHIFT 7
+struct core_tx_bd_data {
+	__le16 as_bitfield;
+#define CORE_TX_BD_DATA_FORCE_VLAN_MODE_MASK	0x1
+#define CORE_TX_BD_DATA_FORCE_VLAN_MODE_SHIFT     0
+#define CORE_TX_BD_DATA_VLAN_INSERTION_MASK	0x1
+#define CORE_TX_BD_DATA_VLAN_INSERTION_SHIFT      1
+#define CORE_TX_BD_DATA_START_BD_MASK	0x1
+#define CORE_TX_BD_DATA_START_BD_SHIFT            2
+#define CORE_TX_BD_DATA_IP_CSUM_MASK	0x1
+#define CORE_TX_BD_DATA_IP_CSUM_SHIFT             3
+#define CORE_TX_BD_DATA_L4_CSUM_MASK	0x1
+#define CORE_TX_BD_DATA_L4_CSUM_SHIFT             4
+#define CORE_TX_BD_DATA_IPV6_EXT_MASK	0x1
+#define CORE_TX_BD_DATA_IPV6_EXT_SHIFT            5
+#define CORE_TX_BD_DATA_L4_PROTOCOL_MASK	0x1
+#define CORE_TX_BD_DATA_L4_PROTOCOL_SHIFT         6
+#define CORE_TX_BD_DATA_L4_PSEUDO_CSUM_MODE_MASK	0x1
+#define CORE_TX_BD_DATA_L4_PSEUDO_CSUM_MODE_SHIFT 7
+#define CORE_TX_BD_DATA_NBDS_MASK	0xF
+#define CORE_TX_BD_DATA_NBDS_SHIFT                8
+#define CORE_TX_BD_DATA_ROCE_FLAV_MASK	0x1
+#define CORE_TX_BD_DATA_ROCE_FLAV_SHIFT           12
+#define CORE_TX_BD_DATA_IP_LEN_MASK	0x1
+#define CORE_TX_BD_DATA_IP_LEN_SHIFT              13
+#define CORE_TX_BD_DATA_RESERVED0_MASK            0x3
+#define CORE_TX_BD_DATA_RESERVED0_SHIFT           14
 };
 
 struct core_tx_bd {
 	struct regpair addr;
 	__le16 nbytes;
 	__le16 nw_vlan_or_lb_echo;
-	u8 bitfield0;
-#define CORE_TX_BD_NBDS_MASK	0xF
-#define CORE_TX_BD_NBDS_SHIFT	0
-#define CORE_TX_BD_ROCE_FLAV_MASK	0x1
-#define CORE_TX_BD_ROCE_FLAV_SHIFT	4
-#define CORE_TX_BD_RESERVED0_MASK	0x7
-#define CORE_TX_BD_RESERVED0_SHIFT	5
-	struct core_tx_bd_flags bd_flags;
+	struct core_tx_bd_data bd_data;
 	__le16 bitfield1;
 #define CORE_TX_BD_L4_HDR_OFFSET_W_MASK	0x3FFF
 #define CORE_TX_BD_L4_HDR_OFFSET_W_SHIFT 0
 #define CORE_TX_BD_TX_DST_MASK	0x1
 #define CORE_TX_BD_TX_DST_SHIFT	14
-#define CORE_TX_BD_RESERVED1_MASK	0x1
-#define CORE_TX_BD_RESERVED1_SHIFT	15
+#define CORE_TX_BD_RESERVED_MASK         0x1
+#define CORE_TX_BD_RESERVED_SHIFT        15
 };
 
 enum core_tx_dest {
@@ -800,6 +804,14 @@ struct core_tx_stop_ramrod_data {
 	__le32 reserved0[2];
 };
 
+enum dcb_dhcp_update_flag {
+	DONT_UPDATE_DCB_DHCP,
+	UPDATE_DCB,
+	UPDATE_DSCP,
+	UPDATE_DCB_DSCP,
+	MAX_DCB_DHCP_UPDATE_FLAG
+};
+
 struct eth_mstorm_per_pf_stat {
 	struct regpair gre_discard_pkts;
 	struct regpair vxlan_discard_pkts;
@@ -893,6 +905,12 @@ union event_ring_element {
 	struct event_ring_next_addr next_addr;
 };
 
+enum fw_flow_ctrl_mode {
+	flow_ctrl_pause,
+	flow_ctrl_pfc,
+	MAX_FW_FLOW_CTRL_MODE
+};
+
 /* Major and Minor hsi Versions */
 struct hsi_fp_ver_struct {
 	u8 minor_ver_arr[2];
@@ -921,6 +939,7 @@ enum malicious_vf_error_id {
 	ETH_EDPM_OUT_OF_SYNC,
 	ETH_TUNN_IPV6_EXT_NBD_ERR,
 	ETH_CONTROL_PACKET_VIOLATION,
+	ETH_ANTI_SPOOFING_ERR,
 	MAX_MALICIOUS_VF_ERROR_ID
 };
 
@@ -1106,8 +1125,9 @@ struct tstorm_per_port_stat {
 	struct regpair ll2_mac_filter_discard;
 	struct regpair ll2_conn_disabled_discard;
 	struct regpair iscsi_irregular_pkt;
-	struct regpair reserved;
+	struct regpair fcoe_irregular_pkt;
 	struct regpair roce_irregular_pkt;
+	struct regpair reserved;
 	struct regpair eth_irregular_pkt;
 	struct regpair reserved1;
 	struct regpair preroce_irregular_pkt;
@@ -1648,6 +1668,11 @@ enum block_addr {
 	GRCBASE_MS = 0x6a0000,
 	GRCBASE_PHY_PCIE = 0x620000,
 	GRCBASE_LED = 0x6b8000,
+	GRCBASE_AVS_WRAP = 0x6b0000,
+	GRCBASE_RGFS = 0x19d0000,
+	GRCBASE_TGFS = 0x19e0000,
+	GRCBASE_PTLD = 0x19f0000,
+	GRCBASE_YPLD = 0x1a10000,
 	GRCBASE_MISC_AEU = 0x8000,
 	GRCBASE_BAR0_MAP = 0x1c00000,
 	MAX_BLOCK_ADDR
@@ -1732,6 +1757,11 @@ enum block_id {
 	BLOCK_MS,
 	BLOCK_PHY_PCIE,
 	BLOCK_LED,
+	BLOCK_AVS_WRAP,
+	BLOCK_RGFS,
+	BLOCK_TGFS,
+	BLOCK_PTLD,
+	BLOCK_YPLD,
 	BLOCK_MISC_AEU,
 	BLOCK_BAR0_MAP,
 	MAX_BLOCK_ID
@@ -1783,9 +1813,9 @@ struct dbg_attn_reg_result {
 	__le32 data;
 #define DBG_ATTN_REG_RESULT_STS_ADDRESS_MASK	0xFFFFFF
 #define DBG_ATTN_REG_RESULT_STS_ADDRESS_SHIFT	0
-#define DBG_ATTN_REG_RESULT_NUM_ATTN_IDX_MASK	0xFF
-#define DBG_ATTN_REG_RESULT_NUM_ATTN_IDX_SHIFT	24
-	__le16 attn_idx_offset;
+#define DBG_ATTN_REG_RESULT_NUM_REG_ATTN_MASK	0xFF
+#define DBG_ATTN_REG_RESULT_NUM_REG_ATTN_SHIFT	24
+	__le16 block_attn_offset;
 	__le16 reserved;
 	__le32 sts_val;
 	__le32 mask_val;
@@ -1815,12 +1845,12 @@ struct dbg_mode_hdr {
 /* Attention register */
 struct dbg_attn_reg {
 	struct dbg_mode_hdr mode;
-	__le16 attn_idx_offset;
+	__le16 block_attn_offset;
 	__le32 data;
 #define DBG_ATTN_REG_STS_ADDRESS_MASK	0xFFFFFF
 #define DBG_ATTN_REG_STS_ADDRESS_SHIFT	0
-#define DBG_ATTN_REG_NUM_ATTN_IDX_MASK	0xFF
-#define DBG_ATTN_REG_NUM_ATTN_IDX_SHIFT	24
+#define DBG_ATTN_REG_NUM_REG_ATTN_MASK	0xFF
+#define DBG_ATTN_REG_NUM_REG_ATTN_SHIFT 24
 	__le32 sts_clr_address;
 	__le32 mask_address;
 };
@@ -2001,6 +2031,20 @@ enum dbg_bus_clients {
 	MAX_DBG_BUS_CLIENTS
 };
 
+enum dbg_bus_constraint_ops {
+	DBG_BUS_CONSTRAINT_OP_EQ,
+	DBG_BUS_CONSTRAINT_OP_NE,
+	DBG_BUS_CONSTRAINT_OP_LT,
+	DBG_BUS_CONSTRAINT_OP_LTC,
+	DBG_BUS_CONSTRAINT_OP_LE,
+	DBG_BUS_CONSTRAINT_OP_LEC,
+	DBG_BUS_CONSTRAINT_OP_GT,
+	DBG_BUS_CONSTRAINT_OP_GTC,
+	DBG_BUS_CONSTRAINT_OP_GE,
+	DBG_BUS_CONSTRAINT_OP_GEC,
+	MAX_DBG_BUS_CONSTRAINT_OPS
+};
+
 /* Debug Bus memory address */
 struct dbg_bus_mem_addr {
 	__le32 lo;
@@ -2092,10 +2136,18 @@ struct dbg_bus_data {
 					      * DBG_BUS_TARGET_ID_PCI.
 					      */
 	__le16 reserved;
-	struct dbg_bus_block_data blocks[80];/* Debug Bus data for each block */
+	struct dbg_bus_block_data blocks[88];/* Debug Bus data for each block */
 	struct dbg_bus_storm_data storms[6]; /* Debug Bus data for each block */
 };
 
+enum dbg_bus_filter_types {
+	DBG_BUS_FILTER_TYPE_OFF,
+	DBG_BUS_FILTER_TYPE_PRE,
+	DBG_BUS_FILTER_TYPE_POST,
+	DBG_BUS_FILTER_TYPE_ON,
+	MAX_DBG_BUS_FILTER_TYPES
+};
+
 /* Debug bus frame modes */
 enum dbg_bus_frame_modes {
 	DBG_BUS_FRAME_MODE_0HW_4ST = 0, /* 0 HW dwords, 4 Storm dwords */
@@ -2104,6 +2156,40 @@ enum dbg_bus_frame_modes {
 	MAX_DBG_BUS_FRAME_MODES
 };
 
+enum dbg_bus_input_types {
+	DBG_BUS_INPUT_TYPE_STORM,
+	DBG_BUS_INPUT_TYPE_BLOCK,
+	MAX_DBG_BUS_INPUT_TYPES
+};
+
+enum dbg_bus_other_engine_modes {
+	DBG_BUS_OTHER_ENGINE_MODE_NONE,
+	DBG_BUS_OTHER_ENGINE_MODE_DOUBLE_BW_TX,
+	DBG_BUS_OTHER_ENGINE_MODE_DOUBLE_BW_RX,
+	DBG_BUS_OTHER_ENGINE_MODE_CROSS_ENGINE_TX,
+	DBG_BUS_OTHER_ENGINE_MODE_CROSS_ENGINE_RX,
+	MAX_DBG_BUS_OTHER_ENGINE_MODES
+};
+
+enum dbg_bus_post_trigger_types {
+	DBG_BUS_POST_TRIGGER_RECORD,
+	DBG_BUS_POST_TRIGGER_DROP,
+	MAX_DBG_BUS_POST_TRIGGER_TYPES
+};
+
+enum dbg_bus_pre_trigger_types {
+	DBG_BUS_PRE_TRIGGER_START_FROM_ZERO,
+	DBG_BUS_PRE_TRIGGER_NUM_CHUNKS,
+	DBG_BUS_PRE_TRIGGER_DROP,
+	MAX_DBG_BUS_PRE_TRIGGER_TYPES
+};
+
+enum dbg_bus_semi_frame_modes {
+	DBG_BUS_SEMI_FRAME_MODE_0SLOW_4FAST = 0,
+	DBG_BUS_SEMI_FRAME_MODE_4SLOW_0FAST = 3,
+	MAX_DBG_BUS_SEMI_FRAME_MODES
+};
+
 /* Debug bus states */
 enum dbg_bus_states {
 	DBG_BUS_STATE_IDLE, /* debug bus idle state (not recording) */
@@ -2115,6 +2201,19 @@ enum dbg_bus_states {
 	MAX_DBG_BUS_STATES
 };
 
+enum dbg_bus_storm_modes {
+	DBG_BUS_STORM_MODE_PRINTF,
+	DBG_BUS_STORM_MODE_PRAM_ADDR,
+	DBG_BUS_STORM_MODE_DRA_RW,
+	DBG_BUS_STORM_MODE_DRA_W,
+	DBG_BUS_STORM_MODE_LD_ST_ADDR,
+	DBG_BUS_STORM_MODE_DRA_FSM,
+	DBG_BUS_STORM_MODE_RH,
+	DBG_BUS_STORM_MODE_FOC,
+	DBG_BUS_STORM_MODE_EXT_STORE,
+	MAX_DBG_BUS_STORM_MODES
+};
+
 /* Debug bus target IDs */
 enum dbg_bus_targets {
 	/* records debug bus to DBG block internal buffer */
@@ -2128,13 +2227,10 @@ enum dbg_bus_targets {
 
 /* GRC Dump data */
 struct dbg_grc_data {
-	__le32 param_val[40]; /* Value of each GRC parameter. Array size must
-			       * match the enum dbg_grc_params.
-			       */
-	u8 param_set_by_user[40]; /* Indicates for each GRC parameter if it was
-				   * set by the user (0/1). Array size must
-				   * match the enum dbg_grc_params.
-				   */
+	u8 params_initialized;
+	u8 reserved1;
+	__le16 reserved2;
+	__le32 param_val[48];
 };
 
 /* Debug GRC params */
@@ -2181,6 +2277,8 @@ enum dbg_grc_params {
 	DBG_GRC_PARAM_PARITY_SAFE,
 	DBG_GRC_PARAM_DUMP_CM, /* dump CM memories (0/1) */
 	DBG_GRC_PARAM_DUMP_PHY, /* dump PHY memories (0/1) */
+	DBG_GRC_PARAM_NO_MCP,
+	DBG_GRC_PARAM_NO_FW_VER,
 	MAX_DBG_GRC_PARAMS
 };
 
@@ -2280,7 +2378,7 @@ struct dbg_tools_data {
 	struct dbg_bus_data bus; /* Debug Bus data */
 	struct idle_chk_data idle_chk; /* Idle Check data */
 	u8 mode_enable[40]; /* Indicates if a mode is enabled (0/1) */
-	u8 block_in_reset[80]; /* Indicates if a block is in reset state (0/1).
+	u8 block_in_reset[88]; /* Indicates if a block is in reset state (0/1).
 				*/
 	u8 chip_id; /* Chip ID (from enum chip_ids) */
 	u8 platform_id; /* Platform ID (from enum platform_ids) */
@@ -2404,7 +2502,7 @@ struct fw_info_location {
 
 enum init_modes {
 	MODE_RESERVED,
-	MODE_BB_B0,
+	MODE_BB,
 	MODE_K2,
 	MODE_ASIC,
 	MODE_RESERVED2,
@@ -2418,7 +2516,6 @@ enum init_modes {
 	MODE_PORTS_PER_ENG_2,
 	MODE_PORTS_PER_ENG_4,
 	MODE_100G,
-	MODE_40G,
 	MODE_RESERVED6,
 	MAX_INIT_MODES
 };
@@ -2686,6 +2783,13 @@ struct iro {
  */
 enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr);
 /**
+ * @brief qed_dbg_grc_set_params_default - Reverts all GRC parameters to their
+ *	default value.
+ *
+ * @param p_hwfn		- HW device data
+ */
+void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn);
+/**
  * @brief qed_dbg_grc_get_dump_buf_size - Returns the required buffer size for
  *	GRC Dump.
  *
@@ -3418,7 +3522,7 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn,
 #define	MSTORM_TPA_TIMEOUT_US_SIZE			(IRO[21].size)
 #define	MSTORM_ETH_PF_STAT_OFFSET(pf_id) \
 	(IRO[22].base + ((pf_id) * IRO[22].m1))
-#define	MSTORM_ETH_PF_STAT_SIZE				(IRO[21].size)
+#define	MSTORM_ETH_PF_STAT_SIZE				(IRO[22].size)
 #define	USTORM_QUEUE_STAT_OFFSET(stat_counter_id) \
 	(IRO[23].base + ((stat_counter_id) * IRO[23].m1))
 #define	USTORM_QUEUE_STAT_SIZE				(IRO[23].size)
@@ -3482,7 +3586,7 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn,
 
 static const struct iro iro_arr[47] = {
 	{0x0, 0x0, 0x0, 0x0, 0x8},
-	{0x4cb0, 0x78, 0x0, 0x0, 0x78},
+	{0x4cb0, 0x80, 0x0, 0x0, 0x80},
 	{0x6318, 0x20, 0x0, 0x0, 0x20},
 	{0xb00, 0x8, 0x0, 0x0, 0x4},
 	{0xa80, 0x8, 0x0, 0x0, 0x4},
@@ -3521,13 +3625,13 @@ static const struct iro iro_arr[47] = {
 	{0xd888, 0x38, 0x0, 0x0, 0x24},
 	{0x12c38, 0x10, 0x0, 0x0, 0x8},
 	{0x11aa0, 0x38, 0x0, 0x0, 0x18},
-	{0xa8c0, 0x30, 0x0, 0x0, 0x10},
-	{0x86f8, 0x28, 0x0, 0x0, 0x18},
+	{0xa8c0, 0x38, 0x0, 0x0, 0x10},
+	{0x86f8, 0x30, 0x0, 0x0, 0x18},
 	{0x101f8, 0x10, 0x0, 0x0, 0x10},
 	{0xdd08, 0x48, 0x0, 0x0, 0x38},
 	{0x10660, 0x20, 0x0, 0x0, 0x20},
 	{0x2b80, 0x80, 0x0, 0x0, 0x10},
-	{0x5000, 0x10, 0x0, 0x0, 0x10},
+	{0x5020, 0x10, 0x0, 0x0, 0x10},
 };
 
 /* Runtime array offsets */
@@ -4595,6 +4699,12 @@ enum eth_ipv4_frag_type {
 	MAX_ETH_IPV4_FRAG_TYPE
 };
 
+enum eth_ip_type {
+	ETH_IPV4,
+	ETH_IPV6,
+	MAX_ETH_IP_TYPE
+};
+
 enum eth_ramrod_cmd_id {
 	ETH_RAMROD_UNUSED,
 	ETH_RAMROD_VPORT_START,
@@ -4944,7 +5054,10 @@ struct vport_update_ramrod_data_cmn {
 	u8 update_mtu_flg;
 
 	__le16 mtu;
-	u8 reserved[2];
+	u8 update_ctl_frame_checks_en_flg;
+	u8 ctl_frame_mac_check_en;
+	u8 ctl_frame_ethtype_check_en;
+	u8 reserved[15];
 };
 
 struct vport_update_ramrod_mcast {
@@ -4962,6 +5075,492 @@ struct vport_update_ramrod_data {
 	struct eth_vport_rss_config rss_config;
 };
 
+struct mstorm_eth_conn_ag_ctx {
+	u8 byte0;
+	u8 byte1;
+	u8 flags0;
+#define MSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0
+#define MSTORM_ETH_CONN_AG_CTX_BIT1_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_BIT1_SHIFT         1
+#define MSTORM_ETH_CONN_AG_CTX_CF0_MASK	0x3
+#define MSTORM_ETH_CONN_AG_CTX_CF0_SHIFT          2
+#define MSTORM_ETH_CONN_AG_CTX_CF1_MASK	0x3
+#define MSTORM_ETH_CONN_AG_CTX_CF1_SHIFT          4
+#define MSTORM_ETH_CONN_AG_CTX_CF2_MASK	0x3
+#define MSTORM_ETH_CONN_AG_CTX_CF2_SHIFT          6
+	u8 flags1;
+#define MSTORM_ETH_CONN_AG_CTX_CF0EN_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_CF0EN_SHIFT        0
+#define MSTORM_ETH_CONN_AG_CTX_CF1EN_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_CF1EN_SHIFT        1
+#define MSTORM_ETH_CONN_AG_CTX_CF2EN_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT        2
+#define MSTORM_ETH_CONN_AG_CTX_RULE0EN_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT      3
+#define MSTORM_ETH_CONN_AG_CTX_RULE1EN_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT      4
+#define MSTORM_ETH_CONN_AG_CTX_RULE2EN_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT      5
+#define MSTORM_ETH_CONN_AG_CTX_RULE3EN_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT      6
+#define MSTORM_ETH_CONN_AG_CTX_RULE4EN_MASK	0x1
+#define MSTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT      7
+	__le16 word0;
+	__le16 word1;
+	__le32 reg0;
+	__le32 reg1;
+};
+
+struct xstorm_eth_conn_agctxdq_ext_ldpart {
+	u8 reserved0;
+	u8 eth_state;
+	u8 flags0;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM0_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM0_SHIFT           0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED1_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED1_SHIFT              1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED2_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED2_SHIFT              2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM3_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM3_SHIFT           3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED3_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED3_SHIFT              4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED4_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED4_SHIFT              5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED5_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED5_SHIFT              6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED6_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED6_SHIFT              7
+	u8 flags1;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED7_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED7_SHIFT              0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED8_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED8_SHIFT              1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED9_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED9_SHIFT              2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT11_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT11_SHIFT                  3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT12_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT12_SHIFT                  4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT13_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT13_SHIFT                  5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_RULE_ACTIVE_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_RULE_ACTIVE_SHIFT         6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_ACTIVE_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_ACTIVE_SHIFT           7
+	u8 flags2;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0_SHIFT                    0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1_SHIFT                    2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2_SHIFT                    4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3_SHIFT                    6
+	u8 flags3;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4_SHIFT                    0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5_SHIFT                    2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6_SHIFT                    4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7_SHIFT                    6
+	u8 flags4;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8_SHIFT                    0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9_SHIFT                    2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10_SHIFT                   4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11_SHIFT                   6
+	u8 flags5;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12_SHIFT                   0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13_SHIFT                   2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14_SHIFT                   4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15_SHIFT                   6
+	u8 flags6;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_SHIFT       0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_SHIFT       2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_SHIFT                  4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_SHIFT           6
+	u8 flags7;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_SHIFT               0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED10_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED10_SHIFT             2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_SHIFT              4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0EN_SHIFT                  6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1EN_SHIFT                  7
+	u8 flags8;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2EN_SHIFT                  0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3EN_SHIFT                  1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4EN_SHIFT                  2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5EN_SHIFT                  3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6EN_SHIFT                  4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7EN_SHIFT                  5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8EN_SHIFT                  6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9EN_SHIFT                  7
+	u8 flags9;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10EN_SHIFT                 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11EN_SHIFT                 1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12EN_SHIFT                 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13EN_SHIFT                 3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14EN_SHIFT                 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15EN_SHIFT                 5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_EN_SHIFT    6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_EN_SHIFT    7
+	u8 flags10;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_EN_SHIFT               0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_EN_SHIFT        1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_EN_SHIFT            2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED11_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED11_SHIFT             3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_EN_SHIFT           4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_EN_RESERVED_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_EN_RESERVED_SHIFT 5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED12_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED12_SHIFT             6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED13_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED13_SHIFT             7
+	u8 flags11;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED14_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED14_SHIFT             0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED15_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED15_SHIFT             1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_DEC_RULE_EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_DEC_RULE_EN_SHIFT         2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE5EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE5EN_SHIFT                3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE6EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE6EN_SHIFT                4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE7EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE7EN_SHIFT                5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED1_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED1_SHIFT           6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE9EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE9EN_SHIFT                7
+	u8 flags12;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE10EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE10EN_SHIFT               0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE11EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE11EN_SHIFT               1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED2_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED2_SHIFT           2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED3_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED3_SHIFT           3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE14EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE14EN_SHIFT               4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE15EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE15EN_SHIFT               5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE16EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE16EN_SHIFT               6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE17EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE17EN_SHIFT               7
+	u8 flags13;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE18EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE18EN_SHIFT               0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE19EN_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE19EN_SHIFT               1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED4_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED4_SHIFT           2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED5_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED5_SHIFT           3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED6_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED6_SHIFT           4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED7_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED7_SHIFT           5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED8_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED8_SHIFT           6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED9_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED9_SHIFT           7
+	u8 flags14;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_USE_EXT_HDR_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_USE_EXT_HDR_SHIFT       0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_RAW_L3L4_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_RAW_L3L4_SHIFT     1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_INBAND_PROP_HDR_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_INBAND_PROP_HDR_SHIFT   2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_EXT_TUNNEL_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_EXT_TUNNEL_SHIFT   3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_L2_EDPM_ENABLE_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_L2_EDPM_ENABLE_SHIFT         4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_ROCE_EDPM_ENABLE_MASK	0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_ROCE_EDPM_ENABLE_SHIFT       5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_MASK	0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_SHIFT             6
+	u8 edpm_event_id;
+	__le16 physical_q0;
+	__le16 quota;
+	__le16 edpm_num_bds;
+	__le16 tx_bd_cons;
+	__le16 tx_bd_prod;
+	__le16 tx_class;
+	__le16 conn_dpi;
+	u8 byte3;
+	u8 byte4;
+	u8 byte5;
+	u8 byte6;
+	__le32 reg0;
+	__le32 reg1;
+	__le32 reg2;
+	__le32 reg3;
+	__le32 reg4;
+};
+
+struct xstorm_eth_hw_conn_ag_ctx {
+	u8 reserved0;
+	u8 eth_state;
+	u8 flags0;
+#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM0_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM0_SHIFT           0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED1_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED1_SHIFT              1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED2_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED2_SHIFT              2
+#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM3_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM3_SHIFT           3
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED3_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED3_SHIFT              4
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED4_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED4_SHIFT              5
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED5_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED5_SHIFT              6
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED6_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED6_SHIFT              7
+	u8 flags1;
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED7_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED7_SHIFT              0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED8_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED8_SHIFT              1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED9_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED9_SHIFT              2
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT11_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT11_SHIFT                  3
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT12_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT12_SHIFT                  4
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT13_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT13_SHIFT                  5
+#define XSTORM_ETH_HW_CONN_AG_CTX_TX_RULE_ACTIVE_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_TX_RULE_ACTIVE_SHIFT         6
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_ACTIVE_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_ACTIVE_SHIFT           7
+	u8 flags2;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF0_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF0_SHIFT                    0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF1_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF1_SHIFT                    2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF2_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF2_SHIFT                    4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF3_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF3_SHIFT                    6
+	u8 flags3;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF4_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF4_SHIFT                    0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF5_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF5_SHIFT                    2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF6_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF6_SHIFT                    4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF7_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF7_SHIFT                    6
+	u8 flags4;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF8_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF8_SHIFT                    0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF9_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF9_SHIFT                    2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF10_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF10_SHIFT                   4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF11_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF11_SHIFT                   6
+	u8 flags5;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF12_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF12_SHIFT                   0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF13_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF13_SHIFT                   2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF14_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF14_SHIFT                   4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF15_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF15_SHIFT                   6
+	u8 flags6;
+#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_SHIFT       0
+#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_SHIFT       2
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_SHIFT                  4
+#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_SHIFT           6
+	u8 flags7;
+#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_SHIFT               0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED10_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED10_SHIFT             2
+#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_SHIFT              4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF0EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF0EN_SHIFT                  6
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF1EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF1EN_SHIFT                  7
+	u8 flags8;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF2EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF2EN_SHIFT                  0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF3EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF3EN_SHIFT                  1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF4EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF4EN_SHIFT                  2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF5EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF5EN_SHIFT                  3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF6EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF6EN_SHIFT                  4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF7EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF7EN_SHIFT                  5
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF8EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF8EN_SHIFT                  6
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF9EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF9EN_SHIFT                  7
+	u8 flags9;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF10EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF10EN_SHIFT                 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF11EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF11EN_SHIFT                 1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF12EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF12EN_SHIFT                 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF13EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF13EN_SHIFT                 3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF14EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF14EN_SHIFT                 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF15EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF15EN_SHIFT                 5
+#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_SHIFT    6
+#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_EN_SHIFT    7
+	u8 flags10;
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_EN_SHIFT               0
+#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_EN_SHIFT        1
+#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT            2
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED11_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED11_SHIFT             3
+#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_EN_SHIFT           4
+#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_SHIFT 5
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED12_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED12_SHIFT             6
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED13_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED13_SHIFT             7
+	u8 flags11;
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED14_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED14_SHIFT             0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED15_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED15_SHIFT             1
+#define XSTORM_ETH_HW_CONN_AG_CTX_TX_DEC_RULE_EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_TX_DEC_RULE_EN_SHIFT         2
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE5EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE5EN_SHIFT                3
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE6EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE6EN_SHIFT                4
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE7EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE7EN_SHIFT                5
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED1_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED1_SHIFT           6
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE9EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE9EN_SHIFT                7
+	u8 flags12;
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE10EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE10EN_SHIFT               0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE11EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE11EN_SHIFT               1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED2_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED2_SHIFT           2
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED3_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED3_SHIFT           3
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE14EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE14EN_SHIFT               4
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE15EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE15EN_SHIFT               5
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE16EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE16EN_SHIFT               6
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE17EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE17EN_SHIFT               7
+	u8 flags13;
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE18EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE18EN_SHIFT               0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE19EN_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE19EN_SHIFT               1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED4_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED4_SHIFT           2
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED5_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED5_SHIFT           3
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED6_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED6_SHIFT           4
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED7_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED7_SHIFT           5
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED8_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED8_SHIFT           6
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED9_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED9_SHIFT           7
+	u8 flags14;
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_USE_EXT_HDR_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_USE_EXT_HDR_SHIFT       0
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_SHIFT     1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_SHIFT   2
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_SHIFT   3
+#define XSTORM_ETH_HW_CONN_AG_CTX_L2_EDPM_ENABLE_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_L2_EDPM_ENABLE_SHIFT         4
+#define XSTORM_ETH_HW_CONN_AG_CTX_ROCE_EDPM_ENABLE_MASK	0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_ROCE_EDPM_ENABLE_SHIFT       5
+#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_MASK	0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_SHIFT             6
+	u8 edpm_event_id;
+	__le16 physical_q0;
+	__le16 quota;
+	__le16 edpm_num_bds;
+	__le16 tx_bd_cons;
+	__le16 tx_bd_prod;
+	__le16 tx_class;
+	__le16 conn_dpi;
+};
+
 struct mstorm_rdma_task_st_ctx {
 	struct regpair temp[4];
 };
@@ -6165,7 +6764,7 @@ struct ystorm_roce_conn_st_ctx {
 };
 
 struct xstorm_roce_conn_st_ctx {
-	struct regpair temp[22];
+	struct regpair temp[24];
 };
 
 struct tstorm_roce_conn_st_ctx {
@@ -6220,7 +6819,7 @@ struct roce_create_qp_req_ramrod_data {
 	__le16 mtu;
 	__le16 pd;
 	__le16 sq_num_pages;
-	__le16 reseved2;
+	__le16 low_latency_phy_queue;
 	struct regpair sq_pbl_addr;
 	struct regpair orq_pbl_addr;
 	__le16 local_mac_addr[3];
@@ -6234,7 +6833,7 @@ struct roce_create_qp_req_ramrod_data {
 	u8 stats_counter_id;
 	u8 reserved3[7];
 	__le32 cq_cid;
-	__le16 physical_queue0;
+	__le16 regular_latency_phy_queue;
 	__le16 dpi;
 };
 
@@ -6282,15 +6881,16 @@ struct roce_create_qp_resp_ramrod_data {
 	__le32 dst_gid[4];
 	struct regpair qp_handle_for_cqe;
 	struct regpair qp_handle_for_async;
-	__le32 reserved2[2];
+	__le16 low_latency_phy_queue;
+	u8 reserved2[6];
 	__le32 cq_cid;
-	__le16 physical_queue0;
+	__le16 regular_latency_phy_queue;
 	__le16 dpi;
 };
 
 struct roce_destroy_qp_req_output_params {
 	__le32 num_bound_mw;
-	__le32 reserved;
+	__le32 cq_prod;
 };
 
 struct roce_destroy_qp_req_ramrod_data {
@@ -6299,7 +6899,7 @@ struct roce_destroy_qp_req_ramrod_data {
 
 struct roce_destroy_qp_resp_output_params {
 	__le32 num_invalidated_mw;
-	__le32 reserved;
+	__le32 cq_prod;
 };
 
 struct roce_destroy_qp_resp_ramrod_data {
@@ -7426,6 +8026,7 @@ struct ystorm_fcoe_conn_st_ctx {
 	u8 fcp_rsp_size;
 	__le16 mss;
 	struct regpair reserved;
+	__le16 min_frame_size;
 	u8 protection_info_flags;
 #define YSTORM_FCOE_CONN_ST_CTX_SUPPORT_PROTECTION_MASK  0x1
 #define YSTORM_FCOE_CONN_ST_CTX_SUPPORT_PROTECTION_SHIFT 0
@@ -7444,7 +8045,6 @@ struct ystorm_fcoe_conn_st_ctx {
 #define YSTORM_FCOE_CONN_ST_CTX_RSRV_MASK                0x3F
 #define YSTORM_FCOE_CONN_ST_CTX_RSRV_SHIFT               2
 	u8 fcp_xfer_size;
-	u8 reserved3[2];
 };
 
 struct fcoe_vlan_fields {
@@ -8273,10 +8873,10 @@ struct xstorm_iscsi_conn_ag_ctx {
 #define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_MASK                    0x3
 #define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_SHIFT                   6
 	u8 flags7;
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_MASK                    0x3
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_SHIFT                   0
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_MASK                    0x3
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_SHIFT                   2
+#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_MASK	0x3
+#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_SHIFT        0
+#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_MASK	0x3
+#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_SHIFT        2
 #define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_MASK                   0x3
 #define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_SHIFT                  4
 #define XSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK                       0x1
@@ -8322,10 +8922,10 @@ struct xstorm_iscsi_conn_ag_ctx {
 #define XSTORM_ISCSI_CONN_AG_CTX_CF18EN_SHIFT                     0
 #define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_EN_MASK                 0x1
 #define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_EN_SHIFT                1
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_EN_MASK                 0x1
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT                2
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_EN_MASK                 0x1
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_EN_SHIFT                3
+#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_EN_MASK	0x1
+#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_EN_SHIFT     2
+#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_EN_MASK	0x1
+#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_EN_SHIFT     3
 #define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_EN_MASK                0x1
 #define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_EN_SHIFT               4
 #define XSTORM_ISCSI_CONN_AG_CTX_PROC_ONLY_CLEANUP_EN_MASK        0x1
@@ -8335,8 +8935,8 @@ struct xstorm_iscsi_conn_ag_ctx {
 #define XSTORM_ISCSI_CONN_AG_CTX_MORE_TO_SEND_DEC_RULE_EN_MASK    0x1
 #define XSTORM_ISCSI_CONN_AG_CTX_MORE_TO_SEND_DEC_RULE_EN_SHIFT   7
 	u8 flags11;
-#define XSTORM_ISCSI_CONN_AG_CTX_RULE2EN_MASK                     0x1
-#define XSTORM_ISCSI_CONN_AG_CTX_RULE2EN_SHIFT                    0
+#define XSTORM_ISCSI_CONN_AG_CTX_TX_BLOCKED_EN_MASK	0x1
+#define XSTORM_ISCSI_CONN_AG_CTX_TX_BLOCKED_EN_SHIFT              0
 #define XSTORM_ISCSI_CONN_AG_CTX_RULE3EN_MASK                     0x1
 #define XSTORM_ISCSI_CONN_AG_CTX_RULE3EN_SHIFT                    1
 #define XSTORM_ISCSI_CONN_AG_CTX_RESERVED3_MASK                   0x1
@@ -8440,7 +9040,7 @@ struct xstorm_iscsi_conn_ag_ctx {
 	__le32 reg10;
 	__le32 reg11;
 	__le32 exp_stat_sn;
-	__le32 reg13;
+	__le32 ongoing_fast_rxmit_seq;
 	__le32 reg14;
 	__le32 reg15;
 	__le32 reg16;
@@ -8466,10 +9066,10 @@ struct tstorm_iscsi_conn_ag_ctx {
 #define TSTORM_ISCSI_CONN_AG_CTX_CF0_MASK                0x3
 #define TSTORM_ISCSI_CONN_AG_CTX_CF0_SHIFT               6
 	u8 flags1;
-#define TSTORM_ISCSI_CONN_AG_CTX_CF1_MASK                0x3
-#define TSTORM_ISCSI_CONN_AG_CTX_CF1_SHIFT               0
-#define TSTORM_ISCSI_CONN_AG_CTX_CF2_MASK                0x3
-#define TSTORM_ISCSI_CONN_AG_CTX_CF2_SHIFT               2
+#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_MASK	0x3
+#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_SHIFT      0
+#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_MASK	0x3
+#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_SHIFT      2
 #define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_MASK     0x3
 #define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_SHIFT    4
 #define TSTORM_ISCSI_CONN_AG_CTX_CF4_MASK                0x3
@@ -8490,10 +9090,10 @@ struct tstorm_iscsi_conn_ag_ctx {
 #define TSTORM_ISCSI_CONN_AG_CTX_CF10_SHIFT              2
 #define TSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK              0x1
 #define TSTORM_ISCSI_CONN_AG_CTX_CF0EN_SHIFT             4
-#define TSTORM_ISCSI_CONN_AG_CTX_CF1EN_MASK              0x1
-#define TSTORM_ISCSI_CONN_AG_CTX_CF1EN_SHIFT             5
-#define TSTORM_ISCSI_CONN_AG_CTX_CF2EN_MASK              0x1
-#define TSTORM_ISCSI_CONN_AG_CTX_CF2EN_SHIFT             6
+#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_EN_MASK	0x1
+#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_EN_SHIFT   5
+#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_EN_MASK	0x1
+#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_EN_SHIFT   6
 #define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_MASK  0x1
 #define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 7
 	u8 flags4;
@@ -8539,7 +9139,7 @@ struct tstorm_iscsi_conn_ag_ctx {
 	__le32 reg6;
 	__le32 reg7;
 	__le32 reg8;
-	u8 byte2;
+	u8 cid_offload_cnt;
 	u8 byte3;
 	__le16 word0;
 };
@@ -8831,11 +9431,24 @@ struct eth_stats {
 	u64 r511;
 	u64 r1023;
 	u64 r1518;
-	u64 r1522;
-	u64 r2047;
-	u64 r4095;
-	u64 r9216;
-	u64 r16383;
+
+	union {
+		struct {
+			u64 r1522;
+			u64 r2047;
+			u64 r4095;
+			u64 r9216;
+			u64 r16383;
+		} bb0;
+		struct {
+			u64 unused1;
+			u64 r1519_to_max;
+			u64 unused2;
+			u64 unused3;
+			u64 unused4;
+		} ah0;
+	} u0;
+
 	u64 rfcs;
 	u64 rxcf;
 	u64 rxpf;
@@ -8852,14 +9465,36 @@ struct eth_stats {
 	u64 t511;
 	u64 t1023;
 	u64 t1518;
-	u64 t2047;
-	u64 t4095;
-	u64 t9216;
-	u64 t16383;
+
+	union {
+		struct {
+			u64 t2047;
+			u64 t4095;
+			u64 t9216;
+			u64 t16383;
+		} bb1;
+		struct {
+			u64 t1519_to_max;
+			u64 unused6;
+			u64 unused7;
+			u64 unused8;
+		} ah1;
+	} u1;
+
 	u64 txpf;
 	u64 txpp;
-	u64 tlpiec;
-	u64 tncl;
+
+	union {
+		struct {
+			u64 tlpiec;
+			u64 tncl;
+		} bb2;
+		struct {
+			u64 unused9;
+			u64 unused10;
+		} ah2;
+	} u2;
+
 	u64 rbyte;
 	u64 rxuca;
 	u64 rxmca;
@@ -8943,12 +9578,12 @@ struct dcbx_ets_feature {
 #define DCBX_ETS_CBS_SHIFT	3
 #define DCBX_ETS_MAX_TCS_MASK	0x000000f0
 #define DCBX_ETS_MAX_TCS_SHIFT	4
-#define DCBX_ISCSI_OOO_TC_MASK	0x00000f00
-#define DCBX_ISCSI_OOO_TC_SHIFT	8
+#define DCBX_OOO_TC_MASK	0x00000f00
+#define DCBX_OOO_TC_SHIFT	8
 	u32 pri_tc_tbl[1];
-#define DCBX_ISCSI_OOO_TC	(4)
+#define DCBX_TCP_OOO_TC		(4)
 
-#define NIG_ETS_ISCSI_OOO_CLIENT_OFFSET	(DCBX_ISCSI_OOO_TC + 1)
+#define NIG_ETS_ISCSI_OOO_CLIENT_OFFSET	(DCBX_TCP_OOO_TC + 1)
 #define DCBX_CEE_STRICT_PRIORITY	0xf
 	u32 tc_bw_tbl[2];
 	u32 tc_tsa_tbl[2];
@@ -8957,6 +9592,9 @@ struct dcbx_ets_feature {
 #define DCBX_ETS_TSA_ETS	2
 };
 
+#define DCBX_TCP_OOO_TC			(4)
+#define DCBX_TCP_OOO_K2_4PORT_TC	(3)
+
 struct dcbx_app_priority_entry {
 	u32 entry;
 #define DCBX_APP_PRI_MAP_MASK		0x000000ff
@@ -9067,6 +9705,10 @@ struct dcb_dscp_map {
 struct public_global {
 	u32 max_path;
 	u32 max_ports;
+#define MODE_1P 1
+#define MODE_2P 2
+#define MODE_3P 3
+#define MODE_4P 4
 	u32 debug_mb_offset;
 	u32 phymod_dbg_mb_offset;
 	struct couple_mode_teaming cmt;
@@ -9248,9 +9890,11 @@ struct public_func {
 #define DRV_ID_PDA_COMP_VER_MASK	0x0000ffff
 #define DRV_ID_PDA_COMP_VER_SHIFT	0
 
+#define LOAD_REQ_HSI_VERSION		2
 #define DRV_ID_MCP_HSI_VER_MASK		0x00ff0000
 #define DRV_ID_MCP_HSI_VER_SHIFT	16
-#define DRV_ID_MCP_HSI_VER_CURRENT	(1 << DRV_ID_MCP_HSI_VER_SHIFT)
+#define DRV_ID_MCP_HSI_VER_CURRENT	(LOAD_REQ_HSI_VERSION << \
+					 DRV_ID_MCP_HSI_VER_SHIFT)
 
 #define DRV_ID_DRV_TYPE_MASK		0x7f000000
 #define DRV_ID_DRV_TYPE_SHIFT		24
@@ -9345,6 +9989,7 @@ enum resource_id_enum {
 	RESOURCE_NUM_RSS_ENGINES_E = 14,
 	RESOURCE_LL2_QUEUE_E = 15,
 	RESOURCE_RDMA_STATS_QUEUE_E = 16,
+	RESOURCE_BDQ_E = 17,
 	RESOURCE_MAX_NUM,
 	RESOURCE_NUM_INVALID = 0xFFFFFFFF
 };
@@ -9362,6 +10007,46 @@ struct resource_info {
 #define RESOURCE_ELEMENT_STRICT (1 << 0)
 };
 
+#define DRV_ROLE_NONE           0
+#define DRV_ROLE_PREBOOT        1
+#define DRV_ROLE_OS             2
+#define DRV_ROLE_KDUMP          3
+
+struct load_req_stc {
+	u32 drv_ver_0;
+	u32 drv_ver_1;
+	u32 fw_ver;
+	u32 misc0;
+#define LOAD_REQ_ROLE_MASK              0x000000FF
+#define LOAD_REQ_ROLE_SHIFT             0
+#define LOAD_REQ_LOCK_TO_MASK           0x0000FF00
+#define LOAD_REQ_LOCK_TO_SHIFT          8
+#define LOAD_REQ_LOCK_TO_DEFAULT        0
+#define LOAD_REQ_LOCK_TO_NONE           255
+#define LOAD_REQ_FORCE_MASK             0x000F0000
+#define LOAD_REQ_FORCE_SHIFT            16
+#define LOAD_REQ_FORCE_NONE             0
+#define LOAD_REQ_FORCE_PF               1
+#define LOAD_REQ_FORCE_ALL              2
+#define LOAD_REQ_FLAGS0_MASK            0x00F00000
+#define LOAD_REQ_FLAGS0_SHIFT           20
+#define LOAD_REQ_FLAGS0_AVOID_RESET     (0x1 << 0)
+};
+
+struct load_rsp_stc {
+	u32 drv_ver_0;
+	u32 drv_ver_1;
+	u32 fw_ver;
+	u32 misc0;
+#define LOAD_RSP_ROLE_MASK              0x000000FF
+#define LOAD_RSP_ROLE_SHIFT             0
+#define LOAD_RSP_HSI_MASK               0x0000FF00
+#define LOAD_RSP_HSI_SHIFT              8
+#define LOAD_RSP_FLAGS0_MASK            0x000F0000
+#define LOAD_RSP_FLAGS0_SHIFT           16
+#define LOAD_RSP_FLAGS0_DRV_EXISTS      (0x1 << 0)
+};
+
 union drv_union_data {
 	u32 ver_str[MCP_DRV_VER_STR_SIZE_DWORD];
 	struct mcp_mac wol_mac;
@@ -9393,6 +10078,7 @@ struct public_drv_mb {
 #define DRV_MSG_CODE_LOAD_REQ			0x10000000
 #define DRV_MSG_CODE_LOAD_DONE			0x11000000
 #define DRV_MSG_CODE_INIT_HW			0x12000000
+#define DRV_MSG_CODE_CANCEL_LOAD_REQ            0x13000000
 #define DRV_MSG_CODE_UNLOAD_REQ			0x20000000
 #define DRV_MSG_CODE_UNLOAD_DONE		0x21000000
 #define DRV_MSG_CODE_INIT_PHY			0x22000000
@@ -9405,12 +10091,14 @@ struct public_drv_mb {
 #define DRV_MSG_CODE_OV_UPDATE_DRIVER_STATE     0x31000000
 #define DRV_MSG_CODE_BW_UPDATE_ACK              0x32000000
 #define DRV_MSG_CODE_OV_UPDATE_MTU              0x33000000
+#define DRV_MSG_GET_RESOURCE_ALLOC_MSG		0x34000000
+#define DRV_MSG_SET_RESOURCE_VALUE_MSG		0x35000000
 #define DRV_MSG_CODE_OV_UPDATE_WOL              0x38000000
 #define DRV_MSG_CODE_OV_UPDATE_ESWITCH_MODE     0x39000000
 
 #define DRV_MSG_CODE_BW_UPDATE_ACK		0x32000000
 #define DRV_MSG_CODE_NIG_DRAIN			0x30000000
-#define DRV_MSG_GET_RESOURCE_ALLOC_MSG          0x34000000
+#define DRV_MSG_CODE_INITIATE_PF_FLR            0x02010000
 #define DRV_MSG_CODE_VF_DISABLED_DONE		0xc0000000
 #define DRV_MSG_CODE_CFG_VF_MSIX		0xc0010000
 #define DRV_MSG_CODE_NVM_GET_FILE_ATT		0x00030000
@@ -9436,6 +10124,33 @@ struct public_drv_mb {
 
 #define DRV_MSG_CODE_BIST_TEST			0x001e0000
 #define DRV_MSG_CODE_SET_LED_MODE		0x00200000
+#define DRV_MSG_CODE_RESOURCE_CMD	0x00230000
+
+#define RESOURCE_CMD_REQ_RESC_MASK		0x0000001F
+#define RESOURCE_CMD_REQ_RESC_SHIFT		0
+#define RESOURCE_CMD_REQ_OPCODE_MASK		0x000000E0
+#define RESOURCE_CMD_REQ_OPCODE_SHIFT		5
+#define RESOURCE_OPCODE_REQ			1
+#define RESOURCE_OPCODE_REQ_WO_AGING		2
+#define RESOURCE_OPCODE_REQ_W_AGING		3
+#define RESOURCE_OPCODE_RELEASE			4
+#define RESOURCE_OPCODE_FORCE_RELEASE		5
+#define RESOURCE_CMD_REQ_AGE_MASK		0x0000FF00
+#define RESOURCE_CMD_REQ_AGE_SHIFT		8
+
+#define RESOURCE_CMD_RSP_OWNER_MASK		0x000000FF
+#define RESOURCE_CMD_RSP_OWNER_SHIFT		0
+#define RESOURCE_CMD_RSP_OPCODE_MASK		0x00000700
+#define RESOURCE_CMD_RSP_OPCODE_SHIFT		8
+#define RESOURCE_OPCODE_GNT			1
+#define RESOURCE_OPCODE_BUSY			2
+#define RESOURCE_OPCODE_RELEASED		3
+#define RESOURCE_OPCODE_RELEASED_PREVIOUS	4
+#define RESOURCE_OPCODE_WRONG_OWNER		5
+#define RESOURCE_OPCODE_UNKNOWN_CMD		255
+
+#define RESOURCE_DUMP				0
+
 #define DRV_MSG_CODE_GET_PF_RDMA_PROTOCOL	0x002b0000
 #define DRV_MSG_CODE_OS_WOL			0x002e0000
 
@@ -9524,12 +10239,16 @@ struct public_drv_mb {
 
 	u32 fw_mb_header;
 #define FW_MSG_CODE_MASK			0xffff0000
+#define FW_MSG_CODE_UNSUPPORTED                 0x00000000
 #define FW_MSG_CODE_DRV_LOAD_ENGINE		0x10100000
 #define FW_MSG_CODE_DRV_LOAD_PORT		0x10110000
 #define FW_MSG_CODE_DRV_LOAD_FUNCTION		0x10120000
 #define FW_MSG_CODE_DRV_LOAD_REFUSED_PDA	0x10200000
-#define FW_MSG_CODE_DRV_LOAD_REFUSED_HSI	0x10210000
+#define FW_MSG_CODE_DRV_LOAD_REFUSED_HSI_1	0x10210000
 #define FW_MSG_CODE_DRV_LOAD_REFUSED_DIAG	0x10220000
+#define FW_MSG_CODE_DRV_LOAD_REFUSED_HSI        0x10230000
+#define FW_MSG_CODE_DRV_LOAD_REFUSED_REQUIRES_FORCE 0x10300000
+#define FW_MSG_CODE_DRV_LOAD_REFUSED_REJECT     0x10310000
 #define FW_MSG_CODE_DRV_LOAD_DONE		0x11100000
 #define FW_MSG_CODE_DRV_UNLOAD_ENGINE		0x20110000
 #define FW_MSG_CODE_DRV_UNLOAD_PORT		0x20120000
@@ -9549,6 +10268,10 @@ struct public_drv_mb {
 #define FW_MSG_SEQ_NUMBER_MASK			0x0000ffff
 
 	u32 fw_mb_param;
+#define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_MASK	0xFFFF0000
+#define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_SHIFT	16
+#define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR_MASK	0x0000FFFF
+#define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR_SHIFT	0
 
 	/* get pf rdma protocol command responce */
 #define FW_MB_PARAM_GET_PF_RDMA_NONE		0x0
@@ -9659,6 +10382,8 @@ struct nvm_cfg1_glob {
 #define NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X25G		0xC
 #define NVM_CFG1_GLOB_NETWORK_PORT_MODE_1X25G		0xD
 #define NVM_CFG1_GLOB_NETWORK_PORT_MODE_4X25G		0xE
+#define NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X10G		0xF
+
 	u32 e_lane_cfg1;
 	u32 e_lane_cfg2;
 	u32 f_lane_cfg1;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c
index 899cad7f97ea..79e584a57d26 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c
@@ -800,55 +800,3 @@ int qed_dmae_host2host(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-u16 qed_get_qm_pq(struct qed_hwfn *p_hwfn,
-		  enum protocol_type proto, union qed_qm_pq_params *p_params)
-{
-	u16 pq_id = 0;
-
-	if ((proto == PROTOCOLID_CORE ||
-	     proto == PROTOCOLID_ETH ||
-	     proto == PROTOCOLID_ISCSI ||
-	     proto == PROTOCOLID_ROCE) && !p_params) {
-		DP_NOTICE(p_hwfn,
-			  "Protocol %d received NULL PQ params\n", proto);
-		return 0;
-	}
-
-	switch (proto) {
-	case PROTOCOLID_CORE:
-		if (p_params->core.tc == LB_TC)
-			pq_id = p_hwfn->qm_info.pure_lb_pq;
-		else if (p_params->core.tc == OOO_LB_TC)
-			pq_id = p_hwfn->qm_info.ooo_pq;
-		else
-			pq_id = p_hwfn->qm_info.offload_pq;
-		break;
-	case PROTOCOLID_ETH:
-		pq_id = p_params->eth.tc;
-		if (p_params->eth.is_vf)
-			pq_id += p_hwfn->qm_info.vf_queues_offset +
-				 p_params->eth.vf_id;
-		break;
-	case PROTOCOLID_ISCSI:
-		if (p_params->iscsi.q_idx == 1)
-			pq_id = p_hwfn->qm_info.pure_ack_pq;
-		break;
-	case PROTOCOLID_ROCE:
-		if (p_params->roce.dcqcn)
-			pq_id = p_params->roce.qpid;
-		else
-			pq_id = p_hwfn->qm_info.offload_pq;
-		if (pq_id > p_hwfn->qm_info.num_pf_rls)
-			pq_id = p_hwfn->qm_info.offload_pq;
-		break;
-	case PROTOCOLID_FCOE:
-		pq_id = p_hwfn->qm_info.offload_pq;
-		break;
-	default:
-		pq_id = 0;
-	}
-
-	pq_id = CM_TX_PQ_BASE + pq_id + RESC_START(p_hwfn, QED_PQ);
-
-	return pq_id;
-}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.h b/drivers/net/ethernet/qlogic/qed/qed_hw.h
index 9277264d2e65..f2505c691c26 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.h
@@ -297,9 +297,6 @@ union qed_qm_pq_params {
 	} roce;
 };
 
-u16 qed_get_qm_pq(struct qed_hwfn *p_hwfn,
-		  enum protocol_type proto, union qed_qm_pq_params *params);
-
 int qed_init_fw_data(struct qed_dev *cdev,
 		     const u8 *fw_data);
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
index d891a6852695..2a50e2b7568f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
@@ -215,13 +215,6 @@ static void qed_cmdq_lines_voq_rt_init(struct qed_hwfn *p_hwfn,
 {
 	u32 qm_line_crd;
 
-	/* In A0 - Limit the size of pbf queue so that only 511 commands with
-	 * the minimum size of 4 (FCoE minimum size)
-	 */
-	bool is_bb_a0 = QED_IS_BB_A0(p_hwfn->cdev);
-
-	if (is_bb_a0)
-		cmdq_lines = min_t(u32, cmdq_lines, 1022);
 	qm_line_crd = QM_VOQ_LINE_CRD(cmdq_lines);
 	OVERWRITE_RT_REG(p_hwfn, PBF_CMDQ_LINES_RT_OFFSET(voq),
 			 (u32)cmdq_lines);
@@ -343,13 +336,11 @@ static void qed_tx_pq_map_rt_init(
 	u16 first_pq_group = p_params->start_pq / QM_PF_QUEUE_GROUP_SIZE;
 	u16 last_pq_group = (p_params->start_pq + num_pqs - 1) /
 			    QM_PF_QUEUE_GROUP_SIZE;
-	bool is_bb_a0 = QED_IS_BB_A0(p_hwfn->cdev);
 	u16 i, pq_id, pq_group;
 
 	/* a bit per Tx PQ indicating if the PQ is associated with a VF */
 	u32 tx_pq_vf_mask[MAX_QM_TX_QUEUES / QM_PF_QUEUE_GROUP_SIZE] = { 0 };
-	u32 tx_pq_vf_mask_width = is_bb_a0 ? 32 : QM_PF_QUEUE_GROUP_SIZE;
-	u32 num_tx_pq_vf_masks = MAX_QM_TX_QUEUES / tx_pq_vf_mask_width;
+	u32 num_tx_pq_vf_masks = MAX_QM_TX_QUEUES / QM_PF_QUEUE_GROUP_SIZE;
 	u32 pq_mem_4kb = QM_PQ_MEM_4KB(p_params->num_pf_cids);
 	u32 vport_pq_mem_4kb = QM_PQ_MEM_4KB(p_params->num_vf_cids);
 	u32 mem_addr_4kb = base_mem_addr_4kb;
@@ -371,6 +362,10 @@ static void qed_tx_pq_map_rt_init(
 		bool is_vf_pq = (i >= p_params->num_pf_pqs);
 		struct qm_rf_pq_map tx_pq_map;
 
+		bool rl_valid = p_params->pq_params[i].rl_valid &&
+				(p_params->pq_params[i].vport_id <
+				 MAX_QM_GLOBAL_RLS);
+
 		/* update first Tx PQ of VPORT/TC */
 		u8 vport_id_in_pf = p_params->pq_params[i].vport_id -
 				    p_params->start_vport;
@@ -389,14 +384,18 @@ static void qed_tx_pq_map_rt_init(
 				     (p_params->pf_id <<
 				      QM_WFQ_VP_PQ_PF_SHIFT));
 		}
+
+		if (p_params->pq_params[i].rl_valid && !rl_valid)
+			DP_NOTICE(p_hwfn,
+				  "Invalid VPORT ID for rate limiter configuration");
 		/* fill PQ map entry */
 		memset(&tx_pq_map, 0, sizeof(tx_pq_map));
 		SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_PQ_VALID, 1);
-		SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_RL_VALID,
-			  p_params->pq_params[i].rl_valid ? 1 : 0);
+		SET_FIELD(tx_pq_map.reg,
+			  QM_RF_PQ_MAP_RL_VALID, rl_valid ? 1 : 0);
 		SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_VP_PQ_ID, first_tx_pq_id);
 		SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_RL_ID,
-			  p_params->pq_params[i].rl_valid ?
+			  rl_valid ?
 			  p_params->pq_params[i].vport_id : 0);
 		SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_VOQ, voq);
 		SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_WRR_WEIGHT_GROUP,
@@ -413,8 +412,9 @@ static void qed_tx_pq_map_rt_init(
 			/* if PQ is associated with a VF, add indication
 			 * to PQ VF mask
 			 */
-			tx_pq_vf_mask[pq_id / tx_pq_vf_mask_width] |=
-				(1 << (pq_id % tx_pq_vf_mask_width));
+			tx_pq_vf_mask[pq_id /
+				      QM_PF_QUEUE_GROUP_SIZE] |=
+			    BIT((pq_id % QM_PF_QUEUE_GROUP_SIZE));
 			mem_addr_4kb += vport_pq_mem_4kb;
 		} else {
 			mem_addr_4kb += pq_mem_4kb;
@@ -480,8 +480,8 @@ static int qed_pf_wfq_rt_init(struct qed_hwfn *p_hwfn,
 	if (p_params->pf_id < MAX_NUM_PFS_BB)
 		crd_reg_offset = QM_REG_WFQPFCRD_RT_OFFSET;
 	else
-		crd_reg_offset = QM_REG_WFQPFCRD_MSB_RT_OFFSET +
-				 (p_params->pf_id % MAX_NUM_PFS_BB);
+		crd_reg_offset = QM_REG_WFQPFCRD_MSB_RT_OFFSET;
+	crd_reg_offset += p_params->pf_id % MAX_NUM_PFS_BB;
 
 	inc_val = QM_WFQ_INC_VAL(p_params->pf_wfq);
 	if (!inc_val || inc_val > QM_WFQ_MAX_INC_VAL) {
@@ -498,11 +498,11 @@ static int qed_pf_wfq_rt_init(struct qed_hwfn *p_hwfn,
 				 QM_WFQ_CRD_REG_SIGN_BIT);
 	}
 
-	STORE_RT_REG(p_hwfn, QM_REG_WFQPFWEIGHT_RT_OFFSET + p_params->pf_id,
-		     inc_val);
 	STORE_RT_REG(p_hwfn,
 		     QM_REG_WFQPFUPPERBOUND_RT_OFFSET + p_params->pf_id,
 		     QM_WFQ_UPPER_BOUND | QM_WFQ_CRD_REG_SIGN_BIT);
+	STORE_RT_REG(p_hwfn, QM_REG_WFQPFWEIGHT_RT_OFFSET + p_params->pf_id,
+		     inc_val);
 	return 0;
 }
 
@@ -576,6 +576,12 @@ static int qed_vport_rl_rt_init(struct qed_hwfn *p_hwfn,
 {
 	u8 i, vport_id;
 
+	if (start_vport + num_vports >= MAX_QM_GLOBAL_RLS) {
+		DP_NOTICE(p_hwfn,
+			  "Invalid VPORT ID for rate limiter configuration");
+		return -1;
+	}
+
 	/* go over all PF VPORTs */
 	for (i = 0, vport_id = start_vport; i < num_vports; i++, vport_id++) {
 		u32 inc_val = QM_RL_INC_VAL(vport_params[i].vport_rl);
@@ -785,6 +791,12 @@ int qed_init_vport_rl(struct qed_hwfn *p_hwfn,
 {
 	u32 inc_val = QM_RL_INC_VAL(vport_rl);
 
+	if (vport_id >= MAX_QM_GLOBAL_RLS) {
+		DP_NOTICE(p_hwfn,
+			  "Invalid VPORT ID for rate limiter configuration");
+		return -1;
+	}
+
 	if (inc_val > QM_RL_MAX_INC_VAL) {
 		DP_NOTICE(p_hwfn, "Invalid VPORT rate-limit configuration");
 		return -1;
@@ -940,12 +952,6 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn,
 	       eth_geneve_enable ? 1 : 0);
 	qed_wr(p_hwfn, p_ptt, NIG_REG_NGE_IP_ENABLE, ip_geneve_enable ? 1 : 0);
 
-	/* comp ver */
-	reg_val = (ip_geneve_enable || eth_geneve_enable) ? 1 : 0;
-	qed_wr(p_hwfn, p_ptt, NIG_REG_NGE_COMP_VER, reg_val);
-	qed_wr(p_hwfn, p_ptt, PBF_REG_NGE_COMP_VER, reg_val);
-	qed_wr(p_hwfn, p_ptt, PRS_REG_NGE_COMP_VER, reg_val);
-
 	/* EDPM with geneve tunnel not supported in BB_B0 */
 	if (QED_IS_BB_B0(p_hwfn->cdev))
 		return;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
index 243b64e0d4dc..4a2e7be5bf72 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
@@ -554,7 +554,7 @@ int qed_init_fw_data(struct qed_dev *cdev, const u8 *data)
 	}
 
 	/* First Dword contains metadata and should be skipped */
-	buf_hdr = (struct bin_buffer_hdr *)(data + sizeof(u32));
+	buf_hdr = (struct bin_buffer_hdr *)data;
 
 	offset = buf_hdr[BIN_BUF_INIT_FW_VER_INFO].offset;
 	fw->fw_ver_info = (struct fw_ver_info *)(data + offset);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index 84310b60849b..0ed24d6e6c65 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -2500,8 +2500,9 @@ void qed_int_cau_conf_sb(struct qed_hwfn *p_hwfn,
 
 	/* Configure pi coalescing if set */
 	if (p_hwfn->cdev->int_coalescing_mode == QED_COAL_MODE_ENABLE) {
+		u8 num_tc = p_hwfn->hw_info.num_hw_tc;
 		u8 timeset, timer_res;
-		u8 num_tc = 1, i;
+		u8 i;
 
 		/* timeset = (coalesce >> timer-res), timeset is 7bit wide */
 		if (p_hwfn->cdev->rx_coalesce_usecs <= 0x7F)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
index 098766f7fe88..112b96fba433 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
@@ -216,7 +216,7 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn,
 		p_queue->cq_cmdq_sb_num_arr[i] = cpu_to_le16(val);
 	}
 
-	p_queue->bdq_resource_id = ISCSI_BDQ_ID(p_hwfn->port_id);
+	p_queue->bdq_resource_id = (u8)RESC_START(p_hwfn, QED_BDQ);
 
 	DMA_REGPAIR_LE(p_queue->bdq_pbl_base_address[BDQ_ID_RQ],
 		       p_params->bdq_pbl_base_addr[BDQ_ID_RQ]);
@@ -270,11 +270,10 @@ static int qed_sp_iscsi_conn_offload(struct qed_hwfn *p_hwfn,
 	struct tcp_offload_params *p_tcp = NULL;
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
-	union qed_qm_pq_params pq_params;
-	u16 pq0_id = 0, pq1_id = 0;
 	dma_addr_t r2tq_pbl_addr;
 	dma_addr_t xhq_pbl_addr;
 	dma_addr_t uhq_pbl_addr;
+	u16 physical_q;
 	int rc = 0;
 	u32 dval;
 	u16 wval;
@@ -297,16 +296,14 @@ static int qed_sp_iscsi_conn_offload(struct qed_hwfn *p_hwfn,
 	p_ramrod = &p_ent->ramrod.iscsi_conn_offload;
 
 	/* Transmission PQ is the first of the PF */
-	memset(&pq_params, 0, sizeof(pq_params));
-	pq0_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_ISCSI, &pq_params);
-	p_conn->physical_q0 = cpu_to_le16(pq0_id);
-	p_ramrod->iscsi.physical_q0 = cpu_to_le16(pq0_id);
+	physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+	p_conn->physical_q0 = cpu_to_le16(physical_q);
+	p_ramrod->iscsi.physical_q0 = cpu_to_le16(physical_q);
 
 	/* iSCSI Pure-ACK PQ */
-	pq_params.iscsi.q_idx = 1;
-	pq1_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_ISCSI, &pq_params);
-	p_conn->physical_q1 = cpu_to_le16(pq1_id);
-	p_ramrod->iscsi.physical_q1 = cpu_to_le16(pq1_id);
+	physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_ACK);
+	p_conn->physical_q1 = cpu_to_le16(physical_q);
+	p_ramrod->iscsi.physical_q1 = cpu_to_le16(physical_q);
 
 	p_ramrod->hdr.op_code = ISCSI_RAMROD_CMD_ID_OFFLOAD_CONN;
 	SET_FIELD(p_ramrod->hdr.flags, ISCSI_SLOW_PATH_HDR_LAYER_CODE,
@@ -593,21 +590,31 @@ static void __iomem *qed_iscsi_get_db_addr(struct qed_hwfn *p_hwfn, u32 cid)
 static void __iomem *qed_iscsi_get_primary_bdq_prod(struct qed_hwfn *p_hwfn,
 						    u8 bdq_id)
 {
-	u8 bdq_function_id = ISCSI_BDQ_ID(p_hwfn->port_id);
-
-	return (u8 __iomem *)p_hwfn->regview + GTT_BAR0_MAP_REG_MSDM_RAM +
-			     MSTORM_SCSI_BDQ_EXT_PROD_OFFSET(bdq_function_id,
-							     bdq_id);
+	if (RESC_NUM(p_hwfn, QED_BDQ)) {
+		return (u8 __iomem *)p_hwfn->regview +
+		       GTT_BAR0_MAP_REG_MSDM_RAM +
+		       MSTORM_SCSI_BDQ_EXT_PROD_OFFSET(RESC_START(p_hwfn,
+								  QED_BDQ),
+						       bdq_id);
+	} else {
+		DP_NOTICE(p_hwfn, "BDQ is not allocated!\n");
+		return NULL;
+	}
 }
 
 static void __iomem *qed_iscsi_get_secondary_bdq_prod(struct qed_hwfn *p_hwfn,
 						      u8 bdq_id)
 {
-	u8 bdq_function_id = ISCSI_BDQ_ID(p_hwfn->port_id);
-
-	return (u8 __iomem *)p_hwfn->regview + GTT_BAR0_MAP_REG_TSDM_RAM +
-			     TSTORM_SCSI_BDQ_EXT_PROD_OFFSET(bdq_function_id,
-							     bdq_id);
+	if (RESC_NUM(p_hwfn, QED_BDQ)) {
+		return (u8 __iomem *)p_hwfn->regview +
+		       GTT_BAR0_MAP_REG_TSDM_RAM +
+		       TSTORM_SCSI_BDQ_EXT_PROD_OFFSET(RESC_START(p_hwfn,
+								  QED_BDQ),
+						       bdq_id);
+	} else {
+		DP_NOTICE(p_hwfn, "BDQ is not allocated!\n");
+		return NULL;
+	}
 }
 
 static int qed_iscsi_setup_connection(struct qed_hwfn *p_hwfn,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index df932be5a4e5..9900f7a1f9f1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -938,15 +938,12 @@ qed_eth_pf_tx_queue_start(struct qed_hwfn *p_hwfn,
 			  dma_addr_t pbl_addr,
 			  u16 pbl_size, void __iomem **pp_doorbell)
 {
-	union qed_qm_pq_params pq_params;
 	int rc;
 
-	memset(&pq_params, 0, sizeof(pq_params));
 
 	rc = qed_eth_txq_start_ramrod(p_hwfn, p_cid,
 				      pbl_addr, pbl_size,
-				      qed_get_qm_pq(p_hwfn, PROTOCOLID_ETH,
-						    &pq_params));
+				      qed_get_cm_pq_idx_mcos(p_hwfn, tc));
 	if (rc)
 		return rc;
 
@@ -1470,13 +1467,20 @@ static void __qed_get_vport_pstats(struct qed_hwfn *p_hwfn,
 	memset(&pstats, 0, sizeof(pstats));
 	qed_memcpy_from(p_hwfn, p_ptt, &pstats, pstats_addr, pstats_len);
 
-	p_stats->tx_ucast_bytes += HILO_64_REGPAIR(pstats.sent_ucast_bytes);
-	p_stats->tx_mcast_bytes += HILO_64_REGPAIR(pstats.sent_mcast_bytes);
-	p_stats->tx_bcast_bytes += HILO_64_REGPAIR(pstats.sent_bcast_bytes);
-	p_stats->tx_ucast_pkts += HILO_64_REGPAIR(pstats.sent_ucast_pkts);
-	p_stats->tx_mcast_pkts += HILO_64_REGPAIR(pstats.sent_mcast_pkts);
-	p_stats->tx_bcast_pkts += HILO_64_REGPAIR(pstats.sent_bcast_pkts);
-	p_stats->tx_err_drop_pkts += HILO_64_REGPAIR(pstats.error_drop_pkts);
+	p_stats->common.tx_ucast_bytes +=
+	    HILO_64_REGPAIR(pstats.sent_ucast_bytes);
+	p_stats->common.tx_mcast_bytes +=
+	    HILO_64_REGPAIR(pstats.sent_mcast_bytes);
+	p_stats->common.tx_bcast_bytes +=
+	    HILO_64_REGPAIR(pstats.sent_bcast_bytes);
+	p_stats->common.tx_ucast_pkts +=
+	    HILO_64_REGPAIR(pstats.sent_ucast_pkts);
+	p_stats->common.tx_mcast_pkts +=
+	    HILO_64_REGPAIR(pstats.sent_mcast_pkts);
+	p_stats->common.tx_bcast_pkts +=
+	    HILO_64_REGPAIR(pstats.sent_bcast_pkts);
+	p_stats->common.tx_err_drop_pkts +=
+	    HILO_64_REGPAIR(pstats.error_drop_pkts);
 }
 
 static void __qed_get_vport_tstats(struct qed_hwfn *p_hwfn,
@@ -1502,10 +1506,10 @@ static void __qed_get_vport_tstats(struct qed_hwfn *p_hwfn,
 	memset(&tstats, 0, sizeof(tstats));
 	qed_memcpy_from(p_hwfn, p_ptt, &tstats, tstats_addr, tstats_len);
 
-	p_stats->mftag_filter_discards +=
-		HILO_64_REGPAIR(tstats.mftag_filter_discard);
-	p_stats->mac_filter_discards +=
-		HILO_64_REGPAIR(tstats.eth_mac_filter_discard);
+	p_stats->common.mftag_filter_discards +=
+	    HILO_64_REGPAIR(tstats.mftag_filter_discard);
+	p_stats->common.mac_filter_discards +=
+	    HILO_64_REGPAIR(tstats.eth_mac_filter_discard);
 }
 
 static void __qed_get_vport_ustats_addrlen(struct qed_hwfn *p_hwfn,
@@ -1539,12 +1543,15 @@ static void __qed_get_vport_ustats(struct qed_hwfn *p_hwfn,
 	memset(&ustats, 0, sizeof(ustats));
 	qed_memcpy_from(p_hwfn, p_ptt, &ustats, ustats_addr, ustats_len);
 
-	p_stats->rx_ucast_bytes += HILO_64_REGPAIR(ustats.rcv_ucast_bytes);
-	p_stats->rx_mcast_bytes += HILO_64_REGPAIR(ustats.rcv_mcast_bytes);
-	p_stats->rx_bcast_bytes += HILO_64_REGPAIR(ustats.rcv_bcast_bytes);
-	p_stats->rx_ucast_pkts += HILO_64_REGPAIR(ustats.rcv_ucast_pkts);
-	p_stats->rx_mcast_pkts += HILO_64_REGPAIR(ustats.rcv_mcast_pkts);
-	p_stats->rx_bcast_pkts += HILO_64_REGPAIR(ustats.rcv_bcast_pkts);
+	p_stats->common.rx_ucast_bytes +=
+	    HILO_64_REGPAIR(ustats.rcv_ucast_bytes);
+	p_stats->common.rx_mcast_bytes +=
+	    HILO_64_REGPAIR(ustats.rcv_mcast_bytes);
+	p_stats->common.rx_bcast_bytes +=
+	    HILO_64_REGPAIR(ustats.rcv_bcast_bytes);
+	p_stats->common.rx_ucast_pkts += HILO_64_REGPAIR(ustats.rcv_ucast_pkts);
+	p_stats->common.rx_mcast_pkts += HILO_64_REGPAIR(ustats.rcv_mcast_pkts);
+	p_stats->common.rx_bcast_pkts += HILO_64_REGPAIR(ustats.rcv_bcast_pkts);
 }
 
 static void __qed_get_vport_mstats_addrlen(struct qed_hwfn *p_hwfn,
@@ -1578,23 +1585,26 @@ static void __qed_get_vport_mstats(struct qed_hwfn *p_hwfn,
 	memset(&mstats, 0, sizeof(mstats));
 	qed_memcpy_from(p_hwfn, p_ptt, &mstats, mstats_addr, mstats_len);
 
-	p_stats->no_buff_discards += HILO_64_REGPAIR(mstats.no_buff_discard);
-	p_stats->packet_too_big_discard +=
-		HILO_64_REGPAIR(mstats.packet_too_big_discard);
-	p_stats->ttl0_discard += HILO_64_REGPAIR(mstats.ttl0_discard);
-	p_stats->tpa_coalesced_pkts +=
-		HILO_64_REGPAIR(mstats.tpa_coalesced_pkts);
-	p_stats->tpa_coalesced_events +=
-		HILO_64_REGPAIR(mstats.tpa_coalesced_events);
-	p_stats->tpa_aborts_num += HILO_64_REGPAIR(mstats.tpa_aborts_num);
-	p_stats->tpa_coalesced_bytes +=
-		HILO_64_REGPAIR(mstats.tpa_coalesced_bytes);
+	p_stats->common.no_buff_discards +=
+	    HILO_64_REGPAIR(mstats.no_buff_discard);
+	p_stats->common.packet_too_big_discard +=
+	    HILO_64_REGPAIR(mstats.packet_too_big_discard);
+	p_stats->common.ttl0_discard += HILO_64_REGPAIR(mstats.ttl0_discard);
+	p_stats->common.tpa_coalesced_pkts +=
+	    HILO_64_REGPAIR(mstats.tpa_coalesced_pkts);
+	p_stats->common.tpa_coalesced_events +=
+	    HILO_64_REGPAIR(mstats.tpa_coalesced_events);
+	p_stats->common.tpa_aborts_num +=
+	    HILO_64_REGPAIR(mstats.tpa_aborts_num);
+	p_stats->common.tpa_coalesced_bytes +=
+	    HILO_64_REGPAIR(mstats.tpa_coalesced_bytes);
 }
 
 static void __qed_get_vport_port_stats(struct qed_hwfn *p_hwfn,
 				       struct qed_ptt *p_ptt,
 				       struct qed_eth_stats *p_stats)
 {
+	struct qed_eth_stats_common *p_common = &p_stats->common;
 	struct port_stats port_stats;
 	int j;
 
@@ -1605,54 +1615,75 @@ static void __qed_get_vport_port_stats(struct qed_hwfn *p_hwfn,
 			offsetof(struct public_port, stats),
 			sizeof(port_stats));
 
-	p_stats->rx_64_byte_packets		+= port_stats.eth.r64;
-	p_stats->rx_65_to_127_byte_packets	+= port_stats.eth.r127;
-	p_stats->rx_128_to_255_byte_packets	+= port_stats.eth.r255;
-	p_stats->rx_256_to_511_byte_packets	+= port_stats.eth.r511;
-	p_stats->rx_512_to_1023_byte_packets	+= port_stats.eth.r1023;
-	p_stats->rx_1024_to_1518_byte_packets	+= port_stats.eth.r1518;
-	p_stats->rx_1519_to_1522_byte_packets	+= port_stats.eth.r1522;
-	p_stats->rx_1519_to_2047_byte_packets	+= port_stats.eth.r2047;
-	p_stats->rx_2048_to_4095_byte_packets	+= port_stats.eth.r4095;
-	p_stats->rx_4096_to_9216_byte_packets	+= port_stats.eth.r9216;
-	p_stats->rx_9217_to_16383_byte_packets	+= port_stats.eth.r16383;
-	p_stats->rx_crc_errors			+= port_stats.eth.rfcs;
-	p_stats->rx_mac_crtl_frames		+= port_stats.eth.rxcf;
-	p_stats->rx_pause_frames		+= port_stats.eth.rxpf;
-	p_stats->rx_pfc_frames			+= port_stats.eth.rxpp;
-	p_stats->rx_align_errors		+= port_stats.eth.raln;
-	p_stats->rx_carrier_errors		+= port_stats.eth.rfcr;
-	p_stats->rx_oversize_packets		+= port_stats.eth.rovr;
-	p_stats->rx_jabbers			+= port_stats.eth.rjbr;
-	p_stats->rx_undersize_packets		+= port_stats.eth.rund;
-	p_stats->rx_fragments			+= port_stats.eth.rfrg;
-	p_stats->tx_64_byte_packets		+= port_stats.eth.t64;
-	p_stats->tx_65_to_127_byte_packets	+= port_stats.eth.t127;
-	p_stats->tx_128_to_255_byte_packets	+= port_stats.eth.t255;
-	p_stats->tx_256_to_511_byte_packets	+= port_stats.eth.t511;
-	p_stats->tx_512_to_1023_byte_packets	+= port_stats.eth.t1023;
-	p_stats->tx_1024_to_1518_byte_packets	+= port_stats.eth.t1518;
-	p_stats->tx_1519_to_2047_byte_packets	+= port_stats.eth.t2047;
-	p_stats->tx_2048_to_4095_byte_packets	+= port_stats.eth.t4095;
-	p_stats->tx_4096_to_9216_byte_packets	+= port_stats.eth.t9216;
-	p_stats->tx_9217_to_16383_byte_packets	+= port_stats.eth.t16383;
-	p_stats->tx_pause_frames		+= port_stats.eth.txpf;
-	p_stats->tx_pfc_frames			+= port_stats.eth.txpp;
-	p_stats->tx_lpi_entry_count		+= port_stats.eth.tlpiec;
-	p_stats->tx_total_collisions		+= port_stats.eth.tncl;
-	p_stats->rx_mac_bytes			+= port_stats.eth.rbyte;
-	p_stats->rx_mac_uc_packets		+= port_stats.eth.rxuca;
-	p_stats->rx_mac_mc_packets		+= port_stats.eth.rxmca;
-	p_stats->rx_mac_bc_packets		+= port_stats.eth.rxbca;
-	p_stats->rx_mac_frames_ok		+= port_stats.eth.rxpok;
-	p_stats->tx_mac_bytes			+= port_stats.eth.tbyte;
-	p_stats->tx_mac_uc_packets		+= port_stats.eth.txuca;
-	p_stats->tx_mac_mc_packets		+= port_stats.eth.txmca;
-	p_stats->tx_mac_bc_packets		+= port_stats.eth.txbca;
-	p_stats->tx_mac_ctrl_frames		+= port_stats.eth.txcf;
+	p_common->rx_64_byte_packets += port_stats.eth.r64;
+	p_common->rx_65_to_127_byte_packets += port_stats.eth.r127;
+	p_common->rx_128_to_255_byte_packets += port_stats.eth.r255;
+	p_common->rx_256_to_511_byte_packets += port_stats.eth.r511;
+	p_common->rx_512_to_1023_byte_packets += port_stats.eth.r1023;
+	p_common->rx_1024_to_1518_byte_packets += port_stats.eth.r1518;
+	p_common->rx_crc_errors += port_stats.eth.rfcs;
+	p_common->rx_mac_crtl_frames += port_stats.eth.rxcf;
+	p_common->rx_pause_frames += port_stats.eth.rxpf;
+	p_common->rx_pfc_frames += port_stats.eth.rxpp;
+	p_common->rx_align_errors += port_stats.eth.raln;
+	p_common->rx_carrier_errors += port_stats.eth.rfcr;
+	p_common->rx_oversize_packets += port_stats.eth.rovr;
+	p_common->rx_jabbers += port_stats.eth.rjbr;
+	p_common->rx_undersize_packets += port_stats.eth.rund;
+	p_common->rx_fragments += port_stats.eth.rfrg;
+	p_common->tx_64_byte_packets += port_stats.eth.t64;
+	p_common->tx_65_to_127_byte_packets += port_stats.eth.t127;
+	p_common->tx_128_to_255_byte_packets += port_stats.eth.t255;
+	p_common->tx_256_to_511_byte_packets += port_stats.eth.t511;
+	p_common->tx_512_to_1023_byte_packets += port_stats.eth.t1023;
+	p_common->tx_1024_to_1518_byte_packets += port_stats.eth.t1518;
+	p_common->tx_pause_frames += port_stats.eth.txpf;
+	p_common->tx_pfc_frames += port_stats.eth.txpp;
+	p_common->rx_mac_bytes += port_stats.eth.rbyte;
+	p_common->rx_mac_uc_packets += port_stats.eth.rxuca;
+	p_common->rx_mac_mc_packets += port_stats.eth.rxmca;
+	p_common->rx_mac_bc_packets += port_stats.eth.rxbca;
+	p_common->rx_mac_frames_ok += port_stats.eth.rxpok;
+	p_common->tx_mac_bytes += port_stats.eth.tbyte;
+	p_common->tx_mac_uc_packets += port_stats.eth.txuca;
+	p_common->tx_mac_mc_packets += port_stats.eth.txmca;
+	p_common->tx_mac_bc_packets += port_stats.eth.txbca;
+	p_common->tx_mac_ctrl_frames += port_stats.eth.txcf;
 	for (j = 0; j < 8; j++) {
-		p_stats->brb_truncates	+= port_stats.brb.brb_truncate[j];
-		p_stats->brb_discards	+= port_stats.brb.brb_discard[j];
+		p_common->brb_truncates += port_stats.brb.brb_truncate[j];
+		p_common->brb_discards += port_stats.brb.brb_discard[j];
+	}
+
+	if (QED_IS_BB(p_hwfn->cdev)) {
+		struct qed_eth_stats_bb *p_bb = &p_stats->bb;
+
+		p_bb->rx_1519_to_1522_byte_packets +=
+		    port_stats.eth.u0.bb0.r1522;
+		p_bb->rx_1519_to_2047_byte_packets +=
+		    port_stats.eth.u0.bb0.r2047;
+		p_bb->rx_2048_to_4095_byte_packets +=
+		    port_stats.eth.u0.bb0.r4095;
+		p_bb->rx_4096_to_9216_byte_packets +=
+		    port_stats.eth.u0.bb0.r9216;
+		p_bb->rx_9217_to_16383_byte_packets +=
+		    port_stats.eth.u0.bb0.r16383;
+		p_bb->tx_1519_to_2047_byte_packets +=
+		    port_stats.eth.u1.bb1.t2047;
+		p_bb->tx_2048_to_4095_byte_packets +=
+		    port_stats.eth.u1.bb1.t4095;
+		p_bb->tx_4096_to_9216_byte_packets +=
+		    port_stats.eth.u1.bb1.t9216;
+		p_bb->tx_9217_to_16383_byte_packets +=
+		    port_stats.eth.u1.bb1.t16383;
+		p_bb->tx_lpi_entry_count += port_stats.eth.u2.bb2.tlpiec;
+		p_bb->tx_total_collisions += port_stats.eth.u2.bb2.tncl;
+	} else {
+		struct qed_eth_stats_ah *p_ah = &p_stats->ah;
+
+		p_ah->rx_1519_to_max_byte_packets +=
+		    port_stats.eth.u0.ah0.r1519_to_max;
+		p_ah->tx_1519_to_max_byte_packets =
+		    port_stats.eth.u1.ah1.t1519_to_max;
 	}
 }
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 0d3cef409c96..708c601e8ccf 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -597,7 +597,7 @@ static u8 qed_ll2_convert_rx_parse_to_tx_flags(u16 parse_flags)
 	u8 bd_flags = 0;
 
 	if (GET_FIELD(parse_flags, PARSING_AND_ERR_FLAGS_TAG8021QEXIST))
-		SET_FIELD(bd_flags, CORE_TX_BD_FLAGS_VLAN_INSERTION, 1);
+		SET_FIELD(bd_flags, CORE_TX_BD_DATA_VLAN_INSERTION, 1);
 
 	return bd_flags;
 }
@@ -758,8 +758,8 @@ qed_ooo_submit_tx_buffers(struct qed_hwfn *p_hwfn,
 			     p_buffer->placement_offset;
 		parse_flags = p_buffer->parse_flags;
 		bd_flags = qed_ll2_convert_rx_parse_to_tx_flags(parse_flags);
-		SET_FIELD(bd_flags, CORE_TX_BD_FLAGS_FORCE_VLAN_MODE, 1);
-		SET_FIELD(bd_flags, CORE_TX_BD_FLAGS_L4_PROTOCOL, 1);
+		SET_FIELD(bd_flags, CORE_TX_BD_DATA_FORCE_VLAN_MODE, 1);
+		SET_FIELD(bd_flags, CORE_TX_BD_DATA_L4_PROTOCOL, 1);
 
 		rc = qed_ll2_prepare_tx_packet(p_hwfn, p_ll2_conn->my_id, 1,
 					       p_buffer->vlan, bd_flags,
@@ -1090,7 +1090,6 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn,
 	struct core_tx_start_ramrod_data *p_ramrod = NULL;
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
-	union qed_qm_pq_params pq_params;
 	u16 pq_id = 0, pbl_size;
 	int rc = -EINVAL;
 
@@ -1127,9 +1126,17 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn,
 	pbl_size = qed_chain_get_page_cnt(&p_tx->txq_chain);
 	p_ramrod->pbl_size = cpu_to_le16(pbl_size);
 
-	memset(&pq_params, 0, sizeof(pq_params));
-	pq_params.core.tc = p_ll2_conn->conn.tx_tc;
-	pq_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_CORE, &pq_params);
+	switch (p_ll2_conn->conn.tx_tc) {
+	case LB_TC:
+		pq_id = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LB);
+		break;
+	case OOO_LB_TC:
+		pq_id = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OOO);
+	default:
+		pq_id = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+		break;
+	}
+
 	p_ramrod->qm_pq_id = cpu_to_le16(pq_id);
 
 	switch (conn_type) {
@@ -1591,33 +1598,34 @@ static void qed_ll2_prepare_tx_packet_set(struct qed_hwfn *p_hwfn,
 	p_tx->cur_send_frag_num++;
 }
 
-static void qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn,
-					     struct qed_ll2_info *p_ll2,
-					     struct qed_ll2_tx_packet *p_curp,
-					     u8 num_of_bds,
-					     enum core_tx_dest tx_dest,
-					     u16 vlan,
-					     u8 bd_flags,
-					     u16 l4_hdr_offset_w,
-					     enum core_roce_flavor_type type,
-					     dma_addr_t first_frag,
-					     u16 first_frag_len)
+static void
+qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn,
+				 struct qed_ll2_info *p_ll2,
+				 struct qed_ll2_tx_packet *p_curp,
+				 u8 num_of_bds,
+				 enum core_tx_dest tx_dest,
+				 u16 vlan,
+				 u8 bd_flags,
+				 u16 l4_hdr_offset_w,
+				 enum core_roce_flavor_type roce_flavor,
+				 dma_addr_t first_frag,
+				 u16 first_frag_len)
 {
 	struct qed_chain *p_tx_chain = &p_ll2->tx_queue.txq_chain;
 	u16 prod_idx = qed_chain_get_prod_idx(p_tx_chain);
 	struct core_tx_bd *start_bd = NULL;
-	u16 frag_idx;
+	u16 bd_data = 0, frag_idx;
 
 	start_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain);
 	start_bd->nw_vlan_or_lb_echo = cpu_to_le16(vlan);
 	SET_FIELD(start_bd->bitfield1, CORE_TX_BD_L4_HDR_OFFSET_W,
 		  cpu_to_le16(l4_hdr_offset_w));
 	SET_FIELD(start_bd->bitfield1, CORE_TX_BD_TX_DST, tx_dest);
-	start_bd->bd_flags.as_bitfield = bd_flags;
-	start_bd->bd_flags.as_bitfield |= CORE_TX_BD_FLAGS_START_BD_MASK <<
-	    CORE_TX_BD_FLAGS_START_BD_SHIFT;
-	SET_FIELD(start_bd->bitfield0, CORE_TX_BD_NBDS, num_of_bds);
-	SET_FIELD(start_bd->bitfield0, CORE_TX_BD_ROCE_FLAV, type);
+	bd_data |= bd_flags;
+	SET_FIELD(bd_data, CORE_TX_BD_DATA_START_BD, 0x1);
+	SET_FIELD(bd_data, CORE_TX_BD_DATA_NBDS, num_of_bds);
+	SET_FIELD(bd_data, CORE_TX_BD_DATA_ROCE_FLAV, roce_flavor);
+	start_bd->bd_data.as_bitfield = cpu_to_le16(bd_data);
 	DMA_REGPAIR_LE(start_bd->addr, first_frag);
 	start_bd->nbytes = cpu_to_le16(first_frag_len);
 
@@ -1642,9 +1650,8 @@ static void qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn,
 		struct core_tx_bd **p_bd = &p_curp->bds_set[frag_idx].txq_bd;
 
 		*p_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain);
-		(*p_bd)->bd_flags.as_bitfield = 0;
+		(*p_bd)->bd_data.as_bitfield = 0;
 		(*p_bd)->bitfield1 = 0;
-		(*p_bd)->bitfield0 = 0;
 		p_curp->bds_set[frag_idx].tx_frag = 0;
 		p_curp->bds_set[frag_idx].frag_len = 0;
 	}
@@ -2241,11 +2248,11 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb)
 	/* Request HW to calculate IP csum */
 	if (!((vlan_get_protocol(skb) == htons(ETH_P_IPV6)) &&
 	      ipv6_hdr(skb)->nexthdr == NEXTHDR_IPV6))
-		flags |= BIT(CORE_TX_BD_FLAGS_IP_CSUM_SHIFT);
+		flags |= BIT(CORE_TX_BD_DATA_IP_CSUM_SHIFT);
 
 	if (skb_vlan_tag_present(skb)) {
 		vlan = skb_vlan_tag_get(skb);
-		flags |= BIT(CORE_TX_BD_FLAGS_VLAN_INSERTION_SHIFT);
+		flags |= BIT(CORE_TX_BD_DATA_VLAN_INSERTION_SHIFT);
 	}
 
 	rc = qed_ll2_prepare_tx_packet(QED_LEADING_HWFN(cdev),
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index eef30a598b40..634e7a2433a9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -45,6 +45,7 @@
 #include <linux/ethtool.h>
 #include <linux/etherdevice.h>
 #include <linux/vmalloc.h>
+#include <linux/crash_dump.h>
 #include <linux/qed/qed_if.h>
 #include <linux/qed/qed_ll2_if.h>
 
@@ -238,6 +239,7 @@ int qed_fill_dev_info(struct qed_dev *cdev,
 	dev_info->rdma_supported = (cdev->hwfns[0].hw_info.personality ==
 				    QED_PCI_ETH_ROCE);
 	dev_info->is_mf_default = IS_MF_DEFAULT(&cdev->hwfns[0]);
+	dev_info->dev_type = cdev->type;
 	ether_addr_copy(dev_info->hw_mac, cdev->hwfns[0].hw_info.hw_mac_addr);
 
 	if (IS_PF(cdev)) {
@@ -588,6 +590,19 @@ int qed_slowpath_irq_req(struct qed_hwfn *hwfn)
 	return rc;
 }
 
+void qed_slowpath_irq_sync(struct qed_hwfn *p_hwfn)
+{
+	struct qed_dev *cdev = p_hwfn->cdev;
+	u8 id = p_hwfn->my_id;
+	u32 int_mode;
+
+	int_mode = cdev->int_params.out.int_mode;
+	if (int_mode == QED_INT_MODE_MSIX)
+		synchronize_irq(cdev->int_params.msix_table[id].vector);
+	else
+		synchronize_irq(cdev->pdev->irq);
+}
+
 static void qed_slowpath_irq_free(struct qed_dev *cdev)
 {
 	int i;
@@ -630,19 +645,6 @@ static int qed_nic_stop(struct qed_dev *cdev)
 	return rc;
 }
 
-static int qed_nic_reset(struct qed_dev *cdev)
-{
-	int rc;
-
-	rc = qed_hw_reset(cdev);
-	if (rc)
-		return rc;
-
-	qed_resc_free(cdev);
-
-	return 0;
-}
-
 static int qed_nic_setup(struct qed_dev *cdev)
 {
 	int rc, i;
@@ -875,7 +877,6 @@ static void qed_update_pf_params(struct qed_dev *cdev,
 		params->rdma_pf_params.num_qps = QED_ROCE_QPS;
 		params->rdma_pf_params.min_dpis = QED_ROCE_DPIS;
 		/* divide by 3 the MRs to avoid MF ILT overflow */
-		params->rdma_pf_params.num_mrs = RDMA_MAX_TIDS;
 		params->rdma_pf_params.gl_pi = QED_ROCE_PROTOCOL_INDEX;
 	}
 
@@ -900,6 +901,8 @@ static void qed_update_pf_params(struct qed_dev *cdev,
 static int qed_slowpath_start(struct qed_dev *cdev,
 			      struct qed_slowpath_params *params)
 {
+	struct qed_drv_load_params drv_load_params;
+	struct qed_hw_init_params hw_init_params;
 	struct qed_tunn_start_params tunn_info;
 	struct qed_mcp_drv_version drv_version;
 	const u8 *data = NULL;
@@ -965,9 +968,21 @@ static int qed_slowpath_start(struct qed_dev *cdev,
 	tunn_info.tunn_clss_ipgre = QED_TUNN_CLSS_MAC_VLAN;
 
 	/* Start the slowpath */
-	rc = qed_hw_init(cdev, &tunn_info, true,
-			 cdev->int_params.out.int_mode,
-			 true, data);
+	memset(&hw_init_params, 0, sizeof(hw_init_params));
+	hw_init_params.p_tunn = &tunn_info;
+	hw_init_params.b_hw_start = true;
+	hw_init_params.int_mode = cdev->int_params.out.int_mode;
+	hw_init_params.allow_npar_tx_switch = true;
+	hw_init_params.bin_fw_data = data;
+
+	memset(&drv_load_params, 0, sizeof(drv_load_params));
+	drv_load_params.is_crash_kernel = is_kdump_kernel();
+	drv_load_params.mfw_timeout_val = QED_LOAD_REQ_LOCK_TO_DEFAULT;
+	drv_load_params.avoid_eng_reset = false;
+	drv_load_params.override_force_load = QED_OVERRIDE_FORCE_LOAD_NONE;
+	hw_init_params.p_drv_load_params = &drv_load_params;
+
+	rc = qed_hw_init(cdev, &hw_init_params);
 	if (rc)
 		goto err2;
 
@@ -1042,7 +1057,8 @@ static int qed_slowpath_stop(struct qed_dev *cdev)
 	}
 
 	qed_disable_msix(cdev);
-	qed_nic_reset(cdev);
+
+	qed_resc_free(cdev);
 
 	qed_iov_wq_stop(cdev, true);
 
@@ -1653,8 +1669,10 @@ void qed_get_protocol_stats(struct qed_dev *cdev,
 	switch (type) {
 	case QED_MCP_LAN_STATS:
 		qed_get_vport_stats(cdev, &eth_stats);
-		stats->lan_stats.ucast_rx_pkts = eth_stats.rx_ucast_pkts;
-		stats->lan_stats.ucast_tx_pkts = eth_stats.tx_ucast_pkts;
+		stats->lan_stats.ucast_rx_pkts =
+					eth_stats.common.rx_ucast_pkts;
+		stats->lan_stats.ucast_tx_pkts =
+					eth_stats.common.tx_ucast_pkts;
 		stats->lan_stats.fcs_err = -1;
 		break;
 	case QED_MCP_FCOE_STATS:
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 87fde205149f..ff6080df2246 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -111,12 +111,71 @@ void qed_mcp_read_mb(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	}
 }
 
+struct qed_mcp_cmd_elem {
+	struct list_head list;
+	struct qed_mcp_mb_params *p_mb_params;
+	u16 expected_seq_num;
+	bool b_is_completed;
+};
+
+/* Must be called while cmd_lock is acquired */
+static struct qed_mcp_cmd_elem *
+qed_mcp_cmd_add_elem(struct qed_hwfn *p_hwfn,
+		     struct qed_mcp_mb_params *p_mb_params,
+		     u16 expected_seq_num)
+{
+	struct qed_mcp_cmd_elem *p_cmd_elem = NULL;
+
+	p_cmd_elem = kzalloc(sizeof(*p_cmd_elem), GFP_ATOMIC);
+	if (!p_cmd_elem)
+		goto out;
+
+	p_cmd_elem->p_mb_params = p_mb_params;
+	p_cmd_elem->expected_seq_num = expected_seq_num;
+	list_add(&p_cmd_elem->list, &p_hwfn->mcp_info->cmd_list);
+out:
+	return p_cmd_elem;
+}
+
+/* Must be called while cmd_lock is acquired */
+static void qed_mcp_cmd_del_elem(struct qed_hwfn *p_hwfn,
+				 struct qed_mcp_cmd_elem *p_cmd_elem)
+{
+	list_del(&p_cmd_elem->list);
+	kfree(p_cmd_elem);
+}
+
+/* Must be called while cmd_lock is acquired */
+static struct qed_mcp_cmd_elem *qed_mcp_cmd_get_elem(struct qed_hwfn *p_hwfn,
+						     u16 seq_num)
+{
+	struct qed_mcp_cmd_elem *p_cmd_elem = NULL;
+
+	list_for_each_entry(p_cmd_elem, &p_hwfn->mcp_info->cmd_list, list) {
+		if (p_cmd_elem->expected_seq_num == seq_num)
+			return p_cmd_elem;
+	}
+
+	return NULL;
+}
+
 int qed_mcp_free(struct qed_hwfn *p_hwfn)
 {
 	if (p_hwfn->mcp_info) {
+		struct qed_mcp_cmd_elem *p_cmd_elem, *p_tmp;
+
 		kfree(p_hwfn->mcp_info->mfw_mb_cur);
 		kfree(p_hwfn->mcp_info->mfw_mb_shadow);
+
+		spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
+		list_for_each_entry_safe(p_cmd_elem,
+					 p_tmp,
+					 &p_hwfn->mcp_info->cmd_list, list) {
+			qed_mcp_cmd_del_elem(p_hwfn, p_cmd_elem);
+		}
+		spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
 	}
+
 	kfree(p_hwfn->mcp_info);
 
 	return 0;
@@ -160,7 +219,7 @@ static int qed_load_mcp_offsets(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	p_info->drv_pulse_seq = DRV_MB_RD(p_hwfn, p_ptt, drv_pulse_mb) &
 				DRV_PULSE_SEQ_MASK;
 
-	p_info->mcp_hist = (u16)qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0);
+	p_info->mcp_hist = qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0);
 
 	return 0;
 }
@@ -176,6 +235,12 @@ int qed_mcp_cmd_init(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		goto err;
 	p_info = p_hwfn->mcp_info;
 
+	/* Initialize the MFW spinlock */
+	spin_lock_init(&p_info->cmd_lock);
+	spin_lock_init(&p_info->link_lock);
+
+	INIT_LIST_HEAD(&p_info->cmd_list);
+
 	if (qed_load_mcp_offsets(p_hwfn, p_ptt) != 0) {
 		DP_NOTICE(p_hwfn, "MCP is not initialized\n");
 		/* Do not free mcp_info here, since public_base indicate that
@@ -190,10 +255,6 @@ int qed_mcp_cmd_init(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	if (!p_info->mfw_mb_shadow || !p_info->mfw_mb_addr)
 		goto err;
 
-	/* Initialize the MFW spinlock */
-	spin_lock_init(&p_info->lock);
-	spin_lock_init(&p_info->link_lock);
-
 	return 0;
 
 err:
@@ -201,68 +262,39 @@ err:
 	return -ENOMEM;
 }
 
-/* Locks the MFW mailbox of a PF to ensure a single access.
- * The lock is achieved in most cases by holding a spinlock, causing other
- * threads to wait till a previous access is done.
- * In some cases (currently when a [UN]LOAD_REQ commands are sent), the single
- * access is achieved by setting a blocking flag, which will fail other
- * competing contexts to send their mailboxes.
- */
-static int qed_mcp_mb_lock(struct qed_hwfn *p_hwfn, u32 cmd)
+static void qed_mcp_reread_offsets(struct qed_hwfn *p_hwfn,
+				   struct qed_ptt *p_ptt)
 {
-	spin_lock_bh(&p_hwfn->mcp_info->lock);
+	u32 generic_por_0 = qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0);
 
-	/* The spinlock shouldn't be acquired when the mailbox command is
-	 * [UN]LOAD_REQ, since the engine is locked by the MFW, and a parallel
-	 * pending [UN]LOAD_REQ command of another PF together with a spinlock
-	 * (i.e. interrupts are disabled) - can lead to a deadlock.
-	 * It is assumed that for a single PF, no other mailbox commands can be
-	 * sent from another context while sending LOAD_REQ, and that any
-	 * parallel commands to UNLOAD_REQ can be cancelled.
+	/* Use MCP history register to check if MCP reset occurred between init
+	 * time and now.
 	 */
-	if (cmd == DRV_MSG_CODE_LOAD_DONE || cmd == DRV_MSG_CODE_UNLOAD_DONE)
-		p_hwfn->mcp_info->block_mb_sending = false;
-
-	if (p_hwfn->mcp_info->block_mb_sending) {
-		DP_NOTICE(p_hwfn,
-			  "Trying to send a MFW mailbox command [0x%x] in parallel to [UN]LOAD_REQ. Aborting.\n",
-			  cmd);
-		spin_unlock_bh(&p_hwfn->mcp_info->lock);
-		return -EBUSY;
-	}
+	if (p_hwfn->mcp_info->mcp_hist != generic_por_0) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_SP,
+			   "Rereading MCP offsets [mcp_hist 0x%08x, generic_por_0 0x%08x]\n",
+			   p_hwfn->mcp_info->mcp_hist, generic_por_0);
 
-	if (cmd == DRV_MSG_CODE_LOAD_REQ || cmd == DRV_MSG_CODE_UNLOAD_REQ) {
-		p_hwfn->mcp_info->block_mb_sending = true;
-		spin_unlock_bh(&p_hwfn->mcp_info->lock);
+		qed_load_mcp_offsets(p_hwfn, p_ptt);
+		qed_mcp_cmd_port_init(p_hwfn, p_ptt);
 	}
-
-	return 0;
-}
-
-static void qed_mcp_mb_unlock(struct qed_hwfn *p_hwfn, u32 cmd)
-{
-	if (cmd != DRV_MSG_CODE_LOAD_REQ && cmd != DRV_MSG_CODE_UNLOAD_REQ)
-		spin_unlock_bh(&p_hwfn->mcp_info->lock);
 }
 
 int qed_mcp_reset(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
-	u32 seq = ++p_hwfn->mcp_info->drv_mb_seq;
-	u8 delay = CHIP_MCP_RESP_ITER_US;
-	u32 org_mcp_reset_seq, cnt = 0;
+	u32 org_mcp_reset_seq, seq, delay = CHIP_MCP_RESP_ITER_US, cnt = 0;
 	int rc = 0;
 
-	/* Ensure that only a single thread is accessing the mailbox at a
-	 * certain time.
-	 */
-	rc = qed_mcp_mb_lock(p_hwfn, DRV_MSG_CODE_MCP_RESET);
-	if (rc != 0)
-		return rc;
+	/* Ensure that only a single thread is accessing the mailbox */
+	spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
 
-	/* Set drv command along with the updated sequence */
 	org_mcp_reset_seq = qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0);
-	DRV_MB_WR(p_hwfn, p_ptt, drv_mb_header,
-		  (DRV_MSG_CODE_MCP_RESET | seq));
+
+	/* Set drv command along with the updated sequence */
+	qed_mcp_reread_offsets(p_hwfn, p_ptt);
+	seq = ++p_hwfn->mcp_info->drv_mb_seq;
+	DRV_MB_WR(p_hwfn, p_ptt, drv_mb_header, (DRV_MSG_CODE_MCP_RESET | seq));
 
 	do {
 		/* Wait for MFW response */
@@ -281,72 +313,207 @@ int qed_mcp_reset(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		rc = -EAGAIN;
 	}
 
-	qed_mcp_mb_unlock(p_hwfn, DRV_MSG_CODE_MCP_RESET);
+	spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
 
 	return rc;
 }
 
-static int qed_do_mcp_cmd(struct qed_hwfn *p_hwfn,
-			  struct qed_ptt *p_ptt,
-			  u32 cmd,
-			  u32 param,
-			  u32 *o_mcp_resp,
-			  u32 *o_mcp_param)
+/* Must be called while cmd_lock is acquired */
+static bool qed_mcp_has_pending_cmd(struct qed_hwfn *p_hwfn)
 {
-	u8 delay = CHIP_MCP_RESP_ITER_US;
-	u32 seq, cnt = 1, actual_mb_seq;
-	int rc = 0;
+	struct qed_mcp_cmd_elem *p_cmd_elem;
 
-	/* Get actual driver mailbox sequence */
-	actual_mb_seq = DRV_MB_RD(p_hwfn, p_ptt, drv_mb_header) &
-			DRV_MSG_SEQ_NUMBER_MASK;
-
-	/* Use MCP history register to check if MCP reset occurred between
-	 * init time and now.
+	/* There is at most one pending command at a certain time, and if it
+	 * exists - it is placed at the HEAD of the list.
 	 */
-	if (p_hwfn->mcp_info->mcp_hist !=
-	    qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0)) {
-		DP_VERBOSE(p_hwfn, QED_MSG_SP, "Rereading MCP offsets\n");
-		qed_load_mcp_offsets(p_hwfn, p_ptt);
-		qed_mcp_cmd_port_init(p_hwfn, p_ptt);
+	if (!list_empty(&p_hwfn->mcp_info->cmd_list)) {
+		p_cmd_elem = list_first_entry(&p_hwfn->mcp_info->cmd_list,
+					      struct qed_mcp_cmd_elem, list);
+		return !p_cmd_elem->b_is_completed;
 	}
-	seq = ++p_hwfn->mcp_info->drv_mb_seq;
 
-	/* Set drv param */
-	DRV_MB_WR(p_hwfn, p_ptt, drv_mb_param, param);
+	return false;
+}
 
-	/* Set drv command along with the updated sequence */
-	DRV_MB_WR(p_hwfn, p_ptt, drv_mb_header, (cmd | seq));
+/* Must be called while cmd_lock is acquired */
+static int
+qed_mcp_update_pending_cmd(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_mcp_mb_params *p_mb_params;
+	struct qed_mcp_cmd_elem *p_cmd_elem;
+	u32 mcp_resp;
+	u16 seq_num;
+
+	mcp_resp = DRV_MB_RD(p_hwfn, p_ptt, fw_mb_header);
+	seq_num = (u16)(mcp_resp & FW_MSG_SEQ_NUMBER_MASK);
+
+	/* Return if no new non-handled response has been received */
+	if (seq_num != p_hwfn->mcp_info->drv_mb_seq)
+		return -EAGAIN;
+
+	p_cmd_elem = qed_mcp_cmd_get_elem(p_hwfn, seq_num);
+	if (!p_cmd_elem) {
+		DP_ERR(p_hwfn,
+		       "Failed to find a pending mailbox cmd that expects sequence number %d\n",
+		       seq_num);
+		return -EINVAL;
+	}
+
+	p_mb_params = p_cmd_elem->p_mb_params;
+
+	/* Get the MFW response along with the sequence number */
+	p_mb_params->mcp_resp = mcp_resp;
+
+	/* Get the MFW param */
+	p_mb_params->mcp_param = DRV_MB_RD(p_hwfn, p_ptt, fw_mb_param);
+
+	/* Get the union data */
+	if (p_mb_params->p_data_dst != NULL && p_mb_params->data_dst_size) {
+		u32 union_data_addr = p_hwfn->mcp_info->drv_mb_addr +
+				      offsetof(struct public_drv_mb,
+					       union_data);
+		qed_memcpy_from(p_hwfn, p_ptt, p_mb_params->p_data_dst,
+				union_data_addr, p_mb_params->data_dst_size);
+	}
+
+	p_cmd_elem->b_is_completed = true;
+
+	return 0;
+}
+
+/* Must be called while cmd_lock is acquired */
+static void __qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
+				    struct qed_ptt *p_ptt,
+				    struct qed_mcp_mb_params *p_mb_params,
+				    u16 seq_num)
+{
+	union drv_union_data union_data;
+	u32 union_data_addr;
+
+	/* Set the union data */
+	union_data_addr = p_hwfn->mcp_info->drv_mb_addr +
+			  offsetof(struct public_drv_mb, union_data);
+	memset(&union_data, 0, sizeof(union_data));
+	if (p_mb_params->p_data_src != NULL && p_mb_params->data_src_size)
+		memcpy(&union_data, p_mb_params->p_data_src,
+		       p_mb_params->data_src_size);
+	qed_memcpy_to(p_hwfn, p_ptt, union_data_addr, &union_data,
+		      sizeof(union_data));
+
+	/* Set the drv param */
+	DRV_MB_WR(p_hwfn, p_ptt, drv_mb_param, p_mb_params->param);
+
+	/* Set the drv command along with the sequence number */
+	DRV_MB_WR(p_hwfn, p_ptt, drv_mb_header, (p_mb_params->cmd | seq_num));
 
 	DP_VERBOSE(p_hwfn, QED_MSG_SP,
-		   "wrote command (%x) to MFW MB param 0x%08x\n",
-		   (cmd | seq), param);
+		   "MFW mailbox: command 0x%08x param 0x%08x\n",
+		   (p_mb_params->cmd | seq_num), p_mb_params->param);
+}
+
+static int
+_qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
+		       struct qed_ptt *p_ptt,
+		       struct qed_mcp_mb_params *p_mb_params,
+		       u32 max_retries, u32 delay)
+{
+	struct qed_mcp_cmd_elem *p_cmd_elem;
+	u32 cnt = 0;
+	u16 seq_num;
+	int rc = 0;
 
+	/* Wait until the mailbox is non-occupied */
 	do {
-		/* Wait for MFW response */
+		/* Exit the loop if there is no pending command, or if the
+		 * pending command is completed during this iteration.
+		 * The spinlock stays locked until the command is sent.
+		 */
+
+		spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
+
+		if (!qed_mcp_has_pending_cmd(p_hwfn))
+			break;
+
+		rc = qed_mcp_update_pending_cmd(p_hwfn, p_ptt);
+		if (!rc)
+			break;
+		else if (rc != -EAGAIN)
+			goto err;
+
+		spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
 		udelay(delay);
-		*o_mcp_resp = DRV_MB_RD(p_hwfn, p_ptt, fw_mb_header);
+	} while (++cnt < max_retries);
 
-		/* Give the FW up to 5 second (500*10ms) */
-	} while ((seq != (*o_mcp_resp & FW_MSG_SEQ_NUMBER_MASK)) &&
-		 (cnt++ < QED_DRV_MB_MAX_RETRIES));
+	if (cnt >= max_retries) {
+		DP_NOTICE(p_hwfn,
+			  "The MFW mailbox is occupied by an uncompleted command. Failed to send command 0x%08x [param 0x%08x].\n",
+			  p_mb_params->cmd, p_mb_params->param);
+		return -EAGAIN;
+	}
 
-	DP_VERBOSE(p_hwfn, QED_MSG_SP,
-		   "[after %d ms] read (%x) seq is (%x) from FW MB\n",
-		   cnt * delay, *o_mcp_resp, seq);
-
-	/* Is this a reply to our command? */
-	if (seq == (*o_mcp_resp & FW_MSG_SEQ_NUMBER_MASK)) {
-		*o_mcp_resp &= FW_MSG_CODE_MASK;
-		/* Get the MCP param */
-		*o_mcp_param = DRV_MB_RD(p_hwfn, p_ptt, fw_mb_param);
-	} else {
-		/* FW BUG! */
-		DP_ERR(p_hwfn, "MFW failed to respond [cmd 0x%x param 0x%x]\n",
-		       cmd, param);
-		*o_mcp_resp = 0;
-		rc = -EAGAIN;
+	/* Send the mailbox command */
+	qed_mcp_reread_offsets(p_hwfn, p_ptt);
+	seq_num = ++p_hwfn->mcp_info->drv_mb_seq;
+	p_cmd_elem = qed_mcp_cmd_add_elem(p_hwfn, p_mb_params, seq_num);
+	if (!p_cmd_elem) {
+		rc = -ENOMEM;
+		goto err;
 	}
+
+	__qed_mcp_cmd_and_union(p_hwfn, p_ptt, p_mb_params, seq_num);
+	spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
+
+	/* Wait for the MFW response */
+	do {
+		/* Exit the loop if the command is already completed, or if the
+		 * command is completed during this iteration.
+		 * The spinlock stays locked until the list element is removed.
+		 */
+
+		udelay(delay);
+		spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
+
+		if (p_cmd_elem->b_is_completed)
+			break;
+
+		rc = qed_mcp_update_pending_cmd(p_hwfn, p_ptt);
+		if (!rc)
+			break;
+		else if (rc != -EAGAIN)
+			goto err;
+
+		spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
+	} while (++cnt < max_retries);
+
+	if (cnt >= max_retries) {
+		DP_NOTICE(p_hwfn,
+			  "The MFW failed to respond to command 0x%08x [param 0x%08x].\n",
+			  p_mb_params->cmd, p_mb_params->param);
+
+		spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
+		qed_mcp_cmd_del_elem(p_hwfn, p_cmd_elem);
+		spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
+
+		return -EAGAIN;
+	}
+
+	qed_mcp_cmd_del_elem(p_hwfn, p_cmd_elem);
+	spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
+
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_SP,
+		   "MFW mailbox: response 0x%08x param 0x%08x [after %d.%03d ms]\n",
+		   p_mb_params->mcp_resp,
+		   p_mb_params->mcp_param,
+		   (cnt * delay) / 1000, (cnt * delay) % 1000);
+
+	/* Clear the sequence number from the MFW response */
+	p_mb_params->mcp_resp &= FW_MSG_CODE_MASK;
+
+	return 0;
+
+err:
+	spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
 	return rc;
 }
 
@@ -354,9 +521,9 @@ static int qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
 				 struct qed_ptt *p_ptt,
 				 struct qed_mcp_mb_params *p_mb_params)
 {
-	u32 union_data_addr;
-
-	int rc;
+	size_t union_data_size = sizeof(union drv_union_data);
+	u32 max_retries = QED_DRV_MB_MAX_RETRIES;
+	u32 delay = CHIP_MCP_RESP_ITER_US;
 
 	/* MCP not initialized */
 	if (!qed_mcp_is_init(p_hwfn)) {
@@ -364,33 +531,17 @@ static int qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
 		return -EBUSY;
 	}
 
-	union_data_addr = p_hwfn->mcp_info->drv_mb_addr +
-			  offsetof(struct public_drv_mb, union_data);
-
-	/* Ensure that only a single thread is accessing the mailbox at a
-	 * certain time.
-	 */
-	rc = qed_mcp_mb_lock(p_hwfn, p_mb_params->cmd);
-	if (rc)
-		return rc;
-
-	if (p_mb_params->p_data_src != NULL)
-		qed_memcpy_to(p_hwfn, p_ptt, union_data_addr,
-			      p_mb_params->p_data_src,
-			      sizeof(*p_mb_params->p_data_src));
-
-	rc = qed_do_mcp_cmd(p_hwfn, p_ptt, p_mb_params->cmd,
-			    p_mb_params->param, &p_mb_params->mcp_resp,
-			    &p_mb_params->mcp_param);
-
-	if (p_mb_params->p_data_dst != NULL)
-		qed_memcpy_from(p_hwfn, p_ptt, p_mb_params->p_data_dst,
-				union_data_addr,
-				sizeof(*p_mb_params->p_data_dst));
-
-	qed_mcp_mb_unlock(p_hwfn, p_mb_params->cmd);
+	if (p_mb_params->data_src_size > union_data_size ||
+	    p_mb_params->data_dst_size > union_data_size) {
+		DP_ERR(p_hwfn,
+		       "The provided size is larger than the union data size [src_size %u, dst_size %u, union_data_size %zu]\n",
+		       p_mb_params->data_src_size,
+		       p_mb_params->data_dst_size, union_data_size);
+		return -EINVAL;
+	}
 
-	return rc;
+	return _qed_mcp_cmd_and_union(p_hwfn, p_ptt, p_mb_params, max_retries,
+				      delay);
 }
 
 int qed_mcp_cmd(struct qed_hwfn *p_hwfn,
@@ -401,32 +552,12 @@ int qed_mcp_cmd(struct qed_hwfn *p_hwfn,
 		u32 *o_mcp_param)
 {
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data data_src;
 	int rc;
 
 	memset(&mb_params, 0, sizeof(mb_params));
-	memset(&data_src, 0, sizeof(data_src));
 	mb_params.cmd = cmd;
 	mb_params.param = param;
 
-	/* In case of UNLOAD_DONE, set the primary MAC */
-	if ((cmd == DRV_MSG_CODE_UNLOAD_DONE) &&
-	    (p_hwfn->cdev->wol_config == QED_OV_WOL_ENABLED)) {
-		u8 *p_mac = p_hwfn->cdev->wol_mac;
-
-		data_src.wol_mac.mac_upper = p_mac[0] << 8 | p_mac[1];
-		data_src.wol_mac.mac_lower = p_mac[2] << 24 | p_mac[3] << 16 |
-					     p_mac[4] << 8 | p_mac[5];
-
-		DP_VERBOSE(p_hwfn,
-			   (QED_MSG_SP | NETIF_MSG_IFDOWN),
-			   "Setting WoL MAC: %pM --> [%08x,%08x]\n",
-			   p_mac, data_src.wol_mac.mac_upper,
-			   data_src.wol_mac.mac_lower);
-
-		mb_params.p_data_src = &data_src;
-	}
-
 	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 	if (rc)
 		return rc;
@@ -445,13 +576,17 @@ int qed_mcp_nvm_rd_cmd(struct qed_hwfn *p_hwfn,
 		       u32 *o_mcp_param, u32 *o_txn_size, u32 *o_buf)
 {
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data union_data;
+	u8 raw_data[MCP_DRV_NVM_BUF_LEN];
 	int rc;
 
 	memset(&mb_params, 0, sizeof(mb_params));
 	mb_params.cmd = cmd;
 	mb_params.param = param;
-	mb_params.p_data_dst = &union_data;
+	mb_params.p_data_dst = raw_data;
+
+	/* Use the maximal value since the actual one is part of the response */
+	mb_params.data_dst_size = MCP_DRV_NVM_BUF_LEN;
+
 	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 	if (rc)
 		return rc;
@@ -460,55 +595,413 @@ int qed_mcp_nvm_rd_cmd(struct qed_hwfn *p_hwfn,
 	*o_mcp_param = mb_params.mcp_param;
 
 	*o_txn_size = *o_mcp_param;
-	memcpy(o_buf, &union_data.raw_data, *o_txn_size);
+	memcpy(o_buf, raw_data, *o_txn_size);
 
 	return 0;
 }
 
-int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
-		     struct qed_ptt *p_ptt, u32 *p_load_code)
+static bool
+qed_mcp_can_force_load(u8 drv_role,
+		       u8 exist_drv_role,
+		       enum qed_override_force_load override_force_load)
+{
+	bool can_force_load = false;
+
+	switch (override_force_load) {
+	case QED_OVERRIDE_FORCE_LOAD_ALWAYS:
+		can_force_load = true;
+		break;
+	case QED_OVERRIDE_FORCE_LOAD_NEVER:
+		can_force_load = false;
+		break;
+	default:
+		can_force_load = (drv_role == DRV_ROLE_OS &&
+				  exist_drv_role == DRV_ROLE_PREBOOT) ||
+				 (drv_role == DRV_ROLE_KDUMP &&
+				  exist_drv_role == DRV_ROLE_OS);
+		break;
+	}
+
+	return can_force_load;
+}
+
+static int qed_mcp_cancel_load_req(struct qed_hwfn *p_hwfn,
+				   struct qed_ptt *p_ptt)
+{
+	u32 resp = 0, param = 0;
+	int rc;
+
+	rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_CANCEL_LOAD_REQ, 0,
+			 &resp, &param);
+	if (rc)
+		DP_NOTICE(p_hwfn,
+			  "Failed to send cancel load request, rc = %d\n", rc);
+
+	return rc;
+}
+
+#define CONFIG_QEDE_BITMAP_IDX		BIT(0)
+#define CONFIG_QED_SRIOV_BITMAP_IDX	BIT(1)
+#define CONFIG_QEDR_BITMAP_IDX		BIT(2)
+#define CONFIG_QEDF_BITMAP_IDX		BIT(4)
+#define CONFIG_QEDI_BITMAP_IDX		BIT(5)
+#define CONFIG_QED_LL2_BITMAP_IDX	BIT(6)
+
+static u32 qed_get_config_bitmap(void)
+{
+	u32 config_bitmap = 0x0;
+
+	if (IS_ENABLED(CONFIG_QEDE))
+		config_bitmap |= CONFIG_QEDE_BITMAP_IDX;
+
+	if (IS_ENABLED(CONFIG_QED_SRIOV))
+		config_bitmap |= CONFIG_QED_SRIOV_BITMAP_IDX;
+
+	if (IS_ENABLED(CONFIG_QED_RDMA))
+		config_bitmap |= CONFIG_QEDR_BITMAP_IDX;
+
+	if (IS_ENABLED(CONFIG_QED_FCOE))
+		config_bitmap |= CONFIG_QEDF_BITMAP_IDX;
+
+	if (IS_ENABLED(CONFIG_QED_ISCSI))
+		config_bitmap |= CONFIG_QEDI_BITMAP_IDX;
+
+	if (IS_ENABLED(CONFIG_QED_LL2))
+		config_bitmap |= CONFIG_QED_LL2_BITMAP_IDX;
+
+	return config_bitmap;
+}
+
+struct qed_load_req_in_params {
+	u8 hsi_ver;
+#define QED_LOAD_REQ_HSI_VER_DEFAULT	0
+#define QED_LOAD_REQ_HSI_VER_1		1
+	u32 drv_ver_0;
+	u32 drv_ver_1;
+	u32 fw_ver;
+	u8 drv_role;
+	u8 timeout_val;
+	u8 force_cmd;
+	bool avoid_eng_reset;
+};
+
+struct qed_load_req_out_params {
+	u32 load_code;
+	u32 exist_drv_ver_0;
+	u32 exist_drv_ver_1;
+	u32 exist_fw_ver;
+	u8 exist_drv_role;
+	u8 mfw_hsi_ver;
+	bool drv_exists;
+};
+
+static int
+__qed_mcp_load_req(struct qed_hwfn *p_hwfn,
+		   struct qed_ptt *p_ptt,
+		   struct qed_load_req_in_params *p_in_params,
+		   struct qed_load_req_out_params *p_out_params)
 {
-	struct qed_dev *cdev = p_hwfn->cdev;
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data union_data;
+	struct load_req_stc load_req;
+	struct load_rsp_stc load_rsp;
+	u32 hsi_ver;
 	int rc;
 
+	memset(&load_req, 0, sizeof(load_req));
+	load_req.drv_ver_0 = p_in_params->drv_ver_0;
+	load_req.drv_ver_1 = p_in_params->drv_ver_1;
+	load_req.fw_ver = p_in_params->fw_ver;
+	QED_MFW_SET_FIELD(load_req.misc0, LOAD_REQ_ROLE, p_in_params->drv_role);
+	QED_MFW_SET_FIELD(load_req.misc0, LOAD_REQ_LOCK_TO,
+			  p_in_params->timeout_val);
+	QED_MFW_SET_FIELD(load_req.misc0, LOAD_REQ_FORCE,
+			  p_in_params->force_cmd);
+	QED_MFW_SET_FIELD(load_req.misc0, LOAD_REQ_FLAGS0,
+			  p_in_params->avoid_eng_reset);
+
+	hsi_ver = (p_in_params->hsi_ver == QED_LOAD_REQ_HSI_VER_DEFAULT) ?
+		  DRV_ID_MCP_HSI_VER_CURRENT :
+		  (p_in_params->hsi_ver << DRV_ID_MCP_HSI_VER_SHIFT);
+
 	memset(&mb_params, 0, sizeof(mb_params));
-	/* Load Request */
 	mb_params.cmd = DRV_MSG_CODE_LOAD_REQ;
-	mb_params.param = PDA_COMP | DRV_ID_MCP_HSI_VER_CURRENT |
-			  cdev->drv_type;
-	memcpy(&union_data.ver_str, cdev->ver_str, MCP_DRV_VER_STR_SIZE);
-	mb_params.p_data_src = &union_data;
-	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
+	mb_params.param = PDA_COMP | hsi_ver | p_hwfn->cdev->drv_type;
+	mb_params.p_data_src = &load_req;
+	mb_params.data_src_size = sizeof(load_req);
+	mb_params.p_data_dst = &load_rsp;
+	mb_params.data_dst_size = sizeof(load_rsp);
 
-	/* if mcp fails to respond we must abort */
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "Load Request: param 0x%08x [init_hw %d, drv_type %d, hsi_ver %d, pda 0x%04x]\n",
+		   mb_params.param,
+		   QED_MFW_GET_FIELD(mb_params.param, DRV_ID_DRV_INIT_HW),
+		   QED_MFW_GET_FIELD(mb_params.param, DRV_ID_DRV_TYPE),
+		   QED_MFW_GET_FIELD(mb_params.param, DRV_ID_MCP_HSI_VER),
+		   QED_MFW_GET_FIELD(mb_params.param, DRV_ID_PDA_COMP_VER));
+
+	if (p_in_params->hsi_ver != QED_LOAD_REQ_HSI_VER_1) {
+		DP_VERBOSE(p_hwfn, QED_MSG_SP,
+			   "Load Request: drv_ver 0x%08x_0x%08x, fw_ver 0x%08x, misc0 0x%08x [role %d, timeout %d, force %d, flags0 0x%x]\n",
+			   load_req.drv_ver_0,
+			   load_req.drv_ver_1,
+			   load_req.fw_ver,
+			   load_req.misc0,
+			   QED_MFW_GET_FIELD(load_req.misc0, LOAD_REQ_ROLE),
+			   QED_MFW_GET_FIELD(load_req.misc0,
+					     LOAD_REQ_LOCK_TO),
+			   QED_MFW_GET_FIELD(load_req.misc0, LOAD_REQ_FORCE),
+			   QED_MFW_GET_FIELD(load_req.misc0, LOAD_REQ_FLAGS0));
+	}
+
+	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 	if (rc) {
-		DP_ERR(p_hwfn, "MCP response failure, aborting\n");
+		DP_NOTICE(p_hwfn, "Failed to send load request, rc = %d\n", rc);
 		return rc;
 	}
 
-	*p_load_code = mb_params.mcp_resp;
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "Load Response: resp 0x%08x\n", mb_params.mcp_resp);
+	p_out_params->load_code = mb_params.mcp_resp;
+
+	if (p_in_params->hsi_ver != QED_LOAD_REQ_HSI_VER_1 &&
+	    p_out_params->load_code != FW_MSG_CODE_DRV_LOAD_REFUSED_HSI_1) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_SP,
+			   "Load Response: exist_drv_ver 0x%08x_0x%08x, exist_fw_ver 0x%08x, misc0 0x%08x [exist_role %d, mfw_hsi %d, flags0 0x%x]\n",
+			   load_rsp.drv_ver_0,
+			   load_rsp.drv_ver_1,
+			   load_rsp.fw_ver,
+			   load_rsp.misc0,
+			   QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_ROLE),
+			   QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_HSI),
+			   QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_FLAGS0));
+
+		p_out_params->exist_drv_ver_0 = load_rsp.drv_ver_0;
+		p_out_params->exist_drv_ver_1 = load_rsp.drv_ver_1;
+		p_out_params->exist_fw_ver = load_rsp.fw_ver;
+		p_out_params->exist_drv_role =
+		    QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_ROLE);
+		p_out_params->mfw_hsi_ver =
+		    QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_HSI);
+		p_out_params->drv_exists =
+		    QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_FLAGS0) &
+		    LOAD_RSP_FLAGS0_DRV_EXISTS;
+	}
+
+	return 0;
+}
+
+static int eocre_get_mfw_drv_role(struct qed_hwfn *p_hwfn,
+				  enum qed_drv_role drv_role,
+				  u8 *p_mfw_drv_role)
+{
+	switch (drv_role) {
+	case QED_DRV_ROLE_OS:
+		*p_mfw_drv_role = DRV_ROLE_OS;
+		break;
+	case QED_DRV_ROLE_KDUMP:
+		*p_mfw_drv_role = DRV_ROLE_KDUMP;
+		break;
+	default:
+		DP_ERR(p_hwfn, "Unexpected driver role %d\n", drv_role);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+enum qed_load_req_force {
+	QED_LOAD_REQ_FORCE_NONE,
+	QED_LOAD_REQ_FORCE_PF,
+	QED_LOAD_REQ_FORCE_ALL,
+};
+
+static void qed_get_mfw_force_cmd(struct qed_hwfn *p_hwfn,
 
-	/* If MFW refused (e.g. other port is in diagnostic mode) we
-	 * must abort. This can happen in the following cases:
-	 * - Other port is in diagnostic mode
-	 * - Previously loaded function on the engine is not compliant with
-	 *   the requester.
-	 * - MFW cannot cope with the requester's DRV_MFW_HSI_VERSION.
-	 *      -
+				  enum qed_load_req_force force_cmd,
+				  u8 *p_mfw_force_cmd)
+{
+	switch (force_cmd) {
+	case QED_LOAD_REQ_FORCE_NONE:
+		*p_mfw_force_cmd = LOAD_REQ_FORCE_NONE;
+		break;
+	case QED_LOAD_REQ_FORCE_PF:
+		*p_mfw_force_cmd = LOAD_REQ_FORCE_PF;
+		break;
+	case QED_LOAD_REQ_FORCE_ALL:
+		*p_mfw_force_cmd = LOAD_REQ_FORCE_ALL;
+		break;
+	}
+}
+
+int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
+		     struct qed_ptt *p_ptt,
+		     struct qed_load_req_params *p_params)
+{
+	struct qed_load_req_out_params out_params;
+	struct qed_load_req_in_params in_params;
+	u8 mfw_drv_role, mfw_force_cmd;
+	int rc;
+
+	memset(&in_params, 0, sizeof(in_params));
+	in_params.hsi_ver = QED_LOAD_REQ_HSI_VER_DEFAULT;
+	in_params.drv_ver_0 = QED_VERSION;
+	in_params.drv_ver_1 = qed_get_config_bitmap();
+	in_params.fw_ver = STORM_FW_VERSION;
+	rc = eocre_get_mfw_drv_role(p_hwfn, p_params->drv_role, &mfw_drv_role);
+	if (rc)
+		return rc;
+
+	in_params.drv_role = mfw_drv_role;
+	in_params.timeout_val = p_params->timeout_val;
+	qed_get_mfw_force_cmd(p_hwfn,
+			      QED_LOAD_REQ_FORCE_NONE, &mfw_force_cmd);
+
+	in_params.force_cmd = mfw_force_cmd;
+	in_params.avoid_eng_reset = p_params->avoid_eng_reset;
+
+	memset(&out_params, 0, sizeof(out_params));
+	rc = __qed_mcp_load_req(p_hwfn, p_ptt, &in_params, &out_params);
+	if (rc)
+		return rc;
+
+	/* First handle cases where another load request should/might be sent:
+	 * - MFW expects the old interface [HSI version = 1]
+	 * - MFW responds that a force load request is required
 	 */
-	if (!(*p_load_code) ||
-	    ((*p_load_code) == FW_MSG_CODE_DRV_LOAD_REFUSED_HSI) ||
-	    ((*p_load_code) == FW_MSG_CODE_DRV_LOAD_REFUSED_PDA) ||
-	    ((*p_load_code) == FW_MSG_CODE_DRV_LOAD_REFUSED_DIAG)) {
-		DP_ERR(p_hwfn, "MCP refused load request, aborting\n");
+	if (out_params.load_code == FW_MSG_CODE_DRV_LOAD_REFUSED_HSI_1) {
+		DP_INFO(p_hwfn,
+			"MFW refused a load request due to HSI > 1. Resending with HSI = 1\n");
+
+		in_params.hsi_ver = QED_LOAD_REQ_HSI_VER_1;
+		memset(&out_params, 0, sizeof(out_params));
+		rc = __qed_mcp_load_req(p_hwfn, p_ptt, &in_params, &out_params);
+		if (rc)
+			return rc;
+	} else if (out_params.load_code ==
+		   FW_MSG_CODE_DRV_LOAD_REFUSED_REQUIRES_FORCE) {
+		if (qed_mcp_can_force_load(in_params.drv_role,
+					   out_params.exist_drv_role,
+					   p_params->override_force_load)) {
+			DP_INFO(p_hwfn,
+				"A force load is required [{role, fw_ver, drv_ver}: loading={%d, 0x%08x, x%08x_0x%08x}, existing={%d, 0x%08x, 0x%08x_0x%08x}]\n",
+				in_params.drv_role, in_params.fw_ver,
+				in_params.drv_ver_0, in_params.drv_ver_1,
+				out_params.exist_drv_role,
+				out_params.exist_fw_ver,
+				out_params.exist_drv_ver_0,
+				out_params.exist_drv_ver_1);
+
+			qed_get_mfw_force_cmd(p_hwfn,
+					      QED_LOAD_REQ_FORCE_ALL,
+					      &mfw_force_cmd);
+
+			in_params.force_cmd = mfw_force_cmd;
+			memset(&out_params, 0, sizeof(out_params));
+			rc = __qed_mcp_load_req(p_hwfn, p_ptt, &in_params,
+						&out_params);
+			if (rc)
+				return rc;
+		} else {
+			DP_NOTICE(p_hwfn,
+				  "A force load is required [{role, fw_ver, drv_ver}: loading={%d, 0x%08x, x%08x_0x%08x}, existing={%d, 0x%08x, 0x%08x_0x%08x}] - Avoid\n",
+				  in_params.drv_role, in_params.fw_ver,
+				  in_params.drv_ver_0, in_params.drv_ver_1,
+				  out_params.exist_drv_role,
+				  out_params.exist_fw_ver,
+				  out_params.exist_drv_ver_0,
+				  out_params.exist_drv_ver_1);
+			DP_NOTICE(p_hwfn,
+				  "Avoid sending a force load request to prevent disruption of active PFs\n");
+
+			qed_mcp_cancel_load_req(p_hwfn, p_ptt);
+			return -EBUSY;
+		}
+	}
+
+	/* Now handle the other types of responses.
+	 * The "REFUSED_HSI_1" and "REFUSED_REQUIRES_FORCE" responses are not
+	 * expected here after the additional revised load requests were sent.
+	 */
+	switch (out_params.load_code) {
+	case FW_MSG_CODE_DRV_LOAD_ENGINE:
+	case FW_MSG_CODE_DRV_LOAD_PORT:
+	case FW_MSG_CODE_DRV_LOAD_FUNCTION:
+		if (out_params.mfw_hsi_ver != QED_LOAD_REQ_HSI_VER_1 &&
+		    out_params.drv_exists) {
+			/* The role and fw/driver version match, but the PF is
+			 * already loaded and has not been unloaded gracefully.
+			 */
+			DP_NOTICE(p_hwfn,
+				  "PF is already loaded\n");
+			return -EINVAL;
+		}
+		break;
+	default:
+		DP_NOTICE(p_hwfn,
+			  "Unexpected refusal to load request [resp 0x%08x]. Aborting.\n",
+			  out_params.load_code);
 		return -EBUSY;
 	}
 
+	p_params->load_code = out_params.load_code;
+
 	return 0;
 }
 
+int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	u32 wol_param, mcp_resp, mcp_param;
+
+	switch (p_hwfn->cdev->wol_config) {
+	case QED_OV_WOL_DISABLED:
+		wol_param = DRV_MB_PARAM_UNLOAD_WOL_DISABLED;
+		break;
+	case QED_OV_WOL_ENABLED:
+		wol_param = DRV_MB_PARAM_UNLOAD_WOL_ENABLED;
+		break;
+	default:
+		DP_NOTICE(p_hwfn,
+			  "Unknown WoL configuration %02x\n",
+			  p_hwfn->cdev->wol_config);
+		/* Fallthrough */
+	case QED_OV_WOL_DEFAULT:
+		wol_param = DRV_MB_PARAM_UNLOAD_WOL_MCP;
+	}
+
+	return qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_UNLOAD_REQ, wol_param,
+			   &mcp_resp, &mcp_param);
+}
+
+int qed_mcp_unload_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_mcp_mb_params mb_params;
+	struct mcp_mac wol_mac;
+
+	memset(&mb_params, 0, sizeof(mb_params));
+	mb_params.cmd = DRV_MSG_CODE_UNLOAD_DONE;
+
+	/* Set the primary MAC if WoL is enabled */
+	if (p_hwfn->cdev->wol_config == QED_OV_WOL_ENABLED) {
+		u8 *p_mac = p_hwfn->cdev->wol_mac;
+
+		memset(&wol_mac, 0, sizeof(wol_mac));
+		wol_mac.mac_upper = p_mac[0] << 8 | p_mac[1];
+		wol_mac.mac_lower = p_mac[2] << 24 | p_mac[3] << 16 |
+				    p_mac[4] << 8 | p_mac[5];
+
+		DP_VERBOSE(p_hwfn,
+			   (QED_MSG_SP | NETIF_MSG_IFDOWN),
+			   "Setting WoL MAC: %pM --> [%08x,%08x]\n",
+			   p_mac, wol_mac.mac_upper, wol_mac.mac_lower);
+
+		mb_params.p_data_src = &wol_mac;
+		mb_params.data_src_size = sizeof(wol_mac);
+	}
+
+	return qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
+}
+
 static void qed_mcp_handle_vf_flr(struct qed_hwfn *p_hwfn,
 				  struct qed_ptt *p_ptt)
 {
@@ -549,7 +1042,6 @@ int qed_mcp_ack_vf_flr(struct qed_hwfn *p_hwfn,
 	u32 func_addr = SECTION_ADDR(mfw_func_offsize,
 				     MCP_PF_ID(p_hwfn));
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data union_data;
 	int rc;
 	int i;
 
@@ -560,8 +1052,8 @@ int qed_mcp_ack_vf_flr(struct qed_hwfn *p_hwfn,
 
 	memset(&mb_params, 0, sizeof(mb_params));
 	mb_params.cmd = DRV_MSG_CODE_VF_DISABLED_DONE;
-	memcpy(&union_data.ack_vf_disabled, vfs_to_ack, VF_MAX_STATIC / 8);
-	mb_params.p_data_src = &union_data;
+	mb_params.p_data_src = vfs_to_ack;
+	mb_params.data_src_size = VF_MAX_STATIC / 8;
 	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 	if (rc) {
 		DP_NOTICE(p_hwfn, "Failed to pass ACK for VF flr to MFW\n");
@@ -744,33 +1236,31 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up)
 {
 	struct qed_mcp_link_params *params = &p_hwfn->mcp_info->link_input;
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data union_data;
-	struct eth_phy_cfg *phy_cfg;
+	struct eth_phy_cfg phy_cfg;
 	int rc = 0;
 	u32 cmd;
 
 	/* Set the shmem configuration according to params */
-	phy_cfg = &union_data.drv_phy_cfg;
-	memset(phy_cfg, 0, sizeof(*phy_cfg));
+	memset(&phy_cfg, 0, sizeof(phy_cfg));
 	cmd = b_up ? DRV_MSG_CODE_INIT_PHY : DRV_MSG_CODE_LINK_RESET;
 	if (!params->speed.autoneg)
-		phy_cfg->speed = params->speed.forced_speed;
-	phy_cfg->pause |= (params->pause.autoneg) ? ETH_PAUSE_AUTONEG : 0;
-	phy_cfg->pause |= (params->pause.forced_rx) ? ETH_PAUSE_RX : 0;
-	phy_cfg->pause |= (params->pause.forced_tx) ? ETH_PAUSE_TX : 0;
-	phy_cfg->adv_speed = params->speed.advertised_speeds;
-	phy_cfg->loopback_mode = params->loopback_mode;
+		phy_cfg.speed = params->speed.forced_speed;
+	phy_cfg.pause |= (params->pause.autoneg) ? ETH_PAUSE_AUTONEG : 0;
+	phy_cfg.pause |= (params->pause.forced_rx) ? ETH_PAUSE_RX : 0;
+	phy_cfg.pause |= (params->pause.forced_tx) ? ETH_PAUSE_TX : 0;
+	phy_cfg.adv_speed = params->speed.advertised_speeds;
+	phy_cfg.loopback_mode = params->loopback_mode;
 
 	p_hwfn->b_drv_link_init = b_up;
 
 	if (b_up) {
 		DP_VERBOSE(p_hwfn, NETIF_MSG_LINK,
 			   "Configuring Link: Speed 0x%08x, Pause 0x%08x, adv_speed 0x%08x, loopback 0x%08x, features 0x%08x\n",
-			   phy_cfg->speed,
-			   phy_cfg->pause,
-			   phy_cfg->adv_speed,
-			   phy_cfg->loopback_mode,
-			   phy_cfg->feature_config_flags);
+			   phy_cfg.speed,
+			   phy_cfg.pause,
+			   phy_cfg.adv_speed,
+			   phy_cfg.loopback_mode,
+			   phy_cfg.feature_config_flags);
 	} else {
 		DP_VERBOSE(p_hwfn, NETIF_MSG_LINK,
 			   "Resetting link\n");
@@ -778,7 +1268,8 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up)
 
 	memset(&mb_params, 0, sizeof(mb_params));
 	mb_params.cmd = cmd;
-	mb_params.p_data_src = &union_data;
+	mb_params.p_data_src = &phy_cfg;
+	mb_params.data_src_size = sizeof(phy_cfg);
 	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 
 	/* if mcp fails to respond we must abort */
@@ -805,7 +1296,6 @@ static void qed_mcp_send_protocol_stats(struct qed_hwfn *p_hwfn,
 	enum qed_mcp_protocol_type stats_type;
 	union qed_mcp_protocol_stats stats;
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data union_data;
 	u32 hsi_param;
 
 	switch (type) {
@@ -835,8 +1325,8 @@ static void qed_mcp_send_protocol_stats(struct qed_hwfn *p_hwfn,
 	memset(&mb_params, 0, sizeof(mb_params));
 	mb_params.cmd = DRV_MSG_CODE_GET_STATS;
 	mb_params.param = hsi_param;
-	memcpy(&union_data, &stats, sizeof(stats));
-	mb_params.p_data_src = &union_data;
+	mb_params.p_data_src = &stats;
+	mb_params.data_src_size = sizeof(stats);
 	qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 }
 
@@ -963,7 +1453,7 @@ int qed_mcp_handle_events(struct qed_hwfn *p_hwfn,
 			qed_mcp_update_bw(p_hwfn, p_ptt);
 			break;
 		default:
-			DP_NOTICE(p_hwfn, "Unimplemented MFW message %d\n", i);
+			DP_INFO(p_hwfn, "Unimplemented MFW message %d\n", i);
 			rc = -EINVAL;
 		}
 	}
@@ -1316,24 +1806,23 @@ qed_mcp_send_drv_version(struct qed_hwfn *p_hwfn,
 			 struct qed_ptt *p_ptt,
 			 struct qed_mcp_drv_version *p_ver)
 {
-	struct drv_version_stc *p_drv_version;
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data union_data;
+	struct drv_version_stc drv_version;
 	__be32 val;
 	u32 i;
 	int rc;
 
-	p_drv_version = &union_data.drv_version;
-	p_drv_version->version = p_ver->version;
-
+	memset(&drv_version, 0, sizeof(drv_version));
+	drv_version.version = p_ver->version;
 	for (i = 0; i < (MCP_DRV_VER_STR_SIZE - 4) / sizeof(u32); i++) {
 		val = cpu_to_be32(*((u32 *)&p_ver->name[i * sizeof(u32)]));
-		*(__be32 *)&p_drv_version->name[i * sizeof(u32)] = val;
+		*(__be32 *)&drv_version.name[i * sizeof(u32)] = val;
 	}
 
 	memset(&mb_params, 0, sizeof(mb_params));
 	mb_params.cmd = DRV_MSG_CODE_SET_VERSION;
-	mb_params.p_data_src = &union_data;
+	mb_params.p_data_src = &drv_version;
+	mb_params.data_src_size = sizeof(drv_version);
 	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 	if (rc)
 		DP_ERR(p_hwfn, "MCP response failure, aborting\n");
@@ -1450,7 +1939,7 @@ int qed_mcp_ov_update_mac(struct qed_hwfn *p_hwfn,
 			  struct qed_ptt *p_ptt, u8 *mac)
 {
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data union_data;
+	u32 mfw_mac[2];
 	int rc;
 
 	memset(&mb_params, 0, sizeof(mb_params));
@@ -1458,8 +1947,17 @@ int qed_mcp_ov_update_mac(struct qed_hwfn *p_hwfn,
 	mb_params.param = DRV_MSG_CODE_VMAC_TYPE_MAC <<
 			  DRV_MSG_CODE_VMAC_TYPE_SHIFT;
 	mb_params.param |= MCP_PF_ID(p_hwfn);
-	ether_addr_copy(&union_data.raw_data[0], mac);
-	mb_params.p_data_src = &union_data;
+
+	/* MCP is BE, and on LE platforms PCI would swap access to SHMEM
+	 * in 32-bit granularity.
+	 * So the MAC has to be set in native order [and not byte order],
+	 * otherwise it would be read incorrectly by MFW after swap.
+	 */
+	mfw_mac[0] = mac[0] << 24 | mac[1] << 16 | mac[2] << 8 | mac[3];
+	mfw_mac[1] = mac[4] << 24 | mac[5] << 16;
+
+	mb_params.p_data_src = (u8 *)mfw_mac;
+	mb_params.data_src_size = 8;
 	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 	if (rc)
 		DP_ERR(p_hwfn, "Failed to send mac address, rc = %d\n", rc);
@@ -1724,52 +2222,396 @@ int qed_mcp_bist_nvm_test_get_image_att(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-#define QED_RESC_ALLOC_VERSION_MAJOR    1
+static enum resource_id_enum qed_mcp_get_mfw_res_id(enum qed_resources res_id)
+{
+	enum resource_id_enum mfw_res_id = RESOURCE_NUM_INVALID;
+
+	switch (res_id) {
+	case QED_SB:
+		mfw_res_id = RESOURCE_NUM_SB_E;
+		break;
+	case QED_L2_QUEUE:
+		mfw_res_id = RESOURCE_NUM_L2_QUEUE_E;
+		break;
+	case QED_VPORT:
+		mfw_res_id = RESOURCE_NUM_VPORT_E;
+		break;
+	case QED_RSS_ENG:
+		mfw_res_id = RESOURCE_NUM_RSS_ENGINES_E;
+		break;
+	case QED_PQ:
+		mfw_res_id = RESOURCE_NUM_PQ_E;
+		break;
+	case QED_RL:
+		mfw_res_id = RESOURCE_NUM_RL_E;
+		break;
+	case QED_MAC:
+	case QED_VLAN:
+		/* Each VFC resource can accommodate both a MAC and a VLAN */
+		mfw_res_id = RESOURCE_VFC_FILTER_E;
+		break;
+	case QED_ILT:
+		mfw_res_id = RESOURCE_ILT_E;
+		break;
+	case QED_LL2_QUEUE:
+		mfw_res_id = RESOURCE_LL2_QUEUE_E;
+		break;
+	case QED_RDMA_CNQ_RAM:
+	case QED_CMDQS_CQS:
+		/* CNQ/CMDQS are the same resource */
+		mfw_res_id = RESOURCE_CQS_E;
+		break;
+	case QED_RDMA_STATS_QUEUE:
+		mfw_res_id = RESOURCE_RDMA_STATS_QUEUE_E;
+		break;
+	case QED_BDQ:
+		mfw_res_id = RESOURCE_BDQ_E;
+		break;
+	default:
+		break;
+	}
+
+	return mfw_res_id;
+}
+
+#define QED_RESC_ALLOC_VERSION_MAJOR    2
 #define QED_RESC_ALLOC_VERSION_MINOR    0
 #define QED_RESC_ALLOC_VERSION				     \
 	((QED_RESC_ALLOC_VERSION_MAJOR <<		     \
 	  DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_SHIFT) | \
 	 (QED_RESC_ALLOC_VERSION_MINOR <<		     \
 	  DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR_SHIFT))
-int qed_mcp_get_resc_info(struct qed_hwfn *p_hwfn,
-			  struct qed_ptt *p_ptt,
-			  struct resource_info *p_resc_info,
-			  u32 *p_mcp_resp, u32 *p_mcp_param)
+
+struct qed_resc_alloc_in_params {
+	u32 cmd;
+	enum qed_resources res_id;
+	u32 resc_max_val;
+};
+
+struct qed_resc_alloc_out_params {
+	u32 mcp_resp;
+	u32 mcp_param;
+	u32 resc_num;
+	u32 resc_start;
+	u32 vf_resc_num;
+	u32 vf_resc_start;
+	u32 flags;
+};
+
+static int
+qed_mcp_resc_allocation_msg(struct qed_hwfn *p_hwfn,
+			    struct qed_ptt *p_ptt,
+			    struct qed_resc_alloc_in_params *p_in_params,
+			    struct qed_resc_alloc_out_params *p_out_params)
 {
 	struct qed_mcp_mb_params mb_params;
-	union drv_union_data union_data;
+	struct resource_info mfw_resc_info;
 	int rc;
 
+	memset(&mfw_resc_info, 0, sizeof(mfw_resc_info));
+
+	mfw_resc_info.res_id = qed_mcp_get_mfw_res_id(p_in_params->res_id);
+	if (mfw_resc_info.res_id == RESOURCE_NUM_INVALID) {
+		DP_ERR(p_hwfn,
+		       "Failed to match resource %d [%s] with the MFW resources\n",
+		       p_in_params->res_id,
+		       qed_hw_get_resc_name(p_in_params->res_id));
+		return -EINVAL;
+	}
+
+	switch (p_in_params->cmd) {
+	case DRV_MSG_SET_RESOURCE_VALUE_MSG:
+		mfw_resc_info.size = p_in_params->resc_max_val;
+		/* Fallthrough */
+	case DRV_MSG_GET_RESOURCE_ALLOC_MSG:
+		break;
+	default:
+		DP_ERR(p_hwfn, "Unexpected resource alloc command [0x%08x]\n",
+		       p_in_params->cmd);
+		return -EINVAL;
+	}
+
 	memset(&mb_params, 0, sizeof(mb_params));
-	memset(&union_data, 0, sizeof(union_data));
-	mb_params.cmd = DRV_MSG_GET_RESOURCE_ALLOC_MSG;
+	mb_params.cmd = p_in_params->cmd;
 	mb_params.param = QED_RESC_ALLOC_VERSION;
+	mb_params.p_data_src = &mfw_resc_info;
+	mb_params.data_src_size = sizeof(mfw_resc_info);
+	mb_params.p_data_dst = mb_params.p_data_src;
+	mb_params.data_dst_size = mb_params.data_src_size;
 
-	/* Need to have a sufficient large struct, as the cmd_and_union
-	 * is going to do memcpy from and to it.
-	 */
-	memcpy(&union_data.resource, p_resc_info, sizeof(*p_resc_info));
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_SP,
+		   "Resource message request: cmd 0x%08x, res_id %d [%s], hsi_version %d.%d, val 0x%x\n",
+		   p_in_params->cmd,
+		   p_in_params->res_id,
+		   qed_hw_get_resc_name(p_in_params->res_id),
+		   QED_MFW_GET_FIELD(mb_params.param,
+				     DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR),
+		   QED_MFW_GET_FIELD(mb_params.param,
+				     DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR),
+		   p_in_params->resc_max_val);
 
-	mb_params.p_data_src = &union_data;
-	mb_params.p_data_dst = &union_data;
 	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
 	if (rc)
 		return rc;
 
-	/* Copy the data back */
-	memcpy(p_resc_info, &union_data.resource, sizeof(*p_resc_info));
-	*p_mcp_resp = mb_params.mcp_resp;
-	*p_mcp_param = mb_params.mcp_param;
+	p_out_params->mcp_resp = mb_params.mcp_resp;
+	p_out_params->mcp_param = mb_params.mcp_param;
+	p_out_params->resc_num = mfw_resc_info.size;
+	p_out_params->resc_start = mfw_resc_info.offset;
+	p_out_params->vf_resc_num = mfw_resc_info.vf_size;
+	p_out_params->vf_resc_start = mfw_resc_info.vf_offset;
+	p_out_params->flags = mfw_resc_info.flags;
+
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_SP,
+		   "Resource message response: mfw_hsi_version %d.%d, num 0x%x, start 0x%x, vf_num 0x%x, vf_start 0x%x, flags 0x%08x\n",
+		   QED_MFW_GET_FIELD(p_out_params->mcp_param,
+				     FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR),
+		   QED_MFW_GET_FIELD(p_out_params->mcp_param,
+				     FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR),
+		   p_out_params->resc_num,
+		   p_out_params->resc_start,
+		   p_out_params->vf_resc_num,
+		   p_out_params->vf_resc_start, p_out_params->flags);
+
+	return 0;
+}
+
+int
+qed_mcp_set_resc_max_val(struct qed_hwfn *p_hwfn,
+			 struct qed_ptt *p_ptt,
+			 enum qed_resources res_id,
+			 u32 resc_max_val, u32 *p_mcp_resp)
+{
+	struct qed_resc_alloc_out_params out_params;
+	struct qed_resc_alloc_in_params in_params;
+	int rc;
+
+	memset(&in_params, 0, sizeof(in_params));
+	in_params.cmd = DRV_MSG_SET_RESOURCE_VALUE_MSG;
+	in_params.res_id = res_id;
+	in_params.resc_max_val = resc_max_val;
+	memset(&out_params, 0, sizeof(out_params));
+	rc = qed_mcp_resc_allocation_msg(p_hwfn, p_ptt, &in_params,
+					 &out_params);
+	if (rc)
+		return rc;
+
+	*p_mcp_resp = out_params.mcp_resp;
+
+	return 0;
+}
+
+int
+qed_mcp_get_resc_info(struct qed_hwfn *p_hwfn,
+		      struct qed_ptt *p_ptt,
+		      enum qed_resources res_id,
+		      u32 *p_mcp_resp, u32 *p_resc_num, u32 *p_resc_start)
+{
+	struct qed_resc_alloc_out_params out_params;
+	struct qed_resc_alloc_in_params in_params;
+	int rc;
+
+	memset(&in_params, 0, sizeof(in_params));
+	in_params.cmd = DRV_MSG_GET_RESOURCE_ALLOC_MSG;
+	in_params.res_id = res_id;
+	memset(&out_params, 0, sizeof(out_params));
+	rc = qed_mcp_resc_allocation_msg(p_hwfn, p_ptt, &in_params,
+					 &out_params);
+	if (rc)
+		return rc;
+
+	*p_mcp_resp = out_params.mcp_resp;
+
+	if (*p_mcp_resp == FW_MSG_CODE_RESOURCE_ALLOC_OK) {
+		*p_resc_num = out_params.resc_num;
+		*p_resc_start = out_params.resc_start;
+	}
+
+	return 0;
+}
+
+int qed_mcp_initiate_pf_flr(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	u32 mcp_resp, mcp_param;
+
+	return qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_INITIATE_PF_FLR, 0,
+			   &mcp_resp, &mcp_param);
+}
+
+static int qed_mcp_resource_cmd(struct qed_hwfn *p_hwfn,
+				struct qed_ptt *p_ptt,
+				u32 param, u32 *p_mcp_resp, u32 *p_mcp_param)
+{
+	int rc;
+
+	rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_RESOURCE_CMD, param,
+			 p_mcp_resp, p_mcp_param);
+	if (rc)
+		return rc;
+
+	if (*p_mcp_resp == FW_MSG_CODE_UNSUPPORTED) {
+		DP_INFO(p_hwfn,
+			"The resource command is unsupported by the MFW\n");
+		return -EINVAL;
+	}
+
+	if (*p_mcp_param == RESOURCE_OPCODE_UNKNOWN_CMD) {
+		u8 opcode = QED_MFW_GET_FIELD(param, RESOURCE_CMD_REQ_OPCODE);
+
+		DP_NOTICE(p_hwfn,
+			  "The resource command is unknown to the MFW [param 0x%08x, opcode %d]\n",
+			  param, opcode);
+		return -EINVAL;
+	}
+
+	return rc;
+}
+
+int
+__qed_mcp_resc_lock(struct qed_hwfn *p_hwfn,
+		    struct qed_ptt *p_ptt,
+		    struct qed_resc_lock_params *p_params)
+{
+	u32 param = 0, mcp_resp, mcp_param;
+	u8 opcode;
+	int rc;
+
+	switch (p_params->timeout) {
+	case QED_MCP_RESC_LOCK_TO_DEFAULT:
+		opcode = RESOURCE_OPCODE_REQ;
+		p_params->timeout = 0;
+		break;
+	case QED_MCP_RESC_LOCK_TO_NONE:
+		opcode = RESOURCE_OPCODE_REQ_WO_AGING;
+		p_params->timeout = 0;
+		break;
+	default:
+		opcode = RESOURCE_OPCODE_REQ_W_AGING;
+		break;
+	}
+
+	QED_MFW_SET_FIELD(param, RESOURCE_CMD_REQ_RESC, p_params->resource);
+	QED_MFW_SET_FIELD(param, RESOURCE_CMD_REQ_OPCODE, opcode);
+	QED_MFW_SET_FIELD(param, RESOURCE_CMD_REQ_AGE, p_params->timeout);
+
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_SP,
+		   "Resource lock request: param 0x%08x [age %d, opcode %d, resource %d]\n",
+		   param, p_params->timeout, opcode, p_params->resource);
+
+	/* Attempt to acquire the resource */
+	rc = qed_mcp_resource_cmd(p_hwfn, p_ptt, param, &mcp_resp, &mcp_param);
+	if (rc)
+		return rc;
+
+	/* Analyze the response */
+	p_params->owner = QED_MFW_GET_FIELD(mcp_param, RESOURCE_CMD_RSP_OWNER);
+	opcode = QED_MFW_GET_FIELD(mcp_param, RESOURCE_CMD_RSP_OPCODE);
 
 	DP_VERBOSE(p_hwfn,
 		   QED_MSG_SP,
-		   "MFW resource_info: version 0x%x, res_id 0x%x, size 0x%x, offset 0x%x, vf_size 0x%x, vf_offset 0x%x, flags 0x%x\n",
-		   *p_mcp_param,
-		   p_resc_info->res_id,
-		   p_resc_info->size,
-		   p_resc_info->offset,
-		   p_resc_info->vf_size,
-		   p_resc_info->vf_offset, p_resc_info->flags);
+		   "Resource lock response: mcp_param 0x%08x [opcode %d, owner %d]\n",
+		   mcp_param, opcode, p_params->owner);
+
+	switch (opcode) {
+	case RESOURCE_OPCODE_GNT:
+		p_params->b_granted = true;
+		break;
+	case RESOURCE_OPCODE_BUSY:
+		p_params->b_granted = false;
+		break;
+	default:
+		DP_NOTICE(p_hwfn,
+			  "Unexpected opcode in resource lock response [mcp_param 0x%08x, opcode %d]\n",
+			  mcp_param, opcode);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int
+qed_mcp_resc_lock(struct qed_hwfn *p_hwfn,
+		  struct qed_ptt *p_ptt, struct qed_resc_lock_params *p_params)
+{
+	u32 retry_cnt = 0;
+	int rc;
+
+	do {
+		/* No need for an interval before the first iteration */
+		if (retry_cnt) {
+			if (p_params->sleep_b4_retry) {
+				u16 retry_interval_in_ms =
+				    DIV_ROUND_UP(p_params->retry_interval,
+						 1000);
+
+				msleep(retry_interval_in_ms);
+			} else {
+				udelay(p_params->retry_interval);
+			}
+		}
+
+		rc = __qed_mcp_resc_lock(p_hwfn, p_ptt, p_params);
+		if (rc)
+			return rc;
+
+		if (p_params->b_granted)
+			break;
+	} while (retry_cnt++ < p_params->retry_num);
+
+	return 0;
+}
+
+int
+qed_mcp_resc_unlock(struct qed_hwfn *p_hwfn,
+		    struct qed_ptt *p_ptt,
+		    struct qed_resc_unlock_params *p_params)
+{
+	u32 param = 0, mcp_resp, mcp_param;
+	u8 opcode;
+	int rc;
+
+	opcode = p_params->b_force ? RESOURCE_OPCODE_FORCE_RELEASE
+				   : RESOURCE_OPCODE_RELEASE;
+	QED_MFW_SET_FIELD(param, RESOURCE_CMD_REQ_RESC, p_params->resource);
+	QED_MFW_SET_FIELD(param, RESOURCE_CMD_REQ_OPCODE, opcode);
+
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "Resource unlock request: param 0x%08x [opcode %d, resource %d]\n",
+		   param, opcode, p_params->resource);
+
+	/* Attempt to release the resource */
+	rc = qed_mcp_resource_cmd(p_hwfn, p_ptt, param, &mcp_resp, &mcp_param);
+	if (rc)
+		return rc;
+
+	/* Analyze the response */
+	opcode = QED_MFW_GET_FIELD(mcp_param, RESOURCE_CMD_RSP_OPCODE);
+
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "Resource unlock response: mcp_param 0x%08x [opcode %d]\n",
+		   mcp_param, opcode);
+
+	switch (opcode) {
+	case RESOURCE_OPCODE_RELEASED_PREVIOUS:
+		DP_INFO(p_hwfn,
+			"Resource unlock request for an already released resource [%d]\n",
+			p_params->resource);
+		/* Fallthrough */
+	case RESOURCE_OPCODE_RELEASED:
+		p_params->b_released = true;
+		break;
+	case RESOURCE_OPCODE_WRONG_OWNER:
+		p_params->b_released = false;
+		break;
+	default:
+		DP_NOTICE(p_hwfn,
+			  "Unexpected opcode in resource unlock response [mcp_param 0x%08x, opcode %d]\n",
+			  mcp_param, opcode);
+		return -EINVAL;
+	}
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index 368e88de146c..ac7d406be1ed 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -39,6 +39,7 @@
 #include <linux/spinlock.h>
 #include <linux/qed/qed_fcoe_if.h>
 #include "qed_hsi.h"
+#include "qed_dev_api.h"
 
 struct qed_mcp_link_speed_params {
 	bool    autoneg;
@@ -479,14 +480,18 @@ int qed_mcp_bist_nvm_test_get_image_att(struct qed_hwfn *p_hwfn,
 					    rel_pfid)
 #define MCP_PF_ID(p_hwfn) MCP_PF_ID_BY_REL(p_hwfn, (p_hwfn)->rel_pf_id)
 
-/* TODO - this is only correct as long as only BB is supported, and
- * no port-swapping is implemented; Afterwards we'll need to fix it.
- */
-#define MFW_PORT(_p_hwfn)       ((_p_hwfn)->abs_pf_id %	\
-				 ((_p_hwfn)->cdev->num_ports_in_engines * 2))
+#define MFW_PORT(_p_hwfn)       ((_p_hwfn)->abs_pf_id %			  \
+				 ((_p_hwfn)->cdev->num_ports_in_engines * \
+				  qed_device_num_engines((_p_hwfn)->cdev)))
+
 struct qed_mcp_info {
-	/* Spinlock used for protecting the access to the MFW mailbox */
-	spinlock_t				lock;
+	/* List for mailbox commands which were sent and wait for a response */
+	struct list_head			cmd_list;
+
+	/* Spinlock used for protecting the access to the mailbox commands list
+	 * and the sending of the commands.
+	 */
+	spinlock_t				cmd_lock;
 
 	/* Spinlock used for syncing SW link-changes and link-changes
 	 * originating from attention context.
@@ -506,14 +511,16 @@ struct qed_mcp_info {
 	u8					*mfw_mb_cur;
 	u8					*mfw_mb_shadow;
 	u16					mfw_mb_length;
-	u16					mcp_hist;
+	u32					mcp_hist;
 };
 
 struct qed_mcp_mb_params {
 	u32			cmd;
 	u32			param;
-	union drv_union_data	*p_data_src;
-	union drv_union_data	*p_data_dst;
+	void			*p_data_src;
+	u8			data_src_size;
+	void			*p_data_dst;
+	u8			data_dst_size;
 	u32			mcp_resp;
 	u32			mcp_param;
 };
@@ -564,27 +571,55 @@ int qed_mcp_free(struct qed_hwfn *p_hwfn);
 int qed_mcp_handle_events(struct qed_hwfn *p_hwfn,
 			  struct qed_ptt *p_ptt);
 
+enum qed_drv_role {
+	QED_DRV_ROLE_OS,
+	QED_DRV_ROLE_KDUMP,
+};
+
+struct qed_load_req_params {
+	/* Input params */
+	enum qed_drv_role drv_role;
+	u8 timeout_val;
+	bool avoid_eng_reset;
+	enum qed_override_force_load override_force_load;
+
+	/* Output params */
+	u32 load_code;
+};
+
 /**
- * @brief Sends a LOAD_REQ to the MFW, and in case operation
- *        succeed, returns whether this PF is the first on the
- *        chip/engine/port or function. This function should be
- *        called when driver is ready to accept MFW events after
- *        Storms initializations are done.
+ * @brief Sends a LOAD_REQ to the MFW, and in case the operation succeeds,
+ *        returns whether this PF is the first on the engine/port or function.
  *
- * @param p_hwfn       - hw function
- * @param p_ptt        - PTT required for register access
- * @param p_load_code  - The MCP response param containing one
- *      of the following:
- *      FW_MSG_CODE_DRV_LOAD_ENGINE
- *      FW_MSG_CODE_DRV_LOAD_PORT
- *      FW_MSG_CODE_DRV_LOAD_FUNCTION
- * @return int -
- *      0 - Operation was successul.
- *      -EBUSY - Operation failed
+ * @param p_hwfn
+ * @param p_ptt
+ * @param p_params
+ *
+ * @return int - 0 - Operation was successful.
  */
 int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
 		     struct qed_ptt *p_ptt,
-		     u32 *p_load_code);
+		     struct qed_load_req_params *p_params);
+
+/**
+ * @brief Sends a UNLOAD_REQ message to the MFW
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ *
+ * @return int - 0 - Operation was successful.
+ */
+int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+
+/**
+ * @brief Sends a UNLOAD_DONE message to the MFW
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ *
+ * @return int - 0 - Operation was successful.
+ */
+int qed_mcp_unload_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
 
 /**
  * @brief Read the MFW mailbox into Current buffer.
@@ -708,6 +743,41 @@ int qed_mcp_mask_parities(struct qed_hwfn *p_hwfn,
 			  struct qed_ptt *p_ptt, u32 mask_parities);
 
 /**
+ * @brief - Sets the MFW's max value for the given resource
+ *
+ *  @param p_hwfn
+ *  @param p_ptt
+ *  @param res_id
+ *  @param resc_max_val
+ *  @param p_mcp_resp
+ *
+ * @return int - 0 - operation was successful.
+ */
+int
+qed_mcp_set_resc_max_val(struct qed_hwfn *p_hwfn,
+			 struct qed_ptt *p_ptt,
+			 enum qed_resources res_id,
+			 u32 resc_max_val, u32 *p_mcp_resp);
+
+/**
+ * @brief - Gets the MFW allocation info for the given resource
+ *
+ *  @param p_hwfn
+ *  @param p_ptt
+ *  @param res_id
+ *  @param p_mcp_resp
+ *  @param p_resc_num
+ *  @param p_resc_start
+ *
+ * @return int - 0 - operation was successful.
+ */
+int
+qed_mcp_get_resc_info(struct qed_hwfn *p_hwfn,
+		      struct qed_ptt *p_ptt,
+		      enum qed_resources res_id,
+		      u32 *p_mcp_resp, u32 *p_resc_num, u32 *p_resc_start);
+
+/**
  * @brief Send eswitch mode to MFW
  *
  *  @param p_hwfn
@@ -720,19 +790,86 @@ int qed_mcp_ov_update_eswitch(struct qed_hwfn *p_hwfn,
 			      struct qed_ptt *p_ptt,
 			      enum qed_ov_eswitch eswitch);
 
+#define QED_MCP_RESC_LOCK_MIN_VAL       RESOURCE_DUMP
+#define QED_MCP_RESC_LOCK_MAX_VAL       31
+
+enum qed_resc_lock {
+	QED_RESC_LOCK_DBG_DUMP = QED_MCP_RESC_LOCK_MIN_VAL,
+	QED_RESC_LOCK_RESC_ALLOC = QED_MCP_RESC_LOCK_MAX_VAL
+};
+
 /**
- * @brief - Gets the MFW allocation info for the given resource
+ * @brief - Initiates PF FLR
  *
  *  @param p_hwfn
  *  @param p_ptt
- *  @param p_resc_info - descriptor of requested resource
- *  @param p_mcp_resp
- *  @param p_mcp_param
  *
  * @return int - 0 - operation was successful.
  */
-int qed_mcp_get_resc_info(struct qed_hwfn *p_hwfn,
-			  struct qed_ptt *p_ptt,
-			  struct resource_info *p_resc_info,
-			  u32 *p_mcp_resp, u32 *p_mcp_param);
+int qed_mcp_initiate_pf_flr(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+struct qed_resc_lock_params {
+	/* Resource number [valid values are 0..31] */
+	u8 resource;
+
+	/* Lock timeout value in seconds [default, none or 1..254] */
+	u8 timeout;
+#define QED_MCP_RESC_LOCK_TO_DEFAULT    0
+#define QED_MCP_RESC_LOCK_TO_NONE       255
+
+	/* Number of times to retry locking */
+	u8 retry_num;
+
+	/* The interval in usec between retries */
+	u16 retry_interval;
+
+	/* Use sleep or delay between retries */
+	bool sleep_b4_retry;
+
+	/* Will be set as true if the resource is free and granted */
+	bool b_granted;
+
+	/* Will be filled with the resource owner.
+	 * [0..15 = PF0-15, 16 = MFW]
+	 */
+	u8 owner;
+};
+
+/**
+ * @brief Acquires MFW generic resource lock
+ *
+ *  @param p_hwfn
+ *  @param p_ptt
+ *  @param p_params
+ *
+ * @return int - 0 - operation was successful.
+ */
+int
+qed_mcp_resc_lock(struct qed_hwfn *p_hwfn,
+		  struct qed_ptt *p_ptt, struct qed_resc_lock_params *p_params);
+
+struct qed_resc_unlock_params {
+	/* Resource number [valid values are 0..31] */
+	u8 resource;
+
+	/* Allow to release a resource even if belongs to another PF */
+	bool b_force;
+
+	/* Will be set as true if the resource is released */
+	bool b_released;
+};
+
+/**
+ * @brief Releases MFW generic resource lock
+ *
+ *  @param p_hwfn
+ *  @param p_ptt
+ *  @param p_params
+ *
+ * @return int - 0 - operation was successful.
+ */
+int
+qed_mcp_resc_unlock(struct qed_hwfn *p_hwfn,
+		    struct qed_ptt *p_ptt,
+		    struct qed_resc_unlock_params *p_params);
+
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ptp.c b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
index d27aa85da23c..80c9c0b172dd 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ptp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
@@ -262,12 +262,20 @@ static int qed_ptp_hw_enable(struct qed_dev *cdev)
 	qed_wr(p_hwfn, p_ptt, NIG_REG_TS_OUTPUT_ENABLE_PDA, 0x1);
 
 	/* Pause free running counter */
-	qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 2);
+	if (QED_IS_BB_B0(p_hwfn->cdev))
+		qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 2);
+	if (QED_IS_AH(p_hwfn->cdev))
+		qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREECNT_UPDATE_K2, 2);
 
 	qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREE_CNT_VALUE_LSB, 0);
 	qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREE_CNT_VALUE_MSB, 0);
 	/* Resume free running counter */
-	qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 4);
+	if (QED_IS_BB_B0(p_hwfn->cdev))
+		qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 4);
+	if (QED_IS_AH(p_hwfn->cdev)) {
+		qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREECNT_UPDATE_K2, 4);
+		qed_wr(p_hwfn, p_ptt, NIG_REG_PTP_LATCH_OSTS_PKT_TIME, 1);
+	}
 
 	/* Disable drift register */
 	qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_DRIFT_CNTR_CONF, 0x0);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
index d59d9df60cd2..6d4ac7e2ee83 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
@@ -160,13 +160,13 @@
 	0x2e0704UL
 #define  CCFC_REG_STRONG_ENABLE_PF \
 	0x2e0708UL
-#define  PGLUE_B_REG_PGL_ADDR_88_F0 \
+#define  PGLUE_B_REG_PGL_ADDR_88_F0_BB \
 	0x2aa404UL
-#define  PGLUE_B_REG_PGL_ADDR_8C_F0 \
+#define  PGLUE_B_REG_PGL_ADDR_8C_F0_BB \
 	0x2aa408UL
-#define  PGLUE_B_REG_PGL_ADDR_90_F0 \
+#define  PGLUE_B_REG_PGL_ADDR_90_F0_BB \
 	0x2aa40cUL
-#define  PGLUE_B_REG_PGL_ADDR_94_F0 \
+#define  PGLUE_B_REG_PGL_ADDR_94_F0_BB \
 	0x2aa410UL
 #define  PGLUE_B_REG_WAS_ERROR_PF_31_0_CLR \
 	0x2aa138UL
@@ -356,6 +356,10 @@
 	0x238804UL
 #define  RDIF_REG_STOP_ON_ERROR \
 	0x300040UL
+#define RDIF_REG_DEBUG_ERROR_INFO \
+	0x300400UL
+#define RDIF_REG_DEBUG_ERROR_INFO_SIZE \
+	64
 #define  SRC_REG_SOFT_RST \
 	0x23874cUL
 #define  TCFC_REG_ACTIVITY_COUNTER \
@@ -370,6 +374,10 @@
 	0x1700004UL
 #define  TDIF_REG_STOP_ON_ERROR \
 	0x310040UL
+#define TDIF_REG_DEBUG_ERROR_INFO \
+	0x310400UL
+#define TDIF_REG_DEBUG_ERROR_INFO_SIZE \
+	64
 #define  UCM_REG_INIT \
 	0x1280000UL
 #define  UMAC_REG_IPG_HD_BKP_CNTL_BB_B0 \
@@ -1236,6 +1244,26 @@
 	0x1901534UL
 #define USEM_REG_DBG_FORCE_FRAME \
 	0x1901538UL
+#define NWS_REG_DBG_SELECT \
+	0x700128UL
+#define NWS_REG_DBG_DWORD_ENABLE \
+	0x70012cUL
+#define NWS_REG_DBG_SHIFT \
+	0x700130UL
+#define NWS_REG_DBG_FORCE_VALID	\
+	0x700134UL
+#define NWS_REG_DBG_FORCE_FRAME	\
+	0x700138UL
+#define MS_REG_DBG_SELECT \
+	0x6a0228UL
+#define MS_REG_DBG_DWORD_ENABLE \
+	0x6a022cUL
+#define MS_REG_DBG_SHIFT \
+	0x6a0230UL
+#define MS_REG_DBG_FORCE_VALID \
+	0x6a0234UL
+#define MS_REG_DBG_FORCE_FRAME \
+	0x6a0238UL
 #define PCIE_REG_DBG_COMMON_SELECT \
 	0x054398UL
 #define PCIE_REG_DBG_COMMON_DWORD_ENABLE \
@@ -1448,6 +1476,8 @@
 	0x000b48UL
 #define RSS_REG_RSS_RAM_DATA \
 	0x238c20UL
+#define RSS_REG_RSS_RAM_DATA_SIZE \
+	4
 #define MISC_REG_BLOCK_256B_EN \
 	0x008c14UL
 #define NWS_REG_NWS_CMU	\
@@ -1520,4 +1550,13 @@
 #define NIG_REG_TIMESYNC_GEN_REG_BB 0x500d00UL
 #define NIG_REG_TSGEN_FREE_CNT_VALUE_LSB 0x5088a8UL
 #define NIG_REG_TSGEN_FREE_CNT_VALUE_MSB 0x5088acUL
+#define NIG_REG_PTP_LATCH_OSTS_PKT_TIME 0x509040UL
+
+#define PGLUE_B_REG_PGL_ADDR_E8_F0_K2 0x2aaf98UL
+#define PGLUE_B_REG_PGL_ADDR_EC_F0_K2 0x2aaf9cUL
+#define PGLUE_B_REG_PGL_ADDR_F0_F0_K2 0x2aafa0UL
+#define PGLUE_B_REG_PGL_ADDR_F4_F0_K2 0x2aafa4UL
+#define NIG_REG_TSGEN_FREECNT_UPDATE_K2 0x509008UL
+#define CNIG_REG_NIG_PORT0_CONF_K2 0x218200UL
+
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index d9ff6b28591c..b8c811f95205 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -66,13 +66,27 @@
 #include "qed_roce.h"
 #include "qed_ll2.h"
 
-void qed_async_roce_event(struct qed_hwfn *p_hwfn,
-			  struct event_ring_entry *p_eqe)
+static void qed_roce_free_real_icid(struct qed_hwfn *p_hwfn, u16 icid);
+
+void qed_roce_async_event(struct qed_hwfn *p_hwfn,
+			  u8 fw_event_code, union rdma_eqe_data *rdma_data)
 {
-	struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
+	if (fw_event_code == ROCE_ASYNC_EVENT_DESTROY_QP_DONE) {
+		u16 icid =
+		    (u16)le32_to_cpu(rdma_data->rdma_destroy_qp_data.cid);
+
+		/* icid release in this async event can occur only if the icid
+		 * was offloaded to the FW. In case it wasn't offloaded this is
+		 * handled in qed_roce_sp_destroy_qp.
+		 */
+		qed_roce_free_real_icid(p_hwfn, icid);
+	} else {
+		struct qed_rdma_events *events = &p_hwfn->p_rdma_info->events;
 
-	p_rdma_info->events.affiliated_event(p_rdma_info->events.context,
-					     p_eqe->opcode, &p_eqe->data);
+		events->affiliated_event(p_hwfn->p_rdma_info->events.context,
+					 fw_event_code,
+					 &rdma_data->async_handle);
+	}
 }
 
 static int qed_rdma_bmap_alloc(struct qed_hwfn *p_hwfn,
@@ -113,6 +127,15 @@ static int qed_rdma_bmap_alloc_id(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
+static void qed_bmap_set_id(struct qed_hwfn *p_hwfn,
+			    struct qed_bmap *bmap, u32 id_num)
+{
+	if (id_num >= bmap->max_count)
+		return;
+
+	__set_bit(id_num, bmap->bitmap);
+}
+
 static void qed_bmap_release_id(struct qed_hwfn *p_hwfn,
 				struct qed_bmap *bmap, u32 id_num)
 {
@@ -129,6 +152,15 @@ static void qed_bmap_release_id(struct qed_hwfn *p_hwfn,
 	}
 }
 
+static int qed_bmap_test_id(struct qed_hwfn *p_hwfn,
+			    struct qed_bmap *bmap, u32 id_num)
+{
+	if (id_num >= bmap->max_count)
+		return -1;
+
+	return test_bit(id_num, bmap->bitmap);
+}
+
 static u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id)
 {
 	/* First sb id for RoCE is after all the l2 sb */
@@ -170,7 +202,8 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
 	/* Queue zone lines are shared between RoCE and L2 in such a way that
 	 * they can be used by each without obstructing the other.
 	 */
-	p_rdma_info->queue_zone_base = (u16)FEAT_NUM(p_hwfn, QED_L2_QUEUE);
+	p_rdma_info->queue_zone_base = (u16)RESC_START(p_hwfn, QED_L2_QUEUE);
+	p_rdma_info->max_queue_zones = (u16)RESC_NUM(p_hwfn, QED_L2_QUEUE);
 
 	/* Allocate a struct with device params and fill it */
 	p_rdma_info->dev = kzalloc(sizeof(*p_rdma_info->dev), GFP_KERNEL);
@@ -248,9 +281,18 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
 		goto free_tid_map;
 	}
 
+	/* Allocate bitmap for cids used for responders/requesters. */
+	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->real_cid_map, num_cons);
+	if (rc) {
+		DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
+			   "Failed to allocate real cid bitmap, rc = %d\n", rc);
+		goto free_cid_map;
+	}
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Allocation successful\n");
 	return 0;
 
+free_cid_map:
+	kfree(p_rdma_info->cid_map.bitmap);
 free_tid_map:
 	kfree(p_rdma_info->tid_map.bitmap);
 free_toggle_map:
@@ -273,7 +315,22 @@ free_rdma_info:
 
 static void qed_rdma_resc_free(struct qed_hwfn *p_hwfn)
 {
+	struct qed_bmap *rcid_map = &p_hwfn->p_rdma_info->real_cid_map;
 	struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
+	int wait_count = 0;
+
+	/* when destroying a_RoCE QP the control is returned to the user after
+	 * the synchronous part. The asynchronous part may take a little longer.
+	 * We delay for a short while if an async destroy QP is still expected.
+	 * Beyond the added delay we clear the bitmap anyway.
+	 */
+	while (bitmap_weight(rcid_map->bitmap, rcid_map->max_count)) {
+		msleep(100);
+		if (wait_count++ > 20) {
+			DP_NOTICE(p_hwfn, "cid bitmap wait timed out\n");
+			break;
+		}
+	}
 
 	kfree(p_rdma_info->cid_map.bitmap);
 	kfree(p_rdma_info->tid_map.bitmap);
@@ -724,6 +781,14 @@ static void qed_rdma_cnq_prod_update(void *rdma_cxt, u8 qz_offset, u16 prod)
 	u32 addr;
 
 	p_hwfn = (struct qed_hwfn *)rdma_cxt;
+
+	if (qz_offset > p_hwfn->p_rdma_info->max_queue_zones) {
+		DP_NOTICE(p_hwfn,
+			  "queue zone offset %d is too large (max is %d)\n",
+			  qz_offset, p_hwfn->p_rdma_info->max_queue_zones);
+		return;
+	}
+
 	qz_num = p_hwfn->p_rdma_info->queue_zone_base + qz_offset;
 	addr = GTT_BAR0_MAP_REG_USDM_RAM +
 	       USTORM_COMMON_QUEUE_CONS_OFFSET(qz_num);
@@ -1080,6 +1145,14 @@ static enum roce_flavor qed_roce_mode_to_flavor(enum roce_mode roce_mode)
 	return flavor;
 }
 
+void qed_roce_free_cid_pair(struct qed_hwfn *p_hwfn, u16 cid)
+{
+	spin_lock_bh(&p_hwfn->p_rdma_info->lock);
+	qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->cid_map, cid);
+	qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->cid_map, cid + 1);
+	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
+}
+
 static int qed_roce_alloc_cid(struct qed_hwfn *p_hwfn, u16 *cid)
 {
 	struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
@@ -1139,15 +1212,22 @@ err:
 	return rc;
 }
 
+static void qed_roce_set_real_cid(struct qed_hwfn *p_hwfn, u32 cid)
+{
+	spin_lock_bh(&p_hwfn->p_rdma_info->lock);
+	qed_bmap_set_id(p_hwfn, &p_hwfn->p_rdma_info->real_cid_map, cid);
+	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
+}
+
 static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 					struct qed_rdma_qp *qp)
 {
 	struct roce_create_qp_resp_ramrod_data *p_ramrod;
 	struct qed_sp_init_data init_data;
-	union qed_qm_pq_params qm_params;
 	enum roce_flavor roce_flavor;
 	struct qed_spq_entry *p_ent;
-	u16 physical_queue0 = 0;
+	u16 regular_latency_queue;
+	enum protocol_type proto;
 	int rc;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
@@ -1229,15 +1309,16 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 	p_ramrod->qp_handle_for_async.lo = cpu_to_le32(qp->qp_handle_async.lo);
 	p_ramrod->qp_handle_for_cqe.hi = cpu_to_le32(qp->qp_handle.hi);
 	p_ramrod->qp_handle_for_cqe.lo = cpu_to_le32(qp->qp_handle.lo);
-	p_ramrod->stats_counter_id = p_hwfn->rel_pf_id;
 	p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) |
 				       qp->rq_cq_id);
 
-	memset(&qm_params, 0, sizeof(qm_params));
-	qm_params.roce.qpid = qp->icid >> 1;
-	physical_queue0 = qed_get_qm_pq(p_hwfn, PROTOCOLID_ROCE, &qm_params);
+	regular_latency_queue = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+
+	p_ramrod->regular_latency_phy_queue =
+	    cpu_to_le16(regular_latency_queue);
+	p_ramrod->low_latency_phy_queue =
+	    cpu_to_le16(regular_latency_queue);
 
-	p_ramrod->physical_queue0 = cpu_to_le16(physical_queue0);
 	p_ramrod->dpi = cpu_to_le16(qp->dpi);
 
 	qed_rdma_set_fw_mac(p_ramrod->remote_mac_addr, qp->remote_mac_addr);
@@ -1253,13 +1334,19 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 
 	rc = qed_spq_post(p_hwfn, p_ent, NULL);
 
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "rc = %d physical_queue0 = 0x%x\n",
-		   rc, physical_queue0);
+	DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
+		   "rc = %d regular physical queue = 0x%x\n", rc,
+		   regular_latency_queue);
 
 	if (rc)
 		goto err;
 
 	qp->resp_offloaded = true;
+	qp->cq_prod = 0;
+
+	proto = p_hwfn->p_rdma_info->proto;
+	qed_roce_set_real_cid(p_hwfn, qp->icid -
+			      qed_cxt_get_proto_cid_start(p_hwfn, proto));
 
 	return rc;
 
@@ -1277,10 +1364,10 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 {
 	struct roce_create_qp_req_ramrod_data *p_ramrod;
 	struct qed_sp_init_data init_data;
-	union qed_qm_pq_params qm_params;
 	enum roce_flavor roce_flavor;
 	struct qed_spq_entry *p_ent;
-	u16 physical_queue0 = 0;
+	u16 regular_latency_queue;
+	enum protocol_type proto;
 	int rc;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
@@ -1351,15 +1438,16 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 	p_ramrod->qp_handle_for_async.lo = cpu_to_le32(qp->qp_handle_async.lo);
 	p_ramrod->qp_handle_for_cqe.hi = cpu_to_le32(qp->qp_handle.hi);
 	p_ramrod->qp_handle_for_cqe.lo = cpu_to_le32(qp->qp_handle.lo);
-	p_ramrod->stats_counter_id = p_hwfn->rel_pf_id;
-	p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) |
-				       qp->sq_cq_id);
+	p_ramrod->cq_cid =
+	    cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | qp->sq_cq_id);
+
+	regular_latency_queue = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
 
-	memset(&qm_params, 0, sizeof(qm_params));
-	qm_params.roce.qpid = qp->icid >> 1;
-	physical_queue0 = qed_get_qm_pq(p_hwfn, PROTOCOLID_ROCE, &qm_params);
+	p_ramrod->regular_latency_phy_queue =
+	    cpu_to_le16(regular_latency_queue);
+	p_ramrod->low_latency_phy_queue =
+	    cpu_to_le16(regular_latency_queue);
 
-	p_ramrod->physical_queue0 = cpu_to_le16(physical_queue0);
 	p_ramrod->dpi = cpu_to_le16(qp->dpi);
 
 	qed_rdma_set_fw_mac(p_ramrod->remote_mac_addr, qp->remote_mac_addr);
@@ -1378,6 +1466,10 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 		goto err;
 
 	qp->req_offloaded = true;
+	proto = p_hwfn->p_rdma_info->proto;
+	qed_roce_set_real_cid(p_hwfn,
+			      qp->icid + 1 -
+			      qed_cxt_get_proto_cid_start(p_hwfn, proto));
 
 	return rc;
 
@@ -1577,7 +1669,8 @@ static int qed_roce_sp_modify_requester(struct qed_hwfn *p_hwfn,
 
 static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn,
 					    struct qed_rdma_qp *qp,
-					    u32 *num_invalidated_mw)
+					    u32 *num_invalidated_mw,
+					    u32 *cq_prod)
 {
 	struct roce_destroy_qp_resp_output_params *p_ramrod_res;
 	struct roce_destroy_qp_resp_ramrod_data *p_ramrod;
@@ -1588,8 +1681,22 @@ static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn,
 
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
 
-	if (!qp->resp_offloaded)
+	*num_invalidated_mw = 0;
+	*cq_prod = qp->cq_prod;
+
+	if (!qp->resp_offloaded) {
+		/* If a responder was never offload, we need to free the cids
+		 * allocated in create_qp as a FW async event will never arrive
+		 */
+		u32 cid;
+
+		cid = qp->icid -
+		      qed_cxt_get_proto_cid_start(p_hwfn,
+						  p_hwfn->p_rdma_info->proto);
+		qed_roce_free_cid_pair(p_hwfn, (u16)cid);
+
 		return 0;
+	}
 
 	/* Get SPQ entry */
 	memset(&init_data, 0, sizeof(init_data));
@@ -1624,6 +1731,8 @@ static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn,
 		goto err;
 
 	*num_invalidated_mw = le32_to_cpu(p_ramrod_res->num_invalidated_mw);
+	*cq_prod = le32_to_cpu(p_ramrod_res->cq_prod);
+	qp->cq_prod = *cq_prod;
 
 	/* Free IRQ - only if ramrod succeeded, in case FW is still using it */
 	dma_free_coherent(&p_hwfn->cdev->pdev->dev,
@@ -1827,10 +1936,8 @@ static int qed_roce_query_qp(struct qed_hwfn *p_hwfn,
 
 	out_params->draining = false;
 
-	if (rq_err_state)
+	if (rq_err_state || sq_err_state)
 		qp->cur_state = QED_ROCE_QP_STATE_ERR;
-	else if (sq_err_state)
-		qp->cur_state = QED_ROCE_QP_STATE_SQE;
 	else if (sq_draining)
 		out_params->draining = true;
 	out_params->state = qp->cur_state;
@@ -1849,10 +1956,9 @@ err_resp:
 
 static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
 {
-	struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
 	u32 num_invalidated_mw = 0;
 	u32 num_bound_mw = 0;
-	u32 start_cid;
+	u32 cq_prod;
 	int rc;
 
 	/* Destroys the specified QP */
@@ -1866,7 +1972,8 @@ static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
 
 	if (qp->cur_state != QED_ROCE_QP_STATE_RESET) {
 		rc = qed_roce_sp_destroy_qp_responder(p_hwfn, qp,
-						      &num_invalidated_mw);
+						      &num_invalidated_mw,
+						      &cq_prod);
 		if (rc)
 			return rc;
 
@@ -1881,21 +1988,6 @@ static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
 				  "number of invalidate memory windows is different from bounded ones\n");
 			return -EINVAL;
 		}
-
-		spin_lock_bh(&p_rdma_info->lock);
-
-		start_cid = qed_cxt_get_proto_cid_start(p_hwfn,
-							p_rdma_info->proto);
-
-		/* Release responder's icid */
-		qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map,
-				    qp->icid - start_cid);
-
-		/* Release requester's icid */
-		qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map,
-				    qp->icid + 1 - start_cid);
-
-		spin_unlock_bh(&p_rdma_info->lock);
 	}
 
 	return 0;
@@ -2110,12 +2202,19 @@ static int qed_roce_modify_qp(struct qed_hwfn *p_hwfn,
 		return rc;
 	} else if (qp->cur_state == QED_ROCE_QP_STATE_RESET) {
 		/* Any state -> RESET */
+		u32 cq_prod;
+
+		/* Send destroy responder ramrod */
+		rc = qed_roce_sp_destroy_qp_responder(p_hwfn,
+						      qp,
+						      &num_invalidated_mw,
+						      &cq_prod);
 
-		rc = qed_roce_sp_destroy_qp_responder(p_hwfn, qp,
-						      &num_invalidated_mw);
 		if (rc)
 			return rc;
 
+		qp->cq_prod = cq_prod;
+
 		rc = qed_roce_sp_destroy_qp_requester(p_hwfn, qp,
 						      &num_bound_mw);
 
@@ -2454,6 +2553,31 @@ static int qed_rdma_deregister_tid(void *rdma_cxt, u32 itid)
 	return rc;
 }
 
+static void qed_roce_free_real_icid(struct qed_hwfn *p_hwfn, u16 icid)
+{
+	struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
+	u32 start_cid, cid, xcid;
+
+	/* an even icid belongs to a responder while an odd icid belongs to a
+	 * requester. The 'cid' received as an input can be either. We calculate
+	 * the "partner" icid and call it xcid. Only if both are free then the
+	 * "cid" map can be cleared.
+	 */
+	start_cid = qed_cxt_get_proto_cid_start(p_hwfn, p_rdma_info->proto);
+	cid = icid - start_cid;
+	xcid = cid ^ 1;
+
+	spin_lock_bh(&p_rdma_info->lock);
+
+	qed_bmap_release_id(p_hwfn, &p_rdma_info->real_cid_map, cid);
+	if (qed_bmap_test_id(p_hwfn, &p_rdma_info->real_cid_map, xcid) == 0) {
+		qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map, cid);
+		qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map, xcid);
+	}
+
+	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
+}
+
 static void *qed_rdma_get_rdma_ctx(struct qed_dev *cdev)
 {
 	return QED_LEADING_HWFN(cdev);
@@ -2773,7 +2897,7 @@ static int qed_roce_ll2_tx(struct qed_dev *cdev,
 						      : QED_LL2_RROCE;
 
 	if (pkt->roce_mode == ROCE_V2_IPV4)
-		flags |= BIT(CORE_TX_BD_FLAGS_IP_CSUM_SHIFT);
+		flags |= BIT(CORE_TX_BD_DATA_IP_CSUM_SHIFT);
 
 	/* Tx header */
 	rc = qed_ll2_prepare_tx_packet(QED_LEADING_HWFN(cdev), roce_ll2->handle,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.h b/drivers/net/ethernet/qlogic/qed/qed_roce.h
index 36cf4b2ab7fa..3ccc08a7c995 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.h
@@ -82,6 +82,7 @@ struct qed_rdma_info {
 	struct qed_bmap qp_map;
 	struct qed_bmap srq_map;
 	struct qed_bmap cid_map;
+	struct qed_bmap real_cid_map;
 	struct qed_bmap dpi_map;
 	struct qed_bmap toggle_bits;
 	struct qed_rdma_events events;
@@ -92,6 +93,7 @@ struct qed_rdma_info {
 	u32 num_qps;
 	u32 num_mrs;
 	u16 queue_zone_base;
+	u16 max_queue_zones;
 	enum protocol_type proto;
 };
 
@@ -153,6 +155,7 @@ struct qed_rdma_qp {
 	dma_addr_t irq_phys_addr;
 	u8 irq_num_pages;
 	bool resp_offloaded;
+	u32 cq_prod;
 
 	u8 remote_mac_addr[6];
 	u8 local_mac_addr[6];
@@ -163,8 +166,8 @@ struct qed_rdma_qp {
 
 #if IS_ENABLED(CONFIG_QED_RDMA)
 void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
-void qed_async_roce_event(struct qed_hwfn *p_hwfn,
-			  struct event_ring_entry *p_eqe);
+void qed_roce_async_event(struct qed_hwfn *p_hwfn,
+			  u8 fw_event_code, union rdma_eqe_data *rdma_data);
 void qed_ll2b_complete_tx_gsi_packet(struct qed_hwfn *p_hwfn,
 				     u8 connection_handle,
 				     void *cookie,
@@ -187,7 +190,9 @@ void qed_ll2b_complete_rx_gsi_packet(struct qed_hwfn *p_hwfn,
 				     u16 src_mac_addr_lo, bool b_last_packet);
 #else
 static inline void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) {}
-static inline void qed_async_roce_event(struct qed_hwfn *p_hwfn, struct event_ring_entry *p_eqe) {}
+static inline void qed_roce_async_event(struct qed_hwfn *p_hwfn,
+					u8 fw_event_code,
+					union rdma_eqe_data *rdma_data) {}
 static inline void qed_ll2b_complete_tx_gsi_packet(struct qed_hwfn *p_hwfn,
 						   u8 connection_handle,
 						   void *cookie,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 645328a9f0cf..13f715569253 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -205,11 +205,10 @@ static int qed_spq_fill_entry(struct qed_hwfn *p_hwfn,
 static void qed_spq_hw_initialize(struct qed_hwfn *p_hwfn,
 				  struct qed_spq *p_spq)
 {
-	u16				pq;
-	struct qed_cxt_info		cxt_info;
-	struct core_conn_context	*p_cxt;
-	union qed_qm_pq_params		pq_params;
-	int				rc;
+	struct core_conn_context *p_cxt;
+	struct qed_cxt_info cxt_info;
+	u16 physical_q;
+	int rc;
 
 	cxt_info.iid = p_spq->cid;
 
@@ -231,10 +230,8 @@ static void qed_spq_hw_initialize(struct qed_hwfn *p_hwfn,
 		  XSTORM_CORE_CONN_AG_CTX_CONSOLID_PROD_CF_EN, 1);
 
 	/* QM physical queue */
-	memset(&pq_params, 0, sizeof(pq_params));
-	pq_params.core.tc = LB_TC;
-	pq = qed_get_qm_pq(p_hwfn, PROTOCOLID_CORE, &pq_params);
-	p_cxt->xstorm_ag_context.physical_q0 = cpu_to_le16(pq);
+	physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LB);
+	p_cxt->xstorm_ag_context.physical_q0 = cpu_to_le16(physical_q);
 
 	p_cxt->xstorm_st_context.spq_base_lo =
 		DMA_LO_LE(p_spq->chain.p_phys_addr);
@@ -296,9 +293,12 @@ qed_async_event_completion(struct qed_hwfn *p_hwfn,
 			   struct event_ring_entry *p_eqe)
 {
 	switch (p_eqe->protocol_id) {
+#if IS_ENABLED(CONFIG_QED_RDMA)
 	case PROTOCOLID_ROCE:
-		qed_async_roce_event(p_hwfn, p_eqe);
+		qed_roce_async_event(p_hwfn, p_eqe->opcode,
+				     &p_eqe->data.rdma_data);
 		return 0;
+#endif
 	case PROTOCOLID_COMMON:
 		return qed_sriov_eqe_event(p_hwfn,
 					   p_eqe->opcode,
@@ -306,14 +306,6 @@ qed_async_event_completion(struct qed_hwfn *p_hwfn,
 	case PROTOCOLID_ISCSI:
 		if (!IS_ENABLED(CONFIG_QED_ISCSI))
 			return -EINVAL;
-		if (p_eqe->opcode == ISCSI_EVENT_TYPE_ASYN_DELETE_OOO_ISLES) {
-			u32 cid = le32_to_cpu(p_eqe->data.iscsi_info.cid);
-
-			qed_ooo_release_connection_isles(p_hwfn,
-							 p_hwfn->p_ooo_info,
-							 cid);
-			return 0;
-		}
 
 		if (p_hwfn->p_iscsi_info->event_cb) {
 			struct qed_iscsi_info *p_iscsi = p_hwfn->p_iscsi_info;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index 253c2bbe1e4e..92a3ee1715d9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -178,26 +178,59 @@ static struct qed_vf_info *qed_iov_get_vf_info(struct qed_hwfn *p_hwfn,
 	return vf;
 }
 
+enum qed_iov_validate_q_mode {
+	QED_IOV_VALIDATE_Q_NA,
+	QED_IOV_VALIDATE_Q_ENABLE,
+	QED_IOV_VALIDATE_Q_DISABLE,
+};
+
+static bool qed_iov_validate_queue_mode(struct qed_hwfn *p_hwfn,
+					struct qed_vf_info *p_vf,
+					u16 qid,
+					enum qed_iov_validate_q_mode mode,
+					bool b_is_tx)
+{
+	if (mode == QED_IOV_VALIDATE_Q_NA)
+		return true;
+
+	if ((b_is_tx && p_vf->vf_queues[qid].p_tx_cid) ||
+	    (!b_is_tx && p_vf->vf_queues[qid].p_rx_cid))
+		return mode == QED_IOV_VALIDATE_Q_ENABLE;
+
+	/* In case we haven't found any valid cid, then its disabled */
+	return mode == QED_IOV_VALIDATE_Q_DISABLE;
+}
+
 static bool qed_iov_validate_rxq(struct qed_hwfn *p_hwfn,
-				 struct qed_vf_info *p_vf, u16 rx_qid)
+				 struct qed_vf_info *p_vf,
+				 u16 rx_qid,
+				 enum qed_iov_validate_q_mode mode)
 {
-	if (rx_qid >= p_vf->num_rxqs)
+	if (rx_qid >= p_vf->num_rxqs) {
 		DP_VERBOSE(p_hwfn,
 			   QED_MSG_IOV,
 			   "VF[0x%02x] - can't touch Rx queue[%04x]; Only 0x%04x are allocated\n",
 			   p_vf->abs_vf_id, rx_qid, p_vf->num_rxqs);
-	return rx_qid < p_vf->num_rxqs;
+		return false;
+	}
+
+	return qed_iov_validate_queue_mode(p_hwfn, p_vf, rx_qid, mode, false);
 }
 
 static bool qed_iov_validate_txq(struct qed_hwfn *p_hwfn,
-				 struct qed_vf_info *p_vf, u16 tx_qid)
+				 struct qed_vf_info *p_vf,
+				 u16 tx_qid,
+				 enum qed_iov_validate_q_mode mode)
 {
-	if (tx_qid >= p_vf->num_txqs)
+	if (tx_qid >= p_vf->num_txqs) {
 		DP_VERBOSE(p_hwfn,
 			   QED_MSG_IOV,
 			   "VF[0x%02x] - can't touch Tx queue[%04x]; Only 0x%04x are allocated\n",
 			   p_vf->abs_vf_id, tx_qid, p_vf->num_txqs);
-	return tx_qid < p_vf->num_txqs;
+		return false;
+	}
+
+	return qed_iov_validate_queue_mode(p_hwfn, p_vf, tx_qid, mode, true);
 }
 
 static bool qed_iov_validate_sb(struct qed_hwfn *p_hwfn,
@@ -217,6 +250,34 @@ static bool qed_iov_validate_sb(struct qed_hwfn *p_hwfn,
 	return false;
 }
 
+static bool qed_iov_validate_active_rxq(struct qed_hwfn *p_hwfn,
+					struct qed_vf_info *p_vf)
+{
+	u8 i;
+
+	for (i = 0; i < p_vf->num_rxqs; i++)
+		if (qed_iov_validate_queue_mode(p_hwfn, p_vf, i,
+						QED_IOV_VALIDATE_Q_ENABLE,
+						false))
+			return true;
+
+	return false;
+}
+
+static bool qed_iov_validate_active_txq(struct qed_hwfn *p_hwfn,
+					struct qed_vf_info *p_vf)
+{
+	u8 i;
+
+	for (i = 0; i < p_vf->num_txqs; i++)
+		if (qed_iov_validate_queue_mode(p_hwfn, p_vf, i,
+						QED_IOV_VALIDATE_Q_ENABLE,
+						true))
+			return true;
+
+	return false;
+}
+
 static int qed_iov_post_vf_bulletin(struct qed_hwfn *p_hwfn,
 				    int vfid, struct qed_ptt *p_ptt)
 {
@@ -557,14 +618,30 @@ int qed_iov_hw_info(struct qed_hwfn *p_hwfn)
 		return 0;
 	}
 
-	/* Calculate the first VF index - this is a bit tricky; Basically,
-	 * VFs start at offset 16 relative to PF0, and 2nd engine VFs begin
-	 * after the first engine's VFs.
+	/* First VF index based on offset is tricky:
+	 *  - If ARI is supported [likely], offset - (16 - pf_id) would
+	 *    provide the number for eng0. 2nd engine Vfs would begin
+	 *    after the first engine's VFs.
+	 *  - If !ARI, VFs would start on next device.
+	 *    so offset - (256 - pf_id) would provide the number.
+	 * Utilize the fact that (256 - pf_id) is achieved only by later
+	 * to diffrentiate between the two.
 	 */
-	cdev->p_iov_info->first_vf_in_pf = p_hwfn->cdev->p_iov_info->offset +
-					   p_hwfn->abs_pf_id - 16;
-	if (QED_PATH_ID(p_hwfn))
-		cdev->p_iov_info->first_vf_in_pf -= MAX_NUM_VFS_BB;
+
+	if (p_hwfn->cdev->p_iov_info->offset < (256 - p_hwfn->abs_pf_id)) {
+		u32 first = p_hwfn->cdev->p_iov_info->offset +
+			    p_hwfn->abs_pf_id - 16;
+
+		cdev->p_iov_info->first_vf_in_pf = first;
+
+		if (QED_PATH_ID(p_hwfn))
+			cdev->p_iov_info->first_vf_in_pf -= MAX_NUM_VFS_BB;
+	} else {
+		u32 first = p_hwfn->cdev->p_iov_info->offset +
+			    p_hwfn->abs_pf_id - 256;
+
+		cdev->p_iov_info->first_vf_in_pf = first;
+	}
 
 	DP_VERBOSE(p_hwfn, QED_MSG_IOV,
 		   "First VF in hwfn 0x%08x\n",
@@ -677,6 +754,11 @@ static int qed_iov_enable_vf_access(struct qed_hwfn *p_hwfn,
 	u32 igu_vf_conf = IGU_VF_CONF_FUNC_EN;
 	int rc;
 
+	/* It's possible VF was previously considered malicious -
+	 * clear the indication even if we're only going to disable VF.
+	 */
+	vf->b_malicious = false;
+
 	if (vf->to_disable)
 		return 0;
 
@@ -689,9 +771,6 @@ static int qed_iov_enable_vf_access(struct qed_hwfn *p_hwfn,
 
 	qed_iov_vf_igu_reset(p_hwfn, p_ptt, vf);
 
-	/* It's possible VF was previously considered malicious */
-	vf->b_malicious = false;
-
 	rc = qed_mcp_config_vf_msix(p_hwfn, p_ptt, vf->abs_vf_id, vf->num_sbs);
 	if (rc)
 		return rc;
@@ -1118,13 +1197,17 @@ static void qed_iov_send_response(struct qed_hwfn *p_hwfn,
 			   (sizeof(union pfvf_tlvs) - sizeof(u64)) / 4,
 			   &params);
 
-	qed_dmae_host2host(p_hwfn, p_ptt, mbx->reply_phys,
-			   mbx->req_virt->first_tlv.reply_address,
-			   sizeof(u64) / 4, &params);
-
+	/* Once PF copies the rc to the VF, the latter can continue
+	 * and send an additional message. So we have to make sure the
+	 * channel would be re-set to ready prior to that.
+	 */
 	REG_WR(p_hwfn,
 	       GTT_BAR0_MAP_REG_USDM_RAM +
 	       USTORM_VF_PF_CHANNEL_READY_OFFSET(eng_vf_id), 1);
+
+	qed_dmae_host2host(p_hwfn, p_ptt, mbx->reply_phys,
+			   mbx->req_virt->first_tlv.reply_address,
+			   sizeof(u64) / 4, &params);
 }
 
 static u16 qed_iov_vport_to_tlv(struct qed_hwfn *p_hwfn,
@@ -1733,6 +1816,8 @@ static void qed_iov_vf_mbx_start_vport(struct qed_hwfn *p_hwfn,
 	vf->state = VF_ENABLED;
 	start = &mbx->req_virt->start_vport;
 
+	qed_iov_enable_vf_traffic(p_hwfn, p_ptt, vf);
+
 	/* Initialize Status block in CAU */
 	for (sb_id = 0; sb_id < vf->num_sbs; sb_id++) {
 		if (!start->sb_addr[sb_id]) {
@@ -1746,7 +1831,6 @@ static void qed_iov_vf_mbx_start_vport(struct qed_hwfn *p_hwfn,
 				    start->sb_addr[sb_id],
 				    vf->igu_sbs[sb_id], vf->abs_vf_id, 1);
 	}
-	qed_iov_enable_vf_traffic(p_hwfn, p_ptt, vf);
 
 	vf->mtu = start->mtu;
 	vf->shadow_config.inner_vlan_removal = start->inner_vlan_removal;
@@ -1803,6 +1887,16 @@ static void qed_iov_vf_mbx_stop_vport(struct qed_hwfn *p_hwfn,
 	vf->vport_instance--;
 	vf->spoof_chk = false;
 
+	if ((qed_iov_validate_active_rxq(p_hwfn, vf)) ||
+	    (qed_iov_validate_active_txq(p_hwfn, vf))) {
+		vf->b_malicious = true;
+		DP_NOTICE(p_hwfn,
+			  "VF [%02x] - considered malicious; Unable to stop RX/TX queuess\n",
+			  vf->abs_vf_id);
+		status = PFVF_STATUS_MALICIOUS;
+		goto out;
+	}
+
 	rc = qed_sp_vport_stop(p_hwfn, vf->opaque_fid, vf->vport_id);
 	if (rc) {
 		DP_ERR(p_hwfn, "qed_iov_vf_mbx_stop_vport returned error %d\n",
@@ -1814,6 +1908,7 @@ static void qed_iov_vf_mbx_stop_vport(struct qed_hwfn *p_hwfn,
 	vf->configured_features = 0;
 	memset(&vf->shadow_config, 0, sizeof(vf->shadow_config));
 
+out:
 	qed_iov_prepare_resp(p_hwfn, p_ptt, vf, CHANNEL_TLV_VPORT_TEARDOWN,
 			     sizeof(struct pfvf_def_resp_tlv), status);
 }
@@ -1870,7 +1965,8 @@ static void qed_iov_vf_mbx_start_rxq(struct qed_hwfn *p_hwfn,
 
 	req = &mbx->req_virt->start_rxq;
 
-	if (!qed_iov_validate_rxq(p_hwfn, vf, req->rx_qid) ||
+	if (!qed_iov_validate_rxq(p_hwfn, vf, req->rx_qid,
+				  QED_IOV_VALIDATE_Q_DISABLE) ||
 	    !qed_iov_validate_sb(p_hwfn, vf, req->hw_sb))
 		goto out;
 
@@ -1970,21 +2066,16 @@ static void qed_iov_vf_mbx_start_txq(struct qed_hwfn *p_hwfn,
 	struct qed_queue_start_common_params params;
 	struct qed_iov_vf_mbx *mbx = &vf->vf_mbx;
 	u8 status = PFVF_STATUS_NO_RESOURCE;
-	union qed_qm_pq_params pq_params;
 	struct vfpf_start_txq_tlv *req;
 	struct qed_vf_q_info *p_queue;
 	int rc;
 	u16 pq;
 
-	/* Prepare the parameters which would choose the right PQ */
-	memset(&pq_params, 0, sizeof(pq_params));
-	pq_params.eth.is_vf = 1;
-	pq_params.eth.vf_id = vf->relative_vf_id;
-
 	memset(&params, 0, sizeof(params));
 	req = &mbx->req_virt->start_txq;
 
-	if (!qed_iov_validate_txq(p_hwfn, vf, req->tx_qid) ||
+	if (!qed_iov_validate_txq(p_hwfn, vf, req->tx_qid,
+				  QED_IOV_VALIDATE_Q_DISABLE) ||
 	    !qed_iov_validate_sb(p_hwfn, vf, req->hw_sb))
 		goto out;
 
@@ -2004,7 +2095,7 @@ static void qed_iov_vf_mbx_start_txq(struct qed_hwfn *p_hwfn,
 	if (!p_queue->p_tx_cid)
 		goto out;
 
-	pq = qed_get_qm_pq(p_hwfn, PROTOCOLID_ETH, &pq_params);
+	pq = qed_get_cm_pq_idx_vf(p_hwfn, vf->relative_vf_id);
 	rc = qed_eth_txq_start_ramrod(p_hwfn, p_queue->p_tx_cid,
 				      req->pbl_addr, req->pbl_size, pq);
 	if (rc) {
@@ -2021,57 +2112,53 @@ out:
 
 static int qed_iov_vf_stop_rxqs(struct qed_hwfn *p_hwfn,
 				struct qed_vf_info *vf,
-				u16 rxq_id, u8 num_rxqs, bool cqe_completion)
+				u16 rxq_id, bool cqe_completion)
 {
 	struct qed_vf_q_info *p_queue;
 	int rc = 0;
-	int qid;
 
-	if (rxq_id + num_rxqs > ARRAY_SIZE(vf->vf_queues))
+	if (!qed_iov_validate_rxq(p_hwfn, vf, rxq_id,
+				  QED_IOV_VALIDATE_Q_ENABLE)) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_IOV,
+			   "VF[%d] Tried Closing Rx 0x%04x which is inactive\n",
+			   vf->relative_vf_id, rxq_id);
 		return -EINVAL;
+	}
 
-	for (qid = rxq_id; qid < rxq_id + num_rxqs; qid++) {
-		p_queue = &vf->vf_queues[qid];
-
-		if (!p_queue->p_rx_cid)
-			continue;
+	p_queue = &vf->vf_queues[rxq_id];
 
-		rc = qed_eth_rx_queue_stop(p_hwfn,
-					   p_queue->p_rx_cid,
-					   false, cqe_completion);
-		if (rc)
-			return rc;
+	rc = qed_eth_rx_queue_stop(p_hwfn,
+				   p_queue->p_rx_cid,
+				   false, cqe_completion);
+	if (rc)
+		return rc;
 
-		vf->vf_queues[qid].p_rx_cid = NULL;
-		vf->num_active_rxqs--;
-	}
+	p_queue->p_rx_cid = NULL;
+	vf->num_active_rxqs--;
 
-	return rc;
+	return 0;
 }
 
 static int qed_iov_vf_stop_txqs(struct qed_hwfn *p_hwfn,
-				struct qed_vf_info *vf, u16 txq_id, u8 num_txqs)
+				struct qed_vf_info *vf, u16 txq_id)
 {
-	int rc = 0;
 	struct qed_vf_q_info *p_queue;
-	int qid;
+	int rc = 0;
 
-	if (txq_id + num_txqs > ARRAY_SIZE(vf->vf_queues))
+	if (!qed_iov_validate_txq(p_hwfn, vf, txq_id,
+				  QED_IOV_VALIDATE_Q_ENABLE))
 		return -EINVAL;
 
-	for (qid = txq_id; qid < txq_id + num_txqs; qid++) {
-		p_queue = &vf->vf_queues[qid];
-		if (!p_queue->p_tx_cid)
-			continue;
+	p_queue = &vf->vf_queues[txq_id];
 
-		rc = qed_eth_tx_queue_stop(p_hwfn, p_queue->p_tx_cid);
-		if (rc)
-			return rc;
+	rc = qed_eth_tx_queue_stop(p_hwfn, p_queue->p_tx_cid);
+	if (rc)
+		return rc;
 
-		p_queue->p_tx_cid = NULL;
-	}
+	p_queue->p_tx_cid = NULL;
 
-	return rc;
+	return 0;
 }
 
 static void qed_iov_vf_mbx_stop_rxqs(struct qed_hwfn *p_hwfn,
@@ -2080,20 +2167,28 @@ static void qed_iov_vf_mbx_stop_rxqs(struct qed_hwfn *p_hwfn,
 {
 	u16 length = sizeof(struct pfvf_def_resp_tlv);
 	struct qed_iov_vf_mbx *mbx = &vf->vf_mbx;
-	u8 status = PFVF_STATUS_SUCCESS;
+	u8 status = PFVF_STATUS_FAILURE;
 	struct vfpf_stop_rxqs_tlv *req;
 	int rc;
 
-	/* We give the option of starting from qid != 0, in this case we
-	 * need to make sure that qid + num_qs doesn't exceed the actual
-	 * amount of queues that exist.
+	/* There has never been an official driver that used this interface
+	 * for stopping multiple queues, and it is now considered deprecated.
+	 * Validate this isn't used here.
 	 */
 	req = &mbx->req_virt->stop_rxqs;
-	rc = qed_iov_vf_stop_rxqs(p_hwfn, vf, req->rx_qid,
-				  req->num_rxqs, req->cqe_completion);
-	if (rc)
-		status = PFVF_STATUS_FAILURE;
+	if (req->num_rxqs != 1) {
+		DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+			   "Odd; VF[%d] tried stopping multiple Rx queues\n",
+			   vf->relative_vf_id);
+		status = PFVF_STATUS_NOT_SUPPORTED;
+		goto out;
+	}
 
+	rc = qed_iov_vf_stop_rxqs(p_hwfn, vf, req->rx_qid,
+				  req->cqe_completion);
+	if (!rc)
+		status = PFVF_STATUS_SUCCESS;
+out:
 	qed_iov_prepare_resp(p_hwfn, p_ptt, vf, CHANNEL_TLV_STOP_RXQS,
 			     length, status);
 }
@@ -2104,19 +2199,27 @@ static void qed_iov_vf_mbx_stop_txqs(struct qed_hwfn *p_hwfn,
 {
 	u16 length = sizeof(struct pfvf_def_resp_tlv);
 	struct qed_iov_vf_mbx *mbx = &vf->vf_mbx;
-	u8 status = PFVF_STATUS_SUCCESS;
+	u8 status = PFVF_STATUS_FAILURE;
 	struct vfpf_stop_txqs_tlv *req;
 	int rc;
 
-	/* We give the option of starting from qid != 0, in this case we
-	 * need to make sure that qid + num_qs doesn't exceed the actual
-	 * amount of queues that exist.
+	/* There has never been an official driver that used this interface
+	 * for stopping multiple queues, and it is now considered deprecated.
+	 * Validate this isn't used here.
 	 */
 	req = &mbx->req_virt->stop_txqs;
-	rc = qed_iov_vf_stop_txqs(p_hwfn, vf, req->tx_qid, req->num_txqs);
-	if (rc)
-		status = PFVF_STATUS_FAILURE;
+	if (req->num_txqs != 1) {
+		DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+			   "Odd; VF[%d] tried stopping multiple Tx queues\n",
+			   vf->relative_vf_id);
+		status = PFVF_STATUS_NOT_SUPPORTED;
+		goto out;
+	}
+	rc = qed_iov_vf_stop_txqs(p_hwfn, vf, req->tx_qid);
+	if (!rc)
+		status = PFVF_STATUS_SUCCESS;
 
+out:
 	qed_iov_prepare_resp(p_hwfn, p_ptt, vf, CHANNEL_TLV_STOP_TXQS,
 			     length, status);
 }
@@ -2141,22 +2244,17 @@ static void qed_iov_vf_mbx_update_rxqs(struct qed_hwfn *p_hwfn,
 	complete_event_flg = !!(req->flags & VFPF_RXQ_UPD_COMPLETE_EVENT_FLAG);
 
 	/* Validate inputs */
-	if (req->num_rxqs + req->rx_qid > QED_MAX_VF_CHAINS_PER_PF ||
-	    !qed_iov_validate_rxq(p_hwfn, vf, req->rx_qid)) {
-		DP_INFO(p_hwfn, "VF[%d]: Incorrect Rxqs [%04x, %02x]\n",
-			vf->relative_vf_id, req->rx_qid, req->num_rxqs);
-		goto out;
-	}
-
-	for (i = 0; i < req->num_rxqs; i++) {
-		qid = req->rx_qid + i;
-		if (!vf->vf_queues[qid].p_rx_cid) {
-			DP_INFO(p_hwfn,
-				"VF[%d] rx_qid = %d isn`t active!\n",
-				vf->relative_vf_id, qid);
+	for (i = req->rx_qid; i < req->rx_qid + req->num_rxqs; i++)
+		if (!qed_iov_validate_rxq(p_hwfn, vf, i,
+					  QED_IOV_VALIDATE_Q_ENABLE)) {
+			DP_INFO(p_hwfn, "VF[%d]: Incorrect Rxqs [%04x, %02x]\n",
+				vf->relative_vf_id, req->rx_qid, req->num_rxqs);
 			goto out;
 		}
 
+	/* Prepare the handlers */
+	for (i = 0; i < req->num_rxqs; i++) {
+		qid = req->rx_qid + i;
 		handlers[i] = vf->vf_queues[qid].p_rx_cid;
 	}
 
@@ -2372,7 +2470,8 @@ qed_iov_vp_update_rss_param(struct qed_hwfn *p_hwfn,
 
 	for (i = 0; i < table_size; i++) {
 		q_idx = p_rss_tlv->rss_ind_table[i];
-		if (!qed_iov_validate_rxq(p_hwfn, vf, q_idx)) {
+		if (!qed_iov_validate_rxq(p_hwfn, vf, q_idx,
+					  QED_IOV_VALIDATE_Q_ENABLE)) {
 			DP_VERBOSE(p_hwfn,
 				   QED_MSG_IOV,
 				   "VF[%d]: Omitting RSS due to wrong queue %04x\n",
@@ -2381,15 +2480,6 @@ qed_iov_vp_update_rss_param(struct qed_hwfn *p_hwfn,
 			goto out;
 		}
 
-		if (!vf->vf_queues[q_idx].p_rx_cid) {
-			DP_VERBOSE(p_hwfn,
-				   QED_MSG_IOV,
-				   "VF[%d]: Omitting RSS due to inactive queue %08x\n",
-				   vf->relative_vf_id, q_idx);
-			b_reject = true;
-			goto out;
-		}
-
 		p_rss->rss_ind_table[i] = vf->vf_queues[q_idx].p_rx_cid;
 	}
 
@@ -3042,9 +3132,10 @@ qed_iov_vf_flr_cleanup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	return rc;
 }
 
-int qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *p_disabled_vfs)
+bool qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *p_disabled_vfs)
 {
-	u16 i, found = 0;
+	bool found = false;
+	u16 i;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_IOV, "Marking FLR-ed VFs\n");
 	for (i = 0; i < (VF_MAX_STATIC / 32); i++)
@@ -3054,7 +3145,7 @@ int qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *p_disabled_vfs)
 
 	if (!p_hwfn->cdev->p_iov_info) {
 		DP_NOTICE(p_hwfn, "VF flr but no IOV\n");
-		return 0;
+		return false;
 	}
 
 	/* Mark VFs */
@@ -3083,7 +3174,7 @@ int qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *p_disabled_vfs)
 			 * VF flr until ACKs, we're safe.
 			 */
 			p_flr[rel_vf_id / 64] |= 1ULL << (rel_vf_id % 64);
-			found = 1;
+			found = true;
 		}
 	}
 
@@ -3289,11 +3380,17 @@ static void qed_sriov_vfpf_malicious(struct qed_hwfn *p_hwfn,
 	if (!p_vf)
 		return;
 
-	DP_INFO(p_hwfn,
-		"VF [%d] - Malicious behavior [%02x]\n",
-		p_vf->abs_vf_id, p_data->err_id);
+	if (!p_vf->b_malicious) {
+		DP_NOTICE(p_hwfn,
+			  "VF [%d] - Malicious behavior [%02x]\n",
+			  p_vf->abs_vf_id, p_data->err_id);
 
-	p_vf->b_malicious = true;
+		p_vf->b_malicious = true;
+	} else {
+		DP_INFO(p_hwfn,
+			"VF [%d] - Malicious behavior [%02x]\n",
+			p_vf->abs_vf_id, p_data->err_id);
+	}
 }
 
 int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn,
@@ -3842,6 +3939,7 @@ static int qed_get_vf_config(struct qed_dev *cdev,
 
 void qed_inform_vf_link_state(struct qed_hwfn *hwfn)
 {
+	struct qed_hwfn *lead_hwfn = QED_LEADING_HWFN(hwfn->cdev);
 	struct qed_mcp_link_capabilities caps;
 	struct qed_mcp_link_params params;
 	struct qed_mcp_link_state link;
@@ -3858,9 +3956,15 @@ void qed_inform_vf_link_state(struct qed_hwfn *hwfn)
 		if (!vf_info)
 			continue;
 
-		memcpy(&params, qed_mcp_get_link_params(hwfn), sizeof(params));
-		memcpy(&link, qed_mcp_get_link_state(hwfn), sizeof(link));
-		memcpy(&caps, qed_mcp_get_link_capabilities(hwfn),
+		/* Only hwfn0 is actually interested in the link speed.
+		 * But since only it would receive an MFW indication of link,
+		 * need to take configuration from it - otherwise things like
+		 * rate limiting for hwfn1 VF would not work.
+		 */
+		memcpy(&params, qed_mcp_get_link_params(lead_hwfn),
+		       sizeof(params));
+		memcpy(&link, qed_mcp_get_link_state(lead_hwfn), sizeof(link));
+		memcpy(&caps, qed_mcp_get_link_capabilities(lead_hwfn),
 		       sizeof(caps));
 
 		/* Modify link according to the VF's configured link state */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.h b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
index a89605821522..8e96b1d19308 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
@@ -348,9 +348,9 @@ int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn,
  * @param p_hwfn
  * @param disabled_vfs - bitmask of all VFs on path that were FLRed
  *
- * @return 1 iff one of the PF's vfs got FLRed. 0 otherwise.
+ * @return true iff one of the PF's vfs got FLRed. false otherwise.
  */
-int qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *disabled_vfs);
+bool qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *disabled_vfs);
 
 /**
  * @brief Search extended TLVs in request/reply buffer.
@@ -407,10 +407,10 @@ static inline int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn,
 	return -EINVAL;
 }
 
-static inline int qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn,
-				      u32 *disabled_vfs)
+static inline bool qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn,
+				       u32 *disabled_vfs)
 {
-	return 0;
+	return false;
 }
 
 static inline void qed_iov_wq_stop(struct qed_dev *cdev, bool schedule_first)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index 15d2855ec563..798786562b1b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -134,14 +134,20 @@ static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size)
 	}
 
 	if (!*done) {
-		DP_VERBOSE(p_hwfn, QED_MSG_IOV,
-			   "VF <-- PF Timeout [Type %d]\n",
-			   p_req->first_tlv.tl.type);
+		DP_NOTICE(p_hwfn,
+			  "VF <-- PF Timeout [Type %d]\n",
+			  p_req->first_tlv.tl.type);
 		rc = -EBUSY;
 	} else {
-		DP_VERBOSE(p_hwfn, QED_MSG_IOV,
-			   "PF response: %d [Type %d]\n",
-			   *done, p_req->first_tlv.tl.type);
+		if ((*done != PFVF_STATUS_SUCCESS) &&
+		    (*done != PFVF_STATUS_NO_RESOURCE))
+			DP_NOTICE(p_hwfn,
+				  "PF response: %d [Type %d]\n",
+				  *done, p_req->first_tlv.tl.type);
+		else
+			DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+				   "PF response: %d [Type %d]\n",
+				   *done, p_req->first_tlv.tl.type);
 	}
 
 	return rc;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h
index 7da0b165d8bc..105c0edd2a01 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h
@@ -275,6 +275,8 @@ struct vfpf_stop_rxqs_tlv {
 	struct vfpf_first_tlv first_tlv;
 
 	u16 rx_qid;
+
+	/* this field is deprecated and should *always* be set to '1' */
 	u8 num_rxqs;
 	u8 cqe_completion;
 	u8 padding[4];
@@ -285,6 +287,8 @@ struct vfpf_stop_txqs_tlv {
 	struct vfpf_first_tlv first_tlv;
 
 	u16 tx_qid;
+
+	/* this field is deprecated and should *always* be set to '1' */
 	u8 num_txqs;
 	u8 padding[5];
 };
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index f2aaef2cfb86..e73a4a5165ee 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -50,7 +50,7 @@
 #define QEDE_MAJOR_VERSION		8
 #define QEDE_MINOR_VERSION		10
 #define QEDE_REVISION_VERSION		10
-#define QEDE_ENGINEERING_VERSION	20
+#define QEDE_ENGINEERING_VERSION	21
 #define DRV_MODULE_VERSION __stringify(QEDE_MAJOR_VERSION) "."	\
 		__stringify(QEDE_MINOR_VERSION) "."		\
 		__stringify(QEDE_REVISION_VERSION) "."		\
@@ -58,7 +58,7 @@
 
 #define DRV_MODULE_SYM		qede
 
-struct qede_stats {
+struct qede_stats_common {
 	u64 no_buff_discards;
 	u64 packet_too_big_discard;
 	u64 ttl0_discard;
@@ -90,11 +90,6 @@ struct qede_stats {
 	u64 rx_256_to_511_byte_packets;
 	u64 rx_512_to_1023_byte_packets;
 	u64 rx_1024_to_1518_byte_packets;
-	u64 rx_1519_to_1522_byte_packets;
-	u64 rx_1519_to_2047_byte_packets;
-	u64 rx_2048_to_4095_byte_packets;
-	u64 rx_4096_to_9216_byte_packets;
-	u64 rx_9217_to_16383_byte_packets;
 	u64 rx_crc_errors;
 	u64 rx_mac_crtl_frames;
 	u64 rx_pause_frames;
@@ -111,17 +106,39 @@ struct qede_stats {
 	u64 tx_256_to_511_byte_packets;
 	u64 tx_512_to_1023_byte_packets;
 	u64 tx_1024_to_1518_byte_packets;
+	u64 tx_pause_frames;
+	u64 tx_pfc_frames;
+	u64 brb_truncates;
+	u64 brb_discards;
+	u64 tx_mac_ctrl_frames;
+};
+
+struct qede_stats_bb {
+	u64 rx_1519_to_1522_byte_packets;
+	u64 rx_1519_to_2047_byte_packets;
+	u64 rx_2048_to_4095_byte_packets;
+	u64 rx_4096_to_9216_byte_packets;
+	u64 rx_9217_to_16383_byte_packets;
 	u64 tx_1519_to_2047_byte_packets;
 	u64 tx_2048_to_4095_byte_packets;
 	u64 tx_4096_to_9216_byte_packets;
 	u64 tx_9217_to_16383_byte_packets;
-	u64 tx_pause_frames;
-	u64 tx_pfc_frames;
 	u64 tx_lpi_entry_count;
 	u64 tx_total_collisions;
-	u64 brb_truncates;
-	u64 brb_discards;
-	u64 tx_mac_ctrl_frames;
+};
+
+struct qede_stats_ah {
+	u64 rx_1519_to_max_byte_packets;
+	u64 tx_1519_to_max_byte_packets;
+};
+
+struct qede_stats {
+	struct qede_stats_common common;
+
+	union {
+		struct qede_stats_bb bb;
+		struct qede_stats_ah ah;
+	};
 };
 
 struct qede_vlan {
@@ -158,6 +175,10 @@ struct qede_dev {
 	struct qed_dev_eth_info dev_info;
 #define QEDE_MAX_RSS_CNT(edev)	((edev)->dev_info.num_queues)
 #define QEDE_MAX_TSS_CNT(edev)	((edev)->dev_info.num_queues)
+#define QEDE_IS_BB(edev) \
+	((edev)->dev_info.common.dev_type == QED_DEV_TYPE_BB)
+#define QEDE_IS_AH(edev) \
+	((edev)->dev_info.common.dev_type == QED_DEV_TYPE_AH)
 
 	struct qede_fastpath		*fp_array;
 	u8				req_num_tx;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index 897953133245..4dcfe9614731 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -75,16 +75,33 @@ static const struct {
 	QEDE_TQSTAT(stopped_cnt),
 };
 
-#define QEDE_STAT_OFFSET(stat_name) (offsetof(struct qede_stats, stat_name))
-#define QEDE_STAT_STRING(stat_name) (#stat_name)
-#define _QEDE_STAT(stat_name, pf_only) \
-	 {QEDE_STAT_OFFSET(stat_name), QEDE_STAT_STRING(stat_name), pf_only}
-#define QEDE_PF_STAT(stat_name)	_QEDE_STAT(stat_name, true)
-#define QEDE_STAT(stat_name)	_QEDE_STAT(stat_name, false)
+#define QEDE_STAT_OFFSET(stat_name, type, base) \
+	(offsetof(type, stat_name) + (base))
+#define QEDE_STAT_STRING(stat_name)	(#stat_name)
+#define _QEDE_STAT(stat_name, type, base, attr) \
+	{QEDE_STAT_OFFSET(stat_name, type, base), \
+	 QEDE_STAT_STRING(stat_name), \
+	 attr}
+#define QEDE_STAT(stat_name) \
+	_QEDE_STAT(stat_name, struct qede_stats_common, 0, 0x0)
+#define QEDE_PF_STAT(stat_name) \
+	_QEDE_STAT(stat_name, struct qede_stats_common, 0, \
+		   BIT(QEDE_STAT_PF_ONLY))
+#define QEDE_PF_BB_STAT(stat_name) \
+	_QEDE_STAT(stat_name, struct qede_stats_bb, \
+		   offsetof(struct qede_stats, bb), \
+		   BIT(QEDE_STAT_PF_ONLY) | BIT(QEDE_STAT_BB_ONLY))
+#define QEDE_PF_AH_STAT(stat_name) \
+	_QEDE_STAT(stat_name, struct qede_stats_ah, \
+		   offsetof(struct qede_stats, ah), \
+		   BIT(QEDE_STAT_PF_ONLY) | BIT(QEDE_STAT_AH_ONLY))
 static const struct {
 	u64 offset;
 	char string[ETH_GSTRING_LEN];
-	bool pf_only;
+	unsigned long attr;
+#define QEDE_STAT_PF_ONLY	0
+#define QEDE_STAT_BB_ONLY	1
+#define QEDE_STAT_AH_ONLY	2
 } qede_stats_arr[] = {
 	QEDE_STAT(rx_ucast_bytes),
 	QEDE_STAT(rx_mcast_bytes),
@@ -106,22 +123,23 @@ static const struct {
 	QEDE_PF_STAT(rx_256_to_511_byte_packets),
 	QEDE_PF_STAT(rx_512_to_1023_byte_packets),
 	QEDE_PF_STAT(rx_1024_to_1518_byte_packets),
-	QEDE_PF_STAT(rx_1519_to_1522_byte_packets),
-	QEDE_PF_STAT(rx_1519_to_2047_byte_packets),
-	QEDE_PF_STAT(rx_2048_to_4095_byte_packets),
-	QEDE_PF_STAT(rx_4096_to_9216_byte_packets),
-	QEDE_PF_STAT(rx_9217_to_16383_byte_packets),
+	QEDE_PF_BB_STAT(rx_1519_to_1522_byte_packets),
+	QEDE_PF_BB_STAT(rx_1519_to_2047_byte_packets),
+	QEDE_PF_BB_STAT(rx_2048_to_4095_byte_packets),
+	QEDE_PF_BB_STAT(rx_4096_to_9216_byte_packets),
+	QEDE_PF_BB_STAT(rx_9217_to_16383_byte_packets),
+	QEDE_PF_AH_STAT(rx_1519_to_max_byte_packets),
 	QEDE_PF_STAT(tx_64_byte_packets),
 	QEDE_PF_STAT(tx_65_to_127_byte_packets),
 	QEDE_PF_STAT(tx_128_to_255_byte_packets),
 	QEDE_PF_STAT(tx_256_to_511_byte_packets),
 	QEDE_PF_STAT(tx_512_to_1023_byte_packets),
 	QEDE_PF_STAT(tx_1024_to_1518_byte_packets),
-	QEDE_PF_STAT(tx_1519_to_2047_byte_packets),
-	QEDE_PF_STAT(tx_2048_to_4095_byte_packets),
-	QEDE_PF_STAT(tx_4096_to_9216_byte_packets),
-	QEDE_PF_STAT(tx_9217_to_16383_byte_packets),
-
+	QEDE_PF_BB_STAT(tx_1519_to_2047_byte_packets),
+	QEDE_PF_BB_STAT(tx_2048_to_4095_byte_packets),
+	QEDE_PF_BB_STAT(tx_4096_to_9216_byte_packets),
+	QEDE_PF_BB_STAT(tx_9217_to_16383_byte_packets),
+	QEDE_PF_AH_STAT(tx_1519_to_max_byte_packets),
 	QEDE_PF_STAT(rx_mac_crtl_frames),
 	QEDE_PF_STAT(tx_mac_ctrl_frames),
 	QEDE_PF_STAT(rx_pause_frames),
@@ -136,8 +154,8 @@ static const struct {
 	QEDE_PF_STAT(rx_jabbers),
 	QEDE_PF_STAT(rx_undersize_packets),
 	QEDE_PF_STAT(rx_fragments),
-	QEDE_PF_STAT(tx_lpi_entry_count),
-	QEDE_PF_STAT(tx_total_collisions),
+	QEDE_PF_BB_STAT(tx_lpi_entry_count),
+	QEDE_PF_BB_STAT(tx_total_collisions),
 	QEDE_PF_STAT(brb_truncates),
 	QEDE_PF_STAT(brb_discards),
 	QEDE_STAT(no_buff_discards),
@@ -155,6 +173,12 @@ static const struct {
 };
 
 #define QEDE_NUM_STATS	ARRAY_SIZE(qede_stats_arr)
+#define QEDE_STAT_IS_PF_ONLY(i) \
+	test_bit(QEDE_STAT_PF_ONLY, &qede_stats_arr[i].attr)
+#define QEDE_STAT_IS_BB_ONLY(i) \
+	test_bit(QEDE_STAT_BB_ONLY, &qede_stats_arr[i].attr)
+#define QEDE_STAT_IS_AH_ONLY(i) \
+	test_bit(QEDE_STAT_AH_ONLY, &qede_stats_arr[i].attr)
 
 enum {
 	QEDE_PRI_FLAG_CMT,
@@ -213,6 +237,13 @@ static void qede_get_strings_stats_rxq(struct qede_dev *edev,
 	}
 }
 
+static bool qede_is_irrelevant_stat(struct qede_dev *edev, int stat_index)
+{
+	return (IS_VF(edev) && QEDE_STAT_IS_PF_ONLY(stat_index)) ||
+	       (QEDE_IS_BB(edev) && QEDE_STAT_IS_AH_ONLY(stat_index)) ||
+	       (QEDE_IS_AH(edev) && QEDE_STAT_IS_BB_ONLY(stat_index));
+}
+
 static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf)
 {
 	struct qede_fastpath *fp;
@@ -234,7 +265,7 @@ static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf)
 
 	/* Account for non-queue statistics */
 	for (i = 0; i < QEDE_NUM_STATS; i++) {
-		if (IS_VF(edev) && qede_stats_arr[i].pf_only)
+		if (qede_is_irrelevant_stat(edev, i))
 			continue;
 		strcpy(buf, qede_stats_arr[i].string);
 		buf += ETH_GSTRING_LEN;
@@ -309,7 +340,7 @@ static void qede_get_ethtool_stats(struct net_device *dev,
 	}
 
 	for (i = 0; i < QEDE_NUM_STATS; i++) {
-		if (IS_VF(edev) && qede_stats_arr[i].pf_only)
+		if (qede_is_irrelevant_stat(edev, i))
 			continue;
 		*buf = *((u64 *)(((void *)&edev->stats) +
 				 qede_stats_arr[i].offset));
@@ -323,17 +354,13 @@ static void qede_get_ethtool_stats(struct net_device *dev,
 static int qede_get_sset_count(struct net_device *dev, int stringset)
 {
 	struct qede_dev *edev = netdev_priv(dev);
-	int num_stats = QEDE_NUM_STATS;
+	int num_stats = QEDE_NUM_STATS, i;
 
 	switch (stringset) {
 	case ETH_SS_STATS:
-		if (IS_VF(edev)) {
-			int i;
-
-			for (i = 0; i < QEDE_NUM_STATS; i++)
-				if (qede_stats_arr[i].pf_only)
-					num_stats--;
-		}
+		for (i = 0; i < QEDE_NUM_STATS; i++)
+			if (qede_is_irrelevant_stat(edev, i))
+				num_stats--;
 
