1411 files changed, 73817 insertions, 19627 deletions

diff --git a/Documentation/ABI/testing/sysfs-devices-platform-soc-ipa b/Documentation/ABI/testing/sysfs-devices-platform-soc-ipa
new file mode 100644
index 000000000000..c56dcf15bf29
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-platform-soc-ipa
@@ -0,0 +1,78 @@
+What:		/sys/devices/platform/soc@X/XXXXXXX.ipa/
+Date:		June 2021
+KernelVersion:	v5.14
+Contact:	Alex Elder <elder@kernel.org>
+Description:
+		The /sys/devices/platform/soc@X/XXXXXXX.ipa/ directory
+		contains read-only attributes exposing information about
+		an IPA device.  The X values could vary, but are typically
+		"soc@0/1e40000.ipa".
+
+What:		.../XXXXXXX.ipa/version
+Date:		June 2021
+KernelVersion:	v5.14
+Contact:	Alex Elder <elder@kernel.org>
+Description:
+		The .../XXXXXXX.ipa/version file contains the IPA hardware
+		version, as a period-separated set of two or three integers
+		(e.g., "3.5.1" or "4.2").
+
+What:		.../XXXXXXX.ipa/feature/
+Date:		June 2021
+KernelVersion:	v5.14
+Contact:	Alex Elder <elder@kernel.org>
+Description:
+		The .../XXXXXXX.ipa/feature/ directory contains a set of
+		attributes describing features implemented by the IPA
+		hardware.
+
+What:		.../XXXXXXX.ipa/feature/rx_offload
+Date:		June 2021
+KernelVersion:	v5.14
+Contact:	Alex Elder <elder@kernel.org>
+Description:
+		The .../XXXXXXX.ipa/feature/rx_offload file contains a
+		string indicating the type of receive checksum offload
+		that is supported by the hardware.  The possible values
+		are "MAPv4" or "MAPv5".
+
+What:		.../XXXXXXX.ipa/feature/tx_offload
+Date:		June 2021
+KernelVersion:	v5.14
+Contact:	Alex Elder <elder@kernel.org>
+Description:
+		The .../XXXXXXX.ipa/feature/tx_offload file contains a
+		string indicating the type of transmit checksum offload
+		that is supported by the hardware.  The possible values
+		are "MAPv4" or "MAPv5".
+
+What:		.../XXXXXXX.ipa/modem/
+Date:		June 2021
+KernelVersion:	v5.14
+Contact:	Alex Elder <elder@kernel.org>
+Description:
+		The .../XXXXXXX.ipa/modem/ directory contains a set of
+		attributes describing properties of the modem execution
+		environment reachable by the IPA hardware.
+
+What:		.../XXXXXXX.ipa/modem/rx_endpoint_id
+Date:		June 2021
+KernelVersion:	v5.14
+Contact:	Alex Elder <elder@kernel.org>
+Description:
+		The .../XXXXXXX.ipa/feature/rx_endpoint_id file contains
+		the AP endpoint ID that receives packets originating from
+		the modem execution environment.  The "rx" is from the
+		perspective of the AP; this endpoint is considered an "IPA
+		producer".  An endpoint ID is a small unsigned integer.
+
+What:		.../XXXXXXX.ipa/modem/tx_endpoint_id
+Date:		June 2021
+KernelVersion:	v5.14
+Contact:	Alex Elder <elder@kernel.org>
+Description:
+		The .../XXXXXXX.ipa/feature/tx_endpoint_id file contains
+		the AP endpoint ID used to transmit packets destined for
+		the modem execution environment.  The "tx" is from the
+		perspective of the AP; this endpoint is considered an "IPA
+		consumer".  An endpoint ID is a small unsigned integer.
diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst
index a702f67dd45f..93e8cf12a6d4 100644
--- a/Documentation/bpf/index.rst
+++ b/Documentation/bpf/index.rst
@@ -84,6 +84,7 @@ Other
    :maxdepth: 1
 
    ringbuf
+   llvm_reloc
 
 .. Links:
 .. _networking-filter: ../networking/filter.rst
diff --git a/Documentation/bpf/llvm_reloc.rst b/Documentation/bpf/llvm_reloc.rst
new file mode 100644
index 000000000000..ca8957d5b671
--- /dev/null
+++ b/Documentation/bpf/llvm_reloc.rst
@@ -0,0 +1,240 @@
+.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+====================
+BPF LLVM Relocations
+====================
+
+This document describes LLVM BPF backend relocation types.
+
+Relocation Record
+=================
+
+LLVM BPF backend records each relocation with the following 16-byte
+ELF structure::
+
+  typedef struct
+  {
+    Elf64_Addr    r_offset;  // Offset from the beginning of section.
+    Elf64_Xword   r_info;    // Relocation type and symbol index.
+  } Elf64_Rel;
+
+For example, for the following code::
+
+  int g1 __attribute__((section("sec")));
+  int g2 __attribute__((section("sec")));
+  static volatile int l1 __attribute__((section("sec")));
+  static volatile int l2 __attribute__((section("sec")));
+  int test() {
+    return g1 + g2 + l1 + l2;
+  }
+
+Compiled with ``clang -target bpf -O2 -c test.c``, the following is
+the code with ``llvm-objdump -dr test.o``::
+
+       0:       18 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r1 = 0 ll
+                0000000000000000:  R_BPF_64_64  g1
+       2:       61 11 00 00 00 00 00 00 r1 = *(u32 *)(r1 + 0)
+       3:       18 02 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r2 = 0 ll
+                0000000000000018:  R_BPF_64_64  g2
+       5:       61 20 00 00 00 00 00 00 r0 = *(u32 *)(r2 + 0)
+       6:       0f 10 00 00 00 00 00 00 r0 += r1
+       7:       18 01 00 00 08 00 00 00 00 00 00 00 00 00 00 00 r1 = 8 ll
+                0000000000000038:  R_BPF_64_64  sec
+       9:       61 11 00 00 00 00 00 00 r1 = *(u32 *)(r1 + 0)
+      10:       0f 10 00 00 00 00 00 00 r0 += r1
+      11:       18 01 00 00 0c 00 00 00 00 00 00 00 00 00 00 00 r1 = 12 ll
+                0000000000000058:  R_BPF_64_64  sec
+      13:       61 11 00 00 00 00 00 00 r1 = *(u32 *)(r1 + 0)
+      14:       0f 10 00 00 00 00 00 00 r0 += r1
+      15:       95 00 00 00 00 00 00 00 exit
+
+There are four relations in the above for four ``LD_imm64`` instructions.
+The following ``llvm-readelf -r test.o`` shows the binary values of the four
+relocations::
+
+  Relocation section '.rel.text' at offset 0x190 contains 4 entries:
+      Offset             Info             Type               Symbol's Value  Symbol's Name
+  0000000000000000  0000000600000001 R_BPF_64_64            0000000000000000 g1
+  0000000000000018  0000000700000001 R_BPF_64_64            0000000000000004 g2
+  0000000000000038  0000000400000001 R_BPF_64_64            0000000000000000 sec
+  0000000000000058  0000000400000001 R_BPF_64_64            0000000000000000 sec
+
+Each relocation is represented by ``Offset`` (8 bytes) and ``Info`` (8 bytes).
+For example, the first relocation corresponds to the first instruction
+(Offset 0x0) and the corresponding ``Info`` indicates the relocation type
+of ``R_BPF_64_64`` (type 1) and the entry in the symbol table (entry 6).
+The following is the symbol table with ``llvm-readelf -s test.o``::
+
+  Symbol table '.symtab' contains 8 entries:
+     Num:    Value          Size Type    Bind   Vis       Ndx Name
+       0: 0000000000000000     0 NOTYPE  LOCAL  DEFAULT   UND
+       1: 0000000000000000     0 FILE    LOCAL  DEFAULT   ABS test.c
+       2: 0000000000000008     4 OBJECT  LOCAL  DEFAULT     4 l1
+       3: 000000000000000c     4 OBJECT  LOCAL  DEFAULT     4 l2
+       4: 0000000000000000     0 SECTION LOCAL  DEFAULT     4 sec
+       5: 0000000000000000   128 FUNC    GLOBAL DEFAULT     2 test
+       6: 0000000000000000     4 OBJECT  GLOBAL DEFAULT     4 g1
+       7: 0000000000000004     4 OBJECT  GLOBAL DEFAULT     4 g2
+
+The 6th entry is global variable ``g1`` with value 0.
+
+Similarly, the second relocation is at ``.text`` offset ``0x18``, instruction 3,
+for global variable ``g2`` which has a symbol value 4, the offset
+from the start of ``.data`` section.
+
+The third and fourth relocations refers to static variables ``l1``
+and ``l2``. From ``.rel.text`` section above, it is not clear
+which symbols they really refers to as they both refers to
+symbol table entry 4, symbol ``sec``, which has ``STT_SECTION`` type
+and represents a section. So for static variable or function,
+the section offset is written to the original insn
+buffer, which is called ``A`` (addend). Looking at
+above insn ``7`` and ``11``, they have section offset ``8`` and ``12``.
+From symbol table, we can find that they correspond to entries ``2``
+and ``3`` for ``l1`` and ``l2``.
+
+In general, the ``A`` is 0 for global variables and functions,
+and is the section offset or some computation result based on
+section offset for static variables/functions. The non-section-offset
+case refers to function calls. See below for more details.
+
+Different Relocation Types
+==========================
+
+Six relocation types are supported. The following is an overview and
+``S`` represents the value of the symbol in the symbol table::
+
+  Enum  ELF Reloc Type     Description      BitSize  Offset        Calculation
+  0     R_BPF_NONE         None
+  1     R_BPF_64_64        ld_imm64 insn    32       r_offset + 4  S + A
+  2     R_BPF_64_ABS64     normal data      64       r_offset      S + A
+  3     R_BPF_64_ABS32     normal data      32       r_offset      S + A
+  4     R_BPF_64_NODYLD32  .BTF[.ext] data  32       r_offset      S + A
+  10    R_BPF_64_32        call insn        32       r_offset + 4  (S + A) / 8 - 1
+
+For example, ``R_BPF_64_64`` relocation type is used for ``ld_imm64`` instruction.
+The actual to-be-relocated data (0 or section offset)
+is stored at ``r_offset + 4`` and the read/write
+data bitsize is 32 (4 bytes). The relocation can be resolved with
+the symbol value plus implicit addend. Note that the ``BitSize`` is 32 which
+means the section offset must be less than or equal to ``UINT32_MAX`` and this
+is enforced by LLVM BPF backend.
+
+In another case, ``R_BPF_64_ABS64`` relocation type is used for normal 64-bit data.
+The actual to-be-relocated data is stored at ``r_offset`` and the read/write data
+bitsize is 64 (8 bytes). The relocation can be resolved with
+the symbol value plus implicit addend.
+
+Both ``R_BPF_64_ABS32`` and ``R_BPF_64_NODYLD32`` types are for 32-bit data.
+But ``R_BPF_64_NODYLD32`` specifically refers to relocations in ``.BTF`` and
+``.BTF.ext`` sections. For cases like bcc where llvm ``ExecutionEngine RuntimeDyld``
+is involved, ``R_BPF_64_NODYLD32`` types of relocations should not be resolved
+to actual function/variable address. Otherwise, ``.BTF`` and ``.BTF.ext``
+become unusable by bcc and kernel.
+
+Type ``R_BPF_64_32`` is used for call instruction. The call target section
+offset is stored at ``r_offset + 4`` (32bit) and calculated as
+``(S + A) / 8 - 1``.
+
+Examples
+========
+
+Types ``R_BPF_64_64`` and ``R_BPF_64_32`` are used to resolve ``ld_imm64``
+and ``call`` instructions. For example::
+
+  __attribute__((noinline)) __attribute__((section("sec1")))
+  int gfunc(int a, int b) {
+    return a * b;
+  }
+  static __attribute__((noinline)) __attribute__((section("sec1")))
+  int lfunc(int a, int b) {
+    return a + b;
+  }
+  int global __attribute__((section("sec2")));
+  int test(int a, int b) {
+    return gfunc(a, b) +  lfunc(a, b) + global;
+  }
+
+Compiled with ``clang -target bpf -O2 -c test.c``, we will have
+following code with `llvm-objdump -dr test.o``::
+
+  Disassembly of section .text:
+
+  0000000000000000 <test>:
+         0:       bf 26 00 00 00 00 00 00 r6 = r2
+         1:       bf 17 00 00 00 00 00 00 r7 = r1
+         2:       85 10 00 00 ff ff ff ff call -1
+                  0000000000000010:  R_BPF_64_32  gfunc
+         3:       bf 08 00 00 00 00 00 00 r8 = r0
+         4:       bf 71 00 00 00 00 00 00 r1 = r7
+         5:       bf 62 00 00 00 00 00 00 r2 = r6
+         6:       85 10 00 00 02 00 00 00 call 2
+                  0000000000000030:  R_BPF_64_32  sec1
+         7:       0f 80 00 00 00 00 00 00 r0 += r8
+         8:       18 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r1 = 0 ll
+                  0000000000000040:  R_BPF_64_64  global
+        10:       61 11 00 00 00 00 00 00 r1 = *(u32 *)(r1 + 0)
+        11:       0f 10 00 00 00 00 00 00 r0 += r1
+        12:       95 00 00 00 00 00 00 00 exit
+
+  Disassembly of section sec1:
+
+  0000000000000000 <gfunc>:
+         0:       bf 20 00 00 00 00 00 00 r0 = r2
+         1:       2f 10 00 00 00 00 00 00 r0 *= r1
+         2:       95 00 00 00 00 00 00 00 exit
+
+  0000000000000018 <lfunc>:
+         3:       bf 20 00 00 00 00 00 00 r0 = r2
+         4:       0f 10 00 00 00 00 00 00 r0 += r1
+         5:       95 00 00 00 00 00 00 00 exit
+
+The first relocation corresponds to ``gfunc(a, b)`` where ``gfunc`` has a value of 0,
+so the ``call`` instruction offset is ``(0 + 0)/8 - 1 = -1``.
+The second relocation corresponds to ``lfunc(a, b)`` where ``lfunc`` has a section
+offset ``0x18``, so the ``call`` instruction offset is ``(0 + 0x18)/8 - 1 = 2``.
+The third relocation corresponds to ld_imm64 of ``global``, which has a section
+offset ``0``.
+
+The following is an example to show how R_BPF_64_ABS64 could be generated::
+
+  int global() { return 0; }
+  struct t { void *g; } gbl = { global };
+
+Compiled with ``clang -target bpf -O2 -g -c test.c``, we will see a
+relocation below in ``.data`` section with command
+``llvm-readelf -r test.o``::
+
+  Relocation section '.rel.data' at offset 0x458 contains 1 entries:
+      Offset             Info             Type               Symbol's Value  Symbol's Name
+  0000000000000000  0000000700000002 R_BPF_64_ABS64         0000000000000000 global
+
+The relocation says the first 8-byte of ``.data`` section should be
+filled with address of ``global`` variable.
+
+With ``llvm-readelf`` output, we can see that dwarf sections have a bunch of
+``R_BPF_64_ABS32`` and ``R_BPF_64_ABS64`` relocations::
+
+  Relocation section '.rel.debug_info' at offset 0x468 contains 13 entries:
+      Offset             Info             Type               Symbol's Value  Symbol's Name
+  0000000000000006  0000000300000003 R_BPF_64_ABS32         0000000000000000 .debug_abbrev
+  000000000000000c  0000000400000003 R_BPF_64_ABS32         0000000000000000 .debug_str
+  0000000000000012  0000000400000003 R_BPF_64_ABS32         0000000000000000 .debug_str
+  0000000000000016  0000000600000003 R_BPF_64_ABS32         0000000000000000 .debug_line
+  000000000000001a  0000000400000003 R_BPF_64_ABS32         0000000000000000 .debug_str
+  000000000000001e  0000000200000002 R_BPF_64_ABS64         0000000000000000 .text
+  000000000000002b  0000000400000003 R_BPF_64_ABS32         0000000000000000 .debug_str
+  0000000000000037  0000000800000002 R_BPF_64_ABS64         0000000000000000 gbl
+  0000000000000040  0000000400000003 R_BPF_64_ABS32         0000000000000000 .debug_str
+  ......
+
+The .BTF/.BTF.ext sections has R_BPF_64_NODYLD32 relocations::
+
+  Relocation section '.rel.BTF' at offset 0x538 contains 1 entries:
+      Offset             Info             Type               Symbol's Value  Symbol's Name
+  0000000000000084  0000000800000004 R_BPF_64_NODYLD32      0000000000000000 gbl
+
+  Relocation section '.rel.BTF.ext' at offset 0x548 contains 2 entries:
+      Offset             Info             Type               Symbol's Value  Symbol's Name
+  000000000000002c  0000000200000004 R_BPF_64_NODYLD32      0000000000000000 .text
+  0000000000000040  0000000200000004 R_BPF_64_NODYLD32      0000000000000000 .text
diff --git a/Documentation/devicetree/bindings/net/brcm,iproc-mdio.txt b/Documentation/devicetree/bindings/net/brcm,iproc-mdio.txt
deleted file mode 100644
index 8ba9ed11d716..000000000000
--- a/Documentation/devicetree/bindings/net/brcm,iproc-mdio.txt
+++ /dev/null
@@ -1,23 +0,0 @@
-* Broadcom iProc MDIO bus controller
-
-Required properties:
-- compatible: should be "brcm,iproc-mdio"
-- reg: address and length of the register set for the MDIO interface
-- #size-cells: must be 1
-- #address-cells: must be 0
-
-Child nodes of this MDIO bus controller node are standard Ethernet PHY device
-nodes as described in Documentation/devicetree/bindings/net/phy.txt
-
-Example:
-
-mdio@18002000 {
-	compatible = "brcm,iproc-mdio";
-	reg = <0x18002000 0x8>;
-	#size-cells = <1>;
-	#address-cells = <0>;
-
-	enet-gphy@0 {
-		reg = <0>;
-	};
-};
diff --git a/Documentation/devicetree/bindings/net/brcm,iproc-mdio.yaml b/Documentation/devicetree/bindings/net/brcm,iproc-mdio.yaml
new file mode 100644
index 000000000000..3031395f7e6e
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/brcm,iproc-mdio.yaml
@@ -0,0 +1,38 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/brcm,iproc-mdio.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Broadcom iProc MDIO bus controller
+
+maintainers:
+  - Rafał Miłecki <rafal@milecki.pl>
+
+allOf:
+  - $ref: mdio.yaml#
+
+properties:
+  compatible:
+    const: brcm,iproc-mdio
+
+  reg:
+    maxItems: 1
+
+unevaluatedProperties: false
+
+required:
+  - reg
+
+examples:
+  - |
+    mdio@18002000 {
+        compatible = "brcm,iproc-mdio";
+        reg = <0x18002000 0x8>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        ethernet-phy@0 {
+            reg = <0>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/net/can/rcar_can.txt b/Documentation/devicetree/bindings/net/can/rcar_can.txt
deleted file mode 100644
index 90ac4fef23f5..000000000000
--- a/Documentation/devicetree/bindings/net/can/rcar_can.txt
+++ /dev/null
@@ -1,80 +0,0 @@
-Renesas R-Car CAN controller Device Tree Bindings
--------------------------------------------------
-
-Required properties:
-- compatible: "renesas,can-r8a7742" if CAN controller is a part of R8A7742 SoC.
-	      "renesas,can-r8a7743" if CAN controller is a part of R8A7743 SoC.
-	      "renesas,can-r8a7744" if CAN controller is a part of R8A7744 SoC.
-	      "renesas,can-r8a7745" if CAN controller is a part of R8A7745 SoC.
-	      "renesas,can-r8a77470" if CAN controller is a part of R8A77470 SoC.
-	      "renesas,can-r8a774a1" if CAN controller is a part of R8A774A1 SoC.
-	      "renesas,can-r8a774b1" if CAN controller is a part of R8A774B1 SoC.
-	      "renesas,can-r8a774c0" if CAN controller is a part of R8A774C0 SoC.
-	      "renesas,can-r8a774e1" if CAN controller is a part of R8A774E1 SoC.
-	      "renesas,can-r8a7778" if CAN controller is a part of R8A7778 SoC.
-	      "renesas,can-r8a7779" if CAN controller is a part of R8A7779 SoC.
-	      "renesas,can-r8a7790" if CAN controller is a part of R8A7790 SoC.
-	      "renesas,can-r8a7791" if CAN controller is a part of R8A7791 SoC.
-	      "renesas,can-r8a7792" if CAN controller is a part of R8A7792 SoC.
-	      "renesas,can-r8a7793" if CAN controller is a part of R8A7793 SoC.
-	      "renesas,can-r8a7794" if CAN controller is a part of R8A7794 SoC.
-	      "renesas,can-r8a7795" if CAN controller is a part of R8A7795 SoC.
-	      "renesas,can-r8a7796" if CAN controller is a part of R8A77960 SoC.
-	      "renesas,can-r8a77961" if CAN controller is a part of R8A77961 SoC.
-	      "renesas,can-r8a77965" if CAN controller is a part of R8A77965 SoC.
-	      "renesas,can-r8a77990" if CAN controller is a part of R8A77990 SoC.
-	      "renesas,can-r8a77995" if CAN controller is a part of R8A77995 SoC.
-	      "renesas,rcar-gen1-can" for a generic R-Car Gen1 compatible device.
-	      "renesas,rcar-gen2-can" for a generic R-Car Gen2 or RZ/G1
-	      compatible device.
-	      "renesas,rcar-gen3-can" for a generic R-Car Gen3 or RZ/G2
-	      compatible device.
-	      When compatible with the generic version, nodes must list the
-	      SoC-specific version corresponding to the platform first
-	      followed by the generic version.
-
-- reg: physical base address and size of the R-Car CAN register map.
-- interrupts: interrupt specifier for the sole interrupt.
-- clocks: phandles and clock specifiers for 3 CAN clock inputs.
-- clock-names: 3 clock input name strings: "clkp1", "clkp2", and "can_clk".
-- pinctrl-0: pin control group to be used for this controller.
-- pinctrl-names: must be "default".
-
-Required properties for R8A774A1, R8A774B1, R8A774C0, R8A774E1, R8A7795,
-R8A77960, R8A77961, R8A77965, R8A77990, and R8A77995:
-For the denoted SoCs, "clkp2" can be CANFD clock. This is a div6 clock and can
-be used by both CAN and CAN FD controller at the same time. It needs to be
-scaled to maximum frequency if any of these controllers use it. This is done
-using the below properties:
-
-- assigned-clocks: phandle of clkp2(CANFD) clock.
-- assigned-clock-rates: maximum frequency of this clock.
-
-Optional properties:
-- renesas,can-clock-select: R-Car CAN Clock Source Select. Valid values are:
-			    <0x0> (default) : Peripheral clock (clkp1)
-			    <0x1> : Peripheral clock (clkp2)
-			    <0x3> : External input clock
-
-Example
--------
-
-SoC common .dtsi file:
-
-	can0: can@e6e80000 {
-		compatible = "renesas,can-r8a7791", "renesas,rcar-gen2-can";
-		reg = <0 0xe6e80000 0 0x1000>;
-		interrupts = <0 186 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&mstp9_clks R8A7791_CLK_RCAN0>,
-			 <&cpg_clocks R8A7791_CLK_RCAN>, <&can_clk>;
-		clock-names = "clkp1", "clkp2", "can_clk";
-		status = "disabled";
-	};
-
-Board specific .dts file:
-
-&can0 {
-	pinctrl-0 = <&can0_pins>;
-	pinctrl-names = "default";
-	status = "okay";
-};
diff --git a/Documentation/devicetree/bindings/net/can/rcar_canfd.txt b/Documentation/devicetree/bindings/net/can/rcar_canfd.txt
deleted file mode 100644
index 248c4ed97a0a..000000000000
--- a/Documentation/devicetree/bindings/net/can/rcar_canfd.txt
+++ /dev/null
@@ -1,107 +0,0 @@
-Renesas R-Car CAN FD controller Device Tree Bindings
-----------------------------------------------------
-
-Required properties:
-- compatible: Must contain one or more of the following:
-  - "renesas,rcar-gen3-canfd" for R-Car Gen3 and RZ/G2 compatible controllers.
-  - "renesas,r8a774a1-canfd" for R8A774A1 (RZ/G2M) compatible controller.
-  - "renesas,r8a774b1-canfd" for R8A774B1 (RZ/G2N) compatible controller.
-  - "renesas,r8a774c0-canfd" for R8A774C0 (RZ/G2E) compatible controller.
-  - "renesas,r8a774e1-canfd" for R8A774E1 (RZ/G2H) compatible controller.
-  - "renesas,r8a7795-canfd" for R8A7795 (R-Car H3) compatible controller.
-  - "renesas,r8a7796-canfd" for R8A7796 (R-Car M3-W) compatible controller.
-  - "renesas,r8a77965-canfd" for R8A77965 (R-Car M3-N) compatible controller.
-  - "renesas,r8a77970-canfd" for R8A77970 (R-Car V3M) compatible controller.
-  - "renesas,r8a77980-canfd" for R8A77980 (R-Car V3H) compatible controller.
-  - "renesas,r8a77990-canfd" for R8A77990 (R-Car E3) compatible controller.
-  - "renesas,r8a77995-canfd" for R8A77995 (R-Car D3) compatible controller.
-
-  When compatible with the generic version, nodes must list the
-  SoC-specific version corresponding to the platform first, followed by the
-  family-specific and/or generic versions.
-
-- reg: physical base address and size of the R-Car CAN FD register map.
-- interrupts: interrupt specifiers for the Channel & Global interrupts
-- clocks: phandles and clock specifiers for 3 clock inputs.
-- clock-names: 3 clock input name strings: "fck", "canfd", "can_clk".
-- pinctrl-0: pin control group to be used for this controller.
-- pinctrl-names: must be "default".
-
-Required child nodes:
-The controller supports two channels and each is represented as a child node.
-The name of the child nodes are "channel0" and "channel1" respectively. Each
-child node supports the "status" property only, which is used to
-enable/disable the respective channel.
-
-Required properties for R8A774A1, R8A774B1, R8A774C0, R8A774E1, R8A7795,
-R8A7796, R8A77965, R8A77990, and R8A77995:
-In the denoted SoCs, canfd clock is a div6 clock and can be used by both CAN
-and CAN FD controller at the same time. It needs to be scaled to maximum
-frequency if any of these controllers use it. This is done using the below
-properties:
-
-- assigned-clocks: phandle of canfd clock.
-- assigned-clock-rates: maximum frequency of this clock.
-
-Optional property:
-The controller can operate in either CAN FD only mode (default) or
-Classical CAN only mode. The mode is global to both the channels. In order to
-enable the later, define the following optional property.
- - renesas,no-can-fd: puts the controller in Classical CAN only mode.
-
-Example
--------
-
-SoC common .dtsi file:
-
-		canfd: can@e66c0000 {
-			compatible = "renesas,r8a7795-canfd",
-				     "renesas,rcar-gen3-canfd";
-			reg = <0 0xe66c0000 0 0x8000>;
-			interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>,
-				   <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&cpg CPG_MOD 914>,
-			       <&cpg CPG_CORE R8A7795_CLK_CANFD>,
-			       <&can_clk>;
-			clock-names = "fck", "canfd", "can_clk";
-			assigned-clocks = <&cpg CPG_CORE R8A7795_CLK_CANFD>;
-			assigned-clock-rates = <40000000>;
-			power-domains = <&cpg>;
-			status = "disabled";
-
-			channel0 {
-				status = "disabled";
-			};
-
-			channel1 {
-				status = "disabled";
-			};
-		};
-
-Board specific .dts file:
-
-E.g. below enables Channel 1 alone in the board in Classical CAN only mode.
-
-&canfd {
-	pinctrl-0 = <&canfd1_pins>;
-	pinctrl-names = "default";
-	renesas,no-can-fd;
-	status = "okay";
-
-	channel1 {
-		status = "okay";
-	};
-};
-
-E.g. below enables Channel 0 alone in the board using External clock
-as fCAN clock.
-
-&canfd {
-	pinctrl-0 = <&canfd0_pins>, <&can_clk_pins>;
-	pinctrl-names = "default";
-	status = "okay";
-
-	channel0 {
-		status = "okay";
-	};
-};
diff --git a/Documentation/devicetree/bindings/net/can/renesas,rcar-can.yaml b/Documentation/devicetree/bindings/net/can/renesas,rcar-can.yaml
new file mode 100644
index 000000000000..fadc871fd6b0
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/renesas,rcar-can.yaml
@@ -0,0 +1,139 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/can/renesas,rcar-can.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Renesas R-Car CAN Controller
+
+maintainers:
+  - Sergei Shtylyov <sergei.shtylyov@gmail.com>
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+          - enum:
+              - renesas,can-r8a7778      # R-Car M1-A
+              - renesas,can-r8a7779      # R-Car H1
+          - const: renesas,rcar-gen1-can # R-Car Gen1
+
+      - items:
+          - enum:
+              - renesas,can-r8a7742      # RZ/G1H
+              - renesas,can-r8a7743      # RZ/G1M
+              - renesas,can-r8a7744      # RZ/G1N
+              - renesas,can-r8a7745      # RZ/G1E
+              - renesas,can-r8a77470     # RZ/G1C
+              - renesas,can-r8a7790      # R-Car H2
+              - renesas,can-r8a7791      # R-Car M2-W
+              - renesas,can-r8a7792      # R-Car V2H
+              - renesas,can-r8a7793      # R-Car M2-N
+              - renesas,can-r8a7794      # R-Car E2
+          - const: renesas,rcar-gen2-can # R-Car Gen2 and RZ/G1
+
+      - items:
+          - enum:
+              - renesas,can-r8a774a1     # RZ/G2M
+              - renesas,can-r8a774b1     # RZ/G2N
+              - renesas,can-r8a774c0     # RZ/G2E
+              - renesas,can-r8a774e1     # RZ/G2H
+              - renesas,can-r8a7795      # R-Car H3
+              - renesas,can-r8a7796      # R-Car M3-W
+              - renesas,can-r8a77961     # R-Car M3-W+
+              - renesas,can-r8a77965     # R-Car M3-N
+              - renesas,can-r8a77990     # R-Car E3
+              - renesas,can-r8a77995     # R-Car D3
+          - const: renesas,rcar-gen3-can # R-Car Gen3 and RZ/G2
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 3
+
+  clock-names:
+    items:
+      - const: clkp1
+      - const: clkp2
+      - const: can_clk
+
+  power-domains:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  renesas,can-clock-select:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum: [ 0, 1, 3 ]
+    default: 0
+    description: |
+      R-Car CAN Clock Source Select.  Valid values are:
+        <0x0> (default) : Peripheral clock (clkp1)
+        <0x1> : Peripheral clock (clkp2)
+        <0x3> : External input clock
+
+  assigned-clocks:
+    description:
+      Reference to the clkp2 (CANFD) clock.
+      On R-Car Gen3 and RZ/G2 SoCs, "clkp2" is the CANFD clock.  This is a div6
+      clock and can be used by both CAN and CAN FD controllers at the same
+      time.  It needs to be scaled to maximum frequency if any of these
+      controllers use it.
+
+  assigned-clock-rates:
+    description: Maximum frequency of the CANFD clock.
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - power-domains
+
+allOf:
+  - $ref: can-controller.yaml#
+
+  - if:
+      not:
+        properties:
+          compatible:
+            contains:
+              const: renesas,rcar-gen1-can
+    then:
+      required:
+        - resets
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: renesas,rcar-gen3-can
+    then:
+      required:
+        - assigned-clocks
+        - assigned-clock-rates
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/r8a7791-cpg-mssr.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/power/r8a7791-sysc.h>
+
+    can0: can@e6e80000 {
+            compatible = "renesas,can-r8a7791", "renesas,rcar-gen2-can";
+            reg = <0xe6e80000 0x1000>;
+            interrupts = <GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>;
+            clocks = <&cpg CPG_MOD 916>,
+                     <&cpg CPG_CORE R8A7791_CLK_RCAN>, <&can_clk>;
+            clock-names = "clkp1", "clkp2", "can_clk";
+            power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
+            resets = <&cpg 916>;
+    };
diff --git a/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml
new file mode 100644
index 000000000000..0b33ba9ccb47
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml
@@ -0,0 +1,122 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/can/renesas,rcar-canfd.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Renesas R-Car CAN FD Controller
+
+maintainers:
+  - Fabrizio Castro <fabrizio.castro.jz@renesas.com>
+
+allOf:
+  - $ref: can-controller.yaml#
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+          - enum:
+              - renesas,r8a774a1-canfd     # RZ/G2M
+              - renesas,r8a774b1-canfd     # RZ/G2N
+              - renesas,r8a774c0-canfd     # RZ/G2E
+              - renesas,r8a774e1-canfd     # RZ/G2H
+              - renesas,r8a7795-canfd      # R-Car H3
+              - renesas,r8a7796-canfd      # R-Car M3-W
+              - renesas,r8a77965-canfd     # R-Car M3-N
+              - renesas,r8a77970-canfd     # R-Car V3M
+              - renesas,r8a77980-canfd     # R-Car V3H
+              - renesas,r8a77990-canfd     # R-Car E3
+              - renesas,r8a77995-canfd     # R-Car D3
+          - const: renesas,rcar-gen3-canfd # R-Car Gen3 and RZ/G2
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    items:
+      - description: Channel interrupt
+      - description: Global interrupt
+
+  clocks:
+    maxItems: 3
+
+  clock-names:
+    items:
+      - const: fck
+      - const: canfd
+      - const: can_clk
+
+  power-domains:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  renesas,no-can-fd:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description:
+      The controller can operate in either CAN FD only mode (default) or
+      Classical CAN only mode.  The mode is global to both the channels.
+      Specify this property to put the controller in Classical CAN only mode.
+
+  assigned-clocks:
+    description:
+      Reference to the CANFD clock.  The CANFD clock is a div6 clock and can be
+      used by both CAN (if present) and CAN FD controllers at the same time.
+      It needs to be scaled to maximum frequency if any of these controllers
+      use it.
+
+  assigned-clock-rates:
+    description: Maximum frequency of the CANFD clock.
+
+patternProperties:
+  "^channel[01]$":
+    type: object
+    description:
+      The controller supports two channels and each is represented as a child
+      node.  Each child node supports the "status" property only, which
+      is used to enable/disable the respective channel.
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - power-domains
+  - resets
+  - assigned-clocks
+  - assigned-clock-rates
+  - channel0
+  - channel1
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/r8a7795-cpg-mssr.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/power/r8a7795-sysc.h>
+
+    canfd: can@e66c0000 {
+            compatible = "renesas,r8a7795-canfd",
+                         "renesas,rcar-gen3-canfd";
+            reg = <0xe66c0000 0x8000>;
+            interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+            clocks = <&cpg CPG_MOD 914>,
+                     <&cpg CPG_CORE R8A7795_CLK_CANFD>,
+                     <&can_clk>;
+            clock-names = "fck", "canfd", "can_clk";
+            assigned-clocks = <&cpg CPG_CORE R8A7795_CLK_CANFD>;
+            assigned-clock-rates = <40000000>;
+            power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+            resets = <&cpg 914>;
+
+            channel0 {
+            };
+
+            channel1 {
+            };
+    };
diff --git a/Documentation/devicetree/bindings/net/dsa/mt7530.txt b/Documentation/devicetree/bindings/net/dsa/mt7530.txt
index de04626a8e9d..18247ebfc487 100644
--- a/Documentation/devicetree/bindings/net/dsa/mt7530.txt
+++ b/Documentation/devicetree/bindings/net/dsa/mt7530.txt
@@ -81,6 +81,12 @@ Optional properties:
 - gpio-controller: Boolean; if defined, MT7530's LED controller will run on
 	GPIO mode.
 - #gpio-cells: Must be 2 if gpio-controller is defined.
+- interrupt-controller: Boolean; Enables the internal interrupt controller.
+
+If interrupt-controller is defined, the following properties are required.
+
+- #interrupt-cells: Must be 1.
+- interrupts: Parent interrupt for the interrupt controller.
 
 See Documentation/devicetree/bindings/net/dsa/dsa.txt for a list of additional
 required, optional properties and how the integrated switch subnodes must
diff --git a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml
new file mode 100644
index 000000000000..0b8a05dd52e6
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml
@@ -0,0 +1,132 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/dsa/nxp,sja1105.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: NXP SJA1105 Automotive Ethernet Switch Family Device Tree Bindings
+
+description:
+  The SJA1105 SPI interface requires a CS-to-CLK time (t2 in UM10944.pdf) of at
+  least one half of t_CLK. At an SPI frequency of 1MHz, this means a minimum
+  cs_sck_delay of 500ns. Ensuring that this SPI timing requirement is observed
+  depends on the SPI bus master driver.
+
+allOf:
+  - $ref: "dsa.yaml#"
+
+maintainers:
+  - Vladimir Oltean <vladimir.oltean@nxp.com>
+
+properties:
+  compatible:
+    enum:
+      - nxp,sja1105e
+      - nxp,sja1105t
+      - nxp,sja1105p
+      - nxp,sja1105q
+      - nxp,sja1105r
+      - nxp,sja1105s
+      - nxp,sja1110a
+      - nxp,sja1110b
+      - nxp,sja1110c
+      - nxp,sja1110d
+
+  reg:
+    maxItems: 1
+
+  # Optional container node for the 2 internal MDIO buses of the SJA1110
+  # (one for the internal 100base-T1 PHYs and the other for the single
+  # 100base-TX PHY). The "reg" property does not have physical significance.
+  # The PHY addresses to port correspondence is as follows: for 100base-T1,
+  # port 5 has PHY 1, port 6 has PHY 2 etc, while for 100base-TX, port 1 has
+  # PHY 1.
+  mdios:
+    type: object
+
+    properties:
+      '#address-cells':
+        const: 1
+      '#size-cells':
+        const: 0
+
+    patternProperties:
+      "^mdio@[0-1]$":
+        type: object
+
+        allOf:
+          - $ref: "http://devicetree.org/schemas/net/mdio.yaml#"
+
+        properties:
+          compatible:
+            oneOf:
+              - enum:
+                  - nxp,sja1110-base-t1-mdio
+                  - nxp,sja1110-base-tx-mdio
+
+          reg:
+            oneOf:
+              - enum:
+                - 0
+                - 1
+
+        required:
+          - compatible
+          - reg
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    spi {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            ethernet-switch@1 {
+                    reg = <0x1>;
+                    compatible = "nxp,sja1105t";
+
+                    ethernet-ports {
+                            #address-cells = <1>;
+                            #size-cells = <0>;
+
+                            port@0 {
+                                    phy-handle = <&rgmii_phy6>;
+                                    phy-mode = "rgmii-id";
+                                    reg = <0>;
+                            };
+
+                            port@1 {
+                                    phy-handle = <&rgmii_phy3>;
+                                    phy-mode = "rgmii-id";
+                                    reg = <1>;
+                            };
+
+                            port@2 {
+                                    phy-handle = <&rgmii_phy4>;
+                                    phy-mode = "rgmii-id";
+                                    reg = <2>;
+                            };
+
+                            port@3 {
+                                    phy-mode = "rgmii-id";
+                                    reg = <3>;
+                            };
+
+                            port@4 {
+                                    ethernet = <&enet2>;
+                                    phy-mode = "rgmii";
+                                    reg = <4>;
+
+                                    fixed-link {
+                                            speed = <1000>;
+                                            full-duplex;
+                                    };
+                            };
+                    };
+            };
+    };
diff --git a/Documentation/devicetree/bindings/net/dsa/qca8k.txt b/Documentation/devicetree/bindings/net/dsa/qca8k.txt
index ccbc6d89325d..8c73f67c43ca 100644
--- a/Documentation/devicetree/bindings/net/dsa/qca8k.txt
+++ b/Documentation/devicetree/bindings/net/dsa/qca8k.txt
@@ -3,6 +3,7 @@
 Required properties:
 
 - compatible: should be one of:
+    "qca,qca8327"
     "qca,qca8334"
     "qca,qca8337"
 
@@ -20,6 +21,10 @@ described in dsa/dsa.txt. If the QCA8K switch is connect to a SoC's external
 mdio-bus each subnode describing a port needs to have a valid phandle
 referencing the internal PHY it is connected to. This is because there's no
 N:N mapping of port and PHY id.
+To declare the internal mdio-bus configuration, declare a mdio node in the
+switch node and declare the phandle for the port referencing the internal
+PHY is connected to. In this config a internal mdio-bus is registered and
+the mdio MASTER is used as communication.
 
 Don't use mixed external and internal mdio-bus configurations, as this is
 not supported by the hardware.
@@ -149,26 +154,61 @@ for the internal master mdio-bus configuration:
 				port@1 {
 					reg = <1>;
 					label = "lan1";
+					phy-mode = "internal";
+					phy-handle = <&phy_port1>;
 				};
 
 				port@2 {
 					reg = <2>;
 					label = "lan2";
+					phy-mode = "internal";
+					phy-handle = <&phy_port2>;
 				};
 
 				port@3 {
 					reg = <3>;
 					label = "lan3";
+					phy-mode = "internal";
+					phy-handle = <&phy_port3>;
 				};
 
 				port@4 {
 					reg = <4>;
 					label = "lan4";
+					phy-mode = "internal";
+					phy-handle = <&phy_port4>;
 				};
 
 				port@5 {
 					reg = <5>;
 					label = "wan";
+					phy-mode = "internal";
+					phy-handle = <&phy_port5>;
+				};
+			};
+
+			mdio {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				phy_port1: phy@0 {
+					reg = <0>;
+				};
+
+				phy_port2: phy@1 {
+					reg = <1>;
+				};
+
+				phy_port3: phy@2 {
+					reg = <2>;
+				};
+
+				phy_port4: phy@3 {
+					reg = <3>;
+				};
+
+				phy_port5: phy@4 {
+					reg = <4>;
 				};
 			};
 		};
diff --git a/Documentation/devicetree/bindings/net/dsa/sja1105.txt b/Documentation/devicetree/bindings/net/dsa/sja1105.txt
deleted file mode 100644
index 13fd21074d48..000000000000
--- a/Documentation/devicetree/bindings/net/dsa/sja1105.txt
+++ /dev/null
@@ -1,156 +0,0 @@
-NXP SJA1105 switch driver
-=========================
-
-Required properties:
-
-- compatible:
-	Must be one of:
-	- "nxp,sja1105e"
-	- "nxp,sja1105t"
-	- "nxp,sja1105p"
-	- "nxp,sja1105q"
-	- "nxp,sja1105r"
-	- "nxp,sja1105s"
-
-	Although the device ID could be detected at runtime, explicit bindings
-	are required in order to be able to statically check their validity.
-	For example, SGMII can only be specified on port 4 of R and S devices,
-	and the non-SGMII devices, while pin-compatible, are not equal in terms
-	of support for RGMII internal delays (supported on P/Q/R/S, but not on
-	E/T).
-
-Optional properties:
-
-- sja1105,role-mac:
-- sja1105,role-phy:
-	Boolean properties that can be assigned under each port node. By
-	default (unless otherwise specified) a port is configured as MAC if it
-	is driving a PHY (phy-handle is present) or as PHY if it is PHY-less
-	(fixed-link specified, presumably because it is connected to a MAC).
-	The effect of this property (in either its implicit or explicit form)
-	is:
-	- In the case of MII or RMII it specifies whether the SJA1105 port is a
-	  clock source or sink for this interface (not applicable for RGMII
-	  where there is a Tx and an Rx clock).
-	- In the case of RGMII it affects the behavior regarding internal
-	  delays:
-	  1. If sja1105,role-mac is specified, and the phy-mode property is one
-	     of "rgmii-id", "rgmii-txid" or "rgmii-rxid", then the entity
-	     designated to apply the delay/clock skew necessary for RGMII
-	     is the PHY. The SJA1105 MAC does not apply any internal delays.
-	  2. If sja1105,role-phy is specified, and the phy-mode property is one
-	     of the above, the designated entity to apply the internal delays
-	     is the SJA1105 MAC (if hardware-supported). This is only supported
-	     by the second-generation (P/Q/R/S) hardware. On a first-generation
-	     E or T device, it is an error to specify an RGMII phy-mode other
-	     than "rgmii" for a port that is in fixed-link mode. In that case,
-	     the clock skew must either be added by the MAC at the other end of
-	     the fixed-link, or by PCB serpentine traces on the board.
-	These properties are required, for example, in the case where SJA1105
-	ports are at both ends of a MII/RMII PHY-less setup. One end would need
-	to have sja1105,role-mac, while the other sja1105,role-phy.
-
-See Documentation/devicetree/bindings/net/dsa/dsa.txt for the list of standard
-DSA required and optional properties.
-
-Other observations
-------------------
-
-The SJA1105 SPI interface requires a CS-to-CLK time (t2 in UM10944) of at least
-one half of t_CLK. At an SPI frequency of 1MHz, this means a minimum
-cs_sck_delay of 500ns. Ensuring that this SPI timing requirement is observed
-depends on the SPI bus master driver.
-
-Example
--------
-
-Ethernet switch connected via SPI to the host, CPU port wired to enet2:
-
-arch/arm/boot/dts/ls1021a-tsn.dts:
-
-/* SPI controller of the LS1021 */
-&dspi0 {
-	sja1105@1 {
-		reg = <0x1>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		compatible = "nxp,sja1105t";
-		spi-max-frequency = <4000000>;
-		fsl,spi-cs-sck-delay = <1000>;
-		fsl,spi-sck-cs-delay = <1000>;
-		ports {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			port@0 {
-				/* ETH5 written on chassis */
-				label = "swp5";
-				phy-handle = <&rgmii_phy6>;
-				phy-mode = "rgmii-id";
-				reg = <0>;
-				/* Implicit "sja1105,role-mac;" */
-			};
-			port@1 {
-				/* ETH2 written on chassis */
-				label = "swp2";
-				phy-handle = <&rgmii_phy3>;
-				phy-mode = "rgmii-id";
-				reg = <1>;
-				/* Implicit "sja1105,role-mac;" */
-			};
-			port@2 {
-				/* ETH3 written on chassis */
-				label = "swp3";
-				phy-handle = <&rgmii_phy4>;
-				phy-mode = "rgmii-id";
-				reg = <2>;
-				/* Implicit "sja1105,role-mac;" */
-			};
-			port@3 {
-				/* ETH4 written on chassis */
-				phy-handle = <&rgmii_phy5>;
-				label = "swp4";
-				phy-mode = "rgmii-id";
-				reg = <3>;
-				/* Implicit "sja1105,role-mac;" */
-			};
-			port@4 {
-				/* Internal port connected to eth2 */
-				ethernet = <&enet2>;
-				phy-mode = "rgmii";
-				reg = <4>;
-				/* Implicit "sja1105,role-phy;" */
-				fixed-link {
-					speed = <1000>;
-					full-duplex;
-				};
-			};
-		};
-	};
-};
-
-/* MDIO controller of the LS1021 */
-&mdio0 {
-	/* BCM5464 */
-	rgmii_phy3: ethernet-phy@3 {
-		reg = <0x3>;
-	};
-	rgmii_phy4: ethernet-phy@4 {
-		reg = <0x4>;
-	};
-	rgmii_phy5: ethernet-phy@5 {
-		reg = <0x5>;
-	};
-	rgmii_phy6: ethernet-phy@6 {
-		reg = <0x6>;
-	};
-};
-
-/* Ethernet master port of the LS1021 */
-&enet2 {
-	phy-connection-type = "rgmii";
-	status = "ok";
-	fixed-link {
-		speed = <1000>;
-		full-duplex;
-	};
-};
diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
index e8f04687a3e0..b0933a8c295a 100644
--- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
@@ -68,6 +68,7 @@ properties:
       - tbi
       - rev-mii
       - rmii
+      - rev-rmii
 
       # RX and TX delays are added by the MAC when required
       - rgmii
@@ -97,6 +98,7 @@ properties:
       - 10gbase-kr
       - usxgmii
       - 10gbase-r
+      - 25gbase-r
 
   phy-mode:
     $ref: "#/properties/phy-connection-type"
diff --git a/Documentation/devicetree/bindings/net/ingenic,mac.yaml b/Documentation/devicetree/bindings/net/ingenic,mac.yaml
new file mode 100644
index 000000000000..5e93d4f9a080
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/ingenic,mac.yaml
@@ -0,0 +1,76 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/ingenic,mac.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Bindings for MAC in Ingenic SoCs
+
+maintainers:
+  - 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>
+
+description:
+  The Ethernet Media Access Controller in Ingenic SoCs.
+
+properties:
+  compatible:
+    enum:
+      - ingenic,jz4775-mac
+      - ingenic,x1000-mac
+      - ingenic,x1600-mac
+      - ingenic,x1830-mac
+      - ingenic,x2000-mac
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  interrupt-names:
+    const: macirq
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    const: stmmaceth
+
+  mode-reg:
+    description: An extra syscon register that control ethernet interface and timing delay
+
+  rx-clk-delay-ps:
+    description: RGMII receive clock delay defined in pico seconds
+
+  tx-clk-delay-ps:
+    description: RGMII transmit clock delay defined in pico seconds
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - interrupt-names
+  - clocks
+  - clock-names
+  - mode-reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/x1000-cgu.h>
+
+    mac: ethernet@134b0000 {
+        compatible = "ingenic,x1000-mac", "snps,dwmac";
+        reg = <0x134b0000 0x2000>;
+
+        interrupt-parent = <&intc>;
+        interrupts = <55>;
+        interrupt-names = "macirq";
+
+        clocks = <&cgu X1000_CLK_MAC>;
+        clock-names = "stmmaceth";
+
+        mode-reg = <&mac_phy_ctrl>;
+    };
+...
diff --git a/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml b/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml
index 477066e2b821..081742c2b726 100644
--- a/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml
+++ b/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml
@@ -27,6 +27,9 @@ properties:
   reg:
     maxItems: 1
 
+  clocks:
+    maxItems: 1
+
   wake-gpios:
     maxItems: 1
     description:
@@ -80,6 +83,8 @@ examples:
 
             en-gpios = <&gpf1 4 GPIO_ACTIVE_HIGH>;
             wake-gpios = <&gpj0 2 GPIO_ACTIVE_HIGH>;
+
+            clocks = <&rpmcc 20>;
         };
     };
   # UART example on Raspberry Pi
diff --git a/Documentation/devicetree/bindings/net/realtek,rtl82xx.yaml b/Documentation/devicetree/bindings/net/realtek,rtl82xx.yaml
new file mode 100644
index 000000000000..bb94a2388520
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/realtek,rtl82xx.yaml
@@ -0,0 +1,45 @@
+# SPDX-License-Identifier: GPL-2.0+
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/realtek,rtl82xx.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Realtek RTL82xx PHY
+
+maintainers:
+  - Andrew Lunn <andrew@lunn.ch>
+  - Florian Fainelli <f.fainelli@gmail.com>
+  - Heiner Kallweit <hkallweit1@gmail.com>
+
+description:
+  Bindings for Realtek RTL82xx PHYs
+
+allOf:
+  - $ref: ethernet-phy.yaml#
+
+properties:
+  realtek,clkout-disable:
+    type: boolean
+    description:
+      Disable CLKOUT clock, CLKOUT clock default is enabled after hardware reset.
+
+
+  realtek,aldps-enable:
+    type: boolean
+    description:
+      Enable ALDPS mode, ALDPS mode default is disabled after hardware reset.
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    mdio {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        ethphy1: ethernet-phy@1 {
+                reg = <1>;
+                realtek,clkout-disable;
+                realtek,aldps-enable;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
index 5acddb6171bf..083623c8d718 100644
--- a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
@@ -19,10 +19,12 @@ select:
           - rockchip,rk3128-gmac
           - rockchip,rk3228-gmac
           - rockchip,rk3288-gmac
+          - rockchip,rk3308-gmac
           - rockchip,rk3328-gmac
           - rockchip,rk3366-gmac
           - rockchip,rk3368-gmac
           - rockchip,rk3399-gmac
+          - rockchip,rk3568-gmac
           - rockchip,rv1108-gmac
   required:
     - compatible
@@ -32,17 +34,23 @@ allOf:
 
 properties:
   compatible:
-    items:
-      - enum:
-          - rockchip,px30-gmac
-          - rockchip,rk3128-gmac
-          - rockchip,rk3228-gmac
-          - rockchip,rk3288-gmac
-          - rockchip,rk3328-gmac
-          - rockchip,rk3366-gmac
-          - rockchip,rk3368-gmac
-          - rockchip,rk3399-gmac
-          - rockchip,rv1108-gmac
+    oneOf:
+      - items:
+          - enum:
+              - rockchip,px30-gmac
+              - rockchip,rk3128-gmac
+              - rockchip,rk3228-gmac
+              - rockchip,rk3288-gmac
+              - rockchip,rk3308-gmac
+              - rockchip,rk3328-gmac
+              - rockchip,rk3366-gmac
+              - rockchip,rk3368-gmac
+              - rockchip,rk3399-gmac
+              - rockchip,rv1108-gmac
+      - items:
+          - enum:
+              - rockchip,rk3568-gmac
+          - const: snps,dwmac-4.20a
 
   clocks:
     minItems: 5
diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
index 2edd8bea993e..56f2235f5fb5 100644
--- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
@@ -51,11 +51,20 @@ properties:
         - allwinner,sun8i-r40-emac
         - allwinner,sun8i-v3s-emac
         - allwinner,sun50i-a64-emac
+        - loongson,ls2k-dwmac
+        - loongson,ls7a-dwmac
         - amlogic,meson6-dwmac
         - amlogic,meson8b-dwmac
         - amlogic,meson8m2-dwmac
         - amlogic,meson-gxbb-dwmac
         - amlogic,meson-axg-dwmac
+        - loongson,ls2k-dwmac
+        - loongson,ls7a-dwmac
+        - ingenic,jz4775-mac
+        - ingenic,x1000-mac
+        - ingenic,x1600-mac
+        - ingenic,x1830-mac
+        - ingenic,x2000-mac
         - rockchip,px30-gmac
         - rockchip,rk3128-gmac
         - rockchip,rk3228-gmac
@@ -310,6 +319,11 @@ allOf:
               - allwinner,sun8i-r40-emac
               - allwinner,sun8i-v3s-emac
               - allwinner,sun50i-a64-emac
+              - ingenic,jz4775-mac
+              - ingenic,x1000-mac
+              - ingenic,x1600-mac
+              - ingenic,x1830-mac
+              - ingenic,x2000-mac
               - snps,dwxgmac
               - snps,dwxgmac-2.10
               - st,spear600-gmac
@@ -353,6 +367,13 @@ allOf:
               - allwinner,sun8i-r40-emac
               - allwinner,sun8i-v3s-emac
               - allwinner,sun50i-a64-emac
+              - loongson,ls2k-dwmac
+              - loongson,ls7a-dwmac
+              - ingenic,jz4775-mac
+              - ingenic,x1000-mac
+              - ingenic,x1600-mac
+              - ingenic,x1830-mac
+              - ingenic,x2000-mac
               - snps,dwmac-4.00
               - snps,dwmac-4.10a
               - snps,dwmac-4.20a
diff --git a/Documentation/firmware-guide/acpi/dsd/phy.rst b/Documentation/firmware-guide/acpi/dsd/phy.rst
new file mode 100644
index 000000000000..0d49bad2ea9c
--- /dev/null
+++ b/Documentation/firmware-guide/acpi/dsd/phy.rst
@@ -0,0 +1,140 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================
+MDIO bus and PHYs in ACPI
+=========================
+
+The PHYs on an MDIO bus [1] are probed and registered using
+fwnode_mdiobus_register_phy().
+
+Later, for connecting these PHYs to their respective MACs, the PHYs registered
+on the MDIO bus have to be referenced.
+
+This document introduces two _DSD properties that are to be used
+for connecting PHYs on the MDIO bus [3] to the MAC layer.
+
+These properties are defined in accordance with the "Device
+Properties UUID For _DSD" [2] document and the
+daffd814-6eba-4d8c-8a91-bc9bbf4aa301 UUID must be used in the Device
+Data Descriptors containing them.
+
+phy-handle
+----------
+For each MAC node, a device property "phy-handle" is used to reference
+the PHY that is registered on an MDIO bus. This is mandatory for
+network interfaces that have PHYs connected to MAC via MDIO bus.
+
+During the MDIO bus driver initialization, PHYs on this bus are probed
+using the _ADR object as shown below and are registered on the MDIO bus.
+
+.. code-block:: none
+
+      Scope(\_SB.MDI0)
+      {
+        Device(PHY1) {
+          Name (_ADR, 0x1)
+        } // end of PHY1
+
+        Device(PHY2) {
+          Name (_ADR, 0x2)
+        } // end of PHY2
+      }
+
+Later, during the MAC driver initialization, the registered PHY devices
+have to be retrieved from the MDIO bus. For this, the MAC driver needs
+references to the previously registered PHYs which are provided
+as device object references (e.g. \_SB.MDI0.PHY1).
+
+phy-mode
+--------
+The "phy-mode" _DSD property is used to describe the connection to
+the PHY. The valid values for "phy-mode" are defined in [4].
+
+The following ASL example illustrates the usage of these properties.
+
+DSDT entry for MDIO node
+------------------------
+
+The MDIO bus has an SoC component (MDIO controller) and a platform
+component (PHYs on the MDIO bus).
+
+a) Silicon Component
+This node describes the MDIO controller, MDI0
+---------------------------------------------
+
+.. code-block:: none
+
+	Scope(_SB)
+	{
+	  Device(MDI0) {
+	    Name(_HID, "NXP0006")
+	    Name(_CCA, 1)
+	    Name(_UID, 0)
+	    Name(_CRS, ResourceTemplate() {
+	      Memory32Fixed(ReadWrite, MDI0_BASE, MDI_LEN)
+	      Interrupt(ResourceConsumer, Level, ActiveHigh, Shared)
+	       {
+		 MDI0_IT
+	       }
+	    }) // end of _CRS for MDI0
+	  } // end of MDI0
+	}
+
+b) Platform Component
+The PHY1 and PHY2 nodes represent the PHYs connected to MDIO bus MDI0
+---------------------------------------------------------------------
+
+.. code-block:: none
+
+	Scope(\_SB.MDI0)
+	{
+	  Device(PHY1) {
+	    Name (_ADR, 0x1)
+	  } // end of PHY1
+
+	  Device(PHY2) {
+	    Name (_ADR, 0x2)
+	  } // end of PHY2
+	}
+
+DSDT entries representing MAC nodes
+-----------------------------------
+
+Below are the MAC nodes where PHY nodes are referenced.
+phy-mode and phy-handle are used as explained earlier.
+------------------------------------------------------
+
+.. code-block:: none
+
+	Scope(\_SB.MCE0.PR17)
+	{
+	  Name (_DSD, Package () {
+	     ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+		 Package () {
+		     Package (2) {"phy-mode", "rgmii-id"},
+		     Package (2) {"phy-handle", \_SB.MDI0.PHY1}
+	      }
+	   })
+	}
+
+	Scope(\_SB.MCE0.PR18)
+	{
+	  Name (_DSD, Package () {
+	    ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+		Package () {
+		    Package (2) {"phy-mode", "rgmii-id"},
+		    Package (2) {"phy-handle", \_SB.MDI0.PHY2}}
+	    }
+	  })
+	}
+
+References
+==========
+
+[1] Documentation/networking/phy.rst
+
+[2] https://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf
+
+[3] Documentation/firmware-guide/acpi/DSD-properties-rules.rst
+
+[4] Documentation/devicetree/bindings/net/ethernet-controller.yaml
diff --git a/Documentation/firmware-guide/acpi/index.rst b/Documentation/firmware-guide/acpi/index.rst
index f72b5f1769fb..a99ee402b212 100644
--- a/Documentation/firmware-guide/acpi/index.rst
+++ b/Documentation/firmware-guide/acpi/index.rst
@@ -11,6 +11,7 @@ ACPI Support
    dsd/graph
    dsd/data-node-references
    dsd/leds
+   dsd/phy
    enumeration
    osi
    method-customizing
diff --git a/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst b/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst
index 70643b58de05..4118384cf8eb 100644
--- a/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst
+++ b/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst
@@ -27,34 +27,136 @@ these MAP frames and send them to appropriate PDN's.
 2. Packet format
 ================
 
-a. MAP packet (data / control)
+a. MAP packet v1 (data / control)
 
-MAP header has the same endianness of the IP packet.
+MAP header fields are in big endian format.
 
 Packet format::
 
-  Bit             0             1           2-7      8 - 15           16 - 31
+  Bit             0             1           2-7      8-15           16-31
   Function   Command / Data   Reserved     Pad   Multiplexer ID    Payload length
-  Bit            32 - x
-  Function     Raw  Bytes
+
+  Bit            32-x
+  Function      Raw bytes
 
 Command (1)/ Data (0) bit value is to indicate if the packet is a MAP command
-or data packet. Control packet is used for transport level flow control. Data
+or data packet. Command packet is used for transport level flow control. Data
 packets are standard IP packets.
 
-Reserved bits are usually zeroed out and to be ignored by receiver.
+Reserved bits must be zero when sent and ignored when received.
 
-Padding is number of bytes to be added for 4 byte alignment if required by
-hardware.
+Padding is the number of bytes to be appended to the payload to
+ensure 4 byte alignment.
 
 Multiplexer ID is to indicate the PDN on which data has to be sent.
 
 Payload length includes the padding length but does not include MAP header
 length.
 
-b. MAP packet (command specific)::
+b. Map packet v4 (data / control)
+
+MAP header fields are in big endian format.
+
+Packet format::
+
+  Bit             0             1           2-7      8-15           16-31
+  Function   Command / Data   Reserved     Pad   Multiplexer ID    Payload length
+
+  Bit            32-(x-33)      (x-32)-x
+  Function      Raw bytes      Checksum offload header
+
+Command (1)/ Data (0) bit value is to indicate if the packet is a MAP command
+or data packet. Command packet is used for transport level flow control. Data
+packets are standard IP packets.
+
+Reserved bits must be zero when sent and ignored when received.
+
+Padding is the number of bytes to be appended to the payload to
+ensure 4 byte alignment.
+
+Multiplexer ID is to indicate the PDN on which data has to be sent.
+
+Payload length includes the padding length but does not include MAP header
+length.
+
+Checksum offload header, has the information about the checksum processing done
+by the hardware.Checksum offload header fields are in big endian format.
+
+Packet format::
+
+  Bit             0-14        15              16-31
+  Function      Reserved   Valid     Checksum start offset
+
+  Bit                31-47                    48-64
+  Function      Checksum length           Checksum value
+
+Reserved bits must be zero when sent and ignored when received.
+
+Valid bit indicates whether the partial checksum is calculated and is valid.
+Set to 1, if its is valid. Set to 0 otherwise.
+
+Padding is the number of bytes to be appended to the payload to
+ensure 4 byte alignment.
+
+Checksum start offset, Indicates the offset in bytes from the beginning of the
+IP header, from which modem computed checksum.
+
+Checksum length is the Length in bytes starting from CKSUM_START_OFFSET,
+over which checksum is computed.
+
+Checksum value, indicates the checksum computed.
+
+c. MAP packet v5 (data / control)
+
+MAP header fields are in big endian format.
+
+Packet format::
+
+  Bit             0             1         2-7      8-15           16-31
+  Function   Command / Data  Next header  Pad   Multiplexer ID   Payload length
+
+  Bit            32-x
+  Function      Raw bytes
+
+Command (1)/ Data (0) bit value is to indicate if the packet is a MAP command
+or data packet. Command packet is used for transport level flow control. Data
+packets are standard IP packets.
+
+Next header is used to indicate the presence of another header, currently is
+limited to checksum header.
+
+Padding is the number of bytes to be appended to the payload to
+ensure 4 byte alignment.
+
+Multiplexer ID is to indicate the PDN on which data has to be sent.
+
+Payload length includes the padding length but does not include MAP header
+length.
+
+d. Checksum offload header v5
+
+Checksum offload header fields are in big endian format.
+
+  Bit            0 - 6          7               8-15              16-31
+  Function     Header Type    Next Header     Checksum Valid    Reserved
+
+Header Type is to indicate the type of header, this usually is set to CHECKSUM
+
+Header types
+= ==========================================
+0 Reserved
+1 Reserved
+2 checksum header
+
+Checksum Valid is to indicate whether the header checksum is valid. Value of 1
+implies that checksum is calculated on this packet and is valid, value of 0
+indicates that the calculated packet checksum is invalid.
+
+Reserved bits must be zero when sent and ignored when received.
+
+e. MAP packet v1/v5 (command specific)::
 
-    Bit             0             1           2-7      8 - 15           16 - 31
+    Bit             0             1         2-7      8 - 15           16 - 31
     Function   Command         Reserved     Pad   Multiplexer ID    Payload length
     Bit          32 - 39        40 - 45    46 - 47       48 - 63
     Function   Command name    Reserved   Command Type   Reserved
@@ -74,7 +176,7 @@ Command types
 3 is for error during processing of commands
 = ==========================================
 
-c. Aggregation
+f. Aggregation
 
 Aggregation is multiple MAP packets (can be data or command) delivered to
 rmnet in a single linear skb. rmnet will process the individual
diff --git a/Documentation/networking/device_drivers/ethernet/amazon/ena.rst b/Documentation/networking/device_drivers/ethernet/amazon/ena.rst
index f8c6469f2bd2..01b2a69b0cb0 100644
--- a/Documentation/networking/device_drivers/ethernet/amazon/ena.rst
+++ b/Documentation/networking/device_drivers/ethernet/amazon/ena.rst
@@ -11,12 +11,12 @@ ENA is a networking interface designed to make good use of modern CPU
 features and system architectures.
 
 The ENA device exposes a lightweight management interface with a
-minimal set of memory mapped registers and extendable command set
+minimal set of memory mapped registers and extendible command set
 through an Admin Queue.
 
 The driver supports a range of ENA devices, is link-speed independent
-(i.e., the same driver is used for 10GbE, 25GbE, 40GbE, etc.), and has
-a negotiated and extendable feature set.
+(i.e., the same driver is used for 10GbE, 25GbE, 40GbE, etc), and has
+a negotiated and extendible feature set.
 
 Some ENA devices support SR-IOV. This driver is used for both the
 SR-IOV Physical Function (PF) and Virtual Function (VF) devices.
@@ -27,9 +27,9 @@ is advertised by the device via the Admin Queue), a dedicated MSI-X
 interrupt vector per Tx/Rx queue pair, adaptive interrupt moderation,
 and CPU cacheline optimized data placement.
 
-The ENA driver supports industry standard TCP/IP offload features such
-as checksum offload and TCP transmit segmentation offload (TSO).
-Receive-side scaling (RSS) is supported for multi-core scaling.
+The ENA driver supports industry standard TCP/IP offload features such as
+checksum offload. Receive-side scaling (RSS) is supported for multi-core
+scaling.
 
 The ENA driver and its corresponding devices implement health
 monitoring mechanisms such as watchdog, enabling the device and driver
@@ -38,22 +38,20 @@ debug logs.
 
 Some of the ENA devices support a working mode called Low-latency
 Queue (LLQ), which saves several more microseconds.
-
 ENA Source Code Directory Structure
 ===================================
 
 =================   ======================================================
 ena_com.[ch]        Management communication layer. This layer is
-		    responsible for the handling all the management
-		    (admin) communication between the device and the
-		    driver.
+                    responsible for the handling all the management
+                    (admin) communication between the device and the
+                    driver.
 ena_eth_com.[ch]    Tx/Rx data path.
 ena_admin_defs.h    Definition of ENA management interface.
 ena_eth_io_defs.h   Definition of ENA data path interface.
 ena_common_defs.h   Common definitions for ena_com layer.
 ena_regs_defs.h     Definition of ENA PCI memory-mapped (MMIO) registers.
 ena_netdev.[ch]     Main Linux kernel driver.
-ena_syfsfs.[ch]     Sysfs files.
 ena_ethtool.c       ethtool callbacks.
 ena_pci_id_tbl.h    Supported device IDs.
 =================   ======================================================
@@ -69,7 +67,7 @@ ENA management interface is exposed by means of:
 - Asynchronous Event Notification Queue (AENQ)
 
 ENA device MMIO Registers are accessed only during driver
-initialization and are not involved in further normal device
+initialization and are not used during further normal device
 operation.
 
 AQ is used for submitting management commands, and the
@@ -100,28 +98,27 @@ group may have multiple syndromes, as shown below
 
 The events are:
 
-	====================	===============
-	Group			Syndrome
-	====================	===============
-	Link state change	**X**
-	Fatal error		**X**
-	Notification		Suspend traffic
-	Notification		Resume traffic
-	Keep-Alive		**X**
-	====================	===============
+====================    ===============
+Group                   Syndrome
+====================    ===============
+Link state change       **X**
+Fatal error             **X**
+Notification            Suspend traffic
+Notification            Resume traffic
+Keep-Alive              **X**
+====================    ===============
 
 ACQ and AENQ share the same MSI-X vector.
 
-Keep-Alive is a special mechanism that allows monitoring of the
-device's health. The driver maintains a watchdog (WD) handler which,
-if fired, logs the current state and statistics then resets and
-restarts the ENA device and driver. A Keep-Alive event is delivered by
-the device every second. The driver re-arms the WD upon reception of a
-Keep-Alive event. A missed Keep-Alive event causes the WD handler to
-fire.
+Keep-Alive is a special mechanism that allows monitoring the device's health.
+A Keep-Alive event is delivered by the device every second.
+The driver maintains a watchdog (WD) handler which logs the current state and
+statistics. If the keep-alive events aren't delivered as expected the WD resets
+the device and the driver.
 
 Data Path Interface
 ===================
+
 I/O operations are based on Tx and Rx Submission Queues (Tx SQ and Rx
 SQ correspondingly). Each SQ has a completion queue (CQ) associated
 with it.
@@ -131,26 +128,24 @@ physical memory.
 
 The ENA driver supports two Queue Operation modes for Tx SQs:
 
-- Regular mode
+- **Regular mode:**
+  In this mode the Tx SQs reside in the host's memory. The ENA
+  device fetches the ENA Tx descriptors and packet data from host
+  memory.
 
-  * In this mode the Tx SQs reside in the host's memory. The ENA
-    device fetches the ENA Tx descriptors and packet data from host
-    memory.
+- **Low Latency Queue (LLQ) mode or "push-mode":**
+  In this mode the driver pushes the transmit descriptors and the
+  first 128 bytes of the packet directly to the ENA device memory
+  space. The rest of the packet payload is fetched by the
+  device. For this operation mode, the driver uses a dedicated PCI
+  device memory BAR, which is mapped with write-combine capability.
 
-- Low Latency Queue (LLQ) mode or "push-mode".
-
-  * In this mode the driver pushes the transmit descriptors and the
-    first 128 bytes of the packet directly to the ENA device memory
-    space. The rest of the packet payload is fetched by the
-    device. For this operation mode, the driver uses a dedicated PCI
-    device memory BAR, which is mapped with write-combine capability.
+  **Note that** not all ENA devices support LLQ, and this feature is negotiated
+  with the device upon initialization. If the ENA device does not
+  support LLQ mode, the driver falls back to the regular mode.
 
 The Rx SQs support only the regular mode.
 
-Note: Not all ENA devices support LLQ, and this feature is negotiated
-      with the device upon initialization. If the ENA device does not
-      support LLQ mode, the driver falls back to the regular mode.
-
 The driver supports multi-queue for both Tx and Rx. This has various
 benefits:
 
@@ -165,6 +160,7 @@ benefits:
 
 Interrupt Modes
 ===============
+
 The driver assigns a single MSI-X vector per queue pair (for both Tx
 and Rx directions). The driver assigns an additional dedicated MSI-X vector
 for management (for ACQ and AENQ).
@@ -190,20 +186,21 @@ unmasked by the driver after NAPI processing is complete.
 
 Interrupt Moderation
 ====================
+
 ENA driver and device can operate in conventional or adaptive interrupt
 moderation mode.
 
-In conventional mode the driver instructs device to postpone interrupt
+**In conventional mode** the driver instructs device to postpone interrupt
 posting according to static interrupt delay value. The interrupt delay
-value can be configured through ethtool(8). The following ethtool
-parameters are supported by the driver: tx-usecs, rx-usecs
+value can be configured through `ethtool(8)`. The following `ethtool`
+parameters are supported by the driver: ``tx-usecs``, ``rx-usecs``
 
-In adaptive interrupt moderation mode the interrupt delay value is
+**In adaptive interrupt** moderation mode the interrupt delay value is
 updated by the driver dynamically and adjusted every NAPI cycle
 according to the traffic nature.
 
-Adaptive coalescing can be switched on/off through ethtool(8)
-adaptive_rx on|off parameter.
+Adaptive coalescing can be switched on/off through `ethtool(8)`'s
+:code:`adaptive_rx on|off` parameter.
 
 More information about Adaptive Interrupt Moderation (DIM) can be found in
 Documentation/networking/net_dim.rst
@@ -214,17 +211,10 @@ The rx_copybreak is initialized by default to ENA_DEFAULT_RX_COPYBREAK
 and can be configured by the ETHTOOL_STUNABLE command of the
 SIOCETHTOOL ioctl.
 
-SKB
-===
-The driver-allocated SKB for frames received from Rx handling using
-NAPI context. The allocation method depends on the size of the packet.
-If the frame length is larger than rx_copybreak, napi_get_frags()
-is used, otherwise netdev_alloc_skb_ip_align() is used, the buffer
-content is copied (by CPU) to the SKB, and the buffer is recycled.
-
 Statistics
 ==========
-The user can obtain ENA device and driver statistics using ethtool.
+
+The user can obtain ENA device and driver statistics using `ethtool`.
 The driver can collect regular or extended statistics (including
 per-queue stats) from the device.
 
@@ -232,22 +222,23 @@ In addition the driver logs the stats to syslog upon device reset.
 
 MTU
 ===
+
 The driver supports an arbitrarily large MTU with a maximum that is
 negotiated with the device. The driver configures MTU using the
 SetFeature command (ENA_ADMIN_MTU property). The user can change MTU
-via ip(8) and similar legacy tools.
+via `ip(8)` and similar legacy tools.
 
 Stateless Offloads
 ==================
+
 The ENA driver supports:
 
-- TSO over IPv4/IPv6
-- TSO with ECN
 - IPv4 header checksum offload
 - TCP/UDP over IPv4/IPv6 checksum offloads
 
 RSS
 ===
+
 - The ENA device supports RSS that allows flexible Rx traffic
   steering.
 - Toeplitz and CRC32 hash functions are supported.
@@ -260,41 +251,42 @@ RSS
   function delivered in the Rx CQ descriptor is set in the received
   SKB.
 - The user can provide a hash key, hash function, and configure the
-  indirection table through ethtool(8).
+  indirection table through `ethtool(8)`.
 
 DATA PATH
 =========
+
 Tx
 --
 
-ena_start_xmit() is called by the stack. This function does the following:
+:code:`ena_start_xmit()` is called by the stack. This function does the following:
 
-- Maps data buffers (skb->data and frags).
-- Populates ena_buf for the push buffer (if the driver and device are
-  in push mode.)
+- Maps data buffers (``skb->data`` and frags).
+- Populates ``ena_buf`` for the push buffer (if the driver and device are
+  in push mode).
 - Prepares ENA bufs for the remaining frags.
-- Allocates a new request ID from the empty req_id ring. The request
+- Allocates a new request ID from the empty ``req_id`` ring. The request
   ID is the index of the packet in the Tx info. This is used for
-  out-of-order TX completions.
+  out-of-order Tx completions.
 - Adds the packet to the proper place in the Tx ring.
-- Calls ena_com_prepare_tx(), an ENA communication layer that converts
-  the ena_bufs to ENA descriptors (and adds meta ENA descriptors as
-  needed.)
+- Calls :code:`ena_com_prepare_tx()`, an ENA communication layer that converts
+  the ``ena_bufs`` to ENA descriptors (and adds meta ENA descriptors as
+  needed).
 
   * This function also copies the ENA descriptors and the push buffer
-    to the Device memory space (if in push mode.)
+    to the Device memory space (if in push mode).
 
-- Writes doorbell to the ENA device.
+- Writes a doorbell to the ENA device.
 - When the ENA device finishes sending the packet, a completion
   interrupt is raised.
 - The interrupt handler schedules NAPI.
-- The ena_clean_tx_irq() function is called. This function handles the
+- The :code:`ena_clean_tx_irq()` function is called. This function handles the
   completion descriptors generated by the ENA, with a single
   completion descriptor per completed packet.
 
-  * req_id is retrieved from the completion descriptor. The tx_info of
-    the packet is retrieved via the req_id. The data buffers are
-    unmapped and req_id is returned to the empty req_id ring.
+  * ``req_id`` is retrieved from the completion descriptor. The ``tx_info`` of
+    the packet is retrieved via the ``req_id``. The data buffers are
+    unmapped and ``req_id`` is returned to the empty ``req_id`` ring.
   * The function stops when the completion descriptors are completed or
     the budget is reached.
 
@@ -303,12 +295,11 @@ Rx
 
 - When a packet is received from the ENA device.
 - The interrupt handler schedules NAPI.
-- The ena_clean_rx_irq() function is called. This function calls
-  ena_rx_pkt(), an ENA communication layer function, which returns the
-  number of descriptors used for a new unhandled packet, and zero if
+- The :code:`ena_clean_rx_irq()` function is called. This function calls
+  :code:`ena_com_rx_pkt()`, an ENA communication layer function, which returns the
+  number of descriptors used for a new packet, and zero if
   no new packet is found.
-- Then it calls the ena_clean_rx_irq() function.
-- ena_eth_rx_skb() checks packet length:
+- :code:`ena_rx_skb()` checks packet length:
 
   * If the packet is small (len < rx_copybreak), the driver allocates
     a SKB for the new packet, and copies the packet payload into the
@@ -317,9 +308,10 @@ Rx
     - In this way the original data buffer is not passed to the stack
       and is reused for future Rx packets.
 
-  * Otherwise the function unmaps the Rx buffer, then allocates the
-    new SKB structure and hooks the Rx buffer to the SKB frags.
+  * Otherwise the function unmaps the Rx buffer, sets the first
+    descriptor as `skb`'s linear part and the other descriptors as the
+    `skb`'s frags.
 
 - The new SKB is updated with the necessary information (protocol,
-  checksum hw verify result, etc.), and then passed to the network
-  stack, using the NAPI interface function napi_gro_receive().
+  checksum hw verify result, etc), and then passed to the network
+  stack, using the NAPI interface function :code:`napi_gro_receive()`.
diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
index 936a10f1942c..ef8cb62e82a1 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
@@ -12,6 +12,7 @@ Contents
 - `Enabling the driver and kconfig options`_
 - `Devlink info`_
 - `Devlink parameters`_
+- `Bridge offload`_
 - `mlx5 subfunction`_
 - `mlx5 function attributes`_
 - `Devlink health reporters`_
@@ -217,6 +218,37 @@ users try to enable them.
 
     $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev
 
+Bridge offload
+==============
+The mlx5 driver implements support for offloading bridge rules when in switchdev
+mode. Linux bridge FDBs are automatically offloaded when mlx5 switchdev
+representor is attached to bridge.
+
+- Change device to switchdev mode::
+
+    $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev
+
+- Attach mlx5 switchdev representor 'enp8s0f0' to bridge netdev 'bridge1'::
+
+    $ ip link set enp8s0f0 master bridge1
+
+VLANs
+-----
+Following bridge VLAN functions are supported by mlx5:
+
+- VLAN filtering (including multiple VLANs per port)::
+
+    $ ip link set bridge1 type bridge vlan_filtering 1
+    $ bridge vlan add dev enp8s0f0 vid 2-3
+
+- VLAN push on bridge ingress::
+
+    $ bridge vlan add dev enp8s0f0 vid 3 pvid
+
+- VLAN pop on bridge egress::
+
+    $ bridge vlan add dev enp8s0f0 vid 3 untagged
+
 mlx5 subfunction
 ================
 mlx5 supports subfunction management using devlink port (see :ref:`Documentation/networking/devlink/devlink-port.rst <devlink_port>`) interface.
@@ -568,3 +600,59 @@ tc and eswitch offloads tracepoints:
     $ cat /sys/kernel/debug/tracing/trace
     ...
     kworker/u48:7-2221  [009] ...1  1475.387435: mlx5e_rep_neigh_update: netdev: ens1f0 MAC: 24:8a:07:9a:17:9a IPv4: 1.1.1.10 IPv6: ::ffff:1.1.1.10 neigh_connected=1
+
+Bridge offloads tracepoints:
+
+- mlx5_esw_bridge_fdb_entry_init: trace bridge FDB entry offloaded to mlx5::
+
+    $ echo mlx5:mlx5_esw_bridge_fdb_entry_init >> set_event
+    $ cat /sys/kernel/debug/tracing/trace
+    ...
+    kworker/u20:9-2217    [003] ...1   318.582243: mlx5_esw_bridge_fdb_entry_init: net_device=enp8s0f0_0 addr=e4:fd:05:08:00:02 vid=0 flags=0 used=0
+
+- mlx5_esw_bridge_fdb_entry_cleanup: trace bridge FDB entry deleted from mlx5::
+
+    $ echo mlx5:mlx5_esw_bridge_fdb_entry_cleanup >> set_event
+    $ cat /sys/kernel/debug/tracing/trace
+    ...
+    ip-2581    [005] ...1   318.629871: mlx5_esw_bridge_fdb_entry_cleanup: net_device=enp8s0f0_1 addr=e4:fd:05:08:00:03 vid=0 flags=0 used=16
+
+- mlx5_esw_bridge_fdb_entry_refresh: trace bridge FDB entry offload refreshed in
+  mlx5::
+
+    $ echo mlx5:mlx5_esw_bridge_fdb_entry_refresh >> set_event
+    $ cat /sys/kernel/debug/tracing/trace
+    ...
+    kworker/u20:8-3849    [003] ...1       466716: mlx5_esw_bridge_fdb_entry_refresh: net_device=enp8s0f0_0 addr=e4:fd:05:08:00:02 vid=3 flags=0 used=0
+
+- mlx5_esw_bridge_vlan_create: trace bridge VLAN object add on mlx5
+  representor::
+
+    $ echo mlx5:mlx5_esw_bridge_vlan_create >> set_event
+    $ cat /sys/kernel/debug/tracing/trace
+    ...
+    ip-2560    [007] ...1   318.460258: mlx5_esw_bridge_vlan_create: vid=1 flags=6
+
+- mlx5_esw_bridge_vlan_cleanup: trace bridge VLAN object delete from mlx5
+  representor::
+
+    $ echo mlx5:mlx5_esw_bridge_vlan_cleanup >> set_event
+    $ cat /sys/kernel/debug/tracing/trace
+    ...
+    bridge-2582    [007] ...1   318.653496: mlx5_esw_bridge_vlan_cleanup: vid=2 flags=8
+
+- mlx5_esw_bridge_vport_init: trace mlx5 vport assigned with bridge upper
+  device::
+
+    $ echo mlx5:mlx5_esw_bridge_vport_init >> set_event
+    $ cat /sys/kernel/debug/tracing/trace
+    ...
+    ip-2560    [007] ...1   318.458915: mlx5_esw_bridge_vport_init: vport_num=1
+
+- mlx5_esw_bridge_vport_cleanup: trace mlx5 vport removed from bridge upper
+  device::
+
+    $ echo mlx5:mlx5_esw_bridge_vport_cleanup >> set_event
+    $ cat /sys/kernel/debug/tracing/trace
+    ...
+    ip-5387    [000] ...1       573713: mlx5_esw_bridge_vport_cleanup: vport_num=1
diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst
index d8279de7bf25..3a5a1d46e77e 100644
--- a/Documentation/networking/device_drivers/index.rst
+++ b/Documentation/networking/device_drivers/index.rst
@@ -18,6 +18,7 @@ Contents:
    qlogic/index
    wan/index
    wifi/index
+   wwan/index
 
 .. only::  subproject and html
 
diff --git a/Documentation/networking/device_drivers/wwan/index.rst b/Documentation/networking/device_drivers/wwan/index.rst
new file mode 100644
index 000000000000..1cb8c7371401
--- /dev/null
+++ b/Documentation/networking/device_drivers/wwan/index.rst
@@ -0,0 +1,18 @@
+.. SPDX-License-Identifier: GPL-2.0-only
+
+WWAN Device Drivers
+===================
+
+Contents:
+
+.. toctree::
+   :maxdepth: 2
+
+   iosm
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`
diff --git a/Documentation/networking/device_drivers/wwan/iosm.rst b/Documentation/networking/device_drivers/wwan/iosm.rst
new file mode 100644
index 000000000000..aceb0223eb46
--- /dev/null
+++ b/Documentation/networking/device_drivers/wwan/iosm.rst
@@ -0,0 +1,96 @@
+.. SPDX-License-Identifier: GPL-2.0-only
+
+.. Copyright (C) 2020-21 Intel Corporation
+
+.. _iosm_driver_doc:
+
+===========================================
+IOSM Driver for Intel M.2 PCIe based Modems
+===========================================
+The IOSM (IPC over Shared Memory) driver is a WWAN PCIe host driver developed
+for linux or chrome platform for data exchange over PCIe interface between
+Host platform & Intel M.2 Modem. The driver exposes interface conforming to the
+MBIM protocol [1]. Any front end application ( eg: Modem Manager) could easily
+manage the MBIM interface to enable data communication towards WWAN.
+
+Basic usage
+===========
+MBIM functions are inactive when unmanaged. The IOSM driver only provides a
+userspace interface MBIM "WWAN PORT" representing MBIM control channel and does
+not play any role in managing the functionality. It is the job of a userspace
+application to detect port enumeration and enable MBIM functionality.
+
+Examples of few such userspace application are:
+- mbimcli (included with the libmbim [2] library), and
+- Modem Manager [3]
+
+Management Applications to carry out below required actions for establishing
+MBIM IP session:
+- open the MBIM control channel
+- configure network connection settings
+- connect to network
+- configure IP network interface
+
+Management application development
+==================================
+The driver and userspace interfaces are described below. The MBIM protocol is
+described in [1] Mobile Broadband Interface Model v1.0 Errata-1.
+
+MBIM control channel userspace ABI
+----------------------------------
+
+/dev/wwan0mbim0 character device
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+The driver exposes an MBIM interface to the MBIM function by implementing
+MBIM WWAN Port. The userspace end of the control channel pipe is a
+/dev/wwan0mbim0 character device. Application shall use this interface for
+MBIM protocol communication.
+
+Fragmentation
+~~~~~~~~~~~~~
+The userspace application is responsible for all control message fragmentation
+and defragmentation as per MBIM specification.
+
+/dev/wwan0mbim0 write()
+~~~~~~~~~~~~~~~~~~~~~~~
+The MBIM control messages from the management application must not exceed the
+negotiated control message size.
+
+/dev/wwan0mbim0 read()
+~~~~~~~~~~~~~~~~~~~~~~
+The management application must accept control messages of up the negotiated
+control message size.
+
+MBIM data channel userspace ABI
+-------------------------------
+
+wwan0-X network device
+~~~~~~~~~~~~~~~~~~~~~~
+The IOSM driver exposes IP link interface "wwan0-X" of type "wwan" for IP
+traffic. Iproute network utility is used for creating "wwan0-X" network
+interface and for associating it with MBIM IP session. The Driver supports
+upto 8 IP sessions for simultaneous IP communication.
+
+The userspace management application is responsible for creating new IP link
+prior to establishing MBIM IP session where the SessionId is greater than 0.
+
+For example, creating new IP link for a MBIM IP session with SessionId 1:
+
+  ip link add dev wwan0-1 parentdev-name wwan0 type wwan linkid 1
+
+The driver will automatically map the "wwan0-1" network device to MBIM IP
+session 1.
+
+References
+==========
+[1] "MBIM (Mobile Broadband Interface Model) Errata-1"
+      - https://www.usb.org/document-library/
+
+[2] libmbim - "a glib-based library for talking to WWAN modems and
+      devices which speak the Mobile Interface Broadband Model (MBIM)
+      protocol"
+      - http://www.freedesktop.org/wiki/Software/libmbim/
+
+[3] Modem Manager - "a DBus-activated daemon which controls mobile
+      broadband (2G/3G/4G) devices and connections"
+      - http://www.freedesktop.org/wiki/Software/ModemManager/
diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst
index ab790e7980b8..7627b1da01f2 100644
--- a/Documentation/networking/devlink/devlink-port.rst
+++ b/Documentation/networking/devlink/devlink-port.rst
@@ -164,6 +164,41 @@ device to instantiate the subfunction device on particular PCI function.
 A subfunction device is created on the :ref:`Documentation/driver-api/auxiliary_bus.rst <auxiliary_bus>`.
 At this point a matching subfunction driver binds to the subfunction's auxiliary device.
 
+Rate object management
+======================
+
+Devlink provides API to manage tx rates of single devlink port or a group.
+This is done through rate objects, which can be one of the two types:
+
+``leaf``
+  Represents a single devlink port; created/destroyed by the driver. Since leaf
+  have 1to1 mapping to its devlink port, in user space it is referred as
+  ``pci/<bus_addr>/<port_index>``;
+
+``node``
+  Represents a group of rate objects (leafs and/or nodes); created/deleted by
+  request from the userspace; initially empty (no rate objects added). In
+  userspace it is referred as ``pci/<bus_addr>/<node_name>``, where
+  ``node_name`` can be any identifier, except decimal number, to avoid
+  collisions with leafs.
+
+API allows to configure following rate object's parameters:
+
+``tx_share``
+  Minimum TX rate value shared among all other rate objects, or rate objects
+  that parts of the parent group, if it is a part of the same group.
+
+``tx_max``
+  Maximum TX rate value.
+
+``parent``
+  Parent node name. Parent node rate limits are considered as additional limits
+  to all node children limits. ``tx_max`` is an upper limit for children.
+  ``tx_share`` is a total bandwidth distributed among children.
+
+Driver implementations are allowed to support both or either rate object types
+and setting methods of their parameters.
+
 Terms and Definitions
 =====================
 
diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst
index 935b6397e8cf..ef8928c355df 100644
--- a/Documentation/networking/devlink/devlink-trap.rst
+++ b/Documentation/networking/devlink/devlink-trap.rst
@@ -497,6 +497,7 @@ drivers:
 
   * :doc:`netdevsim`
   * :doc:`mlxsw`
+  * :doc:`prestera`
 
 .. _Generic-Packet-Trap-Groups:
 
diff --git a/Documentation/networking/devlink/index.rst b/Documentation/networking/devlink/index.rst
index 8428a1220723..b3b9e0692088 100644
--- a/Documentation/networking/devlink/index.rst
+++ b/Documentation/networking/devlink/index.rst
@@ -46,3 +46,4 @@ parameters, info versions, and other features it supports.
    qed
    ti-cpsw-switch
    am65-nuss-cpsw-switch
+   prestera
diff --git a/Documentation/networking/devlink/netdevsim.rst b/Documentation/networking/devlink/netdevsim.rst
index 02c2d20dc673..8a292fb5aaea 100644
--- a/Documentation/networking/devlink/netdevsim.rst
+++ b/Documentation/networking/devlink/netdevsim.rst
@@ -57,6 +57,32 @@ entries, FIB rule entries and nexthops that the driver will allow.
     $ devlink resource set netdevsim/netdevsim0 path /nexthops size 16
     $ devlink dev reload netdevsim/netdevsim0
 
+Rate objects
+============
+
+The ``netdevsim`` driver supports rate objects management, which includes:
+
+- registerging/unregistering leaf rate objects per VF devlink port;
+- creation/deletion node rate objects;
+- setting tx_share and tx_max rate values for any rate object type;
+- setting parent node for any rate object type.
+
+Rate nodes and it's parameters are exposed in ``netdevsim`` debugfs in RO mode.
+For example created rate node with name ``some_group``:
+
+.. code:: shell
+
+    $ ls /sys/kernel/debug/netdevsim/netdevsim0/rate_groups/some_group
+    rate_parent  tx_max  tx_share
+
+Same parameters are exposed for leaf objects in corresponding ports directories.
+For ex.:
+
+.. code:: shell
+
+    $ ls /sys/kernel/debug/netdevsim/netdevsim0/ports/1
+    dev  ethtool  rate_parent  tx_max  tx_share
+
 Driver-specific Traps
 =====================
 
diff --git a/Documentation/networking/devlink/prestera.rst b/Documentation/networking/devlink/prestera.rst
new file mode 100644
index 000000000000..49409d1d3081
--- /dev/null
+++ b/Documentation/networking/devlink/prestera.rst
@@ -0,0 +1,141 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+========================
+prestera devlink support
+========================
+
+This document describes the devlink features implemented by the ``prestera``
+device driver.
+
+Driver-specific Traps
+=====================
+
+.. list-table:: List of Driver-specific Traps Registered by ``prestera``
+   :widths: 5 5 90
+
+   * - Name
+     - Type
+     - Description
+.. list-table:: List of Driver-specific Traps Registered by ``prestera``
+   :widths: 5 5 90
+
+   * - Name
+     - Type
+     - Description
+   * - ``arp_bc``
+     - ``trap``
+     - Traps ARP broadcast packets (both requests/responses)
+   * - ``is_is``
+     - ``trap``
+     - Traps IS-IS packets
+   * - ``ospf``
+     - ``trap``
+     - Traps OSPF packets
+   * - ``ip_bc_mac``
+     - ``trap``
+     - Traps IPv4 packets with broadcast DA Mac address
+   * - ``stp``
+     - ``trap``
+     - Traps STP BPDU
+   * - ``lacp``
+     - ``trap``
+     - Traps LACP packets
+   * - ``lldp``
+     - ``trap``
+     - Traps LLDP packets
+   * - ``router_mc``
+     - ``trap``
+     - Traps multicast packets
+   * - ``vrrp``
+     - ``trap``
+     - Traps VRRP packets
+   * - ``dhcp``
+     - ``trap``
+     - Traps DHCP packets
+   * - ``mtu_error``
+     - ``trap``
+     - Traps (exception) packets that exceeded port's MTU
+   * - ``mac_to_me``
+     - ``trap``
+     -  Traps packets with switch-port's DA Mac address
+   * - ``ttl_error``
+     - ``trap``
+     - Traps (exception) IPv4 packets whose TTL exceeded
+   * - ``ipv4_options``
+     - ``trap``
+     - Traps (exception) packets due to the malformed IPV4 header options
+   * - ``ip_default_route``
+     - ``trap``
+     - Traps packets that have no specific IP interface (IP to me) and no forwarding prefix
+   * - ``local_route``
+     - ``trap``
+     - Traps packets that have been send to one of switch IP interfaces addresses
+   * - ``ipv4_icmp_redirect``
+     - ``trap``
+     - Traps (exception) IPV4 ICMP redirect packets
+   * - ``arp_response``
+     - ``trap``
+     - Traps ARP replies packets that have switch-port's DA Mac address
+   * - ``acl_code_0``
+     - ``trap``
+     - Traps packets that have ACL priority set to 0 (tc pref 0)
+   * - ``acl_code_1``
+     - ``trap``
+     - Traps packets that have ACL priority set to 1 (tc pref 1)
+   * - ``acl_code_2``
+     - ``trap``
+     - Traps packets that have ACL priority set to 2 (tc pref 2)
+   * - ``acl_code_3``
+     - ``trap``
+     - Traps packets that have ACL priority set to 3 (tc pref 3)
+   * - ``acl_code_4``
+     - ``trap``
+     - Traps packets that have ACL priority set to 4 (tc pref 4)
+   * - ``acl_code_5``
+     - ``trap``
+     - Traps packets that have ACL priority set to 5 (tc pref 5)
+   * - ``acl_code_6``
+     - ``trap``
+     - Traps packets that have ACL priority set to 6 (tc pref 6)
+   * - ``acl_code_7``
+     - ``trap``
+     - Traps packets that have ACL priority set to 7 (tc pref 7)
+   * - ``ipv4_bgp``
+     - ``trap``
+     - Traps IPv4 BGP packets
+   * - ``ssh``
+     - ``trap``
+     - Traps SSH packets
+   * - ``telnet``
+     - ``trap``
+     - Traps Telnet packets
+   * - ``icmp``
+     - ``trap``
+     - Traps ICMP packets
+   * - ``rxdma_drop``
+     - ``drop``
+     - Drops packets (RxDMA) due to the lack of ingress buffers etc.
+   * - ``port_no_vlan``
+     - ``drop``
+     - Drops packets due to faulty-configured network or due to internal bug (config issue).
+   * - ``local_port``
+     - ``drop``
+     - Drops packets whose decision (FDB entry) is to bridge packet back to the incoming port/trunk.
+   * - ``invalid_sa``
+     - ``drop``
+     - Drops packets with multicast source MAC address.
+   * - ``illegal_ip_addr``
+     - ``drop``
+     - Drops packets with illegal SIP/DIP multicast/unicast addresses.
+   * - ``illegal_ipv4_hdr``
+     - ``drop``
+     - Drops packets with illegal IPV4 header.
+   * - ``ip_uc_dip_da_mismatch``
+     - ``drop``
+     - Drops packets with destination MAC being unicast, but destination IP address being multicast.
+   * - ``ip_sip_is_zero``
+     - ``drop``
+     - Drops packets with zero (0) IPV4 source address.
+   * - ``met_red``
+     - ``drop``
+     - Drops non-conforming packets (dropped by Ingress policer, metering drop), e.g. packet rate exceeded configured bandwith.
diff --git a/Documentation/networking/dsa/dsa.rst b/Documentation/networking/dsa/dsa.rst
index 8688009514cc..20baacf2bc5c 100644
--- a/Documentation/networking/dsa/dsa.rst
+++ b/Documentation/networking/dsa/dsa.rst
@@ -93,14 +93,15 @@ A tagging protocol may tag all packets with switch tags of the same length, or
 the tag length might vary (for example packets with PTP timestamps might
 require an extended switch tag, or there might be one tag length on TX and a
 different one on RX). Either way, the tagging protocol driver must populate the
-``struct dsa_device_ops::overhead`` with the length in octets of the longest
-switch frame header. The DSA framework will automatically adjust the MTU of the
-master interface to accomodate for this extra size in order for DSA user ports
-to support the standard MTU (L2 payload length) of 1500 octets. The ``overhead``
-is also used to request from the network stack, on a best-effort basis, the
-allocation of packets with a ``needed_headroom`` or ``needed_tailroom``
-sufficient such that the act of pushing the switch tag on transmission of a
-packet does not cause it to reallocate due to lack of memory.
+``struct dsa_device_ops::needed_headroom`` and/or ``struct dsa_device_ops::needed_tailroom``
+with the length in octets of the longest switch frame header/trailer. The DSA
+framework will automatically adjust the MTU of the master interface to
+accommodate for this extra size in order for DSA user ports to support the
+standard MTU (L2 payload length) of 1500 octets. The ``needed_headroom`` and
+``needed_tailroom`` properties are also used to request from the network stack,
+on a best-effort basis, the allocation of packets with enough extra space such
+that the act of pushing the switch tag on transmission of a packet does not
+cause it to reallocate due to lack of memory.
 
 Even though applications are not expected to parse DSA-specific frame headers,
 the format on the wire of the tagging protocol represents an Application Binary
@@ -169,8 +170,8 @@ The job of this method is to prepare the skb in a way that the switch will
 understand what egress port the packet is for (and not deliver it towards other
 ports). Typically this is fulfilled by pushing a frame header. Checking for
 insufficient size in the skb headroom or tailroom is unnecessary provided that
-the ``overhead`` and ``tail_tag`` properties were filled out properly, because
-DSA ensures there is enough space before calling this method.
+the ``needed_headroom`` and ``needed_tailroom`` properties were filled out
+properly, because DSA ensures there is enough space before calling this method.
 
 The reception of a packet goes through the tagger's ``rcv`` function. The
 passed ``struct sk_buff *skb`` has ``skb->data`` pointing at
diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index c2ecc9894fd0..b0436d3a4f11 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -99,6 +99,35 @@ fib_multipath_hash_policy - INTEGER
 	- 0 - Layer 3
 	- 1 - Layer 4
 	- 2 - Layer 3 or inner Layer 3 if present
+	- 3 - Custom multipath hash. Fields used for multipath hash calculation
+	  are determined by fib_multipath_hash_fields sysctl
+
+fib_multipath_hash_fields - UNSIGNED INTEGER
+	When fib_multipath_hash_policy is set to 3 (custom multipath hash), the
+	fields used for multipath hash calculation are determined by this
+	sysctl.
+
+	This value is a bitmask which enables various fields for multipath hash
+	calculation.
+
+	Possible fields are:
+
+	====== ============================
+	0x0001 Source IP address
+	0x0002 Destination IP address
+	0x0004 IP protocol
+	0x0008 Unused (Flow Label)
+	0x0010 Source port
+	0x0020 Destination port
+	0x0040 Inner source IP address
+	0x0080 Inner destination IP address
+	0x0100 Inner IP protocol
+	0x0200 Inner Flow Label
+	0x0400 Inner source port
+	0x0800 Inner destination port
+	====== ============================
+
+	Default: 0x0007 (source IP, destination IP and IP protocol)
 
 fib_sync_mem - UNSIGNED INTEGER
 	Amount of dirty memory from fib entries that can be backlogged before
@@ -732,6 +761,31 @@ tcp_syncookies - INTEGER
 	network connections you can set this knob to 2 to enable
 	unconditionally generation of syncookies.
 
+tcp_migrate_req - BOOLEAN
+	The incoming connection is tied to a specific listening socket when
+	the initial SYN packet is received during the three-way handshake.
+	When a listener is closed, in-flight request sockets during the
+	handshake and established sockets in the accept queue are aborted.
+
+	If the listener has SO_REUSEPORT enabled, other listeners on the
+	same port should have been able to accept such connections. This
+	option makes it possible to migrate such child sockets to another
+	listener after close() or shutdown().
+
+	The BPF_SK_REUSEPORT_SELECT_OR_MIGRATE type of eBPF program should
+	usually be used to define the policy to pick an alive listener.
+	Otherwise, the kernel will randomly pick an alive listener only if
+	this option is enabled.
+
+	Note that migration between listeners with different settings may
+	crash applications. Let's say migration happens from listener A to
+	B, and only B has TCP_SAVE_SYN enabled. B cannot read SYN data from
+	the requests migrated from A. To avoid such a situation, cancel
+	migration by returning SK_DROP in the type of eBPF program, or
+	disable this option.
+
+	Default: 0
+
 tcp_fastopen - INTEGER
 	Enable TCP Fast Open (RFC7413) to send and accept data in the opening
 	SYN packet.
@@ -1743,6 +1797,35 @@ fib_multipath_hash_policy - INTEGER
 	- 0 - Layer 3 (source and destination addresses plus flow label)
 	- 1 - Layer 4 (standard 5-tuple)
 	- 2 - Layer 3 or inner Layer 3 if present
+	- 3 - Custom multipath hash. Fields used for multipath hash calculation
+	  are determined by fib_multipath_hash_fields sysctl
+
+fib_multipath_hash_fields - UNSIGNED INTEGER
+	When fib_multipath_hash_policy is set to 3 (custom multipath hash), the
+	fields used for multipath hash calculation are determined by this
+	sysctl.
+
+	This value is a bitmask which enables various fields for multipath hash
+	calculation.
+
+	Possible fields are:
+
+	====== ============================
+	0x0001 Source IP address
+	0x0002 Destination IP address
+	0x0004 IP protocol
+	0x0008 Flow Label
+	0x0010 Source port
+	0x0020 Destination port
+	0x0040 Inner source IP address
+	0x0080 Inner destination IP address
+	0x0100 Inner IP protocol
+	0x0200 Inner Flow Label
+	0x0400 Inner source port
+	0x0800 Inner destination port
+	====== ============================
+
+	Default: 0x0007 (source IP, destination IP and IP protocol)
 
 anycast_src_echo_reply - BOOLEAN
 	Controls the use of anycast addresses as source addresses for ICMPv6
diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index 6af0196c4297..ee06fd782465 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -7,13 +7,13 @@ MPTCP Sysfs variables
 /proc/sys/net/mptcp/* Variables
 ===============================
 
-enabled - INTEGER
+enabled - BOOLEAN
 	Control whether MPTCP sockets can be created.
 
-	MPTCP sockets can be created if the value is nonzero. This is
-	a per-namespace sysctl.
+	MPTCP sockets can be created if the value is 1. This is a
+	per-namespace sysctl.
 
-	Default: 1
+	Default: 1 (enabled)
 
 add_addr_timeout - INTEGER (seconds)
 	Set the timeout after which an ADD_ADDR control message will be
@@ -24,3 +24,11 @@ add_addr_timeout - INTEGER (seconds)
 	sysctl.
 
 	Default: 120
+
+checksum_enabled - BOOLEAN
+	Control whether DSS checksum can be enabled.
+
+	DSS checksum can be enabled if the value is nonzero. This is a
+	per-namespace sysctl.
+
+	Default: 0
diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst
index 3f05d50ecd6e..571ba08386e7 100644
--- a/Documentation/networking/phy.rst
+++ b/Documentation/networking/phy.rst
@@ -292,6 +292,12 @@ Some of the interface modes are described below:
     Note: due to legacy usage, some 10GBASE-R usage incorrectly makes
     use of this definition.
 
+``PHY_INTERFACE_MODE_25GBASER``
+    This is the IEEE 802.3 PCS Clause 107 defined 25GBASE-R protocol.
+    The PCS is identical to 10GBASE-R, i.e. 64B/66B encoded
+    running 2.5 as fast, giving a fixed bit rate of 25.78125 Gbaud.
+    Please refer to the IEEE standard for further information.
+
 ``PHY_INTERFACE_MODE_100BASEX``
     This defines IEEE 802.3 Clause 24.  The link operates at a fixed data
     rate of 125Mpbs using a 4B/5B encoding scheme, resulting in an underlying
diff --git a/MAINTAINERS b/MAINTAINERS
index 8c5ee008301a..395b052635ca 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6812,6 +6812,8 @@ F:	Documentation/devicetree/bindings/net/mdio*
 F:	Documentation/devicetree/bindings/net/qca,ar803x.yaml
 F:	Documentation/networking/phy.rst
 F:	drivers/net/mdio/
+F:	drivers/net/mdio/acpi_mdio.c
+F:	drivers/net/mdio/fwnode_mdio.c
 F:	drivers/net/mdio/of_mdio.c
 F:	drivers/net/pcs/
 F:	drivers/net/phy/
@@ -9139,6 +9141,7 @@ F:	Documentation/networking/device_drivers/ethernet/intel/
 F:	drivers/net/ethernet/intel/
 F:	drivers/net/ethernet/intel/*/
 F:	include/linux/avf/virtchnl.h
+F:	include/linux/net/intel/iidc.h
 
 INTEL FRAMEBUFFER DRIVER (excluding 810 and 815)
 M:	Maik Broemme <mbroemme@libmpq.org>
@@ -9452,6 +9455,13 @@ L:	Dell.Client.Kernel@dell.com
 S:	Maintained
 F:	drivers/platform/x86/intel-wmi-thunderbolt.c
 
+INTEL WWAN IOSM DRIVER
+M:	M Chetan Kumar <m.chetan.kumar@intel.com>
+M:	Intel Corporation <linuxwwan@intel.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/wwan/iosm/
+
 INTEL(R) TRACE HUB
 M:	Alexander Shishkin <alexander.shishkin@linux.intel.com>
 S:	Supported
@@ -12388,6 +12398,12 @@ F:	Documentation/userspace-api/media/drivers/meye*
 F:	drivers/media/pci/meye/
 F:	include/uapi/linux/meye.h
 
+MOTORCOMM PHY DRIVER
+M:	Peter Geis <pgwipeout@gmail.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/phy/motorcomm.c
+
 MOXA SMARTIO/INDUSTIO/INTELLIO SERIAL CARD
 S:	Orphan
 F:	Documentation/driver-api/serial/moxa-smartio.rst
@@ -13196,6 +13212,7 @@ M:	Vladimir Oltean <olteanv@gmail.com>
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 F:	drivers/net/dsa/sja1105
+F:	drivers/net/pcs/pcs-xpcs-nxp.c
 
 NXP TDA998X DRM DRIVER
 M:	Russell King <linux@armlinux.org.uk>
@@ -15576,6 +15593,13 @@ F:	include/linux/rpmsg/
 F:	include/uapi/linux/rpmsg.h
 F:	samples/rpmsg/
 
+REMOTE PROCESSOR MESSAGING (RPMSG) WWAN CONTROL DRIVER
+M:	Stephan Gerhold <stephan@gerhold.net>
+L:	netdev@vger.kernel.org
+L:	linux-remoteproc@vger.kernel.org
+S:	Maintained
+F:	drivers/net/wwan/rpmsg_wwan_ctrl.c
+
 RENESAS CLOCK DRIVERS
 M:	Geert Uytterhoeven <geert+renesas@glider.be>
 L:	linux-renesas-soc@vger.kernel.org
@@ -17674,6 +17698,7 @@ M:	Jose Abreu <Jose.Abreu@synopsys.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/pcs/pcs-xpcs.c
+F:	drivers/net/pcs/pcs-xpcs.h
 F:	include/linux/pcs/pcs-xpcs.h
 
 SYNOPSYS DESIGNWARE I2C DRIVER
diff --git a/arch/arm64/boot/dts/rockchip/rk3308.dtsi b/arch/arm64/boot/dts/rockchip/rk3308.dtsi
index 0c5fa9801e6f..b815ce73e5c6 100644
--- a/arch/arm64/boot/dts/rockchip/rk3308.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3308.dtsi
@@ -637,6 +637,28 @@
 		status = "disabled";
 	};
 
+	gmac: ethernet@ff4e0000 {
+		compatible = "rockchip,rk3308-gmac";
+		reg = <0x0 0xff4e0000 0x0 0x10000>;
+		interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "macirq";
+		clocks = <&cru SCLK_MAC>, <&cru SCLK_MAC_RX_TX>,
+			 <&cru SCLK_MAC_RX_TX>, <&cru SCLK_MAC_REF>,
+			 <&cru SCLK_MAC>, <&cru ACLK_MAC>,
+			 <&cru PCLK_MAC>, <&cru SCLK_MAC_RMII>;
+		clock-names = "stmmaceth", "mac_clk_rx",
+			      "mac_clk_tx", "clk_mac_ref",
+			      "clk_mac_refout", "aclk_mac",
+			      "pclk_mac", "clk_mac_speed";
+		phy-mode = "rmii";
+		pinctrl-names = "default";
+		pinctrl-0 = <&rmii_pins &mac_refclk_12ma>;
+		resets = <&cru SRST_MAC_A>;
+		reset-names = "stmmaceth";
+		rockchip,grf = <&grf>;
+		status = "disabled";
+	};
+
 	cru: clock-controller@ff500000 {
 		compatible = "rockchip,rk3308-cru";
 		reg = <0x0 0xff500000 0x0 0x1000>;
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index f7b194878a99..be873a7da62b 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -178,9 +178,6 @@ static bool is_addsub_imm(u32 imm)
 	return !(imm & ~0xfff) || !(imm & ~0xfff000);
 }
 
-/* Stack must be multiples of 16B */
-#define STACK_ALIGN(sz) (((sz) + 15) & ~15)
-
 /* Tail call offset to jump into */
 #if IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)
 #define PROLOGUE_OFFSET 8
@@ -255,7 +252,8 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 			emit(A64_BTI_J, ctx);
 	}
 
-	ctx->stack_size = STACK_ALIGN(prog->aux->stack_depth);
+	/* Stack must be multiples of 16B */
+	ctx->stack_size = round_up(prog->aux->stack_depth, 16);
 
 	/* Set up function call stack */
 	emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
@@ -487,17 +485,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		break;
 	case BPF_ALU | BPF_DIV | BPF_X:
 	case BPF_ALU64 | BPF_DIV | BPF_X:
+		emit(A64_UDIV(is64, dst, dst, src), ctx);
+		break;
 	case BPF_ALU | BPF_MOD | BPF_X:
 	case BPF_ALU64 | BPF_MOD | BPF_X:
-		switch (BPF_OP(code)) {
-		case BPF_DIV:
-			emit(A64_UDIV(is64, dst, dst, src), ctx);
-			break;
-		case BPF_MOD:
-			emit(A64_UDIV(is64, tmp, dst, src), ctx);
-			emit(A64_MSUB(is64, dst, dst, tmp, src), ctx);
-			break;
-		}
+		emit(A64_UDIV(is64, tmp, dst, src), ctx);
+		emit(A64_MSUB(is64, dst, dst, tmp, src), ctx);
 		break;
 	case BPF_ALU | BPF_LSH | BPF_X:
 	case BPF_ALU64 | BPF_LSH | BPF_X:
diff --git a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
index 569e814def83..5747f171de29 100644
--- a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
+++ b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
@@ -114,6 +114,52 @@
 			ranges = <0x01000000 0x0 0x00000000 0x0 0x18000000  0x0 0x00010000>,
 				 <0x02000000 0x0 0x40000000 0x0 0x40000000  0x0 0x40000000>;
 
+			gmac@3,0 {
+				compatible = "pci0014,7a03.0",
+						   "pci0014,7a03",
+						   "pciclass0c0320",
+						   "pciclass0c03",
+						   "loongson, pci-gmac";
+
+				reg = <0x1800 0x0 0x0 0x0 0x0>;
+				interrupts = <12 IRQ_TYPE_LEVEL_LOW>,
+					     <13 IRQ_TYPE_LEVEL_LOW>;
+				interrupt-names = "macirq", "eth_lpi";
+				interrupt-parent = <&liointc0>;
+				phy-mode = "rgmii";
+				mdio {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					compatible = "snps,dwmac-mdio";
+					phy0: ethernet-phy@0 {
+						reg = <0>;
+					};
+				};
+			};
+
+			gmac@3,1 {
+				compatible = "pci0014,7a03.0",
+						   "pci0014,7a03",
+						   "pciclass0c0320",
+						   "pciclass0c03",
+						   "loongson, pci-gmac";
+
+				reg = <0x1900 0x0 0x0 0x0 0x0>;
+				interrupts = <14 IRQ_TYPE_LEVEL_LOW>,
+					     <15 IRQ_TYPE_LEVEL_LOW>;
+				interrupt-names = "macirq", "eth_lpi";
+				interrupt-parent = <&liointc0>;
+				phy-mode = "rgmii";
+				mdio {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					compatible = "snps,dwmac-mdio";
+					phy1: ethernet-phy@1 {
+						reg = <0>;
+					};
+				};
+			};
+
 			ehci@4,1 {
 				compatible = "pci0014,7a14.0",
 						   "pci0014,7a14",
diff --git a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi
index f99a7a11fded..58b9bb47c58a 100644
--- a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi
+++ b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi
@@ -186,7 +186,8 @@
 				compatible = "pci0014,7a03.0",
 						   "pci0014,7a03",
 						   "pciclass020000",
-						   "pciclass0200";
+						   "pciclass0200",
+						   "loongson, pci-gmac";
 
 				reg = <0x1800 0x0 0x0 0x0 0x0>;
 				interrupts = <12 IRQ_TYPE_LEVEL_HIGH>,
@@ -208,7 +209,8 @@
 				compatible = "pci0014,7a03.0",
 						   "pci0014,7a03",
 						   "pciclass020000",
-						   "pciclass0200";
+						   "pciclass0200",
+						   "loongson, pci-gmac";
 
 				reg = <0x1900 0x0 0x0 0x0 0x0>;
 				interrupts = <14 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index 8fc52679543d..cb4f73c7228d 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -137,7 +137,6 @@ struct slibe {
  * @user0: user defineable value
  * @res4: reserved paramater
  * @user1: user defineable value
- * @user2: user defineable value
  */
 struct qaob {
 	u64 res0[6];
@@ -152,8 +151,7 @@ struct qaob {
 	u16 dcount[QDIO_MAX_ELEMENTS_PER_BUFFER];
 	u64 user0;
 	u64 res4[2];
-	u64 user1;
-	u64 user2;
+	u8 user1[16];
 } __attribute__ ((packed, aligned(256)));
 
 /**
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 3b54b8fd7396..e7ddd281afff 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -277,6 +277,20 @@ acpi_evaluate_integer(acpi_handle handle,
 
 EXPORT_SYMBOL(acpi_evaluate_integer);
 
+int acpi_get_local_address(acpi_handle handle, u32 *addr)
+{
+	unsigned long long adr;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL, &adr);
+	if (ACPI_FAILURE(status))
+		return -ENODATA;
+
+	*addr = (u32)adr;
+	return 0;
+}
+EXPORT_SYMBOL(acpi_get_local_address);
+
 acpi_status
 acpi_evaluate_reference(acpi_handle handle,
 			acpi_string pathname,
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index 933e3ff2ee8d..bc8e8d9f176b 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -47,6 +47,7 @@
 #include <linux/errno.h>  
 #include <linux/atm.h>  
 #include <linux/atmdev.h>  
+#include <linux/ctype.h>
 #include <linux/sonet.h>  
 #include <linux/skbuff.h>  
 #include <linux/time.h>  
@@ -996,10 +997,12 @@ static void xdump( u_char*  cp, int  length, char*  prefix )
         }
         pBuf += sprintf( pBuf, "  " );
         for(col = 0;count + col < length && col < 16; col++){
-            if (isprint((int)cp[count + col]))
-                pBuf += sprintf( pBuf, "%c", cp[count + col] );
-            else
-                pBuf += sprintf( pBuf, "." );
+		u_char c = cp[count + col];
+
+		if (isascii(c) && isprint(c))
+			pBuf += sprintf(pBuf, "%c", c);
+		else
+			pBuf += sprintf(pBuf, ".");
                 }
         printk("%s\n", prntBuf);
         count += col;
@@ -3279,7 +3282,7 @@ static void __exit ia_module_exit(void)
 {
 	pci_unregister_driver(&ia_driver);
 
-        del_timer(&ia_timer);
+	del_timer_sync(&ia_timer);
 }
 
 module_init(ia_module_init);
diff --git a/drivers/atm/iphase.h b/drivers/atm/iphase.h
index 2beacf2fc1ec..2f5f8875cbd1 100644
--- a/drivers/atm/iphase.h
+++ b/drivers/atm/iphase.h
@@ -124,7 +124,6 @@
 #define IF_RXPKT(A)
 #endif /* CONFIG_ATM_IA_DEBUG */ 
 
-#define isprint(a) ((a >=' ')&&(a <= '~'))  
 #define ATM_DESC(skb) (skb->protocol)
 #define IA_SKB_STATE(skb) (skb->protocol)
 #define IA_DLED   1
diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c
index 5c7e4df159b9..b015c3e14336 100644
--- a/drivers/atm/nicstar.c
+++ b/drivers/atm/nicstar.c
@@ -299,7 +299,7 @@ static void __exit nicstar_cleanup(void)
 {
 	XPRINTK("nicstar: nicstar_cleanup() called.\n");
 
-	del_timer(&ns_timer);
+	del_timer_sync(&ns_timer);
 
 	pci_unregister_driver(&nicstar_driver);
 
diff --git a/drivers/atm/zeprom.h b/drivers/atm/zeprom.h
index 88e01f808a86..8e8819a3840d 100644
--- a/drivers/atm/zeprom.h
+++ b/drivers/atm/zeprom.h
@@ -12,7 +12,7 @@
 #define ZEPROM_V1_REG	PCI_VENDOR_ID	/* PCI register */
 #define ZEPROM_V2_REG	0x40
 
-/* Bits in contol register */
+/* Bits in control register */
 
 #define ZEPROM_SK	0x80000000	/* strobe (probably on raising edge) */
 #define ZEPROM_CS	0x40000000	/* Chip Select */
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 54ba506e5a89..2a61003ea2c1 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -4727,6 +4727,13 @@ void device_set_of_node_from_dev(struct device *dev, const struct device *dev2)
 }
 EXPORT_SYMBOL_GPL(device_set_of_node_from_dev);
 
+void device_set_node(struct device *dev, struct fwnode_handle *fwnode)
+{
+	dev->fwnode = fwnode;
+	dev->of_node = to_of_node(fwnode);
+}
+EXPORT_SYMBOL_GPL(device_set_node);
+
 int device_match_name(struct device *dev, const void *name)
 {
 	return sysfs_streq(dev_name(dev), name);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c
index b496f30ce066..364f69cd620f 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_main.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_main.c
@@ -1423,7 +1423,7 @@ static enum i40iw_status_code i40iw_save_msix_info(struct i40iw_device *iwdev,
 	struct i40e_qv_info *iw_qvinfo;
 	u32 ceq_idx;
 	u32 i;
-	u32 size;
+	size_t size;
 
 	if (!ldev->msix_count) {
 		i40iw_pr_err("No MSI-X vectors\n");
@@ -1433,8 +1433,7 @@ static enum i40iw_status_code i40iw_save_msix_info(struct i40iw_device *iwdev,
 	iwdev->msix_count = ldev->msix_count;
 
 	size = sizeof(struct i40iw_msix_vector) * iwdev->msix_count;
-	size += sizeof(struct i40e_qvlist_info);
-	size +=  sizeof(struct i40e_qv_info) * iwdev->msix_count - 1;
+	size += struct_size(iw_qvlist, qv_info, iwdev->msix_count);
 	iwdev->iw_msixtbl = kzalloc(size, GFP_KERNEL);
 
 	if (!iwdev->iw_msixtbl)
diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c
index 18ee2f293825..5fbc0a8454b9 100644
--- a/drivers/infiniband/hw/mlx5/fs.c
+++ b/drivers/infiniband/hw/mlx5/fs.c
@@ -2285,6 +2285,7 @@ static int mlx5_ib_flow_action_create_packet_reformat_ctx(
 	u8 ft_type, u8 dv_prt,
 	void *in, size_t len)
 {
+	struct mlx5_pkt_reformat_params reformat_params;
 	enum mlx5_flow_namespace_type namespace;
 	u8 prm_prt;
 	int ret;
@@ -2297,9 +2298,13 @@ static int mlx5_ib_flow_action_create_packet_reformat_ctx(
 	if (ret)
 		return ret;
 
+	memset(&reformat_params, 0, sizeof(reformat_params));
+	reformat_params.type = prm_prt;
+	reformat_params.size = len;
+	reformat_params.data = in;
 	maction->flow_action_raw.pkt_reformat =
-		mlx5_packet_reformat_alloc(dev->mdev, prm_prt, len,
-					   in, namespace);
+		mlx5_packet_reformat_alloc(dev->mdev, &reformat_params,
+					   namespace);
 	if (IS_ERR(maction->flow_action_raw.pkt_reformat)) {
 		ret = PTR_ERR(maction->flow_action_raw.pkt_reformat);
 		return ret;
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 782b2af8f211..1338c11fd121 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -1559,12 +1559,16 @@ int mlx5r_odp_create_eq(struct mlx5_ib_dev *dev, struct mlx5_ib_pf_eq *eq)
 	}
 
 	eq->irq_nb.notifier_call = mlx5_ib_eq_pf_int;
-	param = (struct mlx5_eq_param){
-		.irq_index = 0,
+	param = (struct mlx5_eq_param) {
 		.nent = MLX5_IB_NUM_PF_EQE,
 	};
 	param.mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_FAULT;
+	if (!zalloc_cpumask_var(&param.affinity, GFP_KERNEL)) {
+		err = -ENOMEM;
+		goto err_wq;
+	}
 	eq->core = mlx5_eq_create_generic(dev->mdev, &param);
+	free_cpumask_var(param.affinity);
 	if (IS_ERR(eq->core)) {
 		err = PTR_ERR(eq->core);
 		goto err_wq;
diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c
index 56bd2e9db6ed..e501cb03f211 100644
--- a/drivers/isdn/hardware/mISDN/hfcpci.c
+++ b/drivers/isdn/hardware/mISDN/hfcpci.c
@@ -2342,7 +2342,7 @@ static void __exit
 HFC_cleanup(void)
 {
 	if (timer_pending(&hfc_tl))
-		del_timer(&hfc_tl);
+		del_timer_sync(&hfc_tl);
 
 	pci_unregister_driver(&hfc_driver);
 }
diff --git a/drivers/isdn/mISDN/dsp_pipeline.c b/drivers/isdn/mISDN/dsp_pipeline.c
index 40588692cec7..e11ca6bbc7f4 100644
--- a/drivers/isdn/mISDN/dsp_pipeline.c
+++ b/drivers/isdn/mISDN/dsp_pipeline.c
@@ -17,9 +17,6 @@
 #include "dsp.h"
 #include "dsp_hwec.h"
 
-/* uncomment for debugging */
-/*#define PIPELINE_DEBUG*/
-
 struct dsp_pipeline_entry {
 	struct mISDN_dsp_element *elem;
 	void                *p;
@@ -104,10 +101,6 @@ int mISDN_dsp_element_register(struct mISDN_dsp_element *elem)
 		}
 	}
 
-#ifdef PIPELINE_DEBUG
-	printk(KERN_DEBUG "%s: %s registered\n", __func__, elem->name);
-#endif
-
 	return 0;
 
 err2:
@@ -129,10 +122,6 @@ void mISDN_dsp_element_unregister(struct mISDN_dsp_element *elem)
 	list_for_each_entry_safe(entry, n, &dsp_elements, list)
 		if (entry->elem == elem) {
 			device_unregister(&entry->dev);
-#ifdef PIPELINE_DEBUG
-			printk(KERN_DEBUG "%s: %s unregistered\n",
-			       __func__, elem->name);
-#endif
 			return;
 		}
 	printk(KERN_ERR "%s: element %s not in list.\n", __func__, elem->name);
@@ -145,10 +134,6 @@ int dsp_pipeline_module_init(void)
 	if (IS_ERR(elements_class))
 		return PTR_ERR(elements_class);
 
-#ifdef PIPELINE_DEBUG
-	printk(KERN_DEBUG "%s: dsp pipeline module initialized\n", __func__);
-#endif
-
 	dsp_hwec_init();
 
 	return 0;
@@ -168,10 +153,6 @@ void dsp_pipeline_module_exit(void)
 		       __func__, entry->elem->name);
 		kfree(entry);
 	}
-
-#ifdef PIPELINE_DEBUG
-	printk(KERN_DEBUG "%s: dsp pipeline module exited\n", __func__);
-#endif
 }
 
 int dsp_pipeline_init(struct dsp_pipeline *pipeline)
@@ -181,10 +162,6 @@ int dsp_pipeline_init(struct dsp_pipeline *pipeline)
 
 	INIT_LIST_HEAD(&pipeline->list);
 
-#ifdef PIPELINE_DEBUG
-	printk(KERN_DEBUG "%s: dsp pipeline ready\n", __func__);
-#endif
-
 	return 0;
 }
 
@@ -210,15 +187,11 @@ void dsp_pipeline_destroy(struct dsp_pipeline *pipeline)
 		return;
 
 	_dsp_pipeline_destroy(pipeline);
-
-#ifdef PIPELINE_DEBUG
-	printk(KERN_DEBUG "%s: dsp pipeline destroyed\n", __func__);
-#endif
 }
 
 int dsp_pipeline_build(struct dsp_pipeline *pipeline, const char *cfg)
 {
-	int incomplete = 0, found = 0;
+	int found = 0;
 	char *dup, *tok, *name, *args;
 	struct dsp_element_entry *entry, *n;
 	struct dsp_pipeline_entry *pipeline_entry;
@@ -251,7 +224,6 @@ int dsp_pipeline_build(struct dsp_pipeline *pipeline, const char *cfg)
 					printk(KERN_ERR "%s: failed to add "
 					       "entry to pipeline: %s (out of "
 					       "memory)\n", __func__, elem->name);
-					incomplete = 1;
 					goto _out;
 				}
 				pipeline_entry->elem = elem;
@@ -268,20 +240,12 @@ int dsp_pipeline_build(struct dsp_pipeline *pipeline, const char *cfg)
 					if (pipeline_entry->p) {
 						list_add_tail(&pipeline_entry->
 							      list, &pipeline->list);
-#ifdef PIPELINE_DEBUG
-						printk(KERN_DEBUG "%s: created "
-						       "instance of %s%s%s\n",
-						       __func__, name, args ?
-						       " with args " : "", args ?
-						       args : "");
-#endif
 					} else {
 						printk(KERN_ERR "%s: failed "
 						       "to add entry to pipeline: "
 						       "%s (new() returned NULL)\n",
 						       __func__, elem->name);
 						kfree(pipeline_entry);
-						incomplete = 1;
 					}
 				}
 				found = 1;
@@ -290,11 +254,9 @@ int dsp_pipeline_build(struct dsp_pipeline *pipeline, const char *cfg)
 
 		if (found)
 			found = 0;
-		else {
+		else
 			printk(KERN_ERR "%s: element not found, skipping: "
 			       "%s\n", __func__, name);
-			incomplete = 1;
-		}
 	}
 
 _out:
@@ -303,10 +265,6 @@ _out:
 	else
 		pipeline->inuse = 0;
 
-#ifdef PIPELINE_DEBUG
-	printk(KERN_DEBUG "%s: dsp pipeline built%s: %s\n",
-	       __func__, incomplete ? " incomplete" : "", cfg);
-#endif
 	kfree(dup);
 	return 0;
 }
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 74dc8e249faa..6977f8248df7 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -262,17 +262,17 @@ config GENEVE
 	  will be called geneve.
 
 config BAREUDP
-       tristate "Bare UDP Encapsulation"
-       depends on INET
-       depends on IPV6 || !IPV6
-       select NET_UDP_TUNNEL
-       select GRO_CELLS
-       help
-          This adds a bare UDP tunnel module for tunnelling different
-          kinds of traffic like MPLS, IP, etc. inside a UDP tunnel.
-
-          To compile this driver as a module, choose M here: the module
-          will be called bareudp.
+	tristate "Bare UDP Encapsulation"
+	depends on INET
+	depends on IPV6 || !IPV6
+	select NET_UDP_TUNNEL
+	select GRO_CELLS
+	help
+	  This adds a bare UDP tunnel module for tunnelling different
+	  kinds of traffic like MPLS, IP, etc. inside a UDP tunnel.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called bareudp.
 
 config GTP
 	tristate "GPRS Tunneling Protocol datapath (GTP-U)"
@@ -431,6 +431,7 @@ config VSOCKMON
 config MHI_NET
 	tristate "MHI network driver"
 	depends on MHI_BUS
+	select WWAN
 	help
 	  This is the network driver for MHI bus.  It can be used with
 	  QCOM based WWAN modems (like SDX55).  Say Y or M.
diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c
index 6b12ce822e51..f0695d68c47e 100644
--- a/drivers/net/appletalk/cops.c
+++ b/drivers/net/appletalk/cops.c
@@ -609,12 +609,12 @@ static int cops_nodeid (struct net_device *dev, int nodeid)
 
 	if(lp->board == DAYNA)
         {
-        	/* Empty any pending adapter responses. */
+		/* Empty any pending adapter responses. */
                 while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0)
                 {
 			outb(0, ioaddr+COPS_CLEAR_INT);	/* Clear interrupts. */
-        		if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_REQUEST)
-                		cops_rx(dev);	/* Kick any packets waiting. */
+			if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_REQUEST)
+				cops_rx(dev);	/* Kick any packets waiting. */
 			schedule();
                 }
 
@@ -630,13 +630,13 @@ static int cops_nodeid (struct net_device *dev, int nodeid)
                 while(inb(ioaddr+TANG_CARD_STATUS)&TANG_RX_READY)
                 {
 			outb(0, ioaddr+COPS_CLEAR_INT);	/* Clear interrupt. */
-                	cops_rx(dev);          	/* Kick out packets waiting. */
+			cops_rx(dev);          	/* Kick out packets waiting. */
 			schedule();
                 }
 
 		/* Not sure what Tangent does if nodeid picked is used. */
                 if(nodeid == 0)	         		/* Seed. */
-                	nodeid = jiffies&0xFF;		/* Get a random try */
+			nodeid = jiffies&0xFF;		/* Get a random try */
                 outb(2, ioaddr);        		/* Command length LSB */
                 outb(0, ioaddr);       			/* Command length MSB */
                 outb(LAP_INIT, ioaddr); 		/* Send LAP_INIT byte */
@@ -651,13 +651,13 @@ static int cops_nodeid (struct net_device *dev, int nodeid)
 
 		if(lp->board == DAYNA)
 		{
-                	if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_REQUEST)
-                		cops_rx(dev);	/* Grab the nodeid put in lp->node_acquire. */
+			if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_REQUEST)
+				cops_rx(dev);	/* Grab the nodeid put in lp->node_acquire. */
 		}
 		if(lp->board == TANGENT)
 		{	
 			if(inb(ioaddr+TANG_CARD_STATUS)&TANG_RX_READY)
-                                cops_rx(dev);   /* Grab the nodeid put in lp->node_acquire. */
+				cops_rx(dev);   /* Grab the nodeid put in lp->node_acquire. */
 		}
 		schedule();
 	}
@@ -719,16 +719,16 @@ static irqreturn_t cops_interrupt(int irq, void *dev_id)
 	{
 		do {
 			outb(0, ioaddr + COPS_CLEAR_INT);
-                       	status=inb(ioaddr+DAYNA_CARD_STATUS);
-                       	if((status&0x03)==DAYNA_RX_REQUEST)
-                       	        cops_rx(dev);
-                	netif_wake_queue(dev);
+			status=inb(ioaddr+DAYNA_CARD_STATUS);
+			if((status&0x03)==DAYNA_RX_REQUEST)
+				cops_rx(dev);
+			netif_wake_queue(dev);
 		} while(++boguscount < 20);
 	}
 	else
 	{
 		do {
-                       	status=inb(ioaddr+TANG_CARD_STATUS);
+			status=inb(ioaddr+TANG_CARD_STATUS);
 			if(status & TANG_RX_READY)
 				cops_rx(dev);
 			if(status & TANG_TX_READY)
@@ -855,7 +855,7 @@ static void cops_timeout(struct net_device *dev, unsigned int txqueue)
         if(lp->board==TANGENT)
         {
 		if((inb(ioaddr+TANG_CARD_STATUS)&TANG_TX_READY)==0)
-               		printk(KERN_WARNING "%s: No TX complete interrupt.\n", dev->name);
+			printk(KERN_WARNING "%s: No TX complete interrupt.\n", dev->name);
 	}
 	printk(KERN_WARNING "%s: Transmit timed out.\n", dev->name);
 	cops_jumpstart(dev);	/* Restart the card. */
@@ -897,7 +897,7 @@ static netdev_tx_t cops_send_packet(struct sk_buff *skb,
 	outb(LAP_WRITE, ioaddr);
 
 	if(lp->board == DAYNA)	/* Check the transmit buffer again. */
-        	while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0);
+		while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0);
 
 	outsb(ioaddr, skb->data, skb->len);	/* Send out the data. */
 
diff --git a/drivers/net/appletalk/ltpc.c b/drivers/net/appletalk/ltpc.c
index c6f73aa3700c..69c270885ff0 100644
--- a/drivers/net/appletalk/ltpc.c
+++ b/drivers/net/appletalk/ltpc.c
@@ -584,11 +584,13 @@ loop:
 						printk("%02x ",ltdmacbuf[i]);
 					printk("\n");
 				}
+
 				handlecommand(dev);
-					if(0xfa==inb_p(base+6)) {
-						/* we timed out, so return */
-						goto done;
-					} 
+
+				if (0xfa == inb_p(base + 6)) {
+					/* we timed out, so return */
+					goto done;
+				}
 			} else {
 				/* we don't seem to have a command */
 				if (!mboxinuse[0]) {
@@ -935,10 +937,10 @@ static netdev_tx_t ltpc_xmit(struct sk_buff *skb, struct net_device *dev)
 static int __init ltpc_probe_dma(int base, int dma)
 {
 	int want = (dma == 3) ? 2 : (dma == 1) ? 1 : 3;
-  	unsigned long timeout;
-  	unsigned long f;
+	unsigned long timeout;
+	unsigned long f;
   