 		/* Account for the Regular Tx statistics */
 		num_stats += QEDE_TSS_COUNT(edev) * QEDE_NUM_TQSTATS;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 3a78c3f25157..abd99109e532 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -84,6 +84,8 @@ static const struct qed_eth_ops *qed_ops;
 #define CHIP_NUM_57980S_50		0x1654
 #define CHIP_NUM_57980S_25		0x1656
 #define CHIP_NUM_57980S_IOV		0x1664
+#define CHIP_NUM_AH			0x8070
+#define CHIP_NUM_AH_IOV			0x8090
 
 #ifndef PCI_DEVICE_ID_NX2_57980E
 #define PCI_DEVICE_ID_57980S_40		CHIP_NUM_57980S_40
@@ -93,6 +95,9 @@ static const struct qed_eth_ops *qed_ops;
 #define PCI_DEVICE_ID_57980S_50		CHIP_NUM_57980S_50
 #define PCI_DEVICE_ID_57980S_25		CHIP_NUM_57980S_25
 #define PCI_DEVICE_ID_57980S_IOV	CHIP_NUM_57980S_IOV
+#define PCI_DEVICE_ID_AH		CHIP_NUM_AH
+#define PCI_DEVICE_ID_AH_IOV		CHIP_NUM_AH_IOV
+
 #endif
 
 enum qede_pci_private {
@@ -110,6 +115,10 @@ static const struct pci_device_id qede_pci_tbl[] = {
 #ifdef CONFIG_QED_SRIOV
 	{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_IOV), QEDE_PRIVATE_VF},
 #endif
+	{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_AH), QEDE_PRIVATE_PF},
+#ifdef CONFIG_QED_SRIOV
+	{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_AH_IOV), QEDE_PRIVATE_VF},
+#endif
 	{ 0 }
 };
 
@@ -314,122 +323,135 @@ static int qede_close(struct net_device *ndev);
 
 void qede_fill_by_demand_stats(struct qede_dev *edev)
 {
+	struct qede_stats_common *p_common = &edev->stats.common;
 	struct qed_eth_stats stats;
 
 	edev->ops->get_vport_stats(edev->cdev, &stats);
-	edev->stats.no_buff_discards = stats.no_buff_discards;
-	edev->stats.packet_too_big_discard = stats.packet_too_big_discard;
-	edev->stats.ttl0_discard = stats.ttl0_discard;
-	edev->stats.rx_ucast_bytes = stats.rx_ucast_bytes;
-	edev->stats.rx_mcast_bytes = stats.rx_mcast_bytes;
-	edev->stats.rx_bcast_bytes = stats.rx_bcast_bytes;
-	edev->stats.rx_ucast_pkts = stats.rx_ucast_pkts;
-	edev->stats.rx_mcast_pkts = stats.rx_mcast_pkts;
-	edev->stats.rx_bcast_pkts = stats.rx_bcast_pkts;
-	edev->stats.mftag_filter_discards = stats.mftag_filter_discards;
-	edev->stats.mac_filter_discards = stats.mac_filter_discards;
-
-	edev->stats.tx_ucast_bytes = stats.tx_ucast_bytes;
-	edev->stats.tx_mcast_bytes = stats.tx_mcast_bytes;
-	edev->stats.tx_bcast_bytes = stats.tx_bcast_bytes;
-	edev->stats.tx_ucast_pkts = stats.tx_ucast_pkts;
-	edev->stats.tx_mcast_pkts = stats.tx_mcast_pkts;
-	edev->stats.tx_bcast_pkts = stats.tx_bcast_pkts;
-	edev->stats.tx_err_drop_pkts = stats.tx_err_drop_pkts;
-	edev->stats.coalesced_pkts = stats.tpa_coalesced_pkts;
-	edev->stats.coalesced_events = stats.tpa_coalesced_events;
-	edev->stats.coalesced_aborts_num = stats.tpa_aborts_num;
-	edev->stats.non_coalesced_pkts = stats.tpa_not_coalesced_pkts;
-	edev->stats.coalesced_bytes = stats.tpa_coalesced_bytes;
-
-	edev->stats.rx_64_byte_packets = stats.rx_64_byte_packets;
-	edev->stats.rx_65_to_127_byte_packets = stats.rx_65_to_127_byte_packets;
-	edev->stats.rx_128_to_255_byte_packets =
-				stats.rx_128_to_255_byte_packets;
-	edev->stats.rx_256_to_511_byte_packets =
-				stats.rx_256_to_511_byte_packets;
-	edev->stats.rx_512_to_1023_byte_packets =
-				stats.rx_512_to_1023_byte_packets;
-	edev->stats.rx_1024_to_1518_byte_packets =
-				stats.rx_1024_to_1518_byte_packets;
-	edev->stats.rx_1519_to_1522_byte_packets =
-				stats.rx_1519_to_1522_byte_packets;
-	edev->stats.rx_1519_to_2047_byte_packets =
-				stats.rx_1519_to_2047_byte_packets;
-	edev->stats.rx_2048_to_4095_byte_packets =
-				stats.rx_2048_to_4095_byte_packets;
-	edev->stats.rx_4096_to_9216_byte_packets =
-				stats.rx_4096_to_9216_byte_packets;
-	edev->stats.rx_9217_to_16383_byte_packets =
-				stats.rx_9217_to_16383_byte_packets;
-	edev->stats.rx_crc_errors = stats.rx_crc_errors;
-	edev->stats.rx_mac_crtl_frames = stats.rx_mac_crtl_frames;
-	edev->stats.rx_pause_frames = stats.rx_pause_frames;
-	edev->stats.rx_pfc_frames = stats.rx_pfc_frames;
-	edev->stats.rx_align_errors = stats.rx_align_errors;
-	edev->stats.rx_carrier_errors = stats.rx_carrier_errors;
-	edev->stats.rx_oversize_packets = stats.rx_oversize_packets;
-	edev->stats.rx_jabbers = stats.rx_jabbers;
-	edev->stats.rx_undersize_packets = stats.rx_undersize_packets;
-	edev->stats.rx_fragments = stats.rx_fragments;
-	edev->stats.tx_64_byte_packets = stats.tx_64_byte_packets;
-	edev->stats.tx_65_to_127_byte_packets = stats.tx_65_to_127_byte_packets;
-	edev->stats.tx_128_to_255_byte_packets =
-				stats.tx_128_to_255_byte_packets;
-	edev->stats.tx_256_to_511_byte_packets =
-				stats.tx_256_to_511_byte_packets;
-	edev->stats.tx_512_to_1023_byte_packets =
-				stats.tx_512_to_1023_byte_packets;
-	edev->stats.tx_1024_to_1518_byte_packets =
-				stats.tx_1024_to_1518_byte_packets;
-	edev->stats.tx_1519_to_2047_byte_packets =
-				stats.tx_1519_to_2047_byte_packets;
-	edev->stats.tx_2048_to_4095_byte_packets =
-				stats.tx_2048_to_4095_byte_packets;
-	edev->stats.tx_4096_to_9216_byte_packets =
-				stats.tx_4096_to_9216_byte_packets;
-	edev->stats.tx_9217_to_16383_byte_packets =
-				stats.tx_9217_to_16383_byte_packets;
-	edev->stats.tx_pause_frames = stats.tx_pause_frames;
-	edev->stats.tx_pfc_frames = stats.tx_pfc_frames;
-	edev->stats.tx_lpi_entry_count = stats.tx_lpi_entry_count;
-	edev->stats.tx_total_collisions = stats.tx_total_collisions;
-	edev->stats.brb_truncates = stats.brb_truncates;
-	edev->stats.brb_discards = stats.brb_discards;
-	edev->stats.tx_mac_ctrl_frames = stats.tx_mac_ctrl_frames;
+
+	p_common->no_buff_discards = stats.common.no_buff_discards;
+	p_common->packet_too_big_discard = stats.common.packet_too_big_discard;
+	p_common->ttl0_discard = stats.common.ttl0_discard;
+	p_common->rx_ucast_bytes = stats.common.rx_ucast_bytes;
+	p_common->rx_mcast_bytes = stats.common.rx_mcast_bytes;
+	p_common->rx_bcast_bytes = stats.common.rx_bcast_bytes;
+	p_common->rx_ucast_pkts = stats.common.rx_ucast_pkts;
+	p_common->rx_mcast_pkts = stats.common.rx_mcast_pkts;
+	p_common->rx_bcast_pkts = stats.common.rx_bcast_pkts;
+	p_common->mftag_filter_discards = stats.common.mftag_filter_discards;
+	p_common->mac_filter_discards = stats.common.mac_filter_discards;
+
+	p_common->tx_ucast_bytes = stats.common.tx_ucast_bytes;
+	p_common->tx_mcast_bytes = stats.common.tx_mcast_bytes;
+	p_common->tx_bcast_bytes = stats.common.tx_bcast_bytes;
+	p_common->tx_ucast_pkts = stats.common.tx_ucast_pkts;
+	p_common->tx_mcast_pkts = stats.common.tx_mcast_pkts;
+	p_common->tx_bcast_pkts = stats.common.tx_bcast_pkts;
+	p_common->tx_err_drop_pkts = stats.common.tx_err_drop_pkts;
+	p_common->coalesced_pkts = stats.common.tpa_coalesced_pkts;
+	p_common->coalesced_events = stats.common.tpa_coalesced_events;
+	p_common->coalesced_aborts_num = stats.common.tpa_aborts_num;
+	p_common->non_coalesced_pkts = stats.common.tpa_not_coalesced_pkts;
+	p_common->coalesced_bytes = stats.common.tpa_coalesced_bytes;
+
+	p_common->rx_64_byte_packets = stats.common.rx_64_byte_packets;
+	p_common->rx_65_to_127_byte_packets =
+	    stats.common.rx_65_to_127_byte_packets;
+	p_common->rx_128_to_255_byte_packets =
+	    stats.common.rx_128_to_255_byte_packets;
+	p_common->rx_256_to_511_byte_packets =
+	    stats.common.rx_256_to_511_byte_packets;
+	p_common->rx_512_to_1023_byte_packets =
+	    stats.common.rx_512_to_1023_byte_packets;
+	p_common->rx_1024_to_1518_byte_packets =
+	    stats.common.rx_1024_to_1518_byte_packets;
+	p_common->rx_crc_errors = stats.common.rx_crc_errors;
+	p_common->rx_mac_crtl_frames = stats.common.rx_mac_crtl_frames;
+	p_common->rx_pause_frames = stats.common.rx_pause_frames;
+	p_common->rx_pfc_frames = stats.common.rx_pfc_frames;
+	p_common->rx_align_errors = stats.common.rx_align_errors;
+	p_common->rx_carrier_errors = stats.common.rx_carrier_errors;
+	p_common->rx_oversize_packets = stats.common.rx_oversize_packets;
+	p_common->rx_jabbers = stats.common.rx_jabbers;
+	p_common->rx_undersize_packets = stats.common.rx_undersize_packets;
+	p_common->rx_fragments = stats.common.rx_fragments;
+	p_common->tx_64_byte_packets = stats.common.tx_64_byte_packets;
+	p_common->tx_65_to_127_byte_packets =
+	    stats.common.tx_65_to_127_byte_packets;
+	p_common->tx_128_to_255_byte_packets =
+	    stats.common.tx_128_to_255_byte_packets;
+	p_common->tx_256_to_511_byte_packets =
+	    stats.common.tx_256_to_511_byte_packets;
+	p_common->tx_512_to_1023_byte_packets =
+	    stats.common.tx_512_to_1023_byte_packets;
+	p_common->tx_1024_to_1518_byte_packets =
+	    stats.common.tx_1024_to_1518_byte_packets;
+	p_common->tx_pause_frames = stats.common.tx_pause_frames;
+	p_common->tx_pfc_frames = stats.common.tx_pfc_frames;
+	p_common->brb_truncates = stats.common.brb_truncates;
+	p_common->brb_discards = stats.common.brb_discards;
+	p_common->tx_mac_ctrl_frames = stats.common.tx_mac_ctrl_frames;
+
+	if (QEDE_IS_BB(edev)) {
+		struct qede_stats_bb *p_bb = &edev->stats.bb;
+
+		p_bb->rx_1519_to_1522_byte_packets =
+		    stats.bb.rx_1519_to_1522_byte_packets;
+		p_bb->rx_1519_to_2047_byte_packets =
+		    stats.bb.rx_1519_to_2047_byte_packets;
+		p_bb->rx_2048_to_4095_byte_packets =
+		    stats.bb.rx_2048_to_4095_byte_packets;
+		p_bb->rx_4096_to_9216_byte_packets =
+		    stats.bb.rx_4096_to_9216_byte_packets;
+		p_bb->rx_9217_to_16383_byte_packets =
+		    stats.bb.rx_9217_to_16383_byte_packets;
+		p_bb->tx_1519_to_2047_byte_packets =
+		    stats.bb.tx_1519_to_2047_byte_packets;
+		p_bb->tx_2048_to_4095_byte_packets =
+		    stats.bb.tx_2048_to_4095_byte_packets;
+		p_bb->tx_4096_to_9216_byte_packets =
+		    stats.bb.tx_4096_to_9216_byte_packets;
+		p_bb->tx_9217_to_16383_byte_packets =
+		    stats.bb.tx_9217_to_16383_byte_packets;
+		p_bb->tx_lpi_entry_count = stats.bb.tx_lpi_entry_count;
+		p_bb->tx_total_collisions = stats.bb.tx_total_collisions;
+	} else {
+		struct qede_stats_ah *p_ah = &edev->stats.ah;
+
+		p_ah->rx_1519_to_max_byte_packets =
+		    stats.ah.rx_1519_to_max_byte_packets;
+		p_ah->tx_1519_to_max_byte_packets =
+		    stats.ah.tx_1519_to_max_byte_packets;
+	}
 }
 
 static void qede_get_stats64(struct net_device *dev,
 			     struct rtnl_link_stats64 *stats)
 {
 	struct qede_dev *edev = netdev_priv(dev);
+	struct qede_stats_common *p_common;
 
 	qede_fill_by_demand_stats(edev);
+	p_common = &edev->stats.common;
 
-	stats->rx_packets = edev->stats.rx_ucast_pkts +
-			    edev->stats.rx_mcast_pkts +
-			    edev->stats.rx_bcast_pkts;
-	stats->tx_packets = edev->stats.tx_ucast_pkts +
-			    edev->stats.tx_mcast_pkts +
-			    edev->stats.tx_bcast_pkts;
-
-	stats->rx_bytes = edev->stats.rx_ucast_bytes +
-			  edev->stats.rx_mcast_bytes +
-			  edev->stats.rx_bcast_bytes;
+	stats->rx_packets = p_common->rx_ucast_pkts + p_common->rx_mcast_pkts +
+			    p_common->rx_bcast_pkts;
+	stats->tx_packets = p_common->tx_ucast_pkts + p_common->tx_mcast_pkts +
+			    p_common->tx_bcast_pkts;
 
-	stats->tx_bytes = edev->stats.tx_ucast_bytes +
-			  edev->stats.tx_mcast_bytes +
-			  edev->stats.tx_bcast_bytes;
+	stats->rx_bytes = p_common->rx_ucast_bytes + p_common->rx_mcast_bytes +
+			  p_common->rx_bcast_bytes;
+	stats->tx_bytes = p_common->tx_ucast_bytes + p_common->tx_mcast_bytes +
+			  p_common->tx_bcast_bytes;
 
-	stats->tx_errors = edev->stats.tx_err_drop_pkts;
-	stats->multicast = edev->stats.rx_mcast_pkts +
-			   edev->stats.rx_bcast_pkts;
+	stats->tx_errors = p_common->tx_err_drop_pkts;
+	stats->multicast = p_common->rx_mcast_pkts + p_common->rx_bcast_pkts;
 
-	stats->rx_fifo_errors = edev->stats.no_buff_discards;
+	stats->rx_fifo_errors = p_common->no_buff_discards;
 
-	stats->collisions = edev->stats.tx_total_collisions;
-	stats->rx_crc_errors = edev->stats.rx_crc_errors;
-	stats->rx_frame_errors = edev->stats.rx_align_errors;
+	if (QEDE_IS_BB(edev))
+		stats->collisions = edev->stats.bb.tx_total_collisions;
+	stats->rx_crc_errors = p_common->rx_crc_errors;
+	stats->rx_frame_errors = p_common->rx_align_errors;
 }
 
 #ifdef CONFIG_QED_SRIOV
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c
index f62c215be779..7116be485e61 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c
@@ -26,6 +26,7 @@
 
 /* SGMII digital lane registers */
 #define EMAC_SGMII_LN_DRVR_CTRL0		0x000C
+#define EMAC_SGMII_LN_DRVR_CTRL1		0x0010
 #define EMAC_SGMII_LN_DRVR_TAP_EN		0x0018
 #define EMAC_SGMII_LN_TX_MARGINING		0x001C
 #define EMAC_SGMII_LN_TX_PRE			0x0020
@@ -48,6 +49,7 @@
 #define EMAC_SGMII_LN_RX_EN_SIGNAL		0x02AC
 #define EMAC_SGMII_LN_RX_MISC_CNTRL0		0x02B8
 #define EMAC_SGMII_LN_DRVR_LOGIC_CLKDIV		0x02C8
+#define EMAC_SGMII_LN_RX_RESECODE_OFFSET	0x02CC
 
 /* SGMII digital lane register values */
 #define UCDR_STEP_BY_TWO_MODE0			BIT(7)
@@ -73,6 +75,8 @@
 #define CML_GEAR_MODE(x)			(((x) & 7) << 3)
 #define CML2CMOS_IBOOST_MODE(x)			((x) & 7)
 
+#define RESCODE_OFFSET(x)			((x) & 0x1f)
+
 #define MIXER_LOADB_MODE(x)			(((x) & 0xf) << 2)
 #define MIXER_DATARATE_MODE(x)			((x) & 3)
 
@@ -159,6 +163,8 @@ static const struct emac_reg_write sgmii_laned[] = {
 	{EMAC_SGMII_LN_PARALLEL_RATE, PARALLEL_RATE_MODE0(1)},
 	{EMAC_SGMII_LN_TX_BAND_MODE, BAND_MODE0(1)},
 	{EMAC_SGMII_LN_RX_BAND, BAND_MODE0(2)},
+	{EMAC_SGMII_LN_DRVR_CTRL1, RESCODE_OFFSET(7)},
+	{EMAC_SGMII_LN_RX_RESECODE_OFFSET, RESCODE_OFFSET(9)},
 	{EMAC_SGMII_LN_LANE_MODE, LANE_MODE(26)},
 	{EMAC_SGMII_LN_RX_RCVR_PATH1_MODE0, CDR_PD_SEL_MODE0(2) |
 		EN_DLL_MODE0 | EN_IQ_DCC_MODE0 | EN_IQCAL_MODE0},
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
index 040b28977ee7..18c184ee1f3c 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
@@ -13,6 +13,7 @@
 /* Qualcomm Technologies, Inc. EMAC SGMII Controller driver.
  */
 
+#include <linux/interrupt.h>
 #include <linux/iopoll.h>
 #include <linux/acpi.h>
 #include <linux/of_device.h>
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index 672f6b696069..72233ab9474b 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -1406,27 +1406,29 @@ static int cp_get_sset_count (struct net_device *dev, int sset)
 	}
 }
 
-static int cp_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int cp_get_link_ksettings(struct net_device *dev,
+				 struct ethtool_link_ksettings *cmd)
 {
 	struct cp_private *cp = netdev_priv(dev);
 	int rc;
 	unsigned long flags;
 
 	spin_lock_irqsave(&cp->lock, flags);
-	rc = mii_ethtool_gset(&cp->mii_if, cmd);
+	rc = mii_ethtool_get_link_ksettings(&cp->mii_if, cmd);
 	spin_unlock_irqrestore(&cp->lock, flags);
 
 	return rc;
 }
 
-static int cp_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int cp_set_link_ksettings(struct net_device *dev,
+				 const struct ethtool_link_ksettings *cmd)
 {
 	struct cp_private *cp = netdev_priv(dev);
 	int rc;
 	unsigned long flags;
 
 	spin_lock_irqsave(&cp->lock, flags);
-	rc = mii_ethtool_sset(&cp->mii_if, cmd);
+	rc = mii_ethtool_set_link_ksettings(&cp->mii_if, cmd);
 	spin_unlock_irqrestore(&cp->lock, flags);
 
 	return rc;
@@ -1578,8 +1580,6 @@ static const struct ethtool_ops cp_ethtool_ops = {
 	.get_drvinfo		= cp_get_drvinfo,
 	.get_regs_len		= cp_get_regs_len,
 	.get_sset_count		= cp_get_sset_count,
-	.get_settings		= cp_get_settings,
-	.set_settings		= cp_set_settings,
 	.nway_reset		= cp_nway_reset,
 	.get_link		= ethtool_op_get_link,
 	.get_msglevel		= cp_get_msglevel,
@@ -1593,6 +1593,8 @@ static const struct ethtool_ops cp_ethtool_ops = {
 	.get_eeprom		= cp_get_eeprom,
 	.set_eeprom		= cp_set_eeprom,
 	.get_ringparam		= cp_get_ringparam,
+	.get_link_ksettings	= cp_get_link_ksettings,
+	.set_link_ksettings	= cp_set_link_ksettings,
 };
 
 static int cp_ioctl (struct net_device *dev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index 89631753e799..ca22f2898664 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -2384,21 +2384,23 @@ static void rtl8139_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *
 	strlcpy(info->bus_info, pci_name(tp->pci_dev), sizeof(info->bus_info));
 }
 
-static int rtl8139_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int rtl8139_get_link_ksettings(struct net_device *dev,
+				      struct ethtool_link_ksettings *cmd)
 {
 	struct rtl8139_private *tp = netdev_priv(dev);
 	spin_lock_irq(&tp->lock);
-	mii_ethtool_gset(&tp->mii, cmd);
+	mii_ethtool_get_link_ksettings(&tp->mii, cmd);
 	spin_unlock_irq(&tp->lock);
 	return 0;
 }
 
-static int rtl8139_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int rtl8139_set_link_ksettings(struct net_device *dev,
+				      const struct ethtool_link_ksettings *cmd)
 {
 	struct rtl8139_private *tp = netdev_priv(dev);
 	int rc;
 	spin_lock_irq(&tp->lock);
-	rc = mii_ethtool_sset(&tp->mii, cmd);
+	rc = mii_ethtool_set_link_ksettings(&tp->mii, cmd);
 	spin_unlock_irq(&tp->lock);
 	return rc;
 }
@@ -2480,8 +2482,6 @@ static void rtl8139_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 
 static const struct ethtool_ops rtl8139_ethtool_ops = {
 	.get_drvinfo		= rtl8139_get_drvinfo,
-	.get_settings		= rtl8139_get_settings,
-	.set_settings		= rtl8139_set_settings,
 	.get_regs_len		= rtl8139_get_regs_len,
 	.get_regs		= rtl8139_get_regs,
 	.nway_reset		= rtl8139_nway_reset,
@@ -2493,6 +2493,8 @@ static const struct ethtool_ops rtl8139_ethtool_ops = {
 	.get_strings		= rtl8139_get_strings,
 	.get_sset_count		= rtl8139_get_sset_count,
 	.get_ethtool_stats	= rtl8139_get_ethtool_stats,
+	.get_link_ksettings	= rtl8139_get_link_ksettings,
+	.set_link_ksettings	= rtl8139_set_link_ksettings,
 };
 
 static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 81f18a833527..0a8f2817ea60 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -817,7 +817,8 @@ struct rtl8169_private {
 	} csi_ops;
 
 	int (*set_speed)(struct net_device *, u8 aneg, u16 sp, u8 dpx, u32 adv);
-	int (*get_settings)(struct net_device *, struct ethtool_cmd *);
+	int (*get_link_ksettings)(struct net_device *,
+				  struct ethtool_link_ksettings *);
 	void (*phy_reset_enable)(struct rtl8169_private *tp);
 	void (*hw_start)(struct net_device *);
 	unsigned int (*phy_reset_pending)(struct rtl8169_private *tp);
@@ -2115,41 +2116,49 @@ static void rtl8169_rx_vlan_tag(struct RxDesc *desc, struct sk_buff *skb)
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), swab16(opts2 & 0xffff));
 }
 
-static int rtl8169_gset_tbi(struct net_device *dev, struct ethtool_cmd *cmd)
+static int rtl8169_get_link_ksettings_tbi(struct net_device *dev,
+					  struct ethtool_link_ksettings *cmd)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 	void __iomem *ioaddr = tp->mmio_addr;
 	u32 status;
+	u32 supported, advertising;
 
-	cmd->supported =
+	supported =
 		SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg | SUPPORTED_FIBRE;
-	cmd->port = PORT_FIBRE;
-	cmd->transceiver = XCVR_INTERNAL;
+	cmd->base.port = PORT_FIBRE;
 
 	status = RTL_R32(TBICSR);
-	cmd->advertising = (status & TBINwEnable) ?  ADVERTISED_Autoneg : 0;
-	cmd->autoneg = !!(status & TBINwEnable);
+	advertising = (status & TBINwEnable) ?  ADVERTISED_Autoneg : 0;
+	cmd->base.autoneg = !!(status & TBINwEnable);
 
-	ethtool_cmd_speed_set(cmd, SPEED_1000);
-	cmd->duplex = DUPLEX_FULL; /* Always set */
+	cmd->base.speed = SPEED_1000;
+	cmd->base.duplex = DUPLEX_FULL; /* Always set */
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 
 	return 0;
 }
 
-static int rtl8169_gset_xmii(struct net_device *dev, struct ethtool_cmd *cmd)
+static int rtl8169_get_link_ksettings_xmii(struct net_device *dev,
+					   struct ethtool_link_ksettings *cmd)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	return mii_ethtool_gset(&tp->mii, cmd);
+	return mii_ethtool_get_link_ksettings(&tp->mii, cmd);
 }
 
-static int rtl8169_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int rtl8169_get_link_ksettings(struct net_device *dev,
+				      struct ethtool_link_ksettings *cmd)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 	int rc;
 
 	rtl_lock_work(tp);
-	rc = tp->get_settings(dev, cmd);
+	rc = tp->get_link_ksettings(dev, cmd);
 	rtl_unlock_work(tp);
 
 	return rc;
@@ -2356,7 +2365,6 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_drvinfo		= rtl8169_get_drvinfo,
 	.get_regs_len		= rtl8169_get_regs_len,
 	.get_link		= ethtool_op_get_link,
-	.get_settings		= rtl8169_get_settings,
 	.set_settings		= rtl8169_set_settings,
 	.get_msglevel		= rtl8169_get_msglevel,
 	.set_msglevel		= rtl8169_set_msglevel,
@@ -2368,6 +2376,7 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_ethtool_stats	= rtl8169_get_ethtool_stats,
 	.get_ts_info		= ethtool_op_get_ts_info,
 	.nway_reset		= rtl8169_nway_reset,
+	.get_link_ksettings	= rtl8169_get_link_ksettings,
 };
 
 static void rtl8169_get_mac_version(struct rtl8169_private *tp,
@@ -8351,14 +8360,14 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	if (rtl_tbi_enabled(tp)) {
 		tp->set_speed = rtl8169_set_speed_tbi;
-		tp->get_settings = rtl8169_gset_tbi;
+		tp->get_link_ksettings = rtl8169_get_link_ksettings_tbi;
 		tp->phy_reset_enable = rtl8169_tbi_reset_enable;
 		tp->phy_reset_pending = rtl8169_tbi_reset_pending;
 		tp->link_ok = rtl8169_tbi_link_ok;
 		tp->do_ioctl = rtl_tbi_ioctl;
 	} else {
 		tp->set_speed = rtl8169_set_speed_xmii;
-		tp->get_settings = rtl8169_gset_xmii;
+		tp->get_link_ksettings = rtl8169_get_link_ksettings_xmii;
 		tp->phy_reset_enable = rtl8169_xmii_reset_enable;
 		tp->phy_reset_pending = rtl8169_xmii_reset_pending;
 		tp->link_ok = rtl8169_xmii_link_ok;
@@ -8444,9 +8453,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	tp->opts1_mask = (tp->mac_version != RTL_GIGA_MAC_VER_01) ?
 		~(RxBOVF | RxFOVF) : ~0;
 
-	init_timer(&tp->timer);
-	tp->timer.data = (unsigned long) dev;
-	tp->timer.function = rtl8169_phy_timer;
+	setup_timer(&tp->timer, rtl8169_phy_timer, (unsigned long)dev);
 
 	tp->rtl_fw = RTL_FIRMWARE_UNKNOWN;
 
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 0f63a44a955d..bab13613b138 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -33,6 +33,7 @@
 #include <net/rtnetlink.h>
 #include <net/netevent.h>
 #include <net/arp.h>
+#include <net/fib_rules.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <generated/utsrelease.h>
 
@@ -1115,7 +1116,7 @@ rocker_cmd_get_port_settings_ethtool_proc(const struct rocker_port *rocker_port,
 					  const struct rocker_desc_info *desc_info,
 					  void *priv)
 {
-	struct ethtool_cmd *ecmd = priv;
+	struct ethtool_link_ksettings *ecmd = priv;
 	const struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1];
 	const struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1];
 	u32 speed;
@@ -1137,13 +1138,14 @@ rocker_cmd_get_port_settings_ethtool_proc(const struct rocker_port *rocker_port,
 	duplex = rocker_tlv_get_u8(info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_DUPLEX]);
 	autoneg = rocker_tlv_get_u8(info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_AUTONEG]);
 
-	ecmd->transceiver = XCVR_INTERNAL;
-	ecmd->supported = SUPPORTED_TP;
-	ecmd->phy_address = 0xff;
-	ecmd->port = PORT_TP;
-	ethtool_cmd_speed_set(ecmd, speed);
-	ecmd->duplex = duplex ? DUPLEX_FULL : DUPLEX_HALF;
-	ecmd->autoneg = autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE;
+	ethtool_link_ksettings_zero_link_mode(ecmd, supported);
+	ethtool_link_ksettings_add_link_mode(ecmd, supported, TP);
+
+	ecmd->base.phy_address = 0xff;
+	ecmd->base.port = PORT_TP;
+	ecmd->base.speed = speed;
+	ecmd->base.duplex = duplex ? DUPLEX_FULL : DUPLEX_HALF;
+	ecmd->base.autoneg = autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE;
 
 	return 0;
 }
@@ -1250,7 +1252,7 @@ rocker_cmd_set_port_settings_ethtool_prep(const struct rocker_port *rocker_port,
 					  struct rocker_desc_info *desc_info,
 					  void *priv)
 {
-	struct ethtool_cmd *ecmd = priv;
+	struct ethtool_link_ksettings *ecmd = priv;
 	struct rocker_tlv *cmd_info;
 
 	if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE,
@@ -1263,13 +1265,13 @@ rocker_cmd_set_port_settings_ethtool_prep(const struct rocker_port *rocker_port,
 			       rocker_port->pport))
 		return -EMSGSIZE;
 	if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_SPEED,
-			       ethtool_cmd_speed(ecmd)))
+			       ecmd->base.speed))
 		return -EMSGSIZE;
 	if (rocker_tlv_put_u8(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_DUPLEX,
-			      ecmd->duplex))
+			      ecmd->base.duplex))
 		return -EMSGSIZE;
 	if (rocker_tlv_put_u8(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_AUTONEG,
-			      ecmd->autoneg))
+			      ecmd->base.autoneg))
 		return -EMSGSIZE;
 	rocker_tlv_nest_end(desc_info, cmd_info);
 	return 0;
@@ -1347,8 +1349,9 @@ rocker_cmd_set_port_learning_prep(const struct rocker_port *rocker_port,
 	return 0;
 }
 
-static int rocker_cmd_get_port_settings_ethtool(struct rocker_port *rocker_port,
-						struct ethtool_cmd *ecmd)
+static int
+rocker_cmd_get_port_settings_ethtool(struct rocker_port *rocker_port,
+				     struct ethtool_link_ksettings *ecmd)
 {
 	return rocker_cmd_exec(rocker_port, false,
 			       rocker_cmd_get_port_settings_prep, NULL,
@@ -1373,12 +1376,17 @@ static int rocker_cmd_get_port_settings_mode(struct rocker_port *rocker_port,
 			       rocker_cmd_get_port_settings_mode_proc, p_mode);
 }
 
-static int rocker_cmd_set_port_settings_ethtool(struct rocker_port *rocker_port,
-						struct ethtool_cmd *ecmd)
+static int
+rocker_cmd_set_port_settings_ethtool(struct rocker_port *rocker_port,
+				     const struct ethtool_link_ksettings *ecmd)
 {
+	struct ethtool_link_ksettings copy_ecmd;
+
+	memcpy(&copy_ecmd, ecmd, sizeof(copy_ecmd));
+
 	return rocker_cmd_exec(rocker_port, false,
 			       rocker_cmd_set_port_settings_ethtool_prep,
-			       ecmd, NULL, NULL);
+			       &copy_ecmd, NULL, NULL);
 }
 
 static int rocker_cmd_set_port_settings_macaddr(struct rocker_port *rocker_port,
@@ -2168,7 +2176,10 @@ static const struct switchdev_ops rocker_port_switchdev_ops = {
 
 struct rocker_fib_event_work {
 	struct work_struct work;
-	struct fib_entry_notifier_info fen_info;
+	union {
+		struct fib_entry_notifier_info fen_info;
+		struct fib_rule_notifier_info fr_info;
+	};
 	struct rocker *rocker;
 	unsigned long event;
 };
@@ -2178,6 +2189,7 @@ static void rocker_router_fib_event_work(struct work_struct *work)
 	struct rocker_fib_event_work *fib_work =
 		container_of(work, struct rocker_fib_event_work, work);
 	struct rocker *rocker = fib_work->rocker;
+	struct fib_rule *rule;
 	int err;
 
 	/* Protect internal structures from changes */
@@ -2195,7 +2207,10 @@ static void rocker_router_fib_event_work(struct work_struct *work)
 		break;
 	case FIB_EVENT_RULE_ADD: /* fall through */
 	case FIB_EVENT_RULE_DEL:
-		rocker_world_fib4_abort(rocker);
+		rule = fib_work->fr_info.rule;
+		if (!fib4_rule_default(rule))
+			rocker_world_fib4_abort(rocker);
+		fib_rule_put(rule);
 		break;
 	}
 	rtnl_unlock();
@@ -2226,6 +2241,11 @@ static int rocker_router_fib_event(struct notifier_block *nb,
 		 */
 		fib_info_hold(fib_work->fen_info.fi);
 		break;
+	case FIB_EVENT_RULE_ADD: /* fall through */
+	case FIB_EVENT_RULE_DEL:
+		memcpy(&fib_work->fr_info, ptr, sizeof(fib_work->fr_info));
+		fib_rule_get(fib_work->fr_info.rule);
+		break;
 	}
 
 	queue_work(rocker->rocker_owq, &fib_work->work);
@@ -2237,16 +2257,18 @@ static int rocker_router_fib_event(struct notifier_block *nb,
  * ethtool interface
  ********************/
 
-static int rocker_port_get_settings(struct net_device *dev,
-				    struct ethtool_cmd *ecmd)
+static int
+rocker_port_get_link_ksettings(struct net_device *dev,
+			       struct ethtool_link_ksettings *ecmd)
 {
 	struct rocker_port *rocker_port = netdev_priv(dev);
 
 	return rocker_cmd_get_port_settings_ethtool(rocker_port, ecmd);
 }
 
-static int rocker_port_set_settings(struct net_device *dev,
-				    struct ethtool_cmd *ecmd)
+static int
+rocker_port_set_link_ksettings(struct net_device *dev,
+			       const struct ethtool_link_ksettings *ecmd)
 {
 	struct rocker_port *rocker_port = netdev_priv(dev);
 
@@ -2388,13 +2410,13 @@ static int rocker_port_get_sset_count(struct net_device *netdev, int sset)
 }
 
 static const struct ethtool_ops rocker_port_ethtool_ops = {
-	.get_settings		= rocker_port_get_settings,
-	.set_settings		= rocker_port_set_settings,
 	.get_drvinfo		= rocker_port_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_strings		= rocker_port_get_strings,
 	.get_ethtool_stats	= rocker_port_get_stats,
 	.get_sset_count		= rocker_port_get_sset_count,
+	.get_link_ksettings	= rocker_port_get_link_ksettings,
+	.set_link_ksettings	= rocker_port_set_link_ksettings,
 };
 
 /*****************
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index c60c2d4c646a..78efb2822b86 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -119,6 +119,7 @@ struct efx_ef10_filter_table {
 	bool mc_promisc;
 /* Whether in multicast promiscuous mode when last changed */
 	bool mc_promisc_last;
+	bool mc_overflow; /* Too many MC addrs; should always imply mc_promisc */
 	bool vlan_filter;
 	struct list_head vlan_list;
 };
@@ -5058,6 +5059,7 @@ static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx)
 	struct netdev_hw_addr *mc;
 	unsigned int i, addr_count;
 
+	table->mc_overflow = false;
 	table->mc_promisc = !!(net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI));
 
 	addr_count = netdev_mc_count(net_dev);
@@ -5065,6 +5067,7 @@ static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx)
 	netdev_for_each_mc_addr(mc, net_dev) {
 		if (i >= EFX_EF10_FILTER_DEV_MC_MAX) {
 			table->mc_promisc = true;
+			table->mc_overflow = true;
 			break;
 		}
 		ether_addr_copy(table->dev_mc_list[i].addr, mc->addr);
@@ -5469,12 +5472,15 @@ static void efx_ef10_filter_vlan_sync_rx_mode(struct efx_nic *efx,
 			}
 		} else {
 			/* If we failed to insert promiscuous filters, don't
-			 * rollback.  Regardless, also insert the mc_list
+			 * rollback.  Regardless, also insert the mc_list,
+			 * unless it's incomplete due to overflow
 			 */
 			efx_ef10_filter_insert_def(efx, vlan,
 						   EFX_ENCAP_TYPE_NONE,
 						   true, false);
-			efx_ef10_filter_insert_addr_list(efx, vlan, true, false);
+			if (!table->mc_overflow)
+				efx_ef10_filter_insert_addr_list(efx, vlan,
+								 true, false);
 		}
 	} else {
 		/* If any filters failed to insert, rollback and fall back to
diff --git a/drivers/net/ethernet/sfc/falcon/tx.c b/drivers/net/ethernet/sfc/falcon/tx.c
index 104fb15a73f2..f6daf09b8627 100644
--- a/drivers/net/ethernet/sfc/falcon/tx.c
+++ b/drivers/net/ethernet/sfc/falcon/tx.c
@@ -437,11 +437,13 @@ int ef4_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto,
 	if (ntc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
-	num_tc = ntc->tc;
+	num_tc = ntc->mqprio->num_tc;
 
 	if (ef4_nic_rev(efx) < EF4_REV_FALCON_B0 || num_tc > EF4_MAX_TX_TC)
 		return -EINVAL;
 
+	ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
 	if (num_tc == net_dev->num_tc)
 		return 0;
 
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index ff88d60aa6d5..3bdf87f31087 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -665,11 +665,13 @@ int efx_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto,
 	if (ntc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
-	num_tc = ntc->tc;
+	num_tc = ntc->mqprio->num_tc;
 
 	if (num_tc > EFX_MAX_TX_TC)
 		return -EINVAL;
 
+	ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
 	if (num_tc == net_dev->num_tc)
 		return 0;
 
diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c
index 57e6cef81ebe..52ead5524de7 100644
--- a/drivers/net/ethernet/sgi/ioc3-eth.c
+++ b/drivers/net/ethernet/sgi/ioc3-eth.c
@@ -1558,25 +1558,27 @@ static void ioc3_get_drvinfo (struct net_device *dev,
 	strlcpy(info->bus_info, pci_name(ip->pdev), sizeof(info->bus_info));
 }
 
-static int ioc3_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int ioc3_get_link_ksettings(struct net_device *dev,
+				   struct ethtool_link_ksettings *cmd)
 {
 	struct ioc3_private *ip = netdev_priv(dev);
 	int rc;
 
 	spin_lock_irq(&ip->ioc3_lock);
-	rc = mii_ethtool_gset(&ip->mii, cmd);
+	rc = mii_ethtool_get_link_ksettings(&ip->mii, cmd);
 	spin_unlock_irq(&ip->ioc3_lock);
 
 	return rc;
 }
 
-static int ioc3_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int ioc3_set_link_ksettings(struct net_device *dev,
+				   const struct ethtool_link_ksettings *cmd)
 {
 	struct ioc3_private *ip = netdev_priv(dev);
 	int rc;
 
 	spin_lock_irq(&ip->ioc3_lock);
-	rc = mii_ethtool_sset(&ip->mii, cmd);
+	rc = mii_ethtool_set_link_ksettings(&ip->mii, cmd);
 	spin_unlock_irq(&ip->ioc3_lock);
 
 	return rc;
@@ -1608,10 +1610,10 @@ static u32 ioc3_get_link(struct net_device *dev)
 
 static const struct ethtool_ops ioc3_ethtool_ops = {
 	.get_drvinfo		= ioc3_get_drvinfo,
-	.get_settings		= ioc3_get_settings,
-	.set_settings		= ioc3_set_settings,
 	.nway_reset		= ioc3_nway_reset,
 	.get_link		= ioc3_get_link,
+	.get_link_ksettings	= ioc3_get_link_ksettings,
+	.set_link_ksettings	= ioc3_set_link_ksettings,
 };
 
 static int ioc3_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/ethernet/silan/sc92031.c b/drivers/net/ethernet/silan/sc92031.c
index 6c2e2b311c16..751c81848f35 100644
--- a/drivers/net/ethernet/silan/sc92031.c
+++ b/drivers/net/ethernet/silan/sc92031.c
@@ -1122,14 +1122,16 @@ static void sc92031_poll_controller(struct net_device *dev)
 }
 #endif
 
-static int sc92031_ethtool_get_settings(struct net_device *dev,
-		struct ethtool_cmd *cmd)
+static int
+sc92031_ethtool_get_link_ksettings(struct net_device *dev,
+				   struct ethtool_link_ksettings *cmd)
 {
 	struct sc92031_priv *priv = netdev_priv(dev);
 	void __iomem *port_base = priv->port_base;
 	u8 phy_address;
 	u32 phy_ctrl;
 	u16 output_status;
+	u32 supported, advertising;
 
 	spin_lock_bh(&priv->lock);
 
@@ -1142,68 +1144,77 @@ static int sc92031_ethtool_get_settings(struct net_device *dev,
 
 	spin_unlock_bh(&priv->lock);
 
-	cmd->supported = SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full
+	supported = SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full
 			| SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full
 			| SUPPORTED_Autoneg | SUPPORTED_TP | SUPPORTED_MII;
 
-	cmd->advertising = ADVERTISED_TP | ADVERTISED_MII;
+	advertising = ADVERTISED_TP | ADVERTISED_MII;
 
 	if ((phy_ctrl & (PhyCtrlDux | PhyCtrlSpd100 | PhyCtrlSpd10))
 			== (PhyCtrlDux | PhyCtrlSpd100 | PhyCtrlSpd10))
-		cmd->advertising |= ADVERTISED_Autoneg;
+		advertising |= ADVERTISED_Autoneg;
 
 	if ((phy_ctrl & PhyCtrlSpd10) == PhyCtrlSpd10)
-		cmd->advertising |= ADVERTISED_10baseT_Half;
+		advertising |= ADVERTISED_10baseT_Half;
 
 	if ((phy_ctrl & (PhyCtrlSpd10 | PhyCtrlDux))
 			== (PhyCtrlSpd10 | PhyCtrlDux))
-		cmd->advertising |= ADVERTISED_10baseT_Full;
+		advertising |= ADVERTISED_10baseT_Full;
 
 	if ((phy_ctrl & PhyCtrlSpd100) == PhyCtrlSpd100)
-		cmd->advertising |= ADVERTISED_100baseT_Half;
+		advertising |= ADVERTISED_100baseT_Half;
 
 	if ((phy_ctrl & (PhyCtrlSpd100 | PhyCtrlDux))
 			== (PhyCtrlSpd100 | PhyCtrlDux))
-		cmd->advertising |= ADVERTISED_100baseT_Full;
+		advertising |= ADVERTISED_100baseT_Full;
 
 	if (phy_ctrl & PhyCtrlAne)
-		cmd->advertising |= ADVERTISED_Autoneg;
+		advertising |= ADVERTISED_Autoneg;
 
-	ethtool_cmd_speed_set(cmd,
-			      (output_status & 0x2) ? SPEED_100 : SPEED_10);
-	cmd->duplex = (output_status & 0x4) ? DUPLEX_FULL : DUPLEX_HALF;
-	cmd->port = PORT_MII;
-	cmd->phy_address = phy_address;
-	cmd->transceiver = XCVR_INTERNAL;
-	cmd->autoneg = (phy_ctrl & PhyCtrlAne) ? AUTONEG_ENABLE : AUTONEG_DISABLE;
+	cmd->base.speed = (output_status & 0x2) ? SPEED_100 : SPEED_10;
+	cmd->base.duplex = (output_status & 0x4) ? DUPLEX_FULL : DUPLEX_HALF;
+	cmd->base.port = PORT_MII;
+	cmd->base.phy_address = phy_address;
+	cmd->base.autoneg = (phy_ctrl & PhyCtrlAne) ?
+		AUTONEG_ENABLE : AUTONEG_DISABLE;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 
 	return 0;
 }
 
-static int sc92031_ethtool_set_settings(struct net_device *dev,
-		struct ethtool_cmd *cmd)
+static int
+sc92031_ethtool_set_link_ksettings(struct net_device *dev,
+				   const struct ethtool_link_ksettings *cmd)
 {
 	struct sc92031_priv *priv = netdev_priv(dev);
 	void __iomem *port_base = priv->port_base;
-	u32 speed = ethtool_cmd_speed(cmd);
+	u32 speed = cmd->base.speed;
 	u32 phy_ctrl;
 	u32 old_phy_ctrl;
+	u32 advertising;
+
+	ethtool_convert_link_mode_to_legacy_u32(&advertising,
+						cmd->link_modes.advertising);
 
 	if (!(speed == SPEED_10 || speed == SPEED_100))
 		return -EINVAL;
-	if (!(cmd->duplex == DUPLEX_HALF || cmd->duplex == DUPLEX_FULL))
-		return -EINVAL;
-	if (!(cmd->port == PORT_MII))
+	if (!(cmd->base.duplex == DUPLEX_HALF ||
+	      cmd->base.duplex == DUPLEX_FULL))
 		return -EINVAL;
-	if (!(cmd->phy_address == 0x1f))
+	if (!(cmd->base.port == PORT_MII))
 		return -EINVAL;
-	if (!(cmd->transceiver == XCVR_INTERNAL))
+	if (!(cmd->base.phy_address == 0x1f))
 		return -EINVAL;
-	if (!(cmd->autoneg == AUTONEG_DISABLE || cmd->autoneg == AUTONEG_ENABLE))
+	if (!(cmd->base.autoneg == AUTONEG_DISABLE ||
+	      cmd->base.autoneg == AUTONEG_ENABLE))
 		return -EINVAL;
 
-	if (cmd->autoneg == AUTONEG_ENABLE) {
-		if (!(cmd->advertising & (ADVERTISED_Autoneg
+	if (cmd->base.autoneg == AUTONEG_ENABLE) {
+		if (!(advertising & (ADVERTISED_Autoneg
 				| ADVERTISED_100baseT_Full
 				| ADVERTISED_100baseT_Half
 				| ADVERTISED_10baseT_Full
@@ -1213,15 +1224,15 @@ static int sc92031_ethtool_set_settings(struct net_device *dev,
 		phy_ctrl = PhyCtrlAne;
 
 		// FIXME: I'm not sure what the original code was trying to do
-		if (cmd->advertising & ADVERTISED_Autoneg)
+		if (advertising & ADVERTISED_Autoneg)
 			phy_ctrl |= PhyCtrlDux | PhyCtrlSpd100 | PhyCtrlSpd10;
-		if (cmd->advertising & ADVERTISED_100baseT_Full)
+		if (advertising & ADVERTISED_100baseT_Full)
 			phy_ctrl |= PhyCtrlDux | PhyCtrlSpd100;
-		if (cmd->advertising & ADVERTISED_100baseT_Half)
+		if (advertising & ADVERTISED_100baseT_Half)
 			phy_ctrl |= PhyCtrlSpd100;
-		if (cmd->advertising & ADVERTISED_10baseT_Full)
+		if (advertising & ADVERTISED_10baseT_Full)
 			phy_ctrl |= PhyCtrlSpd10 | PhyCtrlDux;
-		if (cmd->advertising & ADVERTISED_10baseT_Half)
+		if (advertising & ADVERTISED_10baseT_Half)
 			phy_ctrl |= PhyCtrlSpd10;
 	} else {
 		// FIXME: Whole branch guessed
@@ -1232,7 +1243,7 @@ static int sc92031_ethtool_set_settings(struct net_device *dev,
 		else /* cmd->speed == SPEED_100 */
 			phy_ctrl |= PhyCtrlSpd100;
 
-		if (cmd->duplex == DUPLEX_FULL)
+		if (cmd->base.duplex == DUPLEX_FULL)
 			phy_ctrl |= PhyCtrlDux;
 	}
 
@@ -1368,8 +1379,6 @@ static void sc92031_ethtool_get_ethtool_stats(struct net_device *dev,
 }
 
 static const struct ethtool_ops sc92031_ethtool_ops = {
-	.get_settings		= sc92031_ethtool_get_settings,
-	.set_settings		= sc92031_ethtool_set_settings,
 	.get_wol		= sc92031_ethtool_get_wol,
 	.set_wol		= sc92031_ethtool_set_wol,
 	.nway_reset		= sc92031_ethtool_nway_reset,
@@ -1377,6 +1386,8 @@ static const struct ethtool_ops sc92031_ethtool_ops = {
 	.get_strings		= sc92031_ethtool_get_strings,
 	.get_sset_count		= sc92031_ethtool_get_sset_count,
 	.get_ethtool_stats	= sc92031_ethtool_get_ethtool_stats,
+	.get_link_ksettings	= sc92031_ethtool_get_link_ksettings,
+	.set_link_ksettings	= sc92031_ethtool_set_link_ksettings,
 };
 
 
diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c
index 210e35d079dd..02da106c6e04 100644
--- a/drivers/net/ethernet/sis/sis190.c
+++ b/drivers/net/ethernet/sis/sis190.c
@@ -1734,18 +1734,20 @@ static void sis190_set_speed_auto(struct net_device *dev)
 		   BMCR_ANENABLE | BMCR_ANRESTART | BMCR_RESET);
 }
 
-static int sis190_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int sis190_get_link_ksettings(struct net_device *dev,
+				     struct ethtool_link_ksettings *cmd)
 {
 	struct sis190_private *tp = netdev_priv(dev);
 
-	return mii_ethtool_gset(&tp->mii_if, cmd);
+	return mii_ethtool_get_link_ksettings(&tp->mii_if, cmd);
 }
 
-static int sis190_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int sis190_set_link_ksettings(struct net_device *dev,
+				     const struct ethtool_link_ksettings *cmd)
 {
 	struct sis190_private *tp = netdev_priv(dev);
 
-	return mii_ethtool_sset(&tp->mii_if, cmd);
+	return mii_ethtool_set_link_ksettings(&tp->mii_if, cmd);
 }
 
 static void sis190_get_drvinfo(struct net_device *dev,
@@ -1797,8 +1799,6 @@ static void sis190_set_msglevel(struct net_device *dev, u32 value)
 }
 
 static const struct ethtool_ops sis190_ethtool_ops = {
-	.get_settings	= sis190_get_settings,
-	.set_settings	= sis190_set_settings,
 	.get_drvinfo	= sis190_get_drvinfo,
 	.get_regs_len	= sis190_get_regs_len,
 	.get_regs	= sis190_get_regs,
@@ -1806,6 +1806,8 @@ static const struct ethtool_ops sis190_ethtool_ops = {
 	.get_msglevel	= sis190_get_msglevel,
 	.set_msglevel	= sis190_set_msglevel,
 	.nway_reset	= sis190_nway_reset,
+	.get_link_ksettings = sis190_get_link_ksettings,
+	.set_link_ksettings = sis190_set_link_ksettings,
 };
 
 static int sis190_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index 1b6f6171d078..40bd88362e3d 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -2035,23 +2035,23 @@ static u32 sis900_get_link(struct net_device *net_dev)
 	return mii_link_ok(&sis_priv->mii_info);
 }
 
-static int sis900_get_settings(struct net_device *net_dev,
-				struct ethtool_cmd *cmd)
+static int sis900_get_link_ksettings(struct net_device *net_dev,
+				     struct ethtool_link_ksettings *cmd)
 {
 	struct sis900_private *sis_priv = netdev_priv(net_dev);
 	spin_lock_irq(&sis_priv->lock);
-	mii_ethtool_gset(&sis_priv->mii_info, cmd);
+	mii_ethtool_get_link_ksettings(&sis_priv->mii_info, cmd);
 	spin_unlock_irq(&sis_priv->lock);
 	return 0;
 }
 
-static int sis900_set_settings(struct net_device *net_dev,
-				struct ethtool_cmd *cmd)
+static int sis900_set_link_ksettings(struct net_device *net_dev,
+				     const struct ethtool_link_ksettings *cmd)
 {
 	struct sis900_private *sis_priv = netdev_priv(net_dev);
 	int rt;
 	spin_lock_irq(&sis_priv->lock);
-	rt = mii_ethtool_sset(&sis_priv->mii_info, cmd);
+	rt = mii_ethtool_set_link_ksettings(&sis_priv->mii_info, cmd);
 	spin_unlock_irq(&sis_priv->lock);
 	return rt;
 }
@@ -2129,11 +2129,11 @@ static const struct ethtool_ops sis900_ethtool_ops = {
 	.get_msglevel	= sis900_get_msglevel,
 	.set_msglevel	= sis900_set_msglevel,
 	.get_link	= sis900_get_link,
-	.get_settings	= sis900_get_settings,
-	.set_settings	= sis900_set_settings,
 	.nway_reset	= sis900_nway_reset,
 	.get_wol	= sis900_get_wol,
-	.set_wol	= sis900_set_wol
+	.set_wol	= sis900_set_wol,
+	.get_link_ksettings = sis900_get_link_ksettings,
+	.set_link_ksettings = sis900_set_link_ksettings,
 };
 
 /**
diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c
index 5f2737189c72..db6dcb06193d 100644
--- a/drivers/net/ethernet/smsc/epic100.c
+++ b/drivers/net/ethernet/smsc/epic100.c
@@ -1387,25 +1387,27 @@ static void netdev_get_drvinfo (struct net_device *dev, struct ethtool_drvinfo *
 	strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
 }
 
-static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int netdev_get_link_ksettings(struct net_device *dev,
+				     struct ethtool_link_ksettings *cmd)
 {
 	struct epic_private *np = netdev_priv(dev);
 	int rc;
 
 	spin_lock_irq(&np->lock);
-	rc = mii_ethtool_gset(&np->mii, cmd);
+	rc = mii_ethtool_get_link_ksettings(&np->mii, cmd);
 	spin_unlock_irq(&np->lock);
 
 	return rc;
 }
 
-static int netdev_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int netdev_set_link_ksettings(struct net_device *dev,
+				     const struct ethtool_link_ksettings *cmd)
 {
 	struct epic_private *np = netdev_priv(dev);
 	int rc;
 
 	spin_lock_irq(&np->lock);
-	rc = mii_ethtool_sset(&np->mii, cmd);
+	rc = mii_ethtool_set_link_ksettings(&np->mii, cmd);
 	spin_unlock_irq(&np->lock);
 
 	return rc;
@@ -1460,14 +1462,14 @@ static void ethtool_complete(struct net_device *dev)
 
 static const struct ethtool_ops netdev_ethtool_ops = {
 	.get_drvinfo		= netdev_get_drvinfo,
-	.get_settings		= netdev_get_settings,
-	.set_settings		= netdev_set_settings,
 	.nway_reset		= netdev_nway_reset,
 	.get_link		= netdev_get_link,
 	.get_msglevel		= netdev_get_msglevel,
 	.set_msglevel		= netdev_set_msglevel,
 	.begin			= ethtool_begin,
-	.complete		= ethtool_complete
+	.complete		= ethtool_complete,
+	.get_link_ksettings	= netdev_get_link_ksettings,
+	.set_link_ksettings	= netdev_set_link_ksettings,
 };
 
 static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c
index 4f19c6166182..36307d34f641 100644
--- a/drivers/net/ethernet/smsc/smc911x.c
+++ b/drivers/net/ethernet/smsc/smc911x.c
@@ -1446,40 +1446,40 @@ static int smc911x_close(struct net_device *dev)
  * Ethtool support
  */
 static int
-smc911x_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd)
+smc911x_ethtool_get_link_ksettings(struct net_device *dev,
+				   struct ethtool_link_ksettings *cmd)
 {
 	struct smc911x_local *lp = netdev_priv(dev);
 	int ret, status;
 	unsigned long flags;
+	u32 supported;
 
 	DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__);
-	cmd->maxtxpkt = 1;
-	cmd->maxrxpkt = 1;
 
 	if (lp->phy_type != 0) {
 		spin_lock_irqsave(&lp->lock, flags);
-		ret = mii_ethtool_gset(&lp->mii, cmd);
+		ret = mii_ethtool_get_link_ksettings(&lp->mii, cmd);
 		spin_unlock_irqrestore(&lp->lock, flags);
 	} else {
-		cmd->supported = SUPPORTED_10baseT_Half |
+		supported = SUPPORTED_10baseT_Half |
 				SUPPORTED_10baseT_Full |
 				SUPPORTED_TP | SUPPORTED_AUI;
 
 		if (lp->ctl_rspeed == 10)
-			ethtool_cmd_speed_set(cmd, SPEED_10);
+			cmd->base.speed = SPEED_10;
 		else if (lp->ctl_rspeed == 100)
-			ethtool_cmd_speed_set(cmd, SPEED_100);
-
-		cmd->autoneg = AUTONEG_DISABLE;
-		if (lp->mii.phy_id==1)
-			cmd->transceiver = XCVR_INTERNAL;
-		else
-			cmd->transceiver = XCVR_EXTERNAL;
-		cmd->port = 0;
+			cmd->base.speed = SPEED_100;
+
+		cmd->base.autoneg = AUTONEG_DISABLE;
+		cmd->base.port = 0;
 		SMC_GET_PHY_SPECIAL(lp, lp->mii.phy_id, status);
-		cmd->duplex =
+		cmd->base.duplex =
 			(status & (PHY_SPECIAL_SPD_10FULL_ | PHY_SPECIAL_SPD_100FULL_)) ?
 				DUPLEX_FULL : DUPLEX_HALF;
+
+		ethtool_convert_legacy_u32_to_link_mode(
+			cmd->link_modes.supported, supported);
+
 		ret = 0;
 	}
 
@@ -1487,7 +1487,8 @@ smc911x_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd)
 }
 
 static int
-smc911x_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd)
+smc911x_ethtool_set_link_ksettings(struct net_device *dev,
+				   const struct ethtool_link_ksettings *cmd)
 {
 	struct smc911x_local *lp = netdev_priv(dev);
 	int ret;
@@ -1495,16 +1496,18 @@ smc911x_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd)
 
 	if (lp->phy_type != 0) {
 		spin_lock_irqsave(&lp->lock, flags);
-		ret = mii_ethtool_sset(&lp->mii, cmd);
+		ret = mii_ethtool_set_link_ksettings(&lp->mii, cmd);
 		spin_unlock_irqrestore(&lp->lock, flags);
 	} else {
-		if (cmd->autoneg != AUTONEG_DISABLE ||
-			cmd->speed != SPEED_10 ||
-			(cmd->duplex != DUPLEX_HALF && cmd->duplex != DUPLEX_FULL) ||
-			(cmd->port != PORT_TP && cmd->port != PORT_AUI))
+		if (cmd->base.autoneg != AUTONEG_DISABLE ||
+		    cmd->base.speed != SPEED_10 ||
+		    (cmd->base.duplex != DUPLEX_HALF &&
+		     cmd->base.duplex != DUPLEX_FULL) ||
+		    (cmd->base.port != PORT_TP &&
+		     cmd->base.port != PORT_AUI))
 			return -EINVAL;
 
-		lp->ctl_rfduplx = cmd->duplex == DUPLEX_FULL;
+		lp->ctl_rfduplx = cmd->base.duplex == DUPLEX_FULL;
 
 		ret = 0;
 	}
@@ -1686,8 +1689,6 @@ static int smc911x_ethtool_geteeprom_len(struct net_device *dev)
 }
 
 static const struct ethtool_ops smc911x_ethtool_ops = {
-	.get_settings	 = smc911x_ethtool_getsettings,
-	.set_settings	 = smc911x_ethtool_setsettings,
 	.get_drvinfo	 = smc911x_ethtool_getdrvinfo,
 	.get_msglevel	 = smc911x_ethtool_getmsglevel,
 	.set_msglevel	 = smc911x_ethtool_setmsglevel,
@@ -1698,6 +1699,8 @@ static const struct ethtool_ops smc911x_ethtool_ops = {
 	.get_eeprom_len = smc911x_ethtool_geteeprom_len,
 	.get_eeprom = smc911x_ethtool_geteeprom,
 	.set_eeprom = smc911x_ethtool_seteeprom,
+	.get_link_ksettings	 = smc911x_ethtool_get_link_ksettings,
+	.set_link_ksettings	 = smc911x_ethtool_set_link_ksettings,
 };
 
 /*
diff --git a/drivers/net/ethernet/smsc/smc91c92_cs.c b/drivers/net/ethernet/smsc/smc91c92_cs.c
index 97280daba27f..976aa876789a 100644
--- a/drivers/net/ethernet/smsc/smc91c92_cs.c
+++ b/drivers/net/ethernet/smsc/smc91c92_cs.c
@@ -1843,56 +1843,60 @@ static int smc_link_ok(struct net_device *dev)
     }
 }
 
-static int smc_netdev_get_ecmd(struct net_device *dev, struct ethtool_cmd *ecmd)
+static int smc_netdev_get_ecmd(struct net_device *dev,
+			       struct ethtool_link_ksettings *ecmd)
 {
-    u16 tmp;
-    unsigned int ioaddr = dev->base_addr;
+	u16 tmp;
+	unsigned int ioaddr = dev->base_addr;
+	u32 supported;
 
-    ecmd->supported = (SUPPORTED_TP | SUPPORTED_AUI |
-	SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full);
-		
-    SMC_SELECT_BANK(1);
-    tmp = inw(ioaddr + CONFIG);
-    ecmd->port = (tmp & CFG_AUI_SELECT) ? PORT_AUI : PORT_TP;
-    ecmd->transceiver = XCVR_INTERNAL;
-    ethtool_cmd_speed_set(ecmd, SPEED_10);
-    ecmd->phy_address = ioaddr + MGMT;
+	supported = (SUPPORTED_TP | SUPPORTED_AUI |
+		     SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full);
 
-    SMC_SELECT_BANK(0);
-    tmp = inw(ioaddr + TCR);
-    ecmd->duplex = (tmp & TCR_FDUPLX) ? DUPLEX_FULL : DUPLEX_HALF;
+	SMC_SELECT_BANK(1);
+	tmp = inw(ioaddr + CONFIG);
+	ecmd->base.port = (tmp & CFG_AUI_SELECT) ? PORT_AUI : PORT_TP;
+	ecmd->base.speed = SPEED_10;
+	ecmd->base.phy_address = ioaddr + MGMT;
 
-    return 0;
+	SMC_SELECT_BANK(0);
+	tmp = inw(ioaddr + TCR);
+	ecmd->base.duplex = (tmp & TCR_FDUPLX) ? DUPLEX_FULL : DUPLEX_HALF;
+
+	ethtool_convert_legacy_u32_to_link_mode(ecmd->link_modes.supported,
+						supported);
+
+	return 0;
 }
 
-static int smc_netdev_set_ecmd(struct net_device *dev, struct ethtool_cmd *ecmd)
+static int smc_netdev_set_ecmd(struct net_device *dev,
+			       const struct ethtool_link_ksettings *ecmd)
 {
-    u16 tmp;
-    unsigned int ioaddr = dev->base_addr;
+	u16 tmp;
+	unsigned int ioaddr = dev->base_addr;
 
-    if (ethtool_cmd_speed(ecmd) != SPEED_10)
-	return -EINVAL;
-    if (ecmd->duplex != DUPLEX_HALF && ecmd->duplex != DUPLEX_FULL)
-    	return -EINVAL;
-    if (ecmd->port != PORT_TP && ecmd->port != PORT_AUI)
-	return -EINVAL;
-    if (ecmd->transceiver != XCVR_INTERNAL)
-    	return -EINVAL;
+	if (ecmd->base.speed != SPEED_10)
+		return -EINVAL;
+	if (ecmd->base.duplex != DUPLEX_HALF &&
+	    ecmd->base.duplex != DUPLEX_FULL)
+		return -EINVAL;
+	if (ecmd->base.port != PORT_TP && ecmd->base.port != PORT_AUI)
+		return -EINVAL;
 
-    if (ecmd->port == PORT_AUI)
-	smc_set_xcvr(dev, 1);
-    else
-	smc_set_xcvr(dev, 0);
+	if (ecmd->base.port == PORT_AUI)
+		smc_set_xcvr(dev, 1);
+	else
+		smc_set_xcvr(dev, 0);
 
-    SMC_SELECT_BANK(0);
-    tmp = inw(ioaddr + TCR);
-    if (ecmd->duplex == DUPLEX_FULL)
-	tmp |= TCR_FDUPLX;
-    else
-	tmp &= ~TCR_FDUPLX;
-    outw(tmp, ioaddr + TCR);
-	
-    return 0;
+	SMC_SELECT_BANK(0);
+	tmp = inw(ioaddr + TCR);
+	if (ecmd->base.duplex == DUPLEX_FULL)
+		tmp |= TCR_FDUPLX;
+	else
+		tmp &= ~TCR_FDUPLX;
+	outw(tmp, ioaddr + TCR);
+
+	return 0;
 }
 
 static int check_if_running(struct net_device *dev)
@@ -1908,7 +1912,8 @@ static void smc_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info
 	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
 }
 
-static int smc_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+static int smc_get_link_ksettings(struct net_device *dev,
+				  struct ethtool_link_ksettings *ecmd)
 {
 	struct smc_private *smc = netdev_priv(dev);
 	unsigned int ioaddr = dev->base_addr;
@@ -1919,7 +1924,7 @@ static int smc_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
 	spin_lock_irqsave(&smc->lock, flags);
 	SMC_SELECT_BANK(3);
 	if (smc->cfg & CFG_MII_SELECT)
-		ret = mii_ethtool_gset(&smc->mii_if, ecmd);
+		ret = mii_ethtool_get_link_ksettings(&smc->mii_if, ecmd);
 	else
 		ret = smc_netdev_get_ecmd(dev, ecmd);
 	SMC_SELECT_BANK(saved_bank);
@@ -1927,7 +1932,8 @@ static int smc_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
 	return ret;
 }
 
-static int smc_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+static int smc_set_link_ksettings(struct net_device *dev,
+				  const struct ethtool_link_ksettings *ecmd)
 {
 	struct smc_private *smc = netdev_priv(dev);
 	unsigned int ioaddr = dev->base_addr;
@@ -1938,7 +1944,7 @@ static int smc_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
 	spin_lock_irqsave(&smc->lock, flags);
 	SMC_SELECT_BANK(3);
 	if (smc->cfg & CFG_MII_SELECT)
-		ret = mii_ethtool_sset(&smc->mii_if, ecmd);
+		ret = mii_ethtool_set_link_ksettings(&smc->mii_if, ecmd);
 	else
 		ret = smc_netdev_set_ecmd(dev, ecmd);
 	SMC_SELECT_BANK(saved_bank);
@@ -1982,10 +1988,10 @@ static int smc_nway_reset(struct net_device *dev)
 static const struct ethtool_ops ethtool_ops = {
 	.begin = check_if_running,
 	.get_drvinfo = smc_get_drvinfo,
-	.get_settings = smc_get_settings,
-	.set_settings = smc_set_settings,
 	.get_link = smc_get_link,
 	.nway_reset = smc_nway_reset,
+	.get_link_ksettings = smc_get_link_ksettings,
+	.set_link_ksettings = smc_set_link_ksettings,
 };
 
 static int smc_ioctl (struct net_device *dev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 04d9245b7149..90d28bcad880 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -246,6 +246,15 @@ struct stmmac_extra_stats {
 #define STMMAC_TX_MAX_FRAMES	256
 #define STMMAC_TX_FRAMES	64
 
+/* Packets types */
+enum packets_types {
+	PACKET_AVCPQ = 0x1, /* AV Untagged Control packets */
+	PACKET_PTPQ = 0x2, /* PTP Packets */
+	PACKET_DCBCPQ = 0x3, /* DCB Control Packets */
+	PACKET_UPQ = 0x4, /* Untagged Packets */
+	PACKET_MCBCQ = 0x5, /* Multicast & Broadcast Packets */
+};
+
 /* Rx IPC status */
 enum rx_frame_status {
 	good_frame = 0x0,
@@ -324,6 +333,9 @@ struct dma_features {
 	unsigned int number_tx_queues;
 	/* Alternate (enhanced) DESC mode */
 	unsigned int enh_desc;
+	/* TX and RX FIFO sizes */
+	unsigned int tx_fifo_size;
+	unsigned int rx_fifo_size;
 };
 
 /* GMAC TX FIFO is 8K, Rx FIFO is 16K */
@@ -413,6 +425,14 @@ struct stmmac_dma_ops {
 	int (*reset)(void __iomem *ioaddr);
 	void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg,
 		     u32 dma_tx, u32 dma_rx, int atds);
+	void (*init_chan)(void __iomem *ioaddr,
+			  struct stmmac_dma_cfg *dma_cfg, u32 chan);
+	void (*init_rx_chan)(void __iomem *ioaddr,
+			     struct stmmac_dma_cfg *dma_cfg,
+			     u32 dma_rx_phy, u32 chan);
+	void (*init_tx_chan)(void __iomem *ioaddr,
+			     struct stmmac_dma_cfg *dma_cfg,
+			     u32 dma_tx_phy, u32 chan);
 	/* Configure the AXI Bus Mode Register */
 	void (*axi)(void __iomem *ioaddr, struct stmmac_axi *axi);
 	/* Dump DMA registers */
@@ -421,25 +441,28 @@ struct stmmac_dma_ops {
 	 * An invalid value enables the store-and-forward mode */
 	void (*dma_mode)(void __iomem *ioaddr, int txmode, int rxmode,
 			 int rxfifosz);
+	void (*dma_rx_mode)(void __iomem *ioaddr, int mode, u32 channel,
+			    int fifosz);
+	void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel);
 	/* To track extra statistic (if supported) */
 	void (*dma_diagnostic_fr) (void *data, struct stmmac_extra_stats *x,
 				   void __iomem *ioaddr);
 	void (*enable_dma_transmission) (void __iomem *ioaddr);
-	void (*enable_dma_irq) (void __iomem *ioaddr);
-	void (*disable_dma_irq) (void __iomem *ioaddr);
-	void (*start_tx) (void __iomem *ioaddr);
-	void (*stop_tx) (void __iomem *ioaddr);
-	void (*start_rx) (void __iomem *ioaddr);
-	void (*stop_rx) (void __iomem *ioaddr);
+	void (*enable_dma_irq)(void __iomem *ioaddr, u32 chan);
+	void (*disable_dma_irq)(void __iomem *ioaddr, u32 chan);
+	void (*start_tx)(void __iomem *ioaddr, u32 chan);
+	void (*stop_tx)(void __iomem *ioaddr, u32 chan);
+	void (*start_rx)(void __iomem *ioaddr, u32 chan);
+	void (*stop_rx)(void __iomem *ioaddr, u32 chan);
 	int (*dma_interrupt) (void __iomem *ioaddr,
-			      struct stmmac_extra_stats *x);
+			      struct stmmac_extra_stats *x, u32 chan);
 	/* If supported then get the optional core features */
 	void (*get_hw_feature)(void __iomem *ioaddr,
 			       struct dma_features *dma_cap);
 	/* Program the HW RX Watchdog */
-	void (*rx_watchdog) (void __iomem *ioaddr, u32 riwt);
-	void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len);
-	void (*set_rx_ring_len)(void __iomem *ioaddr, u32 len);
+	void (*rx_watchdog)(void __iomem *ioaddr, u32 riwt, u32 number_chan);
+	void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan);
+	void (*set_rx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan);
 	void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 	void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 	void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan);
@@ -451,20 +474,44 @@ struct mac_device_info;
 struct stmmac_ops {
 	/* MAC core initialization */
 	void (*core_init)(struct mac_device_info *hw, int mtu);
+	/* Enable the MAC RX/TX */
+	void (*set_mac)(void __iomem *ioaddr, bool enable);
 	/* Enable and verify that the IPC module is supported */
 	int (*rx_ipc)(struct mac_device_info *hw);
 	/* Enable RX Queues */
-	void (*rx_queue_enable)(struct mac_device_info *hw, u32 queue);
+	void (*rx_queue_enable)(struct mac_device_info *hw, u8 mode, u32 queue);
+	/* RX Queues Priority */
+	void (*rx_queue_prio)(struct mac_device_info *hw, u32 prio, u32 queue);
+	/* TX Queues Priority */
+	void (*tx_queue_prio)(struct mac_device_info *hw, u32 prio, u32 queue);
+	/* RX Queues Routing */
+	void (*rx_queue_routing)(struct mac_device_info *hw, u8 packet,
+				 u32 queue);
+	/* Program RX Algorithms */
+	void (*prog_mtl_rx_algorithms)(struct mac_device_info *hw, u32 rx_alg);
+	/* Program TX Algorithms */
+	void (*prog_mtl_tx_algorithms)(struct mac_device_info *hw, u32 tx_alg);
+	/* Set MTL TX queues weight */
+	void (*set_mtl_tx_queue_weight)(struct mac_device_info *hw,
+					u32 weight, u32 queue);
+	/* RX MTL queue to RX dma mapping */
+	void (*map_mtl_to_dma)(struct mac_device_info *hw, u32 queue, u32 chan);
+	/* Configure AV Algorithm */
+	void (*config_cbs)(struct mac_device_info *hw, u32 send_slope,
+			   u32 idle_slope, u32 high_credit, u32 low_credit,
+			   u32 queue);
 	/* Dump MAC registers */
 	void (*dump_regs)(struct mac_device_info *hw, u32 *reg_space);
 	/* Handle extra events on specific interrupts hw dependent */
 	int (*host_irq_status)(struct mac_device_info *hw,
 			       struct stmmac_extra_stats *x);
+	/* Handle MTL interrupts */
+	int (*host_mtl_irq_status)(struct mac_device_info *hw, u32 chan);
 	/* Multicast filter setting */
 	void (*set_filter)(struct mac_device_info *hw, struct net_device *dev);
 	/* Flow control setting */
 	void (*flow_ctrl)(struct mac_device_info *hw, unsigned int duplex,
-			  unsigned int fc, unsigned int pause_time);
+			  unsigned int fc, unsigned int pause_time, u32 tx_cnt);
 	/* Set power management mode (e.g. magic frame) */
 	void (*pmt)(struct mac_device_info *hw, unsigned long mode);
 	/* Set/Get Unicast MAC addresses */
@@ -477,7 +524,8 @@ struct stmmac_ops {
 	void (*reset_eee_mode)(struct mac_device_info *hw);
 	void (*set_eee_timer)(struct mac_device_info *hw, int ls, int tw);
 	void (*set_eee_pls)(struct mac_device_info *hw, int link);
-	void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x);
+	void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x,
+		      u32 rx_queues, u32 tx_queues);
 	/* PCS calls */
 	void (*pcs_ctrl_ane)(void __iomem *ioaddr, bool ane, bool srgmi_ral,
 			     bool loopback);
@@ -547,6 +595,11 @@ struct mac_device_info {
 	unsigned int ps;
 };
 
+struct stmmac_rx_routing {
+	u32 reg_mask;
+	u32 reg_shift;
+};
+
 struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr, int mcbins,
 					int perfect_uc_entries,
 					int *synopsys_id);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index 1a3fa3d9f855..dd6a2f9791cc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -14,16 +14,34 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/device.h>
+#include <linux/gpio/consumer.h>
 #include <linux/ethtool.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/of_net.h>
 #include <linux/mfd/syscon.h>
 #include <linux/platform_device.h>
+#include <linux/reset.h>
 #include <linux/stmmac.h>
 
 #include "stmmac_platform.h"
+#include "dwmac4.h"
+
+struct tegra_eqos {
+	struct device *dev;
+	void __iomem *regs;
+
+	struct reset_control *rst;
+	struct clk *clk_master;
+	struct clk *clk_slave;
+	struct clk *clk_tx;
+	struct clk *clk_rx;
+
+	struct gpio_desc *reset;
+};
 
 static int dwc_eth_dwmac_config_dt(struct platform_device *pdev,
 				   struct plat_stmmacenet_data *plat_dat)
@@ -106,13 +124,309 @@ static int dwc_eth_dwmac_config_dt(struct platform_device *pdev,
 	return 0;
 }
 
+static void *dwc_qos_probe(struct platform_device *pdev,
+			   struct plat_stmmacenet_data *plat_dat,
+			   struct stmmac_resources *stmmac_res)
+{
+	int err;
+
+	plat_dat->stmmac_clk = devm_clk_get(&pdev->dev, "apb_pclk");
+	if (IS_ERR(plat_dat->stmmac_clk)) {
+		dev_err(&pdev->dev, "apb_pclk clock not found.\n");
+		return ERR_CAST(plat_dat->stmmac_clk);
+	}
+
+	err = clk_prepare_enable(plat_dat->stmmac_clk);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to enable apb_pclk clock: %d\n",
+			err);
+		return ERR_PTR(err);
+	}
+
+	plat_dat->pclk = devm_clk_get(&pdev->dev, "phy_ref_clk");
+	if (IS_ERR(plat_dat->pclk)) {
+		dev_err(&pdev->dev, "phy_ref_clk clock not found.\n");
+		err = PTR_ERR(plat_dat->pclk);
+		goto disable;
+	}
+
+	err = clk_prepare_enable(plat_dat->pclk);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to enable phy_ref clock: %d\n",
+			err);
+		goto disable;
+	}
+
+	return NULL;
+
+disable:
+	clk_disable_unprepare(plat_dat->stmmac_clk);
+	return ERR_PTR(err);
+}
+
+static int dwc_qos_remove(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct stmmac_priv *priv = netdev_priv(ndev);
+
+	clk_disable_unprepare(priv->plat->pclk);
+	clk_disable_unprepare(priv->plat->stmmac_clk);
+
+	return 0;
+}
+
+#define SDMEMCOMPPADCTRL 0x8800
+#define  SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD BIT(31)
+
+#define AUTO_CAL_CONFIG 0x8804
+#define  AUTO_CAL_CONFIG_START BIT(31)
+#define  AUTO_CAL_CONFIG_ENABLE BIT(29)
+
+#define AUTO_CAL_STATUS 0x880c
+#define  AUTO_CAL_STATUS_ACTIVE BIT(31)
+
+static void tegra_eqos_fix_speed(void *priv, unsigned int speed)
+{
+	struct tegra_eqos *eqos = priv;
+	unsigned long rate = 125000000;
+	bool needs_calibration = false;
+	u32 value;
+	int err;
+
+	switch (speed) {
+	case SPEED_1000:
+		needs_calibration = true;
+		rate = 125000000;
+		break;
+
+	case SPEED_100:
+		needs_calibration = true;
+		rate = 25000000;
+		break;
+
+	case SPEED_10:
+		rate = 2500000;
+		break;
+
+	default:
+		dev_err(eqos->dev, "invalid speed %u\n", speed);
+		break;
+	}
+
+	if (needs_calibration) {
+		/* calibrate */
+		value = readl(eqos->regs + SDMEMCOMPPADCTRL);
+		value |= SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD;
+		writel(value, eqos->regs + SDMEMCOMPPADCTRL);
+
+		udelay(1);
+
+		value = readl(eqos->regs + AUTO_CAL_CONFIG);
+		value |= AUTO_CAL_CONFIG_START | AUTO_CAL_CONFIG_ENABLE;
+		writel(value, eqos->regs + AUTO_CAL_CONFIG);
+
+		err = readl_poll_timeout_atomic(eqos->regs + AUTO_CAL_STATUS,
+						value,
+						value & AUTO_CAL_STATUS_ACTIVE,
+						1, 10);
+		if (err < 0) {
+			dev_err(eqos->dev, "calibration did not start\n");
+			goto failed;
+		}
+
+		err = readl_poll_timeout_atomic(eqos->regs + AUTO_CAL_STATUS,
+						value,
+						(value & AUTO_CAL_STATUS_ACTIVE) == 0,
+						20, 200);
+		if (err < 0) {
+			dev_err(eqos->dev, "calibration didn't finish\n");
+			goto failed;
+		}
+
+	failed:
+		value = readl(eqos->regs + SDMEMCOMPPADCTRL);
+		value &= ~SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD;
+		writel(value, eqos->regs + SDMEMCOMPPADCTRL);
+	} else {
+		value = readl(eqos->regs + AUTO_CAL_CONFIG);
+		value &= ~AUTO_CAL_CONFIG_ENABLE;
+		writel(value, eqos->regs + AUTO_CAL_CONFIG);
+	}
+
+	err = clk_set_rate(eqos->clk_tx, rate);
+	if (err < 0)
+		dev_err(eqos->dev, "failed to set TX rate: %d\n", err);
+}
+
+static int tegra_eqos_init(struct platform_device *pdev, void *priv)
+{
+	struct tegra_eqos *eqos = priv;
+	unsigned long rate;
+	u32 value;
+
+	rate = clk_get_rate(eqos->clk_slave);
+
+	value = (rate / 1000000) - 1;
+	writel(value, eqos->regs + GMAC_1US_TIC_COUNTER);
+
+	return 0;
+}
+
+static void *tegra_eqos_probe(struct platform_device *pdev,
+			      struct plat_stmmacenet_data *data,
+			      struct stmmac_resources *res)
+{
+	struct tegra_eqos *eqos;
+	int err;
+
+	eqos = devm_kzalloc(&pdev->dev, sizeof(*eqos), GFP_KERNEL);
+	if (!eqos) {
+		err = -ENOMEM;
+		goto error;
+	}
+
+	eqos->dev = &pdev->dev;
+	eqos->regs = res->addr;
+
+	eqos->clk_master = devm_clk_get(&pdev->dev, "master_bus");
+	if (IS_ERR(eqos->clk_master)) {
+		err = PTR_ERR(eqos->clk_master);
+		goto error;
+	}
+
+	err = clk_prepare_enable(eqos->clk_master);
+	if (err < 0)
+		goto error;
+
+	eqos->clk_slave = devm_clk_get(&pdev->dev, "slave_bus");
+	if (IS_ERR(eqos->clk_slave)) {
+		err = PTR_ERR(eqos->clk_slave);
+		goto disable_master;
+	}
+
+	data->stmmac_clk = eqos->clk_slave;
+
+	err = clk_prepare_enable(eqos->clk_slave);
+	if (err < 0)
+		goto disable_master;
+
+	eqos->clk_rx = devm_clk_get(&pdev->dev, "rx");
+	if (IS_ERR(eqos->clk_rx)) {
+		err = PTR_ERR(eqos->clk_rx);
+		goto disable_slave;
+	}
+
+	err = clk_prepare_enable(eqos->clk_rx);
+	if (err < 0)
+		goto disable_slave;
+
+	eqos->clk_tx = devm_clk_get(&pdev->dev, "tx");
+	if (IS_ERR(eqos->clk_tx)) {
+		err = PTR_ERR(eqos->clk_tx);
+		goto disable_rx;
+	}
+
+	err = clk_prepare_enable(eqos->clk_tx);
+	if (err < 0)
+		goto disable_rx;
+
+	eqos->reset = devm_gpiod_get(&pdev->dev, "phy-reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(eqos->reset)) {
+		err = PTR_ERR(eqos->reset);
+		goto disable_tx;
+	}
+
+	usleep_range(2000, 4000);
+	gpiod_set_value(eqos->reset, 0);
+
+	eqos->rst = devm_reset_control_get(&pdev->dev, "eqos");
+	if (IS_ERR(eqos->rst)) {
+		err = PTR_ERR(eqos->rst);
+		goto reset_phy;
+	}
+
+	err = reset_control_assert(eqos->rst);
+	if (err < 0)
+		goto reset_phy;
+
+	usleep_range(2000, 4000);
+
+	err = reset_control_deassert(eqos->rst);
+	if (err < 0)
+		goto reset_phy;
+
+	usleep_range(2000, 4000);
+
+	data->fix_mac_speed = tegra_eqos_fix_speed;
+	data->init = tegra_eqos_init;
+	data->bsp_priv = eqos;
+
+	err = tegra_eqos_init(pdev, eqos);
+	if (err < 0)
+		goto reset;
+
+out:
+	return eqos;
+
+reset:
+	reset_control_assert(eqos->rst);
+reset_phy:
+	gpiod_set_value(eqos->reset, 1);
+disable_tx:
+	clk_disable_unprepare(eqos->clk_tx);
+disable_rx:
+	clk_disable_unprepare(eqos->clk_rx);
+disable_slave:
+	clk_disable_unprepare(eqos->clk_slave);
+disable_master:
+	clk_disable_unprepare(eqos->clk_master);
+error:
+	eqos = ERR_PTR(err);
+	goto out;
+}
+
+static int tegra_eqos_remove(struct platform_device *pdev)
+{
+	struct tegra_eqos *eqos = get_stmmac_bsp_priv(&pdev->dev);
+
+	reset_control_assert(eqos->rst);
+	gpiod_set_value(eqos->reset, 1);
+	clk_disable_unprepare(eqos->clk_tx);
+	clk_disable_unprepare(eqos->clk_rx);
+	clk_disable_unprepare(eqos->clk_slave);
+	clk_disable_unprepare(eqos->clk_master);
+
+	return 0;
+}
+
+struct dwc_eth_dwmac_data {
+	void *(*probe)(struct platform_device *pdev,
+		       struct plat_stmmacenet_data *data,
+		       struct stmmac_resources *res);
+	int (*remove)(struct platform_device *pdev);
+};
+
+static const struct dwc_eth_dwmac_data dwc_qos_data = {
+	.probe = dwc_qos_probe,
+	.remove = dwc_qos_remove,
+};
+
+static const struct dwc_eth_dwmac_data tegra_eqos_data = {
+	.probe = tegra_eqos_probe,
+	.remove = tegra_eqos_remove,
+};
+
 static int dwc_eth_dwmac_probe(struct platform_device *pdev)
 {
+	const struct dwc_eth_dwmac_data *data;
 	struct plat_stmmacenet_data *plat_dat;
 	struct stmmac_resources stmmac_res;
 	struct resource *res;
+	void *priv;
 	int ret;
 
+	data = of_device_get_match_data(&pdev->dev);
+
 	memset(&stmmac_res, 0, sizeof(struct stmmac_resources));
 
 	/**
@@ -138,39 +452,26 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev)
 	if (IS_ERR(plat_dat))
 		return PTR_ERR(plat_dat);
 
-	plat_dat->stmmac_clk = devm_clk_get(&pdev->dev, "apb_pclk");
-	if (IS_ERR(plat_dat->stmmac_clk)) {
-		dev_err(&pdev->dev, "apb_pclk clock not found.\n");
-		ret = PTR_ERR(plat_dat->stmmac_clk);
-		plat_dat->stmmac_clk = NULL;
-		goto err_remove_config_dt;
-	}
-	clk_prepare_enable(plat_dat->stmmac_clk);
-
-	plat_dat->pclk = devm_clk_get(&pdev->dev, "phy_ref_clk");
-	if (IS_ERR(plat_dat->pclk)) {
-		dev_err(&pdev->dev, "phy_ref_clk clock not found.\n");
-		ret = PTR_ERR(plat_dat->pclk);
-		plat_dat->pclk = NULL;
-		goto err_out_clk_dis_phy;
+	priv = data->probe(pdev, plat_dat, &stmmac_res);
+	if (IS_ERR(priv)) {
+		ret = PTR_ERR(priv);
+		dev_err(&pdev->dev, "failed to probe subdriver: %d\n", ret);
+		goto remove_config;
 	}
-	clk_prepare_enable(plat_dat->pclk);
 
 	ret = dwc_eth_dwmac_config_dt(pdev, plat_dat);
 	if (ret)
-		goto err_out_clk_dis_aper;
+		goto remove;
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret)
-		goto err_out_clk_dis_aper;
+		goto remove;
 
-	return 0;
+	return ret;
 
-err_out_clk_dis_aper:
-	clk_disable_unprepare(plat_dat->pclk);
-err_out_clk_dis_phy:
-	clk_disable_unprepare(plat_dat->stmmac_clk);
-err_remove_config_dt:
+remove:
+	data->remove(pdev);
+remove_config:
 	stmmac_remove_config_dt(pdev, plat_dat);
 
 	return ret;
@@ -178,11 +479,29 @@ err_remove_config_dt:
 
 static int dwc_eth_dwmac_remove(struct platform_device *pdev)
 {
-	return stmmac_pltfr_remove(pdev);
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	const struct dwc_eth_dwmac_data *data;
+	int err;
+
+	data = of_device_get_match_data(&pdev->dev);
+
+	err = stmmac_dvr_remove(&pdev->dev);
+	if (err < 0)
+		dev_err(&pdev->dev, "failed to remove platform: %d\n", err);
+
+	err = data->remove(pdev);
+	if (err < 0)
+		dev_err(&pdev->dev, "failed to remove subdriver: %d\n", err);
+
+	stmmac_remove_config_dt(pdev, priv->plat);
+
+	return err;
 }
 
 static const struct of_device_id dwc_eth_dwmac_match[] = {
-	{ .compatible = "snps,dwc-qos-ethernet-4.10", },
+	{ .compatible = "snps,dwc-qos-ethernet-4.10", .data = &dwc_qos_data },
+	{ .compatible = "nvidia,tegra186-eqos", .data = &tegra_eqos_data },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, dwc_eth_dwmac_match);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index e5db6ac36235..f0df5193f047 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -74,6 +74,10 @@ struct rk_priv_data {
 #define GRF_BIT(nr)	(BIT(nr) | BIT(nr+16))
 #define GRF_CLR_BIT(nr)	(BIT(nr+16))
 
+#define DELAY_ENABLE(soc, tx, rx) \
+	(((tx) ? soc##_GMAC_TXCLK_DLY_ENABLE : soc##_GMAC_TXCLK_DLY_DISABLE) | \
+	 ((rx) ? soc##_GMAC_RXCLK_DLY_ENABLE : soc##_GMAC_RXCLK_DLY_DISABLE))
+
 #define RK3228_GRF_MAC_CON0	0x0900
 #define RK3228_GRF_MAC_CON1	0x0904
 
@@ -115,8 +119,7 @@ static void rk3228_set_to_rgmii(struct rk_priv_data *bsp_priv,
 	regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
 		     RK3228_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3228_GMAC_RMII_MODE_CLR |
-		     RK3228_GMAC_RXCLK_DLY_ENABLE |
-		     RK3228_GMAC_TXCLK_DLY_ENABLE);
+		     DELAY_ENABLE(RK3228, tx_delay, rx_delay));
 
 	regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON0,
 		     RK3228_GMAC_CLK_RX_DL_CFG(rx_delay) |
@@ -232,8 +235,7 @@ static void rk3288_set_to_rgmii(struct rk_priv_data *bsp_priv,
 		     RK3288_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3288_GMAC_RMII_MODE_CLR);
 	regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON3,
-		     RK3288_GMAC_RXCLK_DLY_ENABLE |
-		     RK3288_GMAC_TXCLK_DLY_ENABLE |
+		     DELAY_ENABLE(RK3288, tx_delay, rx_delay) |
 		     RK3288_GMAC_CLK_RX_DL_CFG(rx_delay) |
 		     RK3288_GMAC_CLK_TX_DL_CFG(tx_delay));
 }
@@ -460,8 +462,7 @@ static void rk3366_set_to_rgmii(struct rk_priv_data *bsp_priv,
 		     RK3366_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3366_GMAC_RMII_MODE_CLR);
 	regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON7,
-		     RK3366_GMAC_RXCLK_DLY_ENABLE |
-		     RK3366_GMAC_TXCLK_DLY_ENABLE |
+		     DELAY_ENABLE(RK3366, tx_delay, rx_delay) |
 		     RK3366_GMAC_CLK_RX_DL_CFG(rx_delay) |
 		     RK3366_GMAC_CLK_TX_DL_CFG(tx_delay));
 }
@@ -572,8 +573,7 @@ static void rk3368_set_to_rgmii(struct rk_priv_data *bsp_priv,
 		     RK3368_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3368_GMAC_RMII_MODE_CLR);
 	regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON16,
-		     RK3368_GMAC_RXCLK_DLY_ENABLE |
-		     RK3368_GMAC_TXCLK_DLY_ENABLE |
+		     DELAY_ENABLE(RK3368, tx_delay, rx_delay) |
 		     RK3368_GMAC_CLK_RX_DL_CFG(rx_delay) |
 		     RK3368_GMAC_CLK_TX_DL_CFG(tx_delay));
 }
@@ -684,8 +684,7 @@ static void rk3399_set_to_rgmii(struct rk_priv_data *bsp_priv,
 		     RK3399_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3399_GMAC_RMII_MODE_CLR);
 	regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON6,
-		     RK3399_GMAC_RXCLK_DLY_ENABLE |
-		     RK3399_GMAC_TXCLK_DLY_ENABLE |
+		     DELAY_ENABLE(RK3399, tx_delay, rx_delay) |
 		     RK3399_GMAC_CLK_RX_DL_CFG(rx_delay) |
 		     RK3399_GMAC_CLK_TX_DL_CFG(tx_delay));
 }
@@ -985,14 +984,29 @@ static int rk_gmac_powerup(struct rk_priv_data *bsp_priv)
 		return ret;
 
 	/*rmii or rgmii*/
-	if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RGMII) {
+	switch (bsp_priv->phy_iface) {
+	case PHY_INTERFACE_MODE_RGMII:
 		dev_info(dev, "init for RGMII\n");
 		bsp_priv->ops->set_to_rgmii(bsp_priv, bsp_priv->tx_delay,
 					    bsp_priv->rx_delay);
-	} else if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII) {
+		break;
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		dev_info(dev, "init for RGMII_ID\n");
+		bsp_priv->ops->set_to_rgmii(bsp_priv, 0, 0);
+		break;
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+		dev_info(dev, "init for RGMII_RXID\n");
+		bsp_priv->ops->set_to_rgmii(bsp_priv, bsp_priv->tx_delay, 0);
+		break;
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		dev_info(dev, "init for RGMII_TXID\n");
+		bsp_priv->ops->set_to_rgmii(bsp_priv, 0, bsp_priv->rx_delay);
+		break;
+	case PHY_INTERFACE_MODE_RMII:
 		dev_info(dev, "init for RMII\n");
 		bsp_priv->ops->set_to_rmii(bsp_priv);
-	} else {
+		break;
+	default:
 		dev_err(dev, "NO interface defined!\n");
 	}
 
@@ -1022,12 +1036,19 @@ static void rk_fix_speed(void *priv, unsigned int speed)
 	struct rk_priv_data *bsp_priv = priv;
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RGMII)
+	switch (bsp_priv->phy_iface) {
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		bsp_priv->ops->set_rgmii_speed(bsp_priv, speed);
-	else if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII)
+		break;
+	case PHY_INTERFACE_MODE_RMII:
 		bsp_priv->ops->set_rmii_speed(bsp_priv, speed);
-	else
+		break;
+	default:
 		dev_err(dev, "unsupported interface %d", bsp_priv->phy_iface);
+	}
 }
 
 static int rk_gmac_probe(struct platform_device *pdev)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 19b9b3087099..f3d9305e5f70 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -216,7 +216,8 @@ static void dwmac1000_set_filter(struct mac_device_info *hw,
 
 
 static void dwmac1000_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
-				unsigned int fc, unsigned int pause_time)
+				unsigned int fc, unsigned int pause_time,
+				u32 tx_cnt)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	/* Set flow such that DZPQ in Mac Register 6 is 0,
@@ -412,7 +413,8 @@ static void dwmac1000_get_adv_lp(void __iomem *ioaddr, struct rgmii_adv *adv)
 	dwmac_get_adv_lp(ioaddr, GMAC_PCS_BASE, adv);
 }
 
-static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
+static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x,
+			    u32 rx_queues, u32 tx_queues)
 {
 	u32 value = readl(ioaddr + GMAC_DEBUG);
 
@@ -488,6 +490,7 @@ static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
 
 static const struct stmmac_ops dwmac1000_ops = {
 	.core_init = dwmac1000_core_init,
+	.set_mac = stmmac_set_mac,
 	.rx_ipc = dwmac1000_rx_ipc_enable,
 	.dump_regs = dwmac1000_dump_regs,
 	.host_irq_status = dwmac1000_irq_status,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
index d3654a447046..471a9aa6ac94 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
@@ -247,7 +247,8 @@ static void dwmac1000_get_hw_feature(void __iomem *ioaddr,
 	dma_cap->enh_desc = (hw_cap & DMA_HW_FEAT_ENHDESSEL) >> 24;
 }
 
-static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt)
+static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt,
+				  u32 number_chan)
 {
 	writel(riwt, ioaddr + DMA_RX_WATCHDOG);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
index e370ccec6176..1b3609105484 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
@@ -131,7 +131,8 @@ static void dwmac100_set_filter(struct mac_device_info *hw,
 }
 
 static void dwmac100_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
-			       unsigned int fc, unsigned int pause_time)
+			       unsigned int fc, unsigned int pause_time,
+			       u32 tx_cnt)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	unsigned int flow = MAC_FLOW_CTRL_ENABLE;
@@ -149,6 +150,7 @@ static void dwmac100_pmt(struct mac_device_info *hw, unsigned long mode)
 
 static const struct stmmac_ops dwmac100_ops = {
 	.core_init = dwmac100_core_init,
+	.set_mac = stmmac_set_mac,
 	.rx_ipc = dwmac100_rx_ipc_enable,
 	.dump_regs = dwmac100_dump_mac_regs,
 	.host_irq_status = dwmac100_irq_status,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index db45134fddf0..d74cedf2a397 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -22,9 +22,15 @@
 #define GMAC_HASH_TAB_32_63		0x00000014
 #define GMAC_RX_FLOW_CTRL		0x00000090
 #define GMAC_QX_TX_FLOW_CTRL(x)		(0x70 + x * 4)
+#define GMAC_TXQ_PRTY_MAP0		0x98
+#define GMAC_TXQ_PRTY_MAP1		0x9C
 #define GMAC_RXQ_CTRL0			0x000000a0
+#define GMAC_RXQ_CTRL1			0x000000a4
+#define GMAC_RXQ_CTRL2			0x000000a8
+#define GMAC_RXQ_CTRL3			0x000000ac
 #define GMAC_INT_STATUS			0x000000b0
 #define GMAC_INT_EN			0x000000b4
+#define GMAC_1US_TIC_COUNTER		0x000000dc
 #define GMAC_PCS_BASE			0x000000e0
 #define GMAC_PHYIF_CONTROL_STATUS	0x000000f8
 #define GMAC_PMT			0x000000c0
@@ -38,6 +44,22 @@
 #define GMAC_ADDR_HIGH(reg)		(0x300 + reg * 8)
 #define GMAC_ADDR_LOW(reg)		(0x304 + reg * 8)
 
+/* RX Queues Routing */
+#define GMAC_RXQCTRL_AVCPQ_MASK		GENMASK(2, 0)
+#define GMAC_RXQCTRL_AVCPQ_SHIFT	0
+#define GMAC_RXQCTRL_PTPQ_MASK		GENMASK(6, 4)
+#define GMAC_RXQCTRL_PTPQ_SHIFT		4
+#define GMAC_RXQCTRL_DCBCPQ_MASK	GENMASK(10, 8)
+#define GMAC_RXQCTRL_DCBCPQ_SHIFT	8
+#define GMAC_RXQCTRL_UPQ_MASK		GENMASK(14, 12)
+#define GMAC_RXQCTRL_UPQ_SHIFT		12
+#define GMAC_RXQCTRL_MCBCQ_MASK		GENMASK(18, 16)
+#define GMAC_RXQCTRL_MCBCQ_SHIFT	16
+#define GMAC_RXQCTRL_MCBCQEN		BIT(20)
+#define GMAC_RXQCTRL_MCBCQEN_SHIFT	20
+#define GMAC_RXQCTRL_TACPQE		BIT(21)
+#define GMAC_RXQCTRL_TACPQE_SHIFT	21
+
 /* MAC Packet Filtering */
 #define GMAC_PACKET_FILTER_PR		BIT(0)
 #define GMAC_PACKET_FILTER_HMC		BIT(2)
@@ -53,6 +75,14 @@
 /* MAC Flow Control RX */
 #define GMAC_RX_FLOW_CTRL_RFE		BIT(0)
 
+/* RX Queues Priorities */
+#define GMAC_RXQCTRL_PSRQX_MASK(x)	GENMASK(7 + ((x) * 8), 0 + ((x) * 8))
+#define GMAC_RXQCTRL_PSRQX_SHIFT(x)	((x) * 8)
+
+/* TX Queues Priorities */
+#define GMAC_TXQCTRL_PSTQX_MASK(x)	GENMASK(7 + ((x) * 8), 0 + ((x) * 8))
+#define GMAC_TXQCTRL_PSTQX_SHIFT(x)	((x) * 8)
+
 /* MAC Flow Control TX */
 #define GMAC_TX_FLOW_CTRL_TFE		BIT(1)
 #define GMAC_TX_FLOW_CTRL_PT_SHIFT	16
@@ -148,6 +178,8 @@ enum power_event {
 /* MAC HW features1 bitmap */
 #define GMAC_HW_FEAT_AVSEL		BIT(20)
 #define GMAC_HW_TSOEN			BIT(18)
+#define GMAC_HW_TXFIFOSIZE		GENMASK(10, 6)
+#define GMAC_HW_RXFIFOSIZE		GENMASK(4, 0)
 
 /* MAC HW features2 bitmap */
 #define GMAC_HW_FEAT_TXCHCNT		GENMASK(21, 18)
@@ -161,8 +193,25 @@ enum power_event {
 #define GMAC_HI_REG_AE			BIT(31)
 
 /*  MTL registers */
+#define MTL_OPERATION_MODE		0x00000c00
+#define MTL_OPERATION_SCHALG_MASK	GENMASK(6, 5)
+#define MTL_OPERATION_SCHALG_WRR	(0x0 << 5)
+#define MTL_OPERATION_SCHALG_WFQ	(0x1 << 5)
+#define MTL_OPERATION_SCHALG_DWRR	(0x2 << 5)
+#define MTL_OPERATION_SCHALG_SP		(0x3 << 5)
+#define MTL_OPERATION_RAA		BIT(2)
+#define MTL_OPERATION_RAA_SP		(0x0 << 2)
+#define MTL_OPERATION_RAA_WSP		(0x1 << 2)
+
 #define MTL_INT_STATUS			0x00000c20
-#define MTL_INT_Q0			BIT(0)
+#define MTL_INT_QX(x)			BIT(x)
+
+#define MTL_RXQ_DMA_MAP0		0x00000c30 /* queue 0 to 3 */
+#define MTL_RXQ_DMA_MAP1		0x00000c34 /* queue 4 to 7 */
+#define MTL_RXQ_DMA_Q04MDMACH_MASK	GENMASK(3, 0)
+#define MTL_RXQ_DMA_Q04MDMACH(x)	((x) << 0)
+#define MTL_RXQ_DMA_QXMDMACH_MASK(x)	GENMASK(11 + (8 * ((x) - 1)), 8 * (x))
+#define MTL_RXQ_DMA_QXMDMACH(chan, q)	((chan) << (8 * (q)))
 
 #define MTL_CHAN_BASE_ADDR		0x00000d00
 #define MTL_CHAN_BASE_OFFSET		0x40
@@ -180,6 +229,7 @@ enum power_event {
 #define MTL_OP_MODE_TSF			BIT(1)
 
 #define MTL_OP_MODE_TQS_MASK		GENMASK(24, 16)
+#define MTL_OP_MODE_TQS_SHIFT		16
 
 #define MTL_OP_MODE_TTC_MASK		0x70
 #define MTL_OP_MODE_TTC_SHIFT		4
@@ -193,6 +243,17 @@ enum power_event {
 #define MTL_OP_MODE_TTC_384		(6 << MTL_OP_MODE_TTC_SHIFT)
 #define MTL_OP_MODE_TTC_512		(7 << MTL_OP_MODE_TTC_SHIFT)
 
+#define MTL_OP_MODE_RQS_MASK		GENMASK(29, 20)
+#define MTL_OP_MODE_RQS_SHIFT		20
+
+#define MTL_OP_MODE_RFD_MASK		GENMASK(19, 14)
+#define MTL_OP_MODE_RFD_SHIFT		14
+
+#define MTL_OP_MODE_RFA_MASK		GENMASK(13, 8)
+#define MTL_OP_MODE_RFA_SHIFT		8
+
+#define MTL_OP_MODE_EHFC		BIT(7)
+
 #define MTL_OP_MODE_RTC_MASK		0x18
 #define MTL_OP_MODE_RTC_SHIFT		3
 
@@ -201,6 +262,46 @@ enum power_event {
 #define MTL_OP_MODE_RTC_96		(2 << MTL_OP_MODE_RTC_SHIFT)
 #define MTL_OP_MODE_RTC_128		(3 << MTL_OP_MODE_RTC_SHIFT)
 
+/* MTL ETS Control register */
+#define MTL_ETS_CTRL_BASE_ADDR		0x00000d10
+#define MTL_ETS_CTRL_BASE_OFFSET	0x40
+#define MTL_ETSX_CTRL_BASE_ADDR(x)	(MTL_ETS_CTRL_BASE_ADDR + \
+					((x) * MTL_ETS_CTRL_BASE_OFFSET))
+
+#define MTL_ETS_CTRL_CC			BIT(3)
+#define MTL_ETS_CTRL_AVALG		BIT(2)
+
+/* MTL Queue Quantum Weight */
+#define MTL_TXQ_WEIGHT_BASE_ADDR	0x00000d18
+#define MTL_TXQ_WEIGHT_BASE_OFFSET	0x40
+#define MTL_TXQX_WEIGHT_BASE_ADDR(x)	(MTL_TXQ_WEIGHT_BASE_ADDR + \
+					((x) * MTL_TXQ_WEIGHT_BASE_OFFSET))
+#define MTL_TXQ_WEIGHT_ISCQW_MASK	GENMASK(20, 0)
+
+/* MTL sendSlopeCredit register */
+#define MTL_SEND_SLP_CRED_BASE_ADDR	0x00000d1c
+#define MTL_SEND_SLP_CRED_OFFSET	0x40
+#define MTL_SEND_SLP_CREDX_BASE_ADDR(x)	(MTL_SEND_SLP_CRED_BASE_ADDR + \
+					((x) * MTL_SEND_SLP_CRED_OFFSET))
+
+#define MTL_SEND_SLP_CRED_SSC_MASK	GENMASK(13, 0)
+
+/* MTL hiCredit register */
+#define MTL_HIGH_CRED_BASE_ADDR		0x00000d20
+#define MTL_HIGH_CRED_OFFSET		0x40
+#define MTL_HIGH_CREDX_BASE_ADDR(x)	(MTL_HIGH_CRED_BASE_ADDR + \
+					((x) * MTL_HIGH_CRED_OFFSET))
+
+#define MTL_HIGH_CRED_HC_MASK		GENMASK(28, 0)
+
+/* MTL loCredit register */
+#define MTL_LOW_CRED_BASE_ADDR		0x00000d24
+#define MTL_LOW_CRED_OFFSET		0x40
+#define MTL_LOW_CREDX_BASE_ADDR(x)	(MTL_LOW_CRED_BASE_ADDR + \
+					((x) * MTL_LOW_CRED_OFFSET))
+
+#define MTL_HIGH_CRED_LC_MASK		GENMASK(28, 0)
+
 /*  MTL debug */
 #define MTL_DEBUG_TXSTSFSTS		BIT(5)
 #define MTL_DEBUG_TXFSTS		BIT(4)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 1e79e6529c4a..48793f2e9307 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -59,17 +59,211 @@ static void dwmac4_core_init(struct mac_device_info *hw, int mtu)
 	writel(value, ioaddr + GMAC_INT_EN);
 }
 
-static void dwmac4_rx_queue_enable(struct mac_device_info *hw, u32 queue)
+static void dwmac4_rx_queue_enable(struct mac_device_info *hw,
+				   u8 mode, u32 queue)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value = readl(ioaddr + GMAC_RXQ_CTRL0);
 
 	value &= GMAC_RX_QUEUE_CLEAR(queue);
-	value |= GMAC_RX_AV_QUEUE_ENABLE(queue);
+	if (mode == MTL_QUEUE_AVB)
+		value |= GMAC_RX_AV_QUEUE_ENABLE(queue);
+	else if (mode == MTL_QUEUE_DCB)
+		value |= GMAC_RX_DCB_QUEUE_ENABLE(queue);
 
 	writel(value, ioaddr + GMAC_RXQ_CTRL0);
 }
 
+static void dwmac4_rx_queue_priority(struct mac_device_info *hw,
+				     u32 prio, u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 base_register;
+	u32 value;
+
+	base_register = (queue < 4) ? GMAC_RXQ_CTRL2 : GMAC_RXQ_CTRL3;
+
+	value = readl(ioaddr + base_register);
+
+	value &= ~GMAC_RXQCTRL_PSRQX_MASK(queue);
+	value |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) &
+						GMAC_RXQCTRL_PSRQX_MASK(queue);
+	writel(value, ioaddr + base_register);
+}
+
+static void dwmac4_tx_queue_priority(struct mac_device_info *hw,
+				     u32 prio, u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 base_register;
+	u32 value;
+
+	base_register = (queue < 4) ? GMAC_TXQ_PRTY_MAP0 : GMAC_TXQ_PRTY_MAP1;
+
+	value = readl(ioaddr + base_register);
+
+	value &= ~GMAC_TXQCTRL_PSTQX_MASK(queue);
+	value |= (prio << GMAC_TXQCTRL_PSTQX_SHIFT(queue)) &
+						GMAC_TXQCTRL_PSTQX_MASK(queue);
+
+	writel(value, ioaddr + base_register);
+}
+
+static void dwmac4_tx_queue_routing(struct mac_device_info *hw,
+				    u8 packet, u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	const struct stmmac_rx_routing route_possibilities[] = {
+		{ GMAC_RXQCTRL_AVCPQ_MASK, GMAC_RXQCTRL_AVCPQ_SHIFT },
+		{ GMAC_RXQCTRL_PTPQ_MASK, GMAC_RXQCTRL_PTPQ_SHIFT },
+		{ GMAC_RXQCTRL_DCBCPQ_MASK, GMAC_RXQCTRL_DCBCPQ_SHIFT },
+		{ GMAC_RXQCTRL_UPQ_MASK, GMAC_RXQCTRL_UPQ_SHIFT },
+		{ GMAC_RXQCTRL_MCBCQ_MASK, GMAC_RXQCTRL_MCBCQ_SHIFT },
+	};
+
+	value = readl(ioaddr + GMAC_RXQ_CTRL1);
+
+	/* routing configuration */
+	value &= ~route_possibilities[packet - 1].reg_mask;
+	value |= (queue << route_possibilities[packet-1].reg_shift) &
+		 route_possibilities[packet - 1].reg_mask;
+
+	/* some packets require extra ops */
+	if (packet == PACKET_AVCPQ) {
+		value &= ~GMAC_RXQCTRL_TACPQE;
+		value |= 0x1 << GMAC_RXQCTRL_TACPQE_SHIFT;
+	} else if (packet == PACKET_MCBCQ) {
+		value &= ~GMAC_RXQCTRL_MCBCQEN;
+		value |= 0x1 << GMAC_RXQCTRL_MCBCQEN_SHIFT;
+	}
+
+	writel(value, ioaddr + GMAC_RXQ_CTRL1);
+}
+
+static void dwmac4_prog_mtl_rx_algorithms(struct mac_device_info *hw,
+					  u32 rx_alg)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value = readl(ioaddr + MTL_OPERATION_MODE);
+
+	value &= ~MTL_OPERATION_RAA;
+	switch (rx_alg) {
+	case MTL_RX_ALGORITHM_SP:
+		value |= MTL_OPERATION_RAA_SP;
+		break;
+	case MTL_RX_ALGORITHM_WSP:
+		value |= MTL_OPERATION_RAA_WSP;
+		break;
+	default:
+		break;
+	}
+
+	writel(value, ioaddr + MTL_OPERATION_MODE);
+}
+
+static void dwmac4_prog_mtl_tx_algorithms(struct mac_device_info *hw,
+					  u32 tx_alg)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value = readl(ioaddr + MTL_OPERATION_MODE);
+
+	value &= ~MTL_OPERATION_SCHALG_MASK;
+	switch (tx_alg) {
+	case MTL_TX_ALGORITHM_WRR:
+		value |= MTL_OPERATION_SCHALG_WRR;
+		break;
+	case MTL_TX_ALGORITHM_WFQ:
+		value |= MTL_OPERATION_SCHALG_WFQ;
+		break;
+	case MTL_TX_ALGORITHM_DWRR:
+		value |= MTL_OPERATION_SCHALG_DWRR;
+		break;
+	case MTL_TX_ALGORITHM_SP:
+		value |= MTL_OPERATION_SCHALG_SP;
+		break;
+	default:
+		break;
+	}
+}
+
+static void dwmac4_set_mtl_tx_queue_weight(struct mac_device_info *hw,
+					   u32 weight, u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value = readl(ioaddr + MTL_TXQX_WEIGHT_BASE_ADDR(queue));
+
+	value &= ~MTL_TXQ_WEIGHT_ISCQW_MASK;
+	value |= weight & MTL_TXQ_WEIGHT_ISCQW_MASK;
+	writel(value, ioaddr + MTL_TXQX_WEIGHT_BASE_ADDR(queue));
+}
+
+static void dwmac4_map_mtl_dma(struct mac_device_info *hw, u32 queue, u32 chan)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	if (queue < 4)
+		value = readl(ioaddr + MTL_RXQ_DMA_MAP0);
+	else
+		value = readl(ioaddr + MTL_RXQ_DMA_MAP1);
+
+	if (queue == 0 || queue == 4) {
+		value &= ~MTL_RXQ_DMA_Q04MDMACH_MASK;
+		value |= MTL_RXQ_DMA_Q04MDMACH(chan);
+	} else {
+		value &= ~MTL_RXQ_DMA_QXMDMACH_MASK(queue);
+		value |= MTL_RXQ_DMA_QXMDMACH(chan, queue);
+	}
+
+	if (queue < 4)
+		writel(value, ioaddr + MTL_RXQ_DMA_MAP0);
+	else
+		writel(value, ioaddr + MTL_RXQ_DMA_MAP1);
+}
+
+static void dwmac4_config_cbs(struct mac_device_info *hw,
+			      u32 send_slope, u32 idle_slope,
+			      u32 high_credit, u32 low_credit, u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	pr_debug("Queue %d configured as AVB. Parameters:\n", queue);
+	pr_debug("\tsend_slope: 0x%08x\n", send_slope);
+	pr_debug("\tidle_slope: 0x%08x\n", idle_slope);
+	pr_debug("\thigh_credit: 0x%08x\n", high_credit);
+	pr_debug("\tlow_credit: 0x%08x\n", low_credit);
+
+	/* enable AV algorithm */
+	value = readl(ioaddr + MTL_ETSX_CTRL_BASE_ADDR(queue));
+	value |= MTL_ETS_CTRL_AVALG;
+	value |= MTL_ETS_CTRL_CC;
+	writel(value, ioaddr + MTL_ETSX_CTRL_BASE_ADDR(queue));
+
+	/* configure send slope */
+	value = readl(ioaddr + MTL_SEND_SLP_CREDX_BASE_ADDR(queue));
+	value &= ~MTL_SEND_SLP_CRED_SSC_MASK;
+	value |= send_slope & MTL_SEND_SLP_CRED_SSC_MASK;
+	writel(value, ioaddr + MTL_SEND_SLP_CREDX_BASE_ADDR(queue));
+
+	/* configure idle slope (same register as tx weight) */
+	dwmac4_set_mtl_tx_queue_weight(hw, idle_slope, queue);
+
+	/* configure high credit */
+	value = readl(ioaddr + MTL_HIGH_CREDX_BASE_ADDR(queue));
+	value &= ~MTL_HIGH_CRED_HC_MASK;
+	value |= high_credit & MTL_HIGH_CRED_HC_MASK;
+	writel(value, ioaddr + MTL_HIGH_CREDX_BASE_ADDR(queue));
+
+	/* configure high credit */
+	value = readl(ioaddr + MTL_LOW_CREDX_BASE_ADDR(queue));
+	value &= ~MTL_HIGH_CRED_LC_MASK;
+	value |= low_credit & MTL_HIGH_CRED_LC_MASK;
+	writel(value, ioaddr + MTL_LOW_CREDX_BASE_ADDR(queue));
+}
+
 static void dwmac4_dump_regs(struct mac_device_info *hw, u32 *reg_space)
 {
 	void __iomem *ioaddr = hw->pcsr;
@@ -251,11 +445,12 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 }
 
 static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
-			     unsigned int fc, unsigned int pause_time)
+			     unsigned int fc, unsigned int pause_time,
+			     u32 tx_cnt)
 {
 	void __iomem *ioaddr = hw->pcsr;
-	u32 channel = STMMAC_CHAN0;	/* FIXME */
 	unsigned int flow = 0;
+	u32 queue = 0;
 
 	pr_debug("GMAC Flow-Control:\n");
 	if (fc & FLOW_RX) {
@@ -265,13 +460,18 @@ static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
 	}
 	if (fc & FLOW_TX) {
 		pr_debug("\tTransmit Flow-Control ON\n");
-		flow |= GMAC_TX_FLOW_CTRL_TFE;
-		writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(channel));
 
-		if (duplex) {
+		if (duplex)
 			pr_debug("\tduplex mode: PAUSE %d\n", pause_time);
-			flow |= (pause_time << GMAC_TX_FLOW_CTRL_PT_SHIFT);
-			writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(channel));
+
+		for (queue = 0; queue < tx_cnt; queue++) {
+			flow |= GMAC_TX_FLOW_CTRL_TFE;
+
+			if (duplex)
+				flow |=
+				(pause_time << GMAC_TX_FLOW_CTRL_PT_SHIFT);
+
+			writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(queue));
 		}
 	}
 }
@@ -325,11 +525,34 @@ static void dwmac4_phystatus(void __iomem *ioaddr, struct stmmac_extra_stats *x)
 	}
 }
 
+static int dwmac4_irq_mtl_status(struct mac_device_info *hw, u32 chan)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 mtl_int_qx_status;
+	int ret = 0;
+
+	mtl_int_qx_status = readl(ioaddr + MTL_INT_STATUS);
+
+	/* Check MTL Interrupt */
+	if (mtl_int_qx_status & MTL_INT_QX(chan)) {
+		/* read Queue x Interrupt status */
+		u32 status = readl(ioaddr + MTL_CHAN_INT_CTRL(chan));
+
+		if (status & MTL_RX_OVERFLOW_INT) {
+			/*  clear Interrupt */
+			writel(status | MTL_RX_OVERFLOW_INT,
+			       ioaddr + MTL_CHAN_INT_CTRL(chan));
+			ret = CORE_IRQ_MTL_RX_OVERFLOW;
+		}
+	}
+
+	return ret;
+}
+
 static int dwmac4_irq_status(struct mac_device_info *hw,
 			     struct stmmac_extra_stats *x)
 {
 	void __iomem *ioaddr = hw->pcsr;
-	u32 mtl_int_qx_status;
 	u32 intr_status;
 	int ret = 0;
 
@@ -348,20 +571,6 @@ static int dwmac4_irq_status(struct mac_device_info *hw,
 		x->irq_receive_pmt_irq_n++;
 	}
 
-	mtl_int_qx_status = readl(ioaddr + MTL_INT_STATUS);
-	/* Check MTL Interrupt: Currently only one queue is used: Q0. */
-	if (mtl_int_qx_status & MTL_INT_Q0) {
-		/* read Queue 0 Interrupt status */
-		u32 status = readl(ioaddr + MTL_CHAN_INT_CTRL(STMMAC_CHAN0));
-
-		if (status & MTL_RX_OVERFLOW_INT) {
-			/*  clear Interrupt */
-			writel(status | MTL_RX_OVERFLOW_INT,
-			       ioaddr + MTL_CHAN_INT_CTRL(STMMAC_CHAN0));
-			ret = CORE_IRQ_MTL_RX_OVERFLOW;
-		}
-	}
-
 	dwmac_pcs_isr(ioaddr, GMAC_PCS_BASE, intr_status, x);
 	if (intr_status & PCS_RGSMIIIS_IRQ)
 		dwmac4_phystatus(ioaddr, x);
@@ -369,64 +578,69 @@ static int dwmac4_irq_status(struct mac_device_info *hw,
 	return ret;
 }
 
-static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
+static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x,
+			 u32 rx_queues, u32 tx_queues)
 {
 	u32 value;
-
-	/*  Currently only channel 0 is supported */
-	value = readl(ioaddr + MTL_CHAN_TX_DEBUG(STMMAC_CHAN0));
-
-	if (value & MTL_DEBUG_TXSTSFSTS)
-		x->mtl_tx_status_fifo_full++;
-	if (value & MTL_DEBUG_TXFSTS)
-		x->mtl_tx_fifo_not_empty++;
-	if (value & MTL_DEBUG_TWCSTS)
-		x->mmtl_fifo_ctrl++;
-	if (value & MTL_DEBUG_TRCSTS_MASK) {
-		u32 trcsts = (value & MTL_DEBUG_TRCSTS_MASK)
-			     >> MTL_DEBUG_TRCSTS_SHIFT;
-		if (trcsts == MTL_DEBUG_TRCSTS_WRITE)
-			x->mtl_tx_fifo_read_ctrl_write++;
-		else if (trcsts == MTL_DEBUG_TRCSTS_TXW)
-			x->mtl_tx_fifo_read_ctrl_wait++;
-		else if (trcsts == MTL_DEBUG_TRCSTS_READ)
-			x->mtl_tx_fifo_read_ctrl_read++;
-		else
-			x->mtl_tx_fifo_read_ctrl_idle++;
+	u32 queue;
+
+	for (queue = 0; queue < tx_queues; queue++) {
+		value = readl(ioaddr + MTL_CHAN_TX_DEBUG(queue));
+
+		if (value & MTL_DEBUG_TXSTSFSTS)
+			x->mtl_tx_status_fifo_full++;
+		if (value & MTL_DEBUG_TXFSTS)
+			x->mtl_tx_fifo_not_empty++;
+		if (value & MTL_DEBUG_TWCSTS)
+			x->mmtl_fifo_ctrl++;
+		if (value & MTL_DEBUG_TRCSTS_MASK) {
+			u32 trcsts = (value & MTL_DEBUG_TRCSTS_MASK)
+				     >> MTL_DEBUG_TRCSTS_SHIFT;
+			if (trcsts == MTL_DEBUG_TRCSTS_WRITE)
+				x->mtl_tx_fifo_read_ctrl_write++;
+			else if (trcsts == MTL_DEBUG_TRCSTS_TXW)
+				x->mtl_tx_fifo_read_ctrl_wait++;
+			else if (trcsts == MTL_DEBUG_TRCSTS_READ)
+				x->mtl_tx_fifo_read_ctrl_read++;
+			else
+				x->mtl_tx_fifo_read_ctrl_idle++;
+		}
+		if (value & MTL_DEBUG_TXPAUSED)
+			x->mac_tx_in_pause++;
 	}
-	if (value & MTL_DEBUG_TXPAUSED)
-		x->mac_tx_in_pause++;
 
-	value = readl(ioaddr + MTL_CHAN_RX_DEBUG(STMMAC_CHAN0));
+	for (queue = 0; queue < rx_queues; queue++) {
+		value = readl(ioaddr + MTL_CHAN_RX_DEBUG(queue));
 
-	if (value & MTL_DEBUG_RXFSTS_MASK) {
-		u32 rxfsts = (value & MTL_DEBUG_RXFSTS_MASK)
-			     >> MTL_DEBUG_RRCSTS_SHIFT;
+		if (value & MTL_DEBUG_RXFSTS_MASK) {
+			u32 rxfsts = (value & MTL_DEBUG_RXFSTS_MASK)
+				     >> MTL_DEBUG_RRCSTS_SHIFT;
 
-		if (rxfsts == MTL_DEBUG_RXFSTS_FULL)
-			x->mtl_rx_fifo_fill_level_full++;
-		else if (rxfsts == MTL_DEBUG_RXFSTS_AT)
-			x->mtl_rx_fifo_fill_above_thresh++;
-		else if (rxfsts == MTL_DEBUG_RXFSTS_BT)
-			x->mtl_rx_fifo_fill_below_thresh++;
-		else
-			x->mtl_rx_fifo_fill_level_empty++;
-	}
-	if (value & MTL_DEBUG_RRCSTS_MASK) {
-		u32 rrcsts = (value & MTL_DEBUG_RRCSTS_MASK) >>
-			     MTL_DEBUG_RRCSTS_SHIFT;
-
-		if (rrcsts == MTL_DEBUG_RRCSTS_FLUSH)
-			x->mtl_rx_fifo_read_ctrl_flush++;
-		else if (rrcsts == MTL_DEBUG_RRCSTS_RSTAT)
-			x->mtl_rx_fifo_read_ctrl_read_data++;
-		else if (rrcsts == MTL_DEBUG_RRCSTS_RDATA)
-			x->mtl_rx_fifo_read_ctrl_status++;
-		else
-			x->mtl_rx_fifo_read_ctrl_idle++;
+			if (rxfsts == MTL_DEBUG_RXFSTS_FULL)
+				x->mtl_rx_fifo_fill_level_full++;
+			else if (rxfsts == MTL_DEBUG_RXFSTS_AT)
+				x->mtl_rx_fifo_fill_above_thresh++;
+			else if (rxfsts == MTL_DEBUG_RXFSTS_BT)
+				x->mtl_rx_fifo_fill_below_thresh++;
+			else
+				x->mtl_rx_fifo_fill_level_empty++;
+		}
+		if (value & MTL_DEBUG_RRCSTS_MASK) {
+			u32 rrcsts = (value & MTL_DEBUG_RRCSTS_MASK) >>
+				     MTL_DEBUG_RRCSTS_SHIFT;
+
+			if (rrcsts == MTL_DEBUG_RRCSTS_FLUSH)
+				x->mtl_rx_fifo_read_ctrl_flush++;
+			else if (rrcsts == MTL_DEBUG_RRCSTS_RSTAT)
+				x->mtl_rx_fifo_read_ctrl_read_data++;
+			else if (rrcsts == MTL_DEBUG_RRCSTS_RDATA)
+				x->mtl_rx_fifo_read_ctrl_status++;
+			else
+				x->mtl_rx_fifo_read_ctrl_idle++;
+		}
+		if (value & MTL_DEBUG_RWCSTS)
+			x->mtl_rx_fifo_ctrl_active++;
 	}
-	if (value & MTL_DEBUG_RWCSTS)
-		x->mtl_rx_fifo_ctrl_active++;
 
 	/* GMAC debug */
 	value = readl(ioaddr + GMAC_DEBUG);
@@ -455,10 +669,51 @@ static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
 
 static const struct stmmac_ops dwmac4_ops = {
 	.core_init = dwmac4_core_init,
+	.set_mac = stmmac_set_mac,
 	.rx_ipc = dwmac4_rx_ipc_enable,
 	.rx_queue_enable = dwmac4_rx_queue_enable,
+	.rx_queue_prio = dwmac4_rx_queue_priority,
+	.tx_queue_prio = dwmac4_tx_queue_priority,
+	.rx_queue_routing = dwmac4_tx_queue_routing,
+	.prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms,
+	.prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms,
+	.set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight,
+	.map_mtl_to_dma = dwmac4_map_mtl_dma,
+	.config_cbs = dwmac4_config_cbs,
 	.dump_regs = dwmac4_dump_regs,
 	.host_irq_status = dwmac4_irq_status,
+	.host_mtl_irq_status = dwmac4_irq_mtl_status,
+	.flow_ctrl = dwmac4_flow_ctrl,
+	.pmt = dwmac4_pmt,
+	.set_umac_addr = dwmac4_set_umac_addr,
+	.get_umac_addr = dwmac4_get_umac_addr,
+	.set_eee_mode = dwmac4_set_eee_mode,
+	.reset_eee_mode = dwmac4_reset_eee_mode,
+	.set_eee_timer = dwmac4_set_eee_timer,
+	.set_eee_pls = dwmac4_set_eee_pls,
+	.pcs_ctrl_ane = dwmac4_ctrl_ane,
+	.pcs_rane = dwmac4_rane,
+	.pcs_get_adv_lp = dwmac4_get_adv_lp,
+	.debug = dwmac4_debug,
+	.set_filter = dwmac4_set_filter,
+};
+
+static const struct stmmac_ops dwmac410_ops = {
+	.core_init = dwmac4_core_init,
+	.set_mac = stmmac_dwmac4_set_mac,
+	.rx_ipc = dwmac4_rx_ipc_enable,
+	.rx_queue_enable = dwmac4_rx_queue_enable,
+	.rx_queue_prio = dwmac4_rx_queue_priority,
+	.tx_queue_prio = dwmac4_tx_queue_priority,
+	.rx_queue_routing = dwmac4_tx_queue_routing,
+	.prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms,
+	.prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms,
+	.set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight,
+	.map_mtl_to_dma = dwmac4_map_mtl_dma,
+	.config_cbs = dwmac4_config_cbs,
+	.dump_regs = dwmac4_dump_regs,
+	.host_irq_status = dwmac4_irq_status,
+	.host_mtl_irq_status = dwmac4_irq_mtl_status,
 	.flow_ctrl = dwmac4_flow_ctrl,
 	.pmt = dwmac4_pmt,
 	.set_umac_addr = dwmac4_set_umac_addr,
@@ -492,8 +747,6 @@ struct mac_device_info *dwmac4_setup(void __iomem *ioaddr, int mcbins,
 	if (mac->multicast_filter_bins)
 		mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
 
-	mac->mac = &dwmac4_ops;
-
 	mac->link.port = GMAC_CONFIG_PS;
 	mac->link.duplex = GMAC_CONFIG_DM;
 	mac->link.speed = GMAC_CONFIG_FES;
@@ -514,5 +767,10 @@ struct mac_device_info *dwmac4_setup(void __iomem *ioaddr, int mcbins,
 	else
 		mac->dma = &dwmac4_dma_ops;
 
+	if (*synopsys_id >= DWMAC_CORE_4_00)
+		mac->mac = &dwmac410_ops;
+	else
+		mac->mac = &dwmac4_ops;
+
 	return mac;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index f97b0d5d9987..eec8463057fd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -71,36 +71,48 @@ static void dwmac4_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi)
 	writel(value, ioaddr + DMA_SYS_BUS_MODE);
 }
 
-static void dwmac4_dma_init_channel(void __iomem *ioaddr,
-				    struct stmmac_dma_cfg *dma_cfg,
-				    u32 dma_tx_phy, u32 dma_rx_phy,
-				    u32 channel)
+void dwmac4_dma_init_rx_chan(void __iomem *ioaddr,
+			     struct stmmac_dma_cfg *dma_cfg,
+			     u32 dma_rx_phy, u32 chan)
 {
 	u32 value;
-	int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
-	int rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
+	u32 rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
 
-	/* set PBL for each channels. Currently we affect same configuration
-	 * on each channel
-	 */
-	value = readl(ioaddr + DMA_CHAN_CONTROL(channel));
-	if (dma_cfg->pblx8)
-		value = value | DMA_BUS_MODE_PBL;
-	writel(value, ioaddr + DMA_CHAN_CONTROL(channel));
+	value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
+	value = value | (rxpbl << DMA_BUS_MODE_RPBL_SHIFT);
+	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
+
+	writel(dma_rx_phy, ioaddr + DMA_CHAN_RX_BASE_ADDR(chan));
+}
 
-	value = readl(ioaddr + DMA_CHAN_TX_CONTROL(channel));
+void dwmac4_dma_init_tx_chan(void __iomem *ioaddr,
+			     struct stmmac_dma_cfg *dma_cfg,
+			     u32 dma_tx_phy, u32 chan)
+{
+	u32 value;
+	u32 txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
+
+	value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan));
 	value = value | (txpbl << DMA_BUS_MODE_PBL_SHIFT);
-	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(channel));
+	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
-	value = readl(ioaddr + DMA_CHAN_RX_CONTROL(channel));
-	value = value | (rxpbl << DMA_BUS_MODE_RPBL_SHIFT);
-	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(channel));
+	writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(chan));
+}
 
-	/* Mask interrupts by writing to CSR7 */
-	writel(DMA_CHAN_INTR_DEFAULT_MASK, ioaddr + DMA_CHAN_INTR_ENA(channel));
+void dwmac4_dma_init_channel(void __iomem *ioaddr,
+			     struct stmmac_dma_cfg *dma_cfg, u32 chan)
+{
+	u32 value;
+
+	/* common channel control register config */
+	value = readl(ioaddr + DMA_CHAN_CONTROL(chan));
+	if (dma_cfg->pblx8)
+		value = value | DMA_BUS_MODE_PBL;
+	writel(value, ioaddr + DMA_CHAN_CONTROL(chan));
 
-	writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(channel));
-	writel(dma_rx_phy, ioaddr + DMA_CHAN_RX_BASE_ADDR(channel));
+	/* Mask interrupts by writing to CSR7 */
+	writel(DMA_CHAN_INTR_DEFAULT_MASK,
+	       ioaddr + DMA_CHAN_INTR_ENA(chan));
 }
 
 static void dwmac4_dma_init(void __iomem *ioaddr,
@@ -108,7 +120,6 @@ static void dwmac4_dma_init(void __iomem *ioaddr,
 			    u32 dma_tx, u32 dma_rx, int atds)
 {
 	u32 value = readl(ioaddr + DMA_SYS_BUS_MODE);
-	int i;
 
 	/* Set the Fixed burst mode */
 	if (dma_cfg->fixed_burst)
@@ -122,9 +133,6 @@ static void dwmac4_dma_init(void __iomem *ioaddr,
 		value |= DMA_SYS_BUS_AAL;
 
 	writel(value, ioaddr + DMA_SYS_BUS_MODE);
-
-	for (i = 0; i < DMA_CHANNEL_NB_MAX; i++)
-		dwmac4_dma_init_channel(ioaddr, dma_cfg, dma_tx, dma_rx, i);
 }
 
 static void _dwmac4_dump_dma_regs(void __iomem *ioaddr, u32 channel,
@@ -174,46 +182,121 @@ static void dwmac4_dump_dma_regs(void __iomem *ioaddr, u32 *reg_space)
 		_dwmac4_dump_dma_regs(ioaddr, i, reg_space);
 }
 
-static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt)
+static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 number_chan)
 {
-	int i;
+	u32 chan;
 
-	for (i = 0; i < DMA_CHANNEL_NB_MAX; i++)
-		writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(i));
+	for (chan = 0; chan < number_chan; chan++)
+		writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(chan));
 }
 
-static void dwmac4_dma_chan_op_mode(void __iomem *ioaddr, int txmode,
-				    int rxmode, u32 channel)
+static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode,
+				       u32 channel, int fifosz)
 {
-	u32 mtl_tx_op, mtl_rx_op, mtl_rx_int;
+	unsigned int rqs = fifosz / 256 - 1;
+	u32 mtl_rx_op, mtl_rx_int;
 
-	/* Following code only done for channel 0, other channels not yet
-	 * supported.
-	 */
-	mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel));
+	mtl_rx_op = readl(ioaddr + MTL_CHAN_RX_OP_MODE(channel));
+
+	if (mode == SF_DMA_MODE) {
+		pr_debug("GMAC: enable RX store and forward mode\n");
+		mtl_rx_op |= MTL_OP_MODE_RSF;
+	} else {
+		pr_debug("GMAC: disable RX SF mode (threshold %d)\n", mode);
+		mtl_rx_op &= ~MTL_OP_MODE_RSF;
+		mtl_rx_op &= MTL_OP_MODE_RTC_MASK;
+		if (mode <= 32)
+			mtl_rx_op |= MTL_OP_MODE_RTC_32;
+		else if (mode <= 64)
+			mtl_rx_op |= MTL_OP_MODE_RTC_64;
+		else if (mode <= 96)
+			mtl_rx_op |= MTL_OP_MODE_RTC_96;
+		else
+			mtl_rx_op |= MTL_OP_MODE_RTC_128;
+	}
+
+	mtl_rx_op &= ~MTL_OP_MODE_RQS_MASK;
+	mtl_rx_op |= rqs << MTL_OP_MODE_RQS_SHIFT;
+
+	/* enable flow control only if each channel gets 4 KiB or more FIFO */
+	if (fifosz >= 4096) {
+		unsigned int rfd, rfa;
+
+		mtl_rx_op |= MTL_OP_MODE_EHFC;
+
+		/* Set Threshold for Activating Flow Control to min 2 frames,
+		 * i.e. 1500 * 2 = 3000 bytes.
+		 *
+		 * Set Threshold for Deactivating Flow Control to min 1 frame,
+		 * i.e. 1500 bytes.
+		 */
+		switch (fifosz) {
+		case 4096:
+			/* This violates the above formula because of FIFO size
+			 * limit therefore overflow may occur in spite of this.
+			 */
+			rfd = 0x03; /* Full-2.5K */
+			rfa = 0x01; /* Full-1.5K */
+			break;
+
+		case 8192:
+			rfd = 0x06; /* Full-4K */
+			rfa = 0x0a; /* Full-6K */
+			break;
+
+		case 16384:
+			rfd = 0x06; /* Full-4K */
+			rfa = 0x12; /* Full-10K */
+			break;
+
+		default:
+			rfd = 0x06; /* Full-4K */
+			rfa = 0x1e; /* Full-16K */
+			break;
+		}
+
+		mtl_rx_op &= ~MTL_OP_MODE_RFD_MASK;
+		mtl_rx_op |= rfd << MTL_OP_MODE_RFD_SHIFT;
 
-	if (txmode == SF_DMA_MODE) {
+		mtl_rx_op &= ~MTL_OP_MODE_RFA_MASK;
+		mtl_rx_op |= rfa << MTL_OP_MODE_RFA_SHIFT;
+	}
+
+	writel(mtl_rx_op, ioaddr + MTL_CHAN_RX_OP_MODE(channel));
+
+	/* Enable MTL RX overflow */
+	mtl_rx_int = readl(ioaddr + MTL_CHAN_INT_CTRL(channel));
+	writel(mtl_rx_int | MTL_RX_OVERFLOW_INT_EN,
+	       ioaddr + MTL_CHAN_INT_CTRL(channel));
+}
+
+static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode,
+				       u32 channel)
+{
+	u32 mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel));
+
+	if (mode == SF_DMA_MODE) {
 		pr_debug("GMAC: enable TX store and forward mode\n");
 		/* Transmit COE type 2 cannot be done in cut-through mode. */
 		mtl_tx_op |= MTL_OP_MODE_TSF;
 	} else {
-		pr_debug("GMAC: disabling TX SF (threshold %d)\n", txmode);
+		pr_debug("GMAC: disabling TX SF (threshold %d)\n", mode);
 		mtl_tx_op &= ~MTL_OP_MODE_TSF;
 		mtl_tx_op &= MTL_OP_MODE_TTC_MASK;
 		/* Set the transmit threshold */
-		if (txmode <= 32)
+		if (mode <= 32)
 			mtl_tx_op |= MTL_OP_MODE_TTC_32;
-		else if (txmode <= 64)
+		else if (mode <= 64)
 			mtl_tx_op |= MTL_OP_MODE_TTC_64;
-		else if (txmode <= 96)
+		else if (mode <= 96)
 			mtl_tx_op |= MTL_OP_MODE_TTC_96;
-		else if (txmode <= 128)
+		else if (mode <= 128)
 			mtl_tx_op |= MTL_OP_MODE_TTC_128;
-		else if (txmode <= 192)
+		else if (mode <= 192)
 			mtl_tx_op |= MTL_OP_MODE_TTC_192;
-		else if (txmode <= 256)
+		else if (mode <= 256)
 			mtl_tx_op |= MTL_OP_MODE_TTC_256;
-		else if (txmode <= 384)
+		else if (mode <= 384)
 			mtl_tx_op |= MTL_OP_MODE_TTC_384;
 		else
 			mtl_tx_op |= MTL_OP_MODE_TTC_512;
@@ -230,39 +313,6 @@ static void dwmac4_dma_chan_op_mode(void __iomem *ioaddr, int txmode,
 	 */
 	mtl_tx_op |= MTL_OP_MODE_TXQEN | MTL_OP_MODE_TQS_MASK;
 	writel(mtl_tx_op, ioaddr +  MTL_CHAN_TX_OP_MODE(channel));
-
-	mtl_rx_op = readl(ioaddr + MTL_CHAN_RX_OP_MODE(channel));
-
-	if (rxmode == SF_DMA_MODE) {
-		pr_debug("GMAC: enable RX store and forward mode\n");
-		mtl_rx_op |= MTL_OP_MODE_RSF;
-	} else {
-		pr_debug("GMAC: disable RX SF mode (threshold %d)\n", rxmode);
-		mtl_rx_op &= ~MTL_OP_MODE_RSF;
-		mtl_rx_op &= MTL_OP_MODE_RTC_MASK;
-		if (rxmode <= 32)
-			mtl_rx_op |= MTL_OP_MODE_RTC_32;
-		else if (rxmode <= 64)
-			mtl_rx_op |= MTL_OP_MODE_RTC_64;
-		else if (rxmode <= 96)
-			mtl_rx_op |= MTL_OP_MODE_RTC_96;
-		else
-			mtl_rx_op |= MTL_OP_MODE_RTC_128;
-	}
-
-	writel(mtl_rx_op, ioaddr + MTL_CHAN_RX_OP_MODE(channel));
-
-	/* Enable MTL RX overflow */
-	mtl_rx_int = readl(ioaddr + MTL_CHAN_INT_CTRL(channel));
-	writel(mtl_rx_int | MTL_RX_OVERFLOW_INT_EN,
-	       ioaddr + MTL_CHAN_INT_CTRL(channel));
-}
-
-static void dwmac4_dma_operation_mode(void __iomem *ioaddr, int txmode,
-				      int rxmode, int rxfifosz)
-{
-	/* Only Channel 0 is actually configured and used */
-	dwmac4_dma_chan_op_mode(ioaddr, txmode, rxmode, 0);
 }
 
 static void dwmac4_get_hw_feature(void __iomem *ioaddr,
@@ -294,6 +344,11 @@ static void dwmac4_get_hw_feature(void __iomem *ioaddr,
 	hw_cap = readl(ioaddr + GMAC_HW_FEATURE1);
 	dma_cap->av = (hw_cap & GMAC_HW_FEAT_AVSEL) >> 20;
 	dma_cap->tsoen = (hw_cap & GMAC_HW_TSOEN) >> 18;
+	/* RX and TX FIFO sizes are encoded as log2(n / 128). Undo that by
+	 * shifting and store the sizes in bytes.
+	 */
+	dma_cap->tx_fifo_size = 128 << ((hw_cap & GMAC_HW_TXFIFOSIZE) >> 6);
+	dma_cap->rx_fifo_size = 128 << ((hw_cap & GMAC_HW_RXFIFOSIZE) >> 0);
 	/* MAC HW feature2 */
 	hw_cap = readl(ioaddr + GMAC_HW_FEATURE2);
 	/* TX and RX number of channels */
@@ -332,9 +387,13 @@ static void dwmac4_enable_tso(void __iomem *ioaddr, bool en, u32 chan)
 const struct stmmac_dma_ops dwmac4_dma_ops = {
 	.reset = dwmac4_dma_reset,
 	.init = dwmac4_dma_init,
+	.init_chan = dwmac4_dma_init_channel,
+	.init_rx_chan = dwmac4_dma_init_rx_chan,
+	.init_tx_chan = dwmac4_dma_init_tx_chan,
 	.axi = dwmac4_dma_axi,
 	.dump_regs = dwmac4_dump_dma_regs,
-	.dma_mode = dwmac4_dma_operation_mode,
+	.dma_rx_mode = dwmac4_dma_rx_chan_op_mode,
+	.dma_tx_mode = dwmac4_dma_tx_chan_op_mode,
 	.enable_dma_irq = dwmac4_enable_dma_irq,
 	.disable_dma_irq = dwmac4_disable_dma_irq,
 	.start_tx = dwmac4_dma_start_tx,
@@ -354,9 +413,13 @@ const struct stmmac_dma_ops dwmac4_dma_ops = {
 const struct stmmac_dma_ops dwmac410_dma_ops = {
 	.reset = dwmac4_dma_reset,
 	.init = dwmac4_dma_init,
+	.init_chan = dwmac4_dma_init_channel,
+	.init_rx_chan = dwmac4_dma_init_rx_chan,
+	.init_tx_chan = dwmac4_dma_init_tx_chan,
 	.axi = dwmac4_dma_axi,
 	.dump_regs = dwmac4_dump_dma_regs,
-	.dma_mode = dwmac4_dma_operation_mode,
+	.dma_rx_mode = dwmac4_dma_rx_chan_op_mode,
+	.dma_tx_mode = dwmac4_dma_tx_chan_op_mode,
 	.enable_dma_irq = dwmac410_enable_dma_irq,
 	.disable_dma_irq = dwmac4_disable_dma_irq,
 	.start_tx = dwmac4_dma_start_tx,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
index 1b06df749e2b..8474bf961dd0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
@@ -185,17 +185,17 @@
 
 int dwmac4_dma_reset(void __iomem *ioaddr);
 void dwmac4_enable_dma_transmission(void __iomem *ioaddr, u32 tail_ptr);
-void dwmac4_enable_dma_irq(void __iomem *ioaddr);
-void dwmac410_enable_dma_irq(void __iomem *ioaddr);
-void dwmac4_disable_dma_irq(void __iomem *ioaddr);
-void dwmac4_dma_start_tx(void __iomem *ioaddr);
-void dwmac4_dma_stop_tx(void __iomem *ioaddr);
-void dwmac4_dma_start_rx(void __iomem *ioaddr);
-void dwmac4_dma_stop_rx(void __iomem *ioaddr);
+void dwmac4_enable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac410_enable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac4_dma_start_tx(void __iomem *ioaddr, u32 chan);
+void dwmac4_dma_stop_tx(void __iomem *ioaddr, u32 chan);
+void dwmac4_dma_start_rx(void __iomem *ioaddr, u32 chan);
+void dwmac4_dma_stop_rx(void __iomem *ioaddr, u32 chan);
 int dwmac4_dma_interrupt(void __iomem *ioaddr,
-			 struct stmmac_extra_stats *x);
-void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len);
-void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len);
+			 struct stmmac_extra_stats *x, u32 chan);
+void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len, u32 chan);
+void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len, u32 chan);
 void dwmac4_set_rx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 void dwmac4_set_tx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
index c7326d5b2f43..49f5687879df 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
@@ -37,96 +37,96 @@ int dwmac4_dma_reset(void __iomem *ioaddr)
 
 void dwmac4_set_rx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan)
 {
-	writel(tail_ptr, ioaddr + DMA_CHAN_RX_END_ADDR(0));
+	writel(tail_ptr, ioaddr + DMA_CHAN_RX_END_ADDR(chan));
 }
 
 void dwmac4_set_tx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan)
 {
-	writel(tail_ptr, ioaddr + DMA_CHAN_TX_END_ADDR(0));
+	writel(tail_ptr, ioaddr + DMA_CHAN_TX_END_ADDR(chan));
 }
 
-void dwmac4_dma_start_tx(void __iomem *ioaddr)
+void dwmac4_dma_start_tx(void __iomem *ioaddr, u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0));
+	u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
 	value |= DMA_CONTROL_ST;
-	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0));
+	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
 	value = readl(ioaddr + GMAC_CONFIG);
 	value |= GMAC_CONFIG_TE;
 	writel(value, ioaddr + GMAC_CONFIG);
 }
 
-void dwmac4_dma_stop_tx(void __iomem *ioaddr)
+void dwmac4_dma_stop_tx(void __iomem *ioaddr, u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0));
+	u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
 	value &= ~DMA_CONTROL_ST;
-	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0));
+	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
 	value = readl(ioaddr + GMAC_CONFIG);
 	value &= ~GMAC_CONFIG_TE;
 	writel(value, ioaddr + GMAC_CONFIG);
 }
 
-void dwmac4_dma_start_rx(void __iomem *ioaddr)
+void dwmac4_dma_start_rx(void __iomem *ioaddr, u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0));
+	u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
 
 	value |= DMA_CONTROL_SR;
 
-	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0));
+	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
 
 	value = readl(ioaddr + GMAC_CONFIG);
 	value |= GMAC_CONFIG_RE;
 	writel(value, ioaddr + GMAC_CONFIG);
 }
 
-void dwmac4_dma_stop_rx(void __iomem *ioaddr)
+void dwmac4_dma_stop_rx(void __iomem *ioaddr, u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0));
+	u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
 
 	value &= ~DMA_CONTROL_SR;
-	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0));
+	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
 
 	value = readl(ioaddr + GMAC_CONFIG);
 	value &= ~GMAC_CONFIG_RE;
 	writel(value, ioaddr + GMAC_CONFIG);
 }
 
-void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len)
+void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len, u32 chan)
 {
-	writel(len, ioaddr + DMA_CHAN_TX_RING_LEN(STMMAC_CHAN0));
+	writel(len, ioaddr + DMA_CHAN_TX_RING_LEN(chan));
 }
 
-void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len)
+void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len, u32 chan)
 {
-	writel(len, ioaddr + DMA_CHAN_RX_RING_LEN(STMMAC_CHAN0));
+	writel(len, ioaddr + DMA_CHAN_RX_RING_LEN(chan));
 }
 
-void dwmac4_enable_dma_irq(void __iomem *ioaddr)
+void dwmac4_enable_dma_irq(void __iomem *ioaddr, u32 chan)
 {
 	writel(DMA_CHAN_INTR_DEFAULT_MASK, ioaddr +
-	       DMA_CHAN_INTR_ENA(STMMAC_CHAN0));
+	       DMA_CHAN_INTR_ENA(chan));
 }
 
-void dwmac410_enable_dma_irq(void __iomem *ioaddr)
+void dwmac410_enable_dma_irq(void __iomem *ioaddr, u32 chan)
 {
 	writel(DMA_CHAN_INTR_DEFAULT_MASK_4_10,
-	       ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0));
+	       ioaddr + DMA_CHAN_INTR_ENA(chan));
 }
 
-void dwmac4_disable_dma_irq(void __iomem *ioaddr)
+void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan)
 {
-	writel(0, ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0));
+	writel(0, ioaddr + DMA_CHAN_INTR_ENA(chan));
 }
 
 int dwmac4_dma_interrupt(void __iomem *ioaddr,
-			 struct stmmac_extra_stats *x)
+			 struct stmmac_extra_stats *x, u32 chan)
 {
 	int ret = 0;
 
-	u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(0));
+	u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(chan));
 
 	/* ABNORMAL interrupts */
 	if (unlikely(intr_status & DMA_CHAN_STATUS_AIS)) {
@@ -153,7 +153,7 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr,
 		if (likely(intr_status & DMA_CHAN_STATUS_RI)) {
 			u32 value;
 
-			value = readl(ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0));
+			value = readl(ioaddr + DMA_CHAN_INTR_ENA(chan));
 			/* to schedule NAPI on real RIE event. */
 			if (likely(value & DMA_CHAN_INTR_ENA_RIE)) {
 				x->rx_normal_irq_n++;
@@ -172,7 +172,7 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr,
 	 * status [21-0] expect reserved bits [5-3]
 	 */
 	writel((intr_status & 0x3fffc7),
-	       ioaddr + DMA_CHAN_STATUS(STMMAC_CHAN0));
+	       ioaddr + DMA_CHAN_STATUS(chan));
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
index 56e485f79077..9091df86723a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
@@ -137,13 +137,14 @@
 #define DMA_CONTROL_FTF		0x00100000	/* Flush transmit FIFO */
 
 void dwmac_enable_dma_transmission(void __iomem *ioaddr);
-void dwmac_enable_dma_irq(void __iomem *ioaddr);
-void dwmac_disable_dma_irq(void __iomem *ioaddr);
-void dwmac_dma_start_tx(void __iomem *ioaddr);
-void dwmac_dma_stop_tx(void __iomem *ioaddr);
-void dwmac_dma_start_rx(void __iomem *ioaddr);
-void dwmac_dma_stop_rx(void __iomem *ioaddr);
-int dwmac_dma_interrupt(void __iomem *ioaddr, struct stmmac_extra_stats *x);
+void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac_disable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac_dma_start_tx(void __iomem *ioaddr, u32 chan);
+void dwmac_dma_stop_tx(void __iomem *ioaddr, u32 chan);
+void dwmac_dma_start_rx(void __iomem *ioaddr, u32 chan);
+void dwmac_dma_stop_rx(void __iomem *ioaddr, u32 chan);
+int dwmac_dma_interrupt(void __iomem *ioaddr, struct stmmac_extra_stats *x,
+			u32 chan);
 int dwmac_dma_reset(void __iomem *ioaddr);
 
 #endif /* __DWMAC_DMA_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
index e60bfca2a763..38f94305aab5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -47,38 +47,38 @@ void dwmac_enable_dma_transmission(void __iomem *ioaddr)
 	writel(1, ioaddr + DMA_XMT_POLL_DEMAND);
 }
 
-void dwmac_enable_dma_irq(void __iomem *ioaddr)
+void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan)
 {
 	writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_INTR_ENA);
 }
 
-void dwmac_disable_dma_irq(void __iomem *ioaddr)
+void dwmac_disable_dma_irq(void __iomem *ioaddr, u32 chan)
 {
 	writel(0, ioaddr + DMA_INTR_ENA);
 }
 
-void dwmac_dma_start_tx(void __iomem *ioaddr)
+void dwmac_dma_start_tx(void __iomem *ioaddr, u32 chan)
 {
 	u32 value = readl(ioaddr + DMA_CONTROL);
 	value |= DMA_CONTROL_ST;
 	writel(value, ioaddr + DMA_CONTROL);
 }
 
-void dwmac_dma_stop_tx(void __iomem *ioaddr)
+void dwmac_dma_stop_tx(void __iomem *ioaddr, u32 chan)
 {
 	u32 value = readl(ioaddr + DMA_CONTROL);
 	value &= ~DMA_CONTROL_ST;
 	writel(value, ioaddr + DMA_CONTROL);
 }
 
-void dwmac_dma_start_rx(void __iomem *ioaddr)
+void dwmac_dma_start_rx(void __iomem *ioaddr, u32 chan)
 {
 	u32 value = readl(ioaddr + DMA_CONTROL);
 	value |= DMA_CONTROL_SR;
 	writel(value, ioaddr + DMA_CONTROL);
 }
 
-void dwmac_dma_stop_rx(void __iomem *ioaddr)
+void dwmac_dma_stop_rx(void __iomem *ioaddr, u32 chan)
 {
 	u32 value = readl(ioaddr + DMA_CONTROL);
 	value &= ~DMA_CONTROL_SR;
@@ -156,7 +156,7 @@ static void show_rx_process_state(unsigned int status)
 #endif
 
 int dwmac_dma_interrupt(void __iomem *ioaddr,
-			struct stmmac_extra_stats *x)
+			struct stmmac_extra_stats *x, u32 chan)
 {
 	int ret = 0;
 	/* read the status register (CSR5) */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 85d64114e159..16808e48ca1c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -481,6 +481,7 @@ stmmac_set_pauseparam(struct net_device *netdev,
 		      struct ethtool_pauseparam *pause)
 {
 	struct stmmac_priv *priv = netdev_priv(netdev);
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
 	struct phy_device *phy = netdev->phydev;
 	int new_pause = FLOW_OFF;
 
@@ -511,7 +512,7 @@ stmmac_set_pauseparam(struct net_device *netdev,
 	}
 
 	priv->hw->mac->flow_ctrl(priv->hw, phy->duplex, priv->flow_ctrl,
-				 priv->pause);
+				 priv->pause, tx_cnt);
 	return 0;
 }
 
@@ -519,6 +520,8 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
 				 struct ethtool_stats *dummy, u64 *data)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
 	int i, j = 0;
 
 	/* Update the DMA HW counters for dwmac10/100 */
@@ -549,7 +552,8 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
 		if ((priv->hw->mac->debug) &&
 		    (priv->synopsys_id >= DWMAC_CORE_3_50))
 			priv->hw->mac->debug(priv->ioaddr,
-					     (void *)&priv->xstats);
+					     (void *)&priv->xstats,
+					     rx_queues_count, tx_queues_count);
 	}
 	for (i = 0; i < STMMAC_STATS_LEN; i++) {
 		char *p = (char *)priv + stmmac_gstrings_stats[i].stat_offset;
@@ -726,6 +730,7 @@ static int stmmac_set_coalesce(struct net_device *dev,
 			       struct ethtool_coalesce *ec)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
 	unsigned int rx_riwt;
 
 	/* Check not supported parameters  */
@@ -764,7 +769,7 @@ static int stmmac_set_coalesce(struct net_device *dev,
 	priv->tx_coal_frames = ec->tx_max_coalesced_frames;
 	priv->tx_coal_timer = ec->tx_coalesce_usecs;
 	priv->rx_riwt = rx_riwt;
-	priv->hw->dma->rx_watchdog(priv->ioaddr, priv->rx_riwt);
+	priv->hw->dma->rx_watchdog(priv->ioaddr, priv->rx_riwt, rx_cnt);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 4498a3861aa3..7cbda41dc996 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -673,6 +673,19 @@ static void stmmac_release_ptp(struct stmmac_priv *priv)
 }
 
 /**
+ *  stmmac_mac_flow_ctrl - Configure flow control in all queues
+ *  @priv: driver private structure
+ *  Description: It is used for configuring the flow control in all queues
+ */
+static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex)
+{
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+
+	priv->hw->mac->flow_ctrl(priv->hw, duplex, priv->flow_ctrl,
+				 priv->pause, tx_cnt);
+}
+
+/**
  * stmmac_adjust_link - adjusts the link parameters
  * @dev: net device structure
  * Description: this is the helper called by the physical abstraction layer
@@ -687,7 +700,6 @@ static void stmmac_adjust_link(struct net_device *dev)
 	struct phy_device *phydev = dev->phydev;
 	unsigned long flags;
 	int new_state = 0;
-	unsigned int fc = priv->flow_ctrl, pause_time = priv->pause;
 
 	if (!phydev)
 		return;
@@ -709,8 +721,7 @@ static void stmmac_adjust_link(struct net_device *dev)
 		}
 		/* Flow Control operation */
 		if (phydev->pause)
-			priv->hw->mac->flow_ctrl(priv->hw, phydev->duplex,
-						 fc, pause_time);
+			stmmac_mac_flow_ctrl(priv, phydev->duplex);
 
 		if (phydev->speed != priv->speed) {
 			new_state = 1;
@@ -1256,19 +1267,104 @@ static void free_dma_desc_resources(struct stmmac_priv *priv)
  */
 static void stmmac_mac_enable_rx_queues(struct stmmac_priv *priv)
 {
-	int rx_count = priv->dma_cap.number_rx_queues;
-	int queue = 0;
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	int queue;
+	u8 mode;
 
-	/* If GMAC does not have multiple queues, then this is not necessary*/
-	if (rx_count == 1)
-		return;
+	for (queue = 0; queue < rx_queues_count; queue++) {
+		mode = priv->plat->rx_queues_cfg[queue].mode_to_use;
+		priv->hw->mac->rx_queue_enable(priv->hw, mode, queue);
+	}
+}
 
-	/**
-	 *  If the core is synthesized with multiple rx queues / multiple
-	 *  dma channels, then rx queues will be disabled by default.
-	 *  For now only rx queue 0 is enabled.
-	 */
-	priv->hw->mac->rx_queue_enable(priv->hw, queue);
+/**
+ * stmmac_start_rx_dma - start RX DMA channel
+ * @priv: driver private structure
+ * @chan: RX channel index
+ * Description:
+ * This starts a RX DMA channel
+ */
+static void stmmac_start_rx_dma(struct stmmac_priv *priv, u32 chan)
+{
+	netdev_dbg(priv->dev, "DMA RX processes started in channel %d\n", chan);
+	priv->hw->dma->start_rx(priv->ioaddr, chan);
+}
+
+/**
+ * stmmac_start_tx_dma - start TX DMA channel
+ * @priv: driver private structure
+ * @chan: TX channel index
+ * Description:
+ * This starts a TX DMA channel
+ */
+static void stmmac_start_tx_dma(struct stmmac_priv *priv, u32 chan)
+{
+	netdev_dbg(priv->dev, "DMA TX processes started in channel %d\n", chan);
+	priv->hw->dma->start_tx(priv->ioaddr, chan);
+}
+
+/**
+ * stmmac_stop_rx_dma - stop RX DMA channel
+ * @priv: driver private structure
+ * @chan: RX channel index
+ * Description:
+ * This stops a RX DMA channel
+ */
+static void stmmac_stop_rx_dma(struct stmmac_priv *priv, u32 chan)
+{
+	netdev_dbg(priv->dev, "DMA RX processes stopped in channel %d\n", chan);
+	priv->hw->dma->stop_rx(priv->ioaddr, chan);
+}
+
+/**
+ * stmmac_stop_tx_dma - stop TX DMA channel
+ * @priv: driver private structure
+ * @chan: TX channel index
+ * Description:
+ * This stops a TX DMA channel
+ */
+static void stmmac_stop_tx_dma(struct stmmac_priv *priv, u32 chan)
+{
+	netdev_dbg(priv->dev, "DMA TX processes stopped in channel %d\n", chan);
+	priv->hw->dma->stop_tx(priv->ioaddr, chan);
+}
+
+/**
+ * stmmac_start_all_dma - start all RX and TX DMA channels
+ * @priv: driver private structure
+ * Description:
+ * This starts all the RX and TX DMA channels
+ */
+static void stmmac_start_all_dma(struct stmmac_priv *priv)
+{
+	u32 rx_channels_count = priv->plat->rx_queues_to_use;
+	u32 tx_channels_count = priv->plat->tx_queues_to_use;
+	u32 chan = 0;
+
+	for (chan = 0; chan < rx_channels_count; chan++)
+		stmmac_start_rx_dma(priv, chan);
+
+	for (chan = 0; chan < tx_channels_count; chan++)
+		stmmac_start_tx_dma(priv, chan);
+}
+
+/**
+ * stmmac_stop_all_dma - stop all RX and TX DMA channels
+ * @priv: driver private structure
+ * Description:
+ * This stops the RX and TX DMA channels
+ */
+static void stmmac_stop_all_dma(struct stmmac_priv *priv)
+{
+	u32 rx_channels_count = priv->plat->rx_queues_to_use;
+	u32 tx_channels_count = priv->plat->tx_queues_to_use;
+	u32 chan = 0;
+
+	for (chan = 0; chan < rx_channels_count; chan++)
+		stmmac_stop_rx_dma(priv, chan);
+
+	for (chan = 0; chan < tx_channels_count; chan++)
+		stmmac_stop_tx_dma(priv, chan);
 }
 
 /**
@@ -1279,11 +1375,20 @@ static void stmmac_mac_enable_rx_queues(struct stmmac_priv *priv)
  */
 static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
 {
+	u32 rx_channels_count = priv->plat->rx_queues_to_use;
+	u32 tx_channels_count = priv->plat->tx_queues_to_use;
 	int rxfifosz = priv->plat->rx_fifo_size;
+	u32 txmode = 0;
+	u32 rxmode = 0;
+	u32 chan = 0;
+
+	if (rxfifosz == 0)
+		rxfifosz = priv->dma_cap.rx_fifo_size;
 
-	if (priv->plat->force_thresh_dma_mode)
-		priv->hw->dma->dma_mode(priv->ioaddr, tc, tc, rxfifosz);
-	else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) {
+	if (priv->plat->force_thresh_dma_mode) {
+		txmode = tc;
+		rxmode = tc;
+	} else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) {
 		/*
 		 * In case of GMAC, SF mode can be enabled
 		 * to perform the TX COE in HW. This depends on:
@@ -1291,12 +1396,26 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
 		 * 2) There is no bugged Jumbo frame support
 		 *    that needs to not insert csum in the TDES.
 		 */
-		priv->hw->dma->dma_mode(priv->ioaddr, SF_DMA_MODE, SF_DMA_MODE,
-					rxfifosz);
+		txmode = SF_DMA_MODE;
+		rxmode = SF_DMA_MODE;
 		priv->xstats.threshold = SF_DMA_MODE;
-	} else
-		priv->hw->dma->dma_mode(priv->ioaddr, tc, SF_DMA_MODE,
+	} else {
+		txmode = tc;
+		rxmode = SF_DMA_MODE;
+	}
+
+	/* configure all channels */
+	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+		for (chan = 0; chan < rx_channels_count; chan++)
+			priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan,
+						   rxfifosz);
+
+		for (chan = 0; chan < tx_channels_count; chan++)
+			priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan);
+	} else {
+		priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode,
 					rxfifosz);
+	}
 }
 
 /**
@@ -1393,28 +1512,29 @@ static void stmmac_tx_clean(struct stmmac_priv *priv)
 	netif_tx_unlock(priv->dev);
 }
 
-static inline void stmmac_enable_dma_irq(struct stmmac_priv *priv)
+static inline void stmmac_enable_dma_irq(struct stmmac_priv *priv, u32 chan)
 {
-	priv->hw->dma->enable_dma_irq(priv->ioaddr);
+	priv->hw->dma->enable_dma_irq(priv->ioaddr, chan);
 }
 
-static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv)
+static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv, u32 chan)
 {
-	priv->hw->dma->disable_dma_irq(priv->ioaddr);
+	priv->hw->dma->disable_dma_irq(priv->ioaddr, chan);
 }
 
 /**
  * stmmac_tx_err - to manage the tx error
  * @priv: driver private structure
+ * @chan: channel index
  * Description: it cleans the descriptors and restarts the transmission
  * in case of transmission errors.
  */
-static void stmmac_tx_err(struct stmmac_priv *priv)
+static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan)
 {
 	int i;
 	netif_stop_queue(priv->dev);
 
-	priv->hw->dma->stop_tx(priv->ioaddr);
+	stmmac_stop_tx_dma(priv, chan);
 	dma_free_tx_skbufs(priv);
 	for (i = 0; i < DMA_TX_SIZE; i++)
 		if (priv->extend_desc)
@@ -1428,13 +1548,41 @@ static void stmmac_tx_err(struct stmmac_priv *priv)
 	priv->dirty_tx = 0;
 	priv->cur_tx = 0;
 	netdev_reset_queue(priv->dev);
-	priv->hw->dma->start_tx(priv->ioaddr);
+	stmmac_start_tx_dma(priv, chan);
 
 	priv->dev->stats.tx_errors++;
 	netif_wake_queue(priv->dev);
 }
 
 /**
+ *  stmmac_set_dma_operation_mode - Set DMA operation mode by channel
+ *  @priv: driver private structure
+ *  @txmode: TX operating mode
+ *  @rxmode: RX operating mode
+ *  @chan: channel index
+ *  Description: it is used for configuring of the DMA operation mode in
+ *  runtime in order to program the tx/rx DMA thresholds or Store-And-Forward
+ *  mode.
+ */
+static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode,
+					  u32 rxmode, u32 chan)
+{
+	int rxfifosz = priv->plat->rx_fifo_size;
+
+	if (rxfifosz == 0)
+		rxfifosz = priv->dma_cap.rx_fifo_size;
+
+	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+		priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan,
+					   rxfifosz);
+		priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan);
+	} else {
+		priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode,
+					rxfifosz);
+	}
+}
+
+/**
  * stmmac_dma_interrupt - DMA ISR
  * @priv: driver private structure
  * Description: this is the DMA ISR. It is called by the main ISR.
@@ -1443,31 +1591,41 @@ static void stmmac_tx_err(struct stmmac_priv *priv)
  */
 static void stmmac_dma_interrupt(struct stmmac_priv *priv)
 {
+	u32 tx_channel_count = priv->plat->tx_queues_to_use;
 	int status;
-	int rxfifosz = priv->plat->rx_fifo_size;
+	u32 chan;
+
+	for (chan = 0; chan < tx_channel_count; chan++) {
+		status = priv->hw->dma->dma_interrupt(priv->ioaddr,
+						      &priv->xstats, chan);
+		if (likely((status & handle_rx)) || (status & handle_tx)) {
+			if (likely(napi_schedule_prep(&priv->napi))) {
+				stmmac_disable_dma_irq(priv, chan);
+				__napi_schedule(&priv->napi);
+			}
+		}
 
-	status = priv->hw->dma->dma_interrupt(priv->ioaddr, &priv->xstats);
-	if (likely((status & handle_rx)) || (status & handle_tx)) {
-		if (likely(napi_schedule_prep(&priv->napi))) {
-			stmmac_disable_dma_irq(priv);
-			__napi_schedule(&priv->napi);
+		if (unlikely(status & tx_hard_error_bump_tc)) {
+			/* Try to bump up the dma threshold on this failure */
+			if (unlikely(priv->xstats.threshold != SF_DMA_MODE) &&
+			    (tc <= 256)) {
+				tc += 64;
+				if (priv->plat->force_thresh_dma_mode)
+					stmmac_set_dma_operation_mode(priv,
+								      tc,
+								      tc,
+								      chan);
+				else
+					stmmac_set_dma_operation_mode(priv,
+								    tc,
+								    SF_DMA_MODE,
+								    chan);
+				priv->xstats.threshold = tc;
+			}
+		} else if (unlikely(status == tx_hard_error)) {
+			stmmac_tx_err(priv, chan);
 		}
 	}
-	if (unlikely(status & tx_hard_error_bump_tc)) {
-		/* Try to bump up the dma threshold on this failure */
-		if (unlikely(priv->xstats.threshold != SF_DMA_MODE) &&
-		    (tc <= 256)) {
-			tc += 64;
-			if (priv->plat->force_thresh_dma_mode)
-				priv->hw->dma->dma_mode(priv->ioaddr, tc, tc,
-							rxfifosz);
-			else
-				priv->hw->dma->dma_mode(priv->ioaddr, tc,
-							SF_DMA_MODE, rxfifosz);
-			priv->xstats.threshold = tc;
-		}
-	} else if (unlikely(status == tx_hard_error))
-		stmmac_tx_err(priv);
 }
 
 /**
@@ -1574,6 +1732,11 @@ static void stmmac_check_ether_addr(struct stmmac_priv *priv)
  */
 static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 {
+	u32 rx_channels_count = priv->plat->rx_queues_to_use;
+	u32 tx_channels_count = priv->plat->tx_queues_to_use;
+	u32 dummy_dma_rx_phy = 0;
+	u32 dummy_dma_tx_phy = 0;
+	u32 chan = 0;
 	int atds = 0;
 	int ret = 0;
 
@@ -1591,19 +1754,43 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 		return ret;
 	}
 
-	priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg,
-			    priv->dma_tx_phy, priv->dma_rx_phy, atds);
-
 	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
-		priv->rx_tail_addr = priv->dma_rx_phy +
-			    (DMA_RX_SIZE * sizeof(struct dma_desc));
-		priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, priv->rx_tail_addr,
-					       STMMAC_CHAN0);
+		/* DMA Configuration */
+		priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg,
+				    dummy_dma_tx_phy, dummy_dma_rx_phy, atds);
+
+		/* DMA RX Channel Configuration */
+		for (chan = 0; chan < rx_channels_count; chan++) {
+			priv->hw->dma->init_rx_chan(priv->ioaddr,
+						    priv->plat->dma_cfg,
+						    priv->dma_rx_phy, chan);
+
+			priv->rx_tail_addr = priv->dma_rx_phy +
+				    (DMA_RX_SIZE * sizeof(struct dma_desc));
+			priv->hw->dma->set_rx_tail_ptr(priv->ioaddr,
+						       priv->rx_tail_addr,
+						       chan);
+		}
 
-		priv->tx_tail_addr = priv->dma_tx_phy +
-			    (DMA_TX_SIZE * sizeof(struct dma_desc));
-		priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, priv->tx_tail_addr,
-					       STMMAC_CHAN0);
+		/* DMA TX Channel Configuration */
+		for (chan = 0; chan < tx_channels_count; chan++) {
+			priv->hw->dma->init_chan(priv->ioaddr,
+							priv->plat->dma_cfg,
+							chan);
+
+			priv->hw->dma->init_tx_chan(priv->ioaddr,
+						    priv->plat->dma_cfg,
+						    priv->dma_tx_phy, chan);
+
+			priv->tx_tail_addr = priv->dma_tx_phy +
+				    (DMA_TX_SIZE * sizeof(struct dma_desc));
+			priv->hw->dma->set_tx_tail_ptr(priv->ioaddr,
+						       priv->tx_tail_addr,
+						       chan);
+		}
+	} else {
+		priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg,
+				    priv->dma_tx_phy, priv->dma_rx_phy, atds);
 	}
 
 	if (priv->plat->axi && priv->hw->dma->axi)
@@ -1644,6 +1831,196 @@ static void stmmac_init_tx_coalesce(struct stmmac_priv *priv)
 	add_timer(&priv->txtimer);
 }
 
+static void stmmac_set_rings_length(struct stmmac_priv *priv)
+{
+	u32 rx_channels_count = priv->plat->rx_queues_to_use;
+	u32 tx_channels_count = priv->plat->tx_queues_to_use;
+	u32 chan;
+
+	/* set TX ring length */
+	if (priv->hw->dma->set_tx_ring_len) {
+		for (chan = 0; chan < tx_channels_count; chan++)
+			priv->hw->dma->set_tx_ring_len(priv->ioaddr,
+						       (DMA_TX_SIZE - 1), chan);
+	}
+
+	/* set RX ring length */
+	if (priv->hw->dma->set_rx_ring_len) {
+		for (chan = 0; chan < rx_channels_count; chan++)
+			priv->hw->dma->set_rx_ring_len(priv->ioaddr,
+						       (DMA_RX_SIZE - 1), chan);
+	}
+}
+
+/**
+ *  stmmac_set_tx_queue_weight - Set TX queue weight
+ *  @priv: driver private structure
+ *  Description: It is used for setting TX queues weight
+ */
+static void stmmac_set_tx_queue_weight(struct stmmac_priv *priv)
+{
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+	u32 weight;
+	u32 queue;
+
+	for (queue = 0; queue < tx_queues_count; queue++) {
+		weight = priv->plat->tx_queues_cfg[queue].weight;
+		priv->hw->mac->set_mtl_tx_queue_weight(priv->hw, weight, queue);
+	}
+}
+
+/**
+ *  stmmac_configure_cbs - Configure CBS in TX queue
+ *  @priv: driver private structure
+ *  Description: It is used for configuring CBS in AVB TX queues
+ */
+static void stmmac_configure_cbs(struct stmmac_priv *priv)
+{
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+	u32 mode_to_use;
+	u32 queue;
+
+	/* queue 0 is reserved for legacy traffic */
+	for (queue = 1; queue < tx_queues_count; queue++) {
+		mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use;
+		if (mode_to_use == MTL_QUEUE_DCB)
+			continue;
+
+		priv->hw->mac->config_cbs(priv->hw,
+				priv->plat->tx_queues_cfg[queue].send_slope,
+				priv->plat->tx_queues_cfg[queue].idle_slope,
+				priv->plat->tx_queues_cfg[queue].high_credit,
+				priv->plat->tx_queues_cfg[queue].low_credit,
+				queue);
+	}
+}
+
+/**
+ *  stmmac_rx_queue_dma_chan_map - Map RX queue to RX dma channel
+ *  @priv: driver private structure
+ *  Description: It is used for mapping RX queues to RX dma channels
+ */
+static void stmmac_rx_queue_dma_chan_map(struct stmmac_priv *priv)
+{
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	u32 queue;
+	u32 chan;
+
+	for (queue = 0; queue < rx_queues_count; queue++) {
+		chan = priv->plat->rx_queues_cfg[queue].chan;
+		priv->hw->mac->map_mtl_to_dma(priv->hw, queue, chan);
+	}
+}
+
+/**
+ *  stmmac_mac_config_rx_queues_prio - Configure RX Queue priority
+ *  @priv: driver private structure
+ *  Description: It is used for configuring the RX Queue Priority
+ */
+static void stmmac_mac_config_rx_queues_prio(struct stmmac_priv *priv)
+{
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	u32 queue;
+	u32 prio;
+
+	for (queue = 0; queue < rx_queues_count; queue++) {
+		if (!priv->plat->rx_queues_cfg[queue].use_prio)
+			continue;
+
+		prio = priv->plat->rx_queues_cfg[queue].prio;
+		priv->hw->mac->rx_queue_prio(priv->hw, prio, queue);
+	}
+}
+
+/**
+ *  stmmac_mac_config_tx_queues_prio - Configure TX Queue priority
+ *  @priv: driver private structure
+ *  Description: It is used for configuring the TX Queue Priority
+ */
+static void stmmac_mac_config_tx_queues_prio(struct stmmac_priv *priv)
+{
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+	u32 queue;
+	u32 prio;
+
+	for (queue = 0; queue < tx_queues_count; queue++) {
+		if (!priv->plat->tx_queues_cfg[queue].use_prio)
+			continue;
+
+		prio = priv->plat->tx_queues_cfg[queue].prio;
+		priv->hw->mac->tx_queue_prio(priv->hw, prio, queue);
+	}
+}
+
+/**
+ *  stmmac_mac_config_rx_queues_routing - Configure RX Queue Routing
+ *  @priv: driver private structure
+ *  Description: It is used for configuring the RX queue routing
+ */
+static void stmmac_mac_config_rx_queues_routing(struct stmmac_priv *priv)
+{
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	u32 queue;
+	u8 packet;
+
+	for (queue = 0; queue < rx_queues_count; queue++) {
+		/* no specific packet type routing specified for the queue */
+		if (priv->plat->rx_queues_cfg[queue].pkt_route == 0x0)
+			continue;
+
+		packet = priv->plat->rx_queues_cfg[queue].pkt_route;
+		priv->hw->mac->rx_queue_prio(priv->hw, packet, queue);
+	}
+}
+
+/**
+ *  stmmac_mtl_configuration - Configure MTL
+ *  @priv: driver private structure
+ *  Description: It is used for configurring MTL
+ */
+static void stmmac_mtl_configuration(struct stmmac_priv *priv)
+{
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+
+	if (tx_queues_count > 1 && priv->hw->mac->set_mtl_tx_queue_weight)
+		stmmac_set_tx_queue_weight(priv);
+
+	/* Configure MTL RX algorithms */
+	if (rx_queues_count > 1 && priv->hw->mac->prog_mtl_rx_algorithms)
+		priv->hw->mac->prog_mtl_rx_algorithms(priv->hw,
+						priv->plat->rx_sched_algorithm);
+
+	/* Configure MTL TX algorithms */
+	if (tx_queues_count > 1 && priv->hw->mac->prog_mtl_tx_algorithms)
+		priv->hw->mac->prog_mtl_tx_algorithms(priv->hw,
+						priv->plat->tx_sched_algorithm);
+
+	/* Configure CBS in AVB TX queues */
+	if (tx_queues_count > 1 && priv->hw->mac->config_cbs)
+		stmmac_configure_cbs(priv);
+
+	/* Map RX MTL to DMA channels */
+	if (priv->hw->mac->map_mtl_to_dma)
+		stmmac_rx_queue_dma_chan_map(priv);
+
+	/* Enable MAC RX Queues */
+	if (priv->hw->mac->rx_queue_enable)
+		stmmac_mac_enable_rx_queues(priv);
+
+	/* Set RX priorities */
+	if (rx_queues_count > 1 && priv->hw->mac->rx_queue_prio)
+		stmmac_mac_config_rx_queues_prio(priv);
+
+	/* Set TX priorities */
+	if (tx_queues_count > 1 && priv->hw->mac->tx_queue_prio)
+		stmmac_mac_config_tx_queues_prio(priv);
+
+	/* Set RX routing */
+	if (rx_queues_count > 1 && priv->hw->mac->rx_queue_routing)
+		stmmac_mac_config_rx_queues_routing(priv);
+}
+
 /**
  * stmmac_hw_setup - setup mac in a usable state.
  *  @dev : pointer to the device structure.
@@ -1659,6 +2036,9 @@ static void stmmac_init_tx_coalesce(struct stmmac_priv *priv)
 static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	u32 chan;
 	int ret;
 
 	/* DMA initialization and SW reset */
@@ -1688,9 +2068,9 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 	/* Initialize the MAC Core */
 	priv->hw->mac->core_init(priv->hw, dev->mtu);
 
-	/* Initialize MAC RX Queues */
-	if (priv->hw->mac->rx_queue_enable)
-		stmmac_mac_enable_rx_queues(priv);
+	/* Initialize MTL*/
+	if (priv->synopsys_id >= DWMAC_CORE_4_00)
+		stmmac_mtl_configuration(priv);
 
 	ret = priv->hw->mac->rx_ipc(priv->hw);
 	if (!ret) {
@@ -1700,10 +2080,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 	}
 
 	/* Enable the MAC Rx/Tx */
-	if (priv->synopsys_id >= DWMAC_CORE_4_00)
-		stmmac_dwmac4_set_mac(priv->ioaddr, true);
-	else
-		stmmac_set_mac(priv->ioaddr, true);
+	priv->hw->mac->set_mac(priv->ioaddr, true);
 
 	/* Set the HW DMA mode and the COE */
 	stmmac_dma_operation_mode(priv);
@@ -1711,6 +2088,10 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 	stmmac_mmc_setup(priv);
 
 	if (init_ptp) {
+		ret = clk_prepare_enable(priv->plat->clk_ptp_ref);
+		if (ret < 0)
+			netdev_warn(priv->dev, "failed to enable PTP reference clock: %d\n", ret);
+
 		ret = stmmac_init_ptp(priv);
 		if (ret == -EOPNOTSUPP)
 			netdev_warn(priv->dev, "PTP not supported by HW\n");
@@ -1725,35 +2106,37 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 			    __func__);
 #endif
 	/* Start the ball rolling... */
-	netdev_dbg(priv->dev, "DMA RX/TX processes started...\n");
-	priv->hw->dma->start_tx(priv->ioaddr);
-	priv->hw->dma->start_rx(priv->ioaddr);
+	stmmac_start_all_dma(priv);
 
 	priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS;
 
 	if ((priv->use_riwt) && (priv->hw->dma->rx_watchdog)) {
 		priv->rx_riwt = MAX_DMA_RIWT;
-		priv->hw->dma->rx_watchdog(priv->ioaddr, MAX_DMA_RIWT);
+		priv->hw->dma->rx_watchdog(priv->ioaddr, MAX_DMA_RIWT, rx_cnt);
 	}
 
 	if (priv->hw->pcs && priv->hw->mac->pcs_ctrl_ane)
 		priv->hw->mac->pcs_ctrl_ane(priv->hw, 1, priv->hw->ps, 0);
 
-	/*  set TX ring length */
-	if (priv->hw->dma->set_tx_ring_len)
-		priv->hw->dma->set_tx_ring_len(priv->ioaddr,
-					       (DMA_TX_SIZE - 1));
-	/*  set RX ring length */
-	if (priv->hw->dma->set_rx_ring_len)
-		priv->hw->dma->set_rx_ring_len(priv->ioaddr,
-					       (DMA_RX_SIZE - 1));
+	/* set TX and RX rings length */
+	stmmac_set_rings_length(priv);
+
 	/* Enable TSO */
-	if (priv->tso)
-		priv->hw->dma->enable_tso(priv->ioaddr, 1, STMMAC_CHAN0);
+	if (priv->tso) {
+		for (chan = 0; chan < tx_cnt; chan++)
+			priv->hw->dma->enable_tso(priv->ioaddr, 1, chan);
+	}
 
 	return 0;
 }
 
+static void stmmac_hw_teardown(struct net_device *dev)
+{
+	struct stmmac_priv *priv = netdev_priv(dev);
+
+	clk_disable_unprepare(priv->plat->clk_ptp_ref);
+}
+
 /**
  *  stmmac_open - open entry point of the driver
  *  @dev : pointer to the device structure.
@@ -1821,7 +2204,7 @@ static int stmmac_open(struct net_device *dev)
 		netdev_err(priv->dev,
 			   "%s: ERROR: allocating the IRQ %d (error: %d)\n",
 			   __func__, dev->irq, ret);
-		goto init_error;
+		goto irq_error;
 	}
 
 	/* Request the Wake IRQ in case of another line is used for WoL */
@@ -1858,7 +2241,12 @@ lpiirq_error:
 		free_irq(priv->wol_irq, dev);
 wolirq_error:
 	free_irq(dev->irq, dev);
+irq_error:
+	if (dev->phydev)
+		phy_stop(dev->phydev);
 
+	del_timer_sync(&priv->txtimer);
+	stmmac_hw_teardown(dev);
 init_error:
 	free_dma_desc_resources(priv);
 dma_desc_error:
@@ -1901,14 +2289,13 @@ static int stmmac_release(struct net_device *dev)
 		free_irq(priv->lpi_irq, dev);
 
 	/* Stop TX/RX DMA and clear the descriptors */
-	priv->hw->dma->stop_tx(priv->ioaddr);
-	priv->hw->dma->stop_rx(priv->ioaddr);
+	stmmac_stop_all_dma(priv);
 
 	/* Release and free the Rx/Tx resources */
 	free_dma_desc_resources(priv);
 
 	/* Disable the MAC Rx/Tx */
-	stmmac_set_mac(priv->ioaddr, false);
+	priv->hw->mac->set_mac(priv->ioaddr, false);
 
 	netif_carrier_off(dev);
 
@@ -2063,6 +2450,8 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 		des = skb_frag_dma_map(priv->device, frag, 0,
 				       skb_frag_size(frag),
 				       DMA_TO_DEVICE);
+		if (dma_mapping_error(priv->device, des))
+			goto dma_map_err;
 
 		stmmac_tso_allocator(priv, des, skb_frag_size(frag),
 				     (i == nfrags - 1));
@@ -2661,6 +3050,7 @@ static int stmmac_poll(struct napi_struct *napi, int budget)
 {
 	struct stmmac_priv *priv = container_of(napi, struct stmmac_priv, napi);
 	int work_done = 0;
+	u32 chan = STMMAC_CHAN0;
 
 	priv->xstats.napi_poll++;
 	stmmac_tx_clean(priv);
@@ -2668,7 +3058,7 @@ static int stmmac_poll(struct napi_struct *napi, int budget)
 	work_done = stmmac_rx(priv, budget);
 	if (work_done < budget) {
 		napi_complete_done(napi, work_done);
-		stmmac_enable_dma_irq(priv);
+		stmmac_enable_dma_irq(priv, chan);
 	}
 	return work_done;
 }
@@ -2684,9 +3074,10 @@ static int stmmac_poll(struct napi_struct *napi, int budget)
 static void stmmac_tx_timeout(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 chan = STMMAC_CHAN0;
 
 	/* Clear Tx resources and restart transmitting again */
-	stmmac_tx_err(priv);
+	stmmac_tx_err(priv, chan);
 }
 
 /**
@@ -2795,6 +3186,12 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 {
 	struct net_device *dev = (struct net_device *)dev_id;
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	u32 queues_count;
+	u32 queue;
+
+	queues_count = (rx_cnt > tx_cnt) ? rx_cnt : tx_cnt;
 
 	if (priv->irq_wake)
 		pm_wakeup_event(priv->device, 0);
@@ -2808,16 +3205,27 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 	if ((priv->plat->has_gmac) || (priv->plat->has_gmac4)) {
 		int status = priv->hw->mac->host_irq_status(priv->hw,
 							    &priv->xstats);
+
 		if (unlikely(status)) {
 			/* For LPI we need to save the tx status */
 			if (status & CORE_IRQ_TX_PATH_IN_LPI_MODE)
 				priv->tx_path_in_lpi_mode = true;
 			if (status & CORE_IRQ_TX_PATH_EXIT_LPI_MODE)
 				priv->tx_path_in_lpi_mode = false;
-			if (status & CORE_IRQ_MTL_RX_OVERFLOW && priv->hw->dma->set_rx_tail_ptr)
-				priv->hw->dma->set_rx_tail_ptr(priv->ioaddr,
-							priv->rx_tail_addr,
-							STMMAC_CHAN0);
+		}
+
+		if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+			for (queue = 0; queue < queues_count; queue++) {
+				status |=
+				priv->hw->mac->host_mtl_irq_status(priv->hw,
+								   queue);
+
+				if (status & CORE_IRQ_MTL_RX_OVERFLOW &&
+				    priv->hw->dma->set_rx_tail_ptr)
+					priv->hw->dma->set_rx_tail_ptr(priv->ioaddr,
+								priv->rx_tail_addr,
+								queue);
+			}
 		}
 
 		/* PCS link status */
@@ -3369,10 +3777,9 @@ int stmmac_dvr_remove(struct device *dev)
 
 	netdev_info(priv->dev, "%s: removing driver", __func__);
 
-	priv->hw->dma->stop_rx(priv->ioaddr);
-	priv->hw->dma->stop_tx(priv->ioaddr);
+	stmmac_stop_all_dma(priv);
 
-	stmmac_set_mac(priv->ioaddr, false);
+	priv->hw->mac->set_mac(priv->ioaddr, false);
 	netif_carrier_off(ndev);
 	unregister_netdev(ndev);
 	if (priv->plat->stmmac_rst)
@@ -3416,15 +3823,14 @@ int stmmac_suspend(struct device *dev)
 	napi_disable(&priv->napi);
 
 	/* Stop TX/RX DMA */
-	priv->hw->dma->stop_tx(priv->ioaddr);
-	priv->hw->dma->stop_rx(priv->ioaddr);
+	stmmac_stop_all_dma(priv);
 
 	/* Enable Power down mode by programming the PMT regs */
 	if (device_may_wakeup(priv->device)) {
 		priv->hw->mac->pmt(priv->hw, priv->wolopts);
 		priv->irq_wake = 1;
 	} else {
-		stmmac_set_mac(priv->ioaddr, false);
+		priv->hw->mac->set_mac(priv->ioaddr, false);
 		pinctrl_pm_select_sleep_state(priv->device);
 		/* Disable clock in case of PWM is off */
 		clk_disable(priv->plat->pclk);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index 5c9e462276b9..a224d7bf1c1b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -88,6 +88,17 @@ static void stmmac_default_data(struct plat_stmmacenet_data *plat)
 
 	/* Set the maxmtu to a default of JUMBO_LEN */
 	plat->maxmtu = JUMBO_LEN;
+
+	/* Set default number of RX and TX queues to use */
+	plat->tx_queues_to_use = 1;
+	plat->rx_queues_to_use = 1;
+
+	/* Disable Priority config by default */
+	plat->tx_queues_cfg[0].use_prio = false;
+	plat->rx_queues_cfg[0].use_prio = false;
+
+	/* Disable RX queues routing by default */
+	plat->rx_queues_cfg[0].pkt_route = 0x0;
 }
 
 static int quark_default_data(struct plat_stmmacenet_data *plat,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 433a84239a68..7fc3a1ef395a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -108,7 +108,7 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev)
 	if (!np)
 		return NULL;
 
-	axi = kzalloc(sizeof(*axi), GFP_KERNEL);
+	axi = devm_kzalloc(&pdev->dev, sizeof(*axi), GFP_KERNEL);
 	if (!axi) {
 		of_node_put(np);
 		return ERR_PTR(-ENOMEM);
@@ -132,6 +132,155 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev)
 }
 
 /**
+ * stmmac_mtl_setup - parse DT parameters for multiple queues configuration
+ * @pdev: platform device
+ */
+static void stmmac_mtl_setup(struct platform_device *pdev,
+			     struct plat_stmmacenet_data *plat)
+{
+	struct device_node *q_node;
+	struct device_node *rx_node;
+	struct device_node *tx_node;
+	u8 queue = 0;
+
+	/* For backwards-compatibility with device trees that don't have any
+	 * snps,mtl-rx-config or snps,mtl-tx-config properties, we fall back
+	 * to one RX and TX queues each.
+	 */
+	plat->rx_queues_to_use = 1;
+	plat->tx_queues_to_use = 1;
+
+	rx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-rx-config", 0);
+	if (!rx_node)
+		return;
+
+	tx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-tx-config", 0);
+	if (!tx_node) {
+		of_node_put(rx_node);
+		return;
+	}
+
+	/* Processing RX queues common config */
+	if (of_property_read_u8(rx_node, "snps,rx-queues-to-use",
+				&plat->rx_queues_to_use))
+		plat->rx_queues_to_use = 1;
+
+	if (of_property_read_bool(rx_node, "snps,rx-sched-sp"))
+		plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP;
+	else if (of_property_read_bool(rx_node, "snps,rx-sched-wsp"))
+		plat->rx_sched_algorithm = MTL_RX_ALGORITHM_WSP;
+	else
+		plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP;
+
+	/* Processing individual RX queue config */
+	for_each_child_of_node(rx_node, q_node) {
+		if (queue >= plat->rx_queues_to_use)
+			break;
+
+		if (of_property_read_bool(q_node, "snps,dcb-algorithm"))
+			plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+		else if (of_property_read_bool(q_node, "snps,avb-algorithm"))
+			plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB;
+		else
+			plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+
+		if (of_property_read_u8(q_node, "snps,map-to-dma-channel",
+					&plat->rx_queues_cfg[queue].chan))
+			plat->rx_queues_cfg[queue].chan = queue;
+		/* TODO: Dynamic mapping to be included in the future */
+
+		if (of_property_read_u32(q_node, "snps,priority",
+					&plat->rx_queues_cfg[queue].prio)) {
+			plat->rx_queues_cfg[queue].prio = 0;
+			plat->rx_queues_cfg[queue].use_prio = false;
+		} else {
+			plat->rx_queues_cfg[queue].use_prio = true;
+		}
+
+		/* RX queue specific packet type routing */
+		if (of_property_read_bool(q_node, "snps,route-avcp"))
+			plat->rx_queues_cfg[queue].pkt_route = PACKET_AVCPQ;
+		else if (of_property_read_bool(q_node, "snps,route-ptp"))
+			plat->rx_queues_cfg[queue].pkt_route = PACKET_PTPQ;
+		else if (of_property_read_bool(q_node, "snps,route-dcbcp"))
+			plat->rx_queues_cfg[queue].pkt_route = PACKET_DCBCPQ;
+		else if (of_property_read_bool(q_node, "snps,route-up"))
+			plat->rx_queues_cfg[queue].pkt_route = PACKET_UPQ;
+		else if (of_property_read_bool(q_node, "snps,route-multi-broad"))
+			plat->rx_queues_cfg[queue].pkt_route = PACKET_MCBCQ;
+		else
+			plat->rx_queues_cfg[queue].pkt_route = 0x0;
+
+		queue++;
+	}
+
+	/* Processing TX queues common config */
+	if (of_property_read_u8(tx_node, "snps,tx-queues-to-use",
+				&plat->tx_queues_to_use))
+		plat->tx_queues_to_use = 1;
+
+	if (of_property_read_bool(tx_node, "snps,tx-sched-wrr"))
+		plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WRR;
+	else if (of_property_read_bool(tx_node, "snps,tx-sched-wfq"))
+		plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WFQ;
+	else if (of_property_read_bool(tx_node, "snps,tx-sched-dwrr"))
+		plat->tx_sched_algorithm = MTL_TX_ALGORITHM_DWRR;
+	else if (of_property_read_bool(tx_node, "snps,tx-sched-sp"))
+		plat->tx_sched_algorithm = MTL_TX_ALGORITHM_SP;
+	else
+		plat->tx_sched_algorithm = MTL_TX_ALGORITHM_SP;
+
+	queue = 0;
+
+	/* Processing individual TX queue config */
+	for_each_child_of_node(tx_node, q_node) {
+		if (queue >= plat->tx_queues_to_use)
+			break;
+
+		if (of_property_read_u8(q_node, "snps,weight",
+					&plat->tx_queues_cfg[queue].weight))
+			plat->tx_queues_cfg[queue].weight = 0x10 + queue;
+
+		if (of_property_read_bool(q_node, "snps,dcb-algorithm")) {
+			plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+		} else if (of_property_read_bool(q_node,
+						 "snps,avb-algorithm")) {
+			plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB;
+
+			/* Credit Base Shaper parameters used by AVB */
+			if (of_property_read_u32(q_node, "snps,send_slope",
+				&plat->tx_queues_cfg[queue].send_slope))
+				plat->tx_queues_cfg[queue].send_slope = 0x0;
+			if (of_property_read_u32(q_node, "snps,idle_slope",
+				&plat->tx_queues_cfg[queue].idle_slope))
+				plat->tx_queues_cfg[queue].idle_slope = 0x0;
+			if (of_property_read_u32(q_node, "snps,high_credit",
+				&plat->tx_queues_cfg[queue].high_credit))
+				plat->tx_queues_cfg[queue].high_credit = 0x0;
+			if (of_property_read_u32(q_node, "snps,low_credit",
+				&plat->tx_queues_cfg[queue].low_credit))
+				plat->tx_queues_cfg[queue].low_credit = 0x0;
+		} else {
+			plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+		}
+
+		if (of_property_read_u32(q_node, "snps,priority",
+					&plat->tx_queues_cfg[queue].prio)) {
+			plat->tx_queues_cfg[queue].prio = 0;
+			plat->tx_queues_cfg[queue].use_prio = false;
+		} else {
+			plat->tx_queues_cfg[queue].use_prio = true;
+		}
+
+		queue++;
+	}
+
+	of_node_put(rx_node);
+	of_node_put(tx_node);
+	of_node_put(q_node);
+}
+
+/**
  * stmmac_dt_phy - parse device-tree driver parameters to allocate PHY resources
  * @plat: driver data platform structure
  * @np: device tree node
@@ -340,6 +489,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 
 	plat->axi = stmmac_axi_setup(pdev);
 
+	stmmac_mtl_setup(pdev, plat);
+
 	/* clock setup */
 	plat->stmmac_clk = devm_clk_get(&pdev->dev,
 					STMMAC_RESOURCE_NAME);
@@ -359,13 +510,12 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 	clk_prepare_enable(plat->pclk);
 
 	/* Fall-back to main clock in case of no PTP ref is passed */
-	plat->clk_ptp_ref = devm_clk_get(&pdev->dev, "clk_ptp_ref");
+	plat->clk_ptp_ref = devm_clk_get(&pdev->dev, "ptp_ref");
 	if (IS_ERR(plat->clk_ptp_ref)) {
 		plat->clk_ptp_rate = clk_get_rate(plat->stmmac_clk);
 		plat->clk_ptp_ref = NULL;
 		dev_warn(&pdev->dev, "PTP uses main clock\n");
 	} else {
-		clk_prepare_enable(plat->clk_ptp_ref);
 		plat->clk_ptp_rate = clk_get_rate(plat->clk_ptp_ref);
 		dev_dbg(&pdev->dev, "PTP rate %d\n", plat->clk_ptp_rate);
 	}
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 0e8e89f17dbb..382993c1561c 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -691,7 +691,8 @@ static void cas_mif_poll(struct cas *cp, const int enable)
 }
 
 /* Must be invoked under cp->lock */
-static void cas_begin_auto_negotiation(struct cas *cp, struct ethtool_cmd *ep)
+static void cas_begin_auto_negotiation(struct cas *cp,
+				       const struct ethtool_link_ksettings *ep)
 {
 	u16 ctl;
 #if 1
@@ -704,16 +705,16 @@ static void cas_begin_auto_negotiation(struct cas *cp, struct ethtool_cmd *ep)
 	if (!ep)
 		goto start_aneg;
 	lcntl = cp->link_cntl;
-	if (ep->autoneg == AUTONEG_ENABLE)
+	if (ep->base.autoneg == AUTONEG_ENABLE) {
 		cp->link_cntl = BMCR_ANENABLE;
-	else {
-		u32 speed = ethtool_cmd_speed(ep);
+	} else {
+		u32 speed = ep->base.speed;
 		cp->link_cntl = 0;
 		if (speed == SPEED_100)
 			cp->link_cntl |= BMCR_SPEED100;
 		else if (speed == SPEED_1000)
 			cp->link_cntl |= CAS_BMCR_SPEED1000;
-		if (ep->duplex == DUPLEX_FULL)
+		if (ep->base.duplex == DUPLEX_FULL)
 			cp->link_cntl |= BMCR_FULLDPLX;
 	}
 #if 1
@@ -4528,19 +4529,21 @@ static void cas_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info
 	strlcpy(info->bus_info, pci_name(cp->pdev), sizeof(info->bus_info));
 }
 
-static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int cas_get_link_ksettings(struct net_device *dev,
+				  struct ethtool_link_ksettings *cmd)
 {
 	struct cas *cp = netdev_priv(dev);
 	u16 bmcr;
 	int full_duplex, speed, pause;
 	unsigned long flags;
 	enum link_state linkstate = link_up;
+	u32 supported, advertising;
 
-	cmd->advertising = 0;
-	cmd->supported = SUPPORTED_Autoneg;
+	advertising = 0;
+	supported = SUPPORTED_Autoneg;
 	if (cp->cas_flags & CAS_FLAG_1000MB_CAP) {
-		cmd->supported |= SUPPORTED_1000baseT_Full;
-		cmd->advertising |= ADVERTISED_1000baseT_Full;
+		supported |= SUPPORTED_1000baseT_Full;
+		advertising |= ADVERTISED_1000baseT_Full;
 	}
 
 	/* Record PHY settings if HW is on. */
@@ -4548,17 +4551,15 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 	bmcr = 0;
 	linkstate = cp->lstate;
 	if (CAS_PHY_MII(cp->phy_type)) {
-		cmd->port = PORT_MII;
-		cmd->transceiver = (cp->cas_flags & CAS_FLAG_SATURN) ?
-			XCVR_INTERNAL : XCVR_EXTERNAL;
-		cmd->phy_address = cp->phy_addr;
-		cmd->advertising |= ADVERTISED_TP | ADVERTISED_MII |
+		cmd->base.port = PORT_MII;
+		cmd->base.phy_address = cp->phy_addr;
+		advertising |= ADVERTISED_TP | ADVERTISED_MII |
 			ADVERTISED_10baseT_Half |
 			ADVERTISED_10baseT_Full |
 			ADVERTISED_100baseT_Half |
 			ADVERTISED_100baseT_Full;
 
-		cmd->supported |=
+		supported |=
 			(SUPPORTED_10baseT_Half |
 			 SUPPORTED_10baseT_Full |
 			 SUPPORTED_100baseT_Half |
@@ -4574,11 +4575,10 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 		}
 
 	} else {
-		cmd->port = PORT_FIBRE;
-		cmd->transceiver = XCVR_INTERNAL;
-		cmd->phy_address = 0;
-		cmd->supported   |= SUPPORTED_FIBRE;
-		cmd->advertising |= ADVERTISED_FIBRE;
+		cmd->base.port = PORT_FIBRE;
+		cmd->base.phy_address = 0;
+		supported   |= SUPPORTED_FIBRE;
+		advertising |= ADVERTISED_FIBRE;
 
 		if (cp->hw_running) {
 			/* pcs uses the same bits as mii */
@@ -4590,21 +4590,20 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 	spin_unlock_irqrestore(&cp->lock, flags);
 
 	if (bmcr & BMCR_ANENABLE) {
-		cmd->advertising |= ADVERTISED_Autoneg;
-		cmd->autoneg = AUTONEG_ENABLE;
-		ethtool_cmd_speed_set(cmd, ((speed == 10) ?
+		advertising |= ADVERTISED_Autoneg;
+		cmd->base.autoneg = AUTONEG_ENABLE;
+		cmd->base.speed =  ((speed == 10) ?
 					    SPEED_10 :
 					    ((speed == 1000) ?
-					     SPEED_1000 : SPEED_100)));
-		cmd->duplex = full_duplex ? DUPLEX_FULL : DUPLEX_HALF;
+					     SPEED_1000 : SPEED_100));
+		cmd->base.duplex = full_duplex ? DUPLEX_FULL : DUPLEX_HALF;
 	} else {
-		cmd->autoneg = AUTONEG_DISABLE;
-		ethtool_cmd_speed_set(cmd, ((bmcr & CAS_BMCR_SPEED1000) ?
+		cmd->base.autoneg = AUTONEG_DISABLE;
+		cmd->base.speed = ((bmcr & CAS_BMCR_SPEED1000) ?
 					    SPEED_1000 :
 					    ((bmcr & BMCR_SPEED100) ?
-					     SPEED_100 : SPEED_10)));
-		cmd->duplex =
-			(bmcr & BMCR_FULLDPLX) ?
+					     SPEED_100 : SPEED_10));
+		cmd->base.duplex = (bmcr & BMCR_FULLDPLX) ?
 			DUPLEX_FULL : DUPLEX_HALF;
 	}
 	if (linkstate != link_up) {
@@ -4619,39 +4618,46 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 		 * settings that we configured.
 		 */
 		if (cp->link_cntl & BMCR_ANENABLE) {
-			ethtool_cmd_speed_set(cmd, 0);
-			cmd->duplex = 0xff;
+			cmd->base.speed = 0;
+			cmd->base.duplex = 0xff;
 		} else {
-			ethtool_cmd_speed_set(cmd, SPEED_10);
+			cmd->base.speed = SPEED_10;
 			if (cp->link_cntl & BMCR_SPEED100) {
-				ethtool_cmd_speed_set(cmd, SPEED_100);
+				cmd->base.speed = SPEED_100;
 			} else if (cp->link_cntl & CAS_BMCR_SPEED1000) {
-				ethtool_cmd_speed_set(cmd, SPEED_1000);
+				cmd->base.speed = SPEED_1000;
 			}
-			cmd->duplex = (cp->link_cntl & BMCR_FULLDPLX)?
+			cmd->base.duplex = (cp->link_cntl & BMCR_FULLDPLX) ?
 				DUPLEX_FULL : DUPLEX_HALF;
 		}
 	}
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
+
 	return 0;
 }
 
-static int cas_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int cas_set_link_ksettings(struct net_device *dev,
+				  const struct ethtool_link_ksettings *cmd)
 {
 	struct cas *cp = netdev_priv(dev);
 	unsigned long flags;
-	u32 speed = ethtool_cmd_speed(cmd);
+	u32 speed = cmd->base.speed;
 
 	/* Verify the settings we care about. */
-	if (cmd->autoneg != AUTONEG_ENABLE &&
-	    cmd->autoneg != AUTONEG_DISABLE)
+	if (cmd->base.autoneg != AUTONEG_ENABLE &&
+	    cmd->base.autoneg != AUTONEG_DISABLE)
 		return -EINVAL;
 
-	if (cmd->autoneg == AUTONEG_DISABLE &&
+	if (cmd->base.autoneg == AUTONEG_DISABLE &&
 	    ((speed != SPEED_1000 &&
 	      speed != SPEED_100 &&
 	      speed != SPEED_10) ||
-	     (cmd->duplex != DUPLEX_HALF &&
-	      cmd->duplex != DUPLEX_FULL)))
+	     (cmd->base.duplex != DUPLEX_HALF &&
+	      cmd->base.duplex != DUPLEX_FULL)))
 		return -EINVAL;
 
 	/* Apply settings and restart link process. */
@@ -4753,8 +4759,6 @@ static void cas_get_ethtool_stats(struct net_device *dev,
 
 static const struct ethtool_ops cas_ethtool_ops = {
 	.get_drvinfo		= cas_get_drvinfo,
-	.get_settings		= cas_get_settings,
-	.set_settings		= cas_set_settings,
 	.nway_reset		= cas_nway_reset,
 	.get_link		= cas_get_link,
 	.get_msglevel		= cas_get_msglevel,
@@ -4764,6 +4768,8 @@ static const struct ethtool_ops cas_ethtool_ops = {
 	.get_sset_count		= cas_get_sset_count,
 	.get_strings		= cas_get_strings,
 	.get_ethtool_stats	= cas_get_ethtool_stats,
+	.get_link_ksettings	= cas_get_link_ksettings,
+	.set_link_ksettings	= cas_set_link_ksettings,
 };
 
 static int cas_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c
index 89952deae47f..5a90fed06260 100644
--- a/drivers/net/ethernet/sun/ldmvsw.c
+++ b/drivers/net/ethernet/sun/ldmvsw.c
@@ -1,6 +1,6 @@
 /* ldmvsw.c: Sun4v LDOM Virtual Switch Driver.
  *
- * Copyright (C) 2016 Oracle. All rights reserved.
+ * Copyright (C) 2016-2017 Oracle. All rights reserved.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -41,8 +41,8 @@
 static u8 vsw_port_hwaddr[ETH_ALEN] = {0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF};
 
 #define DRV_MODULE_NAME		"ldmvsw"
-#define DRV_MODULE_VERSION	"1.1"
-#define DRV_MODULE_RELDATE	"February 3, 2017"
+#define DRV_MODULE_VERSION	"1.2"
+#define DRV_MODULE_RELDATE	"March 4, 2017"
 
 static char version[] =
 	DRV_MODULE_NAME " " DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")";
@@ -123,6 +123,20 @@ static void vsw_set_rx_mode(struct net_device *dev)
 	return sunvnet_set_rx_mode_common(dev, port->vp);
 }
 
+int ldmvsw_open(struct net_device *dev)
+{
+	struct vnet_port *port = netdev_priv(dev);
+	struct vio_driver_state *vio = &port->vio;
+
+	/* reset the channel */
+	vio_link_state_change(vio, LDC_EVENT_RESET);
+	vnet_port_reset(port);
+	vio_port_up(vio);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ldmvsw_open);
+
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void vsw_poll_controller(struct net_device *dev)
 {
@@ -133,7 +147,7 @@ static void vsw_poll_controller(struct net_device *dev)
 #endif
 
 static const struct net_device_ops vsw_ops = {
-	.ndo_open		= sunvnet_open_common,
+	.ndo_open		= ldmvsw_open,
 	.ndo_stop		= sunvnet_close_common,
 	.ndo_set_rx_mode	= vsw_set_rx_mode,
 	.ndo_set_mac_address	= sunvnet_set_mac_addr_common,
@@ -365,6 +379,11 @@ static int vsw_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	napi_enable(&port->napi);
 	vio_port_up(&port->vio);
 
+	/* assure no carrier until we receive an LDC_EVENT_UP,
+	 * even if the vsw config script tries to force us up
+	 */
+	netif_carrier_off(dev);
+
 	netdev_info(dev, "LDOM vsw-port %pM\n", dev->dev_addr);
 
 	pr_info("%s: PORT ( remote-mac %pM%s )\n", dev->name,
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 57978056b336..2dcca249eb9c 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -6813,7 +6813,8 @@ static void niu_get_drvinfo(struct net_device *dev,
 			sizeof(info->bus_info));
 }
 
-static int niu_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int niu_get_link_ksettings(struct net_device *dev,
+				  struct ethtool_link_ksettings *cmd)
 {
 	struct niu *np = netdev_priv(dev);
 	struct niu_link_config *lp;
@@ -6821,28 +6822,30 @@ static int niu_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 	lp = &np->link_config;
 
 	memset(cmd, 0, sizeof(*cmd));
-	cmd->phy_address = np->phy_addr;
-	cmd->supported = lp->supported;
-	cmd->advertising = lp->active_advertising;
-	cmd->autoneg = lp->active_autoneg;
-	ethtool_cmd_speed_set(cmd, lp->active_speed);
-	cmd->duplex = lp->active_duplex;
-	cmd->port = (np->flags & NIU_FLAGS_FIBER) ? PORT_FIBRE : PORT_TP;
-	cmd->transceiver = (np->flags & NIU_FLAGS_XCVR_SERDES) ?
-		XCVR_EXTERNAL : XCVR_INTERNAL;
+	cmd->base.phy_address = np->phy_addr;
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						lp->supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						lp->active_advertising);
+	cmd->base.autoneg = lp->active_autoneg;
+	cmd->base.speed = lp->active_speed;
+	cmd->base.duplex = lp->active_duplex;
+	cmd->base.port = (np->flags & NIU_FLAGS_FIBER) ? PORT_FIBRE : PORT_TP;
 
 	return 0;
 }
 
-static int niu_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int niu_set_link_ksettings(struct net_device *dev,
+				  const struct ethtool_link_ksettings *cmd)
 {
 	struct niu *np = netdev_priv(dev);
 	struct niu_link_config *lp = &np->link_config;
 
-	lp->advertising = cmd->advertising;
-	lp->speed = ethtool_cmd_speed(cmd);
-	lp->duplex = cmd->duplex;
-	lp->autoneg = cmd->autoneg;
+	ethtool_convert_link_mode_to_legacy_u32(&lp->advertising,
+						cmd->link_modes.advertising);
+	lp->speed = cmd->base.speed;
+	lp->duplex = cmd->base.duplex;
+	lp->autoneg = cmd->base.autoneg;
 	return niu_init_link(np);
 }
 
@@ -7902,14 +7905,14 @@ static const struct ethtool_ops niu_ethtool_ops = {
 	.nway_reset		= niu_nway_reset,
 	.get_eeprom_len		= niu_get_eeprom_len,
 	.get_eeprom		= niu_get_eeprom,
-	.get_settings		= niu_get_settings,
-	.set_settings		= niu_set_settings,
 	.get_strings		= niu_get_strings,
 	.get_sset_count		= niu_get_sset_count,
 	.get_ethtool_stats	= niu_get_ethtool_stats,
 	.set_phys_id		= niu_set_phys_id,
 	.get_rxnfc		= niu_get_nfc,
 	.set_rxnfc		= niu_set_nfc,
+	.get_link_ksettings	= niu_get_link_ksettings,
+	.set_link_ksettings	= niu_set_link_ksettings,
 };
 
 static int niu_ldg_assign_ldn(struct niu *np, struct niu_parent *parent,
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index 5c5952e782cd..fa607d062cb3 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -1250,12 +1250,18 @@ static void gem_stop_dma(struct gem *gp)
 
 
 // XXX dbl check what that function should do when called on PCS PHY
-static void gem_begin_auto_negotiation(struct gem *gp, struct ethtool_cmd *ep)
+static void gem_begin_auto_negotiation(struct gem *gp,
+				       const struct ethtool_link_ksettings *ep)
 {
 	u32 advertise, features;
 	int autoneg;
 	int speed;
 	int duplex;
+	u32 advertising;
+
+	if (ep)
+		ethtool_convert_link_mode_to_legacy_u32(
+			&advertising, ep->link_modes.advertising);
 
 	if (gp->phy_type != phy_mii_mdio0 &&
      	    gp->phy_type != phy_mii_mdio1)
@@ -1278,13 +1284,13 @@ static void gem_begin_auto_negotiation(struct gem *gp, struct ethtool_cmd *ep)
 	/* Setup link parameters */
 	if (!ep)
 		goto start_aneg;
-	if (ep->autoneg == AUTONEG_ENABLE) {
-		advertise = ep->advertising;
+	if (ep->base.autoneg == AUTONEG_ENABLE) {
+		advertise = advertising;
 		autoneg = 1;
 	} else {
 		autoneg = 0;
-		speed = ethtool_cmd_speed(ep);
-		duplex = ep->duplex;
+		speed = ep->base.speed;
+		duplex = ep->base.duplex;
 	}
 
 start_aneg:
@@ -2515,85 +2521,96 @@ static void gem_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info
 	strlcpy(info->bus_info, pci_name(gp->pdev), sizeof(info->bus_info));
 }
 
-static int gem_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int gem_get_link_ksettings(struct net_device *dev,
+				  struct ethtool_link_ksettings *cmd)
 {
 	struct gem *gp = netdev_priv(dev);
+	u32 supported, advertising;
 
 	if (gp->phy_type == phy_mii_mdio0 ||
 	    gp->phy_type == phy_mii_mdio1) {
 		if (gp->phy_mii.def)
-			cmd->supported = gp->phy_mii.def->features;
+			supported = gp->phy_mii.def->features;
 		else
-			cmd->supported = (SUPPORTED_10baseT_Half |
+			supported = (SUPPORTED_10baseT_Half |
 					  SUPPORTED_10baseT_Full);
 
 		/* XXX hardcoded stuff for now */
-		cmd->port = PORT_MII;
-		cmd->transceiver = XCVR_EXTERNAL;
-		cmd->phy_address = 0; /* XXX fixed PHYAD */
+		cmd->base.port = PORT_MII;
+		cmd->base.phy_address = 0; /* XXX fixed PHYAD */
 
 		/* Return current PHY settings */
-		cmd->autoneg = gp->want_autoneg;
-		ethtool_cmd_speed_set(cmd, gp->phy_mii.speed);
-		cmd->duplex = gp->phy_mii.duplex;
-		cmd->advertising = gp->phy_mii.advertising;
+		cmd->base.autoneg = gp->want_autoneg;
+		cmd->base.speed = gp->phy_mii.speed;
+		cmd->base.duplex = gp->phy_mii.duplex;
+		advertising = gp->phy_mii.advertising;
 
 		/* If we started with a forced mode, we don't have a default
 		 * advertise set, we need to return something sensible so
 		 * userland can re-enable autoneg properly.
 		 */
-		if (cmd->advertising == 0)
-			cmd->advertising = cmd->supported;
+		if (advertising == 0)
+			advertising = supported;
 	} else { // XXX PCS ?
-		cmd->supported =
+		supported =
 			(SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full |
 			 SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full |
 			 SUPPORTED_Autoneg);
-		cmd->advertising = cmd->supported;
-		ethtool_cmd_speed_set(cmd, 0);
-		cmd->duplex = cmd->port = cmd->phy_address =
-			cmd->transceiver = cmd->autoneg = 0;
+		advertising = supported;
+		cmd->base.speed = 0;
+		cmd->base.duplex = 0;
+		cmd->base.port = 0;
+		cmd->base.phy_address = 0;
+		cmd->base.autoneg = 0;
 
 		/* serdes means usually a Fibre connector, with most fixed */
 		if (gp->phy_type == phy_serdes) {
-			cmd->port = PORT_FIBRE;
-			cmd->supported = (SUPPORTED_1000baseT_Half |
+			cmd->base.port = PORT_FIBRE;
+			supported = (SUPPORTED_1000baseT_Half |
 				SUPPORTED_1000baseT_Full |
 				SUPPORTED_FIBRE | SUPPORTED_Autoneg |
 				SUPPORTED_Pause | SUPPORTED_Asym_Pause);
-			cmd->advertising = cmd->supported;
-			cmd->transceiver = XCVR_INTERNAL;
+			advertising = supported;
 			if (gp->lstate == link_up)
-				ethtool_cmd_speed_set(cmd, SPEED_1000);
-			cmd->duplex = DUPLEX_FULL;
-			cmd->autoneg = 1;
+				cmd->base.speed = SPEED_1000;
+			cmd->base.duplex = DUPLEX_FULL;
+			cmd->base.autoneg = 1;
 		}
 	}
-	cmd->maxtxpkt = cmd->maxrxpkt = 0;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 
 	return 0;
 }
 
-static int gem_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int gem_set_link_ksettings(struct net_device *dev,
+				  const struct ethtool_link_ksettings *cmd)
 {
 	struct gem *gp = netdev_priv(dev);
-	u32 speed = ethtool_cmd_speed(cmd);
+	u32 speed = cmd->base.speed;
+	u32 advertising;
+
+	ethtool_convert_link_mode_to_legacy_u32(&advertising,
+						cmd->link_modes.advertising);
 
 	/* Verify the settings we care about. */
-	if (cmd->autoneg != AUTONEG_ENABLE &&
-	    cmd->autoneg != AUTONEG_DISABLE)
+	if (cmd->base.autoneg != AUTONEG_ENABLE &&
+	    cmd->base.autoneg != AUTONEG_DISABLE)
 		return -EINVAL;
 
-	if (cmd->autoneg == AUTONEG_ENABLE &&
-	    cmd->advertising == 0)
+	if (cmd->base.autoneg == AUTONEG_ENABLE &&
+	    advertising == 0)
 		return -EINVAL;
 
-	if (cmd->autoneg == AUTONEG_DISABLE &&
+	if (cmd->base.autoneg == AUTONEG_DISABLE &&
 	    ((speed != SPEED_1000 &&
 	      speed != SPEED_100 &&
 	      speed != SPEED_10) ||
-	     (cmd->duplex != DUPLEX_HALF &&
-	      cmd->duplex != DUPLEX_FULL)))
+	     (cmd->base.duplex != DUPLEX_HALF &&
+	      cmd->base.duplex != DUPLEX_FULL)))
 		return -EINVAL;
 
 	/* Apply settings and restart link process. */
@@ -2666,13 +2683,13 @@ static int gem_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 static const struct ethtool_ops gem_ethtool_ops = {
 	.get_drvinfo		= gem_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
-	.get_settings		= gem_get_settings,
-	.set_settings		= gem_set_settings,
 	.nway_reset		= gem_nway_reset,
 	.get_msglevel		= gem_get_msglevel,
 	.set_msglevel		= gem_set_msglevel,
 	.get_wol		= gem_get_wol,
 	.set_wol		= gem_set_wol,
+	.get_link_ksettings	= gem_get_link_ksettings,
+	.set_link_ksettings	= gem_set_link_ksettings,
 };
 
 static int gem_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index 72ff05cd3ed8..53ff66ef53ac 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -1294,9 +1294,10 @@ static void happy_meal_init_rings(struct happy_meal *hp)
 }
 
 /* hp->happy_lock must be held */
-static void happy_meal_begin_auto_negotiation(struct happy_meal *hp,
-					      void __iomem *tregs,
-					      struct ethtool_cmd *ep)
+static void
+happy_meal_begin_auto_negotiation(struct happy_meal *hp,
+				  void __iomem *tregs,
+				  const struct ethtool_link_ksettings *ep)
 {
 	int timeout;
 
@@ -1309,7 +1310,7 @@ static void happy_meal_begin_auto_negotiation(struct happy_meal *hp,
 	/* XXX Check BMSR_ANEGCAPABLE, should not be necessary though. */
 
 	hp->sw_advertise = happy_meal_tcvr_read(hp, tregs, MII_ADVERTISE);
-	if (ep == NULL || ep->autoneg == AUTONEG_ENABLE) {
+	if (!ep || ep->base.autoneg == AUTONEG_ENABLE) {
 		/* Advertise everything we can support. */
 		if (hp->sw_bmsr & BMSR_10HALF)
 			hp->sw_advertise |= (ADVERTISE_10HALF);
@@ -1384,14 +1385,14 @@ force_link:
 		/* Disable auto-negotiation in BMCR, enable the duplex and
 		 * speed setting, init the timer state machine, and fire it off.
 		 */
-		if (ep == NULL || ep->autoneg == AUTONEG_ENABLE) {
+		if (!ep || ep->base.autoneg == AUTONEG_ENABLE) {
 			hp->sw_bmcr = BMCR_SPEED100;
 		} else {
-			if (ethtool_cmd_speed(ep) == SPEED_100)
+			if (ep->base.speed == SPEED_100)
 				hp->sw_bmcr = BMCR_SPEED100;
 			else
 				hp->sw_bmcr = 0;
-			if (ep->duplex == DUPLEX_FULL)
+			if (ep->base.duplex == DUPLEX_FULL)
 				hp->sw_bmcr |= BMCR_FULLDPLX;
 		}
 		happy_meal_tcvr_write(hp, tregs, MII_BMCR, hp->sw_bmcr);
@@ -2434,20 +2435,21 @@ static void happy_meal_set_multicast(struct net_device *dev)
 }
 
 /* Ethtool support... */
-static int hme_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int hme_get_link_ksettings(struct net_device *dev,
+				  struct ethtool_link_ksettings *cmd)
 {
 	struct happy_meal *hp = netdev_priv(dev);
 	u32 speed;
+	u32 supported;
 
-	cmd->supported =
+	supported =
 		(SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full |
 		 SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full |
 		 SUPPORTED_Autoneg | SUPPORTED_TP | SUPPORTED_MII);
 
 	/* XXX hardcoded stuff for now */
-	cmd->port = PORT_TP; /* XXX no MII support */
-	cmd->transceiver = XCVR_INTERNAL; /* XXX no external xcvr support */
-	cmd->phy_address = 0; /* XXX fixed PHYAD */
+	cmd->base.port = PORT_TP; /* XXX no MII support */
+	cmd->base.phy_address = 0; /* XXX fixed PHYAD */
 
 	/* Record PHY settings. */
 	spin_lock_irq(&hp->happy_lock);
@@ -2456,41 +2458,45 @@ static int hme_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 	spin_unlock_irq(&hp->happy_lock);
 
 	if (hp->sw_bmcr & BMCR_ANENABLE) {
-		cmd->autoneg = AUTONEG_ENABLE;
+		cmd->base.autoneg = AUTONEG_ENABLE;
 		speed = ((hp->sw_lpa & (LPA_100HALF | LPA_100FULL)) ?
 			 SPEED_100 : SPEED_10);
 		if (speed == SPEED_100)
-			cmd->duplex =
+			cmd->base.duplex =
 				(hp->sw_lpa & (LPA_100FULL)) ?
 				DUPLEX_FULL : DUPLEX_HALF;
 		else
-			cmd->duplex =
+			cmd->base.duplex =
 				(hp->sw_lpa & (LPA_10FULL)) ?
 				DUPLEX_FULL : DUPLEX_HALF;
 	} else {
-		cmd->autoneg = AUTONEG_DISABLE;
+		cmd->base.autoneg = AUTONEG_DISABLE;
 		speed = (hp->sw_bmcr & BMCR_SPEED100) ? SPEED_100 : SPEED_10;
-		cmd->duplex =
+		cmd->base.duplex =
 			(hp->sw_bmcr & BMCR_FULLDPLX) ?
 			DUPLEX_FULL : DUPLEX_HALF;
 	}
-	ethtool_cmd_speed_set(cmd, speed);
+	cmd->base.speed = speed;
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+
 	return 0;
 }
 
-static int hme_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int hme_set_link_ksettings(struct net_device *dev,
+				  const struct ethtool_link_ksettings *cmd)
 {
 	struct happy_meal *hp = netdev_priv(dev);
 
 	/* Verify the settings we care about. */
-	if (cmd->autoneg != AUTONEG_ENABLE &&
-	    cmd->autoneg != AUTONEG_DISABLE)
+	if (cmd->base.autoneg != AUTONEG_ENABLE &&
+	    cmd->base.autoneg != AUTONEG_DISABLE)
 		return -EINVAL;
-	if (cmd->autoneg == AUTONEG_DISABLE &&
-	    ((ethtool_cmd_speed(cmd) != SPEED_100 &&
-	      ethtool_cmd_speed(cmd) != SPEED_10) ||
-	     (cmd->duplex != DUPLEX_HALF &&
-	      cmd->duplex != DUPLEX_FULL)))
+	if (cmd->base.autoneg == AUTONEG_DISABLE &&
+	    ((cmd->base.speed != SPEED_100 &&
+	      cmd->base.speed != SPEED_10) ||
+	     (cmd->base.duplex != DUPLEX_HALF &&
+	      cmd->base.duplex != DUPLEX_FULL)))
 		return -EINVAL;
 
 	/* Ok, do it to it. */
@@ -2537,10 +2543,10 @@ static u32 hme_get_link(struct net_device *dev)
 }
 
 static const struct ethtool_ops hme_ethtool_ops = {
-	.get_settings		= hme_get_settings,
-	.set_settings		= hme_set_settings,
 	.get_drvinfo		= hme_get_drvinfo,
 	.get_link		= hme_get_link,
+	.get_link_ksettings	= hme_get_link_ksettings,
+	.set_link_ksettings	= hme_set_link_ksettings,
 };
 
 static int hme_version_printed;
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 4cc2571f71c6..0b95105f7060 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -1,7 +1,7 @@
 /* sunvnet.c: Sun LDOM Virtual Network Driver.
  *
  * Copyright (C) 2007, 2008 David S. Miller <davem@davemloft.net>
- * Copyright (C) 2016 Oracle. All rights reserved.
+ * Copyright (C) 2016-2017 Oracle. All rights reserved.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -77,11 +77,125 @@ static void vnet_set_msglevel(struct net_device *dev, u32 value)
 	vp->msg_enable = value;
 }
 
+static const struct {
+	const char string[ETH_GSTRING_LEN];
+} ethtool_stats_keys[] = {
+	{ "rx_packets" },
+	{ "tx_packets" },
+	{ "rx_bytes" },
+	{ "tx_bytes" },
+	{ "rx_errors" },
+	{ "tx_errors" },
+	{ "rx_dropped" },
+	{ "tx_dropped" },
+	{ "multicast" },
+	{ "rx_length_errors" },
+	{ "rx_frame_errors" },
+	{ "rx_missed_errors" },
+	{ "tx_carrier_errors" },
+	{ "nports" },
+};
+
+static int vnet_get_sset_count(struct net_device *dev, int sset)
+{
+	struct vnet *vp = (struct vnet *)netdev_priv(dev);
+
+	switch (sset) {
+	case ETH_SS_STATS:
+		return ARRAY_SIZE(ethtool_stats_keys)
+			+ (NUM_VNET_PORT_STATS * vp->nports);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void vnet_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
+{
+	struct vnet *vp = (struct vnet *)netdev_priv(dev);
+	struct vnet_port *port;
+	char *p = (char *)buf;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		memcpy(buf, &ethtool_stats_keys, sizeof(ethtool_stats_keys));
+		p += sizeof(ethtool_stats_keys);
+
+		rcu_read_lock();
+		list_for_each_entry_rcu(port, &vp->port_list, list) {
+			snprintf(p, ETH_GSTRING_LEN, "p%u.%s-%pM",
+				 port->q_index, port->switch_port ? "s" : "q",
+				 port->raddr);
+			p += ETH_GSTRING_LEN;
+			snprintf(p, ETH_GSTRING_LEN, "p%u.rx_packets",
+				 port->q_index);
+			p += ETH_GSTRING_LEN;
+			snprintf(p, ETH_GSTRING_LEN, "p%u.tx_packets",
+				 port->q_index);
+			p += ETH_GSTRING_LEN;
+			snprintf(p, ETH_GSTRING_LEN, "p%u.rx_bytes",
+				 port->q_index);
+			p += ETH_GSTRING_LEN;
+			snprintf(p, ETH_GSTRING_LEN, "p%u.tx_bytes",
+				 port->q_index);
+			p += ETH_GSTRING_LEN;
+			snprintf(p, ETH_GSTRING_LEN, "p%u.event_up",
+				 port->q_index);
+			p += ETH_GSTRING_LEN;
+			snprintf(p, ETH_GSTRING_LEN, "p%u.event_reset",
+				 port->q_index);
+			p += ETH_GSTRING_LEN;
+		}
+		rcu_read_unlock();
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
+}
+
+static void vnet_get_ethtool_stats(struct net_device *dev,
+				   struct ethtool_stats *estats, u64 *data)
+{
+	struct vnet *vp = (struct vnet *)netdev_priv(dev);
+	struct vnet_port *port;
+	int i = 0;
+
+	data[i++] = dev->stats.rx_packets;
+	data[i++] = dev->stats.tx_packets;
+	data[i++] = dev->stats.rx_bytes;
+	data[i++] = dev->stats.tx_bytes;
+	data[i++] = dev->stats.rx_errors;
+	data[i++] = dev->stats.tx_errors;
+	data[i++] = dev->stats.rx_dropped;
+	data[i++] = dev->stats.tx_dropped;
+	data[i++] = dev->stats.multicast;
+	data[i++] = dev->stats.rx_length_errors;
+	data[i++] = dev->stats.rx_frame_errors;
+	data[i++] = dev->stats.rx_missed_errors;
+	data[i++] = dev->stats.tx_carrier_errors;
+	data[i++] = vp->nports;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(port, &vp->port_list, list) {
+		data[i++] = port->q_index;
+		data[i++] = port->stats.rx_packets;
+		data[i++] = port->stats.tx_packets;
+		data[i++] = port->stats.rx_bytes;
+		data[i++] = port->stats.tx_bytes;
+		data[i++] = port->stats.event_up;
+		data[i++] = port->stats.event_reset;
+	}
+	rcu_read_unlock();
+}
+
 static const struct ethtool_ops vnet_ethtool_ops = {
 	.get_drvinfo		= vnet_get_drvinfo,
 	.get_msglevel		= vnet_get_msglevel,
 	.set_msglevel		= vnet_set_msglevel,
 	.get_link		= ethtool_op_get_link,
+	.get_sset_count		= vnet_get_sset_count,
+	.get_strings		= vnet_get_strings,
+	.get_ethtool_stats	= vnet_get_ethtool_stats,
 };
 
 static LIST_HEAD(vnet_list);
diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c
index fa2d11ca9b81..9e86833249d4 100644
--- a/drivers/net/ethernet/sun/sunvnet_common.c
+++ b/drivers/net/ethernet/sun/sunvnet_common.c
@@ -1,7 +1,7 @@
 /* sunvnet.c: Sun LDOM Virtual Network Driver.
  *
  * Copyright (C) 2007, 2008 David S. Miller <davem@davemloft.net>
- * Copyright (C) 2016 Oracle. All rights reserved.
+ * Copyright (C) 2016-2017 Oracle. All rights reserved.
  */
 
 #include <linux/module.h>
@@ -43,7 +43,6 @@ MODULE_LICENSE("GPL");
 MODULE_VERSION("1.1");
 
 static int __vnet_tx_trigger(struct vnet_port *port, u32 start);
-static void vnet_port_reset(struct vnet_port *port);
 
 static inline u32 vnet_tx_dring_avail(struct vio_dring_state *dr)
 {
@@ -410,8 +409,12 @@ static int vnet_rx_one(struct vnet_port *port, struct vio_net_desc *desc)
 
 	skb->ip_summed = port->switch_port ? CHECKSUM_NONE : CHECKSUM_PARTIAL;
 
+	if (unlikely(is_multicast_ether_addr(eth_hdr(skb)->h_dest)))
+		dev->stats.multicast++;
 	dev->stats.rx_packets++;
 	dev->stats.rx_bytes += len;
+	port->stats.rx_packets++;
+	port->stats.rx_bytes += len;
 	napi_gro_receive(&port->napi, skb);
 	return 0;
 
@@ -747,6 +750,13 @@ static int vnet_event_napi(struct vnet_port *port, int budget)
 
 	/* RESET takes precedent over any other event */
 	if (port->rx_event & LDC_EVENT_RESET) {
+		/* a link went down */
+
+		if (port->vsw == 1) {
+			netif_tx_stop_all_queues(dev);
+			netif_carrier_off(dev);
+		}
+
 		vio_link_state_change(vio, LDC_EVENT_RESET);
 		vnet_port_reset(port);
 		vio_port_up(vio);
@@ -762,12 +772,21 @@ static int vnet_event_napi(struct vnet_port *port, int budget)
 			maybe_tx_wakeup(port);
 
 		port->rx_event = 0;
+		port->stats.event_reset++;
 		return 0;
 	}
 
 	if (port->rx_event & LDC_EVENT_UP) {
+		/* a link came up */
+
+		if (port->vsw == 1) {
+			netif_carrier_on(port->dev);
+			netif_tx_start_all_queues(port->dev);
+		}
+
 		vio_link_state_change(vio, LDC_EVENT_UP);
 		port->rx_event = 0;
+		port->stats.event_up++;
 		return 0;
 	}
 
@@ -1417,6 +1436,8 @@ ldc_start_done:
 
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += port->tx_bufs[txi].skb->len;
+	port->stats.tx_packets++;
+	port->stats.tx_bytes += port->tx_bufs[txi].skb->len;
 
 	dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1);
 	if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
@@ -1631,7 +1652,7 @@ void sunvnet_port_free_tx_bufs_common(struct vnet_port *port)
 }
 EXPORT_SYMBOL_GPL(sunvnet_port_free_tx_bufs_common);
 
-static void vnet_port_reset(struct vnet_port *port)
+void vnet_port_reset(struct vnet_port *port)
 {
 	del_timer(&port->clean_timer);
 	sunvnet_port_free_tx_bufs_common(port);
@@ -1639,6 +1660,7 @@ static void vnet_port_reset(struct vnet_port *port)
 	port->tso = (port->vsw == 0);  /* no tso in vsw, misbehaves in bridge */
 	port->tsolen = 0;
 }
+EXPORT_SYMBOL_GPL(vnet_port_reset);
 
 static int vnet_port_alloc_tx_ring(struct vnet_port *port)
 {
@@ -1708,20 +1730,32 @@ EXPORT_SYMBOL_GPL(sunvnet_poll_controller_common);
 void sunvnet_port_add_txq_common(struct vnet_port *port)
 {
 	struct vnet *vp = port->vp;
-	int n;
+	int smallest = 0;
+	int i;
+
+	/* find the first least-used q
+	 * When there are more ldoms than q's, we start to
+	 * double up on ports per queue.
+	 */
+	for (i = 0; i < VNET_MAX_TXQS; i++) {
+		if (vp->q_used[i] == 0) {
+			smallest = i;
+			break;
+		}
+		if (vp->q_used[i] < vp->q_used[smallest])
+			smallest = i;
+	}
 
-	n = vp->nports++;
-	n = n & (VNET_MAX_TXQS - 1);
-	port->q_index = n;
-	netif_tx_wake_queue(netdev_get_tx_queue(VNET_PORT_TO_NET_DEVICE(port),
-						port->q_index));
+	vp->nports++;
+	vp->q_used[smallest]++;
+	port->q_index = smallest;
 }
 EXPORT_SYMBOL_GPL(sunvnet_port_add_txq_common);
 
 void sunvnet_port_rm_txq_common(struct vnet_port *port)
 {
 	port->vp->nports--;
-	netif_tx_stop_queue(netdev_get_tx_queue(VNET_PORT_TO_NET_DEVICE(port),
-						port->q_index));
+	port->vp->q_used[port->q_index]--;
+	port->q_index = 0;
 }
 EXPORT_SYMBOL_GPL(sunvnet_port_rm_txq_common);
diff --git a/drivers/net/ethernet/sun/sunvnet_common.h b/drivers/net/ethernet/sun/sunvnet_common.h
index ce5c824128a3..b20d6fa7ef25 100644
--- a/drivers/net/ethernet/sun/sunvnet_common.h
+++ b/drivers/net/ethernet/sun/sunvnet_common.h
@@ -35,6 +35,19 @@ struct vnet_tx_entry {
 
 struct vnet;
 
+struct vnet_port_stats {
+	/* keep them all the same size */
+	u32 rx_bytes;
+	u32 tx_bytes;
+	u32 rx_packets;
+	u32 tx_packets;
+	u32 event_up;
+	u32 event_reset;
+	u32 q_placeholder;
+};
+
+#define NUM_VNET_PORT_STATS  (sizeof(struct vnet_port_stats) / sizeof(u32))
+
 /* Structure to describe a vnet-port or vsw-port in the MD.
  * If the vsw bit is set, this structure represents a vswitch
  * port, and the net_device can be found from ->dev. If the
@@ -44,6 +57,8 @@ struct vnet;
 struct vnet_port {
 	struct vio_driver_state	vio;
 
+	struct vnet_port_stats stats;
+
 	struct hlist_node	hash;
 	u8			raddr[ETH_ALEN];
 	unsigned		switch_port:1;
@@ -97,22 +112,15 @@ struct vnet_mcast_entry {
 };
 
 struct vnet {
-	/* Protects port_list and port_hash.  */
-	spinlock_t		lock;
-
+	spinlock_t		lock; /* Protects port_list and port_hash.  */
 	struct net_device	*dev;
-
 	u32			msg_enable;
-
+	u8			q_used[VNET_MAX_TXQS];
 	struct list_head	port_list;
-
 	struct hlist_head	port_hash[VNET_PORT_HASH_SIZE];
-
 	struct vnet_mcast_entry	*mcast_list;
-
 	struct list_head	list;
 	u64			local_mac;
-
 	int			nports;
 };
 
@@ -139,6 +147,7 @@ int sunvnet_handle_attr_common(struct vio_driver_state *vio, void *arg);
 void sunvnet_handshake_complete_common(struct vio_driver_state *vio);
 int sunvnet_poll_common(struct napi_struct *napi, int budget);
 void sunvnet_port_free_tx_bufs_common(struct vnet_port *port);
+void vnet_port_reset(struct vnet_port *port);
 bool sunvnet_port_is_up_common(struct vnet_port *vnet);
 void sunvnet_port_add_txq_common(struct vnet_port *port);
 void sunvnet_port_rm_txq_common(struct vnet_port *port);
diff --git a/drivers/net/ethernet/synopsys/Kconfig b/drivers/net/ethernet/synopsys/Kconfig
new file mode 100644
index 000000000000..a9503884e1c2
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/Kconfig
@@ -0,0 +1,41 @@
+#
+# Synopsys network device configuration
+#
+
+config NET_VENDOR_SYNOPSYS
+	bool "Synopsys devices"
+	default y
+	---help---
+	  If you have a network (Ethernet) device belonging to this class, say Y.
+
+	  Note that the answer to this question doesn't directly affect the
+	  kernel: saying N will just cause the configurator to skip all
+	  the questions about Synopsys devices. If you say Y, you will be asked
+	  for your specific device in the following questions.
+
+if NET_VENDOR_SYNOPSYS
+
+config DWC_XLGMAC
+	tristate "Synopsys DWC Enterprise Ethernet (XLGMAC) driver support"
+	depends on HAS_IOMEM && HAS_DMA
+	select BITREVERSE
+	select CRC32
+	---help---
+	  This driver supports the Synopsys DesignWare Cores Enterprise
+	  Ethernet (dwc-xlgmac).
+
+if DWC_XLGMAC
+
+config DWC_XLGMAC_PCI
+	tristate "XLGMAC PCI bus support"
+	depends on DWC_XLGMAC && PCI
+	---help---
+	  This selects the pci bus support for the dwc-xlgmac driver.
+	  This driver was tested on Synopsys XLGMAC IP Prototyping Kit.
+
+	  If you have a controller with this interface, say Y or M here.
+	  If unsure, say N.
+
+endif # DWC_XLGMAC
+
+endif # NET_VENDOR_SYNOPSYS
diff --git a/drivers/net/ethernet/synopsys/Makefile b/drivers/net/ethernet/synopsys/Makefile
new file mode 100644
index 000000000000..c06e2eb3be90
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/Makefile
@@ -0,0 +1,9 @@
+#
+# Makefile for the Synopsys network device drivers.
+#
+
+obj-$(CONFIG_DWC_XLGMAC) += dwc-xlgmac.o
+dwc-xlgmac-objs := dwc-xlgmac-net.o dwc-xlgmac-desc.o \
+		   dwc-xlgmac-hw.o dwc-xlgmac-common.o
+
+dwc-xlgmac-$(CONFIG_DWC_XLGMAC_PCI) += dwc-xlgmac-pci.o
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c
new file mode 100644
index 000000000000..07def2beabfa
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c
@@ -0,0 +1,736 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include "dwc-xlgmac.h"
+#include "dwc-xlgmac-reg.h"
+
+MODULE_LICENSE("Dual BSD/GPL");
+
+static int debug = -1;
+module_param(debug, int, 0644);
+MODULE_PARM_DESC(debug, "DWC ethernet debug level (0=none,...,16=all)");
+static const u32 default_msg_level = (NETIF_MSG_LINK | NETIF_MSG_IFDOWN |
+				      NETIF_MSG_IFUP);
+
+static unsigned char dev_addr[6] = {0, 0x55, 0x7b, 0xb5, 0x7d, 0xf7};
+
+static void xlgmac_read_mac_addr(struct xlgmac_pdata *pdata)
+{
+	struct net_device *netdev = pdata->netdev;
+
+	/* Currently it uses a static mac address for test */
+	memcpy(pdata->mac_addr, dev_addr, netdev->addr_len);
+}
+
+static void xlgmac_default_config(struct xlgmac_pdata *pdata)
+{
+	pdata->tx_osp_mode = DMA_OSP_ENABLE;
+	pdata->tx_sf_mode = MTL_TSF_ENABLE;
+	pdata->rx_sf_mode = MTL_RSF_DISABLE;
+	pdata->pblx8 = DMA_PBL_X8_ENABLE;
+	pdata->tx_pbl = DMA_PBL_32;
+	pdata->rx_pbl = DMA_PBL_32;
+	pdata->tx_threshold = MTL_TX_THRESHOLD_128;
+	pdata->rx_threshold = MTL_RX_THRESHOLD_128;
+	pdata->tx_pause = 1;
+	pdata->rx_pause = 1;
+	pdata->phy_speed = SPEED_25000;
+	pdata->sysclk_rate = XLGMAC_SYSCLOCK;
+
+	strlcpy(pdata->drv_name, XLGMAC_DRV_NAME, sizeof(pdata->drv_name));
+	strlcpy(pdata->drv_ver, XLGMAC_DRV_VERSION, sizeof(pdata->drv_ver));
+}
+
+static void xlgmac_init_all_ops(struct xlgmac_pdata *pdata)
+{
+	xlgmac_init_desc_ops(&pdata->desc_ops);
+	xlgmac_init_hw_ops(&pdata->hw_ops);
+}
+
+static int xlgmac_init(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	struct net_device *netdev = pdata->netdev;
+	unsigned int i;
+	int ret;
+
+	/* Set default configuration data */
+	xlgmac_default_config(pdata);
+
+	/* Set irq, base_addr, MAC address, */
+	netdev->irq = pdata->dev_irq;
+	netdev->base_addr = (unsigned long)pdata->mac_regs;
+	xlgmac_read_mac_addr(pdata);
+	memcpy(netdev->dev_addr, pdata->mac_addr, netdev->addr_len);
+
+	/* Set all the function pointers */
+	xlgmac_init_all_ops(pdata);
+
+	/* Issue software reset to device */
+	hw_ops->exit(pdata);
+
+	/* Populate the hardware features */
+	xlgmac_get_all_hw_features(pdata);
+	xlgmac_print_all_hw_features(pdata);
+
+	/* TODO: Set the PHY mode to XLGMII */
+
+	/* Set the DMA mask */
+	ret = dma_set_mask_and_coherent(pdata->dev,
+					DMA_BIT_MASK(pdata->hw_feat.dma_width));
+	if (ret) {
+		dev_err(pdata->dev, "dma_set_mask_and_coherent failed\n");
+		return ret;
+	}
+
+	/* Channel and ring params initializtion
+	 *  pdata->channel_count;
+	 *  pdata->tx_ring_count;
+	 *  pdata->rx_ring_count;
+	 *  pdata->tx_desc_count;
+	 *  pdata->rx_desc_count;
+	 */
+	BUILD_BUG_ON_NOT_POWER_OF_2(XLGMAC_TX_DESC_CNT);
+	pdata->tx_desc_count = XLGMAC_TX_DESC_CNT;
+	if (pdata->tx_desc_count & (pdata->tx_desc_count - 1)) {
+		dev_err(pdata->dev, "tx descriptor count (%d) is not valid\n",
+			pdata->tx_desc_count);
+		ret = -EINVAL;
+		return ret;
+	}
+	BUILD_BUG_ON_NOT_POWER_OF_2(XLGMAC_RX_DESC_CNT);
+	pdata->rx_desc_count = XLGMAC_RX_DESC_CNT;
+	if (pdata->rx_desc_count & (pdata->rx_desc_count - 1)) {
+		dev_err(pdata->dev, "rx descriptor count (%d) is not valid\n",
+			pdata->rx_desc_count);
+		ret = -EINVAL;
+		return ret;
+	}
+
+	pdata->tx_ring_count = min_t(unsigned int, num_online_cpus(),
+				     pdata->hw_feat.tx_ch_cnt);
+	pdata->tx_ring_count = min_t(unsigned int, pdata->tx_ring_count,
+				     pdata->hw_feat.tx_q_cnt);
+	pdata->tx_q_count = pdata->tx_ring_count;
+	ret = netif_set_real_num_tx_queues(netdev, pdata->tx_q_count);
+	if (ret) {
+		dev_err(pdata->dev, "error setting real tx queue count\n");
+		return ret;
+	}
+
+	pdata->rx_ring_count = min_t(unsigned int,
+				     netif_get_num_default_rss_queues(),
+				     pdata->hw_feat.rx_ch_cnt);
+	pdata->rx_ring_count = min_t(unsigned int, pdata->rx_ring_count,
+				     pdata->hw_feat.rx_q_cnt);
+	pdata->rx_q_count = pdata->rx_ring_count;
+	ret = netif_set_real_num_rx_queues(netdev, pdata->rx_q_count);
+	if (ret) {
+		dev_err(pdata->dev, "error setting real rx queue count\n");
+		return ret;
+	}
+
+	pdata->channel_count =
+		max_t(unsigned int, pdata->tx_ring_count, pdata->rx_ring_count);
+
+	/* Initialize RSS hash key and lookup table */
+	netdev_rss_key_fill(pdata->rss_key, sizeof(pdata->rss_key));
+
+	for (i = 0; i < XLGMAC_RSS_MAX_TABLE_SIZE; i++)
+		pdata->rss_table[i] = XLGMAC_SET_REG_BITS(
+					pdata->rss_table[i],
+					MAC_RSSDR_DMCH_POS,
+					MAC_RSSDR_DMCH_LEN,
+					i % pdata->rx_ring_count);
+
+	pdata->rss_options = XLGMAC_SET_REG_BITS(
+				pdata->rss_options,
+				MAC_RSSCR_IP2TE_POS,
+				MAC_RSSCR_IP2TE_LEN, 1);
+	pdata->rss_options = XLGMAC_SET_REG_BITS(
+				pdata->rss_options,
+				MAC_RSSCR_TCP4TE_POS,
+				MAC_RSSCR_TCP4TE_LEN, 1);
+	pdata->rss_options = XLGMAC_SET_REG_BITS(
+				pdata->rss_options,
+				MAC_RSSCR_UDP4TE_POS,
+				MAC_RSSCR_UDP4TE_LEN, 1);
+
+	/* Set device operations */
+	netdev->netdev_ops = xlgmac_get_netdev_ops();
+
+	/* Set device features */
+	if (pdata->hw_feat.tso) {
+		netdev->hw_features = NETIF_F_TSO;
+		netdev->hw_features |= NETIF_F_TSO6;
+		netdev->hw_features |= NETIF_F_SG;
+		netdev->hw_features |= NETIF_F_IP_CSUM;
+		netdev->hw_features |= NETIF_F_IPV6_CSUM;
+	} else if (pdata->hw_feat.tx_coe) {
+		netdev->hw_features = NETIF_F_IP_CSUM;
+		netdev->hw_features |= NETIF_F_IPV6_CSUM;
+	}
+
+	if (pdata->hw_feat.rx_coe) {
+		netdev->hw_features |= NETIF_F_RXCSUM;
+		netdev->hw_features |= NETIF_F_GRO;
+	}
+
+	if (pdata->hw_feat.rss)
+		netdev->hw_features |= NETIF_F_RXHASH;
+
+	netdev->vlan_features |= netdev->hw_features;
+
+	netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
+	if (pdata->hw_feat.sa_vlan_ins)
+		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX;
+	if (pdata->hw_feat.vlhash)
+		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	netdev->features |= netdev->hw_features;
+	pdata->netdev_features = netdev->features;
+
+	netdev->priv_flags |= IFF_UNICAST_FLT;
+
+	/* Use default watchdog timeout */
+	netdev->watchdog_timeo = 0;
+
+	/* Tx coalesce parameters initialization */
+	pdata->tx_usecs = XLGMAC_INIT_DMA_TX_USECS;
+	pdata->tx_frames = XLGMAC_INIT_DMA_TX_FRAMES;
+
+	/* Rx coalesce parameters initialization */
+	pdata->rx_riwt = hw_ops->usec_to_riwt(pdata, XLGMAC_INIT_DMA_RX_USECS);
+	pdata->rx_usecs = XLGMAC_INIT_DMA_RX_USECS;
+	pdata->rx_frames = XLGMAC_INIT_DMA_RX_FRAMES;
+
+	return 0;
+}
+
+int xlgmac_drv_probe(struct device *dev, struct xlgmac_resources *res)
+{
+	struct xlgmac_pdata *pdata;
+	struct net_device *netdev;
+	int ret;
+
+	netdev = alloc_etherdev_mq(sizeof(struct xlgmac_pdata),
+				   XLGMAC_MAX_DMA_CHANNELS);
+
+	if (!netdev) {
+		dev_err(dev, "alloc_etherdev failed\n");
+		return -ENOMEM;
+	}
+
+	SET_NETDEV_DEV(netdev, dev);
+	dev_set_drvdata(dev, netdev);
+	pdata = netdev_priv(netdev);
+	pdata->dev = dev;
+	pdata->netdev = netdev;
+
+	pdata->dev_irq = res->irq;
+	pdata->mac_regs = res->addr;
+
+	mutex_init(&pdata->rss_mutex);
+	pdata->msg_enable = netif_msg_init(debug, default_msg_level);
+
+	ret = xlgmac_init(pdata);
+	if (ret) {
+		dev_err(dev, "xlgmac init failed\n");
+		goto err_free_netdev;
+	}
+
+	ret = register_netdev(netdev);
+	if (ret) {
+		dev_err(dev, "net device registration failed\n");
+		goto err_free_netdev;
+	}
+
+	return 0;
+
+err_free_netdev:
+	free_netdev(netdev);
+
+	return ret;
+}
+
+int xlgmac_drv_remove(struct device *dev)
+{
+	struct net_device *netdev = dev_get_drvdata(dev);
+
+	unregister_netdev(netdev);
+	free_netdev(netdev);
+
+	return 0;
+}
+
+void xlgmac_dump_tx_desc(struct xlgmac_pdata *pdata,
+			 struct xlgmac_ring *ring,
+			 unsigned int idx,
+			 unsigned int count,
+			 unsigned int flag)
+{
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_dma_desc *dma_desc;
+
+	while (count--) {
+		desc_data = XLGMAC_GET_DESC_DATA(ring, idx);
+		dma_desc = desc_data->dma_desc;
+
+		netdev_dbg(pdata->netdev, "TX: dma_desc=%p, dma_desc_addr=%pad\n",
+			   desc_data->dma_desc, &desc_data->dma_desc_addr);
+		netdev_dbg(pdata->netdev,
+			   "TX_NORMAL_DESC[%d %s] = %08x:%08x:%08x:%08x\n", idx,
+			   (flag == 1) ? "QUEUED FOR TX" : "TX BY DEVICE",
+			   le32_to_cpu(dma_desc->desc0),
+			   le32_to_cpu(dma_desc->desc1),
+			   le32_to_cpu(dma_desc->desc2),
+			   le32_to_cpu(dma_desc->desc3));
+
+		idx++;
+	}
+}
+
+void xlgmac_dump_rx_desc(struct xlgmac_pdata *pdata,
+			 struct xlgmac_ring *ring,
+			 unsigned int idx)
+{
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_dma_desc *dma_desc;
+
+	desc_data = XLGMAC_GET_DESC_DATA(ring, idx);
+	dma_desc = desc_data->dma_desc;
+
+	netdev_dbg(pdata->netdev, "RX: dma_desc=%p, dma_desc_addr=%pad\n",
+		   desc_data->dma_desc, &desc_data->dma_desc_addr);
+	netdev_dbg(pdata->netdev,
+		   "RX_NORMAL_DESC[%d RX BY DEVICE] = %08x:%08x:%08x:%08x\n",
+		   idx,
+		   le32_to_cpu(dma_desc->desc0),
+		   le32_to_cpu(dma_desc->desc1),
+		   le32_to_cpu(dma_desc->desc2),
+		   le32_to_cpu(dma_desc->desc3));
+}
+
+void xlgmac_print_pkt(struct net_device *netdev,
+		      struct sk_buff *skb, bool tx_rx)
+{
+	struct ethhdr *eth = (struct ethhdr *)skb->data;
+	unsigned char *buf = skb->data;
+	unsigned char buffer[128];
+	unsigned int i, j;
+
+	netdev_dbg(netdev, "\n************** SKB dump ****************\n");
+
+	netdev_dbg(netdev, "%s packet of %d bytes\n",
+		   (tx_rx ? "TX" : "RX"), skb->len);
+
+	netdev_dbg(netdev, "Dst MAC addr: %pM\n", eth->h_dest);
+	netdev_dbg(netdev, "Src MAC addr: %pM\n", eth->h_source);
+	netdev_dbg(netdev, "Protocol: %#06hx\n", ntohs(eth->h_proto));
+
+	for (i = 0, j = 0; i < skb->len;) {
+		j += snprintf(buffer + j, sizeof(buffer) - j, "%02hhx",
+			      buf[i++]);
+
+		if ((i % 32) == 0) {
+			netdev_dbg(netdev, "  %#06x: %s\n", i - 32, buffer);
+			j = 0;
+		} else if ((i % 16) == 0) {
+			buffer[j++] = ' ';
+			buffer[j++] = ' ';
+		} else if ((i % 4) == 0) {
+			buffer[j++] = ' ';
+		}
+	}
+	if (i % 32)
+		netdev_dbg(netdev, "  %#06x: %s\n", i - (i % 32), buffer);
+
+	netdev_dbg(netdev, "\n************** SKB dump ****************\n");
+}
+
+void xlgmac_get_all_hw_features(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_hw_features *hw_feat = &pdata->hw_feat;
+	unsigned int mac_hfr0, mac_hfr1, mac_hfr2;
+
+	mac_hfr0 = readl(pdata->mac_regs + MAC_HWF0R);
+	mac_hfr1 = readl(pdata->mac_regs + MAC_HWF1R);
+	mac_hfr2 = readl(pdata->mac_regs + MAC_HWF2R);
+
+	memset(hw_feat, 0, sizeof(*hw_feat));
+
+	hw_feat->version = readl(pdata->mac_regs + MAC_VR);
+
+	/* Hardware feature register 0 */
+	hw_feat->phyifsel    = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_PHYIFSEL_POS,
+						MAC_HWF0R_PHYIFSEL_LEN);
+	hw_feat->vlhash      = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_VLHASH_POS,
+						MAC_HWF0R_VLHASH_LEN);
+	hw_feat->sma         = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_SMASEL_POS,
+						MAC_HWF0R_SMASEL_LEN);
+	hw_feat->rwk         = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_RWKSEL_POS,
+						MAC_HWF0R_RWKSEL_LEN);
+	hw_feat->mgk         = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_MGKSEL_POS,
+						MAC_HWF0R_MGKSEL_LEN);
+	hw_feat->mmc         = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_MMCSEL_POS,
+						MAC_HWF0R_MMCSEL_LEN);
+	hw_feat->aoe         = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_ARPOFFSEL_POS,
+						MAC_HWF0R_ARPOFFSEL_LEN);
+	hw_feat->ts          = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_TSSEL_POS,
+						MAC_HWF0R_TSSEL_LEN);
+	hw_feat->eee         = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_EEESEL_POS,
+						MAC_HWF0R_EEESEL_LEN);
+	hw_feat->tx_coe      = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_TXCOESEL_POS,
+						MAC_HWF0R_TXCOESEL_LEN);
+	hw_feat->rx_coe      = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_RXCOESEL_POS,
+						MAC_HWF0R_RXCOESEL_LEN);
+	hw_feat->addn_mac    = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_ADDMACADRSEL_POS,
+						MAC_HWF0R_ADDMACADRSEL_LEN);
+	hw_feat->ts_src      = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_TSSTSSEL_POS,
+						MAC_HWF0R_TSSTSSEL_LEN);
+	hw_feat->sa_vlan_ins = XLGMAC_GET_REG_BITS(mac_hfr0,
+						MAC_HWF0R_SAVLANINS_POS,
+						MAC_HWF0R_SAVLANINS_LEN);
+
+	/* Hardware feature register 1 */
+	hw_feat->rx_fifo_size  = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_RXFIFOSIZE_POS,
+						MAC_HWF1R_RXFIFOSIZE_LEN);
+	hw_feat->tx_fifo_size  = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_TXFIFOSIZE_POS,
+						MAC_HWF1R_TXFIFOSIZE_LEN);
+	hw_feat->adv_ts_hi     = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_ADVTHWORD_POS,
+						MAC_HWF1R_ADVTHWORD_LEN);
+	hw_feat->dma_width     = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_ADDR64_POS,
+						MAC_HWF1R_ADDR64_LEN);
+	hw_feat->dcb           = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_DCBEN_POS,
+						MAC_HWF1R_DCBEN_LEN);
+	hw_feat->sph           = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_SPHEN_POS,
+						MAC_HWF1R_SPHEN_LEN);
+	hw_feat->tso           = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_TSOEN_POS,
+						MAC_HWF1R_TSOEN_LEN);
+	hw_feat->dma_debug     = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_DBGMEMA_POS,
+						MAC_HWF1R_DBGMEMA_LEN);
+	hw_feat->rss           = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_RSSEN_POS,
+						MAC_HWF1R_RSSEN_LEN);
+	hw_feat->tc_cnt	       = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_NUMTC_POS,
+						MAC_HWF1R_NUMTC_LEN);
+	hw_feat->hash_table_size = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_HASHTBLSZ_POS,
+						MAC_HWF1R_HASHTBLSZ_LEN);
+	hw_feat->l3l4_filter_num = XLGMAC_GET_REG_BITS(mac_hfr1,
+						MAC_HWF1R_L3L4FNUM_POS,
+						MAC_HWF1R_L3L4FNUM_LEN);
+
+	/* Hardware feature register 2 */
+	hw_feat->rx_q_cnt     = XLGMAC_GET_REG_BITS(mac_hfr2,
+						MAC_HWF2R_RXQCNT_POS,
+						MAC_HWF2R_RXQCNT_LEN);
+	hw_feat->tx_q_cnt     = XLGMAC_GET_REG_BITS(mac_hfr2,
+						MAC_HWF2R_TXQCNT_POS,
+						MAC_HWF2R_TXQCNT_LEN);
+	hw_feat->rx_ch_cnt    = XLGMAC_GET_REG_BITS(mac_hfr2,
+						MAC_HWF2R_RXCHCNT_POS,
+						MAC_HWF2R_RXCHCNT_LEN);
+	hw_feat->tx_ch_cnt    = XLGMAC_GET_REG_BITS(mac_hfr2,
+						MAC_HWF2R_TXCHCNT_POS,
+						MAC_HWF2R_TXCHCNT_LEN);
+	hw_feat->pps_out_num  = XLGMAC_GET_REG_BITS(mac_hfr2,
+						MAC_HWF2R_PPSOUTNUM_POS,
+						MAC_HWF2R_PPSOUTNUM_LEN);
+	hw_feat->aux_snap_num = XLGMAC_GET_REG_BITS(mac_hfr2,
+						MAC_HWF2R_AUXSNAPNUM_POS,
+						MAC_HWF2R_AUXSNAPNUM_LEN);
+
+	/* Translate the Hash Table size into actual number */
+	switch (hw_feat->hash_table_size) {
+	case 0:
+		break;
+	case 1:
+		hw_feat->hash_table_size = 64;
+		break;
+	case 2:
+		hw_feat->hash_table_size = 128;
+		break;
+	case 3:
+		hw_feat->hash_table_size = 256;
+		break;
+	}
+
+	/* Translate the address width setting into actual number */
+	switch (hw_feat->dma_width) {
+	case 0:
+		hw_feat->dma_width = 32;
+		break;
+	case 1:
+		hw_feat->dma_width = 40;
+		break;
+	case 2:
+		hw_feat->dma_width = 48;
+		break;
+	default:
+		hw_feat->dma_width = 32;
+	}
+
+	/* The Queue, Channel and TC counts are zero based so increment them
+	 * to get the actual number
+	 */
+	hw_feat->rx_q_cnt++;
+	hw_feat->tx_q_cnt++;
+	hw_feat->rx_ch_cnt++;
+	hw_feat->tx_ch_cnt++;
+	hw_feat->tc_cnt++;
+}
+
+void xlgmac_print_all_hw_features(struct xlgmac_pdata *pdata)
+{
+	char *str = NULL;
+
+	XLGMAC_PR("\n");
+	XLGMAC_PR("=====================================================\n");
+	XLGMAC_PR("\n");
+	XLGMAC_PR("HW support following features\n");
+	XLGMAC_PR("\n");
+	/* HW Feature Register0 */
+	XLGMAC_PR("VLAN Hash Filter Selected                   : %s\n",
+		  pdata->hw_feat.vlhash ? "YES" : "NO");
+	XLGMAC_PR("SMA (MDIO) Interface                        : %s\n",
+		  pdata->hw_feat.sma ? "YES" : "NO");
+	XLGMAC_PR("PMT Remote Wake-up Packet Enable            : %s\n",
+		  pdata->hw_feat.rwk ? "YES" : "NO");
+	XLGMAC_PR("PMT Magic Packet Enable                     : %s\n",
+		  pdata->hw_feat.mgk ? "YES" : "NO");
+	XLGMAC_PR("RMON/MMC Module Enable                      : %s\n",
+		  pdata->hw_feat.mmc ? "YES" : "NO");
+	XLGMAC_PR("ARP Offload Enabled                         : %s\n",
+		  pdata->hw_feat.aoe ? "YES" : "NO");
+	XLGMAC_PR("IEEE 1588-2008 Timestamp Enabled            : %s\n",
+		  pdata->hw_feat.ts ? "YES" : "NO");
+	XLGMAC_PR("Energy Efficient Ethernet Enabled           : %s\n",
+		  pdata->hw_feat.eee ? "YES" : "NO");
+	XLGMAC_PR("Transmit Checksum Offload Enabled           : %s\n",
+		  pdata->hw_feat.tx_coe ? "YES" : "NO");
+	XLGMAC_PR("Receive Checksum Offload Enabled            : %s\n",
+		  pdata->hw_feat.rx_coe ? "YES" : "NO");
+	XLGMAC_PR("Additional MAC Addresses 1-31 Selected      : %s\n",
+		  pdata->hw_feat.addn_mac ? "YES" : "NO");
+
+	switch (pdata->hw_feat.ts_src) {
+	case 0:
+		str = "RESERVED";
+		break;
+	case 1:
+		str = "INTERNAL";
+		break;
+	case 2:
+		str = "EXTERNAL";
+		break;
+	case 3:
+		str = "BOTH";
+		break;
+	}
+	XLGMAC_PR("Timestamp System Time Source                : %s\n", str);
+
+	XLGMAC_PR("Source Address or VLAN Insertion Enable     : %s\n",
+		  pdata->hw_feat.sa_vlan_ins ? "YES" : "NO");
+
+	/* HW Feature Register1 */
+	switch (pdata->hw_feat.rx_fifo_size) {
+	case 0:
+		str = "128 bytes";
+		break;
+	case 1:
+		str = "256 bytes";
+		break;
+	case 2:
+		str = "512 bytes";
+		break;
+	case 3:
+		str = "1 KBytes";
+		break;
+	case 4:
+		str = "2 KBytes";
+		break;
+	case 5:
+		str = "4 KBytes";
+		break;
+	case 6:
+		str = "8 KBytes";
+		break;
+	case 7:
+		str = "16 KBytes";
+		break;
+	case 8:
+		str = "32 kBytes";
+		break;
+	case 9:
+		str = "64 KBytes";
+		break;
+	case 10:
+		str = "128 KBytes";
+		break;
+	case 11:
+		str = "256 KBytes";
+		break;
+	default:
+		str = "RESERVED";
+	}
+	XLGMAC_PR("MTL Receive FIFO Size                       : %s\n", str);
+
+	switch (pdata->hw_feat.tx_fifo_size) {
+	case 0:
+		str = "128 bytes";
+		break;
+	case 1:
+		str = "256 bytes";
+		break;
+	case 2:
+		str = "512 bytes";
+		break;
+	case 3:
+		str = "1 KBytes";
+		break;
+	case 4:
+		str = "2 KBytes";
+		break;
+	case 5:
+		str = "4 KBytes";
+		break;
+	case 6:
+		str = "8 KBytes";
+		break;
+	case 7:
+		str = "16 KBytes";
+		break;
+	case 8:
+		str = "32 kBytes";
+		break;
+	case 9:
+		str = "64 KBytes";
+		break;
+	case 10:
+		str = "128 KBytes";
+		break;
+	case 11:
+		str = "256 KBytes";
+		break;
+	default:
+		str = "RESERVED";
+	}
+	XLGMAC_PR("MTL Transmit FIFO Size                      : %s\n", str);
+
+	XLGMAC_PR("IEEE 1588 High Word Register Enable         : %s\n",
+		  pdata->hw_feat.adv_ts_hi ? "YES" : "NO");
+	XLGMAC_PR("Address width                               : %u\n",
+		  pdata->hw_feat.dma_width);
+	XLGMAC_PR("DCB Feature Enable                          : %s\n",
+		  pdata->hw_feat.dcb ? "YES" : "NO");
+	XLGMAC_PR("Split Header Feature Enable                 : %s\n",
+		  pdata->hw_feat.sph ? "YES" : "NO");
+	XLGMAC_PR("TCP Segmentation Offload Enable             : %s\n",
+		  pdata->hw_feat.tso ? "YES" : "NO");
+	XLGMAC_PR("DMA Debug Registers Enabled                 : %s\n",
+		  pdata->hw_feat.dma_debug ? "YES" : "NO");
+	XLGMAC_PR("RSS Feature Enabled                         : %s\n",
+		  pdata->hw_feat.rss ? "YES" : "NO");
+	XLGMAC_PR("Number of Traffic classes                   : %u\n",
+		  (pdata->hw_feat.tc_cnt));
+	XLGMAC_PR("Hash Table Size                             : %u\n",
+		  pdata->hw_feat.hash_table_size);
+	XLGMAC_PR("Total number of L3 or L4 Filters            : %u\n",
+		  pdata->hw_feat.l3l4_filter_num);
+
+	/* HW Feature Register2 */
+	XLGMAC_PR("Number of MTL Receive Queues                : %u\n",
+		  pdata->hw_feat.rx_q_cnt);
+	XLGMAC_PR("Number of MTL Transmit Queues               : %u\n",
+		  pdata->hw_feat.tx_q_cnt);
+	XLGMAC_PR("Number of DMA Receive Channels              : %u\n",
+		  pdata->hw_feat.rx_ch_cnt);
+	XLGMAC_PR("Number of DMA Transmit Channels             : %u\n",
+		  pdata->hw_feat.tx_ch_cnt);
+
+	switch (pdata->hw_feat.pps_out_num) {
+	case 0:
+		str = "No PPS output";
+		break;
+	case 1:
+		str = "1 PPS output";
+		break;
+	case 2:
+		str = "2 PPS output";
+		break;
+	case 3:
+		str = "3 PPS output";
+		break;
+	case 4:
+		str = "4 PPS output";
+		break;
+	default:
+		str = "RESERVED";
+	}
+	XLGMAC_PR("Number of PPS Outputs                       : %s\n", str);
+
+	switch (pdata->hw_feat.aux_snap_num) {
+	case 0:
+		str = "No auxiliary input";
+		break;
+	case 1:
+		str = "1 auxiliary input";
+		break;
+	case 2:
+		str = "2 auxiliary input";
+		break;
+	case 3:
+		str = "3 auxiliary input";
+		break;
+	case 4:
+		str = "4 auxiliary input";
+		break;
+	default:
+		str = "RESERVED";
+	}
+	XLGMAC_PR("Number of Auxiliary Snapshot Inputs         : %s", str);
+
+	XLGMAC_PR("\n");
+	XLGMAC_PR("=====================================================\n");
+	XLGMAC_PR("\n");
+}
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c
new file mode 100644
index 000000000000..e9672b1f9968
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c
@@ -0,0 +1,644 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#include "dwc-xlgmac.h"
+#include "dwc-xlgmac-reg.h"
+
+static void xlgmac_unmap_desc_data(struct xlgmac_pdata *pdata,
+				   struct xlgmac_desc_data *desc_data)
+{
+	if (desc_data->skb_dma) {
+		if (desc_data->mapped_as_page) {
+			dma_unmap_page(pdata->dev, desc_data->skb_dma,
+				       desc_data->skb_dma_len, DMA_TO_DEVICE);
+		} else {
+			dma_unmap_single(pdata->dev, desc_data->skb_dma,
+					 desc_data->skb_dma_len, DMA_TO_DEVICE);
+		}
+		desc_data->skb_dma = 0;
+		desc_data->skb_dma_len = 0;
+	}
+
+	if (desc_data->skb) {
+		dev_kfree_skb_any(desc_data->skb);
+		desc_data->skb = NULL;
+	}
+
+	if (desc_data->rx.hdr.pa.pages)
+		put_page(desc_data->rx.hdr.pa.pages);
+
+	if (desc_data->rx.hdr.pa_unmap.pages) {
+		dma_unmap_page(pdata->dev, desc_data->rx.hdr.pa_unmap.pages_dma,
+			       desc_data->rx.hdr.pa_unmap.pages_len,
+			       DMA_FROM_DEVICE);
+		put_page(desc_data->rx.hdr.pa_unmap.pages);
+	}
+
+	if (desc_data->rx.buf.pa.pages)
+		put_page(desc_data->rx.buf.pa.pages);
+
+	if (desc_data->rx.buf.pa_unmap.pages) {
+		dma_unmap_page(pdata->dev, desc_data->rx.buf.pa_unmap.pages_dma,
+			       desc_data->rx.buf.pa_unmap.pages_len,
+			       DMA_FROM_DEVICE);
+		put_page(desc_data->rx.buf.pa_unmap.pages);
+	}
+
+	memset(&desc_data->tx, 0, sizeof(desc_data->tx));
+	memset(&desc_data->rx, 0, sizeof(desc_data->rx));
+
+	desc_data->mapped_as_page = 0;
+
+	if (desc_data->state_saved) {
+		desc_data->state_saved = 0;
+		desc_data->state.skb = NULL;
+		desc_data->state.len = 0;
+		desc_data->state.error = 0;
+	}
+}
+
+static void xlgmac_free_ring(struct xlgmac_pdata *pdata,
+			     struct xlgmac_ring *ring)
+{
+	struct xlgmac_desc_data *desc_data;
+	unsigned int i;
+
+	if (!ring)
+		return;
+
+	if (ring->desc_data_head) {
+		for (i = 0; i < ring->dma_desc_count; i++) {
+			desc_data = XLGMAC_GET_DESC_DATA(ring, i);
+			xlgmac_unmap_desc_data(pdata, desc_data);
+		}
+
+		kfree(ring->desc_data_head);
+		ring->desc_data_head = NULL;
+	}
+
+	if (ring->rx_hdr_pa.pages) {
+		dma_unmap_page(pdata->dev, ring->rx_hdr_pa.pages_dma,
+			       ring->rx_hdr_pa.pages_len, DMA_FROM_DEVICE);
+		put_page(ring->rx_hdr_pa.pages);
+
+		ring->rx_hdr_pa.pages = NULL;
+		ring->rx_hdr_pa.pages_len = 0;
+		ring->rx_hdr_pa.pages_offset = 0;
+		ring->rx_hdr_pa.pages_dma = 0;
+	}
+
+	if (ring->rx_buf_pa.pages) {
+		dma_unmap_page(pdata->dev, ring->rx_buf_pa.pages_dma,
+			       ring->rx_buf_pa.pages_len, DMA_FROM_DEVICE);
+		put_page(ring->rx_buf_pa.pages);
+
+		ring->rx_buf_pa.pages = NULL;
+		ring->rx_buf_pa.pages_len = 0;
+		ring->rx_buf_pa.pages_offset = 0;
+		ring->rx_buf_pa.pages_dma = 0;
+	}
+
+	if (ring->dma_desc_head) {
+		dma_free_coherent(pdata->dev,
+				  (sizeof(struct xlgmac_dma_desc) *
+				  ring->dma_desc_count),
+				  ring->dma_desc_head,
+				  ring->dma_desc_head_addr);
+		ring->dma_desc_head = NULL;
+	}
+}
+
+static int xlgmac_init_ring(struct xlgmac_pdata *pdata,
+			    struct xlgmac_ring *ring,
+			    unsigned int dma_desc_count)
+{
+	if (!ring)
+		return 0;
+
+	/* Descriptors */
+	ring->dma_desc_count = dma_desc_count;
+	ring->dma_desc_head = dma_alloc_coherent(pdata->dev,
+					(sizeof(struct xlgmac_dma_desc) *
+					 dma_desc_count),
+					&ring->dma_desc_head_addr,
+					GFP_KERNEL);
+	if (!ring->dma_desc_head)
+		return -ENOMEM;
+
+	/* Array of descriptor data */
+	ring->desc_data_head = kcalloc(dma_desc_count,
+					sizeof(struct xlgmac_desc_data),
+					GFP_KERNEL);
+	if (!ring->desc_data_head)
+		return -ENOMEM;
+
+	netif_dbg(pdata, drv, pdata->netdev,
+		  "dma_desc_head=%p, dma_desc_head_addr=%pad, desc_data_head=%p\n",
+		ring->dma_desc_head,
+		&ring->dma_desc_head_addr,
+		ring->desc_data_head);
+
+	return 0;
+}
+
+static void xlgmac_free_rings(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+
+	if (!pdata->channel_head)
+		return;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		xlgmac_free_ring(pdata, channel->tx_ring);
+		xlgmac_free_ring(pdata, channel->rx_ring);
+	}
+}
+
+static int xlgmac_alloc_rings(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	int ret;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		netif_dbg(pdata, drv, pdata->netdev, "%s - Tx ring:\n",
+			  channel->name);
+
+		ret = xlgmac_init_ring(pdata, channel->tx_ring,
+				       pdata->tx_desc_count);
+
+		if (ret) {
+			netdev_alert(pdata->netdev,
+				     "error initializing Tx ring");
+			goto err_init_ring;
+		}
+
+		netif_dbg(pdata, drv, pdata->netdev, "%s - Rx ring:\n",
+			  channel->name);
+
+		ret = xlgmac_init_ring(pdata, channel->rx_ring,
+				       pdata->rx_desc_count);
+		if (ret) {
+			netdev_alert(pdata->netdev,
+				     "error initializing Rx ring\n");
+			goto err_init_ring;
+		}
+	}
+
+	return 0;
+
+err_init_ring:
+	xlgmac_free_rings(pdata);
+
+	return ret;
+}
+
+static void xlgmac_free_channels(struct xlgmac_pdata *pdata)
+{
+	if (!pdata->channel_head)
+		return;
+
+	kfree(pdata->channel_head->tx_ring);
+	pdata->channel_head->tx_ring = NULL;
+
+	kfree(pdata->channel_head->rx_ring);
+	pdata->channel_head->rx_ring = NULL;
+
+	kfree(pdata->channel_head);
+
+	pdata->channel_head = NULL;
+	pdata->channel_count = 0;
+}
+
+static int xlgmac_alloc_channels(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel_head, *channel;
+	struct xlgmac_ring *tx_ring, *rx_ring;
+	int ret = -ENOMEM;
+	unsigned int i;
+
+	channel_head = kcalloc(pdata->channel_count,
+			       sizeof(struct xlgmac_channel), GFP_KERNEL);
+	if (!channel_head)
+		return ret;
+
+	netif_dbg(pdata, drv, pdata->netdev,
+		  "channel_head=%p\n", channel_head);
+
+	tx_ring = kcalloc(pdata->tx_ring_count, sizeof(struct xlgmac_ring),
+			  GFP_KERNEL);
+	if (!tx_ring)
+		goto err_tx_ring;
+
+	rx_ring = kcalloc(pdata->rx_ring_count, sizeof(struct xlgmac_ring),
+			  GFP_KERNEL);
+	if (!rx_ring)
+		goto err_rx_ring;
+
+	for (i = 0, channel = channel_head; i < pdata->channel_count;
+		i++, channel++) {
+		snprintf(channel->name, sizeof(channel->name), "channel-%u", i);
+		channel->pdata = pdata;
+		channel->queue_index = i;
+		channel->dma_regs = pdata->mac_regs + DMA_CH_BASE +
+				    (DMA_CH_INC * i);
+
+		if (pdata->per_channel_irq) {
+			/* Get the per DMA interrupt */
+			ret = pdata->channel_irq[i];
+			if (ret < 0) {
+				netdev_err(pdata->netdev,
+					   "get_irq %u failed\n",
+					   i + 1);
+				goto err_irq;
+			}
+			channel->dma_irq = ret;
+		}
+
+		if (i < pdata->tx_ring_count)
+			channel->tx_ring = tx_ring++;
+
+		if (i < pdata->rx_ring_count)
+			channel->rx_ring = rx_ring++;
+
+		netif_dbg(pdata, drv, pdata->netdev,
+			  "%s: dma_regs=%p, tx_ring=%p, rx_ring=%p\n",
+			  channel->name, channel->dma_regs,
+			  channel->tx_ring, channel->rx_ring);
+	}
+
+	pdata->channel_head = channel_head;
+
+	return 0;
+
+err_irq:
+	kfree(rx_ring);
+
+err_rx_ring:
+	kfree(tx_ring);
+
+err_tx_ring:
+	kfree(channel_head);
+
+	return ret;
+}
+
+static void xlgmac_free_channels_and_rings(struct xlgmac_pdata *pdata)
+{
+	xlgmac_free_rings(pdata);
+
+	xlgmac_free_channels(pdata);
+}
+
+static int xlgmac_alloc_channels_and_rings(struct xlgmac_pdata *pdata)
+{
+	int ret;
+
+	ret = xlgmac_alloc_channels(pdata);
+	if (ret)
+		goto err_alloc;
+
+	ret = xlgmac_alloc_rings(pdata);
+	if (ret)
+		goto err_alloc;
+
+	return 0;
+
+err_alloc:
+	xlgmac_free_channels_and_rings(pdata);
+
+	return ret;
+}
+
+static int xlgmac_alloc_pages(struct xlgmac_pdata *pdata,
+			      struct xlgmac_page_alloc *pa,
+			      gfp_t gfp, int order)
+{
+	struct page *pages = NULL;
+	dma_addr_t pages_dma;
+
+	/* Try to obtain pages, decreasing order if necessary */
+	gfp |= __GFP_COLD | __GFP_COMP | __GFP_NOWARN;
+	while (order >= 0) {
+		pages = alloc_pages(gfp, order);
+		if (pages)
+			break;
+
+		order--;
+	}
+	if (!pages)
+		return -ENOMEM;
+
+	/* Map the pages */
+	pages_dma = dma_map_page(pdata->dev, pages, 0,
+				 PAGE_SIZE << order, DMA_FROM_DEVICE);
+	if (dma_mapping_error(pdata->dev, pages_dma)) {
+		put_page(pages);
+		return -ENOMEM;
+	}
+
+	pa->pages = pages;
+	pa->pages_len = PAGE_SIZE << order;
+	pa->pages_offset = 0;
+	pa->pages_dma = pages_dma;
+
+	return 0;
+}
+
+static void xlgmac_set_buffer_data(struct xlgmac_buffer_data *bd,
+				   struct xlgmac_page_alloc *pa,
+				   unsigned int len)
+{
+	get_page(pa->pages);
+	bd->pa = *pa;
+
+	bd->dma_base = pa->pages_dma;
+	bd->dma_off = pa->pages_offset;
+	bd->dma_len = len;
+
+	pa->pages_offset += len;
+	if ((pa->pages_offset + len) > pa->pages_len) {
+		/* This data descriptor is responsible for unmapping page(s) */
+		bd->pa_unmap = *pa;
+
+		/* Get a new allocation next time */
+		pa->pages = NULL;
+		pa->pages_len = 0;
+		pa->pages_offset = 0;
+		pa->pages_dma = 0;
+	}
+}
+
+static int xlgmac_map_rx_buffer(struct xlgmac_pdata *pdata,
+				struct xlgmac_ring *ring,
+				struct xlgmac_desc_data *desc_data)
+{
+	int order, ret;
+
+	if (!ring->rx_hdr_pa.pages) {
+		ret = xlgmac_alloc_pages(pdata, &ring->rx_hdr_pa,
+					 GFP_ATOMIC, 0);
+		if (ret)
+			return ret;
+	}
+
+	if (!ring->rx_buf_pa.pages) {
+		order = max_t(int, PAGE_ALLOC_COSTLY_ORDER - 1, 0);
+		ret = xlgmac_alloc_pages(pdata, &ring->rx_buf_pa,
+					 GFP_ATOMIC, order);
+		if (ret)
+			return ret;
+	}
+
+	/* Set up the header page info */
+	xlgmac_set_buffer_data(&desc_data->rx.hdr, &ring->rx_hdr_pa,
+			       XLGMAC_SKB_ALLOC_SIZE);
+
+	/* Set up the buffer page info */
+	xlgmac_set_buffer_data(&desc_data->rx.buf, &ring->rx_buf_pa,
+			       pdata->rx_buf_size);
+
+	return 0;
+}
+
+static void xlgmac_tx_desc_init(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_dma_desc *dma_desc;
+	struct xlgmac_channel *channel;
+	struct xlgmac_ring *ring;
+	dma_addr_t dma_desc_addr;
+	unsigned int i, j;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		ring = channel->tx_ring;
+		if (!ring)
+			break;
+
+		dma_desc = ring->dma_desc_head;
+		dma_desc_addr = ring->dma_desc_head_addr;
+
+		for (j = 0; j < ring->dma_desc_count; j++) {
+			desc_data = XLGMAC_GET_DESC_DATA(ring, j);
+
+			desc_data->dma_desc = dma_desc;
+			desc_data->dma_desc_addr = dma_desc_addr;
+
+			dma_desc++;
+			dma_desc_addr += sizeof(struct xlgmac_dma_desc);
+		}
+
+		ring->cur = 0;
+		ring->dirty = 0;
+		memset(&ring->tx, 0, sizeof(ring->tx));
+
+		hw_ops->tx_desc_init(channel);
+	}
+}
+
+static void xlgmac_rx_desc_init(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_dma_desc *dma_desc;
+	struct xlgmac_channel *channel;
+	struct xlgmac_ring *ring;
+	dma_addr_t dma_desc_addr;
+	unsigned int i, j;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		ring = channel->rx_ring;
+		if (!ring)
+			break;
+
+		dma_desc = ring->dma_desc_head;
+		dma_desc_addr = ring->dma_desc_head_addr;
+
+		for (j = 0; j < ring->dma_desc_count; j++) {
+			desc_data = XLGMAC_GET_DESC_DATA(ring, j);
+
+			desc_data->dma_desc = dma_desc;
+			desc_data->dma_desc_addr = dma_desc_addr;
+
+			if (xlgmac_map_rx_buffer(pdata, ring, desc_data))
+				break;
+
+			dma_desc++;
+			dma_desc_addr += sizeof(struct xlgmac_dma_desc);
+		}
+
+		ring->cur = 0;
+		ring->dirty = 0;
+
+		hw_ops->rx_desc_init(channel);
+	}
+}
+
+static int xlgmac_map_tx_skb(struct xlgmac_channel *channel,
+			     struct sk_buff *skb)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct xlgmac_ring *ring = channel->tx_ring;
+	unsigned int start_index, cur_index;
+	struct xlgmac_desc_data *desc_data;
+	unsigned int offset, datalen, len;
+	struct xlgmac_pkt_info *pkt_info;
+	struct skb_frag_struct *frag;
+	unsigned int tso, vlan;
+	dma_addr_t skb_dma;
+	unsigned int i;
+
+	offset = 0;
+	start_index = ring->cur;
+	cur_index = ring->cur;
+
+	pkt_info = &ring->pkt_info;
+	pkt_info->desc_count = 0;
+	pkt_info->length = 0;
+
+	tso = XLGMAC_GET_REG_BITS(pkt_info->attributes,
+				  TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS,
+				  TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN);
+	vlan = XLGMAC_GET_REG_BITS(pkt_info->attributes,
+				   TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS,
+				   TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN);
+
+	/* Save space for a context descriptor if needed */
+	if ((tso && (pkt_info->mss != ring->tx.cur_mss)) ||
+	    (vlan && (pkt_info->vlan_ctag != ring->tx.cur_vlan_ctag)))
+		cur_index++;
+	desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+
+	if (tso) {
+		/* Map the TSO header */
+		skb_dma = dma_map_single(pdata->dev, skb->data,
+					 pkt_info->header_len, DMA_TO_DEVICE);
+		if (dma_mapping_error(pdata->dev, skb_dma)) {
+			netdev_alert(pdata->netdev, "dma_map_single failed\n");
+			goto err_out;
+		}
+		desc_data->skb_dma = skb_dma;
+		desc_data->skb_dma_len = pkt_info->header_len;
+		netif_dbg(pdata, tx_queued, pdata->netdev,
+			  "skb header: index=%u, dma=%pad, len=%u\n",
+			  cur_index, &skb_dma, pkt_info->header_len);
+
+		offset = pkt_info->header_len;
+
+		pkt_info->length += pkt_info->header_len;
+
+		cur_index++;
+		desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+	}
+
+	/* Map the (remainder of the) packet */
+	for (datalen = skb_headlen(skb) - offset; datalen; ) {
+		len = min_t(unsigned int, datalen, XLGMAC_TX_MAX_BUF_SIZE);
+
+		skb_dma = dma_map_single(pdata->dev, skb->data + offset, len,
+					 DMA_TO_DEVICE);
+		if (dma_mapping_error(pdata->dev, skb_dma)) {
+			netdev_alert(pdata->netdev, "dma_map_single failed\n");
+			goto err_out;
+		}
+		desc_data->skb_dma = skb_dma;
+		desc_data->skb_dma_len = len;
+		netif_dbg(pdata, tx_queued, pdata->netdev,
+			  "skb data: index=%u, dma=%pad, len=%u\n",
+			  cur_index, &skb_dma, len);
+
+		datalen -= len;
+		offset += len;
+
+		pkt_info->length += len;
+
+		cur_index++;
+		desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+	}
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		netif_dbg(pdata, tx_queued, pdata->netdev,
+			  "mapping frag %u\n", i);
+
+		frag = &skb_shinfo(skb)->frags[i];
+		offset = 0;
+
+		for (datalen = skb_frag_size(frag); datalen; ) {
+			len = min_t(unsigned int, datalen,
+				    XLGMAC_TX_MAX_BUF_SIZE);
+
+			skb_dma = skb_frag_dma_map(pdata->dev, frag, offset,
+						   len, DMA_TO_DEVICE);
+			if (dma_mapping_error(pdata->dev, skb_dma)) {
+				netdev_alert(pdata->netdev,
+					     "skb_frag_dma_map failed\n");
+				goto err_out;
+			}
+			desc_data->skb_dma = skb_dma;
+			desc_data->skb_dma_len = len;
+			desc_data->mapped_as_page = 1;
+			netif_dbg(pdata, tx_queued, pdata->netdev,
+				  "skb frag: index=%u, dma=%pad, len=%u\n",
+				  cur_index, &skb_dma, len);
+
+			datalen -= len;
+			offset += len;
+
+			pkt_info->length += len;
+
+			cur_index++;
+			desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+		}
+	}
+
+	/* Save the skb address in the last entry. We always have some data
+	 * that has been mapped so desc_data is always advanced past the last
+	 * piece of mapped data - use the entry pointed to by cur_index - 1.
+	 */
+	desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index - 1);
+	desc_data->skb = skb;
+
+	/* Save the number of descriptor entries used */
+	pkt_info->desc_count = cur_index - start_index;
+
+	return pkt_info->desc_count;
+
+err_out:
+	while (start_index < cur_index) {
+		desc_data = XLGMAC_GET_DESC_DATA(ring, start_index++);
+		xlgmac_unmap_desc_data(pdata, desc_data);
+	}
+
+	return 0;
+}
+
+void xlgmac_init_desc_ops(struct xlgmac_desc_ops *desc_ops)
+{
+	desc_ops->alloc_channles_and_rings = xlgmac_alloc_channels_and_rings;
+	desc_ops->free_channels_and_rings = xlgmac_free_channels_and_rings;
+	desc_ops->map_tx_skb = xlgmac_map_tx_skb;
+	desc_ops->map_rx_buffer = xlgmac_map_rx_buffer;
+	desc_ops->unmap_desc_data = xlgmac_unmap_desc_data;
+	desc_ops->tx_desc_init = xlgmac_tx_desc_init;
+	desc_ops->rx_desc_init = xlgmac_rx_desc_init;
+}
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
new file mode 100644
index 000000000000..0dec1dcf8457
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
@@ -0,0 +1,3145 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#include <linux/phy.h>
+#include <linux/mdio.h>
+#include <linux/clk.h>
+#include <linux/bitrev.h>
+#include <linux/crc32.h>
+#include <linux/dcbnl.h>
+
+#include "dwc-xlgmac.h"
+#include "dwc-xlgmac-reg.h"
+
+static int xlgmac_tx_complete(struct xlgmac_dma_desc *dma_desc)
+{
+	return !XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				TX_NORMAL_DESC3_OWN_POS,
+				TX_NORMAL_DESC3_OWN_LEN);
+}
+
+static int xlgmac_disable_rx_csum(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_RCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_IPC_POS,
+				     MAC_RCR_IPC_LEN, 0);
+	writel(regval, pdata->mac_regs + MAC_RCR);
+
+	return 0;
+}
+
+static int xlgmac_enable_rx_csum(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_RCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_IPC_POS,
+				     MAC_RCR_IPC_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_RCR);
+
+	return 0;
+}
+
+static int xlgmac_set_mac_address(struct xlgmac_pdata *pdata, u8 *addr)
+{
+	unsigned int mac_addr_hi, mac_addr_lo;
+
+	mac_addr_hi = (addr[5] <<  8) | (addr[4] <<  0);
+	mac_addr_lo = (addr[3] << 24) | (addr[2] << 16) |
+		      (addr[1] <<  8) | (addr[0] <<  0);
+
+	writel(mac_addr_hi, pdata->mac_regs + MAC_MACA0HR);
+	writel(mac_addr_lo, pdata->mac_regs + MAC_MACA0LR);
+
+	return 0;
+}
+
+static void xlgmac_set_mac_reg(struct xlgmac_pdata *pdata,
+			       struct netdev_hw_addr *ha,
+			       unsigned int *mac_reg)
+{
+	unsigned int mac_addr_hi, mac_addr_lo;
+	u8 *mac_addr;
+
+	mac_addr_lo = 0;
+	mac_addr_hi = 0;
+
+	if (ha) {
+		mac_addr = (u8 *)&mac_addr_lo;
+		mac_addr[0] = ha->addr[0];
+		mac_addr[1] = ha->addr[1];
+		mac_addr[2] = ha->addr[2];
+		mac_addr[3] = ha->addr[3];
+		mac_addr = (u8 *)&mac_addr_hi;
+		mac_addr[0] = ha->addr[4];
+		mac_addr[1] = ha->addr[5];
+
+		netif_dbg(pdata, drv, pdata->netdev,
+			  "adding mac address %pM at %#x\n",
+			  ha->addr, *mac_reg);
+
+		mac_addr_hi = XLGMAC_SET_REG_BITS(mac_addr_hi,
+						  MAC_MACA1HR_AE_POS,
+						MAC_MACA1HR_AE_LEN,
+						1);
+	}
+
+	writel(mac_addr_hi, pdata->mac_regs + *mac_reg);
+	*mac_reg += MAC_MACA_INC;
+	writel(mac_addr_lo, pdata->mac_regs + *mac_reg);
+	*mac_reg += MAC_MACA_INC;
+}
+
+static int xlgmac_enable_rx_vlan_stripping(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_VLANTR);
+	/* Put the VLAN tag in the Rx descriptor */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_EVLRXS_POS,
+				     MAC_VLANTR_EVLRXS_LEN, 1);
+	/* Don't check the VLAN type */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_DOVLTC_POS,
+				     MAC_VLANTR_DOVLTC_LEN, 1);
+	/* Check only C-TAG (0x8100) packets */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_ERSVLM_POS,
+				     MAC_VLANTR_ERSVLM_LEN, 0);
+	/* Don't consider an S-TAG (0x88A8) packet as a VLAN packet */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_ESVL_POS,
+				     MAC_VLANTR_ESVL_LEN, 0);
+	/* Enable VLAN tag stripping */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_EVLS_POS,
+				     MAC_VLANTR_EVLS_LEN, 0x3);
+	writel(regval, pdata->mac_regs + MAC_VLANTR);
+
+	return 0;
+}
+
+static int xlgmac_disable_rx_vlan_stripping(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_VLANTR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_EVLS_POS,
+				     MAC_VLANTR_EVLS_LEN, 0);
+	writel(regval, pdata->mac_regs + MAC_VLANTR);
+
+	return 0;
+}
+
+static int xlgmac_enable_rx_vlan_filtering(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_PFR);
+	/* Enable VLAN filtering */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_VTFE_POS,
+				     MAC_PFR_VTFE_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_PFR);
+
+	regval = readl(pdata->mac_regs + MAC_VLANTR);
+	/* Enable VLAN Hash Table filtering */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_VTHM_POS,
+				     MAC_VLANTR_VTHM_LEN, 1);
+	/* Disable VLAN tag inverse matching */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_VTIM_POS,
+				     MAC_VLANTR_VTIM_LEN, 0);
+	/* Only filter on the lower 12-bits of the VLAN tag */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_ETV_POS,
+				     MAC_VLANTR_ETV_LEN, 1);
+	/* In order for the VLAN Hash Table filtering to be effective,
+	 * the VLAN tag identifier in the VLAN Tag Register must not
+	 * be zero.  Set the VLAN tag identifier to "1" to enable the
+	 * VLAN Hash Table filtering.  This implies that a VLAN tag of
+	 * 1 will always pass filtering.
+	 */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_VL_POS,
+				     MAC_VLANTR_VL_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_VLANTR);
+
+	return 0;
+}
+
+static int xlgmac_disable_rx_vlan_filtering(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_PFR);
+	/* Disable VLAN filtering */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_VTFE_POS,
+				     MAC_PFR_VTFE_LEN, 0);
+	writel(regval, pdata->mac_regs + MAC_PFR);
+
+	return 0;
+}
+
+static u32 xlgmac_vid_crc32_le(__le16 vid_le)
+{
+	unsigned char *data = (unsigned char *)&vid_le;
+	unsigned char data_byte = 0;
+	u32 poly = 0xedb88320;
+	u32 crc = ~0;
+	u32 temp = 0;
+	int i, bits;
+
+	bits = get_bitmask_order(VLAN_VID_MASK);
+	for (i = 0; i < bits; i++) {
+		if ((i % 8) == 0)
+			data_byte = data[i / 8];
+
+		temp = ((crc & 1) ^ data_byte) & 1;
+		crc >>= 1;
+		data_byte >>= 1;
+
+		if (temp)
+			crc ^= poly;
+	}
+
+	return crc;
+}
+
+static int xlgmac_update_vlan_hash_table(struct xlgmac_pdata *pdata)
+{
+	u16 vlan_hash_table = 0;
+	__le16 vid_le;
+	u32 regval;
+	u32 crc;
+	u16 vid;
+
+	/* Generate the VLAN Hash Table value */
+	for_each_set_bit(vid, pdata->active_vlans, VLAN_N_VID) {
+		/* Get the CRC32 value of the VLAN ID */
+		vid_le = cpu_to_le16(vid);
+		crc = bitrev32(~xlgmac_vid_crc32_le(vid_le)) >> 28;
+
+		vlan_hash_table |= (1 << crc);
+	}
+
+	regval = readl(pdata->mac_regs + MAC_VLANHTR);
+	/* Set the VLAN Hash Table filtering register */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANHTR_VLHT_POS,
+				     MAC_VLANHTR_VLHT_LEN, vlan_hash_table);
+	writel(regval, pdata->mac_regs + MAC_VLANHTR);
+
+	return 0;
+}
+
+static int xlgmac_set_promiscuous_mode(struct xlgmac_pdata *pdata,
+				       unsigned int enable)
+{
+	unsigned int val = enable ? 1 : 0;
+	u32 regval;
+
+	regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_PFR),
+				     MAC_PFR_PR_POS, MAC_PFR_PR_LEN);
+	if (regval == val)
+		return 0;
+
+	netif_dbg(pdata, drv, pdata->netdev, "%s promiscuous mode\n",
+		  enable ? "entering" : "leaving");
+
+	regval = readl(pdata->mac_regs + MAC_PFR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_PR_POS,
+				     MAC_PFR_PR_LEN, val);
+	writel(regval, pdata->mac_regs + MAC_PFR);
+
+	/* Hardware will still perform VLAN filtering in promiscuous mode */
+	if (enable) {
+		xlgmac_disable_rx_vlan_filtering(pdata);
+	} else {
+		if (pdata->netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
+			xlgmac_enable_rx_vlan_filtering(pdata);
+	}
+
+	return 0;
+}
+
+static int xlgmac_set_all_multicast_mode(struct xlgmac_pdata *pdata,
+					 unsigned int enable)
+{
+	unsigned int val = enable ? 1 : 0;
+	u32 regval;
+
+	regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_PFR),
+				     MAC_PFR_PM_POS, MAC_PFR_PM_LEN);
+	if (regval == val)
+		return 0;
+
+	netif_dbg(pdata, drv, pdata->netdev, "%s allmulti mode\n",
+		  enable ? "entering" : "leaving");
+
+	regval = readl(pdata->mac_regs + MAC_PFR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_PM_POS,
+				     MAC_PFR_PM_LEN, val);
+	writel(regval, pdata->mac_regs + MAC_PFR);
+
+	return 0;
+}
+
+static void xlgmac_set_mac_addn_addrs(struct xlgmac_pdata *pdata)
+{
+	struct net_device *netdev = pdata->netdev;
+	struct netdev_hw_addr *ha;
+	unsigned int addn_macs;
+	unsigned int mac_reg;
+
+	mac_reg = MAC_MACA1HR;
+	addn_macs = pdata->hw_feat.addn_mac;
+
+	if (netdev_uc_count(netdev) > addn_macs) {
+		xlgmac_set_promiscuous_mode(pdata, 1);
+	} else {
+		netdev_for_each_uc_addr(ha, netdev) {
+			xlgmac_set_mac_reg(pdata, ha, &mac_reg);
+			addn_macs--;
+		}
+
+		if (netdev_mc_count(netdev) > addn_macs) {
+			xlgmac_set_all_multicast_mode(pdata, 1);
+		} else {
+			netdev_for_each_mc_addr(ha, netdev) {
+				xlgmac_set_mac_reg(pdata, ha, &mac_reg);
+				addn_macs--;
+			}
+		}
+	}
+
+	/* Clear remaining additional MAC address entries */
+	while (addn_macs--)
+		xlgmac_set_mac_reg(pdata, NULL, &mac_reg);
+}
+
+static void xlgmac_set_mac_hash_table(struct xlgmac_pdata *pdata)
+{
+	unsigned int hash_table_shift, hash_table_count;
+	u32 hash_table[XLGMAC_MAC_HASH_TABLE_SIZE];
+	struct net_device *netdev = pdata->netdev;
+	struct netdev_hw_addr *ha;
+	unsigned int hash_reg;
+	unsigned int i;
+	u32 crc;
+
+	hash_table_shift = 26 - (pdata->hw_feat.hash_table_size >> 7);
+	hash_table_count = pdata->hw_feat.hash_table_size / 32;
+	memset(hash_table, 0, sizeof(hash_table));
+
+	/* Build the MAC Hash Table register values */
+	netdev_for_each_uc_addr(ha, netdev) {
+		crc = bitrev32(~crc32_le(~0, ha->addr, ETH_ALEN));
+		crc >>= hash_table_shift;
+		hash_table[crc >> 5] |= (1 << (crc & 0x1f));
+	}
+
+	netdev_for_each_mc_addr(ha, netdev) {
+		crc = bitrev32(~crc32_le(~0, ha->addr, ETH_ALEN));
+		crc >>= hash_table_shift;
+		hash_table[crc >> 5] |= (1 << (crc & 0x1f));
+	}
+
+	/* Set the MAC Hash Table registers */
+	hash_reg = MAC_HTR0;
+	for (i = 0; i < hash_table_count; i++) {
+		writel(hash_table[i], pdata->mac_regs + hash_reg);
+		hash_reg += MAC_HTR_INC;
+	}
+}
+
+static int xlgmac_add_mac_addresses(struct xlgmac_pdata *pdata)
+{
+	if (pdata->hw_feat.hash_table_size)
+		xlgmac_set_mac_hash_table(pdata);
+	else
+		xlgmac_set_mac_addn_addrs(pdata);
+
+	return 0;
+}
+
+static void xlgmac_config_mac_address(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	xlgmac_set_mac_address(pdata, pdata->netdev->dev_addr);
+
+	/* Filtering is done using perfect filtering and hash filtering */
+	if (pdata->hw_feat.hash_table_size) {
+		regval = readl(pdata->mac_regs + MAC_PFR);
+		regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_HPF_POS,
+					     MAC_PFR_HPF_LEN, 1);
+		regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_HUC_POS,
+					     MAC_PFR_HUC_LEN, 1);
+		regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_HMC_POS,
+					     MAC_PFR_HMC_LEN, 1);
+		writel(regval, pdata->mac_regs + MAC_PFR);
+	}
+}
+
+static void xlgmac_config_jumbo_enable(struct xlgmac_pdata *pdata)
+{
+	unsigned int val;
+	u32 regval;
+
+	val = (pdata->netdev->mtu > XLGMAC_STD_PACKET_MTU) ? 1 : 0;
+
+	regval = readl(pdata->mac_regs + MAC_RCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_JE_POS,
+				     MAC_RCR_JE_LEN, val);
+	writel(regval, pdata->mac_regs + MAC_RCR);
+}
+
+static void xlgmac_config_checksum_offload(struct xlgmac_pdata *pdata)
+{
+	if (pdata->netdev->features & NETIF_F_RXCSUM)
+		xlgmac_enable_rx_csum(pdata);
+	else
+		xlgmac_disable_rx_csum(pdata);
+}
+
+static void xlgmac_config_vlan_support(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_VLANIR);
+	/* Indicate that VLAN Tx CTAGs come from context descriptors */
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANIR_CSVL_POS,
+				     MAC_VLANIR_CSVL_LEN, 0);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANIR_VLTI_POS,
+				     MAC_VLANIR_VLTI_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_VLANIR);
+
+	/* Set the current VLAN Hash Table register value */
+	xlgmac_update_vlan_hash_table(pdata);
+
+	if (pdata->netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
+		xlgmac_enable_rx_vlan_filtering(pdata);
+	else
+		xlgmac_disable_rx_vlan_filtering(pdata);
+
+	if (pdata->netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
+		xlgmac_enable_rx_vlan_stripping(pdata);
+	else
+		xlgmac_disable_rx_vlan_stripping(pdata);
+}
+
+static int xlgmac_config_rx_mode(struct xlgmac_pdata *pdata)
+{
+	struct net_device *netdev = pdata->netdev;
+	unsigned int pr_mode, am_mode;
+
+	pr_mode = ((netdev->flags & IFF_PROMISC) != 0);
+	am_mode = ((netdev->flags & IFF_ALLMULTI) != 0);
+
+	xlgmac_set_promiscuous_mode(pdata, pr_mode);
+	xlgmac_set_all_multicast_mode(pdata, am_mode);
+
+	xlgmac_add_mac_addresses(pdata);
+
+	return 0;
+}
+
+static void xlgmac_prepare_tx_stop(struct xlgmac_pdata *pdata,
+				   struct xlgmac_channel *channel)
+{
+	unsigned int tx_dsr, tx_pos, tx_qidx;
+	unsigned long tx_timeout;
+	unsigned int tx_status;
+
+	/* Calculate the status register to read and the position within */
+	if (channel->queue_index < DMA_DSRX_FIRST_QUEUE) {
+		tx_dsr = DMA_DSR0;
+		tx_pos = (channel->queue_index * DMA_DSR_Q_LEN) +
+			 DMA_DSR0_TPS_START;
+	} else {
+		tx_qidx = channel->queue_index - DMA_DSRX_FIRST_QUEUE;
+
+		tx_dsr = DMA_DSR1 + ((tx_qidx / DMA_DSRX_QPR) * DMA_DSRX_INC);
+		tx_pos = ((tx_qidx % DMA_DSRX_QPR) * DMA_DSR_Q_LEN) +
+			 DMA_DSRX_TPS_START;
+	}
+
+	/* The Tx engine cannot be stopped if it is actively processing
+	 * descriptors. Wait for the Tx engine to enter the stopped or
+	 * suspended state.  Don't wait forever though...
+	 */
+	tx_timeout = jiffies + (XLGMAC_DMA_STOP_TIMEOUT * HZ);
+	while (time_before(jiffies, tx_timeout)) {
+		tx_status = readl(pdata->mac_regs + tx_dsr);
+		tx_status = XLGMAC_GET_REG_BITS(tx_status, tx_pos,
+						DMA_DSR_TPS_LEN);
+		if ((tx_status == DMA_TPS_STOPPED) ||
+		    (tx_status == DMA_TPS_SUSPENDED))
+			break;
+
+		usleep_range(500, 1000);
+	}
+
+	if (!time_before(jiffies, tx_timeout))
+		netdev_info(pdata->netdev,
+			    "timed out waiting for Tx DMA channel %u to stop\n",
+			    channel->queue_index);
+}
+
+static void xlgmac_enable_tx(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	/* Enable each Tx DMA channel */
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_ST_POS,
+					     DMA_CH_TCR_ST_LEN, 1);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+	}
+
+	/* Enable each Tx queue */
+	for (i = 0; i < pdata->tx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TXQEN_POS,
+					     MTL_Q_TQOMR_TXQEN_LEN,
+					MTL_Q_ENABLED);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+	}
+
+	/* Enable MAC Tx */
+	regval = readl(pdata->mac_regs + MAC_TCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_TE_POS,
+				     MAC_TCR_TE_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_TCR);
+}
+
+static void xlgmac_disable_tx(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	/* Prepare for Tx DMA channel stop */
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		xlgmac_prepare_tx_stop(pdata, channel);
+	}
+
+	/* Disable MAC Tx */
+	regval = readl(pdata->mac_regs + MAC_TCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_TE_POS,
+				     MAC_TCR_TE_LEN, 0);
+	writel(regval, pdata->mac_regs + MAC_TCR);
+
+	/* Disable each Tx queue */
+	for (i = 0; i < pdata->tx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TXQEN_POS,
+					     MTL_Q_TQOMR_TXQEN_LEN, 0);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+	}
+
+	/* Disable each Tx DMA channel */
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_ST_POS,
+					     DMA_CH_TCR_ST_LEN, 0);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+	}
+}
+
+static void xlgmac_prepare_rx_stop(struct xlgmac_pdata *pdata,
+				   unsigned int queue)
+{
+	unsigned int rx_status, prxq, rxqsts;
+	unsigned long rx_timeout;
+
+	/* The Rx engine cannot be stopped if it is actively processing
+	 * packets. Wait for the Rx queue to empty the Rx fifo.  Don't
+	 * wait forever though...
+	 */
+	rx_timeout = jiffies + (XLGMAC_DMA_STOP_TIMEOUT * HZ);
+	while (time_before(jiffies, rx_timeout)) {
+		rx_status = readl(XLGMAC_MTL_REG(pdata, queue, MTL_Q_RQDR));
+		prxq = XLGMAC_GET_REG_BITS(rx_status, MTL_Q_RQDR_PRXQ_POS,
+					   MTL_Q_RQDR_PRXQ_LEN);
+		rxqsts = XLGMAC_GET_REG_BITS(rx_status, MTL_Q_RQDR_RXQSTS_POS,
+					     MTL_Q_RQDR_RXQSTS_LEN);
+		if ((prxq == 0) && (rxqsts == 0))
+			break;
+
+		usleep_range(500, 1000);
+	}
+
+	if (!time_before(jiffies, rx_timeout))
+		netdev_info(pdata->netdev,
+			    "timed out waiting for Rx queue %u to empty\n",
+			    queue);
+}
+
+static void xlgmac_enable_rx(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int regval, i;
+
+	/* Enable each Rx DMA channel */
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_SR_POS,
+					     DMA_CH_RCR_SR_LEN, 1);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+	}
+
+	/* Enable each Rx queue */
+	regval = 0;
+	for (i = 0; i < pdata->rx_q_count; i++)
+		regval |= (0x02 << (i << 1));
+	writel(regval, pdata->mac_regs + MAC_RQC0R);
+
+	/* Enable MAC Rx */
+	regval = readl(pdata->mac_regs + MAC_RCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_DCRCC_POS,
+				     MAC_RCR_DCRCC_LEN, 1);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_CST_POS,
+				     MAC_RCR_CST_LEN, 1);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_ACS_POS,
+				     MAC_RCR_ACS_LEN, 1);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_RE_POS,
+				     MAC_RCR_RE_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_RCR);
+}
+
+static void xlgmac_disable_rx(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	/* Disable MAC Rx */
+	regval = readl(pdata->mac_regs + MAC_RCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_DCRCC_POS,
+				     MAC_RCR_DCRCC_LEN, 0);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_CST_POS,
+				     MAC_RCR_CST_LEN, 0);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_ACS_POS,
+				     MAC_RCR_ACS_LEN, 0);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_RE_POS,
+				     MAC_RCR_RE_LEN, 0);
+	writel(regval, pdata->mac_regs + MAC_RCR);
+
+	/* Prepare for Rx DMA channel stop */
+	for (i = 0; i < pdata->rx_q_count; i++)
+		xlgmac_prepare_rx_stop(pdata, i);
+
+	/* Disable each Rx queue */
+	writel(0, pdata->mac_regs + MAC_RQC0R);
+
+	/* Disable each Rx DMA channel */
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_SR_POS,
+					     DMA_CH_RCR_SR_LEN, 0);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+	}
+}
+
+static void xlgmac_tx_start_xmit(struct xlgmac_channel *channel,
+				 struct xlgmac_ring *ring)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct xlgmac_desc_data *desc_data;
+
+	/* Make sure everything is written before the register write */
+	wmb();
+
+	/* Issue a poll command to Tx DMA by writing address
+	 * of next immediate free descriptor
+	 */
+	desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur);
+	writel(lower_32_bits(desc_data->dma_desc_addr),
+	       XLGMAC_DMA_REG(channel, DMA_CH_TDTR_LO));
+
+	/* Start the Tx timer */
+	if (pdata->tx_usecs && !channel->tx_timer_active) {
+		channel->tx_timer_active = 1;
+		mod_timer(&channel->tx_timer,
+			  jiffies + usecs_to_jiffies(pdata->tx_usecs));
+	}
+
+	ring->tx.xmit_more = 0;
+}
+
+static void xlgmac_dev_xmit(struct xlgmac_channel *channel)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct xlgmac_ring *ring = channel->tx_ring;
+	unsigned int tso_context, vlan_context;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_dma_desc *dma_desc;
+	struct xlgmac_pkt_info *pkt_info;
+	unsigned int csum, tso, vlan;
+	int start_index = ring->cur;
+	int cur_index = ring->cur;
+	unsigned int tx_set_ic;
+	int i;
+
+	pkt_info = &ring->pkt_info;
+	csum = XLGMAC_GET_REG_BITS(pkt_info->attributes,
+				   TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS,
+				TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN);
+	tso = XLGMAC_GET_REG_BITS(pkt_info->attributes,
+				  TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS,
+				TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN);
+	vlan = XLGMAC_GET_REG_BITS(pkt_info->attributes,
+				   TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS,
+				TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN);
+
+	if (tso && (pkt_info->mss != ring->tx.cur_mss))
+		tso_context = 1;
+	else
+		tso_context = 0;
+
+	if (vlan && (pkt_info->vlan_ctag != ring->tx.cur_vlan_ctag))
+		vlan_context = 1;
+	else
+		vlan_context = 0;
+
+	/* Determine if an interrupt should be generated for this Tx:
+	 *   Interrupt:
+	 *     - Tx frame count exceeds the frame count setting
+	 *     - Addition of Tx frame count to the frame count since the
+	 *       last interrupt was set exceeds the frame count setting
+	 *   No interrupt:
+	 *     - No frame count setting specified (ethtool -C ethX tx-frames 0)
+	 *     - Addition of Tx frame count to the frame count since the
+	 *       last interrupt was set does not exceed the frame count setting
+	 */
+	ring->coalesce_count += pkt_info->tx_packets;
+	if (!pdata->tx_frames)
+		tx_set_ic = 0;
+	else if (pkt_info->tx_packets > pdata->tx_frames)
+		tx_set_ic = 1;
+	else if ((ring->coalesce_count % pdata->tx_frames) <
+		 pkt_info->tx_packets)
+		tx_set_ic = 1;
+	else
+		tx_set_ic = 0;
+
+	desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+	dma_desc = desc_data->dma_desc;
+
+	/* Create a context descriptor if this is a TSO pkt_info */
+	if (tso_context || vlan_context) {
+		if (tso_context) {
+			netif_dbg(pdata, tx_queued, pdata->netdev,
+				  "TSO context descriptor, mss=%u\n",
+				  pkt_info->mss);
+
+			/* Set the MSS size */
+			dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+						dma_desc->desc2,
+						TX_CONTEXT_DESC2_MSS_POS,
+						TX_CONTEXT_DESC2_MSS_LEN,
+						pkt_info->mss);
+
+			/* Mark it as a CONTEXT descriptor */
+			dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+						dma_desc->desc3,
+						TX_CONTEXT_DESC3_CTXT_POS,
+						TX_CONTEXT_DESC3_CTXT_LEN,
+						1);
+
+			/* Indicate this descriptor contains the MSS */
+			dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+						dma_desc->desc3,
+						TX_CONTEXT_DESC3_TCMSSV_POS,
+						TX_CONTEXT_DESC3_TCMSSV_LEN,
+						1);
+
+			ring->tx.cur_mss = pkt_info->mss;
+		}
+
+		if (vlan_context) {
+			netif_dbg(pdata, tx_queued, pdata->netdev,
+				  "VLAN context descriptor, ctag=%u\n",
+				  pkt_info->vlan_ctag);
+
+			/* Mark it as a CONTEXT descriptor */
+			dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+						dma_desc->desc3,
+						TX_CONTEXT_DESC3_CTXT_POS,
+						TX_CONTEXT_DESC3_CTXT_LEN,
+						1);
+
+			/* Set the VLAN tag */
+			dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+						dma_desc->desc3,
+						TX_CONTEXT_DESC3_VT_POS,
+						TX_CONTEXT_DESC3_VT_LEN,
+						pkt_info->vlan_ctag);
+
+			/* Indicate this descriptor contains the VLAN tag */
+			dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+						dma_desc->desc3,
+						TX_CONTEXT_DESC3_VLTV_POS,
+						TX_CONTEXT_DESC3_VLTV_LEN,
+						1);
+
+			ring->tx.cur_vlan_ctag = pkt_info->vlan_ctag;
+		}
+
+		cur_index++;
+		desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+		dma_desc = desc_data->dma_desc;
+	}
+
+	/* Update buffer address (for TSO this is the header) */
+	dma_desc->desc0 =  cpu_to_le32(lower_32_bits(desc_data->skb_dma));
+	dma_desc->desc1 =  cpu_to_le32(upper_32_bits(desc_data->skb_dma));
+
+	/* Update the buffer length */
+	dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+				dma_desc->desc2,
+				TX_NORMAL_DESC2_HL_B1L_POS,
+				TX_NORMAL_DESC2_HL_B1L_LEN,
+				desc_data->skb_dma_len);
+
+	/* VLAN tag insertion check */
+	if (vlan)
+		dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc2,
+					TX_NORMAL_DESC2_VTIR_POS,
+					TX_NORMAL_DESC2_VTIR_LEN,
+					TX_NORMAL_DESC2_VLAN_INSERT);
+
+	/* Timestamp enablement check */
+	if (XLGMAC_GET_REG_BITS(pkt_info->attributes,
+				TX_PACKET_ATTRIBUTES_PTP_POS,
+				TX_PACKET_ATTRIBUTES_PTP_LEN))
+		dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc2,
+					TX_NORMAL_DESC2_TTSE_POS,
+					TX_NORMAL_DESC2_TTSE_LEN,
+					1);
+
+	/* Mark it as First Descriptor */
+	dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+				dma_desc->desc3,
+				TX_NORMAL_DESC3_FD_POS,
+				TX_NORMAL_DESC3_FD_LEN,
+				1);
+
+	/* Mark it as a NORMAL descriptor */
+	dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+				dma_desc->desc3,
+				TX_NORMAL_DESC3_CTXT_POS,
+				TX_NORMAL_DESC3_CTXT_LEN,
+				0);
+
+	/* Set OWN bit if not the first descriptor */
+	if (cur_index != start_index)
+		dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc3,
+					TX_NORMAL_DESC3_OWN_POS,
+					TX_NORMAL_DESC3_OWN_LEN,
+					1);
+
+	if (tso) {
+		/* Enable TSO */
+		dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc3,
+					TX_NORMAL_DESC3_TSE_POS,
+					TX_NORMAL_DESC3_TSE_LEN, 1);
+		dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc3,
+					TX_NORMAL_DESC3_TCPPL_POS,
+					TX_NORMAL_DESC3_TCPPL_LEN,
+					pkt_info->tcp_payload_len);
+		dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc3,
+					TX_NORMAL_DESC3_TCPHDRLEN_POS,
+					TX_NORMAL_DESC3_TCPHDRLEN_LEN,
+					pkt_info->tcp_header_len / 4);
+
+		pdata->stats.tx_tso_packets++;
+	} else {
+		/* Enable CRC and Pad Insertion */
+		dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc3,
+					TX_NORMAL_DESC3_CPC_POS,
+					TX_NORMAL_DESC3_CPC_LEN, 0);
+
+		/* Enable HW CSUM */
+		if (csum)
+			dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+						dma_desc->desc3,
+						TX_NORMAL_DESC3_CIC_POS,
+						TX_NORMAL_DESC3_CIC_LEN,
+						0x3);
+
+		/* Set the total length to be transmitted */
+		dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc3,
+					TX_NORMAL_DESC3_FL_POS,
+					TX_NORMAL_DESC3_FL_LEN,
+					pkt_info->length);
+	}
+
+	for (i = cur_index - start_index + 1; i < pkt_info->desc_count; i++) {
+		cur_index++;
+		desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+		dma_desc = desc_data->dma_desc;
+
+		/* Update buffer address */
+		dma_desc->desc0 =
+			cpu_to_le32(lower_32_bits(desc_data->skb_dma));
+		dma_desc->desc1 =
+			cpu_to_le32(upper_32_bits(desc_data->skb_dma));
+
+		/* Update the buffer length */
+		dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc2,
+					TX_NORMAL_DESC2_HL_B1L_POS,
+					TX_NORMAL_DESC2_HL_B1L_LEN,
+					desc_data->skb_dma_len);
+
+		/* Set OWN bit */
+		dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc3,
+					TX_NORMAL_DESC3_OWN_POS,
+					TX_NORMAL_DESC3_OWN_LEN, 1);
+
+		/* Mark it as NORMAL descriptor */
+		dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc3,
+					TX_NORMAL_DESC3_CTXT_POS,
+					TX_NORMAL_DESC3_CTXT_LEN, 0);
+
+		/* Enable HW CSUM */
+		if (csum)
+			dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+						dma_desc->desc3,
+						TX_NORMAL_DESC3_CIC_POS,
+						TX_NORMAL_DESC3_CIC_LEN,
+						0x3);
+	}
+
+	/* Set LAST bit for the last descriptor */
+	dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+				dma_desc->desc3,
+				TX_NORMAL_DESC3_LD_POS,
+				TX_NORMAL_DESC3_LD_LEN, 1);
+
+	/* Set IC bit based on Tx coalescing settings */
+	if (tx_set_ic)
+		dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+					dma_desc->desc2,
+					TX_NORMAL_DESC2_IC_POS,
+					TX_NORMAL_DESC2_IC_LEN, 1);
+
+	/* Save the Tx info to report back during cleanup */
+	desc_data->tx.packets = pkt_info->tx_packets;
+	desc_data->tx.bytes = pkt_info->tx_bytes;
+
+	/* In case the Tx DMA engine is running, make sure everything
+	 * is written to the descriptor(s) before setting the OWN bit
+	 * for the first descriptor
+	 */
+	dma_wmb();
+
+	/* Set OWN bit for the first descriptor */
+	desc_data = XLGMAC_GET_DESC_DATA(ring, start_index);
+	dma_desc = desc_data->dma_desc;
+	dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+				dma_desc->desc3,
+				TX_NORMAL_DESC3_OWN_POS,
+				TX_NORMAL_DESC3_OWN_LEN, 1);
+
+	if (netif_msg_tx_queued(pdata))
+		xlgmac_dump_tx_desc(pdata, ring, start_index,
+				    pkt_info->desc_count, 1);
+
+	/* Make sure ownership is written to the descriptor */
+	smp_wmb();
+
+	ring->cur = cur_index + 1;
+	if (!pkt_info->skb->xmit_more ||
+	    netif_xmit_stopped(netdev_get_tx_queue(pdata->netdev,
+						   channel->queue_index)))
+		xlgmac_tx_start_xmit(channel, ring);
+	else
+		ring->tx.xmit_more = 1;
+
+	XLGMAC_PR("%s: descriptors %u to %u written\n",
+		  channel->name, start_index & (ring->dma_desc_count - 1),
+		  (ring->cur - 1) & (ring->dma_desc_count - 1));
+}
+
+static void xlgmac_get_rx_tstamp(struct xlgmac_pkt_info *pkt_info,
+				 struct xlgmac_dma_desc *dma_desc)
+{
+	u32 tsa, tsd;
+	u64 nsec;
+
+	tsa = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				     RX_CONTEXT_DESC3_TSA_POS,
+				RX_CONTEXT_DESC3_TSA_LEN);
+	tsd = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				     RX_CONTEXT_DESC3_TSD_POS,
+				RX_CONTEXT_DESC3_TSD_LEN);
+	if (tsa && !tsd) {
+		nsec = le32_to_cpu(dma_desc->desc1);
+		nsec <<= 32;
+		nsec |= le32_to_cpu(dma_desc->desc0);
+		if (nsec != 0xffffffffffffffffULL) {
+			pkt_info->rx_tstamp = nsec;
+			pkt_info->attributes = XLGMAC_SET_REG_BITS(
+					pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_RX_TSTAMP_POS,
+					RX_PACKET_ATTRIBUTES_RX_TSTAMP_LEN,
+					1);
+		}
+	}
+}
+
+static void xlgmac_tx_desc_reset(struct xlgmac_desc_data *desc_data)
+{
+	struct xlgmac_dma_desc *dma_desc = desc_data->dma_desc;
+
+	/* Reset the Tx descriptor
+	 *   Set buffer 1 (lo) address to zero
+	 *   Set buffer 1 (hi) address to zero
+	 *   Reset all other control bits (IC, TTSE, B2L & B1L)
+	 *   Reset all other control bits (OWN, CTXT, FD, LD, CPC, CIC, etc)
+	 */
+	dma_desc->desc0 = 0;
+	dma_desc->desc1 = 0;
+	dma_desc->desc2 = 0;
+	dma_desc->desc3 = 0;
+
+	/* Make sure ownership is written to the descriptor */
+	dma_wmb();
+}
+
+static void xlgmac_tx_desc_init(struct xlgmac_channel *channel)
+{
+	struct xlgmac_ring *ring = channel->tx_ring;
+	struct xlgmac_desc_data *desc_data;
+	int start_index = ring->cur;
+	int i;
+
+	/* Initialze all descriptors */
+	for (i = 0; i < ring->dma_desc_count; i++) {
+		desc_data = XLGMAC_GET_DESC_DATA(ring, i);
+
+		/* Initialize Tx descriptor */
+		xlgmac_tx_desc_reset(desc_data);
+	}
+
+	/* Update the total number of Tx descriptors */
+	writel(ring->dma_desc_count - 1, XLGMAC_DMA_REG(channel, DMA_CH_TDRLR));
+
+	/* Update the starting address of descriptor ring */
+	desc_data = XLGMAC_GET_DESC_DATA(ring, start_index);
+	writel(upper_32_bits(desc_data->dma_desc_addr),
+	       XLGMAC_DMA_REG(channel, DMA_CH_TDLR_HI));
+	writel(lower_32_bits(desc_data->dma_desc_addr),
+	       XLGMAC_DMA_REG(channel, DMA_CH_TDLR_LO));
+}
+
+static void xlgmac_rx_desc_reset(struct xlgmac_pdata *pdata,
+				 struct xlgmac_desc_data *desc_data,
+				 unsigned int index)
+{
+	struct xlgmac_dma_desc *dma_desc = desc_data->dma_desc;
+	unsigned int rx_frames = pdata->rx_frames;
+	unsigned int rx_usecs = pdata->rx_usecs;
+	dma_addr_t hdr_dma, buf_dma;
+	unsigned int inte;
+
+	if (!rx_usecs && !rx_frames) {
+		/* No coalescing, interrupt for every descriptor */
+		inte = 1;
+	} else {
+		/* Set interrupt based on Rx frame coalescing setting */
+		if (rx_frames && !((index + 1) % rx_frames))
+			inte = 1;
+		else
+			inte = 0;
+	}
+
+	/* Reset the Rx descriptor
+	 *   Set buffer 1 (lo) address to header dma address (lo)
+	 *   Set buffer 1 (hi) address to header dma address (hi)
+	 *   Set buffer 2 (lo) address to buffer dma address (lo)
+	 *   Set buffer 2 (hi) address to buffer dma address (hi) and
+	 *     set control bits OWN and INTE
+	 */
+	hdr_dma = desc_data->rx.hdr.dma_base + desc_data->rx.hdr.dma_off;
+	buf_dma = desc_data->rx.buf.dma_base + desc_data->rx.buf.dma_off;
+	dma_desc->desc0 = cpu_to_le32(lower_32_bits(hdr_dma));
+	dma_desc->desc1 = cpu_to_le32(upper_32_bits(hdr_dma));
+	dma_desc->desc2 = cpu_to_le32(lower_32_bits(buf_dma));
+	dma_desc->desc3 = cpu_to_le32(upper_32_bits(buf_dma));
+
+	dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+				dma_desc->desc3,
+				RX_NORMAL_DESC3_INTE_POS,
+				RX_NORMAL_DESC3_INTE_LEN,
+				inte);
+
+	/* Since the Rx DMA engine is likely running, make sure everything
+	 * is written to the descriptor(s) before setting the OWN bit
+	 * for the descriptor
+	 */
+	dma_wmb();
+
+	dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+				dma_desc->desc3,
+				RX_NORMAL_DESC3_OWN_POS,
+				RX_NORMAL_DESC3_OWN_LEN,
+				1);
+
+	/* Make sure ownership is written to the descriptor */
+	dma_wmb();
+}
+
+static void xlgmac_rx_desc_init(struct xlgmac_channel *channel)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct xlgmac_ring *ring = channel->rx_ring;
+	unsigned int start_index = ring->cur;
+	struct xlgmac_desc_data *desc_data;
+	unsigned int i;
+
+	/* Initialize all descriptors */
+	for (i = 0; i < ring->dma_desc_count; i++) {
+		desc_data = XLGMAC_GET_DESC_DATA(ring, i);
+
+		/* Initialize Rx descriptor */
+		xlgmac_rx_desc_reset(pdata, desc_data, i);
+	}
+
+	/* Update the total number of Rx descriptors */
+	writel(ring->dma_desc_count - 1, XLGMAC_DMA_REG(channel, DMA_CH_RDRLR));
+
+	/* Update the starting address of descriptor ring */
+	desc_data = XLGMAC_GET_DESC_DATA(ring, start_index);
+	writel(upper_32_bits(desc_data->dma_desc_addr),
+	       XLGMAC_DMA_REG(channel, DMA_CH_RDLR_HI));
+	writel(lower_32_bits(desc_data->dma_desc_addr),
+	       XLGMAC_DMA_REG(channel, DMA_CH_RDLR_LO));
+
+	/* Update the Rx Descriptor Tail Pointer */
+	desc_data = XLGMAC_GET_DESC_DATA(ring, start_index +
+					  ring->dma_desc_count - 1);
+	writel(lower_32_bits(desc_data->dma_desc_addr),
+	       XLGMAC_DMA_REG(channel, DMA_CH_RDTR_LO));
+}
+
+static int xlgmac_is_context_desc(struct xlgmac_dma_desc *dma_desc)
+{
+	/* Rx and Tx share CTXT bit, so check TDES3.CTXT bit */
+	return XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				TX_NORMAL_DESC3_CTXT_POS,
+				TX_NORMAL_DESC3_CTXT_LEN);
+}
+
+static int xlgmac_is_last_desc(struct xlgmac_dma_desc *dma_desc)
+{
+	/* Rx and Tx share LD bit, so check TDES3.LD bit */
+	return XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				TX_NORMAL_DESC3_LD_POS,
+				TX_NORMAL_DESC3_LD_LEN);
+}
+
+static int xlgmac_disable_tx_flow_control(struct xlgmac_pdata *pdata)
+{
+	unsigned int max_q_count, q_count;
+	unsigned int reg, regval;
+	unsigned int i;
+
+	/* Clear MTL flow control */
+	for (i = 0; i < pdata->rx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_EHFC_POS,
+					     MTL_Q_RQOMR_EHFC_LEN, 0);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+	}
+
+	/* Clear MAC flow control */
+	max_q_count = XLGMAC_MAX_FLOW_CONTROL_QUEUES;
+	q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count);
+	reg = MAC_Q0TFCR;
+	for (i = 0; i < q_count; i++) {
+		regval = readl(pdata->mac_regs + reg);
+		regval = XLGMAC_SET_REG_BITS(regval,
+					     MAC_Q0TFCR_TFE_POS,
+					MAC_Q0TFCR_TFE_LEN,
+					0);
+		writel(regval, pdata->mac_regs + reg);
+
+		reg += MAC_QTFCR_INC;
+	}
+
+	return 0;
+}
+
+static int xlgmac_enable_tx_flow_control(struct xlgmac_pdata *pdata)
+{
+	unsigned int max_q_count, q_count;
+	unsigned int reg, regval;
+	unsigned int i;
+
+	/* Set MTL flow control */
+	for (i = 0; i < pdata->rx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_EHFC_POS,
+					     MTL_Q_RQOMR_EHFC_LEN, 1);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+	}
+
+	/* Set MAC flow control */
+	max_q_count = XLGMAC_MAX_FLOW_CONTROL_QUEUES;
+	q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count);
+	reg = MAC_Q0TFCR;
+	for (i = 0; i < q_count; i++) {
+		regval = readl(pdata->mac_regs + reg);
+
+		/* Enable transmit flow control */
+		regval = XLGMAC_SET_REG_BITS(regval, MAC_Q0TFCR_TFE_POS,
+					     MAC_Q0TFCR_TFE_LEN, 1);
+		/* Set pause time */
+		regval = XLGMAC_SET_REG_BITS(regval, MAC_Q0TFCR_PT_POS,
+					     MAC_Q0TFCR_PT_LEN, 0xffff);
+
+		writel(regval, pdata->mac_regs + reg);
+
+		reg += MAC_QTFCR_INC;
+	}
+
+	return 0;
+}
+
+static int xlgmac_disable_rx_flow_control(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_RFCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RFCR_RFE_POS,
+				     MAC_RFCR_RFE_LEN, 0);
+	writel(regval, pdata->mac_regs + MAC_RFCR);
+
+	return 0;
+}
+
+static int xlgmac_enable_rx_flow_control(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MAC_RFCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RFCR_RFE_POS,
+				     MAC_RFCR_RFE_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_RFCR);
+
+	return 0;
+}
+
+static int xlgmac_config_tx_flow_control(struct xlgmac_pdata *pdata)
+{
+	if (pdata->tx_pause)
+		xlgmac_enable_tx_flow_control(pdata);
+	else
+		xlgmac_disable_tx_flow_control(pdata);
+
+	return 0;
+}
+
+static int xlgmac_config_rx_flow_control(struct xlgmac_pdata *pdata)
+{
+	if (pdata->rx_pause)
+		xlgmac_enable_rx_flow_control(pdata);
+	else
+		xlgmac_disable_rx_flow_control(pdata);
+
+	return 0;
+}
+
+static int xlgmac_config_rx_coalesce(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RIWT));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RIWT_RWT_POS,
+					     DMA_CH_RIWT_RWT_LEN,
+					     pdata->rx_riwt);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RIWT));
+	}
+
+	return 0;
+}
+
+static void xlgmac_config_flow_control(struct xlgmac_pdata *pdata)
+{
+	xlgmac_config_tx_flow_control(pdata);
+	xlgmac_config_rx_flow_control(pdata);
+}
+
+static void xlgmac_config_rx_fep_enable(struct xlgmac_pdata *pdata)
+{
+	unsigned int i;
+	u32 regval;
+
+	for (i = 0; i < pdata->rx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_FEP_POS,
+					     MTL_Q_RQOMR_FEP_LEN, 1);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+	}
+}
+
+static void xlgmac_config_rx_fup_enable(struct xlgmac_pdata *pdata)
+{
+	unsigned int i;
+	u32 regval;
+
+	for (i = 0; i < pdata->rx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_FUP_POS,
+					     MTL_Q_RQOMR_FUP_LEN, 1);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+	}
+}
+
+static int xlgmac_config_tx_coalesce(struct xlgmac_pdata *pdata)
+{
+	return 0;
+}
+
+static void xlgmac_config_rx_buffer_size(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_RBSZ_POS,
+					     DMA_CH_RCR_RBSZ_LEN,
+					pdata->rx_buf_size);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+	}
+}
+
+static void xlgmac_config_tso_mode(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		if (pdata->hw_feat.tso) {
+			regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+			regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_TSE_POS,
+						     DMA_CH_TCR_TSE_LEN, 1);
+			writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+		}
+	}
+}
+
+static void xlgmac_config_sph_mode(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_CR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_CR_SPH_POS,
+					     DMA_CH_CR_SPH_LEN, 1);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_CR));
+	}
+
+	regval = readl(pdata->mac_regs + MAC_RCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_HDSMS_POS,
+				     MAC_RCR_HDSMS_LEN,
+				XLGMAC_SPH_HDSMS_SIZE);
+	writel(regval, pdata->mac_regs + MAC_RCR);
+}
+
+static unsigned int xlgmac_usec_to_riwt(struct xlgmac_pdata *pdata,
+					unsigned int usec)
+{
+	unsigned long rate;
+	unsigned int ret;
+
+	rate = pdata->sysclk_rate;
+
+	/* Convert the input usec value to the watchdog timer value. Each
+	 * watchdog timer value is equivalent to 256 clock cycles.
+	 * Calculate the required value as:
+	 *   ( usec * ( system_clock_mhz / 10^6 ) / 256
+	 */
+	ret = (usec * (rate / 1000000)) / 256;
+
+	return ret;
+}
+
+static unsigned int xlgmac_riwt_to_usec(struct xlgmac_pdata *pdata,
+					unsigned int riwt)
+{
+	unsigned long rate;
+	unsigned int ret;
+
+	rate = pdata->sysclk_rate;
+
+	/* Convert the input watchdog timer value to the usec value. Each
+	 * watchdog timer value is equivalent to 256 clock cycles.
+	 * Calculate the required value as:
+	 *   ( riwt * 256 ) / ( system_clock_mhz / 10^6 )
+	 */
+	ret = (riwt * 256) / (rate / 1000000);
+
+	return ret;
+}
+
+static int xlgmac_config_rx_threshold(struct xlgmac_pdata *pdata,
+				      unsigned int val)
+{
+	unsigned int i;
+	u32 regval;
+
+	for (i = 0; i < pdata->rx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_RTC_POS,
+					     MTL_Q_RQOMR_RTC_LEN, val);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+	}
+
+	return 0;
+}
+
+static void xlgmac_config_mtl_mode(struct xlgmac_pdata *pdata)
+{
+	unsigned int i;
+	u32 regval;
+
+	/* Set Tx to weighted round robin scheduling algorithm */
+	regval = readl(pdata->mac_regs + MTL_OMR);
+	regval = XLGMAC_SET_REG_BITS(regval, MTL_OMR_ETSALG_POS,
+				     MTL_OMR_ETSALG_LEN, MTL_ETSALG_WRR);
+	writel(regval, pdata->mac_regs + MTL_OMR);
+
+	/* Set Tx traffic classes to use WRR algorithm with equal weights */
+	for (i = 0; i < pdata->hw_feat.tc_cnt; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_TC_ETSCR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_TC_ETSCR_TSA_POS,
+					     MTL_TC_ETSCR_TSA_LEN, MTL_TSA_ETS);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_TC_ETSCR));
+
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_TC_QWR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_TC_QWR_QW_POS,
+					     MTL_TC_QWR_QW_LEN, 1);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_TC_QWR));
+	}
+
+	/* Set Rx to strict priority algorithm */
+	regval = readl(pdata->mac_regs + MTL_OMR);
+	regval = XLGMAC_SET_REG_BITS(regval, MTL_OMR_RAA_POS,
+				     MTL_OMR_RAA_LEN, MTL_RAA_SP);
+	writel(regval, pdata->mac_regs + MTL_OMR);
+}
+
+static void xlgmac_config_queue_mapping(struct xlgmac_pdata *pdata)
+{
+	unsigned int ppq, ppq_extra, prio, prio_queues;
+	unsigned int qptc, qptc_extra, queue;
+	unsigned int reg, regval;
+	unsigned int mask;
+	unsigned int i, j;
+
+	/* Map the MTL Tx Queues to Traffic Classes
+	 *   Note: Tx Queues >= Traffic Classes
+	 */
+	qptc = pdata->tx_q_count / pdata->hw_feat.tc_cnt;
+	qptc_extra = pdata->tx_q_count % pdata->hw_feat.tc_cnt;
+
+	for (i = 0, queue = 0; i < pdata->hw_feat.tc_cnt; i++) {
+		for (j = 0; j < qptc; j++) {
+			netif_dbg(pdata, drv, pdata->netdev,
+				  "TXq%u mapped to TC%u\n", queue, i);
+			regval = readl(XLGMAC_MTL_REG(pdata, queue,
+						      MTL_Q_TQOMR));
+			regval = XLGMAC_SET_REG_BITS(regval,
+						     MTL_Q_TQOMR_Q2TCMAP_POS,
+						     MTL_Q_TQOMR_Q2TCMAP_LEN,
+						     i);
+			writel(regval, XLGMAC_MTL_REG(pdata, queue,
+						      MTL_Q_TQOMR));
+			queue++;
+		}
+
+		if (i < qptc_extra) {
+			netif_dbg(pdata, drv, pdata->netdev,
+				  "TXq%u mapped to TC%u\n", queue, i);
+			regval = readl(XLGMAC_MTL_REG(pdata, queue,
+						      MTL_Q_TQOMR));
+			regval = XLGMAC_SET_REG_BITS(regval,
+						     MTL_Q_TQOMR_Q2TCMAP_POS,
+						     MTL_Q_TQOMR_Q2TCMAP_LEN,
+						     i);
+			writel(regval, XLGMAC_MTL_REG(pdata, queue,
+						      MTL_Q_TQOMR));
+			queue++;
+		}
+	}
+
+	/* Map the 8 VLAN priority values to available MTL Rx queues */
+	prio_queues = min_t(unsigned int, IEEE_8021QAZ_MAX_TCS,
+			    pdata->rx_q_count);
+	ppq = IEEE_8021QAZ_MAX_TCS / prio_queues;
+	ppq_extra = IEEE_8021QAZ_MAX_TCS % prio_queues;
+
+	reg = MAC_RQC2R;
+	regval = 0;
+	for (i = 0, prio = 0; i < prio_queues;) {
+		mask = 0;
+		for (j = 0; j < ppq; j++) {
+			netif_dbg(pdata, drv, pdata->netdev,
+				  "PRIO%u mapped to RXq%u\n", prio, i);
+			mask |= (1 << prio);
+			prio++;
+		}
+
+		if (i < ppq_extra) {
+			netif_dbg(pdata, drv, pdata->netdev,
+				  "PRIO%u mapped to RXq%u\n", prio, i);
+			mask |= (1 << prio);
+			prio++;
+		}
+
+		regval |= (mask << ((i++ % MAC_RQC2_Q_PER_REG) << 3));
+
+		if ((i % MAC_RQC2_Q_PER_REG) && (i != prio_queues))
+			continue;
+
+		writel(regval, pdata->mac_regs + reg);
+		reg += MAC_RQC2_INC;
+		regval = 0;
+	}
+
+	/* Configure one to one, MTL Rx queue to DMA Rx channel mapping
+	 *  ie Q0 <--> CH0, Q1 <--> CH1 ... Q11 <--> CH11
+	 */
+	reg = MTL_RQDCM0R;
+	regval = readl(pdata->mac_regs + reg);
+	regval |= (MTL_RQDCM0R_Q0MDMACH | MTL_RQDCM0R_Q1MDMACH |
+		    MTL_RQDCM0R_Q2MDMACH | MTL_RQDCM0R_Q3MDMACH);
+	writel(regval, pdata->mac_regs + reg);
+
+	reg += MTL_RQDCM_INC;
+	regval = readl(pdata->mac_regs + reg);
+	regval |= (MTL_RQDCM1R_Q4MDMACH | MTL_RQDCM1R_Q5MDMACH |
+		    MTL_RQDCM1R_Q6MDMACH | MTL_RQDCM1R_Q7MDMACH);
+	writel(regval, pdata->mac_regs + reg);
+
+	reg += MTL_RQDCM_INC;
+	regval = readl(pdata->mac_regs + reg);
+	regval |= (MTL_RQDCM2R_Q8MDMACH | MTL_RQDCM2R_Q9MDMACH |
+		    MTL_RQDCM2R_Q10MDMACH | MTL_RQDCM2R_Q11MDMACH);
+	writel(regval, pdata->mac_regs + reg);
+}
+
+static unsigned int xlgmac_calculate_per_queue_fifo(
+					unsigned int fifo_size,
+					unsigned int queue_count)
+{
+	unsigned int q_fifo_size;
+	unsigned int p_fifo;
+
+	/* Calculate the configured fifo size */
+	q_fifo_size = 1 << (fifo_size + 7);
+
+	/* The configured value may not be the actual amount of fifo RAM */
+	q_fifo_size = min_t(unsigned int, XLGMAC_MAX_FIFO, q_fifo_size);
+
+	q_fifo_size = q_fifo_size / queue_count;
+
+	/* Each increment in the queue fifo size represents 256 bytes of
+	 * fifo, with 0 representing 256 bytes. Distribute the fifo equally
+	 * between the queues.
+	 */
+	p_fifo = q_fifo_size / 256;
+	if (p_fifo)
+		p_fifo--;
+
+	return p_fifo;
+}
+
+static void xlgmac_config_tx_fifo_size(struct xlgmac_pdata *pdata)
+{
+	unsigned int fifo_size;
+	unsigned int i;
+	u32 regval;
+
+	fifo_size = xlgmac_calculate_per_queue_fifo(
+				pdata->hw_feat.tx_fifo_size,
+				pdata->tx_q_count);
+
+	for (i = 0; i < pdata->tx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TQS_POS,
+					     MTL_Q_TQOMR_TQS_LEN, fifo_size);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+	}
+
+	netif_info(pdata, drv, pdata->netdev,
+		   "%d Tx hardware queues, %d byte fifo per queue\n",
+		   pdata->tx_q_count, ((fifo_size + 1) * 256));
+}
+
+static void xlgmac_config_rx_fifo_size(struct xlgmac_pdata *pdata)
+{
+	unsigned int fifo_size;
+	unsigned int i;
+	u32 regval;
+
+	fifo_size = xlgmac_calculate_per_queue_fifo(
+					pdata->hw_feat.rx_fifo_size,
+					pdata->rx_q_count);
+
+	for (i = 0; i < pdata->rx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_RQS_POS,
+					     MTL_Q_RQOMR_RQS_LEN, fifo_size);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+	}
+
+	netif_info(pdata, drv, pdata->netdev,
+		   "%d Rx hardware queues, %d byte fifo per queue\n",
+		   pdata->rx_q_count, ((fifo_size + 1) * 256));
+}
+
+static void xlgmac_config_flow_control_threshold(struct xlgmac_pdata *pdata)
+{
+	unsigned int i;
+	u32 regval;
+
+	for (i = 0; i < pdata->rx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQFCR));
+		/* Activate flow control when less than 4k left in fifo */
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQFCR_RFA_POS,
+					     MTL_Q_RQFCR_RFA_LEN, 2);
+		/* De-activate flow control when more than 6k left in fifo */
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQFCR_RFD_POS,
+					     MTL_Q_RQFCR_RFD_LEN, 4);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQFCR));
+	}
+}
+
+static int xlgmac_config_tx_threshold(struct xlgmac_pdata *pdata,
+				      unsigned int val)
+{
+	unsigned int i;
+	u32 regval;
+
+	for (i = 0; i < pdata->tx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TTC_POS,
+					     MTL_Q_TQOMR_TTC_LEN, val);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+	}
+
+	return 0;
+}
+
+static int xlgmac_config_rsf_mode(struct xlgmac_pdata *pdata,
+				  unsigned int val)
+{
+	unsigned int i;
+	u32 regval;
+
+	for (i = 0; i < pdata->rx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_RSF_POS,
+					     MTL_Q_RQOMR_RSF_LEN, val);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+	}
+
+	return 0;
+}
+
+static int xlgmac_config_tsf_mode(struct xlgmac_pdata *pdata,
+				  unsigned int val)
+{
+	unsigned int i;
+	u32 regval;
+
+	for (i = 0; i < pdata->tx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TSF_POS,
+					     MTL_Q_TQOMR_TSF_LEN, val);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+	}
+
+	return 0;
+}
+
+static int xlgmac_config_osp_mode(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_OSP_POS,
+					     DMA_CH_TCR_OSP_LEN,
+					pdata->tx_osp_mode);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+	}
+
+	return 0;
+}
+
+static int xlgmac_config_pblx8(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_CR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_CR_PBLX8_POS,
+					     DMA_CH_CR_PBLX8_LEN,
+					pdata->pblx8);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_CR));
+	}
+
+	return 0;
+}
+
+static int xlgmac_get_tx_pbl_val(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(XLGMAC_DMA_REG(pdata->channel_head, DMA_CH_TCR));
+	regval = XLGMAC_GET_REG_BITS(regval, DMA_CH_TCR_PBL_POS,
+				     DMA_CH_TCR_PBL_LEN);
+	return regval;
+}
+
+static int xlgmac_config_tx_pbl_val(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_PBL_POS,
+					     DMA_CH_TCR_PBL_LEN,
+					pdata->tx_pbl);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+	}
+
+	return 0;
+}
+
+static int xlgmac_get_rx_pbl_val(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(XLGMAC_DMA_REG(pdata->channel_head, DMA_CH_RCR));
+	regval = XLGMAC_GET_REG_BITS(regval, DMA_CH_RCR_PBL_POS,
+				     DMA_CH_RCR_PBL_LEN);
+	return regval;
+}
+
+static int xlgmac_config_rx_pbl_val(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	u32 regval;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+		regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_PBL_POS,
+					     DMA_CH_RCR_PBL_LEN,
+					pdata->rx_pbl);
+		writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+	}
+
+	return 0;
+}
+
+static u64 xlgmac_mmc_read(struct xlgmac_pdata *pdata, unsigned int reg_lo)
+{
+	bool read_hi;
+	u64 val;
+
+	switch (reg_lo) {
+	/* These registers are always 64 bit */
+	case MMC_TXOCTETCOUNT_GB_LO:
+	case MMC_TXOCTETCOUNT_G_LO:
+	case MMC_RXOCTETCOUNT_GB_LO:
+	case MMC_RXOCTETCOUNT_G_LO:
+		read_hi = true;
+		break;
+
+	default:
+		read_hi = false;
+	}
+
+	val = (u64)readl(pdata->mac_regs + reg_lo);
+
+	if (read_hi)
+		val |= ((u64)readl(pdata->mac_regs + reg_lo + 4) << 32);
+
+	return val;
+}
+
+static void xlgmac_tx_mmc_int(struct xlgmac_pdata *pdata)
+{
+	unsigned int mmc_isr = readl(pdata->mac_regs + MMC_TISR);
+	struct xlgmac_stats *stats = &pdata->stats;
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXOCTETCOUNT_GB_POS,
+				MMC_TISR_TXOCTETCOUNT_GB_LEN))
+		stats->txoctetcount_gb +=
+			xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXFRAMECOUNT_GB_POS,
+				MMC_TISR_TXFRAMECOUNT_GB_LEN))
+		stats->txframecount_gb +=
+			xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXBROADCASTFRAMES_G_POS,
+				MMC_TISR_TXBROADCASTFRAMES_G_LEN))
+		stats->txbroadcastframes_g +=
+			xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_G_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXMULTICASTFRAMES_G_POS,
+				MMC_TISR_TXMULTICASTFRAMES_G_LEN))
+		stats->txmulticastframes_g +=
+			xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_G_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TX64OCTETS_GB_POS,
+				MMC_TISR_TX64OCTETS_GB_LEN))
+		stats->tx64octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_TX64OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TX65TO127OCTETS_GB_POS,
+				MMC_TISR_TX65TO127OCTETS_GB_LEN))
+		stats->tx65to127octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_TX65TO127OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TX128TO255OCTETS_GB_POS,
+				MMC_TISR_TX128TO255OCTETS_GB_LEN))
+		stats->tx128to255octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_TX128TO255OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TX256TO511OCTETS_GB_POS,
+				MMC_TISR_TX256TO511OCTETS_GB_LEN))
+		stats->tx256to511octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_TX256TO511OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TX512TO1023OCTETS_GB_POS,
+				MMC_TISR_TX512TO1023OCTETS_GB_LEN))
+		stats->tx512to1023octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_TX512TO1023OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TX1024TOMAXOCTETS_GB_POS,
+				MMC_TISR_TX1024TOMAXOCTETS_GB_LEN))
+		stats->tx1024tomaxoctets_gb +=
+			xlgmac_mmc_read(pdata, MMC_TX1024TOMAXOCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXUNICASTFRAMES_GB_POS,
+				MMC_TISR_TXUNICASTFRAMES_GB_LEN))
+		stats->txunicastframes_gb +=
+			xlgmac_mmc_read(pdata, MMC_TXUNICASTFRAMES_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXMULTICASTFRAMES_GB_POS,
+				MMC_TISR_TXMULTICASTFRAMES_GB_LEN))
+		stats->txmulticastframes_gb +=
+			xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXBROADCASTFRAMES_GB_POS,
+				MMC_TISR_TXBROADCASTFRAMES_GB_LEN))
+		stats->txbroadcastframes_g +=
+			xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXUNDERFLOWERROR_POS,
+				MMC_TISR_TXUNDERFLOWERROR_LEN))
+		stats->txunderflowerror +=
+			xlgmac_mmc_read(pdata, MMC_TXUNDERFLOWERROR_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXOCTETCOUNT_G_POS,
+				MMC_TISR_TXOCTETCOUNT_G_LEN))
+		stats->txoctetcount_g +=
+			xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_G_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXFRAMECOUNT_G_POS,
+				MMC_TISR_TXFRAMECOUNT_G_LEN))
+		stats->txframecount_g +=
+			xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_G_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXPAUSEFRAMES_POS,
+				MMC_TISR_TXPAUSEFRAMES_LEN))
+		stats->txpauseframes +=
+			xlgmac_mmc_read(pdata, MMC_TXPAUSEFRAMES_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_TISR_TXVLANFRAMES_G_POS,
+				MMC_TISR_TXVLANFRAMES_G_LEN))
+		stats->txvlanframes_g +=
+			xlgmac_mmc_read(pdata, MMC_TXVLANFRAMES_G_LO);
+}
+
+static void xlgmac_rx_mmc_int(struct xlgmac_pdata *pdata)
+{
+	unsigned int mmc_isr = readl(pdata->mac_regs + MMC_RISR);
+	struct xlgmac_stats *stats = &pdata->stats;
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXFRAMECOUNT_GB_POS,
+				MMC_RISR_RXFRAMECOUNT_GB_LEN))
+		stats->rxframecount_gb +=
+			xlgmac_mmc_read(pdata, MMC_RXFRAMECOUNT_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXOCTETCOUNT_GB_POS,
+				MMC_RISR_RXOCTETCOUNT_GB_LEN))
+		stats->rxoctetcount_gb +=
+			xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXOCTETCOUNT_G_POS,
+				MMC_RISR_RXOCTETCOUNT_G_LEN))
+		stats->rxoctetcount_g +=
+			xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_G_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXBROADCASTFRAMES_G_POS,
+				MMC_RISR_RXBROADCASTFRAMES_G_LEN))
+		stats->rxbroadcastframes_g +=
+			xlgmac_mmc_read(pdata, MMC_RXBROADCASTFRAMES_G_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXMULTICASTFRAMES_G_POS,
+				MMC_RISR_RXMULTICASTFRAMES_G_LEN))
+		stats->rxmulticastframes_g +=
+			xlgmac_mmc_read(pdata, MMC_RXMULTICASTFRAMES_G_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXCRCERROR_POS,
+				MMC_RISR_RXCRCERROR_LEN))
+		stats->rxcrcerror +=
+			xlgmac_mmc_read(pdata, MMC_RXCRCERROR_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXRUNTERROR_POS,
+				MMC_RISR_RXRUNTERROR_LEN))
+		stats->rxrunterror +=
+			xlgmac_mmc_read(pdata, MMC_RXRUNTERROR);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXJABBERERROR_POS,
+				MMC_RISR_RXJABBERERROR_LEN))
+		stats->rxjabbererror +=
+			xlgmac_mmc_read(pdata, MMC_RXJABBERERROR);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXUNDERSIZE_G_POS,
+				MMC_RISR_RXUNDERSIZE_G_LEN))
+		stats->rxundersize_g +=
+			xlgmac_mmc_read(pdata, MMC_RXUNDERSIZE_G);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXOVERSIZE_G_POS,
+				MMC_RISR_RXOVERSIZE_G_LEN))
+		stats->rxoversize_g +=
+			xlgmac_mmc_read(pdata, MMC_RXOVERSIZE_G);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RX64OCTETS_GB_POS,
+				MMC_RISR_RX64OCTETS_GB_LEN))
+		stats->rx64octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_RX64OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RX65TO127OCTETS_GB_POS,
+				MMC_RISR_RX65TO127OCTETS_GB_LEN))
+		stats->rx65to127octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_RX65TO127OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RX128TO255OCTETS_GB_POS,
+				MMC_RISR_RX128TO255OCTETS_GB_LEN))
+		stats->rx128to255octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_RX128TO255OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RX256TO511OCTETS_GB_POS,
+				MMC_RISR_RX256TO511OCTETS_GB_LEN))
+		stats->rx256to511octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_RX256TO511OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RX512TO1023OCTETS_GB_POS,
+				MMC_RISR_RX512TO1023OCTETS_GB_LEN))
+		stats->rx512to1023octets_gb +=
+			xlgmac_mmc_read(pdata, MMC_RX512TO1023OCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RX1024TOMAXOCTETS_GB_POS,
+				MMC_RISR_RX1024TOMAXOCTETS_GB_LEN))
+		stats->rx1024tomaxoctets_gb +=
+			xlgmac_mmc_read(pdata, MMC_RX1024TOMAXOCTETS_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXUNICASTFRAMES_G_POS,
+				MMC_RISR_RXUNICASTFRAMES_G_LEN))
+		stats->rxunicastframes_g +=
+			xlgmac_mmc_read(pdata, MMC_RXUNICASTFRAMES_G_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXLENGTHERROR_POS,
+				MMC_RISR_RXLENGTHERROR_LEN))
+		stats->rxlengtherror +=
+			xlgmac_mmc_read(pdata, MMC_RXLENGTHERROR_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXOUTOFRANGETYPE_POS,
+				MMC_RISR_RXOUTOFRANGETYPE_LEN))
+		stats->rxoutofrangetype +=
+			xlgmac_mmc_read(pdata, MMC_RXOUTOFRANGETYPE_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXPAUSEFRAMES_POS,
+				MMC_RISR_RXPAUSEFRAMES_LEN))
+		stats->rxpauseframes +=
+			xlgmac_mmc_read(pdata, MMC_RXPAUSEFRAMES_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXFIFOOVERFLOW_POS,
+				MMC_RISR_RXFIFOOVERFLOW_LEN))
+		stats->rxfifooverflow +=
+			xlgmac_mmc_read(pdata, MMC_RXFIFOOVERFLOW_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXVLANFRAMES_GB_POS,
+				MMC_RISR_RXVLANFRAMES_GB_LEN))
+		stats->rxvlanframes_gb +=
+			xlgmac_mmc_read(pdata, MMC_RXVLANFRAMES_GB_LO);
+
+	if (XLGMAC_GET_REG_BITS(mmc_isr,
+				MMC_RISR_RXWATCHDOGERROR_POS,
+				MMC_RISR_RXWATCHDOGERROR_LEN))
+		stats->rxwatchdogerror +=
+			xlgmac_mmc_read(pdata, MMC_RXWATCHDOGERROR);
+}
+
+static void xlgmac_read_mmc_stats(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_stats *stats = &pdata->stats;
+	u32 regval;
+
+	/* Freeze counters */
+	regval = readl(pdata->mac_regs + MMC_CR);
+	regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_MCF_POS,
+				     MMC_CR_MCF_LEN, 1);
+	writel(regval, pdata->mac_regs + MMC_CR);
+
+	stats->txoctetcount_gb +=
+		xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_GB_LO);
+
+	stats->txframecount_gb +=
+		xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_GB_LO);
+
+	stats->txbroadcastframes_g +=
+		xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_G_LO);
+
+	stats->txmulticastframes_g +=
+		xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_G_LO);
+
+	stats->tx64octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_TX64OCTETS_GB_LO);
+
+	stats->tx65to127octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_TX65TO127OCTETS_GB_LO);
+
+	stats->tx128to255octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_TX128TO255OCTETS_GB_LO);
+
+	stats->tx256to511octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_TX256TO511OCTETS_GB_LO);
+
+	stats->tx512to1023octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_TX512TO1023OCTETS_GB_LO);
+
+	stats->tx1024tomaxoctets_gb +=
+		xlgmac_mmc_read(pdata, MMC_TX1024TOMAXOCTETS_GB_LO);
+
+	stats->txunicastframes_gb +=
+		xlgmac_mmc_read(pdata, MMC_TXUNICASTFRAMES_GB_LO);
+
+	stats->txmulticastframes_gb +=
+		xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_GB_LO);
+
+	stats->txbroadcastframes_g +=
+		xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_GB_LO);
+
+	stats->txunderflowerror +=
+		xlgmac_mmc_read(pdata, MMC_TXUNDERFLOWERROR_LO);
+
+	stats->txoctetcount_g +=
+		xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_G_LO);
+
+	stats->txframecount_g +=
+		xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_G_LO);
+
+	stats->txpauseframes +=
+		xlgmac_mmc_read(pdata, MMC_TXPAUSEFRAMES_LO);
+
+	stats->txvlanframes_g +=
+		xlgmac_mmc_read(pdata, MMC_TXVLANFRAMES_G_LO);
+
+	stats->rxframecount_gb +=
+		xlgmac_mmc_read(pdata, MMC_RXFRAMECOUNT_GB_LO);
+
+	stats->rxoctetcount_gb +=
+		xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_GB_LO);
+
+	stats->rxoctetcount_g +=
+		xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_G_LO);
+
+	stats->rxbroadcastframes_g +=
+		xlgmac_mmc_read(pdata, MMC_RXBROADCASTFRAMES_G_LO);
+
+	stats->rxmulticastframes_g +=
+		xlgmac_mmc_read(pdata, MMC_RXMULTICASTFRAMES_G_LO);
+
+	stats->rxcrcerror +=
+		xlgmac_mmc_read(pdata, MMC_RXCRCERROR_LO);
+
+	stats->rxrunterror +=
+		xlgmac_mmc_read(pdata, MMC_RXRUNTERROR);
+
+	stats->rxjabbererror +=
+		xlgmac_mmc_read(pdata, MMC_RXJABBERERROR);
+
+	stats->rxundersize_g +=
+		xlgmac_mmc_read(pdata, MMC_RXUNDERSIZE_G);
+
+	stats->rxoversize_g +=
+		xlgmac_mmc_read(pdata, MMC_RXOVERSIZE_G);
+
+	stats->rx64octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_RX64OCTETS_GB_LO);
+
+	stats->rx65to127octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_RX65TO127OCTETS_GB_LO);
+
+	stats->rx128to255octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_RX128TO255OCTETS_GB_LO);
+
+	stats->rx256to511octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_RX256TO511OCTETS_GB_LO);
+
+	stats->rx512to1023octets_gb +=
+		xlgmac_mmc_read(pdata, MMC_RX512TO1023OCTETS_GB_LO);
+
+	stats->rx1024tomaxoctets_gb +=
+		xlgmac_mmc_read(pdata, MMC_RX1024TOMAXOCTETS_GB_LO);
+
+	stats->rxunicastframes_g +=
+		xlgmac_mmc_read(pdata, MMC_RXUNICASTFRAMES_G_LO);
+
+	stats->rxlengtherror +=
+		xlgmac_mmc_read(pdata, MMC_RXLENGTHERROR_LO);
+
+	stats->rxoutofrangetype +=
+		xlgmac_mmc_read(pdata, MMC_RXOUTOFRANGETYPE_LO);
+
+	stats->rxpauseframes +=
+		xlgmac_mmc_read(pdata, MMC_RXPAUSEFRAMES_LO);
+
+	stats->rxfifooverflow +=
+		xlgmac_mmc_read(pdata, MMC_RXFIFOOVERFLOW_LO);
+
+	stats->rxvlanframes_gb +=
+		xlgmac_mmc_read(pdata, MMC_RXVLANFRAMES_GB_LO);
+
+	stats->rxwatchdogerror +=
+		xlgmac_mmc_read(pdata, MMC_RXWATCHDOGERROR);
+
+	/* Un-freeze counters */
+	regval = readl(pdata->mac_regs + MMC_CR);
+	regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_MCF_POS,
+				     MMC_CR_MCF_LEN, 0);
+	writel(regval, pdata->mac_regs + MMC_CR);
+}
+
+static void xlgmac_config_mmc(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + MMC_CR);
+	/* Set counters to reset on read */
+	regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_ROR_POS,
+				     MMC_CR_ROR_LEN, 1);
+	/* Reset the counters */
+	regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_CR_POS,
+				     MMC_CR_CR_LEN, 1);
+	writel(regval, pdata->mac_regs + MMC_CR);
+}
+
+static int xlgmac_write_rss_reg(struct xlgmac_pdata *pdata, unsigned int type,
+				unsigned int index, unsigned int val)
+{
+	unsigned int wait;
+	int ret = 0;
+	u32 regval;
+
+	mutex_lock(&pdata->rss_mutex);
+
+	regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_RSSAR),
+				     MAC_RSSAR_OB_POS, MAC_RSSAR_OB_LEN);
+	if (regval) {
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	writel(val, pdata->mac_regs + MAC_RSSDR);
+
+	regval = readl(pdata->mac_regs + MAC_RSSAR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_RSSIA_POS,
+				     MAC_RSSAR_RSSIA_LEN, index);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_ADDRT_POS,
+				     MAC_RSSAR_ADDRT_LEN, type);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_CT_POS,
+				     MAC_RSSAR_CT_LEN, 0);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_OB_POS,
+				     MAC_RSSAR_OB_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_RSSAR);
+
+	wait = 1000;
+	while (wait--) {
+		regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_RSSAR),
+					     MAC_RSSAR_OB_POS,
+					     MAC_RSSAR_OB_LEN);
+		if (!regval)
+			goto unlock;
+
+		usleep_range(1000, 1500);
+	}
+
+	ret = -EBUSY;
+
+unlock:
+	mutex_unlock(&pdata->rss_mutex);
+
+	return ret;
+}
+
+static int xlgmac_write_rss_hash_key(struct xlgmac_pdata *pdata)
+{
+	unsigned int key_regs = sizeof(pdata->rss_key) / sizeof(u32);
+	unsigned int *key = (unsigned int *)&pdata->rss_key;
+	int ret;
+
+	while (key_regs--) {
+		ret = xlgmac_write_rss_reg(pdata, XLGMAC_RSS_HASH_KEY_TYPE,
+					   key_regs, *key++);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int xlgmac_write_rss_lookup_table(struct xlgmac_pdata *pdata)
+{
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < ARRAY_SIZE(pdata->rss_table); i++) {
+		ret = xlgmac_write_rss_reg(pdata,
+					   XLGMAC_RSS_LOOKUP_TABLE_TYPE, i,
+					   pdata->rss_table[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int xlgmac_set_rss_hash_key(struct xlgmac_pdata *pdata, const u8 *key)
+{
+	memcpy(pdata->rss_key, key, sizeof(pdata->rss_key));
+
+	return xlgmac_write_rss_hash_key(pdata);
+}
+
+static int xlgmac_set_rss_lookup_table(struct xlgmac_pdata *pdata,
+				       const u32 *table)
+{
+	unsigned int i;
+	u32 tval;
+
+	for (i = 0; i < ARRAY_SIZE(pdata->rss_table); i++) {
+		tval = table[i];
+		pdata->rss_table[i] = XLGMAC_SET_REG_BITS(
+						pdata->rss_table[i],
+						MAC_RSSDR_DMCH_POS,
+						MAC_RSSDR_DMCH_LEN,
+						tval);
+	}
+
+	return xlgmac_write_rss_lookup_table(pdata);
+}
+
+static int xlgmac_enable_rss(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+	int ret;
+
+	if (!pdata->hw_feat.rss)
+		return -EOPNOTSUPP;
+
+	/* Program the hash key */
+	ret = xlgmac_write_rss_hash_key(pdata);
+	if (ret)
+		return ret;
+
+	/* Program the lookup table */
+	ret = xlgmac_write_rss_lookup_table(pdata);
+	if (ret)
+		return ret;
+
+	/* Set the RSS options */
+	writel(pdata->rss_options, pdata->mac_regs + MAC_RSSCR);
+
+	/* Enable RSS */
+	regval = readl(pdata->mac_regs + MAC_RSSCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSCR_RSSE_POS,
+				     MAC_RSSCR_RSSE_LEN, 1);
+	writel(regval, pdata->mac_regs + MAC_RSSCR);
+
+	return 0;
+}
+
+static int xlgmac_disable_rss(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	if (!pdata->hw_feat.rss)
+		return -EOPNOTSUPP;
+
+	regval = readl(pdata->mac_regs + MAC_RSSCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSCR_RSSE_POS,
+				     MAC_RSSCR_RSSE_LEN, 0);
+	writel(regval, pdata->mac_regs + MAC_RSSCR);
+
+	return 0;
+}
+
+static void xlgmac_config_rss(struct xlgmac_pdata *pdata)
+{
+	int ret;
+
+	if (!pdata->hw_feat.rss)
+		return;
+
+	if (pdata->netdev->features & NETIF_F_RXHASH)
+		ret = xlgmac_enable_rss(pdata);
+	else
+		ret = xlgmac_disable_rss(pdata);
+
+	if (ret)
+		netdev_err(pdata->netdev,
+			   "error configuring RSS, RSS disabled\n");
+}
+
+static void xlgmac_enable_dma_interrupts(struct xlgmac_pdata *pdata)
+{
+	unsigned int dma_ch_isr, dma_ch_ier;
+	struct xlgmac_channel *channel;
+	unsigned int i;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		/* Clear all the interrupts which are set */
+		dma_ch_isr = readl(XLGMAC_DMA_REG(channel, DMA_CH_SR));
+		writel(dma_ch_isr, XLGMAC_DMA_REG(channel, DMA_CH_SR));
+
+		/* Clear all interrupt enable bits */
+		dma_ch_ier = 0;
+
+		/* Enable following interrupts
+		 *   NIE  - Normal Interrupt Summary Enable
+		 *   AIE  - Abnormal Interrupt Summary Enable
+		 *   FBEE - Fatal Bus Error Enable
+		 */
+		dma_ch_ier = XLGMAC_SET_REG_BITS(dma_ch_ier,
+						 DMA_CH_IER_NIE_POS,
+					DMA_CH_IER_NIE_LEN, 1);
+		dma_ch_ier = XLGMAC_SET_REG_BITS(dma_ch_ier,
+						 DMA_CH_IER_AIE_POS,
+					DMA_CH_IER_AIE_LEN, 1);
+		dma_ch_ier = XLGMAC_SET_REG_BITS(dma_ch_ier,
+						 DMA_CH_IER_FBEE_POS,
+					DMA_CH_IER_FBEE_LEN, 1);
+
+		if (channel->tx_ring) {
+			/* Enable the following Tx interrupts
+			 *   TIE  - Transmit Interrupt Enable (unless using
+			 *          per channel interrupts)
+			 */
+			if (!pdata->per_channel_irq)
+				dma_ch_ier = XLGMAC_SET_REG_BITS(
+						dma_ch_ier,
+						DMA_CH_IER_TIE_POS,
+						DMA_CH_IER_TIE_LEN,
+						1);
+		}
+		if (channel->rx_ring) {
+			/* Enable following Rx interrupts
+			 *   RBUE - Receive Buffer Unavailable Enable
+			 *   RIE  - Receive Interrupt Enable (unless using
+			 *          per channel interrupts)
+			 */
+			dma_ch_ier = XLGMAC_SET_REG_BITS(
+					dma_ch_ier,
+					DMA_CH_IER_RBUE_POS,
+					DMA_CH_IER_RBUE_LEN,
+					1);
+			if (!pdata->per_channel_irq)
+				dma_ch_ier = XLGMAC_SET_REG_BITS(
+						dma_ch_ier,
+						DMA_CH_IER_RIE_POS,
+						DMA_CH_IER_RIE_LEN,
+						1);
+		}
+
+		writel(dma_ch_isr, XLGMAC_DMA_REG(channel, DMA_CH_IER));
+	}
+}
+
+static void xlgmac_enable_mtl_interrupts(struct xlgmac_pdata *pdata)
+{
+	unsigned int q_count, i;
+	unsigned int mtl_q_isr;
+
+	q_count = max(pdata->hw_feat.tx_q_cnt, pdata->hw_feat.rx_q_cnt);
+	for (i = 0; i < q_count; i++) {
+		/* Clear all the interrupts which are set */
+		mtl_q_isr = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_ISR));
+		writel(mtl_q_isr, XLGMAC_MTL_REG(pdata, i, MTL_Q_ISR));
+
+		/* No MTL interrupts to be enabled */
+		writel(0, XLGMAC_MTL_REG(pdata, i, MTL_Q_IER));
+	}
+}
+
+static void xlgmac_enable_mac_interrupts(struct xlgmac_pdata *pdata)
+{
+	unsigned int mac_ier = 0;
+	u32 regval;
+
+	/* Enable Timestamp interrupt */
+	mac_ier = XLGMAC_SET_REG_BITS(mac_ier, MAC_IER_TSIE_POS,
+				      MAC_IER_TSIE_LEN, 1);
+
+	writel(mac_ier, pdata->mac_regs + MAC_IER);
+
+	/* Enable all counter interrupts */
+	regval = readl(pdata->mac_regs + MMC_RIER);
+	regval = XLGMAC_SET_REG_BITS(regval, MMC_RIER_ALL_INTERRUPTS_POS,
+				     MMC_RIER_ALL_INTERRUPTS_LEN, 0xffffffff);
+	writel(regval, pdata->mac_regs + MMC_RIER);
+	regval = readl(pdata->mac_regs + MMC_TIER);
+	regval = XLGMAC_SET_REG_BITS(regval, MMC_TIER_ALL_INTERRUPTS_POS,
+				     MMC_TIER_ALL_INTERRUPTS_LEN, 0xffffffff);
+	writel(regval, pdata->mac_regs + MMC_TIER);
+}
+
+static int xlgmac_set_xlgmii_25000_speed(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR),
+				     MAC_TCR_SS_POS, MAC_TCR_SS_LEN);
+	if (regval == 0x1)
+		return 0;
+
+	regval = readl(pdata->mac_regs + MAC_TCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS,
+				     MAC_TCR_SS_LEN, 0x1);
+	writel(regval, pdata->mac_regs + MAC_TCR);
+
+	return 0;
+}
+
+static int xlgmac_set_xlgmii_40000_speed(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR),
+				     MAC_TCR_SS_POS, MAC_TCR_SS_LEN);
+	if (regval == 0)
+		return 0;
+
+	regval = readl(pdata->mac_regs + MAC_TCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS,
+				     MAC_TCR_SS_LEN, 0);
+	writel(regval, pdata->mac_regs + MAC_TCR);
+
+	return 0;
+}
+
+static int xlgmac_set_xlgmii_50000_speed(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR),
+				     MAC_TCR_SS_POS, MAC_TCR_SS_LEN);
+	if (regval == 0x2)
+		return 0;
+
+	regval = readl(pdata->mac_regs + MAC_TCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS,
+				     MAC_TCR_SS_LEN, 0x2);
+	writel(regval, pdata->mac_regs + MAC_TCR);
+
+	return 0;
+}
+
+static int xlgmac_set_xlgmii_100000_speed(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR),
+				     MAC_TCR_SS_POS, MAC_TCR_SS_LEN);
+	if (regval == 0x3)
+		return 0;
+
+	regval = readl(pdata->mac_regs + MAC_TCR);
+	regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS,
+				     MAC_TCR_SS_LEN, 0x3);
+	writel(regval, pdata->mac_regs + MAC_TCR);
+
+	return 0;
+}
+
+static void xlgmac_config_mac_speed(struct xlgmac_pdata *pdata)
+{
+	switch (pdata->phy_speed) {
+	case SPEED_100000:
+		xlgmac_set_xlgmii_100000_speed(pdata);
+		break;
+
+	case SPEED_50000:
+		xlgmac_set_xlgmii_50000_speed(pdata);
+		break;
+
+	case SPEED_40000:
+		xlgmac_set_xlgmii_40000_speed(pdata);
+		break;
+
+	case SPEED_25000:
+		xlgmac_set_xlgmii_25000_speed(pdata);
+		break;
+	}
+}
+
+static int xlgmac_dev_read(struct xlgmac_channel *channel)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct xlgmac_ring *ring = channel->rx_ring;
+	struct net_device *netdev = pdata->netdev;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_dma_desc *dma_desc;
+	struct xlgmac_pkt_info *pkt_info;
+	unsigned int err, etlt, l34t;
+
+	desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur);
+	dma_desc = desc_data->dma_desc;
+	pkt_info = &ring->pkt_info;
+
+	/* Check for data availability */
+	if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				   RX_NORMAL_DESC3_OWN_POS,
+				   RX_NORMAL_DESC3_OWN_LEN))
+		return 1;
+
+	/* Make sure descriptor fields are read after reading the OWN bit */
+	dma_rmb();
+
+	if (netif_msg_rx_status(pdata))
+		xlgmac_dump_rx_desc(pdata, ring, ring->cur);
+
+	if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				   RX_NORMAL_DESC3_CTXT_POS,
+				   RX_NORMAL_DESC3_CTXT_LEN)) {
+		/* Timestamp Context Descriptor */
+		xlgmac_get_rx_tstamp(pkt_info, dma_desc);
+
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+					pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_CONTEXT_POS,
+					RX_PACKET_ATTRIBUTES_CONTEXT_LEN,
+					1);
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+				pkt_info->attributes,
+				RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS,
+				RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN,
+				0);
+		return 0;
+	}
+
+	/* Normal Descriptor, be sure Context Descriptor bit is off */
+	pkt_info->attributes = XLGMAC_SET_REG_BITS(
+				pkt_info->attributes,
+				RX_PACKET_ATTRIBUTES_CONTEXT_POS,
+				RX_PACKET_ATTRIBUTES_CONTEXT_LEN,
+				0);
+
+	/* Indicate if a Context Descriptor is next */
+	if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				   RX_NORMAL_DESC3_CDA_POS,
+				   RX_NORMAL_DESC3_CDA_LEN))
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+				pkt_info->attributes,
+				RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS,
+				RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN,
+				1);
+
+	/* Get the header length */
+	if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				   RX_NORMAL_DESC3_FD_POS,
+				   RX_NORMAL_DESC3_FD_LEN)) {
+		desc_data->rx.hdr_len = XLGMAC_GET_REG_BITS_LE(dma_desc->desc2,
+							RX_NORMAL_DESC2_HL_POS,
+							RX_NORMAL_DESC2_HL_LEN);
+		if (desc_data->rx.hdr_len)
+			pdata->stats.rx_split_header_packets++;
+	}
+
+	/* Get the RSS hash */
+	if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				   RX_NORMAL_DESC3_RSV_POS,
+				   RX_NORMAL_DESC3_RSV_LEN)) {
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+				pkt_info->attributes,
+				RX_PACKET_ATTRIBUTES_RSS_HASH_POS,
+				RX_PACKET_ATTRIBUTES_RSS_HASH_LEN,
+				1);
+
+		pkt_info->rss_hash = le32_to_cpu(dma_desc->desc1);
+
+		l34t = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+					      RX_NORMAL_DESC3_L34T_POS,
+					  RX_NORMAL_DESC3_L34T_LEN);
+		switch (l34t) {
+		case RX_DESC3_L34T_IPV4_TCP:
+		case RX_DESC3_L34T_IPV4_UDP:
+		case RX_DESC3_L34T_IPV6_TCP:
+		case RX_DESC3_L34T_IPV6_UDP:
+			pkt_info->rss_hash_type = PKT_HASH_TYPE_L4;
+			break;
+		default:
+			pkt_info->rss_hash_type = PKT_HASH_TYPE_L3;
+		}
+	}
+
+	/* Get the pkt_info length */
+	desc_data->rx.len = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+					RX_NORMAL_DESC3_PL_POS,
+					RX_NORMAL_DESC3_PL_LEN);
+
+	if (!XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				    RX_NORMAL_DESC3_LD_POS,
+				    RX_NORMAL_DESC3_LD_LEN)) {
+		/* Not all the data has been transferred for this pkt_info */
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+				pkt_info->attributes,
+				RX_PACKET_ATTRIBUTES_INCOMPLETE_POS,
+				RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN,
+				1);
+		return 0;
+	}
+
+	/* This is the last of the data for this pkt_info */
+	pkt_info->attributes = XLGMAC_SET_REG_BITS(
+			pkt_info->attributes,
+			RX_PACKET_ATTRIBUTES_INCOMPLETE_POS,
+			RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN,
+			0);
+
+	/* Set checksum done indicator as appropriate */
+	if (netdev->features & NETIF_F_RXCSUM)
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+				pkt_info->attributes,
+				RX_PACKET_ATTRIBUTES_CSUM_DONE_POS,
+				RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN,
+				1);
+
+	/* Check for errors (only valid in last descriptor) */
+	err = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				     RX_NORMAL_DESC3_ES_POS,
+				     RX_NORMAL_DESC3_ES_LEN);
+	etlt = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+				      RX_NORMAL_DESC3_ETLT_POS,
+				      RX_NORMAL_DESC3_ETLT_LEN);
+	netif_dbg(pdata, rx_status, netdev, "err=%u, etlt=%#x\n", err, etlt);
+
+	if (!err || !etlt) {
+		/* No error if err is 0 or etlt is 0 */
+		if ((etlt == 0x09) &&
+		    (netdev->features & NETIF_F_HW_VLAN_CTAG_RX)) {
+			pkt_info->attributes = XLGMAC_SET_REG_BITS(
+					pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_VLAN_CTAG_POS,
+					RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN,
+					1);
+			pkt_info->vlan_ctag =
+				XLGMAC_GET_REG_BITS_LE(dma_desc->desc0,
+						       RX_NORMAL_DESC0_OVT_POS,
+						   RX_NORMAL_DESC0_OVT_LEN);
+			netif_dbg(pdata, rx_status, netdev, "vlan-ctag=%#06x\n",
+				  pkt_info->vlan_ctag);
+		}
+	} else {
+		if ((etlt == 0x05) || (etlt == 0x06))
+			pkt_info->attributes = XLGMAC_SET_REG_BITS(
+					pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_CSUM_DONE_POS,
+					RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN,
+					0);
+		else
+			pkt_info->errors = XLGMAC_SET_REG_BITS(
+					pkt_info->errors,
+					RX_PACKET_ERRORS_FRAME_POS,
+					RX_PACKET_ERRORS_FRAME_LEN,
+					1);
+	}
+
+	XLGMAC_PR("%s - descriptor=%u (cur=%d)\n", channel->name,
+		  ring->cur & (ring->dma_desc_count - 1), ring->cur);
+
+	return 0;
+}
+
+static int xlgmac_enable_int(struct xlgmac_channel *channel,
+			     enum xlgmac_int int_id)
+{
+	unsigned int dma_ch_ier;
+
+	dma_ch_ier = readl(XLGMAC_DMA_REG(channel, DMA_CH_IER));
+
+	switch (int_id) {
+	case XLGMAC_INT_DMA_CH_SR_TI:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_TIE_POS,
+				DMA_CH_IER_TIE_LEN, 1);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_TPS:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_TXSE_POS,
+				DMA_CH_IER_TXSE_LEN, 1);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_TBU:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_TBUE_POS,
+				DMA_CH_IER_TBUE_LEN, 1);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_RI:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_RIE_POS,
+				DMA_CH_IER_RIE_LEN, 1);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_RBU:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_RBUE_POS,
+				DMA_CH_IER_RBUE_LEN, 1);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_RPS:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_RSE_POS,
+				DMA_CH_IER_RSE_LEN, 1);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_TI_RI:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_TIE_POS,
+				DMA_CH_IER_TIE_LEN, 1);
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_RIE_POS,
+				DMA_CH_IER_RIE_LEN, 1);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_FBE:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_FBEE_POS,
+				DMA_CH_IER_FBEE_LEN, 1);
+		break;
+	case XLGMAC_INT_DMA_ALL:
+		dma_ch_ier |= channel->saved_ier;
+		break;
+	default:
+		return -1;
+	}
+
+	writel(dma_ch_ier, XLGMAC_DMA_REG(channel, DMA_CH_IER));
+
+	return 0;
+}
+
+static int xlgmac_disable_int(struct xlgmac_channel *channel,
+			      enum xlgmac_int int_id)
+{
+	unsigned int dma_ch_ier;
+
+	dma_ch_ier = readl(XLGMAC_DMA_REG(channel, DMA_CH_IER));
+
+	switch (int_id) {
+	case XLGMAC_INT_DMA_CH_SR_TI:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_TIE_POS,
+				DMA_CH_IER_TIE_LEN, 0);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_TPS:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_TXSE_POS,
+				DMA_CH_IER_TXSE_LEN, 0);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_TBU:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_TBUE_POS,
+				DMA_CH_IER_TBUE_LEN, 0);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_RI:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_RIE_POS,
+				DMA_CH_IER_RIE_LEN, 0);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_RBU:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_RBUE_POS,
+				DMA_CH_IER_RBUE_LEN, 0);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_RPS:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_RSE_POS,
+				DMA_CH_IER_RSE_LEN, 0);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_TI_RI:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_TIE_POS,
+				DMA_CH_IER_TIE_LEN, 0);
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_RIE_POS,
+				DMA_CH_IER_RIE_LEN, 0);
+		break;
+	case XLGMAC_INT_DMA_CH_SR_FBE:
+		dma_ch_ier = XLGMAC_SET_REG_BITS(
+				dma_ch_ier, DMA_CH_IER_FBEE_POS,
+				DMA_CH_IER_FBEE_LEN, 0);
+		break;
+	case XLGMAC_INT_DMA_ALL:
+		channel->saved_ier = dma_ch_ier & XLGMAC_DMA_INTERRUPT_MASK;
+		dma_ch_ier &= ~XLGMAC_DMA_INTERRUPT_MASK;
+		break;
+	default:
+		return -1;
+	}
+
+	writel(dma_ch_ier, XLGMAC_DMA_REG(channel, DMA_CH_IER));
+
+	return 0;
+}
+
+static int xlgmac_flush_tx_queues(struct xlgmac_pdata *pdata)
+{
+	unsigned int i, count;
+	u32 regval;
+
+	for (i = 0; i < pdata->tx_q_count; i++) {
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+		regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_FTQ_POS,
+					     MTL_Q_TQOMR_FTQ_LEN, 1);
+		writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+	}
+
+	/* Poll Until Poll Condition */
+	for (i = 0; i < pdata->tx_q_count; i++) {
+		count = 2000;
+		regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+		regval = XLGMAC_GET_REG_BITS(regval, MTL_Q_TQOMR_FTQ_POS,
+					     MTL_Q_TQOMR_FTQ_LEN);
+		while (--count && regval)
+			usleep_range(500, 600);
+
+		if (!count)
+			return -EBUSY;
+	}
+
+	return 0;
+}
+
+static void xlgmac_config_dma_bus(struct xlgmac_pdata *pdata)
+{
+	u32 regval;
+
+	regval = readl(pdata->mac_regs + DMA_SBMR);
+	/* Set enhanced addressing mode */
+	regval = XLGMAC_SET_REG_BITS(regval, DMA_SBMR_EAME_POS,
+				     DMA_SBMR_EAME_LEN, 1);
+	/* Set the System Bus mode */
+	regval = XLGMAC_SET_REG_BITS(regval, DMA_SBMR_UNDEF_POS,
+				     DMA_SBMR_UNDEF_LEN, 1);
+	regval = XLGMAC_SET_REG_BITS(regval, DMA_SBMR_BLEN_256_POS,
+				     DMA_SBMR_BLEN_256_LEN, 1);
+	writel(regval, pdata->mac_regs + DMA_SBMR);
+}
+
+static int xlgmac_hw_init(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_desc_ops *desc_ops = &pdata->desc_ops;
+	int ret;
+
+	/* Flush Tx queues */
+	ret = xlgmac_flush_tx_queues(pdata);
+	if (ret)
+		return ret;
+
+	/* Initialize DMA related features */
+	xlgmac_config_dma_bus(pdata);
+	xlgmac_config_osp_mode(pdata);
+	xlgmac_config_pblx8(pdata);
+	xlgmac_config_tx_pbl_val(pdata);
+	xlgmac_config_rx_pbl_val(pdata);
+	xlgmac_config_rx_coalesce(pdata);
+	xlgmac_config_tx_coalesce(pdata);
+	xlgmac_config_rx_buffer_size(pdata);
+	xlgmac_config_tso_mode(pdata);
+	xlgmac_config_sph_mode(pdata);
+	xlgmac_config_rss(pdata);
+	desc_ops->tx_desc_init(pdata);
+	desc_ops->rx_desc_init(pdata);
+	xlgmac_enable_dma_interrupts(pdata);
+
+	/* Initialize MTL related features */
+	xlgmac_config_mtl_mode(pdata);
+	xlgmac_config_queue_mapping(pdata);
+	xlgmac_config_tsf_mode(pdata, pdata->tx_sf_mode);
+	xlgmac_config_rsf_mode(pdata, pdata->rx_sf_mode);
+	xlgmac_config_tx_threshold(pdata, pdata->tx_threshold);
+	xlgmac_config_rx_threshold(pdata, pdata->rx_threshold);
+	xlgmac_config_tx_fifo_size(pdata);
+	xlgmac_config_rx_fifo_size(pdata);
+	xlgmac_config_flow_control_threshold(pdata);
+	xlgmac_config_rx_fep_enable(pdata);
+	xlgmac_config_rx_fup_enable(pdata);
+	xlgmac_enable_mtl_interrupts(pdata);
+
+	/* Initialize MAC related features */
+	xlgmac_config_mac_address(pdata);
+	xlgmac_config_rx_mode(pdata);
+	xlgmac_config_jumbo_enable(pdata);
+	xlgmac_config_flow_control(pdata);
+	xlgmac_config_mac_speed(pdata);
+	xlgmac_config_checksum_offload(pdata);
+	xlgmac_config_vlan_support(pdata);
+	xlgmac_config_mmc(pdata);
+	xlgmac_enable_mac_interrupts(pdata);
+
+	return 0;
+}
+
+static int xlgmac_hw_exit(struct xlgmac_pdata *pdata)
+{
+	unsigned int count = 2000;
+	u32 regval;
+
+	/* Issue a software reset */
+	regval = readl(pdata->mac_regs + DMA_MR);
+	regval = XLGMAC_SET_REG_BITS(regval, DMA_MR_SWR_POS,
+				     DMA_MR_SWR_LEN, 1);
+	writel(regval, pdata->mac_regs + DMA_MR);
+	usleep_range(10, 15);
+
+	/* Poll Until Poll Condition */
+	while (--count &&
+	       XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + DMA_MR),
+				   DMA_MR_SWR_POS, DMA_MR_SWR_LEN))
+		usleep_range(500, 600);
+
+	if (!count)
+		return -EBUSY;
+
+	return 0;
+}
+
+void xlgmac_init_hw_ops(struct xlgmac_hw_ops *hw_ops)
+{
+	hw_ops->init = xlgmac_hw_init;
+	hw_ops->exit = xlgmac_hw_exit;
+
+	hw_ops->tx_complete = xlgmac_tx_complete;
+
+	hw_ops->enable_tx = xlgmac_enable_tx;
+	hw_ops->disable_tx = xlgmac_disable_tx;
+	hw_ops->enable_rx = xlgmac_enable_rx;
+	hw_ops->disable_rx = xlgmac_disable_rx;
+
+	hw_ops->dev_xmit = xlgmac_dev_xmit;
+	hw_ops->dev_read = xlgmac_dev_read;
+	hw_ops->enable_int = xlgmac_enable_int;
+	hw_ops->disable_int = xlgmac_disable_int;
+
+	hw_ops->set_mac_address = xlgmac_set_mac_address;
+	hw_ops->config_rx_mode = xlgmac_config_rx_mode;
+	hw_ops->enable_rx_csum = xlgmac_enable_rx_csum;
+	hw_ops->disable_rx_csum = xlgmac_disable_rx_csum;
+
+	/* For MII speed configuration */
+	hw_ops->set_xlgmii_25000_speed = xlgmac_set_xlgmii_25000_speed;
+	hw_ops->set_xlgmii_40000_speed = xlgmac_set_xlgmii_40000_speed;
+	hw_ops->set_xlgmii_50000_speed = xlgmac_set_xlgmii_50000_speed;
+	hw_ops->set_xlgmii_100000_speed = xlgmac_set_xlgmii_100000_speed;
+
+	/* For descriptor related operation */
+	hw_ops->tx_desc_init = xlgmac_tx_desc_init;
+	hw_ops->rx_desc_init = xlgmac_rx_desc_init;
+	hw_ops->tx_desc_reset = xlgmac_tx_desc_reset;
+	hw_ops->rx_desc_reset = xlgmac_rx_desc_reset;
+	hw_ops->is_last_desc = xlgmac_is_last_desc;
+	hw_ops->is_context_desc = xlgmac_is_context_desc;
+	hw_ops->tx_start_xmit = xlgmac_tx_start_xmit;
+
+	/* For Flow Control */
+	hw_ops->config_tx_flow_control = xlgmac_config_tx_flow_control;
+	hw_ops->config_rx_flow_control = xlgmac_config_rx_flow_control;
+
+	/* For Vlan related config */
+	hw_ops->enable_rx_vlan_stripping = xlgmac_enable_rx_vlan_stripping;
+	hw_ops->disable_rx_vlan_stripping = xlgmac_disable_rx_vlan_stripping;
+	hw_ops->enable_rx_vlan_filtering = xlgmac_enable_rx_vlan_filtering;
+	hw_ops->disable_rx_vlan_filtering = xlgmac_disable_rx_vlan_filtering;
+	hw_ops->update_vlan_hash_table = xlgmac_update_vlan_hash_table;
+
+	/* For RX coalescing */
+	hw_ops->config_rx_coalesce = xlgmac_config_rx_coalesce;
+	hw_ops->config_tx_coalesce = xlgmac_config_tx_coalesce;
+	hw_ops->usec_to_riwt = xlgmac_usec_to_riwt;
+	hw_ops->riwt_to_usec = xlgmac_riwt_to_usec;
+
+	/* For RX and TX threshold config */
+	hw_ops->config_rx_threshold = xlgmac_config_rx_threshold;
+	hw_ops->config_tx_threshold = xlgmac_config_tx_threshold;
+
+	/* For RX and TX Store and Forward Mode config */
+	hw_ops->config_rsf_mode = xlgmac_config_rsf_mode;
+	hw_ops->config_tsf_mode = xlgmac_config_tsf_mode;
+
+	/* For TX DMA Operating on Second Frame config */
+	hw_ops->config_osp_mode = xlgmac_config_osp_mode;
+
+	/* For RX and TX PBL config */
+	hw_ops->config_rx_pbl_val = xlgmac_config_rx_pbl_val;
+	hw_ops->get_rx_pbl_val = xlgmac_get_rx_pbl_val;
+	hw_ops->config_tx_pbl_val = xlgmac_config_tx_pbl_val;
+	hw_ops->get_tx_pbl_val = xlgmac_get_tx_pbl_val;
+	hw_ops->config_pblx8 = xlgmac_config_pblx8;
+
+	/* For MMC statistics support */
+	hw_ops->tx_mmc_int = xlgmac_tx_mmc_int;
+	hw_ops->rx_mmc_int = xlgmac_rx_mmc_int;
+	hw_ops->read_mmc_stats = xlgmac_read_mmc_stats;
+
+	/* For Receive Side Scaling */
+	hw_ops->enable_rss = xlgmac_enable_rss;
+	hw_ops->disable_rss = xlgmac_disable_rss;
+	hw_ops->set_rss_hash_key = xlgmac_set_rss_hash_key;
+	hw_ops->set_rss_lookup_table = xlgmac_set_rss_lookup_table;
+}
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c
new file mode 100644
index 000000000000..6acf86ced61d
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c
@@ -0,0 +1,1332 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/tcp.h>
+
+#include "dwc-xlgmac.h"
+#include "dwc-xlgmac-reg.h"
+
+static int xlgmac_one_poll(struct napi_struct *, int);
+static int xlgmac_all_poll(struct napi_struct *, int);
+
+static inline unsigned int xlgmac_tx_avail_desc(struct xlgmac_ring *ring)
+{
+	return (ring->dma_desc_count - (ring->cur - ring->dirty));
+}
+
+static inline unsigned int xlgmac_rx_dirty_desc(struct xlgmac_ring *ring)
+{
+	return (ring->cur - ring->dirty);
+}
+
+static int xlgmac_maybe_stop_tx_queue(
+			struct xlgmac_channel *channel,
+			struct xlgmac_ring *ring,
+			unsigned int count)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+
+	if (count > xlgmac_tx_avail_desc(ring)) {
+		netif_info(pdata, drv, pdata->netdev,
+			   "Tx queue stopped, not enough descriptors available\n");
+		netif_stop_subqueue(pdata->netdev, channel->queue_index);
+		ring->tx.queue_stopped = 1;
+
+		/* If we haven't notified the hardware because of xmit_more
+		 * support, tell it now
+		 */
+		if (ring->tx.xmit_more)
+			pdata->hw_ops.tx_start_xmit(channel, ring);
+
+		return NETDEV_TX_BUSY;
+	}
+
+	return 0;
+}
+
+static void xlgmac_prep_vlan(struct sk_buff *skb,
+			     struct xlgmac_pkt_info *pkt_info)
+{
+	if (skb_vlan_tag_present(skb))
+		pkt_info->vlan_ctag = skb_vlan_tag_get(skb);
+}
+
+static int xlgmac_prep_tso(struct sk_buff *skb,
+			   struct xlgmac_pkt_info *pkt_info)
+{
+	int ret;
+
+	if (!XLGMAC_GET_REG_BITS(pkt_info->attributes,
+				 TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS,
+				 TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN))
+		return 0;
+
+	ret = skb_cow_head(skb, 0);
+	if (ret)
+		return ret;
+
+	pkt_info->header_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	pkt_info->tcp_header_len = tcp_hdrlen(skb);
+	pkt_info->tcp_payload_len = skb->len - pkt_info->header_len;
+	pkt_info->mss = skb_shinfo(skb)->gso_size;
+
+	XLGMAC_PR("header_len=%u\n", pkt_info->header_len);
+	XLGMAC_PR("tcp_header_len=%u, tcp_payload_len=%u\n",
+		  pkt_info->tcp_header_len, pkt_info->tcp_payload_len);
+	XLGMAC_PR("mss=%u\n", pkt_info->mss);
+
+	/* Update the number of packets that will ultimately be transmitted
+	 * along with the extra bytes for each extra packet
+	 */
+	pkt_info->tx_packets = skb_shinfo(skb)->gso_segs;
+	pkt_info->tx_bytes += (pkt_info->tx_packets - 1) * pkt_info->header_len;
+
+	return 0;
+}
+
+static int xlgmac_is_tso(struct sk_buff *skb)
+{
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return 0;
+
+	if (!skb_is_gso(skb))
+		return 0;
+
+	return 1;
+}
+
+static void xlgmac_prep_tx_pkt(struct xlgmac_pdata *pdata,
+			       struct xlgmac_ring *ring,
+			       struct sk_buff *skb,
+			       struct xlgmac_pkt_info *pkt_info)
+{
+	struct skb_frag_struct *frag;
+	unsigned int context_desc;
+	unsigned int len;
+	unsigned int i;
+
+	pkt_info->skb = skb;
+
+	context_desc = 0;
+	pkt_info->desc_count = 0;
+
+	pkt_info->tx_packets = 1;
+	pkt_info->tx_bytes = skb->len;
+
+	if (xlgmac_is_tso(skb)) {
+		/* TSO requires an extra descriptor if mss is different */
+		if (skb_shinfo(skb)->gso_size != ring->tx.cur_mss) {
+			context_desc = 1;
+			pkt_info->desc_count++;
+		}
+
+		/* TSO requires an extra descriptor for TSO header */
+		pkt_info->desc_count++;
+
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+					pkt_info->attributes,
+					TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS,
+					TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN,
+					1);
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+					pkt_info->attributes,
+					TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS,
+					TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN,
+					1);
+	} else if (skb->ip_summed == CHECKSUM_PARTIAL)
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+					pkt_info->attributes,
+					TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS,
+					TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN,
+					1);
+
+	if (skb_vlan_tag_present(skb)) {
+		/* VLAN requires an extra descriptor if tag is different */
+		if (skb_vlan_tag_get(skb) != ring->tx.cur_vlan_ctag)
+			/* We can share with the TSO context descriptor */
+			if (!context_desc) {
+				context_desc = 1;
+				pkt_info->desc_count++;
+			}
+
+		pkt_info->attributes = XLGMAC_SET_REG_BITS(
+					pkt_info->attributes,
+					TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS,
+					TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN,
+					1);
+	}
+
+	for (len = skb_headlen(skb); len;) {
+		pkt_info->desc_count++;
+		len -= min_t(unsigned int, len, XLGMAC_TX_MAX_BUF_SIZE);
+	}
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		frag = &skb_shinfo(skb)->frags[i];
+		for (len = skb_frag_size(frag); len; ) {
+			pkt_info->desc_count++;
+			len -= min_t(unsigned int, len, XLGMAC_TX_MAX_BUF_SIZE);
+		}
+	}
+}
+
+static int xlgmac_calc_rx_buf_size(struct net_device *netdev, unsigned int mtu)
+{
+	unsigned int rx_buf_size;
+
+	if (mtu > XLGMAC_JUMBO_PACKET_MTU) {
+		netdev_alert(netdev, "MTU exceeds maximum supported value\n");
+		return -EINVAL;
+	}
+
+	rx_buf_size = mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+	rx_buf_size = clamp_val(rx_buf_size, XLGMAC_RX_MIN_BUF_SIZE, PAGE_SIZE);
+
+	rx_buf_size = (rx_buf_size + XLGMAC_RX_BUF_ALIGN - 1) &
+		      ~(XLGMAC_RX_BUF_ALIGN - 1);
+
+	return rx_buf_size;
+}
+
+static void xlgmac_enable_rx_tx_ints(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	struct xlgmac_channel *channel;
+	enum xlgmac_int int_id;
+	unsigned int i;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (channel->tx_ring && channel->rx_ring)
+			int_id = XLGMAC_INT_DMA_CH_SR_TI_RI;
+		else if (channel->tx_ring)
+			int_id = XLGMAC_INT_DMA_CH_SR_TI;
+		else if (channel->rx_ring)
+			int_id = XLGMAC_INT_DMA_CH_SR_RI;
+		else
+			continue;
+
+		hw_ops->enable_int(channel, int_id);
+	}
+}
+
+static void xlgmac_disable_rx_tx_ints(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	struct xlgmac_channel *channel;
+	enum xlgmac_int int_id;
+	unsigned int i;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (channel->tx_ring && channel->rx_ring)
+			int_id = XLGMAC_INT_DMA_CH_SR_TI_RI;
+		else if (channel->tx_ring)
+			int_id = XLGMAC_INT_DMA_CH_SR_TI;
+		else if (channel->rx_ring)
+			int_id = XLGMAC_INT_DMA_CH_SR_RI;
+		else
+			continue;
+
+		hw_ops->disable_int(channel, int_id);
+	}
+}
+
+static irqreturn_t xlgmac_isr(int irq, void *data)
+{
+	unsigned int dma_isr, dma_ch_isr, mac_isr;
+	struct xlgmac_pdata *pdata = data;
+	struct xlgmac_channel *channel;
+	struct xlgmac_hw_ops *hw_ops;
+	unsigned int i, ti, ri;
+
+	hw_ops = &pdata->hw_ops;
+
+	/* The DMA interrupt status register also reports MAC and MTL
+	 * interrupts. So for polling mode, we just need to check for
+	 * this register to be non-zero
+	 */
+	dma_isr = readl(pdata->mac_regs + DMA_ISR);
+	if (!dma_isr)
+		return IRQ_HANDLED;
+
+	netif_dbg(pdata, intr, pdata->netdev, "DMA_ISR=%#010x\n", dma_isr);
+
+	for (i = 0; i < pdata->channel_count; i++) {
+		if (!(dma_isr & (1 << i)))
+			continue;
+
+		channel = pdata->channel_head + i;
+
+		dma_ch_isr = readl(XLGMAC_DMA_REG(channel, DMA_CH_SR));
+		netif_dbg(pdata, intr, pdata->netdev, "DMA_CH%u_ISR=%#010x\n",
+			  i, dma_ch_isr);
+
+		/* The TI or RI interrupt bits may still be set even if using
+		 * per channel DMA interrupts. Check to be sure those are not
+		 * enabled before using the private data napi structure.
+		 */
+		ti = XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_TI_POS,
+					 DMA_CH_SR_TI_LEN);
+		ri = XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_RI_POS,
+					 DMA_CH_SR_RI_LEN);
+		if (!pdata->per_channel_irq && (ti || ri)) {
+			if (napi_schedule_prep(&pdata->napi)) {
+				/* Disable Tx and Rx interrupts */
+				xlgmac_disable_rx_tx_ints(pdata);
+
+				/* Turn on polling */
+				__napi_schedule_irqoff(&pdata->napi);
+			}
+		}
+
+		if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_RBU_POS,
+					DMA_CH_SR_RBU_LEN))
+			pdata->stats.rx_buffer_unavailable++;
+
+		/* Restart the device on a Fatal Bus Error */
+		if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_FBE_POS,
+					DMA_CH_SR_FBE_LEN))
+			schedule_work(&pdata->restart_work);
+
+		/* Clear all interrupt signals */
+		writel(dma_ch_isr, XLGMAC_DMA_REG(channel, DMA_CH_SR));
+	}
+
+	if (XLGMAC_GET_REG_BITS(dma_isr, DMA_ISR_MACIS_POS,
+				DMA_ISR_MACIS_LEN)) {
+		mac_isr = readl(pdata->mac_regs + MAC_ISR);
+
+		if (XLGMAC_GET_REG_BITS(mac_isr, MAC_ISR_MMCTXIS_POS,
+					MAC_ISR_MMCTXIS_LEN))
+			hw_ops->tx_mmc_int(pdata);
+
+		if (XLGMAC_GET_REG_BITS(mac_isr, MAC_ISR_MMCRXIS_POS,
+					MAC_ISR_MMCRXIS_LEN))
+			hw_ops->rx_mmc_int(pdata);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t xlgmac_dma_isr(int irq, void *data)
+{
+	struct xlgmac_channel *channel = data;
+
+	/* Per channel DMA interrupts are enabled, so we use the per
+	 * channel napi structure and not the private data napi structure
+	 */
+	if (napi_schedule_prep(&channel->napi)) {
+		/* Disable Tx and Rx interrupts */
+		disable_irq_nosync(channel->dma_irq);
+
+		/* Turn on polling */
+		__napi_schedule_irqoff(&channel->napi);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void xlgmac_tx_timer(unsigned long data)
+{
+	struct xlgmac_channel *channel = (struct xlgmac_channel *)data;
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct napi_struct *napi;
+
+	napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi;
+
+	if (napi_schedule_prep(napi)) {
+		/* Disable Tx and Rx interrupts */
+		if (pdata->per_channel_irq)
+			disable_irq_nosync(channel->dma_irq);
+		else
+			xlgmac_disable_rx_tx_ints(pdata);
+
+		/* Turn on polling */
+		__napi_schedule(napi);
+	}
+
+	channel->tx_timer_active = 0;
+}
+
+static void xlgmac_init_timers(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		setup_timer(&channel->tx_timer, xlgmac_tx_timer,
+			    (unsigned long)channel);
+	}
+}
+
+static void xlgmac_stop_timers(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		del_timer_sync(&channel->tx_timer);
+	}
+}
+
+static void xlgmac_napi_enable(struct xlgmac_pdata *pdata, unsigned int add)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+
+	if (pdata->per_channel_irq) {
+		channel = pdata->channel_head;
+		for (i = 0; i < pdata->channel_count; i++, channel++) {
+			if (add)
+				netif_napi_add(pdata->netdev, &channel->napi,
+					       xlgmac_one_poll,
+					       NAPI_POLL_WEIGHT);
+
+			napi_enable(&channel->napi);
+		}
+	} else {
+		if (add)
+			netif_napi_add(pdata->netdev, &pdata->napi,
+				       xlgmac_all_poll, NAPI_POLL_WEIGHT);
+
+		napi_enable(&pdata->napi);
+	}
+}
+
+static void xlgmac_napi_disable(struct xlgmac_pdata *pdata, unsigned int del)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+
+	if (pdata->per_channel_irq) {
+		channel = pdata->channel_head;
+		for (i = 0; i < pdata->channel_count; i++, channel++) {
+			napi_disable(&channel->napi);
+
+			if (del)
+				netif_napi_del(&channel->napi);
+		}
+	} else {
+		napi_disable(&pdata->napi);
+
+		if (del)
+			netif_napi_del(&pdata->napi);
+	}
+}
+
+static int xlgmac_request_irqs(struct xlgmac_pdata *pdata)
+{
+	struct net_device *netdev = pdata->netdev;
+	struct xlgmac_channel *channel;
+	unsigned int i;
+	int ret;
+
+	ret = devm_request_irq(pdata->dev, pdata->dev_irq, xlgmac_isr,
+			       IRQF_SHARED, netdev->name, pdata);
+	if (ret) {
+		netdev_alert(netdev, "error requesting irq %d\n",
+			     pdata->dev_irq);
+		return ret;
+	}
+
+	if (!pdata->per_channel_irq)
+		return 0;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		snprintf(channel->dma_irq_name,
+			 sizeof(channel->dma_irq_name) - 1,
+			 "%s-TxRx-%u", netdev_name(netdev),
+			 channel->queue_index);
+
+		ret = devm_request_irq(pdata->dev, channel->dma_irq,
+				       xlgmac_dma_isr, 0,
+				       channel->dma_irq_name, channel);
+		if (ret) {
+			netdev_alert(netdev, "error requesting irq %d\n",
+				     channel->dma_irq);
+			goto err_irq;
+		}
+	}
+
+	return 0;
+
+err_irq:
+	/* Using an unsigned int, 'i' will go to UINT_MAX and exit */
+	for (i--, channel--; i < pdata->channel_count; i--, channel--)
+		devm_free_irq(pdata->dev, channel->dma_irq, channel);
+
+	devm_free_irq(pdata->dev, pdata->dev_irq, pdata);
+
+	return ret;
+}
+
+static void xlgmac_free_irqs(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_channel *channel;
+	unsigned int i;
+
+	devm_free_irq(pdata->dev, pdata->dev_irq, pdata);
+
+	if (!pdata->per_channel_irq)
+		return;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++)
+		devm_free_irq(pdata->dev, channel->dma_irq, channel);
+}
+
+static void xlgmac_free_tx_data(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_desc_ops *desc_ops = &pdata->desc_ops;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_channel *channel;
+	struct xlgmac_ring *ring;
+	unsigned int i, j;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		ring = channel->tx_ring;
+		if (!ring)
+			break;
+
+		for (j = 0; j < ring->dma_desc_count; j++) {
+			desc_data = XLGMAC_GET_DESC_DATA(ring, j);
+			desc_ops->unmap_desc_data(pdata, desc_data);
+		}
+	}
+}
+
+static void xlgmac_free_rx_data(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_desc_ops *desc_ops = &pdata->desc_ops;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_channel *channel;
+	struct xlgmac_ring *ring;
+	unsigned int i, j;
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		ring = channel->rx_ring;
+		if (!ring)
+			break;
+
+		for (j = 0; j < ring->dma_desc_count; j++) {
+			desc_data = XLGMAC_GET_DESC_DATA(ring, j);
+			desc_ops->unmap_desc_data(pdata, desc_data);
+		}
+	}
+}
+
+static int xlgmac_start(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	struct net_device *netdev = pdata->netdev;
+	int ret;
+
+	hw_ops->init(pdata);
+	xlgmac_napi_enable(pdata, 1);
+
+	ret = xlgmac_request_irqs(pdata);
+	if (ret)
+		goto err_napi;
+
+	hw_ops->enable_tx(pdata);
+	hw_ops->enable_rx(pdata);
+	netif_tx_start_all_queues(netdev);
+
+	return 0;
+
+err_napi:
+	xlgmac_napi_disable(pdata, 1);
+	hw_ops->exit(pdata);
+
+	return ret;
+}
+
+static void xlgmac_stop(struct xlgmac_pdata *pdata)
+{
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	struct net_device *netdev = pdata->netdev;
+	struct xlgmac_channel *channel;
+	struct netdev_queue *txq;
+	unsigned int i;
+
+	netif_tx_stop_all_queues(netdev);
+	xlgmac_stop_timers(pdata);
+	hw_ops->disable_tx(pdata);
+	hw_ops->disable_rx(pdata);
+	xlgmac_free_irqs(pdata);
+	xlgmac_napi_disable(pdata, 1);
+	hw_ops->exit(pdata);
+
+	channel = pdata->channel_head;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			continue;
+
+		txq = netdev_get_tx_queue(netdev, channel->queue_index);
+		netdev_tx_reset_queue(txq);
+	}
+}
+
+static void xlgmac_restart_dev(struct xlgmac_pdata *pdata)
+{
+	/* If not running, "restart" will happen on open */
+	if (!netif_running(pdata->netdev))
+		return;
+
+	xlgmac_stop(pdata);
+
+	xlgmac_free_tx_data(pdata);
+	xlgmac_free_rx_data(pdata);
+
+	xlgmac_start(pdata);
+}
+
+static void xlgmac_restart(struct work_struct *work)
+{
+	struct xlgmac_pdata *pdata = container_of(work,
+						   struct xlgmac_pdata,
+						   restart_work);
+
+	rtnl_lock();
+
+	xlgmac_restart_dev(pdata);
+
+	rtnl_unlock();
+}
+
+static int xlgmac_open(struct net_device *netdev)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_desc_ops *desc_ops;
+	int ret;
+
+	desc_ops = &pdata->desc_ops;
+
+	/* TODO: Initialize the phy */
+
+	/* Calculate the Rx buffer size before allocating rings */
+	ret = xlgmac_calc_rx_buf_size(netdev, netdev->mtu);
+	if (ret < 0)
+		return ret;
+	pdata->rx_buf_size = ret;
+
+	/* Allocate the channels and rings */
+	ret = desc_ops->alloc_channles_and_rings(pdata);
+	if (ret)
+		return ret;
+
+	INIT_WORK(&pdata->restart_work, xlgmac_restart);
+	xlgmac_init_timers(pdata);
+
+	ret = xlgmac_start(pdata);
+	if (ret)
+		goto err_channels_and_rings;
+
+	return 0;
+
+err_channels_and_rings:
+	desc_ops->free_channels_and_rings(pdata);
+
+	return ret;
+}
+
+static int xlgmac_close(struct net_device *netdev)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_desc_ops *desc_ops;
+
+	desc_ops = &pdata->desc_ops;
+
+	/* Stop the device */
+	xlgmac_stop(pdata);
+
+	/* Free the channels and rings */
+	desc_ops->free_channels_and_rings(pdata);
+
+	return 0;
+}
+
+static void xlgmac_tx_timeout(struct net_device *netdev)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+
+	netdev_warn(netdev, "tx timeout, device restarting\n");
+	schedule_work(&pdata->restart_work);
+}
+
+static int xlgmac_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_pkt_info *tx_pkt_info;
+	struct xlgmac_desc_ops *desc_ops;
+	struct xlgmac_channel *channel;
+	struct xlgmac_hw_ops *hw_ops;
+	struct netdev_queue *txq;
+	struct xlgmac_ring *ring;
+	int ret;
+
+	desc_ops = &pdata->desc_ops;
+	hw_ops = &pdata->hw_ops;
+
+	XLGMAC_PR("skb->len = %d\n", skb->len);
+
+	channel = pdata->channel_head + skb->queue_mapping;
+	txq = netdev_get_tx_queue(netdev, channel->queue_index);
+	ring = channel->tx_ring;
+	tx_pkt_info = &ring->pkt_info;
+
+	if (skb->len == 0) {
+		netif_err(pdata, tx_err, netdev,
+			  "empty skb received from stack\n");
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+
+	/* Prepare preliminary packet info for TX */
+	memset(tx_pkt_info, 0, sizeof(*tx_pkt_info));
+	xlgmac_prep_tx_pkt(pdata, ring, skb, tx_pkt_info);
+
+	/* Check that there are enough descriptors available */
+	ret = xlgmac_maybe_stop_tx_queue(channel, ring,
+					 tx_pkt_info->desc_count);
+	if (ret)
+		return ret;
+
+	ret = xlgmac_prep_tso(skb, tx_pkt_info);
+	if (ret) {
+		netif_err(pdata, tx_err, netdev,
+			  "error processing TSO packet\n");
+		dev_kfree_skb_any(skb);
+		return ret;
+	}
+	xlgmac_prep_vlan(skb, tx_pkt_info);
+
+	if (!desc_ops->map_tx_skb(channel, skb)) {
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+
+	/* Report on the actual number of bytes (to be) sent */
+	netdev_tx_sent_queue(txq, tx_pkt_info->tx_bytes);
+
+	/* Configure required descriptor fields for transmission */
+	hw_ops->dev_xmit(channel);
+
+	if (netif_msg_pktdata(pdata))
+		xlgmac_print_pkt(netdev, skb, true);
+
+	/* Stop the queue in advance if there may not be enough descriptors */
+	xlgmac_maybe_stop_tx_queue(channel, ring, XLGMAC_TX_MAX_DESC_NR);
+
+	return NETDEV_TX_OK;
+}
+
+static void xlgmac_get_stats64(struct net_device *netdev,
+			       struct rtnl_link_stats64 *s)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_stats *pstats = &pdata->stats;
+
+	pdata->hw_ops.read_mmc_stats(pdata);
+
+	s->rx_packets = pstats->rxframecount_gb;
+	s->rx_bytes = pstats->rxoctetcount_gb;
+	s->rx_errors = pstats->rxframecount_gb -
+		       pstats->rxbroadcastframes_g -
+		       pstats->rxmulticastframes_g -
+		       pstats->rxunicastframes_g;
+	s->multicast = pstats->rxmulticastframes_g;
+	s->rx_length_errors = pstats->rxlengtherror;
+	s->rx_crc_errors = pstats->rxcrcerror;
+	s->rx_fifo_errors = pstats->rxfifooverflow;
+
+	s->tx_packets = pstats->txframecount_gb;
+	s->tx_bytes = pstats->txoctetcount_gb;
+	s->tx_errors = pstats->txframecount_gb - pstats->txframecount_g;
+	s->tx_dropped = netdev->stats.tx_dropped;
+}
+
+static int xlgmac_set_mac_address(struct net_device *netdev, void *addr)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	struct sockaddr *saddr = addr;
+
+	if (!is_valid_ether_addr(saddr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	memcpy(netdev->dev_addr, saddr->sa_data, netdev->addr_len);
+
+	hw_ops->set_mac_address(pdata, netdev->dev_addr);
+
+	return 0;
+}
+
+static int xlgmac_ioctl(struct net_device *netdev,
+			struct ifreq *ifreq, int cmd)
+{
+	if (!netif_running(netdev))
+		return -ENODEV;
+
+	return 0;
+}
+
+static int xlgmac_change_mtu(struct net_device *netdev, int mtu)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	int ret;
+
+	ret = xlgmac_calc_rx_buf_size(netdev, mtu);
+	if (ret < 0)
+		return ret;
+
+	pdata->rx_buf_size = ret;
+	netdev->mtu = mtu;
+
+	xlgmac_restart_dev(pdata);
+
+	return 0;
+}
+
+static int xlgmac_vlan_rx_add_vid(struct net_device *netdev,
+				  __be16 proto,
+				  u16 vid)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+
+	set_bit(vid, pdata->active_vlans);
+	hw_ops->update_vlan_hash_table(pdata);
+
+	return 0;
+}
+
+static int xlgmac_vlan_rx_kill_vid(struct net_device *netdev,
+				   __be16 proto,
+				   u16 vid)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+
+	clear_bit(vid, pdata->active_vlans);
+	hw_ops->update_vlan_hash_table(pdata);
+
+	return 0;
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void xlgmac_poll_controller(struct net_device *netdev)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_channel *channel;
+	unsigned int i;
+
+	if (pdata->per_channel_irq) {
+		channel = pdata->channel_head;
+		for (i = 0; i < pdata->channel_count; i++, channel++)
+			xlgmac_dma_isr(channel->dma_irq, channel);
+	} else {
+		disable_irq(pdata->dev_irq);
+		xlgmac_isr(pdata->dev_irq, pdata);
+		enable_irq(pdata->dev_irq);
+	}
+}
+#endif /* CONFIG_NET_POLL_CONTROLLER */
+
+static int xlgmac_set_features(struct net_device *netdev,
+			       netdev_features_t features)
+{
+	netdev_features_t rxhash, rxcsum, rxvlan, rxvlan_filter;
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+	int ret = 0;
+
+	rxhash = pdata->netdev_features & NETIF_F_RXHASH;
+	rxcsum = pdata->netdev_features & NETIF_F_RXCSUM;
+	rxvlan = pdata->netdev_features & NETIF_F_HW_VLAN_CTAG_RX;
+	rxvlan_filter = pdata->netdev_features & NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	if ((features & NETIF_F_RXHASH) && !rxhash)
+		ret = hw_ops->enable_rss(pdata);
+	else if (!(features & NETIF_F_RXHASH) && rxhash)
+		ret = hw_ops->disable_rss(pdata);
+	if (ret)
+		return ret;
+
+	if ((features & NETIF_F_RXCSUM) && !rxcsum)
+		hw_ops->enable_rx_csum(pdata);
+	else if (!(features & NETIF_F_RXCSUM) && rxcsum)
+		hw_ops->disable_rx_csum(pdata);
+
+	if ((features & NETIF_F_HW_VLAN_CTAG_RX) && !rxvlan)
+		hw_ops->enable_rx_vlan_stripping(pdata);
+	else if (!(features & NETIF_F_HW_VLAN_CTAG_RX) && rxvlan)
+		hw_ops->disable_rx_vlan_stripping(pdata);
+
+	if ((features & NETIF_F_HW_VLAN_CTAG_FILTER) && !rxvlan_filter)
+		hw_ops->enable_rx_vlan_filtering(pdata);
+	else if (!(features & NETIF_F_HW_VLAN_CTAG_FILTER) && rxvlan_filter)
+		hw_ops->disable_rx_vlan_filtering(pdata);
+
+	pdata->netdev_features = features;
+
+	return 0;
+}
+
+static void xlgmac_set_rx_mode(struct net_device *netdev)
+{
+	struct xlgmac_pdata *pdata = netdev_priv(netdev);
+	struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+
+	hw_ops->config_rx_mode(pdata);
+}
+
+static const struct net_device_ops xlgmac_netdev_ops = {
+	.ndo_open		= xlgmac_open,
+	.ndo_stop		= xlgmac_close,
+	.ndo_start_xmit		= xlgmac_xmit,
+	.ndo_tx_timeout		= xlgmac_tx_timeout,
+	.ndo_get_stats64	= xlgmac_get_stats64,
+	.ndo_change_mtu		= xlgmac_change_mtu,
+	.ndo_set_mac_address	= xlgmac_set_mac_address,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_do_ioctl		= xlgmac_ioctl,
+	.ndo_vlan_rx_add_vid	= xlgmac_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= xlgmac_vlan_rx_kill_vid,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= xlgmac_poll_controller,
+#endif
+	.ndo_set_features	= xlgmac_set_features,
+	.ndo_set_rx_mode	= xlgmac_set_rx_mode,
+};
+
+const struct net_device_ops *xlgmac_get_netdev_ops(void)
+{
+	return &xlgmac_netdev_ops;
+}
+
+static void xlgmac_rx_refresh(struct xlgmac_channel *channel)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct xlgmac_ring *ring = channel->rx_ring;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_desc_ops *desc_ops;
+	struct xlgmac_hw_ops *hw_ops;
+
+	desc_ops = &pdata->desc_ops;
+	hw_ops = &pdata->hw_ops;
+
+	while (ring->dirty != ring->cur) {
+		desc_data = XLGMAC_GET_DESC_DATA(ring, ring->dirty);
+
+		/* Reset desc_data values */
+		desc_ops->unmap_desc_data(pdata, desc_data);
+
+		if (desc_ops->map_rx_buffer(pdata, ring, desc_data))
+			break;
+
+		hw_ops->rx_desc_reset(pdata, desc_data, ring->dirty);
+
+		ring->dirty++;
+	}
+
+	/* Make sure everything is written before the register write */
+	wmb();
+
+	/* Update the Rx Tail Pointer Register with address of
+	 * the last cleaned entry
+	 */
+	desc_data = XLGMAC_GET_DESC_DATA(ring, ring->dirty - 1);
+	writel(lower_32_bits(desc_data->dma_desc_addr),
+	       XLGMAC_DMA_REG(channel, DMA_CH_RDTR_LO));
+}
+
+static struct sk_buff *xlgmac_create_skb(struct xlgmac_pdata *pdata,
+					 struct napi_struct *napi,
+					 struct xlgmac_desc_data *desc_data,
+					 unsigned int len)
+{
+	unsigned int copy_len;
+	struct sk_buff *skb;
+	u8 *packet;
+
+	skb = napi_alloc_skb(napi, desc_data->rx.hdr.dma_len);
+	if (!skb)
+		return NULL;
+
+	/* Start with the header buffer which may contain just the header
+	 * or the header plus data
+	 */
+	dma_sync_single_range_for_cpu(pdata->dev, desc_data->rx.hdr.dma_base,
+				      desc_data->rx.hdr.dma_off,
+				      desc_data->rx.hdr.dma_len,
+				      DMA_FROM_DEVICE);
+
+	packet = page_address(desc_data->rx.hdr.pa.pages) +
+		 desc_data->rx.hdr.pa.pages_offset;
+	copy_len = (desc_data->rx.hdr_len) ? desc_data->rx.hdr_len : len;
+	copy_len = min(desc_data->rx.hdr.dma_len, copy_len);
+	skb_copy_to_linear_data(skb, packet, copy_len);
+	skb_put(skb, copy_len);
+
+	len -= copy_len;
+	if (len) {
+		/* Add the remaining data as a frag */
+		dma_sync_single_range_for_cpu(pdata->dev,
+					      desc_data->rx.buf.dma_base,
+					      desc_data->rx.buf.dma_off,
+					      desc_data->rx.buf.dma_len,
+					      DMA_FROM_DEVICE);
+
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+				desc_data->rx.buf.pa.pages,
+				desc_data->rx.buf.pa.pages_offset,
+				len, desc_data->rx.buf.dma_len);
+		desc_data->rx.buf.pa.pages = NULL;
+	}
+
+	return skb;
+}
+
+static int xlgmac_tx_poll(struct xlgmac_channel *channel)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct xlgmac_ring *ring = channel->tx_ring;
+	struct net_device *netdev = pdata->netdev;
+	unsigned int tx_packets = 0, tx_bytes = 0;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_dma_desc *dma_desc;
+	struct xlgmac_desc_ops *desc_ops;
+	struct xlgmac_hw_ops *hw_ops;
+	struct netdev_queue *txq;
+	int processed = 0;
+	unsigned int cur;
+
+	desc_ops = &pdata->desc_ops;
+	hw_ops = &pdata->hw_ops;
+
+	/* Nothing to do if there isn't a Tx ring for this channel */
+	if (!ring)
+		return 0;
+
+	cur = ring->cur;
+
+	/* Be sure we get ring->cur before accessing descriptor data */
+	smp_rmb();
+
+	txq = netdev_get_tx_queue(netdev, channel->queue_index);
+
+	while ((processed < XLGMAC_TX_DESC_MAX_PROC) &&
+	       (ring->dirty != cur)) {
+		desc_data = XLGMAC_GET_DESC_DATA(ring, ring->dirty);
+		dma_desc = desc_data->dma_desc;
+
+		if (!hw_ops->tx_complete(dma_desc))
+			break;
+
+		/* Make sure descriptor fields are read after reading
+		 * the OWN bit
+		 */
+		dma_rmb();
+
+		if (netif_msg_tx_done(pdata))
+			xlgmac_dump_tx_desc(pdata, ring, ring->dirty, 1, 0);
+
+		if (hw_ops->is_last_desc(dma_desc)) {
+			tx_packets += desc_data->tx.packets;
+			tx_bytes += desc_data->tx.bytes;
+		}
+
+		/* Free the SKB and reset the descriptor for re-use */
+		desc_ops->unmap_desc_data(pdata, desc_data);
+		hw_ops->tx_desc_reset(desc_data);
+
+		processed++;
+		ring->dirty++;
+	}
+
+	if (!processed)
+		return 0;
+
+	netdev_tx_completed_queue(txq, tx_packets, tx_bytes);
+
+	if ((ring->tx.queue_stopped == 1) &&
+	    (xlgmac_tx_avail_desc(ring) > XLGMAC_TX_DESC_MIN_FREE)) {
+		ring->tx.queue_stopped = 0;
+		netif_tx_wake_queue(txq);
+	}
+
+	XLGMAC_PR("processed=%d\n", processed);
+
+	return processed;
+}
+
+static int xlgmac_rx_poll(struct xlgmac_channel *channel, int budget)
+{
+	struct xlgmac_pdata *pdata = channel->pdata;
+	struct xlgmac_ring *ring = channel->rx_ring;
+	struct net_device *netdev = pdata->netdev;
+	unsigned int len, dma_desc_len, max_len;
+	unsigned int context_next, context;
+	struct xlgmac_desc_data *desc_data;
+	struct xlgmac_pkt_info *pkt_info;
+	unsigned int incomplete, error;
+	struct xlgmac_hw_ops *hw_ops;
+	unsigned int received = 0;
+	struct napi_struct *napi;
+	struct sk_buff *skb;
+	int packet_count = 0;
+
+	hw_ops = &pdata->hw_ops;
+
+	/* Nothing to do if there isn't a Rx ring for this channel */
+	if (!ring)
+		return 0;
+
+	incomplete = 0;
+	context_next = 0;
+
+	napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi;
+
+	desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur);
+	pkt_info = &ring->pkt_info;
+	while (packet_count < budget) {
+		/* First time in loop see if we need to restore state */
+		if (!received && desc_data->state_saved) {
+			skb = desc_data->state.skb;
+			error = desc_data->state.error;
+			len = desc_data->state.len;
+		} else {
+			memset(pkt_info, 0, sizeof(*pkt_info));
+			skb = NULL;
+			error = 0;
+			len = 0;
+		}
+
+read_again:
+		desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur);
+
+		if (xlgmac_rx_dirty_desc(ring) > XLGMAC_RX_DESC_MAX_DIRTY)
+			xlgmac_rx_refresh(channel);
+
+		if (hw_ops->dev_read(channel))
+			break;
+
+		received++;
+		ring->cur++;
+
+		incomplete = XLGMAC_GET_REG_BITS(
+					pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_INCOMPLETE_POS,
+					RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN);
+		context_next = XLGMAC_GET_REG_BITS(
+					pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS,
+					RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN);
+		context = XLGMAC_GET_REG_BITS(
+					pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_CONTEXT_POS,
+					RX_PACKET_ATTRIBUTES_CONTEXT_LEN);
+
+		/* Earlier error, just drain the remaining data */
+		if ((incomplete || context_next) && error)
+			goto read_again;
+
+		if (error || pkt_info->errors) {
+			if (pkt_info->errors)
+				netif_err(pdata, rx_err, netdev,
+					  "error in received packet\n");
+			dev_kfree_skb(skb);
+			goto next_packet;
+		}
+
+		if (!context) {
+			/* Length is cumulative, get this descriptor's length */
+			dma_desc_len = desc_data->rx.len - len;
+			len += dma_desc_len;
+
+			if (dma_desc_len && !skb) {
+				skb = xlgmac_create_skb(pdata, napi, desc_data,
+							dma_desc_len);
+				if (!skb)
+					error = 1;
+			} else if (dma_desc_len) {
+				dma_sync_single_range_for_cpu(
+						pdata->dev,
+						desc_data->rx.buf.dma_base,
+						desc_data->rx.buf.dma_off,
+						desc_data->rx.buf.dma_len,
+						DMA_FROM_DEVICE);
+
+				skb_add_rx_frag(
+					skb, skb_shinfo(skb)->nr_frags,
+					desc_data->rx.buf.pa.pages,
+					desc_data->rx.buf.pa.pages_offset,
+					dma_desc_len,
+					desc_data->rx.buf.dma_len);
+				desc_data->rx.buf.pa.pages = NULL;
+			}
+		}
+
+		if (incomplete || context_next)
+			goto read_again;
+
+		if (!skb)
+			goto next_packet;
+
+		/* Be sure we don't exceed the configured MTU */
+		max_len = netdev->mtu + ETH_HLEN;
+		if (!(netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+		    (skb->protocol == htons(ETH_P_8021Q)))
+			max_len += VLAN_HLEN;
+
+		if (skb->len > max_len) {
+			netif_err(pdata, rx_err, netdev,
+				  "packet length exceeds configured MTU\n");
+			dev_kfree_skb(skb);
+			goto next_packet;
+		}
+
+		if (netif_msg_pktdata(pdata))
+			xlgmac_print_pkt(netdev, skb, false);
+
+		skb_checksum_none_assert(skb);
+		if (XLGMAC_GET_REG_BITS(pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_CSUM_DONE_POS,
+				    RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN))
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+		if (XLGMAC_GET_REG_BITS(pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_VLAN_CTAG_POS,
+				    RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN))
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+					       pkt_info->vlan_ctag);
+
+		if (XLGMAC_GET_REG_BITS(pkt_info->attributes,
+					RX_PACKET_ATTRIBUTES_RSS_HASH_POS,
+				    RX_PACKET_ATTRIBUTES_RSS_HASH_LEN))
+			skb_set_hash(skb, pkt_info->rss_hash,
+				     pkt_info->rss_hash_type);
+
+		skb->dev = netdev;
+		skb->protocol = eth_type_trans(skb, netdev);
+		skb_record_rx_queue(skb, channel->queue_index);
+
+		napi_gro_receive(napi, skb);
+
+next_packet:
+		packet_count++;
+	}
+
+	/* Check if we need to save state before leaving */
+	if (received && (incomplete || context_next)) {
+		desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur);
+		desc_data->state_saved = 1;
+		desc_data->state.skb = skb;
+		desc_data->state.len = len;
+		desc_data->state.error = error;
+	}
+
+	XLGMAC_PR("packet_count = %d\n", packet_count);
+
+	return packet_count;
+}
+
+static int xlgmac_one_poll(struct napi_struct *napi, int budget)
+{
+	struct xlgmac_channel *channel = container_of(napi,
+						struct xlgmac_channel,
+						napi);
+	int processed = 0;
+
+	XLGMAC_PR("budget=%d\n", budget);
+
+	/* Cleanup Tx ring first */
+	xlgmac_tx_poll(channel);
+
+	/* Process Rx ring next */
+	processed = xlgmac_rx_poll(channel, budget);
+
+	/* If we processed everything, we are done */
+	if (processed < budget) {
+		/* Turn off polling */
+		napi_complete_done(napi, processed);
+
+		/* Enable Tx and Rx interrupts */
+		enable_irq(channel->dma_irq);
+	}
+
+	XLGMAC_PR("received = %d\n", processed);
+
+	return processed;
+}
+
+static int xlgmac_all_poll(struct napi_struct *napi, int budget)
+{
+	struct xlgmac_pdata *pdata = container_of(napi,
+						   struct xlgmac_pdata,
+						   napi);
+	struct xlgmac_channel *channel;
+	int processed, last_processed;
+	int ring_budget;
+	unsigned int i;
+
+	XLGMAC_PR("budget=%d\n", budget);
+
+	processed = 0;
+	ring_budget = budget / pdata->rx_ring_count;
+	do {
+		last_processed = processed;
+
+		channel = pdata->channel_head;
+		for (i = 0; i < pdata->channel_count; i++, channel++) {
+			/* Cleanup Tx ring first */
+			xlgmac_tx_poll(channel);
+
+			/* Process Rx ring next */
+			if (ring_budget > (budget - processed))
+				ring_budget = budget - processed;
+			processed += xlgmac_rx_poll(channel, ring_budget);
+		}
+	} while ((processed < budget) && (processed != last_processed));
+
+	/* If we processed everything, we are done */
+	if (processed < budget) {
+		/* Turn off polling */
+		napi_complete_done(napi, processed);
+
+		/* Enable Tx and Rx interrupts */
+		xlgmac_enable_rx_tx_ints(pdata);
+	}
+
+	XLGMAC_PR("received = %d\n", processed);
+
+	return processed;
+}
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c
new file mode 100644
index 000000000000..386bafe74c3f
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c
@@ -0,0 +1,78 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include "dwc-xlgmac.h"
+#include "dwc-xlgmac-reg.h"
+
+static int xlgmac_probe(struct pci_dev *pcidev, const struct pci_device_id *id)
+{
+	struct device *dev = &pcidev->dev;
+	struct xlgmac_resources res;
+	int i, ret;
+
+	ret = pcim_enable_device(pcidev);
+	if (ret) {
+		dev_err(dev, "ERROR: failed to enable device\n");
+		return ret;
+	}
+
+	for (i = 0; i <= PCI_STD_RESOURCE_END; i++) {
+		if (pci_resource_len(pcidev, i) == 0)
+			continue;
+		ret = pcim_iomap_regions(pcidev, BIT(i), XLGMAC_DRV_NAME);
+		if (ret)
+			return ret;
+		break;
+	}
+
+	pci_set_master(pcidev);
+
+	memset(&res, 0, sizeof(res));
+	res.irq = pcidev->irq;
+	res.addr = pcim_iomap_table(pcidev)[i];
+
+	return xlgmac_drv_probe(&pcidev->dev, &res);
+}
+
+static void xlgmac_remove(struct pci_dev *pcidev)
+{
+	xlgmac_drv_remove(&pcidev->dev);
+}
+
+static const struct pci_device_id xlgmac_pci_tbl[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_SYNOPSYS, 0x7302) },
+	{ 0 }
+};
+MODULE_DEVICE_TABLE(pci, xlgmac_pci_tbl);
+
+static struct pci_driver xlgmac_pci_driver = {
+	.name		= XLGMAC_DRV_NAME,
+	.id_table	= xlgmac_pci_tbl,
+	.probe		= xlgmac_probe,
+	.remove		= xlgmac_remove,
+};
+
+module_pci_driver(xlgmac_pci_driver);
+
+MODULE_DESCRIPTION(XLGMAC_DRV_DESC);
+MODULE_VERSION(XLGMAC_DRV_VERSION);
+MODULE_AUTHOR("Jie Deng <jiedeng@synopsys.com>");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-reg.h b/drivers/net/ethernet/synopsys/dwc-xlgmac-reg.h
new file mode 100644
index 000000000000..3754f220567d
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-reg.h
@@ -0,0 +1,744 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#ifndef __DWC_XLGMAC_REG_H__
+#define __DWC_XLGMAC_REG_H__
+
+/* MAC register offsets */
+#define MAC_TCR				0x0000
+#define MAC_RCR				0x0004
+#define MAC_PFR				0x0008
+#define MAC_HTR0			0x0010
+#define MAC_VLANTR			0x0050
+#define MAC_VLANHTR			0x0058
+#define MAC_VLANIR			0x0060
+#define MAC_Q0TFCR			0x0070
+#define MAC_RFCR			0x0090
+#define MAC_RQC0R			0x00a0
+#define MAC_RQC1R			0x00a4
+#define MAC_RQC2R			0x00a8
+#define MAC_RQC3R			0x00ac
+#define MAC_ISR				0x00b0
+#define MAC_IER				0x00b4
+#define MAC_VR				0x0110
+#define MAC_HWF0R			0x011c
+#define MAC_HWF1R			0x0120
+#define MAC_HWF2R			0x0124
+#define MAC_MACA0HR			0x0300
+#define MAC_MACA0LR			0x0304
+#define MAC_MACA1HR			0x0308
+#define MAC_MACA1LR			0x030c
+#define MAC_RSSCR			0x0c80
+#define MAC_RSSAR			0x0c88
+#define MAC_RSSDR			0x0c8c
+
+#define MAC_QTFCR_INC			4
+#define MAC_MACA_INC			4
+#define MAC_HTR_INC			4
+#define MAC_RQC2_INC			4
+#define MAC_RQC2_Q_PER_REG		4
+
+/* MAC register entry bit positions and sizes */
+#define MAC_HWF0R_ADDMACADRSEL_POS	18
+#define MAC_HWF0R_ADDMACADRSEL_LEN	5
+#define MAC_HWF0R_ARPOFFSEL_POS		9
+#define MAC_HWF0R_ARPOFFSEL_LEN		1
+#define MAC_HWF0R_EEESEL_POS		13
+#define MAC_HWF0R_EEESEL_LEN		1
+#define MAC_HWF0R_PHYIFSEL_POS		1
+#define MAC_HWF0R_PHYIFSEL_LEN		2
+#define MAC_HWF0R_MGKSEL_POS		7
+#define MAC_HWF0R_MGKSEL_LEN		1
+#define MAC_HWF0R_MMCSEL_POS		8
+#define MAC_HWF0R_MMCSEL_LEN		1
+#define MAC_HWF0R_RWKSEL_POS		6
+#define MAC_HWF0R_RWKSEL_LEN		1
+#define MAC_HWF0R_RXCOESEL_POS		16
+#define MAC_HWF0R_RXCOESEL_LEN		1
+#define MAC_HWF0R_SAVLANINS_POS		27
+#define MAC_HWF0R_SAVLANINS_LEN		1
+#define MAC_HWF0R_SMASEL_POS		5
+#define MAC_HWF0R_SMASEL_LEN		1
+#define MAC_HWF0R_TSSEL_POS		12
+#define MAC_HWF0R_TSSEL_LEN		1
+#define MAC_HWF0R_TSSTSSEL_POS		25
+#define MAC_HWF0R_TSSTSSEL_LEN		2
+#define MAC_HWF0R_TXCOESEL_POS		14
+#define MAC_HWF0R_TXCOESEL_LEN		1
+#define MAC_HWF0R_VLHASH_POS		4
+#define MAC_HWF0R_VLHASH_LEN		1
+#define MAC_HWF1R_ADDR64_POS		14
+#define MAC_HWF1R_ADDR64_LEN		2
+#define MAC_HWF1R_ADVTHWORD_POS		13
+#define MAC_HWF1R_ADVTHWORD_LEN		1
+#define MAC_HWF1R_DBGMEMA_POS		19
+#define MAC_HWF1R_DBGMEMA_LEN		1
+#define MAC_HWF1R_DCBEN_POS		16
+#define MAC_HWF1R_DCBEN_LEN		1
+#define MAC_HWF1R_HASHTBLSZ_POS		24
+#define MAC_HWF1R_HASHTBLSZ_LEN		3
+#define MAC_HWF1R_L3L4FNUM_POS		27
+#define MAC_HWF1R_L3L4FNUM_LEN		4
+#define MAC_HWF1R_NUMTC_POS		21
+#define MAC_HWF1R_NUMTC_LEN		3
+#define MAC_HWF1R_RSSEN_POS		20
+#define MAC_HWF1R_RSSEN_LEN		1
+#define MAC_HWF1R_RXFIFOSIZE_POS	0
+#define MAC_HWF1R_RXFIFOSIZE_LEN	5
+#define MAC_HWF1R_SPHEN_POS		17
+#define MAC_HWF1R_SPHEN_LEN		1
+#define MAC_HWF1R_TSOEN_POS		18
+#define MAC_HWF1R_TSOEN_LEN		1
+#define MAC_HWF1R_TXFIFOSIZE_POS	6
+#define MAC_HWF1R_TXFIFOSIZE_LEN	5
+#define MAC_HWF2R_AUXSNAPNUM_POS	28
+#define MAC_HWF2R_AUXSNAPNUM_LEN	3
+#define MAC_HWF2R_PPSOUTNUM_POS		24
+#define MAC_HWF2R_PPSOUTNUM_LEN		3
+#define MAC_HWF2R_RXCHCNT_POS		12
+#define MAC_HWF2R_RXCHCNT_LEN		4
+#define MAC_HWF2R_RXQCNT_POS		0
+#define MAC_HWF2R_RXQCNT_LEN		4
+#define MAC_HWF2R_TXCHCNT_POS		18
+#define MAC_HWF2R_TXCHCNT_LEN		4
+#define MAC_HWF2R_TXQCNT_POS		6
+#define MAC_HWF2R_TXQCNT_LEN		4
+#define MAC_IER_TSIE_POS		12
+#define MAC_IER_TSIE_LEN		1
+#define MAC_ISR_MMCRXIS_POS		9
+#define MAC_ISR_MMCRXIS_LEN		1
+#define MAC_ISR_MMCTXIS_POS		10
+#define MAC_ISR_MMCTXIS_LEN		1
+#define MAC_ISR_PMTIS_POS		4
+#define MAC_ISR_PMTIS_LEN		1
+#define MAC_ISR_TSIS_POS		12
+#define MAC_ISR_TSIS_LEN		1
+#define MAC_MACA1HR_AE_POS		31
+#define MAC_MACA1HR_AE_LEN		1
+#define MAC_PFR_HMC_POS			2
+#define MAC_PFR_HMC_LEN			1
+#define MAC_PFR_HPF_POS			10
+#define MAC_PFR_HPF_LEN			1
+#define MAC_PFR_HUC_POS			1
+#define MAC_PFR_HUC_LEN			1
+#define MAC_PFR_PM_POS			4
+#define MAC_PFR_PM_LEN			1
+#define MAC_PFR_PR_POS			0
+#define MAC_PFR_PR_LEN			1
+#define MAC_PFR_VTFE_POS		16
+#define MAC_PFR_VTFE_LEN		1
+#define MAC_Q0TFCR_PT_POS		16
+#define MAC_Q0TFCR_PT_LEN		16
+#define MAC_Q0TFCR_TFE_POS		1
+#define MAC_Q0TFCR_TFE_LEN		1
+#define MAC_RCR_ACS_POS			1
+#define MAC_RCR_ACS_LEN			1
+#define MAC_RCR_CST_POS			2
+#define MAC_RCR_CST_LEN			1
+#define MAC_RCR_DCRCC_POS		3
+#define MAC_RCR_DCRCC_LEN		1
+#define MAC_RCR_HDSMS_POS		12
+#define MAC_RCR_HDSMS_LEN		3
+#define MAC_RCR_IPC_POS			9
+#define MAC_RCR_IPC_LEN			1
+#define MAC_RCR_JE_POS			8
+#define MAC_RCR_JE_LEN			1
+#define MAC_RCR_LM_POS			10
+#define MAC_RCR_LM_LEN			1
+#define MAC_RCR_RE_POS			0
+#define MAC_RCR_RE_LEN			1
+#define MAC_RFCR_PFCE_POS		8
+#define MAC_RFCR_PFCE_LEN		1
+#define MAC_RFCR_RFE_POS		0
+#define MAC_RFCR_RFE_LEN		1
+#define MAC_RFCR_UP_POS			1
+#define MAC_RFCR_UP_LEN			1
+#define MAC_RQC0R_RXQ0EN_POS		0
+#define MAC_RQC0R_RXQ0EN_LEN		2
+#define MAC_RSSAR_ADDRT_POS		2
+#define MAC_RSSAR_ADDRT_LEN		1
+#define MAC_RSSAR_CT_POS		1
+#define MAC_RSSAR_CT_LEN		1
+#define MAC_RSSAR_OB_POS		0
+#define MAC_RSSAR_OB_LEN		1
+#define MAC_RSSAR_RSSIA_POS		8
+#define MAC_RSSAR_RSSIA_LEN		8
+#define MAC_RSSCR_IP2TE_POS		1
+#define MAC_RSSCR_IP2TE_LEN		1
+#define MAC_RSSCR_RSSE_POS		0
+#define MAC_RSSCR_RSSE_LEN		1
+#define MAC_RSSCR_TCP4TE_POS		2
+#define MAC_RSSCR_TCP4TE_LEN		1
+#define MAC_RSSCR_UDP4TE_POS		3
+#define MAC_RSSCR_UDP4TE_LEN		1
+#define MAC_RSSDR_DMCH_POS		0
+#define MAC_RSSDR_DMCH_LEN		4
+#define MAC_TCR_SS_POS			28
+#define MAC_TCR_SS_LEN			3
+#define MAC_TCR_TE_POS			0
+#define MAC_TCR_TE_LEN			1
+#define MAC_VLANHTR_VLHT_POS		0
+#define MAC_VLANHTR_VLHT_LEN		16
+#define MAC_VLANIR_VLTI_POS		20
+#define MAC_VLANIR_VLTI_LEN		1
+#define MAC_VLANIR_CSVL_POS		19
+#define MAC_VLANIR_CSVL_LEN		1
+#define MAC_VLANTR_DOVLTC_POS		20
+#define MAC_VLANTR_DOVLTC_LEN		1
+#define MAC_VLANTR_ERSVLM_POS		19
+#define MAC_VLANTR_ERSVLM_LEN		1
+#define MAC_VLANTR_ESVL_POS		18
+#define MAC_VLANTR_ESVL_LEN		1
+#define MAC_VLANTR_ETV_POS		16
+#define MAC_VLANTR_ETV_LEN		1
+#define MAC_VLANTR_EVLS_POS		21
+#define MAC_VLANTR_EVLS_LEN		2
+#define MAC_VLANTR_EVLRXS_POS		24
+#define MAC_VLANTR_EVLRXS_LEN		1
+#define MAC_VLANTR_VL_POS		0
+#define MAC_VLANTR_VL_LEN		16
+#define MAC_VLANTR_VTHM_POS		25
+#define MAC_VLANTR_VTHM_LEN		1
+#define MAC_VLANTR_VTIM_POS		17
+#define MAC_VLANTR_VTIM_LEN		1
+#define MAC_VR_DEVID_POS		8
+#define MAC_VR_DEVID_LEN		8
+#define MAC_VR_SNPSVER_POS		0
+#define MAC_VR_SNPSVER_LEN		8
+#define MAC_VR_USERVER_POS		16
+#define MAC_VR_USERVER_LEN		8
+
+/* MMC register offsets */
+#define MMC_CR				0x0800
+#define MMC_RISR			0x0804
+#define MMC_TISR			0x0808
+#define MMC_RIER			0x080c
+#define MMC_TIER			0x0810
+#define MMC_TXOCTETCOUNT_GB_LO		0x0814
+#define MMC_TXFRAMECOUNT_GB_LO		0x081c
+#define MMC_TXBROADCASTFRAMES_G_LO	0x0824
+#define MMC_TXMULTICASTFRAMES_G_LO	0x082c
+#define MMC_TX64OCTETS_GB_LO		0x0834
+#define MMC_TX65TO127OCTETS_GB_LO	0x083c
+#define MMC_TX128TO255OCTETS_GB_LO	0x0844
+#define MMC_TX256TO511OCTETS_GB_LO	0x084c
+#define MMC_TX512TO1023OCTETS_GB_LO	0x0854
+#define MMC_TX1024TOMAXOCTETS_GB_LO	0x085c
+#define MMC_TXUNICASTFRAMES_GB_LO	0x0864
+#define MMC_TXMULTICASTFRAMES_GB_LO	0x086c
+#define MMC_TXBROADCASTFRAMES_GB_LO	0x0874
+#define MMC_TXUNDERFLOWERROR_LO		0x087c
+#define MMC_TXOCTETCOUNT_G_LO		0x0884
+#define MMC_TXFRAMECOUNT_G_LO		0x088c
+#define MMC_TXPAUSEFRAMES_LO		0x0894
+#define MMC_TXVLANFRAMES_G_LO		0x089c
+#define MMC_RXFRAMECOUNT_GB_LO		0x0900
+#define MMC_RXOCTETCOUNT_GB_LO		0x0908
+#define MMC_RXOCTETCOUNT_G_LO		0x0910
+#define MMC_RXBROADCASTFRAMES_G_LO	0x0918
+#define MMC_RXMULTICASTFRAMES_G_LO	0x0920
+#define MMC_RXCRCERROR_LO		0x0928
+#define MMC_RXRUNTERROR			0x0930
+#define MMC_RXJABBERERROR		0x0934
+#define MMC_RXUNDERSIZE_G		0x0938
+#define MMC_RXOVERSIZE_G		0x093c
+#define MMC_RX64OCTETS_GB_LO		0x0940
+#define MMC_RX65TO127OCTETS_GB_LO	0x0948
+#define MMC_RX128TO255OCTETS_GB_LO	0x0950
+#define MMC_RX256TO511OCTETS_GB_LO	0x0958
+#define MMC_RX512TO1023OCTETS_GB_LO	0x0960
+#define MMC_RX1024TOMAXOCTETS_GB_LO	0x0968
+#define MMC_RXUNICASTFRAMES_G_LO	0x0970
+#define MMC_RXLENGTHERROR_LO		0x0978
+#define MMC_RXOUTOFRANGETYPE_LO		0x0980
+#define MMC_RXPAUSEFRAMES_LO		0x0988
+#define MMC_RXFIFOOVERFLOW_LO		0x0990
+#define MMC_RXVLANFRAMES_GB_LO		0x0998
+#define MMC_RXWATCHDOGERROR		0x09a0
+
+/* MMC register entry bit positions and sizes */
+#define MMC_CR_CR_POS				0
+#define MMC_CR_CR_LEN				1
+#define MMC_CR_CSR_POS				1
+#define MMC_CR_CSR_LEN				1
+#define MMC_CR_ROR_POS				2
+#define MMC_CR_ROR_LEN				1
+#define MMC_CR_MCF_POS				3
+#define MMC_CR_MCF_LEN				1
+#define MMC_CR_MCT_POS				4
+#define MMC_CR_MCT_LEN				2
+#define MMC_RIER_ALL_INTERRUPTS_POS		0
+#define MMC_RIER_ALL_INTERRUPTS_LEN		23
+#define MMC_RISR_RXFRAMECOUNT_GB_POS		0
+#define MMC_RISR_RXFRAMECOUNT_GB_LEN		1
+#define MMC_RISR_RXOCTETCOUNT_GB_POS		1
+#define MMC_RISR_RXOCTETCOUNT_GB_LEN		1
+#define MMC_RISR_RXOCTETCOUNT_G_POS		2
+#define MMC_RISR_RXOCTETCOUNT_G_LEN		1
+#define MMC_RISR_RXBROADCASTFRAMES_G_POS	3
+#define MMC_RISR_RXBROADCASTFRAMES_G_LEN	1
+#define MMC_RISR_RXMULTICASTFRAMES_G_POS	4
+#define MMC_RISR_RXMULTICASTFRAMES_G_LEN	1
+#define MMC_RISR_RXCRCERROR_POS			5
+#define MMC_RISR_RXCRCERROR_LEN			1
+#define MMC_RISR_RXRUNTERROR_POS		6
+#define MMC_RISR_RXRUNTERROR_LEN		1
+#define MMC_RISR_RXJABBERERROR_POS		7
+#define MMC_RISR_RXJABBERERROR_LEN		1
+#define MMC_RISR_RXUNDERSIZE_G_POS		8
+#define MMC_RISR_RXUNDERSIZE_G_LEN		1
+#define MMC_RISR_RXOVERSIZE_G_POS		9
+#define MMC_RISR_RXOVERSIZE_G_LEN		1
+#define MMC_RISR_RX64OCTETS_GB_POS		10
+#define MMC_RISR_RX64OCTETS_GB_LEN		1
+#define MMC_RISR_RX65TO127OCTETS_GB_POS		11
+#define MMC_RISR_RX65TO127OCTETS_GB_LEN		1
+#define MMC_RISR_RX128TO255OCTETS_GB_POS	12
+#define MMC_RISR_RX128TO255OCTETS_GB_LEN	1
+#define MMC_RISR_RX256TO511OCTETS_GB_POS	13
+#define MMC_RISR_RX256TO511OCTETS_GB_LEN	1
+#define MMC_RISR_RX512TO1023OCTETS_GB_POS	14
+#define MMC_RISR_RX512TO1023OCTETS_GB_LEN	1
+#define MMC_RISR_RX1024TOMAXOCTETS_GB_POS	15
+#define MMC_RISR_RX1024TOMAXOCTETS_GB_LEN	1
+#define MMC_RISR_RXUNICASTFRAMES_G_POS		16
+#define MMC_RISR_RXUNICASTFRAMES_G_LEN		1
+#define MMC_RISR_RXLENGTHERROR_POS		17
+#define MMC_RISR_RXLENGTHERROR_LEN		1
+#define MMC_RISR_RXOUTOFRANGETYPE_POS		18
+#define MMC_RISR_RXOUTOFRANGETYPE_LEN		1
+#define MMC_RISR_RXPAUSEFRAMES_POS		19
+#define MMC_RISR_RXPAUSEFRAMES_LEN		1
+#define MMC_RISR_RXFIFOOVERFLOW_POS		20
+#define MMC_RISR_RXFIFOOVERFLOW_LEN		1
+#define MMC_RISR_RXVLANFRAMES_GB_POS		21
+#define MMC_RISR_RXVLANFRAMES_GB_LEN		1
+#define MMC_RISR_RXWATCHDOGERROR_POS		22
+#define MMC_RISR_RXWATCHDOGERROR_LEN		1
+#define MMC_TIER_ALL_INTERRUPTS_POS		0
+#define MMC_TIER_ALL_INTERRUPTS_LEN		18
+#define MMC_TISR_TXOCTETCOUNT_GB_POS		0
+#define MMC_TISR_TXOCTETCOUNT_GB_LEN		1
+#define MMC_TISR_TXFRAMECOUNT_GB_POS		1
+#define MMC_TISR_TXFRAMECOUNT_GB_LEN		1
+#define MMC_TISR_TXBROADCASTFRAMES_G_POS	2
+#define MMC_TISR_TXBROADCASTFRAMES_G_LEN	1
+#define MMC_TISR_TXMULTICASTFRAMES_G_POS	3
+#define MMC_TISR_TXMULTICASTFRAMES_G_LEN	1
+#define MMC_TISR_TX64OCTETS_GB_POS		4
+#define MMC_TISR_TX64OCTETS_GB_LEN		1
+#define MMC_TISR_TX65TO127OCTETS_GB_POS		5
+#define MMC_TISR_TX65TO127OCTETS_GB_LEN		1
+#define MMC_TISR_TX128TO255OCTETS_GB_POS	6
+#define MMC_TISR_TX128TO255OCTETS_GB_LEN	1
+#define MMC_TISR_TX256TO511OCTETS_GB_POS	7
+#define MMC_TISR_TX256TO511OCTETS_GB_LEN	1
+#define MMC_TISR_TX512TO1023OCTETS_GB_POS	8
+#define MMC_TISR_TX512TO1023OCTETS_GB_LEN	1
+#define MMC_TISR_TX1024TOMAXOCTETS_GB_POS	9
+#define MMC_TISR_TX1024TOMAXOCTETS_GB_LEN	1
+#define MMC_TISR_TXUNICASTFRAMES_GB_POS		10
+#define MMC_TISR_TXUNICASTFRAMES_GB_LEN		1
+#define MMC_TISR_TXMULTICASTFRAMES_GB_POS	11
+#define MMC_TISR_TXMULTICASTFRAMES_GB_LEN	1
+#define MMC_TISR_TXBROADCASTFRAMES_GB_POS	12
+#define MMC_TISR_TXBROADCASTFRAMES_GB_LEN	1
+#define MMC_TISR_TXUNDERFLOWERROR_POS		13
+#define MMC_TISR_TXUNDERFLOWERROR_LEN		1
+#define MMC_TISR_TXOCTETCOUNT_G_POS		14
+#define MMC_TISR_TXOCTETCOUNT_G_LEN		1
+#define MMC_TISR_TXFRAMECOUNT_G_POS		15
+#define MMC_TISR_TXFRAMECOUNT_G_LEN		1
+#define MMC_TISR_TXPAUSEFRAMES_POS		16
+#define MMC_TISR_TXPAUSEFRAMES_LEN		1
+#define MMC_TISR_TXVLANFRAMES_G_POS		17
+#define MMC_TISR_TXVLANFRAMES_G_LEN		1
+
+/* MTL register offsets */
+#define MTL_OMR				0x1000
+#define MTL_FDDR			0x1010
+#define MTL_RQDCM0R			0x1030
+
+#define MTL_RQDCM_INC			4
+#define MTL_RQDCM_Q_PER_REG		4
+
+/* MTL register entry bit positions and sizes */
+#define MTL_OMR_ETSALG_POS		5
+#define MTL_OMR_ETSALG_LEN		2
+#define MTL_OMR_RAA_POS			2
+#define MTL_OMR_RAA_LEN			1
+
+/* MTL queue register offsets
+ *   Multiple queues can be active.  The first queue has registers
+ *   that begin at 0x1100.  Each subsequent queue has registers that
+ *   are accessed using an offset of 0x80 from the previous queue.
+ */
+#define MTL_Q_BASE			0x1100
+#define MTL_Q_INC			0x80
+
+#define MTL_Q_TQOMR			0x00
+#define MTL_Q_RQOMR			0x40
+#define MTL_Q_RQDR			0x48
+#define MTL_Q_RQFCR			0x50
+#define MTL_Q_IER			0x70
+#define MTL_Q_ISR			0x74
+
+/* MTL queue register entry bit positions and sizes */
+#define MTL_Q_RQDR_PRXQ_POS		16
+#define MTL_Q_RQDR_PRXQ_LEN		14
+#define MTL_Q_RQDR_RXQSTS_POS		4
+#define MTL_Q_RQDR_RXQSTS_LEN		2
+#define MTL_Q_RQFCR_RFA_POS		1
+#define MTL_Q_RQFCR_RFA_LEN		6
+#define MTL_Q_RQFCR_RFD_POS		17
+#define MTL_Q_RQFCR_RFD_LEN		6
+#define MTL_Q_RQOMR_EHFC_POS		7
+#define MTL_Q_RQOMR_EHFC_LEN		1
+#define MTL_Q_RQOMR_RQS_POS		16
+#define MTL_Q_RQOMR_RQS_LEN		9
+#define MTL_Q_RQOMR_RSF_POS		5
+#define MTL_Q_RQOMR_RSF_LEN		1
+#define MTL_Q_RQOMR_FEP_POS		4
+#define MTL_Q_RQOMR_FEP_LEN		1
+#define MTL_Q_RQOMR_FUP_POS		3
+#define MTL_Q_RQOMR_FUP_LEN		1
+#define MTL_Q_RQOMR_RTC_POS		0
+#define MTL_Q_RQOMR_RTC_LEN		2
+#define MTL_Q_TQOMR_FTQ_POS		0
+#define MTL_Q_TQOMR_FTQ_LEN		1
+#define MTL_Q_TQOMR_Q2TCMAP_POS		8
+#define MTL_Q_TQOMR_Q2TCMAP_LEN		3
+#define MTL_Q_TQOMR_TQS_POS		16
+#define MTL_Q_TQOMR_TQS_LEN		10
+#define MTL_Q_TQOMR_TSF_POS		1
+#define MTL_Q_TQOMR_TSF_LEN		1
+#define MTL_Q_TQOMR_TTC_POS		4
+#define MTL_Q_TQOMR_TTC_LEN		3
+#define MTL_Q_TQOMR_TXQEN_POS		2
+#define MTL_Q_TQOMR_TXQEN_LEN		2
+
+/* MTL queue register value */
+#define MTL_RSF_DISABLE			0x00
+#define MTL_RSF_ENABLE			0x01
+#define MTL_TSF_DISABLE			0x00
+#define MTL_TSF_ENABLE			0x01
+
+#define MTL_RX_THRESHOLD_64		0x00
+#define MTL_RX_THRESHOLD_96		0x02
+#define MTL_RX_THRESHOLD_128		0x03
+#define MTL_TX_THRESHOLD_64		0x00
+#define MTL_TX_THRESHOLD_96		0x02
+#define MTL_TX_THRESHOLD_128		0x03
+#define MTL_TX_THRESHOLD_192		0x04
+#define MTL_TX_THRESHOLD_256		0x05
+#define MTL_TX_THRESHOLD_384		0x06
+#define MTL_TX_THRESHOLD_512		0x07
+
+#define MTL_ETSALG_WRR			0x00
+#define MTL_ETSALG_WFQ			0x01
+#define MTL_ETSALG_DWRR			0x02
+#define MTL_RAA_SP			0x00
+#define MTL_RAA_WSP			0x01
+
+#define MTL_Q_DISABLED			0x00
+#define MTL_Q_ENABLED			0x02
+
+#define MTL_RQDCM0R_Q0MDMACH		0x0
+#define MTL_RQDCM0R_Q1MDMACH		0x00000100
+#define MTL_RQDCM0R_Q2MDMACH		0x00020000
+#define MTL_RQDCM0R_Q3MDMACH		0x03000000
+#define MTL_RQDCM1R_Q4MDMACH		0x00000004
+#define MTL_RQDCM1R_Q5MDMACH		0x00000500
+#define MTL_RQDCM1R_Q6MDMACH		0x00060000
+#define MTL_RQDCM1R_Q7MDMACH		0x07000000
+#define MTL_RQDCM2R_Q8MDMACH		0x00000008
+#define MTL_RQDCM2R_Q9MDMACH		0x00000900
+#define MTL_RQDCM2R_Q10MDMACH		0x000A0000
+#define MTL_RQDCM2R_Q11MDMACH		0x0B000000
+
+/* MTL traffic class register offsets
+ *   Multiple traffic classes can be active.  The first class has registers
+ *   that begin at 0x1100.  Each subsequent queue has registers that
+ *   are accessed using an offset of 0x80 from the previous queue.
+ */
+#define MTL_TC_BASE			MTL_Q_BASE
+#define MTL_TC_INC			MTL_Q_INC
+
+#define MTL_TC_ETSCR			0x10
+#define MTL_TC_ETSSR			0x14
+#define MTL_TC_QWR			0x18
+
+/* MTL traffic class register entry bit positions and sizes */
+#define MTL_TC_ETSCR_TSA_POS		0
+#define MTL_TC_ETSCR_TSA_LEN		2
+#define MTL_TC_QWR_QW_POS		0
+#define MTL_TC_QWR_QW_LEN		21
+
+/* MTL traffic class register value */
+#define MTL_TSA_SP			0x00
+#define MTL_TSA_ETS			0x02
+
+/* DMA register offsets */
+#define DMA_MR				0x3000
+#define DMA_SBMR			0x3004
+#define DMA_ISR				0x3008
+#define DMA_DSR0			0x3020
+#define DMA_DSR1			0x3024
+
+/* DMA register entry bit positions and sizes */
+#define DMA_ISR_MACIS_POS		17
+#define DMA_ISR_MACIS_LEN		1
+#define DMA_ISR_MTLIS_POS		16
+#define DMA_ISR_MTLIS_LEN		1
+#define DMA_MR_SWR_POS			0
+#define DMA_MR_SWR_LEN			1
+#define DMA_SBMR_EAME_POS		11
+#define DMA_SBMR_EAME_LEN		1
+#define DMA_SBMR_BLEN_64_POS		5
+#define DMA_SBMR_BLEN_64_LEN		1
+#define DMA_SBMR_BLEN_128_POS		6
+#define DMA_SBMR_BLEN_128_LEN		1
+#define DMA_SBMR_BLEN_256_POS		7
+#define DMA_SBMR_BLEN_256_LEN		1
+#define DMA_SBMR_UNDEF_POS		0
+#define DMA_SBMR_UNDEF_LEN		1
+
+/* DMA register values */
+#define DMA_DSR_RPS_LEN			4
+#define DMA_DSR_TPS_LEN			4
+#define DMA_DSR_Q_LEN			(DMA_DSR_RPS_LEN + DMA_DSR_TPS_LEN)
+#define DMA_DSR0_TPS_START		12
+#define DMA_DSRX_FIRST_QUEUE		3
+#define DMA_DSRX_INC			4
+#define DMA_DSRX_QPR			4
+#define DMA_DSRX_TPS_START		4
+#define DMA_TPS_STOPPED			0x00
+#define DMA_TPS_SUSPENDED		0x06
+
+/* DMA channel register offsets
+ *   Multiple channels can be active.  The first channel has registers
+ *   that begin at 0x3100.  Each subsequent channel has registers that
+ *   are accessed using an offset of 0x80 from the previous channel.
+ */
+#define DMA_CH_BASE			0x3100
+#define DMA_CH_INC			0x80
+
+#define DMA_CH_CR			0x00
+#define DMA_CH_TCR			0x04
+#define DMA_CH_RCR			0x08
+#define DMA_CH_TDLR_HI			0x10
+#define DMA_CH_TDLR_LO			0x14
+#define DMA_CH_RDLR_HI			0x18
+#define DMA_CH_RDLR_LO			0x1c
+#define DMA_CH_TDTR_LO			0x24
+#define DMA_CH_RDTR_LO			0x2c
+#define DMA_CH_TDRLR			0x30
+#define DMA_CH_RDRLR			0x34
+#define DMA_CH_IER			0x38
+#define DMA_CH_RIWT			0x3c
+#define DMA_CH_SR			0x60
+
+/* DMA channel register entry bit positions and sizes */
+#define DMA_CH_CR_PBLX8_POS		16
+#define DMA_CH_CR_PBLX8_LEN		1
+#define DMA_CH_CR_SPH_POS		24
+#define DMA_CH_CR_SPH_LEN		1
+#define DMA_CH_IER_AIE_POS		15
+#define DMA_CH_IER_AIE_LEN		1
+#define DMA_CH_IER_FBEE_POS		12
+#define DMA_CH_IER_FBEE_LEN		1
+#define DMA_CH_IER_NIE_POS		16
+#define DMA_CH_IER_NIE_LEN		1
+#define DMA_CH_IER_RBUE_POS		7
+#define DMA_CH_IER_RBUE_LEN		1
+#define DMA_CH_IER_RIE_POS		6
+#define DMA_CH_IER_RIE_LEN		1
+#define DMA_CH_IER_RSE_POS		8
+#define DMA_CH_IER_RSE_LEN		1
+#define DMA_CH_IER_TBUE_POS		2
+#define DMA_CH_IER_TBUE_LEN		1
+#define DMA_CH_IER_TIE_POS		0
+#define DMA_CH_IER_TIE_LEN		1
+#define DMA_CH_IER_TXSE_POS		1
+#define DMA_CH_IER_TXSE_LEN		1
+#define DMA_CH_RCR_PBL_POS		16
+#define DMA_CH_RCR_PBL_LEN		6
+#define DMA_CH_RCR_RBSZ_POS		1
+#define DMA_CH_RCR_RBSZ_LEN		14
+#define DMA_CH_RCR_SR_POS		0
+#define DMA_CH_RCR_SR_LEN		1
+#define DMA_CH_RIWT_RWT_POS		0
+#define DMA_CH_RIWT_RWT_LEN		8
+#define DMA_CH_SR_FBE_POS		12
+#define DMA_CH_SR_FBE_LEN		1
+#define DMA_CH_SR_RBU_POS		7
+#define DMA_CH_SR_RBU_LEN		1
+#define DMA_CH_SR_RI_POS		6
+#define DMA_CH_SR_RI_LEN		1
+#define DMA_CH_SR_RPS_POS		8
+#define DMA_CH_SR_RPS_LEN		1
+#define DMA_CH_SR_TBU_POS		2
+#define DMA_CH_SR_TBU_LEN		1
+#define DMA_CH_SR_TI_POS		0
+#define DMA_CH_SR_TI_LEN		1
+#define DMA_CH_SR_TPS_POS		1
+#define DMA_CH_SR_TPS_LEN		1
+#define DMA_CH_TCR_OSP_POS		4
+#define DMA_CH_TCR_OSP_LEN		1
+#define DMA_CH_TCR_PBL_POS		16
+#define DMA_CH_TCR_PBL_LEN		6
+#define DMA_CH_TCR_ST_POS		0
+#define DMA_CH_TCR_ST_LEN		1
+#define DMA_CH_TCR_TSE_POS		12
+#define DMA_CH_TCR_TSE_LEN		1
+
+/* DMA channel register values */
+#define DMA_OSP_DISABLE			0x00
+#define DMA_OSP_ENABLE			0x01
+#define DMA_PBL_1			1
+#define DMA_PBL_2			2
+#define DMA_PBL_4			4
+#define DMA_PBL_8			8
+#define DMA_PBL_16			16
+#define DMA_PBL_32			32
+#define DMA_PBL_64			64
+#define DMA_PBL_128			128
+#define DMA_PBL_256			256
+#define DMA_PBL_X8_DISABLE		0x00
+#define DMA_PBL_X8_ENABLE		0x01
+
+/* Descriptor/Packet entry bit positions and sizes */
+#define RX_PACKET_ERRORS_CRC_POS		2
+#define RX_PACKET_ERRORS_CRC_LEN		1
+#define RX_PACKET_ERRORS_FRAME_POS		3
+#define RX_PACKET_ERRORS_FRAME_LEN		1
+#define RX_PACKET_ERRORS_LENGTH_POS		0
+#define RX_PACKET_ERRORS_LENGTH_LEN		1
+#define RX_PACKET_ERRORS_OVERRUN_POS		1
+#define RX_PACKET_ERRORS_OVERRUN_LEN		1
+
+#define RX_PACKET_ATTRIBUTES_CSUM_DONE_POS	0
+#define RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN	1
+#define RX_PACKET_ATTRIBUTES_VLAN_CTAG_POS	1
+#define RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN	1
+#define RX_PACKET_ATTRIBUTES_INCOMPLETE_POS	2
+#define RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN	1
+#define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS	3
+#define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN	1
+#define RX_PACKET_ATTRIBUTES_CONTEXT_POS	4
+#define RX_PACKET_ATTRIBUTES_CONTEXT_LEN	1
+#define RX_PACKET_ATTRIBUTES_RX_TSTAMP_POS	5
+#define RX_PACKET_ATTRIBUTES_RX_TSTAMP_LEN	1
+#define RX_PACKET_ATTRIBUTES_RSS_HASH_POS	6
+#define RX_PACKET_ATTRIBUTES_RSS_HASH_LEN	1
+
+#define RX_NORMAL_DESC0_OVT_POS			0
+#define RX_NORMAL_DESC0_OVT_LEN			16
+#define RX_NORMAL_DESC2_HL_POS			0
+#define RX_NORMAL_DESC2_HL_LEN			10
+#define RX_NORMAL_DESC3_CDA_POS			27
+#define RX_NORMAL_DESC3_CDA_LEN			1
+#define RX_NORMAL_DESC3_CTXT_POS		30
+#define RX_NORMAL_DESC3_CTXT_LEN		1
+#define RX_NORMAL_DESC3_ES_POS			15
+#define RX_NORMAL_DESC3_ES_LEN			1
+#define RX_NORMAL_DESC3_ETLT_POS		16
+#define RX_NORMAL_DESC3_ETLT_LEN		4
+#define RX_NORMAL_DESC3_FD_POS			29
+#define RX_NORMAL_DESC3_FD_LEN			1
+#define RX_NORMAL_DESC3_INTE_POS		30
+#define RX_NORMAL_DESC3_INTE_LEN		1
+#define RX_NORMAL_DESC3_L34T_POS		20
+#define RX_NORMAL_DESC3_L34T_LEN		4
+#define RX_NORMAL_DESC3_LD_POS			28
+#define RX_NORMAL_DESC3_LD_LEN			1
+#define RX_NORMAL_DESC3_OWN_POS			31
+#define RX_NORMAL_DESC3_OWN_LEN			1
+#define RX_NORMAL_DESC3_PL_POS			0
+#define RX_NORMAL_DESC3_PL_LEN			14
+#define RX_NORMAL_DESC3_RSV_POS			26
+#define RX_NORMAL_DESC3_RSV_LEN			1
+
+#define RX_DESC3_L34T_IPV4_TCP			1
+#define RX_DESC3_L34T_IPV4_UDP			2
+#define RX_DESC3_L34T_IPV4_ICMP			3
+#define RX_DESC3_L34T_IPV6_TCP			9
+#define RX_DESC3_L34T_IPV6_UDP			10
+#define RX_DESC3_L34T_IPV6_ICMP			11
+
+#define RX_CONTEXT_DESC3_TSA_POS		4
+#define RX_CONTEXT_DESC3_TSA_LEN		1
+#define RX_CONTEXT_DESC3_TSD_POS		6
+#define RX_CONTEXT_DESC3_TSD_LEN		1
+
+#define TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS	0
+#define TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN	1
+#define TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS	1
+#define TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN	1
+#define TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS	2
+#define TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN	1
+#define TX_PACKET_ATTRIBUTES_PTP_POS		3
+#define TX_PACKET_ATTRIBUTES_PTP_LEN		1
+
+#define TX_CONTEXT_DESC2_MSS_POS		0
+#define TX_CONTEXT_DESC2_MSS_LEN		15
+#define TX_CONTEXT_DESC3_CTXT_POS		30
+#define TX_CONTEXT_DESC3_CTXT_LEN		1
+#define TX_CONTEXT_DESC3_TCMSSV_POS		26
+#define TX_CONTEXT_DESC3_TCMSSV_LEN		1
+#define TX_CONTEXT_DESC3_VLTV_POS		16
+#define TX_CONTEXT_DESC3_VLTV_LEN		1
+#define TX_CONTEXT_DESC3_VT_POS			0
+#define TX_CONTEXT_DESC3_VT_LEN			16
+
+#define TX_NORMAL_DESC2_HL_B1L_POS		0
+#define TX_NORMAL_DESC2_HL_B1L_LEN		14
+#define TX_NORMAL_DESC2_IC_POS			31
+#define TX_NORMAL_DESC2_IC_LEN			1
+#define TX_NORMAL_DESC2_TTSE_POS		30
+#define TX_NORMAL_DESC2_TTSE_LEN		1
+#define TX_NORMAL_DESC2_VTIR_POS		14
+#define TX_NORMAL_DESC2_VTIR_LEN		2
+#define TX_NORMAL_DESC3_CIC_POS			16
+#define TX_NORMAL_DESC3_CIC_LEN			2
+#define TX_NORMAL_DESC3_CPC_POS			26
+#define TX_NORMAL_DESC3_CPC_LEN			2
+#define TX_NORMAL_DESC3_CTXT_POS		30
+#define TX_NORMAL_DESC3_CTXT_LEN		1
+#define TX_NORMAL_DESC3_FD_POS			29
+#define TX_NORMAL_DESC3_FD_LEN			1
+#define TX_NORMAL_DESC3_FL_POS			0
+#define TX_NORMAL_DESC3_FL_LEN			15
+#define TX_NORMAL_DESC3_LD_POS			28
+#define TX_NORMAL_DESC3_LD_LEN			1
+#define TX_NORMAL_DESC3_OWN_POS			31
+#define TX_NORMAL_DESC3_OWN_LEN			1
+#define TX_NORMAL_DESC3_TCPHDRLEN_POS		19
+#define TX_NORMAL_DESC3_TCPHDRLEN_LEN		4
+#define TX_NORMAL_DESC3_TCPPL_POS		0
+#define TX_NORMAL_DESC3_TCPPL_LEN		18
+#define TX_NORMAL_DESC3_TSE_POS			18
+#define TX_NORMAL_DESC3_TSE_LEN			1
+
+#define TX_NORMAL_DESC2_VLAN_INSERT		0x2
+
+#define XLGMAC_MTL_REG(pdata, n, reg)					\
+	((pdata)->mac_regs + MTL_Q_BASE + ((n) * MTL_Q_INC) + (reg))
+
+#define XLGMAC_DMA_REG(channel, reg)	((channel)->dma_regs + (reg))
+
+#endif /* __DWC_XLGMAC_REG_H__ */
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac.h b/drivers/net/ethernet/synopsys/dwc-xlgmac.h
new file mode 100644
index 000000000000..676b2fb8dfcc
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac.h
@@ -0,0 +1,649 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#ifndef __DWC_XLGMAC_H__
+#define __DWC_XLGMAC_H__
+
+#include <linux/dma-mapping.h>
+#include <linux/netdevice.h>
+#include <linux/workqueue.h>
+#include <linux/phy.h>
+#include <linux/if_vlan.h>
+#include <linux/bitops.h>
+#include <linux/timecounter.h>
+
+#define XLGMAC_DRV_NAME			"dwc-xlgmac"
+#define XLGMAC_DRV_VERSION		"1.0.0"
+#define XLGMAC_DRV_DESC			"Synopsys DWC XLGMAC Driver"
+
+/* Descriptor related parameters */
+#define XLGMAC_TX_DESC_CNT		1024
+#define XLGMAC_TX_DESC_MIN_FREE		(XLGMAC_TX_DESC_CNT >> 3)
+#define XLGMAC_TX_DESC_MAX_PROC		(XLGMAC_TX_DESC_CNT >> 1)
+#define XLGMAC_RX_DESC_CNT		1024
+#define XLGMAC_RX_DESC_MAX_DIRTY	(XLGMAC_RX_DESC_CNT >> 3)
+
+/* Descriptors required for maximum contiguous TSO/GSO packet */
+#define XLGMAC_TX_MAX_SPLIT	((GSO_MAX_SIZE / XLGMAC_TX_MAX_BUF_SIZE) + 1)
+
+/* Maximum possible descriptors needed for a SKB */
+#define XLGMAC_TX_MAX_DESC_NR	(MAX_SKB_FRAGS + XLGMAC_TX_MAX_SPLIT + 2)
+
+#define XLGMAC_TX_MAX_BUF_SIZE	(0x3fff & ~(64 - 1))
+#define XLGMAC_RX_MIN_BUF_SIZE	(ETH_FRAME_LEN + ETH_FCS_LEN + VLAN_HLEN)
+#define XLGMAC_RX_BUF_ALIGN	64
+
+/* Maximum Size for Splitting the Header Data
+ * Keep in sync with SKB_ALLOC_SIZE
+ * 3'b000: 64 bytes, 3'b001: 128 bytes
+ * 3'b010: 256 bytes, 3'b011: 512 bytes
+ * 3'b100: 1023 bytes ,   3'b101'3'b111: Reserved
+ */
+#define XLGMAC_SPH_HDSMS_SIZE		3
+#define XLGMAC_SKB_ALLOC_SIZE		512
+
+#define XLGMAC_MAX_FIFO			81920
+
+#define XLGMAC_MAX_DMA_CHANNELS		16
+#define XLGMAC_DMA_STOP_TIMEOUT		5
+#define XLGMAC_DMA_INTERRUPT_MASK	0x31c7
+
+/* Default coalescing parameters */
+#define XLGMAC_INIT_DMA_TX_USECS	1000
+#define XLGMAC_INIT_DMA_TX_FRAMES	25
+#define XLGMAC_INIT_DMA_RX_USECS	30
+#define XLGMAC_INIT_DMA_RX_FRAMES	25
+
+/* Flow control queue count */
+#define XLGMAC_MAX_FLOW_CONTROL_QUEUES	8
+
+/* System clock is 125 MHz */
+#define XLGMAC_SYSCLOCK			125000000
+
+/* Maximum MAC address hash table size (256 bits = 8 bytes) */
+#define XLGMAC_MAC_HASH_TABLE_SIZE	8
+
+/* Receive Side Scaling */
+#define XLGMAC_RSS_HASH_KEY_SIZE	40
+#define XLGMAC_RSS_MAX_TABLE_SIZE	256
+#define XLGMAC_RSS_LOOKUP_TABLE_TYPE	0
+#define XLGMAC_RSS_HASH_KEY_TYPE	1
+
+#define XLGMAC_STD_PACKET_MTU		1500
+#define XLGMAC_JUMBO_PACKET_MTU		9000
+
+/* Helper macro for descriptor handling
+ *  Always use XLGMAC_GET_DESC_DATA to access the descriptor data
+ */
+#define XLGMAC_GET_DESC_DATA(ring, idx) ({				\
+	typeof(ring) _ring = (ring);					\
+	((_ring)->desc_data_head +					\
+	 ((idx) & ((_ring)->dma_desc_count - 1)));			\
+})
+
+#define XLGMAC_GET_REG_BITS(var, pos, len) ({				\
+	typeof(pos) _pos = (pos);					\
+	typeof(len) _len = (len);					\
+	((var) & GENMASK(_pos + _len - 1, _pos)) >> (_pos);		\
+})
+
+#define XLGMAC_GET_REG_BITS_LE(var, pos, len) ({			\
+	typeof(pos) _pos = (pos);					\
+	typeof(len) _len = (len);					\
+	typeof(var) _var = le32_to_cpu((var));				\
+	((_var) & GENMASK(_pos + _len - 1, _pos)) >> (_pos);		\
+})
+
+#define XLGMAC_SET_REG_BITS(var, pos, len, val) ({			\
+	typeof(var) _var = (var);					\
+	typeof(pos) _pos = (pos);					\
+	typeof(len) _len = (len);					\
+	typeof(val) _val = (val);					\
+	_val = (_val << _pos) & GENMASK(_pos + _len - 1, _pos);		\
+	_var = (_var & ~GENMASK(_pos + _len - 1, _pos)) | _val;		\
+})
+
+#define XLGMAC_SET_REG_BITS_LE(var, pos, len, val) ({			\
+	typeof(var) _var = (var);					\
+	typeof(pos) _pos = (pos);					\
+	typeof(len) _len = (len);					\
+	typeof(val) _val = (val);					\
+	_val = (_val << _pos) & GENMASK(_pos + _len - 1, _pos);		\
+	_var = (_var & ~GENMASK(_pos + _len - 1, _pos)) | _val;		\
+	cpu_to_le32(_var);						\
+})
+
+struct xlgmac_pdata;
+
+enum xlgmac_int {
+	XLGMAC_INT_DMA_CH_SR_TI,
+	XLGMAC_INT_DMA_CH_SR_TPS,
+	XLGMAC_INT_DMA_CH_SR_TBU,
+	XLGMAC_INT_DMA_CH_SR_RI,
+	XLGMAC_INT_DMA_CH_SR_RBU,
+	XLGMAC_INT_DMA_CH_SR_RPS,
+	XLGMAC_INT_DMA_CH_SR_TI_RI,
+	XLGMAC_INT_DMA_CH_SR_FBE,
+	XLGMAC_INT_DMA_ALL,
+};
+
+struct xlgmac_stats {
+	/* MMC TX counters */
+	u64 txoctetcount_gb;
+	u64 txframecount_gb;
+	u64 txbroadcastframes_g;
+	u64 txmulticastframes_g;
+	u64 tx64octets_gb;
+	u64 tx65to127octets_gb;
+	u64 tx128to255octets_gb;
+	u64 tx256to511octets_gb;
+	u64 tx512to1023octets_gb;
+	u64 tx1024tomaxoctets_gb;
+	u64 txunicastframes_gb;
+	u64 txmulticastframes_gb;
+	u64 txbroadcastframes_gb;
+	u64 txunderflowerror;
+	u64 txoctetcount_g;
+	u64 txframecount_g;
+	u64 txpauseframes;
+	u64 txvlanframes_g;
+
+	/* MMC RX counters */
+	u64 rxframecount_gb;
+	u64 rxoctetcount_gb;
+	u64 rxoctetcount_g;
+	u64 rxbroadcastframes_g;
+	u64 rxmulticastframes_g;
+	u64 rxcrcerror;
+	u64 rxrunterror;
+	u64 rxjabbererror;
+	u64 rxundersize_g;
+	u64 rxoversize_g;
+	u64 rx64octets_gb;
+	u64 rx65to127octets_gb;
+	u64 rx128to255octets_gb;
+	u64 rx256to511octets_gb;
+	u64 rx512to1023octets_gb;
+	u64 rx1024tomaxoctets_gb;
+	u64 rxunicastframes_g;
+	u64 rxlengtherror;
+	u64 rxoutofrangetype;
+	u64 rxpauseframes;
+	u64 rxfifooverflow;
+	u64 rxvlanframes_gb;
+	u64 rxwatchdogerror;
+
+	/* Extra counters */
+	u64 tx_tso_packets;
+	u64 rx_split_header_packets;
+	u64 rx_buffer_unavailable;
+};
+
+struct xlgmac_ring_buf {
+	struct sk_buff *skb;
+	dma_addr_t skb_dma;
+	unsigned int skb_len;
+};
+
+/* Common Tx and Rx DMA hardware descriptor */
+struct xlgmac_dma_desc {
+	__le32 desc0;
+	__le32 desc1;
+	__le32 desc2;
+	__le32 desc3;
+};
+
+/* Page allocation related values */
+struct xlgmac_page_alloc {
+	struct page *pages;
+	unsigned int pages_len;
+	unsigned int pages_offset;
+
+	dma_addr_t pages_dma;
+};
+
+/* Ring entry buffer data */
+struct xlgmac_buffer_data {
+	struct xlgmac_page_alloc pa;
+	struct xlgmac_page_alloc pa_unmap;
+
+	dma_addr_t dma_base;
+	unsigned long dma_off;
+	unsigned int dma_len;
+};
+
+/* Tx-related desc data */
+struct xlgmac_tx_desc_data {
+	unsigned int packets;		/* BQL packet count */
+	unsigned int bytes;		/* BQL byte count */
+};
+
+/* Rx-related desc data */
+struct xlgmac_rx_desc_data {
+	struct xlgmac_buffer_data hdr;	/* Header locations */
+	struct xlgmac_buffer_data buf;	/* Payload locations */
+
+	unsigned short hdr_len;		/* Length of received header */
+	unsigned short len;		/* Length of received packet */
+};
+
+struct xlgmac_pkt_info {
+	struct sk_buff *skb;
+
+	unsigned int attributes;
+
+	unsigned int errors;
+
+	/* descriptors needed for this packet */
+	unsigned int desc_count;
+	unsigned int length;
+
+	unsigned int tx_packets;
+	unsigned int tx_bytes;
+
+	unsigned int header_len;
+	unsigned int tcp_header_len;
+	unsigned int tcp_payload_len;
+	unsigned short mss;
+
+	unsigned short vlan_ctag;
+
+	u64 rx_tstamp;
+
+	u32 rss_hash;
+	enum pkt_hash_types rss_hash_type;
+};
+
+struct xlgmac_desc_data {
+	/* dma_desc: Virtual address of descriptor
+	 *  dma_desc_addr: DMA address of descriptor
+	 */
+	struct xlgmac_dma_desc *dma_desc;
+	dma_addr_t dma_desc_addr;
+
+	/* skb: Virtual address of SKB
+	 *  skb_dma: DMA address of SKB data
+	 *  skb_dma_len: Length of SKB DMA area
+	 */
+	struct sk_buff *skb;
+	dma_addr_t skb_dma;
+	unsigned int skb_dma_len;
+
+	/* Tx/Rx -related data */
+	struct xlgmac_tx_desc_data tx;
+	struct xlgmac_rx_desc_data rx;
+
+	unsigned int mapped_as_page;
+
+	/* Incomplete receive save location.  If the budget is exhausted
+	 * or the last descriptor (last normal descriptor or a following
+	 * context descriptor) has not been DMA'd yet the current state
+	 * of the receive processing needs to be saved.
+	 */
+	unsigned int state_saved;
+	struct {
+		struct sk_buff *skb;
+		unsigned int len;
+		unsigned int error;
+	} state;
+};
+
+struct xlgmac_ring {
+	/* Per packet related information */
+	struct xlgmac_pkt_info pkt_info;
+
+	/* Virtual/DMA addresses of DMA descriptor list and the total count */
+	struct xlgmac_dma_desc *dma_desc_head;
+	dma_addr_t dma_desc_head_addr;
+	unsigned int dma_desc_count;
+
+	/* Array of descriptor data corresponding the DMA descriptor
+	 * (always use the XLGMAC_GET_DESC_DATA macro to access this data)
+	 */
+	struct xlgmac_desc_data *desc_data_head;
+
+	/* Page allocation for RX buffers */
+	struct xlgmac_page_alloc rx_hdr_pa;
+	struct xlgmac_page_alloc rx_buf_pa;
+
+	/* Ring index values
+	 *  cur   - Tx: index of descriptor to be used for current transfer
+	 *          Rx: index of descriptor to check for packet availability
+	 *  dirty - Tx: index of descriptor to check for transfer complete
+	 *          Rx: index of descriptor to check for buffer reallocation
+	 */
+	unsigned int cur;
+	unsigned int dirty;
+
+	/* Coalesce frame count used for interrupt bit setting */
+	unsigned int coalesce_count;
+
+	union {
+		struct {
+			unsigned int xmit_more;
+			unsigned int queue_stopped;
+			unsigned short cur_mss;
+			unsigned short cur_vlan_ctag;
+		} tx;
+	};
+} ____cacheline_aligned;
+
+struct xlgmac_channel {
+	char name[16];
+
+	/* Address of private data area for device */
+	struct xlgmac_pdata *pdata;
+
+	/* Queue index and base address of queue's DMA registers */
+	unsigned int queue_index;
+	void __iomem *dma_regs;
+
+	/* Per channel interrupt irq number */
+	int dma_irq;
+	char dma_irq_name[IFNAMSIZ + 32];
+
+	/* Netdev related settings */
+	struct napi_struct napi;
+
+	unsigned int saved_ier;
+
+	unsigned int tx_timer_active;
+	struct timer_list tx_timer;
+
+	struct xlgmac_ring *tx_ring;
+	struct xlgmac_ring *rx_ring;
+} ____cacheline_aligned;
+
+struct xlgmac_desc_ops {
+	int (*alloc_channles_and_rings)(struct xlgmac_pdata *pdata);
+	void (*free_channels_and_rings)(struct xlgmac_pdata *pdata);
+	int (*map_tx_skb)(struct xlgmac_channel *channel,
+			  struct sk_buff *skb);
+	int (*map_rx_buffer)(struct xlgmac_pdata *pdata,
+			     struct xlgmac_ring *ring,
+			struct xlgmac_desc_data *desc_data);
+	void (*unmap_desc_data)(struct xlgmac_pdata *pdata,
+				struct xlgmac_desc_data *desc_data);
+	void (*tx_desc_init)(struct xlgmac_pdata *pdata);
+	void (*rx_desc_init)(struct xlgmac_pdata *pdata);
+};
+
+struct xlgmac_hw_ops {
+	int (*init)(struct xlgmac_pdata *pdata);
+	int (*exit)(struct xlgmac_pdata *pdata);
+
+	int (*tx_complete)(struct xlgmac_dma_desc *dma_desc);
+
+	void (*enable_tx)(struct xlgmac_pdata *pdata);
+	void (*disable_tx)(struct xlgmac_pdata *pdata);
+	void (*enable_rx)(struct xlgmac_pdata *pdata);
+	void (*disable_rx)(struct xlgmac_pdata *pdata);
+
+	int (*enable_int)(struct xlgmac_channel *channel,
+			  enum xlgmac_int int_id);
+	int (*disable_int)(struct xlgmac_channel *channel,
+			   enum xlgmac_int int_id);
+	void (*dev_xmit)(struct xlgmac_channel *channel);
+	int (*dev_read)(struct xlgmac_channel *channel);
+
+	int (*set_mac_address)(struct xlgmac_pdata *pdata, u8 *addr);
+	int (*config_rx_mode)(struct xlgmac_pdata *pdata);
+	int (*enable_rx_csum)(struct xlgmac_pdata *pdata);
+	int (*disable_rx_csum)(struct xlgmac_pdata *pdata);
+
+	/* For MII speed configuration */
+	int (*set_xlgmii_25000_speed)(struct xlgmac_pdata *pdata);
+	int (*set_xlgmii_40000_speed)(struct xlgmac_pdata *pdata);
+	int (*set_xlgmii_50000_speed)(struct xlgmac_pdata *pdata);
+	int (*set_xlgmii_100000_speed)(struct xlgmac_pdata *pdata);
+
+	/* For descriptor related operation */
+	void (*tx_desc_init)(struct xlgmac_channel *channel);
+	void (*rx_desc_init)(struct xlgmac_channel *channel);
+	void (*tx_desc_reset)(struct xlgmac_desc_data *desc_data);
+	void (*rx_desc_reset)(struct xlgmac_pdata *pdata,
+			      struct xlgmac_desc_data *desc_data,
+			unsigned int index);
+	int (*is_last_desc)(struct xlgmac_dma_desc *dma_desc);
+	int (*is_context_desc)(struct xlgmac_dma_desc *dma_desc);
+	void (*tx_start_xmit)(struct xlgmac_channel *channel,
+			      struct xlgmac_ring *ring);
+
+	/* For Flow Control */
+	int (*config_tx_flow_control)(struct xlgmac_pdata *pdata);
+	int (*config_rx_flow_control)(struct xlgmac_pdata *pdata);
+
+	/* For Vlan related config */
+	int (*enable_rx_vlan_stripping)(struct xlgmac_pdata *pdata);
+	int (*disable_rx_vlan_stripping)(struct xlgmac_pdata *pdata);
+	int (*enable_rx_vlan_filtering)(struct xlgmac_pdata *pdata);
+	int (*disable_rx_vlan_filtering)(struct xlgmac_pdata *pdata);
+	int (*update_vlan_hash_table)(struct xlgmac_pdata *pdata);
+
+	/* For RX coalescing */
+	int (*config_rx_coalesce)(struct xlgmac_pdata *pdata);
+	int (*config_tx_coalesce)(struct xlgmac_pdata *pdata);
+	unsigned int (*usec_to_riwt)(struct xlgmac_pdata *pdata,
+				     unsigned int usec);
+	unsigned int (*riwt_to_usec)(struct xlgmac_pdata *pdata,
+				     unsigned int riwt);
+
+	/* For RX and TX threshold config */
+	int (*config_rx_threshold)(struct xlgmac_pdata *pdata,
+				   unsigned int val);
+	int (*config_tx_threshold)(struct xlgmac_pdata *pdata,
+				   unsigned int val);
+
+	/* For RX and TX Store and Forward Mode config */
+	int (*config_rsf_mode)(struct xlgmac_pdata *pdata,
+			       unsigned int val);
+	int (*config_tsf_mode)(struct xlgmac_pdata *pdata,
+			       unsigned int val);
+
+	/* For TX DMA Operate on Second Frame config */
+	int (*config_osp_mode)(struct xlgmac_pdata *pdata);
+
+	/* For RX and TX PBL config */
+	int (*config_rx_pbl_val)(struct xlgmac_pdata *pdata);
+	int (*get_rx_pbl_val)(struct xlgmac_pdata *pdata);
+	int (*config_tx_pbl_val)(struct xlgmac_pdata *pdata);
+	int (*get_tx_pbl_val)(struct xlgmac_pdata *pdata);
+	int (*config_pblx8)(struct xlgmac_pdata *pdata);
+
+	/* For MMC statistics */
+	void (*rx_mmc_int)(struct xlgmac_pdata *pdata);
+	void (*tx_mmc_int)(struct xlgmac_pdata *pdata);
+	void (*read_mmc_stats)(struct xlgmac_pdata *pdata);
+
+	/* For Receive Side Scaling */
+	int (*enable_rss)(struct xlgmac_pdata *pdata);
+	int (*disable_rss)(struct xlgmac_pdata *pdata);
+	int (*set_rss_hash_key)(struct xlgmac_pdata *pdata,
+				const u8 *key);
+	int (*set_rss_lookup_table)(struct xlgmac_pdata *pdata,
+				    const u32 *table);
+};
+
+/* This structure contains flags that indicate what hardware features
+ * or configurations are present in the device.
+ */
+struct xlgmac_hw_features {
+	/* HW Version */
+	unsigned int version;
+
+	/* HW Feature Register0 */
+	unsigned int phyifsel;		/* PHY interface support */
+	unsigned int vlhash;		/* VLAN Hash Filter */
+	unsigned int sma;		/* SMA(MDIO) Interface */
+	unsigned int rwk;		/* PMT remote wake-up packet */
+	unsigned int mgk;		/* PMT magic packet */
+	unsigned int mmc;		/* RMON module */
+	unsigned int aoe;		/* ARP Offload */
+	unsigned int ts;		/* IEEE 1588-2008 Advanced Timestamp */
+	unsigned int eee;		/* Energy Efficient Ethernet */
+	unsigned int tx_coe;		/* Tx Checksum Offload */
+	unsigned int rx_coe;		/* Rx Checksum Offload */
+	unsigned int addn_mac;		/* Additional MAC Addresses */
+	unsigned int ts_src;		/* Timestamp Source */
+	unsigned int sa_vlan_ins;	/* Source Address or VLAN Insertion */
+
+	/* HW Feature Register1 */
+	unsigned int rx_fifo_size;	/* MTL Receive FIFO Size */
+	unsigned int tx_fifo_size;	/* MTL Transmit FIFO Size */
+	unsigned int adv_ts_hi;		/* Advance Timestamping High Word */
+	unsigned int dma_width;		/* DMA width */
+	unsigned int dcb;		/* DCB Feature */
+	unsigned int sph;		/* Split Header Feature */
+	unsigned int tso;		/* TCP Segmentation Offload */
+	unsigned int dma_debug;		/* DMA Debug Registers */
+	unsigned int rss;		/* Receive Side Scaling */
+	unsigned int tc_cnt;		/* Number of Traffic Classes */
+	unsigned int hash_table_size;	/* Hash Table Size */
+	unsigned int l3l4_filter_num;	/* Number of L3-L4 Filters */
+
+	/* HW Feature Register2 */
+	unsigned int rx_q_cnt;		/* Number of MTL Receive Queues */
+	unsigned int tx_q_cnt;		/* Number of MTL Transmit Queues */
+	unsigned int rx_ch_cnt;		/* Number of DMA Receive Channels */
+	unsigned int tx_ch_cnt;		/* Number of DMA Transmit Channels */
+	unsigned int pps_out_num;	/* Number of PPS outputs */
+	unsigned int aux_snap_num;	/* Number of Aux snapshot inputs */
+};
+
+struct xlgmac_resources {
+	void __iomem *addr;
+	int irq;
+};
+
+struct xlgmac_pdata {
+	struct net_device *netdev;
+	struct device *dev;
+
+	struct xlgmac_hw_ops hw_ops;
+	struct xlgmac_desc_ops desc_ops;
+
+	/* Device statistics */
+	struct xlgmac_stats stats;
+
+	u32 msg_enable;
+
+	/* MAC registers base */
+	void __iomem *mac_regs;
+
+	/* Hardware features of the device */
+	struct xlgmac_hw_features hw_feat;
+
+	struct work_struct restart_work;
+
+	/* Rings for Tx/Rx on a DMA channel */
+	struct xlgmac_channel *channel_head;
+	unsigned int channel_count;
+	unsigned int tx_ring_count;
+	unsigned int rx_ring_count;
+	unsigned int tx_desc_count;
+	unsigned int rx_desc_count;
+	unsigned int tx_q_count;
+	unsigned int rx_q_count;
+
+	/* Tx/Rx common settings */
+	unsigned int pblx8;
+
+	/* Tx settings */
+	unsigned int tx_sf_mode;
+	unsigned int tx_threshold;
+	unsigned int tx_pbl;
+	unsigned int tx_osp_mode;
+
+	/* Rx settings */
+	unsigned int rx_sf_mode;
+	unsigned int rx_threshold;
+	unsigned int rx_pbl;
+
+	/* Tx coalescing settings */
+	unsigned int tx_usecs;
+	unsigned int tx_frames;
+
+	/* Rx coalescing settings */
+	unsigned int rx_riwt;
+	unsigned int rx_usecs;
+	unsigned int rx_frames;
+
+	/* Current Rx buffer size */
+	unsigned int rx_buf_size;
+
+	/* Flow control settings */
+	unsigned int tx_pause;
+	unsigned int rx_pause;
+
+	/* Device interrupt number */
+	int dev_irq;
+	unsigned int per_channel_irq;
+	int channel_irq[XLGMAC_MAX_DMA_CHANNELS];
+
+	/* Netdev related settings */
+	unsigned char mac_addr[ETH_ALEN];
+	netdev_features_t netdev_features;
+	struct napi_struct napi;
+
+	/* Filtering support */
+	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
+
+	/* Device clocks */
+	unsigned long sysclk_rate;
+
+	/* RSS addressing mutex */
+	struct mutex rss_mutex;
+
+	/* Receive Side Scaling settings */
+	u8 rss_key[XLGMAC_RSS_HASH_KEY_SIZE];
+	u32 rss_table[XLGMAC_RSS_MAX_TABLE_SIZE];
+	u32 rss_options;
+
+	int phy_speed;
+
+	char drv_name[32];
+	char drv_ver[32];
+};
+
+void xlgmac_init_desc_ops(struct xlgmac_desc_ops *desc_ops);
+void xlgmac_init_hw_ops(struct xlgmac_hw_ops *hw_ops);
+const struct net_device_ops *xlgmac_get_netdev_ops(void);
+void xlgmac_dump_tx_desc(struct xlgmac_pdata *pdata,
+			 struct xlgmac_ring *ring,
+			 unsigned int idx,
+			 unsigned int count,
+			 unsigned int flag);
+void xlgmac_dump_rx_desc(struct xlgmac_pdata *pdata,
+			 struct xlgmac_ring *ring,
+			 unsigned int idx);
+void xlgmac_print_pkt(struct net_device *netdev,
+		      struct sk_buff *skb, bool tx_rx);
+void xlgmac_get_all_hw_features(struct xlgmac_pdata *pdata);
+void xlgmac_print_all_hw_features(struct xlgmac_pdata *pdata);
+int xlgmac_drv_probe(struct device *dev,
+		     struct xlgmac_resources *res);
+int xlgmac_drv_remove(struct device *dev);
+
+/* For debug prints */
+#ifdef XLGMAC_DEBUG
+#define XLGMAC_PR(fmt, args...) \
+	pr_alert("[%s,%d]:" fmt, __func__, __LINE__, ## args)
+#else
+#define XLGMAC_PR(x...)		do { } while (0)
+#endif
+
+#endif /* __DWC_XLGMAC_H__ */
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index f864fd0663db..711fbbbc4b1f 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -2124,33 +2124,26 @@ static const char
 };
 