-  	if (want & 1) {
+	if (want & 1) {
 		if (request_dma(1,"ltpc")) {
 			want &= ~1;
 		} else {
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 3455f2cc13f2..22e5632089ac 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -104,6 +104,7 @@ static void __tlb_clear_slave(struct bonding *bond, struct slave *slave,
 		index = SLAVE_TLB_INFO(slave).head;
 		while (index != TLB_NULL_INDEX) {
 			u32 next_index = tx_hash_table[index].next;
+
 			tlb_init_table_entry(&tx_hash_table[index], save_load);
 			index = next_index;
 		}
@@ -228,7 +229,7 @@ static struct slave *tlb_choose_channel(struct bonding *bond, u32 hash_index,
 {
 	struct slave *tx_slave;
 
-	/* We don't need to disable softirq here, becase
+	/* We don't need to disable softirq here, because
 	 * tlb_choose_channel() is only called by bond_alb_xmit()
 	 * which already has softirq disabled.
 	 */
@@ -608,7 +609,7 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb,
 
 		client_info->ip_src = arp->ip_src;
 		client_info->ip_dst = arp->ip_dst;
-		/* arp->mac_dst is broadcast for arp reqeusts.
+		/* arp->mac_dst is broadcast for arp requests.
 		 * will be updated with clients actual unicast mac address
 		 * upon receiving an arp reply.
 		 */
@@ -628,6 +629,7 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb,
 
 		if (!client_info->assigned) {
 			u32 prev_tbl_head = bond_info->rx_hashtbl_used_head;
+
 			bond_info->rx_hashtbl_used_head = hash_index;
 			client_info->used_next = prev_tbl_head;
 			if (prev_tbl_head != RLB_NULL_INDEX) {
@@ -830,9 +832,10 @@ static void rlb_purge_src_ip(struct bonding *bond, struct arp_pkt *arp)
 	while (index != RLB_NULL_INDEX) {
 		struct rlb_client_info *entry = &(bond_info->rx_hashtbl[index]);
 		u32 next_index = entry->src_next;
+
 		if (entry->ip_src == arp->ip_src &&
 		    !ether_addr_equal_64bits(arp->mac_src, entry->mac_src))
-				rlb_delete_table_entry(bond, index);
+			rlb_delete_table_entry(bond, index);
 		index = next_index;
 	}
 	spin_unlock_bh(&bond->mode_lock);
@@ -1268,7 +1271,7 @@ unwind:
 	return res;
 }
 
-/************************ exported alb funcions ************************/
+/************************ exported alb functions ************************/
 
 int bond_alb_initialize(struct bonding *bond, int rlb_enabled)
 {
@@ -1547,7 +1550,7 @@ void bond_alb_monitor(struct work_struct *work)
 
 		bond_for_each_slave_rcu(bond, slave, iter) {
 			/* If updating current_active, use all currently
-			 * user mac addreses (!strict_match).  Otherwise, only
+			 * user mac addresses (!strict_match).  Otherwise, only
 			 * use mac of the slave device.
 			 * In RLB mode, we always use strict matches.
 			 */
diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c
index f3f86ef68ae0..4f9b4a18c74c 100644
--- a/drivers/net/bonding/bond_debugfs.c
+++ b/drivers/net/bonding/bond_debugfs.c
@@ -88,9 +88,8 @@ void bond_create_debugfs(void)
 {
 	bonding_debug_root = debugfs_create_dir("bonding", NULL);
 
-	if (!bonding_debug_root) {
+	if (!bonding_debug_root)
 		pr_warn("Warning: Cannot create bonding directory in debugfs\n");
-	}
 }
 
 void bond_destroy_debugfs(void)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index c5a646d06102..1d9137e77dfc 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -620,7 +620,7 @@ static int bond_check_dev_link(struct bonding *bond,
 		 */
 
 		/* Yes, the mii is overlaid on the ifreq.ifr_ifru */
-		strncpy(ifr.ifr_name, slave_dev->name, IFNAMSIZ);
+		strscpy_pad(ifr.ifr_name, slave_dev->name, IFNAMSIZ);
 		mii = if_mii(&ifr);
 		if (ioctl(slave_dev, &ifr, SIOCGMIIPHY) == 0) {
 			mii->reg_num = MII_BMSR;
@@ -1013,9 +1013,8 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 			if (bond_is_lb(bond))
 				bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP);
 		} else {
-			if (bond_uses_primary(bond)) {
+			if (bond_uses_primary(bond))
 				slave_info(bond->dev, new_active->dev, "making interface the new active one\n");
-			}
 		}
 	}
 
@@ -2272,6 +2271,7 @@ static int bond_release_and_destroy(struct net_device *bond_dev,
 static void bond_info_query(struct net_device *bond_dev, struct ifbond *info)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
+
 	bond_fill_ifbond(bond, info);
 }
 
@@ -4202,16 +4202,16 @@ static u32 bond_rr_gen_slave_id(struct bonding *bond)
 		slave_id = prandom_u32();
 		break;
 	case 1:
-		slave_id = bond->rr_tx_counter;
+		slave_id = this_cpu_inc_return(*bond->rr_tx_counter);
 		break;
 	default:
 		reciprocal_packets_per_slave =
 			bond->params.reciprocal_packets_per_slave;
-		slave_id = reciprocal_divide(bond->rr_tx_counter,
+		slave_id = this_cpu_inc_return(*bond->rr_tx_counter);
+		slave_id = reciprocal_divide(slave_id,
 					     reciprocal_packets_per_slave);
 		break;
 	}
-	bond->rr_tx_counter++;
 
 	return slave_id;
 }
@@ -4849,8 +4849,12 @@ static const struct device_type bond_type = {
 static void bond_destructor(struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
+
 	if (bond->wq)
 		destroy_workqueue(bond->wq);
+
+	if (bond->rr_tx_counter)
+		free_percpu(bond->rr_tx_counter);
 }
 
 void bond_setup(struct net_device *bond_dev)
@@ -5329,10 +5333,8 @@ static int bond_check_params(struct bond_params *params)
 			(struct reciprocal_value) { 0 };
 	}
 
-	if (primary) {
-		strncpy(params->primary, primary, IFNAMSIZ);
-		params->primary[IFNAMSIZ - 1] = 0;
-	}
+	if (primary)
+		strscpy_pad(params->primary, primary, sizeof(params->primary));
 
 	memcpy(params->arp_targets, arp_target, sizeof(arp_target));
 
@@ -5351,6 +5353,15 @@ static int bond_init(struct net_device *bond_dev)
 	if (!bond->wq)
 		return -ENOMEM;
 
+	if (BOND_MODE(bond) == BOND_MODE_ROUNDROBIN) {
+		bond->rr_tx_counter = alloc_percpu(u32);
+		if (!bond->rr_tx_counter) {
+			destroy_workqueue(bond->wq);
+			bond->wq = NULL;
+			return -ENOMEM;
+		}
+	}
+
 	spin_lock_init(&bond->stats_lock);
 	netdev_lockdep_set_classes(bond_dev);
 
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index f0f9138e967f..0561ece1ba45 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -598,7 +598,7 @@ static int bond_fill_info(struct sk_buff *skb,
 		goto nla_put_failure;
 
 	if (nla_put_u32(skb, IFLA_BOND_RESEND_IGMP,
-		        bond->params.resend_igmp))
+			bond->params.resend_igmp))
 		goto nla_put_failure;
 
 	if (nla_put_u8(skb, IFLA_BOND_NUM_PEER_NOTIF,
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index c9d3604ae129..0cf25de6f46d 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -705,7 +705,7 @@ out:
 int __bond_opt_set_notify(struct bonding *bond,
 			  unsigned int option, struct bond_opt_value *val)
 {
-	int ret = -ENOENT;
+	int ret;
 
 	ASSERT_RTNL();
 
@@ -1206,8 +1206,7 @@ static int bond_option_primary_set(struct bonding *bond,
 		RCU_INIT_POINTER(bond->primary_slave, NULL);
 		bond_select_active_slave(bond);
 	}
-	strncpy(bond->params.primary, primary, IFNAMSIZ);
-	bond->params.primary[IFNAMSIZ - 1] = 0;
+	strscpy_pad(bond->params.primary, primary, IFNAMSIZ);
 
 	netdev_dbg(bond->dev, "Recording %s as primary, but it has not been enslaved yet\n",
 		   primary);
diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c
index 56d34be5e797..0fb1da361bb1 100644
--- a/drivers/net/bonding/bond_procfs.c
+++ b/drivers/net/bonding/bond_procfs.c
@@ -112,6 +112,7 @@ static void bond_info_show_master(struct seq_file *seq)
 	/* ARP information */
 	if (bond->params.arp_interval > 0) {
 		int printed = 0;
+
 		seq_printf(seq, "ARP Polling Interval (ms): %d\n",
 				bond->params.arp_interval);
 
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 2d615a93685e..5f9e9a240226 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -385,6 +385,7 @@ static ssize_t bonding_show_num_peer_notif(struct device *d,
 					   char *buf)
 {
 	struct bonding *bond = to_bond(d);
+
 	return sprintf(buf, "%d\n", bond->params.num_peer_notif);
 }
 static DEVICE_ATTR(num_grat_arp, 0644,
@@ -496,6 +497,7 @@ static ssize_t bonding_show_ad_aggregator(struct device *d,
 
 	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 		struct ad_info ad_info;
+
 		count = sprintf(buf, "%d\n",
 				bond_3ad_get_active_agg_info(bond, &ad_info)
 				?  0 : ad_info.aggregator_id);
@@ -516,6 +518,7 @@ static ssize_t bonding_show_ad_num_ports(struct device *d,
 
 	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 		struct ad_info ad_info;
+
 		count = sprintf(buf, "%d\n",
 				bond_3ad_get_active_agg_info(bond, &ad_info)
 				?  0 : ad_info.ports);
@@ -536,6 +539,7 @@ static ssize_t bonding_show_ad_actor_key(struct device *d,
 
 	if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN)) {
 		struct ad_info ad_info;
+
 		count = sprintf(buf, "%d\n",
 				bond_3ad_get_active_agg_info(bond, &ad_info)
 				?  0 : ad_info.actor_key);
@@ -556,6 +560,7 @@ static ssize_t bonding_show_ad_partner_key(struct device *d,
 
 	if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN)) {
 		struct ad_info ad_info;
+
 		count = sprintf(buf, "%d\n",
 				bond_3ad_get_active_agg_info(bond, &ad_info)
 				?  0 : ad_info.partner_key);
@@ -576,6 +581,7 @@ static ssize_t bonding_show_ad_partner_mac(struct device *d,
 
 	if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN)) {
 		struct ad_info ad_info;
+
 		if (!bond_3ad_get_active_agg_info(bond, &ad_info))
 			count = sprintf(buf, "%pM\n", ad_info.partner_system);
 	}
@@ -660,6 +666,7 @@ static ssize_t bonding_show_tlb_dynamic_lb(struct device *d,
 					   char *buf)
 {
 	struct bonding *bond = to_bond(d);
+
 	return sprintf(buf, "%d\n", bond->params.tlb_dynamic_lb);
 }
 static DEVICE_ATTR(tlb_dynamic_lb, 0644,
diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c
index 106f089eb2a8..91230894692d 100644
--- a/drivers/net/caif/caif_virtio.c
+++ b/drivers/net/caif/caif_virtio.c
@@ -315,7 +315,7 @@ exit:
 	case 0:
 		++cfv->stats.rx_napi_complete;
 
-		/* Really out of patckets? (stolen from virtio_net)*/
+		/* Really out of packets? (stolen from virtio_net)*/
 		napi_complete(napi);
 		if (unlikely(!vringh_notify_enable_kern(cfv->vr_rx)) &&
 		    napi_schedule_prep(napi)) {
@@ -463,7 +463,7 @@ static int cfv_netdev_close(struct net_device *netdev)
 	vringh_notify_disable_kern(cfv->vr_rx);
 	napi_disable(&cfv->napi);
 
-	/* Release any TX buffers on both used and avilable rings */
+	/* Release any TX buffers on both used and available rings */
 	cfv_release_used_buf(cfv->vq_tx);
 	spin_lock_irqsave(&cfv->tx_lock, flags);
 	while ((buf_info = virtqueue_detach_unused_buf(cfv->vq_tx)))
@@ -497,7 +497,7 @@ static struct buf_info *cfv_alloc_and_copy_to_shm(struct cfv_info *cfv,
 	if (unlikely(!buf_info))
 		goto err;
 
-	/* Make the IP header aligned in tbe buffer */
+	/* Make the IP header aligned in the buffer */
 	hdr_ofs = cfv->tx_hr + info->hdr_len;
 	pad_len = hdr_ofs & (IP_HDR_ALIGN - 1);
 	buf_info->size = cfv->tx_hr + skb->len + cfv->tx_tr + pad_len;
diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index 9ad9b39f480e..04d0bb3ffe89 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -169,7 +169,7 @@ static const struct can_bittiming_const at91_bittiming_const = {
 };
 
 #define AT91_IS(_model) \
-static inline int at91_is_sam##_model(const struct at91_priv *priv) \
+static inline int __maybe_unused at91_is_sam##_model(const struct at91_priv *priv) \
 { \
 	return priv->devtype_data.type == AT91_DEVTYPE_SAM##_model; \
 }
diff --git a/drivers/net/can/c_can/Makefile b/drivers/net/can/c_can/Makefile
index e6a94c948531..6fa3b2b9e4b9 100644
--- a/drivers/net/can/c_can/Makefile
+++ b/drivers/net/can/c_can/Makefile
@@ -4,5 +4,10 @@
 #
 
 obj-$(CONFIG_CAN_C_CAN) += c_can.o
+
+c_can-objs :=
+c_can-objs += c_can_ethtool.o
+c_can-objs += c_can_main.o
+
 obj-$(CONFIG_CAN_C_CAN_PLATFORM) += c_can_platform.o
 obj-$(CONFIG_CAN_C_CAN_PCI) += c_can_pci.o
diff --git a/drivers/net/can/c_can/c_can.h b/drivers/net/can/c_can/c_can.h
index 06045f610f0e..4247ff80a29c 100644
--- a/drivers/net/can/c_can/c_can.h
+++ b/drivers/net/can/c_can/c_can.h
@@ -205,7 +205,6 @@ struct c_can_priv {
 	struct c_can_raminit raminit_sys;	/* RAMINIT via syscon regmap */
 	void (*raminit)(const struct c_can_priv *priv, bool enable);
 	u32 comm_rcv_high;
-	u32 rxmasked;
 	u32 dlc[];
 };
 
@@ -219,4 +218,6 @@ int c_can_power_up(struct net_device *dev);
 int c_can_power_down(struct net_device *dev);
 #endif
 
+void c_can_set_ethtool_ops(struct net_device *dev);
+
 #endif /* C_CAN_H */
diff --git a/drivers/net/can/c_can/c_can_ethtool.c b/drivers/net/can/c_can/c_can_ethtool.c
new file mode 100644
index 000000000000..cd5f07fca2a5
--- /dev/null
+++ b/drivers/net/can/c_can/c_can_ethtool.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2021, Dario Binacchi <dariobin@libero.it>
+ */
+
+#include <linux/ethtool.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/netdevice.h>
+#include <linux/can/dev.h>
+
+#include "c_can.h"
+
+static void c_can_get_drvinfo(struct net_device *netdev,
+			      struct ethtool_drvinfo *info)
+{
+	struct c_can_priv *priv = netdev_priv(netdev);
+	struct platform_device *pdev = to_platform_device(priv->device);
+
+	strscpy(info->driver, "c_can", sizeof(info->driver));
+	strscpy(info->bus_info, pdev->name, sizeof(info->bus_info));
+}
+
+static void c_can_get_ringparam(struct net_device *netdev,
+				struct ethtool_ringparam *ring)
+{
+	struct c_can_priv *priv = netdev_priv(netdev);
+
+	ring->rx_max_pending = priv->msg_obj_num;
+	ring->tx_max_pending = priv->msg_obj_num;
+	ring->rx_pending = priv->msg_obj_rx_num;
+	ring->tx_pending = priv->msg_obj_tx_num;
+}
+
+static const struct ethtool_ops c_can_ethtool_ops = {
+	.get_drvinfo = c_can_get_drvinfo,
+	.get_ringparam = c_can_get_ringparam,
+};
+
+void c_can_set_ethtool_ops(struct net_device *netdev)
+{
+	netdev->ethtool_ops = &c_can_ethtool_ops;
+}
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can_main.c
index 313793f6922d..7588f70ca0fe 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can_main.c
@@ -599,7 +599,6 @@ static int c_can_chip_config(struct net_device *dev)
 
 	/* Clear all internal status */
 	atomic_set(&priv->tx_active, 0);
-	priv->rxmasked = 0;
 	priv->tx_dir = 0;
 
 	/* set bittiming params */
@@ -1335,6 +1334,7 @@ int register_c_can_dev(struct net_device *dev)
 
 	dev->flags |= IFF_ECHO;	/* we support local echo */
 	dev->netdev_ops = &c_can_netdev_ops;
+	c_can_set_ethtool_ops(dev);
 
 	err = register_candev(dev);
 	if (!err)
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 3cf6de21d19c..bba2a449ac70 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -83,44 +83,25 @@ enum m_can_reg {
 #define MRAM_CFG_LEN	8
 
 /* Core Release Register (CREL) */
-#define CREL_REL_SHIFT		28
-#define CREL_REL_MASK		(0xF << CREL_REL_SHIFT)
-#define CREL_STEP_SHIFT		24
-#define CREL_STEP_MASK		(0xF << CREL_STEP_SHIFT)
-#define CREL_SUBSTEP_SHIFT	20
-#define CREL_SUBSTEP_MASK	(0xF << CREL_SUBSTEP_SHIFT)
+#define CREL_REL_MASK		GENMASK(31, 28)
+#define CREL_STEP_MASK		GENMASK(27, 24)
+#define CREL_SUBSTEP_MASK	GENMASK(23, 20)
 
 /* Data Bit Timing & Prescaler Register (DBTP) */
 #define DBTP_TDC		BIT(23)
-#define DBTP_DBRP_SHIFT		16
-#define DBTP_DBRP_MASK		(0x1f << DBTP_DBRP_SHIFT)
-#define DBTP_DTSEG1_SHIFT	8
-#define DBTP_DTSEG1_MASK	(0x1f << DBTP_DTSEG1_SHIFT)
-#define DBTP_DTSEG2_SHIFT	4
-#define DBTP_DTSEG2_MASK	(0xf << DBTP_DTSEG2_SHIFT)
-#define DBTP_DSJW_SHIFT		0
-#define DBTP_DSJW_MASK		(0xf << DBTP_DSJW_SHIFT)
+#define DBTP_DBRP_MASK		GENMASK(20, 16)
+#define DBTP_DTSEG1_MASK	GENMASK(12, 8)
+#define DBTP_DTSEG2_MASK	GENMASK(7, 4)
+#define DBTP_DSJW_MASK		GENMASK(3, 0)
 
 /* Transmitter Delay Compensation Register (TDCR) */
-#define TDCR_TDCO_SHIFT		8
-#define TDCR_TDCO_MASK		(0x7F << TDCR_TDCO_SHIFT)
-#define TDCR_TDCF_SHIFT		0
-#define TDCR_TDCF_MASK		(0x7F << TDCR_TDCF_SHIFT)
+#define TDCR_TDCO_MASK		GENMASK(14, 8)
+#define TDCR_TDCF_MASK		GENMASK(6, 0)
 
 /* Test Register (TEST) */
 #define TEST_LBCK		BIT(4)
 
-/* CC Control Register(CCCR) */
-#define CCCR_CMR_MASK		0x3
-#define CCCR_CMR_SHIFT		10
-#define CCCR_CMR_CANFD		0x1
-#define CCCR_CMR_CANFD_BRS	0x2
-#define CCCR_CMR_CAN		0x3
-#define CCCR_CME_MASK		0x3
-#define CCCR_CME_SHIFT		8
-#define CCCR_CME_CAN		0
-#define CCCR_CME_CANFD		0x1
-#define CCCR_CME_CANFD_BRS	0x2
+/* CC Control Register (CCCR) */
 #define CCCR_TXP		BIT(14)
 #define CCCR_TEST		BIT(7)
 #define CCCR_DAR		BIT(6)
@@ -130,24 +111,31 @@ enum m_can_reg {
 #define CCCR_ASM		BIT(2)
 #define CCCR_CCE		BIT(1)
 #define CCCR_INIT		BIT(0)
-#define CCCR_CANFD		0x10
+/* for version 3.0.x */
+#define CCCR_CMR_MASK		GENMASK(11, 10)
+#define CCCR_CMR_CANFD		0x1
+#define CCCR_CMR_CANFD_BRS	0x2
+#define CCCR_CMR_CAN		0x3
+#define CCCR_CME_MASK		GENMASK(9, 8)
+#define CCCR_CME_CAN		0
+#define CCCR_CME_CANFD		0x1
+#define CCCR_CME_CANFD_BRS	0x2
 /* for version >=3.1.x */
 #define CCCR_EFBI		BIT(13)
 #define CCCR_PXHD		BIT(12)
 #define CCCR_BRSE		BIT(9)
 #define CCCR_FDOE		BIT(8)
-/* only for version >=3.2.x */
+/* for version >=3.2.x */
 #define CCCR_NISO		BIT(15)
+/* for version >=3.3.x */
+#define CCCR_WMM		BIT(11)
+#define CCCR_UTSU		BIT(10)
 
 /* Nominal Bit Timing & Prescaler Register (NBTP) */
-#define NBTP_NSJW_SHIFT		25
-#define NBTP_NSJW_MASK		(0x7f << NBTP_NSJW_SHIFT)
-#define NBTP_NBRP_SHIFT		16
-#define NBTP_NBRP_MASK		(0x1ff << NBTP_NBRP_SHIFT)
-#define NBTP_NTSEG1_SHIFT	8
-#define NBTP_NTSEG1_MASK	(0xff << NBTP_NTSEG1_SHIFT)
-#define NBTP_NTSEG2_SHIFT	0
-#define NBTP_NTSEG2_MASK	(0x7f << NBTP_NTSEG2_SHIFT)
+#define NBTP_NSJW_MASK		GENMASK(31, 25)
+#define NBTP_NBRP_MASK		GENMASK(24, 16)
+#define NBTP_NTSEG1_MASK	GENMASK(15, 8)
+#define NBTP_NTSEG2_MASK	GENMASK(6, 0)
 
 /* Timestamp Counter Configuration Register (TSCC) */
 #define TSCC_TCP_MASK		GENMASK(19, 16)
@@ -159,20 +147,18 @@ enum m_can_reg {
 /* Timestamp Counter Value Register (TSCV) */
 #define TSCV_TSC_MASK		GENMASK(15, 0)
 
-/* Error Counter Register(ECR) */
+/* Error Counter Register (ECR) */
 #define ECR_RP			BIT(15)
-#define ECR_REC_SHIFT		8
-#define ECR_REC_MASK		(0x7f << ECR_REC_SHIFT)
-#define ECR_TEC_SHIFT		0
-#define ECR_TEC_MASK		0xff
+#define ECR_REC_MASK		GENMASK(14, 8)
+#define ECR_TEC_MASK		GENMASK(7, 0)
 
-/* Protocol Status Register(PSR) */
+/* Protocol Status Register (PSR) */
 #define PSR_BO		BIT(7)
 #define PSR_EW		BIT(6)
 #define PSR_EP		BIT(5)
-#define PSR_LEC_MASK	0x7
+#define PSR_LEC_MASK	GENMASK(2, 0)
 
-/* Interrupt Register(IR) */
+/* Interrupt Register (IR) */
 #define IR_ALL_INT	0xffffffff
 
 /* Renamed bits for versions > 3.1.x */
@@ -221,6 +207,7 @@ enum m_can_reg {
 			 IR_BEC | IR_TOO | IR_MRAF | IR_TSW | IR_TEFL | \
 			 IR_RF1L | IR_RF0L)
 #define IR_ERR_ALL_30X	(IR_ERR_STATE | IR_ERR_BUS_30X)
+
 /* Interrupts for version >= 3.1.x */
 #define IR_ERR_LEC_31X	(IR_PED | IR_PEA)
 #define IR_ERR_BUS_31X      (IR_ERR_LEC_31X | IR_WDI | IR_ELO | IR_BEU | \
@@ -237,58 +224,47 @@ enum m_can_reg {
 #define ILE_EINT0	BIT(0)
 
 /* Rx FIFO 0/1 Configuration (RXF0C/RXF1C) */
-#define RXFC_FWM_SHIFT	24
-#define RXFC_FWM_MASK	(0x7f << RXFC_FWM_SHIFT)
-#define RXFC_FS_SHIFT	16
-#define RXFC_FS_MASK	(0x7f << RXFC_FS_SHIFT)
+#define RXFC_FWM_MASK	GENMASK(30, 24)
+#define RXFC_FS_MASK	GENMASK(22, 16)
 
 /* Rx FIFO 0/1 Status (RXF0S/RXF1S) */
 #define RXFS_RFL	BIT(25)
 #define RXFS_FF		BIT(24)
-#define RXFS_FPI_SHIFT	16
-#define RXFS_FPI_MASK	0x3f0000
-#define RXFS_FGI_SHIFT	8
-#define RXFS_FGI_MASK	0x3f00
-#define RXFS_FFL_MASK	0x7f
+#define RXFS_FPI_MASK	GENMASK(21, 16)
+#define RXFS_FGI_MASK	GENMASK(13, 8)
+#define RXFS_FFL_MASK	GENMASK(6, 0)
 
 /* Rx Buffer / FIFO Element Size Configuration (RXESC) */
-#define M_CAN_RXESC_8BYTES	0x0
-#define M_CAN_RXESC_64BYTES	0x777
+#define RXESC_RBDS_MASK		GENMASK(10, 8)
+#define RXESC_F1DS_MASK		GENMASK(6, 4)
+#define RXESC_F0DS_MASK		GENMASK(2, 0)
+#define RXESC_64B		0x7
 
-/* Tx Buffer Configuration(TXBC) */
-#define TXBC_NDTB_SHIFT		16
-#define TXBC_NDTB_MASK		(0x3f << TXBC_NDTB_SHIFT)
-#define TXBC_TFQS_SHIFT		24
-#define TXBC_TFQS_MASK		(0x3f << TXBC_TFQS_SHIFT)
+/* Tx Buffer Configuration (TXBC) */
+#define TXBC_TFQS_MASK		GENMASK(29, 24)
+#define TXBC_NDTB_MASK		GENMASK(21, 16)
 
 /* Tx FIFO/Queue Status (TXFQS) */
 #define TXFQS_TFQF		BIT(21)
-#define TXFQS_TFQPI_SHIFT	16
-#define TXFQS_TFQPI_MASK	(0x1f << TXFQS_TFQPI_SHIFT)
-#define TXFQS_TFGI_SHIFT	8
-#define TXFQS_TFGI_MASK		(0x1f << TXFQS_TFGI_SHIFT)
-#define TXFQS_TFFL_SHIFT	0
-#define TXFQS_TFFL_MASK		(0x3f << TXFQS_TFFL_SHIFT)
+#define TXFQS_TFQPI_MASK	GENMASK(20, 16)
+#define TXFQS_TFGI_MASK		GENMASK(12, 8)
+#define TXFQS_TFFL_MASK		GENMASK(5, 0)
 
-/* Tx Buffer Element Size Configuration(TXESC) */
-#define TXESC_TBDS_8BYTES	0x0
-#define TXESC_TBDS_64BYTES	0x7
+/* Tx Buffer Element Size Configuration (TXESC) */
+#define TXESC_TBDS_MASK		GENMASK(2, 0)
+#define TXESC_TBDS_64B		0x7
 
 /* Tx Event FIFO Configuration (TXEFC) */
-#define TXEFC_EFS_SHIFT		16
-#define TXEFC_EFS_MASK		(0x3f << TXEFC_EFS_SHIFT)
+#define TXEFC_EFS_MASK		GENMASK(21, 16)
 
 /* Tx Event FIFO Status (TXEFS) */
 #define TXEFS_TEFL		BIT(25)
 #define TXEFS_EFF		BIT(24)
-#define TXEFS_EFGI_SHIFT	8
-#define	TXEFS_EFGI_MASK		(0x1f << TXEFS_EFGI_SHIFT)
-#define TXEFS_EFFL_SHIFT	0
-#define TXEFS_EFFL_MASK		(0x3f << TXEFS_EFFL_SHIFT)
+#define TXEFS_EFGI_MASK		GENMASK(12, 8)
+#define TXEFS_EFFL_MASK		GENMASK(5, 0)
 
 /* Tx Event FIFO Acknowledge (TXEFA) */
-#define TXEFA_EFAI_SHIFT	0
-#define TXEFA_EFAI_MASK		(0x1f << TXEFA_EFAI_SHIFT)
+#define TXEFA_EFAI_MASK		GENMASK(4, 0)
 
 /* Message RAM Configuration (in bytes) */
 #define SIDF_ELEMENT_SIZE	4
@@ -324,13 +300,12 @@ enum m_can_reg {
 #define TX_BUF_EFC		BIT(23)
 #define TX_BUF_FDF		BIT(21)
 #define TX_BUF_BRS		BIT(20)
-#define TX_BUF_MM_SHIFT		24
-#define TX_BUF_MM_MASK		(0xff << TX_BUF_MM_SHIFT)
+#define TX_BUF_MM_MASK		GENMASK(31, 24)
+#define TX_BUF_DLC_MASK		GENMASK(19, 16)
 
 /* Tx event FIFO Element */
 /* E1 */
-#define TX_EVENT_MM_SHIFT	TX_BUF_MM_SHIFT
-#define TX_EVENT_MM_MASK	(0xff << TX_EVENT_MM_SHIFT)
+#define TX_EVENT_MM_MASK	GENMASK(31, 24)
 #define TX_EVENT_TXTS_MASK	GENMASK(15, 0)
 
 static inline u32 m_can_read(struct m_can_classdev *cdev, enum m_can_reg reg)
@@ -449,8 +424,8 @@ static void m_can_clean(struct net_device *net)
 
 		net->stats.tx_errors++;
 		if (cdev->version > 30)
-			putidx = ((m_can_read(cdev, M_CAN_TXFQS) &
-				   TXFQS_TFQPI_MASK) >> TXFQS_TFQPI_SHIFT);
+			putidx = FIELD_GET(TXFQS_TFQPI_MASK,
+					   m_can_read(cdev, M_CAN_TXFQS));
 
 		can_free_echo_skb(cdev->net, putidx, NULL);
 		cdev->tx_skb = NULL;
@@ -490,7 +465,7 @@ static void m_can_read_fifo(struct net_device *dev, u32 rxfs)
 	int i;
 
 	/* calculate the fifo get index for where to read data */
-	fgi = (rxfs & RXFS_FGI_MASK) >> RXFS_FGI_SHIFT;
+	fgi = FIELD_GET(RXFS_FGI_MASK, rxfs);
 	dlc = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_DLC);
 	if (dlc & RX_BUF_FDF)
 		skb = alloc_canfd_skb(dev, &cf);
@@ -663,8 +638,8 @@ static int __m_can_get_berr_counter(const struct net_device *dev,
 	unsigned int ecr;
 
 	ecr = m_can_read(cdev, M_CAN_ECR);
-	bec->rxerr = (ecr & ECR_REC_MASK) >> ECR_REC_SHIFT;
-	bec->txerr = (ecr & ECR_TEC_MASK) >> ECR_TEC_SHIFT;
+	bec->rxerr = FIELD_GET(ECR_REC_MASK, ecr);
+	bec->txerr = FIELD_GET(ECR_TEC_MASK, ecr);
 
 	return 0;
 }
@@ -1004,24 +979,23 @@ static void m_can_echo_tx_event(struct net_device *dev)
 	m_can_txefs = m_can_read(cdev, M_CAN_TXEFS);
 
 	/* Get Tx Event fifo element count */
-	txe_count = (m_can_txefs & TXEFS_EFFL_MASK) >> TXEFS_EFFL_SHIFT;
+	txe_count = FIELD_GET(TXEFS_EFFL_MASK, m_can_txefs);
 
 	/* Get and process all sent elements */
 	for (i = 0; i < txe_count; i++) {
 		u32 txe, timestamp = 0;
 
 		/* retrieve get index */
-		fgi = (m_can_read(cdev, M_CAN_TXEFS) & TXEFS_EFGI_MASK) >>
-			TXEFS_EFGI_SHIFT;
+		fgi = FIELD_GET(TXEFS_EFGI_MASK, m_can_read(cdev, M_CAN_TXEFS));
 
 		/* get message marker, timestamp */
 		txe = m_can_txe_fifo_read(cdev, fgi, 4);
-		msg_mark = (txe & TX_EVENT_MM_MASK) >> TX_EVENT_MM_SHIFT;
+		msg_mark = FIELD_GET(TX_EVENT_MM_MASK, txe);
 		timestamp = FIELD_GET(TX_EVENT_TXTS_MASK, txe);
 
 		/* ack txe element */
-		m_can_write(cdev, M_CAN_TXEFA, (TXEFA_EFAI_MASK &
-						(fgi << TXEFA_EFAI_SHIFT)));
+		m_can_write(cdev, M_CAN_TXEFA, FIELD_PREP(TXEFA_EFAI_MASK,
+							  fgi));
 
 		/* update stats */
 		m_can_tx_update_stats(cdev, msg_mark, timestamp);
@@ -1147,8 +1121,10 @@ static int m_can_set_bittiming(struct net_device *dev)
 	sjw = bt->sjw - 1;
 	tseg1 = bt->prop_seg + bt->phase_seg1 - 1;
 	tseg2 = bt->phase_seg2 - 1;
-	reg_btp = (brp << NBTP_NBRP_SHIFT) | (sjw << NBTP_NSJW_SHIFT) |
-		(tseg1 << NBTP_NTSEG1_SHIFT) | (tseg2 << NBTP_NTSEG2_SHIFT);
+	reg_btp = FIELD_PREP(NBTP_NBRP_MASK, brp) |
+		  FIELD_PREP(NBTP_NSJW_MASK, sjw) |
+		  FIELD_PREP(NBTP_NTSEG1_MASK, tseg1) |
+		  FIELD_PREP(NBTP_NTSEG2_MASK, tseg2);
 	m_can_write(cdev, M_CAN_NBTP, reg_btp);
 
 	if (cdev->can.ctrlmode & CAN_CTRLMODE_FD) {
@@ -1185,13 +1161,13 @@ static int m_can_set_bittiming(struct net_device *dev)
 
 			reg_btp |= DBTP_TDC;
 			m_can_write(cdev, M_CAN_TDCR,
-				    tdco << TDCR_TDCO_SHIFT);
+				    FIELD_PREP(TDCR_TDCO_MASK, tdco));
 		}
 
-		reg_btp |= (brp << DBTP_DBRP_SHIFT) |
-			(sjw << DBTP_DSJW_SHIFT) |
-			(tseg1 << DBTP_DTSEG1_SHIFT) |
-			(tseg2 << DBTP_DTSEG2_SHIFT);
+		reg_btp = FIELD_PREP(NBTP_NBRP_MASK, brp) |
+			  FIELD_PREP(NBTP_NSJW_MASK, sjw) |
+			  FIELD_PREP(NBTP_NTSEG1_MASK, tseg1) |
+			  FIELD_PREP(NBTP_NTSEG2_MASK, tseg2);
 
 		m_can_write(cdev, M_CAN_DBTP, reg_btp);
 	}
@@ -1217,44 +1193,50 @@ static void m_can_chip_config(struct net_device *dev)
 	m_can_config_endisable(cdev, true);
 
 	/* RX Buffer/FIFO Element Size 64 bytes data field */
-	m_can_write(cdev, M_CAN_RXESC, M_CAN_RXESC_64BYTES);
+	m_can_write(cdev, M_CAN_RXESC,
+		    FIELD_PREP(RXESC_RBDS_MASK, RXESC_64B) |
+		    FIELD_PREP(RXESC_F1DS_MASK, RXESC_64B) |
+		    FIELD_PREP(RXESC_F0DS_MASK, RXESC_64B));
 
 	/* Accept Non-matching Frames Into FIFO 0 */
 	m_can_write(cdev, M_CAN_GFC, 0x0);
 
 	if (cdev->version == 30) {
 		/* only support one Tx Buffer currently */
-		m_can_write(cdev, M_CAN_TXBC, (1 << TXBC_NDTB_SHIFT) |
+		m_can_write(cdev, M_CAN_TXBC, FIELD_PREP(TXBC_NDTB_MASK, 1) |
 			    cdev->mcfg[MRAM_TXB].off);
 	} else {
 		/* TX FIFO is used for newer IP Core versions */
 		m_can_write(cdev, M_CAN_TXBC,
-			    (cdev->mcfg[MRAM_TXB].num << TXBC_TFQS_SHIFT) |
-			    (cdev->mcfg[MRAM_TXB].off));
+			    FIELD_PREP(TXBC_TFQS_MASK,
+				       cdev->mcfg[MRAM_TXB].num) |
+			    cdev->mcfg[MRAM_TXB].off);
 	}
 
 	/* support 64 bytes payload */
-	m_can_write(cdev, M_CAN_TXESC, TXESC_TBDS_64BYTES);
+	m_can_write(cdev, M_CAN_TXESC,
+		    FIELD_PREP(TXESC_TBDS_MASK, TXESC_TBDS_64B));
 
 	/* TX Event FIFO */
 	if (cdev->version == 30) {
-		m_can_write(cdev, M_CAN_TXEFC, (1 << TXEFC_EFS_SHIFT) |
+		m_can_write(cdev, M_CAN_TXEFC,
+			    FIELD_PREP(TXEFC_EFS_MASK, 1) |
 			    cdev->mcfg[MRAM_TXE].off);
 	} else {
 		/* Full TX Event FIFO is used */
 		m_can_write(cdev, M_CAN_TXEFC,
-			    ((cdev->mcfg[MRAM_TXE].num << TXEFC_EFS_SHIFT)
-			     & TXEFC_EFS_MASK) |
+			    FIELD_PREP(TXEFC_EFS_MASK,
+				       cdev->mcfg[MRAM_TXE].num) |
 			    cdev->mcfg[MRAM_TXE].off);
 	}
 
 	/* rx fifo configuration, blocking mode, fifo size 1 */
 	m_can_write(cdev, M_CAN_RXF0C,
-		    (cdev->mcfg[MRAM_RXF0].num << RXFC_FS_SHIFT) |
+		    FIELD_PREP(RXFC_FS_MASK, cdev->mcfg[MRAM_RXF0].num) |
 		    cdev->mcfg[MRAM_RXF0].off);
 
 	m_can_write(cdev, M_CAN_RXF1C,
-		    (cdev->mcfg[MRAM_RXF1].num << RXFC_FS_SHIFT) |
+		    FIELD_PREP(RXFC_FS_MASK, cdev->mcfg[MRAM_RXF1].num) |
 		    cdev->mcfg[MRAM_RXF1].off);
 
 	cccr = m_can_read(cdev, M_CAN_CCCR);
@@ -1264,11 +1246,11 @@ static void m_can_chip_config(struct net_device *dev)
 		/* Version 3.0.x */
 
 		cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_DAR |
-			  (CCCR_CMR_MASK << CCCR_CMR_SHIFT) |
-			  (CCCR_CME_MASK << CCCR_CME_SHIFT));
+			  FIELD_PREP(CCCR_CMR_MASK, FIELD_MAX(CCCR_CMR_MASK)) |
+			  FIELD_PREP(CCCR_CME_MASK, FIELD_MAX(CCCR_CME_MASK)));
 
 		if (cdev->can.ctrlmode & CAN_CTRLMODE_FD)
-			cccr |= CCCR_CME_CANFD_BRS << CCCR_CME_SHIFT;
+			cccr |= FIELD_PREP(CCCR_CME_MASK, CCCR_CME_CANFD_BRS);
 
 	} else {
 		/* Version 3.1.x or 3.2.x */
@@ -1372,8 +1354,8 @@ static int m_can_check_core_release(struct m_can_classdev *cdev)
 	 * Example: Version 3.2.1 => rel = 3; step = 2; substep = 1;
 	 */
 	crel_reg = m_can_read(cdev, M_CAN_CREL);
-	rel = (u8)((crel_reg & CREL_REL_MASK) >> CREL_REL_SHIFT);
-	step = (u8)((crel_reg & CREL_STEP_MASK) >> CREL_STEP_SHIFT);
+	rel = (u8)FIELD_GET(CREL_REL_MASK, crel_reg);
+	step = (u8)FIELD_GET(CREL_STEP_MASK, crel_reg);
 
 	if (rel == 3) {
 		/* M_CAN v3.x.y: create return value */
@@ -1593,16 +1575,16 @@ static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev)
 
 		if (cdev->can.ctrlmode & CAN_CTRLMODE_FD) {
 			cccr = m_can_read(cdev, M_CAN_CCCR);
-			cccr &= ~(CCCR_CMR_MASK << CCCR_CMR_SHIFT);
+			cccr &= ~CCCR_CMR_MASK;
 			if (can_is_canfd_skb(skb)) {
 				if (cf->flags & CANFD_BRS)
-					cccr |= CCCR_CMR_CANFD_BRS <<
-						CCCR_CMR_SHIFT;
+					cccr |= FIELD_PREP(CCCR_CMR_MASK,
+							   CCCR_CMR_CANFD_BRS);
 				else
-					cccr |= CCCR_CMR_CANFD <<
-						CCCR_CMR_SHIFT;
+					cccr |= FIELD_PREP(CCCR_CMR_MASK,
+							   CCCR_CMR_CANFD);
 			} else {
-				cccr |= CCCR_CMR_CAN << CCCR_CMR_SHIFT;
+				cccr |= FIELD_PREP(CCCR_CMR_MASK, CCCR_CMR_CAN);
 			}
 			m_can_write(cdev, M_CAN_CCCR, cccr);
 		}
@@ -1629,8 +1611,8 @@ static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev)
 		}
 
 		/* get put index for frame */
-		putidx = ((m_can_read(cdev, M_CAN_TXFQS) & TXFQS_TFQPI_MASK)
-			  >> TXFQS_TFQPI_SHIFT);
+		putidx = FIELD_GET(TXFQS_TFQPI_MASK,
+				   m_can_read(cdev, M_CAN_TXFQS));
 		/* Write ID Field to FIFO Element */
 		m_can_fifo_write(cdev, putidx, M_CAN_FIFO_ID, id);
 
@@ -1648,9 +1630,9 @@ static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev)
 		 * sending the correct echo frame
 		 */
 		m_can_fifo_write(cdev, putidx, M_CAN_FIFO_DLC,
-				 ((putidx << TX_BUF_MM_SHIFT) &
-				  TX_BUF_MM_MASK) |
-				 (can_fd_len2dlc(cf->len) << 16) |
+				 FIELD_PREP(TX_BUF_MM_MASK, putidx) |
+				 FIELD_PREP(TX_BUF_DLC_MASK,
+					    can_fd_len2dlc(cf->len)) |
 				 fdflags | TX_BUF_EFC);
 
 		for (i = 0; i < cf->len; i += 4)
@@ -1810,11 +1792,11 @@ static void m_can_of_parse_mram(struct m_can_classdev *cdev,
 	cdev->mcfg[MRAM_RXF0].off = cdev->mcfg[MRAM_XIDF].off +
 		cdev->mcfg[MRAM_XIDF].num * XIDF_ELEMENT_SIZE;
 	cdev->mcfg[MRAM_RXF0].num = mram_config_vals[3] &
-		(RXFC_FS_MASK >> RXFC_FS_SHIFT);
+		FIELD_MAX(RXFC_FS_MASK);
 	cdev->mcfg[MRAM_RXF1].off = cdev->mcfg[MRAM_RXF0].off +
 		cdev->mcfg[MRAM_RXF0].num * RXF0_ELEMENT_SIZE;
 	cdev->mcfg[MRAM_RXF1].num = mram_config_vals[4] &
-		(RXFC_FS_MASK >> RXFC_FS_SHIFT);
+		FIELD_MAX(RXFC_FS_MASK);
 	cdev->mcfg[MRAM_RXB].off = cdev->mcfg[MRAM_RXF1].off +
 		cdev->mcfg[MRAM_RXF1].num * RXF1_ELEMENT_SIZE;
 	cdev->mcfg[MRAM_RXB].num = mram_config_vals[5];
@@ -1824,7 +1806,7 @@ static void m_can_of_parse_mram(struct m_can_classdev *cdev,
 	cdev->mcfg[MRAM_TXB].off = cdev->mcfg[MRAM_TXE].off +
 		cdev->mcfg[MRAM_TXE].num * TXE_ELEMENT_SIZE;
 	cdev->mcfg[MRAM_TXB].num = mram_config_vals[7] &
-		(TXBC_NDTB_MASK >> TXBC_NDTB_SHIFT);
+		FIELD_MAX(TXBC_NDTB_MASK);
 
 	dev_dbg(cdev->dev,
 		"sidf 0x%x %d xidf 0x%x %d rxf0 0x%x %d rxf1 0x%x %d rxb 0x%x %d txe 0x%x %d txb 0x%x %d\n",
diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c
index c44f3411e561..cfc1325aad10 100644
--- a/drivers/net/can/softing/softing_main.c
+++ b/drivers/net/can/softing/softing_main.c
@@ -239,7 +239,6 @@ static int softing_handle_1(struct softing *card)
 				DPRAM_INFO_BUSSTATE2 : DPRAM_INFO_BUSSTATE]);
 		/* timestamp */
 		tmp_u32 = le32_to_cpup((void *)ptr);
-		ptr += 4;
 		ktime = softing_raw2ktime(card, tmp_u32);
 
 		++netdev->stats.rx_errors;
@@ -276,7 +275,6 @@ static int softing_handle_1(struct softing *card)
 		ktime = softing_raw2ktime(card, tmp_u32);
 		if (!(msg.can_id & CAN_RTR_FLAG))
 			memcpy(&msg.data[0], ptr, 8);
-		ptr += 8;
 		/* update socket */
 		if (cmd & CMD_ACK) {
 			/* acknowledge, was tx msg */
diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c
index 6f5d6d04a8b9..dd17b8c53e1c 100644
--- a/drivers/net/can/spi/hi311x.c
+++ b/drivers/net/can/spi/hi311x.c
@@ -871,7 +871,7 @@ static int hi3110_can_probe(struct spi_device *spi)
 		CAN_CTRLMODE_BERR_REPORTING;
 
 	if (of_id)
-		priv->model = (enum hi3110_model)of_id->data;
+		priv->model = (enum hi3110_model)(uintptr_t)of_id->data;
 	else
 		priv->model = spi_get_device_id(spi)->driver_data;
 	priv->net = net;
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index 173c6614086f..0579ab74f728 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -1330,7 +1330,7 @@ static int mcp251x_can_probe(struct spi_device *spi)
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES |
 		CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY;
 	if (match)
-		priv->model = (enum mcp251x_model)match;
+		priv->model = (enum mcp251x_model)(uintptr_t)match;
 	else
 		priv->model = spi_get_device_id(spi)->driver_data;
 	priv->net = net;
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index e0ae00e34c7b..47c3f408a799 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -560,7 +560,7 @@ mcp251xfd_chip_set_mode(const struct mcp251xfd_priv *priv,
 	return __mcp251xfd_chip_set_mode(priv, mode_req, false);
 }
 
-static inline int
+static inline int __maybe_unused
 mcp251xfd_chip_set_mode_nowait(const struct mcp251xfd_priv *priv,
 			       const u8 mode_req)
 {
diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig
index 3deb9f1cd292..f959215c9d53 100644
--- a/drivers/net/can/usb/Kconfig
+++ b/drivers/net/can/usb/Kconfig
@@ -76,7 +76,9 @@ config CAN_KVASER_USB
 	    - Scania VCI2 (if you have the Kvaser logo on top)
 	    - Kvaser BlackBird v2
 	    - Kvaser Leaf Pro HS v2
+	    - Kvaser Hybrid CAN/LIN
 	    - Kvaser Hybrid 2xCAN/LIN
+	    - Kvaser Hybrid Pro CAN/LIN
 	    - Kvaser Hybrid Pro 2xCAN/LIN
 	    - Kvaser Memorator 2xHS v2
 	    - Kvaser Memorator Pro 2xHS v2
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
index 90ebcae13409..0cc0fc866a2a 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -79,16 +79,18 @@
 #define USB_USBCAN_PRO_2HS_V2_PRODUCT_ID	264
 #define USB_MEMO_2HS_PRODUCT_ID			265
 #define USB_MEMO_PRO_2HS_V2_PRODUCT_ID		266
-#define USB_HYBRID_CANLIN_PRODUCT_ID		267
+#define USB_HYBRID_2CANLIN_PRODUCT_ID		267
 #define USB_ATI_USBCAN_PRO_2HS_V2_PRODUCT_ID	268
 #define USB_ATI_MEMO_PRO_2HS_V2_PRODUCT_ID	269
-#define USB_HYBRID_PRO_CANLIN_PRODUCT_ID	270
+#define USB_HYBRID_PRO_2CANLIN_PRODUCT_ID	270
 #define USB_U100_PRODUCT_ID			273
 #define USB_U100P_PRODUCT_ID			274
 #define USB_U100S_PRODUCT_ID			275
 #define USB_USBCAN_PRO_4HS_PRODUCT_ID		276
+#define USB_HYBRID_CANLIN_PRODUCT_ID		277
+#define USB_HYBRID_PRO_CANLIN_PRODUCT_ID	278
 #define USB_HYDRA_PRODUCT_ID_END \
-	USB_USBCAN_PRO_4HS_PRODUCT_ID
+	USB_HYBRID_PRO_CANLIN_PRODUCT_ID
 
 static inline bool kvaser_is_leaf(const struct usb_device_id *id)
 {
@@ -187,14 +189,16 @@ static const struct usb_device_id kvaser_usb_table[] = {
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_2HS_V2_PRODUCT_ID) },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_2HS_PRODUCT_ID) },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_PRO_2HS_V2_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_CANLIN_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_2CANLIN_PRODUCT_ID) },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_ATI_USBCAN_PRO_2HS_V2_PRODUCT_ID) },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_ATI_MEMO_PRO_2HS_V2_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_PRO_CANLIN_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_PRO_2CANLIN_PRODUCT_ID) },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_U100_PRODUCT_ID) },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_U100P_PRODUCT_ID) },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_U100S_PRODUCT_ID) },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_4HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_CANLIN_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_PRO_CANLIN_PRODUCT_ID) },
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, kvaser_usb_table);
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 3ca6b394dd5f..6e199454e41d 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1084,6 +1084,11 @@ static int b53_setup(struct dsa_switch *ds)
 	unsigned int port;
 	int ret;
 
+	/* Request bridge PVID untagged when DSA_TAG_PROTO_NONE is set
+	 * which forces the CPU port to be tagged in all VLANs.
+	 */
+	ds->untag_bridge_pvid = dev->tag_protocol == DSA_TAG_PROTO_NONE;
+
 	ret = b53_reset_switch(dev);
 	if (ret) {
 		dev_err(ds->dev, "failed to reset switch\n");
@@ -1455,6 +1460,13 @@ static int b53_vlan_prepare(struct dsa_switch *ds, int port,
 	return 0;
 }
 
+static bool b53_vlan_port_needs_forced_tagged(struct dsa_switch *ds, int port)
+{
+	struct b53_device *dev = ds->priv;
+
+	return dev->tag_protocol == DSA_TAG_PROTO_NONE && dsa_is_cpu_port(ds, port);
+}
+
 int b53_vlan_add(struct dsa_switch *ds, int port,
 		 const struct switchdev_obj_port_vlan *vlan,
 		 struct netlink_ext_ack *extack)
@@ -1477,7 +1489,7 @@ int b53_vlan_add(struct dsa_switch *ds, int port,
 		untagged = true;
 
 	vl->members |= BIT(port);
-	if (untagged && !dsa_is_cpu_port(ds, port))
+	if (untagged && !b53_vlan_port_needs_forced_tagged(ds, port))
 		vl->untag |= BIT(port);
 	else
 		vl->untag &= ~BIT(port);
@@ -1514,7 +1526,7 @@ int b53_vlan_del(struct dsa_switch *ds, int port,
 	if (pvid == vlan->vid)
 		pvid = b53_default_pvid(dev);
 
-	if (untagged && !dsa_is_cpu_port(ds, port))
+	if (untagged && !b53_vlan_port_needs_forced_tagged(ds, port))
 		vl->untag &= ~(BIT(port));
 
 	b53_set_vlan_entry(dev, vlan->vid, vl);
@@ -2660,7 +2672,6 @@ struct b53_device *b53_switch_alloc(struct device *base,
 	dev->priv = priv;
 	dev->ops = ops;
 	ds->ops = &b53_switch_ops;
-	ds->untag_bridge_pvid = true;
 	dev->vlan_enabled = true;
 	/* Let DSA handle the case were multiple bridges span the same switch
 	 * device and different VLAN awareness settings are requested, which
diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c
index aaa12d73784e..3f4249de70c5 100644
--- a/drivers/net/dsa/b53/b53_srab.c
+++ b/drivers/net/dsa/b53/b53_srab.c
@@ -632,8 +632,7 @@ static int b53_srab_remove(struct platform_device *pdev)
 	struct b53_srab_priv *priv = dev->priv;
 
 	b53_srab_intr_set(priv, false);
-	if (dev)
-		b53_switch_remove(dev);
+	b53_switch_remove(dev);
 
 	return 0;
 }
diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c
index 4d78219da253..9fdcc4bde480 100644
--- a/drivers/net/dsa/hirschmann/hellcreek.c
+++ b/drivers/net/dsa/hirschmann/hellcreek.c
@@ -927,7 +927,6 @@ static int hellcreek_fdb_dump(struct dsa_switch *ds, int port,
 
 	/* Read table */
 	for (i = 0; i < hellcreek->fdb_entries; ++i) {
-		unsigned char null_addr[ETH_ALEN] = { 0 };
 		struct hellcreek_fdb_entry entry = { 0 };
 
 		/* Read entry */
@@ -937,7 +936,7 @@ static int hellcreek_fdb_dump(struct dsa_switch *ds, int port,
 		hellcreek_write(hellcreek, 0x00, HR_FDBRDH);
 
 		/* Check valid */
-		if (!memcmp(entry.mac, null_addr, ETH_ALEN))
+		if (is_zero_ether_addr(entry.mac))
 			continue;
 
 		/* Check port mask */
diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index ad509a57a945..560f6843bb65 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -6,6 +6,7 @@
  *	Tristram Ha <Tristram.Ha@microchip.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/gpio.h>
@@ -15,8 +16,10 @@
 #include <linux/phy.h>
 #include <linux/etherdevice.h>
 #include <linux/if_bridge.h>
+#include <linux/micrel_phy.h>
 #include <net/dsa.h>
 #include <net/switchdev.h>
+#include <linux/phylink.h>
 
 #include "ksz_common.h"
 #include "ksz8795_reg.h"
@@ -727,92 +730,114 @@ static void ksz8_r_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 *val)
 	u8 restart, speed, ctrl, link;
 	const u8 *regs = ksz8->regs;
 	int processed = true;
+	u8 val1, val2;
 	u16 data = 0;
 	u8 p = phy;
 
 	switch (reg) {
-	case PHY_REG_CTRL:
+	case MII_BMCR:
 		ksz_pread8(dev, p, regs[P_NEG_RESTART_CTRL], &restart);
 		ksz_pread8(dev, p, regs[P_SPEED_STATUS], &speed);
 		ksz_pread8(dev, p, regs[P_FORCE_CTRL], &ctrl);
 		if (restart & PORT_PHY_LOOPBACK)
-			data |= PHY_LOOPBACK;
+			data |= BMCR_LOOPBACK;
 		if (ctrl & PORT_FORCE_100_MBIT)
-			data |= PHY_SPEED_100MBIT;
+			data |= BMCR_SPEED100;
 		if (ksz_is_ksz88x3(dev)) {
 			if ((ctrl & PORT_AUTO_NEG_ENABLE))
-				data |= PHY_AUTO_NEG_ENABLE;
+				data |= BMCR_ANENABLE;
 		} else {
 			if (!(ctrl & PORT_AUTO_NEG_DISABLE))
-				data |= PHY_AUTO_NEG_ENABLE;
+				data |= BMCR_ANENABLE;
 		}
 		if (restart & PORT_POWER_DOWN)
-			data |= PHY_POWER_DOWN;
+			data |= BMCR_PDOWN;
 		if (restart & PORT_AUTO_NEG_RESTART)
-			data |= PHY_AUTO_NEG_RESTART;
+			data |= BMCR_ANRESTART;
 		if (ctrl & PORT_FORCE_FULL_DUPLEX)
-			data |= PHY_FULL_DUPLEX;
+			data |= BMCR_FULLDPLX;
 		if (speed & PORT_HP_MDIX)
-			data |= PHY_HP_MDIX;
+			data |= KSZ886X_BMCR_HP_MDIX;
 		if (restart & PORT_FORCE_MDIX)
-			data |= PHY_FORCE_MDIX;
+			data |= KSZ886X_BMCR_FORCE_MDI;
 		if (restart & PORT_AUTO_MDIX_DISABLE)
-			data |= PHY_AUTO_MDIX_DISABLE;
+			data |= KSZ886X_BMCR_DISABLE_AUTO_MDIX;
 		if (restart & PORT_TX_DISABLE)
-			data |= PHY_TRANSMIT_DISABLE;
+			data |= KSZ886X_BMCR_DISABLE_TRANSMIT;
 		if (restart & PORT_LED_OFF)
-			data |= PHY_LED_DISABLE;
+			data |= KSZ886X_BMCR_DISABLE_LED;
 		break;
-	case PHY_REG_STATUS:
+	case MII_BMSR:
 		ksz_pread8(dev, p, regs[P_LINK_STATUS], &link);
-		data = PHY_100BTX_FD_CAPABLE |
-		       PHY_100BTX_CAPABLE |
-		       PHY_10BT_FD_CAPABLE |
-		       PHY_10BT_CAPABLE |
-		       PHY_AUTO_NEG_CAPABLE;
+		data = BMSR_100FULL |
+		       BMSR_100HALF |
+		       BMSR_10FULL |
+		       BMSR_10HALF |
+		       BMSR_ANEGCAPABLE;
 		if (link & PORT_AUTO_NEG_COMPLETE)
-			data |= PHY_AUTO_NEG_ACKNOWLEDGE;
+			data |= BMSR_ANEGCOMPLETE;
 		if (link & PORT_STAT_LINK_GOOD)
-			data |= PHY_LINK_STATUS;
+			data |= BMSR_LSTATUS;
 		break;
-	case PHY_REG_ID_1:
+	case MII_PHYSID1:
 		data = KSZ8795_ID_HI;
 		break;
-	case PHY_REG_ID_2:
+	case MII_PHYSID2:
 		if (ksz_is_ksz88x3(dev))
 			data = KSZ8863_ID_LO;
 		else
 			data = KSZ8795_ID_LO;
 		break;
-	case PHY_REG_AUTO_NEGOTIATION:
+	case MII_ADVERTISE:
 		ksz_pread8(dev, p, regs[P_LOCAL_CTRL], &ctrl);
-		data = PHY_AUTO_NEG_802_3;
+		data = ADVERTISE_CSMA;
 		if (ctrl & PORT_AUTO_NEG_SYM_PAUSE)
-			data |= PHY_AUTO_NEG_SYM_PAUSE;
+			data |= ADVERTISE_PAUSE_CAP;
 		if (ctrl & PORT_AUTO_NEG_100BTX_FD)
-			data |= PHY_AUTO_NEG_100BTX_FD;
+			data |= ADVERTISE_100FULL;
 		if (ctrl & PORT_AUTO_NEG_100BTX)
-			data |= PHY_AUTO_NEG_100BTX;
+			data |= ADVERTISE_100HALF;
 		if (ctrl & PORT_AUTO_NEG_10BT_FD)
-			data |= PHY_AUTO_NEG_10BT_FD;
+			data |= ADVERTISE_10FULL;
 		if (ctrl & PORT_AUTO_NEG_10BT)
-			data |= PHY_AUTO_NEG_10BT;
+			data |= ADVERTISE_10HALF;
 		break;
-	case PHY_REG_REMOTE_CAPABILITY:
+	case MII_LPA:
 		ksz_pread8(dev, p, regs[P_REMOTE_STATUS], &link);
-		data = PHY_AUTO_NEG_802_3;
+		data = LPA_SLCT;
 		if (link & PORT_REMOTE_SYM_PAUSE)
-			data |= PHY_AUTO_NEG_SYM_PAUSE;
+			data |= LPA_PAUSE_CAP;
 		if (link & PORT_REMOTE_100BTX_FD)
-			data |= PHY_AUTO_NEG_100BTX_FD;
+			data |= LPA_100FULL;
 		if (link & PORT_REMOTE_100BTX)
-			data |= PHY_AUTO_NEG_100BTX;
+			data |= LPA_100HALF;
 		if (link & PORT_REMOTE_10BT_FD)
-			data |= PHY_AUTO_NEG_10BT_FD;
+			data |= LPA_10FULL;
 		if (link & PORT_REMOTE_10BT)
-			data |= PHY_AUTO_NEG_10BT;
-		if (data & ~PHY_AUTO_NEG_802_3)
-			data |= PHY_REMOTE_ACKNOWLEDGE_NOT;
+			data |= LPA_10HALF;
+		if (data & ~LPA_SLCT)
+			data |= LPA_LPACK;
+		break;
+	case PHY_REG_LINK_MD:
+		ksz_pread8(dev, p, REG_PORT_LINK_MD_CTRL, &val1);
+		ksz_pread8(dev, p, REG_PORT_LINK_MD_RESULT, &val2);
+		if (val1 & PORT_START_CABLE_DIAG)
+			data |= PHY_START_CABLE_DIAG;
+
+		if (val1 & PORT_CABLE_10M_SHORT)
+			data |= PHY_CABLE_10M_SHORT;
+
+		data |= FIELD_PREP(PHY_CABLE_DIAG_RESULT_M,
+				FIELD_GET(PORT_CABLE_DIAG_RESULT_M, val1));
+
+		data |= FIELD_PREP(PHY_CABLE_FAULT_COUNTER_M,
+				(FIELD_GET(PORT_CABLE_FAULT_COUNTER_H, val1) << 8) |
+				FIELD_GET(PORT_CABLE_FAULT_COUNTER_L, val2));
+		break;
+	case PHY_REG_PHY_CTRL:
+		ksz_pread8(dev, p, regs[P_LINK_STATUS], &link);
+		if (link & PORT_MDIX_STATUS)
+			data |= KSZ886X_CTRL_MDIX_STAT;
 		break;
 	default:
 		processed = false;
@@ -830,14 +855,14 @@ static void ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val)
 	u8 p = phy;
 
 	switch (reg) {
-	case PHY_REG_CTRL:
+	case MII_BMCR:
 
 		/* Do not support PHY reset function. */
-		if (val & PHY_RESET)
+		if (val & BMCR_RESET)
 			break;
 		ksz_pread8(dev, p, regs[P_SPEED_STATUS], &speed);
 		data = speed;
-		if (val & PHY_HP_MDIX)
+		if (val & KSZ886X_BMCR_HP_MDIX)
 			data |= PORT_HP_MDIX;
 		else
 			data &= ~PORT_HP_MDIX;
@@ -846,12 +871,12 @@ static void ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val)
 		ksz_pread8(dev, p, regs[P_FORCE_CTRL], &ctrl);
 		data = ctrl;
 		if (ksz_is_ksz88x3(dev)) {
-			if ((val & PHY_AUTO_NEG_ENABLE))
+			if ((val & BMCR_ANENABLE))
 				data |= PORT_AUTO_NEG_ENABLE;
 			else
 				data &= ~PORT_AUTO_NEG_ENABLE;
 		} else {
-			if (!(val & PHY_AUTO_NEG_ENABLE))
+			if (!(val & BMCR_ANENABLE))
 				data |= PORT_AUTO_NEG_DISABLE;
 			else
 				data &= ~PORT_AUTO_NEG_DISABLE;
@@ -861,11 +886,11 @@ static void ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val)
 				data |= PORT_AUTO_NEG_DISABLE;
 		}
 
-		if (val & PHY_SPEED_100MBIT)
+		if (val & BMCR_SPEED100)
 			data |= PORT_FORCE_100_MBIT;
 		else
 			data &= ~PORT_FORCE_100_MBIT;
-		if (val & PHY_FULL_DUPLEX)
+		if (val & BMCR_FULLDPLX)
 			data |= PORT_FORCE_FULL_DUPLEX;
 		else
 			data &= ~PORT_FORCE_FULL_DUPLEX;
@@ -873,38 +898,38 @@ static void ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val)
 			ksz_pwrite8(dev, p, regs[P_FORCE_CTRL], data);
 		ksz_pread8(dev, p, regs[P_NEG_RESTART_CTRL], &restart);
 		data = restart;
-		if (val & PHY_LED_DISABLE)
+		if (val & KSZ886X_BMCR_DISABLE_LED)
 			data |= PORT_LED_OFF;
 		else
 			data &= ~PORT_LED_OFF;
-		if (val & PHY_TRANSMIT_DISABLE)
+		if (val & KSZ886X_BMCR_DISABLE_TRANSMIT)
 			data |= PORT_TX_DISABLE;
 		else
 			data &= ~PORT_TX_DISABLE;
-		if (val & PHY_AUTO_NEG_RESTART)
+		if (val & BMCR_ANRESTART)
 			data |= PORT_AUTO_NEG_RESTART;
 		else
 			data &= ~(PORT_AUTO_NEG_RESTART);
-		if (val & PHY_POWER_DOWN)
+		if (val & BMCR_PDOWN)
 			data |= PORT_POWER_DOWN;
 		else
 			data &= ~PORT_POWER_DOWN;
-		if (val & PHY_AUTO_MDIX_DISABLE)
+		if (val & KSZ886X_BMCR_DISABLE_AUTO_MDIX)
 			data |= PORT_AUTO_MDIX_DISABLE;
 		else
 			data &= ~PORT_AUTO_MDIX_DISABLE;
-		if (val & PHY_FORCE_MDIX)
+		if (val & KSZ886X_BMCR_FORCE_MDI)
 			data |= PORT_FORCE_MDIX;
 		else
 			data &= ~PORT_FORCE_MDIX;
-		if (val & PHY_LOOPBACK)
+		if (val & BMCR_LOOPBACK)
 			data |= PORT_PHY_LOOPBACK;
 		else
 			data &= ~PORT_PHY_LOOPBACK;
 		if (data != restart)
 			ksz_pwrite8(dev, p, regs[P_NEG_RESTART_CTRL], data);
 		break;
-	case PHY_REG_AUTO_NEGOTIATION:
+	case MII_ADVERTISE:
 		ksz_pread8(dev, p, regs[P_LOCAL_CTRL], &ctrl);
 		data = ctrl;
 		data &= ~(PORT_AUTO_NEG_SYM_PAUSE |
@@ -912,19 +937,23 @@ static void ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val)
 			  PORT_AUTO_NEG_100BTX |
 			  PORT_AUTO_NEG_10BT_FD |
 			  PORT_AUTO_NEG_10BT);
-		if (val & PHY_AUTO_NEG_SYM_PAUSE)
+		if (val & ADVERTISE_PAUSE_CAP)
 			data |= PORT_AUTO_NEG_SYM_PAUSE;
-		if (val & PHY_AUTO_NEG_100BTX_FD)
+		if (val & ADVERTISE_100FULL)
 			data |= PORT_AUTO_NEG_100BTX_FD;
-		if (val & PHY_AUTO_NEG_100BTX)
+		if (val & ADVERTISE_100HALF)
 			data |= PORT_AUTO_NEG_100BTX;
-		if (val & PHY_AUTO_NEG_10BT_FD)
+		if (val & ADVERTISE_10FULL)
 			data |= PORT_AUTO_NEG_10BT_FD;
-		if (val & PHY_AUTO_NEG_10BT)
+		if (val & ADVERTISE_10HALF)
 			data |= PORT_AUTO_NEG_10BT;
 		if (data != ctrl)
 			ksz_pwrite8(dev, p, regs[P_LOCAL_CTRL], data);
 		break;
+	case PHY_REG_LINK_MD:
+		if (val & PHY_START_CABLE_DIAG)
+			ksz_port_cfg(dev, p, REG_PORT_LINK_MD_CTRL, PORT_START_CABLE_DIAG, true);
+		break;
 	default:
 		break;
 	}
@@ -941,6 +970,18 @@ static enum dsa_tag_protocol ksz8_get_tag_protocol(struct dsa_switch *ds,
 		DSA_TAG_PROTO_KSZ9893 : DSA_TAG_PROTO_KSZ8795;
 }
 
+static u32 ksz8_sw_get_phy_flags(struct dsa_switch *ds, int port)
+{
+	/* Silicon Errata Sheet (DS80000830A):
+	 * Port 1 does not work with LinkMD Cable-Testing.
+	 * Port 1 does not respond to received PAUSE control frames.
+	 */
+	if (!port)
+		return MICREL_KSZ8_P1_ERRATA;
+
+	return 0;
+}
+
 static void ksz8_get_strings(struct dsa_switch *ds, int port,
 			     u32 stringset, uint8_t *buf)
 {
@@ -1419,11 +1460,66 @@ static int ksz8_setup(struct dsa_switch *ds)
 	return 0;
 }
 
+static void ksz8_validate(struct dsa_switch *ds, int port,
+			  unsigned long *supported,
+			  struct phylink_link_state *state)
+{
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
+	struct ksz_device *dev = ds->priv;
+
+	if (port == dev->cpu_port) {
+		if (state->interface != PHY_INTERFACE_MODE_RMII &&
+		    state->interface != PHY_INTERFACE_MODE_MII &&
+		    state->interface != PHY_INTERFACE_MODE_NA)
+			goto unsupported;
+	} else {
+		if (state->interface != PHY_INTERFACE_MODE_INTERNAL &&
+		    state->interface != PHY_INTERFACE_MODE_NA)
+			goto unsupported;
+	}
+
+	/* Allow all the expected bits */
+	phylink_set_port_modes(mask);
+	phylink_set(mask, Autoneg);
+
+	/* Silicon Errata Sheet (DS80000830A):
+	 * "Port 1 does not respond to received flow control PAUSE frames"
+	 * So, disable Pause support on "Port 1" (port == 0) for all ksz88x3
+	 * switches.
+	 */
+	if (!ksz_is_ksz88x3(dev) || port)
+		phylink_set(mask, Pause);
+
+	/* Asym pause is not supported on KSZ8863 and KSZ8873 */
+	if (!ksz_is_ksz88x3(dev))
+		phylink_set(mask, Asym_Pause);
+
+	/* 10M and 100M are only supported */
+	phylink_set(mask, 10baseT_Half);
+	phylink_set(mask, 10baseT_Full);
+	phylink_set(mask, 100baseT_Half);
+	phylink_set(mask, 100baseT_Full);
+
+	bitmap_and(supported, supported, mask,
+		   __ETHTOOL_LINK_MODE_MASK_NBITS);
+	bitmap_and(state->advertising, state->advertising, mask,
+		   __ETHTOOL_LINK_MODE_MASK_NBITS);
+
+	return;
+
+unsupported:
+	bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
+	dev_err(ds->dev, "Unsupported interface: %s, port: %d\n",
+		phy_modes(state->interface), port);
+}
+
 static const struct dsa_switch_ops ksz8_switch_ops = {
 	.get_tag_protocol	= ksz8_get_tag_protocol,
+	.get_phy_flags		= ksz8_sw_get_phy_flags,
 	.setup			= ksz8_setup,
 	.phy_read		= ksz_phy_read16,
 	.phy_write		= ksz_phy_write16,
+	.phylink_validate	= ksz8_validate,
 	.phylink_mac_link_down	= ksz_mac_link_down,
 	.port_enable		= ksz_enable_port,
 	.get_strings		= ksz8_get_strings,
diff --git a/drivers/net/dsa/microchip/ksz8795_reg.h b/drivers/net/dsa/microchip/ksz8795_reg.h
index c2e52c40a54c..a32355624f31 100644
--- a/drivers/net/dsa/microchip/ksz8795_reg.h
+++ b/drivers/net/dsa/microchip/ksz8795_reg.h
@@ -249,7 +249,7 @@
 #define REG_PORT_4_LINK_MD_CTRL		0x4A
 
 #define PORT_CABLE_10M_SHORT		BIT(7)
-#define PORT_CABLE_DIAG_RESULT_M	0x3
+#define PORT_CABLE_DIAG_RESULT_M	GENMASK(6, 5)
 #define PORT_CABLE_DIAG_RESULT_S	5
 #define PORT_CABLE_STAT_NORMAL		0
 #define PORT_CABLE_STAT_OPEN		1
@@ -744,68 +744,6 @@
 
 #define PORT_ACL_FORCE_DLR_MISS		BIT(0)
 
-#ifndef PHY_REG_CTRL
-#define PHY_REG_CTRL			0
-
-#define PHY_RESET			BIT(15)
-#define PHY_LOOPBACK			BIT(14)
-#define PHY_SPEED_100MBIT		BIT(13)
-#define PHY_AUTO_NEG_ENABLE		BIT(12)
-#define PHY_POWER_DOWN			BIT(11)
-#define PHY_MII_DISABLE			BIT(10)
-#define PHY_AUTO_NEG_RESTART		BIT(9)
-#define PHY_FULL_DUPLEX			BIT(8)
-#define PHY_COLLISION_TEST_NOT		BIT(7)
-#define PHY_HP_MDIX			BIT(5)
-#define PHY_FORCE_MDIX			BIT(4)
-#define PHY_AUTO_MDIX_DISABLE		BIT(3)
-#define PHY_REMOTE_FAULT_DISABLE	BIT(2)
-#define PHY_TRANSMIT_DISABLE		BIT(1)
-#define PHY_LED_DISABLE			BIT(0)
-
-#define PHY_REG_STATUS			1
-
-#define PHY_100BT4_CAPABLE		BIT(15)
-#define PHY_100BTX_FD_CAPABLE		BIT(14)
-#define PHY_100BTX_CAPABLE		BIT(13)
-#define PHY_10BT_FD_CAPABLE		BIT(12)
-#define PHY_10BT_CAPABLE		BIT(11)
-#define PHY_MII_SUPPRESS_CAPABLE_NOT	BIT(6)
-#define PHY_AUTO_NEG_ACKNOWLEDGE	BIT(5)
-#define PHY_REMOTE_FAULT		BIT(4)
-#define PHY_AUTO_NEG_CAPABLE		BIT(3)
-#define PHY_LINK_STATUS			BIT(2)
-#define PHY_JABBER_DETECT_NOT		BIT(1)
-#define PHY_EXTENDED_CAPABILITY		BIT(0)
-
-#define PHY_REG_ID_1			2
-#define PHY_REG_ID_2			3
-
-#define PHY_REG_AUTO_NEGOTIATION	4
-
-#define PHY_AUTO_NEG_NEXT_PAGE_NOT	BIT(15)
-#define PHY_AUTO_NEG_REMOTE_FAULT_NOT	BIT(13)
-#define PHY_AUTO_NEG_SYM_PAUSE		BIT(10)
-#define PHY_AUTO_NEG_100BT4		BIT(9)
-#define PHY_AUTO_NEG_100BTX_FD		BIT(8)
-#define PHY_AUTO_NEG_100BTX		BIT(7)
-#define PHY_AUTO_NEG_10BT_FD		BIT(6)
-#define PHY_AUTO_NEG_10BT		BIT(5)
-#define PHY_AUTO_NEG_SELECTOR		0x001F
-#define PHY_AUTO_NEG_802_3		0x0001
-
-#define PHY_REG_REMOTE_CAPABILITY	5
-
-#define PHY_REMOTE_NEXT_PAGE_NOT	BIT(15)
-#define PHY_REMOTE_ACKNOWLEDGE_NOT	BIT(14)
-#define PHY_REMOTE_REMOTE_FAULT_NOT	BIT(13)
-#define PHY_REMOTE_SYM_PAUSE		BIT(10)
-#define PHY_REMOTE_100BTX_FD		BIT(8)
-#define PHY_REMOTE_100BTX		BIT(7)
-#define PHY_REMOTE_10BT_FD		BIT(6)
-#define PHY_REMOTE_10BT			BIT(5)
-#endif
-
 #define KSZ8795_ID_HI			0x0022
 #define KSZ8795_ID_LO			0x1550
 #define KSZ8863_ID_LO			0x1430
@@ -815,13 +753,14 @@
 #define PHY_REG_LINK_MD			0x1D
 
 #define PHY_START_CABLE_DIAG		BIT(15)
+#define PHY_CABLE_DIAG_RESULT_M		GENMASK(14, 13)
 #define PHY_CABLE_DIAG_RESULT		0x6000
 #define PHY_CABLE_STAT_NORMAL		0x0000
 #define PHY_CABLE_STAT_OPEN		0x2000
 #define PHY_CABLE_STAT_SHORT		0x4000
 #define PHY_CABLE_STAT_FAILED		0x6000
 #define PHY_CABLE_10M_SHORT		BIT(12)
-#define PHY_CABLE_FAULT_COUNTER		0x01FF
+#define PHY_CABLE_FAULT_COUNTER_M	GENMASK(8, 0)
 
 #define PHY_REG_PHY_CTRL		0x1F
 
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 9b90f3d3a8f5..93136f7e69f5 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -10,6 +10,7 @@
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
+#include <linux/of_irq.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/of_platform.h>
@@ -596,18 +597,14 @@ mt7530_mib_reset(struct dsa_switch *ds)
 	mt7530_write(priv, MT7530_MIB_CCR, CCR_MIB_ACTIVATE);
 }
 
-static int mt7530_phy_read(struct dsa_switch *ds, int port, int regnum)
+static int mt7530_phy_read(struct mt7530_priv *priv, int port, int regnum)
 {
-	struct mt7530_priv *priv = ds->priv;
-
 	return mdiobus_read_nested(priv->bus, port, regnum);
 }
 
-static int mt7530_phy_write(struct dsa_switch *ds, int port, int regnum,
+static int mt7530_phy_write(struct mt7530_priv *priv, int port, int regnum,
 			    u16 val)
 {
-	struct mt7530_priv *priv = ds->priv;
-
 	return mdiobus_write_nested(priv->bus, port, regnum, val);
 }
 
@@ -785,9 +782,8 @@ out:
 }
 
 static int
-mt7531_ind_phy_read(struct dsa_switch *ds, int port, int regnum)
+mt7531_ind_phy_read(struct mt7530_priv *priv, int port, int regnum)
 {
-	struct mt7530_priv *priv = ds->priv;
 	int devad;
 	int ret;
 
@@ -803,10 +799,9 @@ mt7531_ind_phy_read(struct dsa_switch *ds, int port, int regnum)
 }
 
 static int
-mt7531_ind_phy_write(struct dsa_switch *ds, int port, int regnum,
+mt7531_ind_phy_write(struct mt7530_priv *priv, int port, int regnum,
 		     u16 data)
 {
-	struct mt7530_priv *priv = ds->priv;
 	int devad;
 	int ret;
 
@@ -822,6 +817,22 @@ mt7531_ind_phy_write(struct dsa_switch *ds, int port, int regnum,
 	return ret;
 }
 
+static int
+mt753x_phy_read(struct mii_bus *bus, int port, int regnum)
+{
+	struct mt7530_priv *priv = bus->priv;
+
+	return priv->info->phy_read(priv, port, regnum);
+}
+
+static int
+mt753x_phy_write(struct mii_bus *bus, int port, int regnum, u16 val)
+{
+	struct mt7530_priv *priv = bus->priv;
+
+	return priv->info->phy_write(priv, port, regnum, val);
+}
+
 static void
 mt7530_get_strings(struct dsa_switch *ds, int port, u32 stringset,
 		   uint8_t *data)
@@ -1820,6 +1831,210 @@ mt7530_setup_gpio(struct mt7530_priv *priv)
 }
 #endif /* CONFIG_GPIOLIB */
 
+static irqreturn_t
+mt7530_irq_thread_fn(int irq, void *dev_id)
+{
+	struct mt7530_priv *priv = dev_id;
+	bool handled = false;
+	u32 val;
+	int p;
+
+	mutex_lock_nested(&priv->bus->mdio_lock, MDIO_MUTEX_NESTED);
+	val = mt7530_mii_read(priv, MT7530_SYS_INT_STS);
+	mt7530_mii_write(priv, MT7530_SYS_INT_STS, val);
+	mutex_unlock(&priv->bus->mdio_lock);
+
+	for (p = 0; p < MT7530_NUM_PHYS; p++) {
+		if (BIT(p) & val) {
+			unsigned int irq;
+
+			irq = irq_find_mapping(priv->irq_domain, p);
+			handle_nested_irq(irq);
+			handled = true;
+		}
+	}
+
+	return IRQ_RETVAL(handled);
+}
+
+static void
+mt7530_irq_mask(struct irq_data *d)
+{
+	struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
+
+	priv->irq_enable &= ~BIT(d->hwirq);
+}
+
+static void
+mt7530_irq_unmask(struct irq_data *d)
+{
+	struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
+
+	priv->irq_enable |= BIT(d->hwirq);
+}
+
+static void
+mt7530_irq_bus_lock(struct irq_data *d)
+{
+	struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
+
+	mutex_lock_nested(&priv->bus->mdio_lock, MDIO_MUTEX_NESTED);
+}
+
+static void
+mt7530_irq_bus_sync_unlock(struct irq_data *d)
+{
+	struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
+
+	mt7530_mii_write(priv, MT7530_SYS_INT_EN, priv->irq_enable);
+	mutex_unlock(&priv->bus->mdio_lock);
+}
+
+static struct irq_chip mt7530_irq_chip = {
+	.name = KBUILD_MODNAME,
+	.irq_mask = mt7530_irq_mask,
+	.irq_unmask = mt7530_irq_unmask,
+	.irq_bus_lock = mt7530_irq_bus_lock,
+	.irq_bus_sync_unlock = mt7530_irq_bus_sync_unlock,
+};
+
+static int
+mt7530_irq_map(struct irq_domain *domain, unsigned int irq,
+	       irq_hw_number_t hwirq)
+{
+	irq_set_chip_data(irq, domain->host_data);
+	irq_set_chip_and_handler(irq, &mt7530_irq_chip, handle_simple_irq);
+	irq_set_nested_thread(irq, true);
+	irq_set_noprobe(irq);
+
+	return 0;
+}
+
+static const struct irq_domain_ops mt7530_irq_domain_ops = {
+	.map = mt7530_irq_map,
+	.xlate = irq_domain_xlate_onecell,
+};
+
+static void
+mt7530_setup_mdio_irq(struct mt7530_priv *priv)
+{
+	struct dsa_switch *ds = priv->ds;
+	int p;
+
+	for (p = 0; p < MT7530_NUM_PHYS; p++) {
+		if (BIT(p) & ds->phys_mii_mask) {
+			unsigned int irq;
+
+			irq = irq_create_mapping(priv->irq_domain, p);
+			ds->slave_mii_bus->irq[p] = irq;
+		}
+	}
+}
+
+static int
+mt7530_setup_irq(struct mt7530_priv *priv)
+{
+	struct device *dev = priv->dev;
+	struct device_node *np = dev->of_node;
+	int ret;
+
+	if (!of_property_read_bool(np, "interrupt-controller")) {
+		dev_info(dev, "no interrupt support\n");
+		return 0;
+	}
+
+	priv->irq = of_irq_get(np, 0);
+	if (priv->irq <= 0) {
+		dev_err(dev, "failed to get parent IRQ: %d\n", priv->irq);
+		return priv->irq ? : -EINVAL;
+	}
+
+	priv->irq_domain = irq_domain_add_linear(np, MT7530_NUM_PHYS,
+						 &mt7530_irq_domain_ops, priv);
+	if (!priv->irq_domain) {
+		dev_err(dev, "failed to create IRQ domain\n");
+		return -ENOMEM;
+	}
+
+	/* This register must be set for MT7530 to properly fire interrupts */
+	if (priv->id != ID_MT7531)
+		mt7530_set(priv, MT7530_TOP_SIG_CTRL, TOP_SIG_CTRL_NORMAL);
+
+	ret = request_threaded_irq(priv->irq, NULL, mt7530_irq_thread_fn,
+				   IRQF_ONESHOT, KBUILD_MODNAME, priv);
+	if (ret) {
+		irq_domain_remove(priv->irq_domain);
+		dev_err(dev, "failed to request IRQ: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void
+mt7530_free_mdio_irq(struct mt7530_priv *priv)
+{
+	int p;
+
+	for (p = 0; p < MT7530_NUM_PHYS; p++) {
+		if (BIT(p) & priv->ds->phys_mii_mask) {
+			unsigned int irq;
+
+			irq = irq_find_mapping(priv->irq_domain, p);
+			irq_dispose_mapping(irq);
+		}
+	}
+}
+
+static void
+mt7530_free_irq_common(struct mt7530_priv *priv)
+{
+	free_irq(priv->irq, priv);
+	irq_domain_remove(priv->irq_domain);
+}
+
+static void
+mt7530_free_irq(struct mt7530_priv *priv)
+{
+	mt7530_free_mdio_irq(priv);
+	mt7530_free_irq_common(priv);
+}
+
+static int
+mt7530_setup_mdio(struct mt7530_priv *priv)
+{
+	struct dsa_switch *ds = priv->ds;
+	struct device *dev = priv->dev;
+	struct mii_bus *bus;
+	static int idx;
+	int ret;
+
+	bus = devm_mdiobus_alloc(dev);
+	if (!bus)
+		return -ENOMEM;
+
+	ds->slave_mii_bus = bus;
+	bus->priv = priv;
+	bus->name = KBUILD_MODNAME "-mii";
+	snprintf(bus->id, MII_BUS_ID_SIZE, KBUILD_MODNAME "-%d", idx++);
+	bus->read = mt753x_phy_read;
+	bus->write = mt753x_phy_write;
+	bus->parent = dev;
+	bus->phy_mask = ~ds->phys_mii_mask;
+
+	if (priv->irq)
+		mt7530_setup_mdio_irq(priv);
+
+	ret = mdiobus_register(bus);
+	if (ret) {
+		dev_err(dev, "failed to register MDIO bus: %d\n", ret);
+		if (priv->irq)
+			mt7530_free_mdio_irq(priv);
+	}
+
+	return ret;
+}
+
 static int
 mt7530_setup(struct dsa_switch *ds)
 {
@@ -2783,24 +2998,20 @@ static int
 mt753x_setup(struct dsa_switch *ds)
 {
 	struct mt7530_priv *priv = ds->priv;
+	int ret = priv->info->sw_setup(ds);
 
-	return priv->info->sw_setup(ds);
-}
-
-static int
-mt753x_phy_read(struct dsa_switch *ds, int port, int regnum)
-{
-	struct mt7530_priv *priv = ds->priv;
+	if (ret)
+		return ret;
 
-	return priv->info->phy_read(ds, port, regnum);
-}
+	ret = mt7530_setup_irq(priv);
+	if (ret)
+		return ret;
 
-static int
-mt753x_phy_write(struct dsa_switch *ds, int port, int regnum, u16 val)
-{
-	struct mt7530_priv *priv = ds->priv;
+	ret = mt7530_setup_mdio(priv);
+	if (ret && priv->irq)
+		mt7530_free_irq_common(priv);
 
-	return priv->info->phy_write(ds, port, regnum, val);
+	return ret;
 }
 
 static int mt753x_get_mac_eee(struct dsa_switch *ds, int port,
@@ -2837,8 +3048,6 @@ static const struct dsa_switch_ops mt7530_switch_ops = {
 	.get_tag_protocol	= mtk_get_tag_protocol,
 	.setup			= mt753x_setup,
 	.get_strings		= mt7530_get_strings,
-	.phy_read		= mt753x_phy_read,
-	.phy_write		= mt753x_phy_write,
 	.get_ethtool_stats	= mt7530_get_ethtool_stats,
 	.get_sset_count		= mt7530_get_sset_count,
 	.set_ageing_time	= mt7530_set_ageing_time,
@@ -3021,6 +3230,9 @@ mt7530_remove(struct mdio_device *mdiodev)
 		dev_err(priv->dev, "Failed to disable io pwr: %d\n",
 			ret);
 
+	if (priv->irq)
+		mt7530_free_irq(priv);
+
 	dsa_unregister_switch(priv->ds);
 	mutex_destroy(&priv->reg_mutex);
 }
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index 0204da486f3a..334d610a503d 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -7,6 +7,7 @@
 #define __MT7530_H
 
 #define MT7530_NUM_PORTS		7
+#define MT7530_NUM_PHYS			5
 #define MT7530_CPU_PORT			6
 #define MT7530_NUM_FDB_RECORDS		2048
 #define MT7530_ALL_MEMBERS		0xff
@@ -393,6 +394,12 @@ enum mt7531_sgmii_force_duplex {
 #define  SYS_CTRL_SW_RST		BIT(1)
 #define  SYS_CTRL_REG_RST		BIT(0)
 
+/* Register for system interrupt */
+#define MT7530_SYS_INT_EN		0x7008
+
+/* Register for system interrupt status */
+#define MT7530_SYS_INT_STS		0x700c
+
 /* Register for PHY Indirect Access Control */
 #define MT7531_PHY_IAC			0x701C
 #define  MT7531_PHY_ACS_ST		BIT(31)
@@ -714,6 +721,8 @@ static const char *p5_intf_modes(unsigned int p5_interface)
 	}
 }
 
+struct mt7530_priv;
+
 /* struct mt753x_info -	This is the main data structure for holding the specific
  *			part for each supported device
  * @sw_setup:		Holding the handler to a device initialization
@@ -738,8 +747,8 @@ struct mt753x_info {
 	enum mt753x_id id;
 
 	int (*sw_setup)(struct dsa_switch *ds);
-	int (*phy_read)(struct dsa_switch *ds, int port, int regnum);
-	int (*phy_write)(struct dsa_switch *ds, int port, int regnum, u16 val);
+	int (*phy_read)(struct mt7530_priv *priv, int port, int regnum);
+	int (*phy_write)(struct mt7530_priv *priv, int port, int regnum, u16 val);
 	int (*pad_setup)(struct dsa_switch *ds, phy_interface_t interface);
 	int (*cpu_port_config)(struct dsa_switch *ds, int port);
 	bool (*phy_mode_supported)(struct dsa_switch *ds, int port,
@@ -773,6 +782,10 @@ struct mt753x_info {
  *			registers
  * @p6_interface	Holding the current port 6 interface
  * @p5_intf_sel:	Holding the current port 5 interface select
+ *
+ * @irq:		IRQ number of the switch
+ * @irq_domain:		IRQ domain of the switch irq_chip
+ * @irq_enable:		IRQ enable bits, synced to SYS_INT_EN
  */
 struct mt7530_priv {
 	struct device		*dev;
@@ -794,6 +807,9 @@ struct mt7530_priv {
 	struct mt7530_port	ports[MT7530_NUM_PORTS];
 	/* protect among processes for registers access*/
 	struct mutex reg_mutex;
+	int irq;
+	struct irq_domain *irq_domain;
+	u32 irq_enable;
 };
 
 struct mt7530_hw_vlan_entry {
diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index ce607fbaaa3a..a2a15919b960 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -940,6 +940,8 @@ static void felix_phylink_mac_link_up(struct dsa_switch *ds, int port,
 
 	ocelot_write_rix(ocelot, 0, ANA_POL_FLOWC, port);
 
+	ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, tx_pause);
+
 	/* Undo the effects of felix_phylink_mac_link_down:
 	 * enable MAC module
 	 */
diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c
index 84f93a874d50..deae923c8b7a 100644
--- a/drivers/net/dsa/ocelot/seville_vsc9953.c
+++ b/drivers/net/dsa/ocelot/seville_vsc9953.c
@@ -1206,6 +1206,11 @@ static int seville_probe(struct platform_device *pdev)
 	felix->info = &seville_info_vsc9953;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		err = -EINVAL;
+		dev_err(&pdev->dev, "Invalid resource\n");
+		goto err_alloc_felix;
+	}
 	felix->switch_base = res->start;
 
 	ds = kzalloc(sizeof(struct dsa_switch), GFP_KERNEL);
diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c
index cdaf9f85a2cb..1f63f50f73f1 100644
--- a/drivers/net/dsa/qca8k.c
+++ b/drivers/net/dsa/qca8k.c
@@ -11,6 +11,7 @@
 #include <linux/netdevice.h>
 #include <net/dsa.h>
 #include <linux/of_net.h>
+#include <linux/of_mdio.h>
 #include <linux/of_platform.h>
 #include <linux/if_bridge.h>
 #include <linux/mdio.h>
@@ -88,26 +89,26 @@ qca8k_split_addr(u32 regaddr, u16 *r1, u16 *r2, u16 *page)
 	*page = regaddr & 0x3ff;
 }
 
-static u32
-qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum)
+static int
+qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
 {
-	u32 val;
 	int ret;
 
 	ret = bus->read(bus, phy_id, regnum);
 	if (ret >= 0) {
-		val = ret;
+		*val = ret;
 		ret = bus->read(bus, phy_id, regnum + 1);
-		val |= ret << 16;
+		*val |= ret << 16;
 	}
 
 	if (ret < 0) {
 		dev_err_ratelimited(&bus->dev,
 				    "failed to read qca8k 32bit register\n");
+		*val = 0;
 		return ret;
 	}
 
-	return val;
+	return 0;
 }
 
 static void
@@ -127,82 +128,110 @@ qca8k_mii_write32(struct mii_bus *bus, int phy_id, u32 regnum, u32 val)
 				    "failed to write qca8k 32bit register\n");
 }
 
-static void
+static int
 qca8k_set_page(struct mii_bus *bus, u16 page)
 {
+	int ret;
+
 	if (page == qca8k_current_page)
-		return;
+		return 0;
 
-	if (bus->write(bus, 0x18, 0, page) < 0)
+	ret = bus->write(bus, 0x18, 0, page);
+	if (ret < 0) {
 		dev_err_ratelimited(&bus->dev,
 				    "failed to set qca8k page\n");
+		return ret;
+	}
+
 	qca8k_current_page = page;
+	usleep_range(1000, 2000);
+	return 0;
 }
 
-static u32
-qca8k_read(struct qca8k_priv *priv, u32 reg)
+static int
+qca8k_read(struct qca8k_priv *priv, u32 reg, u32 *val)
 {
+	struct mii_bus *bus = priv->bus;
 	u16 r1, r2, page;
-	u32 val;
+	int ret;
 
 	qca8k_split_addr(reg, &r1, &r2, &page);
 
-	mutex_lock_nested(&priv->bus->mdio_lock, MDIO_MUTEX_NESTED);
+	mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
 
-	qca8k_set_page(priv->bus, page);
-	val = qca8k_mii_read32(priv->bus, 0x10 | r2, r1);
+	ret = qca8k_set_page(bus, page);
+	if (ret < 0)
+		goto exit;
 
-	mutex_unlock(&priv->bus->mdio_lock);
+	ret = qca8k_mii_read32(bus, 0x10 | r2, r1, val);
 
-	return val;
+exit:
+	mutex_unlock(&bus->mdio_lock);
+	return ret;
 }
 
-static void
+static int
 qca8k_write(struct qca8k_priv *priv, u32 reg, u32 val)
 {
+	struct mii_bus *bus = priv->bus;
 	u16 r1, r2, page;
+	int ret;
 
 	qca8k_split_addr(reg, &r1, &r2, &page);
 
-	mutex_lock_nested(&priv->bus->mdio_lock, MDIO_MUTEX_NESTED);
+	mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+	ret = qca8k_set_page(bus, page);
+	if (ret < 0)
+		goto exit;
 
-	qca8k_set_page(priv->bus, page);
-	qca8k_mii_write32(priv->bus, 0x10 | r2, r1, val);
+	qca8k_mii_write32(bus, 0x10 | r2, r1, val);
 
-	mutex_unlock(&priv->bus->mdio_lock);
+exit:
+	mutex_unlock(&bus->mdio_lock);
+	return ret;
 }
 
-static u32
-qca8k_rmw(struct qca8k_priv *priv, u32 reg, u32 mask, u32 val)
+static int
+qca8k_rmw(struct qca8k_priv *priv, u32 reg, u32 mask, u32 write_val)
 {
+	struct mii_bus *bus = priv->bus;
 	u16 r1, r2, page;
-	u32 ret;
+	u32 val;
+	int ret;
 
 	qca8k_split_addr(reg, &r1, &r2, &page);
 
-	mutex_lock_nested(&priv->bus->mdio_lock, MDIO_MUTEX_NESTED);
+	mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+	ret = qca8k_set_page(bus, page);
+	if (ret < 0)
+		goto exit;
+
+	ret = qca8k_mii_read32(bus, 0x10 | r2, r1, &val);
+	if (ret < 0)
+		goto exit;
 
-	qca8k_set_page(priv->bus, page);
-	ret = qca8k_mii_read32(priv->bus, 0x10 | r2, r1);
-	ret &= ~mask;
-	ret |= val;
-	qca8k_mii_write32(priv->bus, 0x10 | r2, r1, ret);
+	val &= ~mask;
+	val |= write_val;
+	qca8k_mii_write32(bus, 0x10 | r2, r1, val);
 
-	mutex_unlock(&priv->bus->mdio_lock);
+exit:
+	mutex_unlock(&bus->mdio_lock);
 
 	return ret;
 }
 
-static void
+static int
 qca8k_reg_set(struct qca8k_priv *priv, u32 reg, u32 val)
 {
-	qca8k_rmw(priv, reg, 0, val);
+	return qca8k_rmw(priv, reg, 0, val);
 }
 
-static void
+static int
 qca8k_reg_clear(struct qca8k_priv *priv, u32 reg, u32 val)
 {
-	qca8k_rmw(priv, reg, val, 0);
+	return qca8k_rmw(priv, reg, val, 0);
 }
 
 static int
@@ -210,9 +239,7 @@ qca8k_regmap_read(void *ctx, uint32_t reg, uint32_t *val)
 {
 	struct qca8k_priv *priv = (struct qca8k_priv *)ctx;
 
-	*val = qca8k_read(priv, reg);
-
-	return 0;
+	return qca8k_read(priv, reg, val);
 }
 
 static int
@@ -220,9 +247,7 @@ qca8k_regmap_write(void *ctx, uint32_t reg, uint32_t val)
 {
 	struct qca8k_priv *priv = (struct qca8k_priv *)ctx;
 
-	qca8k_write(priv, reg, val);
-
-	return 0;
+	return qca8k_write(priv, reg, val);
 }
 
 static const struct regmap_range qca8k_readable_ranges[] = {
@@ -262,32 +287,36 @@ static struct regmap_config qca8k_regmap_config = {
 static int
 qca8k_busy_wait(struct qca8k_priv *priv, u32 reg, u32 mask)
 {
-	unsigned long timeout;
-
-	timeout = jiffies + msecs_to_jiffies(20);
+	int ret, ret1;
+	u32 val;
 
-	/* loop until the busy flag has cleared */
-	do {
-		u32 val = qca8k_read(priv, reg);
-		int busy = val & mask;
+	ret = read_poll_timeout(qca8k_read, ret1, !(val & mask),
+				0, QCA8K_BUSY_WAIT_TIMEOUT * USEC_PER_MSEC, false,
+				priv, reg, &val);
 
-		if (!busy)
-			break;
-		cond_resched();
-	} while (!time_after_eq(jiffies, timeout));
+	/* Check if qca8k_read has failed for a different reason
+	 * before returning -ETIMEDOUT
+	 */
+	if (ret < 0 && ret1 < 0)
+		return ret1;
 
-	return time_after_eq(jiffies, timeout);
+	return ret;
 }
 
-static void
+static int
 qca8k_fdb_read(struct qca8k_priv *priv, struct qca8k_fdb *fdb)
 {
-	u32 reg[4];
-	int i;
+	u32 reg[4], val;
+	int i, ret;
 
 	/* load the ARL table into an array */
-	for (i = 0; i < 4; i++)
-		reg[i] = qca8k_read(priv, QCA8K_REG_ATU_DATA0 + (i * 4));
+	for (i = 0; i < 4; i++) {
+		ret = qca8k_read(priv, QCA8K_REG_ATU_DATA0 + (i * 4), &val);
+		if (ret < 0)
+			return ret;
+
+		reg[i] = val;
+	}
 
 	/* vid - 83:72 */
 	fdb->vid = (reg[2] >> QCA8K_ATU_VID_S) & QCA8K_ATU_VID_M;
@@ -302,6 +331,8 @@ qca8k_fdb_read(struct qca8k_priv *priv, struct qca8k_fdb *fdb)
 	fdb->mac[3] = (reg[0] >> QCA8K_ATU_ADDR3_S) & 0xff;
 	fdb->mac[4] = (reg[0] >> QCA8K_ATU_ADDR4_S) & 0xff;
 	fdb->mac[5] = reg[0] & 0xff;
+
+	return 0;
 }
 
 static void
@@ -334,6 +365,7 @@ static int
 qca8k_fdb_access(struct qca8k_priv *priv, enum qca8k_fdb_cmd cmd, int port)
 {
 	u32 reg;
+	int ret;
 
 	/* Set the command and FDB index */
 	reg = QCA8K_ATU_FUNC_BUSY;
@@ -344,15 +376,20 @@ qca8k_fdb_access(struct qca8k_priv *priv, enum qca8k_fdb_cmd cmd, int port)
 	}
 
 	/* Write the function register triggering the table access */
-	qca8k_write(priv, QCA8K_REG_ATU_FUNC, reg);
+	ret = qca8k_write(priv, QCA8K_REG_ATU_FUNC, reg);
+	if (ret)
+		return ret;
 
 	/* wait for completion */
-	if (qca8k_busy_wait(priv, QCA8K_REG_ATU_FUNC, QCA8K_ATU_FUNC_BUSY))
-		return -1;
+	ret = qca8k_busy_wait(priv, QCA8K_REG_ATU_FUNC, QCA8K_ATU_FUNC_BUSY);
+	if (ret)
+		return ret;
 
 	/* Check for table full violation when adding an entry */
 	if (cmd == QCA8K_FDB_LOAD) {
-		reg = qca8k_read(priv, QCA8K_REG_ATU_FUNC);
+		ret = qca8k_read(priv, QCA8K_REG_ATU_FUNC, &reg);
+		if (ret < 0)
+			return ret;
 		if (reg & QCA8K_ATU_FUNC_FULL)
 			return -1;
 	}
@@ -367,10 +404,10 @@ qca8k_fdb_next(struct qca8k_priv *priv, struct qca8k_fdb *fdb, int port)
 
 	qca8k_fdb_write(priv, fdb->vid, fdb->port_mask, fdb->mac, fdb->aging);
 	ret = qca8k_fdb_access(priv, QCA8K_FDB_NEXT, port);
-	if (ret >= 0)
-		qca8k_fdb_read(priv, fdb);
+	if (ret < 0)
+		return ret;
 
-	return ret;
+	return qca8k_fdb_read(priv, fdb);
 }
 
 static int
@@ -412,6 +449,7 @@ static int
 qca8k_vlan_access(struct qca8k_priv *priv, enum qca8k_vlan_cmd cmd, u16 vid)
 {
 	u32 reg;
+	int ret;
 
 	/* Set the command and VLAN index */
 	reg = QCA8K_VTU_FUNC1_BUSY;
@@ -419,15 +457,20 @@ qca8k_vlan_access(struct qca8k_priv *priv, enum qca8k_vlan_cmd cmd, u16 vid)
 	reg |= vid << QCA8K_VTU_FUNC1_VID_S;
 
 	/* Write the function register triggering the table access */
-	qca8k_write(priv, QCA8K_REG_VTU_FUNC1, reg);
+	ret = qca8k_write(priv, QCA8K_REG_VTU_FUNC1, reg);
+	if (ret)
+		return ret;
 
 	/* wait for completion */
-	if (qca8k_busy_wait(priv, QCA8K_REG_VTU_FUNC1, QCA8K_VTU_FUNC1_BUSY))
-		return -ETIMEDOUT;
+	ret = qca8k_busy_wait(priv, QCA8K_REG_VTU_FUNC1, QCA8K_VTU_FUNC1_BUSY);
+	if (ret)
+		return ret;
 
 	/* Check for table full violation when adding an entry */
 	if (cmd == QCA8K_VLAN_LOAD) {
-		reg = qca8k_read(priv, QCA8K_REG_VTU_FUNC1);
+		ret = qca8k_read(priv, QCA8K_REG_VTU_FUNC1, &reg);
+		if (ret < 0)
+			return ret;
 		if (reg & QCA8K_VTU_FUNC1_FULL)
 			return -ENOMEM;
 	}
@@ -453,7 +496,9 @@ qca8k_vlan_add(struct qca8k_priv *priv, u8 port, u16 vid, bool untagged)
 	if (ret < 0)
 		goto out;
 
-	reg = qca8k_read(priv, QCA8K_REG_VTU_FUNC0);
+	ret = qca8k_read(priv, QCA8K_REG_VTU_FUNC0, &reg);
+	if (ret < 0)
+		goto out;
 	reg |= QCA8K_VTU_FUNC0_VALID | QCA8K_VTU_FUNC0_IVL_EN;
 	reg &= ~(QCA8K_VTU_FUNC0_EG_MODE_MASK << QCA8K_VTU_FUNC0_EG_MODE_S(port));
 	if (untagged)
@@ -463,7 +508,9 @@ qca8k_vlan_add(struct qca8k_priv *priv, u8 port, u16 vid, bool untagged)
 		reg |= QCA8K_VTU_FUNC0_EG_MODE_TAG <<
 				QCA8K_VTU_FUNC0_EG_MODE_S(port);
 
-	qca8k_write(priv, QCA8K_REG_VTU_FUNC0, reg);
+	ret = qca8k_write(priv, QCA8K_REG_VTU_FUNC0, reg);
+	if (ret)
+		goto out;
 	ret = qca8k_vlan_access(priv, QCA8K_VLAN_LOAD, vid);
 
 out:
@@ -484,7 +531,9 @@ qca8k_vlan_del(struct qca8k_priv *priv, u8 port, u16 vid)
 	if (ret < 0)
 		goto out;
 
-	reg = qca8k_read(priv, QCA8K_REG_VTU_FUNC0);
+	ret = qca8k_read(priv, QCA8K_REG_VTU_FUNC0, &reg);
+	if (ret < 0)
+		goto out;
 	reg &= ~(3 << QCA8K_VTU_FUNC0_EG_MODE_S(port));
 	reg |= QCA8K_VTU_FUNC0_EG_MODE_NOT <<
 			QCA8K_VTU_FUNC0_EG_MODE_S(port);
@@ -504,7 +553,9 @@ qca8k_vlan_del(struct qca8k_priv *priv, u8 port, u16 vid)
 	if (del) {
 		ret = qca8k_vlan_access(priv, QCA8K_VLAN_PURGE, vid);
 	} else {
-		qca8k_write(priv, QCA8K_REG_VTU_FUNC0, reg);
+		ret = qca8k_write(priv, QCA8K_REG_VTU_FUNC0, reg);
+		if (ret)
+			goto out;
 		ret = qca8k_vlan_access(priv, QCA8K_VLAN_LOAD, vid);
 	}
 
@@ -514,15 +565,29 @@ out:
 	return ret;
 }
 
-static void
+static int
 qca8k_mib_init(struct qca8k_priv *priv)
 {
+	int ret;
+
 	mutex_lock(&priv->reg_mutex);
-	qca8k_reg_set(priv, QCA8K_REG_MIB, QCA8K_MIB_FLUSH | QCA8K_MIB_BUSY);
-	qca8k_busy_wait(priv, QCA8K_REG_MIB, QCA8K_MIB_BUSY);
-	qca8k_reg_set(priv, QCA8K_REG_MIB, QCA8K_MIB_CPU_KEEP);
-	qca8k_write(priv, QCA8K_REG_MODULE_EN, QCA8K_MODULE_EN_MIB);
+	ret = qca8k_reg_set(priv, QCA8K_REG_MIB, QCA8K_MIB_FLUSH | QCA8K_MIB_BUSY);
+	if (ret)
+		goto exit;
+
+	ret = qca8k_busy_wait(priv, QCA8K_REG_MIB, QCA8K_MIB_BUSY);
+	if (ret)
+		goto exit;
+
+	ret = qca8k_reg_set(priv, QCA8K_REG_MIB, QCA8K_MIB_CPU_KEEP);
+	if (ret)
+		goto exit;
+
+	ret = qca8k_write(priv, QCA8K_REG_MODULE_EN, QCA8K_MODULE_EN_MIB);
+
+exit:
 	mutex_unlock(&priv->reg_mutex);
+	return ret;
 }
 
 static void
@@ -556,54 +621,109 @@ qca8k_port_to_phy(int port)
 }
 
 static int
-qca8k_mdio_write(struct qca8k_priv *priv, int port, u32 regnum, u16 data)
+qca8k_mdio_busy_wait(struct mii_bus *bus, u32 reg, u32 mask)
 {
-	u32 phy, val;
+	u16 r1, r2, page;
+	u32 val;
+	int ret, ret1;
+
+	qca8k_split_addr(reg, &r1, &r2, &page);
+
+	ret = read_poll_timeout(qca8k_mii_read32, ret1, !(val & mask), 0,
+				QCA8K_BUSY_WAIT_TIMEOUT * USEC_PER_MSEC, false,
+				bus, 0x10 | r2, r1, &val);
+
+	/* Check if qca8k_read has failed for a different reason
+	 * before returnting -ETIMEDOUT
+	 */
+	if (ret < 0 && ret1 < 0)
+		return ret1;
+
+	return ret;
+}
+
+static int
+qca8k_mdio_write(struct mii_bus *salve_bus, int phy, int regnum, u16 data)
+{
+	struct qca8k_priv *priv = salve_bus->priv;
+	struct mii_bus *bus = priv->bus;
+	u16 r1, r2, page;
+	u32 val;
+	int ret;
 
 	if (regnum >= QCA8K_MDIO_MASTER_MAX_REG)
 		return -EINVAL;
 
-	/* callee is responsible for not passing bad ports,
-	 * but we still would like to make spills impossible.
-	 */
-	phy = qca8k_port_to_phy(port) % PHY_MAX_ADDR;
 	val = QCA8K_MDIO_MASTER_BUSY | QCA8K_MDIO_MASTER_EN |
 	      QCA8K_MDIO_MASTER_WRITE | QCA8K_MDIO_MASTER_PHY_ADDR(phy) |
 	      QCA8K_MDIO_MASTER_REG_ADDR(regnum) |
 	      QCA8K_MDIO_MASTER_DATA(data);
 
-	qca8k_write(priv, QCA8K_MDIO_MASTER_CTRL, val);
+	qca8k_split_addr(QCA8K_MDIO_MASTER_CTRL, &r1, &r2, &page);
+
+	mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+	ret = qca8k_set_page(bus, page);
+	if (ret)
+		goto exit;
+
+	qca8k_mii_write32(bus, 0x10 | r2, r1, val);
 
-	return qca8k_busy_wait(priv, QCA8K_MDIO_MASTER_CTRL,
-		QCA8K_MDIO_MASTER_BUSY);
+	ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL,
+				   QCA8K_MDIO_MASTER_BUSY);
+
+exit:
+	/* even if the busy_wait timeouts try to clear the MASTER_EN */
+	qca8k_mii_write32(bus, 0x10 | r2, r1, 0);
+
+	mutex_unlock(&bus->mdio_lock);
+
+	return ret;
 }
 
 static int
-qca8k_mdio_read(struct qca8k_priv *priv, int port, u32 regnum)
+qca8k_mdio_read(struct mii_bus *salve_bus, int phy, int regnum)
 {
-	u32 phy, val;
+	struct qca8k_priv *priv = salve_bus->priv;
+	struct mii_bus *bus = priv->bus;
+	u16 r1, r2, page;
+	u32 val;
+	int ret;
 
 	if (regnum >= QCA8K_MDIO_MASTER_MAX_REG)
 		return -EINVAL;
 
-	/* callee is responsible for not passing bad ports,
-	 * but we still would like to make spills impossible.
-	 */
-	phy = qca8k_port_to_phy(port) % PHY_MAX_ADDR;
 	val = QCA8K_MDIO_MASTER_BUSY | QCA8K_MDIO_MASTER_EN |
 	      QCA8K_MDIO_MASTER_READ | QCA8K_MDIO_MASTER_PHY_ADDR(phy) |
 	      QCA8K_MDIO_MASTER_REG_ADDR(regnum);
 
-	qca8k_write(priv, QCA8K_MDIO_MASTER_CTRL, val);
+	qca8k_split_addr(QCA8K_MDIO_MASTER_CTRL, &r1, &r2, &page);
+
+	mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+	ret = qca8k_set_page(bus, page);
+	if (ret)
+		goto exit;
+
+	qca8k_mii_write32(bus, 0x10 | r2, r1, val);
 
-	if (qca8k_busy_wait(priv, QCA8K_MDIO_MASTER_CTRL,
-			    QCA8K_MDIO_MASTER_BUSY))
-		return -ETIMEDOUT;
+	ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL,
+				   QCA8K_MDIO_MASTER_BUSY);
+	if (ret)
+		goto exit;
+
+	ret = qca8k_mii_read32(bus, 0x10 | r2, r1, &val);
+
+exit:
+	/* even if the busy_wait timeouts try to clear the MASTER_EN */
+	qca8k_mii_write32(bus, 0x10 | r2, r1, 0);
 
-	val = (qca8k_read(priv, QCA8K_MDIO_MASTER_CTRL) &
-		QCA8K_MDIO_MASTER_DATA_MASK);
+	mutex_unlock(&bus->mdio_lock);
+
+	if (ret >= 0)
+		ret = val & QCA8K_MDIO_MASTER_DATA_MASK;
 
-	return val;
+	return ret;
 }
 
 static int
@@ -611,7 +731,14 @@ qca8k_phy_write(struct dsa_switch *ds, int port, int regnum, u16 data)
 {
 	struct qca8k_priv *priv = ds->priv;
 
-	return qca8k_mdio_write(priv, port, regnum, data);
+	/* Check if the legacy mapping should be used and the
+	 * port is not correctly mapped to the right PHY in the
+	 * devicetree
+	 */
+	if (priv->legacy_phy_port_mapping)
+		port = qca8k_port_to_phy(port) % PHY_MAX_ADDR;
+
+	return qca8k_mdio_write(priv->bus, port, regnum, data);
 }
 
 static int
@@ -620,7 +747,14 @@ qca8k_phy_read(struct dsa_switch *ds, int port, int regnum)
 	struct qca8k_priv *priv = ds->priv;
 	int ret;
 
-	ret = qca8k_mdio_read(priv, port, regnum);
+	/* Check if the legacy mapping should be used and the
+	 * port is not correctly mapped to the right PHY in the
+	 * devicetree
+	 */
+	if (priv->legacy_phy_port_mapping)
+		port = qca8k_port_to_phy(port) % PHY_MAX_ADDR;
+
+	ret = qca8k_mdio_read(priv->bus, port, regnum);
 
 	if (ret < 0)
 		return 0xffff;
@@ -629,14 +763,44 @@ qca8k_phy_read(struct dsa_switch *ds, int port, int regnum)
 }
 
 static int
+qca8k_mdio_register(struct qca8k_priv *priv, struct device_node *mdio)
+{
+	struct dsa_switch *ds = priv->ds;
+	struct mii_bus *bus;
+
+	bus = devm_mdiobus_alloc(ds->dev);
+
+	if (!bus)
+		return -ENOMEM;
+
+	bus->priv = (void *)priv;
+	bus->name = "qca8k slave mii";
+	bus->read = qca8k_mdio_read;
+	bus->write = qca8k_mdio_write;
+	snprintf(bus->id, MII_BUS_ID_SIZE, "qca8k-%d",
+		 ds->index);
+
+	bus->parent = ds->dev;
+	bus->phy_mask = ~ds->phys_mii_mask;
+
+	ds->slave_mii_bus = bus;
+
+	return devm_of_mdiobus_register(priv->dev, bus, mdio);
+}
+
+static int
 qca8k_setup_mdio_bus(struct qca8k_priv *priv)
 {
 	u32 internal_mdio_mask = 0, external_mdio_mask = 0, reg;
-	struct device_node *ports, *port;
+	struct device_node *ports, *port, *mdio;
+	phy_interface_t mode;
 	int err;
 
 	ports = of_get_child_by_name(priv->dev->of_node, "ports");
 	if (!ports)
+		ports = of_get_child_by_name(priv->dev->of_node, "ethernet-ports");
+
+	if (!ports)
 		return -EINVAL;
 
 	for_each_available_child_of_node(ports, port) {
@@ -650,7 +814,10 @@ qca8k_setup_mdio_bus(struct qca8k_priv *priv)
 		if (!dsa_is_user_port(priv->ds, reg))
 			continue;
 
-		if (of_property_read_bool(port, "phy-handle"))
+		of_get_phy_mode(port, &mode);
+
+		if (of_property_read_bool(port, "phy-handle") &&
+		    mode != PHY_INTERFACE_MODE_INTERNAL)
 			external_mdio_mask |= BIT(reg);
 		else
 			internal_mdio_mask |= BIT(reg);
@@ -683,13 +850,89 @@ qca8k_setup_mdio_bus(struct qca8k_priv *priv)
 		 * a dt-overlay and driver reload changed the configuration
 		 */
 
-		qca8k_reg_clear(priv, QCA8K_MDIO_MASTER_CTRL,
-				QCA8K_MDIO_MASTER_EN);
-		return 0;
+		return qca8k_reg_clear(priv, QCA8K_MDIO_MASTER_CTRL,
+				       QCA8K_MDIO_MASTER_EN);
+	}
+
+	/* Check if the devicetree declare the port:phy mapping */
+	mdio = of_get_child_by_name(priv->dev->of_node, "mdio");
+	if (of_device_is_available(mdio)) {
+		err = qca8k_mdio_register(priv, mdio);
+		if (err)
+			of_node_put(mdio);
+
+		return err;
 	}
 
+	/* If a mapping can't be found the legacy mapping is used,
+	 * using the qca8k_port_to_phy function
+	 */
+	priv->legacy_phy_port_mapping = true;
 	priv->ops.phy_read = qca8k_phy_read;
 	priv->ops.phy_write = qca8k_phy_write;
+
+	return 0;
+}
+
+static int
+qca8k_setup_of_rgmii_delay(struct qca8k_priv *priv)
+{
+	struct device_node *port_dn;
+	phy_interface_t mode;
+	struct dsa_port *dp;
+	u32 val;
+
+	/* CPU port is already checked */
+	dp = dsa_to_port(priv->ds, 0);
+
+	port_dn = dp->dn;
+
+	/* Check if port 0 is set to the correct type */
+	of_get_phy_mode(port_dn, &mode);
+	if (mode != PHY_INTERFACE_MODE_RGMII_ID &&
+	    mode != PHY_INTERFACE_MODE_RGMII_RXID &&
+	    mode != PHY_INTERFACE_MODE_RGMII_TXID) {
+		return 0;
+	}
+
+	switch (mode) {
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+		if (of_property_read_u32(port_dn, "rx-internal-delay-ps", &val))
+			val = 2;
+		else
+			/* Switch regs accept value in ns, convert ps to ns */
+			val = val / 1000;
+
+		if (val > QCA8K_MAX_DELAY) {
+			dev_err(priv->dev, "rgmii rx delay is limited to a max value of 3ns, setting to the max value");
+			val = 3;
+		}
+
+		priv->rgmii_rx_delay = val;
+		/* Stop here if we need to check only for rx delay */
+		if (mode != PHY_INTERFACE_MODE_RGMII_ID)
+			break;
+
+		fallthrough;
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		if (of_property_read_u32(port_dn, "tx-internal-delay-ps", &val))
+			val = 1;
+		else
+			/* Switch regs accept value in ns, convert ps to ns */
+			val = val / 1000;
+
+		if (val > QCA8K_MAX_DELAY) {
+			dev_err(priv->dev, "rgmii tx delay is limited to a max value of 3ns, setting to the max value");
+			val = 3;
+		}
+
+		priv->rgmii_tx_delay = val;
+		break;
+	default:
+		return 0;
+	}
+
 	return 0;
 }
 
@@ -698,10 +941,11 @@ qca8k_setup(struct dsa_switch *ds)
 {
 	struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv;
 	int ret, i;
+	u32 mask;
 
 	/* Make sure that port 0 is the cpu port */
 	if (!dsa_is_cpu_port(ds, 0)) {
-		pr_err("port 0 is not the CPU port\n");
+		dev_err(priv->dev, "port 0 is not the CPU port");
 		return -EINVAL;
 	}
 
@@ -711,76 +955,163 @@ qca8k_setup(struct dsa_switch *ds)
 	priv->regmap = devm_regmap_init(ds->dev, NULL, priv,
 					&qca8k_regmap_config);
 	if (IS_ERR(priv->regmap))
-		pr_warn("regmap initialization failed");
+		dev_warn(priv->dev, "regmap initialization failed");
 
 	ret = qca8k_setup_mdio_bus(priv);
 	if (ret)
 		return ret;
 
+	ret = qca8k_setup_of_rgmii_delay(priv);
+	if (ret)
+		return ret;
+
 	/* Enable CPU Port */
-	qca8k_reg_set(priv, QCA8K_REG_GLOBAL_FW_CTRL0,
-		      QCA8K_GLOBAL_FW_CTRL0_CPU_PORT_EN);
+	ret = qca8k_reg_set(priv, QCA8K_REG_GLOBAL_FW_CTRL0,
+			    QCA8K_GLOBAL_FW_CTRL0_CPU_PORT_EN);
+	if (ret) {
+		dev_err(priv->dev, "failed enabling CPU port");
+		return ret;
+	}
 
 	/* Enable MIB counters */
-	qca8k_mib_init(priv);
+	ret = qca8k_mib_init(priv);
+	if (ret)
+		dev_warn(priv->dev, "mib init failed");
 
 	/* Enable QCA header mode on the cpu port */
-	qca8k_write(priv, QCA8K_REG_PORT_HDR_CTRL(QCA8K_CPU_PORT),
-		    QCA8K_PORT_HDR_CTRL_ALL << QCA8K_PORT_HDR_CTRL_TX_S |
-		    QCA8K_PORT_HDR_CTRL_ALL << QCA8K_PORT_HDR_CTRL_RX_S);
+	ret = qca8k_write(priv, QCA8K_REG_PORT_HDR_CTRL(QCA8K_CPU_PORT),
+			  QCA8K_PORT_HDR_CTRL_ALL << QCA8K_PORT_HDR_CTRL_TX_S |
+			  QCA8K_PORT_HDR_CTRL_ALL << QCA8K_PORT_HDR_CTRL_RX_S);
+	if (ret) {
+		dev_err(priv->dev, "failed enabling QCA header mode");
+		return ret;
+	}
 
 	/* Disable forwarding by default on all ports */
-	for (i = 0; i < QCA8K_NUM_PORTS; i++)
-		qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i),
-			  QCA8K_PORT_LOOKUP_MEMBER, 0);
+	for (i = 0; i < QCA8K_NUM_PORTS; i++) {
+		ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i),
+				QCA8K_PORT_LOOKUP_MEMBER, 0);
+		if (ret)
+			return ret;
+	}
 
 	/* Disable MAC by default on all ports */
 	for (i = 1; i < QCA8K_NUM_PORTS; i++)
 		qca8k_port_set_status(priv, i, 0);
 
 	/* Forward all unknown frames to CPU port for Linux processing */
-	qca8k_write(priv, QCA8K_REG_GLOBAL_FW_CTRL1,
-		    BIT(0) << QCA8K_GLOBAL_FW_CTRL1_IGMP_DP_S |
-		    BIT(0) << QCA8K_GLOBAL_FW_CTRL1_BC_DP_S |
-		    BIT(0) << QCA8K_GLOBAL_FW_CTRL1_MC_DP_S |
-		    BIT(0) << QCA8K_GLOBAL_FW_CTRL1_UC_DP_S);
+	ret = qca8k_write(priv, QCA8K_REG_GLOBAL_FW_CTRL1,
+			  BIT(0) << QCA8K_GLOBAL_FW_CTRL1_IGMP_DP_S |
+			  BIT(0) << QCA8K_GLOBAL_FW_CTRL1_BC_DP_S |
+			  BIT(0) << QCA8K_GLOBAL_FW_CTRL1_MC_DP_S |
+			  BIT(0) << QCA8K_GLOBAL_FW_CTRL1_UC_DP_S);
+	if (ret)
+		return ret;
 
 	/* Setup connection between CPU port & user ports */
 	for (i = 0; i < QCA8K_NUM_PORTS; i++) {
 		/* CPU port gets connected to all user ports of the switch */
 		if (dsa_is_cpu_port(ds, i)) {
-			qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(QCA8K_CPU_PORT),
-				  QCA8K_PORT_LOOKUP_MEMBER, dsa_user_ports(ds));
+			ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(QCA8K_CPU_PORT),
+					QCA8K_PORT_LOOKUP_MEMBER, dsa_user_ports(ds));
+			if (ret)
+				return ret;
 		}
 
 		/* Individual user ports get connected to CPU port only */
 		if (dsa_is_user_port(ds, i)) {
 			int shift = 16 * (i % 2);
 
-			qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i),
-				  QCA8K_PORT_LOOKUP_MEMBER,
-				  BIT(QCA8K_CPU_PORT));
+			ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i),
+					QCA8K_PORT_LOOKUP_MEMBER,
+					BIT(QCA8K_CPU_PORT));
+			if (ret)
+				return ret;
 
 			/* Enable ARP Auto-learning by default */
-			qca8k_reg_set(priv, QCA8K_PORT_LOOKUP_CTRL(i),
-				      QCA8K_PORT_LOOKUP_LEARN);
+			ret = qca8k_reg_set(priv, QCA8K_PORT_LOOKUP_CTRL(i),
+					    QCA8K_PORT_LOOKUP_LEARN);
+			if (ret)
+				return ret;
 
 			/* For port based vlans to work we need to set the
 			 * default egress vid
 			 */
-			qca8k_rmw(priv, QCA8K_EGRESS_VLAN(i),
-				  0xfff << shift,
-				  QCA8K_PORT_VID_DEF << shift);
-			qca8k_write(priv, QCA8K_REG_PORT_VLAN_CTRL0(i),
-				    QCA8K_PORT_VLAN_CVID(QCA8K_PORT_VID_DEF) |
-				    QCA8K_PORT_VLAN_SVID(QCA8K_PORT_VID_DEF));
+			ret = qca8k_rmw(priv, QCA8K_EGRESS_VLAN(i),
+					0xfff << shift,
+					QCA8K_PORT_VID_DEF << shift);
+			if (ret)
+				return ret;
+
+			ret = qca8k_write(priv, QCA8K_REG_PORT_VLAN_CTRL0(i),
+					  QCA8K_PORT_VLAN_CVID(QCA8K_PORT_VID_DEF) |
+					  QCA8K_PORT_VLAN_SVID(QCA8K_PORT_VID_DEF));
+			if (ret)
+				return ret;
 		}
 	}
 
+	/* The port 5 of the qca8337 have some problem in flood condition. The
+	 * original legacy driver had some specific buffer and priority settings
+	 * for the different port suggested by the QCA switch team. Add this
+	 * missing settings to improve switch stability under load condition.
+	 * This problem is limited to qca8337 and other qca8k switch are not affected.
+	 */
+	if (priv->switch_id == QCA8K_ID_QCA8337) {
+		for (i = 0; i < QCA8K_NUM_PORTS; i++) {
+			switch (i) {
+			/* The 2 CPU port and port 5 requires some different
+			 * priority than any other ports.
+			 */
+			case 0:
+			case 5:
+			case 6:
+				mask = QCA8K_PORT_HOL_CTRL0_EG_PRI0(0x3) |
+					QCA8K_PORT_HOL_CTRL0_EG_PRI1(0x4) |
+					QCA8K_PORT_HOL_CTRL0_EG_PRI2(0x4) |
+					QCA8K_PORT_HOL_CTRL0_EG_PRI3(0x4) |
+					QCA8K_PORT_HOL_CTRL0_EG_PRI4(0x6) |
+					QCA8K_PORT_HOL_CTRL0_EG_PRI5(0x8) |
+					QCA8K_PORT_HOL_CTRL0_EG_PORT(0x1e);
+				break;
+			default:
+				mask = QCA8K_PORT_HOL_CTRL0_EG_PRI0(0x3) |
+					QCA8K_PORT_HOL_CTRL0_EG_PRI1(0x4) |
+					QCA8K_PORT_HOL_CTRL0_EG_PRI2(0x6) |
+					QCA8K_PORT_HOL_CTRL0_EG_PRI3(0x8) |
+					QCA8K_PORT_HOL_CTRL0_EG_PORT(0x19);
+			}
+			qca8k_write(priv, QCA8K_REG_PORT_HOL_CTRL0(i), mask);
+
+			mask = QCA8K_PORT_HOL_CTRL1_ING(0x6) |
+			QCA8K_PORT_HOL_CTRL1_EG_PRI_BUF_EN |
+			QCA8K_PORT_HOL_CTRL1_EG_PORT_BUF_EN |
+			QCA8K_PORT_HOL_CTRL1_WRED_EN;
+			qca8k_rmw(priv, QCA8K_REG_PORT_HOL_CTRL1(i),
+				  QCA8K_PORT_HOL_CTRL1_ING_BUF |
+				  QCA8K_PORT_HOL_CTRL1_EG_PRI_BUF_EN |
+				  QCA8K_PORT_HOL_CTRL1_EG_PORT_BUF_EN |
+				  QCA8K_PORT_HOL_CTRL1_WRED_EN,
+				  mask);
+		}
+	}
+
+	/* Special GLOBAL_FC_THRESH value are needed for ar8327 switch */
+	if (priv->switch_id == QCA8K_ID_QCA8327) {
+		mask = QCA8K_GLOBAL_FC_GOL_XON_THRES(288) |
+		       QCA8K_GLOBAL_FC_GOL_XOFF_THRES(496);
+		qca8k_rmw(priv, QCA8K_REG_GLOBAL_FC_THRESH,
+			  QCA8K_GLOBAL_FC_GOL_XON_THRES_S |
+			  QCA8K_GLOBAL_FC_GOL_XOFF_THRES_S,
+			  mask);
+	}
+
 	/* Setup our port MTUs to match power on defaults */
 	for (i = 0; i < QCA8K_NUM_PORTS; i++)
 		priv->port_mtu[i] = ETH_FRAME_LEN + ETH_FCS_LEN;
-	qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, ETH_FRAME_LEN + ETH_FCS_LEN);
+	ret = qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, ETH_FRAME_LEN + ETH_FCS_LEN);
+	if (ret)
+		dev_warn(priv->dev, "failed setting MTU settings");
 
 	/* Flush the FDB table */
 	qca8k_fdb_flush(priv);
@@ -797,11 +1128,14 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode,
 {
 	struct qca8k_priv *priv = ds->priv;
 	u32 reg, val;
+	int ret;
 
 	switch (port) {
 	case 0: /* 1st CPU port */
 		if (state->interface != PHY_INTERFACE_MODE_RGMII &&
 		    state->interface != PHY_INTERFACE_MODE_RGMII_ID &&
+		    state->interface != PHY_INTERFACE_MODE_RGMII_TXID &&
+		    state->interface != PHY_INTERFACE_MODE_RGMII_RXID &&
 		    state->interface != PHY_INTERFACE_MODE_SGMII)
 			return;
 
@@ -817,6 +1151,8 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode,
 	case 6: /* 2nd CPU port / external PHY */
 		if (state->interface != PHY_INTERFACE_MODE_RGMII &&
 		    state->interface != PHY_INTERFACE_MODE_RGMII_ID &&
+		    state->interface != PHY_INTERFACE_MODE_RGMII_TXID &&
+		    state->interface != PHY_INTERFACE_MODE_RGMII_RXID &&
 		    state->interface != PHY_INTERFACE_MODE_SGMII &&
 		    state->interface != PHY_INTERFACE_MODE_1000BASEX)
 			return;
@@ -840,16 +1176,22 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode,
 		qca8k_write(priv, reg, QCA8K_PORT_PAD_RGMII_EN);
 		break;
 	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
 		/* RGMII_ID needs internal delay. This is enabled through
 		 * PORT5_PAD_CTRL for all ports, rather than individual port
 		 * registers
 		 */
 		qca8k_write(priv, reg,
 			    QCA8K_PORT_PAD_RGMII_EN |
-			    QCA8K_PORT_PAD_RGMII_TX_DELAY(QCA8K_MAX_DELAY) |
-			    QCA8K_PORT_PAD_RGMII_RX_DELAY(QCA8K_MAX_DELAY));
-		qca8k_write(priv, QCA8K_REG_PORT5_PAD_CTRL,
+			    QCA8K_PORT_PAD_RGMII_TX_DELAY(priv->rgmii_tx_delay) |
+			    QCA8K_PORT_PAD_RGMII_RX_DELAY(priv->rgmii_rx_delay) |
+			    QCA8K_PORT_PAD_RGMII_TX_DELAY_EN |
 			    QCA8K_PORT_PAD_RGMII_RX_DELAY_EN);
+		/* QCA8337 requires to set rgmii rx delay */
+		if (priv->switch_id == QCA8K_ID_QCA8337)
+			qca8k_write(priv, QCA8K_REG_PORT5_PAD_CTRL,
+				    QCA8K_PORT_PAD_RGMII_RX_DELAY_EN);
 		break;
 	case PHY_INTERFACE_MODE_SGMII:
 	case PHY_INTERFACE_MODE_1000BASEX:
@@ -857,7 +1199,9 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode,
 		qca8k_write(priv, reg, QCA8K_PORT_PAD_SGMII_EN);
 