 /*
- * bdx_get_settings - get device-specific settings
+ * bdx_get_link_ksettings - get device-specific settings
  * @netdev
  * @ecmd
  */
-static int bdx_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
-{
-	u32 rdintcm;
-	u32 tdintcm;
-	struct bdx_priv *priv = netdev_priv(netdev);
-
-	rdintcm = priv->rdintcm;
-	tdintcm = priv->tdintcm;
-
-	ecmd->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE);
-	ecmd->advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_FIBRE);
-	ethtool_cmd_speed_set(ecmd, SPEED_10000);
-	ecmd->duplex = DUPLEX_FULL;
-	ecmd->port = PORT_FIBRE;
-	ecmd->transceiver = XCVR_EXTERNAL;	/* what does it mean? */
-	ecmd->autoneg = AUTONEG_DISABLE;
-
-	/* PCK_TH measures in multiples of FIFO bytes
-	   We translate to packets */
-	ecmd->maxtxpkt =
-	    ((GET_PCK_TH(tdintcm) * PCK_TH_MULT) / BDX_TXF_DESC_SZ);
-	ecmd->maxrxpkt =
-	    ((GET_PCK_TH(rdintcm) * PCK_TH_MULT) / sizeof(struct rxf_desc));
+static int bdx_get_link_ksettings(struct net_device *netdev,
+				  struct ethtool_link_ksettings *ecmd)
+{
+	ethtool_link_ksettings_zero_link_mode(ecmd, supported);
+	ethtool_link_ksettings_add_link_mode(ecmd, supported,
+					     10000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(ecmd, supported, FIBRE);
+	ethtool_link_ksettings_zero_link_mode(ecmd, advertising);
+	ethtool_link_ksettings_add_link_mode(ecmd, advertising,
+					     10000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(ecmd, advertising, FIBRE);
+
+	ecmd->base.speed = SPEED_10000;
+	ecmd->base.duplex = DUPLEX_FULL;
+	ecmd->base.port = PORT_FIBRE;
+	ecmd->base.autoneg = AUTONEG_DISABLE;
 
 	return 0;
 }
@@ -2384,7 +2377,6 @@ static void bdx_get_ethtool_stats(struct net_device *netdev,
 static void bdx_set_ethtool_ops(struct net_device *netdev)
 {
 	static const struct ethtool_ops bdx_ethtool_ops = {
-		.get_settings = bdx_get_settings,
 		.get_drvinfo = bdx_get_drvinfo,
 		.get_link = ethtool_op_get_link,
 		.get_coalesce = bdx_get_coalesce,
@@ -2394,6 +2386,7 @@ static void bdx_set_ethtool_ops(struct net_device *netdev)
 		.get_strings = bdx_get_strings,
 		.get_sset_count = bdx_get_sset_count,
 		.get_ethtool_stats = bdx_get_ethtool_stats,
+		.get_link_ksettings = bdx_get_link_ksettings,
 	};
 
 	netdev->ethtool_ops = &bdx_ethtool_ops;
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 7c7ae0890e90..9027c9c509b5 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -1882,6 +1882,7 @@ static u16 netcp_select_queue(struct net_device *dev, struct sk_buff *skb,
 static int netcp_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
 			  struct tc_to_netdev *tc)
 {
+	u8 num_tc;
 	int i;
 
 	/* setup tc must be called under rtnl lock */
@@ -1890,15 +1891,18 @@ static int netcp_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
 	if (tc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
 
+	tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+	num_tc = tc->mqprio->num_tc;
+
 	/* Sanity-check the number of traffic classes requested */
 	if ((dev->real_num_tx_queues <= 1) ||
-	    (dev->real_num_tx_queues < tc->tc))
+	    (dev->real_num_tx_queues < num_tc))
 		return -EINVAL;
 
 	/* Configure traffic class to queue mappings */
-	if (tc->tc) {
-		netdev_set_num_tc(dev, tc->tc);
-		for (i = 0; i < tc->tc; i++)
+	if (num_tc) {
+		netdev_set_num_tc(dev, num_tc);
+		for (i = 0; i < num_tc; i++)
 			netdev_set_tc_queue(dev, i, 1, i);
 	} else {
 		netdev_reset_tc(dev);
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
index 72013314bba8..fa6a06571187 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
@@ -1206,61 +1206,68 @@ void gelic_net_get_drvinfo(struct net_device *netdev,
 	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
 }
 
-static int gelic_ether_get_settings(struct net_device *netdev,
-				    struct ethtool_cmd *cmd)
+static int gelic_ether_get_link_ksettings(struct net_device *netdev,
+					  struct ethtool_link_ksettings *cmd)
 {
 	struct gelic_card *card = netdev_card(netdev);
+	u32 supported, advertising;
 
 	gelic_card_get_ether_port_status(card, 0);
 
 	if (card->ether_port_status & GELIC_LV1_ETHER_FULL_DUPLEX)
-		cmd->duplex = DUPLEX_FULL;
+		cmd->base.duplex = DUPLEX_FULL;
 	else
-		cmd->duplex = DUPLEX_HALF;
+		cmd->base.duplex = DUPLEX_HALF;
 
 	switch (card->ether_port_status & GELIC_LV1_ETHER_SPEED_MASK) {
 	case GELIC_LV1_ETHER_SPEED_10:
-		ethtool_cmd_speed_set(cmd, SPEED_10);
+		cmd->base.speed = SPEED_10;
 		break;
 	case GELIC_LV1_ETHER_SPEED_100:
-		ethtool_cmd_speed_set(cmd, SPEED_100);
+		cmd->base.speed = SPEED_100;
 		break;
 	case GELIC_LV1_ETHER_SPEED_1000:
-		ethtool_cmd_speed_set(cmd, SPEED_1000);
+		cmd->base.speed = SPEED_1000;
 		break;
 	default:
 		pr_info("%s: speed unknown\n", __func__);
-		ethtool_cmd_speed_set(cmd, SPEED_10);
+		cmd->base.speed = SPEED_10;
 		break;
 	}
 
-	cmd->supported = SUPPORTED_TP | SUPPORTED_Autoneg |
+	supported = SUPPORTED_TP | SUPPORTED_Autoneg |
 			SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full |
 			SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full |
 			SUPPORTED_1000baseT_Full;
-	cmd->advertising = cmd->supported;
+	advertising = supported;
 	if (card->link_mode & GELIC_LV1_ETHER_AUTO_NEG) {
-		cmd->autoneg = AUTONEG_ENABLE;
+		cmd->base.autoneg = AUTONEG_ENABLE;
 	} else {
-		cmd->autoneg = AUTONEG_DISABLE;
-		cmd->advertising &= ~ADVERTISED_Autoneg;
+		cmd->base.autoneg = AUTONEG_DISABLE;
+		advertising &= ~ADVERTISED_Autoneg;
 	}
-	cmd->port = PORT_TP;
+	cmd->base.port = PORT_TP;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 
 	return 0;
 }
 
-static int gelic_ether_set_settings(struct net_device *netdev,
-				    struct ethtool_cmd *cmd)
+static int
+gelic_ether_set_link_ksettings(struct net_device *netdev,
+			       const struct ethtool_link_ksettings *cmd)
 {
 	struct gelic_card *card = netdev_card(netdev);
 	u64 mode;
 	int ret;
 
-	if (cmd->autoneg == AUTONEG_ENABLE) {
+	if (cmd->base.autoneg == AUTONEG_ENABLE) {
 		mode = GELIC_LV1_ETHER_AUTO_NEG;
 	} else {
-		switch (cmd->speed) {
+		switch (cmd->base.speed) {
 		case SPEED_10:
 			mode = GELIC_LV1_ETHER_SPEED_10;
 			break;
@@ -1273,9 +1280,9 @@ static int gelic_ether_set_settings(struct net_device *netdev,
 		default:
 			return -EINVAL;
 		}
-		if (cmd->duplex == DUPLEX_FULL)
+		if (cmd->base.duplex == DUPLEX_FULL) {
 			mode |= GELIC_LV1_ETHER_FULL_DUPLEX;
-		else if (cmd->speed == SPEED_1000) {
+		} else if (cmd->base.speed == SPEED_1000) {
 			pr_info("1000 half duplex is not supported.\n");
 			return -EINVAL;
 		}
@@ -1370,11 +1377,11 @@ done:
 
 static const struct ethtool_ops gelic_ether_ethtool_ops = {
 	.get_drvinfo	= gelic_net_get_drvinfo,
-	.get_settings	= gelic_ether_get_settings,
-	.set_settings	= gelic_ether_set_settings,
 	.get_link	= ethtool_op_get_link,
 	.get_wol	= gelic_net_get_wol,
 	.set_wol	= gelic_net_set_wol,
+	.get_link_ksettings = gelic_ether_get_link_ksettings,
+	.set_link_ksettings = gelic_ether_set_link_ksettings,
 };
 
 /**
diff --git a/drivers/net/ethernet/toshiba/spider_net_ethtool.c b/drivers/net/ethernet/toshiba/spider_net_ethtool.c
index ffe519382e11..16bd036d0682 100644
--- a/drivers/net/ethernet/toshiba/spider_net_ethtool.c
+++ b/drivers/net/ethernet/toshiba/spider_net_ethtool.c
@@ -47,19 +47,23 @@ static struct {
 };
 
 static int
-spider_net_ethtool_get_settings(struct net_device *netdev,
-			       struct ethtool_cmd *cmd)
+spider_net_ethtool_get_link_ksettings(struct net_device *netdev,
+				      struct ethtool_link_ksettings *cmd)
 {
 	struct spider_net_card *card;
 	card = netdev_priv(netdev);
 
-	cmd->supported   = (SUPPORTED_1000baseT_Full |
-			     SUPPORTED_FIBRE);
-	cmd->advertising = (ADVERTISED_1000baseT_Full |
-			     ADVERTISED_FIBRE);
-	cmd->port = PORT_FIBRE;
-	ethtool_cmd_speed_set(cmd, card->phy.speed);
-	cmd->duplex = DUPLEX_FULL;
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+
+	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE);
+
+	cmd->base.port = PORT_FIBRE;
+	cmd->base.speed = card->phy.speed;
+	cmd->base.duplex = DUPLEX_FULL;
 
 	return 0;
 }
@@ -166,7 +170,6 @@ static void spider_net_get_strings(struct net_device *netdev, u32 stringset,
 }
 
 const struct ethtool_ops spider_net_ethtool_ops = {
-	.get_settings		= spider_net_ethtool_get_settings,
 	.get_drvinfo		= spider_net_ethtool_get_drvinfo,
 	.get_wol		= spider_net_ethtool_get_wol,
 	.get_msglevel		= spider_net_ethtool_get_msglevel,
@@ -177,5 +180,6 @@ const struct ethtool_ops spider_net_ethtool_ops = {
 	.get_strings		= spider_net_get_strings,
 	.get_sset_count		= spider_net_get_sset_count,
 	.get_ethtool_stats	= spider_net_get_ethtool_stats,
+	.get_link_ksettings	= spider_net_ethtool_get_link_ksettings,
 };
 
diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c
index c5583991da4a..5ac6eaa9e785 100644
--- a/drivers/net/ethernet/tundra/tsi108_eth.c
+++ b/drivers/net/ethernet/tundra/tsi108_eth.c
@@ -1499,27 +1499,29 @@ static void tsi108_init_mac(struct net_device *dev)
 	TSI_WRITE(TSI108_EC_INTMASK, ~0);
 }
 
-static int tsi108_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int tsi108_get_link_ksettings(struct net_device *dev,
+				     struct ethtool_link_ksettings *cmd)
 {
 	struct tsi108_prv_data *data = netdev_priv(dev);
 	unsigned long flags;
 	int rc;
 
 	spin_lock_irqsave(&data->txlock, flags);
-	rc = mii_ethtool_gset(&data->mii_if, cmd);
+	rc = mii_ethtool_get_link_ksettings(&data->mii_if, cmd);
 	spin_unlock_irqrestore(&data->txlock, flags);
 
 	return rc;
 }
 
-static int tsi108_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int tsi108_set_link_ksettings(struct net_device *dev,
+				     const struct ethtool_link_ksettings *cmd)
 {
 	struct tsi108_prv_data *data = netdev_priv(dev);
 	unsigned long flags;
 	int rc;
 
 	spin_lock_irqsave(&data->txlock, flags);
-	rc = mii_ethtool_sset(&data->mii_if, cmd);
+	rc = mii_ethtool_set_link_ksettings(&data->mii_if, cmd);
 	spin_unlock_irqrestore(&data->txlock, flags);
 
 	return rc;
@@ -1535,8 +1537,8 @@ static int tsi108_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 
 static const struct ethtool_ops tsi108_ethtool_ops = {
 	.get_link 	= ethtool_op_get_link,
-	.get_settings	= tsi108_get_settings,
-	.set_settings	= tsi108_set_settings,
+	.get_link_ksettings	= tsi108_get_link_ksettings,
+	.set_link_ksettings	= tsi108_set_link_ksettings,
 };
 
 static const struct net_device_ops tsi108_netdev_ops = {
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index c068c58428f7..4cf41f779d0e 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -2303,25 +2303,27 @@ static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *i
 	strlcpy(info->bus_info, dev_name(hwdev), sizeof(info->bus_info));
 }
 
-static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int netdev_get_link_ksettings(struct net_device *dev,
+				     struct ethtool_link_ksettings *cmd)
 {
 	struct rhine_private *rp = netdev_priv(dev);
 	int rc;
 
 	mutex_lock(&rp->task_lock);
-	rc = mii_ethtool_gset(&rp->mii_if, cmd);
+	rc = mii_ethtool_get_link_ksettings(&rp->mii_if, cmd);
 	mutex_unlock(&rp->task_lock);
 
 	return rc;
 }
 
-static int netdev_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int netdev_set_link_ksettings(struct net_device *dev,
+				     const struct ethtool_link_ksettings *cmd)
 {
 	struct rhine_private *rp = netdev_priv(dev);
 	int rc;
 
 	mutex_lock(&rp->task_lock);
-	rc = mii_ethtool_sset(&rp->mii_if, cmd);
+	rc = mii_ethtool_set_link_ksettings(&rp->mii_if, cmd);
 	rhine_set_carrier(&rp->mii_if);
 	mutex_unlock(&rp->task_lock);
 
@@ -2391,14 +2393,14 @@ static int rhine_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 
 static const struct ethtool_ops netdev_ethtool_ops = {
 	.get_drvinfo		= netdev_get_drvinfo,
-	.get_settings		= netdev_get_settings,
-	.set_settings		= netdev_set_settings,
 	.nway_reset		= netdev_nway_reset,
 	.get_link		= netdev_get_link,
 	.get_msglevel		= netdev_get_msglevel,
 	.set_msglevel		= netdev_set_msglevel,
 	.get_wol		= rhine_get_wol,
 	.set_wol		= rhine_set_wol,
+	.get_link_ksettings	= netdev_get_link_ksettings,
+	.set_link_ksettings	= netdev_set_link_ksettings,
 };
 
 static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index d088788b27a7..ef9538ee53d0 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -3291,15 +3291,17 @@ static void velocity_ethtool_down(struct net_device *dev)
 		velocity_set_power_state(vptr, PCI_D3hot);
 }
 
-static int velocity_get_settings(struct net_device *dev,
-				 struct ethtool_cmd *cmd)
+static int velocity_get_link_ksettings(struct net_device *dev,
+				       struct ethtool_link_ksettings *cmd)
 {
 	struct velocity_info *vptr = netdev_priv(dev);
 	struct mac_regs __iomem *regs = vptr->mac_regs;
 	u32 status;
+	u32 supported, advertising;
+
 	status = check_connection_type(vptr->mac_regs);
 
-	cmd->supported = SUPPORTED_TP |
+	supported = SUPPORTED_TP |
 			SUPPORTED_Autoneg |
 			SUPPORTED_10baseT_Half |
 			SUPPORTED_10baseT_Full |
@@ -3308,9 +3310,9 @@ static int velocity_get_settings(struct net_device *dev,
 			SUPPORTED_1000baseT_Half |
 			SUPPORTED_1000baseT_Full;
 
-	cmd->advertising = ADVERTISED_TP | ADVERTISED_Autoneg;
+	advertising = ADVERTISED_TP | ADVERTISED_Autoneg;
 	if (vptr->options.spd_dpx == SPD_DPX_AUTO) {
-		cmd->advertising |=
+		advertising |=
 			ADVERTISED_10baseT_Half |
 			ADVERTISED_10baseT_Full |
 			ADVERTISED_100baseT_Half |
@@ -3320,19 +3322,19 @@ static int velocity_get_settings(struct net_device *dev,
 	} else {
 		switch (vptr->options.spd_dpx) {
 		case SPD_DPX_1000_FULL:
-			cmd->advertising |= ADVERTISED_1000baseT_Full;
+			advertising |= ADVERTISED_1000baseT_Full;
 			break;
 		case SPD_DPX_100_HALF:
-			cmd->advertising |= ADVERTISED_100baseT_Half;
+			advertising |= ADVERTISED_100baseT_Half;
 			break;
 		case SPD_DPX_100_FULL:
-			cmd->advertising |= ADVERTISED_100baseT_Full;
+			advertising |= ADVERTISED_100baseT_Full;
 			break;
 		case SPD_DPX_10_HALF:
-			cmd->advertising |= ADVERTISED_10baseT_Half;
+			advertising |= ADVERTISED_10baseT_Half;
 			break;
 		case SPD_DPX_10_FULL:
-			cmd->advertising |= ADVERTISED_10baseT_Full;
+			advertising |= ADVERTISED_10baseT_Full;
 			break;
 		default:
 			break;
@@ -3340,30 +3342,35 @@ static int velocity_get_settings(struct net_device *dev,
 	}
 
 	if (status & VELOCITY_SPEED_1000)
-		ethtool_cmd_speed_set(cmd, SPEED_1000);
+		cmd->base.speed = SPEED_1000;
 	else if (status & VELOCITY_SPEED_100)
-		ethtool_cmd_speed_set(cmd, SPEED_100);
+		cmd->base.speed = SPEED_100;
 	else
-		ethtool_cmd_speed_set(cmd, SPEED_10);
+		cmd->base.speed = SPEED_10;
 
-	cmd->autoneg = (status & VELOCITY_AUTONEG_ENABLE) ? AUTONEG_ENABLE : AUTONEG_DISABLE;
-	cmd->port = PORT_TP;
-	cmd->transceiver = XCVR_INTERNAL;
-	cmd->phy_address = readb(&regs->MIIADR) & 0x1F;
+	cmd->base.autoneg = (status & VELOCITY_AUTONEG_ENABLE) ?
+		AUTONEG_ENABLE : AUTONEG_DISABLE;
+	cmd->base.port = PORT_TP;
+	cmd->base.phy_address = readb(&regs->MIIADR) & 0x1F;
 
 	if (status & VELOCITY_DUPLEX_FULL)
-		cmd->duplex = DUPLEX_FULL;
+		cmd->base.duplex = DUPLEX_FULL;
 	else
-		cmd->duplex = DUPLEX_HALF;
+		cmd->base.duplex = DUPLEX_HALF;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+						advertising);
 
 	return 0;
 }
 
-static int velocity_set_settings(struct net_device *dev,
-				 struct ethtool_cmd *cmd)
+static int velocity_set_link_ksettings(struct net_device *dev,
+				       const struct ethtool_link_ksettings *cmd)
 {
 	struct velocity_info *vptr = netdev_priv(dev);
-	u32 speed = ethtool_cmd_speed(cmd);
+	u32 speed = cmd->base.speed;
 	u32 curr_status;
 	u32 new_status = 0;
 	int ret = 0;
@@ -3371,11 +3378,12 @@ static int velocity_set_settings(struct net_device *dev,
 	curr_status = check_connection_type(vptr->mac_regs);
 	curr_status &= (~VELOCITY_LINK_FAIL);
 
-	new_status |= ((cmd->autoneg) ? VELOCITY_AUTONEG_ENABLE : 0);
+	new_status |= ((cmd->base.autoneg) ? VELOCITY_AUTONEG_ENABLE : 0);
 	new_status |= ((speed == SPEED_1000) ? VELOCITY_SPEED_1000 : 0);
 	new_status |= ((speed == SPEED_100) ? VELOCITY_SPEED_100 : 0);
 	new_status |= ((speed == SPEED_10) ? VELOCITY_SPEED_10 : 0);
-	new_status |= ((cmd->duplex == DUPLEX_FULL) ? VELOCITY_DUPLEX_FULL : 0);
+	new_status |= ((cmd->base.duplex == DUPLEX_FULL) ?
+		       VELOCITY_DUPLEX_FULL : 0);
 
 	if ((new_status & VELOCITY_AUTONEG_ENABLE) &&
 	    (new_status != (curr_status | VELOCITY_AUTONEG_ENABLE))) {
@@ -3644,8 +3652,6 @@ static void velocity_get_ethtool_stats(struct net_device *dev,
 }
 
 static const struct ethtool_ops velocity_ethtool_ops = {
-	.get_settings		= velocity_get_settings,
-	.set_settings		= velocity_set_settings,
 	.get_drvinfo		= velocity_get_drvinfo,
 	.get_wol		= velocity_ethtool_get_wol,
 	.set_wol		= velocity_ethtool_set_wol,
@@ -3658,7 +3664,9 @@ static const struct ethtool_ops velocity_ethtool_ops = {
 	.get_coalesce		= velocity_get_coalesce,
 	.set_coalesce		= velocity_set_coalesce,
 	.begin			= velocity_ethtool_up,
-	.complete		= velocity_ethtool_down
+	.complete		= velocity_ethtool_down,
+	.get_link_ksettings	= velocity_get_link_ksettings,
+	.set_link_ksettings	= velocity_set_link_ksettings,
 };
 
 #if defined(CONFIG_PM) && defined(CONFIG_INET)
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index b96e96919e31..33c595f4691d 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -301,7 +301,7 @@ static void axienet_set_mac_address(struct net_device *ndev,
 	if (address)
 		memcpy(ndev->dev_addr, address, ETH_ALEN);
 	if (!is_valid_ether_addr(ndev->dev_addr))
-		eth_random_addr(ndev->dev_addr);
+		eth_hw_addr_random(ndev);
 
 	/* Set up unicast MAC address filter set its mac address */
 	axienet_iow(lp, XAE_UAW0_OFFSET,
diff --git a/drivers/net/fjes/fjes_ethtool.c b/drivers/net/fjes/fjes_ethtool.c
index 6575f880f1be..7d101714c2ef 100644
--- a/drivers/net/fjes/fjes_ethtool.c
+++ b/drivers/net/fjes/fjes_ethtool.c
@@ -175,16 +175,15 @@ static void fjes_get_drvinfo(struct net_device *netdev,
 		 "platform:%s", plat_dev->name);
 }
 
-static int fjes_get_settings(struct net_device *netdev,
-			     struct ethtool_cmd *ecmd)
+static int fjes_get_link_ksettings(struct net_device *netdev,
+				   struct ethtool_link_ksettings *ecmd)
 {
-	ecmd->supported = 0;
-	ecmd->advertising = 0;
-	ecmd->duplex = DUPLEX_FULL;
-	ecmd->autoneg = AUTONEG_DISABLE;
-	ecmd->transceiver = XCVR_DUMMY1;
-	ecmd->port = PORT_NONE;
-	ethtool_cmd_speed_set(ecmd, 20000);	/* 20Gb/s */
+	ethtool_link_ksettings_zero_link_mode(ecmd, supported);
+	ethtool_link_ksettings_zero_link_mode(ecmd, advertising);
+	ecmd->base.duplex = DUPLEX_FULL;
+	ecmd->base.autoneg = AUTONEG_DISABLE;
+	ecmd->base.port = PORT_NONE;
+	ecmd->base.speed = 20000;	/* 20Gb/s */
 
 	return 0;
 }
@@ -296,7 +295,6 @@ static int fjes_get_dump_data(struct net_device *netdev,
 }
 
 static const struct ethtool_ops fjes_ethtool_ops = {
-		.get_settings		= fjes_get_settings,
 		.get_drvinfo		= fjes_get_drvinfo,
 		.get_ethtool_stats = fjes_get_ethtool_stats,
 		.get_strings      = fjes_get_strings,
@@ -306,6 +304,7 @@ static const struct ethtool_ops fjes_ethtool_ops = {
 		.set_dump		= fjes_set_dump,
 		.get_dump_flag		= fjes_get_dump_flag,
 		.get_dump_data		= fjes_get_dump_data,
+		.get_link_ksettings	= fjes_get_link_ksettings,
 };
 
 void fjes_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 89698741682f..4fea1b3dfbb4 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -56,7 +56,10 @@ struct pdp_ctx {
 	u16			af;
 
 	struct in_addr		ms_addr_ip4;
-	struct in_addr		sgsn_addr_ip4;
+	struct in_addr		peer_addr_ip4;
+
+	struct sock		*sk;
+	struct net_device       *dev;
 
 	atomic_t		tx_seq;
 	struct rcu_head		rcu_head;
@@ -66,11 +69,12 @@ struct pdp_ctx {
 struct gtp_dev {
 	struct list_head	list;
 
-	struct socket		*sock0;
-	struct socket		*sock1u;
+	struct sock		*sk0;
+	struct sock		*sk1u;
 
 	struct net_device	*dev;
 
+	unsigned int		role;
 	unsigned int		hash_size;
 	struct hlist_head	*tid_hash;
 	struct hlist_head	*addr_hash;
@@ -84,6 +88,8 @@ struct gtp_net {
 
 static u32 gtp_h_initval;
 
+static void pdp_context_delete(struct pdp_ctx *pctx);
+
 static inline u32 gtp0_hashfn(u64 tid)
 {
 	u32 *tid32 = (u32 *) &tid;
@@ -149,8 +155,8 @@ static struct pdp_ctx *ipv4_pdp_find(struct gtp_dev *gtp, __be32 ms_addr)
 	return NULL;
 }
 
-static bool gtp_check_src_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx,
-				  unsigned int hdrlen)
+static bool gtp_check_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx,
+				  unsigned int hdrlen, unsigned int role)
 {
 	struct iphdr *iph;
 
@@ -159,25 +165,62 @@ static bool gtp_check_src_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx,
 
 	iph = (struct iphdr *)(skb->data + hdrlen);
 
-	return iph->saddr == pctx->ms_addr_ip4.s_addr;
+	if (role == GTP_ROLE_SGSN)
+		return iph->daddr == pctx->ms_addr_ip4.s_addr;
+	else
+		return iph->saddr == pctx->ms_addr_ip4.s_addr;
 }
 
-/* Check if the inner IP source address in this packet is assigned to any
+/* Check if the inner IP address in this packet is assigned to any
  * existing mobile subscriber.
  */
-static bool gtp_check_src_ms(struct sk_buff *skb, struct pdp_ctx *pctx,
-			     unsigned int hdrlen)
+static bool gtp_check_ms(struct sk_buff *skb, struct pdp_ctx *pctx,
+			     unsigned int hdrlen, unsigned int role)
 {
 	switch (ntohs(skb->protocol)) {
 	case ETH_P_IP:
-		return gtp_check_src_ms_ipv4(skb, pctx, hdrlen);
+		return gtp_check_ms_ipv4(skb, pctx, hdrlen, role);
 	}
 	return false;
 }
 
+static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb,
+			unsigned int hdrlen, unsigned int role)
+{
+	struct pcpu_sw_netstats *stats;
+
+	if (!gtp_check_ms(skb, pctx, hdrlen, role)) {
+		netdev_dbg(pctx->dev, "No PDP ctx for this MS\n");
+		return 1;
+	}
+
+	/* Get rid of the GTP + UDP headers. */
+	if (iptunnel_pull_header(skb, hdrlen, skb->protocol,
+				 !net_eq(sock_net(pctx->sk), dev_net(pctx->dev))))
+		return -1;
+
+	netdev_dbg(pctx->dev, "forwarding packet from GGSN to uplink\n");
+
+	/* Now that the UDP and the GTP header have been removed, set up the
+	 * new network header. This is required by the upper layer to
+	 * calculate the transport header.
+	 */
+	skb_reset_network_header(skb);
+
+	skb->dev = pctx->dev;
+
+	stats = this_cpu_ptr(pctx->dev->tstats);
+	u64_stats_update_begin(&stats->syncp);
+	stats->rx_packets++;
+	stats->rx_bytes += skb->len;
+	u64_stats_update_end(&stats->syncp);
+
+	netif_rx(skb);
+	return 0;
+}
+
 /* 1 means pass up to the stack, -1 means drop and 0 means decapsulated. */
-static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb,
-			       bool xnet)
+static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb)
 {
 	unsigned int hdrlen = sizeof(struct udphdr) +
 			      sizeof(struct gtp0_header);
@@ -201,17 +244,10 @@ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb,
 		return 1;
 	}
 
-	if (!gtp_check_src_ms(skb, pctx, hdrlen)) {
-		netdev_dbg(gtp->dev, "No PDP ctx for this MS\n");
-		return 1;
-	}
-
-	/* Get rid of the GTP + UDP headers. */
-	return iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet);
+	return gtp_rx(pctx, skb, hdrlen, gtp->role);
 }
 
-static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb,
-				bool xnet)
+static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb)
 {
 	unsigned int hdrlen = sizeof(struct udphdr) +
 			      sizeof(struct gtp1_header);
@@ -250,37 +286,33 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb,
 		return 1;
 	}
 
-	if (!gtp_check_src_ms(skb, pctx, hdrlen)) {
-		netdev_dbg(gtp->dev, "No PDP ctx for this MS\n");
-		return 1;
-	}
-
-	/* Get rid of the GTP + UDP headers. */
-	return iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet);
+	return gtp_rx(pctx, skb, hdrlen, gtp->role);
 }
 
-static void gtp_encap_disable(struct gtp_dev *gtp)
+static void gtp_encap_destroy(struct sock *sk)
 {
-	if (gtp->sock0 && gtp->sock0->sk) {
-		udp_sk(gtp->sock0->sk)->encap_type = 0;
-		rcu_assign_sk_user_data(gtp->sock0->sk, NULL);
-	}
-	if (gtp->sock1u && gtp->sock1u->sk) {
-		udp_sk(gtp->sock1u->sk)->encap_type = 0;
-		rcu_assign_sk_user_data(gtp->sock1u->sk, NULL);
-	}
+	struct gtp_dev *gtp;
 
-	gtp->sock0 = NULL;
-	gtp->sock1u = NULL;
+	gtp = rcu_dereference_sk_user_data(sk);
+	if (gtp) {
+		udp_sk(sk)->encap_type = 0;
+		rcu_assign_sk_user_data(sk, NULL);
+		sock_put(sk);
+	}
 }
 
-static void gtp_encap_destroy(struct sock *sk)
+static void gtp_encap_disable_sock(struct sock *sk)
 {
-	struct gtp_dev *gtp;
+	if (!sk)
+		return;
 
-	gtp = rcu_dereference_sk_user_data(sk);
-	if (gtp)
-		gtp_encap_disable(gtp);
+	gtp_encap_destroy(sk);
+}
+
+static void gtp_encap_disable(struct gtp_dev *gtp)
+{
+	gtp_encap_disable_sock(gtp->sk0);
+	gtp_encap_disable_sock(gtp->sk1u);
 }
 
 /* UDP encapsulation receive handler. See net/ipv4/udp.c.
@@ -288,10 +320,8 @@ static void gtp_encap_destroy(struct sock *sk)
  */
 static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
-	struct pcpu_sw_netstats *stats;
 	struct gtp_dev *gtp;
-	bool xnet;
-	int ret;
+	int ret = 0;
 
 	gtp = rcu_dereference_sk_user_data(sk);
 	if (!gtp)
@@ -299,16 +329,14 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb)
 
 	netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk);
 
-	xnet = !net_eq(sock_net(sk), dev_net(gtp->dev));
-
 	switch (udp_sk(sk)->encap_type) {
 	case UDP_ENCAP_GTP0:
 		netdev_dbg(gtp->dev, "received GTP0 packet\n");
-		ret = gtp0_udp_encap_recv(gtp, skb, xnet);
+		ret = gtp0_udp_encap_recv(gtp, skb);
 		break;
 	case UDP_ENCAP_GTP1U:
 		netdev_dbg(gtp->dev, "received GTP1U packet\n");
-		ret = gtp1u_udp_encap_recv(gtp, skb, xnet);
+		ret = gtp1u_udp_encap_recv(gtp, skb);
 		break;
 	default:
 		ret = -1; /* Shouldn't happen. */
@@ -317,33 +345,17 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb)
 	switch (ret) {
 	case 1:
 		netdev_dbg(gtp->dev, "pass up to the process\n");
-		return 1;
+		break;
 	case 0:
-		netdev_dbg(gtp->dev, "forwarding packet from GGSN to uplink\n");
 		break;
 	case -1:
 		netdev_dbg(gtp->dev, "GTP packet has been dropped\n");
 		kfree_skb(skb);
-		return 0;
+		ret = 0;
+		break;
 	}
 
-	/* Now that the UDP and the GTP header have been removed, set up the
-	 * new network header. This is required by the upper layer to
-	 * calculate the transport header.
-	 */
-	skb_reset_network_header(skb);
-
-	skb->dev = gtp->dev;
-
-	stats = this_cpu_ptr(gtp->dev->tstats);
-	u64_stats_update_begin(&stats->syncp);
-	stats->rx_packets++;
-	stats->rx_bytes += skb->len;
-	u64_stats_update_end(&stats->syncp);
-
-	netif_rx(skb);
-
-	return 0;
+	return ret;
 }
 
 static int gtp_dev_init(struct net_device *dev)
@@ -367,8 +379,9 @@ static void gtp_dev_uninit(struct net_device *dev)
 	free_percpu(dev->tstats);
 }
 
-static struct rtable *ip4_route_output_gtp(struct net *net, struct flowi4 *fl4,
-					   const struct sock *sk, __be32 daddr)
+static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4,
+					   const struct sock *sk,
+					   __be32 daddr)
 {
 	memset(fl4, 0, sizeof(*fl4));
 	fl4->flowi4_oif		= sk->sk_bound_dev_if;
@@ -377,7 +390,7 @@ static struct rtable *ip4_route_output_gtp(struct net *net, struct flowi4 *fl4,
 	fl4->flowi4_tos		= RT_CONN_FLAGS(sk);
 	fl4->flowi4_proto	= sk->sk_protocol;
 
-	return ip_route_output_key(net, fl4);
+	return ip_route_output_key(sock_net(sk), fl4);
 }
 
 static inline void gtp0_push_header(struct sk_buff *skb, struct pdp_ctx *pctx)
@@ -466,7 +479,6 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
 	struct rtable *rt;
 	struct flowi4 fl4;
 	struct iphdr *iph;
-	struct sock *sk;
 	__be16 df;
 	int mtu;
 
@@ -474,7 +486,11 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
 	 * Prepend PDP header with TEI/TID from PDP ctx.
 	 */
 	iph = ip_hdr(skb);
-	pctx = ipv4_pdp_find(gtp, iph->daddr);
+	if (gtp->role == GTP_ROLE_SGSN)
+		pctx = ipv4_pdp_find(gtp, iph->saddr);
+	else
+		pctx = ipv4_pdp_find(gtp, iph->daddr);
+
 	if (!pctx) {
 		netdev_dbg(dev, "no PDP ctx found for %pI4, skip\n",
 			   &iph->daddr);
@@ -482,40 +498,17 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
 	}
 	netdev_dbg(dev, "found PDP context %p\n", pctx);
 
-	switch (pctx->gtp_version) {
-	case GTP_V0:
-		if (gtp->sock0)
-			sk = gtp->sock0->sk;
-		else
-			sk = NULL;
-		break;
-	case GTP_V1:
-		if (gtp->sock1u)
-			sk = gtp->sock1u->sk;
-		else
-			sk = NULL;
-		break;
-	default:
-		return -ENOENT;
-	}
-
-	if (!sk) {
-		netdev_dbg(dev, "no userspace socket is available, skip\n");
-		return -ENOENT;
-	}
-
-	rt = ip4_route_output_gtp(sock_net(sk), &fl4, gtp->sock0->sk,
-				  pctx->sgsn_addr_ip4.s_addr);
+	rt = ip4_route_output_gtp(&fl4, pctx->sk, pctx->peer_addr_ip4.s_addr);
 	if (IS_ERR(rt)) {
 		netdev_dbg(dev, "no route to SSGN %pI4\n",
-			   &pctx->sgsn_addr_ip4.s_addr);
+			   &pctx->peer_addr_ip4.s_addr);
 		dev->stats.tx_carrier_errors++;
 		goto err;
 	}
 
 	if (rt->dst.dev == dev) {
 		netdev_dbg(dev, "circular route to SSGN %pI4\n",
-			   &pctx->sgsn_addr_ip4.s_addr);
+			   &pctx->peer_addr_ip4.s_addr);
 		dev->stats.collisions++;
 		goto err_rt;
 	}
@@ -550,7 +543,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
 		goto err_rt;
 	}
 
-	gtp_set_pktinfo_ipv4(pktinfo, sk, iph, pctx, rt, &fl4, dev);
+	gtp_set_pktinfo_ipv4(pktinfo, pctx->sk, iph, pctx, rt, &fl4, dev);
 	gtp_push_header(skb, pktinfo);
 
 	return 0;
@@ -640,27 +633,23 @@ static void gtp_link_setup(struct net_device *dev)
 
 static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize);
 static void gtp_hashtable_free(struct gtp_dev *gtp);
-static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp,
-			    int fd_gtp0, int fd_gtp1);
+static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]);
 
 static int gtp_newlink(struct net *src_net, struct net_device *dev,
 			struct nlattr *tb[], struct nlattr *data[])
 {
-	int hashsize, err, fd0, fd1;
 	struct gtp_dev *gtp;
 	struct gtp_net *gn;
+	int hashsize, err;
 
-	if (!data[IFLA_GTP_FD0] || !data[IFLA_GTP_FD1])
+	if (!data[IFLA_GTP_FD0] && !data[IFLA_GTP_FD1])
 		return -EINVAL;
 
 	gtp = netdev_priv(dev);
 
-	fd0 = nla_get_u32(data[IFLA_GTP_FD0]);
-	fd1 = nla_get_u32(data[IFLA_GTP_FD1]);
-
-	err = gtp_encap_enable(dev, gtp, fd0, fd1);
+	err = gtp_encap_enable(gtp, data);
 	if (err < 0)
-		goto out_err;
+		return err;
 
 	if (!data[IFLA_GTP_PDP_HASHSIZE])
 		hashsize = 1024;
@@ -688,7 +677,6 @@ out_hashtable:
 	gtp_hashtable_free(gtp);
 out_encap:
 	gtp_encap_disable(gtp);
-out_err:
 	return err;
 }
 
@@ -706,6 +694,7 @@ static const struct nla_policy gtp_policy[IFLA_GTP_MAX + 1] = {
 	[IFLA_GTP_FD0]			= { .type = NLA_U32 },
 	[IFLA_GTP_FD1]			= { .type = NLA_U32 },
 	[IFLA_GTP_PDP_HASHSIZE]		= { .type = NLA_U32 },
+	[IFLA_GTP_ROLE]			= { .type = NLA_U32 },
 };
 
 static int gtp_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -747,21 +736,6 @@ static struct rtnl_link_ops gtp_link_ops __read_mostly = {
 	.fill_info	= gtp_fill_info,
 };
 
-static struct net *gtp_genl_get_net(struct net *src_net, struct nlattr *tb[])
-{
-	struct net *net;
-
-	/* Examine the link attributes and figure out which network namespace
-	 * we are talking about.
-	 */
-	if (tb[GTPA_NET_NS_FD])
-		net = get_net_ns_by_fd(nla_get_u32(tb[GTPA_NET_NS_FD]));
-	else
-		net = get_net(src_net);
-
-	return net;
-}
-
 static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize)
 {
 	int i;
@@ -791,93 +765,127 @@ static void gtp_hashtable_free(struct gtp_dev *gtp)
 	struct pdp_ctx *pctx;
 	int i;
 
-	for (i = 0; i < gtp->hash_size; i++) {
-		hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i], hlist_tid) {
-			hlist_del_rcu(&pctx->hlist_tid);
-			hlist_del_rcu(&pctx->hlist_addr);
-			kfree_rcu(pctx, rcu_head);
-		}
-	}
+	for (i = 0; i < gtp->hash_size; i++)
+		hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i], hlist_tid)
+			pdp_context_delete(pctx);
+
 	synchronize_rcu();
 	kfree(gtp->addr_hash);
 	kfree(gtp->tid_hash);
 }
 
-static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp,
-			    int fd_gtp0, int fd_gtp1)
+static struct sock *gtp_encap_enable_socket(int fd, int type,
+					    struct gtp_dev *gtp)
 {
 	struct udp_tunnel_sock_cfg tuncfg = {NULL};
-	struct socket *sock0, *sock1u;
+	struct socket *sock;
+	struct sock *sk;
 	int err;
 
-	netdev_dbg(dev, "enable gtp on %d, %d\n", fd_gtp0, fd_gtp1);
-
-	sock0 = sockfd_lookup(fd_gtp0, &err);
-	if (sock0 == NULL) {
-		netdev_dbg(dev, "socket fd=%d not found (gtp0)\n", fd_gtp0);
-		return -ENOENT;
-	}
+	pr_debug("enable gtp on %d, %d\n", fd, type);
 
-	if (sock0->sk->sk_protocol != IPPROTO_UDP) {
-		netdev_dbg(dev, "socket fd=%d not UDP\n", fd_gtp0);
-		err = -EINVAL;
-		goto err1;
+	sock = sockfd_lookup(fd, &err);
+	if (!sock) {
+		pr_debug("gtp socket fd=%d not found\n", fd);
+		return NULL;
 	}
 
-	sock1u = sockfd_lookup(fd_gtp1, &err);
-	if (sock1u == NULL) {
-		netdev_dbg(dev, "socket fd=%d not found (gtp1u)\n", fd_gtp1);
-		err = -ENOENT;
-		goto err1;
+	if (sock->sk->sk_protocol != IPPROTO_UDP) {
+		pr_debug("socket fd=%d not UDP\n", fd);
+		sk = ERR_PTR(-EINVAL);
+		goto out_sock;
 	}
 
-	if (sock1u->sk->sk_protocol != IPPROTO_UDP) {
-		netdev_dbg(dev, "socket fd=%d not UDP\n", fd_gtp1);
-		err = -EINVAL;
-		goto err2;
+	if (rcu_dereference_sk_user_data(sock->sk)) {
+		sk = ERR_PTR(-EBUSY);
+		goto out_sock;
 	}
 
-	netdev_dbg(dev, "enable gtp on %p, %p\n", sock0, sock1u);
-
-	gtp->sock0 = sock0;
-	gtp->sock1u = sock1u;
+	sk = sock->sk;
+	sock_hold(sk);
 
 	tuncfg.sk_user_data = gtp;
+	tuncfg.encap_type = type;
 	tuncfg.encap_rcv = gtp_encap_recv;
 	tuncfg.encap_destroy = gtp_encap_destroy;
 
-	tuncfg.encap_type = UDP_ENCAP_GTP0;
-	setup_udp_tunnel_sock(sock_net(gtp->sock0->sk), gtp->sock0, &tuncfg);
-
-	tuncfg.encap_type = UDP_ENCAP_GTP1U;
-	setup_udp_tunnel_sock(sock_net(gtp->sock1u->sk), gtp->sock1u, &tuncfg);
+	setup_udp_tunnel_sock(sock_net(sock->sk), sock, &tuncfg);
 
-	err = 0;
-err2:
-	sockfd_put(sock1u);
-err1:
-	sockfd_put(sock0);
-	return err;
+out_sock:
+	sockfd_put(sock);
+	return sk;
 }
 
-static struct net_device *gtp_find_dev(struct net *net, int ifindex)
+static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[])
 {
-	struct gtp_net *gn = net_generic(net, gtp_net_id);
-	struct gtp_dev *gtp;
+	struct sock *sk1u = NULL;
+	struct sock *sk0 = NULL;
+	unsigned int role = GTP_ROLE_GGSN;
 
-	list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) {
-		if (ifindex == gtp->dev->ifindex)
-			return gtp->dev;
+	if (data[IFLA_GTP_FD0]) {
+		u32 fd0 = nla_get_u32(data[IFLA_GTP_FD0]);
+
+		sk0 = gtp_encap_enable_socket(fd0, UDP_ENCAP_GTP0, gtp);
+		if (IS_ERR(sk0))
+			return PTR_ERR(sk0);
 	}
-	return NULL;
+
+	if (data[IFLA_GTP_FD1]) {
+		u32 fd1 = nla_get_u32(data[IFLA_GTP_FD1]);
+
+		sk1u = gtp_encap_enable_socket(fd1, UDP_ENCAP_GTP1U, gtp);
+		if (IS_ERR(sk1u)) {
+			if (sk0)
+				gtp_encap_disable_sock(sk0);
+			return PTR_ERR(sk1u);
+		}
+	}
+
+	if (data[IFLA_GTP_ROLE]) {
+		role = nla_get_u32(data[IFLA_GTP_ROLE]);
+		if (role > GTP_ROLE_SGSN)
+			return -EINVAL;
+	}
+
+	gtp->sk0 = sk0;
+	gtp->sk1u = sk1u;
+	gtp->role = role;
+
+	return 0;
+}
+
+static struct gtp_dev *gtp_find_dev(struct net *src_net, struct nlattr *nla[])
+{
+	struct gtp_dev *gtp = NULL;
+	struct net_device *dev;
+	struct net *net;
+
+	/* Examine the link attributes and figure out which network namespace
+	 * we are talking about.
+	 */
+	if (nla[GTPA_NET_NS_FD])
+		net = get_net_ns_by_fd(nla_get_u32(nla[GTPA_NET_NS_FD]));
+	else
+		net = get_net(src_net);
+
+	if (IS_ERR(net))
+		return NULL;
+
+	/* Check if there's an existing gtpX device to configure */
+	dev = dev_get_by_index_rcu(net, nla_get_u32(nla[GTPA_LINK]));
+	if (dev->netdev_ops == &gtp_netdev_ops)
+		gtp = netdev_priv(dev);
+
+	put_net(net);
+	return gtp;
 }
 
 static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
 {
 	pctx->gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]);
 	pctx->af = AF_INET;
-	pctx->sgsn_addr_ip4.s_addr =
-		nla_get_be32(info->attrs[GTPA_SGSN_ADDRESS]);
+	pctx->peer_addr_ip4.s_addr =
+		nla_get_be32(info->attrs[GTPA_PEER_ADDRESS]);
 	pctx->ms_addr_ip4.s_addr =
 		nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
 
@@ -899,9 +907,10 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
 	}
 }
 
-static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info)
+static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
+			struct genl_info *info)
 {
-	struct gtp_dev *gtp = netdev_priv(dev);
+	struct net_device *dev = gtp->dev;
 	u32 hash_ms, hash_tid = 0;
 	struct pdp_ctx *pctx;
 	bool found = false;
@@ -940,6 +949,9 @@ static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info)
 	if (pctx == NULL)
 		return -ENOMEM;
 
+	sock_hold(sk);
+	pctx->sk = sk;
+	pctx->dev = gtp->dev;
 	ipv4_pdp_fill(pctx, info);
 	atomic_set(&pctx->tx_seq, 0);
 
@@ -963,31 +975,50 @@ static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info)
 	switch (pctx->gtp_version) {
 	case GTP_V0:
 		netdev_dbg(dev, "GTPv0-U: new PDP ctx id=%llx ssgn=%pI4 ms=%pI4 (pdp=%p)\n",
-			   pctx->u.v0.tid, &pctx->sgsn_addr_ip4,
+			   pctx->u.v0.tid, &pctx->peer_addr_ip4,
 			   &pctx->ms_addr_ip4, pctx);
 		break;
 	case GTP_V1:
 		netdev_dbg(dev, "GTPv1-U: new PDP ctx id=%x/%x ssgn=%pI4 ms=%pI4 (pdp=%p)\n",
 			   pctx->u.v1.i_tei, pctx->u.v1.o_tei,
-			   &pctx->sgsn_addr_ip4, &pctx->ms_addr_ip4, pctx);
+			   &pctx->peer_addr_ip4, &pctx->ms_addr_ip4, pctx);
 		break;
 	}
 
 	return 0;
 }
 
+static void pdp_context_free(struct rcu_head *head)
+{
+	struct pdp_ctx *pctx = container_of(head, struct pdp_ctx, rcu_head);
+
+	sock_put(pctx->sk);
+	kfree(pctx);
+}
+
+static void pdp_context_delete(struct pdp_ctx *pctx)
+{
+	hlist_del_rcu(&pctx->hlist_tid);
+	hlist_del_rcu(&pctx->hlist_addr);
+	call_rcu(&pctx->rcu_head, pdp_context_free);
+}
+
 static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
 {
-	struct net_device *dev;
-	struct net *net;
+	unsigned int version;
+	struct gtp_dev *gtp;
+	struct sock *sk;
+	int err;
 
 	if (!info->attrs[GTPA_VERSION] ||
 	    !info->attrs[GTPA_LINK] ||
-	    !info->attrs[GTPA_SGSN_ADDRESS] ||
+	    !info->attrs[GTPA_PEER_ADDRESS] ||
 	    !info->attrs[GTPA_MS_ADDRESS])
 		return -EINVAL;
 
-	switch (nla_get_u32(info->attrs[GTPA_VERSION])) {
+	version = nla_get_u32(info->attrs[GTPA_VERSION]);
+
+	switch (version) {
 	case GTP_V0:
 		if (!info->attrs[GTPA_TID] ||
 		    !info->attrs[GTPA_FLOW])
@@ -1003,77 +1034,101 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 	}
 
-	net = gtp_genl_get_net(sock_net(skb->sk), info->attrs);
-	if (IS_ERR(net))
-		return PTR_ERR(net);
+	rcu_read_lock();
 
-	/* Check if there's an existing gtpX device to configure */
-	dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK]));
-	if (dev == NULL) {
-		put_net(net);
-		return -ENODEV;
+	gtp = gtp_find_dev(sock_net(skb->sk), info->attrs);
+	if (!gtp) {
+		err = -ENODEV;
+		goto out_unlock;
 	}
-	put_net(net);
 
-	return ipv4_pdp_add(dev, info);
+	if (version == GTP_V0)
+		sk = gtp->sk0;
+	else if (version == GTP_V1)
+		sk = gtp->sk1u;
+	else
+		sk = NULL;
+
+	if (!sk) {
+		err = -ENODEV;
+		goto out_unlock;
+	}
+
+	err = ipv4_pdp_add(gtp, sk, info);
+
+out_unlock:
+	rcu_read_unlock();
+	return err;
 }
 
-static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info)
+static struct pdp_ctx *gtp_find_pdp_by_link(struct net *net,
+					    struct nlattr *nla[])
 {
-	struct net_device *dev;
-	struct pdp_ctx *pctx;
 	struct gtp_dev *gtp;
-	struct net *net;
 
-	if (!info->attrs[GTPA_VERSION] ||
-	    !info->attrs[GTPA_LINK])
-		return -EINVAL;
+	gtp = gtp_find_dev(net, nla);
+	if (!gtp)
+		return ERR_PTR(-ENODEV);
 
-	net = gtp_genl_get_net(sock_net(skb->sk), info->attrs);
-	if (IS_ERR(net))
-		return PTR_ERR(net);
+	if (nla[GTPA_MS_ADDRESS]) {
+		__be32 ip = nla_get_be32(nla[GTPA_MS_ADDRESS]);
 
-	/* Check if there's an existing gtpX device to configure */
-	dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK]));
-	if (dev == NULL) {
-		put_net(net);
-		return -ENODEV;
+		return ipv4_pdp_find(gtp, ip);
+	} else if (nla[GTPA_VERSION]) {
+		u32 gtp_version = nla_get_u32(nla[GTPA_VERSION]);
+
+		if (gtp_version == GTP_V0 && nla[GTPA_TID])
+			return gtp0_pdp_find(gtp, nla_get_u64(nla[GTPA_TID]));
+		else if (gtp_version == GTP_V1 && nla[GTPA_I_TEI])
+			return gtp1_pdp_find(gtp, nla_get_u32(nla[GTPA_I_TEI]));
 	}
-	put_net(net);
 
-	gtp = netdev_priv(dev);
+	return ERR_PTR(-EINVAL);
+}
 
-	switch (nla_get_u32(info->attrs[GTPA_VERSION])) {
-	case GTP_V0:
-		if (!info->attrs[GTPA_TID])
-			return -EINVAL;
-		pctx = gtp0_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_TID]));
-		break;
-	case GTP_V1:
-		if (!info->attrs[GTPA_I_TEI])
-			return -EINVAL;
-		pctx = gtp1_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_I_TEI]));
-		break;
+static struct pdp_ctx *gtp_find_pdp(struct net *net, struct nlattr *nla[])
+{
+	struct pdp_ctx *pctx;
 
-	default:
+	if (nla[GTPA_LINK])
+		pctx = gtp_find_pdp_by_link(net, nla);
+	else
+		pctx = ERR_PTR(-EINVAL);
+
+	if (!pctx)
+		pctx = ERR_PTR(-ENOENT);
+
+	return pctx;
+}
+
+static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info)
+{
+	struct pdp_ctx *pctx;
+	int err = 0;
+
+	if (!info->attrs[GTPA_VERSION])
 		return -EINVAL;
-	}
 
-	if (pctx == NULL)
-		return -ENOENT;
+	rcu_read_lock();
+
+	pctx = gtp_find_pdp(sock_net(skb->sk), info->attrs);
+	if (IS_ERR(pctx)) {
+		err = PTR_ERR(pctx);
+		goto out_unlock;
+	}
 
 	if (pctx->gtp_version == GTP_V0)
-		netdev_dbg(dev, "GTPv0-U: deleting tunnel id = %llx (pdp %p)\n",
+		netdev_dbg(pctx->dev, "GTPv0-U: deleting tunnel id = %llx (pdp %p)\n",
 			   pctx->u.v0.tid, pctx);
 	else if (pctx->gtp_version == GTP_V1)
-		netdev_dbg(dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n",
+		netdev_dbg(pctx->dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n",
 			   pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx);
 
-	hlist_del_rcu(&pctx->hlist_tid);
-	hlist_del_rcu(&pctx->hlist_addr);
-	kfree_rcu(pctx, rcu_head);
+	pdp_context_delete(pctx);
 
-	return 0;
+out_unlock:
+	rcu_read_unlock();
+	return err;
 }
 
 static struct genl_family gtp_genl_family;
@@ -1089,7 +1144,7 @@ static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq,
 		goto nlmsg_failure;
 
 	if (nla_put_u32(skb, GTPA_VERSION, pctx->gtp_version) ||
-	    nla_put_be32(skb, GTPA_SGSN_ADDRESS, pctx->sgsn_addr_ip4.s_addr) ||
+	    nla_put_be32(skb, GTPA_PEER_ADDRESS, pctx->peer_addr_ip4.s_addr) ||
 	    nla_put_be32(skb, GTPA_MS_ADDRESS, pctx->ms_addr_ip4.s_addr))
 		goto nla_put_failure;
 
@@ -1117,59 +1172,17 @@ nla_put_failure:
 static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info)
 {
 	struct pdp_ctx *pctx = NULL;
-	struct net_device *dev;
 	struct sk_buff *skb2;
-	struct gtp_dev *gtp;
-	u32 gtp_version;
-	struct net *net;
 	int err;
 
-	if (!info->attrs[GTPA_VERSION] ||
-	    !info->attrs[GTPA_LINK])
-		return -EINVAL;
-
-	gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]);
-	switch (gtp_version) {
-	case GTP_V0:
-	case GTP_V1:
-		break;
-	default:
+	if (!info->attrs[GTPA_VERSION])
 		return -EINVAL;
-	}
-
-	net = gtp_genl_get_net(sock_net(skb->sk), info->attrs);
-	if (IS_ERR(net))
-		return PTR_ERR(net);
-
-	/* Check if there's an existing gtpX device to configure */
-	dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK]));
-	if (dev == NULL) {
-		put_net(net);
-		return -ENODEV;
-	}
-	put_net(net);
-
-	gtp = netdev_priv(dev);
 
 	rcu_read_lock();
-	if (gtp_version == GTP_V0 &&
-	    info->attrs[GTPA_TID]) {
-		u64 tid = nla_get_u64(info->attrs[GTPA_TID]);
-
-		pctx = gtp0_pdp_find(gtp, tid);
-	} else if (gtp_version == GTP_V1 &&
-		 info->attrs[GTPA_I_TEI]) {
-		u32 tid = nla_get_u32(info->attrs[GTPA_I_TEI]);
-
-		pctx = gtp1_pdp_find(gtp, tid);
-	} else if (info->attrs[GTPA_MS_ADDRESS]) {
-		__be32 ip = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
-
-		pctx = ipv4_pdp_find(gtp, ip);
-	}
 
-	if (pctx == NULL) {
-		err = -ENOENT;
+	pctx = gtp_find_pdp(sock_net(skb->sk), info->attrs);
+	if (IS_ERR(pctx)) {
+		err = PTR_ERR(pctx);
 		goto err_unlock;
 	}
 
@@ -1242,7 +1255,7 @@ static struct nla_policy gtp_genl_policy[GTPA_MAX + 1] = {
 	[GTPA_LINK]		= { .type = NLA_U32, },
 	[GTPA_VERSION]		= { .type = NLA_U32, },
 	[GTPA_TID]		= { .type = NLA_U64, },
-	[GTPA_SGSN_ADDRESS]	= { .type = NLA_U32, },
+	[GTPA_PEER_ADDRESS]	= { .type = NLA_U32, },
 	[GTPA_MS_ADDRESS]	= { .type = NLA_U32, },
 	[GTPA_FLOW]		= { .type = NLA_U16, },
 	[GTPA_NET_NS_FD]	= { .type = NLA_U32, },
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index f9f3dba7a588..4747ad48b3cc 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -196,6 +196,7 @@ int netvsc_recv_callback(struct net_device *net,
 			 const struct ndis_tcp_ip_checksum_info *csum_info,
 			 const struct ndis_pkt_8021q_info *vlan);
 void netvsc_channel_cb(void *context);
+int netvsc_poll(struct napi_struct *napi, int budget);
 int rndis_filter_open(struct netvsc_device *nvdev);
 int rndis_filter_close(struct netvsc_device *nvdev);
 int rndis_filter_device_add(struct hv_device *dev,
@@ -685,7 +686,7 @@ struct net_device_context {
 	/* point back to our device context */
 	struct hv_device *device_ctx;
 	/* netvsc_device */
-	struct netvsc_device *nvdev;
+	struct netvsc_device __rcu *nvdev;
 	/* reconfigure work */
 	struct delayed_work dwork;
 	/* last reconfig time */
@@ -707,9 +708,6 @@ struct net_device_context {
 	u32 speed;
 	struct netvsc_ethtool_stats eth_stats;
 
-	/* the device is going away */
-	bool start_remove;
-
 	/* State to manage the associated VF interface. */
 	struct net_device __rcu *vf_netdev;
 
@@ -722,6 +720,8 @@ struct net_device_context {
 /* Per channel data */
 struct netvsc_channel {
 	struct vmbus_channel *channel;
+	const struct vmpacket_descriptor *desc;
+	struct napi_struct napi;
 	struct multi_send_data msd;
 	struct multi_recv_comp mrc;
 	atomic_t queue_sends;
@@ -761,8 +761,8 @@ struct netvsc_device {
 
 	u32 max_chn;
 	u32 num_chn;
-	spinlock_t sc_lock; /* Protects num_sc_offered variable */
-	u32 num_sc_offered;
+
+	refcount_t sc_offered;
 
 	/* Holds rndis device info */
 	void *extension;
@@ -777,6 +777,8 @@ struct netvsc_device {
 	atomic_t open_cnt;
 
 	struct netvsc_channel chan_table[VRSS_CHANNEL_MAX];
+
+	struct rcu_head rcu;
 };
 
 static inline struct netvsc_device *
@@ -1425,9 +1427,6 @@ struct rndis_message {
 	((void *) rndis_msg)
 
 
-#define __struct_bcount(x)
-
-
 
 #define RNDIS_HEADER_SIZE	(sizeof(struct rndis_message) - \
 				 sizeof(union rndis_message_container))
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 8dd0b8770328..e998e2f7a619 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -80,8 +80,10 @@ static struct netvsc_device *alloc_net_device(void)
 	return net_device;
 }
 
-static void free_netvsc_device(struct netvsc_device *nvdev)
+static void free_netvsc_device(struct rcu_head *head)
 {
+	struct netvsc_device *nvdev
+		= container_of(head, struct netvsc_device, rcu);
 	int i;
 
 	for (i = 0; i < VRSS_CHANNEL_MAX; i++)
@@ -90,14 +92,9 @@ static void free_netvsc_device(struct netvsc_device *nvdev)
 	kfree(nvdev);
 }
 
-
-static inline bool netvsc_channel_idle(const struct netvsc_device *net_device,
-				       u16 q_idx)
+static void free_netvsc_device_rcu(struct netvsc_device *nvdev)
 {
-	const struct netvsc_channel *nvchan = &net_device->chan_table[q_idx];
-
-	return atomic_read(&net_device->num_outstanding_recvs) == 0 &&
-		atomic_read(&nvchan->queue_sends) == 0;
+	call_rcu(&nvdev->rcu, free_netvsc_device);
 }
 
 static struct netvsc_device *get_outbound_net_device(struct hv_device *device)
@@ -556,10 +553,11 @@ void netvsc_device_remove(struct hv_device *device)
 	struct net_device *ndev = hv_get_drvdata(device);
 	struct net_device_context *net_device_ctx = netdev_priv(ndev);
 	struct netvsc_device *net_device = net_device_ctx->nvdev;
+	int i;
 
 	netvsc_disconnect_vsp(device);
 
-	net_device_ctx->nvdev = NULL;
+	RCU_INIT_POINTER(net_device_ctx->nvdev, NULL);
 
 	/*
 	 * At this point, no one should be accessing net_device
@@ -570,8 +568,11 @@ void netvsc_device_remove(struct hv_device *device)
 	/* Now, we can close the channel safely */
 	vmbus_close(device->channel);
 
+	for (i = 0; i < net_device->num_chn; i++)
+		napi_disable(&net_device->chan_table[i].napi);
+
 	/* Release all resources */
-	free_netvsc_device(net_device);
+	free_netvsc_device_rcu(net_device);
 }
 
 #define RING_AVAIL_PERCENT_HIWATER 20
@@ -600,11 +601,10 @@ static inline void netvsc_free_send_slot(struct netvsc_device *net_device,
 static void netvsc_send_tx_complete(struct netvsc_device *net_device,
 				    struct vmbus_channel *incoming_channel,
 				    struct hv_device *device,
-				    struct vmpacket_descriptor *packet)
+				    const struct vmpacket_descriptor *desc)
 {
-	struct sk_buff *skb = (struct sk_buff *)(unsigned long)packet->trans_id;
+	struct sk_buff *skb = (struct sk_buff *)(unsigned long)desc->trans_id;
 	struct net_device *ndev = hv_get_drvdata(device);
-	struct net_device_context *net_device_ctx = netdev_priv(ndev);
 	struct vmbus_channel *channel = device->channel;
 	u16 q_idx = 0;
 	int queue_sends;
@@ -638,7 +638,6 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device,
 		wake_up(&net_device->wait_drain);
 
 	if (netif_tx_queue_stopped(netdev_get_tx_queue(ndev, q_idx)) &&
-	    !net_device_ctx->start_remove &&
 	    (hv_ringbuf_avail_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER ||
 	     queue_sends < 1))
 		netif_tx_wake_queue(netdev_get_tx_queue(ndev, q_idx));
@@ -647,14 +646,11 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device,
 static void netvsc_send_completion(struct netvsc_device *net_device,
 				   struct vmbus_channel *incoming_channel,
 				   struct hv_device *device,
-				   struct vmpacket_descriptor *packet)
+				   const struct vmpacket_descriptor *desc)
 {
-	struct nvsp_message *nvsp_packet;
+	struct nvsp_message *nvsp_packet = hv_pkt_data(desc);
 	struct net_device *ndev = hv_get_drvdata(device);
 
-	nvsp_packet = (struct nvsp_message *)((unsigned long)packet +
-					      (packet->offset8 << 3));
-
 	switch (nvsp_packet->hdr.msg_type) {
 	case NVSP_MSG_TYPE_INIT_COMPLETE:
 	case NVSP_MSG1_TYPE_SEND_RECV_BUF_COMPLETE:
@@ -668,7 +664,7 @@ static void netvsc_send_completion(struct netvsc_device *net_device,
 
 	case NVSP_MSG1_TYPE_SEND_RNDIS_PKT_COMPLETE:
 		netvsc_send_tx_complete(net_device, incoming_channel,
-					device, packet);
+					device, desc);
 		break;
 
 	default:
@@ -710,8 +706,7 @@ static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 		packet->page_buf_cnt;
 
 	/* Add padding */
-	if (skb && skb->xmit_more && remain &&
-	    !packet->cp_partial) {
+	if (skb->xmit_more && remain && !packet->cp_partial) {
 		padding = net_device->pkt_align - remain;
 		rndis_msg->msg_len += padding;
 		packet->total_data_buflen += padding;
@@ -869,9 +864,7 @@ int netvsc_send(struct hv_device *device,
 	if (msdp->pkt)
 		msd_len = msdp->pkt->total_data_buflen;
 
-	try_batch = (skb != NULL) && msd_len > 0 && msdp->count <
-		    net_device->max_pkt;
-
+	try_batch =  msd_len > 0 && msdp->count < net_device->max_pkt;
 	if (try_batch && msd_len + pktlen + net_device->pkt_align <
 	    net_device->send_section_size) {
 		section_index = msdp->pkt->send_buf_index;
@@ -881,7 +874,7 @@ int netvsc_send(struct hv_device *device,
 		section_index = msdp->pkt->send_buf_index;
 		packet->cp_partial = true;
 
-	} else if ((skb != NULL) && pktlen + net_device->pkt_align <
+	} else if (pktlen + net_device->pkt_align <
 		   net_device->send_section_size) {
 		section_index = netvsc_get_next_send_section(net_device);
 		if (section_index != NETVSC_INVALID_INDEX) {
@@ -1066,28 +1059,29 @@ static inline struct recv_comp_data *get_recv_comp_slot(
 	return rcd;
 }
 
-static void netvsc_receive(struct net_device *ndev,
+static int netvsc_receive(struct net_device *ndev,
 		   struct netvsc_device *net_device,
 		   struct net_device_context *net_device_ctx,
 		   struct hv_device *device,
 		   struct vmbus_channel *channel,
-		   struct vmtransfer_page_packet_header *vmxferpage_packet,
+		   const struct vmpacket_descriptor *desc,
 		   struct nvsp_message *nvsp)
 {
+	const struct vmtransfer_page_packet_header *vmxferpage_packet
+		= container_of(desc, const struct vmtransfer_page_packet_header, d);
+	u16 q_idx = channel->offermsg.offer.sub_channel_index;
 	char *recv_buf = net_device->recv_buf;
 	u32 status = NVSP_STAT_SUCCESS;
 	int i;
 	int count = 0;
 	int ret;
-	struct recv_comp_data *rcd;
-	u16 q_idx = channel->offermsg.offer.sub_channel_index;
 
 	/* Make sure this is a valid nvsp packet */
 	if (unlikely(nvsp->hdr.msg_type != NVSP_MSG1_TYPE_SEND_RNDIS_PKT)) {
 		netif_err(net_device_ctx, rx_err, ndev,
 			  "Unknown nvsp packet type received %u\n",
 			  nvsp->hdr.msg_type);
-		return;
+		return 0;
 	}
 
 	if (unlikely(vmxferpage_packet->xfer_pageset_id != NETVSC_RECEIVE_BUFFER_ID)) {
@@ -1095,7 +1089,7 @@ static void netvsc_receive(struct net_device *ndev,
 			  "Invalid xfer page set id - expecting %x got %x\n",
 			  NETVSC_RECEIVE_BUFFER_ID,
 			  vmxferpage_packet->xfer_pageset_id);
-		return;
+		return 0;
 	}
 
 	count = vmxferpage_packet->range_cnt;
@@ -1111,26 +1105,26 @@ static void netvsc_receive(struct net_device *ndev,
 					      channel, data, buflen);
 	}
 
-	if (!net_device->chan_table[q_idx].mrc.buf) {
+	if (net_device->chan_table[q_idx].mrc.buf) {
+		struct recv_comp_data *rcd;
+
+		rcd = get_recv_comp_slot(net_device, channel, q_idx);
+		if (rcd) {
+			rcd->tid = vmxferpage_packet->d.trans_id;
+			rcd->status = status;
+		} else {
+			netdev_err(ndev, "Recv_comp full buf q:%hd, tid:%llx\n",
+				   q_idx, vmxferpage_packet->d.trans_id);
+		}
+	} else {
 		ret = netvsc_send_recv_completion(channel,
 						  vmxferpage_packet->d.trans_id,
 						  status);
 		if (ret)
 			netdev_err(ndev, "Recv_comp q:%hd, tid:%llx, err:%d\n",
 				   q_idx, vmxferpage_packet->d.trans_id, ret);
-		return;
-	}
-
-	rcd = get_recv_comp_slot(net_device, channel, q_idx);
-
-	if (!rcd) {
-		netdev_err(ndev, "Recv_comp full buf q:%hd, tid:%llx\n",
-			   q_idx, vmxferpage_packet->d.trans_id);
-		return;
 	}
-
-	rcd->tid = vmxferpage_packet->d.trans_id;
-	rcd->status = status;
+	return count;
 }
 
 static void netvsc_send_table(struct hv_device *hdev,
@@ -1176,17 +1170,14 @@ static inline void netvsc_receive_inband(struct hv_device *hdev,
 	}
 }
 
-static void netvsc_process_raw_pkt(struct hv_device *device,
-				   struct vmbus_channel *channel,
-				   struct netvsc_device *net_device,
-				   struct net_device *ndev,
-				   u64 request_id,
-				   struct vmpacket_descriptor *desc)
+static int netvsc_process_raw_pkt(struct hv_device *device,
+				  struct vmbus_channel *channel,
+				  struct netvsc_device *net_device,
+				  struct net_device *ndev,
+				  const struct vmpacket_descriptor *desc)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(ndev);
-	struct nvsp_message *nvmsg
-		= (struct nvsp_message *)((unsigned long)desc
-					  + (desc->offset8 << 3));
+	struct nvsp_message *nvmsg = hv_pkt_data(desc);
 
 	switch (desc->type) {
 	case VM_PKT_COMP:
@@ -1194,10 +1185,8 @@ static void netvsc_process_raw_pkt(struct hv_device *device,
 		break;
 
 	case VM_PKT_DATA_USING_XFER_PAGES:
-		netvsc_receive(ndev, net_device, net_device_ctx,
-			       device, channel,
-			       (struct vmtransfer_page_packet_header *)desc,
-			       nvmsg);
+		return netvsc_receive(ndev, net_device, net_device_ctx,
+				      device, channel, desc, nvmsg);
 		break;
 
 	case VM_PKT_DATA_INBAND:
@@ -1206,53 +1195,74 @@ static void netvsc_process_raw_pkt(struct hv_device *device,
 
 	default:
 		netdev_err(ndev, "unhandled packet type %d, tid %llx\n",
-			   desc->type, request_id);
+			   desc->type, desc->trans_id);
 		break;
 	}
+
+	return 0;
 }
 
-void netvsc_channel_cb(void *context)
+static struct hv_device *netvsc_channel_to_device(struct vmbus_channel *channel)
 {
-	struct vmbus_channel *channel = context;
-	u16 q_idx = channel->offermsg.offer.sub_channel_index;
-	struct hv_device *device;
-	struct netvsc_device *net_device;
-	struct vmpacket_descriptor *desc;
-	struct net_device *ndev;
-	bool need_to_commit = false;
+	struct vmbus_channel *primary = channel->primary_channel;
 
-	if (channel->primary_channel != NULL)
-		device = channel->primary_channel->device_obj;
-	else
-		device = channel->device_obj;
+	return primary ? primary->device_obj : channel->device_obj;
+}
 
-	ndev = hv_get_drvdata(device);
-	if (unlikely(!ndev))
-		return;
+/* Network processing softirq
+ * Process data in incoming ring buffer from host
+ * Stops when ring is empty or budget is met or exceeded.
+ */
+int netvsc_poll(struct napi_struct *napi, int budget)
+{
+	struct netvsc_channel *nvchan
+		= container_of(napi, struct netvsc_channel, napi);
+	struct vmbus_channel *channel = nvchan->channel;
+	struct hv_device *device = netvsc_channel_to_device(channel);
+	u16 q_idx = channel->offermsg.offer.sub_channel_index;
+	struct net_device *ndev = hv_get_drvdata(device);
+	struct netvsc_device *net_device = net_device_to_netvsc_device(ndev);
+	int work_done = 0;
 
-	net_device = net_device_to_netvsc_device(ndev);
-	if (unlikely(!net_device))
-		return;
+	/* If starting a new interval */
+	if (!nvchan->desc)
+		nvchan->desc = hv_pkt_iter_first(channel);
 
-	if (unlikely(net_device->destroy &&
-		     netvsc_channel_idle(net_device, q_idx)))
-		return;
+	while (nvchan->desc && work_done < budget) {
+		work_done += netvsc_process_raw_pkt(device, channel, net_device,
+						    ndev, nvchan->desc);
+		nvchan->desc = hv_pkt_iter_next(channel, nvchan->desc);
+	}
 
-	/* commit_rd_index() -> hv_signal_on_read() needs this. */
-	init_cached_read_index(channel);
+	/* If receive ring was exhausted
+	 * and not doing busy poll
+	 * then re-enable host interrupts
+	 *  and reschedule if ring is not empty.
+	 */
+	if (work_done < budget &&
+	    napi_complete_done(napi, work_done) &&
+	    hv_end_read(&channel->inbound) != 0)
+		napi_reschedule(napi);
 
-	while ((desc = get_next_pkt_raw(channel)) != NULL) {
-		netvsc_process_raw_pkt(device, channel, net_device,
-				       ndev, desc->trans_id, desc);
+	netvsc_chk_recv_comp(net_device, channel, q_idx);
 
-		put_pkt_raw(channel, desc);
-		need_to_commit = true;
-	}
+	/* Driver may overshoot since multiple packets per descriptor */
+	return min(work_done, budget);
+}
+
+/* Call back when data is available in host ring buffer.
+ * Processing is deferred until network softirq (NAPI)
+ */
+void netvsc_channel_cb(void *context)
+{
+	struct netvsc_channel *nvchan = context;
 
-	if (need_to_commit)
-		commit_rd_index(channel);
+	if (napi_schedule_prep(&nvchan->napi)) {
+		/* disable interupts from host */
+		hv_begin_read(&nvchan->channel->inbound);
 
-	netvsc_chk_recv_comp(net_device, channel, q_idx);
+		__napi_schedule(&nvchan->napi);
+	}
 }
 
 /*
@@ -1274,10 +1284,16 @@ int netvsc_device_add(struct hv_device *device,
 
 	net_device->ring_size = ring_size;
 
+	/* Because the device uses NAPI, all the interrupt batching and
+	 * control is done via Net softirq, not the channel handling
+	 */
+	set_channel_read_mode(device->channel, HV_CALL_ISR);
+
 	/* Open the channel */
 	ret = vmbus_open(device->channel, ring_size * PAGE_SIZE,
 			 ring_size * PAGE_SIZE, NULL, 0,
-			 netvsc_channel_cb, device->channel);
+			 netvsc_channel_cb,
+			 net_device->chan_table);
 
 	if (ret != 0) {
 		netdev_err(ndev, "unable to open channel: %d\n", ret);
@@ -1291,15 +1307,21 @@ int netvsc_device_add(struct hv_device *device,
 	 * chn_table with the default channel to use it before subchannels are
 	 * opened.
 	 */
-	for (i = 0; i < VRSS_CHANNEL_MAX; i++)
-		net_device->chan_table[i].channel = device->channel;
+	for (i = 0; i < VRSS_CHANNEL_MAX; i++) {
+		struct netvsc_channel *nvchan = &net_device->chan_table[i];
+
+		nvchan->channel = device->channel;
+		netif_napi_add(ndev, &nvchan->napi,
+			       netvsc_poll, NAPI_POLL_WEIGHT);
+	}
+
+	/* Enable NAPI handler for init callbacks */
+	napi_enable(&net_device->chan_table[0].napi);
 
 	/* Writing nvdev pointer unlocks netvsc_send(), make sure chn_table is
 	 * populated.
 	 */
-	wmb();
-
-	net_device_ctx->nvdev = net_device;
+	rcu_assign_pointer(net_device_ctx->nvdev, net_device);
 
 	/* Connect with the NetVsp */
 	ret = netvsc_connect_vsp(device);
@@ -1312,11 +1334,13 @@ int netvsc_device_add(struct hv_device *device,
 	return ret;
 
 close:
+	napi_disable(&net_device->chan_table[0].napi);
+
 	/* Now, we can close the channel safely */
 	vmbus_close(device->channel);
 
 cleanup:
-	free_netvsc_device(net_device);
+	free_netvsc_device(&net_device->rcu);
 
 	return ret;
 }
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 5ede87f30463..f24c2891dd0c 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -62,7 +62,7 @@ static void do_set_multicast(struct work_struct *w)
 		container_of(w, struct net_device_context, work);
 	struct hv_device *device_obj = ndevctx->device_ctx;
 	struct net_device *ndev = hv_get_drvdata(device_obj);
-	struct netvsc_device *nvdev = ndevctx->nvdev;
+	struct netvsc_device *nvdev = rcu_dereference(ndevctx->nvdev);
 	struct rndis_device *rdev;
 
 	if (!nvdev)
@@ -116,7 +116,7 @@ static int netvsc_open(struct net_device *net)
 static int netvsc_close(struct net_device *net)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
-	struct netvsc_device *nvdev = net_device_ctx->nvdev;
+	struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
 	int ret;
 	u32 aread, awrite, i, msec = 10, retry = 0, retry_max = 20;
 	struct vmbus_channel *chn;
@@ -584,13 +584,14 @@ void netvsc_linkstatus_callback(struct hv_device *device_obj,
 }
 
 static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net,
+					     struct napi_struct *napi,
 					     const struct ndis_tcp_ip_checksum_info *csum_info,
 					     const struct ndis_pkt_8021q_info *vlan,
 					     void *data, u32 buflen)
 {
 	struct sk_buff *skb;
 
-	skb = netdev_alloc_skb_ip_align(net, buflen);
+	skb = napi_alloc_skb(napi, buflen);
 	if (!skb)
 		return skb;
 
@@ -636,12 +637,12 @@ int netvsc_recv_callback(struct net_device *net,
 			 const struct ndis_pkt_8021q_info *vlan)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
-	struct netvsc_device *net_device = net_device_ctx->nvdev;
+	struct netvsc_device *net_device;
+	u16 q_idx = channel->offermsg.offer.sub_channel_index;
+	struct netvsc_channel *nvchan;
 	struct net_device *vf_netdev;
 	struct sk_buff *skb;
 	struct netvsc_stats *rx_stats;
-	u16 q_idx = channel->offermsg.offer.sub_channel_index;
-
 
 	if (net->reg_state != NETREG_REGISTERED)
 		return NVSP_STAT_FAIL;
@@ -654,13 +655,20 @@ int netvsc_recv_callback(struct net_device *net,
 	 * interface in the guest.
 	 */
 	rcu_read_lock();
+	net_device = rcu_dereference(net_device_ctx->nvdev);
+	if (unlikely(!net_device))
+		goto drop;
+
+	nvchan = &net_device->chan_table[q_idx];
 	vf_netdev = rcu_dereference(net_device_ctx->vf_netdev);
 	if (vf_netdev && (vf_netdev->flags & IFF_UP))
 		net = vf_netdev;
 
 	/* Allocate a skb - TODO direct I/O to pages? */
-	skb = netvsc_alloc_recv_skb(net, csum_info, vlan, data, len);
+	skb = netvsc_alloc_recv_skb(net, &nvchan->napi,
+				    csum_info, vlan, data, len);
 	if (unlikely(!skb)) {
+drop:
 		++net->stats.rx_dropped;
 		rcu_read_unlock();
 		return NVSP_STAT_FAIL;
@@ -674,7 +682,7 @@ int netvsc_recv_callback(struct net_device *net,
 	 * on the synthetic device because modifying the VF device
 	 * statistics will not work correctly.
 	 */
-	rx_stats = &net_device->chan_table[q_idx].rx_stats;
+	rx_stats = &nvchan->rx_stats;
 	u64_stats_update_begin(&rx_stats->syncp);
 	rx_stats->packets++;
 	rx_stats->bytes += len;
@@ -685,12 +693,7 @@ int netvsc_recv_callback(struct net_device *net,
 		++rx_stats->multicast;
 	u64_stats_update_end(&rx_stats->syncp);
 
-	/*
-	 * Pass the skb back up. Network stack will deallocate the skb when it
-	 * is done.
-	 * TODO - use NAPI?
-	 */
-	netif_receive_skb(skb);
+	napi_gro_receive(&nvchan->napi, skb);
 	rcu_read_unlock();
 
 	return 0;
@@ -707,7 +710,7 @@ static void netvsc_get_channels(struct net_device *net,
 				struct ethtool_channels *channel)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
-	struct netvsc_device *nvdev = net_device_ctx->nvdev;
+	struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
 
 	if (nvdev) {
 		channel->max_combined	= nvdev->max_chn;
@@ -744,8 +747,9 @@ static int netvsc_set_channels(struct net_device *net,
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
 	struct hv_device *dev = net_device_ctx->device_ctx;
-	struct netvsc_device *nvdev = net_device_ctx->nvdev;
+	struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
 	unsigned int count = channels->combined_count;
+	bool was_running;
 	int ret;
 
 	/* We do not support separate count for rx, tx, or other */
@@ -756,7 +760,7 @@ static int netvsc_set_channels(struct net_device *net,
 	if (count > net->num_tx_queues || count > net->num_rx_queues)
 		return -EINVAL;
 
-	if (net_device_ctx->start_remove || !nvdev || nvdev->destroy)
+	if (!nvdev || nvdev->destroy)
 		return -ENODEV;
 
 	if (nvdev->nvsp_version < NVSP_PROTOCOL_VERSION_5)
@@ -765,11 +769,13 @@ static int netvsc_set_channels(struct net_device *net,
 	if (count > nvdev->max_chn)
 		return -EINVAL;
 
-	ret = netvsc_close(net);
-	if (ret)
-		return ret;
+	was_running = netif_running(net);
+	if (was_running) {
+		ret = netvsc_close(net);
+		if (ret)
+			return ret;
+	}
 
-	net_device_ctx->start_remove = true;
 	rndis_filter_device_remove(dev, nvdev);
 
 	ret = netvsc_set_queues(net, dev, count);
@@ -778,8 +784,8 @@ static int netvsc_set_channels(struct net_device *net,
 	else
 		netvsc_set_queues(net, dev, nvdev->num_chn);
 
-	netvsc_open(net);
-	net_device_ctx->start_remove = false;
+	if (was_running)
+		ret = netvsc_open(net);
 
 	/* We may have missed link change notifications */
 	schedule_delayed_work(&net_device_ctx->dwork, 0);
@@ -787,18 +793,19 @@ static int netvsc_set_channels(struct net_device *net,
 	return ret;
 }
 
-static bool netvsc_validate_ethtool_ss_cmd(const struct ethtool_cmd *cmd)
+static bool
+netvsc_validate_ethtool_ss_cmd(const struct ethtool_link_ksettings *cmd)
 {
-	struct ethtool_cmd diff1 = *cmd;
-	struct ethtool_cmd diff2 = {};
+	struct ethtool_link_ksettings diff1 = *cmd;
+	struct ethtool_link_ksettings diff2 = {};
 
-	ethtool_cmd_speed_set(&diff1, 0);
-	diff1.duplex = 0;
+	diff1.base.speed = 0;
+	diff1.base.duplex = 0;
 	/* advertising and cmd are usually set */
-	diff1.advertising = 0;
-	diff1.cmd = 0;
+	ethtool_link_ksettings_zero_link_mode(&diff1, advertising);
+	diff1.base.cmd = 0;
 	/* We set port to PORT_OTHER */
-	diff2.port = PORT_OTHER;
+	diff2.base.port = PORT_OTHER;
 
 	return !memcmp(&diff1, &diff2, sizeof(diff1));
 }
@@ -811,30 +818,32 @@ static void netvsc_init_settings(struct net_device *dev)
 	ndc->duplex = DUPLEX_UNKNOWN;
 }
 
-static int netvsc_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int netvsc_get_link_ksettings(struct net_device *dev,
+				     struct ethtool_link_ksettings *cmd)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
 
-	ethtool_cmd_speed_set(cmd, ndc->speed);
-	cmd->duplex = ndc->duplex;
-	cmd->port = PORT_OTHER;
+	cmd->base.speed = ndc->speed;
+	cmd->base.duplex = ndc->duplex;
+	cmd->base.port = PORT_OTHER;
 
 	return 0;
 }
 
-static int netvsc_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int netvsc_set_link_ksettings(struct net_device *dev,
+				     const struct ethtool_link_ksettings *cmd)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
 	u32 speed;
 
-	speed = ethtool_cmd_speed(cmd);
+	speed = cmd->base.speed;
 	if (!ethtool_validate_speed(speed) ||
-	    !ethtool_validate_duplex(cmd->duplex) ||
+	    !ethtool_validate_duplex(cmd->base.duplex) ||
 	    !netvsc_validate_ethtool_ss_cmd(cmd))
 		return -EINVAL;
 
 	ndc->speed = speed;
-	ndc->duplex = cmd->duplex;
+	ndc->duplex = cmd->base.duplex;
 
 	return 0;
 }
@@ -842,24 +851,27 @@ static int netvsc_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 {
 	struct net_device_context *ndevctx = netdev_priv(ndev);
-	struct netvsc_device *nvdev = ndevctx->nvdev;
+	struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);
 	struct hv_device *hdev = ndevctx->device_ctx;
 	struct netvsc_device_info device_info;
-	int ret;
+	bool was_running;
+	int ret = 0;
 
-	if (ndevctx->start_remove || !nvdev || nvdev->destroy)
+	if (!nvdev || nvdev->destroy)
 		return -ENODEV;
 
-	ret = netvsc_close(ndev);
-	if (ret)
-		goto out;
+	was_running = netif_running(ndev);
+	if (was_running) {
+		ret = netvsc_close(ndev);
+		if (ret)
+			return ret;
+	}
 
 	memset(&device_info, 0, sizeof(device_info));
 	device_info.ring_size = ring_size;
 	device_info.num_chn = nvdev->num_chn;
 	device_info.max_num_vrss_chns = nvdev->num_chn;
 
-	ndevctx->start_remove = true;
 	rndis_filter_device_remove(hdev, nvdev);
 
 	/* 'nvdev' has been freed in rndis_filter_device_remove() ->
@@ -872,9 +884,8 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 
 	rndis_filter_device_add(hdev, &device_info);
 
-out:
-	netvsc_open(ndev);
-	ndevctx->start_remove = false;
+	if (was_running)
+		ret = netvsc_open(ndev);
 
 	/* We may have missed link change notifications */
 	schedule_delayed_work(&ndevctx->dwork, 0);
@@ -886,7 +897,7 @@ static void netvsc_get_stats64(struct net_device *net,
 			       struct rtnl_link_stats64 *t)
 {
 	struct net_device_context *ndev_ctx = netdev_priv(net);
-	struct netvsc_device *nvdev = ndev_ctx->nvdev;
+	struct netvsc_device *nvdev = rcu_dereference(ndev_ctx->nvdev);
 	int i;
 
 	if (!nvdev)
@@ -971,7 +982,10 @@ static const struct {
 static int netvsc_get_sset_count(struct net_device *dev, int string_set)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
-	struct netvsc_device *nvdev = ndc->nvdev;
+	struct netvsc_device *nvdev = rcu_dereference(ndc->nvdev);
+
+	if (!nvdev)
+		return -ENODEV;
 
 	switch (string_set) {
 	case ETH_SS_STATS:
@@ -985,13 +999,16 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
 				     struct ethtool_stats *stats, u64 *data)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
-	struct netvsc_device *nvdev = ndc->nvdev;
+	struct netvsc_device *nvdev = rcu_dereference(ndc->nvdev);
 	const void *nds = &ndc->eth_stats;
 	const struct netvsc_stats *qstats;
 	unsigned int start;
 	u64 packets, bytes;
 	int i, j;
 
+	if (!nvdev)
+		return;
+
 	for (i = 0; i < NETVSC_GLOBAL_STATS_LEN; i++)
 		data[i] = *(unsigned long *)(nds + netvsc_stats[i].offset);
 
@@ -1020,10 +1037,13 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
 static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
-	struct netvsc_device *nvdev = ndc->nvdev;
+	struct netvsc_device *nvdev = rcu_dereference(ndc->nvdev);
 	u8 *p = data;
 	int i;
 
+	if (!nvdev)
+		return;
+
 	switch (stringset) {
 	case ETH_SS_STATS:
 		for (i = 0; i < ARRAY_SIZE(netvsc_stats); i++)
@@ -1075,7 +1095,10 @@ netvsc_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
 		 u32 *rules)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
-	struct netvsc_device *nvdev = ndc->nvdev;
+	struct netvsc_device *nvdev = rcu_dereference(ndc->nvdev);
+
+	if (!nvdev)
+		return -ENODEV;
 
 	switch (info->cmd) {
 	case ETHTOOL_GRXRINGS:
@@ -1111,13 +1134,17 @@ static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
 			   u8 *hfunc)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
-	struct netvsc_device *ndev = ndc->nvdev;
-	struct rndis_device *rndis_dev = ndev->extension;
+	struct netvsc_device *ndev = rcu_dereference(ndc->nvdev);
+	struct rndis_device *rndis_dev;
 	int i;
 
+	if (!ndev)
+		return -ENODEV;
+
 	if (hfunc)
 		*hfunc = ETH_RSS_HASH_TOP;	/* Toeplitz */
 
+	rndis_dev = ndev->extension;
 	if (indir) {
 		for (i = 0; i < ITAB_NUM; i++)
 			indir[i] = rndis_dev->ind_table[i];
@@ -1133,13 +1160,17 @@ static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir,
 			   const u8 *key, const u8 hfunc)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
-	struct netvsc_device *ndev = ndc->nvdev;
-	struct rndis_device *rndis_dev = ndev->extension;
+	struct netvsc_device *ndev = rtnl_dereference(ndc->nvdev);
+	struct rndis_device *rndis_dev;
 	int i;
 
+	if (!ndev)
+		return -ENODEV;
+
 	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
+	rndis_dev = ndev->extension;
 	if (indir) {
 		for (i = 0; i < ITAB_NUM; i++)
 			if (indir[i] >= dev->num_rx_queues)
@@ -1168,13 +1199,13 @@ static const struct ethtool_ops ethtool_ops = {
 	.get_channels   = netvsc_get_channels,
 	.set_channels   = netvsc_set_channels,
 	.get_ts_info	= ethtool_op_get_ts_info,
-	.get_settings	= netvsc_get_settings,
-	.set_settings	= netvsc_set_settings,
 	.get_rxnfc	= netvsc_get_rxnfc,
 	.get_rxfh_key_size = netvsc_get_rxfh_key_size,
 	.get_rxfh_indir_size = netvsc_rss_indir_size,
 	.get_rxfh	= netvsc_get_rxfh,
 	.set_rxfh	= netvsc_set_rxfh,
+	.get_link_ksettings = netvsc_get_link_ksettings,
+	.set_link_ksettings = netvsc_set_link_ksettings,
 };
 
 static const struct net_device_ops device_ops = {
@@ -1210,10 +1241,10 @@ static void netvsc_link_change(struct work_struct *w)
 	unsigned long flags, next_reconfig, delay;
 
 	rtnl_lock();
-	if (ndev_ctx->start_remove)
+	net_device = rtnl_dereference(ndev_ctx->nvdev);
+	if (!net_device)
 		goto out_unlock;
 
-	net_device = ndev_ctx->nvdev;
 	rdev = net_device->extension;
 
 	next_reconfig = ndev_ctx->last_reconfig + LINKCHANGE_INT;
@@ -1354,7 +1385,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
 		return NOTIFY_DONE;
 
 	net_device_ctx = netdev_priv(ndev);
-	netvsc_dev = net_device_ctx->nvdev;
+	netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
 	if (!netvsc_dev || rtnl_dereference(net_device_ctx->vf_netdev))
 		return NOTIFY_DONE;
 
@@ -1380,7 +1411,7 @@ static int netvsc_vf_up(struct net_device *vf_netdev)
 		return NOTIFY_DONE;
 
 	net_device_ctx = netdev_priv(ndev);
-	netvsc_dev = net_device_ctx->nvdev;
+	netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
 
 	netdev_info(ndev, "VF up: %s\n", vf_netdev->name);
 
@@ -1414,7 +1445,7 @@ static int netvsc_vf_down(struct net_device *vf_netdev)
 		return NOTIFY_DONE;
 
 	net_device_ctx = netdev_priv(ndev);
-	netvsc_dev = net_device_ctx->nvdev;
+	netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
 
 	netdev_info(ndev, "VF down: %s\n", vf_netdev->name);
 	netvsc_switch_datapath(ndev, false);
@@ -1474,8 +1505,6 @@ static int netvsc_probe(struct hv_device *dev,
 
 	hv_set_drvdata(dev, net);
 
-	net_device_ctx->start_remove = false;
-
 	INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change);
 	INIT_WORK(&net_device_ctx->work, do_set_multicast);
 
@@ -1492,8 +1521,7 @@ static int netvsc_probe(struct hv_device *dev,
 	/* Notify the netvsc driver of the new device */
 	memset(&device_info, 0, sizeof(device_info));
 	device_info.ring_size = ring_size;
-	device_info.max_num_vrss_chns = min_t(u32, VRSS_CHANNEL_DEFAULT,
-					      num_online_cpus());
+	device_info.num_chn = VRSS_CHANNEL_DEFAULT;
 	ret = rndis_filter_device_add(dev, &device_info);
 	if (ret != 0) {
 		netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
@@ -1509,6 +1537,7 @@ static int netvsc_probe(struct hv_device *dev,
 		NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
 	net->vlan_features = net->features;
 
+	/* RCU not necessary here, device not registered */
 	nvdev = net_device_ctx->nvdev;
 	netif_set_real_num_tx_queues(net, nvdev->num_chn);
 	netif_set_real_num_rx_queues(net, nvdev->num_chn);
@@ -1544,26 +1573,20 @@ static int netvsc_remove(struct hv_device *dev)
 
 	ndev_ctx = netdev_priv(net);
 
-	/* Avoid racing with netvsc_change_mtu()/netvsc_set_channels()
-	 * removing the device.
-	 */
-	rtnl_lock();
-	ndev_ctx->start_remove = true;
-	rtnl_unlock();
+	netif_device_detach(net);
 
 	cancel_delayed_work_sync(&ndev_ctx->dwork);
 	cancel_work_sync(&ndev_ctx->work);
 
-	/* Stop outbound asap */
-	netif_tx_disable(net);
-
-	unregister_netdev(net);
-
 	/*
 	 * Call to the vsc driver to let it know that the device is being
-	 * removed
+	 * removed. Also blocks mtu and channel changes.
 	 */
+	rtnl_lock();
 	rndis_filter_device_remove(dev, ndev_ctx->nvdev);
+	rtnl_unlock();
+
+	unregister_netdev(net);
 
 	hv_set_drvdata(dev, NULL);
 
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 19356f56b7b1..983582526b37 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -819,16 +819,14 @@ int rndis_filter_set_packet_filter(struct rndis_device *dev, u32 new_filter)
 {
 	struct rndis_request *request;
 	struct rndis_set_request *set;
-	struct rndis_set_complete *set_complete;
 	int ret;
 
 	request = get_rndis_request(dev, RNDIS_MSG_SET,
 			RNDIS_MESSAGE_SIZE(struct rndis_set_request) +
 			sizeof(u32));
-	if (!request) {
-		ret = -ENOMEM;
-		goto cleanup;
-	}
+	if (!request)
+		return -ENOMEM;
+
 
 	/* Setup the rndis set */
 	set = &request->request_msg.msg.set_req;
@@ -840,15 +838,11 @@ int rndis_filter_set_packet_filter(struct rndis_device *dev, u32 new_filter)
 	       &new_filter, sizeof(u32));
 
 	ret = rndis_filter_send_request(dev, request);
-	if (ret != 0)
-		goto cleanup;
+	if (ret == 0)
+		wait_for_completion(&request->wait_event);
 
-	wait_for_completion(&request->wait_event);
+	put_rndis_request(dev, request);
 
-	set_complete = &request->response_msg.msg.set_complete;
-cleanup:
-	if (request)
-		put_rndis_request(dev, request);
 	return ret;
 }
 
@@ -926,8 +920,6 @@ static void rndis_filter_halt_device(struct rndis_device *dev)
 	struct rndis_halt_request *halt;
 	struct net_device_context *net_device_ctx = netdev_priv(dev->ndev);
 	struct netvsc_device *nvdev = net_device_ctx->nvdev;
-	struct hv_device *hdev = net_device_ctx->device_ctx;
-	ulong flags;
 
 	/* Attempt to do a rndis device halt */
 	request = get_rndis_request(dev, RNDIS_MSG_HALT,
@@ -945,9 +937,10 @@ static void rndis_filter_halt_device(struct rndis_device *dev)
 	dev->state = RNDIS_DEV_UNINITIALIZED;
 
 cleanup:
-	spin_lock_irqsave(&hdev->channel->inbound_lock, flags);
 	nvdev->destroy = true;
-	spin_unlock_irqrestore(&hdev->channel->inbound_lock, flags);
+
+	/* Force flag to be ordered before waiting */
+	wmb();
 
 	/* Wait for all send completions */
 	wait_event(nvdev->wait_drain, netvsc_device_idle(nvdev));
@@ -996,26 +989,34 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
 		hv_get_drvdata(new_sc->primary_channel->device_obj);
 	struct netvsc_device *nvscdev = net_device_to_netvsc_device(ndev);
 	u16 chn_index = new_sc->offermsg.offer.sub_channel_index;
+	struct netvsc_channel *nvchan;
 	int ret;
-	unsigned long flags;
 
 	if (chn_index >= nvscdev->num_chn)
 		return;
 
-	nvscdev->chan_table[chn_index].mrc.buf
+	nvchan = nvscdev->chan_table + chn_index;
+	nvchan->mrc.buf
 		= vzalloc(NETVSC_RECVSLOT_MAX * sizeof(struct recv_comp_data));
 
+	if (!nvchan->mrc.buf)
+		return;
+
+	/* Because the device uses NAPI, all the interrupt batching and
+	 * control is done via Net softirq, not the channel handling
+	 */
+	set_channel_read_mode(new_sc, HV_CALL_ISR);
+
 	ret = vmbus_open(new_sc, nvscdev->ring_size * PAGE_SIZE,
 			 nvscdev->ring_size * PAGE_SIZE, NULL, 0,
-			 netvsc_channel_cb, new_sc);
+			 netvsc_channel_cb, nvchan);
 
 	if (ret == 0)
-		nvscdev->chan_table[chn_index].channel = new_sc;
+		nvchan->channel = new_sc;
+
+	napi_enable(&nvchan->napi);
 
-	spin_lock_irqsave(&nvscdev->sc_lock, flags);
-	nvscdev->num_sc_offered--;
-	spin_unlock_irqrestore(&nvscdev->sc_lock, flags);
-	if (nvscdev->num_sc_offered == 0)
+	if (refcount_dec_and_test(&nvscdev->sc_offered))
 		complete(&nvscdev->channel_init_wait);
 }
 
@@ -1032,12 +1033,9 @@ int rndis_filter_device_add(struct hv_device *dev,
 	struct ndis_recv_scale_cap rsscap;
 	u32 rsscap_size = sizeof(struct ndis_recv_scale_cap);
 	unsigned int gso_max_size = GSO_MAX_SIZE;
-	u32 mtu, size;
-	u32 num_rss_qs;
-	u32 sc_delta;
+	u32 mtu, size, num_rss_qs;
 	const struct cpumask *node_cpu_mask;
 	u32 num_possible_rss_qs;
-	unsigned long flags;
 	int i, ret;
 
 	rndis_device = get_rndis_device();
@@ -1060,7 +1058,7 @@ int rndis_filter_device_add(struct hv_device *dev,
 	net_device->max_chn = 1;
 	net_device->num_chn = 1;
 
-	spin_lock_init(&net_device->sc_lock);
+	refcount_set(&net_device->sc_offered, 0);
 
 	net_device->extension = rndis_device;
 	rndis_device->ndev = net;
@@ -1174,34 +1172,30 @@ int rndis_filter_device_add(struct hv_device *dev,
 	if (ret || rsscap.num_recv_que < 2)
 		goto out;
 
-	net_device->max_chn = min_t(u32, VRSS_CHANNEL_MAX, rsscap.num_recv_que);
-
-	num_rss_qs = min(device_info->max_num_vrss_chns, net_device->max_chn);
-
 	/*
 	 * We will limit the VRSS channels to the number CPUs in the NUMA node
 	 * the primary channel is currently bound to.
+	 *
+	 * This also guarantees that num_possible_rss_qs <= num_online_cpus
 	 */
 	node_cpu_mask = cpumask_of_node(cpu_to_node(dev->channel->target_cpu));
-	num_possible_rss_qs = cpumask_weight(node_cpu_mask);
+	num_possible_rss_qs = min_t(u32, cpumask_weight(node_cpu_mask),
+				    rsscap.num_recv_que);
 
-	/* We will use the given number of channels if available. */
-	if (device_info->num_chn && device_info->num_chn < net_device->max_chn)
-		net_device->num_chn = device_info->num_chn;
-	else
-		net_device->num_chn = min(num_possible_rss_qs, num_rss_qs);
+	net_device->max_chn = min_t(u32, VRSS_CHANNEL_MAX, num_possible_rss_qs);
 
-	num_rss_qs = net_device->num_chn - 1;
+	/* We will use the given number of channels if available. */
+	net_device->num_chn = min(net_device->max_chn, device_info->num_chn);
 
 	for (i = 0; i < ITAB_NUM; i++)
 		rndis_device->ind_table[i] = ethtool_rxfh_indir_default(i,
 							net_device->num_chn);
 
-	net_device->num_sc_offered = num_rss_qs;
-
-	if (net_device->num_chn == 1)
-		goto out;
+	num_rss_qs = net_device->num_chn - 1;
+	if (num_rss_qs == 0)
+		return 0;
 
+	refcount_set(&net_device->sc_offered, num_rss_qs);
 	vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open);
 
 	init_packet = &net_device->channel_init_pkt;
@@ -1217,32 +1211,23 @@ int rndis_filter_device_add(struct hv_device *dev,
 			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
 	if (ret)
 		goto out;
-	wait_for_completion(&net_device->channel_init_wait);
 
-	if (init_packet->msg.v5_msg.subchn_comp.status !=
-	    NVSP_STAT_SUCCESS) {
+	if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) {
 		ret = -ENODEV;
 		goto out;
 	}
+	wait_for_completion(&net_device->channel_init_wait);
+
 	net_device->num_chn = 1 +
 		init_packet->msg.v5_msg.subchn_comp.num_subchannels;
 
-	ret = rndis_filter_set_rss_param(rndis_device, netvsc_hash_key,
-					 net_device->num_chn);
-
-	/*
-	 * Set the number of sub-channels to be received.
-	 */
-	spin_lock_irqsave(&net_device->sc_lock, flags);
-	sc_delta = num_rss_qs - (net_device->num_chn - 1);
-	net_device->num_sc_offered -= sc_delta;
-	spin_unlock_irqrestore(&net_device->sc_lock, flags);
-
+	/* ignore failues from setting rss parameters, still have channels */
+	rndis_filter_set_rss_param(rndis_device, netvsc_hash_key,
+				   net_device->num_chn);
 out:
 	if (ret) {
 		net_device->max_chn = 1;
 		net_device->num_chn = 1;
-		net_device->num_sc_offered = 0;
 	}
 
 	return 0; /* return 0 because primary channel can be used alone */
@@ -1257,12 +1242,6 @@ void rndis_filter_device_remove(struct hv_device *dev,
 {
 	struct rndis_device *rndis_dev = net_dev->extension;
 
-	/* If not all subchannel offers are complete, wait for them until
-	 * completion to avoid race.
-	 */
-	if (net_dev->num_sc_offered > 0)
-		wait_for_completion(&net_dev->channel_init_wait);
-
 	/* Halt and release the rndis device */
 	rndis_filter_halt_device(rndis_dev);
 
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index 7b131f8e4093..bd63289c55e8 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -18,6 +18,7 @@
 #include <linux/spi/spi.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/regmap.h>
 #include <linux/ieee802154.h>
 #include <linux/irq.h>
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index b23b71981fd5..224f65cb576b 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -13,7 +13,7 @@
  *
  *		Alan Cox	:	Fixed oddments for NET3.014
  *		Alan Cox	:	Rejig for NET3.029 snap #3
- *		Alan Cox	: 	Fixed NET3.029 bugs and sped up
+ *		Alan Cox	:	Fixed NET3.029 bugs and sped up
  *		Larry McVoy	:	Tiny tweak to double performance
  *		Alan Cox	:	Backed out LMV's tweak - the linux mm
  *					can't take it...
@@ -41,7 +41,7 @@
 #include <linux/in.h>
 
 #include <linux/uaccess.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 #include <linux/inet.h>
 #include <linux/netdevice.h>
@@ -55,6 +55,7 @@
 #include <linux/ip.h>
 #include <linux/tcp.h>
 #include <linux/percpu.h>
+#include <linux/net_tstamp.h>
 #include <net/net_namespace.h>
 #include <linux/u64_stats_sync.h>
 
@@ -64,8 +65,7 @@ struct pcpu_lstats {
 	struct u64_stats_sync	syncp;
 };
 
-/*
- * The higher levels take care of making this non-reentrant (it's
+/* The higher levels take care of making this non-reentrant (it's
  * called with bh's disabled).
  */
 static netdev_tx_t loopback_xmit(struct sk_buff *skb,
@@ -74,6 +74,7 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb,
 	struct pcpu_lstats *lb_stats;
 	int len;
 
+	skb_tx_timestamp(skb);
 	skb_orphan(skb);
 
 	/* Before queueing this packet to netif_rx(),
@@ -129,8 +130,21 @@ static u32 always_on(struct net_device *dev)
 	return 1;
 }
 
+static int loopback_get_ts_info(struct net_device *netdev,
+				struct ethtool_ts_info *ts_info)
+{
+	ts_info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+				   SOF_TIMESTAMPING_RX_SOFTWARE |
+				   SOF_TIMESTAMPING_SOFTWARE;
+
+	ts_info->phc_index = -1;
+
+	return 0;
+};
+
 static const struct ethtool_ops loopback_ethtool_ops = {
 	.get_link		= always_on,
+	.get_ts_info		= loopback_get_ts_info,
 };
 
 static int loopback_dev_init(struct net_device *dev)
@@ -149,14 +163,13 @@ static void loopback_dev_free(struct net_device *dev)
 }
 
 static const struct net_device_ops loopback_ops = {
-	.ndo_init      = loopback_dev_init,
-	.ndo_start_xmit= loopback_xmit,
+	.ndo_init        = loopback_dev_init,
+	.ndo_start_xmit  = loopback_xmit,
 	.ndo_get_stats64 = loopback_get_stats64,
 	.ndo_set_mac_address = eth_mac_addr,
 };
 
-/*
- * The loopback device is special. There is only one instance
+/* The loopback device is special. There is only one instance
  * per network namespace.
  */
 static void loopback_setup(struct net_device *dev)
@@ -170,7 +183,7 @@ static void loopback_setup(struct net_device *dev)
 	dev->priv_flags		|= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
 	netif_keep_dst(dev);
 	dev->hw_features	= NETIF_F_GSO_SOFTWARE;
-	dev->features 		= NETIF_F_SG | NETIF_F_FRAGLIST
+	dev->features		= NETIF_F_SG | NETIF_F_FRAGLIST
 		| NETIF_F_GSO_SOFTWARE
 		| NETIF_F_HW_CSUM
 		| NETIF_F_RXCSUM
@@ -206,7 +219,6 @@ static __net_init int loopback_net_init(struct net *net)
 	net->loopback_dev = dev;
 	return 0;
 
-
 out_free_netdev:
 	free_netdev(dev);
 out:
@@ -217,5 +229,5 @@ out:
 
 /* Registered in net/core/dev.c */
 struct pernet_operations __net_initdata loopback_net_ops = {
-       .init = loopback_net_init,
+	.init = loopback_net_init,
 };
diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c
index 36877ba65516..4daf3d0926a8 100644
--- a/drivers/net/ntb_netdev.c
+++ b/drivers/net/ntb_netdev.c
@@ -372,18 +372,19 @@ static void ntb_get_drvinfo(struct net_device *ndev,
 	strlcpy(info->bus_info, pci_name(dev->pdev), sizeof(info->bus_info));
 }
 
-static int ntb_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int ntb_get_link_ksettings(struct net_device *dev,
+				  struct ethtool_link_ksettings *cmd)
 {
-	cmd->supported = SUPPORTED_Backplane;
-	cmd->advertising = ADVERTISED_Backplane;
-	ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN);
-	cmd->duplex = DUPLEX_FULL;
-	cmd->port = PORT_OTHER;
-	cmd->phy_address = 0;
-	cmd->transceiver = XCVR_DUMMY1;
-	cmd->autoneg = AUTONEG_ENABLE;
-	cmd->maxtxpkt = 0;
-	cmd->maxrxpkt = 0;
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, Backplane);
+	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, Backplane);
+
+	cmd->base.speed = SPEED_UNKNOWN;
+	cmd->base.duplex = DUPLEX_FULL;
+	cmd->base.port = PORT_OTHER;
+	cmd->base.phy_address = 0;
+	cmd->base.autoneg = AUTONEG_ENABLE;
 
 	return 0;
 }
@@ -391,7 +392,7 @@ static int ntb_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 static const struct ethtool_ops ntb_ethtool_ops = {
 	.get_drvinfo = ntb_get_drvinfo,
 	.get_link = ethtool_op_get_link,
-	.get_settings = ntb_get_settings,
+	.get_link_ksettings = ntb_get_link_ksettings,
 };
 
 static const struct ntb_queue_handlers ntb_netdev_handlers = {
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 8dbd59baa34d..60ffc9da6a28 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -2,33 +2,12 @@
 # PHY Layer Configuration
 #
 
-menuconfig PHYLIB
-	tristate "PHY Device support and infrastructure"
-	depends on NETDEVICES
+menuconfig MDIO_DEVICE
+	tristate "MDIO bus device drivers"
 	help
-	  Ethernet controllers are usually attached to PHY
-	  devices.  This option provides infrastructure for
-	  managing PHY devices.
-
-if PHYLIB
+	   MDIO devices and driver infrastructure code.
 
-config SWPHY
-	bool
-
-config LED_TRIGGER_PHY
-	bool "Support LED triggers for tracking link state"
-	depends on LEDS_TRIGGERS
-	---help---
-	  Adds support for a set of LED trigger events per-PHY.  Link
-	  state change will trigger the events, for consumption by an
-	  LED class driver.  There are triggers for each link speed currently
-	  supported by the phy, and are of the form:
-	       <mii bus id>:<phy>:<speed>
-
-	  Where speed is in the form:
-		<Speed in megabits>Mbps or <Speed in gigabits>Gbps
-
-comment "MDIO bus device drivers"
+if MDIO_DEVICE
 
 config MDIO_BCM_IPROC
 	tristate "Broadcom iProc MDIO bus controller"
@@ -40,7 +19,7 @@ config MDIO_BCM_IPROC
 
 config MDIO_BCM_UNIMAC
 	tristate "Broadcom UniMAC MDIO bus controller"
-	depends on HAS_IOMEM
+	depends on HAS_IOMEM && OF_MDIO
 	help
 	  This module provides a driver for the Broadcom UniMAC MDIO busses.
 	  This hardware can be found in the Broadcom GENET Ethernet MAC
@@ -49,6 +28,7 @@ config MDIO_BCM_UNIMAC
 
 config MDIO_BITBANG
 	tristate "Bitbanged MDIO buses"
+	depends on !(MDIO_DEVICE=y && PHYLIB=m)
 	help
 	  This module implements the MDIO bus protocol in software,
 	  for use by low level drivers that export the ability to
@@ -160,6 +140,36 @@ config MDIO_XGENE
 	  This module provides a driver for the MDIO busses found in the
 	  APM X-Gene SoC's.
 
+endif
+
+menuconfig PHYLIB
+	tristate "PHY Device support and infrastructure"
+	depends on NETDEVICES
+	select MDIO_DEVICE
+	help
+	  Ethernet controllers are usually attached to PHY
+	  devices.  This option provides infrastructure for
+	  managing PHY devices.
+
+if PHYLIB
+
+config SWPHY
+	bool
+
+config LED_TRIGGER_PHY
+	bool "Support LED triggers for tracking link state"
+	depends on LEDS_TRIGGERS
+	---help---
+	  Adds support for a set of LED trigger events per-PHY.  Link
+	  state change will trigger the events, for consumption by an
+	  LED class driver.  There are triggers for each link speed currently
+	  supported by the phy, and are of the form:
+	       <mii bus id>:<phy>:<speed>
+
+	  Where speed is in the form:
+		<Speed in megabits>Mbps or <Speed in gigabits>Gbps
+
+
 comment "MII PHY device drivers"
 
 config AMD_PHY
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 407b0b601ea8..e36db9a2ba38 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -1,7 +1,20 @@
 # Makefile for Linux PHY drivers and MDIO bus drivers
 
-libphy-y			:= phy.o phy_device.o mdio_bus.o mdio_device.o \
-				   mdio-boardinfo.o
+libphy-y			:= phy.o phy-core.o phy_device.o
+mdio-bus-y			+= mdio_bus.o mdio_device.o
+
+ifdef CONFIG_MDIO_DEVICE
+obj-y				+= mdio-boardinfo.o
+endif
+
+# PHYLIB implies MDIO_DEVICE, in that case, we have a bunch of circular
+# dependencies that does not make it possible to split mdio-bus objects into a
+# dedicated loadable module, so we bundle them all together into libphy.ko
+ifdef CONFIG_PHYLIB
+libphy-y			+= $(mdio-bus-y)
+else
+obj-$(CONFIG_MDIO_DEVICE)	+= mdio-bus.o
+endif
 libphy-$(CONFIG_SWPHY)		+= swphy.o
 libphy-$(CONFIG_LED_TRIGGER_PHY)	+= phy_led_triggers.o
 
diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c
index ab9ad689617c..171010eb4d9c 100644
--- a/drivers/net/phy/bcm-phy-lib.c
+++ b/drivers/net/phy/bcm-phy-lib.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015 Broadcom Corporation
+ * Copyright (C) 2015-2017 Broadcom
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
@@ -201,8 +201,7 @@ int bcm_phy_set_eee(struct phy_device *phydev, bool enable)
 	int val;
 
 	/* Enable EEE at PHY level */
-	val = phy_read_mmd_indirect(phydev, BRCM_CL45VEN_EEE_CONTROL,
-				    MDIO_MMD_AN);
+	val = phy_read_mmd(phydev, MDIO_MMD_AN, BRCM_CL45VEN_EEE_CONTROL);
 	if (val < 0)
 		return val;
 
@@ -211,22 +210,19 @@ int bcm_phy_set_eee(struct phy_device *phydev, bool enable)
 	else
 		val &= ~(LPI_FEATURE_EN | LPI_FEATURE_EN_DIG1000X);
 
-	phy_write_mmd_indirect(phydev, BRCM_CL45VEN_EEE_CONTROL,
-			       MDIO_MMD_AN, (u32)val);
+	phy_write_mmd(phydev, MDIO_MMD_AN, BRCM_CL45VEN_EEE_CONTROL, (u32)val);
 
 	/* Advertise EEE */
-	val = phy_read_mmd_indirect(phydev, BCM_CL45VEN_EEE_ADV,
-				    MDIO_MMD_AN);
+	val = phy_read_mmd(phydev, MDIO_MMD_AN, BCM_CL45VEN_EEE_ADV);
 	if (val < 0)
 		return val;
 
 	if (enable)
-		val |= (MDIO_AN_EEE_ADV_100TX | MDIO_AN_EEE_ADV_1000T);
+		val |= (MDIO_EEE_100TX | MDIO_EEE_1000T);
 	else
-		val &= ~(MDIO_AN_EEE_ADV_100TX | MDIO_AN_EEE_ADV_1000T);
+		val &= ~(MDIO_EEE_100TX | MDIO_EEE_1000T);
 
-	phy_write_mmd_indirect(phydev, BCM_CL45VEN_EEE_ADV,
-			       MDIO_MMD_AN, (u32)val);
+	phy_write_mmd(phydev, MDIO_MMD_AN, BCM_CL45VEN_EEE_ADV, (u32)val);
 
 	return 0;
 }
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index d1c2614dad3a..caa9f6e17f34 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -1,7 +1,7 @@
 /*
  * Broadcom BCM7xxx internal transceivers support.
  *
- * Copyright (C) 2014, Broadcom Corporation
+ * Copyright (C) 2014-2017 Broadcom
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -19,7 +19,7 @@
 
 /* Broadcom BCM7xxx internal PHY registers */
 
-/* 40nm only register definitions */
+/* EPHY only register definitions */
 #define MII_BCM7XXX_100TX_AUX_CTL	0x10
 #define MII_BCM7XXX_100TX_FALSE_CAR	0x13
 #define MII_BCM7XXX_100TX_DISC		0x14
@@ -27,6 +27,19 @@
 #define  MII_BCM7XXX_64CLK_MDIO		BIT(12)
 #define MII_BCM7XXX_TEST		0x1f
 #define  MII_BCM7XXX_SHD_MODE_2		BIT(2)
+#define MII_BCM7XXX_SHD_2_ADDR_CTRL	0xe
+#define MII_BCM7XXX_SHD_2_CTRL_STAT	0xf
+#define MII_BCM7XXX_SHD_2_BIAS_TRIM	0x1a
+#define MII_BCM7XXX_SHD_3_AN_EEE_ADV	0x3
+#define MII_BCM7XXX_SHD_3_PCS_CTRL_2	0x6
+#define  MII_BCM7XXX_PCS_CTRL_2_DEF	0x4400
+#define MII_BCM7XXX_SHD_3_AN_STAT	0xb
+#define  MII_BCM7XXX_AN_NULL_MSG_EN	BIT(0)
+#define  MII_BCM7XXX_AN_EEE_EN		BIT(1)
+#define MII_BCM7XXX_SHD_3_EEE_THRESH	0xe
+#define  MII_BCM7XXX_EEE_THRESH_DEF	0x50
+#define MII_BCM7XXX_SHD_3_TL4		0x23
+#define  MII_BCM7XXX_TL4_RST_MSK	(BIT(2) | BIT(1))
 
 /* 28nm only register definitions */
 #define MISC_ADDR(base, channel)	base, channel
@@ -286,6 +299,181 @@ static int phy_set_clr_bits(struct phy_device *dev, int location,
 	return v;
 }
 
+static int bcm7xxx_28nm_ephy_01_afe_config_init(struct phy_device *phydev)
+{
+	int ret;
+
+	/* set shadow mode 2 */
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST,
+			       MII_BCM7XXX_SHD_MODE_2, 0);
+	if (ret < 0)
+		return ret;
+
+	/* Set current trim values INT_trim = -1, Ext_trim =0 */
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_BIAS_TRIM, 0x3BE0);
+	if (ret < 0)
+		goto reset_shadow_mode;
+
+	/* Cal reset */
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+			MII_BCM7XXX_SHD_3_TL4);
+	if (ret < 0)
+		goto reset_shadow_mode;
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+			       MII_BCM7XXX_TL4_RST_MSK, 0);
+	if (ret < 0)
+		goto reset_shadow_mode;
+
+	/* Cal reset disable */
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+			MII_BCM7XXX_SHD_3_TL4);
+	if (ret < 0)
+		goto reset_shadow_mode;
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+			       0, MII_BCM7XXX_TL4_RST_MSK);
+	if (ret < 0)
+		goto reset_shadow_mode;
+
+reset_shadow_mode:
+	/* reset shadow mode 2 */
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0,
+			       MII_BCM7XXX_SHD_MODE_2);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+/* The 28nm EPHY does not support Clause 45 (MMD) used by bcm-phy-lib */
+static int bcm7xxx_28nm_ephy_apd_enable(struct phy_device *phydev)
+{
+	int ret;
+
+	/* set shadow mode 1 */
+	ret = phy_set_clr_bits(phydev, MII_BRCM_FET_BRCMTEST,
+			       MII_BRCM_FET_BT_SRE, 0);
+	if (ret < 0)
+		return ret;
+
+	/* Enable auto-power down */
+	ret = phy_set_clr_bits(phydev, MII_BRCM_FET_SHDW_AUXSTAT2,
+			       MII_BRCM_FET_SHDW_AS2_APDE, 0);
+	if (ret < 0)
+		return ret;
+
+	/* reset shadow mode 1 */
+	ret = phy_set_clr_bits(phydev, MII_BRCM_FET_BRCMTEST, 0,
+			       MII_BRCM_FET_BT_SRE);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int bcm7xxx_28nm_ephy_eee_enable(struct phy_device *phydev)
+{
+	int ret;
+
+	/* set shadow mode 2 */
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST,
+			       MII_BCM7XXX_SHD_MODE_2, 0);
+	if (ret < 0)
+		return ret;
+
+	/* Advertise supported modes */
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+			MII_BCM7XXX_SHD_3_AN_EEE_ADV);
+	if (ret < 0)
+		goto reset_shadow_mode;
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+			MDIO_EEE_100TX);
+	if (ret < 0)
+		goto reset_shadow_mode;
+
+	/* Restore Defaults */
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+			MII_BCM7XXX_SHD_3_PCS_CTRL_2);
+	if (ret < 0)
+		goto reset_shadow_mode;
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+			MII_BCM7XXX_PCS_CTRL_2_DEF);
+	if (ret < 0)
+		goto reset_shadow_mode;
+
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+			MII_BCM7XXX_SHD_3_EEE_THRESH);
+	if (ret < 0)
+		goto reset_shadow_mode;
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+			MII_BCM7XXX_EEE_THRESH_DEF);
+	if (ret < 0)
+		goto reset_shadow_mode;
+
+	/* Enable EEE autonegotiation */
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+			MII_BCM7XXX_SHD_3_AN_STAT);
+	if (ret < 0)
+		goto reset_shadow_mode;
+	ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+			(MII_BCM7XXX_AN_NULL_MSG_EN | MII_BCM7XXX_AN_EEE_EN));
+	if (ret < 0)
+		goto reset_shadow_mode;
+
+reset_shadow_mode:
+	/* reset shadow mode 2 */
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0,
+			       MII_BCM7XXX_SHD_MODE_2);
+	if (ret < 0)
+		return ret;
+
+	/* Restart autoneg */
+	phy_write(phydev, MII_BMCR,
+		  (BMCR_SPEED100 | BMCR_ANENABLE | BMCR_ANRESTART));
+
+	return 0;
+}
+
+static int bcm7xxx_28nm_ephy_config_init(struct phy_device *phydev)
+{
+	u8 rev = phydev->phy_id & ~phydev->drv->phy_id_mask;
+	int ret = 0;
+
+	pr_info_once("%s: %s PHY revision: 0x%02x\n",
+		     phydev_name(phydev), phydev->drv->name, rev);
+
+	/* Dummy read to a register to workaround a possible issue upon reset
+	 * where the internal inverter may not allow the first MDIO transaction
+	 * to pass the MDIO management controller and make us return 0xffff for
+	 * such reads.
+	 */
+	phy_read(phydev, MII_BMSR);
+
+	/* Apply AFE software work-around if necessary */
+	if (rev == 0x01) {
+		ret = bcm7xxx_28nm_ephy_01_afe_config_init(phydev);
+		if (ret)
+			return ret;
+	}
+
+	ret = bcm7xxx_28nm_ephy_eee_enable(phydev);
+	if (ret)
+		return ret;
+
+	return bcm7xxx_28nm_ephy_apd_enable(phydev);
+}
+
+static int bcm7xxx_28nm_ephy_resume(struct phy_device *phydev)
+{
+	int ret;
+
+	/* Re-apply workarounds coming out suspend/resume */
+	ret = bcm7xxx_28nm_ephy_config_init(phydev);
+	if (ret)
+		return ret;
+
+	return genphy_config_aneg(phydev);
+}
+
 static int bcm7xxx_config_init(struct phy_device *phydev)
 {
 	int ret;
@@ -434,6 +622,23 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev)
 	.probe		= bcm7xxx_28nm_probe,				\
 }
 
+#define BCM7XXX_28NM_EPHY(_oui, _name)					\
+{									\
+	.phy_id		= (_oui),					\
+	.phy_id_mask	= 0xfffffff0,					\
+	.name		= _name,					\
+	.features	= PHY_BASIC_FEATURES,				\
+	.flags		= PHY_IS_INTERNAL,				\
+	.config_init	= bcm7xxx_28nm_ephy_config_init,		\
+	.config_aneg	= genphy_config_aneg,				\
+	.read_status	= genphy_read_status,				\
+	.resume		= bcm7xxx_28nm_ephy_resume,			\
+	.get_sset_count	= bcm_phy_get_sset_count,			\
+	.get_strings	= bcm_phy_get_strings,				\
+	.get_stats	= bcm7xxx_28nm_get_phy_stats,			\
+	.probe		= bcm7xxx_28nm_probe,				\
+}
+
 #define BCM7XXX_40NM_EPHY(_oui, _name)					\
 {									\
 	.phy_id         = (_oui),					\
@@ -450,6 +655,9 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev)
 
 static struct phy_driver bcm7xxx_driver[] = {
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7250, "Broadcom BCM7250"),
+	BCM7XXX_28NM_EPHY(PHY_ID_BCM7260, "Broadcom BCM7260"),
+	BCM7XXX_28NM_EPHY(PHY_ID_BCM7268, "Broadcom BCM7268"),
+	BCM7XXX_28NM_EPHY(PHY_ID_BCM7271, "Broadcom BCM7271"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7278, "Broadcom BCM7278"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7364, "Broadcom BCM7364"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7366, "Broadcom BCM7366"),
@@ -466,6 +674,9 @@ static struct phy_driver bcm7xxx_driver[] = {
 
 static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
 	{ PHY_ID_BCM7250, 0xfffffff0, },
+	{ PHY_ID_BCM7260, 0xfffffff0, },
+	{ PHY_ID_BCM7268, 0xfffffff0, },
+	{ PHY_ID_BCM7271, 0xfffffff0, },
 	{ PHY_ID_BCM7278, 0xfffffff0, },
 	{ PHY_ID_BCM7364, 0xfffffff0, },
 	{ PHY_ID_BCM7366, 0xfffffff0, },
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index 19865530e0b1..b57f20e552ba 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -133,14 +133,14 @@ static int dp83867_config_port_mirroring(struct phy_device *phydev)
 		(struct dp83867_private *)phydev->priv;
 	u16 val;
 
-	val = phy_read_mmd_indirect(phydev, DP83867_CFG4, DP83867_DEVADDR);
+	val = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4);
 
 	if (dp83867->port_mirroring == DP83867_PORT_MIRROING_EN)
 		val |= DP83867_CFG4_PORT_MIRROR_EN;
 	else
 		val &= ~DP83867_CFG4_PORT_MIRROR_EN;
 
-	phy_write_mmd_indirect(phydev, DP83867_CFG4, DP83867_DEVADDR, val);
+	phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4, val);
 
 	return 0;
 }
@@ -231,8 +231,7 @@ static int dp83867_config_init(struct phy_device *phydev)
 		 * register's bit 11 (marked as RESERVED).
 		 */
 
-		bs = phy_read_mmd_indirect(phydev, DP83867_STRAP_STS1,
-					   DP83867_DEVADDR);
+		bs = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_STRAP_STS1);
 		if (bs & DP83867_STRAP_STS1_RESERVED)
 			val &= ~DP83867_PHYCR_RESERVED_MASK;
 
@@ -243,8 +242,7 @@ static int dp83867_config_init(struct phy_device *phydev)
 
 	if ((phydev->interface >= PHY_INTERFACE_MODE_RGMII_ID) &&
 	    (phydev->interface <= PHY_INTERFACE_MODE_RGMII_RXID)) {
-		val = phy_read_mmd_indirect(phydev, DP83867_RGMIICTL,
-					    DP83867_DEVADDR);
+		val = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_RGMIICTL);
 
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID)
 			val |= (DP83867_RGMII_TX_CLK_DELAY_EN | DP83867_RGMII_RX_CLK_DELAY_EN);
@@ -255,25 +253,24 @@ static int dp83867_config_init(struct phy_device *phydev)
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID)
 			val |= DP83867_RGMII_RX_CLK_DELAY_EN;
 
-		phy_write_mmd_indirect(phydev, DP83867_RGMIICTL,
-				       DP83867_DEVADDR, val);
+		phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RGMIICTL, val);
 
 		delay = (dp83867->rx_id_delay |
 			(dp83867->tx_id_delay << DP83867_RGMII_TX_CLK_DELAY_SHIFT));
 
-		phy_write_mmd_indirect(phydev, DP83867_RGMIIDCTL,
-				       DP83867_DEVADDR, delay);
+		phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RGMIIDCTL,
+			      delay);
 
 		if (dp83867->io_impedance >= 0) {
-			val = phy_read_mmd_indirect(phydev, DP83867_IO_MUX_CFG,
-						    DP83867_DEVADDR);
+			val = phy_read_mmd(phydev, DP83867_DEVADDR,
+					   DP83867_IO_MUX_CFG);
 
 			val &= ~DP83867_IO_MUX_CFG_IO_IMPEDANCE_CTRL;
 			val |= dp83867->io_impedance &
 			       DP83867_IO_MUX_CFG_IO_IMPEDANCE_CTRL;
 
-			phy_write_mmd_indirect(phydev, DP83867_IO_MUX_CFG,
-					       DP83867_DEVADDR, val);
+			phy_write_mmd(phydev, DP83867_DEVADDR,
+				      DP83867_IO_MUX_CFG, val);
 		}
 	}
 
diff --git a/drivers/net/phy/intel-xway.c b/drivers/net/phy/intel-xway.c
index b1fd7bb0e4db..55f8c52dd2f1 100644
--- a/drivers/net/phy/intel-xway.c
+++ b/drivers/net/phy/intel-xway.c
@@ -166,13 +166,13 @@ static int xway_gphy_config_init(struct phy_device *phydev)
 	/* Clear all pending interrupts */
 	phy_read(phydev, XWAY_MDIO_ISTAT);
 
-	phy_write_mmd_indirect(phydev, XWAY_MMD_LEDCH, MDIO_MMD_VEND2,
-			       XWAY_MMD_LEDCH_NACS_NONE |
-			       XWAY_MMD_LEDCH_SBF_F02HZ |
-			       XWAY_MMD_LEDCH_FBF_F16HZ);
-	phy_write_mmd_indirect(phydev, XWAY_MMD_LEDCL, MDIO_MMD_VEND2,
-			       XWAY_MMD_LEDCH_CBLINK_NONE |
-			       XWAY_MMD_LEDCH_SCAN_NONE);
+	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LEDCH,
+		      XWAY_MMD_LEDCH_NACS_NONE |
+		      XWAY_MMD_LEDCH_SBF_F02HZ |
+		      XWAY_MMD_LEDCH_FBF_F16HZ);
+	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LEDCL,
+		      XWAY_MMD_LEDCH_CBLINK_NONE |
+		      XWAY_MMD_LEDCH_SCAN_NONE);
 
 	/**
 	 * In most cases only one LED is connected to this phy, so
@@ -183,12 +183,12 @@ static int xway_gphy_config_init(struct phy_device *phydev)
 	ledxh = XWAY_MMD_LEDxH_BLINKF_NONE | XWAY_MMD_LEDxH_CON_LINK10XX;
 	ledxl = XWAY_MMD_LEDxL_PULSE_TXACT | XWAY_MMD_LEDxL_PULSE_RXACT |
 		XWAY_MMD_LEDxL_BLINKS_NONE;
-	phy_write_mmd_indirect(phydev, XWAY_MMD_LED0H, MDIO_MMD_VEND2, ledxh);
-	phy_write_mmd_indirect(phydev, XWAY_MMD_LED0L, MDIO_MMD_VEND2, ledxl);
-	phy_write_mmd_indirect(phydev, XWAY_MMD_LED1H, MDIO_MMD_VEND2, ledxh);
-	phy_write_mmd_indirect(phydev, XWAY_MMD_LED1L, MDIO_MMD_VEND2, ledxl);
-	phy_write_mmd_indirect(phydev, XWAY_MMD_LED2H, MDIO_MMD_VEND2, ledxh);
-	phy_write_mmd_indirect(phydev, XWAY_MMD_LED2L, MDIO_MMD_VEND2, ledxl);
+	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED0H, ledxh);
+	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED0L, ledxl);
+	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED1H, ledxh);
+	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED1L, ledxl);
+	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED2H, ledxh);
+	phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED2L, ledxl);
 
 	return 0;
 }
diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/phy/mdio-bcm-unimac.c
index 8c73b2e771dd..34395230ce70 100644
--- a/drivers/net/phy/mdio-bcm-unimac.c
+++ b/drivers/net/phy/mdio-bcm-unimac.c
@@ -1,7 +1,7 @@
 /*
  * Broadcom UniMAC MDIO bus controller driver
  *
- * Copyright (C) 2014, Broadcom Corporation
+ * Copyright (C) 2014-2017 Broadcom
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -228,6 +228,7 @@ static int unimac_mdio_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id unimac_mdio_ids[] = {
+	{ .compatible = "brcm,genet-mdio-v5", },
 	{ .compatible = "brcm,genet-mdio-v4", },
 	{ .compatible = "brcm,genet-mdio-v3", },
 	{ .compatible = "brcm,genet-mdio-v2", },
diff --git a/drivers/net/phy/mdio-boardinfo.c b/drivers/net/phy/mdio-boardinfo.c
index 61941e29daae..1861f387820d 100644
--- a/drivers/net/phy/mdio-boardinfo.c
+++ b/drivers/net/phy/mdio-boardinfo.c
@@ -24,10 +24,12 @@ static DEFINE_MUTEX(mdio_board_lock);
  * @mdiodev: MDIO device pointer
  * Context: can sleep
  */
-void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus)
+void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus,
+					   int (*cb)
+					   (struct mii_bus *bus,
+					    struct mdio_board_info *bi))
 {
 	struct mdio_board_entry *be;
-	struct mdio_device *mdiodev;
 	struct mdio_board_info *bi;
 	int ret;
 
@@ -38,23 +40,14 @@ void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus)
 		if (strcmp(bus->id, bi->bus_id))
 			continue;
 
-		mdiodev = mdio_device_create(bus, bi->mdio_addr);
-		if (IS_ERR(mdiodev))
+		ret = cb(bus, bi);
+		if (ret)
 			continue;
 
-		strncpy(mdiodev->modalias, bi->modalias,
-			sizeof(mdiodev->modalias));
-		mdiodev->bus_match = mdio_device_bus_match;
-		mdiodev->dev.platform_data = (void *)bi->platform_data;
-
-		ret = mdio_device_register(mdiodev);
-		if (ret) {
-			mdio_device_free(mdiodev);
-			continue;
-		}
 	}
 	mutex_unlock(&mdio_board_lock);
 }
+EXPORT_SYMBOL(mdiobus_setup_mdiodev_from_board_info);
 
 /**
  * mdio_register_board_info - register MDIO devices for a given board
diff --git a/drivers/net/phy/mdio-boardinfo.h b/drivers/net/phy/mdio-boardinfo.h
index 00f98163e90e..3a7f143904e8 100644
--- a/drivers/net/phy/mdio-boardinfo.h
+++ b/drivers/net/phy/mdio-boardinfo.h
@@ -14,6 +14,9 @@ struct mdio_board_entry {
 	struct mdio_board_info	board_info;
 };
 
-void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus);
+void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus,
+					   int (*cb)
+					   (struct mii_bus *bus,
+					    struct mdio_board_info *bi));
 
 #endif /* __MDIO_BOARD_INFO_H */
diff --git a/drivers/net/phy/mdio-xgene.c b/drivers/net/phy/mdio-xgene.c
index f095051beb54..3e2ac07b6e37 100644
--- a/drivers/net/phy/mdio-xgene.c
+++ b/drivers/net/phy/mdio-xgene.c
@@ -229,7 +229,7 @@ static int xgene_xfi_mdio_write(struct mii_bus *bus, int phy_id,
 
 	val = SET_VAL(HSTPHYADX, phy_id) | SET_VAL(HSTREGADX, reg) |
 	      SET_VAL(HSTMIIMWRDAT, data);
-	xgene_enet_wr_mdio_csr(addr, MIIM_FIELD_ADDR, data);
+	xgene_enet_wr_mdio_csr(addr, MIIM_FIELD_ADDR, val);
 
 	val = HSTLDCMD | SET_VAL(HSTMIIMCMD, MIIM_CMD_LEGACY_WRITE);
 	xgene_enet_wr_mdio_csr(addr, MIIM_COMMAND_ADDR, val);
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index fa7d51f14869..5a214f3b8671 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -290,6 +290,36 @@ static inline void of_mdiobus_link_mdiodev(struct mii_bus *mdio,
 #endif
 
 /**
+ * mdiobus_create_device_from_board_info - create a full MDIO device given
+ * a mdio_board_info structure
+ * @bus: MDIO bus to create the devices on
+ * @bi: mdio_board_info structure describing the devices
+ *
+ * Returns 0 on success or < 0 on error.
+ */
+static int mdiobus_create_device(struct mii_bus *bus,
+				 struct mdio_board_info *bi)
+{
+	struct mdio_device *mdiodev;
+	int ret = 0;
+
+	mdiodev = mdio_device_create(bus, bi->mdio_addr);
+	if (IS_ERR(mdiodev))
+		return -ENODEV;
+
+	strncpy(mdiodev->modalias, bi->modalias,
+		sizeof(mdiodev->modalias));
+	mdiodev->bus_match = mdio_device_bus_match;
+	mdiodev->dev.platform_data = (void *)bi->platform_data;
+
+	ret = mdio_device_register(mdiodev);
+	if (ret)
+		mdio_device_free(mdiodev);
+
+	return ret;
+}
+
+/**
  * __mdiobus_register - bring up all the PHYs on a given bus and attach them to bus
  * @bus: target mii_bus
  * @owner: module containing bus accessor functions
@@ -345,7 +375,7 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner)
 		}
 	}
 
-	mdiobus_setup_mdiodev_from_board_info(bus);
+	mdiobus_setup_mdiodev_from_board_info(bus, mdiobus_create_device);
 
 	bus->state = MDIOBUS_REGISTERED;
 	pr_info("%s: probed\n", bus->name);
@@ -648,9 +678,18 @@ int __init mdio_bus_init(void)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(mdio_bus_init);
 
+#if IS_ENABLED(CONFIG_PHYLIB)
 void mdio_bus_exit(void)
 {
 	class_unregister(&mdio_bus_class);
 	bus_unregister(&mdio_bus_type);
 }
+EXPORT_SYMBOL_GPL(mdio_bus_exit);
+#else
+module_init(mdio_bus_init);
+/* no module_exit, intentional */
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MDIO bus/device layer");
+#endif
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 6742070ca676..b847184de6fc 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -637,8 +637,7 @@ static int ksz8873mll_config_aneg(struct phy_device *phydev)
  * MMD extended PHY registers.
  */
 static int
-ksz9021_rd_mmd_phyreg(struct phy_device *phydev, int ptrad, int devnum,
-		      int regnum)
+ksz9021_rd_mmd_phyreg(struct phy_device *phydev, int devad, u16 regnum)
 {
 	return -1;
 }
@@ -646,10 +645,10 @@ ksz9021_rd_mmd_phyreg(struct phy_device *phydev, int ptrad, int devnum,
 /* This routine does nothing since the Micrel ksz9021 does not support
  * standard IEEE MMD extended PHY registers.
  */
-static void
-ksz9021_wr_mmd_phyreg(struct phy_device *phydev, int ptrad, int devnum,
-		      int regnum, u32 val)
+static int
+ksz9021_wr_mmd_phyreg(struct phy_device *phydev, int devad, u16 regnum, u16 val)
 {
+	return -1;
 }
 
 static int kszphy_get_sset_count(struct phy_device *phydev)
@@ -962,8 +961,8 @@ static struct phy_driver ksphy_driver[] = {
 	.get_stats	= kszphy_get_stats,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
-	.read_mmd_indirect = ksz9021_rd_mmd_phyreg,
-	.write_mmd_indirect = ksz9021_wr_mmd_phyreg,
+	.read_mmd	= ksz9021_rd_mmd_phyreg,
+	.write_mmd	= ksz9021_wr_mmd_phyreg,
 }, {
 	.phy_id		= PHY_ID_KSZ9031,
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c
index 324fbf6ad8ff..2b2f543cf9f0 100644
--- a/drivers/net/phy/microchip.c
+++ b/drivers/net/phy/microchip.c
@@ -78,9 +78,8 @@ static int lan88xx_probe(struct phy_device *phydev)
 	priv->wolopts = 0;
 
 	/* these values can be used to identify internal PHY */
-	priv->chip_id = phy_read_mmd_indirect(phydev, LAN88XX_MMD3_CHIP_ID, 3);
-	priv->chip_rev = phy_read_mmd_indirect(phydev, LAN88XX_MMD3_CHIP_REV,
-					       3);
+	priv->chip_id = phy_read_mmd(phydev, 3, LAN88XX_MMD3_CHIP_ID);
+	priv->chip_rev = phy_read_mmd(phydev, 3, LAN88XX_MMD3_CHIP_REV);
 
 	phydev->priv = priv;
 
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
new file mode 100644
index 000000000000..357a4d0d7641
--- /dev/null
+++ b/drivers/net/phy/phy-core.c
@@ -0,0 +1,101 @@
+/*
+ * Core PHY library, taken from phy.c
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+#include <linux/export.h>
+#include <linux/phy.h>
+
+static void mmd_phy_indirect(struct mii_bus *bus, int phy_addr, int devad,
+			     u16 regnum)
+{
+	/* Write the desired MMD Devad */
+	bus->write(bus, phy_addr, MII_MMD_CTRL, devad);
+
+	/* Write the desired MMD register address */
+	bus->write(bus, phy_addr, MII_MMD_DATA, regnum);
+
+	/* Select the Function : DATA with no post increment */
+	bus->write(bus, phy_addr, MII_MMD_CTRL, devad | MII_MMD_CTRL_NOINCR);
+}
+
+/**
+ * phy_read_mmd - Convenience function for reading a register
+ * from an MMD on a given PHY.
+ * @phydev: The phy_device struct
+ * @devad: The MMD to read from (0..31)
+ * @regnum: The register on the MMD to read (0..65535)
+ *
+ * Same rules as for phy_read();
+ */
+int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum)
+{
+	int val;
+
+	if (regnum > (u16)~0 || devad > 32)
+		return -EINVAL;
+
+	if (phydev->drv->read_mmd) {
+		val = phydev->drv->read_mmd(phydev, devad, regnum);
+	} else if (phydev->is_c45) {
+		u32 addr = MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff);
+
+		val = mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, addr);
+	} else {
+		struct mii_bus *bus = phydev->mdio.bus;
+		int phy_addr = phydev->mdio.addr;
+
+		mutex_lock(&bus->mdio_lock);
+		mmd_phy_indirect(bus, phy_addr, devad, regnum);
+
+		/* Read the content of the MMD's selected register */
+		val = bus->read(bus, phy_addr, MII_MMD_DATA);
+		mutex_unlock(&bus->mdio_lock);
+	}
+	return val;
+}
+EXPORT_SYMBOL(phy_read_mmd);
+
+/**
+ * phy_write_mmd - Convenience function for writing a register
+ * on an MMD on a given PHY.
+ * @phydev: The phy_device struct
+ * @devad: The MMD to read from
+ * @regnum: The register on the MMD to read
+ * @val: value to write to @regnum
+ *
+ * Same rules as for phy_write();
+ */
+int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val)
+{
+	int ret;
+
+	if (regnum > (u16)~0 || devad > 32)
+		return -EINVAL;
+
+	if (phydev->drv->read_mmd) {
+		ret = phydev->drv->write_mmd(phydev, devad, regnum, val);
+	} else if (phydev->is_c45) {
+		u32 addr = MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff);
+
+		ret = mdiobus_write(phydev->mdio.bus, phydev->mdio.addr,
+				    addr, val);
+	} else {
+		struct mii_bus *bus = phydev->mdio.bus;
+		int phy_addr = phydev->mdio.addr;
+
+		mutex_lock(&bus->mdio_lock);
+		mmd_phy_indirect(bus, phy_addr, devad, regnum);
+
+		/* Write the data into MMD's selected register */
+		bus->write(bus, phy_addr, MII_MMD_DATA, val);
+		mutex_unlock(&bus->mdio_lock);
+
+		ret = 0;
+	}
+	return ret;
+}
+EXPORT_SYMBOL(phy_write_mmd);
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index a2bfc82e95d7..bf7d614ff18f 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -50,8 +50,22 @@ static const char *phy_speed_to_str(int speed)
 		return "1Gbps";
 	case SPEED_2500:
 		return "2.5Gbps";
+	case SPEED_5000:
+		return "5Gbps";
 	case SPEED_10000:
 		return "10Gbps";
+	case SPEED_20000:
+		return "20Gbps";
+	case SPEED_25000:
+		return "25Gbps";
+	case SPEED_40000:
+		return "40Gbps";
+	case SPEED_50000:
+		return "50Gbps";
+	case SPEED_56000:
+		return "56Gbps";
+	case SPEED_100000:
+		return "100Gbps";
 	case SPEED_UNKNOWN:
 		return "Unknown";
 	default:
@@ -1192,91 +1206,6 @@ void phy_mac_interrupt(struct phy_device *phydev, int new_link)
 }
 EXPORT_SYMBOL(phy_mac_interrupt);
 
-static inline void mmd_phy_indirect(struct mii_bus *bus, int prtad, int devad,
-				    int addr)
-{
-	/* Write the desired MMD Devad */
-	bus->write(bus, addr, MII_MMD_CTRL, devad);
-
-	/* Write the desired MMD register address */
-	bus->write(bus, addr, MII_MMD_DATA, prtad);
-
-	/* Select the Function : DATA with no post increment */
-	bus->write(bus, addr, MII_MMD_CTRL, (devad | MII_MMD_CTRL_NOINCR));
-}
-
-/**
- * phy_read_mmd_indirect - reads data from the MMD registers
- * @phydev: The PHY device bus
- * @prtad: MMD Address
- * @devad: MMD DEVAD
- *
- * Description: it reads data from the MMD registers (clause 22 to access to
- * clause 45) of the specified phy address.
- * To read these register we have:
- * 1) Write reg 13 // DEVAD
- * 2) Write reg 14 // MMD Address
- * 3) Write reg 13 // MMD Data Command for MMD DEVAD
- * 3) Read  reg 14 // Read MMD data
- */
-int phy_read_mmd_indirect(struct phy_device *phydev, int prtad, int devad)
-{
-	struct phy_driver *phydrv = phydev->drv;
-	int addr = phydev->mdio.addr;
-	int value = -1;
-
-	if (!phydrv->read_mmd_indirect) {
-		struct mii_bus *bus = phydev->mdio.bus;
-
-		mutex_lock(&bus->mdio_lock);
-		mmd_phy_indirect(bus, prtad, devad, addr);
-
-		/* Read the content of the MMD's selected register */
-		value = bus->read(bus, addr, MII_MMD_DATA);
-		mutex_unlock(&bus->mdio_lock);
-	} else {
-		value = phydrv->read_mmd_indirect(phydev, prtad, devad, addr);
-	}
-	return value;
-}
-EXPORT_SYMBOL(phy_read_mmd_indirect);
-
-/**
- * phy_write_mmd_indirect - writes data to the MMD registers
- * @phydev: The PHY device
- * @prtad: MMD Address
- * @devad: MMD DEVAD
- * @data: data to write in the MMD register
- *
- * Description: Write data from the MMD registers of the specified
- * phy address.
- * To write these register we have:
- * 1) Write reg 13 // DEVAD
- * 2) Write reg 14 // MMD Address
- * 3) Write reg 13 // MMD Data Command for MMD DEVAD
- * 3) Write reg 14 // Write MMD data
- */
-void phy_write_mmd_indirect(struct phy_device *phydev, int prtad,
-				   int devad, u32 data)
-{
-	struct phy_driver *phydrv = phydev->drv;
-	int addr = phydev->mdio.addr;
-
-	if (!phydrv->write_mmd_indirect) {
-		struct mii_bus *bus = phydev->mdio.bus;
-
-		mutex_lock(&bus->mdio_lock);
-		mmd_phy_indirect(bus, prtad, devad, addr);
-
-		/* Write the data into MMD's selected register */
-		bus->write(bus, addr, MII_MMD_DATA, data);
-		mutex_unlock(&bus->mdio_lock);
-	} else {
-		phydrv->write_mmd_indirect(phydev, prtad, devad, addr, data);
-	}
-}
-EXPORT_SYMBOL(phy_write_mmd_indirect);
-
 /**
  * phy_init_eee - init and check the EEE feature
  * @phydev: target phy_device struct
@@ -1293,15 +1222,8 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 		return -EIO;
 
 	/* According to 802.3az,the EEE is supported only in full duplex-mode.
-	 * Also EEE feature is active when core is operating with MII, GMII
-	 * or RGMII (all kinds). Internal PHYs are also allowed to proceed and
-	 * should return an error if they do not support EEE.
 	 */
-	if ((phydev->duplex == DUPLEX_FULL) &&
-	    ((phydev->interface == PHY_INTERFACE_MODE_MII) ||
-	    (phydev->interface == PHY_INTERFACE_MODE_GMII) ||
-	     phy_interface_is_rgmii(phydev) ||
-	     phy_is_internal(phydev))) {
+	if (phydev->duplex == DUPLEX_FULL) {
 		int eee_lp, eee_cap, eee_adv;
 		u32 lp, cap, adv;
 		int status;
@@ -1312,8 +1234,7 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 			return status;
 
 		/* First check if the EEE ability is supported */
-		eee_cap = phy_read_mmd_indirect(phydev, MDIO_PCS_EEE_ABLE,
-						MDIO_MMD_PCS);
+		eee_cap = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE);
 		if (eee_cap <= 0)
 			goto eee_exit_err;
 
@@ -1324,13 +1245,11 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 		/* Check which link settings negotiated and verify it in
 		 * the EEE advertising registers.
 		 */
-		eee_lp = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_LPABLE,
-					       MDIO_MMD_AN);
+		eee_lp = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_LPABLE);
 		if (eee_lp <= 0)
 			goto eee_exit_err;
 
-		eee_adv = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_ADV,
-						MDIO_MMD_AN);
+		eee_adv = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV);
 		if (eee_adv <= 0)
 			goto eee_exit_err;
 
@@ -1343,14 +1262,12 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 			/* Configure the PHY to stop receiving xMII
 			 * clock while it is signaling LPI.
 			 */
-			int val = phy_read_mmd_indirect(phydev, MDIO_CTRL1,
-							MDIO_MMD_PCS);
+			int val = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
 			if (val < 0)
 				return val;
 
 			val |= MDIO_PCS_CTRL1_CLKSTOP_EN;
-			phy_write_mmd_indirect(phydev, MDIO_CTRL1,
-					       MDIO_MMD_PCS, val);
+			phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, val);
 		}
 
 		return 0; /* EEE supported */
@@ -1372,7 +1289,7 @@ int phy_get_eee_err(struct phy_device *phydev)
 	if (!phydev->drv)
 		return -EIO;
 
-	return phy_read_mmd_indirect(phydev, MDIO_PCS_EEE_WK_ERR, MDIO_MMD_PCS);
+	return phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_WK_ERR);
 }
 EXPORT_SYMBOL(phy_get_eee_err);
 
@@ -1392,19 +1309,19 @@ int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data)
 		return -EIO;
 
 	/* Get Supported EEE */
-	val = phy_read_mmd_indirect(phydev, MDIO_PCS_EEE_ABLE, MDIO_MMD_PCS);
+	val = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE);
 	if (val < 0)
 		return val;
 	data->supported = mmd_eee_cap_to_ethtool_sup_t(val);
 
 	/* Get advertisement EEE */
-	val = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_ADV, MDIO_MMD_AN);
+	val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV);
 	if (val < 0)
 		return val;
 	data->advertised = mmd_eee_adv_to_ethtool_adv_t(val);
 
 	/* Get LP advertisement EEE */
-	val = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_LPABLE, MDIO_MMD_AN);
+	val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_LPABLE);
 	if (val < 0)
 		return val;
 	data->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(val);
@@ -1422,15 +1339,37 @@ EXPORT_SYMBOL(phy_ethtool_get_eee);
  */
 int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data)
 {
-	int val = ethtool_adv_to_mmd_eee_adv_t(data->advertised);
+	int cap, old_adv, adv, ret;
 
 	if (!phydev->drv)
 		return -EIO;
 
+	/* Get Supported EEE */
+	cap = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE);
+	if (cap < 0)
+		return cap;
+
+	old_adv = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV);
+	if (old_adv < 0)
+		return old_adv;
+
+	adv = ethtool_adv_to_mmd_eee_adv_t(data->advertised) & cap;
+
 	/* Mask prohibited EEE modes */
-	val &= ~phydev->eee_broken_modes;
+	adv &= ~phydev->eee_broken_modes;
+
+	if (old_adv != adv) {
+		ret = phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, adv);
+		if (ret < 0)
+			return ret;
 
-	phy_write_mmd_indirect(phydev, MDIO_AN_EEE_ADV, MDIO_MMD_AN, val);
+		/* Restart autonegotiation so the new modes get sent to the
+		 * link partner.
+		 */
+		ret = genphy_restart_aneg(phydev);
+		if (ret < 0)
+			return ret;
+	}
 
 	return 0;
 }
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 5198ccfa347f..1219eeab69d1 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1217,7 +1217,7 @@ static int genphy_config_eee_advert(struct phy_device *phydev)
 	 * supported by the phy. If we read 0, EEE is not advertised
 	 * In both case, we don't need to continue
 	 */
-	adv = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_ADV, MDIO_MMD_AN);
+	adv = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV);
 	if (adv <= 0)
 		return 0;
 
@@ -1228,7 +1228,7 @@ static int genphy_config_eee_advert(struct phy_device *phydev)
 	if (old_adv == adv)
 		return 0;
 
-	phy_write_mmd_indirect(phydev, MDIO_AN_EEE_ADV, MDIO_MMD_AN, adv);
+	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, adv);
 
 	return 1;
 }
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index fb32eaf2255d..cef6967b0396 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -20,6 +20,7 @@
 #include <linux/module.h>
 #include <linux/mii.h>
 #include <linux/ethtool.h>
+#include <linux/of.h>
 #include <linux/phy.h>
 #include <linux/netdevice.h>
 #include <linux/smscphy.h>
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index cc88cd7856f5..bbd707b9ef7a 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2444,18 +2444,16 @@ static struct miscdevice tun_miscdev = {
 
 /* ethtool interface */
 
-static int tun_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	cmd->supported		= 0;
-	cmd->advertising	= 0;
-	ethtool_cmd_speed_set(cmd, SPEED_10);
-	cmd->duplex		= DUPLEX_FULL;
-	cmd->port		= PORT_TP;
-	cmd->phy_address	= 0;
-	cmd->transceiver	= XCVR_INTERNAL;
-	cmd->autoneg		= AUTONEG_DISABLE;
-	cmd->maxtxpkt		= 0;
-	cmd->maxrxpkt		= 0;
+static int tun_get_link_ksettings(struct net_device *dev,
+				  struct ethtool_link_ksettings *cmd)
+{
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+	cmd->base.speed		= SPEED_10;
+	cmd->base.duplex	= DUPLEX_FULL;
+	cmd->base.port		= PORT_TP;
+	cmd->base.phy_address	= 0;
+	cmd->base.autoneg	= AUTONEG_DISABLE;
 	return 0;
 }
 
@@ -2518,7 +2516,6 @@ static int tun_set_coalesce(struct net_device *dev,
 }
 
 static const struct ethtool_ops tun_ethtool_ops = {
-	.get_settings	= tun_get_settings,
 	.get_drvinfo	= tun_get_drvinfo,
 	.get_msglevel	= tun_get_msglevel,
 	.set_msglevel	= tun_set_msglevel,
@@ -2526,6 +2523,7 @@ static const struct ethtool_ops tun_ethtool_ops = {
 	.get_ts_info	= ethtool_op_get_ts_info,
 	.get_coalesce   = tun_get_coalesce,
 	.set_coalesce   = tun_set_coalesce,
+	.get_link_ksettings = tun_get_link_ksettings,
 };
 
 static int tun_queue_resize(struct tun_struct *tun)
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 0dd510604118..a3aa0a27dfe5 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -136,9 +136,9 @@ static const struct ethtool_ops ax88172_ethtool_ops = {
 	.get_eeprom_len		= asix_get_eeprom_len,
 	.get_eeprom		= asix_get_eeprom,
 	.set_eeprom		= asix_set_eeprom,
-	.get_settings		= usbnet_get_settings,
-	.set_settings		= usbnet_set_settings,
 	.nway_reset		= usbnet_nway_reset,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 static void ax88172_set_multicast(struct net_device *net)
@@ -206,6 +206,7 @@ static const struct net_device_ops ax88172_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= asix_ioctl,
@@ -301,9 +302,9 @@ static const struct ethtool_ops ax88772_ethtool_ops = {
 	.get_eeprom_len		= asix_get_eeprom_len,
 	.get_eeprom		= asix_get_eeprom,
 	.set_eeprom		= asix_set_eeprom,
-	.get_settings		= usbnet_get_settings,
-	.set_settings		= usbnet_set_settings,
 	.nway_reset		= usbnet_nway_reset,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 static int ax88772_link_reset(struct usbnet *dev)
@@ -591,6 +592,7 @@ static const struct net_device_ops ax88772_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address 	= asix_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= asix_ioctl,
@@ -775,9 +777,9 @@ static const struct ethtool_ops ax88178_ethtool_ops = {
 	.get_eeprom_len		= asix_get_eeprom_len,
 	.get_eeprom		= asix_get_eeprom,
 	.set_eeprom		= asix_set_eeprom,
-	.get_settings		= usbnet_get_settings,
-	.set_settings		= usbnet_set_settings,
 	.nway_reset		= usbnet_nway_reset,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 static int marvell_phy_init(struct usbnet *dev)
@@ -1044,6 +1046,7 @@ static const struct net_device_ops ax88178_netdev_ops = {
 	.ndo_stop		= usbnet_stop,
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address 	= asix_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= asix_set_multicast,
diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index 6308386b09df..501576f53854 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -143,6 +143,7 @@ static const struct net_device_ops ax88172a_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address	= asix_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= ax88172a_ioctl,
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index a3a7db0702d8..51cf60092a18 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -620,16 +620,18 @@ ax88179_get_eeprom(struct net_device *net, struct ethtool_eeprom *eeprom,
 	return 0;
 }
 
-static int ax88179_get_settings(struct net_device *net, struct ethtool_cmd *cmd)
+static int ax88179_get_link_ksettings(struct net_device *net,
+				      struct ethtool_link_ksettings *cmd)
 {
 	struct usbnet *dev = netdev_priv(net);
-	return mii_ethtool_gset(&dev->mii, cmd);
+	return mii_ethtool_get_link_ksettings(&dev->mii, cmd);
 }
 
-static int ax88179_set_settings(struct net_device *net, struct ethtool_cmd *cmd)
+static int ax88179_set_link_ksettings(struct net_device *net,
+				      const struct ethtool_link_ksettings *cmd)
 {
 	struct usbnet *dev = netdev_priv(net);
-	return mii_ethtool_sset(&dev->mii, cmd);
+	return mii_ethtool_set_link_ksettings(&dev->mii, cmd);
 }
 
 static int
@@ -826,11 +828,11 @@ static const struct ethtool_ops ax88179_ethtool_ops = {
 	.set_wol		= ax88179_set_wol,
 	.get_eeprom_len		= ax88179_get_eeprom_len,
 	.get_eeprom		= ax88179_get_eeprom,
-	.get_settings		= ax88179_get_settings,
-	.set_settings		= ax88179_set_settings,
 	.get_eee		= ax88179_get_eee,
 	.set_eee		= ax88179_set_eee,
 	.nway_reset		= usbnet_nway_reset,
+	.get_link_ksettings	= ax88179_get_link_ksettings,
+	.set_link_ksettings	= ax88179_set_link_ksettings,
 };
 
 static void ax88179_set_multicast(struct net_device *net)
@@ -957,6 +959,7 @@ static const struct net_device_ops ax88179_netdev_ops = {
 	.ndo_stop		= usbnet_stop,
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_change_mtu		= ax88179_change_mtu,
 	.ndo_set_mac_address	= ax88179_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index 0acc9b640419..fce92f0e5abd 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -688,29 +688,34 @@ static void catc_get_drvinfo(struct net_device *dev,
 	usb_make_path(catc->usbdev, info->bus_info, sizeof(info->bus_info));
 }
 
-static int catc_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int catc_get_link_ksettings(struct net_device *dev,
+				   struct ethtool_link_ksettings *cmd)
 {
 	struct catc *catc = netdev_priv(dev);
 	if (!catc->is_f5u011)
 		return -EOPNOTSUPP;
 
-	cmd->supported = SUPPORTED_10baseT_Half | SUPPORTED_TP;
-	cmd->advertising = ADVERTISED_10baseT_Half | ADVERTISED_TP;
-	ethtool_cmd_speed_set(cmd, SPEED_10);
-	cmd->duplex = DUPLEX_HALF;
-	cmd->port = PORT_TP; 
-	cmd->phy_address = 0;
-	cmd->transceiver = XCVR_INTERNAL;
-	cmd->autoneg = AUTONEG_DISABLE;
-	cmd->maxtxpkt = 1;
-	cmd->maxrxpkt = 1;
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Half);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, TP);
+
+	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Half);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, TP);
+
+	cmd->base.speed = SPEED_10;
+	cmd->base.duplex = DUPLEX_HALF;
+	cmd->base.port = PORT_TP;
+	cmd->base.phy_address = 0;
+	cmd->base.autoneg = AUTONEG_DISABLE;
+
 	return 0;
 }
 
 static const struct ethtool_ops ops = {
 	.get_drvinfo = catc_get_drvinfo,
-	.get_settings = catc_get_settings,
-	.get_link = ethtool_op_get_link
+	.get_link = ethtool_op_get_link,
+	.get_link_ksettings = catc_get_link_ksettings,
 };
 
 /*
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 3a98f3762a4c..a6b997cffd3b 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -100,6 +100,7 @@ static const struct net_device_ops cdc_mbim_netdev_ops = {
 	.ndo_stop             = usbnet_stop,
 	.ndo_start_xmit       = usbnet_start_xmit,
 	.ndo_tx_timeout       = usbnet_tx_timeout,
+	.ndo_get_stats64      = usbnet_get_stats64,
 	.ndo_change_mtu       = cdc_ncm_change_mtu,
 	.ndo_set_mac_address  = eth_mac_addr,
 	.ndo_validate_addr    = eth_validate_addr,
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index f317984f7536..bb3f71f9fbde 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -131,8 +131,6 @@ static void cdc_ncm_get_strings(struct net_device __always_unused *netdev, u32 s
 static void cdc_ncm_update_rxtx_max(struct usbnet *dev, u32 new_rx, u32 new_tx);
 
 static const struct ethtool_ops cdc_ncm_ethtool_ops = {
-	.get_settings      = usbnet_get_settings,
-	.set_settings      = usbnet_set_settings,
 	.get_link          = usbnet_get_link,
 	.nway_reset        = usbnet_nway_reset,
 	.get_drvinfo       = usbnet_get_drvinfo,
@@ -142,6 +140,8 @@ static const struct ethtool_ops cdc_ncm_ethtool_ops = {
 	.get_sset_count    = cdc_ncm_get_sset_count,
 	.get_strings       = cdc_ncm_get_strings,
 	.get_ethtool_stats = cdc_ncm_get_ethtool_stats,
+	.get_link_ksettings      = usbnet_get_link_ksettings,
+	.set_link_ksettings      = usbnet_set_link_ksettings,
 };
 
 static u32 cdc_ncm_check_rx_max(struct usbnet *dev, u32 new_rx)
@@ -753,6 +753,7 @@ static const struct net_device_ops cdc_ncm_netdev_ops = {
 	.ndo_stop	     = usbnet_stop,
 	.ndo_start_xmit	     = usbnet_start_xmit,
 	.ndo_tx_timeout	     = usbnet_tx_timeout,
+	.ndo_get_stats64     = usbnet_get_stats64,
 	.ndo_change_mtu	     = cdc_ncm_change_mtu,
 	.ndo_set_mac_address = eth_mac_addr,
 	.ndo_validate_addr   = eth_validate_addr,
diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index 0b4bdd39106b..b91f92e4e5f2 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -281,9 +281,9 @@ static const struct ethtool_ops dm9601_ethtool_ops = {
 	.set_msglevel	= usbnet_set_msglevel,
 	.get_eeprom_len	= dm9601_get_eeprom_len,
 	.get_eeprom	= dm9601_get_eeprom,
-	.get_settings	= usbnet_get_settings,
-	.set_settings	= usbnet_set_settings,
 	.nway_reset	= usbnet_nway_reset,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 static void dm9601_set_multicast(struct net_device *net)
@@ -343,6 +343,7 @@ static const struct net_device_ops dm9601_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl 		= dm9601_ioctl,
 	.ndo_set_rx_mode	= dm9601_set_multicast,
diff --git a/drivers/net/usb/int51x1.c b/drivers/net/usb/int51x1.c
index 4ff70b22c6ee..5a43b77a6b9c 100644
--- a/drivers/net/usb/int51x1.c
+++ b/drivers/net/usb/int51x1.c
@@ -144,6 +144,7 @@ static const struct net_device_ops int51x1_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= int51x1_set_multicast,
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 9889a70ff4f6..a17e32bf5f92 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -29,6 +29,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/mdio.h>
+#include <linux/phy.h>
 #include <net/ip6_checksum.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
@@ -1952,10 +1953,10 @@ static int lan8835_fixup(struct phy_device *phydev)
 	struct lan78xx_net *dev = netdev_priv(phydev->attached_dev);
 
 	/* LED2/PME_N/IRQ_N/RGMII_ID pin to IRQ_N mode */
-	buf = phy_read_mmd_indirect(phydev, 0x8010, 3);
+	buf = phy_read_mmd(phydev, MDIO_MMD_PCS, 0x8010);
 	buf &= ~0x1800;
 	buf |= 0x0800;
-	phy_write_mmd_indirect(phydev, 0x8010, 3, buf);
+	phy_write_mmd(phydev, MDIO_MMD_PCS, 0x8010, buf);
 
 	/* RGMII MAC TXC Delay Enable */
 	ret = lan78xx_write_reg(dev, MAC_RGMII_ID,
@@ -1975,11 +1976,11 @@ static int ksz9031rnx_fixup(struct phy_device *phydev)
 
 	/* Micrel9301RNX PHY configuration */
 	/* RGMII Control Signal Pad Skew */
-	phy_write_mmd_indirect(phydev, 4, 2, 0x0077);
+	phy_write_mmd(phydev, MDIO_MMD_WIS, 4, 0x0077);
 	/* RGMII RX Data Pad Skew */
-	phy_write_mmd_indirect(phydev, 5, 2, 0x7777);
+	phy_write_mmd(phydev, MDIO_MMD_WIS, 5, 0x7777);
 	/* RGMII RX Clock Pad Skew */
-	phy_write_mmd_indirect(phydev, 8, 2, 0x1FF);
+	phy_write_mmd(phydev, MDIO_MMD_WIS, 8, 0x1FF);
 
 	dev->interface = PHY_INTERFACE_MODE_RGMII_RXID;
 
diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c
index 4f345bd4e6e2..5a47e5510ca8 100644
--- a/drivers/net/usb/mcs7830.c
+++ b/drivers/net/usb/mcs7830.c
@@ -464,9 +464,9 @@ static const struct ethtool_ops mcs7830_ethtool_ops = {
 	.get_link		= usbnet_get_link,
 	.get_msglevel		= usbnet_get_msglevel,
 	.set_msglevel		= usbnet_set_msglevel,
-	.get_settings		= usbnet_get_settings,
-	.set_settings		= usbnet_set_settings,
 	.nway_reset		= usbnet_nway_reset,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 static const struct net_device_ops mcs7830_netdev_ops = {
@@ -475,6 +475,7 @@ static const struct net_device_ops mcs7830_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl 		= mcs7830_ioctl,
 	.ndo_set_rx_mode	= mcs7830_set_multicast,
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 36674484c6fb..321e059e13ae 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -953,20 +953,22 @@ static inline void pegasus_reset_wol(struct net_device *dev)
 }
 
 static int
-pegasus_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+pegasus_get_link_ksettings(struct net_device *dev,
+			   struct ethtool_link_ksettings *ecmd)
 {
 	pegasus_t *pegasus;
 
 	pegasus = netdev_priv(dev);
-	mii_ethtool_gset(&pegasus->mii, ecmd);
+	mii_ethtool_get_link_ksettings(&pegasus->mii, ecmd);
 	return 0;
 }
 
 static int
-pegasus_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+pegasus_set_link_ksettings(struct net_device *dev,
+			   const struct ethtool_link_ksettings *ecmd)
 {
 	pegasus_t *pegasus = netdev_priv(dev);
-	return mii_ethtool_sset(&pegasus->mii, ecmd);
+	return mii_ethtool_set_link_ksettings(&pegasus->mii, ecmd);
 }
 
 static int pegasus_nway_reset(struct net_device *dev)
@@ -995,14 +997,14 @@ static void pegasus_set_msglevel(struct net_device *dev, u32 v)
 
 static const struct ethtool_ops ops = {
 	.get_drvinfo = pegasus_get_drvinfo,
-	.get_settings = pegasus_get_settings,
-	.set_settings = pegasus_set_settings,
 	.nway_reset = pegasus_nway_reset,
 	.get_link = pegasus_get_link,
 	.get_msglevel = pegasus_get_msglevel,
 	.set_msglevel = pegasus_set_msglevel,
 	.get_wol = pegasus_get_wol,
 	.set_wol = pegasus_set_wol,
+	.get_link_ksettings = pegasus_get_link_ksettings,
+	.set_link_ksettings = pegasus_set_link_ksettings,
 };
 
 static int pegasus_ioctl(struct net_device *net, struct ifreq *rq, int cmd)
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 156f7f85e486..adbed261cc8a 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -58,12 +58,198 @@ struct qmi_wwan_state {
 
 enum qmi_wwan_flags {
 	QMI_WWAN_FLAG_RAWIP = 1 << 0,
+	QMI_WWAN_FLAG_MUX = 1 << 1,
 };
 
 enum qmi_wwan_quirks {
 	QMI_WWAN_QUIRK_DTR = 1 << 0,	/* needs "set DTR" request */
 };
 
+struct qmimux_hdr {
+	u8 pad;
+	u8 mux_id;
+	__be16 pkt_len;
+};
+
+struct qmimux_priv {
+	struct net_device *real_dev;
+	u8 mux_id;
+};
+
+static int qmimux_open(struct net_device *dev)
+{
+	struct qmimux_priv *priv = netdev_priv(dev);
+	struct net_device *real_dev = priv->real_dev;
+
+	if (!(priv->real_dev->flags & IFF_UP))
+		return -ENETDOWN;
+
+	if (netif_carrier_ok(real_dev))
+		netif_carrier_on(dev);
+	return 0;
+}
+
+static int qmimux_stop(struct net_device *dev)
+{
+	netif_carrier_off(dev);
+	return 0;
+}
+
+static netdev_tx_t qmimux_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct qmimux_priv *priv = netdev_priv(dev);
+	unsigned int len = skb->len;
+	struct qmimux_hdr *hdr;
+
+	hdr = (struct qmimux_hdr *)skb_push(skb, sizeof(struct qmimux_hdr));
+	hdr->pad = 0;
+	hdr->mux_id = priv->mux_id;
+	hdr->pkt_len = cpu_to_be16(len);
+	skb->dev = priv->real_dev;
+	return dev_queue_xmit(skb);
+}
+
+static const struct net_device_ops qmimux_netdev_ops = {
+	.ndo_open       = qmimux_open,
+	.ndo_stop       = qmimux_stop,
+	.ndo_start_xmit = qmimux_start_xmit,
+};
+
+static void qmimux_setup(struct net_device *dev)
+{
+	dev->header_ops      = NULL;  /* No header */
+	dev->type            = ARPHRD_NONE;
+	dev->hard_header_len = 0;
+	dev->addr_len        = 0;
+	dev->flags           = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
+	dev->netdev_ops      = &qmimux_netdev_ops;
+	dev->destructor      = free_netdev;
+}
+
+static struct net_device *qmimux_find_dev(struct usbnet *dev, u8 mux_id)
+{
+	struct qmimux_priv *priv;
+	struct list_head *iter;
+	struct net_device *ldev;
+
+	rcu_read_lock();
+	netdev_for_each_upper_dev_rcu(dev->net, ldev, iter) {
+		priv = netdev_priv(ldev);
+		if (priv->mux_id == mux_id) {
+			rcu_read_unlock();
+			return ldev;
+		}
+	}
+	rcu_read_unlock();
+	return NULL;
+}
+
+static bool qmimux_has_slaves(struct usbnet *dev)
+{
+	return !list_empty(&dev->net->adj_list.upper);
+}
+
+static int qmimux_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
+{
+	unsigned int len, offset = sizeof(struct qmimux_hdr);
+	struct qmimux_hdr *hdr;
+	struct net_device *net;
+	struct sk_buff *skbn;
+
+	while (offset < skb->len) {
+		hdr = (struct qmimux_hdr *)skb->data;
+		len = be16_to_cpu(hdr->pkt_len);
+
+		/* drop the packet, bogus length */
+		if (offset + len > skb->len)
+			return 0;
+
+		/* control packet, we do not know what to do */
+		if (hdr->pad & 0x80)
+			goto skip;
+
+		net = qmimux_find_dev(dev, hdr->mux_id);
+		if (!net)
+			goto skip;
+		skbn = netdev_alloc_skb(net, len);
+		if (!skbn)
+			return 0;
+		skbn->dev = net;
+
+		switch (skb->data[offset] & 0xf0) {
+		case 0x40:
+			skbn->protocol = htons(ETH_P_IP);
+			break;
+		case 0x60:
+			skbn->protocol = htons(ETH_P_IPV6);
+			break;
+		default:
+			/* not ip - do not know what to do */
+			goto skip;
+		}
+
+		memcpy(skb_put(skbn, len), skb->data + offset, len);
+		if (netif_rx(skbn) != NET_RX_SUCCESS)
+			return 0;
+
+skip:
+		offset += len + sizeof(struct qmimux_hdr);
+	}
+	return 1;
+}
+
+static int qmimux_register_device(struct net_device *real_dev, u8 mux_id)
+{
+	struct net_device *new_dev;
+	struct qmimux_priv *priv;
+	int err;
+
+	new_dev = alloc_netdev(sizeof(struct qmimux_priv),
+			       "qmimux%d", NET_NAME_UNKNOWN, qmimux_setup);
+	if (!new_dev)
+		return -ENOBUFS;
+
+	dev_net_set(new_dev, dev_net(real_dev));
+	priv = netdev_priv(new_dev);
+	priv->mux_id = mux_id;
+	priv->real_dev = real_dev;
+
+	err = register_netdevice(new_dev);
+	if (err < 0)
+		goto out_free_newdev;
+
+	/* Account for reference in struct qmimux_priv_priv */
+	dev_hold(real_dev);
+
+	err = netdev_upper_dev_link(real_dev, new_dev);
+	if (err)
+		goto out_unregister_netdev;
+
+	netif_stacked_transfer_operstate(real_dev, new_dev);
+
+	return 0;
+
+out_unregister_netdev:
+	unregister_netdevice(new_dev);
+	dev_put(real_dev);
+
+out_free_newdev:
+	free_netdev(new_dev);
+	return err;
+}
+
+static void qmimux_unregister_device(struct net_device *dev)
+{
+	struct qmimux_priv *priv = netdev_priv(dev);
+	struct net_device *real_dev = priv->real_dev;
+
+	netdev_upper_dev_unlink(real_dev, dev);
+	unregister_netdevice(dev);
+
+	/* Get rid of the reference to real_dev */
+	dev_put(real_dev);
+}
+
 static void qmi_wwan_netdev_setup(struct net_device *net)
 {
 	struct usbnet *dev = netdev_priv(net);
@@ -137,10 +323,114 @@ err:
 	return ret;
 }
 
+static ssize_t add_mux_show(struct device *d, struct device_attribute *attr, char *buf)
+{
+	struct net_device *dev = to_net_dev(d);
+	struct qmimux_priv *priv;
+	struct list_head *iter;
+	struct net_device *ldev;
+	ssize_t count = 0;
+
+	rcu_read_lock();
+	netdev_for_each_upper_dev_rcu(dev, ldev, iter) {
+		priv = netdev_priv(ldev);
+		count += scnprintf(&buf[count], PAGE_SIZE - count,
+				   "0x%02x\n", priv->mux_id);
+	}
+	rcu_read_unlock();
+	return count;
+}
+
+static ssize_t add_mux_store(struct device *d,  struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct usbnet *dev = netdev_priv(to_net_dev(d));
+	struct qmi_wwan_state *info = (void *)&dev->data;
+	u8 mux_id;
+	int ret;
+
+	if (kstrtou8(buf, 0, &mux_id))
+		return -EINVAL;
+
+	/* mux_id [1 - 0x7f] range empirically found */
+	if (mux_id < 1 || mux_id > 0x7f)
+		return -EINVAL;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	if (qmimux_find_dev(dev, mux_id)) {
+		netdev_err(dev->net, "mux_id already present\n");
+		ret = -EINVAL;
+		goto err;
+	}
+
+	/* we don't want to modify a running netdev */
+	if (netif_running(dev->net)) {
+		netdev_err(dev->net, "Cannot change a running device\n");
+		ret = -EBUSY;
+		goto err;
+	}
+
+	ret = qmimux_register_device(dev->net, mux_id);
+	if (!ret) {
+		info->flags |= QMI_WWAN_FLAG_MUX;
+		ret = len;
+	}
+err:
+	rtnl_unlock();
+	return ret;
+}
+
+static ssize_t del_mux_show(struct device *d, struct device_attribute *attr, char *buf)
+{
+	return add_mux_show(d, attr, buf);
+}
+
+static ssize_t del_mux_store(struct device *d,  struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct usbnet *dev = netdev_priv(to_net_dev(d));
+	struct qmi_wwan_state *info = (void *)&dev->data;
+	struct net_device *del_dev;
+	u8 mux_id;
+	int ret = 0;
+
+	if (kstrtou8(buf, 0, &mux_id))
+		return -EINVAL;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	/* we don't want to modify a running netdev */
+	if (netif_running(dev->net)) {
+		netdev_err(dev->net, "Cannot change a running device\n");
+		ret = -EBUSY;
+		goto err;
+	}
+
+	del_dev = qmimux_find_dev(dev, mux_id);
+	if (!del_dev) {
+		netdev_err(dev->net, "mux_id not present\n");
+		ret = -EINVAL;
+		goto err;
+	}
+	qmimux_unregister_device(del_dev);
+
+	if (!qmimux_has_slaves(dev))
+		info->flags &= ~QMI_WWAN_FLAG_MUX;
+	ret = len;
+err:
+	rtnl_unlock();
+	return ret;
+}
+
 static DEVICE_ATTR_RW(raw_ip);
+static DEVICE_ATTR_RW(add_mux);
+static DEVICE_ATTR_RW(del_mux);
 
 static struct attribute *qmi_wwan_sysfs_attrs[] = {
 	&dev_attr_raw_ip.attr,
+	&dev_attr_add_mux.attr,
+	&dev_attr_del_mux.attr,
 	NULL,
 };
 
@@ -184,6 +474,9 @@ static int qmi_wwan_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 	if (skb->len < dev->net->hard_header_len)
 		return 0;
 
+	if (info->flags & QMI_WWAN_FLAG_MUX)
+		return qmimux_rx_fixup(dev, skb);
+
 	switch (skb->data[0] & 0xf0) {
 	case 0x40:
 		proto = htons(ETH_P_IP);
@@ -249,6 +542,7 @@ static const struct net_device_ops qmi_wwan_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address	= qmi_wwan_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 };
@@ -1036,11 +1330,33 @@ static int qmi_wwan_probe(struct usb_interface *intf,
 	return usbnet_probe(intf, id);
 }
 
+static void qmi_wwan_disconnect(struct usb_interface *intf)
+{
+	struct usbnet *dev = usb_get_intfdata(intf);
+	struct qmi_wwan_state *info = (void *)&dev->data;
+	struct list_head *iter;
+	struct net_device *ldev;
+
+	if (info->flags & QMI_WWAN_FLAG_MUX) {
+		if (!rtnl_trylock()) {
+			restart_syscall();
+			return;
+		}
+		rcu_read_lock();
+		netdev_for_each_upper_dev_rcu(dev->net, ldev, iter)
+			qmimux_unregister_device(ldev);
+		rcu_read_unlock();
+		rtnl_unlock();
+		info->flags &= ~QMI_WWAN_FLAG_MUX;
+	}
+	usbnet_disconnect(intf);
+}
+
 static struct usb_driver qmi_wwan_driver = {
 	.name		      = "qmi_wwan",
 	.id_table	      = products,
 	.probe		      = qmi_wwan_probe,
-	.disconnect	      = usbnet_disconnect,
+	.disconnect	      = qmi_wwan_disconnect,
 	.suspend	      = qmi_wwan_suspend,
 	.resume		      =	qmi_wwan_resume,
 	.reset_resume         = qmi_wwan_resume,
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 07f788c49d57..ddc62cb69be8 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1766,6 +1766,7 @@ static int rx_bottom(struct r8152 *tp, int budget)
 	unsigned long flags;
 	struct list_head *cursor, *next, rx_queue;
 	int ret = 0, work_done = 0;
+	struct napi_struct *napi = &tp->napi;
 
 	if (!skb_queue_empty(&tp->rx_queue)) {
 		while (work_done < budget) {
@@ -1778,7 +1779,7 @@ static int rx_bottom(struct r8152 *tp, int budget)
 				break;
 
 			pkt_len = skb->len;
-			napi_gro_receive(&tp->napi, skb);
+			napi_gro_receive(napi, skb);
 			work_done++;
 			stats->rx_packets++;
 			stats->rx_bytes += pkt_len;
@@ -1828,7 +1829,7 @@ static int rx_bottom(struct r8152 *tp, int budget)
 			pkt_len -= CRC_SIZE;
 			rx_data += sizeof(struct rx_desc);
 
-			skb = napi_alloc_skb(&tp->napi, pkt_len);
+			skb = napi_alloc_skb(napi, pkt_len);
 			if (!skb) {
 				stats->rx_dropped++;
 				goto find_next_rx;
@@ -1840,7 +1841,7 @@ static int rx_bottom(struct r8152 *tp, int budget)
 			skb->protocol = eth_type_trans(skb, netdev);
 			rtl_rx_vlan_tag(rx_desc, skb);
 			if (work_done < budget) {
-				napi_gro_receive(&tp->napi, skb);
+				napi_gro_receive(napi, skb);
 				work_done++;
 				stats->rx_packets++;
 				stats->rx_bytes += pkt_len;
@@ -3156,6 +3157,7 @@ static bool rtl8153_in_nway(struct r8152 *tp)
 static void set_carrier(struct r8152 *tp)
 {
 	struct net_device *netdev = tp->netdev;
+	struct napi_struct *napi = &tp->napi;
 	u8 speed;
 
 	speed = rtl8152_get_speed(tp);
@@ -3165,7 +3167,7 @@ static void set_carrier(struct r8152 *tp)
 			tp->rtl_ops.enable(tp);
 			set_bit(RTL8152_SET_RX_MODE, &tp->flags);
 			netif_stop_queue(netdev);
-			napi_disable(&tp->napi);
+			napi_disable(napi);
 			netif_carrier_on(netdev);
 			rtl_start_rx(tp);
 			napi_enable(&tp->napi);
@@ -3178,9 +3180,9 @@ static void set_carrier(struct r8152 *tp)
 	} else {
 		if (netif_carrier_ok(netdev)) {
 			netif_carrier_off(netdev);
-			napi_disable(&tp->napi);
+			napi_disable(napi);
 			tp->rtl_ops.disable(tp);
-			napi_enable(&tp->napi);
+			napi_enable(napi);
 			netif_info(tp, link, netdev, "carrier off\n");
 		}
 	}
@@ -3642,11 +3644,13 @@ static int rtl8152_runtime_suspend(struct r8152 *tp)
 		tp->rtl_ops.autosuspend_en(tp, true);
 
 		if (netif_carrier_ok(netdev)) {
-			napi_disable(&tp->napi);
+			struct napi_struct *napi = &tp->napi;
+
+			napi_disable(napi);
 			rtl_stop_rx(tp);
 			rxdy_gated_en(tp, false);
 			ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr);
-			napi_enable(&tp->napi);
+			napi_enable(napi);
 		}
 	}
 
@@ -3662,12 +3666,14 @@ static int rtl8152_system_suspend(struct r8152 *tp)
 	netif_device_detach(netdev);
 
 	if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) {
+		struct napi_struct *napi = &tp->napi;
+
 		clear_bit(WORK_ENABLE, &tp->flags);
 		usb_kill_urb(tp->intr_urb);
-		napi_disable(&tp->napi);
+		napi_disable(napi);
 		cancel_delayed_work_sync(&tp->schedule);
 		tp->rtl_ops.down(tp);
-		napi_enable(&tp->napi);
+		napi_enable(napi);
 	}
 
 	return ret;
@@ -3693,45 +3699,46 @@ static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
 static int rtl8152_resume(struct usb_interface *intf)
 {
 	struct r8152 *tp = usb_get_intfdata(intf);
+	struct net_device *netdev = tp->netdev;
 
 	mutex_lock(&tp->control);
 
 	if (!test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 		tp->rtl_ops.init(tp);
 		queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0);
-		netif_device_attach(tp->netdev);
+		netif_device_attach(netdev);
 	}
 
-	if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) {
+	if (netif_running(netdev) && netdev->flags & IFF_UP) {
 		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
+			struct napi_struct *napi = &tp->napi;
+
 			tp->rtl_ops.autosuspend_en(tp, false);
-			napi_disable(&tp->napi);
+			napi_disable(napi);
 			set_bit(WORK_ENABLE, &tp->flags);
-
-			if (netif_carrier_ok(tp->netdev)) {
+			if (netif_carrier_ok(netdev)) {
 				if (rtl8152_get_speed(tp) & LINK_STATUS) {
 					rtl_start_rx(tp);
 				} else {
-					netif_carrier_off(tp->netdev);
+					netif_carrier_off(netdev);
 					tp->rtl_ops.disable(tp);
-					netif_info(tp, link, tp->netdev,
+					netif_info(tp, link, netdev,
 						   "linking down\n");
 				}
 			}
-
-			napi_enable(&tp->napi);
+			napi_enable(napi);
 			clear_bit(SELECTIVE_SUSPEND, &tp->flags);
 			smp_mb__after_atomic();
 			if (!list_empty(&tp->rx_done))
 				napi_schedule(&tp->napi);
 		} else {
 			tp->rtl_ops.up(tp);
-			netif_carrier_off(tp->netdev);
+			netif_carrier_off(netdev);
 			set_bit(WORK_ENABLE, &tp->flags);
 		}
 		usb_submit_urb(tp->intr_urb, GFP_KERNEL);
 	} else if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
-		if (tp->netdev->flags & IFF_UP)
+		if (netdev->flags & IFF_UP)
 			tp->rtl_ops.autosuspend_en(tp, false);
 		clear_bit(SELECTIVE_SUSPEND, &tp->flags);
 	}
@@ -3819,7 +3826,8 @@ static void rtl8152_get_drvinfo(struct net_device *netdev,
 }
 
 static
-int rtl8152_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd)
+int rtl8152_get_link_ksettings(struct net_device *netdev,
+			       struct ethtool_link_ksettings *cmd)
 {
 	struct r8152 *tp = netdev_priv(netdev);
 	int ret;
@@ -3833,7 +3841,7 @@ int rtl8152_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd)
 
 	mutex_lock(&tp->control);
 
-	ret = mii_ethtool_gset(&tp->mii, cmd);
+	ret = mii_ethtool_get_link_ksettings(&tp->mii, cmd);
 
 	mutex_unlock(&tp->control);
 
@@ -3843,7 +3851,8 @@ out:
 	return ret;
 }
 
-static int rtl8152_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int rtl8152_set_link_ksettings(struct net_device *dev,
+				      const struct ethtool_link_ksettings *cmd)
 {
 	struct r8152 *tp = netdev_priv(dev);
 	int ret;
@@ -3854,11 +3863,12 @@ static int rtl8152_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 
 	mutex_lock(&tp->control);
 
-	ret = rtl8152_set_speed(tp, cmd->autoneg, cmd->speed, cmd->duplex);
+	ret = rtl8152_set_speed(tp, cmd->base.autoneg, cmd->base.speed,
+				cmd->base.duplex);
 	if (!ret) {
-		tp->autoneg = cmd->autoneg;
-		tp->speed = cmd->speed;
-		tp->duplex = cmd->duplex;
+		tp->autoneg = cmd->base.autoneg;
+		tp->speed = cmd->base.speed;
+		tp->duplex = cmd->base.duplex;
 	}
 
 	mutex_unlock(&tp->control);
@@ -4136,8 +4146,6 @@ static int rtl8152_set_coalesce(struct net_device *netdev,
 
 static const struct ethtool_ops ops = {
 	.get_drvinfo = rtl8152_get_drvinfo,
-	.get_settings = rtl8152_get_settings,
-	.set_settings = rtl8152_set_settings,
 	.get_link = ethtool_op_get_link,
 	.nway_reset = rtl8152_nway_reset,
 	.get_msglevel = rtl8152_get_msglevel,
@@ -4151,6 +4159,8 @@ static const struct ethtool_ops ops = {
 	.set_coalesce = rtl8152_set_coalesce,
 	.get_eee = rtl_ethtool_get_eee,
 	.set_eee = rtl_ethtool_set_eee,
+	.get_link_ksettings = rtl8152_get_link_ksettings,
+	.set_link_ksettings = rtl8152_set_link_ksettings,
 };
 
 static int rtl8152_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
@@ -4249,44 +4259,6 @@ static const struct net_device_ops rtl8152_netdev_ops = {
 	.ndo_features_check	= rtl8152_features_check,
 };
 
-static void r8152b_get_version(struct r8152 *tp)
-{
-	u32	ocp_data;
-	u16	version;
-
-	ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_TCR1);
-	version = (u16)(ocp_data & VERSION_MASK);
-
-	switch (version) {
-	case 0x4c00:
-		tp->version = RTL_VER_01;
-		break;
-	case 0x4c10:
-		tp->version = RTL_VER_02;
-		break;
-	case 0x5c00:
-		tp->version = RTL_VER_03;
-		tp->mii.supports_gmii = 1;
-		break;
-	case 0x5c10:
-		tp->version = RTL_VER_04;
-		tp->mii.supports_gmii = 1;
-		break;
-	case 0x5c20:
-		tp->version = RTL_VER_05;
-		tp->mii.supports_gmii = 1;
-		break;
-	case 0x5c30:
-		tp->version = RTL_VER_06;
-		tp->mii.supports_gmii = 1;
-		break;
-	default:
-		netif_info(tp, probe, tp->netdev,
-			   "Unknown version 0x%04x\n", version);
-		break;
-	}
-}
-
 static void rtl8152_unload(struct r8152 *tp)
 {
 	if (test_bit(RTL8152_UNPLUG, &tp->flags))
@@ -4351,14 +4323,66 @@ static int rtl_ops_init(struct r8152 *tp)
 	return ret;
 }
 
+static u8 rtl_get_version(struct usb_interface *intf)
+{
+	struct usb_device *udev = interface_to_usbdev(intf);
+	u32 ocp_data = 0;
+	__le32 *tmp;
+	u8 version;
+	int ret;
+
+	tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return 0;
+
+	ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
+			      RTL8152_REQ_GET_REGS, RTL8152_REQT_READ,
+			      PLA_TCR0, MCU_TYPE_PLA, tmp, sizeof(*tmp), 500);
+	if (ret > 0)
+		ocp_data = (__le32_to_cpu(*tmp) >> 16) & VERSION_MASK;
+
+	kfree(tmp);
+
+	switch (ocp_data) {
+	case 0x4c00:
+		version = RTL_VER_01;
+		break;
+	case 0x4c10:
+		version = RTL_VER_02;
+		break;
+	case 0x5c00:
+		version = RTL_VER_03;
+		break;
+	case 0x5c10:
+		version = RTL_VER_04;
+		break;
+	case 0x5c20:
+		version = RTL_VER_05;
+		break;
+	case 0x5c30:
+		version = RTL_VER_06;
+		break;
+	default:
+		version = RTL_VER_UNKNOWN;
+		dev_info(&intf->dev, "Unknown version 0x%04x\n", ocp_data);
+		break;
+	}
+
+	return version;
+}
+
 static int rtl8152_probe(struct usb_interface *intf,
 			 const struct usb_device_id *id)
 {
 	struct usb_device *udev = interface_to_usbdev(intf);
+	u8 version = rtl_get_version(intf);
 	struct r8152 *tp;
 	struct net_device *netdev;
 	int ret;
 
+	if (version == RTL_VER_UNKNOWN)
+		return -ENODEV;
+
 	if (udev->actconfig->desc.bConfigurationValue != 1) {
 		usb_driver_set_configuration(udev, 1);
 		return -ENODEV;
@@ -4378,8 +4402,18 @@ static int rtl8152_probe(struct usb_interface *intf,
 	tp->udev = udev;
 	tp->netdev = netdev;
 	tp->intf = intf;
+	tp->version = version;
+
+	switch (version) {
+	case RTL_VER_01:
+	case RTL_VER_02:
+		tp->mii.supports_gmii = 0;
+		break;
+	default:
+		tp->mii.supports_gmii = 1;
+		break;
+	}
 
-	r8152b_get_version(tp);
 	ret = rtl_ops_init(tp);
 	if (ret)
 		goto out;
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index c5b21138b7eb..e96e2e5673d7 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -291,6 +291,7 @@ static const struct net_device_ops rndis_netdev_ops = {
 	.ndo_stop		= usbnet_stop,
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 };
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index c81c79110cef..daaa88a66f40 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -791,47 +791,52 @@ static void rtl8150_get_drvinfo(struct net_device *netdev, struct ethtool_drvinf
 	usb_make_path(dev->udev, info->bus_info, sizeof(info->bus_info));
 }
 
-static int rtl8150_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+static int rtl8150_get_link_ksettings(struct net_device *netdev,
+				      struct ethtool_link_ksettings *ecmd)
 {
 	rtl8150_t *dev = netdev_priv(netdev);
 	short lpa, bmcr;
+	u32 supported;
 
-	ecmd->supported = (SUPPORTED_10baseT_Half |
+	supported = (SUPPORTED_10baseT_Half |
 			  SUPPORTED_10baseT_Full |
 			  SUPPORTED_100baseT_Half |
 			  SUPPORTED_100baseT_Full |
 			  SUPPORTED_Autoneg |
 			  SUPPORTED_TP | SUPPORTED_MII);
-	ecmd->port = PORT_TP;
-	ecmd->transceiver = XCVR_INTERNAL;
-	ecmd->phy_address = dev->phy;
+	ecmd->base.port = PORT_TP;
+	ecmd->base.phy_address = dev->phy;
 	get_registers(dev, BMCR, 2, &bmcr);
 	get_registers(dev, ANLP, 2, &lpa);
 	if (bmcr & BMCR_ANENABLE) {
 		u32 speed = ((lpa & (LPA_100HALF | LPA_100FULL)) ?
 			     SPEED_100 : SPEED_10);
-		ethtool_cmd_speed_set(ecmd, speed);
-		ecmd->autoneg = AUTONEG_ENABLE;
+		ecmd->base.speed = speed;
+		ecmd->base.autoneg = AUTONEG_ENABLE;
 		if (speed == SPEED_100)
-			ecmd->duplex = (lpa & LPA_100FULL) ?
+			ecmd->base.duplex = (lpa & LPA_100FULL) ?
 			    DUPLEX_FULL : DUPLEX_HALF;
 		else
-			ecmd->duplex = (lpa & LPA_10FULL) ?
+			ecmd->base.duplex = (lpa & LPA_10FULL) ?
 			    DUPLEX_FULL : DUPLEX_HALF;
 	} else {
-		ecmd->autoneg = AUTONEG_DISABLE;
-		ethtool_cmd_speed_set(ecmd, ((bmcr & BMCR_SPEED100) ?
-					     SPEED_100 : SPEED_10));
-		ecmd->duplex = (bmcr & BMCR_FULLDPLX) ?
+		ecmd->base.autoneg = AUTONEG_DISABLE;
+		ecmd->base.speed = ((bmcr & BMCR_SPEED100) ?
+					     SPEED_100 : SPEED_10);
+		ecmd->base.duplex = (bmcr & BMCR_FULLDPLX) ?
 		    DUPLEX_FULL : DUPLEX_HALF;
 	}
+
+	ethtool_convert_legacy_u32_to_link_mode(ecmd->link_modes.supported,
+						supported);
+
 	return 0;
 }
 
 static const struct ethtool_ops ops = {
 	.get_drvinfo = rtl8150_get_drvinfo,
-	.get_settings = rtl8150_get_settings,
-	.get_link = ethtool_op_get_link
+	.get_link = ethtool_op_get_link,
+	.get_link_ksettings = rtl8150_get_link_ksettings,
 };
 
 static int rtl8150_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c
index ac69f28d92d2..2110ab3513f0 100644
--- a/drivers/net/usb/sierra_net.c
+++ b/drivers/net/usb/sierra_net.c
@@ -199,6 +199,7 @@ static const struct net_device_ops sierra_net_device_ops = {
 	.ndo_start_xmit         = usbnet_start_xmit,
 	.ndo_tx_timeout         = usbnet_tx_timeout,
 	.ndo_change_mtu         = usbnet_change_mtu,
+	.ndo_get_stats64        = usbnet_get_stats64,
 	.ndo_set_mac_address    = eth_mac_addr,
 	.ndo_validate_addr      = eth_validate_addr,
 };
@@ -648,9 +649,9 @@ static const struct ethtool_ops sierra_net_ethtool_ops = {
 	.get_link = sierra_net_get_link,
 	.get_msglevel = usbnet_get_msglevel,
 	.set_msglevel = usbnet_set_msglevel,
-	.get_settings = usbnet_get_settings,
-	.set_settings = usbnet_set_settings,
 	.nway_reset = usbnet_nway_reset,
+	.get_link_ksettings = usbnet_get_link_ksettings,
+	.set_link_ksettings = usbnet_set_link_ksettings,
 };
 
 static int sierra_net_get_fw_attr(struct usbnet *dev, u16 *datap)
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index 0b17b40d7a4f..1ce01dbd494f 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -743,13 +743,13 @@ static const struct ethtool_ops smsc75xx_ethtool_ops = {
 	.get_drvinfo	= usbnet_get_drvinfo,
 	.get_msglevel	= usbnet_get_msglevel,
 	.set_msglevel	= usbnet_set_msglevel,
-	.get_settings	= usbnet_get_settings,
-	.set_settings	= usbnet_set_settings,
 	.get_eeprom_len	= smsc75xx_ethtool_get_eeprom_len,
 	.get_eeprom	= smsc75xx_ethtool_get_eeprom,
 	.set_eeprom	= smsc75xx_ethtool_set_eeprom,
 	.get_wol	= smsc75xx_ethtool_get_wol,
 	.set_wol	= smsc75xx_ethtool_set_wol,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 static int smsc75xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
@@ -1381,6 +1381,7 @@ static const struct net_device_ops smsc75xx_netdev_ops = {
 	.ndo_stop		= usbnet_stop,
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_change_mtu		= smsc75xx_change_mtu,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 831aa33d078a..c2f67cecdf5b 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -853,32 +853,32 @@ static void set_mdix_status(struct net_device *net, __u8 mdix_ctrl)
 	pdata->mdix_ctrl = mdix_ctrl;
 }
 
-static int smsc95xx_get_settings(struct net_device *net,
-				 struct ethtool_cmd *cmd)
+static int smsc95xx_get_link_ksettings(struct net_device *net,
+				       struct ethtool_link_ksettings *cmd)
 {
 	struct usbnet *dev = netdev_priv(net);
 	struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]);
 	int retval;
 
-	retval = usbnet_get_settings(net, cmd);
+	retval = usbnet_get_link_ksettings(net, cmd);
 
-	cmd->eth_tp_mdix = pdata->mdix_ctrl;
-	cmd->eth_tp_mdix_ctrl = pdata->mdix_ctrl;
+	cmd->base.eth_tp_mdix = pdata->mdix_ctrl;
+	cmd->base.eth_tp_mdix_ctrl = pdata->mdix_ctrl;
 
 	return retval;
 }
 
-static int smsc95xx_set_settings(struct net_device *net,
-				 struct ethtool_cmd *cmd)
+static int smsc95xx_set_link_ksettings(struct net_device *net,
+				       const struct ethtool_link_ksettings *cmd)
 {
 	struct usbnet *dev = netdev_priv(net);
 	struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]);
 	int retval;
 
-	if (pdata->mdix_ctrl != cmd->eth_tp_mdix_ctrl)
-		set_mdix_status(net, cmd->eth_tp_mdix_ctrl);
+	if (pdata->mdix_ctrl != cmd->base.eth_tp_mdix_ctrl)
+		set_mdix_status(net, cmd->base.eth_tp_mdix_ctrl);
 
-	retval = usbnet_set_settings(net, cmd);
+	retval = usbnet_set_link_ksettings(net, cmd);
 
 	return retval;
 }
@@ -889,8 +889,6 @@ static const struct ethtool_ops smsc95xx_ethtool_ops = {
 	.get_drvinfo	= usbnet_get_drvinfo,
 	.get_msglevel	= usbnet_get_msglevel,
 	.set_msglevel	= usbnet_set_msglevel,
-	.get_settings	= smsc95xx_get_settings,
-	.set_settings	= smsc95xx_set_settings,
 	.get_eeprom_len	= smsc95xx_ethtool_get_eeprom_len,
 	.get_eeprom	= smsc95xx_ethtool_get_eeprom,
 	.set_eeprom	= smsc95xx_ethtool_set_eeprom,
@@ -898,6 +896,8 @@ static const struct ethtool_ops smsc95xx_ethtool_ops = {
 	.get_regs	= smsc95xx_ethtool_getregs,
 	.get_wol	= smsc95xx_ethtool_get_wol,
 	.set_wol	= smsc95xx_ethtool_set_wol,
+	.get_link_ksettings	= smsc95xx_get_link_ksettings,
+	.set_link_ksettings	= smsc95xx_set_link_ksettings,
 };
 
 static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
@@ -1248,6 +1248,7 @@ static const struct net_device_ops smsc95xx_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl 		= smsc95xx_ioctl,
diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c
index 4a1e9c489f1f..317287f4409c 100644
--- a/drivers/net/usb/sr9700.c
+++ b/drivers/net/usb/sr9700.c
@@ -249,9 +249,9 @@ static const struct ethtool_ops sr9700_ethtool_ops = {
 	.set_msglevel	= usbnet_set_msglevel,
 	.get_eeprom_len	= sr9700_get_eeprom_len,
 	.get_eeprom	= sr9700_get_eeprom,
-	.get_settings	= usbnet_get_settings,
-	.set_settings	= usbnet_set_settings,
 	.nway_reset	= usbnet_nway_reset,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 static void sr9700_set_multicast(struct net_device *netdev)
@@ -308,6 +308,7 @@ static const struct net_device_ops sr9700_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= sr9700_ioctl,
 	.ndo_set_rx_mode	= sr9700_set_multicast,
diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c
index a50df0d8fb9a..9277a0f228df 100644
--- a/drivers/net/usb/sr9800.c
+++ b/drivers/net/usb/sr9800.c
@@ -524,9 +524,9 @@ static const struct ethtool_ops sr9800_ethtool_ops = {
 	.set_wol	= sr_set_wol,
 	.get_eeprom_len	= sr_get_eeprom_len,
 	.get_eeprom	= sr_get_eeprom,
-	.get_settings	= usbnet_get_settings,
-	.set_settings	= usbnet_set_settings,
 	.nway_reset	= usbnet_nway_reset,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 static int sr9800_link_reset(struct usbnet *dev)
@@ -679,6 +679,7 @@ static const struct net_device_ops sr9800_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address	= sr_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= sr_ioctl,
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 3de65ea6531a..9890656af735 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -316,6 +316,7 @@ static void __usbnet_status_stop_force(struct usbnet *dev)
  */
 void usbnet_skb_return (struct usbnet *dev, struct sk_buff *skb)
 {
+	struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->stats64);
 	int	status;
 
 	if (test_bit(EVENT_RX_PAUSED, &dev->flags)) {
@@ -327,8 +328,10 @@ void usbnet_skb_return (struct usbnet *dev, struct sk_buff *skb)
 	if (skb->protocol == 0)
 		skb->protocol = eth_type_trans (skb, dev->net);
 
-	dev->net->stats.rx_packets++;
-	dev->net->stats.rx_bytes += skb->len;
+	u64_stats_update_begin(&stats64->syncp);
+	stats64->rx_packets++;
+	stats64->rx_bytes += skb->len;
+	u64_stats_update_end(&stats64->syncp);
 
 	netif_dbg(dev, rx_status, dev->net, "< rx, len %zu, type 0x%x\n",
 		  skb->len + sizeof (struct ethhdr), skb->protocol);
@@ -947,18 +950,20 @@ EXPORT_SYMBOL_GPL(usbnet_open);
  * they'll probably want to use this base set.
  */
 
-int usbnet_get_settings (struct net_device *net, struct ethtool_cmd *cmd)
+int usbnet_get_link_ksettings(struct net_device *net,
+			      struct ethtool_link_ksettings *cmd)
 {
 	struct usbnet *dev = netdev_priv(net);
 
 	if (!dev->mii.mdio_read)
 		return -EOPNOTSUPP;
 
-	return mii_ethtool_gset(&dev->mii, cmd);
+	return mii_ethtool_get_link_ksettings(&dev->mii, cmd);
 }
-EXPORT_SYMBOL_GPL(usbnet_get_settings);
+EXPORT_SYMBOL_GPL(usbnet_get_link_ksettings);
 
-int usbnet_set_settings (struct net_device *net, struct ethtool_cmd *cmd)
+int usbnet_set_link_ksettings(struct net_device *net,
+			      const struct ethtool_link_ksettings *cmd)
 {
 	struct usbnet *dev = netdev_priv(net);
 	int retval;
@@ -966,7 +971,7 @@ int usbnet_set_settings (struct net_device *net, struct ethtool_cmd *cmd)
 	if (!dev->mii.mdio_write)
 		return -EOPNOTSUPP;
 
-	retval = mii_ethtool_sset(&dev->mii, cmd);
+	retval = mii_ethtool_set_link_ksettings(&dev->mii, cmd);
 
 	/* link speed/duplex might have changed */
 	if (dev->driver_info->link_reset)
@@ -976,9 +981,39 @@ int usbnet_set_settings (struct net_device *net, struct ethtool_cmd *cmd)
 	usbnet_update_max_qlen(dev);
 
 	return retval;
+}
+EXPORT_SYMBOL_GPL(usbnet_set_link_ksettings);
 
+void usbnet_get_stats64(struct net_device *net, struct rtnl_link_stats64 *stats)
+{
+	struct usbnet *dev = netdev_priv(net);
+	unsigned int start;
+	int cpu;
+
+	netdev_stats_to_stats64(stats, &net->stats);
+
+	for_each_possible_cpu(cpu) {
+		struct pcpu_sw_netstats *stats64;
+		u64 rx_packets, rx_bytes;
+		u64 tx_packets, tx_bytes;
+
+		stats64 = per_cpu_ptr(dev->stats64, cpu);
+
+		do {
+			start = u64_stats_fetch_begin_irq(&stats64->syncp);
+			rx_packets = stats64->rx_packets;
+			rx_bytes = stats64->rx_bytes;
+			tx_packets = stats64->tx_packets;
+			tx_bytes = stats64->tx_bytes;
+		} while (u64_stats_fetch_retry_irq(&stats64->syncp, start));
+
+		stats->rx_packets += rx_packets;
+		stats->rx_bytes += rx_bytes;
+		stats->tx_packets += tx_packets;
+		stats->tx_bytes += tx_bytes;
+	}
 }
-EXPORT_SYMBOL_GPL(usbnet_set_settings);
+EXPORT_SYMBOL_GPL(usbnet_get_stats64);
 
 u32 usbnet_get_link (struct net_device *net)
 {
@@ -1038,14 +1073,14 @@ EXPORT_SYMBOL_GPL(usbnet_set_msglevel);
 
 /* drivers may override default ethtool_ops in their bind() routine */
 static const struct ethtool_ops usbnet_ethtool_ops = {
-	.get_settings		= usbnet_get_settings,
-	.set_settings		= usbnet_set_settings,
 	.get_link		= usbnet_get_link,
 	.nway_reset		= usbnet_nway_reset,
 	.get_drvinfo		= usbnet_get_drvinfo,
 	.get_msglevel		= usbnet_get_msglevel,
 	.set_msglevel		= usbnet_set_msglevel,
 	.get_ts_info		= ethtool_op_get_ts_info,
+	.get_link_ksettings	= usbnet_get_link_ksettings,
+	.set_link_ksettings	= usbnet_set_link_ksettings,
 };
 
 /*-------------------------------------------------------------------------*/
@@ -1211,8 +1246,12 @@ static void tx_complete (struct urb *urb)
 	struct usbnet		*dev = entry->dev;
 
 	if (urb->status == 0) {
-		dev->net->stats.tx_packets += entry->packets;
-		dev->net->stats.tx_bytes += entry->length;
+		struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->stats64);
+
+		u64_stats_update_begin(&stats64->syncp);
+		stats64->tx_packets += entry->packets;
+		stats64->tx_bytes += entry->length;
+		u64_stats_update_end(&stats64->syncp);
 	} else {
 		dev->net->stats.tx_errors++;
 
@@ -1569,6 +1608,7 @@ void usbnet_disconnect (struct usb_interface *intf)
 	usb_free_urb(dev->interrupt);
 	kfree(dev->padding_pkt);
 
+	free_percpu(dev->stats64);
 	free_netdev(net);
 }
 EXPORT_SYMBOL_GPL(usbnet_disconnect);
@@ -1580,6 +1620,7 @@ static const struct net_device_ops usbnet_netdev_ops = {
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_set_rx_mode	= usbnet_set_rx_mode,
 	.ndo_change_mtu		= usbnet_change_mtu,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 };
@@ -1641,6 +1682,11 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
 	dev->intf = udev;
 	dev->driver_info = info;
 	dev->driver_name = name;
+
+	dev->stats64 = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+	if (!dev->stats64)
+		goto out0;
+
 	dev->msg_enable = netif_msg_init (msg_level, NETIF_MSG_DRV
 				| NETIF_MSG_PROBE | NETIF_MSG_LINK);
 	init_waitqueue_head(&dev->wait);
@@ -1780,6 +1826,8 @@ out1:
 	 */
 	cancel_work_sync(&dev->kevent);
 	del_timer_sync(&dev->delay);
+	free_percpu(dev->stats64);
+out0:
 	free_netdev(net);
 out:
 	return status;
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 8c39d6d690e5..317103680675 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -45,18 +45,13 @@ static struct {
 	{ "peer_ifindex" },
 };
 
-static int veth_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int veth_get_link_ksettings(struct net_device *dev,
+				   struct ethtool_link_ksettings *cmd)
 {
-	cmd->supported		= 0;
-	cmd->advertising	= 0;
-	ethtool_cmd_speed_set(cmd, SPEED_10000);
-	cmd->duplex		= DUPLEX_FULL;
-	cmd->port		= PORT_TP;
-	cmd->phy_address	= 0;
-	cmd->transceiver	= XCVR_INTERNAL;
-	cmd->autoneg		= AUTONEG_DISABLE;
-	cmd->maxtxpkt		= 0;
-	cmd->maxrxpkt		= 0;
+	cmd->base.speed		= SPEED_10000;
+	cmd->base.duplex	= DUPLEX_FULL;
+	cmd->base.port		= PORT_TP;
+	cmd->base.autoneg	= AUTONEG_DISABLE;
 	return 0;
 }
 
@@ -95,12 +90,12 @@ static void veth_get_ethtool_stats(struct net_device *dev,
 }
 
 static const struct ethtool_ops veth_ethtool_ops = {
-	.get_settings		= veth_get_settings,
 	.get_drvinfo		= veth_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_strings		= veth_get_strings,
 	.get_sset_count		= veth_get_sset_count,
 	.get_ethtool_stats	= veth_get_ethtool_stats,
+	.get_link_ksettings	= veth_get_link_ksettings,
 };
 
 static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ea9890d61967..b0d241d110ec 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1636,47 +1636,57 @@ static void virtnet_get_channels(struct net_device *dev,
 }
 
 /* Check if the user is trying to change anything besides speed/duplex */
-static bool virtnet_validate_ethtool_cmd(const struct ethtool_cmd *cmd)
+static bool
+virtnet_validate_ethtool_cmd(const struct ethtool_link_ksettings *cmd)
 {
-	struct ethtool_cmd diff1 = *cmd;
-	struct ethtool_cmd diff2 = {};
+	struct ethtool_link_ksettings diff1 = *cmd;
+	struct ethtool_link_ksettings diff2 = {};
 
 	/* cmd is always set so we need to clear it, validate the port type
 	 * and also without autonegotiation we can ignore advertising
 	 */
-	ethtool_cmd_speed_set(&diff1, 0);
-	diff2.port = PORT_OTHER;
-	diff1.advertising = 0;
-	diff1.duplex = 0;
-	diff1.cmd = 0;
+	diff1.base.speed = 0;
+	diff2.base.port = PORT_OTHER;
+	ethtool_link_ksettings_zero_link_mode(&diff1, advertising);
+	diff1.base.duplex = 0;
+	diff1.base.cmd = 0;
+	diff1.base.link_mode_masks_nwords = 0;
 
-	return !memcmp(&diff1, &diff2, sizeof(diff1));
+	return !memcmp(&diff1.base, &diff2.base, sizeof(diff1.base)) &&
+		bitmap_empty(diff1.link_modes.supported,
+			     __ETHTOOL_LINK_MODE_MASK_NBITS) &&
+		bitmap_empty(diff1.link_modes.advertising,
+			     __ETHTOOL_LINK_MODE_MASK_NBITS) &&
+		bitmap_empty(diff1.link_modes.lp_advertising,
+			     __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
-static int virtnet_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int virtnet_set_link_ksettings(struct net_device *dev,
+				      const struct ethtool_link_ksettings *cmd)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 	u32 speed;
 