 		/* Enable/disable SerDes auto-negotiation as necessary */
-		val = qca8k_read(priv, QCA8K_REG_PWS);
+		ret = qca8k_read(priv, QCA8K_REG_PWS, &val);
+		if (ret)
+			return;
 		if (phylink_autoneg_inband(mode))
 			val &= ~QCA8K_PWS_SERDES_AEN_DIS;
 		else
@@ -865,7 +1209,9 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode,
 		qca8k_write(priv, QCA8K_REG_PWS, val);
 
 		/* Configure the SGMII parameters */
-		val = qca8k_read(priv, QCA8K_REG_SGMII_CTRL);
+		ret = qca8k_read(priv, QCA8K_REG_SGMII_CTRL, &val);
+		if (ret)
+			return;
 
 		val |= QCA8K_SGMII_EN_PLL | QCA8K_SGMII_EN_RX |
 			QCA8K_SGMII_EN_TX | QCA8K_SGMII_EN_SD;
@@ -903,6 +1249,8 @@ qca8k_phylink_validate(struct dsa_switch *ds, int port,
 		if (state->interface != PHY_INTERFACE_MODE_NA &&
 		    state->interface != PHY_INTERFACE_MODE_RGMII &&
 		    state->interface != PHY_INTERFACE_MODE_RGMII_ID &&
+		    state->interface != PHY_INTERFACE_MODE_RGMII_TXID &&
+		    state->interface != PHY_INTERFACE_MODE_RGMII_RXID &&
 		    state->interface != PHY_INTERFACE_MODE_SGMII)
 			goto unsupported;
 		break;
@@ -913,13 +1261,16 @@ qca8k_phylink_validate(struct dsa_switch *ds, int port,
 	case 5:
 		/* Internal PHY */
 		if (state->interface != PHY_INTERFACE_MODE_NA &&
-		    state->interface != PHY_INTERFACE_MODE_GMII)
+		    state->interface != PHY_INTERFACE_MODE_GMII &&
+		    state->interface != PHY_INTERFACE_MODE_INTERNAL)
 			goto unsupported;
 		break;
 	case 6: /* 2nd CPU port / external PHY */
 		if (state->interface != PHY_INTERFACE_MODE_NA &&
 		    state->interface != PHY_INTERFACE_MODE_RGMII &&
 		    state->interface != PHY_INTERFACE_MODE_RGMII_ID &&
+		    state->interface != PHY_INTERFACE_MODE_RGMII_TXID &&
+		    state->interface != PHY_INTERFACE_MODE_RGMII_RXID &&
 		    state->interface != PHY_INTERFACE_MODE_SGMII &&
 		    state->interface != PHY_INTERFACE_MODE_1000BASEX)
 			goto unsupported;
@@ -955,8 +1306,11 @@ qca8k_phylink_mac_link_state(struct dsa_switch *ds, int port,
 {
 	struct qca8k_priv *priv = ds->priv;
 	u32 reg;
+	int ret;
 
-	reg = qca8k_read(priv, QCA8K_REG_PORT_STATUS(port));
+	ret = qca8k_read(priv, QCA8K_REG_PORT_STATUS(port), &reg);
+	if (ret < 0)
+		return ret;
 
 	state->link = !!(reg & QCA8K_PORT_STATUS_LINK_UP);
 	state->an_complete = state->link;
@@ -1057,18 +1411,27 @@ qca8k_get_ethtool_stats(struct dsa_switch *ds, int port,
 {
 	struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv;
 	const struct qca8k_mib_desc *mib;
-	u32 reg, i;
-	u64 hi;
+	u32 reg, i, val;
+	u32 hi = 0;
+	int ret;
 
 	for (i = 0; i < ARRAY_SIZE(ar8327_mib); i++) {
 		mib = &ar8327_mib[i];
 		reg = QCA8K_PORT_MIB_COUNTER(port) + mib->offset;
 
-		data[i] = qca8k_read(priv, reg);
+		ret = qca8k_read(priv, reg, &val);
+		if (ret < 0)
+			continue;
+
 		if (mib->size == 2) {
-			hi = qca8k_read(priv, reg + 4);
-			data[i] |= hi << 32;
+			ret = qca8k_read(priv, reg + 4, &hi);
+			if (ret < 0)
+				continue;
 		}
+
+		data[i] = val;
+		if (mib->size == 2)
+			data[i] |= (u64)hi << 32;
 	}
 }
 
@@ -1087,17 +1450,22 @@ qca8k_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *eee)
 	struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv;
 	u32 lpi_en = QCA8K_REG_EEE_CTRL_LPI_EN(port);
 	u32 reg;
+	int ret;
 
 	mutex_lock(&priv->reg_mutex);
-	reg = qca8k_read(priv, QCA8K_REG_EEE_CTRL);
+	ret = qca8k_read(priv, QCA8K_REG_EEE_CTRL, &reg);
+	if (ret < 0)
+		goto exit;
+
 	if (eee->eee_enabled)
 		reg |= lpi_en;
 	else
 		reg &= ~lpi_en;
-	qca8k_write(priv, QCA8K_REG_EEE_CTRL, reg);
-	mutex_unlock(&priv->reg_mutex);
+	ret = qca8k_write(priv, QCA8K_REG_EEE_CTRL, reg);
 
-	return 0;
+exit:
+	mutex_unlock(&priv->reg_mutex);
+	return ret;
 }
 
 static int
@@ -1141,7 +1509,7 @@ qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br)
 {
 	struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv;
 	int port_mask = BIT(QCA8K_CPU_PORT);
-	int i;
+	int i, ret;
 
 	for (i = 1; i < QCA8K_NUM_PORTS; i++) {
 		if (dsa_to_port(ds, i)->bridge_dev != br)
@@ -1149,17 +1517,20 @@ qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br)
 		/* Add this port to the portvlan mask of the other ports
 		 * in the bridge
 		 */
-		qca8k_reg_set(priv,
-			      QCA8K_PORT_LOOKUP_CTRL(i),
-			      BIT(port));
+		ret = qca8k_reg_set(priv,
+				    QCA8K_PORT_LOOKUP_CTRL(i),
+				    BIT(port));
+		if (ret)
+			return ret;
 		if (i != port)
 			port_mask |= BIT(i);
 	}
+
 	/* Add all other ports to this ports portvlan mask */
-	qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port),
-		  QCA8K_PORT_LOOKUP_MEMBER, port_mask);
+	ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port),
+			QCA8K_PORT_LOOKUP_MEMBER, port_mask);
 
-	return 0;
+	return ret;
 }
 
 static void
@@ -1223,9 +1594,7 @@ qca8k_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
 			mtu = priv->port_mtu[i];
 
 	/* Include L2 header / FCS length */
-	qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, mtu + ETH_HLEN + ETH_FCS_LEN);
-
-	return 0;
+	return qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, mtu + ETH_HLEN + ETH_FCS_LEN);
 }
 
 static int
@@ -1298,18 +1667,19 @@ qca8k_port_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering,
 			  struct netlink_ext_ack *extack)
 {
 	struct qca8k_priv *priv = ds->priv;
+	int ret;
 
 	if (vlan_filtering) {
-		qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port),
-			  QCA8K_PORT_LOOKUP_VLAN_MODE,
-			  QCA8K_PORT_LOOKUP_VLAN_MODE_SECURE);
+		ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port),
+				QCA8K_PORT_LOOKUP_VLAN_MODE,
+				QCA8K_PORT_LOOKUP_VLAN_MODE_SECURE);
 	} else {
-		qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port),
-			  QCA8K_PORT_LOOKUP_VLAN_MODE,
-			  QCA8K_PORT_LOOKUP_VLAN_MODE_NONE);
+		ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port),
+				QCA8K_PORT_LOOKUP_VLAN_MODE,
+				QCA8K_PORT_LOOKUP_VLAN_MODE_NONE);
 	}
 
-	return 0;
+	return ret;
 }
 
 static int
@@ -1320,7 +1690,7 @@ qca8k_port_vlan_add(struct dsa_switch *ds, int port,
 	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
 	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
 	struct qca8k_priv *priv = ds->priv;
-	int ret = 0;
+	int ret;
 
 	ret = qca8k_vlan_add(priv, port, vlan->vid, untagged);
 	if (ret) {
@@ -1331,14 +1701,17 @@ qca8k_port_vlan_add(struct dsa_switch *ds, int port,
 	if (pvid) {
 		int shift = 16 * (port % 2);
 
-		qca8k_rmw(priv, QCA8K_EGRESS_VLAN(port),
-			  0xfff << shift, vlan->vid << shift);
-		qca8k_write(priv, QCA8K_REG_PORT_VLAN_CTRL0(port),
-			    QCA8K_PORT_VLAN_CVID(vlan->vid) |
-			    QCA8K_PORT_VLAN_SVID(vlan->vid));
+		ret = qca8k_rmw(priv, QCA8K_EGRESS_VLAN(port),
+				0xfff << shift, vlan->vid << shift);
+		if (ret)
+			return ret;
+
+		ret = qca8k_write(priv, QCA8K_REG_PORT_VLAN_CTRL0(port),
+				  QCA8K_PORT_VLAN_CVID(vlan->vid) |
+				  QCA8K_PORT_VLAN_SVID(vlan->vid));
 	}
 
-	return 0;
+	return ret;
 }
 
 static int
@@ -1346,7 +1719,7 @@ qca8k_port_vlan_del(struct dsa_switch *ds, int port,
 		    const struct switchdev_obj_port_vlan *vlan)
 {
 	struct qca8k_priv *priv = ds->priv;
-	int ret = 0;
+	int ret;
 
 	ret = qca8k_vlan_del(priv, port, vlan->vid);
 	if (ret)
@@ -1355,6 +1728,22 @@ qca8k_port_vlan_del(struct dsa_switch *ds, int port,
 	return ret;
 }
 
+static u32 qca8k_get_phy_flags(struct dsa_switch *ds, int port)
+{
+	struct qca8k_priv *priv = ds->priv;
+
+	/* Communicate to the phy internal driver the switch revision.
+	 * Based on the switch revision different values needs to be
+	 * set to the dbg and mmd reg on the phy.
+	 * The first 2 bit are used to communicate the switch revision
+	 * to the phy driver.
+	 */
+	if (port > 0 && port < 6)
+		return priv->switch_revision;
+
+	return 0;
+}
+
 static enum dsa_tag_protocol
 qca8k_get_tag_protocol(struct dsa_switch *ds, int port,
 		       enum dsa_tag_protocol mp)
@@ -1388,13 +1777,44 @@ static const struct dsa_switch_ops qca8k_switch_ops = {
 	.phylink_mac_config	= qca8k_phylink_mac_config,
 	.phylink_mac_link_down	= qca8k_phylink_mac_link_down,
 	.phylink_mac_link_up	= qca8k_phylink_mac_link_up,
+	.get_phy_flags		= qca8k_get_phy_flags,
 };
 
+static int qca8k_read_switch_id(struct qca8k_priv *priv)
+{
+	const struct qca8k_match_data *data;
+	u32 val;
+	u8 id;
+	int ret;
+
+	/* get the switches ID from the compatible */
+	data = of_device_get_match_data(priv->dev);
+	if (!data)
+		return -ENODEV;
+
+	ret = qca8k_read(priv, QCA8K_REG_MASK_CTRL, &val);
+	if (ret < 0)
+		return -ENODEV;
+
+	id = QCA8K_MASK_CTRL_DEVICE_ID(val & QCA8K_MASK_CTRL_DEVICE_ID_MASK);
+	if (id != data->id) {
+		dev_err(priv->dev, "Switch id detected %x but expected %x", id, data->id);
+		return -ENODEV;
+	}
+
+	priv->switch_id = id;
+
+	/* Save revision to communicate to the internal PHY driver */
+	priv->switch_revision = (val & QCA8K_MASK_CTRL_REV_ID_MASK);
+
+	return 0;
+}
+
 static int
 qca8k_sw_probe(struct mdio_device *mdiodev)
 {
 	struct qca8k_priv *priv;
-	u32 id;
+	int ret;
 
 	/* allocate the private data struct so that we can probe the switches
 	 * ID register
@@ -1420,12 +1840,10 @@ qca8k_sw_probe(struct mdio_device *mdiodev)
 		gpiod_set_value_cansleep(priv->reset_gpio, 0);
 	}
 
-	/* read the switches ID register */
-	id = qca8k_read(priv, QCA8K_REG_MASK_CTRL);
-	id >>= QCA8K_MASK_CTRL_ID_S;
-	id &= QCA8K_MASK_CTRL_ID_M;
-	if (id != QCA8K_ID_QCA8337)
-		return -ENODEV;
+	/* Check the detected switch id */
+	ret = qca8k_read_switch_id(priv);
+	if (ret)
+		return ret;
 
 	priv->ds = devm_kzalloc(&mdiodev->dev, sizeof(*priv->ds), GFP_KERNEL);
 	if (!priv->ds)
@@ -1490,9 +1908,18 @@ static int qca8k_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(qca8k_pm_ops,
 			 qca8k_suspend, qca8k_resume);
 
+static const struct qca8k_match_data qca832x = {
+	.id = QCA8K_ID_QCA8327,
+};
+
+static const struct qca8k_match_data qca833x = {
+	.id = QCA8K_ID_QCA8337,
+};
+
 static const struct of_device_id qca8k_of_match[] = {
-	{ .compatible = "qca,qca8334" },
-	{ .compatible = "qca,qca8337" },
+	{ .compatible = "qca,qca8327", .data = &qca832x },
+	{ .compatible = "qca,qca8334", .data = &qca833x },
+	{ .compatible = "qca,qca8337", .data = &qca833x },
 	{ /* sentinel */ },
 };
 
diff --git a/drivers/net/dsa/qca8k.h b/drivers/net/dsa/qca8k.h
index 7ca4b93e0bb5..ed3b05ad6745 100644
--- a/drivers/net/dsa/qca8k.h
+++ b/drivers/net/dsa/qca8k.h
@@ -15,9 +15,13 @@
 #define QCA8K_NUM_PORTS					7
 #define QCA8K_MAX_MTU					9000
 
+#define PHY_ID_QCA8327					0x004dd034
+#define QCA8K_ID_QCA8327				0x12
 #define PHY_ID_QCA8337					0x004dd036
 #define QCA8K_ID_QCA8337				0x13
 
+#define QCA8K_BUSY_WAIT_TIMEOUT				2000
+
 #define QCA8K_NUM_FDB_RECORDS				2048
 
 #define QCA8K_CPU_PORT					0
@@ -26,18 +30,19 @@
 
 /* Global control registers */
 #define QCA8K_REG_MASK_CTRL				0x000
-#define   QCA8K_MASK_CTRL_ID_M				0xff
-#define   QCA8K_MASK_CTRL_ID_S				8
+#define   QCA8K_MASK_CTRL_REV_ID_MASK			GENMASK(7, 0)
+#define   QCA8K_MASK_CTRL_REV_ID(x)			((x) >> 0)
+#define   QCA8K_MASK_CTRL_DEVICE_ID_MASK		GENMASK(15, 8)
+#define   QCA8K_MASK_CTRL_DEVICE_ID(x)			((x) >> 8)
 #define QCA8K_REG_PORT0_PAD_CTRL			0x004
 #define QCA8K_REG_PORT5_PAD_CTRL			0x008
 #define QCA8K_REG_PORT6_PAD_CTRL			0x00c
 #define   QCA8K_PORT_PAD_RGMII_EN			BIT(26)
-#define   QCA8K_PORT_PAD_RGMII_TX_DELAY(x)		\
-						((0x8 + (x & 0x3)) << 22)
-#define   QCA8K_PORT_PAD_RGMII_RX_DELAY(x)		\
-						((0x10 + (x & 0x3)) << 20)
-#define   QCA8K_MAX_DELAY				3
+#define   QCA8K_PORT_PAD_RGMII_TX_DELAY(x)		((x) << 22)
+#define   QCA8K_PORT_PAD_RGMII_RX_DELAY(x)		((x) << 20)
+#define	  QCA8K_PORT_PAD_RGMII_TX_DELAY_EN		BIT(25)
 #define   QCA8K_PORT_PAD_RGMII_RX_DELAY_EN		BIT(24)
+#define   QCA8K_MAX_DELAY				3
 #define   QCA8K_PORT_PAD_SGMII_EN			BIT(7)
 #define QCA8K_REG_PWS					0x010
 #define   QCA8K_PWS_SERDES_AEN_DIS			BIT(7)
@@ -164,6 +169,36 @@
 #define   QCA8K_PORT_LOOKUP_STATE			GENMASK(18, 16)
 #define   QCA8K_PORT_LOOKUP_LEARN			BIT(20)
 
+#define QCA8K_REG_GLOBAL_FC_THRESH			0x800
+#define   QCA8K_GLOBAL_FC_GOL_XON_THRES(x)		((x) << 16)
+#define   QCA8K_GLOBAL_FC_GOL_XON_THRES_S		GENMASK(24, 16)
+#define   QCA8K_GLOBAL_FC_GOL_XOFF_THRES(x)		((x) << 0)
+#define   QCA8K_GLOBAL_FC_GOL_XOFF_THRES_S		GENMASK(8, 0)
+
+#define QCA8K_REG_PORT_HOL_CTRL0(_i)			(0x970 + (_i) * 0x8)
+#define   QCA8K_PORT_HOL_CTRL0_EG_PRI0_BUF		GENMASK(3, 0)
+#define   QCA8K_PORT_HOL_CTRL0_EG_PRI0(x)		((x) << 0)
+#define   QCA8K_PORT_HOL_CTRL0_EG_PRI1_BUF		GENMASK(7, 4)
+#define   QCA8K_PORT_HOL_CTRL0_EG_PRI1(x)		((x) << 4)
+#define   QCA8K_PORT_HOL_CTRL0_EG_PRI2_BUF		GENMASK(11, 8)
+#define   QCA8K_PORT_HOL_CTRL0_EG_PRI2(x)		((x) << 8)
+#define   QCA8K_PORT_HOL_CTRL0_EG_PRI3_BUF		GENMASK(15, 12)
+#define   QCA8K_PORT_HOL_CTRL0_EG_PRI3(x)		((x) << 12)
+#define   QCA8K_PORT_HOL_CTRL0_EG_PRI4_BUF		GENMASK(19, 16)
+#define   QCA8K_PORT_HOL_CTRL0_EG_PRI4(x)		((x) << 16)
+#define   QCA8K_PORT_HOL_CTRL0_EG_PRI5_BUF		GENMASK(23, 20)
+#define   QCA8K_PORT_HOL_CTRL0_EG_PRI5(x)		((x) << 20)
+#define   QCA8K_PORT_HOL_CTRL0_EG_PORT_BUF		GENMASK(29, 24)
+#define   QCA8K_PORT_HOL_CTRL0_EG_PORT(x)		((x) << 24)
+
+#define QCA8K_REG_PORT_HOL_CTRL1(_i)			(0x974 + (_i) * 0x8)
+#define   QCA8K_PORT_HOL_CTRL1_ING_BUF			GENMASK(3, 0)
+#define   QCA8K_PORT_HOL_CTRL1_ING(x)			((x) << 0)
+#define   QCA8K_PORT_HOL_CTRL1_EG_PRI_BUF_EN		BIT(6)
+#define   QCA8K_PORT_HOL_CTRL1_EG_PORT_BUF_EN		BIT(7)
+#define   QCA8K_PORT_HOL_CTRL1_WRED_EN			BIT(8)
+#define   QCA8K_PORT_HOL_CTRL1_EG_MIRROR_EN		BIT(16)
+
 /* Pkt edit registers */
 #define QCA8K_EGRESS_VLAN(x)				(0x0c70 + (4 * (x / 2)))
 
@@ -211,7 +246,16 @@ struct ar8xxx_port_status {
 	int enabled;
 };
 
+struct qca8k_match_data {
+	u8 id;
+};
+
 struct qca8k_priv {
+	u8 switch_id;
+	u8 switch_revision;
+	u8 rgmii_tx_delay;
+	u8 rgmii_rx_delay;
+	bool legacy_phy_port_mapping;
 	struct regmap *regmap;
 	struct mii_bus *bus;
 	struct ar8xxx_port_status port_sts[QCA8K_NUM_PORTS];
diff --git a/drivers/net/dsa/sja1105/Kconfig b/drivers/net/dsa/sja1105/Kconfig
index 5e83b365f17a..8383cd6d2178 100644
--- a/drivers/net/dsa/sja1105/Kconfig
+++ b/drivers/net/dsa/sja1105/Kconfig
@@ -3,6 +3,7 @@ config NET_DSA_SJA1105
 tristate "NXP SJA1105 Ethernet switch family support"
 	depends on NET_DSA && SPI
 	select NET_DSA_TAG_SJA1105
+	select PCS_XPCS
 	select PACKING
 	select CRC32
 	help
diff --git a/drivers/net/dsa/sja1105/Makefile b/drivers/net/dsa/sja1105/Makefile
index a860e3a910be..40d69e6c0bae 100644
--- a/drivers/net/dsa/sja1105/Makefile
+++ b/drivers/net/dsa/sja1105/Makefile
@@ -4,6 +4,7 @@ obj-$(CONFIG_NET_DSA_SJA1105) += sja1105.o
 sja1105-objs := \
     sja1105_spi.o \
     sja1105_main.o \
+    sja1105_mdio.o \
     sja1105_flower.o \
     sja1105_ethtool.o \
     sja1105_devlink.o \
diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h
index f9e87fb33da0..221c7abdef0e 100644
--- a/drivers/net/dsa/sja1105/sja1105.h
+++ b/drivers/net/dsa/sja1105/sja1105.h
@@ -13,14 +13,12 @@
 #include <linux/mutex.h>
 #include "sja1105_static_config.h"
 
-#define SJA1105_NUM_PORTS		5
-#define SJA1105_NUM_TC			8
 #define SJA1105ET_FDB_BIN_SIZE		4
 /* The hardware value is in multiples of 10 ms.
  * The passed parameter is in multiples of 1 ms.
  */
 #define SJA1105_AGEING_TIME_MS(ms)	((ms) / 10)
-#define SJA1105_NUM_L2_POLICERS		45
+#define SJA1105_NUM_L2_POLICERS		SJA1110_MAX_L2_POLICING_COUNT
 
 typedef enum {
 	SPI_READ = 0,
@@ -30,6 +28,14 @@ typedef enum {
 #include "sja1105_tas.h"
 #include "sja1105_ptp.h"
 
+enum sja1105_stats_area {
+	MAC,
+	HL1,
+	HL2,
+	ETHER,
+	__MAX_SJA1105_STATS_AREA,
+};
+
 /* Keeps the different addresses between E/T and P/Q/R/S */
 struct sja1105_regs {
 	u64 device_id;
@@ -39,7 +45,6 @@ struct sja1105_regs {
 	u64 rgu;
 	u64 vl_status;
 	u64 config;
-	u64 sgmii;
 	u64 rmii_pll1;
 	u64 ptppinst;
 	u64 ptppindur;
@@ -49,23 +54,41 @@ struct sja1105_regs {
 	u64 ptpclkcorp;
 	u64 ptpsyncts;
 	u64 ptpschtm;
-	u64 ptpegr_ts[SJA1105_NUM_PORTS];
-	u64 pad_mii_tx[SJA1105_NUM_PORTS];
-	u64 pad_mii_rx[SJA1105_NUM_PORTS];
-	u64 pad_mii_id[SJA1105_NUM_PORTS];
-	u64 cgu_idiv[SJA1105_NUM_PORTS];
-	u64 mii_tx_clk[SJA1105_NUM_PORTS];
-	u64 mii_rx_clk[SJA1105_NUM_PORTS];
-	u64 mii_ext_tx_clk[SJA1105_NUM_PORTS];
-	u64 mii_ext_rx_clk[SJA1105_NUM_PORTS];
-	u64 rgmii_tx_clk[SJA1105_NUM_PORTS];
-	u64 rmii_ref_clk[SJA1105_NUM_PORTS];
-	u64 rmii_ext_tx_clk[SJA1105_NUM_PORTS];
-	u64 mac[SJA1105_NUM_PORTS];
-	u64 mac_hl1[SJA1105_NUM_PORTS];
-	u64 mac_hl2[SJA1105_NUM_PORTS];
-	u64 ether_stats[SJA1105_NUM_PORTS];
-	u64 qlevel[SJA1105_NUM_PORTS];
+	u64 ptpegr_ts[SJA1105_MAX_NUM_PORTS];
+	u64 pad_mii_tx[SJA1105_MAX_NUM_PORTS];
+	u64 pad_mii_rx[SJA1105_MAX_NUM_PORTS];
+	u64 pad_mii_id[SJA1105_MAX_NUM_PORTS];
+	u64 cgu_idiv[SJA1105_MAX_NUM_PORTS];
+	u64 mii_tx_clk[SJA1105_MAX_NUM_PORTS];
+	u64 mii_rx_clk[SJA1105_MAX_NUM_PORTS];
+	u64 mii_ext_tx_clk[SJA1105_MAX_NUM_PORTS];
+	u64 mii_ext_rx_clk[SJA1105_MAX_NUM_PORTS];
+	u64 rgmii_tx_clk[SJA1105_MAX_NUM_PORTS];
+	u64 rmii_ref_clk[SJA1105_MAX_NUM_PORTS];
+	u64 rmii_ext_tx_clk[SJA1105_MAX_NUM_PORTS];
+	u64 stats[__MAX_SJA1105_STATS_AREA][SJA1105_MAX_NUM_PORTS];
+	u64 mdio_100base_tx;
+	u64 mdio_100base_t1;
+	u64 pcs_base[SJA1105_MAX_NUM_PORTS];
+};
+
+struct sja1105_mdio_private {
+	struct sja1105_private *priv;
+};
+
+enum {
+	SJA1105_SPEED_AUTO,
+	SJA1105_SPEED_10MBPS,
+	SJA1105_SPEED_100MBPS,
+	SJA1105_SPEED_1000MBPS,
+	SJA1105_SPEED_2500MBPS,
+	SJA1105_SPEED_MAX,
+};
+
+enum sja1105_internal_phy_t {
+	SJA1105_NO_PHY		= 0,
+	SJA1105_PHY_BASE_TX,
+	SJA1105_PHY_BASE_T1,
 };
 
 struct sja1105_info {
@@ -85,6 +108,10 @@ struct sja1105_info {
 	 */
 	int ptpegr_ts_bytes;
 	int num_cbs_shapers;
+	int max_frame_mem;
+	int num_ports;
+	bool multiple_cascade_ports;
+	enum dsa_tag_protocol tag_proto;
 	const struct sja1105_dynamic_table_ops *dyn_ops;
 	const struct sja1105_table_ops *static_ops;
 	const struct sja1105_regs *regs;
@@ -104,7 +131,20 @@ struct sja1105_info {
 			   const unsigned char *addr, u16 vid);
 	void (*ptp_cmd_packing)(u8 *buf, struct sja1105_ptp_cmd *cmd,
 				enum packing_op op);
+	bool (*rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb);
+	void (*txtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb);
+	int (*clocking_setup)(struct sja1105_private *priv);
+	int (*pcs_mdio_read)(struct mii_bus *bus, int phy, int reg);
+	int (*pcs_mdio_write)(struct mii_bus *bus, int phy, int reg, u16 val);
+	int (*disable_microcontroller)(struct sja1105_private *priv);
 	const char *name;
+	bool supports_mii[SJA1105_MAX_NUM_PORTS];
+	bool supports_rmii[SJA1105_MAX_NUM_PORTS];
+	bool supports_rgmii[SJA1105_MAX_NUM_PORTS];
+	bool supports_sgmii[SJA1105_MAX_NUM_PORTS];
+	bool supports_2500basex[SJA1105_MAX_NUM_PORTS];
+	enum sja1105_internal_phy_t internal_phy[SJA1105_MAX_NUM_PORTS];
+	const u64 port_speed[SJA1105_SPEED_MAX];
 };
 
 enum sja1105_key_type {
@@ -202,20 +242,23 @@ enum sja1105_vlan_state {
 
 struct sja1105_private {
 	struct sja1105_static_config static_config;
-	bool rgmii_rx_delay[SJA1105_NUM_PORTS];
-	bool rgmii_tx_delay[SJA1105_NUM_PORTS];
+	bool rgmii_rx_delay[SJA1105_MAX_NUM_PORTS];
+	bool rgmii_tx_delay[SJA1105_MAX_NUM_PORTS];
+	phy_interface_t phy_mode[SJA1105_MAX_NUM_PORTS];
+	bool fixed_link[SJA1105_MAX_NUM_PORTS];
 	bool best_effort_vlan_filtering;
 	unsigned long learn_ena;
 	unsigned long ucast_egress_floods;
 	unsigned long bcast_egress_floods;
 	const struct sja1105_info *info;
+	size_t max_xfer_len;
 	struct gpio_desc *reset_gpio;
 	struct spi_device *spidev;
 	struct dsa_switch *ds;
 	struct list_head dsa_8021q_vlans;
 	struct list_head bridge_vlans;
 	struct sja1105_flow_block flow_block;
-	struct sja1105_port ports[SJA1105_NUM_PORTS];
+	struct sja1105_port ports[SJA1105_MAX_NUM_PORTS];
 	/* Serializes transmission of management frames so that
 	 * the switch doesn't confuse them with one another.
 	 */
@@ -224,6 +267,10 @@ struct sja1105_private {
 	enum sja1105_vlan_state vlan_state;
 	struct devlink_region **regions;
 	struct sja1105_cbs_entry *cbs;
+	struct mii_bus *mdio_base_t1;
+	struct mii_bus *mdio_base_tx;
+	struct mii_bus *mdio_pcs;
+	struct dw_xpcs *xpcs[SJA1105_MAX_NUM_PORTS];
 	struct sja1105_tagger_data tagger_data;
 	struct sja1105_ptp_data ptp_data;
 	struct sja1105_tas_data tas_data;
@@ -253,6 +300,14 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled,
 			   struct netlink_ext_ack *extack);
 void sja1105_frame_memory_partitioning(struct sja1105_private *priv);
 
+/* From sja1105_mdio.c */
+int sja1105_mdiobus_register(struct dsa_switch *ds);
+void sja1105_mdiobus_unregister(struct dsa_switch *ds);
+int sja1105_pcs_mdio_read(struct mii_bus *bus, int phy, int reg);
+int sja1105_pcs_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val);
+int sja1110_pcs_mdio_read(struct mii_bus *bus, int phy, int reg);
+int sja1110_pcs_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val);
+
 /* From sja1105_devlink.c */
 int sja1105_devlink_setup(struct dsa_switch *ds);
 void sja1105_devlink_teardown(struct dsa_switch *ds);
@@ -286,6 +341,10 @@ extern const struct sja1105_info sja1105p_info;
 extern const struct sja1105_info sja1105q_info;
 extern const struct sja1105_info sja1105r_info;
 extern const struct sja1105_info sja1105s_info;
+extern const struct sja1105_info sja1110a_info;
+extern const struct sja1105_info sja1110b_info;
+extern const struct sja1105_info sja1110c_info;
+extern const struct sja1105_info sja1110d_info;
 
 /* From sja1105_clocking.c */
 
@@ -301,16 +360,11 @@ typedef enum {
 	XMII_MODE_SGMII		= 3,
 } sja1105_phy_interface_t;
 
-typedef enum {
-	SJA1105_SPEED_10MBPS	= 3,
-	SJA1105_SPEED_100MBPS	= 2,
-	SJA1105_SPEED_1000MBPS	= 1,
-	SJA1105_SPEED_AUTO	= 0,
-} sja1105_speed_t;
-
 int sja1105pqrs_setup_rgmii_delay(const void *ctx, int port);
+int sja1110_setup_rgmii_delay(const void *ctx, int port);
 int sja1105_clocking_setup_port(struct sja1105_private *priv, int port);
 int sja1105_clocking_setup(struct sja1105_private *priv);
+int sja1110_disable_microcontroller(struct sja1105_private *priv);
 
 /* From sja1105_ethtool.c */
 void sja1105_get_ethtool_stats(struct dsa_switch *ds, int port, u64 *data);
@@ -331,6 +385,18 @@ enum sja1105_iotag {
 	SJA1105_S_TAG = 1, /* Outer VLAN header */
 };
 
+enum sja1110_vlan_type {
+	SJA1110_VLAN_INVALID = 0,
+	SJA1110_VLAN_C_TAG = 1, /* Single inner VLAN tag */
+	SJA1110_VLAN_S_TAG = 2, /* Single outer VLAN tag */
+	SJA1110_VLAN_D_TAG = 3, /* Double tagged, use outer tag for lookup */
+};
+
+enum sja1110_shaper_type {
+	SJA1110_LEAKY_BUCKET_SHAPER = 0,
+	SJA1110_CBS_SHAPER = 1,
+};
+
 u8 sja1105et_fdb_hash(struct sja1105_private *priv, const u8 *addr, u16 vid);
 int sja1105et_fdb_add(struct dsa_switch *ds, int port,
 		      const unsigned char *addr, u16 vid);
diff --git a/drivers/net/dsa/sja1105/sja1105_clocking.c b/drivers/net/dsa/sja1105/sja1105_clocking.c
index 2a9b8a6a5306..387a1f2f161c 100644
--- a/drivers/net/dsa/sja1105/sja1105_clocking.c
+++ b/drivers/net/dsa/sja1105/sja1105_clocking.c
@@ -6,6 +6,8 @@
 #include "sja1105.h"
 
 #define SJA1105_SIZE_CGU_CMD	4
+#define SJA1110_BASE_MCSS_CLK	SJA1110_CGU_ADDR(0x70)
+#define SJA1110_BASE_TIMER_CLK	SJA1110_CGU_ADDR(0x74)
 
 /* Common structure for CFG_PAD_MIIx_RX and CFG_PAD_MIIx_TX */
 struct sja1105_cfg_pad_mii {
@@ -61,6 +63,12 @@ struct sja1105_cgu_pll_ctrl {
 	u64 pd;
 };
 
+struct sja1110_cgu_outclk {
+	u64 clksrc;
+	u64 autoblock;
+	u64 pd;
+};
+
 enum {
 	CLKSRC_MII0_TX_CLK	= 0x00,
 	CLKSRC_MII0_RX_CLK	= 0x01,
@@ -110,6 +118,9 @@ static int sja1105_cgu_idiv_config(struct sja1105_private *priv, int port,
 	struct sja1105_cgu_idiv idiv;
 	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
 
+	if (regs->cgu_idiv[port] == SJA1105_RSV_ADDR)
+		return 0;
+
 	if (enabled && factor != 1 && factor != 10) {
 		dev_err(dev, "idiv factor must be 1 or 10\n");
 		return -ERANGE;
@@ -159,6 +170,9 @@ static int sja1105_cgu_mii_tx_clk_config(struct sja1105_private *priv,
 	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
 	int clksrc;
 
+	if (regs->mii_tx_clk[port] == SJA1105_RSV_ADDR)
+		return 0;
+
 	if (role == XMII_MAC)
 		clksrc = mac_clk_sources[port];
 	else
@@ -188,6 +202,9 @@ sja1105_cgu_mii_rx_clk_config(struct sja1105_private *priv, int port)
 		CLKSRC_MII4_RX_CLK,
 	};
 
+	if (regs->mii_rx_clk[port] == SJA1105_RSV_ADDR)
+		return 0;
+
 	/* Payload for packed_buf */
 	mii_rx_clk.clksrc    = clk_sources[port];
 	mii_rx_clk.autoblock = 1;  /* Autoblock clk while changing clksrc */
@@ -212,6 +229,9 @@ sja1105_cgu_mii_ext_tx_clk_config(struct sja1105_private *priv, int port)
 		CLKSRC_IDIV4,
 	};
 
+	if (regs->mii_ext_tx_clk[port] == SJA1105_RSV_ADDR)
+		return 0;
+
 	/* Payload for packed_buf */
 	mii_ext_tx_clk.clksrc    = clk_sources[port];
 	mii_ext_tx_clk.autoblock = 1; /* Autoblock clk while changing clksrc */
@@ -236,6 +256,9 @@ sja1105_cgu_mii_ext_rx_clk_config(struct sja1105_private *priv, int port)
 		CLKSRC_IDIV4,
 	};
 
+	if (regs->mii_ext_rx_clk[port] == SJA1105_RSV_ADDR)
+		return 0;
+
 	/* Payload for packed_buf */
 	mii_ext_rx_clk.clksrc    = clk_sources[port];
 	mii_ext_rx_clk.autoblock = 1; /* Autoblock clk while changing clksrc */
@@ -313,14 +336,17 @@ sja1105_cgu_pll_control_packing(void *buf, struct sja1105_cgu_pll_ctrl *cmd,
 }
 
 static int sja1105_cgu_rgmii_tx_clk_config(struct sja1105_private *priv,
-					   int port, sja1105_speed_t speed)
+					   int port, u64 speed)
 {
 	const struct sja1105_regs *regs = priv->info->regs;
 	struct sja1105_cgu_mii_ctrl txc;
 	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
 	int clksrc;
 
-	if (speed == SJA1105_SPEED_1000MBPS) {
+	if (regs->rgmii_tx_clk[port] == SJA1105_RSV_ADDR)
+		return 0;
+
+	if (speed == priv->info->port_speed[SJA1105_SPEED_1000MBPS]) {
 		clksrc = CLKSRC_PLL0;
 	} else {
 		int clk_sources[] = {CLKSRC_IDIV0, CLKSRC_IDIV1, CLKSRC_IDIV2,
@@ -368,6 +394,9 @@ static int sja1105_rgmii_cfg_pad_tx_config(struct sja1105_private *priv,
 	struct sja1105_cfg_pad_mii pad_mii_tx = {0};
 	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
 
+	if (regs->pad_mii_tx[port] == SJA1105_RSV_ADDR)
+		return 0;
+
 	/* Payload */
 	pad_mii_tx.d32_os    = 3; /* TXD[3:2] output stage: */
 				  /*          high noise/high speed */
@@ -394,6 +423,9 @@ static int sja1105_cfg_pad_rx_config(struct sja1105_private *priv, int port)
 	struct sja1105_cfg_pad_mii pad_mii_rx = {0};
 	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
 
+	if (regs->pad_mii_rx[port] == SJA1105_RSV_ADDR)
+		return 0;
+
 	/* Payload */
 	pad_mii_rx.d32_ih    = 0; /* RXD[3:2] input stage hysteresis: */
 				  /*          non-Schmitt (default) */
@@ -437,6 +469,35 @@ sja1105_cfg_pad_mii_id_packing(void *buf, struct sja1105_cfg_pad_mii_id *cmd,
 	sja1105_packing(buf, &cmd->txc_pd,          0,  0, size, op);
 }
 
+static void
+sja1110_cfg_pad_mii_id_packing(void *buf, struct sja1105_cfg_pad_mii_id *cmd,
+			       enum packing_op op)
+{
+	const int size = SJA1105_SIZE_CGU_CMD;
+	u64 range = 4;
+
+	/* Fields RXC_RANGE and TXC_RANGE select the input frequency range:
+	 * 0 = 2.5MHz
+	 * 1 = 25MHz
+	 * 2 = 50MHz
+	 * 3 = 125MHz
+	 * 4 = Automatically determined by port speed.
+	 * There's no point in defining a structure different than the one for
+	 * SJA1105, so just hardcode the frequency range to automatic, just as
+	 * before.
+	 */
+	sja1105_packing(buf, &cmd->rxc_stable_ovr, 26, 26, size, op);
+	sja1105_packing(buf, &cmd->rxc_delay,      25, 21, size, op);
+	sja1105_packing(buf, &range,               20, 18, size, op);
+	sja1105_packing(buf, &cmd->rxc_bypass,     17, 17, size, op);
+	sja1105_packing(buf, &cmd->rxc_pd,         16, 16, size, op);
+	sja1105_packing(buf, &cmd->txc_stable_ovr, 10, 10, size, op);
+	sja1105_packing(buf, &cmd->txc_delay,       9,  5, size, op);
+	sja1105_packing(buf, &range,                4,  2, size, op);
+	sja1105_packing(buf, &cmd->txc_bypass,      1,  1, size, op);
+	sja1105_packing(buf, &cmd->txc_pd,          0,  0, size, op);
+}
+
 /* Valid range in degrees is an integer between 73.8 and 101.7 */
 static u64 sja1105_rgmii_delay(u64 phase)
 {
@@ -495,40 +556,65 @@ int sja1105pqrs_setup_rgmii_delay(const void *ctx, int port)
 				packed_buf, SJA1105_SIZE_CGU_CMD);
 }
 
+int sja1110_setup_rgmii_delay(const void *ctx, int port)
+{
+	const struct sja1105_private *priv = ctx;
+	const struct sja1105_regs *regs = priv->info->regs;
+	struct sja1105_cfg_pad_mii_id pad_mii_id = {0};
+	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
+
+	pad_mii_id.rxc_pd = 1;
+	pad_mii_id.txc_pd = 1;
+
+	if (priv->rgmii_rx_delay[port]) {
+		pad_mii_id.rxc_delay = sja1105_rgmii_delay(90);
+		/* The "BYPASS" bit in SJA1110 is actually a "don't bypass" */
+		pad_mii_id.rxc_bypass = 1;
+		pad_mii_id.rxc_pd = 0;
+	}
+
+	if (priv->rgmii_tx_delay[port]) {
+		pad_mii_id.txc_delay = sja1105_rgmii_delay(90);
+		pad_mii_id.txc_bypass = 1;
+		pad_mii_id.txc_pd = 0;
+	}
+
+	sja1110_cfg_pad_mii_id_packing(packed_buf, &pad_mii_id, PACK);
+
+	return sja1105_xfer_buf(priv, SPI_WRITE, regs->pad_mii_id[port],
+				packed_buf, SJA1105_SIZE_CGU_CMD);
+}
+
 static int sja1105_rgmii_clocking_setup(struct sja1105_private *priv, int port,
 					sja1105_mii_role_t role)
 {
 	struct device *dev = priv->ds->dev;
 	struct sja1105_mac_config_entry *mac;
-	sja1105_speed_t speed;
+	u64 speed;
 	int rc;
 
 	mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries;
 	speed = mac[port].speed;
 
-	dev_dbg(dev, "Configuring port %d RGMII at speed %dMbps\n",
+	dev_dbg(dev, "Configuring port %d RGMII at speed %lldMbps\n",
 		port, speed);
 
-	switch (speed) {
-	case SJA1105_SPEED_1000MBPS:
+	if (speed == priv->info->port_speed[SJA1105_SPEED_1000MBPS]) {
 		/* 1000Mbps, IDIV disabled (125 MHz) */
 		rc = sja1105_cgu_idiv_config(priv, port, false, 1);
-		break;
-	case SJA1105_SPEED_100MBPS:
+	} else if (speed == priv->info->port_speed[SJA1105_SPEED_100MBPS]) {
 		/* 100Mbps, IDIV enabled, divide by 1 (25 MHz) */
 		rc = sja1105_cgu_idiv_config(priv, port, true, 1);
-		break;
-	case SJA1105_SPEED_10MBPS:
+	} else if (speed == priv->info->port_speed[SJA1105_SPEED_10MBPS]) {
 		/* 10Mbps, IDIV enabled, divide by 10 (2.5 MHz) */
 		rc = sja1105_cgu_idiv_config(priv, port, true, 10);
-		break;
-	case SJA1105_SPEED_AUTO:
+	} else if (speed == priv->info->port_speed[SJA1105_SPEED_AUTO]) {
 		/* Skip CGU configuration if there is no speed available
 		 * (e.g. link is not established yet)
 		 */
 		dev_dbg(dev, "Speed not available, skipping CGU config\n");
 		return 0;
-	default:
+	} else {
 		rc = -EINVAL;
 	}
 
@@ -546,14 +632,9 @@ static int sja1105_rgmii_clocking_setup(struct sja1105_private *priv, int port,
 		dev_err(dev, "Failed to configure Tx pad registers\n");
 		return rc;
 	}
+
 	if (!priv->info->setup_rgmii_delay)
 		return 0;
-	/* The role has no hardware effect for RGMII. However we use it as
-	 * a proxy for this interface being a MAC-to-MAC connection, with
-	 * the RGMII internal delays needing to be applied by us.
-	 */
-	if (role == XMII_MAC)
-		return 0;
 
 	return priv->info->setup_rgmii_delay(priv, port);
 }
@@ -572,6 +653,9 @@ static int sja1105_cgu_rmii_ref_clk_config(struct sja1105_private *priv,
 		CLKSRC_MII4_TX_CLK,
 	};
 
+	if (regs->rmii_ref_clk[port] == SJA1105_RSV_ADDR)
+		return 0;
+
 	/* Payload for packed_buf */
 	ref_clk.clksrc    = clk_sources[port];
 	ref_clk.autoblock = 1;      /* Autoblock clk while changing clksrc */
@@ -589,6 +673,9 @@ sja1105_cgu_rmii_ext_tx_clk_config(struct sja1105_private *priv, int port)
 	struct sja1105_cgu_mii_ctrl ext_tx_clk;
 	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
 
+	if (regs->rmii_ext_tx_clk[port] == SJA1105_RSV_ADDR)
+		return 0;
+
 	/* Payload for packed_buf */
 	ext_tx_clk.clksrc    = CLKSRC_PLL1;
 	ext_tx_clk.autoblock = 1;   /* Autoblock clk while changing clksrc */
@@ -607,6 +694,9 @@ static int sja1105_cgu_rmii_pll_config(struct sja1105_private *priv)
 	struct device *dev = priv->ds->dev;
 	int rc;
 
+	if (regs->rmii_pll1 == SJA1105_RSV_ADDR)
+		return 0;
+
 	/* PLL1 must be enabled and output 50 Mhz.
 	 * This is done by writing first 0x0A010941 to
 	 * the PLL_1_C register and then deasserting
@@ -721,12 +811,52 @@ int sja1105_clocking_setup_port(struct sja1105_private *priv, int port)
 
 int sja1105_clocking_setup(struct sja1105_private *priv)
 {
+	struct dsa_switch *ds = priv->ds;
 	int port, rc;
 
-	for (port = 0; port < SJA1105_NUM_PORTS; port++) {
+	for (port = 0; port < ds->num_ports; port++) {
 		rc = sja1105_clocking_setup_port(priv, port);
 		if (rc < 0)
 			return rc;
 	}
 	return 0;
 }
+
+static void
+sja1110_cgu_outclk_packing(void *buf, struct sja1110_cgu_outclk *outclk,
+			   enum packing_op op)
+{
+	const int size = 4;
+
+	sja1105_packing(buf, &outclk->clksrc,    27, 24, size, op);
+	sja1105_packing(buf, &outclk->autoblock, 11, 11, size, op);
+	sja1105_packing(buf, &outclk->pd,         0,  0, size, op);
+}
+
+int sja1110_disable_microcontroller(struct sja1105_private *priv)
+{
+	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
+	struct sja1110_cgu_outclk outclk_6_c = {
+		.clksrc = 0x3,
+		.pd = true,
+	};
+	struct sja1110_cgu_outclk outclk_7_c = {
+		.clksrc = 0x5,
+		.pd = true,
+	};
+	int rc;
+
+	/* Power down the BASE_TIMER_CLK to disable the watchdog timer */
+	sja1110_cgu_outclk_packing(packed_buf, &outclk_7_c, PACK);
+
+	rc = sja1105_xfer_buf(priv, SPI_WRITE, SJA1110_BASE_TIMER_CLK,
+			      packed_buf, SJA1105_SIZE_CGU_CMD);
+	if (rc)
+		return rc;
+
+	/* Power down the BASE_MCSS_CLOCK to gate the microcontroller off */
+	sja1110_cgu_outclk_packing(packed_buf, &outclk_6_c, PACK);
+
+	return sja1105_xfer_buf(priv, SPI_WRITE, SJA1110_BASE_MCSS_CLK,
+				packed_buf, SJA1105_SIZE_CGU_CMD);
+}
diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
index 12cd04b56803..4c4c04f04269 100644
--- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
+++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
@@ -78,6 +78,9 @@
  *		   on its ENTRY portion, as a result of a SPI write command.
  *		   Only the TCAM-based FDB table on SJA1105 P/Q/R/S supports
  *		   this.
+ *	OP_VALID_ANYWAY: Reading some tables through the dynamic config
+ *			 interface is possible even if the VALIDENT bit is not
+ *			 set in the writeback. So don't error out in that case.
  * - .max_entry_count: The number of entries, counting from zero, that can be
  *		       reconfigured through the dynamic interface. If a static
  *		       table can be reconfigured at all dynamically, this
@@ -103,6 +106,9 @@
 #define SJA1105PQRS_SIZE_VL_LOOKUP_DYN_CMD			\
 	(SJA1105_SIZE_DYN_CMD + SJA1105_SIZE_VL_LOOKUP_ENTRY)
 
+#define SJA1110_SIZE_VL_POLICING_DYN_CMD			\
+	(SJA1105_SIZE_DYN_CMD + SJA1105_SIZE_VL_POLICING_ENTRY)
+
 #define SJA1105ET_SIZE_MAC_CONFIG_DYN_ENTRY			\
 	SJA1105_SIZE_DYN_CMD
 
@@ -112,9 +118,15 @@
 #define SJA1105PQRS_SIZE_L2_LOOKUP_DYN_CMD			\
 	(SJA1105_SIZE_DYN_CMD + SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY)
 
+#define SJA1110_SIZE_L2_LOOKUP_DYN_CMD				\
+	(SJA1105_SIZE_DYN_CMD + SJA1110_SIZE_L2_LOOKUP_ENTRY)
+
 #define SJA1105_SIZE_VLAN_LOOKUP_DYN_CMD			\
 	(SJA1105_SIZE_DYN_CMD + 4 + SJA1105_SIZE_VLAN_LOOKUP_ENTRY)
 
+#define SJA1110_SIZE_VLAN_LOOKUP_DYN_CMD			\
+	(SJA1105_SIZE_DYN_CMD + SJA1110_SIZE_VLAN_LOOKUP_ENTRY)
+
 #define SJA1105_SIZE_L2_FORWARDING_DYN_CMD			\
 	(SJA1105_SIZE_DYN_CMD + SJA1105_SIZE_L2_FORWARDING_ENTRY)
 
@@ -130,12 +142,18 @@
 #define SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_DYN_CMD		\
 	(SJA1105_SIZE_DYN_CMD + SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY)
 
+#define SJA1110_SIZE_L2_LOOKUP_PARAMS_DYN_CMD		\
+	(SJA1105_SIZE_DYN_CMD + SJA1110_SIZE_L2_LOOKUP_PARAMS_ENTRY)
+
 #define SJA1105ET_SIZE_GENERAL_PARAMS_DYN_CMD			\
 	SJA1105_SIZE_DYN_CMD
 
 #define SJA1105PQRS_SIZE_GENERAL_PARAMS_DYN_CMD			\
 	(SJA1105_SIZE_DYN_CMD + SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY)
 
+#define SJA1110_SIZE_GENERAL_PARAMS_DYN_CMD			\
+	(SJA1105_SIZE_DYN_CMD + SJA1110_SIZE_GENERAL_PARAMS_ENTRY)
+
 #define SJA1105PQRS_SIZE_AVB_PARAMS_DYN_CMD			\
 	(SJA1105_SIZE_DYN_CMD + SJA1105PQRS_SIZE_AVB_PARAMS_ENTRY)
 
@@ -148,8 +166,17 @@
 #define SJA1105PQRS_SIZE_CBS_DYN_CMD				\
 	(SJA1105_SIZE_DYN_CMD + SJA1105PQRS_SIZE_CBS_ENTRY)
 
+#define SJA1110_SIZE_XMII_PARAMS_DYN_CMD			\
+	SJA1110_SIZE_XMII_PARAMS_ENTRY
+
+#define SJA1110_SIZE_L2_POLICING_DYN_CMD			\
+	(SJA1105_SIZE_DYN_CMD + SJA1105_SIZE_L2_POLICING_ENTRY)
+
+#define SJA1110_SIZE_L2_FORWARDING_PARAMS_DYN_CMD		\
+	SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY
+
 #define SJA1105_MAX_DYN_CMD_SIZE				\
-	SJA1105PQRS_SIZE_GENERAL_PARAMS_DYN_CMD
+	SJA1110_SIZE_GENERAL_PARAMS_DYN_CMD
 
 struct sja1105_dyn_cmd {
 	bool search;
@@ -194,6 +221,19 @@ sja1105pqrs_vl_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
 	sja1105_packing(p, &cmd->index,    9,  0, size, op);
 }
 
+static void
+sja1110_vl_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+			      enum packing_op op)
+{
+	u8 *p = buf + SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY;
+	const int size = SJA1105_SIZE_DYN_CMD;
+
+	sja1105_packing(p, &cmd->valid,   31, 31, size, op);
+	sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op);
+	sja1105_packing(p, &cmd->errors,  29, 29, size, op);
+	sja1105_packing(p, &cmd->index,   11,  0, size, op);
+}
+
 static size_t sja1105et_vl_lookup_entry_packing(void *buf, void *entry_ptr,
 						enum packing_op op)
 {
@@ -206,6 +246,18 @@ static size_t sja1105et_vl_lookup_entry_packing(void *buf, void *entry_ptr,
 }
 
 static void
+sja1110_vl_policing_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				enum packing_op op)
+{
+	u8 *p = buf + SJA1105_SIZE_VL_LOOKUP_ENTRY;
+	const int size = SJA1105_SIZE_DYN_CMD;
+
+	sja1105_packing(p, &cmd->valid,   31, 31, size, op);
+	sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op);
+	sja1105_packing(p, &cmd->index,   11,  0, size, op);
+}
+
+static void
 sja1105pqrs_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
 				  enum packing_op op)
 {
@@ -323,6 +375,18 @@ sja1105pqrs_dyn_l2_lookup_entry_packing(void *buf, void *entry_ptr,
 	return sja1105pqrs_l2_lookup_entry_packing(buf, entry_ptr, op);
 }
 
+static size_t sja1110_dyn_l2_lookup_entry_packing(void *buf, void *entry_ptr,
+						  enum packing_op op)
+{
+	struct sja1105_l2_lookup_entry *entry = entry_ptr;
+	u8 *cmd = buf + SJA1110_SIZE_L2_LOOKUP_ENTRY;
+	const int size = SJA1105_SIZE_DYN_CMD;
+
+	sja1105_packing(cmd, &entry->lockeds, 28, 28, size, op);
+
+	return sja1110_l2_lookup_entry_packing(buf, entry_ptr, op);
+}
+
 static void
 sja1105et_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
 				enum packing_op op)
@@ -434,6 +498,39 @@ sja1105_vlan_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
 			SJA1105_SIZE_VLAN_LOOKUP_ENTRY, op);
 }
 
+/* In SJA1110 there is no gap between the command and the data, yay... */
+static void
+sja1110_vlan_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				enum packing_op op)
+{
+	u8 *p = buf + SJA1110_SIZE_VLAN_LOOKUP_ENTRY;
+	const int size = SJA1105_SIZE_DYN_CMD;
+	u64 type_entry = 0;
+
+	sja1105_packing(p, &cmd->valid,   31, 31, size, op);
+	sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op);
+	sja1105_packing(p, &cmd->errors,  29, 29, size, op);
+	/* Hack: treat 'vlanid' field of struct sja1105_vlan_lookup_entry as
+	 * cmd->index.
+	 */
+	sja1105_packing(buf, &cmd->index, 38, 27,
+			SJA1110_SIZE_VLAN_LOOKUP_ENTRY, op);
+
+	/* But the VALIDENT bit has disappeared, now we are supposed to
+	 * invalidate an entry through the TYPE_ENTRY field of the entry..
+	 * This is a hack to transform the non-zero quality of the TYPE_ENTRY
+	 * field into a VALIDENT bit.
+	 */
+	if (op == PACK && !cmd->valident) {
+		sja1105_packing(buf, &type_entry, 40, 39,
+				SJA1110_SIZE_VLAN_LOOKUP_ENTRY, PACK);
+	} else if (op == UNPACK) {
+		sja1105_packing(buf, &type_entry, 40, 39,
+				SJA1110_SIZE_VLAN_LOOKUP_ENTRY, UNPACK);
+		cmd->valident = !!type_entry;
+	}
+}
+
 static void
 sja1105_l2_forwarding_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
 				  enum packing_op op)
@@ -448,6 +545,19 @@ sja1105_l2_forwarding_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
 }
 
 static void
+sja1110_l2_forwarding_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				  enum packing_op op)
+{
+	u8 *p = buf + SJA1105_SIZE_L2_FORWARDING_ENTRY;
+	const int size = SJA1105_SIZE_DYN_CMD;
+
+	sja1105_packing(p, &cmd->valid,   31, 31, size, op);
+	sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op);
+	sja1105_packing(p, &cmd->errors,  29, 29, size, op);
+	sja1105_packing(p, &cmd->index,    4,  0, size, op);
+}
+
+static void
 sja1105et_mac_config_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
 				 enum packing_op op)
 {
@@ -502,6 +612,19 @@ sja1105pqrs_mac_config_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
 }
 
 static void
+sja1110_mac_config_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+			       enum packing_op op)
+{
+	u8 *p = buf + SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY;
+	const int size = SJA1105_SIZE_DYN_CMD;
+
+	sja1105_packing(p, &cmd->valid,   31, 31, size, op);
+	sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op);
+	sja1105_packing(p, &cmd->errors,  29, 29, size, op);
+	sja1105_packing(p, &cmd->index,    3,  0, size, op);
+}
+
+static void
 sja1105et_l2_lookup_params_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
 				       enum packing_op op)
 {
@@ -534,6 +657,18 @@ sja1105pqrs_l2_lookup_params_cmd_packing(void *buf,
 }
 
 static void
+sja1110_l2_lookup_params_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				     enum packing_op op)
+{
+	u8 *p = buf + SJA1110_SIZE_L2_LOOKUP_PARAMS_ENTRY;
+	const int size = SJA1105_SIZE_DYN_CMD;
+
+	sja1105_packing(p, &cmd->valid,   31, 31, size, op);
+	sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op);
+	sja1105_packing(p, &cmd->errors,  29, 29, size, op);
+}
+
+static void
 sja1105et_general_params_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
 				     enum packing_op op)
 {
@@ -568,6 +703,18 @@ sja1105pqrs_general_params_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
 }
 
 static void
+sja1110_general_params_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				   enum packing_op op)
+{
+	u8 *p = buf + SJA1110_SIZE_GENERAL_PARAMS_ENTRY;
+	const int size = SJA1105_SIZE_DYN_CMD;
+
+	sja1105_packing(p, &cmd->valid,   31, 31, size, op);
+	sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op);
+	sja1105_packing(p, &cmd->errors,  29, 29, size, op);
+}
+
+static void
 sja1105pqrs_avb_params_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
 				   enum packing_op op)
 {
@@ -593,6 +740,20 @@ sja1105_retagging_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
 	sja1105_packing(p, &cmd->index,     5,  0, size, op);
 }
 
+static void
+sja1110_retagging_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+			      enum packing_op op)
+{
+	u8 *p = buf + SJA1105_SIZE_RETAGGING_ENTRY;
+	const int size = SJA1105_SIZE_DYN_CMD;
+
+	sja1105_packing(p, &cmd->valid,    31, 31, size, op);
+	sja1105_packing(p, &cmd->rdwrset,  30, 30, size, op);
+	sja1105_packing(p, &cmd->errors,   29, 29, size, op);
+	sja1105_packing(p, &cmd->valident, 28, 28, size, op);
+	sja1105_packing(p, &cmd->index,     4,  0, size, op);
+}
+
 static void sja1105et_cbs_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
 				      enum packing_op op)
 {
@@ -632,6 +793,18 @@ static void sja1105pqrs_cbs_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
 	sja1105_packing(p, &cmd->index,    3,  0, size, op);
 }
 
+static void sja1110_cbs_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				    enum packing_op op)
+{
+	u8 *p = buf + SJA1105PQRS_SIZE_CBS_ENTRY;
+	const int size = SJA1105_SIZE_DYN_CMD;
+
+	sja1105_packing(p, &cmd->valid,   31, 31, size, op);
+	sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op);
+	sja1105_packing(p, &cmd->errors,  29, 29, size, op);
+	sja1105_packing(p, &cmd->index,    7,  0, size, op);
+}
+
 static size_t sja1105pqrs_cbs_entry_packing(void *buf, void *entry_ptr,
 					    enum packing_op op)
 {
@@ -647,10 +820,44 @@ static size_t sja1105pqrs_cbs_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+static size_t sja1110_cbs_entry_packing(void *buf, void *entry_ptr,
+					enum packing_op op)
+{
+	const size_t size = SJA1105PQRS_SIZE_CBS_ENTRY;
+	struct sja1105_cbs_entry *entry = entry_ptr;
+	u64 entry_type = SJA1110_CBS_SHAPER;
+
+	sja1105_packing(buf, &entry_type,       159, 159, size, op);
+	sja1105_packing(buf, &entry->credit_lo, 151, 120, size, op);
+	sja1105_packing(buf, &entry->credit_hi, 119,  88, size, op);
+	sja1105_packing(buf, &entry->send_slope, 87,  56, size, op);
+	sja1105_packing(buf, &entry->idle_slope, 55,  24, size, op);
+	return size;
+}
+
+static void sja1110_dummy_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				      enum packing_op op)
+{
+}
+
+static void
+sja1110_l2_policing_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				enum packing_op op)
+{
+	u8 *p = buf + SJA1105_SIZE_L2_POLICING_ENTRY;
+	const int size = SJA1105_SIZE_DYN_CMD;
+
+	sja1105_packing(p, &cmd->valid,   31, 31, size, op);
+	sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op);
+	sja1105_packing(p, &cmd->errors,  29, 29, size, op);
+	sja1105_packing(p, &cmd->index,    6,  0, size, op);
+}
+
 #define OP_READ		BIT(0)
 #define OP_WRITE	BIT(1)
 #define OP_DEL		BIT(2)
 #define OP_SEARCH	BIT(3)
+#define OP_VALID_ANYWAY	BIT(4)
 
 /* SJA1105E/T: First generation */
 const struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = {
@@ -673,7 +880,7 @@ const struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = {
 	[BLK_IDX_MGMT_ROUTE] = {
 		.entry_packing = sja1105et_mgmt_route_entry_packing,
 		.cmd_packing = sja1105et_mgmt_route_cmd_packing,
-		.access = (OP_READ | OP_WRITE),
+		.access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY),
 		.max_entry_count = SJA1105_NUM_PORTS,
 		.packed_size = SJA1105ET_SIZE_L2_LOOKUP_DYN_CMD,
 		.addr = 0x20,
@@ -757,7 +964,7 @@ const struct sja1105_dynamic_table_ops sja1105pqrs_dyn_ops[BLK_IDX_MAX_DYN] = {
 	[BLK_IDX_MGMT_ROUTE] = {
 		.entry_packing = sja1105pqrs_mgmt_route_entry_packing,
 		.cmd_packing = sja1105pqrs_mgmt_route_cmd_packing,
-		.access = (OP_READ | OP_WRITE | OP_DEL | OP_SEARCH),
+		.access = (OP_READ | OP_WRITE | OP_DEL | OP_SEARCH | OP_VALID_ANYWAY),
 		.max_entry_count = SJA1105_NUM_PORTS,
 		.packed_size = SJA1105PQRS_SIZE_L2_LOOKUP_DYN_CMD,
 		.addr = 0x24,
@@ -828,6 +1035,122 @@ const struct sja1105_dynamic_table_ops sja1105pqrs_dyn_ops[BLK_IDX_MAX_DYN] = {
 	},
 };
 
+/* SJA1110: Third generation */
+const struct sja1105_dynamic_table_ops sja1110_dyn_ops[BLK_IDX_MAX_DYN] = {
+	[BLK_IDX_VL_LOOKUP] = {
+		.entry_packing = sja1110_vl_lookup_entry_packing,
+		.cmd_packing = sja1110_vl_lookup_cmd_packing,
+		.access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY),
+		.max_entry_count = SJA1110_MAX_VL_LOOKUP_COUNT,
+		.packed_size = SJA1105PQRS_SIZE_VL_LOOKUP_DYN_CMD,
+		.addr = SJA1110_SPI_ADDR(0x124),
+	},
+	[BLK_IDX_VL_POLICING] = {
+		.entry_packing = sja1110_vl_policing_entry_packing,
+		.cmd_packing = sja1110_vl_policing_cmd_packing,
+		.access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY),
+		.max_entry_count = SJA1110_MAX_VL_POLICING_COUNT,
+		.packed_size = SJA1110_SIZE_VL_POLICING_DYN_CMD,
+		.addr = SJA1110_SPI_ADDR(0x310),
+	},
+	[BLK_IDX_L2_LOOKUP] = {
+		.entry_packing = sja1110_dyn_l2_lookup_entry_packing,
+		.cmd_packing = sja1105pqrs_l2_lookup_cmd_packing,
+		.access = (OP_READ | OP_WRITE | OP_DEL | OP_SEARCH),
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT,
+		.packed_size = SJA1110_SIZE_L2_LOOKUP_DYN_CMD,
+		.addr = SJA1110_SPI_ADDR(0x8c),
+	},
+	[BLK_IDX_VLAN_LOOKUP] = {
+		.entry_packing = sja1110_vlan_lookup_entry_packing,
+		.cmd_packing = sja1110_vlan_lookup_cmd_packing,
+		.access = (OP_READ | OP_WRITE | OP_DEL),
+		.max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT,
+		.packed_size = SJA1110_SIZE_VLAN_LOOKUP_DYN_CMD,
+		.addr = SJA1110_SPI_ADDR(0xb4),
+	},
+	[BLK_IDX_L2_FORWARDING] = {
+		.entry_packing = sja1110_l2_forwarding_entry_packing,
+		.cmd_packing = sja1110_l2_forwarding_cmd_packing,
+		.max_entry_count = SJA1110_MAX_L2_FORWARDING_COUNT,
+		.access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY),
+		.packed_size = SJA1105_SIZE_L2_FORWARDING_DYN_CMD,
+		.addr = SJA1110_SPI_ADDR(0xa8),
+	},
+	[BLK_IDX_MAC_CONFIG] = {
+		.entry_packing = sja1110_mac_config_entry_packing,
+		.cmd_packing = sja1110_mac_config_cmd_packing,
+		.max_entry_count = SJA1110_MAX_MAC_CONFIG_COUNT,
+		.access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY),
+		.packed_size = SJA1105PQRS_SIZE_MAC_CONFIG_DYN_CMD,
+		.addr = SJA1110_SPI_ADDR(0x134),
+	},
+	[BLK_IDX_L2_LOOKUP_PARAMS] = {
+		.entry_packing = sja1110_l2_lookup_params_entry_packing,
+		.cmd_packing = sja1110_l2_lookup_params_cmd_packing,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT,
+		.access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY),
+		.packed_size = SJA1110_SIZE_L2_LOOKUP_PARAMS_DYN_CMD,
+		.addr = SJA1110_SPI_ADDR(0x158),
+	},
+	[BLK_IDX_AVB_PARAMS] = {
+		.entry_packing = sja1105pqrs_avb_params_entry_packing,
+		.cmd_packing = sja1105pqrs_avb_params_cmd_packing,
+		.max_entry_count = SJA1105_MAX_AVB_PARAMS_COUNT,
+		.access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY),
+		.packed_size = SJA1105PQRS_SIZE_AVB_PARAMS_DYN_CMD,
+		.addr = SJA1110_SPI_ADDR(0x2000C),
+	},
+	[BLK_IDX_GENERAL_PARAMS] = {
+		.entry_packing = sja1110_general_params_entry_packing,
+		.cmd_packing = sja1110_general_params_cmd_packing,
+		.max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT,
+		.access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY),
+		.packed_size = SJA1110_SIZE_GENERAL_PARAMS_DYN_CMD,
+		.addr = SJA1110_SPI_ADDR(0xe8),
+	},
+	[BLK_IDX_RETAGGING] = {
+		.entry_packing = sja1110_retagging_entry_packing,
+		.cmd_packing = sja1110_retagging_cmd_packing,
+		.max_entry_count = SJA1105_MAX_RETAGGING_COUNT,
+		.access = (OP_READ | OP_WRITE | OP_DEL),
+		.packed_size = SJA1105_SIZE_RETAGGING_DYN_CMD,
+		.addr = SJA1110_SPI_ADDR(0xdc),
+	},
+	[BLK_IDX_CBS] = {
+		.entry_packing = sja1110_cbs_entry_packing,
+		.cmd_packing = sja1110_cbs_cmd_packing,
+		.max_entry_count = SJA1110_MAX_CBS_COUNT,
+		.access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY),
+		.packed_size = SJA1105PQRS_SIZE_CBS_DYN_CMD,
+		.addr = SJA1110_SPI_ADDR(0xc4),
+	},
+	[BLK_IDX_XMII_PARAMS] = {
+		.entry_packing = sja1110_xmii_params_entry_packing,
+		.cmd_packing = sja1110_dummy_cmd_packing,
+		.max_entry_count = SJA1105_MAX_XMII_PARAMS_COUNT,
+		.access = (OP_READ | OP_VALID_ANYWAY),
+		.packed_size = SJA1110_SIZE_XMII_PARAMS_DYN_CMD,
+		.addr = SJA1110_SPI_ADDR(0x3c),
+	},
+	[BLK_IDX_L2_POLICING] = {
+		.entry_packing = sja1110_l2_policing_entry_packing,
+		.cmd_packing = sja1110_l2_policing_cmd_packing,
+		.max_entry_count = SJA1110_MAX_L2_POLICING_COUNT,
+		.access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY),
+		.packed_size = SJA1110_SIZE_L2_POLICING_DYN_CMD,
+		.addr = SJA1110_SPI_ADDR(0x2fc),
+	},
+	[BLK_IDX_L2_FORWARDING_PARAMS] = {
+		.entry_packing = sja1110_l2_forwarding_params_entry_packing,
+		.cmd_packing = sja1110_dummy_cmd_packing,
+		.max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT,
+		.access = (OP_READ | OP_VALID_ANYWAY),
+		.packed_size = SJA1110_SIZE_L2_FORWARDING_PARAMS_DYN_CMD,
+		.addr = SJA1110_SPI_ADDR(0x20000),
+	},
+};
+
 /* Provides read access to the settings through the dynamic interface
  * of the switch.
  * @blk_idx	is used as key to select from the sja1105_dynamic_table_ops.
@@ -911,11 +1234,8 @@ int sja1105_dynamic_config_read(struct sja1105_private *priv,
 
 		cmd = (struct sja1105_dyn_cmd) {0};
 		ops->cmd_packing(packed_buf, &cmd, UNPACK);
-		/* UM10944: [valident] will always be found cleared
-		 * during a read access with MGMTROUTE set.
-		 * So don't error out in that case.
-		 */
-		if (!cmd.valident && blk_idx != BLK_IDX_MGMT_ROUTE)
+
+		if (!cmd.valident && !(ops->access & OP_VALID_ANYWAY))
 			return -ENOENT;
 		cpu_relax();
 	} while (cmd.valid && --retries);
diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.h b/drivers/net/dsa/sja1105/sja1105_dynamic_config.h
index 28d4eb5efb8b..a1472f80a059 100644
--- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.h
+++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.h
@@ -36,5 +36,6 @@ struct sja1105_mgmt_entry {
 
 extern const struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN];
 extern const struct sja1105_dynamic_table_ops sja1105pqrs_dyn_ops[BLK_IDX_MAX_DYN];
+extern const struct sja1105_dynamic_table_ops sja1110_dyn_ops[BLK_IDX_MAX_DYN];
 
 #endif
diff --git a/drivers/net/dsa/sja1105/sja1105_ethtool.c b/drivers/net/dsa/sja1105/sja1105_ethtool.c
index 9133a831ec79..decc6c931dc1 100644
--- a/drivers/net/dsa/sja1105/sja1105_ethtool.c
+++ b/drivers/net/dsa/sja1105/sja1105_ethtool.c
@@ -3,552 +3,627 @@
  */
 #include "sja1105.h"
 
-#define SJA1105_SIZE_MAC_AREA		(0x02 * 4)
-#define SJA1105_SIZE_HL1_AREA		(0x10 * 4)
-#define SJA1105_SIZE_HL2_AREA		(0x4 * 4)
-#define SJA1105_SIZE_QLEVEL_AREA	(0x8 * 4) /* 0x4 to 0xB */
-#define SJA1105_SIZE_ETHER_AREA		(0x17 * 4)
-
-struct sja1105_port_status_mac {
-	u64 n_runt;
-	u64 n_soferr;
-	u64 n_alignerr;
-	u64 n_miierr;
-	u64 typeerr;
-	u64 sizeerr;
-	u64 tctimeout;
-	u64 priorerr;
-	u64 nomaster;
-	u64 memov;
-	u64 memerr;
-	u64 invtyp;
-	u64 intcyov;
-	u64 domerr;
-	u64 pcfbagdrop;
-	u64 spcprior;
-	u64 ageprior;
-	u64 portdrop;
-	u64 lendrop;
-	u64 bagdrop;
-	u64 policeerr;
-	u64 drpnona664err;
-	u64 spcerr;
-	u64 agedrp;
-};
-
-struct sja1105_port_status_hl1 {
-	u64 n_n664err;
-	u64 n_vlanerr;
-	u64 n_unreleased;
-	u64 n_sizeerr;
-	u64 n_crcerr;
-	u64 n_vlnotfound;
-	u64 n_ctpolerr;
-	u64 n_polerr;
-	u64 n_rxfrmsh;
-	u64 n_rxfrm;
-	u64 n_rxbytesh;
-	u64 n_rxbyte;
-	u64 n_txfrmsh;
-	u64 n_txfrm;
-	u64 n_txbytesh;
-	u64 n_txbyte;
+enum sja1105_counter_index {
+	__SJA1105_COUNTER_UNUSED,
+	/* MAC */
+	N_RUNT,
+	N_SOFERR,
+	N_ALIGNERR,
+	N_MIIERR,
+	TYPEERR,
+	SIZEERR,
+	TCTIMEOUT,
+	PRIORERR,
+	NOMASTER,
+	MEMOV,
+	MEMERR,
+	INVTYP,
+	INTCYOV,
+	DOMERR,
+	PCFBAGDROP,
+	SPCPRIOR,
+	AGEPRIOR,
+	PORTDROP,
+	LENDROP,
+	BAGDROP,
+	POLICEERR,
+	DRPNONA664ERR,
+	SPCERR,
+	AGEDRP,
+	/* HL1 */
+	N_N664ERR,
+	N_VLANERR,
+	N_UNRELEASED,
+	N_SIZEERR,
+	N_CRCERR,
+	N_VLNOTFOUND,
+	N_CTPOLERR,
+	N_POLERR,
+	N_RXFRM,
+	N_RXBYTE,
+	N_TXFRM,
+	N_TXBYTE,
+	/* HL2 */
+	N_QFULL,
+	N_PART_DROP,
+	N_EGR_DISABLED,
+	N_NOT_REACH,
+	__MAX_SJA1105ET_PORT_COUNTER,
+	/* P/Q/R/S only */
+	/* ETHER */
+	N_DROPS_NOLEARN = __MAX_SJA1105ET_PORT_COUNTER,
+	N_DROPS_NOROUTE,
+	N_DROPS_ILL_DTAG,
+	N_DROPS_DTAG,
+	N_DROPS_SOTAG,
+	N_DROPS_SITAG,
+	N_DROPS_UTAG,
+	N_TX_BYTES_1024_2047,
+	N_TX_BYTES_512_1023,
+	N_TX_BYTES_256_511,
+	N_TX_BYTES_128_255,
+	N_TX_BYTES_65_127,
+	N_TX_BYTES_64,
+	N_TX_MCAST,
+	N_TX_BCAST,
+	N_RX_BYTES_1024_2047,
+	N_RX_BYTES_512_1023,
+	N_RX_BYTES_256_511,
+	N_RX_BYTES_128_255,
+	N_RX_BYTES_65_127,
+	N_RX_BYTES_64,
+	N_RX_MCAST,
+	N_RX_BCAST,
+	__MAX_SJA1105PQRS_PORT_COUNTER,
 };
 
-struct sja1105_port_status_hl2 {
-	u64 n_qfull;
-	u64 n_part_drop;
-	u64 n_egr_disabled;
-	u64 n_not_reach;
-	u64 qlevel_hwm[8]; /* Only for P/Q/R/S */
-	u64 qlevel[8];     /* Only for P/Q/R/S */
+struct sja1105_port_counter {
+	enum sja1105_stats_area area;
+	const char name[ETH_GSTRING_LEN];
+	int offset;
+	int start;
+	int end;
+	bool is_64bit;
 };
 
-struct sja1105_port_status_ether {
-	u64 n_drops_nolearn;
-	u64 n_drops_noroute;
-	u64 n_drops_ill_dtag;
-	u64 n_drops_dtag;
-	u64 n_drops_sotag;
-	u64 n_drops_sitag;
-	u64 n_drops_utag;
-	u64 n_tx_bytes_1024_2047;
-	u64 n_tx_bytes_512_1023;
-	u64 n_tx_bytes_256_511;
-	u64 n_tx_bytes_128_255;
-	u64 n_tx_bytes_65_127;
-	u64 n_tx_bytes_64;
-	u64 n_tx_mcast;
-	u64 n_tx_bcast;
-	u64 n_rx_bytes_1024_2047;
-	u64 n_rx_bytes_512_1023;
-	u64 n_rx_bytes_256_511;
-	u64 n_rx_bytes_128_255;
-	u64 n_rx_bytes_65_127;
-	u64 n_rx_bytes_64;
-	u64 n_rx_mcast;
-	u64 n_rx_bcast;
-};
-
-struct sja1105_port_status {
-	struct sja1105_port_status_mac mac;
-	struct sja1105_port_status_hl1 hl1;
-	struct sja1105_port_status_hl2 hl2;
-	struct sja1105_port_status_ether ether;
+static const struct sja1105_port_counter sja1105_port_counters[] = {
+	/* MAC-Level Diagnostic Counters */
+	[N_RUNT] = {
+		.area = MAC,
+		.name = "n_runt",
+		.offset = 0,
+		.start = 31,
+		.end = 24,
+	},
+	[N_SOFERR] = {
+		.area = MAC,
+		.name = "n_soferr",
+		.offset = 0x0,
+		.start = 23,
+		.end = 16,
+	},
+	[N_ALIGNERR] = {
+		.area = MAC,
+		.name = "n_alignerr",
+		.offset = 0x0,
+		.start = 15,
+		.end = 8,
+	},
+	[N_MIIERR] = {
+		.area = MAC,
+		.name = "n_miierr",
+		.offset = 0x0,
+		.start = 7,
+		.end = 0,
+	},
+	/* MAC-Level Diagnostic Flags */
+	[TYPEERR] = {
+		.area = MAC,
+		.name = "typeerr",
+		.offset = 0x1,
+		.start = 27,
+		.end = 27,
+	},
+	[SIZEERR] = {
+		.area = MAC,
+		.name = "sizeerr",
+		.offset = 0x1,
+		.start = 26,
+		.end = 26,
+	},
+	[TCTIMEOUT] = {
+		.area = MAC,
+		.name = "tctimeout",
+		.offset = 0x1,
+		.start = 25,
+		.end = 25,
+	},
+	[PRIORERR] = {
+		.area = MAC,
+		.name = "priorerr",
+		.offset = 0x1,
+		.start = 24,
+		.end = 24,
+	},
+	[NOMASTER] = {
+		.area = MAC,
+		.name = "nomaster",
+		.offset = 0x1,
+		.start = 23,
+		.end = 23,
+	},
+	[MEMOV] = {
+		.area = MAC,
+		.name = "memov",
+		.offset = 0x1,
+		.start = 22,
+		.end = 22,
+	},
+	[MEMERR] = {
+		.area = MAC,
+		.name = "memerr",
+		.offset = 0x1,
+		.start = 21,
+		.end = 21,
+	},
+	[INVTYP] = {
+		.area = MAC,
+		.name = "invtyp",
+		.offset = 0x1,
+		.start = 19,
+		.end = 19,
+	},
+	[INTCYOV] = {
+		.area = MAC,
+		.name = "intcyov",
+		.offset = 0x1,
+		.start = 18,
+		.end = 18,
+	},
+	[DOMERR] = {
+		.area = MAC,
+		.name = "domerr",
+		.offset = 0x1,
+		.start = 17,
+		.end = 17,
+	},
+	[PCFBAGDROP] = {
+		.area = MAC,
+		.name = "pcfbagdrop",
+		.offset = 0x1,
+		.start = 16,
+		.end = 16,
+	},
+	[SPCPRIOR] = {
+		.area = MAC,
+		.name = "spcprior",
+		.offset = 0x1,
+		.start = 15,
+		.end = 12,
+	},
+	[AGEPRIOR] = {
+		.area = MAC,
+		.name = "ageprior",
+		.offset = 0x1,
+		.start = 11,
+		.end = 8,
+	},
+	[PORTDROP] = {
+		.area = MAC,
+		.name = "portdrop",
+		.offset = 0x1,
+		.start = 6,
+		.end = 6,
+	},
+	[LENDROP] = {
+		.area = MAC,
+		.name = "lendrop",
+		.offset = 0x1,
+		.start = 5,
+		.end = 5,
+	},
+	[BAGDROP] = {
+		.area = MAC,
+		.name = "bagdrop",
+		.offset = 0x1,
+		.start = 4,
+		.end = 4,
+	},
+	[POLICEERR] = {
+		.area = MAC,
+		.name = "policeerr",
+		.offset = 0x1,
+		.start = 3,
+		.end = 3,
+	},
+	[DRPNONA664ERR] = {
+		.area = MAC,
+		.name = "drpnona664err",
+		.offset = 0x1,
+		.start = 2,
+		.end = 2,
+	},
+	[SPCERR] = {
+		.area = MAC,
+		.name = "spcerr",
+		.offset = 0x1,
+		.start = 1,
+		.end = 1,
+	},
+	[AGEDRP] = {
+		.area = MAC,
+		.name = "agedrp",
+		.offset = 0x1,
+		.start = 0,
+		.end = 0,
+	},
+	/* High-Level Diagnostic Counters */
+	[N_N664ERR] = {
+		.area = HL1,
+		.name = "n_n664err",
+		.offset = 0xF,
+		.start = 31,
+		.end = 0,
+	},
+	[N_VLANERR] = {
+		.area = HL1,
+		.name = "n_vlanerr",
+		.offset = 0xE,
+		.start = 31,
+		.end = 0,
+	},
+	[N_UNRELEASED] = {
+		.area = HL1,
+		.name = "n_unreleased",
+		.offset = 0xD,
+		.start = 31,
+		.end = 0,
+	},
+	[N_SIZEERR] = {
+		.area = HL1,
+		.name = "n_sizeerr",
+		.offset = 0xC,
+		.start = 31,
+		.end = 0,
+	},
+	[N_CRCERR] = {
+		.area = HL1,
+		.name = "n_crcerr",
+		.offset = 0xB,
+		.start = 31,
+		.end = 0,
+	},
+	[N_VLNOTFOUND] = {
+		.area = HL1,
+		.name = "n_vlnotfound",
+		.offset = 0xA,
+		.start = 31,
+		.end = 0,
+	},
+	[N_CTPOLERR] = {
+		.area = HL1,
+		.name = "n_ctpolerr",
+		.offset = 0x9,
+		.start = 31,
+		.end = 0,
+	},
+	[N_POLERR] = {
+		.area = HL1,
+		.name = "n_polerr",
+		.offset = 0x8,
+		.start = 31,
+		.end = 0,
+	},
+	[N_RXFRM] = {
+		.area = HL1,
+		.name = "n_rxfrm",
+		.offset = 0x6,
+		.start = 31,
+		.end = 0,
+		.is_64bit = true,
+	},
+	[N_RXBYTE] = {
+		.area = HL1,
+		.name = "n_rxbyte",
+		.offset = 0x4,
+		.start = 31,
+		.end = 0,
+		.is_64bit = true,
+	},
+	[N_TXFRM] = {
+		.area = HL1,
+		.name = "n_txfrm",
+		.offset = 0x2,
+		.start = 31,
+		.end = 0,
+		.is_64bit = true,
+	},
+	[N_TXBYTE] = {
+		.area = HL1,
+		.name = "n_txbyte",
+		.offset = 0x0,
+		.start = 31,
+		.end = 0,
+		.is_64bit = true,
+	},
+	[N_QFULL] = {
+		.area = HL2,
+		.name = "n_qfull",
+		.offset = 0x3,
+		.start = 31,
+		.end = 0,
+	},
+	[N_PART_DROP] = {
+		.area = HL2,
+		.name = "n_part_drop",
+		.offset = 0x2,
+		.start = 31,
+		.end = 0,
+	},
+	[N_EGR_DISABLED] = {
+		.area = HL2,
+		.name = "n_egr_disabled",
+		.offset = 0x1,
+		.start = 31,
+		.end = 0,
+	},
+	[N_NOT_REACH] = {
+		.area = HL2,
+		.name = "n_not_reach",
+		.offset = 0x0,
+		.start = 31,
+		.end = 0,
+	},
+	/* Ether Stats */
+	[N_DROPS_NOLEARN] = {
+		.area = ETHER,
+		.name = "n_drops_nolearn",
+		.offset = 0x16,
+		.start = 31,
+		.end = 0,
+	},
+	[N_DROPS_NOROUTE] = {
+		.area = ETHER,
+		.name = "n_drops_noroute",
+		.offset = 0x15,
+		.start = 31,
+		.end = 0,
+	},
+	[N_DROPS_ILL_DTAG] = {
+		.area = ETHER,
+		.name = "n_drops_ill_dtag",
+		.offset = 0x14,
+		.start = 31,
+		.end = 0,
+	},
+	[N_DROPS_DTAG] = {
+		.area = ETHER,
+		.name = "n_drops_dtag",
+		.offset = 0x13,
+		.start = 31,
+		.end = 0,
+	},
+	[N_DROPS_SOTAG] = {
+		.area = ETHER,
+		.name = "n_drops_sotag",
+		.offset = 0x12,
+		.start = 31,
+		.end = 0,
+	},
+	[N_DROPS_SITAG] = {
+		.area = ETHER,
+		.name = "n_drops_sitag",
+		.offset = 0x11,
+		.start = 31,
+		.end = 0,
+	},
+	[N_DROPS_UTAG] = {
+		.area = ETHER,
+		.name = "n_drops_utag",
+		.offset = 0x10,
+		.start = 31,
+		.end = 0,
+	},
+	[N_TX_BYTES_1024_2047] = {
+		.area = ETHER,
+		.name = "n_tx_bytes_1024_2047",
+		.offset = 0x0F,
+		.start = 31,
+		.end = 0,
+	},
+	[N_TX_BYTES_512_1023] = {
+		.area = ETHER,
+		.name = "n_tx_bytes_512_1023",
+		.offset = 0x0E,
+		.start = 31,
+		.end = 0,
+	},
+	[N_TX_BYTES_256_511] = {
+		.area = ETHER,
+		.name = "n_tx_bytes_256_511",
+		.offset = 0x0D,
+		.start = 31,
+		.end = 0,
+	},
+	[N_TX_BYTES_128_255] = {
+		.area = ETHER,
+		.name = "n_tx_bytes_128_255",
+		.offset = 0x0C,
+		.start = 31,
+		.end = 0,
+	},
+	[N_TX_BYTES_65_127] = {
+		.area = ETHER,
+		.name = "n_tx_bytes_65_127",
+		.offset = 0x0B,
+		.start = 31,
+		.end = 0,
+	},
+	[N_TX_BYTES_64] = {
+		.area = ETHER,
+		.name = "n_tx_bytes_64",
+		.offset = 0x0A,
+		.start = 31,
+		.end = 0,
+	},
+	[N_TX_MCAST] = {
+		.area = ETHER,
+		.name = "n_tx_mcast",
+		.offset = 0x09,
+		.start = 31,
+		.end = 0,
+	},
+	[N_TX_BCAST] = {
+		.area = ETHER,
+		.name = "n_tx_bcast",
+		.offset = 0x08,
+		.start = 31,
+		.end = 0,
+	},
+	[N_RX_BYTES_1024_2047] = {
+		.area = ETHER,
+		.name = "n_rx_bytes_1024_2047",
+		.offset = 0x07,
+		.start = 31,
+		.end = 0,
+	},
+	[N_RX_BYTES_512_1023] = {
+		.area = ETHER,
+		.name = "n_rx_bytes_512_1023",
+		.offset = 0x06,
+		.start = 31,
+		.end = 0,
+	},
+	[N_RX_BYTES_256_511] = {
+		.area = ETHER,
+		.name = "n_rx_bytes_256_511",
+		.offset = 0x05,
+		.start = 31,
+		.end = 0,
+	},
+	[N_RX_BYTES_128_255] = {
+		.area = ETHER,
+		.name = "n_rx_bytes_128_255",
+		.offset = 0x04,
+		.start = 31,
+		.end = 0,
+	},
+	[N_RX_BYTES_65_127] = {
+		.area = ETHER,
+		.name = "n_rx_bytes_65_127",
+		.offset = 0x03,
+		.start = 31,
+		.end = 0,
+	},
+	[N_RX_BYTES_64] = {
+		.area = ETHER,
+		.name = "n_rx_bytes_64",
+		.offset = 0x02,
+		.start = 31,
+		.end = 0,
+	},
+	[N_RX_MCAST] = {
+		.area = ETHER,
+		.name = "n_rx_mcast",
+		.offset = 0x01,
+		.start = 31,
+		.end = 0,
+	},
+	[N_RX_BCAST] = {
+		.area = ETHER,
+		.name = "n_rx_bcast",
+		.offset = 0x00,
+		.start = 31,
+		.end = 0,
+	},
 };
 
-static void
-sja1105_port_status_mac_unpack(void *buf,
-			       struct sja1105_port_status_mac *status)
-{
-	/* Make pointer arithmetic work on 4 bytes */
-	u32 *p = buf;
-
-	sja1105_unpack(p + 0x0, &status->n_runt,       31, 24, 4);
-	sja1105_unpack(p + 0x0, &status->n_soferr,     23, 16, 4);
-	sja1105_unpack(p + 0x0, &status->n_alignerr,   15,  8, 4);
-	sja1105_unpack(p + 0x0, &status->n_miierr,      7,  0, 4);
-	sja1105_unpack(p + 0x1, &status->typeerr,      27, 27, 4);
-	sja1105_unpack(p + 0x1, &status->sizeerr,      26, 26, 4);
-	sja1105_unpack(p + 0x1, &status->tctimeout,    25, 25, 4);
-	sja1105_unpack(p + 0x1, &status->priorerr,     24, 24, 4);
-	sja1105_unpack(p + 0x1, &status->nomaster,     23, 23, 4);
-	sja1105_unpack(p + 0x1, &status->memov,        22, 22, 4);
-	sja1105_unpack(p + 0x1, &status->memerr,       21, 21, 4);
-	sja1105_unpack(p + 0x1, &status->invtyp,       19, 19, 4);
-	sja1105_unpack(p + 0x1, &status->intcyov,      18, 18, 4);
-	sja1105_unpack(p + 0x1, &status->domerr,       17, 17, 4);
-	sja1105_unpack(p + 0x1, &status->pcfbagdrop,   16, 16, 4);
-	sja1105_unpack(p + 0x1, &status->spcprior,     15, 12, 4);
-	sja1105_unpack(p + 0x1, &status->ageprior,     11,  8, 4);
-	sja1105_unpack(p + 0x1, &status->portdrop,      6,  6, 4);
-	sja1105_unpack(p + 0x1, &status->lendrop,       5,  5, 4);
-	sja1105_unpack(p + 0x1, &status->bagdrop,       4,  4, 4);
-	sja1105_unpack(p + 0x1, &status->policeerr,     3,  3, 4);
-	sja1105_unpack(p + 0x1, &status->drpnona664err, 2,  2, 4);
-	sja1105_unpack(p + 0x1, &status->spcerr,        1,  1, 4);
-	sja1105_unpack(p + 0x1, &status->agedrp,        0,  0, 4);
-}
-
-static void
-sja1105_port_status_hl1_unpack(void *buf,
-			       struct sja1105_port_status_hl1 *status)
-{
-	/* Make pointer arithmetic work on 4 bytes */
-	u32 *p = buf;
-
-	sja1105_unpack(p + 0xF, &status->n_n664err,    31,  0, 4);
-	sja1105_unpack(p + 0xE, &status->n_vlanerr,    31,  0, 4);
-	sja1105_unpack(p + 0xD, &status->n_unreleased, 31,  0, 4);
-	sja1105_unpack(p + 0xC, &status->n_sizeerr,    31,  0, 4);
-	sja1105_unpack(p + 0xB, &status->n_crcerr,     31,  0, 4);
-	sja1105_unpack(p + 0xA, &status->n_vlnotfound, 31,  0, 4);
-	sja1105_unpack(p + 0x9, &status->n_ctpolerr,   31,  0, 4);
-	sja1105_unpack(p + 0x8, &status->n_polerr,     31,  0, 4);
-	sja1105_unpack(p + 0x7, &status->n_rxfrmsh,    31,  0, 4);
-	sja1105_unpack(p + 0x6, &status->n_rxfrm,      31,  0, 4);
-	sja1105_unpack(p + 0x5, &status->n_rxbytesh,   31,  0, 4);
-	sja1105_unpack(p + 0x4, &status->n_rxbyte,     31,  0, 4);
-	sja1105_unpack(p + 0x3, &status->n_txfrmsh,    31,  0, 4);
-	sja1105_unpack(p + 0x2, &status->n_txfrm,      31,  0, 4);
-	sja1105_unpack(p + 0x1, &status->n_txbytesh,   31,  0, 4);
-	sja1105_unpack(p + 0x0, &status->n_txbyte,     31,  0, 4);
-	status->n_rxfrm  += status->n_rxfrmsh  << 32;
-	status->n_rxbyte += status->n_rxbytesh << 32;
-	status->n_txfrm  += status->n_txfrmsh  << 32;
-	status->n_txbyte += status->n_txbytesh << 32;
-}
-
-static void
-sja1105_port_status_hl2_unpack(void *buf,
-			       struct sja1105_port_status_hl2 *status)
-{
-	/* Make pointer arithmetic work on 4 bytes */
-	u32 *p = buf;
-
-	sja1105_unpack(p + 0x3, &status->n_qfull,        31,  0, 4);
-	sja1105_unpack(p + 0x2, &status->n_part_drop,    31,  0, 4);
-	sja1105_unpack(p + 0x1, &status->n_egr_disabled, 31,  0, 4);
-	sja1105_unpack(p + 0x0, &status->n_not_reach,    31,  0, 4);
-}
-
-static void
-sja1105pqrs_port_status_qlevel_unpack(void *buf,
-				      struct sja1105_port_status_hl2 *status)
-{
-	/* Make pointer arithmetic work on 4 bytes */
-	u32 *p = buf;
-	int i;
-
-	for (i = 0; i < 8; i++) {
-		sja1105_unpack(p + i, &status->qlevel_hwm[i], 24, 16, 4);
-		sja1105_unpack(p + i, &status->qlevel[i],      8,  0, 4);
-	}
-}
-
-static void
-sja1105pqrs_port_status_ether_unpack(void *buf,
-				     struct sja1105_port_status_ether *status)
-{
-	/* Make pointer arithmetic work on 4 bytes */
-	u32 *p = buf;
-
-	sja1105_unpack(p + 0x16, &status->n_drops_nolearn,      31, 0, 4);
-	sja1105_unpack(p + 0x15, &status->n_drops_noroute,      31, 0, 4);
-	sja1105_unpack(p + 0x14, &status->n_drops_ill_dtag,     31, 0, 4);
-	sja1105_unpack(p + 0x13, &status->n_drops_dtag,         31, 0, 4);
-	sja1105_unpack(p + 0x12, &status->n_drops_sotag,        31, 0, 4);
-	sja1105_unpack(p + 0x11, &status->n_drops_sitag,        31, 0, 4);
-	sja1105_unpack(p + 0x10, &status->n_drops_utag,         31, 0, 4);
-	sja1105_unpack(p + 0x0F, &status->n_tx_bytes_1024_2047, 31, 0, 4);
-	sja1105_unpack(p + 0x0E, &status->n_tx_bytes_512_1023,  31, 0, 4);
-	sja1105_unpack(p + 0x0D, &status->n_tx_bytes_256_511,   31, 0, 4);
-	sja1105_unpack(p + 0x0C, &status->n_tx_bytes_128_255,   31, 0, 4);
-	sja1105_unpack(p + 0x0B, &status->n_tx_bytes_65_127,    31, 0, 4);
-	sja1105_unpack(p + 0x0A, &status->n_tx_bytes_64,        31, 0, 4);
-	sja1105_unpack(p + 0x09, &status->n_tx_mcast,           31, 0, 4);
-	sja1105_unpack(p + 0x08, &status->n_tx_bcast,           31, 0, 4);
-	sja1105_unpack(p + 0x07, &status->n_rx_bytes_1024_2047, 31, 0, 4);
-	sja1105_unpack(p + 0x06, &status->n_rx_bytes_512_1023,  31, 0, 4);
-	sja1105_unpack(p + 0x05, &status->n_rx_bytes_256_511,   31, 0, 4);
-	sja1105_unpack(p + 0x04, &status->n_rx_bytes_128_255,   31, 0, 4);
-	sja1105_unpack(p + 0x03, &status->n_rx_bytes_65_127,    31, 0, 4);
-	sja1105_unpack(p + 0x02, &status->n_rx_bytes_64,        31, 0, 4);
-	sja1105_unpack(p + 0x01, &status->n_rx_mcast,           31, 0, 4);
-	sja1105_unpack(p + 0x00, &status->n_rx_bcast,           31, 0, 4);
-}
-
-static int
-sja1105pqrs_port_status_get_ether(struct sja1105_private *priv,
-				  struct sja1105_port_status_ether *ether,
-				  int port)
-{
-	const struct sja1105_regs *regs = priv->info->regs;
-	u8 packed_buf[SJA1105_SIZE_ETHER_AREA] = {0};
-	int rc;
-
-	/* Ethernet statistics area */
-	rc = sja1105_xfer_buf(priv, SPI_READ, regs->ether_stats[port],
-			      packed_buf, SJA1105_SIZE_ETHER_AREA);
-	if (rc < 0)
-		return rc;
-
-	sja1105pqrs_port_status_ether_unpack(packed_buf, ether);
-
-	return 0;
-}
-
-static int sja1105_port_status_get_mac(struct sja1105_private *priv,
-				       struct sja1105_port_status_mac *status,
-				       int port)
-{
-	const struct sja1105_regs *regs = priv->info->regs;
-	u8 packed_buf[SJA1105_SIZE_MAC_AREA] = {0};
-	int rc;
-
-	/* MAC area */
-	rc = sja1105_xfer_buf(priv, SPI_READ, regs->mac[port], packed_buf,
-			      SJA1105_SIZE_MAC_AREA);
-	if (rc < 0)
-		return rc;
-
-	sja1105_port_status_mac_unpack(packed_buf, status);
-
-	return 0;
-}
-
-static int sja1105_port_status_get_hl1(struct sja1105_private *priv,
-				       struct sja1105_port_status_hl1 *status,
-				       int port)
-{
-	const struct sja1105_regs *regs = priv->info->regs;
-	u8 packed_buf[SJA1105_SIZE_HL1_AREA] = {0};
-	int rc;
-
-	rc = sja1105_xfer_buf(priv, SPI_READ, regs->mac_hl1[port], packed_buf,
-			      SJA1105_SIZE_HL1_AREA);
-	if (rc < 0)
-		return rc;
-
-	sja1105_port_status_hl1_unpack(packed_buf, status);
-
-	return 0;
-}
-
-static int sja1105_port_status_get_hl2(struct sja1105_private *priv,
-				       struct sja1105_port_status_hl2 *status,
-				       int port)
+static int sja1105_port_counter_read(struct sja1105_private *priv, int port,
+				     enum sja1105_counter_index idx, u64 *ctr)
 {
-	const struct sja1105_regs *regs = priv->info->regs;
-	u8 packed_buf[SJA1105_SIZE_QLEVEL_AREA] = {0};
+	const struct sja1105_port_counter *c = &sja1105_port_counters[idx];
+	size_t size = c->is_64bit ? 8 : 4;
+	u8 buf[8] = {0};
+	u64 regs;
 	int rc;
 
-	rc = sja1105_xfer_buf(priv, SPI_READ, regs->mac_hl2[port], packed_buf,
-			      SJA1105_SIZE_HL2_AREA);
-	if (rc < 0)
-		return rc;
-
-	sja1105_port_status_hl2_unpack(packed_buf, status);
-
-	/* Code below is strictly P/Q/R/S specific. */
-	if (priv->info->device_id == SJA1105E_DEVICE_ID ||
-	    priv->info->device_id == SJA1105T_DEVICE_ID)
-		return 0;
+	regs = priv->info->regs->stats[c->area][port];
 
-	rc = sja1105_xfer_buf(priv, SPI_READ, regs->qlevel[port], packed_buf,
-			      SJA1105_SIZE_QLEVEL_AREA);
-	if (rc < 0)
+	rc = sja1105_xfer_buf(priv, SPI_READ, regs + c->offset, buf, size);
+	if (rc)
 		return rc;
 
-	sja1105pqrs_port_status_qlevel_unpack(packed_buf, status);
+	sja1105_unpack(buf, ctr, c->start, c->end, size);
 
 	return 0;
 }
 
-static int sja1105_port_status_get(struct sja1105_private *priv,
-				   struct sja1105_port_status *status,
-				   int port)
-{
-	int rc;
-
-	rc = sja1105_port_status_get_mac(priv, &status->mac, port);
-	if (rc < 0)
-		return rc;
-	rc = sja1105_port_status_get_hl1(priv, &status->hl1, port);
-	if (rc < 0)
-		return rc;
-	rc = sja1105_port_status_get_hl2(priv, &status->hl2, port);
-	if (rc < 0)
-		return rc;
-
-	if (priv->info->device_id == SJA1105E_DEVICE_ID ||
-	    priv->info->device_id == SJA1105T_DEVICE_ID)
-		return 0;
-
-	return sja1105pqrs_port_status_get_ether(priv, &status->ether, port);
-}
-
-static char sja1105_port_stats[][ETH_GSTRING_LEN] = {
-	/* MAC-Level Diagnostic Counters */
-	"n_runt",
-	"n_soferr",
-	"n_alignerr",
-	"n_miierr",
-	/* MAC-Level Diagnostic Flags */
-	"typeerr",
-	"sizeerr",
-	"tctimeout",
-	"priorerr",
-	"nomaster",
-	"memov",
-	"memerr",
-	"invtyp",
-	"intcyov",
-	"domerr",
-	"pcfbagdrop",
-	"spcprior",
-	"ageprior",
-	"portdrop",
-	"lendrop",
-	"bagdrop",
-	"policeerr",
-	"drpnona664err",
-	"spcerr",
-	"agedrp",
-	/* High-Level Diagnostic Counters */
-	"n_n664err",
-	"n_vlanerr",
-	"n_unreleased",
-	"n_sizeerr",
-	"n_crcerr",
-	"n_vlnotfound",
-	"n_ctpolerr",
-	"n_polerr",
-	"n_rxfrm",
-	"n_rxbyte",
-	"n_txfrm",
-	"n_txbyte",
-	"n_qfull",
-	"n_part_drop",
-	"n_egr_disabled",
-	"n_not_reach",
-};
-
-static char sja1105pqrs_extra_port_stats[][ETH_GSTRING_LEN] = {
-	/* Queue Levels */
-	"qlevel_hwm_0",
-	"qlevel_hwm_1",
-	"qlevel_hwm_2",
-	"qlevel_hwm_3",
-	"qlevel_hwm_4",
-	"qlevel_hwm_5",
-	"qlevel_hwm_6",
-	"qlevel_hwm_7",
-	"qlevel_0",
-	"qlevel_1",
-	"qlevel_2",
-	"qlevel_3",
-	"qlevel_4",
-	"qlevel_5",
-	"qlevel_6",
-	"qlevel_7",
-	/* Ether Stats */
-	"n_drops_nolearn",
-	"n_drops_noroute",
-	"n_drops_ill_dtag",
-	"n_drops_dtag",
-	"n_drops_sotag",
-	"n_drops_sitag",
-	"n_drops_utag",
-	"n_tx_bytes_1024_2047",
-	"n_tx_bytes_512_1023",
-	"n_tx_bytes_256_511",
-	"n_tx_bytes_128_255",
-	"n_tx_bytes_65_127",
-	"n_tx_bytes_64",
-	"n_tx_mcast",
-	"n_tx_bcast",
-	"n_rx_bytes_1024_2047",
-	"n_rx_bytes_512_1023",
-	"n_rx_bytes_256_511",
-	"n_rx_bytes_128_255",
-	"n_rx_bytes_65_127",
-	"n_rx_bytes_64",
-	"n_rx_mcast",
-	"n_rx_bcast",
-};
-
 void sja1105_get_ethtool_stats(struct dsa_switch *ds, int port, u64 *data)
 {
 	struct sja1105_private *priv = ds->priv;
-	struct sja1105_port_status *status;
-	int rc, i, k = 0;
-
-	status = kzalloc(sizeof(*status), GFP_KERNEL);
-	if (!status)
-		goto out;
-
-	rc = sja1105_port_status_get(priv, status, port);
-	if (rc < 0) {
-		dev_err(ds->dev, "Failed to read port %d counters: %d\n",
-			port, rc);
-		goto out;
-	}
-	memset(data, 0, ARRAY_SIZE(sja1105_port_stats) * sizeof(u64));
-	data[k++] = status->mac.n_runt;
-	data[k++] = status->mac.n_soferr;
-	data[k++] = status->mac.n_alignerr;
-	data[k++] = status->mac.n_miierr;
-	data[k++] = status->mac.typeerr;
-	data[k++] = status->mac.sizeerr;
-	data[k++] = status->mac.tctimeout;
-	data[k++] = status->mac.priorerr;
-	data[k++] = status->mac.nomaster;
-	data[k++] = status->mac.memov;
-	data[k++] = status->mac.memerr;
-	data[k++] = status->mac.invtyp;
-	data[k++] = status->mac.intcyov;
-	data[k++] = status->mac.domerr;
-	data[k++] = status->mac.pcfbagdrop;
-	data[k++] = status->mac.spcprior;
-	data[k++] = status->mac.ageprior;
-	data[k++] = status->mac.portdrop;
-	data[k++] = status->mac.lendrop;
-	data[k++] = status->mac.bagdrop;
-	data[k++] = status->mac.policeerr;
-	data[k++] = status->mac.drpnona664err;
-	data[k++] = status->mac.spcerr;
-	data[k++] = status->mac.agedrp;
-	data[k++] = status->hl1.n_n664err;
-	data[k++] = status->hl1.n_vlanerr;
-	data[k++] = status->hl1.n_unreleased;
-	data[k++] = status->hl1.n_sizeerr;
-	data[k++] = status->hl1.n_crcerr;
-	data[k++] = status->hl1.n_vlnotfound;
-	data[k++] = status->hl1.n_ctpolerr;
-	data[k++] = status->hl1.n_polerr;
-	data[k++] = status->hl1.n_rxfrm;
-	data[k++] = status->hl1.n_rxbyte;
-	data[k++] = status->hl1.n_txfrm;
-	data[k++] = status->hl1.n_txbyte;
-	data[k++] = status->hl2.n_qfull;
-	data[k++] = status->hl2.n_part_drop;
-	data[k++] = status->hl2.n_egr_disabled;
-	data[k++] = status->hl2.n_not_reach;
+	enum sja1105_counter_index max_ctr, i;
+	int rc, k = 0;
 
 	if (priv->info->device_id == SJA1105E_DEVICE_ID ||
 	    priv->info->device_id == SJA1105T_DEVICE_ID)
-		goto out;
-
-	memset(data + k, 0, ARRAY_SIZE(sja1105pqrs_extra_port_stats) *
-			sizeof(u64));
-	for (i = 0; i < 8; i++) {
-		data[k++] = status->hl2.qlevel_hwm[i];
-		data[k++] = status->hl2.qlevel[i];
+		max_ctr = __MAX_SJA1105ET_PORT_COUNTER;
+	else
+		max_ctr = __MAX_SJA1105PQRS_PORT_COUNTER;
+
+	for (i = 0; i < max_ctr; i++) {
+		rc = sja1105_port_counter_read(priv, port, i, &data[k++]);
+		if (rc) {
+			dev_err(ds->dev,
+				"Failed to read port %d counters: %d\n",
+				port, rc);
+			break;
+		}
 	}
-	data[k++] = status->ether.n_drops_nolearn;
-	data[k++] = status->ether.n_drops_noroute;
-	data[k++] = status->ether.n_drops_ill_dtag;
-	data[k++] = status->ether.n_drops_dtag;
-	data[k++] = status->ether.n_drops_sotag;
-	data[k++] = status->ether.n_drops_sitag;
-	data[k++] = status->ether.n_drops_utag;
-	data[k++] = status->ether.n_tx_bytes_1024_2047;
-	data[k++] = status->ether.n_tx_bytes_512_1023;
-	data[k++] = status->ether.n_tx_bytes_256_511;
-	data[k++] = status->ether.n_tx_bytes_128_255;
-	data[k++] = status->ether.n_tx_bytes_65_127;
-	data[k++] = status->ether.n_tx_bytes_64;
-	data[k++] = status->ether.n_tx_mcast;
-	data[k++] = status->ether.n_tx_bcast;
-	data[k++] = status->ether.n_rx_bytes_1024_2047;
-	data[k++] = status->ether.n_rx_bytes_512_1023;
-	data[k++] = status->ether.n_rx_bytes_256_511;
-	data[k++] = status->ether.n_rx_bytes_128_255;
-	data[k++] = status->ether.n_rx_bytes_65_127;
-	data[k++] = status->ether.n_rx_bytes_64;
-	data[k++] = status->ether.n_rx_mcast;
-	data[k++] = status->ether.n_rx_bcast;
-out:
-	kfree(status);
 }
 
 void sja1105_get_strings(struct dsa_switch *ds, int port,
 			 u32 stringset, u8 *data)
 {
 	struct sja1105_private *priv = ds->priv;
-	u8 *p = data;
-	int i;
+	enum sja1105_counter_index max_ctr, i;
+	char *p = data;
 
-	switch (stringset) {
-	case ETH_SS_STATS:
-		for (i = 0; i < ARRAY_SIZE(sja1105_port_stats); i++) {
-			strlcpy(p, sja1105_port_stats[i], ETH_GSTRING_LEN);
-			p += ETH_GSTRING_LEN;
-		}
-		if (priv->info->device_id == SJA1105E_DEVICE_ID ||
-		    priv->info->device_id == SJA1105T_DEVICE_ID)
-			return;
-		for (i = 0; i < ARRAY_SIZE(sja1105pqrs_extra_port_stats); i++) {
-			strlcpy(p, sja1105pqrs_extra_port_stats[i],
-				ETH_GSTRING_LEN);
-			p += ETH_GSTRING_LEN;
-		}
-		break;
+	if (stringset != ETH_SS_STATS)
+		return;
+
+	if (priv->info->device_id == SJA1105E_DEVICE_ID ||
+	    priv->info->device_id == SJA1105T_DEVICE_ID)
+		max_ctr = __MAX_SJA1105ET_PORT_COUNTER;
+	else
+		max_ctr = __MAX_SJA1105PQRS_PORT_COUNTER;
+
+	for (i = 0; i < max_ctr; i++) {
+		strscpy(p, sja1105_port_counters[i].name, ETH_GSTRING_LEN);
+		p += ETH_GSTRING_LEN;
 	}
 }
 
 int sja1105_get_sset_count(struct dsa_switch *ds, int port, int sset)
 {
-	int count = ARRAY_SIZE(sja1105_port_stats);
 	struct sja1105_private *priv = ds->priv;
+	enum sja1105_counter_index max_ctr, i;
+	int sset_count = 0;
 
 	if (sset != ETH_SS_STATS)
 		return -EOPNOTSUPP;
 
-	if (priv->info->device_id == SJA1105PR_DEVICE_ID ||
-	    priv->info->device_id == SJA1105QS_DEVICE_ID)
-		count += ARRAY_SIZE(sja1105pqrs_extra_port_stats);
+	if (priv->info->device_id == SJA1105E_DEVICE_ID ||
+	    priv->info->device_id == SJA1105T_DEVICE_ID)
+		max_ctr = __MAX_SJA1105ET_PORT_COUNTER;
+	else
+		max_ctr = __MAX_SJA1105PQRS_PORT_COUNTER;
+
+	for (i = 0; i < max_ctr; i++) {
+		if (!strlen(sja1105_port_counters[i].name))
+			continue;
+
+		sset_count++;
+	}
 
-	return count;
+	return sset_count;
 }
diff --git a/drivers/net/dsa/sja1105/sja1105_flower.c b/drivers/net/dsa/sja1105/sja1105_flower.c
index 973761132fc3..6c10ffa968ce 100644
--- a/drivers/net/dsa/sja1105/sja1105_flower.c
+++ b/drivers/net/dsa/sja1105/sja1105_flower.c
@@ -35,6 +35,7 @@ static int sja1105_setup_bcast_policer(struct sja1105_private *priv,
 {
 	struct sja1105_rule *rule = sja1105_rule_find(priv, cookie);
 	struct sja1105_l2_policing_entry *policing;
+	struct dsa_switch *ds = priv->ds;
 	bool new_rule = false;
 	unsigned long p;
 	int rc;
@@ -59,7 +60,7 @@ static int sja1105_setup_bcast_policer(struct sja1105_private *priv,
 
 	policing = priv->static_config.tables[BLK_IDX_L2_POLICING].entries;
 
-	if (policing[(SJA1105_NUM_PORTS * SJA1105_NUM_TC) + port].sharindx != port) {
+	if (policing[(ds->num_ports * SJA1105_NUM_TC) + port].sharindx != port) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Port already has a broadcast policer");
 		rc = -EEXIST;
@@ -71,8 +72,8 @@ static int sja1105_setup_bcast_policer(struct sja1105_private *priv,
 	/* Make the broadcast policers of all ports attached to this block
 	 * point to the newly allocated policer
 	 */
-	for_each_set_bit(p, &rule->port_mask, SJA1105_NUM_PORTS) {
-		int bcast = (SJA1105_NUM_PORTS * SJA1105_NUM_TC) + p;
+	for_each_set_bit(p, &rule->port_mask, SJA1105_MAX_NUM_PORTS) {
+		int bcast = (ds->num_ports * SJA1105_NUM_TC) + p;
 
 		policing[bcast].sharindx = rule->bcast_pol.sharindx;
 	}
@@ -143,7 +144,7 @@ static int sja1105_setup_tc_policer(struct sja1105_private *priv,
 	/* Make the policers for traffic class @tc of all ports attached to
 	 * this block point to the newly allocated policer
 	 */
-	for_each_set_bit(p, &rule->port_mask, SJA1105_NUM_PORTS) {
+	for_each_set_bit(p, &rule->port_mask, SJA1105_MAX_NUM_PORTS) {
 		int index = (p * SJA1105_NUM_TC) + tc;
 
 		policing[index].sharindx = rule->tc_pol.sharindx;
@@ -435,7 +436,7 @@ int sja1105_cls_flower_del(struct dsa_switch *ds, int port,
 	policing = priv->static_config.tables[BLK_IDX_L2_POLICING].entries;
 
 	if (rule->type == SJA1105_RULE_BCAST_POLICER) {
-		int bcast = (SJA1105_NUM_PORTS * SJA1105_NUM_TC) + port;
+		int bcast = (ds->num_ports * SJA1105_NUM_TC) + port;
 
 		old_sharindx = policing[bcast].sharindx;
 		policing[bcast].sharindx = port;
@@ -486,7 +487,7 @@ void sja1105_flower_setup(struct dsa_switch *ds)
 
 	INIT_LIST_HEAD(&priv->flow_block.rules);
 
-	for (port = 0; port < SJA1105_NUM_PORTS; port++)
+	for (port = 0; port < ds->num_ports; port++)
 		priv->flow_block.l2_policer_used[port] = true;
 }
 
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index b88d9ef45a1f..a9777eb564c6 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -16,13 +16,13 @@
 #include <linux/of_net.h>
 #include <linux/of_mdio.h>
 #include <linux/of_device.h>
+#include <linux/pcs/pcs-xpcs.h>
 #include <linux/netdev_features.h>
 #include <linux/netdevice.h>
 #include <linux/if_bridge.h>
 #include <linux/if_ether.h>
 #include <linux/dsa/8021q.h>
 #include "sja1105.h"
-#include "sja1105_sgmii.h"
 #include "sja1105_tas.h"
 
 #define SJA1105_UNKNOWN_MULTICAST	0x010000000000ull
@@ -57,14 +57,6 @@ static bool sja1105_can_forward(struct sja1105_l2_forwarding_entry *l2_fwd,
 	return !!(l2_fwd[from].reach_port & BIT(to));
 }
 
-/* Structure used to temporarily transport device tree
- * settings into sja1105_setup
- */
-struct sja1105_dt_port {
-	phy_interface_t phy_mode;
-	sja1105_mii_role_t role;
-};
-
 static int sja1105_init_mac_settings(struct sja1105_private *priv)
 {
 	struct sja1105_mac_config_entry default_mac = {
@@ -80,7 +72,7 @@ static int sja1105_init_mac_settings(struct sja1105_private *priv)
 		/* Always put the MAC speed in automatic mode, where it can be
 		 * adjusted at runtime by PHYLINK.
 		 */
-		.speed = SJA1105_SPEED_AUTO,
+		.speed = priv->info->port_speed[SJA1105_SPEED_AUTO],
 		/* No static correction for 1-step 1588 events */
 		.tp_delin = 0,
 		.tp_delout = 0,
@@ -107,6 +99,7 @@ static int sja1105_init_mac_settings(struct sja1105_private *priv)
 		.ingress = false,
 	};
 	struct sja1105_mac_config_entry *mac;
+	struct dsa_switch *ds = priv->ds;
 	struct sja1105_table *table;
 	int i;
 
@@ -118,16 +111,16 @@ static int sja1105_init_mac_settings(struct sja1105_private *priv)
 		table->entry_count = 0;
 	}
 
-	table->entries = kcalloc(SJA1105_NUM_PORTS,
+	table->entries = kcalloc(table->ops->max_entry_count,
 				 table->ops->unpacked_entry_size, GFP_KERNEL);
 	if (!table->entries)
 		return -ENOMEM;
 
-	table->entry_count = SJA1105_NUM_PORTS;
+	table->entry_count = table->ops->max_entry_count;
 
 	mac = table->entries;
 
-	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
+	for (i = 0; i < ds->num_ports; i++) {
 		mac[i] = default_mac;
 		if (i == dsa_upstream_port(priv->ds, i)) {
 			/* STP doesn't get called for CPU port, so we need to
@@ -142,26 +135,11 @@ static int sja1105_init_mac_settings(struct sja1105_private *priv)
 	return 0;
 }
 
-static bool sja1105_supports_sgmii(struct sja1105_private *priv, int port)
-{
-	if (priv->info->part_no != SJA1105R_PART_NO &&
-	    priv->info->part_no != SJA1105S_PART_NO)
-		return false;
-
-	if (port != SJA1105_SGMII_PORT)
-		return false;
-
-	if (dsa_is_unused_port(priv->ds, port))
-		return false;
-
-	return true;
-}
-
-static int sja1105_init_mii_settings(struct sja1105_private *priv,
-				     struct sja1105_dt_port *ports)
+static int sja1105_init_mii_settings(struct sja1105_private *priv)
 {
 	struct device *dev = &priv->spidev->dev;
 	struct sja1105_xmii_params_entry *mii;
+	struct dsa_switch *ds = priv->ds;
 	struct sja1105_table *table;
 	int i;
 
@@ -173,52 +151,81 @@ static int sja1105_init_mii_settings(struct sja1105_private *priv,
 		table->entry_count = 0;
 	}
 
-	table->entries = kcalloc(SJA1105_MAX_XMII_PARAMS_COUNT,
+	table->entries = kcalloc(table->ops->max_entry_count,
 				 table->ops->unpacked_entry_size, GFP_KERNEL);
 	if (!table->entries)
 		return -ENOMEM;
 
 	/* Override table based on PHYLINK DT bindings */
-	table->entry_count = SJA1105_MAX_XMII_PARAMS_COUNT;
+	table->entry_count = table->ops->max_entry_count;
 
 	mii = table->entries;
 
-	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
+	for (i = 0; i < ds->num_ports; i++) {
+		sja1105_mii_role_t role = XMII_MAC;
+
 		if (dsa_is_unused_port(priv->ds, i))
 			continue;
 
-		switch (ports[i].phy_mode) {
+		switch (priv->phy_mode[i]) {
+		case PHY_INTERFACE_MODE_INTERNAL:
+			if (priv->info->internal_phy[i] == SJA1105_NO_PHY)
+				goto unsupported;
+
+			mii->xmii_mode[i] = XMII_MODE_MII;
+			if (priv->info->internal_phy[i] == SJA1105_PHY_BASE_TX)
+				mii->special[i] = true;
+
+			break;
+		case PHY_INTERFACE_MODE_REVMII:
+			role = XMII_PHY;
+			fallthrough;
 		case PHY_INTERFACE_MODE_MII:
+			if (!priv->info->supports_mii[i])
+				goto unsupported;
+
 			mii->xmii_mode[i] = XMII_MODE_MII;
 			break;
+		case PHY_INTERFACE_MODE_REVRMII:
+			role = XMII_PHY;
+			fallthrough;
 		case PHY_INTERFACE_MODE_RMII:
+			if (!priv->info->supports_rmii[i])
+				goto unsupported;
+
 			mii->xmii_mode[i] = XMII_MODE_RMII;
 			break;
 		case PHY_INTERFACE_MODE_RGMII:
 		case PHY_INTERFACE_MODE_RGMII_ID:
 		case PHY_INTERFACE_MODE_RGMII_RXID:
 		case PHY_INTERFACE_MODE_RGMII_TXID:
+			if (!priv->info->supports_rgmii[i])
+				goto unsupported;
+
 			mii->xmii_mode[i] = XMII_MODE_RGMII;
 			break;
 		case PHY_INTERFACE_MODE_SGMII:
-			if (!sja1105_supports_sgmii(priv, i))
-				return -EINVAL;
+			if (!priv->info->supports_sgmii[i])
+				goto unsupported;
+
+			mii->xmii_mode[i] = XMII_MODE_SGMII;
+			mii->special[i] = true;
+			break;
+		case PHY_INTERFACE_MODE_2500BASEX:
+			if (!priv->info->supports_2500basex[i])
+				goto unsupported;
+
 			mii->xmii_mode[i] = XMII_MODE_SGMII;
+			mii->special[i] = true;
 			break;
+unsupported:
 		default:
-			dev_err(dev, "Unsupported PHY mode %s!\n",
-				phy_modes(ports[i].phy_mode));
+			dev_err(dev, "Unsupported PHY mode %s on port %d!\n",
+				phy_modes(priv->phy_mode[i]), i);
 			return -EINVAL;
 		}
 
-		/* Even though the SerDes port is able to drive SGMII autoneg
-		 * like a PHY would, from the perspective of the XMII tables,
-		 * the SGMII port should always be put in MAC mode.
-		 */
-		if (ports[i].phy_mode == PHY_INTERFACE_MODE_SGMII)
-			mii->phy_mac[i] = XMII_MAC;
-		else
-			mii->phy_mac[i] = ports[i].role;
+		mii->phy_mac[i] = role;
 	}
 	return 0;
 }
@@ -267,8 +274,6 @@ static int sja1105_init_static_fdb(struct sja1105_private *priv)
 
 static int sja1105_init_l2_lookup_params(struct sja1105_private *priv)
 {
-	struct sja1105_table *table;
-	u64 max_fdb_entries = SJA1105_MAX_L2_LOOKUP_COUNT / SJA1105_NUM_PORTS;
 	struct sja1105_l2_lookup_params_entry default_l2_lookup_params = {
 		/* Learned FDB entries are forgotten after 300 seconds */
 		.maxage = SJA1105_AGEING_TIME_MS(300000),
@@ -276,8 +281,6 @@ static int sja1105_init_l2_lookup_params(struct sja1105_private *priv)
 		.dyn_tbsz = SJA1105ET_FDB_BIN_SIZE,
 		/* And the P/Q/R/S equivalent setting: */
 		.start_dynspc = 0,
-		.maxaddrp = {max_fdb_entries, max_fdb_entries, max_fdb_entries,
-			     max_fdb_entries, max_fdb_entries, },
 		/* 2^8 + 2^5 + 2^3 + 2^2 + 2^1 + 1 in Koopman notation */
 		.poly = 0x97,
 		/* This selects between Independent VLAN Learning (IVL) and
@@ -301,6 +304,23 @@ static int sja1105_init_l2_lookup_params(struct sja1105_private *priv)
 		.owr_dyn = true,
 		.drpnolearn = true,
 	};
+	struct dsa_switch *ds = priv->ds;
+	int port, num_used_ports = 0;
+	struct sja1105_table *table;
+	u64 max_fdb_entries;
+
+	for (port = 0; port < ds->num_ports; port++)
+		if (!dsa_is_unused_port(ds, port))
+			num_used_ports++;
+
+	max_fdb_entries = SJA1105_MAX_L2_LOOKUP_COUNT / num_used_ports;
+
+	for (port = 0; port < ds->num_ports; port++) {
+		if (dsa_is_unused_port(ds, port))
+			continue;
+
+		default_l2_lookup_params.maxaddrp[port] = max_fdb_entries;
+	}
 
 	table = &priv->static_config.tables[BLK_IDX_L2_LOOKUP_PARAMS];
 
@@ -309,12 +329,12 @@ static int sja1105_init_l2_lookup_params(struct sja1105_private *priv)
 		table->entry_count = 0;
 	}
 
-	table->entries = kcalloc(SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT,
+	table->entries = kcalloc(table->ops->max_entry_count,
 				 table->ops->unpacked_entry_size, GFP_KERNEL);
 	if (!table->entries)
 		return -ENOMEM;
 
-	table->entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT;
+	table->entry_count = table->ops->max_entry_count;
 
 	/* This table only has a single entry */
 	((struct sja1105_l2_lookup_params_entry *)table->entries)[0] =
@@ -334,6 +354,7 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv)
 {
 	struct sja1105_table *table;
 	struct sja1105_vlan_lookup_entry pvid = {
+		.type_entry = SJA1110_VLAN_D_TAG,
 		.ving_mirr = 0,
 		.vegr_mirr = 0,
 		.vmemb_port = 0,
@@ -387,6 +408,7 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv)
 static int sja1105_init_l2_forwarding(struct sja1105_private *priv)
 {
 	struct sja1105_l2_forwarding_entry *l2fwd;
+	struct dsa_switch *ds = priv->ds;
 	struct sja1105_table *table;
 	int i, j;
 
@@ -397,19 +419,22 @@ static int sja1105_init_l2_forwarding(struct sja1105_private *priv)
 		table->entry_count = 0;
 	}
 
-	table->entries = kcalloc(SJA1105_MAX_L2_FORWARDING_COUNT,
+	table->entries = kcalloc(table->ops->max_entry_count,
 				 table->ops->unpacked_entry_size, GFP_KERNEL);
 	if (!table->entries)
 		return -ENOMEM;
 
-	table->entry_count = SJA1105_MAX_L2_FORWARDING_COUNT;
+	table->entry_count = table->ops->max_entry_count;
 
 	l2fwd = table->entries;
 
 	/* First 5 entries define the forwarding rules */
-	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
+	for (i = 0; i < ds->num_ports; i++) {
 		unsigned int upstream = dsa_upstream_port(priv->ds, i);
 
+		if (dsa_is_unused_port(ds, i))
+			continue;
+
 		for (j = 0; j < SJA1105_NUM_TC; j++)
 			l2fwd[i].vlan_pmap[j] = j;
 
@@ -431,24 +456,66 @@ static int sja1105_init_l2_forwarding(struct sja1105_private *priv)
 		l2fwd[upstream].bc_domain |= BIT(i);
 		l2fwd[upstream].fl_domain |= BIT(i);
 	}
+
 	/* Next 8 entries define VLAN PCP mapping from ingress to egress.
 	 * Create a one-to-one mapping.
 	 */
-	for (i = 0; i < SJA1105_NUM_TC; i++)
-		for (j = 0; j < SJA1105_NUM_PORTS; j++)
-			l2fwd[SJA1105_NUM_PORTS + i].vlan_pmap[j] = i;
+	for (i = 0; i < SJA1105_NUM_TC; i++) {
+		for (j = 0; j < ds->num_ports; j++) {
+			if (dsa_is_unused_port(ds, j))
+				continue;
+
+			l2fwd[ds->num_ports + i].vlan_pmap[j] = i;
+		}
+
+		l2fwd[ds->num_ports + i].type_egrpcp2outputq = true;
+	}
+
+	return 0;
+}
+
+static int sja1110_init_pcp_remapping(struct sja1105_private *priv)
+{
+	struct sja1110_pcp_remapping_entry *pcp_remap;
+	struct dsa_switch *ds = priv->ds;
+	struct sja1105_table *table;
+	int port, tc;
+
+	table = &priv->static_config.tables[BLK_IDX_PCP_REMAPPING];
+
+	/* Nothing to do for SJA1105 */
+	if (!table->ops->max_entry_count)
+		return 0;
+
+	if (table->entry_count) {
+		kfree(table->entries);
+		table->entry_count = 0;
+	}
+
+	table->entries = kcalloc(table->ops->max_entry_count,
+				 table->ops->unpacked_entry_size, GFP_KERNEL);
+	if (!table->entries)
+		return -ENOMEM;
+
+	table->entry_count = table->ops->max_entry_count;
+
+	pcp_remap = table->entries;
+
+	/* Repeat the configuration done for vlan_pmap */
+	for (port = 0; port < ds->num_ports; port++) {
+		if (dsa_is_unused_port(ds, port))
+			continue;
+
+		for (tc = 0; tc < SJA1105_NUM_TC; tc++)
+			pcp_remap[port].egrpcp[tc] = tc;
+	}
 
 	return 0;
 }
 
 static int sja1105_init_l2_forwarding_params(struct sja1105_private *priv)
 {
-	struct sja1105_l2_forwarding_params_entry default_l2fwd_params = {
-		/* Disallow dynamic reconfiguration of vlan_pmap */
-		.max_dynp = 0,
-		/* Use a single memory partition for all ingress queues */
-		.part_spc = { SJA1105_MAX_FRAME_MEMORY, 0, 0, 0, 0, 0, 0, 0 },
-	};
+	struct sja1105_l2_forwarding_params_entry *l2fwd_params;
 	struct sja1105_table *table;
 
 	table = &priv->static_config.tables[BLK_IDX_L2_FORWARDING_PARAMS];
@@ -458,16 +525,20 @@ static int sja1105_init_l2_forwarding_params(struct sja1105_private *priv)
 		table->entry_count = 0;
 	}
 
-	table->entries = kcalloc(SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT,
+	table->entries = kcalloc(table->ops->max_entry_count,
 				 table->ops->unpacked_entry_size, GFP_KERNEL);
 	if (!table->entries)
 		return -ENOMEM;
 
-	table->entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT;
+	table->entry_count = table->ops->max_entry_count;
 
 	/* This table only has a single entry */
-	((struct sja1105_l2_forwarding_params_entry *)table->entries)[0] =
-				default_l2fwd_params;
+	l2fwd_params = table->entries;
+
+	/* Disallow dynamic reconfiguration of vlan_pmap */
+	l2fwd_params->max_dynp = 0;
+	/* Use a single memory partition for all ingress queues */
+	l2fwd_params->part_spc[0] = priv->info->max_frame_mem;
 
 	return 0;
 }
@@ -476,16 +547,14 @@ void sja1105_frame_memory_partitioning(struct sja1105_private *priv)
 {
 	struct sja1105_l2_forwarding_params_entry *l2_fwd_params;
 	struct sja1105_vl_forwarding_params_entry *vl_fwd_params;
+	int max_mem = priv->info->max_frame_mem;
 	struct sja1105_table *table;
-	int max_mem;
 
 	/* VLAN retagging is implemented using a loopback port that consumes
 	 * frame buffers. That leaves less for us.
 	 */
 	if (priv->vlan_state == SJA1105_VLAN_BEST_EFFORT)
-		max_mem = SJA1105_MAX_FRAME_MEMORY_RETAGGING;
-	else
-		max_mem = SJA1105_MAX_FRAME_MEMORY;
+		max_mem -= SJA1105_FRAME_MEMORY_RETAGGING_OVERHEAD;
 
 	table = &priv->static_config.tables[BLK_IDX_L2_FORWARDING_PARAMS];
 	l2_fwd_params = table->entries;
@@ -507,6 +576,60 @@ void sja1105_frame_memory_partitioning(struct sja1105_private *priv)
 	vl_fwd_params->partspc[0] = SJA1105_VL_FRAME_MEMORY;
 }
 