-	speed = ethtool_cmd_speed(cmd);
+	speed = cmd->base.speed;
 	/* don't allow custom speed and duplex */
 	if (!ethtool_validate_speed(speed) ||
-	    !ethtool_validate_duplex(cmd->duplex) ||
+	    !ethtool_validate_duplex(cmd->base.duplex) ||
 	    !virtnet_validate_ethtool_cmd(cmd))
 		return -EINVAL;
 	vi->speed = speed;
-	vi->duplex = cmd->duplex;
+	vi->duplex = cmd->base.duplex;
 
 	return 0;
 }
 
-static int virtnet_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int virtnet_get_link_ksettings(struct net_device *dev,
+				      struct ethtool_link_ksettings *cmd)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 
-	ethtool_cmd_speed_set(cmd, vi->speed);
-	cmd->duplex = vi->duplex;
-	cmd->port = PORT_OTHER;
+	cmd->base.speed = vi->speed;
+	cmd->base.duplex = vi->duplex;
+	cmd->base.port = PORT_OTHER;
 
 	return 0;
 }
@@ -1696,8 +1706,8 @@ static const struct ethtool_ops virtnet_ethtool_ops = {
 	.set_channels = virtnet_set_channels,
 	.get_channels = virtnet_get_channels,
 	.get_ts_info = ethtool_op_get_ts_info,
-	.get_settings = virtnet_get_settings,
-	.set_settings = virtnet_set_settings,
+	.get_link_ksettings = virtnet_get_link_ksettings,
+	.set_link_ksettings = virtnet_set_link_ksettings,
 };
 
 static void virtnet_freeze_down(struct virtio_device *vdev)
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index f88ffafebfbf..2ff27314e047 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -471,22 +471,25 @@ vmxnet3_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 
 
 static int
-vmxnet3_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+vmxnet3_get_link_ksettings(struct net_device *netdev,
+			   struct ethtool_link_ksettings *ecmd)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 
-	ecmd->supported = SUPPORTED_10000baseT_Full | SUPPORTED_1000baseT_Full |
-			  SUPPORTED_TP;
-	ecmd->advertising = ADVERTISED_TP;
-	ecmd->port = PORT_TP;
-	ecmd->transceiver = XCVR_INTERNAL;
+	ethtool_link_ksettings_zero_link_mode(ecmd, supported);
+	ethtool_link_ksettings_add_link_mode(ecmd, supported, 10000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(ecmd, supported, 1000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(ecmd, supported, TP);
+	ethtool_link_ksettings_zero_link_mode(ecmd, advertising);
+	ethtool_link_ksettings_add_link_mode(ecmd, advertising, TP);
+	ecmd->base.port = PORT_TP;
 
 	if (adapter->link_speed) {
-		ethtool_cmd_speed_set(ecmd, adapter->link_speed);
-		ecmd->duplex = DUPLEX_FULL;
+		ecmd->base.speed = adapter->link_speed;
+		ecmd->base.duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
-		ecmd->duplex = DUPLEX_UNKNOWN;
+		ecmd->base.speed = SPEED_UNKNOWN;
+		ecmd->base.duplex = DUPLEX_UNKNOWN;
 	}
 	return 0;
 }
@@ -880,7 +883,6 @@ done:
 }
 
 static const struct ethtool_ops vmxnet3_ethtool_ops = {
-	.get_settings      = vmxnet3_get_settings,
 	.get_drvinfo       = vmxnet3_get_drvinfo,
 	.get_regs_len      = vmxnet3_get_regs_len,
 	.get_regs          = vmxnet3_get_regs,
@@ -900,6 +902,7 @@ static const struct ethtool_ops vmxnet3_ethtool_ops = {
 	.get_rxfh          = vmxnet3_get_rss,
 	.set_rxfh          = vmxnet3_set_rss,
 #endif
+	.get_link_ksettings = vmxnet3_get_link_ksettings,
 };
 
 void vmxnet3_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index d6988db1930d..eb5493e83556 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -104,6 +104,23 @@ static void vrf_get_stats64(struct net_device *dev,
 	}
 }
 
+/* by default VRF devices do not have a qdisc and are expected
+ * to be created with only a single queue.
+ */
+static bool qdisc_tx_is_default(const struct net_device *dev)
+{
+	struct netdev_queue *txq;
+	struct Qdisc *qdisc;
+
+	if (dev->num_tx_queues > 1)
+		return false;
+
+	txq = netdev_get_tx_queue(dev, 0);
+	qdisc = rcu_access_pointer(txq->qdisc);
+
+	return !qdisc->enqueue;
+}
+
 /* Local traffic destined to local address. Reinsert the packet to rx
  * path, similar to loopback handling.
  */
@@ -357,6 +374,29 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 	return ret;
 }
 
+static int vrf_finish_direct(struct net *net, struct sock *sk,
+			     struct sk_buff *skb)
+{
+	struct net_device *vrf_dev = skb->dev;
+
+	if (!list_empty(&vrf_dev->ptype_all) &&
+	    likely(skb_headroom(skb) >= ETH_HLEN)) {
+		struct ethhdr *eth = (struct ethhdr *)skb_push(skb, ETH_HLEN);
+
+		ether_addr_copy(eth->h_source, vrf_dev->dev_addr);
+		eth_zero_addr(eth->h_dest);
+		eth->h_proto = skb->protocol;
+
+		rcu_read_lock_bh();
+		dev_queue_xmit_nit(skb, vrf_dev);
+		rcu_read_unlock_bh();
+
+		skb_pull(skb, ETH_HLEN);
+	}
+
+	return 1;
+}
+
 #if IS_ENABLED(CONFIG_IPV6)
 /* modelled after ip6_finish_output2 */
 static int vrf_finish_output6(struct net *net, struct sock *sk,
@@ -405,18 +445,13 @@ static int vrf_output6(struct net *net, struct sock *sk, struct sk_buff *skb)
  * packet to go through device based features such as qdisc, netfilter
  * hooks and packet sockets with skb->dev set to vrf device.
  */
-static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
-				   struct sock *sk,
-				   struct sk_buff *skb)
+static struct sk_buff *vrf_ip6_out_redirect(struct net_device *vrf_dev,
+					    struct sk_buff *skb)
 {
 	struct net_vrf *vrf = netdev_priv(vrf_dev);
 	struct dst_entry *dst = NULL;
 	struct rt6_info *rt6;
 
-	/* don't divert link scope packets */
-	if (rt6_need_strict(&ipv6_hdr(skb)->daddr))
-		return skb;
-
 	rcu_read_lock();
 
 	rt6 = rcu_dereference(vrf->rt6);
@@ -438,6 +473,55 @@ static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
 	return skb;
 }
 
+static int vrf_output6_direct(struct net *net, struct sock *sk,
+			      struct sk_buff *skb)
+{
+	skb->protocol = htons(ETH_P_IPV6);
+
+	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
+			    net, sk, skb, NULL, skb->dev,
+			    vrf_finish_direct,
+			    !(IPCB(skb)->flags & IPSKB_REROUTED));
+}
+
+static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev,
+					  struct sock *sk,
+					  struct sk_buff *skb)
+{
+	struct net *net = dev_net(vrf_dev);
+	int err;
+
+	skb->dev = vrf_dev;
+
+	err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk,
+		      skb, NULL, vrf_dev, vrf_output6_direct);
+
+	if (likely(err == 1))
+		err = vrf_output6_direct(net, sk, skb);
+
+	/* reset skb device */
+	if (likely(err == 1))
+		nf_reset(skb);
+	else
+		skb = NULL;
+
+	return skb;
+}
+
+static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
+				   struct sock *sk,
+				   struct sk_buff *skb)
+{
+	/* don't divert link scope packets */
+	if (rt6_need_strict(&ipv6_hdr(skb)->daddr))
+		return skb;
+
+	if (qdisc_tx_is_default(vrf_dev))
+		return vrf_ip6_out_direct(vrf_dev, sk, skb);
+
+	return vrf_ip6_out_redirect(vrf_dev, skb);
+}
+
 /* holding rtnl */
 static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
 {
@@ -609,18 +693,13 @@ static int vrf_output(struct net *net, struct sock *sk, struct sk_buff *skb)
  * packet to go through device based features such as qdisc, netfilter
  * hooks and packet sockets with skb->dev set to vrf device.
  */
-static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
-				  struct sock *sk,
-				  struct sk_buff *skb)
+static struct sk_buff *vrf_ip_out_redirect(struct net_device *vrf_dev,
+					   struct sk_buff *skb)
 {
 	struct net_vrf *vrf = netdev_priv(vrf_dev);
 	struct dst_entry *dst = NULL;
 	struct rtable *rth;
 
-	/* don't divert multicast */
-	if (ipv4_is_multicast(ip_hdr(skb)->daddr))
-		return skb;
-
 	rcu_read_lock();
 
 	rth = rcu_dereference(vrf->rth);
@@ -642,6 +721,55 @@ static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
 	return skb;
 }
 
+static int vrf_output_direct(struct net *net, struct sock *sk,
+			     struct sk_buff *skb)
+{
+	skb->protocol = htons(ETH_P_IP);
+
+	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
+			    net, sk, skb, NULL, skb->dev,
+			    vrf_finish_direct,
+			    !(IPCB(skb)->flags & IPSKB_REROUTED));
+}
+
+static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev,
+					 struct sock *sk,
+					 struct sk_buff *skb)
+{
+	struct net *net = dev_net(vrf_dev);
+	int err;
+
+	skb->dev = vrf_dev;
+
+	err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk,
+		      skb, NULL, vrf_dev, vrf_output_direct);
+
+	if (likely(err == 1))
+		err = vrf_output_direct(net, sk, skb);
+
+	/* reset skb device */
+	if (likely(err == 1))
+		nf_reset(skb);
+	else
+		skb = NULL;
+
+	return skb;
+}
+
+static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
+				  struct sock *sk,
+				  struct sk_buff *skb)
+{
+	/* don't divert multicast */
+	if (ipv4_is_multicast(ip_hdr(skb)->daddr))
+		return skb;
+
+	if (qdisc_tx_is_default(vrf_dev))
+		return vrf_ip_out_direct(vrf_dev, sk, skb);
+
+	return vrf_ip_out_redirect(vrf_dev, skb);
+}
+
 /* called with rcu lock held */
 static struct sk_buff *vrf_l3_out(struct net_device *vrf_dev,
 				  struct sock *sk,
@@ -749,14 +877,18 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
 {
 	int ret;
 
+	port_dev->priv_flags |= IFF_L3MDEV_SLAVE;
 	ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL);
 	if (ret < 0)
-		return ret;
+		goto err;
 
-	port_dev->priv_flags |= IFF_L3MDEV_SLAVE;
 	cycle_netdev(port_dev);
 
 	return 0;
+
+err:
+	port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE;
+	return ret;
 }
 
 static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
@@ -978,9 +1110,11 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 		skb->dev = vrf_dev;
 		skb->skb_iif = vrf_dev->ifindex;
 
-		skb_push(skb, skb->mac_len);
-		dev_queue_xmit_nit(skb, vrf_dev);
-		skb_pull(skb, skb->mac_len);
+		if (!list_empty(&vrf_dev->ptype_all)) {
+			skb_push(skb, skb->mac_len);
+			dev_queue_xmit_nit(skb, vrf_dev);
+			skb_pull(skb, skb->mac_len);
+		}
 
 		IP6CB(skb)->flags |= IP6SKB_L3SLAVE;
 	}
@@ -1021,9 +1155,11 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev,
 
 	vrf_rx_stats(vrf_dev, skb->len);
 
-	skb_push(skb, skb->mac_len);
-	dev_queue_xmit_nit(skb, vrf_dev);
-	skb_pull(skb, skb->mac_len);
+	if (!list_empty(&vrf_dev->ptype_all)) {
+		skb_push(skb, skb->mac_len);
+		dev_queue_xmit_nit(skb, vrf_dev);
+		skb_pull(skb, skb->mac_len);
+	}
 
 	skb = vrf_rcv_nfhook(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, vrf_dev);
 out:
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index bdb6ae16d4a8..ebc98bb17a51 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -276,9 +276,9 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 	send_eth = send_ip = true;
 
 	if (type == RTM_GETNEIGH) {
-		ndm->ndm_family	= AF_INET;
 		send_ip = !vxlan_addr_any(&rdst->remote_ip);
 		send_eth = !is_zero_ether_addr(fdb->eth_addr);
+		ndm->ndm_family = send_ip ? rdst->remote_ip.sa.sa_family : AF_INET;
 	} else
 		ndm->ndm_family	= AF_BRIDGE;
 	ndm->ndm_state = fdb->state;
@@ -1515,7 +1515,7 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request,
 	int ns_olen;
 	int i, len;
 
-	if (dev == NULL)
+	if (dev == NULL || !pskb_may_pull(request, request->len))
 		return NULL;
 
 	len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) +
@@ -1530,10 +1530,11 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request,
 	skb_push(reply, sizeof(struct ethhdr));
 	skb_reset_mac_header(reply);
 
-	ns = (struct nd_msg *)skb_transport_header(request);
+	ns = (struct nd_msg *)(ipv6_hdr(request) + 1);
 
 	daddr = eth_hdr(request)->h_source;
-	ns_olen = request->len - skb_transport_offset(request) - sizeof(*ns);
+	ns_olen = request->len - skb_network_offset(request) -
+		sizeof(struct ipv6hdr) - sizeof(*ns);
 	for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) {
 		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
 			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
@@ -1604,10 +1605,13 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 	if (!in6_dev)
 		goto out;
 
+	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)))
+		goto out;
+
 	iphdr = ipv6_hdr(skb);
 	daddr = &iphdr->daddr;
 
-	msg = (struct nd_msg *)skb_transport_header(skb);
+	msg = (struct nd_msg *)(iphdr + 1);
 	if (msg->icmph.icmp6_code != 0 ||
 	    msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
 		goto out;
@@ -2242,16 +2246,13 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (ntohs(eth->h_proto) == ETH_P_ARP)
 			return arp_reduce(dev, skb, vni);
 #if IS_ENABLED(CONFIG_IPV6)
-		else if (ntohs(eth->h_proto) == ETH_P_IPV6 &&
-			 pskb_may_pull(skb, sizeof(struct ipv6hdr)
-				       + sizeof(struct nd_msg)) &&
-			 ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
-				struct nd_msg *msg;
-
-				msg = (struct nd_msg *)skb_transport_header(skb);
-				if (msg->icmph.icmp6_code == 0 &&
-				    msg->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION)
-					return neigh_reduce(dev, skb, vni);
+		else if (ntohs(eth->h_proto) == ETH_P_IPV6) {
+			struct ipv6hdr *hdr, _hdr;
+			if ((hdr = skb_header_pointer(skb,
+						      skb_network_offset(skb),
+						      sizeof(_hdr), &_hdr)) &&
+			    hdr->nexthdr == IPPROTO_ICMPV6)
+				return neigh_reduce(dev, skb, vni);
 		}
 #endif
 	}
@@ -2322,6 +2323,9 @@ static void vxlan_cleanup(unsigned long arg)
 			if (f->state & (NUD_PERMANENT | NUD_NOARP))
 				continue;
 
+			if (f->flags & NTF_EXT_LEARNED)
+				continue;
+
 			timeout = f->used + vxlan->cfg.age_interval * HZ;
 			if (time_before_eq(timeout, jiffies)) {
 				netdev_dbg(vxlan->dev,
@@ -2923,6 +2927,11 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 		return -EINVAL;
 	}
 
+	if (lowerdev) {
+		dev->gso_max_size = lowerdev->gso_max_size;
+		dev->gso_max_segs = lowerdev->gso_max_segs;
+	}
+
 	if (conf->mtu) {
 		int max_mtu = ETH_MAX_MTU;
 
diff --git a/drivers/net/wireless/ath/wcn36xx/Kconfig b/drivers/net/wireless/ath/wcn36xx/Kconfig
index 4b83e87f0b94..20bf967a70b9 100644
--- a/drivers/net/wireless/ath/wcn36xx/Kconfig
+++ b/drivers/net/wireless/ath/wcn36xx/Kconfig
@@ -2,7 +2,7 @@ config WCN36XX
 	tristate "Qualcomm Atheros WCN3660/3680 support"
 	depends on MAC80211 && HAS_DMA
 	depends on QCOM_WCNSS_CTRL || QCOM_WCNSS_CTRL=n
-	depends on QCOM_SMD || QCOM_SMD=n
+	depends on RPMSG || RPMSG=n
 	---help---
 	  This module adds support for wireless adapters based on
 	  Qualcomm Atheros WCN3660 and WCN3680 mobile chipsets.
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index 7a0c2e7da7f6..bb7110f7fc86 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -22,7 +22,7 @@
 #include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
 #include <linux/soc/qcom/smem_state.h>
 #include <linux/soc/qcom/wcnss_ctrl.h>
 #include "wcn36xx.h"
@@ -1218,15 +1218,13 @@ static int wcn36xx_probe(struct platform_device *pdev)
 
 	INIT_WORK(&wcn->scan_work, wcn36xx_hw_scan_worker);
 
-	wcn->smd_channel = qcom_wcnss_open_channel(wcnss, "WLAN_CTRL", wcn36xx_smd_rsp_process);
+	wcn->smd_channel = qcom_wcnss_open_channel(wcnss, "WLAN_CTRL", wcn36xx_smd_rsp_process, hw);
 	if (IS_ERR(wcn->smd_channel)) {
 		wcn36xx_err("failed to open WLAN_CTRL channel\n");
 		ret = PTR_ERR(wcn->smd_channel);
 		goto out_wq;
 	}
 
-	qcom_smd_set_drvdata(wcn->smd_channel, hw);
-
 	addr = of_get_property(pdev->dev.of_node, "local-mac-address", &ret);
 	if (addr && ret != ETH_ALEN) {
 		wcn36xx_err("invalid local-mac-address\n");
diff --git a/drivers/net/wireless/ath/wcn36xx/smd.c b/drivers/net/wireless/ath/wcn36xx/smd.c
index 1c2966f7db7a..9c6590d5348a 100644
--- a/drivers/net/wireless/ath/wcn36xx/smd.c
+++ b/drivers/net/wireless/ath/wcn36xx/smd.c
@@ -19,7 +19,7 @@
 #include <linux/etherdevice.h>
 #include <linux/firmware.h>
 #include <linux/bitops.h>
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
 #include "smd.h"
 
 struct wcn36xx_cfg_val {
@@ -254,7 +254,7 @@ static int wcn36xx_smd_send_and_wait(struct wcn36xx *wcn, size_t len)
 
 	init_completion(&wcn->hal_rsp_compl);
 	start = jiffies;
-	ret = qcom_smd_send(wcn->smd_channel, wcn->hal_buf, len);
+	ret = rpmsg_send(wcn->smd_channel, wcn->hal_buf, len);
 	if (ret) {
 		wcn36xx_err("HAL TX failed\n");
 		goto out;
@@ -2205,11 +2205,11 @@ out:
 	return ret;
 }
 
-int wcn36xx_smd_rsp_process(struct qcom_smd_channel *channel,
-			    const void *buf, size_t len)
+int wcn36xx_smd_rsp_process(struct rpmsg_device *rpdev,
+			    void *buf, int len, void *priv, u32 addr)
 {
 	const struct wcn36xx_hal_msg_header *msg_header = buf;
-	struct ieee80211_hw *hw = qcom_smd_get_drvdata(channel);
+	struct ieee80211_hw *hw = priv;
 	struct wcn36xx *wcn = hw->priv;
 	struct wcn36xx_hal_ind_msg *msg_ind;
 	wcn36xx_dbg_dump(WCN36XX_DBG_SMD_DUMP, "SMD <<< ", buf, len);
diff --git a/drivers/net/wireless/ath/wcn36xx/smd.h b/drivers/net/wireless/ath/wcn36xx/smd.h
index 8892ccd67b14..013fc9546f56 100644
--- a/drivers/net/wireless/ath/wcn36xx/smd.h
+++ b/drivers/net/wireless/ath/wcn36xx/smd.h
@@ -51,7 +51,7 @@ struct wcn36xx_hal_ind_msg {
 };
 
 struct wcn36xx;
-struct qcom_smd_channel;
+struct rpmsg_device;
 
 int wcn36xx_smd_open(struct wcn36xx *wcn);
 void wcn36xx_smd_close(struct wcn36xx *wcn);
@@ -129,8 +129,8 @@ int wcn36xx_smd_trigger_ba(struct wcn36xx *wcn, u8 sta_index);
 
 int wcn36xx_smd_update_cfg(struct wcn36xx *wcn, u32 cfg_id, u32 value);
 
-int wcn36xx_smd_rsp_process(struct qcom_smd_channel *channel,
-			    const void *buf, size_t len);
+int wcn36xx_smd_rsp_process(struct rpmsg_device *rpdev,
+			    void *buf, int len, void *priv, u32 addr);
 
 int wcn36xx_smd_set_mc_list(struct wcn36xx *wcn,
 			    struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
index 7423998ddeb4..b52b4da9a967 100644
--- a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
+++ b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
@@ -195,7 +195,7 @@ struct wcn36xx {
 	void __iomem		*ccu_base;
 	void __iomem		*dxe_base;
 
-	struct qcom_smd_channel *smd_channel;
+	struct rpmsg_endpoint	*smd_channel;
 
 	struct qcom_smem_state  *tx_enable_state;
 	unsigned		tx_enable_state_bit;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
index 5bc2ba214735..9b970dc2b922 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -21,6 +21,7 @@
 #include <linux/pci_ids.h>
 #include <linux/sched.h>
 #include <linux/completion.h>
+#include <linux/interrupt.h>
 #include <linux/scatterlist.h>
 #include <linux/mmc/sdio.h>
 #include <linux/mmc/core.h>
diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c
index 785334f7a538..3b68eaffb48c 100644
--- a/drivers/net/wireless/rndis_wlan.c
+++ b/drivers/net/wireless/rndis_wlan.c
@@ -3392,6 +3392,7 @@ static const struct net_device_ops rndis_wlan_netdev_ops = {
 	.ndo_stop		= usbnet_stop,
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
+	.ndo_get_stats64	= usbnet_get_stats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= rndis_wlan_set_multicast_list,
diff --git a/drivers/net/wireless/st/cw1200/cw1200_sdio.c b/drivers/net/wireless/st/cw1200/cw1200_sdio.c
index d3acc85932a5..709f56e5ad87 100644
--- a/drivers/net/wireless/st/cw1200/cw1200_sdio.c
+++ b/drivers/net/wireless/st/cw1200/cw1200_sdio.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/interrupt.h>
 #include <linux/gpio.h>
 #include <linux/delay.h>
 #include <linux/mmc/host.h>
diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index 1dc43fc5f65f..faad69a1a597 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -76,7 +76,7 @@ config QCOM_ADSP_PIL
 	depends on OF && ARCH_QCOM
 	depends on REMOTEPROC
 	depends on QCOM_SMEM
-	depends on RPMSG_QCOM_SMD || QCOM_SMD || (COMPILE_TEST && QCOM_SMD=n && RPMSG_QCOM_SMD=n)
+	depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n)
 	select MFD_SYSCON
 	select QCOM_MDT_LOADER
 	select QCOM_RPROC_COMMON
@@ -93,7 +93,7 @@ config QCOM_Q6V5_PIL
 	depends on OF && ARCH_QCOM
 	depends on QCOM_SMEM
 	depends on REMOTEPROC
-	depends on RPMSG_QCOM_SMD || QCOM_SMD || (COMPILE_TEST && QCOM_SMD=n && RPMSG_QCOM_SMD=n)
+	depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n)
 	select MFD_SYSCON
 	select QCOM_RPROC_COMMON
 	select QCOM_SCM
@@ -104,7 +104,7 @@ config QCOM_Q6V5_PIL
 config QCOM_WCNSS_PIL
 	tristate "Qualcomm WCNSS Peripheral Image Loader"
 	depends on OF && ARCH_QCOM
-	depends on RPMSG_QCOM_SMD || QCOM_SMD || (COMPILE_TEST && QCOM_SMD=n && RPMSG_QCOM_SMD=n)
+	depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n)
 	depends on QCOM_SMEM
 	depends on REMOTEPROC
 	select QCOM_MDT_LOADER
diff --git a/drivers/rpmsg/Kconfig b/drivers/rpmsg/Kconfig
index f12ac0b28263..edc008f55663 100644
--- a/drivers/rpmsg/Kconfig
+++ b/drivers/rpmsg/Kconfig
@@ -16,7 +16,6 @@ config RPMSG_CHAR
 config RPMSG_QCOM_SMD
 	tristate "Qualcomm Shared Memory Driver (SMD)"
 	depends on QCOM_SMEM
-	depends on QCOM_SMD=n
 	select RPMSG
 	help
 	  Say y here to enable support for the Qualcomm Shared Memory Driver
diff --git a/drivers/scsi/qedf/Makefile b/drivers/scsi/qedf/Makefile
index 64e9f507ce32..414f2a772a5f 100644
--- a/drivers/scsi/qedf/Makefile
+++ b/drivers/scsi/qedf/Makefile
@@ -1,5 +1,5 @@
 obj-$(CONFIG_QEDF) := qedf.o
 qedf-y = qedf_dbg.o qedf_main.o qedf_io.o qedf_fip.o \
-	 qedf_attr.o qedf_els.o
+	 qedf_attr.o qedf_els.o drv_scsi_fw_funcs.o drv_fcoe_fw_funcs.o
 
 qedf-$(CONFIG_DEBUG_FS) += qedf_debugfs.o
diff --git a/drivers/scsi/qedf/drv_fcoe_fw_funcs.c b/drivers/scsi/qedf/drv_fcoe_fw_funcs.c
new file mode 100644
index 000000000000..8c65e3b034dc
--- /dev/null
+++ b/drivers/scsi/qedf/drv_fcoe_fw_funcs.c
@@ -0,0 +1,190 @@
+/* QLogic FCoE Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available 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.
+ */
+#include "drv_fcoe_fw_funcs.h"
+#include "drv_scsi_fw_funcs.h"
+
+#define FCOE_RX_ID (0xFFFFu)
+
+static inline void init_common_sqe(struct fcoe_task_params *task_params,
+				   enum fcoe_sqe_request_type request_type)
+{
+	memset(task_params->sqe, 0, sizeof(*(task_params->sqe)));
+	SET_FIELD(task_params->sqe->flags, FCOE_WQE_REQ_TYPE,
+		  request_type);
+	task_params->sqe->task_id = task_params->itid;
+}
+
+int init_initiator_rw_fcoe_task(struct fcoe_task_params *task_params,
+				struct scsi_sgl_task_params *sgl_task_params,
+				struct regpair sense_data_buffer_phys_addr,
+				u32 task_retry_id,
+				u8 fcp_cmd_payload[32])
+{
+	struct fcoe_task_context *ctx = task_params->context;
+	struct ystorm_fcoe_task_st_ctx *y_st_ctx;
+	struct tstorm_fcoe_task_st_ctx *t_st_ctx;
+	struct ustorm_fcoe_task_ag_ctx *u_ag_ctx;
+	struct mstorm_fcoe_task_st_ctx *m_st_ctx;
+	u32 io_size, val;
+	bool slow_sgl;
+
+	memset(ctx, 0, sizeof(*(ctx)));
+	slow_sgl = scsi_is_slow_sgl(sgl_task_params->num_sges,
+				    sgl_task_params->small_mid_sge);
+	io_size = (task_params->task_type == FCOE_TASK_TYPE_WRITE_INITIATOR ?
+		   task_params->tx_io_size : task_params->rx_io_size);
+
+	/* Ystorm ctx */
+	y_st_ctx = &ctx->ystorm_st_context;
+	y_st_ctx->data_2_trns_rem = cpu_to_le32(io_size);
+	y_st_ctx->task_rety_identifier = cpu_to_le32(task_retry_id);
+	y_st_ctx->task_type = task_params->task_type;
+	memcpy(&y_st_ctx->tx_info_union.fcp_cmd_payload,
+	       fcp_cmd_payload, sizeof(struct fcoe_fcp_cmd_payload));
+
+	/* Tstorm ctx */
+	t_st_ctx = &ctx->tstorm_st_context;
+	t_st_ctx->read_only.dev_type = (task_params->is_tape_device == 1 ?
+					FCOE_TASK_DEV_TYPE_TAPE :
+					FCOE_TASK_DEV_TYPE_DISK);
+	t_st_ctx->read_only.cid = cpu_to_le32(task_params->conn_cid);
+	val = cpu_to_le32(task_params->cq_rss_number);
+	t_st_ctx->read_only.glbl_q_num = val;
+	t_st_ctx->read_only.fcp_cmd_trns_size = cpu_to_le32(io_size);
+	t_st_ctx->read_only.task_type = task_params->task_type;
+	SET_FIELD(t_st_ctx->read_write.flags,
+		  FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME, 1);
+	t_st_ctx->read_write.rx_id = cpu_to_le16(FCOE_RX_ID);
+
+	/* Ustorm ctx */
+	u_ag_ctx = &ctx->ustorm_ag_context;
+	u_ag_ctx->global_cq_num = cpu_to_le32(task_params->cq_rss_number);
+
+	/* Mstorm buffer for sense/rsp data placement */
+	m_st_ctx = &ctx->mstorm_st_context;
+	val = cpu_to_le32(sense_data_buffer_phys_addr.hi);
+	m_st_ctx->rsp_buf_addr.hi = val;
+	val = cpu_to_le32(sense_data_buffer_phys_addr.lo);
+	m_st_ctx->rsp_buf_addr.lo = val;
+
+	if (task_params->task_type == FCOE_TASK_TYPE_WRITE_INITIATOR) {
+		/* Ystorm ctx */
+		y_st_ctx->expect_first_xfer = 1;
+
+		/* Set the amount of super SGEs. Can be up to 4. */
+		SET_FIELD(y_st_ctx->sgl_mode,
+			  YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE,
+			  (slow_sgl ? SCSI_TX_SLOW_SGL : SCSI_FAST_SGL));
+		init_scsi_sgl_context(&y_st_ctx->sgl_params,
+				      &y_st_ctx->data_desc,
+				      sgl_task_params);
+
+		/* Mstorm ctx */
+		SET_FIELD(m_st_ctx->flags,
+			  MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE,
+			  (slow_sgl ? SCSI_TX_SLOW_SGL : SCSI_FAST_SGL));
+	} else {
+		/* Tstorm ctx */
+		SET_FIELD(t_st_ctx->read_write.flags,
+			  FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE,
+			  (slow_sgl ? SCSI_TX_SLOW_SGL : SCSI_FAST_SGL));
+
+		/* Mstorm ctx */
+		m_st_ctx->data_2_trns_rem = cpu_to_le32(io_size);
+		init_scsi_sgl_context(&m_st_ctx->sgl_params,
+				      &m_st_ctx->data_desc,
+				      sgl_task_params);
+	}
+
+	init_common_sqe(task_params, SEND_FCOE_CMD);
+	return 0;
+}
+
+int init_initiator_midpath_unsolicited_fcoe_task(
+	struct fcoe_task_params *task_params,
+	struct fcoe_tx_mid_path_params *mid_path_fc_header,
+	struct scsi_sgl_task_params *tx_sgl_task_params,
+	struct scsi_sgl_task_params *rx_sgl_task_params,
+	u8 fw_to_place_fc_header)
+{
+	struct fcoe_task_context *ctx = task_params->context;
+	struct ystorm_fcoe_task_st_ctx *y_st_ctx;
+	struct tstorm_fcoe_task_st_ctx *t_st_ctx;
+	struct ustorm_fcoe_task_ag_ctx *u_ag_ctx;
+	struct mstorm_fcoe_task_st_ctx *m_st_ctx;
+	u32 val;
+
+	memset(ctx, 0, sizeof(*(ctx)));
+
+	/* Init Ystorm */
+	y_st_ctx = &ctx->ystorm_st_context;
+	init_scsi_sgl_context(&y_st_ctx->sgl_params,
+			      &y_st_ctx->data_desc,
+			      tx_sgl_task_params);
+	SET_FIELD(y_st_ctx->sgl_mode,
+		  YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE, SCSI_FAST_SGL);
+	y_st_ctx->data_2_trns_rem = cpu_to_le32(task_params->tx_io_size);
+	y_st_ctx->task_type = task_params->task_type;
+	memcpy(&y_st_ctx->tx_info_union.tx_params.mid_path,
+	       mid_path_fc_header, sizeof(struct fcoe_tx_mid_path_params));
+
+	/* Init Mstorm */
+	m_st_ctx = &ctx->mstorm_st_context;
+	init_scsi_sgl_context(&m_st_ctx->sgl_params,
+			      &m_st_ctx->data_desc,
+			      rx_sgl_task_params);
+	SET_FIELD(m_st_ctx->flags,
+		  MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER,
+		  fw_to_place_fc_header);
+	m_st_ctx->data_2_trns_rem = cpu_to_le32(task_params->rx_io_size);
+
+	/* Init Tstorm */
+	t_st_ctx = &ctx->tstorm_st_context;
+	t_st_ctx->read_only.cid = cpu_to_le32(task_params->conn_cid);
+	val = cpu_to_le32(task_params->cq_rss_number);
+	t_st_ctx->read_only.glbl_q_num = val;
+	t_st_ctx->read_only.task_type = task_params->task_type;
+	SET_FIELD(t_st_ctx->read_write.flags,
+		  FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME, 1);
+	t_st_ctx->read_write.rx_id = cpu_to_le16(FCOE_RX_ID);
+
+	/* Init Ustorm */
+	u_ag_ctx = &ctx->ustorm_ag_context;
+	u_ag_ctx->global_cq_num = cpu_to_le32(task_params->cq_rss_number);
+
+	/* Init SQE */
+	init_common_sqe(task_params, SEND_FCOE_MIDPATH);
+	task_params->sqe->additional_info_union.burst_length =
+				    tx_sgl_task_params->total_buffer_size;
+	SET_FIELD(task_params->sqe->flags,
+		  FCOE_WQE_NUM_SGES, tx_sgl_task_params->num_sges);
+	SET_FIELD(task_params->sqe->flags, FCOE_WQE_SGL_MODE,
+		  SCSI_FAST_SGL);
+
+	return 0;
+}
+
+int init_initiator_abort_fcoe_task(struct fcoe_task_params *task_params)
+{
+	init_common_sqe(task_params, SEND_FCOE_ABTS_REQUEST);
+	return 0;
+}
+
+int init_initiator_cleanup_fcoe_task(struct fcoe_task_params *task_params)
+{
+	init_common_sqe(task_params, FCOE_EXCHANGE_CLEANUP);
+	return 0;
+}
+
+int init_initiator_sequence_recovery_fcoe_task(
+	struct fcoe_task_params *task_params, u32 off)
+{
+	init_common_sqe(task_params, FCOE_SEQUENCE_RECOVERY);
+	task_params->sqe->additional_info_union.seq_rec_updated_offset = off;
+	return 0;
+}
diff --git a/drivers/scsi/qedf/drv_fcoe_fw_funcs.h b/drivers/scsi/qedf/drv_fcoe_fw_funcs.h
new file mode 100644
index 000000000000..617529b058f4
--- /dev/null
+++ b/drivers/scsi/qedf/drv_fcoe_fw_funcs.h
@@ -0,0 +1,93 @@
+/* QLogic FCoE Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available 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.
+ */
+#ifndef _FCOE_FW_FUNCS_H
+#define _FCOE_FW_FUNCS_H
+#include "drv_scsi_fw_funcs.h"
+#include "qedf_hsi.h"
+#include <linux/qed/qed_if.h>
+
+struct fcoe_task_params {
+	/* Output parameter [set/filled by the HSI function] */
+	struct fcoe_task_context *context;
+
+	/* Output parameter [set/filled by the HSI function] */
+	struct fcoe_wqe *sqe;
+	enum fcoe_task_type task_type;
+	u32 tx_io_size; /* in bytes */
+	u32 rx_io_size; /* in bytes */
+	u32 conn_cid;
+	u16 itid;
+	u8 cq_rss_number;
+
+	 /* Whether it's Tape device or not (0=Disk, 1=Tape) */
+	u8 is_tape_device;
+};
+
+/**
+ * @brief init_initiator_rw_fcoe_task - Initializes FCoE task context for
+ * read/write task types and init fcoe_sqe
+ *
+ * @param task_params - Pointer to task parameters struct
+ * @param sgl_task_params - Pointer to SGL task params
+ * @param sense_data_buffer_phys_addr - Pointer to sense data buffer
+ * @param task_retry_id - retry identification - Used only for Tape device
+ * @param fcp_cmnd_payload - FCP CMD Payload
+ */
+int init_initiator_rw_fcoe_task(struct fcoe_task_params *task_params,
+	struct scsi_sgl_task_params *sgl_task_params,
+	struct regpair sense_data_buffer_phys_addr,
+	u32 task_retry_id,
+	u8 fcp_cmd_payload[32]);
+
+/**
+ * @brief init_initiator_midpath_fcoe_task - Initializes FCoE task context for
+ * midpath/unsolicited task types and init fcoe_sqe
+ *
+ * @param task_params - Pointer to task parameters struct
+ * @param mid_path_fc_header - FC header
+ * @param tx_sgl_task_params - Pointer to Tx SGL task params
+ * @param rx_sgl_task_params - Pointer to Rx SGL task params
+ * @param fw_to_place_fc_header	- Indication if the FW will place the FC header
+ * in addition to the data arrives.
+ */
+int init_initiator_midpath_unsolicited_fcoe_task(
+	struct fcoe_task_params *task_params,
+	struct fcoe_tx_mid_path_params *mid_path_fc_header,
+	struct scsi_sgl_task_params *tx_sgl_task_params,
+	struct scsi_sgl_task_params *rx_sgl_task_params,
+	u8 fw_to_place_fc_header);
+
+/**
+ * @brief init_initiator_abort_fcoe_task - Initializes FCoE task context for
+ * abort task types and init fcoe_sqe
+ *
+ * @param task_params - Pointer to task parameters struct
+ */
+int init_initiator_abort_fcoe_task(struct fcoe_task_params *task_params);
+
+/**
+ * @brief init_initiator_cleanup_fcoe_task - Initializes FCoE task context for
+ * cleanup task types and init fcoe_sqe
+ *
+ *
+ * @param task_params - Pointer to task parameters struct
+ */
+int init_initiator_cleanup_fcoe_task(struct fcoe_task_params *task_params);
+
+/**
+ * @brief init_initiator_cleanup_fcoe_task - Initializes FCoE task context for
+ * sequence recovery task types and init fcoe_sqe
+ *
+ *
+ * @param task_params - Pointer to task parameters struct
+ * @param desired_offset - The desired offest the task will be re-sent from
+ */
+int init_initiator_sequence_recovery_fcoe_task(
+	struct fcoe_task_params *task_params,
+	u32 desired_offset);
+#endif
diff --git a/drivers/scsi/qedf/drv_scsi_fw_funcs.c b/drivers/scsi/qedf/drv_scsi_fw_funcs.c
new file mode 100644
index 000000000000..11e0cc082ec0
--- /dev/null
+++ b/drivers/scsi/qedf/drv_scsi_fw_funcs.c
@@ -0,0 +1,44 @@
+/* QLogic FCoE Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available 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.
+ */
+#include "drv_scsi_fw_funcs.h"
+
+#define SCSI_NUM_SGES_IN_CACHE 0x4
+
+bool scsi_is_slow_sgl(u16 num_sges, bool small_mid_sge)
+{
+	return (num_sges > SCSI_NUM_SGES_SLOW_SGL_THR && small_mid_sge);
+}
+
+void init_scsi_sgl_context(struct scsi_sgl_params *ctx_sgl_params,
+			   struct scsi_cached_sges *ctx_data_desc,
+			   struct scsi_sgl_task_params *sgl_task_params)
+{
+	/* no need to check for sgl_task_params->sgl validity */
+	u8 num_sges_to_init = sgl_task_params->num_sges >
+			      SCSI_NUM_SGES_IN_CACHE ? SCSI_NUM_SGES_IN_CACHE :
+			      sgl_task_params->num_sges;
+	u8 sge_index;
+	u32 val;
+
+	val = cpu_to_le32(sgl_task_params->sgl_phys_addr.lo);
+	ctx_sgl_params->sgl_addr.lo = val;
+	val = cpu_to_le32(sgl_task_params->sgl_phys_addr.hi);
+	ctx_sgl_params->sgl_addr.hi = val;
+	val = cpu_to_le32(sgl_task_params->total_buffer_size);
+	ctx_sgl_params->sgl_total_length = val;
+	ctx_sgl_params->sgl_num_sges = cpu_to_le16(sgl_task_params->num_sges);
+
+	for (sge_index = 0; sge_index < num_sges_to_init; sge_index++) {
+		val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.lo);
+		ctx_data_desc->sge[sge_index].sge_addr.lo = val;
+		val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.hi);
+		ctx_data_desc->sge[sge_index].sge_addr.hi = val;
+		val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_len);
+		ctx_data_desc->sge[sge_index].sge_len = val;
+	}
+}
diff --git a/drivers/scsi/qedf/drv_scsi_fw_funcs.h b/drivers/scsi/qedf/drv_scsi_fw_funcs.h
new file mode 100644
index 000000000000..9cb45410bc45
--- /dev/null
+++ b/drivers/scsi/qedf/drv_scsi_fw_funcs.h
@@ -0,0 +1,85 @@
+/* QLogic FCoE Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available 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.
+ */
+#ifndef _SCSI_FW_FUNCS_H
+#define _SCSI_FW_FUNCS_H
+#include <linux/qed/common_hsi.h>
+#include <linux/qed/storage_common.h>
+#include <linux/qed/fcoe_common.h>
+
+struct scsi_sgl_task_params {
+	struct scsi_sge *sgl;
+	struct regpair sgl_phys_addr;
+	u32 total_buffer_size;
+	u16 num_sges;
+
+	 /* true if SGL contains a small (< 4KB) SGE in middle(not 1st or last)
+	  * -> relevant for tx only
+	  */
+	bool small_mid_sge;
+};
+
+struct scsi_dif_task_params {
+	u32 initial_ref_tag;
+	bool initial_ref_tag_is_valid;
+	u16 application_tag;
+	u16 application_tag_mask;
+	u16 dif_block_size_log;
+	bool dif_on_network;
+	bool dif_on_host;
+	u8 host_guard_type;
+	u8 protection_type;
+	u8 ref_tag_mask;
+	bool crc_seed;
+
+	 /* Enable Connection error upon DIF error (segments with DIF errors are
+	  * dropped)
+	  */
+	bool tx_dif_conn_err_en;
+	bool ignore_app_tag;
+	bool keep_ref_tag_const;
+	bool validate_guard;
+	bool validate_app_tag;
+	bool validate_ref_tag;
+	bool forward_guard;
+	bool forward_app_tag;
+	bool forward_ref_tag;
+	bool forward_app_tag_with_mask;
+	bool forward_ref_tag_with_mask;
+};
+
+struct scsi_initiator_cmd_params {
+	 /* for cdb_size > default CDB size (extended CDB > 16 bytes) ->
+	  * pointer to the CDB buffer SGE
+	  */
+	struct scsi_sge extended_cdb_sge;
+
+	/* Physical address of sense data buffer for sense data - 256B buffer */
+	struct regpair sense_data_buffer_phys_addr;
+};
+
+/**
+ * @brief scsi_is_slow_sgl - checks for slow SGL
+ *
+ * @param num_sges - number of sges in SGL
+ * @param small_mid_sge - True is the SGL contains an SGE which is smaller than
+ * 4KB and its not the 1st or last SGE in the SGL
+ */
+bool scsi_is_slow_sgl(u16 num_sges, bool small_mid_sge);
+
+/**
+ * @brief init_scsi_sgl_context - initializes SGL task context
+ *
+ * @param sgl_params - SGL context parameters to initialize (output parameter)
+ * @param data_desc - context struct containing SGEs array to set (output
+ * parameter)
+ * @param sgl_task_params - SGL parameters (input)
+ */
+void init_scsi_sgl_context(struct scsi_sgl_params *sgl_params,
+	struct scsi_cached_sges *ctx_data_desc,
+	struct scsi_sgl_task_params *sgl_task_params);
+#endif
diff --git a/drivers/scsi/qedf/qedf.h b/drivers/scsi/qedf/qedf.h
index 96346a1b1515..40aeb6bb96a2 100644
--- a/drivers/scsi/qedf/qedf.h
+++ b/drivers/scsi/qedf/qedf.h
@@ -26,6 +26,7 @@
 #include <linux/qed/qed_ll2_if.h>
 #include "qedf_version.h"
 #include "qedf_dbg.h"
+#include "drv_fcoe_fw_funcs.h"
 
 /* Helpers to extract upper and lower 32-bits of pointer */
 #define U64_HI(val) ((u32)(((u64)(val)) >> 32))
@@ -59,19 +60,17 @@
 #define UPSTREAM_KEEP		1
 
 struct qedf_mp_req {
-	uint8_t tm_flags;
-
 	uint32_t req_len;
 	void *req_buf;
 	dma_addr_t req_buf_dma;
-	struct fcoe_sge *mp_req_bd;
+	struct scsi_sge *mp_req_bd;
 	dma_addr_t mp_req_bd_dma;
 	struct fc_frame_header req_fc_hdr;
 
 	uint32_t resp_len;
 	void *resp_buf;
 	dma_addr_t resp_buf_dma;
-	struct fcoe_sge *mp_resp_bd;
+	struct scsi_sge *mp_resp_bd;
 	dma_addr_t mp_resp_bd_dma;
 	struct fc_frame_header resp_fc_hdr;
 };
@@ -119,6 +118,7 @@ struct qedf_ioreq {
 #define QEDF_CMD_IN_CLEANUP		0x2
 #define QEDF_CMD_SRR_SENT		0x3
 	u8 io_req_flags;
+	uint8_t tm_flags;
 	struct qedf_rport *fcport;
 	unsigned long flags;
 	enum qedf_ioreq_event event;
@@ -130,6 +130,8 @@ struct qedf_ioreq {
 	struct completion tm_done;
 	struct completion abts_done;
 	struct fcoe_task_context *task;
+	struct fcoe_task_params *task_params;
+	struct scsi_sgl_task_params *sgl_task_params;
 	int idx;
 /*
  * Need to allocate enough room for both sense data and FCP response data
@@ -199,8 +201,8 @@ struct qedf_rport {
 	dma_addr_t sq_pbl_dma;
 	u32 sq_pbl_size;
 	u32 sid;
-#define	QEDF_RPORT_TYPE_DISK		1
-#define	QEDF_RPORT_TYPE_TAPE		2
+#define	QEDF_RPORT_TYPE_DISK		0
+#define	QEDF_RPORT_TYPE_TAPE		1
 	uint dev_type; /* Disk or tape */
 	struct list_head peers;
 };
@@ -391,7 +393,7 @@ struct qedf_ctx {
 
 struct io_bdt {
 	struct qedf_ioreq *io_req;
-	struct fcoe_sge *bd_tbl;
+	struct scsi_sge *bd_tbl;
 	dma_addr_t bd_tbl_dma;
 	u16 bd_valid;
 };
@@ -400,7 +402,7 @@ struct qedf_cmd_mgr {
 	struct qedf_ctx *qedf;
 	u16 idx;
 	struct io_bdt **io_bdt_pool;
-#define FCOE_PARAMS_NUM_TASKS		4096
+#define FCOE_PARAMS_NUM_TASKS		2048
 	struct qedf_ioreq cmds[FCOE_PARAMS_NUM_TASKS];
 	spinlock_t lock;
 	atomic_t free_list_cnt;
@@ -465,9 +467,8 @@ extern void qedf_cmd_timer_set(struct qedf_ctx *qedf, struct qedf_ioreq *io_req,
 	unsigned int timer_msec);
 extern int qedf_init_mp_req(struct qedf_ioreq *io_req);
 extern void qedf_init_mp_task(struct qedf_ioreq *io_req,
-	struct fcoe_task_context *task_ctx);
-extern void qedf_add_to_sq(struct qedf_rport *fcport, u16 xid,
-	u32 ptu_invalidate, enum fcoe_task_type req_type, u32 offset);
+	struct fcoe_task_context *task_ctx, struct fcoe_wqe *wqe);
+extern u16 qedf_get_sqe_idx(struct qedf_rport *fcport);
 extern void qedf_ring_doorbell(struct qedf_rport *fcport);
 extern void qedf_process_els_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
 	struct qedf_ioreq *els_req);
diff --git a/drivers/scsi/qedf/qedf_els.c b/drivers/scsi/qedf/qedf_els.c
index 59f3e5c73a13..c505d41f6dc8 100644
--- a/drivers/scsi/qedf/qedf_els.c
+++ b/drivers/scsi/qedf/qedf_els.c
@@ -25,6 +25,9 @@ static int qedf_initiate_els(struct qedf_rport *fcport, unsigned int op,
 	uint16_t xid;
 	uint32_t start_time = jiffies / HZ;
 	uint32_t current_time;
+	struct fcoe_wqe *sqe;
+	unsigned long flags;
+	u16 sqe_idx;
 
 	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Sending ELS\n");
 
@@ -113,20 +116,25 @@ retry_els:
 	/* Obtain exchange id */
 	xid = els_req->xid;
 
+	spin_lock_irqsave(&fcport->rport_lock, flags);
+
+	sqe_idx = qedf_get_sqe_idx(fcport);
+	sqe = &fcport->sq[sqe_idx];
+	memset(sqe, 0, sizeof(struct fcoe_wqe));
+
 	/* Initialize task context for this IO request */
 	task = qedf_get_task_mem(&qedf->tasks, xid);
-	qedf_init_mp_task(els_req, task);
+	qedf_init_mp_task(els_req, task, sqe);
 
 	/* Put timer on original I/O request */
 	if (timer_msec)
 		qedf_cmd_timer_set(qedf, els_req, timer_msec);
 
-	qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_MIDPATH, 0);
-
 	/* Ring doorbell */
 	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Ringing doorbell for ELS "
 		   "req\n");
 	qedf_ring_doorbell(fcport);
+	spin_unlock_irqrestore(&fcport->rport_lock, flags);
 els_err:
 	return rc;
 }
@@ -604,6 +612,8 @@ static void qedf_initiate_seq_cleanup(struct qedf_ioreq *orig_io_req,
 	struct qedf_rport *fcport;
 	unsigned long flags;
 	struct qedf_els_cb_arg *cb_arg;
+	struct fcoe_wqe *sqe;
+	u16 sqe_idx;
 
 	fcport = orig_io_req->fcport;
 
@@ -631,8 +641,13 @@ static void qedf_initiate_seq_cleanup(struct qedf_ioreq *orig_io_req,
 
 	spin_lock_irqsave(&fcport->rport_lock, flags);
 
-	qedf_add_to_sq(fcport, orig_io_req->xid, 0,
-	    FCOE_TASK_TYPE_SEQUENCE_CLEANUP, offset);
+	sqe_idx = qedf_get_sqe_idx(fcport);
+	sqe = &fcport->sq[sqe_idx];
+	memset(sqe, 0, sizeof(struct fcoe_wqe));
+	orig_io_req->task_params->sqe = sqe;
+
+	init_initiator_sequence_recovery_fcoe_task(orig_io_req->task_params,
+						   offset);
 	qedf_ring_doorbell(fcport);
 
 	spin_unlock_irqrestore(&fcport->rport_lock, flags);
diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c
index 46debe5034af..1d7f90d0adc1 100644
--- a/drivers/scsi/qedf/qedf_io.c
+++ b/drivers/scsi/qedf/qedf_io.c
@@ -96,7 +96,7 @@ void qedf_cmd_mgr_free(struct qedf_cmd_mgr *cmgr)
 	if (!cmgr->io_bdt_pool)
 		goto free_cmd_pool;
 
-	bd_tbl_sz = QEDF_MAX_BDS_PER_CMD * sizeof(struct fcoe_sge);
+	bd_tbl_sz = QEDF_MAX_BDS_PER_CMD * sizeof(struct scsi_sge);
 	for (i = 0; i < num_ios; i++) {
 		bdt_info = cmgr->io_bdt_pool[i];
 		if (bdt_info->bd_tbl) {
@@ -119,6 +119,8 @@ free_cmd_pool:
 
 	for (i = 0; i < num_ios; i++) {
 		io_req = &cmgr->cmds[i];
+		kfree(io_req->sgl_task_params);
+		kfree(io_req->task_params);
 		/* Make sure we free per command sense buffer */
 		if (io_req->sense_buffer)
 			dma_free_coherent(&qedf->pdev->dev,
@@ -178,7 +180,7 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf)
 	spin_lock_init(&cmgr->lock);
 
 	/*
-	 * Initialize list of qedf_ioreq.
+	 * Initialize I/O request fields.
 	 */
 	xid = QEDF_MIN_XID;
 
@@ -196,6 +198,29 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf)
 		    GFP_KERNEL);
 		if (!io_req->sense_buffer)
 			goto mem_err;
+
+		/* Allocate task parameters to pass to f/w init funcions */
+		io_req->task_params = kzalloc(sizeof(*io_req->task_params),
+					      GFP_KERNEL);
+		if (!io_req->task_params) {
+			QEDF_ERR(&(qedf->dbg_ctx),
+				 "Failed to allocate task_params for xid=0x%x\n",
+				 i);
+			goto mem_err;
+		}
+
+		/*
+		 * Allocate scatter/gather list info to pass to f/w init
+		 * functions.
+		 */
+		io_req->sgl_task_params = kzalloc(
+		    sizeof(struct scsi_sgl_task_params), GFP_KERNEL);
+		if (!io_req->sgl_task_params) {
+			QEDF_ERR(&(qedf->dbg_ctx),
+				 "Failed to allocate sgl_task_params for xid=0x%x\n",
+				 i);
+			goto mem_err;
+		}
 	}
 
 	/* Allocate pool of io_bdts - one for each qedf_ioreq */
@@ -211,8 +236,8 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf)
 		cmgr->io_bdt_pool[i] = kmalloc(sizeof(struct io_bdt),
 		    GFP_KERNEL);
 		if (!cmgr->io_bdt_pool[i]) {
-			QEDF_WARN(&(qedf->dbg_ctx), "Failed to alloc "
-				   "io_bdt_pool[%d].\n", i);
+			QEDF_WARN(&(qedf->dbg_ctx),
+				  "Failed to alloc io_bdt_pool[%d].\n", i);
 			goto mem_err;
 		}
 	}
@@ -220,11 +245,11 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf)
 	for (i = 0; i < num_ios; i++) {
 		bdt_info = cmgr->io_bdt_pool[i];
 		bdt_info->bd_tbl = dma_alloc_coherent(&qedf->pdev->dev,
-		    QEDF_MAX_BDS_PER_CMD * sizeof(struct fcoe_sge),
+		    QEDF_MAX_BDS_PER_CMD * sizeof(struct scsi_sge),
 		    &bdt_info->bd_tbl_dma, GFP_KERNEL);
 		if (!bdt_info->bd_tbl) {
-			QEDF_WARN(&(qedf->dbg_ctx), "Failed to alloc "
-				   "bdt_tbl[%d].\n", i);
+			QEDF_WARN(&(qedf->dbg_ctx),
+				  "Failed to alloc bdt_tbl[%d].\n", i);
 			goto mem_err;
 		}
 	}
@@ -318,6 +343,7 @@ struct qedf_ioreq *qedf_alloc_cmd(struct qedf_rport *fcport, u8 cmd_type)
 	}
 	bd_tbl->io_req = io_req;
 	io_req->cmd_type = cmd_type;
+	io_req->tm_flags = 0;
 
 	/* Reset sequence offset data */
 	io_req->rx_buf_off = 0;
@@ -336,10 +362,9 @@ static void qedf_free_mp_resc(struct qedf_ioreq *io_req)
 {
 	struct qedf_mp_req *mp_req = &(io_req->mp_req);
 	struct qedf_ctx *qedf = io_req->fcport->qedf;
-	uint64_t sz = sizeof(struct fcoe_sge);
+	uint64_t sz = sizeof(struct scsi_sge);
 
 	/* clear tm flags */
-	mp_req->tm_flags = 0;
 	if (mp_req->mp_req_bd) {
 		dma_free_coherent(&qedf->pdev->dev, sz,
 		    mp_req->mp_req_bd, mp_req->mp_req_bd_dma);
@@ -387,7 +412,7 @@ void qedf_release_cmd(struct kref *ref)
 static int qedf_split_bd(struct qedf_ioreq *io_req, u64 addr, int sg_len,
 	int bd_index)
 {
-	struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl;
+	struct scsi_sge *bd = io_req->bd_tbl->bd_tbl;
 	int frag_size, sg_frags;
 
 	sg_frags = 0;
@@ -398,7 +423,7 @@ static int qedf_split_bd(struct qedf_ioreq *io_req, u64 addr, int sg_len,
 			frag_size = sg_len;
 		bd[bd_index + sg_frags].sge_addr.lo = U64_LO(addr);
 		bd[bd_index + sg_frags].sge_addr.hi = U64_HI(addr);
-		bd[bd_index + sg_frags].size = (uint16_t)frag_size;
+		bd[bd_index + sg_frags].sge_len = (uint16_t)frag_size;
 
 		addr += (u64)frag_size;
 		sg_frags++;
@@ -413,7 +438,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req)
 	struct Scsi_Host *host = sc->device->host;
 	struct fc_lport *lport = shost_priv(host);
 	struct qedf_ctx *qedf = lport_priv(lport);
-	struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl;
+	struct scsi_sge *bd = io_req->bd_tbl->bd_tbl;
 	struct scatterlist *sg;
 	int byte_count = 0;
 	int sg_count = 0;
@@ -439,7 +464,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req)
 
 		bd[bd_count].sge_addr.lo = (addr & 0xffffffff);
 		bd[bd_count].sge_addr.hi = (addr >> 32);
-		bd[bd_count].size = (u16)sg_len;
+		bd[bd_count].sge_len = (u16)sg_len;
 
 		return ++bd_count;
 	}
@@ -480,7 +505,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req)
 			sg_frags = 1;
 			bd[bd_count].sge_addr.lo = U64_LO(addr);
 			bd[bd_count].sge_addr.hi  = U64_HI(addr);
-			bd[bd_count].size = (uint16_t)sg_len;
+			bd[bd_count].sge_len = (uint16_t)sg_len;
 		}
 
 		bd_count += sg_frags;
@@ -498,7 +523,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req)
 static int qedf_build_bd_list_from_sg(struct qedf_ioreq *io_req)
 {
 	struct scsi_cmnd *sc = io_req->sc_cmd;
-	struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl;
+	struct scsi_sge *bd = io_req->bd_tbl->bd_tbl;
 	int bd_count;
 
 	if (scsi_sg_count(sc)) {
@@ -508,7 +533,7 @@ static int qedf_build_bd_list_from_sg(struct qedf_ioreq *io_req)
 	} else {
 		bd_count = 0;
 		bd[0].sge_addr.lo = bd[0].sge_addr.hi = 0;
-		bd[0].size = 0;
+		bd[0].sge_len = 0;
 	}
 	io_req->bd_tbl->bd_valid = bd_count;
 
@@ -529,430 +554,223 @@ static void qedf_build_fcp_cmnd(struct qedf_ioreq *io_req,
 
 	/* 4 bytes: flag info */
 	fcp_cmnd->fc_pri_ta = 0;
-	fcp_cmnd->fc_tm_flags = io_req->mp_req.tm_flags;
+	fcp_cmnd->fc_tm_flags = io_req->tm_flags;
 	fcp_cmnd->fc_flags = io_req->io_req_flags;
 	fcp_cmnd->fc_cmdref = 0;
 
 	/* Populate data direction */
-	if (sc_cmd->sc_data_direction == DMA_TO_DEVICE)
-		fcp_cmnd->fc_flags |= FCP_CFL_WRDATA;
-	else if (sc_cmd->sc_data_direction == DMA_FROM_DEVICE)
+	if (io_req->cmd_type == QEDF_TASK_MGMT_CMD) {
 		fcp_cmnd->fc_flags |= FCP_CFL_RDDATA;
+	} else {
+		if (sc_cmd->sc_data_direction == DMA_TO_DEVICE)
+			fcp_cmnd->fc_flags |= FCP_CFL_WRDATA;
+		else if (sc_cmd->sc_data_direction == DMA_FROM_DEVICE)
+			fcp_cmnd->fc_flags |= FCP_CFL_RDDATA;
+	}
 
 	fcp_cmnd->fc_pri_ta = FCP_PTA_SIMPLE;
 
 	/* 16 bytes: CDB information */
-	memcpy(fcp_cmnd->fc_cdb, sc_cmd->cmnd, sc_cmd->cmd_len);
+	if (io_req->cmd_type != QEDF_TASK_MGMT_CMD)
+		memcpy(fcp_cmnd->fc_cdb, sc_cmd->cmnd, sc_cmd->cmd_len);
 
 	/* 4 bytes: FCP data length */
 	fcp_cmnd->fc_dl = htonl(io_req->data_xfer_len);
-
 }
 
 static void  qedf_init_task(struct qedf_rport *fcport, struct fc_lport *lport,
-	struct qedf_ioreq *io_req, u32 *ptu_invalidate,
-	struct fcoe_task_context *task_ctx)
+	struct qedf_ioreq *io_req, struct fcoe_task_context *task_ctx,
+	struct fcoe_wqe *sqe)
 {
 	enum fcoe_task_type task_type;
 	struct scsi_cmnd *sc_cmd = io_req->sc_cmd;
 	struct io_bdt *bd_tbl = io_req->bd_tbl;
-	union fcoe_data_desc_ctx *data_desc;
-	u32 *fcp_cmnd;
+	u8 fcp_cmnd[32];
 	u32 tmp_fcp_cmnd[8];
-	int cnt, i;
-	int bd_count;
+	int bd_count = 0;
 	struct qedf_ctx *qedf = fcport->qedf;
 	uint16_t cq_idx = smp_processor_id() % qedf->num_queues;
-	u8 tmp_sgl_mode = 0;
-	u8 mst_sgl_mode = 0;
+	struct regpair sense_data_buffer_phys_addr;
+	u32 tx_io_size = 0;
+	u32 rx_io_size = 0;
+	int i, cnt;
 
-	memset(task_ctx, 0, sizeof(struct fcoe_task_context));
+	/* Note init_initiator_rw_fcoe_task memsets the task context */
 	io_req->task = task_ctx;
+	memset(task_ctx, 0, sizeof(struct fcoe_task_context));
+	memset(io_req->task_params, 0, sizeof(struct fcoe_task_params));
+	memset(io_req->sgl_task_params, 0, sizeof(struct scsi_sgl_task_params));
 
-	if (sc_cmd->sc_data_direction == DMA_TO_DEVICE)
-		task_type = FCOE_TASK_TYPE_WRITE_INITIATOR;
-	else
+	/* Set task type bassed on DMA directio of command */
+	if (io_req->cmd_type == QEDF_TASK_MGMT_CMD) {
 		task_type = FCOE_TASK_TYPE_READ_INITIATOR;
-
-	/* Y Storm context */
-	task_ctx->ystorm_st_context.expect_first_xfer = 1;
-	task_ctx->ystorm_st_context.data_2_trns_rem = io_req->data_xfer_len;
-	/* Check if this is required */
-	task_ctx->ystorm_st_context.ox_id = io_req->xid;
-	task_ctx->ystorm_st_context.task_rety_identifier =
-	    io_req->task_retry_identifier;
-
-	/* T Storm ag context */
-	SET_FIELD(task_ctx->tstorm_ag_context.flags0,
-	    TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE, PROTOCOLID_FCOE);
-	task_ctx->tstorm_ag_context.icid = (u16)fcport->fw_cid;
-
-	/* T Storm st context */
-	SET_FIELD(task_ctx->tstorm_st_context.read_write.flags,
-	    FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME,
-	    1);
-	task_ctx->tstorm_st_context.read_write.rx_id = 0xffff;
-
-	task_ctx->tstorm_st_context.read_only.dev_type =
-	    FCOE_TASK_DEV_TYPE_DISK;
-	task_ctx->tstorm_st_context.read_only.conf_supported = 0;
-	task_ctx->tstorm_st_context.read_only.cid = fcport->fw_cid;
-
-	/* Completion queue for response. */
-	task_ctx->tstorm_st_context.read_only.glbl_q_num = cq_idx;
-	task_ctx->tstorm_st_context.read_only.fcp_cmd_trns_size =
-	    io_req->data_xfer_len;
-	task_ctx->tstorm_st_context.read_write.e_d_tov_exp_timeout_val =
-	    lport->e_d_tov;
-
-	task_ctx->ustorm_ag_context.global_cq_num = cq_idx;
-	io_req->fp_idx = cq_idx;
-
-	bd_count = bd_tbl->bd_valid;
-	if (task_type == FCOE_TASK_TYPE_WRITE_INITIATOR) {
-		/* Setup WRITE task */
-		struct fcoe_sge *fcoe_bd_tbl = bd_tbl->bd_tbl;
-
-		task_ctx->ystorm_st_context.task_type =
-		    FCOE_TASK_TYPE_WRITE_INITIATOR;
-		data_desc = &task_ctx->ystorm_st_context.data_desc;
-
-		if (io_req->use_slowpath) {
-			SET_FIELD(task_ctx->ystorm_st_context.sgl_mode,
-			    YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE,
-			    FCOE_SLOW_SGL);
-			data_desc->slow.base_sgl_addr.lo =
-			    U64_LO(bd_tbl->bd_tbl_dma);
-			data_desc->slow.base_sgl_addr.hi =
-			    U64_HI(bd_tbl->bd_tbl_dma);
-			data_desc->slow.remainder_num_sges = bd_count;
-			data_desc->slow.curr_sge_off = 0;
-			data_desc->slow.curr_sgl_index = 0;
-			qedf->slow_sge_ios++;
-			io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
-		} else {
-			SET_FIELD(task_ctx->ystorm_st_context.sgl_mode,
-			    YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE,
-			    (bd_count <= 4) ? (enum fcoe_sgl_mode)bd_count :
-			    FCOE_MUL_FAST_SGES);
-
-			if (bd_count == 1) {
-				data_desc->single_sge.sge_addr.lo =
-				    fcoe_bd_tbl->sge_addr.lo;
-				data_desc->single_sge.sge_addr.hi =
-				    fcoe_bd_tbl->sge_addr.hi;
-				data_desc->single_sge.size =
-				    fcoe_bd_tbl->size;
-				data_desc->single_sge.is_valid_sge = 0;
-				qedf->single_sge_ios++;
-				io_req->sge_type = QEDF_IOREQ_SINGLE_SGE;
-			} else {
-				data_desc->fast.sgl_start_addr.lo =
-				    U64_LO(bd_tbl->bd_tbl_dma);
-				data_desc->fast.sgl_start_addr.hi =
-				    U64_HI(bd_tbl->bd_tbl_dma);
-				data_desc->fast.sgl_byte_offset =
-				    data_desc->fast.sgl_start_addr.lo &
-				    (QEDF_PAGE_SIZE - 1);
-				if (data_desc->fast.sgl_byte_offset > 0)
-					QEDF_ERR(&(qedf->dbg_ctx),
-					    "byte_offset=%u for xid=0x%x.\n",
-					    io_req->xid,
-					    data_desc->fast.sgl_byte_offset);
-				data_desc->fast.task_reuse_cnt =
-				    io_req->reuse_count;
-				io_req->reuse_count++;
-				if (io_req->reuse_count == QEDF_MAX_REUSE) {
-					*ptu_invalidate = 1;
-					io_req->reuse_count = 0;
-				}
-				qedf->fast_sge_ios++;
-				io_req->sge_type = QEDF_IOREQ_FAST_SGE;
-			}
-		}
-
-		/* T Storm context */
-		task_ctx->tstorm_st_context.read_only.task_type =
-		    FCOE_TASK_TYPE_WRITE_INITIATOR;
-
-		/* M Storm context */
-		tmp_sgl_mode = GET_FIELD(task_ctx->ystorm_st_context.sgl_mode,
-		    YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE);
-		SET_FIELD(task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode,
-		    FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_TX_SGL_MODE,
-		    tmp_sgl_mode);
-
 	} else {
-		/* Setup READ task */
-
-		/* M Storm context */
-		struct fcoe_sge *fcoe_bd_tbl = bd_tbl->bd_tbl;
-
-		data_desc = &task_ctx->mstorm_st_context.fp.data_desc;
-		task_ctx->mstorm_st_context.fp.data_2_trns_rem =
-		    io_req->data_xfer_len;
-
-		if (io_req->use_slowpath) {
-			SET_FIELD(
-			    task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode,
-			    FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE,
-			    FCOE_SLOW_SGL);
-			data_desc->slow.base_sgl_addr.lo =
-			    U64_LO(bd_tbl->bd_tbl_dma);
-			data_desc->slow.base_sgl_addr.hi =
-			    U64_HI(bd_tbl->bd_tbl_dma);
-			data_desc->slow.remainder_num_sges =
-			    bd_count;
-			data_desc->slow.curr_sge_off = 0;
-			data_desc->slow.curr_sgl_index = 0;
-			qedf->slow_sge_ios++;
-			io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
+		if (sc_cmd->sc_data_direction == DMA_TO_DEVICE) {
+			task_type = FCOE_TASK_TYPE_WRITE_INITIATOR;
+			tx_io_size = io_req->data_xfer_len;
 		} else {
-			SET_FIELD(
-			    task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode,
-			    FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE,
-			    (bd_count <= 4) ? (enum fcoe_sgl_mode)bd_count :
-			    FCOE_MUL_FAST_SGES);
-
-			if (bd_count == 1) {
-				data_desc->single_sge.sge_addr.lo =
-				    fcoe_bd_tbl->sge_addr.lo;
-				data_desc->single_sge.sge_addr.hi =
-				    fcoe_bd_tbl->sge_addr.hi;
-				data_desc->single_sge.size =
-				    fcoe_bd_tbl->size;
-				data_desc->single_sge.is_valid_sge = 0;
-				qedf->single_sge_ios++;
-				io_req->sge_type = QEDF_IOREQ_SINGLE_SGE;
-			} else {
-				data_desc->fast.sgl_start_addr.lo =
-				    U64_LO(bd_tbl->bd_tbl_dma);
-				data_desc->fast.sgl_start_addr.hi =
-				    U64_HI(bd_tbl->bd_tbl_dma);
-				data_desc->fast.sgl_byte_offset = 0;
-				data_desc->fast.task_reuse_cnt =
-				    io_req->reuse_count;
-				io_req->reuse_count++;
-				if (io_req->reuse_count == QEDF_MAX_REUSE) {
-					*ptu_invalidate = 1;
-					io_req->reuse_count = 0;
-				}
-				qedf->fast_sge_ios++;
-				io_req->sge_type = QEDF_IOREQ_FAST_SGE;
-			}
+			task_type = FCOE_TASK_TYPE_READ_INITIATOR;
+			rx_io_size = io_req->data_xfer_len;
 		}
-
-		/* Y Storm context */
-		task_ctx->ystorm_st_context.expect_first_xfer = 0;
-		task_ctx->ystorm_st_context.task_type =
-		    FCOE_TASK_TYPE_READ_INITIATOR;
-
-		/* T Storm context */
-		task_ctx->tstorm_st_context.read_only.task_type =
-		    FCOE_TASK_TYPE_READ_INITIATOR;
-		mst_sgl_mode = GET_FIELD(
-		    task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode,
-		    FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE);
-		SET_FIELD(task_ctx->tstorm_st_context.read_write.flags,
-		    FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE,
-		    mst_sgl_mode);
 	}
 
+	/* Setup the fields for fcoe_task_params */
+	io_req->task_params->context = task_ctx;
+	io_req->task_params->sqe = sqe;
+	io_req->task_params->task_type = task_type;
+	io_req->task_params->tx_io_size = tx_io_size;
+	io_req->task_params->rx_io_size = rx_io_size;
+	io_req->task_params->conn_cid = fcport->fw_cid;
+	io_req->task_params->itid = io_req->xid;
+	io_req->task_params->cq_rss_number = cq_idx;
+	io_req->task_params->is_tape_device = fcport->dev_type;
+
+	/* Fill in information for scatter/gather list */
+	if (io_req->cmd_type != QEDF_TASK_MGMT_CMD) {
+		bd_count = bd_tbl->bd_valid;
+		io_req->sgl_task_params->sgl = bd_tbl->bd_tbl;
+		io_req->sgl_task_params->sgl_phys_addr.lo =
+			U64_LO(bd_tbl->bd_tbl_dma);
+		io_req->sgl_task_params->sgl_phys_addr.hi =
+			U64_HI(bd_tbl->bd_tbl_dma);
+		io_req->sgl_task_params->num_sges = bd_count;
+		io_req->sgl_task_params->total_buffer_size =
+		    scsi_bufflen(io_req->sc_cmd);
+		io_req->sgl_task_params->small_mid_sge =
+			io_req->use_slowpath;
+	}
+
+	/* Fill in physical address of sense buffer */
+	sense_data_buffer_phys_addr.lo = U64_LO(io_req->sense_buffer_dma);
+	sense_data_buffer_phys_addr.hi = U64_HI(io_req->sense_buffer_dma);
+
 	/* fill FCP_CMND IU */
-	fcp_cmnd = (u32 *)task_ctx->ystorm_st_context.tx_info_union.fcp_cmd_payload.opaque;
-	qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)&tmp_fcp_cmnd);
+	qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)tmp_fcp_cmnd);
 
 	/* Swap fcp_cmnd since FC is big endian */
 	cnt = sizeof(struct fcp_cmnd) / sizeof(u32);
-
 	for (i = 0; i < cnt; i++) {
-		*fcp_cmnd = cpu_to_be32(tmp_fcp_cmnd[i]);
-		fcp_cmnd++;
+		tmp_fcp_cmnd[i] = cpu_to_be32(tmp_fcp_cmnd[i]);
+	}
+	memcpy(fcp_cmnd, tmp_fcp_cmnd, sizeof(struct fcp_cmnd));
+
+	init_initiator_rw_fcoe_task(io_req->task_params,
+				    io_req->sgl_task_params,
+				    sense_data_buffer_phys_addr,
+				    io_req->task_retry_identifier, fcp_cmnd);
+
+	/* Increment SGL type counters */
+	if (bd_count == 1) {
+		qedf->single_sge_ios++;
+		io_req->sge_type = QEDF_IOREQ_SINGLE_SGE;
+	} else if (io_req->use_slowpath) {
+		qedf->slow_sge_ios++;
+		io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
+	} else {
+		qedf->fast_sge_ios++;
+		io_req->sge_type = QEDF_IOREQ_FAST_SGE;
 	}
-
-	/* M Storm context - Sense buffer */
-	task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.lo =
-		U64_LO(io_req->sense_buffer_dma);
-	task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.hi =
-		U64_HI(io_req->sense_buffer_dma);
 }
 
 void qedf_init_mp_task(struct qedf_ioreq *io_req,
-	struct fcoe_task_context *task_ctx)
+	struct fcoe_task_context *task_ctx, struct fcoe_wqe *sqe)
 {
 	struct qedf_mp_req *mp_req = &(io_req->mp_req);
 	struct qedf_rport *fcport = io_req->fcport;
 	struct qedf_ctx *qedf = io_req->fcport->qedf;
 	struct fc_frame_header *fc_hdr;
-	enum fcoe_task_type task_type = 0;
-	union fcoe_data_desc_ctx *data_desc;
+	struct fcoe_tx_mid_path_params task_fc_hdr;
+	struct scsi_sgl_task_params tx_sgl_task_params;
+	struct scsi_sgl_task_params rx_sgl_task_params;
 
-	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "Initializing MP task "
-		   "for cmd_type = %d\n", io_req->cmd_type);
+	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+		  "Initializing MP task for cmd_type=%d\n",
+		  io_req->cmd_type);
 
 	qedf->control_requests++;
 
-	/* Obtain task_type */
-	if ((io_req->cmd_type == QEDF_TASK_MGMT_CMD) ||
-	    (io_req->cmd_type == QEDF_ELS)) {
-		task_type = FCOE_TASK_TYPE_MIDPATH;
-	} else if (io_req->cmd_type == QEDF_ABTS) {
-		task_type = FCOE_TASK_TYPE_ABTS;
-	}
-
+	memset(&tx_sgl_task_params, 0, sizeof(struct scsi_sgl_task_params));
+	memset(&rx_sgl_task_params, 0, sizeof(struct scsi_sgl_task_params));
 	memset(task_ctx, 0, sizeof(struct fcoe_task_context));
+	memset(&task_fc_hdr, 0, sizeof(struct fcoe_tx_mid_path_params));
 
 	/* Setup the task from io_req for easy reference */
 	io_req->task = task_ctx;
 
-	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "task type = %d\n",
-		   task_type);
-
-	/* YSTORM only */
-	{
-		/* Initialize YSTORM task context */
-		struct fcoe_tx_mid_path_params *task_fc_hdr =
-		    &task_ctx->ystorm_st_context.tx_info_union.tx_params.mid_path;
-		memset(task_fc_hdr, 0, sizeof(struct fcoe_tx_mid_path_params));
-		task_ctx->ystorm_st_context.task_rety_identifier =
-		    io_req->task_retry_identifier;
-
-		/* Init SGL parameters */
-		if ((task_type == FCOE_TASK_TYPE_MIDPATH) ||
-		    (task_type == FCOE_TASK_TYPE_UNSOLICITED)) {
-			data_desc = &task_ctx->ystorm_st_context.data_desc;
-			data_desc->slow.base_sgl_addr.lo =
-			    U64_LO(mp_req->mp_req_bd_dma);
-			data_desc->slow.base_sgl_addr.hi =
-			    U64_HI(mp_req->mp_req_bd_dma);
-			data_desc->slow.remainder_num_sges = 1;
-			data_desc->slow.curr_sge_off = 0;
-			data_desc->slow.curr_sgl_index = 0;
-		}
-
-		fc_hdr = &(mp_req->req_fc_hdr);
-		if (task_type == FCOE_TASK_TYPE_MIDPATH) {
-			fc_hdr->fh_ox_id = io_req->xid;
-			fc_hdr->fh_rx_id = htons(0xffff);
-		} else if (task_type == FCOE_TASK_TYPE_UNSOLICITED) {
-			fc_hdr->fh_rx_id = io_req->xid;
-		}
+	/* Setup the fields for fcoe_task_params */
+	io_req->task_params->context = task_ctx;
+	io_req->task_params->sqe = sqe;
+	io_req->task_params->task_type = FCOE_TASK_TYPE_MIDPATH;
+	io_req->task_params->tx_io_size = io_req->data_xfer_len;
+	/* rx_io_size tells the f/w how large a response buffer we have */
+	io_req->task_params->rx_io_size = PAGE_SIZE;
+	io_req->task_params->conn_cid = fcport->fw_cid;
+	io_req->task_params->itid = io_req->xid;
+	/* Return middle path commands on CQ 0 */
+	io_req->task_params->cq_rss_number = 0;
+	io_req->task_params->is_tape_device = fcport->dev_type;
+
+	fc_hdr = &(mp_req->req_fc_hdr);
+	/* Set OX_ID and RX_ID based on driver task id */
+	fc_hdr->fh_ox_id = io_req->xid;
+	fc_hdr->fh_rx_id = htons(0xffff);
+
+	/* Set up FC header information */
+	task_fc_hdr.parameter = fc_hdr->fh_parm_offset;
+	task_fc_hdr.r_ctl = fc_hdr->fh_r_ctl;
+	task_fc_hdr.type = fc_hdr->fh_type;
+	task_fc_hdr.cs_ctl = fc_hdr->fh_cs_ctl;
+	task_fc_hdr.df_ctl = fc_hdr->fh_df_ctl;
+	task_fc_hdr.rx_id = fc_hdr->fh_rx_id;
+	task_fc_hdr.ox_id = fc_hdr->fh_ox_id;
+
+	/* Set up s/g list parameters for request buffer */
+	tx_sgl_task_params.sgl = mp_req->mp_req_bd;
+	tx_sgl_task_params.sgl_phys_addr.lo = U64_LO(mp_req->mp_req_bd_dma);
+	tx_sgl_task_params.sgl_phys_addr.hi = U64_HI(mp_req->mp_req_bd_dma);
+	tx_sgl_task_params.num_sges = 1;
+	/* Set PAGE_SIZE for now since sg element is that size ??? */
+	tx_sgl_task_params.total_buffer_size = io_req->data_xfer_len;
+	tx_sgl_task_params.small_mid_sge = 0;
+
+	/* Set up s/g list parameters for request buffer */
+	rx_sgl_task_params.sgl = mp_req->mp_resp_bd;
+	rx_sgl_task_params.sgl_phys_addr.lo = U64_LO(mp_req->mp_resp_bd_dma);
+	rx_sgl_task_params.sgl_phys_addr.hi = U64_HI(mp_req->mp_resp_bd_dma);
+	rx_sgl_task_params.num_sges = 1;
+	/* Set PAGE_SIZE for now since sg element is that size ??? */
+	rx_sgl_task_params.total_buffer_size = PAGE_SIZE;
+	rx_sgl_task_params.small_mid_sge = 0;
 
-		/* Fill FC Header into middle path buffer */
-		task_fc_hdr->parameter = fc_hdr->fh_parm_offset;
-		task_fc_hdr->r_ctl = fc_hdr->fh_r_ctl;
-		task_fc_hdr->type = fc_hdr->fh_type;
-		task_fc_hdr->cs_ctl = fc_hdr->fh_cs_ctl;
-		task_fc_hdr->df_ctl = fc_hdr->fh_df_ctl;
-		task_fc_hdr->rx_id = fc_hdr->fh_rx_id;
-		task_fc_hdr->ox_id = fc_hdr->fh_ox_id;
-
-		task_ctx->ystorm_st_context.data_2_trns_rem =
-		    io_req->data_xfer_len;
-		task_ctx->ystorm_st_context.task_type = task_type;
-	}
-
-	/* TSTORM ONLY */
-	{
-		task_ctx->tstorm_ag_context.icid = (u16)fcport->fw_cid;
-		task_ctx->tstorm_st_context.read_only.cid = fcport->fw_cid;
-		/* Always send middle-path repsonses on CQ #0 */
-		task_ctx->tstorm_st_context.read_only.glbl_q_num = 0;
-		io_req->fp_idx = 0;
-		SET_FIELD(task_ctx->tstorm_ag_context.flags0,
-		    TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE,
-		    PROTOCOLID_FCOE);
-		task_ctx->tstorm_st_context.read_only.task_type = task_type;
-		SET_FIELD(task_ctx->tstorm_st_context.read_write.flags,
-		    FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME,
-		    1);
-		task_ctx->tstorm_st_context.read_write.rx_id = 0xffff;
-	}
-
-	/* MSTORM only */
-	{
-		if (task_type == FCOE_TASK_TYPE_MIDPATH) {
-			/* Initialize task context */
-			data_desc = &task_ctx->mstorm_st_context.fp.data_desc;
-
-			/* Set cache sges address and length */
-			data_desc->slow.base_sgl_addr.lo =
-			    U64_LO(mp_req->mp_resp_bd_dma);
-			data_desc->slow.base_sgl_addr.hi =
-			    U64_HI(mp_req->mp_resp_bd_dma);
-			data_desc->slow.remainder_num_sges = 1;
-			data_desc->slow.curr_sge_off = 0;
-			data_desc->slow.curr_sgl_index = 0;
 
-			/*
-			 * Also need to fil in non-fastpath response address
-			 * for middle path commands.
-			 */
-			task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.lo =
-			    U64_LO(mp_req->mp_resp_bd_dma);
-			task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.hi =
-			    U64_HI(mp_req->mp_resp_bd_dma);
-		}
-	}
-
-	/* USTORM ONLY */
-	{
-		task_ctx->ustorm_ag_context.global_cq_num = 0;
-	}
+	/*
+	 * Last arg is 0 as previous code did not set that we wanted the
+	 * fc header information.
+	 */
+	init_initiator_midpath_unsolicited_fcoe_task(io_req->task_params,
+						     &task_fc_hdr,
+						     &tx_sgl_task_params,
+						     &rx_sgl_task_params, 0);
 
-	/* I/O stats. Middle path commands always use slow SGEs */
-	qedf->slow_sge_ios++;
-	io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
+	/* Midpath requests always consume 1 SGE */
+	qedf->single_sge_ios++;
 }
 
-void qedf_add_to_sq(struct qedf_rport *fcport, u16 xid, u32 ptu_invalidate,
-	enum fcoe_task_type req_type, u32 offset)
+/* Presumed that fcport->rport_lock is held */
+u16 qedf_get_sqe_idx(struct qedf_rport *fcport)
 {
-	struct fcoe_wqe *sqe;
 	uint16_t total_sqe = (fcport->sq_mem_size)/(sizeof(struct fcoe_wqe));
+	u16 rval;
 
-	sqe = &fcport->sq[fcport->sq_prod_idx];
+	rval = fcport->sq_prod_idx;
 
+	/* Adjust ring index */
 	fcport->sq_prod_idx++;
 	fcport->fw_sq_prod_idx++;
 	if (fcport->sq_prod_idx == total_sqe)
 		fcport->sq_prod_idx = 0;
 
-	switch (req_type) {
-	case FCOE_TASK_TYPE_WRITE_INITIATOR:
-	case FCOE_TASK_TYPE_READ_INITIATOR:
-		SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, SEND_FCOE_CMD);
-		if (ptu_invalidate)
-			SET_FIELD(sqe->flags, FCOE_WQE_INVALIDATE_PTU, 1);
-		break;
-	case FCOE_TASK_TYPE_MIDPATH:
-		SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, SEND_FCOE_MIDPATH);
-		break;
-	case FCOE_TASK_TYPE_ABTS:
-		SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE,
-		    SEND_FCOE_ABTS_REQUEST);
-		break;
-	case FCOE_TASK_TYPE_EXCHANGE_CLEANUP:
-		SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE,
-		     FCOE_EXCHANGE_CLEANUP);
-		break;
-	case FCOE_TASK_TYPE_SEQUENCE_CLEANUP:
-		SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE,
-		    FCOE_SEQUENCE_RECOVERY);
-		/* NOTE: offset param only used for sequence recovery */
-		sqe->additional_info_union.seq_rec_updated_offset = offset;
-		break;
-	case FCOE_TASK_TYPE_UNSOLICITED:
-		break;
-	default:
-		break;
-	}
-
-	sqe->task_id = xid;
-
-	/* Make sure SQ data is coherent */
-	wmb();
-
+	return rval;
 }
 
 void qedf_ring_doorbell(struct qedf_rport *fcport)
@@ -1029,7 +847,8 @@ int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req)
 	struct fcoe_task_context *task_ctx;
 	u16 xid;
 	enum fcoe_task_type req_type = 0;
-	u32 ptu_invalidate = 0;
+	struct fcoe_wqe *sqe;
+	u16 sqe_idx;
 
 	/* Initialize rest of io_req fileds */
 	io_req->data_xfer_len = scsi_bufflen(sc_cmd);
@@ -1061,6 +880,16 @@ int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req)
 		return -EAGAIN;
 	}
 
+	if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
+		QEDF_ERR(&(qedf->dbg_ctx), "Session not offloaded yet.\n");
+		kref_put(&io_req->refcount, qedf_release_cmd);
+	}
+
+	/* Obtain free SQE */
+	sqe_idx = qedf_get_sqe_idx(fcport);
+	sqe = &fcport->sq[sqe_idx];
+	memset(sqe, 0, sizeof(struct fcoe_wqe));
+
 	/* Get the task context */
 	task_ctx = qedf_get_task_mem(&qedf->tasks, xid);
 	if (!task_ctx) {
@@ -1070,15 +899,7 @@ int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req)
 		return -EINVAL;
 	}
 
-	qedf_init_task(fcport, lport, io_req, &ptu_invalidate, task_ctx);
-
-	if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
-		QEDF_ERR(&(qedf->dbg_ctx), "Session not offloaded yet.\n");
-		kref_put(&io_req->refcount, qedf_release_cmd);
-	}
-
-	/* Obtain free SQ entry */
-	qedf_add_to_sq(fcport, xid, ptu_invalidate, req_type, 0);
+	qedf_init_task(fcport, lport, io_req, task_ctx, sqe);
 
 	/* Ring doorbell */
 	qedf_ring_doorbell(fcport);
@@ -1661,6 +1482,8 @@ int qedf_initiate_abts(struct qedf_ioreq *io_req, bool return_scsi_cmd_on_abts)
 	u32 r_a_tov = 0;
 	int rc = 0;
 	unsigned long flags;
+	struct fcoe_wqe *sqe;
+	u16 sqe_idx;
 
 	r_a_tov = rdata->r_a_tov;
 	lport = qedf->lport;
@@ -1712,10 +1535,12 @@ int qedf_initiate_abts(struct qedf_ioreq *io_req, bool return_scsi_cmd_on_abts)
 
 	spin_lock_irqsave(&fcport->rport_lock, flags);
 
-	/* Add ABTS to send queue */
-	qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_ABTS, 0);
+	sqe_idx = qedf_get_sqe_idx(fcport);
+	sqe = &fcport->sq[sqe_idx];
+	memset(sqe, 0, sizeof(struct fcoe_wqe));
+	io_req->task_params->sqe = sqe;
 
-	/* Ring doorbell */
+	init_initiator_abort_fcoe_task(io_req->task_params);
 	qedf_ring_doorbell(fcport);
 
 	spin_unlock_irqrestore(&fcport->rport_lock, flags);
@@ -1784,8 +1609,8 @@ void qedf_process_abts_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
 int qedf_init_mp_req(struct qedf_ioreq *io_req)
 {
 	struct qedf_mp_req *mp_req;
-	struct fcoe_sge *mp_req_bd;
-	struct fcoe_sge *mp_resp_bd;
+	struct scsi_sge *mp_req_bd;
+	struct scsi_sge *mp_resp_bd;
 	struct qedf_ctx *qedf = io_req->fcport->qedf;
 	dma_addr_t addr;
 	uint64_t sz;
@@ -1819,7 +1644,7 @@ int qedf_init_mp_req(struct qedf_ioreq *io_req)
 	}
 
 	/* Allocate and map mp_req_bd and mp_resp_bd */
-	sz = sizeof(struct fcoe_sge);
+	sz = sizeof(struct scsi_sge);
 	mp_req->mp_req_bd = dma_alloc_coherent(&qedf->pdev->dev, sz,
 	    &mp_req->mp_req_bd_dma, GFP_KERNEL);
 	if (!mp_req->mp_req_bd) {
@@ -1841,7 +1666,7 @@ int qedf_init_mp_req(struct qedf_ioreq *io_req)
 	mp_req_bd = mp_req->mp_req_bd;
 	mp_req_bd->sge_addr.lo = U64_LO(addr);
 	mp_req_bd->sge_addr.hi = U64_HI(addr);
-	mp_req_bd->size = QEDF_PAGE_SIZE;
+	mp_req_bd->sge_len = QEDF_PAGE_SIZE;
 
 	/*
 	 * MP buffer is either a task mgmt command or an ELS.
@@ -1852,7 +1677,7 @@ int qedf_init_mp_req(struct qedf_ioreq *io_req)
 	addr = mp_req->resp_buf_dma;
 	mp_resp_bd->sge_addr.lo = U64_LO(addr);
 	mp_resp_bd->sge_addr.hi = U64_HI(addr);
-	mp_resp_bd->size = QEDF_PAGE_SIZE;
+	mp_resp_bd->sge_len = QEDF_PAGE_SIZE;
 
 	return 0;
 }
@@ -1895,6 +1720,8 @@ int qedf_initiate_cleanup(struct qedf_ioreq *io_req,
 	int tmo = 0;
 	int rc = SUCCESS;
 	unsigned long flags;
+	struct fcoe_wqe *sqe;
+	u16 sqe_idx;
 
 	fcport = io_req->fcport;
 	if (!fcport) {
@@ -1940,12 +1767,16 @@ int qedf_initiate_cleanup(struct qedf_ioreq *io_req,
 
 	init_completion(&io_req->tm_done);
 
-	/* Obtain free SQ entry */
 	spin_lock_irqsave(&fcport->rport_lock, flags);
-	qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_EXCHANGE_CLEANUP, 0);
 
-	/* Ring doorbell */
+	sqe_idx = qedf_get_sqe_idx(fcport);
+	sqe = &fcport->sq[sqe_idx];
+	memset(sqe, 0, sizeof(struct fcoe_wqe));
+	io_req->task_params->sqe = sqe;
+
+	init_initiator_cleanup_fcoe_task(io_req->task_params);
 	qedf_ring_doorbell(fcport);
+
 	spin_unlock_irqrestore(&fcport->rport_lock, flags);
 
 	tmo = wait_for_completion_timeout(&io_req->tm_done,
@@ -1991,16 +1822,15 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd,
 	uint8_t tm_flags)
 {
 	struct qedf_ioreq *io_req;
-	struct qedf_mp_req *tm_req;
 	struct fcoe_task_context *task;
-	struct fc_frame_header *fc_hdr;
-	struct fcp_cmnd *fcp_cmnd;
 	struct qedf_ctx *qedf = fcport->qedf;
+	struct fc_lport *lport = qedf->lport;
 	int rc = 0;
 	uint16_t xid;
-	uint32_t sid, did;
 	int tmo = 0;
 	unsigned long flags;
+	struct fcoe_wqe *sqe;
+	u16 sqe_idx;
 
 	if (!sc_cmd) {
 		QEDF_ERR(&(qedf->dbg_ctx), "invalid arg\n");
@@ -2031,36 +1861,14 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd,
 	/* Set the return CPU to be the same as the request one */
 	io_req->cpu = smp_processor_id();
 
-	tm_req = (struct qedf_mp_req *)&(io_req->mp_req);
-
-	rc = qedf_init_mp_req(io_req);
-	if (rc == FAILED) {
-		QEDF_ERR(&(qedf->dbg_ctx), "Task mgmt MP request init "
-			  "failed\n");
-		kref_put(&io_req->refcount, qedf_release_cmd);
-		goto reset_tmf_err;
-	}
-
 	/* Set TM flags */
-	io_req->io_req_flags = 0;
-	tm_req->tm_flags = tm_flags;
+	io_req->io_req_flags = QEDF_READ;
+	io_req->data_xfer_len = 0;
+	io_req->tm_flags = tm_flags;
 
 	/* Default is to return a SCSI command when an error occurs */
 	io_req->return_scsi_cmd_on_abts = true;
 
-	/* Fill FCP_CMND */
-	qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)tm_req->req_buf);
-	fcp_cmnd = (struct fcp_cmnd *)tm_req->req_buf;
-	memset(fcp_cmnd->fc_cdb, 0, FCP_CMND_LEN);
-	fcp_cmnd->fc_dl = 0;
-
-	/* Fill FC header */
-	fc_hdr = &(tm_req->req_fc_hdr);
-	sid = fcport->sid;
-	did = fcport->rdata->ids.port_id;
-	__fc_fill_fc_hdr(fc_hdr, FC_RCTL_DD_UNSOL_CMD, sid, did,
-			   FC_TYPE_FCP, FC_FC_FIRST_SEQ | FC_FC_END_SEQ |
-			   FC_FC_SEQ_INIT, 0);
 	/* Obtain exchange id */
 	xid = io_req->xid;
 
@@ -2069,16 +1877,18 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd,
 
 	/* Initialize task context for this IO request */
 	task = qedf_get_task_mem(&qedf->tasks, xid);
-	qedf_init_mp_task(io_req, task);
 
 	init_completion(&io_req->tm_done);
 
-	/* Obtain free SQ entry */
 	spin_lock_irqsave(&fcport->rport_lock, flags);
-	qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_MIDPATH, 0);
 
-	/* Ring doorbell */
+	sqe_idx = qedf_get_sqe_idx(fcport);
+	sqe = &fcport->sq[sqe_idx];
+	memset(sqe, 0, sizeof(struct fcoe_wqe));
+
+	qedf_init_task(fcport, lport, io_req, task, sqe);
 	qedf_ring_doorbell(fcport);
+
 	spin_unlock_irqrestore(&fcport->rport_lock, flags);
 
 	tmo = wait_for_completion_timeout(&io_req->tm_done,
@@ -2162,14 +1972,6 @@ void qedf_process_tmf_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
 	struct qedf_ioreq *io_req)
 {
 	struct fcoe_cqe_rsp_info *fcp_rsp;
-	struct fcoe_cqe_midpath_info *mp_info;
-
-
-	/* Get TMF response length from CQE */
-	mp_info = &cqe->cqe_info.midpath_info;
-	io_req->mp_req.resp_len = mp_info->data_placement_size;
-	QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_SCSI_TM,
-	    "Response len is %d.\n", io_req->mp_req.resp_len);
 
 	fcp_rsp = &cqe->cqe_info.rsp_info;
 	qedf_parse_fcp_rsp(io_req, fcp_rsp);
diff --git a/drivers/scsi/qedi/Makefile b/drivers/scsi/qedi/Makefile
index 2b3e16b24299..90a6925577cc 100644
--- a/drivers/scsi/qedi/Makefile
+++ b/drivers/scsi/qedi/Makefile
@@ -1,5 +1,5 @@
 obj-$(CONFIG_QEDI) := qedi.o
 qedi-y := qedi_main.o qedi_iscsi.o qedi_fw.o qedi_sysfs.o \
-	    qedi_dbg.o
+	    qedi_dbg.o qedi_fw_api.o
 
 qedi-$(CONFIG_DEBUG_FS) += qedi_debugfs.o
diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c
index 2bce3efc66a4..d6978cbc56f0 100644
--- a/drivers/scsi/qedi/qedi_fw.c
+++ b/drivers/scsi/qedi/qedi_fw.c
@@ -14,6 +14,8 @@
 #include "qedi.h"
 #include "qedi_iscsi.h"
 #include "qedi_gbl.h"
+#include "qedi_fw_iscsi.h"
+#include "qedi_fw_scsi.h"
 
 static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn,
 			       struct iscsi_task *mtask);
@@ -53,8 +55,8 @@ static void qedi_process_logout_resp(struct qedi_ctx *qedi,
 	resp_hdr->exp_cmdsn = cpu_to_be32(cqe_logout_response->exp_cmd_sn);
 	resp_hdr->max_cmdsn = cpu_to_be32(cqe_logout_response->max_cmd_sn);
 
-	resp_hdr->t2wait = cpu_to_be32(cqe_logout_response->time2wait);
-	resp_hdr->t2retain = cpu_to_be32(cqe_logout_response->time2retain);
+	resp_hdr->t2wait = cpu_to_be32(cqe_logout_response->time_2_wait);
+	resp_hdr->t2retain = cpu_to_be32(cqe_logout_response->time_2_retain);
 
 	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
 		  "Freeing tid=0x%x for cid=0x%x\n",
@@ -975,81 +977,6 @@ exit_fp_process:
 	return;
 }
 
-static void qedi_add_to_sq(struct qedi_conn *qedi_conn, struct iscsi_task *task,
-			   u16 tid, uint16_t ptu_invalidate, int is_cleanup)
-{
-	struct iscsi_wqe *wqe;
-	struct iscsi_wqe_field *cont_field;
-	struct qedi_endpoint *ep;
-	struct scsi_cmnd *sc = task->sc;
-	struct iscsi_login_req *login_hdr;
-	struct qedi_cmd *cmd = task->dd_data;
-
-	login_hdr = (struct iscsi_login_req *)task->hdr;
-	ep = qedi_conn->ep;
-	wqe = &ep->sq[ep->sq_prod_idx];
-
-	memset(wqe, 0, sizeof(*wqe));
-
-	ep->sq_prod_idx++;
-	ep->fw_sq_prod_idx++;
-	if (ep->sq_prod_idx == QEDI_SQ_SIZE)
-		ep->sq_prod_idx = 0;
-
-	if (is_cleanup) {
-		SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
-			  ISCSI_WQE_TYPE_TASK_CLEANUP);
-		wqe->task_id = tid;
-		return;
-	}
-
-	if (ptu_invalidate) {
-		SET_FIELD(wqe->flags, ISCSI_WQE_PTU_INVALIDATE,
-			  ISCSI_WQE_SET_PTU_INVALIDATE);
-	}
-
-	cont_field = &wqe->cont_prevtid_union.cont_field;
-
-	switch (task->hdr->opcode & ISCSI_OPCODE_MASK) {
-	case ISCSI_OP_LOGIN:
-	case ISCSI_OP_TEXT:
-		SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
-			  ISCSI_WQE_TYPE_MIDDLE_PATH);
-		SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES,
-			  1);
-		cont_field->contlen_cdbsize_field = ntoh24(login_hdr->dlength);
-		break;
-	case ISCSI_OP_LOGOUT:
-	case ISCSI_OP_NOOP_OUT:
-	case ISCSI_OP_SCSI_TMFUNC:
-		 SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
-			   ISCSI_WQE_TYPE_NORMAL);
-		break;
-	default:
-		if (!sc)
-			break;
-
-		SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
-			  ISCSI_WQE_TYPE_NORMAL);
-		cont_field->contlen_cdbsize_field =
-				(sc->sc_data_direction == DMA_TO_DEVICE) ?
-				scsi_bufflen(sc) : 0;
-		if (cmd->use_slowpath)
-			SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES, 0);
-		else
-			SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES,
-				  (sc->sc_data_direction ==
-				   DMA_TO_DEVICE) ?
-				  min((u16)QEDI_FAST_SGE_COUNT,
-				      (u16)cmd->io_tbl.sge_valid) : 0);
-		break;
-	}
-
-	wqe->task_id = tid;
-	/* Make sure SQ data is coherent */
-	wmb();
-}
-
 static void qedi_ring_doorbell(struct qedi_conn *qedi_conn)
 {
 	struct iscsi_db_data dbell = { 0 };
@@ -1076,96 +1003,116 @@ static void qedi_ring_doorbell(struct qedi_conn *qedi_conn)
 		  qedi_conn->iscsi_conn_id);
 }
 
+static u16 qedi_get_wqe_idx(struct qedi_conn *qedi_conn)
+{
+	struct qedi_endpoint *ep;
+	u16 rval;
+
+	ep = qedi_conn->ep;
+	rval = ep->sq_prod_idx;
+
+	/* Increament SQ index */
+	ep->sq_prod_idx++;
+	ep->fw_sq_prod_idx++;
+	if (ep->sq_prod_idx == QEDI_SQ_SIZE)
+		ep->sq_prod_idx = 0;
+
+	return rval;
+}
+
 int qedi_send_iscsi_login(struct qedi_conn *qedi_conn,
 			  struct iscsi_task *task)
 {
-	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_login_req_hdr login_req_pdu_header;
+	struct scsi_sgl_task_params tx_sgl_task_params;
+	struct scsi_sgl_task_params rx_sgl_task_params;
+	struct iscsi_task_params task_params;
 	struct iscsi_task_context *fw_task_ctx;
+	struct qedi_ctx *qedi = qedi_conn->qedi;
 	struct iscsi_login_req *login_hdr;
-	struct iscsi_login_req_hdr *fw_login_req = NULL;
-	struct iscsi_cached_sge_ctx *cached_sge = NULL;
-	struct iscsi_sge *single_sge = NULL;
-	struct iscsi_sge *req_sge = NULL;
-	struct iscsi_sge *resp_sge = NULL;
+	struct scsi_sge *req_sge = NULL;
+	struct scsi_sge *resp_sge = NULL;
 	struct qedi_cmd *qedi_cmd;
-	s16 ptu_invalidate = 0;
+	struct qedi_endpoint *ep;
 	s16 tid = 0;
+	u16 sq_idx = 0;
+	int rval = 0;
 
-	req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
-	resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	req_sge = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	resp_sge = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
 	qedi_cmd = (struct qedi_cmd *)task->dd_data;
+	ep = qedi_conn->ep;
 	login_hdr = (struct iscsi_login_req *)task->hdr;
 
 	tid = qedi_get_task_idx(qedi);
 	if (tid == -1)
 		return -ENOMEM;
 
-	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+	fw_task_ctx =
+	     (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
 	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
 
 	qedi_cmd->task_id = tid;
 
-	/* Ystorm context */
-	fw_login_req = &fw_task_ctx->ystorm_st_context.pdu_hdr.login_req;
-	fw_login_req->opcode = login_hdr->opcode;
-	fw_login_req->version_min = login_hdr->min_version;
-	fw_login_req->version_max = login_hdr->max_version;
-	fw_login_req->flags_attr = login_hdr->flags;
-	fw_login_req->isid_tabc = *((u16 *)login_hdr->isid + 2);
-	fw_login_req->isid_d = *((u32 *)login_hdr->isid);
-	fw_login_req->tsih = login_hdr->tsih;
-	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
-	fw_login_req->itt = qedi_set_itt(tid, get_itt(task->itt));
-	fw_login_req->cid = qedi_conn->iscsi_conn_id;
-	fw_login_req->cmd_sn = be32_to_cpu(login_hdr->cmdsn);
-	fw_login_req->exp_stat_sn = be32_to_cpu(login_hdr->exp_statsn);
-	fw_login_req->exp_stat_sn = 0;
-
-	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
-		ptu_invalidate = 1;
-		qedi->tid_reuse_count[tid] = 0;
-	}
+	memset(&task_params, 0, sizeof(task_params));
+	memset(&login_req_pdu_header, 0, sizeof(login_req_pdu_header));
+	memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params));
+	memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params));
+	/* Update header info */
+	login_req_pdu_header.opcode = login_hdr->opcode;
+	login_req_pdu_header.version_min = login_hdr->min_version;
+	login_req_pdu_header.version_max = login_hdr->max_version;
+	login_req_pdu_header.flags_attr = login_hdr->flags;
+	login_req_pdu_header.isid_tabc = swab32p((u32 *)login_hdr->isid);
+	login_req_pdu_header.isid_d = swab16p((u16 *)&login_hdr->isid[4]);
+
+	login_req_pdu_header.tsih = login_hdr->tsih;
+	login_req_pdu_header.hdr_second_dword = ntoh24(login_hdr->dlength);
 
-	fw_task_ctx->ystorm_st_context.state.reuse_count =
-						qedi->tid_reuse_count[tid];
-	fw_task_ctx->mstorm_st_context.reuse_count =
-						qedi->tid_reuse_count[tid]++;
-	cached_sge =
-	       &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge;
-	cached_sge->sge.sge_len = req_sge->sge_len;
-	cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr);
-	cached_sge->sge.sge_addr.hi =
-			     (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
-
-	/* Mstorm context */
-	single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
-	fw_task_ctx->mstorm_st_context.task_type = 0x2;
-	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
-	single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
-	single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
-	single_sge->sge_len = resp_sge->sge_len;
-
-	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-		  ISCSI_MFLAGS_SINGLE_SGE, 1);
-	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-		  ISCSI_MFLAGS_SLOW_IO, 0);
-	fw_task_ctx->mstorm_st_context.sgl_size = 1;
-	fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
-
-	/* Ustorm context */
-	fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len;
-	fw_task_ctx->ustorm_st_context.exp_data_transfer_len =
-						ntoh24(login_hdr->dlength);
-	fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
-	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
-	fw_task_ctx->ustorm_st_context.task_type = 0x2;
-	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
-	fw_task_ctx->ustorm_ag_context.exp_data_acked =
-						 ntoh24(login_hdr->dlength);
-	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
-		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
-	SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
-		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
+	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
+	login_req_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt));
+	login_req_pdu_header.cid = qedi_conn->iscsi_conn_id;
+	login_req_pdu_header.cmd_sn = be32_to_cpu(login_hdr->cmdsn);
+	login_req_pdu_header.exp_stat_sn = be32_to_cpu(login_hdr->exp_statsn);
+	login_req_pdu_header.exp_stat_sn = 0;
+
+	/* Fill tx AHS and rx buffer */
+	tx_sgl_task_params.sgl =
+			       (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	tx_sgl_task_params.sgl_phys_addr.lo =
+					 (u32)(qedi_conn->gen_pdu.req_dma_addr);
+	tx_sgl_task_params.sgl_phys_addr.hi =
+			      (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+	tx_sgl_task_params.total_buffer_size = ntoh24(login_hdr->dlength);
+	tx_sgl_task_params.num_sges = 1;
+
+	rx_sgl_task_params.sgl =
+			      (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	rx_sgl_task_params.sgl_phys_addr.lo =
+					(u32)(qedi_conn->gen_pdu.resp_dma_addr);
+	rx_sgl_task_params.sgl_phys_addr.hi =
+			     (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32);
+	rx_sgl_task_params.total_buffer_size = resp_sge->sge_len;
+	rx_sgl_task_params.num_sges = 1;
+
+	/* Fill fw input params */
+	task_params.context = fw_task_ctx;
+	task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+	task_params.itid = tid;
+	task_params.cq_rss_number = 0;
+	task_params.tx_io_size = ntoh24(login_hdr->dlength);
+	task_params.rx_io_size = resp_sge->sge_len;
+
+	sq_idx = qedi_get_wqe_idx(qedi_conn);
+	task_params.sqe = &ep->sq[sq_idx];
+
+	memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+	rval = init_initiator_login_request_task(&task_params,
+						 &login_req_pdu_header,
+						 &tx_sgl_task_params,
+						 &rx_sgl_task_params);
+	if (rval)
+		return -1;
 
 	spin_lock(&qedi_conn->list_lock);
 	list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
@@ -1173,7 +1120,6 @@ int qedi_send_iscsi_login(struct qedi_conn *qedi_conn,
 	qedi_conn->active_cmd_count++;
 	spin_unlock(&qedi_conn->list_lock);
 
-	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
 	qedi_ring_doorbell(qedi_conn);
 	return 0;
 }
@@ -1181,65 +1127,64 @@ int qedi_send_iscsi_login(struct qedi_conn *qedi_conn,
 int qedi_send_iscsi_logout(struct qedi_conn *qedi_conn,
 			   struct iscsi_task *task)
 {
-	struct qedi_ctx *qedi = qedi_conn->qedi;
-	struct iscsi_logout_req_hdr *fw_logout_req = NULL;
-	struct iscsi_task_context *fw_task_ctx = NULL;
+	struct iscsi_logout_req_hdr logout_pdu_header;
+	struct scsi_sgl_task_params tx_sgl_task_params;
+	struct scsi_sgl_task_params rx_sgl_task_params;
+	struct iscsi_task_params task_params;
+	struct iscsi_task_context *fw_task_ctx;
 	struct iscsi_logout *logout_hdr = NULL;
-	struct qedi_cmd *qedi_cmd = NULL;
-	s16  tid = 0;
-	s16 ptu_invalidate = 0;
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct qedi_cmd *qedi_cmd;
+	struct qedi_endpoint *ep;
+	s16 tid = 0;
+	u16 sq_idx = 0;
+	int rval = 0;
 
 	qedi_cmd = (struct qedi_cmd *)task->dd_data;
 	logout_hdr = (struct iscsi_logout *)task->hdr;
+	ep = qedi_conn->ep;
 
 	tid = qedi_get_task_idx(qedi);
 	if (tid == -1)
 		return -ENOMEM;
 
-	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
-
+	fw_task_ctx =
+	     (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
 	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+
 	qedi_cmd->task_id = tid;
 
-	/* Ystorm context */
-	fw_logout_req = &fw_task_ctx->ystorm_st_context.pdu_hdr.logout_req;
-	fw_logout_req->opcode = ISCSI_OPCODE_LOGOUT_REQUEST;
-	fw_logout_req->reason_code = 0x80 | logout_hdr->flags;
-	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
-	fw_logout_req->itt = qedi_set_itt(tid, get_itt(task->itt));
-	fw_logout_req->exp_stat_sn = be32_to_cpu(logout_hdr->exp_statsn);
-	fw_logout_req->cmd_sn = be32_to_cpu(logout_hdr->cmdsn);
+	memset(&task_params, 0, sizeof(task_params));
+	memset(&logout_pdu_header, 0, sizeof(logout_pdu_header));
+	memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params));
+	memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params));
 
-	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
-		ptu_invalidate = 1;
-		qedi->tid_reuse_count[tid] = 0;
-	}
-	fw_task_ctx->ystorm_st_context.state.reuse_count =
-						  qedi->tid_reuse_count[tid];
-	fw_task_ctx->mstorm_st_context.reuse_count =
-						qedi->tid_reuse_count[tid]++;
-	fw_logout_req->cid = qedi_conn->iscsi_conn_id;
-	fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0;
-
-	/* Mstorm context */
-	fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
-	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
-
-	/* Ustorm context */
-	fw_task_ctx->ustorm_st_context.rem_rcv_len = 0;
-	fw_task_ctx->ustorm_st_context.exp_data_transfer_len = 0;
-	fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
-	fw_task_ctx->ustorm_st_context.task_type =  ISCSI_TASK_TYPE_MIDPATH;
-	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
-
-	SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
-		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
-	SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
-		  ISCSI_REG1_NUM_FAST_SGES, 0);
-
-	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
-	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
-		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+	/* Update header info */
+	logout_pdu_header.opcode = logout_hdr->opcode;
+	logout_pdu_header.reason_code = 0x80 | logout_hdr->flags;
+	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
+	logout_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt));
+	logout_pdu_header.exp_stat_sn = be32_to_cpu(logout_hdr->exp_statsn);
+	logout_pdu_header.cmd_sn = be32_to_cpu(logout_hdr->cmdsn);
+	logout_pdu_header.cid = qedi_conn->iscsi_conn_id;
+
+	/* Fill fw input params */
+	task_params.context = fw_task_ctx;
+	task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+	task_params.itid = tid;
+	task_params.cq_rss_number = 0;
+	task_params.tx_io_size = 0;
+	task_params.rx_io_size = 0;
+
+	sq_idx = qedi_get_wqe_idx(qedi_conn);
+	task_params.sqe = &ep->sq[sq_idx];
+	memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+
+	rval = init_initiator_logout_request_task(&task_params,
+						  &logout_pdu_header,
+						  NULL, NULL);
+	if (rval)
+		return -1;
 
 	spin_lock(&qedi_conn->list_lock);
 	list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
@@ -1247,9 +1192,7 @@ int qedi_send_iscsi_logout(struct qedi_conn *qedi_conn,
 	qedi_conn->active_cmd_count++;
 	spin_unlock(&qedi_conn->list_lock);
 
-	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
 	qedi_ring_doorbell(qedi_conn);
-
 	return 0;
 }
 
@@ -1533,47 +1476,46 @@ ldel_exit:
 static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn,
 			       struct iscsi_task *mtask)
 {
-	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_tmf_request_hdr tmf_pdu_header;
+	struct iscsi_task_params task_params;
 	struct qedi_ctx *qedi = qedi_conn->qedi;
 	struct iscsi_task_context *fw_task_ctx;
-	struct iscsi_tmf_request_hdr *fw_tmf_request;
-	struct iscsi_sge *single_sge;
-	struct qedi_cmd *qedi_cmd;
-	struct qedi_cmd *cmd;
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
 	struct iscsi_task *ctask;
 	struct iscsi_tm *tmf_hdr;
-	struct iscsi_sge *req_sge;
-	struct iscsi_sge *resp_sge;
-	u32 lun[2];
-	s16 tid = 0, ptu_invalidate = 0;
+	struct qedi_cmd *qedi_cmd;
+	struct qedi_cmd *cmd;
+	struct qedi_endpoint *ep;
+	u32 scsi_lun[2];
+	s16 tid = 0;
+	u16 sq_idx = 0;
+	int rval = 0;
 
-	req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
-	resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
-	qedi_cmd = (struct qedi_cmd *)mtask->dd_data;
 	tmf_hdr = (struct iscsi_tm *)mtask->hdr;
+	qedi_cmd = (struct qedi_cmd *)mtask->dd_data;
+	ep = qedi_conn->ep;
 
-	tid = qedi_cmd->task_id;
-	qedi_update_itt_map(qedi, tid, mtask->itt, qedi_cmd);
+	tid = qedi_get_task_idx(qedi);
+	if (tid == -1)
+		return -ENOMEM;
 
-	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+	fw_task_ctx =
+	     (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
 	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
 
-	fw_tmf_request = &fw_task_ctx->ystorm_st_context.pdu_hdr.tmf_request;
-	fw_tmf_request->itt = qedi_set_itt(tid, get_itt(mtask->itt));
-	fw_tmf_request->cmd_sn = be32_to_cpu(tmf_hdr->cmdsn);
+	qedi_cmd->task_id = tid;
 
-	memcpy(lun, &tmf_hdr->lun, sizeof(struct scsi_lun));
-	fw_tmf_request->lun.lo = be32_to_cpu(lun[0]);
-	fw_tmf_request->lun.hi = be32_to_cpu(lun[1]);
+	memset(&task_params, 0, sizeof(task_params));
+	memset(&tmf_pdu_header, 0, sizeof(tmf_pdu_header));
 
-	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
-		ptu_invalidate = 1;
-		qedi->tid_reuse_count[tid] = 0;
-	}
-	fw_task_ctx->ystorm_st_context.state.reuse_count =
-						qedi->tid_reuse_count[tid];
-	fw_task_ctx->mstorm_st_context.reuse_count =
-						qedi->tid_reuse_count[tid]++;
+	/* Update header info */
+	qedi_update_itt_map(qedi, tid, mtask->itt, qedi_cmd);
+	tmf_pdu_header.itt = qedi_set_itt(tid, get_itt(mtask->itt));
+	tmf_pdu_header.cmd_sn = be32_to_cpu(tmf_hdr->cmdsn);
+
+	memcpy(scsi_lun, &tmf_hdr->lun, sizeof(struct scsi_lun));
+	tmf_pdu_header.lun.lo = be32_to_cpu(scsi_lun[0]);
+	tmf_pdu_header.lun.hi = be32_to_cpu(scsi_lun[1]);
 
 	if ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
 	     ISCSI_TM_FUNC_ABORT_TASK) {
@@ -1584,53 +1526,34 @@ static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn,
 			return 0;
 		}
 		cmd = (struct qedi_cmd *)ctask->dd_data;
-		fw_tmf_request->rtt =
+		tmf_pdu_header.rtt =
 				qedi_set_itt(cmd->task_id,
 					     get_itt(tmf_hdr->rtt));
 	} else {
-		fw_tmf_request->rtt = ISCSI_RESERVED_TAG;
+		tmf_pdu_header.rtt = ISCSI_RESERVED_TAG;
 	}
 
-	fw_tmf_request->opcode = tmf_hdr->opcode;
-	fw_tmf_request->function = tmf_hdr->flags;
-	fw_tmf_request->hdr_second_dword = ntoh24(tmf_hdr->dlength);
-	fw_tmf_request->ref_cmd_sn = be32_to_cpu(tmf_hdr->refcmdsn);
-
-	single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
-	fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
-	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
-	single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
-	single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
-	single_sge->sge_len = resp_sge->sge_len;
-
-	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-		  ISCSI_MFLAGS_SINGLE_SGE, 1);
-	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-		  ISCSI_MFLAGS_SLOW_IO, 0);
-	fw_task_ctx->mstorm_st_context.sgl_size = 1;
-	fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
-
-	/* Ustorm context */
-	fw_task_ctx->ustorm_st_context.rem_rcv_len = 0;
-	fw_task_ctx->ustorm_st_context.exp_data_transfer_len = 0;
-	fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
-	fw_task_ctx->ustorm_st_context.task_type =  ISCSI_TASK_TYPE_MIDPATH;
-	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
-
-	SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
-		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
-	SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
-		  ISCSI_REG1_NUM_FAST_SGES, 0);
-
-	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
-	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
-		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
-	fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]);
-	fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]);
+	tmf_pdu_header.opcode = tmf_hdr->opcode;
+	tmf_pdu_header.function = tmf_hdr->flags;
+	tmf_pdu_header.hdr_second_dword = ntoh24(tmf_hdr->dlength);
+	tmf_pdu_header.ref_cmd_sn = be32_to_cpu(tmf_hdr->refcmdsn);
 
-	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
-		  "Add TMF to SQ, tmf tid=0x%x, itt=0x%x, cid=0x%x\n",
-		  tid,  mtask->itt, qedi_conn->iscsi_conn_id);
+	/* Fill fw input params */
+	task_params.context = fw_task_ctx;
+	task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+	task_params.itid = tid;
+	task_params.cq_rss_number = 0;
+	task_params.tx_io_size = 0;
+	task_params.rx_io_size = 0;
+
+	sq_idx = qedi_get_wqe_idx(qedi_conn);
+	task_params.sqe = &ep->sq[sq_idx];
+
+	memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+	rval = init_initiator_tmf_request_task(&task_params,
+					       &tmf_pdu_header);
+	if (rval)
+		return -1;
 
 	spin_lock(&qedi_conn->list_lock);
 	list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
@@ -1638,7 +1561,6 @@ static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn,
 	qedi_conn->active_cmd_count++;
 	spin_unlock(&qedi_conn->list_lock);
 
-	qedi_add_to_sq(qedi_conn, mtask, tid, ptu_invalidate, false);
 	qedi_ring_doorbell(qedi_conn);
 	return 0;
 }
@@ -1689,101 +1611,98 @@ int qedi_iscsi_abort_work(struct qedi_conn *qedi_conn,
 int qedi_send_iscsi_text(struct qedi_conn *qedi_conn,
 			 struct iscsi_task *task)
 {
-	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_text_request_hdr text_request_pdu_header;
+	struct scsi_sgl_task_params tx_sgl_task_params;
+	struct scsi_sgl_task_params rx_sgl_task_params;
+	struct iscsi_task_params task_params;
 	struct iscsi_task_context *fw_task_ctx;
-	struct iscsi_text_request_hdr *fw_text_request;
-	struct iscsi_cached_sge_ctx *cached_sge;
-	struct iscsi_sge *single_sge;
-	struct qedi_cmd *qedi_cmd;
-	/* For 6.5 hdr iscsi_hdr */
+	struct qedi_ctx *qedi = qedi_conn->qedi;
 	struct iscsi_text *text_hdr;
-	struct iscsi_sge *req_sge;
-	struct iscsi_sge *resp_sge;
-	s16 ptu_invalidate = 0;
+	struct scsi_sge *req_sge = NULL;
+	struct scsi_sge *resp_sge = NULL;
+	struct qedi_cmd *qedi_cmd;
+	struct qedi_endpoint *ep;
 	s16 tid = 0;
+	u16 sq_idx = 0;
+	int rval = 0;
 
-	req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
-	resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	req_sge = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	resp_sge = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
 	qedi_cmd = (struct qedi_cmd *)task->dd_data;
 	text_hdr = (struct iscsi_text *)task->hdr;
+	ep = qedi_conn->ep;
 
 	tid = qedi_get_task_idx(qedi);
 	if (tid == -1)
 		return -ENOMEM;
 
-	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+	fw_task_ctx =
+	     (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
 	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
 
 	qedi_cmd->task_id = tid;
 
-	/* Ystorm context */
-	fw_text_request =
-			&fw_task_ctx->ystorm_st_context.pdu_hdr.text_request;
-	fw_text_request->opcode = text_hdr->opcode;
-	fw_text_request->flags_attr = text_hdr->flags;
+	memset(&task_params, 0, sizeof(task_params));
+	memset(&text_request_pdu_header, 0, sizeof(text_request_pdu_header));
+	memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params));
+	memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params));
+
+	/* Update header info */
+	text_request_pdu_header.opcode = text_hdr->opcode;
+	text_request_pdu_header.flags_attr = text_hdr->flags;
 
 	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
-	fw_text_request->itt = qedi_set_itt(tid, get_itt(task->itt));
-	fw_text_request->ttt = text_hdr->ttt;
-	fw_text_request->cmd_sn = be32_to_cpu(text_hdr->cmdsn);
-	fw_text_request->exp_stat_sn = be32_to_cpu(text_hdr->exp_statsn);
-	fw_text_request->hdr_second_dword = ntoh24(text_hdr->dlength);
-
-	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
-		ptu_invalidate = 1;
-		qedi->tid_reuse_count[tid] = 0;
-	}
-	fw_task_ctx->ystorm_st_context.state.reuse_count =
-						     qedi->tid_reuse_count[tid];
-	fw_task_ctx->mstorm_st_context.reuse_count =
-						   qedi->tid_reuse_count[tid]++;
-
-	cached_sge =
-	       &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge;
-	cached_sge->sge.sge_len = req_sge->sge_len;
-	cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr);
-	cached_sge->sge.sge_addr.hi =
+	text_request_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt));
+	text_request_pdu_header.ttt = text_hdr->ttt;
+	text_request_pdu_header.cmd_sn = be32_to_cpu(text_hdr->cmdsn);
+	text_request_pdu_header.exp_stat_sn = be32_to_cpu(text_hdr->exp_statsn);
+	text_request_pdu_header.hdr_second_dword = ntoh24(text_hdr->dlength);
+
+	/* Fill tx AHS and rx buffer */
+	tx_sgl_task_params.sgl =
+			       (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	tx_sgl_task_params.sgl_phys_addr.lo =
+					 (u32)(qedi_conn->gen_pdu.req_dma_addr);
+	tx_sgl_task_params.sgl_phys_addr.hi =
 			      (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+	tx_sgl_task_params.total_buffer_size = req_sge->sge_len;
+	tx_sgl_task_params.num_sges = 1;
+
+	rx_sgl_task_params.sgl =
+			      (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	rx_sgl_task_params.sgl_phys_addr.lo =
+					(u32)(qedi_conn->gen_pdu.resp_dma_addr);
+	rx_sgl_task_params.sgl_phys_addr.hi =
+			     (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32);
+	rx_sgl_task_params.total_buffer_size = resp_sge->sge_len;
+	rx_sgl_task_params.num_sges = 1;
+
+	/* Fill fw input params */
+	task_params.context = fw_task_ctx;
+	task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+	task_params.itid = tid;
+	task_params.cq_rss_number = 0;
+	task_params.tx_io_size = ntoh24(text_hdr->dlength);
+	task_params.rx_io_size = resp_sge->sge_len;
+
+	sq_idx = qedi_get_wqe_idx(qedi_conn);
+	task_params.sqe = &ep->sq[sq_idx];
+
+	memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+	rval = init_initiator_text_request_task(&task_params,
+						&text_request_pdu_header,
+						&tx_sgl_task_params,
+						&rx_sgl_task_params);
+	if (rval)
+		return -1;
 
-	/* Mstorm context */
-	single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
-	fw_task_ctx->mstorm_st_context.task_type = 0x2;
-	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
-	single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
-	single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
-	single_sge->sge_len = resp_sge->sge_len;
-
-	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-		  ISCSI_MFLAGS_SINGLE_SGE, 1);
-	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-		  ISCSI_MFLAGS_SLOW_IO, 0);
-	fw_task_ctx->mstorm_st_context.sgl_size = 1;
-	fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
-
-	/* Ustorm context */
-	fw_task_ctx->ustorm_ag_context.exp_data_acked =
-						      ntoh24(text_hdr->dlength);
-	fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len;
-	fw_task_ctx->ustorm_st_context.exp_data_transfer_len =
-						      ntoh24(text_hdr->dlength);
-	fw_task_ctx->ustorm_st_context.exp_data_sn =
-					      be32_to_cpu(text_hdr->exp_statsn);
-	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
-	fw_task_ctx->ustorm_st_context.task_type = 0x2;
-	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
-	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
-		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
-
-	/*  Add command in active command list */
 	spin_lock(&qedi_conn->list_lock);
 	list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
 	qedi_cmd->io_cmd_in_list = true;
 	qedi_conn->active_cmd_count++;
 	spin_unlock(&qedi_conn->list_lock);
 
-	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
 	qedi_ring_doorbell(qedi_conn);
-
 	return 0;
 }
 
@@ -1791,58 +1710,62 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn,
 			   struct iscsi_task *task,
 			   char *datap, int data_len, int unsol)
 {
+	struct iscsi_nop_out_hdr nop_out_pdu_header;
+	struct scsi_sgl_task_params tx_sgl_task_params;
+	struct scsi_sgl_task_params rx_sgl_task_params;
+	struct iscsi_task_params task_params;
 	struct qedi_ctx *qedi = qedi_conn->qedi;
 	struct iscsi_task_context *fw_task_ctx;
-	struct iscsi_nop_out_hdr *fw_nop_out;
-	struct qedi_cmd *qedi_cmd;
-	/* For 6.5 hdr iscsi_hdr */
 	struct iscsi_nopout *nopout_hdr;
-	struct iscsi_cached_sge_ctx *cached_sge;
-	struct iscsi_sge *single_sge;
-	struct iscsi_sge *req_sge;
-	struct iscsi_sge *resp_sge;
-	u32 lun[2];
-	s16 ptu_invalidate = 0;
+	struct scsi_sge *req_sge = NULL;
+	struct scsi_sge *resp_sge = NULL;
+	struct qedi_cmd *qedi_cmd;
+	struct qedi_endpoint *ep;
+	u32 scsi_lun[2];
 	s16 tid = 0;
+	u16 sq_idx = 0;
+	int rval = 0;
 
-	req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
-	resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	req_sge = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	resp_sge = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
 	qedi_cmd = (struct qedi_cmd *)task->dd_data;
 	nopout_hdr = (struct iscsi_nopout *)task->hdr;
+	ep = qedi_conn->ep;
 
 	tid = qedi_get_task_idx(qedi);
-	if (tid == -1) {
-		QEDI_WARN(&qedi->dbg_ctx, "Invalid tid\n");
+	if (tid == -1)
 		return -ENOMEM;
-	}
-
-	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
 
+	fw_task_ctx =
+	     (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
 	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+
 	qedi_cmd->task_id = tid;
 
-	/* Ystorm context */
-	fw_nop_out = &fw_task_ctx->ystorm_st_context.pdu_hdr.nop_out;
-	SET_FIELD(fw_nop_out->flags_attr, ISCSI_NOP_OUT_HDR_CONST1, 1);
-	SET_FIELD(fw_nop_out->flags_attr, ISCSI_NOP_OUT_HDR_RSRV, 0);
+	memset(&task_params, 0, sizeof(task_params));
+	memset(&nop_out_pdu_header, 0, sizeof(nop_out_pdu_header));
+	memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params));
+	memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params));
+
+	/* Update header info */
+	nop_out_pdu_header.opcode = nopout_hdr->opcode;
+	SET_FIELD(nop_out_pdu_header.flags_attr, ISCSI_NOP_OUT_HDR_CONST1, 1);
+	SET_FIELD(nop_out_pdu_header.flags_attr, ISCSI_NOP_OUT_HDR_RSRV, 0);
 
-	memcpy(lun, &nopout_hdr->lun, sizeof(struct scsi_lun));
-	fw_nop_out->lun.lo = be32_to_cpu(lun[0]);
-	fw_nop_out->lun.hi = be32_to_cpu(lun[1]);
+	memcpy(scsi_lun, &nopout_hdr->lun, sizeof(struct scsi_lun));
+	nop_out_pdu_header.lun.lo = be32_to_cpu(scsi_lun[0]);
+	nop_out_pdu_header.lun.hi = be32_to_cpu(scsi_lun[1]);
+	nop_out_pdu_header.cmd_sn = be32_to_cpu(nopout_hdr->cmdsn);
+	nop_out_pdu_header.exp_stat_sn = be32_to_cpu(nopout_hdr->exp_statsn);
 
 	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
 
 	if (nopout_hdr->ttt != ISCSI_TTT_ALL_ONES) {
-		fw_nop_out->itt = be32_to_cpu(nopout_hdr->itt);
-		fw_nop_out->ttt = be32_to_cpu(nopout_hdr->ttt);
-		fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0;
-		fw_task_ctx->ystorm_st_context.state.local_comp = 1;
-		SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
-			  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 1);
+		nop_out_pdu_header.itt = be32_to_cpu(nopout_hdr->itt);
+		nop_out_pdu_header.ttt = be32_to_cpu(nopout_hdr->ttt);
 	} else {
-		fw_nop_out->itt = qedi_set_itt(tid, get_itt(task->itt));
-		fw_nop_out->ttt = ISCSI_TTT_ALL_ONES;
-		fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0;
+		nop_out_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt));
+		nop_out_pdu_header.ttt = ISCSI_TTT_ALL_ONES;
 
 		spin_lock(&qedi_conn->list_lock);
 		list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
@@ -1851,53 +1774,46 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn,
 		spin_unlock(&qedi_conn->list_lock);
 	}
 
-	fw_nop_out->opcode = ISCSI_OPCODE_NOP_OUT;
-	fw_nop_out->cmd_sn = be32_to_cpu(nopout_hdr->cmdsn);
-	fw_nop_out->exp_stat_sn = be32_to_cpu(nopout_hdr->exp_statsn);
-
-	cached_sge =
-	       &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge;
-	cached_sge->sge.sge_len = req_sge->sge_len;
-	cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr);
-	cached_sge->sge.sge_addr.hi =
-			(u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
-
-	/* Mstorm context */
-	fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
-	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
-
-	single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
-	single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
-	single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
-	single_sge->sge_len = resp_sge->sge_len;
-	fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
-
-	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
-		ptu_invalidate = 1;
-		qedi->tid_reuse_count[tid] = 0;
-	}
-	fw_task_ctx->ystorm_st_context.state.reuse_count =
-						qedi->tid_reuse_count[tid];
-	fw_task_ctx->mstorm_st_context.reuse_count =
-						qedi->tid_reuse_count[tid]++;
-	/* Ustorm context */
-	fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len;
-	fw_task_ctx->ustorm_st_context.exp_data_transfer_len = data_len;
-	fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
-	fw_task_ctx->ustorm_st_context.task_type =  ISCSI_TASK_TYPE_MIDPATH;
-	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
-
-	SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
-		  ISCSI_REG1_NUM_FAST_SGES, 0);
-
-	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
-	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
-		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
-
-	fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]);
-	fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]);
-
-	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
+	/* Fill tx AHS and rx buffer */
+	if (data_len) {
+		tx_sgl_task_params.sgl =
+			       (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+		tx_sgl_task_params.sgl_phys_addr.lo =
+					 (u32)(qedi_conn->gen_pdu.req_dma_addr);
+		tx_sgl_task_params.sgl_phys_addr.hi =
+			      (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+		tx_sgl_task_params.total_buffer_size = data_len;
+		tx_sgl_task_params.num_sges = 1;
+
+		rx_sgl_task_params.sgl =
+			      (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+		rx_sgl_task_params.sgl_phys_addr.lo =
+					(u32)(qedi_conn->gen_pdu.resp_dma_addr);
+		rx_sgl_task_params.sgl_phys_addr.hi =
+			     (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32);
+		rx_sgl_task_params.total_buffer_size = resp_sge->sge_len;
+		rx_sgl_task_params.num_sges = 1;
+	}
+
+	/* Fill fw input params */
+	task_params.context = fw_task_ctx;
+	task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+	task_params.itid = tid;
+	task_params.cq_rss_number = 0;
+	task_params.tx_io_size = data_len;
+	task_params.rx_io_size = resp_sge->sge_len;
+
+	sq_idx = qedi_get_wqe_idx(qedi_conn);
+	task_params.sqe = &ep->sq[sq_idx];
+
+	memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+	rval = init_initiator_nop_out_task(&task_params,
+					   &nop_out_pdu_header,
+					   &tx_sgl_task_params,
+					   &rx_sgl_task_params);
+	if (rval)
+		return -1;
+
 	qedi_ring_doorbell(qedi_conn);
 	return 0;
 }
@@ -1905,7 +1821,7 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn,
 static int qedi_split_bd(struct qedi_cmd *cmd, u64 addr, int sg_len,
 			 int bd_index)
 {
-	struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+	struct scsi_sge *bd = cmd->io_tbl.sge_tbl;
 	int frag_size, sg_frags;
 
 	sg_frags = 0;
@@ -1938,7 +1854,7 @@ static int qedi_split_bd(struct qedi_cmd *cmd, u64 addr, int sg_len,
 static int qedi_map_scsi_sg(struct qedi_ctx *qedi, struct qedi_cmd *cmd)
 {
 	struct scsi_cmnd *sc = cmd->scsi_cmd;
-	struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+	struct scsi_sge *bd = cmd->io_tbl.sge_tbl;
 	struct scatterlist *sg;
 	int byte_count = 0;
 	int bd_count = 0;
@@ -2040,7 +1956,7 @@ static void qedi_iscsi_map_sg_list(struct qedi_cmd *cmd)
 		if (bd_count == 0)
 			return;
 	} else {
-		struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+		struct scsi_sge *bd = cmd->io_tbl.sge_tbl;
 
 		bd[0].sge_addr.lo = 0;
 		bd[0].sge_addr.hi = 0;
@@ -2136,244 +2052,182 @@ int qedi_iscsi_send_ioreq(struct iscsi_task *task)
 	struct qedi_conn *qedi_conn = conn->dd_data;
 	struct qedi_cmd *cmd = task->dd_data;
 	struct scsi_cmnd *sc = task->sc;
+	struct iscsi_cmd_hdr cmd_pdu_header;
+	struct scsi_sgl_task_params tx_sgl_task_params;
+	struct scsi_sgl_task_params rx_sgl_task_params;
+	struct scsi_sgl_task_params *prx_sgl = NULL;
+	struct scsi_sgl_task_params *ptx_sgl = NULL;
+	struct iscsi_task_params task_params;
+	struct iscsi_conn_params conn_params;
+	struct scsi_initiator_cmd_params cmd_params;
 	struct iscsi_task_context *fw_task_ctx;
-	struct iscsi_cached_sge_ctx *cached_sge;
-	struct iscsi_phys_sgl_ctx *phys_sgl;
-	struct iscsi_virt_sgl_ctx *virt_sgl;
-	struct ystorm_iscsi_task_st_ctx *yst_cxt;
-	struct mstorm_iscsi_task_st_ctx *mst_cxt;
-	struct iscsi_sgl *sgl_struct;
-	struct iscsi_sge *single_sge;
+	struct iscsi_cls_conn *cls_conn;
 	struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)task->hdr;
-	struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
-	enum iscsi_task_type task_type;
-	struct iscsi_cmd_hdr *fw_cmd;
-	u32 lun[2];
-	u32 exp_data;
-	u16 cq_idx = smp_processor_id() % qedi->num_queues;
-	s16 ptu_invalidate = 0;
+	enum iscsi_task_type task_type = MAX_ISCSI_TASK_TYPE;
+	struct qedi_endpoint *ep;
+	u32 scsi_lun[2];
 	s16 tid = 0;
-	u8 num_fast_sgs;
+	u16 sq_idx = 0;
+	u16 cq_idx;
+	int rval = 0;
 
-	tid = qedi_get_task_idx(qedi);
-	if (tid == -1)
-		return -ENOMEM;
+	ep = qedi_conn->ep;
+	cls_conn = qedi_conn->cls_conn;
+	conn = cls_conn->dd_data;
 
 	qedi_iscsi_map_sg_list(cmd);
+	int_to_scsilun(sc->device->lun, (struct scsi_lun *)scsi_lun);
 
-	int_to_scsilun(sc->device->lun, (struct scsi_lun *)lun);
-	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+	tid = qedi_get_task_idx(qedi);
+	if (tid == -1)
+		return -ENOMEM;
 
+	fw_task_ctx =
+	     (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
 	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
-	cmd->task_id = tid;
 
-	/* Ystorm context */
-	fw_cmd = &fw_task_ctx->ystorm_st_context.pdu_hdr.cmd;
-	SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_ATTR, ISCSI_ATTR_SIMPLE);
+	cmd->task_id = tid;
 
+	memset(&task_params, 0, sizeof(task_params));
+	memset(&cmd_pdu_header, 0, sizeof(cmd_pdu_header));
+	memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params));
+	memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params));
+	memset(&conn_params, 0, sizeof(conn_params));
+	memset(&cmd_params, 0, sizeof(cmd_params));
+
+	cq_idx = smp_processor_id() % qedi->num_queues;
+	/* Update header info */
+	SET_FIELD(cmd_pdu_header.flags_attr, ISCSI_CMD_HDR_ATTR,
+		  ISCSI_ATTR_SIMPLE);
 	if (sc->sc_data_direction == DMA_TO_DEVICE) {
-		if (conn->session->initial_r2t_en) {
-			exp_data = min((conn->session->imm_data_en *
-					conn->max_xmit_dlength),
-				       conn->session->first_burst);
-			exp_data = min(exp_data, scsi_bufflen(sc));
-			fw_task_ctx->ustorm_ag_context.exp_data_acked =
-							  cpu_to_le32(exp_data);
-		} else {
-			fw_task_ctx->ustorm_ag_context.exp_data_acked =
-			      min(conn->session->first_burst, scsi_bufflen(sc));
-		}
-
-		SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_WRITE, 1);
+		SET_FIELD(cmd_pdu_header.flags_attr,
+			  ISCSI_CMD_HDR_WRITE, 1);
 		task_type = ISCSI_TASK_TYPE_INITIATOR_WRITE;
 	} else {
-		if (scsi_bufflen(sc))
-			SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_READ, 1);
+		SET_FIELD(cmd_pdu_header.flags_attr,
+			  ISCSI_CMD_HDR_READ, 1);
 		task_type = ISCSI_TASK_TYPE_INITIATOR_READ;
 	}
 
-	fw_cmd->lun.lo = be32_to_cpu(lun[0]);
-	fw_cmd->lun.hi = be32_to_cpu(lun[1]);
+	cmd_pdu_header.lun.lo = be32_to_cpu(scsi_lun[0]);
+	cmd_pdu_header.lun.hi = be32_to_cpu(scsi_lun[1]);
 
 	qedi_update_itt_map(qedi, tid, task->itt, cmd);
-	fw_cmd->itt = qedi_set_itt(tid, get_itt(task->itt));
-	fw_cmd->expected_transfer_length = scsi_bufflen(sc);
-	fw_cmd->cmd_sn = be32_to_cpu(hdr->cmdsn);
-	fw_cmd->opcode = hdr->opcode;
-	qedi_cpy_scsi_cdb(sc, (u32 *)fw_cmd->cdb);
-
-	/* Mstorm context */
-	fw_task_ctx->mstorm_st_context.sense_db.lo = (u32)cmd->sense_buffer_dma;
-	fw_task_ctx->mstorm_st_context.sense_db.hi =
-					(u32)((u64)cmd->sense_buffer_dma >> 32);
-	fw_task_ctx->mstorm_ag_context.task_cid = qedi_conn->iscsi_conn_id;
-	fw_task_ctx->mstorm_st_context.task_type = task_type;
-
-	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
-		ptu_invalidate = 1;
-		qedi->tid_reuse_count[tid] = 0;
-	}
-	fw_task_ctx->ystorm_st_context.state.reuse_count =
-						     qedi->tid_reuse_count[tid];
-	fw_task_ctx->mstorm_st_context.reuse_count =
-						   qedi->tid_reuse_count[tid]++;
-
-	/* Ustorm context */
-	fw_task_ctx->ustorm_st_context.rem_rcv_len = scsi_bufflen(sc);
-	fw_task_ctx->ustorm_st_context.exp_data_transfer_len = scsi_bufflen(sc);
-	fw_task_ctx->ustorm_st_context.exp_data_sn =
-						   be32_to_cpu(hdr->exp_statsn);
-	fw_task_ctx->ustorm_st_context.task_type = task_type;
-	fw_task_ctx->ustorm_st_context.cq_rss_number = cq_idx;
-	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
-
-	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
-		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
-	SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
-		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
-
-	num_fast_sgs = (cmd->io_tbl.sge_valid ?
-			min((u16)QEDI_FAST_SGE_COUNT,
-			    (u16)cmd->io_tbl.sge_valid) : 0);
-	SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
-		  ISCSI_REG1_NUM_FAST_SGES, num_fast_sgs);
-
-	fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]);
-	fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]);
-
-	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO, "Total sge count [%d]\n",
-		  cmd->io_tbl.sge_valid);
-
-	yst_cxt = &fw_task_ctx->ystorm_st_context;
-	mst_cxt = &fw_task_ctx->mstorm_st_context;
-	/* Tx path */
+	cmd_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt));
+	cmd_pdu_header.expected_transfer_length = cpu_to_be32(hdr->data_length);
+	cmd_pdu_header.hdr_second_dword = ntoh24(hdr->dlength);
+	cmd_pdu_header.cmd_sn = be32_to_cpu(hdr->cmdsn);
+	cmd_pdu_header.opcode = hdr->opcode;
+	qedi_cpy_scsi_cdb(sc, (u32 *)cmd_pdu_header.cdb);
+
+	/* Fill tx AHS and rx buffer */
 	if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) {
-		/* not considering  superIO or FastIO */
-		if (cmd->io_tbl.sge_valid == 1) {
-			cached_sge = &yst_cxt->state.sgl_ctx_union.cached_sge;
-			cached_sge->sge.sge_addr.lo = bd[0].sge_addr.lo;
-			cached_sge->sge.sge_addr.hi = bd[0].sge_addr.hi;
-			cached_sge->sge.sge_len = bd[0].sge_len;
-			qedi->cached_sgls++;
-		} else if ((cmd->io_tbl.sge_valid != 1) && cmd->use_slowpath) {
-			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-				  ISCSI_MFLAGS_SLOW_IO, 1);
-			SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
-				  ISCSI_REG1_NUM_FAST_SGES, 0);
-			phys_sgl = &yst_cxt->state.sgl_ctx_union.phys_sgl;
-			phys_sgl->sgl_base.lo = (u32)(cmd->io_tbl.sge_tbl_dma);
-			phys_sgl->sgl_base.hi =
-				     (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
-			phys_sgl->sgl_size = cmd->io_tbl.sge_valid;
-			qedi->slow_sgls++;
-		} else if ((cmd->io_tbl.sge_valid != 1) && !cmd->use_slowpath) {
-			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-				  ISCSI_MFLAGS_SLOW_IO, 0);
-			SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
-				  ISCSI_REG1_NUM_FAST_SGES,
-				  min((u16)QEDI_FAST_SGE_COUNT,
-				      (u16)cmd->io_tbl.sge_valid));
-			virt_sgl = &yst_cxt->state.sgl_ctx_union.virt_sgl;
-			virt_sgl->sgl_base.lo = (u32)(cmd->io_tbl.sge_tbl_dma);
-			virt_sgl->sgl_base.hi =
+		tx_sgl_task_params.sgl = cmd->io_tbl.sge_tbl;
+		tx_sgl_task_params.sgl_phys_addr.lo =
+						 (u32)(cmd->io_tbl.sge_tbl_dma);
+		tx_sgl_task_params.sgl_phys_addr.hi =
 				      (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
-			virt_sgl->sgl_initial_offset =
-				 (u32)bd[0].sge_addr.lo & (QEDI_PAGE_SIZE - 1);
-			qedi->fast_sgls++;
-		}
-		fw_task_ctx->mstorm_st_context.sgl_size = cmd->io_tbl.sge_valid;
-		fw_task_ctx->mstorm_st_context.rem_task_size = scsi_bufflen(sc);
-	} else {
-	/* Rx path */
-		if (cmd->io_tbl.sge_valid == 1) {
-			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-				  ISCSI_MFLAGS_SLOW_IO, 0);
-			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-				  ISCSI_MFLAGS_SINGLE_SGE, 1);
-			single_sge = &mst_cxt->sgl_union.single_sge;
-			single_sge->sge_addr.lo = bd[0].sge_addr.lo;
-			single_sge->sge_addr.hi = bd[0].sge_addr.hi;
-			single_sge->sge_len = bd[0].sge_len;
-			qedi->cached_sgls++;
-		} else if ((cmd->io_tbl.sge_valid != 1) && cmd->use_slowpath) {
-			sgl_struct = &mst_cxt->sgl_union.sgl_struct;
-			sgl_struct->sgl_addr.lo =
-						(u32)(cmd->io_tbl.sge_tbl_dma);
-			sgl_struct->sgl_addr.hi =
-				     (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
-			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-				  ISCSI_MFLAGS_SLOW_IO, 1);
-			SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
-				  ISCSI_REG1_NUM_FAST_SGES, 0);
-			sgl_struct->updated_sge_size = 0;
-			sgl_struct->updated_sge_offset = 0;
-			qedi->slow_sgls++;
-		} else if ((cmd->io_tbl.sge_valid != 1) && !cmd->use_slowpath) {
-			sgl_struct = &mst_cxt->sgl_union.sgl_struct;
-			sgl_struct->sgl_addr.lo =
-						(u32)(cmd->io_tbl.sge_tbl_dma);
-			sgl_struct->sgl_addr.hi =
-				     (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
-			sgl_struct->byte_offset =
-				(u32)bd[0].sge_addr.lo & (QEDI_PAGE_SIZE - 1);
-			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
-				  ISCSI_MFLAGS_SLOW_IO, 0);
-			SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
-				  ISCSI_REG1_NUM_FAST_SGES, 0);
-			sgl_struct->updated_sge_size = 0;
-			sgl_struct->updated_sge_offset = 0;
-			qedi->fast_sgls++;
-		}
-		fw_task_ctx->mstorm_st_context.sgl_size = cmd->io_tbl.sge_valid;
-		fw_task_ctx->mstorm_st_context.rem_task_size = scsi_bufflen(sc);
-	}
-
-	if (cmd->io_tbl.sge_valid == 1)
-		/* Singel-SGL */
-		qedi->use_cached_sge = true;
-	else {
+		tx_sgl_task_params.total_buffer_size = scsi_bufflen(sc);
+		tx_sgl_task_params.num_sges = cmd->io_tbl.sge_valid;
 		if (cmd->use_slowpath)
-			qedi->use_slow_sge = true;
-		else
-			qedi->use_fast_sge = true;
-	}
+			tx_sgl_task_params.small_mid_sge = true;
+	} else if (task_type == ISCSI_TASK_TYPE_INITIATOR_READ) {
+		rx_sgl_task_params.sgl = cmd->io_tbl.sge_tbl;
+		rx_sgl_task_params.sgl_phys_addr.lo =
+						 (u32)(cmd->io_tbl.sge_tbl_dma);
+		rx_sgl_task_params.sgl_phys_addr.hi =
+				      (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
+		rx_sgl_task_params.total_buffer_size = scsi_bufflen(sc);
+		rx_sgl_task_params.num_sges = cmd->io_tbl.sge_valid;
+	}
+
+	/* Add conn param */
+	conn_params.first_burst_length = conn->session->first_burst;
+	conn_params.max_send_pdu_length = conn->max_xmit_dlength;
+	conn_params.max_burst_length = conn->session->max_burst;
+	if (conn->session->initial_r2t_en)
+		conn_params.initial_r2t = true;
+	if (conn->session->imm_data_en)
+		conn_params.immediate_data = true;
+
+	/* Add cmd params */
+	cmd_params.sense_data_buffer_phys_addr.lo = (u32)cmd->sense_buffer_dma;
+	cmd_params.sense_data_buffer_phys_addr.hi =
+					(u32)((u64)cmd->sense_buffer_dma >> 32);
+	/* Fill fw input params */
+	task_params.context = fw_task_ctx;
+	task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+	task_params.itid = tid;
+	task_params.cq_rss_number = cq_idx;
+	if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE)
+		task_params.tx_io_size = scsi_bufflen(sc);
+	else if (task_type == ISCSI_TASK_TYPE_INITIATOR_READ)
+		task_params.rx_io_size = scsi_bufflen(sc);
+
+	sq_idx = qedi_get_wqe_idx(qedi_conn);
+	task_params.sqe = &ep->sq[sq_idx];
+
 	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO,
-		  "%s: %s-SGL: num_sges=0x%x first-sge-lo=0x%x first-sge-hi=0x%x",
+		  "%s: %s-SGL: sg_len=0x%x num_sges=0x%x first-sge-lo=0x%x first-sge-hi=0x%x\n",
 		  (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) ?
 		  "Write " : "Read ", (cmd->io_tbl.sge_valid == 1) ?
 		  "Single" : (cmd->use_slowpath ? "SLOW" : "FAST"),
-		  (u16)cmd->io_tbl.sge_valid, (u32)(cmd->io_tbl.sge_tbl_dma),
+		  (u16)cmd->io_tbl.sge_valid, scsi_bufflen(sc),
+		  (u32)(cmd->io_tbl.sge_tbl_dma),
 		  (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32));
 
-	/*  Add command in active command list */
+	memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+
+	if (task_params.tx_io_size != 0)
+		ptx_sgl = &tx_sgl_task_params;
+	if (task_params.rx_io_size != 0)
+		prx_sgl = &rx_sgl_task_params;
+
+	rval = init_initiator_rw_iscsi_task(&task_params, &conn_params,
+					    &cmd_params, &cmd_pdu_header,
+					    ptx_sgl, prx_sgl,
+					    NULL);
+	if (rval)
+		return -1;
+
 	spin_lock(&qedi_conn->list_lock);
 	list_add_tail(&cmd->io_cmd, &qedi_conn->active_cmd_list);
 	cmd->io_cmd_in_list = true;
 	qedi_conn->active_cmd_count++;
 	spin_unlock(&qedi_conn->list_lock);
 
-	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
 	qedi_ring_doorbell(qedi_conn);
-	if (qedi_io_tracing)
-		qedi_trace_io(qedi, task, tid, QEDI_IO_TRACE_REQ);
-
 	return 0;
 }
 
 int qedi_iscsi_cleanup_task(struct iscsi_task *task, bool mark_cmd_node_deleted)
 {
+	struct iscsi_task_params task_params;
+	struct qedi_endpoint *ep;
 	struct iscsi_conn *conn = task->conn;
 	struct qedi_conn *qedi_conn = conn->dd_data;
 	struct qedi_cmd *cmd = task->dd_data;
-	s16 ptu_invalidate = 0;
+	u16 sq_idx = 0;
+	int rval = 0;
 
 	QEDI_INFO(&qedi_conn->qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
 		  "issue cleanup tid=0x%x itt=0x%x task_state=%d cmd_state=0%x cid=0x%x\n",
 		  cmd->task_id, get_itt(task->itt), task->state,
 		  cmd->state, qedi_conn->iscsi_conn_id);
 
-	qedi_add_to_sq(qedi_conn, task, cmd->task_id, ptu_invalidate, true);
-	qedi_ring_doorbell(qedi_conn);
+	memset(&task_params, 0, sizeof(task_params));
+	ep = qedi_conn->ep;
+
+	sq_idx = qedi_get_wqe_idx(qedi_conn);
+
+	task_params.sqe = &ep->sq[sq_idx];
+	memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+	task_params.itid = cmd->task_id;
 
+	rval = init_cleanup_task(&task_params);
+	if (rval)
+		return rval;
+
+	qedi_ring_doorbell(qedi_conn);
 	return 0;
 }
diff --git a/drivers/scsi/qedi/qedi_fw_api.c b/drivers/scsi/qedi/qedi_fw_api.c
new file mode 100644
index 000000000000..fd354d4e03eb
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_fw_api.c
@@ -0,0 +1,781 @@
+/* QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available 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.
+ */
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include "qedi_hsi.h"
+#include <linux/qed/qed_if.h>
+
+#include "qedi_fw_iscsi.h"
+#include "qedi_fw_scsi.h"
+
+#define SCSI_NUM_SGES_IN_CACHE 0x4
+
+static bool scsi_is_slow_sgl(u16 num_sges, bool small_mid_sge)
+{
+	return (num_sges > SCSI_NUM_SGES_SLOW_SGL_THR && small_mid_sge);
+}
+
+static
+void init_scsi_sgl_context(struct scsi_sgl_params *ctx_sgl_params,
+			   struct scsi_cached_sges *ctx_data_desc,
+			   struct scsi_sgl_task_params *sgl_task_params)
+{
+	u8 sge_index;
+	u8 num_sges;
+	u32 val;
+
+	num_sges = (sgl_task_params->num_sges > SCSI_NUM_SGES_IN_CACHE) ?
+			     SCSI_NUM_SGES_IN_CACHE : sgl_task_params->num_sges;
+
+	/* sgl params */
+	val = cpu_to_le32(sgl_task_params->sgl_phys_addr.lo);
+	ctx_sgl_params->sgl_addr.lo = val;
+	val = cpu_to_le32(sgl_task_params->sgl_phys_addr.hi);
+	ctx_sgl_params->sgl_addr.hi = val;
+	val = cpu_to_le32(sgl_task_params->total_buffer_size);
+	ctx_sgl_params->sgl_total_length = val;
+	ctx_sgl_params->sgl_num_sges = cpu_to_le16(sgl_task_params->num_sges);
+
+	for (sge_index = 0; sge_index < num_sges; sge_index++) {
+		val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.lo);
+		ctx_data_desc->sge[sge_index].sge_addr.lo = val;
+		val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.hi);
+		ctx_data_desc->sge[sge_index].sge_addr.hi = val;
+		val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_len);
+		ctx_data_desc->sge[sge_index].sge_len = val;
+	}
+}
+
+static u32 calc_rw_task_size(struct iscsi_task_params *task_params,
+			     enum iscsi_task_type task_type,
+			     struct scsi_sgl_task_params *sgl_task_params,
+			     struct scsi_dif_task_params *dif_task_params)
+{
+	u32 io_size;
+
+	if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE ||
+	    task_type == ISCSI_TASK_TYPE_TARGET_READ)
+		io_size = task_params->tx_io_size;
+	else
+		io_size = task_params->rx_io_size;
+
+	if (!io_size)
+		return 0;
+
+	if (!dif_task_params)
+		return io_size;
+
+	return !dif_task_params->dif_on_network ?
+	       io_size : sgl_task_params->total_buffer_size;
+}
+
+static void
+init_dif_context_flags(struct iscsi_dif_flags *ctx_dif_flags,
+		       struct scsi_dif_task_params *dif_task_params)
+{
+	if (!dif_task_params)
+		return;
+
+	SET_FIELD(ctx_dif_flags->flags, ISCSI_DIF_FLAGS_PROT_INTERVAL_SIZE_LOG,
+		  dif_task_params->dif_block_size_log);
+	SET_FIELD(ctx_dif_flags->flags, ISCSI_DIF_FLAGS_DIF_TO_PEER,
+		  dif_task_params->dif_on_network ? 1 : 0);
+	SET_FIELD(ctx_dif_flags->flags, ISCSI_DIF_FLAGS_HOST_INTERFACE,
+		  dif_task_params->dif_on_host ? 1 : 0);
+}
+
+static void init_sqe(struct iscsi_task_params *task_params,
+		     struct scsi_sgl_task_params *sgl_task_params,
+		     struct scsi_dif_task_params *dif_task_params,
+		     struct iscsi_common_hdr *pdu_header,
+		     struct scsi_initiator_cmd_params *cmd_params,
+		     enum iscsi_task_type task_type,
+		     bool is_cleanup)
+{
+	if (!task_params->sqe)
+		return;
+
+	memset(task_params->sqe, 0, sizeof(*task_params->sqe));
+	task_params->sqe->task_id = cpu_to_le16(task_params->itid);
+	if (is_cleanup) {
+		SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE,
+			  ISCSI_WQE_TYPE_TASK_CLEANUP);
+		return;
+	}
+
+	switch (task_type) {
+	case ISCSI_TASK_TYPE_INITIATOR_WRITE:
+	{
+		u32 buf_size = 0;
+		u32 num_sges = 0;
+
+		init_dif_context_flags(&task_params->sqe->prot_flags,
+				       dif_task_params);
+
+		SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE,
+			  ISCSI_WQE_TYPE_NORMAL);
+
+		if (task_params->tx_io_size) {
+			buf_size = calc_rw_task_size(task_params, task_type,
+						     sgl_task_params,
+						     dif_task_params);
+
+		if (scsi_is_slow_sgl(sgl_task_params->num_sges,
+				     sgl_task_params->small_mid_sge))
+			num_sges = ISCSI_WQE_NUM_SGES_SLOWIO;
+		else
+			num_sges = min(sgl_task_params->num_sges,
+				       (u16)SCSI_NUM_SGES_SLOW_SGL_THR);
+	}
+
+	SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES, num_sges);
+	SET_FIELD(task_params->sqe->contlen_cdbsize, ISCSI_WQE_CONT_LEN,
+		  buf_size);
+
+	if (GET_FIELD(pdu_header->hdr_second_dword,
+		      ISCSI_CMD_HDR_TOTAL_AHS_LEN))
+		SET_FIELD(task_params->sqe->contlen_cdbsize, ISCSI_WQE_CDB_SIZE,
+			  cmd_params->extended_cdb_sge.sge_len);
+	}
+		break;
+	case ISCSI_TASK_TYPE_INITIATOR_READ:
+		SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE,
+			  ISCSI_WQE_TYPE_NORMAL);
+
+		if (GET_FIELD(pdu_header->hdr_second_dword,
+			      ISCSI_CMD_HDR_TOTAL_AHS_LEN))
+			SET_FIELD(task_params->sqe->contlen_cdbsize,
+				  ISCSI_WQE_CDB_SIZE,
+				  cmd_params->extended_cdb_sge.sge_len);
+		break;
+	case ISCSI_TASK_TYPE_LOGIN_RESPONSE:
+	case ISCSI_TASK_TYPE_MIDPATH:
+	{
+		bool advance_statsn = true;
+
+		if (task_type == ISCSI_TASK_TYPE_LOGIN_RESPONSE)
+			SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE,
+				  ISCSI_WQE_TYPE_LOGIN);
+		else
+			SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE,
+				  ISCSI_WQE_TYPE_MIDDLE_PATH);
+
+		if (task_type == ISCSI_TASK_TYPE_MIDPATH) {
+			u8 opcode = GET_FIELD(pdu_header->hdr_first_byte,
+					      ISCSI_COMMON_HDR_OPCODE);
+
+			if (opcode != ISCSI_OPCODE_TEXT_RESPONSE &&
+			    (opcode != ISCSI_OPCODE_NOP_IN ||
+			    pdu_header->itt == ISCSI_TTT_ALL_ONES))
+				advance_statsn = false;
+		}
+
+		SET_FIELD(task_params->sqe->flags, ISCSI_WQE_RESPONSE,
+			  advance_statsn ? 1 : 0);
+
+		if (task_params->tx_io_size) {
+			SET_FIELD(task_params->sqe->contlen_cdbsize,
+				  ISCSI_WQE_CONT_LEN, task_params->tx_io_size);
+
+		if (scsi_is_slow_sgl(sgl_task_params->num_sges,
+				     sgl_task_params->small_mid_sge))
+			SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES,
+				  ISCSI_WQE_NUM_SGES_SLOWIO);
+		else
+			SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES,
+				  min(sgl_task_params->num_sges,
+				      (u16)SCSI_NUM_SGES_SLOW_SGL_THR));
+		}
+	}
+		break;
+	default:
+		break;
+	}
+}
+
+static void init_default_iscsi_task(struct iscsi_task_params *task_params,
+				    struct data_hdr *pdu_header,
+				    enum iscsi_task_type task_type)
+{
+	struct iscsi_task_context *context;
+	u16 index;
+	u32 val;
+
+	context = task_params->context;
+	memset(context, 0, sizeof(*context));
+
+	for (index = 0; index <
+	     ARRAY_SIZE(context->ystorm_st_context.pdu_hdr.data.data);
+	     index++) {
+		val = cpu_to_le32(pdu_header->data[index]);
+		context->ystorm_st_context.pdu_hdr.data.data[index] = val;
+	}
+
+	context->mstorm_st_context.task_type = task_type;
+	context->mstorm_ag_context.task_cid =
+					    cpu_to_le16(task_params->conn_icid);
+
+	SET_FIELD(context->ustorm_ag_context.flags1,
+		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+
+	context->ustorm_st_context.task_type = task_type;
+	context->ustorm_st_context.cq_rss_number = task_params->cq_rss_number;
+	context->ustorm_ag_context.icid = cpu_to_le16(task_params->conn_icid);
+}
+
+static
+void init_initiator_rw_cdb_ystorm_context(struct ystorm_iscsi_task_st_ctx *ystc,
+					  struct scsi_initiator_cmd_params *cmd)
+{
+	union iscsi_task_hdr *ctx_pdu_hdr = &ystc->pdu_hdr;
+	u32 val;
+
+	if (!cmd->extended_cdb_sge.sge_len)
+		return;
+
+	SET_FIELD(ctx_pdu_hdr->ext_cdb_cmd.hdr_second_dword,
+		  ISCSI_EXT_CDB_CMD_HDR_CDB_SIZE,
+		  cmd->extended_cdb_sge.sge_len);
+	val = cpu_to_le32(cmd->extended_cdb_sge.sge_addr.lo);
+	ctx_pdu_hdr->ext_cdb_cmd.cdb_sge.sge_addr.lo = val;
+	val = cpu_to_le32(cmd->extended_cdb_sge.sge_addr.hi);
+	ctx_pdu_hdr->ext_cdb_cmd.cdb_sge.sge_addr.hi = val;
+	val = cpu_to_le32(cmd->extended_cdb_sge.sge_len);
+	ctx_pdu_hdr->ext_cdb_cmd.cdb_sge.sge_len  = val;
+}
+
+static
+void init_ustorm_task_contexts(struct ustorm_iscsi_task_st_ctx *ustorm_st_cxt,
+			       struct ustorm_iscsi_task_ag_ctx *ustorm_ag_cxt,
+			       u32 remaining_recv_len,
+			       u32 expected_data_transfer_len,
+			       u8 num_sges, bool tx_dif_conn_err_en)
+{
+	u32 val;
+
+	ustorm_st_cxt->rem_rcv_len = cpu_to_le32(remaining_recv_len);
+	ustorm_ag_cxt->exp_data_acked = cpu_to_le32(expected_data_transfer_len);
+	val = cpu_to_le32(expected_data_transfer_len);
+	ustorm_st_cxt->exp_data_transfer_len = val;
+	SET_FIELD(ustorm_st_cxt->reg1.reg1_map, ISCSI_REG1_NUM_SGES, num_sges);
+	SET_FIELD(ustorm_ag_cxt->flags2,
+		  USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_EN,
+		  tx_dif_conn_err_en ? 1 : 0);
+}
+
+static
+void set_rw_exp_data_acked_and_cont_len(struct iscsi_task_context *context,
+					struct iscsi_conn_params  *conn_params,
+					enum iscsi_task_type task_type,
+					u32 task_size,
+					u32 exp_data_transfer_len,
+					u8 total_ahs_length)
+{
+	u32 max_unsolicited_data = 0, val;
+
+	if (total_ahs_length &&
+	    (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE ||
+	     task_type == ISCSI_TASK_TYPE_INITIATOR_READ))
+		SET_FIELD(context->ustorm_st_context.flags2,
+			  USTORM_ISCSI_TASK_ST_CTX_AHS_EXIST, 1);
+
+	switch (task_type) {
+	case ISCSI_TASK_TYPE_INITIATOR_WRITE:
+		if (!conn_params->initial_r2t)
+			max_unsolicited_data = conn_params->first_burst_length;
+		else if (conn_params->immediate_data)
+			max_unsolicited_data =
+					  min(conn_params->first_burst_length,
+					      conn_params->max_send_pdu_length);
+
+		context->ustorm_ag_context.exp_data_acked =
+				   cpu_to_le32(total_ahs_length == 0 ?
+						min(exp_data_transfer_len,
+						    max_unsolicited_data) :
+						((u32)(total_ahs_length +
+						       ISCSI_AHS_CNTL_SIZE)));
+		break;
+	case ISCSI_TASK_TYPE_TARGET_READ:
+		val = cpu_to_le32(exp_data_transfer_len);
+		context->ustorm_ag_context.exp_data_acked = val;
+		break;
+	case ISCSI_TASK_TYPE_INITIATOR_READ:
+		context->ustorm_ag_context.exp_data_acked =
+					cpu_to_le32((total_ahs_length == 0 ? 0 :
+						     total_ahs_length +
+						     ISCSI_AHS_CNTL_SIZE));
+		break;
+	case ISCSI_TASK_TYPE_TARGET_WRITE:
+		val = cpu_to_le32(task_size);
+		context->ustorm_ag_context.exp_cont_len = val;
+		break;
+	default:
+		break;
+	}
+}
+
+static
+void init_rtdif_task_context(struct rdif_task_context *rdif_context,
+			     struct tdif_task_context *tdif_context,
+			     struct scsi_dif_task_params *dif_task_params,
+			     enum iscsi_task_type task_type)
+{
+	u32 val;
+
+	if (!dif_task_params->dif_on_network || !dif_task_params->dif_on_host)
+		return;
+
+	if (task_type == ISCSI_TASK_TYPE_TARGET_WRITE ||
+	    task_type == ISCSI_TASK_TYPE_INITIATOR_READ) {
+		rdif_context->app_tag_value =
+				  cpu_to_le16(dif_task_params->application_tag);
+		rdif_context->partial_crc_value = cpu_to_le16(0xffff);
+		val = cpu_to_le32(dif_task_params->initial_ref_tag);
+		rdif_context->initial_ref_tag = val;
+		rdif_context->app_tag_mask =
+			     cpu_to_le16(dif_task_params->application_tag_mask);
+		SET_FIELD(rdif_context->flags0, RDIF_TASK_CONTEXT_CRC_SEED,
+			  dif_task_params->crc_seed ? 1 : 0);
+		SET_FIELD(rdif_context->flags0, RDIF_TASK_CONTEXT_HOSTGUARDTYPE,
+			  dif_task_params->host_guard_type);
+		SET_FIELD(rdif_context->flags0,
+			  RDIF_TASK_CONTEXT_PROTECTIONTYPE,
+			  dif_task_params->protection_type);
+		SET_FIELD(rdif_context->flags0,
+			  RDIF_TASK_CONTEXT_INITIALREFTAGVALID, 1);
+		SET_FIELD(rdif_context->flags0,
+			  RDIF_TASK_CONTEXT_KEEPREFTAGCONST,
+			  dif_task_params->keep_ref_tag_const ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_VALIDATEAPPTAG,
+			  (dif_task_params->validate_app_tag &&
+			  dif_task_params->dif_on_network) ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_VALIDATEGUARD,
+			  (dif_task_params->validate_guard &&
+			  dif_task_params->dif_on_network) ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_VALIDATEREFTAG,
+			  (dif_task_params->validate_ref_tag &&
+			  dif_task_params->dif_on_network) ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_HOSTINTERFACE,
+			  dif_task_params->dif_on_host ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_NETWORKINTERFACE,
+			  dif_task_params->dif_on_network ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_FORWARDGUARD,
+			  dif_task_params->forward_guard ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_FORWARDAPPTAG,
+			  dif_task_params->forward_app_tag ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_FORWARDREFTAG,
+			  dif_task_params->forward_ref_tag ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_FORWARDAPPTAGWITHMASK,
+			  dif_task_params->forward_app_tag_with_mask ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_FORWARDREFTAGWITHMASK,
+			  dif_task_params->forward_ref_tag_with_mask ? 1 : 0);
+		SET_FIELD(rdif_context->flags1,
+			  RDIF_TASK_CONTEXT_INTERVALSIZE,
+			  dif_task_params->dif_block_size_log - 9);
+		SET_FIELD(rdif_context->state,
+			  RDIF_TASK_CONTEXT_REFTAGMASK,
+			  dif_task_params->ref_tag_mask);
+		SET_FIELD(rdif_context->state, RDIF_TASK_CONTEXT_IGNOREAPPTAG,
+			  dif_task_params->ignore_app_tag);
+	}
+
+	if (task_type == ISCSI_TASK_TYPE_TARGET_READ ||
+	    task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) {
+		tdif_context->app_tag_value =
+				  cpu_to_le16(dif_task_params->application_tag);
+		tdif_context->partial_crc_valueB =
+		       cpu_to_le16(dif_task_params->crc_seed ? 0xffff : 0x0000);
+		tdif_context->partial_crc_value_a =
+		       cpu_to_le16(dif_task_params->crc_seed ? 0xffff : 0x0000);
+		SET_FIELD(tdif_context->flags0, TDIF_TASK_CONTEXT_CRC_SEED,
+			  dif_task_params->crc_seed ? 1 : 0);
+
+		SET_FIELD(tdif_context->flags0,
+			  TDIF_TASK_CONTEXT_SETERRORWITHEOP,
+			  dif_task_params->tx_dif_conn_err_en ? 1 : 0);
+		SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_FORWARDGUARD,
+			  dif_task_params->forward_guard   ? 1 : 0);
+		SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_FORWARDAPPTAG,
+			  dif_task_params->forward_app_tag ? 1 : 0);
+		SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_FORWARDREFTAG,
+			  dif_task_params->forward_ref_tag ? 1 : 0);
+		SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_INTERVALSIZE,
+			  dif_task_params->dif_block_size_log - 9);
+		SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_HOSTINTERFACE,
+			  dif_task_params->dif_on_host    ? 1 : 0);
+		SET_FIELD(tdif_context->flags1,
+			  TDIF_TASK_CONTEXT_NETWORKINTERFACE,
+			  dif_task_params->dif_on_network ? 1 : 0);
+		val = cpu_to_le32(dif_task_params->initial_ref_tag);
+		tdif_context->initial_ref_tag = val;
+		tdif_context->app_tag_mask =
+			     cpu_to_le16(dif_task_params->application_tag_mask);
+		SET_FIELD(tdif_context->flags0,
+			  TDIF_TASK_CONTEXT_HOSTGUARDTYPE,
+			  dif_task_params->host_guard_type);
+		SET_FIELD(tdif_context->flags0,
+			  TDIF_TASK_CONTEXT_PROTECTIONTYPE,
+			  dif_task_params->protection_type);
+		SET_FIELD(tdif_context->flags0,
+			  TDIF_TASK_CONTEXT_INITIALREFTAGVALID,
+			  dif_task_params->initial_ref_tag_is_valid ? 1 : 0);
+		SET_FIELD(tdif_context->flags0,
+			  TDIF_TASK_CONTEXT_KEEPREFTAGCONST,
+			  dif_task_params->keep_ref_tag_const ? 1 : 0);
+		SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_VALIDATEGUARD,
+			  (dif_task_params->validate_guard &&
+			   dif_task_params->dif_on_host) ? 1 : 0);
+		SET_FIELD(tdif_context->flags1,
+			  TDIF_TASK_CONTEXT_VALIDATEAPPTAG,
+			  (dif_task_params->validate_app_tag &&
+			  dif_task_params->dif_on_host) ? 1 : 0);
+		SET_FIELD(tdif_context->flags1,
+			  TDIF_TASK_CONTEXT_VALIDATEREFTAG,
+			  (dif_task_params->validate_ref_tag &&
+			   dif_task_params->dif_on_host) ? 1 : 0);
+		SET_FIELD(tdif_context->flags1,
+			  TDIF_TASK_CONTEXT_FORWARDAPPTAGWITHMASK,
+			  dif_task_params->forward_app_tag_with_mask ? 1 : 0);
+		SET_FIELD(tdif_context->flags1,
+			  TDIF_TASK_CONTEXT_FORWARDREFTAGWITHMASK,
+			  dif_task_params->forward_ref_tag_with_mask ? 1 : 0);
+		SET_FIELD(tdif_context->flags1,
+			  TDIF_TASK_CONTEXT_REFTAGMASK,
+			  dif_task_params->ref_tag_mask);
+		SET_FIELD(tdif_context->flags0,
+			  TDIF_TASK_CONTEXT_IGNOREAPPTAG,
+			  dif_task_params->ignore_app_tag ? 1 : 0);
+	}
+}
+
+static void set_local_completion_context(struct iscsi_task_context *context)
+{
+	SET_FIELD(context->ystorm_st_context.state.flags,
+		  YSTORM_ISCSI_TASK_STATE_LOCAL_COMP, 1);
+	SET_FIELD(context->ustorm_st_context.flags,
+		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 1);
+}
+
+static int init_rw_iscsi_task(struct iscsi_task_params *task_params,
+			      enum iscsi_task_type task_type,
+			      struct iscsi_conn_params *conn_params,
+			      struct iscsi_common_hdr *pdu_header,
+			      struct scsi_sgl_task_params *sgl_task_params,
+			      struct scsi_initiator_cmd_params *cmd_params,
+			      struct scsi_dif_task_params *dif_task_params)
+{
+	u32 exp_data_transfer_len = conn_params->max_burst_length;
+	struct iscsi_task_context *cxt;
+	bool slow_io = false;
+	u32 task_size, val;
+	u8 num_sges = 0;
+
+	task_size = calc_rw_task_size(task_params, task_type, sgl_task_params,
+				      dif_task_params);
+
+	init_default_iscsi_task(task_params, (struct data_hdr *)pdu_header,
+				task_type);
+
+	cxt = task_params->context;
+
+	val = cpu_to_le32(task_size);
+	cxt->ystorm_st_context.pdu_hdr.cmd.expected_transfer_length = val;
+	init_initiator_rw_cdb_ystorm_context(&cxt->ystorm_st_context,
+					     cmd_params);
+	val = cpu_to_le32(cmd_params->sense_data_buffer_phys_addr.lo);
+	cxt->mstorm_st_context.sense_db.lo = val;
+
+	val = cpu_to_le32(cmd_params->sense_data_buffer_phys_addr.hi);
+	cxt->mstorm_st_context.sense_db.hi = val;
+
+	if (task_params->tx_io_size) {
+		init_dif_context_flags(&cxt->ystorm_st_context.state.dif_flags,
+				       dif_task_params);
+		init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params,
+				      &cxt->ystorm_st_context.state.data_desc,
+				      sgl_task_params);
+
+		slow_io = scsi_is_slow_sgl(sgl_task_params->num_sges,
+					   sgl_task_params->small_mid_sge);
+
+		num_sges = !slow_io ? min_t(u16, sgl_task_params->num_sges,
+					    (u16)SCSI_NUM_SGES_SLOW_SGL_THR) :
+				      ISCSI_WQE_NUM_SGES_SLOWIO;
+
+		if (slow_io) {
+			SET_FIELD(cxt->ystorm_st_context.state.flags,
+				  YSTORM_ISCSI_TASK_STATE_SLOW_IO, 1);
+		}
+	} else if (task_params->rx_io_size) {
+		init_dif_context_flags(&cxt->mstorm_st_context.dif_flags,
+				       dif_task_params);
+		init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params,
+				      &cxt->mstorm_st_context.data_desc,
+				      sgl_task_params);
+		num_sges = !scsi_is_slow_sgl(sgl_task_params->num_sges,
+				sgl_task_params->small_mid_sge) ?
+				min_t(u16, sgl_task_params->num_sges,
+				      (u16)SCSI_NUM_SGES_SLOW_SGL_THR) :
+				ISCSI_WQE_NUM_SGES_SLOWIO;
+		cxt->mstorm_st_context.rem_task_size = cpu_to_le32(task_size);
+	}
+
+	if (exp_data_transfer_len > task_size  ||
+	    task_type != ISCSI_TASK_TYPE_TARGET_WRITE)
+		exp_data_transfer_len = task_size;
+
+	init_ustorm_task_contexts(&task_params->context->ustorm_st_context,
+				  &task_params->context->ustorm_ag_context,
+				  task_size, exp_data_transfer_len, num_sges,
+				  dif_task_params ?
+				  dif_task_params->tx_dif_conn_err_en : false);
+
+	set_rw_exp_data_acked_and_cont_len(task_params->context, conn_params,
+					   task_type, task_size,
+					   exp_data_transfer_len,
+					GET_FIELD(pdu_header->hdr_second_dword,
+						  ISCSI_CMD_HDR_TOTAL_AHS_LEN));
+
+	if (dif_task_params)
+		init_rtdif_task_context(&task_params->context->rdif_context,
+					&task_params->context->tdif_context,
+					dif_task_params, task_type);
+
+	init_sqe(task_params, sgl_task_params, dif_task_params, pdu_header,
+		 cmd_params, task_type, false);
+
+	return 0;
+}
+
+int init_initiator_rw_iscsi_task(struct iscsi_task_params *task_params,
+				 struct iscsi_conn_params *conn_params,
+				 struct scsi_initiator_cmd_params *cmd_params,
+				 struct iscsi_cmd_hdr *cmd_header,
+				 struct scsi_sgl_task_params *tx_sgl_params,
+				 struct scsi_sgl_task_params *rx_sgl_params,
+				 struct scsi_dif_task_params *dif_task_params)
+{
+	if (GET_FIELD(cmd_header->flags_attr, ISCSI_CMD_HDR_WRITE))
+		return init_rw_iscsi_task(task_params,
+					  ISCSI_TASK_TYPE_INITIATOR_WRITE,
+					  conn_params,
+					  (struct iscsi_common_hdr *)cmd_header,
+					  tx_sgl_params, cmd_params,
+					  dif_task_params);
+	else if (GET_FIELD(cmd_header->flags_attr, ISCSI_CMD_HDR_READ))
+		return init_rw_iscsi_task(task_params,
+					  ISCSI_TASK_TYPE_INITIATOR_READ,
+					  conn_params,
+					  (struct iscsi_common_hdr *)cmd_header,
+					  rx_sgl_params, cmd_params,
+					  dif_task_params);
+	else
+		return -1;
+}
+
+int init_initiator_login_request_task(struct iscsi_task_params *task_params,
+				      struct iscsi_login_req_hdr  *login_header,
+				      struct scsi_sgl_task_params *tx_params,
+				      struct scsi_sgl_task_params *rx_params)
+{
+	struct iscsi_task_context *cxt;
+
+	cxt = task_params->context;
+
+	init_default_iscsi_task(task_params,
+				(struct data_hdr *)login_header,
+				ISCSI_TASK_TYPE_MIDPATH);
+
+	init_ustorm_task_contexts(&cxt->ustorm_st_context,
+				  &cxt->ustorm_ag_context,
+				  task_params->rx_io_size ?
+				  rx_params->total_buffer_size : 0,
+				  task_params->tx_io_size ?
+				  tx_params->total_buffer_size : 0, 0,
+				  0);
+
+	if (task_params->tx_io_size)
+		init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params,
+				      &cxt->ystorm_st_context.state.data_desc,
+				      tx_params);
+
+	if (task_params->rx_io_size)
+		init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params,
+				      &cxt->mstorm_st_context.data_desc,
+				      rx_params);
+
+	cxt->mstorm_st_context.rem_task_size =
+			cpu_to_le32(task_params->rx_io_size ?
+				    rx_params->total_buffer_size : 0);
+
+	init_sqe(task_params, tx_params, NULL,
+		 (struct iscsi_common_hdr *)login_header, NULL,
+		 ISCSI_TASK_TYPE_MIDPATH, false);
+
+	return 0;
+}
+
+int init_initiator_nop_out_task(struct iscsi_task_params *task_params,
+				struct iscsi_nop_out_hdr *nop_out_pdu_header,
+				struct scsi_sgl_task_params *tx_sgl_task_params,
+				struct scsi_sgl_task_params *rx_sgl_task_params)
+{
+	struct iscsi_task_context *cxt;
+
+	cxt = task_params->context;
+
+	init_default_iscsi_task(task_params,
+				(struct data_hdr *)nop_out_pdu_header,
+				ISCSI_TASK_TYPE_MIDPATH);
+
+	if (nop_out_pdu_header->itt == ISCSI_ITT_ALL_ONES)
+		set_local_completion_context(task_params->context);
+
+	if (task_params->tx_io_size)
+		init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params,
+				      &cxt->ystorm_st_context.state.data_desc,
+				      tx_sgl_task_params);
+
+	if (task_params->rx_io_size)
+		init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params,
+				      &cxt->mstorm_st_context.data_desc,
+				      rx_sgl_task_params);
+
+	init_ustorm_task_contexts(&cxt->ustorm_st_context,
+				  &cxt->ustorm_ag_context,
+				  task_params->rx_io_size ?
+				  rx_sgl_task_params->total_buffer_size : 0,
+				  task_params->tx_io_size ?
+				  tx_sgl_task_params->total_buffer_size : 0,
+				  0, 0);
+
+	cxt->mstorm_st_context.rem_task_size =
+				cpu_to_le32(task_params->rx_io_size ?
+					rx_sgl_task_params->total_buffer_size :
+					0);
+
+	init_sqe(task_params, tx_sgl_task_params, NULL,
+		 (struct iscsi_common_hdr *)nop_out_pdu_header, NULL,
+		 ISCSI_TASK_TYPE_MIDPATH, false);
+
+	return 0;
+}
+
+int init_initiator_logout_request_task(struct iscsi_task_params *task_params,
+				       struct iscsi_logout_req_hdr *logout_hdr,
+				       struct scsi_sgl_task_params *tx_params,
+				       struct scsi_sgl_task_params *rx_params)
+{
+	struct iscsi_task_context *cxt;
+
+	cxt = task_params->context;
+
+	init_default_iscsi_task(task_params,
+				(struct data_hdr *)logout_hdr,
+				ISCSI_TASK_TYPE_MIDPATH);
+
+	if (task_params->tx_io_size)
+		init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params,
+				      &cxt->ystorm_st_context.state.data_desc,
+				      tx_params);
+
+	if (task_params->rx_io_size)
+		init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params,
+				      &cxt->mstorm_st_context.data_desc,
+				      rx_params);
+
+	init_ustorm_task_contexts(&cxt->ustorm_st_context,
+				  &cxt->ustorm_ag_context,
+				  task_params->rx_io_size ?
+				  rx_params->total_buffer_size : 0,
+				  task_params->tx_io_size ?
+				  tx_params->total_buffer_size : 0,
+				  0, 0);
+
+	cxt->mstorm_st_context.rem_task_size =
+					cpu_to_le32(task_params->rx_io_size ?
+					rx_params->total_buffer_size : 0);
+
+	init_sqe(task_params, tx_params, NULL,
+		 (struct iscsi_common_hdr *)logout_hdr, NULL,
+		 ISCSI_TASK_TYPE_MIDPATH, false);
+
+	return 0;
+}
+
+int init_initiator_tmf_request_task(struct iscsi_task_params *task_params,
+				    struct iscsi_tmf_request_hdr *tmf_header)
+{
+	init_default_iscsi_task(task_params, (struct data_hdr *)tmf_header,
+				ISCSI_TASK_TYPE_MIDPATH);
+
+	init_sqe(task_params, NULL, NULL,
+		 (struct iscsi_common_hdr *)tmf_header, NULL,
+		 ISCSI_TASK_TYPE_MIDPATH, false);
+
+	return 0;
+}
+
+int init_initiator_text_request_task(struct iscsi_task_params *task_params,
+				     struct iscsi_text_request_hdr *text_header,
+				     struct scsi_sgl_task_params *tx_params,
+				     struct scsi_sgl_task_params *rx_params)
+{
+	struct iscsi_task_context *cxt;
+
+	cxt = task_params->context;
+
+	init_default_iscsi_task(task_params,
+				(struct data_hdr *)text_header,
+				ISCSI_TASK_TYPE_MIDPATH);
+
+	if (task_params->tx_io_size)
+		init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params,
+				      &cxt->ystorm_st_context.state.data_desc,
+				      tx_params);
+
+	if (task_params->rx_io_size)
+		init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params,
+				      &cxt->mstorm_st_context.data_desc,
+				      rx_params);
+
+	cxt->mstorm_st_context.rem_task_size =
+				cpu_to_le32(task_params->rx_io_size ?
+					rx_params->total_buffer_size : 0);
+
+	init_ustorm_task_contexts(&cxt->ustorm_st_context,
+				  &cxt->ustorm_ag_context,
+				  task_params->rx_io_size ?
+				  rx_params->total_buffer_size : 0,
+				  task_params->tx_io_size ?
+				  tx_params->total_buffer_size : 0, 0, 0);
+
+	init_sqe(task_params, tx_params, NULL,
+		 (struct iscsi_common_hdr *)text_header, NULL,
+		 ISCSI_TASK_TYPE_MIDPATH, false);
+
+	return 0;
+}
+
+int init_cleanup_task(struct iscsi_task_params *task_params)
+{
+	init_sqe(task_params, NULL, NULL, NULL, NULL, ISCSI_TASK_TYPE_MIDPATH,
+		 true);
+	return 0;
+}
diff --git a/drivers/scsi/qedi/qedi_fw_iscsi.h b/drivers/scsi/qedi/qedi_fw_iscsi.h
new file mode 100644
index 000000000000..b6f24f91849d
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_fw_iscsi.h
@@ -0,0 +1,117 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available 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.
+ */
+
+#ifndef _QEDI_FW_ISCSI_H_
+#define _QEDI_FW_ISCSI_H_
+
+#include "qedi_fw_scsi.h"
+
+struct iscsi_task_params {
+	struct iscsi_task_context *context;
+	struct iscsi_wqe	  *sqe;
+	u32			  tx_io_size;
+	u32			  rx_io_size;
+	u16			  conn_icid;
+	u16			  itid;
+	u8			  cq_rss_number;
+};
+
+struct iscsi_conn_params {
+	u32	first_burst_length;
+	u32	max_send_pdu_length;
+	u32	max_burst_length;
+	bool	initial_r2t;
+	bool	immediate_data;
+};
+
+/* @brief init_initiator_read_iscsi_task - initializes iSCSI Initiator Read
+ * task context.
+ *
+ * @param task_params	  - Pointer to task parameters struct
+ * @param conn_params	  - Connection Parameters
+ * @param cmd_params	  - command specific parameters
+ * @param cmd_pdu_header  - PDU Header Parameters
+ * @param sgl_task_params - Pointer to SGL task params
+ * @param dif_task_params - Pointer to DIF parameters struct
+ */
+int init_initiator_rw_iscsi_task(struct iscsi_task_params *task_params,
+				 struct iscsi_conn_params *conn_params,
+				 struct scsi_initiator_cmd_params *cmd_params,
+				 struct iscsi_cmd_hdr *cmd_pdu_header,
+				 struct scsi_sgl_task_params *tx_sgl_params,
+				 struct scsi_sgl_task_params *rx_sgl_params,
+				 struct scsi_dif_task_params *dif_task_params);
+
+/* @brief init_initiator_login_request_task - initializes iSCSI Initiator Login
+ * Request task context.
+ *
+ * @param task_params		  - Pointer to task parameters struct
+ * @param login_req_pdu_header    - PDU Header Parameters
+ * @param tx_sgl_task_params	  - Pointer to SGL task params
+ * @param rx_sgl_task_params	  - Pointer to SGL task params
+ */
+int init_initiator_login_request_task(struct iscsi_task_params *task_params,
+				      struct iscsi_login_req_hdr *login_header,
+				      struct scsi_sgl_task_params *tx_params,
+				      struct scsi_sgl_task_params *rx_params);
+
+/* @brief init_initiator_nop_out_task - initializes iSCSI Initiator NOP Out
+ * task context.
+ *
+ * @param task_params		- Pointer to task parameters struct
+ * @param nop_out_pdu_header    - PDU Header Parameters
+ * @param tx_sgl_task_params	- Pointer to SGL task params
+ * @param rx_sgl_task_params	- Pointer to SGL task params
+ */
+int init_initiator_nop_out_task(struct iscsi_task_params *task_params,
+				struct iscsi_nop_out_hdr *nop_out_pdu_header,
+				struct scsi_sgl_task_params *tx_sgl_params,
+				struct scsi_sgl_task_params *rx_sgl_params);
+
+/* @brief init_initiator_logout_request_task - initializes iSCSI Initiator
+ * Logout Request task context.
+ *
+ * @param task_params		- Pointer to task parameters struct
+ * @param logout_pdu_header  - PDU Header Parameters
+ * @param tx_sgl_task_params	- Pointer to SGL task params
+ * @param rx_sgl_task_params	- Pointer to SGL task params
+ */
+int init_initiator_logout_request_task(struct iscsi_task_params *task_params,
+				       struct iscsi_logout_req_hdr *logout_hdr,
+				       struct scsi_sgl_task_params *tx_params,
+				       struct scsi_sgl_task_params *rx_params);
+
+/* @brief init_initiator_tmf_request_task - initializes iSCSI Initiator TMF
+ * task context.
+ *
+ * @param task_params	- Pointer to task parameters struct
+ * @param tmf_pdu_header - PDU Header Parameters
+ */
+int init_initiator_tmf_request_task(struct iscsi_task_params *task_params,
+				    struct iscsi_tmf_request_hdr *tmf_header);
+
+/* @brief init_initiator_text_request_task - initializes iSCSI Initiator Text
+ * Request task context.
+ *
+ * @param task_params		     - Pointer to task parameters struct
+ * @param text_request_pdu_header    - PDU Header Parameters
+ * @param tx_sgl_task_params	     - Pointer to Tx SGL task params
+ * @param rx_sgl_task_params	     - Pointer to Rx SGL task params
+ */
+int init_initiator_text_request_task(struct iscsi_task_params *task_params,
+				     struct iscsi_text_request_hdr *text_header,
+				     struct scsi_sgl_task_params *tx_params,
+				     struct scsi_sgl_task_params *rx_params);
+
+/* @brief init_cleanup_task - initializes Clean task (SQE)
+ *
+ * @param task_params - Pointer to task parameters struct
+ */
+int init_cleanup_task(struct iscsi_task_params *task_params);
+#endif
diff --git a/drivers/scsi/qedi/qedi_fw_scsi.h b/drivers/scsi/qedi/qedi_fw_scsi.h
new file mode 100644
index 000000000000..cdaf918f1019
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_fw_scsi.h
@@ -0,0 +1,55 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available 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.
+ */
+
+#ifndef _QEDI_FW_SCSI_H_
+#define _QEDI_FW_SCSI_H_
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include "qedi_hsi.h"
+#include <linux/qed/qed_if.h>
+
+struct scsi_sgl_task_params {
+	struct scsi_sge	*sgl;
+	struct regpair	sgl_phys_addr;
+	u32		total_buffer_size;
+	u16		num_sges;
+	bool		small_mid_sge;
+};
+
+struct scsi_dif_task_params {
+	u32	initial_ref_tag;
+	bool	initial_ref_tag_is_valid;
+	u16	application_tag;
+	u16	application_tag_mask;
+	u16	dif_block_size_log;
+	bool	dif_on_network;
+	bool	dif_on_host;
+	u8	host_guard_type;
+	u8	protection_type;
+	u8	ref_tag_mask;
+	bool	crc_seed;
+	bool	tx_dif_conn_err_en;
+	bool	ignore_app_tag;
+	bool	keep_ref_tag_const;
+	bool	validate_guard;
+	bool	validate_app_tag;
+	bool	validate_ref_tag;
+	bool	forward_guard;
+	bool	forward_app_tag;
+	bool	forward_ref_tag;
+	bool	forward_app_tag_with_mask;
+	bool	forward_ref_tag_with_mask;
+};
+
+struct scsi_initiator_cmd_params {
+	struct scsi_sge	extended_cdb_sge;
+	struct regpair	sense_data_buffer_phys_addr;
+};
+#endif
diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c
index 4cc474364c50..d1de172bebac 100644
--- a/drivers/scsi/qedi/qedi_iscsi.c
+++ b/drivers/scsi/qedi/qedi_iscsi.c
@@ -175,7 +175,7 @@ static void qedi_destroy_cmd_pool(struct qedi_ctx *qedi,
 		if (cmd->io_tbl.sge_tbl)
 			dma_free_coherent(&qedi->pdev->dev,
 					  QEDI_ISCSI_MAX_BDS_PER_CMD *
-					  sizeof(struct iscsi_sge),
+					  sizeof(struct scsi_sge),
 					  cmd->io_tbl.sge_tbl,
 					  cmd->io_tbl.sge_tbl_dma);
 
@@ -191,7 +191,7 @@ static int qedi_alloc_sget(struct qedi_ctx *qedi, struct iscsi_session *session,
 			   struct qedi_cmd *cmd)
 {
 	struct qedi_io_bdt *io = &cmd->io_tbl;
-	struct iscsi_sge *sge;
+	struct scsi_sge *sge;
 
 	io->sge_tbl = dma_alloc_coherent(&qedi->pdev->dev,
 					 QEDI_ISCSI_MAX_BDS_PER_CMD *
@@ -708,22 +708,20 @@ static void qedi_conn_get_stats(struct iscsi_cls_conn *cls_conn,
 
 static void qedi_iscsi_prep_generic_pdu_bd(struct qedi_conn *qedi_conn)
 {
-	struct iscsi_sge *bd_tbl;
+	struct scsi_sge *bd_tbl;
 
-	bd_tbl = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	bd_tbl = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
 
 	bd_tbl->sge_addr.hi =
 		(u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
 	bd_tbl->sge_addr.lo = (u32)qedi_conn->gen_pdu.req_dma_addr;
 	bd_tbl->sge_len = qedi_conn->gen_pdu.req_wr_ptr -
 				qedi_conn->gen_pdu.req_buf;
-	bd_tbl->reserved0 = 0;
-	bd_tbl = (struct iscsi_sge  *)qedi_conn->gen_pdu.resp_bd_tbl;
+	bd_tbl = (struct scsi_sge  *)qedi_conn->gen_pdu.resp_bd_tbl;
 	bd_tbl->sge_addr.hi =
 			(u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32);
 	bd_tbl->sge_addr.lo = (u32)qedi_conn->gen_pdu.resp_dma_addr;
 	bd_tbl->sge_len = ISCSI_DEF_MAX_RECV_SEG_LEN;
-	bd_tbl->reserved0 = 0;
 }
 
 static int qedi_iscsi_send_generic_request(struct iscsi_task *task)
diff --git a/drivers/scsi/qedi/qedi_iscsi.h b/drivers/scsi/qedi/qedi_iscsi.h
index d3c06bbddb4e..3247287cb0e7 100644
--- a/drivers/scsi/qedi/qedi_iscsi.h
+++ b/drivers/scsi/qedi/qedi_iscsi.h
@@ -102,7 +102,7 @@ struct qedi_endpoint {
 #define QEDI_SQ_WQES_MIN	16
 
 struct qedi_io_bdt {
-	struct iscsi_sge *sge_tbl;
+	struct scsi_sge *sge_tbl;
 	dma_addr_t sge_tbl_dma;
 	u16 sge_valid;
 };
diff --git a/drivers/scsi/qedi/qedi_version.h b/drivers/scsi/qedi/qedi_version.h
index 9543a1b139d4..d61e3ac22e67 100644
--- a/drivers/scsi/qedi/qedi_version.h
+++ b/drivers/scsi/qedi/qedi_version.h
@@ -7,8 +7,8 @@
  * this source tree.
  */
 
-#define QEDI_MODULE_VERSION	"8.10.3.0"
+#define QEDI_MODULE_VERSION	"8.10.4.0"
 #define QEDI_DRIVER_MAJOR_VER		8
 #define QEDI_DRIVER_MINOR_VER		10
-#define QEDI_DRIVER_REV_VER		3
+#define QEDI_DRIVER_REV_VER		4
 #define QEDI_DRIVER_ENG_VER		0
diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index 78b1bb7bcf20..9fca977ef18d 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -33,17 +33,10 @@ config QCOM_SMEM
 	  The driver provides an interface to items in a heap shared among all
 	  processors in a Qualcomm platform.
 
-config QCOM_SMD
-	tristate "Qualcomm Shared Memory Driver (SMD)"
-	depends on QCOM_SMEM
-	help
-	  Say y here to enable support for the Qualcomm Shared Memory Driver
-	  providing communication channels to remote processors in Qualcomm
-	  platforms.
-
 config QCOM_SMD_RPM
 	tristate "Qualcomm Resource Power Manager (RPM) over SMD"
-	depends on QCOM_SMD && OF
+	depends on ARCH_QCOM
+	depends on RPMSG && OF
 	help
 	  If you say yes to this option, support will be included for the
 	  Resource Power Manager system found in the Qualcomm 8974 based
@@ -76,7 +69,8 @@ config QCOM_SMSM
 
 config QCOM_WCNSS_CTRL
 	tristate "Qualcomm WCNSS control driver"
-	depends on QCOM_SMD
+	depends on ARCH_QCOM
+	depends on RPMSG
 	help
 	  Client driver for the WCNSS_CTRL SMD channel, used to download nv
 	  firmware to a newly booted WCNSS chip.
diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index 1f30260b06b8..414f0de274fa 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -1,7 +1,6 @@
 obj-$(CONFIG_QCOM_GSBI)	+=	qcom_gsbi.o
 obj-$(CONFIG_QCOM_MDT_LOADER)	+= mdt_loader.o
 obj-$(CONFIG_QCOM_PM)	+=	spm.o
-obj-$(CONFIG_QCOM_SMD) +=	smd.o
 obj-$(CONFIG_QCOM_SMD_RPM)	+= smd-rpm.o
 obj-$(CONFIG_QCOM_SMEM) +=	smem.o
 obj-$(CONFIG_QCOM_SMEM_STATE) += smem_state.o
diff --git a/drivers/soc/qcom/smd-rpm.c b/drivers/soc/qcom/smd-rpm.c
index 6609d7e0edb0..c2346752b3ea 100644
--- a/drivers/soc/qcom/smd-rpm.c
+++ b/drivers/soc/qcom/smd-rpm.c
@@ -19,7 +19,7 @@
 #include <linux/interrupt.h>
 #include <linux/slab.h>
 
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
 #include <linux/soc/qcom/smd-rpm.h>
 
 #define RPM_REQUEST_TIMEOUT     (5 * HZ)
@@ -32,7 +32,7 @@
  * @ack_status:		result of the rpm request
  */
 struct qcom_smd_rpm {
-	struct qcom_smd_channel *rpm_channel;
+	struct rpmsg_endpoint *rpm_channel;
 	struct device *dev;
 
 	struct completion ack;
@@ -133,7 +133,7 @@ int qcom_rpm_smd_write(struct qcom_smd_rpm *rpm,
 	pkt->req.data_len = cpu_to_le32(count);
 	memcpy(pkt->payload, buf, count);
 
-	ret = qcom_smd_send(rpm->rpm_channel, pkt, size);
+	ret = rpmsg_send(rpm->rpm_channel, pkt, size);
 	if (ret)
 		goto out;
 
@@ -150,14 +150,16 @@ out:
 }
 EXPORT_SYMBOL(qcom_rpm_smd_write);
 
-static int qcom_smd_rpm_callback(struct qcom_smd_channel *channel,
-				 const void *data,
-				 size_t count)
+static int qcom_smd_rpm_callback(struct rpmsg_device *rpdev,
+				 void *data,
+				 int count,
+				 void *priv,
+				 u32 addr)
 {
 	const struct qcom_rpm_header *hdr = data;
 	size_t hdr_length = le32_to_cpu(hdr->length);
 	const struct qcom_rpm_message *msg;
-	struct qcom_smd_rpm *rpm = qcom_smd_get_drvdata(channel);
+	struct qcom_smd_rpm *rpm = dev_get_drvdata(&rpdev->dev);
 	const u8 *buf = data + sizeof(struct qcom_rpm_header);
 	const u8 *end = buf + hdr_length;
 	char msgbuf[32];
@@ -196,59 +198,57 @@ static int qcom_smd_rpm_callback(struct qcom_smd_channel *channel,
 	return 0;
 }
 
-static int qcom_smd_rpm_probe(struct qcom_smd_device *sdev)
+static int qcom_smd_rpm_probe(struct rpmsg_device *rpdev)
 {
 	struct qcom_smd_rpm *rpm;
 
-	rpm = devm_kzalloc(&sdev->dev, sizeof(*rpm), GFP_KERNEL);
+	rpm = devm_kzalloc(&rpdev->dev, sizeof(*rpm), GFP_KERNEL);
 	if (!rpm)
 		return -ENOMEM;
 
 	mutex_init(&rpm->lock);
 	init_completion(&rpm->ack);
 
-	rpm->dev = &sdev->dev;
-	rpm->rpm_channel = sdev->channel;
-	qcom_smd_set_drvdata(sdev->channel, rpm);
+	rpm->dev = &rpdev->dev;
+	rpm->rpm_channel = rpdev->ept;
+	dev_set_drvdata(&rpdev->dev, rpm);
 
-	dev_set_drvdata(&sdev->dev, rpm);
-
-	return of_platform_populate(sdev->dev.of_node, NULL, NULL, &sdev->dev);
+	return of_platform_populate(rpdev->dev.of_node, NULL, NULL, &rpdev->dev);
 }
 
-static void qcom_smd_rpm_remove(struct qcom_smd_device *sdev)
+static void qcom_smd_rpm_remove(struct rpmsg_device *rpdev)
 {
-	of_platform_depopulate(&sdev->dev);
+	of_platform_depopulate(&rpdev->dev);
 }
 
 static const struct of_device_id qcom_smd_rpm_of_match[] = {
 	{ .compatible = "qcom,rpm-apq8084" },
 	{ .compatible = "qcom,rpm-msm8916" },
 	{ .compatible = "qcom,rpm-msm8974" },
+	{ .compatible = "qcom,rpm-msm8996" },
 	{}
 };
 MODULE_DEVICE_TABLE(of, qcom_smd_rpm_of_match);
 
-static struct qcom_smd_driver qcom_smd_rpm_driver = {
+static struct rpmsg_driver qcom_smd_rpm_driver = {
 	.probe = qcom_smd_rpm_probe,
 	.remove = qcom_smd_rpm_remove,
 	.callback = qcom_smd_rpm_callback,
-	.driver  = {
+	.drv  = {
 		.name  = "qcom_smd_rpm",
-		.owner = THIS_MODULE,
 		.of_match_table = qcom_smd_rpm_of_match,
 	},
 };
 
 static int __init qcom_smd_rpm_init(void)
 {
-	return qcom_smd_driver_register(&qcom_smd_rpm_driver);
+	return register_rpmsg_driver(&qcom_smd_rpm_driver);
 }
 arch_initcall(qcom_smd_rpm_init);
 
 static void __exit qcom_smd_rpm_exit(void)
 {
-	qcom_smd_driver_unregister(&qcom_smd_rpm_driver);
+	unregister_rpmsg_driver(&qcom_smd_rpm_driver);
 }
 module_exit(qcom_smd_rpm_exit);
 
diff --git a/drivers/soc/qcom/smd.c b/drivers/soc/qcom/smd.c
deleted file mode 100644
index 322034ab9d37..000000000000
--- a/drivers/soc/qcom/smd.c
+++ /dev/null
@@ -1,1560 +0,0 @@
-/*
- * Copyright (c) 2015, Sony Mobile Communications AB.
- * Copyright (c) 2012-2013, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/mfd/syscon.h>
-#include <linux/module.h>
-#include <linux/of_irq.h>
-#include <linux/of_platform.h>
-#include <linux/platform_device.h>
-#include <linux/regmap.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/soc/qcom/smd.h>
-#include <linux/soc/qcom/smem.h>
-#include <linux/wait.h>
-
-/*
- * The Qualcomm Shared Memory communication solution provides point-to-point
- * channels for clients to send and receive streaming or packet based data.
- *
- * Each channel consists of a control item (channel info) and a ring buffer
- * pair. The channel info carry information related to channel state, flow
- * control and the offsets within the ring buffer.
- *
- * All allocated channels are listed in an allocation table, identifying the
- * pair of items by name, type and remote processor.
- *
- * Upon creating a new channel the remote processor allocates channel info and
- * ring buffer items from the smem heap and populate the allocation table. An
- * interrupt is sent to the other end of the channel and a scan for new
- * channels should be done. A channel never goes away, it will only change
- * state.
- *
- * The remote processor signals it intent for bring up the communication
- * channel by setting the state of its end of the channel to "opening" and
- * sends out an interrupt. We detect this change and register a smd device to
- * consume the channel. Upon finding a consumer we finish the handshake and the
- * channel is up.
- *
- * Upon closing a channel, the remote processor will update the state of its
- * end of the channel and signal us, we will then unregister any attached
- * device and close our end of the channel.
- *
- * Devices attached to a channel can use the qcom_smd_send function to push
- * data to the channel, this is done by copying the data into the tx ring
- * buffer, updating the pointers in the channel info and signaling the remote
- * processor.
- *
- * The remote processor does the equivalent when it transfer data and upon
- * receiving the interrupt we check the channel info for new data and delivers
- * this to the attached device. If the device is not ready to receive the data
- * we leave it in the ring buffer for now.
- */
-
-struct smd_channel_info;
-struct smd_channel_info_pair;
-struct smd_channel_info_word;
-struct smd_channel_info_word_pair;
-
-#define SMD_ALLOC_TBL_COUNT	2
-#define SMD_ALLOC_TBL_SIZE	64
-
-/*
- * This lists the various smem heap items relevant for the allocation table and
- * smd channel entries.
- */
-static const struct {
-	unsigned alloc_tbl_id;
-	unsigned info_base_id;
-	unsigned fifo_base_id;
-} smem_items[SMD_ALLOC_TBL_COUNT] = {
-	{
-		.alloc_tbl_id = 13,
-		.info_base_id = 14,
-		.fifo_base_id = 338
-	},
-	{
-		.alloc_tbl_id = 266,
-		.info_base_id = 138,
-		.fifo_base_id = 202,
-	},
-};
-
-/**
- * struct qcom_smd_edge - representing a remote processor
- * @dev:		device for this edge
- * @of_node:		of_node handle for information related to this edge
- * @edge_id:		identifier of this edge
- * @remote_pid:		identifier of remote processor
- * @irq:		interrupt for signals on this edge
- * @ipc_regmap:		regmap handle holding the outgoing ipc register
- * @ipc_offset:		offset within @ipc_regmap of the register for ipc
- * @ipc_bit:		bit in the register at @ipc_offset of @ipc_regmap
- * @channels:		list of all channels detected on this edge
- * @channels_lock:	guard for modifications of @channels
- * @allocated:		array of bitmaps representing already allocated channels
- * @smem_available:	last available amount of smem triggering a channel scan
- * @scan_work:		work item for discovering new channels
- * @state_work:		work item for edge state changes
- */
-struct qcom_smd_edge {
-	struct device dev;
-
-	struct device_node *of_node;
-	unsigned edge_id;
-	unsigned remote_pid;
-
-	int irq;
-
-	struct regmap *ipc_regmap;
-	int ipc_offset;
-	int ipc_bit;
-
-	struct list_head channels;
-	spinlock_t channels_lock;
-
-	DECLARE_BITMAP(allocated[SMD_ALLOC_TBL_COUNT], SMD_ALLOC_TBL_SIZE);
-
-	unsigned smem_available;
-
-	wait_queue_head_t new_channel_event;
-
-	struct work_struct scan_work;
-	struct work_struct state_work;
-};
-
-#define to_smd_edge(d) container_of(d, struct qcom_smd_edge, dev)
-
-/*
- * SMD channel states.
- */
-enum smd_channel_state {
-	SMD_CHANNEL_CLOSED,
-	SMD_CHANNEL_OPENING,
-	SMD_CHANNEL_OPENED,
-	SMD_CHANNEL_FLUSHING,
-	SMD_CHANNEL_CLOSING,
-	SMD_CHANNEL_RESET,
-	SMD_CHANNEL_RESET_OPENING
-};
-
-/**
- * struct qcom_smd_channel - smd channel struct
- * @edge:		qcom_smd_edge this channel is living on
- * @qsdev:		reference to a associated smd client device
- * @name:		name of the channel
- * @state:		local state of the channel
- * @remote_state:	remote state of the channel
- * @info:		byte aligned outgoing/incoming channel info
- * @info_word:		word aligned outgoing/incoming channel info
- * @tx_lock:		lock to make writes to the channel mutually exclusive
- * @fblockread_event:	wakeup event tied to tx fBLOCKREADINTR
- * @tx_fifo:		pointer to the outgoing ring buffer
- * @rx_fifo:		pointer to the incoming ring buffer
- * @fifo_size:		size of each ring buffer
- * @bounce_buffer:	bounce buffer for reading wrapped packets
- * @cb:			callback function registered for this channel
- * @recv_lock:		guard for rx info modifications and cb pointer
- * @pkt_size:		size of the currently handled packet
- * @list:		lite entry for @channels in qcom_smd_edge
- */
-struct qcom_smd_channel {
-	struct qcom_smd_edge *edge;
-
-	struct qcom_smd_device *qsdev;
-
-	char *name;
-	enum smd_channel_state state;
-	enum smd_channel_state remote_state;
-
-	struct smd_channel_info_pair *info;
-	struct smd_channel_info_word_pair *info_word;
-
-	struct mutex tx_lock;
-	wait_queue_head_t fblockread_event;
-
-	void *tx_fifo;
-	void *rx_fifo;
-	int fifo_size;
-
-	void *bounce_buffer;
-	qcom_smd_cb_t cb;
-
-	spinlock_t recv_lock;
-
-	int pkt_size;
-
-	void *drvdata;
-
-	struct list_head list;
-};
-
-/*
- * Format of the smd_info smem items, for byte aligned channels.
- */
-struct smd_channel_info {
-	__le32 state;
-	u8  fDSR;
-	u8  fCTS;
-	u8  fCD;
-	u8  fRI;
-	u8  fHEAD;
-	u8  fTAIL;
-	u8  fSTATE;
-	u8  fBLOCKREADINTR;
-	__le32 tail;
-	__le32 head;
-};
-
-struct smd_channel_info_pair {
-	struct smd_channel_info tx;
-	struct smd_channel_info rx;
-};
-
-/*
- * Format of the smd_info smem items, for word aligned channels.
- */
-struct smd_channel_info_word {
-	__le32 state;
-	__le32 fDSR;
-	__le32 fCTS;
-	__le32 fCD;
-	__le32 fRI;
-	__le32 fHEAD;
-	__le32 fTAIL;
-	__le32 fSTATE;
-	__le32 fBLOCKREADINTR;
-	__le32 tail;
-	__le32 head;
-};
-
-struct smd_channel_info_word_pair {
-	struct smd_channel_info_word tx;
-	struct smd_channel_info_word rx;
-};
-
-#define GET_RX_CHANNEL_FLAG(channel, param)				     \
-	({								     \
-		BUILD_BUG_ON(sizeof(channel->info->rx.param) != sizeof(u8)); \
-		channel->info_word ?					     \
-			le32_to_cpu(channel->info_word->rx.param) :	     \
-			channel->info->rx.param;			     \
-	})
-
-#define GET_RX_CHANNEL_INFO(channel, param)				      \
-	({								      \
-		BUILD_BUG_ON(sizeof(channel->info->rx.param) != sizeof(u32)); \
-		le32_to_cpu(channel->info_word ?			      \
-			channel->info_word->rx.param :			      \
-			channel->info->rx.param);			      \
-	})
-
-#define SET_RX_CHANNEL_FLAG(channel, param, value)			     \
-	({								     \
-		BUILD_BUG_ON(sizeof(channel->info->rx.param) != sizeof(u8)); \
-		if (channel->info_word)					     \
-			channel->info_word->rx.param = cpu_to_le32(value);   \
-		else							     \
-			channel->info->rx.param = value;		     \
-	})
-
-#define SET_RX_CHANNEL_INFO(channel, param, value)			      \
-	({								      \
-		BUILD_BUG_ON(sizeof(channel->info->rx.param) != sizeof(u32)); \
-		if (channel->info_word)					      \
-			channel->info_word->rx.param = cpu_to_le32(value);    \
-		else							      \
-			channel->info->rx.param = cpu_to_le32(value);	      \
-	})
-
-#define GET_TX_CHANNEL_FLAG(channel, param)				     \
-	({								     \
-		BUILD_BUG_ON(sizeof(channel->info->tx.param) != sizeof(u8)); \
-		channel->info_word ?					     \
-			le32_to_cpu(channel->info_word->tx.param) :          \
-			channel->info->tx.param;			     \
-	})
-
-#define GET_TX_CHANNEL_INFO(channel, param)				      \
-	({								      \
-		BUILD_BUG_ON(sizeof(channel->info->tx.param) != sizeof(u32)); \
-		le32_to_cpu(channel->info_word ?			      \
-			channel->info_word->tx.param :			      \
-			channel->info->tx.param);			      \
-	})
-
-#define SET_TX_CHANNEL_FLAG(channel, param, value)			     \
-	({								     \
-		BUILD_BUG_ON(sizeof(channel->info->tx.param) != sizeof(u8)); \
-		if (channel->info_word)					     \
-			channel->info_word->tx.param = cpu_to_le32(value);   \
-		else							     \
-			channel->info->tx.param = value;		     \
-	})
-
-#define SET_TX_CHANNEL_INFO(channel, param, value)			      \
-	({								      \
-		BUILD_BUG_ON(sizeof(channel->info->tx.param) != sizeof(u32)); \
-		if (channel->info_word)					      \
-			channel->info_word->tx.param = cpu_to_le32(value);   \
-		else							      \
-			channel->info->tx.param = cpu_to_le32(value);	      \
-	})
-
-/**
- * struct qcom_smd_alloc_entry - channel allocation entry
- * @name:	channel name
- * @cid:	channel index
- * @flags:	channel flags and edge id
- * @ref_count:	reference count of the channel
- */
-struct qcom_smd_alloc_entry {
-	u8 name[20];
-	__le32 cid;
-	__le32 flags;
-	__le32 ref_count;
-} __packed;
-
-#define SMD_CHANNEL_FLAGS_EDGE_MASK	0xff
-#define SMD_CHANNEL_FLAGS_STREAM	BIT(8)
-#define SMD_CHANNEL_FLAGS_PACKET	BIT(9)
-
-/*
- * Each smd packet contains a 20 byte header, with the first 4 being the length
- * of the packet.
- */
-#define SMD_PACKET_HEADER_LEN	20
-
-/*
- * Signal the remote processor associated with 'channel'.
- */
-static void qcom_smd_signal_channel(struct qcom_smd_channel *channel)
-{
-	struct qcom_smd_edge *edge = channel->edge;
-
-	regmap_write(edge->ipc_regmap, edge->ipc_offset, BIT(edge->ipc_bit));
-}
-
-/*
- * Initialize the tx channel info
- */
-static void qcom_smd_channel_reset(struct qcom_smd_channel *channel)
-{
-	SET_TX_CHANNEL_INFO(channel, state, SMD_CHANNEL_CLOSED);
-	SET_TX_CHANNEL_FLAG(channel, fDSR, 0);
-	SET_TX_CHANNEL_FLAG(channel, fCTS, 0);
-	SET_TX_CHANNEL_FLAG(channel, fCD, 0);
-	SET_TX_CHANNEL_FLAG(channel, fRI, 0);
-	SET_TX_CHANNEL_FLAG(channel, fHEAD, 0);
-	SET_TX_CHANNEL_FLAG(channel, fTAIL, 0);
-	SET_TX_CHANNEL_FLAG(channel, fSTATE, 1);
-	SET_TX_CHANNEL_FLAG(channel, fBLOCKREADINTR, 1);
-	SET_TX_CHANNEL_INFO(channel, head, 0);
-	SET_RX_CHANNEL_INFO(channel, tail, 0);
-
-	qcom_smd_signal_channel(channel);
-
-	channel->state = SMD_CHANNEL_CLOSED;
-	channel->pkt_size = 0;
-}
-
-/*
- * Set the callback for a channel, with appropriate locking
- */
-static void qcom_smd_channel_set_callback(struct qcom_smd_channel *channel,
-					  qcom_smd_cb_t cb)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&channel->recv_lock, flags);
-	channel->cb = cb;
-	spin_unlock_irqrestore(&channel->recv_lock, flags);
-};
-
-/*
- * Calculate the amount of data available in the rx fifo
- */
-static size_t qcom_smd_channel_get_rx_avail(struct qcom_smd_channel *channel)
-{
-	unsigned head;
-	unsigned tail;
-
-	head = GET_RX_CHANNEL_INFO(channel, head);
-	tail = GET_RX_CHANNEL_INFO(channel, tail);
-
-	return (head - tail) & (channel->fifo_size - 1);
-}
-
-/*
- * Set tx channel state and inform the remote processor
- */
-static void qcom_smd_channel_set_state(struct qcom_smd_channel *channel,
-				       int state)
-{
-	struct qcom_smd_edge *edge = channel->edge;
-	bool is_open = state == SMD_CHANNEL_OPENED;
-
-	if (channel->state == state)
-		return;
-
-	dev_dbg(&edge->dev, "set_state(%s, %d)\n", channel->name, state);
-
-	SET_TX_CHANNEL_FLAG(channel, fDSR, is_open);
-	SET_TX_CHANNEL_FLAG(channel, fCTS, is_open);
-	SET_TX_CHANNEL_FLAG(channel, fCD, is_open);
-
-	SET_TX_CHANNEL_INFO(channel, state, state);
-	SET_TX_CHANNEL_FLAG(channel, fSTATE, 1);
-
-	channel->state = state;
-	qcom_smd_signal_channel(channel);
-}
-
-/*
- * Copy count bytes of data using 32bit accesses, if that's required.
- */
-static void smd_copy_to_fifo(void __iomem *dst,
-			     const void *src,
-			     size_t count,
-			     bool word_aligned)
-{
-	if (word_aligned) {
-		__iowrite32_copy(dst, src, count / sizeof(u32));
-	} else {
-		memcpy_toio(dst, src, count);
-	}
-}
-
-/*
- * Copy count bytes of data using 32bit accesses, if that is required.
- */
-static void smd_copy_from_fifo(void *dst,
-			       const void __iomem *src,
-			       size_t count,
-			       bool word_aligned)
-{
-	if (word_aligned) {
-		__ioread32_copy(dst, src, count / sizeof(u32));
-	} else {
-		memcpy_fromio(dst, src, count);
-	}
-}
-
-/*
- * Read count bytes of data from the rx fifo into buf, but don't advance the
- * tail.
- */
-static size_t qcom_smd_channel_peek(struct qcom_smd_channel *channel,
-				    void *buf, size_t count)
-{
-	bool word_aligned;
-	unsigned tail;
-	size_t len;
-
-	word_aligned = channel->info_word;
-	tail = GET_RX_CHANNEL_INFO(channel, tail);
-
-	len = min_t(size_t, count, channel->fifo_size - tail);
-	if (len) {
-		smd_copy_from_fifo(buf,
-				   channel->rx_fifo + tail,
-				   len,
-				   word_aligned);
-	}
-
-	if (len != count) {
-		smd_copy_from_fifo(buf + len,
-				   channel->rx_fifo,
-				   count - len,
-				   word_aligned);
-	}
-
-	return count;
-}
-
-/*
- * Advance the rx tail by count bytes.
- */
-static void qcom_smd_channel_advance(struct qcom_smd_channel *channel,
-				     size_t count)
-{
-	unsigned tail;
-
-	tail = GET_RX_CHANNEL_INFO(channel, tail);
-	tail += count;
-	tail &= (channel->fifo_size - 1);
-	SET_RX_CHANNEL_INFO(channel, tail, tail);
-}
-
-/*
- * Read out a single packet from the rx fifo and deliver it to the device
- */
-static int qcom_smd_channel_recv_single(struct qcom_smd_channel *channel)
-{
-	unsigned tail;
-	size_t len;
-	void *ptr;
-	int ret;
-
-	if (!channel->cb)
-		return 0;
-
-	tail = GET_RX_CHANNEL_INFO(channel, tail);
-
-	/* Use bounce buffer if the data wraps */
-	if (tail + channel->pkt_size >= channel->fifo_size) {
-		ptr = channel->bounce_buffer;
-		len = qcom_smd_channel_peek(channel, ptr, channel->pkt_size);
-	} else {
-		ptr = channel->rx_fifo + tail;
-		len = channel->pkt_size;
-	}
-
-	ret = channel->cb(channel, ptr, len);
-	if (ret < 0)
-		return ret;
-
-	/* Only forward the tail if the client consumed the data */
-	qcom_smd_channel_advance(channel, len);
-
-	channel->pkt_size = 0;
-
-	return 0;
-}
-
-/*
- * Per channel interrupt handling
- */
-static bool qcom_smd_channel_intr(struct qcom_smd_channel *channel)
-{
-	bool need_state_scan = false;
-	int remote_state;
-	__le32 pktlen;
-	int avail;
-	int ret;
-
-	/* Handle state changes */
-	remote_state = GET_RX_CHANNEL_INFO(channel, state);
-	if (remote_state != channel->remote_state) {
-		channel->remote_state = remote_state;
-		need_state_scan = true;
-	}
-	/* Indicate that we have seen any state change */
-	SET_RX_CHANNEL_FLAG(channel, fSTATE, 0);
-
-	/* Signal waiting qcom_smd_send() about the interrupt */
-	if (!GET_TX_CHANNEL_FLAG(channel, fBLOCKREADINTR))
-		wake_up_interruptible(&channel->fblockread_event);
-
-	/* Don't consume any data until we've opened the channel */
-	if (channel->state != SMD_CHANNEL_OPENED)
-		goto out;
-
-	/* Indicate that we've seen the new data */
-	SET_RX_CHANNEL_FLAG(channel, fHEAD, 0);
-
-	/* Consume data */
-	for (;;) {
-		avail = qcom_smd_channel_get_rx_avail(channel);
-
-		if (!channel->pkt_size && avail >= SMD_PACKET_HEADER_LEN) {
-			qcom_smd_channel_peek(channel, &pktlen, sizeof(pktlen));
-			qcom_smd_channel_advance(channel, SMD_PACKET_HEADER_LEN);
-			channel->pkt_size = le32_to_cpu(pktlen);
-		} else if (channel->pkt_size && avail >= channel->pkt_size) {
-			ret = qcom_smd_channel_recv_single(channel);
-			if (ret)
-				break;
-		} else {
-			break;
-		}
-	}
-
-	/* Indicate that we have seen and updated tail */
-	SET_RX_CHANNEL_FLAG(channel, fTAIL, 1);
-
-	/* Signal the remote that we've consumed the data (if requested) */
-	if (!GET_RX_CHANNEL_FLAG(channel, fBLOCKREADINTR)) {
-		/* Ensure ordering of channel info updates */
-		wmb();
-
-		qcom_smd_signal_channel(channel);
-	}
-
-out:
-	return need_state_scan;
-}
-
-/*
- * The edge interrupts are triggered by the remote processor on state changes,
- * channel info updates or when new channels are created.
- */
-static irqreturn_t qcom_smd_edge_intr(int irq, void *data)
-{
-	struct qcom_smd_edge *edge = data;
-	struct qcom_smd_channel *channel;
-	unsigned available;
-	bool kick_scanner = false;
-	bool kick_state = false;
-
-	/*
-	 * Handle state changes or data on each of the channels on this edge
-	 */
-	spin_lock(&edge->channels_lock);
-	list_for_each_entry(channel, &edge->channels, list) {
-		spin_lock(&channel->recv_lock);
-		kick_state |= qcom_smd_channel_intr(channel);
-		spin_unlock(&channel->recv_lock);
-	}
-	spin_unlock(&edge->channels_lock);
-
-	/*
-	 * Creating a new channel requires allocating an smem entry, so we only
-	 * have to scan if the amount of available space in smem have changed
-	 * since last scan.
-	 */
-	available = qcom_smem_get_free_space(edge->remote_pid);
-	if (available != edge->smem_available) {
-		edge->smem_available = available;
-		kick_scanner = true;
-	}
-
-	if (kick_scanner)
-		schedule_work(&edge->scan_work);
-	if (kick_state)
-		schedule_work(&edge->state_work);
-
-	return IRQ_HANDLED;
-}
-
-/*
- * Delivers any outstanding packets in the rx fifo, can be used after probe of
- * the clients to deliver any packets that wasn't delivered before the client
- * was setup.
- */
-static void qcom_smd_channel_resume(struct qcom_smd_channel *channel)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&channel->recv_lock, flags);
-	qcom_smd_channel_intr(channel);
-	spin_unlock_irqrestore(&channel->recv_lock, flags);
-}
-
-/*
- * Calculate how much space is available in the tx fifo.
- */
-static size_t qcom_smd_get_tx_avail(struct qcom_smd_channel *channel)
-{
-	unsigned head;
-	unsigned tail;
-	unsigned mask = channel->fifo_size - 1;
-
-	head = GET_TX_CHANNEL_INFO(channel, head);
-	tail = GET_TX_CHANNEL_INFO(channel, tail);
-
-	return mask - ((head - tail) & mask);
-}
-
-/*
- * Write count bytes of data into channel, possibly wrapping in the ring buffer
- */
-static int qcom_smd_write_fifo(struct qcom_smd_channel *channel,
-			       const void *data,
-			       size_t count)
-{
-	bool word_aligned;
-	unsigned head;
-	size_t len;
-
-	word_aligned = channel->info_word;
-	head = GET_TX_CHANNEL_INFO(channel, head);
-
-	len = min_t(size_t, count, channel->fifo_size - head);
-	if (len) {
-		smd_copy_to_fifo(channel->tx_fifo + head,
-				 data,
-				 len,
-				 word_aligned);
-	}
-
-	if (len != count) {
-		smd_copy_to_fifo(channel->tx_fifo,
-				 data + len,
-				 count - len,
-				 word_aligned);
-	}
-
-	head += count;
-	head &= (channel->fifo_size - 1);
-	SET_TX_CHANNEL_INFO(channel, head, head);
-
-	return count;
-}
-
-/**
- * qcom_smd_send - write data to smd channel
- * @channel:	channel handle
- * @data:	buffer of data to write
- * @len:	number of bytes to write
- *
- * This is a blocking write of len bytes into the channel's tx ring buffer and
- * signal the remote end. It will sleep until there is enough space available
- * in the tx buffer, utilizing the fBLOCKREADINTR signaling mechanism to avoid
- * polling.
- */
-int qcom_smd_send(struct qcom_smd_channel *channel, const void *data, int len)
-{
-	__le32 hdr[5] = { cpu_to_le32(len), };
-	int tlen = sizeof(hdr) + len;
-	int ret;
-
-	/* Word aligned channels only accept word size aligned data */
-	if (channel->info_word && len % 4)
-		return -EINVAL;
-
-	/* Reject packets that are too big */
-	if (tlen >= channel->fifo_size)
-		return -EINVAL;
-
-	ret = mutex_lock_interruptible(&channel->tx_lock);
-	if (ret)
-		return ret;
-
-	while (qcom_smd_get_tx_avail(channel) < tlen) {
-		if (channel->state != SMD_CHANNEL_OPENED) {
-			ret = -EPIPE;
-			goto out;
-		}
-
-		SET_TX_CHANNEL_FLAG(channel, fBLOCKREADINTR, 0);
-
-		ret = wait_event_interruptible(channel->fblockread_event,
-				       qcom_smd_get_tx_avail(channel) >= tlen ||
-				       channel->state != SMD_CHANNEL_OPENED);
-		if (ret)
-			goto out;
-
-		SET_TX_CHANNEL_FLAG(channel, fBLOCKREADINTR, 1);
-	}
-
-	SET_TX_CHANNEL_FLAG(channel, fTAIL, 0);
-
-	qcom_smd_write_fifo(channel, hdr, sizeof(hdr));
-	qcom_smd_write_fifo(channel, data, len);
-
-	SET_TX_CHANNEL_FLAG(channel, fHEAD, 1);
-
-	/* Ensure ordering of channel info updates */
-	wmb();
-
-	qcom_smd_signal_channel(channel);
-
-out:
-	mutex_unlock(&channel->tx_lock);
-
-	return ret;
-}
-EXPORT_SYMBOL(qcom_smd_send);
-
-static struct qcom_smd_device *to_smd_device(struct device *dev)
-{
-	return container_of(dev, struct qcom_smd_device, dev);
-}
-
-static struct qcom_smd_driver *to_smd_driver(struct device *dev)
-{
-	struct qcom_smd_device *qsdev = to_smd_device(dev);
-
-	return container_of(qsdev->dev.driver, struct qcom_smd_driver, driver);
-}
-
-static int qcom_smd_dev_match(struct device *dev, struct device_driver *drv)
-{
-	struct qcom_smd_device *qsdev = to_smd_device(dev);
-	struct qcom_smd_driver *qsdrv = container_of(drv, struct qcom_smd_driver, driver);
-	const struct qcom_smd_id *match = qsdrv->smd_match_table;
-	const char *name = qsdev->channel->name;
-
-	if (match) {
-		while (match->name[0]) {
-			if (!strcmp(match->name, name))
-				return 1;
-			match++;
-		}
-	}
-
-	return of_driver_match_device(dev, drv);
-}
-
-/*
- * Helper for opening a channel
- */
-static int qcom_smd_channel_open(struct qcom_smd_channel *channel,
-				 qcom_smd_cb_t cb)
-{
-	size_t bb_size;
-
-	/*
-	 * Packets are maximum 4k, but reduce if the fifo is smaller
-	 */
-	bb_size = min(channel->fifo_size, SZ_4K);
-	channel->bounce_buffer = kmalloc(bb_size, GFP_KERNEL);
-	if (!channel->bounce_buffer)
-		return -ENOMEM;
-
-	qcom_smd_channel_set_callback(channel, cb);
-	qcom_smd_channel_set_state(channel, SMD_CHANNEL_OPENING);
-	qcom_smd_channel_set_state(channel, SMD_CHANNEL_OPENED);
-
-	return 0;
-}
-
-/*
- * Helper for closing and resetting a channel
- */
-static void qcom_smd_channel_close(struct qcom_smd_channel *channel)
-{
-	qcom_smd_channel_set_callback(channel, NULL);
-
-	kfree(channel->bounce_buffer);
-	channel->bounce_buffer = NULL;
-
-	qcom_smd_channel_set_state(channel, SMD_CHANNEL_CLOSED);
-	qcom_smd_channel_reset(channel);
-}
-
-/*
- * Probe the smd client.
- *
- * The remote side have indicated that it want the channel to be opened, so
- * complete the state handshake and probe our client driver.
- */
-static int qcom_smd_dev_probe(struct device *dev)
-{
-	struct qcom_smd_device *qsdev = to_smd_device(dev);
-	struct qcom_smd_driver *qsdrv = to_smd_driver(dev);
-	struct qcom_smd_channel *channel = qsdev->channel;
-	int ret;
-
-	ret = qcom_smd_channel_open(channel, qsdrv->callback);
-	if (ret)
-		return ret;
-
-	ret = qsdrv->probe(qsdev);
-	if (ret)
-		goto err;
-
-	qcom_smd_channel_resume(channel);
-
-	return 0;
-
-err:
-	dev_err(&qsdev->dev, "probe failed\n");
-
-	qcom_smd_channel_close(channel);
-	return ret;
-}
-
-/*
- * Remove the smd client.
- *
- * The channel is going away, for some reason, so remove the smd client and
- * reset the channel state.
- */
-static int qcom_smd_dev_remove(struct device *dev)
-{
-	struct qcom_smd_device *qsdev = to_smd_device(dev);
-	struct qcom_smd_driver *qsdrv = to_smd_driver(dev);
-	struct qcom_smd_channel *channel = qsdev->channel;
-
-	qcom_smd_channel_set_state(channel, SMD_CHANNEL_CLOSING);
-
-	/*
-	 * Make sure we don't race with the code receiving data.
-	 */
-	qcom_smd_channel_set_callback(channel, NULL);
-
-	/* Wake up any sleepers in qcom_smd_send() */
-	wake_up_interruptible(&channel->fblockread_event);
-
-	/*
-	 * We expect that the client might block in remove() waiting for any
-	 * outstanding calls to qcom_smd_send() to wake up and finish.
-	 */
-	if (qsdrv->remove)
-		qsdrv->remove(qsdev);
-
-	/* The client is now gone, close the primary channel */
-	qcom_smd_channel_close(channel);
-	channel->qsdev = NULL;
-
-	return 0;
-}
-
-static struct bus_type qcom_smd_bus = {
-	.name = "qcom_smd",
-	.match = qcom_smd_dev_match,
-	.probe = qcom_smd_dev_probe,
-	.remove = qcom_smd_dev_remove,
-};
-
-/*
- * Release function for the qcom_smd_device object.
- */
-static void qcom_smd_release_device(struct device *dev)
-{
-	struct qcom_smd_device *qsdev = to_smd_device(dev);
-
-	kfree(qsdev);
-}
-
-/*
- * Finds the device_node for the smd child interested in this channel.
- */
-static struct device_node *qcom_smd_match_channel(struct device_node *edge_node,
-						  const char *channel)
-{
-	struct device_node *child;
-	const char *name;
-	const char *key;
-	int ret;
-
-	for_each_available_child_of_node(edge_node, child) {
-		key = "qcom,smd-channels";
-		ret = of_property_read_string(child, key, &name);
-		if (ret)
-			continue;
-
-		if (strcmp(name, channel) == 0)
-			return child;
-	}
-
-	return NULL;
-}
-
-/*
- * Create a smd client device for channel that is being opened.
- */
-static int qcom_smd_create_device(struct qcom_smd_channel *channel)
-{
-	struct qcom_smd_device *qsdev;
-	struct qcom_smd_edge *edge = channel->edge;
-	struct device_node *node;
-	int ret;
-
-	if (channel->qsdev)
-		return -EEXIST;
-
-	dev_dbg(&edge->dev, "registering '%s'\n", channel->name);
-
-	qsdev = kzalloc(sizeof(*qsdev), GFP_KERNEL);
-	if (!qsdev)
-		return -ENOMEM;
-
-	node = qcom_smd_match_channel(edge->of_node, channel->name);
-	dev_set_name(&qsdev->dev, "%s.%s",
-		     edge->of_node->name,
-		     node ? node->name : channel->name);
-
-	qsdev->dev.parent = &edge->dev;
-	qsdev->dev.bus = &qcom_smd_bus;
-	qsdev->dev.release = qcom_smd_release_device;
-	qsdev->dev.of_node = node;
-
-	qsdev->channel = channel;
-
-	channel->qsdev = qsdev;
-
-	ret = device_register(&qsdev->dev);
-	if (ret) {
-		dev_err(&edge->dev, "device_register failed: %d\n", ret);
-		put_device(&qsdev->dev);
-	}
-
-	return ret;
-}
-
-/*
- * Destroy a smd client device for a channel that's going away.
- */
-static void qcom_smd_destroy_device(struct qcom_smd_channel *channel)
-{
-	struct device *dev;
-
-	BUG_ON(!channel->qsdev);
-
-	dev = &channel->qsdev->dev;
-
-	device_unregister(dev);
-	of_node_put(dev->of_node);
-	put_device(dev);
-}
-
-/**
- * qcom_smd_driver_register - register a smd driver
- * @qsdrv:	qcom_smd_driver struct
- */
-int qcom_smd_driver_register(struct qcom_smd_driver *qsdrv)
-{
-	qsdrv->driver.bus = &qcom_smd_bus;
-	return driver_register(&qsdrv->driver);
-}
-EXPORT_SYMBOL(qcom_smd_driver_register);
-
-void *qcom_smd_get_drvdata(struct qcom_smd_channel *channel)
-{
-	return channel->drvdata;
-}
-EXPORT_SYMBOL(qcom_smd_get_drvdata);
-
-void qcom_smd_set_drvdata(struct qcom_smd_channel *channel, void *data)
-{
-	channel->drvdata = data;
-}
-EXPORT_SYMBOL(qcom_smd_set_drvdata);
-
-/**
- * qcom_smd_driver_unregister - unregister a smd driver
- * @qsdrv:	qcom_smd_driver struct
- */
-void qcom_smd_driver_unregister(struct qcom_smd_driver *qsdrv)
-{
-	driver_unregister(&qsdrv->driver);
-}
-EXPORT_SYMBOL(qcom_smd_driver_unregister);
-
-static struct qcom_smd_channel *
-qcom_smd_find_channel(struct qcom_smd_edge *edge, const char *name)
-{
-	struct qcom_smd_channel *channel;
-	struct qcom_smd_channel *ret = NULL;
-	unsigned long flags;
-	unsigned state;
-
-	spin_lock_irqsave(&edge->channels_lock, flags);
-	list_for_each_entry(channel, &edge->channels, list) {
-		if (strcmp(channel->name, name))
-			continue;
-
-		state = GET_RX_CHANNEL_INFO(channel, state);
-		if (state != SMD_CHANNEL_OPENING &&
-		    state != SMD_CHANNEL_OPENED)
-			continue;
-
-		ret = channel;
-		break;
-	}
-	spin_unlock_irqrestore(&edge->channels_lock, flags);
-
-	return ret;
-}
-
-/**
- * qcom_smd_open_channel() - claim additional channels on the same edge
- * @sdev:	smd_device handle
- * @name:	channel name
- * @cb:		callback method to use for incoming data
- *
- * Returns a channel handle on success, or -EPROBE_DEFER if the channel isn't
- * ready.
- *
- * Any channels returned must be closed with a call to qcom_smd_close_channel()
- */
-struct qcom_smd_channel *qcom_smd_open_channel(struct qcom_smd_channel *parent,
-					       const char *name,
-					       qcom_smd_cb_t cb)
-{
-	struct qcom_smd_channel *channel;
-	struct qcom_smd_device *sdev = parent->qsdev;
-	struct qcom_smd_edge *edge = parent->edge;
-	int ret;
-
-	/* Wait up to HZ for the channel to appear */
-	ret = wait_event_interruptible_timeout(edge->new_channel_event,
-			(channel = qcom_smd_find_channel(edge, name)) != NULL,
-			HZ);
-	if (!ret)
-		return ERR_PTR(-ETIMEDOUT);
-
-	if (channel->state != SMD_CHANNEL_CLOSED) {
-		dev_err(&sdev->dev, "channel %s is busy\n", channel->name);
-		return ERR_PTR(-EBUSY);
-	}
-
-	channel->qsdev = sdev;
-	ret = qcom_smd_channel_open(channel, cb);
-	if (ret) {
-		channel->qsdev = NULL;
-		return ERR_PTR(ret);
-	}
-
-	return channel;
-}
-EXPORT_SYMBOL(qcom_smd_open_channel);
-
-/**
- * qcom_smd_close_channel() - close an additionally opened channel
- * @channel:	channel handle, returned by qcom_smd_open_channel()
- */
-void qcom_smd_close_channel(struct qcom_smd_channel *channel)
-{
-	qcom_smd_channel_close(channel);
-	channel->qsdev = NULL;
-}
-EXPORT_SYMBOL(qcom_smd_close_channel);
-
-/*
- * Allocate the qcom_smd_channel object for a newly found smd channel,
- * retrieving and validating the smem items involved.
- */
-static struct qcom_smd_channel *qcom_smd_create_channel(struct qcom_smd_edge *edge,
-							unsigned smem_info_item,
-							unsigned smem_fifo_item,
-							char *name)
-{
-	struct qcom_smd_channel *channel;
-	size_t fifo_size;
-	size_t info_size;
-	void *fifo_base;
-	void *info;
-	int ret;
-
-	channel = devm_kzalloc(&edge->dev, sizeof(*channel), GFP_KERNEL);
-	if (!channel)
-		return ERR_PTR(-ENOMEM);
-
-	channel->edge = edge;
-	channel->name = devm_kstrdup(&edge->dev, name, GFP_KERNEL);
-	if (!channel->name)
-		return ERR_PTR(-ENOMEM);
-
-	mutex_init(&channel->tx_lock);
-	spin_lock_init(&channel->recv_lock);
-	init_waitqueue_head(&channel->fblockread_event);
-
-	info = qcom_smem_get(edge->remote_pid, smem_info_item, &info_size);
-	if (IS_ERR(info)) {
-		ret = PTR_ERR(info);
-		goto free_name_and_channel;
-	}
-
-	/*
-	 * Use the size of the item to figure out which channel info struct to
-	 * use.
-	 */
-	if (info_size == 2 * sizeof(struct smd_channel_info_word)) {
-		channel->info_word = info;
-	} else if (info_size == 2 * sizeof(struct smd_channel_info)) {
-		channel->info = info;
-	} else {
-		dev_err(&edge->dev,
-			"channel info of size %zu not supported\n", info_size);
-		ret = -EINVAL;
-		goto free_name_and_channel;
-	}
-
-	fifo_base = qcom_smem_get(edge->remote_pid, smem_fifo_item, &fifo_size);
-	if (IS_ERR(fifo_base)) {
-		ret =  PTR_ERR(fifo_base);
-		goto free_name_and_channel;
-	}
-
-	/* The channel consist of a rx and tx fifo of equal size */
-	fifo_size /= 2;
-
-	dev_dbg(&edge->dev, "new channel '%s' info-size: %zu fifo-size: %zu\n",
-			  name, info_size, fifo_size);
-
-	channel->tx_fifo = fifo_base;
-	channel->rx_fifo = fifo_base + fifo_size;
-	channel->fifo_size = fifo_size;
-
-	qcom_smd_channel_reset(channel);
-
-	return channel;
-
-free_name_and_channel:
-	devm_kfree(&edge->dev, channel->name);
-	devm_kfree(&edge->dev, channel);
-
-	return ERR_PTR(ret);
-}
-
-/*
- * Scans the allocation table for any newly allocated channels, calls
- * qcom_smd_create_channel() to create representations of these and add
- * them to the edge's list of channels.
- */
-static void qcom_channel_scan_worker(struct work_struct *work)
-{
-	struct qcom_smd_edge *edge = container_of(work, struct qcom_smd_edge, scan_work);
-	struct qcom_smd_alloc_entry *alloc_tbl;
-	struct qcom_smd_alloc_entry *entry;
-	struct qcom_smd_channel *channel;
-	unsigned long flags;
-	unsigned fifo_id;
-	unsigned info_id;
-	int tbl;
-	int i;
-	u32 eflags, cid;
-
-	for (tbl = 0; tbl < SMD_ALLOC_TBL_COUNT; tbl++) {
-		alloc_tbl = qcom_smem_get(edge->remote_pid,
-				    smem_items[tbl].alloc_tbl_id, NULL);
-		if (IS_ERR(alloc_tbl))
-			continue;
-
-		for (i = 0; i < SMD_ALLOC_TBL_SIZE; i++) {
-			entry = &alloc_tbl[i];
-			eflags = le32_to_cpu(entry->flags);
-			if (test_bit(i, edge->allocated[tbl]))
-				continue;
-
-			if (entry->ref_count == 0)
-				continue;
-
-			if (!entry->name[0])
-				continue;
-
-			if (!(eflags & SMD_CHANNEL_FLAGS_PACKET))
-				continue;
-
-			if ((eflags & SMD_CHANNEL_FLAGS_EDGE_MASK) != edge->edge_id)
-				continue;
-
-			cid = le32_to_cpu(entry->cid);
-			info_id = smem_items[tbl].info_base_id + cid;
-			fifo_id = smem_items[tbl].fifo_base_id + cid;
-
-			channel = qcom_smd_create_channel(edge, info_id, fifo_id, entry->name);
-			if (IS_ERR(channel))
-				continue;
-
-			spin_lock_irqsave(&edge->channels_lock, flags);
-			list_add(&channel->list, &edge->channels);
-			spin_unlock_irqrestore(&edge->channels_lock, flags);
-
-			dev_dbg(&edge->dev, "new channel found: '%s'\n", channel->name);
-			set_bit(i, edge->allocated[tbl]);
-
-			wake_up_interruptible(&edge->new_channel_event);
-		}
-	}
-
-	schedule_work(&edge->state_work);
-}
-
-/*
- * This per edge worker scans smem for any new channels and register these. It
- * then scans all registered channels for state changes that should be handled
- * by creating or destroying smd client devices for the registered channels.
- *
- * LOCKING: edge->channels_lock only needs to cover the list operations, as the
- * worker is killed before any channels are deallocated
- */
-static void qcom_channel_state_worker(struct work_struct *work)
-{
-	struct qcom_smd_channel *channel;
-	struct qcom_smd_edge *edge = container_of(work,
-						  struct qcom_smd_edge,
-						  state_work);
-	unsigned remote_state;
-	unsigned long flags;
-
-	/*
-	 * Register a device for any closed channel where the remote processor
-	 * is showing interest in opening the channel.
-	 */
-	spin_lock_irqsave(&edge->channels_lock, flags);
-	list_for_each_entry(channel, &edge->channels, list) {
-		if (channel->state != SMD_CHANNEL_CLOSED)
-			continue;
-
-		remote_state = GET_RX_CHANNEL_INFO(channel, state);
-		if (remote_state != SMD_CHANNEL_OPENING &&
-		    remote_state != SMD_CHANNEL_OPENED)
-			continue;
-
-		spin_unlock_irqrestore(&edge->channels_lock, flags);
-		qcom_smd_create_device(channel);
-		spin_lock_irqsave(&edge->channels_lock, flags);
-	}
-
-	/*
-	 * Unregister the device for any channel that is opened where the
-	 * remote processor is closing the channel.
-	 */
-	list_for_each_entry(channel, &edge->channels, list) {
-		if (channel->state != SMD_CHANNEL_OPENING &&
-		    channel->state != SMD_CHANNEL_OPENED)
-			continue;
-
-		remote_state = GET_RX_CHANNEL_INFO(channel, state);
-		if (remote_state == SMD_CHANNEL_OPENING ||
-		    remote_state == SMD_CHANNEL_OPENED)
-			continue;
-
-		spin_unlock_irqrestore(&edge->channels_lock, flags);
-		qcom_smd_destroy_device(channel);
-		spin_lock_irqsave(&edge->channels_lock, flags);
-	}
-	spin_unlock_irqrestore(&edge->channels_lock, flags);
-}
-
-/*
- * Parses an of_node describing an edge.
- */
-static int qcom_smd_parse_edge(struct device *dev,
-			       struct device_node *node,
-			       struct qcom_smd_edge *edge)
-{
-	struct device_node *syscon_np;
-	const char *key;
-	int irq;
-	int ret;
-
-	INIT_LIST_HEAD(&edge->channels);
-	spin_lock_init(&edge->channels_lock);
-
-	INIT_WORK(&edge->scan_work, qcom_channel_scan_worker);
-	INIT_WORK(&edge->state_work, qcom_channel_state_worker);
-
-	edge->of_node = of_node_get(node);
-
-	key = "qcom,smd-edge";
-	ret = of_property_read_u32(node, key, &edge->edge_id);
-	if (ret) {
-		dev_err(dev, "edge missing %s property\n", key);
-		return -EINVAL;
-	}
-
-	edge->remote_pid = QCOM_SMEM_HOST_ANY;
-	key = "qcom,remote-pid";
-	of_property_read_u32(node, key, &edge->remote_pid);
-
-	syscon_np = of_parse_phandle(node, "qcom,ipc", 0);
-	if (!syscon_np) {
-		dev_err(dev, "no qcom,ipc node\n");
-		return -ENODEV;
-	}
-
-	edge->ipc_regmap = syscon_node_to_regmap(syscon_np);
-	if (IS_ERR(edge->ipc_regmap))
-		return PTR_ERR(edge->ipc_regmap);
-
-	key = "qcom,ipc";
-	ret = of_property_read_u32_index(node, key, 1, &edge->ipc_offset);
-	if (ret < 0) {
-		dev_err(dev, "no offset in %s\n", key);
-		return -EINVAL;
-	}
-
-	ret = of_property_read_u32_index(node, key, 2, &edge->ipc_bit);
-	if (ret < 0) {
-		dev_err(dev, "no bit in %s\n", key);
-		return -EINVAL;
-	}
-
-	irq = irq_of_parse_and_map(node, 0);
-	if (irq < 0) {
-		dev_err(dev, "required smd interrupt missing\n");
-		return -EINVAL;
-	}
-
-	ret = devm_request_irq(dev, irq,
-			       qcom_smd_edge_intr, IRQF_TRIGGER_RISING,
-			       node->name, edge);
-	if (ret) {
-		dev_err(dev, "failed to request smd irq\n");
-		return ret;
-	}
-
-	edge->irq = irq;
-
-	return 0;
-}
-
-/*
- * Release function for an edge.
- * Reset the state of each associated channel and free the edge context.
- */
-static void qcom_smd_edge_release(struct device *dev)
-{
-	struct qcom_smd_channel *channel;
-	struct qcom_smd_edge *edge = to_smd_edge(dev);
-
-	list_for_each_entry(channel, &edge->channels, list) {
-		SET_RX_CHANNEL_INFO(channel, state, SMD_CHANNEL_CLOSED);
-		SET_RX_CHANNEL_INFO(channel, head, 0);
-		SET_RX_CHANNEL_INFO(channel, tail, 0);
-	}
-
-	kfree(edge);
-}
-
-/**
- * qcom_smd_register_edge() - register an edge based on an device_node
- * @parent:	parent device for the edge
- * @node:	device_node describing the edge
- *
- * Returns an edge reference, or negative ERR_PTR() on failure.
- */
-struct qcom_smd_edge *qcom_smd_register_edge(struct device *parent,
-					     struct device_node *node)
-{
-	struct qcom_smd_edge *edge;
-	int ret;
-
-	edge = kzalloc(sizeof(*edge), GFP_KERNEL);
-	if (!edge)
-		return ERR_PTR(-ENOMEM);
-
-	init_waitqueue_head(&edge->new_channel_event);
-
-	edge->dev.parent = parent;
-	edge->dev.release = qcom_smd_edge_release;
-	dev_set_name(&edge->dev, "%s:%s", dev_name(parent), node->name);
-	ret = device_register(&edge->dev);
-	if (ret) {
-		pr_err("failed to register smd edge\n");
-		return ERR_PTR(ret);
-	}
-
-	ret = qcom_smd_parse_edge(&edge->dev, node, edge);
-	if (ret) {
-		dev_err(&edge->dev, "failed to parse smd edge\n");
-		goto unregister_dev;
-	}
-
-	schedule_work(&edge->scan_work);
-
-	return edge;
-
-unregister_dev:
-	put_device(&edge->dev);
-	return ERR_PTR(ret);
-}
-EXPORT_SYMBOL(qcom_smd_register_edge);
-
-static int qcom_smd_remove_device(struct device *dev, void *data)
-{
-	device_unregister(dev);
-	of_node_put(dev->of_node);
-	put_device(dev);
-
-	return 0;
-}
-
-/**
- * qcom_smd_unregister_edge() - release an edge and its children
- * @edge:	edge reference acquired from qcom_smd_register_edge
- */
-int qcom_smd_unregister_edge(struct qcom_smd_edge *edge)
-{
-	int ret;
-
-	disable_irq(edge->irq);
-	cancel_work_sync(&edge->scan_work);
-	cancel_work_sync(&edge->state_work);
-
-	ret = device_for_each_child(&edge->dev, NULL, qcom_smd_remove_device);
-	if (ret)
-		dev_warn(&edge->dev, "can't remove smd device: %d\n", ret);
-
-	device_unregister(&edge->dev);
-
-	return 0;
-}
-EXPORT_SYMBOL(qcom_smd_unregister_edge);
-
-static int qcom_smd_probe(struct platform_device *pdev)
-{
-	struct device_node *node;
-	void *p;
-
-	/* Wait for smem */
-	p = qcom_smem_get(QCOM_SMEM_HOST_ANY, smem_items[0].alloc_tbl_id, NULL);
-	if (PTR_ERR(p) == -EPROBE_DEFER)
-		return PTR_ERR(p);
-
-	for_each_available_child_of_node(pdev->dev.of_node, node)
-		qcom_smd_register_edge(&pdev->dev, node);
-
-	return 0;
-}
-
-static int qcom_smd_remove_edge(struct device *dev, void *data)
-{
-	struct qcom_smd_edge *edge = to_smd_edge(dev);
-
-	return qcom_smd_unregister_edge(edge);
-}
-
-/*
- * Shut down all smd clients by making sure that each edge stops processing
- * events and scanning for new channels, then call destroy on the devices.
- */
-static int qcom_smd_remove(struct platform_device *pdev)
-{
-	int ret;
-
-	ret = device_for_each_child(&pdev->dev, NULL, qcom_smd_remove_edge);
-	if (ret)
-		dev_warn(&pdev->dev, "can't remove smd device: %d\n", ret);
-
-	return ret;
-}
-
-static const struct of_device_id qcom_smd_of_match[] = {
-	{ .compatible = "qcom,smd" },
-	{}
-};
-MODULE_DEVICE_TABLE(of, qcom_smd_of_match);
-
-static struct platform_driver qcom_smd_driver = {
-	.probe = qcom_smd_probe,
-	.remove = qcom_smd_remove,
-	.driver = {
-		.name = "qcom-smd",
-		.of_match_table = qcom_smd_of_match,
-	},
-};
-
-static int __init qcom_smd_init(void)
-{
-	int ret;
-
-	ret = bus_register(&qcom_smd_bus);
-	if (ret) {
-		pr_err("failed to register smd bus: %d\n", ret);
-		return ret;
-	}
-
-	return platform_driver_register(&qcom_smd_driver);
-}
-postcore_initcall(qcom_smd_init);
-
-static void __exit qcom_smd_exit(void)
-{
-	platform_driver_unregister(&qcom_smd_driver);
-	bus_unregister(&qcom_smd_bus);
-}
-module_exit(qcom_smd_exit);
-
-MODULE_AUTHOR("Bjorn Andersson <bjorn.andersson@sonymobile.com>");
-MODULE_DESCRIPTION("Qualcomm Shared Memory Driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/soc/qcom/wcnss_ctrl.c b/drivers/soc/qcom/wcnss_ctrl.c
index 520aedd29965..b9069184df19 100644
--- a/drivers/soc/qcom/wcnss_ctrl.c
+++ b/drivers/soc/qcom/wcnss_ctrl.c
@@ -14,10 +14,10 @@
 #include <linux/firmware.h>
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/soc/qcom/smd.h>
 #include <linux/io.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
+#include <linux/rpmsg.h>
 #include <linux/soc/qcom/wcnss_ctrl.h>
 