+/* SJA1110 TDMACONFIGIDX values:
+ *
+ *      | 100 Mbps ports |  1Gbps ports  | 2.5Gbps ports | Disabled ports
+ * -----+----------------+---------------+---------------+---------------
+ *   0  |   0, [5:10]    |     [1:2]     |     [3:4]     |     retag
+ *   1  |0, [5:10], retag|     [1:2]     |     [3:4]     |       -
+ *   2  |   0, [5:10]    |  [1:3], retag |       4       |       -
+ *   3  |   0, [5:10]    |[1:2], 4, retag|       3       |       -
+ *   4  |  0, 2, [5:10]  |    1, retag   |     [3:4]     |       -
+ *   5  |  0, 1, [5:10]  |    2, retag   |     [3:4]     |       -
+ *  14  |   0, [5:10]    | [1:4], retag  |       -       |       -
+ *  15  |     [5:10]     | [0:4], retag  |       -       |       -
+ */
+static void sja1110_select_tdmaconfigidx(struct sja1105_private *priv)
+{
+	struct sja1105_general_params_entry *general_params;
+	struct sja1105_table *table;
+	bool port_1_is_base_tx;
+	bool port_3_is_2500;
+	bool port_4_is_2500;
+	u64 tdmaconfigidx;
+
+	if (priv->info->device_id != SJA1110_DEVICE_ID)
+		return;
+
+	table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS];
+	general_params = table->entries;
+
+	/* All the settings below are "as opposed to SGMII", which is the
+	 * other pinmuxing option.
+	 */
+	port_1_is_base_tx = priv->phy_mode[1] == PHY_INTERFACE_MODE_INTERNAL;
+	port_3_is_2500 = priv->phy_mode[3] == PHY_INTERFACE_MODE_2500BASEX;
+	port_4_is_2500 = priv->phy_mode[4] == PHY_INTERFACE_MODE_2500BASEX;
+
+	if (port_1_is_base_tx)
+		/* Retagging port will operate at 1 Gbps */
+		tdmaconfigidx = 5;
+	else if (port_3_is_2500 && port_4_is_2500)
+		/* Retagging port will operate at 100 Mbps */
+		tdmaconfigidx = 1;
+	else if (port_3_is_2500)
+		/* Retagging port will operate at 1 Gbps */
+		tdmaconfigidx = 3;
+	else if (port_4_is_2500)
+		/* Retagging port will operate at 1 Gbps */
+		tdmaconfigidx = 2;
+	else
+		/* Retagging port will operate at 1 Gbps */
+		tdmaconfigidx = 14;
+
+	general_params->tdmaconfigidx = tdmaconfigidx;
+}
+
 static int sja1105_init_general_params(struct sja1105_private *priv)
 {
 	struct sja1105_general_params_entry default_general_params = {
@@ -530,17 +653,9 @@ static int sja1105_init_general_params(struct sja1105_private *priv)
 		 * receieved on host_port itself would be dropped, except
 		 * by installing a temporary 'management route'
 		 */
-		.host_port = dsa_upstream_port(priv->ds, 0),
+		.host_port = priv->ds->num_ports,
 		/* Default to an invalid value */
-		.mirr_port = SJA1105_NUM_PORTS,
-		/* Link-local traffic received on casc_port will be forwarded
-		 * to host_port without embedding the source port and device ID
-		 * info in the destination MAC address (presumably because it
-		 * is a cascaded port and a downstream SJA switch already did
-		 * that). Default to an invalid port (to disable the feature)
-		 * and overwrite this if we find any DSA (cascaded) ports.
-		 */
-		.casc_port = SJA1105_NUM_PORTS,
+		.mirr_port = priv->ds->num_ports,
 		/* No TTEthernet */
 		.vllupformat = SJA1105_VL_FORMAT_PSFP,
 		.vlmarker = 0,
@@ -552,8 +667,22 @@ static int sja1105_init_general_params(struct sja1105_private *priv)
 		 */
 		.tpid = ETH_P_SJA1105,
 		.tpid2 = ETH_P_SJA1105,
+		/* Enable the TTEthernet engine on SJA1110 */
+		.tte_en = true,
+		/* Set up the EtherType for control packets on SJA1110 */
+		.header_type = ETH_P_SJA1110,
 	};
+	struct sja1105_general_params_entry *general_params;
+	struct dsa_switch *ds = priv->ds;
 	struct sja1105_table *table;
+	int port;
+
+	for (port = 0; port < ds->num_ports; port++) {
+		if (dsa_is_cpu_port(ds, port)) {
+			default_general_params.host_port = port;
+			break;
+		}
+	}
 
 	table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS];
 
@@ -562,16 +691,32 @@ static int sja1105_init_general_params(struct sja1105_private *priv)
 		table->entry_count = 0;
 	}
 
-	table->entries = kcalloc(SJA1105_MAX_GENERAL_PARAMS_COUNT,
+	table->entries = kcalloc(table->ops->max_entry_count,
 				 table->ops->unpacked_entry_size, GFP_KERNEL);
 	if (!table->entries)
 		return -ENOMEM;
 
-	table->entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT;
+	table->entry_count = table->ops->max_entry_count;
+
+	general_params = table->entries;
 
 	/* This table only has a single entry */
-	((struct sja1105_general_params_entry *)table->entries)[0] =
-				default_general_params;
+	general_params[0] = default_general_params;
+
+	sja1110_select_tdmaconfigidx(priv);
+
+	/* Link-local traffic received on casc_port will be forwarded
+	 * to host_port without embedding the source port and device ID
+	 * info in the destination MAC address, and no RX timestamps will be
+	 * taken either (presumably because it is a cascaded port and a
+	 * downstream SJA switch already did that).
+	 * To disable the feature, we need to do different things depending on
+	 * switch generation. On SJA1105 we need to set an invalid port, while
+	 * on SJA1110 which support multiple cascaded ports, this field is a
+	 * bitmask so it must be left zero.
+	 */
+	if (!priv->info->multiple_cascade_ports)
+		general_params->casc_port = ds->num_ports;
 
 	return 0;
 }
@@ -589,12 +734,12 @@ static int sja1105_init_avb_params(struct sja1105_private *priv)
 		table->entry_count = 0;
 	}
 
-	table->entries = kcalloc(SJA1105_MAX_AVB_PARAMS_COUNT,
+	table->entries = kcalloc(table->ops->max_entry_count,
 				 table->ops->unpacked_entry_size, GFP_KERNEL);
 	if (!table->entries)
 		return -ENOMEM;
 
-	table->entry_count = SJA1105_MAX_AVB_PARAMS_COUNT;
+	table->entry_count = table->ops->max_entry_count;
 
 	avb = table->entries;
 
@@ -661,6 +806,7 @@ static int sja1105_init_avb_params(struct sja1105_private *priv)
 static int sja1105_init_l2_policing(struct sja1105_private *priv)
 {
 	struct sja1105_l2_policing_entry *policing;
+	struct dsa_switch *ds = priv->ds;
 	struct sja1105_table *table;
 	int port, tc;
 
@@ -672,27 +818,31 @@ static int sja1105_init_l2_policing(struct sja1105_private *priv)
 		table->entry_count = 0;
 	}
 
-	table->entries = kcalloc(SJA1105_MAX_L2_POLICING_COUNT,
+	table->entries = kcalloc(table->ops->max_entry_count,
 				 table->ops->unpacked_entry_size, GFP_KERNEL);
 	if (!table->entries)
 		return -ENOMEM;
 
-	table->entry_count = SJA1105_MAX_L2_POLICING_COUNT;
+	table->entry_count = table->ops->max_entry_count;
 
 	policing = table->entries;
 
 	/* Setup shared indices for the matchall policers */
-	for (port = 0; port < SJA1105_NUM_PORTS; port++) {
-		int bcast = (SJA1105_NUM_PORTS * SJA1105_NUM_TC) + port;
+	for (port = 0; port < ds->num_ports; port++) {
+		int mcast = (ds->num_ports * (SJA1105_NUM_TC + 1)) + port;
+		int bcast = (ds->num_ports * SJA1105_NUM_TC) + port;
 
 		for (tc = 0; tc < SJA1105_NUM_TC; tc++)
 			policing[port * SJA1105_NUM_TC + tc].sharindx = port;
 
 		policing[bcast].sharindx = port;
+		/* Only SJA1110 has multicast policers */
+		if (mcast <= table->ops->max_entry_count)
+			policing[mcast].sharindx = port;
 	}
 
 	/* Setup the matchall policer parameters */
-	for (port = 0; port < SJA1105_NUM_PORTS; port++) {
+	for (port = 0; port < ds->num_ports; port++) {
 		int mtu = VLAN_ETH_FRAME_LEN + ETH_FCS_LEN;
 
 		if (dsa_is_cpu_port(priv->ds, port))
@@ -707,8 +857,7 @@ static int sja1105_init_l2_policing(struct sja1105_private *priv)
 	return 0;
 }
 
-static int sja1105_static_config_load(struct sja1105_private *priv,
-				      struct sja1105_dt_port *ports)
+static int sja1105_static_config_load(struct sja1105_private *priv)
 {
 	int rc;
 
@@ -723,7 +872,7 @@ static int sja1105_static_config_load(struct sja1105_private *priv,
 	rc = sja1105_init_mac_settings(priv);
 	if (rc < 0)
 		return rc;
-	rc = sja1105_init_mii_settings(priv, ports);
+	rc = sja1105_init_mii_settings(priv);
 	if (rc < 0)
 		return rc;
 	rc = sja1105_init_static_fdb(priv);
@@ -750,37 +899,39 @@ static int sja1105_static_config_load(struct sja1105_private *priv,
 	rc = sja1105_init_avb_params(priv);
 	if (rc < 0)
 		return rc;
+	rc = sja1110_init_pcp_remapping(priv);
+	if (rc < 0)
+		return rc;
 
 	/* Send initial configuration to hardware via SPI */
 	return sja1105_static_config_upload(priv);
 }
 
-static int sja1105_parse_rgmii_delays(struct sja1105_private *priv,
-				      const struct sja1105_dt_port *ports)
+static int sja1105_parse_rgmii_delays(struct sja1105_private *priv)
 {
-	int i;
+	struct dsa_switch *ds = priv->ds;
+	int port;
 
-	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
-		if (ports[i].role == XMII_MAC)
+	for (port = 0; port < ds->num_ports; port++) {
+		if (!priv->fixed_link[port])
 			continue;
 
-		if (ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_RXID ||
-		    ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_ID)
-			priv->rgmii_rx_delay[i] = true;
+		if (priv->phy_mode[port] == PHY_INTERFACE_MODE_RGMII_RXID ||
+		    priv->phy_mode[port] == PHY_INTERFACE_MODE_RGMII_ID)
+			priv->rgmii_rx_delay[port] = true;
 
-		if (ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_TXID ||
-		    ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_ID)
-			priv->rgmii_tx_delay[i] = true;
+		if (priv->phy_mode[port] == PHY_INTERFACE_MODE_RGMII_TXID ||
+		    priv->phy_mode[port] == PHY_INTERFACE_MODE_RGMII_ID)
+			priv->rgmii_tx_delay[port] = true;
 
-		if ((priv->rgmii_rx_delay[i] || priv->rgmii_tx_delay[i]) &&
-		     !priv->info->setup_rgmii_delay)
+		if ((priv->rgmii_rx_delay[port] || priv->rgmii_tx_delay[port]) &&
+		    !priv->info->setup_rgmii_delay)
 			return -EINVAL;
 	}
 	return 0;
 }
 
 static int sja1105_parse_ports_node(struct sja1105_private *priv,
-				    struct sja1105_dt_port *ports,
 				    struct device_node *ports_node)
 {
 	struct device *dev = &priv->spidev->dev;
@@ -809,7 +960,6 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv,
 			of_node_put(child);
 			return -ENODEV;
 		}
-		ports[index].phy_mode = phy_mode;
 
 		phy_node = of_parse_phandle(child, "phy-handle", 0);
 		if (!phy_node) {
@@ -822,25 +972,18 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv,
 			/* phy-handle is missing, but fixed-link isn't.
 			 * So it's a fixed link. Default to PHY role.
 			 */
-			ports[index].role = XMII_PHY;
+			priv->fixed_link[index] = true;
 		} else {
-			/* phy-handle present => put port in MAC role */
-			ports[index].role = XMII_MAC;
 			of_node_put(phy_node);
 		}
 
-		/* The MAC/PHY role can be overridden with explicit bindings */
-		if (of_property_read_bool(child, "sja1105,role-mac"))
-			ports[index].role = XMII_MAC;
-		else if (of_property_read_bool(child, "sja1105,role-phy"))
-			ports[index].role = XMII_PHY;
+		priv->phy_mode[index] = phy_mode;
 	}
 
 	return 0;
 }
 
-static int sja1105_parse_dt(struct sja1105_private *priv,
-			    struct sja1105_dt_port *ports)
+static int sja1105_parse_dt(struct sja1105_private *priv)
 {
 	struct device *dev = &priv->spidev->dev;
 	struct device_node *switch_node = dev->of_node;
@@ -848,113 +991,41 @@ static int sja1105_parse_dt(struct sja1105_private *priv,
 	int rc;
 
 	ports_node = of_get_child_by_name(switch_node, "ports");
+	if (!ports_node)
+		ports_node = of_get_child_by_name(switch_node, "ethernet-ports");
 	if (!ports_node) {
 		dev_err(dev, "Incorrect bindings: absent \"ports\" node\n");
 		return -ENODEV;
 	}
 
-	rc = sja1105_parse_ports_node(priv, ports, ports_node);
+	rc = sja1105_parse_ports_node(priv, ports_node);
 	of_node_put(ports_node);
 
 	return rc;
 }
 
-static int sja1105_sgmii_read(struct sja1105_private *priv, int pcs_reg)
-{
-	const struct sja1105_regs *regs = priv->info->regs;
-	u32 val;
-	int rc;
-
-	rc = sja1105_xfer_u32(priv, SPI_READ, regs->sgmii + pcs_reg, &val,
-			      NULL);
-	if (rc < 0)
-		return rc;
-
-	return val;
-}
-
-static int sja1105_sgmii_write(struct sja1105_private *priv, int pcs_reg,
-			       u16 pcs_val)
-{
-	const struct sja1105_regs *regs = priv->info->regs;
-	u32 val = pcs_val;
-	int rc;
-
-	rc = sja1105_xfer_u32(priv, SPI_WRITE, regs->sgmii + pcs_reg, &val,
-			      NULL);
-	if (rc < 0)
-		return rc;
-
-	return val;
-}
-
-static void sja1105_sgmii_pcs_config(struct sja1105_private *priv,
-				     bool an_enabled, bool an_master)
+/* Convert link speed from SJA1105 to ethtool encoding */
+static int sja1105_port_speed_to_ethtool(struct sja1105_private *priv,
+					 u64 speed)
 {
-	u16 ac = SJA1105_AC_AUTONEG_MODE_SGMII;
-
-	/* DIGITAL_CONTROL_1: Enable vendor-specific MMD1, allow the PHY to
-	 * stop the clock during LPI mode, make the MAC reconfigure
-	 * autonomously after PCS autoneg is done, flush the internal FIFOs.
-	 */
-	sja1105_sgmii_write(priv, SJA1105_DC1, SJA1105_DC1_EN_VSMMD1 |
-					       SJA1105_DC1_CLOCK_STOP_EN |
-					       SJA1105_DC1_MAC_AUTO_SW |
-					       SJA1105_DC1_INIT);
-	/* DIGITAL_CONTROL_2: No polarity inversion for TX and RX lanes */
-	sja1105_sgmii_write(priv, SJA1105_DC2, SJA1105_DC2_TX_POL_INV_DISABLE);
-	/* AUTONEG_CONTROL: Use SGMII autoneg */
-	if (an_master)
-		ac |= SJA1105_AC_PHY_MODE | SJA1105_AC_SGMII_LINK;
-	sja1105_sgmii_write(priv, SJA1105_AC, ac);
-	/* BASIC_CONTROL: enable in-band AN now, if requested. Otherwise,
-	 * sja1105_sgmii_pcs_force_speed must be called later for the link
-	 * to become operational.
-	 */
-	if (an_enabled)
-		sja1105_sgmii_write(priv, MII_BMCR,
-				    BMCR_ANENABLE | BMCR_ANRESTART);
+	if (speed == priv->info->port_speed[SJA1105_SPEED_10MBPS])
+		return SPEED_10;
+	if (speed == priv->info->port_speed[SJA1105_SPEED_100MBPS])
+		return SPEED_100;
+	if (speed == priv->info->port_speed[SJA1105_SPEED_1000MBPS])
+		return SPEED_1000;
+	if (speed == priv->info->port_speed[SJA1105_SPEED_2500MBPS])
+		return SPEED_2500;
+	return SPEED_UNKNOWN;
 }
 
-static void sja1105_sgmii_pcs_force_speed(struct sja1105_private *priv,
-					  int speed)
-{
-	int pcs_speed;
-
-	switch (speed) {
-	case SPEED_1000:
-		pcs_speed = BMCR_SPEED1000;
-		break;
-	case SPEED_100:
-		pcs_speed = BMCR_SPEED100;
-		break;
-	case SPEED_10:
-		pcs_speed = BMCR_SPEED10;
-		break;
-	default:
-		dev_err(priv->ds->dev, "Invalid speed %d\n", speed);
-		return;
-	}
-	sja1105_sgmii_write(priv, MII_BMCR, pcs_speed | BMCR_FULLDPLX);
-}
-
-/* Convert link speed from SJA1105 to ethtool encoding */
-static int sja1105_speed[] = {
-	[SJA1105_SPEED_AUTO]		= SPEED_UNKNOWN,
-	[SJA1105_SPEED_10MBPS]		= SPEED_10,
-	[SJA1105_SPEED_100MBPS]		= SPEED_100,
-	[SJA1105_SPEED_1000MBPS]	= SPEED_1000,
-};
-
 /* Set link speed in the MAC configuration for a specific port. */
 static int sja1105_adjust_port_config(struct sja1105_private *priv, int port,
 				      int speed_mbps)
 {
-	struct sja1105_xmii_params_entry *mii;
 	struct sja1105_mac_config_entry *mac;
 	struct device *dev = priv->ds->dev;
-	sja1105_phy_interface_t phy_mode;
-	sja1105_speed_t speed;
+	u64 speed;
 	int rc;
 
 	/* On P/Q/R/S, one can read from the device via the MAC reconfiguration
@@ -964,7 +1035,6 @@ static int sja1105_adjust_port_config(struct sja1105_private *priv, int port,
 	 * reasonable approximation for both E/T and P/Q/R/S.
 	 */
 	mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries;
-	mii = priv->static_config.tables[BLK_IDX_XMII_PARAMS].entries;
 
 	switch (speed_mbps) {
 	case SPEED_UNKNOWN:
@@ -975,16 +1045,19 @@ static int sja1105_adjust_port_config(struct sja1105_private *priv, int port,
 		 * ok for power consumption in case AN will never complete -
 		 * otherwise PHYLINK should come back with a new update.
 		 */
-		speed = SJA1105_SPEED_AUTO;
+		speed = priv->info->port_speed[SJA1105_SPEED_AUTO];
 		break;
 	case SPEED_10:
-		speed = SJA1105_SPEED_10MBPS;
+		speed = priv->info->port_speed[SJA1105_SPEED_10MBPS];
 		break;
 	case SPEED_100:
-		speed = SJA1105_SPEED_100MBPS;
+		speed = priv->info->port_speed[SJA1105_SPEED_100MBPS];
 		break;
 	case SPEED_1000:
-		speed = SJA1105_SPEED_1000MBPS;
+		speed = priv->info->port_speed[SJA1105_SPEED_1000MBPS];
+		break;
+	case SPEED_2500:
+		speed = priv->info->port_speed[SJA1105_SPEED_2500MBPS];
 		break;
 	default:
 		dev_err(dev, "Invalid speed %iMbps\n", speed_mbps);
@@ -998,8 +1071,10 @@ static int sja1105_adjust_port_config(struct sja1105_private *priv, int port,
 	 * Actually for the SGMII port, the MAC is fixed at 1 Gbps and
 	 * we need to configure the PCS only (if even that).
 	 */
-	if (sja1105_supports_sgmii(priv, port))
-		mac[port].speed = SJA1105_SPEED_1000MBPS;
+	if (priv->phy_mode[port] == PHY_INTERFACE_MODE_SGMII)
+		mac[port].speed = priv->info->port_speed[SJA1105_SPEED_1000MBPS];
+	else if (priv->phy_mode[port] == PHY_INTERFACE_MODE_2500BASEX)
+		mac[port].speed = priv->info->port_speed[SJA1105_SPEED_2500MBPS];
 	else
 		mac[port].speed = speed;
 
@@ -1017,8 +1092,7 @@ static int sja1105_adjust_port_config(struct sja1105_private *priv, int port,
 	 * the clock setup does interrupt the clock signal for a certain time
 	 * which causes trouble for all PHYs relying on this signal.
 	 */
-	phy_mode = mii->xmii_mode[port];
-	if (phy_mode != XMII_MODE_RGMII)
+	if (!phy_interface_mode_is_rgmii(priv->phy_mode[port]))
 		return 0;
 
 	return sja1105_clocking_setup_port(priv, port);
@@ -1034,35 +1108,16 @@ static int sja1105_adjust_port_config(struct sja1105_private *priv, int port,
 static bool sja1105_phy_mode_mismatch(struct sja1105_private *priv, int port,
 				      phy_interface_t interface)
 {
-	struct sja1105_xmii_params_entry *mii;
-	sja1105_phy_interface_t phy_mode;
-
-	mii = priv->static_config.tables[BLK_IDX_XMII_PARAMS].entries;
-	phy_mode = mii->xmii_mode[port];
-
-	switch (interface) {
-	case PHY_INTERFACE_MODE_MII:
-		return (phy_mode != XMII_MODE_MII);
-	case PHY_INTERFACE_MODE_RMII:
-		return (phy_mode != XMII_MODE_RMII);
-	case PHY_INTERFACE_MODE_RGMII:
-	case PHY_INTERFACE_MODE_RGMII_ID:
-	case PHY_INTERFACE_MODE_RGMII_RXID:
-	case PHY_INTERFACE_MODE_RGMII_TXID:
-		return (phy_mode != XMII_MODE_RGMII);
-	case PHY_INTERFACE_MODE_SGMII:
-		return (phy_mode != XMII_MODE_SGMII);
-	default:
-		return true;
-	}
+	return priv->phy_mode[port] != interface;
 }
 
 static void sja1105_mac_config(struct dsa_switch *ds, int port,
 			       unsigned int mode,
 			       const struct phylink_link_state *state)
 {
+	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct sja1105_private *priv = ds->priv;
-	bool is_sgmii = sja1105_supports_sgmii(priv, port);
+	struct dw_xpcs *xpcs;
 
 	if (sja1105_phy_mode_mismatch(priv, port, state->interface)) {
 		dev_err(ds->dev, "Changing PHY mode to %s not supported!\n",
@@ -1070,14 +1125,10 @@ static void sja1105_mac_config(struct dsa_switch *ds, int port,
 		return;
 	}
 
-	if (phylink_autoneg_inband(mode) && !is_sgmii) {
-		dev_err(ds->dev, "In-band AN not supported!\n");
-		return;
-	}
+	xpcs = priv->xpcs[port];
 
-	if (is_sgmii)
-		sja1105_sgmii_pcs_config(priv, phylink_autoneg_inband(mode),
-					 false);
+	if (xpcs)
+		phylink_set_pcs(dp->pl, &xpcs->pcs);
 }
 
 static void sja1105_mac_link_down(struct dsa_switch *ds, int port,
@@ -1098,9 +1149,6 @@ static void sja1105_mac_link_up(struct dsa_switch *ds, int port,
 
 	sja1105_adjust_port_config(priv, port, speed);
 
-	if (sja1105_supports_sgmii(priv, port) && !phylink_autoneg_inband(mode))
-		sja1105_sgmii_pcs_force_speed(priv, speed);
-
 	sja1105_inhibit_tx(priv, BIT(port), false);
 }
 
@@ -1139,44 +1187,16 @@ static void sja1105_phylink_validate(struct dsa_switch *ds, int port,
 	if (mii->xmii_mode[port] == XMII_MODE_RGMII ||
 	    mii->xmii_mode[port] == XMII_MODE_SGMII)
 		phylink_set(mask, 1000baseT_Full);
+	if (priv->info->supports_2500basex[port]) {
+		phylink_set(mask, 2500baseT_Full);
+		phylink_set(mask, 2500baseX_Full);
+	}
 
 	bitmap_and(supported, supported, mask, __ETHTOOL_LINK_MODE_MASK_NBITS);
 	bitmap_and(state->advertising, state->advertising, mask,
 		   __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
-static int sja1105_mac_pcs_get_state(struct dsa_switch *ds, int port,
-				     struct phylink_link_state *state)
-{
-	struct sja1105_private *priv = ds->priv;
-	int ais;
-
-	/* Read the vendor-specific AUTONEG_INTR_STATUS register */
-	ais = sja1105_sgmii_read(priv, SJA1105_AIS);
-	if (ais < 0)
-		return ais;
-
-	switch (SJA1105_AIS_SPEED(ais)) {
-	case 0:
-		state->speed = SPEED_10;
-		break;
-	case 1:
-		state->speed = SPEED_100;
-		break;
-	case 2:
-		state->speed = SPEED_1000;
-		break;
-	default:
-		dev_err(ds->dev, "Invalid SGMII PCS speed %lu\n",
-			SJA1105_AIS_SPEED(ais));
-	}
-	state->duplex = SJA1105_AIS_DUPLEX_MODE(ais);
-	state->an_complete = SJA1105_AIS_COMPLETE(ais);
-	state->link = SJA1105_AIS_LINK_STATUS(ais);
-
-	return 0;
-}
-
 static int
 sja1105_find_static_fdb_entry(struct sja1105_private *priv, int port,
 			      const struct sja1105_l2_lookup_entry *requested)
@@ -1635,7 +1655,7 @@ static int sja1105_bridge_member(struct dsa_switch *ds, int port,
 
 	l2_fwd = priv->static_config.tables[BLK_IDX_L2_FORWARDING].entries;
 
-	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
+	for (i = 0; i < ds->num_ports; i++) {
 		/* Add this port to the forwarding matrix of the
 		 * other ports in the same bridge, and viceversa.
 		 */
@@ -1833,12 +1853,12 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
 {
 	struct ptp_system_timestamp ptp_sts_before;
 	struct ptp_system_timestamp ptp_sts_after;
+	int speed_mbps[SJA1105_MAX_NUM_PORTS];
+	u16 bmcr[SJA1105_MAX_NUM_PORTS] = {0};
 	struct sja1105_mac_config_entry *mac;
-	int speed_mbps[SJA1105_NUM_PORTS];
 	struct dsa_switch *ds = priv->ds;
 	s64 t1, t2, t3, t4;
 	s64 t12, t34;
-	u16 bmcr = 0;
 	int rc, i;
 	s64 now;
 
@@ -1851,29 +1871,38 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
 	 * switch wants to see in the static config in order to allow us to
 	 * change it through the dynamic interface later.
 	 */
-	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
-		speed_mbps[i] = sja1105_speed[mac[i].speed];
-		mac[i].speed = SJA1105_SPEED_AUTO;
-	}
+	for (i = 0; i < ds->num_ports; i++) {
+		u32 reg_addr = mdiobus_c45_addr(MDIO_MMD_VEND2, MDIO_CTRL1);
+
+		speed_mbps[i] = sja1105_port_speed_to_ethtool(priv,
+							      mac[i].speed);
+		mac[i].speed = priv->info->port_speed[SJA1105_SPEED_AUTO];
 
-	if (sja1105_supports_sgmii(priv, SJA1105_SGMII_PORT))
-		bmcr = sja1105_sgmii_read(priv, MII_BMCR);
+		if (priv->xpcs[i])
+			bmcr[i] = mdiobus_read(priv->mdio_pcs, i, reg_addr);
+	}
 
 	/* No PTP operations can run right now */
 	mutex_lock(&priv->ptp_data.lock);
 
 	rc = __sja1105_ptp_gettimex(ds, &now, &ptp_sts_before);
-	if (rc < 0)
-		goto out_unlock_ptp;
+	if (rc < 0) {
+		mutex_unlock(&priv->ptp_data.lock);
+		goto out;
+	}
 
 	/* Reset switch and send updated static configuration */
 	rc = sja1105_static_config_upload(priv);
-	if (rc < 0)
-		goto out_unlock_ptp;
+	if (rc < 0) {
+		mutex_unlock(&priv->ptp_data.lock);
+		goto out;
+	}
 
 	rc = __sja1105_ptp_settime(ds, 0, &ptp_sts_after);
-	if (rc < 0)
-		goto out_unlock_ptp;
+	if (rc < 0) {
+		mutex_unlock(&priv->ptp_data.lock);
+		goto out;
+	}
 
 	t1 = timespec64_to_ns(&ptp_sts_before.pre_ts);
 	t2 = timespec64_to_ns(&ptp_sts_before.post_ts);
@@ -1888,7 +1917,6 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
 
 	__sja1105_ptp_adjtime(ds, now);
 
-out_unlock_ptp:
 	mutex_unlock(&priv->ptp_data.lock);
 
 	dev_info(priv->ds->dev,
@@ -1899,32 +1927,48 @@ out_unlock_ptp:
 	 * For these interfaces there is no dynamic configuration
 	 * needed, since PLLs have same settings at all speeds.
 	 */
-	rc = sja1105_clocking_setup(priv);
-	if (rc < 0)
-		goto out;
+	if (priv->info->clocking_setup) {
+		rc = priv->info->clocking_setup(priv);
+		if (rc < 0)
+			goto out;
+	}
+
+	for (i = 0; i < ds->num_ports; i++) {
+		struct dw_xpcs *xpcs = priv->xpcs[i];
+		unsigned int mode;
 
-	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
 		rc = sja1105_adjust_port_config(priv, i, speed_mbps[i]);
 		if (rc < 0)
 			goto out;
-	}
 
-	if (sja1105_supports_sgmii(priv, SJA1105_SGMII_PORT)) {
-		bool an_enabled = !!(bmcr & BMCR_ANENABLE);
+		if (!xpcs)
+			continue;
 
-		sja1105_sgmii_pcs_config(priv, an_enabled, false);
+		if (bmcr[i] & BMCR_ANENABLE)
+			mode = MLO_AN_INBAND;
+		else if (priv->fixed_link[i])
+			mode = MLO_AN_FIXED;
+		else
+			mode = MLO_AN_PHY;
 
-		if (!an_enabled) {
+		rc = xpcs_do_config(xpcs, priv->phy_mode[i], mode);
+		if (rc < 0)
+			goto out;
+
+		if (!phylink_autoneg_inband(mode)) {
 			int speed = SPEED_UNKNOWN;
 
-			if (bmcr & BMCR_SPEED1000)
+			if (priv->phy_mode[i] == PHY_INTERFACE_MODE_2500BASEX)
+				speed = SPEED_2500;
+			else if (bmcr[i] & BMCR_SPEED1000)
 				speed = SPEED_1000;
-			else if (bmcr & BMCR_SPEED100)
+			else if (bmcr[i] & BMCR_SPEED100)
 				speed = SPEED_100;
 			else
 				speed = SPEED_10;
 
-			sja1105_sgmii_pcs_force_speed(priv, speed);
+			xpcs_link_up(&xpcs->pcs, mode, priv->phy_mode[i],
+				     speed, DUPLEX_FULL);
 		}
 	}
 
@@ -2032,7 +2076,9 @@ static enum dsa_tag_protocol
 sja1105_get_tag_protocol(struct dsa_switch *ds, int port,
 			 enum dsa_tag_protocol mp)
 {
-	return DSA_TAG_PROTO_SJA1105;
+	struct sja1105_private *priv = ds->priv;
+
+	return priv->info->tag_proto;
 }
 
 static int sja1105_find_free_subvlan(u16 *subvlan_map, bool pvid)
@@ -2272,6 +2318,7 @@ sja1105_build_bridge_vlans(struct sja1105_private *priv,
 		new_vlan[match].vlan_bc |= BIT(v->port);
 		if (!v->untagged)
 			new_vlan[match].tag_port |= BIT(v->port);
+		new_vlan[match].type_entry = SJA1110_VLAN_D_TAG;
 	}
 
 	return 0;
@@ -2294,6 +2341,7 @@ sja1105_build_dsa_8021q_vlans(struct sja1105_private *priv,
 		new_vlan[match].vlan_bc |= BIT(v->port);
 		if (!v->untagged)
 			new_vlan[match].tag_port |= BIT(v->port);
+		new_vlan[match].type_entry = SJA1110_VLAN_D_TAG;
 	}
 
 	return 0;
@@ -2354,6 +2402,7 @@ static int sja1105_build_subvlans(struct sja1105_private *priv,
 			new_vlan[match].tag_port |= BIT(v->port);
 		/* But it's always tagged towards the CPU */
 		new_vlan[match].tag_port |= BIT(upstream);
+		new_vlan[match].type_entry = SJA1110_VLAN_D_TAG;
 
 		/* The Retagging Table generates packet *clones* with
 		 * the new VLAN. This is a very odd hardware quirk
@@ -2521,6 +2570,7 @@ sja1105_build_crosschip_subvlans(struct sja1105_private *priv,
 		if (!tmp->untagged)
 			new_vlan[match].tag_port |= BIT(tmp->port);
 		new_vlan[match].tag_port |= BIT(upstream);
+		new_vlan[match].type_entry = SJA1110_VLAN_D_TAG;
 		/* Deny egress of @rx_vid towards our front-panel port.
 		 * This will force the switch to drop it, and we'll see
 		 * only the re-retagged packets (having the original,
@@ -2611,7 +2661,7 @@ out:
 
 static int sja1105_build_vlan_table(struct sja1105_private *priv, bool notify)
 {
-	u16 subvlan_map[SJA1105_NUM_PORTS][DSA_8021Q_N_SUBVLAN];
+	u16 subvlan_map[SJA1105_MAX_NUM_PORTS][DSA_8021Q_N_SUBVLAN];
 	struct sja1105_retagging_entry *new_retagging;
 	struct sja1105_vlan_lookup_entry *new_vlan;
 	struct sja1105_table *table;
@@ -2958,11 +3008,10 @@ static const struct dsa_8021q_ops sja1105_dsa_8021q_ops = {
  */
 static int sja1105_setup(struct dsa_switch *ds)
 {
-	struct sja1105_dt_port ports[SJA1105_NUM_PORTS];
 	struct sja1105_private *priv = ds->priv;
 	int rc;
 
-	rc = sja1105_parse_dt(priv, ports);
+	rc = sja1105_parse_dt(priv);
 	if (rc < 0) {
 		dev_err(ds->dev, "Failed to parse DT: %d\n", rc);
 		return rc;
@@ -2971,7 +3020,7 @@ static int sja1105_setup(struct dsa_switch *ds)
 	/* Error out early if internal delays are required through DT
 	 * and we can't apply them.
 	 */
-	rc = sja1105_parse_rgmii_delays(priv, ports);
+	rc = sja1105_parse_rgmii_delays(priv);
 	if (rc < 0) {
 		dev_err(ds->dev, "RGMII delay not supported\n");
 		return rc;
@@ -2982,18 +3031,42 @@ static int sja1105_setup(struct dsa_switch *ds)
 		dev_err(ds->dev, "Failed to register PTP clock: %d\n", rc);
 		return rc;
 	}
+
+	rc = sja1105_mdiobus_register(ds);
+	if (rc < 0) {
+		dev_err(ds->dev, "Failed to register MDIO bus: %pe\n",
+			ERR_PTR(rc));
+		goto out_ptp_clock_unregister;
+	}
+
+	if (priv->info->disable_microcontroller) {
+		rc = priv->info->disable_microcontroller(priv);
+		if (rc < 0) {
+			dev_err(ds->dev,
+				"Failed to disable microcontroller: %pe\n",
+				ERR_PTR(rc));
+			goto out_mdiobus_unregister;
+		}
+	}
+
 	/* Create and send configuration down to device */
-	rc = sja1105_static_config_load(priv, ports);
+	rc = sja1105_static_config_load(priv);
 	if (rc < 0) {
 		dev_err(ds->dev, "Failed to load static config: %d\n", rc);
-		goto out_ptp_clock_unregister;
+		goto out_mdiobus_unregister;
 	}
+
 	/* Configure the CGU (PHY link modes and speeds) */
-	rc = sja1105_clocking_setup(priv);
-	if (rc < 0) {
-		dev_err(ds->dev, "Failed to configure MII clocking: %d\n", rc);
-		goto out_static_config_free;
+	if (priv->info->clocking_setup) {
+		rc = priv->info->clocking_setup(priv);
+		if (rc < 0) {
+			dev_err(ds->dev,
+				"Failed to configure MII clocking: %pe\n",
+				ERR_PTR(rc));
+			goto out_static_config_free;
+		}
 	}
+
 	/* On SJA1105, VLAN filtering per se is always enabled in hardware.
 	 * The only thing we can do to disable it is lie about what the 802.1Q
 	 * EtherType is.
@@ -3029,6 +3102,8 @@ static int sja1105_setup(struct dsa_switch *ds)
 
 out_devlink_teardown:
 	sja1105_devlink_teardown(ds);
+out_mdiobus_unregister:
+	sja1105_mdiobus_unregister(ds);
 out_ptp_clock_unregister:
 	sja1105_ptp_clock_unregister(ds);
 out_static_config_free:
@@ -3043,7 +3118,7 @@ static void sja1105_teardown(struct dsa_switch *ds)
 	struct sja1105_bridge_vlan *v, *n;
 	int port;
 
-	for (port = 0; port < SJA1105_NUM_PORTS; port++) {
+	for (port = 0; port < ds->num_ports; port++) {
 		struct sja1105_port *sp = &priv->ports[port];
 
 		if (!dsa_is_user_port(ds, port))
@@ -3246,6 +3321,7 @@ static int sja1105_mirror_apply(struct sja1105_private *priv, int from, int to,
 {
 	struct sja1105_general_params_entry *general_params;
 	struct sja1105_mac_config_entry *mac;
+	struct dsa_switch *ds = priv->ds;
 	struct sja1105_table *table;
 	bool already_enabled;
 	u64 new_mirr_port;
@@ -3256,7 +3332,7 @@ static int sja1105_mirror_apply(struct sja1105_private *priv, int from, int to,
 
 	mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries;
 
-	already_enabled = (general_params->mirr_port != SJA1105_NUM_PORTS);
+	already_enabled = (general_params->mirr_port != ds->num_ports);
 	if (already_enabled && enabled && general_params->mirr_port != to) {
 		dev_err(priv->ds->dev,
 			"Delete mirroring rules towards port %llu first\n",
@@ -3270,7 +3346,7 @@ static int sja1105_mirror_apply(struct sja1105_private *priv, int from, int to,
 		int port;
 
 		/* Anybody still referencing mirr_port? */
-		for (port = 0; port < SJA1105_NUM_PORTS; port++) {
+		for (port = 0; port < ds->num_ports; port++) {
 			if (mac[port].ing_mirr || mac[port].egr_mirr) {
 				keep = true;
 				break;
@@ -3278,7 +3354,7 @@ static int sja1105_mirror_apply(struct sja1105_private *priv, int from, int to,
 		}
 		/* Unset already_enabled for next time */
 		if (!keep)
-			new_mirr_port = SJA1105_NUM_PORTS;
+			new_mirr_port = ds->num_ports;
 	}
 	if (new_mirr_port != general_params->mirr_port) {
 		general_params->mirr_port = new_mirr_port;
@@ -3489,7 +3565,6 @@ static const struct dsa_switch_ops sja1105_switch_ops = {
 	.port_change_mtu	= sja1105_change_mtu,
 	.port_max_mtu		= sja1105_get_max_mtu,
 	.phylink_validate	= sja1105_phylink_validate,
-	.phylink_mac_link_state	= sja1105_mac_pcs_get_state,
 	.phylink_mac_config	= sja1105_mac_config,
 	.phylink_mac_link_up	= sja1105_mac_link_up,
 	.phylink_mac_link_down	= sja1105_mac_link_down,
@@ -3584,6 +3659,7 @@ static int sja1105_probe(struct spi_device *spi)
 	struct sja1105_tagger_data *tagger_data;
 	struct device *dev = &spi->dev;
 	struct sja1105_private *priv;
+	size_t max_xfer, max_msg;
 	struct dsa_switch *ds;
 	int rc, port;
 
@@ -3617,6 +3693,33 @@ static int sja1105_probe(struct spi_device *spi)
 		return rc;
 	}
 
+	/* In sja1105_xfer, we send spi_messages composed of two spi_transfers:
+	 * a small one for the message header and another one for the current
+	 * chunk of the packed buffer.
+	 * Check that the restrictions imposed by the SPI controller are
+	 * respected: the chunk buffer is smaller than the max transfer size,
+	 * and the total length of the chunk plus its message header is smaller
+	 * than the max message size.
+	 * We do that during probe time since the maximum transfer size is a
+	 * runtime invariant.
+	 */
+	max_xfer = spi_max_transfer_size(spi);
+	max_msg = spi_max_message_size(spi);
+
+	/* We need to send at least one 64-bit word of SPI payload per message
+	 * in order to be able to make useful progress.
+	 */
+	if (max_msg < SJA1105_SIZE_SPI_MSG_HEADER + 8) {
+		dev_err(dev, "SPI master cannot send large enough buffers, aborting\n");
+		return -EINVAL;
+	}
+
+	priv->max_xfer_len = SJA1105_SIZE_SPI_MSG_MAXLEN;
+	if (priv->max_xfer_len > max_xfer)
+		priv->max_xfer_len = max_xfer;
+	if (priv->max_xfer_len > max_msg - SJA1105_SIZE_SPI_MSG_HEADER)
+		priv->max_xfer_len = max_msg - SJA1105_SIZE_SPI_MSG_HEADER;
+
 	priv->info = of_device_get_match_data(dev);
 
 	/* Detect hardware device */
@@ -3633,7 +3736,7 @@ static int sja1105_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	ds->dev = dev;
-	ds->num_ports = SJA1105_NUM_PORTS;
+	ds->num_ports = priv->info->num_ports;
 	ds->ops = &sja1105_switch_ops;
 	ds->priv = priv;
 	priv->ds = ds;
@@ -3674,7 +3777,7 @@ static int sja1105_probe(struct spi_device *spi)
 	}
 
 	/* Connections between dsa_port and sja1105_port */
-	for (port = 0; port < SJA1105_NUM_PORTS; port++) {
+	for (port = 0; port < ds->num_ports; port++) {
 		struct sja1105_port *sp = &priv->ports[port];
 		struct dsa_port *dp = dsa_to_port(ds, port);
 		struct net_device *slave;
@@ -3737,6 +3840,10 @@ static const struct of_device_id sja1105_dt_ids[] = {
 	{ .compatible = "nxp,sja1105q", .data = &sja1105q_info },
 	{ .compatible = "nxp,sja1105r", .data = &sja1105r_info },
 	{ .compatible = "nxp,sja1105s", .data = &sja1105s_info },
+	{ .compatible = "nxp,sja1110a", .data = &sja1110a_info },
+	{ .compatible = "nxp,sja1110b", .data = &sja1110b_info },
+	{ .compatible = "nxp,sja1110c", .data = &sja1110c_info },
+	{ .compatible = "nxp,sja1110d", .data = &sja1110d_info },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, sja1105_dt_ids);
diff --git a/drivers/net/dsa/sja1105/sja1105_mdio.c b/drivers/net/dsa/sja1105/sja1105_mdio.c
new file mode 100644
index 000000000000..19aea8fb76f6
--- /dev/null
+++ b/drivers/net/dsa/sja1105/sja1105_mdio.c
@@ -0,0 +1,543 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright 2021, NXP Semiconductors
+ */
+#include <linux/pcs/pcs-xpcs.h>
+#include <linux/of_mdio.h>
+#include "sja1105.h"
+
+#define SJA1110_PCS_BANK_REG		SJA1110_SPI_ADDR(0x3fc)
+
+int sja1105_pcs_mdio_read(struct mii_bus *bus, int phy, int reg)
+{
+	struct sja1105_mdio_private *mdio_priv = bus->priv;
+	struct sja1105_private *priv = mdio_priv->priv;
+	u64 addr;
+	u32 tmp;
+	u16 mmd;
+	int rc;
+
+	if (!(reg & MII_ADDR_C45))
+		return -EINVAL;
+
+	mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f;
+	addr = (mmd << 16) | (reg & GENMASK(15, 0));
+
+	if (mmd != MDIO_MMD_VEND1 && mmd != MDIO_MMD_VEND2)
+		return 0xffff;
+
+	if (mmd == MDIO_MMD_VEND2 && (reg & GENMASK(15, 0)) == MII_PHYSID1)
+		return NXP_SJA1105_XPCS_ID >> 16;
+	if (mmd == MDIO_MMD_VEND2 && (reg & GENMASK(15, 0)) == MII_PHYSID2)
+		return NXP_SJA1105_XPCS_ID & GENMASK(15, 0);
+
+	rc = sja1105_xfer_u32(priv, SPI_READ, addr, &tmp, NULL);
+	if (rc < 0)
+		return rc;
+
+	return tmp & 0xffff;
+}
+
+int sja1105_pcs_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val)
+{
+	struct sja1105_mdio_private *mdio_priv = bus->priv;
+	struct sja1105_private *priv = mdio_priv->priv;
+	u64 addr;
+	u32 tmp;
+	u16 mmd;
+
+	if (!(reg & MII_ADDR_C45))
+		return -EINVAL;
+
+	mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f;
+	addr = (mmd << 16) | (reg & GENMASK(15, 0));
+	tmp = val;
+
+	if (mmd != MDIO_MMD_VEND1 && mmd != MDIO_MMD_VEND2)
+		return -EINVAL;
+
+	return sja1105_xfer_u32(priv, SPI_WRITE, addr, &tmp, NULL);
+}
+
+int sja1110_pcs_mdio_read(struct mii_bus *bus, int phy, int reg)
+{
+	struct sja1105_mdio_private *mdio_priv = bus->priv;
+	struct sja1105_private *priv = mdio_priv->priv;
+	const struct sja1105_regs *regs = priv->info->regs;
+	int offset, bank;
+	u64 addr;
+	u32 tmp;
+	u16 mmd;
+	int rc;
+
+	if (!(reg & MII_ADDR_C45))
+		return -EINVAL;
+
+	if (regs->pcs_base[phy] == SJA1105_RSV_ADDR)
+		return -ENODEV;
+
+	mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f;
+	addr = (mmd << 16) | (reg & GENMASK(15, 0));
+
+	if (mmd == MDIO_MMD_VEND2 && (reg & GENMASK(15, 0)) == MII_PHYSID1)
+		return NXP_SJA1110_XPCS_ID >> 16;
+	if (mmd == MDIO_MMD_VEND2 && (reg & GENMASK(15, 0)) == MII_PHYSID2)
+		return NXP_SJA1110_XPCS_ID & GENMASK(15, 0);
+
+	bank = addr >> 8;
+	offset = addr & GENMASK(7, 0);
+
+	/* This addressing scheme reserves register 0xff for the bank address
+	 * register, so that can never be addressed.
+	 */
+	if (WARN_ON(offset == 0xff))
+		return -ENODEV;
+
+	tmp = bank;
+
+	rc = sja1105_xfer_u32(priv, SPI_WRITE,
+			      regs->pcs_base[phy] + SJA1110_PCS_BANK_REG,
+			      &tmp, NULL);
+	if (rc < 0)
+		return rc;
+
+	rc = sja1105_xfer_u32(priv, SPI_READ, regs->pcs_base[phy] + offset,
+			      &tmp, NULL);
+	if (rc < 0)
+		return rc;
+
+	return tmp & 0xffff;
+}
+
+int sja1110_pcs_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val)
+{
+	struct sja1105_mdio_private *mdio_priv = bus->priv;
+	struct sja1105_private *priv = mdio_priv->priv;
+	const struct sja1105_regs *regs = priv->info->regs;
+	int offset, bank;
+	u64 addr;
+	u32 tmp;
+	u16 mmd;
+	int rc;
+
+	if (!(reg & MII_ADDR_C45))
+		return -EINVAL;
+
+	if (regs->pcs_base[phy] == SJA1105_RSV_ADDR)
+		return -ENODEV;
+
+	mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f;
+	addr = (mmd << 16) | (reg & GENMASK(15, 0));
+
+	bank = addr >> 8;
+	offset = addr & GENMASK(7, 0);
+
+	/* This addressing scheme reserves register 0xff for the bank address
+	 * register, so that can never be addressed.
+	 */
+	if (WARN_ON(offset == 0xff))
+		return -ENODEV;
+
+	tmp = bank;
+
+	rc = sja1105_xfer_u32(priv, SPI_WRITE,
+			      regs->pcs_base[phy] + SJA1110_PCS_BANK_REG,
+			      &tmp, NULL);
+	if (rc < 0)
+		return rc;
+
+	tmp = val;
+
+	return sja1105_xfer_u32(priv, SPI_WRITE, regs->pcs_base[phy] + offset,
+				&tmp, NULL);
+}
+
+enum sja1105_mdio_opcode {
+	SJA1105_C45_ADDR = 0,
+	SJA1105_C22 = 1,
+	SJA1105_C45_DATA = 2,
+	SJA1105_C45_DATA_AUTOINC = 3,
+};
+
+static u64 sja1105_base_t1_encode_addr(struct sja1105_private *priv,
+				       int phy, enum sja1105_mdio_opcode op,
+				       int xad)
+{
+	const struct sja1105_regs *regs = priv->info->regs;
+
+	return regs->mdio_100base_t1 | (phy << 7) | (op << 5) | (xad << 0);
+}
+
+static int sja1105_base_t1_mdio_read(struct mii_bus *bus, int phy, int reg)
+{
+	struct sja1105_mdio_private *mdio_priv = bus->priv;
+	struct sja1105_private *priv = mdio_priv->priv;
+	u64 addr;
+	u32 tmp;
+	int rc;
+
+	if (reg & MII_ADDR_C45) {
+		u16 mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f;
+
+		addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C45_ADDR,
+						   mmd);
+
+		tmp = reg & MII_REGADDR_C45_MASK;
+
+		rc = sja1105_xfer_u32(priv, SPI_WRITE, addr, &tmp, NULL);
+		if (rc < 0)
+			return rc;
+
+		addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C45_DATA,
+						   mmd);
+
+		rc = sja1105_xfer_u32(priv, SPI_READ, addr, &tmp, NULL);
+		if (rc < 0)
+			return rc;
+
+		return tmp & 0xffff;
+	}
+
+	/* Clause 22 read */
+	addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C22, reg & 0x1f);
+
+	rc = sja1105_xfer_u32(priv, SPI_READ, addr, &tmp, NULL);
+	if (rc < 0)
+		return rc;
+
+	return tmp & 0xffff;
+}
+
+static int sja1105_base_t1_mdio_write(struct mii_bus *bus, int phy, int reg,
+				      u16 val)
+{
+	struct sja1105_mdio_private *mdio_priv = bus->priv;
+	struct sja1105_private *priv = mdio_priv->priv;
+	u64 addr;
+	u32 tmp;
+	int rc;
+
+	if (reg & MII_ADDR_C45) {
+		u16 mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f;
+
+		addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C45_ADDR,
+						   mmd);
+
+		tmp = reg & MII_REGADDR_C45_MASK;
+
+		rc = sja1105_xfer_u32(priv, SPI_WRITE, addr, &tmp, NULL);
+		if (rc < 0)
+			return rc;
+
+		addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C45_DATA,
+						   mmd);
+
+		tmp = val & 0xffff;
+
+		rc = sja1105_xfer_u32(priv, SPI_WRITE, addr, &tmp, NULL);
+		if (rc < 0)
+			return rc;
+
+		return 0;
+	}
+
+	/* Clause 22 write */
+	addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C22, reg & 0x1f);
+
+	tmp = val & 0xffff;
+
+	return sja1105_xfer_u32(priv, SPI_WRITE, addr, &tmp, NULL);
+}
+
+static int sja1105_base_tx_mdio_read(struct mii_bus *bus, int phy, int reg)
+{
+	struct sja1105_mdio_private *mdio_priv = bus->priv;
+	struct sja1105_private *priv = mdio_priv->priv;
+	const struct sja1105_regs *regs = priv->info->regs;
+	u32 tmp;
+	int rc;
+
+	rc = sja1105_xfer_u32(priv, SPI_READ, regs->mdio_100base_tx + reg,
+			      &tmp, NULL);
+	if (rc < 0)
+		return rc;
+
+	return tmp & 0xffff;
+}
+
+static int sja1105_base_tx_mdio_write(struct mii_bus *bus, int phy, int reg,
+				      u16 val)
+{
+	struct sja1105_mdio_private *mdio_priv = bus->priv;
+	struct sja1105_private *priv = mdio_priv->priv;
+	const struct sja1105_regs *regs = priv->info->regs;
+	u32 tmp = val;
+
+	return sja1105_xfer_u32(priv, SPI_WRITE, regs->mdio_100base_tx + reg,
+				&tmp, NULL);
+}
+
+static int sja1105_mdiobus_base_tx_register(struct sja1105_private *priv,
+					    struct device_node *mdio_node)
+{
+	struct sja1105_mdio_private *mdio_priv;
+	struct device_node *np;
+	struct mii_bus *bus;
+	int rc = 0;
+
+	np = of_find_compatible_node(mdio_node, NULL,
+				     "nxp,sja1110-base-tx-mdio");
+	if (!np)
+		return 0;
+
+	if (!of_device_is_available(np))
+		goto out_put_np;
+
+	bus = mdiobus_alloc_size(sizeof(*mdio_priv));
+	if (!bus) {
+		rc = -ENOMEM;
+		goto out_put_np;
+	}
+
+	bus->name = "SJA1110 100base-TX MDIO bus";
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-base-tx",
+		 dev_name(priv->ds->dev));
+	bus->read = sja1105_base_tx_mdio_read;
+	bus->write = sja1105_base_tx_mdio_write;
+	bus->parent = priv->ds->dev;
+	mdio_priv = bus->priv;
+	mdio_priv->priv = priv;
+
+	rc = of_mdiobus_register(bus, np);
+	if (rc) {
+		mdiobus_free(bus);
+		goto out_put_np;
+	}
+
+	priv->mdio_base_tx = bus;
+
+out_put_np:
+	of_node_put(np);
+
+	return rc;
+}
+
+static void sja1105_mdiobus_base_tx_unregister(struct sja1105_private *priv)
+{
+	if (!priv->mdio_base_tx)
+		return;
+
+	mdiobus_unregister(priv->mdio_base_tx);
+	mdiobus_free(priv->mdio_base_tx);
+	priv->mdio_base_tx = NULL;
+}
+
+static int sja1105_mdiobus_base_t1_register(struct sja1105_private *priv,
+					    struct device_node *mdio_node)
+{
+	struct sja1105_mdio_private *mdio_priv;
+	struct device_node *np;
+	struct mii_bus *bus;
+	int rc = 0;
+
+	np = of_find_compatible_node(mdio_node, NULL,
+				     "nxp,sja1110-base-t1-mdio");
+	if (!np)
+		return 0;
+
+	if (!of_device_is_available(np))
+		goto out_put_np;
+
+	bus = mdiobus_alloc_size(sizeof(*mdio_priv));
+	if (!bus) {
+		rc = -ENOMEM;
+		goto out_put_np;
+	}
+
+	bus->name = "SJA1110 100base-T1 MDIO bus";
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-base-t1",
+		 dev_name(priv->ds->dev));
+	bus->read = sja1105_base_t1_mdio_read;
+	bus->write = sja1105_base_t1_mdio_write;
+	bus->parent = priv->ds->dev;
+	mdio_priv = bus->priv;
+	mdio_priv->priv = priv;
+
+	rc = of_mdiobus_register(bus, np);
+	if (rc) {
+		mdiobus_free(bus);
+		goto out_put_np;
+	}
+
+	priv->mdio_base_t1 = bus;
+
+out_put_np:
+	of_node_put(np);
+
+	return rc;
+}
+
+static void sja1105_mdiobus_base_t1_unregister(struct sja1105_private *priv)
+{
+	if (!priv->mdio_base_t1)
+		return;
+
+	mdiobus_unregister(priv->mdio_base_t1);
+	mdiobus_free(priv->mdio_base_t1);
+	priv->mdio_base_t1 = NULL;
+}
+
+static int sja1105_mdiobus_pcs_register(struct sja1105_private *priv)
+{
+	struct sja1105_mdio_private *mdio_priv;
+	struct dsa_switch *ds = priv->ds;
+	struct mii_bus *bus;
+	int rc = 0;
+	int port;
+
+	if (!priv->info->pcs_mdio_read || !priv->info->pcs_mdio_write)
+		return 0;
+
+	bus = mdiobus_alloc_size(sizeof(*mdio_priv));
+	if (!bus)
+		return -ENOMEM;
+
+	bus->name = "SJA1105 PCS MDIO bus";
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-pcs",
+		 dev_name(ds->dev));
+	bus->read = priv->info->pcs_mdio_read;
+	bus->write = priv->info->pcs_mdio_write;
+	bus->parent = ds->dev;
+	/* There is no PHY on this MDIO bus => mask out all PHY addresses
+	 * from auto probing.
+	 */
+	bus->phy_mask = ~0;
+	mdio_priv = bus->priv;
+	mdio_priv->priv = priv;
+
+	rc = mdiobus_register(bus);
+	if (rc) {
+		mdiobus_free(bus);
+		return rc;
+	}
+
+	for (port = 0; port < ds->num_ports; port++) {
+		struct mdio_device *mdiodev;
+		struct dw_xpcs *xpcs;
+
+		if (dsa_is_unused_port(ds, port))
+			continue;
+
+		if (priv->phy_mode[port] != PHY_INTERFACE_MODE_SGMII &&
+		    priv->phy_mode[port] != PHY_INTERFACE_MODE_2500BASEX)
+			continue;
+
+		mdiodev = mdio_device_create(bus, port);
+		if (IS_ERR(mdiodev)) {
+			rc = PTR_ERR(mdiodev);
+			goto out_pcs_free;
+		}
+
+		xpcs = xpcs_create(mdiodev, priv->phy_mode[port]);
+		if (IS_ERR(xpcs)) {
+			rc = PTR_ERR(xpcs);
+			goto out_pcs_free;
+		}
+
+		priv->xpcs[port] = xpcs;
+	}
+
+	priv->mdio_pcs = bus;
+
+	return 0;
+
+out_pcs_free:
+	for (port = 0; port < ds->num_ports; port++) {
+		if (!priv->xpcs[port])
+			continue;
+
+		mdio_device_free(priv->xpcs[port]->mdiodev);
+		xpcs_destroy(priv->xpcs[port]);
+		priv->xpcs[port] = NULL;
+	}
+
+	mdiobus_unregister(bus);
+	mdiobus_free(bus);
+
+	return rc;
+}
+
+static void sja1105_mdiobus_pcs_unregister(struct sja1105_private *priv)
+{
+	struct dsa_switch *ds = priv->ds;
+	int port;
+
+	if (!priv->mdio_pcs)
+		return;
+
+	for (port = 0; port < ds->num_ports; port++) {
+		if (!priv->xpcs[port])
+			continue;
+
+		mdio_device_free(priv->xpcs[port]->mdiodev);
+		xpcs_destroy(priv->xpcs[port]);
+		priv->xpcs[port] = NULL;
+	}
+
+	mdiobus_unregister(priv->mdio_pcs);
+	mdiobus_free(priv->mdio_pcs);
+	priv->mdio_pcs = NULL;
+}
+
+int sja1105_mdiobus_register(struct dsa_switch *ds)
+{
+	struct sja1105_private *priv = ds->priv;
+	const struct sja1105_regs *regs = priv->info->regs;
+	struct device_node *switch_node = ds->dev->of_node;
+	struct device_node *mdio_node;
+	int rc;
+
+	rc = sja1105_mdiobus_pcs_register(priv);
+	if (rc)
+		return rc;
+
+	mdio_node = of_get_child_by_name(switch_node, "mdios");
+	if (!mdio_node)
+		return 0;
+
+	if (!of_device_is_available(mdio_node))
+		goto out_put_mdio_node;
+
+	if (regs->mdio_100base_tx != SJA1105_RSV_ADDR) {
+		rc = sja1105_mdiobus_base_tx_register(priv, mdio_node);
+		if (rc)
+			goto err_put_mdio_node;
+	}
+
+	if (regs->mdio_100base_t1 != SJA1105_RSV_ADDR) {
+		rc = sja1105_mdiobus_base_t1_register(priv, mdio_node);
+		if (rc)
+			goto err_free_base_tx_mdiobus;
+	}
+
+out_put_mdio_node:
+	of_node_put(mdio_node);
+
+	return 0;
+
+err_free_base_tx_mdiobus:
+	sja1105_mdiobus_base_tx_unregister(priv);
+err_put_mdio_node:
+	of_node_put(mdio_node);
+	sja1105_mdiobus_pcs_unregister(priv);
+
+	return rc;
+}
+
+void sja1105_mdiobus_unregister(struct dsa_switch *ds)
+{
+	struct sja1105_private *priv = ds->priv;
+
+	sja1105_mdiobus_base_t1_unregister(priv);
+	sja1105_mdiobus_base_tx_unregister(priv);
+	sja1105_mdiobus_pcs_unregister(priv);
+}
diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c
index 0bc566b9e958..691f6dd7e669 100644
--- a/drivers/net/dsa/sja1105/sja1105_ptp.c
+++ b/drivers/net/dsa/sja1105/sja1105_ptp.c
@@ -79,6 +79,7 @@ static int sja1105_change_rxtstamping(struct sja1105_private *priv,
 		priv->tagger_data.stampable_skb = NULL;
 	}
 	ptp_cancel_worker_sync(ptp_data->clock);
+	skb_queue_purge(&ptp_data->skb_txtstamp_queue);
 	skb_queue_purge(&ptp_data->skb_rxtstamp_queue);
 
 	return sja1105_static_config_reload(priv, SJA1105_RX_HWTSTAMPING);
@@ -397,7 +398,7 @@ static long sja1105_rxtstamp_work(struct ptp_clock_info *ptp)
 
 		*shwt = (struct skb_shared_hwtstamps) {0};
 
-		ts = SJA1105_SKB_CB(skb)->meta_tstamp;
+		ts = SJA1105_SKB_CB(skb)->tstamp;
 		ts = sja1105_tstamp_reconstruct(ds, ticks, ts);
 
 		shwt->hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(ts));
@@ -413,9 +414,7 @@ static long sja1105_rxtstamp_work(struct ptp_clock_info *ptp)
 	return -1;
 }
 
-/* Called from dsa_skb_defer_rx_timestamp */
-bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port,
-			   struct sk_buff *skb, unsigned int type)
+bool sja1105_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb)
 {
 	struct sja1105_private *priv = ds->priv;
 	struct sja1105_ptp_data *ptp_data = &priv->ptp_data;
@@ -431,6 +430,89 @@ bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port,
 	return true;
 }
 
+bool sja1110_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb)
+{
+	struct skb_shared_hwtstamps *shwt = skb_hwtstamps(skb);
+	u64 ts = SJA1105_SKB_CB(skb)->tstamp;
+
+	*shwt = (struct skb_shared_hwtstamps) {0};
+
+	shwt->hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(ts));
+
+	/* Don't defer */
+	return false;
+}
+
+/* Called from dsa_skb_defer_rx_timestamp */
+bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port,
+			   struct sk_buff *skb, unsigned int type)
+{
+	struct sja1105_private *priv = ds->priv;
+
+	return priv->info->rxtstamp(ds, port, skb);
+}
+
+void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id,
+				 enum sja1110_meta_tstamp dir, u64 tstamp)
+{
+	struct sja1105_private *priv = ds->priv;
+	struct sja1105_ptp_data *ptp_data = &priv->ptp_data;
+	struct sk_buff *skb, *skb_tmp, *skb_match = NULL;
+	struct skb_shared_hwtstamps shwt = {0};
+
+	/* We don't care about RX timestamps on the CPU port */
+	if (dir == SJA1110_META_TSTAMP_RX)
+		return;
+
+	spin_lock(&ptp_data->skb_txtstamp_queue.lock);
+
+	skb_queue_walk_safe(&ptp_data->skb_txtstamp_queue, skb, skb_tmp) {
+		if (SJA1105_SKB_CB(skb)->ts_id != ts_id)
+			continue;
+
+		__skb_unlink(skb, &ptp_data->skb_txtstamp_queue);
+		skb_match = skb;
+
+		break;
+	}
+
+	spin_unlock(&ptp_data->skb_txtstamp_queue.lock);
+
+	if (WARN_ON(!skb_match))
+		return;
+
+	shwt.hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(tstamp));
+	skb_complete_tx_timestamp(skb_match, &shwt);
+}
+EXPORT_SYMBOL_GPL(sja1110_process_meta_tstamp);
+
+/* In addition to cloning the skb which is done by the common
+ * sja1105_port_txtstamp, we need to generate a timestamp ID and save the
+ * packet to the TX timestamping queue.
+ */
+void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb)
+{
+	struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone;
+	struct sja1105_private *priv = ds->priv;
+	struct sja1105_ptp_data *ptp_data = &priv->ptp_data;
+	struct sja1105_port *sp = &priv->ports[port];
+	u8 ts_id;
+
+	skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+
+	spin_lock(&sp->data->meta_lock);
+
+	ts_id = sp->data->ts_id;
+	/* Deal automatically with 8-bit wraparound */
+	sp->data->ts_id++;
+
+	SJA1105_SKB_CB(clone)->ts_id = ts_id;
+
+	spin_unlock(&sp->data->meta_lock);
+
+	skb_queue_tail(&ptp_data->skb_txtstamp_queue, clone);
+}
+
 /* Called from dsa_skb_tx_timestamp. This callback is just to clone
  * the skb and have it available in SJA1105_SKB_CB in the .port_deferred_xmit
  * callback, where we will timestamp it synchronously.
@@ -449,6 +531,9 @@ void sja1105_port_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb)
 		return;
 
 	SJA1105_SKB_CB(skb)->clone = clone;
+
+	if (priv->info->txtstamp)
+		priv->info->txtstamp(ds, port, skb);
 }
 
 static int sja1105_ptp_reset(struct dsa_switch *ds)
@@ -865,7 +950,10 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds)
 		.n_per_out	= 1,
 	};
 
+	/* Only used on SJA1105 */
 	skb_queue_head_init(&ptp_data->skb_rxtstamp_queue);
+	/* Only used on SJA1110 */
+	skb_queue_head_init(&ptp_data->skb_txtstamp_queue);
 	spin_lock_init(&tagger_data->meta_lock);
 
 	ptp_data->clock = ptp_clock_register(&ptp_data->caps, ds->dev);
@@ -890,6 +978,7 @@ void sja1105_ptp_clock_unregister(struct dsa_switch *ds)
 
 	del_timer_sync(&ptp_data->extts_timer);
 	ptp_cancel_worker_sync(ptp_data->clock);
+	skb_queue_purge(&ptp_data->skb_txtstamp_queue);
 	skb_queue_purge(&ptp_data->skb_rxtstamp_queue);
 	ptp_clock_unregister(ptp_data->clock);
 	ptp_data->clock = NULL;
diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.h b/drivers/net/dsa/sja1105/sja1105_ptp.h
index 34f97f58a355..3c874bb4c17b 100644
--- a/drivers/net/dsa/sja1105/sja1105_ptp.h
+++ b/drivers/net/dsa/sja1105/sja1105_ptp.h
@@ -75,7 +75,12 @@ struct sja1105_ptp_cmd {
 
 struct sja1105_ptp_data {
 	struct timer_list extts_timer;
+	/* Used only on SJA1105 to reconstruct partial timestamps */
 	struct sk_buff_head skb_rxtstamp_queue;
+	/* Used on SJA1110 where meta frames are generated only for
+	 * 2-step TX timestamps
+	 */
+	struct sk_buff_head skb_txtstamp_queue;
 	struct ptp_clock_info caps;
 	struct ptp_clock *clock;
 	struct sja1105_ptp_cmd cmd;
@@ -122,6 +127,10 @@ int __sja1105_ptp_adjtime(struct dsa_switch *ds, s64 delta);
 int sja1105_ptp_commit(struct dsa_switch *ds, struct sja1105_ptp_cmd *cmd,
 		       sja1105_spi_rw_mode_t rw);
 
+bool sja1105_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb);
+bool sja1110_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb);
+void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb);
+
 #else
 
 struct sja1105_ptp_cmd;
@@ -184,6 +193,10 @@ static inline int sja1105_ptp_commit(struct dsa_switch *ds,
 
 #define sja1105_hwtstamp_set NULL
 
+#define sja1105_rxtstamp NULL
+#define sja1110_rxtstamp NULL
+#define sja1110_txtstamp NULL
+
 #endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */
 
 #endif /* _SJA1105_PTP_H */
diff --git a/drivers/net/dsa/sja1105/sja1105_sgmii.h b/drivers/net/dsa/sja1105/sja1105_sgmii.h
deleted file mode 100644
index 24d9bc046e70..000000000000
--- a/drivers/net/dsa/sja1105/sja1105_sgmii.h
+++ /dev/null
@@ -1,53 +0,0 @@
-/* SPDX-License-Identifier: BSD-3-Clause */
-/* Copyright 2020, NXP Semiconductors
- */
-#ifndef _SJA1105_SGMII_H
-#define _SJA1105_SGMII_H
-
-#define SJA1105_SGMII_PORT		4
-
-/* DIGITAL_CONTROL_1 (address 1f8000h) */
-#define SJA1105_DC1			0x8000
-#define SJA1105_DC1_VS_RESET		BIT(15)
-#define SJA1105_DC1_REMOTE_LOOPBACK	BIT(14)
-#define SJA1105_DC1_EN_VSMMD1		BIT(13)
-#define SJA1105_DC1_POWER_SAVE		BIT(11)
-#define SJA1105_DC1_CLOCK_STOP_EN	BIT(10)
-#define SJA1105_DC1_MAC_AUTO_SW		BIT(9)
-#define SJA1105_DC1_INIT		BIT(8)
-#define SJA1105_DC1_TX_DISABLE		BIT(4)
-#define SJA1105_DC1_AUTONEG_TIMER_OVRR	BIT(3)
-#define SJA1105_DC1_BYP_POWERUP		BIT(1)
-#define SJA1105_DC1_PHY_MODE_CONTROL	BIT(0)
-
-/* DIGITAL_CONTROL_2 register (address 1f80E1h) */
-#define SJA1105_DC2			0x80e1
-#define SJA1105_DC2_TX_POL_INV_DISABLE	BIT(4)
-#define SJA1105_DC2_RX_POL_INV		BIT(0)
-
-/* DIGITAL_ERROR_CNT register (address 1f80E2h) */
-#define SJA1105_DEC			0x80e2
-#define SJA1105_DEC_ICG_EC_ENA		BIT(4)
-#define SJA1105_DEC_CLEAR_ON_READ	BIT(0)
-
-/* AUTONEG_CONTROL register (address 1f8001h) */
-#define SJA1105_AC			0x8001
-#define SJA1105_AC_MII_CONTROL		BIT(8)
-#define SJA1105_AC_SGMII_LINK		BIT(4)
-#define SJA1105_AC_PHY_MODE		BIT(3)
-#define SJA1105_AC_AUTONEG_MODE(x)	(((x) << 1) & GENMASK(2, 1))
-#define SJA1105_AC_AUTONEG_MODE_SGMII	SJA1105_AC_AUTONEG_MODE(2)
-
-/* AUTONEG_INTR_STATUS register (address 1f8002h) */
-#define SJA1105_AIS			0x8002
-#define SJA1105_AIS_LINK_STATUS(x)	(!!((x) & BIT(4)))
-#define SJA1105_AIS_SPEED(x)		(((x) & GENMASK(3, 2)) >> 2)
-#define SJA1105_AIS_DUPLEX_MODE(x)	(!!((x) & BIT(1)))
-#define SJA1105_AIS_COMPLETE(x)		(!!((x) & BIT(0)))
-
-/* DEBUG_CONTROL register (address 1f8005h) */
-#define SJA1105_DC			0x8005
-#define SJA1105_DC_SUPPRESS_LOS		BIT(4)
-#define SJA1105_DC_RESTART_SYNC		BIT(0)
-
-#endif
diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c
index f7a1514f81e8..08cc5dbf2fa6 100644
--- a/drivers/net/dsa/sja1105/sja1105_spi.c
+++ b/drivers/net/dsa/sja1105/sja1105_spi.c
@@ -7,10 +7,6 @@
 #include <linux/packing.h>
 #include "sja1105.h"
 
-#define SJA1105_SIZE_RESET_CMD		4
-#define SJA1105_SIZE_SPI_MSG_HEADER	4
-#define SJA1105_SIZE_SPI_MSG_MAXLEN	(64 * 4)
-
 struct sja1105_chunk {
 	u8	*buf;
 	size_t	len;
@@ -29,13 +25,6 @@ sja1105_spi_message_pack(void *buf, const struct sja1105_spi_message *msg)
 	sja1105_pack(buf, &msg->address,    24,  4, size);
 }
 
-#define sja1105_hdr_xfer(xfers, chunk) \
-	((xfers) + 2 * (chunk))
-#define sja1105_chunk_xfer(xfers, chunk) \
-	((xfers) + 2 * (chunk) + 1)
-#define sja1105_hdr_buf(hdr_bufs, chunk) \
-	((hdr_bufs) + (chunk) * SJA1105_SIZE_SPI_MSG_HEADER)
-
 /* If @rw is:
  * - SPI_WRITE: creates and sends an SPI write message at absolute
  *		address reg_addr, taking @len bytes from *buf
@@ -46,41 +35,25 @@ static int sja1105_xfer(const struct sja1105_private *priv,
 			sja1105_spi_rw_mode_t rw, u64 reg_addr, u8 *buf,
 			size_t len, struct ptp_system_timestamp *ptp_sts)
 {
-	struct sja1105_chunk chunk = {
-		.len = min_t(size_t, len, SJA1105_SIZE_SPI_MSG_MAXLEN),
-		.reg_addr = reg_addr,
-		.buf = buf,
-	};
+	u8 hdr_buf[SJA1105_SIZE_SPI_MSG_HEADER] = {0};
 	struct spi_device *spi = priv->spidev;
-	struct spi_transfer *xfers;
+	struct spi_transfer xfers[2] = {0};
+	struct spi_transfer *chunk_xfer;
+	struct spi_transfer *hdr_xfer;
+	struct sja1105_chunk chunk;
 	int num_chunks;
 	int rc, i = 0;
-	u8 *hdr_bufs;
 
-	num_chunks = DIV_ROUND_UP(len, SJA1105_SIZE_SPI_MSG_MAXLEN);
+	num_chunks = DIV_ROUND_UP(len, priv->max_xfer_len);
 
-	/* One transfer for each message header, one for each message
-	 * payload (chunk).
-	 */
-	xfers = kcalloc(2 * num_chunks, sizeof(struct spi_transfer),
-			GFP_KERNEL);
-	if (!xfers)
-		return -ENOMEM;
+	chunk.reg_addr = reg_addr;
+	chunk.buf = buf;
+	chunk.len = min_t(size_t, len, priv->max_xfer_len);
 
-	/* Packed buffers for the num_chunks SPI message headers,
-	 * stored as a contiguous array
-	 */
-	hdr_bufs = kcalloc(num_chunks, SJA1105_SIZE_SPI_MSG_HEADER,
-			   GFP_KERNEL);
-	if (!hdr_bufs) {
-		kfree(xfers);
-		return -ENOMEM;
-	}
+	hdr_xfer = &xfers[0];
+	chunk_xfer = &xfers[1];
 
 	for (i = 0; i < num_chunks; i++) {
-		struct spi_transfer *chunk_xfer = sja1105_chunk_xfer(xfers, i);
-		struct spi_transfer *hdr_xfer = sja1105_hdr_xfer(xfers, i);
-		u8 *hdr_buf = sja1105_hdr_buf(hdr_bufs, i);
 		struct spi_transfer *ptp_sts_xfer;
 		struct sja1105_spi_message msg;
 
@@ -127,21 +100,16 @@ static int sja1105_xfer(const struct sja1105_private *priv,
 		chunk.buf += chunk.len;
 		chunk.reg_addr += chunk.len / 4;
 		chunk.len = min_t(size_t, (ptrdiff_t)(buf + len - chunk.buf),
-				  SJA1105_SIZE_SPI_MSG_MAXLEN);
+				  priv->max_xfer_len);
 
-		/* De-assert the chip select after each chunk. */
-		if (chunk.len)
-			chunk_xfer->cs_change = 1;
+		rc = spi_sync_transfer(spi, xfers, 2);
+		if (rc < 0) {
+			dev_err(&spi->dev, "SPI transfer failed: %d\n", rc);
+			return rc;
+		}
 	}
 
-	rc = spi_sync_transfer(spi, xfers, 2 * num_chunks);
-	if (rc < 0)
-		dev_err(&spi->dev, "SPI transfer failed: %d\n", rc);
-
-	kfree(hdr_bufs);
-	kfree(xfers);
-
-	return rc;
+	return 0;
 }
 
 int sja1105_xfer_buf(const struct sja1105_private *priv,
@@ -209,28 +177,34 @@ static int sja1105et_reset_cmd(struct dsa_switch *ds)
 {
 	struct sja1105_private *priv = ds->priv;
 	const struct sja1105_regs *regs = priv->info->regs;
-	u8 packed_buf[SJA1105_SIZE_RESET_CMD] = {0};
-	const int size = SJA1105_SIZE_RESET_CMD;
-	u64 cold_rst = 1;
+	u32 cold_reset = BIT(3);
 
-	sja1105_pack(packed_buf, &cold_rst, 3, 3, size);
-
-	return sja1105_xfer_buf(priv, SPI_WRITE, regs->rgu, packed_buf,
-				SJA1105_SIZE_RESET_CMD);
+	/* Cold reset */
+	return sja1105_xfer_u32(priv, SPI_WRITE, regs->rgu, &cold_reset, NULL);
 }
 
 static int sja1105pqrs_reset_cmd(struct dsa_switch *ds)
 {
 	struct sja1105_private *priv = ds->priv;
 	const struct sja1105_regs *regs = priv->info->regs;
-	u8 packed_buf[SJA1105_SIZE_RESET_CMD] = {0};
-	const int size = SJA1105_SIZE_RESET_CMD;
-	u64 cold_rst = 1;
+	u32 cold_reset = BIT(2);
 
-	sja1105_pack(packed_buf, &cold_rst, 2, 2, size);
+	/* Cold reset */
+	return sja1105_xfer_u32(priv, SPI_WRITE, regs->rgu, &cold_reset, NULL);
+}
 
-	return sja1105_xfer_buf(priv, SPI_WRITE, regs->rgu, packed_buf,
-				SJA1105_SIZE_RESET_CMD);
+static int sja1110_reset_cmd(struct dsa_switch *ds)
+{
+	struct sja1105_private *priv = ds->priv;
+	const struct sja1105_regs *regs = priv->info->regs;
+	u32 switch_reset = BIT(20);
+
+	/* Only reset the switch core.
+	 * A full cold reset would re-enable the BASE_MCSS_CLOCK PLL which
+	 * would turn on the microcontroller, potentially letting it execute
+	 * code which could interfere with our configuration.
+	 */
+	return sja1105_xfer_u32(priv, SPI_WRITE, regs->rgu, &switch_reset, NULL);
 }
 
 int sja1105_inhibit_tx(const struct sja1105_private *priv,
@@ -311,7 +285,8 @@ int static_config_buf_prepare_for_upload(struct sja1105_private *priv,
 	char *final_header_ptr;
 	int crc_len;
 
-	valid = sja1105_static_config_check_valid(config);
+	valid = sja1105_static_config_check_valid(config,
+						  priv->info->max_frame_mem);
 	if (valid != SJA1105_CONFIG_OK) {
 		dev_err(&priv->spidev->dev,
 			sja1105_static_config_error_msg[valid]);
@@ -339,10 +314,10 @@ int static_config_buf_prepare_for_upload(struct sja1105_private *priv,
 
 int sja1105_static_config_upload(struct sja1105_private *priv)
 {
-	unsigned long port_bitmap = GENMASK_ULL(SJA1105_NUM_PORTS - 1, 0);
 	struct sja1105_static_config *config = &priv->static_config;
 	const struct sja1105_regs *regs = priv->info->regs;
 	struct device *dev = &priv->spidev->dev;
+	struct dsa_switch *ds = priv->ds;
 	struct sja1105_status status;
 	int rc, retries = RETRIES;
 	u8 *config_buf;
@@ -363,7 +338,7 @@ int sja1105_static_config_upload(struct sja1105_private *priv)
 	 * Tx on all ports and waiting for current packet to drain.
 	 * Otherwise, the PHY will see an unterminated Ethernet packet.
 	 */
-	rc = sja1105_inhibit_tx(priv, port_bitmap, true);
+	rc = sja1105_inhibit_tx(priv, GENMASK_ULL(ds->num_ports - 1, 0), true);
 	if (rc < 0) {
 		dev_err(dev, "Failed to inhibit Tx on ports\n");
 		rc = -ENXIO;
@@ -433,7 +408,7 @@ out:
 	return rc;
 }
 
-static struct sja1105_regs sja1105et_regs = {
+static const struct sja1105_regs sja1105et_regs = {
 	.device_id = 0x0,
 	.prod_id = 0x100BC3,
 	.status = 0x1,
@@ -446,9 +421,9 @@ static struct sja1105_regs sja1105et_regs = {
 	.pad_mii_rx = {0x100801, 0x100803, 0x100805, 0x100807, 0x100809},
 	.rmii_pll1 = 0x10000A,
 	.cgu_idiv = {0x10000B, 0x10000C, 0x10000D, 0x10000E, 0x10000F},
-	.mac = {0x200, 0x202, 0x204, 0x206, 0x208},
-	.mac_hl1 = {0x400, 0x410, 0x420, 0x430, 0x440},
-	.mac_hl2 = {0x600, 0x610, 0x620, 0x630, 0x640},
+	.stats[MAC] = {0x200, 0x202, 0x204, 0x206, 0x208},
+	.stats[HL1] = {0x400, 0x410, 0x420, 0x430, 0x440},
+	.stats[HL2] = {0x600, 0x610, 0x620, 0x630, 0x640},
 	/* UM10944.pdf, Table 78, CGU Register overview */
 	.mii_tx_clk = {0x100013, 0x10001A, 0x100021, 0x100028, 0x10002F},
 	.mii_rx_clk = {0x100014, 0x10001B, 0x100022, 0x100029, 0x100030},
@@ -465,9 +440,11 @@ static struct sja1105_regs sja1105et_regs = {
 	.ptpclkval = 0x18, /* Spans 0x18 to 0x19 */
 	.ptpclkrate = 0x1A,
 	.ptpclkcorp = 0x1D,
+	.mdio_100base_tx = SJA1105_RSV_ADDR,
+	.mdio_100base_t1 = SJA1105_RSV_ADDR,
 };
 
-static struct sja1105_regs sja1105pqrs_regs = {
+static const struct sja1105_regs sja1105pqrs_regs = {
 	.device_id = 0x0,
 	.prod_id = 0x100BC3,
 	.status = 0x1,
@@ -479,13 +456,12 @@ static struct sja1105_regs sja1105pqrs_regs = {
 	.pad_mii_tx = {0x100800, 0x100802, 0x100804, 0x100806, 0x100808},
 	.pad_mii_rx = {0x100801, 0x100803, 0x100805, 0x100807, 0x100809},
 	.pad_mii_id = {0x100810, 0x100811, 0x100812, 0x100813, 0x100814},
-	.sgmii = 0x1F0000,
 	.rmii_pll1 = 0x10000A,
 	.cgu_idiv = {0x10000B, 0x10000C, 0x10000D, 0x10000E, 0x10000F},
-	.mac = {0x200, 0x202, 0x204, 0x206, 0x208},
-	.mac_hl1 = {0x400, 0x410, 0x420, 0x430, 0x440},
-	.mac_hl2 = {0x600, 0x610, 0x620, 0x630, 0x640},
-	.ether_stats = {0x1400, 0x1418, 0x1430, 0x1448, 0x1460},
+	.stats[MAC] = {0x200, 0x202, 0x204, 0x206, 0x208},
+	.stats[HL1] = {0x400, 0x410, 0x420, 0x430, 0x440},
+	.stats[HL2] = {0x600, 0x610, 0x620, 0x630, 0x640},
+	.stats[ETHER] = {0x1400, 0x1418, 0x1430, 0x1448, 0x1460},
 	/* UM11040.pdf, Table 114 */
 	.mii_tx_clk = {0x100013, 0x100019, 0x10001F, 0x100025, 0x10002B},
 	.mii_rx_clk = {0x100014, 0x10001A, 0x100020, 0x100026, 0x10002C},
@@ -494,7 +470,6 @@ static struct sja1105_regs sja1105pqrs_regs = {
 	.rgmii_tx_clk = {0x100016, 0x10001C, 0x100022, 0x100028, 0x10002E},
 	.rmii_ref_clk = {0x100015, 0x10001B, 0x100021, 0x100027, 0x10002D},
 	.rmii_ext_tx_clk = {0x100017, 0x10001D, 0x100023, 0x100029, 0x10002F},
-	.qlevel = {0x604, 0x614, 0x624, 0x634, 0x644},
 	.ptpegr_ts = {0xC0, 0xC4, 0xC8, 0xCC, 0xD0},
 	.ptpschtm = 0x13, /* Spans 0x13 to 0x14 */
 	.ptppinst = 0x15,
@@ -504,6 +479,95 @@ static struct sja1105_regs sja1105pqrs_regs = {
 	.ptpclkrate = 0x1B,
 	.ptpclkcorp = 0x1E,
 	.ptpsyncts = 0x1F,
+	.mdio_100base_tx = SJA1105_RSV_ADDR,
+	.mdio_100base_t1 = SJA1105_RSV_ADDR,
+};
+
+static const struct sja1105_regs sja1110_regs = {
+	.device_id = SJA1110_SPI_ADDR(0x0),
+	.prod_id = SJA1110_ACU_ADDR(0xf00),
+	.status = SJA1110_SPI_ADDR(0x4),
+	.port_control = SJA1110_SPI_ADDR(0x50), /* actually INHIB_TX */
+	.vl_status = 0x10000,
+	.config = 0x020000,
+	.rgu = SJA1110_RGU_ADDR(0x100), /* Reset Control Register 0 */
+	/* Ports 2 and 3 are capable of xMII, but there isn't anything to
+	 * configure in the CGU/ACU for them.
+	 */
+	.pad_mii_tx = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR},
+	.pad_mii_rx = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR},
+	.pad_mii_id = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1110_ACU_ADDR(0x18), SJA1110_ACU_ADDR(0x28),
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR},
+	.rmii_pll1 = SJA1105_RSV_ADDR,
+	.cgu_idiv = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		     SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		     SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		     SJA1105_RSV_ADDR, SJA1105_RSV_ADDR},
+	.stats[MAC] = {0x200, 0x202, 0x204, 0x206, 0x208, 0x20a,
+		       0x20c, 0x20e, 0x210, 0x212, 0x214},
+	.stats[HL1] = {0x400, 0x410, 0x420, 0x430, 0x440, 0x450,
+		       0x460, 0x470, 0x480, 0x490, 0x4a0},
+	.stats[HL2] = {0x600, 0x610, 0x620, 0x630, 0x640, 0x650,
+		       0x660, 0x670, 0x680, 0x690, 0x6a0},
+	.stats[ETHER] = {0x1400, 0x1418, 0x1430, 0x1448, 0x1460, 0x1478,
+			 0x1490, 0x14a8, 0x14c0, 0x14d8, 0x14f0},
+	.mii_tx_clk = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR},
+	.mii_rx_clk = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		       SJA1105_RSV_ADDR, SJA1105_RSV_ADDR},
+	.mii_ext_tx_clk = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			   SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			   SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			   SJA1105_RSV_ADDR, SJA1105_RSV_ADDR},
+	.mii_ext_rx_clk = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			   SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			   SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			   SJA1105_RSV_ADDR, SJA1105_RSV_ADDR},
+	.rgmii_tx_clk = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			 SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			 SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			 SJA1105_RSV_ADDR, SJA1105_RSV_ADDR},
+	.rmii_ref_clk = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			 SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			 SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			 SJA1105_RSV_ADDR, SJA1105_RSV_ADDR},
+	.rmii_ext_tx_clk = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			    SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			    SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			    SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			    SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+			    SJA1105_RSV_ADDR},
+	.ptpschtm = SJA1110_SPI_ADDR(0x54),
+	.ptppinst = SJA1110_SPI_ADDR(0x5c),
+	.ptppindur = SJA1110_SPI_ADDR(0x64),
+	.ptp_control = SJA1110_SPI_ADDR(0x68),
+	.ptpclkval = SJA1110_SPI_ADDR(0x6c),
+	.ptpclkrate = SJA1110_SPI_ADDR(0x74),
+	.ptpclkcorp = SJA1110_SPI_ADDR(0x80),
+	.ptpsyncts = SJA1110_SPI_ADDR(0x84),
+	.mdio_100base_tx = 0x1c2400,
+	.mdio_100base_t1 = 0x1c1000,
+	.pcs_base = {SJA1105_RSV_ADDR, 0x1c1400, 0x1c1800, 0x1c1c00, 0x1c2000,
+		     SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR,
+		     SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR},
 };
 
 const struct sja1105_info sja1105e_info = {
@@ -512,15 +576,30 @@ const struct sja1105_info sja1105e_info = {
 	.static_ops		= sja1105e_table_ops,
 	.dyn_ops		= sja1105et_dyn_ops,
 	.qinq_tpid		= ETH_P_8021Q,
+	.tag_proto		= DSA_TAG_PROTO_SJA1105,
 	.can_limit_mcast_flood	= false,
 	.ptp_ts_bits		= 24,
 	.ptpegr_ts_bytes	= 4,
+	.max_frame_mem		= SJA1105_MAX_FRAME_MEMORY,
+	.num_ports		= SJA1105_NUM_PORTS,
 	.num_cbs_shapers	= SJA1105ET_MAX_CBS_COUNT,
 	.reset_cmd		= sja1105et_reset_cmd,
 	.fdb_add_cmd		= sja1105et_fdb_add,
 	.fdb_del_cmd		= sja1105et_fdb_del,
 	.ptp_cmd_packing	= sja1105et_ptp_cmd_packing,
+	.rxtstamp		= sja1105_rxtstamp,
+	.clocking_setup		= sja1105_clocking_setup,
 	.regs			= &sja1105et_regs,
+	.port_speed		= {
+		[SJA1105_SPEED_AUTO] = 0,
+		[SJA1105_SPEED_10MBPS] = 3,
+		[SJA1105_SPEED_100MBPS] = 2,
+		[SJA1105_SPEED_1000MBPS] = 1,
+		[SJA1105_SPEED_2500MBPS] = 0, /* Not supported */
+	},
+	.supports_mii		= {true, true, true, true, true},
+	.supports_rmii		= {true, true, true, true, true},
+	.supports_rgmii		= {true, true, true, true, true},
 	.name			= "SJA1105E",
 };
 
@@ -530,15 +609,30 @@ const struct sja1105_info sja1105t_info = {
 	.static_ops		= sja1105t_table_ops,
 	.dyn_ops		= sja1105et_dyn_ops,
 	.qinq_tpid		= ETH_P_8021Q,
+	.tag_proto		= DSA_TAG_PROTO_SJA1105,
 	.can_limit_mcast_flood	= false,
 	.ptp_ts_bits		= 24,
 	.ptpegr_ts_bytes	= 4,
+	.max_frame_mem		= SJA1105_MAX_FRAME_MEMORY,
+	.num_ports		= SJA1105_NUM_PORTS,
 	.num_cbs_shapers	= SJA1105ET_MAX_CBS_COUNT,
 	.reset_cmd		= sja1105et_reset_cmd,
 	.fdb_add_cmd		= sja1105et_fdb_add,
 	.fdb_del_cmd		= sja1105et_fdb_del,
 	.ptp_cmd_packing	= sja1105et_ptp_cmd_packing,
+	.rxtstamp		= sja1105_rxtstamp,
+	.clocking_setup		= sja1105_clocking_setup,
 	.regs			= &sja1105et_regs,
+	.port_speed		= {
+		[SJA1105_SPEED_AUTO] = 0,
+		[SJA1105_SPEED_10MBPS] = 3,
+		[SJA1105_SPEED_100MBPS] = 2,
+		[SJA1105_SPEED_1000MBPS] = 1,
+		[SJA1105_SPEED_2500MBPS] = 0, /* Not supported */
+	},
+	.supports_mii		= {true, true, true, true, true},
+	.supports_rmii		= {true, true, true, true, true},
+	.supports_rgmii		= {true, true, true, true, true},
 	.name			= "SJA1105T",
 };
 
@@ -548,16 +642,31 @@ const struct sja1105_info sja1105p_info = {
 	.static_ops		= sja1105p_table_ops,
 	.dyn_ops		= sja1105pqrs_dyn_ops,
 	.qinq_tpid		= ETH_P_8021AD,
+	.tag_proto		= DSA_TAG_PROTO_SJA1105,
 	.can_limit_mcast_flood	= true,
 	.ptp_ts_bits		= 32,
 	.ptpegr_ts_bytes	= 8,
+	.max_frame_mem		= SJA1105_MAX_FRAME_MEMORY,
+	.num_ports		= SJA1105_NUM_PORTS,
 	.num_cbs_shapers	= SJA1105PQRS_MAX_CBS_COUNT,
 	.setup_rgmii_delay	= sja1105pqrs_setup_rgmii_delay,
 	.reset_cmd		= sja1105pqrs_reset_cmd,
 	.fdb_add_cmd		= sja1105pqrs_fdb_add,
 	.fdb_del_cmd		= sja1105pqrs_fdb_del,
 	.ptp_cmd_packing	= sja1105pqrs_ptp_cmd_packing,
+	.rxtstamp		= sja1105_rxtstamp,
+	.clocking_setup		= sja1105_clocking_setup,
 	.regs			= &sja1105pqrs_regs,
+	.port_speed		= {
+		[SJA1105_SPEED_AUTO] = 0,
+		[SJA1105_SPEED_10MBPS] = 3,
+		[SJA1105_SPEED_100MBPS] = 2,
+		[SJA1105_SPEED_1000MBPS] = 1,
+		[SJA1105_SPEED_2500MBPS] = 0, /* Not supported */
+	},
+	.supports_mii		= {true, true, true, true, true},
+	.supports_rmii		= {true, true, true, true, true},
+	.supports_rgmii		= {true, true, true, true, true},
 	.name			= "SJA1105P",
 };
 
@@ -567,16 +676,31 @@ const struct sja1105_info sja1105q_info = {
 	.static_ops		= sja1105q_table_ops,
 	.dyn_ops		= sja1105pqrs_dyn_ops,
 	.qinq_tpid		= ETH_P_8021AD,
+	.tag_proto		= DSA_TAG_PROTO_SJA1105,
 	.can_limit_mcast_flood	= true,
 	.ptp_ts_bits		= 32,
 	.ptpegr_ts_bytes	= 8,
+	.max_frame_mem		= SJA1105_MAX_FRAME_MEMORY,
+	.num_ports		= SJA1105_NUM_PORTS,
 	.num_cbs_shapers	= SJA1105PQRS_MAX_CBS_COUNT,
 	.setup_rgmii_delay	= sja1105pqrs_setup_rgmii_delay,
 	.reset_cmd		= sja1105pqrs_reset_cmd,
 	.fdb_add_cmd		= sja1105pqrs_fdb_add,
 	.fdb_del_cmd		= sja1105pqrs_fdb_del,
 	.ptp_cmd_packing	= sja1105pqrs_ptp_cmd_packing,
+	.rxtstamp		= sja1105_rxtstamp,
+	.clocking_setup		= sja1105_clocking_setup,
 	.regs			= &sja1105pqrs_regs,
+	.port_speed		= {
+		[SJA1105_SPEED_AUTO] = 0,
+		[SJA1105_SPEED_10MBPS] = 3,
+		[SJA1105_SPEED_100MBPS] = 2,
+		[SJA1105_SPEED_1000MBPS] = 1,
+		[SJA1105_SPEED_2500MBPS] = 0, /* Not supported */
+	},
+	.supports_mii		= {true, true, true, true, true},
+	.supports_rmii		= {true, true, true, true, true},
+	.supports_rgmii		= {true, true, true, true, true},
 	.name			= "SJA1105Q",
 };
 
@@ -586,16 +710,34 @@ const struct sja1105_info sja1105r_info = {
 	.static_ops		= sja1105r_table_ops,
 	.dyn_ops		= sja1105pqrs_dyn_ops,
 	.qinq_tpid		= ETH_P_8021AD,
+	.tag_proto		= DSA_TAG_PROTO_SJA1105,
 	.can_limit_mcast_flood	= true,
 	.ptp_ts_bits		= 32,
 	.ptpegr_ts_bytes	= 8,
+	.max_frame_mem		= SJA1105_MAX_FRAME_MEMORY,
+	.num_ports		= SJA1105_NUM_PORTS,
 	.num_cbs_shapers	= SJA1105PQRS_MAX_CBS_COUNT,
 	.setup_rgmii_delay	= sja1105pqrs_setup_rgmii_delay,
 	.reset_cmd		= sja1105pqrs_reset_cmd,
 	.fdb_add_cmd		= sja1105pqrs_fdb_add,
 	.fdb_del_cmd		= sja1105pqrs_fdb_del,
 	.ptp_cmd_packing	= sja1105pqrs_ptp_cmd_packing,
+	.rxtstamp		= sja1105_rxtstamp,
+	.clocking_setup		= sja1105_clocking_setup,
+	.pcs_mdio_read		= sja1105_pcs_mdio_read,
+	.pcs_mdio_write		= sja1105_pcs_mdio_write,
 	.regs			= &sja1105pqrs_regs,
+	.port_speed		= {
+		[SJA1105_SPEED_AUTO] = 0,
+		[SJA1105_SPEED_10MBPS] = 3,
+		[SJA1105_SPEED_100MBPS] = 2,
+		[SJA1105_SPEED_1000MBPS] = 1,
+		[SJA1105_SPEED_2500MBPS] = 0, /* Not supported */
+	},
+	.supports_mii		= {true, true, true, true, true},
+	.supports_rmii		= {true, true, true, true, true},
+	.supports_rgmii		= {true, true, true, true, true},
+	.supports_sgmii		= {false, false, false, false, true},
 	.name			= "SJA1105R",
 };
 
@@ -606,14 +748,236 @@ const struct sja1105_info sja1105s_info = {
 	.dyn_ops		= sja1105pqrs_dyn_ops,
 	.regs			= &sja1105pqrs_regs,
 	.qinq_tpid		= ETH_P_8021AD,
+	.tag_proto		= DSA_TAG_PROTO_SJA1105,
 	.can_limit_mcast_flood	= true,
 	.ptp_ts_bits		= 32,
 	.ptpegr_ts_bytes	= 8,
+	.max_frame_mem		= SJA1105_MAX_FRAME_MEMORY,
+	.num_ports		= SJA1105_NUM_PORTS,
 	.num_cbs_shapers	= SJA1105PQRS_MAX_CBS_COUNT,
 	.setup_rgmii_delay	= sja1105pqrs_setup_rgmii_delay,
 	.reset_cmd		= sja1105pqrs_reset_cmd,
 	.fdb_add_cmd		= sja1105pqrs_fdb_add,
 	.fdb_del_cmd		= sja1105pqrs_fdb_del,
 	.ptp_cmd_packing	= sja1105pqrs_ptp_cmd_packing,
+	.rxtstamp		= sja1105_rxtstamp,
+	.clocking_setup		= sja1105_clocking_setup,
+	.pcs_mdio_read		= sja1105_pcs_mdio_read,
+	.pcs_mdio_write		= sja1105_pcs_mdio_write,
+	.port_speed		= {
+		[SJA1105_SPEED_AUTO] = 0,
+		[SJA1105_SPEED_10MBPS] = 3,
+		[SJA1105_SPEED_100MBPS] = 2,
+		[SJA1105_SPEED_1000MBPS] = 1,
+		[SJA1105_SPEED_2500MBPS] = 0, /* Not supported */
+	},
+	.supports_mii		= {true, true, true, true, true},
+	.supports_rmii		= {true, true, true, true, true},
+	.supports_rgmii		= {true, true, true, true, true},
+	.supports_sgmii		= {false, false, false, false, true},
 	.name			= "SJA1105S",
 };
+
+const struct sja1105_info sja1110a_info = {
+	.device_id		= SJA1110_DEVICE_ID,
+	.part_no		= SJA1110A_PART_NO,
+	.static_ops		= sja1110_table_ops,
+	.dyn_ops		= sja1110_dyn_ops,
+	.regs			= &sja1110_regs,
+	.qinq_tpid		= ETH_P_8021AD,
+	.tag_proto		= DSA_TAG_PROTO_SJA1110,
+	.can_limit_mcast_flood	= true,
+	.multiple_cascade_ports	= true,
+	.ptp_ts_bits		= 32,
+	.ptpegr_ts_bytes	= 8,
+	.max_frame_mem		= SJA1110_MAX_FRAME_MEMORY,
+	.num_ports		= SJA1110_NUM_PORTS,
+	.num_cbs_shapers	= SJA1110_MAX_CBS_COUNT,
+	.setup_rgmii_delay	= sja1110_setup_rgmii_delay,
+	.reset_cmd		= sja1110_reset_cmd,
+	.fdb_add_cmd		= sja1105pqrs_fdb_add,
+	.fdb_del_cmd		= sja1105pqrs_fdb_del,
+	.ptp_cmd_packing	= sja1105pqrs_ptp_cmd_packing,
+	.rxtstamp		= sja1110_rxtstamp,
+	.txtstamp		= sja1110_txtstamp,
+	.disable_microcontroller = sja1110_disable_microcontroller,
+	.pcs_mdio_read		= sja1110_pcs_mdio_read,
+	.pcs_mdio_write		= sja1110_pcs_mdio_write,
+	.port_speed		= {
+		[SJA1105_SPEED_AUTO] = 0,
+		[SJA1105_SPEED_10MBPS] = 4,
+		[SJA1105_SPEED_100MBPS] = 3,
+		[SJA1105_SPEED_1000MBPS] = 2,
+		[SJA1105_SPEED_2500MBPS] = 1,
+	},
+	.supports_mii		= {true, true, true, true, false,
+				   true, true, true, true, true, true},
+	.supports_rmii		= {false, false, true, true, false,
+				   false, false, false, false, false, false},
+	.supports_rgmii		= {false, false, true, true, false,
+				   false, false, false, false, false, false},
+	.supports_sgmii		= {false, true, true, true, true,
+				   false, false, false, false, false, false},
+	.supports_2500basex	= {false, false, false, true, true,
+				   false, false, false, false, false, false},
+	.internal_phy		= {SJA1105_NO_PHY, SJA1105_PHY_BASE_TX,
+				   SJA1105_NO_PHY, SJA1105_NO_PHY,
+				   SJA1105_NO_PHY, SJA1105_PHY_BASE_T1,
+				   SJA1105_PHY_BASE_T1, SJA1105_PHY_BASE_T1,
+				   SJA1105_PHY_BASE_T1, SJA1105_PHY_BASE_T1,
+				   SJA1105_PHY_BASE_T1},
+	.name			= "SJA1110A",
+};
+
+const struct sja1105_info sja1110b_info = {
+	.device_id		= SJA1110_DEVICE_ID,
+	.part_no		= SJA1110B_PART_NO,
+	.static_ops		= sja1110_table_ops,
+	.dyn_ops		= sja1110_dyn_ops,
+	.regs			= &sja1110_regs,
+	.qinq_tpid		= ETH_P_8021AD,
+	.tag_proto		= DSA_TAG_PROTO_SJA1110,
+	.can_limit_mcast_flood	= true,
+	.multiple_cascade_ports	= true,
+	.ptp_ts_bits		= 32,
+	.ptpegr_ts_bytes	= 8,
+	.max_frame_mem		= SJA1110_MAX_FRAME_MEMORY,
+	.num_ports		= SJA1110_NUM_PORTS,
+	.num_cbs_shapers	= SJA1110_MAX_CBS_COUNT,
+	.setup_rgmii_delay	= sja1110_setup_rgmii_delay,
+	.reset_cmd		= sja1110_reset_cmd,
+	.fdb_add_cmd		= sja1105pqrs_fdb_add,
+	.fdb_del_cmd		= sja1105pqrs_fdb_del,
+	.ptp_cmd_packing	= sja1105pqrs_ptp_cmd_packing,
+	.rxtstamp		= sja1110_rxtstamp,
+	.txtstamp		= sja1110_txtstamp,
+	.disable_microcontroller = sja1110_disable_microcontroller,
+	.pcs_mdio_read		= sja1110_pcs_mdio_read,
+	.pcs_mdio_write		= sja1110_pcs_mdio_write,
+	.port_speed		= {
+		[SJA1105_SPEED_AUTO] = 0,
+		[SJA1105_SPEED_10MBPS] = 4,
+		[SJA1105_SPEED_100MBPS] = 3,
+		[SJA1105_SPEED_1000MBPS] = 2,
+		[SJA1105_SPEED_2500MBPS] = 1,
+	},
+	.supports_mii		= {true, true, true, true, false,
+				   true, true, true, true, true, false},
+	.supports_rmii		= {false, false, true, true, false,
+				   false, false, false, false, false, false},
+	.supports_rgmii		= {false, false, true, true, false,
+				   false, false, false, false, false, false},
+	.supports_sgmii		= {false, false, false, true, true,
+				   false, false, false, false, false, false},
+	.supports_2500basex	= {false, false, false, true, true,
+				   false, false, false, false, false, false},
+	.internal_phy		= {SJA1105_NO_PHY, SJA1105_PHY_BASE_TX,
+				   SJA1105_NO_PHY, SJA1105_NO_PHY,
+				   SJA1105_NO_PHY, SJA1105_PHY_BASE_T1,
+				   SJA1105_PHY_BASE_T1, SJA1105_PHY_BASE_T1,
+				   SJA1105_PHY_BASE_T1, SJA1105_PHY_BASE_T1,
+				   SJA1105_NO_PHY},
+	.name			= "SJA1110B",
+};
+
+const struct sja1105_info sja1110c_info = {
+	.device_id		= SJA1110_DEVICE_ID,
+	.part_no		= SJA1110C_PART_NO,
+	.static_ops		= sja1110_table_ops,
+	.dyn_ops		= sja1110_dyn_ops,
+	.regs			= &sja1110_regs,
+	.qinq_tpid		= ETH_P_8021AD,
+	.tag_proto		= DSA_TAG_PROTO_SJA1110,
+	.can_limit_mcast_flood	= true,
+	.multiple_cascade_ports	= true,
+	.ptp_ts_bits		= 32,
+	.ptpegr_ts_bytes	= 8,
+	.max_frame_mem		= SJA1110_MAX_FRAME_MEMORY,
+	.num_ports		= SJA1110_NUM_PORTS,
+	.num_cbs_shapers	= SJA1110_MAX_CBS_COUNT,
+	.setup_rgmii_delay	= sja1110_setup_rgmii_delay,
+	.reset_cmd		= sja1110_reset_cmd,
+	.fdb_add_cmd		= sja1105pqrs_fdb_add,
+	.fdb_del_cmd		= sja1105pqrs_fdb_del,
+	.ptp_cmd_packing	= sja1105pqrs_ptp_cmd_packing,
+	.rxtstamp		= sja1110_rxtstamp,
+	.txtstamp		= sja1110_txtstamp,
+	.disable_microcontroller = sja1110_disable_microcontroller,
+	.pcs_mdio_read		= sja1110_pcs_mdio_read,
+	.pcs_mdio_write		= sja1110_pcs_mdio_write,
+	.port_speed		= {
+		[SJA1105_SPEED_AUTO] = 0,
+		[SJA1105_SPEED_10MBPS] = 4,
+		[SJA1105_SPEED_100MBPS] = 3,
+		[SJA1105_SPEED_1000MBPS] = 2,
+		[SJA1105_SPEED_2500MBPS] = 1,
+	},
+	.supports_mii		= {true, true, true, true, false,
+				   true, true, true, false, false, false},
+	.supports_rmii		= {false, false, true, true, false,
+				   false, false, false, false, false, false},
+	.supports_rgmii		= {false, false, true, true, false,
+				   false, false, false, false, false, false},
+	.supports_sgmii		= {false, false, false, false, true,
+				   false, false, false, false, false, false},
+	.supports_2500basex	= {false, false, false, false, true,
+				   false, false, false, false, false, false},
+	.internal_phy		= {SJA1105_NO_PHY, SJA1105_PHY_BASE_TX,
+				   SJA1105_NO_PHY, SJA1105_NO_PHY,
+				   SJA1105_NO_PHY, SJA1105_PHY_BASE_T1,
+				   SJA1105_PHY_BASE_T1, SJA1105_PHY_BASE_T1,
+				   SJA1105_NO_PHY, SJA1105_NO_PHY,
+				   SJA1105_NO_PHY},
+	.name			= "SJA1110C",
+};
+
+const struct sja1105_info sja1110d_info = {
+	.device_id		= SJA1110_DEVICE_ID,
+	.part_no		= SJA1110D_PART_NO,
+	.static_ops		= sja1110_table_ops,
+	.dyn_ops		= sja1110_dyn_ops,
+	.regs			= &sja1110_regs,
+	.qinq_tpid		= ETH_P_8021AD,
+	.tag_proto		= DSA_TAG_PROTO_SJA1110,
+	.can_limit_mcast_flood	= true,
+	.multiple_cascade_ports	= true,
+	.ptp_ts_bits		= 32,
+	.ptpegr_ts_bytes	= 8,
+	.max_frame_mem		= SJA1110_MAX_FRAME_MEMORY,
+	.num_ports		= SJA1110_NUM_PORTS,
+	.num_cbs_shapers	= SJA1110_MAX_CBS_COUNT,
+	.setup_rgmii_delay	= sja1110_setup_rgmii_delay,
+	.reset_cmd		= sja1110_reset_cmd,
+	.fdb_add_cmd		= sja1105pqrs_fdb_add,
+	.fdb_del_cmd		= sja1105pqrs_fdb_del,
+	.ptp_cmd_packing	= sja1105pqrs_ptp_cmd_packing,
+	.rxtstamp		= sja1110_rxtstamp,
+	.txtstamp		= sja1110_txtstamp,
+	.disable_microcontroller = sja1110_disable_microcontroller,
+	.pcs_mdio_read		= sja1110_pcs_mdio_read,
+	.pcs_mdio_write		= sja1110_pcs_mdio_write,
+	.port_speed		= {
+		[SJA1105_SPEED_AUTO] = 0,
+		[SJA1105_SPEED_10MBPS] = 4,
+		[SJA1105_SPEED_100MBPS] = 3,
+		[SJA1105_SPEED_1000MBPS] = 2,
+		[SJA1105_SPEED_2500MBPS] = 1,
+	},
+	.supports_mii		= {true, false, true, false, false,
+				   true, true, true, false, false, false},
+	.supports_rmii		= {false, false, true, false, false,
+				   false, false, false, false, false, false},
+	.supports_rgmii		= {false, false, true, false, false,
+				   false, false, false, false, false, false},
+	.supports_sgmii		= {false, true, true, true, true,
+				   false, false, false, false, false, false},
+	.supports_2500basex     = {false, false, false, true, true,
+				   false, false, false, false, false, false},
+	.internal_phy		= {SJA1105_NO_PHY, SJA1105_NO_PHY,
+				   SJA1105_NO_PHY, SJA1105_NO_PHY,
+				   SJA1105_NO_PHY, SJA1105_PHY_BASE_T1,
+				   SJA1105_PHY_BASE_T1, SJA1105_PHY_BASE_T1,
+				   SJA1105_NO_PHY, SJA1105_NO_PHY,
+				   SJA1105_NO_PHY},
+	.name			= "SJA1110D",
+};
diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c
index a8efb7fac395..7a422ef4deb6 100644
--- a/drivers/net/dsa/sja1105/sja1105_static_config.c
+++ b/drivers/net/dsa/sja1105/sja1105_static_config.c
@@ -180,6 +180,43 @@ size_t sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+size_t sja1110_general_params_entry_packing(void *buf, void *entry_ptr,
+					    enum packing_op op)
+{
+	struct sja1105_general_params_entry *entry = entry_ptr;
+	const size_t size = SJA1110_SIZE_GENERAL_PARAMS_ENTRY;
+
+	sja1105_packing(buf, &entry->vllupformat,  447, 447, size, op);
+	sja1105_packing(buf, &entry->mirr_ptacu,   446, 446, size, op);
+	sja1105_packing(buf, &entry->switchid,     445, 442, size, op);
+	sja1105_packing(buf, &entry->hostprio,     441, 439, size, op);
+	sja1105_packing(buf, &entry->mac_fltres1,  438, 391, size, op);
+	sja1105_packing(buf, &entry->mac_fltres0,  390, 343, size, op);
+	sja1105_packing(buf, &entry->mac_flt1,     342, 295, size, op);
+	sja1105_packing(buf, &entry->mac_flt0,     294, 247, size, op);
+	sja1105_packing(buf, &entry->incl_srcpt1,  246, 246, size, op);
+	sja1105_packing(buf, &entry->incl_srcpt0,  245, 245, size, op);
+	sja1105_packing(buf, &entry->send_meta1,   244, 244, size, op);
+	sja1105_packing(buf, &entry->send_meta0,   243, 243, size, op);
+	sja1105_packing(buf, &entry->casc_port,    242, 232, size, op);
+	sja1105_packing(buf, &entry->host_port,    231, 228, size, op);
+	sja1105_packing(buf, &entry->mirr_port,    227, 224, size, op);
+	sja1105_packing(buf, &entry->vlmarker,     223, 192, size, op);
+	sja1105_packing(buf, &entry->vlmask,       191, 160, size, op);
+	sja1105_packing(buf, &entry->tpid2,        159, 144, size, op);
+	sja1105_packing(buf, &entry->ignore2stf,   143, 143, size, op);
+	sja1105_packing(buf, &entry->tpid,         142, 127, size, op);
+	sja1105_packing(buf, &entry->queue_ts,     126, 126, size, op);
+	sja1105_packing(buf, &entry->egrmirrvid,   125, 114, size, op);
+	sja1105_packing(buf, &entry->egrmirrpcp,   113, 111, size, op);
+	sja1105_packing(buf, &entry->egrmirrdei,   110, 110, size, op);
+	sja1105_packing(buf, &entry->replay_port,  109, 106, size, op);
+	sja1105_packing(buf, &entry->tdmaconfigidx, 70,  67, size, op);
+	sja1105_packing(buf, &entry->header_type,   64,  49, size, op);
+	sja1105_packing(buf, &entry->tte_en,        16,  16, size, op);
+	return size;
+}
+
 static size_t
 sja1105_l2_forwarding_params_entry_packing(void *buf, void *entry_ptr,
 					   enum packing_op op)
@@ -195,6 +232,20 @@ sja1105_l2_forwarding_params_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+size_t sja1110_l2_forwarding_params_entry_packing(void *buf, void *entry_ptr,
+						  enum packing_op op)
+{
+	struct sja1105_l2_forwarding_params_entry *entry = entry_ptr;
+	const size_t size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY;
+	int offset, i;
+
+	sja1105_packing(buf, &entry->max_dynp, 95, 93, size, op);
+	for (i = 0, offset = 5; i < 8; i++, offset += 11)
+		sja1105_packing(buf, &entry->part_spc[i],
+				offset + 10, offset + 0, size, op);
+	return size;
+}
+
 size_t sja1105_l2_forwarding_entry_packing(void *buf, void *entry_ptr,
 					   enum packing_op op)
 {
@@ -211,6 +262,27 @@ size_t sja1105_l2_forwarding_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+size_t sja1110_l2_forwarding_entry_packing(void *buf, void *entry_ptr,
+					   enum packing_op op)
+{
+	struct sja1105_l2_forwarding_entry *entry = entry_ptr;
+	const size_t size = SJA1105_SIZE_L2_FORWARDING_ENTRY;
+	int offset, i;
+
+	if (entry->type_egrpcp2outputq) {
+		for (i = 0, offset = 31; i < SJA1110_NUM_PORTS;
+		     i++, offset += 3) {
+			sja1105_packing(buf, &entry->vlan_pmap[i],
+					offset + 2, offset + 0, size, op);
+		}
+	} else {
+		sja1105_packing(buf, &entry->bc_domain,  63, 53, size, op);
+		sja1105_packing(buf, &entry->reach_port, 52, 42, size, op);
+		sja1105_packing(buf, &entry->fl_domain,  41, 31, size, op);
+	}
+	return size;
+}
+
 static size_t
 sja1105et_l2_lookup_params_entry_packing(void *buf, void *entry_ptr,
 					 enum packing_op op)
@@ -249,6 +321,28 @@ size_t sja1105pqrs_l2_lookup_params_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+size_t sja1110_l2_lookup_params_entry_packing(void *buf, void *entry_ptr,
+					      enum packing_op op)
+{
+	struct sja1105_l2_lookup_params_entry *entry = entry_ptr;
+	const size_t size = SJA1110_SIZE_L2_LOOKUP_PARAMS_ENTRY;
+	int offset, i;
+
+	for (i = 0, offset = 70; i < SJA1110_NUM_PORTS; i++, offset += 11)
+		sja1105_packing(buf, &entry->maxaddrp[i],
+				offset + 10, offset + 0, size, op);
+	sja1105_packing(buf, &entry->maxage,         69,  55, size, op);
+	sja1105_packing(buf, &entry->start_dynspc,   54,  45, size, op);
+	sja1105_packing(buf, &entry->drpnolearn,     44,  34, size, op);
+	sja1105_packing(buf, &entry->shared_learn,   33,  33, size, op);
+	sja1105_packing(buf, &entry->no_enf_hostprt, 32,  32, size, op);
+	sja1105_packing(buf, &entry->no_mgmt_learn,  31,  31, size, op);
+	sja1105_packing(buf, &entry->use_static,     30,  30, size, op);
+	sja1105_packing(buf, &entry->owr_dyn,        29,  29, size, op);
+	sja1105_packing(buf, &entry->learn_once,     28,  28, size, op);
+	return size;
+}
+
 size_t sja1105et_l2_lookup_entry_packing(void *buf, void *entry_ptr,
 					 enum packing_op op)
 {
@@ -291,6 +385,36 @@ size_t sja1105pqrs_l2_lookup_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+size_t sja1110_l2_lookup_entry_packing(void *buf, void *entry_ptr,
+				       enum packing_op op)
+{
+	const size_t size = SJA1110_SIZE_L2_LOOKUP_ENTRY;
+	struct sja1105_l2_lookup_entry *entry = entry_ptr;
+
+	if (entry->lockeds) {
+		sja1105_packing(buf, &entry->trap,     168, 168, size, op);
+		sja1105_packing(buf, &entry->mirrvlan, 167, 156, size, op);
+		sja1105_packing(buf, &entry->takets,   155, 155, size, op);
+		sja1105_packing(buf, &entry->mirr,     154, 154, size, op);
+		sja1105_packing(buf, &entry->retag,    153, 153, size, op);
+	} else {
+		sja1105_packing(buf, &entry->touched,  168, 168, size, op);
+		sja1105_packing(buf, &entry->age,      167, 153, size, op);
+	}
+	sja1105_packing(buf, &entry->mask_iotag,   152, 152, size, op);
+	sja1105_packing(buf, &entry->mask_vlanid,  151, 140, size, op);
+	sja1105_packing(buf, &entry->mask_macaddr, 139,  92, size, op);
+	sja1105_packing(buf, &entry->mask_srcport,  91,  88, size, op);
+	sja1105_packing(buf, &entry->iotag,         87,  87, size, op);
+	sja1105_packing(buf, &entry->vlanid,        86,  75, size, op);
+	sja1105_packing(buf, &entry->macaddr,       74,  27, size, op);
+	sja1105_packing(buf, &entry->srcport,       26,  23, size, op);
+	sja1105_packing(buf, &entry->destports,     22,  12, size, op);
+	sja1105_packing(buf, &entry->enfport,       11,  11, size, op);
+	sja1105_packing(buf, &entry->index,         10,   1, size, op);
+	return size;
+}
+
 static size_t sja1105_l2_policing_entry_packing(void *buf, void *entry_ptr,
 						enum packing_op op)
 {
@@ -305,6 +429,20 @@ static size_t sja1105_l2_policing_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+size_t sja1110_l2_policing_entry_packing(void *buf, void *entry_ptr,
+					 enum packing_op op)
+{
+	struct sja1105_l2_policing_entry *entry = entry_ptr;
+	const size_t size = SJA1105_SIZE_L2_POLICING_ENTRY;
+
+	sja1105_packing(buf, &entry->sharindx, 63, 57, size, op);
+	sja1105_packing(buf, &entry->smax,     56, 39, size, op);
+	sja1105_packing(buf, &entry->rate,     38, 21, size, op);
+	sja1105_packing(buf, &entry->maxlen,   20, 10, size, op);
+	sja1105_packing(buf, &entry->partition, 9,  7, size, op);
+	return size;
+}
+
 static size_t sja1105et_mac_config_entry_packing(void *buf, void *entry_ptr,
 						 enum packing_op op)
 {
@@ -373,6 +511,40 @@ size_t sja1105pqrs_mac_config_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+size_t sja1110_mac_config_entry_packing(void *buf, void *entry_ptr,
+					enum packing_op op)
+{
+	const size_t size = SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY;
+	struct sja1105_mac_config_entry *entry = entry_ptr;
+	int offset, i;
+
+	for (i = 0, offset = 104; i < 8; i++, offset += 19) {
+		sja1105_packing(buf, &entry->enabled[i],
+				offset +  0, offset +  0, size, op);
+		sja1105_packing(buf, &entry->base[i],
+				offset +  9, offset +  1, size, op);
+		sja1105_packing(buf, &entry->top[i],
+				offset + 18, offset + 10, size, op);
+	}
+	sja1105_packing(buf, &entry->speed,      98, 96, size, op);
+	sja1105_packing(buf, &entry->tp_delin,   95, 80, size, op);
+	sja1105_packing(buf, &entry->tp_delout,  79, 64, size, op);
+	sja1105_packing(buf, &entry->maxage,     63, 56, size, op);
+	sja1105_packing(buf, &entry->vlanprio,   55, 53, size, op);
+	sja1105_packing(buf, &entry->vlanid,     52, 41, size, op);
+	sja1105_packing(buf, &entry->ing_mirr,   40, 40, size, op);
+	sja1105_packing(buf, &entry->egr_mirr,   39, 39, size, op);
+	sja1105_packing(buf, &entry->drpnona664, 38, 38, size, op);
+	sja1105_packing(buf, &entry->drpdtag,    37, 37, size, op);
+	sja1105_packing(buf, &entry->drpuntag,   34, 34, size, op);
+	sja1105_packing(buf, &entry->retag,      33, 33, size, op);
+	sja1105_packing(buf, &entry->dyn_learn,  32, 32, size, op);
+	sja1105_packing(buf, &entry->egress,     31, 31, size, op);
+	sja1105_packing(buf, &entry->ingress,    30, 30, size, op);
+	sja1105_packing(buf, &entry->ifg,        10,  5, size, op);
+	return size;
+}
+
 static size_t
 sja1105_schedule_entry_points_params_entry_packing(void *buf, void *entry_ptr,
 						   enum packing_op op)
@@ -398,6 +570,19 @@ sja1105_schedule_entry_points_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+static size_t
+sja1110_schedule_entry_points_entry_packing(void *buf, void *entry_ptr,
+					    enum packing_op op)
+{
+	struct sja1105_schedule_entry_points_entry *entry = entry_ptr;
+	const size_t size = SJA1110_SIZE_SCHEDULE_ENTRY_POINTS_ENTRY;
+
+	sja1105_packing(buf, &entry->subschindx, 63, 61, size, op);
+	sja1105_packing(buf, &entry->delta,      60, 43, size, op);
+	sja1105_packing(buf, &entry->address,    42, 31, size, op);
+	return size;
+}
+
 static size_t sja1105_schedule_params_entry_packing(void *buf, void *entry_ptr,
 						    enum packing_op op)
 {
@@ -411,6 +596,19 @@ static size_t sja1105_schedule_params_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+static size_t sja1110_schedule_params_entry_packing(void *buf, void *entry_ptr,
+						    enum packing_op op)
+{
+	struct sja1105_schedule_params_entry *entry = entry_ptr;
+	const size_t size = SJA1105_SIZE_SCHEDULE_PARAMS_ENTRY;
+	int offset, i;
+
+	for (i = 0, offset = 0; i < 8; i++, offset += 12)
+		sja1105_packing(buf, &entry->subscheind[i],
+				offset + 11, offset + 0, size, op);
+	return size;
+}
+
 static size_t sja1105_schedule_entry_packing(void *buf, void *entry_ptr,
 					     enum packing_op op)
 {
@@ -430,6 +628,25 @@ static size_t sja1105_schedule_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+static size_t sja1110_schedule_entry_packing(void *buf, void *entry_ptr,
+					     enum packing_op op)
+{
+	const size_t size = SJA1110_SIZE_SCHEDULE_ENTRY;
+	struct sja1105_schedule_entry *entry = entry_ptr;
+
+	sja1105_packing(buf, &entry->winstindex,  95, 84, size, op);
+	sja1105_packing(buf, &entry->winend,      83, 83, size, op);
+	sja1105_packing(buf, &entry->winst,       82, 82, size, op);
+	sja1105_packing(buf, &entry->destports,   81, 71, size, op);
+	sja1105_packing(buf, &entry->setvalid,    70, 70, size, op);
+	sja1105_packing(buf, &entry->txen,        69, 69, size, op);
+	sja1105_packing(buf, &entry->resmedia_en, 68, 68, size, op);
+	sja1105_packing(buf, &entry->resmedia,    67, 60, size, op);
+	sja1105_packing(buf, &entry->vlindex,     59, 48, size, op);
+	sja1105_packing(buf, &entry->delta,       47, 30, size, op);
+	return size;
+}
+
 static size_t
 sja1105_vl_forwarding_params_entry_packing(void *buf, void *entry_ptr,
 					   enum packing_op op)
@@ -445,6 +662,21 @@ sja1105_vl_forwarding_params_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+static size_t
+sja1110_vl_forwarding_params_entry_packing(void *buf, void *entry_ptr,
+					   enum packing_op op)
+{
+	struct sja1105_vl_forwarding_params_entry *entry = entry_ptr;
+	const size_t size = SJA1105_SIZE_VL_FORWARDING_PARAMS_ENTRY;
+	int offset, i;
+
+	for (i = 0, offset = 8; i < 8; i++, offset += 11)
+		sja1105_packing(buf, &entry->partspc[i],
+				offset + 10, offset + 0, size, op);
+	sja1105_packing(buf, &entry->debugen, 7, 7, size, op);
+	return size;
+}
+
 static size_t sja1105_vl_forwarding_entry_packing(void *buf, void *entry_ptr,
 						  enum packing_op op)
 {
@@ -458,6 +690,19 @@ static size_t sja1105_vl_forwarding_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+static size_t sja1110_vl_forwarding_entry_packing(void *buf, void *entry_ptr,
+						  enum packing_op op)
+{
+	struct sja1105_vl_forwarding_entry *entry = entry_ptr;
+	const size_t size = SJA1105_SIZE_VL_FORWARDING_ENTRY;
+
+	sja1105_packing(buf, &entry->type,      31, 31, size, op);
+	sja1105_packing(buf, &entry->priority,  30, 28, size, op);
+	sja1105_packing(buf, &entry->partition, 27, 25, size, op);
+	sja1105_packing(buf, &entry->destports, 24, 14, size, op);
+	return size;
+}
+
 size_t sja1105_vl_lookup_entry_packing(void *buf, void *entry_ptr,
 				       enum packing_op op)
 {
@@ -492,6 +737,40 @@ size_t sja1105_vl_lookup_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+size_t sja1110_vl_lookup_entry_packing(void *buf, void *entry_ptr,
+				       enum packing_op op)
+{
+	struct sja1105_vl_lookup_entry *entry = entry_ptr;
+	const size_t size = SJA1105_SIZE_VL_LOOKUP_ENTRY;
+
+	if (entry->format == SJA1105_VL_FORMAT_PSFP) {
+		/* Interpreting vllupformat as 0 */
+		sja1105_packing(buf, &entry->destports,
+				94, 84, size, op);
+		sja1105_packing(buf, &entry->iscritical,
+				83, 83, size, op);
+		sja1105_packing(buf, &entry->macaddr,
+				82, 35, size, op);
+		sja1105_packing(buf, &entry->vlanid,
+				34, 23, size, op);
+		sja1105_packing(buf, &entry->port,
+				22, 19, size, op);
+		sja1105_packing(buf, &entry->vlanprior,
+				18, 16, size, op);
+	} else {
+		/* Interpreting vllupformat as 1 */
+		sja1105_packing(buf, &entry->egrmirr,
+				94, 84, size, op);
+		sja1105_packing(buf, &entry->ingrmirr,
+				83, 83, size, op);
+		sja1105_packing(buf, &entry->vlid,
+				50, 35, size, op);
+		sja1105_packing(buf, &entry->port,
+				22, 19, size, op);
+	}
+	return size;
+}
+
 static size_t sja1105_vl_policing_entry_packing(void *buf, void *entry_ptr,
 						enum packing_op op)
 {
@@ -508,6 +787,22 @@ static size_t sja1105_vl_policing_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+size_t sja1110_vl_policing_entry_packing(void *buf, void *entry_ptr,
+					 enum packing_op op)
+{
+	struct sja1105_vl_policing_entry *entry = entry_ptr;
+	const size_t size = SJA1105_SIZE_VL_POLICING_ENTRY;
+
+	sja1105_packing(buf, &entry->type,      63, 63, size, op);
+	sja1105_packing(buf, &entry->maxlen,    62, 52, size, op);
+	sja1105_packing(buf, &entry->sharindx,  51, 40, size, op);
+	if (entry->type == 0) {
+		sja1105_packing(buf, &entry->bag,    41, 28, size, op);
+		sja1105_packing(buf, &entry->jitter, 27, 18, size, op);
+	}
+	return size;
+}
+
 size_t sja1105_vlan_lookup_entry_packing(void *buf, void *entry_ptr,
 					 enum packing_op op)
 {
@@ -523,6 +818,22 @@ size_t sja1105_vlan_lookup_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+size_t sja1110_vlan_lookup_entry_packing(void *buf, void *entry_ptr,
+					 enum packing_op op)
+{
+	struct sja1105_vlan_lookup_entry *entry = entry_ptr;
+	const size_t size = SJA1110_SIZE_VLAN_LOOKUP_ENTRY;
+
+	sja1105_packing(buf, &entry->ving_mirr,  95, 85, size, op);
+	sja1105_packing(buf, &entry->vegr_mirr,  84, 74, size, op);
+	sja1105_packing(buf, &entry->vmemb_port, 73, 63, size, op);
+	sja1105_packing(buf, &entry->vlan_bc,    62, 52, size, op);
+	sja1105_packing(buf, &entry->tag_port,   51, 41, size, op);
+	sja1105_packing(buf, &entry->type_entry, 40, 39, size, op);
+	sja1105_packing(buf, &entry->vlanid,     38, 27, size, op);
+	return size;
+}
+
 static size_t sja1105_xmii_params_entry_packing(void *buf, void *entry_ptr,
 						enum packing_op op)
 {
@@ -539,6 +850,24 @@ static size_t sja1105_xmii_params_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+size_t sja1110_xmii_params_entry_packing(void *buf, void *entry_ptr,
+					 enum packing_op op)
+{
+	const size_t size = SJA1110_SIZE_XMII_PARAMS_ENTRY;
+	struct sja1105_xmii_params_entry *entry = entry_ptr;
+	int offset, i;
+
+	for (i = 0, offset = 20; i < SJA1110_NUM_PORTS; i++, offset += 4) {
+		sja1105_packing(buf, &entry->xmii_mode[i],
+				offset + 1, offset + 0, size, op);
+		sja1105_packing(buf, &entry->phy_mac[i],
+				offset + 2, offset + 2, size, op);
+		sja1105_packing(buf, &entry->special[i],
+				offset + 3, offset + 3, size, op);
+	}
+	return size;
+}
+
 size_t sja1105_retagging_entry_packing(void *buf, void *entry_ptr,
 				       enum packing_op op)
 {
@@ -555,6 +884,36 @@ size_t sja1105_retagging_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+size_t sja1110_retagging_entry_packing(void *buf, void *entry_ptr,
+				       enum packing_op op)
+{
+	struct sja1105_retagging_entry *entry = entry_ptr;
+	const size_t size = SJA1105_SIZE_RETAGGING_ENTRY;
+
+	sja1105_packing(buf, &entry->egr_port,       63, 53, size, op);
+	sja1105_packing(buf, &entry->ing_port,       52, 42, size, op);
+	sja1105_packing(buf, &entry->vlan_ing,       41, 30, size, op);
+	sja1105_packing(buf, &entry->vlan_egr,       29, 18, size, op);
+	sja1105_packing(buf, &entry->do_not_learn,   17, 17, size, op);
+	sja1105_packing(buf, &entry->use_dest_ports, 16, 16, size, op);
+	sja1105_packing(buf, &entry->destports,      15, 5, size, op);
+	return size;
+}
+
+static size_t sja1110_pcp_remapping_entry_packing(void *buf, void *entry_ptr,
+						  enum packing_op op)
+{
+	struct sja1110_pcp_remapping_entry *entry = entry_ptr;
+	const size_t size = SJA1110_SIZE_PCP_REMAPPING_ENTRY;
+	int offset, i;
+
+	for (i = 0, offset = 8; i < SJA1105_NUM_TC; i++, offset += 3)
+		sja1105_packing(buf, &entry->egrpcp[i],
+				offset + 2, offset + 0, size, op);
+
+	return size;
+}
+
 size_t sja1105_table_header_packing(void *buf, void *entry_ptr,
 				    enum packing_op op)
 {
@@ -619,6 +978,7 @@ static u64 blk_id_map[BLK_IDX_MAX] = {
 	[BLK_IDX_GENERAL_PARAMS] = BLKID_GENERAL_PARAMS,
 	[BLK_IDX_RETAGGING] = BLKID_RETAGGING,
 	[BLK_IDX_XMII_PARAMS] = BLKID_XMII_PARAMS,
+	[BLK_IDX_PCP_REMAPPING] = BLKID_PCP_REMAPPING,
 };
 
 const char *sja1105_static_config_error_msg[] = {
@@ -657,11 +1017,11 @@ const char *sja1105_static_config_error_msg[] = {
 };
 
 static sja1105_config_valid_t
-static_config_check_memory_size(const struct sja1105_table *tables)
+static_config_check_memory_size(const struct sja1105_table *tables, int max_mem)
 {
 	const struct sja1105_l2_forwarding_params_entry *l2_fwd_params;
 	const struct sja1105_vl_forwarding_params_entry *vl_fwd_params;
-	int i, max_mem, mem = 0;
+	int i, mem = 0;
 
 	l2_fwd_params = tables[BLK_IDX_L2_FORWARDING_PARAMS].entries;
 
@@ -675,9 +1035,7 @@ static_config_check_memory_size(const struct sja1105_table *tables)
 	}
 
 	if (tables[BLK_IDX_RETAGGING].entry_count)
-		max_mem = SJA1105_MAX_FRAME_MEMORY_RETAGGING;
-	else
-		max_mem = SJA1105_MAX_FRAME_MEMORY;
+		max_mem -= SJA1105_FRAME_MEMORY_RETAGGING_OVERHEAD;
 
 	if (mem > max_mem)
 		return SJA1105_OVERCOMMITTED_FRAME_MEMORY;
@@ -686,15 +1044,15 @@ static_config_check_memory_size(const struct sja1105_table *tables)
 }
 
 sja1105_config_valid_t
-sja1105_static_config_check_valid(const struct sja1105_static_config *config)
+sja1105_static_config_check_valid(const struct sja1105_static_config *config,
+				  int max_mem)
 {
 	const struct sja1105_table *tables = config->tables;
 #define IS_FULL(blk_idx) \
 	(tables[blk_idx].entry_count == tables[blk_idx].ops->max_entry_count)
 
 	if (tables[BLK_IDX_SCHEDULE].entry_count) {
-		if (config->device_id != SJA1105T_DEVICE_ID &&
-		    config->device_id != SJA1105QS_DEVICE_ID)
+		if (!tables[BLK_IDX_SCHEDULE].ops->max_entry_count)
 			return SJA1105_TTETHERNET_NOT_SUPPORTED;
 
 		if (tables[BLK_IDX_SCHEDULE_ENTRY_POINTS].entry_count == 0)
@@ -754,7 +1112,7 @@ sja1105_static_config_check_valid(const struct sja1105_static_config *config)
 	if (!IS_FULL(BLK_IDX_XMII_PARAMS))
 		return SJA1105_MISSING_XMII_TABLE;
 
-	return static_config_check_memory_size(tables);
+	return static_config_check_memory_size(tables, max_mem);
 #undef IS_FULL
 }
 
@@ -1401,6 +1759,130 @@ const struct sja1105_table_ops sja1105s_table_ops[BLK_IDX_MAX] = {
 	},
 };
 
+/* SJA1110A: Third generation */
+const struct sja1105_table_ops sja1110_table_ops[BLK_IDX_MAX] = {
+	[BLK_IDX_SCHEDULE] = {
+		.packing = sja1110_schedule_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_schedule_entry),
+		.packed_entry_size = SJA1110_SIZE_SCHEDULE_ENTRY,
+		.max_entry_count = SJA1110_MAX_SCHEDULE_COUNT,
+	},
+	[BLK_IDX_SCHEDULE_ENTRY_POINTS] = {
+		.packing = sja1110_schedule_entry_points_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_schedule_entry_points_entry),
+		.packed_entry_size = SJA1110_SIZE_SCHEDULE_ENTRY_POINTS_ENTRY,
+		.max_entry_count = SJA1105_MAX_SCHEDULE_ENTRY_POINTS_COUNT,
+	},
+	[BLK_IDX_VL_LOOKUP] = {
+		.packing = sja1110_vl_lookup_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_vl_lookup_entry),
+		.packed_entry_size = SJA1105_SIZE_VL_LOOKUP_ENTRY,
+		.max_entry_count = SJA1110_MAX_VL_LOOKUP_COUNT,
+	},
+	[BLK_IDX_VL_POLICING] = {
+		.packing = sja1110_vl_policing_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_vl_policing_entry),
+		.packed_entry_size = SJA1105_SIZE_VL_POLICING_ENTRY,
+		.max_entry_count = SJA1110_MAX_VL_POLICING_COUNT,
+	},
+	[BLK_IDX_VL_FORWARDING] = {
+		.packing = sja1110_vl_forwarding_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_vl_forwarding_entry),
+		.packed_entry_size = SJA1105_SIZE_VL_FORWARDING_ENTRY,
+		.max_entry_count = SJA1110_MAX_VL_FORWARDING_COUNT,
+	},
+	[BLK_IDX_L2_LOOKUP] = {
+		.packing = sja1110_l2_lookup_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_lookup_entry),
+		.packed_entry_size = SJA1110_SIZE_L2_LOOKUP_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT,
+	},
+	[BLK_IDX_L2_POLICING] = {
+		.packing = sja1110_l2_policing_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_policing_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_POLICING_ENTRY,
+		.max_entry_count = SJA1110_MAX_L2_POLICING_COUNT,
+	},
+	[BLK_IDX_VLAN_LOOKUP] = {
+		.packing = sja1110_vlan_lookup_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_vlan_lookup_entry),
+		.packed_entry_size = SJA1110_SIZE_VLAN_LOOKUP_ENTRY,
+		.max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT,
+	},
+	[BLK_IDX_L2_FORWARDING] = {
+		.packing = sja1110_l2_forwarding_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_ENTRY,
+		.max_entry_count = SJA1110_MAX_L2_FORWARDING_COUNT,
+	},
+	[BLK_IDX_MAC_CONFIG] = {
+		.packing = sja1110_mac_config_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_mac_config_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY,
+		.max_entry_count = SJA1110_MAX_MAC_CONFIG_COUNT,
+	},
+	[BLK_IDX_SCHEDULE_PARAMS] = {
+		.packing = sja1110_schedule_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_schedule_params_entry),
+		.packed_entry_size = SJA1105_SIZE_SCHEDULE_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_SCHEDULE_PARAMS_COUNT,
+	},
+	[BLK_IDX_SCHEDULE_ENTRY_POINTS_PARAMS] = {
+		.packing = sja1105_schedule_entry_points_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_schedule_entry_points_params_entry),
+		.packed_entry_size = SJA1105_SIZE_SCHEDULE_ENTRY_POINTS_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_SCHEDULE_ENTRY_POINTS_PARAMS_COUNT,
+	},
+	[BLK_IDX_VL_FORWARDING_PARAMS] = {
+		.packing = sja1110_vl_forwarding_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_vl_forwarding_params_entry),
+		.packed_entry_size = SJA1105_SIZE_VL_FORWARDING_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_VL_FORWARDING_PARAMS_COUNT,
+	},
+	[BLK_IDX_L2_LOOKUP_PARAMS] = {
+		.packing = sja1110_l2_lookup_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_lookup_params_entry),
+		.packed_entry_size = SJA1110_SIZE_L2_LOOKUP_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT,
+	},
+	[BLK_IDX_L2_FORWARDING_PARAMS] = {
+		.packing = sja1110_l2_forwarding_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_params_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT,
+	},
+	[BLK_IDX_AVB_PARAMS] = {
+		.packing = sja1105pqrs_avb_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_avb_params_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_AVB_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_AVB_PARAMS_COUNT,
+	},
+	[BLK_IDX_GENERAL_PARAMS] = {
+		.packing = sja1110_general_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_general_params_entry),
+		.packed_entry_size = SJA1110_SIZE_GENERAL_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT,
+	},
+	[BLK_IDX_RETAGGING] = {
+		.packing = sja1110_retagging_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_retagging_entry),
+		.packed_entry_size = SJA1105_SIZE_RETAGGING_ENTRY,
+		.max_entry_count = SJA1105_MAX_RETAGGING_COUNT,
+	},
+	[BLK_IDX_XMII_PARAMS] = {
+		.packing = sja1110_xmii_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_xmii_params_entry),
+		.packed_entry_size = SJA1110_SIZE_XMII_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_XMII_PARAMS_COUNT,
+	},
+	[BLK_IDX_PCP_REMAPPING] = {
+		.packing = sja1110_pcp_remapping_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1110_pcp_remapping_entry),
+		.packed_entry_size = SJA1110_SIZE_PCP_REMAPPING_ENTRY,
+		.max_entry_count = SJA1110_MAX_PCP_REMAPPING_COUNT,
+	},
+};
+
 int sja1105_static_config_init(struct sja1105_static_config *config,
 			       const struct sja1105_table_ops *static_ops,
 			       u64 device_id)
diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.h b/drivers/net/dsa/sja1105/sja1105_static_config.h
index bc7606899289..bce0f5c03d0b 100644
--- a/drivers/net/dsa/sja1105/sja1105_static_config.h
+++ b/drivers/net/dsa/sja1105/sja1105_static_config.h
@@ -9,19 +9,30 @@
 #include <linux/types.h>
 #include <asm/types.h>
 
+#define SJA1105_NUM_PORTS				5
+#define SJA1110_NUM_PORTS				11
+#define SJA1105_MAX_NUM_PORTS				SJA1110_NUM_PORTS
+#define SJA1105_NUM_TC					8
+
+#define SJA1105_SIZE_SPI_MSG_HEADER			4
+#define SJA1105_SIZE_SPI_MSG_MAXLEN			(64 * 4)
 #define SJA1105_SIZE_DEVICE_ID				4
 #define SJA1105_SIZE_TABLE_HEADER			12
 #define SJA1105_SIZE_SCHEDULE_ENTRY			8
+#define SJA1110_SIZE_SCHEDULE_ENTRY			12
 #define SJA1105_SIZE_SCHEDULE_ENTRY_POINTS_ENTRY	4
+#define SJA1110_SIZE_SCHEDULE_ENTRY_POINTS_ENTRY	8
 #define SJA1105_SIZE_VL_LOOKUP_ENTRY			12
 #define SJA1105_SIZE_VL_POLICING_ENTRY			8
 #define SJA1105_SIZE_VL_FORWARDING_ENTRY		4
 #define SJA1105_SIZE_L2_POLICING_ENTRY			8
 #define SJA1105_SIZE_VLAN_LOOKUP_ENTRY			8
+#define SJA1110_SIZE_VLAN_LOOKUP_ENTRY			12
 #define SJA1105_SIZE_L2_FORWARDING_ENTRY		8
 #define SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY		12
 #define SJA1105_SIZE_RETAGGING_ENTRY			8
 #define SJA1105_SIZE_XMII_PARAMS_ENTRY			4
+#define SJA1110_SIZE_XMII_PARAMS_ENTRY			8
 #define SJA1105_SIZE_SCHEDULE_PARAMS_ENTRY		12
 #define SJA1105_SIZE_SCHEDULE_ENTRY_POINTS_PARAMS_ENTRY	4
 #define SJA1105_SIZE_VL_FORWARDING_PARAMS_ENTRY         12
@@ -32,11 +43,15 @@
 #define SJA1105ET_SIZE_AVB_PARAMS_ENTRY			12
 #define SJA1105ET_SIZE_CBS_ENTRY			16
 #define SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY		20
+#define SJA1110_SIZE_L2_LOOKUP_ENTRY			24
 #define SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY		32
 #define SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY		16
+#define SJA1110_SIZE_L2_LOOKUP_PARAMS_ENTRY		28
 #define SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY		44
+#define SJA1110_SIZE_GENERAL_PARAMS_ENTRY		56
 #define SJA1105PQRS_SIZE_AVB_PARAMS_ENTRY		16
 #define SJA1105PQRS_SIZE_CBS_ENTRY			20
+#define SJA1110_SIZE_PCP_REMAPPING_ENTRY		4
 
 /* UM10944.pdf Page 11, Table 2. Configuration Blocks */
 enum {
@@ -59,6 +74,7 @@ enum {
 	BLKID_GENERAL_PARAMS				= 0x11,
 	BLKID_RETAGGING					= 0x12,
 	BLKID_CBS					= 0x13,
+	BLKID_PCP_REMAPPING				= 0x1C,
 	BLKID_XMII_PARAMS				= 0x4E,
 };
 
@@ -83,6 +99,7 @@ enum sja1105_blk_idx {
 	BLK_IDX_RETAGGING,
 	BLK_IDX_CBS,
 	BLK_IDX_XMII_PARAMS,
+	BLK_IDX_PCP_REMAPPING,
 	BLK_IDX_MAX,
 	/* Fake block indices that are only valid for dynamic access */
 	BLK_IDX_MGMT_ROUTE,
@@ -91,15 +108,22 @@ enum sja1105_blk_idx {
 };
 
 #define SJA1105_MAX_SCHEDULE_COUNT			1024
+#define SJA1110_MAX_SCHEDULE_COUNT			4096
 #define SJA1105_MAX_SCHEDULE_ENTRY_POINTS_COUNT		2048
 #define SJA1105_MAX_VL_LOOKUP_COUNT			1024
+#define SJA1110_MAX_VL_LOOKUP_COUNT			4096
 #define SJA1105_MAX_VL_POLICING_COUNT			1024
+#define SJA1110_MAX_VL_POLICING_COUNT			4096
 #define SJA1105_MAX_VL_FORWARDING_COUNT			1024
+#define SJA1110_MAX_VL_FORWARDING_COUNT			4096
 #define SJA1105_MAX_L2_LOOKUP_COUNT			1024
 #define SJA1105_MAX_L2_POLICING_COUNT			45
+#define SJA1110_MAX_L2_POLICING_COUNT			110
 #define SJA1105_MAX_VLAN_LOOKUP_COUNT			4096
 #define SJA1105_MAX_L2_FORWARDING_COUNT			13
+#define SJA1110_MAX_L2_FORWARDING_COUNT			19
 #define SJA1105_MAX_MAC_CONFIG_COUNT			5
+#define SJA1110_MAX_MAC_CONFIG_COUNT			11
 #define SJA1105_MAX_SCHEDULE_PARAMS_COUNT		1
 #define SJA1105_MAX_SCHEDULE_ENTRY_POINTS_PARAMS_COUNT	1
 #define SJA1105_MAX_VL_FORWARDING_PARAMS_COUNT		1
@@ -111,21 +135,40 @@ enum sja1105_blk_idx {
 #define SJA1105_MAX_AVB_PARAMS_COUNT			1
 #define SJA1105ET_MAX_CBS_COUNT				10
 #define SJA1105PQRS_MAX_CBS_COUNT			16
+#define SJA1110_MAX_CBS_COUNT				80
+#define SJA1110_MAX_PCP_REMAPPING_COUNT			11
 
 #define SJA1105_MAX_FRAME_MEMORY			929
-#define SJA1105_MAX_FRAME_MEMORY_RETAGGING		910
+#define SJA1110_MAX_FRAME_MEMORY			1820
+#define SJA1105_FRAME_MEMORY_RETAGGING_OVERHEAD		19
 #define SJA1105_VL_FRAME_MEMORY				100
 
 #define SJA1105E_DEVICE_ID				0x9C00000Cull
 #define SJA1105T_DEVICE_ID				0x9E00030Eull
 #define SJA1105PR_DEVICE_ID				0xAF00030Eull
 #define SJA1105QS_DEVICE_ID				0xAE00030Eull
+#define SJA1110_DEVICE_ID				0xB700030Full
 
 #define SJA1105ET_PART_NO				0x9A83
 #define SJA1105P_PART_NO				0x9A84
 #define SJA1105Q_PART_NO				0x9A85
 #define SJA1105R_PART_NO				0x9A86
 #define SJA1105S_PART_NO				0x9A87
+#define SJA1110A_PART_NO				0x1110
+#define SJA1110B_PART_NO				0x1111
+#define SJA1110C_PART_NO				0x1112
+#define SJA1110D_PART_NO				0x1113
+
+#define SJA1110_ACU			0x1c4400
+#define SJA1110_RGU			0x1c6000
+#define SJA1110_CGU			0x1c6400
+
+#define SJA1110_SPI_ADDR(x)		((x) / 4)
+#define SJA1110_ACU_ADDR(x)		(SJA1110_ACU + SJA1110_SPI_ADDR(x))
+#define SJA1110_CGU_ADDR(x)		(SJA1110_CGU + SJA1110_SPI_ADDR(x))
+#define SJA1110_RGU_ADDR(x)		(SJA1110_RGU + SJA1110_SPI_ADDR(x))
+
+#define SJA1105_RSV_ADDR		0xffffffffffffffffull
 
 struct sja1105_schedule_entry {
 	u64 winstindex;
@@ -171,6 +214,10 @@ struct sja1105_general_params_entry {
 	u64 egrmirrpcp;
 	u64 egrmirrdei;
 	u64 replay_port;
+	/* SJA1110 only */
+	u64 tte_en;
+	u64 tdmaconfigidx;
+	u64 header_type;
 };
 
 struct sja1105_schedule_entry_points_entry {
@@ -191,6 +238,7 @@ struct sja1105_vlan_lookup_entry {
 	u64 vlan_bc;
 	u64 tag_port;
 	u64 vlanid;
+	u64 type_entry; /* SJA1110 only */
 };
 
 struct sja1105_l2_lookup_entry {
@@ -203,11 +251,17 @@ struct sja1105_l2_lookup_entry {
 	u64 mask_iotag;
 	u64 mask_vlanid;
 	u64 mask_macaddr;
+	u64 mask_srcport;
 	u64 iotag;
+	u64 srcport;
 	u64 lockeds;
 	union {
 		/* LOCKEDS=1: Static FDB entries */
 		struct {
+			/* TSREG is deprecated in SJA1110, TRAP is supported only
+			 * in SJA1110.
+			 */
+			u64 trap;
 			u64 tsreg;
 			u64 mirrvlan;
 			u64 takets;
@@ -223,7 +277,7 @@ struct sja1105_l2_lookup_entry {
 };
 
 struct sja1105_l2_lookup_params_entry {
-	u64 maxaddrp[5];     /* P/Q/R/S only */
+	u64 maxaddrp[SJA1105_MAX_NUM_PORTS]; /* P/Q/R/S only */
 	u64 start_dynspc;    /* P/Q/R/S only */
 	u64 drpnolearn;      /* P/Q/R/S only */
 	u64 use_static;      /* P/Q/R/S only */
@@ -241,7 +295,9 @@ struct sja1105_l2_forwarding_entry {
 	u64 bc_domain;
 	u64 reach_port;
 	u64 fl_domain;
-	u64 vlan_pmap[8];
+	/* This is actually max(SJA1105_NUM_TC, SJA1105_MAX_NUM_PORTS) */
+	u64 vlan_pmap[SJA1105_MAX_NUM_PORTS];
+	bool type_egrpcp2outputq;
 };
 
 struct sja1105_l2_forwarding_params_entry {
@@ -296,8 +352,8 @@ struct sja1105_retagging_entry {
 };
 
 struct sja1105_cbs_entry {
-	u64 port;
-	u64 prio;
+	u64 port; /* Not used for SJA1110 */
+	u64 prio; /* Not used for SJA1110 */
 	u64 credit_hi;
 	u64 credit_lo;
 	u64 send_slope;
@@ -305,8 +361,19 @@ struct sja1105_cbs_entry {
 };
 
 struct sja1105_xmii_params_entry {
-	u64 phy_mac[5];
-	u64 xmii_mode[5];
+	u64 phy_mac[SJA1105_MAX_NUM_PORTS];
+	u64 xmii_mode[SJA1105_MAX_NUM_PORTS];
+	/* The SJA1110 insists being a snowflake, and requires SGMII,
+	 * 2500base-x and internal MII ports connected to the 100base-TX PHY to
+	 * set this bit. We set it unconditionally from the high-level logic,
+	 * and only sja1110_xmii_params_entry_packing writes it to the static
+	 * config. I have no better name for it than "special".
+	 */
+	u64 special[SJA1105_MAX_NUM_PORTS];
+};
+
+struct sja1110_pcp_remapping_entry {
+	u64 egrpcp[SJA1105_NUM_TC];
 };
 
 enum {
@@ -387,6 +454,7 @@ extern const struct sja1105_table_ops sja1105p_table_ops[BLK_IDX_MAX];
 extern const struct sja1105_table_ops sja1105q_table_ops[BLK_IDX_MAX];
 extern const struct sja1105_table_ops sja1105r_table_ops[BLK_IDX_MAX];
 extern const struct sja1105_table_ops sja1105s_table_ops[BLK_IDX_MAX];
+extern const struct sja1105_table_ops sja1110_table_ops[BLK_IDX_MAX];
 
 size_t sja1105_table_header_packing(void *buf, void *hdr, enum packing_op op);
 void
@@ -412,7 +480,8 @@ typedef enum {
 extern const char *sja1105_static_config_error_msg[];
 
 sja1105_config_valid_t
-sja1105_static_config_check_valid(const struct sja1105_static_config *config);
+sja1105_static_config_check_valid(const struct sja1105_static_config *config,
+				  int max_mem);
 void
 sja1105_static_config_pack(void *buf, struct sja1105_static_config *config);
 int sja1105_static_config_init(struct sja1105_static_config *config,
@@ -433,23 +502,47 @@ void sja1105_packing(void *buf, u64 *val, int start, int end,
 /* Common implementations for the static and dynamic configs */
 size_t sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr,
 						enum packing_op op);
+size_t sja1110_general_params_entry_packing(void *buf, void *entry_ptr,
+					    enum packing_op op);
 size_t sja1105pqrs_l2_lookup_params_entry_packing(void *buf, void *entry_ptr,
 						  enum packing_op op);
+size_t sja1110_l2_lookup_params_entry_packing(void *buf, void *entry_ptr,
+					      enum packing_op op);
 size_t sja1105_l2_forwarding_entry_packing(void *buf, void *entry_ptr,
 					   enum packing_op op);
+size_t sja1110_l2_forwarding_entry_packing(void *buf, void *entry_ptr,
+					   enum packing_op op);
 size_t sja1105pqrs_l2_lookup_entry_packing(void *buf, void *entry_ptr,
 					   enum packing_op op);
 size_t sja1105et_l2_lookup_entry_packing(void *buf, void *entry_ptr,
 					 enum packing_op op);
+size_t sja1110_l2_lookup_entry_packing(void *buf, void *entry_ptr,
+				       enum packing_op op);
 size_t sja1105_vlan_lookup_entry_packing(void *buf, void *entry_ptr,
 					 enum packing_op op);
+size_t sja1110_vlan_lookup_entry_packing(void *buf, void *entry_ptr,
+					 enum packing_op op);
 size_t sja1105_retagging_entry_packing(void *buf, void *entry_ptr,
 				       enum packing_op op);
+size_t sja1110_retagging_entry_packing(void *buf, void *entry_ptr,
+				       enum packing_op op);
 size_t sja1105pqrs_mac_config_entry_packing(void *buf, void *entry_ptr,
 					    enum packing_op op);
+size_t sja1110_mac_config_entry_packing(void *buf, void *entry_ptr,
+					enum packing_op op);
 size_t sja1105pqrs_avb_params_entry_packing(void *buf, void *entry_ptr,
 					    enum packing_op op);
 size_t sja1105_vl_lookup_entry_packing(void *buf, void *entry_ptr,
 				       enum packing_op op);
+size_t sja1110_vl_lookup_entry_packing(void *buf, void *entry_ptr,
+				       enum packing_op op);
+size_t sja1110_vl_policing_entry_packing(void *buf, void *entry_ptr,
+					 enum packing_op op);
+size_t sja1110_xmii_params_entry_packing(void *buf, void *entry_ptr,
+					 enum packing_op op);
+size_t sja1110_l2_policing_entry_packing(void *buf, void *entry_ptr,
+					 enum packing_op op);
+size_t sja1110_l2_forwarding_params_entry_packing(void *buf, void *entry_ptr,
+						  enum packing_op op);
 
 #endif
diff --git a/drivers/net/dsa/sja1105/sja1105_tas.c b/drivers/net/dsa/sja1105/sja1105_tas.c
index 31d8acff1f01..e6153848a950 100644
--- a/drivers/net/dsa/sja1105/sja1105_tas.c
+++ b/drivers/net/dsa/sja1105/sja1105_tas.c
@@ -27,7 +27,7 @@ static int sja1105_tas_set_runtime_params(struct sja1105_private *priv)
 
 	tas_data->enabled = false;
 
-	for (port = 0; port < SJA1105_NUM_PORTS; port++) {
+	for (port = 0; port < ds->num_ports; port++) {
 		const struct tc_taprio_qopt_offload *offload;
 
 		offload = tas_data->offload[port];
@@ -164,6 +164,7 @@ int sja1105_init_scheduling(struct sja1105_private *priv)
 	struct sja1105_tas_data *tas_data = &priv->tas_data;
 	struct sja1105_gating_config *gating_cfg = &tas_data->gating_cfg;
 	struct sja1105_schedule_entry *schedule;
+	struct dsa_switch *ds = priv->ds;
 	struct sja1105_table *table;
 	int schedule_start_idx;
 	s64 entry_point_delta;
@@ -207,7 +208,7 @@ int sja1105_init_scheduling(struct sja1105_private *priv)
 	}
 
 	/* Figure out the dimensioning of the problem */
-	for (port = 0; port < SJA1105_NUM_PORTS; port++) {
+	for (port = 0; port < ds->num_ports; port++) {
 		if (tas_data->offload[port]) {
 			num_entries += tas_data->offload[port]->num_entries;
 			num_cycles++;
@@ -269,7 +270,7 @@ int sja1105_init_scheduling(struct sja1105_private *priv)
 	schedule_entry_points_params->clksrc = SJA1105_TAS_CLKSRC_PTP;
 	schedule_entry_points_params->actsubsch = num_cycles - 1;
 
-	for (port = 0; port < SJA1105_NUM_PORTS; port++) {
+	for (port = 0; port < ds->num_ports; port++) {
 		const struct tc_taprio_qopt_offload *offload;
 		/* Relative base time */
 		s64 rbt;
@@ -468,6 +469,7 @@ bool sja1105_gating_check_conflicts(struct sja1105_private *priv, int port,
 	struct sja1105_gating_config *gating_cfg = &priv->tas_data.gating_cfg;
 	size_t num_entries = gating_cfg->num_entries;
 	struct tc_taprio_qopt_offload *dummy;
+	struct dsa_switch *ds = priv->ds;
 	struct sja1105_gate_entry *e;
 	bool conflict;
 	int i = 0;
@@ -491,7 +493,7 @@ bool sja1105_gating_check_conflicts(struct sja1105_private *priv, int port,
 	if (port != -1) {
 		conflict = sja1105_tas_check_conflicts(priv, port, dummy);
 	} else {
-		for (port = 0; port < SJA1105_NUM_PORTS; port++) {
+		for (port = 0; port < ds->num_ports; port++) {
 			conflict = sja1105_tas_check_conflicts(priv, port,
 							       dummy);
 			if (conflict)
@@ -554,7 +556,7 @@ int sja1105_setup_tc_taprio(struct dsa_switch *ds, int port,
 		}
 	}
 
-	for (other_port = 0; other_port < SJA1105_NUM_PORTS; other_port++) {
+	for (other_port = 0; other_port < ds->num_ports; other_port++) {
 		if (other_port == port)
 			continue;
 
@@ -885,7 +887,7 @@ void sja1105_tas_teardown(struct dsa_switch *ds)
 
 	cancel_work_sync(&priv->tas_data.tas_work);
 
-	for (port = 0; port < SJA1105_NUM_PORTS; port++) {
+	for (port = 0; port < ds->num_ports; port++) {
 		offload = priv->tas_data.offload[port];
 		if (!offload)
 			continue;
diff --git a/drivers/net/dsa/sja1105/sja1105_tas.h b/drivers/net/dsa/sja1105/sja1105_tas.h
index 0c173ff51751..c05bd07e8221 100644
--- a/drivers/net/dsa/sja1105/sja1105_tas.h
+++ b/drivers/net/dsa/sja1105/sja1105_tas.h
@@ -39,7 +39,7 @@ struct sja1105_gating_config {
 };
 
 struct sja1105_tas_data {
-	struct tc_taprio_qopt_offload *offload[SJA1105_NUM_PORTS];
+	struct tc_taprio_qopt_offload *offload[SJA1105_MAX_NUM_PORTS];
 	struct sja1105_gating_config gating_cfg;
 	enum sja1105_tas_state state;
 	enum sja1105_ptp_op last_op;
diff --git a/drivers/net/dsa/sja1105/sja1105_vl.c b/drivers/net/dsa/sja1105/sja1105_vl.c
index ffc4042b4502..f6e13e6c6a18 100644
--- a/drivers/net/dsa/sja1105/sja1105_vl.c
+++ b/drivers/net/dsa/sja1105/sja1105_vl.c
@@ -386,7 +386,7 @@ static int sja1105_init_virtual_links(struct sja1105_private *priv,
 		if (rule->type != SJA1105_RULE_VL)
 			continue;
 
-		for_each_set_bit(port, &rule->port_mask, SJA1105_NUM_PORTS) {
+		for_each_set_bit(port, &rule->port_mask, SJA1105_MAX_NUM_PORTS) {
 			vl_lookup[k].format = SJA1105_VL_FORMAT_PSFP;
 			vl_lookup[k].port = port;
 			vl_lookup[k].macaddr = rule->key.vl.dmac;
diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c
index fde6e99274b6..130abb0f1438 100644
--- a/drivers/net/dsa/xrs700x/xrs700x.c
+++ b/drivers/net/dsa/xrs700x/xrs700x.c
@@ -79,6 +79,9 @@ static const struct xrs700x_mib xrs700x_mibs[] = {
 	XRS700X_MIB(XRS_EARLY_DROP_L, "early_drop", tx_dropped),
 };
 
+static const u8 eth_hsrsup_addr[ETH_ALEN] = {
+	0x01, 0x15, 0x4e, 0x00, 0x01, 0x00};
+
 static void xrs700x_get_strings(struct dsa_switch *ds, int port,
 				u32 stringset, u8 *data)
 {
@@ -329,6 +332,54 @@ static int xrs700x_port_add_bpdu_ipf(struct dsa_switch *ds, int port)
 	return 0;
 }
 
+/* Add an inbound policy filter which matches the HSR/PRP supervision MAC
+ * range and forwards to the CPU port without discarding duplicates.
+ * This is required to correctly populate the HSR/PRP node_table.
+ * Leave the policy disabled, it will be enabled as needed.
+ */
+static int xrs700x_port_add_hsrsup_ipf(struct dsa_switch *ds, int port,
+				       int fwdport)
+{
+	struct xrs700x *priv = ds->priv;
+	unsigned int val = 0;
+	int i = 0;
+	int ret;
+
+	/* Compare 40 bits of the destination MAC address. */
+	ret = regmap_write(priv->regmap, XRS_ETH_ADDR_CFG(port, 1), 40 << 2);
+	if (ret)
+		return ret;
+
+	/* match HSR/PRP supervision destination 01:15:4e:00:01:XX */
+	for (i = 0; i < sizeof(eth_hsrsup_addr); i += 2) {
+		ret = regmap_write(priv->regmap, XRS_ETH_ADDR_0(port, 1) + i,
+				   eth_hsrsup_addr[i] |
+				   (eth_hsrsup_addr[i + 1] << 8));
+		if (ret)
+			return ret;
+	}
+
+	/* Mirror HSR/PRP supervision to CPU port */
+	for (i = 0; i < ds->num_ports; i++) {
+		if (dsa_is_cpu_port(ds, i))
+			val |= BIT(i);
+	}
+
+	ret = regmap_write(priv->regmap, XRS_ETH_ADDR_FWD_MIRROR(port, 1), val);
+	if (ret)
+		return ret;
+
+	if (fwdport >= 0)
+		val |= BIT(fwdport);
+
+	/* Allow must be set prevent duplicate discard */
+	ret = regmap_write(priv->regmap, XRS_ETH_ADDR_FWD_ALLOW(port, 1), val);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
 static int xrs700x_port_setup(struct dsa_switch *ds, int port)
 {
 	bool cpu_port = dsa_is_cpu_port(ds, port);
@@ -511,6 +562,7 @@ static int xrs700x_hsr_join(struct dsa_switch *ds, int port,
 	struct net_device *slave;
 	int ret, i, hsr_pair[2];
 	enum hsr_version ver;
+	bool fwd = false;
 
 	ret = hsr_get_version(hsr, &ver);
 	if (ret)
@@ -556,6 +608,7 @@ static int xrs700x_hsr_join(struct dsa_switch *ds, int port,
 	if (ver == HSR_V1) {
 		val &= ~BIT(partner->index);
 		val &= ~BIT(port);
+		fwd = true;
 	}
 	val &= ~BIT(dsa_upstream_port(ds, port));
 	regmap_write(priv->regmap, XRS_PORT_FWD_MASK(partner->index), val);
@@ -565,6 +618,23 @@ static int xrs700x_hsr_join(struct dsa_switch *ds, int port,
 			    XRS_PORT_FORWARDING);
 	regmap_fields_write(priv->ps_forward, port, XRS_PORT_FORWARDING);
 
+	/* Enable inbound policy which allows HSR/PRP supervision forwarding
+	 * to the CPU port without discarding duplicates. Continue to
+	 * forward to redundant ports when in HSR mode while discarding
+	 * duplicates.
+	 */
+	ret = xrs700x_port_add_hsrsup_ipf(ds, partner->index, fwd ? port : -1);
+	if (ret)
+		return ret;
+
+	ret = xrs700x_port_add_hsrsup_ipf(ds, port, fwd ? partner->index : -1);
+	if (ret)
+		return ret;
+
+	regmap_update_bits(priv->regmap,
+			   XRS_ETH_ADDR_CFG(partner->index, 1), 1, 1);
+	regmap_update_bits(priv->regmap, XRS_ETH_ADDR_CFG(port, 1), 1, 1);
+
 	hsr_pair[0] = port;
 	hsr_pair[1] = partner->index;
 	for (i = 0; i < ARRAY_SIZE(hsr_pair); i++) {
@@ -611,6 +681,14 @@ static int xrs700x_hsr_leave(struct dsa_switch *ds, int port,
 			    XRS_PORT_FORWARDING);
 	regmap_fields_write(priv->ps_forward, port, XRS_PORT_FORWARDING);
 
+	/* Disable inbound policy added by xrs700x_port_add_hsrsup_ipf()
+	 * which allows HSR/PRP supervision forwarding to the CPU port without
+	 * discarding duplicates.
+	 */
+	regmap_update_bits(priv->regmap,
+			   XRS_ETH_ADDR_CFG(partner->index, 1), 1, 0);
+	regmap_update_bits(priv->regmap, XRS_ETH_ADDR_CFG(port, 1), 1, 0);
+
 	hsr_pair[0] = port;
 	hsr_pair[1] = partner->index;
 	for (i = 0; i < ARRAY_SIZE(hsr_pair); i++) {
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 741c67e546d4..7d7d3ffe25c3 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -1464,7 +1464,7 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq,
 	if (pdev) {
 		vp->pm_state_valid = 1;
 		pci_save_state(pdev);
- 		acpi_set_WOL(dev);
+		acpi_set_WOL(dev);
 	}
 	retval = register_netdev(dev);
 	if (retval == 0)
diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c
index 2488bfdb9133..8c321dfc7b3b 100644
--- a/drivers/net/ethernet/8390/axnet_cs.c
+++ b/drivers/net/ethernet/8390/axnet_cs.c
@@ -767,7 +767,7 @@ module_pcmcia_driver(axnet_cs_driver);
   Paul Gortmaker	: tweak ANK's above multicast changes a bit.
   Paul Gortmaker	: update packet statistics for v2.1.x
   Alan Cox		: support arbitrary stupid port mappings on the
-  			  68K Macintosh. Support >16bit I/O spaces
+			  68K Macintosh. Support >16bit I/O spaces
   Paul Gortmaker	: add kmod support for auto-loading of the 8390
 			  module by all drivers that require it.
   Alan Cox		: Spinlocking work, added 'BUG_83C690'
@@ -1091,7 +1091,7 @@ static irqreturn_t ax_interrupt(int irq, void *dev_id)
 	long e8390_base;
 	int interrupts, nr_serviced = 0, i;
 	struct ei_device *ei_local;
-    	int handled = 0;
+	int handled = 0;
 	unsigned long flags;
 
 	e8390_base = dev->base_addr;
@@ -1587,12 +1587,12 @@ static void do_set_multicast_list(struct net_device *dev)
 	}
 	outb_p(E8390_NODMA + E8390_PAGE0, e8390_base + E8390_CMD);
 
-  	if(dev->flags&IFF_PROMISC)
-  		outb_p(E8390_RXCONFIG | 0x58, e8390_base + EN0_RXCR);
+	if(dev->flags&IFF_PROMISC)
+		outb_p(E8390_RXCONFIG | 0x58, e8390_base + EN0_RXCR);
 	else if (dev->flags & IFF_ALLMULTI || !netdev_mc_empty(dev))
-  		outb_p(E8390_RXCONFIG | 0x48, e8390_base + EN0_RXCR);
-  	else
-  		outb_p(E8390_RXCONFIG | 0x40, e8390_base + EN0_RXCR);
+		outb_p(E8390_RXCONFIG | 0x48, e8390_base + EN0_RXCR);
+	else
+		outb_p(E8390_RXCONFIG | 0x40, e8390_base + EN0_RXCR);
 
 	outb_p(E8390_NODMA+E8390_PAGE0+E8390_START, e8390_base+E8390_CMD);
 }
diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c
index 9d3b1e0e425c..cac036706382 100644
--- a/drivers/net/ethernet/8390/pcnet_cs.c
+++ b/drivers/net/ethernet/8390/pcnet_cs.c
@@ -1527,7 +1527,7 @@ static const struct pcmcia_device_id pcnet_ids[] = {
 	PCMCIA_DEVICE_PROD_ID12("ACCTON", "EN2216-PCMCIA-ETHERNET", 0xdfc6b5b2, 0x5542bfff),
 	PCMCIA_DEVICE_PROD_ID12("Allied Telesis, K.K.", "CentreCOM LA100-PCM-T V2 100/10M LAN PC Card", 0xbb7fbdd7, 0xcd91cc68),
 	PCMCIA_DEVICE_PROD_ID12("Allied Telesis K.K.", "LA100-PCM V2", 0x36634a66, 0xc6d05997),
-  	PCMCIA_DEVICE_PROD_ID12("Allied Telesis, K.K.", "CentreCOM LA-PCM_V2", 0xbb7fBdd7, 0x28e299f8),
+	PCMCIA_DEVICE_PROD_ID12("Allied Telesis, K.K.", "CentreCOM LA-PCM_V2", 0xbb7fBdd7, 0x28e299f8),
 	PCMCIA_DEVICE_PROD_ID12("Allied Telesis K.K.", "LA-PCM V3", 0x36634a66, 0x62241d96),
 	PCMCIA_DEVICE_PROD_ID12("AmbiCom", "AMB8010", 0x5070a7f9, 0x82f96e96),
 	PCMCIA_DEVICE_PROD_ID12("AmbiCom", "AMB8610", 0x5070a7f9, 0x86741224),
diff --git a/drivers/net/ethernet/8390/smc-ultra.c b/drivers/net/ethernet/8390/smc-ultra.c
index 3fe3b4dfa7c5..1d8ed7357b7f 100644
--- a/drivers/net/ethernet/8390/smc-ultra.c
+++ b/drivers/net/ethernet/8390/smc-ultra.c
@@ -347,11 +347,11 @@ static int __init ultra_probe_isapnp(struct net_device *dev)
                                             idev))) {
                         /* Avoid already found cards from previous calls */
                         if (pnp_device_attach(idev) < 0)
-                        	continue;
+				continue;
                         if (pnp_activate_dev(idev) < 0) {
                               __again:
-                        	pnp_device_detach(idev);
-                        	continue;
+				pnp_device_detach(idev);
+				continue;
                         }
 			/* if no io and irq, search for next */
 			if (!pnp_port_valid(idev, 0) || !pnp_irq_valid(idev, 0))
diff --git a/drivers/net/ethernet/8390/stnic.c b/drivers/net/ethernet/8390/stnic.c
index 1f0670cd3ea3..fbbd7f22c142 100644
--- a/drivers/net/ethernet/8390/stnic.c
+++ b/drivers/net/ethernet/8390/stnic.c
@@ -114,7 +114,7 @@ static int __init stnic_probe(void)
   /* New style probing API */
   dev = alloc_ei_netdev();
   if (!dev)
-  	return -ENOMEM;
+	return -ENOMEM;
 
 #ifdef CONFIG_SH_STANDARD_BIOS
   sh_bios_get_node_addr (stnic_eadr);
diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c
index 1a7e4df9b3e9..9dc12b13061f 100644
--- a/drivers/net/ethernet/alteon/acenic.c
+++ b/drivers/net/ethernet/alteon/acenic.c
@@ -1883,16 +1883,16 @@ static u32 ace_handle_event(struct net_device *dev, u32 evtcsm, u32 evtprd)
 				}
 			}
 
- 			if (ACE_IS_TIGON_I(ap)) {
- 				struct cmd cmd;
- 				cmd.evt = C_SET_RX_JUMBO_PRD_IDX;
- 				cmd.code = 0;
- 				cmd.idx = 0;
- 				ace_issue_cmd(ap->regs, &cmd);
- 			} else {
- 				writel(0, &((ap->regs)->RxJumboPrd));
- 				wmb();
- 			}
+			if (ACE_IS_TIGON_I(ap)) {
+				struct cmd cmd;
+				cmd.evt = C_SET_RX_JUMBO_PRD_IDX;
+				cmd.code = 0;
+				cmd.idx = 0;
+				ace_issue_cmd(ap->regs, &cmd);
+			} else {
+				writel(0, &((ap->regs)->RxJumboPrd));
+				wmb();
+			}
 
 			ap->jumbo = 0;
 			ap->rx_jumbo_skbprd = 0;
@@ -2489,9 +2489,9 @@ restart:
 		}
 	}
 
- 	wmb();
- 	ap->tx_prd = idx;
- 	ace_set_txprd(regs, ap, idx);
+	wmb();
+	ap->tx_prd = idx;
+	ace_set_txprd(regs, ap, idx);
 
 	if (flagsize & BD_FLG_COAL_NOW) {
 		netif_stop_queue(dev);
diff --git a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
index 4164eacc5c28..f5ec35fa4c63 100644
--- a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
@@ -1042,8 +1042,6 @@ enum ena_admin_aenq_group {
 };
 
 enum ena_admin_aenq_notification_syndrome {
-	ENA_ADMIN_SUSPEND                           = 0,
-	ENA_ADMIN_RESUME                            = 1,
 	ENA_ADMIN_UPDATE_HINTS                      = 2,
 };
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 764852ead1d6..ab413fc1f68e 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -1979,7 +1979,8 @@ int ena_com_get_dev_attr_feat(struct ena_com_dev *ena_dev,
 		if (rc)
 			return rc;
 
-		if (get_resp.u.max_queue_ext.version != ENA_FEATURE_MAX_QUEUE_EXT_VER)
+		if (get_resp.u.max_queue_ext.version !=
+		    ENA_FEATURE_MAX_QUEUE_EXT_VER)
 			return -EINVAL;
 
 		memcpy(&get_feat_ctx->max_queue_ext, &get_resp.u.max_queue_ext,
diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
index c3be751e7379..3d6f0a466a9e 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
@@ -151,11 +151,14 @@ static int ena_com_close_bounce_buffer(struct ena_com_io_sq *io_sq)
 		return 0;
 
 	/* bounce buffer was used, so write it and get a new one */
-	if (pkt_ctrl->idx) {
+	if (likely(pkt_ctrl->idx)) {
 		rc = ena_com_write_bounce_buffer_to_dev(io_sq,
 							pkt_ctrl->curr_bounce_buf);
-		if (unlikely(rc))
+		if (unlikely(rc)) {
+			netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device,
+				   "Failed to write bounce buffer to device\n");
 			return rc;
+		}
 
 		pkt_ctrl->curr_bounce_buf =
 			ena_com_get_next_bounce_buffer(&io_sq->bounce_buf_ctrl);
@@ -185,8 +188,11 @@ static int ena_com_sq_update_llq_tail(struct ena_com_io_sq *io_sq)
 	if (!pkt_ctrl->descs_left_in_line) {
 		rc = ena_com_write_bounce_buffer_to_dev(io_sq,
 							pkt_ctrl->curr_bounce_buf);
-		if (unlikely(rc))
+		if (unlikely(rc)) {
+			netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device,
+				   "Failed to write bounce buffer to device\n");
 			return rc;
+		}
 
 		pkt_ctrl->curr_bounce_buf =
 			ena_com_get_next_bounce_buffer(&io_sq->bounce_buf_ctrl);
@@ -406,8 +412,11 @@ int ena_com_prepare_tx(struct ena_com_io_sq *io_sq,
 	}
 
 	if (unlikely(io_sq->mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV &&
-		     !buffer_to_push))
+		     !buffer_to_push)) {
+		netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device,
+			   "Push header wasn't provided in LLQ mode\n");
 		return -EINVAL;
+	}
 
 	rc = ena_com_write_header_to_bounce(io_sq, buffer_to_push, header_len);
 	if (unlikely(rc))
@@ -423,6 +432,9 @@ int ena_com_prepare_tx(struct ena_com_io_sq *io_sq,
 	/* If the caller doesn't want to send packets */
 	if (unlikely(!num_bufs && !header_len)) {
 		rc = ena_com_close_bounce_buffer(io_sq);
+		if (rc)
+			netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device,
+				   "Failed to write buffers to LLQ\n");
 		*nb_hw_desc = io_sq->tail - start_tail;
 		return rc;
 	}
@@ -482,8 +494,11 @@ int ena_com_prepare_tx(struct ena_com_io_sq *io_sq,
 		/* The first desc share the same desc as the header */
 		if (likely(i != 0)) {
 			rc = ena_com_sq_update_tail(io_sq);
-			if (unlikely(rc))
+			if (unlikely(rc)) {
+				netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device,
+					   "Failed to update sq tail\n");
 				return rc;
+			}
 
 			desc = get_sq_desc(io_sq);
 			if (unlikely(!desc))
@@ -512,8 +527,11 @@ int ena_com_prepare_tx(struct ena_com_io_sq *io_sq,
 	desc->len_ctrl |= ENA_ETH_IO_TX_DESC_LAST_MASK;
 
 	rc = ena_com_sq_update_tail(io_sq);
-	if (unlikely(rc))
+	if (unlikely(rc)) {
+		netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device,
+			   "Failed to update sq tail of the last descriptor\n");
 		return rc;
+	}
 
 	rc = ena_com_close_bounce_buffer(io_sq);
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index 2fe7ccee55b2..27dae632efcb 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -233,10 +233,13 @@ int ena_get_sset_count(struct net_device *netdev, int sset)
 {
 	struct ena_adapter *adapter = netdev_priv(netdev);
 
-	if (sset != ETH_SS_STATS)
-		return -EOPNOTSUPP;
+	switch (sset) {
+	case ETH_SS_STATS:
+		return ena_get_sw_stats_count(adapter) +
+		       ena_get_hw_stats_count(adapter);
+	}
 
-	return ena_get_sw_stats_count(adapter) + ena_get_hw_stats_count(adapter);
+	return -EOPNOTSUPP;
 }
 
 static void ena_queue_strings(struct ena_adapter *adapter, u8 **data)
@@ -314,10 +317,11 @@ static void ena_get_ethtool_strings(struct net_device *netdev,
 {
 	struct ena_adapter *adapter = netdev_priv(netdev);
 
-	if (sset != ETH_SS_STATS)
-		return;
-
-	ena_get_strings(adapter, data, adapter->eni_stats_supported);
+	switch (sset) {
+	case ETH_SS_STATS:
+		ena_get_strings(adapter, data, adapter->eni_stats_supported);
+		break;
+	}
 }
 
 static int ena_get_link_ksettings(struct net_device *netdev,
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 52571486705e..edaf37823c50 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -35,9 +35,6 @@ MODULE_LICENSE("GPL");
 
 #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_IFUP | \
 		NETIF_MSG_TX_DONE | NETIF_MSG_TX_ERR | NETIF_MSG_RX_ERR)
-static int debug = -1;
-module_param(debug, int, 0);
-MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
 
 static struct ena_aenq_handlers aenq_handlers;
 
@@ -89,6 +86,12 @@ static void ena_increase_stat(u64 *statp, u64 cnt,
 	u64_stats_update_end(syncp);
 }
 
+static void ena_ring_tx_doorbell(struct ena_ring *tx_ring)
+{
+	ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq);
+	ena_increase_stat(&tx_ring->tx_stats.doorbells, 1, &tx_ring->syncp);
+}
+
 static void ena_tx_timeout(struct net_device *dev, unsigned int txqueue)
 {
 	struct ena_adapter *adapter = netdev_priv(dev);
@@ -147,7 +150,7 @@ static int ena_xmit_common(struct net_device *dev,
 		netif_dbg(adapter, tx_queued, dev,
 			  "llq tx max burst size of queue %d achieved, writing doorbell to send burst\n",
 			  ring->qid);
-		ena_com_write_sq_doorbell(ring->ena_com_io_sq);
+		ena_ring_tx_doorbell(ring);
 	}
 
 	/* prepare the packet's descriptors to dma engine */
@@ -197,7 +200,6 @@ static int ena_xdp_io_poll(struct napi_struct *napi, int budget)
 	int ret;
 
 	xdp_ring = ena_napi->xdp_ring;
-	xdp_ring->first_interrupt = ena_napi->first_interrupt;
 
 	xdp_budget = budget;
 
@@ -229,6 +231,7 @@ static int ena_xdp_io_poll(struct napi_struct *napi, int budget)
 	xdp_ring->tx_stats.napi_comp += napi_comp_call;
 	xdp_ring->tx_stats.tx_poll++;
 	u64_stats_update_end(&xdp_ring->syncp);
+	xdp_ring->tx_stats.last_napi_jiffies = jiffies;
 
 	return ret;
 }
@@ -318,14 +321,12 @@ static int ena_xdp_xmit_frame(struct ena_ring *xdp_ring,
 			     xdpf->len);
 	if (rc)
 		goto error_unmap_dma;
-	/* trigger the dma engine. ena_com_write_sq_doorbell()
-	 * has a mb
+
+	/* trigger the dma engine. ena_ring_tx_doorbell()
+	 * calls a memory barrier inside it.
 	 */
-	if (flags & XDP_XMIT_FLUSH) {
-		ena_com_write_sq_doorbell(xdp_ring->ena_com_io_sq);
-		ena_increase_stat(&xdp_ring->tx_stats.doorbells, 1,
-				  &xdp_ring->syncp);
-	}
+	if (flags & XDP_XMIT_FLUSH)
+		ena_ring_tx_doorbell(xdp_ring);
 
 	return rc;
 
@@ -366,11 +367,8 @@ static int ena_xdp_xmit(struct net_device *dev, int n,
 	}
 
 	/* Ring doorbell to make device aware of the packets */
-	if (flags & XDP_XMIT_FLUSH) {
-		ena_com_write_sq_doorbell(xdp_ring->ena_com_io_sq);
-		ena_increase_stat(&xdp_ring->tx_stats.doorbells, 1,
-				  &xdp_ring->syncp);
-	}
+	if (flags & XDP_XMIT_FLUSH)
+		ena_ring_tx_doorbell(xdp_ring);
 
 	spin_unlock(&xdp_ring->xdp_tx_lock);
 
@@ -385,7 +383,6 @@ static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp)
 	u32 verdict = XDP_PASS;
 	struct xdp_frame *xdpf;
 	u64 *xdp_stat;
-	int qid;
 
 	rcu_read_lock();
 	xdp_prog = READ_ONCE(rx_ring->xdp_bpf_prog);
@@ -406,8 +403,7 @@ static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp)
 		}
 
 		/* Find xmit queue */
-		qid = rx_ring->qid + rx_ring->adapter->num_io_queues;
-		xdp_ring = &rx_ring->adapter->tx_ring[qid];
+		xdp_ring = rx_ring->xdp_ring;
 
 		/* The XDP queues are shared between XDP_TX and XDP_REDIRECT */
 		spin_lock(&xdp_ring->xdp_tx_lock);
@@ -534,7 +530,7 @@ static void ena_xdp_exchange_program_rx_in_range(struct ena_adapter *adapter,
 			rx_ring->rx_headroom = XDP_PACKET_HEADROOM;
 		} else {
 			ena_xdp_unregister_rxq_info(rx_ring);
-			rx_ring->rx_headroom = 0;
+			rx_ring->rx_headroom = NET_SKB_PAD;
 		}
 	}
 }
@@ -683,7 +679,6 @@ static void ena_init_io_rings_common(struct ena_adapter *adapter,
 	ring->ena_dev = adapter->ena_dev;
 	ring->per_napi_packets = 0;
 	ring->cpu = 0;
-	ring->first_interrupt = false;
 	ring->no_interrupt_event_cnt = 0;
 	u64_stats_init(&ring->syncp);
 }
@@ -726,7 +721,9 @@ static void ena_init_io_rings(struct ena_adapter *adapter,
 			rxr->smoothed_interval =
 				ena_com_get_nonadaptive_moderation_interval_rx(ena_dev);
 			rxr->empty_rx_queue = 0;
+			rxr->rx_headroom = NET_SKB_PAD;
 			adapter->ena_napi[i].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+			rxr->xdp_ring = &adapter->tx_ring[i + adapter->num_io_queues];
 		}
 	}
 }
@@ -980,47 +977,66 @@ static void ena_free_all_io_rx_resources(struct ena_adapter *adapter)
 		ena_free_rx_resources(adapter, i);
 }
 
-static int ena_alloc_rx_page(struct ena_ring *rx_ring,
-				    struct ena_rx_buffer *rx_info, gfp_t gfp)
+static struct page *ena_alloc_map_page(struct ena_ring *rx_ring,
+				       dma_addr_t *dma)
 {
-	int headroom = rx_ring->rx_headroom;
-	struct ena_com_buf *ena_buf;
 	struct page *page;
-	dma_addr_t dma;
 
-	/* restore page offset value in case it has been changed by device */
-	rx_info->page_offset = headroom;
-
-	/* if previous allocated page is not used */
-	if (unlikely(rx_info->page))
-		return 0;
-
-	page = alloc_page(gfp);
-	if (unlikely(!page)) {
+	/* This would allocate the page on the same NUMA node the executing code
+	 * is running on.
+	 */
+	page = dev_alloc_page();
+	if (!page) {
 		ena_increase_stat(&rx_ring->rx_stats.page_alloc_fail, 1,
 				  &rx_ring->syncp);
-		return -ENOMEM;
+		return ERR_PTR(-ENOSPC);
 	}
 
 	/* To enable NIC-side port-mirroring, AKA SPAN port,
 	 * we make the buffer readable from the nic as well
 	 */
-	dma = dma_map_page(rx_ring->dev, page, 0, ENA_PAGE_SIZE,
-			   DMA_BIDIRECTIONAL);
-	if (unlikely(dma_mapping_error(rx_ring->dev, dma))) {
+	*dma = dma_map_page(rx_ring->dev, page, 0, ENA_PAGE_SIZE,
+			    DMA_BIDIRECTIONAL);
+	if (unlikely(dma_mapping_error(rx_ring->dev, *dma))) {
 		ena_increase_stat(&rx_ring->rx_stats.dma_mapping_err, 1,
 				  &rx_ring->syncp);
-
 		__free_page(page);
-		return -EIO;
+		return ERR_PTR(-EIO);
 	}
+
+	return page;
+}
+
+static int ena_alloc_rx_buffer(struct ena_ring *rx_ring,
+			       struct ena_rx_buffer *rx_info)
+{
+	int headroom = rx_ring->rx_headroom;
+	struct ena_com_buf *ena_buf;
+	struct page *page;
+	dma_addr_t dma;
+	int tailroom;
+
+	/* restore page offset value in case it has been changed by device */
+	rx_info->page_offset = headroom;
+
+	/* if previous allocated page is not used */
+	if (unlikely(rx_info->page))
+		return 0;
+
+	/* We handle DMA here */
+	page = ena_alloc_map_page(rx_ring, &dma);
+	if (unlikely(IS_ERR(page)))
+		return PTR_ERR(page);
+
 	netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev,
 		  "Allocate page %p, rx_info %p\n", page, rx_info);
 
+	tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
 	rx_info->page = page;
 	ena_buf = &rx_info->ena_buf;
 	ena_buf->paddr = dma + headroom;
-	ena_buf->len = ENA_PAGE_SIZE - headroom;
+	ena_buf->len = ENA_PAGE_SIZE - headroom - tailroom;
 
 	return 0;
 }
@@ -1067,8 +1083,7 @@ static int ena_refill_rx_bufs(struct ena_ring *rx_ring, u32 num)
 
 		rx_info = &rx_ring->rx_buffer_info[req_id];
 
-		rc = ena_alloc_rx_page(rx_ring, rx_info,
-				       GFP_ATOMIC | __GFP_COMP);
+		rc = ena_alloc_rx_buffer(rx_ring, rx_info);
 		if (unlikely(rc < 0)) {
 			netif_warn(rx_ring->adapter, rx_err, rx_ring->netdev,
 				   "Failed to allocate buffer for rx queue %d\n",
@@ -1386,21 +1401,23 @@ static int ena_clean_tx_irq(struct ena_ring *tx_ring, u32 budget)
 	return tx_pkts;
 }
 
-static struct sk_buff *ena_alloc_skb(struct ena_ring *rx_ring, bool frags)
+static struct sk_buff *ena_alloc_skb(struct ena_ring *rx_ring, void *first_frag)
 {
 	struct sk_buff *skb;
 
-	if (frags)
-		skb = napi_get_frags(rx_ring->napi);
-	else
+	if (!first_frag)
 		skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
 						rx_ring->rx_copybreak);
+	else
+		skb = build_skb(first_frag, ENA_PAGE_SIZE);
 
 	if (unlikely(!skb)) {
 		ena_increase_stat(&rx_ring->rx_stats.skb_alloc_fail, 1,
 				  &rx_ring->syncp);
+
 		netif_dbg(rx_ring->adapter, rx_err, rx_ring->netdev,
-			  "Failed to allocate skb. frags: %d\n", frags);
+			  "Failed to allocate skb. first_frag %s\n",
+			  first_frag ? "provided" : "not provided");
 		return NULL;
 	}
 
@@ -1412,10 +1429,12 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 				  u32 descs,
 				  u16 *next_to_clean)
 {
-	struct sk_buff *skb;
 	struct ena_rx_buffer *rx_info;
 	u16 len, req_id, buf = 0;
-	void *va;
+	struct sk_buff *skb;
+	void *page_addr;
+	u32 page_offset;
+	void *data_addr;
 
 	len = ena_bufs[buf].len;
 	req_id = ena_bufs[buf].req_id;
@@ -1433,12 +1452,14 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 		  rx_info, rx_info->page);
 
 	/* save virt address of first buffer */
-	va = page_address(rx_info->page) + rx_info->page_offset;
+	page_addr = page_address(rx_info->page);
+	page_offset = rx_info->page_offset;
+	data_addr = page_addr + page_offset;
 
-	prefetch(va);
+	prefetch(data_addr);
 
 	if (len <= rx_ring->rx_copybreak) {
-		skb = ena_alloc_skb(rx_ring, false);
+		skb = ena_alloc_skb(rx_ring, NULL);
 		if (unlikely(!skb))
 			return NULL;
 
@@ -1451,7 +1472,7 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 					dma_unmap_addr(&rx_info->ena_buf, paddr),
 					len,
 					DMA_FROM_DEVICE);
-		skb_copy_to_linear_data(skb, va, len);
+		skb_copy_to_linear_data(skb, data_addr, len);
 		dma_sync_single_for_device(rx_ring->dev,
 					   dma_unmap_addr(&rx_info->ena_buf, paddr),
 					   len,
@@ -1465,16 +1486,18 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 		return skb;
 	}
 
-	skb = ena_alloc_skb(rx_ring, true);
+	ena_unmap_rx_buff(rx_ring, rx_info);
+
+	skb = ena_alloc_skb(rx_ring, page_addr);
 	if (unlikely(!skb))
 		return NULL;
 
-	do {
-		ena_unmap_rx_buff(rx_ring, rx_info);
-
-		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_info->page,
-				rx_info->page_offset, len, ENA_PAGE_SIZE);
+	/* Populate skb's linear part */
+	skb_reserve(skb, page_offset);
+	skb_put(skb, len);
+	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 
+	do {
 		netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev,
 			  "RX skb updated. len %d. data_len %d\n",
 			  skb->len, skb->data_len);
@@ -1493,6 +1516,12 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 		req_id = ena_bufs[buf].req_id;
 
 		rx_info = &rx_ring->rx_buffer_info[req_id];
+
+		ena_unmap_rx_buff(rx_ring, rx_info);
+
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_info->page,
+				rx_info->page_offset, len, ENA_PAGE_SIZE);
+
 	} while (1);
 
 	return skb;
@@ -1705,14 +1734,12 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 
 		skb_record_rx_queue(skb, rx_ring->qid);
 
-		if (rx_ring->ena_bufs[0].len <= rx_ring->rx_copybreak) {
-			total_len += rx_ring->ena_bufs[0].len;
+		if (rx_ring->ena_bufs[0].len <= rx_ring->rx_copybreak)
 			rx_copybreak_pkt++;
-			napi_gro_receive(napi, skb);
-		} else {
-			total_len += skb->len;
-			napi_gro_frags(napi);
-		}
+
+		total_len += skb->len;
+
+		napi_gro_receive(napi, skb);
 
 		res_budget--;
 	} while (likely(res_budget));
@@ -1924,9 +1951,6 @@ static int ena_io_poll(struct napi_struct *napi, int budget)
 	tx_ring = ena_napi->tx_ring;
 	rx_ring = ena_napi->rx_ring;
 
-	tx_ring->first_interrupt = ena_napi->first_interrupt;
-	rx_ring->first_interrupt = ena_napi->first_interrupt;
-
 	tx_budget = tx_ring->ring_size / ENA_TX_POLL_BUDGET_DIVIDER;
 
 	if (!test_bit(ENA_FLAG_DEV_UP, &tx_ring->adapter->flags) ||
@@ -1981,6 +2005,8 @@ static int ena_io_poll(struct napi_struct *napi, int budget)
 	tx_ring->tx_stats.tx_poll++;
 	u64_stats_update_end(&tx_ring->syncp);
 
+	tx_ring->tx_stats.last_napi_jiffies = jiffies;
+
 	return ret;
 }
 
@@ -2005,7 +2031,8 @@ static irqreturn_t ena_intr_msix_io(int irq, void *data)
 {
 	struct ena_napi *ena_napi = data;
 
-	ena_napi->first_interrupt = true;
+	/* Used to check HW health */
+	WRITE_ONCE(ena_napi->first_interrupt, true);
 
 	WRITE_ONCE(ena_napi->interrupts_masked, true);
 	smp_wmb(); /* write interrupts_masked before calling napi */
@@ -3091,14 +3118,11 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 
-	if (netif_xmit_stopped(txq) || !netdev_xmit_more()) {
-		/* trigger the dma engine. ena_com_write_sq_doorbell()
-		 * has a mb
+	if (netif_xmit_stopped(txq) || !netdev_xmit_more())
+		/* trigger the dma engine. ena_ring_tx_doorbell()
+		 * calls a memory barrier inside it.
 		 */
-		ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq);
-		ena_increase_stat(&tx_ring->tx_stats.doorbells, 1,
-				  &tx_ring->syncp);
-	}
+		ena_ring_tx_doorbell(tx_ring);
 
 	return NETDEV_TX_OK;
 
@@ -3348,7 +3372,7 @@ static int ena_set_queues_placement_policy(struct pci_dev *pdev,
 
 	llq_feature_mask = 1 << ENA_ADMIN_LLQ;
 	if (!(ena_dev->supported_features & llq_feature_mask)) {
-		dev_err(&pdev->dev,
+		dev_warn(&pdev->dev,
 			"LLQ is not supported Fallback to host mode policy.\n");
 		ena_dev->tx_mem_queue_type = ENA_ADMIN_PLACEMENT_POLICY_HOST;
 		return 0;
@@ -3659,7 +3683,9 @@ static void ena_fw_reset_device(struct work_struct *work)
 static int check_for_rx_interrupt_queue(struct ena_adapter *adapter,
 					struct ena_ring *rx_ring)
 {
-	if (likely(rx_ring->first_interrupt))
+	struct ena_napi *ena_napi = container_of(rx_ring->napi, struct ena_napi, napi);
+
+	if (likely(READ_ONCE(ena_napi->first_interrupt)))
 		return 0;
 
 	if (ena_com_cq_empty(rx_ring->ena_com_io_cq))
@@ -3683,6 +3709,10 @@ static int check_for_rx_interrupt_queue(struct ena_adapter *adapter,
 static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter,
 					  struct ena_ring *tx_ring)
 {
+	struct ena_napi *ena_napi = container_of(tx_ring->napi, struct ena_napi, napi);
+	unsigned int time_since_last_napi;
+	unsigned int missing_tx_comp_to;
+	bool is_tx_comp_time_expired;
 	struct ena_tx_buffer *tx_buf;
 	unsigned long last_jiffies;
 	u32 missed_tx = 0;
@@ -3696,8 +3726,10 @@ static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter,
 			/* no pending Tx at this location */
 			continue;
 
-		if (unlikely(!tx_ring->first_interrupt && time_is_before_jiffies(last_jiffies +
-			     2 * adapter->missing_tx_completion_to))) {
+		is_tx_comp_time_expired = time_is_before_jiffies(last_jiffies +
+			 2 * adapter->missing_tx_completion_to);
+
+		if (unlikely(!READ_ONCE(ena_napi->first_interrupt) && is_tx_comp_time_expired)) {
 			/* If after graceful period interrupt is still not
 			 * received, we schedule a reset
 			 */
@@ -3710,12 +3742,17 @@ static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter,
 			return -EIO;
 		}
 
-		if (unlikely(time_is_before_jiffies(last_jiffies +
-				adapter->missing_tx_completion_to))) {
-			if (!tx_buf->print_once)
+		is_tx_comp_time_expired = time_is_before_jiffies(last_jiffies +
+			adapter->missing_tx_completion_to);
+
+		if (unlikely(is_tx_comp_time_expired)) {
+			if (!tx_buf->print_once) {
+				time_since_last_napi = jiffies_to_usecs(jiffies - tx_ring->tx_stats.last_napi_jiffies);
+				missing_tx_comp_to = jiffies_to_msecs(adapter->missing_tx_completion_to);
 				netif_notice(adapter, tx_err, adapter->netdev,
-					     "Found a Tx that wasn't completed on time, qid %d, index %d.\n",
-					     tx_ring->qid, i);
+					     "Found a Tx that wasn't completed on time, qid %d, index %d. %u usecs have passed since last napi execution. Missing Tx timeout value %u msecs\n",
+					     tx_ring->qid, i, time_since_last_napi, missing_tx_comp_to);
+			}
 
 			tx_buf->print_once = 1;
 			missed_tx++;
@@ -4246,7 +4283,7 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	adapter->ena_dev = ena_dev;
 	adapter->netdev = netdev;
 	adapter->pdev = pdev;
-	adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
+	adapter->msg_enable = DEFAULT_MSG_ENABLE;
 
 	ena_dev->net_device = netdev;
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 74af15d62ee1..0c39fc2fa345 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -55,12 +55,6 @@
 #define ENA_TX_WAKEUP_THRESH		(MAX_SKB_FRAGS + 2)
 #define ENA_DEFAULT_RX_COPYBREAK	(256 - NET_IP_ALIGN)
 
-/* limit the buffer size to 600 bytes to handle MTU changes from very
- * small to very large, in which case the number of buffers per packet
- * could exceed ENA_PKT_MAX_BUFS
- */
-#define ENA_DEFAULT_MIN_RX_BUFF_ALLOC_SIZE 600
-
 #define ENA_MIN_MTU		128
 
 #define ENA_NAME_MAX_LEN	20
@@ -135,12 +129,12 @@ struct ena_irq {
 };
 
 struct ena_napi {
-	struct napi_struct napi ____cacheline_aligned;
+	u8 first_interrupt ____cacheline_aligned;
+	u8 interrupts_masked;
+	struct napi_struct napi;
 	struct ena_ring *tx_ring;
 	struct ena_ring *rx_ring;
 	struct ena_ring *xdp_ring;
-	bool first_interrupt;
-	bool interrupts_masked;
 	u32 qid;
 	struct dim dim;
 };
@@ -212,6 +206,7 @@ struct ena_stats_tx {
 	u64 llq_buffer_copy;
 	u64 missed_tx;
 	u64 unmask_interrupt;
+	u64 last_napi_jiffies;
 };
 
 struct ena_stats_rx {
@@ -259,6 +254,10 @@ struct ena_ring {
 	struct bpf_prog *xdp_bpf_prog;
 	struct xdp_rxq_info xdp_rxq;
 	spinlock_t xdp_tx_lock;	/* synchronize XDP TX/Redirect traffic */
+	/* Used for rx queues only to point to the xdp tx ring, to
+	 * which traffic should be redirected from this rx ring.
+	 */
+	struct ena_ring *xdp_ring;
 
 	u16 next_to_use;
 	u16 next_to_clean;
@@ -271,7 +270,6 @@ struct ena_ring {
 	/* The maximum header length the device can handle */
 	u8 tx_max_header_size;
 
-	bool first_interrupt;
 	bool disable_meta_caching;
 	u16 no_interrupt_event_cnt;
 
@@ -414,11 +412,6 @@ enum ena_xdp_errors_t {
 	ENA_XDP_NO_ENOUGH_QUEUES,
 };
 
-static inline bool ena_xdp_queues_present(struct ena_adapter *adapter)
-{
-	return adapter->xdp_first_ring != 0;
-}
-
 static inline bool ena_xdp_present(struct ena_adapter *adapter)
 {
 	return !!adapter->xdp_bpf_prog;
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index 4a1220cc6f10..9cac5aa75a73 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -19,14 +19,14 @@ Module Name:
 
 Abstract:
 
- 	 AMD8111 based 10/100 Ethernet Controller Driver.
+	 AMD8111 based 10/100 Ethernet Controller Driver.
 
 Environment:
 
 	Kernel Mode
 
 Revision History:
- 	3.0.0
+	3.0.0
 	   Initial Revision.
 	3.0.1
 	 1. Dynamic interrupt coalescing.
diff --git a/drivers/net/ethernet/amd/amd8111e.h b/drivers/net/ethernet/amd/amd8111e.h
index 493f154eccf4..37da79da5f5e 100644
--- a/drivers/net/ethernet/amd/amd8111e.h
+++ b/drivers/net/ethernet/amd/amd8111e.h
@@ -10,14 +10,14 @@ Module Name:
 
 Abstract:
 
- 	 AMD8111 based 10/100 Ethernet Controller driver definitions.
+	 AMD8111 based 10/100 Ethernet Controller driver definitions.
 
 Environment:
 
 	Kernel Mode
 
 Revision History:
- 	3.0.0
+	3.0.0
 	   Initial Revision.
 	3.0.1
 */
@@ -692,7 +692,7 @@ enum coal_type{
 };
 
 enum coal_mode{
-       	RX_INTR_COAL,
+	RX_INTR_COAL,
 	TX_INTR_COAL,
 	DISABLE_COAL,
 	ENABLE_COAL,
diff --git a/drivers/net/ethernet/amd/atarilance.c b/drivers/net/ethernet/amd/atarilance.c
index c1eab916438f..36f54d13a2eb 100644
--- a/drivers/net/ethernet/amd/atarilance.c
+++ b/drivers/net/ethernet/amd/atarilance.c
@@ -706,7 +706,7 @@ static void lance_init_ring( struct net_device *dev )
 		CHECK_OFFSET(offset);
 		MEM->tx_head[i].base = offset;
 		MEM->tx_head[i].flag = TMD1_OWN_HOST;
- 		MEM->tx_head[i].base_hi = 0;
+		MEM->tx_head[i].base_hi = 0;
 		MEM->tx_head[i].length = 0;
 		MEM->tx_head[i].misc = 0;
 		offset += PKT_BUF_SZ;
diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c
index 7282ce55ffb8..493b0cefcc2a 100644
--- a/drivers/net/ethernet/amd/declance.c
+++ b/drivers/net/ethernet/amd/declance.c
@@ -937,7 +937,7 @@ static netdev_tx_t lance_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	dev_kfree_skb(skb);
 
- 	return NETDEV_TX_OK;
+	return NETDEV_TX_OK;
 }
 
 static void lance_load_multicast(struct net_device *dev)
diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c
index aff44241988c..2178e6b89dbd 100644
--- a/drivers/net/ethernet/amd/lance.c
+++ b/drivers/net/ethernet/amd/lance.c
@@ -780,7 +780,7 @@ lance_open(struct net_device *dev)
 		outw(0x0002, ioaddr+LANCE_ADDR);
 		/* Only touch autoselect bit. */
 		outw(inw(ioaddr+LANCE_BUS_IF) | 0x0002, ioaddr+LANCE_BUS_IF);
- 	}
+	}
 
 	if (lance_debug > 1)
 		printk("%s: lance_open() irq %d dma %d tx/rx rings %#x/%#x init %#x.\n",
@@ -812,7 +812,7 @@ lance_open(struct net_device *dev)
 	 * We used to clear the InitDone bit, 0x0100, here but Mark Stockton
 	 * reports that doing so triggers a bug in the '974.
 	 */
- 	outw(0x0042, ioaddr+LANCE_DATA);
+	outw(0x0042, ioaddr+LANCE_DATA);
 
 	if (lance_debug > 2)
 		printk("%s: LANCE open after %d ticks, init block %#x csr0 %4.4x.\n",
diff --git a/drivers/net/ethernet/amd/ni65.c b/drivers/net/ethernet/amd/ni65.c
index c38edf6f03a3..5c1cfb0c4a42 100644
--- a/drivers/net/ethernet/amd/ni65.c
+++ b/drivers/net/ethernet/amd/ni65.c
@@ -193,7 +193,7 @@ static struct card {
 		.vendor_id   = ni_vendor,
 		.cardname    = "ni6510",
 		.config	     = 0x1,
-       	},
+	},
 	{
 		.id0	     = NI65_EB_ID0,
 		.id1	     = NI65_EB_ID1,
@@ -204,7 +204,7 @@ static struct card {
 		.vendor_id   = ni_vendor,
 		.cardname    = "ni6510 EtherBlaster",
 		.config	     = 0x2,
-       	},
+	},
 	{
 		.id0	     = NE2100_ID0,
 		.id1	     = NE2100_ID1,
@@ -1232,15 +1232,15 @@ MODULE_PARM_DESC(dma, "ni6510 ISA DMA channel (ignored for some cards)");
 
 int __init init_module(void)
 {
- 	dev_ni65 = ni65_probe(-1);
+	dev_ni65 = ni65_probe(-1);
 	return PTR_ERR_OR_ZERO(dev_ni65);
 }
 
 void __exit cleanup_module(void)
 {
- 	unregister_netdev(dev_ni65);
- 	cleanup_card(dev_ni65);
- 	free_netdev(dev_ni65);
+	unregister_netdev(dev_ni65);
+	cleanup_card(dev_ni65);
+	free_netdev(dev_ni65);
 }
 #endif /* MODULE */
 
diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c
index 11c0b13edd30..4019cab87505 100644
--- a/drivers/net/ethernet/amd/nmclan_cs.c
+++ b/drivers/net/ethernet/amd/nmclan_cs.c
@@ -541,7 +541,7 @@ static int mace_init(mace_private *lp, unsigned int ioaddr, char *enet_addr)
     if(++ct > 500)
     {
 	pr_err("reset failed, card removed?\n");
-    	return -1;
+	return -1;
     }
     udelay(1);
   }
@@ -585,11 +585,11 @@ static int mace_init(mace_private *lp, unsigned int ioaddr, char *enet_addr)
   ct = 0;
   while (mace_read(lp, ioaddr, MACE_IAC) & MACE_IAC_ADDRCHG)
   {
-  	if(++ ct > 500)
-  	{
+	if(++ ct > 500)
+	{
 		pr_err("ADDRCHG timeout, card removed?\n");
-  		return -1;
-  	}
+		return -1;
+	}
   }
   /* Set PADR register */
   for (i = 0; i < ETH_ALEN; i++)
@@ -655,7 +655,7 @@ static int nmclan_config(struct pcmcia_device *link)
   }
 
   if(mace_init(lp, ioaddr, dev->dev_addr) == -1)
-  	goto failed;
+	goto failed;
 
   /* The if_port symbol can be set when the module is loaded */
   if (if_port <= 2)
diff --git a/drivers/net/ethernet/amd/sun3lance.c b/drivers/net/ethernet/amd/sun3lance.c
index 00ae1081254d..f8d7a9387a56 100644
--- a/drivers/net/ethernet/amd/sun3lance.c
+++ b/drivers/net/ethernet/amd/sun3lance.c
@@ -150,7 +150,7 @@ struct lance_memory {
 struct lance_private {
 	volatile unsigned short	*iobase;
 	struct lance_memory	*mem;
-     	int new_rx, new_tx;	/* The next free ring entry */
+	int new_rx, new_tx;	/* The next free ring entry */
 	int old_tx, old_rx;     /* ring entry to be processed */
 /* These two must be longs for set_bit() */
 	long	    tx_full;
@@ -465,7 +465,7 @@ static void lance_init_ring( struct net_device *dev )
 	for( i = 0; i < TX_RING_SIZE; i++ ) {
 		MEM->tx_head[i].base = dvma_vtob(MEM->tx_data[i]);
 		MEM->tx_head[i].flag = 0;
- 		MEM->tx_head[i].base_hi =
+		MEM->tx_head[i].base_hi =
 			(dvma_vtob(MEM->tx_data[i])) >>16;
 		MEM->tx_head[i].length = 0;
 		MEM->tx_head[i].misc = 0;
@@ -581,8 +581,8 @@ lance_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	AREG = CSR0;
-  	DPRINTK( 2, ( "%s: lance_start_xmit() called, csr0 %4.4x.\n",
-  				  dev->name, DREG ));
+	DPRINTK( 2, ( "%s: lance_start_xmit() called, csr0 %4.4x.\n",
+				  dev->name, DREG ));
 
 #ifdef CONFIG_SUN3X
 	/* this weirdness doesn't appear on sun3... */
@@ -636,8 +636,8 @@ lance_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Trigger an immediate send poll. */
 	REGA(CSR0) = CSR0_INEA | CSR0_TDMD | CSR0_STRT;
 	AREG = CSR0;
-  	DPRINTK( 2, ( "%s: lance_start_xmit() exiting, csr0 %4.4x.\n",
-  				  dev->name, DREG ));
+	DPRINTK( 2, ( "%s: lance_start_xmit() exiting, csr0 %4.4x.\n",
+				  dev->name, DREG ));
 	dev_kfree_skb(skb);
 
 	lp->lock = 0;
diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c
index 1e4e402f07d7..a989d2df59ad 100644
--- a/drivers/net/ethernet/apple/bmac.c
+++ b/drivers/net/ethernet/apple/bmac.c
@@ -477,26 +477,26 @@ static int bmac_suspend(struct macio_dev *mdev, pm_message_t state)
 		config = bmread(dev, RXCFG);
 		bmwrite(dev, RXCFG, (config & ~RxMACEnable));
 		config = bmread(dev, TXCFG);
-       		bmwrite(dev, TXCFG, (config & ~TxMACEnable));
+		bmwrite(dev, TXCFG, (config & ~TxMACEnable));
 		bmwrite(dev, INTDISABLE, DisableAll); /* disable all intrs */
-       		/* disable rx and tx dma */
+		/* disable rx and tx dma */
 		rd->control = cpu_to_le32(DBDMA_CLEAR(RUN|PAUSE|FLUSH|WAKE));	/* clear run bit */
 		td->control = cpu_to_le32(DBDMA_CLEAR(RUN|PAUSE|FLUSH|WAKE));	/* clear run bit */
-       		/* free some skb's */
-       		for (i=0; i<N_RX_RING; i++) {
-       			if (bp->rx_bufs[i] != NULL) {
-       				dev_kfree_skb(bp->rx_bufs[i]);
-       				bp->rx_bufs[i] = NULL;
-       			}
-       		}
-       		for (i = 0; i<N_TX_RING; i++) {
+		/* free some skb's */
+		for (i=0; i<N_RX_RING; i++) {
+			if (bp->rx_bufs[i] != NULL) {
+				dev_kfree_skb(bp->rx_bufs[i]);
+				bp->rx_bufs[i] = NULL;
+			}
+		}
+		for (i = 0; i<N_TX_RING; i++) {
 			if (bp->tx_bufs[i] != NULL) {
 		       		dev_kfree_skb(bp->tx_bufs[i]);
 	       			bp->tx_bufs[i] = NULL;
 		       	}
 		}
 	}
-       	pmac_call_feature(PMAC_FTR_BMAC_ENABLE, macio_get_of_node(bp->mdev), 0, 0);
+	pmac_call_feature(PMAC_FTR_BMAC_ENABLE, macio_get_of_node(bp->mdev), 0, 0);
 	return 0;
 }
 
@@ -510,9 +510,9 @@ static int bmac_resume(struct macio_dev *mdev)
 		bmac_reset_and_enable(dev);
 
 	enable_irq(dev->irq);
-       	enable_irq(bp->tx_dma_intr);
-       	enable_irq(bp->rx_dma_intr);
-       	netif_device_attach(dev);
+	enable_irq(bp->tx_dma_intr);
+	enable_irq(bp->rx_dma_intr);
+	netif_device_attach(dev);
 
 	return 0;
 }
@@ -1599,7 +1599,7 @@ static int bmac_remove(struct macio_dev *mdev)
 
 	unregister_netdev(dev);
 
-       	free_irq(dev->irq, dev);
+	free_irq(dev->irq, dev);
 	free_irq(bp->tx_dma_intr, dev);
 	free_irq(bp->rx_dma_intr, dev);
 
diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c
index 9e5006e59215..4b80e3a52a19 100644
--- a/drivers/net/ethernet/apple/mace.c
+++ b/drivers/net/ethernet/apple/mace.c
@@ -364,9 +364,9 @@ static void mace_reset(struct net_device *dev)
 	out_8(&mb->iac, 0);
 
     if (mp->port_aaui)
-    	out_8(&mb->plscc, PORTSEL_AUI + ENPLSIO);
+	out_8(&mb->plscc, PORTSEL_AUI + ENPLSIO);
     else
-    	out_8(&mb->plscc, PORTSEL_GPSI + ENPLSIO);
+	out_8(&mb->plscc, PORTSEL_GPSI + ENPLSIO);
 }
 
 static void __mace_set_address(struct net_device *dev, void *addr)
@@ -378,9 +378,9 @@ static void __mace_set_address(struct net_device *dev, void *addr)
 
     /* load up the hardware address */
     if (mp->chipid == BROKEN_ADDRCHG_REV)
-    	out_8(&mb->iac, PHYADDR);
+	out_8(&mb->iac, PHYADDR);
     else {
-    	out_8(&mb->iac, ADDRCHG | PHYADDR);
+	out_8(&mb->iac, ADDRCHG | PHYADDR);
 	while ((in_8(&mb->iac) & ADDRCHG) != 0)
 	    ;
     }
diff --git a/drivers/net/ethernet/arc/emac_rockchip.c b/drivers/net/ethernet/arc/emac_rockchip.c
index 48ecdf15eddc..1c9ca3bcb871 100644
--- a/drivers/net/ethernet/arc/emac_rockchip.c
+++ b/drivers/net/ethernet/arc/emac_rockchip.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
-/**
+/*
  * emac-rockchip.c - Rockchip EMAC specific glue layer
  *
  * Copyright (C) 2014 Romain Perier <romain.perier@gmail.com>
diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h
index 9d0e74f6b089..693006c5a498 100644
--- a/drivers/net/ethernet/atheros/alx/alx.h
+++ b/drivers/net/ethernet/atheros/alx/alx.h
@@ -137,6 +137,8 @@ struct alx_priv {
 
 	/* protects hw.stats */
 	spinlock_t stats_lock;
+
+	struct mutex mtx;
 };
 
 extern const struct ethtool_ops alx_ethtool_ops;
diff --git a/drivers/net/ethernet/atheros/alx/ethtool.c b/drivers/net/ethernet/atheros/alx/ethtool.c
index 2f4eabf652e8..b716adacd815 100644
--- a/drivers/net/ethernet/atheros/alx/ethtool.c
+++ b/drivers/net/ethernet/atheros/alx/ethtool.c
@@ -163,8 +163,10 @@ static int alx_get_link_ksettings(struct net_device *netdev,
 		}
 	}
 
+	mutex_lock(&alx->mtx);
 	cmd->base.speed = hw->link_speed;
 	cmd->base.duplex = hw->duplex;
+	mutex_unlock(&alx->mtx);
 
 	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
 						supported);
@@ -181,8 +183,7 @@ static int alx_set_link_ksettings(struct net_device *netdev,
 	struct alx_hw *hw = &alx->hw;
 	u32 adv_cfg;
 	u32 advertising;
-
-	ASSERT_RTNL();
+	int ret;
 
 	ethtool_convert_link_mode_to_legacy_u32(&advertising,
 						cmd->link_modes.advertising);
@@ -200,7 +201,12 @@ static int alx_set_link_ksettings(struct net_device *netdev,
 	}
 
 	hw->adv_cfg = adv_cfg;
-	return alx_setup_speed_duplex(hw, adv_cfg, hw->flowctrl);
+
+	mutex_lock(&alx->mtx);
+	ret = alx_setup_speed_duplex(hw, adv_cfg, hw->flowctrl);
+	mutex_unlock(&alx->mtx);
+
+	return ret;
 }
 
 static void alx_get_pauseparam(struct net_device *netdev,
@@ -209,10 +215,12 @@ static void alx_get_pauseparam(struct net_device *netdev,
 	struct alx_priv *alx = netdev_priv(netdev);
 	struct alx_hw *hw = &alx->hw;
 
+	mutex_lock(&alx->mtx);
 	pause->autoneg = !!(hw->flowctrl & ALX_FC_ANEG &&
 			    hw->adv_cfg & ADVERTISED_Autoneg);
 	pause->tx_pause = !!(hw->flowctrl & ALX_FC_TX);
 	pause->rx_pause = !!(hw->flowctrl & ALX_FC_RX);
+	mutex_unlock(&alx->mtx);
 }
 
 
@@ -232,7 +240,7 @@ static int alx_set_pauseparam(struct net_device *netdev,
 	if (pause->autoneg)
 		fc |= ALX_FC_ANEG;
 
-	ASSERT_RTNL();
+	mutex_lock(&alx->mtx);
 
 	/* restart auto-neg for auto-mode */
 	if (hw->adv_cfg & ADVERTISED_Autoneg) {
@@ -245,8 +253,10 @@ static int alx_set_pauseparam(struct net_device *netdev,
 
 	if (reconfig_phy) {
 		err = alx_setup_speed_duplex(hw, hw->adv_cfg, fc);
-		if (err)
+		if (err) {
+			mutex_unlock(&alx->mtx);
 			return err;
+		}
 	}
 
 	/* flow control on mac */
@@ -254,6 +264,7 @@ static int alx_set_pauseparam(struct net_device *netdev,
 		alx_cfg_mac_flowcontrol(hw, fc);
 
 	hw->flowctrl = fc;
+	mutex_unlock(&alx->mtx);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 7748b276e5fd..11ef1fbe7aee 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2013 Johannes Berg <johannes@sipsolutions.net>
+ * Copyright (c) 2013, 2021 Johannes Berg <johannes@sipsolutions.net>
  *
  *  This file is free software: you may copy, redistribute and/or modify it
  *  under the terms of the GNU General Public License as published by the
@@ -1091,8 +1091,9 @@ static int alx_init_sw(struct alx_priv *alx)
 		      ALX_MAC_CTRL_RXFC_EN |
 		      ALX_MAC_CTRL_TXFC_EN |
 		      7 << ALX_MAC_CTRL_PRMBLEN_SHIFT;
+	mutex_init(&alx->mtx);
 
-	return err;
+	return 0;
 }
 
 
@@ -1122,6 +1123,8 @@ static void alx_halt(struct alx_priv *alx)
 {
 	struct alx_hw *hw = &alx->hw;
 
+	lockdep_assert_held(&alx->mtx);
+
 	alx_netif_stop(alx);
 	hw->link_speed = SPEED_UNKNOWN;
 	hw->duplex = DUPLEX_UNKNOWN;
@@ -1147,6 +1150,8 @@ static void alx_configure(struct alx_priv *alx)
 
 static void alx_activate(struct alx_priv *alx)
 {
+	lockdep_assert_held(&alx->mtx);
+
 	/* hardware setting lost, restore it */
 	alx_reinit_rings(alx);
 	alx_configure(alx);
@@ -1161,7 +1166,7 @@ static void alx_activate(struct alx_priv *alx)
 
 static void alx_reinit(struct alx_priv *alx)
 {
-	ASSERT_RTNL();
+	lockdep_assert_held(&alx->mtx);
 
 	alx_halt(alx);
 	alx_activate(alx);
@@ -1249,6 +1254,8 @@ out_disable_adv_intr:
 
 static void __alx_stop(struct alx_priv *alx)
 {
+	lockdep_assert_held(&alx->mtx);
+
 	alx_free_irq(alx);
 
 	cancel_work_sync(&alx->link_check_wk);
@@ -1284,6 +1291,8 @@ static void alx_check_link(struct alx_priv *alx)
 	int old_speed;
 	int err;
 
+	lockdep_assert_held(&alx->mtx);
+
 	/* clear PHY internal interrupt status, otherwise the main
 	 * interrupt status will be asserted forever
 	 */
@@ -1338,12 +1347,24 @@ reset:
 
 static int alx_open(struct net_device *netdev)
 {
-	return __alx_open(netdev_priv(netdev), false);
+	struct alx_priv *alx = netdev_priv(netdev);
+	int ret;
+
+	mutex_lock(&alx->mtx);
+	ret = __alx_open(alx, false);
+	mutex_unlock(&alx->mtx);
+
+	return ret;
 }
 
 static int alx_stop(struct net_device *netdev)
 {
-	__alx_stop(netdev_priv(netdev));
+	struct alx_priv *alx = netdev_priv(netdev);
+
+	mutex_lock(&alx->mtx);
+	__alx_stop(alx);
+	mutex_unlock(&alx->mtx);
+
 	return 0;
 }
 
@@ -1353,18 +1374,18 @@ static void alx_link_check(struct work_struct *work)
 
 	alx = container_of(work, struct alx_priv, link_check_wk);
 
-	rtnl_lock();
+	mutex_lock(&alx->mtx);
 	alx_check_link(alx);
-	rtnl_unlock();
+	mutex_unlock(&alx->mtx);
 }
 
 static void alx_reset(struct work_struct *work)
 {
 	struct alx_priv *alx = container_of(work, struct alx_priv, reset_wk);
 
-	rtnl_lock();
+	mutex_lock(&alx->mtx);
 	alx_reinit(alx);
-	rtnl_unlock();
+	mutex_unlock(&alx->mtx);
 }
 
 static int alx_tpd_req(struct sk_buff *skb)
@@ -1771,6 +1792,8 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto out_unmap;
 	}
 
+	mutex_lock(&alx->mtx);
+
 	alx_reset_pcie(hw);
 
 	phy_configured = alx_phy_configured(hw);
@@ -1781,7 +1804,7 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	err = alx_reset_mac(hw);
 	if (err) {
 		dev_err(&pdev->dev, "MAC Reset failed, error = %d\n", err);
-		goto out_unmap;
+		goto out_unlock;
 	}
 
 	/* setup link to put it in a known good starting state */
@@ -1791,7 +1814,7 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			dev_err(&pdev->dev,
 				"failed to configure PHY speed/duplex (err=%d)\n",
 				err);
-			goto out_unmap;
+			goto out_unlock;
 		}
 	}
 
@@ -1824,9 +1847,11 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!alx_get_phy_info(hw)) {
 		dev_err(&pdev->dev, "failed to identify PHY\n");
 		err = -EIO;
-		goto out_unmap;
+		goto out_unlock;
 	}
 
+	mutex_unlock(&alx->mtx);
+
 	INIT_WORK(&alx->link_check_wk, alx_link_check);
 	INIT_WORK(&alx->reset_wk, alx_reset);
 	netif_carrier_off(netdev);
@@ -1843,6 +1868,8 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	return 0;
 
+out_unlock:
+	mutex_unlock(&alx->mtx);
 out_unmap:
 	iounmap(hw->hw_addr);
 out_free_netdev:
@@ -1870,6 +1897,8 @@ static void alx_remove(struct pci_dev *pdev)
 	pci_disable_pcie_error_reporting(pdev);
 	pci_disable_device(pdev);
 
+	mutex_destroy(&alx->mtx);
+
 	free_netdev(alx->dev);
 }
 
@@ -1881,7 +1910,11 @@ static int alx_suspend(struct device *dev)
 	if (!netif_running(alx->dev))
 		return 0;
 	netif_device_detach(alx->dev);
+
+	mutex_lock(&alx->mtx);
 	__alx_stop(alx);
+	mutex_unlock(&alx->mtx);
+
 	return 0;
 }
 
@@ -1891,20 +1924,23 @@ static int alx_resume(struct device *dev)
 	struct alx_hw *hw = &alx->hw;
 	int err;
 
+	mutex_lock(&alx->mtx);
 	alx_reset_phy(hw);
 
-	if (!netif_running(alx->dev))
-		return 0;
+	if (!netif_running(alx->dev)) {
+		err = 0;
+		goto unlock;
+	}
 
-	rtnl_lock();
 	err = __alx_open(alx, true);
-	rtnl_unlock();
 	if (err)
-		return err;
+		goto unlock;
 
 	netif_device_attach(alx->dev);
 
-	return 0;
+unlock:
+	mutex_unlock(&alx->mtx);
+	return err;
 }
 
 static SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume);
@@ -1923,7 +1959,7 @@ static pci_ers_result_t alx_pci_error_detected(struct pci_dev *pdev,
 
 	dev_info(&pdev->dev, "pci error detected\n");
 
-	rtnl_lock();
+	mutex_lock(&alx->mtx);
 
 	if (netif_running(netdev)) {
 		netif_device_detach(netdev);
@@ -1935,7 +1971,7 @@ static pci_ers_result_t alx_pci_error_detected(struct pci_dev *pdev,
 	else
 		pci_disable_device(pdev);
 
-	rtnl_unlock();
+	mutex_unlock(&alx->mtx);
 
 	return rc;
 }
@@ -1948,7 +1984,7 @@ static pci_ers_result_t alx_pci_error_slot_reset(struct pci_dev *pdev)
 
 	dev_info(&pdev->dev, "pci error slot reset\n");
 
-	rtnl_lock();
+	mutex_lock(&alx->mtx);
 
 	if (pci_enable_device(pdev)) {
 		dev_err(&pdev->dev, "Failed to re-enable PCI device after reset\n");
@@ -1961,7 +1997,7 @@ static pci_ers_result_t alx_pci_error_slot_reset(struct pci_dev *pdev)
 	if (!alx_reset_mac(hw))
 		rc = PCI_ERS_RESULT_RECOVERED;
 out:
-	rtnl_unlock();
+	mutex_unlock(&alx->mtx);
 
 	return rc;
 }
@@ -1973,14 +2009,14 @@ static void alx_pci_error_resume(struct pci_dev *pdev)
 
 	dev_info(&pdev->dev, "pci error resume\n");
 
-	rtnl_lock();
+	mutex_lock(&alx->mtx);
 
 	if (netif_running(netdev)) {
 		alx_activate(alx);
 		netif_device_attach(netdev);
 	}
 
-	rtnl_unlock();
+	mutex_unlock(&alx->mtx);
 }
 
 static const struct pci_error_handlers alx_err_handlers = {
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c.h b/drivers/net/ethernet/atheros/atl1c/atl1c.h
index 28ae5c16831e..43d821fe7a54 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c.h
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c.h
@@ -63,7 +63,7 @@
 
 #define AT_MAX_RECEIVE_QUEUE    4
 #define AT_DEF_RECEIVE_QUEUE	1
-#define AT_MAX_TRANSMIT_QUEUE	2
+#define AT_MAX_TRANSMIT_QUEUE  4
 
 #define AT_DMA_HI_ADDR_MASK     0xffffffff00000000ULL
 #define AT_DMA_LO_ADDR_MASK     0x00000000ffffffffULL
@@ -241,6 +241,8 @@ struct atl1c_tpd_ext_desc {
 #define RRS_PACKET_PROT_IS_IPV6_ONLY(word) \
 	((((word) >> RRS_PROT_ID_SHIFT) & RRS_PROT_ID_MASK) == 6)
 
+#define RRS_MT_PROT_ID_TCPUDP	BIT(19)
+
 struct atl1c_recv_ret_status {
 	__le32  word0;
 	__le32	rss_hash;
@@ -289,11 +291,7 @@ enum atl1c_nic_type {
 	athr_l2c_b2,
 	athr_l1d,
 	athr_l1d_2,
-};
-
-enum atl1c_trans_queue {
-	atl1c_trans_normal = 0,
-	atl1c_trans_high = 1
+	athr_mt,
 };
 
 struct atl1c_hw_stats {
@@ -472,13 +470,16 @@ struct atl1c_buffer {
 
 /* transimit packet descriptor (tpd) ring */
 struct atl1c_tpd_ring {
+	struct atl1c_adapter *adapter;
 	void *desc;		/* descriptor ring virtual address */
 	dma_addr_t dma;		/* descriptor ring physical address */
+	u16 num;
 	u16 size;		/* descriptor ring length in bytes */
 	u16 count;		/* number of descriptors in the ring */
 	u16 next_to_use;
 	atomic_t next_to_clean;
 	struct atl1c_buffer *buffer_info;
+	struct napi_struct napi;
 };
 
 /* receive free descriptor (rfd) ring */
@@ -494,27 +495,30 @@ struct atl1c_rfd_ring {
 
 /* receive return descriptor (rrd) ring */
 struct atl1c_rrd_ring {
+	struct atl1c_adapter *adapter;
 	void *desc;		/* descriptor ring virtual address */
 	dma_addr_t dma;		/* descriptor ring physical address */
+	u16 num;
 	u16 size;		/* descriptor ring length in bytes */
 	u16 count;		/* number of descriptors in the ring */
 	u16 next_to_use;
 	u16 next_to_clean;
+	struct napi_struct napi;
+	struct page *rx_page;
+	unsigned int rx_page_offset;
 };
 
 /* board specific private data structure */
 struct atl1c_adapter {
 	struct net_device   *netdev;
 	struct pci_dev      *pdev;
-	struct napi_struct  napi;
-	struct napi_struct  tx_napi;
-	struct page         *rx_page;
-	unsigned int	    rx_page_offset;
 	unsigned int	    rx_frag_size;
 	struct atl1c_hw        hw;
 	struct atl1c_hw_stats  hw_stats;
 	struct mii_if_info  mii;    /* MII interface info */
 	u16 rx_buffer_len;
+	unsigned int tx_queue_count;
+	unsigned int rx_queue_count;
 
 	unsigned long flags;
 #define __AT_TESTING        0x0001
@@ -540,8 +544,8 @@ struct atl1c_adapter {
 	/* All Descriptor memory */
 	struct atl1c_ring_header ring_header;
 	struct atl1c_tpd_ring tpd_ring[AT_MAX_TRANSMIT_QUEUE];
-	struct atl1c_rfd_ring rfd_ring;
-	struct atl1c_rrd_ring rrd_ring;
+	struct atl1c_rfd_ring rfd_ring[AT_MAX_RECEIVE_QUEUE];
+	struct atl1c_rrd_ring rrd_ring[AT_MAX_RECEIVE_QUEUE];
 	u32 bd_number;     /* board number;*/
 };
 
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c
index 140358dcf61e..7dff20350865 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c
@@ -636,6 +636,23 @@ int atl1c_phy_init(struct atl1c_hw *hw)
 	return 0;
 }
 
+bool atl1c_get_link_status(struct atl1c_hw *hw)
+{
+	u16 phy_data;
+
+	if (hw->nic_type == athr_mt) {
+		u32 spd;
+
+		AT_READ_REG(hw, REG_MT_SPEED, &spd);
+		return !!spd;
+	}
+
+	/* MII_BMSR must be read twice */
+	atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
+	atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
+	return !!(phy_data & BMSR_LSTATUS);
+}
+
 /*
  * Detects the current speed and duplex settings of the hardware.
  *
@@ -648,6 +665,15 @@ int atl1c_get_speed_and_duplex(struct atl1c_hw *hw, u16 *speed, u16 *duplex)
 	int err;
 	u16 phy_data;
 
+	if (hw->nic_type == athr_mt) {
+		u32 spd;
+
+		AT_READ_REG(hw, REG_MT_SPEED, &spd);
+		*speed = spd;
+		*duplex = FULL_DUPLEX;
+		return 0;
+	}
+
 	/* Read   PHY Specific Status Register (17) */
 	err = atl1c_read_phy_reg(hw, MII_GIGA_PSSR, &phy_data);
 	if (err)
@@ -686,15 +712,12 @@ int atl1c_phy_to_ps_link(struct atl1c_hw *hw)
 	int ret = 0;
 	u16 autoneg_advertised = ADVERTISED_10baseT_Half;
 	u16 save_autoneg_advertised;
-	u16 phy_data;
 	u16 mii_lpa_data;
 	u16 speed = SPEED_0;
 	u16 duplex = FULL_DUPLEX;
 	int i;
 
-	atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
-	atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
-	if (phy_data & BMSR_LSTATUS) {
+	if (atl1c_get_link_status(hw)) {
 		atl1c_read_phy_reg(hw, MII_LPA, &mii_lpa_data);
 		if (mii_lpa_data & LPA_10FULL)
 			autoneg_advertised = ADVERTISED_10baseT_Full;
@@ -717,9 +740,7 @@ int atl1c_phy_to_ps_link(struct atl1c_hw *hw)
 		if (mii_lpa_data) {
 			for (i = 0; i < AT_SUSPEND_LINK_TIMEOUT; i++) {
 				mdelay(100);
-				atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
-				atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
-				if (phy_data & BMSR_LSTATUS) {
+				if (atl1c_get_link_status(hw)) {
 					if (atl1c_get_speed_and_duplex(hw, &speed,
 									&duplex) != 0)
 						dev_dbg(&pdev->dev,
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
index ce1a123dce2c..c567c920628f 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
@@ -26,6 +26,7 @@ void atl1c_phy_disable(struct atl1c_hw *hw);
 void atl1c_hw_set_mac_addr(struct atl1c_hw *hw, u8 *mac_addr);
 int atl1c_phy_reset(struct atl1c_hw *hw);
 int atl1c_read_mac_addr(struct atl1c_hw *hw);
+bool atl1c_get_link_status(struct atl1c_hw *hw);
 int atl1c_get_speed_and_duplex(struct atl1c_hw *hw, u16 *speed, u16 *duplex);
 u32 atl1c_hash_mc_addr(struct atl1c_hw *hw, u8 *mc_addr);
 void atl1c_hash_set(struct atl1c_hw *hw, u32 hash_value);
@@ -527,15 +528,24 @@ void atl1c_post_phy_linkchg(struct atl1c_hw *hw, u16 link_speed);
 #define REG_RX_BASE_ADDR_HI		0x1540
 #define REG_TX_BASE_ADDR_HI		0x1544
 #define REG_RFD0_HEAD_ADDR_LO		0x1550
+#define REG_RFD1_HEAD_ADDR_LO          0x1554
+#define REG_RFD2_HEAD_ADDR_LO          0x1558
+#define REG_RFD3_HEAD_ADDR_LO          0x155C
 #define REG_RFD_RING_SIZE		0x1560
 #define RFD_RING_SIZE_MASK		0x0FFF
 #define REG_RX_BUF_SIZE			0x1564
 #define RX_BUF_SIZE_MASK		0xFFFF
 #define REG_RRD0_HEAD_ADDR_LO		0x1568
+#define REG_RRD1_HEAD_ADDR_LO          0x156C
+#define REG_RRD2_HEAD_ADDR_LO          0x1570
+#define REG_RRD3_HEAD_ADDR_LO          0x1574
 #define REG_RRD_RING_SIZE		0x1578
 #define RRD_RING_SIZE_MASK		0x0FFF
 #define REG_TPD_PRI1_ADDR_LO		0x157C
 #define REG_TPD_PRI0_ADDR_LO		0x1580
+#define REG_TPD_PRI2_ADDR_LO           0x1F10
+#define REG_TPD_PRI3_ADDR_LO           0x1F14
+
 #define REG_TPD_RING_SIZE		0x1584
 #define TPD_RING_SIZE_MASK		0xFFFF
 
@@ -654,15 +664,26 @@ void atl1c_post_phy_linkchg(struct atl1c_hw *hw, u16 link_speed);
 /* Mail box */
 #define MB_RFDX_PROD_IDX_MASK		0xFFFF
 #define REG_MB_RFD0_PROD_IDX		0x15E0
+#define REG_MB_RFD1_PROD_IDX           0x15E4
+#define REG_MB_RFD2_PROD_IDX           0x15E8
+#define REG_MB_RFD3_PROD_IDX           0x15EC
 
 #define REG_TPD_PRI1_PIDX               0x15F0	/* 16bit,hi-tpd producer idx */
 #define REG_TPD_PRI0_PIDX		0x15F2	/* 16bit,lo-tpd producer idx */
 #define REG_TPD_PRI1_CIDX		0x15F4	/* 16bit,hi-tpd consumer idx */
 #define REG_TPD_PRI0_CIDX		0x15F6	/* 16bit,lo-tpd consumer idx */
+#define REG_TPD_PRI3_PIDX              0x1F18
+#define REG_TPD_PRI2_PIDX              0x1F1A
+#define REG_TPD_PRI3_CIDX              0x1F1C
+#define REG_TPD_PRI2_CIDX              0x1F1E
+
 
 #define REG_MB_RFD01_CONS_IDX		0x15F8
 #define MB_RFD0_CONS_IDX_MASK		0x0000FFFF
 #define MB_RFD1_CONS_IDX_MASK		0xFFFF0000
+#define REG_MB_RFD23_CONS_IDX          0x15FC
+#define MB_RFD2_CONS_IDX_MASK          0x0000FFFF
+#define MB_RFD3_CONS_IDX_MASK          0xFFFF0000
 
 /* Interrupt Status Register */
 #define REG_ISR    			0x1600
@@ -686,7 +707,7 @@ void atl1c_post_phy_linkchg(struct atl1c_hw *hw, u16 link_speed);
 /* GPHY low power state interrupt */
 #define ISR_GPHY_LPW           		0x00002000
 #define ISR_TXQ_TO_RST			0x00004000
-#define ISR_TX_PKT			0x00008000
+#define ISR_TX_PKT_0                   0x00008000
 #define ISR_RX_PKT_0			0x00010000
 #define ISR_RX_PKT_1			0x00020000
 #define ISR_RX_PKT_2			0x00040000
@@ -698,6 +719,9 @@ void atl1c_post_phy_linkchg(struct atl1c_hw *hw, u16 link_speed);
 #define ISR_NFERR_DETECTED		0x01000000
 #define ISR_CERR_DETECTED		0x02000000
 #define ISR_PHY_LINKDOWN		0x04000000
+#define ISR_TX_PKT_1                   0x10000000
+#define ISR_TX_PKT_2                   0x20000000
+#define ISR_TX_PKT_3                   0x40000000
 #define ISR_DIS_INT			0x80000000
 
 /* Interrupt Mask Register */
@@ -712,11 +736,15 @@ void atl1c_post_phy_linkchg(struct atl1c_hw *hw, u16 link_speed);
 		ISR_TXQ_TO_RST  |\
 		ISR_DMAW_TO_RST	|\
 		ISR_GPHY	|\
-		ISR_TX_PKT	|\
-		ISR_RX_PKT_0	|\
 		ISR_GPHY_LPW    |\
 		ISR_PHY_LINKDOWN)
 
+#define ISR_TX_PKT     (			\
+	ISR_TX_PKT_0    |			\
+	ISR_TX_PKT_1    |			\
+	ISR_TX_PKT_2    |			\
+	ISR_TX_PKT_3)
+
 #define ISR_RX_PKT 	(\
 	ISR_RX_PKT_0    |\
 	ISR_RX_PKT_1    |\
@@ -764,6 +792,14 @@ void atl1c_post_phy_linkchg(struct atl1c_hw *hw, u16 link_speed);
 #define REG_DEBUG_DATA0 		0x1900
 #define REG_DEBUG_DATA1 		0x1904
 
+#define REG_MT_MAGIC			0x1F00
+#define REG_MT_MODE			0x1F04
+#define REG_MT_SPEED			0x1F08
+#define REG_MT_VERSION			0x1F0C
+
+#define MT_MAGIC			0xaabb1234
+#define MT_MODE_4Q			BIT(0)
+
 #define L1D_MPW_PHYID1			0xD01C  /* V7 */
 #define L1D_MPW_PHYID2			0xD01D  /* V1-V6 */
 #define L1D_MPW_PHYID3			0xD01E  /* V8 */
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index c6263cf8d3c0..1c6246a5dc22 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -36,18 +36,51 @@ MODULE_AUTHOR("Qualcomm Atheros Inc.");
 MODULE_DESCRIPTION("Qualcomm Atheros 100/1000M Ethernet Network Driver");
 MODULE_LICENSE("GPL");
 
+struct atl1c_qregs {
+	u16 tpd_addr_lo;
+	u16 tpd_prod;
+	u16 tpd_cons;
+	u16 rfd_addr_lo;
+	u16 rrd_addr_lo;
+	u16 rfd_prod;
+	u32 tx_isr;
+	u32 rx_isr;
+};
+
+static struct atl1c_qregs atl1c_qregs[AT_MAX_TRANSMIT_QUEUE] = {
+	{
+		REG_TPD_PRI0_ADDR_LO, REG_TPD_PRI0_PIDX, REG_TPD_PRI0_CIDX,
+		REG_RFD0_HEAD_ADDR_LO, REG_RRD0_HEAD_ADDR_LO,
+		REG_MB_RFD0_PROD_IDX, ISR_TX_PKT_0, ISR_RX_PKT_0
+	},
+	{
+		REG_TPD_PRI1_ADDR_LO, REG_TPD_PRI1_PIDX, REG_TPD_PRI1_CIDX,
+		REG_RFD1_HEAD_ADDR_LO, REG_RRD1_HEAD_ADDR_LO,
+		REG_MB_RFD1_PROD_IDX, ISR_TX_PKT_1, ISR_RX_PKT_1
+	},
+	{
+		REG_TPD_PRI2_ADDR_LO, REG_TPD_PRI2_PIDX, REG_TPD_PRI2_CIDX,
+		REG_RFD2_HEAD_ADDR_LO, REG_RRD2_HEAD_ADDR_LO,
+		REG_MB_RFD2_PROD_IDX, ISR_TX_PKT_2, ISR_RX_PKT_2
+	},
+	{
+		REG_TPD_PRI3_ADDR_LO, REG_TPD_PRI3_PIDX, REG_TPD_PRI3_CIDX,
+		REG_RFD3_HEAD_ADDR_LO, REG_RRD3_HEAD_ADDR_LO,
+		REG_MB_RFD3_PROD_IDX, ISR_TX_PKT_3, ISR_RX_PKT_3
+	},
+};
+
 static int atl1c_stop_mac(struct atl1c_hw *hw);
 static void atl1c_disable_l0s_l1(struct atl1c_hw *hw);
 static void atl1c_set_aspm(struct atl1c_hw *hw, u16 link_speed);
 static void atl1c_start_mac(struct atl1c_adapter *adapter);
-static void atl1c_clean_rx_irq(struct atl1c_adapter *adapter,
-		   int *work_done, int work_to_do);
 static int atl1c_up(struct atl1c_adapter *adapter);
 static void atl1c_down(struct atl1c_adapter *adapter);
 static int atl1c_reset_mac(struct atl1c_hw *hw);
 static void atl1c_reset_dma_ring(struct atl1c_adapter *adapter);
 static int atl1c_configure(struct atl1c_adapter *adapter);
-static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, bool napi_mode);
+static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, u32 queue,
+				 bool napi_mode);
 
 
 static const u32 atl1c_default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE |
@@ -232,15 +265,14 @@ static void atl1c_check_link_status(struct atl1c_adapter *adapter)
 	struct pci_dev    *pdev   = adapter->pdev;
 	int err;
 	unsigned long flags;
-	u16 speed, duplex, phy_data;
+	u16 speed, duplex;
+	bool link;
 
 	spin_lock_irqsave(&adapter->mdio_lock, flags);
-	/* MII_BMSR must read twise */
-	atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
-	atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
+	link = atl1c_get_link_status(hw);
 	spin_unlock_irqrestore(&adapter->mdio_lock, flags);
 
-	if ((phy_data & BMSR_LSTATUS) == 0) {
+	if (!link) {
 		/* link down */
 		netif_carrier_off(netdev);
 		hw->hibernate = true;
@@ -284,16 +316,13 @@ static void atl1c_link_chg_event(struct atl1c_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 	struct pci_dev    *pdev   = adapter->pdev;
-	u16 phy_data;
-	u16 link_up;
+	bool link;
 
 	spin_lock(&adapter->mdio_lock);
-	atl1c_read_phy_reg(&adapter->hw, MII_BMSR, &phy_data);
-	atl1c_read_phy_reg(&adapter->hw, MII_BMSR, &phy_data);
+	link = atl1c_get_link_status(&adapter->hw);
 	spin_unlock(&adapter->mdio_lock);
-	link_up = phy_data & BMSR_LSTATUS;
 	/* notify upper layer link down ASAP */
-	if (!link_up) {
+	if (!link) {
 		if (netif_carrier_ok(netdev)) {
 			/* old link state: Up */
 			netif_carrier_off(netdev);
@@ -436,7 +465,7 @@ static void atl1c_restore_vlan(struct atl1c_adapter *adapter)
 }
 
 /**
- * atl1c_set_mac - Change the Ethernet Address of the NIC
+ * atl1c_set_mac_addr - Change the Ethernet Address of the NIC
  * @netdev: network interface device structure
  * @p: pointer to an address structure
  *
@@ -478,6 +507,9 @@ static void atl1c_set_rxbufsize(struct atl1c_adapter *adapter,
 static netdev_features_t atl1c_fix_features(struct net_device *netdev,
 	netdev_features_t features)
 {
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+	struct atl1c_hw *hw = &adapter->hw;
+
 	/*
 	 * Since there is no support for separate rx/tx vlan accel
 	 * enable/disable make sure tx flag is always in same state as rx.
@@ -487,8 +519,10 @@ static netdev_features_t atl1c_fix_features(struct net_device *netdev,
 	else
 		features &= ~NETIF_F_HW_VLAN_CTAG_TX;
 
-	if (netdev->mtu > MAX_TSO_FRAME_SIZE)
-		features &= ~(NETIF_F_TSO | NETIF_F_TSO6);
+	if (hw->nic_type != athr_mt) {
+		if (netdev->mtu > MAX_TSO_FRAME_SIZE)
+			features &= ~(NETIF_F_TSO | NETIF_F_TSO6);
+	}
 
 	return features;
 }
@@ -515,9 +549,12 @@ static void atl1c_set_max_mtu(struct net_device *netdev)
 	case athr_l1d:
 	case athr_l1d_2:
 		netdev->max_mtu = MAX_JUMBO_FRAME_SIZE -
-				  (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN);
+			(ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN);
+		break;
+	case athr_mt:
+		netdev->max_mtu = 9500;
 		break;
-	/* The 10/100 devices don't support jumbo packets, max_mtu 1500 */
+		/* The 10/100 devices don't support jumbo packets, max_mtu 1500 */
 	default:
 		netdev->max_mtu = ETH_DATA_LEN;
 		break;
@@ -642,29 +679,26 @@ static int atl1c_alloc_queues(struct atl1c_adapter *adapter)
 	return 0;
 }
 
-static void atl1c_set_mac_type(struct atl1c_hw *hw)
+static enum atl1c_nic_type atl1c_get_mac_type(struct pci_dev *pdev,
+					      u8 __iomem *hw_addr)
 {
-	switch (hw->device_id) {
+	switch (pdev->device) {
 	case PCI_DEVICE_ID_ATTANSIC_L2C:
-		hw->nic_type = athr_l2c;
-		break;
+		return athr_l2c;
 	case PCI_DEVICE_ID_ATTANSIC_L1C:
-		hw->nic_type = athr_l1c;
-		break;
+		return athr_l1c;
 	case PCI_DEVICE_ID_ATHEROS_L2C_B:
-		hw->nic_type = athr_l2c_b;
-		break;
+		return athr_l2c_b;
 	case PCI_DEVICE_ID_ATHEROS_L2C_B2:
-		hw->nic_type = athr_l2c_b2;
-		break;
+		return athr_l2c_b2;
 	case PCI_DEVICE_ID_ATHEROS_L1D:
-		hw->nic_type = athr_l1d;
-		break;
+		return athr_l1d;
 	case PCI_DEVICE_ID_ATHEROS_L1D_2_0:
-		hw->nic_type = athr_l1d_2;
-		break;
+		if (readl(hw_addr + REG_MT_MAGIC) == MT_MAGIC)
+			return athr_mt;
+		return athr_l1d_2;
 	default:
-		break;
+		return athr_l1c;
 	}
 }
 
@@ -672,7 +706,6 @@ static int atl1c_setup_mac_funcs(struct atl1c_hw *hw)
 {
 	u32 link_ctrl_data;
 
-	atl1c_set_mac_type(hw);
 	AT_READ_REG(hw, REG_LINK_CTRL, &link_ctrl_data);
 
 	hw->ctrl_flags = ATL1C_INTR_MODRT_ENABLE  |
@@ -763,14 +796,14 @@ static int atl1c_sw_init(struct atl1c_adapter *adapter)
 	struct atl1c_hw *hw   = &adapter->hw;
 	struct pci_dev	*pdev = adapter->pdev;
 	u32 revision;
-
+	int i;
 
 	adapter->wol = 0;
 	device_set_wakeup_enable(&pdev->dev, false);
 	adapter->link_speed = SPEED_0;
 	adapter->link_duplex = FULL_DUPLEX;
 	adapter->tpd_ring[0].count = 1024;
-	adapter->rfd_ring.count = 512;
+	adapter->rfd_ring[0].count = 512;
 
 	hw->vendor_id = pdev->vendor;
 	hw->device_id = pdev->device;
@@ -788,6 +821,10 @@ static int atl1c_sw_init(struct atl1c_adapter *adapter)
 	atl1c_patch_assign(hw);
 
 	hw->intr_mask = IMR_NORMAL_MASK;
+	for (i = 0; i < adapter->tx_queue_count; ++i)
+		hw->intr_mask |= atl1c_qregs[i].tx_isr;
+	for (i = 0; i < adapter->rx_queue_count; ++i)
+		hw->intr_mask |= atl1c_qregs[i].rx_isr;
 	hw->phy_configured = false;
 	hw->preamble_len = 7;
 	hw->max_frame_size = adapter->netdev->mtu;
@@ -847,12 +884,12 @@ static inline void atl1c_clean_buffer(struct pci_dev *pdev,
 /**
  * atl1c_clean_tx_ring - Free Tx-skb
  * @adapter: board private structure
- * @type: type of transmit queue
+ * @queue: idx of transmit queue
  */
 static void atl1c_clean_tx_ring(struct atl1c_adapter *adapter,
-				enum atl1c_trans_queue type)
+				u32 queue)
 {
-	struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[type];
+	struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[queue];
 	struct atl1c_buffer *buffer_info;
 	struct pci_dev *pdev = adapter->pdev;
 	u16 index, ring_count;
@@ -875,11 +912,12 @@ static void atl1c_clean_tx_ring(struct atl1c_adapter *adapter,
 /**
  * atl1c_clean_rx_ring - Free rx-reservation skbs
  * @adapter: board private structure
+ * @queue: idx of transmit queue
  */
-static void atl1c_clean_rx_ring(struct atl1c_adapter *adapter)
+static void atl1c_clean_rx_ring(struct atl1c_adapter *adapter, u32 queue)
 {
-	struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring;
-	struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring;
+	struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring[queue];
+	struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring[queue];
 	struct atl1c_buffer *buffer_info;
 	struct pci_dev *pdev = adapter->pdev;
 	int j;
@@ -902,26 +940,28 @@ static void atl1c_clean_rx_ring(struct atl1c_adapter *adapter)
 static void atl1c_init_ring_ptrs(struct atl1c_adapter *adapter)
 {
 	struct atl1c_tpd_ring *tpd_ring = adapter->tpd_ring;
-	struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring;
-	struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring;
+	struct atl1c_rfd_ring *rfd_ring = adapter->rfd_ring;
+	struct atl1c_rrd_ring *rrd_ring = adapter->rrd_ring;
 	struct atl1c_buffer *buffer_info;
 	int i, j;
 
-	for (i = 0; i < AT_MAX_TRANSMIT_QUEUE; i++) {
+	for (i = 0; i < adapter->tx_queue_count; i++) {
 		tpd_ring[i].next_to_use = 0;
 		atomic_set(&tpd_ring[i].next_to_clean, 0);
 		buffer_info = tpd_ring[i].buffer_info;
 		for (j = 0; j < tpd_ring->count; j++)
 			ATL1C_SET_BUFFER_STATE(&buffer_info[i],
-					ATL1C_BUFFER_FREE);
-	}
-	rfd_ring->next_to_use = 0;
-	rfd_ring->next_to_clean = 0;
-	rrd_ring->next_to_use = 0;
-	rrd_ring->next_to_clean = 0;
-	for (j = 0; j < rfd_ring->count; j++) {
-		buffer_info = &rfd_ring->buffer_info[j];
-		ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_FREE);
+					       ATL1C_BUFFER_FREE);
+	}
+	for (i = 0; i < adapter->rx_queue_count; i++) {
+		rfd_ring[i].next_to_use = 0;
+		rfd_ring[i].next_to_clean = 0;
+		rrd_ring[i].next_to_use = 0;
+		rrd_ring[i].next_to_clean = 0;
+		for (j = 0; j < rfd_ring[i].count; j++) {
+			buffer_info = &rfd_ring[i].buffer_info[j];
+			ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_FREE);
+		}
 	}
 }
 
@@ -934,25 +974,29 @@ static void atl1c_init_ring_ptrs(struct atl1c_adapter *adapter)
 static void atl1c_free_ring_resources(struct atl1c_adapter *adapter)
 {
 	struct pci_dev *pdev = adapter->pdev;
+	int i;
 
 	dma_free_coherent(&pdev->dev, adapter->ring_header.size,
 			  adapter->ring_header.desc, adapter->ring_header.dma);
 	adapter->ring_header.desc = NULL;
 
 	/* Note: just free tdp_ring.buffer_info,
-	*  it contain rfd_ring.buffer_info, do not double free */
+	 * it contain rfd_ring.buffer_info, do not double free
+	 */
 	if (adapter->tpd_ring[0].buffer_info) {
 		kfree(adapter->tpd_ring[0].buffer_info);
 		adapter->tpd_ring[0].buffer_info = NULL;
 	}
-	if (adapter->rx_page) {
-		put_page(adapter->rx_page);
-		adapter->rx_page = NULL;
+	for (i = 0; i < adapter->rx_queue_count; ++i) {
+		if (adapter->rrd_ring[i].rx_page) {
+			put_page(adapter->rrd_ring[i].rx_page);
+			adapter->rrd_ring[i].rx_page = NULL;
+		}
 	}
 }
 
 /**
- * atl1c_setup_mem_resources - allocate Tx / RX descriptor resources
+ * atl1c_setup_ring_resources - allocate Tx / RX descriptor resources
  * @adapter: board private structure
  *
  * Return 0 on success, negative on failure
@@ -961,37 +1005,46 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter)
 {
 	struct pci_dev *pdev = adapter->pdev;
 	struct atl1c_tpd_ring *tpd_ring = adapter->tpd_ring;
-	struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring;
-	struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring;
+	struct atl1c_rfd_ring *rfd_ring = adapter->rfd_ring;
+	struct atl1c_rrd_ring *rrd_ring = adapter->rrd_ring;
 	struct atl1c_ring_header *ring_header = &adapter->ring_header;
+	int tqc = adapter->tx_queue_count;
+	int rqc = adapter->rx_queue_count;
 	int size;
 	int i;
 	int count = 0;
-	int rx_desc_count = 0;
 	u32 offset = 0;
 
-	rrd_ring->count = rfd_ring->count;
-	for (i = 1; i < AT_MAX_TRANSMIT_QUEUE; i++)
+	/* Even though only one tpd queue is actually used, the "high"
+	 * priority tpd queue also gets initialized
+	 */
+	if (tqc == 1)
+		tqc = 2;
+
+	for (i = 1; i < tqc; i++)
 		tpd_ring[i].count = tpd_ring[0].count;
 
-	/* 2 tpd queue, one high priority queue,
-	 * another normal priority queue */
-	size = sizeof(struct atl1c_buffer) * (tpd_ring->count * 2 +
-		rfd_ring->count);
+	size = sizeof(struct atl1c_buffer) * (tpd_ring->count * tqc +
+					      rfd_ring->count * rqc);
 	tpd_ring->buffer_info = kzalloc(size, GFP_KERNEL);
 	if (unlikely(!tpd_ring->buffer_info))
 		goto err_nomem;
 
-	for (i = 0; i < AT_MAX_TRANSMIT_QUEUE; i++) {
-		tpd_ring[i].buffer_info =
-			(tpd_ring->buffer_info + count);
+	for (i = 0; i < tqc; i++) {
+		tpd_ring[i].adapter = adapter;
+		tpd_ring[i].num = i;
+		tpd_ring[i].buffer_info = (tpd_ring->buffer_info + count);
 		count += tpd_ring[i].count;
 	}
 
-	rfd_ring->buffer_info =
-		(tpd_ring->buffer_info + count);
-	count += rfd_ring->count;
-	rx_desc_count += rfd_ring->count;
+	for (i = 0; i < rqc; i++) {
+		rrd_ring[i].adapter = adapter;
+		rrd_ring[i].num = i;
+		rrd_ring[i].count = rfd_ring[0].count;
+		rfd_ring[i].count = rfd_ring[0].count;
+		rfd_ring[i].buffer_info = (tpd_ring->buffer_info + count);
+		count += rfd_ring->count;
+	}
 
 	/*
 	 * real ring DMA buffer
@@ -999,9 +1052,9 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter)
 	 * additional bytes tacked onto the end.
 	 */
 	ring_header->size = size =
-		sizeof(struct atl1c_tpd_desc) * tpd_ring->count * 2 +
-		sizeof(struct atl1c_rx_free_desc) * rx_desc_count +
-		sizeof(struct atl1c_recv_ret_status) * rx_desc_count +
+		sizeof(struct atl1c_tpd_desc) * tpd_ring->count * tqc +
+		sizeof(struct atl1c_rx_free_desc) * rfd_ring->count * rqc +
+		sizeof(struct atl1c_recv_ret_status) * rfd_ring->count * rqc +
 		8 * 4;
 
 	ring_header->desc = dma_alloc_coherent(&pdev->dev, ring_header->size,
@@ -1014,25 +1067,28 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter)
 
 	tpd_ring[0].dma = roundup(ring_header->dma, 8);
 	offset = tpd_ring[0].dma - ring_header->dma;
-	for (i = 0; i < AT_MAX_TRANSMIT_QUEUE; i++) {
+	for (i = 0; i < tqc; i++) {
 		tpd_ring[i].dma = ring_header->dma + offset;
-		tpd_ring[i].desc = (u8 *) ring_header->desc + offset;
+		tpd_ring[i].desc = (u8 *)ring_header->desc + offset;
 		tpd_ring[i].size =
 			sizeof(struct atl1c_tpd_desc) * tpd_ring[i].count;
 		offset += roundup(tpd_ring[i].size, 8);
 	}
-	/* init RFD ring */
-	rfd_ring->dma = ring_header->dma + offset;
-	rfd_ring->desc = (u8 *) ring_header->desc + offset;
-	rfd_ring->size = sizeof(struct atl1c_rx_free_desc) * rfd_ring->count;
-	offset += roundup(rfd_ring->size, 8);
+	for (i = 0; i < rqc; i++) {
+		/* init RFD ring */
+		rfd_ring[i].dma = ring_header->dma + offset;
+		rfd_ring[i].desc = (u8 *)ring_header->desc + offset;
+		rfd_ring[i].size = sizeof(struct atl1c_rx_free_desc) *
+			rfd_ring[i].count;
+		offset += roundup(rfd_ring[i].size, 8);
 
-	/* init RRD ring */
-	rrd_ring->dma = ring_header->dma + offset;
-	rrd_ring->desc = (u8 *) ring_header->desc + offset;
-	rrd_ring->size = sizeof(struct atl1c_recv_ret_status) *
-		rrd_ring->count;
-	offset += roundup(rrd_ring->size, 8);
+		/* init RRD ring */
+		rrd_ring[i].dma = ring_header->dma + offset;
+		rrd_ring[i].desc = (u8 *)ring_header->desc + offset;
+		rrd_ring[i].size = sizeof(struct atl1c_recv_ret_status) *
+			rrd_ring[i].count;
+		offset += roundup(rrd_ring[i].size, 8);
+	}
 
 	return 0;
 
@@ -1044,31 +1100,34 @@ err_nomem:
 static void atl1c_configure_des_ring(struct atl1c_adapter *adapter)
 {
 	struct atl1c_hw *hw = &adapter->hw;
-	struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring;
-	struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring;
-	struct atl1c_tpd_ring *tpd_ring = (struct atl1c_tpd_ring *)
-				adapter->tpd_ring;
+	struct atl1c_rfd_ring *rfd_ring = adapter->rfd_ring;
+	struct atl1c_rrd_ring *rrd_ring = adapter->rrd_ring;
+	struct atl1c_tpd_ring *tpd_ring = adapter->tpd_ring;
+	int i;
+	int tx_queue_count = adapter->tx_queue_count;
+
+	if (tx_queue_count == 1)
+		tx_queue_count = 2;
 
 	/* TPD */
 	AT_WRITE_REG(hw, REG_TX_BASE_ADDR_HI,
-			(u32)((tpd_ring[atl1c_trans_normal].dma &
-				AT_DMA_HI_ADDR_MASK) >> 32));
+		     (u32)((tpd_ring[0].dma & AT_DMA_HI_ADDR_MASK) >> 32));
 	/* just enable normal priority TX queue */
-	AT_WRITE_REG(hw, REG_TPD_PRI0_ADDR_LO,
-			(u32)(tpd_ring[atl1c_trans_normal].dma &
-				AT_DMA_LO_ADDR_MASK));
-	AT_WRITE_REG(hw, REG_TPD_PRI1_ADDR_LO,
-			(u32)(tpd_ring[atl1c_trans_high].dma &
-				AT_DMA_LO_ADDR_MASK));
+	for (i = 0; i < tx_queue_count; i++) {
+		AT_WRITE_REG(hw, atl1c_qregs[i].tpd_addr_lo,
+			     (u32)(tpd_ring[i].dma & AT_DMA_LO_ADDR_MASK));
+	}
 	AT_WRITE_REG(hw, REG_TPD_RING_SIZE,
 			(u32)(tpd_ring[0].count & TPD_RING_SIZE_MASK));
 
 
 	/* RFD */
 	AT_WRITE_REG(hw, REG_RX_BASE_ADDR_HI,
-			(u32)((rfd_ring->dma & AT_DMA_HI_ADDR_MASK) >> 32));
-	AT_WRITE_REG(hw, REG_RFD0_HEAD_ADDR_LO,
-			(u32)(rfd_ring->dma & AT_DMA_LO_ADDR_MASK));
+		     (u32)((rfd_ring->dma & AT_DMA_HI_ADDR_MASK) >> 32));
+	for (i = 0; i < adapter->rx_queue_count; i++) {
+		AT_WRITE_REG(hw, atl1c_qregs[i].rfd_addr_lo,
+			     (u32)(rfd_ring[i].dma & AT_DMA_LO_ADDR_MASK));
+	}
 
 	AT_WRITE_REG(hw, REG_RFD_RING_SIZE,
 			rfd_ring->count & RFD_RING_SIZE_MASK);
@@ -1076,8 +1135,10 @@ static void atl1c_configure_des_ring(struct atl1c_adapter *adapter)
 			adapter->rx_buffer_len & RX_BUF_SIZE_MASK);
 
 	/* RRD */
-	AT_WRITE_REG(hw, REG_RRD0_HEAD_ADDR_LO,
-			(u32)(rrd_ring->dma & AT_DMA_LO_ADDR_MASK));
+	for (i = 0; i < adapter->rx_queue_count; i++) {
+		AT_WRITE_REG(hw, atl1c_qregs[i].rrd_addr_lo,
+			     (u32)(rrd_ring[i].dma & AT_DMA_LO_ADDR_MASK));
+	}
 	AT_WRITE_REG(hw, REG_RRD_RING_SIZE,
 			(rrd_ring->count & RRD_RING_SIZE_MASK));
 
@@ -1358,7 +1419,7 @@ static void atl1c_set_aspm(struct atl1c_hw *hw, u16 link_speed)
 }
 
 /**
- * atl1c_configure - Configure Transmit&Receive Unit after Reset
+ * atl1c_configure_mac - Configure Transmit&Receive Unit after Reset
  * @adapter: board private structure
  *
  * Configure the Tx /Rx unit of the MAC after a reset.
@@ -1430,14 +1491,28 @@ static int atl1c_configure(struct atl1c_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 	int num;
+	int i;
+
+	if (adapter->hw.nic_type == athr_mt) {
+		u32 mode;
+
+		AT_READ_REG(&adapter->hw, REG_MT_MODE, &mode);
+		if (adapter->rx_queue_count == 4)
+			mode |= MT_MODE_4Q;
+		else
+			mode &= ~MT_MODE_4Q;
+		AT_WRITE_REG(&adapter->hw, REG_MT_MODE, mode);
+	}
 
 	atl1c_init_ring_ptrs(adapter);
 	atl1c_set_multi(netdev);
 	atl1c_restore_vlan(adapter);
 