 #define WCNSS_REQUEST_TIMEOUT	(5 * HZ)
@@ -40,7 +40,7 @@
  */
 struct wcnss_ctrl {
 	struct device *dev;
-	struct qcom_smd_channel *channel;
+	struct rpmsg_endpoint *channel;
 
 	struct completion ack;
 	struct completion cbc;
@@ -122,11 +122,13 @@ struct wcnss_download_nv_resp {
  *
  * Handles any incoming packets from the remote WCNSS_CTRL service.
  */
-static int wcnss_ctrl_smd_callback(struct qcom_smd_channel *channel,
-				   const void *data,
-				   size_t count)
+static int wcnss_ctrl_smd_callback(struct rpmsg_device *rpdev,
+				   void *data,
+				   int count,
+				   void *priv,
+				   u32 addr)
 {
-	struct wcnss_ctrl *wcnss = qcom_smd_get_drvdata(channel);
+	struct wcnss_ctrl *wcnss = dev_get_drvdata(&rpdev->dev);
 	const struct wcnss_download_nv_resp *nvresp;
 	const struct wcnss_version_resp *version;
 	const struct wcnss_msg_hdr *hdr = data;
@@ -180,7 +182,7 @@ static int wcnss_request_version(struct wcnss_ctrl *wcnss)
 
 	msg.type = WCNSS_VERSION_REQ;
 	msg.len = sizeof(msg);
-	ret = qcom_smd_send(wcnss->channel, &msg, sizeof(msg));
+	ret = rpmsg_send(wcnss->channel, &msg, sizeof(msg));
 	if (ret < 0)
 		return ret;
 
@@ -238,7 +240,7 @@ static int wcnss_download_nv(struct wcnss_ctrl *wcnss, bool *expect_cbc)
 
 		memcpy(req->fragment, data, req->frag_size);
 
-		ret = qcom_smd_send(wcnss->channel, req, req->hdr.len);
+		ret = rpmsg_send(wcnss->channel, req, req->hdr.len);
 		if (ret < 0) {
 			dev_err(wcnss->dev, "failed to send smd packet\n");
 			goto release_fw;
@@ -274,11 +276,16 @@ free_req:
  * @name:	SMD channel name
  * @cb:		callback to handle incoming data on the channel
  */
-struct qcom_smd_channel *qcom_wcnss_open_channel(void *wcnss, const char *name, qcom_smd_cb_t cb)
+struct rpmsg_endpoint *qcom_wcnss_open_channel(void *wcnss, const char *name, rpmsg_rx_cb_t cb, void *priv)
 {
+	struct rpmsg_channel_info chinfo;
 	struct wcnss_ctrl *_wcnss = wcnss;
 
-	return qcom_smd_open_channel(_wcnss->channel, name, cb);
+	strncpy(chinfo.name, name, sizeof(chinfo.name));
+	chinfo.src = RPMSG_ADDR_ANY;
+	chinfo.dst = RPMSG_ADDR_ANY;
+
+	return rpmsg_create_ept(_wcnss->channel->rpdev, cb, priv, chinfo);
 }
 EXPORT_SYMBOL(qcom_wcnss_open_channel);
 
@@ -306,35 +313,34 @@ static void wcnss_async_probe(struct work_struct *work)
 	of_platform_populate(wcnss->dev->of_node, NULL, NULL, wcnss->dev);
 }
 
-static int wcnss_ctrl_probe(struct qcom_smd_device *sdev)
+static int wcnss_ctrl_probe(struct rpmsg_device *rpdev)
 {
 	struct wcnss_ctrl *wcnss;
 
-	wcnss = devm_kzalloc(&sdev->dev, sizeof(*wcnss), GFP_KERNEL);
+	wcnss = devm_kzalloc(&rpdev->dev, sizeof(*wcnss), GFP_KERNEL);
 	if (!wcnss)
 		return -ENOMEM;
 
-	wcnss->dev = &sdev->dev;
-	wcnss->channel = sdev->channel;
+	wcnss->dev = &rpdev->dev;
+	wcnss->channel = rpdev->ept;
 
 	init_completion(&wcnss->ack);
 	init_completion(&wcnss->cbc);
 	INIT_WORK(&wcnss->probe_work, wcnss_async_probe);
 
-	qcom_smd_set_drvdata(sdev->channel, wcnss);
-	dev_set_drvdata(&sdev->dev, wcnss);
+	dev_set_drvdata(&rpdev->dev, wcnss);
 
 	schedule_work(&wcnss->probe_work);
 
 	return 0;
 }
 
-static void wcnss_ctrl_remove(struct qcom_smd_device *sdev)
+static void wcnss_ctrl_remove(struct rpmsg_device *rpdev)
 {
-	struct wcnss_ctrl *wcnss = qcom_smd_get_drvdata(sdev->channel);
+	struct wcnss_ctrl *wcnss = dev_get_drvdata(&rpdev->dev);
 
 	cancel_work_sync(&wcnss->probe_work);
-	of_platform_depopulate(&sdev->dev);
+	of_platform_depopulate(&rpdev->dev);
 }
 
 static const struct of_device_id wcnss_ctrl_of_match[] = {
@@ -342,18 +348,18 @@ static const struct of_device_id wcnss_ctrl_of_match[] = {
 	{}
 };
 
-static struct qcom_smd_driver wcnss_ctrl_driver = {
+static struct rpmsg_driver wcnss_ctrl_driver = {
 	.probe = wcnss_ctrl_probe,
 	.remove = wcnss_ctrl_remove,
 	.callback = wcnss_ctrl_smd_callback,
-	.driver  = {
+	.drv  = {
 		.name  = "qcom_wcnss_ctrl",
 		.owner = THIS_MODULE,
 		.of_match_table = wcnss_ctrl_of_match,
 	},
 };
 
-module_qcom_smd_driver(wcnss_ctrl_driver);
+module_rpmsg_driver(wcnss_ctrl_driver);
 
 MODULE_DESCRIPTION("Qualcomm WCNSS control driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index c6fc7141d7b2..677f0ddc986c 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -446,7 +446,7 @@ static struct sysrq_key_op *sysrq_key_table[36] = {
 	 */
 	NULL,				/* a */
 	&sysrq_reboot_op,		/* b */
-	&sysrq_crash_op,		/* c & ibm_emac driver debug */
+	&sysrq_crash_op,		/* c */
 	&sysrq_showlocks_op,		/* d */
 	&sysrq_term_op,			/* e */
 	&sysrq_moom_op,			/* f */
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 224717e63a53..864819ff9a7d 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -16,6 +16,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/etherdevice.h>
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 15e1db8738ae..8c91f37ac0eb 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -37,6 +37,7 @@
 #include <linux/freezer.h>
 #include <linux/namei.h>
 #include <linux/random.h>
+#include <linux/uuid.h>
 #include <linux/xattr.h>
 #include <net/ipv6.h>
 #include "cifsfs.h"
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 9ae695ae3ed7..858698dcde3c 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -35,6 +35,7 @@
 #include <linux/pagevec.h>
 #include <linux/freezer.h>
 #include <linux/namei.h>
+#include <linux/uuid.h>
 #include <linux/uaccess.h>
 #include <asm/processor.h>
 #include <linux/inet.h>
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 7446496850a3..fb75fe908225 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -33,6 +33,7 @@
 #include <linux/vfs.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/uaccess.h>
+#include <linux/uuid.h>
 #include <linux/pagemap.h>
 #include <linux/xattr.h>
 #include "smb2pdu.h"
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 341251421ced..5420767c9b68 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -42,6 +42,7 @@
 #include <linux/seq_file.h>
 #include <linux/compat.h>
 #include <linux/rculist.h>
+#include <net/busy_poll.h>
 
 /*
  * LOCKING:
@@ -224,6 +225,11 @@ struct eventpoll {
 	/* used to optimize loop detection check */
 	int visited;
 	struct list_head visited_list_link;
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	/* used to track busy poll napi_id */
+	unsigned int napi_id;
+#endif
 };
 
 /* Wait structure used by the poll hooks */
@@ -384,6 +390,77 @@ static inline int ep_events_available(struct eventpoll *ep)
 	return !list_empty(&ep->rdllist) || ep->ovflist != EP_UNACTIVE_PTR;
 }
 
+#ifdef CONFIG_NET_RX_BUSY_POLL
+static bool ep_busy_loop_end(void *p, unsigned long start_time)
+{
+	struct eventpoll *ep = p;
+
+	return ep_events_available(ep) || busy_loop_timeout(start_time);
+}
+#endif /* CONFIG_NET_RX_BUSY_POLL */
+
+/*
+ * Busy poll if globally on and supporting sockets found && no events,
+ * busy loop will return if need_resched or ep_events_available.
+ *
+ * we must do our busy polling with irqs enabled
+ */
+static void ep_busy_loop(struct eventpoll *ep, int nonblock)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned int napi_id = READ_ONCE(ep->napi_id);
+
+	if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on())
+		napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep);
+#endif
+}
+
+static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	if (ep->napi_id)
+		ep->napi_id = 0;
+#endif
+}
+
+/*
+ * Set epoll busy poll NAPI ID from sk.
+ */
+static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	struct eventpoll *ep;
+	unsigned int napi_id;
+	struct socket *sock;
+	struct sock *sk;
+	int err;
+
+	if (!net_busy_loop_on())
+		return;
+
+	sock = sock_from_file(epi->ffd.file, &err);
+	if (!sock)
+		return;
+
+	sk = sock->sk;
+	if (!sk)
+		return;
+
+	napi_id = READ_ONCE(sk->sk_napi_id);
+	ep = epi->ep;
+
+	/* Non-NAPI IDs can be rejected
+	 *	or
+	 * Nothing to do if we already have this ID
+	 */
+	if (napi_id < MIN_NAPI_ID || napi_id == ep->napi_id)
+		return;
+
+	/* record NAPI ID for use in next busy poll */
+	ep->napi_id = napi_id;
+#endif
+}
+
 /**
  * ep_call_nested - Perform a bound (possibly) nested call, by checking
  *                  that the recursion limit is not exceeded, and that
@@ -1022,6 +1099,8 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
 
 	spin_lock_irqsave(&ep->lock, flags);
 
+	ep_set_busy_poll_napi_id(epi);
+
 	/*
 	 * If the event mask does not contain any poll(2) event, we consider the
 	 * descriptor to be disabled. This condition is likely the effect of the
@@ -1363,6 +1442,9 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 	/* We have to drop the new item inside our item list to keep track of it */
 	spin_lock_irqsave(&ep->lock, flags);
 
+	/* record NAPI ID of new item if present */
+	ep_set_busy_poll_napi_id(epi);
+
 	/* If the file is already "ready" we drop it inside the ready list */
 	if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) {
 		list_add_tail(&epi->rdllink, &ep->rdllist);
@@ -1637,10 +1719,21 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 	}
 
 fetch_events:
+
+	if (!ep_events_available(ep))
+		ep_busy_loop(ep, timed_out);
+
 	spin_lock_irqsave(&ep->lock, flags);
 
 	if (!ep_events_available(ep)) {
 		/*
+		 * Busy poll timed out.  Drop NAPI ID for now, we can add
+		 * it back in when we have moved a socket with a valid NAPI
+		 * ID onto the ready list.
+		 */
+		ep_reset_busy_poll_napi_id(ep);
+
+		/*
 		 * We don't have any available event to return to the caller.
 		 * We need to sleep here, and we will be wake up by
 		 * ep_poll_callback() when events will become available.
diff --git a/fs/select.c b/fs/select.c
index e2112270d75a..9287d3a96e35 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -409,7 +409,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 	int retval, i, timed_out = 0;
 	u64 slack = 0;
 	unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
-	unsigned long busy_end = 0;
+	unsigned long busy_start = 0;
 
 	rcu_read_lock();
 	retval = max_select_fd(n, fds);
@@ -512,11 +512,11 @@ int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 
 		/* only if found POLL_BUSY_LOOP sockets && not out of time */
 		if (can_busy_loop && !need_resched()) {
-			if (!busy_end) {
-				busy_end = busy_loop_end_time();
+			if (!busy_start) {
+				busy_start = busy_loop_current_time();
 				continue;
 			}
-			if (!busy_loop_timeout(busy_end))
+			if (!busy_loop_timeout(busy_start))
 				continue;
 		}
 		busy_flag = 0;
@@ -800,7 +800,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
 	int timed_out = 0, count = 0;
 	u64 slack = 0;
 	unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
-	unsigned long busy_end = 0;
+	unsigned long busy_start = 0;
 
 	/* Optimise the no-wait case */
 	if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
@@ -853,11 +853,11 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
 
 		/* only if found POLL_BUSY_LOOP sockets && not out of time */
 		if (can_busy_loop && !need_resched()) {
-			if (!busy_end) {
-				busy_end = busy_loop_end_time();
+			if (!busy_start) {
+				busy_start = busy_loop_current_time();
 				continue;
 			}
-			if (!busy_loop_timeout(busy_end))
+			if (!busy_loop_timeout(busy_start))
 				continue;
 		}
 		busy_flag = 0;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 909fc033173a..bbb513da5075 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -35,6 +35,7 @@ struct bpf_map_ops {
 	void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
 				int fd);
 	void (*map_fd_put_ptr)(void *ptr);
+	u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
 };
 
 struct bpf_map {
@@ -49,6 +50,7 @@ struct bpf_map {
 	const struct bpf_map_ops *ops;
 	struct work_struct work;
 	atomic_t usercnt;
+	struct bpf_map *inner_map_meta;
 };
 
 struct bpf_map_type_list {
@@ -167,6 +169,8 @@ struct bpf_verifier_ops {
 				  const struct bpf_insn *src,
 				  struct bpf_insn *dst,
 				  struct bpf_prog *prog);
+	int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr,
+			union bpf_attr __user *uattr);
 };
 
 struct bpf_prog_type_list {
@@ -231,6 +235,11 @@ typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src,
 u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 		     void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy);
 
+int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
+			  union bpf_attr __user *uattr);
+int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
+			  union bpf_attr __user *uattr);
+
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
 
@@ -275,6 +284,8 @@ int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value);
 int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
 				 void *key, void *value, u64 map_flags);
 void bpf_fd_array_map_clear(struct bpf_map *map);
+int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
+				void *key, void *value, u64 map_flags);
 
 /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
  * forced to use 'long' read/writes to try to atomically copy long counters.
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index a13b031dc6b8..5efb4db44e1e 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -66,7 +66,10 @@ struct bpf_verifier_state_list {
 };
 
 struct bpf_insn_aux_data {
-	enum bpf_reg_type ptr_type;	/* pointer type for load/store insns */
+	union {
+		enum bpf_reg_type ptr_type;	/* pointer type for load/store insns */
+		struct bpf_map *map_ptr;	/* pointer for call insn into lookup_elem */
+	};
 };
 
 #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 55e517130311..abcda9b458ab 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -25,6 +25,9 @@
 #define PHY_ID_BCM57780			0x03625d90
 
 #define PHY_ID_BCM7250			0xae025280
+#define PHY_ID_BCM7260			0xae025190
+#define PHY_ID_BCM7268			0xae025090
+#define PHY_ID_BCM7271			0xae0253b0
 #define PHY_ID_BCM7278			0xae0251a0
 #define PHY_ID_BCM7364			0xae025260
 #define PHY_ID_BCM7366			0x600d8490
diff --git a/include/linux/can/core.h b/include/linux/can/core.h
index df08a41d5be5..319a0da827b8 100644
--- a/include/linux/can/core.h
+++ b/include/linux/can/core.h
@@ -45,12 +45,13 @@ struct can_proto {
 extern int  can_proto_register(const struct can_proto *cp);
 extern void can_proto_unregister(const struct can_proto *cp);
 
-int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
+int can_rx_register(struct net *net, struct net_device *dev,
+		    canid_t can_id, canid_t mask,
 		    void (*func)(struct sk_buff *, void *),
 		    void *data, char *ident, struct sock *sk);
 
-extern void can_rx_unregister(struct net_device *dev, canid_t can_id,
-			      canid_t mask,
+extern void can_rx_unregister(struct net *net, struct net_device *dev,
+			      canid_t can_id, canid_t mask,
 			      void (*func)(struct sk_buff *, void *),
 			      void *data);
 
diff --git a/include/linux/can/platform/ti_hecc.h b/include/linux/can/platform/ti_hecc.h
deleted file mode 100644
index a52f47ca6c8a..000000000000
--- a/include/linux/can/platform/ti_hecc.h
+++ /dev/null
@@ -1,44 +0,0 @@
-#ifndef _CAN_PLATFORM_TI_HECC_H
-#define _CAN_PLATFORM_TI_HECC_H
-
-/*
- * TI HECC (High End CAN Controller) driver platform header
- *
- * Copyright (C) 2009 Texas Instruments Incorporated - http://www.ti.com/
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed as is WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-/**
- * struct hecc_platform_data - HECC Platform Data
- *
- * @scc_hecc_offset:	mostly 0 - should really never change
- * @scc_ram_offset:	SCC RAM offset
- * @hecc_ram_offset:	HECC RAM offset
- * @mbx_offset:		Mailbox RAM offset
- * @int_line:		Interrupt line to use - 0 or 1
- * @version:		version for future use
- * @transceiver_switch:	platform specific callback fn for transceiver control
- *
- * Platform data structure to get all platform specific settings.
- * this structure also accounts the fact that the IP may have different
- * RAM and mailbox offsets for different SOC's
- */
-struct ti_hecc_platform_data {
-	u32 scc_hecc_offset;
-	u32 scc_ram_offset;
-	u32 hecc_ram_offset;
-	u32 mbx_offset;
-	u32 int_line;
-	u32 version;
-	void (*transceiver_switch) (int);
-};
-#endif /* !_CAN_PLATFORM_TI_HECC_H */
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index c62b709b1ce0..2d9f80848d4b 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -447,21 +447,6 @@ static inline void eth_addr_dec(u8 *addr)
 }
 
 /**
- * ether_addr_greater - Compare two Ethernet addresses
- * @addr1: Pointer to a six-byte array containing the Ethernet address
- * @addr2: Pointer other six-byte array containing the Ethernet address
- *
- * Compare two Ethernet addresses, returns true addr1 is greater than addr2
- */
-static inline bool ether_addr_greater(const u8 *addr1, const u8 *addr2)
-{
-	u64 u1 = ether_addr_to_u64(addr1);
-	u64 u2 = ether_addr_to_u64(addr2);
-
-	return u1 > u2;
-}
-
-/**
  * is_etherdev_addr - Tell if given Ethernet address belongs to the device.
  * @dev: Pointer to a device structure
  * @addr: Pointer to a six-byte array containing the Ethernet address
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 9ded8c6d8176..83cc9863444b 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -60,6 +60,7 @@ enum ethtool_phys_id_state {
 enum {
 	ETH_RSS_HASH_TOP_BIT, /* Configurable RSS hash function - Toeplitz */
 	ETH_RSS_HASH_XOR_BIT, /* Configurable RSS hash function - Xor */
+	ETH_RSS_HASH_CRC32_BIT, /* Configurable RSS hash function - Crc32 */
 
 	/*
 	 * Add your fresh new hash function bits above and remember to update
@@ -73,6 +74,7 @@ enum {
 
 #define ETH_RSS_HASH_TOP	__ETH_RSS_HASH(TOP)
 #define ETH_RSS_HASH_XOR	__ETH_RSS_HASH(XOR)
+#define ETH_RSS_HASH_CRC32	__ETH_RSS_HASH(CRC32)
 
 #define ETH_RSS_HASH_UNKNOWN	0
 #define ETH_RSS_HASH_NO_CHANGE	0
diff --git a/include/linux/filter.h b/include/linux/filter.h
index fbf7b39e8103..511fe910bf1d 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -7,6 +7,7 @@
 #include <stdarg.h>
 
 #include <linux/atomic.h>
+#include <linux/refcount.h>
 #include <linux/compat.h>
 #include <linux/skbuff.h>
 #include <linux/linkage.h>
@@ -430,7 +431,7 @@ struct bpf_prog {
 };
 
 struct sk_filter {
-	atomic_t	refcnt;
+	refcount_t	refcnt;
 	struct rcu_head	rcu;
 	struct bpf_prog	*prog;
 };
@@ -693,6 +694,11 @@ static inline bool bpf_jit_is_ebpf(void)
 # endif
 }
 
+static inline bool ebpf_jit_enabled(void)
+{
+	return bpf_jit_enable && bpf_jit_is_ebpf();
+}
+
 static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp)
 {
 	return fp->jited && bpf_jit_is_ebpf();
@@ -753,6 +759,11 @@ void bpf_prog_kallsyms_del(struct bpf_prog *fp);
 
 #else /* CONFIG_BPF_JIT */
 
+static inline bool ebpf_jit_enabled(void)
+{
+	return false;
+}
+
 static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp)
 {
 	return false;
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 970771a5f739..0c170a3f0d8b 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1508,14 +1508,6 @@ static inline  void hv_signal_on_read(struct vmbus_channel *channel)
 	return;
 }
 
-static inline void
-init_cached_read_index(struct vmbus_channel *channel)
-{
-	struct hv_ring_buffer_info *rbi = &channel->inbound;
-
-	rbi->cached_read_index = rbi->ring_buffer->read_index;
-}
-
 /*
  * Mask off host interrupt callback notifications
  */
@@ -1549,76 +1541,48 @@ static inline u32 hv_end_read(struct hv_ring_buffer_info *rbi)
 /*
  * An API to support in-place processing of incoming VMBUS packets.
  */
-#define VMBUS_PKT_TRAILER	8
 
-static inline struct vmpacket_descriptor *
-get_next_pkt_raw(struct vmbus_channel *channel)
+/* Get data payload associated with descriptor */
+static inline void *hv_pkt_data(const struct vmpacket_descriptor *desc)
 {
-	struct hv_ring_buffer_info *ring_info = &channel->inbound;
-	u32 priv_read_loc = ring_info->priv_read_index;
-	void *ring_buffer = hv_get_ring_buffer(ring_info);
-	u32 dsize = ring_info->ring_datasize;
-	/*
-	 * delta is the difference between what is available to read and
-	 * what was already consumed in place. We commit read index after
-	 * the whole batch is processed.
-	 */
-	u32 delta = priv_read_loc >= ring_info->ring_buffer->read_index ?
-		priv_read_loc - ring_info->ring_buffer->read_index :
-		(dsize - ring_info->ring_buffer->read_index) + priv_read_loc;
-	u32 bytes_avail_toread = (hv_get_bytes_to_read(ring_info) - delta);
-
-	if (bytes_avail_toread < sizeof(struct vmpacket_descriptor))
-		return NULL;
-
-	return ring_buffer + priv_read_loc;
+	return (void *)((unsigned long)desc + (desc->offset8 << 3));
 }
 
-/*
- * A helper function to step through packets "in-place"
- * This API is to be called after each successful call
- * get_next_pkt_raw().
- */
-static inline void put_pkt_raw(struct vmbus_channel *channel,
-				struct vmpacket_descriptor *desc)
+/* Get data size associated with descriptor */
+static inline u32 hv_pkt_datalen(const struct vmpacket_descriptor *desc)
 {
-	struct hv_ring_buffer_info *ring_info = &channel->inbound;
-	u32 packetlen = desc->len8 << 3;
-	u32 dsize = ring_info->ring_datasize;
-
-	/*
-	 * Include the packet trailer.
-	 */
-	ring_info->priv_read_index += packetlen + VMBUS_PKT_TRAILER;
-	ring_info->priv_read_index %= dsize;
+	return (desc->len8 << 3) - (desc->offset8 << 3);
 }
 
+
+struct vmpacket_descriptor *
+hv_pkt_iter_first(struct vmbus_channel *channel);
+
+struct vmpacket_descriptor *
+__hv_pkt_iter_next(struct vmbus_channel *channel,
+		   const struct vmpacket_descriptor *pkt);
+
+void hv_pkt_iter_close(struct vmbus_channel *channel);
+
 /*
- * This call commits the read index and potentially signals the host.
- * Here is the pattern for using the "in-place" consumption APIs:
- *
- * init_cached_read_index();
- *
- * while (get_next_pkt_raw() {
- *	process the packet "in-place";
- *	put_pkt_raw();
- * }
- * if (packets processed in place)
- *	commit_rd_index();
+ * Get next packet descriptor from iterator
+ * If at end of list, return NULL and update host.
  */
-static inline void commit_rd_index(struct vmbus_channel *channel)
+static inline struct vmpacket_descriptor *
+hv_pkt_iter_next(struct vmbus_channel *channel,
+		 const struct vmpacket_descriptor *pkt)
 {
-	struct hv_ring_buffer_info *ring_info = &channel->inbound;
-	/*
-	 * Make sure all reads are done before we update the read index since
-	 * the writer may start writing to the read area once the read index
-	 * is updated.
-	 */
-	virt_rmb();
-	ring_info->ring_buffer->read_index = ring_info->priv_read_index;
+	struct vmpacket_descriptor *nxt;
+
+	nxt = __hv_pkt_iter_next(channel, pkt);
+	if (!nxt)
+		hv_pkt_iter_close(channel);
 
-	hv_signal_on_read(channel);
+	return nxt;
 }
 
+#define foreach_vmbus_pkt(pkt, channel) \
+	for (pkt = hv_pkt_iter_first(channel); pkt; \
+	    pkt = hv_pkt_iter_next(channel, pkt))
 
 #endif /* _HYPERV_H */
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index ee971f335a8b..a2e9d6ea1349 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -153,8 +153,8 @@ struct in_ifaddr {
 int register_inetaddr_notifier(struct notifier_block *nb);
 int unregister_inetaddr_notifier(struct notifier_block *nb);
 
-void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
-				 struct ipv4_devconf *devconf);
+void inet_netconf_notify_devconf(struct net *net, int event, int type,
+				 int ifindex, struct ipv4_devconf *devconf);
 
 struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref);
 static inline struct net_device *ip_dev_find(struct net *net, __be32 addr)
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 71be5b330d21..e1b442996f81 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -37,6 +37,7 @@ struct ipv6_devconf {
 	__s32		accept_ra_rtr_pref;
 	__s32		rtr_probe_interval;
 #ifdef CONFIG_IPV6_ROUTE_INFO
+	__s32		accept_ra_rt_info_min_plen;
 	__s32		accept_ra_rt_info_max_plen;
 #endif
 #endif
@@ -70,6 +71,7 @@ struct ipv6_devconf {
 #endif
 	__u32		enhanced_dad;
 	__u32		addr_gen_mode;
+	__s32		disable_policy;
 
 	struct ctl_table_header *sysctl_header;
 };
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 2fcff6b4503f..f50864626230 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -728,6 +728,7 @@ struct mlx5e_resources {
 	u32                        pdn;
 	struct mlx5_td             td;
 	struct mlx5_core_mkey      mkey;
+	struct mlx5_sq_bfreg       bfreg;
 };
 
 struct mlx5_core_dev {
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 949b24b6c479..ae91a4bda1a3 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -134,8 +134,13 @@ struct mlx5_flow_act {
 	u32 action;
 	u32 flow_tag;
 	u32 encap_id;
+	u32 modify_id;
 };
 
+#define MLX5_DECLARE_FLOW_ACT(name) \
+	struct mlx5_flow_act name = {MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\
+				     MLX5_FS_DEFAULT_FLOW_TAG, 0, 0}
+
 /* Single destination per rule.
  * Group ID is implied by the match criteria.
  */
@@ -156,5 +161,4 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging);
 void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter);
 void mlx5_fc_query_cached(struct mlx5_fc *counter,
 			  u64 *bytes, u64 *packets, u64 *lastuse);
-
 #endif
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 838242697541..56bc842b0620 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -227,6 +227,8 @@ enum {
 	MLX5_CMD_OP_MODIFY_FLOW_TABLE             = 0x93c,
 	MLX5_CMD_OP_ALLOC_ENCAP_HEADER            = 0x93d,
 	MLX5_CMD_OP_DEALLOC_ENCAP_HEADER          = 0x93e,
+	MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT   = 0x940,
+	MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT = 0x941,
 	MLX5_CMD_OP_MAX
 };
 
@@ -302,7 +304,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 
 	u8         reserved_at_20[0x2];
 	u8         log_max_ft_size[0x6];
-	u8         reserved_at_28[0x10];
+	u8         log_max_modify_header_context[0x8];
+	u8         max_modify_header_actions[0x8];
 	u8         max_ft_level[0x8];
 
 	u8         reserved_at_40[0x20];
@@ -2190,6 +2193,7 @@ enum {
 	MLX5_FLOW_CONTEXT_ACTION_COUNT     = 0x8,
 	MLX5_FLOW_CONTEXT_ACTION_ENCAP     = 0x10,
 	MLX5_FLOW_CONTEXT_ACTION_DECAP     = 0x20,
+	MLX5_FLOW_CONTEXT_ACTION_MOD_HDR   = 0x40,
 };
 
 struct mlx5_ifc_flow_context_bits {
@@ -2211,7 +2215,9 @@ struct mlx5_ifc_flow_context_bits {
 
 	u8         encap_id[0x20];
 
-	u8         reserved_at_e0[0x120];
+	u8         modify_header_id[0x20];
+
+	u8         reserved_at_100[0x100];
 
 	struct mlx5_ifc_fte_match_param_bits match_value;
 
@@ -4534,6 +4540,109 @@ struct mlx5_ifc_dealloc_encap_header_in_bits {
 	u8         reserved_60[0x20];
 };
 
+struct mlx5_ifc_set_action_in_bits {
+	u8         action_type[0x4];
+	u8         field[0xc];
+	u8         reserved_at_10[0x3];
+	u8         offset[0x5];
+	u8         reserved_at_18[0x3];
+	u8         length[0x5];
+
+	u8         data[0x20];
+};
+
+struct mlx5_ifc_add_action_in_bits {
+	u8         action_type[0x4];
+	u8         field[0xc];
+	u8         reserved_at_10[0x10];
+
+	u8         data[0x20];
+};
+
+union mlx5_ifc_set_action_in_add_action_in_auto_bits {
+	struct mlx5_ifc_set_action_in_bits set_action_in;
+	struct mlx5_ifc_add_action_in_bits add_action_in;
+	u8         reserved_at_0[0x40];
+};
+
+enum {
+	MLX5_ACTION_TYPE_SET   = 0x1,
+	MLX5_ACTION_TYPE_ADD   = 0x2,
+};
+
+enum {
+	MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16    = 0x1,
+	MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0     = 0x2,
+	MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE     = 0x3,
+	MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16    = 0x4,
+	MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0     = 0x5,
+	MLX5_ACTION_IN_FIELD_OUT_IP_DSCP       = 0x6,
+	MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS     = 0x7,
+	MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT     = 0x8,
+	MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT     = 0x9,
+	MLX5_ACTION_IN_FIELD_OUT_IP_TTL        = 0xa,
+	MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT     = 0xb,
+	MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT     = 0xc,
+	MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96  = 0xd,
+	MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64   = 0xe,
+	MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32   = 0xf,
+	MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0    = 0x10,
+	MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96  = 0x11,
+	MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64   = 0x12,
+	MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32   = 0x13,
+	MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0    = 0x14,
+	MLX5_ACTION_IN_FIELD_OUT_SIPV4         = 0x15,
+	MLX5_ACTION_IN_FIELD_OUT_DIPV4         = 0x16,
+};
+
+struct mlx5_ifc_alloc_modify_header_context_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         modify_header_id[0x20];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_alloc_modify_header_context_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x20];
+
+	u8         table_type[0x8];
+	u8         reserved_at_68[0x10];
+	u8         num_of_actions[0x8];
+
+	union mlx5_ifc_set_action_in_add_action_in_auto_bits actions[0];
+};
+
+struct mlx5_ifc_dealloc_modify_header_context_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_dealloc_modify_header_context_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         modify_header_id[0x20];
+
+	u8         reserved_at_60[0x20];
+};
+
 struct mlx5_ifc_query_dct_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 97456b2539e4..cc07c3be2705 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -41,7 +41,6 @@
 
 #include <linux/ethtool.h>
 #include <net/net_namespace.h>
-#include <net/dsa.h>
 #ifdef CONFIG_DCB
 #include <net/dcbnl.h>
 #endif
@@ -57,6 +56,8 @@
 struct netpoll_info;
 struct device;
 struct phy_device;
+struct dsa_switch_tree;
+
 /* 802.11 specific */
 struct wireless_dev;
 /* 802.15.4 specific */
@@ -786,11 +787,11 @@ struct tc_cls_u32_offload;
 struct tc_to_netdev {
 	unsigned int type;
 	union {
-		u8 tc;
 		struct tc_cls_u32_offload *cls_u32;
 		struct tc_cls_flower_offload *cls_flower;
 		struct tc_cls_matchall_offload *cls_mall;
 		struct tc_cls_bpf_offload *cls_bpf;
+		struct tc_mqprio_qopt *mqprio;
 	};
 	bool egress_dev;
 };
@@ -2004,15 +2005,6 @@ void dev_net_set(struct net_device *dev, struct net *net)
 	write_pnet(&dev->nd_net, net);
 }
 
-static inline bool netdev_uses_dsa(struct net_device *dev)
-{
-#if IS_ENABLED(CONFIG_NET_DSA)
-	if (dev->dsa_ptr != NULL)
-		return dsa_uses_tagged_protocol(dev->dsa_ptr);
-#endif
-	return false;
-}
-
 /**
  *	netdev_priv - access network device private data
  *	@dev: network device
diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h
index a58cca8bcb29..ba35ba520487 100644
--- a/include/linux/of_mdio.h
+++ b/include/linux/of_mdio.h
@@ -12,7 +12,7 @@
 #include <linux/phy.h>
 #include <linux/of.h>
 
-#ifdef CONFIG_OF
+#if IS_ENABLED(CONFIG_OF_MDIO)
 extern int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np);
 extern struct phy_device *of_phy_find_device(struct device_node *phy_np);
 extern struct phy_device *of_phy_connect(struct net_device *dev,
@@ -32,7 +32,7 @@ extern int of_phy_register_fixed_link(struct device_node *np);
 extern void of_phy_deregister_fixed_link(struct device_node *np);
 extern bool of_phy_is_fixed_link(struct device_node *np);
 
-#else /* CONFIG_OF */
+#else /* CONFIG_OF_MDIO */
 static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 {
 	/*
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 43a774873aa9..624cecf69c28 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -587,23 +587,29 @@ struct phy_driver {
 	 */
 	void (*link_change_notify)(struct phy_device *dev);
 
-	/* A function provided by a phy specific driver to override the
-	 * the PHY driver framework support for reading a MMD register
-	 * from the PHY. If not supported, return -1. This function is
-	 * optional for PHY specific drivers, if not provided then the
-	 * default MMD read function is used by the PHY framework.
+	/*
+	 * Phy specific driver override for reading a MMD register.
+	 * This function is optional for PHY specific drivers.  When
+	 * not provided, the default MMD read function will be used
+	 * by phy_read_mmd(), which will use either a direct read for
+	 * Clause 45 PHYs or an indirect read for Clause 22 PHYs.
+	 *  devnum is the MMD device number within the PHY device,
+	 *  regnum is the register within the selected MMD device.
 	 */
-	int (*read_mmd_indirect)(struct phy_device *dev, int ptrad,
-				 int devnum, int regnum);
-
-	/* A function provided by a phy specific driver to override the
-	 * the PHY driver framework support for writing a MMD register
-	 * from the PHY. This function is optional for PHY specific drivers,
-	 * if not provided then the default MMD read function is used by
-	 * the PHY framework.
+	int (*read_mmd)(struct phy_device *dev, int devnum, u16 regnum);
+
+	/*
+	 * Phy specific driver override for writing a MMD register.
+	 * This function is optional for PHY specific drivers.  When
+	 * not provided, the default MMD write function will be used
+	 * by phy_write_mmd(), which will use either a direct write for
+	 * Clause 45 PHYs, or an indirect write for Clause 22 PHYs.
+	 *  devnum is the MMD device number within the PHY device,
+	 *  regnum is the register within the selected MMD device.
+	 *  val is the value to be written.
 	 */
-	void (*write_mmd_indirect)(struct phy_device *dev, int ptrad,
-				   int devnum, int regnum, u32 val);
+	int (*write_mmd)(struct phy_device *dev, int devnum, u16 regnum,
+			 u16 val);
 
 	/* Get the size and type of the eeprom contained within a plug-in
 	 * module */
@@ -651,25 +657,7 @@ struct phy_fixup {
  *
  * Same rules as for phy_read();
  */
-static inline int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum)
-{
-	if (!phydev->is_c45)
-		return -EOPNOTSUPP;
-
-	return mdiobus_read(phydev->mdio.bus, phydev->mdio.addr,
-			    MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff));
-}
-
-/**
- * phy_read_mmd_indirect - reads data from the MMD registers
- * @phydev: The PHY device bus
- * @prtad: MMD Address
- * @addr: PHY address on the MII bus
- *
- * Description: it reads data from the MMD registers (clause 22 to access to
- * clause 45) of the specified phy address.
- */
-int phy_read_mmd_indirect(struct phy_device *phydev, int prtad, int devad);
+int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
 
 /**
  * phy_read - Convenience function for reading a given PHY register
@@ -752,35 +740,29 @@ static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev)
  *
  * Same rules as for phy_write();
  */
-static inline int phy_write_mmd(struct phy_device *phydev, int devad,
-				u32 regnum, u16 val)
-{
-	if (!phydev->is_c45)
-		return -EOPNOTSUPP;
-
-	regnum = MII_ADDR_C45 | ((devad & 0x1f) << 16) | (regnum & 0xffff);
-
-	return mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, regnum, val);
-}
-
-/**
- * phy_write_mmd_indirect - writes data to the MMD registers
- * @phydev: The PHY device
- * @prtad: MMD Address
- * @devad: MMD DEVAD
- * @data: data to write in the MMD register
- *
- * Description: Write data from the MMD registers of the specified
- * phy address.
- */
-void phy_write_mmd_indirect(struct phy_device *phydev, int prtad,
-			    int devad, u32 data);
+int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val);
 
 struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id,
 				     bool is_c45,
 				     struct phy_c45_device_ids *c45_ids);
+#if IS_ENABLED(CONFIG_PHYLIB)
 struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45);
 int phy_device_register(struct phy_device *phy);
+void phy_device_free(struct phy_device *phydev);
+#else
+static inline
+struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45)
+{
+	return NULL;
+}
+
+static inline int phy_device_register(struct phy_device *phy)
+{
+	return 0;
+}
+
+static inline void phy_device_free(struct phy_device *phydev) { }
+#endif /* CONFIG_PHYLIB */
 void phy_device_remove(struct phy_device *phydev);
 int phy_init_hw(struct phy_device *phydev);
 int phy_suspend(struct phy_device *phydev);
@@ -861,7 +843,6 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev,
 int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd);
 int phy_start_interrupts(struct phy_device *phydev);
 void phy_print_status(struct phy_device *phydev);
-void phy_device_free(struct phy_device *phydev);
 int phy_set_max_speed(struct phy_device *phydev, u32 max_speed);
 
 int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask,
@@ -888,8 +869,10 @@ int phy_ethtool_set_link_ksettings(struct net_device *ndev,
 				   const struct ethtool_link_ksettings *cmd);
 int phy_ethtool_nway_reset(struct net_device *ndev);
 
+#if IS_ENABLED(CONFIG_PHYLIB)
 int __init mdio_bus_init(void);
 void mdio_bus_exit(void);
+#endif
 
 extern struct bus_type mdio_bus_type;
 
@@ -900,7 +883,7 @@ struct mdio_board_info {
 	const void	*platform_data;
 };
 
-#if IS_ENABLED(CONFIG_PHYLIB)
+#if IS_ENABLED(CONFIG_MDIO_DEVICE)
 int mdiobus_register_board_info(const struct mdio_board_info *info,
 				unsigned int n);
 #else
diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h
index 52966b9bfde3..fbab6e0514f0 100644
--- a/include/linux/qed/common_hsi.h
+++ b/include/linux/qed/common_hsi.h
@@ -100,8 +100,8 @@
 #define MAX_NUM_LL2_TX_STATS_COUNTERS	32
 
 #define FW_MAJOR_VERSION	8
-#define FW_MINOR_VERSION	10
-#define FW_REVISION_VERSION	10
+#define FW_MINOR_VERSION	15
+#define FW_REVISION_VERSION	3
 #define FW_ENGINEERING_VERSION	0
 
 /***********************/
@@ -187,6 +187,9 @@
 
 /* DEMS */
 #define DQ_DEMS_LEGACY			0
+#define DQ_DEMS_TOE_MORE_TO_SEND	3
+#define DQ_DEMS_TOE_LOCAL_ADV_WND	4
+#define DQ_DEMS_ROCE_CQ_CONS		7
 
 /* XCM agg val selection */
 #define DQ_XCM_AGG_VAL_SEL_WORD2  0
@@ -214,6 +217,9 @@
 #define DQ_XCM_ISCSI_MORE_TO_SEND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG3
 #define DQ_XCM_ISCSI_EXP_STAT_SN_CMD	DQ_XCM_AGG_VAL_SEL_REG6
 #define DQ_XCM_ROCE_SQ_PROD_CMD	DQ_XCM_AGG_VAL_SEL_WORD4
+#define DQ_XCM_TOE_TX_BD_PROD_CMD	DQ_XCM_AGG_VAL_SEL_WORD4
+#define DQ_XCM_TOE_MORE_TO_SEND_SEQ_CMD	DQ_XCM_AGG_VAL_SEL_REG3
+#define DQ_XCM_TOE_LOCAL_ADV_WND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG4
 
 /* UCM agg val selection (HW) */
 #define	DQ_UCM_AGG_VAL_SEL_WORD0	0
@@ -269,6 +275,8 @@
 #define DQ_XCM_ISCSI_DQ_FLUSH_CMD	BIT(DQ_XCM_AGG_FLG_SHIFT_CF19)
 #define DQ_XCM_ISCSI_SLOW_PATH_CMD	BIT(DQ_XCM_AGG_FLG_SHIFT_CF22)
 #define DQ_XCM_ISCSI_PROC_ONLY_CLEANUP_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF23)
+#define DQ_XCM_TOE_DQ_FLUSH_CMD		BIT(DQ_XCM_AGG_FLG_SHIFT_CF19)
+#define DQ_XCM_TOE_SLOW_PATH_CMD	BIT(DQ_XCM_AGG_FLG_SHIFT_CF22)
 
 /* UCM agg counter flag selection (HW) */
 #define	DQ_UCM_AGG_FLG_SHIFT_CF0	0
@@ -285,6 +293,9 @@
 #define DQ_UCM_ETH_PMD_RX_ARM_CMD	BIT(DQ_UCM_AGG_FLG_SHIFT_CF5)
 #define DQ_UCM_ROCE_CQ_ARM_SE_CF_CMD	BIT(DQ_UCM_AGG_FLG_SHIFT_CF4)
 #define DQ_UCM_ROCE_CQ_ARM_CF_CMD	BIT(DQ_UCM_AGG_FLG_SHIFT_CF5)
+#define DQ_UCM_TOE_TIMER_STOP_ALL_CMD	BIT(DQ_UCM_AGG_FLG_SHIFT_CF3)
+#define DQ_UCM_TOE_SLOW_PATH_CF_CMD	BIT(DQ_UCM_AGG_FLG_SHIFT_CF4)
+#define DQ_UCM_TOE_DQ_CF_CMD		BIT(DQ_UCM_AGG_FLG_SHIFT_CF5)
 
 /* TCM agg counter flag selection (HW) */
 #define DQ_TCM_AGG_FLG_SHIFT_CF0	0
@@ -301,6 +312,9 @@
 #define DQ_TCM_FCOE_TIMER_STOP_ALL_CMD      BIT(DQ_TCM_AGG_FLG_SHIFT_CF3)
 #define DQ_TCM_ISCSI_FLUSH_Q0_CMD	BIT(DQ_TCM_AGG_FLG_SHIFT_CF1)
 #define DQ_TCM_ISCSI_TIMER_STOP_ALL_CMD	BIT(DQ_TCM_AGG_FLG_SHIFT_CF3)
+#define DQ_TCM_TOE_FLUSH_Q0_CMD		BIT(DQ_TCM_AGG_FLG_SHIFT_CF1)
+#define DQ_TCM_TOE_TIMER_STOP_ALL_CMD	BIT(DQ_TCM_AGG_FLG_SHIFT_CF3)
+#define DQ_TCM_IWARP_POST_RQ_CF_CMD	BIT(DQ_TCM_AGG_FLG_SHIFT_CF1)
 
 /* PWM address mapping */
 #define DQ_PWM_OFFSET_DPM_BASE	0x0
@@ -689,6 +703,16 @@ struct iscsi_eqe_data {
 #define ISCSI_EQE_DATA_RESERVED0_SHIFT			7
 };
 
+struct rdma_eqe_destroy_qp {
+	__le32 cid;
+	u8 reserved[4];
+};
+
+union rdma_eqe_data {
+	struct regpair async_handle;
+	struct rdma_eqe_destroy_qp rdma_destroy_qp_data;
+};
+
 struct malicious_vf_eqe_data {
 	u8 vf_id;
 	u8 err_id;
@@ -705,9 +729,9 @@ union event_ring_data {
 	u8 bytes[8];
 	struct vf_pf_channel_eqe_data vf_pf_channel;
 	struct iscsi_eqe_data iscsi_info;
+	union rdma_eqe_data rdma_data;
 	struct malicious_vf_eqe_data malicious_vf;
 	struct initial_cleanup_eqe_data vf_init_cleanup;
-	struct regpair roce_handle;
 };
 
 /* Event Ring Entry */
diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h
index 4b402fb0eaad..34d93eb5bfba 100644
--- a/include/linux/qed/eth_common.h
+++ b/include/linux/qed/eth_common.h
@@ -49,6 +49,9 @@
 #define ETH_RX_CQE_PAGE_SIZE_BYTES                      4096
 #define ETH_RX_NUM_NEXT_PAGE_BDS                        2
 
+#define ETH_MAX_TUNN_LSO_INNER_IPV4_OFFSET          253
+#define ETH_MAX_TUNN_LSO_INNER_IPV6_OFFSET          251
+
 #define ETH_TX_MIN_BDS_PER_NON_LSO_PKT                          1
 #define ETH_TX_MAX_BDS_PER_NON_LSO_PACKET                       18
 #define ETH_TX_MAX_BDS_PER_LSO_PACKET	255
diff --git a/include/linux/qed/fcoe_common.h b/include/linux/qed/fcoe_common.h
index 2e417a45c5f7..947a635d04bb 100644
--- a/include/linux/qed/fcoe_common.h
+++ b/include/linux/qed/fcoe_common.h
@@ -109,13 +109,6 @@ struct fcoe_conn_terminate_ramrod_data {
 	struct regpair terminate_params_addr;
 };
 
-struct fcoe_fast_sgl_ctx {
-	struct regpair sgl_start_addr;
-	__le32 sgl_byte_offset;
-	__le16 task_reuse_cnt;
-	__le16 init_offset_in_first_sge;
-};
-
 struct fcoe_slow_sgl_ctx {
 	struct regpair base_sgl_addr;
 	__le16 curr_sge_off;
@@ -124,23 +117,16 @@ struct fcoe_slow_sgl_ctx {
 	__le16 reserved;
 };
 
-struct fcoe_sge {
-	struct regpair sge_addr;
-	__le16 size;
-	__le16 reserved0;
-	u8 reserved1[3];
-	u8 is_valid_sge;
-};
-
-union fcoe_data_desc_ctx {
-	struct fcoe_fast_sgl_ctx fast;
-	struct fcoe_slow_sgl_ctx slow;
-	struct fcoe_sge single_sge;
-};
-
 union fcoe_dix_desc_ctx {
 	struct fcoe_slow_sgl_ctx dix_sgl;
-	struct fcoe_sge cached_dix_sge;
+	struct scsi_sge cached_dix_sge;
+};
+
+struct fcoe_fast_sgl_ctx {
+	struct regpair sgl_start_addr;
+	__le32 sgl_byte_offset;
+	__le16 task_reuse_cnt;
+	__le16 init_offset_in_first_sge;
 };
 
 struct fcoe_fcp_cmd_payload {
@@ -172,57 +158,6 @@ enum fcoe_mode_type {
 	MAX_FCOE_MODE_TYPE
 };
 
-struct fcoe_mstorm_fcoe_task_st_ctx_fp {
-	__le16 flags;
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_RSRV0_MASK                 0x7FFF
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_RSRV0_SHIFT                0
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_MP_INCLUDE_FC_HEADER_MASK  0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_MP_INCLUDE_FC_HEADER_SHIFT 15
-	__le16 difDataResidue;
-	__le16 parent_id;
-	__le16 single_sge_saved_offset;
-	__le32 data_2_trns_rem;
-	__le32 offset_in_io;
-	union fcoe_dix_desc_ctx dix_desc;
-	union fcoe_data_desc_ctx data_desc;
-};
-
-struct fcoe_mstorm_fcoe_task_st_ctx_non_fp {
-	__le16 flags;
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HOST_INTERFACE_MASK            0x3
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HOST_INTERFACE_SHIFT           0
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_TO_PEER_MASK               0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_TO_PEER_SHIFT              2
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_APP_TAG_MASK      0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_APP_TAG_SHIFT     3
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_INTERVAL_SIZE_LOG_MASK         0xF
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_INTERVAL_SIZE_LOG_SHIFT        4
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_BLOCK_SIZE_MASK            0x3
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_BLOCK_SIZE_SHIFT           8
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RESERVED_MASK                  0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RESERVED_SHIFT                 10
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HAS_FIRST_PACKET_ARRIVED_MASK  0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HAS_FIRST_PACKET_ARRIVED_SHIFT 11
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_REF_TAG_MASK      0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_REF_TAG_SHIFT     12
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_CACHED_SGE_FLG_MASK        0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_CACHED_SGE_FLG_SHIFT       13
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_OFFSET_IN_IO_VALID_MASK        0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_OFFSET_IN_IO_VALID_SHIFT       14
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_SUPPORTED_MASK             0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_SUPPORTED_SHIFT            15
-	u8 tx_rx_sgl_mode;
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_TX_SGL_MODE_MASK               0x7
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_TX_SGL_MODE_SHIFT              0
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE_MASK               0x7
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE_SHIFT              3
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RSRV1_MASK                     0x3
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RSRV1_SHIFT                    6
-	u8 rsrv2;
-	__le32 num_prm_zero_read;
-	struct regpair rsp_buf_addr;
-};
-
 struct fcoe_rx_stat {
 	struct regpair fcoe_rx_byte_cnt;
 	struct regpair fcoe_rx_data_pkt_cnt;
@@ -236,16 +171,6 @@ struct fcoe_rx_stat {
 	__le32 rsrv;
 };
 
-enum fcoe_sgl_mode {
-	FCOE_SLOW_SGL,
-	FCOE_SINGLE_FAST_SGE,
-	FCOE_2_FAST_SGE,
-	FCOE_3_FAST_SGE,
-	FCOE_4_FAST_SGE,
-	FCOE_MUL_FAST_SGES,
-	MAX_FCOE_SGL_MODE
-};
-
 struct fcoe_stat_ramrod_data {
 	struct regpair stat_params_addr;
 };
@@ -328,22 +253,24 @@ union fcoe_tx_info_union_ctx {
 struct ystorm_fcoe_task_st_ctx {
 	u8 task_type;
 	u8 sgl_mode;
-#define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK  0x7
+#define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK  0x1
 #define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_SHIFT 0
-#define YSTORM_FCOE_TASK_ST_CTX_RSRV_MASK         0x1F
-#define YSTORM_FCOE_TASK_ST_CTX_RSRV_SHIFT        3
+#define YSTORM_FCOE_TASK_ST_CTX_RSRV_MASK         0x7F
+#define YSTORM_FCOE_TASK_ST_CTX_RSRV_SHIFT        1
 	u8 cached_dix_sge;
 	u8 expect_first_xfer;
 	__le32 num_pbf_zero_write;
 	union protection_info_union_ctx protection_info_union;
 	__le32 data_2_trns_rem;
+	struct scsi_sgl_params sgl_params;
+	u8 reserved1[12];
 	union fcoe_tx_info_union_ctx tx_info_union;
 	union fcoe_dix_desc_ctx dix_desc;
-	union fcoe_data_desc_ctx data_desc;
+	struct scsi_cached_sges data_desc;
 	__le16 ox_id;
 	__le16 rx_id;
 	__le32 task_rety_identifier;
-	__le32 reserved1[2];
+	u8 reserved2[8];
 };
 
 struct ystorm_fcoe_task_ag_ctx {
@@ -484,22 +411,22 @@ struct tstorm_fcoe_task_ag_ctx {
 struct fcoe_tstorm_fcoe_task_st_ctx_read_write {
 	union fcoe_cleanup_addr_exp_ro_union cleanup_addr_exp_ro_union;
 	__le16 flags;
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_MASK       0x7
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_MASK       0x1
 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_SHIFT      0
 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_MASK   0x1
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_SHIFT  3
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_SHIFT  1
 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_MASK        0x1
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_SHIFT       4
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_SHIFT       2
 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_MASK       0x1
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_SHIFT      5
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_SHIFT      3
 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_MASK  0x1
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_SHIFT 6
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_SHIFT 4
 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_MASK   0x1
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_SHIFT  7
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_SHIFT  5
 #define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_MASK        0x3
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_SHIFT       8
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_MASK             0x3F
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_SHIFT            10
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_SHIFT       6
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_MASK             0xFF
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_SHIFT            8
 	__le16 seq_cnt;
 	u8 seq_id;
 	u8 ooo_rx_seq_id;
@@ -582,8 +509,34 @@ struct mstorm_fcoe_task_ag_ctx {
 };
 
 struct mstorm_fcoe_task_st_ctx {
-	struct fcoe_mstorm_fcoe_task_st_ctx_non_fp non_fp;
-	struct fcoe_mstorm_fcoe_task_st_ctx_fp fp;
+	struct regpair rsp_buf_addr;
+	__le32 rsrv[2];
+	struct scsi_sgl_params sgl_params;
+	__le32 data_2_trns_rem;
+	__le32 data_buffer_offset;
+	__le16 parent_id;
+	__le16 flags;
+#define MSTORM_FCOE_TASK_ST_CTX_INTERVAL_SIZE_LOG_MASK     0xF
+#define MSTORM_FCOE_TASK_ST_CTX_INTERVAL_SIZE_LOG_SHIFT    0
+#define MSTORM_FCOE_TASK_ST_CTX_HOST_INTERFACE_MASK        0x3
+#define MSTORM_FCOE_TASK_ST_CTX_HOST_INTERFACE_SHIFT       4
+#define MSTORM_FCOE_TASK_ST_CTX_DIF_TO_PEER_MASK           0x1
+#define MSTORM_FCOE_TASK_ST_CTX_DIF_TO_PEER_SHIFT          6
+#define MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER_MASK  0x1
+#define MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER_SHIFT 7
+#define MSTORM_FCOE_TASK_ST_CTX_DIX_BLOCK_SIZE_MASK        0x3
+#define MSTORM_FCOE_TASK_ST_CTX_DIX_BLOCK_SIZE_SHIFT       8
+#define MSTORM_FCOE_TASK_ST_CTX_VALIDATE_DIX_REF_TAG_MASK  0x1
+#define MSTORM_FCOE_TASK_ST_CTX_VALIDATE_DIX_REF_TAG_SHIFT 10
+#define MSTORM_FCOE_TASK_ST_CTX_DIX_CACHED_SGE_FLG_MASK    0x1
+#define MSTORM_FCOE_TASK_ST_CTX_DIX_CACHED_SGE_FLG_SHIFT   11
+#define MSTORM_FCOE_TASK_ST_CTX_DIF_SUPPORTED_MASK         0x1
+#define MSTORM_FCOE_TASK_ST_CTX_DIF_SUPPORTED_SHIFT        12
+#define MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK           0x1
+#define MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_SHIFT          13
+#define MSTORM_FCOE_TASK_ST_CTX_RESERVED_MASK              0x3
+#define MSTORM_FCOE_TASK_ST_CTX_RESERVED_SHIFT             14
+	struct scsi_cached_sges data_desc;
 };
 
 struct ustorm_fcoe_task_ag_ctx {
@@ -646,6 +599,7 @@ struct ustorm_fcoe_task_ag_ctx {
 
 struct fcoe_task_context {
 	struct ystorm_fcoe_task_st_ctx ystorm_st_context;
+	struct regpair ystorm_st_padding[2];
 	struct tdif_task_context tdif_context;
 	struct ystorm_fcoe_task_ag_ctx ystorm_ag_context;
 	struct tstorm_fcoe_task_ag_ctx tstorm_ag_context;
@@ -668,20 +622,20 @@ struct fcoe_tx_stat {
 struct fcoe_wqe {
 	__le16 task_id;
 	__le16 flags;
-#define FCOE_WQE_REQ_TYPE_MASK        0xF
-#define FCOE_WQE_REQ_TYPE_SHIFT       0
-#define FCOE_WQE_SGL_MODE_MASK        0x7
-#define FCOE_WQE_SGL_MODE_SHIFT       4
-#define FCOE_WQE_CONTINUATION_MASK    0x1
-#define FCOE_WQE_CONTINUATION_SHIFT   7
-#define FCOE_WQE_INVALIDATE_PTU_MASK  0x1
-#define FCOE_WQE_INVALIDATE_PTU_SHIFT 8
-#define FCOE_WQE_SUPER_IO_MASK        0x1
-#define FCOE_WQE_SUPER_IO_SHIFT       9
-#define FCOE_WQE_SEND_AUTO_RSP_MASK   0x1
-#define FCOE_WQE_SEND_AUTO_RSP_SHIFT  10
-#define FCOE_WQE_RESERVED0_MASK       0x1F
-#define FCOE_WQE_RESERVED0_SHIFT      11
+#define FCOE_WQE_REQ_TYPE_MASK       0xF
+#define FCOE_WQE_REQ_TYPE_SHIFT      0
+#define FCOE_WQE_SGL_MODE_MASK       0x1
+#define FCOE_WQE_SGL_MODE_SHIFT      4
+#define FCOE_WQE_CONTINUATION_MASK   0x1
+#define FCOE_WQE_CONTINUATION_SHIFT  5
+#define FCOE_WQE_SEND_AUTO_RSP_MASK  0x1
+#define FCOE_WQE_SEND_AUTO_RSP_SHIFT 6
+#define FCOE_WQE_RESERVED_MASK       0x1
+#define FCOE_WQE_RESERVED_SHIFT      7
+#define FCOE_WQE_NUM_SGES_MASK       0xF
+#define FCOE_WQE_NUM_SGES_SHIFT      8
+#define FCOE_WQE_RESERVED1_MASK      0xF
+#define FCOE_WQE_RESERVED1_SHIFT     12
 	union fcoe_additional_info_union additional_info_union;
 };
 
diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h
index 4c5747babcf6..69949f8e354b 100644
--- a/include/linux/qed/iscsi_common.h
+++ b/include/linux/qed/iscsi_common.h
@@ -39,17 +39,9 @@
 /* iSCSI HSI constants */
 #define ISCSI_DEFAULT_MTU       (1500)
 
-/* Current iSCSI HSI version number composed of two fields (16 bit) */
-#define ISCSI_HSI_MAJOR_VERSION (0)
-#define ISCSI_HSI_MINOR_VERSION (0)
-
 /* KWQ (kernel work queue) layer codes */
 #define ISCSI_SLOW_PATH_LAYER_CODE   (6)
 
-/* CQE completion status */
-#define ISCSI_EQE_COMPLETION_SUCCESS (0x0)
-#define ISCSI_EQE_RST_CONN_RCVD (0x1)
-
 /* iSCSI parameter defaults */
 #define ISCSI_DEFAULT_HEADER_DIGEST         (0)
 #define ISCSI_DEFAULT_DATA_DIGEST           (0)
@@ -68,6 +60,10 @@
 #define ISCSI_MIN_VAL_MAX_OUTSTANDING_R2T   (1)
 #define ISCSI_MAX_VAL_MAX_OUTSTANDING_R2T   (0xff)
 
+#define ISCSI_AHS_CNTL_SIZE 4
+
+#define ISCSI_WQE_NUM_SGES_SLOWIO           (0xf)
+
 /* iSCSI reserved params */
 #define ISCSI_ITT_ALL_ONES	(0xffffffff)
 #define ISCSI_TTT_ALL_ONES	(0xffffffff)
@@ -173,19 +169,6 @@ struct iscsi_async_msg_hdr {
 	__le32 reserved7;
 };
 
-struct iscsi_sge {
-	struct regpair sge_addr;
-	__le16 sge_len;
-	__le16 reserved0;
-	__le32 reserved1;
-};
-
-struct iscsi_cached_sge_ctx {
-	struct iscsi_sge sge;
-	struct regpair reserved;
-	__le32 dsgl_curr_offset[2];
-};
-
 struct iscsi_cmd_hdr {
 	__le16 reserved1;
 	u8 flags_attr;
@@ -229,8 +212,13 @@ struct iscsi_common_hdr {
 #define ISCSI_COMMON_HDR_DATA_SEG_LEN_SHIFT  0
 #define ISCSI_COMMON_HDR_TOTAL_AHS_LEN_MASK  0xFF
 #define ISCSI_COMMON_HDR_TOTAL_AHS_LEN_SHIFT 24
-	__le32 lun_reserved[4];
-	__le32 data[6];
+	struct regpair lun_reserved;
+	__le32 itt;
+	__le32 ttt;
+	__le32 cmdstat_sn;
+	__le32 exp_statcmd_sn;
+	__le32 max_cmd_sn;
+	__le32 data[3];
 };
 
 struct iscsi_conn_offload_params {
@@ -246,8 +234,10 @@ struct iscsi_conn_offload_params {
 #define ISCSI_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_SHIFT 0
 #define ISCSI_CONN_OFFLOAD_PARAMS_TARGET_MODE_MASK     0x1
 #define ISCSI_CONN_OFFLOAD_PARAMS_TARGET_MODE_SHIFT    1
-#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_MASK       0x3F
-#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT      2
+#define ISCSI_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_MASK	0x1
+#define ISCSI_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_SHIFT	2
+#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_MASK	0x1F
+#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT	3
 	u8 pbl_page_size_log;
 	u8 pbe_page_size_log;
 	u8 default_cq;
@@ -278,8 +268,12 @@ struct iscsi_conn_update_ramrod_params {
 #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_INITIAL_R2T_SHIFT    2
 #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA_MASK  0x1
 #define ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA_SHIFT 3
-#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK       0xF
-#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_SHIFT      4
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_BLOCK_SIZE_MASK  0x1
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_BLOCK_SIZE_SHIFT 4
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_ON_HOST_EN_MASK  0x1
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_ON_HOST_EN_SHIFT 5
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK       0x3
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_SHIFT      6
 	u8 reserved0[3];
 	__le32 max_seq_size;
 	__le32 max_send_pdu_length;
@@ -312,7 +306,7 @@ struct iscsi_ext_cdb_cmd_hdr {
 	__le32 expected_transfer_length;
 	__le32 cmd_sn;
 	__le32 exp_stat_sn;
-	struct iscsi_sge cdb_sge;
+	struct scsi_sge cdb_sge;
 };
 
 struct iscsi_login_req_hdr {
@@ -519,8 +513,8 @@ struct iscsi_logout_response_hdr {
 	__le32 exp_cmd_sn;
 	__le32 max_cmd_sn;
 	__le32 reserved4;
-	__le16 time2retain;
-	__le16 time2wait;
+	__le16 time_2_retain;
+	__le16 time_2_wait;
 	__le32 reserved5[1];
 };
 
@@ -602,7 +596,7 @@ struct iscsi_tmf_response_hdr {
 #define ISCSI_TMF_RESPONSE_HDR_TOTAL_AHS_LEN_SHIFT 24
 	struct regpair reserved0;
 	__le32 itt;
-	__le32 rtt;
+	__le32 reserved1;
 	__le32 stat_sn;
 	__le32 exp_cmd_sn;
 	__le32 max_cmd_sn;
@@ -641,7 +635,7 @@ struct iscsi_reject_hdr {
 #define ISCSI_REJECT_HDR_TOTAL_AHS_LEN_MASK  0xFF
 #define ISCSI_REJECT_HDR_TOTAL_AHS_LEN_SHIFT 24
 	struct regpair reserved0;
-	__le32 reserved1;
+	__le32 all_ones;
 	__le32 reserved2;
 	__le32 stat_sn;
 	__le32 exp_cmd_sn;
@@ -688,7 +682,9 @@ struct iscsi_cqe_solicited {
 	__le16 itid;
 	u8 task_type;
 	u8 fw_dbg_field;
-	__le32 reserved1[2];
+	u8 caused_conn_err;
+	u8 reserved0[3];
+	__le32 reserved1[1];
 	union iscsi_task_hdr iscsi_hdr;
 };
 
@@ -727,35 +723,6 @@ enum iscsi_cqe_unsolicited_type {
 	MAX_ISCSI_CQE_UNSOLICITED_TYPE
 };
 
-struct iscsi_virt_sgl_ctx {
-	struct regpair sgl_base;
-	struct regpair dsgl_base;
-	__le32 sgl_initial_offset;
-	__le32 dsgl_initial_offset;
-	__le32 dsgl_curr_offset[2];
-};
-
-struct iscsi_sgl_var_params {
-	u8 sgl_ptr;
-	u8 dsgl_ptr;
-	__le16 sge_offset;
-	__le16 dsge_offset;
-};
-
-struct iscsi_phys_sgl_ctx {
-	struct regpair sgl_base;
-	struct regpair dsgl_base;
-	u8 sgl_size;
-	u8 dsgl_size;
-	__le16 reserved;
-	struct iscsi_sgl_var_params var_params[2];
-};
-
-union iscsi_data_desc_ctx {
-	struct iscsi_virt_sgl_ctx virt_sgl;
-	struct iscsi_phys_sgl_ctx phys_sgl;
-	struct iscsi_cached_sge_ctx cached_sge;
-};
 
 struct iscsi_debug_modes {
 	u8 flags;
@@ -771,8 +738,10 @@ struct iscsi_debug_modes {
 #define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_REJECT_OR_ASYNC_SHIFT 4
 #define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_NOP_MASK              0x1
 #define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_NOP_SHIFT             5
-#define ISCSI_DEBUG_MODES_RESERVED0_MASK                       0x3
-#define ISCSI_DEBUG_MODES_RESERVED0_SHIFT                      6
+#define ISCSI_DEBUG_MODES_ASSERT_IF_DATA_DIGEST_ERROR_MASK     0x1
+#define ISCSI_DEBUG_MODES_ASSERT_IF_DATA_DIGEST_ERROR_SHIFT    6
+#define ISCSI_DEBUG_MODES_ASSERT_IF_DIF_ERROR_MASK             0x1
+#define ISCSI_DEBUG_MODES_ASSERT_IF_DIF_ERROR_SHIFT            7
 };
 
 struct iscsi_dif_flags {
@@ -806,7 +775,6 @@ enum iscsi_eqe_opcode {
 	ISCSI_EVENT_TYPE_ASYN_FIN_WAIT2,
 	ISCSI_EVENT_TYPE_ISCSI_CONN_ERROR,
 	ISCSI_EVENT_TYPE_TCP_CONN_ERROR,
-	ISCSI_EVENT_TYPE_ASYN_DELETE_OOO_ISLES,
 	MAX_ISCSI_EQE_OPCODE
 };
 
@@ -856,31 +824,11 @@ enum iscsi_error_types {
 	ISCSI_CONN_ERROR_PROTOCOL_ERR_DIF_TX,
 	ISCSI_CONN_ERROR_SENSE_DATA_LENGTH,
 	ISCSI_CONN_ERROR_DATA_PLACEMENT_ERROR,
+	ISCSI_CONN_ERROR_INVALID_ITT,
 	ISCSI_ERROR_UNKNOWN,
 	MAX_ISCSI_ERROR_TYPES
 };
 
-struct iscsi_mflags {
-	u8 mflags;
-#define ISCSI_MFLAGS_SLOW_IO_MASK     0x1
-#define ISCSI_MFLAGS_SLOW_IO_SHIFT    0
-#define ISCSI_MFLAGS_SINGLE_SGE_MASK  0x1
-#define ISCSI_MFLAGS_SINGLE_SGE_SHIFT 1
-#define ISCSI_MFLAGS_RESERVED_MASK    0x3F
-#define ISCSI_MFLAGS_RESERVED_SHIFT   2
-};
-
-struct iscsi_sgl {
-	struct regpair sgl_addr;
-	__le16 updated_sge_size;
-	__le16 updated_sge_offset;
-	__le32 byte_offset;
-};
-
-union iscsi_mstorm_sgl {
-	struct iscsi_sgl sgl_struct;
-	struct iscsi_sge single_sge;
-};
 
 enum iscsi_ramrod_cmd_id {
 	ISCSI_RAMROD_CMD_ID_UNUSED = 0,
@@ -896,10 +844,10 @@ enum iscsi_ramrod_cmd_id {
 
 struct iscsi_reg1 {
 	__le32 reg1_map;
-#define ISCSI_REG1_NUM_FAST_SGES_MASK  0x7
-#define ISCSI_REG1_NUM_FAST_SGES_SHIFT 0
-#define ISCSI_REG1_RESERVED1_MASK      0x1FFFFFFF
-#define ISCSI_REG1_RESERVED1_SHIFT     3
+#define ISCSI_REG1_NUM_SGES_MASK   0xF
+#define ISCSI_REG1_NUM_SGES_SHIFT  0
+#define ISCSI_REG1_RESERVED1_MASK  0xFFFFFFF
+#define ISCSI_REG1_RESERVED1_SHIFT 4
 };
 
 union iscsi_seq_num {
@@ -967,22 +915,33 @@ struct iscsi_spe_func_init {
 };
 
 struct ystorm_iscsi_task_state {
-	union iscsi_data_desc_ctx sgl_ctx_union;
-	__le32 buffer_offset[2];
-	__le16 bytes_nxt_dif;
-	__le16 rxmit_bytes_nxt_dif;
-	union iscsi_seq_num seq_num_union;
-	u8 dif_bytes_leftover;
-	u8 rxmit_dif_bytes_leftover;
-	__le16 reuse_count;
-	struct iscsi_dif_flags dif_flags;
-	u8 local_comp;
+	struct scsi_cached_sges data_desc;
+	struct scsi_sgl_params sgl_params;
 	__le32 exp_r2t_sn;
-	__le32 sgl_offset[2];
+	__le32 buffer_offset;
+	union iscsi_seq_num seq_num;
+	struct iscsi_dif_flags dif_flags;
+	u8 flags;
+#define YSTORM_ISCSI_TASK_STATE_LOCAL_COMP_MASK  0x1
+#define YSTORM_ISCSI_TASK_STATE_LOCAL_COMP_SHIFT 0
+#define YSTORM_ISCSI_TASK_STATE_SLOW_IO_MASK     0x1
+#define YSTORM_ISCSI_TASK_STATE_SLOW_IO_SHIFT    1
+#define YSTORM_ISCSI_TASK_STATE_RESERVED0_MASK   0x3F
+#define YSTORM_ISCSI_TASK_STATE_RESERVED0_SHIFT  2
+};
+
+struct ystorm_iscsi_task_rxmit_opt {
+	__le32 fast_rxmit_sge_offset;
+	__le32 scan_start_buffer_offset;
+	__le32 fast_rxmit_buffer_offset;
+	u8 scan_start_sgl_index;
+	u8 fast_rxmit_sgl_index;
+	__le16 reserved;
 };
 
 struct ystorm_iscsi_task_st_ctx {
 	struct ystorm_iscsi_task_state state;
+	struct ystorm_iscsi_task_rxmit_opt rxmit_opt;
 	union iscsi_task_hdr pdu_hdr;
 };
 
@@ -1152,25 +1111,16 @@ struct ustorm_iscsi_task_ag_ctx {
 };
 
 struct mstorm_iscsi_task_st_ctx {
-	union iscsi_mstorm_sgl sgl_union;
-	struct iscsi_dif_flags dif_flags;
-	struct iscsi_mflags flags;
-	u8 sgl_size;
-	u8 host_sge_index;
-	__le16 dix_cur_sge_offset;
-	__le16 dix_cur_sge_size;
-	__le32 data_offset_rtid;
-	u8 dif_offset;
-	u8 dix_sgl_size;
-	u8 dix_sge_index;
+	struct scsi_cached_sges data_desc;
+	struct scsi_sgl_params sgl_params;
+	__le32 rem_task_size;
+	__le32 data_buffer_offset;
 	u8 task_type;
+	struct iscsi_dif_flags dif_flags;
+	u8 reserved0[2];
 	struct regpair sense_db;
-	struct regpair dix_sgl_cur_sge;
-	__le32 rem_task_size;
-	__le16 reuse_count;
-	__le16 dif_data_residue;
-	u8 reserved0[4];
-	__le32 reserved1[1];
+	__le32 expected_itt;
+	__le32 reserved1;
 };
 
 struct ustorm_iscsi_task_st_ctx {
@@ -1184,7 +1134,7 @@ struct ustorm_iscsi_task_st_ctx {
 #define USTORM_ISCSI_TASK_ST_CTX_AHS_EXIST_SHIFT            0
 #define USTORM_ISCSI_TASK_ST_CTX_RESERVED1_MASK             0x7F
 #define USTORM_ISCSI_TASK_ST_CTX_RESERVED1_SHIFT            1
-	u8 reserved2;
+	struct iscsi_dif_flags dif_flags;
 	__le16 reserved3;
 	__le32 reserved4;
 	__le32 reserved5;
@@ -1207,10 +1157,10 @@ struct ustorm_iscsi_task_st_ctx {
 #define USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP_SHIFT           2
 #define USTORM_ISCSI_TASK_ST_CTX_Q0_R2TQE_WRITE_MASK        0x1
 #define USTORM_ISCSI_TASK_ST_CTX_Q0_R2TQE_WRITE_SHIFT       3
-#define USTORM_ISCSI_TASK_ST_CTX_TOTALDATAACKED_DONE_MASK   0x1
-#define USTORM_ISCSI_TASK_ST_CTX_TOTALDATAACKED_DONE_SHIFT  4
-#define USTORM_ISCSI_TASK_ST_CTX_HQSCANNED_DONE_MASK        0x1
-#define USTORM_ISCSI_TASK_ST_CTX_HQSCANNED_DONE_SHIFT       5
+#define USTORM_ISCSI_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_MASK  0x1
+#define USTORM_ISCSI_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_SHIFT 4
+#define USTORM_ISCSI_TASK_ST_CTX_HQ_SCANNED_DONE_MASK        0x1
+#define USTORM_ISCSI_TASK_ST_CTX_HQ_SCANNED_DONE_SHIFT       5
 #define USTORM_ISCSI_TASK_ST_CTX_R2T2RECV_DONE_MASK         0x1
 #define USTORM_ISCSI_TASK_ST_CTX_R2T2RECV_DONE_SHIFT        6
 #define USTORM_ISCSI_TASK_ST_CTX_RESERVED0_MASK             0x1
@@ -1220,7 +1170,6 @@ struct ustorm_iscsi_task_st_ctx {
 
 struct iscsi_task_context {
 	struct ystorm_iscsi_task_st_ctx ystorm_st_context;
-	struct regpair ystorm_st_padding[2];
 	struct ystorm_iscsi_task_ag_ctx ystorm_ag_context;
 	struct regpair ystorm_ag_padding[2];
 	struct tdif_task_context tdif_context;
@@ -1272,32 +1221,22 @@ struct iscsi_uhqe {
 #define ISCSI_UHQE_TASK_ID_LO_SHIFT         24
 };
 
-struct iscsi_wqe_field {
-	__le32 contlen_cdbsize_field;
-#define ISCSI_WQE_FIELD_CONT_LEN_MASK  0xFFFFFF
-#define ISCSI_WQE_FIELD_CONT_LEN_SHIFT 0
-#define ISCSI_WQE_FIELD_CDB_SIZE_MASK  0xFF
-#define ISCSI_WQE_FIELD_CDB_SIZE_SHIFT 24
-};
-
-union iscsi_wqe_field_union {
-	struct iscsi_wqe_field cont_field;
-	__le32 prev_tid;
-};
 
 struct iscsi_wqe {
 	__le16 task_id;
 	u8 flags;
 #define ISCSI_WQE_WQE_TYPE_MASK        0x7
 #define ISCSI_WQE_WQE_TYPE_SHIFT       0
-#define ISCSI_WQE_NUM_FAST_SGES_MASK   0x7
-#define ISCSI_WQE_NUM_FAST_SGES_SHIFT  3
-#define ISCSI_WQE_PTU_INVALIDATE_MASK  0x1
-#define ISCSI_WQE_PTU_INVALIDATE_SHIFT 6
+#define ISCSI_WQE_NUM_SGES_MASK  0xF
+#define ISCSI_WQE_NUM_SGES_SHIFT 3
 #define ISCSI_WQE_RESPONSE_MASK        0x1
 #define ISCSI_WQE_RESPONSE_SHIFT       7
 	struct iscsi_dif_flags prot_flags;
-	union iscsi_wqe_field_union cont_prevtid_union;
+	__le32 contlen_cdbsize;
+#define ISCSI_WQE_CONT_LEN_MASK  0xFFFFFF
+#define ISCSI_WQE_CONT_LEN_SHIFT 0
+#define ISCSI_WQE_CDB_SIZE_MASK  0xFF
+#define ISCSI_WQE_CDB_SIZE_SHIFT 24
 };
 
 enum iscsi_wqe_type {
@@ -1318,17 +1257,15 @@ struct iscsi_xhqe {
 	u8 total_ahs_length;
 	u8 opcode;
 	u8 flags;
-#define ISCSI_XHQE_NUM_FAST_SGES_MASK  0x7
-#define ISCSI_XHQE_NUM_FAST_SGES_SHIFT 0
-#define ISCSI_XHQE_FINAL_MASK          0x1
-#define ISCSI_XHQE_FINAL_SHIFT         3
-#define ISCSI_XHQE_SUPER_IO_MASK       0x1
-#define ISCSI_XHQE_SUPER_IO_SHIFT      4
-#define ISCSI_XHQE_STATUS_BIT_MASK     0x1
-#define ISCSI_XHQE_STATUS_BIT_SHIFT    5
-#define ISCSI_XHQE_RESERVED_MASK       0x3
-#define ISCSI_XHQE_RESERVED_SHIFT      6
-	union iscsi_seq_num seq_num_union;
+#define ISCSI_XHQE_FINAL_MASK       0x1
+#define ISCSI_XHQE_FINAL_SHIFT      0
+#define ISCSI_XHQE_STATUS_BIT_MASK  0x1
+#define ISCSI_XHQE_STATUS_BIT_SHIFT 1
+#define ISCSI_XHQE_NUM_SGES_MASK    0xF
+#define ISCSI_XHQE_NUM_SGES_SHIFT   2
+#define ISCSI_XHQE_RESERVED0_MASK   0x3
+#define ISCSI_XHQE_RESERVED0_SHIFT  6
+	union iscsi_seq_num seq_num;
 	__le16 reserved1;
 };
 
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index fde56c436f71..625f80f08f91 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -263,7 +263,6 @@ struct qed_rdma_pf_params {
 	 * the doorbell BAR).
 	 */
 	u32 min_dpis;		/* number of requested DPIs */
-	u32 num_mrs;		/* number of requested memory regions */
 	u32 num_qps;		/* number of requested Queue Pairs */
 	u32 num_srqs;		/* number of requested SRQ */
 	u8 roce_edpm_mode;	/* see QED_ROCE_EDPM_MODE_ENABLE */
@@ -300,6 +299,11 @@ struct qed_sb_info {
 	struct qed_dev		*cdev;
 };
 
+enum qed_dev_type {
+	QED_DEV_TYPE_BB,
+	QED_DEV_TYPE_AH,
+};
+
 struct qed_dev_info {
 	unsigned long	pci_mem_start;
 	unsigned long	pci_mem_end;
@@ -325,6 +329,8 @@ struct qed_dev_info {
 	u16		mtu;
 
 	bool wol_support;
+
+	enum qed_dev_type dev_type;
 };
 
 enum qed_sb_type {
@@ -752,7 +758,7 @@ enum qed_mf_mode {
 	QED_MF_NPAR,
 };
 
-struct qed_eth_stats {
+struct qed_eth_stats_common {
 	u64	no_buff_discards;
 	u64	packet_too_big_discard;
 	u64	ttl0_discard;
@@ -784,11 +790,6 @@ struct qed_eth_stats {
 	u64	rx_256_to_511_byte_packets;
 	u64	rx_512_to_1023_byte_packets;
 	u64	rx_1024_to_1518_byte_packets;
-	u64	rx_1519_to_1522_byte_packets;
-	u64	rx_1519_to_2047_byte_packets;
-	u64	rx_2048_to_4095_byte_packets;
-	u64	rx_4096_to_9216_byte_packets;
-	u64	rx_9217_to_16383_byte_packets;
 	u64	rx_crc_errors;
 	u64	rx_mac_crtl_frames;
 	u64	rx_pause_frames;
@@ -805,14 +806,8 @@ struct qed_eth_stats {
 	u64	tx_256_to_511_byte_packets;
 	u64	tx_512_to_1023_byte_packets;
 	u64	tx_1024_to_1518_byte_packets;
-	u64	tx_1519_to_2047_byte_packets;
-	u64	tx_2048_to_4095_byte_packets;
-	u64	tx_4096_to_9216_byte_packets;
-	u64	tx_9217_to_16383_byte_packets;
 	u64	tx_pause_frames;
 	u64	tx_pfc_frames;
-	u64	tx_lpi_entry_count;
-	u64	tx_total_collisions;
 	u64	brb_truncates;
 	u64	brb_discards;
 	u64	rx_mac_bytes;
@@ -827,6 +822,34 @@ struct qed_eth_stats {
 	u64	tx_mac_ctrl_frames;
 };
 
+struct qed_eth_stats_bb {
+	u64 rx_1519_to_1522_byte_packets;
+	u64 rx_1519_to_2047_byte_packets;
+	u64 rx_2048_to_4095_byte_packets;
+	u64 rx_4096_to_9216_byte_packets;
+	u64 rx_9217_to_16383_byte_packets;
+	u64 tx_1519_to_2047_byte_packets;
+	u64 tx_2048_to_4095_byte_packets;
+	u64 tx_4096_to_9216_byte_packets;
+	u64 tx_9217_to_16383_byte_packets;
+	u64 tx_lpi_entry_count;
+	u64 tx_total_collisions;
+};
+
+struct qed_eth_stats_ah {
+	u64 rx_1519_to_max_byte_packets;
+	u64 tx_1519_to_max_byte_packets;
+};
+
+struct qed_eth_stats {
+	struct qed_eth_stats_common common;
+
+	union {
+		struct qed_eth_stats_bb bb;
+		struct qed_eth_stats_ah ah;
+	};
+};
+
 #define QED_SB_IDX              0x0002
 
 #define RX_PI           0
diff --git a/include/linux/qed/rdma_common.h b/include/linux/qed/rdma_common.h
index f773aa5e746f..72c770f9f666 100644
--- a/include/linux/qed/rdma_common.h
+++ b/include/linux/qed/rdma_common.h
@@ -52,7 +52,8 @@
 #define RDMA_MAX_PDS                            (64 * 1024)
 
 #define RDMA_NUM_STATISTIC_COUNTERS                     MAX_NUM_VPORTS
-#define RDMA_NUM_STATISTIC_COUNTERS_BB			MAX_NUM_VPORTS_BB
+#define RDMA_NUM_STATISTIC_COUNTERS_K2                  MAX_NUM_VPORTS_K2
+#define RDMA_NUM_STATISTIC_COUNTERS_BB                  MAX_NUM_VPORTS_BB
 
 #define RDMA_TASK_TYPE (PROTOCOLID_ROCE)
 
diff --git a/include/linux/qed/roce_common.h b/include/linux/qed/roce_common.h
index bad02df213df..866f063026de 100644
--- a/include/linux/qed/roce_common.h
+++ b/include/linux/qed/roce_common.h
@@ -38,4 +38,21 @@
 
 #define ROCE_MAX_QPS	(32 * 1024)
 
+enum roce_async_events_type {
+	ROCE_ASYNC_EVENT_NONE = 0,
+	ROCE_ASYNC_EVENT_COMM_EST = 1,
+	ROCE_ASYNC_EVENT_SQ_DRAINED,
+	ROCE_ASYNC_EVENT_SRQ_LIMIT,
+	ROCE_ASYNC_EVENT_LAST_WQE_REACHED,
+	ROCE_ASYNC_EVENT_CQ_ERR,
+	ROCE_ASYNC_EVENT_LOCAL_INVALID_REQUEST_ERR,
+	ROCE_ASYNC_EVENT_LOCAL_CATASTROPHIC_ERR,
+	ROCE_ASYNC_EVENT_LOCAL_ACCESS_ERR,
+	ROCE_ASYNC_EVENT_QP_CATASTROPHIC_ERR,
+	ROCE_ASYNC_EVENT_CQ_OVERFLOW_ERR,
+	ROCE_ASYNC_EVENT_SRQ_EMPTY,
+	ROCE_ASYNC_EVENT_DESTROY_QP_DONE,
+	MAX_ROCE_ASYNC_EVENTS_TYPE
+};
+
 #endif /* __ROCE_COMMON__ */
diff --git a/include/linux/qed/storage_common.h b/include/linux/qed/storage_common.h
index 03f3e37ab059..08df82a096b6 100644
--- a/include/linux/qed/storage_common.h
+++ b/include/linux/qed/storage_common.h
@@ -40,6 +40,8 @@
 #define BDQ_ID_IMM_DATA          (1)
 #define BDQ_NUM_IDS          (2)
 
+#define SCSI_NUM_SGES_SLOW_SGL_THR      8
+
 #define BDQ_MAX_EXTERNAL_RING_SIZE (1 << 15)
 
 struct scsi_bd {
@@ -52,6 +54,16 @@ struct scsi_bdq_ram_drv_data {
 	__le16 reserved0[3];
 };
 
+struct scsi_sge {
+	struct regpair sge_addr;
+	__le32 sge_len;
+	__le32 reserved;
+};
+
+struct scsi_cached_sges {
+	struct scsi_sge sge[4];
+};
+
 struct scsi_drv_cmdq {
 	__le16 cmdq_cons;
 	__le16 reserved0;
@@ -99,11 +111,19 @@ struct scsi_ram_per_bdq_resource_drv_data {
 	struct scsi_bdq_ram_drv_data drv_data_per_bdq_id[BDQ_NUM_IDS];
 };
 
-struct scsi_sge {
-	struct regpair sge_addr;
-	__le16 sge_len;
-	__le16 reserved0;
-	__le32 reserved1;
+enum scsi_sgl_mode {
+	SCSI_TX_SLOW_SGL,
+	SCSI_FAST_SGL,
+	MAX_SCSI_SGL_MODE
+};
+
+struct scsi_sgl_params {
+	struct regpair sgl_addr;
+	__le32 sgl_total_length;
+	__le32 sge_offset;
+	__le16 sgl_num_sges;
+	u8 sgl_index;
+	u8 reserved;
 };
 
 struct scsi_terminate_extra_params {
diff --git a/include/linux/qed/tcp_common.h b/include/linux/qed/tcp_common.h
index 46fe7856f1b2..a5e843268f0e 100644
--- a/include/linux/qed/tcp_common.h
+++ b/include/linux/qed/tcp_common.h
@@ -173,6 +173,7 @@ enum tcp_seg_placement_event {
 	TCP_EVENT_ADD_ISLE_RIGHT,
 	TCP_EVENT_ADD_ISLE_LEFT,
 	TCP_EVENT_JOIN,
+	TCP_EVENT_DELETE_ISLES,
 	TCP_EVENT_NOP,
 	MAX_TCP_SEG_PLACEMENT_EVENT
 };
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 092292b6675e..e507290cd2c7 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -916,6 +916,28 @@ static inline int rhashtable_lookup_insert_fast(
 }
 
 /**
+ * rhashtable_lookup_get_insert_fast - lookup and insert object into hash table
+ * @ht:		hash table
+ * @obj:	pointer to hash head inside object
+ * @params:	hash table parameters
+ *
+ * Just like rhashtable_lookup_insert_fast(), but this function returns the
+ * object if it exists, NULL if it did not and the insertion was successful,
+ * and an ERR_PTR otherwise.
+ */
+static inline void *rhashtable_lookup_get_insert_fast(
+	struct rhashtable *ht, struct rhash_head *obj,
+	const struct rhashtable_params params)
+{
+	const char *key = rht_obj(ht, obj);
+
+	BUG_ON(ht->p.obj_hashfn);
+
+	return __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params,
+					false);
+}
+
+/**
  * rhashtable_lookup_insert_key - search and insert object to hash table
  *				  with explicit key
  * @ht:		hash table
diff --git a/include/linux/rpmsg/qcom_smd.h b/include/linux/rpmsg/qcom_smd.h
index 8ec8b6439b25..f27917e0a101 100644
--- a/include/linux/rpmsg/qcom_smd.h
+++ b/include/linux/rpmsg/qcom_smd.h
@@ -6,7 +6,7 @@
 
 struct qcom_smd_edge;
 
-#if IS_ENABLED(CONFIG_RPMSG_QCOM_SMD) || IS_ENABLED(CONFIG_QCOM_SMD)
+#if IS_ENABLED(CONFIG_RPMSG_QCOM_SMD)
 
 struct qcom_smd_edge *qcom_smd_register_edge(struct device *parent,
 					     struct device_node *node);
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 57e54847b0b9..0459018173cf 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -18,7 +18,8 @@ extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst,
 
 void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags);
 struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
-				       unsigned change, gfp_t flags);
+				       unsigned change, unsigned long event,
+				       gfp_t flags);
 void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev,
 		       gfp_t flags);
 
diff --git a/include/linux/soc/qcom/smd.h b/include/linux/soc/qcom/smd.h
deleted file mode 100644
index f148e0ffbec7..000000000000
--- a/include/linux/soc/qcom/smd.h
+++ /dev/null
@@ -1,139 +0,0 @@
-#ifndef __QCOM_SMD_H__
-#define __QCOM_SMD_H__
-
-#include <linux/device.h>
-#include <linux/mod_devicetable.h>
-
-struct qcom_smd;
-struct qcom_smd_channel;
-struct qcom_smd_lookup;
-
-/**
- * struct qcom_smd_id - struct used for matching a smd device
- * @name:	name of the channel
- */
-struct qcom_smd_id {
-	char name[20];
-};
-
-/**
- * struct qcom_smd_device - smd device struct
- * @dev:	the device struct
- * @channel:	handle to the smd channel for this device
- */
-struct qcom_smd_device {
-	struct device dev;
-	struct qcom_smd_channel *channel;
-};
-
-typedef int (*qcom_smd_cb_t)(struct qcom_smd_channel *, const void *, size_t);
-
-/**
- * struct qcom_smd_driver - smd driver struct
- * @driver:	underlying device driver
- * @smd_match_table: static channel match table
- * @probe:	invoked when the smd channel is found
- * @remove:	invoked when the smd channel is closed
- * @callback:	invoked when an inbound message is received on the channel,
- *		should return 0 on success or -EBUSY if the data cannot be
- *		consumed at this time
- */
-struct qcom_smd_driver {
-	struct device_driver driver;
-	const struct qcom_smd_id *smd_match_table;
-
-	int (*probe)(struct qcom_smd_device *dev);
-	void (*remove)(struct qcom_smd_device *dev);
-	qcom_smd_cb_t callback;
-};
-
-#if IS_ENABLED(CONFIG_QCOM_SMD)
-
-int qcom_smd_driver_register(struct qcom_smd_driver *drv);
-void qcom_smd_driver_unregister(struct qcom_smd_driver *drv);
-
-struct qcom_smd_channel *qcom_smd_open_channel(struct qcom_smd_channel *channel,
-					       const char *name,
-					       qcom_smd_cb_t cb);
-void qcom_smd_close_channel(struct qcom_smd_channel *channel);
-void *qcom_smd_get_drvdata(struct qcom_smd_channel *channel);
-void qcom_smd_set_drvdata(struct qcom_smd_channel *channel, void *data);
-int qcom_smd_send(struct qcom_smd_channel *channel, const void *data, int len);
-
-
-struct qcom_smd_edge *qcom_smd_register_edge(struct device *parent,
-					     struct device_node *node);
-int qcom_smd_unregister_edge(struct qcom_smd_edge *edge);
-
-#else
-
-static inline int qcom_smd_driver_register(struct qcom_smd_driver *drv)
-{
-	return -ENXIO;
-}
-
-static inline void qcom_smd_driver_unregister(struct qcom_smd_driver *drv)
-{
-	/* This shouldn't be possible */
-	WARN_ON(1);
-}
-
-static inline struct qcom_smd_channel *
-qcom_smd_open_channel(struct qcom_smd_channel *channel,
-		      const char *name,
-		      qcom_smd_cb_t cb)
-{
-	/* This shouldn't be possible */
-	WARN_ON(1);
-	return NULL;
-}
-
-static inline void qcom_smd_close_channel(struct qcom_smd_channel *channel)
-{
-	/* This shouldn't be possible */
-	WARN_ON(1);
-}
-
-static inline void *qcom_smd_get_drvdata(struct qcom_smd_channel *channel)
-{
-	/* This shouldn't be possible */
-	WARN_ON(1);
-	return NULL;
-}
-
-static inline void qcom_smd_set_drvdata(struct qcom_smd_channel *channel, void *data)
-{
-	/* This shouldn't be possible */
-	WARN_ON(1);
-}
-
-static inline int qcom_smd_send(struct qcom_smd_channel *channel,
-				const void *data, int len)
-{
-	/* This shouldn't be possible */
-	WARN_ON(1);
-	return -ENXIO;
-}
-
-static inline struct qcom_smd_edge *
-qcom_smd_register_edge(struct device *parent,
-		       struct device_node *node)
-{
-	return ERR_PTR(-ENXIO);
-}
-
-static inline int qcom_smd_unregister_edge(struct qcom_smd_edge *edge)
-{
-	/* This shouldn't be possible */
-	WARN_ON(1);
-	return -ENXIO;
-}
-
-#endif
-
-#define module_qcom_smd_driver(__smd_driver) \
-	module_driver(__smd_driver, qcom_smd_driver_register, \
-		      qcom_smd_driver_unregister)
-
-
-#endif
diff --git a/include/linux/soc/qcom/wcnss_ctrl.h b/include/linux/soc/qcom/wcnss_ctrl.h
index eab64976a73b..a4dd4d7c711d 100644
--- a/include/linux/soc/qcom/wcnss_ctrl.h
+++ b/include/linux/soc/qcom/wcnss_ctrl.h
@@ -1,16 +1,19 @@
 #ifndef __WCNSS_CTRL_H__
 #define __WCNSS_CTRL_H__
 
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
 
 #if IS_ENABLED(CONFIG_QCOM_WCNSS_CTRL)
 
-struct qcom_smd_channel *qcom_wcnss_open_channel(void *wcnss, const char *name, qcom_smd_cb_t cb);
+struct rpmsg_endpoint *qcom_wcnss_open_channel(void *wcnss, const char *name,
+					       rpmsg_rx_cb_t cb, void *priv);
 
 #else
 
-static inline struct qcom_smd_channel*
-qcom_wcnss_open_channel(void *wcnss, const char *name, qcom_smd_cb_t cb)
+static struct rpmsg_endpoint *qcom_wcnss_open_channel(void *wcnss,
+						      const char *name,
+						      rpmsg_rx_cb_t cb,
+						      void *priv)
 {
 	WARN_ON(1);
 	return ERR_PTR(-ENXIO);
diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index a0596ca0e80a..a2f8109bb215 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -24,6 +24,7 @@ void sock_diag_unregister(const struct sock_diag_handler *h);
 void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
 void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
 
+u64 sock_gen_cookie(struct sock *sk);
 int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie);
 void sock_diag_save_cookie(struct sock *sk, __u32 *cookie);
 
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index fc273e9d5f67..3921cb9dfadb 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -28,6 +28,9 @@
 
 #include <linux/platform_device.h>
 
+#define MTL_MAX_RX_QUEUES	8
+#define MTL_MAX_TX_QUEUES	8
+
 #define STMMAC_RX_COE_NONE	0
 #define STMMAC_RX_COE_TYPE1	1
 #define STMMAC_RX_COE_TYPE2	2
@@ -44,6 +47,18 @@
 #define	STMMAC_CSR_150_250M	0x4	/* MDC = clk_scr_i/102 */
 #define	STMMAC_CSR_250_300M	0x5	/* MDC = clk_scr_i/122 */
 
+/* MTL algorithms identifiers */
+#define MTL_TX_ALGORITHM_WRR	0x0
+#define MTL_TX_ALGORITHM_WFQ	0x1
+#define MTL_TX_ALGORITHM_DWRR	0x2
+#define MTL_TX_ALGORITHM_SP	0x3
+#define MTL_RX_ALGORITHM_SP	0x4
+#define MTL_RX_ALGORITHM_WSP	0x5
+
+/* RX/TX Queue Mode */
+#define MTL_QUEUE_AVB		0x0
+#define MTL_QUEUE_DCB		0x1
+
 /* The MDC clock could be set higher than the IEEE 802.3
  * specified frequency limit 0f 2.5 MHz, by programming a clock divider
  * of value different than the above defined values. The resultant MDIO
@@ -109,6 +124,26 @@ struct stmmac_axi {
 	bool axi_rb;
 };
 
+struct stmmac_rxq_cfg {
+	u8 mode_to_use;
+	u8 chan;
+	u8 pkt_route;
+	bool use_prio;
+	u32 prio;
+};
+
+struct stmmac_txq_cfg {
+	u8 weight;
+	u8 mode_to_use;
+	/* Credit Base Shaper parameters */
+	u32 send_slope;
+	u32 idle_slope;
+	u32 high_credit;
+	u32 low_credit;
+	bool use_prio;
+	u32 prio;
+};
+
 struct plat_stmmacenet_data {
 	int bus_id;
 	int phy_addr;
@@ -133,6 +168,12 @@ struct plat_stmmacenet_data {
 	int unicast_filter_entries;
 	int tx_fifo_size;
 	int rx_fifo_size;
+	u8 rx_queues_to_use;
+	u8 tx_queues_to_use;
+	u8 rx_sched_algorithm;
+	u8 tx_sched_algorithm;
+	struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES];
+	struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES];
 	void (*fix_mac_speed)(void *priv, unsigned int speed);
 	int (*init)(struct platform_device *pdev, void *priv);
 	void (*exit)(struct platform_device *pdev, void *priv);
diff --git a/include/linux/udp.h b/include/linux/udp.h
index c0f530809d1f..6cb4061a720d 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -115,6 +115,6 @@ static inline bool udp_get_no_check6_rx(struct sock *sk)
 #define udp_portaddr_for_each_entry_rcu(__sk, list) \
 	hlist_for_each_entry_rcu(__sk, list, __sk_common.skc_portaddr_node)
 
-#define IS_UDPLITE(__sk) (udp_sk(__sk)->pcflag)
+#define IS_UDPLITE(__sk) (__sk->sk_protocol == IPPROTO_UDPLITE)
 
 #endif	/* _LINUX_UDP_H */
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 6e0ce8c7b8cb..7dffa5624ea6 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -64,6 +64,8 @@ struct usbnet {
 	struct usb_anchor	deferred;
 	struct tasklet_struct	bh;
 
+	struct pcpu_sw_netstats __percpu *stats64;
+
 	struct work_struct	kevent;
 	unsigned long		flags;
 #		define EVENT_TX_HALT	0
@@ -261,10 +263,10 @@ extern void usbnet_pause_rx(struct usbnet *);
 extern void usbnet_resume_rx(struct usbnet *);
 extern void usbnet_purge_paused_rxq(struct usbnet *);
 
-extern int usbnet_get_settings(struct net_device *net,
-			       struct ethtool_cmd *cmd);
-extern int usbnet_set_settings(struct net_device *net,
-			       struct ethtool_cmd *cmd);
+extern int usbnet_get_link_ksettings(struct net_device *net,
+				     struct ethtool_link_ksettings *cmd);
+extern int usbnet_set_link_ksettings(struct net_device *net,
+				     const struct ethtool_link_ksettings *cmd);
 extern u32 usbnet_get_link(struct net_device *net);
 extern u32 usbnet_get_msglevel(struct net_device *);
 extern void usbnet_set_msglevel(struct net_device *, u32);
@@ -278,5 +280,7 @@ extern int usbnet_status_start(struct usbnet *dev, gfp_t mem_flags);
 extern void usbnet_status_stop(struct usbnet *dev);
 
 extern void usbnet_update_max_qlen(struct usbnet *dev);
+extern void usbnet_get_stats64(struct net_device *dev,
+			       struct rtnl_link_stats64 *stats);
 
 #endif /* __LINUX_USB_USBNET_H */
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 17c6fd84e287..1aeb25dd42a7 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -262,8 +262,8 @@ int register_inet6addr_notifier(struct notifier_block *nb);
 int unregister_inet6addr_notifier(struct notifier_block *nb);
 int inet6addr_notifier_call_chain(unsigned long val, void *v);
 
-void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
-				  struct ipv6_devconf *devconf);
+void inet6_netconf_notify_devconf(struct net *net, int event, int type,
+				  int ifindex, struct ipv6_devconf *devconf);
 
 /**
  * __in6_dev_get - get inet6_dev pointer from netdevice
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 3c857778a6ca..04a21e8048be 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -153,7 +153,8 @@ struct slave {
 	unsigned long last_link_up;
 	unsigned long last_rx;
 	unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS];
-	s8     link;    /* one of BOND_LINK_XXXX */
+	s8     link;		/* one of BOND_LINK_XXXX */
+	s8     link_new_state;	/* one of BOND_LINK_XXXX */
 	s8     new_link;
 	u8     backup:1,   /* indicates backup slave. Value corresponds with
 			      BOND_STATE_ACTIVE and BOND_STATE_BACKUP */
@@ -165,7 +166,7 @@ struct slave {
 	u32    link_failure_count;
 	u32    speed;
 	u16    queue_id;
-	u8     perm_hwaddr[ETH_ALEN];
+	u8     perm_hwaddr[MAX_ADDR_LEN];
 	struct ad_slave_info *ad_info;
 	struct tlb_slave_info tlb_info;
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -401,6 +402,16 @@ static inline bool bond_slave_can_tx(struct slave *slave)
 	       bond_is_active_slave(slave);
 }
 
+static inline void bond_hw_addr_copy(u8 *dst, const u8 *src, unsigned int len)
+{
+	if (len == ETH_ALEN) {
+		ether_addr_copy(dst, src);
+		return;
+	}
+
+	memcpy(dst, src, len);
+}
+
 #define BOND_PRI_RESELECT_ALWAYS	0
 #define BOND_PRI_RESELECT_BETTER	1
 #define BOND_PRI_RESELECT_FAILURE	2
@@ -504,13 +515,17 @@ static inline bool bond_is_slave_inactive(struct slave *slave)
 	return slave->inactive;
 }
 
-static inline void bond_set_slave_link_state(struct slave *slave, int state,
-					     bool notify)
+static inline void bond_propose_link_state(struct slave *slave, int state)
 {
-	if (slave->link == state)
+	slave->link_new_state = state;
+}
+
+static inline void bond_commit_link_state(struct slave *slave, bool notify)
+{
+	if (slave->link == slave->link_new_state)
 		return;
 
-	slave->link = state;
+	slave->link = slave->link_new_state;
 	if (notify) {
 		bond_queue_slave_event(slave);
 		bond_lower_state_changed(slave);
@@ -523,6 +538,13 @@ static inline void bond_set_slave_link_state(struct slave *slave, int state,
 	}
 }
 
+static inline void bond_set_slave_link_state(struct slave *slave, int state,
+					     bool notify)
+{
+	bond_propose_link_state(slave, state);
+	bond_commit_link_state(slave, notify);
+}
+
 static inline void bond_slave_link_notify(struct bonding *bond)
 {
 	struct list_head *iter;
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index c0452de83086..8ffd434676b7 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -35,83 +35,101 @@ struct napi_struct;
 extern unsigned int sysctl_net_busy_read __read_mostly;
 extern unsigned int sysctl_net_busy_poll __read_mostly;
 
+/*		0 - Reserved to indicate value not set
+ *     1..NR_CPUS - Reserved for sender_cpu
+ *  NR_CPUS+1..~0 - Region available for NAPI IDs
+ */
+#define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1))
+
 static inline bool net_busy_loop_on(void)
 {
 	return sysctl_net_busy_poll;
 }
 
-static inline u64 busy_loop_us_clock(void)
+static inline bool sk_can_busy_loop(const struct sock *sk)
 {
-	return local_clock() >> 10;
+	return sk->sk_ll_usec && !signal_pending(current);
 }
 
-static inline unsigned long sk_busy_loop_end_time(struct sock *sk)
-{
-	return busy_loop_us_clock() + ACCESS_ONCE(sk->sk_ll_usec);
-}
+bool sk_busy_loop_end(void *p, unsigned long start_time);
 
-/* in poll/select we use the global sysctl_net_ll_poll value */
-static inline unsigned long busy_loop_end_time(void)
+void napi_busy_loop(unsigned int napi_id,
+		    bool (*loop_end)(void *, unsigned long),
+		    void *loop_end_arg);
+
+#else /* CONFIG_NET_RX_BUSY_POLL */
+static inline unsigned long net_busy_loop_on(void)
 {
-	return busy_loop_us_clock() + ACCESS_ONCE(sysctl_net_busy_poll);
+	return 0;
 }
 
-static inline bool sk_can_busy_loop(const struct sock *sk)
+static inline bool sk_can_busy_loop(struct sock *sk)
 {
-	return sk->sk_ll_usec && sk->sk_napi_id && !signal_pending(current);
+	return false;
 }
 
+#endif /* CONFIG_NET_RX_BUSY_POLL */
 
-static inline bool busy_loop_timeout(unsigned long end_time)
+static inline unsigned long busy_loop_current_time(void)
 {
-	unsigned long now = busy_loop_us_clock();
-
-	return time_after(now, end_time);
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	return (unsigned long)(local_clock() >> 10);
+#else
+	return 0;
+#endif
 }
 
-bool sk_busy_loop(struct sock *sk, int nonblock);
-
-/* used in the NIC receive handler to mark the skb */
-static inline void skb_mark_napi_id(struct sk_buff *skb,
-				    struct napi_struct *napi)
+/* in poll/select we use the global sysctl_net_ll_poll value */
+static inline bool busy_loop_timeout(unsigned long start_time)
 {
-	skb->napi_id = napi->napi_id;
-}
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned long bp_usec = READ_ONCE(sysctl_net_busy_poll);
 
+	if (bp_usec) {
+		unsigned long end_time = start_time + bp_usec;
+		unsigned long now = busy_loop_current_time();
 
-#else /* CONFIG_NET_RX_BUSY_POLL */
-static inline unsigned long net_busy_loop_on(void)
-{
-	return 0;
+		return time_after(now, end_time);
+	}
+#endif
+	return true;
 }
 
-static inline unsigned long busy_loop_end_time(void)
+static inline bool sk_busy_loop_timeout(struct sock *sk,
+					unsigned long start_time)
 {
-	return 0;
-}
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned long bp_usec = READ_ONCE(sk->sk_ll_usec);
 
-static inline bool sk_can_busy_loop(struct sock *sk)
-{
-	return false;
-}
+	if (bp_usec) {
+		unsigned long end_time = start_time + bp_usec;
+		unsigned long now = busy_loop_current_time();
 
-static inline void skb_mark_napi_id(struct sk_buff *skb,
-				    struct napi_struct *napi)
-{
+		return time_after(now, end_time);
+	}
+#endif
+	return true;
 }
 
-static inline bool busy_loop_timeout(unsigned long end_time)
+static inline void sk_busy_loop(struct sock *sk, int nonblock)
 {
-	return true;
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned int napi_id = READ_ONCE(sk->sk_napi_id);
+
+	if (napi_id >= MIN_NAPI_ID)
+		napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk);
+#endif
 }
 
-static inline bool sk_busy_loop(struct sock *sk, int nonblock)
+/* used in the NIC receive handler to mark the skb */
+static inline void skb_mark_napi_id(struct sk_buff *skb,
+				    struct napi_struct *napi)
 {
-	return false;
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	skb->napi_id = napi->napi_id;
+#endif
 }
 
-#endif /* CONFIG_NET_RX_BUSY_POLL */
-
 /* used in the protocol hanlder to propagate the napi_id to the socket */
 static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
 {
diff --git a/include/net/devlink.h b/include/net/devlink.h
index d29e5fc82582..24de13f8c94f 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -25,6 +25,8 @@ struct devlink {
 	struct list_head list;
 	struct list_head port_list;
 	struct list_head sb_list;
+	struct list_head dpipe_table_list;
+	struct devlink_dpipe_headers *dpipe_headers;
 	const struct devlink_ops *ops;
 	struct device *dev;
 	possible_net_t _net;
@@ -49,6 +51,178 @@ struct devlink_sb_pool_info {
 	enum devlink_sb_threshold_type threshold_type;
 };
 
+/**
+ * struct devlink_dpipe_field - dpipe field object
+ * @name: field name
+ * @id: index inside the headers field array
+ * @bitwidth: bitwidth
+ * @mapping_type: mapping type
+ */
+struct devlink_dpipe_field {
+	const char *name;
+	unsigned int id;
+	unsigned int bitwidth;
+	enum devlink_dpipe_field_mapping_type mapping_type;
+};
+
+/**
+ * struct devlink_dpipe_header - dpipe header object
+ * @name: header name
+ * @id: index, global/local detrmined by global bit
+ * @fields: fields
+ * @fields_count: number of fields
+ * @global: indicates if header is shared like most protocol header
+ *	    or driver specific
+ */
+struct devlink_dpipe_header {
+	const char *name;
+	unsigned int id;
+	struct devlink_dpipe_field *fields;
+	unsigned int fields_count;
+	bool global;
+};
+
+/**
+ * struct devlink_dpipe_match - represents match operation
+ * @type: type of match
+ * @header_index: header index (packets can have several headers of same
+ *		  type like in case of tunnels)
+ * @header: header
+ * @fieled_id: field index
+ */
+struct devlink_dpipe_match {
+	enum devlink_dpipe_match_type type;
+	unsigned int header_index;
+	struct devlink_dpipe_header *header;
+	unsigned int field_id;
+};
+
+/**
+ * struct devlink_dpipe_action - represents action operation
+ * @type: type of action
+ * @header_index: header index (packets can have several headers of same
+ *		  type like in case of tunnels)
+ * @header: header
+ * @fieled_id: field index
+ */
+struct devlink_dpipe_action {
+	enum devlink_dpipe_action_type type;
+	unsigned int header_index;
+	struct devlink_dpipe_header *header;
+	unsigned int field_id;
+};
+
+/**
+ * struct devlink_dpipe_value - represents value of match/action
+ * @action: action
+ * @match: match
+ * @mapping_value: in case the field has some mapping this value
+ *                 specified the mapping value
+ * @mapping_valid: specify if mapping value is valid
+ * @value_size: value size
+ * @value: value
+ * @mask: bit mask
+ */
+struct devlink_dpipe_value {
+	union {
+		struct devlink_dpipe_action *action;
+		struct devlink_dpipe_match *match;
+	};
+	unsigned int mapping_value;
+	bool mapping_valid;
+	unsigned int value_size;
+	void *value;
+	void *mask;
+};
+
+/**
+ * struct devlink_dpipe_entry - table entry object
+ * @index: index of the entry in the table
+ * @match_values: match values
+ * @matche_values_count: count of matches tuples
+ * @action_values: actions values
+ * @action_values_count: count of actions values
+ * @counter: value of counter
+ * @counter_valid: Specify if value is valid from hardware
+ */
+struct devlink_dpipe_entry {
+	u64 index;
+	struct devlink_dpipe_value *match_values;
+	unsigned int match_values_count;
+	struct devlink_dpipe_value *action_values;
+	unsigned int action_values_count;
+	u64 counter;
+	bool counter_valid;
+};
+
+/**
+ * struct devlink_dpipe_dump_ctx - context provided to driver in order
+ *				   to dump
+ * @info: info
+ * @cmd: devlink command
+ * @skb: skb
+ * @nest: top attribute
+ * @hdr: hdr
+ */
+struct devlink_dpipe_dump_ctx {
+	struct genl_info *info;
+	enum devlink_command cmd;
+	struct sk_buff *skb;
+	struct nlattr *nest;
+	void *hdr;
+};
+
+struct devlink_dpipe_table_ops;
+
+/**
+ * struct devlink_dpipe_table - table object
+ * @priv: private
+ * @name: table name
+ * @size: maximum number of entries
+ * @counters_enabled: indicates if counters are active
+ * @counter_control_extern: indicates if counter control is in dpipe or
+ *			    external tool
+ * @table_ops: table operations
+ * @rcu: rcu
+ */
+struct devlink_dpipe_table {
+	void *priv;
+	struct list_head list;
+	const char *name;
+	u64 size;
+	bool counters_enabled;
+	bool counter_control_extern;
+	struct devlink_dpipe_table_ops *table_ops;
+	struct rcu_head rcu;
+};
+
+/**
+ * struct devlink_dpipe_table_ops - dpipe_table ops
+ * @actions_dump - dumps all tables actions
+ * @matches_dump - dumps all tables matches
+ * @entries_dump - dumps all active entries in the table
+ * @counters_set_update - when changing the counter status hardware sync
+ *			  maybe needed to allocate/free counter related
+ *			  resources
+ */
+struct devlink_dpipe_table_ops {
+	int (*actions_dump)(void *priv, struct sk_buff *skb);
+	int (*matches_dump)(void *priv, struct sk_buff *skb);
+	int (*entries_dump)(void *priv, bool counters_enabled,
+			    struct devlink_dpipe_dump_ctx *dump_ctx);
+	int (*counters_set_update)(void *priv, bool enable);
+};
+
+/**
+ * struct devlink_dpipe_headers - dpipe headers
+ * @headers - header array can be shared (global bit) or driver specific
+ * @headers_count - count of headers
+ */
+struct devlink_dpipe_headers {
+	struct devlink_dpipe_header **headers;
+	unsigned int headers_count;
+};
+
 struct devlink_ops {
 	int (*port_type_set)(struct devlink_port *devlink_port,
 			     enum devlink_port_type port_type);
@@ -132,6 +306,26 @@ int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
 			u16 egress_pools_count, u16 ingress_tc_count,
 			u16 egress_tc_count);
 void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index);
+int devlink_dpipe_table_register(struct devlink *devlink,
+				 const char *table_name,
+				 struct devlink_dpipe_table_ops *table_ops,
+				 void *priv, u64 size,
+				 bool counter_control_extern);
+void devlink_dpipe_table_unregister(struct devlink *devlink,
+				    const char *table_name);
+int devlink_dpipe_headers_register(struct devlink *devlink,
+				   struct devlink_dpipe_headers *dpipe_headers);
+void devlink_dpipe_headers_unregister(struct devlink *devlink);
+bool devlink_dpipe_table_counter_enabled(struct devlink *devlink,
+					 const char *table_name);
+int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx);
+int devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx,
+				   struct devlink_dpipe_entry *entry);
+int devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx);
+int devlink_dpipe_action_put(struct sk_buff *skb,
+			     struct devlink_dpipe_action *action);
+int devlink_dpipe_match_put(struct sk_buff *skb,
+			    struct devlink_dpipe_match *match);
 
 #else
 
@@ -200,6 +394,71 @@ static inline void devlink_sb_unregister(struct devlink *devlink,
 {
 }
 
+static inline int
+devlink_dpipe_table_register(struct devlink *devlink,
+			     const char *table_name,
+			     struct devlink_dpipe_table_ops *table_ops,
+			     void *priv, u64 size,
+			     bool counter_control_extern)
+{
+	return 0;
+}
+
+static inline void devlink_dpipe_table_unregister(struct devlink *devlink,
+						  const char *table_name)
+{
+}
+
+static inline int devlink_dpipe_headers_register(struct devlink *devlink,
+						 struct devlink_dpipe_headers *
+						 dpipe_headers)
+{
+	return 0;
+}
+
+static inline void devlink_dpipe_headers_unregister(struct devlink *devlink)
+{
+}
+
+static inline bool devlink_dpipe_table_counter_enabled(struct devlink *devlink,
+						       const char *table_name)
+{
+	return false;
+}
+
+static inline int
+devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+	return 0;
+}
+
+static inline int
+devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx,
+			       struct devlink_dpipe_entry *entry)
+{
+	return 0;
+}
+
+static inline int
+devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+	return 0;
+}
+
+static inline int
+devlink_dpipe_action_put(struct sk_buff *skb,
+			 struct devlink_dpipe_action *action)
+{
+	return 0;
+}
+
+static inline int
+devlink_dpipe_match_put(struct sk_buff *skb,
+			struct devlink_dpipe_match *match)
+{
+	return 0;
+}
+
 #endif
 
 #endif /* _NET_DEVLINK_H_ */
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 4e13e695f025..ffe56cc338fe 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -19,6 +19,7 @@
 #include <linux/workqueue.h>
 #include <linux/of.h>
 #include <linux/ethtool.h>
+#include <net/devlink.h>
 
 struct tc_action;
 struct phy_device;
@@ -182,6 +183,7 @@ struct dsa_port {
 	unsigned int		ageing_time;
 	u8			stp_state;
 	struct net_device	*bridge_dev;
+	struct devlink_port	devlink_port;
 };
 
 struct dsa_switch {
@@ -233,6 +235,13 @@ struct dsa_switch {
 	u32			phys_mii_mask;
 	struct mii_bus		*slave_mii_bus;
 
+	/* Ageing Time limits in msecs */
+	unsigned int ageing_time_min;
+	unsigned int ageing_time_max;
+
+	/* devlink used to represent this switch device */
+	struct devlink		*devlink;
+
 	/* Dynamically allocated ports, keep last */
 	size_t num_ports;
 	struct dsa_port ports[];
@@ -248,6 +257,11 @@ static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p)
 	return !!((ds->dsa_port_mask) & (1 << p));
 }
 
+static inline bool dsa_is_normal_port(struct dsa_switch *ds, int p)
+{
+	return !dsa_is_cpu_port(ds, p) && !dsa_is_dsa_port(ds, p);
+}
+
 static inline bool dsa_is_port_initialized(struct dsa_switch *ds, int p)
 {
 	return ds->enabled_port_mask & (1 << p) && ds->ports[p].netdev;
@@ -442,6 +456,14 @@ struct dsa_switch_ops {
 				   bool ingress);
 	void	(*port_mirror_del)(struct dsa_switch *ds, int port,
 				   struct dsa_mall_mirror_tc_entry *mirror);
+
+	/*
+	 * Cross-chip operations
+	 */
+	int	(*crosschip_bridge_join)(struct dsa_switch *ds, int sw_index,
+					 int port, struct net_device *br);
+	void	(*crosschip_bridge_leave)(struct dsa_switch *ds, int sw_index,
+					  int port, struct net_device *br);
 };
 
 struct dsa_switch_driver {
@@ -459,6 +481,15 @@ static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst)
 	return dst->rcv != NULL;
 }
 
+static inline bool netdev_uses_dsa(struct net_device *dev)
+{
+#if IS_ENABLED(CONFIG_NET_DSA)
+	if (dev->dsa_ptr != NULL)
+		return dsa_uses_tagged_protocol(dev->dsa_ptr);
+#endif
+	return false;
+}
+
 struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n);
 void dsa_unregister_switch(struct dsa_switch *ds);
 int dsa_register_switch(struct dsa_switch *ds, struct device *dev);
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 8dbfdf728cd8..1243b9c7694e 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -141,6 +141,7 @@ int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags,
 		     struct fib_lookup_arg *);
 int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table,
 			 u32 flags);
+bool fib_rule_matchall(const struct fib_rule *rule);
 
 int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh);
 int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh);
diff --git a/include/net/flow.h b/include/net/flow.h
index 6984f1913dc1..bae198b3039e 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -202,7 +202,7 @@ static inline struct flowi *flowidn_to_flowi(struct flowidn *fldn)
 
 typedef unsigned long flow_compare_t;
 
-static inline size_t flow_key_size(u16 family)
+static inline unsigned int flow_key_size(u16 family)
 {
 	switch (family) {
 	case AF_INET:
diff --git a/include/net/flowcache.h b/include/net/flowcache.h
index 9caf3bfc8d2d..51eb971e8973 100644
--- a/include/net/flowcache.h
+++ b/include/net/flowcache.h
@@ -8,7 +8,7 @@
 
 struct flow_cache_percpu {
 	struct hlist_head		*hash_table;
-	int				hash_count;
+	unsigned int			hash_count;
 	u32				hash_rnd;
 	int				hash_rnd_recalc;
 	struct tasklet_struct		flush_tasklet;
@@ -18,8 +18,8 @@ struct flow_cache {
 	u32				hash_shift;
 	struct flow_cache_percpu __percpu *percpu;
 	struct hlist_node		node;
-	int				low_watermark;
-	int				high_watermark;
+	unsigned int			low_watermark;
+	unsigned int			high_watermark;
 	struct timer_list		rnd_timer;
 };
 #endif	/* _NET_FLOWCACHE_H */
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 368bb4024b78..6692c5758b33 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -213,6 +213,11 @@ struct fib_entry_notifier_info {
 	u32 tb_id;
 };
 
+struct fib_rule_notifier_info {
+	struct fib_notifier_info info; /* must be first */
+	struct fib_rule *rule;
+};
+
 struct fib_nh_notifier_info {
 	struct fib_notifier_info info; /* must be first */
 	struct fib_nh *fib_nh;
@@ -232,9 +237,21 @@ enum fib_event_type {
 int register_fib_notifier(struct notifier_block *nb,
 			  void (*cb)(struct notifier_block *nb));
 int unregister_fib_notifier(struct notifier_block *nb);
+int call_fib_notifier(struct notifier_block *nb, struct net *net,
+		      enum fib_event_type event_type,
+		      struct fib_notifier_info *info);
 int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
 		       struct fib_notifier_info *info);
 
+void fib_notify(struct net *net, struct notifier_block *nb);
+#ifdef CONFIG_IP_MULTIPLE_TABLES
+void fib_rules_notify(struct net *net, struct notifier_block *nb);
+#else
+static inline void fib_rules_notify(struct net *net, struct notifier_block *nb)
+{
+}
+#endif
+
 struct fib_table {
 	struct hlist_node	tb_hlist;
 	u32			tb_id;
@@ -299,6 +316,11 @@ static inline int fib_lookup(struct net *net, const struct flowi4 *flp,
 	return err;
 }
 
+static inline bool fib4_rule_default(const struct fib_rule *rule)
+{
+	return true;
+}
+
 #else /* CONFIG_IP_MULTIPLE_TABLES */
 int __net_init fib4_rules_init(struct net *net);
 void __net_exit fib4_rules_exit(struct net *net);
@@ -343,6 +365,8 @@ out:
 	return err;
 }
 
+bool fib4_rule_default(const struct fib_rule *rule);
+
 #endif /* CONFIG_IP_MULTIPLE_TABLES */
 
 /* Exported by fib_frontend.c */
@@ -371,17 +395,13 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force);
 int fib_sync_down_addr(struct net_device *dev, __be32 local);
 int fib_sync_up(struct net_device *dev, unsigned int nh_flags);
 
-extern u32 fib_multipath_secret __read_mostly;
-
-static inline int fib_multipath_hash(__be32 saddr, __be32 daddr)
-{
-	return jhash_2words((__force u32)saddr, (__force u32)daddr,
-			    fib_multipath_secret) >> 1;
-}
-
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
+		       const struct sk_buff *skb);
+#endif
 void fib_select_multipath(struct fib_result *res, int hash);
 void fib_select_path(struct net *net, struct fib_result *res,
-		     struct flowi4 *fl4, int mp_hash);
+		     struct flowi4 *fl4, const struct sk_buff *skb);
 
 /* Exported by fib_trie.c */
 void fib_trie_init(void);
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 7bdfa7d78363..8a4a57b887fb 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -12,6 +12,8 @@
 #include <linux/list.h>                 /* for struct list_head */
 #include <linux/spinlock.h>             /* for struct rwlock_t */
 #include <linux/atomic.h>               /* for struct atomic_t */
+#include <linux/refcount.h>             /* for struct refcount_t */
+
 #include <linux/compiler.h>
 #include <linux/timer.h>
 #include <linux/bug.h>
@@ -525,7 +527,7 @@ struct ip_vs_conn {
 	struct netns_ipvs	*ipvs;
 
 	/* counter and timer */
-	atomic_t		refcnt;		/* reference count */
+	refcount_t		refcnt;		/* reference count */
 	struct timer_list	timer;		/* Expiration timer */
 	volatile unsigned long	timeout;	/* timeout */
 
@@ -667,7 +669,7 @@ struct ip_vs_dest {
 	atomic_t		conn_flags;	/* flags to copy to conn */
 	atomic_t		weight;		/* server weight */
 
-	atomic_t		refcnt;		/* reference counter */
+	refcount_t		refcnt;		/* reference counter */
 	struct ip_vs_stats      stats;          /* statistics */
 	unsigned long		idle_start;	/* start time, jiffies */
 
@@ -1211,14 +1213,14 @@ struct ip_vs_conn * ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af,
  */
 static inline bool __ip_vs_conn_get(struct ip_vs_conn *cp)
 {
-	return atomic_inc_not_zero(&cp->refcnt);
+	return refcount_inc_not_zero(&cp->refcnt);
 }
 
 /* put back the conn without restarting its timer */
 static inline void __ip_vs_conn_put(struct ip_vs_conn *cp)
 {
 	smp_mb__before_atomic();
-	atomic_dec(&cp->refcnt);
+	refcount_dec(&cp->refcnt);
 }
 void ip_vs_conn_put(struct ip_vs_conn *cp);
 void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport);
@@ -1410,18 +1412,18 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp);
 
 static inline void ip_vs_dest_hold(struct ip_vs_dest *dest)
 {
-	atomic_inc(&dest->refcnt);
+	refcount_inc(&dest->refcnt);
 }
 
 static inline void ip_vs_dest_put(struct ip_vs_dest *dest)
 {
 	smp_mb__before_atomic();
-	atomic_dec(&dest->refcnt);
+	refcount_dec(&dest->refcnt);
 }
 
 static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest)
 {
-	if (atomic_dec_and_test(&dest->refcnt))
+	if (refcount_dec_and_test(&dest->refcnt))
 		kfree(dest);
 }
 
diff --git a/include/net/mpls_iptunnel.h b/include/net/mpls_iptunnel.h
index 179253f9dcfd..9d22bf67ac86 100644
--- a/include/net/mpls_iptunnel.h
+++ b/include/net/mpls_iptunnel.h
@@ -14,11 +14,12 @@
 #ifndef _NET_MPLS_IPTUNNEL_H
 #define _NET_MPLS_IPTUNNEL_H 1
 
-#define MAX_NEW_LABELS 2
-
 struct mpls_iptunnel_encap {
-	u32	label[MAX_NEW_LABELS];
 	u8	labels;
+	u8	ttl_propagate;
+	u8	default_ttl;
+	u8	reserved1;
+	u32	label[0];
 };
 
 static inline struct mpls_iptunnel_encap *mpls_lwtunnel_encap(struct lwtunnel_state *lwtstate)
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 8a0214654b6b..1036c902d2c9 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -439,8 +439,10 @@ void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
  *	IGMP
  */
 int igmp6_init(void);
+int igmp6_late_init(void);
 
 void igmp6_cleanup(void);
+void igmp6_late_cleanup(void);
 
 int igmp6_event_query(struct sk_buff *skb);
 
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 5ebf69491160..9496179c7b4e 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -314,7 +314,8 @@ static inline struct neighbour *neigh_create(struct neigh_table *tbl,
 }
 void neigh_destroy(struct neighbour *neigh);
 int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb);
-int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags);
+int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags,
+		 u32 nlmsg_pid);
 void __neigh_set_probe_once(struct neighbour *neigh);
 void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev);
 int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index af8fe8a909dc..fe80bb48ab1f 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -27,6 +27,7 @@
 #include <net/netns/nftables.h>
 #include <net/netns/xfrm.h>
 #include <net/netns/mpls.h>
+#include <net/netns/can.h>
 #include <linux/ns_common.h>
 #include <linux/idr.h>
 #include <linux/skbuff.h>
@@ -141,6 +142,9 @@ struct net {
 #if IS_ENABLED(CONFIG_MPLS)
 	struct netns_mpls	mpls;
 #endif
+#if IS_ENABLED(CONFIG_CAN)
+	struct netns_can	can;
+#endif
 	struct sock		*diag_nlsk;
 	atomic_t		fnhe_genid;
 };
diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index 5ed33ea4718e..65cc2cb005d9 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -5,6 +5,8 @@
 #ifndef _NF_CONNTRACK_EXPECT_H
 #define _NF_CONNTRACK_EXPECT_H
 
+#include <linux/refcount.h>
+
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 
@@ -37,7 +39,7 @@ struct nf_conntrack_expect {
 	struct timer_list timeout;
 
 	/* Usage count. */
-	atomic_t use;
+	refcount_t use;
 
 	/* Flags */
 	unsigned int flags;
diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h
index 5cc5e9e6171a..d40b89355fdd 100644
--- a/include/net/netfilter/nf_conntrack_timeout.h
+++ b/include/net/netfilter/nf_conntrack_timeout.h
@@ -4,6 +4,7 @@
 #include <net/net_namespace.h>
 #include <linux/netfilter/nf_conntrack_common.h>
 #include <linux/netfilter/nf_conntrack_tuple_common.h>
+#include <linux/refcount.h>
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_extend.h>
 
@@ -12,7 +13,7 @@
 struct ctnl_timeout {
 	struct list_head	head;
 	struct rcu_head		rcu_head;
-	atomic_t		refcnt;
+	refcount_t		refcnt;
 	char			name[CTNL_TIMEOUT_NAME_MAX];
 	__u16			l3num;
 	struct nf_conntrack_l4proto *l4proto;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 0136028652bd..f713a053f89d 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -413,10 +413,11 @@ static inline struct nft_set *nft_set_container_of(const void *priv)
 	return (void *)priv - offsetof(struct nft_set, data);
 }
 
-struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
-				     const struct nlattr *nla, u8 genmask);
-struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
-					  const struct nlattr *nla, u8 genmask);
+struct nft_set *nft_set_lookup(const struct net *net,
+			       const struct nft_table *table,
+			       const struct nlattr *nla_set_name,
+			       const struct nlattr *nla_set_id,
+			       u8 genmask);
 
 static inline unsigned long nft_set_gc_interval(const struct nft_set *set)
 {
@@ -1044,7 +1045,8 @@ struct nft_object_type {
 	unsigned int			maxattr;
 	struct module			*owner;
 	const struct nla_policy		*policy;
-	int				(*init)(const struct nlattr * const tb[],
+	int				(*init)(const struct nft_ctx *ctx,
+						const struct nlattr *const tb[],
 						struct nft_object *obj);
 	void				(*destroy)(struct nft_object *obj);
 	int				(*dump)(struct sk_buff *skb,
diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h
index 5ceb2205e4e3..381af9469e6a 100644
--- a/include/net/netfilter/nft_fib.h
+++ b/include/net/netfilter/nft_fib.h
@@ -32,6 +32,6 @@ void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
 void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
 		   const struct nft_pktinfo *pkt);
 
-void nft_fib_store_result(void *reg, enum nft_fib_result r,
+void nft_fib_store_result(void *reg, const struct nft_fib *priv,
 			  const struct nft_pktinfo *pkt, int index);
 #endif
diff --git a/include/net/netns/can.h b/include/net/netns/can.h
new file mode 100644
index 000000000000..e8beba772f1a
--- /dev/null
+++ b/include/net/netns/can.h
@@ -0,0 +1,31 @@
+/*
+ * can in net namespaces
+ */
+
+#ifndef __NETNS_CAN_H__
+#define __NETNS_CAN_H__
+
+#include <linux/spinlock.h>
+
+struct dev_rcv_lists;
+
+struct netns_can {
+#if IS_ENABLED(CONFIG_PROC_FS)
+	struct proc_dir_entry *proc_dir;
+	struct proc_dir_entry *pde_version;
+	struct proc_dir_entry *pde_stats;
+	struct proc_dir_entry *pde_reset_stats;
+	struct proc_dir_entry *pde_rcvlist_all;
+	struct proc_dir_entry *pde_rcvlist_fil;
+	struct proc_dir_entry *pde_rcvlist_inv;
+	struct proc_dir_entry *pde_rcvlist_sff;
+	struct proc_dir_entry *pde_rcvlist_eff;
+	struct proc_dir_entry *pde_rcvlist_err;
+#endif
+
+	/* receive filters subscribed for 'all' CAN devices */
+	struct dev_rcv_lists *can_rx_alldev_list;
+	spinlock_t can_rcvlists_lock;
+};
+
+#endif /* __NETNS_CAN_H__ */
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 622d2da27135..cd686c4fb32d 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -33,7 +33,6 @@ struct inet_timewait_death_row {
 	atomic_t		tw_count;
 
 	struct inet_hashinfo 	*hashinfo ____cacheline_aligned_in_smp;
-	int			sysctl_tw_recycle;
 	int			sysctl_max_tw_buckets;
 };
 
@@ -96,6 +95,8 @@ struct netns_ipv4 {
 	/* Shall we try to damage output packets if routing dev changes? */
 	int sysctl_ip_dynaddr;
 	int sysctl_ip_early_demux;
+	int sysctl_tcp_early_demux;
+	int sysctl_udp_early_demux;
 
 	int sysctl_fwmark_reflect;
 	int sysctl_tcp_fwmark_accept;
@@ -152,6 +153,7 @@ struct netns_ipv4 {
 #endif
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	int sysctl_fib_multipath_use_neigh;
+	int sysctl_fib_multipath_hash_policy;
 #endif
 
 	unsigned int	fib_seq;	/* protected by rtnl_mutex */
diff --git a/include/net/netns/mpls.h b/include/net/netns/mpls.h
index d29203651c01..6608b3693385 100644
--- a/include/net/netns/mpls.h
+++ b/include/net/netns/mpls.h
@@ -9,8 +9,11 @@ struct mpls_route;
 struct ctl_table_header;
 
 struct netns_mpls {
+	int ip_ttl_propagate;
+	int default_ttl;
 	size_t platform_labels;
 	struct mpls_route __rcu * __rcu *platform_label;
+
 	struct ctl_table_header *ctl;
 };
 
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index f1b76b8e6d2d..bec46f63f10c 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -92,7 +92,7 @@ int unregister_qdisc(struct Qdisc_ops *qops);
 void qdisc_get_default(char *id, size_t len);
 int qdisc_set_default(const char *id);
 
-void qdisc_hash_add(struct Qdisc *q);
+void qdisc_hash_add(struct Qdisc *q, bool invisible);
 void qdisc_hash_del(struct Qdisc *q);
 struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle);
 struct Qdisc *qdisc_lookup_class(struct net_device *dev, u32 handle);
diff --git a/include/net/protocol.h b/include/net/protocol.h
index bf36ca34af7a..65ba335b0e7e 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -40,6 +40,7 @@
 /* This is used to register protocols. */
 struct net_protocol {
 	void			(*early_demux)(struct sk_buff *skb);
+	void                    (*early_demux_handler)(struct sk_buff *skb);
 	int			(*handler)(struct sk_buff *skb);
 	void			(*err_handler)(struct sk_buff *skb, u32 info);
 	unsigned int		no_policy:1,
@@ -54,7 +55,7 @@ struct net_protocol {
 #if IS_ENABLED(CONFIG_IPV6)
 struct inet6_protocol {
 	void	(*early_demux)(struct sk_buff *skb);
-
+	void    (*early_demux_handler)(struct sk_buff *skb);
 	int	(*handler)(struct sk_buff *skb);
 
 	void	(*err_handler)(struct sk_buff *skb,
@@ -92,12 +93,12 @@ struct inet_protosw {
 #define INET_PROTOSW_PERMANENT 0x02  /* Permanent protocols are unremovable. */
 #define INET_PROTOSW_ICSK      0x04  /* Is this an inet_connection_sock? */
 
-extern const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS];
+extern struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS];
 extern const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS];
 extern const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS];
 
 #if IS_ENABLED(CONFIG_IPV6)
-extern const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS];
+extern struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS];
 #endif
 
 int inet_add_protocol(const struct net_protocol *prot, unsigned char num);
diff --git a/include/net/route.h b/include/net/route.h
index c0874c87c173..2cc0e14c6359 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -113,13 +113,13 @@ struct in_device;
 int ip_rt_init(void);
 void rt_cache_flush(struct net *net);
 void rt_flush_dev(struct net_device *dev);
-struct rtable *__ip_route_output_key_hash(struct net *, struct flowi4 *flp,
-					  int mp_hash);
+struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *flp,
+					  const struct sk_buff *skb);
 
 static inline struct rtable *__ip_route_output_key(struct net *net,
 						   struct flowi4 *flp)
 {
-	return __ip_route_output_key_hash(net, flp, -1);
+	return __ip_route_output_key_hash(net, flp, NULL);
 }
 
 struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index aeec4086afb2..65d502610314 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -66,6 +66,7 @@ struct Qdisc {
 #define TCQ_F_NOPARENT		0x40 /* root of its hierarchy :
 				      * qdisc_tree_decrease_qlen() should stop.
 				      */
+#define TCQ_F_INVISIBLE		0x80 /* invisible by default in dump */
 	u32			limit;
 	const struct Qdisc_ops	*ops;
 	struct qdisc_size_table	__rcu *stab;
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index b6f682ec184a..47113f2c4b0a 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -293,6 +293,22 @@ struct sctp_chunk *sctp_process_strreset_inreq(
 				struct sctp_association *asoc,
 				union sctp_params param,
 				struct sctp_ulpevent **evp);
+struct sctp_chunk *sctp_process_strreset_tsnreq(
+				struct sctp_association *asoc,
+				union sctp_params param,
+				struct sctp_ulpevent **evp);
+struct sctp_chunk *sctp_process_strreset_addstrm_out(
+				struct sctp_association *asoc,
+				union sctp_params param,
+				struct sctp_ulpevent **evp);
+struct sctp_chunk *sctp_process_strreset_addstrm_in(
+				struct sctp_association *asoc,
+				union sctp_params param,
+				struct sctp_ulpevent **evp);
+struct sctp_chunk *sctp_process_strreset_resp(
+				struct sctp_association *asoc,
+				union sctp_params param,
+				struct sctp_ulpevent **evp);
 
 /* Prototypes for statetable processing. */
 
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 138f8615acf0..b751399aa6b7 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1315,6 +1315,8 @@ struct sctp_inithdr_host {
 struct sctp_stream_out {
 	__u16	ssn;
 	__u8	state;
+	__u64	abandoned_unsent[SCTP_PR_INDEX(MAX) + 1];
+	__u64	abandoned_sent[SCTP_PR_INDEX(MAX) + 1];
 };
 
 struct sctp_stream_in {
diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h
index 324b5965fc4d..1060494ac230 100644
--- a/include/net/sctp/ulpevent.h
+++ b/include/net/sctp/ulpevent.h
@@ -132,6 +132,14 @@ struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event(
 	const struct sctp_association *asoc, __u16 flags,
 	__u16 stream_num, __u16 *stream_list, gfp_t gfp);
 
+struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event(
+	const struct sctp_association *asoc, __u16 flags,
+	 __u32 local_tsn, __u32 remote_tsn, gfp_t gfp);
+
+struct sctp_ulpevent *sctp_ulpevent_make_stream_change_event(
+	const struct sctp_association *asoc, __u16 flags,
+	__u32 strchange_instrms, __u32 strchange_outstrms, gfp_t gfp);
+
 void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event,
 				   struct msghdr *);
 void sctp_ulpevent_read_rcvinfo(const struct sctp_ulpevent *event,
diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h
index 0caee631a836..fe236b3429f0 100644
--- a/include/net/secure_seq.h
+++ b/include/net/secure_seq.h
@@ -6,10 +6,10 @@
 u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
 u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport);
-u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
+u32 secure_tcp_seq_and_tsoff(__be32 saddr, __be32 daddr,
+			     __be16 sport, __be16 dport, u32 *tsoff);
+u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr,
 			       __be16 sport, __be16 dport, u32 *tsoff);
-u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
-				 __be16 sport, __be16 dport, u32 *tsoff);
 u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
 				__be16 sport, __be16 dport);
 u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
diff --git a/include/net/sock.h b/include/net/sock.h
index 03252d53975d..66349e49d468 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1783,11 +1783,8 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst)
 
 	sk_tx_queue_clear(sk);
 	sk->sk_dst_pending_confirm = 0;
-	/*
-	 * This can be called while sk is owned by the caller only,
-	 * with no state that can be checked in a rcu_dereference_check() cond
-	 */
-	old_dst = rcu_dereference_raw(sk->sk_dst_cache);
+	old_dst = rcu_dereference_protected(sk->sk_dst_cache,
+					    lockdep_sock_is_held(sk));
 	rcu_assign_pointer(sk->sk_dst_cache, dst);
 	dst_release(old_dst);
 }
@@ -2242,6 +2239,7 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
 void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 			      struct sk_buff *skb);
 
+#define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC)
 static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 					  struct sk_buff *skb)
 {
@@ -2252,8 +2250,10 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 
 	if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
 		__sock_recv_ts_and_drops(msg, sk, skb);
-	else
+	else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
 		sk->sk_stamp = skb->tstamp;
+	else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP))
+		sk->sk_stamp = 0;
 }
 
 void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags);
@@ -2365,6 +2365,8 @@ bool sk_ns_capable(const struct sock *sk,
 bool sk_capable(const struct sock *sk, int cap);
 bool sk_net_capable(const struct sock *sk, int cap);
 
+void sk_get_meminfo(const struct sock *sk, u32 *meminfo);
+
 extern __u32 sysctl_wmem_max;
 extern __u32 sysctl_rmem_max;
 
diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h
index dfbd6ee0bc7c..a46c3f2ace70 100644
--- a/include/net/tc_act/tc_pedit.h
+++ b/include/net/tc_act/tc_pedit.h
@@ -2,6 +2,7 @@
 #define __NET_TC_PED_H
 
 #include <net/act_api.h>
+#include <linux/tc_act/tc_pedit.h>
 
 struct tcf_pedit_key_ex {
 	enum pedit_header_type htype;
@@ -17,4 +18,48 @@ struct tcf_pedit {
 };
 #define to_pedit(a) ((struct tcf_pedit *)a)
 
+static inline bool is_tcf_pedit(const struct tc_action *a)
+{
+#ifdef CONFIG_NET_CLS_ACT
+	if (a->ops && a->ops->type == TCA_ACT_PEDIT)
+		return true;
+#endif
+	return false;
+}
+
+static inline int tcf_pedit_nkeys(const struct tc_action *a)
+{
+	return to_pedit(a)->tcfp_nkeys;
+}
+
+static inline u32 tcf_pedit_htype(const struct tc_action *a, int index)
+{
+	if (to_pedit(a)->tcfp_keys_ex)
+		return to_pedit(a)->tcfp_keys_ex[index].htype;
+
+	return TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK;
+}
+
+static inline u32 tcf_pedit_cmd(const struct tc_action *a, int index)
+{
+	if (to_pedit(a)->tcfp_keys_ex)
+		return to_pedit(a)->tcfp_keys_ex[index].cmd;
+
+	return __PEDIT_CMD_MAX;
+}
+
+static inline u32 tcf_pedit_mask(const struct tc_action *a, int index)
+{
+	return to_pedit(a)->tcfp_keys[index].mask;
+}
+
+static inline u32 tcf_pedit_val(const struct tc_action *a, int index)
+{
+	return to_pedit(a)->tcfp_keys[index].val;
+}
+
+static inline u32 tcf_pedit_offset(const struct tc_action *a, int index)
+{
+	return to_pedit(a)->tcfp_keys[index].off;
+}
 #endif /* __NET_TC_PED_H */
diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h
index 48cca321ee6c..9690c047b6cf 100644
--- a/include/net/tc_act/tc_vlan.h
+++ b/include/net/tc_act/tc_vlan.h
@@ -49,4 +49,9 @@ static inline __be16 tcf_vlan_push_proto(const struct tc_action *a)
 	return to_vlan(a)->tcfv_push_proto;
 }
 
+static inline u8 tcf_vlan_push_prio(const struct tc_action *a)
+{
+	return to_vlan(a)->tcfv_push_prio;
+}
+
 #endif /* __NET_TC_VLAN_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6ec4ea652f3f..cc6ae0a95201 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -78,6 +78,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 /* Maximal number of ACKs sent quickly to accelerate slow-start. */
 #define TCP_MAX_QUICKACKS	16U
 
+/* Maximal number of window scale according to RFC1323 */
+#define TCP_MAX_WSCALE		14U
+
 /* urg_data states */
 #define TCP_URG_VALID	0x0100
 #define TCP_URG_NOTYET	0x0200
@@ -406,11 +409,7 @@ void tcp_clear_retrans(struct tcp_sock *tp);
 void tcp_update_metrics(struct sock *sk);
 void tcp_init_metrics(struct sock *sk);
 void tcp_metrics_init(void);
-bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst,
-			bool paws_check, bool timestamps);
-bool tcp_remember_stamp(struct sock *sk);
-bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw);
-void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst);
+bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
 void tcp_disable_fack(struct tcp_sock *tp);
 void tcp_close(struct sock *sk, long timeout);
 void tcp_init_sock(struct sock *sk);
@@ -1252,9 +1251,11 @@ void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd,
 
 static inline int tcp_win_from_space(int space)
 {
-	return sysctl_tcp_adv_win_scale<=0 ?
-		(space>>(-sysctl_tcp_adv_win_scale)) :
-		space - (space>>sysctl_tcp_adv_win_scale);
+	int tcp_adv_win_scale = sysctl_tcp_adv_win_scale;
+
+	return tcp_adv_win_scale <= 0 ?
+		(space>>(-tcp_adv_win_scale)) :
+		space - (space>>tcp_adv_win_scale);
 }
 
 /* Note: caller must be prepared to deal with negative returns */
@@ -1814,9 +1815,8 @@ struct tcp_request_sock_ops {
 				 __u16 *mss);
 #endif
 	struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl,
-				       const struct request_sock *req,
-				       bool *strict);
-	__u32 (*init_seq)(const struct sk_buff *skb, u32 *tsoff);
+				       const struct request_sock *req);
+	__u32 (*init_seq_tsoff)(const struct sk_buff *skb, u32 *tsoff);
 	int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
 			   struct flowi *fl, struct request_sock *req,
 			   struct tcp_fastopen_cookie *foc,
diff --git a/include/net/udp.h b/include/net/udp.h
index c9d8b8e848e0..3391dbd73959 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -372,4 +372,5 @@ void udp_encap_enable(void);
 #if IS_ENABLED(CONFIG_IPV6)
 void udpv6_encap_enable(void);
 #endif
+
 #endif	/* _UDP_H */
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 2c748ddad5f8..c98a52fb572a 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -94,4 +94,8 @@
 
 #define SCM_TIMESTAMPING_OPT_STATS	54
 
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
 #endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0539a0ceef38..a1d95386f562 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -81,6 +81,7 @@ enum bpf_cmd {
 	BPF_OBJ_GET,
 	BPF_PROG_ATTACH,
 	BPF_PROG_DETACH,
+	BPF_PROG_TEST_RUN,
 };
 
 enum bpf_map_type {
@@ -96,6 +97,8 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_LRU_HASH,
 	BPF_MAP_TYPE_LRU_PERCPU_HASH,
 	BPF_MAP_TYPE_LPM_TRIE,
+	BPF_MAP_TYPE_ARRAY_OF_MAPS,
+	BPF_MAP_TYPE_HASH_OF_MAPS,
 };
 
 enum bpf_prog_type {
@@ -152,6 +155,7 @@ union bpf_attr {
 		__u32	value_size;	/* size of value in bytes */
 		__u32	max_entries;	/* max number of entries in a map */
 		__u32	map_flags;	/* prealloc or not */
+		__u32	inner_map_fd;	/* fd pointing to the inner map */
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -186,6 +190,17 @@ union bpf_attr {
 		__u32		attach_type;
 		__u32		attach_flags;
 	};
+
+	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
+		__u32		prog_fd;
+		__u32		retval;
+		__u32		data_size_in;
+		__u32		data_size_out;
+		__aligned_u64	data_in;
+		__aligned_u64	data_out;
+		__u32		repeat;
+		__u32		duration;
+	} test;
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:
@@ -456,6 +471,18 @@ union bpf_attr {
  *     Return:
  *       > 0 length of the string including the trailing NUL on success
  *       < 0 error
+ *
+ * u64 bpf_bpf_get_socket_cookie(skb)
+ *     Get the cookie for the socket stored inside sk_buff.
+ *     @skb: pointer to skb
+ *     Return: 8 Bytes non-decreasing number on success or 0 if the socket
+ *     field is missing inside sk_buff
+ *
+ * u32 bpf_get_socket_uid(skb)
+ *     Get the owner uid of the socket stored inside sk_buff.
+ *     @skb: pointer to skb
+ *     Return: uid of the socket owner on success or 0 if the socket pointer
+ *     inside sk_buff is NULL
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -503,7 +530,9 @@ union bpf_attr {
 	FN(get_numa_node_id),		\
 	FN(skb_change_head),		\
 	FN(xdp_adjust_head),		\
-	FN(probe_read_str),
+	FN(probe_read_str),		\
+	FN(get_socket_cookie),		\
+	FN(get_socket_uid),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 0f1f3a12e23c..b47bee277347 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -65,8 +65,12 @@ enum devlink_command {
 #define DEVLINK_CMD_ESWITCH_MODE_SET /* obsolete, never use this! */ \
 	DEVLINK_CMD_ESWITCH_SET
 
-	/* add new commands above here */
+	DEVLINK_CMD_DPIPE_TABLE_GET,
+	DEVLINK_CMD_DPIPE_ENTRIES_GET,
+	DEVLINK_CMD_DPIPE_HEADERS_GET,
+	DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
 
+	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
 };
@@ -148,10 +152,71 @@ enum devlink_attr {
 	DEVLINK_ATTR_ESWITCH_MODE,		/* u16 */
 	DEVLINK_ATTR_ESWITCH_INLINE_MODE,	/* u8 */
 
+	DEVLINK_ATTR_DPIPE_TABLES,		/* nested */
+	DEVLINK_ATTR_DPIPE_TABLE,		/* nested */
+	DEVLINK_ATTR_DPIPE_TABLE_NAME,		/* string */
+	DEVLINK_ATTR_DPIPE_TABLE_SIZE,		/* u64 */
+	DEVLINK_ATTR_DPIPE_TABLE_MATCHES,	/* nested */
+	DEVLINK_ATTR_DPIPE_TABLE_ACTIONS,	/* nested */
+	DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED,	/* u8 */
+
+	DEVLINK_ATTR_DPIPE_ENTRIES,		/* nested */
+	DEVLINK_ATTR_DPIPE_ENTRY,		/* nested */
+	DEVLINK_ATTR_DPIPE_ENTRY_INDEX,		/* u64 */
+	DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES,	/* nested */
+	DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES,	/* nested */
+	DEVLINK_ATTR_DPIPE_ENTRY_COUNTER,	/* u64 */
+
+	DEVLINK_ATTR_DPIPE_MATCH,		/* nested */
+	DEVLINK_ATTR_DPIPE_MATCH_VALUE,		/* nested */
+	DEVLINK_ATTR_DPIPE_MATCH_TYPE,		/* u32 */
+
+	DEVLINK_ATTR_DPIPE_ACTION,		/* nested */
+	DEVLINK_ATTR_DPIPE_ACTION_VALUE,	/* nested */
+	DEVLINK_ATTR_DPIPE_ACTION_TYPE,		/* u32 */
+
+	DEVLINK_ATTR_DPIPE_VALUE,
+	DEVLINK_ATTR_DPIPE_VALUE_MASK,
+	DEVLINK_ATTR_DPIPE_VALUE_MAPPING,	/* u32 */
+
+	DEVLINK_ATTR_DPIPE_HEADERS,		/* nested */
+	DEVLINK_ATTR_DPIPE_HEADER,		/* nested */
+	DEVLINK_ATTR_DPIPE_HEADER_NAME,		/* string */
+	DEVLINK_ATTR_DPIPE_HEADER_ID,		/* u32 */
+	DEVLINK_ATTR_DPIPE_HEADER_FIELDS,	/* nested */
+	DEVLINK_ATTR_DPIPE_HEADER_GLOBAL,	/* u8 */
+	DEVLINK_ATTR_DPIPE_HEADER_INDEX,	/* u32 */
+
+	DEVLINK_ATTR_DPIPE_FIELD,		/* nested */
+	DEVLINK_ATTR_DPIPE_FIELD_NAME,		/* string */
+	DEVLINK_ATTR_DPIPE_FIELD_ID,		/* u32 */
+	DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH,	/* u32 */
+	DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE,	/* u32 */
+
+	DEVLINK_ATTR_PAD,
+
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
 	DEVLINK_ATTR_MAX = __DEVLINK_ATTR_MAX - 1
 };
 
+/* Mapping between internal resource described by the field and system
+ * structure
+ */
+enum devlink_dpipe_field_mapping_type {
+	DEVLINK_DPIPE_FIELD_MAPPING_TYPE_NONE,
+	DEVLINK_DPIPE_FIELD_MAPPING_TYPE_IFINDEX,
+};
+
+/* Match type - specify the type of the match */
+enum devlink_dpipe_match_type {
+	DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT,
+};
+
+/* Action type - specify the action type */
+enum devlink_dpipe_action_type {
+	DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY,
+};
+
 #endif /* _UAPI_LINUX_DEVLINK_H_ */
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 3dc91a46e8b8..5f4ea28eabe4 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1487,6 +1487,7 @@ enum ethtool_link_mode_bit_indices {
  */
 
 /* The forced speed, in units of 1Mb. All values 0 to INT_MAX are legal. */
+/* Update drivers/net/phy/phy.c:phy_speed_to_str() when adding new values */
 #define SPEED_10		10
 #define SPEED_100		100
 #define SPEED_1000		1000
diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h
index 72a04a0e8cce..57d1edb8efd9 100644
--- a/include/uapi/linux/gtp.h
+++ b/include/uapi/linux/gtp.h
@@ -19,7 +19,8 @@ enum gtp_attrs {
 	GTPA_LINK,
 	GTPA_VERSION,
 	GTPA_TID,	/* for GTPv0 only */
-	GTPA_SGSN_ADDRESS,
+	GTPA_PEER_ADDRESS,	/* Remote GSN peer, either SGSN or GGSN */
+#define GTPA_SGSN_ADDRESS GTPA_PEER_ADDRESS /* maintain legacy attr name */
 	GTPA_MS_ADDRESS,
 	GTPA_FLOW,
 	GTPA_NET_NS_FD,
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 320fc1e747ee..97f6d302f627 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -157,6 +157,7 @@ enum {
 	IFLA_GSO_MAX_SIZE,
 	IFLA_PAD,
 	IFLA_XDP,
+	IFLA_EVENT,
 	__IFLA_MAX
 };
 
@@ -538,11 +539,18 @@ enum {
 #define IFLA_PPP_MAX (__IFLA_PPP_MAX - 1)
 
 /* GTP section */
+
+enum ifla_gtp_role {
+	GTP_ROLE_GGSN = 0,
+	GTP_ROLE_SGSN,
+};
+
 enum {
 	IFLA_GTP_UNSPEC,
 	IFLA_GTP_FD0,
 	IFLA_GTP_FD1,
 	IFLA_GTP_PDP_HASHSIZE,
+	IFLA_GTP_ROLE,
 	__IFLA_GTP_MAX,
 };
 #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
@@ -892,4 +900,24 @@ enum {
 
 #define IFLA_XDP_MAX (__IFLA_XDP_MAX - 1)
 
+enum {
+	IFLA_EVENT_UNSPEC,
+	IFLA_EVENT_REBOOT,
+	IFLA_EVENT_CHANGE_MTU,
+	IFLA_EVENT_CHANGE_ADDR,
+	IFLA_EVENT_CHANGE_NAME,
+	IFLA_EVENT_FEAT_CHANGE,
+	IFLA_EVENT_BONDING_FAILOVER,
+	IFLA_EVENT_POST_TYPE_CHANGE,
+	IFLA_EVENT_NOTIFY_PEERS,
+	IFLA_EVENT_CHANGE_UPPER,
+	IFLA_EVENT_RESEND_IGMP,
+	IFLA_EVENT_PRE_CHANGE_MTU,
+	IFLA_EVENT_CHANGE_INFO_DATA,
+	IFLA_EVENT_PRE_CHANGE_UPPER,
+	IFLA_EVENT_CHANGE_LOWER_STATE,
+	IFLA_EVENT_UDP_TUNNEL_PUSH_INFO,
+	IFLA_EVENT_CHANGE_TX_QUEUE_LEN,
+};
+
 #endif /* _UAPI_LINUX_IF_LINK_H */
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index 8ef9e75e004e..2ae59178189d 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -183,6 +183,8 @@ enum {
 	DEVCONF_SEG6_REQUIRE_HMAC,
 	DEVCONF_ENHANCED_DAD,
 	DEVCONF_ADDR_GEN_MODE,
+	DEVCONF_DISABLE_POLICY,
+	DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN,
 	DEVCONF_MAX
 };
 
diff --git a/include/uapi/linux/mpls_iptunnel.h b/include/uapi/linux/mpls_iptunnel.h
index d80a0498f77e..f5e45095b0bb 100644
--- a/include/uapi/linux/mpls_iptunnel.h
+++ b/include/uapi/linux/mpls_iptunnel.h
@@ -16,11 +16,13 @@
 /* MPLS tunnel attributes
  * [RTA_ENCAP] = {
  *     [MPLS_IPTUNNEL_DST]
+ *     [MPLS_IPTUNNEL_TTL]
  * }
  */
 enum {
 	MPLS_IPTUNNEL_UNSPEC,
 	MPLS_IPTUNNEL_DST,
+	MPLS_IPTUNNEL_TTL,
 	__MPLS_IPTUNNEL_MAX,
 };
 #define MPLS_IPTUNNEL_MAX (__MPLS_IPTUNNEL_MAX - 1)
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 05215d30fe5c..8f3842690d17 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -816,6 +816,17 @@ enum nft_rt_keys {
 };
 
 /**
+ * enum nft_hash_types - nf_tables hash expression types
+ *
+ * @NFT_HASH_JENKINS: Jenkins Hash
+ * @NFT_HASH_SYM: Symmetric Hash
+ */
+enum nft_hash_types {
+	NFT_HASH_JENKINS,
+	NFT_HASH_SYM,
+};
+
+/**
  * enum nft_hash_attributes - nf_tables hash expression netlink attributes
  *
  * @NFTA_HASH_SREG: source register (NLA_U32)
@@ -824,6 +835,7 @@ enum nft_rt_keys {
  * @NFTA_HASH_MODULUS: modulus value (NLA_U32)
  * @NFTA_HASH_SEED: seed value (NLA_U32)
  * @NFTA_HASH_OFFSET: add this offset value to hash result (NLA_U32)
+ * @NFTA_HASH_TYPE: hash operation (NLA_U32: nft_hash_types)
  */
 enum nft_hash_attributes {
 	NFTA_HASH_UNSPEC,
@@ -833,6 +845,7 @@ enum nft_hash_attributes {
 	NFTA_HASH_MODULUS,
 	NFTA_HASH_SEED,
 	NFTA_HASH_OFFSET,
+	NFTA_HASH_TYPE,
 	__NFTA_HASH_MAX,
 };
 #define NFTA_HASH_MAX	(__NFTA_HASH_MAX - 1)
@@ -1244,12 +1257,23 @@ enum nft_fib_flags {
 	NFTA_FIB_F_MARK		= 1 << 2,	/* use skb->mark */
 	NFTA_FIB_F_IIF		= 1 << 3,	/* restrict to iif */
 	NFTA_FIB_F_OIF		= 1 << 4,	/* restrict to oif */
+	NFTA_FIB_F_PRESENT	= 1 << 5,	/* check existence only */
+};
+
+enum nft_ct_helper_attributes {
+	NFTA_CT_HELPER_UNSPEC,
+	NFTA_CT_HELPER_NAME,
+	NFTA_CT_HELPER_L3PROTO,
+	NFTA_CT_HELPER_L4PROTO,
+	__NFTA_CT_HELPER_MAX,
 };
+#define NFTA_CT_HELPER_MAX	(__NFTA_CT_HELPER_MAX - 1)
 
 #define NFT_OBJECT_UNSPEC	0
 #define NFT_OBJECT_COUNTER	1
 #define NFT_OBJECT_QUOTA	2
-#define __NFT_OBJECT_MAX	3
+#define NFT_OBJECT_CT_HELPER	3
+#define __NFT_OBJECT_MAX	4
 #define NFT_OBJECT_MAX		(__NFT_OBJECT_MAX - 1)
 
 /**
diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h
index 76b4d87c83a8..6dcd4de3397b 100644
--- a/include/uapi/linux/netlink_diag.h
+++ b/include/uapi/linux/netlink_diag.h
@@ -38,6 +38,7 @@ enum {
 	NETLINK_DIAG_GROUPS,
 	NETLINK_DIAG_RX_RING,
 	NETLINK_DIAG_TX_RING,
+	NETLINK_DIAG_FLAGS,
 
 	__NETLINK_DIAG_MAX,
 };
@@ -52,5 +53,14 @@ enum {
 /* deprecated since 4.6 */
 #define NDIAG_SHOW_RING_CFG	0x00000004 /* show ring configuration */
 #endif
+#define NDIAG_SHOW_FLAGS	0x00000008 /* show flags of a netlink socket */
+
+/* flags */
+#define NDIAG_FLAG_CB_RUNNING		0x00000001
+#define NDIAG_FLAG_PKTINFO		0x00000002
+#define NDIAG_FLAG_BROADCAST_ERROR	0x00000004
+#define NDIAG_FLAG_NO_ENOBUFS		0x00000008
+#define NDIAG_FLAG_LISTEN_ALL_NSID	0x00000010
+#define NDIAG_FLAG_CAP_ACK		0x00000020
 
 #endif
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 7f41f7d0000f..66d1c3ccfd8e 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -578,10 +578,25 @@ enum ovs_sample_attr {
 	OVS_SAMPLE_ATTR_PROBABILITY, /* u32 number */
 	OVS_SAMPLE_ATTR_ACTIONS,     /* Nested OVS_ACTION_ATTR_* attributes. */
 	__OVS_SAMPLE_ATTR_MAX,
+
+#ifdef __KERNEL__
+	OVS_SAMPLE_ATTR_ARG          /* struct sample_arg  */
+#endif
 };
 
 #define OVS_SAMPLE_ATTR_MAX (__OVS_SAMPLE_ATTR_MAX - 1)
 
+#ifdef __KERNEL__
+struct sample_arg {
+	bool exec;                   /* When true, actions in sample will not
+				      * change flow keys. False otherwise.
+				      */
+	u32  probability;            /* Same value as
+				      * 'OVS_SAMPLE_ATTR_PROBABILITY'.
+				      */
+};
+#endif
+
 /**
  * enum ovs_userspace_attr - Attributes for %OVS_ACTION_ATTR_USERSPACE action.
  * @OVS_USERSPACE_ATTR_PID: u32 Netlink PID to which the %OVS_PACKET_CMD_ACTION
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index df7451d35131..099bf5528fed 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -617,6 +617,14 @@ struct tc_drr_stats {
 #define TC_QOPT_BITMASK 15
 #define TC_QOPT_MAX_QUEUE 16
 
+enum {
+	TC_MQPRIO_HW_OFFLOAD_NONE,	/* no offload requested */
+	TC_MQPRIO_HW_OFFLOAD_TCS,	/* offload TCs, no queue counts */
+	__TC_MQPRIO_HW_OFFLOAD_MAX
+};
+
+#define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1)
+
 struct tc_mqprio_qopt {
 	__u8	num_tc;
 	__u8	prio_tc_map[TC_QOPT_BITMASK + 1];
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 6546917d605a..cce061382e40 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -122,6 +122,8 @@ enum {
 
 	RTM_NEWNETCONF = 80,
 #define RTM_NEWNETCONF RTM_NEWNETCONF
+	RTM_DELNETCONF,
+#define RTM_DELNETCONF RTM_DELNETCONF
 	RTM_GETNETCONF = 82,
 #define RTM_GETNETCONF RTM_GETNETCONF
 
@@ -319,6 +321,7 @@ enum rtattr_type_t {
 	RTA_EXPIRES,
 	RTA_PAD,
 	RTA_UID,
+	RTA_TTL_PROPAGATE,
 	__RTA_MAX
 };
 
@@ -545,6 +548,7 @@ enum {
 	TCA_STATS2,
 	TCA_STAB,
 	TCA_PAD,
+	TCA_DUMP_INVISIBLE,
 	__TCA_MAX
 };
 
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index d3ae381fcf33..ced9d8b97426 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -115,6 +115,8 @@ typedef __s32 sctp_assoc_t;
 #define SCTP_PR_SUPPORTED	113
 #define SCTP_DEFAULT_PRINFO	114
 #define SCTP_PR_ASSOC_STATUS	115
+#define SCTP_PR_STREAM_STATUS	116
+#define SCTP_RECONFIG_SUPPORTED	117
 #define SCTP_ENABLE_STREAM_RESET	118
 #define SCTP_RESET_STREAMS	119
 #define SCTP_RESET_ASSOC	120
@@ -502,6 +504,28 @@ struct sctp_stream_reset_event {
 	__u16 strreset_stream_list[];
 };
 
+#define SCTP_ASSOC_RESET_DENIED		0x0004
+#define SCTP_ASSOC_RESET_FAILED		0x0008
+struct sctp_assoc_reset_event {
+	__u16 assocreset_type;
+	__u16 assocreset_flags;
+	__u32 assocreset_length;
+	sctp_assoc_t assocreset_assoc_id;
+	__u32 assocreset_local_tsn;
+	__u32 assocreset_remote_tsn;
+};
+
+#define SCTP_ASSOC_CHANGE_DENIED	0x0004
+#define SCTP_ASSOC_CHANGE_FAILED	0x0008
+struct sctp_stream_change_event {
+	__u16 strchange_type;
+	__u16 strchange_flags;
+	__u32 strchange_length;
+	sctp_assoc_t strchange_assoc_id;
+	__u16 strchange_instrms;
+	__u16 strchange_outstrms;
+};
+
 /*
  * Described in Section 7.3
  *   Ancillary Data and Notification Interest Options
@@ -518,6 +542,8 @@ struct sctp_event_subscribe {
 	__u8 sctp_authentication_event;
 	__u8 sctp_sender_dry_event;
 	__u8 sctp_stream_reset_event;
+	__u8 sctp_assoc_reset_event;
+	__u8 sctp_stream_change_event;
 };
 
 /*
@@ -543,6 +569,8 @@ union sctp_notification {
 	struct sctp_authkey_event sn_authkey_event;
 	struct sctp_sender_dry_event sn_sender_dry_event;
 	struct sctp_stream_reset_event sn_strreset_event;
+	struct sctp_assoc_reset_event sn_assocreset_event;
+	struct sctp_stream_change_event sn_strchange_event;
 };
 
 /* Section 5.3.1
@@ -572,6 +600,10 @@ enum sctp_sn_type {
 #define SCTP_SENDER_DRY_EVENT		SCTP_SENDER_DRY_EVENT
 	SCTP_STREAM_RESET_EVENT,
 #define SCTP_STREAM_RESET_EVENT		SCTP_STREAM_RESET_EVENT
+	SCTP_ASSOC_RESET_EVENT,
+#define SCTP_ASSOC_RESET_EVENT		SCTP_ASSOC_RESET_EVENT
+	SCTP_STREAM_CHANGE_EVENT,
+#define SCTP_STREAM_CHANGE_EVENT	SCTP_STREAM_CHANGE_EVENT
 };
 
 /* Notification error codes used to fill up the error fields in some
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index 3b2bed7ca9a4..cec0e171d20c 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -177,7 +177,6 @@ enum
 	LINUX_MIB_TIMEWAITED,			/* TimeWaited */
 	LINUX_MIB_TIMEWAITRECYCLED,		/* TimeWaitRecycled */
 	LINUX_MIB_TIMEWAITKILLED,		/* TimeWaitKilled */
-	LINUX_MIB_PAWSPASSIVEREJECTED,		/* PAWSPassiveRejected */
 	LINUX_MIB_PAWSACTIVEREJECTED,		/* PAWSActiveRejected */
 	LINUX_MIB_PAWSESTABREJECTED,		/* PAWSEstabRejected */
 	LINUX_MIB_DELAYEDACKS,			/* DelayedACKs */
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index d2b12152e358..e13d48058b8d 100644
--- a/include/uapi/linux/sysctl.h
+++ b/include/uapi/linux/sysctl.h
@@ -568,6 +568,7 @@ enum {
 	NET_IPV6_PROXY_NDP=23,
 	NET_IPV6_ACCEPT_SOURCE_ROUTE=25,
 	NET_IPV6_ACCEPT_RA_FROM_LOCAL=26,
+	NET_IPV6_ACCEPT_RA_RT_INFO_MIN_PLEN=27,
 	__NET_IPV6_MAX
 };
 
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index e1ce4f4fd7fd..e1e5e658f2db 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,7 +1,7 @@
 obj-y := core.o
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o
-obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o
+obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
 ifeq ($(CONFIG_PERF_EVENTS),y)
 obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
 endif
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 6b6f41f0b211..bc9da93db403 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -1,4 +1,5 @@
 /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2016,2017 Facebook
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -16,6 +17,8 @@
 #include <linux/filter.h>
 #include <linux/perf_event.h>
 
+#include "map_in_map.h"
+
 static void bpf_array_free_percpu(struct bpf_array *array)
 {
 	int i;
@@ -113,6 +116,30 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key)
 	return array->value + array->elem_size * index;
 }
 
+/* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
+static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+{
+	struct bpf_insn *insn = insn_buf;
+	u32 elem_size = round_up(map->value_size, 8);
+	const int ret = BPF_REG_0;
+	const int map_ptr = BPF_REG_1;
+	const int index = BPF_REG_2;
+
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
+	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
+	*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3);
+
+	if (is_power_of_2(elem_size)) {
+		*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
+	} else {
+		*insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size);
+	}
+	*insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr);
+	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
+	*insn++ = BPF_MOV64_IMM(ret, 0);
+	return insn - insn_buf;
+}
+
 /* Called from eBPF program */
 static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
 {
@@ -267,6 +294,7 @@ static const struct bpf_map_ops array_ops = {
 	.map_lookup_elem = array_map_lookup_elem,
 	.map_update_elem = array_map_update_elem,
 	.map_delete_elem = array_map_delete_elem,
+	.map_gen_lookup = array_map_gen_lookup,
 };
 
 static struct bpf_map_type_list array_type __ro_after_init = {
@@ -576,3 +604,64 @@ static int __init register_cgroup_array_map(void)
 }
 late_initcall(register_cgroup_array_map);
 #endif
+
+static struct bpf_map *array_of_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_map *map, *inner_map_meta;
+
+	inner_map_meta = bpf_map_meta_alloc(attr->inner_map_fd);
+	if (IS_ERR(inner_map_meta))
+		return inner_map_meta;
+
+	map = fd_array_map_alloc(attr);
+	if (IS_ERR(map)) {
+		bpf_map_meta_free(inner_map_meta);
+		return map;
+	}
+
+	map->inner_map_meta = inner_map_meta;
+
+	return map;
+}
+
+static void array_of_map_free(struct bpf_map *map)
+{
+	/* map->inner_map_meta is only accessed by syscall which
+	 * is protected by fdget/fdput.
+	 */
+	bpf_map_meta_free(map->inner_map_meta);
+	bpf_fd_array_map_clear(map);
+	fd_array_map_free(map);
+}
+
+static void *array_of_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_map **inner_map = array_map_lookup_elem(map, key);
+
+	if (!inner_map)
+		return NULL;
+
+	return READ_ONCE(*inner_map);
+}
+
+static const struct bpf_map_ops array_of_map_ops = {
+	.map_alloc = array_of_map_alloc,
+	.map_free = array_of_map_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = array_of_map_lookup_elem,
+	.map_delete_elem = fd_array_map_delete_elem,
+	.map_fd_get_ptr = bpf_map_fd_get_ptr,
+	.map_fd_put_ptr = bpf_map_fd_put_ptr,
+};
+
+static struct bpf_map_type_list array_of_map_type __ro_after_init = {
+	.ops = &array_of_map_ops,
+	.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
+};
+
+static int __init register_array_of_map(void)
+{
+	bpf_register_map_type(&array_of_map_type);
+	return 0;
+}
+late_initcall(register_array_of_map);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 361a69dfe543..d5b0623ce87d 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -16,6 +16,7 @@
 #include <linux/rculist_nulls.h>
 #include "percpu_freelist.h"
 #include "bpf_lru_list.h"
+#include "map_in_map.h"
 
 struct bucket {
 	struct hlist_nulls_head head;
@@ -86,6 +87,11 @@ static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size
 	return *(void __percpu **)(l->key + key_size);
 }
 
+static void *fd_htab_map_get_ptr(const struct bpf_map *map, struct htab_elem *l)
+{
+	return *(void **)(l->key + roundup(map->key_size, 8));
+}
+
 static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i)
 {
 	return (struct htab_elem *) (htab->elems + i * htab->elem_size);
@@ -426,7 +432,11 @@ again:
 	return NULL;
 }
 
-/* Called from syscall or from eBPF program */
+/* Called from syscall or from eBPF program directly, so
+ * arguments have to match bpf_map_lookup_elem() exactly.
+ * The return value is adjusted by BPF instructions
+ * in htab_map_gen_lookup().
+ */
 static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
@@ -458,6 +468,30 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
 	return NULL;
 }
 
+/* inline bpf_map_lookup_elem() call.
+ * Instead of:
+ * bpf_prog
+ *   bpf_map_lookup_elem
+ *     map->ops->map_lookup_elem
+ *       htab_map_lookup_elem
+ *         __htab_map_lookup_elem
+ * do:
+ * bpf_prog
+ *   __htab_map_lookup_elem
+ */
+static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+{
+	struct bpf_insn *insn = insn_buf;
+	const int ret = BPF_REG_0;
+
+	*insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem);
+	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1);
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
+				offsetof(struct htab_elem, key) +
+				round_up(map->key_size, 8));
+	return insn - insn_buf;
+}
+
 static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct htab_elem *l = __htab_map_lookup_elem(map, key);
@@ -582,6 +616,14 @@ static void htab_elem_free_rcu(struct rcu_head *head)
 
 static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 {
+	struct bpf_map *map = &htab->map;
+
+	if (map->ops->map_fd_put_ptr) {
+		void *ptr = fd_htab_map_get_ptr(map, l);
+
+		map->ops->map_fd_put_ptr(ptr);
+	}
+
 	if (htab_is_prealloc(htab)) {
 		pcpu_freelist_push(&htab->freelist, &l->fnode);
 	} else {
@@ -1027,6 +1069,7 @@ static void delete_all_elements(struct bpf_htab *htab)
 		}
 	}
 }
+
 /* Called when map->refcnt goes to zero, either from workqueue or from syscall */
 static void htab_map_free(struct bpf_map *map)
 {
@@ -1060,6 +1103,7 @@ static const struct bpf_map_ops htab_ops = {
 	.map_lookup_elem = htab_map_lookup_elem,
 	.map_update_elem = htab_map_update_elem,
 	.map_delete_elem = htab_map_delete_elem,
+	.map_gen_lookup = htab_map_gen_lookup,
 };
 
 static struct bpf_map_type_list htab_type __ro_after_init = {
@@ -1182,12 +1226,118 @@ static struct bpf_map_type_list htab_lru_percpu_type __ro_after_init = {
 	.type = BPF_MAP_TYPE_LRU_PERCPU_HASH,
 };
 
+static struct bpf_map *fd_htab_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_map *map;
+
+	if (attr->value_size != sizeof(u32))
+		return ERR_PTR(-EINVAL);
+
+	/* pointer is stored internally */
+	attr->value_size = sizeof(void *);
+	map = htab_map_alloc(attr);
+	attr->value_size = sizeof(u32);
+
+	return map;
+}
+
+static void fd_htab_map_free(struct bpf_map *map)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct hlist_nulls_node *n;
+	struct hlist_nulls_head *head;
+	struct htab_elem *l;
+	int i;
+
+	for (i = 0; i < htab->n_buckets; i++) {
+		head = select_bucket(htab, i);
+
+		hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
+			void *ptr = fd_htab_map_get_ptr(map, l);
+
+			map->ops->map_fd_put_ptr(ptr);
+		}
+	}
+
+	htab_map_free(map);
+}
+
+/* only called from syscall */
+int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
+				void *key, void *value, u64 map_flags)
+{
+	void *ptr;
+	int ret;
+	u32 ufd = *(u32 *)value;
+
+	ptr = map->ops->map_fd_get_ptr(map, map_file, ufd);
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
+
+	ret = htab_map_update_elem(map, key, &ptr, map_flags);
+	if (ret)
+		map->ops->map_fd_put_ptr(ptr);
+
+	return ret;
+}
+
+static struct bpf_map *htab_of_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_map *map, *inner_map_meta;
+
+	inner_map_meta = bpf_map_meta_alloc(attr->inner_map_fd);
+	if (IS_ERR(inner_map_meta))
+		return inner_map_meta;
+
+	map = fd_htab_map_alloc(attr);
+	if (IS_ERR(map)) {
+		bpf_map_meta_free(inner_map_meta);
+		return map;
+	}
+
+	map->inner_map_meta = inner_map_meta;
+
+	return map;
+}
+
+static void *htab_of_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_map **inner_map  = htab_map_lookup_elem(map, key);
+
+	if (!inner_map)
+		return NULL;
+
+	return READ_ONCE(*inner_map);
+}
+
+static void htab_of_map_free(struct bpf_map *map)
+{
+	bpf_map_meta_free(map->inner_map_meta);
+	fd_htab_map_free(map);
+}
+
+static const struct bpf_map_ops htab_of_map_ops = {
+	.map_alloc = htab_of_map_alloc,
+	.map_free = htab_of_map_free,
+	.map_get_next_key = htab_map_get_next_key,
+	.map_lookup_elem = htab_of_map_lookup_elem,
+	.map_delete_elem = htab_map_delete_elem,
+	.map_fd_get_ptr = bpf_map_fd_get_ptr,
+	.map_fd_put_ptr = bpf_map_fd_put_ptr,
+};
+
+static struct bpf_map_type_list htab_of_map_type __ro_after_init = {
+	.ops = &htab_of_map_ops,
+	.type = BPF_MAP_TYPE_HASH_OF_MAPS,
+};
+
 static int __init register_htab_map(void)
 {
 	bpf_register_map_type(&htab_type);
 	bpf_register_map_type(&htab_percpu_type);
 	bpf_register_map_type(&htab_lru_type);
 	bpf_register_map_type(&htab_lru_percpu_type);
+	bpf_register_map_type(&htab_of_map_type);
 	return 0;
 }
 late_initcall(register_htab_map);
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
new file mode 100644
index 000000000000..59bcdf821ae4
--- /dev/null
+++ b/kernel/bpf/map_in_map.c
@@ -0,0 +1,97 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/slab.h>
+#include <linux/bpf.h>
+
+#include "map_in_map.h"
+
+struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
+{
+	struct bpf_map *inner_map, *inner_map_meta;
+	struct fd f;
+
+	f = fdget(inner_map_ufd);
+	inner_map = __bpf_map_get(f);
+	if (IS_ERR(inner_map))
+		return inner_map;
+
+	/* prog_array->owner_prog_type and owner_jited
+	 * is a runtime binding.  Doing static check alone
+	 * in the verifier is not enough.
+	 */
+	if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
+		fdput(f);
+		return ERR_PTR(-ENOTSUPP);
+	}
+
+	/* Does not support >1 level map-in-map */
+	if (inner_map->inner_map_meta) {
+		fdput(f);
+		return ERR_PTR(-EINVAL);
+	}
+
+	inner_map_meta = kzalloc(sizeof(*inner_map_meta), GFP_USER);
+	if (!inner_map_meta) {
+		fdput(f);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	inner_map_meta->map_type = inner_map->map_type;
+	inner_map_meta->key_size = inner_map->key_size;
+	inner_map_meta->value_size = inner_map->value_size;
+	inner_map_meta->map_flags = inner_map->map_flags;
+	inner_map_meta->ops = inner_map->ops;
+	inner_map_meta->max_entries = inner_map->max_entries;
+
+	fdput(f);
+	return inner_map_meta;
+}
+
+void bpf_map_meta_free(struct bpf_map *map_meta)
+{
+	kfree(map_meta);
+}
+
+bool bpf_map_meta_equal(const struct bpf_map *meta0,
+			const struct bpf_map *meta1)
+{
+	/* No need to compare ops because it is covered by map_type */
+	return meta0->map_type == meta1->map_type &&
+		meta0->key_size == meta1->key_size &&
+		meta0->value_size == meta1->value_size &&
+		meta0->map_flags == meta1->map_flags &&
+		meta0->max_entries == meta1->max_entries;
+}
+
+void *bpf_map_fd_get_ptr(struct bpf_map *map,
+			 struct file *map_file /* not used */,
+			 int ufd)
+{
+	struct bpf_map *inner_map;
+	struct fd f;
+
+	f = fdget(ufd);
+	inner_map = __bpf_map_get(f);
+	if (IS_ERR(inner_map))
+		return inner_map;
+
+	if (bpf_map_meta_equal(map->inner_map_meta, inner_map))
+		inner_map = bpf_map_inc(inner_map, false);
+	else
+		inner_map = ERR_PTR(-EINVAL);
+
+	fdput(f);
+	return inner_map;
+}
+
+void bpf_map_fd_put_ptr(void *ptr)
+{
+	/* ptr->ops->map_free() has to go through one
+	 * rcu grace period by itself.
+	 */
+	bpf_map_put(ptr);
+}
diff --git a/kernel/bpf/map_in_map.h b/kernel/bpf/map_in_map.h
new file mode 100644
index 000000000000..177fadb689dc
--- /dev/null
+++ b/kernel/bpf/map_in_map.h
@@ -0,0 +1,23 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef __MAP_IN_MAP_H__
+#define __MAP_IN_MAP_H__
+
+#include <linux/types.h>
+
+struct file;
+struct bpf_map;
+
+struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd);
+void bpf_map_meta_free(struct bpf_map *map_meta);
+bool bpf_map_meta_equal(const struct bpf_map *meta0,
+			const struct bpf_map *meta1);
+void *bpf_map_fd_get_ptr(struct bpf_map *map, struct file *map_file,
+			 int ufd);
+void bpf_map_fd_put_ptr(void *ptr);
+
+#endif
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 7af0dcc5d755..ab0cf4c43690 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -215,7 +215,7 @@ int bpf_map_new_fd(struct bpf_map *map)
 		   offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
 		   sizeof(attr->CMD##_LAST_FIELD)) != NULL
 
-#define BPF_MAP_CREATE_LAST_FIELD map_flags
+#define BPF_MAP_CREATE_LAST_FIELD inner_map_fd
 /* called via syscall */
 static int map_create(union bpf_attr *attr)
 {
@@ -352,6 +352,9 @@ static int map_lookup_elem(union bpf_attr *attr)
 		err = bpf_percpu_array_copy(map, key, value);
 	} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
 		err = bpf_stackmap_copy(map, key, value);
+	} else if (map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+		   map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+		err = -ENOTSUPP;
 	} else {
 		rcu_read_lock();
 		ptr = map->ops->map_lookup_elem(map, key);
@@ -438,11 +441,17 @@ static int map_update_elem(union bpf_attr *attr)
 		err = bpf_percpu_array_update(map, key, value, attr->flags);
 	} else if (map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY ||
 		   map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
-		   map->map_type == BPF_MAP_TYPE_CGROUP_ARRAY) {
+		   map->map_type == BPF_MAP_TYPE_CGROUP_ARRAY ||
+		   map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) {
 		rcu_read_lock();
 		err = bpf_fd_array_map_update_elem(map, f.file, key, value,
 						   attr->flags);
 		rcu_read_unlock();
+	} else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+		rcu_read_lock();
+		err = bpf_fd_htab_map_update_elem(map, f.file, key, value,
+						  attr->flags);
+		rcu_read_unlock();
 	} else {
 		rcu_read_lock();
 		err = map->ops->map_update_elem(map, key, value, attr->flags);
@@ -586,59 +595,6 @@ void bpf_register_prog_type(struct bpf_prog_type_list *tl)
 	list_add(&tl->list_node, &bpf_prog_types);
 }
 
-/* fixup insn->imm field of bpf_call instructions:
- * if (insn->imm == BPF_FUNC_map_lookup_elem)
- *      insn->imm = bpf_map_lookup_elem - __bpf_call_base;
- * else if (insn->imm == BPF_FUNC_map_update_elem)
- *      insn->imm = bpf_map_update_elem - __bpf_call_base;
- * else ...
- *
- * this function is called after eBPF program passed verification
- */
-static void fixup_bpf_calls(struct bpf_prog *prog)
-{
-	const struct bpf_func_proto *fn;
-	int i;
-
-	for (i = 0; i < prog->len; i++) {
-		struct bpf_insn *insn = &prog->insnsi[i];
-
-		if (insn->code == (BPF_JMP | BPF_CALL)) {
-			/* we reach here when program has bpf_call instructions
-			 * and it passed bpf_check(), means that
-			 * ops->get_func_proto must have been supplied, check it
-			 */
-			BUG_ON(!prog->aux->ops->get_func_proto);
-
-			if (insn->imm == BPF_FUNC_get_route_realm)
-				prog->dst_needed = 1;
-			if (insn->imm == BPF_FUNC_get_prandom_u32)
-				bpf_user_rnd_init_once();
-			if (insn->imm == BPF_FUNC_xdp_adjust_head)
-				prog->xdp_adjust_head = 1;
-			if (insn->imm == BPF_FUNC_tail_call) {
-				/* mark bpf_tail_call as different opcode
-				 * to avoid conditional branch in
-				 * interpeter for every normal call
-				 * and to prevent accidental JITing by
-				 * JIT compiler that doesn't support
-				 * bpf_tail_call yet
-				 */
-				insn->imm = 0;
-				insn->code |= BPF_X;
-				continue;
-			}
-
-			fn = prog->aux->ops->get_func_proto(insn->imm);
-			/* all functions that have prototype and verifier allowed
-			 * programs to call them, must be real in-kernel functions
-			 */
-			BUG_ON(!fn->func);
-			insn->imm = fn->func - __bpf_call_base;
-		}
-	}
-}
-
 /* drop refcnt on maps used by eBPF program and free auxilary data */
 static void free_used_maps(struct bpf_prog_aux *aux)
 {
@@ -892,9 +848,6 @@ static int bpf_prog_load(union bpf_attr *attr)
 	if (err < 0)
 		goto free_used_maps;
 
-	/* fixup BPF_CALL->imm field */
-	fixup_bpf_calls(prog);
-
 	/* eBPF program is ready to be JITed */
 	prog = bpf_prog_select_runtime(prog, &err);
 	if (err < 0)
@@ -1020,6 +973,28 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 }
 #endif /* CONFIG_CGROUP_BPF */
 
+#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
+
+static int bpf_prog_test_run(const union bpf_attr *attr,
+			     union bpf_attr __user *uattr)
+{
+	struct bpf_prog *prog;
+	int ret = -ENOTSUPP;
+
+	if (CHECK_ATTR(BPF_PROG_TEST_RUN))
+		return -EINVAL;
+
+	prog = bpf_prog_get(attr->test.prog_fd);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	if (prog->aux->ops->test_run)
+		ret = prog->aux->ops->test_run(prog, attr, uattr);
+
+	bpf_prog_put(prog);
+	return ret;
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
 	union bpf_attr attr = {};
@@ -1086,7 +1061,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_OBJ_GET:
 		err = bpf_obj_get(&attr);
 		break;
-
 #ifdef CONFIG_CGROUP_BPF
 	case BPF_PROG_ATTACH:
 		err = bpf_prog_attach(&attr);
@@ -1095,7 +1069,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 		err = bpf_prog_detach(&attr);
 		break;
 #endif
-
+	case BPF_PROG_TEST_RUN:
+		err = bpf_prog_test_run(&attr, uattr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a834068a400e..62e1e447ded9 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -143,6 +143,8 @@ struct bpf_verifier_stack_elem {
 #define BPF_COMPLEXITY_LIMIT_INSNS	65536
 #define BPF_COMPLEXITY_LIMIT_STACK	1024
 
+#define BPF_MAP_PTR_POISON ((void *)0xeB9F + POISON_POINTER_DELTA)
+
 struct bpf_call_arg_meta {
 	struct bpf_map *map_ptr;
 	bool raw_mode;
@@ -1215,6 +1217,10 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 		    func_id != BPF_FUNC_current_task_under_cgroup)
 			goto error;
 		break;
+	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
+	case BPF_MAP_TYPE_HASH_OF_MAPS:
+		if (func_id != BPF_FUNC_map_lookup_elem)
+			goto error;
 	default:
 		break;
 	}
@@ -1291,7 +1297,7 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
 	}
 }
 
-static int check_call(struct bpf_verifier_env *env, int func_id)
+static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
 {
 	struct bpf_verifier_state *state = &env->cur_state;
 	const struct bpf_func_proto *fn = NULL;
@@ -1375,6 +1381,8 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
 	} else if (fn->ret_type == RET_VOID) {
 		regs[BPF_REG_0].type = NOT_INIT;
 	} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
+		struct bpf_insn_aux_data *insn_aux;
+
 		regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
 		regs[BPF_REG_0].max_value = regs[BPF_REG_0].min_value = 0;
 		/* remember map_ptr, so that check_map_access()
@@ -1387,6 +1395,11 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
 		}
 		regs[BPF_REG_0].map_ptr = meta.map_ptr;
 		regs[BPF_REG_0].id = ++env->id_gen;
+		insn_aux = &env->insn_aux_data[insn_idx];
+		if (!insn_aux->map_ptr)
+			insn_aux->map_ptr = meta.map_ptr;
+		else if (insn_aux->map_ptr != meta.map_ptr)
+			insn_aux->map_ptr = BPF_MAP_PTR_POISON;
 	} else {
 		verbose("unknown return type %d of func %s#%d\n",
 			fn->ret_type, func_id_name(func_id), func_id);
@@ -2112,14 +2125,19 @@ static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
 	struct bpf_reg_state *reg = &regs[regno];
 
 	if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) {
-		reg->type = type;
+		if (type == UNKNOWN_VALUE) {
+			__mark_reg_unknown_value(regs, regno);
+		} else if (reg->map_ptr->inner_map_meta) {
+			reg->type = CONST_PTR_TO_MAP;
+			reg->map_ptr = reg->map_ptr->inner_map_meta;
+		} else {
+			reg->type = type;
+		}
 		/* We don't need id from this point onwards anymore, thus we
 		 * should better reset it, so that state pruning has chances
 		 * to take effect.
 		 */
 		reg->id = 0;
-		if (type == UNKNOWN_VALUE)
-			__mark_reg_unknown_value(regs, regno);
 	}
 }
 
@@ -2960,7 +2978,7 @@ static int do_check(struct bpf_verifier_env *env)
 					return -EINVAL;
 				}
 
-				err = check_call(env, insn->imm);
+				err = check_call(env, insn->imm, insn_idx);
 				if (err)
 					return err;
 
@@ -3044,16 +3062,33 @@ process_bpf_exit:
 	return 0;
 }
 
+static int check_map_prealloc(struct bpf_map *map)
+{
+	return (map->map_type != BPF_MAP_TYPE_HASH &&
+		map->map_type != BPF_MAP_TYPE_PERCPU_HASH &&
+		map->map_type != BPF_MAP_TYPE_HASH_OF_MAPS) ||
+		!(map->map_flags & BPF_F_NO_PREALLOC);
+}
+
 static int check_map_prog_compatibility(struct bpf_map *map,
 					struct bpf_prog *prog)
 
 {
-	if (prog->type == BPF_PROG_TYPE_PERF_EVENT &&
-	    (map->map_type == BPF_MAP_TYPE_HASH ||
-	     map->map_type == BPF_MAP_TYPE_PERCPU_HASH) &&
-	    (map->map_flags & BPF_F_NO_PREALLOC)) {
-		verbose("perf_event programs can only use preallocated hash map\n");
-		return -EINVAL;
+	/* Make sure that BPF_PROG_TYPE_PERF_EVENT programs only use
+	 * preallocated hash maps, since doing memory allocation
+	 * in overflow_handler can crash depending on where nmi got
+	 * triggered.
+	 */
+	if (prog->type == BPF_PROG_TYPE_PERF_EVENT) {
+		if (!check_map_prealloc(map)) {
+			verbose("perf_event programs can only use preallocated hash map\n");
+			return -EINVAL;
+		}
+		if (map->inner_map_meta &&
+		    !check_map_prealloc(map->inner_map_meta)) {
+			verbose("perf_event programs can only use preallocated inner hash map\n");
+			return -EINVAL;
+		}
 	}
 	return 0;
 }
@@ -3182,6 +3217,41 @@ static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env)
 			insn->src_reg = 0;
 }
 
+/* single env->prog->insni[off] instruction was replaced with the range
+ * insni[off, off + cnt).  Adjust corresponding insn_aux_data by copying
+ * [0, off) and [off, end) to new locations, so the patched range stays zero
+ */
+static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len,
+				u32 off, u32 cnt)
+{
+	struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data;
+
+	if (cnt == 1)
+		return 0;
+	new_data = vzalloc(sizeof(struct bpf_insn_aux_data) * prog_len);
+	if (!new_data)
+		return -ENOMEM;
+	memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off);
+	memcpy(new_data + off + cnt - 1, old_data + off,
+	       sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1));
+	env->insn_aux_data = new_data;
+	vfree(old_data);
+	return 0;
+}
+
+static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
+					    const struct bpf_insn *patch, u32 len)
+{
+	struct bpf_prog *new_prog;
+
+	new_prog = bpf_patch_insn_single(env->prog, off, patch, len);
+	if (!new_prog)
+		return NULL;
+	if (adjust_insn_aux_data(env, new_prog->len, off, len))
+		return NULL;
+	return new_prog;
+}
+
 /* convert load instructions that access fields of 'struct __sk_buff'
  * into sequence of instructions that access fields of 'struct sk_buff'
  */
@@ -3201,10 +3271,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 			verbose("bpf verifier is misconfigured\n");
 			return -EINVAL;
 		} else if (cnt) {
-			new_prog = bpf_patch_insn_single(env->prog, 0,
-							 insn_buf, cnt);
+			new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt);
 			if (!new_prog)
 				return -ENOMEM;
+
 			env->prog = new_prog;
 			delta += cnt - 1;
 		}
@@ -3229,7 +3299,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		else
 			continue;
 
-		if (env->insn_aux_data[i].ptr_type != PTR_TO_CTX)
+		if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX)
 			continue;
 
 		cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog);
@@ -3238,8 +3308,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 			return -EINVAL;
 		}
 
-		new_prog = bpf_patch_insn_single(env->prog, i + delta, insn_buf,
-						 cnt);
+		new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
 		if (!new_prog)
 			return -ENOMEM;
 
@@ -3253,6 +3322,84 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 	return 0;
 }
 
+/* fixup insn->imm field of bpf_call instructions
+ * and inline eligible helpers as explicit sequence of BPF instructions
+ *
+ * this function is called after eBPF program passed verification
+ */
+static int fixup_bpf_calls(struct bpf_verifier_env *env)
+{
+	struct bpf_prog *prog = env->prog;
+	struct bpf_insn *insn = prog->insnsi;
+	const struct bpf_func_proto *fn;
+	const int insn_cnt = prog->len;
+	struct bpf_insn insn_buf[16];
+	struct bpf_prog *new_prog;
+	struct bpf_map *map_ptr;
+	int i, cnt, delta = 0;
+
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		if (insn->code != (BPF_JMP | BPF_CALL))
+			continue;
+
+		if (insn->imm == BPF_FUNC_get_route_realm)
+			prog->dst_needed = 1;
+		if (insn->imm == BPF_FUNC_get_prandom_u32)
+			bpf_user_rnd_init_once();
+		if (insn->imm == BPF_FUNC_xdp_adjust_head)
+			prog->xdp_adjust_head = 1;
+		if (insn->imm == BPF_FUNC_tail_call) {
+			/* mark bpf_tail_call as different opcode to avoid
+			 * conditional branch in the interpeter for every normal
+			 * call and to prevent accidental JITing by JIT compiler
+			 * that doesn't support bpf_tail_call yet
+			 */
+			insn->imm = 0;
+			insn->code |= BPF_X;
+			continue;
+		}
+
+		if (ebpf_jit_enabled() && insn->imm == BPF_FUNC_map_lookup_elem) {
+			map_ptr = env->insn_aux_data[i + delta].map_ptr;
+			if (map_ptr == BPF_MAP_PTR_POISON ||
+			    !map_ptr->ops->map_gen_lookup)
+				goto patch_call_imm;
+
+			cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf);
+			if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
+				verbose("bpf verifier is misconfigured\n");
+				return -EINVAL;
+			}
+
+			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf,
+						       cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta += cnt - 1;
+
+			/* keep walking new program and skip insns we just inserted */
+			env->prog = prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			continue;
+		}
+
+patch_call_imm:
+		fn = prog->aux->ops->get_func_proto(insn->imm);
+		/* all functions that have prototype and verifier allowed
+		 * programs to call them, must be real in-kernel functions
+		 */
+		if (!fn->func) {
+			verbose("kernel subsystem misconfigured func %s#%d\n",
+				func_id_name(insn->imm), insn->imm);
+			return -EFAULT;
+		}
+		insn->imm = fn->func - __bpf_call_base;
+	}
+
+	return 0;
+}
+
 static void free_states(struct bpf_verifier_env *env)
 {
 	struct bpf_verifier_state_list *sl, *sln;
@@ -3348,6 +3495,9 @@ skip_full_check:
 		/* program is valid, convert *(u32*)(ctx + off) accesses */
 		ret = convert_ctx_accesses(env);
 
+	if (ret == 0)
+		ret = fixup_bpf_calls(env);
+
 	if (log_level && log_len >= log_size - 1) {
 		BUG_ON(log_len >= log_size);
 		/* verifier log exceeded user supplied buffer */
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index e97ab824e368..9ee5787634e5 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -562,8 +562,7 @@ static int vlan_dev_init(struct net_device *dev)
 			   NETIF_F_HIGHDMA | NETIF_F_SCTP_CRC |
 			   NETIF_F_ALL_FCOE;
 
-	dev->features |= real_dev->vlan_features | NETIF_F_LLTX |
-			 NETIF_F_GSO_SOFTWARE;
+	dev->features |= dev->hw_features | NETIF_F_LLTX;
 	dev->gso_max_size = real_dev->gso_max_size;
 	dev->gso_max_segs = real_dev->gso_max_segs;
 	if (dev->features & NETIF_F_VLAN_FEATURES)
diff --git a/net/Makefile b/net/Makefile
index 9b681550e3a3..9086ffbb5085 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -12,7 +12,7 @@ obj-$(CONFIG_NET)		+= $(tmp-y)
 
 # LLC has to be linked before the files in net/802/
 obj-$(CONFIG_LLC)		+= llc/
-obj-$(CONFIG_NET)		+= ethernet/ 802/ sched/ netlink/
+obj-$(CONFIG_NET)		+= ethernet/ 802/ sched/ netlink/ bpf/
 obj-$(CONFIG_NETFILTER)		+= netfilter/
 obj-$(CONFIG_INET)		+= ipv4/
 obj-$(CONFIG_XFRM)		+= xfrm/
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 53b4ac09e7b7..ec527b62f79d 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -106,7 +106,7 @@ static void unlink_clip_vcc(struct clip_vcc *clip_vcc)
 			entry->expires = jiffies - 1;
 			/* force resolution or expiration */
 			error = neigh_update(entry->neigh, NULL, NUD_NONE,
-					     NEIGH_UPDATE_F_ADMIN);
+					     NEIGH_UPDATE_F_ADMIN, 0);
 			if (error)
 				pr_crit("neigh_update failed with %d\n", error);
 			goto out;
@@ -481,7 +481,7 @@ static int clip_setentry(struct atm_vcc *vcc, __be32 ip)
 		link_vcc(clip_vcc, entry);
 	}
 	error = neigh_update(neigh, llc_oui, NUD_PERMANENT,
-			     NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN);
+			     NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN, 0);
 	neigh_release(neigh);
 	return error;
 }
diff --git a/net/atm/common.c b/net/atm/common.c
index 9613381f5db0..f06422f4108d 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -62,21 +62,16 @@ static void vcc_remove_socket(struct sock *sk)
 	write_unlock_irq(&vcc_sklist_lock);
 }
 
-static struct sk_buff *alloc_tx(struct atm_vcc *vcc, unsigned int size)
+static bool vcc_tx_ready(struct atm_vcc *vcc, unsigned int size)
 {
-	struct sk_buff *skb;
 	struct sock *sk = sk_atm(vcc);
 
 	if (sk_wmem_alloc_get(sk) && !atm_may_send(vcc, size)) {
 		pr_debug("Sorry: wmem_alloc = %d, size = %d, sndbuf = %d\n",
 			 sk_wmem_alloc_get(sk), size, sk->sk_sndbuf);
-		return NULL;
+		return false;
 	}
-	while (!(skb = alloc_skb(size, GFP_KERNEL)))
-		schedule();
-	pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize);
-	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
-	return skb;
+	return true;
 }
 
 static void vcc_sock_destruct(struct sock *sk)
@@ -606,7 +601,7 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
 	eff = (size+3) & ~3; /* align to word boundary */
 	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 	error = 0;
-	while (!(skb = alloc_tx(vcc, eff))) {
+	while (!vcc_tx_ready(vcc, eff)) {
 		if (m->msg_flags & MSG_DONTWAIT) {
 			error = -EAGAIN;
 			break;
@@ -628,6 +623,15 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
 	finish_wait(sk_sleep(sk), &wait);
 	if (error)
 		goto out;
+
+	skb = alloc_skb(eff, GFP_KERNEL);
+	if (!skb) {
+		error = -ENOMEM;
+		goto out;
+	}
+	pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize);
+	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
+
 	skb->dev = NULL; /* for paths shared with net_device interfaces */
 	ATM_SKB(skb)->atm_options = vcc->atm_options;
 	if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) {
diff --git a/net/bpf/Makefile b/net/bpf/Makefile
new file mode 100644
index 000000000000..27b2992a0692
--- /dev/null
+++ b/net/bpf/Makefile
@@ -0,0 +1 @@
+obj-y	:= test_run.o
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
new file mode 100644
index 000000000000..8a6d0a37c30c
--- /dev/null
+++ b/net/bpf/test_run.c
@@ -0,0 +1,172 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/bpf.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/etherdevice.h>
+#include <linux/filter.h>
+#include <linux/sched/signal.h>
+
+static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx)
+{
+	u32 ret;
+
+	preempt_disable();
+	rcu_read_lock();
+	ret = BPF_PROG_RUN(prog, ctx);
+	rcu_read_unlock();
+	preempt_enable();
+
+	return ret;
+}
+
+static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time)
+{
+	u64 time_start, time_spent = 0;
+	u32 ret = 0, i;
+
+	if (!repeat)
+		repeat = 1;
+	time_start = ktime_get_ns();
+	for (i = 0; i < repeat; i++) {
+		ret = bpf_test_run_one(prog, ctx);
+		if (need_resched()) {
+			if (signal_pending(current))
+				break;
+			time_spent += ktime_get_ns() - time_start;
+			cond_resched();
+			time_start = ktime_get_ns();
+		}
+	}
+	time_spent += ktime_get_ns() - time_start;
+	do_div(time_spent, repeat);
+	*time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent;
+
+	return ret;
+}
+
+static int bpf_test_finish(union bpf_attr __user *uattr, const void *data,
+			   u32 size, u32 retval, u32 duration)
+{
+	void __user *data_out = u64_to_user_ptr(uattr->test.data_out);
+	int err = -EFAULT;
+
+	if (data_out && copy_to_user(data_out, data, size))
+		goto out;
+	if (copy_to_user(&uattr->test.data_size_out, &size, sizeof(size)))
+		goto out;
+	if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval)))
+		goto out;
+	if (copy_to_user(&uattr->test.duration, &duration, sizeof(duration)))
+		goto out;
+	err = 0;
+out:
+	return err;
+}
+
+static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
+			   u32 headroom, u32 tailroom)
+{
+	void __user *data_in = u64_to_user_ptr(kattr->test.data_in);
+	void *data;
+
+	if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom)
+		return ERR_PTR(-EINVAL);
+
+	data = kzalloc(size + headroom + tailroom, GFP_USER);
+	if (!data)
+		return ERR_PTR(-ENOMEM);
+
+	if (copy_from_user(data + headroom, data_in, size)) {
+		kfree(data);
+		return ERR_PTR(-EFAULT);
+	}
+	return data;
+}
+
+int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
+			  union bpf_attr __user *uattr)
+{
+	bool is_l2 = false, is_direct_pkt_access = false;
+	u32 size = kattr->test.data_size_in;
+	u32 repeat = kattr->test.repeat;
+	u32 retval, duration;
+	struct sk_buff *skb;
+	void *data;
+	int ret;
+
+	data = bpf_test_init(kattr, size, NET_SKB_PAD,
+			     SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	switch (prog->type) {
+	case BPF_PROG_TYPE_SCHED_CLS:
+	case BPF_PROG_TYPE_SCHED_ACT:
+		is_l2 = true;
+		/* fall through */
+	case BPF_PROG_TYPE_LWT_IN:
+	case BPF_PROG_TYPE_LWT_OUT:
+	case BPF_PROG_TYPE_LWT_XMIT:
+		is_direct_pkt_access = true;
+		break;
+	default:
+		break;
+	}
+
+	skb = build_skb(data, 0);
+	if (!skb) {
+		kfree(data);
+		return -ENOMEM;
+	}
+
+	skb_reserve(skb, NET_SKB_PAD);
+	__skb_put(skb, size);
+	skb->protocol = eth_type_trans(skb, current->nsproxy->net_ns->loopback_dev);
+	skb_reset_network_header(skb);
+
+	if (is_l2)
+		__skb_push(skb, ETH_HLEN);
+	if (is_direct_pkt_access)
+		bpf_compute_data_end(skb);
+	retval = bpf_test_run(prog, skb, repeat, &duration);
+	if (!is_l2)
+		__skb_push(skb, ETH_HLEN);
+	size = skb->len;
+	/* bpf program can never convert linear skb to non-linear */
+	if (WARN_ON_ONCE(skb_is_nonlinear(skb)))
+		size = skb_headlen(skb);
+	ret = bpf_test_finish(uattr, skb->data, size, retval, duration);
+	kfree_skb(skb);
+	return ret;
+}
+
+int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
+			  union bpf_attr __user *uattr)
+{
+	u32 size = kattr->test.data_size_in;
+	u32 repeat = kattr->test.repeat;
+	struct xdp_buff xdp = {};
+	u32 retval, duration;
+	void *data;
+	int ret;
+
+	data = bpf_test_init(kattr, size, XDP_PACKET_HEADROOM, 0);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	xdp.data_hard_start = data;
+	xdp.data = data + XDP_PACKET_HEADROOM;
+	xdp.data_end = xdp.data + size;
+
+	retval = bpf_test_run(prog, &xdp, repeat, &duration);
+	if (xdp.data != data + XDP_PACKET_HEADROOM)
+		size = xdp.data_end - xdp.data;
+	ret = bpf_test_finish(uattr, xdp.data, size, retval, duration);
+	kfree(data);
+	return ret;
+}
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 6e08b7199dd7..5a40a87c4f4f 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -594,6 +594,9 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
 				fdb->updated = now;
 			if (unlikely(added_by_user))
 				fdb->added_by_user = 1;
+			/* Take over HW learned entry */
+			if (unlikely(fdb->added_by_external_learn))
+				fdb->added_by_external_learn = 0;
 			if (unlikely(fdb_modified))
 				fdb_notify(br, fdb, RTM_NEWNEIGH);
 		}
@@ -854,6 +857,8 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br,
 		br_fdb_update(br, p, addr, vid, true);
 		rcu_read_unlock();
 		local_bh_enable();
+	} else if (ndm->ndm_flags & NTF_EXT_LEARNED) {
+		err = br_fdb_external_learn_add(br, p, addr, vid);
 	} else {
 		spin_lock_bh(&br->hash_lock);
 		err = fdb_add_entry(br, p, addr, ndm->ndm_state,
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 8ac1770aa222..6eb52d422dd9 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -22,6 +22,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/if_ether.h>
 #include <linux/slab.h>
+#include <net/dsa.h>
 #include <net/sock.h>
 #include <linux/if_vlan.h>
 #include <net/switchdev.h>
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 1f1e62095464..067cf0313449 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -997,13 +997,10 @@ int br_nf_hook_thresh(unsigned int hook, struct net *net,
 	if (!elem)
 		return okfn(net, sk, skb);
 
-	/* We may already have this, but read-locks nest anyway */
-	rcu_read_lock();
 	nf_hook_state_init(&state, hook, NFPROTO_BRIDGE, indev, outdev,
 			   sk, net, okfn);
 
 	ret = nf_hook_slow(skb, &state, elem);
-	rcu_read_unlock();
 	if (ret == 1)
 		ret = okfn(net, sk, skb);
 
diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c
index 98b9c8e8615e..707caea39743 100644
--- a/net/bridge/netfilter/ebt_log.c
+++ b/net/bridge/netfilter/ebt_log.c
@@ -62,10 +62,10 @@ print_ports(const struct sk_buff *skb, uint8_t protocol, int offset)
 		pptr = skb_header_pointer(skb, offset,
 					  sizeof(_ports), &_ports);
 		if (pptr == NULL) {
-			printk(" INCOMPLETE TCP/UDP header");
+			pr_cont(" INCOMPLETE TCP/UDP header");
 			return;
 		}
-		printk(" SPT=%u DPT=%u", ntohs(pptr->src), ntohs(pptr->dst));
+		pr_cont(" SPT=%u DPT=%u", ntohs(pptr->src), ntohs(pptr->dst));
 	}
 }
 
@@ -100,11 +100,11 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum,
 
 		ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
 		if (ih == NULL) {
-			printk(" INCOMPLETE IP header");
+			pr_cont(" INCOMPLETE IP header");
 			goto out;
 		}
-		printk(" IP SRC=%pI4 IP DST=%pI4, IP tos=0x%02X, IP proto=%d",
-		       &ih->saddr, &ih->daddr, ih->tos, ih->protocol);
+		pr_cont(" IP SRC=%pI4 IP DST=%pI4, IP tos=0x%02X, IP proto=%d",
+			&ih->saddr, &ih->daddr, ih->tos, ih->protocol);
 		print_ports(skb, ih->protocol, ih->ihl*4);
 		goto out;
 	}
@@ -120,11 +120,11 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum,
 
 		ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
 		if (ih == NULL) {
-			printk(" INCOMPLETE IPv6 header");
+			pr_cont(" INCOMPLETE IPv6 header");
 			goto out;
 		}
-		printk(" IPv6 SRC=%pI6 IPv6 DST=%pI6, IPv6 priority=0x%01X, Next Header=%d",
-		       &ih->saddr, &ih->daddr, ih->priority, ih->nexthdr);
+		pr_cont(" IPv6 SRC=%pI6 IPv6 DST=%pI6, IPv6 priority=0x%01X, Next Header=%d",
+			&ih->saddr, &ih->daddr, ih->priority, ih->nexthdr);
 		nexthdr = ih->nexthdr;
 		offset_ph = ipv6_skip_exthdr(skb, sizeof(_iph), &nexthdr, &frag_off);
 		if (offset_ph == -1)
@@ -142,12 +142,12 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum,
 
 		ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph);
 		if (ah == NULL) {
-			printk(" INCOMPLETE ARP header");
+			pr_cont(" INCOMPLETE ARP header");
 			goto out;
 		}
-		printk(" ARP HTYPE=%d, PTYPE=0x%04x, OPCODE=%d",
-		       ntohs(ah->ar_hrd), ntohs(ah->ar_pro),
-		       ntohs(ah->ar_op));
+		pr_cont(" ARP HTYPE=%d, PTYPE=0x%04x, OPCODE=%d",
+			ntohs(ah->ar_hrd), ntohs(ah->ar_pro),
+			ntohs(ah->ar_op));
 
 		/* If it's for Ethernet and the lengths are OK,
 		 * then log the ARP payload
@@ -161,17 +161,17 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum,
 			ap = skb_header_pointer(skb, sizeof(_arph),
 						sizeof(_arpp), &_arpp);
 			if (ap == NULL) {
-				printk(" INCOMPLETE ARP payload");
+				pr_cont(" INCOMPLETE ARP payload");
 				goto out;
 			}
-			printk(" ARP MAC SRC=%pM ARP IP SRC=%pI4 ARP MAC DST=%pM ARP IP DST=%pI4",
-					ap->mac_src, ap->ip_src, ap->mac_dst, ap->ip_dst);
+			pr_cont(" ARP MAC SRC=%pM ARP IP SRC=%pI4 ARP MAC DST=%pM ARP IP DST=%pI4",
+				ap->mac_src, ap->ip_src,
+				ap->mac_dst, ap->ip_dst);
 		}
 	}
 out:
-	printk("\n");
+	pr_cont("\n");
 	spin_unlock_bh(&ebt_log_lock);
-
 }
 
 static unsigned int
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index 206dc266ecd2..346ef6b00b8f 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -375,11 +375,7 @@ static int nft_reject_bridge_init(const struct nft_ctx *ctx,
 				  const struct nlattr * const tb[])
 {
 	struct nft_reject *priv = nft_expr_priv(expr);
-	int icmp_code, err;
-
-	err = nft_reject_bridge_validate(ctx, expr, NULL);
-	if (err < 0)
-		return err;
+	int icmp_code;
 
 	if (tb[NFTA_REJECT_TYPE] == NULL)
 		return -EINVAL;
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 5488e4a6ccd0..abf7d854a94d 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -75,9 +75,7 @@ static int stats_timer __read_mostly = 1;
 module_param(stats_timer, int, S_IRUGO);
 MODULE_PARM_DESC(stats_timer, "enable timer for statistics (default:on)");
 
-/* receive filters subscribed for 'all' CAN devices */
-struct dev_rcv_lists can_rx_alldev_list;
-static DEFINE_SPINLOCK(can_rcvlists_lock);
+static int can_net_id;
 
 static struct kmem_cache *rcv_cache __read_mostly;
 
@@ -145,9 +143,6 @@ static int can_create(struct net *net, struct socket *sock, int protocol,
 	if (protocol < 0 || protocol >= CAN_NPROTO)
 		return -EINVAL;
 
-	if (!net_eq(net, &init_net))
-		return -EAFNOSUPPORT;
-
 	cp = can_get_proto(protocol);
 
 #ifdef CONFIG_MODULES
@@ -331,10 +326,11 @@ EXPORT_SYMBOL(can_send);
  * af_can rx path
  */
 
-static struct dev_rcv_lists *find_dev_rcv_lists(struct net_device *dev)
+static struct dev_rcv_lists *find_dev_rcv_lists(struct net *net,
+						struct net_device *dev)
 {
 	if (!dev)
-		return &can_rx_alldev_list;
+		return net->can.can_rx_alldev_list;
 	else
 		return (struct dev_rcv_lists *)dev->ml_priv;
 }
@@ -467,9 +463,9 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
  *  -ENOMEM on missing cache mem to create subscription entry
  *  -ENODEV unknown device
  */
-int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
-		    void (*func)(struct sk_buff *, void *), void *data,
-		    char *ident, struct sock *sk)
+int can_rx_register(struct net *net, struct net_device *dev, canid_t can_id,
+		    canid_t mask, void (*func)(struct sk_buff *, void *),
+		    void *data, char *ident, struct sock *sk)
 {
 	struct receiver *r;
 	struct hlist_head *rl;
@@ -481,13 +477,16 @@ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
 	if (dev && dev->type != ARPHRD_CAN)
 		return -ENODEV;
 
+	if (dev && !net_eq(net, dev_net(dev)))
+		return -ENODEV;
+
 	r = kmem_cache_alloc(rcv_cache, GFP_KERNEL);
 	if (!r)
 		return -ENOMEM;
 
-	spin_lock(&can_rcvlists_lock);
+	spin_lock(&net->can.can_rcvlists_lock);
 
-	d = find_dev_rcv_lists(dev);
+	d = find_dev_rcv_lists(net, dev);
 	if (d) {
 		rl = find_rcv_list(&can_id, &mask, d);
 
@@ -510,7 +509,7 @@ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
 		err = -ENODEV;
 	}
 
-	spin_unlock(&can_rcvlists_lock);
+	spin_unlock(&net->can.can_rcvlists_lock);
 
 	return err;
 }
@@ -540,8 +539,9 @@ static void can_rx_delete_receiver(struct rcu_head *rp)
  * Description:
  *  Removes subscription entry depending on given (subscription) values.
  */
-void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask,
-		       void (*func)(struct sk_buff *, void *), void *data)
+void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id,
+		       canid_t mask, void (*func)(struct sk_buff *, void *),
+		       void *data)
 {
 	struct receiver *r = NULL;
 	struct hlist_head *rl;
@@ -550,9 +550,12 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask,
 	if (dev && dev->type != ARPHRD_CAN)
 		return;
 
-	spin_lock(&can_rcvlists_lock);
+	if (dev && !net_eq(net, dev_net(dev)))
+		return;
 
-	d = find_dev_rcv_lists(dev);
+	spin_lock(&net->can.can_rcvlists_lock);
+
+	d = find_dev_rcv_lists(net, dev);
 	if (!d) {
 		pr_err("BUG: receive list not found for "
 		       "dev %s, id %03X, mask %03X\n",
@@ -598,7 +601,7 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask,
 	}
 
  out:
-	spin_unlock(&can_rcvlists_lock);
+	spin_unlock(&net->can.can_rcvlists_lock);
 
 	/* schedule the receiver item for deletion */
 	if (r) {
@@ -696,10 +699,10 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev)
 	rcu_read_lock();
 
 	/* deliver the packet to sockets listening on all devices */
-	matches = can_rcv_filter(&can_rx_alldev_list, skb);
+	matches = can_rcv_filter(dev_net(dev)->can.can_rx_alldev_list, skb);
 
 	/* find receive list for this device */
-	d = find_dev_rcv_lists(dev);
+	d = find_dev_rcv_lists(dev_net(dev), dev);
 	if (d)
 		matches += can_rcv_filter(d, skb);
 
@@ -719,9 +722,6 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
 
-	if (unlikely(!net_eq(dev_net(dev), &init_net)))
-		goto drop;
-
 	if (WARN_ONCE(dev->type != ARPHRD_CAN ||
 		      skb->len != CAN_MTU ||
 		      cfd->len > CAN_MAX_DLEN,
@@ -743,9 +743,6 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
 
-	if (unlikely(!net_eq(dev_net(dev), &init_net)))
-		goto drop;
-
 	if (WARN_ONCE(dev->type != ARPHRD_CAN ||
 		      skb->len != CANFD_MTU ||
 		      cfd->len > CANFD_MAX_DLEN,
@@ -835,9 +832,6 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct dev_rcv_lists *d;
 
-	if (!net_eq(dev_net(dev), &init_net))
-		return NOTIFY_DONE;
-
 	if (dev->type != ARPHRD_CAN)
 		return NOTIFY_DONE;
 
@@ -855,7 +849,7 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg,
 		break;
 
 	case NETDEV_UNREGISTER:
-		spin_lock(&can_rcvlists_lock);
+		spin_lock(&dev_net(dev)->can.can_rcvlists_lock);
 
 		d = dev->ml_priv;
 		if (d) {
@@ -869,7 +863,7 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg,
 			pr_err("can: notifier: receive list not found for dev "
 			       "%s\n", dev->name);
 
-		spin_unlock(&can_rcvlists_lock);
+		spin_unlock(&dev_net(dev)->can.can_rcvlists_lock);
 
 		break;
 	}
@@ -877,6 +871,40 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg,
 	return NOTIFY_DONE;
 }
 
+static int can_pernet_init(struct net *net)
+{
+	net->can.can_rcvlists_lock =
+		__SPIN_LOCK_UNLOCKED(net->can.can_rcvlists_lock);
+	net->can.can_rx_alldev_list =
+		kzalloc(sizeof(struct dev_rcv_lists), GFP_KERNEL);
+
+	if (IS_ENABLED(CONFIG_PROC_FS))
+		can_init_proc(net);
+
+	return 0;
+}
+
+static void can_pernet_exit(struct net *net)
+{
+	struct net_device *dev;
+
+	if (IS_ENABLED(CONFIG_PROC_FS))
+		can_remove_proc(net);
+
+	/* remove created dev_rcv_lists from still registered CAN devices */
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
+		if (dev->type == ARPHRD_CAN && dev->ml_priv) {
+			struct dev_rcv_lists *d = dev->ml_priv;
+
+			BUG_ON(d->entries);
+			kfree(d);
+			dev->ml_priv = NULL;
+		}
+	}
+	rcu_read_unlock();
+}
+
 /*
  * af_can module init/exit functions
  */
@@ -902,6 +930,13 @@ static struct notifier_block can_netdev_notifier __read_mostly = {
 	.notifier_call = can_notifier,
 };
 
+static struct pernet_operations can_pernet_ops __read_mostly = {
+	.init = can_pernet_init,
+	.exit = can_pernet_exit,
+	.id = &can_net_id,
+	.size = 0,
+};
+
 static __init int can_init(void)
 {
 	/* check for correct padding to be able to use the structs similarly */
@@ -912,8 +947,6 @@ static __init int can_init(void)
 
 	pr_info("can: controller area network core (" CAN_VERSION_STRING ")\n");
 
-	memset(&can_rx_alldev_list, 0, sizeof(can_rx_alldev_list));
-
 	rcv_cache = kmem_cache_create("can_receiver", sizeof(struct receiver),
 				      0, 0, NULL);
 	if (!rcv_cache)
@@ -925,9 +958,10 @@ static __init int can_init(void)
 			setup_timer(&can_stattimer, can_stat_update, 0);
 			mod_timer(&can_stattimer, round_jiffies(jiffies + HZ));
 		}
-		can_init_proc();
 	}
 
+	register_pernet_subsys(&can_pernet_ops);
+
 	/* protocol register */
 	sock_register(&can_family_ops);
 	register_netdevice_notifier(&can_netdev_notifier);
@@ -939,13 +973,9 @@ static __init int can_init(void)
 
 static __exit void can_exit(void)
 {
-	struct net_device *dev;
-
 	if (IS_ENABLED(CONFIG_PROC_FS)) {
 		if (stats_timer)
 			del_timer_sync(&can_stattimer);
-
-		can_remove_proc();
 	}
 
 	/* protocol unregister */
@@ -954,19 +984,7 @@ static __exit void can_exit(void)
 	unregister_netdevice_notifier(&can_netdev_notifier);
 	sock_unregister(PF_CAN);
 
-	/* remove created dev_rcv_lists from still registered CAN devices */
-	rcu_read_lock();
-	for_each_netdev_rcu(&init_net, dev) {
-		if (dev->type == ARPHRD_CAN && dev->ml_priv) {
-
-			struct dev_rcv_lists *d = dev->ml_priv;
-
-			BUG_ON(d->entries);
-			kfree(d);
-			dev->ml_priv = NULL;
-		}
-	}
-	rcu_read_unlock();
+	unregister_pernet_subsys(&can_pernet_ops);
 
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 
diff --git a/net/can/af_can.h b/net/can/af_can.h
index b86f5129e838..f273c9d9b129 100644
--- a/net/can/af_can.h
+++ b/net/can/af_can.h
@@ -114,8 +114,8 @@ struct s_pstats {
 extern struct dev_rcv_lists can_rx_alldev_list;
 
 /* function prototypes for the CAN networklayer procfs (proc.c) */
-void can_init_proc(void);
-void can_remove_proc(void);
+void can_init_proc(struct net *net);
+void can_remove_proc(struct net *net);
 void can_stat_update(unsigned long data);
 
 /* structures and variables from af_can.c needed in proc.c for reading */
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 95d13b233c65..1976629a8463 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -764,8 +764,8 @@ static void bcm_remove_op(struct bcm_op *op)
 static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op)
 {
 	if (op->rx_reg_dev == dev) {
-		can_rx_unregister(dev, op->can_id, REGMASK(op->can_id),
-				  bcm_rx_handler, op);
+		can_rx_unregister(&init_net, dev, op->can_id,
+				  REGMASK(op->can_id), bcm_rx_handler, op);
 
 		/* mark as removed subscription */
 		op->rx_reg_dev = NULL;
@@ -808,7 +808,7 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
 					}
 				}
 			} else
-				can_rx_unregister(NULL, op->can_id,
+				can_rx_unregister(&init_net, NULL, op->can_id,
 						  REGMASK(op->can_id),
 						  bcm_rx_handler, op);
 
@@ -1222,7 +1222,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 
 			dev = dev_get_by_index(&init_net, ifindex);
 			if (dev) {
-				err = can_rx_register(dev, op->can_id,
+				err = can_rx_register(&init_net, dev,
+						      op->can_id,
 						      REGMASK(op->can_id),
 						      bcm_rx_handler, op,
 						      "bcm", sk);
@@ -1232,7 +1233,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			}
 
 		} else
-			err = can_rx_register(NULL, op->can_id,
+			err = can_rx_register(&init_net, NULL, op->can_id,
 					      REGMASK(op->can_id),
 					      bcm_rx_handler, op, "bcm", sk);
 		if (err) {
@@ -1528,7 +1529,7 @@ static int bcm_release(struct socket *sock)
 				}
 			}
 		} else
-			can_rx_unregister(NULL, op->can_id,
+			can_rx_unregister(&init_net, NULL, op->can_id,
 					  REGMASK(op->can_id),
 					  bcm_rx_handler, op);
 
diff --git a/net/can/gw.c b/net/can/gw.c
index 7056a1a2bb70..3c117a33e15f 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -440,14 +440,14 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
 
 static inline int cgw_register_filter(struct cgw_job *gwj)
 {
-	return can_rx_register(gwj->src.dev, gwj->ccgw.filter.can_id,
+	return can_rx_register(&init_net, gwj->src.dev, gwj->ccgw.filter.can_id,
 			       gwj->ccgw.filter.can_mask, can_can_gw_rcv,
 			       gwj, "gw", NULL);
 }
 
 static inline void cgw_unregister_filter(struct cgw_job *gwj)
 {
-	can_rx_unregister(gwj->src.dev, gwj->ccgw.filter.can_id,
+	can_rx_unregister(&init_net, gwj->src.dev, gwj->ccgw.filter.can_id,
 			  gwj->ccgw.filter.can_mask, can_can_gw_rcv, gwj);
 }
 
diff --git a/net/can/proc.c b/net/can/proc.c
index 85ef7bb0f176..9a8d54d57b22 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -62,17 +62,6 @@
 #define CAN_PROC_RCVLIST_EFF "rcvlist_eff"
 #define CAN_PROC_RCVLIST_ERR "rcvlist_err"
 