-	num = atl1c_alloc_rx_buffer(adapter, false);
-	if (unlikely(num == 0))
-		return -ENOMEM;
+	for (i = 0; i < adapter->rx_queue_count; ++i) {
+		num = atl1c_alloc_rx_buffer(adapter, i, false);
+		if (unlikely(num == 0))
+			return -ENOMEM;
+	}
 
 	if (atl1c_configure_mac(adapter))
 		return -EIO;
@@ -1533,9 +1608,11 @@ static inline void atl1c_clear_phy_int(struct atl1c_adapter *adapter)
 
 static int atl1c_clean_tx(struct napi_struct *napi, int budget)
 {
-	struct atl1c_adapter *adapter =
-		container_of(napi, struct atl1c_adapter, tx_napi);
-	struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[atl1c_trans_normal];
+	struct atl1c_tpd_ring *tpd_ring =
+		container_of(napi, struct atl1c_tpd_ring, napi);
+	struct atl1c_adapter *adapter = tpd_ring->adapter;
+	struct netdev_queue *txq =
+		netdev_get_tx_queue(napi->dev, tpd_ring->num);
 	struct atl1c_buffer *buffer_info;
 	struct pci_dev *pdev = adapter->pdev;
 	u16 next_to_clean = atomic_read(&tpd_ring->next_to_clean);
@@ -1543,7 +1620,8 @@ static int atl1c_clean_tx(struct napi_struct *napi, int budget)
 	unsigned int total_bytes = 0, total_packets = 0;
 	unsigned long flags;
 
-	AT_READ_REGW(&adapter->hw, REG_TPD_PRI0_CIDX, &hw_next_to_clean);
+	AT_READ_REGW(&adapter->hw, atl1c_qregs[tpd_ring->num].tpd_cons,
+		     &hw_next_to_clean);
 
 	while (next_to_clean != hw_next_to_clean) {
 		buffer_info = &tpd_ring->buffer_info[next_to_clean];
@@ -1557,17 +1635,15 @@ static int atl1c_clean_tx(struct napi_struct *napi, int budget)
 		atomic_set(&tpd_ring->next_to_clean, next_to_clean);
 	}
 
-	netdev_completed_queue(adapter->netdev, total_packets, total_bytes);
+	netdev_tx_completed_queue(txq, total_packets, total_bytes);
 
-	if (netif_queue_stopped(adapter->netdev) &&
-			netif_carrier_ok(adapter->netdev)) {
-		netif_wake_queue(adapter->netdev);
-	}
+	if (netif_tx_queue_stopped(txq) && netif_carrier_ok(adapter->netdev))
+		netif_tx_wake_queue(txq);
 
 	if (total_packets < budget) {
 		napi_complete_done(napi, total_packets);
 		spin_lock_irqsave(&adapter->hw.intr_mask_lock, flags);
-		adapter->hw.intr_mask |= ISR_TX_PKT;
+		adapter->hw.intr_mask |= atl1c_qregs[tpd_ring->num].tx_isr;
 		AT_WRITE_REG(&adapter->hw, REG_IMR, adapter->hw.intr_mask);
 		spin_unlock_irqrestore(&adapter->hw.intr_mask_lock, flags);
 		return total_packets;
@@ -1575,6 +1651,38 @@ static int atl1c_clean_tx(struct napi_struct *napi, int budget)
 	return budget;
 }
 
+static void atl1c_intr_rx_tx(struct atl1c_adapter *adapter, u32 status)
+{
+	struct atl1c_hw *hw = &adapter->hw;
+	u32 intr_mask;
+	int i;
+
+	spin_lock(&hw->intr_mask_lock);
+	intr_mask = hw->intr_mask;
+	for (i = 0; i < adapter->rx_queue_count; ++i) {
+		if (!(status & atl1c_qregs[i].rx_isr))
+			continue;
+		if (napi_schedule_prep(&adapter->rrd_ring[i].napi)) {
+			intr_mask &= ~atl1c_qregs[i].rx_isr;
+			__napi_schedule(&adapter->rrd_ring[i].napi);
+		}
+	}
+	for (i = 0; i < adapter->tx_queue_count; ++i) {
+		if (!(status & atl1c_qregs[i].tx_isr))
+			continue;
+		if (napi_schedule_prep(&adapter->tpd_ring[i].napi)) {
+			intr_mask &= ~atl1c_qregs[i].tx_isr;
+			__napi_schedule(&adapter->tpd_ring[i].napi);
+		}
+	}
+
+	if (hw->intr_mask != intr_mask) {
+		hw->intr_mask = intr_mask;
+		AT_WRITE_REG(hw, REG_IMR, hw->intr_mask);
+	}
+	spin_unlock(&hw->intr_mask_lock);
+}
+
 /**
  * atl1c_intr - Interrupt Handler
  * @irq: interrupt number
@@ -1605,24 +1713,8 @@ static irqreturn_t atl1c_intr(int irq, void *data)
 			atl1c_clear_phy_int(adapter);
 		/* Ack ISR */
 		AT_WRITE_REG(hw, REG_ISR, status | ISR_DIS_INT);
-		if (status & ISR_RX_PKT) {
-			if (likely(napi_schedule_prep(&adapter->napi))) {
-				spin_lock(&hw->intr_mask_lock);
-				hw->intr_mask &= ~ISR_RX_PKT;
-				AT_WRITE_REG(hw, REG_IMR, hw->intr_mask);
-				spin_unlock(&hw->intr_mask_lock);
-				__napi_schedule(&adapter->napi);
-			}
-		}
-		if (status & ISR_TX_PKT) {
-			if (napi_schedule_prep(&adapter->tx_napi)) {
-				spin_lock(&hw->intr_mask_lock);
-				hw->intr_mask &= ~ISR_TX_PKT;
-				AT_WRITE_REG(hw, REG_IMR, hw->intr_mask);
-				spin_unlock(&hw->intr_mask_lock);
-				__napi_schedule(&adapter->tx_napi);
-			}
-		}
+		if (status & (ISR_RX_PKT | ISR_TX_PKT))
+			atl1c_intr_rx_tx(adapter, status);
 
 		handled = IRQ_HANDLED;
 		/* check if PCIE PHY Link down */
@@ -1659,6 +1751,11 @@ static irqreturn_t atl1c_intr(int irq, void *data)
 static inline void atl1c_rx_checksum(struct atl1c_adapter *adapter,
 		  struct sk_buff *skb, struct atl1c_recv_ret_status *prrs)
 {
+	if (adapter->hw.nic_type == athr_mt) {
+		if (prrs->word3 & RRS_MT_PROT_ID_TCPUDP)
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+		return;
+	}
 	/*
 	 * The pid field in RRS in not correct sometimes, so we
 	 * cannot figure out if the packet is fragmented or not,
@@ -1668,44 +1765,47 @@ static inline void atl1c_rx_checksum(struct atl1c_adapter *adapter,
 }
 
 static struct sk_buff *atl1c_alloc_skb(struct atl1c_adapter *adapter,
-				       bool napi_mode)
+				       u32 queue, bool napi_mode)
 {
+	struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring[queue];
 	struct sk_buff *skb;
 	struct page *page;
 
 	if (adapter->rx_frag_size > PAGE_SIZE) {
 		if (likely(napi_mode))
-			return napi_alloc_skb(&adapter->napi,
+			return napi_alloc_skb(&rrd_ring->napi,
 					      adapter->rx_buffer_len);
 		else
 			return netdev_alloc_skb_ip_align(adapter->netdev,
 							 adapter->rx_buffer_len);
 	}
 
-	page = adapter->rx_page;
+	page = rrd_ring->rx_page;
 	if (!page) {
-		adapter->rx_page = page = alloc_page(GFP_ATOMIC);
+		page = alloc_page(GFP_ATOMIC);
 		if (unlikely(!page))
 			return NULL;
-		adapter->rx_page_offset = 0;
+		rrd_ring->rx_page = page;
+		rrd_ring->rx_page_offset = 0;
 	}
 
-	skb = build_skb(page_address(page) + adapter->rx_page_offset,
+	skb = build_skb(page_address(page) + rrd_ring->rx_page_offset,
 			adapter->rx_frag_size);
 	if (likely(skb)) {
 		skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
-		adapter->rx_page_offset += adapter->rx_frag_size;
-		if (adapter->rx_page_offset >= PAGE_SIZE)
-			adapter->rx_page = NULL;
+		rrd_ring->rx_page_offset += adapter->rx_frag_size;
+		if (rrd_ring->rx_page_offset >= PAGE_SIZE)
+			rrd_ring->rx_page = NULL;
 		else
 			get_page(page);
 	}
 	return skb;
 }
 
-static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, bool napi_mode)
+static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, u32 queue,
+				 bool napi_mode)
 {
-	struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring;
+	struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring[queue];
 	struct pci_dev *pdev = adapter->pdev;
 	struct atl1c_buffer *buffer_info, *next_info;
 	struct sk_buff *skb;
@@ -1724,7 +1824,7 @@ static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, bool napi_mode)
 	while (next_info->flags & ATL1C_BUFFER_FREE) {
 		rfd_desc = ATL1C_RFD_DESC(rfd_ring, rfd_next_to_use);
 
-		skb = atl1c_alloc_skb(adapter, napi_mode);
+		skb = atl1c_alloc_skb(adapter, queue, napi_mode);
 		if (unlikely(!skb)) {
 			if (netif_msg_rx_err(adapter))
 				dev_warn(&pdev->dev, "alloc rx buffer failed\n");
@@ -1766,8 +1866,8 @@ static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, bool napi_mode)
 		/* TODO: update mailbox here */
 		wmb();
 		rfd_ring->next_to_use = rfd_next_to_use;
-		AT_WRITE_REG(&adapter->hw, REG_MB_RFD0_PROD_IDX,
-			rfd_ring->next_to_use & MB_RFDX_PROD_IDX_MASK);
+		AT_WRITE_REG(&adapter->hw, atl1c_qregs[queue].rfd_prod,
+			     rfd_ring->next_to_use & MB_RFDX_PROD_IDX_MASK);
 	}
 
 	return num_alloc;
@@ -1805,22 +1905,33 @@ static void atl1c_clean_rfd(struct atl1c_rfd_ring *rfd_ring,
 	rfd_ring->next_to_clean = rfd_index;
 }
 
-static void atl1c_clean_rx_irq(struct atl1c_adapter *adapter,
-		   int *work_done, int work_to_do)
+/**
+ * atl1c_clean_rx - NAPI Rx polling callback
+ * @napi: napi info
+ * @budget: limit of packets to clean
+ */
+static int atl1c_clean_rx(struct napi_struct *napi, int budget)
 {
+	struct atl1c_rrd_ring *rrd_ring =
+		container_of(napi, struct atl1c_rrd_ring, napi);
+	struct atl1c_adapter *adapter = rrd_ring->adapter;
 	u16 rfd_num, rfd_index;
-	u16 count = 0;
 	u16 length;
 	struct pci_dev *pdev = adapter->pdev;
 	struct net_device *netdev  = adapter->netdev;
-	struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring;
-	struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring;
+	struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring[rrd_ring->num];
 	struct sk_buff *skb;
 	struct atl1c_recv_ret_status *rrs;
 	struct atl1c_buffer *buffer_info;
+	int work_done = 0;
+	unsigned long flags;
+
+	/* Keep link state information with original netdev */
+	if (!netif_carrier_ok(adapter->netdev))
+		goto quit_polling;
 
 	while (1) {
-		if (*work_done >= work_to_do)
+		if (work_done >= budget)
 			break;
 		rrs = ATL1C_RRD_DESC(rrd_ring, rrd_ring->next_to_clean);
 		if (likely(RRS_RXD_IS_VALID(rrs->word3))) {
@@ -1874,38 +1985,18 @@ rrs_checked:
 			vlan = le16_to_cpu(vlan);
 			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan);
 		}
-		napi_gro_receive(&adapter->napi, skb);
+		napi_gro_receive(napi, skb);
 
-		(*work_done)++;
-		count++;
+		work_done++;
 	}
-	if (count)
-		atl1c_alloc_rx_buffer(adapter, true);
-}
-
-/**
- * atl1c_clean - NAPI Rx polling callback
- * @napi: napi info
- * @budget: limit of packets to clean
- */
-static int atl1c_clean(struct napi_struct *napi, int budget)
-{
-	struct atl1c_adapter *adapter =
-			container_of(napi, struct atl1c_adapter, napi);
-	int work_done = 0;
-	unsigned long flags;
-
-	/* Keep link state information with original netdev */
-	if (!netif_carrier_ok(adapter->netdev))
-		goto quit_polling;
-	/* just enable one RXQ */
-	atl1c_clean_rx_irq(adapter, &work_done, budget);
+	if (work_done)
+		atl1c_alloc_rx_buffer(adapter, rrd_ring->num, true);
 
 	if (work_done < budget) {
 quit_polling:
 		napi_complete_done(napi, work_done);
 		spin_lock_irqsave(&adapter->hw.intr_mask_lock, flags);
-		adapter->hw.intr_mask |= ISR_RX_PKT;
+		adapter->hw.intr_mask |= atl1c_qregs[rrd_ring->num].rx_isr;
 		AT_WRITE_REG(&adapter->hw, REG_IMR, adapter->hw.intr_mask);
 		spin_unlock_irqrestore(&adapter->hw.intr_mask_lock, flags);
 	}
@@ -1929,9 +2020,9 @@ static void atl1c_netpoll(struct net_device *netdev)
 }
 #endif
 
-static inline u16 atl1c_tpd_avail(struct atl1c_adapter *adapter, enum atl1c_trans_queue type)
+static inline u16 atl1c_tpd_avail(struct atl1c_adapter *adapter, u32 queue)
 {
-	struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[type];
+	struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[queue];
 	u16 next_to_use = 0;
 	u16 next_to_clean = 0;
 
@@ -1949,9 +2040,9 @@ static inline u16 atl1c_tpd_avail(struct atl1c_adapter *adapter, enum atl1c_tran
  * there is enough tpd to use
  */
 static struct atl1c_tpd_desc *atl1c_get_tpd(struct atl1c_adapter *adapter,
-	enum atl1c_trans_queue type)
+					    u32 queue)
 {
-	struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[type];
+	struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[queue];
 	struct atl1c_tpd_desc *tpd_desc;
 	u16 next_to_use = 0;
 
@@ -1993,7 +2084,7 @@ static u16 atl1c_cal_tpd_req(const struct sk_buff *skb)
 static int atl1c_tso_csum(struct atl1c_adapter *adapter,
 			  struct sk_buff *skb,
 			  struct atl1c_tpd_desc **tpd,
-			  enum atl1c_trans_queue type)
+			  u32 queue)
 {
 	struct pci_dev *pdev = adapter->pdev;
 	unsigned short offload_type;
@@ -2038,7 +2129,7 @@ static int atl1c_tso_csum(struct atl1c_adapter *adapter,
 				*(struct atl1c_tpd_ext_desc **)(tpd);
 
 			memset(etpd, 0, sizeof(struct atl1c_tpd_ext_desc));
-			*tpd = atl1c_get_tpd(adapter, type);
+			*tpd = atl1c_get_tpd(adapter, queue);
 			ipv6_hdr(skb)->payload_len = 0;
 			/* check payload == 0 byte ? */
 			hdr_len = (skb_transport_offset(skb) + tcp_hdrlen(skb));
@@ -2090,9 +2181,9 @@ check_sum:
 
 static void atl1c_tx_rollback(struct atl1c_adapter *adpt,
 			      struct atl1c_tpd_desc *first_tpd,
-			      enum atl1c_trans_queue type)
+			      u32 queue)
 {
-	struct atl1c_tpd_ring *tpd_ring = &adpt->tpd_ring[type];
+	struct atl1c_tpd_ring *tpd_ring = &adpt->tpd_ring[queue];
 	struct atl1c_buffer *buffer_info;
 	struct atl1c_tpd_desc *tpd;
 	u16 first_index, index;
@@ -2111,8 +2202,8 @@ static void atl1c_tx_rollback(struct atl1c_adapter *adpt,
 }
 
 static int atl1c_tx_map(struct atl1c_adapter *adapter,
-		      struct sk_buff *skb, struct atl1c_tpd_desc *tpd,
-			enum atl1c_trans_queue type)
+			struct sk_buff *skb, struct atl1c_tpd_desc *tpd,
+			u32 queue)
 {
 	struct atl1c_tpd_desc *use_tpd = NULL;
 	struct atl1c_buffer *buffer_info = NULL;
@@ -2152,7 +2243,7 @@ static int atl1c_tx_map(struct atl1c_adapter *adapter,
 		if (mapped_len == 0)
 			use_tpd = tpd;
 		else {
-			use_tpd = atl1c_get_tpd(adapter, type);
+			use_tpd = atl1c_get_tpd(adapter, queue);
 			memcpy(use_tpd, tpd, sizeof(struct atl1c_tpd_desc));
 		}
 		buffer_info = atl1c_get_tx_buffer(adapter, use_tpd);
@@ -2174,7 +2265,7 @@ static int atl1c_tx_map(struct atl1c_adapter *adapter,
 	for (f = 0; f < nr_frags; f++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[f];
 
-		use_tpd = atl1c_get_tpd(adapter, type);
+		use_tpd = atl1c_get_tpd(adapter, queue);
 		memcpy(use_tpd, tpd, sizeof(struct atl1c_tpd_desc));
 
 		buffer_info = atl1c_get_tx_buffer(adapter, use_tpd);
@@ -2207,23 +2298,22 @@ err_dma:
 	return -1;
 }
 
-static void atl1c_tx_queue(struct atl1c_adapter *adapter, struct sk_buff *skb,
-			   struct atl1c_tpd_desc *tpd, enum atl1c_trans_queue type)
+static void atl1c_tx_queue(struct atl1c_adapter *adapter, u32 queue)
 {
-	struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[type];
-	u16 reg;
+	struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[queue];
 
-	reg = type == atl1c_trans_high ? REG_TPD_PRI1_PIDX : REG_TPD_PRI0_PIDX;
-	AT_WRITE_REGW(&adapter->hw, reg, tpd_ring->next_to_use);
+	AT_WRITE_REGW(&adapter->hw, atl1c_qregs[queue].tpd_prod,
+		      tpd_ring->next_to_use);
 }
 
 static netdev_tx_t atl1c_xmit_frame(struct sk_buff *skb,
 					  struct net_device *netdev)
 {
 	struct atl1c_adapter *adapter = netdev_priv(netdev);
-	u16 tpd_req;
+	u32 queue = skb_get_queue_mapping(skb);
+	struct netdev_queue *txq = netdev_get_tx_queue(netdev, queue);
 	struct atl1c_tpd_desc *tpd;
-	enum atl1c_trans_queue type = atl1c_trans_normal;
+	u16 tpd_req;
 
 	if (test_bit(__AT_DOWN, &adapter->flags)) {
 		dev_kfree_skb_any(skb);
@@ -2232,16 +2322,18 @@ static netdev_tx_t atl1c_xmit_frame(struct sk_buff *skb,
 
 	tpd_req = atl1c_cal_tpd_req(skb);
 
-	if (atl1c_tpd_avail(adapter, type) < tpd_req) {
+	if (atl1c_tpd_avail(adapter, queue) < tpd_req) {
 		/* no enough descriptor, just stop queue */
-		netif_stop_queue(netdev);
+		atl1c_tx_queue(adapter, queue);
+		netif_tx_stop_queue(txq);
 		return NETDEV_TX_BUSY;
 	}
 
-	tpd = atl1c_get_tpd(adapter, type);
+	tpd = atl1c_get_tpd(adapter, queue);
 
 	/* do TSO and check sum */
-	if (atl1c_tso_csum(adapter, skb, &tpd, type) != 0) {
+	if (atl1c_tso_csum(adapter, skb, &tpd, queue) != 0) {
+		atl1c_tx_queue(adapter, queue);
 		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
 	}
@@ -2259,15 +2351,17 @@ static netdev_tx_t atl1c_xmit_frame(struct sk_buff *skb,
 	if (skb_network_offset(skb) != ETH_HLEN)
 		tpd->word1 |= 1 << TPD_ETH_TYPE_SHIFT; /* Ethernet frame */
 
-	if (atl1c_tx_map(adapter, skb, tpd, type) < 0) {
+	if (atl1c_tx_map(adapter, skb, tpd, queue) < 0) {
 		netif_info(adapter, tx_done, adapter->netdev,
 			   "tx-skb dropped due to dma error\n");
 		/* roll back tpd/buffer */
-		atl1c_tx_rollback(adapter, tpd, type);
+		atl1c_tx_rollback(adapter, tpd, queue);
 		dev_kfree_skb_any(skb);
 	} else {
-		netdev_sent_queue(adapter->netdev, skb->len);
-		atl1c_tx_queue(adapter, skb, tpd, type);
+		bool more = netdev_xmit_more();
+
+		if (__netdev_tx_sent_queue(txq, skb->len, more))
+			atl1c_tx_queue(adapter, queue);
 	}
 
 	return NETDEV_TX_OK;
@@ -2321,16 +2415,19 @@ static int atl1c_request_irq(struct atl1c_adapter *adapter)
 
 static void atl1c_reset_dma_ring(struct atl1c_adapter *adapter)
 {
+	int i;
 	/* release tx-pending skbs and reset tx/rx ring index */
-	atl1c_clean_tx_ring(adapter, atl1c_trans_normal);
-	atl1c_clean_tx_ring(adapter, atl1c_trans_high);
-	atl1c_clean_rx_ring(adapter);
+	for (i = 0; i < adapter->tx_queue_count; ++i)
+		atl1c_clean_tx_ring(adapter, i);
+	for (i = 0; i < adapter->rx_queue_count; ++i)
+		atl1c_clean_rx_ring(adapter, i);
 }
 
 static int atl1c_up(struct atl1c_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 	int err;
+	int i;
 
 	netif_carrier_off(netdev);
 
@@ -2344,20 +2441,24 @@ static int atl1c_up(struct atl1c_adapter *adapter)
 
 	atl1c_check_link_status(adapter);
 	clear_bit(__AT_DOWN, &adapter->flags);
-	napi_enable(&adapter->napi);
-	napi_enable(&adapter->tx_napi);
+	for (i = 0; i < adapter->tx_queue_count; ++i)
+		napi_enable(&adapter->tpd_ring[i].napi);
+	for (i = 0; i < adapter->rx_queue_count; ++i)
+		napi_enable(&adapter->rrd_ring[i].napi);
 	atl1c_irq_enable(adapter);
 	netif_start_queue(netdev);
 	return err;
 
 err_up:
-	atl1c_clean_rx_ring(adapter);
+	for (i = 0; i < adapter->rx_queue_count; ++i)
+		atl1c_clean_rx_ring(adapter, i);
 	return err;
 }
 
 static void atl1c_down(struct atl1c_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
+	int i;
 
 	atl1c_del_timer(adapter);
 	adapter->work_event = 0; /* clear all event */
@@ -2365,8 +2466,10 @@ static void atl1c_down(struct atl1c_adapter *adapter)
 	 * reschedule our watchdog timer */
 	set_bit(__AT_DOWN, &adapter->flags);
 	netif_carrier_off(netdev);
-	napi_disable(&adapter->napi);
-	napi_disable(&adapter->tx_napi);
+	for (i = 0; i < adapter->tx_queue_count; ++i)
+		napi_disable(&adapter->tpd_ring[i].napi);
+	for (i = 0; i < adapter->rx_queue_count; ++i)
+		napi_disable(&adapter->rrd_ring[i].napi);
 	atl1c_irq_disable(adapter);
 	atl1c_free_irq(adapter);
 	/* disable ASPM if device inactive */
@@ -2551,8 +2654,11 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct net_device *netdev;
 	struct atl1c_adapter *adapter;
 	static int cards_found;
-
+	u8 __iomem *hw_addr;
+	enum atl1c_nic_type nic_type;
+	u32 queue_count = 1;
 	int err = 0;
+	int i;
 
 	/* enable device (incl. PCI PM wakeup and hotplug setup) */
 	err = pci_enable_device_mem(pdev);
@@ -2585,7 +2691,18 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_master(pdev);
 
-	netdev = alloc_etherdev(sizeof(struct atl1c_adapter));
+	hw_addr = pci_ioremap_bar(pdev, 0);
+	if (!hw_addr) {
+		err = -EIO;
+		dev_err(&pdev->dev, "cannot map device registers\n");
+		goto err_ioremap;
+	}
+
+	nic_type = atl1c_get_mac_type(pdev, hw_addr);
+	if (nic_type == athr_mt)
+		queue_count = 4;
+
+	netdev = alloc_etherdev_mq(sizeof(struct atl1c_adapter), queue_count);
 	if (netdev == NULL) {
 		err = -ENOMEM;
 		goto err_alloc_etherdev;
@@ -2601,13 +2718,11 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	adapter->netdev = netdev;
 	adapter->pdev = pdev;
 	adapter->hw.adapter = adapter;
+	adapter->hw.nic_type = nic_type;
 	adapter->msg_enable = netif_msg_init(-1, atl1c_default_msg);
-	adapter->hw.hw_addr = ioremap(pci_resource_start(pdev, 0), pci_resource_len(pdev, 0));
-	if (!adapter->hw.hw_addr) {
-		err = -EIO;
-		dev_err(&pdev->dev, "cannot map device registers\n");
-		goto err_ioremap;
-	}
+	adapter->hw.hw_addr = hw_addr;
+	adapter->tx_queue_count = queue_count;
+	adapter->rx_queue_count = queue_count;
 
 	/* init mii data */
 	adapter->mii.dev = netdev;
@@ -2616,8 +2731,12 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	adapter->mii.phy_id_mask = 0x1f;
 	adapter->mii.reg_num_mask = MDIO_CTRL_REG_MASK;
 	dev_set_threaded(netdev, true);
-	netif_napi_add(netdev, &adapter->napi, atl1c_clean, 64);
-	netif_napi_add(netdev, &adapter->tx_napi, atl1c_clean_tx, 64);
+	for (i = 0; i < adapter->rx_queue_count; ++i)
+		netif_napi_add(netdev, &adapter->rrd_ring[i].napi,
+			       atl1c_clean_rx, 64);
+	for (i = 0; i < adapter->tx_queue_count; ++i)
+		netif_napi_add(netdev, &adapter->tpd_ring[i].napi,
+			       atl1c_clean_tx, 64);
 	timer_setup(&adapter->phy_config_timer, atl1c_phy_config, 0);
 	/* setup the private structure */
 	err = atl1c_sw_init(adapter);
@@ -2670,11 +2789,11 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 err_reset:
 err_register:
 err_sw_init:
-	iounmap(adapter->hw.hw_addr);
 err_init_netdev:
-err_ioremap:
 	free_netdev(netdev);
 err_alloc_etherdev:
+	iounmap(hw_addr);
+err_ioremap:
 	pci_release_regions(pdev);
 err_pci_reg:
 err_dma:
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index ff9f96de74b8..2eb0a2ab69f6 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -357,7 +357,7 @@ static void atl1e_restore_vlan(struct atl1e_adapter *adapter)
 }
 
 /**
- * atl1e_set_mac - Change the Ethernet Address of the NIC
+ * atl1e_set_mac_addr - Change the Ethernet Address of the NIC
  * @netdev: network interface device structure
  * @p: pointer to an address structure
  *
@@ -787,7 +787,7 @@ static void atl1e_free_ring_resources(struct atl1e_adapter *adapter)
 }
 
 /**
- * atl1e_setup_mem_resources - allocate Tx / RX descriptor resources
+ * atl1e_setup_ring_resources - allocate Tx / RX descriptor resources
  * @adapter: board private structure
  *
  * Return 0 on success, negative on failure
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index eaf96d002fa5..c67201a13cf5 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -1011,7 +1011,7 @@ static int atl1_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 }
 
 /**
- * atl1_setup_mem_resources - allocate Tx / RX descriptor resources
+ * atl1_setup_ring_resources - allocate Tx / RX descriptor resources
  * @adapter: board private structure
  *
  * Return 0 on success, negative on failure
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index b455b60a5434..ad2655efe423 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -1556,8 +1556,8 @@ static void b44_setup_pseudo_magicp(struct b44 *bp)
 	plen0 = b44_magic_pattern(bp->dev->dev_addr, pwol_pattern, pwol_mask,
 				  B44_ETHIPV4UDP_HLEN);
 
-   	bwfilter_table(bp, pwol_pattern, B44_PATTERN_SIZE, B44_PATTERN_BASE);
-   	bwfilter_table(bp, pwol_mask, B44_PMASK_SIZE, B44_PMASK_BASE);
+	bwfilter_table(bp, pwol_pattern, B44_PATTERN_SIZE, B44_PATTERN_BASE);
+	bwfilter_table(bp, pwol_mask, B44_PMASK_SIZE, B44_PMASK_BASE);
 
 	/* Raw ethernet II magic packet pattern - pattern 1 */
 	memset(pwol_pattern, 0, B44_PATTERN_SIZE);
@@ -1565,9 +1565,9 @@ static void b44_setup_pseudo_magicp(struct b44 *bp)
 	plen1 = b44_magic_pattern(bp->dev->dev_addr, pwol_pattern, pwol_mask,
 				  ETH_HLEN);
 
-   	bwfilter_table(bp, pwol_pattern, B44_PATTERN_SIZE,
+	bwfilter_table(bp, pwol_pattern, B44_PATTERN_SIZE,
 		       B44_PATTERN_BASE + B44_PATTERN_SIZE);
-  	bwfilter_table(bp, pwol_mask, B44_PMASK_SIZE,
+	bwfilter_table(bp, pwol_mask, B44_PMASK_SIZE,
 		       B44_PMASK_BASE + B44_PMASK_SIZE);
 
 	/* Ipv6 magic packet pattern - pattern 2 */
@@ -1576,9 +1576,9 @@ static void b44_setup_pseudo_magicp(struct b44 *bp)
 	plen2 = b44_magic_pattern(bp->dev->dev_addr, pwol_pattern, pwol_mask,
 				  B44_ETHIPV6UDP_HLEN);
 
-   	bwfilter_table(bp, pwol_pattern, B44_PATTERN_SIZE,
+	bwfilter_table(bp, pwol_pattern, B44_PATTERN_SIZE,
 		       B44_PATTERN_BASE + B44_PATTERN_SIZE + B44_PATTERN_SIZE);
-  	bwfilter_table(bp, pwol_mask, B44_PMASK_SIZE,
+	bwfilter_table(bp, pwol_mask, B44_PMASK_SIZE,
 		       B44_PMASK_BASE + B44_PMASK_SIZE + B44_PMASK_SIZE);
 
 	kfree(pwol_pattern);
@@ -1631,9 +1631,9 @@ static void b44_setup_wol(struct b44 *bp)
 		val = br32(bp, B44_DEVCTRL);
 		bw32(bp, B44_DEVCTRL, val | DEVCTRL_MPM | DEVCTRL_PFE);
 
- 	} else {
- 		b44_setup_pseudo_magicp(bp);
- 	}
+	} else {
+		b44_setup_pseudo_magicp(bp);
+	}
 	b44_setup_wol_pci(bp);
 }
 
@@ -1757,7 +1757,7 @@ static void __b44_set_rx_mode(struct net_device *dev)
 			__b44_cam_write(bp, zero, i);
 
 		bw32(bp, B44_RXCONFIG, val);
-        	val = br32(bp, B44_CAM_CTRL);
+		val = br32(bp, B44_CAM_CTRL);
 	        bw32(bp, B44_CAM_CTRL, val | CAM_CTRL_ENABLE);
 	}
 }
diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c
index 9834b77cf4b6..4ab5bf64d353 100644
--- a/drivers/net/ethernet/broadcom/bgmac-platform.c
+++ b/drivers/net/ethernet/broadcom/bgmac-platform.c
@@ -172,7 +172,6 @@ static int bgmac_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
 	struct bgmac *bgmac;
-	struct resource *regs;
 	int ret;
 
 	bgmac = bgmac_alloc(&pdev->dev);
@@ -206,21 +205,15 @@ static int bgmac_probe(struct platform_device *pdev)
 	if (IS_ERR(bgmac->plat.base))
 		return PTR_ERR(bgmac->plat.base);
 
-	regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "idm_base");
-	if (regs) {
-		bgmac->plat.idm_base = devm_ioremap_resource(&pdev->dev, regs);
-		if (IS_ERR(bgmac->plat.idm_base))
-			return PTR_ERR(bgmac->plat.idm_base);
+	bgmac->plat.idm_base = devm_platform_ioremap_resource_byname(pdev, "idm_base");
+	if (IS_ERR(bgmac->plat.idm_base))
+		return PTR_ERR(bgmac->plat.idm_base);
+	else
 		bgmac->feature_flags &= ~BGMAC_FEAT_IDM_MASK;
-	}
 
-	regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nicpm_base");
-	if (regs) {
-		bgmac->plat.nicpm_base = devm_ioremap_resource(&pdev->dev,
-							       regs);
-		if (IS_ERR(bgmac->plat.nicpm_base))
-			return PTR_ERR(bgmac->plat.nicpm_base);
-	}
+	bgmac->plat.nicpm_base = devm_platform_ioremap_resource_byname(pdev, "nicpm_base");
+	if (IS_ERR(bgmac->plat.nicpm_base))
+		return PTR_ERR(bgmac->plat.nicpm_base);
 
 	bgmac->read = platform_bgmac_read;
 	bgmac->write = platform_bgmac_write;
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index 5bace8a93d73..bee6cfad9fc6 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -572,7 +572,7 @@ bnx2_write_phy(struct bnx2 *bp, u32 reg, u32 val)
 	}
 
 	if (val1 & BNX2_EMAC_MDIO_COMM_START_BUSY)
-        	ret = -EBUSY;
+		ret = -EBUSY;
 	else
 		ret = 0;
 
@@ -3599,7 +3599,7 @@ bnx2_set_rx_mode(struct net_device *dev)
 		for (i = 0; i < NUM_MC_HASH_REGISTERS; i++) {
 			BNX2_WR(bp, BNX2_EMAC_MULTICAST_HASH0 + (i * 4),
 				0xffffffff);
-        	}
+		}
 		sort_mode |= BNX2_RPM_SORT_USER0_MC_EN;
 	}
 	else {
@@ -4674,7 +4674,7 @@ bnx2_nvram_write(struct bnx2 *bp, u32 offset, u8 *data_buf,
 
 				if (addr == page_end-4) {
 					cmd_flags = BNX2_NVM_COMMAND_LAST;
-                		}
+				}
 				rc = bnx2_nvram_write_dword(bp, addr,
 					&flash_buffer[i], cmd_flags);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 281b1c2e04a7..2acbc73dcd18 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -13586,7 +13586,7 @@ static int bnx2x_set_qm_cid_count(struct bnx2x *bp)
 }
 
 /**
- * bnx2x_get_num_none_def_sbs - return the number of none default SBs
+ * bnx2x_get_num_non_def_sbs - return the number of none default SBs
  * @pdev: pci device
  * @cnic_cnt: count
  *
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 6cd1523ad9e5..542c69822649 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -4152,7 +4152,7 @@ void bnx2x_init_mcast_obj(struct bnx2x *bp,
 /*************************** Credit handling **********************************/
 
 /**
- * atomic_add_ifless - add if the result is less than a given value.
+ * __atomic_add_ifless - add if the result is less than a given value.
  *
  * @v:	pointer of type atomic_t
  * @a:	the amount to add to v...
@@ -4180,7 +4180,7 @@ static inline bool __atomic_add_ifless(atomic_t *v, int a, int u)
 }
 
 /**
- * atomic_dec_ifmoe - dec if the result is more or equal than a given value.
+ * __atomic_dec_ifmoe - dec if the result is more or equal than a given value.
  *
  * @v:	pointer of type atomic_t
  * @a:	the amount to dec from v...
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index 3a716c015415..966d5722c5e2 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -504,7 +504,6 @@ enum sample_bulletin_result bnx2x_sample_bulletin(struct bnx2x *bp);
 /* VF side vfpf channel functions */
 int bnx2x_vfpf_acquire(struct bnx2x *bp, u8 tx_count, u8 rx_count);
 int bnx2x_vfpf_release(struct bnx2x *bp);
-int bnx2x_vfpf_release(struct bnx2x *bp);
 int bnx2x_vfpf_init(struct bnx2x *bp);
 void bnx2x_vfpf_close_vf(struct bnx2x *bp);
 int bnx2x_vfpf_setup_q(struct bnx2x *bp, struct bnx2x_fastpath *fp,
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 5335244e4577..89d16c587bb7 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -423,6 +423,10 @@ static int bcmgenet_mii_register(struct bcmgenet_priv *priv)
 	int id, ret;
 
 	pres = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!pres) {
+		dev_err(&pdev->dev, "Invalid resource\n");
+		return -EINVAL;
+	}
 	memset(&res, 0, sizeof(res));
 	memset(&ppd, 0, sizeof(ppd));
 
diff --git a/drivers/net/ethernet/brocade/bna/bfa_cee.c b/drivers/net/ethernet/brocade/bna/bfa_cee.c
index 06f221c44802..eeb05e31713f 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_cee.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_cee.c
@@ -82,7 +82,7 @@ bfa_cee_get_attr_isr(struct bfa_cee *cee, enum bfa_status status)
 }
 
 /**
- * bfa_cee_get_attr_isr - CEE ISR for get-stats responses from f/w
+ * bfa_cee_get_stats_isr - CEE ISR for get-stats responses from f/w
  *
  * @cee: Pointer to the CEE module
  * @status: Return status from the f/w
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index a0c7b1167dbb..7d2fe13a52f8 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -4655,8 +4655,7 @@ static int macb_probe(struct platform_device *pdev)
 	struct macb *bp;
 	int err, val;
 
-	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	mem = devm_ioremap_resource(&pdev->dev, regs);
+	mem = devm_platform_get_and_ioremap_resource(pdev, 0, &regs);
 	if (IS_ERR(mem))
 		return PTR_ERR(mem);
 
diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c
index 353393dea639..8b7b59908a1a 100644
--- a/drivers/net/ethernet/cadence/macb_pci.c
+++ b/drivers/net/ethernet/cadence/macb_pci.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
  * DOC: Cadence GEM PCI wrapper.
  *
  * Copyright (C) 2016 Cadence Design Systems - https://www.cadence.com
diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c
index 283918aeb741..5c368a9cbbbc 100644
--- a/drivers/net/ethernet/cadence/macb_ptp.c
+++ b/drivers/net/ethernet/cadence/macb_ptp.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
  * 1588 PTP support for Cadence GEM device.
  *
  * Copyright (C) 2017 Cadence Design Systems - https://www.cadence.com
diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c
index bbb453c6a5f7..b6a066404f4b 100644
--- a/drivers/net/ethernet/calxeda/xgmac.c
+++ b/drivers/net/ethernet/calxeda/xgmac.c
@@ -711,7 +711,7 @@ static void xgmac_rx_refill(struct xgmac_priv *priv)
 }
 
 /**
- * init_xgmac_dma_desc_rings - init the RX/TX descriptor rings
+ * xgmac_dma_desc_rings_init - init the RX/TX descriptor rings
  * @dev: net device structure
  * Description:  this function initializes the DMA RX/TX descriptors
  * and allocates the socket buffers.
@@ -859,7 +859,7 @@ static void xgmac_free_dma_desc_rings(struct xgmac_priv *priv)
 }
 
 /**
- * xgmac_tx:
+ * xgmac_tx_complete:
  * @priv: private driver structure
  * Description: it reclaims resources after transmission completes.
  */
@@ -1040,7 +1040,7 @@ static int xgmac_open(struct net_device *dev)
 }
 
 /**
- *  xgmac_release - close entry point of the driver
+ *  xgmac_stop - close entry point of the driver
  *  @dev : device pointer.
  *  Description:
  *  This is the stop entry point of the driver.
@@ -1812,7 +1812,7 @@ err_alloc:
 }
 
 /**
- * xgmac_dvr_remove
+ * xgmac_remove
  * @pdev: platform device pointer
  * Description: this function resets the TX/RX processes, disables the MAC RX/TX
  * changes the link status, releases the DMA descriptor rings,
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 0c783aadf393..c36fed9c3d73 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -594,9 +594,6 @@ static void bgx_lmac_handler(struct net_device *netdev)
 	struct phy_device *phydev;
 	int link_changed = 0;
 
-	if (!lmac)
-		return;
-
 	phydev = lmac->phydev;
 
 	if (!phydev->link && lmac->last_link)
diff --git a/drivers/net/ethernet/chelsio/cxgb3/adapter.h b/drivers/net/ethernet/chelsio/cxgb3/adapter.h
index f80fbd81b609..6d682b7c7aac 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/adapter.h
+++ b/drivers/net/ethernet/chelsio/cxgb3/adapter.h
@@ -178,7 +178,7 @@ struct sge_txq {		/* state for an SGE Tx queue */
 	unsigned int token;	/* WR token */
 	dma_addr_t phys_addr;	/* physical address of the ring */
 	struct sk_buff_head sendq;	/* List of backpressured offload packets */
-	struct tasklet_struct qresume_tsk;	/* restarts the queue */
+	struct work_struct qresume_task;	/* restarts the queue */
 	unsigned int cntxt_id;	/* SGE context id for the Tx q */
 	unsigned long stops;	/* # of times q has been stopped */
 	unsigned long restarts;	/* # of queue restarts */
diff --git a/drivers/net/ethernet/chelsio/cxgb3/common.h b/drivers/net/ethernet/chelsio/cxgb3/common.h
index 1bd7d89666c4..b706f2fbe4f4 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/common.h
+++ b/drivers/net/ethernet/chelsio/cxgb3/common.h
@@ -770,4 +770,6 @@ int t3_xaui_direct_phy_prep(struct cphy *phy, struct adapter *adapter,
 			    int phy_addr, const struct mdio_ops *mdio_ops);
 int t3_aq100x_phy_prep(struct cphy *phy, struct adapter *adapter,
 			    int phy_addr, const struct mdio_ops *mdio_ops);
+
+extern struct workqueue_struct *cxgb3_wq;
 #endif				/* __CHELSIO_COMMON_H */
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 84ad7261e243..57f210c53afc 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -1273,14 +1273,14 @@ static int cxgb_up(struct adapter *adap)
 			free_irq(adap->msix_info[0].vec, adap);
 			goto irq_err;
 		}
-	} else if ((err = request_irq(adap->pdev->irq,
-				      t3_intr_handler(adap,
-						      adap->sge.qs[0].rspq.
-						      polling),
-				      (adap->flags & USING_MSI) ?
-				       0 : IRQF_SHARED,
-				      adap->name, adap)))
-		goto irq_err;
+	} else {
+		err = request_irq(adap->pdev->irq,
+				  t3_intr_handler(adap, adap->sge.qs[0].rspq.polling),
+				  (adap->flags & USING_MSI) ? 0 : IRQF_SHARED,
+				  adap->name, adap);
+		if (err)
+			goto irq_err;
+	}
 
 	enable_all_napi(adap);
 	t3_sge_start(adap);
@@ -3098,8 +3098,9 @@ static void set_nqsets(struct adapter *adap)
 			nqsets = num_cpus;
 		if (nqsets < 1 || hwports == 4)
 			nqsets = 1;
-	} else
+	} else {
 		nqsets = 1;
+	}
 
 	for_each_port(adap, i) {
 		struct port_info *pi = adap2pinfo(adap, i);
diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c
index 1cc3c51eff71..cb5c79c43bc9 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c
@@ -665,7 +665,7 @@ static void t3_reset_qset(struct sge_qset *q)
 
 
 /**
- *	free_qset - free the resources of an SGE queue set
+ *	t3_free_qset - free the resources of an SGE queue set
  *	@adapter: the adapter owning the queue set
  *	@q: the queue set
  *
@@ -1256,7 +1256,7 @@ static inline void t3_stop_tx_queue(struct netdev_queue *txq,
 }
 
 /**
- *	eth_xmit - add a packet to the Ethernet Tx queue
+ *	t3_eth_xmit - add a packet to the Ethernet Tx queue
  *	@skb: the packet
  *	@dev: the egress net device
  *
@@ -1518,14 +1518,15 @@ static int ctrl_xmit(struct adapter *adap, struct sge_txq *q,
 
 /**
  *	restart_ctrlq - restart a suspended control queue
- *	@t: pointer to the tasklet associated with this handler
+ *	@w: pointer to the work associated with this handler
  *
  *	Resumes transmission on a suspended Tx control queue.
  */
-static void restart_ctrlq(struct tasklet_struct *t)
+static void restart_ctrlq(struct work_struct *w)
 {
 	struct sk_buff *skb;
-	struct sge_qset *qs = from_tasklet(qs, t, txq[TXQ_CTRL].qresume_tsk);
+	struct sge_qset *qs = container_of(w, struct sge_qset,
+					   txq[TXQ_CTRL].qresume_task);
 	struct sge_txq *q = &qs->txq[TXQ_CTRL];
 
 	spin_lock(&q->lock);
@@ -1736,14 +1737,15 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 
 /**
  *	restart_offloadq - restart a suspended offload queue
- *	@t: pointer to the tasklet associated with this handler
+ *	@w: pointer to the work associated with this handler
  *
  *	Resumes transmission on a suspended Tx offload queue.
  */
-static void restart_offloadq(struct tasklet_struct *t)
+static void restart_offloadq(struct work_struct *w)
 {
 	struct sk_buff *skb;
-	struct sge_qset *qs = from_tasklet(qs, t, txq[TXQ_OFLD].qresume_tsk);
+	struct sge_qset *qs = container_of(w, struct sge_qset,
+					   txq[TXQ_OFLD].qresume_task);
 	struct sge_txq *q = &qs->txq[TXQ_OFLD];
 	const struct port_info *pi = netdev_priv(qs->netdev);
 	struct adapter *adap = pi->adapter;
@@ -1998,13 +2000,17 @@ static void restart_tx(struct sge_qset *qs)
 	    should_restart_tx(&qs->txq[TXQ_OFLD]) &&
 	    test_and_clear_bit(TXQ_OFLD, &qs->txq_stopped)) {
 		qs->txq[TXQ_OFLD].restarts++;
-		tasklet_schedule(&qs->txq[TXQ_OFLD].qresume_tsk);
+
+		/* The work can be quite lengthy so we use driver's own queue */
+		queue_work(cxgb3_wq, &qs->txq[TXQ_OFLD].qresume_task);
 	}
 	if (test_bit(TXQ_CTRL, &qs->txq_stopped) &&
 	    should_restart_tx(&qs->txq[TXQ_CTRL]) &&
 	    test_and_clear_bit(TXQ_CTRL, &qs->txq_stopped)) {
 		qs->txq[TXQ_CTRL].restarts++;
-		tasklet_schedule(&qs->txq[TXQ_CTRL].qresume_tsk);
+
+		/* The work can be quite lengthy so we use driver's own queue */
+		queue_work(cxgb3_wq, &qs->txq[TXQ_CTRL].qresume_task);
 	}
 }
 
@@ -3085,8 +3091,8 @@ int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports,
 		skb_queue_head_init(&q->txq[i].sendq);
 	}
 
-	tasklet_setup(&q->txq[TXQ_OFLD].qresume_tsk, restart_offloadq);
-	tasklet_setup(&q->txq[TXQ_CTRL].qresume_tsk, restart_ctrlq);
+	INIT_WORK(&q->txq[TXQ_OFLD].qresume_task, restart_offloadq);
+	INIT_WORK(&q->txq[TXQ_CTRL].qresume_task, restart_ctrlq);
 
 	q->fl[0].gen = q->fl[1].gen = 1;
 	q->fl[0].size = p->fl_size;
@@ -3276,11 +3282,11 @@ void t3_sge_start(struct adapter *adap)
  *
  *	Can be invoked from interrupt context e.g.  error handler.
  *
- *	Note that this function cannot disable the restart of tasklets as
+ *	Note that this function cannot disable the restart of works as
  *	it cannot wait if called from interrupt context, however the
- *	tasklets will have no effect since the doorbells are disabled. The
+ *	works will have no effect since the doorbells are disabled. The
  *	driver will call tg3_sge_stop() later from process context, at
- *	which time the tasklets will be stopped if they are still running.
+ *	which time the works will be stopped if they are still running.
  */
 void t3_sge_stop_dma(struct adapter *adap)
 {
@@ -3292,7 +3298,7 @@ void t3_sge_stop_dma(struct adapter *adap)
  *	@adap: the adapter
  *
  *	Called from process context. Disables the DMA engine and any
- *	pending queue restart tasklets.
+ *	pending queue restart works.
  */
 void t3_sge_stop(struct adapter *adap)
 {
@@ -3303,8 +3309,8 @@ void t3_sge_stop(struct adapter *adap)
 	for (i = 0; i < SGE_QSETS; ++i) {
 		struct sge_qset *qs = &adap->sge.qs[i];
 
-		tasklet_kill(&qs->txq[TXQ_OFLD].qresume_tsk);
-		tasklet_kill(&qs->txq[TXQ_CTRL].qresume_tsk);
+		cancel_work_sync(&qs->txq[TXQ_OFLD].qresume_task);
+		cancel_work_sync(&qs->txq[TXQ_CTRL].qresume_task);
 	}
 }
 
@@ -3371,7 +3377,7 @@ void t3_sge_prep(struct adapter *adap, struct sge_params *p)
 		q->coalesce_usecs = 5;
 		q->rspq_size = 1024;
 		q->fl_size = 1024;
- 		q->jumbo_size = 512;
+		q->jumbo_size = 512;
 		q->txq_size[TXQ_ETH] = 1024;
 		q->txq_size[TXQ_OFLD] = 1024;
 		q->txq_size[TXQ_CTRL] = 256;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
index 12fcf84d67ad..163efab27e9b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
@@ -106,8 +106,7 @@ int cxgb4_clip_get(const struct net_device *dev, const u32 *lip, u8 v6)
 	if (!list_empty(&ctbl->ce_free_head)) {
 		ce = list_first_entry(&ctbl->ce_free_head,
 				      struct clip_entry, list);
-		list_del(&ce->list);
-		INIT_LIST_HEAD(&ce->list);
+		list_del_init(&ce->list);
 		spin_lock_init(&ce->lock);
 		refcount_set(&ce->refcnt, 0);
 		atomic_dec(&ctbl->nfree);
@@ -179,8 +178,7 @@ found:
 	write_lock_bh(&ctbl->lock);
 	spin_lock_bh(&ce->lock);
 	if (refcount_dec_and_test(&ce->refcnt)) {
-		list_del(&ce->list);
-		INIT_LIST_HEAD(&ce->list);
+		list_del_init(&ce->list);
 		list_add_tail(&ce->list, &ctbl->ce_free_head);
 		atomic_inc(&ctbl->nfree);
 		if (v6)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 762113a04dde..9a2b166d651e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3894,7 +3894,6 @@ static const struct net_device_ops cxgb4_mgmt_netdev_ops = {
 	.ndo_set_vf_vlan        = cxgb4_mgmt_set_vf_vlan,
 	.ndo_set_vf_link_state	= cxgb4_mgmt_set_vf_link_state,
 };
-#endif
 
 static void cxgb4_mgmt_get_drvinfo(struct net_device *dev,
 				   struct ethtool_drvinfo *info)
@@ -3909,6 +3908,7 @@ static void cxgb4_mgmt_get_drvinfo(struct net_device *dev,
 static const struct ethtool_ops cxgb4_mgmt_ethtool_ops = {
 	.get_drvinfo       = cxgb4_mgmt_get_drvinfo,
 };
+#endif
 
 static void notify_fatal_err(struct work_struct *work)
 {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
index 70dbee89118e..5bf117d2179f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
@@ -446,7 +446,7 @@ void cxgb4_ptp_init(struct adapter *adapter)
 }
 
 /**
- * cxgb4_ptp_remove - disable PTP device and stop the overflow check
+ * cxgb4_ptp_stop - disable PTP device and stop the overflow check
  * @adapter: board private structure
  *
  * Stop the PTP support.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index a0555f4d76fc..6606fb8b3e42 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -6993,7 +6993,7 @@ int t4_fw_bye(struct adapter *adap, unsigned int mbox)
 }
 
 /**
- *	t4_init_cmd - ask FW to initialize the device
+ *	t4_early_init - ask FW to initialize the device
  *	@adap: the adapter
  *	@mbox: mailbox to use for the FW command
  *
@@ -7792,7 +7792,6 @@ int t4_free_encap_mac_filt(struct adapter *adap, unsigned int viid,
 			   int idx, bool sleep_ok)
 {
 	struct fw_vi_mac_exact *p;
-	u8 addr[] = {0, 0, 0, 0, 0, 0};
 	struct fw_vi_mac_cmd c;
 	int ret = 0;
 	u32 exact;
@@ -7809,7 +7808,7 @@ int t4_free_encap_mac_filt(struct adapter *adap, unsigned int viid,
 	p = c.u.exact;
 	p->valid_to_idx = cpu_to_be16(FW_VI_MAC_CMD_VALID_F |
 				      FW_VI_MAC_CMD_IDX_V(idx));
-	memcpy(p->macaddr, addr, sizeof(p->macaddr));
+	eth_zero_addr(p->macaddr);
 	ret = t4_wr_mbox_meat(adap, adap->mbox, &c, sizeof(c), &c, sleep_ok);
 	return ret;
 }
@@ -10234,7 +10233,7 @@ out:
 }
 
 /**
- *	t4_set_vf_mac - Set MAC address for the specified VF
+ *	t4_set_vf_mac_acl - Set MAC address for the specified VF
  *	@adapter: The adapter
  *	@vf: one of the VFs instantiated by the specified PF
  *	@naddr: the number of MAC addresses
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
index 95657da0aa4b..7bc80eeb2c21 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -954,7 +954,7 @@ static void write_sgl(const struct sk_buff *skb, struct sge_txq *tq,
 }
 
 /**
- *	check_ring_tx_db - check and potentially ring a TX queue's doorbell
+ *	ring_tx_db - check and potentially ring a TX queue's doorbell
  *	@adapter: the adapter
  *	@tq: the TX queue
  *	@n: number of new descriptors to give to HW
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 8df6f081f244..c2ebb3388789 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -2356,8 +2356,6 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct gemini_ethernet *geth;
 	struct net_device *netdev;
-	struct resource *gmacres;
-	struct resource *dmares;
 	struct device *parent;
 	unsigned int id;
 	int irq;
@@ -2390,24 +2388,18 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 	port->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
 
 	/* DMA memory */
-	dmares = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!dmares) {
-		dev_err(dev, "no DMA resource\n");
-		return -ENODEV;
-	}
-	port->dma_base = devm_ioremap_resource(dev, dmares);
-	if (IS_ERR(port->dma_base))
+	port->dma_base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
+	if (IS_ERR(port->dma_base)) {
+		dev_err(dev, "get DMA address failed\n");
 		return PTR_ERR(port->dma_base);
+	}
 
 	/* GMAC config memory */
-	gmacres = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	if (!gmacres) {
-		dev_err(dev, "no GMAC resource\n");
-		return -ENODEV;
-	}
-	port->gmac_base = devm_ioremap_resource(dev, gmacres);
-	if (IS_ERR(port->gmac_base))
+	port->gmac_base = devm_platform_get_and_ioremap_resource(pdev, 1, NULL);
+	if (IS_ERR(port->gmac_base)) {
+		dev_err(dev, "get GMAC address failed\n");
 		return PTR_ERR(port->gmac_base);
+	}
 
 	/* Interrupt */
 	irq = platform_get_irq(pdev, 0);
@@ -2502,10 +2494,6 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 	if (ret)
 		goto unprepare;
 
-	netdev_info(netdev,
-		    "irq %d, DMA @ 0x%pap, GMAC @ 0x%pap\n",
-		    port->irq, &dmares->start,
-		    &gmacres->start);
 	return 0;
 
 unprepare:
@@ -2544,17 +2532,13 @@ static int gemini_ethernet_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct gemini_ethernet *geth;
 	unsigned int retry = 5;
-	struct resource *res;
 	u32 val;
 
 	/* Global registers */
 	geth = devm_kzalloc(dev, sizeof(*geth), GFP_KERNEL);
 	if (!geth)
 		return -ENOMEM;
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENODEV;
-	geth->base = devm_ioremap_resource(dev, res);
+	geth->base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
 	if (IS_ERR(geth->base))
 		return PTR_ERR(geth->base);
 	geth->dev = dev;
diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c
index b018195f0243..117c26fa5909 100644
--- a/drivers/net/ethernet/dec/tulip/de2104x.c
+++ b/drivers/net/ethernet/dec/tulip/de2104x.c
@@ -832,8 +832,8 @@ static struct net_device_stats *de_get_stats(struct net_device *dev)
 
 	/* The chip only need report frame silently dropped. */
 	spin_lock_irq(&de->lock);
- 	if (netif_running(dev) && netif_device_present(dev))
- 		__de_get_stats(de);
+	if (netif_running(dev) && netif_device_present(dev))
+		__de_get_stats(de);
 	spin_unlock_irq(&de->lock);
 
 	return &dev->stats;
diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index 683e328b5461..b125d7faefdf 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -396,7 +396,7 @@
 			   <earl@exis.net>.
 			  Updated the PCI interface to conform with the latest
 			   version. I hope nothing is broken...
-          		  Add TX done interrupt modification from suggestion
+			  Add TX done interrupt modification from suggestion
 			   by <Austin.Donnelly@cl.cam.ac.uk>.
 			  Fix is_anc_capable() bug reported by
 			   <Austin.Donnelly@cl.cam.ac.uk>.
@@ -1499,7 +1499,7 @@ de4x5_queue_pkt(struct sk_buff *skb, struct net_device *dev)
 	    spin_lock_irqsave(&lp->lock, flags);
 	    netif_stop_queue(dev);
 	    load_packet(dev, skb->data, TD_IC | TD_LS | TD_FS | skb->len, skb);
- 	    lp->stats.tx_bytes += skb->len;
+	    lp->stats.tx_bytes += skb->len;
 	    outl(POLL_DEMAND, DE4X5_TPD);/* Start the TX */
 
 	    lp->tx_new = (lp->tx_new + 1) % lp->txRingSize;
@@ -1651,7 +1651,7 @@ de4x5_rx(struct net_device *dev)
 
 		    /* Update stats */
 		    lp->stats.rx_packets++;
- 		    lp->stats.rx_bytes += pkt_len;
+		    lp->stats.rx_bytes += pkt_len;
 		}
 	    }
 
diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c
index 87a27fe2992d..c763b692e164 100644
--- a/drivers/net/ethernet/dec/tulip/dmfe.c
+++ b/drivers/net/ethernet/dec/tulip/dmfe.c
@@ -518,7 +518,7 @@ static void dmfe_remove_one(struct pci_dev *pdev)
 
 	DMFE_DBUG(0, "dmfe_remove_one()", 0);
 
- 	if (dev) {
+	if (dev) {
 
 		unregister_netdev(dev);
 		pci_iounmap(db->pdev, db->ioaddr);
@@ -567,10 +567,10 @@ static int dmfe_open(struct net_device *dev)
 	/* CR6 operation mode decision */
 	if ( !chkmode || (db->chip_id == PCI_DM9132_ID) ||
 		(db->chip_revision >= 0x30) ) {
-    		db->cr6_data |= DMFE_TXTH_256;
+		db->cr6_data |= DMFE_TXTH_256;
 		db->cr0_data = CR0_DEFAULT;
 		db->dm910x_chk_mode=4;		/* Enter the normal mode */
- 	} else {
+	} else {
 		db->cr6_data |= CR6_SFT;	/* Store & Forward mode */
 		db->cr0_data = 0;
 		db->dm910x_chk_mode = 1;	/* Enter the check mode */
@@ -903,7 +903,7 @@ static void dmfe_free_tx_pkt(struct net_device *dev, struct dmfe_board_info *db)
 			}
 		}
 
-    		txptr = txptr->next_tx_desc;
+		txptr = txptr->next_tx_desc;
 	}/* End of while */
 
 	/* Update TX remove pointer to next */
@@ -1121,7 +1121,7 @@ static void dmfe_timer(struct timer_list *t)
 	void __iomem *ioaddr = db->ioaddr;
 	u32 tmp_cr8;
 	unsigned char tmp_cr12;
- 	unsigned long flags;
+	unsigned long flags;
 
 	int link_ok, link_ok_phy;
 
@@ -1217,7 +1217,7 @@ static void dmfe_timer(struct timer_list *t)
 	if (link_ok_phy != link_ok) {
 		DMFE_DBUG (0, "PHY and chip report different link status", 0);
 		link_ok = link_ok | link_ok_phy;
- 	}
+	}
 
 	if ( !link_ok && netif_carrier_ok(dev)) {
 		/* Link Failed */
@@ -1699,14 +1699,14 @@ static void dmfe_set_phyxcer(struct dmfe_board_info *db)
 		if (db->chip_id == PCI_DM9009_ID) phy_reg &= 0x61;
 	}
 
-  	/* Write new capability to Phyxcer Reg4 */
+	/* Write new capability to Phyxcer Reg4 */
 	if ( !(phy_reg & 0x01e0)) {
 		phy_reg|=db->PHY_reg4;
 		db->media_mode|=DMFE_AUTO;
 	}
 	dmfe_phy_write(db->ioaddr, db->phy_addr, 4, phy_reg, db->chip_id);
 
- 	/* Restart Auto-Negotiation */
+	/* Restart Auto-Negotiation */
 	if ( db->chip_type && (db->chip_id == PCI_DM9102_ID) )
 		dmfe_phy_write(db->ioaddr, db->phy_addr, 0, 0x1800, db->chip_id);
 	if ( !db->chip_type )
@@ -1754,7 +1754,7 @@ static void dmfe_process_mode(struct dmfe_board_info *db)
 			}
 			dmfe_phy_write(db->ioaddr,
 				       db->phy_addr, 0, phy_reg, db->chip_id);
-       			if ( db->chip_type && (db->chip_id == PCI_DM9102_ID) )
+			if ( db->chip_type && (db->chip_id == PCI_DM9102_ID) )
 				mdelay(20);
 			dmfe_phy_write(db->ioaddr,
 				       db->phy_addr, 0, phy_reg, db->chip_id);
diff --git a/drivers/net/ethernet/dec/tulip/pnic2.c b/drivers/net/ethernet/dec/tulip/pnic2.c
index 412adaa7fdf8..72a09156b48b 100644
--- a/drivers/net/ethernet/dec/tulip/pnic2.c
+++ b/drivers/net/ethernet/dec/tulip/pnic2.c
@@ -351,7 +351,7 @@ void pnic2_lnk_change(struct net_device *dev, int csr5)
 			del_timer_sync(&tp->timer);
 			pnic2_start_nway(dev);
 			tp->timer.expires = RUN_AT(3*HZ);
-       			add_timer(&tp->timer);
+			add_timer(&tp->timer);
                 }
 
                 return;
@@ -375,7 +375,7 @@ void pnic2_lnk_change(struct net_device *dev, int csr5)
 			del_timer_sync(&tp->timer);
 			pnic2_start_nway(dev);
 			tp->timer.expires = RUN_AT(3*HZ);
-       			add_timer(&tp->timer);
+			add_timer(&tp->timer);
                 }
 
                 return;
diff --git a/drivers/net/ethernet/dec/tulip/tulip.h b/drivers/net/ethernet/dec/tulip/tulip.h
index 815907259048..0ed598dc7569 100644
--- a/drivers/net/ethernet/dec/tulip/tulip.h
+++ b/drivers/net/ethernet/dec/tulip/tulip.h
@@ -478,7 +478,6 @@ void t21142_lnk_change(struct net_device *dev, int csr5);
 void pnic2_lnk_change(struct net_device *dev, int csr5);
 void pnic2_timer(struct timer_list *t);
 void pnic2_start_nway(struct net_device *dev);
-void pnic2_lnk_change(struct net_device *dev, int csr5);
 
 /* eeprom.c */
 void tulip_parse_eeprom(struct net_device *dev);
diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c
index 13e73ed15ef0..d67ef7d02d6b 100644
--- a/drivers/net/ethernet/dec/tulip/uli526x.c
+++ b/drivers/net/ethernet/dec/tulip/uli526x.c
@@ -780,7 +780,7 @@ static void uli526x_free_tx_pkt(struct net_device *dev,
 			}
 		}
 
-    		txptr = txptr->next_tx_desc;
+		txptr = txptr->next_tx_desc;
 	}/* End of while */
 
 	/* Update TX remove pointer to next */
@@ -1015,7 +1015,7 @@ static void uli526x_timer(struct timer_list *t)
 	struct net_device *dev = pci_get_drvdata(db->pdev);
 	struct uli_phy_ops *phy = &db->phy;
 	void __iomem *ioaddr = db->ioaddr;
- 	unsigned long flags;
+	unsigned long flags;
 	u8 tmp_cr12 = 0;
 	u32 tmp_cr8;
 
@@ -1535,14 +1535,14 @@ static void uli526x_set_phyxcer(struct uli526x_board_info *db)
 
 	}
 
-  	/* Write new capability to Phyxcer Reg4 */
+	/* Write new capability to Phyxcer Reg4 */
 	if ( !(phy_reg & 0x01e0)) {
 		phy_reg|=db->PHY_reg4;
 		db->media_mode|=ULI526X_AUTO;
 	}
 	phy->write(db, db->phy_addr, 4, phy_reg);
 
- 	/* Restart Auto-Negotiation */
+	/* Restart Auto-Negotiation */
 	phy->write(db, db->phy_addr, 0, 0x1200);
 	udelay(50);
 }
@@ -1550,7 +1550,7 @@ static void uli526x_set_phyxcer(struct uli526x_board_info *db)
 
 /*
  *	Process op-mode
- 	AUTO mode : PHY controller in Auto-negotiation Mode
+	AUTO mode : PHY controller in Auto-negotiation Mode
  *	Force mode: PHY controller in force mode with HUB
  *			N-way force capability with SWITCH
  */
diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c
index 514df170ec5d..f6ff1f76eacb 100644
--- a/drivers/net/ethernet/dec/tulip/winbond-840.c
+++ b/drivers/net/ethernet/dec/tulip/winbond-840.c
@@ -36,7 +36,7 @@
 		power management.
 		support for big endian descriptors
 			Copyright (C) 2001 Manfred Spraul
-  	* ethtool support (jgarzik)
+	* ethtool support (jgarzik)
 	* Replace some MII-related magic numbers with constants (jgarzik)
 
 	TODO:
@@ -1479,7 +1479,7 @@ static int netdev_close(struct net_device *dev)
 			   np->cur_rx, np->dirty_rx);
 	}
 
- 	/* Stop the chip's Tx and Rx processes. */
+	/* Stop the chip's Tx and Rx processes. */
 	spin_lock_irq(&np->lock);
 	netif_device_detach(dev);
 	update_csr6(dev, 0);
diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c
index ce61f79f3b7c..ee0ca712dd1c 100644
--- a/drivers/net/ethernet/dlink/sundance.c
+++ b/drivers/net/ethernet/dlink/sundance.c
@@ -1847,20 +1847,20 @@ static int netdev_close(struct net_device *dev)
 	/* Stop the chip's Tx and Rx processes. */
 	iowrite16(TxDisable | RxDisable | StatsDisable, ioaddr + MACCtrl1);
 
-    	for (i = 2000; i > 0; i--) {
- 		if ((ioread32(ioaddr + DMACtrl) & 0xc000) == 0)
+	for (i = 2000; i > 0; i--) {
+		if ((ioread32(ioaddr + DMACtrl) & 0xc000) == 0)
 			break;
 		mdelay(1);
-    	}
+	}
 
-    	iowrite16(GlobalReset | DMAReset | FIFOReset | NetworkReset,
+	iowrite16(GlobalReset | DMAReset | FIFOReset | NetworkReset,
 			ioaddr + ASIC_HI_WORD(ASICCtrl));
 
-    	for (i = 2000; i > 0; i--) {
+	for (i = 2000; i > 0; i--) {
 		if ((ioread16(ioaddr + ASIC_HI_WORD(ASICCtrl)) & ResetBusy) == 0)
 			break;
 		mdelay(1);
-    	}
+	}
 
 #ifdef __i386__
 	if (netif_msg_hw(np)) {
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 04421aec2dfd..11dbbfd38770 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -1830,14 +1830,17 @@ static int ftgmac100_probe(struct platform_device *pdev)
 	if (np && of_get_property(np, "use-ncsi", NULL)) {
 		if (!IS_ENABLED(CONFIG_NET_NCSI)) {
 			dev_err(&pdev->dev, "NCSI stack not enabled\n");
+			err = -EINVAL;
 			goto err_phy_connect;
 		}
 
 		dev_info(&pdev->dev, "Using NCSI interface\n");
 		priv->use_ncsi = true;
 		priv->ndev = ncsi_register_dev(netdev, ftgmac100_ncsi_handler);
-		if (!priv->ndev)
+		if (!priv->ndev) {
+			err = -EINVAL;
 			goto err_phy_connect;
+		}
 	} else if (np && of_get_property(np, "phy-handle", NULL)) {
 		struct phy_device *phy;
 
@@ -1856,6 +1859,7 @@ static int ftgmac100_probe(struct platform_device *pdev)
 					     &ftgmac100_adjust_link);
 		if (!phy) {
 			dev_err(&pdev->dev, "Failed to connect to phy\n");
+			err = -EINVAL;
 			goto err_phy_connect;
 		}
 
diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c
index 0908771aa9ac..0f141c14d72d 100644
--- a/drivers/net/ethernet/fealnx.c
+++ b/drivers/net/ethernet/fealnx.c
@@ -144,7 +144,7 @@ struct chip_info {
 };
 
 static const struct chip_info skel_netdrv_tbl[] = {
- 	{ "100/10M Ethernet PCI Adapter",	HAS_MII_XCVR },
+	{ "100/10M Ethernet PCI Adapter",	HAS_MII_XCVR },
 	{ "100/10M Ethernet PCI Adapter",	HAS_CHIP_XCVR },
 	{ "1000/100/10M Ethernet PCI Adapter",	HAS_MII_XCVR },
 };
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
index b87db0846e10..8356af4631fd 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
@@ -121,10 +121,14 @@ DEFINE_SHOW_ATTRIBUTE(dpaa2_dbg_ch);
 
 void dpaa2_dbg_add(struct dpaa2_eth_priv *priv)
 {
+	struct fsl_mc_device *dpni_dev;
 	struct dentry *dir;
+	char name[10];
 
 	/* Create a directory for the interface */
-	dir = debugfs_create_dir(priv->net_dev->name, dpaa2_dbg_root);
+	dpni_dev = to_fsl_mc_device(priv->net_dev->dev.parent);
+	snprintf(name, 10, "dpni.%d", dpni_dev->obj_desc.id);
+	dir = debugfs_create_dir(name, dpaa2_dbg_root);
 	priv->dbg.dir = dir;
 
 	/* per-cpu stats file */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index e0c3c58e2ac7..8433aa730c42 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -4164,10 +4164,11 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv)
 
 	if (dpaa2_eth_is_type_phy(priv)) {
 		err = dpaa2_mac_connect(mac);
-		if (err) {
-			netdev_err(priv->net_dev, "Error connecting to the MAC endpoint\n");
+		if (err && err != -EPROBE_DEFER)
+			netdev_err(priv->net_dev, "Error connecting to the MAC endpoint: %pe",
+				   ERR_PTR(err));
+		if (err)
 			goto err_close_mac;
-		}
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c
index ccaf7e35abeb..ae6d382d8735 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
 /* Copyright 2019 NXP */
 
+#include <linux/acpi.h>
+#include <linux/property.h>
+
 #include "dpaa2-eth.h"
 #include "dpaa2-mac.h"
 
@@ -34,39 +37,51 @@ static int phy_mode(enum dpmac_eth_if eth_if, phy_interface_t *if_mode)
 	return 0;
 }
 
-/* Caller must call of_node_put on the returned value */
-static struct device_node *dpaa2_mac_get_node(u16 dpmac_id)
+static struct fwnode_handle *dpaa2_mac_get_node(struct device *dev,
+						u16 dpmac_id)
 {
-	struct device_node *dpmacs, *dpmac = NULL;
-	u32 id;
+	struct fwnode_handle *fwnode, *parent, *child  = NULL;
+	struct device_node *dpmacs = NULL;
 	int err;
+	u32 id;
 
-	dpmacs = of_find_node_by_name(NULL, "dpmacs");
-	if (!dpmacs)
-		return NULL;
+	fwnode = dev_fwnode(dev->parent);
+	if (is_of_node(fwnode)) {
+		dpmacs = of_find_node_by_name(NULL, "dpmacs");
+		if (!dpmacs)
+			return NULL;
+		parent = of_fwnode_handle(dpmacs);
+	} else if (is_acpi_node(fwnode)) {
+		parent = fwnode;
+	}
 
-	while ((dpmac = of_get_next_child(dpmacs, dpmac)) != NULL) {
-		err = of_property_read_u32(dpmac, "reg", &id);
+	fwnode_for_each_child_node(parent, child) {
+		err = -EINVAL;
+		if (is_acpi_device_node(child))
+			err = acpi_get_local_address(ACPI_HANDLE_FWNODE(child), &id);
+		else if (is_of_node(child))
+			err = of_property_read_u32(to_of_node(child), "reg", &id);
 		if (err)
 			continue;
-		if (id == dpmac_id)
-			break;
-	}
 
+		if (id == dpmac_id) {
+			of_node_put(dpmacs);
+			return child;
+		}
+	}
 	of_node_put(dpmacs);
-
-	return dpmac;
+	return NULL;
 }
 
-static int dpaa2_mac_get_if_mode(struct device_node *node,
+static int dpaa2_mac_get_if_mode(struct fwnode_handle *dpmac_node,
 				 struct dpmac_attr attr)
 {
 	phy_interface_t if_mode;
 	int err;
 
-	err = of_get_phy_mode(node, &if_mode);
-	if (!err)
-		return if_mode;
+	err = fwnode_get_phy_mode(dpmac_node);
+	if (err > 0)
+		return err;
 
 	err = phy_mode(attr.eth_if, &if_mode);
 	if (!err)
@@ -235,26 +250,27 @@ static const struct phylink_mac_ops dpaa2_mac_phylink_ops = {
 };
 
 static int dpaa2_pcs_create(struct dpaa2_mac *mac,
-			    struct device_node *dpmac_node, int id)
+			    struct fwnode_handle *dpmac_node,
+			    int id)
 {
 	struct mdio_device *mdiodev;
-	struct device_node *node;
+	struct fwnode_handle *node;
 
-	node = of_parse_phandle(dpmac_node, "pcs-handle", 0);
-	if (!node) {
+	node = fwnode_find_reference(dpmac_node, "pcs-handle", 0);
+	if (IS_ERR(node)) {
 		/* do not error out on old DTS files */
 		netdev_warn(mac->net_dev, "pcs-handle node not found\n");
 		return 0;
 	}
 
-	if (!of_device_is_available(node)) {
+	if (!fwnode_device_is_available(node)) {
 		netdev_err(mac->net_dev, "pcs-handle node not available\n");
-		of_node_put(node);
+		fwnode_handle_put(node);
 		return -ENODEV;
 	}
 
-	mdiodev = of_mdio_find_device(node);
-	of_node_put(node);
+	mdiodev = fwnode_mdio_find_device(node);
+	fwnode_handle_put(node);
 	if (!mdiodev)
 		return -EPROBE_DEFER;
 
@@ -283,36 +299,33 @@ static void dpaa2_pcs_destroy(struct dpaa2_mac *mac)
 int dpaa2_mac_connect(struct dpaa2_mac *mac)
 {
 	struct net_device *net_dev = mac->net_dev;
-	struct device_node *dpmac_node;
+	struct fwnode_handle *dpmac_node;
 	struct phylink *phylink;
 	int err;
 
 	mac->if_link_type = mac->attr.link_type;
 
-	dpmac_node = dpaa2_mac_get_node(mac->attr.id);
+	dpmac_node = mac->fw_node;
 	if (!dpmac_node) {
 		netdev_err(net_dev, "No dpmac@%d node found.\n", mac->attr.id);
 		return -ENODEV;
 	}
 
 	err = dpaa2_mac_get_if_mode(dpmac_node, mac->attr);
-	if (err < 0) {
-		err = -EINVAL;
-		goto err_put_node;
-	}
+	if (err < 0)
+		return -EINVAL;
 	mac->if_mode = err;
 
 	/* The MAC does not have the capability to add RGMII delays so
 	 * error out if the interface mode requests them and there is no PHY
 	 * to act upon them
 	 */
-	if (of_phy_is_fixed_link(dpmac_node) &&
+	if (of_phy_is_fixed_link(to_of_node(dpmac_node)) &&
 	    (mac->if_mode == PHY_INTERFACE_MODE_RGMII_ID ||
 	     mac->if_mode == PHY_INTERFACE_MODE_RGMII_RXID ||
 	     mac->if_mode == PHY_INTERFACE_MODE_RGMII_TXID)) {
 		netdev_err(net_dev, "RGMII delay not supported\n");
-		err = -EINVAL;
-		goto err_put_node;
+		return -EINVAL;
 	}
 
 	if ((mac->attr.link_type == DPMAC_LINK_TYPE_PHY &&
@@ -320,14 +333,14 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac)
 	    mac->attr.link_type == DPMAC_LINK_TYPE_BACKPLANE) {
 		err = dpaa2_pcs_create(mac, dpmac_node, mac->attr.id);
 		if (err)
-			goto err_put_node;
+			return err;
 	}
 
 	mac->phylink_config.dev = &net_dev->dev;
 	mac->phylink_config.type = PHYLINK_NETDEV;
 
 	phylink = phylink_create(&mac->phylink_config,
-				 of_fwnode_handle(dpmac_node), mac->if_mode,
+				 dpmac_node, mac->if_mode,
 				 &dpaa2_mac_phylink_ops);
 	if (IS_ERR(phylink)) {
 		err = PTR_ERR(phylink);
@@ -338,22 +351,18 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac)
 	if (mac->pcs)
 		phylink_set_pcs(mac->phylink, &mac->pcs->pcs);
 
-	err = phylink_of_phy_connect(mac->phylink, dpmac_node, 0);
+	err = phylink_fwnode_phy_connect(mac->phylink, dpmac_node, 0);
 	if (err) {
-		netdev_err(net_dev, "phylink_of_phy_connect() = %d\n", err);
+		netdev_err(net_dev, "phylink_fwnode_phy_connect() = %d\n", err);
 		goto err_phylink_destroy;
 	}
 
-	of_node_put(dpmac_node);
-
 	return 0;
 
 err_phylink_destroy:
 	phylink_destroy(mac->phylink);
 err_pcs_destroy:
 	dpaa2_pcs_destroy(mac);
-err_put_node:
-	of_node_put(dpmac_node);
 
 	return err;
 }
@@ -388,6 +397,12 @@ int dpaa2_mac_open(struct dpaa2_mac *mac)
 		goto err_close_dpmac;
 	}
 
+	/* Find the device node representing the MAC device and link the device
+	 * behind the associated netdev to it.
+	 */
+	mac->fw_node = dpaa2_mac_get_node(&mac->mc_dev->dev, mac->attr.id);
+	net_dev->dev.of_node = to_of_node(mac->fw_node);
+
 	return 0;
 
 err_close_dpmac:
@@ -400,6 +415,8 @@ void dpaa2_mac_close(struct dpaa2_mac *mac)
 	struct fsl_mc_device *dpmac_dev = mac->mc_dev;
 
 	dpmac_close(mac->mc_io, 0, dpmac_dev->mc_handle);
+	if (mac->fw_node)
+		fwnode_handle_put(mac->fw_node);
 }
 
 static char dpaa2_mac_ethtool_stats[][ETH_GSTRING_LEN] = {
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h
index 13d42dd58ec9..7842cbb2207a 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h
@@ -24,6 +24,7 @@ struct dpaa2_mac {
 	phy_interface_t if_mode;
 	enum dpmac_link_type if_link_type;
 	struct lynx_pcs *pcs;
+	struct fwnode_handle *fw_node;
 };
 
 bool dpaa2_mac_is_type_fixed(struct fsl_mc_device *dpmac_dev,
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ierb.c b/drivers/net/ethernet/freescale/enetc/enetc_ierb.c
index 8b356c485507..ee1468e3eaa3 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ierb.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ierb.c
@@ -99,15 +99,13 @@ EXPORT_SYMBOL(enetc_ierb_register_pf);
 static int enetc_ierb_probe(struct platform_device *pdev)
 {
 	struct enetc_ierb *ierb;
-	struct resource *res;
 	void __iomem *regs;
 
 	ierb = devm_kzalloc(&pdev->dev, sizeof(*ierb), GFP_KERNEL);
 	if (!ierb)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	regs = devm_ioremap_resource(&pdev->dev, res);
+	regs = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
 	if (IS_ERR(regs))
 		return PTR_ERR(regs);
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 31274325159a..c84f6c226743 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
 /* Copyright 2017-2019 NXP */
 
+#include <asm/unaligned.h>
 #include <linux/mdio.h>
 #include <linux/module.h>
 #include <linux/fsl/enetc_mdio.h>
@@ -17,15 +18,15 @@ static void enetc_pf_get_primary_mac_addr(struct enetc_hw *hw, int si, u8 *addr)
 	u32 upper = __raw_readl(hw->port + ENETC_PSIPMAR0(si));
 	u16 lower = __raw_readw(hw->port + ENETC_PSIPMAR1(si));
 
-	*(u32 *)addr = upper;
-	*(u16 *)(addr + 4) = lower;
+	put_unaligned_le32(upper, addr);
+	put_unaligned_le16(lower, addr + 4);
 }
 
 static void enetc_pf_set_primary_mac_addr(struct enetc_hw *hw, int si,
 					  const u8 *addr)
 {
-	u32 upper = *(const u32 *)addr;
-	u16 lower = *(const u16 *)(addr + 4);
+	u32 upper = get_unaligned_le32(addr);
+	u16 lower = get_unaligned_le16(addr + 4);
 
 	__raw_writel(upper, hw->port + ENETC_PSIPMAR0(si));
 	__raw_writew(lower, hw->port + ENETC_PSIPMAR1(si));
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
index af699f2ad095..4577226d3c6a 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
@@ -465,8 +465,13 @@ static int enetc_streamid_hw_set(struct enetc_ndev_priv *priv,
 	struct streamid_conf *si_conf;
 	u16 data_size;
 	dma_addr_t dma;
+	int port;
 	int err;
 
+	port = enetc_pf_to_port(priv->si->pdev);
+	if (port < 0)
+		return -EINVAL;
+
 	if (sid->index >= priv->psfp_cap.max_streamid)
 		return -EINVAL;
 
@@ -499,7 +504,7 @@ static int enetc_streamid_hw_set(struct enetc_ndev_priv *priv,
 
 	si_conf = &cbd.sid_set;
 	/* Only one port supported for one entry, set itself */
-	si_conf->iports = cpu_to_le32(1 << enetc_pf_to_port(priv->si->pdev));
+	si_conf->iports = cpu_to_le32(1 << port);
 	si_conf->id_type = 1;
 	si_conf->oui[2] = 0x0;
 	si_conf->oui[1] = 0x80;
@@ -524,7 +529,7 @@ static int enetc_streamid_hw_set(struct enetc_ndev_priv *priv,
 
 	si_conf->en = 0x80;
 	si_conf->stream_handle = cpu_to_le32(sid->handle);
-	si_conf->iports = cpu_to_le32(1 << enetc_pf_to_port(priv->si->pdev));
+	si_conf->iports = cpu_to_le32(1 << port);
 	si_conf->id_type = sid->filtertype;
 	si_conf->oui[2] = 0x0;
 	si_conf->oui[1] = 0x80;
@@ -567,6 +572,11 @@ static int enetc_streamfilter_hw_set(struct enetc_ndev_priv *priv,
 {
 	struct enetc_cbd cbd = {.cmd = 0};
 	struct sfi_conf *sfi_config;
+	int port;
+
+	port = enetc_pf_to_port(priv->si->pdev);
+	if (port < 0)
+		return -EINVAL;
 
 	cbd.index = cpu_to_le16(sfi->index);
 	cbd.cls = BDCR_CMD_STREAM_FILTER;
@@ -586,8 +596,7 @@ static int enetc_streamfilter_hw_set(struct enetc_ndev_priv *priv,
 	}
 
 	sfi_config->sg_inst_table_index = cpu_to_le16(sfi->gate_id);
-	sfi_config->input_ports =
-		cpu_to_le32(1 << enetc_pf_to_port(priv->si->pdev));
+	sfi_config->input_ports = cpu_to_le32(1 << port);
 
 	/* The priority value which may be matched against the
 	 * frame’s priority value to determine a match for this entry.
@@ -1548,7 +1557,7 @@ int enetc_setup_tc_psfp(struct net_device *ndev, void *type_data)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	struct flow_block_offload *f = type_data;
-	int err;
+	int port, err;
 
 	err = flow_block_cb_setup_simple(f, &enetc_block_cb_list,
 					 enetc_setup_tc_block_cb,
@@ -1558,10 +1567,18 @@ int enetc_setup_tc_psfp(struct net_device *ndev, void *type_data)
 
 	switch (f->command) {
 	case FLOW_BLOCK_BIND:
-		set_bit(enetc_pf_to_port(priv->si->pdev), &epsfp.dev_bitmap);
+		port = enetc_pf_to_port(priv->si->pdev);
+		if (port < 0)
+			return -EINVAL;
+
+		set_bit(port, &epsfp.dev_bitmap);
 		break;
 	case FLOW_BLOCK_UNBIND:
-		clear_bit(enetc_pf_to_port(priv->si->pdev), &epsfp.dev_bitmap);
+		port = enetc_pf_to_port(priv->si->pdev);
+		if (port < 0)
+			return -EINVAL;
+
+		clear_bit(port, &epsfp.dev_bitmap);
 		if (!epsfp.dev_bitmap)
 			clean_psfp_all();
 		break;
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index f2945abdb041..9646483137c4 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -274,32 +274,44 @@ static void gfar_configure_coalescing_all(struct gfar_private *priv)
 	gfar_configure_coalescing(priv, 0xFF, 0xFF);
 }
 
-static struct net_device_stats *gfar_get_stats(struct net_device *dev)
+static void gfar_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct gfar_private *priv = netdev_priv(dev);
-	unsigned long rx_packets = 0, rx_bytes = 0, rx_dropped = 0;
-	unsigned long tx_packets = 0, tx_bytes = 0;
 	int i;
 
 	for (i = 0; i < priv->num_rx_queues; i++) {
-		rx_packets += priv->rx_queue[i]->stats.rx_packets;
-		rx_bytes   += priv->rx_queue[i]->stats.rx_bytes;
-		rx_dropped += priv->rx_queue[i]->stats.rx_dropped;
+		stats->rx_packets += priv->rx_queue[i]->stats.rx_packets;
+		stats->rx_bytes   += priv->rx_queue[i]->stats.rx_bytes;
+		stats->rx_dropped += priv->rx_queue[i]->stats.rx_dropped;
 	}
 
-	dev->stats.rx_packets = rx_packets;
-	dev->stats.rx_bytes   = rx_bytes;
-	dev->stats.rx_dropped = rx_dropped;
-
 	for (i = 0; i < priv->num_tx_queues; i++) {
-		tx_bytes += priv->tx_queue[i]->stats.tx_bytes;
-		tx_packets += priv->tx_queue[i]->stats.tx_packets;
+		stats->tx_bytes += priv->tx_queue[i]->stats.tx_bytes;
+		stats->tx_packets += priv->tx_queue[i]->stats.tx_packets;
 	}
 
-	dev->stats.tx_bytes   = tx_bytes;
-	dev->stats.tx_packets = tx_packets;
+	if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) {
+		struct rmon_mib __iomem *rmon = &priv->gfargrp[0].regs->rmon;
+		unsigned long flags;
+		u32 rdrp, car, car_before;
+		u64 rdrp_offset;
+
+		spin_lock_irqsave(&priv->rmon_overflow.lock, flags);
+		car = gfar_read(&rmon->car1) & CAR1_C1RDR;
+		do {
+			car_before = car;
+			rdrp = gfar_read(&rmon->rdrp);
+			car = gfar_read(&rmon->car1) & CAR1_C1RDR;
+		} while (car != car_before);
+		if (car) {
+			priv->rmon_overflow.rdrp++;
+			gfar_write(&rmon->car1, car);
+		}
+		rdrp_offset = priv->rmon_overflow.rdrp;
+		spin_unlock_irqrestore(&priv->rmon_overflow.lock, flags);
 
-	return &dev->stats;
+		stats->rx_missed_errors = rdrp + (rdrp_offset << 16);
+	}
 }
 
 /* Set the appropriate hash bit for the given addr */
@@ -390,7 +402,8 @@ static void gfar_ints_enable(struct gfar_private *priv)
 	for (i = 0; i < priv->num_grps; i++) {
 		struct gfar __iomem *regs = priv->gfargrp[i].regs;
 		/* Unmask the interrupts we look for */
-		gfar_write(&regs->imask, IMASK_DEFAULT);
+		gfar_write(&regs->imask,
+			   IMASK_DEFAULT | priv->rmon_overflow.imask);
 	}
 }
 
@@ -2298,7 +2311,7 @@ static irqreturn_t gfar_receive(int irq, void *grp_id)
 	if (likely(napi_schedule_prep(&grp->napi_rx))) {
 		spin_lock_irqsave(&grp->grplock, flags);
 		imask = gfar_read(&grp->regs->imask);
-		imask &= IMASK_RX_DISABLED;
+		imask &= IMASK_RX_DISABLED | grp->priv->rmon_overflow.imask;
 		gfar_write(&grp->regs->imask, imask);
 		spin_unlock_irqrestore(&grp->grplock, flags);
 		__napi_schedule(&grp->napi_rx);
@@ -2322,7 +2335,7 @@ static irqreturn_t gfar_transmit(int irq, void *grp_id)
 	if (likely(napi_schedule_prep(&grp->napi_tx))) {
 		spin_lock_irqsave(&grp->grplock, flags);
 		imask = gfar_read(&grp->regs->imask);
-		imask &= IMASK_TX_DISABLED;
+		imask &= IMASK_TX_DISABLED | grp->priv->rmon_overflow.imask;
 		gfar_write(&grp->regs->imask, imask);
 		spin_unlock_irqrestore(&grp->grplock, flags);
 		__napi_schedule(&grp->napi_tx);
@@ -2693,6 +2706,18 @@ static irqreturn_t gfar_error(int irq, void *grp_id)
 		}
 		netif_dbg(priv, tx_err, dev, "Transmit Error\n");
 	}
+	if (events & IEVENT_MSRO) {
+		struct rmon_mib __iomem *rmon = &regs->rmon;
+		u32 car;
+
+		spin_lock(&priv->rmon_overflow.lock);
+		car = gfar_read(&rmon->car1) & CAR1_C1RDR;
+		if (car) {
+			priv->rmon_overflow.rdrp++;
+			gfar_write(&rmon->car1, car);
+		}
+		spin_unlock(&priv->rmon_overflow.lock);
+	}
 	if (events & IEVENT_BSY) {
 		dev->stats.rx_over_errors++;
 		atomic64_inc(&priv->extra_stats.rx_bsy);
@@ -3109,11 +3134,14 @@ static void gfar_hw_init(struct gfar_private *priv)
 
 	/* Zero out the rmon mib registers if it has them */
 	if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) {
-		memset_io(&(regs->rmon), 0, sizeof(struct rmon_mib));
+		memset_io(&regs->rmon, 0, offsetof(struct rmon_mib, car1));
 
 		/* Mask off the CAM interrupts */
 		gfar_write(&regs->rmon.cam1, 0xffffffff);
 		gfar_write(&regs->rmon.cam2, 0xffffffff);
+		/* Clear the CAR registers (w1c style) */
+		gfar_write(&regs->rmon.car1, 0xffffffff);
+		gfar_write(&regs->rmon.car2, 0xffffffff);
 	}
 
 	/* Initialize ECNTRL */
@@ -3157,7 +3185,7 @@ static const struct net_device_ops gfar_netdev_ops = {
 	.ndo_set_rx_mode = gfar_set_multi,
 	.ndo_tx_timeout = gfar_timeout,
 	.ndo_do_ioctl = gfar_ioctl,
-	.ndo_get_stats = gfar_get_stats,
+	.ndo_get_stats64 = gfar_get_stats64,
 	.ndo_change_carrier = fixed_phy_change_carrier,
 	.ndo_set_mac_address = gfar_set_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
@@ -3267,6 +3295,14 @@ static int gfar_probe(struct platform_device *ofdev)
 
 	gfar_hw_init(priv);
 
+	if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) {
+		struct rmon_mib __iomem *rmon = &priv->gfargrp[0].regs->rmon;
+
+		spin_lock_init(&priv->rmon_overflow.lock);
+		priv->rmon_overflow.imask = IMASK_MSRO;
+		gfar_write(&rmon->cam1, gfar_read(&rmon->cam1) & ~CAM1_M1RDR);
+	}
+
 	/* Carrier starts down, phylib will bring it up */
 	netif_carrier_off(dev);
 
diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h
index 5ea47df93e5e..ca5e14f908fe 100644
--- a/drivers/net/ethernet/freescale/gianfar.h
+++ b/drivers/net/ethernet/freescale/gianfar.h
@@ -445,6 +445,60 @@ struct ethtool_rx_list {
 #define RQFPR_PER		0x00000002
 #define RQFPR_EER		0x00000001
 
+/* CAR1 bits */
+#define CAR1_C164		0x80000000
+#define CAR1_C1127		0x40000000
+#define CAR1_C1255		0x20000000
+#define CAR1_C1511		0x10000000
+#define CAR1_C11K		0x08000000
+#define CAR1_C1MAX		0x04000000
+#define CAR1_C1MGV		0x02000000
+#define CAR1_C1REJ		0x00020000
+#define CAR1_C1RBY		0x00010000
+#define CAR1_C1RPK		0x00008000
+#define CAR1_C1RFC		0x00004000
+#define CAR1_C1RMC		0x00002000
+#define CAR1_C1RBC		0x00001000
+#define CAR1_C1RXC		0x00000800
+#define CAR1_C1RXP		0x00000400
+#define CAR1_C1RXU		0x00000200
+#define CAR1_C1RAL		0x00000100
+#define CAR1_C1RFL		0x00000080
+#define CAR1_C1RCD		0x00000040
+#define CAR1_C1RCS		0x00000020
+#define CAR1_C1RUN		0x00000010
+#define CAR1_C1ROV		0x00000008
+#define CAR1_C1RFR		0x00000004
+#define CAR1_C1RJB		0x00000002
+#define CAR1_C1RDR		0x00000001
+
+/* CAM1 bits */
+#define CAM1_M164		0x80000000
+#define CAM1_M1127		0x40000000
+#define CAM1_M1255		0x20000000
+#define CAM1_M1511		0x10000000
+#define CAM1_M11K		0x08000000
+#define CAM1_M1MAX		0x04000000
+#define CAM1_M1MGV		0x02000000
+#define CAM1_M1REJ		0x00020000
+#define CAM1_M1RBY		0x00010000
+#define CAM1_M1RPK		0x00008000
+#define CAM1_M1RFC		0x00004000
+#define CAM1_M1RMC		0x00002000
+#define CAM1_M1RBC		0x00001000
+#define CAM1_M1RXC		0x00000800
+#define CAM1_M1RXP		0x00000400
+#define CAM1_M1RXU		0x00000200
+#define CAM1_M1RAL		0x00000100
+#define CAM1_M1RFL		0x00000080
+#define CAM1_M1RCD		0x00000040
+#define CAM1_M1RCS		0x00000020
+#define CAM1_M1RUN		0x00000010
+#define CAM1_M1ROV		0x00000008
+#define CAM1_M1RFR		0x00000004
+#define CAM1_M1RJB		0x00000002
+#define CAM1_M1RDR		0x00000001
+
 /* TxBD status field bits */
 #define TXBD_READY		0x8000
 #define TXBD_PADCRC		0x4000
@@ -609,6 +663,15 @@ struct rmon_mib
 	u32	cam2;	/* 0x.73c - Carry Mask Register Two */
 };
 
+struct rmon_overflow {
+	/* lock for synchronization of the rdrp field of this struct, and
+	 * CAR1/CAR2 registers
+	 */
+	spinlock_t lock;
+	u32	imask;
+	u64	rdrp;
+};
+
 struct gfar_extra_stats {
 	atomic64_t rx_alloc_err;
 	atomic64_t rx_large;
@@ -913,8 +976,8 @@ enum {
  * Per TX queue stats
  */
 struct tx_q_stats {
-	unsigned long tx_packets;
-	unsigned long tx_bytes;
+	u64 tx_packets;
+	u64 tx_bytes;
 };
 
 /**
@@ -963,9 +1026,9 @@ struct gfar_priv_tx_q {
  * Per RX queue stats
  */
 struct rx_q_stats {
-	unsigned long rx_packets;
-	unsigned long rx_bytes;
-	unsigned long rx_dropped;
+	u64 rx_packets;
+	u64 rx_bytes;
+	u64 rx_dropped;
 };
 
 struct gfar_rx_buff {
@@ -1096,6 +1159,7 @@ struct gfar_private {
 
 	/* Network Statistics */
 	struct gfar_extra_stats extra_stats;
+	struct rmon_overflow rmon_overflow;
 
 	/* PHY stuff */
 	phy_interface_t interface;
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index e0936510fa34..0acfafb73db1 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -3590,10 +3590,9 @@ static int ucc_geth_probe(struct platform_device* ofdev)
 	if ((ucc_num < 0) || (ucc_num > 7))
 		return -ENODEV;
 
-	ug_info = kmalloc(sizeof(*ug_info), GFP_KERNEL);
+	ug_info = kmemdup(&ugeth_primary_info, sizeof(*ug_info), GFP_KERNEL);
 	if (ug_info == NULL)
 		return -ENOMEM;
-	memcpy(ug_info, &ugeth_primary_info, sizeof(*ug_info));
 
 	ug_info->uf_info.ucc_num = ucc_num;
 
diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c
index bfa2826c5545..0b68852379da 100644
--- a/drivers/net/ethernet/freescale/xgmac_mdio.c
+++ b/drivers/net/ethernet/freescale/xgmac_mdio.c
@@ -2,6 +2,7 @@
  * QorIQ 10G MDIO Controller
  *
  * Copyright 2012 Freescale Semiconductor, Inc.
+ * Copyright 2021 NXP
  *
  * Authors: Andy Fleming <afleming@freescale.com>
  *          Timur Tabi <timur@freescale.com>
@@ -11,15 +12,17 @@
  * kind, whether express or implied.
  */
 
-#include <linux/kernel.h>
-#include <linux/slab.h>
+#include <linux/acpi.h>
+#include <linux/acpi_mdio.h>
 #include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/phy.h>
+#include <linux/kernel.h>
 #include <linux/mdio.h>
+#include <linux/module.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
 #include <linux/of_mdio.h>
+#include <linux/of_platform.h>
+#include <linux/phy.h>
+#include <linux/slab.h>
 
 /* Number of microseconds to wait for a register to respond */
 #define TIMEOUT	1000
@@ -243,10 +246,10 @@ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
 
 static int xgmac_mdio_probe(struct platform_device *pdev)
 {
-	struct device_node *np = pdev->dev.of_node;
-	struct mii_bus *bus;
-	struct resource *res;
+	struct fwnode_handle *fwnode;
 	struct mdio_fsl_priv *priv;
+	struct resource *res;
+	struct mii_bus *bus;
 	int ret;
 
 	/* In DPAA-1, MDIO is one of the many FMan sub-devices. The FMan
@@ -279,13 +282,22 @@ static int xgmac_mdio_probe(struct platform_device *pdev)
 		goto err_ioremap;
 	}
 
+	/* For both ACPI and DT cases, endianness of MDIO controller
+	 * needs to be specified using "little-endian" property.
+	 */
 	priv->is_little_endian = device_property_read_bool(&pdev->dev,
 							   "little-endian");
 
 	priv->has_a011043 = device_property_read_bool(&pdev->dev,
 						      "fsl,erratum-a011043");
 
-	ret = of_mdiobus_register(bus, np);
+	fwnode = pdev->dev.fwnode;
+	if (is_of_node(fwnode))
+		ret = of_mdiobus_register(bus, to_of_node(fwnode));
+	else if (is_acpi_node(fwnode))
+		ret = acpi_mdiobus_register(bus, fwnode);
+	else
+		ret = -EINVAL;
 	if (ret) {
 		dev_err(&pdev->dev, "cannot register MDIO bus\n");
 		goto err_registration;
diff --git a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
index b0c0504950d8..62c0bed82ced 100644
--- a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
+++ b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
@@ -812,9 +812,9 @@ static netdev_tx_t fjn_start_xmit(struct sk_buff *skb,
     
     if (length < ETH_ZLEN)
     {
-    	if (skb_padto(skb, ETH_ZLEN))
-    		return NETDEV_TX_OK;
-    	length = ETH_ZLEN;
+	if (skb_padto(skb, ETH_ZLEN))
+		return NETDEV_TX_OK;
+	length = ETH_ZLEN;
     }
 
     netif_stop_queue(dev);
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index 44f9279cdde1..bb062b02fb85 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -102,6 +102,7 @@ config HNS3_HCLGE
 	tristate "Hisilicon HNS3 HCLGE Acceleration Engine & Compatibility Layer Support"
 	default m
 	depends on PCI_MSI
+	imply PTP_1588_CLOCK
 	help
 	  This selects the HNS3_HCLGE network acceleration engine & its hardware
 	  compatibility layer. The engine would be used in Hisilicon hip08 family of
@@ -130,6 +131,7 @@ config HNS3_ENET
 	default m
 	depends on 64BIT && PCI
 	depends on INET
+	select DIMLIB
 	help
 	  This selects the Ethernet Driver for Hisilicon Network Subsystem 3 for hip08
 	  family of SoCs. This module depends upon HNAE3 driver to access the HNAE3
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
index c615fbf9094e..75e4ec569da8 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
@@ -462,8 +462,6 @@ static void hns_ae_adjust_link(struct hnae_handle *handle, int speed,
 	default:
 		break;
 	}
-
-	return;
 }
 
 static void hns_ae_get_ring_bdnum_limit(struct hnae_queue *queue,
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index f4cf569a2599..f41379de2186 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -111,7 +111,7 @@ int hns_mac_get_port_info(struct hns_mac_cb *mac_cb,
 }
 
 /**
- *hns_mac_is_adjust_link - check is need change mac speed and duplex register
+ *hns_mac_need_adjust_link - check is need change mac speed and duplex register
  *@mac_cb: mac device
  *@speed: phy device speed
  *@duplex:phy device duplex
@@ -374,7 +374,7 @@ static void hns_mac_param_get(struct mac_params *param,
 }
 
 /**
- * hns_mac_queue_config_bc_en - set broadcast rx&tx enable
+ * hns_mac_port_config_bc_en - set broadcast rx&tx enable
  * @mac_cb: mac device
  * @port_num: queue number
  * @vlan_id: vlan id`
@@ -597,7 +597,7 @@ int hns_mac_set_autoneg(struct hns_mac_cb *mac_cb, u8 enable)
 }
 
 /**
- * hns_mac_set_autoneg - set rx & tx pause parameter
+ * hns_mac_set_pauseparam - set rx & tx pause parameter
  * @mac_cb: mac control block
  * @rx_en: rx enable or not
  * @tx_en: tx enable or not
@@ -914,8 +914,7 @@ static int hns_mac_get_info(struct hns_mac_cb *mac_cb)
 		}
 	} else if (is_acpi_node(mac_cb->fw_port)) {
 		ret = hns_mac_register_phy(mac_cb);
-		/*
-		 * Mac can work well if there is phy or not.If the port don't
+		/* Mac can work well if there is phy or not.If the port don't
 		 * connect with phy, the return value will be ignored. Only
 		 * when there is phy but can't find mdio bus, the return value
 		 * will be handled.
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index c2a60612f503..fcaf5132b865 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -227,7 +227,7 @@ hns_dsaf_reg_cnt_clr_ce(struct dsaf_device *dsaf_dev, u32 reg_cnt_clr_ce)
 }
 
 /**
- * hns_ppe_qid_cfg - config ppe qid
+ * hns_dsaf_ppe_qid_cfg - config ppe qid
  * @dsaf_dev: dsa fabric id
  * @qid_cfg: value array
  */
@@ -613,7 +613,7 @@ static void hns_dsaf_tbl_tcam_data_cfg(
 }
 
 /**
- * dsaf_tbl_tcam_mcast_cfg - tbl
+ * hns_dsaf_tbl_tcam_mcast_cfg - tbl
  * @dsaf_dev: dsa fabric id
  * @mcast: addr
  */
@@ -1213,7 +1213,7 @@ void hns_dsaf_get_rx_mac_pause_en(struct dsaf_device *dsaf_dev, int mac_id,
 }
 
 /**
- * hns_dsaf_tbl_tcam_init - INT
+ * hns_dsaf_comm_init - INT
  * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_comm_init(struct dsaf_device *dsaf_dev)
@@ -2111,7 +2111,7 @@ static void hns_dsaf_free_dev(struct dsaf_device *dsaf_dev)
 }
 
 /**
- * dsaf_pfc_unit_cnt - set pfc unit count
+ * hns_dsaf_pfc_unit_cnt - set pfc unit count
  * @dsaf_dev: dsa fabric id
  * @mac_id: id in use
  * @rate:  value array
@@ -2142,7 +2142,7 @@ static void hns_dsaf_pfc_unit_cnt(struct dsaf_device *dsaf_dev, int  mac_id,
 }
 
 /**
- * dsaf_port_work_rate_cfg - fifo
+ * hns_dsaf_port_work_rate_cfg - fifo
  * @dsaf_dev: dsa fabric id
  * @mac_id: mac contrl block
  * @rate_mode: value array
@@ -2738,7 +2738,7 @@ void hns_dsaf_get_strings(int stringset, u8 *data, int port,
 }
 
 /**
- *hns_dsaf_get_sset_count - get dsaf regs count
+ *hns_dsaf_get_regs_count - get dsaf regs count
  *return dsaf regs count
  */
 int hns_dsaf_get_regs_count(void)
@@ -2949,7 +2949,7 @@ int hns_dsaf_wait_pkt_clean(struct dsaf_device *dsaf_dev, int port)
 }
 
 /**
- * dsaf_probe - probo dsaf dev
+ * hns_dsaf_probe - probo dsaf dev
  * @pdev: dasf platform device
  * return 0 - success , negative --fail
  */
@@ -3004,7 +3004,7 @@ free_dev:
 }
 
 /**
- * dsaf_remove - remove dsaf dev
+ * hns_dsaf_remove - remove dsaf dev
  * @pdev: dasf platform device
  */
 static int hns_dsaf_remove(struct platform_device *pdev)
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index 325e81d30cfd..23d9cbf262c3 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -56,31 +56,31 @@ static u32 dsaf_read_sub(struct dsaf_device *dsaf_dev, u32 reg)
 }
 
 static void hns_dsaf_acpi_ledctrl_by_port(struct hns_mac_cb *mac_cb, u8 op_type,
-                                      u32 link, u32 port, u32 act)
+					  u32 link, u32 port, u32 act)
 {
-       union acpi_object *obj;
-       union acpi_object obj_args[3], argv4;
+	union acpi_object *obj;
+	union acpi_object obj_args[3], argv4;
 
-       obj_args[0].integer.type = ACPI_TYPE_INTEGER;
-       obj_args[0].integer.value = link;
-       obj_args[1].integer.type = ACPI_TYPE_INTEGER;
-       obj_args[1].integer.value = port;
-       obj_args[2].integer.type = ACPI_TYPE_INTEGER;
-       obj_args[2].integer.value = act;
+	obj_args[0].integer.type = ACPI_TYPE_INTEGER;
+	obj_args[0].integer.value = link;
+	obj_args[1].integer.type = ACPI_TYPE_INTEGER;
+	obj_args[1].integer.value = port;
+	obj_args[2].integer.type = ACPI_TYPE_INTEGER;
+	obj_args[2].integer.value = act;
 
-       argv4.type = ACPI_TYPE_PACKAGE;
-       argv4.package.count = 3;
-       argv4.package.elements = obj_args;
+	argv4.type = ACPI_TYPE_PACKAGE;
+	argv4.package.count = 3;
+	argv4.package.elements = obj_args;
 
-       obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev),
-                               &hns_dsaf_acpi_dsm_guid, 0, op_type, &argv4);
-       if (!obj) {
-               dev_warn(mac_cb->dev, "ledctrl fail, link:%d port:%d act:%d!\n",
-                        link, port, act);
-               return;
-       }
+	obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev),
+				&hns_dsaf_acpi_dsm_guid, 0, op_type, &argv4);
+	if (!obj) {
+		dev_warn(mac_cb->dev, "ledctrl fail, link:%d port:%d act:%d!\n",
+			 link, port, act);
+		return;
+	}
 
-       ACPI_FREE(obj);
+	ACPI_FREE(obj);
 }
 
 static void hns_dsaf_acpi_locate_ledctrl_by_port(struct hns_mac_cb *mac_cb,
@@ -151,15 +151,15 @@ static void hns_cpld_set_led(struct hns_mac_cb *mac_cb, int link_status,
 }
 
 static void hns_cpld_set_led_acpi(struct hns_mac_cb *mac_cb, int link_status,
-                            u16 speed, int data)
+				  u16 speed, int data)
 {
-       if (!mac_cb) {
-               pr_err("cpld_led_set mac_cb is null!\n");
-               return;
-       }
+	if (!mac_cb) {
+		pr_err("cpld_led_set mac_cb is null!\n");
+		return;
+	}
 
-       hns_dsaf_acpi_ledctrl_by_port(mac_cb, HNS_OP_LED_SET_FUNC,
-               link_status, mac_cb->mac_id, data);
+	hns_dsaf_acpi_ledctrl_by_port(mac_cb, HNS_OP_LED_SET_FUNC,
+				      link_status, mac_cb->mac_id, data);
 }
 
 static void cpld_led_reset(struct hns_mac_cb *mac_cb)
@@ -174,16 +174,16 @@ static void cpld_led_reset(struct hns_mac_cb *mac_cb)
 
 static void cpld_led_reset_acpi(struct hns_mac_cb *mac_cb)
 {
-       if (!mac_cb) {
-               pr_err("cpld_led_reset mac_cb is null!\n");
-               return;
-       }
+	if (!mac_cb) {
+		pr_err("cpld_led_reset mac_cb is null!\n");
+		return;
+	}
 
-       if (mac_cb->media_type != HNAE_MEDIA_TYPE_FIBER)
-                return;
+	if (mac_cb->media_type != HNAE_MEDIA_TYPE_FIBER)
+		return;
 
-       hns_dsaf_acpi_ledctrl_by_port(mac_cb, HNS_OP_LED_SET_FUNC,
-               0, mac_cb->mac_id, 0);
+	hns_dsaf_acpi_ledctrl_by_port(mac_cb, HNS_OP_LED_SET_FUNC,
+				      0, mac_cb->mac_id, 0);
 }
 
 static int cpld_set_led_id(struct hns_mac_cb *mac_cb,
@@ -351,7 +351,7 @@ hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset)
 }
 
 /**
- * hns_dsaf_srst_chns - reset dsaf channels
+ * hns_dsaf_srst_chns_acpi - reset dsaf channels
  * @dsaf_dev: dsaf device struct pointer
  * @msk: xbar channels mask value:
  * @dereset: false - request reset , true - drop reset
@@ -501,7 +501,7 @@ static void hns_ppe_com_srst(struct dsaf_device *dsaf_dev, bool dereset)
 }
 
 /**
- * hns_mac_get_sds_mode - get phy ifterface form serdes mode
+ * hns_mac_get_phy_if - get phy ifterface form serdes mode
  * @mac_cb: mac control block
  * retuen phy interface
  */
@@ -521,7 +521,7 @@ static phy_interface_t hns_mac_get_phy_if(struct hns_mac_cb *mac_cb)
 			reg = HNS_MAC_HILINK4_REG;
 		else
 			reg = HNS_MAC_HILINK3_REG;
-	} else{
+	} else {
 		if (!HNS_DSAF_IS_DEBUG(mac_cb->dsaf_dev) && mac_id <= 3)
 			reg = HNS_MAC_HILINK4V2_REG;
 		else
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
index ff03cafccb66..a7eb87da4e70 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
@@ -296,7 +296,7 @@ int hns_ppe_wait_tx_fifo_clean(struct hns_ppe_cb *ppe_cb)
 }
 
 /**
- * ppe_init_hw - init ppe
+ * hns_ppe_init_hw - init ppe
  * @ppe_cb: ppe device
  */
 static void hns_ppe_init_hw(struct hns_ppe_cb *ppe_cb)
@@ -343,7 +343,7 @@ static void hns_ppe_init_hw(struct hns_ppe_cb *ppe_cb)
 }
 
 /**
- * ppe_uninit_hw - uninit ppe
+ * hns_ppe_uninit_hw - uninit ppe
  * @ppe_cb: ppe device
  */
 static void hns_ppe_uninit_hw(struct hns_ppe_cb *ppe_cb)
@@ -382,7 +382,7 @@ void hns_ppe_uninit(struct dsaf_device *dsaf_dev)
 }
 
 /**
- * hns_ppe_reset - reinit ppe/rcb hw
+ * hns_ppe_reset_common - reinit ppe/rcb hw
  * @dsaf_dev: dasf device
  * @ppe_common_index: the index
  * return void
@@ -455,7 +455,7 @@ int hns_ppe_get_regs_count(void)
 }
 
 /**
- * ppe_get_strings - get ppe srting
+ * hns_ppe_get_strings - get ppe srting
  * @ppe_cb: ppe device
  * @stringset: string set type
  * @data: output string
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
index 5d5dc6942232..e2ff3ca198d1 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
@@ -913,7 +913,7 @@ int hns_rcb_get_common_regs_count(void)
 }
 
 /**
- *rcb_get_sset_count - rcb ring regs count
+ *hns_rcb_get_ring_regs_count - rcb ring regs count
  *return regs count
  */
 int hns_rcb_get_ring_regs_count(void)
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
index be52acd448f9..401fef5f1d07 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
@@ -104,7 +104,7 @@ static void hns_xgmac_rx_enable(struct mac_driver *drv, u32 value)
 }
 
 /**
- * hns_xgmac_tx_lf_rf_insert - insert lf rf control about xgmac
+ * hns_xgmac_lf_rf_insert - insert lf rf control about xgmac
  * @mac_drv: mac driver
  * @mode: inserf rf or lf
  */
@@ -115,7 +115,7 @@ static void hns_xgmac_lf_rf_insert(struct mac_driver *mac_drv, u32 mode)
 }
 
 /**
- * hns_xgmac__lf_rf_control_init - initial the lf rf control register
+ * hns_xgmac_lf_rf_control_init - initial the lf rf control register
  * @mac_drv: mac driver
  */
 static void hns_xgmac_lf_rf_control_init(struct mac_driver *mac_drv)
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 5e349c0bdecc..ad534f9e41ab 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -770,7 +770,7 @@ static u32 smooth_alg(u32 new_param, u32 old_param)
 }
 
 /**
- * hns_nic_adp_coalesce - self adapte coalesce according to rx rate
+ * hns_nic_adpt_coalesce - self adapte coalesce according to rx rate
  * @ring_data: pointer to hns_nic_ring_data
  **/
 static void hns_nic_adpt_coalesce(struct hns_nic_ring_data *ring_data)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
index a2c17af57fde..0a6cda309b24 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
@@ -20,7 +20,7 @@ enum HCLGE_MBX_OPCODE {
 	HCLGE_MBX_API_NEGOTIATE,	/* (VF -> PF) negotiate API version */
 	HCLGE_MBX_GET_QINFO,		/* (VF -> PF) get queue config */
 	HCLGE_MBX_GET_QDEPTH,		/* (VF -> PF) get queue depth */
-	HCLGE_MBX_GET_TCINFO,		/* (VF -> PF) get TC config */
+	HCLGE_MBX_GET_BASIC_INFO,	/* (VF -> PF) get basic info */
 	HCLGE_MBX_GET_RETA,		/* (VF -> PF) get RETA */
 	HCLGE_MBX_GET_RSS_KEY,		/* (VF -> PF) get RSS key */
 	HCLGE_MBX_GET_MAC_ADDR,		/* (VF -> PF) get MAC addr */
@@ -69,6 +69,7 @@ enum hclge_mbx_vlan_cfg_subcode {
 	HCLGE_MBX_VLAN_RX_OFF_CFG,	/* set rx side vlan offload */
 	HCLGE_MBX_PORT_BASE_VLAN_CFG,	/* set port based vlan configuration */
 	HCLGE_MBX_GET_PORT_BASE_VLAN_STATE,	/* get port based vlan state */
+	HCLGE_MBX_ENABLE_VLAN_FILTER,
 };
 
 enum hclge_mbx_tbl_cfg_subcode {
@@ -85,6 +86,13 @@ struct hclge_ring_chain_param {
 	u8 int_gl_index;
 };
 
+struct hclge_basic_info {
+	u8 hw_tc_map;
+	u8 rsv;
+	u16 mbx_api_version;
+	u32 pf_caps;
+};
+
 struct hclgevf_mbx_resp_status {
 	struct mutex mbx_mutex; /* protects against contending sync cmd resp */
 	u32 origin_mbx_msg;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 1d2189047781..0b202f4def83 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -91,6 +91,10 @@ enum HNAE3_DEV_CAP_BITS {
 	HNAE3_DEV_SUPPORT_STASH_B,
 	HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B,
 	HNAE3_DEV_SUPPORT_PAUSE_B,
+	HNAE3_DEV_SUPPORT_RAS_IMP_B,
+	HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B,
+	HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B,
+	HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B,
 };
 
 #define hnae3_dev_fd_supported(hdev) \
@@ -126,6 +130,9 @@ enum HNAE3_DEV_CAP_BITS {
 #define hnae3_dev_phy_imp_supported(hdev) \
 	test_bit(HNAE3_DEV_SUPPORT_PHY_IMP_B, (hdev)->ae_dev->caps)
 
+#define hnae3_dev_ras_imp_supported(hdev) \
+	test_bit(HNAE3_DEV_SUPPORT_RAS_IMP_B, (hdev)->ae_dev->caps)
+
 #define hnae3_dev_tqp_txrx_indep_supported(hdev) \
 	test_bit(HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B, (hdev)->ae_dev->caps)
 
@@ -141,18 +148,17 @@ enum HNAE3_DEV_CAP_BITS {
 #define hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev) \
 	test_bit(HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B, (ae_dev)->caps)
 
+#define hnae3_ae_dev_rxd_adv_layout_supported(ae_dev) \
+	test_bit(HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B, (ae_dev)->caps)
+
+enum HNAE3_PF_CAP_BITS {
+	HNAE3_PF_SUPPORT_VLAN_FLTR_MDF_B = 0,
+};
 #define ring_ptr_move_fw(ring, p) \
 	((ring)->p = ((ring)->p + 1) % (ring)->desc_num)
 #define ring_ptr_move_bw(ring, p) \
 	((ring)->p = ((ring)->p - 1 + (ring)->desc_num) % (ring)->desc_num)
 
-enum hns_desc_type {
-	DESC_TYPE_UNKNOWN,
-	DESC_TYPE_SKB,
-	DESC_TYPE_FRAGLIST_SKB,
-	DESC_TYPE_PAGE,
-};
-
 struct hnae3_handle;
 
 struct hnae3_queue {
@@ -234,7 +240,6 @@ enum hnae3_reset_type {
 	HNAE3_FUNC_RESET,
 	HNAE3_GLOBAL_RESET,
 	HNAE3_IMP_RESET,
-	HNAE3_UNKNOWN_RESET,
 	HNAE3_NONE_RESET,
 	HNAE3_MAX_RESET,
 };
@@ -246,6 +251,50 @@ enum hnae3_port_base_vlan_state {
 	HNAE3_PORT_BASE_VLAN_NOCHANGE,
 };
 
+enum hnae3_dbg_cmd {
+	HNAE3_DBG_CMD_TM_NODES,
+	HNAE3_DBG_CMD_TM_PRI,
+	HNAE3_DBG_CMD_TM_QSET,
+	HNAE3_DBG_CMD_TM_MAP,
+	HNAE3_DBG_CMD_TM_PG,
+	HNAE3_DBG_CMD_TM_PORT,
+	HNAE3_DBG_CMD_TC_SCH_INFO,
+	HNAE3_DBG_CMD_QOS_PAUSE_CFG,
+	HNAE3_DBG_CMD_QOS_PRI_MAP,
+	HNAE3_DBG_CMD_QOS_BUF_CFG,
+	HNAE3_DBG_CMD_DEV_INFO,
+	HNAE3_DBG_CMD_TX_BD,
+	HNAE3_DBG_CMD_RX_BD,
+	HNAE3_DBG_CMD_MAC_UC,
+	HNAE3_DBG_CMD_MAC_MC,
+	HNAE3_DBG_CMD_MNG_TBL,
+	HNAE3_DBG_CMD_LOOPBACK,
+	HNAE3_DBG_CMD_PTP_INFO,
+	HNAE3_DBG_CMD_INTERRUPT_INFO,
+	HNAE3_DBG_CMD_RESET_INFO,
+	HNAE3_DBG_CMD_IMP_INFO,
+	HNAE3_DBG_CMD_NCL_CONFIG,
+	HNAE3_DBG_CMD_REG_BIOS_COMMON,
+	HNAE3_DBG_CMD_REG_SSU,
+	HNAE3_DBG_CMD_REG_IGU_EGU,
+	HNAE3_DBG_CMD_REG_RPU,
+	HNAE3_DBG_CMD_REG_NCSI,
+	HNAE3_DBG_CMD_REG_RTC,
+	HNAE3_DBG_CMD_REG_PPP,
+	HNAE3_DBG_CMD_REG_RCB,
+	HNAE3_DBG_CMD_REG_TQP,
+	HNAE3_DBG_CMD_REG_MAC,
+	HNAE3_DBG_CMD_REG_DCB,
+	HNAE3_DBG_CMD_VLAN_CONFIG,
+	HNAE3_DBG_CMD_QUEUE_MAP,
+	HNAE3_DBG_CMD_RX_QUEUE_INFO,
+	HNAE3_DBG_CMD_TX_QUEUE_INFO,
+	HNAE3_DBG_CMD_FD_TCAM,
+	HNAE3_DBG_CMD_MAC_TNL_STATUS,
+	HNAE3_DBG_CMD_SERV_INFO,
+	HNAE3_DBG_CMD_UNKNOWN,
+};
+
 struct hnae3_vector_info {
 	u8 __iomem *io_addr;
 	int vector;
@@ -470,6 +519,12 @@ struct hnae3_ae_dev {
  *   Check if any cls flower rule exist
  * dbg_read_cmd
  *   Execute debugfs read command.
+ * set_tx_hwts_info
+ *   Save information for 1588 tx packet
+ * get_rx_hwts
+ *   Get 1588 rx hwstamp
+ * get_ts_info
+ *   Get phc info
  */
 struct hnae3_ae_ops {
 	int (*init_ae_dev)(struct hnae3_ae_dev *ae_dev);
@@ -585,7 +640,7 @@ struct hnae3_ae_ops {
 	void (*get_mdix_mode)(struct hnae3_handle *handle,
 			      u8 *tp_mdix_ctrl, u8 *tp_mdix);
 
-	void (*enable_vlan_filter)(struct hnae3_handle *handle, bool enable);
+	int (*enable_vlan_filter)(struct hnae3_handle *handle, bool enable);
 	int (*set_vlan_filter)(struct hnae3_handle *handle, __be16 proto,
 			       u16 vlan_id, bool is_kill);
 	int (*set_vf_vlan_filter)(struct hnae3_handle *handle, int vfid,
@@ -622,8 +677,7 @@ struct hnae3_ae_ops {
 	void (*enable_fd)(struct hnae3_handle *handle, bool enable);
 	int (*add_arfs_entry)(struct hnae3_handle *handle, u16 queue_id,
 			      u16 flow_id, struct flow_keys *fkeys);
-	int (*dbg_run_cmd)(struct hnae3_handle *handle, const char *cmd_buf);
-	int (*dbg_read_cmd)(struct hnae3_handle *handle, const char *cmd_buf,
+	int (*dbg_read_cmd)(struct hnae3_handle *handle, enum hnae3_dbg_cmd cmd,
 			    char *buf, int len);
 	pci_ers_result_t (*handle_hw_ras_error)(struct hnae3_ae_dev *ae_dev);
 	bool (*get_hw_reset_stat)(struct hnae3_handle *handle);
@@ -656,6 +710,12 @@ struct hnae3_ae_ops {
 				      struct ethtool_link_ksettings *cmd);
 	int (*set_phy_link_ksettings)(struct hnae3_handle *handle,
 				      const struct ethtool_link_ksettings *cmd);
+	bool (*set_tx_hwts_info)(struct hnae3_handle *handle,
+				 struct sk_buff *skb);
+	void (*get_rx_hwts)(struct hnae3_handle *handle, struct sk_buff *skb,
+			    u32 nsec, u32 sec);
+	int (*get_ts_info)(struct hnae3_handle *handle,
+			   struct ethtool_ts_info *info);
 };
 
 struct hnae3_dcb_ops {
@@ -700,6 +760,7 @@ struct hnae3_knic_private_info {
 	u16 rx_buf_len;
 	u16 num_tx_desc;
 	u16 num_rx_desc;
+	u32 tx_spare_buf_size;
 
 	struct hnae3_tc_info tc_info;
 
@@ -738,7 +799,6 @@ struct hnae3_roce_private_info {
 #define HNAE3_BPE		BIT(2)	/* broadcast promisc enable */
 #define HNAE3_OVERFLOW_UPE	BIT(3)	/* unicast mac vlan overflow */
 #define HNAE3_OVERFLOW_MPE	BIT(4)	/* multicast mac vlan overflow */
-#define HNAE3_VLAN_FLTR		BIT(5)	/* enable vlan filter */
 #define HNAE3_UPE		(HNAE3_USER_UPE | HNAE3_OVERFLOW_UPE)
 #define HNAE3_MPE		(HNAE3_USER_MPE | HNAE3_OVERFLOW_MPE)
 
@@ -786,10 +846,6 @@ struct hnae3_handle {
 #define hnae3_get_bit(origin, shift) \
 	hnae3_get_field(origin, 0x1 << (shift), shift)
 
-#define HNAE3_DBG_TM_NODES		"tm_nodes"
-#define HNAE3_DBG_TM_PRI		"tm_priority"
-#define HNAE3_DBG_TM_QSET		"tm_qset"
-
 int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev);
 void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 9d702bd0c7c1..34b6cd904a1a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -5,46 +5,525 @@
 #include <linux/device.h>
 
 #include "hnae3.h"
+#include "hns3_debugfs.h"
 #include "hns3_enet.h"
 
-#define HNS3_DBG_READ_LEN 65536
-#define HNS3_DBG_WRITE_LEN 1024
-
 static struct dentry *hns3_dbgfs_root;
 