-static struct proc_dir_entry *can_dir;
-static struct proc_dir_entry *pde_version;
-static struct proc_dir_entry *pde_stats;
-static struct proc_dir_entry *pde_reset_stats;
-static struct proc_dir_entry *pde_rcvlist_all;
-static struct proc_dir_entry *pde_rcvlist_fil;
-static struct proc_dir_entry *pde_rcvlist_inv;
-static struct proc_dir_entry *pde_rcvlist_sff;
-static struct proc_dir_entry *pde_rcvlist_eff;
-static struct proc_dir_entry *pde_rcvlist_err;
-
 static int user_reset;
 
 static const char rx_list_name[][8] = {
@@ -351,20 +340,21 @@ static inline void can_rcvlist_proc_show_one(struct seq_file *m, int idx,
 static int can_rcvlist_proc_show(struct seq_file *m, void *v)
 {
 	/* double cast to prevent GCC warning */
-	int idx = (int)(long)m->private;
+	int idx = (int)(long)PDE_DATA(m->file->f_inode);
 	struct net_device *dev;
 	struct dev_rcv_lists *d;
+	struct net *net = m->private;
 
 	seq_printf(m, "\nreceive list '%s':\n", rx_list_name[idx]);
 
 	rcu_read_lock();
 
 	/* receive list for 'all' CAN devices (dev == NULL) */
-	d = &can_rx_alldev_list;
+	d = net->can.can_rx_alldev_list;
 	can_rcvlist_proc_show_one(m, idx, NULL, d);
 
 	/* receive list for registered CAN devices */
-	for_each_netdev_rcu(&init_net, dev) {
+	for_each_netdev_rcu(net, dev) {
 		if (dev->type == ARPHRD_CAN && dev->ml_priv)
 			can_rcvlist_proc_show_one(m, idx, dev, dev->ml_priv);
 	}
@@ -377,7 +367,7 @@ static int can_rcvlist_proc_show(struct seq_file *m, void *v)
 
 static int can_rcvlist_proc_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, can_rcvlist_proc_show, PDE_DATA(inode));
+	return single_open_net(inode, file, can_rcvlist_proc_show);
 }
 
 static const struct file_operations can_rcvlist_proc_fops = {
@@ -417,6 +407,7 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v)
 {
 	struct net_device *dev;
 	struct dev_rcv_lists *d;
+	struct net *net = m->private;
 
 	/* RX_SFF */
 	seq_puts(m, "\nreceive list 'rx_sff':\n");
@@ -424,11 +415,11 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v)
 	rcu_read_lock();
 
 	/* sff receive list for 'all' CAN devices (dev == NULL) */
-	d = &can_rx_alldev_list;
+	d = net->can.can_rx_alldev_list;
 	can_rcvlist_proc_show_array(m, NULL, d->rx_sff, ARRAY_SIZE(d->rx_sff));
 
 	/* sff receive list for registered CAN devices */
-	for_each_netdev_rcu(&init_net, dev) {
+	for_each_netdev_rcu(net, dev) {
 		if (dev->type == ARPHRD_CAN && dev->ml_priv) {
 			d = dev->ml_priv;
 			can_rcvlist_proc_show_array(m, dev, d->rx_sff,
@@ -444,7 +435,7 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v)
 
 static int can_rcvlist_sff_proc_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, can_rcvlist_sff_proc_show, NULL);
+	return single_open_net(inode, file, can_rcvlist_sff_proc_show);
 }
 
 static const struct file_operations can_rcvlist_sff_proc_fops = {
@@ -460,6 +451,7 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v)
 {
 	struct net_device *dev;
 	struct dev_rcv_lists *d;
+	struct net *net = m->private;
 
 	/* RX_EFF */
 	seq_puts(m, "\nreceive list 'rx_eff':\n");
@@ -467,11 +459,11 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v)
 	rcu_read_lock();
 
 	/* eff receive list for 'all' CAN devices (dev == NULL) */
-	d = &can_rx_alldev_list;
+	d = net->can.can_rx_alldev_list;
 	can_rcvlist_proc_show_array(m, NULL, d->rx_eff, ARRAY_SIZE(d->rx_eff));
 
 	/* eff receive list for registered CAN devices */
-	for_each_netdev_rcu(&init_net, dev) {
+	for_each_netdev_rcu(net, dev) {
 		if (dev->type == ARPHRD_CAN && dev->ml_priv) {
 			d = dev->ml_priv;
 			can_rcvlist_proc_show_array(m, dev, d->rx_eff,
@@ -487,7 +479,7 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v)
 
 static int can_rcvlist_eff_proc_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, can_rcvlist_eff_proc_show, NULL);
+	return single_open_net(inode, file, can_rcvlist_eff_proc_show);
 }
 
 static const struct file_operations can_rcvlist_eff_proc_fops = {
@@ -499,81 +491,85 @@ static const struct file_operations can_rcvlist_eff_proc_fops = {
 };
 
 /*
- * proc utility functions
- */
-
-static void can_remove_proc_readentry(const char *name)
-{
-	if (can_dir)
-		remove_proc_entry(name, can_dir);
-}
-
-/*
  * can_init_proc - create main CAN proc directory and procfs entries
  */
-void can_init_proc(void)
+void can_init_proc(struct net *net)
 {
 	/* create /proc/net/can directory */
-	can_dir = proc_mkdir("can", init_net.proc_net);
+	net->can.proc_dir = proc_net_mkdir(net, "can", net->proc_net);
 
-	if (!can_dir) {
-		pr_info("can: failed to create /proc/net/can.\n");
+	if (!net->can.proc_dir) {
+		printk(KERN_INFO "can: failed to create /proc/net/can . "
+			   "CONFIG_PROC_FS missing?\n");
 		return;
 	}
 
 	/* own procfs entries from the AF_CAN core */
-	pde_version     = proc_create(CAN_PROC_VERSION, 0644, can_dir,
-				      &can_version_proc_fops);
-	pde_stats       = proc_create(CAN_PROC_STATS, 0644, can_dir,
-				      &can_stats_proc_fops);
-	pde_reset_stats = proc_create(CAN_PROC_RESET_STATS, 0644, can_dir,
-				      &can_reset_stats_proc_fops);
-	pde_rcvlist_err = proc_create_data(CAN_PROC_RCVLIST_ERR, 0644, can_dir,
-					   &can_rcvlist_proc_fops, (void *)RX_ERR);
-	pde_rcvlist_all = proc_create_data(CAN_PROC_RCVLIST_ALL, 0644, can_dir,
-					   &can_rcvlist_proc_fops, (void *)RX_ALL);
-	pde_rcvlist_fil = proc_create_data(CAN_PROC_RCVLIST_FIL, 0644, can_dir,
-					   &can_rcvlist_proc_fops, (void *)RX_FIL);
-	pde_rcvlist_inv = proc_create_data(CAN_PROC_RCVLIST_INV, 0644, can_dir,
-					   &can_rcvlist_proc_fops, (void *)RX_INV);
-	pde_rcvlist_eff = proc_create(CAN_PROC_RCVLIST_EFF, 0644, can_dir,
-				      &can_rcvlist_eff_proc_fops);
-	pde_rcvlist_sff = proc_create(CAN_PROC_RCVLIST_SFF, 0644, can_dir,
-				      &can_rcvlist_sff_proc_fops);
+	net->can.pde_version     = proc_create(CAN_PROC_VERSION, 0644,
+					       net->can.proc_dir,
+					       &can_version_proc_fops);
+	net->can.pde_stats       = proc_create(CAN_PROC_STATS, 0644,
+					       net->can.proc_dir,
+					       &can_stats_proc_fops);
+	net->can.pde_reset_stats = proc_create(CAN_PROC_RESET_STATS, 0644,
+					       net->can.proc_dir,
+					       &can_reset_stats_proc_fops);
+	net->can.pde_rcvlist_err = proc_create_data(CAN_PROC_RCVLIST_ERR, 0644,
+						    net->can.proc_dir,
+						    &can_rcvlist_proc_fops,
+						    (void *)RX_ERR);
+	net->can.pde_rcvlist_all = proc_create_data(CAN_PROC_RCVLIST_ALL, 0644,
+						    net->can.proc_dir,
+						    &can_rcvlist_proc_fops,
+						    (void *)RX_ALL);
+	net->can.pde_rcvlist_fil = proc_create_data(CAN_PROC_RCVLIST_FIL, 0644,
+						    net->can.proc_dir,
+						    &can_rcvlist_proc_fops,
+						    (void *)RX_FIL);
+	net->can.pde_rcvlist_inv = proc_create_data(CAN_PROC_RCVLIST_INV, 0644,
+						    net->can.proc_dir,
+						    &can_rcvlist_proc_fops,
+						    (void *)RX_INV);
+	net->can.pde_rcvlist_eff = proc_create(CAN_PROC_RCVLIST_EFF, 0644,
+					       net->can.proc_dir,
+					       &can_rcvlist_eff_proc_fops);
+	net->can.pde_rcvlist_sff = proc_create(CAN_PROC_RCVLIST_SFF, 0644,
+					       net->can.proc_dir,
+					       &can_rcvlist_sff_proc_fops);
 }
 
 /*
  * can_remove_proc - remove procfs entries and main CAN proc directory
  */
-void can_remove_proc(void)
+void can_remove_proc(struct net *net)
 {
-	if (pde_version)
-		can_remove_proc_readentry(CAN_PROC_VERSION);
+	if (net->can.pde_version)
+		remove_proc_entry(CAN_PROC_VERSION, net->can.proc_dir);
 
-	if (pde_stats)
-		can_remove_proc_readentry(CAN_PROC_STATS);
+	if (net->can.pde_stats)
+		remove_proc_entry(CAN_PROC_STATS, net->can.proc_dir);
 
-	if (pde_reset_stats)
-		can_remove_proc_readentry(CAN_PROC_RESET_STATS);
+	if (net->can.pde_reset_stats)
+		remove_proc_entry(CAN_PROC_RESET_STATS, net->can.proc_dir);
 
-	if (pde_rcvlist_err)
-		can_remove_proc_readentry(CAN_PROC_RCVLIST_ERR);
+	if (net->can.pde_rcvlist_err)
+		remove_proc_entry(CAN_PROC_RCVLIST_ERR, net->can.proc_dir);
 
-	if (pde_rcvlist_all)
-		can_remove_proc_readentry(CAN_PROC_RCVLIST_ALL);
+	if (net->can.pde_rcvlist_all)
+		remove_proc_entry(CAN_PROC_RCVLIST_ALL, net->can.proc_dir);
 
-	if (pde_rcvlist_fil)
-		can_remove_proc_readentry(CAN_PROC_RCVLIST_FIL);
+	if (net->can.pde_rcvlist_fil)
+		remove_proc_entry(CAN_PROC_RCVLIST_FIL, net->can.proc_dir);
 
-	if (pde_rcvlist_inv)
-		can_remove_proc_readentry(CAN_PROC_RCVLIST_INV);
+	if (net->can.pde_rcvlist_inv)
+		remove_proc_entry(CAN_PROC_RCVLIST_INV, net->can.proc_dir);
 
-	if (pde_rcvlist_eff)
-		can_remove_proc_readentry(CAN_PROC_RCVLIST_EFF);
+	if (net->can.pde_rcvlist_eff)
+		remove_proc_entry(CAN_PROC_RCVLIST_EFF, net->can.proc_dir);
 
-	if (pde_rcvlist_sff)
-		can_remove_proc_readentry(CAN_PROC_RCVLIST_SFF);
+	if (net->can.pde_rcvlist_sff)
+		remove_proc_entry(CAN_PROC_RCVLIST_SFF, net->can.proc_dir);
 
-	if (can_dir)
-		remove_proc_entry("can", init_net.proc_net);
+	if (net->can.proc_dir)
+		remove_proc_entry("can", net->proc_net);
 }
diff --git a/net/can/raw.c b/net/can/raw.c
index 6dc546a06673..864c80dbdb72 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -181,20 +181,21 @@ static void raw_rcv(struct sk_buff *oskb, void *data)
 		kfree_skb(skb);
 }
 
-static int raw_enable_filters(struct net_device *dev, struct sock *sk,
-			      struct can_filter *filter, int count)
+static int raw_enable_filters(struct net *net, struct net_device *dev,
+			      struct sock *sk, struct can_filter *filter,
+			      int count)
 {
 	int err = 0;
 	int i;
 
 	for (i = 0; i < count; i++) {
-		err = can_rx_register(dev, filter[i].can_id,
+		err = can_rx_register(net, dev, filter[i].can_id,
 				      filter[i].can_mask,
 				      raw_rcv, sk, "raw", sk);
 		if (err) {
 			/* clean up successfully registered filters */
 			while (--i >= 0)
-				can_rx_unregister(dev, filter[i].can_id,
+				can_rx_unregister(net, dev, filter[i].can_id,
 						  filter[i].can_mask,
 						  raw_rcv, sk);
 			break;
@@ -204,57 +205,62 @@ static int raw_enable_filters(struct net_device *dev, struct sock *sk,
 	return err;
 }
 
-static int raw_enable_errfilter(struct net_device *dev, struct sock *sk,
-				can_err_mask_t err_mask)
+static int raw_enable_errfilter(struct net *net, struct net_device *dev,
+				struct sock *sk, can_err_mask_t err_mask)
 {
 	int err = 0;
 
 	if (err_mask)
-		err = can_rx_register(dev, 0, err_mask | CAN_ERR_FLAG,
+		err = can_rx_register(net, dev, 0, err_mask | CAN_ERR_FLAG,
 				      raw_rcv, sk, "raw", sk);
 
 	return err;
 }
 
-static void raw_disable_filters(struct net_device *dev, struct sock *sk,
-			      struct can_filter *filter, int count)
+static void raw_disable_filters(struct net *net, struct net_device *dev,
+				struct sock *sk, struct can_filter *filter,
+				int count)
 {
 	int i;
 
 	for (i = 0; i < count; i++)
-		can_rx_unregister(dev, filter[i].can_id, filter[i].can_mask,
-				  raw_rcv, sk);
+		can_rx_unregister(net, dev, filter[i].can_id,
+				  filter[i].can_mask, raw_rcv, sk);
 }
 
-static inline void raw_disable_errfilter(struct net_device *dev,
+static inline void raw_disable_errfilter(struct net *net,
+					 struct net_device *dev,
 					 struct sock *sk,
 					 can_err_mask_t err_mask)
 
 {
 	if (err_mask)
-		can_rx_unregister(dev, 0, err_mask | CAN_ERR_FLAG,
+		can_rx_unregister(net, dev, 0, err_mask | CAN_ERR_FLAG,
 				  raw_rcv, sk);
 }
 
-static inline void raw_disable_allfilters(struct net_device *dev,
+static inline void raw_disable_allfilters(struct net *net,
+					  struct net_device *dev,
 					  struct sock *sk)
 {
 	struct raw_sock *ro = raw_sk(sk);
 
-	raw_disable_filters(dev, sk, ro->filter, ro->count);
-	raw_disable_errfilter(dev, sk, ro->err_mask);
+	raw_disable_filters(net, dev, sk, ro->filter, ro->count);
+	raw_disable_errfilter(net, dev, sk, ro->err_mask);
 }
 
-static int raw_enable_allfilters(struct net_device *dev, struct sock *sk)
+static int raw_enable_allfilters(struct net *net, struct net_device *dev,
+				 struct sock *sk)
 {
 	struct raw_sock *ro = raw_sk(sk);
 	int err;
 
-	err = raw_enable_filters(dev, sk, ro->filter, ro->count);
+	err = raw_enable_filters(net, dev, sk, ro->filter, ro->count);
 	if (!err) {
-		err = raw_enable_errfilter(dev, sk, ro->err_mask);
+		err = raw_enable_errfilter(net, dev, sk, ro->err_mask);
 		if (err)
-			raw_disable_filters(dev, sk, ro->filter, ro->count);
+			raw_disable_filters(net, dev, sk, ro->filter,
+					    ro->count);
 	}
 
 	return err;
@@ -267,7 +273,7 @@ static int raw_notifier(struct notifier_block *nb,
 	struct raw_sock *ro = container_of(nb, struct raw_sock, notifier);
 	struct sock *sk = &ro->sk;
 
-	if (!net_eq(dev_net(dev), &init_net))
+	if (!net_eq(dev_net(dev), sock_net(sk)))
 		return NOTIFY_DONE;
 
 	if (dev->type != ARPHRD_CAN)
@@ -282,7 +288,7 @@ static int raw_notifier(struct notifier_block *nb,
 		lock_sock(sk);
 		/* remove current filters & unregister */
 		if (ro->bound)
-			raw_disable_allfilters(dev, sk);
+			raw_disable_allfilters(dev_net(dev), dev, sk);
 
 		if (ro->count > 1)
 			kfree(ro->filter);
@@ -358,13 +364,13 @@ static int raw_release(struct socket *sock)
 		if (ro->ifindex) {
 			struct net_device *dev;
 
-			dev = dev_get_by_index(&init_net, ro->ifindex);
+			dev = dev_get_by_index(sock_net(sk), ro->ifindex);
 			if (dev) {
-				raw_disable_allfilters(dev, sk);
+				raw_disable_allfilters(dev_net(dev), dev, sk);
 				dev_put(dev);
 			}
 		} else
-			raw_disable_allfilters(NULL, sk);
+			raw_disable_allfilters(sock_net(sk), NULL, sk);
 	}
 
 	if (ro->count > 1)
@@ -404,7 +410,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 	if (addr->can_ifindex) {
 		struct net_device *dev;
 
-		dev = dev_get_by_index(&init_net, addr->can_ifindex);
+		dev = dev_get_by_index(sock_net(sk), addr->can_ifindex);
 		if (!dev) {
 			err = -ENODEV;
 			goto out;
@@ -420,13 +426,13 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 		ifindex = dev->ifindex;
 
 		/* filters set by default/setsockopt */
-		err = raw_enable_allfilters(dev, sk);
+		err = raw_enable_allfilters(sock_net(sk), dev, sk);
 		dev_put(dev);
 	} else {
 		ifindex = 0;
 
 		/* filters set by default/setsockopt */
-		err = raw_enable_allfilters(NULL, sk);
+		err = raw_enable_allfilters(sock_net(sk), NULL, sk);
 	}
 
 	if (!err) {
@@ -435,13 +441,15 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 			if (ro->ifindex) {
 				struct net_device *dev;
 
-				dev = dev_get_by_index(&init_net, ro->ifindex);
+				dev = dev_get_by_index(sock_net(sk),
+						       ro->ifindex);
 				if (dev) {
-					raw_disable_allfilters(dev, sk);
+					raw_disable_allfilters(dev_net(dev),
+							       dev, sk);
 					dev_put(dev);
 				}
 			} else
-				raw_disable_allfilters(NULL, sk);
+				raw_disable_allfilters(sock_net(sk), NULL, sk);
 		}
 		ro->ifindex = ifindex;
 		ro->bound = 1;
@@ -517,15 +525,16 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		lock_sock(sk);
 
 		if (ro->bound && ro->ifindex)
-			dev = dev_get_by_index(&init_net, ro->ifindex);
+			dev = dev_get_by_index(sock_net(sk), ro->ifindex);
 
 		if (ro->bound) {
 			/* (try to) register the new filters */
 			if (count == 1)
-				err = raw_enable_filters(dev, sk, &sfilter, 1);
+				err = raw_enable_filters(sock_net(sk), dev, sk,
+							 &sfilter, 1);
 			else
-				err = raw_enable_filters(dev, sk, filter,
-							 count);
+				err = raw_enable_filters(sock_net(sk), dev, sk,
+							 filter, count);
 			if (err) {
 				if (count > 1)
 					kfree(filter);
@@ -533,7 +542,8 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 			}
 
 			/* remove old filter registrations */
-			raw_disable_filters(dev, sk, ro->filter, ro->count);
+			raw_disable_filters(sock_net(sk), dev, sk, ro->filter,
+					    ro->count);
 		}
 
 		/* remove old filter space */
@@ -569,18 +579,20 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		lock_sock(sk);
 
 		if (ro->bound && ro->ifindex)
-			dev = dev_get_by_index(&init_net, ro->ifindex);
+			dev = dev_get_by_index(sock_net(sk), ro->ifindex);
 
 		/* remove current error mask */
 		if (ro->bound) {
 			/* (try to) register the new err_mask */
-			err = raw_enable_errfilter(dev, sk, err_mask);
+			err = raw_enable_errfilter(sock_net(sk), dev, sk,
+						   err_mask);
 
 			if (err)
 				goto out_err;
 
 			/* remove old err_mask registration */
-			raw_disable_errfilter(dev, sk, ro->err_mask);
+			raw_disable_errfilter(sock_net(sk), dev, sk,
+					      ro->err_mask);
 		}
 
 		/* link new err_mask to the socket */
@@ -741,7 +753,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 			return -EINVAL;
 	}
 
-	dev = dev_get_by_index(&init_net, ifindex);
+	dev = dev_get_by_index(sock_net(sk), ifindex);
 	if (!dev)
 		return -ENXIO;
 
diff --git a/net/core/datagram.c b/net/core/datagram.c
index ea633342ab0d..4608aa245410 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -256,8 +256,12 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
 		}
 
 		spin_unlock_irqrestore(&queue->lock, cpu_flags);
-	} while (sk_can_busy_loop(sk) &&
-		 sk_busy_loop(sk, flags & MSG_DONTWAIT));
+
+		if (!sk_can_busy_loop(sk))
+			break;
+
+		sk_busy_loop(sk, flags & MSG_DONTWAIT);
+	} while (!skb_queue_empty(&sk->sk_receive_queue));
 
 	error = -EAGAIN;
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 7869ae3837ca..7efb4178ffef 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5060,27 +5060,28 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
 		do_softirq();
 }
 
-bool sk_busy_loop(struct sock *sk, int nonblock)
+void napi_busy_loop(unsigned int napi_id,
+		    bool (*loop_end)(void *, unsigned long),
+		    void *loop_end_arg)
 {
-	unsigned long end_time = !nonblock ? sk_busy_loop_end_time(sk) : 0;
+	unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
 	int (*napi_poll)(struct napi_struct *napi, int budget);
 	void *have_poll_lock = NULL;
 	struct napi_struct *napi;
-	int rc;
 
 restart:
-	rc = false;
 	napi_poll = NULL;
 
 	rcu_read_lock();
 
-	napi = napi_by_id(sk->sk_napi_id);
+	napi = napi_by_id(napi_id);
 	if (!napi)
 		goto out;
 
 	preempt_disable();
 	for (;;) {
-		rc = 0;
+		int work = 0;
+
 		local_bh_disable();
 		if (!napi_poll) {
 			unsigned long val = READ_ONCE(napi->state);
@@ -5098,16 +5099,15 @@ restart:
 			have_poll_lock = netpoll_poll_lock(napi);
 			napi_poll = napi->poll;
 		}
-		rc = napi_poll(napi, BUSY_POLL_BUDGET);
-		trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
+		work = napi_poll(napi, BUSY_POLL_BUDGET);
+		trace_napi_poll(napi, work, BUSY_POLL_BUDGET);
 count:
-		if (rc > 0)
-			__NET_ADD_STATS(sock_net(sk),
-					LINUX_MIB_BUSYPOLLRXPACKETS, rc);
+		if (work > 0)
+			__NET_ADD_STATS(dev_net(napi->dev),
+					LINUX_MIB_BUSYPOLLRXPACKETS, work);
 		local_bh_enable();
 
-		if (nonblock || !skb_queue_empty(&sk->sk_receive_queue) ||
-		    busy_loop_timeout(end_time))
+		if (!loop_end || loop_end(loop_end_arg, start_time))
 			break;
 
 		if (unlikely(need_resched())) {
@@ -5116,9 +5116,8 @@ count:
 			preempt_enable();
 			rcu_read_unlock();
 			cond_resched();
-			rc = !skb_queue_empty(&sk->sk_receive_queue);
-			if (rc || busy_loop_timeout(end_time))
-				return rc;
+			if (loop_end(loop_end_arg, start_time))
+				return;
 			goto restart;
 		}
 		cpu_relax();
@@ -5126,12 +5125,10 @@ count:
 	if (napi_poll)
 		busy_poll_stop(napi, have_poll_lock);
 	preempt_enable();
-	rc = !skb_queue_empty(&sk->sk_receive_queue);
 out:
 	rcu_read_unlock();
-	return rc;
 }
-EXPORT_SYMBOL(sk_busy_loop);
+EXPORT_SYMBOL(napi_busy_loop);
 
 #endif /* CONFIG_NET_RX_BUSY_POLL */
 
@@ -5143,10 +5140,10 @@ static void napi_hash_add(struct napi_struct *napi)
 
 	spin_lock(&napi_hash_lock);
 
-	/* 0..NR_CPUS+1 range is reserved for sender_cpu use */
+	/* 0..NR_CPUS range is reserved for sender_cpu use */
 	do {
-		if (unlikely(++napi_gen_id < NR_CPUS + 1))
-			napi_gen_id = NR_CPUS + 1;
+		if (unlikely(++napi_gen_id < MIN_NAPI_ID))
+			napi_gen_id = MIN_NAPI_ID;
 	} while (napi_by_id(napi_gen_id));
 	napi->napi_id = napi_gen_id;
 
@@ -6843,7 +6840,7 @@ static void rollback_registered_many(struct list_head *head)
 
 		if (!dev->rtnl_link_ops ||
 		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
-			skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U,
+			skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0,
 						     GFP_KERNEL);
 
 		/*
diff --git a/net/core/devlink.c b/net/core/devlink.c
index e9c1e6acfb6d..24b766003a61 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1493,8 +1493,686 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
 		if (err)
 			return err;
 	}
+	return 0;
+}
+
+int devlink_dpipe_match_put(struct sk_buff *skb,
+			    struct devlink_dpipe_match *match)
+{
+	struct devlink_dpipe_header *header = match->header;
+	struct devlink_dpipe_field *field = &header->fields[match->field_id];
+	struct nlattr *match_attr;
+
+	match_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_MATCH);
+	if (!match_attr)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_MATCH_TYPE, match->type) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, match->header_index) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
+	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, match_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, match_attr);
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_match_put);
+
+static int devlink_dpipe_matches_put(struct devlink_dpipe_table *table,
+				     struct sk_buff *skb)
+{
+	struct nlattr *matches_attr;
+
+	matches_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE_MATCHES);
+	if (!matches_attr)
+		return -EMSGSIZE;
+
+	if (table->table_ops->matches_dump(table->priv, skb))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, matches_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, matches_attr);
+	return -EMSGSIZE;
+}
+
+int devlink_dpipe_action_put(struct sk_buff *skb,
+			     struct devlink_dpipe_action *action)
+{
+	struct devlink_dpipe_header *header = action->header;
+	struct devlink_dpipe_field *field = &header->fields[action->field_id];
+	struct nlattr *action_attr;
+
+	action_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ACTION);
+	if (!action_attr)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_ACTION_TYPE, action->type) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, action->header_index) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
+	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, action_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, action_attr);
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_action_put);
+
+static int devlink_dpipe_actions_put(struct devlink_dpipe_table *table,
+				     struct sk_buff *skb)
+{
+	struct nlattr *actions_attr;
+
+	actions_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE_ACTIONS);
+	if (!actions_attr)
+		return -EMSGSIZE;
+
+	if (table->table_ops->actions_dump(table->priv, skb))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, actions_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, actions_attr);
+	return -EMSGSIZE;
+}
+
+static int devlink_dpipe_table_put(struct sk_buff *skb,
+				   struct devlink_dpipe_table *table)
+{
+	struct nlattr *table_attr;
+
+	table_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE);
+	if (!table_attr)
+		return -EMSGSIZE;
+
+	if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_TABLE_NAME, table->name) ||
+	    nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_SIZE, table->size,
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+	if (nla_put_u8(skb, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED,
+		       table->counters_enabled))
+		goto nla_put_failure;
+
+	if (devlink_dpipe_matches_put(table, skb))
+		goto nla_put_failure;
+
+	if (devlink_dpipe_actions_put(table, skb))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, table_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, table_attr);
+	return -EMSGSIZE;
+}
+
+static int devlink_dpipe_send_and_alloc_skb(struct sk_buff **pskb,
+					    struct genl_info *info)
+{
+	int err;
+
+	if (*pskb) {
+		err = genlmsg_reply(*pskb, info);
+		if (err)
+			return err;
+	}
+	*pskb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!*pskb)
+		return -ENOMEM;
+	return 0;
+}
+
+static int devlink_dpipe_tables_fill(struct genl_info *info,
+				     enum devlink_command cmd, int flags,
+				     struct list_head *dpipe_tables,
+				     const char *table_name)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_dpipe_table *table;
+	struct nlattr *tables_attr;
+	struct sk_buff *skb = NULL;
+	struct nlmsghdr *nlh;
+	bool incomplete;
+	void *hdr;
+	int i;
+	int err;
+
+	table = list_first_entry(dpipe_tables,
+				 struct devlink_dpipe_table, list);
+start_again:
+	err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+	if (err)
+		return err;
+
+	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
+			  &devlink_nl_family, NLM_F_MULTI, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(skb, devlink))
+		goto nla_put_failure;
+	tables_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLES);
+	if (!tables_attr)
+		goto nla_put_failure;
+
+	i = 0;
+	incomplete = false;
+	list_for_each_entry_from(table, dpipe_tables, list) {
+		if (!table_name) {
+			err = devlink_dpipe_table_put(skb, table);
+			if (err) {
+				if (!i)
+					goto err_table_put;
+				incomplete = true;
+				break;
+			}
+		} else {
+			if (!strcmp(table->name, table_name)) {
+				err = devlink_dpipe_table_put(skb, table);
+				if (err)
+					break;
+			}
+		}
+		i++;
+	}
+
+	nla_nest_end(skb, tables_attr);
+	genlmsg_end(skb, hdr);
+	if (incomplete)
+		goto start_again;
+
+send_done:
+	nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
+			NLMSG_DONE, 0, flags | NLM_F_MULTI);
+	if (!nlh) {
+		err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+		if (err)
+			goto err_skb_send_alloc;
+		goto send_done;
+	}
+
+	return genlmsg_reply(skb, info);
+
+nla_put_failure:
+	err = -EMSGSIZE;
+err_table_put:
+err_skb_send_alloc:
+	genlmsg_cancel(skb, hdr);
+	nlmsg_free(skb);
+	return err;
+}
+
+static int devlink_nl_cmd_dpipe_table_get(struct sk_buff *skb,
+					  struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	const char *table_name =  NULL;
+
+	if (info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME])
+		table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
+
+	return devlink_dpipe_tables_fill(info, DEVLINK_CMD_DPIPE_TABLE_GET, 0,
+					 &devlink->dpipe_table_list,
+					 table_name);
+}
+
+static int devlink_dpipe_value_put(struct sk_buff *skb,
+				   struct devlink_dpipe_value *value)
+{
+	if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE,
+		    value->value_size, value->value))
+		return -EMSGSIZE;
+	if (value->mask)
+		if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE_MASK,
+			    value->value_size, value->mask))
+			return -EMSGSIZE;
+	if (value->mapping_valid)
+		if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_VALUE_MAPPING,
+				value->mapping_value))
+			return -EMSGSIZE;
+	return 0;
+}
+
+static int devlink_dpipe_action_value_put(struct sk_buff *skb,
+					  struct devlink_dpipe_value *value)
+{
+	if (!value->action)
+		return -EINVAL;
+	if (devlink_dpipe_action_put(skb, value->action))
+		return -EMSGSIZE;
+	if (devlink_dpipe_value_put(skb, value))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int devlink_dpipe_action_values_put(struct sk_buff *skb,
+					   struct devlink_dpipe_value *values,
+					   unsigned int values_count)
+{
+	struct nlattr *action_attr;
+	int i;
+	int err;
+
+	for (i = 0; i < values_count; i++) {
+		action_attr = nla_nest_start(skb,
+					     DEVLINK_ATTR_DPIPE_ACTION_VALUE);
+		if (!action_attr)
+			return -EMSGSIZE;
+		err = devlink_dpipe_action_value_put(skb, &values[i]);
+		if (err)
+			goto err_action_value_put;
+		nla_nest_end(skb, action_attr);
+	}
+	return 0;
+
+err_action_value_put:
+	nla_nest_cancel(skb, action_attr);
+	return err;
+}
+
+static int devlink_dpipe_match_value_put(struct sk_buff *skb,
+					 struct devlink_dpipe_value *value)
+{
+	if (!value->match)
+		return -EINVAL;
+	if (devlink_dpipe_match_put(skb, value->match))
+		return -EMSGSIZE;
+	if (devlink_dpipe_value_put(skb, value))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int devlink_dpipe_match_values_put(struct sk_buff *skb,
+					  struct devlink_dpipe_value *values,
+					  unsigned int values_count)
+{
+	struct nlattr *match_attr;
+	int i;
+	int err;
+
+	for (i = 0; i < values_count; i++) {
+		match_attr = nla_nest_start(skb,
+					    DEVLINK_ATTR_DPIPE_MATCH_VALUE);
+		if (!match_attr)
+			return -EMSGSIZE;
+		err = devlink_dpipe_match_value_put(skb, &values[i]);
+		if (err)
+			goto err_match_value_put;
+		nla_nest_end(skb, match_attr);
+	}
+	return 0;
+
+err_match_value_put:
+	nla_nest_cancel(skb, match_attr);
+	return err;
+}
+
+static int devlink_dpipe_entry_put(struct sk_buff *skb,
+				   struct devlink_dpipe_entry *entry)
+{
+	struct nlattr *entry_attr, *matches_attr, *actions_attr;
+	int err;
+
+	entry_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ENTRY);
+	if (!entry_attr)
+		return  -EMSGSIZE;
+
+	if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_INDEX, entry->index,
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+	if (entry->counter_valid)
+		if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_COUNTER,
+				      entry->counter, DEVLINK_ATTR_PAD))
+			goto nla_put_failure;
+
+	matches_attr = nla_nest_start(skb,
+				      DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES);
+	if (!matches_attr)
+		goto nla_put_failure;
+
+	err = devlink_dpipe_match_values_put(skb, entry->match_values,
+					     entry->match_values_count);
+	if (err) {
+		nla_nest_cancel(skb, matches_attr);
+		goto err_match_values_put;
+	}
+	nla_nest_end(skb, matches_attr);
+
+	actions_attr = nla_nest_start(skb,
+				      DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES);
+	if (!actions_attr)
+		goto nla_put_failure;
+
+	err = devlink_dpipe_action_values_put(skb, entry->action_values,
+					      entry->action_values_count);
+	if (err) {
+		nla_nest_cancel(skb, actions_attr);
+		goto err_action_values_put;
+	}
+	nla_nest_end(skb, actions_attr);
 
+	nla_nest_end(skb, entry_attr);
 	return 0;
+
+nla_put_failure:
+	err = -EMSGSIZE;
+err_match_values_put:
+err_action_values_put:
+	nla_nest_cancel(skb, entry_attr);
+	return err;
+}
+
+static struct devlink_dpipe_table *
+devlink_dpipe_table_find(struct list_head *dpipe_tables,
+			 const char *table_name)
+{
+	struct devlink_dpipe_table *table;
+
+	list_for_each_entry_rcu(table, dpipe_tables, list) {
+		if (!strcmp(table->name, table_name))
+			return table;
+	}
+	return NULL;
+}
+
+int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+	struct devlink *devlink;
+	int err;
+
+	err = devlink_dpipe_send_and_alloc_skb(&dump_ctx->skb,
+					       dump_ctx->info);
+	if (err)
+		return err;
+
+	dump_ctx->hdr = genlmsg_put(dump_ctx->skb,
+				    dump_ctx->info->snd_portid,
+				    dump_ctx->info->snd_seq,
+				    &devlink_nl_family, NLM_F_MULTI,
+				    dump_ctx->cmd);
+	if (!dump_ctx->hdr)
+		goto nla_put_failure;
+
+	devlink = dump_ctx->info->user_ptr[0];
+	if (devlink_nl_put_handle(dump_ctx->skb, devlink))
+		goto nla_put_failure;
+	dump_ctx->nest = nla_nest_start(dump_ctx->skb,
+					DEVLINK_ATTR_DPIPE_ENTRIES);
+	if (!dump_ctx->nest)
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(dump_ctx->skb, dump_ctx->hdr);
+	nlmsg_free(dump_ctx->skb);
+	return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_prepare);
+
+int devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx,
+				   struct devlink_dpipe_entry *entry)
+{
+	return devlink_dpipe_entry_put(dump_ctx->skb, entry);
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_append);
+
+int devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+	nla_nest_end(dump_ctx->skb, dump_ctx->nest);
+	genlmsg_end(dump_ctx->skb, dump_ctx->hdr);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_close);
+
+static int devlink_dpipe_entries_fill(struct genl_info *info,
+				      enum devlink_command cmd, int flags,
+				      struct devlink_dpipe_table *table)
+{
+	struct devlink_dpipe_dump_ctx dump_ctx;
+	struct nlmsghdr *nlh;
+	int err;
+
+	dump_ctx.skb = NULL;
+	dump_ctx.cmd = cmd;
+	dump_ctx.info = info;
+
+	err = table->table_ops->entries_dump(table->priv,
+					     table->counters_enabled,
+					     &dump_ctx);
+	if (err)
+		goto err_entries_dump;
+
+send_done:
+	nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq,
+			NLMSG_DONE, 0, flags | NLM_F_MULTI);
+	if (!nlh) {
+		err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info);
+		if (err)
+			goto err_skb_send_alloc;
+		goto send_done;
+	}
+	return genlmsg_reply(dump_ctx.skb, info);
+
+err_entries_dump:
+err_skb_send_alloc:
+	genlmsg_cancel(dump_ctx.skb, dump_ctx.hdr);
+	nlmsg_free(dump_ctx.skb);
+	return err;
+}
+
+static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb,
+					    struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_dpipe_table *table;
+	const char *table_name;
+
+	if (!info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME])
+		return -EINVAL;
+
+	table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name);
+	if (!table)
+		return -EINVAL;
+
+	if (!table->table_ops->entries_dump)
+		return -EINVAL;
+
+	return devlink_dpipe_entries_fill(info, DEVLINK_CMD_DPIPE_ENTRIES_GET,
+					  0, table);
+}
+
+static int devlink_dpipe_fields_put(struct sk_buff *skb,
+				    const struct devlink_dpipe_header *header)
+{
+	struct devlink_dpipe_field *field;
+	struct nlattr *field_attr;
+	int i;
+
+	for (i = 0; i < header->fields_count; i++) {
+		field = &header->fields[i];
+		field_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_FIELD);
+		if (!field_attr)
+			return -EMSGSIZE;
+		if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_FIELD_NAME, field->name) ||
+		    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
+		    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH, field->bitwidth) ||
+		    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE, field->mapping_type))
+			goto nla_put_failure;
+		nla_nest_end(skb, field_attr);
+	}
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, field_attr);
+	return -EMSGSIZE;
+}
+
+static int devlink_dpipe_header_put(struct sk_buff *skb,
+				    struct devlink_dpipe_header *header)
+{
+	struct nlattr *fields_attr, *header_attr;
+	int err;
+
+	header_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADER);
+	if (!header)
+		return -EMSGSIZE;
+
+	if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_HEADER_NAME, header->name) ||
+	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
+	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
+		goto nla_put_failure;
+
+	fields_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADER_FIELDS);
+	if (!fields_attr)
+		goto nla_put_failure;
+
+	err = devlink_dpipe_fields_put(skb, header);
+	if (err) {
+		nla_nest_cancel(skb, fields_attr);
+		goto nla_put_failure;
+	}
+	nla_nest_end(skb, fields_attr);
+	nla_nest_end(skb, header_attr);
+	return 0;
+
+nla_put_failure:
+	err = -EMSGSIZE;
+	nla_nest_cancel(skb, header_attr);
+	return err;
+}
+
+static int devlink_dpipe_headers_fill(struct genl_info *info,
+				      enum devlink_command cmd, int flags,
+				      struct devlink_dpipe_headers *
+				      dpipe_headers)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct nlattr *headers_attr;
+	struct sk_buff *skb = NULL;
+	struct nlmsghdr *nlh;
+	void *hdr;
+	int i, j;
+	int err;
+
+	i = 0;
+start_again:
+	err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+	if (err)
+		return err;
+
+	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
+			  &devlink_nl_family, NLM_F_MULTI, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(skb, devlink))
+		goto nla_put_failure;
+	headers_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADERS);
+	if (!headers_attr)
+		goto nla_put_failure;
+
+	j = 0;
+	for (; i < dpipe_headers->headers_count; i++) {
+		err = devlink_dpipe_header_put(skb, dpipe_headers->headers[i]);
+		if (err) {
+			if (!j)
+				goto err_table_put;
+			break;
+		}
+		j++;
+	}
+	nla_nest_end(skb, headers_attr);
+	genlmsg_end(skb, hdr);
+	if (i != dpipe_headers->headers_count)
+		goto start_again;
+
+send_done:
+	nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
+			NLMSG_DONE, 0, flags | NLM_F_MULTI);
+	if (!nlh) {
+		err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+		if (err)
+			goto err_skb_send_alloc;
+		goto send_done;
+	}
+	return genlmsg_reply(skb, info);
+
+nla_put_failure:
+	err = -EMSGSIZE;
+err_table_put:
+err_skb_send_alloc:
+	genlmsg_cancel(skb, hdr);
+	nlmsg_free(skb);
+	return err;
+}
+
+static int devlink_nl_cmd_dpipe_headers_get(struct sk_buff *skb,
+					    struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+
+	if (!devlink->dpipe_headers)
+		return -EOPNOTSUPP;
+	return devlink_dpipe_headers_fill(info, DEVLINK_CMD_DPIPE_HEADERS_GET,
+					  0, devlink->dpipe_headers);
+}
+
+static int devlink_dpipe_table_counters_set(struct devlink *devlink,
+					    const char *table_name,
+					    bool enable)
+{
+	struct devlink_dpipe_table *table;
+
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name);
+	if (!table)
+		return -EINVAL;
+
+	if (table->counter_control_extern)
+		return -EOPNOTSUPP;
+
+	if (!(table->counters_enabled ^ enable))
+		return 0;
+
+	table->counters_enabled = enable;
+	if (table->table_ops->counters_set_update)
+		table->table_ops->counters_set_update(table->priv, enable);
+	return 0;
+}
+
+static int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb,
+						   struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	const char *table_name;
+	bool counters_enable;
+
+	if (!info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME] ||
+	    !info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED])
+		return -EINVAL;
+
+	table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
+	counters_enable = !!nla_get_u8(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED]);
+
+	return devlink_dpipe_table_counters_set(devlink, table_name,
+						counters_enable);
 }
 
 static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
@@ -1512,6 +2190,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 },
 	[DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 },
 	[DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 },
 };
 
 static const struct genl_ops devlink_nl_ops[] = {
@@ -1644,6 +2324,34 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_TABLE_GET,
+		.doit = devlink_nl_cmd_dpipe_table_get,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET,
+		.doit = devlink_nl_cmd_dpipe_entries_get,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_HEADERS_GET,
+		.doit = devlink_nl_cmd_dpipe_headers_get,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
+	{
+		.cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
+		.doit = devlink_nl_cmd_dpipe_table_counters_set,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
 };
 
 static struct genl_family devlink_nl_family __ro_after_init = {
@@ -1680,6 +2388,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
 	devlink_net_set(devlink, &init_net);
 	INIT_LIST_HEAD(&devlink->port_list);
 	INIT_LIST_HEAD(&devlink->sb_list);
+	INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list);
 	return devlink;
 }
 EXPORT_SYMBOL_GPL(devlink_alloc);
@@ -1880,6 +2589,133 @@ void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index)
 }
 EXPORT_SYMBOL_GPL(devlink_sb_unregister);
 
+/**
+ *	devlink_dpipe_headers_register - register dpipe headers
+ *
+ *	@devlink: devlink
+ *	@dpipe_headers: dpipe header array
+ *
+ *	Register the headers supported by hardware.
+ */
+int devlink_dpipe_headers_register(struct devlink *devlink,
+				   struct devlink_dpipe_headers *dpipe_headers)
+{
+	mutex_lock(&devlink_mutex);
+	devlink->dpipe_headers = dpipe_headers;
+	mutex_unlock(&devlink_mutex);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_headers_register);
+
+/**
+ *	devlink_dpipe_headers_unregister - unregister dpipe headers
+ *
+ *	@devlink: devlink
+ *
+ *	Unregister the headers supported by hardware.
+ */
+void devlink_dpipe_headers_unregister(struct devlink *devlink)
+{
+	mutex_lock(&devlink_mutex);
+	devlink->dpipe_headers = NULL;
+	mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_headers_unregister);
+
+/**
+ *	devlink_dpipe_table_counter_enabled - check if counter allocation
+ *					      required
+ *	@devlink: devlink
+ *	@table_name: tables name
+ *
+ *	Used by driver to check if counter allocation is required.
+ *	After counter allocation is turned on the table entries
+ *	are updated to include counter statistics.
+ *
+ *	After that point on the driver must respect the counter
+ *	state so that each entry added to the table is added
+ *	with a counter.
+ */
+bool devlink_dpipe_table_counter_enabled(struct devlink *devlink,
+					 const char *table_name)
+{
+	struct devlink_dpipe_table *table;
+	bool enabled;
+
+	rcu_read_lock();
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name);
+	enabled = false;
+	if (table)
+		enabled = table->counters_enabled;
+	rcu_read_unlock();
+	return enabled;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_table_counter_enabled);
+
+/**
+ *	devlink_dpipe_table_register - register dpipe table
+ *
+ *	@devlink: devlink
+ *	@table_name: table name
+ *	@table_ops: table ops
+ *	@priv: priv
+ *	@size: size
+ *	@counter_control_extern: external control for counters
+ */
+int devlink_dpipe_table_register(struct devlink *devlink,
+				 const char *table_name,
+				 struct devlink_dpipe_table_ops *table_ops,
+				 void *priv, u64 size,
+				 bool counter_control_extern)
+{
+	struct devlink_dpipe_table *table;
+
+	if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name))
+		return -EEXIST;
+
+	table = kzalloc(sizeof(*table), GFP_KERNEL);
+	if (!table)
+		return -ENOMEM;
+
+	table->name = table_name;
+	table->table_ops = table_ops;
+	table->priv = priv;
+	table->size = size;
+	table->counter_control_extern = counter_control_extern;
+
+	mutex_lock(&devlink_mutex);
+	list_add_tail_rcu(&table->list, &devlink->dpipe_table_list);
+	mutex_unlock(&devlink_mutex);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_table_register);
+
+/**
+ *	devlink_dpipe_table_unregister - unregister dpipe table
+ *
+ *	@devlink: devlink
+ *	@table_name: table name
+ */
+void devlink_dpipe_table_unregister(struct devlink *devlink,
+				    const char *table_name)
+{
+	struct devlink_dpipe_table *table;
+
+	mutex_lock(&devlink_mutex);
+	table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+					 table_name);
+	if (!table)
+		goto unlock;
+	list_del_rcu(&table->list);
+	mutex_unlock(&devlink_mutex);
+	kfree_rcu(table, rcu);
+	return;
+unlock:
+	mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_table_unregister);
+
 static int __init devlink_module_init(void)
 {
 	return genl_register_family(&devlink_nl_family);
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index fb55327dcfea..70ccda233bd1 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -412,9 +412,8 @@ static int __init init_net_drop_monitor(void)
 	for_each_possible_cpu(cpu) {
 		data = &per_cpu(dm_cpu_data, cpu);
 		INIT_WORK(&data->dm_alert_work, send_dm_alert);
-		init_timer(&data->send_timer);
-		data->send_timer.data = (unsigned long)data;
-		data->send_timer.function = sched_send_work;
+		setup_timer(&data->send_timer, sched_send_work,
+			    (unsigned long)data);
 		spin_lock_init(&data->lock);
 		reset_per_cpu_data(data);
 	}
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index aecb2c7241b6..905a88ad28e0 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -109,6 +109,7 @@ static const char
 rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = {
 	[ETH_RSS_HASH_TOP_BIT] =	"toeplitz",
 	[ETH_RSS_HASH_XOR_BIT] =	"xor",
+	[ETH_RSS_HASH_CRC32_BIT] =	"crc32",
 };
 
 static const char
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index b6791d94841d..816e3ccb0ec9 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -23,6 +23,20 @@ static const struct fib_kuid_range fib_kuid_range_unset = {
 	KUIDT_INIT(~0),
 };
 
+bool fib_rule_matchall(const struct fib_rule *rule)
+{
+	if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id ||
+	    rule->flags)
+		return false;
+	if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1)
+		return false;
+	if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) ||
+	    !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end))
+		return false;
+	return true;
+}
+EXPORT_SYMBOL_GPL(fib_rule_matchall);
+
 int fib_default_rule_add(struct fib_rules_ops *ops,
 			 u32 pref, u32 table, u32 flags)
 {
diff --git a/net/core/filter.c b/net/core/filter.c
index ebaeaf2e46e8..15e9a81ffebe 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -26,6 +26,7 @@
 #include <linux/mm.h>
 #include <linux/fcntl.h>
 #include <linux/socket.h>
+#include <linux/sock_diag.h>
 #include <linux/in.h>
 #include <linux/inet.h>
 #include <linux/netdevice.h>
@@ -928,7 +929,7 @@ static void sk_filter_release_rcu(struct rcu_head *rcu)
  */
 static void sk_filter_release(struct sk_filter *fp)
 {
-	if (atomic_dec_and_test(&fp->refcnt))
+	if (refcount_dec_and_test(&fp->refcnt))
 		call_rcu(&fp->rcu, sk_filter_release_rcu);
 }
 
@@ -943,20 +944,27 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
 /* try to charge the socket memory if there is space available
  * return true on success
  */
-bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
+static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 {
 	u32 filter_size = bpf_prog_size(fp->prog->len);
 
 	/* same check as in sock_kmalloc() */
 	if (filter_size <= sysctl_optmem_max &&
 	    atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) {
-		atomic_inc(&fp->refcnt);
 		atomic_add(filter_size, &sk->sk_omem_alloc);
 		return true;
 	}
 	return false;
 }
 
+bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
+{
+	bool ret = __sk_filter_charge(sk, fp);
+	if (ret)
+		refcount_inc(&fp->refcnt);
+	return ret;
+}
+
 static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
 {
 	struct sock_filter *old_prog;
@@ -1179,12 +1187,12 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
 		return -ENOMEM;
 
 	fp->prog = prog;
-	atomic_set(&fp->refcnt, 0);
 
-	if (!sk_filter_charge(sk, fp)) {
+	if (!__sk_filter_charge(sk, fp)) {
 		kfree(fp);
 		return -ENOMEM;
 	}
+	refcount_set(&fp->refcnt, 1);
 
 	old_fp = rcu_dereference_protected(sk->sk_filter,
 					   lockdep_sock_is_held(sk));
@@ -2599,6 +2607,36 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb)
+{
+	return skb->sk ? sock_gen_cookie(skb->sk) : 0;
+}
+
+static const struct bpf_func_proto bpf_get_socket_cookie_proto = {
+	.func           = bpf_get_socket_cookie,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+};
+
+BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb)
+{
+	struct sock *sk = sk_to_full_sk(skb->sk);
+	kuid_t kuid;
+
+	if (!sk || !sk_fullsock(sk))
+		return overflowuid;
+	kuid = sock_net_uid(sock_net(sk), sk);
+	return from_kuid_munged(sock_net(sk)->user_ns, kuid);
+}
+
+static const struct bpf_func_proto bpf_get_socket_uid_proto = {
+	.func           = bpf_get_socket_uid,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+};
+
 static const struct bpf_func_proto *
 bpf_base_func_proto(enum bpf_func_id func_id)
 {
@@ -2633,6 +2671,10 @@ sk_filter_func_proto(enum bpf_func_id func_id)
 	switch (func_id) {
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_skb_load_bytes_proto;
+	case BPF_FUNC_get_socket_cookie:
+		return &bpf_get_socket_cookie_proto;
+	case BPF_FUNC_get_socket_uid:
+		return &bpf_get_socket_uid_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -2692,6 +2734,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
 		return &bpf_get_smp_processor_id_proto;
 	case BPF_FUNC_skb_under_cgroup:
 		return &bpf_skb_under_cgroup_proto;
+	case BPF_FUNC_get_socket_cookie:
+		return &bpf_get_socket_cookie_proto;
+	case BPF_FUNC_get_socket_uid:
+		return &bpf_get_socket_uid_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -3263,24 +3309,28 @@ static const struct bpf_verifier_ops tc_cls_act_ops = {
 	.is_valid_access	= tc_cls_act_is_valid_access,
 	.convert_ctx_access	= tc_cls_act_convert_ctx_access,
 	.gen_prologue		= tc_cls_act_prologue,
+	.test_run		= bpf_prog_test_run_skb,
 };
 
 static const struct bpf_verifier_ops xdp_ops = {
 	.get_func_proto		= xdp_func_proto,
 	.is_valid_access	= xdp_is_valid_access,
 	.convert_ctx_access	= xdp_convert_ctx_access,
+	.test_run		= bpf_prog_test_run_xdp,
 };
 
 static const struct bpf_verifier_ops cg_skb_ops = {
 	.get_func_proto		= cg_skb_func_proto,
 	.is_valid_access	= sk_filter_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
+	.test_run		= bpf_prog_test_run_skb,
 };
 
 static const struct bpf_verifier_ops lwt_inout_ops = {
 	.get_func_proto		= lwt_inout_func_proto,
 	.is_valid_access	= lwt_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
+	.test_run		= bpf_prog_test_run_skb,
 };
 
 static const struct bpf_verifier_ops lwt_xmit_ops = {
@@ -3288,6 +3338,7 @@ static const struct bpf_verifier_ops lwt_xmit_ops = {
 	.is_valid_access	= lwt_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
 	.gen_prologue		= tc_cls_act_prologue,
+	.test_run		= bpf_prog_test_run_skb,
 };
 
 static const struct bpf_verifier_ops cg_sock_ops = {
diff --git a/net/core/flow.c b/net/core/flow.c
index f765c11d8df5..f7f5d1932a27 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -47,7 +47,7 @@ struct flow_flush_info {
 
 static struct kmem_cache *flow_cachep __read_mostly;
 
-#define flow_cache_hash_size(cache)	(1 << (cache)->hash_shift)
+#define flow_cache_hash_size(cache)	(1U << (cache)->hash_shift)
 #define FLOW_HASH_RND_PERIOD		(10 * 60 * HZ)
 
 static void flow_cache_new_hashrnd(unsigned long arg)
@@ -99,7 +99,8 @@ static void flow_cache_gc_task(struct work_struct *work)
 }
 
 static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
-				     int deleted, struct list_head *gc_list,
+				     unsigned int deleted,
+				     struct list_head *gc_list,
 				     struct netns_xfrm *xfrm)
 {
 	if (deleted) {
@@ -114,17 +115,18 @@ static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
 
 static void __flow_cache_shrink(struct flow_cache *fc,
 				struct flow_cache_percpu *fcp,
-				int shrink_to)
+				unsigned int shrink_to)
 {
 	struct flow_cache_entry *fle;
 	struct hlist_node *tmp;
 	LIST_HEAD(gc_list);
-	int i, deleted = 0;
+	unsigned int deleted = 0;
 	struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
 						flow_cache_global);
+	unsigned int i;
 
 	for (i = 0; i < flow_cache_hash_size(fc); i++) {
-		int saved = 0;
+		unsigned int saved = 0;
 
 		hlist_for_each_entry_safe(fle, tmp,
 					  &fcp->hash_table[i], u.hlist) {
@@ -145,7 +147,7 @@ static void __flow_cache_shrink(struct flow_cache *fc,
 static void flow_cache_shrink(struct flow_cache *fc,
 			      struct flow_cache_percpu *fcp)
 {
-	int shrink_to = fc->low_watermark / flow_cache_hash_size(fc);
+	unsigned int shrink_to = fc->low_watermark / flow_cache_hash_size(fc);
 
 	__flow_cache_shrink(fc, fcp, shrink_to);
 }
@@ -161,7 +163,7 @@ static void flow_new_hash_rnd(struct flow_cache *fc,
 static u32 flow_hash_code(struct flow_cache *fc,
 			  struct flow_cache_percpu *fcp,
 			  const struct flowi *key,
-			  size_t keysize)
+			  unsigned int keysize)
 {
 	const u32 *k = (const u32 *) key;
 	const u32 length = keysize * sizeof(flow_compare_t) / sizeof(u32);
@@ -174,7 +176,7 @@ static u32 flow_hash_code(struct flow_cache *fc,
  * important assumptions that we can here, such as alignment.
  */
 static int flow_key_compare(const struct flowi *key1, const struct flowi *key2,
-			    size_t keysize)
+			    unsigned int keysize)
 {
 	const flow_compare_t *k1, *k1_lim, *k2;
 
@@ -199,7 +201,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
 	struct flow_cache_percpu *fcp;
 	struct flow_cache_entry *fle, *tfle;
 	struct flow_cache_object *flo;
-	size_t keysize;
+	unsigned int keysize;
 	unsigned int hash;
 
 	local_bh_disable();
@@ -295,9 +297,10 @@ static void flow_cache_flush_tasklet(unsigned long data)
 	struct flow_cache_entry *fle;
 	struct hlist_node *tmp;
 	LIST_HEAD(gc_list);
-	int i, deleted = 0;
+	unsigned int deleted = 0;
 	struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
 						flow_cache_global);
+	unsigned int i;
 
 	fcp = this_cpu_ptr(fc->percpu);
 	for (i = 0; i < flow_cache_hash_size(fc); i++) {
@@ -327,7 +330,7 @@ static void flow_cache_flush_tasklet(unsigned long data)
 static int flow_cache_percpu_empty(struct flow_cache *fc, int cpu)
 {
 	struct flow_cache_percpu *fcp;
-	int i;
+	unsigned int i;
 
 	fcp = per_cpu_ptr(fc->percpu, cpu);
 	for (i = 0; i < flow_cache_hash_size(fc); i++)
@@ -402,12 +405,12 @@ void flow_cache_flush_deferred(struct net *net)
 static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu)
 {
 	struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
-	size_t sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc);
+	unsigned int sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc);
 
 	if (!fcp->hash_table) {
 		fcp->hash_table = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
 		if (!fcp->hash_table) {
-			pr_err("NET: failed to allocate flow cache sz %zu\n", sz);
+			pr_err("NET: failed to allocate flow cache sz %u\n", sz);
 			return -ENOMEM;
 		}
 		fcp->hash_rnd_recalc = 1;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d98d4998213d..c9cf425303f8 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -113,6 +113,216 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
 }
 EXPORT_SYMBOL(__skb_flow_get_ports);
 
+enum flow_dissect_ret {
+	FLOW_DISSECT_RET_OUT_GOOD,
+	FLOW_DISSECT_RET_OUT_BAD,
+	FLOW_DISSECT_RET_OUT_PROTO_AGAIN,
+};
+
+static enum flow_dissect_ret
+__skb_flow_dissect_mpls(const struct sk_buff *skb,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data, int nhoff, int hlen)
+{
+	struct flow_dissector_key_keyid *key_keyid;
+	struct mpls_label *hdr, _hdr[2];
+
+	if (!dissector_uses_key(flow_dissector,
+				FLOW_DISSECTOR_KEY_MPLS_ENTROPY))
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
+	hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data,
+				   hlen, &_hdr);
+	if (!hdr)
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) >>
+	    MPLS_LS_LABEL_SHIFT == MPLS_LABEL_ENTROPY) {
+		key_keyid = skb_flow_dissector_target(flow_dissector,
+						      FLOW_DISSECTOR_KEY_MPLS_ENTROPY,
+						      target_container);
+		key_keyid->keyid = hdr[1].entry & htonl(MPLS_LS_LABEL_MASK);
+	}
+	return FLOW_DISSECT_RET_OUT_GOOD;
+}
+
+static enum flow_dissect_ret
+__skb_flow_dissect_arp(const struct sk_buff *skb,
+		       struct flow_dissector *flow_dissector,
+		       void *target_container, void *data, int nhoff, int hlen)
+{
+	struct flow_dissector_key_arp *key_arp;
+	struct {
+		unsigned char ar_sha[ETH_ALEN];
+		unsigned char ar_sip[4];
+		unsigned char ar_tha[ETH_ALEN];
+		unsigned char ar_tip[4];
+	} *arp_eth, _arp_eth;
+	const struct arphdr *arp;
+	struct arphdr _arp;
+
+	if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ARP))
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
+	arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data,
+				   hlen, &_arp);
+	if (!arp)
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	if (arp->ar_hrd != htons(ARPHRD_ETHER) ||
+	    arp->ar_pro != htons(ETH_P_IP) ||
+	    arp->ar_hln != ETH_ALEN ||
+	    arp->ar_pln != 4 ||
+	    (arp->ar_op != htons(ARPOP_REPLY) &&
+	     arp->ar_op != htons(ARPOP_REQUEST)))
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp),
+				       sizeof(_arp_eth), data,
+				       hlen, &_arp_eth);
+	if (!arp_eth)
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	key_arp = skb_flow_dissector_target(flow_dissector,
+					    FLOW_DISSECTOR_KEY_ARP,
+					    target_container);
+
+	memcpy(&key_arp->sip, arp_eth->ar_sip, sizeof(key_arp->sip));
+	memcpy(&key_arp->tip, arp_eth->ar_tip, sizeof(key_arp->tip));
+
+	/* Only store the lower byte of the opcode;
+	 * this covers ARPOP_REPLY and ARPOP_REQUEST.
+	 */
+	key_arp->op = ntohs(arp->ar_op) & 0xff;
+
+	ether_addr_copy(key_arp->sha, arp_eth->ar_sha);
+	ether_addr_copy(key_arp->tha, arp_eth->ar_tha);
+
+	return FLOW_DISSECT_RET_OUT_GOOD;
+}
+
+static enum flow_dissect_ret
+__skb_flow_dissect_gre(const struct sk_buff *skb,
+		       struct flow_dissector_key_control *key_control,
+		       struct flow_dissector *flow_dissector,
+		       void *target_container, void *data,
+		       __be16 *p_proto, int *p_nhoff, int *p_hlen,
+		       unsigned int flags)
+{
+	struct flow_dissector_key_keyid *key_keyid;
+	struct gre_base_hdr *hdr, _hdr;
+	int offset = 0;
+	u16 gre_ver;
+
+	hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr),
+				   data, *p_hlen, &_hdr);
+	if (!hdr)
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	/* Only look inside GRE without routing */
+	if (hdr->flags & GRE_ROUTING)
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
+	/* Only look inside GRE for version 0 and 1 */
+	gre_ver = ntohs(hdr->flags & GRE_VERSION);
+	if (gre_ver > 1)
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
+	*p_proto = hdr->protocol;
+	if (gre_ver) {
+		/* Version1 must be PPTP, and check the flags */
+		if (!(*p_proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY)))
+			return FLOW_DISSECT_RET_OUT_GOOD;
+	}
+
+	offset += sizeof(struct gre_base_hdr);
+
+	if (hdr->flags & GRE_CSUM)
+		offset += sizeof(((struct gre_full_hdr *) 0)->csum) +
+			  sizeof(((struct gre_full_hdr *) 0)->reserved1);
+
+	if (hdr->flags & GRE_KEY) {
+		const __be32 *keyid;
+		__be32 _keyid;
+
+		keyid = __skb_header_pointer(skb, *p_nhoff + offset,
+					     sizeof(_keyid),
+					     data, *p_hlen, &_keyid);
+		if (!keyid)
+			return FLOW_DISSECT_RET_OUT_BAD;
+
+		if (dissector_uses_key(flow_dissector,
+				       FLOW_DISSECTOR_KEY_GRE_KEYID)) {
+			key_keyid = skb_flow_dissector_target(flow_dissector,
+							      FLOW_DISSECTOR_KEY_GRE_KEYID,
+							      target_container);
+			if (gre_ver == 0)
+				key_keyid->keyid = *keyid;
+			else
+				key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK;
+		}
+		offset += sizeof(((struct gre_full_hdr *) 0)->key);
+	}
+
+	if (hdr->flags & GRE_SEQ)
+		offset += sizeof(((struct pptp_gre_header *) 0)->seq);
+
+	if (gre_ver == 0) {
+		if (*p_proto == htons(ETH_P_TEB)) {
+			const struct ethhdr *eth;
+			struct ethhdr _eth;
+
+			eth = __skb_header_pointer(skb, *p_nhoff + offset,
+						   sizeof(_eth),
+						   data, *p_hlen, &_eth);
+			if (!eth)
+				return FLOW_DISSECT_RET_OUT_BAD;
+			*p_proto = eth->h_proto;
+			offset += sizeof(*eth);
+
+			/* Cap headers that we access via pointers at the
+			 * end of the Ethernet header as our maximum alignment
+			 * at that point is only 2 bytes.
+			 */
+			if (NET_IP_ALIGN)
+				*p_hlen = *p_nhoff + offset;
+		}
+	} else { /* version 1, must be PPTP */
+		u8 _ppp_hdr[PPP_HDRLEN];
+		u8 *ppp_hdr;
+
+		if (hdr->flags & GRE_ACK)
+			offset += sizeof(((struct pptp_gre_header *) 0)->ack);
+
+		ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset,
+					       sizeof(_ppp_hdr),
+					       data, *p_hlen, _ppp_hdr);
+		if (!ppp_hdr)
+			return FLOW_DISSECT_RET_OUT_BAD;
+
+		switch (PPP_PROTOCOL(ppp_hdr)) {
+		case PPP_IP:
+			*p_proto = htons(ETH_P_IP);
+			break;
+		case PPP_IPV6:
+			*p_proto = htons(ETH_P_IPV6);
+			break;
+		default:
+			/* Could probably catch some more like MPLS */
+			break;
+		}
+
+		offset += PPP_HDRLEN;
+	}
+
+	*p_nhoff += offset;
+	key_control->flags |= FLOW_DIS_ENCAPSULATION;
+	if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP)
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
+	return FLOW_DISSECT_RET_OUT_PROTO_AGAIN;
+}
+
 /**
  * __skb_flow_dissect - extract the flow_keys struct and return it
  * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
@@ -138,12 +348,10 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 	struct flow_dissector_key_control *key_control;
 	struct flow_dissector_key_basic *key_basic;
 	struct flow_dissector_key_addrs *key_addrs;
-	struct flow_dissector_key_arp *key_arp;
 	struct flow_dissector_key_ports *key_ports;
 	struct flow_dissector_key_icmp *key_icmp;
 	struct flow_dissector_key_tags *key_tags;
 	struct flow_dissector_key_vlan *key_vlan;
-	struct flow_dissector_key_keyid *key_keyid;
 	bool skip_vlan = false;
 	u8 ip_proto = 0;
 	bool ret;
@@ -181,7 +389,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 		memcpy(key_eth_addrs, &eth->h_dest, sizeof(*key_eth_addrs));
 	}
 
-again:
+proto_again:
 	switch (proto) {
 	case htons(ETH_P_IP): {
 		const struct iphdr *iph;
@@ -284,7 +492,7 @@ ipv6:
 			proto = vlan->h_vlan_encapsulated_proto;
 			nhoff += sizeof(*vlan);
 			if (skip_vlan)
-				goto again;
+				goto proto_again;
 		}
 
 		skip_vlan = true;
@@ -307,7 +515,7 @@ ipv6:
 			}
 		}
 
-		goto again;
+		goto proto_again;
 	}
 	case htons(ETH_P_PPP_SES): {
 		struct {
@@ -349,31 +557,17 @@ ipv6:
 	}
 
 	case htons(ETH_P_MPLS_UC):
-	case htons(ETH_P_MPLS_MC): {
-		struct mpls_label *hdr, _hdr[2];
+	case htons(ETH_P_MPLS_MC):
 mpls:
-		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data,
-					   hlen, &_hdr);
-		if (!hdr)
-			goto out_bad;
-
-		if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) >>
-		     MPLS_LS_LABEL_SHIFT == MPLS_LABEL_ENTROPY) {
-			if (dissector_uses_key(flow_dissector,
-					       FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) {
-				key_keyid = skb_flow_dissector_target(flow_dissector,
-								      FLOW_DISSECTOR_KEY_MPLS_ENTROPY,
-								      target_container);
-				key_keyid->keyid = hdr[1].entry &
-					htonl(MPLS_LS_LABEL_MASK);
-			}
-
+		switch (__skb_flow_dissect_mpls(skb, flow_dissector,
+						target_container, data,
+						nhoff, hlen)) {
+		case FLOW_DISSECT_RET_OUT_GOOD:
 			goto out_good;
+		case FLOW_DISSECT_RET_OUT_BAD:
+		default:
+			goto out_bad;
 		}
-
-		goto out_good;
-	}
-
 	case htons(ETH_P_FCOE):
 		if ((hlen - nhoff) < FCOE_HEADER_LEN)
 			goto out_bad;
@@ -382,177 +576,33 @@ mpls:
 		goto out_good;
 
 	case htons(ETH_P_ARP):
-	case htons(ETH_P_RARP): {
-		struct {
-			unsigned char ar_sha[ETH_ALEN];
-			unsigned char ar_sip[4];
-			unsigned char ar_tha[ETH_ALEN];
-			unsigned char ar_tip[4];
-		} *arp_eth, _arp_eth;
-		const struct arphdr *arp;
-		struct arphdr _arp;
-
-		arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data,
-					   hlen, &_arp);
-		if (!arp)
-			goto out_bad;
-
-		if (arp->ar_hrd != htons(ARPHRD_ETHER) ||
-		    arp->ar_pro != htons(ETH_P_IP) ||
-		    arp->ar_hln != ETH_ALEN ||
-		    arp->ar_pln != 4 ||
-		    (arp->ar_op != htons(ARPOP_REPLY) &&
-		     arp->ar_op != htons(ARPOP_REQUEST)))
-			goto out_bad;
-
-		arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp),
-					       sizeof(_arp_eth), data,
-					       hlen,
-					       &_arp_eth);
-		if (!arp_eth)
+	case htons(ETH_P_RARP):
+		switch (__skb_flow_dissect_arp(skb, flow_dissector,
+					       target_container, data,
+					       nhoff, hlen)) {
+		case FLOW_DISSECT_RET_OUT_GOOD:
+			goto out_good;
+		case FLOW_DISSECT_RET_OUT_BAD:
+		default:
 			goto out_bad;
-
-		if (dissector_uses_key(flow_dissector,
-				       FLOW_DISSECTOR_KEY_ARP)) {
-
-			key_arp = skb_flow_dissector_target(flow_dissector,
-							    FLOW_DISSECTOR_KEY_ARP,
-							    target_container);
-
-			memcpy(&key_arp->sip, arp_eth->ar_sip,
-			       sizeof(key_arp->sip));
-			memcpy(&key_arp->tip, arp_eth->ar_tip,
-			       sizeof(key_arp->tip));
-
-			/* Only store the lower byte of the opcode;
-			 * this covers ARPOP_REPLY and ARPOP_REQUEST.
-			 */
-			key_arp->op = ntohs(arp->ar_op) & 0xff;
-
-			ether_addr_copy(key_arp->sha, arp_eth->ar_sha);
-			ether_addr_copy(key_arp->tha, arp_eth->ar_tha);
 		}
-
-		goto out_good;
-	}
-
 	default:
 		goto out_bad;
 	}
 
 ip_proto_again:
 	switch (ip_proto) {
-	case IPPROTO_GRE: {
-		struct gre_base_hdr *hdr, _hdr;
-		u16 gre_ver;
-		int offset = 0;
-
-		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
-		if (!hdr)
+	case IPPROTO_GRE:
+		switch (__skb_flow_dissect_gre(skb, key_control, flow_dissector,
+					       target_container, data,
+					       &proto, &nhoff, &hlen, flags)) {
+		case FLOW_DISSECT_RET_OUT_GOOD:
+			goto out_good;
+		case FLOW_DISSECT_RET_OUT_BAD:
 			goto out_bad;
-
-		/* Only look inside GRE without routing */
-		if (hdr->flags & GRE_ROUTING)
-			break;
-
-		/* Only look inside GRE for version 0 and 1 */
-		gre_ver = ntohs(hdr->flags & GRE_VERSION);
-		if (gre_ver > 1)
-			break;
-
-		proto = hdr->protocol;
-		if (gre_ver) {
-			/* Version1 must be PPTP, and check the flags */
-			if (!(proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY)))
-				break;
-		}
-
-		offset += sizeof(struct gre_base_hdr);
-
-		if (hdr->flags & GRE_CSUM)
-			offset += sizeof(((struct gre_full_hdr *)0)->csum) +
-				  sizeof(((struct gre_full_hdr *)0)->reserved1);
-
-		if (hdr->flags & GRE_KEY) {
-			const __be32 *keyid;
-			__be32 _keyid;
-
-			keyid = __skb_header_pointer(skb, nhoff + offset, sizeof(_keyid),
-						     data, hlen, &_keyid);
-			if (!keyid)
-				goto out_bad;
-
-			if (dissector_uses_key(flow_dissector,
-					       FLOW_DISSECTOR_KEY_GRE_KEYID)) {
-				key_keyid = skb_flow_dissector_target(flow_dissector,
-								      FLOW_DISSECTOR_KEY_GRE_KEYID,
-								      target_container);
-				if (gre_ver == 0)
-					key_keyid->keyid = *keyid;
-				else
-					key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK;
-			}
-			offset += sizeof(((struct gre_full_hdr *)0)->key);
+		case FLOW_DISSECT_RET_OUT_PROTO_AGAIN:
+			goto proto_again;
 		}
-
-		if (hdr->flags & GRE_SEQ)
-			offset += sizeof(((struct pptp_gre_header *)0)->seq);
-
-		if (gre_ver == 0) {
-			if (proto == htons(ETH_P_TEB)) {
-				const struct ethhdr *eth;
-				struct ethhdr _eth;
-
-				eth = __skb_header_pointer(skb, nhoff + offset,
-							   sizeof(_eth),
-							   data, hlen, &_eth);
-				if (!eth)
-					goto out_bad;
-				proto = eth->h_proto;
-				offset += sizeof(*eth);
-
-				/* Cap headers that we access via pointers at the
-				 * end of the Ethernet header as our maximum alignment
-				 * at that point is only 2 bytes.
-				 */
-				if (NET_IP_ALIGN)
-					hlen = (nhoff + offset);
-			}
-		} else { /* version 1, must be PPTP */
-			u8 _ppp_hdr[PPP_HDRLEN];
-			u8 *ppp_hdr;
-
-			if (hdr->flags & GRE_ACK)
-				offset += sizeof(((struct pptp_gre_header *)0)->ack);
-
-			ppp_hdr = __skb_header_pointer(skb, nhoff + offset,
-						     sizeof(_ppp_hdr),
-						     data, hlen, _ppp_hdr);
-			if (!ppp_hdr)
-				goto out_bad;
-
-			switch (PPP_PROTOCOL(ppp_hdr)) {
-			case PPP_IP:
-				proto = htons(ETH_P_IP);
-				break;
-			case PPP_IPV6:
-				proto = htons(ETH_P_IPV6);
-				break;
-			default:
-				/* Could probably catch some more like MPLS */
-				break;
-			}
-
-			offset += PPP_HDRLEN;
-		}
-
-		nhoff += offset;
-		key_control->flags |= FLOW_DIS_ENCAPSULATION;
-		if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP)
-			goto out_good;
-
-		goto again;
-	}
 	case NEXTHDR_HOP:
 	case NEXTHDR_ROUTING:
 	case NEXTHDR_DEST: {
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 6df9f8fabf0c..b5888190223c 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -162,7 +162,6 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining)
 	struct rtnexthop *rtnh = (struct rtnexthop *)attr;
 	struct nlattr *nla_entype;
 	struct nlattr *attrs;
-	struct nlattr *nla;
 	u16 encap_type;
 	int attrlen;
 
@@ -170,7 +169,6 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining)
 		attrlen = rtnh_attrlen(rtnh);
 		if (attrlen > 0) {
 			attrs = rtnh_attrs(rtnh);
-			nla = nla_find(attrs, attrlen, RTA_ENCAP);
 			nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
 
 			if (nla_entype) {
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 4526cbd7e28a..8ae87c591c8e 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -52,8 +52,9 @@ do {						\
 #define PNEIGH_HASHMASK		0xF
 
 static void neigh_timer_handler(unsigned long arg);
-static void __neigh_notify(struct neighbour *n, int type, int flags);
-static void neigh_update_notify(struct neighbour *neigh);
+static void __neigh_notify(struct neighbour *n, int type, int flags,
+			   u32 pid);
+static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid);
 static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
 
 #ifdef CONFIG_PROC_FS
@@ -99,7 +100,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh)
 	if (neigh->parms->neigh_cleanup)
 		neigh->parms->neigh_cleanup(neigh);
 
-	__neigh_notify(neigh, RTM_DELNEIGH, 0);
+	__neigh_notify(neigh, RTM_DELNEIGH, 0, 0);
 	call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh);
 	neigh_release(neigh);
 }
@@ -949,7 +950,7 @@ out:
 	}
 
 	if (notify)
-		neigh_update_notify(neigh);
+		neigh_update_notify(neigh, 0);
 
 	neigh_release(neigh);
 }
@@ -1073,7 +1074,7 @@ static void neigh_update_hhs(struct neighbour *neigh)
  */
 
 int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
-		 u32 flags)
+		 u32 flags, u32 nlmsg_pid)
 {
 	u8 old;
 	int err;
@@ -1230,7 +1231,7 @@ out:
 	write_unlock_bh(&neigh->lock);
 
 	if (notify)
-		neigh_update_notify(neigh);
+		neigh_update_notify(neigh, nlmsg_pid);
 
 	return err;
 }
@@ -1261,7 +1262,7 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl,
 						 lladdr || !dev->addr_len);
 	if (neigh)
 		neigh_update(neigh, lladdr, NUD_STALE,
-			     NEIGH_UPDATE_F_OVERRIDE);
+			     NEIGH_UPDATE_F_OVERRIDE, 0);
 	return neigh;
 }
 EXPORT_SYMBOL(neigh_event_ns);
@@ -1639,7 +1640,8 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	err = neigh_update(neigh, NULL, NUD_FAILED,
 			   NEIGH_UPDATE_F_OVERRIDE |
-			   NEIGH_UPDATE_F_ADMIN);
+			   NEIGH_UPDATE_F_ADMIN,
+			   NETLINK_CB(skb).portid);
 	neigh_release(neigh);
 
 out:
@@ -1730,7 +1732,8 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 		neigh_event_send(neigh, NULL);
 		err = 0;
 	} else
-		err = neigh_update(neigh, lladdr, ndm->ndm_state, flags);
+		err = neigh_update(neigh, lladdr, ndm->ndm_state, flags,
+				   NETLINK_CB(skb).portid);
 	neigh_release(neigh);
 
 out:
@@ -2230,10 +2233,10 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static void neigh_update_notify(struct neighbour *neigh)
+static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid)
 {
 	call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh);
-	__neigh_notify(neigh, RTM_NEWNEIGH, 0);
+	__neigh_notify(neigh, RTM_NEWNEIGH, 0, nlmsg_pid);
 }
 
 static bool neigh_master_filtered(struct net_device *dev, int master_idx)
@@ -2831,7 +2834,8 @@ static inline size_t neigh_nlmsg_size(void)
 	       + nla_total_size(4); /* NDA_PROBES */
 }
 
-static void __neigh_notify(struct neighbour *n, int type, int flags)
+static void __neigh_notify(struct neighbour *n, int type, int flags,
+			   u32 pid)
 {
 	struct net *net = dev_net(n->dev);
 	struct sk_buff *skb;
@@ -2841,7 +2845,7 @@ static void __neigh_notify(struct neighbour *n, int type, int flags)
 	if (skb == NULL)
 		goto errout;
 
-	err = neigh_fill_info(skb, n, 0, 0, type, flags);
+	err = neigh_fill_info(skb, n, pid, 0, type, flags);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in neigh_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);
@@ -2857,7 +2861,7 @@ errout:
 
 void neigh_app_ns(struct neighbour *n)
 {
-	__neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST);
+	__neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST, 0);
 }
 EXPORT_SYMBOL(neigh_app_ns);
 
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 0f9275ee5595..1c4810919a0a 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -11,6 +11,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/module.h>
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c4e84c558240..b2bd4c9ee860 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -944,6 +944,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */
 	       + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */
 	       + rtnl_xdp_size(dev) /* IFLA_XDP */
+	       + nla_total_size(4)  /* IFLA_EVENT */
 	       + nla_total_size(1); /* IFLA_PROTO_DOWN */
 
 }
@@ -1276,9 +1277,70 @@ err_cancel:
 	return err;
 }
 
+static int rtnl_fill_link_event(struct sk_buff *skb, unsigned long event)
+{
+	u32 rtnl_event;
+
+	switch (event) {
+	case NETDEV_REBOOT:
+		rtnl_event = IFLA_EVENT_REBOOT;
+		break;
+	case NETDEV_CHANGEMTU:
+		rtnl_event = IFLA_EVENT_CHANGE_MTU;
+		break;
+	case NETDEV_CHANGEADDR:
+		rtnl_event = IFLA_EVENT_CHANGE_ADDR;
+		break;
+	case NETDEV_CHANGENAME:
+		rtnl_event = IFLA_EVENT_CHANGE_NAME;
+		break;
+	case NETDEV_FEAT_CHANGE:
+		rtnl_event = IFLA_EVENT_FEAT_CHANGE;
+		break;
+	case NETDEV_BONDING_FAILOVER:
+		rtnl_event = IFLA_EVENT_BONDING_FAILOVER;
+		break;
+	case NETDEV_POST_TYPE_CHANGE:
+		rtnl_event = IFLA_EVENT_POST_TYPE_CHANGE;
+		break;
+	case NETDEV_NOTIFY_PEERS:
+		rtnl_event = IFLA_EVENT_NOTIFY_PEERS;
+		break;
+	case NETDEV_CHANGEUPPER:
+		rtnl_event = IFLA_EVENT_CHANGE_UPPER;
+		break;
+	case NETDEV_RESEND_IGMP:
+		rtnl_event = IFLA_EVENT_RESEND_IGMP;
+		break;
+	case NETDEV_PRECHANGEMTU:
+		rtnl_event = IFLA_EVENT_PRE_CHANGE_MTU;
+		break;
+	case NETDEV_CHANGEINFODATA:
+		rtnl_event = IFLA_EVENT_CHANGE_INFO_DATA;
+		break;
+	case NETDEV_PRECHANGEUPPER:
+		rtnl_event = IFLA_EVENT_PRE_CHANGE_UPPER;
+		break;
+	case NETDEV_CHANGELOWERSTATE:
+		rtnl_event = IFLA_EVENT_CHANGE_LOWER_STATE;
+		break;
+	case NETDEV_UDP_TUNNEL_PUSH_INFO:
+		rtnl_event = IFLA_EVENT_UDP_TUNNEL_PUSH_INFO;
+		break;
+	case NETDEV_CHANGE_TX_QUEUE_LEN:
+		rtnl_event = IFLA_EVENT_CHANGE_TX_QUEUE_LEN;
+		break;
+	default:
+		return 0;
+	}
+
+	return nla_put_u32(skb, IFLA_EVENT, rtnl_event);
+}
+
 static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			    int type, u32 pid, u32 seq, u32 change,
-			    unsigned int flags, u32 ext_filter_mask)
+			    unsigned int flags, u32 ext_filter_mask,
+			    unsigned long event)
 {
 	struct ifinfomsg *ifm;
 	struct nlmsghdr *nlh;
@@ -1327,6 +1389,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 	    nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down))
 		goto nla_put_failure;
 
+	if (rtnl_fill_link_event(skb, event))
+		goto nla_put_failure;
+
 	if (rtnl_fill_link_ifmap(skb, dev))
 		goto nla_put_failure;
 
@@ -1461,6 +1526,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_LINK_NETNSID]	= { .type = NLA_S32 },
 	[IFLA_PROTO_DOWN]	= { .type = NLA_U8 },
 	[IFLA_XDP]		= { .type = NLA_NESTED },
+	[IFLA_EVENT]		= { .type = NLA_U32 },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -1619,7 +1685,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 					       NETLINK_CB(cb->skb).portid,
 					       cb->nlh->nlmsg_seq, 0,
 					       flags,
-					       ext_filter_mask);
+					       ext_filter_mask, 0);
 			/* If we ran out of room on the first message,
 			 * we're in trouble
 			 */
@@ -2710,7 +2776,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh)
 		return -ENOBUFS;
 
 	err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid,
-			       nlh->nlmsg_seq, 0, 0, ext_filter_mask);
+			       nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in if_nlmsg_size */
 		WARN_ON(err == -EMSGSIZE);
@@ -2782,7 +2848,8 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 }
 
 struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
-				       unsigned int change, gfp_t flags)
+				       unsigned int change,
+				       unsigned long event, gfp_t flags)
 {
 	struct net *net = dev_net(dev);
 	struct sk_buff *skb;
@@ -2793,7 +2860,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
 	if (skb == NULL)
 		goto errout;
 
-	err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0);
+	err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in if_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);
@@ -2814,18 +2881,25 @@ void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags)
 	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
 }
 
-void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
-		  gfp_t flags)
+static void rtmsg_ifinfo_event(int type, struct net_device *dev,
+			       unsigned int change, unsigned long event,
+			       gfp_t flags)
 {
 	struct sk_buff *skb;
 
 	if (dev->reg_state != NETREG_REGISTERED)
 		return;
 
-	skb = rtmsg_ifinfo_build_skb(type, dev, change, flags);
+	skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags);
 	if (skb)
 		rtmsg_ifinfo_send(skb, dev, flags);
 }
+
+void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
+		  gfp_t flags)
+{
+	rtmsg_ifinfo_event(type, dev, change, 0, flags);
+}
 EXPORT_SYMBOL(rtmsg_ifinfo);
 
 static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
@@ -4116,22 +4190,25 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
 	switch (event) {
-	case NETDEV_UP:
-	case NETDEV_DOWN:
-	case NETDEV_PRE_UP:
-	case NETDEV_POST_INIT:
-	case NETDEV_REGISTER:
-	case NETDEV_CHANGE:
-	case NETDEV_PRE_TYPE_CHANGE:
-	case NETDEV_GOING_DOWN:
-	case NETDEV_UNREGISTER:
-	case NETDEV_UNREGISTER_FINAL:
-	case NETDEV_RELEASE:
-	case NETDEV_JOIN:
-	case NETDEV_BONDING_INFO:
+	case NETDEV_REBOOT:
+	case NETDEV_CHANGEMTU:
+	case NETDEV_CHANGEADDR:
+	case NETDEV_CHANGENAME:
+	case NETDEV_FEAT_CHANGE:
+	case NETDEV_BONDING_FAILOVER:
+	case NETDEV_POST_TYPE_CHANGE:
+	case NETDEV_NOTIFY_PEERS:
+	case NETDEV_CHANGEUPPER:
+	case NETDEV_RESEND_IGMP:
+	case NETDEV_PRECHANGEMTU:
+	case NETDEV_CHANGEINFODATA:
+	case NETDEV_PRECHANGEUPPER:
+	case NETDEV_CHANGELOWERSTATE:
+	case NETDEV_UDP_TUNNEL_PUSH_INFO:
+	case NETDEV_CHANGE_TX_QUEUE_LEN:
+		rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, event, GFP_KERNEL);
 		break;
 	default:
-		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
 		break;
 	}
 	return NOTIFY_DONE;
@@ -4185,6 +4262,7 @@ void __init rtnetlink_init(void)
 
 	rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL);
 	rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETNETCONF, NULL, rtnl_dump_all, NULL);
 
 	rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, NULL);
 	rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, NULL);
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index d28da7d363f1..6bd2f8fb0476 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -64,8 +64,8 @@ static u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr)
 		       &ts_secret);
 }
 
-u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
-				 __be16 sport, __be16 dport, u32 *tsoff)
+u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr,
+			       __be16 sport, __be16 dport, u32 *tsoff)
 {
 	const struct {
 		struct in6_addr saddr;
@@ -85,7 +85,7 @@ u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
 	*tsoff = secure_tcpv6_ts_off(saddr, daddr);
 	return seq_scale(hash);
 }
-EXPORT_SYMBOL(secure_tcpv6_sequence_number);
+EXPORT_SYMBOL(secure_tcpv6_seq_and_tsoff);
 
 u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport)
@@ -116,14 +116,13 @@ static u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr)
 			    &ts_secret);
 }
 
-/* secure_tcp_sequence_number(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d),
+/* secure_tcp_seq_and_tsoff(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d),
  * but fortunately, `sport' cannot be 0 in any circumstances. If this changes,
  * it would be easy enough to have the former function use siphash_4u32, passing
  * the arguments as separate u32.
  */
-
-u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
-			       __be16 sport, __be16 dport, u32 *tsoff)
+u32 secure_tcp_seq_and_tsoff(__be32 saddr, __be32 daddr,
+			     __be16 sport, __be16 dport, u32 *tsoff)
 {
 	u64 hash;
 	net_secret_init();
diff --git a/net/core/sock.c b/net/core/sock.c
index 2c4f574168fb..392f9b6f96e2 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -247,12 +247,66 @@ static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = {
 static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = {
 	_sock_locks("k-clock-")
 };
+static const char *const af_family_rlock_key_strings[AF_MAX+1] = {
+  "rlock-AF_UNSPEC", "rlock-AF_UNIX"     , "rlock-AF_INET"     ,
+  "rlock-AF_AX25"  , "rlock-AF_IPX"      , "rlock-AF_APPLETALK",
+  "rlock-AF_NETROM", "rlock-AF_BRIDGE"   , "rlock-AF_ATMPVC"   ,
+  "rlock-AF_X25"   , "rlock-AF_INET6"    , "rlock-AF_ROSE"     ,
+  "rlock-AF_DECnet", "rlock-AF_NETBEUI"  , "rlock-AF_SECURITY" ,
+  "rlock-AF_KEY"   , "rlock-AF_NETLINK"  , "rlock-AF_PACKET"   ,
+  "rlock-AF_ASH"   , "rlock-AF_ECONET"   , "rlock-AF_ATMSVC"   ,
+  "rlock-AF_RDS"   , "rlock-AF_SNA"      , "rlock-AF_IRDA"     ,
+  "rlock-AF_PPPOX" , "rlock-AF_WANPIPE"  , "rlock-AF_LLC"      ,
+  "rlock-27"       , "rlock-28"          , "rlock-AF_CAN"      ,
+  "rlock-AF_TIPC"  , "rlock-AF_BLUETOOTH", "rlock-AF_IUCV"     ,
+  "rlock-AF_RXRPC" , "rlock-AF_ISDN"     , "rlock-AF_PHONET"   ,
+  "rlock-AF_IEEE802154", "rlock-AF_CAIF" , "rlock-AF_ALG"      ,
+  "rlock-AF_NFC"   , "rlock-AF_VSOCK"    , "rlock-AF_KCM"      ,
+  "rlock-AF_QIPCRTR", "rlock-AF_SMC"     , "rlock-AF_MAX"
+};
+static const char *const af_family_wlock_key_strings[AF_MAX+1] = {
+  "wlock-AF_UNSPEC", "wlock-AF_UNIX"     , "wlock-AF_INET"     ,
+  "wlock-AF_AX25"  , "wlock-AF_IPX"      , "wlock-AF_APPLETALK",
+  "wlock-AF_NETROM", "wlock-AF_BRIDGE"   , "wlock-AF_ATMPVC"   ,
+  "wlock-AF_X25"   , "wlock-AF_INET6"    , "wlock-AF_ROSE"     ,
+  "wlock-AF_DECnet", "wlock-AF_NETBEUI"  , "wlock-AF_SECURITY" ,
+  "wlock-AF_KEY"   , "wlock-AF_NETLINK"  , "wlock-AF_PACKET"   ,
+  "wlock-AF_ASH"   , "wlock-AF_ECONET"   , "wlock-AF_ATMSVC"   ,
+  "wlock-AF_RDS"   , "wlock-AF_SNA"      , "wlock-AF_IRDA"     ,
+  "wlock-AF_PPPOX" , "wlock-AF_WANPIPE"  , "wlock-AF_LLC"      ,
+  "wlock-27"       , "wlock-28"          , "wlock-AF_CAN"      ,
+  "wlock-AF_TIPC"  , "wlock-AF_BLUETOOTH", "wlock-AF_IUCV"     ,
+  "wlock-AF_RXRPC" , "wlock-AF_ISDN"     , "wlock-AF_PHONET"   ,
+  "wlock-AF_IEEE802154", "wlock-AF_CAIF" , "wlock-AF_ALG"      ,
+  "wlock-AF_NFC"   , "wlock-AF_VSOCK"    , "wlock-AF_KCM"      ,
+  "wlock-AF_QIPCRTR", "wlock-AF_SMC"     , "wlock-AF_MAX"
+};
+static const char *const af_family_elock_key_strings[AF_MAX+1] = {
+  "elock-AF_UNSPEC", "elock-AF_UNIX"     , "elock-AF_INET"     ,
+  "elock-AF_AX25"  , "elock-AF_IPX"      , "elock-AF_APPLETALK",
+  "elock-AF_NETROM", "elock-AF_BRIDGE"   , "elock-AF_ATMPVC"   ,
+  "elock-AF_X25"   , "elock-AF_INET6"    , "elock-AF_ROSE"     ,
+  "elock-AF_DECnet", "elock-AF_NETBEUI"  , "elock-AF_SECURITY" ,
+  "elock-AF_KEY"   , "elock-AF_NETLINK"  , "elock-AF_PACKET"   ,
+  "elock-AF_ASH"   , "elock-AF_ECONET"   , "elock-AF_ATMSVC"   ,
+  "elock-AF_RDS"   , "elock-AF_SNA"      , "elock-AF_IRDA"     ,
+  "elock-AF_PPPOX" , "elock-AF_WANPIPE"  , "elock-AF_LLC"      ,
+  "elock-27"       , "elock-28"          , "elock-AF_CAN"      ,
+  "elock-AF_TIPC"  , "elock-AF_BLUETOOTH", "elock-AF_IUCV"     ,
+  "elock-AF_RXRPC" , "elock-AF_ISDN"     , "elock-AF_PHONET"   ,
+  "elock-AF_IEEE802154", "elock-AF_CAIF" , "elock-AF_ALG"      ,
+  "elock-AF_NFC"   , "elock-AF_VSOCK"    , "elock-AF_KCM"      ,
+  "elock-AF_QIPCRTR", "elock-AF_SMC"     , "elock-AF_MAX"
+};
 
 /*
- * sk_callback_lock locking rules are per-address-family,
+ * sk_callback_lock and sk queues locking rules are per-address-family,
  * so split the lock classes by using a per-AF key:
  */
 static struct lock_class_key af_callback_keys[AF_MAX];
+static struct lock_class_key af_rlock_keys[AF_MAX];
+static struct lock_class_key af_wlock_keys[AF_MAX];
+static struct lock_class_key af_elock_keys[AF_MAX];
 static struct lock_class_key af_kern_callback_keys[AF_MAX];
 
 /* Take into consideration the size of the struct sk_buff overhead in the
@@ -1259,6 +1313,33 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val = sk->sk_incoming_cpu;
 		break;
 
+	case SO_MEMINFO:
+	{
+		u32 meminfo[SK_MEMINFO_VARS];
+
+		if (get_user(len, optlen))
+			return -EFAULT;
+
+		sk_get_meminfo(sk, meminfo);
+
+		len = min_t(unsigned int, len, sizeof(meminfo));
+		if (copy_to_user(optval, &meminfo, len))
+			return -EFAULT;
+
+		goto lenout;
+	}
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	case SO_INCOMING_NAPI_ID:
+		v.val = READ_ONCE(sk->sk_napi_id);
+
+		/* aggregate non-NAPI IDs down to 0 */
+		if (v.val < MIN_NAPI_ID)
+			v.val = 0;
+
+		break;
+#endif
+
 	default:
 		/* We implement the SO_SNDLOWAT etc to not be settable
 		 * (1003.1g 7).
@@ -1483,6 +1564,27 @@ void sk_free(struct sock *sk)
 }
 EXPORT_SYMBOL(sk_free);
 
+static void sk_init_common(struct sock *sk)
+{
+	skb_queue_head_init(&sk->sk_receive_queue);
+	skb_queue_head_init(&sk->sk_write_queue);
+	skb_queue_head_init(&sk->sk_error_queue);
+
+	rwlock_init(&sk->sk_callback_lock);
+	lockdep_set_class_and_name(&sk->sk_receive_queue.lock,
+			af_rlock_keys + sk->sk_family,
+			af_family_rlock_key_strings[sk->sk_family]);
+	lockdep_set_class_and_name(&sk->sk_write_queue.lock,
+			af_wlock_keys + sk->sk_family,
+			af_family_wlock_key_strings[sk->sk_family]);
+	lockdep_set_class_and_name(&sk->sk_error_queue.lock,
+			af_elock_keys + sk->sk_family,
+			af_family_elock_key_strings[sk->sk_family]);
+	lockdep_set_class_and_name(&sk->sk_callback_lock,
+			af_callback_keys + sk->sk_family,
+			af_family_clock_key_strings[sk->sk_family]);
+}
+
 /**
  *	sk_clone_lock - clone a socket, and lock its clone
  *	@sk: the socket to clone
@@ -1516,13 +1618,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		 */
 		atomic_set(&newsk->sk_wmem_alloc, 1);
 		atomic_set(&newsk->sk_omem_alloc, 0);
-		skb_queue_head_init(&newsk->sk_receive_queue);
-		skb_queue_head_init(&newsk->sk_write_queue);
-
-		rwlock_init(&newsk->sk_callback_lock);
-		lockdep_set_class_and_name(&newsk->sk_callback_lock,
-				af_callback_keys + newsk->sk_family,
-				af_family_clock_key_strings[newsk->sk_family]);
+		sk_init_common(newsk);
 
 		newsk->sk_dst_cache	= NULL;
 		newsk->sk_dst_pending_confirm = 0;
@@ -1533,7 +1629,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		newsk->sk_userlocks	= sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
 
 		sock_reset_flag(newsk, SOCK_DONE);
-		skb_queue_head_init(&newsk->sk_error_queue);
 
 		filter = rcu_dereference_protected(newsk->sk_filter, 1);
 		if (filter != NULL)
@@ -2466,10 +2561,7 @@ EXPORT_SYMBOL(sk_stop_timer);
 
 void sock_init_data(struct socket *sock, struct sock *sk)
 {
-	skb_queue_head_init(&sk->sk_receive_queue);
-	skb_queue_head_init(&sk->sk_write_queue);
-	skb_queue_head_init(&sk->sk_error_queue);
-
+	sk_init_common(sk);
 	sk->sk_send_head	=	NULL;
 
 	init_timer(&sk->sk_timer);
@@ -2521,7 +2613,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	sk->sk_rcvtimeo		=	MAX_SCHEDULE_TIMEOUT;
 	sk->sk_sndtimeo		=	MAX_SCHEDULE_TIMEOUT;
 
-	sk->sk_stamp = ktime_set(-1L, 0);
+	sk->sk_stamp = SK_DEFAULT_STAMP;
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	sk->sk_napi_id		=	0;
@@ -2802,6 +2894,21 @@ void sk_common_release(struct sock *sk)
 }
 EXPORT_SYMBOL(sk_common_release);
 
+void sk_get_meminfo(const struct sock *sk, u32 *mem)
+{
+	memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS);
+
+	mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
+	mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
+	mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
+	mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
+	mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
+	mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
+	mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
+	mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
+	mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
+}
+
 #ifdef CONFIG_PROC_FS
 #define PROTO_INUSE_NR	64	/* should be enough for the first time */
 struct prot_inuse {
@@ -3142,3 +3249,14 @@ static int __init proto_init(void)
 subsys_initcall(proto_init);
 
 #endif /* PROC_FS */
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+bool sk_busy_loop_end(void *p, unsigned long start_time)
+{
+	struct sock *sk = p;
+
+	return !skb_queue_empty(&sk->sk_receive_queue) ||
+	       sk_busy_loop_timeout(sk, start_time);
+}
+EXPORT_SYMBOL(sk_busy_loop_end);
+#endif /* CONFIG_NET_RX_BUSY_POLL */
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 6b10573cc9fa..fb9d0e2fd148 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -19,7 +19,7 @@ static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
 static DEFINE_MUTEX(sock_diag_table_mutex);
 static struct workqueue_struct *broadcast_wq;
 
-static u64 sock_gen_cookie(struct sock *sk)
+u64 sock_gen_cookie(struct sock *sk)
 {
 	while (1) {
 		u64 res = atomic64_read(&sk->sk_cookie);
@@ -59,15 +59,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype)
 {
 	u32 mem[SK_MEMINFO_VARS];
 
-	mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
-	mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
-	mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
-	mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
-	mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
-	mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
-	mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
-	mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
-	mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
+	sk_get_meminfo(sk, mem);
 
 	return nla_put(skb, attrtype, sizeof(mem), &mem);
 }
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 9a1a352fd1eb..eed1ebf7f29d 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -13,9 +13,9 @@
 
 static DEFINE_SPINLOCK(reuseport_lock);
 
-static struct sock_reuseport *__reuseport_alloc(u16 max_socks)
+static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks)
 {
-	size_t size = sizeof(struct sock_reuseport) +
+	unsigned int size = sizeof(struct sock_reuseport) +
 		      sizeof(struct sock *) * max_socks;
 	struct sock_reuseport *reuse = kzalloc(size, GFP_ATOMIC);
 
diff --git a/net/core/utils.c b/net/core/utils.c
index 6592d7bbed39..d758880c09a7 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -51,7 +51,7 @@ EXPORT_SYMBOL(net_ratelimit);
 
 __be32 in_aton(const char *str)
 {
-	unsigned long l;
+	unsigned int l;
 	unsigned int val;
 	int i;
 
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 7de5b40a5d0d..9afa2a5030b2 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -132,6 +132,7 @@ Version 0.0.6    2.1.110   07-aug-98   Eduardo Marcelo Serrat
 #include <net/neighbour.h>
 #include <net/dst.h>
 #include <net/fib_rules.h>
+#include <net/tcp.h>
 #include <net/dn.h>
 #include <net/dn_nsp.h>
 #include <net/dn_dev.h>
@@ -1469,18 +1470,18 @@ static int __dn_setsockopt(struct socket *sock, int level,int optname, char __us
 	case DSO_NODELAY:
 		if (optlen != sizeof(int))
 			return -EINVAL;
-		if (scp->nonagle == 2)
+		if (scp->nonagle == TCP_NAGLE_CORK)
 			return -EINVAL;
-		scp->nonagle = (u.val == 0) ? 0 : 1;
+		scp->nonagle = (u.val == 0) ? 0 : TCP_NAGLE_OFF;
 		/* if (scp->nonagle == 1) { Push pending frames } */
 		break;
 
 	case DSO_CORK:
 		if (optlen != sizeof(int))
 			return -EINVAL;
-		if (scp->nonagle == 1)
+		if (scp->nonagle == TCP_NAGLE_OFF)
 			return -EINVAL;
-		scp->nonagle = (u.val == 0) ? 0 : 2;
+		scp->nonagle = (u.val == 0) ? 0 : TCP_NAGLE_CORK;
 		/* if (scp->nonagle == 0) { Push pending frames } */
 		break;
 
@@ -1608,14 +1609,14 @@ static int __dn_getsockopt(struct socket *sock, int level,int optname, char __us
 	case DSO_NODELAY:
 		if (r_len > sizeof(int))
 			r_len = sizeof(int);
-		val = (scp->nonagle == 1);
+		val = (scp->nonagle == TCP_NAGLE_OFF);
 		r_data = &val;
 		break;
 
 	case DSO_CORK:
 		if (r_len > sizeof(int))
 			r_len = sizeof(int);
-		val = (scp->nonagle == 2);
+		val = (scp->nonagle == TCP_NAGLE_CORK);
 		r_data = &val;
 		break;
 
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index 9649238eef40..da4d64f432db 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -6,7 +6,7 @@ config HAVE_NET_DSA
 
 config NET_DSA
 	tristate "Distributed Switch Architecture"
-	depends on HAVE_NET_DSA
+	depends on HAVE_NET_DSA && MAY_USE_DEVLINK
 	select NET_SWITCHDEV
 	select PHYLIB
 	---help---
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index b6d4f6a23f06..95d1a756202c 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -14,15 +14,16 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/module.h>
-#include <net/dsa.h>
 #include <linux/of.h>
 #include <linux/of_mdio.h>
 #include <linux/of_platform.h>
 #include <linux/of_net.h>
 #include <linux/of_gpio.h>
+#include <linux/netdevice.h>
 #include <linux/sysfs.h>
 #include <linux/phy_fixed.h>
 #include <linux/gpio/consumer.h>
+#include <net/dsa.h>
 #include "dsa_priv.h"
 
 static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb,
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 737be6470c7f..033b3bfb63dc 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -13,16 +13,20 @@
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/list.h>
+#include <linux/netdevice.h>
 #include <linux/slab.h>
 #include <linux/rtnetlink.h>
-#include <net/dsa.h>
 #include <linux/of.h>
 #include <linux/of_net.h>
+#include <net/dsa.h>
 #include "dsa_priv.h"
 
 static LIST_HEAD(dsa_switch_trees);
 static DEFINE_MUTEX(dsa2_mutex);
 
+static const struct devlink_ops dsa_devlink_ops = {
+};
+
 static struct dsa_switch_tree *dsa_get_dst(u32 tree)
 {
 	struct dsa_switch_tree *dst;
@@ -222,12 +226,18 @@ static int dsa_dsa_port_apply(struct dsa_port *port, u32 index,
 		return err;
 	}
 
-	return 0;
+	memset(&ds->ports[index].devlink_port, 0,
+	       sizeof(ds->ports[index].devlink_port));
+
+	return devlink_port_register(ds->devlink,
+				     &ds->ports[index].devlink_port,
+				     index);
 }
 
 static void dsa_dsa_port_unapply(struct dsa_port *port, u32 index,
 				 struct dsa_switch *ds)
 {
+	devlink_port_unregister(&ds->ports[index].devlink_port);
 	dsa_cpu_dsa_destroy(port);
 }
 
@@ -245,12 +255,17 @@ static int dsa_cpu_port_apply(struct dsa_port *port, u32 index,
 
 	ds->cpu_port_mask |= BIT(index);
 
-	return 0;
+	memset(&ds->ports[index].devlink_port, 0,
+	       sizeof(ds->ports[index].devlink_port));
+	err = devlink_port_register(ds->devlink, &ds->ports[index].devlink_port,
+				    index);
+	return err;
 }
 
 static void dsa_cpu_port_unapply(struct dsa_port *port, u32 index,
 				 struct dsa_switch *ds)
 {
+	devlink_port_unregister(&ds->ports[index].devlink_port);
 	dsa_cpu_dsa_destroy(port);
 	ds->cpu_port_mask &= ~BIT(index);
 
@@ -275,12 +290,23 @@ static int dsa_user_port_apply(struct dsa_port *port, u32 index,
 		return err;
 	}
 
+	memset(&ds->ports[index].devlink_port, 0,
+	       sizeof(ds->ports[index].devlink_port));
+	err = devlink_port_register(ds->devlink, &ds->ports[index].devlink_port,
+				    index);
+	if (err)
+		return err;
+
+	devlink_port_type_eth_set(&ds->ports[index].devlink_port,
+				  ds->ports[index].netdev);
+
 	return 0;
 }
 
 static void dsa_user_port_unapply(struct dsa_port *port, u32 index,
 				  struct dsa_switch *ds)
 {
+	devlink_port_unregister(&ds->ports[index].devlink_port);
 	if (ds->ports[index].netdev) {
 		dsa_slave_destroy(ds->ports[index].netdev);
 		ds->ports[index].netdev = NULL;
@@ -301,6 +327,17 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
 	 */
 	ds->phys_mii_mask = ds->enabled_port_mask;
 
+	/* Add the switch to devlink before calling setup, so that setup can
+	 * add dpipe tables
+	 */
+	ds->devlink = devlink_alloc(&dsa_devlink_ops, 0);
+	if (!ds->devlink)
+		return -ENOMEM;
+
+	err = devlink_register(ds->devlink, ds->dev);
+	if (err)
+		return err;
+
 	err = ds->ops->setup(ds);
 	if (err < 0)
 		return err;
@@ -381,6 +418,13 @@ static void dsa_ds_unapply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
 		mdiobus_unregister(ds->slave_mii_bus);
 
 	dsa_switch_unregister_notifier(ds);
+
+	if (ds->devlink) {
+		devlink_unregister(ds->devlink);
+		devlink_free(ds->devlink);
+		ds->devlink = NULL;
+	}
+
 }
 
 static int dsa_dst_apply(struct dsa_switch_tree *dst)
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index c34872e1febc..7693182df81e 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -17,6 +17,7 @@
 #include <linux/of_mdio.h>
 #include <linux/mdio.h>
 #include <linux/list.h>
+#include <net/dsa.h>
 #include <net/rtnetlink.h>
 #include <net/switchdev.h>
 #include <net/pkt_cls.h>
@@ -419,8 +420,8 @@ static int dsa_slave_vlan_filtering(struct net_device *dev,
 	return 0;
 }
 
-static int dsa_fastest_ageing_time(struct dsa_switch *ds,
-				   unsigned int ageing_time)
+static unsigned int dsa_fastest_ageing_time(struct dsa_switch *ds,
+					    unsigned int ageing_time)
 {
 	int i;
 
@@ -443,9 +444,13 @@ static int dsa_slave_ageing_time(struct net_device *dev,
 	unsigned long ageing_jiffies = clock_t_to_jiffies(attr->u.ageing_time);
 	unsigned int ageing_time = jiffies_to_msecs(ageing_jiffies);
 
-	/* bridge skips -EOPNOTSUPP, so skip the prepare phase */
-	if (switchdev_trans_ph_prepare(trans))
+	if (switchdev_trans_ph_prepare(trans)) {
+		if (ds->ageing_time_min && ageing_time < ds->ageing_time_min)
+			return -ERANGE;
+		if (ds->ageing_time_max && ageing_time > ds->ageing_time_max)
+			return -ERANGE;
 		return 0;
+	}
 
 	/* Keep the fastest ageing time in case of multiple bridges */
 	p->dp->ageing_time = ageing_time;
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 6456dacf9ae9..ca6e26e514f0 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -1,7 +1,8 @@
 /*
  * Handling of a single switch chip, part of a switch fabric
  *
- * Copyright (c) 2017 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2017 Savoir-faire Linux Inc.
+ *	Vivien Didelot <vivien.didelot@savoirfairelinux.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -19,9 +20,9 @@ static int dsa_switch_bridge_join(struct dsa_switch *ds,
 	if (ds->index == info->sw_index && ds->ops->port_bridge_join)
 		return ds->ops->port_bridge_join(ds, info->port, info->br);
 
-	if (ds->index != info->sw_index)
-		dev_dbg(ds->dev, "crosschip DSA port %d.%d bridged to %s\n",
-			info->sw_index, info->port, netdev_name(info->br));
+	if (ds->index != info->sw_index && ds->ops->crosschip_bridge_join)
+		return ds->ops->crosschip_bridge_join(ds, info->sw_index,
+						      info->port, info->br);
 
 	return 0;
 }
@@ -32,9 +33,9 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds,
 	if (ds->index == info->sw_index && ds->ops->port_bridge_leave)
 		ds->ops->port_bridge_leave(ds, info->port, info->br);
 
-	if (ds->index != info->sw_index)
-		dev_dbg(ds->dev, "crosschip DSA port %d.%d unbridged from %s\n",
-			info->sw_index, info->port, netdev_name(info->br));
+	if (ds->index != info->sw_index && ds->ops->crosschip_bridge_leave)
+		ds->ops->crosschip_bridge_leave(ds, info->sw_index, info->port,
+						info->br);
 
 	return 0;
 }
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index 5d925b6b2bb1..e2ed6cf68261 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -12,6 +12,7 @@
 #include <linux/etherdevice.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <net/dsa.h>
 #include "dsa_priv.h"
 
 /* This tag length is 4 bytes, older ones were 6 bytes, we do not
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index 72579ceea381..e42ba906100c 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -11,6 +11,7 @@
 #include <linux/etherdevice.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <net/dsa.h>
 #include "dsa_priv.h"
 
 #define DSA_HLEN	4
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index 648c051817a1..6a9b7a9e4e15 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -11,6 +11,7 @@
 #include <linux/etherdevice.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <net/dsa.h>
 #include "dsa_priv.h"
 
 #define DSA_HLEN	4
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index 30240f343aea..4e0dad759d04 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/etherdevice.h>
+#include <net/dsa.h>
 #include "dsa_priv.h"
 
 #define QCA_HDR_LEN	2
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 26f977176978..74c948512550 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -11,6 +11,7 @@
 #include <linux/etherdevice.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <net/dsa.h>
 #include "dsa_priv.h"
 
 static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev)
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index c6d4238ff94a..f83de23a30e7 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -11,7 +11,7 @@ obj-y     := route.o inetpeer.o protocol.o \
 	     tcp_rate.o tcp_recovery.o \
 	     tcp_offload.o datagram.o raw.o udp.o udplite.o \
 	     udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \
-	     fib_frontend.o fib_semantics.o fib_trie.o \
+	     fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \
 	     inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o
 
 obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 6b1fc6e4278e..d1a11707a126 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1599,8 +1599,9 @@ static const struct net_protocol igmp_protocol = {
 };
 #endif
 
-static const struct net_protocol tcp_protocol = {
+static struct net_protocol tcp_protocol = {
 	.early_demux	=	tcp_v4_early_demux,
+	.early_demux_handler =  tcp_v4_early_demux,
 	.handler	=	tcp_v4_rcv,
 	.err_handler	=	tcp_v4_err,
 	.no_policy	=	1,
@@ -1608,8 +1609,9 @@ static const struct net_protocol tcp_protocol = {
 	.icmp_strict_tag_validation = 1,
 };
 
-static const struct net_protocol udp_protocol = {
+static struct net_protocol udp_protocol = {
 	.early_demux =	udp_v4_early_demux,
+	.early_demux_handler =	udp_v4_early_demux,
 	.handler =	udp_rcv,
 	.err_handler =	udp_err,
 	.no_policy =	1,
@@ -1720,6 +1722,8 @@ static __net_init int inet_init_net(struct net *net)
 	net->ipv4.sysctl_ip_default_ttl = IPDEFTTL;
 	net->ipv4.sysctl_ip_dynaddr = 0;
 	net->ipv4.sysctl_ip_early_demux = 1;
+	net->ipv4.sysctl_udp_early_demux = 1;
+	net->ipv4.sysctl_tcp_early_demux = 1;
 #ifdef CONFIG_SYSCTL
 	net->ipv4.sysctl_ip_prot_sock = PROT_SOCK;
 #endif
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 51b27ae09fbd..0937b34c27ca 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -872,7 +872,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb)
 		    skb->pkt_type != PACKET_HOST)
 			state = NUD_STALE;
 		neigh_update(n, sha, state,
-			     override ? NEIGH_UPDATE_F_OVERRIDE : 0);
+			     override ? NEIGH_UPDATE_F_OVERRIDE : 0, 0);
 		neigh_release(n);
 	}
 
@@ -1033,7 +1033,7 @@ static int arp_req_set(struct net *net, struct arpreq *r,
 		err = neigh_update(neigh, (r->arp_flags & ATF_COM) ?
 				   r->arp_ha.sa_data : NULL, state,
 				   NEIGH_UPDATE_F_OVERRIDE |
-				   NEIGH_UPDATE_F_ADMIN);
+				   NEIGH_UPDATE_F_ADMIN, 0);
 		neigh_release(neigh);
 	}
 	return err;
@@ -1084,7 +1084,7 @@ static int arp_invalidate(struct net_device *dev, __be32 ip)
 		if (neigh->nud_state & ~NUD_NOARP)
 			err = neigh_update(neigh, NULL, NUD_FAILED,
 					   NEIGH_UPDATE_F_OVERRIDE|
-					   NEIGH_UPDATE_F_ADMIN);
+					   NEIGH_UPDATE_F_ADMIN, 0);
 		neigh_release(neigh);
 	}
 
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index cebedd545e5e..6d3602ec640c 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1192,6 +1192,18 @@ out:
 	return done;
 }
 
+static __be32 in_dev_select_addr(const struct in_device *in_dev,
+				 int scope)
+{
+	for_primary_ifa(in_dev) {
+		if (ifa->ifa_scope != RT_SCOPE_LINK &&
+		    ifa->ifa_scope <= scope)
+			return ifa->ifa_local;
+	} endfor_ifa(in_dev);
+
+	return 0;
+}
+
 __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope)
 {
 	__be32 addr = 0;
@@ -1228,13 +1240,9 @@ no_in_dev:
 	if (master_idx &&
 	    (dev = dev_get_by_index_rcu(net, master_idx)) &&
 	    (in_dev = __in_dev_get_rcu(dev))) {
-		for_primary_ifa(in_dev) {
-			if (ifa->ifa_scope != RT_SCOPE_LINK &&
-			    ifa->ifa_scope <= scope) {
-				addr = ifa->ifa_local;
-				goto out_unlock;
-			}
-		} endfor_ifa(in_dev);
+		addr = in_dev_select_addr(in_dev, scope);
+		if (addr)
+			goto out_unlock;
 	}
 
 	/* Not loopback addresses on loopback should be preferred
@@ -1249,13 +1257,9 @@ no_in_dev:
 		if (!in_dev)
 			continue;
 
-		for_primary_ifa(in_dev) {
-			if (ifa->ifa_scope != RT_SCOPE_LINK &&
-			    ifa->ifa_scope <= scope) {
-				addr = ifa->ifa_local;
-				goto out_unlock;
-			}
-		} endfor_ifa(in_dev);
+		addr = in_dev_select_addr(in_dev, scope);
+		if (addr)
+			goto out_unlock;
 	}
 out_unlock:
 	rcu_read_unlock();
@@ -1798,6 +1802,9 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 	if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0)
 		goto nla_put_failure;
 
+	if (!devconf)
+		goto out;
+
 	if ((all || type == NETCONFA_FORWARDING) &&
 	    nla_put_s32(skb, NETCONFA_FORWARDING,
 			IPV4_DEVCONF(*devconf, FORWARDING)) < 0)
@@ -1819,6 +1826,7 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 			IPV4_DEVCONF(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0)
 		goto nla_put_failure;
 
+out:
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -1827,8 +1835,8 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
-				 struct ipv4_devconf *devconf)
+void inet_netconf_notify_devconf(struct net *net, int event, int type,
+				 int ifindex, struct ipv4_devconf *devconf)
 {
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
@@ -1838,7 +1846,7 @@ void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
 		goto errout;
 
 	err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0,
-					RTM_NEWNETCONF, 0, type);
+					event, 0, type);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */
 		WARN_ON(err == -EMSGSIZE);
@@ -2017,10 +2025,12 @@ static void inet_forward_change(struct net *net)
 
 	IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on;
 	IPV4_DEVCONF_DFLT(net, FORWARDING) = on;
-	inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+	inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+				    NETCONFA_FORWARDING,
 				    NETCONFA_IFINDEX_ALL,
 				    net->ipv4.devconf_all);
-	inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+	inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+				    NETCONFA_FORWARDING,
 				    NETCONFA_IFINDEX_DEFAULT,
 				    net->ipv4.devconf_dflt);
 
@@ -2033,7 +2043,8 @@ static void inet_forward_change(struct net *net)
 		in_dev = __in_dev_get_rtnl(dev);
 		if (in_dev) {
 			IN_DEV_CONF_SET(in_dev, FORWARDING, on);
-			inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_FORWARDING,
 						    dev->ifindex, &in_dev->cnf);
 		}
 	}
@@ -2078,19 +2089,22 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write,
 		if (i == IPV4_DEVCONF_RP_FILTER - 1 &&
 		    new_value != old_value) {
 			ifindex = devinet_conf_ifindex(net, cnf);
-			inet_netconf_notify_devconf(net, NETCONFA_RP_FILTER,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_RP_FILTER,
 						    ifindex, cnf);
 		}
 		if (i == IPV4_DEVCONF_PROXY_ARP - 1 &&
 		    new_value != old_value) {
 			ifindex = devinet_conf_ifindex(net, cnf);
-			inet_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_PROXY_NEIGH,
 						    ifindex, cnf);
 		}
 		if (i == IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN - 1 &&
 		    new_value != old_value) {
 			ifindex = devinet_conf_ifindex(net, cnf);
-			inet_netconf_notify_devconf(net, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 						    ifindex, cnf);
 		}
 	}
@@ -2125,7 +2139,7 @@ static int devinet_sysctl_forward(struct ctl_table *ctl, int write,
 					container_of(cnf, struct in_device, cnf);
 				if (*valp)
 					dev_disable_lro(idev->dev);
-				inet_netconf_notify_devconf(net,
+				inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
 							    NETCONFA_FORWARDING,
 							    idev->dev->ifindex,
 							    cnf);
@@ -2133,7 +2147,8 @@ static int devinet_sysctl_forward(struct ctl_table *ctl, int write,
 			rtnl_unlock();
 			rt_cache_flush(net);
 		} else
-			inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_FORWARDING,
 						    NETCONFA_IFINDEX_DEFAULT,
 						    net->ipv4.devconf_dflt);
 	}
@@ -2255,7 +2270,8 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name,
 
 	p->sysctl = t;
 
-	inet_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p);
+	inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL,
+				    ifindex, p);
 	return 0;
 
 free:
@@ -2264,16 +2280,18 @@ out:
 	return -ENOBUFS;
 }
 
-static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf)
+static void __devinet_sysctl_unregister(struct net *net,
+					struct ipv4_devconf *cnf, int ifindex)
 {
 	struct devinet_sysctl_table *t = cnf->sysctl;
 
-	if (!t)
-		return;
+	if (t) {
+		cnf->sysctl = NULL;
+		unregister_net_sysctl_table(t->sysctl_header);
+		kfree(t);
+	}
 
-	cnf->sysctl = NULL;
-	unregister_net_sysctl_table(t->sysctl_header);
-	kfree(t);
+	inet_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL);
 }
 
 static int devinet_sysctl_register(struct in_device *idev)
@@ -2295,7 +2313,9 @@ static int devinet_sysctl_register(struct in_device *idev)
 
 static void devinet_sysctl_unregister(struct in_device *idev)
 {
-	__devinet_sysctl_unregister(&idev->cnf);
+	struct net *net = dev_net(idev->dev);
+
+	__devinet_sysctl_unregister(net, &idev->cnf, idev->dev->ifindex);
 	neigh_sysctl_unregister(idev->arp_parms);
 }
 
@@ -2370,9 +2390,9 @@ static __net_init int devinet_init_net(struct net *net)
 
 #ifdef CONFIG_SYSCTL
 err_reg_ctl:
-	__devinet_sysctl_unregister(dflt);
+	__devinet_sysctl_unregister(net, dflt, NETCONFA_IFINDEX_DEFAULT);
 err_reg_dflt:
-	__devinet_sysctl_unregister(all);
+	__devinet_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL);
 err_reg_all:
 	if (tbl != ctl_forward_entry)
 		kfree(tbl);
@@ -2394,8 +2414,10 @@ static __net_exit void devinet_exit_net(struct net *net)
 
 	tbl = net->ipv4.forw_hdr->ctl_table_arg;
 	unregister_net_sysctl_table(net->ipv4.forw_hdr);
-	__devinet_sysctl_unregister(net->ipv4.devconf_dflt);
-	__devinet_sysctl_unregister(net->ipv4.devconf_all);
+	__devinet_sysctl_unregister(net, net->ipv4.devconf_dflt,
+				    NETCONFA_IFINDEX_DEFAULT);
+	__devinet_sysctl_unregister(net, net->ipv4.devconf_all,
+				    NETCONFA_IFINDEX_ALL);
 	kfree(tbl);
 #endif
 	kfree(net->ipv4.devconf_dflt);
diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c
new file mode 100644
index 000000000000..e0714d975947
--- /dev/null
+++ b/net/ipv4/fib_notifier.c
@@ -0,0 +1,86 @@
+#include <linux/rtnetlink.h>
+#include <linux/notifier.h>
+#include <linux/rcupdate.h>
+#include <linux/kernel.h>
+#include <net/net_namespace.h>
+#include <net/netns/ipv4.h>
+#include <net/ip_fib.h>
+
+static ATOMIC_NOTIFIER_HEAD(fib_chain);
+
+int call_fib_notifier(struct notifier_block *nb, struct net *net,
+		      enum fib_event_type event_type,
+		      struct fib_notifier_info *info)
+{
+	info->net = net;
+	return nb->notifier_call(nb, event_type, info);
+}
+
+int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
+		       struct fib_notifier_info *info)
+{
+	net->ipv4.fib_seq++;
+	info->net = net;
+	return atomic_notifier_call_chain(&fib_chain, event_type, info);
+}
+
+static unsigned int fib_seq_sum(void)
+{
+	unsigned int fib_seq = 0;
+	struct net *net;
+
+	rtnl_lock();
+	for_each_net(net)
+		fib_seq += net->ipv4.fib_seq;
+	rtnl_unlock();
+
+	return fib_seq;
+}
+
+static bool fib_dump_is_consistent(struct notifier_block *nb,
+				   void (*cb)(struct notifier_block *nb),
+				   unsigned int fib_seq)
+{
+	atomic_notifier_chain_register(&fib_chain, nb);
+	if (fib_seq == fib_seq_sum())
+		return true;
+	atomic_notifier_chain_unregister(&fib_chain, nb);
+	if (cb)
+		cb(nb);
+	return false;
+}
+
+#define FIB_DUMP_MAX_RETRIES 5
+int register_fib_notifier(struct notifier_block *nb,
+			  void (*cb)(struct notifier_block *nb))
+{
+	int retries = 0;
+
+	do {
+		unsigned int fib_seq = fib_seq_sum();
+		struct net *net;
+
+		/* Mutex semantics guarantee that every change done to
+		 * FIB tries before we read the change sequence counter
+		 * is now visible to us.
+		 */
+		rcu_read_lock();
+		for_each_net_rcu(net) {
+			fib_rules_notify(net, nb);
+			fib_notify(net, nb);
+		}
+		rcu_read_unlock();
+
+		if (fib_dump_is_consistent(nb, cb, fib_seq))
+			return 0;
+	} while (++retries < FIB_DUMP_MAX_RETRIES);
+
+	return -EBUSY;
+}
+EXPORT_SYMBOL(register_fib_notifier);
+
+int unregister_fib_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(&fib_chain, nb);
+}
+EXPORT_SYMBOL(unregister_fib_notifier);
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 2e50062f642d..778ecf977eb2 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -47,6 +47,27 @@ struct fib4_rule {
 #endif
 };
 
+static bool fib4_rule_matchall(const struct fib_rule *rule)
+{
+	struct fib4_rule *r = container_of(rule, struct fib4_rule, common);
+
+	if (r->dst_len || r->src_len || r->tos)
+		return false;
+	return fib_rule_matchall(rule);
+}
+
+bool fib4_rule_default(const struct fib_rule *rule)
+{
+	if (!fib4_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL ||
+	    rule->l3mdev)
+		return false;
+	if (rule->table != RT_TABLE_LOCAL && rule->table != RT_TABLE_MAIN &&
+	    rule->table != RT_TABLE_DEFAULT)
+		return false;
+	return true;
+}
+EXPORT_SYMBOL_GPL(fib4_rule_default);
+
 int __fib_lookup(struct net *net, struct flowi4 *flp,
 		 struct fib_result *res, unsigned int flags)
 {
@@ -164,12 +185,36 @@ static struct fib_table *fib_empty_table(struct net *net)
 	return NULL;
 }
 
+static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net,
+				  enum fib_event_type event_type,
+				  struct fib_rule *rule)
+{
+	struct fib_rule_notifier_info info = {
+		.rule = rule,
+	};
+
+	return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
 static int call_fib_rule_notifiers(struct net *net,
-				   enum fib_event_type event_type)
+				   enum fib_event_type event_type,
+				   struct fib_rule *rule)
+{
+	struct fib_rule_notifier_info info = {
+		.rule = rule,
+	};
+
+	return call_fib_notifiers(net, event_type, &info.info);
+}
+
+/* Called with rcu_read_lock() */
+void fib_rules_notify(struct net *net, struct notifier_block *nb)
 {
-	struct fib_notifier_info info;
+	struct fib_rules_ops *ops = net->ipv4.rules_ops;
+	struct fib_rule *rule;
 
-	return call_fib_notifiers(net, event_type, &info);
+	list_for_each_entry_rcu(rule, &ops->rules_list, list)
+		call_fib_rule_notifier(nb, net, FIB_EVENT_RULE_ADD, rule);
 }
 
 static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = {
@@ -228,7 +273,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	rule4->tos = frh->tos;
 
 	net->ipv4.fib_has_custom_rules = true;
-	call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD);
+	call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule);
 
 	err = 0;
 errout:
@@ -250,7 +295,7 @@ static int fib4_rule_delete(struct fib_rule *rule)
 		net->ipv4.fib_num_tclassid_users--;
 #endif
 	net->ipv4.fib_has_custom_rules = true;
-	call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL);
+	call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule);
 errout:
 	return err;
 }
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 317026a39cfa..da449ddb8cc1 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -57,7 +57,6 @@ static unsigned int fib_info_cnt;
 static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE];
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-u32 fib_multipath_secret __read_mostly;
 
 #define for_nexthops(fi) {						\
 	int nhsel; const struct fib_nh *nh;				\
@@ -576,9 +575,6 @@ static void fib_rebalance(struct fib_info *fi)
 
 		atomic_set(&nexthop_nh->nh_upper_bound, upper_bound);
 	} endfor_nexthops(fi);
-
-	net_get_random_once(&fib_multipath_secret,
-			    sizeof(fib_multipath_secret));
 }
 
 static inline void fib_add_weight(struct fib_info *fi,
@@ -1641,7 +1637,7 @@ void fib_select_multipath(struct fib_result *res, int hash)
 #endif
 
 void fib_select_path(struct net *net, struct fib_result *res,
-		     struct flowi4 *fl4, int mp_hash)
+		     struct flowi4 *fl4, const struct sk_buff *skb)
 {
 	bool oif_check;
 
@@ -1650,10 +1646,9 @@ void fib_select_path(struct net *net, struct fib_result *res,
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res->fi->fib_nhs > 1 && oif_check) {
-		if (mp_hash < 0)
-			mp_hash = get_hash_from_flowi4(fl4) >> 1;
+		int h = fib_multipath_hash(res->fi, fl4, skb);
 
-		fib_select_multipath(res, mp_hash);
+		fib_select_multipath(res, h);
 	}
 	else
 #endif
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 2f0d8233950f..1201409ba1dc 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -84,43 +84,6 @@
 #include <trace/events/fib.h>
 #include "fib_lookup.h"
 
-static unsigned int fib_seq_sum(void)
-{
-	unsigned int fib_seq = 0;
-	struct net *net;
-
-	rtnl_lock();
-	for_each_net(net)
-		fib_seq += net->ipv4.fib_seq;
-	rtnl_unlock();
-
-	return fib_seq;
-}
-
-static ATOMIC_NOTIFIER_HEAD(fib_chain);
-
-static int call_fib_notifier(struct notifier_block *nb, struct net *net,
-			     enum fib_event_type event_type,
-			     struct fib_notifier_info *info)
-{
-	info->net = net;
-	return nb->notifier_call(nb, event_type, info);
-}
-
-static void fib_rules_notify(struct net *net, struct notifier_block *nb,
-			     enum fib_event_type event_type)
-{
-#ifdef CONFIG_IP_MULTIPLE_TABLES
-	struct fib_notifier_info info;
-
-	if (net->ipv4.fib_has_custom_rules)
-		call_fib_notifier(nb, net, event_type, &info);
-#endif
-}
-
-static void fib_notify(struct net *net, struct notifier_block *nb,
-		       enum fib_event_type event_type);
-
 static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net,
 				   enum fib_event_type event_type, u32 dst,
 				   int dst_len, struct fib_info *fi,
@@ -137,62 +100,6 @@ static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net,
 	return call_fib_notifier(nb, net, event_type, &info.info);
 }
 
-static bool fib_dump_is_consistent(struct notifier_block *nb,
-				   void (*cb)(struct notifier_block *nb),
-				   unsigned int fib_seq)
-{
-	atomic_notifier_chain_register(&fib_chain, nb);
-	if (fib_seq == fib_seq_sum())
-		return true;
-	atomic_notifier_chain_unregister(&fib_chain, nb);
-	if (cb)
-		cb(nb);
-	return false;
-}
-
-#define FIB_DUMP_MAX_RETRIES 5
-int register_fib_notifier(struct notifier_block *nb,
-			  void (*cb)(struct notifier_block *nb))
-{
-	int retries = 0;
-
-	do {
-		unsigned int fib_seq = fib_seq_sum();
-		struct net *net;
-
-		/* Mutex semantics guarantee that every change done to
-		 * FIB tries before we read the change sequence counter
-		 * is now visible to us.
-		 */
-		rcu_read_lock();
-		for_each_net_rcu(net) {
-			fib_rules_notify(net, nb, FIB_EVENT_RULE_ADD);
-			fib_notify(net, nb, FIB_EVENT_ENTRY_ADD);
-		}
-		rcu_read_unlock();
-
-		if (fib_dump_is_consistent(nb, cb, fib_seq))
-			return 0;
-	} while (++retries < FIB_DUMP_MAX_RETRIES);
-
-	return -EBUSY;
-}
-EXPORT_SYMBOL(register_fib_notifier);
-
-int unregister_fib_notifier(struct notifier_block *nb)
-{
-	return atomic_notifier_chain_unregister(&fib_chain, nb);
-}
-EXPORT_SYMBOL(unregister_fib_notifier);
-
-int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
-		       struct fib_notifier_info *info)
-{
-	net->ipv4.fib_seq++;
-	info->net = net;
-	return atomic_notifier_call_chain(&fib_chain, event_type, info);
-}
-
 static int call_fib_entry_notifiers(struct net *net,
 				    enum fib_event_type event_type, u32 dst,
 				    int dst_len, struct fib_info *fi,
@@ -1995,8 +1902,7 @@ int fib_table_flush(struct net *net, struct fib_table *tb)
 }
 
 static void fib_leaf_notify(struct net *net, struct key_vector *l,
-			    struct fib_table *tb, struct notifier_block *nb,
-			    enum fib_event_type event_type)
+			    struct fib_table *tb, struct notifier_block *nb)
 {
 	struct fib_alias *fa;
 
@@ -2012,22 +1918,21 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l,
 		if (tb->tb_id != fa->tb_id)
 			continue;
 
-		call_fib_entry_notifier(nb, net, event_type, l->key,
+		call_fib_entry_notifier(nb, net, FIB_EVENT_ENTRY_ADD, l->key,
 					KEYLENGTH - fa->fa_slen, fi, fa->fa_tos,
 					fa->fa_type, fa->tb_id);
 	}
 }
 
 static void fib_table_notify(struct net *net, struct fib_table *tb,
-			     struct notifier_block *nb,
-			     enum fib_event_type event_type)
+			     struct notifier_block *nb)
 {
 	struct trie *t = (struct trie *)tb->tb_data;
 	struct key_vector *l, *tp = t->kv;
 	t_key key = 0;
 
 	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
-		fib_leaf_notify(net, l, tb, nb, event_type);
+		fib_leaf_notify(net, l, tb, nb);
 
 		key = l->key + 1;
 		/* stop in case of wrap around */
@@ -2036,8 +1941,7 @@ static void fib_table_notify(struct net *net, struct fib_table *tb,
 	}
 }
 
-static void fib_notify(struct net *net, struct notifier_block *nb,
-		       enum fib_event_type event_type)
+void fib_notify(struct net *net, struct notifier_block *nb)
 {
 	unsigned int h;
 
@@ -2046,7 +1950,7 @@ static void fib_notify(struct net *net, struct notifier_block *nb,
 		struct fib_table *tb;
 
 		hlist_for_each_entry_rcu(tb, head, tb_hlist)
-			fib_table_notify(net, tb, nb, event_type);
+			fib_table_notify(net, tb, nb);
 	}
 }
 
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index fc310db2708b..43318b5f5647 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -464,22 +464,6 @@ out_bh_enable:
 	local_bh_enable();
 }
 
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
-
-/* Source and destination is swapped. See ip_multipath_icmp_hash */
-static int icmp_multipath_hash_skb(const struct sk_buff *skb)
-{
-	const struct iphdr *iph = ip_hdr(skb);
-
-	return fib_multipath_hash(iph->daddr, iph->saddr);
-}
-
-#else
-
-#define icmp_multipath_hash_skb(skb) (-1)
-
-#endif
-
 static struct rtable *icmp_route_lookup(struct net *net,
 					struct flowi4 *fl4,
 					struct sk_buff *skb_in,
@@ -505,8 +489,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev);
 
 	security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
-	rt = __ip_route_output_key_hash(net, fl4,
-					icmp_multipath_hash_skb(skb_in));
+	rt = __ip_route_output_key_hash(net, fl4, skb_in);
 	if (IS_ERR(rt))
 		return rt;
 
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index d6feabb03516..fa2dc8f692c6 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -313,6 +313,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 	const struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt;
 	struct net_device *dev = skb->dev;
+	void (*edemux)(struct sk_buff *skb);
 
 	/* if ingress device is enslaved to an L3 master device pass the
 	 * skb to its handler for processing
@@ -329,8 +330,8 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 		int protocol = iph->protocol;
 
 		ipprot = rcu_dereference(inet_protos[protocol]);
-		if (ipprot && ipprot->early_demux) {
-			ipprot->early_demux(skb);
+		if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) {
+			edemux(skb);
 			/* must reload iph, skb->head might have changed */
 			iph = ip_hdr(skb);
 		}
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index dfb2ab2dd3c8..c3b12b1c7162 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -57,6 +57,7 @@
 #include <linux/export.h>
 #include <net/net_namespace.h>
 #include <net/arp.h>
+#include <net/dsa.h>
 #include <net/ip.h>
 #include <net/ipconfig.h>
 #include <net/route.h>
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c0317c940bcd..5bca64fc71b7 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -631,7 +631,7 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify,
 	in_dev = __in_dev_get_rtnl(dev);
 	if (in_dev) {
 		IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)--;
-		inet_netconf_notify_devconf(dev_net(dev),
+		inet_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
 					    NETCONFA_MC_FORWARDING,
 					    dev->ifindex, &in_dev->cnf);
 		ip_rt_multicast_event(in_dev);
@@ -820,8 +820,8 @@ static int vif_add(struct net *net, struct mr_table *mrt,
 		return -EADDRNOTAVAIL;
 	}
 	IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)++;
-	inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, dev->ifindex,
-				    &in_dev->cnf);
+	inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING,
+				    dev->ifindex, &in_dev->cnf);
 	ip_rt_multicast_event(in_dev);
 
 	/* Fill in the VIF structures */
@@ -1282,7 +1282,8 @@ static void mrtsock_destruct(struct sock *sk)
 	ipmr_for_each_table(mrt, net) {
 		if (sk == rtnl_dereference(mrt->mroute_sk)) {
 			IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
-			inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_MC_FORWARDING,
 						    NETCONFA_IFINDEX_ALL,
 						    net->ipv4.devconf_all);
 			RCU_INIT_POINTER(mrt->mroute_sk, NULL);
@@ -1344,7 +1345,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 		if (ret == 0) {
 			rcu_assign_pointer(mrt->mroute_sk, sk);
 			IPV4_DEVCONF_ALL(net, MC_FORWARDING)++;
-			inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+			inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_MC_FORWARDING,
 						    NETCONFA_IFINDEX_ALL,
 						    net->ipv4.devconf_all);
 		}
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 6241a81fd7f5..f17dab1dee6e 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -562,8 +562,6 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 		    XT_ERROR_TARGET) == 0)
 			++newinfo->stacksize;
 	}
-	if (ret != 0)
-		goto out_free;
 
 	ret = -EINVAL;
 	if (i != repl->num_entries)
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 52f26459efc3..fcbdc0c49b0e 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -22,6 +22,7 @@
 #include <linux/icmp.h>
 #include <linux/if_arp.h>
 #include <linux/seq_file.h>
+#include <linux/refcount.h>
 #include <linux/netfilter_arp.h>
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter_ipv4/ip_tables.h>
@@ -40,8 +41,8 @@ MODULE_DESCRIPTION("Xtables: CLUSTERIP target");
 
 struct clusterip_config {
 	struct list_head list;			/* list of all configs */
-	atomic_t refcount;			/* reference count */
-	atomic_t entries;			/* number of entries/rules
+	refcount_t refcount;			/* reference count */
+	refcount_t entries;			/* number of entries/rules
 						 * referencing us */
 
 	__be32 clusterip;			/* the IP address */
@@ -77,7 +78,7 @@ struct clusterip_net {
 static inline void
 clusterip_config_get(struct clusterip_config *c)
 {
-	atomic_inc(&c->refcount);
+	refcount_inc(&c->refcount);
 }
 
 
@@ -89,7 +90,7 @@ static void clusterip_config_rcu_free(struct rcu_head *head)
 static inline void
 clusterip_config_put(struct clusterip_config *c)
 {
-	if (atomic_dec_and_test(&c->refcount))
+	if (refcount_dec_and_test(&c->refcount))
 		call_rcu_bh(&c->rcu, clusterip_config_rcu_free);
 }
 
@@ -103,7 +104,7 @@ clusterip_config_entry_put(struct clusterip_config *c)
 	struct clusterip_net *cn = net_generic(net, clusterip_net_id);
 
 	local_bh_disable();
-	if (atomic_dec_and_lock(&c->entries, &cn->lock)) {
+	if (refcount_dec_and_lock(&c->entries, &cn->lock)) {
 		list_del_rcu(&c->list);
 		spin_unlock(&cn->lock);
 		local_bh_enable();
@@ -149,10 +150,10 @@ clusterip_config_find_get(struct net *net, __be32 clusterip, int entry)
 			c = NULL;
 		else
 #endif
-		if (unlikely(!atomic_inc_not_zero(&c->refcount)))
+		if (unlikely(!refcount_inc_not_zero(&c->refcount)))
 			c = NULL;
 		else if (entry)
-			atomic_inc(&c->entries);
+			refcount_inc(&c->entries);
 	}
 	rcu_read_unlock_bh();
 
@@ -188,8 +189,8 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip,
 	clusterip_config_init_nodelist(c, i);
 	c->hash_mode = i->hash_mode;
 	c->hash_initval = i->hash_initval;
-	atomic_set(&c->refcount, 1);
-	atomic_set(&c->entries, 1);
+	refcount_set(&c->refcount, 1);
+	refcount_set(&c->entries, 1);
 
 	spin_lock_bh(&cn->lock);
 	if (__clusterip_config_find(net, ip)) {
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index 53e49f5011d3..da04b9c33ef3 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -998,18 +998,6 @@ err_id_free:
  *
  *****************************************************************************/
 
-static void hex_dump(const unsigned char *buf, size_t len)
-{
-	size_t i;
-
-	for (i = 0; i < len; i++) {
-		if (i && !(i % 16))
-			printk("\n");
-		printk("%02x ", *(buf + i));
-	}
-	printk("\n");
-}
-
 /*
  * Parse and mangle SNMP message according to mapping.
  * (And this is the fucking 'basic' method).
@@ -1026,7 +1014,8 @@ static int snmp_parse_mangle(unsigned char *msg,
 	struct snmp_object *obj;
 
 	if (debug > 1)
-		hex_dump(msg, len);
+		print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_NONE, 16, 1,
+			       msg, len, 0);
 
 	asn1_open(&ctx, msg, len);
 
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 146d86105183..7cd8d0d918f8 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -104,7 +104,6 @@ EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_put);
 void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 {
 	struct sk_buff *nskb;
-	const struct iphdr *oiph;
 	struct iphdr *niph;
 	const struct tcphdr *oth;
 	struct tcphdr _oth;
@@ -116,8 +115,6 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 	if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
 		return;
 
-	oiph = ip_hdr(oldskb);
-
 	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
 			 LL_MAX_HEADER, GFP_ATOMIC);
 	if (!nskb)
diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
index 2981291910dd..f4e4462cb5bb 100644
--- a/net/ipv4/netfilter/nft_fib_ipv4.c
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -90,7 +90,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 
 	if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
 	    nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
-		nft_fib_store_result(dest, priv->result, pkt,
+		nft_fib_store_result(dest, priv, pkt,
 				     nft_in(pkt)->ifindex);
 		return;
 	}
@@ -99,7 +99,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	if (ipv4_is_zeronet(iph->saddr)) {
 		if (ipv4_is_lbcast(iph->daddr) ||
 		    ipv4_is_local_multicast(iph->daddr)) {
-			nft_fib_store_result(dest, priv->result, pkt,
+			nft_fib_store_result(dest, priv, pkt,
 					     get_ifindex(pkt->skb->dev));
 			return;
 		}
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 69cf49e8356d..4ccbf464d1ac 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -199,7 +199,6 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TW", LINUX_MIB_TIMEWAITED),
 	SNMP_MIB_ITEM("TWRecycled", LINUX_MIB_TIMEWAITRECYCLED),
 	SNMP_MIB_ITEM("TWKilled", LINUX_MIB_TIMEWAITKILLED),
-	SNMP_MIB_ITEM("PAWSPassive", LINUX_MIB_PAWSPASSIVEREJECTED),
 	SNMP_MIB_ITEM("PAWSActive", LINUX_MIB_PAWSACTIVEREJECTED),
 	SNMP_MIB_ITEM("PAWSEstab", LINUX_MIB_PAWSESTABREJECTED),
 	SNMP_MIB_ITEM("DelayedACKs", LINUX_MIB_DELAYEDACKS),
diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index 4b7c0ec65251..32a691b7ce2c 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -28,7 +28,7 @@
 #include <linux/spinlock.h>
 #include <net/protocol.h>
 
-const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly;
+struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly;
 const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly;
 EXPORT_SYMBOL(inet_offloads);
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8471dd116771..5dda1ef81c7e 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1734,45 +1734,97 @@ out:
 }
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-
 /* To make ICMP packets follow the right flow, the multipath hash is
- * calculated from the inner IP addresses in reverse order.
+ * calculated from the inner IP addresses.
  */
-static int ip_multipath_icmp_hash(struct sk_buff *skb)
+static void ip_multipath_l3_keys(const struct sk_buff *skb,
+				 struct flow_keys *hash_keys)
 {
 	const struct iphdr *outer_iph = ip_hdr(skb);
-	struct icmphdr _icmph;
+	const struct iphdr *inner_iph;
 	const struct icmphdr *icmph;
 	struct iphdr _inner_iph;
-	const struct iphdr *inner_iph;
+	struct icmphdr _icmph;
+
+	hash_keys->addrs.v4addrs.src = outer_iph->saddr;
+	hash_keys->addrs.v4addrs.dst = outer_iph->daddr;
+	if (likely(outer_iph->protocol != IPPROTO_ICMP))
+		return;
 
 	if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0))
-		goto standard_hash;
+		return;
 
 	icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph),
 				   &_icmph);
 	if (!icmph)
-		goto standard_hash;
+		return;
 
 	if (icmph->type != ICMP_DEST_UNREACH &&
 	    icmph->type != ICMP_REDIRECT &&
 	    icmph->type != ICMP_TIME_EXCEEDED &&
-	    icmph->type != ICMP_PARAMETERPROB) {
-		goto standard_hash;
-	}
+	    icmph->type != ICMP_PARAMETERPROB)
+		return;
 
 	inner_iph = skb_header_pointer(skb,
 				       outer_iph->ihl * 4 + sizeof(_icmph),
 				       sizeof(_inner_iph), &_inner_iph);
 	if (!inner_iph)
-		goto standard_hash;
+		return;
+	hash_keys->addrs.v4addrs.src = inner_iph->saddr;
+	hash_keys->addrs.v4addrs.dst = inner_iph->daddr;
+}
 
-	return fib_multipath_hash(inner_iph->daddr, inner_iph->saddr);
+/* if skb is set it will be used and fl4 can be NULL */
+int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
+		       const struct sk_buff *skb)
+{
+	struct net *net = fi->fib_net;
+	struct flow_keys hash_keys;
+	u32 mhash;
 
-standard_hash:
-	return fib_multipath_hash(outer_iph->saddr, outer_iph->daddr);
-}
+	switch (net->ipv4.sysctl_fib_multipath_hash_policy) {
+	case 0:
+		memset(&hash_keys, 0, sizeof(hash_keys));
+		hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+		if (skb) {
+			ip_multipath_l3_keys(skb, &hash_keys);
+		} else {
+			hash_keys.addrs.v4addrs.src = fl4->saddr;
+			hash_keys.addrs.v4addrs.dst = fl4->daddr;
+		}
+		break;
+	case 1:
+		/* skb is currently provided only when forwarding */
+		if (skb) {
+			unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP;
+			struct flow_keys keys;
+
+			/* short-circuit if we already have L4 hash present */
+			if (skb->l4_hash)
+				return skb_get_hash_raw(skb) >> 1;
+			memset(&hash_keys, 0, sizeof(hash_keys));
+			skb_flow_dissect_flow_keys(skb, &keys, flag);
+			hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
+			hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
+			hash_keys.ports.src = keys.ports.src;
+			hash_keys.ports.dst = keys.ports.dst;
+			hash_keys.basic.ip_proto = keys.basic.ip_proto;
+		} else {
+			memset(&hash_keys, 0, sizeof(hash_keys));
+			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+			hash_keys.addrs.v4addrs.src = fl4->saddr;
+			hash_keys.addrs.v4addrs.dst = fl4->daddr;
+			hash_keys.ports.src = fl4->fl4_sport;
+			hash_keys.ports.dst = fl4->fl4_dport;
+			hash_keys.basic.ip_proto = fl4->flowi4_proto;
+		}
+		break;
+	}
+	mhash = flow_hash_from_keys(&hash_keys);
 
+	return mhash >> 1;
+}
+EXPORT_SYMBOL_GPL(fib_multipath_hash);
 #endif /* CONFIG_IP_ROUTE_MULTIPATH */
 
 static int ip_mkroute_input(struct sk_buff *skb,
@@ -1782,12 +1834,8 @@ static int ip_mkroute_input(struct sk_buff *skb,
 {
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res->fi && res->fi->fib_nhs > 1) {
-		int h;
+		int h = fib_multipath_hash(res->fi, NULL, skb);
 
-		if (unlikely(ip_hdr(skb)->protocol == IPPROTO_ICMP))
-			h = ip_multipath_icmp_hash(skb);
-		else
-			h = fib_multipath_hash(saddr, daddr);
 		fib_select_multipath(res, h);
 	}
 #endif
@@ -2203,7 +2251,7 @@ add:
  */
 
 struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
-					  int mp_hash)
+					  const struct sk_buff *skb)
 {
 	struct net_device *dev_out = NULL;
 	__u8 tos = RT_FL_TOS(fl4);
@@ -2365,7 +2413,7 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
 		goto make_route;
 	}
 
-	fib_select_path(net, &res, fl4, mp_hash);
+	fib_select_path(net, &res, fl4, skb);
 
 	dev_out = FIB_RES_DEV(res);
 	fl4->flowi4_oif = dev_out->ifindex;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d6880a6149ee..6fb25693c00b 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -24,6 +24,7 @@
 #include <net/cipso_ipv4.h>
 #include <net/inet_frag.h>
 #include <net/ping.h>
+#include <net/protocol.h>
 
 static int zero;
 static int one = 1;
@@ -294,6 +295,58 @@ bad_key:
 	return ret;
 }
 
+static void proc_configure_early_demux(int enabled, int protocol)
+{
+	struct net_protocol *ipprot;
+#if IS_ENABLED(CONFIG_IPV6)
+	struct inet6_protocol *ip6prot;
+#endif
+
+	ipprot = rcu_dereference(inet_protos[protocol]);
+	if (ipprot)
+		ipprot->early_demux = enabled ? ipprot->early_demux_handler :
+						NULL;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	ip6prot = rcu_dereference(inet6_protos[protocol]);
+	if (ip6prot)
+		ip6prot->early_demux = enabled ? ip6prot->early_demux_handler :
+						 NULL;
+#endif
+}
+
+static int proc_tcp_early_demux(struct ctl_table *table, int write,
+				void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret = 0;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+	if (write && !ret) {
+		int enabled = init_net.ipv4.sysctl_tcp_early_demux;
+
+		proc_configure_early_demux(enabled, IPPROTO_TCP);
+	}
+
+	return ret;
+}
+
+static int proc_udp_early_demux(struct ctl_table *table, int write,
+				void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret = 0;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+	if (write && !ret) {
+		int enabled = init_net.ipv4.sysctl_udp_early_demux;
+
+		proc_configure_early_demux(enabled, IPPROTO_UDP);
+	}
+
+	return ret;
+}
+
 static struct ctl_table ipv4_table[] = {
 	{
 		.procname	= "tcp_timestamps",
@@ -750,6 +803,20 @@ static struct ctl_table ipv4_net_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 	{
+		.procname       = "udp_early_demux",
+		.data           = &init_net.ipv4.sysctl_udp_early_demux,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_udp_early_demux
+	},
+	{
+		.procname       = "tcp_early_demux",
+		.data           = &init_net.ipv4.sysctl_tcp_early_demux,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_tcp_early_demux
+	},
+	{
 		.procname	= "ip_default_ttl",
 		.data		= &init_net.ipv4.sysctl_ip_default_ttl,
 		.maxlen		= sizeof(int),
@@ -981,13 +1048,6 @@ static struct ctl_table ipv4_net_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 	{
-		.procname	= "tcp_tw_recycle",
-		.data		= &init_net.ipv4.tcp_death_row.sysctl_tw_recycle,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
 		.procname	= "tcp_max_syn_backlog",
 		.data		= &init_net.ipv4.sysctl_max_syn_backlog,
 		.maxlen		= sizeof(int),
@@ -1004,6 +1064,15 @@ static struct ctl_table ipv4_net_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
+	{
+		.procname	= "fib_multipath_hash_policy",
+		.data		= &init_net.ipv4.sysctl_fib_multipath_hash_policy,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 #endif
 	{
 		.procname	= "ip_unprivileged_port_start",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1e319a525d51..94f0b5b50e0d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2393,7 +2393,7 @@ static int tcp_repair_options_est(struct tcp_sock *tp,
 				u16 snd_wscale = opt.opt_val & 0xFFFF;
 				u16 rcv_wscale = opt.opt_val >> 16;
 
-				if (snd_wscale > 14 || rcv_wscale > 14)
+				if (snd_wscale > TCP_MAX_WSCALE || rcv_wscale > TCP_MAX_WSCALE)
 					return -EFBIG;
 
 				tp->rx_opt.snd_wscale = snd_wscale;
@@ -2470,7 +2470,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		/* Values greater than interface MTU won't take effect. However
 		 * at the point when this call is done we typically don't yet
 		 * know which interface is going to be used */
-		if (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW) {
+		if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) {
 			err = -EINVAL;
 			break;
 		}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2c1f59386a7b..31f2765ef851 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3764,11 +3764,12 @@ void tcp_parse_options(const struct sk_buff *skb,
 				    !estab && sysctl_tcp_window_scaling) {
 					__u8 snd_wscale = *(__u8 *)ptr;
 					opt_rx->wscale_ok = 1;
-					if (snd_wscale > 14) {
-						net_info_ratelimited("%s: Illegal window scaling value %d >14 received\n",
+					if (snd_wscale > TCP_MAX_WSCALE) {
+						net_info_ratelimited("%s: Illegal window scaling value %d > %u received\n",
 								     __func__,
-								     snd_wscale);
-						snd_wscale = 14;
+								     snd_wscale,
+								     TCP_MAX_WSCALE);
+						snd_wscale = TCP_MAX_WSCALE;
 					}
 					opt_rx->snd_wscale = snd_wscale;
 				}
@@ -6329,36 +6330,14 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		goto drop_and_free;
 
 	if (isn && tmp_opt.tstamp_ok)
-		af_ops->init_seq(skb, &tcp_rsk(req)->ts_off);
+		af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off);
 
 	if (!want_cookie && !isn) {
-		/* VJ's idea. We save last timestamp seen
-		 * from the destination in peer table, when entering
-		 * state TIME-WAIT, and check against it before
-		 * accepting new connection request.
-		 *
-		 * If "isn" is not zero, this request hit alive
-		 * timewait bucket, so that all the necessary checks
-		 * are made in the function processing timewait state.
-		 */
-		if (net->ipv4.tcp_death_row.sysctl_tw_recycle) {
-			bool strict;
-
-			dst = af_ops->route_req(sk, &fl, req, &strict);
-
-			if (dst && strict &&
-			    !tcp_peer_is_proven(req, dst, true,
-						tmp_opt.saw_tstamp)) {
-				NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
-				goto drop_and_release;
-			}
-		}
 		/* Kill the following clause, if you dislike this way. */
-		else if (!net->ipv4.sysctl_tcp_syncookies &&
-			 (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
-			  (net->ipv4.sysctl_max_syn_backlog >> 2)) &&
-			 !tcp_peer_is_proven(req, dst, false,
-					     tmp_opt.saw_tstamp)) {
+		if (!net->ipv4.sysctl_tcp_syncookies &&
+		    (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
+		     (net->ipv4.sysctl_max_syn_backlog >> 2)) &&
+		    !tcp_peer_is_proven(req, dst)) {
 			/* Without syncookies last quarter of
 			 * backlog is filled with destinations,
 			 * proven to be alive.
@@ -6371,10 +6350,10 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			goto drop_and_release;
 		}
 
-		isn = af_ops->init_seq(skb, &tcp_rsk(req)->ts_off);
+		isn = af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off);
 	}
 	if (!dst) {
-		dst = af_ops->route_req(sk, &fl, req, NULL);
+		dst = af_ops->route_req(sk, &fl, req);
 		if (!dst)
 			goto drop_and_free;
 	}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 575e19dcc017..20cbd2f07f28 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -94,12 +94,12 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 struct inet_hashinfo tcp_hashinfo;
 EXPORT_SYMBOL(tcp_hashinfo);
 
-static u32 tcp_v4_init_sequence(const struct sk_buff *skb, u32 *tsoff)
+static u32 tcp_v4_init_seq_and_tsoff(const struct sk_buff *skb, u32 *tsoff)
 {
-	return secure_tcp_sequence_number(ip_hdr(skb)->daddr,
-					  ip_hdr(skb)->saddr,
-					  tcp_hdr(skb)->dest,
-					  tcp_hdr(skb)->source, tsoff);
+	return secure_tcp_seq_and_tsoff(ip_hdr(skb)->daddr,
+					ip_hdr(skb)->saddr,
+					tcp_hdr(skb)->dest,
+					tcp_hdr(skb)->source, tsoff);
 }
 
 int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
@@ -198,10 +198,6 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 			tp->write_seq	   = 0;
 	}
 
-	if (tcp_death_row->sysctl_tw_recycle &&
-	    !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr)
-		tcp_fetch_timewait_stamp(sk, &rt->dst);
-
 	inet->inet_dport = usin->sin_port;
 	sk_daddr_set(sk, daddr);
 
@@ -236,11 +232,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	rt = NULL;
 
 	if (likely(!tp->repair)) {
-		seq = secure_tcp_sequence_number(inet->inet_saddr,
-						 inet->inet_daddr,
-						 inet->inet_sport,
-						 usin->sin_port,
-						 &tp->tsoffset);
+		seq = secure_tcp_seq_and_tsoff(inet->inet_saddr,
+					       inet->inet_daddr,
+					       inet->inet_sport,
+					       usin->sin_port,
+					       &tp->tsoffset);
 		if (!tp->write_seq)
 			tp->write_seq = seq;
 	}
@@ -1217,19 +1213,9 @@ static void tcp_v4_init_req(struct request_sock *req,
 
 static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
 					  struct flowi *fl,
-					  const struct request_sock *req,
-					  bool *strict)
+					  const struct request_sock *req)
 {
-	struct dst_entry *dst = inet_csk_route_req(sk, &fl->u.ip4, req);
-
-	if (strict) {
-		if (fl->u.ip4.daddr == inet_rsk(req)->ir_rmt_addr)
-			*strict = true;
-		else
-			*strict = false;
-	}
-
-	return dst;
+	return inet_csk_route_req(sk, &fl->u.ip4, req);
 }
 
 struct request_sock_ops tcp_request_sock_ops __read_mostly = {
@@ -1253,7 +1239,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
 	.cookie_init_seq =	cookie_v4_init_sequence,
 #endif
 	.route_req	=	tcp_v4_route_req,
-	.init_seq	=	tcp_v4_init_sequence,
+	.init_seq_tsoff	=	tcp_v4_init_seq_and_tsoff,
 	.send_synack	=	tcp_v4_send_synack,
 };
 
@@ -1423,8 +1409,6 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 		if (!nsk)
 			goto discard;
 		if (nsk != sk) {
-			sock_rps_save_rxhash(nsk, skb);
-			sk_mark_napi_id(nsk, skb);
 			if (tcp_child_process(sk, nsk, skb)) {
 				rsk = nsk;
 				goto reset;
@@ -2466,7 +2450,6 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_tw_reuse = 0;
 
 	cnt = tcp_hashinfo.ehash_mask + 1;
-	net->ipv4.tcp_death_row.sysctl_tw_recycle = 0;
 	net->ipv4.tcp_death_row.sysctl_max_tw_buckets = (cnt + 1) / 2;
 	net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo;
 
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 0f46e5fe31ad..9d0d4f39e42b 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -45,8 +45,6 @@ struct tcp_metrics_block {
 	struct inetpeer_addr		tcpm_saddr;
 	struct inetpeer_addr		tcpm_daddr;
 	unsigned long			tcpm_stamp;
-	u32				tcpm_ts;
-	u32				tcpm_ts_stamp;
 	u32				tcpm_lock;
 	u32				tcpm_vals[TCP_METRIC_MAX_KERNEL + 1];
 	struct tcp_fastopen_metrics	tcpm_fastopen;
@@ -123,8 +121,6 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm,
 	tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH);
 	tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND);
 	tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING);
-	tm->tcpm_ts = 0;
-	tm->tcpm_ts_stamp = 0;
 	if (fastopen_clear) {
 		tm->tcpm_fastopen.mss = 0;
 		tm->tcpm_fastopen.syn_loss = 0;
@@ -273,48 +269,6 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
 	return tm;
 }
 
-static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw)
-{
-	struct tcp_metrics_block *tm;
-	struct inetpeer_addr saddr, daddr;
-	unsigned int hash;
-	struct net *net;
-
-	if (tw->tw_family == AF_INET) {
-		inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr);
-		inetpeer_set_addr_v4(&daddr, tw->tw_daddr);
-		hash = ipv4_addr_hash(tw->tw_daddr);
-	}
-#if IS_ENABLED(CONFIG_IPV6)
-	else if (tw->tw_family == AF_INET6) {
-		if (ipv6_addr_v4mapped(&tw->tw_v6_daddr)) {
-			inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr);
-			inetpeer_set_addr_v4(&daddr, tw->tw_daddr);
-			hash = ipv4_addr_hash(tw->tw_daddr);
-		} else {
-			inetpeer_set_addr_v6(&saddr, &tw->tw_v6_rcv_saddr);
-			inetpeer_set_addr_v6(&daddr, &tw->tw_v6_daddr);
-			hash = ipv6_addr_hash(&tw->tw_v6_daddr);
-		}
-	}
-#endif
-	else
-		return NULL;
-
-	net = twsk_net(tw);
-	hash ^= net_hash_mix(net);
-	hash = hash_32(hash, tcp_metrics_hash_log);
-
-	for (tm = rcu_dereference(tcp_metrics_hash[hash].chain); tm;
-	     tm = rcu_dereference(tm->tcpm_next)) {
-		if (addr_same(&tm->tcpm_saddr, &saddr) &&
-		    addr_same(&tm->tcpm_daddr, &daddr) &&
-		    net_eq(tm_net(tm), net))
-			break;
-	}
-	return tm;
-}
-
 static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 						 struct dst_entry *dst,
 						 bool create)
@@ -573,8 +527,7 @@ reset:
 	tp->snd_cwnd_stamp = tcp_time_stamp;
 }
 
-bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst,
-			bool paws_check, bool timestamps)
+bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst)
 {
 	struct tcp_metrics_block *tm;
 	bool ret;
@@ -584,94 +537,10 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst,
 
 	rcu_read_lock();
 	tm = __tcp_get_metrics_req(req, dst);
-	if (paws_check) {
-		if (tm &&
-		    (u32)get_seconds() - tm->tcpm_ts_stamp < TCP_PAWS_MSL &&
-		    ((s32)(tm->tcpm_ts - req->ts_recent) > TCP_PAWS_WINDOW ||
-		     !timestamps))
-			ret = false;
-		else
-			ret = true;
-	} else {
-		if (tm && tcp_metric_get(tm, TCP_METRIC_RTT) && tm->tcpm_ts_stamp)
-			ret = true;
-		else
-			ret = false;
-	}
-	rcu_read_unlock();
-
-	return ret;
-}
-
-void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst)
-{
-	struct tcp_metrics_block *tm;
-
-	rcu_read_lock();
-	tm = tcp_get_metrics(sk, dst, true);
-	if (tm) {
-		struct tcp_sock *tp = tcp_sk(sk);
-
-		if ((u32)get_seconds() - tm->tcpm_ts_stamp <= TCP_PAWS_MSL) {
-			tp->rx_opt.ts_recent_stamp = tm->tcpm_ts_stamp;
-			tp->rx_opt.ts_recent = tm->tcpm_ts;
-		}
-	}
-	rcu_read_unlock();
-}
-EXPORT_SYMBOL_GPL(tcp_fetch_timewait_stamp);
-
-/* VJ's idea. Save last timestamp seen from this destination and hold
- * it at least for normal timewait interval to use for duplicate
- * segment detection in subsequent connections, before they enter
- * synchronized state.
- */
-bool tcp_remember_stamp(struct sock *sk)
-{
-	struct dst_entry *dst = __sk_dst_get(sk);
-	bool ret = false;
-
-	if (dst) {
-		struct tcp_metrics_block *tm;
-
-		rcu_read_lock();
-		tm = tcp_get_metrics(sk, dst, true);
-		if (tm) {
-			struct tcp_sock *tp = tcp_sk(sk);
-
-			if ((s32)(tm->tcpm_ts - tp->rx_opt.ts_recent) <= 0 ||
-			    ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL &&
-			     tm->tcpm_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) {
-				tm->tcpm_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp;
-				tm->tcpm_ts = tp->rx_opt.ts_recent;
-			}
-			ret = true;
-		}
-		rcu_read_unlock();
-	}
-	return ret;
-}
-
-bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw)
-{
-	struct tcp_metrics_block *tm;
-	bool ret = false;
-
-	rcu_read_lock();
-	tm = __tcp_get_metrics_tw(tw);
-	if (tm) {
-		const struct tcp_timewait_sock *tcptw;
-		struct sock *sk = (struct sock *) tw;
-
-		tcptw = tcp_twsk(sk);
-		if ((s32)(tm->tcpm_ts - tcptw->tw_ts_recent) <= 0 ||
-		    ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL &&
-		     tm->tcpm_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) {
-			tm->tcpm_ts_stamp = (u32)tcptw->tw_ts_recent_stamp;
-			tm->tcpm_ts	   = tcptw->tw_ts_recent;
-		}
+	if (tm && tcp_metric_get(tm, TCP_METRIC_RTT))
 		ret = true;
-	}
+	else
+		ret = false;
 	rcu_read_unlock();
 
 	return ret;
@@ -791,14 +660,6 @@ static int tcp_metrics_fill_info(struct sk_buff *msg,
 			  jiffies - tm->tcpm_stamp,
 			  TCP_METRICS_ATTR_PAD) < 0)
 		goto nla_put_failure;
-	if (tm->tcpm_ts_stamp) {
-		if (nla_put_s32(msg, TCP_METRICS_ATTR_TW_TS_STAMP,
-				(s32) (get_seconds() - tm->tcpm_ts_stamp)) < 0)
-			goto nla_put_failure;
-		if (nla_put_u32(msg, TCP_METRICS_ATTR_TW_TSVAL,
-				tm->tcpm_ts) < 0)
-			goto nla_put_failure;
-	}
 
 	{
 		int n = 0;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 65c0f3d13eca..8f6373b0cd77 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -26,6 +26,7 @@
 #include <net/tcp.h>
 #include <net/inet_common.h>
 #include <net/xfrm.h>
+#include <net/busy_poll.h>
 
 int sysctl_tcp_abort_on_overflow __read_mostly;
 
@@ -94,7 +95,6 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 	struct tcp_options_received tmp_opt;
 	struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
 	bool paws_reject = false;
-	struct inet_timewait_death_row *tcp_death_row = &sock_net((struct sock*)tw)->ipv4.tcp_death_row;
 
 	tmp_opt.saw_tstamp = 0;
 	if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
@@ -149,12 +149,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;
 		}
 
-		if (tcp_death_row->sysctl_tw_recycle &&
-		    tcptw->tw_ts_recent_stamp &&
-		    tcp_tw_remember_stamp(tw))
-			inet_twsk_reschedule(tw, tw->tw_timeout);
-		else
-			inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
+		inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
 		return TCP_TW_ACK;
 	}
 
@@ -259,12 +254,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_timewait_sock *tw;
-	bool recycle_ok = false;
 	struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
 
-	if (tcp_death_row->sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp)
-		recycle_ok = tcp_remember_stamp(sk);
-
 	tw = inet_twsk_alloc(sk, tcp_death_row, state);
 
 	if (tw) {
@@ -317,13 +308,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		if (timeo < rto)
 			timeo = rto;
 
-		if (recycle_ok) {
-			tw->tw_timeout = rto;
-		} else {
-			tw->tw_timeout = TCP_TIMEWAIT_LEN;
-			if (state == TCP_TIME_WAIT)
-				timeo = TCP_TIMEWAIT_LEN;
-		}
+		tw->tw_timeout = TCP_TIMEWAIT_LEN;
+		if (state == TCP_TIME_WAIT)
+			timeo = TCP_TIMEWAIT_LEN;
 
 		inet_twsk_schedule(tw, timeo);
 		/* Linkage updates. */
@@ -813,6 +800,9 @@ int tcp_child_process(struct sock *parent, struct sock *child,
 	int ret = 0;
 	int state = child->sk_state;
 
+	/* record NAPI ID of child */
+	sk_mark_napi_id(child, skb);
+
 	tcp_segs_in(tcp_sk(child), skb);
 	if (!sock_owned_by_user(child)) {
 		ret = tcp_rcv_state_process(child, skb);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 22548b5f05cb..0e807a83c1bc 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -212,12 +212,12 @@ void tcp_select_initial_window(int __space, __u32 mss,
 
 	/* If no clamp set the clamp to the max possible scaled window */
 	if (*window_clamp == 0)
-		(*window_clamp) = (65535 << 14);
+		(*window_clamp) = (U16_MAX << TCP_MAX_WSCALE);
 	space = min(*window_clamp, space);
 
 	/* Quantize space offering to a multiple of mss if possible. */
 	if (space > mss)
-		space = (space / mss) * mss;
+		space = rounddown(space, mss);
 
 	/* NOTE: offering an initial window larger than 32767
 	 * will break some buggy TCP stacks. If the admin tells us
@@ -234,13 +234,11 @@ void tcp_select_initial_window(int __space, __u32 mss,
 
 	(*rcv_wscale) = 0;
 	if (wscale_ok) {
-		/* Set window scaling on max possible window
-		 * See RFC1323 for an explanation of the limit to 14
-		 */
+		/* Set window scaling on max possible window */
 		space = max_t(u32, space, sysctl_tcp_rmem[2]);
 		space = max_t(u32, space, sysctl_rmem_max);
 		space = min_t(u32, space, *window_clamp);
-		while (space > 65535 && (*rcv_wscale) < 14) {
+		while (space > U16_MAX && (*rcv_wscale) < TCP_MAX_WSCALE) {
 			space >>= 1;
 			(*rcv_wscale)++;
 		}
@@ -253,7 +251,7 @@ void tcp_select_initial_window(int __space, __u32 mss,
 	}
 
 	/* Set the clamp no higher than max representable value */
-	(*window_clamp) = min(65535U << (*rcv_wscale), *window_clamp);
+	(*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp);
 }
 EXPORT_SYMBOL(tcp_select_initial_window);
 
@@ -2561,7 +2559,6 @@ u32 __tcp_select_window(struct sock *sk)
 	/* Don't do rounding if we are using window scaling, since the
 	 * scaled window will not line up with the MSS boundary anyway.
 	 */
-	window = tp->rcv_wnd;
 	if (tp->rx_opt.rcv_wscale) {
 		window = free_space;
 
@@ -2569,10 +2566,9 @@ u32 __tcp_select_window(struct sock *sk)
 		 * Import case: prevent zero window announcement if
 		 * 1<<rcv_wscale > mss.
 		 */
-		if (((window >> tp->rx_opt.rcv_wscale) << tp->rx_opt.rcv_wscale) != window)
-			window = (((window >> tp->rx_opt.rcv_wscale) + 1)
-				  << tp->rx_opt.rcv_wscale);
+		window = ALIGN(window, (1 << tp->rx_opt.rcv_wscale));
 	} else {
+		window = tp->rcv_wnd;
 		/* Get the largest window that is a nice multiple of mss.
 		 * Window clamp already applied above.
 		 * If our current window offering is within 1 mss of the
@@ -2582,7 +2578,7 @@ u32 __tcp_select_window(struct sock *sk)
 		 * is too small.
 		 */
 		if (window <= free_space - mss || window > free_space)
-			window = (free_space / mss) * mss;
+			window = rounddown(free_space, mss);
 		else if (mss == full_space &&
 			 free_space > window + (full_space >> 1))
 			window = free_space;
diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c
index fed66dc0e0f5..9775453b8d17 100644
--- a/net/ipv4/tcp_westwood.c
+++ b/net/ipv4/tcp_westwood.c
@@ -265,8 +265,8 @@ static size_t tcp_westwood_info(struct sock *sk, u32 ext, int *attr,
 	if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
 		info->vegas.tcpv_enabled = 1;
 		info->vegas.tcpv_rttcnt	= 0;
-		info->vegas.tcpv_rtt	= jiffies_to_usecs(ca->rtt),
-		info->vegas.tcpv_minrtt	= jiffies_to_usecs(ca->rtt_min),
+		info->vegas.tcpv_rtt	= jiffies_to_usecs(ca->rtt);
+		info->vegas.tcpv_minrtt	= jiffies_to_usecs(ca->rtt_min);
 
 		*attr = INET_DIAG_VEGASINFO;
 		return sizeof(struct tcpvegas_info);
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index e2afe677a9d9..48c452959d2c 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -307,6 +307,7 @@ config IPV6_SEG6_LWTUNNEL
 	bool "IPv6: Segment Routing Header encapsulation support"
 	depends on IPV6
 	select LWTUNNEL
+	select DST_CACHE
 	---help---
 	  Support for encapsulation of packets within an outer IPv6
 	  header and a Segment Routing Header using the lightweight
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 363172527e43..67ec87ea5fb6 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -224,6 +224,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.accept_ra_rtr_pref	= 1,
 	.rtr_probe_interval	= 60 * HZ,
 #ifdef CONFIG_IPV6_ROUTE_INFO
+	.accept_ra_rt_info_min_plen = 0,
 	.accept_ra_rt_info_max_plen = 0,
 #endif
 #endif
@@ -245,6 +246,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 #endif
 	.enhanced_dad           = 1,
 	.addr_gen_mode		= IN6_ADDR_GEN_MODE_EUI64,
+	.disable_policy		= 0,
 };
 
 static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -276,6 +278,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.accept_ra_rtr_pref	= 1,
 	.rtr_probe_interval	= 60 * HZ,
 #ifdef CONFIG_IPV6_ROUTE_INFO
+	.accept_ra_rt_info_min_plen = 0,
 	.accept_ra_rt_info_max_plen = 0,
 #endif
 #endif
@@ -297,6 +300,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 #endif
 	.enhanced_dad           = 1,
 	.addr_gen_mode		= IN6_ADDR_GEN_MODE_EUI64,
+	.disable_policy		= 0,
 };
 
 /* Check if a valid qdisc is available */
@@ -545,6 +549,9 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 	if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0)
 		goto nla_put_failure;
 
+	if (!devconf)
+		goto out;
+
 	if ((all || type == NETCONFA_FORWARDING) &&
 	    nla_put_s32(skb, NETCONFA_FORWARDING, devconf->forwarding) < 0)
 		goto nla_put_failure;
@@ -563,6 +570,7 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 			devconf->ignore_routes_with_linkdown) < 0)
 		goto nla_put_failure;
 
+out:
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -571,8 +579,8 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
-				  struct ipv6_devconf *devconf)
+void inet6_netconf_notify_devconf(struct net *net, int event, int type,
+				  int ifindex, struct ipv6_devconf *devconf)
 {
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
@@ -582,7 +590,7 @@ void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
 		goto errout;
 
 	err = inet6_netconf_fill_devconf(skb, ifindex, devconf, 0, 0,
-					 RTM_NEWNETCONF, 0, type);
+					 event, 0, type);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in inet6_netconf_msgsize_devconf() */
 		WARN_ON(err == -EMSGSIZE);
@@ -765,7 +773,8 @@ static void dev_forward_change(struct inet6_dev *idev)
 		else
 			addrconf_leave_anycast(ifa);
 	}
-	inet6_netconf_notify_devconf(dev_net(dev), NETCONFA_FORWARDING,
+	inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
+				     NETCONFA_FORWARDING,
 				     dev->ifindex, &idev->cnf);
 }
 
@@ -800,7 +809,8 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf)
 
 	if (p == &net->ipv6.devconf_dflt->forwarding) {
 		if ((!newf) ^ (!old))
-			inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						     NETCONFA_FORWARDING,
 						     NETCONFA_IFINDEX_DEFAULT,
 						     net->ipv6.devconf_dflt);
 		rtnl_unlock();
@@ -812,13 +822,15 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf)
 
 		net->ipv6.devconf_dflt->forwarding = newf;
 		if ((!newf) ^ (!old_dflt))
-			inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						     NETCONFA_FORWARDING,
 						     NETCONFA_IFINDEX_DEFAULT,
 						     net->ipv6.devconf_dflt);
 
 		addrconf_forward_change(net, newf);
 		if ((!newf) ^ (!old))
-			inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						     NETCONFA_FORWARDING,
 						     NETCONFA_IFINDEX_ALL,
 						     net->ipv6.devconf_all);
 	} else if ((!newf) ^ (!old))
@@ -843,6 +855,7 @@ static void addrconf_linkdown_change(struct net *net, __s32 newf)
 			idev->cnf.ignore_routes_with_linkdown = newf;
 			if (changed)
 				inet6_netconf_notify_devconf(dev_net(dev),
+							     RTM_NEWNETCONF,
 							     NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 							     dev->ifindex,
 							     &idev->cnf);
@@ -865,6 +878,7 @@ static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf)
 	if (p == &net->ipv6.devconf_dflt->ignore_routes_with_linkdown) {
 		if ((!newf) ^ (!old))
 			inet6_netconf_notify_devconf(net,
+						     RTM_NEWNETCONF,
 						     NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 						     NETCONFA_IFINDEX_DEFAULT,
 						     net->ipv6.devconf_dflt);
@@ -877,6 +891,7 @@ static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf)
 		addrconf_linkdown_change(net, newf);
 		if ((!newf) ^ (!old))
 			inet6_netconf_notify_devconf(net,
+						     RTM_NEWNETCONF,
 						     NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 						     NETCONFA_IFINDEX_ALL,
 						     net->ipv6.devconf_all);
@@ -944,6 +959,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 	      const struct in6_addr *peer_addr, int pfxlen,
 	      int scope, u32 flags, u32 valid_lft, u32 prefered_lft)
 {
+	struct net *net = dev_net(idev->dev);
 	struct inet6_ifaddr *ifa = NULL;
 	struct rt6_info *rt;
 	unsigned int hash;
@@ -990,6 +1006,10 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 		goto out;
 	}
 
+	if (net->ipv6.devconf_all->disable_policy ||
+	    idev->cnf.disable_policy)
+		rt->dst.flags |= DST_NOPOLICY;
+
 	neigh_parms_data_state_setall(idev->nd_parms);
 
 	ifa->addr = *addr;
@@ -4972,6 +4992,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_RTR_PROBE_INTERVAL] =
 		jiffies_to_msecs(cnf->rtr_probe_interval);
 #ifdef CONFIG_IPV6_ROUTE_INFO
+	array[DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN] = cnf->accept_ra_rt_info_min_plen;
 	array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen;
 #endif
 #endif
@@ -5003,6 +5024,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 #endif
 	array[DEVCONF_ENHANCED_DAD] = cnf->enhanced_dad;
 	array[DEVCONF_ADDR_GEN_MODE] = cnf->addr_gen_mode;
+	array[DEVCONF_DISABLE_POLICY] = cnf->disable_policy;
 }
 
 static inline size_t inet6_ifla6_size(void)
@@ -5664,17 +5686,20 @@ int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write,
 			return restart_syscall();
 
 		if (valp == &net->ipv6.devconf_dflt->proxy_ndp)
-			inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						     NETCONFA_PROXY_NEIGH,
 						     NETCONFA_IFINDEX_DEFAULT,
 						     net->ipv6.devconf_dflt);
 		else if (valp == &net->ipv6.devconf_all->proxy_ndp)
-			inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						     NETCONFA_PROXY_NEIGH,
 						     NETCONFA_IFINDEX_ALL,
 						     net->ipv6.devconf_all);
 		else {
 			struct inet6_dev *idev = ctl->extra1;
 
-			inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						     NETCONFA_PROXY_NEIGH,
 						     idev->dev->ifindex,
 						     &idev->cnf);
 		}
@@ -5827,6 +5852,105 @@ int addrconf_sysctl_ignore_routes_with_linkdown(struct ctl_table *ctl,
 	return ret;
 }
 
+static
+void addrconf_set_nopolicy(struct rt6_info *rt, int action)
+{
+	if (rt) {
+		if (action)
+			rt->dst.flags |= DST_NOPOLICY;
+		else
+			rt->dst.flags &= ~DST_NOPOLICY;
+	}
+}
+
+static
+void addrconf_disable_policy_idev(struct inet6_dev *idev, int val)
+{
+	struct inet6_ifaddr *ifa;
+
+	read_lock_bh(&idev->lock);
+	list_for_each_entry(ifa, &idev->addr_list, if_list) {
+		spin_lock(&ifa->lock);
+		if (ifa->rt) {
+			struct rt6_info *rt = ifa->rt;
+			struct fib6_table *table = rt->rt6i_table;
+			int cpu;
+
+			read_lock(&table->tb6_lock);
+			addrconf_set_nopolicy(ifa->rt, val);
+			if (rt->rt6i_pcpu) {
+				for_each_possible_cpu(cpu) {
+					struct rt6_info **rtp;
+
+					rtp = per_cpu_ptr(rt->rt6i_pcpu, cpu);
+					addrconf_set_nopolicy(*rtp, val);
+				}
+			}
+			read_unlock(&table->tb6_lock);
+		}
+		spin_unlock(&ifa->lock);
+	}
+	read_unlock_bh(&idev->lock);
+}
+
+static
+int addrconf_disable_policy(struct ctl_table *ctl, int *valp, int val)
+{
+	struct inet6_dev *idev;
+	struct net *net;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	*valp = val;
+
+	net = (struct net *)ctl->extra2;
+	if (valp == &net->ipv6.devconf_dflt->disable_policy) {
+		rtnl_unlock();
+		return 0;
+	}
+
+	if (valp == &net->ipv6.devconf_all->disable_policy)  {
+		struct net_device *dev;
+
+		for_each_netdev(net, dev) {
+			idev = __in6_dev_get(dev);
+			if (idev)
+				addrconf_disable_policy_idev(idev, val);
+		}
+	} else {
+		idev = (struct inet6_dev *)ctl->extra1;
+		addrconf_disable_policy_idev(idev, val);
+	}
+
+	rtnl_unlock();
+	return 0;
+}
+
+static
+int addrconf_sysctl_disable_policy(struct ctl_table *ctl, int write,
+				   void __user *buffer, size_t *lenp,
+				   loff_t *ppos)
+{
+	int *valp = ctl->data;
+	int val = *valp;
+	loff_t pos = *ppos;
+	struct ctl_table lctl;
+	int ret;
+
+	lctl = *ctl;
+	lctl.data = &val;
+	ret = proc_dointvec(&lctl, write, buffer, lenp, ppos);
+
+	if (write && (*valp != val))
+		ret = addrconf_disable_policy(ctl, valp, val);
+
+	if (ret)
+		*ppos = pos;
+
+	return ret;
+}
+
 static int minus_one = -1;
 static const int one = 1;
 static const int two_five_five = 255;
@@ -6015,6 +6139,13 @@ static const struct ctl_table addrconf_sysctl[] = {
 	},
 #ifdef CONFIG_IPV6_ROUTE_INFO
 	{
+		.procname	= "accept_ra_rt_info_min_plen",
+		.data		= &ipv6_devconf.accept_ra_rt_info_min_plen,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
 		.procname	= "accept_ra_rt_info_max_plen",
 		.data		= &ipv6_devconf.accept_ra_rt_info_max_plen,
 		.maxlen		= sizeof(int),
@@ -6185,6 +6316,13 @@ static const struct ctl_table addrconf_sysctl[] = {
 		.proc_handler	= addrconf_sysctl_addr_gen_mode,
 	},
 	{
+		.procname       = "disable_policy",
+		.data           = &ipv6_devconf.disable_policy,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = addrconf_sysctl_disable_policy,
+	},
+	{
 		/* sentinel */
 	}
 };
@@ -6224,7 +6362,8 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name,
 		ifindex = NETCONFA_IFINDEX_DEFAULT;
 	else
 		ifindex = idev->dev->ifindex;
-	inet6_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p);
+	inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL,
+				     ifindex, p);
 	return 0;
 
 free:
@@ -6233,7 +6372,8 @@ out:
 	return -ENOBUFS;
 }
 
-static void __addrconf_sysctl_unregister(struct ipv6_devconf *p)
+static void __addrconf_sysctl_unregister(struct net *net,
+					 struct ipv6_devconf *p, int ifindex)
 {
 	struct ctl_table *table;
 
@@ -6244,6 +6384,8 @@ static void __addrconf_sysctl_unregister(struct ipv6_devconf *p)
 	unregister_net_sysctl_table(p->sysctl_header);
 	p->sysctl_header = NULL;
 	kfree(table);
+
+	inet6_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL);
 }
 
 static int addrconf_sysctl_register(struct inet6_dev *idev)
@@ -6267,7 +6409,8 @@ static int addrconf_sysctl_register(struct inet6_dev *idev)
 
 static void addrconf_sysctl_unregister(struct inet6_dev *idev)
 {
-	__addrconf_sysctl_unregister(&idev->cnf);
+	__addrconf_sysctl_unregister(dev_net(idev->dev), &idev->cnf,
+				     idev->dev->ifindex);
 	neigh_sysctl_unregister(idev->nd_parms);
 }
 
@@ -6310,7 +6453,7 @@ static int __net_init addrconf_init_net(struct net *net)
 
 #ifdef CONFIG_SYSCTL
 err_reg_dflt:
-	__addrconf_sysctl_unregister(all);
+	__addrconf_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL);
 err_reg_all:
 	kfree(dflt);
 #endif
@@ -6323,8 +6466,10 @@ err_alloc_all:
 static void __net_exit addrconf_exit_net(struct net *net)
 {
 #ifdef CONFIG_SYSCTL
-	__addrconf_sysctl_unregister(net->ipv6.devconf_dflt);
-	__addrconf_sysctl_unregister(net->ipv6.devconf_all);
+	__addrconf_sysctl_unregister(net, net->ipv6.devconf_dflt,
+				     NETCONFA_IFINDEX_DEFAULT);
+	__addrconf_sysctl_unregister(net, net->ipv6.devconf_all,
+				     NETCONFA_IFINDEX_ALL);
 #endif
 	kfree(net->ipv6.devconf_dflt);
 	kfree(net->ipv6.devconf_all);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index a9a9553ee63d..1635d218735e 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1005,6 +1005,10 @@ static int __init inet6_init(void)
 	if (err)
 		goto seg6_fail;
 
+	err = igmp6_late_init();
+	if (err)
+		goto igmp6_late_err;
+
 #ifdef CONFIG_SYSCTL
 	err = ipv6_sysctl_register();
 	if (err)
@@ -1015,8 +1019,10 @@ out:
 
 #ifdef CONFIG_SYSCTL
 sysctl_fail:
-	seg6_exit();
+	igmp6_late_cleanup();
 #endif
+igmp6_late_err:
+	seg6_exit();
 seg6_fail:
 	calipso_exit();
 calipso_fail:
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index aacfb4bce153..b04539dd4629 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -49,6 +49,8 @@
 
 int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	void (*edemux)(struct sk_buff *skb);
+
 	/* if ingress device is enslaved to an L3 master device pass the
 	 * skb to its handler for processing
 	 */
@@ -60,8 +62,8 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 		const struct inet6_protocol *ipprot;
 
 		ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
-		if (ipprot && ipprot->early_demux)
-			ipprot->early_demux(skb);
+		if (ipprot && (edemux = READ_ONCE(ipprot->early_demux)))
+			edemux(skb);
 	}
 	if (!skb_valid_dst(skb))
 		ip6_route_input(skb);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 6ba6c900ebcf..fb4546e80c82 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -815,7 +815,7 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head)
 	in6_dev = __in6_dev_get(dev);
 	if (in6_dev) {
 		in6_dev->cnf.mc_forwarding--;
-		inet6_netconf_notify_devconf(dev_net(dev),
+		inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
 					     NETCONFA_MC_FORWARDING,
 					     dev->ifindex, &in6_dev->cnf);
 	}
@@ -974,7 +974,7 @@ static int mif6_add(struct net *net, struct mr6_table *mrt,
 	in6_dev = __in6_dev_get(dev);
 	if (in6_dev) {
 		in6_dev->cnf.mc_forwarding++;
-		inet6_netconf_notify_devconf(dev_net(dev),
+		inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
 					     NETCONFA_MC_FORWARDING,
 					     dev->ifindex, &in6_dev->cnf);
 	}
@@ -1599,7 +1599,8 @@ static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk)
 	write_unlock_bh(&mrt_lock);
 
 	if (!err)
-		inet6_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+		inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+					     NETCONFA_MC_FORWARDING,
 					     NETCONFA_IFINDEX_ALL,
 					     net->ipv6.devconf_all);
 	rtnl_unlock();
@@ -1620,7 +1621,7 @@ int ip6mr_sk_done(struct sock *sk)
 			mrt->mroute6_sk = NULL;
 			net->ipv6.devconf_all->mc_forwarding--;
 			write_unlock_bh(&mrt_lock);
-			inet6_netconf_notify_devconf(net,
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
 						     NETCONFA_MC_FORWARDING,
 						     NETCONFA_IFINDEX_ALL,
 						     net->ipv6.devconf_all);
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 1bdc703cb966..07403fa164e1 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2463,7 +2463,6 @@ static void mld_ifc_event(struct inet6_dev *idev)
 	mld_ifc_start_timer(idev, 1);
 }
 
-
 static void igmp6_timer_handler(unsigned long data)
 {
 	struct ifmcaddr6 *ma = (struct ifmcaddr6 *) data;
@@ -2599,6 +2598,44 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev)
 	write_unlock_bh(&idev->lock);
 }
 
+static void ipv6_mc_rejoin_groups(struct inet6_dev *idev)
+{
+	struct ifmcaddr6 *pmc;
+
+	ASSERT_RTNL();
+
+	if (mld_in_v1_mode(idev)) {
+		read_lock_bh(&idev->lock);
+		for (pmc = idev->mc_list; pmc; pmc = pmc->next)
+			igmp6_join_group(pmc);
+		read_unlock_bh(&idev->lock);
+	} else
+		mld_send_report(idev, NULL);
+}
+
+static int ipv6_mc_netdev_event(struct notifier_block *this,
+				unsigned long event,
+				void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct inet6_dev *idev = __in6_dev_get(dev);
+
+	switch (event) {
+	case NETDEV_RESEND_IGMP:
+		if (idev)
+			ipv6_mc_rejoin_groups(idev);
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block igmp6_netdev_notifier = {
+	.notifier_call = ipv6_mc_netdev_event,
+};
+
 #ifdef CONFIG_PROC_FS
 struct igmp6_mc_iter_state {
 	struct seq_net_private p;
@@ -2970,7 +3007,17 @@ int __init igmp6_init(void)
 	return register_pernet_subsys(&igmp6_net_ops);
 }
 
+int __init igmp6_late_init(void)
+{
+	return register_netdevice_notifier(&igmp6_netdev_notifier);
+}
+
 void igmp6_cleanup(void)
 {
 	unregister_pernet_subsys(&igmp6_net_ops);
 }
+
+void igmp6_late_cleanup(void)
+{
+	unregister_netdevice_notifier(&igmp6_netdev_notifier);
+}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 7ebac630d3c6..b5812b3f7539 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -732,7 +732,7 @@ void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
 		  const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type,
 		  struct ndisc_options *ndopts)
 {
-	neigh_update(neigh, lladdr, new, flags);
+	neigh_update(neigh, lladdr, new, flags, 0);
 	/* report ndisc ops about neighbour update */
 	ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts);
 }
@@ -1418,6 +1418,8 @@ skip_linkparms:
 			if (ri->prefix_len == 0 &&
 			    !in6_dev->cnf.accept_ra_defrtr)
 				continue;
+			if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen)
+				continue;
 			if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen)
 				continue;
 			rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3,
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index 765facf03d45..e8d88d82636b 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -159,7 +159,7 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
 
 	if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
 	    nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
-		nft_fib_store_result(dest, priv->result, pkt,
+		nft_fib_store_result(dest, priv, pkt,
 				     nft_in(pkt)->ifindex);
 		return;
 	}
diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c
index e3770abe688a..b5d54d4f995c 100644
--- a/net/ipv6/protocol.c
+++ b/net/ipv6/protocol.c
@@ -26,7 +26,7 @@
 #include <net/protocol.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
-const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly;
+struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly;
 EXPORT_SYMBOL(inet6_protos);
 
 int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol)
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 85582257d3af..a644aaecdfd3 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -26,17 +26,13 @@
 #include <linux/seg6_iptunnel.h>
 #include <net/addrconf.h>
 #include <net/ip6_route.h>
-#ifdef CONFIG_DST_CACHE
 #include <net/dst_cache.h>
-#endif
 #ifdef CONFIG_IPV6_SEG6_HMAC
 #include <net/seg6_hmac.h>
 #endif
 
 struct seg6_lwt {
-#ifdef CONFIG_DST_CACHE
 	struct dst_cache cache;
-#endif
 	struct seg6_iptunnel_encap tuninfo[0];
 };
 
@@ -105,7 +101,7 @@ static int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
 	hdrlen = (osrh->hdrlen + 1) << 3;
 	tot_len = hdrlen + sizeof(*hdr);
 
-	err = pskb_expand_head(skb, tot_len, 0, GFP_ATOMIC);
+	err = skb_cow_head(skb, tot_len);
 	if (unlikely(err))
 		return err;
 
@@ -156,7 +152,7 @@ static int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
 
 	hdrlen = (osrh->hdrlen + 1) << 3;
 
-	err = pskb_expand_head(skb, hdrlen, 0, GFP_ATOMIC);
+	err = skb_cow_head(skb, hdrlen);
 	if (unlikely(err))
 		return err;
 
@@ -237,6 +233,9 @@ static int seg6_do_srh(struct sk_buff *skb)
 
 static int seg6_input(struct sk_buff *skb)
 {
+	struct dst_entry *orig_dst = skb_dst(skb);
+	struct dst_entry *dst = NULL;
+	struct seg6_lwt *slwt;
 	int err;
 
 	err = seg6_do_srh(skb);
@@ -245,8 +244,26 @@ static int seg6_input(struct sk_buff *skb)
 		return err;
 	}
 
+	slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
+
+	preempt_disable();
+	dst = dst_cache_get(&slwt->cache);
+	preempt_enable();
+
 	skb_dst_drop(skb);
-	ip6_route_input(skb);
+
+	if (!dst) {
+		ip6_route_input(skb);
+		dst = skb_dst(skb);
+		if (!dst->error) {
+			preempt_disable();
+			dst_cache_set_ip6(&slwt->cache, dst,
+					  &ipv6_hdr(skb)->saddr);
+			preempt_enable();
+		}
+	} else {
+		skb_dst_set(skb, dst);
+	}
 
 	return dst_input(skb);
 }
@@ -264,11 +281,9 @@ static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 
 	slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
 
-#ifdef CONFIG_DST_CACHE
 	preempt_disable();
 	dst = dst_cache_get(&slwt->cache);
 	preempt_enable();
-#endif
 
 	if (unlikely(!dst)) {
 		struct ipv6hdr *hdr = ipv6_hdr(skb);
@@ -287,11 +302,9 @@ static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 			goto drop;
 		}
 
-#ifdef CONFIG_DST_CACHE
 		preempt_disable();
 		dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
 		preempt_enable();
-#endif
 	}
 
 	skb_dst_drop(skb);
@@ -355,13 +368,11 @@ static int seg6_build_state(struct nlattr *nla,
 
 	slwt = seg6_lwt_lwtunnel(newts);
 
-#ifdef CONFIG_DST_CACHE
 	err = dst_cache_init(&slwt->cache, GFP_KERNEL);
 	if (err) {
 		kfree(newts);
 		return err;
 	}
-#endif
 
 	memcpy(&slwt->tuninfo, tuninfo, tuninfo_len);
 
@@ -375,12 +386,10 @@ static int seg6_build_state(struct nlattr *nla,
 	return 0;
 }
 
-#ifdef CONFIG_DST_CACHE
 static void seg6_destroy_state(struct lwtunnel_state *lwt)
 {
 	dst_cache_destroy(&seg6_lwt_lwtunnel(lwt)->cache);
 }
-#endif
 
 static int seg6_fill_encap_info(struct sk_buff *skb,
 				struct lwtunnel_state *lwtstate)
@@ -414,9 +423,7 @@ static int seg6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
 
 static const struct lwtunnel_encap_ops seg6_iptun_ops = {
 	.build_state = seg6_build_state,
-#ifdef CONFIG_DST_CACHE
 	.destroy_state = seg6_destroy_state,
-#endif
 	.output = seg6_output,
 	.input = seg6_input,
 	.fill_encap = seg6_fill_encap_info,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 49fa2e8c3fa9..8e42e8f54b70 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -101,12 +101,12 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 	}
 }
 
-static u32 tcp_v6_init_sequence(const struct sk_buff *skb, u32 *tsoff)
+static u32 tcp_v6_init_seq_and_tsoff(const struct sk_buff *skb, u32 *tsoff)
 {
-	return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32,
-					    ipv6_hdr(skb)->saddr.s6_addr32,
-					    tcp_hdr(skb)->dest,
-					    tcp_hdr(skb)->source, tsoff);
+	return secure_tcpv6_seq_and_tsoff(ipv6_hdr(skb)->daddr.s6_addr32,
+					  ipv6_hdr(skb)->saddr.s6_addr32,
+					  tcp_hdr(skb)->dest,
+					  tcp_hdr(skb)->source, tsoff);
 }
 
 static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
@@ -265,11 +265,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	sk->sk_gso_type = SKB_GSO_TCPV6;
 	ip6_dst_store(sk, dst, NULL, NULL);
 
-	if (tcp_death_row->sysctl_tw_recycle &&
-	    !tp->rx_opt.ts_recent_stamp &&
-	    ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr))
-		tcp_fetch_timewait_stamp(sk, dst);
-
 	icsk->icsk_ext_hdr_len = 0;
 	if (opt)
 		icsk->icsk_ext_hdr_len = opt->opt_flen +
@@ -287,11 +282,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	sk_set_txhash(sk);
 
 	if (likely(!tp->repair)) {
-		seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
-						   sk->sk_v6_daddr.s6_addr32,
-						   inet->inet_sport,
-						   inet->inet_dport,
-						   &tp->tsoffset);
+		seq = secure_tcpv6_seq_and_tsoff(np->saddr.s6_addr32,
+						 sk->sk_v6_daddr.s6_addr32,
+						 inet->inet_sport,
+						 inet->inet_dport,
+						 &tp->tsoffset);
 		if (!tp->write_seq)
 			tp->write_seq = seq;
 	}
@@ -727,11 +722,8 @@ static void tcp_v6_init_req(struct request_sock *req,
 
 static struct dst_entry *tcp_v6_route_req(const struct sock *sk,
 					  struct flowi *fl,
-					  const struct request_sock *req,
-					  bool *strict)
+					  const struct request_sock *req)
 {
-	if (strict)
-		*strict = true;
 	return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP);
 }
 
@@ -757,7 +749,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 	.cookie_init_seq =	cookie_v6_init_sequence,
 #endif
 	.route_req	=	tcp_v6_route_req,
-	.init_seq	=	tcp_v6_init_sequence,
+	.init_seq_tsoff	=	tcp_v6_init_seq_and_tsoff,
 	.send_synack	=	tcp_v6_send_synack,
 };
 
@@ -1301,8 +1293,6 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 			goto discard;
 
 		if (nsk != sk) {
-			sock_rps_save_rxhash(nsk, skb);
-			sk_mark_napi_id(nsk, skb);
 			if (tcp_child_process(sk, nsk, skb))
 				goto reset;
 			if (opt_skb)
@@ -1933,8 +1923,9 @@ struct proto tcpv6_prot = {
 	.diag_destroy		= tcp_abort,
 };
 
-static const struct inet6_protocol tcpv6_protocol = {
+static struct inet6_protocol tcpv6_protocol = {
 	.early_demux	=	tcp_v6_early_demux,
+	.early_demux_handler =  tcp_v6_early_demux,
 	.handler	=	tcp_v6_rcv,
 	.err_handler	=	tcp_v6_err,
 	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e28082f0a307..fd4b1c98a472 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -864,6 +864,64 @@ discard:
 	return 0;
 }
 
+static struct sock *__udp6_lib_demux_lookup(struct net *net,
+			__be16 loc_port, const struct in6_addr *loc_addr,
+			__be16 rmt_port, const struct in6_addr *rmt_addr,
+			int dif)
+{
+	struct sock *sk;
+
+	rcu_read_lock();
+	sk = __udp6_lib_lookup(net, rmt_addr, rmt_port, loc_addr, loc_port,
+			       dif, &udp_table, NULL);
+	if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+		sk = NULL;
+	rcu_read_unlock();
+
+	return sk;
+}
+
+static void udp_v6_early_demux(struct sk_buff *skb)
+{
+	struct net *net = dev_net(skb->dev);
+	const struct udphdr *uh;
+	struct sock *sk;
+	struct dst_entry *dst;
+	int dif = skb->dev->ifindex;
+
+	if (!pskb_may_pull(skb, skb_transport_offset(skb) +
+	    sizeof(struct udphdr)))
+		return;
+
+	uh = udp_hdr(skb);
+
+	if (skb->pkt_type == PACKET_HOST)
+		sk = __udp6_lib_demux_lookup(net, uh->dest,
+					     &ipv6_hdr(skb)->daddr,
+					     uh->source, &ipv6_hdr(skb)->saddr,
+					     dif);
+	else
+		return;
+
+	if (!sk)
+		return;
+
+	skb->sk = sk;
+	skb->destructor = sock_efree;
+	dst = READ_ONCE(sk->sk_rx_dst);
+
+	if (dst)
+		dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
+	if (dst) {
+		if (dst->flags & DST_NOCACHE) {
+			if (likely(atomic_inc_not_zero(&dst->__refcnt)))
+				skb_dst_set(skb, dst);
+		} else {
+			skb_dst_set_noref(skb, dst);
+		}
+	}
+}
+
 static __inline__ int udpv6_rcv(struct sk_buff *skb)
 {
 	return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP);
@@ -1378,7 +1436,9 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
 }
 #endif
 
-static const struct inet6_protocol udpv6_protocol = {
+static struct inet6_protocol udpv6_protocol = {
+	.early_demux	=	udp_v6_early_demux,
+	.early_demux_handler =  udp_v6_early_demux,
 	.handler	=	udpv6_rcv,
 	.err_handler	=	udpv6_err,
 	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index 56ccffa3f2bf..62141dcec2d6 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -19,6 +19,7 @@
 #ifndef __IEEE802154_I_H
 #define __IEEE802154_I_H
 
+#include <linux/interrupt.h>
 #include <linux/mutex.h>
 #include <linux/hrtimer.h>
 #include <net/cfg802154.h>
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 6414079aa729..5928d22ba9c8 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -24,6 +24,9 @@
 #include <net/nexthop.h>
 #include "internal.h"
 
+/* max memory we will use for mpls_route */
+#define MAX_MPLS_ROUTE_MEM	4096
+
 /* Maximum number of labels to look ahead at when selecting a path of
  * a multipath route
  */
@@ -32,7 +35,9 @@
 #define MPLS_NEIGH_TABLE_UNSPEC (NEIGH_LINK_TABLE + 1)
 
 static int zero = 0;
+static int one = 1;
 static int label_limit = (1 << 20) - 1;
+static int ttl_max = 255;
 
 static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt,
 		       struct nlmsghdr *nlh, struct net *net, u32 portid,
@@ -58,10 +63,7 @@ EXPORT_SYMBOL_GPL(mpls_output_possible);
 
 static u8 *__mpls_nh_via(struct mpls_route *rt, struct mpls_nh *nh)
 {
-	u8 *nh0_via = PTR_ALIGN((u8 *)&rt->rt_nh[rt->rt_nhn], VIA_ALEN_ALIGN);
-	int nh_index = nh - rt->rt_nh;
-
-	return nh0_via + rt->rt_max_alen * nh_index;
+	return (u8 *)nh + rt->rt_via_offset;
 }
 
 static const u8 *mpls_nh_via(const struct mpls_route *rt,
@@ -187,21 +189,32 @@ static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb)
 	return hash;
 }
 
+static struct mpls_nh *mpls_get_nexthop(struct mpls_route *rt, u8 index)
+{
+	return (struct mpls_nh *)((u8 *)rt->rt_nh + index * rt->rt_nh_size);
+}
+
+/* number of alive nexthops (rt->rt_nhn_alive) and the flags for
+ * a next hop (nh->nh_flags) are modified by netdev event handlers.
+ * Since those fields can change at any moment, use READ_ONCE to
+ * access both.
+ */
 static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
 					     struct sk_buff *skb)
 {
-	int alive = ACCESS_ONCE(rt->rt_nhn_alive);
 	u32 hash = 0;
 	int nh_index = 0;
 	int n = 0;
+	u8 alive;
 
 	/* No need to look further into packet if there's only
 	 * one path
 	 */
 	if (rt->rt_nhn == 1)
-		goto out;
+		return rt->rt_nh;
 
-	if (alive <= 0)
+	alive = READ_ONCE(rt->rt_nhn_alive);
+	if (alive == 0)
 		return NULL;
 
 	hash = mpls_multipath_hash(rt, skb);
@@ -209,7 +222,9 @@ static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
 	if (alive == rt->rt_nhn)
 		goto out;
 	for_nexthops(rt) {
-		if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+		unsigned int nh_flags = READ_ONCE(nh->nh_flags);
+
+		if (nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
 			continue;
 		if (n == nh_index)
 			return nh;
@@ -217,11 +232,11 @@ static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
 	} endfor_nexthops(rt);
 
 out:
-	return &rt->rt_nh[nh_index];
+	return mpls_get_nexthop(rt, nh_index);
 }
 
-static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb,
-			struct mpls_entry_decoded dec)
+static bool mpls_egress(struct net *net, struct mpls_route *rt,
+			struct sk_buff *skb, struct mpls_entry_decoded dec)
 {
 	enum mpls_payload_type payload_type;
 	bool success = false;
@@ -246,22 +261,46 @@ static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb,
 	switch (payload_type) {
 	case MPT_IPV4: {
 		struct iphdr *hdr4 = ip_hdr(skb);
+		u8 new_ttl;
 		skb->protocol = htons(ETH_P_IP);
+
+		/* If propagating TTL, take the decremented TTL from
+		 * the incoming MPLS header, otherwise decrement the
+		 * TTL, but only if not 0 to avoid underflow.
+		 */
+		if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED ||
+		    (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT &&
+		     net->mpls.ip_ttl_propagate))
+			new_ttl = dec.ttl;
+		else
+			new_ttl = hdr4->ttl ? hdr4->ttl - 1 : 0;
+
 		csum_replace2(&hdr4->check,
 			      htons(hdr4->ttl << 8),
-			      htons(dec.ttl << 8));
-		hdr4->ttl = dec.ttl;
+			      htons(new_ttl << 8));
+		hdr4->ttl = new_ttl;
 		success = true;
 		break;
 	}
 	case MPT_IPV6: {
 		struct ipv6hdr *hdr6 = ipv6_hdr(skb);
 		skb->protocol = htons(ETH_P_IPV6);
-		hdr6->hop_limit = dec.ttl;
+
+		/* If propagating TTL, take the decremented TTL from
+		 * the incoming MPLS header, otherwise decrement the
+		 * hop limit, but only if not 0 to avoid underflow.
+		 */
+		if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED ||
+		    (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT &&
+		     net->mpls.ip_ttl_propagate))
+			hdr6->hop_limit = dec.ttl;
+		else if (hdr6->hop_limit)
+			hdr6->hop_limit = hdr6->hop_limit - 1;
 		success = true;
 		break;
 	}
 	case MPT_UNSPEC:
+		/* Should have decided which protocol it is by now */
 		break;
 	}
 
@@ -361,7 +400,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
 
 	if (unlikely(!new_header_size && dec.bos)) {
 		/* Penultimate hop popping */
-		if (!mpls_egress(rt, skb, dec))
+		if (!mpls_egress(dev_net(out_dev), rt, skb, dec))
 			goto err;
 	} else {
 		bool bos;
@@ -412,6 +451,7 @@ static struct packet_type mpls_packet_type __read_mostly = {
 static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = {
 	[RTA_DST]		= { .type = NLA_U32 },
 	[RTA_OIF]		= { .type = NLA_U32 },
+	[RTA_TTL_PROPAGATE]	= { .type = NLA_U8 },
 };
 
 struct mpls_route_config {
@@ -421,6 +461,7 @@ struct mpls_route_config {
 	u8			rc_via_alen;
 	u8			rc_via[MAX_VIA_ALEN];
 	u32			rc_label;
+	u8			rc_ttl_propagate;
 	u8			rc_output_labels;
 	u32			rc_output_label[MAX_NEW_LABELS];
 	u32			rc_nlflags;
@@ -430,20 +471,27 @@ struct mpls_route_config {
 	int			rc_mp_len;
 };
 
-static struct mpls_route *mpls_rt_alloc(int num_nh, u8 max_alen)
+/* all nexthops within a route have the same size based on max
+ * number of labels and max via length for a hop
+ */
+static struct mpls_route *mpls_rt_alloc(u8 num_nh, u8 max_alen, u8 max_labels)
 {
-	u8 max_alen_aligned = ALIGN(max_alen, VIA_ALEN_ALIGN);
+	u8 nh_size = MPLS_NH_SIZE(max_labels, max_alen);
 	struct mpls_route *rt;
+	size_t size;
 
-	rt = kzalloc(ALIGN(sizeof(*rt) + num_nh * sizeof(*rt->rt_nh),
-			   VIA_ALEN_ALIGN) +
-		     num_nh * max_alen_aligned,
-		     GFP_KERNEL);
-	if (rt) {
-		rt->rt_nhn = num_nh;
-		rt->rt_nhn_alive = num_nh;
-		rt->rt_max_alen = max_alen_aligned;
-	}
+	size = sizeof(*rt) + num_nh * nh_size;
+	if (size > MAX_MPLS_ROUTE_MEM)
+		return ERR_PTR(-EINVAL);
+
+	rt = kzalloc(size, GFP_KERNEL);
+	if (!rt)
+		return ERR_PTR(-ENOMEM);
+
+	rt->rt_nhn = num_nh;
+	rt->rt_nhn_alive = num_nh;
+	rt->rt_nh_size = nh_size;
+	rt->rt_via_offset = MPLS_NH_VIA_OFF(max_labels);
 
 	return rt;
 }
@@ -648,9 +696,6 @@ static int mpls_nh_build_from_cfg(struct mpls_route_config *cfg,
 		return -ENOMEM;
 
 	err = -EINVAL;
-	/* Ensure only a supported number of labels are present */
-	if (cfg->rc_output_labels > MAX_NEW_LABELS)
-		goto errout;
 
 	nh->nh_labels = cfg->rc_output_labels;
 	for (i = 0; i < nh->nh_labels; i++)
@@ -675,7 +720,7 @@ errout:
 
 static int mpls_nh_build(struct net *net, struct mpls_route *rt,
 			 struct mpls_nh *nh, int oif, struct nlattr *via,
-			 struct nlattr *newdst)
+			 struct nlattr *newdst, u8 max_labels)
 {
 	int err = -ENOMEM;
 
@@ -683,7 +728,7 @@ static int mpls_nh_build(struct net *net, struct mpls_route *rt,
 		goto errout;
 
 	if (newdst) {
-		err = nla_get_labels(newdst, MAX_NEW_LABELS,
+		err = nla_get_labels(newdst, max_labels,
 				     &nh->nh_labels, nh->nh_label);
 		if (err)
 			goto errout;
@@ -708,22 +753,20 @@ errout:
 	return err;
 }
 
-static int mpls_count_nexthops(struct rtnexthop *rtnh, int len,
-			       u8 cfg_via_alen, u8 *max_via_alen)
+static u8 mpls_count_nexthops(struct rtnexthop *rtnh, int len,
+			      u8 cfg_via_alen, u8 *max_via_alen,
+			      u8 *max_labels)
 {
-	int nhs = 0;
 	int remaining = len;
-
-	if (!rtnh) {
-		*max_via_alen = cfg_via_alen;
-		return 1;
-	}
+	u8 nhs = 0;
 
 	*max_via_alen = 0;
+	*max_labels = 0;
 
 	while (rtnh_ok(rtnh, remaining)) {
 		struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
 		int attrlen;
+		u8 n_labels = 0;
 
 		attrlen = rtnh_attrlen(rtnh);
 		nla = nla_find(attrs, attrlen, RTA_VIA);
@@ -737,7 +780,20 @@ static int mpls_count_nexthops(struct rtnexthop *rtnh, int len,
 						      via_alen);
 		}
 
+		nla = nla_find(attrs, attrlen, RTA_NEWDST);
+		if (nla &&
+		    nla_get_labels(nla, MAX_NEW_LABELS, &n_labels, NULL) != 0)
+			return 0;
+
+		*max_labels = max_t(u8, *max_labels, n_labels);
+
+		/* number of nexthops is tracked by a u8.
+		 * Check for overflow.
+		 */
+		if (nhs == 255)
+			return 0;
 		nhs++;
+
 		rtnh = rtnh_next(rtnh, &remaining);
 	}
 
@@ -746,13 +802,13 @@ static int mpls_count_nexthops(struct rtnexthop *rtnh, int len,
 }
 
 static int mpls_nh_build_multi(struct mpls_route_config *cfg,
-			       struct mpls_route *rt)
+			       struct mpls_route *rt, u8 max_labels)
 {
 	struct rtnexthop *rtnh = cfg->rc_mp;
 	struct nlattr *nla_via, *nla_newdst;
 	int remaining = cfg->rc_mp_len;
-	int nhs = 0;
 	int err = 0;
+	u8 nhs = 0;
 
 	change_nexthops(rt) {
 		int attrlen;
@@ -779,7 +835,8 @@ static int mpls_nh_build_multi(struct mpls_route_config *cfg,
 		}
 
 		err = mpls_nh_build(cfg->rc_nlinfo.nl_net, rt, nh,
-				    rtnh->rtnh_ifindex, nla_via, nla_newdst);
+				    rtnh->rtnh_ifindex, nla_via, nla_newdst,
+				    max_labels);
 		if (err)
 			goto errout;
 
@@ -806,7 +863,8 @@ static int mpls_route_add(struct mpls_route_config *cfg)
 	int err = -EINVAL;
 	u8 max_via_alen;
 	unsigned index;
-	int nhs;
+	u8 max_labels;
+	u8 nhs;
 
 	index = cfg->rc_label;
 
@@ -844,21 +902,32 @@ static int mpls_route_add(struct mpls_route_config *cfg)
 		goto errout;
 
 	err = -EINVAL;
-	nhs = mpls_count_nexthops(cfg->rc_mp, cfg->rc_mp_len,
-				  cfg->rc_via_alen, &max_via_alen);
+	if (cfg->rc_mp) {
+		nhs = mpls_count_nexthops(cfg->rc_mp, cfg->rc_mp_len,
+					  cfg->rc_via_alen, &max_via_alen,
+					  &max_labels);
+	} else {
+		max_via_alen = cfg->rc_via_alen;
+		max_labels = cfg->rc_output_labels;
+		nhs = 1;
+	}
+
 	if (nhs == 0)
 		goto errout;
 
 	err = -ENOMEM;
-	rt = mpls_rt_alloc(nhs, max_via_alen);
-	if (!rt)
+	rt = mpls_rt_alloc(nhs, max_via_alen, max_labels);
+	if (IS_ERR(rt)) {
+		err = PTR_ERR(rt);
 		goto errout;
+	}
 
 	rt->rt_protocol = cfg->rc_protocol;
 	rt->rt_payload_type = cfg->rc_payload_type;
+	rt->rt_ttl_propagate = cfg->rc_ttl_propagate;
 
 	if (cfg->rc_mp)
-		err = mpls_nh_build_multi(cfg, rt);
+		err = mpls_nh_build_multi(cfg, rt, max_labels);
 	else
 		err = mpls_nh_build_from_cfg(cfg, rt);
 	if (err)
@@ -1011,8 +1080,8 @@ static int mpls_netconf_msgsize_devconf(int type)
 	return size;
 }
 
-static void mpls_netconf_notify_devconf(struct net *net, int type,
-					struct mpls_dev *mdev)
+static void mpls_netconf_notify_devconf(struct net *net, int event,
+					int type, struct mpls_dev *mdev)
 {
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
@@ -1021,8 +1090,7 @@ static void mpls_netconf_notify_devconf(struct net *net, int type,
 	if (!skb)
 		goto errout;
 
-	err = mpls_netconf_fill_devconf(skb, mdev, 0, 0, RTM_NEWNETCONF,
-					0, type);
+	err = mpls_netconf_fill_devconf(skb, mdev, 0, 0, event, 0, type);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in mpls_netconf_msgsize_devconf() */
 		WARN_ON(err == -EMSGSIZE);
@@ -1155,9 +1223,8 @@ static int mpls_conf_proc(struct ctl_table *ctl, int write,
 
 		if (i == offsetof(struct mpls_dev, input_enabled) &&
 		    val != oval) {
-			mpls_netconf_notify_devconf(net,
-						    NETCONFA_INPUT,
-						    mdev);
+			mpls_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						    NETCONFA_INPUT, mdev);
 		}
 	}
 
@@ -1198,10 +1265,11 @@ static int mpls_dev_sysctl_register(struct net_device *dev,
 
 	snprintf(path, sizeof(path), "net/mpls/conf/%s", dev->name);
 
-	mdev->sysctl = register_net_sysctl(dev_net(dev), path, table);
+	mdev->sysctl = register_net_sysctl(net, path, table);
 	if (!mdev->sysctl)
 		goto free;
 
+	mpls_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, mdev);
 	return 0;
 
 free:
@@ -1210,13 +1278,17 @@ out:
 	return -ENOBUFS;
 }
 
-static void mpls_dev_sysctl_unregister(struct mpls_dev *mdev)
+static void mpls_dev_sysctl_unregister(struct net_device *dev,
+				       struct mpls_dev *mdev)
 {
+	struct net *net = dev_net(dev);
 	struct ctl_table *table;
 
 	table = mdev->sysctl->ctl_table_arg;
 	unregister_net_sysctl_table(mdev->sysctl);
 	kfree(table);
+
+	mpls_netconf_notify_devconf(net, RTM_DELNETCONF, 0, mdev);
 }
 
 static struct mpls_dev *mpls_add_dev(struct net_device *dev)
@@ -1242,11 +1314,12 @@ static struct mpls_dev *mpls_add_dev(struct net_device *dev)
 		u64_stats_init(&mpls_stats->syncp);
 	}
 
+	mdev->dev = dev;
+
 	err = mpls_dev_sysctl_register(dev, mdev);
 	if (err)
 		goto free;
 
-	mdev->dev = dev;
 	rcu_assign_pointer(dev->mpls_ptr, mdev);
 
 	return mdev;
@@ -1269,8 +1342,7 @@ static void mpls_ifdown(struct net_device *dev, int event)
 {
 	struct mpls_route __rcu **platform_label;
 	struct net *net = dev_net(dev);
-	unsigned int nh_flags = RTNH_F_DEAD | RTNH_F_LINKDOWN;
-	unsigned int alive;
+	u8 alive, deleted;
 	unsigned index;
 
 	platform_label = rtnl_dereference(net->mpls.platform_label);
@@ -1281,36 +1353,48 @@ static void mpls_ifdown(struct net_device *dev, int event)
 			continue;
 
 		alive = 0;
+		deleted = 0;
 		change_nexthops(rt) {
+			unsigned int nh_flags = nh->nh_flags;
+
 			if (rtnl_dereference(nh->nh_dev) != dev)
 				goto next;
 
 			switch (event) {
 			case NETDEV_DOWN:
 			case NETDEV_UNREGISTER:
-				nh->nh_flags |= RTNH_F_DEAD;
+				nh_flags |= RTNH_F_DEAD;
 				/* fall through */
 			case NETDEV_CHANGE:
-				nh->nh_flags |= RTNH_F_LINKDOWN;
+				nh_flags |= RTNH_F_LINKDOWN;
 				break;
 			}
 			if (event == NETDEV_UNREGISTER)
 				RCU_INIT_POINTER(nh->nh_dev, NULL);
+
+			if (nh->nh_flags != nh_flags)
+				WRITE_ONCE(nh->nh_flags, nh_flags);
 next:
-			if (!(nh->nh_flags & nh_flags))
+			if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)))
 				alive++;
+			if (!rtnl_dereference(nh->nh_dev))
+				deleted++;
 		} endfor_nexthops(rt);
 
 		WRITE_ONCE(rt->rt_nhn_alive, alive);
+
+		/* if there are no more nexthops, delete the route */
+		if (event == NETDEV_UNREGISTER && deleted == rt->rt_nhn)
+			mpls_route_update(net, index, NULL, NULL);
 	}
 }
 
-static void mpls_ifup(struct net_device *dev, unsigned int nh_flags)
+static void mpls_ifup(struct net_device *dev, unsigned int flags)
 {
 	struct mpls_route __rcu **platform_label;
 	struct net *net = dev_net(dev);
 	unsigned index;
-	int alive;
+	u8 alive;
 
 	platform_label = rtnl_dereference(net->mpls.platform_label);
 	for (index = 0; index < net->mpls.platform_labels; index++) {
@@ -1321,20 +1405,22 @@ static void mpls_ifup(struct net_device *dev, unsigned int nh_flags)
 
 		alive = 0;
 		change_nexthops(rt) {
+			unsigned int nh_flags = nh->nh_flags;
 			struct net_device *nh_dev =
 				rtnl_dereference(nh->nh_dev);
 
-			if (!(nh->nh_flags & nh_flags)) {
+			if (!(nh_flags & flags)) {
 				alive++;
 				continue;
 			}
 			if (nh_dev != dev)
 				continue;
 			alive++;
-			nh->nh_flags &= ~nh_flags;
+			nh_flags &= ~flags;
+			WRITE_ONCE(nh->nh_flags, flags);
 		} endfor_nexthops(rt);
 
-		ACCESS_ONCE(rt->rt_nhn_alive) = alive;
+		WRITE_ONCE(rt->rt_nhn_alive, alive);
 	}
 }
 
@@ -1385,7 +1471,7 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 		mpls_ifdown(dev, event);
 		mdev = mpls_dev_get(dev);
 		if (mdev) {
-			mpls_dev_sysctl_unregister(mdev);
+			mpls_dev_sysctl_unregister(dev, mdev);
 			RCU_INIT_POINTER(dev->mpls_ptr, NULL);
 			call_rcu(&mdev->rcu, mpls_dev_destroy_rcu);
 		}
@@ -1395,7 +1481,7 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 		if (mdev) {
 			int err;
 
-			mpls_dev_sysctl_unregister(mdev);
+			mpls_dev_sysctl_unregister(dev, mdev);
 			err = mpls_dev_sysctl_register(dev, mdev);
 			if (err)
 				return notifier_from_errno(err);
@@ -1455,16 +1541,18 @@ int nla_put_labels(struct sk_buff *skb, int attrtype,
 EXPORT_SYMBOL_GPL(nla_put_labels);
 
 int nla_get_labels(const struct nlattr *nla,
-		   u32 max_labels, u8 *labels, u32 label[])
+		   u8 max_labels, u8 *labels, u32 label[])
 {
 	unsigned len = nla_len(nla);
-	unsigned nla_labels;
 	struct mpls_shim_hdr *nla_label;
+	u8 nla_labels;
 	bool bos;
 	int i;
 
-	/* len needs to be an even multiple of 4 (the label size) */
-	if (len & 3)
+	/* len needs to be an even multiple of 4 (the label size). Number
+	 * of labels is a u8 so check for overflow.
+	 */
+	if (len & 3 || len / 4 > 255)
 		return -EINVAL;
 
 	/* Limit the number of new labels allowed */
@@ -1472,6 +1560,10 @@ int nla_get_labels(const struct nlattr *nla,
 	if (nla_labels > max_labels)
 		return -EINVAL;
 
+	/* when label == NULL, caller wants number of labels */
+	if (!label)
+		goto out;
+
 	nla_label = nla_data(nla);
 	bos = true;
 	for (i = nla_labels - 1; i >= 0; i--, bos = false) {
@@ -1495,6 +1587,7 @@ int nla_get_labels(const struct nlattr *nla,
 
 		label[i] = dec.label;
 	}
+out:
 	*labels = nla_labels;
 	return 0;
 }
@@ -1556,7 +1649,6 @@ static int rtm_to_route_config(struct sk_buff *skb,  struct nlmsghdr *nlh,
 
 	err = -EINVAL;
 	rtm = nlmsg_data(nlh);
-	memset(cfg, 0, sizeof(*cfg));
 
 	if (rtm->rtm_family != AF_MPLS)
 		goto errout;
@@ -1584,6 +1676,7 @@ static int rtm_to_route_config(struct sk_buff *skb,  struct nlmsghdr *nlh,
 	cfg->rc_label		= LABEL_NOT_SPECIFIED;
 	cfg->rc_protocol	= rtm->rtm_protocol;
 	cfg->rc_via_table	= MPLS_NEIGH_TABLE_UNSPEC;
+	cfg->rc_ttl_propagate	= MPLS_TTL_PROP_DEFAULT;
 	cfg->rc_nlflags		= nlh->nlmsg_flags;
 	cfg->rc_nlinfo.portid	= NETLINK_CB(skb).portid;
 	cfg->rc_nlinfo.nlh	= nlh;
@@ -1630,6 +1723,17 @@ static int rtm_to_route_config(struct sk_buff *skb,  struct nlmsghdr *nlh,
 			cfg->rc_mp_len = nla_len(nla);
 			break;
 		}
+		case RTA_TTL_PROPAGATE:
+		{
+			u8 ttl_propagate = nla_get_u8(nla);
+
+			if (ttl_propagate > 1)
+				goto errout;
+			cfg->rc_ttl_propagate = ttl_propagate ?
+				MPLS_TTL_PROP_ENABLED :
+				MPLS_TTL_PROP_DISABLED;
+			break;
+		}
 		default:
 			/* Unsupported attribute */
 			goto errout;
@@ -1643,27 +1747,43 @@ errout:
 
 static int mpls_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
-	struct mpls_route_config cfg;
+	struct mpls_route_config *cfg;
 	int err;
 
-	err = rtm_to_route_config(skb, nlh, &cfg);
+	cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+	if (!cfg)
+		return -ENOMEM;
+
+	err = rtm_to_route_config(skb, nlh, cfg);
 	if (err < 0)
-		return err;
+		goto out;
+
+	err = mpls_route_del(cfg);
+out:
+	kfree(cfg);
 
-	return mpls_route_del(&cfg);
+	return err;
 }
 
 
 static int mpls_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
-	struct mpls_route_config cfg;
+	struct mpls_route_config *cfg;
 	int err;
 
-	err = rtm_to_route_config(skb, nlh, &cfg);
+	cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+	if (!cfg)
+		return -ENOMEM;
+
+	err = rtm_to_route_config(skb, nlh, cfg);
 	if (err < 0)
-		return err;
+		goto out;
 
-	return mpls_route_add(&cfg);
+	err = mpls_route_add(cfg);
+out:
+	kfree(cfg);
+
+	return err;
 }
 
 static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
@@ -1690,6 +1810,15 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
 
 	if (nla_put_labels(skb, RTA_DST, 1, &label))
 		goto nla_put_failure;
+
+	if (rt->rt_ttl_propagate != MPLS_TTL_PROP_DEFAULT) {
+		bool ttl_propagate =
+			rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED;
+
+		if (nla_put_u8(skb, RTA_TTL_PROPAGATE,
+			       ttl_propagate))
+			goto nla_put_failure;
+	}
 	if (rt->rt_nhn == 1) {
 		const struct mpls_nh *nh = rt->rt_nh;
 
@@ -1711,21 +1840,23 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
 	} else {
 		struct rtnexthop *rtnh;
 		struct nlattr *mp;
-		int dead = 0;
-		int linkdown = 0;
+		u8 linkdown = 0;
+		u8 dead = 0;
 
 		mp = nla_nest_start(skb, RTA_MULTIPATH);
 		if (!mp)
 			goto nla_put_failure;
 
 		for_nexthops(rt) {
+			dev = rtnl_dereference(nh->nh_dev);
+			if (!dev)
+				continue;
+
 			rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
 			if (!rtnh)
 				goto nla_put_failure;
 
-			dev = rtnl_dereference(nh->nh_dev);
-			if (dev)
-				rtnh->rtnh_ifindex = dev->ifindex;
+			rtnh->rtnh_ifindex = dev->ifindex;
 			if (nh->nh_flags & RTNH_F_LINKDOWN) {
 				rtnh->rtnh_flags |= RTNH_F_LINKDOWN;
 				linkdown++;
@@ -1800,7 +1931,8 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt)
 {
 	size_t payload =
 		NLMSG_ALIGN(sizeof(struct rtmsg))
-		+ nla_total_size(4);			/* RTA_DST */
+		+ nla_total_size(4)			/* RTA_DST */
+		+ nla_total_size(1);			/* RTA_TTL_PROPAGATE */
 
 	if (rt->rt_nhn == 1) {
 		struct mpls_nh *nh = rt->rt_nh;
@@ -1816,6 +1948,8 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt)
 		size_t nhsize = 0;
 
 		for_nexthops(rt) {
+			if (!rtnl_dereference(nh->nh_dev))
+				continue;
 			nhsize += nla_total_size(sizeof(struct rtnexthop));
 			/* RTA_VIA */
 			if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC)
@@ -1878,12 +2012,13 @@ static int resize_platform_label_table(struct net *net, size_t limit)
 	/* In case the predefined labels need to be populated */
 	if (limit > MPLS_LABEL_IPV4NULL) {
 		struct net_device *lo = net->loopback_dev;
-		rt0 = mpls_rt_alloc(1, lo->addr_len);
-		if (!rt0)
+		rt0 = mpls_rt_alloc(1, lo->addr_len, 0);
+		if (IS_ERR(rt0))
 			goto nort0;
 		RCU_INIT_POINTER(rt0->rt_nh->nh_dev, lo);
 		rt0->rt_protocol = RTPROT_KERNEL;
 		rt0->rt_payload_type = MPT_IPV4;
+		rt0->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT;
 		rt0->rt_nh->nh_via_table = NEIGH_LINK_TABLE;
 		rt0->rt_nh->nh_via_alen = lo->addr_len;
 		memcpy(__mpls_nh_via(rt0, rt0->rt_nh), lo->dev_addr,
@@ -1891,12 +2026,13 @@ static int resize_platform_label_table(struct net *net, size_t limit)
 	}
 	if (limit > MPLS_LABEL_IPV6NULL) {
 		struct net_device *lo = net->loopback_dev;
-		rt2 = mpls_rt_alloc(1, lo->addr_len);
-		if (!rt2)
+		rt2 = mpls_rt_alloc(1, lo->addr_len, 0);
+		if (IS_ERR(rt2))
 			goto nort2;
 		RCU_INIT_POINTER(rt2->rt_nh->nh_dev, lo);
 		rt2->rt_protocol = RTPROT_KERNEL;
 		rt2->rt_payload_type = MPT_IPV6;
+		rt2->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT;
 		rt2->rt_nh->nh_via_table = NEIGH_LINK_TABLE;
 		rt2->rt_nh->nh_via_alen = lo->addr_len;
 		memcpy(__mpls_nh_via(rt2, rt2->rt_nh), lo->dev_addr,
@@ -1978,6 +2114,9 @@ static int mpls_platform_labels(struct ctl_table *table, int write,
 	return ret;
 }
 
+#define MPLS_NS_SYSCTL_OFFSET(field)		\
+	(&((struct net *)0)->field)
+
 static const struct ctl_table mpls_table[] = {
 	{
 		.procname	= "platform_labels",
@@ -1986,21 +2125,47 @@ static const struct ctl_table mpls_table[] = {
 		.mode		= 0644,
 		.proc_handler	= mpls_platform_labels,
 	},
+	{
+		.procname	= "ip_ttl_propagate",
+		.data		= MPLS_NS_SYSCTL_OFFSET(mpls.ip_ttl_propagate),
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{
+		.procname	= "default_ttl",
+		.data		= MPLS_NS_SYSCTL_OFFSET(mpls.default_ttl),
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+		.extra2		= &ttl_max,
+	},
 	{ }
 };
 
 static int mpls_net_init(struct net *net)
 {
 	struct ctl_table *table;
+	int i;
 
 	net->mpls.platform_labels = 0;
 	net->mpls.platform_label = NULL;
+	net->mpls.ip_ttl_propagate = 1;
+	net->mpls.default_ttl = 255;
 
 	table = kmemdup(mpls_table, sizeof(mpls_table), GFP_KERNEL);
 	if (table == NULL)
 		return -ENOMEM;
 
-	table[0].data = net;
+	/* Table data contains only offsets relative to the base of
+	 * the mdev at this point, so make them absolute.
+	 */
+	for (i = 0; i < ARRAY_SIZE(mpls_table) - 1; i++)
+		table[i].data = (char *)net + (uintptr_t)table[i].data;
+
 	net->mpls.ctl = register_net_sysctl(net, "net/mpls", table);
 	if (net->mpls.ctl == NULL) {
 		kfree(table);
diff --git a/net/mpls/internal.h b/net/mpls/internal.h
index 76360d8b9579..4db6a5971322 100644
--- a/net/mpls/internal.h
+++ b/net/mpls/internal.h
@@ -2,6 +2,11 @@
 #define MPLS_INTERNAL_H
 #include <net/mpls.h>
 
+/* put a reasonable limit on the number of labels
+ * we will accept from userspace
+ */
+#define MAX_NEW_LABELS 30
+
 struct mpls_entry_decoded {
 	u32 label;
 	u8 ttl;
@@ -64,7 +69,6 @@ struct mpls_dev {
 struct sk_buff;
 
 #define LABEL_NOT_SPECIFIED (1 << 20)
-#define MAX_NEW_LABELS 2
 
 /* This maximum ha length copied from the definition of struct neighbour */
 #define VIA_ALEN_ALIGN sizeof(unsigned long)
@@ -83,11 +87,35 @@ enum mpls_payload_type {
 
 struct mpls_nh { /* next hop label forwarding entry */
 	struct net_device __rcu *nh_dev;
+
+	/* nh_flags is accessed under RCU in the packet path; it is
+	 * modified handling netdev events with rtnl lock held
+	 */
 	unsigned int		nh_flags;
-	u32			nh_label[MAX_NEW_LABELS];
 	u8			nh_labels;
 	u8			nh_via_alen;
 	u8			nh_via_table;
+	u8			nh_reserved1;
+
+	u32			nh_label[0];
+};
+
+/* offset of via from beginning of mpls_nh */
+#define MPLS_NH_VIA_OFF(num_labels) \
+		ALIGN(sizeof(struct mpls_nh) + (num_labels) * sizeof(u32), \
+		      VIA_ALEN_ALIGN)
+
+/* all nexthops within a route have the same size based on the
+ * max number of labels and max via length across all nexthops
+ */
+#define MPLS_NH_SIZE(num_labels, max_via_alen)		\
+		(MPLS_NH_VIA_OFF((num_labels)) +	\
+		ALIGN((max_via_alen), VIA_ALEN_ALIGN))
+
+enum mpls_ttl_propagation {
+	MPLS_TTL_PROP_DEFAULT,
+	MPLS_TTL_PROP_ENABLED,
+	MPLS_TTL_PROP_DISABLED,
 };
 
 /* The route, nexthops and vias are stored together in the same memory
@@ -98,16 +126,16 @@ struct mpls_nh { /* next hop label forwarding entry */
  * +----------------------+
  * | mpls_nh 0            |
  * +----------------------+
- * | ...                  |
- * +----------------------+
- * | mpls_nh n-1          |
- * +----------------------+
- * | alignment padding    |
+ * | alignment padding    |   4 bytes for odd number of labels
  * +----------------------+
  * | via[rt_max_alen] 0   |
  * +----------------------+
+ * | alignment padding    |   via's aligned on sizeof(unsigned long)
+ * +----------------------+
  * | ...                  |
  * +----------------------+
+ * | mpls_nh n-1          |
+ * +----------------------+
  * | via[rt_max_alen] n-1 |
  * +----------------------+
  */
@@ -116,22 +144,30 @@ struct mpls_route { /* next hop label forwarding entry */
 	u8			rt_protocol;
 	u8			rt_payload_type;
 	u8			rt_max_alen;
-	unsigned int		rt_nhn;
-	unsigned int		rt_nhn_alive;
+	u8			rt_ttl_propagate;
+	u8			rt_nhn;
+	/* rt_nhn_alive is accessed under RCU in the packet path; it
+	 * is modified handling netdev events with rtnl lock held
+	 */
+	u8			rt_nhn_alive;
+	u8			rt_nh_size;
+	u8			rt_via_offset;
+	u8			rt_reserved1;
 	struct mpls_nh		rt_nh[0];
 };
 
 #define for_nexthops(rt) {						\
-	int nhsel; struct mpls_nh *nh;			\
-	for (nhsel = 0, nh = (rt)->rt_nh;				\
+	int nhsel; struct mpls_nh *nh;  u8 *__nh;			\
+	for (nhsel = 0, nh = (rt)->rt_nh, __nh = (u8 *)((rt)->rt_nh);	\
 	     nhsel < (rt)->rt_nhn;					\
-	     nh++, nhsel++)
+	     __nh += rt->rt_nh_size, nh = (struct mpls_nh *)__nh, nhsel++)
 
 #define change_nexthops(rt) {						\
-	int nhsel; struct mpls_nh *nh;				\
-	for (nhsel = 0,	nh = (struct mpls_nh *)((rt)->rt_nh);	\
+	int nhsel; struct mpls_nh *nh; u8 *__nh;			\
+	for (nhsel = 0, nh = (struct mpls_nh *)((rt)->rt_nh),		\
+			__nh = (u8 *)((rt)->rt_nh);			\
 	     nhsel < (rt)->rt_nhn;					\
-	     nh++, nhsel++)
+	     __nh += rt->rt_nh_size, nh = (struct mpls_nh *)__nh, nhsel++)
 
 #define endfor_nexthops(rt) }
 
@@ -166,7 +202,7 @@ static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev)
 
 int nla_put_labels(struct sk_buff *skb, int attrtype,  u8 labels,
 		   const u32 label[]);
-int nla_get_labels(const struct nlattr *nla, u32 max_labels, u8 *labels,
+int nla_get_labels(const struct nlattr *nla, u8 max_labels, u8 *labels,
 		   u32 label[]);
 int nla_get_via(const struct nlattr *nla, u8 *via_alen, u8 *via_table,
 		u8 via[]);
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index e4e4424f9eb1..fe00e98667cf 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -29,6 +29,7 @@
 
 static const struct nla_policy mpls_iptunnel_policy[MPLS_IPTUNNEL_MAX + 1] = {
 	[MPLS_IPTUNNEL_DST]	= { .type = NLA_U32 },
+	[MPLS_IPTUNNEL_TTL]	= { .type = NLA_U8 },
 };
 
 static unsigned int mpls_encap_size(struct mpls_iptunnel_encap *en)
@@ -49,6 +50,7 @@ static int mpls_xmit(struct sk_buff *skb)
 	struct rtable *rt = NULL;
 	struct rt6_info *rt6 = NULL;
 	struct mpls_dev *out_mdev;
+	struct net *net;
 	int err = 0;
 	bool bos;
 	int i;
@@ -56,17 +58,7 @@ static int mpls_xmit(struct sk_buff *skb)
 
 	/* Find the output device */
 	out_dev = dst->dev;
-
-	/* Obtain the ttl */
-	if (dst->ops->family == AF_INET) {
-		ttl = ip_hdr(skb)->ttl;
-		rt = (struct rtable *)dst;
-	} else if (dst->ops->family == AF_INET6) {
-		ttl = ipv6_hdr(skb)->hop_limit;
-		rt6 = (struct rt6_info *)dst;
-	} else {
-		goto drop;
-	}
+	net = dev_net(out_dev);
 
 	skb_orphan(skb);
 
@@ -78,6 +70,38 @@ static int mpls_xmit(struct sk_buff *skb)
 
 	tun_encap_info = mpls_lwtunnel_encap(dst->lwtstate);
 
+	/* Obtain the ttl using the following set of rules.
+	 *
+	 * LWT ttl propagation setting:
+	 *  - disabled => use default TTL value from LWT
+	 *  - enabled  => use TTL value from IPv4/IPv6 header
+	 *  - default  =>
+	 *   Global ttl propagation setting:
+	 *    - disabled => use default TTL value from global setting
+	 *    - enabled => use TTL value from IPv4/IPv6 header
+	 */
+	if (dst->ops->family == AF_INET) {
+		if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED)
+			ttl = tun_encap_info->default_ttl;
+		else if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DEFAULT &&
+			 !net->mpls.ip_ttl_propagate)
+			ttl = net->mpls.default_ttl;
+		else
+			ttl = ip_hdr(skb)->ttl;
+		rt = (struct rtable *)dst;
+	} else if (dst->ops->family == AF_INET6) {
+		if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED)
+			ttl = tun_encap_info->default_ttl;
+		else if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DEFAULT &&
+			 !net->mpls.ip_ttl_propagate)
+			ttl = net->mpls.default_ttl;
+		else
+			ttl = ipv6_hdr(skb)->hop_limit;
+		rt6 = (struct rt6_info *)dst;
+	} else {
+		goto drop;
+	}
+
 	/* Verify the destination can hold the packet */
 	new_header_size = mpls_encap_size(tun_encap_info);
 	mtu = mpls_dev_mtu(out_dev);
@@ -140,6 +164,7 @@ static int mpls_build_state(struct nlattr *nla,
 	struct mpls_iptunnel_encap *tun_encap_info;
 	struct nlattr *tb[MPLS_IPTUNNEL_MAX + 1];
 	struct lwtunnel_state *newts;
+	u8 n_labels;
 	int ret;
 
 	ret = nla_parse_nested(tb, MPLS_IPTUNNEL_MAX, nla,
@@ -151,15 +176,32 @@ static int mpls_build_state(struct nlattr *nla,
 		return -EINVAL;
 
 
-	newts = lwtunnel_state_alloc(sizeof(*tun_encap_info));
+	/* determine number of labels */
+	if (nla_get_labels(tb[MPLS_IPTUNNEL_DST],
+			   MAX_NEW_LABELS, &n_labels, NULL))
+		return -EINVAL;
+
+	newts = lwtunnel_state_alloc(sizeof(*tun_encap_info) +
+				     n_labels * sizeof(u32));
 	if (!newts)
 		return -ENOMEM;
 
 	tun_encap_info = mpls_lwtunnel_encap(newts);
-	ret = nla_get_labels(tb[MPLS_IPTUNNEL_DST], MAX_NEW_LABELS,
+	ret = nla_get_labels(tb[MPLS_IPTUNNEL_DST], n_labels,
 			     &tun_encap_info->labels, tun_encap_info->label);
 	if (ret)
 		goto errout;
+
+	tun_encap_info->ttl_propagate = MPLS_TTL_PROP_DEFAULT;
+
+	if (tb[MPLS_IPTUNNEL_TTL]) {
+		tun_encap_info->default_ttl = nla_get_u8(tb[MPLS_IPTUNNEL_TTL]);
+		/* TTL 0 implies propagate from IP header */
+		tun_encap_info->ttl_propagate = tun_encap_info->default_ttl ?
+			MPLS_TTL_PROP_DISABLED :
+			MPLS_TTL_PROP_ENABLED;
+	}
+
 	newts->type = LWTUNNEL_ENCAP_MPLS;
 	newts->flags |= LWTUNNEL_STATE_XMIT_REDIRECT;
 	newts->headroom = mpls_encap_size(tun_encap_info);
@@ -186,6 +228,10 @@ static int mpls_fill_encap_info(struct sk_buff *skb,
 			   tun_encap_info->label))
 		goto nla_put_failure;
 
+	if (tun_encap_info->ttl_propagate != MPLS_TTL_PROP_DEFAULT &&
+	    nla_put_u8(skb, MPLS_IPTUNNEL_TTL, tun_encap_info->default_ttl))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
@@ -195,10 +241,16 @@ nla_put_failure:
 static int mpls_encap_nlsize(struct lwtunnel_state *lwtstate)
 {
 	struct mpls_iptunnel_encap *tun_encap_info;
+	int nlsize;
 
 	tun_encap_info = mpls_lwtunnel_encap(lwtstate);
 
-	return nla_total_size(tun_encap_info->labels * 4);
+	nlsize = nla_total_size(tun_encap_info->labels * 4);
+
+	if (tun_encap_info->ttl_propagate != MPLS_TTL_PROP_DEFAULT)
+		nlsize += nla_total_size(1);
+
+	return nlsize;
 }
 
 static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
@@ -207,10 +259,12 @@ static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
 	struct mpls_iptunnel_encap *b_hdr = mpls_lwtunnel_encap(b);
 	int l;
 
-	if (a_hdr->labels != b_hdr->labels)
+	if (a_hdr->labels != b_hdr->labels ||
+	    a_hdr->ttl_propagate != b_hdr->ttl_propagate ||
+	    a_hdr->default_ttl != b_hdr->default_ttl)
 		return 1;
 
-	for (l = 0; l < MAX_NEW_LABELS; l++)
+	for (l = 0; l < a_hdr->labels; l++)
 		if (a_hdr->label[l] != b_hdr->label[l])
 			return 1;
 	return 0;
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index e6a2753dff9e..3d2ac71a83ec 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -181,7 +181,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
 
 	if (!(cp->flags & IP_VS_CONN_F_HASHED)) {
 		cp->flags |= IP_VS_CONN_F_HASHED;
-		atomic_inc(&cp->refcnt);
+		refcount_inc(&cp->refcnt);
 		hlist_add_head_rcu(&cp->c_list, &ip_vs_conn_tab[hash]);
 		ret = 1;
 	} else {
@@ -215,7 +215,7 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp)
 	if (cp->flags & IP_VS_CONN_F_HASHED) {
 		hlist_del_rcu(&cp->c_list);
 		cp->flags &= ~IP_VS_CONN_F_HASHED;
-		atomic_dec(&cp->refcnt);
+		refcount_dec(&cp->refcnt);
 		ret = 1;
 	} else
 		ret = 0;
@@ -242,13 +242,13 @@ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp)
 	if (cp->flags & IP_VS_CONN_F_HASHED) {
 		ret = false;
 		/* Decrease refcnt and unlink conn only if we are last user */
-		if (atomic_cmpxchg(&cp->refcnt, 1, 0) == 1) {
+		if (refcount_dec_if_one(&cp->refcnt)) {
 			hlist_del_rcu(&cp->c_list);
 			cp->flags &= ~IP_VS_CONN_F_HASHED;
 			ret = true;
 		}
 	} else
-		ret = atomic_read(&cp->refcnt) ? false : true;
+		ret = refcount_read(&cp->refcnt) ? false : true;
 
 	spin_unlock(&cp->lock);
 	ct_write_unlock_bh(hash);
@@ -475,7 +475,7 @@ static void __ip_vs_conn_put_timer(struct ip_vs_conn *cp)
 void ip_vs_conn_put(struct ip_vs_conn *cp)
 {
 	if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) &&
-	    (atomic_read(&cp->refcnt) == 1) &&
+	    (refcount_read(&cp->refcnt) == 1) &&
 	    !timer_pending(&cp->timer))
 		/* expire connection immediately */
 		__ip_vs_conn_put_notimer(cp);
@@ -617,8 +617,8 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
 		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
 		      IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport),
 		      ip_vs_fwd_tag(cp), cp->state,
-		      cp->flags, atomic_read(&cp->refcnt),
-		      atomic_read(&dest->refcnt));
+		      cp->flags, refcount_read(&cp->refcnt),
+		      refcount_read(&dest->refcnt));
 
 	/* Update the connection counters */
 	if (!(flags & IP_VS_CONN_F_TEMPLATE)) {
@@ -714,8 +714,8 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
 		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
 		      IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport),
 		      ip_vs_fwd_tag(cp), cp->state,
-		      cp->flags, atomic_read(&cp->refcnt),
-		      atomic_read(&dest->refcnt));
+		      cp->flags, refcount_read(&cp->refcnt),
+		      refcount_read(&dest->refcnt));
 
 	/* Update the connection counters */
 	if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) {
@@ -863,10 +863,10 @@ static void ip_vs_conn_expire(unsigned long data)
 
   expire_later:
 	IP_VS_DBG(7, "delayed: conn->refcnt=%d conn->n_control=%d\n",
-		  atomic_read(&cp->refcnt),
+		  refcount_read(&cp->refcnt),
 		  atomic_read(&cp->n_control));
 
-	atomic_inc(&cp->refcnt);
+	refcount_inc(&cp->refcnt);
 	cp->timeout = 60*HZ;
 
 	if (ipvs->sync_state & IP_VS_STATE_MASTER)
@@ -941,7 +941,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af,
 	 * it in the table, so that other thread run ip_vs_random_dropentry
 	 * but cannot drop this entry.
 	 */
-	atomic_set(&cp->refcnt, 1);
+	refcount_set(&cp->refcnt, 1);
 
 	cp->control = NULL;
 	atomic_set(&cp->n_control, 0);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index db40050f8785..b4a746d0e39b 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -542,7 +542,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 		      IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),
 		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
 		      IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport),
-		      cp->flags, atomic_read(&cp->refcnt));
+		      cp->flags, refcount_read(&cp->refcnt));
 
 	ip_vs_conn_stats(cp, svc);
 	return cp;
@@ -1193,7 +1193,7 @@ struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc,
 		      IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),
 		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
 		      IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport),
-		      cp->flags, atomic_read(&cp->refcnt));
+		      cp->flags, refcount_read(&cp->refcnt));
 	LeaveFunction(12);
 	return cp;
 }
@@ -2231,8 +2231,6 @@ static int __net_init __ip_vs_init(struct net *net)
 	if (ip_vs_sync_net_init(ipvs) < 0)
 		goto sync_fail;
 
-	printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n",
-			 sizeof(struct netns_ipvs), ipvs->gen);
 	return 0;
 /*
  * Error handling
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 5aeb0dde6ccc..541aa7694775 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -699,7 +699,7 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, int dest_af,
 			      dest->vfwmark,
 			      IP_VS_DBG_ADDR(dest->af, &dest->addr),
 			      ntohs(dest->port),
-			      atomic_read(&dest->refcnt));
+			      refcount_read(&dest->refcnt));
 		if (dest->af == dest_af &&
 		    ip_vs_addr_equal(dest_af, &dest->addr, daddr) &&
 		    dest->port == dport &&
@@ -934,7 +934,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
 	atomic_set(&dest->activeconns, 0);
 	atomic_set(&dest->inactconns, 0);
 	atomic_set(&dest->persistconns, 0);
-	atomic_set(&dest->refcnt, 1);
+	refcount_set(&dest->refcnt, 1);
 
 	INIT_HLIST_NODE(&dest->d_list);
 	spin_lock_init(&dest->dst_lock);
@@ -998,7 +998,7 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 		IP_VS_DBG_BUF(3, "Get destination %s:%u from trash, "
 			      "dest->refcnt=%d, service %u/%s:%u\n",
 			      IP_VS_DBG_ADDR(udest->af, &daddr), ntohs(dport),
-			      atomic_read(&dest->refcnt),
+			      refcount_read(&dest->refcnt),
 			      dest->vfwmark,
 			      IP_VS_DBG_ADDR(svc->af, &dest->vaddr),
 			      ntohs(dest->vport));
@@ -1074,7 +1074,7 @@ static void __ip_vs_del_dest(struct netns_ipvs *ipvs, struct ip_vs_dest *dest,
 	spin_lock_bh(&ipvs->dest_trash_lock);
 	IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, dest->refcnt=%d\n",
 		      IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port),
-		      atomic_read(&dest->refcnt));
+		      refcount_read(&dest->refcnt));
 	if (list_empty(&ipvs->dest_trash) && !cleanup)
 		mod_timer(&ipvs->dest_trash_timer,
 			  jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1));
@@ -1157,7 +1157,7 @@ static void ip_vs_dest_trash_expire(unsigned long data)
 
 	spin_lock(&ipvs->dest_trash_lock);
 	list_for_each_entry_safe(dest, next, &ipvs->dest_trash, t_list) {
-		if (atomic_read(&dest->refcnt) > 1)
+		if (refcount_read(&dest->refcnt) > 1)
 			continue;
 		if (dest->idle_start) {
 			if (time_before(now, dest->idle_start +
@@ -1545,7 +1545,7 @@ ip_vs_forget_dev(struct ip_vs_dest *dest, struct net_device *dev)
 			      dev->name,
 			      IP_VS_DBG_ADDR(dest->af, &dest->addr),
 			      ntohs(dest->port),
-			      atomic_read(&dest->refcnt));
+			      refcount_read(&dest->refcnt));
 		__ip_vs_dst_cache_reset(dest);
 	}
 	spin_unlock_bh(&dest->dst_lock);
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 5824927cf8e0..b6aa4a970c6e 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -448,7 +448,7 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc)
 		      IP_VS_DBG_ADDR(least->af, &least->addr),
 		      ntohs(least->port),
 		      atomic_read(&least->activeconns),
-		      atomic_read(&least->refcnt),
+		      refcount_read(&least->refcnt),
 		      atomic_read(&least->weight), loh);
 
 	return least;
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 703f11877bee..c13ff575f9f7 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -204,7 +204,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set)
 		      IP_VS_DBG_ADDR(least->af, &least->addr),
 		      ntohs(least->port),
 		      atomic_read(&least->activeconns),
-		      atomic_read(&least->refcnt),
+		      refcount_read(&least->refcnt),
 		      atomic_read(&least->weight), loh);
 	return least;
 }
@@ -249,7 +249,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set)
 		      __func__,
 		      IP_VS_DBG_ADDR(most->af, &most->addr), ntohs(most->port),
 		      atomic_read(&most->activeconns),
-		      atomic_read(&most->refcnt),
+		      refcount_read(&most->refcnt),
 		      atomic_read(&most->weight), moh);
 	return most;
 }
@@ -612,7 +612,7 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc)
 		      IP_VS_DBG_ADDR(least->af, &least->addr),
 		      ntohs(least->port),
 		      atomic_read(&least->activeconns),
-		      atomic_read(&least->refcnt),
+		      refcount_read(&least->refcnt),
 		      atomic_read(&least->weight), loh);
 
 	return least;
diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c
index a8b63401e773..7d9d4ac596ca 100644
--- a/net/netfilter/ipvs/ip_vs_nq.c
+++ b/net/netfilter/ipvs/ip_vs_nq.c
@@ -110,7 +110,7 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 		      IP_VS_DBG_ADDR(least->af, &least->addr),
 		      ntohs(least->port),
 		      atomic_read(&least->activeconns),
-		      atomic_read(&least->refcnt),
+		      refcount_read(&least->refcnt),
 		      atomic_read(&least->weight), loh);
 
 	return least;
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index d952d67f904d..56f8e4b204ff 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -447,7 +447,7 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 				ntohs(cp->cport),
 				sctp_state_name(cp->state),
 				sctp_state_name(next_state),
-				atomic_read(&cp->refcnt));
+				refcount_read(&cp->refcnt));
 		if (dest) {
 			if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
 				(next_state != IP_VS_SCTP_S_ESTABLISHED)) {
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 5117bcb7d2f0..12dc8d5bc37d 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -557,7 +557,7 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 			      ntohs(cp->cport),
 			      tcp_state_name(cp->state),
 			      tcp_state_name(new_state),
-			      atomic_read(&cp->refcnt));
+			      refcount_read(&cp->refcnt));
 
 		if (dest) {
 			if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
diff --git a/net/netfilter/ipvs/ip_vs_rr.c b/net/netfilter/ipvs/ip_vs_rr.c
index 58bacfc461ee..ee0530d14c5f 100644
--- a/net/netfilter/ipvs/ip_vs_rr.c
+++ b/net/netfilter/ipvs/ip_vs_rr.c
@@ -97,7 +97,7 @@ stop:
 		      "activeconns %d refcnt %d weight %d\n",
 		      IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port),
 		      atomic_read(&dest->activeconns),
-		      atomic_read(&dest->refcnt), atomic_read(&dest->weight));
+		      refcount_read(&dest->refcnt), atomic_read(&dest->weight));
 
 	return dest;
 }
diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c
index f8e2d00f528b..ab23cf203437 100644
--- a/net/netfilter/ipvs/ip_vs_sed.c
+++ b/net/netfilter/ipvs/ip_vs_sed.c
@@ -111,7 +111,7 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 		      IP_VS_DBG_ADDR(least->af, &least->addr),
 		      ntohs(least->port),
 		      atomic_read(&least->activeconns),
-		      atomic_read(&least->refcnt),
+		      refcount_read(&least->refcnt),
 		      atomic_read(&least->weight), loh);
 
 	return least;
diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c
index 6b366fd90554..6add39e0ec20 100644
--- a/net/netfilter/ipvs/ip_vs_wlc.c
+++ b/net/netfilter/ipvs/ip_vs_wlc.c
@@ -83,7 +83,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 		      IP_VS_DBG_ADDR(least->af, &least->addr),
 		      ntohs(least->port),
 		      atomic_read(&least->activeconns),
-		      atomic_read(&least->refcnt),
+		      refcount_read(&least->refcnt),
 		      atomic_read(&least->weight), loh);
 
 	return least;
diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c
index 17e6d4406ca7..62258dd457ac 100644
--- a/net/netfilter/ipvs/ip_vs_wrr.c
+++ b/net/netfilter/ipvs/ip_vs_wrr.c
@@ -218,7 +218,7 @@ found:
 		      "activeconns %d refcnt %d weight %d\n",
 		      IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port),
 		      atomic_read(&dest->activeconns),
-		      atomic_read(&dest->refcnt),
+		      refcount_read(&dest->refcnt),
 		      atomic_read(&dest->weight));
 	mark->cl = dest;
 
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index ffb78e5f7b70..3d621b8d7b8a 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1133,7 +1133,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_free);
 
 /* Allocate a new conntrack: we return -ENOMEM if classification
    failed due to stress.  Otherwise it really is unclassifiable. */
-static struct nf_conntrack_tuple_hash *
+static noinline struct nf_conntrack_tuple_hash *
 init_conntrack(struct net *net, struct nf_conn *tmpl,
 	       const struct nf_conntrack_tuple *tuple,
 	       struct nf_conntrack_l3proto *l3proto,
@@ -1241,21 +1241,20 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	return &ct->tuplehash[IP_CT_DIR_ORIGINAL];
 }
 
-/* On success, returns conntrack ptr, sets skb->_nfct | ctinfo */
-static inline struct nf_conn *
+/* On success, returns 0, sets skb->_nfct | ctinfo */
+static int
 resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 		  struct sk_buff *skb,
 		  unsigned int dataoff,
 		  u_int16_t l3num,
 		  u_int8_t protonum,
 		  struct nf_conntrack_l3proto *l3proto,
-		  struct nf_conntrack_l4proto *l4proto,
-		  int *set_reply,
-		  enum ip_conntrack_info *ctinfo)
+		  struct nf_conntrack_l4proto *l4proto)
 {
 	const struct nf_conntrack_zone *zone;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_tuple_hash *h;
+	enum ip_conntrack_info ctinfo;
 	struct nf_conntrack_zone tmp;
 	struct nf_conn *ct;
 	u32 hash;
@@ -1264,7 +1263,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 			     dataoff, l3num, protonum, net, &tuple, l3proto,
 			     l4proto)) {
 		pr_debug("Can't get tuple\n");
-		return NULL;
+		return 0;
 	}
 
 	/* look for tuple match */
@@ -1275,33 +1274,30 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 		h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto,
 				   skb, dataoff, hash);
 		if (!h)
-			return NULL;
+			return 0;
 		if (IS_ERR(h))
-			return (void *)h;
+			return PTR_ERR(h);
 	}
 	ct = nf_ct_tuplehash_to_ctrack(h);
 
 	/* It exists; we have (non-exclusive) reference. */
 	if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) {
-		*ctinfo = IP_CT_ESTABLISHED_REPLY;
-		/* Please set reply bit if this packet OK */
-		*set_reply = 1;
+		ctinfo = IP_CT_ESTABLISHED_REPLY;
 	} else {
 		/* Once we've had two way comms, always ESTABLISHED. */
 		if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
 			pr_debug("normal packet for %p\n", ct);
-			*ctinfo = IP_CT_ESTABLISHED;
+			ctinfo = IP_CT_ESTABLISHED;
 		} else if (test_bit(IPS_EXPECTED_BIT, &ct->status)) {
 			pr_debug("related packet for %p\n", ct);
-			*ctinfo = IP_CT_RELATED;
+			ctinfo = IP_CT_RELATED;
 		} else {
 			pr_debug("new packet for %p\n", ct);
-			*ctinfo = IP_CT_NEW;
+			ctinfo = IP_CT_NEW;
 		}
-		*set_reply = 0;
 	}
-	nf_ct_set(skb, ct, *ctinfo);
-	return ct;
+	nf_ct_set(skb, ct, ctinfo);
+	return 0;
 }
 
 unsigned int
@@ -1315,7 +1311,6 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 	unsigned int *timeouts;
 	unsigned int dataoff;
 	u_int8_t protonum;
-	int set_reply = 0;
 	int ret;
 
 	tmpl = nf_ct_get(skb, &ctinfo);
@@ -1358,23 +1353,22 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 			goto out;
 	}
 repeat:
-	ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum,
-			       l3proto, l4proto, &set_reply, &ctinfo);
-	if (!ct) {
-		/* Not valid part of a connection */
-		NF_CT_STAT_INC_ATOMIC(net, invalid);
-		ret = NF_ACCEPT;
-		goto out;
-	}
-
-	if (IS_ERR(ct)) {
+	ret = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum,
+				l3proto, l4proto);
+	if (ret < 0) {
 		/* Too stressed to deal. */
 		NF_CT_STAT_INC_ATOMIC(net, drop);
 		ret = NF_DROP;
 		goto out;
 	}
 
-	NF_CT_ASSERT(skb_nfct(skb));
+	ct = nf_ct_get(skb, &ctinfo);
+	if (!ct) {
+		/* Not valid part of a connection */
+		NF_CT_STAT_INC_ATOMIC(net, invalid);
+		ret = NF_ACCEPT;
+		goto out;
+	}
 
 	/* Decide what timeout policy we want to apply to this flow. */
 	timeouts = nf_ct_timeout_lookup(net, ct, l4proto);
@@ -1399,7 +1393,8 @@ repeat:
 		goto out;
 	}
 
-	if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status))
+	if (ctinfo == IP_CT_ESTABLISHED_REPLY &&
+	    !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status))
 		nf_conntrack_event_cache(IPCT_REPLY, ct);
 out:
 	if (tmpl)
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 4b2e1fb28bb4..cb29e598605f 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -133,7 +133,7 @@ nf_ct_expect_find_get(struct net *net,
 
 	rcu_read_lock();
 	i = __nf_ct_expect_find(net, zone, tuple);
-	if (i && !atomic_inc_not_zero(&i->use))
+	if (i && !refcount_inc_not_zero(&i->use))
 		i = NULL;
 	rcu_read_unlock();
 
@@ -186,7 +186,7 @@ nf_ct_find_expectation(struct net *net,
 		return NULL;
 
 	if (exp->flags & NF_CT_EXPECT_PERMANENT) {
-		atomic_inc(&exp->use);
+		refcount_inc(&exp->use);
 		return exp;
 	} else if (del_timer(&exp->timeout)) {
 		nf_ct_unlink_expect(exp);
@@ -275,7 +275,7 @@ struct nf_conntrack_expect *nf_ct_expect_alloc(struct nf_conn *me)
 		return NULL;
 
 	new->master = me;
-	atomic_set(&new->use, 1);
+	refcount_set(&new->use, 1);
 	return new;
 }
 EXPORT_SYMBOL_GPL(nf_ct_expect_alloc);
@@ -348,7 +348,7 @@ static void nf_ct_expect_free_rcu(struct rcu_head *head)
 
 void nf_ct_expect_put(struct nf_conntrack_expect *exp)
 {
-	if (atomic_dec_and_test(&exp->use))
+	if (refcount_dec_and_test(&exp->use))
 		call_rcu(&exp->rcu, nf_ct_expect_free_rcu);
 }
 EXPORT_SYMBOL_GPL(nf_ct_expect_put);
@@ -361,7 +361,7 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp)
 	unsigned int h = nf_ct_expect_dst_hash(net, &exp->tuple);
 
 	/* two references : one for hash insert, one for the timer */
-	atomic_add(2, &exp->use);
+	refcount_add(2, &exp->use);
 
 	hlist_add_head(&exp->lnode, &master_help->expectations);
 	master_help->expecting[exp->class]++;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 908d858034e4..ecdc324c7785 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2693,7 +2693,7 @@ restart:
 						    cb->nlh->nlmsg_seq,
 						    IPCTNL_MSG_EXP_NEW,
 						    exp) < 0) {
-				if (!atomic_inc_not_zero(&exp->use))
+				if (!refcount_inc_not_zero(&exp->use))
 					continue;
 				cb->args[1] = (unsigned long)exp;
 				goto out;
@@ -2739,7 +2739,7 @@ restart:
 					    cb->nlh->nlmsg_seq,
 					    IPCTNL_MSG_EXP_NEW,
 					    exp) < 0) {
-			if (!atomic_inc_not_zero(&exp->use))
+			if (!refcount_inc_not_zero(&exp->use))
 				continue;
 			cb->args[1] = (unsigned long)exp;
 			goto out;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 434c739dfeca..2d822d2fd830 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1772,8 +1772,19 @@ static int nf_tables_newexpr(const struct nft_ctx *ctx,
 			goto err1;
 	}
 
+	if (ops->validate) {
+		const struct nft_data *data = NULL;
+
+		err = ops->validate(ctx, expr, &data);
+		if (err < 0)
+			goto err2;
+	}
+
 	return 0;
 
+err2:
+	if (ops->destroy)
+		ops->destroy(ctx, expr);
 err1:
 	expr->ops = NULL;
 	return err;
@@ -2523,8 +2534,8 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net,
 	return 0;
 }
 
-struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
-				     const struct nlattr *nla, u8 genmask)
+static struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
+					    const struct nlattr *nla, u8 genmask)
 {
 	struct nft_set *set;
 
@@ -2538,11 +2549,10 @@ struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
 	}
 	return ERR_PTR(-ENOENT);
 }
-EXPORT_SYMBOL_GPL(nf_tables_set_lookup);
 
-struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
-					  const struct nlattr *nla,
-					  u8 genmask)
+static struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
+						 const struct nlattr *nla,
+						 u8 genmask)
 {
 	struct nft_trans *trans;
 	u32 id = ntohl(nla_get_be32(nla));
@@ -2557,7 +2567,25 @@ struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
 	}
 	return ERR_PTR(-ENOENT);
 }
-EXPORT_SYMBOL_GPL(nf_tables_set_lookup_byid);
+
+struct nft_set *nft_set_lookup(const struct net *net,
+			       const struct nft_table *table,
+			       const struct nlattr *nla_set_name,
+			       const struct nlattr *nla_set_id,
+			       u8 genmask)
+{
+	struct nft_set *set;
+
+	set = nf_tables_set_lookup(table, nla_set_name, genmask);
+	if (IS_ERR(set)) {
+		if (!nla_set_id)
+			return set;
+
+		set = nf_tables_set_lookup_byid(net, nla_set_id, genmask);
+	}
+	return set;
+}
+EXPORT_SYMBOL_GPL(nft_set_lookup);
 
 static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set,
 				    const char *name)
@@ -4064,7 +4092,8 @@ static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = {
 	[NFTA_OBJ_DATA]		= { .type = NLA_NESTED },
 };
 
-static struct nft_object *nft_obj_init(const struct nft_object_type *type,
+static struct nft_object *nft_obj_init(const struct nft_ctx *ctx,
+				       const struct nft_object_type *type,
 				       const struct nlattr *attr)
 {
 	struct nlattr *tb[type->maxattr + 1];
@@ -4084,7 +4113,7 @@ static struct nft_object *nft_obj_init(const struct nft_object_type *type,
 	if (obj == NULL)
 		goto err1;
 
-	err = type->init((const struct nlattr * const *)tb, obj);
+	err = type->init(ctx, (const struct nlattr * const *)tb, obj);
 	if (err < 0)
 		goto err2;
 
@@ -4192,7 +4221,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 	if (IS_ERR(type))
 		return PTR_ERR(type);
 
-	obj = nft_obj_init(type, nla[NFTA_OBJ_DATA]);
+	obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
 		goto err1;
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index d44d89b56127..c86da174a5fc 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
 #include <linux/atomic.h>
+#include <linux/refcount.h>
 #include <linux/netlink.h>
 #include <linux/rculist.h>
 #include <linux/slab.h>
@@ -32,7 +33,7 @@ struct nf_acct {
 	atomic64_t		bytes;
 	unsigned long		flags;
 	struct list_head	head;
-	atomic_t		refcnt;
+	refcount_t		refcnt;
 	char			name[NFACCT_NAME_MAX];
 	struct rcu_head		rcu_head;
 	char			data[0];
@@ -123,7 +124,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl,
 		atomic64_set(&nfacct->pkts,
 			     be64_to_cpu(nla_get_be64(tb[NFACCT_PKTS])));
 	}
-	atomic_set(&nfacct->refcnt, 1);
+	refcount_set(&nfacct->refcnt, 1);
 	list_add_tail_rcu(&nfacct->head, &net->nfnl_acct_list);
 	return 0;
 }
@@ -166,7 +167,7 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 			 NFACCT_PAD) ||
 	    nla_put_be64(skb, NFACCT_BYTES, cpu_to_be64(bytes),
 			 NFACCT_PAD) ||
-	    nla_put_be32(skb, NFACCT_USE, htonl(atomic_read(&acct->refcnt))))
+	    nla_put_be32(skb, NFACCT_USE, htonl(refcount_read(&acct->refcnt))))
 		goto nla_put_failure;
 	if (acct->flags & NFACCT_F_QUOTA) {
 		u64 *quota = (u64 *)acct->data;
@@ -329,7 +330,7 @@ static int nfnl_acct_try_del(struct nf_acct *cur)
 	/* We want to avoid races with nfnl_acct_put. So only when the current
 	 * refcnt is 1, we decrease it to 0.
 	 */
-	if (atomic_cmpxchg(&cur->refcnt, 1, 0) == 1) {
+	if (refcount_dec_if_one(&cur->refcnt)) {
 		/* We are protected by nfnl mutex. */
 		list_del_rcu(&cur->head);
 		kfree_rcu(cur, rcu_head);
@@ -413,7 +414,7 @@ struct nf_acct *nfnl_acct_find_get(struct net *net, const char *acct_name)
 		if (!try_module_get(THIS_MODULE))
 			goto err;
 
-		if (!atomic_inc_not_zero(&cur->refcnt)) {
+		if (!refcount_inc_not_zero(&cur->refcnt)) {
 			module_put(THIS_MODULE);
 			goto err;
 		}
@@ -429,7 +430,7 @@ EXPORT_SYMBOL_GPL(nfnl_acct_find_get);
 
 void nfnl_acct_put(struct nf_acct *acct)
 {
-	if (atomic_dec_and_test(&acct->refcnt))
+	if (refcount_dec_and_test(&acct->refcnt))
 		kfree_rcu(acct, rcu_head);
 
 	module_put(THIS_MODULE);
@@ -502,7 +503,7 @@ static void __net_exit nfnl_acct_net_exit(struct net *net)
 	list_for_each_entry_safe(cur, tmp, &net->nfnl_acct_list, head) {
 		list_del_rcu(&cur->head);
 
-		if (atomic_dec_and_test(&cur->refcnt))
+		if (refcount_dec_and_test(&cur->refcnt))
 			kfree_rcu(cur, rcu_head);
 	}
 }
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 47d6656c9119..57c2cdf7b691 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -138,7 +138,7 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl,
 	strcpy(timeout->name, nla_data(cda[CTA_TIMEOUT_NAME]));
 	timeout->l3num = l3num;
 	timeout->l4proto = l4proto;
-	atomic_set(&timeout->refcnt, 1);
+	refcount_set(&timeout->refcnt, 1);
 	list_add_tail_rcu(&timeout->head, &net->nfct_timeout_list);
 
 	return 0;
@@ -172,7 +172,7 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 	    nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, htons(timeout->l3num)) ||
 	    nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, timeout->l4proto->l4proto) ||
 	    nla_put_be32(skb, CTA_TIMEOUT_USE,
-			 htonl(atomic_read(&timeout->refcnt))))
+			 htonl(refcount_read(&timeout->refcnt))))
 		goto nla_put_failure;
 
 	if (likely(l4proto->ctnl_timeout.obj_to_nlattr)) {
@@ -339,7 +339,7 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout)
 	/* We want to avoid races with ctnl_timeout_put. So only when the
 	 * current refcnt is 1, we decrease it to 0.
 	 */
-	if (atomic_cmpxchg(&timeout->refcnt, 1, 0) == 1) {
+	if (refcount_dec_if_one(&timeout->refcnt)) {
 		/* We are protected by nfnl mutex. */
 		list_del_rcu(&timeout->head);
 		nf_ct_l4proto_put(timeout->l4proto);
@@ -536,7 +536,7 @@ ctnl_timeout_find_get(struct net *net, const char *name)
 		if (!try_module_get(THIS_MODULE))
 			goto err;
 
-		if (!atomic_inc_not_zero(&timeout->refcnt)) {
+		if (!refcount_inc_not_zero(&timeout->refcnt)) {
 			module_put(THIS_MODULE);
 			goto err;
 		}
@@ -550,7 +550,7 @@ err:
 
 static void ctnl_timeout_put(struct ctnl_timeout *timeout)
 {
-	if (atomic_dec_and_test(&timeout->refcnt))
+	if (refcount_dec_and_test(&timeout->refcnt))
 		kfree_rcu(timeout, rcu_head);
 
 	module_put(THIS_MODULE);
@@ -601,7 +601,7 @@ static void __net_exit cttimeout_net_exit(struct net *net)
 		list_del_rcu(&cur->head);
 		nf_ct_l4proto_put(cur->l4proto);
 
-		if (atomic_dec_and_test(&cur->refcnt))
+		if (refcount_dec_and_test(&cur->refcnt))
 			kfree_rcu(cur, rcu_head);
 	}
 }
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 08247bf7d7b8..ecd857b75ffe 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -40,6 +40,8 @@
 #include <net/netfilter/nfnetlink_log.h>
 
 #include <linux/atomic.h>
+#include <linux/refcount.h>
+
 
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 #include "../bridge/br_private.h"
@@ -57,7 +59,7 @@
 struct nfulnl_instance {
 	struct hlist_node hlist;	/* global list of instances */
 	spinlock_t lock;
-	atomic_t use;			/* use count */
+	refcount_t use;			/* use count */
 
 	unsigned int qlen;		/* number of nlmsgs in skb */
 	struct sk_buff *skb;		/* pre-allocatd skb */
@@ -115,7 +117,7 @@ __instance_lookup(struct nfnl_log_net *log, u_int16_t group_num)
 static inline void
 instance_get(struct nfulnl_instance *inst)
 {
-	atomic_inc(&inst->use);
+	refcount_inc(&inst->use);
 }
 
 static struct nfulnl_instance *
@@ -125,7 +127,7 @@ instance_lookup_get(struct nfnl_log_net *log, u_int16_t group_num)
 
 	rcu_read_lock_bh();
 	inst = __instance_lookup(log, group_num);
-	if (inst && !atomic_inc_not_zero(&inst->use))
+	if (inst && !refcount_inc_not_zero(&inst->use))
 		inst = NULL;
 	rcu_read_unlock_bh();
 
@@ -145,7 +147,7 @@ static void nfulnl_instance_free_rcu(struct rcu_head *head)
 static void
 instance_put(struct nfulnl_instance *inst)
 {
-	if (inst && atomic_dec_and_test(&inst->use))
+	if (inst && refcount_dec_and_test(&inst->use))
 		call_rcu_bh(&inst->rcu, nfulnl_instance_free_rcu);
 }
 
@@ -180,7 +182,7 @@ instance_create(struct net *net, u_int16_t group_num,
 	INIT_HLIST_NODE(&inst->hlist);
 	spin_lock_init(&inst->lock);
 	/* needs to be two, since we _put() after creation */
-	atomic_set(&inst->use, 2);
+	refcount_set(&inst->use, 2);
 
 	setup_timer(&inst->timer, nfulnl_timer, (unsigned long)inst);
 
@@ -1031,7 +1033,7 @@ static int seq_show(struct seq_file *s, void *v)
 		   inst->group_num,
 		   inst->peer_portid, inst->qlen,
 		   inst->copy_mode, inst->copy_range,
-		   inst->flushtimeout, atomic_read(&inst->use));
+		   inst->flushtimeout, refcount_read(&inst->use));
 
 	return 0;
 }
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index c21e7eb8dce0..fab6bf3f955e 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -230,10 +230,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	union nft_entry e = {};
 	int ret;
 
-	ret = nft_compat_chain_validate_dependency(target->table, ctx->chain);
-	if (ret < 0)
-		goto err;
-
 	target_compat_from_user(target, nla_data(tb[NFTA_TARGET_INFO]), info);
 
 	if (ctx->nla[NFTA_RULE_COMPAT]) {
@@ -419,10 +415,6 @@ nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	union nft_entry e = {};
 	int ret;
 
-	ret = nft_compat_chain_validate_dependency(match->table, ctx->chain);
-	if (ret < 0)
-		goto err;
-
 	match_compat_from_user(match, nla_data(tb[NFTA_MATCH_INFO]), info);
 
 	if (ctx->nla[NFTA_RULE_COMPAT]) {
diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c
index 7f8422213341..67a710ebde09 100644
--- a/net/netfilter/nft_counter.c
+++ b/net/netfilter/nft_counter.c
@@ -82,7 +82,8 @@ static int nft_counter_do_init(const struct nlattr * const tb[],
 	return 0;
 }
 
-static int nft_counter_obj_init(const struct nlattr * const tb[],
+static int nft_counter_obj_init(const struct nft_ctx *ctx,
+				const struct nlattr * const tb[],
 				struct nft_object *obj)
 {
 	struct nft_counter_percpu_priv *priv = nft_obj_data(obj);
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 0264258c46fe..640fe5a5865e 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -32,6 +32,12 @@ struct nft_ct {
 	};
 };
 
+struct nft_ct_helper_obj  {
+	struct nf_conntrack_helper *helper4;
+	struct nf_conntrack_helper *helper6;
+	u8 l4proto;
+};
+
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 static DEFINE_PER_CPU(struct nf_conn *, nft_ct_pcpu_template);
 static unsigned int nft_ct_pcpu_template_refcnt __read_mostly;
@@ -733,6 +739,162 @@ static struct nft_expr_type nft_notrack_type __read_mostly = {
 	.owner		= THIS_MODULE,
 };
 
+static int nft_ct_helper_obj_init(const struct nft_ctx *ctx,
+				  const struct nlattr * const tb[],
+				  struct nft_object *obj)
+{
+	struct nft_ct_helper_obj *priv = nft_obj_data(obj);
+	struct nf_conntrack_helper *help4, *help6;
+	char name[NF_CT_HELPER_NAME_LEN];
+	int family = ctx->afi->family;
+
+	if (!tb[NFTA_CT_HELPER_NAME] || !tb[NFTA_CT_HELPER_L4PROTO])
+		return -EINVAL;
+
+	priv->l4proto = nla_get_u8(tb[NFTA_CT_HELPER_L4PROTO]);
+	if (!priv->l4proto)
+		return -ENOENT;
+
+	nla_strlcpy(name, tb[NFTA_CT_HELPER_NAME], sizeof(name));
+
+	if (tb[NFTA_CT_HELPER_L3PROTO])
+		family = ntohs(nla_get_be16(tb[NFTA_CT_HELPER_L3PROTO]));
+
+	help4 = NULL;
+	help6 = NULL;
+
+	switch (family) {
+	case NFPROTO_IPV4:
+		if (ctx->afi->family == NFPROTO_IPV6)
+			return -EINVAL;
+
+		help4 = nf_conntrack_helper_try_module_get(name, family,
+							   priv->l4proto);
+		break;
+	case NFPROTO_IPV6:
+		if (ctx->afi->family == NFPROTO_IPV4)
+			return -EINVAL;
+
+		help6 = nf_conntrack_helper_try_module_get(name, family,
+							   priv->l4proto);
+		break;
+	case NFPROTO_NETDEV: /* fallthrough */
+	case NFPROTO_BRIDGE: /* same */
+	case NFPROTO_INET:
+		help4 = nf_conntrack_helper_try_module_get(name, NFPROTO_IPV4,
+							   priv->l4proto);
+		help6 = nf_conntrack_helper_try_module_get(name, NFPROTO_IPV6,
+							   priv->l4proto);
+		break;
+	default:
+		return -EAFNOSUPPORT;
+	}
+
+	/* && is intentional; only error if INET found neither ipv4 or ipv6 */
+	if (!help4 && !help6)
+		return -ENOENT;
+
+	priv->helper4 = help4;
+	priv->helper6 = help6;
+
+	return 0;
+}
+
+static void nft_ct_helper_obj_destroy(struct nft_object *obj)
+{
+	struct nft_ct_helper_obj *priv = nft_obj_data(obj);
+
+	if (priv->helper4)
+		module_put(priv->helper4->me);
+	if (priv->helper6)
+		module_put(priv->helper6->me);
+}
+
+static void nft_ct_helper_obj_eval(struct nft_object *obj,
+				   struct nft_regs *regs,
+				   const struct nft_pktinfo *pkt)
+{
+	const struct nft_ct_helper_obj *priv = nft_obj_data(obj);
+	struct nf_conn *ct = (struct nf_conn *)skb_nfct(pkt->skb);
+	struct nf_conntrack_helper *to_assign = NULL;
+	struct nf_conn_help *help;
+
+	if (!ct ||
+	    nf_ct_is_confirmed(ct) ||
+	    nf_ct_is_template(ct) ||
+	    priv->l4proto != nf_ct_protonum(ct))
+		return;
+
+	switch (nf_ct_l3num(ct)) {
+	case NFPROTO_IPV4:
+		to_assign = priv->helper4;
+		break;
+	case NFPROTO_IPV6:
+		to_assign = priv->helper6;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	if (!to_assign)
+		return;
+
+	if (test_bit(IPS_HELPER_BIT, &ct->status))
+		return;
+
+	help = nf_ct_helper_ext_add(ct, to_assign, GFP_ATOMIC);
+	if (help) {
+		rcu_assign_pointer(help->helper, to_assign);
+		set_bit(IPS_HELPER_BIT, &ct->status);
+	}
+}
+
+static int nft_ct_helper_obj_dump(struct sk_buff *skb,
+				  struct nft_object *obj, bool reset)
+{
+	const struct nft_ct_helper_obj *priv = nft_obj_data(obj);
+	const struct nf_conntrack_helper *helper = priv->helper4;
+	u16 family;
+
+	if (nla_put_string(skb, NFTA_CT_HELPER_NAME, helper->name))
+		return -1;
+
+	if (nla_put_u8(skb, NFTA_CT_HELPER_L4PROTO, priv->l4proto))
+		return -1;
+
+	if (priv->helper4 && priv->helper6)
+		family = NFPROTO_INET;
+	else if (priv->helper6)
+		family = NFPROTO_IPV6;
+	else
+		family = NFPROTO_IPV4;
+
+	if (nla_put_be16(skb, NFTA_CT_HELPER_L3PROTO, htons(family)))
+		return -1;
+
+	return 0;
+}
+
+static const struct nla_policy nft_ct_helper_policy[NFTA_CT_HELPER_MAX + 1] = {
+	[NFTA_CT_HELPER_NAME] = { .type = NLA_STRING,
+				  .len = NF_CT_HELPER_NAME_LEN - 1 },
+	[NFTA_CT_HELPER_L3PROTO] = { .type = NLA_U16 },
+	[NFTA_CT_HELPER_L4PROTO] = { .type = NLA_U8 },
+};
+
+static struct nft_object_type nft_ct_helper_obj __read_mostly = {
+	.type		= NFT_OBJECT_CT_HELPER,
+	.size		= sizeof(struct nft_ct_helper_obj),
+	.maxattr	= NFTA_CT_HELPER_MAX,
+	.policy		= nft_ct_helper_policy,
+	.eval		= nft_ct_helper_obj_eval,
+	.init		= nft_ct_helper_obj_init,
+	.destroy	= nft_ct_helper_obj_destroy,
+	.dump		= nft_ct_helper_obj_dump,
+	.owner		= THIS_MODULE,
+};
+
 static int __init nft_ct_module_init(void)
 {
 	int err;
@@ -747,7 +909,14 @@ static int __init nft_ct_module_init(void)
 	if (err < 0)
 		goto err1;
 
+	err = nft_register_obj(&nft_ct_helper_obj);
+	if (err < 0)
+		goto err2;
+
 	return 0;
+
+err2:
+	nft_unregister_expr(&nft_notrack_type);
 err1:
 	nft_unregister_expr(&nft_ct_type);
 	return err;
@@ -755,6 +924,7 @@ err1:
 
 static void __exit nft_ct_module_exit(void)
 {
+	nft_unregister_obj(&nft_ct_helper_obj);
 	nft_unregister_expr(&nft_notrack_type);
 	nft_unregister_expr(&nft_ct_type);
 }
@@ -766,3 +936,4 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
 MODULE_ALIAS_NFT_EXPR("ct");
 MODULE_ALIAS_NFT_EXPR("notrack");
+MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CT_HELPER);
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 049ad2d9ee66..3948da380259 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -133,16 +133,10 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 			priv->invert = true;
 	}
 
-	set = nf_tables_set_lookup(ctx->table, tb[NFTA_DYNSET_SET_NAME],
-				   genmask);
-	if (IS_ERR(set)) {
-		if (tb[NFTA_DYNSET_SET_ID])
-			set = nf_tables_set_lookup_byid(ctx->net,
-							tb[NFTA_DYNSET_SET_ID],
-							genmask);
-		if (IS_ERR(set))
-			return PTR_ERR(set);
-	}
+	set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_DYNSET_SET_NAME],
+			     tb[NFTA_DYNSET_SET_ID], genmask);
+	if (IS_ERR(set))
+		return PTR_ERR(set);
 
 	if (set->ops->update == NULL)
 		return -EOPNOTSUPP;
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index c308920b194c..d212a85d2f33 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -98,14 +98,21 @@ static void nft_exthdr_tcp_eval(const struct nft_expr *expr,
 			goto err;
 
 		offset = i + priv->offset;
-		dest[priv->len / NFT_REG32_SIZE] = 0;
-		memcpy(dest, opt + offset, priv->len);
+		if (priv->flags & NFT_EXTHDR_F_PRESENT) {
+			*dest = 1;
+		} else {
+			dest[priv->len / NFT_REG32_SIZE] = 0;
+			memcpy(dest, opt + offset, priv->len);
+		}
 
 		return;
 	}
 
 err:
-	regs->verdict.code = NFT_BREAK;
+	if (priv->flags & NFT_EXTHDR_F_PRESENT)
+		*dest = 0;
+	else
+		regs->verdict.code = NFT_BREAK;
 }
 
 static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = {
diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c
index 29a4906adc27..21df8cccea65 100644
--- a/net/netfilter/nft_fib.c
+++ b/net/netfilter/nft_fib.c
@@ -24,7 +24,8 @@ const struct nla_policy nft_fib_policy[NFTA_FIB_MAX + 1] = {
 EXPORT_SYMBOL(nft_fib_policy);
 
 #define NFTA_FIB_F_ALL (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR | \
-			NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF)
+			NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF | \
+			NFTA_FIB_F_PRESENT)
 
 int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		     const struct nft_data **data)
@@ -112,7 +113,7 @@ int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	if (err < 0)
 		return err;
 
-	return nft_fib_validate(ctx, expr, NULL);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(nft_fib_init);
 
@@ -133,19 +134,22 @@ int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr)
 }
 EXPORT_SYMBOL_GPL(nft_fib_dump);
 
-void nft_fib_store_result(void *reg, enum nft_fib_result r,
+void nft_fib_store_result(void *reg, const struct nft_fib *priv,
 			  const struct nft_pktinfo *pkt, int index)
 {
 	struct net_device *dev;
 	u32 *dreg = reg;
 
-	switch (r) {
+	switch (priv->result) {
 	case NFT_FIB_RESULT_OIF:
-		*dreg = index;
+		*dreg = (priv->flags & NFTA_FIB_F_PRESENT) ? !!index : index;
 		break;
 	case NFT_FIB_RESULT_OIFNAME:
 		dev = dev_get_by_index_rcu(nft_net(pkt), index);
-		strncpy(reg, dev ? dev->name : "", IFNAMSIZ);
+		if (priv->flags & NFTA_FIB_F_PRESENT)
+			*dreg = !!dev;
+		else
+			strncpy(reg, dev ? dev->name : "", IFNAMSIZ);
 		break;
 	default:
 		WARN_ON_ONCE(1);
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index eb2721af898d..a6a4633725bb 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -17,7 +17,7 @@
 #include <net/netfilter/nf_tables_core.h>
 #include <linux/jhash.h>
 
-struct nft_hash {
+struct nft_jhash {
 	enum nft_registers      sreg:8;
 	enum nft_registers      dreg:8;
 	u8			len;
@@ -26,11 +26,11 @@ struct nft_hash {
 	u32			offset;
 };
 
-static void nft_hash_eval(const struct nft_expr *expr,
-			  struct nft_regs *regs,
-			  const struct nft_pktinfo *pkt)
+static void nft_jhash_eval(const struct nft_expr *expr,
+			   struct nft_regs *regs,
+			   const struct nft_pktinfo *pkt)
 {
-	struct nft_hash *priv = nft_expr_priv(expr);
+	struct nft_jhash *priv = nft_expr_priv(expr);
 	const void *data = &regs->data[priv->sreg];
 	u32 h;
 
@@ -38,6 +38,25 @@ static void nft_hash_eval(const struct nft_expr *expr,
 	regs->data[priv->dreg] = h + priv->offset;
 }
 
+struct nft_symhash {
+	enum nft_registers      dreg:8;
+	u32			modulus;
+	u32			offset;
+};
+
+static void nft_symhash_eval(const struct nft_expr *expr,
+			     struct nft_regs *regs,
+			     const struct nft_pktinfo *pkt)
+{
+	struct nft_symhash *priv = nft_expr_priv(expr);
+	struct sk_buff *skb = pkt->skb;
+	u32 h;
+
+	h = reciprocal_scale(__skb_get_hash_symmetric(skb), priv->modulus);
+
+	regs->data[priv->dreg] = h + priv->offset;
+}
+
 static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = {
 	[NFTA_HASH_SREG]	= { .type = NLA_U32 },
 	[NFTA_HASH_DREG]	= { .type = NLA_U32 },
@@ -45,13 +64,14 @@ static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = {
 	[NFTA_HASH_MODULUS]	= { .type = NLA_U32 },
 	[NFTA_HASH_SEED]	= { .type = NLA_U32 },
 	[NFTA_HASH_OFFSET]	= { .type = NLA_U32 },
+	[NFTA_HASH_TYPE]	= { .type = NLA_U32 },
 };
 
-static int nft_hash_init(const struct nft_ctx *ctx,
-			 const struct nft_expr *expr,
-			 const struct nlattr * const tb[])
+static int nft_jhash_init(const struct nft_ctx *ctx,
+			  const struct nft_expr *expr,
+			  const struct nlattr * const tb[])
 {
-	struct nft_hash *priv = nft_expr_priv(expr);
+	struct nft_jhash *priv = nft_expr_priv(expr);
 	u32 len;
 	int err;
 
@@ -92,10 +112,36 @@ static int nft_hash_init(const struct nft_ctx *ctx,
 					   NFT_DATA_VALUE, sizeof(u32));
 }
 
-static int nft_hash_dump(struct sk_buff *skb,
-			 const struct nft_expr *expr)
+static int nft_symhash_init(const struct nft_ctx *ctx,
+			    const struct nft_expr *expr,
+			    const struct nlattr * const tb[])
 {
-	const struct nft_hash *priv = nft_expr_priv(expr);
+	struct nft_symhash *priv = nft_expr_priv(expr);
+
+	if (!tb[NFTA_HASH_DREG]    ||
+	    !tb[NFTA_HASH_MODULUS])
+		return -EINVAL;
+
+	if (tb[NFTA_HASH_OFFSET])
+		priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET]));
+
+	priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]);
+
+	priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS]));
+	if (priv->modulus <= 1)
+		return -ERANGE;
+
+	if (priv->offset + priv->modulus - 1 < priv->offset)
+		return -EOVERFLOW;
+
+	return nft_validate_register_store(ctx, priv->dreg, NULL,
+					   NFT_DATA_VALUE, sizeof(u32));
+}
+
+static int nft_jhash_dump(struct sk_buff *skb,
+			  const struct nft_expr *expr)
+{
+	const struct nft_jhash *priv = nft_expr_priv(expr);
 
 	if (nft_dump_register(skb, NFTA_HASH_SREG, priv->sreg))
 		goto nla_put_failure;
@@ -110,6 +156,28 @@ static int nft_hash_dump(struct sk_buff *skb,
 	if (priv->offset != 0)
 		if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset)))
 			goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_HASH_TYPE, htonl(NFT_HASH_JENKINS)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static int nft_symhash_dump(struct sk_buff *skb,
+			    const struct nft_expr *expr)
+{
+	const struct nft_symhash *priv = nft_expr_priv(expr);
+
+	if (nft_dump_register(skb, NFTA_HASH_DREG, priv->dreg))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_HASH_MODULUS, htonl(priv->modulus)))
+		goto nla_put_failure;
+	if (priv->offset != 0)
+		if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset)))
+			goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_HASH_TYPE, htonl(NFT_HASH_SYM)))
+		goto nla_put_failure;
 	return 0;
 
 nla_put_failure:
@@ -117,17 +185,46 @@ nla_put_failure:
 }
 
 static struct nft_expr_type nft_hash_type;
-static const struct nft_expr_ops nft_hash_ops = {
+static const struct nft_expr_ops nft_jhash_ops = {
 	.type		= &nft_hash_type,
-	.size		= NFT_EXPR_SIZE(sizeof(struct nft_hash)),
-	.eval		= nft_hash_eval,
-	.init		= nft_hash_init,
-	.dump		= nft_hash_dump,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_jhash)),
+	.eval		= nft_jhash_eval,
+	.init		= nft_jhash_init,
+	.dump		= nft_jhash_dump,
 };
 
+static const struct nft_expr_ops nft_symhash_ops = {
+	.type		= &nft_hash_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_symhash)),
+	.eval		= nft_symhash_eval,
+	.init		= nft_symhash_init,
+	.dump		= nft_symhash_dump,
+};
+
+static const struct nft_expr_ops *
+nft_hash_select_ops(const struct nft_ctx *ctx,
+		    const struct nlattr * const tb[])
+{
+	u32 type;
+
+	if (!tb[NFTA_HASH_TYPE])
+		return &nft_jhash_ops;
+
+	type = ntohl(nla_get_be32(tb[NFTA_HASH_TYPE]));
+	switch (type) {
+	case NFT_HASH_SYM:
+		return &nft_symhash_ops;
+	case NFT_HASH_JENKINS:
+		return &nft_jhash_ops;
+	default:
+		break;
+	}
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
 static struct nft_expr_type nft_hash_type __read_mostly = {
 	.name		= "hash",
-	.ops		= &nft_hash_ops,
+	.select_ops	= &nft_hash_select_ops,
 	.policy		= nft_hash_policy,
 	.maxattr	= NFTA_HASH_MAX,
 	.owner		= THIS_MODULE,
diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c
index c6baf412236d..18dd57a52651 100644
--- a/net/netfilter/nft_limit.c
+++ b/net/netfilter/nft_limit.c
@@ -17,9 +17,8 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 
-static DEFINE_SPINLOCK(limit_lock);
-
 struct nft_limit {
+	spinlock_t	lock;
 	u64		last;
 	u64		tokens;
 	u64		tokens_max;
@@ -34,7 +33,7 @@ static inline bool nft_limit_eval(struct nft_limit *limit, u64 cost)
 	u64 now, tokens;
 	s64 delta;
 
-	spin_lock_bh(&limit_lock);
+	spin_lock_bh(&limit->lock);
 	now = ktime_get_ns();
 	tokens = limit->tokens + now - limit->last;
 	if (tokens > limit->tokens_max)
@@ -44,11 +43,11 @@ static inline bool nft_limit_eval(struct nft_limit *limit, u64 cost)
 	delta = tokens - cost;
 	if (delta >= 0) {
 		limit->tokens = delta;
-		spin_unlock_bh(&limit_lock);
+		spin_unlock_bh(&limit->lock);
 		return limit->invert;
 	}
 	limit->tokens = tokens;
-	spin_unlock_bh(&limit_lock);
+	spin_unlock_bh(&limit->lock);
 	return !limit->invert;
 }
 
@@ -86,6 +85,7 @@ static int nft_limit_init(struct nft_limit *limit,
 			limit->invert = true;
 	}
 	limit->last = ktime_get_ns();
+	spin_lock_init(&limit->lock);
 
 	return 0;
 }
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index e21aea7e5ec8..475570e89ede 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -71,16 +71,10 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
 	    tb[NFTA_LOOKUP_SREG] == NULL)
 		return -EINVAL;
 
-	set = nf_tables_set_lookup(ctx->table, tb[NFTA_LOOKUP_SET], genmask);
-	if (IS_ERR(set)) {
-		if (tb[NFTA_LOOKUP_SET_ID]) {
-			set = nf_tables_set_lookup_byid(ctx->net,
-							tb[NFTA_LOOKUP_SET_ID],
-							genmask);
-		}
-		if (IS_ERR(set))
-			return PTR_ERR(set);
-	}
+	set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_LOOKUP_SET],
+			     tb[NFTA_LOOKUP_SET_ID], genmask);
+	if (IS_ERR(set))
+		return PTR_ERR(set);
 
 	if (set->flags & NFT_SET_EVAL)
 		return -EOPNOTSUPP;
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
index 11ce016cd479..6ac03d4266c9 100644
--- a/net/netfilter/nft_masq.c
+++ b/net/netfilter/nft_masq.c
@@ -46,10 +46,6 @@ int nft_masq_init(const struct nft_ctx *ctx,
 	struct nft_masq *priv = nft_expr_priv(expr);
 	int err;
 
-	err = nft_masq_validate(ctx, expr, NULL);
-	if (err)
-		return err;
-
 	if (tb[NFTA_MASQ_FLAGS]) {
 		priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS]));
 		if (priv->flags & ~NF_NAT_RANGE_MASK)
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 7b60e01f38ff..9563ce3c23aa 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -372,10 +372,6 @@ int nft_meta_set_init(const struct nft_ctx *ctx,
 		return -EOPNOTSUPP;
 	}
 
-	err = nft_meta_set_validate(ctx, expr, NULL);
-	if (err < 0)
-		return err;
-
 	priv->sreg = nft_parse_register(tb[NFTA_META_SREG]);
 	err = nft_validate_register_load(priv->sreg, len);
 	if (err < 0)
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index 439e0bd152a0..ed548d06b6dd 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -138,10 +138,6 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		return -EINVAL;
 	}
 
-	err = nft_nat_validate(ctx, expr, NULL);
-	if (err < 0)
-		return err;
-
 	if (tb[NFTA_NAT_FAMILY] == NULL)
 		return -EINVAL;
 
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index 1ae8c49ca4a1..1dd428fbaaa3 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -116,16 +116,10 @@ static int nft_objref_map_init(const struct nft_ctx *ctx,
 	struct nft_set *set;
 	int err;
 
-	set = nf_tables_set_lookup(ctx->table, tb[NFTA_OBJREF_SET_NAME], genmask);
-	if (IS_ERR(set)) {
-		if (tb[NFTA_OBJREF_SET_ID]) {
-			set = nf_tables_set_lookup_byid(ctx->net,
-							tb[NFTA_OBJREF_SET_ID],
-							genmask);
-		}
-		if (IS_ERR(set))
-			return PTR_ERR(set);
-	}
+	set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_OBJREF_SET_NAME],
+			     tb[NFTA_OBJREF_SET_ID], genmask);
+	if (IS_ERR(set))
+		return PTR_ERR(set);
 
 	if (!(set->flags & NFT_SET_OBJECT))
 		return -EINVAL;
diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c
index 2d6fe3559912..25e33159be57 100644
--- a/net/netfilter/nft_quota.c
+++ b/net/netfilter/nft_quota.c
@@ -99,7 +99,8 @@ static int nft_quota_do_init(const struct nlattr * const tb[],
 	return 0;
 }
 
-static int nft_quota_obj_init(const struct nlattr * const tb[],
+static int nft_quota_obj_init(const struct nft_ctx *ctx,
+			      const struct nlattr * const tb[],
 			      struct nft_object *obj)
 {
 	struct nft_quota *priv = nft_obj_data(obj);
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
index 40dcd05146d5..1e66538bf0ff 100644
--- a/net/netfilter/nft_redir.c
+++ b/net/netfilter/nft_redir.c
@@ -47,10 +47,6 @@ int nft_redir_init(const struct nft_ctx *ctx,
 	unsigned int plen;
 	int err;
 
-	err = nft_redir_validate(ctx, expr, NULL);
-	if (err < 0)
-		return err;
-
 	plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all);
 	if (tb[NFTA_REDIR_REG_PROTO_MIN]) {
 		priv->sreg_proto_min =
diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c
index c64de3f7379d..29f5bd2377b0 100644
--- a/net/netfilter/nft_reject.c
+++ b/net/netfilter/nft_reject.c
@@ -42,11 +42,6 @@ int nft_reject_init(const struct nft_ctx *ctx,
 		    const struct nlattr * const tb[])
 {
 	struct nft_reject *priv = nft_expr_priv(expr);
-	int err;
-
-	err = nft_reject_validate(ctx, expr, NULL);
-	if (err < 0)
-		return err;
 
 	if (tb[NFTA_REJECT_TYPE] == NULL)
 		return -EINVAL;
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
index 9e90a02cb104..5a7fb5ff867d 100644
--- a/net/netfilter/nft_reject_inet.c
+++ b/net/netfilter/nft_reject_inet.c
@@ -66,11 +66,7 @@ static int nft_reject_inet_init(const struct nft_ctx *ctx,
 				const struct nlattr * const tb[])
 {
 	struct nft_reject *priv = nft_expr_priv(expr);
-	int icmp_code, err;
-
-	err = nft_reject_validate(ctx, expr, NULL);
-	if (err < 0)
-		return err;
+	int icmp_code;
 
 	if (tb[NFTA_REJECT_TYPE] == NULL)
 		return -EINVAL;
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 78dfbf9588b3..e97e2fb53f0a 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -18,9 +18,8 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 
-static DEFINE_SPINLOCK(nft_rbtree_lock);
-
 struct nft_rbtree {
+	rwlock_t		lock;
 	struct rb_root		root;
 };
 
@@ -44,14 +43,14 @@ static bool nft_rbtree_equal(const struct nft_set *set, const void *this,
 static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
 			      const u32 *key, const struct nft_set_ext **ext)
 {
-	const struct nft_rbtree *priv = nft_set_priv(set);
+	struct nft_rbtree *priv = nft_set_priv(set);
 	const struct nft_rbtree_elem *rbe, *interval = NULL;
 	u8 genmask = nft_genmask_cur(net);
 	const struct rb_node *parent;
 	const void *this;
 	int d;
 
-	spin_lock_bh(&nft_rbtree_lock);
+	read_lock_bh(&priv->lock);
 	parent = priv->root.rb_node;
 	while (parent != NULL) {
 		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
@@ -75,7 +74,7 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
 			}
 			if (nft_rbtree_interval_end(rbe))
 				goto out;
-			spin_unlock_bh(&nft_rbtree_lock);
+			read_unlock_bh(&priv->lock);
 
 			*ext = &rbe->ext;
 			return true;
@@ -85,12 +84,12 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
 	if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
 	    nft_set_elem_active(&interval->ext, genmask) &&
 	    !nft_rbtree_interval_end(interval)) {
-		spin_unlock_bh(&nft_rbtree_lock);
+		read_unlock_bh(&priv->lock);
 		*ext = &interval->ext;
 		return true;
 	}
 out:
-	spin_unlock_bh(&nft_rbtree_lock);
+	read_unlock_bh(&priv->lock);
 	return false;
 }
 
@@ -140,12 +139,13 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 			     const struct nft_set_elem *elem,
 			     struct nft_set_ext **ext)
 {
+	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe = elem->priv;
 	int err;
 
-	spin_lock_bh(&nft_rbtree_lock);
+	write_lock_bh(&priv->lock);
 	err = __nft_rbtree_insert(net, set, rbe, ext);
-	spin_unlock_bh(&nft_rbtree_lock);
+	write_unlock_bh(&priv->lock);
 
 	return err;
 }
@@ -157,9 +157,9 @@ static void nft_rbtree_remove(const struct net *net,
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe = elem->priv;
 
-	spin_lock_bh(&nft_rbtree_lock);
+	write_lock_bh(&priv->lock);
 	rb_erase(&rbe->node, &priv->root);
-	spin_unlock_bh(&nft_rbtree_lock);
+	write_unlock_bh(&priv->lock);
 }
 
 static void nft_rbtree_activate(const struct net *net,
@@ -224,12 +224,12 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 			    struct nft_set *set,
 			    struct nft_set_iter *iter)
 {
-	const struct nft_rbtree *priv = nft_set_priv(set);
+	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe;
 	struct nft_set_elem elem;
 	struct rb_node *node;
 
-	spin_lock_bh(&nft_rbtree_lock);
+	read_lock_bh(&priv->lock);
 	for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
 
@@ -242,13 +242,13 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 
 		iter->err = iter->fn(ctx, set, iter, &elem);
 		if (iter->err < 0) {
-			spin_unlock_bh(&nft_rbtree_lock);
+			read_unlock_bh(&priv->lock);
 			return;
 		}
 cont:
 		iter->count++;
 	}
-	spin_unlock_bh(&nft_rbtree_lock);
+	read_unlock_bh(&priv->lock);
 }
 
 static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[])
@@ -262,6 +262,7 @@ static int nft_rbtree_init(const struct nft_set *set,
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 
+	rwlock_init(&priv->lock);
 	priv->root = RB_ROOT;
 	return 0;
 }
diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c
index dab962df1787..d27b5f1ea619 100644
--- a/net/netfilter/xt_limit.c
+++ b/net/netfilter/xt_limit.c
@@ -18,6 +18,7 @@
 #include <linux/netfilter/xt_limit.h>
 
 struct xt_limit_priv {
+	spinlock_t lock;
 	unsigned long prev;
 	uint32_t credit;
 };
@@ -32,8 +33,6 @@ MODULE_ALIAS("ip6t_limit");
  * see net/sched/sch_tbf.c in the linux source tree
  */
 
-static DEFINE_SPINLOCK(limit_lock);
-
 /* Rusty: This is my (non-mathematically-inclined) understanding of
    this algorithm.  The `average rate' in jiffies becomes your initial
    amount of credit `credit' and the most credit you can ever have
@@ -72,7 +71,7 @@ limit_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	struct xt_limit_priv *priv = r->master;
 	unsigned long now = jiffies;
 
-	spin_lock_bh(&limit_lock);
+	spin_lock_bh(&priv->lock);
 	priv->credit += (now - xchg(&priv->prev, now)) * CREDITS_PER_JIFFY;
 	if (priv->credit > r->credit_cap)
 		priv->credit = r->credit_cap;
@@ -80,11 +79,11 @@ limit_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	if (priv->credit >= r->cost) {
 		/* We're not limited. */
 		priv->credit -= r->cost;
-		spin_unlock_bh(&limit_lock);
+		spin_unlock_bh(&priv->lock);
 		return true;
 	}
 
-	spin_unlock_bh(&limit_lock);
+	spin_unlock_bh(&priv->lock);
 	return false;
 }
 
@@ -126,6 +125,8 @@ static int limit_mt_check(const struct xt_mtchk_param *par)
 		r->credit_cap = priv->credit; /* Credits full. */
 		r->cost = user2credits(r->avg);
 	}
+	spin_lock_init(&priv->lock);
+
 	return 0;
 }
 
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 596eaff66649..fc232441cf23 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -78,14 +78,6 @@ struct listeners {
 /* state bits */
 #define NETLINK_S_CONGESTED		0x0
 
-/* flags */
-#define NETLINK_F_KERNEL_SOCKET		0x1
-#define NETLINK_F_RECV_PKTINFO		0x2
-#define NETLINK_F_BROADCAST_SEND_ERROR	0x4
-#define NETLINK_F_RECV_NO_ENOBUFS	0x8
-#define NETLINK_F_LISTEN_ALL_NSID	0x10
-#define NETLINK_F_CAP_ACK		0x20
-
 static inline int netlink_is_kernel(struct sock *sk)
 {
 	return nlk_sk(sk)->flags & NETLINK_F_KERNEL_SOCKET;
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 4fdb38318977..f792f8d7f982 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -6,6 +6,14 @@
 #include <linux/workqueue.h>
 #include <net/sock.h>
 
+/* flags */
+#define NETLINK_F_KERNEL_SOCKET		0x1
+#define NETLINK_F_RECV_PKTINFO		0x2
+#define NETLINK_F_BROADCAST_SEND_ERROR	0x4
+#define NETLINK_F_RECV_NO_ENOBUFS	0x8
+#define NETLINK_F_LISTEN_ALL_NSID	0x10
+#define NETLINK_F_CAP_ACK		0x20
+
 #define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
 #define NLGRPLONGS(x)	(NLGRPSZ(x)/sizeof(unsigned long))
 
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index a5546249fb10..8faa20b4d457 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -19,6 +19,27 @@ static int sk_diag_dump_groups(struct sock *sk, struct sk_buff *nlskb)
 		       nlk->groups);
 }
 
+static int sk_diag_put_flags(struct sock *sk, struct sk_buff *skb)
+{
+	struct netlink_sock *nlk = nlk_sk(sk);
+	u32 flags = 0;
+
+	if (nlk->cb_running)
+		flags |= NDIAG_FLAG_CB_RUNNING;
+	if (nlk->flags & NETLINK_F_RECV_PKTINFO)
+		flags |= NDIAG_FLAG_PKTINFO;
+	if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR)
+		flags |= NDIAG_FLAG_BROADCAST_ERROR;
+	if (nlk->flags & NETLINK_F_RECV_NO_ENOBUFS)
+		flags |= NDIAG_FLAG_NO_ENOBUFS;
+	if (nlk->flags & NETLINK_F_LISTEN_ALL_NSID)
+		flags |= NDIAG_FLAG_LISTEN_ALL_NSID;
+	if (nlk->flags & NETLINK_F_CAP_ACK)
+		flags |= NDIAG_FLAG_CAP_ACK;
+
+	return nla_put_u32(skb, NETLINK_DIAG_FLAGS, flags);
+}
+
 static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 			struct netlink_diag_req *req,
 			u32 portid, u32 seq, u32 flags, int sk_ino)
@@ -52,6 +73,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 	    sock_diag_put_meminfo(sk, skb, NETLINK_DIAG_MEMINFO))
 		goto out_nlmsg_trim;
 
+	if ((req->ndiag_show & NDIAG_SHOW_FLAGS) &&
+	    sk_diag_put_flags(sk, skb))
+		goto out_nlmsg_trim;
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index c82301ce3fff..e4610676299b 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007-2014 Nicira, Inc.
+ * Copyright (c) 2007-2017 Nicira, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -44,13 +44,10 @@
 #include "conntrack.h"
 #include "vport.h"
 
-static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
-			      struct sw_flow_key *key,
-			      const struct nlattr *attr, int len);
-
 struct deferred_action {
 	struct sk_buff *skb;
 	const struct nlattr *actions;
+	int actions_len;
 
 	/* Store pkt_key clone when creating deferred action. */
 	struct sw_flow_key pkt_key;
@@ -82,14 +79,31 @@ struct action_fifo {
 	struct deferred_action fifo[DEFERRED_ACTION_FIFO_SIZE];
 };
 
-struct recirc_keys {
+struct action_flow_keys {
 	struct sw_flow_key key[OVS_DEFERRED_ACTION_THRESHOLD];
 };
 
 static struct action_fifo __percpu *action_fifos;
-static struct recirc_keys __percpu *recirc_keys;
+static struct action_flow_keys __percpu *flow_keys;
 static DEFINE_PER_CPU(int, exec_actions_level);
 
+/* Make a clone of the 'key', using the pre-allocated percpu 'flow_keys'
+ * space. Return NULL if out of key spaces.
+ */
+static struct sw_flow_key *clone_key(const struct sw_flow_key *key_)
+{
+	struct action_flow_keys *keys = this_cpu_ptr(flow_keys);
+	int level = this_cpu_read(exec_actions_level);
+	struct sw_flow_key *key = NULL;
+
+	if (level <= OVS_DEFERRED_ACTION_THRESHOLD) {
+		key = &keys->key[level - 1];
+		*key = *key_;
+	}
+
+	return key;
+}
+
 static void action_fifo_init(struct action_fifo *fifo)
 {
 	fifo->head = 0;
@@ -119,8 +133,9 @@ static struct deferred_action *action_fifo_put(struct action_fifo *fifo)
 
 /* Return true if fifo is not full */
 static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
-						    const struct sw_flow_key *key,
-						    const struct nlattr *attr)
+				    const struct sw_flow_key *key,
+				    const struct nlattr *actions,
+				    const int actions_len)
 {
 	struct action_fifo *fifo;
 	struct deferred_action *da;
@@ -129,7 +144,8 @@ static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
 	da = action_fifo_put(fifo);
 	if (da) {
 		da->skb = skb;
-		da->actions = attr;
+		da->actions = actions;
+		da->actions_len = actions_len;
 		da->pkt_key = *key;
 	}
 
@@ -146,6 +162,12 @@ static bool is_flow_key_valid(const struct sw_flow_key *key)
 	return !(key->mac_proto & SW_FLOW_KEY_INVALID);
 }
 
+static int clone_execute(struct datapath *dp, struct sk_buff *skb,
+			 struct sw_flow_key *key,
+			 u32 recirc_id,
+			 const struct nlattr *actions, int len,
+			 bool last, bool clone_flow_key);
+
 static void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr,
 			     __be16 ethertype)
 {
@@ -908,72 +930,35 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 	return ovs_dp_upcall(dp, skb, key, &upcall, cutlen);
 }
 
+/* When 'last' is true, sample() should always consume the 'skb'.
+ * Otherwise, sample() should keep 'skb' intact regardless what
+ * actions are executed within sample().
+ */
 static int sample(struct datapath *dp, struct sk_buff *skb,
 		  struct sw_flow_key *key, const struct nlattr *attr,
-		  const struct nlattr *actions, int actions_len)
+		  bool last)
 {
-	const struct nlattr *acts_list = NULL;
-	const struct nlattr *a;
-	int rem;
-	u32 cutlen = 0;
-
-	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
-		 a = nla_next(a, &rem)) {
-		u32 probability;
-
-		switch (nla_type(a)) {
-		case OVS_SAMPLE_ATTR_PROBABILITY:
-			probability = nla_get_u32(a);
-			if (!probability || prandom_u32() > probability)
-				return 0;
-			break;
-
-		case OVS_SAMPLE_ATTR_ACTIONS:
-			acts_list = a;
-			break;
-		}
-	}
-
-	rem = nla_len(acts_list);
-	a = nla_data(acts_list);
-
-	/* Actions list is empty, do nothing */
-	if (unlikely(!rem))
+	struct nlattr *actions;
+	struct nlattr *sample_arg;
+	int rem = nla_len(attr);
+	const struct sample_arg *arg;
+	bool clone_flow_key;
+
+	/* The first action is always 'OVS_SAMPLE_ATTR_ARG'. */
+	sample_arg = nla_data(attr);
+	arg = nla_data(sample_arg);
+	actions = nla_next(sample_arg, &rem);
+
+	if ((arg->probability != U32_MAX) &&
+	    (!arg->probability || prandom_u32() > arg->probability)) {
+		if (last)
+			consume_skb(skb);
 		return 0;
-
-	/* The only known usage of sample action is having a single user-space
-	 * action, or having a truncate action followed by a single user-space
-	 * action. Treat this usage as a special case.
-	 * The output_userspace() should clone the skb to be sent to the
-	 * user space. This skb will be consumed by its caller.
-	 */
-	if (unlikely(nla_type(a) == OVS_ACTION_ATTR_TRUNC)) {
-		struct ovs_action_trunc *trunc = nla_data(a);
-
-		if (skb->len > trunc->max_len)
-			cutlen = skb->len - trunc->max_len;
-
-		a = nla_next(a, &rem);
 	}
 
-	if (likely(nla_type(a) == OVS_ACTION_ATTR_USERSPACE &&
-		   nla_is_last(a, rem)))
-		return output_userspace(dp, skb, key, a, actions,
-					actions_len, cutlen);
-
-	skb = skb_clone(skb, GFP_ATOMIC);
-	if (!skb)
-		/* Skip the sample action when out of memory. */
-		return 0;
-
-	if (!add_deferred_actions(skb, key, a)) {
-		if (net_ratelimit())
-			pr_warn("%s: deferred actions limit reached, dropping sample action\n",
-				ovs_dp_name(dp));
-
-		kfree_skb(skb);
-	}
-	return 0;
+	clone_flow_key = !arg->exec;
+	return clone_execute(dp, skb, key, 0, actions, rem, last,
+			     clone_flow_key);
 }
 
 static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key,
@@ -1084,10 +1069,9 @@ static int execute_masked_set_action(struct sk_buff *skb,
 
 static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
 			  struct sw_flow_key *key,
-			  const struct nlattr *a, int rem)
+			  const struct nlattr *a, bool last)
 {
-	struct deferred_action *da;
-	int level;
+	u32 recirc_id;
 
 	if (!is_flow_key_valid(key)) {
 		int err;
@@ -1098,43 +1082,8 @@ static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
 	}
 	BUG_ON(!is_flow_key_valid(key));
 
-	if (!nla_is_last(a, rem)) {
-		/* Recirc action is the not the last action
-		 * of the action list, need to clone the skb.
-		 */
-		skb = skb_clone(skb, GFP_ATOMIC);
-
-		/* Skip the recirc action when out of memory, but
-		 * continue on with the rest of the action list.
-		 */
-		if (!skb)
-			return 0;
-	}
-
-	level = this_cpu_read(exec_actions_level);
-	if (level <= OVS_DEFERRED_ACTION_THRESHOLD) {
-		struct recirc_keys *rks = this_cpu_ptr(recirc_keys);
-		struct sw_flow_key *recirc_key = &rks->key[level - 1];
-
-		*recirc_key = *key;
-		recirc_key->recirc_id = nla_get_u32(a);
-		ovs_dp_process_packet(skb, recirc_key);
-
-		return 0;
-	}
-
-	da = add_deferred_actions(skb, key, NULL);
-	if (da) {
-		da->pkt_key.recirc_id = nla_get_u32(a);
-	} else {
-		kfree_skb(skb);
-
-		if (net_ratelimit())
-			pr_warn("%s: deferred action limit reached, drop recirc action\n",
-				ovs_dp_name(dp));
-	}
-
-	return 0;
+	recirc_id = nla_get_u32(a);
+	return clone_execute(dp, skb, key, recirc_id, NULL, 0, last, true);
 }
 
 /* Execute a list of actions against 'skb'. */
@@ -1206,9 +1155,11 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			err = pop_vlan(skb, key);
 			break;
 
-		case OVS_ACTION_ATTR_RECIRC:
-			err = execute_recirc(dp, skb, key, a, rem);
-			if (nla_is_last(a, rem)) {
+		case OVS_ACTION_ATTR_RECIRC: {
+			bool last = nla_is_last(a, rem);
+
+			err = execute_recirc(dp, skb, key, a, last);
+			if (last) {
 				/* If this is the last action, the skb has
 				 * been consumed or freed.
 				 * Return immediately.
@@ -1216,6 +1167,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 				return err;
 			}
 			break;
+		}
 
 		case OVS_ACTION_ATTR_SET:
 			err = execute_set_action(skb, key, nla_data(a));
@@ -1226,9 +1178,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			err = execute_masked_set_action(skb, key, nla_data(a));
 			break;
 
-		case OVS_ACTION_ATTR_SAMPLE:
-			err = sample(dp, skb, key, a, attr, len);
+		case OVS_ACTION_ATTR_SAMPLE: {
+			bool last = nla_is_last(a, rem);
+
+			err = sample(dp, skb, key, a, last);
+			if (last)
+				return err;
+
 			break;
+		}
 
 		case OVS_ACTION_ATTR_CT:
 			if (!is_flow_key_valid(key)) {
@@ -1264,6 +1222,79 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 	return 0;
 }
 
+/* Execute the actions on the clone of the packet. The effect of the
+ * execution does not affect the original 'skb' nor the original 'key'.
+ *
+ * The execution may be deferred in case the actions can not be executed
+ * immediately.
+ */
+static int clone_execute(struct datapath *dp, struct sk_buff *skb,
+			 struct sw_flow_key *key, u32 recirc_id,
+			 const struct nlattr *actions, int len,
+			 bool last, bool clone_flow_key)
+{
+	struct deferred_action *da;
+	struct sw_flow_key *clone;
+
+	skb = last ? skb : skb_clone(skb, GFP_ATOMIC);
+	if (!skb) {
+		/* Out of memory, skip this action.
+		 */
+		return 0;
+	}
+
+	/* When clone_flow_key is false, the 'key' will not be change
+	 * by the actions, then the 'key' can be used directly.
+	 * Otherwise, try to clone key from the next recursion level of
+	 * 'flow_keys'. If clone is successful, execute the actions
+	 * without deferring.
+	 */
+	clone = clone_flow_key ? clone_key(key) : key;
+	if (clone) {
+		int err = 0;
+
+		if (actions) { /* Sample action */
+			if (clone_flow_key)
+				__this_cpu_inc(exec_actions_level);
+
+			err = do_execute_actions(dp, skb, clone,
+						 actions, len);
+
+			if (clone_flow_key)
+				__this_cpu_dec(exec_actions_level);
+		} else { /* Recirc action */
+			clone->recirc_id = recirc_id;
+			ovs_dp_process_packet(skb, clone);
+		}
+		return err;
+	}
+
+	/* Out of 'flow_keys' space. Defer actions */
+	da = add_deferred_actions(skb, key, actions, len);
+	if (da) {
+		if (!actions) { /* Recirc action */
+			key = &da->pkt_key;
+			key->recirc_id = recirc_id;
+		}
+	} else {
+		/* Out of per CPU action FIFO space. Drop the 'skb' and
+		 * log an error.
+		 */
+		kfree_skb(skb);
+
+		if (net_ratelimit()) {
+			if (actions) { /* Sample action */
+				pr_warn("%s: deferred action limit reached, drop sample action\n",
+					ovs_dp_name(dp));
+			} else {  /* Recirc action */
+				pr_warn("%s: deferred action limit reached, drop recirc action\n",
+					ovs_dp_name(dp));
+			}
+		}
+	}
+	return 0;
+}
+
 static void process_deferred_actions(struct datapath *dp)
 {
 	struct action_fifo *fifo = this_cpu_ptr(action_fifos);
@@ -1278,10 +1309,10 @@ static void process_deferred_actions(struct datapath *dp)
 		struct sk_buff *skb = da->skb;
 		struct sw_flow_key *key = &da->pkt_key;
 		const struct nlattr *actions = da->actions;
+		int actions_len = da->actions_len;
 
 		if (actions)
-			do_execute_actions(dp, skb, key, actions,
-					   nla_len(actions));
+			do_execute_actions(dp, skb, key, actions, actions_len);
 		else
 			ovs_dp_process_packet(skb, key);
 	} while (!action_fifo_is_empty(fifo));
@@ -1323,8 +1354,8 @@ int action_fifos_init(void)
 	if (!action_fifos)
 		return -ENOMEM;
 
-	recirc_keys = alloc_percpu(struct recirc_keys);
-	if (!recirc_keys) {
+	flow_keys = alloc_percpu(struct action_flow_keys);
+	if (!flow_keys) {
 		free_percpu(action_fifos);
 		return -ENOMEM;
 	}
@@ -1335,5 +1366,5 @@ int action_fifos_init(void)
 void action_fifos_exit(void)
 {
 	free_percpu(action_fifos);
-	free_percpu(recirc_keys);
+	free_percpu(flow_keys);
 }
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 1c6e9377436d..da931bdef8a7 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -34,8 +34,6 @@
 #define DP_MAX_PORTS           USHRT_MAX
 #define DP_VPORT_HASH_BUCKETS  1024
 
-#define SAMPLE_ACTION_DEPTH 3
-
 /**
  * struct dp_stats_percpu - per-cpu packet processing statistics for a given
  * datapath.
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 1105a838bab8..df82b81a9b35 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007-2014 Nicira, Inc.
+ * Copyright (c) 2007-2017 Nicira, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -59,6 +59,39 @@ struct ovs_len_tbl {
 #define OVS_ATTR_NESTED -1
 #define OVS_ATTR_VARIABLE -2
 
+static bool actions_may_change_flow(const struct nlattr *actions)
+{
+	struct nlattr *nla;
+	int rem;
+
+	nla_for_each_nested(nla, actions, rem) {
+		u16 action = nla_type(nla);
+
+		switch (action) {
+		case OVS_ACTION_ATTR_OUTPUT:
+		case OVS_ACTION_ATTR_RECIRC:
+		case OVS_ACTION_ATTR_TRUNC:
+		case OVS_ACTION_ATTR_USERSPACE:
+			break;
+
+		case OVS_ACTION_ATTR_CT:
+		case OVS_ACTION_ATTR_HASH:
+		case OVS_ACTION_ATTR_POP_ETH:
+		case OVS_ACTION_ATTR_POP_MPLS:
+		case OVS_ACTION_ATTR_POP_VLAN:
+		case OVS_ACTION_ATTR_PUSH_ETH:
+		case OVS_ACTION_ATTR_PUSH_MPLS:
+		case OVS_ACTION_ATTR_PUSH_VLAN:
+		case OVS_ACTION_ATTR_SAMPLE:
+		case OVS_ACTION_ATTR_SET:
+		case OVS_ACTION_ATTR_SET_MASKED:
+		default:
+			return true;
+		}
+	}
+	return false;
+}
+
 static void update_range(struct sw_flow_match *match,
 			 size_t offset, size_t size, bool is_mask)
 {
@@ -2023,18 +2056,20 @@ static inline void add_nested_action_end(struct sw_flow_actions *sfa,
 
 static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				  const struct sw_flow_key *key,
-				  int depth, struct sw_flow_actions **sfa,
+				  struct sw_flow_actions **sfa,
 				  __be16 eth_type, __be16 vlan_tci, bool log);
 
 static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
-				    const struct sw_flow_key *key, int depth,
+				    const struct sw_flow_key *key,
 				    struct sw_flow_actions **sfa,
-				    __be16 eth_type, __be16 vlan_tci, bool log)
+				    __be16 eth_type, __be16 vlan_tci,
+				    bool log, bool last)
 {
 	const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
 	const struct nlattr *probability, *actions;
 	const struct nlattr *a;
-	int rem, start, err, st_acts;
+	int rem, start, err;
+	struct sample_arg arg;
 
 	memset(attrs, 0, sizeof(attrs));
 	nla_for_each_nested(a, attr, rem) {
@@ -2058,20 +2093,32 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
 	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE, log);
 	if (start < 0)
 		return start;
-	err = ovs_nla_add_action(sfa, OVS_SAMPLE_ATTR_PROBABILITY,
-				 nla_data(probability), sizeof(u32), log);
+
+	/* When both skb and flow may be changed, put the sample
+	 * into a deferred fifo. On the other hand, if only skb
+	 * may be modified, the actions can be executed in place.
+	 *
+	 * Do this analysis at the flow installation time.
+	 * Set 'clone_action->exec' to true if the actions can be
+	 * executed without being deferred.
+	 *
+	 * If the sample is the last action, it can always be excuted
+	 * rather than deferred.
+	 */
+	arg.exec = last || !actions_may_change_flow(actions);
+	arg.probability = nla_get_u32(probability);
+
+	err = ovs_nla_add_action(sfa, OVS_SAMPLE_ATTR_ARG, &arg, sizeof(arg),
+				 log);
 	if (err)
 		return err;
-	st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS, log);
-	if (st_acts < 0)
-		return st_acts;
 
-	err = __ovs_nla_copy_actions(net, actions, key, depth + 1, sfa,
+	err = __ovs_nla_copy_actions(net, actions, key, sfa,
 				     eth_type, vlan_tci, log);
+
 	if (err)
 		return err;
 
-	add_nested_action_end(*sfa, st_acts);
 	add_nested_action_end(*sfa, start);
 
 	return 0;
@@ -2408,16 +2455,13 @@ static int copy_action(const struct nlattr *from,
 
 static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				  const struct sw_flow_key *key,
-				  int depth, struct sw_flow_actions **sfa,
+				  struct sw_flow_actions **sfa,
 				  __be16 eth_type, __be16 vlan_tci, bool log)
 {
 	u8 mac_proto = ovs_key_mac_proto(key);
 	const struct nlattr *a;
 	int rem, err;
 
-	if (depth >= SAMPLE_ACTION_DEPTH)
-		return -EOVERFLOW;
-
 	nla_for_each_nested(a, attr, rem) {
 		/* Expected argument lengths, (u32)-1 for variable length. */
 		static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = {
@@ -2555,13 +2599,17 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				return err;
 			break;
 
-		case OVS_ACTION_ATTR_SAMPLE:
-			err = validate_and_copy_sample(net, a, key, depth, sfa,
-						       eth_type, vlan_tci, log);
+		case OVS_ACTION_ATTR_SAMPLE: {
+			bool last = nla_is_last(a, rem);
+
+			err = validate_and_copy_sample(net, a, key, sfa,
+						       eth_type, vlan_tci,
+						       log, last);
 			if (err)
 				return err;
 			skip_copy = true;
 			break;
+		}
 
 		case OVS_ACTION_ATTR_CT:
 			err = ovs_ct_copy_action(net, a, key, sfa, log);
@@ -2615,7 +2663,7 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 		return PTR_ERR(*sfa);
 
 	(*sfa)->orig_len = nla_len(attr);
-	err = __ovs_nla_copy_actions(net, attr, key, 0, sfa, key->eth.type,
+	err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type,
 				     key->eth.vlan.tci, log);
 	if (err)
 		ovs_nla_free_flow_actions(*sfa);
@@ -2623,39 +2671,44 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 	return err;
 }
 
-static int sample_action_to_attr(const struct nlattr *attr, struct sk_buff *skb)
+static int sample_action_to_attr(const struct nlattr *attr,
+				 struct sk_buff *skb)
 {
-	const struct nlattr *a;
-	struct nlattr *start;
-	int err = 0, rem;
+	struct nlattr *start, *ac_start = NULL, *sample_arg;
+	int err = 0, rem = nla_len(attr);
+	const struct sample_arg *arg;
+	struct nlattr *actions;
 
 	start = nla_nest_start(skb, OVS_ACTION_ATTR_SAMPLE);
 	if (!start)
 		return -EMSGSIZE;
 
-	nla_for_each_nested(a, attr, rem) {
-		int type = nla_type(a);
-		struct nlattr *st_sample;
+	sample_arg = nla_data(attr);
+	arg = nla_data(sample_arg);
+	actions = nla_next(sample_arg, &rem);
 
-		switch (type) {
-		case OVS_SAMPLE_ATTR_PROBABILITY:
-			if (nla_put(skb, OVS_SAMPLE_ATTR_PROBABILITY,
-				    sizeof(u32), nla_data(a)))
-				return -EMSGSIZE;
-			break;
-		case OVS_SAMPLE_ATTR_ACTIONS:
-			st_sample = nla_nest_start(skb, OVS_SAMPLE_ATTR_ACTIONS);
-			if (!st_sample)
-				return -EMSGSIZE;
-			err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb);
-			if (err)
-				return err;
-			nla_nest_end(skb, st_sample);
-			break;
-		}
+	if (nla_put_u32(skb, OVS_SAMPLE_ATTR_PROBABILITY, arg->probability)) {
+		err = -EMSGSIZE;
+		goto out;
+	}
+
+	ac_start = nla_nest_start(skb, OVS_SAMPLE_ATTR_ACTIONS);
+	if (!ac_start) {
+		err = -EMSGSIZE;
+		goto out;
+	}
+
+	err = ovs_nla_put_actions(actions, rem, skb);
+
+out:
+	if (err) {
+		nla_nest_cancel(skb, ac_start);
+		nla_nest_cancel(skb, start);
+	} else {
+		nla_nest_end(skb, ac_start);
+		nla_nest_end(skb, start);
 	}
 
-	nla_nest_end(skb, start);
 	return err;
 }
 
diff --git a/net/qrtr/Kconfig b/net/qrtr/Kconfig
index b83c6807a5ae..326fd97444f5 100644
--- a/net/qrtr/Kconfig
+++ b/net/qrtr/Kconfig
@@ -16,7 +16,7 @@ if QRTR
 
 config QRTR_SMD
 	tristate "SMD IPC Router channels"
-	depends on QCOM_SMD || (COMPILE_TEST && QCOM_SMD=n)
+	depends on RPMSG || (COMPILE_TEST && RPMSG=n)
 	---help---
 	  Say Y here to support SMD based ipcrouter channels.  SMD is the
 	  most common transport for IPC Router.
diff --git a/net/qrtr/smd.c b/net/qrtr/smd.c
index 0d11132b3370..50615d5efac1 100644
--- a/net/qrtr/smd.c
+++ b/net/qrtr/smd.c
@@ -14,21 +14,21 @@
 
 #include <linux/module.h>
 #include <linux/skbuff.h>
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
 
 #include "qrtr.h"
 
 struct qrtr_smd_dev {
 	struct qrtr_endpoint ep;
-	struct qcom_smd_channel *channel;
+	struct rpmsg_endpoint *channel;
 	struct device *dev;
 };
 
 /* from smd to qrtr */
-static int qcom_smd_qrtr_callback(struct qcom_smd_channel *channel,
-				  const void *data, size_t len)
+static int qcom_smd_qrtr_callback(struct rpmsg_device *rpdev,
+				  void *data, int len, void *priv, u32 addr)
 {
-	struct qrtr_smd_dev *qdev = qcom_smd_get_drvdata(channel);
+	struct qrtr_smd_dev *qdev = dev_get_drvdata(&rpdev->dev);
 	int rc;
 
 	if (!qdev)
@@ -54,7 +54,7 @@ static int qcom_smd_qrtr_send(struct qrtr_endpoint *ep, struct sk_buff *skb)
 	if (rc)
 		goto out;
 
-	rc = qcom_smd_send(qdev->channel, skb->data, skb->len);
+	rc = rpmsg_send(qdev->channel, skb->data, skb->len);
 
 out:
 	if (rc)
@@ -64,57 +64,55 @@ out:
 	return rc;
 }
 
-static int qcom_smd_qrtr_probe(struct qcom_smd_device *sdev)
+static int qcom_smd_qrtr_probe(struct rpmsg_device *rpdev)
 {
 	struct qrtr_smd_dev *qdev;
 	int rc;
 
-	qdev = devm_kzalloc(&sdev->dev, sizeof(*qdev), GFP_KERNEL);
+	qdev = devm_kzalloc(&rpdev->dev, sizeof(*qdev), GFP_KERNEL);
 	if (!qdev)
 		return -ENOMEM;
 
-	qdev->channel = sdev->channel;
-	qdev->dev = &sdev->dev;
+	qdev->channel = rpdev->ept;
+	qdev->dev = &rpdev->dev;
 	qdev->ep.xmit = qcom_smd_qrtr_send;
 
 	rc = qrtr_endpoint_register(&qdev->ep, QRTR_EP_NID_AUTO);
 	if (rc)
 		return rc;
 
-	qcom_smd_set_drvdata(sdev->channel, qdev);
-	dev_set_drvdata(&sdev->dev, qdev);
+	dev_set_drvdata(&rpdev->dev, qdev);
 
-	dev_dbg(&sdev->dev, "Qualcomm SMD QRTR driver probed\n");
+	dev_dbg(&rpdev->dev, "Qualcomm SMD QRTR driver probed\n");
 
 	return 0;
 }
 
-static void qcom_smd_qrtr_remove(struct qcom_smd_device *sdev)
+static void qcom_smd_qrtr_remove(struct rpmsg_device *rpdev)
 {
-	struct qrtr_smd_dev *qdev = dev_get_drvdata(&sdev->dev);
+	struct qrtr_smd_dev *qdev = dev_get_drvdata(&rpdev->dev);
 
 	qrtr_endpoint_unregister(&qdev->ep);
 
-	dev_set_drvdata(&sdev->dev, NULL);
+	dev_set_drvdata(&rpdev->dev, NULL);
 }
 
-static const struct qcom_smd_id qcom_smd_qrtr_smd_match[] = {
+static const struct rpmsg_device_id qcom_smd_qrtr_smd_match[] = {
 	{ "IPCRTR" },
 	{}
 };
 
-static struct qcom_smd_driver qcom_smd_qrtr_driver = {
+static struct rpmsg_driver qcom_smd_qrtr_driver = {
 	.probe = qcom_smd_qrtr_probe,
 	.remove = qcom_smd_qrtr_remove,
 	.callback = qcom_smd_qrtr_callback,
-	.smd_match_table = qcom_smd_qrtr_smd_match,
-	.driver = {
+	.id_table = qcom_smd_qrtr_smd_match,
+	.drv = {
 		.name = "qcom_smd_qrtr",
-		.owner = THIS_MODULE,
 	},
 };
 
-module_qcom_smd_driver(qcom_smd_qrtr_driver);
+module_rpmsg_driver(qcom_smd_qrtr_driver);
 
 MODULE_DESCRIPTION("Qualcomm IPC-Router SMD interface driver");
 MODULE_LICENSE("GPL v2");
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 1fa75ab7b733..6a5ebdea7d2e 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -333,11 +333,19 @@ void rds_conn_shutdown(struct rds_conn_path *cp)
 		rds_conn_path_reset(cp);
 
 		if (!rds_conn_path_transition(cp, RDS_CONN_DISCONNECTING,
+					      RDS_CONN_DOWN) &&
+		    !rds_conn_path_transition(cp, RDS_CONN_ERROR,
 					      RDS_CONN_DOWN)) {
 			/* This can happen - eg when we're in the middle of tearing
 			 * down the connection, and someone unloads the rds module.
-			 * Quite reproduceable with loopback connections.
+			 * Quite reproducible with loopback connections.
 			 * Mostly harmless.
+			 *
+			 * Note that this also happens with rds-tcp because
+			 * we could have triggered rds_conn_path_drop in irq
+			 * mode from rds_tcp_state change on the receipt of
+			 * a FIN, thus we need to recheck for RDS_CONN_ERROR
+			 * here.
 			 */
 			rds_conn_path_error(cp, "%s: failed to transition "
 					    "to state DOWN, current state "
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 1c38d2c7caa8..80fb6f63e768 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -702,9 +702,8 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
 		event->param.conn.initiator_depth);
 
 	/* rdma_accept() calls rdma_reject() internally if it fails */
-	err = rdma_accept(cm_id, &conn_param);
-	if (err)
-		rds_ib_conn_error(conn, "rdma_accept failed (%d)\n", err);
+	if (rdma_accept(cm_id, &conn_param))
+		rds_ib_conn_error(conn, "rdma_accept failed\n");
 
 out:
 	if (conn)
diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c
index 4fe8f4fec4ee..86ef907067bb 100644
--- a/net/rds/ib_fmr.c
+++ b/net/rds/ib_fmr.c
@@ -78,17 +78,15 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages)
 	return ibmr;
 
 out_no_cigar:
-	if (ibmr) {
-		if (fmr->fmr)
-			ib_dealloc_fmr(fmr->fmr);
-		kfree(ibmr);
-	}
+	kfree(ibmr);
 	atomic_dec(&pool->item_count);
+
 	return ERR_PTR(err);
 }
 
-int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibmr,
-		   struct scatterlist *sg, unsigned int nents)
+static int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev,
+			  struct rds_ib_mr *ibmr, struct scatterlist *sg,
+			  unsigned int nents)
 {
 	struct ib_device *dev = rds_ibdev->dev;
 	struct rds_ib_fmr *fmr = &ibmr->u.fmr;
@@ -114,29 +112,39 @@ int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibmr,
 		u64 dma_addr = ib_sg_dma_address(dev, &scat[i]);
 
 		if (dma_addr & ~PAGE_MASK) {
-			if (i > 0)
+			if (i > 0) {
+				ib_dma_unmap_sg(dev, sg, nents,
+						DMA_BIDIRECTIONAL);
 				return -EINVAL;
-			else
+			} else {
 				++page_cnt;
+			}
 		}
 		if ((dma_addr + dma_len) & ~PAGE_MASK) {
-			if (i < sg_dma_len - 1)
+			if (i < sg_dma_len - 1) {
+				ib_dma_unmap_sg(dev, sg, nents,
+						DMA_BIDIRECTIONAL);
 				return -EINVAL;
-			else
+			} else {
 				++page_cnt;
+			}
 		}
 
 		len += dma_len;
 	}
 
 	page_cnt += len >> PAGE_SHIFT;
-	if (page_cnt > ibmr->pool->fmr_attr.max_pages)
+	if (page_cnt > ibmr->pool->fmr_attr.max_pages) {
+		ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL);
 		return -EINVAL;
+	}
 
 	dma_pages = kmalloc_node(sizeof(u64) * page_cnt, GFP_ATOMIC,
 				 rdsibdev_to_node(rds_ibdev));
-	if (!dma_pages)
+	if (!dma_pages) {
+		ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL);
 		return -ENOMEM;
+	}
 
 	page_cnt = 0;
 	for (i = 0; i < sg_dma_len; ++i) {
@@ -149,8 +157,10 @@ int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibmr,
 	}
 
 	ret = ib_map_phys_fmr(fmr->fmr, dma_pages, page_cnt, io_addr);
-	if (ret)
+	if (ret) {
+		ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL);
 		goto out;
+	}
 
 	/* Success - we successfully remapped the MR, so we can
 	 * safely tear down the old mapping.
diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h
index 5d6e98a79a5e..0ea4ab017a8c 100644
--- a/net/rds/ib_mr.h
+++ b/net/rds/ib_mr.h
@@ -125,8 +125,6 @@ void rds_ib_mr_exit(void);
 void __rds_ib_teardown_mr(struct rds_ib_mr *);
 void rds_ib_teardown_mr(struct rds_ib_mr *);
 struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *, int);
-int rds_ib_map_fmr(struct rds_ib_device *, struct rds_ib_mr *,
-		   struct scatterlist *, unsigned int);
 struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *);
 int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *, int, struct rds_ib_mr **);
 struct rds_ib_mr *rds_ib_reg_fmr(struct rds_ib_device *, struct scatterlist *,
diff --git a/net/rds/threads.c b/net/rds/threads.c
index e36e333a0aa0..3e447d056d09 100644
--- a/net/rds/threads.c
+++ b/net/rds/threads.c
@@ -156,7 +156,7 @@ void rds_connect_worker(struct work_struct *work)
 	struct rds_connection *conn = cp->cp_conn;
 	int ret;
 
-	if (cp->cp_index > 1 && cp->cp_conn->c_laddr > cp->cp_conn->c_faddr)
+	if (cp->cp_index > 0 && cp->cp_conn->c_laddr > cp->cp_conn->c_faddr)
 		return;
 	clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags);
 	ret = rds_conn_path_transition(cp, RDS_CONN_DOWN, RDS_CONN_CONNECTING);
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index e978ccd4402c..6c319a40c1cc 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -181,6 +181,9 @@ static int tcf_csum_ipv4_tcp(struct sk_buff *skb, unsigned int ihl,
 	struct tcphdr *tcph;
 	const struct iphdr *iph;
 
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
+		return 1;
+
 	tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph));
 	if (tcph == NULL)
 		return 0;
@@ -202,6 +205,9 @@ static int tcf_csum_ipv6_tcp(struct sk_buff *skb, unsigned int ihl,
 	struct tcphdr *tcph;
 	const struct ipv6hdr *ip6h;
 
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+		return 1;
+
 	tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph));
 	if (tcph == NULL)
 		return 0;
@@ -225,6 +231,9 @@ static int tcf_csum_ipv4_udp(struct sk_buff *skb, unsigned int ihl,
 	const struct iphdr *iph;
 	u16 ul;
 
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+		return 1;
+
 	/*
 	 * Support both UDP and UDPLITE checksum algorithms, Don't use
 	 * udph->len to get the real length without any protocol check,
@@ -278,6 +287,9 @@ static int tcf_csum_ipv6_udp(struct sk_buff *skb, unsigned int ihl,
 	const struct ipv6hdr *ip6h;
 	u16 ul;
 
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+		return 1;
+
 	/*
 	 * Support both UDP and UDPLITE checksum algorithms, Don't use
 	 * udph->len to get the real length without any protocol check,
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 71e7ff22f7c9..c75ea5c9102c 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -603,8 +603,8 @@ nla_put_failure:
 	return -1;
 }
 
-int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
-		       u16 metaid, u16 mlen, void *mdata)
+static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
+			      u16 metaid, u16 mlen, void *mdata)
 {
 	struct tcf_meta_info *e;
 
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 3d6b9286c203..ca193af8634a 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -508,9 +508,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 		get_random_bytes(&fnew->hashrnd, 4);
 	}
 
-	fnew->perturb_timer.function = flow_perturbation;
-	fnew->perturb_timer.data = (unsigned long)fnew;
-	init_timer_deferrable(&fnew->perturb_timer);
+	setup_deferrable_timer(&fnew->perturb_timer, flow_perturbation,
+			       (unsigned long)fnew);
 
 	tcf_exts_change(tp, &fnew->exts, &e);
 	tcf_em_tree_change(tp, &fnew->ematches, &t);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index bcf49cd22786..62567bfe52c7 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -274,7 +274,7 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
 	return NULL;
 }
 
-void qdisc_hash_add(struct Qdisc *q)
+void qdisc_hash_add(struct Qdisc *q, bool invisible)
 {
 	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
 		struct Qdisc *root = qdisc_dev(q)->qdisc;
@@ -282,6 +282,8 @@ void qdisc_hash_add(struct Qdisc *q)
 		WARN_ON_ONCE(root == &noop_qdisc);
 		ASSERT_RTNL();
 		hash_add_rcu(qdisc_dev(q)->qdisc_hash, &q->hash, q->handle);
+		if (invisible)
+			q->flags |= TCQ_F_INVISIBLE;
 	}
 }
 EXPORT_SYMBOL(qdisc_hash_add);
@@ -1003,7 +1005,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
 				goto err_out4;
 		}
 
-		qdisc_hash_add(sch);
+		qdisc_hash_add(sch, false);
 
 		return sch;
 	}
@@ -1401,9 +1403,14 @@ nla_put_failure:
 	return -1;
 }
 
-static bool tc_qdisc_dump_ignore(struct Qdisc *q)
+static bool tc_qdisc_dump_ignore(struct Qdisc *q, bool dump_invisible)
 {
-	return (q->flags & TCQ_F_BUILTIN) ? true : false;
+	if (q->flags & TCQ_F_BUILTIN)
+		return true;
+	if ((q->flags & TCQ_F_INVISIBLE) && !dump_invisible)
+		return true;
+
+	return false;
 }
 
 static int qdisc_notify(struct net *net, struct sk_buff *oskb,
@@ -1417,12 +1424,12 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb,
 	if (!skb)
 		return -ENOBUFS;
 
-	if (old && !tc_qdisc_dump_ignore(old)) {
+	if (old && !tc_qdisc_dump_ignore(old, false)) {
 		if (tc_fill_qdisc(skb, old, clid, portid, n->nlmsg_seq,
 				  0, RTM_DELQDISC) < 0)
 			goto err_out;
 	}
-	if (new && !tc_qdisc_dump_ignore(new)) {
+	if (new && !tc_qdisc_dump_ignore(new, false)) {
 		if (tc_fill_qdisc(skb, new, clid, portid, n->nlmsg_seq,
 				  old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0)
 			goto err_out;
@@ -1439,7 +1446,8 @@ err_out:
 
 static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb,
 			      struct netlink_callback *cb,
-			      int *q_idx_p, int s_q_idx, bool recur)
+			      int *q_idx_p, int s_q_idx, bool recur,
+			      bool dump_invisible)
 {
 	int ret = 0, q_idx = *q_idx_p;
 	struct Qdisc *q;
@@ -1452,7 +1460,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb,
 	if (q_idx < s_q_idx) {
 		q_idx++;
 	} else {
-		if (!tc_qdisc_dump_ignore(q) &&
+		if (!tc_qdisc_dump_ignore(q, dump_invisible) &&
 		    tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid,
 				  cb->nlh->nlmsg_seq, NLM_F_MULTI,
 				  RTM_NEWQDISC) <= 0)
@@ -1474,7 +1482,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb,
 			q_idx++;
 			continue;
 		}
-		if (!tc_qdisc_dump_ignore(q) &&
+		if (!tc_qdisc_dump_ignore(q, dump_invisible) &&
 		    tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid,
 				  cb->nlh->nlmsg_seq, NLM_F_MULTI,
 				  RTM_NEWQDISC) <= 0)
@@ -1496,12 +1504,21 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
 	int idx, q_idx;
 	int s_idx, s_q_idx;
 	struct net_device *dev;
+	const struct nlmsghdr *nlh = cb->nlh;
+	struct tcmsg *tcm = nlmsg_data(nlh);
+	struct nlattr *tca[TCA_MAX + 1];
+	int err;
 
 	s_idx = cb->args[0];
 	s_q_idx = q_idx = cb->args[1];
 
 	idx = 0;
 	ASSERT_RTNL();
+
+	err = nlmsg_parse(nlh, sizeof(*tcm), tca, TCA_MAX, NULL);
+	if (err < 0)
+		return err;
+
 	for_each_netdev(net, dev) {
 		struct netdev_queue *dev_queue;
 
@@ -1512,13 +1529,14 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
 		q_idx = 0;
 
 		if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx,
-				       true) < 0)
+				       true, tca[TCA_DUMP_INVISIBLE]) < 0)
 			goto done;
 
 		dev_queue = dev_ingress_queue(dev);
 		if (dev_queue &&
 		    tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb,
-				       &q_idx, s_q_idx, false) < 0)
+				       &q_idx, s_q_idx, false,
+				       tca[TCA_DUMP_INVISIBLE]) < 0)
 			goto done;
 
 cont:
@@ -1762,7 +1780,7 @@ static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb,
 {
 	struct qdisc_dump_args arg;
 
-	if (tc_qdisc_dump_ignore(q) ||
+	if (tc_qdisc_dump_ignore(q, false) ||
 	    *t_p < s_t || !q->ops->cl_ops ||
 	    (tcm->tcm_parent &&
 	     TC_H_MAJ(tcm->tcm_parent) != q->handle)) {
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index d6ca18dc04c3..cf93e5ff3d63 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1161,6 +1161,8 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt)
 				      sch->handle);
 	if (!q->link.q)
 		q->link.q = &noop_qdisc;
+	else
+		qdisc_hash_add(q->link.q, true);
 
 	q->link.priority = TC_CBQ_MAXPRIO - 1;
 	q->link.priority2 = TC_CBQ_MAXPRIO - 1;
@@ -1600,6 +1602,9 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 	cl->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid);
 	if (!cl->q)
 		cl->q = &noop_qdisc;
+	else
+		qdisc_hash_add(cl->q, true);
+
 	cl->common.classid = classid;
 	cl->tparent = parent;
 	cl->qdisc = sch;
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 3b86a97bc67c..593183a5b5b5 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -58,7 +58,6 @@ struct choke_sched_data {
 
 /* Variables */
 	struct red_vars  vars;
-	struct tcf_proto __rcu *filter_list;
 	struct {
 		u32	prob_drop;	/* Early probability drops */
 		u32	prob_mark;	/* Early probability marks */
@@ -152,11 +151,6 @@ static inline void choke_set_classid(struct sk_buff *skb, u16 classid)
 	choke_skb_cb(skb)->classid = classid;
 }
 
-static u16 choke_get_classid(const struct sk_buff *skb)
-{
-	return choke_skb_cb(skb)->classid;
-}
-
 /*
  * Compare flow of two packets
  *  Returns true only if source and destination address and port match.
@@ -188,40 +182,6 @@ static bool choke_match_flow(struct sk_buff *skb1,
 }
 
 /*
- * Classify flow using either:
- *  1. pre-existing classification result in skb
- *  2. fast internal classification
- *  3. use TC filter based classification
- */
-static bool choke_classify(struct sk_buff *skb,
-			   struct Qdisc *sch, int *qerr)
-
-{
-	struct choke_sched_data *q = qdisc_priv(sch);
-	struct tcf_result res;
-	struct tcf_proto *fl;
-	int result;
-
-	fl = rcu_dereference_bh(q->filter_list);
-	result = tc_classify(skb, fl, &res, false);
-	if (result >= 0) {
-#ifdef CONFIG_NET_CLS_ACT
-		switch (result) {
-		case TC_ACT_STOLEN:
-		case TC_ACT_QUEUED:
-			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
-		case TC_ACT_SHOT:
-			return false;
-		}
-#endif
-		choke_set_classid(skb, TC_H_MIN(res.classid));
-		return true;
-	}
-
-	return false;
-}
-
-/*
  * Select a packet at random from queue
  * HACK: since queue can have holes from previous deletion; retry several
  *   times to find a random skb but then just give up and return the head
@@ -257,25 +217,15 @@ static bool choke_match_random(const struct choke_sched_data *q,
 		return false;
 
 	oskb = choke_peek_random(q, pidx);
-	if (rcu_access_pointer(q->filter_list))
-		return choke_get_classid(nskb) == choke_get_classid(oskb);
-
 	return choke_match_flow(oskb, nskb);
 }
 
 static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			 struct sk_buff **to_free)
 {
-	int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 	struct choke_sched_data *q = qdisc_priv(sch);
 	const struct red_parms *p = &q->parms;
 
-	if (rcu_access_pointer(q->filter_list)) {
-		/* If using external classifiers, get result and record it. */
-		if (!choke_classify(skb, sch, &ret))
-			goto other_drop;	/* Packet was eaten by filter */
-	}
-
 	choke_skb_cb(skb)->keys_valid = 0;
 	/* Compute average queue usage (see RED) */
 	q->vars.qavg = red_calc_qavg(p, &q->vars, sch->q.qlen);
@@ -339,12 +289,6 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 congestion_drop:
 	qdisc_drop(skb, sch, to_free);
 	return NET_XMIT_CN;
-
-other_drop:
-	if (ret & __NET_XMIT_BYPASS)
-		qdisc_qstats_drop(sch);
-	__qdisc_drop(skb, to_free);
-	return ret;
 }
 
 static struct sk_buff *choke_dequeue(struct Qdisc *sch)
@@ -538,7 +482,6 @@ static void choke_destroy(struct Qdisc *sch)
 {
 	struct choke_sched_data *q = qdisc_priv(sch);
 
-	tcf_destroy_chain(&q->filter_list);
 	choke_free(q->tab);
 }
 
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index bb4cbdf75004..9fe67e257dfa 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -117,6 +117,8 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 					       &pfifo_qdisc_ops, classid);
 	if (cl->qdisc == NULL)
 		cl->qdisc = &noop_qdisc;
+	else
+		qdisc_hash_add(cl->qdisc, true);
 
 	if (tca[TCA_RATE]) {
 		err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est,
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 5334e309f17f..cfa1f2cdbaf7 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -374,6 +374,8 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt)
 	p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle);
 	if (p->q == NULL)
 		p->q = &noop_qdisc;
+	else
+		qdisc_hash_add(p->q, true);
 
 	pr_debug("%s: qdisc %p\n", __func__, p->q);
 
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 9f3a884d1590..097bbe9857a5 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -288,7 +288,6 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
 	struct fq_codel_flow *flow;
 	struct list_head *head;
 	u32 prev_drop_count, prev_ecn_mark;
-	unsigned int prev_backlog;
 
 begin:
 	head = &q->new_flows;
@@ -307,7 +306,6 @@ begin:
 
 	prev_drop_count = q->cstats.drop_count;
 	prev_ecn_mark = q->cstats.ecn_mark;
-	prev_backlog = sch->qstats.backlog;
 
 	skb = codel_dequeue(sch, &sch->qstats.backlog, &q->cparams,
 			    &flow->cvars, &q->cstats, qdisc_pkt_len,
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index b052b27a984e..3e64d23e098c 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -795,7 +795,7 @@ static void attach_default_qdiscs(struct net_device *dev)
 	}
 #ifdef CONFIG_NET_SCHED
 	if (dev->qdisc)
-		qdisc_hash_add(dev->qdisc);
+		qdisc_hash_add(dev->qdisc, false);
 #endif
 }
 
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 3ffaa6fb0990..0198c6cdda49 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1066,6 +1066,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 				      &pfifo_qdisc_ops, classid);
 	if (cl->qdisc == NULL)
 		cl->qdisc = &noop_qdisc;
+	else
+		qdisc_hash_add(cl->qdisc, true);
 	INIT_LIST_HEAD(&cl->children);
 	cl->vt_tree = RB_ROOT;
 	cl->cf_tree = RB_ROOT;
@@ -1425,6 +1427,8 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
 					  sch->handle);
 	if (q->root.qdisc == NULL)
 		q->root.qdisc = &noop_qdisc;
+	else
+		qdisc_hash_add(q->root.qdisc, true);
 	INIT_LIST_HEAD(&q->root.children);
 	q->root.vt_tree = RB_ROOT;
 	q->root.cf_tree = RB_ROOT;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 4cd5fb134bc9..95867033542e 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1460,6 +1460,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		qdisc_class_hash_insert(&q->clhash, &cl->common);
 		if (parent)
 			parent->children++;
+		if (cl->un.leaf.q != &noop_qdisc)
+			qdisc_hash_add(cl->un.leaf.q, true);
 	} else {
 		if (tca[TCA_RATE]) {
 			err = gen_replace_estimator(&cl->bstats, NULL,
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index 20b7f1646f69..cadfdd4f1e52 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -84,7 +84,7 @@ static void mq_attach(struct Qdisc *sch)
 			qdisc_destroy(old);
 #ifdef CONFIG_NET_SCHED
 		if (ntx < dev->real_num_tx_queues)
-			qdisc_hash_add(qdisc);
+			qdisc_hash_add(qdisc, false);
 #endif
 
 	}
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 922683418e53..0a4cf27ea54b 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -21,14 +21,13 @@
 
 struct mqprio_sched {
 	struct Qdisc		**qdiscs;
-	int hw_owned;
+	int hw_offload;
 };
 
 static void mqprio_destroy(struct Qdisc *sch)
 {
 	struct net_device *dev = qdisc_dev(sch);
 	struct mqprio_sched *priv = qdisc_priv(sch);
-	struct tc_to_netdev tc = {.type = TC_SETUP_MQPRIO};
 	unsigned int ntx;
 
 	if (priv->qdiscs) {
@@ -39,10 +38,15 @@ static void mqprio_destroy(struct Qdisc *sch)
 		kfree(priv->qdiscs);
 	}
 
-	if (priv->hw_owned && dev->netdev_ops->ndo_setup_tc)
+	if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) {
+		struct tc_mqprio_qopt offload = { 0 };
+		struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO,
+					   { .mqprio = &offload } };
+
 		dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc);
-	else
+	} else {
 		netdev_set_num_tc(dev, 0);
+	}
 }
 
 static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt)
@@ -59,15 +63,20 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt)
 			return -EINVAL;
 	}
 
-	/* net_device does not support requested operation */
-	if (qopt->hw && !dev->netdev_ops->ndo_setup_tc)
-		return -EINVAL;
+	/* Limit qopt->hw to maximum supported offload value.  Drivers have
+	 * the option of overriding this later if they don't support the a
+	 * given offload type.
+	 */
+	if (qopt->hw > TC_MQPRIO_HW_OFFLOAD_MAX)
+		qopt->hw = TC_MQPRIO_HW_OFFLOAD_MAX;
 
-	/* if hw owned qcount and qoffset are taken from LLD so
-	 * no reason to verify them here
+	/* If hardware offload is requested we will leave it to the device
+	 * to either populate the queue counts itself or to validate the
+	 * provided queue counts.  If ndo_setup_tc is not present then
+	 * hardware doesn't support offload and we should return an error.
 	 */
 	if (qopt->hw)
-		return 0;
+		return dev->netdev_ops->ndo_setup_tc ? 0 : -EINVAL;
 
 	for (i = 0; i < qopt->num_tc; i++) {
 		unsigned int last = qopt->offset[i] + qopt->count[i];
@@ -139,13 +148,15 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
 	 * supplied and verified mapping
 	 */
 	if (qopt->hw) {
-		struct tc_to_netdev tc = {.type = TC_SETUP_MQPRIO,
-					  { .tc = qopt->num_tc }};
+		struct tc_mqprio_qopt offload = *qopt;
+		struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO,
+					   { .mqprio = &offload } };
 
-		priv->hw_owned = 1;
 		err = dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc);
 		if (err)
 			return err;
+
+		priv->hw_offload = offload.hw;
 	} else {
 		netdev_set_num_tc(dev, qopt->num_tc);
 		for (i = 0; i < qopt->num_tc; i++)
@@ -175,7 +186,7 @@ static void mqprio_attach(struct Qdisc *sch)
 		if (old)
 			qdisc_destroy(old);
 		if (ntx < dev->real_num_tx_queues)
-			qdisc_hash_add(qdisc);
+			qdisc_hash_add(qdisc, false);
 	}
 	kfree(priv->qdiscs);
 	priv->qdiscs = NULL;
@@ -243,7 +254,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 
 	opt.num_tc = netdev_get_num_tc(dev);
 	memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map));
-	opt.hw = priv->hw_owned;
+	opt.hw = priv->hw_offload;
 
 	for (i = 0; i < netdev_get_num_tc(dev); i++) {
 		opt.count[i] = dev->tc_to_txq[i].count;
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index e7839a0d0eaa..43a3a10b3c81 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -217,6 +217,8 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt)
 				sch_tree_lock(sch);
 				old = q->queues[i];
 				q->queues[i] = child;
+				if (child != &noop_qdisc)
+					qdisc_hash_add(child, true);
 
 				if (old != &noop_qdisc) {
 					qdisc_tree_reduce_backlog(old,
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index c8bb62a1e744..94b4928ad413 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -462,7 +462,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	/* If a delay is expected, orphan the skb. (orphaning usually takes
 	 * place at TX completion time, so _before_ the link transit delay)
 	 */
-	if (q->latency || q->jitter)
+	if (q->latency || q->jitter || q->rate)
 		skb_orphan_partial(skb);
 
 	/*
@@ -530,21 +530,31 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		now = psched_get_time();
 
 		if (q->rate) {
-			struct sk_buff *last;
+			struct netem_skb_cb *last = NULL;
+
+			if (sch->q.tail)
+				last = netem_skb_cb(sch->q.tail);
+			if (q->t_root.rb_node) {
+				struct sk_buff *t_skb;
+				struct netem_skb_cb *t_last;
+
+				t_skb = netem_rb_to_skb(rb_last(&q->t_root));
+				t_last = netem_skb_cb(t_skb);
+				if (!last ||
+				    t_last->time_to_send > last->time_to_send) {
+					last = t_last;
+				}
+			}
 
-			if (sch->q.qlen)
-				last = sch->q.tail;
-			else
-				last = netem_rb_to_skb(rb_last(&q->t_root));
 			if (last) {
 				/*
 				 * Last packet in queue is reference point (now),
 				 * calculate this time bonus and subtract
 				 * from delay.
 				 */
-				delay -= netem_skb_cb(last)->time_to_send - now;
+				delay -= last->time_to_send - now;
 				delay = max_t(psched_tdiff_t, 0, delay);
-				now = netem_skb_cb(last)->time_to_send;
+				now = last->time_to_send;
 			}
 
 			delay += packet_len_2_sched_time(qdisc_pkt_len(skb), q);
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index d4d7db267b6e..92c2e6d448d7 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -192,8 +192,11 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 		qdisc_destroy(child);
 	}
 
-	for (i = oldbands; i < q->bands; i++)
+	for (i = oldbands; i < q->bands; i++) {
 		q->queues[i] = queues[i];
+		if (q->queues[i] != &noop_qdisc)
+			qdisc_hash_add(q->queues[i], true);
+	}
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index f9e712ce2d15..6c85f3e9239b 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -494,6 +494,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 			goto destroy_class;
 	}
 
+	if (cl->qdisc != &noop_qdisc)
+		qdisc_hash_add(cl->qdisc, true);
 	sch_tree_lock(sch);
 	qdisc_class_hash_insert(&q->clhash, &cl->common);
 	sch_tree_unlock(sch);
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 249b2a18acbd..799ea6dd69b2 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -191,6 +191,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt)
 			return PTR_ERR(child);
 	}
 
+	if (child != &noop_qdisc)
+		qdisc_hash_add(child, true);
 	sch_tree_lock(sch);
 	q->flags = ctl->flags;
 	q->limit = ctl->limit;
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index fe6963d21519..ae862f172c94 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -513,6 +513,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt)
 	if (IS_ERR(child))
 		return PTR_ERR(child);
 
+	if (child != &noop_qdisc)
+		qdisc_hash_add(child, true);
 	sch_tree_lock(sch);
 
 	qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 42e8c8615e65..b00e02c139de 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -714,9 +714,8 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt)
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	int i;
 
-	q->perturb_timer.function = sfq_perturbation;
-	q->perturb_timer.data = (unsigned long)sch;
-	init_timer_deferrable(&q->perturb_timer);
+	setup_deferrable_timer(&q->perturb_timer, sfq_perturbation,
+			       (unsigned long)sch);
 
 	for (i = 0; i < SFQ_MAX_DEPTH + 1; i++) {
 		q->dep[i].next = i + SFQ_MAX_FLOWS;
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 303355c449ab..9850126129a3 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -396,6 +396,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 					  q->qdisc->qstats.backlog);
 		qdisc_destroy(q->qdisc);
 		q->qdisc = child;
+		if (child != &noop_qdisc)
+			qdisc_hash_add(child, true);
 	}
 	q->limit = qopt->limit;
 	if (tb[TCA_TBF_PBURST])
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index e3621cb4827f..697721a7a3f1 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -306,14 +306,24 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk)
 
 	if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) &&
 	    time_after(jiffies, chunk->msg->expires_at)) {
-		if (chunk->sent_count)
+		struct sctp_stream_out *streamout =
+			&chunk->asoc->stream->out[chunk->sinfo.sinfo_stream];
+
+		if (chunk->sent_count) {
 			chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
-		else
+			streamout->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
+		} else {
 			chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
+			streamout->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
+		}
 		return 1;
 	} else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) &&
 		   chunk->sent_count > chunk->sinfo.sinfo_timetolive) {
+		struct sctp_stream_out *streamout =
+			&chunk->asoc->stream->out[chunk->sinfo.sinfo_stream];
+
 		chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
+		streamout->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
 		return 1;
 	} else if (!SCTP_PR_POLICY(chunk->sinfo.sinfo_flags) &&
 		   chunk->msg->expires_at &&
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 8081476ed313..fe4c3d462f6e 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -353,6 +353,8 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc,
 	struct sctp_chunk *chk, *temp;
 
 	list_for_each_entry_safe(chk, temp, queue, transmitted_list) {
+		struct sctp_stream_out *streamout;
+
 		if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) ||
 		    chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)
 			continue;
@@ -361,8 +363,10 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc,
 		sctp_insert_list(&asoc->outqueue.abandoned,
 				 &chk->transmitted_list);
 
+		streamout = &asoc->stream->out[chk->sinfo.sinfo_stream];
 		asoc->sent_cnt_removable--;
 		asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++;
+		streamout->abandoned_sent[SCTP_PR_INDEX(PRIO)]++;
 
 		if (!chk->tsn_gap_acked) {
 			if (chk->transport)
@@ -396,6 +400,12 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc,
 		q->out_qlen -= chk->skb->len;
 		asoc->sent_cnt_removable--;
 		asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++;
+		if (chk->sinfo.sinfo_stream < asoc->stream->outcnt) {
+			struct sctp_stream_out *streamout =
+				&asoc->stream->out[chk->sinfo.sinfo_stream];
+
+			streamout->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++;
+		}
 
 		msg_len -= SCTP_DATA_SNDSIZE(chk) +
 			   sizeof(struct sk_buff) +
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 24c6ccce7539..4f5e6cfc7f60 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3872,9 +3872,18 @@ sctp_disposition_t sctp_sf_do_reconf(struct net *net,
 		else if (param.p->type == SCTP_PARAM_RESET_IN_REQUEST)
 			reply = sctp_process_strreset_inreq(
 				(struct sctp_association *)asoc, param, &ev);
-		/* More handles for other types will be added here, by now it
-		 * just ignores other types.
-		 */
+		else if (param.p->type == SCTP_PARAM_RESET_TSN_REQUEST)
+			reply = sctp_process_strreset_tsnreq(
+				(struct sctp_association *)asoc, param, &ev);
+		else if (param.p->type == SCTP_PARAM_RESET_ADD_OUT_STREAMS)
+			reply = sctp_process_strreset_addstrm_out(
+				(struct sctp_association *)asoc, param, &ev);
+		else if (param.p->type == SCTP_PARAM_RESET_ADD_IN_STREAMS)
+			reply = sctp_process_strreset_addstrm_in(
+				(struct sctp_association *)asoc, param, &ev);
+		else if (param.p->type == SCTP_PARAM_RESET_RESPONSE)
+			reply = sctp_process_strreset_resp(
+				(struct sctp_association *)asoc, param, &ev);
 
 		if (ev)
 			sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP,
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index c1401f43d40f..8e56df8d175d 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3758,6 +3758,39 @@ out:
 	return retval;
 }
 
+static int sctp_setsockopt_reconfig_supported(struct sock *sk,
+					      char __user *optval,
+					      unsigned int optlen)
+{
+	struct sctp_assoc_value params;
+	struct sctp_association *asoc;
+	int retval = -EINVAL;
+
+	if (optlen != sizeof(params))
+		goto out;
+
+	if (copy_from_user(&params, optval, optlen)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	asoc = sctp_id2assoc(sk, params.assoc_id);
+	if (asoc) {
+		asoc->reconf_enable = !!params.assoc_value;
+	} else if (!params.assoc_id) {
+		struct sctp_sock *sp = sctp_sk(sk);
+
+		sp->ep->reconf_enable = !!params.assoc_value;
+	} else {
+		goto out;
+	}
+
+	retval = 0;
+
+out:
+	return retval;
+}
+
 static int sctp_setsockopt_enable_strreset(struct sock *sk,
 					   char __user *optval,
 					   unsigned int optlen)
@@ -4038,6 +4071,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 	case SCTP_DEFAULT_PRINFO:
 		retval = sctp_setsockopt_default_prinfo(sk, optval, optlen);
 		break;
+	case SCTP_RECONFIG_SUPPORTED:
+		retval = sctp_setsockopt_reconfig_supported(sk, optval, optlen);
+		break;
 	case SCTP_ENABLE_STREAM_RESET:
 		retval = sctp_setsockopt_enable_strreset(sk, optval, optlen);
 		break;
@@ -6540,6 +6576,102 @@ out:
 	return retval;
 }
 
+static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len,
+					   char __user *optval,
+					   int __user *optlen)
+{
+	struct sctp_stream_out *streamout;
+	struct sctp_association *asoc;
+	struct sctp_prstatus params;
+	int retval = -EINVAL;
+	int policy;
+
+	if (len < sizeof(params))
+		goto out;
+
+	len = sizeof(params);
+	if (copy_from_user(&params, optval, len)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	policy = params.sprstat_policy;
+	if (policy & ~SCTP_PR_SCTP_MASK)
+		goto out;
+
+	asoc = sctp_id2assoc(sk, params.sprstat_assoc_id);
+	if (!asoc || params.sprstat_sid >= asoc->stream->outcnt)
+		goto out;
+
+	streamout = &asoc->stream->out[params.sprstat_sid];
+	if (policy == SCTP_PR_SCTP_NONE) {
+		params.sprstat_abandoned_unsent = 0;
+		params.sprstat_abandoned_sent = 0;
+		for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) {
+			params.sprstat_abandoned_unsent +=
+				streamout->abandoned_unsent[policy];
+			params.sprstat_abandoned_sent +=
+				streamout->abandoned_sent[policy];
+		}
+	} else {
+		params.sprstat_abandoned_unsent =
+			streamout->abandoned_unsent[__SCTP_PR_INDEX(policy)];
+		params.sprstat_abandoned_sent =
+			streamout->abandoned_sent[__SCTP_PR_INDEX(policy)];
+	}
+
+	if (put_user(len, optlen) || copy_to_user(optval, &params, len)) {
+		retval = -EFAULT;
+		goto out;
+	}
+
+	retval = 0;
+
+out:
+	return retval;
+}
+
+static int sctp_getsockopt_reconfig_supported(struct sock *sk, int len,
+					      char __user *optval,
+					      int __user *optlen)
+{
+	struct sctp_assoc_value params;
+	struct sctp_association *asoc;
+	int retval = -EFAULT;
+
+	if (len < sizeof(params)) {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	len = sizeof(params);
+	if (copy_from_user(&params, optval, len))
+		goto out;
+
+	asoc = sctp_id2assoc(sk, params.assoc_id);
+	if (asoc) {
+		params.assoc_value = asoc->reconf_enable;
+	} else if (!params.assoc_id) {
+		struct sctp_sock *sp = sctp_sk(sk);
+
+		params.assoc_value = sp->ep->reconf_enable;
+	} else {
+		retval = -EINVAL;
+		goto out;
+	}
+
+	if (put_user(len, optlen))
+		goto out;
+
+	if (copy_to_user(optval, &params, len))
+		goto out;
+
+	retval = 0;
+
+out:
+	return retval;
+}
+
 static int sctp_getsockopt_enable_strreset(struct sock *sk, int len,
 					   char __user *optval,
 					   int __user *optlen)
@@ -6748,6 +6880,14 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 		retval = sctp_getsockopt_pr_assocstatus(sk, len, optval,
 							optlen);
 		break;
+	case SCTP_PR_STREAM_STATUS:
+		retval = sctp_getsockopt_pr_streamstatus(sk, len, optval,
+							 optlen);
+		break;
+	case SCTP_RECONFIG_SUPPORTED:
+		retval = sctp_getsockopt_reconfig_supported(sk, len, optval,
+							    optlen);
+		break;
 	case SCTP_ENABLE_STREAM_RESET:
 		retval = sctp_getsockopt_enable_strreset(sk, len, optval,
 							 optlen);
@@ -7437,9 +7577,12 @@ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags,
 		if (sk->sk_shutdown & RCV_SHUTDOWN)
 			break;
 
-		if (sk_can_busy_loop(sk) &&
-		    sk_busy_loop(sk, noblock))
-			continue;
+		if (sk_can_busy_loop(sk)) {
+			sk_busy_loop(sk, noblock);
+
+			if (!skb_queue_empty(&sk->sk_receive_queue))
+				continue;
+		}
 
 		/* User doesn't want to wait.  */
 		error = -EAGAIN;
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index bbed997e1c5f..eff6008a32ba 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -294,18 +294,6 @@ int sctp_send_add_streams(struct sctp_association *asoc,
 		stream->out = streamout;
 	}
 
-	if (in) {
-		struct sctp_stream_in *streamin;
-
-		streamin = krealloc(stream->in, incnt * sizeof(*streamin),
-				    GFP_KERNEL);
-		if (!streamin)
-			goto out;
-
-		memset(streamin + stream->incnt, 0, in * sizeof(*streamin));
-		stream->in = streamin;
-	}
-
 	chunk = sctp_make_strreset_addstrm(asoc, out, in);
 	if (!chunk)
 		goto out;
@@ -330,13 +318,14 @@ out:
 }
 
 static sctp_paramhdr_t *sctp_chunk_lookup_strreset_param(
-			struct sctp_association *asoc, __u32 resp_seq)
+			struct sctp_association *asoc, __u32 resp_seq,
+			__be16 type)
 {
 	struct sctp_chunk *chunk = asoc->strreset_chunk;
 	struct sctp_reconf_chunk *hdr;
 	union sctp_params param;
 
-	if (ntohl(resp_seq) != asoc->strreset_outseq || !chunk)
+	if (!chunk)
 		return NULL;
 
 	hdr = (struct sctp_reconf_chunk *)chunk->chunk_hdr;
@@ -347,7 +336,8 @@ static sctp_paramhdr_t *sctp_chunk_lookup_strreset_param(
 		 */
 		struct sctp_strreset_tsnreq *req = param.v;
 
-		if (req->request_seq == resp_seq)
+		if ((!resp_seq || req->request_seq == resp_seq) &&
+		    (!type || type == req->param_hdr.type))
 			return param.v;
 	}
 
@@ -388,13 +378,9 @@ struct sctp_chunk *sctp_process_strreset_outreq(
 		goto out;
 
 	if (asoc->strreset_chunk) {
-		sctp_paramhdr_t *param_hdr;
-		struct sctp_transport *t;
-
-		param_hdr = sctp_chunk_lookup_strreset_param(
-					asoc, outreq->response_seq);
-		if (!param_hdr || param_hdr->type !=
-					SCTP_PARAM_RESET_IN_REQUEST) {
+		if (!sctp_chunk_lookup_strreset_param(
+				asoc, outreq->response_seq,
+				SCTP_PARAM_RESET_IN_REQUEST)) {
 			/* same process with outstanding isn't 0 */
 			result = SCTP_STRRESET_ERR_IN_PROGRESS;
 			goto out;
@@ -404,6 +390,8 @@ struct sctp_chunk *sctp_process_strreset_outreq(
 		asoc->strreset_outseq++;
 
 		if (!asoc->strreset_outstanding) {
+			struct sctp_transport *t;
+
 			t = asoc->strreset_chunk->transport;
 			if (del_timer(&t->reconf_timer))
 				sctp_transport_put(t);
@@ -504,3 +492,367 @@ out:
 
 	return chunk;
 }
+
+struct sctp_chunk *sctp_process_strreset_tsnreq(
+				struct sctp_association *asoc,
+				union sctp_params param,
+				struct sctp_ulpevent **evp)
+{
+	__u32 init_tsn = 0, next_tsn = 0, max_tsn_seen;
+	struct sctp_strreset_tsnreq *tsnreq = param.v;
+	struct sctp_stream *stream = asoc->stream;
+	__u32 result = SCTP_STRRESET_DENIED;
+	__u32 request_seq;
+	__u16 i;
+
+	request_seq = ntohl(tsnreq->request_seq);
+	if (request_seq > asoc->strreset_inseq) {
+		result = SCTP_STRRESET_ERR_BAD_SEQNO;
+		goto out;
+	} else if (request_seq == asoc->strreset_inseq) {
+		asoc->strreset_inseq++;
+	}
+
+	if (!(asoc->strreset_enable & SCTP_ENABLE_RESET_ASSOC_REQ))
+		goto out;
+
+	if (asoc->strreset_outstanding) {
+		result = SCTP_STRRESET_ERR_IN_PROGRESS;
+		goto out;
+	}
+
+	/* G3: The same processing as though a SACK chunk with no gap report
+	 *     and a cumulative TSN ACK of the Sender's Next TSN minus 1 were
+	 *     received MUST be performed.
+	 */
+	max_tsn_seen = sctp_tsnmap_get_max_tsn_seen(&asoc->peer.tsn_map);
+	sctp_ulpq_reasm_flushtsn(&asoc->ulpq, max_tsn_seen);
+	sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC);
+
+	/* G1: Compute an appropriate value for the Receiver's Next TSN -- the
+	 *     TSN that the peer should use to send the next DATA chunk.  The
+	 *     value SHOULD be the smallest TSN not acknowledged by the
+	 *     receiver of the request plus 2^31.
+	 */
+	init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1 << 31);
+	sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL,
+			 init_tsn, GFP_ATOMIC);
+
+	/* G4: The same processing as though a FWD-TSN chunk (as defined in
+	 *     [RFC3758]) with all streams affected and a new cumulative TSN
+	 *     ACK of the Receiver's Next TSN minus 1 were received MUST be
+	 *     performed.
+	 */
+	sctp_outq_free(&asoc->outqueue);
+
+	/* G2: Compute an appropriate value for the local endpoint's next TSN,
+	 *     i.e., the next TSN assigned by the receiver of the SSN/TSN reset
+	 *     chunk.  The value SHOULD be the highest TSN sent by the receiver
+	 *     of the request plus 1.
+	 */
+	next_tsn = asoc->next_tsn;
+	asoc->ctsn_ack_point = next_tsn - 1;
+	asoc->adv_peer_ack_point = asoc->ctsn_ack_point;
+
+	/* G5:  The next expected and outgoing SSNs MUST be reset to 0 for all
+	 *      incoming and outgoing streams.
+	 */
+	for (i = 0; i < stream->outcnt; i++)
+		stream->out[i].ssn = 0;
+	for (i = 0; i < stream->incnt; i++)
+		stream->in[i].ssn = 0;
+
+	result = SCTP_STRRESET_PERFORMED;
+
+	*evp = sctp_ulpevent_make_assoc_reset_event(asoc, 0, init_tsn,
+						    next_tsn, GFP_ATOMIC);
+
+out:
+	return sctp_make_strreset_tsnresp(asoc, result, request_seq,
+					  next_tsn, init_tsn);
+}
+
+struct sctp_chunk *sctp_process_strreset_addstrm_out(
+				struct sctp_association *asoc,
+				union sctp_params param,
+				struct sctp_ulpevent **evp)
+{
+	struct sctp_strreset_addstrm *addstrm = param.v;
+	struct sctp_stream *stream = asoc->stream;
+	__u32 result = SCTP_STRRESET_DENIED;
+	struct sctp_stream_in *streamin;
+	__u32 request_seq, incnt;
+	__u16 in;
+
+	request_seq = ntohl(addstrm->request_seq);
+	if (request_seq > asoc->strreset_inseq) {
+		result = SCTP_STRRESET_ERR_BAD_SEQNO;
+		goto out;
+	} else if (request_seq == asoc->strreset_inseq) {
+		asoc->strreset_inseq++;
+	}
+
+	if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ))
+		goto out;
+
+	if (asoc->strreset_chunk) {
+		if (!sctp_chunk_lookup_strreset_param(
+			asoc, 0, SCTP_PARAM_RESET_ADD_IN_STREAMS)) {
+			/* same process with outstanding isn't 0 */
+			result = SCTP_STRRESET_ERR_IN_PROGRESS;
+			goto out;
+		}
+
+		asoc->strreset_outstanding--;
+		asoc->strreset_outseq++;
+
+		if (!asoc->strreset_outstanding) {
+			struct sctp_transport *t;
+
+			t = asoc->strreset_chunk->transport;
+			if (del_timer(&t->reconf_timer))
+				sctp_transport_put(t);
+
+			sctp_chunk_put(asoc->strreset_chunk);
+			asoc->strreset_chunk = NULL;
+		}
+	}
+
+	in = ntohs(addstrm->number_of_streams);
+	incnt = stream->incnt + in;
+	if (!in || incnt > SCTP_MAX_STREAM)
+		goto out;
+
+	streamin = krealloc(stream->in, incnt * sizeof(*streamin),
+			    GFP_ATOMIC);
+	if (!streamin)
+		goto out;
+
+	memset(streamin + stream->incnt, 0, in * sizeof(*streamin));
+	stream->in = streamin;
+	stream->incnt = incnt;
+
+	result = SCTP_STRRESET_PERFORMED;
+
+	*evp = sctp_ulpevent_make_stream_change_event(asoc,
+		0, ntohs(addstrm->number_of_streams), 0, GFP_ATOMIC);
+
+out:
+	return sctp_make_strreset_resp(asoc, result, request_seq);
+}
+
+struct sctp_chunk *sctp_process_strreset_addstrm_in(
+				struct sctp_association *asoc,
+				union sctp_params param,
+				struct sctp_ulpevent **evp)
+{
+	struct sctp_strreset_addstrm *addstrm = param.v;
+	struct sctp_stream *stream = asoc->stream;
+	__u32 result = SCTP_STRRESET_DENIED;
+	struct sctp_stream_out *streamout;
+	struct sctp_chunk *chunk = NULL;
+	__u32 request_seq, outcnt;
+	__u16 out;
+
+	request_seq = ntohl(addstrm->request_seq);
+	if (request_seq > asoc->strreset_inseq) {
+		result = SCTP_STRRESET_ERR_BAD_SEQNO;
+		goto out;
+	} else if (request_seq == asoc->strreset_inseq) {
+		asoc->strreset_inseq++;
+	}
+
+	if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ))
+		goto out;
+
+	if (asoc->strreset_outstanding) {
+		result = SCTP_STRRESET_ERR_IN_PROGRESS;
+		goto out;
+	}
+
+	out = ntohs(addstrm->number_of_streams);
+	outcnt = stream->outcnt + out;
+	if (!out || outcnt > SCTP_MAX_STREAM)
+		goto out;
+
+	streamout = krealloc(stream->out, outcnt * sizeof(*streamout),
+			     GFP_ATOMIC);
+	if (!streamout)
+		goto out;
+
+	memset(streamout + stream->outcnt, 0, out * sizeof(*streamout));
+	stream->out = streamout;
+
+	chunk = sctp_make_strreset_addstrm(asoc, out, 0);
+	if (!chunk)
+		goto out;
+
+	asoc->strreset_chunk = chunk;
+	asoc->strreset_outstanding = 1;
+	sctp_chunk_hold(asoc->strreset_chunk);
+
+	stream->outcnt = outcnt;
+
+	*evp = sctp_ulpevent_make_stream_change_event(asoc,
+		0, 0, ntohs(addstrm->number_of_streams), GFP_ATOMIC);
+
+out:
+	if (!chunk)
+		chunk = sctp_make_strreset_resp(asoc, result, request_seq);
+
+	return chunk;
+}
+
+struct sctp_chunk *sctp_process_strreset_resp(
+				struct sctp_association *asoc,
+				union sctp_params param,
+				struct sctp_ulpevent **evp)
+{
+	struct sctp_strreset_resp *resp = param.v;
+	struct sctp_stream *stream = asoc->stream;
+	struct sctp_transport *t;
+	__u16 i, nums, flags = 0;
+	sctp_paramhdr_t *req;
+	__u32 result;
+
+	req = sctp_chunk_lookup_strreset_param(asoc, resp->response_seq, 0);
+	if (!req)
+		return NULL;
+
+	result = ntohl(resp->result);
+	if (result != SCTP_STRRESET_PERFORMED) {
+		/* if in progress, do nothing but retransmit */
+		if (result == SCTP_STRRESET_IN_PROGRESS)
+			return NULL;
+		else if (result == SCTP_STRRESET_DENIED)
+			flags = SCTP_STREAM_RESET_DENIED;
+		else
+			flags = SCTP_STREAM_RESET_FAILED;
+	}
+
+	if (req->type == SCTP_PARAM_RESET_OUT_REQUEST) {
+		struct sctp_strreset_outreq *outreq;
+		__u16 *str_p = NULL;
+
+		outreq = (struct sctp_strreset_outreq *)req;
+		nums = (ntohs(outreq->param_hdr.length) - sizeof(*outreq)) / 2;
+
+		if (result == SCTP_STRRESET_PERFORMED) {
+			if (nums) {
+				str_p = outreq->list_of_streams;
+				for (i = 0; i < nums; i++)
+					stream->out[ntohs(str_p[i])].ssn = 0;
+			} else {
+				for (i = 0; i < stream->outcnt; i++)
+					stream->out[i].ssn = 0;
+			}
+
+			flags = SCTP_STREAM_RESET_OUTGOING_SSN;
+		}
+
+		for (i = 0; i < stream->outcnt; i++)
+			stream->out[i].state = SCTP_STREAM_OPEN;
+
+		*evp = sctp_ulpevent_make_stream_reset_event(asoc, flags,
+			nums, str_p, GFP_ATOMIC);
+	} else if (req->type == SCTP_PARAM_RESET_IN_REQUEST) {
+		struct sctp_strreset_inreq *inreq;
+		__u16 *str_p = NULL;
+
+		/* if the result is performed, it's impossible for inreq */
+		if (result == SCTP_STRRESET_PERFORMED)
+			return NULL;
+
+		inreq = (struct sctp_strreset_inreq *)req;
+		nums = (ntohs(inreq->param_hdr.length) - sizeof(*inreq)) / 2;
+
+		str_p = inreq->list_of_streams;
+		*evp = sctp_ulpevent_make_stream_reset_event(asoc, flags,
+			nums, str_p, GFP_ATOMIC);
+	} else if (req->type == SCTP_PARAM_RESET_TSN_REQUEST) {
+		struct sctp_strreset_resptsn *resptsn;
+		__u32 stsn, rtsn;
+
+		/* check for resptsn, as sctp_verify_reconf didn't do it*/
+		if (ntohs(param.p->length) != sizeof(*resptsn))
+			return NULL;
+
+		resptsn = (struct sctp_strreset_resptsn *)resp;
+		stsn = ntohl(resptsn->senders_next_tsn);
+		rtsn = ntohl(resptsn->receivers_next_tsn);
+
+		if (result == SCTP_STRRESET_PERFORMED) {
+			__u32 mtsn = sctp_tsnmap_get_max_tsn_seen(
+						&asoc->peer.tsn_map);
+
+			sctp_ulpq_reasm_flushtsn(&asoc->ulpq, mtsn);
+			sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC);
+
+			sctp_tsnmap_init(&asoc->peer.tsn_map,
+					 SCTP_TSN_MAP_INITIAL,
+					 stsn, GFP_ATOMIC);
+
+			sctp_outq_free(&asoc->outqueue);
+
+			asoc->next_tsn = rtsn;
+			asoc->ctsn_ack_point = asoc->next_tsn - 1;
+			asoc->adv_peer_ack_point = asoc->ctsn_ack_point;
+
+			for (i = 0; i < stream->outcnt; i++)
+				stream->out[i].ssn = 0;
+			for (i = 0; i < stream->incnt; i++)
+				stream->in[i].ssn = 0;
+		}
+
+		for (i = 0; i < stream->outcnt; i++)
+			stream->out[i].state = SCTP_STREAM_OPEN;
+
+		*evp = sctp_ulpevent_make_assoc_reset_event(asoc, flags,
+			stsn, rtsn, GFP_ATOMIC);
+	} else if (req->type == SCTP_PARAM_RESET_ADD_OUT_STREAMS) {
+		struct sctp_strreset_addstrm *addstrm;
+		__u16 number;
+
+		addstrm = (struct sctp_strreset_addstrm *)req;
+		nums = ntohs(addstrm->number_of_streams);
+		number = stream->outcnt - nums;
+
+		if (result == SCTP_STRRESET_PERFORMED)
+			for (i = number; i < stream->outcnt; i++)
+				stream->out[i].state = SCTP_STREAM_OPEN;
+		else
+			stream->outcnt = number;
+
+		*evp = sctp_ulpevent_make_stream_change_event(asoc, flags,
+			0, nums, GFP_ATOMIC);
+	} else if (req->type == SCTP_PARAM_RESET_ADD_IN_STREAMS) {
+		struct sctp_strreset_addstrm *addstrm;
+
+		/* if the result is performed, it's impossible for addstrm in
+		 * request.
+		 */
+		if (result == SCTP_STRRESET_PERFORMED)
+			return NULL;
+
+		addstrm = (struct sctp_strreset_addstrm *)req;
+		nums = ntohs(addstrm->number_of_streams);
+
+		*evp = sctp_ulpevent_make_stream_change_event(asoc, flags,
+			nums, 0, GFP_ATOMIC);
+	}
+
+	asoc->strreset_outstanding--;
+	asoc->strreset_outseq++;
+
+	/* remove everything for this reconf request */
+	if (!asoc->strreset_outstanding) {
+		t = asoc->strreset_chunk->transport;
+		if (del_timer(&t->reconf_timer))
+			sctp_transport_put(t);
+
+		sctp_chunk_put(asoc->strreset_chunk);
+		asoc->strreset_chunk = NULL;
+	}
+
+	return NULL;
+}
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index daf8554fd42a..0e732f68c2bf 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -275,6 +275,13 @@ static struct ctl_table sctp_net_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 	{
+		.procname	= "reconf_enable",
+		.data		= &init_net.sctp.reconf_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
 		.procname	= "auth_enable",
 		.data		= &init_net.sctp.auth_enable,
 		.maxlen		= sizeof(int),
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index c8881bc542a0..ec2b3e013c2f 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -883,6 +883,62 @@ struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event(
 	return event;
 }
 
+struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event(
+	const struct sctp_association *asoc, __u16 flags, __u32 local_tsn,
+	__u32 remote_tsn, gfp_t gfp)
+{
+	struct sctp_assoc_reset_event *areset;
+	struct sctp_ulpevent *event;
+	struct sk_buff *skb;
+
+	event = sctp_ulpevent_new(sizeof(struct sctp_assoc_reset_event),
+				  MSG_NOTIFICATION, gfp);
+	if (!event)
+		return NULL;
+
+	skb = sctp_event2skb(event);
+	areset = (struct sctp_assoc_reset_event *)
+		skb_put(skb, sizeof(struct sctp_assoc_reset_event));
+
+	areset->assocreset_type = SCTP_ASSOC_RESET_EVENT;
+	areset->assocreset_flags = flags;
+	areset->assocreset_length = sizeof(struct sctp_assoc_reset_event);
+	sctp_ulpevent_set_owner(event, asoc);
+	areset->assocreset_assoc_id = sctp_assoc2id(asoc);
+	areset->assocreset_local_tsn = local_tsn;
+	areset->assocreset_remote_tsn = remote_tsn;
+
+	return event;
+}
+
+struct sctp_ulpevent *sctp_ulpevent_make_stream_change_event(
+	const struct sctp_association *asoc, __u16 flags,
+	__u32 strchange_instrms, __u32 strchange_outstrms, gfp_t gfp)
+{
+	struct sctp_stream_change_event *schange;
+	struct sctp_ulpevent *event;
+	struct sk_buff *skb;
+
+	event = sctp_ulpevent_new(sizeof(struct sctp_stream_change_event),
+				  MSG_NOTIFICATION, gfp);
+	if (!event)
+		return NULL;
+
+	skb = sctp_event2skb(event);
+	schange = (struct sctp_stream_change_event *)
+		skb_put(skb, sizeof(struct sctp_stream_change_event));
+
+	schange->strchange_type = SCTP_STREAM_CHANGE_EVENT;
+	schange->strchange_flags = flags;
+	schange->strchange_length = sizeof(struct sctp_stream_change_event);
+	sctp_ulpevent_set_owner(event, asoc);
+	schange->strchange_assoc_id = sctp_assoc2id(asoc);
+	schange->strchange_instrms = strchange_instrms;
+	schange->strchange_outstrms = strchange_outstrms;
+
+	return event;
+}
+
 /* Return the notification type, assuming this is a notification
  * event.
  */
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index a95f74bb5569..7e1f0e24d177 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -11,6 +11,7 @@
 #ifndef _SMC_IB_H
 #define _SMC_IB_H
 
+#include <linux/interrupt.h>
 #include <linux/if_ether.h>
 #include <rdma/ib_verbs.h>
 
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 9be6592e4a6f..bd0aac87b41a 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -416,6 +416,7 @@ static void tipc_nameseq_subscribe(struct name_seq *nseq,
 
 	tipc_subscrp_convert_seq(&s->evt.s.seq, s->swap, &ns);
 
+	tipc_subscrp_get(s);
 	list_add(&s->nameseq_list, &nseq->subscriptions);
 
 	if (!sseq)
@@ -787,6 +788,7 @@ void tipc_nametbl_unsubscribe(struct tipc_subscription *s)
 	if (seq != NULL) {
 		spin_lock_bh(&seq->lock);
 		list_del_init(&s->nameseq_list);
+		tipc_subscrp_put(s);
 		if (!seq->first_free && list_empty(&seq->subscriptions)) {
 			hlist_del_init_rcu(&seq->ns_list);
 			kfree(seq->sseqs);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 7130e73bd42c..15f6ce7bf868 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2511,6 +2511,28 @@ static int tipc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	}
 }
 
+static int tipc_socketpair(struct socket *sock1, struct socket *sock2)
+{
+	struct tipc_sock *tsk2 = tipc_sk(sock2->sk);
+	struct tipc_sock *tsk1 = tipc_sk(sock1->sk);
+	u32 onode = tipc_own_addr(sock_net(sock1->sk));
+
+	tsk1->peer.family = AF_TIPC;
+	tsk1->peer.addrtype = TIPC_ADDR_ID;
+	tsk1->peer.scope = TIPC_NODE_SCOPE;
+	tsk1->peer.addr.id.ref = tsk2->portid;
+	tsk1->peer.addr.id.node = onode;
+	tsk2->peer.family = AF_TIPC;
+	tsk2->peer.addrtype = TIPC_ADDR_ID;
+	tsk2->peer.scope = TIPC_NODE_SCOPE;
+	tsk2->peer.addr.id.ref = tsk1->portid;
+	tsk2->peer.addr.id.node = onode;
+
+	tipc_sk_finish_conn(tsk1, tsk2->portid, onode);
+	tipc_sk_finish_conn(tsk2, tsk1->portid, onode);
+	return 0;
+}
+
 /* Protocol switches for the various types of TIPC sockets */
 
 static const struct proto_ops msg_ops = {
@@ -2519,7 +2541,7 @@ static const struct proto_ops msg_ops = {
 	.release	= tipc_release,
 	.bind		= tipc_bind,
 	.connect	= tipc_connect,
-	.socketpair	= sock_no_socketpair,
+	.socketpair	= tipc_socketpair,
 	.accept		= sock_no_accept,
 	.getname	= tipc_getname,
 	.poll		= tipc_poll,
@@ -2540,7 +2562,7 @@ static const struct proto_ops packet_ops = {
 	.release	= tipc_release,
 	.bind		= tipc_bind,
 	.connect	= tipc_connect,
-	.socketpair	= sock_no_socketpair,
+	.socketpair	= tipc_socketpair,
 	.accept		= tipc_accept,
 	.getname	= tipc_getname,
 	.poll		= tipc_poll,
@@ -2561,7 +2583,7 @@ static const struct proto_ops stream_ops = {
 	.release	= tipc_release,
 	.bind		= tipc_bind,
 	.connect	= tipc_connect,
-	.socketpair	= sock_no_socketpair,
+	.socketpair	= tipc_socketpair,
 	.accept		= tipc_accept,
 	.getname	= tipc_getname,
 	.poll		= tipc_poll,
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 271cd66e4b3b..0bf91cd3733c 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -54,8 +54,6 @@ struct tipc_subscriber {
 
 static void tipc_subscrp_delete(struct tipc_subscription *sub);
 static void tipc_subscrb_put(struct tipc_subscriber *subscriber);
-static void tipc_subscrp_put(struct tipc_subscription *subscription);
-static void tipc_subscrp_get(struct tipc_subscription *subscription);
 
 /**
  * htohl - convert value to endianness used by destination
@@ -125,7 +123,6 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower,
 {
 	struct tipc_name_seq seq;
 
-	tipc_subscrp_get(sub);
 	tipc_subscrp_convert_seq(&sub->evt.s.seq, sub->swap, &seq);
 	if (!tipc_subscrp_check_overlap(&seq, found_lower, found_upper))
 		return;
@@ -135,7 +132,6 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower,
 
 	tipc_subscrp_send_event(sub, found_lower, found_upper, event, port_ref,
 				node);
-	tipc_subscrp_put(sub);
 }
 
 static void tipc_subscrp_timeout(unsigned long data)
@@ -145,6 +141,7 @@ static void tipc_subscrp_timeout(unsigned long data)
 
 	spin_lock_bh(&subscriber->lock);
 	tipc_nametbl_unsubscribe(sub);
+	list_del(&sub->subscrp_list);
 	spin_unlock_bh(&subscriber->lock);
 
 	/* Notify subscriber of timeout */
@@ -177,20 +174,17 @@ static void tipc_subscrp_kref_release(struct kref *kref)
 	struct tipc_net *tn = net_generic(sub->net, tipc_net_id);
 	struct tipc_subscriber *subscriber = sub->subscriber;
 
-	spin_lock_bh(&subscriber->lock);
-	list_del(&sub->subscrp_list);
 	atomic_dec(&tn->subscription_count);
-	spin_unlock_bh(&subscriber->lock);
 	kfree(sub);
 	tipc_subscrb_put(subscriber);
 }
 
-static void tipc_subscrp_put(struct tipc_subscription *subscription)
+void tipc_subscrp_put(struct tipc_subscription *subscription)
 {
 	kref_put(&subscription->kref, tipc_subscrp_kref_release);
 }
 
-static void tipc_subscrp_get(struct tipc_subscription *subscription)
+void tipc_subscrp_get(struct tipc_subscription *subscription)
 {
 	kref_get(&subscription->kref);
 }
@@ -210,11 +204,8 @@ static void tipc_subscrb_subscrp_delete(struct tipc_subscriber *subscriber,
 			continue;
 
 		tipc_nametbl_unsubscribe(sub);
-		tipc_subscrp_get(sub);
-		spin_unlock_bh(&subscriber->lock);
+		list_del(&sub->subscrp_list);
 		tipc_subscrp_delete(sub);
-		tipc_subscrp_put(sub);
-		spin_lock_bh(&subscriber->lock);
 
 		if (s)
 			break;
diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h
index ffdc214c117a..ee52957dc952 100644
--- a/net/tipc/subscr.h
+++ b/net/tipc/subscr.h
@@ -78,4 +78,7 @@ u32 tipc_subscrp_convert_seq_type(u32 type, int swap);
 int tipc_topsrv_start(struct net *net);
 void tipc_topsrv_stop(struct net *net);
 
+void tipc_subscrp_put(struct tipc_subscription *subscription);
+void tipc_subscrp_get(struct tipc_subscription *subscription);
+
 #endif
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 4be4fbbc0b50..10ae7823a19d 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -96,31 +96,23 @@ static int PROTOCOL_OVERRIDE = -1;
 
 static s32 vmci_transport_error_to_vsock_error(s32 vmci_error)
 {
-	int err;
-
 	switch (vmci_error) {
 	case VMCI_ERROR_NO_MEM:
-		err = ENOMEM;
-		break;
+		return -ENOMEM;
 	case VMCI_ERROR_DUPLICATE_ENTRY:
 	case VMCI_ERROR_ALREADY_EXISTS:
-		err = EADDRINUSE;
-		break;
+		return -EADDRINUSE;
 	case VMCI_ERROR_NO_ACCESS:
-		err = EPERM;
-		break;
+		return -EPERM;
 	case VMCI_ERROR_NO_RESOURCES:
-		err = ENOBUFS;
-		break;
+		return -ENOBUFS;
 	case VMCI_ERROR_INVALID_RESOURCE:
-		err = EHOSTUNREACH;
-		break;
+		return -EHOSTUNREACH;
 	case VMCI_ERROR_INVALID_ARGS:
 	default:
-		err = EINVAL;
+		break;
 	}
-
-	return err > 0 ? -err : err;
+	return -EINVAL;
 }
 
 static u32 vmci_transport_peer_rid(u32 peer_cid)
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 09e9d535bd74..d42b495b0992 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -34,6 +34,8 @@ hostprogs-y += sampleip
 hostprogs-y += tc_l2_redirect
 hostprogs-y += lwt_len_hist
 hostprogs-y += xdp_tx_iptunnel
+hostprogs-y += test_map_in_map
+hostprogs-y += per_socket_stats_example
 
 # Libbpf dependencies
 LIBBPF := ../../tools/lib/bpf/bpf.o
@@ -72,6 +74,8 @@ sampleip-objs := bpf_load.o $(LIBBPF) sampleip_user.o
 tc_l2_redirect-objs := bpf_load.o $(LIBBPF) tc_l2_redirect_user.o
 lwt_len_hist-objs := bpf_load.o $(LIBBPF) lwt_len_hist_user.o
 xdp_tx_iptunnel-objs := bpf_load.o $(LIBBPF) xdp_tx_iptunnel_user.o
+test_map_in_map-objs := bpf_load.o $(LIBBPF) test_map_in_map_user.o
+per_socket_stats_example-objs := $(LIBBPF) cookie_uid_helper_example.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -105,6 +109,8 @@ always += trace_event_kern.o
 always += sampleip_kern.o
 always += lwt_len_hist_kern.o
 always += xdp_tx_iptunnel_kern.o
+always += test_map_in_map_kern.o
+always += cookie_uid_helper_example.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/lib/
@@ -139,6 +145,7 @@ HOSTLOADLIBES_sampleip += -lelf
 HOSTLOADLIBES_tc_l2_redirect += -l elf
 HOSTLOADLIBES_lwt_len_hist += -l elf
 HOSTLOADLIBES_xdp_tx_iptunnel += -lelf
+HOSTLOADLIBES_test_map_in_map += -lelf
 
 # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
 #  make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index faaffe2e139a..52de9d88c021 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -80,6 +80,7 @@ struct bpf_map_def {
 	unsigned int value_size;
 	unsigned int max_entries;
 	unsigned int map_flags;
+	unsigned int inner_map_idx;
 };
 
 static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index b86ee54da2d1..dcdce1270d38 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -43,6 +43,7 @@ struct bpf_map_def {
 	unsigned int value_size;
 	unsigned int max_entries;
 	unsigned int map_flags;
+	unsigned int inner_map_idx;
 };
 
 static int populate_prog_array(const char *event, int prog_fd)
@@ -198,11 +199,22 @@ static int load_maps(struct bpf_map_def *maps, int len)
 
 	for (i = 0; i < len / sizeof(struct bpf_map_def); i++) {
 
-		map_fd[i] = bpf_create_map(maps[i].type,
-					   maps[i].key_size,
-					   maps[i].value_size,
-					   maps[i].max_entries,
-					   maps[i].map_flags);
+		if (maps[i].type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+		    maps[i].type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+			int inner_map_fd = map_fd[maps[i].inner_map_idx];
+
+			map_fd[i] = bpf_create_map_in_map(maps[i].type,
+							  maps[i].key_size,
+							  inner_map_fd,
+							  maps[i].max_entries,
+							  maps[i].map_flags);
+		} else {
+			map_fd[i] = bpf_create_map(maps[i].type,
+						   maps[i].key_size,
+						   maps[i].value_size,
+						   maps[i].max_entries,
+						   maps[i].map_flags);
+		}
 		if (map_fd[i] < 0) {
 			printf("failed to create a map: %d %s\n",
 			       errno, strerror(errno));
diff --git a/samples/bpf/cookie_uid_helper_example.c b/samples/bpf/cookie_uid_helper_example.c
new file mode 100644
index 000000000000..f6e5e58931c5
--- /dev/null
+++ b/samples/bpf/cookie_uid_helper_example.c
@@ -0,0 +1,217 @@
+/* This test is a demo of using get_socket_uid and get_socket_cookie
+ * helper function to do per socket based network traffic monitoring.
+ * It requires iptables version higher then 1.6.1. to load pinned eBPF
+ * program into the xt_bpf match.
+ *
+ * TEST:
+ * ./run_cookie_uid_helper_example.sh
+ * Then generate some traffic in variate ways. ping 0 -c 10 would work
+ * but the cookie and uid in this case could both be 0. A sample output
+ * with some traffic generated by web browser is shown below:
+ *
+ * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058
+ * cookie: 132, uid: 0x0, Pakcet Count: 2, Bytes Count: 286
+ * cookie: 812, uid: 0x3e8, Pakcet Count: 3, Bytes Count: 1726
+ * cookie: 802, uid: 0x3e8, Pakcet Count: 2, Bytes Count: 104
+ * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058
+ * cookie: 831, uid: 0x3e8, Pakcet Count: 2, Bytes Count: 104
+ * cookie: 0, uid: 0x0, Pakcet Count: 6, Bytes Count: 712
+ * cookie: 880, uid: 0xfffe, Pakcet Count: 1, Bytes Count: 70
+ *
+ * Clean up: if using shell script, the script file will delete the iptables
+ * rule and unmount the bpf program when exit. Else the iptables rule need
+ * to be deleted by hand, see run_cookie_uid_helper_example.sh for detail.
+ */
+
+#define _GNU_SOURCE
+
+#define offsetof(type, member)	__builtin_offsetof(type, member)
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <limits.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <bpf/bpf.h>
+#include "libbpf.h"
+
+struct stats {
+	uint32_t uid;
+	uint64_t packets;
+	uint64_t bytes;
+};
+
+static int map_fd, prog_fd;
+
+static void maps_create(void)
+{
+	map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(uint32_t),
+				sizeof(struct stats), 100, 0);
+	if (map_fd < 0)
+		error(1, errno, "map create failed!\n");
+}
+
+static void prog_load(void)
+{
+	static char log_buf[1 << 16];
+
+	struct bpf_insn prog[] = {
+		/*
+		 * Save sk_buff for future usage. value stored in R6 to R10 will
+		 * not be reset after a bpf helper function call.
+		 */
+		BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+		/*
+		 * pc1: BPF_FUNC_get_socket_cookie takes one parameter,
+		 * R1: sk_buff
+		 */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_get_socket_cookie),
+		/* pc2-4: save &socketCookie to r7 for future usage*/
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+		BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+		/*
+		 * pc5-8: set up the registers for BPF_FUNC_map_lookup_elem,
+		 * it takes two parameters (R1: map_fd,  R2: &socket_cookie)
+		 */
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_map_lookup_elem),
+		/*
+		 * pc9. if r0 != 0x0, go to pc+14, since we have the cookie
+		 * stored already
+		 * Otherwise do pc10-22 to setup a new data entry.
+		 */
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 14),
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_get_socket_uid),
+		/*
+		 * Place a struct stats in the R10 stack and sequentially
+		 * place the member value into the memory. Packets value
+		 * is set by directly place a IMM value 1 into the stack.
+		 */
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0,
+				-32 + offsetof(struct stats, uid)),
+		BPF_ST_MEM(BPF_DW, BPF_REG_10,
+				-32 + offsetof(struct stats, packets), 1),
+		/*
+		 * __sk_buff is a special struct used for eBPF program to
+		 * directly access some sk_buff field.
+		 */
+		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				offsetof(struct __sk_buff, len)),
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1,
+				-32 + offsetof(struct stats, bytes)),
+		/*
+		 * add new map entry using BPF_FUNC_map_update_elem, it takes
+		 * 4 parameters (R1: map_fd, R2: &socket_cookie, R3: &stats,
+		 * R4: flags)
+		 */
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+		BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -32),
+		BPF_MOV64_IMM(BPF_REG_4, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_map_update_elem),
+		BPF_JMP_IMM(BPF_JA, 0, 0, 5),
+		/*
+		 * pc24-30 update the packet info to a exist data entry, it can
+		 * be done by directly write to pointers instead of using
+		 * BPF_FUNC_map_update_elem helper function
+		 */
+		BPF_MOV64_REG(BPF_REG_9, BPF_REG_0),
+		BPF_MOV64_IMM(BPF_REG_1, 1),
+		BPF_STX_XADD(BPF_DW, BPF_REG_9, BPF_REG_1,
+				offsetof(struct stats, packets)),
+		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				offsetof(struct __sk_buff, len)),
+		BPF_STX_XADD(BPF_DW, BPF_REG_9, BPF_REG_1,
+				offsetof(struct stats, bytes)),
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6,
+				offsetof(struct __sk_buff, len)),
+		BPF_EXIT_INSN(),
+	};
+	prog_fd = bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog,
+					ARRAY_SIZE(prog), "GPL", 0,
+					log_buf, sizeof(log_buf));
+	if (prog_fd < 0)
+		error(1, errno, "failed to load prog\n%s\n", log_buf);
+}
+
+static void prog_attach_iptables(char *file)
+{
+	int ret;
+	char rules[100];
+
+	if (bpf_obj_pin(prog_fd, file))
+		error(1, errno, "bpf_obj_pin");
+	if (strlen(file) > 50) {
+		printf("file path too long: %s\n", file);
+		exit(1);
+	}
+	sprintf(rules, "iptables -A INPUT -m bpf --object-pinned %s -j ACCEPT",
+		file);
+	ret = system(rules);
+	if (ret < 0) {
+		printf("iptables rule update failed: %d/n", WEXITSTATUS(ret));
+		exit(1);
+	}
+}
+
+static void print_table(void)
+{
+	struct stats curEntry;
+	uint32_t curN = UINT32_MAX;
+	uint32_t nextN, res;
+
+	while (bpf_map_get_next_key(map_fd, &curN, &nextN) > -1) {
+		curN = nextN;
+		res = bpf_map_lookup_elem(map_fd, &curN, &curEntry);
+		if (res < 0) {
+			error(1, errno, "fail to get entry value of Key: %u\n",
+				curN);
+		} else {
+			printf("cookie: %u, uid: 0x%x, Packet Count: %lu,"
+				" Bytes Count: %lu\n", curN, curEntry.uid,
+				curEntry.packets, curEntry.bytes);
+		}
+	}
+}
+
+int main(int argc, char *argv[])
+{
+	if (argc > 2) {
+		printf("Too many argument provided\n");
+		return 1;
+	} else if (argc < 2) {
+		printf("Usage: %s bpfObjName\n", argv[0]);
+		return 1;
+	}
+
+	maps_create();
+	prog_load();
+	prog_attach_iptables(argv[1]);
+
+	while (true) {
+		print_table();
+		printf("\n");
+		sleep(1);
+	};
+
+	return 0;
+}
diff --git a/samples/bpf/libbpf.h b/samples/bpf/libbpf.h
index 3705fba453a0..8ab36a04c174 100644
--- a/samples/bpf/libbpf.h
+++ b/samples/bpf/libbpf.h
@@ -135,6 +135,16 @@ struct bpf_insn;
 		.off   = OFF,					\
 		.imm   = 0 })
 
+/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */
+
+#define BPF_STX_XADD(SIZE, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
 /* Memory store, *(uint *) (dst_reg + off16) = imm32 */
 
 #define BPF_ST_MEM(SIZE, DST, OFF, IMM)				\
diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c
index a91872a97742..9da2a3441b0a 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -65,6 +65,13 @@ struct bpf_map_def SEC("maps") lpm_trie_map_alloc = {
 	.map_flags = BPF_F_NO_PREALLOC,
 };
 
+struct bpf_map_def SEC("maps") array_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(long),
+	.max_entries = MAX_ENTRIES,
+};
+
 SEC("kprobe/sys_getuid")
 int stress_hmap(struct pt_regs *ctx)
 {
@@ -165,5 +172,31 @@ int stress_lpm_trie_map_alloc(struct pt_regs *ctx)
 	return 0;
 }
 
+SEC("kprobe/sys_getpgid")
+int stress_hash_map_lookup(struct pt_regs *ctx)
+{
+	u32 key = 1, i;
+	long *value;
+
+#pragma clang loop unroll(full)
+	for (i = 0; i < 64; ++i)
+		value = bpf_map_lookup_elem(&hash_map, &key);
+
+	return 0;
+}
+
+SEC("kprobe/sys_getpgrp")
+int stress_array_map_lookup(struct pt_regs *ctx)
+{
+	u32 key = 1, i;
+	long *value;
+
+#pragma clang loop unroll(full)
+	for (i = 0; i < 64; ++i)
+		value = bpf_map_lookup_elem(&array_map, &key);
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
 u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index 680260a91f50..e29ff318a793 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -38,6 +38,8 @@ static __u64 time_get_ns(void)
 #define LRU_HASH_PREALLOC	(1 << 4)
 #define PERCPU_LRU_HASH_PREALLOC	(1 << 5)
 #define LPM_KMALLOC		(1 << 6)
+#define HASH_LOOKUP		(1 << 7)
+#define ARRAY_LOOKUP		(1 << 8)
 
 static int test_flags = ~0;
 
@@ -125,6 +127,30 @@ static void test_lpm_kmalloc(int cpu)
 	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
 }
 
+static void test_hash_lookup(int cpu)
+{
+	__u64 start_time;
+	int i;
+
+	start_time = time_get_ns();
+	for (i = 0; i < MAX_CNT; i++)
+		syscall(__NR_getpgid, 0);
+	printf("%d:hash_lookup %lld lookups per sec\n",
+	       cpu, MAX_CNT * 1000000000ll * 64 / (time_get_ns() - start_time));
+}
+
+static void test_array_lookup(int cpu)
+{
+	__u64 start_time;
+	int i;
+
+	start_time = time_get_ns();
+	for (i = 0; i < MAX_CNT; i++)
+		syscall(__NR_getpgrp, 0);
+	printf("%d:array_lookup %lld lookups per sec\n",
+	       cpu, MAX_CNT * 1000000000ll * 64 / (time_get_ns() - start_time));
+}
+
 static void loop(int cpu)
 {
 	cpu_set_t cpuset;
@@ -153,6 +179,12 @@ static void loop(int cpu)
 
 	if (test_flags & LPM_KMALLOC)
 		test_lpm_kmalloc(cpu);
+
+	if (test_flags & HASH_LOOKUP)
+		test_hash_lookup(cpu);
+
+	if (test_flags & ARRAY_LOOKUP)
+		test_array_lookup(cpu);
 }
 
 static void run_perf_test(int tasks)
diff --git a/samples/bpf/run_cookie_uid_helper_example.sh b/samples/bpf/run_cookie_uid_helper_example.sh
new file mode 100644
index 000000000000..40da8aa75c44
--- /dev/null
+++ b/samples/bpf/run_cookie_uid_helper_example.sh
@@ -0,0 +1,14 @@
+#!/bin/bash
+local_dir="$(pwd)"
+root_dir=$local_dir/../..
+mnt_dir=$(mktemp -d --tmp)
+
+on_exit() {
+	iptables -D INPUT -m bpf --object-pinned ${mnt_dir}/bpf_prog -j ACCEPT
+	umount ${mnt_dir}
+	rm -r ${mnt_dir}
+}
+
+trap on_exit EXIT
+mount -t bpf bpf ${mnt_dir}
+./per_socket_stats_example ${mnt_dir}/bpf_prog
diff --git a/samples/bpf/test_map_in_map_kern.c b/samples/bpf/test_map_in_map_kern.c
new file mode 100644
index 000000000000..42c44d091dd1
--- /dev/null
+++ b/samples/bpf/test_map_in_map_kern.c
@@ -0,0 +1,173 @@
+/*
+ * Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#define KBUILD_MODNAME "foo"
+#include <linux/ptrace.h>
+#include <linux/version.h>
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/in6.h>
+#include "bpf_helpers.h"
+
+#define MAX_NR_PORTS 65536
+
+/* map #0 */
+struct bpf_map_def SEC("maps") port_a = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(int),
+	.max_entries = MAX_NR_PORTS,
+};
+
+/* map #1 */
+struct bpf_map_def SEC("maps") port_h = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(int),
+	.max_entries = 1,
+};
+
+/* map #2 */
+struct bpf_map_def SEC("maps") reg_result_h = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(int),
+	.max_entries = 1,
+};
+
+/* map #3 */
+struct bpf_map_def SEC("maps") inline_result_h = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(int),
+	.max_entries = 1,
+};
+
+/* map #4 */ /* Test case #0 */
+struct bpf_map_def SEC("maps") a_of_port_a = {
+	.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
+	.key_size = sizeof(u32),
+	.inner_map_idx = 0, /* map_fd[0] is port_a */
+	.max_entries = MAX_NR_PORTS,
+};
+
+/* map #5 */ /* Test case #1 */
+struct bpf_map_def SEC("maps") h_of_port_a = {
+	.type = BPF_MAP_TYPE_HASH_OF_MAPS,
+	.key_size = sizeof(u32),
+	.inner_map_idx = 0, /* map_fd[0] is port_a */
+	.max_entries = 1,
+};
+
+/* map #6 */ /* Test case #2 */
+struct bpf_map_def SEC("maps") h_of_port_h = {
+	.type = BPF_MAP_TYPE_HASH_OF_MAPS,
+	.key_size = sizeof(u32),
+	.inner_map_idx = 1, /* map_fd[1] is port_h */
+	.max_entries = 1,
+};
+
+static __always_inline int do_reg_lookup(void *inner_map, u32 port)
+{
+	int *result;
+
+	result = bpf_map_lookup_elem(inner_map, &port);
+	return result ? *result : -ENOENT;
+}
+
+static __always_inline int do_inline_array_lookup(void *inner_map, u32 port)
+{
+	int *result;
+
+	if (inner_map != &port_a)
+		return -EINVAL;
+
+	result = bpf_map_lookup_elem(&port_a, &port);
+	return result ? *result : -ENOENT;
+}
+
+static __always_inline int do_inline_hash_lookup(void *inner_map, u32 port)
+{
+	int *result;
+
+	if (inner_map != &port_h)
+		return -EINVAL;
+
+	result = bpf_map_lookup_elem(&port_h, &port);
+	return result ? *result : -ENOENT;
+}
+
+SEC("kprobe/sys_connect")
+int trace_sys_connect(struct pt_regs *ctx)
+{
+	struct sockaddr_in6 *in6;
+	u16 test_case, port, dst6[8];
+	int addrlen, ret, inline_ret, ret_key = 0;
+	u32 port_key;
+	void *outer_map, *inner_map;
+	bool inline_hash = false;
+
+	in6 = (struct sockaddr_in6 *)PT_REGS_PARM2(ctx);
+	addrlen = (int)PT_REGS_PARM3(ctx);
+
+	if (addrlen != sizeof(*in6))
+		return 0;
+
+	ret = bpf_probe_read(dst6, sizeof(dst6), &in6->sin6_addr);
+	if (ret) {
+		inline_ret = ret;
+		goto done;
+	}
+
+	if (dst6[0] != 0xdead || dst6[1] != 0xbeef)
+		return 0;
+
+	test_case = dst6[7];
+
+	ret = bpf_probe_read(&port, sizeof(port), &in6->sin6_port);
+	if (ret) {
+		inline_ret = ret;
+		goto done;
+	}
+
+	port_key = port;
+
+	ret = -ENOENT;
+	if (test_case == 0) {
+		outer_map = &a_of_port_a;
+	} else if (test_case == 1) {
+		outer_map = &h_of_port_a;
+	} else if (test_case == 2) {
+		outer_map = &h_of_port_h;
+	} else {
+		ret = __LINE__;
+		inline_ret = ret;
+		goto done;
+	}
+
+	inner_map = bpf_map_lookup_elem(outer_map, &port_key);
+	if (!inner_map) {
+		ret = __LINE__;
+		inline_ret = ret;
+		goto done;
+	}
+
+	ret = do_reg_lookup(inner_map, port_key);
+
+	if (test_case == 0 || test_case == 1)
+		inline_ret = do_inline_array_lookup(inner_map, port_key);
+	else
+		inline_ret = do_inline_hash_lookup(inner_map, port_key);
+
+done:
+	bpf_map_update_elem(&reg_result_h, &ret_key, &ret, BPF_ANY);
+	bpf_map_update_elem(&inline_result_h, &ret_key, &inline_ret, BPF_ANY);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/test_map_in_map_user.c b/samples/bpf/test_map_in_map_user.c
new file mode 100644
index 000000000000..f62fdc2bd428
--- /dev/null
+++ b/samples/bpf/test_map_in_map_user.c
@@ -0,0 +1,116 @@
+/*
+ * Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <sys/resource.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+#include <stdint.h>
+#include <assert.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+#define PORT_A		(map_fd[0])
+#define PORT_H		(map_fd[1])
+#define REG_RESULT_H	(map_fd[2])
+#define INLINE_RESULT_H	(map_fd[3])
+#define A_OF_PORT_A	(map_fd[4]) /* Test case #0 */
+#define H_OF_PORT_A	(map_fd[5]) /* Test case #1 */
+#define H_OF_PORT_H	(map_fd[6]) /* Test case #2 */
+
+static const char * const test_names[] = {
+	"Array of Array",
+	"Hash of Array",
+	"Hash of Hash",
+};
+
+#define NR_TESTS (sizeof(test_names) / sizeof(*test_names))
+
+static void populate_map(uint32_t port_key, int magic_result)
+{
+	int ret;
+
+	ret = bpf_map_update_elem(PORT_A, &port_key, &magic_result, BPF_ANY);
+	assert(!ret);
+
+	ret = bpf_map_update_elem(PORT_H, &port_key, &magic_result,
+				  BPF_NOEXIST);
+	assert(!ret);
+
+	ret = bpf_map_update_elem(A_OF_PORT_A, &port_key, &PORT_A, BPF_ANY);
+	assert(!ret);
+
+	ret = bpf_map_update_elem(H_OF_PORT_A, &port_key, &PORT_A, BPF_NOEXIST);
+	assert(!ret);
+
+	ret = bpf_map_update_elem(H_OF_PORT_H, &port_key, &PORT_H, BPF_NOEXIST);
+	assert(!ret);
+}
+
+static void test_map_in_map(void)
+{
+	struct sockaddr_in6 in6 = { .sin6_family = AF_INET6 };
+	uint32_t result_key = 0, port_key;
+	int result, inline_result;
+	int magic_result = 0xfaceb00c;
+	int ret;
+	int i;
+
+	port_key = rand() & 0x00FF;
+	populate_map(port_key, magic_result);
+
+	in6.sin6_addr.s6_addr16[0] = 0xdead;
+	in6.sin6_addr.s6_addr16[1] = 0xbeef;
+	in6.sin6_port = port_key;
+
+	for (i = 0; i < NR_TESTS; i++) {
+		printf("%s: ", test_names[i]);
+
+		in6.sin6_addr.s6_addr16[7] = i;
+		ret = connect(-1, (struct sockaddr *)&in6, sizeof(in6));
+		assert(ret == -1 && errno == EBADF);
+
+		ret = bpf_map_lookup_elem(REG_RESULT_H, &result_key, &result);
+		assert(!ret);
+
+		ret = bpf_map_lookup_elem(INLINE_RESULT_H, &result_key,
+					  &inline_result);
+		assert(!ret);
+
+		if (result != magic_result || inline_result != magic_result) {
+			printf("Error. result:%d inline_result:%d\n",
+			       result, inline_result);
+			exit(1);
+		}
+
+		bpf_map_delete_elem(REG_RESULT_H, &result_key);
+		bpf_map_delete_elem(INLINE_RESULT_H, &result_key);
+
+		printf("Pass\n");
+	}
+}
+
+int main(int argc, char **argv)
+{
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+	char filename[256];
+
+	assert(!setrlimit(RLIMIT_MEMLOCK, &r));
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	test_map_in_map();
+
+	return 0;
+}
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index 2ca9cde939d4..8e67bb4c9cab 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -69,6 +69,7 @@ static struct nlmsg_perm nlmsg_route_perms[] =
 	{ RTM_GETDCB,		NETLINK_ROUTE_SOCKET__NLMSG_READ  },
 	{ RTM_SETDCB,		NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
 	{ RTM_NEWNETCONF,	NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELNETCONF,	NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
 	{ RTM_GETNETCONF,	NETLINK_ROUTE_SOCKET__NLMSG_READ  },
 	{ RTM_NEWMDB,		NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
 	{ RTM_DELMDB,		NETLINK_ROUTE_SOCKET__NLMSG_WRITE  },
diff --git a/tools/hv/bondvf.sh b/tools/hv/bondvf.sh
index 4aa5369ffa4e..d85968cb1bf2 100755
--- a/tools/hv/bondvf.sh
+++ b/tools/hv/bondvf.sh
@@ -101,9 +101,25 @@ function create_bond_cfg_redhat {
 	echo BONDING_OPTS=\"mode=active-backup miimon=100 primary=$2\" >>$fn
 }
 
+function del_eth_cfg_ubuntu {
+	local fn=$cfgdir/interfaces
+	local tmpfl=$(mktemp)
+
+	local nic_start='^[ \t]*(auto|iface|mapping|allow-.*)[ \t]+'$1
+	local nic_end='^[ \t]*(auto|iface|mapping|allow-.*|source)'
+
+	awk "/$nic_end/{x=0} x{next} /$nic_start/{x=1;next} 1"  $fn >$tmpfl
+
+	cp $tmpfl $fn
+
+	rm $tmpfl
+}
+
 function create_eth_cfg_ubuntu {
 	local fn=$cfgdir/interfaces
 
+	del_eth_cfg_ubuntu $1
+
 	echo $'\n'auto $1 >>$fn
 	echo iface $1 inet manual >>$fn
 	echo bond-master $2 >>$fn
@@ -119,6 +135,8 @@ function create_eth_cfg_pri_ubuntu {
 function create_bond_cfg_ubuntu {
 	local fn=$cfgdir/interfaces
 
+	del_eth_cfg_ubuntu $1
+
 	echo $'\n'auto $1 >>$fn
 	echo iface $1 inet dhcp >>$fn
 	echo bond-mode active-backup >>$fn
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0539a0ceef38..a1d95386f562 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -81,6 +81,7 @@ enum bpf_cmd {
 	BPF_OBJ_GET,
 	BPF_PROG_ATTACH,
 	BPF_PROG_DETACH,
+	BPF_PROG_TEST_RUN,
 };
 
 enum bpf_map_type {
@@ -96,6 +97,8 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_LRU_HASH,
 	BPF_MAP_TYPE_LRU_PERCPU_HASH,
 	BPF_MAP_TYPE_LPM_TRIE,
+	BPF_MAP_TYPE_ARRAY_OF_MAPS,
+	BPF_MAP_TYPE_HASH_OF_MAPS,
 };
 
 enum bpf_prog_type {
@@ -152,6 +155,7 @@ union bpf_attr {
 		__u32	value_size;	/* size of value in bytes */
 		__u32	max_entries;	/* max number of entries in a map */
 		__u32	map_flags;	/* prealloc or not */
+		__u32	inner_map_fd;	/* fd pointing to the inner map */
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -186,6 +190,17 @@ union bpf_attr {
 		__u32		attach_type;
 		__u32		attach_flags;
 	};
+
+	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
+		__u32		prog_fd;
+		__u32		retval;
+		__u32		data_size_in;
+		__u32		data_size_out;
+		__aligned_u64	data_in;
+		__aligned_u64	data_out;
+		__u32		repeat;
+		__u32		duration;
+	} test;
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:
@@ -456,6 +471,18 @@ union bpf_attr {
  *     Return:
  *       > 0 length of the string including the trailing NUL on success
  *       < 0 error
+ *
+ * u64 bpf_bpf_get_socket_cookie(skb)
+ *     Get the cookie for the socket stored inside sk_buff.
+ *     @skb: pointer to skb
+ *     Return: 8 Bytes non-decreasing number on success or 0 if the socket
+ *     field is missing inside sk_buff
+ *
+ * u32 bpf_get_socket_uid(skb)
+ *     Get the owner uid of the socket stored inside sk_buff.
+ *     @skb: pointer to skb
+ *     Return: uid of the socket owner on success or 0 if the socket pointer
+ *     inside sk_buff is NULL
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -503,7 +530,9 @@ union bpf_attr {
 	FN(get_numa_node_id),		\
 	FN(skb_change_head),		\
 	FN(xdp_adjust_head),		\
-	FN(probe_read_str),
+	FN(probe_read_str),		\
+	FN(get_socket_cookie),		\
+	FN(get_socket_uid),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 207c2eeddab0..f84c398c11f4 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -69,6 +69,23 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size,
 	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }
 
+int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
+			  int inner_map_fd, int max_entries, __u32 map_flags)
+{
+	union bpf_attr attr;
+
+	memset(&attr, '\0', sizeof(attr));
+
+	attr.map_type = map_type;
+	attr.key_size = key_size;
+	attr.value_size = 4;
+	attr.inner_map_fd = inner_map_fd;
+	attr.max_entries = max_entries;
+	attr.map_flags = map_flags;
+
+	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+}
+
 int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 		     size_t insns_cnt, const char *license,
 		     __u32 kern_version, char *log_buf, size_t log_buf_sz)
@@ -192,3 +209,27 @@ int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
 
 	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
 }
+
+int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
+		      void *data_out, __u32 *size_out, __u32 *retval,
+		      __u32 *duration)
+{
+	union bpf_attr attr;
+	int ret;
+
+	bzero(&attr, sizeof(attr));
+	attr.test.prog_fd = prog_fd;
+	attr.test.data_in = ptr_to_u64(data);
+	attr.test.data_out = ptr_to_u64(data_out);
+	attr.test.data_size_in = size;
+	attr.test.repeat = repeat;
+
+	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
+	if (size_out)
+		*size_out = attr.test.data_size_out;
+	if (retval)
+		*retval = attr.test.retval;
+	if (duration)
+		*duration = attr.test.duration;
+	return ret;
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 09c3dcac0496..edb4daeff7a5 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -26,6 +26,8 @@
 
 int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
 		   int max_entries, __u32 map_flags);
+int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
+			  int inner_map_fd, int max_entries, __u32 map_flags);
 
 /* Recommend log buffer size */
 #define BPF_LOG_BUF_SIZE 65536
@@ -45,6 +47,8 @@ int bpf_obj_get(const char *pathname);
 int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
 		    unsigned int flags);
 int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
-
+int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
+		      void *data_out, __u32 *size_out, __u32 *retval,
+		      __u32 *duration);
 
 #endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ac6eb863b2a4..1a2c07eb7795 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1618,8 +1618,7 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n)
 	return fd;
 }
 
-static void bpf_program__set_type(struct bpf_program *prog,
-				  enum bpf_prog_type type)
+void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
 {
 	prog->type = type;
 }
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index b30394f9947a..32c7252f734e 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -25,6 +25,7 @@
 #include <stdint.h>
 #include <stdbool.h>
 #include <sys/types.h>  // for size_t
+#include <linux/bpf.h>
 
 enum libbpf_errno {
 	__LIBBPF_ERRNO__START = 4000,
@@ -185,6 +186,7 @@ int bpf_program__set_sched_cls(struct bpf_program *prog);
 int bpf_program__set_sched_act(struct bpf_program *prog);
 int bpf_program__set_xdp(struct bpf_program *prog);
 int bpf_program__set_perf_event(struct bpf_program *prog);
+void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type);
 
 bool bpf_program__is_socket_filter(struct bpf_program *prog);
 bool bpf_program__is_tracepoint(struct bpf_program *prog);
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 9af09e8099c0..d8d94b9bd76c 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -8,16 +8,18 @@ ifneq ($(wildcard $(GENHDR)),)
   GENFLAGS := -DHAVE_GENHDR
 endif
 
-CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS)
-LDLIBS += -lcap
+CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
+LDLIBS += -lcap -lelf
 
-TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map
+TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs
+
+TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o
 
 TEST_PROGS := test_kmod.sh
 
 include ../lib.mk
 
-BPFOBJ := $(OUTPUT)/bpf.o
+BPFOBJ := $(OUTPUT)/libbpf.a
 
 $(TEST_GEN_PROGS): $(BPFOBJ)
 
@@ -28,3 +30,10 @@ force:
 
 $(BPFOBJ): force
 	$(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/
+
+CLANG ?= clang
+
+%.o: %.c
+	$(CLANG) -I../../../include/uapi -I../../../../samples/bpf/ \
+		-D__x86_64__ -Wno-compare-distinct-pointer-types \
+		-O2 -target bpf -c $< -o $@
diff --git a/tools/testing/selftests/bpf/test_iptunnel_common.h b/tools/testing/selftests/bpf/test_iptunnel_common.h
new file mode 100644
index 000000000000..e4cd252a1b20
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_iptunnel_common.h
@@ -0,0 +1,37 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _TEST_IPTNL_COMMON_H
+#define _TEST_IPTNL_COMMON_H
+
+#include <linux/types.h>
+
+#define MAX_IPTNL_ENTRIES 256U
+
+struct vip {
+	union {
+		__u32 v6[4];
+		__u32 v4;
+	} daddr;
+	__u16 dport;
+	__u16 family;
+	__u8 protocol;
+};
+
+struct iptnl_info {
+	union {
+		__u32 v6[4];
+		__u32 v4;
+	} saddr;
+	union {
+		__u32 v6[4];
+		__u32 v4;
+	} daddr;
+	__u16 family;
+	__u8 dmac[6];
+};
+
+#endif
diff --git a/tools/testing/selftests/bpf/test_l4lb.c b/tools/testing/selftests/bpf/test_l4lb.c
new file mode 100644
index 000000000000..368bfe8b9842
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_l4lb.c
@@ -0,0 +1,474 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stddef.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/pkt_cls.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include "bpf_helpers.h"
+#include "test_iptunnel_common.h"
+
+#define htons __builtin_bswap16
+#define ntohs __builtin_bswap16
+int _version SEC("version") = 1;
+
+static inline __u32 rol32(__u32 word, unsigned int shift)
+{
+	return (word << shift) | (word >> ((-shift) & 31));
+}
+
+/* copy paste of jhash from kernel sources to make sure llvm
+ * can compile it into valid sequence of bpf instructions
+ */
+#define __jhash_mix(a, b, c)			\
+{						\
+	a -= c;  a ^= rol32(c, 4);  c += b;	\
+	b -= a;  b ^= rol32(a, 6);  a += c;	\
+	c -= b;  c ^= rol32(b, 8);  b += a;	\
+	a -= c;  a ^= rol32(c, 16); c += b;	\
+	b -= a;  b ^= rol32(a, 19); a += c;	\
+	c -= b;  c ^= rol32(b, 4);  b += a;	\
+}
+
+#define __jhash_final(a, b, c)			\
+{						\
+	c ^= b; c -= rol32(b, 14);		\
+	a ^= c; a -= rol32(c, 11);		\
+	b ^= a; b -= rol32(a, 25);		\
+	c ^= b; c -= rol32(b, 16);		\
+	a ^= c; a -= rol32(c, 4);		\
+	b ^= a; b -= rol32(a, 14);		\
+	c ^= b; c -= rol32(b, 24);		\
+}
+
+#define JHASH_INITVAL		0xdeadbeef
+
+typedef unsigned int u32;
+
+static inline u32 jhash(const void *key, u32 length, u32 initval)
+{
+	u32 a, b, c;
+	const unsigned char *k = key;
+
+	a = b = c = JHASH_INITVAL + length + initval;
+
+	while (length > 12) {
+		a += *(u32 *)(k);
+		b += *(u32 *)(k + 4);
+		c += *(u32 *)(k + 8);
+		__jhash_mix(a, b, c);
+		length -= 12;
+		k += 12;
+	}
+	switch (length) {
+	case 12: c += (u32)k[11]<<24;
+	case 11: c += (u32)k[10]<<16;
+	case 10: c += (u32)k[9]<<8;
+	case 9:  c += k[8];
+	case 8:  b += (u32)k[7]<<24;
+	case 7:  b += (u32)k[6]<<16;
+	case 6:  b += (u32)k[5]<<8;
+	case 5:  b += k[4];
+	case 4:  a += (u32)k[3]<<24;
+	case 3:  a += (u32)k[2]<<16;
+	case 2:  a += (u32)k[1]<<8;
+	case 1:  a += k[0];
+		 __jhash_final(a, b, c);
+	case 0: /* Nothing left to add */
+		break;
+	}
+
+	return c;
+}
+
+static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
+{
+	a += initval;
+	b += initval;
+	c += initval;
+	__jhash_final(a, b, c);
+	return c;
+}
+
+static inline u32 jhash_2words(u32 a, u32 b, u32 initval)
+{
+	return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
+}
+
+#define PCKT_FRAGMENTED 65343
+#define IPV4_HDR_LEN_NO_OPT 20
+#define IPV4_PLUS_ICMP_HDR 28
+#define IPV6_PLUS_ICMP_HDR 48
+#define RING_SIZE 2
+#define MAX_VIPS 12
+#define MAX_REALS 5
+#define CTL_MAP_SIZE 16
+#define CH_RINGS_SIZE (MAX_VIPS * RING_SIZE)
+#define F_IPV6 (1 << 0)
+#define F_HASH_NO_SRC_PORT (1 << 0)
+#define F_ICMP (1 << 0)
+#define F_SYN_SET (1 << 1)
+
+struct packet_description {
+	union {
+		__be32 src;
+		__be32 srcv6[4];
+	};
+	union {
+		__be32 dst;
+		__be32 dstv6[4];
+	};
+	union {
+		__u32 ports;
+		__u16 port16[2];
+	};
+	__u8 proto;
+	__u8 flags;
+};
+
+struct ctl_value {
+	union {
+		__u64 value;
+		__u32 ifindex;
+		__u8 mac[6];
+	};
+};
+
+struct vip_meta {
+	__u32 flags;
+	__u32 vip_num;
+};
+
+struct real_definition {
+	union {
+		__be32 dst;
+		__be32 dstv6[4];
+	};
+	__u8 flags;
+};
+
+struct vip_stats {
+	__u64 bytes;
+	__u64 pkts;
+};
+
+struct eth_hdr {
+	unsigned char eth_dest[ETH_ALEN];
+	unsigned char eth_source[ETH_ALEN];
+	unsigned short eth_proto;
+};
+
+struct bpf_map_def SEC("maps") vip_map = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(struct vip),
+	.value_size = sizeof(struct vip_meta),
+	.max_entries = MAX_VIPS,
+};
+
+struct bpf_map_def SEC("maps") ch_rings = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u32),
+	.max_entries = CH_RINGS_SIZE,
+};
+
+struct bpf_map_def SEC("maps") reals = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct real_definition),
+	.max_entries = MAX_REALS,
+};
+
+struct bpf_map_def SEC("maps") stats = {
+	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct vip_stats),
+	.max_entries = MAX_VIPS,
+};
+
+struct bpf_map_def SEC("maps") ctl_array = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct ctl_value),
+	.max_entries = CTL_MAP_SIZE,
+};
+
+static __always_inline __u32 get_packet_hash(struct packet_description *pckt,
+					     bool ipv6)
+{
+	if (ipv6)
+		return jhash_2words(jhash(pckt->srcv6, 16, MAX_VIPS),
+				    pckt->ports, CH_RINGS_SIZE);
+	else
+		return jhash_2words(pckt->src, pckt->ports, CH_RINGS_SIZE);
+}
+
+static __always_inline bool get_packet_dst(struct real_definition **real,
+					   struct packet_description *pckt,
+					   struct vip_meta *vip_info,
+					   bool is_ipv6)
+{
+	__u32 hash = get_packet_hash(pckt, is_ipv6) % RING_SIZE;
+	__u32 key = RING_SIZE * vip_info->vip_num + hash;
+	__u32 *real_pos;
+
+	real_pos = bpf_map_lookup_elem(&ch_rings, &key);
+	if (!real_pos)
+		return false;
+	key = *real_pos;
+	*real = bpf_map_lookup_elem(&reals, &key);
+	if (!(*real))
+		return false;
+	return true;
+}
+
+static __always_inline int parse_icmpv6(void *data, void *data_end, __u64 off,
+					struct packet_description *pckt)
+{
+	struct icmp6hdr *icmp_hdr;
+	struct ipv6hdr *ip6h;
+
+	icmp_hdr = data + off;
+	if (icmp_hdr + 1 > data_end)
+		return TC_ACT_SHOT;
+	if (icmp_hdr->icmp6_type != ICMPV6_PKT_TOOBIG)
+		return TC_ACT_OK;
+	off += sizeof(struct icmp6hdr);
+	ip6h = data + off;
+	if (ip6h + 1 > data_end)
+		return TC_ACT_SHOT;
+	pckt->proto = ip6h->nexthdr;
+	pckt->flags |= F_ICMP;
+	memcpy(pckt->srcv6, ip6h->daddr.s6_addr32, 16);
+	memcpy(pckt->dstv6, ip6h->saddr.s6_addr32, 16);
+	return TC_ACT_UNSPEC;
+}
+
+static __always_inline int parse_icmp(void *data, void *data_end, __u64 off,
+				      struct packet_description *pckt)
+{
+	struct icmphdr *icmp_hdr;
+	struct iphdr *iph;
+
+	icmp_hdr = data + off;
+	if (icmp_hdr + 1 > data_end)
+		return TC_ACT_SHOT;
+	if (icmp_hdr->type != ICMP_DEST_UNREACH ||
+	    icmp_hdr->code != ICMP_FRAG_NEEDED)
+		return TC_ACT_OK;
+	off += sizeof(struct icmphdr);
+	iph = data + off;
+	if (iph + 1 > data_end)
+		return TC_ACT_SHOT;
+	if (iph->ihl != 5)
+		return TC_ACT_SHOT;
+	pckt->proto = iph->protocol;
+	pckt->flags |= F_ICMP;
+	pckt->src = iph->daddr;
+	pckt->dst = iph->saddr;
+	return TC_ACT_UNSPEC;
+}
+
+static __always_inline bool parse_udp(void *data, __u64 off, void *data_end,
+				      struct packet_description *pckt)
+{
+	struct udphdr *udp;
+	udp = data + off;
+
+	if (udp + 1 > data_end)
+		return false;
+
+	if (!(pckt->flags & F_ICMP)) {
+		pckt->port16[0] = udp->source;
+		pckt->port16[1] = udp->dest;
+	} else {
+		pckt->port16[0] = udp->dest;
+		pckt->port16[1] = udp->source;
+	}
+	return true;
+}
+
+static __always_inline bool parse_tcp(void *data, __u64 off, void *data_end,
+				      struct packet_description *pckt)
+{
+	struct tcphdr *tcp;
+
+	tcp = data + off;
+	if (tcp + 1 > data_end)
+		return false;
+
+	if (tcp->syn)
+		pckt->flags |= F_SYN_SET;
+
+	if (!(pckt->flags & F_ICMP)) {
+		pckt->port16[0] = tcp->source;
+		pckt->port16[1] = tcp->dest;
+	} else {
+		pckt->port16[0] = tcp->dest;
+		pckt->port16[1] = tcp->source;
+	}
+	return true;
+}
+
+static __always_inline int process_packet(void *data, __u64 off, void *data_end,
+					  bool is_ipv6, struct __sk_buff *skb)
+{
+	void *pkt_start = (void *)(long)skb->data;
+	struct packet_description pckt = {};
+	struct eth_hdr *eth = pkt_start;
+	struct bpf_tunnel_key tkey = {};
+	struct vip_stats *data_stats;
+	struct real_definition *dst;
+	struct vip_meta *vip_info;
+	struct ctl_value *cval;
+	__u32 v4_intf_pos = 1;
+	__u32 v6_intf_pos = 2;
+	struct ipv6hdr *ip6h;
+	struct vip vip = {};
+	struct iphdr *iph;
+	int tun_flag = 0;
+	__u16 pkt_bytes;
+	__u64 iph_len;
+	__u32 ifindex;
+	__u8 protocol;
+	__u32 vip_num;
+	int action;
+
+	tkey.tunnel_ttl = 64;
+	if (is_ipv6) {
+		ip6h = data + off;
+		if (ip6h + 1 > data_end)
+			return TC_ACT_SHOT;
+
+		iph_len = sizeof(struct ipv6hdr);
+		protocol = ip6h->nexthdr;
+		pckt.proto = protocol;
+		pkt_bytes = ntohs(ip6h->payload_len);
+		off += iph_len;
+		if (protocol == IPPROTO_FRAGMENT) {
+			return TC_ACT_SHOT;
+		} else if (protocol == IPPROTO_ICMPV6) {
+			action = parse_icmpv6(data, data_end, off, &pckt);
+			if (action >= 0)
+				return action;
+			off += IPV6_PLUS_ICMP_HDR;
+		} else {
+			memcpy(pckt.srcv6, ip6h->saddr.s6_addr32, 16);
+			memcpy(pckt.dstv6, ip6h->daddr.s6_addr32, 16);
+		}
+	} else {
+		iph = data + off;
+		if (iph + 1 > data_end)
+			return TC_ACT_SHOT;
+		if (iph->ihl != 5)
+			return TC_ACT_SHOT;
+
+		protocol = iph->protocol;
+		pckt.proto = protocol;
+		pkt_bytes = ntohs(iph->tot_len);
+		off += IPV4_HDR_LEN_NO_OPT;
+
+		if (iph->frag_off & PCKT_FRAGMENTED)
+			return TC_ACT_SHOT;
+		if (protocol == IPPROTO_ICMP) {
+			action = parse_icmp(data, data_end, off, &pckt);
+			if (action >= 0)
+				return action;
+			off += IPV4_PLUS_ICMP_HDR;
+		} else {
+			pckt.src = iph->saddr;
+			pckt.dst = iph->daddr;
+		}
+	}
+	protocol = pckt.proto;
+
+	if (protocol == IPPROTO_TCP) {
+		if (!parse_tcp(data, off, data_end, &pckt))
+			return TC_ACT_SHOT;
+	} else if (protocol == IPPROTO_UDP) {
+		if (!parse_udp(data, off, data_end, &pckt))
+			return TC_ACT_SHOT;
+	} else {
+		return TC_ACT_SHOT;
+	}
+
+	if (is_ipv6)
+		memcpy(vip.daddr.v6, pckt.dstv6, 16);
+	else
+		vip.daddr.v4 = pckt.dst;
+
+	vip.dport = pckt.port16[1];
+	vip.protocol = pckt.proto;
+	vip_info = bpf_map_lookup_elem(&vip_map, &vip);
+	if (!vip_info) {
+		vip.dport = 0;
+		vip_info = bpf_map_lookup_elem(&vip_map, &vip);
+		if (!vip_info)
+			return TC_ACT_SHOT;
+		pckt.port16[1] = 0;
+	}
+
+	if (vip_info->flags & F_HASH_NO_SRC_PORT)
+		pckt.port16[0] = 0;
+
+	if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6))
+		return TC_ACT_SHOT;
+
+	if (dst->flags & F_IPV6) {
+		cval = bpf_map_lookup_elem(&ctl_array, &v6_intf_pos);
+		if (!cval)
+			return TC_ACT_SHOT;
+		ifindex = cval->ifindex;
+		memcpy(tkey.remote_ipv6, dst->dstv6, 16);
+		tun_flag = BPF_F_TUNINFO_IPV6;
+	} else {
+		cval = bpf_map_lookup_elem(&ctl_array, &v4_intf_pos);
+		if (!cval)
+			return TC_ACT_SHOT;
+		ifindex = cval->ifindex;
+		tkey.remote_ipv4 = dst->dst;
+	}
+	vip_num = vip_info->vip_num;
+	data_stats = bpf_map_lookup_elem(&stats, &vip_num);
+	if (!data_stats)
+		return TC_ACT_SHOT;
+	data_stats->pkts++;
+	data_stats->bytes += pkt_bytes;
+	bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), tun_flag);
+	*(u32 *)eth->eth_dest = tkey.remote_ipv4;
+	return bpf_redirect(ifindex, 0);
+}
+
+SEC("l4lb-demo")
+int balancer_ingress(struct __sk_buff *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	struct eth_hdr *eth = data;
+	__u32 eth_proto;
+	__u32 nh_off;
+
+	nh_off = sizeof(struct eth_hdr);
+	if (data + nh_off > data_end)
+		return TC_ACT_SHOT;
+	eth_proto = eth->eth_proto;
+	if (eth_proto == htons(ETH_P_IP))
+		return process_packet(data, nh_off, data_end, false, ctx);
+	else if (eth_proto == htons(ETH_P_IPV6))
+		return process_packet(data, nh_off, data_end, true, ctx);
+	else
+		return TC_ACT_SHOT;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_pkt_access.c b/tools/testing/selftests/bpf/test_pkt_access.c
new file mode 100644
index 000000000000..fd1e0832d409
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_pkt_access.c
@@ -0,0 +1,64 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/tcp.h>
+#include <linux/pkt_cls.h>
+#include "bpf_helpers.h"
+
+#define _htons __builtin_bswap16
+#define barrier() __asm__ __volatile__("": : :"memory")
+int _version SEC("version") = 1;
+
+SEC("test1")
+int process(struct __sk_buff *skb)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	struct ethhdr *eth = (struct ethhdr *)(data);
+	struct tcphdr *tcp = NULL;
+	__u8 proto = 255;
+	__u64 ihl_len;
+
+	if (eth + 1 > data_end)
+		return TC_ACT_SHOT;
+
+	if (eth->h_proto == _htons(ETH_P_IP)) {
+		struct iphdr *iph = (struct iphdr *)(eth + 1);
+
+		if (iph + 1 > data_end)
+			return TC_ACT_SHOT;
+		ihl_len = iph->ihl * 4;
+		proto = iph->protocol;
+		tcp = (struct tcphdr *)((void *)(iph) + ihl_len);
+	} else if (eth->h_proto == _htons(ETH_P_IPV6)) {
+		struct ipv6hdr *ip6h = (struct ipv6hdr *)(eth + 1);
+
+		if (ip6h + 1 > data_end)
+			return TC_ACT_SHOT;
+		ihl_len = sizeof(*ip6h);
+		proto = ip6h->nexthdr;
+		tcp = (struct tcphdr *)((void *)(ip6h) + ihl_len);
+	}
+
+	if (tcp) {
+		if (((void *)(tcp) + 20) > data_end || proto != 6)
+			return TC_ACT_SHOT;
+		barrier(); /* to force ordering of checks */
+		if (((void *)(tcp) + 18) > data_end)
+			return TC_ACT_SHOT;
+		if (tcp->urg_ptr == 123)
+			return TC_ACT_OK;
+	}
+
+	return TC_ACT_UNSPEC;
+}
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
new file mode 100644
index 000000000000..5275d4a1df24
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -0,0 +1,284 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <errno.h>
+#include <string.h>
+#include <assert.h>
+#include <stdlib.h>
+
+#include <linux/types.h>
+typedef __u16 __sum16;
+#include <arpa/inet.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+
+#include <sys/wait.h>
+#include <sys/resource.h>
+
+#include <linux/bpf.h>
+#include <linux/err.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "test_iptunnel_common.h"
+#include "bpf_util.h"
+
+#define _htons __builtin_bswap16
+
+static int error_cnt, pass_cnt;
+
+#define MAGIC_BYTES 123
+
+/* ipv4 test vector */
+static struct {
+	struct ethhdr eth;
+	struct iphdr iph;
+	struct tcphdr tcp;
+} __packed pkt_v4 = {
+	.eth.h_proto = _htons(ETH_P_IP),
+	.iph.ihl = 5,
+	.iph.protocol = 6,
+	.iph.tot_len = _htons(MAGIC_BYTES),
+	.tcp.urg_ptr = 123,
+};
+
+/* ipv6 test vector */
+static struct {
+	struct ethhdr eth;
+	struct ipv6hdr iph;
+	struct tcphdr tcp;
+} __packed pkt_v6 = {
+	.eth.h_proto = _htons(ETH_P_IPV6),
+	.iph.nexthdr = 6,
+	.iph.payload_len = _htons(MAGIC_BYTES),
+	.tcp.urg_ptr = 123,
+};
+
+#define CHECK(condition, tag, format...) ({				\
+	int __ret = !!(condition);					\
+	if (__ret) {							\
+		error_cnt++;						\
+		printf("%s:FAIL:%s ", __func__, tag);			\
+		printf(format);						\
+	} else {							\
+		pass_cnt++;						\
+		printf("%s:PASS:%s %d nsec\n", __func__, tag, duration);\
+	}								\
+})
+
+static int bpf_prog_load(const char *file, enum bpf_prog_type type,
+			 struct bpf_object **pobj, int *prog_fd)
+{
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	int err;
+
+	obj = bpf_object__open(file);
+	if (IS_ERR(obj)) {
+		error_cnt++;
+		return -ENOENT;
+	}
+
+	prog = bpf_program__next(NULL, obj);
+	if (!prog) {
+		bpf_object__close(obj);
+		error_cnt++;
+		return -ENOENT;
+	}
+
+	bpf_program__set_type(prog, type);
+	err = bpf_object__load(obj);
+	if (err) {
+		bpf_object__close(obj);
+		error_cnt++;
+		return -EINVAL;
+	}
+
+	*pobj = obj;
+	*prog_fd = bpf_program__fd(prog);
+	return 0;
+}
+
+static int bpf_find_map(const char *test, struct bpf_object *obj,
+			const char *name)
+{
+	struct bpf_map *map;
+
+	map = bpf_object__find_map_by_name(obj, name);
+	if (!map) {
+		printf("%s:FAIL:map '%s' not found\n", test, name);
+		error_cnt++;
+		return -1;
+	}
+	return bpf_map__fd(map);
+}
+
+static void test_pkt_access(void)
+{
+	const char *file = "./test_pkt_access.o";
+	struct bpf_object *obj;
+	__u32 duration, retval;
+	int err, prog_fd;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
+	if (err)
+		return;
+
+	err = bpf_prog_test_run(prog_fd, 100000, &pkt_v4, sizeof(pkt_v4),
+				NULL, NULL, &retval, &duration);
+	CHECK(err || errno || retval, "ipv4",
+	      "err %d errno %d retval %d duration %d\n",
+	      err, errno, retval, duration);
+
+	err = bpf_prog_test_run(prog_fd, 100000, &pkt_v6, sizeof(pkt_v6),
+				NULL, NULL, &retval, &duration);
+	CHECK(err || errno || retval, "ipv6",
+	      "err %d errno %d retval %d duration %d\n",
+	      err, errno, retval, duration);
+	bpf_object__close(obj);
+}
+
+static void test_xdp(void)
+{
+	struct vip key4 = {.protocol = 6, .family = AF_INET};
+	struct vip key6 = {.protocol = 6, .family = AF_INET6};
+	struct iptnl_info value4 = {.family = AF_INET};
+	struct iptnl_info value6 = {.family = AF_INET6};
+	const char *file = "./test_xdp.o";
+	struct bpf_object *obj;
+	char buf[128];
+	struct ipv6hdr *iph6 = (void *)buf + sizeof(struct ethhdr);
+	struct iphdr *iph = (void *)buf + sizeof(struct ethhdr);
+	__u32 duration, retval, size;
+	int err, prog_fd, map_fd;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
+	if (err)
+		return;
+
+	map_fd = bpf_find_map(__func__, obj, "vip2tnl");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_update_elem(map_fd, &key4, &value4, 0);
+	bpf_map_update_elem(map_fd, &key6, &value6, 0);
+
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				buf, &size, &retval, &duration);
+
+	CHECK(err || errno || retval != XDP_TX || size != 74 ||
+	      iph->protocol != IPPROTO_IPIP, "ipv4",
+	      "err %d errno %d retval %d size %d\n",
+	      err, errno, retval, size);
+
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
+				buf, &size, &retval, &duration);
+	CHECK(err || errno || retval != XDP_TX || size != 114 ||
+	      iph6->nexthdr != IPPROTO_IPV6, "ipv6",
+	      "err %d errno %d retval %d size %d\n",
+	      err, errno, retval, size);
+out:
+	bpf_object__close(obj);
+}
+
+#define MAGIC_VAL 0x1234
+#define NUM_ITER 100000
+#define VIP_NUM 5
+
+static void test_l4lb(void)
+{
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	const char *file = "./test_l4lb.o";
+	struct vip key = {.protocol = 6};
+	struct vip_meta {
+		__u32 flags;
+		__u32 vip_num;
+	} value = {.vip_num = VIP_NUM};
+	__u32 stats_key = VIP_NUM;
+	struct vip_stats {
+		__u64 bytes;
+		__u64 pkts;
+	} stats[nr_cpus];
+	struct real_definition {
+		union {
+			__be32 dst;
+			__be32 dstv6[4];
+		};
+		__u8 flags;
+	} real_def = {.dst = MAGIC_VAL};
+	__u32 ch_key = 11, real_num = 3;
+	__u32 duration, retval, size;
+	int err, i, prog_fd, map_fd;
+	__u64 bytes = 0, pkts = 0;
+	struct bpf_object *obj;
+	char buf[128];
+	u32 *magic = (u32 *)buf;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
+	if (err)
+		return;
+
+	map_fd = bpf_find_map(__func__, obj, "vip_map");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_update_elem(map_fd, &key, &value, 0);
+
+	map_fd = bpf_find_map(__func__, obj, "ch_rings");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_update_elem(map_fd, &ch_key, &real_num, 0);
+
+	map_fd = bpf_find_map(__func__, obj, "reals");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_update_elem(map_fd, &real_num, &real_def, 0);
+
+	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4),
+				buf, &size, &retval, &duration);
+	CHECK(err || errno || retval != 7/*TC_ACT_REDIRECT*/ || size != 54 ||
+	      *magic != MAGIC_VAL, "ipv4",
+	      "err %d errno %d retval %d size %d magic %x\n",
+	      err, errno, retval, size, *magic);
+
+	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6),
+				buf, &size, &retval, &duration);
+	CHECK(err || errno || retval != 7/*TC_ACT_REDIRECT*/ || size != 74 ||
+	      *magic != MAGIC_VAL, "ipv6",
+	      "err %d errno %d retval %d size %d magic %x\n",
+	      err, errno, retval, size, *magic);
+
+	map_fd = bpf_find_map(__func__, obj, "stats");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_lookup_elem(map_fd, &stats_key, stats);
+	for (i = 0; i < nr_cpus; i++) {
+		bytes += stats[i].bytes;
+		pkts += stats[i].pkts;
+	}
+	if (bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2) {
+		error_cnt++;
+		printf("test_l4lb:FAIL:stats %lld %lld\n", bytes, pkts);
+	}
+out:
+	bpf_object__close(obj);
+}
+
+int main(void)
+{
+	struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY };
+
+	setrlimit(RLIMIT_MEMLOCK, &rinf);
+
+	test_pkt_access();
+	test_xdp();
+	test_l4lb();
+
+	printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index c848e90b6421..0963f8ffd25c 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -46,6 +46,7 @@
 
 #define MAX_INSNS	512
 #define MAX_FIXUPS	8
+#define MAX_NR_MAPS	4
 
 #define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS	(1 << 0)
 
@@ -55,6 +56,7 @@ struct bpf_test {
 	int fixup_map1[MAX_FIXUPS];
 	int fixup_map2[MAX_FIXUPS];
 	int fixup_prog[MAX_FIXUPS];
+	int fixup_map_in_map[MAX_FIXUPS];
 	const char *errstr;
 	const char *errstr_unpriv;
 	enum {
@@ -4720,6 +4722,75 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.result_unpriv = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"map in map access",
+		.insns = {
+			BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+			BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_MOV64_REG(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_in_map = { 3 },
+		.result = ACCEPT,
+	},
+	{
+		"invalid inner map pointer",
+		.insns = {
+			BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+			BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_MOV64_REG(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_in_map = { 3 },
+		.errstr = "R1 type=inv expected=map_ptr",
+		.errstr_unpriv = "R1 pointer arithmetic prohibited",
+		.result = REJECT,
+	},
+	{
+		"forgot null checking on the inner map pointer",
+		.insns = {
+			BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_MOV64_REG(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_in_map = { 3 },
+		.errstr = "R1 type=map_value_or_null expected=map_ptr",
+		.result = REJECT,
 	}
 };
 
@@ -4757,42 +4828,73 @@ static int create_prog_array(void)
 	return fd;
 }
 
+static int create_map_in_map(void)
+{
+	int inner_map_fd, outer_map_fd;
+
+	inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(int),
+				      sizeof(int), 1, 0);
+	if (inner_map_fd < 0) {
+		printf("Failed to create array '%s'!\n", strerror(errno));
+		return inner_map_fd;
+	}
+
+	outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS,
+					     sizeof(int), inner_map_fd, 1, 0);
+	if (outer_map_fd < 0)
+		printf("Failed to create array of maps '%s'!\n",
+		       strerror(errno));
+
+	close(inner_map_fd);
+
+	return outer_map_fd;
+}
+
 static char bpf_vlog[32768];
 
 static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
-			  int *fd_f1, int *fd_f2, int *fd_f3)
+			  int *map_fds)
 {
 	int *fixup_map1 = test->fixup_map1;
 	int *fixup_map2 = test->fixup_map2;
 	int *fixup_prog = test->fixup_prog;
+	int *fixup_map_in_map = test->fixup_map_in_map;
 
 	/* Allocating HTs with 1 elem is fine here, since we only test
 	 * for verifier and not do a runtime lookup, so the only thing
 	 * that really matters is value size in this case.
 	 */
 	if (*fixup_map1) {
-		*fd_f1 = create_map(sizeof(long long), 1);
+		map_fds[0] = create_map(sizeof(long long), 1);
 		do {
-			prog[*fixup_map1].imm = *fd_f1;
+			prog[*fixup_map1].imm = map_fds[0];
 			fixup_map1++;
 		} while (*fixup_map1);
 	}
 
 	if (*fixup_map2) {
-		*fd_f2 = create_map(sizeof(struct test_val), 1);
+		map_fds[1] = create_map(sizeof(struct test_val), 1);
 		do {
-			prog[*fixup_map2].imm = *fd_f2;
+			prog[*fixup_map2].imm = map_fds[1];
 			fixup_map2++;
 		} while (*fixup_map2);
 	}
 
 	if (*fixup_prog) {
-		*fd_f3 = create_prog_array();
+		map_fds[2] = create_prog_array();
 		do {
-			prog[*fixup_prog].imm = *fd_f3;
+			prog[*fixup_prog].imm = map_fds[2];
 			fixup_prog++;
 		} while (*fixup_prog);
 	}
+
+	if (*fixup_map_in_map) {
+		map_fds[3] = create_map_in_map();
+		do {
+			prog[*fixup_map_in_map].imm = map_fds[3];
+			fixup_map_in_map++;
+		} while (*fixup_map_in_map);
+	}
 }
 
 static void do_test_single(struct bpf_test *test, bool unpriv,
@@ -4802,10 +4904,19 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	struct bpf_insn *prog = test->insns;
 	int prog_len = probe_filter_length(prog);
 	int prog_type = test->prog_type;
+<<<<<<< HEAD
+	int map_fds[MAX_NR_MAPS];
+	int fd_prog, expected_ret;
+=======
 	int fd_f1 = -1, fd_f2 = -1, fd_f3 = -1;
+>>>>>>> ea6b1720ce25f92f7a17b2e0c2b653d20773d10a
 	const char *expected_err;
+	int i;
+
+	for (i = 0; i < MAX_NR_MAPS; i++)
+		map_fds[i] = -1;
 
-	do_test_fixup(test, prog, &fd_f1, &fd_f2, &fd_f3);
+	do_test_fixup(test, prog, map_fds);
 
 	fd_prog = bpf_load_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
 				   prog, prog_len, "GPL", 0, bpf_vlog,
@@ -4848,9 +4959,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	       " (NOTE: reject due to unknown alignment)" : "");
 close_fds:
 	close(fd_prog);
-	close(fd_f1);
-	close(fd_f2);
-	close(fd_f3);
+	for (i = 0; i < MAX_NR_MAPS; i++)
+		close(map_fds[i]);
 	sched_yield();
 	return;
 fail_log:
diff --git a/tools/testing/selftests/bpf/test_xdp.c b/tools/testing/selftests/bpf/test_xdp.c
new file mode 100644
index 000000000000..9a33b038cb31
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp.c
@@ -0,0 +1,236 @@
+/* Copyright (c) 2016,2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
+#include <linux/pkt_cls.h>
+#include <sys/socket.h>
+#include "bpf_helpers.h"
+#include "test_iptunnel_common.h"
+
+#define htons __builtin_bswap16
+#define ntohs __builtin_bswap16
+int _version SEC("version") = 1;
+
+struct bpf_map_def SEC("maps") rxcnt = {
+	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u64),
+	.max_entries = 256,
+};
+
+struct bpf_map_def SEC("maps") vip2tnl = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(struct vip),
+	.value_size = sizeof(struct iptnl_info),
+	.max_entries = MAX_IPTNL_ENTRIES,
+};
+
+static __always_inline void count_tx(__u32 protocol)
+{
+	__u64 *rxcnt_count;
+
+	rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol);
+	if (rxcnt_count)
+		*rxcnt_count += 1;
+}
+
+static __always_inline int get_dport(void *trans_data, void *data_end,
+				     __u8 protocol)
+{
+	struct tcphdr *th;
+	struct udphdr *uh;
+
+	switch (protocol) {
+	case IPPROTO_TCP:
+		th = (struct tcphdr *)trans_data;
+		if (th + 1 > data_end)
+			return -1;
+		return th->dest;
+	case IPPROTO_UDP:
+		uh = (struct udphdr *)trans_data;
+		if (uh + 1 > data_end)
+			return -1;
+		return uh->dest;
+	default:
+		return 0;
+	}
+}
+
+static __always_inline void set_ethhdr(struct ethhdr *new_eth,
+				       const struct ethhdr *old_eth,
+				       const struct iptnl_info *tnl,
+				       __be16 h_proto)
+{
+	memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source));
+	memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest));
+	new_eth->h_proto = h_proto;
+}
+
+static __always_inline int handle_ipv4(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct iptnl_info *tnl;
+	struct ethhdr *new_eth;
+	struct ethhdr *old_eth;
+	struct iphdr *iph = data + sizeof(struct ethhdr);
+	__u16 *next_iph;
+	__u16 payload_len;
+	struct vip vip = {};
+	int dport;
+	__u32 csum = 0;
+	int i;
+
+	if (iph + 1 > data_end)
+		return XDP_DROP;
+
+	dport = get_dport(iph + 1, data_end, iph->protocol);
+	if (dport == -1)
+		return XDP_DROP;
+
+	vip.protocol = iph->protocol;
+	vip.family = AF_INET;
+	vip.daddr.v4 = iph->daddr;
+	vip.dport = dport;
+	payload_len = ntohs(iph->tot_len);
+
+	tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
+	/* It only does v4-in-v4 */
+	if (!tnl || tnl->family != AF_INET)
+		return XDP_PASS;
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr)))
+		return XDP_DROP;
+
+	data = (void *)(long)xdp->data;
+	data_end = (void *)(long)xdp->data_end;
+
+	new_eth = data;
+	iph = data + sizeof(*new_eth);
+	old_eth = data + sizeof(*iph);
+
+	if (new_eth + 1 > data_end ||
+	    old_eth + 1 > data_end ||
+	    iph + 1 > data_end)
+		return XDP_DROP;
+
+	set_ethhdr(new_eth, old_eth, tnl, htons(ETH_P_IP));
+
+	iph->version = 4;
+	iph->ihl = sizeof(*iph) >> 2;
+	iph->frag_off =	0;
+	iph->protocol = IPPROTO_IPIP;
+	iph->check = 0;
+	iph->tos = 0;
+	iph->tot_len = htons(payload_len + sizeof(*iph));
+	iph->daddr = tnl->daddr.v4;
+	iph->saddr = tnl->saddr.v4;
+	iph->ttl = 8;
+
+	next_iph = (__u16 *)iph;
+#pragma clang loop unroll(full)
+	for (i = 0; i < sizeof(*iph) >> 1; i++)
+		csum += *next_iph++;
+
+	iph->check = ~((csum & 0xffff) + (csum >> 16));
+
+	count_tx(vip.protocol);
+
+	return XDP_TX;
+}
+
+static __always_inline int handle_ipv6(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct iptnl_info *tnl;
+	struct ethhdr *new_eth;
+	struct ethhdr *old_eth;
+	struct ipv6hdr *ip6h = data + sizeof(struct ethhdr);
+	__u16 payload_len;
+	struct vip vip = {};
+	int dport;
+
+	if (ip6h + 1 > data_end)
+		return XDP_DROP;
+
+	dport = get_dport(ip6h + 1, data_end, ip6h->nexthdr);
+	if (dport == -1)
+		return XDP_DROP;
+
+	vip.protocol = ip6h->nexthdr;
+	vip.family = AF_INET6;
+	memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr));
+	vip.dport = dport;
+	payload_len = ip6h->payload_len;
+
+	tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
+	/* It only does v6-in-v6 */
+	if (!tnl || tnl->family != AF_INET6)
+		return XDP_PASS;
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr)))
+		return XDP_DROP;
+
+	data = (void *)(long)xdp->data;
+	data_end = (void *)(long)xdp->data_end;
+
+	new_eth = data;
+	ip6h = data + sizeof(*new_eth);
+	old_eth = data + sizeof(*ip6h);
+
+	if (new_eth + 1 > data_end || old_eth + 1 > data_end ||
+	    ip6h + 1 > data_end)
+		return XDP_DROP;
+
+	set_ethhdr(new_eth, old_eth, tnl, htons(ETH_P_IPV6));
+
+	ip6h->version = 6;
+	ip6h->priority = 0;
+	memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl));
+	ip6h->payload_len = htons(ntohs(payload_len) + sizeof(*ip6h));
+	ip6h->nexthdr = IPPROTO_IPV6;
+	ip6h->hop_limit = 8;
+	memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6));
+	memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6));
+
+	count_tx(vip.protocol);
+
+	return XDP_TX;
+}
+
+SEC("xdp_tx_iptunnel")
+int _xdp_tx_iptunnel(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct ethhdr *eth = data;
+	__u16 h_proto;
+
+	if (eth + 1 > data_end)
+		return XDP_DROP;
+
+	h_proto = eth->h_proto;
+
+	if (h_proto == htons(ETH_P_IP))
+		return handle_ipv4(xdp);
+	else if (h_proto == htons(ETH_P_IPV6))
+
+		return handle_ipv6(xdp);
+	else
+		return XDP_DROP;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index fbfe5d0d5c2e..35cbb4cba410 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -5,7 +5,7 @@ CFLAGS += -I../../../../usr/include/
 
 reuseport_bpf_numa: LDFLAGS += -lnuma
 
-TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh
+TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket
 TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh
new file mode 100755
index 000000000000..4e00568d70c2
--- /dev/null
+++ b/tools/testing/selftests/net/netdevice.sh
@@ -0,0 +1,200 @@
+#!/bin/sh
+#
+# This test is for checking network interface
+# For the moment it tests only ethernet interface (but wifi could be easily added)
+#
+# We assume that all network driver are loaded
+# if not they probably have failed earlier in the boot process and their logged error will be catched by another test
+#
+
+# this function will try to up the interface
+# if already up, nothing done
+# arg1: network interface name
+kci_net_start()
+{
+	netdev=$1
+
+	ip link show "$netdev" |grep -q UP
+	if [ $? -eq 0 ];then
+		echo "SKIP: $netdev: interface already up"
+		return 0
+	fi
+
+	ip link set "$netdev" up
+	if [ $? -ne 0 ];then
+		echo "FAIL: $netdev: Fail to up interface"
+		return 1
+	else
+		echo "PASS: $netdev: set interface up"
+		NETDEV_STARTED=1
+	fi
+	return 0
+}
+
+# this function will try to setup an IP and MAC address on a network interface
+# Doing nothing if the interface was already up
+# arg1: network interface name
+kci_net_setup()
+{
+	netdev=$1
+
+	# do nothing if the interface was already up
+	if [ $NETDEV_STARTED -eq 0 ];then
+		return 0
+	fi
+
+	MACADDR='02:03:04:05:06:07'
+	ip link set dev $netdev address "$MACADDR"
+	if [ $? -ne 0 ];then
+		echo "FAIL: $netdev: Cannot set MAC address"
+	else
+		ip link show $netdev |grep -q "$MACADDR"
+		if [ $? -eq 0 ];then
+			echo "PASS: $netdev: set MAC address"
+		else
+			echo "FAIL: $netdev: Cannot set MAC address"
+		fi
+	fi
+
+	#check that the interface did not already have an IP
+	ip address show "$netdev" |grep '^[[:space:]]*inet'
+	if [ $? -eq 0 ];then
+		echo "SKIP: $netdev: already have an IP"
+		return 0
+	fi
+
+	# TODO what ipaddr to set ? DHCP ?
+	echo "SKIP: $netdev: set IP address"
+	return 0
+}
+
+# test an ethtool command
+# arg1: return code for not supported (see ethtool code source)
+# arg2: summary of the command
+# arg3: command to execute
+kci_netdev_ethtool_test()
+{
+	if [ $# -le 2 ];then
+		echo "SKIP: $netdev: ethtool: invalid number of arguments"
+		return 1
+	fi
+	$3 >/dev/null
+	ret=$?
+	if [ $ret -ne 0 ];then
+		if [ $ret -eq "$1" ];then
+			echo "SKIP: $netdev: ethtool $2 not supported"
+		else
+			echo "FAIL: $netdev: ethtool $2"
+			return 1
+		fi
+	else
+		echo "PASS: $netdev: ethtool $2"
+	fi
+	return 0
+}
+
+# test ethtool commands
+# arg1: network interface name
+kci_netdev_ethtool()
+{
+	netdev=$1
+
+	#check presence of ethtool
+	ethtool --version 2>/dev/null >/dev/null
+	if [ $? -ne 0 ];then
+		echo "SKIP: ethtool not present"
+		return 1
+	fi
+
+	TMP_ETHTOOL_FEATURES="$(mktemp)"
+	if [ ! -e "$TMP_ETHTOOL_FEATURES" ];then
+		echo "SKIP: Cannot create a tmp file"
+		return 1
+	fi
+
+	ethtool -k "$netdev" > "$TMP_ETHTOOL_FEATURES"
+	if [ $? -ne 0 ];then
+		echo "FAIL: $netdev: ethtool list features"
+		rm "$TMP_ETHTOOL_FEATURES"
+		return 1
+	fi
+	echo "PASS: $netdev: ethtool list features"
+	#TODO for each non fixed features, try to turn them on/off
+	rm "$TMP_ETHTOOL_FEATURES"
+
+	kci_netdev_ethtool_test 74 'dump' "ethtool -d $netdev"
+	kci_netdev_ethtool_test 94 'stats' "ethtool -S $netdev"
+	return 0
+}
+
+# stop a netdev
+# arg1: network interface name
+kci_netdev_stop()
+{
+	netdev=$1
+
+	if [ $NETDEV_STARTED -eq 0 ];then
+		echo "SKIP: $netdev: interface kept up"
+		return 0
+	fi
+
+	ip link set "$netdev" down
+	if [ $? -ne 0 ];then
+		echo "FAIL: $netdev: stop interface"
+		return 1
+	fi
+	echo "PASS: $netdev: stop interface"
+	return 0
+}
+
+# run all test on a netdev
+# arg1: network interface name
+kci_test_netdev()
+{
+	NETDEV_STARTED=0
+	IFACE_TO_UPDOWN="$1"
+	IFACE_TO_TEST="$1"
+	#check for VLAN interface
+	MASTER_IFACE="$(echo $1 | cut -d@ -f2)"
+	if [ ! -z "$MASTER_IFACE" ];then
+		IFACE_TO_UPDOWN="$MASTER_IFACE"
+		IFACE_TO_TEST="$(echo $1 | cut -d@ -f1)"
+	fi
+
+	NETDEV_STARTED=0
+	kci_net_start "$IFACE_TO_UPDOWN"
+
+	kci_net_setup "$IFACE_TO_TEST"
+
+	kci_netdev_ethtool "$IFACE_TO_TEST"
+
+	kci_netdev_stop "$IFACE_TO_UPDOWN"
+	return 0
+}
+
+#check for needed privileges
+if [ "$(id -u)" -ne 0 ];then
+	echo "SKIP: Need root privileges"
+	exit 0
+fi
+
+ip -Version 2>/dev/null >/dev/null
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without the ip tool"
+	exit 0
+fi
+
+TMP_LIST_NETDEV="$(mktemp)"
+if [ ! -e "$TMP_LIST_NETDEV" ];then
+	echo "FAIL: Cannot create a tmp file"
+	exit 1
+fi
+
+ip link show |grep '^[0-9]' | grep -oE '[[:space:]].*eth[0-9]*:|[[:space:]].*enp[0-9]s[0-9]:' | cut -d\  -f2 | cut -d: -f1> "$TMP_LIST_NETDEV"
+while read netdev
+do
+	kci_test_netdev "$netdev"
+done < "$TMP_LIST_NETDEV"
+
+rm "$TMP_LIST_NETDEV"
+exit 0