-static int hns3_dbg_queue_info(struct hnae3_handle *h,
-			       const char *cmd_buf)
+static struct hns3_dbg_dentry_info hns3_dbg_dentry[] = {
+	{
+		.name = "tm"
+	},
+	{
+		.name = "tx_bd_info"
+	},
+	{
+		.name = "rx_bd_info"
+	},
+	{
+		.name = "mac_list"
+	},
+	{
+		.name = "reg"
+	},
+	{
+		.name = "queue"
+	},
+	{
+		.name = "fd"
+	},
+	/* keep common at the bottom and add new directory above */
+	{
+		.name = "common"
+	},
+};
+
+static int hns3_dbg_bd_file_init(struct hnae3_handle *handle, unsigned int cmd);
+static int hns3_dbg_common_file_init(struct hnae3_handle *handle,
+				     unsigned int cmd);
+
+static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = {
+	{
+		.name = "tm_nodes",
+		.cmd = HNAE3_DBG_CMD_TM_NODES,
+		.dentry = HNS3_DBG_DENTRY_TM,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "tm_priority",
+		.cmd = HNAE3_DBG_CMD_TM_PRI,
+		.dentry = HNS3_DBG_DENTRY_TM,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "tm_qset",
+		.cmd = HNAE3_DBG_CMD_TM_QSET,
+		.dentry = HNS3_DBG_DENTRY_TM,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "tm_map",
+		.cmd = HNAE3_DBG_CMD_TM_MAP,
+		.dentry = HNS3_DBG_DENTRY_TM,
+		.buf_len = HNS3_DBG_READ_LEN_1MB,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "tm_pg",
+		.cmd = HNAE3_DBG_CMD_TM_PG,
+		.dentry = HNS3_DBG_DENTRY_TM,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "tm_port",
+		.cmd = HNAE3_DBG_CMD_TM_PORT,
+		.dentry = HNS3_DBG_DENTRY_TM,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "tc_sch_info",
+		.cmd = HNAE3_DBG_CMD_TC_SCH_INFO,
+		.dentry = HNS3_DBG_DENTRY_TM,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "qos_pause_cfg",
+		.cmd = HNAE3_DBG_CMD_QOS_PAUSE_CFG,
+		.dentry = HNS3_DBG_DENTRY_TM,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "qos_pri_map",
+		.cmd = HNAE3_DBG_CMD_QOS_PRI_MAP,
+		.dentry = HNS3_DBG_DENTRY_TM,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "qos_buf_cfg",
+		.cmd = HNAE3_DBG_CMD_QOS_BUF_CFG,
+		.dentry = HNS3_DBG_DENTRY_TM,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "dev_info",
+		.cmd = HNAE3_DBG_CMD_DEV_INFO,
+		.dentry = HNS3_DBG_DENTRY_COMMON,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "tx_bd_queue",
+		.cmd = HNAE3_DBG_CMD_TX_BD,
+		.dentry = HNS3_DBG_DENTRY_TX_BD,
+		.buf_len = HNS3_DBG_READ_LEN_4MB,
+		.init = hns3_dbg_bd_file_init,
+	},
+	{
+		.name = "rx_bd_queue",
+		.cmd = HNAE3_DBG_CMD_RX_BD,
+		.dentry = HNS3_DBG_DENTRY_RX_BD,
+		.buf_len = HNS3_DBG_READ_LEN_4MB,
+		.init = hns3_dbg_bd_file_init,
+	},
+	{
+		.name = "uc",
+		.cmd = HNAE3_DBG_CMD_MAC_UC,
+		.dentry = HNS3_DBG_DENTRY_MAC,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "mc",
+		.cmd = HNAE3_DBG_CMD_MAC_MC,
+		.dentry = HNS3_DBG_DENTRY_MAC,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "mng_tbl",
+		.cmd = HNAE3_DBG_CMD_MNG_TBL,
+		.dentry = HNS3_DBG_DENTRY_COMMON,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "loopback",
+		.cmd = HNAE3_DBG_CMD_LOOPBACK,
+		.dentry = HNS3_DBG_DENTRY_COMMON,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "interrupt_info",
+		.cmd = HNAE3_DBG_CMD_INTERRUPT_INFO,
+		.dentry = HNS3_DBG_DENTRY_COMMON,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "reset_info",
+		.cmd = HNAE3_DBG_CMD_RESET_INFO,
+		.dentry = HNS3_DBG_DENTRY_COMMON,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "imp_info",
+		.cmd = HNAE3_DBG_CMD_IMP_INFO,
+		.dentry = HNS3_DBG_DENTRY_COMMON,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "ncl_config",
+		.cmd = HNAE3_DBG_CMD_NCL_CONFIG,
+		.dentry = HNS3_DBG_DENTRY_COMMON,
+		.buf_len = HNS3_DBG_READ_LEN_128KB,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "mac_tnl_status",
+		.cmd = HNAE3_DBG_CMD_MAC_TNL_STATUS,
+		.dentry = HNS3_DBG_DENTRY_COMMON,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "bios_common",
+		.cmd = HNAE3_DBG_CMD_REG_BIOS_COMMON,
+		.dentry = HNS3_DBG_DENTRY_REG,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "ssu",
+		.cmd = HNAE3_DBG_CMD_REG_SSU,
+		.dentry = HNS3_DBG_DENTRY_REG,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "igu_egu",
+		.cmd = HNAE3_DBG_CMD_REG_IGU_EGU,
+		.dentry = HNS3_DBG_DENTRY_REG,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "rpu",
+		.cmd = HNAE3_DBG_CMD_REG_RPU,
+		.dentry = HNS3_DBG_DENTRY_REG,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "ncsi",
+		.cmd = HNAE3_DBG_CMD_REG_NCSI,
+		.dentry = HNS3_DBG_DENTRY_REG,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "rtc",
+		.cmd = HNAE3_DBG_CMD_REG_RTC,
+		.dentry = HNS3_DBG_DENTRY_REG,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "ppp",
+		.cmd = HNAE3_DBG_CMD_REG_PPP,
+		.dentry = HNS3_DBG_DENTRY_REG,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "rcb",
+		.cmd = HNAE3_DBG_CMD_REG_RCB,
+		.dentry = HNS3_DBG_DENTRY_REG,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "tqp",
+		.cmd = HNAE3_DBG_CMD_REG_TQP,
+		.dentry = HNS3_DBG_DENTRY_REG,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "mac",
+		.cmd = HNAE3_DBG_CMD_REG_MAC,
+		.dentry = HNS3_DBG_DENTRY_REG,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "dcb",
+		.cmd = HNAE3_DBG_CMD_REG_DCB,
+		.dentry = HNS3_DBG_DENTRY_REG,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "queue_map",
+		.cmd = HNAE3_DBG_CMD_QUEUE_MAP,
+		.dentry = HNS3_DBG_DENTRY_QUEUE,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "rx_queue_info",
+		.cmd = HNAE3_DBG_CMD_RX_QUEUE_INFO,
+		.dentry = HNS3_DBG_DENTRY_QUEUE,
+		.buf_len = HNS3_DBG_READ_LEN_1MB,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "tx_queue_info",
+		.cmd = HNAE3_DBG_CMD_TX_QUEUE_INFO,
+		.dentry = HNS3_DBG_DENTRY_QUEUE,
+		.buf_len = HNS3_DBG_READ_LEN_1MB,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "fd_tcam",
+		.cmd = HNAE3_DBG_CMD_FD_TCAM,
+		.dentry = HNS3_DBG_DENTRY_FD,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "service_task_info",
+		.cmd = HNAE3_DBG_CMD_SERV_INFO,
+		.dentry = HNS3_DBG_DENTRY_COMMON,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "vlan_config",
+		.cmd = HNAE3_DBG_CMD_VLAN_CONFIG,
+		.dentry = HNS3_DBG_DENTRY_COMMON,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+	{
+		.name = "ptp_info",
+		.cmd = HNAE3_DBG_CMD_PTP_INFO,
+		.dentry = HNS3_DBG_DENTRY_COMMON,
+		.buf_len = HNS3_DBG_READ_LEN,
+		.init = hns3_dbg_common_file_init,
+	},
+};
+
+static struct hns3_dbg_cap_info hns3_dbg_cap[] = {
+	{
+		.name = "support FD",
+		.cap_bit = HNAE3_DEV_SUPPORT_FD_B,
+	}, {
+		.name = "support GRO",
+		.cap_bit = HNAE3_DEV_SUPPORT_GRO_B,
+	}, {
+		.name = "support FEC",
+		.cap_bit = HNAE3_DEV_SUPPORT_FEC_B,
+	}, {
+		.name = "support UDP GSO",
+		.cap_bit = HNAE3_DEV_SUPPORT_UDP_GSO_B,
+	}, {
+		.name = "support PTP",
+		.cap_bit = HNAE3_DEV_SUPPORT_PTP_B,
+	}, {
+		.name = "support INT QL",
+		.cap_bit = HNAE3_DEV_SUPPORT_INT_QL_B,
+	}, {
+		.name = "support HW TX csum",
+		.cap_bit = HNAE3_DEV_SUPPORT_HW_TX_CSUM_B,
+	}, {
+		.name = "support UDP tunnel csum",
+		.cap_bit = HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B,
+	}, {
+		.name = "support TX push",
+		.cap_bit = HNAE3_DEV_SUPPORT_TX_PUSH_B,
+	}, {
+		.name = "support imp-controlled PHY",
+		.cap_bit = HNAE3_DEV_SUPPORT_PHY_IMP_B,
+	}, {
+		.name = "support imp-controlled RAS",
+		.cap_bit = HNAE3_DEV_SUPPORT_RAS_IMP_B,
+	}, {
+		.name = "support rxd advanced layout",
+		.cap_bit = HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B,
+	}, {
+		.name = "support port vlan bypass",
+		.cap_bit = HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B,
+	}, {
+		.name = "support modify vlan filter state",
+		.cap_bit = HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B,
+	}
+};
+
+static void hns3_dbg_fill_content(char *content, u16 len,
+				  const struct hns3_dbg_item *items,
+				  const char **result, u16 size)
+{
+	char *pos = content;
+	u16 i;
+
+	memset(content, ' ', len);
+	for (i = 0; i < size; i++) {
+		if (result)
+			strncpy(pos, result[i], strlen(result[i]));
+		else
+			strncpy(pos, items[i].name, strlen(items[i].name));
+
+		pos += strlen(items[i].name) + items[i].interval;
+	}
+
+	*pos++ = '\n';
+	*pos++ = '\0';
+}
+
+static const struct hns3_dbg_item tx_spare_info_items[] = {
+	{ "QUEUE_ID", 2 },
+	{ "COPYBREAK", 2 },
+	{ "LEN", 7 },
+	{ "NTU", 4 },
+	{ "NTC", 4 },
+	{ "LTC", 4 },
+	{ "DMA", 17 },
+};
+
+static void hns3_dbg_tx_spare_info(struct hns3_enet_ring *ring, char *buf,
+				   int len, u32 ring_num, int *pos)
+{
+	char data_str[ARRAY_SIZE(tx_spare_info_items)][HNS3_DBG_DATA_STR_LEN];
+	struct hns3_tx_spare *tx_spare = ring->tx_spare;
+	char *result[ARRAY_SIZE(tx_spare_info_items)];
+	char content[HNS3_DBG_INFO_LEN];
+	u32 i, j;
+
+	if (!tx_spare) {
+		*pos += scnprintf(buf + *pos, len - *pos,
+				  "tx spare buffer is not enabled\n");
+		return;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(tx_spare_info_items); i++)
+		result[i] = &data_str[i][0];
+
+	*pos += scnprintf(buf + *pos, len - *pos, "tx spare buffer info\n");
+	hns3_dbg_fill_content(content, sizeof(content), tx_spare_info_items,
+			      NULL, ARRAY_SIZE(tx_spare_info_items));
+	*pos += scnprintf(buf + *pos, len - *pos, "%s", content);
+
+	for (i = 0; i < ring_num; i++) {
+		j = 0;
+		sprintf(result[j++], "%8u", i);
+		sprintf(result[j++], "%9u", ring->tx_copybreak);
+		sprintf(result[j++], "%3u", tx_spare->len);
+		sprintf(result[j++], "%3u", tx_spare->next_to_use);
+		sprintf(result[j++], "%3u", tx_spare->next_to_clean);
+		sprintf(result[j++], "%3u", tx_spare->last_to_clean);
+		sprintf(result[j++], "%pad", &tx_spare->dma);
+		hns3_dbg_fill_content(content, sizeof(content),
+				      tx_spare_info_items,
+				      (const char **)result,
+				      ARRAY_SIZE(tx_spare_info_items));
+		*pos += scnprintf(buf + *pos, len - *pos, "%s", content);
+	}
+}
+
+static const struct hns3_dbg_item rx_queue_info_items[] = {
+	{ "QUEUE_ID", 2 },
+	{ "BD_NUM", 2 },
+	{ "BD_LEN", 2 },
+	{ "TAIL", 2 },
+	{ "HEAD", 2 },
+	{ "FBDNUM", 2 },
+	{ "PKTNUM", 2 },
+	{ "COPYBREAK", 2 },
+	{ "RING_EN", 2 },
+	{ "RX_RING_EN", 2 },
+	{ "BASE_ADDR", 10 },
+};
+
+static void hns3_dump_rx_queue_info(struct hns3_enet_ring *ring,
+				    struct hnae3_ae_dev *ae_dev, char **result,
+				    u32 index)
 {
+	u32 base_add_l, base_add_h;
+	u32 j = 0;
+
+	sprintf(result[j++], "%8u", index);
+
+	sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base +
+		HNS3_RING_RX_RING_BD_NUM_REG));
+
+	sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base +
+		HNS3_RING_RX_RING_BD_LEN_REG));
+
+	sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base +
+		HNS3_RING_RX_RING_TAIL_REG));
+
+	sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base +
+		HNS3_RING_RX_RING_HEAD_REG));
+
+	sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base +
+		HNS3_RING_RX_RING_FBDNUM_REG));
+
+	sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base +
+		HNS3_RING_RX_RING_PKTNUM_RECORD_REG));
+	sprintf(result[j++], "%9u", ring->rx_copybreak);
+
+	sprintf(result[j++], "%7s", readl_relaxed(ring->tqp->io_base +
+		HNS3_RING_EN_REG) ? "on" : "off");
+
+	if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev))
+		sprintf(result[j++], "%10s", readl_relaxed(ring->tqp->io_base +
+			HNS3_RING_RX_EN_REG) ? "on" : "off");
+	else
+		sprintf(result[j++], "%10s", "NA");
+
+	base_add_h = readl_relaxed(ring->tqp->io_base +
+					HNS3_RING_RX_RING_BASEADDR_H_REG);
+	base_add_l = readl_relaxed(ring->tqp->io_base +
+					HNS3_RING_RX_RING_BASEADDR_L_REG);
+	sprintf(result[j++], "0x%08x%08x", base_add_h, base_add_l);
+}
+
+static int hns3_dbg_rx_queue_info(struct hnae3_handle *h,
+				  char *buf, int len)
+{
+	char data_str[ARRAY_SIZE(rx_queue_info_items)][HNS3_DBG_DATA_STR_LEN];
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
+	char *result[ARRAY_SIZE(rx_queue_info_items)];
 	struct hns3_nic_priv *priv = h->priv;
+	char content[HNS3_DBG_INFO_LEN];
 	struct hns3_enet_ring *ring;
-	u32 base_add_l, base_add_h;
-	u32 queue_num, queue_max;
-	u32 value, i;
-	int cnt;
+	int pos = 0;
+	u32 i;
 
 	if (!priv->ring) {
 		dev_err(&h->pdev->dev, "priv->ring is NULL\n");
 		return -EFAULT;
 	}
 
-	queue_max = h->kinfo.num_tqps;
-	cnt = kstrtouint(&cmd_buf[11], 0, &queue_num);
-	if (cnt)
-		queue_num = 0;
-	else
-		queue_max = queue_num + 1;
+	for (i = 0; i < ARRAY_SIZE(rx_queue_info_items); i++)
+		result[i] = &data_str[i][0];
 
-	dev_info(&h->pdev->dev, "queue info\n");
-
-	if (queue_num >= h->kinfo.num_tqps) {
-		dev_err(&h->pdev->dev,
-			"Queue number(%u) is out of range(0-%u)\n", queue_num,
-			h->kinfo.num_tqps - 1);
-		return -EINVAL;
-	}
-
-	for (i = queue_num; i < queue_max; i++) {
+	hns3_dbg_fill_content(content, sizeof(content), rx_queue_info_items,
+			      NULL, ARRAY_SIZE(rx_queue_info_items));
+	pos += scnprintf(buf + pos, len - pos, "%s", content);
+	for (i = 0; i < h->kinfo.num_tqps; i++) {
 		/* Each cycle needs to determine whether the instance is reset,
 		 * to prevent reference to invalid memory. And need to ensure
 		 * that the following code is executed within 100ms.
@@ -54,491 +533,524 @@ static int hns3_dbg_queue_info(struct hnae3_handle *h,
 			return -EPERM;
 
 		ring = &priv->ring[(u32)(i + h->kinfo.num_tqps)];
-		base_add_h = readl_relaxed(ring->tqp->io_base +
-					   HNS3_RING_RX_RING_BASEADDR_H_REG);
-		base_add_l = readl_relaxed(ring->tqp->io_base +
-					   HNS3_RING_RX_RING_BASEADDR_L_REG);
-		dev_info(&h->pdev->dev, "RX(%u) BASE ADD: 0x%08x%08x\n", i,
-			 base_add_h, base_add_l);
+		hns3_dump_rx_queue_info(ring, ae_dev, result, i);
+		hns3_dbg_fill_content(content, sizeof(content),
+				      rx_queue_info_items,
+				      (const char **)result,
+				      ARRAY_SIZE(rx_queue_info_items));
+		pos += scnprintf(buf + pos, len - pos, "%s", content);
+	}
+
+	return 0;
+}
 
-		value = readl_relaxed(ring->tqp->io_base +
-				      HNS3_RING_RX_RING_BD_NUM_REG);
-		dev_info(&h->pdev->dev, "RX(%u) RING BD NUM: %u\n", i, value);
+static const struct hns3_dbg_item tx_queue_info_items[] = {
+	{ "QUEUE_ID", 2 },
+	{ "BD_NUM", 2 },
+	{ "TC", 2 },
+	{ "TAIL", 2 },
+	{ "HEAD", 2 },
+	{ "FBDNUM", 2 },
+	{ "OFFSET", 2 },
+	{ "PKTNUM", 2 },
+	{ "RING_EN", 2 },
+	{ "TX_RING_EN", 2 },
+	{ "BASE_ADDR", 10 },
+};
 
-		value = readl_relaxed(ring->tqp->io_base +
-				      HNS3_RING_RX_RING_BD_LEN_REG);
-		dev_info(&h->pdev->dev, "RX(%u) RING BD LEN: %u\n", i, value);
+static void hns3_dump_tx_queue_info(struct hns3_enet_ring *ring,
+				    struct hnae3_ae_dev *ae_dev, char **result,
+				    u32 index)
+{
+	u32 base_add_l, base_add_h;
+	u32 j = 0;
 
-		value = readl_relaxed(ring->tqp->io_base +
-				      HNS3_RING_RX_RING_TAIL_REG);
-		dev_info(&h->pdev->dev, "RX(%u) RING TAIL: %u\n", i, value);
+	sprintf(result[j++], "%8u", index);
+	sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base +
+		HNS3_RING_TX_RING_BD_NUM_REG));
 
-		value = readl_relaxed(ring->tqp->io_base +
-				      HNS3_RING_RX_RING_HEAD_REG);
-		dev_info(&h->pdev->dev, "RX(%u) RING HEAD: %u\n", i, value);
+	sprintf(result[j++], "%2u", readl_relaxed(ring->tqp->io_base +
+		HNS3_RING_TX_RING_TC_REG));
 
-		value = readl_relaxed(ring->tqp->io_base +
-				      HNS3_RING_RX_RING_FBDNUM_REG);
-		dev_info(&h->pdev->dev, "RX(%u) RING FBDNUM: %u\n", i, value);
+	sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base +
+		HNS3_RING_TX_RING_TAIL_REG));
 
-		value = readl_relaxed(ring->tqp->io_base +
-				      HNS3_RING_RX_RING_PKTNUM_RECORD_REG);
-		dev_info(&h->pdev->dev, "RX(%u) RING PKTNUM: %u\n", i, value);
+	sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base +
+		HNS3_RING_TX_RING_HEAD_REG));
 
-		ring = &priv->ring[i];
-		base_add_h = readl_relaxed(ring->tqp->io_base +
-					   HNS3_RING_TX_RING_BASEADDR_H_REG);
-		base_add_l = readl_relaxed(ring->tqp->io_base +
-					   HNS3_RING_TX_RING_BASEADDR_L_REG);
-		dev_info(&h->pdev->dev, "TX(%u) BASE ADD: 0x%08x%08x\n", i,
-			 base_add_h, base_add_l);
-
-		value = readl_relaxed(ring->tqp->io_base +
-				      HNS3_RING_TX_RING_BD_NUM_REG);
-		dev_info(&h->pdev->dev, "TX(%u) RING BD NUM: %u\n", i, value);
-
-		value = readl_relaxed(ring->tqp->io_base +
-				      HNS3_RING_TX_RING_TC_REG);
-		dev_info(&h->pdev->dev, "TX(%u) RING TC: %u\n", i, value);
-
-		value = readl_relaxed(ring->tqp->io_base +
-				      HNS3_RING_TX_RING_TAIL_REG);
-		dev_info(&h->pdev->dev, "TX(%u) RING TAIL: %u\n", i, value);
-
-		value = readl_relaxed(ring->tqp->io_base +
-				      HNS3_RING_TX_RING_HEAD_REG);
-		dev_info(&h->pdev->dev, "TX(%u) RING HEAD: %u\n", i, value);
-
-		value = readl_relaxed(ring->tqp->io_base +
-				      HNS3_RING_TX_RING_FBDNUM_REG);
-		dev_info(&h->pdev->dev, "TX(%u) RING FBDNUM: %u\n", i, value);
-
-		value = readl_relaxed(ring->tqp->io_base +
-				      HNS3_RING_TX_RING_OFFSET_REG);
-		dev_info(&h->pdev->dev, "TX(%u) RING OFFSET: %u\n", i, value);
-
-		value = readl_relaxed(ring->tqp->io_base +
-				      HNS3_RING_TX_RING_PKTNUM_RECORD_REG);
-		dev_info(&h->pdev->dev, "TX(%u) RING PKTNUM: %u\n", i, value);
-
-		value = readl_relaxed(ring->tqp->io_base + HNS3_RING_EN_REG);
-		dev_info(&h->pdev->dev, "TX/RX(%u) RING EN: %s\n", i,
-			 value ? "enable" : "disable");
-
-		if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev)) {
-			value = readl_relaxed(ring->tqp->io_base +
-					      HNS3_RING_TX_EN_REG);
-			dev_info(&h->pdev->dev, "TX(%u) RING EN: %s\n", i,
-				 value ? "enable" : "disable");
-
-			value = readl_relaxed(ring->tqp->io_base +
-					      HNS3_RING_RX_EN_REG);
-			dev_info(&h->pdev->dev, "RX(%u) RING EN: %s\n", i,
-				 value ? "enable" : "disable");
-		}
+	sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base +
+		HNS3_RING_TX_RING_FBDNUM_REG));
+
+	sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base +
+		HNS3_RING_TX_RING_OFFSET_REG));
+
+	sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base +
+		HNS3_RING_TX_RING_PKTNUM_RECORD_REG));
+
+	sprintf(result[j++], "%7s", readl_relaxed(ring->tqp->io_base +
+		HNS3_RING_EN_REG) ? "on" : "off");
+
+	if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev))
+		sprintf(result[j++], "%10s", readl_relaxed(ring->tqp->io_base +
+			HNS3_RING_TX_EN_REG) ? "on" : "off");
+	else
+		sprintf(result[j++], "%10s", "NA");
+
+	base_add_h = readl_relaxed(ring->tqp->io_base +
+					HNS3_RING_TX_RING_BASEADDR_H_REG);
+	base_add_l = readl_relaxed(ring->tqp->io_base +
+					HNS3_RING_TX_RING_BASEADDR_L_REG);
+	sprintf(result[j++], "0x%08x%08x", base_add_h, base_add_l);
+}
+
+static int hns3_dbg_tx_queue_info(struct hnae3_handle *h,
+				  char *buf, int len)
+{
+	char data_str[ARRAY_SIZE(tx_queue_info_items)][HNS3_DBG_DATA_STR_LEN];
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
+	char *result[ARRAY_SIZE(tx_queue_info_items)];
+	struct hns3_nic_priv *priv = h->priv;
+	char content[HNS3_DBG_INFO_LEN];
+	struct hns3_enet_ring *ring;
+	int pos = 0;
+	u32 i;
+
+	if (!priv->ring) {
+		dev_err(&h->pdev->dev, "priv->ring is NULL\n");
+		return -EFAULT;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(tx_queue_info_items); i++)
+		result[i] = &data_str[i][0];
+
+	hns3_dbg_fill_content(content, sizeof(content), tx_queue_info_items,
+			      NULL, ARRAY_SIZE(tx_queue_info_items));
+	pos += scnprintf(buf + pos, len - pos, "%s", content);
+
+	for (i = 0; i < h->kinfo.num_tqps; i++) {
+		/* Each cycle needs to determine whether the instance is reset,
+		 * to prevent reference to invalid memory. And need to ensure
+		 * that the following code is executed within 100ms.
+		 */
+		if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
+		    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
+			return -EPERM;
 
-		dev_info(&h->pdev->dev, "\n");
+		ring = &priv->ring[i];
+		hns3_dump_tx_queue_info(ring, ae_dev, result, i);
+		hns3_dbg_fill_content(content, sizeof(content),
+				      tx_queue_info_items,
+				      (const char **)result,
+				      ARRAY_SIZE(tx_queue_info_items));
+		pos += scnprintf(buf + pos, len - pos, "%s", content);
 	}
 
+	hns3_dbg_tx_spare_info(ring, buf, len, h->kinfo.num_tqps, &pos);
+
 	return 0;
 }
 
-static int hns3_dbg_queue_map(struct hnae3_handle *h)
+static const struct hns3_dbg_item queue_map_items[] = {
+	{ "local_queue_id", 2 },
+	{ "global_queue_id", 2 },
+	{ "vector_id", 2 },
+};
+
+static int hns3_dbg_queue_map(struct hnae3_handle *h, char *buf, int len)
 {
+	char data_str[ARRAY_SIZE(queue_map_items)][HNS3_DBG_DATA_STR_LEN];
+	char *result[ARRAY_SIZE(queue_map_items)];
 	struct hns3_nic_priv *priv = h->priv;
-	int i;
+	char content[HNS3_DBG_INFO_LEN];
+	int pos = 0;
+	int j;
+	u32 i;
 
 	if (!h->ae_algo->ops->get_global_queue_id)
 		return -EOPNOTSUPP;
 
-	dev_info(&h->pdev->dev, "map info for queue id and vector id\n");
-	dev_info(&h->pdev->dev,
-		 "local queue id | global queue id | vector id\n");
-	for (i = 0; i < h->kinfo.num_tqps; i++) {
-		u16 global_qid;
+	for (i = 0; i < ARRAY_SIZE(queue_map_items); i++)
+		result[i] = &data_str[i][0];
 
-		global_qid = h->ae_algo->ops->get_global_queue_id(h, i);
+	hns3_dbg_fill_content(content, sizeof(content), queue_map_items,
+			      NULL, ARRAY_SIZE(queue_map_items));
+	pos += scnprintf(buf + pos, len - pos, "%s", content);
+	for (i = 0; i < h->kinfo.num_tqps; i++) {
 		if (!priv->ring || !priv->ring[i].tqp_vector)
 			continue;
-
-		dev_info(&h->pdev->dev,
-			 "      %4d            %4u            %4d\n",
-			 i, global_qid, priv->ring[i].tqp_vector->vector_irq);
+		j = 0;
+		sprintf(result[j++], "%u", i);
+		sprintf(result[j++], "%u",
+			h->ae_algo->ops->get_global_queue_id(h, i));
+		sprintf(result[j++], "%u",
+			priv->ring[i].tqp_vector->vector_irq);
+		hns3_dbg_fill_content(content, sizeof(content), queue_map_items,
+				      (const char **)result,
+				      ARRAY_SIZE(queue_map_items));
+		pos += scnprintf(buf + pos, len - pos, "%s", content);
 	}
 
 	return 0;
 }
 
-static int hns3_dbg_bd_info(struct hnae3_handle *h, const char *cmd_buf)
+static const struct hns3_dbg_item rx_bd_info_items[] = {
+	{ "BD_IDX", 3 },
+	{ "L234_INFO", 2 },
+	{ "PKT_LEN", 3 },
+	{ "SIZE", 4 },
+	{ "RSS_HASH", 4 },
+	{ "FD_ID", 2 },
+	{ "VLAN_TAG", 2 },
+	{ "O_DM_VLAN_ID_FB", 2 },
+	{ "OT_VLAN_TAG", 2 },
+	{ "BD_BASE_INFO", 2 },
+	{ "PTYPE", 2 },
+	{ "HW_CSUM", 2 },
+};
+
+static void hns3_dump_rx_bd_info(struct hns3_nic_priv *priv,
+				 struct hns3_desc *desc, char **result, int idx)
 {
-	struct hns3_nic_priv *priv = h->priv;
-	struct hns3_desc *rx_desc, *tx_desc;
-	struct device *dev = &h->pdev->dev;
-	struct hns3_enet_ring *ring;
-	u32 tx_index, rx_index;
-	u32 q_num, value;
-	dma_addr_t addr;
-	u16 mss_hw_csum;
-	u32 l234info;
-	int cnt;
-
-	cnt = sscanf(&cmd_buf[8], "%u %u", &q_num, &tx_index);
-	if (cnt == 2) {
-		rx_index = tx_index;
-	} else if (cnt != 1) {
-		dev_err(dev, "bd info: bad command string, cnt=%d\n", cnt);
-		return -EINVAL;
+	unsigned int j = 0;
+
+	sprintf(result[j++], "%5d", idx);
+	sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.l234_info));
+	sprintf(result[j++], "%7u", le16_to_cpu(desc->rx.pkt_len));
+	sprintf(result[j++], "%4u", le16_to_cpu(desc->rx.size));
+	sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.rss_hash));
+	sprintf(result[j++], "%5u", le16_to_cpu(desc->rx.fd_id));
+	sprintf(result[j++], "%8u", le16_to_cpu(desc->rx.vlan_tag));
+	sprintf(result[j++], "%15u", le16_to_cpu(desc->rx.o_dm_vlan_id_fb));
+	sprintf(result[j++], "%11u", le16_to_cpu(desc->rx.ot_vlan_tag));
+	sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.bd_base_info));
+	if (test_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state)) {
+		u32 ol_info = le32_to_cpu(desc->rx.ol_info);
+
+		sprintf(result[j++], "%5lu", hnae3_get_field(ol_info,
+							     HNS3_RXD_PTYPE_M,
+							     HNS3_RXD_PTYPE_S));
+		sprintf(result[j++], "%7u", le16_to_cpu(desc->csum));
+	} else {
+		sprintf(result[j++], "NA");
+		sprintf(result[j++], "NA");
 	}
+}
+
+static int hns3_dbg_rx_bd_info(struct hns3_dbg_data *d, char *buf, int len)
+{
+	char data_str[ARRAY_SIZE(rx_bd_info_items)][HNS3_DBG_DATA_STR_LEN];
+	struct hns3_nic_priv *priv = d->handle->priv;
+	char *result[ARRAY_SIZE(rx_bd_info_items)];
+	char content[HNS3_DBG_INFO_LEN];
+	struct hns3_enet_ring *ring;
+	struct hns3_desc *desc;
+	unsigned int i;
+	int pos = 0;
 
-	if (q_num >= h->kinfo.num_tqps) {
-		dev_err(dev, "Queue number(%u) is out of range(0-%u)\n", q_num,
-			h->kinfo.num_tqps - 1);
+	if (d->qid >= d->handle->kinfo.num_tqps) {
+		dev_err(&d->handle->pdev->dev,
+			"queue%u is not in use\n", d->qid);
 		return -EINVAL;
 	}
 
-	ring = &priv->ring[q_num];
-	value = readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG);
-	tx_index = (cnt == 1) ? value : tx_index;
+	for (i = 0; i < ARRAY_SIZE(rx_bd_info_items); i++)
+		result[i] = &data_str[i][0];
 
-	if (tx_index >= ring->desc_num) {
-		dev_err(dev, "bd index(%u) is out of range(0-%u)\n", tx_index,
-			ring->desc_num - 1);
-		return -EINVAL;
-	}
+	pos += scnprintf(buf + pos, len - pos,
+			  "Queue %u rx bd info:\n", d->qid);
+	hns3_dbg_fill_content(content, sizeof(content), rx_bd_info_items,
+			      NULL, ARRAY_SIZE(rx_bd_info_items));
+	pos += scnprintf(buf + pos, len - pos, "%s", content);
 
-	tx_desc = &ring->desc[tx_index];
-	addr = le64_to_cpu(tx_desc->addr);
-	mss_hw_csum = le16_to_cpu(tx_desc->tx.mss_hw_csum);
-	dev_info(dev, "TX Queue Num: %u, BD Index: %u\n", q_num, tx_index);
-	dev_info(dev, "(TX)addr: %pad\n", &addr);
-	dev_info(dev, "(TX)vlan_tag: %u\n", le16_to_cpu(tx_desc->tx.vlan_tag));
-	dev_info(dev, "(TX)send_size: %u\n",
-		 le16_to_cpu(tx_desc->tx.send_size));
-
-	if (mss_hw_csum & BIT(HNS3_TXD_HW_CS_B)) {
-		u32 offset = le32_to_cpu(tx_desc->tx.ol_type_vlan_len_msec);
-		u32 start = le32_to_cpu(tx_desc->tx.type_cs_vlan_tso_len);
-
-		dev_info(dev, "(TX)csum start: %u\n",
-			 hnae3_get_field(start,
-					 HNS3_TXD_CSUM_START_M,
-					 HNS3_TXD_CSUM_START_S));
-		dev_info(dev, "(TX)csum offset: %u\n",
-			 hnae3_get_field(offset,
-					 HNS3_TXD_CSUM_OFFSET_M,
-					 HNS3_TXD_CSUM_OFFSET_S));
-	} else {
-		dev_info(dev, "(TX)vlan_tso: %u\n",
-			 tx_desc->tx.type_cs_vlan_tso);
-		dev_info(dev, "(TX)l2_len: %u\n", tx_desc->tx.l2_len);
-		dev_info(dev, "(TX)l3_len: %u\n", tx_desc->tx.l3_len);
-		dev_info(dev, "(TX)l4_len: %u\n", tx_desc->tx.l4_len);
-		dev_info(dev, "(TX)vlan_msec: %u\n",
-			 tx_desc->tx.ol_type_vlan_msec);
-		dev_info(dev, "(TX)ol2_len: %u\n", tx_desc->tx.ol2_len);
-		dev_info(dev, "(TX)ol3_len: %u\n", tx_desc->tx.ol3_len);
-		dev_info(dev, "(TX)ol4_len: %u\n", tx_desc->tx.ol4_len);
-	}
+	ring = &priv->ring[d->qid + d->handle->kinfo.num_tqps];
+	for (i = 0; i < ring->desc_num; i++) {
+		desc = &ring->desc[i];
 
-	dev_info(dev, "(TX)vlan_tag: %u\n",
-		 le16_to_cpu(tx_desc->tx.outer_vlan_tag));
-	dev_info(dev, "(TX)tv: %u\n", le16_to_cpu(tx_desc->tx.tv));
-	dev_info(dev, "(TX)paylen_ol4cs: %u\n",
-		 le32_to_cpu(tx_desc->tx.paylen_ol4cs));
-	dev_info(dev, "(TX)vld_ra_ri: %u\n",
-		 le16_to_cpu(tx_desc->tx.bdtp_fe_sc_vld_ra_ri));
-	dev_info(dev, "(TX)mss_hw_csum: %u\n", mss_hw_csum);
-
-	ring = &priv->ring[q_num + h->kinfo.num_tqps];
-	value = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_TAIL_REG);
-	rx_index = (cnt == 1) ? value : tx_index;
-	rx_desc = &ring->desc[rx_index];
-
-	addr = le64_to_cpu(rx_desc->addr);
-	l234info = le32_to_cpu(rx_desc->rx.l234_info);
-	dev_info(dev, "RX Queue Num: %u, BD Index: %u\n", q_num, rx_index);
-	dev_info(dev, "(RX)addr: %pad\n", &addr);
-	dev_info(dev, "(RX)l234_info: %u\n", l234info);
-
-	if (l234info & BIT(HNS3_RXD_L2_CSUM_B)) {
-		u32 lo, hi;
-
-		lo = hnae3_get_field(l234info, HNS3_RXD_L2_CSUM_L_M,
-				     HNS3_RXD_L2_CSUM_L_S);
-		hi = hnae3_get_field(l234info, HNS3_RXD_L2_CSUM_H_M,
-				     HNS3_RXD_L2_CSUM_H_S);
-		dev_info(dev, "(RX)csum: %u\n", lo | hi << 8);
+		hns3_dump_rx_bd_info(priv, desc, result, i);
+		hns3_dbg_fill_content(content, sizeof(content),
+				      rx_bd_info_items, (const char **)result,
+				      ARRAY_SIZE(rx_bd_info_items));
+		pos += scnprintf(buf + pos, len - pos, "%s", content);
 	}
 
-	dev_info(dev, "(RX)pkt_len: %u\n", le16_to_cpu(rx_desc->rx.pkt_len));
-	dev_info(dev, "(RX)size: %u\n", le16_to_cpu(rx_desc->rx.size));
-	dev_info(dev, "(RX)rss_hash: %u\n", le32_to_cpu(rx_desc->rx.rss_hash));
-	dev_info(dev, "(RX)fd_id: %u\n", le16_to_cpu(rx_desc->rx.fd_id));
-	dev_info(dev, "(RX)vlan_tag: %u\n", le16_to_cpu(rx_desc->rx.vlan_tag));
-	dev_info(dev, "(RX)o_dm_vlan_id_fb: %u\n",
-		 le16_to_cpu(rx_desc->rx.o_dm_vlan_id_fb));
-	dev_info(dev, "(RX)ot_vlan_tag: %u\n",
-		 le16_to_cpu(rx_desc->rx.ot_vlan_tag));
-	dev_info(dev, "(RX)bd_base_info: %u\n",
-		 le32_to_cpu(rx_desc->rx.bd_base_info));
-
 	return 0;
 }
 
-static void hns3_dbg_help(struct hnae3_handle *h)
-{
-#define HNS3_DBG_BUF_LEN 256
-
-	char printf_buf[HNS3_DBG_BUF_LEN];
-
-	dev_info(&h->pdev->dev, "available commands\n");
-	dev_info(&h->pdev->dev, "queue info <number>\n");
-	dev_info(&h->pdev->dev, "queue map\n");
-	dev_info(&h->pdev->dev, "bd info <q_num> <bd index>\n");
-	dev_info(&h->pdev->dev, "dev capability\n");
-	dev_info(&h->pdev->dev, "dev spec\n");
-
-	if (!hns3_is_phys_func(h->pdev))
-		return;
-
-	dev_info(&h->pdev->dev, "dump fd tcam\n");
-	dev_info(&h->pdev->dev, "dump tc\n");
-	dev_info(&h->pdev->dev, "dump tm map <q_num>\n");
-	dev_info(&h->pdev->dev, "dump tm\n");
-	dev_info(&h->pdev->dev, "dump qos pause cfg\n");
-	dev_info(&h->pdev->dev, "dump qos pri map\n");
-	dev_info(&h->pdev->dev, "dump qos buf cfg\n");
-	dev_info(&h->pdev->dev, "dump mng tbl\n");
-	dev_info(&h->pdev->dev, "dump reset info\n");
-	dev_info(&h->pdev->dev, "dump m7 info\n");
-	dev_info(&h->pdev->dev, "dump ncl_config <offset> <length>(in hex)\n");
-	dev_info(&h->pdev->dev, "dump mac tnl status\n");
-	dev_info(&h->pdev->dev, "dump loopback\n");
-	dev_info(&h->pdev->dev, "dump qs shaper [qs id]\n");
-	dev_info(&h->pdev->dev, "dump uc mac list <func id>\n");
-	dev_info(&h->pdev->dev, "dump mc mac list <func id>\n");
-	dev_info(&h->pdev->dev, "dump intr\n");
-
-	memset(printf_buf, 0, HNS3_DBG_BUF_LEN);
-	strncat(printf_buf, "dump reg [[bios common] [ssu <port_id>]",
-		HNS3_DBG_BUF_LEN - 1);
-	strncat(printf_buf + strlen(printf_buf),
-		" [igu egu <port_id>] [rpu <tc_queue_num>]",
-		HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1);
-	strncat(printf_buf + strlen(printf_buf),
-		" [rtc] [ppp] [rcb] [tqp <queue_num>] [mac]]\n",
-		HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1);
-	dev_info(&h->pdev->dev, "%s", printf_buf);
-
-	memset(printf_buf, 0, HNS3_DBG_BUF_LEN);
-	strncat(printf_buf, "dump reg dcb <port_id> <pri_id> <pg_id>",
-		HNS3_DBG_BUF_LEN - 1);
-	strncat(printf_buf + strlen(printf_buf), " <rq_id> <nq_id> <qset_id>\n",
-		HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1);
-	dev_info(&h->pdev->dev, "%s", printf_buf);
-}
+static const struct hns3_dbg_item tx_bd_info_items[] = {
+	{ "BD_IDX", 5 },
+	{ "ADDRESS", 2 },
+	{ "VLAN_TAG", 2 },
+	{ "SIZE", 2 },
+	{ "T_CS_VLAN_TSO", 2 },
+	{ "OT_VLAN_TAG", 3 },
+	{ "TV", 2 },
+	{ "OLT_VLAN_LEN", 2},
+	{ "PAYLEN_OL4CS", 2},
+	{ "BD_FE_SC_VLD", 2},
+	{ "MSS_HW_CSUM", 0},
+};
 
-static void hns3_dbg_dev_caps(struct hnae3_handle *h)
+static void hns3_dump_tx_bd_info(struct hns3_nic_priv *priv,
+				 struct hns3_desc *desc, char **result, int idx)
 {
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
-	unsigned long *caps;
-
-	caps = ae_dev->caps;
-
-	dev_info(&h->pdev->dev, "support FD: %s\n",
-		 test_bit(HNAE3_DEV_SUPPORT_FD_B, caps) ? "yes" : "no");
-	dev_info(&h->pdev->dev, "support GRO: %s\n",
-		 test_bit(HNAE3_DEV_SUPPORT_GRO_B, caps) ? "yes" : "no");
-	dev_info(&h->pdev->dev, "support FEC: %s\n",
-		 test_bit(HNAE3_DEV_SUPPORT_FEC_B, caps) ? "yes" : "no");
-	dev_info(&h->pdev->dev, "support UDP GSO: %s\n",
-		 test_bit(HNAE3_DEV_SUPPORT_UDP_GSO_B, caps) ? "yes" : "no");
-	dev_info(&h->pdev->dev, "support PTP: %s\n",
-		 test_bit(HNAE3_DEV_SUPPORT_PTP_B, caps) ? "yes" : "no");
-	dev_info(&h->pdev->dev, "support INT QL: %s\n",
-		 test_bit(HNAE3_DEV_SUPPORT_INT_QL_B, caps) ? "yes" : "no");
-	dev_info(&h->pdev->dev, "support HW TX csum: %s\n",
-		 test_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, caps) ? "yes" : "no");
-	dev_info(&h->pdev->dev, "support UDP tunnel csum: %s\n",
-		 test_bit(HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, caps) ?
-		 "yes" : "no");
-	dev_info(&h->pdev->dev, "support PAUSE: %s\n",
-		 test_bit(HNAE3_DEV_SUPPORT_PAUSE_B, ae_dev->caps) ?
-		 "yes" : "no");
-	dev_info(&h->pdev->dev, "support imp-controlled PHY: %s\n",
-		 test_bit(HNAE3_DEV_SUPPORT_PHY_IMP_B, caps) ? "yes" : "no");
+	unsigned int j = 0;
+
+	sprintf(result[j++], "%6d", idx);
+	sprintf(result[j++], "%#llx", le64_to_cpu(desc->addr));
+	sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.vlan_tag));
+	sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.send_size));
+	sprintf(result[j++], "%#x",
+		le32_to_cpu(desc->tx.type_cs_vlan_tso_len));
+	sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.outer_vlan_tag));
+	sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.tv));
+	sprintf(result[j++], "%10u",
+		le32_to_cpu(desc->tx.ol_type_vlan_len_msec));
+	sprintf(result[j++], "%#x", le32_to_cpu(desc->tx.paylen_ol4cs));
+	sprintf(result[j++], "%#x", le16_to_cpu(desc->tx.bdtp_fe_sc_vld_ra_ri));
+	sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.mss_hw_csum));
 }
 
-static void hns3_dbg_dev_specs(struct hnae3_handle *h)
+static int hns3_dbg_tx_bd_info(struct hns3_dbg_data *d, char *buf, int len)
 {
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
-	struct hnae3_dev_specs *dev_specs = &ae_dev->dev_specs;
-	struct hnae3_knic_private_info *kinfo = &h->kinfo;
-	struct hns3_nic_priv *priv  = h->priv;
-
-	dev_info(priv->dev, "MAC entry num: %u\n", dev_specs->mac_entry_num);
-	dev_info(priv->dev, "MNG entry num: %u\n", dev_specs->mng_entry_num);
-	dev_info(priv->dev, "MAX non tso bd num: %u\n",
-		 dev_specs->max_non_tso_bd_num);
-	dev_info(priv->dev, "RSS ind tbl size: %u\n",
-		 dev_specs->rss_ind_tbl_size);
-	dev_info(priv->dev, "RSS key size: %u\n", dev_specs->rss_key_size);
-	dev_info(priv->dev, "RSS size: %u\n", kinfo->rss_size);
-	dev_info(priv->dev, "Allocated RSS size: %u\n", kinfo->req_rss_size);
-	dev_info(priv->dev, "Task queue pairs numbers: %u\n", kinfo->num_tqps);
-
-	dev_info(priv->dev, "RX buffer length: %u\n", kinfo->rx_buf_len);
-	dev_info(priv->dev, "Desc num per TX queue: %u\n", kinfo->num_tx_desc);
-	dev_info(priv->dev, "Desc num per RX queue: %u\n", kinfo->num_rx_desc);
-	dev_info(priv->dev, "Total number of enabled TCs: %u\n",
-		 kinfo->tc_info.num_tc);
-	dev_info(priv->dev, "MAX INT QL: %u\n", dev_specs->int_ql_max);
-	dev_info(priv->dev, "MAX INT GL: %u\n", dev_specs->max_int_gl);
-	dev_info(priv->dev, "MAX frame size: %u\n", dev_specs->max_frm_size);
-	dev_info(priv->dev, "MAX TM RATE: %uMbps\n", dev_specs->max_tm_rate);
-	dev_info(priv->dev, "MAX QSET number: %u\n", dev_specs->max_qset_num);
-}
+	char data_str[ARRAY_SIZE(tx_bd_info_items)][HNS3_DBG_DATA_STR_LEN];
+	struct hns3_nic_priv *priv = d->handle->priv;
+	char *result[ARRAY_SIZE(tx_bd_info_items)];
+	char content[HNS3_DBG_INFO_LEN];
+	struct hns3_enet_ring *ring;
+	struct hns3_desc *desc;
+	unsigned int i;
+	int pos = 0;
 
-static ssize_t hns3_dbg_cmd_read(struct file *filp, char __user *buffer,
-				 size_t count, loff_t *ppos)
-{
-	int uncopy_bytes;
-	char *buf;
-	int len;
+	if (d->qid >= d->handle->kinfo.num_tqps) {
+		dev_err(&d->handle->pdev->dev,
+			"queue%u is not in use\n", d->qid);
+		return -EINVAL;
+	}
 
-	if (*ppos != 0)
-		return 0;
+	for (i = 0; i < ARRAY_SIZE(tx_bd_info_items); i++)
+		result[i] = &data_str[i][0];
 
-	if (count < HNS3_DBG_READ_LEN)
-		return -ENOSPC;
+	pos += scnprintf(buf + pos, len - pos,
+			  "Queue %u tx bd info:\n", d->qid);
+	hns3_dbg_fill_content(content, sizeof(content), tx_bd_info_items,
+			      NULL, ARRAY_SIZE(tx_bd_info_items));
+	pos += scnprintf(buf + pos, len - pos, "%s", content);
 
-	buf = kzalloc(HNS3_DBG_READ_LEN, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
+	ring = &priv->ring[d->qid];
+	for (i = 0; i < ring->desc_num; i++) {
+		desc = &ring->desc[i];
 
-	len = scnprintf(buf, HNS3_DBG_READ_LEN, "%s\n",
-			"Please echo help to cmd to get help information");
-	uncopy_bytes = copy_to_user(buffer, buf, len);
+		hns3_dump_tx_bd_info(priv, desc, result, i);
+		hns3_dbg_fill_content(content, sizeof(content),
+				      tx_bd_info_items, (const char **)result,
+				      ARRAY_SIZE(tx_bd_info_items));
+		pos += scnprintf(buf + pos, len - pos, "%s", content);
+	}
 
-	kfree(buf);
+	return 0;
+}
 
-	if (uncopy_bytes)
-		return -EFAULT;
+static void
+hns3_dbg_dev_caps(struct hnae3_handle *h, char *buf, int len, int *pos)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
+	static const char * const str[] = {"no", "yes"};
+	unsigned long *caps = ae_dev->caps;
+	u32 i, state;
+
+	*pos += scnprintf(buf + *pos, len - *pos, "dev capability:\n");
+
+	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cap); i++) {
+		state = test_bit(hns3_dbg_cap[i].cap_bit, caps);
+		*pos += scnprintf(buf + *pos, len - *pos, "%s: %s\n",
+				  hns3_dbg_cap[i].name, str[state]);
+	}
 
-	return (*ppos = len);
+	*pos += scnprintf(buf + *pos, len - *pos, "\n");
 }
 
-static int hns3_dbg_check_cmd(struct hnae3_handle *handle, char *cmd_buf)
+static void
+hns3_dbg_dev_specs(struct hnae3_handle *h, char *buf, int len, int *pos)
 {
-	int ret = 0;
-
-	if (strncmp(cmd_buf, "help", 4) == 0)
-		hns3_dbg_help(handle);
-	else if (strncmp(cmd_buf, "queue info", 10) == 0)
-		ret = hns3_dbg_queue_info(handle, cmd_buf);
-	else if (strncmp(cmd_buf, "queue map", 9) == 0)
-		ret = hns3_dbg_queue_map(handle);
-	else if (strncmp(cmd_buf, "bd info", 7) == 0)
-		ret = hns3_dbg_bd_info(handle, cmd_buf);
-	else if (strncmp(cmd_buf, "dev capability", 14) == 0)
-		hns3_dbg_dev_caps(handle);
-	else if (strncmp(cmd_buf, "dev spec", 8) == 0)
-		hns3_dbg_dev_specs(handle);
-	else if (handle->ae_algo->ops->dbg_run_cmd)
-		ret = handle->ae_algo->ops->dbg_run_cmd(handle, cmd_buf);
-	else
-		ret = -EOPNOTSUPP;
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
+	struct hnae3_dev_specs *dev_specs = &ae_dev->dev_specs;
+	struct hnae3_knic_private_info *kinfo = &h->kinfo;
 
-	return ret;
+	*pos += scnprintf(buf + *pos, len - *pos, "dev_spec:\n");
+	*pos += scnprintf(buf + *pos, len - *pos, "MAC entry num: %u\n",
+			  dev_specs->mac_entry_num);
+	*pos += scnprintf(buf + *pos, len - *pos, "MNG entry num: %u\n",
+			  dev_specs->mng_entry_num);
+	*pos += scnprintf(buf + *pos, len - *pos, "MAX non tso bd num: %u\n",
+			  dev_specs->max_non_tso_bd_num);
+	*pos += scnprintf(buf + *pos, len - *pos, "RSS ind tbl size: %u\n",
+			  dev_specs->rss_ind_tbl_size);
+	*pos += scnprintf(buf + *pos, len - *pos, "RSS key size: %u\n",
+			  dev_specs->rss_key_size);
+	*pos += scnprintf(buf + *pos, len - *pos, "RSS size: %u\n",
+			  kinfo->rss_size);
+	*pos += scnprintf(buf + *pos, len - *pos, "Allocated RSS size: %u\n",
+			  kinfo->req_rss_size);
+	*pos += scnprintf(buf + *pos, len - *pos,
+			  "Task queue pairs numbers: %u\n",
+			  kinfo->num_tqps);
+	*pos += scnprintf(buf + *pos, len - *pos, "RX buffer length: %u\n",
+			  kinfo->rx_buf_len);
+	*pos += scnprintf(buf + *pos, len - *pos, "Desc num per TX queue: %u\n",
+			  kinfo->num_tx_desc);
+	*pos += scnprintf(buf + *pos, len - *pos, "Desc num per RX queue: %u\n",
+			  kinfo->num_rx_desc);
+	*pos += scnprintf(buf + *pos, len - *pos,
+			  "Total number of enabled TCs: %u\n",
+			  kinfo->tc_info.num_tc);
+	*pos += scnprintf(buf + *pos, len - *pos, "MAX INT QL: %u\n",
+			  dev_specs->int_ql_max);
+	*pos += scnprintf(buf + *pos, len - *pos, "MAX INT GL: %u\n",
+			  dev_specs->max_int_gl);
+	*pos += scnprintf(buf + *pos, len - *pos, "MAX TM RATE: %u\n",
+			  dev_specs->max_tm_rate);
+	*pos += scnprintf(buf + *pos, len - *pos, "MAX QSET number: %u\n",
+			  dev_specs->max_qset_num);
 }
 
-static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer,
-				  size_t count, loff_t *ppos)
+static int hns3_dbg_dev_info(struct hnae3_handle *h, char *buf, int len)
 {
-	struct hnae3_handle *handle = filp->private_data;
-	struct hns3_nic_priv *priv  = handle->priv;
-	char *cmd_buf, *cmd_buf_tmp;
-	int uncopied_bytes;
-	int ret;
+	int pos = 0;
 
-	if (*ppos != 0)
-		return 0;
+	hns3_dbg_dev_caps(h, buf, len, &pos);
 
-	/* Judge if the instance is being reset. */
-	if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
-	    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
-		return 0;
+	hns3_dbg_dev_specs(h, buf, len, &pos);
 
-	if (count > HNS3_DBG_WRITE_LEN)
-		return -ENOSPC;
+	return 0;
+}
 
-	cmd_buf = kzalloc(count + 1, GFP_KERNEL);
-	if (!cmd_buf)
-		return count;
+static int hns3_dbg_get_cmd_index(struct hnae3_handle *handle,
+				  const unsigned char *name, u32 *index)
+{
+	u32 i;
 
-	uncopied_bytes = copy_from_user(cmd_buf, buffer, count);
-	if (uncopied_bytes) {
-		kfree(cmd_buf);
-		return -EFAULT;
+	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) {
+		if (!strncmp(name, hns3_dbg_cmd[i].name,
+			     strlen(hns3_dbg_cmd[i].name))) {
+			*index = i;
+			return 0;
+		}
 	}
 
-	cmd_buf[count] = '\0';
+	dev_err(&handle->pdev->dev, "unknown command(%s)\n", name);
+	return -EINVAL;
+}
 
-	cmd_buf_tmp = strchr(cmd_buf, '\n');
-	if (cmd_buf_tmp) {
-		*cmd_buf_tmp = '\0';
-		count = cmd_buf_tmp - cmd_buf + 1;
-	}
+static const struct hns3_dbg_func hns3_dbg_cmd_func[] = {
+	{
+		.cmd = HNAE3_DBG_CMD_QUEUE_MAP,
+		.dbg_dump = hns3_dbg_queue_map,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_DEV_INFO,
+		.dbg_dump = hns3_dbg_dev_info,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_TX_BD,
+		.dbg_dump_bd = hns3_dbg_tx_bd_info,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_RX_BD,
+		.dbg_dump_bd = hns3_dbg_rx_bd_info,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_RX_QUEUE_INFO,
+		.dbg_dump = hns3_dbg_rx_queue_info,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_TX_QUEUE_INFO,
+		.dbg_dump = hns3_dbg_tx_queue_info,
+	},
+};
 
-	ret = hns3_dbg_check_cmd(handle, cmd_buf);
-	if (ret)
-		hns3_dbg_help(handle);
+static int hns3_dbg_read_cmd(struct hns3_dbg_data *dbg_data,
+			     enum hnae3_dbg_cmd cmd, char *buf, int len)
+{
+	const struct hnae3_ae_ops *ops = dbg_data->handle->ae_algo->ops;
+	const struct hns3_dbg_func *cmd_func;
+	u32 i;
+
+	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd_func); i++) {
+		if (cmd == hns3_dbg_cmd_func[i].cmd) {
+			cmd_func = &hns3_dbg_cmd_func[i];
+			if (cmd_func->dbg_dump)
+				return cmd_func->dbg_dump(dbg_data->handle, buf,
+							  len);
+			else
+				return cmd_func->dbg_dump_bd(dbg_data, buf,
+							     len);
+		}
+	}
 
-	kfree(cmd_buf);
-	cmd_buf = NULL;
+	if (!ops->dbg_read_cmd)
+		return -EOPNOTSUPP;
 
-	return count;
+	return ops->dbg_read_cmd(dbg_data->handle, cmd, buf, len);
 }
 
 static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer,
 			     size_t count, loff_t *ppos)
 {
-	struct hnae3_handle *handle = filp->private_data;
-	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	struct hns3_dbg_data *dbg_data = filp->private_data;
+	struct hnae3_handle *handle = dbg_data->handle;
 	struct hns3_nic_priv *priv = handle->priv;
-	char *cmd_buf, *read_buf;
 	ssize_t size = 0;
-	int ret = 0;
-
-	read_buf = kzalloc(HNS3_DBG_READ_LEN, GFP_KERNEL);
-	if (!read_buf)
-		return -ENOMEM;
+	char **save_buf;
+	char *read_buf;
+	u32 index;
+	int ret;
 
-	cmd_buf = filp->f_path.dentry->d_iname;
+	ret = hns3_dbg_get_cmd_index(handle, filp->f_path.dentry->d_iname,
+				     &index);
+	if (ret)
+		return ret;
 
-	if (ops->dbg_read_cmd)
-		ret = ops->dbg_read_cmd(handle, cmd_buf, read_buf,
-					HNS3_DBG_READ_LEN);
+	save_buf = &hns3_dbg_cmd[index].buf;
 
-	if (ret) {
-		dev_info(priv->dev, "unknown command\n");
+	if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
+	    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) {
+		ret = -EBUSY;
 		goto out;
 	}
 
+	if (*save_buf) {
+		read_buf = *save_buf;
+	} else {
+		read_buf = kvzalloc(hns3_dbg_cmd[index].buf_len, GFP_KERNEL);
+		if (!read_buf)
+			return -ENOMEM;
+
+		/* save the buffer addr until the last read operation */
+		*save_buf = read_buf;
+	}
+
+	/* get data ready for the first time to read */
+	if (!*ppos) {
+		ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd,
+					read_buf, hns3_dbg_cmd[index].buf_len);
+		if (ret)
+			goto out;
+	}
+
 	size = simple_read_from_buffer(buffer, count, ppos, read_buf,
 				       strlen(read_buf));
+	if (size > 0)
+		return size;
 
 out:
-	kfree(read_buf);
-	return size;
-}
+	/* free the buffer for the last read operation */
+	if (*save_buf) {
+		kvfree(*save_buf);
+		*save_buf = NULL;
+	}
 
-static const struct file_operations hns3_dbg_cmd_fops = {
-	.owner = THIS_MODULE,
-	.open  = simple_open,
-	.read  = hns3_dbg_cmd_read,
-	.write = hns3_dbg_cmd_write,
-};
+	return ret;
+}
 
 static const struct file_operations hns3_dbg_fops = {
 	.owner = THIS_MODULE,
@@ -546,29 +1058,108 @@ static const struct file_operations hns3_dbg_fops = {
 	.read  = hns3_dbg_read,
 };
 
-void hns3_dbg_init(struct hnae3_handle *handle)
+static int hns3_dbg_bd_file_init(struct hnae3_handle *handle, u32 cmd)
+{
+	struct dentry *entry_dir;
+	struct hns3_dbg_data *data;
+	u16 max_queue_num;
+	unsigned int i;
+
+	entry_dir = hns3_dbg_dentry[hns3_dbg_cmd[cmd].dentry].dentry;
+	max_queue_num = hns3_get_max_available_channels(handle);
+	data = devm_kzalloc(&handle->pdev->dev, max_queue_num * sizeof(*data),
+			    GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	for (i = 0; i < max_queue_num; i++) {
+		char name[HNS3_DBG_FILE_NAME_LEN];
+
+		data[i].handle = handle;
+		data[i].qid = i;
+		sprintf(name, "%s%u", hns3_dbg_cmd[cmd].name, i);
+		debugfs_create_file(name, 0400, entry_dir, &data[i],
+				    &hns3_dbg_fops);
+	}
+
+	return 0;
+}
+
+static int
+hns3_dbg_common_file_init(struct hnae3_handle *handle, u32 cmd)
+{
+	struct hns3_dbg_data *data;
+	struct dentry *entry_dir;
+
+	data = devm_kzalloc(&handle->pdev->dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->handle = handle;
+	entry_dir = hns3_dbg_dentry[hns3_dbg_cmd[cmd].dentry].dentry;
+	debugfs_create_file(hns3_dbg_cmd[cmd].name, 0400, entry_dir,
+			    data, &hns3_dbg_fops);
+
+	return 0;
+}
+
+int hns3_dbg_init(struct hnae3_handle *handle)
 {
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
 	const char *name = pci_name(handle->pdev);
-	struct dentry *entry_dir;
+	int ret;
+	u32 i;
+
+	hns3_dbg_dentry[HNS3_DBG_DENTRY_COMMON].dentry =
+				debugfs_create_dir(name, hns3_dbgfs_root);
+	handle->hnae3_dbgfs = hns3_dbg_dentry[HNS3_DBG_DENTRY_COMMON].dentry;
+
+	for (i = 0; i < HNS3_DBG_DENTRY_COMMON; i++)
+		hns3_dbg_dentry[i].dentry =
+			debugfs_create_dir(hns3_dbg_dentry[i].name,
+					   handle->hnae3_dbgfs);
+
+	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) {
+		if ((hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_TM_NODES &&
+		     ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2) ||
+		    (hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_PTP_INFO &&
+		     !test_bit(HNAE3_DEV_SUPPORT_PTP_B, ae_dev->caps)))
+			continue;
 
-	handle->hnae3_dbgfs = debugfs_create_dir(name, hns3_dbgfs_root);
+		if (!hns3_dbg_cmd[i].init) {
+			dev_err(&handle->pdev->dev,
+				"cmd %s lack of init func\n",
+				hns3_dbg_cmd[i].name);
+			ret = -EINVAL;
+			goto out;
+		}
 
-	debugfs_create_file("cmd", 0600, handle->hnae3_dbgfs, handle,
-			    &hns3_dbg_cmd_fops);
+		ret = hns3_dbg_cmd[i].init(handle, i);
+		if (ret) {
+			dev_err(&handle->pdev->dev, "failed to init cmd %s\n",
+				hns3_dbg_cmd[i].name);
+			goto out;
+		}
+	}
 
-	entry_dir = debugfs_create_dir("tm", handle->hnae3_dbgfs);
-	if (ae_dev->dev_version > HNAE3_DEVICE_VERSION_V2)
-		debugfs_create_file(HNAE3_DBG_TM_NODES, 0600, entry_dir, handle,
-				    &hns3_dbg_fops);
-	debugfs_create_file(HNAE3_DBG_TM_PRI, 0600, entry_dir, handle,
-			    &hns3_dbg_fops);
-	debugfs_create_file(HNAE3_DBG_TM_QSET, 0600, entry_dir, handle,
-			    &hns3_dbg_fops);
+	return 0;
+
+out:
+	debugfs_remove_recursive(handle->hnae3_dbgfs);
+	handle->hnae3_dbgfs = NULL;
+	return ret;
 }
 
 void hns3_dbg_uninit(struct hnae3_handle *handle)
 {
+	u32 i;
+
+	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++)
+		if (hns3_dbg_cmd[i].buf) {
+			kvfree(hns3_dbg_cmd[i].buf);
+			hns3_dbg_cmd[i].buf = NULL;
+		}
+
 	debugfs_remove_recursive(handle->hnae3_dbgfs);
 	handle->hnae3_dbgfs = NULL;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h
new file mode 100644
index 000000000000..f3766ff38bb7
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2021 Hisilicon Limited. */
+
+#ifndef __HNS3_DEBUGFS_H
+#define __HNS3_DEBUGFS_H
+
+#define HNS3_DBG_READ_LEN	65536
+#define HNS3_DBG_READ_LEN_128KB	0x20000
+#define HNS3_DBG_READ_LEN_1MB	0x100000
+#define HNS3_DBG_READ_LEN_4MB	0x400000
+#define HNS3_DBG_WRITE_LEN	1024
+
+#define HNS3_DBG_DATA_STR_LEN	32
+#define HNS3_DBG_INFO_LEN	256
+#define HNS3_DBG_ITEM_NAME_LEN	32
+#define HNS3_DBG_FILE_NAME_LEN	16
+
+struct hns3_dbg_item {
+	char name[HNS3_DBG_ITEM_NAME_LEN];
+	u16 interval; /* blank numbers after the item */
+};
+
+struct hns3_dbg_data {
+	struct hnae3_handle *handle;
+	u16 qid;
+};
+
+enum hns3_dbg_dentry_type {
+	HNS3_DBG_DENTRY_TM,
+	HNS3_DBG_DENTRY_TX_BD,
+	HNS3_DBG_DENTRY_RX_BD,
+	HNS3_DBG_DENTRY_MAC,
+	HNS3_DBG_DENTRY_REG,
+	HNS3_DBG_DENTRY_QUEUE,
+	HNS3_DBG_DENTRY_FD,
+	HNS3_DBG_DENTRY_COMMON,
+};
+
+struct hns3_dbg_dentry_info {
+	const char *name;
+	struct dentry *dentry;
+};
+
+struct hns3_dbg_cmd_info {
+	const char *name;
+	enum hnae3_dbg_cmd cmd;
+	enum hns3_dbg_dentry_type dentry;
+	u32 buf_len;
+	char *buf;
+	int (*init)(struct hnae3_handle *handle, unsigned int cmd);
+};
+
+struct hns3_dbg_func {
+	enum hnae3_dbg_cmd cmd;
+	int (*dbg_dump)(struct hnae3_handle *handle, char *buf, int len);
+	int (*dbg_dump_bd)(struct hns3_dbg_data *data, char *buf, int len);
+};
+
+struct hns3_dbg_cap_info {
+	const char *name;
+	enum HNAE3_DEV_CAP_BITS cap_bit;
+};
+
+#endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 026558f8e04b..cdb5f14fb6bc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -53,6 +53,19 @@ static int debug = -1;
 module_param(debug, int, 0);
 MODULE_PARM_DESC(debug, " Network interface message level setting");
 
+static unsigned int tx_spare_buf_size;
+module_param(tx_spare_buf_size, uint, 0400);
+MODULE_PARM_DESC(tx_spare_buf_size, "Size used to allocate tx spare buffer");
+
+static unsigned int tx_sgl = 1;
+module_param(tx_sgl, uint, 0600);
+MODULE_PARM_DESC(tx_sgl, "Minimum number of frags when using dma_map_sg() to optimize the IOMMU mapping");
+
+#define HNS3_SGL_SIZE(nfrag)	(sizeof(struct scatterlist) * (nfrag) +	\
+				 sizeof(struct sg_table))
+#define HNS3_MAX_SGL_SIZE	ALIGN(HNS3_SGL_SIZE(HNS3_MAX_TSO_BD_NUM),\
+				      dma_get_cache_alignment())
+
 #define DEFAULT_MSG_LEVEL (NETIF_MSG_PROBE | NETIF_MSG_LINK | \
 			   NETIF_MSG_IFDOWN | NETIF_MSG_IFUP)
 
@@ -91,11 +104,284 @@ static const struct pci_device_id hns3_pci_tbl[] = {
 };
 MODULE_DEVICE_TABLE(pci, hns3_pci_tbl);
 
+#define HNS3_RX_PTYPE_ENTRY(ptype, l, s, t) \
+	{	ptype, \
+		l, \
+		CHECKSUM_##s, \
+		HNS3_L3_TYPE_##t, \
+		1 }
+
+#define HNS3_RX_PTYPE_UNUSED_ENTRY(ptype) \
+		{ ptype, 0, CHECKSUM_NONE, HNS3_L3_TYPE_PARSE_FAIL, 0 }
+
+static const struct hns3_rx_ptype hns3_rx_ptype_tbl[] = {
+	HNS3_RX_PTYPE_UNUSED_ENTRY(0),
+	HNS3_RX_PTYPE_ENTRY(1, 0, COMPLETE, ARP),
+	HNS3_RX_PTYPE_ENTRY(2, 0, COMPLETE, RARP),
+	HNS3_RX_PTYPE_ENTRY(3, 0, COMPLETE, LLDP),
+	HNS3_RX_PTYPE_ENTRY(4, 0, COMPLETE, PARSE_FAIL),
+	HNS3_RX_PTYPE_ENTRY(5, 0, COMPLETE, PARSE_FAIL),
+	HNS3_RX_PTYPE_ENTRY(6, 0, COMPLETE, PARSE_FAIL),
+	HNS3_RX_PTYPE_ENTRY(7, 0, COMPLETE, CNM),
+	HNS3_RX_PTYPE_ENTRY(8, 0, NONE, PARSE_FAIL),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(9),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(10),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(11),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(12),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(13),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(14),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(15),
+	HNS3_RX_PTYPE_ENTRY(16, 0, COMPLETE, PARSE_FAIL),
+	HNS3_RX_PTYPE_ENTRY(17, 0, COMPLETE, IPV4),
+	HNS3_RX_PTYPE_ENTRY(18, 0, COMPLETE, IPV4),
+	HNS3_RX_PTYPE_ENTRY(19, 0, UNNECESSARY, IPV4),
+	HNS3_RX_PTYPE_ENTRY(20, 0, UNNECESSARY, IPV4),
+	HNS3_RX_PTYPE_ENTRY(21, 0, NONE, IPV4),
+	HNS3_RX_PTYPE_ENTRY(22, 0, UNNECESSARY, IPV4),
+	HNS3_RX_PTYPE_ENTRY(23, 0, NONE, IPV4),
+	HNS3_RX_PTYPE_ENTRY(24, 0, NONE, IPV4),
+	HNS3_RX_PTYPE_ENTRY(25, 0, UNNECESSARY, IPV4),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(26),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(27),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(28),
+	HNS3_RX_PTYPE_ENTRY(29, 0, COMPLETE, PARSE_FAIL),
+	HNS3_RX_PTYPE_ENTRY(30, 0, COMPLETE, PARSE_FAIL),
+	HNS3_RX_PTYPE_ENTRY(31, 0, COMPLETE, IPV4),
+	HNS3_RX_PTYPE_ENTRY(32, 0, COMPLETE, IPV4),
+	HNS3_RX_PTYPE_ENTRY(33, 1, UNNECESSARY, IPV4),
+	HNS3_RX_PTYPE_ENTRY(34, 1, UNNECESSARY, IPV4),
+	HNS3_RX_PTYPE_ENTRY(35, 1, UNNECESSARY, IPV4),
+	HNS3_RX_PTYPE_ENTRY(36, 0, COMPLETE, IPV4),
+	HNS3_RX_PTYPE_ENTRY(37, 0, COMPLETE, IPV4),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(38),
+	HNS3_RX_PTYPE_ENTRY(39, 0, COMPLETE, IPV6),
+	HNS3_RX_PTYPE_ENTRY(40, 0, COMPLETE, IPV6),
+	HNS3_RX_PTYPE_ENTRY(41, 1, UNNECESSARY, IPV6),
+	HNS3_RX_PTYPE_ENTRY(42, 1, UNNECESSARY, IPV6),
+	HNS3_RX_PTYPE_ENTRY(43, 1, UNNECESSARY, IPV6),
+	HNS3_RX_PTYPE_ENTRY(44, 0, COMPLETE, IPV6),
+	HNS3_RX_PTYPE_ENTRY(45, 0, COMPLETE, IPV6),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(46),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(47),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(48),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(49),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(50),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(51),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(52),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(53),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(54),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(55),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(56),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(57),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(58),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(59),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(60),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(61),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(62),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(63),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(64),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(65),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(66),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(67),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(68),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(69),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(70),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(71),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(72),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(73),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(74),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(75),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(76),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(77),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(78),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(79),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(80),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(81),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(82),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(83),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(84),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(85),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(86),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(87),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(88),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(89),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(90),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(91),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(92),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(93),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(94),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(95),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(96),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(97),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(98),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(99),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(100),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(101),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(102),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(103),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(104),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(105),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(106),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(107),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(108),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(109),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(110),
+	HNS3_RX_PTYPE_ENTRY(111, 0, COMPLETE, IPV6),
+	HNS3_RX_PTYPE_ENTRY(112, 0, COMPLETE, IPV6),
+	HNS3_RX_PTYPE_ENTRY(113, 0, UNNECESSARY, IPV6),
+	HNS3_RX_PTYPE_ENTRY(114, 0, UNNECESSARY, IPV6),
+	HNS3_RX_PTYPE_ENTRY(115, 0, NONE, IPV6),
+	HNS3_RX_PTYPE_ENTRY(116, 0, UNNECESSARY, IPV6),
+	HNS3_RX_PTYPE_ENTRY(117, 0, NONE, IPV6),
+	HNS3_RX_PTYPE_ENTRY(118, 0, NONE, IPV6),
+	HNS3_RX_PTYPE_ENTRY(119, 0, UNNECESSARY, IPV6),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(120),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(121),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(122),
+	HNS3_RX_PTYPE_ENTRY(123, 0, COMPLETE, PARSE_FAIL),
+	HNS3_RX_PTYPE_ENTRY(124, 0, COMPLETE, PARSE_FAIL),
+	HNS3_RX_PTYPE_ENTRY(125, 0, COMPLETE, IPV4),
+	HNS3_RX_PTYPE_ENTRY(126, 0, COMPLETE, IPV4),
+	HNS3_RX_PTYPE_ENTRY(127, 1, UNNECESSARY, IPV4),
+	HNS3_RX_PTYPE_ENTRY(128, 1, UNNECESSARY, IPV4),
+	HNS3_RX_PTYPE_ENTRY(129, 1, UNNECESSARY, IPV4),
+	HNS3_RX_PTYPE_ENTRY(130, 0, COMPLETE, IPV4),
+	HNS3_RX_PTYPE_ENTRY(131, 0, COMPLETE, IPV4),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(132),
+	HNS3_RX_PTYPE_ENTRY(133, 0, COMPLETE, IPV6),
+	HNS3_RX_PTYPE_ENTRY(134, 0, COMPLETE, IPV6),
+	HNS3_RX_PTYPE_ENTRY(135, 1, UNNECESSARY, IPV6),
+	HNS3_RX_PTYPE_ENTRY(136, 1, UNNECESSARY, IPV6),
+	HNS3_RX_PTYPE_ENTRY(137, 1, UNNECESSARY, IPV6),
+	HNS3_RX_PTYPE_ENTRY(138, 0, COMPLETE, IPV6),
+	HNS3_RX_PTYPE_ENTRY(139, 0, COMPLETE, IPV6),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(140),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(141),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(142),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(143),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(144),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(145),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(146),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(147),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(148),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(149),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(150),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(151),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(152),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(153),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(154),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(155),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(156),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(157),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(158),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(159),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(160),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(161),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(162),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(163),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(164),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(165),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(166),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(167),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(168),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(169),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(170),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(171),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(172),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(173),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(174),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(175),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(176),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(177),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(178),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(179),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(180),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(181),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(182),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(183),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(184),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(185),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(186),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(187),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(188),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(189),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(190),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(191),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(192),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(193),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(194),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(195),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(196),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(197),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(198),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(199),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(200),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(201),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(202),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(203),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(204),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(205),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(206),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(207),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(208),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(209),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(210),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(211),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(212),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(213),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(214),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(215),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(216),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(217),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(218),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(219),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(220),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(221),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(222),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(223),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(224),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(225),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(226),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(227),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(228),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(229),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(230),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(231),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(232),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(233),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(234),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(235),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(236),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(237),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(238),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(239),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(240),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(241),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(242),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(243),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(244),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(245),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(246),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(247),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(248),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(249),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(250),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(251),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(252),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(253),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(254),
+	HNS3_RX_PTYPE_UNUSED_ENTRY(255),
+};
+
+#define HNS3_INVALID_PTYPE \
+		ARRAY_SIZE(hns3_rx_ptype_tbl)
+
 static irqreturn_t hns3_irq_handle(int irq, void *vector)
 {
 	struct hns3_enet_tqp_vector *tqp_vector = vector;
 
 	napi_schedule_irqoff(&tqp_vector->napi);
+	tqp_vector->event_cnt++;
 
 	return IRQ_HANDLED;
 }
@@ -199,6 +485,8 @@ static void hns3_vector_disable(struct hns3_enet_tqp_vector *tqp_vector)
 
 	disable_irq(tqp_vector->vector_irq);
 	napi_disable(&tqp_vector->napi);
+	cancel_work_sync(&tqp_vector->rx_group.dim.work);
+	cancel_work_sync(&tqp_vector->tx_group.dim.work);
 }
 
 void hns3_set_vector_coalesce_rl(struct hns3_enet_tqp_vector *tqp_vector,
@@ -357,7 +645,7 @@ static int hns3_nic_set_real_num_queue(struct net_device *netdev)
 	return 0;
 }
 
-static u16 hns3_get_max_available_channels(struct hnae3_handle *h)
+u16 hns3_get_max_available_channels(struct hnae3_handle *h)
 {
 	u16 alloc_tqps, max_rss_size, rss_size;
 
@@ -633,13 +921,10 @@ static u8 hns3_get_netdev_flags(struct net_device *netdev)
 {
 	u8 flags = 0;
 
-	if (netdev->flags & IFF_PROMISC) {
+	if (netdev->flags & IFF_PROMISC)
 		flags = HNAE3_USER_UPE | HNAE3_USER_MPE | HNAE3_BPE;
-	} else {
-		flags |= HNAE3_VLAN_FLTR;
-		if (netdev->flags & IFF_ALLMULTI)
-			flags |= HNAE3_USER_MPE;
-	}
+	else if (netdev->flags & IFF_ALLMULTI)
+		flags = HNAE3_USER_MPE;
 
 	return flags;
 }
@@ -669,23 +954,202 @@ void hns3_request_update_promisc_mode(struct hnae3_handle *handle)
 		ops->request_update_promisc_mode(handle);
 }
 
-void hns3_enable_vlan_filter(struct net_device *netdev, bool enable)
+static u32 hns3_tx_spare_space(struct hns3_enet_ring *ring)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = priv->ae_handle;
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
-	bool last_state;
+	struct hns3_tx_spare *tx_spare = ring->tx_spare;
+	u32 ntc, ntu;
 
-	if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2 &&
-	    h->ae_algo->ops->enable_vlan_filter) {
-		last_state = h->netdev_flags & HNAE3_VLAN_FLTR ? true : false;
-		if (enable != last_state) {
-			netdev_info(netdev,
-				    "%s vlan filter\n",
-				    enable ? "enable" : "disable");
-			h->ae_algo->ops->enable_vlan_filter(h, enable);
+	/* This smp_load_acquire() pairs with smp_store_release() in
+	 * hns3_tx_spare_update() called in tx desc cleaning process.
+	 */
+	ntc = smp_load_acquire(&tx_spare->last_to_clean);
+	ntu = tx_spare->next_to_use;
+
+	if (ntc > ntu)
+		return ntc - ntu - 1;
+
+	/* The free tx buffer is divided into two part, so pick the
+	 * larger one.
+	 */
+	return (ntc > (tx_spare->len - ntu) ? ntc :
+			(tx_spare->len - ntu)) - 1;
+}
+
+static void hns3_tx_spare_update(struct hns3_enet_ring *ring)
+{
+	struct hns3_tx_spare *tx_spare = ring->tx_spare;
+
+	if (!tx_spare ||
+	    tx_spare->last_to_clean == tx_spare->next_to_clean)
+		return;
+
+	/* This smp_store_release() pairs with smp_load_acquire() in
+	 * hns3_tx_spare_space() called in xmit process.
+	 */
+	smp_store_release(&tx_spare->last_to_clean,
+			  tx_spare->next_to_clean);
+}
+
+static bool hns3_can_use_tx_bounce(struct hns3_enet_ring *ring,
+				   struct sk_buff *skb,
+				   u32 space)
+{
+	u32 len = skb->len <= ring->tx_copybreak ? skb->len :
+				skb_headlen(skb);
+
+	if (len > ring->tx_copybreak)
+		return false;
+
+	if (ALIGN(len, dma_get_cache_alignment()) > space) {
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.tx_spare_full++;
+		u64_stats_update_end(&ring->syncp);
+		return false;
+	}
+
+	return true;
+}
+
+static bool hns3_can_use_tx_sgl(struct hns3_enet_ring *ring,
+				struct sk_buff *skb,
+				u32 space)
+{
+	if (skb->len <= ring->tx_copybreak || !tx_sgl ||
+	    (!skb_has_frag_list(skb) &&
+	     skb_shinfo(skb)->nr_frags < tx_sgl))
+		return false;
+
+	if (space < HNS3_MAX_SGL_SIZE) {
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.tx_spare_full++;
+		u64_stats_update_end(&ring->syncp);
+		return false;
+	}
+
+	return true;
+}
+
+static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring)
+{
+	struct hns3_tx_spare *tx_spare;
+	struct page *page;
+	u32 alloc_size;
+	dma_addr_t dma;
+	int order;
+
+	alloc_size = tx_spare_buf_size ? tx_spare_buf_size :
+		     ring->tqp->handle->kinfo.tx_spare_buf_size;
+	if (!alloc_size)
+		return;
+
+	order = get_order(alloc_size);
+	tx_spare = devm_kzalloc(ring_to_dev(ring), sizeof(*tx_spare),
+				GFP_KERNEL);
+	if (!tx_spare) {
+		/* The driver still work without the tx spare buffer */
+		dev_warn(ring_to_dev(ring), "failed to allocate hns3_tx_spare\n");
+		return;
+	}
+
+	page = alloc_pages_node(dev_to_node(ring_to_dev(ring)),
+				GFP_KERNEL, order);
+	if (!page) {
+		dev_warn(ring_to_dev(ring), "failed to allocate tx spare pages\n");
+		devm_kfree(ring_to_dev(ring), tx_spare);
+		return;
+	}
+
+	dma = dma_map_page(ring_to_dev(ring), page, 0,
+			   PAGE_SIZE << order, DMA_TO_DEVICE);
+	if (dma_mapping_error(ring_to_dev(ring), dma)) {
+		dev_warn(ring_to_dev(ring), "failed to map pages for tx spare\n");
+		put_page(page);
+		devm_kfree(ring_to_dev(ring), tx_spare);
+		return;
+	}
+
+	tx_spare->dma = dma;
+	tx_spare->buf = page_address(page);
+	tx_spare->len = PAGE_SIZE << order;
+	ring->tx_spare = tx_spare;
+}
+
+/* Use hns3_tx_spare_space() to make sure there is enough buffer
+ * before calling below function to allocate tx buffer.
+ */
+static void *hns3_tx_spare_alloc(struct hns3_enet_ring *ring,
+				 unsigned int size, dma_addr_t *dma,
+				 u32 *cb_len)
+{
+	struct hns3_tx_spare *tx_spare = ring->tx_spare;
+	u32 ntu = tx_spare->next_to_use;
+
+	size = ALIGN(size, dma_get_cache_alignment());
+	*cb_len = size;
+
+	/* Tx spare buffer wraps back here because the end of
+	 * freed tx buffer is not enough.
+	 */
+	if (ntu + size > tx_spare->len) {
+		*cb_len += (tx_spare->len - ntu);
+		ntu = 0;
+	}
+
+	tx_spare->next_to_use = ntu + size;
+	if (tx_spare->next_to_use == tx_spare->len)
+		tx_spare->next_to_use = 0;
+
+	*dma = tx_spare->dma + ntu;
+
+	return tx_spare->buf + ntu;
+}
+
+static void hns3_tx_spare_rollback(struct hns3_enet_ring *ring, u32 len)
+{
+	struct hns3_tx_spare *tx_spare = ring->tx_spare;
+
+	if (len > tx_spare->next_to_use) {
+		len -= tx_spare->next_to_use;
+		tx_spare->next_to_use = tx_spare->len - len;
+	} else {
+		tx_spare->next_to_use -= len;
+	}
+}
+
+static void hns3_tx_spare_reclaim_cb(struct hns3_enet_ring *ring,
+				     struct hns3_desc_cb *cb)
+{
+	struct hns3_tx_spare *tx_spare = ring->tx_spare;
+	u32 ntc = tx_spare->next_to_clean;
+	u32 len = cb->length;
+
+	tx_spare->next_to_clean += len;
+
+	if (tx_spare->next_to_clean >= tx_spare->len) {
+		tx_spare->next_to_clean -= tx_spare->len;
+
+		if (tx_spare->next_to_clean) {
+			ntc = 0;
+			len = tx_spare->next_to_clean;
 		}
 	}
+
+	/* This tx spare buffer is only really reclaimed after calling
+	 * hns3_tx_spare_update(), so it is still safe to use the info in
+	 * the tx buffer to do the dma sync or sg unmapping after
+	 * tx_spare->next_to_clean is moved forword.
+	 */
+	if (cb->type & (DESC_TYPE_BOUNCE_HEAD | DESC_TYPE_BOUNCE_ALL)) {
+		dma_addr_t dma = tx_spare->dma + ntc;
+
+		dma_sync_single_for_cpu(ring_to_dev(ring), dma, len,
+					DMA_TO_DEVICE);
+	} else {
+		struct sg_table *sgt = tx_spare->buf + ntc;
+
+		dma_unmap_sg(ring_to_dev(ring), sgt->sgl, sgt->orig_nents,
+			     DMA_TO_DEVICE);
+	}
 }
 
 static int hns3_set_tso(struct sk_buff *skb, u32 *paylen_fdop_ol4cs,
@@ -1159,40 +1623,14 @@ out_hw_tx_csum:
 	return 0;
 }
 
-static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
-			  unsigned int size, enum hns_desc_type type)
+static int hns3_fill_desc(struct hns3_enet_ring *ring, dma_addr_t dma,
+			  unsigned int size)
 {
 #define HNS3_LIKELY_BD_NUM	1
 
-	struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use];
 	struct hns3_desc *desc = &ring->desc[ring->next_to_use];
-	struct device *dev = ring_to_dev(ring);
-	skb_frag_t *frag;
 	unsigned int frag_buf_num;
 	int k, sizeoflast;
-	dma_addr_t dma;
-
-	if (type == DESC_TYPE_FRAGLIST_SKB ||
-	    type == DESC_TYPE_SKB) {
-		struct sk_buff *skb = (struct sk_buff *)priv;
-
-		dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE);
-	} else {
-		frag = (skb_frag_t *)priv;
-		dma = skb_frag_dma_map(dev, frag, 0, size, DMA_TO_DEVICE);
-	}
-
-	if (unlikely(dma_mapping_error(dev, dma))) {
-		u64_stats_update_begin(&ring->syncp);
-		ring->stats.sw_err_cnt++;
-		u64_stats_update_end(&ring->syncp);
-		return -ENOMEM;
-	}
-
-	desc_cb->priv = priv;
-	desc_cb->length = size;
-	desc_cb->dma = dma;
-	desc_cb->type = type;
 
 	if (likely(size <= HNS3_MAX_BD_SIZE)) {
 		desc->addr = cpu_to_le64(dma);
@@ -1228,6 +1666,52 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 	return frag_buf_num;
 }
 
+static int hns3_map_and_fill_desc(struct hns3_enet_ring *ring, void *priv,
+				  unsigned int type)
+{
+	struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use];
+	struct device *dev = ring_to_dev(ring);
+	unsigned int size;
+	dma_addr_t dma;
+
+	if (type & (DESC_TYPE_FRAGLIST_SKB | DESC_TYPE_SKB)) {
+		struct sk_buff *skb = (struct sk_buff *)priv;
+
+		size = skb_headlen(skb);
+		if (!size)
+			return 0;
+
+		dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE);
+	} else if (type & DESC_TYPE_BOUNCE_HEAD) {
+		/* Head data has been filled in hns3_handle_tx_bounce(),
+		 * just return 0 here.
+		 */
+		return 0;
+	} else {
+		skb_frag_t *frag = (skb_frag_t *)priv;
+
+		size = skb_frag_size(frag);
+		if (!size)
+			return 0;
+
+		dma = skb_frag_dma_map(dev, frag, 0, size, DMA_TO_DEVICE);
+	}
+
+	if (unlikely(dma_mapping_error(dev, dma))) {
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.sw_err_cnt++;
+		u64_stats_update_end(&ring->syncp);
+		return -ENOMEM;
+	}
+
+	desc_cb->priv = priv;
+	desc_cb->length = size;
+	desc_cb->dma = dma;
+	desc_cb->type = type;
+
+	return hns3_fill_desc(ring, dma, size);
+}
+
 static unsigned int hns3_skb_bd_num(struct sk_buff *skb, unsigned int *bd_size,
 				    unsigned int bd_num)
 {
@@ -1451,6 +1935,7 @@ static void hns3_clear_desc(struct hns3_enet_ring *ring, int next_to_use_orig)
 
 	for (i = 0; i < ring->desc_num; i++) {
 		struct hns3_desc *desc = &ring->desc[ring->next_to_use];
+		struct hns3_desc_cb *desc_cb;
 
 		memset(desc, 0, sizeof(*desc));
 
@@ -1461,52 +1946,44 @@ static void hns3_clear_desc(struct hns3_enet_ring *ring, int next_to_use_orig)
 		/* rollback one */
 		ring_ptr_move_bw(ring, next_to_use);
 
-		if (!ring->desc_cb[ring->next_to_use].dma)
+		desc_cb = &ring->desc_cb[ring->next_to_use];
+
+		if (!desc_cb->dma)
 			continue;
 
 		/* unmap the descriptor dma address */
-		if (ring->desc_cb[ring->next_to_use].type == DESC_TYPE_SKB ||
-		    ring->desc_cb[ring->next_to_use].type ==
-		    DESC_TYPE_FRAGLIST_SKB)
-			dma_unmap_single(dev,
-					 ring->desc_cb[ring->next_to_use].dma,
-					ring->desc_cb[ring->next_to_use].length,
-					DMA_TO_DEVICE);
-		else if (ring->desc_cb[ring->next_to_use].length)
-			dma_unmap_page(dev,
-				       ring->desc_cb[ring->next_to_use].dma,
-				       ring->desc_cb[ring->next_to_use].length,
+		if (desc_cb->type & (DESC_TYPE_SKB | DESC_TYPE_FRAGLIST_SKB))
+			dma_unmap_single(dev, desc_cb->dma, desc_cb->length,
+					 DMA_TO_DEVICE);
+		else if (desc_cb->type &
+			 (DESC_TYPE_BOUNCE_HEAD | DESC_TYPE_BOUNCE_ALL))
+			hns3_tx_spare_rollback(ring, desc_cb->length);
+		else if (desc_cb->length)
+			dma_unmap_page(dev, desc_cb->dma, desc_cb->length,
 				       DMA_TO_DEVICE);
 
-		ring->desc_cb[ring->next_to_use].length = 0;
-		ring->desc_cb[ring->next_to_use].dma = 0;
-		ring->desc_cb[ring->next_to_use].type = DESC_TYPE_UNKNOWN;
+		desc_cb->length = 0;
+		desc_cb->dma = 0;
+		desc_cb->type = DESC_TYPE_UNKNOWN;
 	}
 }
 
 static int hns3_fill_skb_to_desc(struct hns3_enet_ring *ring,
-				 struct sk_buff *skb, enum hns_desc_type type)
+				 struct sk_buff *skb, unsigned int type)
 {
-	unsigned int size = skb_headlen(skb);
 	struct sk_buff *frag_skb;
 	int i, ret, bd_num = 0;
 
-	if (size) {
-		ret = hns3_fill_desc(ring, skb, size, type);
-		if (unlikely(ret < 0))
-			return ret;
+	ret = hns3_map_and_fill_desc(ring, skb, type);
+	if (unlikely(ret < 0))
+		return ret;
 
-		bd_num += ret;
-	}
+	bd_num += ret;
 
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
-		size = skb_frag_size(frag);
-		if (!size)
-			continue;
-
-		ret = hns3_fill_desc(ring, frag, size, DESC_TYPE_PAGE);
+		ret = hns3_map_and_fill_desc(ring, frag, DESC_TYPE_PAGE);
 		if (unlikely(ret < 0))
 			return ret;
 
@@ -1546,6 +2023,153 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num,
 	WRITE_ONCE(ring->last_to_use, ring->next_to_use);
 }
 
+static void hns3_tsyn(struct net_device *netdev, struct sk_buff *skb,
+		      struct hns3_desc *desc)
+{
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+
+	if (!(h->ae_algo->ops->set_tx_hwts_info &&
+	      h->ae_algo->ops->set_tx_hwts_info(h, skb)))
+		return;
+
+	desc->tx.bdtp_fe_sc_vld_ra_ri |= cpu_to_le16(BIT(HNS3_TXD_TSYN_B));
+}
+
+static int hns3_handle_tx_bounce(struct hns3_enet_ring *ring,
+				 struct sk_buff *skb)
+{
+	struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use];
+	unsigned int type = DESC_TYPE_BOUNCE_HEAD;
+	unsigned int size = skb_headlen(skb);
+	dma_addr_t dma;
+	int bd_num = 0;
+	u32 cb_len;
+	void *buf;
+	int ret;
+
+	if (skb->len <= ring->tx_copybreak) {
+		size = skb->len;
+		type = DESC_TYPE_BOUNCE_ALL;
+	}
+
+	/* hns3_can_use_tx_bounce() is called to ensure the below
+	 * function can always return the tx buffer.
+	 */
+	buf = hns3_tx_spare_alloc(ring, size, &dma, &cb_len);
+
+	ret = skb_copy_bits(skb, 0, buf, size);
+	if (unlikely(ret < 0)) {
+		hns3_tx_spare_rollback(ring, cb_len);
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.copy_bits_err++;
+		u64_stats_update_end(&ring->syncp);
+		return ret;
+	}
+
+	desc_cb->priv = skb;
+	desc_cb->length = cb_len;
+	desc_cb->dma = dma;
+	desc_cb->type = type;
+
+	bd_num += hns3_fill_desc(ring, dma, size);
+
+	if (type == DESC_TYPE_BOUNCE_HEAD) {
+		ret = hns3_fill_skb_to_desc(ring, skb,
+					    DESC_TYPE_BOUNCE_HEAD);
+		if (unlikely(ret < 0))
+			return ret;
+
+		bd_num += ret;
+	}
+
+	dma_sync_single_for_device(ring_to_dev(ring), dma, size,
+				   DMA_TO_DEVICE);
+
+	u64_stats_update_begin(&ring->syncp);
+	ring->stats.tx_bounce++;
+	u64_stats_update_end(&ring->syncp);
+	return bd_num;
+}
+
+static int hns3_handle_tx_sgl(struct hns3_enet_ring *ring,
+			      struct sk_buff *skb)
+{
+	struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use];
+	u32 nfrag = skb_shinfo(skb)->nr_frags + 1;
+	struct sg_table *sgt;
+	int i, bd_num = 0;
+	dma_addr_t dma;
+	u32 cb_len;
+	int nents;
+
+	if (skb_has_frag_list(skb))
+		nfrag = HNS3_MAX_TSO_BD_NUM;
+
+	/* hns3_can_use_tx_sgl() is called to ensure the below
+	 * function can always return the tx buffer.
+	 */
+	sgt = hns3_tx_spare_alloc(ring, HNS3_SGL_SIZE(nfrag),
+				  &dma, &cb_len);
+
+	/* scatterlist follows by the sg table */
+	sgt->sgl = (struct scatterlist *)(sgt + 1);
+	sg_init_table(sgt->sgl, nfrag);
+	nents = skb_to_sgvec(skb, sgt->sgl, 0, skb->len);
+	if (unlikely(nents < 0)) {
+		hns3_tx_spare_rollback(ring, cb_len);
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.skb2sgl_err++;
+		u64_stats_update_end(&ring->syncp);
+		return -ENOMEM;
+	}
+
+	sgt->orig_nents = nents;
+	sgt->nents = dma_map_sg(ring_to_dev(ring), sgt->sgl, sgt->orig_nents,
+				DMA_TO_DEVICE);
+	if (unlikely(!sgt->nents)) {
+		hns3_tx_spare_rollback(ring, cb_len);
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.map_sg_err++;
+		u64_stats_update_end(&ring->syncp);
+		return -ENOMEM;
+	}
+
+	desc_cb->priv = skb;
+	desc_cb->length = cb_len;
+	desc_cb->dma = dma;
+	desc_cb->type = DESC_TYPE_SGL_SKB;
+
+	for (i = 0; i < sgt->nents; i++)
+		bd_num += hns3_fill_desc(ring, sg_dma_address(sgt->sgl + i),
+					 sg_dma_len(sgt->sgl + i));
+
+	u64_stats_update_begin(&ring->syncp);
+	ring->stats.tx_sgl++;
+	u64_stats_update_end(&ring->syncp);
+
+	return bd_num;
+}
+
+static int hns3_handle_desc_filling(struct hns3_enet_ring *ring,
+				    struct sk_buff *skb)
+{
+	u32 space;
+
+	if (!ring->tx_spare)
+		goto out;
+
+	space = hns3_tx_spare_space(ring);
+
+	if (hns3_can_use_tx_sgl(ring, skb, space))
+		return hns3_handle_tx_sgl(ring, skb);
+
+	if (hns3_can_use_tx_bounce(ring, skb, space))
+		return hns3_handle_tx_bounce(ring, skb);
+
+out:
+	return hns3_fill_skb_to_desc(ring, skb, DESC_TYPE_SKB);
+}
+
 netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
@@ -1592,16 +2216,22 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 	 * zero, which is unlikely, and 'ret > 0' means how many tx desc
 	 * need to be notified to the hw.
 	 */
-	ret = hns3_fill_skb_to_desc(ring, skb, DESC_TYPE_SKB);
+	ret = hns3_handle_desc_filling(ring, skb);
 	if (unlikely(ret <= 0))
 		goto fill_err;
 
 	pre_ntu = ring->next_to_use ? (ring->next_to_use - 1) :
 					(ring->desc_num - 1);
+
+	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
+		hns3_tsyn(netdev, skb, &ring->desc[pre_ntu]);
+
 	ring->desc[pre_ntu].tx.bdtp_fe_sc_vld_ra_ri |=
 				cpu_to_le16(BIT(HNS3_TXD_FE_B));
 	trace_hns3_tx_desc(ring, pre_ntu);
 
+	skb_tx_timestamp(skb);
+
 	/* Complete translate all packets */
 	dev_queue = netdev_get_tx_queue(netdev, ring->queue_index);
 	doorbell = __netdev_tx_sent_queue(dev_queue, desc_cb->send_bytes,
@@ -1705,6 +2335,14 @@ static int hns3_nic_set_features(struct net_device *netdev,
 		return -EINVAL;
 	}
 
+	if ((changed & NETIF_F_HW_VLAN_CTAG_FILTER) &&
+	    h->ae_algo->ops->enable_vlan_filter) {
+		enable = !!(features & NETIF_F_HW_VLAN_CTAG_FILTER);
+		ret = h->ae_algo->ops->enable_vlan_filter(h, enable);
+		if (ret)
+			return ret;
+	}
+
 	netdev->features = features;
 	return 0;
 }
@@ -1780,6 +2418,9 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 			tx_drop += ring->stats.tx_tso_err;
 			tx_drop += ring->stats.over_max_recursion;
 			tx_drop += ring->stats.hw_limitation;
+			tx_drop += ring->stats.copy_bits_err;
+			tx_drop += ring->stats.skb2sgl_err;
+			tx_drop += ring->stats.map_sg_err;
 			tx_errors += ring->stats.sw_err_cnt;
 			tx_errors += ring->stats.tx_vlan_err;
 			tx_errors += ring->stats.tx_l4_proto_err;
@@ -1787,6 +2428,9 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 			tx_errors += ring->stats.tx_tso_err;
 			tx_errors += ring->stats.over_max_recursion;
 			tx_errors += ring->stats.hw_limitation;
+			tx_errors += ring->stats.copy_bits_err;
+			tx_errors += ring->stats.skb2sgl_err;
+			tx_errors += ring->stats.map_sg_err;
 		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 
 		/* fetch the rx stats */
@@ -2550,6 +3194,9 @@ static void hns3_set_default_feature(struct net_device *netdev)
 		netdev->hw_features |= NETIF_F_HW_TC;
 		netdev->features |= NETIF_F_HW_TC;
 	}
+
+	if (test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps))
+		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 }
 
 static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
@@ -2577,7 +3224,8 @@ static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
 static void hns3_free_buffer(struct hns3_enet_ring *ring,
 			     struct hns3_desc_cb *cb, int budget)
 {
-	if (cb->type == DESC_TYPE_SKB)
+	if (cb->type & (DESC_TYPE_SKB | DESC_TYPE_BOUNCE_HEAD |
+			DESC_TYPE_BOUNCE_ALL | DESC_TYPE_SGL_SKB))
 		napi_consume_skb(cb->priv, budget);
 	else if (!HNAE3_IS_TX_RING(ring) && cb->pagecnt_bias)
 		__page_frag_cache_drain(cb->priv, cb->pagecnt_bias);
@@ -2598,12 +3246,15 @@ static int hns3_map_buffer(struct hns3_enet_ring *ring, struct hns3_desc_cb *cb)
 static void hns3_unmap_buffer(struct hns3_enet_ring *ring,
 			      struct hns3_desc_cb *cb)
 {
-	if (cb->type == DESC_TYPE_SKB || cb->type == DESC_TYPE_FRAGLIST_SKB)
+	if (cb->type & (DESC_TYPE_SKB | DESC_TYPE_FRAGLIST_SKB))
 		dma_unmap_single(ring_to_dev(ring), cb->dma, cb->length,
 				 ring_to_dma_dir(ring));
-	else if (cb->length)
+	else if ((cb->type & DESC_TYPE_PAGE) && cb->length)
 		dma_unmap_page(ring_to_dev(ring), cb->dma, cb->length,
 			       ring_to_dma_dir(ring));
+	else if (cb->type & (DESC_TYPE_BOUNCE_ALL | DESC_TYPE_BOUNCE_HEAD |
+			     DESC_TYPE_SGL_SKB))
+		hns3_tx_spare_reclaim_cb(ring, cb);
 }
 
 static void hns3_buffer_detach(struct hns3_enet_ring *ring, int i)
@@ -2755,7 +3406,9 @@ static bool hns3_nic_reclaim_desc(struct hns3_enet_ring *ring,
 
 		desc_cb = &ring->desc_cb[ntc];
 
-		if (desc_cb->type == DESC_TYPE_SKB) {
+		if (desc_cb->type & (DESC_TYPE_SKB | DESC_TYPE_BOUNCE_ALL |
+				     DESC_TYPE_BOUNCE_HEAD |
+				     DESC_TYPE_SGL_SKB)) {
 			(*pkts)++;
 			(*bytes) += desc_cb->send_bytes;
 		}
@@ -2778,6 +3431,9 @@ static bool hns3_nic_reclaim_desc(struct hns3_enet_ring *ring,
 	 * ring_space called by hns3_nic_net_xmit.
 	 */
 	smp_store_release(&ring->next_to_clean, ntc);
+
+	hns3_tx_spare_update(ring);
+
 	return true;
 }
 
@@ -2869,7 +3525,7 @@ static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring,
 
 static bool hns3_can_reuse_page(struct hns3_desc_cb *cb)
 {
-	return (page_count(cb->priv) - cb->pagecnt_bias) == 1;
+	return page_count(cb->priv) == cb->pagecnt_bias;
 }
 
 static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
@@ -2877,40 +3533,74 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
 				struct hns3_desc_cb *desc_cb)
 {
 	struct hns3_desc *desc = &ring->desc[ring->next_to_clean];
+	u32 frag_offset = desc_cb->page_offset + pull_len;
 	int size = le16_to_cpu(desc->rx.size);
 	u32 truesize = hns3_buf_size(ring);
+	u32 frag_size = size - pull_len;
+	bool reused;
 
-	desc_cb->pagecnt_bias--;
-	skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len,
-			size - pull_len, truesize);
+	/* Avoid re-using remote or pfmem page */
+	if (unlikely(!dev_page_is_reusable(desc_cb->priv)))
+		goto out;
 
-	/* Avoid re-using remote and pfmemalloc pages, or the stack is still
-	 * using the page when page_offset rollback to zero, flag default
-	 * unreuse
+	reused = hns3_can_reuse_page(desc_cb);
+
+	/* Rx page can be reused when:
+	 * 1. Rx page is only owned by the driver when page_offset
+	 *    is zero, which means 0 @ truesize will be used by
+	 *    stack after skb_add_rx_frag() is called, and the rest
+	 *    of rx page can be reused by driver.
+	 * Or
+	 * 2. Rx page is only owned by the driver when page_offset
+	 *    is non-zero, which means page_offset @ truesize will
+	 *    be used by stack after skb_add_rx_frag() is called,
+	 *    and 0 @ truesize can be reused by driver.
 	 */
-	if (!dev_page_is_reusable(desc_cb->priv) ||
-	    (!desc_cb->page_offset && !hns3_can_reuse_page(desc_cb))) {
-		__page_frag_cache_drain(desc_cb->priv, desc_cb->pagecnt_bias);
-		return;
-	}
+	if ((!desc_cb->page_offset && reused) ||
+	    ((desc_cb->page_offset + truesize + truesize) <=
+	     hns3_page_size(ring) && desc_cb->page_offset)) {
+		desc_cb->page_offset += truesize;
+		desc_cb->reuse_flag = 1;
+	} else if (desc_cb->page_offset && reused) {
+		desc_cb->page_offset = 0;
+		desc_cb->reuse_flag = 1;
+	} else if (frag_size <= ring->rx_copybreak) {
+		void *frag = napi_alloc_frag(frag_size);
+
+		if (unlikely(!frag)) {
+			u64_stats_update_begin(&ring->syncp);
+			ring->stats.frag_alloc_err++;
+			u64_stats_update_end(&ring->syncp);
 
-	/* Move offset up to the next cache line */
-	desc_cb->page_offset += truesize;
+			hns3_rl_err(ring_to_netdev(ring),
+				    "failed to allocate rx frag\n");
+			goto out;
+		}
 
-	if (desc_cb->page_offset + truesize <= hns3_page_size(ring)) {
-		desc_cb->reuse_flag = 1;
-	} else if (hns3_can_reuse_page(desc_cb)) {
 		desc_cb->reuse_flag = 1;
-		desc_cb->page_offset = 0;
-	} else if (desc_cb->pagecnt_bias) {
-		__page_frag_cache_drain(desc_cb->priv, desc_cb->pagecnt_bias);
+		memcpy(frag, desc_cb->buf + frag_offset, frag_size);
+		skb_add_rx_frag(skb, i, virt_to_page(frag),
+				offset_in_page(frag), frag_size, frag_size);
+
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.frag_alloc++;
+		u64_stats_update_end(&ring->syncp);
 		return;
 	}
 
+out:
+	desc_cb->pagecnt_bias--;
+
 	if (unlikely(!desc_cb->pagecnt_bias)) {
 		page_ref_add(desc_cb->priv, USHRT_MAX);
 		desc_cb->pagecnt_bias = USHRT_MAX;
 	}
+
+	skb_add_rx_frag(skb, i, desc_cb->priv, frag_offset,
+			frag_size, truesize);
+
+	if (unlikely(!desc_cb->reuse_flag))
+		__page_frag_cache_drain(desc_cb->priv, desc_cb->pagecnt_bias);
 }
 
 static int hns3_gro_complete(struct sk_buff *skb, u32 l234info)
@@ -2971,51 +3661,31 @@ static int hns3_gro_complete(struct sk_buff *skb, u32 l234info)
 	return 0;
 }
 
-static void hns3_checksum_complete(struct hns3_enet_ring *ring,
-				   struct sk_buff *skb, u32 l234info)
+static bool hns3_checksum_complete(struct hns3_enet_ring *ring,
+				   struct sk_buff *skb, u32 ptype, u16 csum)
 {
-	u32 lo, hi;
+	if (ptype == HNS3_INVALID_PTYPE ||
+	    hns3_rx_ptype_tbl[ptype].ip_summed != CHECKSUM_COMPLETE)
+		return false;
 
 	u64_stats_update_begin(&ring->syncp);
 	ring->stats.csum_complete++;
 	u64_stats_update_end(&ring->syncp);
 	skb->ip_summed = CHECKSUM_COMPLETE;
-	lo = hnae3_get_field(l234info, HNS3_RXD_L2_CSUM_L_M,
-			     HNS3_RXD_L2_CSUM_L_S);
-	hi = hnae3_get_field(l234info, HNS3_RXD_L2_CSUM_H_M,
-			     HNS3_RXD_L2_CSUM_H_S);
-	skb->csum = csum_unfold((__force __sum16)(lo | hi << 8));
+	skb->csum = csum_unfold((__force __sum16)csum);
+
+	return true;
 }
 
-static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
-			     u32 l234info, u32 bd_base_info, u32 ol_info)
+static void hns3_rx_handle_csum(struct sk_buff *skb, u32 l234info,
+				u32 ol_info, u32 ptype)
 {
-	struct net_device *netdev = ring_to_netdev(ring);
 	int l3_type, l4_type;
 	int ol4_type;
 
-	skb->ip_summed = CHECKSUM_NONE;
-
-	skb_checksum_none_assert(skb);
-
-	if (!(netdev->features & NETIF_F_RXCSUM))
-		return;
-
-	if (l234info & BIT(HNS3_RXD_L2_CSUM_B)) {
-		hns3_checksum_complete(ring, skb, l234info);
-		return;
-	}
-
-	/* check if hardware has done checksum */
-	if (!(bd_base_info & BIT(HNS3_RXD_L3L4P_B)))
-		return;
-
-	if (unlikely(l234info & (BIT(HNS3_RXD_L3E_B) | BIT(HNS3_RXD_L4E_B) |
-				 BIT(HNS3_RXD_OL3E_B) |
-				 BIT(HNS3_RXD_OL4E_B)))) {
-		u64_stats_update_begin(&ring->syncp);
-		ring->stats.l3l4_csum_err++;
-		u64_stats_update_end(&ring->syncp);
+	if (ptype != HNS3_INVALID_PTYPE) {
+		skb->csum_level = hns3_rx_ptype_tbl[ptype].csum_level;
+		skb->ip_summed = hns3_rx_ptype_tbl[ptype].ip_summed;
 
 		return;
 	}
@@ -3045,6 +3715,45 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 	}
 }
 
+static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
+			     u32 l234info, u32 bd_base_info, u32 ol_info,
+			     u16 csum)
+{
+	struct net_device *netdev = ring_to_netdev(ring);
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	u32 ptype = HNS3_INVALID_PTYPE;
+
+	skb->ip_summed = CHECKSUM_NONE;
+
+	skb_checksum_none_assert(skb);
+
+	if (!(netdev->features & NETIF_F_RXCSUM))
+		return;
+
+	if (test_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state))
+		ptype = hnae3_get_field(ol_info, HNS3_RXD_PTYPE_M,
+					HNS3_RXD_PTYPE_S);
+
+	if (hns3_checksum_complete(ring, skb, ptype, csum))
+		return;
+
+	/* check if hardware has done checksum */
+	if (!(bd_base_info & BIT(HNS3_RXD_L3L4P_B)))
+		return;
+
+	if (unlikely(l234info & (BIT(HNS3_RXD_L3E_B) | BIT(HNS3_RXD_L4E_B) |
+				 BIT(HNS3_RXD_OL3E_B) |
+				 BIT(HNS3_RXD_OL4E_B)))) {
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.l3l4_csum_err++;
+		u64_stats_update_end(&ring->syncp);
+
+		return;
+	}
+
+	hns3_rx_handle_csum(skb, l234info, ol_info, ptype);
+}
+
 static void hns3_rx_skb(struct hns3_enet_ring *ring, struct sk_buff *skb)
 {
 	if (skb_has_frag_list(skb))
@@ -3226,8 +3935,10 @@ static int hns3_add_frag(struct hns3_enet_ring *ring)
 
 static int hns3_set_gro_and_checksum(struct hns3_enet_ring *ring,
 				     struct sk_buff *skb, u32 l234info,
-				     u32 bd_base_info, u32 ol_info)
+				     u32 bd_base_info, u32 ol_info, u16 csum)
 {
+	struct net_device *netdev = ring_to_netdev(ring);
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	u32 l3_type;
 
 	skb_shinfo(skb)->gso_size = hnae3_get_field(bd_base_info,
@@ -3235,7 +3946,8 @@ static int hns3_set_gro_and_checksum(struct hns3_enet_ring *ring,
 						    HNS3_RXD_GRO_SIZE_S);
 	/* if there is no HW GRO, do not set gro params */
 	if (!skb_shinfo(skb)->gso_size) {
-		hns3_rx_checksum(ring, skb, l234info, bd_base_info, ol_info);
+		hns3_rx_checksum(ring, skb, l234info, bd_base_info, ol_info,
+				 csum);
 		return 0;
 	}
 
@@ -3243,7 +3955,16 @@ static int hns3_set_gro_and_checksum(struct hns3_enet_ring *ring,
 						  HNS3_RXD_GRO_COUNT_M,
 						  HNS3_RXD_GRO_COUNT_S);
 
-	l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M, HNS3_RXD_L3ID_S);
+	if (test_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state)) {
+		u32 ptype = hnae3_get_field(ol_info, HNS3_RXD_PTYPE_M,
+					    HNS3_RXD_PTYPE_S);
+
+		l3_type = hns3_rx_ptype_tbl[ptype].l3_type;
+	} else {
+		l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M,
+					  HNS3_RXD_L3ID_S);
+	}
+
 	if (l3_type == HNS3_L3_TYPE_IPV4)
 		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
 	else if (l3_type == HNS3_L3_TYPE_IPV6)
@@ -3276,6 +3997,7 @@ static int hns3_handle_bdinfo(struct hns3_enet_ring *ring, struct sk_buff *skb)
 	struct hns3_desc *desc;
 	unsigned int len;
 	int pre_ntc, ret;
+	u16 csum;
 
 	/* bdinfo handled below is only valid on the last BD of the
 	 * current packet, and ring->next_to_clean indicates the first
@@ -3287,6 +4009,16 @@ static int hns3_handle_bdinfo(struct hns3_enet_ring *ring, struct sk_buff *skb)
 	bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
 	l234info = le32_to_cpu(desc->rx.l234_info);
 	ol_info = le32_to_cpu(desc->rx.ol_info);
+	csum = le16_to_cpu(desc->csum);
+
+	if (unlikely(bd_base_info & BIT(HNS3_RXD_TS_VLD_B))) {
+		struct hnae3_handle *h = hns3_get_handle(netdev);
+		u32 nsec = le32_to_cpu(desc->ts_nsec);
+		u32 sec = le32_to_cpu(desc->ts_sec);
+
+		if (h->ae_algo->ops->get_rx_hwts)
+			h->ae_algo->ops->get_rx_hwts(h, skb, nsec, sec);
+	}
 
 	/* Based on hw strategy, the tag offloaded will be stored at
 	 * ot_vlan_tag in two layer tag case, and stored at vlan_tag
@@ -3319,7 +4051,7 @@ static int hns3_handle_bdinfo(struct hns3_enet_ring *ring, struct sk_buff *skb)
 
 	/* This is needed in order to enable forwarding support */
 	ret = hns3_set_gro_and_checksum(ring, skb, l234info,
-					bd_base_info, ol_info);
+					bd_base_info, ol_info, csum);
 	if (unlikely(ret)) {
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.rx_err_cnt++;
@@ -3458,139 +4190,30 @@ out:
 	return recv_pkts;
 }
 
-static bool hns3_get_new_flow_lvl(struct hns3_enet_ring_group *ring_group)
-{
-#define HNS3_RX_LOW_BYTE_RATE 10000
-#define HNS3_RX_MID_BYTE_RATE 20000
-#define HNS3_RX_ULTRA_PACKET_RATE 40
-
-	enum hns3_flow_level_range new_flow_level;
-	struct hns3_enet_tqp_vector *tqp_vector;
-	int packets_per_msecs, bytes_per_msecs;
-	u32 time_passed_ms;
-
-	tqp_vector = ring_group->ring->tqp_vector;
-	time_passed_ms =
-		jiffies_to_msecs(jiffies - tqp_vector->last_jiffies);
-	if (!time_passed_ms)
-		return false;
-
-	do_div(ring_group->total_packets, time_passed_ms);
-	packets_per_msecs = ring_group->total_packets;
-
-	do_div(ring_group->total_bytes, time_passed_ms);
-	bytes_per_msecs = ring_group->total_bytes;
-
-	new_flow_level = ring_group->coal.flow_level;
-
-	/* Simple throttlerate management
-	 * 0-10MB/s   lower     (50000 ints/s)
-	 * 10-20MB/s   middle    (20000 ints/s)
-	 * 20-1249MB/s high      (18000 ints/s)
-	 * > 40000pps  ultra     (8000 ints/s)
-	 */
-	switch (new_flow_level) {
-	case HNS3_FLOW_LOW:
-		if (bytes_per_msecs > HNS3_RX_LOW_BYTE_RATE)
-			new_flow_level = HNS3_FLOW_MID;
-		break;
-	case HNS3_FLOW_MID:
-		if (bytes_per_msecs > HNS3_RX_MID_BYTE_RATE)
-			new_flow_level = HNS3_FLOW_HIGH;
-		else if (bytes_per_msecs <= HNS3_RX_LOW_BYTE_RATE)
-			new_flow_level = HNS3_FLOW_LOW;
-		break;
-	case HNS3_FLOW_HIGH:
-	case HNS3_FLOW_ULTRA:
-	default:
-		if (bytes_per_msecs <= HNS3_RX_MID_BYTE_RATE)
-			new_flow_level = HNS3_FLOW_MID;
-		break;
-	}
-
-	if (packets_per_msecs > HNS3_RX_ULTRA_PACKET_RATE &&
-	    &tqp_vector->rx_group == ring_group)
-		new_flow_level = HNS3_FLOW_ULTRA;
-
-	ring_group->total_bytes = 0;
-	ring_group->total_packets = 0;
-	ring_group->coal.flow_level = new_flow_level;
-
-	return true;
-}
-
-static bool hns3_get_new_int_gl(struct hns3_enet_ring_group *ring_group)
+static void hns3_update_rx_int_coalesce(struct hns3_enet_tqp_vector *tqp_vector)
 {
-	struct hns3_enet_tqp_vector *tqp_vector;
-	u16 new_int_gl;
-
-	if (!ring_group->ring)
-		return false;
-
-	tqp_vector = ring_group->ring->tqp_vector;
-	if (!tqp_vector->last_jiffies)
-		return false;
-
-	if (ring_group->total_packets == 0) {
-		ring_group->coal.int_gl = HNS3_INT_GL_50K;
-		ring_group->coal.flow_level = HNS3_FLOW_LOW;
-		return true;
-	}
-
-	if (!hns3_get_new_flow_lvl(ring_group))
-		return false;
+	struct hns3_enet_ring_group *rx_group = &tqp_vector->rx_group;
+	struct dim_sample sample = {};
 
-	new_int_gl = ring_group->coal.int_gl;
-	switch (ring_group->coal.flow_level) {
-	case HNS3_FLOW_LOW:
-		new_int_gl = HNS3_INT_GL_50K;
-		break;
-	case HNS3_FLOW_MID:
-		new_int_gl = HNS3_INT_GL_20K;
-		break;
-	case HNS3_FLOW_HIGH:
-		new_int_gl = HNS3_INT_GL_18K;
-		break;
-	case HNS3_FLOW_ULTRA:
-		new_int_gl = HNS3_INT_GL_8K;
-		break;
-	default:
-		break;
-	}
+	if (!rx_group->coal.adapt_enable)
+		return;
 
-	if (new_int_gl != ring_group->coal.int_gl) {
-		ring_group->coal.int_gl = new_int_gl;
-		return true;
-	}
-	return false;
+	dim_update_sample(tqp_vector->event_cnt, rx_group->total_packets,
+			  rx_group->total_bytes, &sample);
+	net_dim(&rx_group->dim, sample);
 }
 
-static void hns3_update_new_int_gl(struct hns3_enet_tqp_vector *tqp_vector)
+static void hns3_update_tx_int_coalesce(struct hns3_enet_tqp_vector *tqp_vector)
 {
-	struct hns3_enet_ring_group *rx_group = &tqp_vector->rx_group;
 	struct hns3_enet_ring_group *tx_group = &tqp_vector->tx_group;
-	bool rx_update, tx_update;
+	struct dim_sample sample = {};
 
-	/* update param every 1000ms */
-	if (time_before(jiffies,
-			tqp_vector->last_jiffies + msecs_to_jiffies(1000)))
+	if (!tx_group->coal.adapt_enable)
 		return;
 
-	if (rx_group->coal.adapt_enable) {
-		rx_update = hns3_get_new_int_gl(rx_group);
-		if (rx_update)
-			hns3_set_vector_coalesce_rx_gl(tqp_vector,
-						       rx_group->coal.int_gl);
-	}
-
-	if (tx_group->coal.adapt_enable) {
-		tx_update = hns3_get_new_int_gl(tx_group);
-		if (tx_update)
-			hns3_set_vector_coalesce_tx_gl(tqp_vector,
-						       tx_group->coal.int_gl);
-	}
-
-	tqp_vector->last_jiffies = jiffies;
+	dim_update_sample(tqp_vector->event_cnt, tx_group->total_packets,
+			  tx_group->total_bytes, &sample);
+	net_dim(&tx_group->dim, sample);
 }
 
 static int hns3_nic_common_poll(struct napi_struct *napi, int budget)
@@ -3635,7 +4258,9 @@ static int hns3_nic_common_poll(struct napi_struct *napi, int budget)
 
 	if (napi_complete(napi) &&
 	    likely(!test_bit(HNS3_NIC_STATE_DOWN, &priv->state))) {
-		hns3_update_new_int_gl(tqp_vector);
+		hns3_update_rx_int_coalesce(tqp_vector);
+		hns3_update_tx_int_coalesce(tqp_vector);
+
 		hns3_mask_vector_irq(tqp_vector, 1);
 	}
 
@@ -3766,6 +4391,54 @@ static void hns3_nic_set_cpumask(struct hns3_nic_priv *priv)
 	}
 }
 
+static void hns3_rx_dim_work(struct work_struct *work)
+{
+	struct dim *dim = container_of(work, struct dim, work);
+	struct hns3_enet_ring_group *group = container_of(dim,
+		struct hns3_enet_ring_group, dim);
+	struct hns3_enet_tqp_vector *tqp_vector = group->ring->tqp_vector;
+	struct dim_cq_moder cur_moder =
+		net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
+
+	hns3_set_vector_coalesce_rx_gl(group->ring->tqp_vector, cur_moder.usec);
+	tqp_vector->rx_group.coal.int_gl = cur_moder.usec;
+
+	if (cur_moder.pkts < tqp_vector->rx_group.coal.int_ql_max) {
+		hns3_set_vector_coalesce_rx_ql(tqp_vector, cur_moder.pkts);
+		tqp_vector->rx_group.coal.int_ql = cur_moder.pkts;
+	}
+
+	dim->state = DIM_START_MEASURE;
+}
+
+static void hns3_tx_dim_work(struct work_struct *work)
+{
+	struct dim *dim = container_of(work, struct dim, work);
+	struct hns3_enet_ring_group *group = container_of(dim,
+		struct hns3_enet_ring_group, dim);
+	struct hns3_enet_tqp_vector *tqp_vector = group->ring->tqp_vector;
+	struct dim_cq_moder cur_moder =
+		net_dim_get_tx_moderation(dim->mode, dim->profile_ix);
+
+	hns3_set_vector_coalesce_tx_gl(tqp_vector, cur_moder.usec);
+	tqp_vector->tx_group.coal.int_gl = cur_moder.usec;
+
+	if (cur_moder.pkts < tqp_vector->tx_group.coal.int_ql_max) {
+		hns3_set_vector_coalesce_tx_ql(tqp_vector, cur_moder.pkts);
+		tqp_vector->tx_group.coal.int_ql = cur_moder.pkts;
+	}
+
+	dim->state = DIM_START_MEASURE;
+}
+
+static void hns3_nic_init_dim(struct hns3_enet_tqp_vector *tqp_vector)
+{
+	INIT_WORK(&tqp_vector->rx_group.dim.work, hns3_rx_dim_work);
+	tqp_vector->rx_group.dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+	INIT_WORK(&tqp_vector->tx_group.dim.work, hns3_tx_dim_work);
+	tqp_vector->tx_group.dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+}
+
 static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv)
 {
 	struct hnae3_handle *h = priv->ae_handle;
@@ -3779,6 +4452,7 @@ static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv)
 		tqp_vector = &priv->tqp_vector[i];
 		hns3_vector_coalesce_init_hw(tqp_vector, priv);
 		tqp_vector->num_tqps = 0;
+		hns3_nic_init_dim(tqp_vector);
 	}
 
 	for (i = 0; i < h->kinfo.num_tqps; i++) {
@@ -3974,10 +4648,13 @@ static void hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
 		ring = &priv->ring[q->tqp_index];
 		desc_num = priv->ae_handle->kinfo.num_tx_desc;
 		ring->queue_index = q->tqp_index;
+		ring->tx_copybreak = priv->tx_copybreak;
+		ring->last_to_use = 0;
 	} else {
 		ring = &priv->ring[q->tqp_index + queue_num];
 		desc_num = priv->ae_handle->kinfo.num_rx_desc;
 		ring->queue_index = q->tqp_index;
+		ring->rx_copybreak = priv->rx_copybreak;
 	}
 
 	hnae3_set_bit(ring->flag, HNAE3_RING_TYPE_B, ring_type);
@@ -3991,7 +4668,6 @@ static void hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
 	ring->desc_num = desc_num;
 	ring->next_to_use = 0;
 	ring->next_to_clean = 0;
-	ring->last_to_use = 0;
 }
 
 static void hns3_queue_to_ring(struct hnae3_queue *tqp,
@@ -4051,6 +4727,8 @@ static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring)
 		ret = hns3_alloc_ring_buffers(ring);
 		if (ret)
 			goto out_with_desc;
+	} else {
+		hns3_init_tx_spare_buffer(ring);
 	}
 
 	return 0;
@@ -4073,9 +4751,18 @@ void hns3_fini_ring(struct hns3_enet_ring *ring)
 	ring->next_to_use = 0;
 	ring->last_to_use = 0;
 	ring->pending_buf = 0;
-	if (ring->skb) {
+	if (!HNAE3_IS_TX_RING(ring) && ring->skb) {
 		dev_kfree_skb_any(ring->skb);
 		ring->skb = NULL;
+	} else if (HNAE3_IS_TX_RING(ring) && ring->tx_spare) {
+		struct hns3_tx_spare *tx_spare = ring->tx_spare;
+
+		dma_unmap_page(ring_to_dev(ring), tx_spare->dma, tx_spare->len,
+			       DMA_TO_DEVICE);
+		free_pages((unsigned long)tx_spare->buf,
+			   get_order(tx_spare->len));
+		devm_kfree(ring_to_dev(ring), tx_spare);
+		ring->tx_spare = NULL;
 	}
 }
 
@@ -4358,13 +5045,21 @@ static int hns3_client_init(struct hnae3_handle *handle)
 
 	hns3_dcbnl_setup(handle);
 
-	hns3_dbg_init(handle);
+	ret = hns3_dbg_init(handle);
+	if (ret) {
+		dev_err(priv->dev, "failed to init debugfs, ret = %d\n",
+			ret);
+		goto out_client_start;
+	}
 
 	netdev->max_mtu = HNS3_MAX_MTU(ae_dev->dev_specs.max_frm_size);
 
 	if (test_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps))
 		set_bit(HNS3_NIC_STATE_HW_TX_CSUM_ENABLE, &priv->state);
 
+	if (hnae3_ae_dev_rxd_adv_layout_supported(ae_dev))
+		set_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state);
+
 	set_bit(HNS3_NIC_STATE_INITED, &priv->state);
 
 	if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index daa04aeb0942..15af3d93857b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -4,6 +4,7 @@
 #ifndef __HNS3_ENET_H
 #define __HNS3_ENET_H
 
+#include <linux/dim.h>
 #include <linux/if_vlan.h>
 
 #include "hnae3.h"
@@ -19,6 +20,7 @@ enum hns3_nic_state {
 	HNS3_NIC_STATE_SERVICE_SCHED,
 	HNS3_NIC_STATE2_RESET_REQUESTED,
 	HNS3_NIC_STATE_HW_TX_CSUM_ENABLE,
+	HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE,
 	HNS3_NIC_STATE_MAX
 };
 
@@ -82,12 +84,6 @@ enum hns3_nic_state {
 #define HNS3_RXD_STRP_TAGP_S			13
 #define HNS3_RXD_STRP_TAGP_M			(0x3 << HNS3_RXD_STRP_TAGP_S)
 
-#define HNS3_RXD_L2_CSUM_B			15
-#define HNS3_RXD_L2_CSUM_L_S			4
-#define HNS3_RXD_L2_CSUM_L_M			(0xff << HNS3_RXD_L2_CSUM_L_S)
-#define HNS3_RXD_L2_CSUM_H_S			24
-#define HNS3_RXD_L2_CSUM_H_M			(0xff << HNS3_RXD_L2_CSUM_H_S)
-
 #define HNS3_RXD_L2E_B				16
 #define HNS3_RXD_L3E_B				17
 #define HNS3_RXD_L4E_B				18
@@ -114,6 +110,9 @@ enum hns3_nic_state {
 #define HNS3_RXD_FBLI_S				14
 #define HNS3_RXD_FBLI_M				(0x3 << HNS3_RXD_FBLI_S)
 
+#define HNS3_RXD_PTYPE_S			4
+#define HNS3_RXD_PTYPE_M			GENMASK(11, 4)
+
 #define HNS3_RXD_BDTYPE_S			0
 #define HNS3_RXD_BDTYPE_M			(0xf << HNS3_RXD_BDTYPE_S)
 #define HNS3_RXD_VLD_B				4
@@ -123,8 +122,9 @@ enum hns3_nic_state {
 #define HNS3_RXD_LUM_B				9
 #define HNS3_RXD_CRCP_B				10
 #define HNS3_RXD_L3L4P_B			11
-#define HNS3_RXD_TSIND_S			12
-#define HNS3_RXD_TSIND_M			(0x7 << HNS3_RXD_TSIND_S)
+#define HNS3_RXD_TSIDX_S			12
+#define HNS3_RXD_TSIDX_M			(0x3 << HNS3_RXD_TSIDX_S)
+#define HNS3_RXD_TS_VLD_B			14
 #define HNS3_RXD_LKBK_B				15
 #define HNS3_RXD_GRO_SIZE_S			16
 #define HNS3_RXD_GRO_SIZE_M			(0x3fff << HNS3_RXD_GRO_SIZE_S)
@@ -238,7 +238,14 @@ enum hns3_pkt_tun_type {
 
 /* hardware spec ring buffer format */
 struct __packed hns3_desc {
-	__le64 addr;
+	union {
+		__le64 addr;
+		__le16 csum;
+		struct {
+			__le32 ts_nsec;
+			__le32 ts_sec;
+		};
+	};
 	union {
 		struct {
 			__le16 vlan_tag;
@@ -292,6 +299,16 @@ struct __packed hns3_desc {
 	};
 };
 
+enum hns3_desc_type {
+	DESC_TYPE_UNKNOWN		= 0,
+	DESC_TYPE_SKB			= 1 << 0,
+	DESC_TYPE_FRAGLIST_SKB		= 1 << 1,
+	DESC_TYPE_PAGE			= 1 << 2,
+	DESC_TYPE_BOUNCE_ALL		= 1 << 3,
+	DESC_TYPE_BOUNCE_HEAD		= 1 << 4,
+	DESC_TYPE_SGL_SKB		= 1 << 5,
+};
+
 struct hns3_desc_cb {
 	dma_addr_t dma; /* dma address of this desc */
 	void *buf;      /* cpu addr for a desc */
@@ -366,6 +383,14 @@ enum hns3_pkt_ol4type {
 	HNS3_OL4_TYPE_UNKNOWN
 };
 
+struct hns3_rx_ptype {
+	u32 ptype:8;
+	u32 csum_level:2;
+	u32 ip_summed:2;
+	u32 l3_type:4;
+	u32 valid:1;
+};
+
 struct ring_stats {
 	u64 sw_err_cnt;
 	u64 seg_pkt_cnt;
@@ -383,6 +408,12 @@ struct ring_stats {
 			u64 tx_tso_err;
 			u64 over_max_recursion;
 			u64 hw_limitation;
+			u64 tx_bounce;
+			u64 tx_spare_full;
+			u64 copy_bits_err;
+			u64 tx_sgl;
+			u64 skb2sgl_err;
+			u64 map_sg_err;
 		};
 		struct {
 			u64 rx_pkts;
@@ -396,10 +427,22 @@ struct ring_stats {
 			u64 csum_complete;
 			u64 rx_multicast;
 			u64 non_reuse_pg;
+			u64 frag_alloc_err;
+			u64 frag_alloc;
 		};
+		__le16 csum;
 	};
 };
 
+struct hns3_tx_spare {
+	dma_addr_t dma;
+	void *buf;
+	u32 next_to_use;
+	u32 next_to_clean;
+	u32 last_to_clean;
+	u32 len;
+};
+
 struct hns3_enet_ring {
 	struct hns3_desc *desc; /* dma map address space */
 	struct hns3_desc_cb *desc_cb;
@@ -422,18 +465,29 @@ struct hns3_enet_ring {
 	 * next_to_use
 	 */
 	int next_to_clean;
-	union {
-		int last_to_use;	/* last idx used by xmit */
-		u32 pull_len;		/* memcpy len for current rx packet */
-	};
-	u32 frag_num;
-	void *va; /* first buffer address for current packet */
-
 	u32 flag;          /* ring attribute */
 
 	int pending_buf;
-	struct sk_buff *skb;
-	struct sk_buff *tail_skb;
+	union {
+		/* for Tx ring */
+		struct {
+			u32 fd_qb_tx_sample;
+			int last_to_use;        /* last idx used by xmit */
+			u32 tx_copybreak;
+			struct hns3_tx_spare *tx_spare;
+		};
+
+		/* for Rx ring */
+		struct {
+			u32 pull_len;   /* memcpy len for current rx packet */
+			u32 rx_copybreak;
+			u32 frag_num;
+			/* first buffer address for current packet */
+			unsigned char *va;
+			struct sk_buff *skb;
+			struct sk_buff *tail_skb;
+		};
+	};
 } ____cacheline_internodealigned_in_smp;
 
 enum hns3_flow_level_range {
@@ -472,6 +526,7 @@ struct hns3_enet_ring_group {
 	u64 total_packets;	/* total packets processed this group */
 	u16 count;
 	struct hns3_enet_coalesce coal;
+	struct dim dim;
 };
 
 struct hns3_enet_tqp_vector {
@@ -493,7 +548,7 @@ struct hns3_enet_tqp_vector {
 
 	char name[HNAE3_INT_NAME_LEN];
 
-	unsigned long last_jiffies;
+	u64 event_cnt;
 } ____cacheline_internodealigned_in_smp;
 
 struct hns3_nic_priv {
@@ -516,6 +571,8 @@ struct hns3_nic_priv {
 
 	struct hns3_enet_coalesce tx_coal;
 	struct hns3_enet_coalesce rx_coal;
+	u32 tx_copybreak;
+	u32 rx_copybreak;
 };
 
 union l3_hdr_info {
@@ -631,7 +688,6 @@ void hns3_set_vector_coalesce_rx_ql(struct hns3_enet_tqp_vector *tqp_vector,
 void hns3_set_vector_coalesce_tx_ql(struct hns3_enet_tqp_vector *tqp_vector,
 				    u32 ql_value);
 
-void hns3_enable_vlan_filter(struct net_device *netdev, bool enable);
 void hns3_request_update_promisc_mode(struct hnae3_handle *handle);
 
 #ifdef CONFIG_HNS3_DCB
@@ -640,9 +696,10 @@ void hns3_dcbnl_setup(struct hnae3_handle *handle);
 static inline void hns3_dcbnl_setup(struct hnae3_handle *handle) {}
 #endif
 
-void hns3_dbg_init(struct hnae3_handle *handle);
+int hns3_dbg_init(struct hnae3_handle *handle);
 void hns3_dbg_uninit(struct hnae3_handle *handle);
 void hns3_dbg_register_debugfs(const char *debugfs_dir_name);
 void hns3_dbg_unregister_debugfs(void);
 void hns3_shinfo_pack(struct skb_shared_info *shinfo, __u32 *size);
+u16 hns3_get_max_available_channels(struct hnae3_handle *h);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index c1ea403d2b56..82061ab6930f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -46,6 +46,12 @@ static const struct hns3_stats hns3_txq_stats[] = {
 	HNS3_TQP_STAT("tso_err", tx_tso_err),
 	HNS3_TQP_STAT("over_max_recursion", over_max_recursion),
 	HNS3_TQP_STAT("hw_limitation", hw_limitation),
+	HNS3_TQP_STAT("bounce", tx_bounce),
+	HNS3_TQP_STAT("spare_full", tx_spare_full),
+	HNS3_TQP_STAT("copy_bits_err", copy_bits_err),
+	HNS3_TQP_STAT("sgl", tx_sgl),
+	HNS3_TQP_STAT("skb2sgl_err", skb2sgl_err),
+	HNS3_TQP_STAT("map_sg_err", map_sg_err),
 };
 
 #define HNS3_TXQ_STATS_COUNT ARRAY_SIZE(hns3_txq_stats)
@@ -65,6 +71,8 @@ static const struct hns3_stats hns3_rxq_stats[] = {
 	HNS3_TQP_STAT("csum_complete", csum_complete),
 	HNS3_TQP_STAT("multicast", rx_multicast),
 	HNS3_TQP_STAT("non_reuse_pg", non_reuse_pg),
+	HNS3_TQP_STAT("frag_alloc_err", frag_alloc_err),
+	HNS3_TQP_STAT("frag_alloc", frag_alloc),
 };
 
 #define HNS3_PRIV_FLAGS_LEN ARRAY_SIZE(hns3_priv_flags)
@@ -88,7 +96,6 @@ static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en)
 {
 	struct hnae3_handle *h = hns3_get_handle(ndev);
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
-	bool vlan_filter_enable;
 	int ret;
 
 	if (!h->ae_algo->ops->set_loopback ||
@@ -110,14 +117,11 @@ static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en)
 	if (ret || ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2)
 		return ret;
 
-	if (en) {
+	if (en)
 		h->ae_algo->ops->set_promisc_mode(h, true, true);
-	} else {
+	else
 		/* recover promisc mode before loopback test */
 		hns3_request_update_promisc_mode(h);
-		vlan_filter_enable = ndev->flags & IFF_PROMISC ? false : true;
-		hns3_enable_vlan_filter(ndev, vlan_filter_enable);
-	}
 
 	return ret;
 }
@@ -1596,12 +1600,77 @@ static int hns3_set_priv_flags(struct net_device *netdev, u32 pflags)
 	return 0;
 }
 
+static int hns3_get_tunable(struct net_device *netdev,
+			    const struct ethtool_tunable *tuna,
+			    void *data)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	int ret = 0;
+
+	switch (tuna->id) {
+	case ETHTOOL_TX_COPYBREAK:
+		/* all the tx rings have the same tx_copybreak */
+		*(u32 *)data = priv->tx_copybreak;
+		break;
+	case ETHTOOL_RX_COPYBREAK:
+		*(u32 *)data = priv->rx_copybreak;
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		break;
+	}
+
+	return ret;
+}
+
+static int hns3_set_tunable(struct net_device *netdev,
+			    const struct ethtool_tunable *tuna,
+			    const void *data)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hnae3_handle *h = priv->ae_handle;
+	int i, ret = 0;
+
+	switch (tuna->id) {
+	case ETHTOOL_TX_COPYBREAK:
+		priv->tx_copybreak = *(u32 *)data;
+
+		for (i = 0; i < h->kinfo.num_tqps; i++)
+			priv->ring[i].tx_copybreak = priv->tx_copybreak;
+
+		break;
+	case ETHTOOL_RX_COPYBREAK:
+		priv->rx_copybreak = *(u32 *)data;
+
+		for (i = h->kinfo.num_tqps; i < h->kinfo.num_tqps * 2; i++)
+			priv->ring[i].rx_copybreak = priv->rx_copybreak;
+
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		break;
+	}
+
+	return ret;
+}
+
 #define HNS3_ETHTOOL_COALESCE	(ETHTOOL_COALESCE_USECS |		\
 				 ETHTOOL_COALESCE_USE_ADAPTIVE |	\
 				 ETHTOOL_COALESCE_RX_USECS_HIGH |	\
 				 ETHTOOL_COALESCE_TX_USECS_HIGH |	\
 				 ETHTOOL_COALESCE_MAX_FRAMES)
 
+static int hns3_get_ts_info(struct net_device *netdev,
+			    struct ethtool_ts_info *info)
+{
+	struct hnae3_handle *handle = hns3_get_handle(netdev);
+
+	if (handle->ae_algo->ops->get_ts_info)
+		return handle->ae_algo->ops->get_ts_info(handle, info);
+
+	return ethtool_op_get_ts_info(netdev, info);
+}
+
 static const struct ethtool_ops hns3vf_ethtool_ops = {
 	.supported_coalesce_params = HNS3_ETHTOOL_COALESCE,
 	.get_drvinfo = hns3_get_drvinfo,
@@ -1628,6 +1697,8 @@ static const struct ethtool_ops hns3vf_ethtool_ops = {
 	.set_msglevel = hns3_set_msglevel,
 	.get_priv_flags = hns3_get_priv_flags,
 	.set_priv_flags = hns3_set_priv_flags,
+	.get_tunable = hns3_get_tunable,
+	.set_tunable = hns3_set_tunable,
 };
 
 static const struct ethtool_ops hns3_ethtool_ops = {
@@ -1666,6 +1737,9 @@ static const struct ethtool_ops hns3_ethtool_ops = {
 	.get_module_eeprom = hns3_get_module_eeprom,
 	.get_priv_flags = hns3_get_priv_flags,
 	.set_priv_flags = hns3_set_priv_flags,
+	.get_ts_info = hns3_get_ts_info,
+	.get_tunable = hns3_get_tunable,
+	.set_tunable = hns3_set_tunable,
 };
 
 void hns3_ethtool_set_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
index 6c28c8f6292c..a685392dbfe9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
@@ -7,6 +7,6 @@ ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3
 ccflags-y += -I $(srctree)/$(src)
 
 obj-$(CONFIG_HNS3_HCLGE) += hclge.o
-hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o  hclge_debugfs.o
+hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o  hclge_debugfs.o hclge_ptp.o
 
 hclge-$(CONFIG_HNS3_DCB) += hclge_dcb.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 76a482456f1f..887297e37cf3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -178,7 +178,8 @@ static bool hclge_is_special_opcode(u16 opcode)
 			     HCLGE_QUERY_CLEAR_MPF_RAS_INT,
 			     HCLGE_QUERY_CLEAR_PF_RAS_INT,
 			     HCLGE_QUERY_CLEAR_ALL_MPF_MSIX_INT,
-			     HCLGE_QUERY_CLEAR_ALL_PF_MSIX_INT};
+			     HCLGE_QUERY_CLEAR_ALL_PF_MSIX_INT,
+			     HCLGE_QUERY_ALL_ERR_INFO};
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(spec_opcode); i++) {
@@ -386,6 +387,14 @@ static void hclge_parse_capability(struct hclge_dev *hdev,
 		set_bit(HNAE3_DEV_SUPPORT_PAUSE_B, ae_dev->caps);
 	if (hnae3_get_bit(caps, HCLGE_CAP_PHY_IMP_B))
 		set_bit(HNAE3_DEV_SUPPORT_PHY_IMP_B, ae_dev->caps);
+	if (hnae3_get_bit(caps, HCLGE_CAP_RAS_IMP_B))
+		set_bit(HNAE3_DEV_SUPPORT_RAS_IMP_B, ae_dev->caps);
+	if (hnae3_get_bit(caps, HCLGE_CAP_RXD_ADV_LAYOUT_B))
+		set_bit(HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B, ae_dev->caps);
+	if (hnae3_get_bit(caps, HCLGE_CAP_PORT_VLAN_BYPASS_B)) {
+		set_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, ae_dev->caps);
+		set_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps);
+	}
 }
 
 static __le32 hclge_build_api_caps(void)
@@ -469,7 +478,7 @@ static int hclge_firmware_compat_config(struct hclge_dev *hdev)
 	struct hclge_desc desc;
 	u32 compat = 0;
 
-	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_M7_COMPAT_CFG, false);
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_IMP_COMPAT_CFG, false);
 
 	req = (struct hclge_firmware_compat_cmd *)desc.data;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index c6fc22e29581..a322dfeba5cf 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -130,6 +130,10 @@ enum hclge_opcode_type {
 	HCLGE_OPC_COMMON_LOOPBACK       = 0x0315,
 	HCLGE_OPC_CONFIG_FEC_MODE	= 0x031A,
 
+	/* PTP commands */
+	HCLGE_OPC_PTP_INT_EN		= 0x0501,
+	HCLGE_OPC_PTP_MODE_CFG		= 0x0507,
+
 	/* PFC/Pause commands */
 	HCLGE_OPC_CFG_MAC_PAUSE_EN      = 0x0701,
 	HCLGE_OPC_CFG_PFC_PAUSE_EN      = 0x0702,
@@ -236,6 +240,7 @@ enum hclge_opcode_type {
 	HCLGE_OPC_VLAN_FILTER_CTRL	    = 0x1100,
 	HCLGE_OPC_VLAN_FILTER_PF_CFG	= 0x1101,
 	HCLGE_OPC_VLAN_FILTER_VF_CFG	= 0x1102,
+	HCLGE_OPC_PORT_VLAN_BYPASS	= 0x1103,
 
 	/* Flow Director commands */
 	HCLGE_OPC_FD_MODE_CTRL		= 0x1200,
@@ -267,10 +272,10 @@ enum hclge_opcode_type {
 	/* NCL config command */
 	HCLGE_OPC_QUERY_NCL_CONFIG	= 0x7011,
 
-	/* M7 stats command */
-	HCLGE_OPC_M7_STATS_BD		= 0x7012,
-	HCLGE_OPC_M7_STATS_INFO		= 0x7013,
-	HCLGE_OPC_M7_COMPAT_CFG		= 0x701A,
+	/* IMP stats command */
+	HCLGE_OPC_IMP_STATS_BD		= 0x7012,
+	HCLGE_OPC_IMP_STATS_INFO		= 0x7013,
+	HCLGE_OPC_IMP_COMPAT_CFG		= 0x701A,
 
 	/* SFP command */
 	HCLGE_OPC_GET_SFP_EEPROM	= 0x7100,
@@ -292,6 +297,8 @@ enum hclge_opcode_type {
 	HCLGE_QUERY_MSIX_INT_STS_BD_NUM	= 0x1513,
 	HCLGE_QUERY_CLEAR_ALL_MPF_MSIX_INT	= 0x1514,
 	HCLGE_QUERY_CLEAR_ALL_PF_MSIX_INT	= 0x1515,
+	HCLGE_QUERY_ALL_ERR_BD_NUM		= 0x1516,
+	HCLGE_QUERY_ALL_ERR_INFO		= 0x1517,
 	HCLGE_CONFIG_ROCEE_RAS_INT_EN	= 0x1580,
 	HCLGE_QUERY_CLEAR_ROCEE_RAS_INT = 0x1581,
 	HCLGE_ROCEE_PF_RAS_INT_CMD	= 0x1584,
@@ -389,8 +396,11 @@ enum HCLGE_CAP_BITS {
 	HCLGE_CAP_HW_PAD_B,
 	HCLGE_CAP_STASH_B,
 	HCLGE_CAP_UDP_TUNNEL_CSUM_B,
+	HCLGE_CAP_RAS_IMP_B = 12,
 	HCLGE_CAP_FEC_B = 13,
 	HCLGE_CAP_PAUSE_B = 14,
+	HCLGE_CAP_RXD_ADV_LAYOUT_B = 15,
+	HCLGE_CAP_PORT_VLAN_BYPASS_B = 17,
 };
 
 enum HCLGE_API_CAP_BITS {
@@ -526,10 +536,14 @@ struct hclge_pf_res_cmd {
 #define HCLGE_CFG_SPEED_ABILITY_M	GENMASK(7, 0)
 #define HCLGE_CFG_SPEED_ABILITY_EXT_S	10
 #define HCLGE_CFG_SPEED_ABILITY_EXT_M	GENMASK(15, 10)
+#define HCLGE_CFG_VLAN_FLTR_CAP_S	8
+#define HCLGE_CFG_VLAN_FLTR_CAP_M	GENMASK(9, 8)
 #define HCLGE_CFG_UMV_TBL_SPACE_S	16
 #define HCLGE_CFG_UMV_TBL_SPACE_M	GENMASK(31, 16)
 #define HCLGE_CFG_PF_RSS_SIZE_S		0
 #define HCLGE_CFG_PF_RSS_SIZE_M		GENMASK(3, 0)
+#define HCLGE_CFG_TX_SPARE_BUF_SIZE_S	4
+#define HCLGE_CFG_TX_SPARE_BUF_SIZE_M	GENMASK(15, 4)
 
 #define HCLGE_CFG_CMD_CNT		4
 
@@ -810,6 +824,14 @@ struct hclge_vlan_filter_vf_cfg_cmd {
 	u8  vf_bitmap[HCLGE_MAX_VF_BYTES];
 };
 
+#define HCLGE_INGRESS_BYPASS_B		0
+struct hclge_port_vlan_filter_bypass_cmd {
+	u8 bypass_state;
+	u8 rsv1[3];
+	u8 vf_id;
+	u8 rsv2[19];
+};
+
 #define HCLGE_SWITCH_ANTI_SPOOF_B	0U
 #define HCLGE_SWITCH_ALW_LPBK_B		1U
 #define HCLGE_SWITCH_ALW_LCL_LPBK_B	2U
@@ -1100,7 +1122,7 @@ struct hclge_fd_user_def_cfg_cmd {
 	u8 rsv[12];
 };
 
-struct hclge_get_m7_bd_cmd {
+struct hclge_get_imp_bd_cmd {
 	__le32 bd_num;
 	u8 rsv[20];
 };
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 85d306459e36..6fc50d09b9db 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -4,74 +4,110 @@
 #include <linux/device.h>
 
 #include "hclge_debugfs.h"
+#include "hclge_err.h"
 #include "hclge_main.h"
 #include "hclge_tm.h"
 #include "hnae3.h"
 
+static const char * const state_str[] = { "off", "on" };
+static const char * const hclge_mac_state_str[] = {
+	"TO_ADD", "TO_DEL", "ACTIVE"
+};
+
 static const struct hclge_dbg_reg_type_info hclge_dbg_reg_info[] = {
-	{ .reg_type = "bios common",
+	{ .cmd = HNAE3_DBG_CMD_REG_BIOS_COMMON,
 	  .dfx_msg = &hclge_dbg_bios_common_reg[0],
 	  .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_bios_common_reg),
 		       .offset = HCLGE_DBG_DFX_BIOS_OFFSET,
 		       .cmd = HCLGE_OPC_DFX_BIOS_COMMON_REG } },
-	{ .reg_type = "ssu",
+	{ .cmd = HNAE3_DBG_CMD_REG_SSU,
 	  .dfx_msg = &hclge_dbg_ssu_reg_0[0],
 	  .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_ssu_reg_0),
 		       .offset = HCLGE_DBG_DFX_SSU_0_OFFSET,
 		       .cmd = HCLGE_OPC_DFX_SSU_REG_0 } },
-	{ .reg_type = "ssu",
+	{ .cmd = HNAE3_DBG_CMD_REG_SSU,
 	  .dfx_msg = &hclge_dbg_ssu_reg_1[0],
 	  .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_ssu_reg_1),
 		       .offset = HCLGE_DBG_DFX_SSU_1_OFFSET,
 		       .cmd = HCLGE_OPC_DFX_SSU_REG_1 } },
-	{ .reg_type = "ssu",
+	{ .cmd = HNAE3_DBG_CMD_REG_SSU,
 	  .dfx_msg = &hclge_dbg_ssu_reg_2[0],
 	  .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_ssu_reg_2),
 		       .offset = HCLGE_DBG_DFX_SSU_2_OFFSET,
 		       .cmd = HCLGE_OPC_DFX_SSU_REG_2 } },
-	{ .reg_type = "igu egu",
+	{ .cmd = HNAE3_DBG_CMD_REG_IGU_EGU,
 	  .dfx_msg = &hclge_dbg_igu_egu_reg[0],
 	  .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_igu_egu_reg),
 		       .offset = HCLGE_DBG_DFX_IGU_OFFSET,
 		       .cmd = HCLGE_OPC_DFX_IGU_EGU_REG } },
-	{ .reg_type = "rpu",
+	{ .cmd = HNAE3_DBG_CMD_REG_RPU,
 	  .dfx_msg = &hclge_dbg_rpu_reg_0[0],
 	  .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_rpu_reg_0),
 		       .offset = HCLGE_DBG_DFX_RPU_0_OFFSET,
 		       .cmd = HCLGE_OPC_DFX_RPU_REG_0 } },
-	{ .reg_type = "rpu",
+	{ .cmd = HNAE3_DBG_CMD_REG_RPU,
 	  .dfx_msg = &hclge_dbg_rpu_reg_1[0],
 	  .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_rpu_reg_1),
 		       .offset = HCLGE_DBG_DFX_RPU_1_OFFSET,
 		       .cmd = HCLGE_OPC_DFX_RPU_REG_1 } },
-	{ .reg_type = "ncsi",
+	{ .cmd = HNAE3_DBG_CMD_REG_NCSI,
 	  .dfx_msg = &hclge_dbg_ncsi_reg[0],
 	  .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_ncsi_reg),
 		       .offset = HCLGE_DBG_DFX_NCSI_OFFSET,
 		       .cmd = HCLGE_OPC_DFX_NCSI_REG } },
-	{ .reg_type = "rtc",
+	{ .cmd = HNAE3_DBG_CMD_REG_RTC,
 	  .dfx_msg = &hclge_dbg_rtc_reg[0],
 	  .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_rtc_reg),
 		       .offset = HCLGE_DBG_DFX_RTC_OFFSET,
 		       .cmd = HCLGE_OPC_DFX_RTC_REG } },
-	{ .reg_type = "ppp",
+	{ .cmd = HNAE3_DBG_CMD_REG_PPP,
 	  .dfx_msg = &hclge_dbg_ppp_reg[0],
 	  .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_ppp_reg),
 		       .offset = HCLGE_DBG_DFX_PPP_OFFSET,
 		       .cmd = HCLGE_OPC_DFX_PPP_REG } },
-	{ .reg_type = "rcb",
+	{ .cmd = HNAE3_DBG_CMD_REG_RCB,
 	  .dfx_msg = &hclge_dbg_rcb_reg[0],
 	  .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_rcb_reg),
 		       .offset = HCLGE_DBG_DFX_RCB_OFFSET,
 		       .cmd = HCLGE_OPC_DFX_RCB_REG } },
-	{ .reg_type = "tqp",
+	{ .cmd = HNAE3_DBG_CMD_REG_TQP,
 	  .dfx_msg = &hclge_dbg_tqp_reg[0],
 	  .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_tqp_reg),
 		       .offset = HCLGE_DBG_DFX_TQP_OFFSET,
 		       .cmd = HCLGE_OPC_DFX_TQP_REG } },
 };
 
-static int hclge_dbg_get_dfx_bd_num(struct hclge_dev *hdev, int offset)
+static void hclge_dbg_fill_content(char *content, u16 len,
+				   const struct hclge_dbg_item *items,
+				   const char **result, u16 size)
+{
+	char *pos = content;
+	u16 i;
+
+	memset(content, ' ', len);
+	for (i = 0; i < size; i++) {
+		if (result)
+			strncpy(pos, result[i], strlen(result[i]));
+		else
+			strncpy(pos, items[i].name, strlen(items[i].name));
+		pos += strlen(items[i].name) + items[i].interval;
+	}
+	*pos++ = '\n';
+	*pos++ = '\0';
+}
+
+static char *hclge_dbg_get_func_id_str(char *buf, u8 id)
+{
+	if (id)
+		sprintf(buf, "vf%u", id - 1);
+	else
+		sprintf(buf, "pf");
+
+	return buf;
+}
+
+static int hclge_dbg_get_dfx_bd_num(struct hclge_dev *hdev, int offset,
+				    u32 *bd_num)
 {
 	struct hclge_desc desc[HCLGE_GET_DFX_REG_TYPE_CNT];
 	int entries_per_desc;
@@ -81,13 +117,21 @@ static int hclge_dbg_get_dfx_bd_num(struct hclge_dev *hdev, int offset)
 	ret = hclge_query_bd_num_cmd_send(hdev, desc);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
-			"get dfx bdnum fail, ret = %d\n", ret);
+			"failed to get dfx bd_num, offset = %d, ret = %d\n",
+			offset, ret);
 		return ret;
 	}
 
 	entries_per_desc = ARRAY_SIZE(desc[0].data);
 	index = offset % entries_per_desc;
-	return le32_to_cpu(desc[offset / entries_per_desc].data[index]);
+
+	*bd_num = le32_to_cpu(desc[offset / entries_per_desc].data[index]);
+	if (!(*bd_num)) {
+		dev_err(&hdev->pdev->dev, "The value of dfx bd_num is 0!\n");
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
 static int hclge_dbg_cmd_send(struct hclge_dev *hdev,
@@ -114,66 +158,108 @@ static int hclge_dbg_cmd_send(struct hclge_dev *hdev,
 	return ret;
 }
 
-static void hclge_dbg_dump_reg_common(struct hclge_dev *hdev,
-				      const struct hclge_dbg_reg_type_info *reg_info,
-				      const char *cmd_buf)
+static int
+hclge_dbg_dump_reg_tqp(struct hclge_dev *hdev,
+		       const struct hclge_dbg_reg_type_info *reg_info,
+		       char *buf, int len, int *pos)
 {
-#define IDX_OFFSET	1
-
-	const char *s = &cmd_buf[strlen(reg_info->reg_type) + IDX_OFFSET];
 	const struct hclge_dbg_dfx_message *dfx_message = reg_info->dfx_msg;
 	const struct hclge_dbg_reg_common_msg *reg_msg = &reg_info->reg_msg;
 	struct hclge_desc *desc_src;
+	u32 index, entry, i, cnt;
+	int bd_num, min_num, ret;
 	struct hclge_desc *desc;
-	int entries_per_desc;
-	int bd_num, buf_len;
-	int index = 0;
-	int min_num;
-	int ret, i;
 
-	if (*s) {
-		ret = kstrtouint(s, 0, &index);
-		index = (ret != 0) ? 0 : index;
-	}
+	ret = hclge_dbg_get_dfx_bd_num(hdev, reg_msg->offset, &bd_num);
+	if (ret)
+		return ret;
+
+	desc_src = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL);
+	if (!desc_src)
+		return -ENOMEM;
+
+	min_num = min_t(int, bd_num * HCLGE_DESC_DATA_LEN, reg_msg->msg_num);
 
-	bd_num = hclge_dbg_get_dfx_bd_num(hdev, reg_msg->offset);
-	if (bd_num <= 0) {
-		dev_err(&hdev->pdev->dev, "get cmd(%d) bd num(%d) failed\n",
-			reg_msg->offset, bd_num);
-		return;
+	for (i = 0, cnt = 0; i < min_num; i++, dfx_message++)
+		*pos += scnprintf(buf + *pos, len - *pos, "item%u = %s\n",
+				  cnt++, dfx_message->message);
+
+	for (i = 0; i < cnt; i++)
+		*pos += scnprintf(buf + *pos, len - *pos, "item%u\t", i);
+
+	*pos += scnprintf(buf + *pos, len - *pos, "\n");
+
+	for (index = 0; index < hdev->vport[0].alloc_tqps; index++) {
+		dfx_message = reg_info->dfx_msg;
+		desc = desc_src;
+		ret = hclge_dbg_cmd_send(hdev, desc, index, bd_num,
+					 reg_msg->cmd);
+		if (ret)
+			break;
+
+		for (i = 0; i < min_num; i++, dfx_message++) {
+			entry = i % HCLGE_DESC_DATA_LEN;
+			if (i > 0 && !entry)
+				desc++;
+
+			*pos += scnprintf(buf + *pos, len - *pos, "%#x\t",
+					  le32_to_cpu(desc->data[entry]));
+		}
+		*pos += scnprintf(buf + *pos, len - *pos, "\n");
 	}
 
-	buf_len = sizeof(struct hclge_desc) * bd_num;
-	desc_src = kzalloc(buf_len, GFP_KERNEL);
+	kfree(desc_src);
+	return ret;
+}
+
+static int
+hclge_dbg_dump_reg_common(struct hclge_dev *hdev,
+			  const struct hclge_dbg_reg_type_info *reg_info,
+			  char *buf, int len, int *pos)
+{
+	const struct hclge_dbg_reg_common_msg *reg_msg = &reg_info->reg_msg;
+	const struct hclge_dbg_dfx_message *dfx_message = reg_info->dfx_msg;
+	struct hclge_desc *desc_src;
+	int bd_num, min_num, ret;
+	struct hclge_desc *desc;
+	u32 entry, i;
+
+	ret = hclge_dbg_get_dfx_bd_num(hdev, reg_msg->offset, &bd_num);
+	if (ret)
+		return ret;
+
+	desc_src = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL);
 	if (!desc_src)
-		return;
+		return -ENOMEM;
 
 	desc = desc_src;
-	ret = hclge_dbg_cmd_send(hdev, desc, index, bd_num, reg_msg->cmd);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, 0, bd_num, reg_msg->cmd);
 	if (ret) {
-		kfree(desc_src);
-		return;
+		kfree(desc);
+		return ret;
 	}
 
-	entries_per_desc = ARRAY_SIZE(desc->data);
-	min_num = min_t(int, bd_num * entries_per_desc, reg_msg->msg_num);
+	min_num = min_t(int, bd_num * HCLGE_DESC_DATA_LEN, reg_msg->msg_num);
 
-	desc = desc_src;
-	for (i = 0; i < min_num; i++) {
-		if (i > 0 && (i % entries_per_desc) == 0)
+	for (i = 0; i < min_num; i++, dfx_message++) {
+		entry = i % HCLGE_DESC_DATA_LEN;
+		if (i > 0 && !entry)
 			desc++;
-		if (dfx_message->flag)
-			dev_info(&hdev->pdev->dev, "%s: 0x%x\n",
-				 dfx_message->message,
-				 le32_to_cpu(desc->data[i % entries_per_desc]));
+		if (!dfx_message->flag)
+			continue;
 
-		dfx_message++;
+		*pos += scnprintf(buf + *pos, len - *pos, "%s: %#x\n",
+				  dfx_message->message,
+				  le32_to_cpu(desc->data[entry]));
 	}
 
 	kfree(desc_src);
+	return 0;
 }
 
-static void hclge_dbg_dump_mac_enable_status(struct hclge_dev *hdev)
+static int  hclge_dbg_dump_mac_enable_status(struct hclge_dev *hdev, char *buf,
+					     int len, int *pos)
 {
 	struct hclge_config_mac_mode_cmd *req;
 	struct hclge_desc desc;
@@ -186,43 +272,51 @@ static void hclge_dbg_dump_mac_enable_status(struct hclge_dev *hdev)
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed to dump mac enable status, ret = %d\n", ret);
-		return;
+		return ret;
 	}
 
 	req = (struct hclge_config_mac_mode_cmd *)desc.data;
 	loop_en = le32_to_cpu(req->txrx_pad_fcs_loop_en);
 
-	dev_info(&hdev->pdev->dev, "config_mac_trans_en: %#x\n",
-		 hnae3_get_bit(loop_en, HCLGE_MAC_TX_EN_B));
-	dev_info(&hdev->pdev->dev, "config_mac_rcv_en: %#x\n",
-		 hnae3_get_bit(loop_en, HCLGE_MAC_RX_EN_B));
-	dev_info(&hdev->pdev->dev, "config_pad_trans_en: %#x\n",
-		 hnae3_get_bit(loop_en, HCLGE_MAC_PAD_TX_B));
-	dev_info(&hdev->pdev->dev, "config_pad_rcv_en: %#x\n",
-		 hnae3_get_bit(loop_en, HCLGE_MAC_PAD_RX_B));
-	dev_info(&hdev->pdev->dev, "config_1588_trans_en: %#x\n",
-		 hnae3_get_bit(loop_en, HCLGE_MAC_1588_TX_B));
-	dev_info(&hdev->pdev->dev, "config_1588_rcv_en: %#x\n",
-		 hnae3_get_bit(loop_en, HCLGE_MAC_1588_RX_B));
-	dev_info(&hdev->pdev->dev, "config_mac_app_loop_en: %#x\n",
-		 hnae3_get_bit(loop_en, HCLGE_MAC_APP_LP_B));
-	dev_info(&hdev->pdev->dev, "config_mac_line_loop_en: %#x\n",
-		 hnae3_get_bit(loop_en, HCLGE_MAC_LINE_LP_B));
-	dev_info(&hdev->pdev->dev, "config_mac_fcs_tx_en: %#x\n",
-		 hnae3_get_bit(loop_en, HCLGE_MAC_FCS_TX_B));
-	dev_info(&hdev->pdev->dev, "config_mac_rx_oversize_truncate_en: %#x\n",
-		 hnae3_get_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B));
-	dev_info(&hdev->pdev->dev, "config_mac_rx_fcs_strip_en: %#x\n",
-		 hnae3_get_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B));
-	dev_info(&hdev->pdev->dev, "config_mac_rx_fcs_en: %#x\n",
-		 hnae3_get_bit(loop_en, HCLGE_MAC_RX_FCS_B));
-	dev_info(&hdev->pdev->dev, "config_mac_tx_under_min_err_en: %#x\n",
-		 hnae3_get_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B));
-	dev_info(&hdev->pdev->dev, "config_mac_tx_oversize_truncate_en: %#x\n",
-		 hnae3_get_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B));
+	*pos += scnprintf(buf + *pos, len - *pos, "mac_trans_en: %#x\n",
+			  hnae3_get_bit(loop_en, HCLGE_MAC_TX_EN_B));
+	*pos += scnprintf(buf + *pos, len - *pos, "mac_rcv_en: %#x\n",
+			  hnae3_get_bit(loop_en, HCLGE_MAC_RX_EN_B));
+	*pos += scnprintf(buf + *pos, len - *pos, "pad_trans_en: %#x\n",
+			  hnae3_get_bit(loop_en, HCLGE_MAC_PAD_TX_B));
+	*pos += scnprintf(buf + *pos, len - *pos, "pad_rcv_en: %#x\n",
+			  hnae3_get_bit(loop_en, HCLGE_MAC_PAD_RX_B));
+	*pos += scnprintf(buf + *pos, len - *pos, "1588_trans_en: %#x\n",
+			  hnae3_get_bit(loop_en, HCLGE_MAC_1588_TX_B));
+	*pos += scnprintf(buf + *pos, len - *pos, "1588_rcv_en: %#x\n",
+			  hnae3_get_bit(loop_en, HCLGE_MAC_1588_RX_B));
+	*pos += scnprintf(buf + *pos, len - *pos, "mac_app_loop_en: %#x\n",
+			  hnae3_get_bit(loop_en, HCLGE_MAC_APP_LP_B));
+	*pos += scnprintf(buf + *pos, len - *pos, "mac_line_loop_en: %#x\n",
+			  hnae3_get_bit(loop_en, HCLGE_MAC_LINE_LP_B));
+	*pos += scnprintf(buf + *pos, len - *pos, "mac_fcs_tx_en: %#x\n",
+			  hnae3_get_bit(loop_en, HCLGE_MAC_FCS_TX_B));
+	*pos += scnprintf(buf + *pos, len - *pos,
+			  "mac_rx_oversize_truncate_en: %#x\n",
+			  hnae3_get_bit(loop_en,
+					HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B));
+	*pos += scnprintf(buf + *pos, len - *pos, "mac_rx_fcs_strip_en: %#x\n",
+			  hnae3_get_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B));
+	*pos += scnprintf(buf + *pos, len - *pos, "mac_rx_fcs_en: %#x\n",
+			  hnae3_get_bit(loop_en, HCLGE_MAC_RX_FCS_B));
+	*pos += scnprintf(buf + *pos, len - *pos,
+			  "mac_tx_under_min_err_en: %#x\n",
+			  hnae3_get_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B));
+	*pos += scnprintf(buf + *pos, len - *pos,
+			  "mac_tx_oversize_truncate_en: %#x\n",
+			  hnae3_get_bit(loop_en,
+					HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B));
+
+	return 0;
 }
 
-static void hclge_dbg_dump_mac_frame_size(struct hclge_dev *hdev)
+static int hclge_dbg_dump_mac_frame_size(struct hclge_dev *hdev, char *buf,
+					 int len, int *pos)
 {
 	struct hclge_config_max_frm_size_cmd *req;
 	struct hclge_desc desc;
@@ -234,17 +328,21 @@ static void hclge_dbg_dump_mac_frame_size(struct hclge_dev *hdev)
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed to dump mac frame size, ret = %d\n", ret);
-		return;
+		return ret;
 	}
 
 	req = (struct hclge_config_max_frm_size_cmd *)desc.data;
 
-	dev_info(&hdev->pdev->dev, "max_frame_size: %u\n",
-		 le16_to_cpu(req->max_frm_size));
-	dev_info(&hdev->pdev->dev, "min_frame_size: %u\n", req->min_frm_size);
+	*pos += scnprintf(buf + *pos, len - *pos, "max_frame_size: %u\n",
+			  le16_to_cpu(req->max_frm_size));
+	*pos += scnprintf(buf + *pos, len - *pos, "min_frame_size: %u\n",
+			  req->min_frm_size);
+
+	return 0;
 }
 
-static void hclge_dbg_dump_mac_speed_duplex(struct hclge_dev *hdev)
+static int hclge_dbg_dump_mac_speed_duplex(struct hclge_dev *hdev, char *buf,
+					   int len, int *pos)
 {
 #define HCLGE_MAC_SPEED_SHIFT	0
 #define HCLGE_MAC_SPEED_MASK	GENMASK(5, 0)
@@ -260,543 +358,540 @@ static void hclge_dbg_dump_mac_speed_duplex(struct hclge_dev *hdev)
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed to dump mac speed duplex, ret = %d\n", ret);
-		return;
+		return ret;
 	}
 
 	req = (struct hclge_config_mac_speed_dup_cmd *)desc.data;
 
-	dev_info(&hdev->pdev->dev, "speed: %#lx\n",
-		 hnae3_get_field(req->speed_dup, HCLGE_MAC_SPEED_MASK,
-				 HCLGE_MAC_SPEED_SHIFT));
-	dev_info(&hdev->pdev->dev, "duplex: %#x\n",
-		 hnae3_get_bit(req->speed_dup, HCLGE_MAC_DUPLEX_SHIFT));
+	*pos += scnprintf(buf + *pos, len - *pos, "speed: %#lx\n",
+			  hnae3_get_field(req->speed_dup, HCLGE_MAC_SPEED_MASK,
+					  HCLGE_MAC_SPEED_SHIFT));
+	*pos += scnprintf(buf + *pos, len - *pos, "duplex: %#x\n",
+			  hnae3_get_bit(req->speed_dup,
+					HCLGE_MAC_DUPLEX_SHIFT));
+	return 0;
 }
 
-static void hclge_dbg_dump_mac(struct hclge_dev *hdev)
+static int hclge_dbg_dump_mac(struct hclge_dev *hdev, char *buf, int len)
 {
-	hclge_dbg_dump_mac_enable_status(hdev);
+	int pos = 0;
+	int ret;
 
-	hclge_dbg_dump_mac_frame_size(hdev);
+	ret = hclge_dbg_dump_mac_enable_status(hdev, buf, len, &pos);
+	if (ret)
+		return ret;
+
+	ret = hclge_dbg_dump_mac_frame_size(hdev, buf, len, &pos);
+	if (ret)
+		return ret;
 
-	hclge_dbg_dump_mac_speed_duplex(hdev);
+	return hclge_dbg_dump_mac_speed_duplex(hdev, buf, len, &pos);
 }
 
-static void hclge_dbg_dump_dcb(struct hclge_dev *hdev, const char *cmd_buf)
+static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len,
+				   int *pos)
 {
-	struct device *dev = &hdev->pdev->dev;
 	struct hclge_dbg_bitmap_cmd *bitmap;
-	enum hclge_opcode_type cmd;
-	int rq_id, pri_id, qset_id;
-	int port_id, nq_id, pg_id;
-	struct hclge_desc desc[2];
-
-	int cnt, ret;
-
-	cnt = sscanf(cmd_buf, "%i %i %i %i %i %i",
-		     &port_id, &pri_id, &pg_id, &rq_id, &nq_id, &qset_id);
-	if (cnt != 6) {
-		dev_err(&hdev->pdev->dev,
-			"dump dcb: bad command parameter, cnt=%d\n", cnt);
-		return;
-	}
+	struct hclge_desc desc;
+	u16 qset_id, qset_num;
+	int ret;
 
-	cmd = HCLGE_OPC_QSET_DFX_STS;
-	ret = hclge_dbg_cmd_send(hdev, desc, qset_id, 1, cmd);
+	ret = hclge_tm_get_qset_num(hdev, &qset_num);
 	if (ret)
-		goto err_dcb_cmd_send;
+		return ret;
 
-	bitmap = (struct hclge_dbg_bitmap_cmd *)&desc[0].data[1];
-	dev_info(dev, "roce_qset_mask: 0x%x\n", bitmap->bit0);
-	dev_info(dev, "nic_qs_mask: 0x%x\n", bitmap->bit1);
-	dev_info(dev, "qs_shaping_pass: 0x%x\n", bitmap->bit2);
-	dev_info(dev, "qs_bp_sts: 0x%x\n", bitmap->bit3);
+	*pos += scnprintf(buf + *pos, len - *pos,
+			  "qset_id  roce_qset_mask  nic_qset_mask  qset_shaping_pass  qset_bp_status\n");
+	for (qset_id = 0; qset_id < qset_num; qset_id++) {
+		ret = hclge_dbg_cmd_send(hdev, &desc, qset_id, 1,
+					 HCLGE_OPC_QSET_DFX_STS);
+		if (ret)
+			return ret;
 
-	cmd = HCLGE_OPC_PRI_DFX_STS;
-	ret = hclge_dbg_cmd_send(hdev, desc, pri_id, 1, cmd);
-	if (ret)
-		goto err_dcb_cmd_send;
+		bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1];
 
-	bitmap = (struct hclge_dbg_bitmap_cmd *)&desc[0].data[1];
-	dev_info(dev, "pri_mask: 0x%x\n", bitmap->bit0);
-	dev_info(dev, "pri_cshaping_pass: 0x%x\n", bitmap->bit1);
-	dev_info(dev, "pri_pshaping_pass: 0x%x\n", bitmap->bit2);
+		*pos += scnprintf(buf + *pos, len - *pos,
+				  "%04u           %#x            %#x             %#x               %#x\n",
+				  qset_id, bitmap->bit0, bitmap->bit1,
+				  bitmap->bit2, bitmap->bit3);
+	}
 
-	cmd = HCLGE_OPC_PG_DFX_STS;
-	ret = hclge_dbg_cmd_send(hdev, desc, pg_id, 1, cmd);
-	if (ret)
-		goto err_dcb_cmd_send;
+	return 0;
+}
 
-	bitmap = (struct hclge_dbg_bitmap_cmd *)&desc[0].data[1];
-	dev_info(dev, "pg_mask: 0x%x\n", bitmap->bit0);
-	dev_info(dev, "pg_cshaping_pass: 0x%x\n", bitmap->bit1);
-	dev_info(dev, "pg_pshaping_pass: 0x%x\n", bitmap->bit2);
+static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len,
+				  int *pos)
+{
+	struct hclge_dbg_bitmap_cmd *bitmap;
+	struct hclge_desc desc;
+	u8 pri_id, pri_num;
+	int ret;
 
-	cmd = HCLGE_OPC_PORT_DFX_STS;
-	ret = hclge_dbg_cmd_send(hdev, desc, port_id, 1, cmd);
+	ret = hclge_tm_get_pri_num(hdev, &pri_num);
 	if (ret)
-		goto err_dcb_cmd_send;
+		return ret;
 
-	bitmap = (struct hclge_dbg_bitmap_cmd *)&desc[0].data[1];
-	dev_info(dev, "port_mask: 0x%x\n", bitmap->bit0);
-	dev_info(dev, "port_shaping_pass: 0x%x\n", bitmap->bit1);
+	*pos += scnprintf(buf + *pos, len - *pos,
+			  "pri_id  pri_mask  pri_cshaping_pass  pri_pshaping_pass\n");
+	for (pri_id = 0; pri_id < pri_num; pri_id++) {
+		ret = hclge_dbg_cmd_send(hdev, &desc, pri_id, 1,
+					 HCLGE_OPC_PRI_DFX_STS);
+		if (ret)
+			return ret;
 
-	cmd = HCLGE_OPC_SCH_NQ_CNT;
-	ret = hclge_dbg_cmd_send(hdev, desc, nq_id, 1, cmd);
-	if (ret)
-		goto err_dcb_cmd_send;
+		bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1];
 
-	dev_info(dev, "sch_nq_cnt: 0x%x\n", le32_to_cpu(desc[0].data[1]));
+		*pos += scnprintf(buf + *pos, len - *pos,
+				  "%03u       %#x           %#x                %#x\n",
+				  pri_id, bitmap->bit0, bitmap->bit1,
+				  bitmap->bit2);
+	}
 
-	cmd = HCLGE_OPC_SCH_RQ_CNT;
-	ret = hclge_dbg_cmd_send(hdev, desc, nq_id, 1, cmd);
-	if (ret)
-		goto err_dcb_cmd_send;
+	return 0;
+}
+
+static int hclge_dbg_dump_dcb_pg(struct hclge_dev *hdev, char *buf, int len,
+				 int *pos)
+{
+	struct hclge_dbg_bitmap_cmd *bitmap;
+	struct hclge_desc desc;
+	u8 pg_id;
+	int ret;
 
-	dev_info(dev, "sch_rq_cnt: 0x%x\n", le32_to_cpu(desc[0].data[1]));
+	*pos += scnprintf(buf + *pos, len - *pos,
+			  "pg_id  pg_mask  pg_cshaping_pass  pg_pshaping_pass\n");
+	for (pg_id = 0; pg_id < hdev->tm_info.num_pg; pg_id++) {
+		ret = hclge_dbg_cmd_send(hdev, &desc, pg_id, 1,
+					 HCLGE_OPC_PG_DFX_STS);
+		if (ret)
+			return ret;
 
-	cmd = HCLGE_OPC_TM_INTERNAL_STS;
-	ret = hclge_dbg_cmd_send(hdev, desc, 0, 2, cmd);
-	if (ret)
-		goto err_dcb_cmd_send;
-
-	dev_info(dev, "pri_bp: 0x%x\n", le32_to_cpu(desc[0].data[1]));
-	dev_info(dev, "fifo_dfx_info: 0x%x\n", le32_to_cpu(desc[0].data[2]));
-	dev_info(dev, "sch_roce_fifo_afull_gap: 0x%x\n",
-		 le32_to_cpu(desc[0].data[3]));
-	dev_info(dev, "tx_private_waterline: 0x%x\n",
-		 le32_to_cpu(desc[0].data[4]));
-	dev_info(dev, "tm_bypass_en: 0x%x\n", le32_to_cpu(desc[0].data[5]));
-	dev_info(dev, "SSU_TM_BYPASS_EN: 0x%x\n", le32_to_cpu(desc[1].data[0]));
-	dev_info(dev, "SSU_RESERVE_CFG: 0x%x\n", le32_to_cpu(desc[1].data[1]));
-
-	cmd = HCLGE_OPC_TM_INTERNAL_CNT;
-	ret = hclge_dbg_cmd_send(hdev, desc, port_id, 1, cmd);
-	if (ret)
-		goto err_dcb_cmd_send;
+		bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1];
 
-	dev_info(dev, "SCH_NIC_NUM: 0x%x\n", le32_to_cpu(desc[0].data[1]));
-	dev_info(dev, "SCH_ROCE_NUM: 0x%x\n", le32_to_cpu(desc[0].data[2]));
+		*pos += scnprintf(buf + *pos, len - *pos,
+				  "%03u      %#x           %#x               %#x\n",
+				  pg_id, bitmap->bit0, bitmap->bit1,
+				  bitmap->bit2);
+	}
 
-	cmd = HCLGE_OPC_TM_INTERNAL_STS_1;
-	ret = hclge_dbg_cmd_send(hdev, desc, port_id, 1, cmd);
-	if (ret)
-		goto err_dcb_cmd_send;
-
-	dev_info(dev, "TC_MAP_SEL: 0x%x\n", le32_to_cpu(desc[0].data[1]));
-	dev_info(dev, "IGU_PFC_PRI_EN: 0x%x\n", le32_to_cpu(desc[0].data[2]));
-	dev_info(dev, "MAC_PFC_PRI_EN: 0x%x\n", le32_to_cpu(desc[0].data[3]));
-	dev_info(dev, "IGU_PRI_MAP_TC_CFG: 0x%x\n",
-		 le32_to_cpu(desc[0].data[4]));
-	dev_info(dev, "IGU_TX_PRI_MAP_TC_CFG: 0x%x\n",
-		 le32_to_cpu(desc[0].data[5]));
-	return;
-
-err_dcb_cmd_send:
-	dev_err(&hdev->pdev->dev,
-		"failed to dump dcb dfx, cmd = %#x, ret = %d\n",
-		cmd, ret);
+	return 0;
 }
 
-static void hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev, const char *cmd_buf)
+static int hclge_dbg_dump_dcb_queue(struct hclge_dev *hdev, char *buf, int len,
+				    int *pos)
 {
-	const struct hclge_dbg_reg_type_info *reg_info;
-	bool has_dump = false;
-	int i;
+	struct hclge_desc desc;
+	u16 nq_id;
+	int ret;
 
-	for (i = 0; i < ARRAY_SIZE(hclge_dbg_reg_info); i++) {
-		reg_info = &hclge_dbg_reg_info[i];
-		if (!strncmp(cmd_buf, reg_info->reg_type,
-			     strlen(reg_info->reg_type))) {
-			hclge_dbg_dump_reg_common(hdev, reg_info, cmd_buf);
-			has_dump = true;
-		}
-	}
+	*pos += scnprintf(buf + *pos, len - *pos,
+			  "nq_id  sch_nic_queue_cnt  sch_roce_queue_cnt\n");
+	for (nq_id = 0; nq_id < hdev->num_tqps; nq_id++) {
+		ret = hclge_dbg_cmd_send(hdev, &desc, nq_id, 1,
+					 HCLGE_OPC_SCH_NQ_CNT);
+		if (ret)
+			return ret;
 
-	if (strncmp(cmd_buf, "mac", strlen("mac")) == 0) {
-		hclge_dbg_dump_mac(hdev);
-		has_dump = true;
-	}
+		*pos += scnprintf(buf + *pos, len - *pos, "%04u           %#x",
+				  nq_id, le32_to_cpu(desc.data[1]));
 
-	if (strncmp(cmd_buf, "dcb", 3) == 0) {
-		hclge_dbg_dump_dcb(hdev, &cmd_buf[sizeof("dcb")]);
-		has_dump = true;
-	}
+		ret = hclge_dbg_cmd_send(hdev, &desc, nq_id, 1,
+					 HCLGE_OPC_SCH_RQ_CNT);
+		if (ret)
+			return ret;
 
-	if (!has_dump) {
-		dev_info(&hdev->pdev->dev, "unknown command\n");
-		return;
+		*pos += scnprintf(buf + *pos, len - *pos,
+				  "               %#x\n",
+				  le32_to_cpu(desc.data[1]));
 	}
-}
 
-static void hclge_print_tc_info(struct hclge_dev *hdev, bool flag, int index)
-{
-	if (flag)
-		dev_info(&hdev->pdev->dev, "tc(%d): no sp mode weight: %u\n",
-			 index, hdev->tm_info.pg_info[0].tc_dwrr[index]);
-	else
-		dev_info(&hdev->pdev->dev, "tc(%d): sp mode\n", index);
+	return 0;
 }
 
-static void hclge_dbg_dump_tc(struct hclge_dev *hdev)
+static int hclge_dbg_dump_dcb_port(struct hclge_dev *hdev, char *buf, int len,
+				   int *pos)
 {
-	struct hclge_ets_tc_weight_cmd *ets_weight;
+	struct hclge_dbg_bitmap_cmd *bitmap;
 	struct hclge_desc desc;
-	int i, ret;
-
-	if (!hnae3_dev_dcb_supported(hdev)) {
-		dev_info(&hdev->pdev->dev,
-			 "Only DCB-supported dev supports tc\n");
-		return;
-	}
-
-	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_ETS_TC_WEIGHT, true);
+	u8 port_id = 0;
+	int ret;
 
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
-		dev_err(&hdev->pdev->dev, "dump tc fail, ret = %d\n", ret);
-		return;
-	}
+	ret = hclge_dbg_cmd_send(hdev, &desc, port_id, 1,
+				 HCLGE_OPC_PORT_DFX_STS);
+	if (ret)
+		return ret;
 
-	ets_weight = (struct hclge_ets_tc_weight_cmd *)desc.data;
+	bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1];
 
-	dev_info(&hdev->pdev->dev, "dump tc: %u tc enabled\n",
-		 hdev->tm_info.num_tc);
-	dev_info(&hdev->pdev->dev, "weight_offset: %u\n",
-		 ets_weight->weight_offset);
+	*pos += scnprintf(buf + *pos, len - *pos, "port_mask: %#x\n",
+			 bitmap->bit0);
+	*pos += scnprintf(buf + *pos, len - *pos, "port_shaping_pass: %#x\n",
+			 bitmap->bit1);
 
-	for (i = 0; i < HNAE3_MAX_TC; i++)
-		hclge_print_tc_info(hdev, ets_weight->tc_weight[i], i);
+	return 0;
 }
 
-static void hclge_dbg_dump_tm_pg(struct hclge_dev *hdev)
+static int hclge_dbg_dump_dcb_tm(struct hclge_dev *hdev, char *buf, int len,
+				 int *pos)
 {
-	struct hclge_port_shapping_cmd *port_shap_cfg_cmd;
-	struct hclge_bp_to_qs_map_cmd *bp_to_qs_map_cmd;
-	struct hclge_pg_shapping_cmd *pg_shap_cfg_cmd;
-	enum hclge_opcode_type cmd;
-	struct hclge_desc desc;
+	struct hclge_desc desc[2];
+	u8 port_id = 0;
 	int ret;
 
-	cmd = HCLGE_OPC_TM_PG_C_SHAPPING;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	ret = hclge_dbg_cmd_send(hdev, desc, port_id, 1,
+				 HCLGE_OPC_TM_INTERNAL_CNT);
 	if (ret)
-		goto err_tm_pg_cmd_send;
+		return ret;
 
-	pg_shap_cfg_cmd = (struct hclge_pg_shapping_cmd *)desc.data;
-	dev_info(&hdev->pdev->dev, "PG_C pg_id: %u\n", pg_shap_cfg_cmd->pg_id);
-	dev_info(&hdev->pdev->dev, "PG_C pg_shapping: 0x%x\n",
-		 le32_to_cpu(pg_shap_cfg_cmd->pg_shapping_para));
+	*pos += scnprintf(buf + *pos, len - *pos, "SCH_NIC_NUM: %#x\n",
+			  le32_to_cpu(desc[0].data[1]));
+	*pos += scnprintf(buf + *pos, len - *pos, "SCH_ROCE_NUM: %#x\n",
+			  le32_to_cpu(desc[0].data[2]));
 
-	cmd = HCLGE_OPC_TM_PG_P_SHAPPING;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	ret = hclge_dbg_cmd_send(hdev, desc, port_id, 2,
+				 HCLGE_OPC_TM_INTERNAL_STS);
 	if (ret)
-		goto err_tm_pg_cmd_send;
-
-	pg_shap_cfg_cmd = (struct hclge_pg_shapping_cmd *)desc.data;
-	dev_info(&hdev->pdev->dev, "PG_P pg_id: %u\n", pg_shap_cfg_cmd->pg_id);
-	dev_info(&hdev->pdev->dev, "PG_P pg_shapping: 0x%x\n",
-		 le32_to_cpu(pg_shap_cfg_cmd->pg_shapping_para));
-	dev_info(&hdev->pdev->dev, "PG_P flag: %#x\n", pg_shap_cfg_cmd->flag);
-	dev_info(&hdev->pdev->dev, "PG_P pg_rate: %u(Mbps)\n",
-		 le32_to_cpu(pg_shap_cfg_cmd->pg_rate));
-
-	cmd = HCLGE_OPC_TM_PORT_SHAPPING;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+		return ret;
+
+	*pos += scnprintf(buf + *pos, len - *pos, "pri_bp: %#x\n",
+			  le32_to_cpu(desc[0].data[1]));
+	*pos += scnprintf(buf + *pos, len - *pos, "fifo_dfx_info: %#x\n",
+			  le32_to_cpu(desc[0].data[2]));
+	*pos += scnprintf(buf + *pos, len - *pos,
+			  "sch_roce_fifo_afull_gap: %#x\n",
+			  le32_to_cpu(desc[0].data[3]));
+	*pos += scnprintf(buf + *pos, len - *pos,
+			  "tx_private_waterline: %#x\n",
+			  le32_to_cpu(desc[0].data[4]));
+	*pos += scnprintf(buf + *pos, len - *pos, "tm_bypass_en: %#x\n",
+			  le32_to_cpu(desc[0].data[5]));
+	*pos += scnprintf(buf + *pos, len - *pos, "SSU_TM_BYPASS_EN: %#x\n",
+			  le32_to_cpu(desc[1].data[0]));
+	*pos += scnprintf(buf + *pos, len - *pos, "SSU_RESERVE_CFG: %#x\n",
+			  le32_to_cpu(desc[1].data[1]));
+
+	if (hdev->hw.mac.media_type == HNAE3_MEDIA_TYPE_COPPER)
+		return 0;
+
+	ret = hclge_dbg_cmd_send(hdev, desc, port_id, 1,
+				 HCLGE_OPC_TM_INTERNAL_STS_1);
 	if (ret)
-		goto err_tm_pg_cmd_send;
+		return ret;
 
-	port_shap_cfg_cmd = (struct hclge_port_shapping_cmd *)desc.data;
-	dev_info(&hdev->pdev->dev, "PORT port_shapping: 0x%x\n",
-		 le32_to_cpu(port_shap_cfg_cmd->port_shapping_para));
-	dev_info(&hdev->pdev->dev, "PORT flag: %#x\n", port_shap_cfg_cmd->flag);
-	dev_info(&hdev->pdev->dev, "PORT port_rate: %u(Mbps)\n",
-		 le32_to_cpu(port_shap_cfg_cmd->port_rate));
+	*pos += scnprintf(buf + *pos, len - *pos, "TC_MAP_SEL: %#x\n",
+			  le32_to_cpu(desc[0].data[1]));
+	*pos += scnprintf(buf + *pos, len - *pos, "IGU_PFC_PRI_EN: %#x\n",
+			  le32_to_cpu(desc[0].data[2]));
+	*pos += scnprintf(buf + *pos, len - *pos, "MAC_PFC_PRI_EN: %#x\n",
+			  le32_to_cpu(desc[0].data[3]));
+	*pos += scnprintf(buf + *pos, len - *pos, "IGU_PRI_MAP_TC_CFG: %#x\n",
+			  le32_to_cpu(desc[0].data[4]));
+	*pos += scnprintf(buf + *pos, len - *pos,
+			  "IGU_TX_PRI_MAP_TC_CFG: %#x\n",
+			  le32_to_cpu(desc[0].data[5]));
 
-	cmd = HCLGE_OPC_TM_PG_SCH_MODE_CFG;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	return 0;
+}
+
+static int hclge_dbg_dump_dcb(struct hclge_dev *hdev, char *buf, int len)
+{
+	int pos = 0;
+	int ret;
+
+	ret = hclge_dbg_dump_dcb_qset(hdev, buf, len, &pos);
 	if (ret)
-		goto err_tm_pg_cmd_send;
+		return ret;
 
-	dev_info(&hdev->pdev->dev, "PG_SCH pg_id: %u\n",
-		 le32_to_cpu(desc.data[0]));
+	ret = hclge_dbg_dump_dcb_pri(hdev, buf, len, &pos);
+	if (ret)
+		return ret;
 
-	cmd = HCLGE_OPC_TM_PRI_SCH_MODE_CFG;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	ret = hclge_dbg_dump_dcb_pg(hdev, buf, len, &pos);
 	if (ret)
-		goto err_tm_pg_cmd_send;
+		return ret;
 
-	dev_info(&hdev->pdev->dev, "PRI_SCH pri_id: %u\n",
-		 le32_to_cpu(desc.data[0]));
+	ret = hclge_dbg_dump_dcb_queue(hdev, buf, len, &pos);
+	if (ret)
+		return ret;
 
-	cmd = HCLGE_OPC_TM_QS_SCH_MODE_CFG;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	ret = hclge_dbg_dump_dcb_port(hdev, buf, len, &pos);
 	if (ret)
-		goto err_tm_pg_cmd_send;
+		return ret;
 
-	dev_info(&hdev->pdev->dev, "QS_SCH qs_id: %u\n",
-		 le32_to_cpu(desc.data[0]));
+	return hclge_dbg_dump_dcb_tm(hdev, buf, len, &pos);
+}
 
-	if (!hnae3_dev_dcb_supported(hdev)) {
-		dev_info(&hdev->pdev->dev,
-			 "Only DCB-supported dev supports tm mapping\n");
-		return;
+static int hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev,
+				  enum hnae3_dbg_cmd cmd, char *buf, int len)
+{
+	const struct hclge_dbg_reg_type_info *reg_info;
+	int pos = 0, ret = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(hclge_dbg_reg_info); i++) {
+		reg_info = &hclge_dbg_reg_info[i];
+		if (cmd == reg_info->cmd) {
+			if (cmd == HNAE3_DBG_CMD_REG_TQP)
+				return hclge_dbg_dump_reg_tqp(hdev, reg_info,
+							      buf, len, &pos);
+
+			ret = hclge_dbg_dump_reg_common(hdev, reg_info, buf,
+							len, &pos);
+			if (ret)
+				break;
+		}
 	}
 
-	cmd = HCLGE_OPC_TM_BP_TO_QSET_MAPPING;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
-		goto err_tm_pg_cmd_send;
-
-	bp_to_qs_map_cmd = (struct hclge_bp_to_qs_map_cmd *)desc.data;
-	dev_info(&hdev->pdev->dev, "BP_TO_QSET tc_id: %u\n",
-		 bp_to_qs_map_cmd->tc_id);
-	dev_info(&hdev->pdev->dev, "BP_TO_QSET qs_group_id: 0x%x\n",
-		 bp_to_qs_map_cmd->qs_group_id);
-	dev_info(&hdev->pdev->dev, "BP_TO_QSET qs_bit_map: 0x%x\n",
-		 le32_to_cpu(bp_to_qs_map_cmd->qs_bit_map));
-	return;
-
-err_tm_pg_cmd_send:
-	dev_err(&hdev->pdev->dev, "dump tm_pg fail(0x%x), ret = %d\n",
-		cmd, ret);
+	return ret;
 }
 
-static void hclge_dbg_dump_tm(struct hclge_dev *hdev)
+static int hclge_dbg_dump_tc(struct hclge_dev *hdev, char *buf, int len)
 {
-	struct hclge_priority_weight_cmd *priority_weight;
-	struct hclge_pg_to_pri_link_cmd *pg_to_pri_map;
-	struct hclge_qs_to_pri_link_cmd *qs_to_pri_map;
-	struct hclge_nq_to_qs_link_cmd *nq_to_qs_map;
-	struct hclge_pri_shapping_cmd *shap_cfg_cmd;
-	struct hclge_pg_weight_cmd *pg_weight;
-	struct hclge_qs_weight_cmd *qs_weight;
-	enum hclge_opcode_type cmd;
+	struct hclge_ets_tc_weight_cmd *ets_weight;
 	struct hclge_desc desc;
+	char *sch_mode_str;
+	int pos = 0;
 	int ret;
+	u8 i;
 
-	cmd = HCLGE_OPC_TM_PG_TO_PRI_LINK;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	if (!hnae3_dev_dcb_supported(hdev)) {
+		dev_err(&hdev->pdev->dev,
+			"Only DCB-supported dev supports tc\n");
+		return -EOPNOTSUPP;
+	}
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_ETS_TC_WEIGHT, true);
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
-		goto err_tm_cmd_send;
+	if (ret) {
+		dev_err(&hdev->pdev->dev, "failed to get tc weight, ret = %d\n",
+			ret);
+		return ret;
+	}
 
-	pg_to_pri_map = (struct hclge_pg_to_pri_link_cmd *)desc.data;
-	dev_info(&hdev->pdev->dev, "dump tm\n");
-	dev_info(&hdev->pdev->dev, "PG_TO_PRI gp_id: %u\n",
-		 pg_to_pri_map->pg_id);
-	dev_info(&hdev->pdev->dev, "PG_TO_PRI map: 0x%x\n",
-		 pg_to_pri_map->pri_bit_map);
+	ets_weight = (struct hclge_ets_tc_weight_cmd *)desc.data;
 
-	cmd = HCLGE_OPC_TM_QS_TO_PRI_LINK;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
-		goto err_tm_cmd_send;
-
-	qs_to_pri_map = (struct hclge_qs_to_pri_link_cmd *)desc.data;
-	dev_info(&hdev->pdev->dev, "QS_TO_PRI qs_id: %u\n",
-		 le16_to_cpu(qs_to_pri_map->qs_id));
-	dev_info(&hdev->pdev->dev, "QS_TO_PRI priority: %u\n",
-		 qs_to_pri_map->priority);
-	dev_info(&hdev->pdev->dev, "QS_TO_PRI link_vld: %u\n",
-		 qs_to_pri_map->link_vld);
-
-	cmd = HCLGE_OPC_TM_NQ_TO_QS_LINK;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
-		goto err_tm_cmd_send;
+	pos += scnprintf(buf + pos, len - pos, "enabled tc number: %u\n",
+			 hdev->tm_info.num_tc);
+	pos += scnprintf(buf + pos, len - pos, "weight_offset: %u\n",
+			 ets_weight->weight_offset);
+
+	pos += scnprintf(buf + pos, len - pos, "TC    MODE  WEIGHT\n");
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
+		sch_mode_str = ets_weight->tc_weight[i] ? "dwrr" : "sp";
+		pos += scnprintf(buf + pos, len - pos, "%u     %4s    %3u\n",
+				 i, sch_mode_str,
+				 hdev->tm_info.pg_info[0].tc_dwrr[i]);
+	}
 
-	nq_to_qs_map = (struct hclge_nq_to_qs_link_cmd *)desc.data;
-	dev_info(&hdev->pdev->dev, "NQ_TO_QS nq_id: %u\n",
-		 le16_to_cpu(nq_to_qs_map->nq_id));
-	dev_info(&hdev->pdev->dev, "NQ_TO_QS qset_id: 0x%x\n",
-		 le16_to_cpu(nq_to_qs_map->qset_id));
+	return 0;
+}
 
-	cmd = HCLGE_OPC_TM_PG_WEIGHT;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
-		goto err_tm_cmd_send;
+static const struct hclge_dbg_item tm_pg_items[] = {
+	{ "ID", 2 },
+	{ "PRI_MAP", 2 },
+	{ "MODE", 2 },
+	{ "DWRR", 2 },
+	{ "C_IR_B", 2 },
+	{ "C_IR_U", 2 },
+	{ "C_IR_S", 2 },
+	{ "C_BS_B", 2 },
+	{ "C_BS_S", 2 },
+	{ "C_FLAG", 2 },
+	{ "C_RATE(Mbps)", 2 },
+	{ "P_IR_B", 2 },
+	{ "P_IR_U", 2 },
+	{ "P_IR_S", 2 },
+	{ "P_BS_B", 2 },
+	{ "P_BS_S", 2 },
+	{ "P_FLAG", 2 },
+	{ "P_RATE(Mbps)", 0 }
+};
 
-	pg_weight = (struct hclge_pg_weight_cmd *)desc.data;
-	dev_info(&hdev->pdev->dev, "PG pg_id: %u\n", pg_weight->pg_id);
-	dev_info(&hdev->pdev->dev, "PG dwrr: %u\n", pg_weight->dwrr);
+static void hclge_dbg_fill_shaper_content(struct hclge_tm_shaper_para *para,
+					  char **result, u8 *index)
+{
+	sprintf(result[(*index)++], "%3u", para->ir_b);
+	sprintf(result[(*index)++], "%3u", para->ir_u);
+	sprintf(result[(*index)++], "%3u", para->ir_s);
+	sprintf(result[(*index)++], "%3u", para->bs_b);
+	sprintf(result[(*index)++], "%3u", para->bs_s);
+	sprintf(result[(*index)++], "%3u", para->flag);
+	sprintf(result[(*index)++], "%6u", para->rate);
+}
 
-	cmd = HCLGE_OPC_TM_QS_WEIGHT;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
-		goto err_tm_cmd_send;
+static int hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *buf, int len)
+{
+	char data_str[ARRAY_SIZE(tm_pg_items)][HCLGE_DBG_DATA_STR_LEN];
+	struct hclge_tm_shaper_para c_shaper_para, p_shaper_para;
+	char *result[ARRAY_SIZE(tm_pg_items)], *sch_mode_str;
+	u8 pg_id, sch_mode, weight, pri_bit_map, i, j;
+	char content[HCLGE_DBG_TM_INFO_LEN];
+	int pos = 0;
+	int ret;
 
-	qs_weight = (struct hclge_qs_weight_cmd *)desc.data;
-	dev_info(&hdev->pdev->dev, "QS qs_id: %u\n",
-		 le16_to_cpu(qs_weight->qs_id));
-	dev_info(&hdev->pdev->dev, "QS dwrr: %u\n", qs_weight->dwrr);
+	for (i = 0; i < ARRAY_SIZE(tm_pg_items); i++)
+		result[i] = &data_str[i][0];
 
-	cmd = HCLGE_OPC_TM_PRI_WEIGHT;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
-		goto err_tm_cmd_send;
+	hclge_dbg_fill_content(content, sizeof(content), tm_pg_items,
+			       NULL, ARRAY_SIZE(tm_pg_items));
+	pos += scnprintf(buf + pos, len - pos, "%s", content);
 
-	priority_weight = (struct hclge_priority_weight_cmd *)desc.data;
-	dev_info(&hdev->pdev->dev, "PRI pri_id: %u\n", priority_weight->pri_id);
-	dev_info(&hdev->pdev->dev, "PRI dwrr: %u\n", priority_weight->dwrr);
+	for (pg_id = 0; pg_id < hdev->tm_info.num_pg; pg_id++) {
+		ret = hclge_tm_get_pg_to_pri_map(hdev, pg_id, &pri_bit_map);
+		if (ret)
+			return ret;
 
-	cmd = HCLGE_OPC_TM_PRI_C_SHAPPING;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
-		goto err_tm_cmd_send;
-
-	shap_cfg_cmd = (struct hclge_pri_shapping_cmd *)desc.data;
-	dev_info(&hdev->pdev->dev, "PRI_C pri_id: %u\n", shap_cfg_cmd->pri_id);
-	dev_info(&hdev->pdev->dev, "PRI_C pri_shapping: 0x%x\n",
-		 le32_to_cpu(shap_cfg_cmd->pri_shapping_para));
-	dev_info(&hdev->pdev->dev, "PRI_C flag: %#x\n", shap_cfg_cmd->flag);
-	dev_info(&hdev->pdev->dev, "PRI_C pri_rate: %u(Mbps)\n",
-		 le32_to_cpu(shap_cfg_cmd->pri_rate));
-
-	cmd = HCLGE_OPC_TM_PRI_P_SHAPPING;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
-		goto err_tm_cmd_send;
+		ret = hclge_tm_get_pg_sch_mode(hdev, pg_id, &sch_mode);
+		if (ret)
+			return ret;
 
-	shap_cfg_cmd = (struct hclge_pri_shapping_cmd *)desc.data;
-	dev_info(&hdev->pdev->dev, "PRI_P pri_id: %u\n", shap_cfg_cmd->pri_id);
-	dev_info(&hdev->pdev->dev, "PRI_P pri_shapping: 0x%x\n",
-		 le32_to_cpu(shap_cfg_cmd->pri_shapping_para));
-	dev_info(&hdev->pdev->dev, "PRI_P flag: %#x\n", shap_cfg_cmd->flag);
-	dev_info(&hdev->pdev->dev, "PRI_P pri_rate: %u(Mbps)\n",
-		 le32_to_cpu(shap_cfg_cmd->pri_rate));
+		ret = hclge_tm_get_pg_weight(hdev, pg_id, &weight);
+		if (ret)
+			return ret;
 
-	hclge_dbg_dump_tm_pg(hdev);
+		ret = hclge_tm_get_pg_shaper(hdev, pg_id,
+					     HCLGE_OPC_TM_PG_C_SHAPPING,
+					     &c_shaper_para);
+		if (ret)
+			return ret;
 
-	return;
+		ret = hclge_tm_get_pg_shaper(hdev, pg_id,
+					     HCLGE_OPC_TM_PG_P_SHAPPING,
+					     &p_shaper_para);
+		if (ret)
+			return ret;
 
-err_tm_cmd_send:
-	dev_err(&hdev->pdev->dev, "dump tm fail(0x%x), ret = %d\n",
-		cmd, ret);
+		sch_mode_str = sch_mode & HCLGE_TM_TX_SCHD_DWRR_MSK ? "dwrr" :
+				       "sp";
+
+		j = 0;
+		sprintf(result[j++], "%02u", pg_id);
+		sprintf(result[j++], "0x%02x", pri_bit_map);
+		sprintf(result[j++], "%4s", sch_mode_str);
+		sprintf(result[j++], "%3u", weight);
+		hclge_dbg_fill_shaper_content(&c_shaper_para, result, &j);
+		hclge_dbg_fill_shaper_content(&p_shaper_para, result, &j);
+
+		hclge_dbg_fill_content(content, sizeof(content), tm_pg_items,
+				       (const char **)result,
+				       ARRAY_SIZE(tm_pg_items));
+		pos += scnprintf(buf + pos, len - pos, "%s", content);
+	}
+
+	return 0;
 }
 
-static void hclge_dbg_dump_tm_map(struct hclge_dev *hdev,
-				  const char *cmd_buf)
+static int hclge_dbg_dump_tm_port(struct hclge_dev *hdev,  char *buf, int len)
 {
-	struct hclge_bp_to_qs_map_cmd *bp_to_qs_map_cmd;
-	struct hclge_nq_to_qs_link_cmd *nq_to_qs_map;
-	u32 qset_mapping[HCLGE_BP_EXT_GRP_NUM];
-	struct hclge_qs_to_pri_link_cmd *map;
-	struct hclge_tqp_tx_queue_tc_cmd *tc;
-	u16 group_id, queue_id, qset_id;
-	enum hclge_opcode_type cmd;
-	u8 grp_num, pri_id, tc_id;
-	struct hclge_desc desc;
-	u16 qs_id_l;
-	u16 qs_id_h;
+	struct hclge_tm_shaper_para shaper_para;
+	int pos = 0;
 	int ret;
-	u32 i;
 
-	ret = kstrtou16(cmd_buf, 0, &queue_id);
-	queue_id = (ret != 0) ? 0 : queue_id;
-
-	cmd = HCLGE_OPC_TM_NQ_TO_QS_LINK;
-	nq_to_qs_map = (struct hclge_nq_to_qs_link_cmd *)desc.data;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	nq_to_qs_map->nq_id = cpu_to_le16(queue_id);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	ret = hclge_tm_get_port_shaper(hdev, &shaper_para);
 	if (ret)
-		goto err_tm_map_cmd_send;
-	qset_id = le16_to_cpu(nq_to_qs_map->qset_id);
-
-	/* convert qset_id to the following format, drop the vld bit
-	 *            | qs_id_h | vld | qs_id_l |
-	 * qset_id:   | 15 ~ 11 |  10 |  9 ~ 0  |
-	 *             \         \   /         /
-	 *              \         \ /         /
-	 * qset_id: | 15 | 14 ~ 10 |  9 ~ 0  |
-	 */
-	qs_id_l = hnae3_get_field(qset_id, HCLGE_TM_QS_ID_L_MSK,
-				  HCLGE_TM_QS_ID_L_S);
-	qs_id_h = hnae3_get_field(qset_id, HCLGE_TM_QS_ID_H_EXT_MSK,
-				  HCLGE_TM_QS_ID_H_EXT_S);
-	qset_id = 0;
-	hnae3_set_field(qset_id, HCLGE_TM_QS_ID_L_MSK, HCLGE_TM_QS_ID_L_S,
-			qs_id_l);
-	hnae3_set_field(qset_id, HCLGE_TM_QS_ID_H_MSK, HCLGE_TM_QS_ID_H_S,
-			qs_id_h);
-
-	cmd = HCLGE_OPC_TM_QS_TO_PRI_LINK;
-	map = (struct hclge_qs_to_pri_link_cmd *)desc.data;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	map->qs_id = cpu_to_le16(qset_id);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
-		goto err_tm_map_cmd_send;
-	pri_id = map->priority;
+		return ret;
 
-	cmd = HCLGE_OPC_TQP_TX_QUEUE_TC;
-	tc = (struct hclge_tqp_tx_queue_tc_cmd *)desc.data;
-	hclge_cmd_setup_basic_desc(&desc, cmd, true);
-	tc->queue_id = cpu_to_le16(queue_id);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
-		goto err_tm_map_cmd_send;
-	tc_id = tc->tc_id & 0x7;
+	pos += scnprintf(buf + pos, len - pos,
+			 "IR_B  IR_U  IR_S  BS_B  BS_S  FLAG  RATE(Mbps)\n");
+	pos += scnprintf(buf + pos, len - pos,
+			 "%3u   %3u   %3u   %3u   %3u     %1u   %6u\n",
+			 shaper_para.ir_b, shaper_para.ir_u, shaper_para.ir_s,
+			 shaper_para.bs_b, shaper_para.bs_s, shaper_para.flag,
+			 shaper_para.rate);
 
-	dev_info(&hdev->pdev->dev, "queue_id | qset_id | pri_id | tc_id\n");
-	dev_info(&hdev->pdev->dev, "%04u     | %04u    | %02u     | %02u\n",
-		 queue_id, qset_id, pri_id, tc_id);
+	return 0;
+}
 
-	if (!hnae3_dev_dcb_supported(hdev)) {
-		dev_info(&hdev->pdev->dev,
-			 "Only DCB-supported dev supports tm mapping\n");
-		return;
-	}
+static int hclge_dbg_dump_tm_bp_qset_map(struct hclge_dev *hdev, u8 tc_id,
+					 char *buf, int len)
+{
+	u32 qset_mapping[HCLGE_BP_EXT_GRP_NUM];
+	struct hclge_bp_to_qs_map_cmd *map;
+	struct hclge_desc desc;
+	int pos = 0;
+	u8 group_id;
+	u8 grp_num;
+	u16 i = 0;
+	int ret;
 
 	grp_num = hdev->num_tqps <= HCLGE_TQP_MAX_SIZE_DEV_V2 ?
 		  HCLGE_BP_GRP_NUM : HCLGE_BP_EXT_GRP_NUM;
-	cmd = HCLGE_OPC_TM_BP_TO_QSET_MAPPING;
-	bp_to_qs_map_cmd = (struct hclge_bp_to_qs_map_cmd *)desc.data;
+	map = (struct hclge_bp_to_qs_map_cmd *)desc.data;
 	for (group_id = 0; group_id < grp_num; group_id++) {
-		hclge_cmd_setup_basic_desc(&desc, cmd, true);
-		bp_to_qs_map_cmd->tc_id = tc_id;
-		bp_to_qs_map_cmd->qs_group_id = group_id;
+		hclge_cmd_setup_basic_desc(&desc,
+					   HCLGE_OPC_TM_BP_TO_QSET_MAPPING,
+					   true);
+		map->tc_id = tc_id;
+		map->qs_group_id = group_id;
 		ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-		if (ret)
-			goto err_tm_map_cmd_send;
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"failed to get bp to qset map, ret = %d\n",
+				ret);
+			return ret;
+		}
 
-		qset_mapping[group_id] =
-			le32_to_cpu(bp_to_qs_map_cmd->qs_bit_map);
+		qset_mapping[group_id] = le32_to_cpu(map->qs_bit_map);
 	}
 
-	dev_info(&hdev->pdev->dev, "index | tm bp qset maping:\n");
-
-	i = 0;
+	pos += scnprintf(buf + pos, len - pos, "INDEX | TM BP QSET MAPPING:\n");
 	for (group_id = 0; group_id < grp_num / 8; group_id++) {
-		dev_info(&hdev->pdev->dev,
+		pos += scnprintf(buf + pos, len - pos,
 			 "%04d  | %08x:%08x:%08x:%08x:%08x:%08x:%08x:%08x\n",
-			 group_id * 256, qset_mapping[(u32)(i + 7)],
-			 qset_mapping[(u32)(i + 6)], qset_mapping[(u32)(i + 5)],
-			 qset_mapping[(u32)(i + 4)], qset_mapping[(u32)(i + 3)],
-			 qset_mapping[(u32)(i + 2)], qset_mapping[(u32)(i + 1)],
+			 group_id * 256, qset_mapping[i + 7],
+			 qset_mapping[i + 6], qset_mapping[i + 5],
+			 qset_mapping[i + 4], qset_mapping[i + 3],
+			 qset_mapping[i + 2], qset_mapping[i + 1],
 			 qset_mapping[i]);
 		i += 8;
 	}
 
-	return;
+	return pos;
+}
+
+static int hclge_dbg_dump_tm_map(struct hclge_dev *hdev, char *buf, int len)
+{
+	u16 queue_id;
+	u16 qset_id;
+	u8 link_vld;
+	int pos = 0;
+	u8 pri_id;
+	u8 tc_id;
+	int ret;
+
+	for (queue_id = 0; queue_id < hdev->num_tqps; queue_id++) {
+		ret = hclge_tm_get_q_to_qs_map(hdev, queue_id, &qset_id);
+		if (ret)
+			return ret;
+
+		ret = hclge_tm_get_qset_map_pri(hdev, qset_id, &pri_id,
+						&link_vld);
+		if (ret)
+			return ret;
+
+		ret = hclge_tm_get_q_to_tc(hdev, queue_id, &tc_id);
+		if (ret)
+			return ret;
+
+		pos += scnprintf(buf + pos, len - pos,
+				 "QUEUE_ID   QSET_ID   PRI_ID   TC_ID\n");
+		pos += scnprintf(buf + pos, len - pos,
+				 "%04u        %4u       %3u      %2u\n",
+				 queue_id, qset_id, pri_id, tc_id);
+
+		if (!hnae3_dev_dcb_supported(hdev))
+			continue;
+
+		ret = hclge_dbg_dump_tm_bp_qset_map(hdev, tc_id, buf + pos,
+						    len - pos);
+		if (ret < 0)
+			return ret;
+		pos += ret;
 
-err_tm_map_cmd_send:
-	dev_err(&hdev->pdev->dev, "dump tqp map fail(0x%x), ret = %d\n",
-		cmd, ret);
+		pos += scnprintf(buf + pos, len - pos, "\n");
+	}
+
+	return 0;
 }
 
 static int hclge_dbg_dump_tm_nodes(struct hclge_dev *hdev, char *buf, int len)
@@ -833,8 +928,8 @@ static int hclge_dbg_dump_tm_nodes(struct hclge_dev *hdev, char *buf, int len)
 
 static int hclge_dbg_dump_tm_pri(struct hclge_dev *hdev, char *buf, int len)
 {
-	struct hclge_pri_shaper_para c_shaper_para;
-	struct hclge_pri_shaper_para p_shaper_para;
+	struct hclge_tm_shaper_para c_shaper_para;
+	struct hclge_tm_shaper_para p_shaper_para;
 	u8 pri_num, sch_mode, weight;
 	char *sch_mode_str;
 	int pos = 0;
@@ -896,19 +991,42 @@ static int hclge_dbg_dump_tm_pri(struct hclge_dev *hdev, char *buf, int len)
 	return 0;
 }
 
+static const struct hclge_dbg_item tm_qset_items[] = {
+	{ "ID", 4 },
+	{ "MAP_PRI", 2 },
+	{ "LINK_VLD", 2 },
+	{ "MODE", 2 },
+	{ "DWRR", 2 },
+	{ "IR_B", 2 },
+	{ "IR_U", 2 },
+	{ "IR_S", 2 },
+	{ "BS_B", 2 },
+	{ "BS_S", 2 },
+	{ "FLAG", 2 },
+	{ "RATE(Mbps)", 0 }
+};
+
 static int hclge_dbg_dump_tm_qset(struct hclge_dev *hdev, char *buf, int len)
 {
+	char data_str[ARRAY_SIZE(tm_qset_items)][HCLGE_DBG_DATA_STR_LEN];
+	char *result[ARRAY_SIZE(tm_qset_items)], *sch_mode_str;
 	u8 priority, link_vld, sch_mode, weight;
-	char *sch_mode_str;
+	struct hclge_tm_shaper_para shaper_para;
+	char content[HCLGE_DBG_TM_INFO_LEN];
+	u16 qset_num, i;
 	int ret, pos;
-	u16 qset_num;
-	u16 i;
+	u8 j;
 
 	ret = hclge_tm_get_qset_num(hdev, &qset_num);
 	if (ret)
 		return ret;
 
-	pos = scnprintf(buf, len, "ID    MAP_PRI  LINK_VLD  MODE  DWRR\n");
+	for (i = 0; i < ARRAY_SIZE(tm_qset_items); i++)
+		result[i] = &data_str[i][0];
+
+	hclge_dbg_fill_content(content, sizeof(content), tm_qset_items,
+			       NULL, ARRAY_SIZE(tm_qset_items));
+	pos = scnprintf(buf, len, "%s", content);
 
 	for (i = 0; i < qset_num; i++) {
 		ret = hclge_tm_get_qset_map_pri(hdev, i, &priority, &link_vld);
@@ -923,280 +1041,326 @@ static int hclge_dbg_dump_tm_qset(struct hclge_dev *hdev, char *buf, int len)
 		if (ret)
 			return ret;
 
+		ret = hclge_tm_get_qset_shaper(hdev, i, &shaper_para);
+		if (ret)
+			return ret;
+
 		sch_mode_str = sch_mode & HCLGE_TM_TX_SCHD_DWRR_MSK ? "dwrr" :
 			       "sp";
-		pos += scnprintf(buf + pos, len - pos,
-				 "%04u  %4u        %1u      %4s  %3u\n",
-				 i, priority, link_vld, sch_mode_str, weight);
+
+		j = 0;
+		sprintf(result[j++], "%04u", i);
+		sprintf(result[j++], "%4u", priority);
+		sprintf(result[j++], "%4u", link_vld);
+		sprintf(result[j++], "%4s", sch_mode_str);
+		sprintf(result[j++], "%3u", weight);
+		hclge_dbg_fill_shaper_content(&shaper_para, result, &j);
+
+		hclge_dbg_fill_content(content, sizeof(content), tm_qset_items,
+				       (const char **)result,
+				       ARRAY_SIZE(tm_qset_items));
+		pos += scnprintf(buf + pos, len - pos, "%s", content);
 	}
 
 	return 0;
 }
 
-static void hclge_dbg_dump_qos_pause_cfg(struct hclge_dev *hdev)
+static int hclge_dbg_dump_qos_pause_cfg(struct hclge_dev *hdev, char *buf,
+					int len)
 {
 	struct hclge_cfg_pause_param_cmd *pause_param;
 	struct hclge_desc desc;
+	int pos = 0;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_MAC_PARA, true);
-
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
-		dev_err(&hdev->pdev->dev, "dump checksum fail, ret = %d\n",
-			ret);
-		return;
+		dev_err(&hdev->pdev->dev,
+			"failed to dump qos pause, ret = %d\n", ret);
+		return ret;
 	}
 
 	pause_param = (struct hclge_cfg_pause_param_cmd *)desc.data;
-	dev_info(&hdev->pdev->dev, "dump qos pause cfg\n");
-	dev_info(&hdev->pdev->dev, "pause_trans_gap: 0x%x\n",
-		 pause_param->pause_trans_gap);
-	dev_info(&hdev->pdev->dev, "pause_trans_time: 0x%x\n",
-		 le16_to_cpu(pause_param->pause_trans_time));
+
+	pos += scnprintf(buf + pos, len - pos, "pause_trans_gap: 0x%x\n",
+			 pause_param->pause_trans_gap);
+	pos += scnprintf(buf + pos, len - pos, "pause_trans_time: 0x%x\n",
+			 le16_to_cpu(pause_param->pause_trans_time));
+	return 0;
 }
 
-static void hclge_dbg_dump_qos_pri_map(struct hclge_dev *hdev)
+static int hclge_dbg_dump_qos_pri_map(struct hclge_dev *hdev, char *buf,
+				      int len)
 {
+#define HCLGE_DBG_TC_MASK		0x0F
+#define HCLGE_DBG_TC_BIT_WIDTH		4
+
 	struct hclge_qos_pri_map_cmd *pri_map;
 	struct hclge_desc desc;
+	int pos = 0;
+	u8 *pri_tc;
+	u8 tc, i;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PRI_TO_TC_MAPPING, true);
-
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
-			"dump qos pri map fail, ret = %d\n", ret);
-		return;
+			"failed to dump qos pri map, ret = %d\n", ret);
+		return ret;
 	}
 
 	pri_map = (struct hclge_qos_pri_map_cmd *)desc.data;
-	dev_info(&hdev->pdev->dev, "dump qos pri map\n");
-	dev_info(&hdev->pdev->dev, "vlan_to_pri: 0x%x\n", pri_map->vlan_pri);
-	dev_info(&hdev->pdev->dev, "pri_0_to_tc: 0x%x\n", pri_map->pri0_tc);
-	dev_info(&hdev->pdev->dev, "pri_1_to_tc: 0x%x\n", pri_map->pri1_tc);
-	dev_info(&hdev->pdev->dev, "pri_2_to_tc: 0x%x\n", pri_map->pri2_tc);
-	dev_info(&hdev->pdev->dev, "pri_3_to_tc: 0x%x\n", pri_map->pri3_tc);
-	dev_info(&hdev->pdev->dev, "pri_4_to_tc: 0x%x\n", pri_map->pri4_tc);
-	dev_info(&hdev->pdev->dev, "pri_5_to_tc: 0x%x\n", pri_map->pri5_tc);
-	dev_info(&hdev->pdev->dev, "pri_6_to_tc: 0x%x\n", pri_map->pri6_tc);
-	dev_info(&hdev->pdev->dev, "pri_7_to_tc: 0x%x\n", pri_map->pri7_tc);
+
+	pos += scnprintf(buf + pos, len - pos, "vlan_to_pri: 0x%x\n",
+			 pri_map->vlan_pri);
+	pos += scnprintf(buf + pos, len - pos, "PRI  TC\n");
+
+	pri_tc = (u8 *)pri_map;
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
+		tc = pri_tc[i >> 1] >> ((i & 1) * HCLGE_DBG_TC_BIT_WIDTH);
+		tc &= HCLGE_DBG_TC_MASK;
+		pos += scnprintf(buf + pos, len - pos, "%u     %u\n", i, tc);
+	}
+
+	return 0;
 }
 
-static int hclge_dbg_dump_tx_buf_cfg(struct hclge_dev *hdev)
+static int hclge_dbg_dump_tx_buf_cfg(struct hclge_dev *hdev, char *buf, int len)
 {
 	struct hclge_tx_buff_alloc_cmd *tx_buf_cmd;
 	struct hclge_desc desc;
+	int pos = 0;
 	int i, ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, true);
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to dump tx buf, ret = %d\n", ret);
 		return ret;
+	}
 
-	dev_info(&hdev->pdev->dev, "dump qos buf cfg\n");
 	tx_buf_cmd = (struct hclge_tx_buff_alloc_cmd *)desc.data;
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++)
-		dev_info(&hdev->pdev->dev, "tx_packet_buf_tc_%d: 0x%x\n", i,
-			 le16_to_cpu(tx_buf_cmd->tx_pkt_buff[i]));
+		pos += scnprintf(buf + pos, len - pos,
+				 "tx_packet_buf_tc_%d: 0x%x\n", i,
+				 le16_to_cpu(tx_buf_cmd->tx_pkt_buff[i]));
 
-	return 0;
+	return pos;
 }
 
-static int hclge_dbg_dump_rx_priv_buf_cfg(struct hclge_dev *hdev)
+static int hclge_dbg_dump_rx_priv_buf_cfg(struct hclge_dev *hdev, char *buf,
+					  int len)
 {
 	struct hclge_rx_priv_buff_cmd *rx_buf_cmd;
 	struct hclge_desc desc;
+	int pos = 0;
 	int i, ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RX_PRIV_BUFF_ALLOC, true);
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to dump rx priv buf, ret = %d\n", ret);
 		return ret;
+	}
+
+	pos += scnprintf(buf + pos, len - pos, "\n");
 
-	dev_info(&hdev->pdev->dev, "\n");
 	rx_buf_cmd = (struct hclge_rx_priv_buff_cmd *)desc.data;
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++)
-		dev_info(&hdev->pdev->dev, "rx_packet_buf_tc_%d: 0x%x\n", i,
-			 le16_to_cpu(rx_buf_cmd->buf_num[i]));
+		pos += scnprintf(buf + pos, len - pos,
+				 "rx_packet_buf_tc_%d: 0x%x\n", i,
+				 le16_to_cpu(rx_buf_cmd->buf_num[i]));
 
-	dev_info(&hdev->pdev->dev, "rx_share_buf: 0x%x\n",
-		 le16_to_cpu(rx_buf_cmd->shared_buf));
+	pos += scnprintf(buf + pos, len - pos, "rx_share_buf: 0x%x\n",
+			 le16_to_cpu(rx_buf_cmd->shared_buf));
 
-	return 0;
+	return pos;
 }
 
-static int hclge_dbg_dump_rx_common_wl_cfg(struct hclge_dev *hdev)
+static int hclge_dbg_dump_rx_common_wl_cfg(struct hclge_dev *hdev, char *buf,
+					   int len)
 {
 	struct hclge_rx_com_wl *rx_com_wl;
 	struct hclge_desc desc;
+	int pos = 0;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RX_COM_WL_ALLOC, true);
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to dump rx common wl, ret = %d\n", ret);
 		return ret;
+	}
 
 	rx_com_wl = (struct hclge_rx_com_wl *)desc.data;
-	dev_info(&hdev->pdev->dev, "\n");
-	dev_info(&hdev->pdev->dev, "rx_com_wl: high: 0x%x, low: 0x%x\n",
-		 le16_to_cpu(rx_com_wl->com_wl.high),
-		 le16_to_cpu(rx_com_wl->com_wl.low));
+	pos += scnprintf(buf + pos, len - pos, "\n");
+	pos += scnprintf(buf + pos, len - pos,
+			 "rx_com_wl: high: 0x%x, low: 0x%x\n",
+			 le16_to_cpu(rx_com_wl->com_wl.high),
+			 le16_to_cpu(rx_com_wl->com_wl.low));
 
-	return 0;
+	return pos;
 }
 
-static int hclge_dbg_dump_rx_global_pkt_cnt(struct hclge_dev *hdev)
+static int hclge_dbg_dump_rx_global_pkt_cnt(struct hclge_dev *hdev, char *buf,
+					    int len)
 {
 	struct hclge_rx_com_wl *rx_packet_cnt;
 	struct hclge_desc desc;
+	int pos = 0;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RX_GBL_PKT_CNT, true);
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to dump rx global pkt cnt, ret = %d\n", ret);
 		return ret;
+	}
 
 	rx_packet_cnt = (struct hclge_rx_com_wl *)desc.data;
-	dev_info(&hdev->pdev->dev,
-		 "rx_global_packet_cnt: high: 0x%x, low: 0x%x\n",
-		 le16_to_cpu(rx_packet_cnt->com_wl.high),
-		 le16_to_cpu(rx_packet_cnt->com_wl.low));
+	pos += scnprintf(buf + pos, len - pos,
+			 "rx_global_packet_cnt: high: 0x%x, low: 0x%x\n",
+			 le16_to_cpu(rx_packet_cnt->com_wl.high),
+			 le16_to_cpu(rx_packet_cnt->com_wl.low));
 
-	return 0;
+	return pos;
 }
 
-static int hclge_dbg_dump_rx_priv_wl_buf_cfg(struct hclge_dev *hdev)
+static int hclge_dbg_dump_rx_priv_wl_buf_cfg(struct hclge_dev *hdev, char *buf,
+					     int len)
 {
 	struct hclge_rx_priv_wl_buf *rx_priv_wl;
 	struct hclge_desc desc[2];
+	int pos = 0;
 	int i, ret;
 
 	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_RX_PRIV_WL_ALLOC, true);
 	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
 	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_RX_PRIV_WL_ALLOC, true);
 	ret = hclge_cmd_send(&hdev->hw, desc, 2);
-	if (ret)
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to dump rx priv wl buf, ret = %d\n", ret);
 		return ret;
+	}
 
 	rx_priv_wl = (struct hclge_rx_priv_wl_buf *)desc[0].data;
 	for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++)
-		dev_info(&hdev->pdev->dev,
+		pos += scnprintf(buf + pos, len - pos,
 			 "rx_priv_wl_tc_%d: high: 0x%x, low: 0x%x\n", i,
 			 le16_to_cpu(rx_priv_wl->tc_wl[i].high),
 			 le16_to_cpu(rx_priv_wl->tc_wl[i].low));
 
 	rx_priv_wl = (struct hclge_rx_priv_wl_buf *)desc[1].data;
 	for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++)
-		dev_info(&hdev->pdev->dev,
+		pos += scnprintf(buf + pos, len - pos,
 			 "rx_priv_wl_tc_%d: high: 0x%x, low: 0x%x\n",
 			 i + HCLGE_TC_NUM_ONE_DESC,
 			 le16_to_cpu(rx_priv_wl->tc_wl[i].high),
 			 le16_to_cpu(rx_priv_wl->tc_wl[i].low));
 
-	return 0;
+	return pos;
 }
 
-static int hclge_dbg_dump_rx_common_threshold_cfg(struct hclge_dev *hdev)
+static int hclge_dbg_dump_rx_common_threshold_cfg(struct hclge_dev *hdev,
+						  char *buf, int len)
 {
 	struct hclge_rx_com_thrd *rx_com_thrd;
 	struct hclge_desc desc[2];
+	int pos = 0;
 	int i, ret;
 
 	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_RX_COM_THRD_ALLOC, true);
 	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
 	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_RX_COM_THRD_ALLOC, true);
 	ret = hclge_cmd_send(&hdev->hw, desc, 2);
-	if (ret)
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to dump rx common threshold, ret = %d\n", ret);
 		return ret;
+	}
 
-	dev_info(&hdev->pdev->dev, "\n");
+	pos += scnprintf(buf + pos, len - pos, "\n");
 	rx_com_thrd = (struct hclge_rx_com_thrd *)desc[0].data;
 	for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++)
-		dev_info(&hdev->pdev->dev,
+		pos += scnprintf(buf + pos, len - pos,
 			 "rx_com_thrd_tc_%d: high: 0x%x, low: 0x%x\n", i,
 			 le16_to_cpu(rx_com_thrd->com_thrd[i].high),
 			 le16_to_cpu(rx_com_thrd->com_thrd[i].low));
 
 	rx_com_thrd = (struct hclge_rx_com_thrd *)desc[1].data;
 	for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++)
-		dev_info(&hdev->pdev->dev,
+		pos += scnprintf(buf + pos, len - pos,
 			 "rx_com_thrd_tc_%d: high: 0x%x, low: 0x%x\n",
 			 i + HCLGE_TC_NUM_ONE_DESC,
 			 le16_to_cpu(rx_com_thrd->com_thrd[i].high),
 			 le16_to_cpu(rx_com_thrd->com_thrd[i].low));
 
-	return 0;
+	return pos;
 }
 
-static void hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev)
+static int hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev, char *buf,
+				      int len)
 {
-	enum hclge_opcode_type cmd;
+	int pos = 0;
 	int ret;
 
-	cmd = HCLGE_OPC_TX_BUFF_ALLOC;
-	ret = hclge_dbg_dump_tx_buf_cfg(hdev);
-	if (ret)
-		goto err_qos_cmd_send;
-
-	cmd = HCLGE_OPC_RX_PRIV_BUFF_ALLOC;
-	ret = hclge_dbg_dump_rx_priv_buf_cfg(hdev);
-	if (ret)
-		goto err_qos_cmd_send;
+	ret = hclge_dbg_dump_tx_buf_cfg(hdev, buf + pos, len - pos);
+	if (ret < 0)
+		return ret;
+	pos += ret;
 
-	cmd = HCLGE_OPC_RX_COM_WL_ALLOC;
-	ret = hclge_dbg_dump_rx_common_wl_cfg(hdev);
-	if (ret)
-		goto err_qos_cmd_send;
+	ret = hclge_dbg_dump_rx_priv_buf_cfg(hdev, buf + pos, len - pos);
+	if (ret < 0)
+		return ret;
+	pos += ret;
 
-	cmd = HCLGE_OPC_RX_GBL_PKT_CNT;
-	ret = hclge_dbg_dump_rx_global_pkt_cnt(hdev);
-	if (ret)
-		goto err_qos_cmd_send;
+	ret = hclge_dbg_dump_rx_common_wl_cfg(hdev, buf + pos, len - pos);
+	if (ret < 0)
+		return ret;
+	pos += ret;
 
-	dev_info(&hdev->pdev->dev, "\n");
-	if (!hnae3_dev_dcb_supported(hdev)) {
-		dev_info(&hdev->pdev->dev,
-			 "Only DCB-supported dev supports rx priv wl\n");
-		return;
-	}
+	ret = hclge_dbg_dump_rx_global_pkt_cnt(hdev, buf + pos, len - pos);
+	if (ret < 0)
+		return ret;
+	pos += ret;
 
-	cmd = HCLGE_OPC_RX_PRIV_WL_ALLOC;
-	ret = hclge_dbg_dump_rx_priv_wl_buf_cfg(hdev);
-	if (ret)
-		goto err_qos_cmd_send;
+	pos += scnprintf(buf + pos, len - pos, "\n");
+	if (!hnae3_dev_dcb_supported(hdev))
+		return 0;
 
-	cmd = HCLGE_OPC_RX_COM_THRD_ALLOC;
-	ret = hclge_dbg_dump_rx_common_threshold_cfg(hdev);
-	if (ret)
-		goto err_qos_cmd_send;
+	ret = hclge_dbg_dump_rx_priv_wl_buf_cfg(hdev, buf + pos, len - pos);
+	if (ret < 0)
+		return ret;
+	pos += ret;
 
-	return;
+	ret = hclge_dbg_dump_rx_common_threshold_cfg(hdev, buf + pos,
+						     len - pos);
+	if (ret < 0)
+		return ret;
 
-err_qos_cmd_send:
-	dev_err(&hdev->pdev->dev,
-		"dump qos buf cfg fail(0x%x), ret = %d\n", cmd, ret);
+	return 0;
 }
 
-static void hclge_dbg_dump_mng_table(struct hclge_dev *hdev)
+static int hclge_dbg_dump_mng_table(struct hclge_dev *hdev, char *buf, int len)
 {
 	struct hclge_mac_ethertype_idx_rd_cmd *req0;
-	char printf_buf[HCLGE_DBG_BUF_LEN];
 	struct hclge_desc desc;
 	u32 msg_egress_port;
+	int pos = 0;
 	int ret, i;
 
-	dev_info(&hdev->pdev->dev, "mng tab:\n");
-	memset(printf_buf, 0, HCLGE_DBG_BUF_LEN);
-	strncat(printf_buf,
-		"entry|mac_addr         |mask|ether|mask|vlan|mask",
-		HCLGE_DBG_BUF_LEN - 1);
-	strncat(printf_buf + strlen(printf_buf),
-		"|i_map|i_dir|e_type|pf_id|vf_id|q_id|drop\n",
-		HCLGE_DBG_BUF_LEN - strlen(printf_buf) - 1);
-
-	dev_info(&hdev->pdev->dev, "%s", printf_buf);
+	pos += scnprintf(buf + pos, len - pos,
+			 "entry  mac_addr          mask  ether  ");
+	pos += scnprintf(buf + pos, len - pos,
+			 "mask  vlan  mask  i_map  i_dir  e_type  ");
+	pos += scnprintf(buf + pos, len - pos, "pf_id  vf_id  q_id  drop\n");
 
 	for (i = 0; i < HCLGE_DBG_MNG_TBL_MAX; i++) {
 		hclge_cmd_setup_basic_desc(&desc, HCLGE_MAC_ETHERTYPE_IDX_RD,
@@ -1207,52 +1371,53 @@ static void hclge_dbg_dump_mng_table(struct hclge_dev *hdev)
 		ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
-				"call hclge_cmd_send fail, ret = %d\n", ret);
-			return;
+				"failed to dump manage table, ret = %d\n", ret);
+			return ret;
 		}
 
 		if (!req0->resp_code)
 			continue;
 
-		memset(printf_buf, 0, HCLGE_DBG_BUF_LEN);
-		snprintf(printf_buf, HCLGE_DBG_BUF_LEN,
-			 "%02u   |%02x:%02x:%02x:%02x:%02x:%02x|",
-			 le16_to_cpu(req0->index),
-			 req0->mac_addr[0], req0->mac_addr[1],
-			 req0->mac_addr[2], req0->mac_addr[3],
-			 req0->mac_addr[4], req0->mac_addr[5]);
-
-		snprintf(printf_buf + strlen(printf_buf),
-			 HCLGE_DBG_BUF_LEN - strlen(printf_buf),
-			 "%x   |%04x |%x   |%04x|%x   |%02x   |%02x   |",
-			 !!(req0->flags & HCLGE_DBG_MNG_MAC_MASK_B),
-			 le16_to_cpu(req0->ethter_type),
-			 !!(req0->flags & HCLGE_DBG_MNG_ETHER_MASK_B),
-			 le16_to_cpu(req0->vlan_tag) & HCLGE_DBG_MNG_VLAN_TAG,
-			 !!(req0->flags & HCLGE_DBG_MNG_VLAN_MASK_B),
-			 req0->i_port_bitmap, req0->i_port_direction);
+		pos += scnprintf(buf + pos, len - pos, "%02u     %pM ",
+				 le16_to_cpu(req0->index), req0->mac_addr);
+
+		pos += scnprintf(buf + pos, len - pos,
+				 "%x     %04x   %x     %04x  ",
+				 !!(req0->flags & HCLGE_DBG_MNG_MAC_MASK_B),
+				 le16_to_cpu(req0->ethter_type),
+				 !!(req0->flags & HCLGE_DBG_MNG_ETHER_MASK_B),
+				 le16_to_cpu(req0->vlan_tag) &
+				 HCLGE_DBG_MNG_VLAN_TAG);
+
+		pos += scnprintf(buf + pos, len - pos,
+				 "%x     %02x     %02x     ",
+				 !!(req0->flags & HCLGE_DBG_MNG_VLAN_MASK_B),
+				 req0->i_port_bitmap, req0->i_port_direction);
 
 		msg_egress_port = le16_to_cpu(req0->egress_port);
-		snprintf(printf_buf + strlen(printf_buf),
-			 HCLGE_DBG_BUF_LEN - strlen(printf_buf),
-			 "%x     |%x    |%02x   |%04x|%x\n",
-			 !!(msg_egress_port & HCLGE_DBG_MNG_E_TYPE_B),
-			 msg_egress_port & HCLGE_DBG_MNG_PF_ID,
-			 (msg_egress_port >> 3) & HCLGE_DBG_MNG_VF_ID,
-			 le16_to_cpu(req0->egress_queue),
-			 !!(msg_egress_port & HCLGE_DBG_MNG_DROP_B));
-
-		dev_info(&hdev->pdev->dev, "%s", printf_buf);
+		pos += scnprintf(buf + pos, len - pos,
+				 "%x       %x      %02x     %04x  %x\n",
+				 !!(msg_egress_port & HCLGE_DBG_MNG_E_TYPE_B),
+				 msg_egress_port & HCLGE_DBG_MNG_PF_ID,
+				 (msg_egress_port >> 3) & HCLGE_DBG_MNG_VF_ID,
+				 le16_to_cpu(req0->egress_queue),
+				 !!(msg_egress_port & HCLGE_DBG_MNG_DROP_B));
 	}
+
+	return 0;
 }
 
-static int hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, u8 stage,
-				  bool sel_x, u32 loc)
+#define HCLGE_DBG_TCAM_BUF_SIZE 256
+
+static int hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, bool sel_x,
+				  char *tcam_buf,
+				  struct hclge_dbg_tcam_msg tcam_msg)
 {
 	struct hclge_fd_tcam_config_1_cmd *req1;
 	struct hclge_fd_tcam_config_2_cmd *req2;
 	struct hclge_fd_tcam_config_3_cmd *req3;
 	struct hclge_desc desc[3];
+	int pos = 0;
 	int ret, i;
 	u32 *req;
 
@@ -1266,31 +1431,35 @@ static int hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, u8 stage,
 	req2 = (struct hclge_fd_tcam_config_2_cmd *)desc[1].data;
 	req3 = (struct hclge_fd_tcam_config_3_cmd *)desc[2].data;
 
-	req1->stage  = stage;
+	req1->stage  = tcam_msg.stage;
 	req1->xy_sel = sel_x ? 1 : 0;
-	req1->index  = cpu_to_le32(loc);
+	req1->index  = cpu_to_le32(tcam_msg.loc);
 
 	ret = hclge_cmd_send(&hdev->hw, desc, 3);
 	if (ret)
 		return ret;
 
-	dev_info(&hdev->pdev->dev, " read result tcam key %s(%u):\n",
-		 sel_x ? "x" : "y", loc);
+	pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
+			 "read result tcam key %s(%u):\n", sel_x ? "x" : "y",
+			 tcam_msg.loc);
 
 	/* tcam_data0 ~ tcam_data1 */
 	req = (u32 *)req1->tcam_data;
 	for (i = 0; i < 2; i++)
-		dev_info(&hdev->pdev->dev, "%08x\n", *req++);
+		pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
+				 "%08x\n", *req++);
 
 	/* tcam_data2 ~ tcam_data7 */
 	req = (u32 *)req2->tcam_data;
 	for (i = 0; i < 6; i++)
-		dev_info(&hdev->pdev->dev, "%08x\n", *req++);
+		pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
+				 "%08x\n", *req++);
 
 	/* tcam_data8 ~ tcam_data12 */
 	req = (u32 *)req3->tcam_data;
 	for (i = 0; i < 5; i++)
-		dev_info(&hdev->pdev->dev, "%08x\n", *req++);
+		pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
+				 "%08x\n", *req++);
 
 	return ret;
 }
@@ -1308,265 +1477,315 @@ static int hclge_dbg_get_rules_location(struct hclge_dev *hdev, u16 *rule_locs)
 	}
 	spin_unlock_bh(&hdev->fd_rule_lock);
 
-	if (cnt != hdev->hclge_fd_rule_num)
+	if (cnt != hdev->hclge_fd_rule_num || cnt == 0)
 		return -EINVAL;
 
 	return cnt;
 }
 
-static void hclge_dbg_fd_tcam(struct hclge_dev *hdev)
+static int hclge_dbg_dump_fd_tcam(struct hclge_dev *hdev, char *buf, int len)
 {
+	u32 rule_num = hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1];
+	struct hclge_dbg_tcam_msg tcam_msg;
 	int i, ret, rule_cnt;
 	u16 *rule_locs;
+	char *tcam_buf;
+	int pos = 0;
 
 	if (!hnae3_dev_fd_supported(hdev)) {
 		dev_err(&hdev->pdev->dev,
 			"Only FD-supported dev supports dump fd tcam\n");
-		return;
+		return -EOPNOTSUPP;
 	}
 
-	if (!hdev->hclge_fd_rule_num ||
-	    !hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1])
-		return;
+	if (!hdev->hclge_fd_rule_num || !rule_num)
+		return 0;
 
-	rule_locs = kcalloc(hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1],
-			    sizeof(u16), GFP_KERNEL);
+	rule_locs = kcalloc(rule_num, sizeof(u16), GFP_KERNEL);
 	if (!rule_locs)
-		return;
+		return -ENOMEM;
+
+	tcam_buf = kzalloc(HCLGE_DBG_TCAM_BUF_SIZE, GFP_KERNEL);
+	if (!tcam_buf) {
+		kfree(rule_locs);
+		return -ENOMEM;
+	}
 
 	rule_cnt = hclge_dbg_get_rules_location(hdev, rule_locs);
-	if (rule_cnt <= 0) {
+	if (rule_cnt < 0) {
+		ret = rule_cnt;
 		dev_err(&hdev->pdev->dev,
-			"failed to get rule number, ret = %d\n", rule_cnt);
-		kfree(rule_locs);
-		return;
+			"failed to get rule number, ret = %d\n", ret);
+		goto out;
 	}
 
+	ret = 0;
 	for (i = 0; i < rule_cnt; i++) {
-		ret = hclge_dbg_fd_tcam_read(hdev, 0, true, rule_locs[i]);
+		tcam_msg.stage = HCLGE_FD_STAGE_1;
+		tcam_msg.loc = rule_locs[i];
+
+		ret = hclge_dbg_fd_tcam_read(hdev, true, tcam_buf, tcam_msg);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
 				"failed to get fd tcam key x, ret = %d\n", ret);
-			kfree(rule_locs);
-			return;
+			goto out;
 		}
 
-		ret = hclge_dbg_fd_tcam_read(hdev, 0, false, rule_locs[i]);
+		pos += scnprintf(buf + pos, len - pos, "%s", tcam_buf);
+
+		ret = hclge_dbg_fd_tcam_read(hdev, false, tcam_buf, tcam_msg);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
 				"failed to get fd tcam key y, ret = %d\n", ret);
-			kfree(rule_locs);
-			return;
+			goto out;
 		}
+
+		pos += scnprintf(buf + pos, len - pos, "%s", tcam_buf);
 	}
 
+out:
+	kfree(tcam_buf);
 	kfree(rule_locs);
+	return ret;
 }
 
-void hclge_dbg_dump_rst_info(struct hclge_dev *hdev)
+int hclge_dbg_dump_rst_info(struct hclge_dev *hdev, char *buf, int len)
 {
-	dev_info(&hdev->pdev->dev, "PF reset count: %u\n",
-		 hdev->rst_stats.pf_rst_cnt);
-	dev_info(&hdev->pdev->dev, "FLR reset count: %u\n",
-		 hdev->rst_stats.flr_rst_cnt);
-	dev_info(&hdev->pdev->dev, "GLOBAL reset count: %u\n",
-		 hdev->rst_stats.global_rst_cnt);
-	dev_info(&hdev->pdev->dev, "IMP reset count: %u\n",
-		 hdev->rst_stats.imp_rst_cnt);
-	dev_info(&hdev->pdev->dev, "reset done count: %u\n",
-		 hdev->rst_stats.reset_done_cnt);
-	dev_info(&hdev->pdev->dev, "HW reset done count: %u\n",
-		 hdev->rst_stats.hw_reset_done_cnt);
-	dev_info(&hdev->pdev->dev, "reset count: %u\n",
-		 hdev->rst_stats.reset_cnt);
-	dev_info(&hdev->pdev->dev, "reset fail count: %u\n",
-		 hdev->rst_stats.reset_fail_cnt);
-	dev_info(&hdev->pdev->dev, "vector0 interrupt enable status: 0x%x\n",
-		 hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_REG_BASE));
-	dev_info(&hdev->pdev->dev, "reset interrupt source: 0x%x\n",
-		 hclge_read_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG));
-	dev_info(&hdev->pdev->dev, "reset interrupt status: 0x%x\n",
-		 hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS));
-	dev_info(&hdev->pdev->dev, "hardware reset status: 0x%x\n",
-		 hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG));
-	dev_info(&hdev->pdev->dev, "handshake status: 0x%x\n",
-		 hclge_read_dev(&hdev->hw, HCLGE_NIC_CSQ_DEPTH_REG));
-	dev_info(&hdev->pdev->dev, "function reset status: 0x%x\n",
-		 hclge_read_dev(&hdev->hw, HCLGE_FUN_RST_ING));
-	dev_info(&hdev->pdev->dev, "hdev state: 0x%lx\n", hdev->state);
+	int pos = 0;
+
+	pos += scnprintf(buf + pos, len - pos, "PF reset count: %u\n",
+			 hdev->rst_stats.pf_rst_cnt);
+	pos += scnprintf(buf + pos, len - pos, "FLR reset count: %u\n",
+			 hdev->rst_stats.flr_rst_cnt);
+	pos += scnprintf(buf + pos, len - pos, "GLOBAL reset count: %u\n",
+			 hdev->rst_stats.global_rst_cnt);
+	pos += scnprintf(buf + pos, len - pos, "IMP reset count: %u\n",
+			 hdev->rst_stats.imp_rst_cnt);
+	pos += scnprintf(buf + pos, len - pos, "reset done count: %u\n",
+			 hdev->rst_stats.reset_done_cnt);
+	pos += scnprintf(buf + pos, len - pos, "HW reset done count: %u\n",
+			 hdev->rst_stats.hw_reset_done_cnt);
+	pos += scnprintf(buf + pos, len - pos, "reset count: %u\n",
+			 hdev->rst_stats.reset_cnt);
+	pos += scnprintf(buf + pos, len - pos, "reset fail count: %u\n",
+			 hdev->rst_stats.reset_fail_cnt);
+	pos += scnprintf(buf + pos, len - pos,
+			 "vector0 interrupt enable status: 0x%x\n",
+			 hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_REG_BASE));
+	pos += scnprintf(buf + pos, len - pos, "reset interrupt source: 0x%x\n",
+			 hclge_read_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG));
+	pos += scnprintf(buf + pos, len - pos, "reset interrupt status: 0x%x\n",
+			 hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS));
+	pos += scnprintf(buf + pos, len - pos, "RAS interrupt status: 0x%x\n",
+			 hclge_read_dev(&hdev->hw,
+					HCLGE_RAS_PF_OTHER_INT_STS_REG));
+	pos += scnprintf(buf + pos, len - pos, "hardware reset status: 0x%x\n",
+			 hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG));
+	pos += scnprintf(buf + pos, len - pos, "handshake status: 0x%x\n",
+			 hclge_read_dev(&hdev->hw, HCLGE_NIC_CSQ_DEPTH_REG));
+	pos += scnprintf(buf + pos, len - pos, "function reset status: 0x%x\n",
+			 hclge_read_dev(&hdev->hw, HCLGE_FUN_RST_ING));
+	pos += scnprintf(buf + pos, len - pos, "hdev state: 0x%lx\n",
+			 hdev->state);
+
+	return 0;
+}
+
+static int hclge_dbg_dump_serv_info(struct hclge_dev *hdev, char *buf, int len)
+{
+	unsigned long rem_nsec;
+	int pos = 0;
+	u64 lc;
+
+	lc = local_clock();
+	rem_nsec = do_div(lc, HCLGE_BILLION_NANO_SECONDS);
+
+	pos += scnprintf(buf + pos, len - pos, "local_clock: [%5lu.%06lu]\n",
+			 (unsigned long)lc, rem_nsec / 1000);
+	pos += scnprintf(buf + pos, len - pos, "delta: %u(ms)\n",
+			 jiffies_to_msecs(jiffies - hdev->last_serv_processed));
+	pos += scnprintf(buf + pos, len - pos,
+			 "last_service_task_processed: %lu(jiffies)\n",
+			 hdev->last_serv_processed);
+	pos += scnprintf(buf + pos, len - pos, "last_service_task_cnt: %lu\n",
+			 hdev->serv_processed_cnt);
+
+	return 0;
 }
 
-static void hclge_dbg_dump_serv_info(struct hclge_dev *hdev)
+static int hclge_dbg_dump_interrupt(struct hclge_dev *hdev, char *buf, int len)
 {
-	dev_info(&hdev->pdev->dev, "last_serv_processed: %lu\n",
-		 hdev->last_serv_processed);
-	dev_info(&hdev->pdev->dev, "last_serv_cnt: %lu\n",
-		 hdev->serv_processed_cnt);
+	int pos = 0;
+
+	pos += scnprintf(buf + pos, len - pos, "num_nic_msi: %u\n",
+			 hdev->num_nic_msi);
+	pos += scnprintf(buf + pos, len - pos, "num_roce_msi: %u\n",
+			 hdev->num_roce_msi);
+	pos += scnprintf(buf + pos, len - pos, "num_msi_used: %u\n",
+			 hdev->num_msi_used);
+	pos += scnprintf(buf + pos, len - pos, "num_msi_left: %u\n",
+			 hdev->num_msi_left);
+
+	return 0;
 }
 
-static void hclge_dbg_dump_interrupt(struct hclge_dev *hdev)
+static void hclge_dbg_imp_info_data_print(struct hclge_desc *desc_src,
+					  char *buf, int len, u32 bd_num)
 {
-	dev_info(&hdev->pdev->dev, "num_nic_msi: %u\n", hdev->num_nic_msi);
-	dev_info(&hdev->pdev->dev, "num_roce_msi: %u\n", hdev->num_roce_msi);
-	dev_info(&hdev->pdev->dev, "num_msi_used: %u\n", hdev->num_msi_used);
-	dev_info(&hdev->pdev->dev, "num_msi_left: %u\n", hdev->num_msi_left);
+#define HCLGE_DBG_IMP_INFO_PRINT_OFFSET 0x2
+
+	struct hclge_desc *desc_index = desc_src;
+	u32 offset = 0;
+	int pos = 0;
+	u32 i, j;
+
+	pos += scnprintf(buf + pos, len - pos, "offset | data\n");
+
+	for (i = 0; i < bd_num; i++) {
+		j = 0;
+		while (j < HCLGE_DESC_DATA_LEN - 1) {
+			pos += scnprintf(buf + pos, len - pos, "0x%04x | ",
+					 offset);
+			pos += scnprintf(buf + pos, len - pos, "0x%08x  ",
+					 le32_to_cpu(desc_index->data[j++]));
+			pos += scnprintf(buf + pos, len - pos, "0x%08x\n",
+					 le32_to_cpu(desc_index->data[j++]));
+			offset += sizeof(u32) * HCLGE_DBG_IMP_INFO_PRINT_OFFSET;
+		}
+		desc_index++;
+	}
 }
 
-static void hclge_dbg_get_m7_stats_info(struct hclge_dev *hdev)
+static int
+hclge_dbg_get_imp_stats_info(struct hclge_dev *hdev, char *buf, int len)
 {
-	struct hclge_desc *desc_src, *desc_tmp;
-	struct hclge_get_m7_bd_cmd *req;
+	struct hclge_get_imp_bd_cmd *req;
+	struct hclge_desc *desc_src;
 	struct hclge_desc desc;
-	u32 bd_num, buf_len;
-	int ret, i;
+	u32 bd_num;
+	int ret;
 
-	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_M7_STATS_BD, true);
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_IMP_STATS_BD, true);
 
-	req = (struct hclge_get_m7_bd_cmd *)desc.data;
+	req = (struct hclge_get_imp_bd_cmd *)desc.data;
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
-			"get firmware statistics bd number failed, ret = %d\n",
+			"failed to get imp statistics bd number, ret = %d\n",
 			ret);
-		return;
+		return ret;
 	}
 
 	bd_num = le32_to_cpu(req->bd_num);
 
-	buf_len	 = sizeof(struct hclge_desc) * bd_num;
-	desc_src = kzalloc(buf_len, GFP_KERNEL);
+	desc_src = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL);
 	if (!desc_src)
-		return;
+		return -ENOMEM;
 
-	desc_tmp = desc_src;
-	ret  = hclge_dbg_cmd_send(hdev, desc_tmp, 0, bd_num,
-				  HCLGE_OPC_M7_STATS_INFO);
+	ret  = hclge_dbg_cmd_send(hdev, desc_src, 0, bd_num,
+				  HCLGE_OPC_IMP_STATS_INFO);
 	if (ret) {
 		kfree(desc_src);
 		dev_err(&hdev->pdev->dev,
-			"get firmware statistics failed, ret = %d\n", ret);
-		return;
+			"failed to get imp statistics, ret = %d\n", ret);
+		return ret;
 	}
 
-	for (i = 0; i < bd_num; i++) {
-		dev_info(&hdev->pdev->dev, "0x%08x  0x%08x  0x%08x\n",
-			 le32_to_cpu(desc_tmp->data[0]),
-			 le32_to_cpu(desc_tmp->data[1]),
-			 le32_to_cpu(desc_tmp->data[2]));
-		dev_info(&hdev->pdev->dev, "0x%08x  0x%08x  0x%08x\n",
-			 le32_to_cpu(desc_tmp->data[3]),
-			 le32_to_cpu(desc_tmp->data[4]),
-			 le32_to_cpu(desc_tmp->data[5]));
-
-		desc_tmp++;
-	}
+	hclge_dbg_imp_info_data_print(desc_src, buf, len, bd_num);
 
 	kfree(desc_src);
+
+	return 0;
 }
 
 #define HCLGE_CMD_NCL_CONFIG_BD_NUM	5
+#define HCLGE_MAX_NCL_CONFIG_LENGTH	16384
 
-static void hclge_ncl_config_data_print(struct hclge_dev *hdev,
-					struct hclge_desc *desc, int *offset,
-					int *length)
+static void hclge_ncl_config_data_print(struct hclge_desc *desc, int *index,
+					char *buf, int *len, int *pos)
 {
 #define HCLGE_CMD_DATA_NUM		6
 
-	int i;
-	int j;
+	int offset = HCLGE_MAX_NCL_CONFIG_LENGTH - *index;
+	int i, j;
 
 	for (i = 0; i < HCLGE_CMD_NCL_CONFIG_BD_NUM; i++) {
 		for (j = 0; j < HCLGE_CMD_DATA_NUM; j++) {
 			if (i == 0 && j == 0)
 				continue;
 
-			dev_info(&hdev->pdev->dev, "0x%04x | 0x%08x\n",
-				 *offset,
-				 le32_to_cpu(desc[i].data[j]));
-			*offset += sizeof(u32);
-			*length -= sizeof(u32);
-			if (*length <= 0)
+			*pos += scnprintf(buf + *pos, *len - *pos,
+					  "0x%04x | 0x%08x\n", offset,
+					  le32_to_cpu(desc[i].data[j]));
+
+			offset += sizeof(u32);
+			*index -= sizeof(u32);
+
+			if (*index <= 0)
 				return;
 		}
 	}
 }
 
-/* hclge_dbg_dump_ncl_config: print specified range of NCL_CONFIG file
- * @hdev: pointer to struct hclge_dev
- * @cmd_buf: string that contains offset and length
- */
-static void hclge_dbg_dump_ncl_config(struct hclge_dev *hdev,
-				      const char *cmd_buf)
+static int
+hclge_dbg_dump_ncl_config(struct hclge_dev *hdev, char *buf, int len)
 {
-#define HCLGE_MAX_NCL_CONFIG_OFFSET	4096
 #define HCLGE_NCL_CONFIG_LENGTH_IN_EACH_CMD	(20 + 24 * 4)
-#define HCLGE_NCL_CONFIG_PARAM_NUM	2
 
 	struct hclge_desc desc[HCLGE_CMD_NCL_CONFIG_BD_NUM];
 	int bd_num = HCLGE_CMD_NCL_CONFIG_BD_NUM;
-	int offset;
-	int length;
-	int data0;
+	int index = HCLGE_MAX_NCL_CONFIG_LENGTH;
+	int pos = 0;
+	u32 data0;
 	int ret;
 
-	ret = sscanf(cmd_buf, "%x %x", &offset, &length);
-	if (ret != HCLGE_NCL_CONFIG_PARAM_NUM) {
-		dev_err(&hdev->pdev->dev,
-			"Too few parameters, num = %d.\n", ret);
-		return;
-	}
-
-	if (offset < 0 || offset >= HCLGE_MAX_NCL_CONFIG_OFFSET ||
-	    length <= 0 || length > HCLGE_MAX_NCL_CONFIG_OFFSET - offset) {
-		dev_err(&hdev->pdev->dev,
-			"Invalid input, offset = %d, length = %d.\n",
-			offset, length);
-		return;
-	}
-
-	dev_info(&hdev->pdev->dev, "offset |    data\n");
+	pos += scnprintf(buf + pos, len - pos, "offset | data\n");
 
-	while (length > 0) {
-		data0 = offset;
-		if (length >= HCLGE_NCL_CONFIG_LENGTH_IN_EACH_CMD)
+	while (index > 0) {
+		data0 = HCLGE_MAX_NCL_CONFIG_LENGTH - index;
+		if (index >= HCLGE_NCL_CONFIG_LENGTH_IN_EACH_CMD)
 			data0 |= HCLGE_NCL_CONFIG_LENGTH_IN_EACH_CMD << 16;
 		else
-			data0 |= length << 16;
+			data0 |= (u32)index << 16;
 		ret = hclge_dbg_cmd_send(hdev, desc, data0, bd_num,
 					 HCLGE_OPC_QUERY_NCL_CONFIG);
 		if (ret)
-			return;
+			return ret;
 
-		hclge_ncl_config_data_print(hdev, desc, &offset, &length);
+		hclge_ncl_config_data_print(desc, &index, buf, &len, &pos);
 	}
+
+	return 0;
 }
 
-static void hclge_dbg_dump_loopback(struct hclge_dev *hdev)
+static int hclge_dbg_dump_loopback(struct hclge_dev *hdev, char *buf, int len)
 {
 	struct phy_device *phydev = hdev->hw.mac.phydev;
 	struct hclge_config_mac_mode_cmd *req_app;
 	struct hclge_common_lb_cmd *req_common;
 	struct hclge_desc desc;
 	u8 loopback_en;
+	int pos = 0;
 	int ret;
 
 	req_app = (struct hclge_config_mac_mode_cmd *)desc.data;
 	req_common = (struct hclge_common_lb_cmd *)desc.data;
 
-	dev_info(&hdev->pdev->dev, "mac id: %u\n", hdev->hw.mac.mac_id);
+	pos += scnprintf(buf + pos, len - pos, "mac id: %u\n",
+			 hdev->hw.mac.mac_id);
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, true);
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed to dump app loopback status, ret = %d\n", ret);
-		return;
+		return ret;
 	}
 
 	loopback_en = hnae3_get_bit(le32_to_cpu(req_app->txrx_pad_fcs_loop_en),
 				    HCLGE_MAC_APP_LP_B);
-	dev_info(&hdev->pdev->dev, "app loopback: %s\n",
-		 loopback_en ? "on" : "off");
+	pos += scnprintf(buf + pos, len - pos, "app loopback: %s\n",
+			 state_str[loopback_en]);
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_COMMON_LOOPBACK, true);
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -1574,247 +1793,609 @@ static void hclge_dbg_dump_loopback(struct hclge_dev *hdev)
 		dev_err(&hdev->pdev->dev,
 			"failed to dump common loopback status, ret = %d\n",
 			ret);
-		return;
+		return ret;
 	}
 
 	loopback_en = req_common->enable & HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B;
-	dev_info(&hdev->pdev->dev, "serdes serial loopback: %s\n",
-		 loopback_en ? "on" : "off");
+	pos += scnprintf(buf + pos, len - pos, "serdes serial loopback: %s\n",
+			 state_str[loopback_en]);
 
 	loopback_en = req_common->enable &
-			HCLGE_CMD_SERDES_PARALLEL_INNER_LOOP_B;
-	dev_info(&hdev->pdev->dev, "serdes parallel loopback: %s\n",
-		 loopback_en ? "on" : "off");
+			HCLGE_CMD_SERDES_PARALLEL_INNER_LOOP_B ? 1 : 0;
+	pos += scnprintf(buf + pos, len - pos, "serdes parallel loopback: %s\n",
+			 state_str[loopback_en]);
 
 	if (phydev) {
-		dev_info(&hdev->pdev->dev, "phy loopback: %s\n",
-			 phydev->loopback_enabled ? "on" : "off");
+		loopback_en = phydev->loopback_enabled;
+		pos += scnprintf(buf + pos, len - pos, "phy loopback: %s\n",
+				 state_str[loopback_en]);
 	} else if (hnae3_dev_phy_imp_supported(hdev)) {
 		loopback_en = req_common->enable &
 			      HCLGE_CMD_GE_PHY_INNER_LOOP_B;
-		dev_info(&hdev->pdev->dev, "phy loopback: %s\n",
-			 loopback_en ? "on" : "off");
+		pos += scnprintf(buf + pos, len - pos, "phy loopback: %s\n",
+				 state_str[loopback_en]);
 	}
+
+	return 0;
 }
 
 /* hclge_dbg_dump_mac_tnl_status: print message about mac tnl interrupt
  * @hdev: pointer to struct hclge_dev
  */
-static void hclge_dbg_dump_mac_tnl_status(struct hclge_dev *hdev)
+static int
+hclge_dbg_dump_mac_tnl_status(struct hclge_dev *hdev, char *buf, int len)
 {
-#define HCLGE_BILLION_NANO_SECONDS 1000000000
-
 	struct hclge_mac_tnl_stats stats;
 	unsigned long rem_nsec;
+	int pos = 0;
 
-	dev_info(&hdev->pdev->dev, "Recently generated mac tnl interruption:\n");
+	pos += scnprintf(buf + pos, len - pos,
+			 "Recently generated mac tnl interruption:\n");
 
 	while (kfifo_get(&hdev->mac_tnl_log, &stats)) {
 		rem_nsec = do_div(stats.time, HCLGE_BILLION_NANO_SECONDS);
-		dev_info(&hdev->pdev->dev, "[%07lu.%03lu] status = 0x%x\n",
-			 (unsigned long)stats.time, rem_nsec / 1000,
-			 stats.status);
+
+		pos += scnprintf(buf + pos, len - pos,
+				 "[%07lu.%03lu] status = 0x%x\n",
+				 (unsigned long)stats.time, rem_nsec / 1000,
+				 stats.status);
 	}
+
+	return 0;
 }
 
-static void hclge_dbg_dump_qs_shaper_single(struct hclge_dev *hdev, u16 qsid)
+
+static const struct hclge_dbg_item mac_list_items[] = {
+	{ "FUNC_ID", 2 },
+	{ "MAC_ADDR", 12 },
+	{ "STATE", 2 },
+};
+
+static void hclge_dbg_dump_mac_list(struct hclge_dev *hdev, char *buf, int len,
+				    bool is_unicast)
 {
-	struct hclge_qs_shapping_cmd *shap_cfg_cmd;
-	u8 ir_u, ir_b, ir_s, bs_b, bs_s;
+	char data_str[ARRAY_SIZE(mac_list_items)][HCLGE_DBG_DATA_STR_LEN];
+	char content[HCLGE_DBG_INFO_LEN], str_id[HCLGE_DBG_ID_LEN];
+	char *result[ARRAY_SIZE(mac_list_items)];
+	struct hclge_mac_node *mac_node, *tmp;
+	struct hclge_vport *vport;
+	struct list_head *list;
+	u32 func_id;
+	int pos = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(mac_list_items); i++)
+		result[i] = &data_str[i][0];
+
+	pos += scnprintf(buf + pos, len - pos, "%s MAC_LIST:\n",
+			 is_unicast ? "UC" : "MC");
+	hclge_dbg_fill_content(content, sizeof(content), mac_list_items,
+			       NULL, ARRAY_SIZE(mac_list_items));
+	pos += scnprintf(buf + pos, len - pos, "%s", content);
+
+	for (func_id = 0; func_id < hdev->num_alloc_vport; func_id++) {
+		vport = &hdev->vport[func_id];
+		list = is_unicast ? &vport->uc_mac_list : &vport->mc_mac_list;
+		spin_lock_bh(&vport->mac_list_lock);
+		list_for_each_entry_safe(mac_node, tmp, list, node) {
+			i = 0;
+			result[i++] = hclge_dbg_get_func_id_str(str_id,
+								func_id);
+			sprintf(result[i++], "%pM", mac_node->mac_addr);
+			sprintf(result[i++], "%5s",
+				hclge_mac_state_str[mac_node->state]);
+			hclge_dbg_fill_content(content, sizeof(content),
+					       mac_list_items,
+					       (const char **)result,
+					       ARRAY_SIZE(mac_list_items));
+			pos += scnprintf(buf + pos, len - pos, "%s", content);
+		}
+		spin_unlock_bh(&vport->mac_list_lock);
+	}
+}
+
+static int hclge_get_vlan_rx_offload_cfg(struct hclge_dev *hdev, u8 vf_id,
+					 struct hclge_dbg_vlan_cfg *vlan_cfg)
+{
+	struct hclge_vport_vtag_rx_cfg_cmd *req;
 	struct hclge_desc desc;
-	u32 shapping_para;
-	u32 rate;
+	u16 bmap_index;
+	u8 rx_cfg;
 	int ret;
 
-	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QCN_SHAPPING_CFG, true);
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_PORT_RX_CFG, true);
 
-	shap_cfg_cmd = (struct hclge_qs_shapping_cmd *)desc.data;
-	shap_cfg_cmd->qs_id = cpu_to_le16(qsid);
+	req = (struct hclge_vport_vtag_rx_cfg_cmd *)desc.data;
+	req->vf_offset = vf_id / HCLGE_VF_NUM_PER_CMD;
+	bmap_index = vf_id % HCLGE_VF_NUM_PER_CMD / HCLGE_VF_NUM_PER_BYTE;
+	req->vf_bitmap[bmap_index] = 1U << (vf_id % HCLGE_VF_NUM_PER_BYTE);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
-			"qs%u failed to get tx_rate, ret=%d\n",
-			qsid, ret);
-		return;
+			"failed to get vport%u rxvlan cfg, ret = %d\n",
+			vf_id, ret);
+		return ret;
 	}
 
-	shapping_para = le32_to_cpu(shap_cfg_cmd->qs_shapping_para);
-	ir_b = hclge_tm_get_field(shapping_para, IR_B);
-	ir_u = hclge_tm_get_field(shapping_para, IR_U);
-	ir_s = hclge_tm_get_field(shapping_para, IR_S);
-	bs_b = hclge_tm_get_field(shapping_para, BS_B);
-	bs_s = hclge_tm_get_field(shapping_para, BS_S);
-	rate = le32_to_cpu(shap_cfg_cmd->qs_rate);
-
-	dev_info(&hdev->pdev->dev,
-		 "qs%u ir_b:%u, ir_u:%u, ir_s:%u, bs_b:%u, bs_s:%u, flag:%#x, rate:%u(Mbps)\n",
-		 qsid, ir_b, ir_u, ir_s, bs_b, bs_s, shap_cfg_cmd->flag, rate);
+	rx_cfg = req->vport_vlan_cfg;
+	vlan_cfg->strip_tag1 = hnae3_get_bit(rx_cfg, HCLGE_REM_TAG1_EN_B);
+	vlan_cfg->strip_tag2 = hnae3_get_bit(rx_cfg, HCLGE_REM_TAG2_EN_B);
+	vlan_cfg->drop_tag1 = hnae3_get_bit(rx_cfg, HCLGE_DISCARD_TAG1_EN_B);
+	vlan_cfg->drop_tag2 = hnae3_get_bit(rx_cfg, HCLGE_DISCARD_TAG2_EN_B);
+	vlan_cfg->pri_only1 = hnae3_get_bit(rx_cfg, HCLGE_SHOW_TAG1_EN_B);
+	vlan_cfg->pri_only2 = hnae3_get_bit(rx_cfg, HCLGE_SHOW_TAG2_EN_B);
+
+	return 0;
 }
 
-static void hclge_dbg_dump_qs_shaper_all(struct hclge_dev *hdev)
+static int hclge_get_vlan_tx_offload_cfg(struct hclge_dev *hdev, u8 vf_id,
+					 struct hclge_dbg_vlan_cfg *vlan_cfg)
 {
-	struct hnae3_knic_private_info *kinfo;
-	struct hclge_vport *vport;
-	int vport_id, i;
+	struct hclge_vport_vtag_tx_cfg_cmd *req;
+	struct hclge_desc desc;
+	u16 bmap_index;
+	u8 tx_cfg;
+	int ret;
 
-	for (vport_id = 0; vport_id <= pci_num_vf(hdev->pdev); vport_id++) {
-		vport = &hdev->vport[vport_id];
-		kinfo = &vport->nic.kinfo;
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_PORT_TX_CFG, true);
+	req = (struct hclge_vport_vtag_tx_cfg_cmd *)desc.data;
+	req->vf_offset = vf_id / HCLGE_VF_NUM_PER_CMD;
+	bmap_index = vf_id % HCLGE_VF_NUM_PER_CMD / HCLGE_VF_NUM_PER_BYTE;
+	req->vf_bitmap[bmap_index] = 1U << (vf_id % HCLGE_VF_NUM_PER_BYTE);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to get vport%u txvlan cfg, ret = %d\n",
+			vf_id, ret);
+		return ret;
+	}
 
-		dev_info(&hdev->pdev->dev, "qs cfg of vport%d:\n", vport_id);
+	tx_cfg = req->vport_vlan_cfg;
+	vlan_cfg->pvid = le16_to_cpu(req->def_vlan_tag1);
 
-		for (i = 0; i < kinfo->tc_info.num_tc; i++) {
-			u16 qsid = vport->qs_offset + i;
+	vlan_cfg->accept_tag1 = hnae3_get_bit(tx_cfg, HCLGE_ACCEPT_TAG1_B);
+	vlan_cfg->accept_tag2 = hnae3_get_bit(tx_cfg, HCLGE_ACCEPT_TAG2_B);
+	vlan_cfg->accept_untag1 = hnae3_get_bit(tx_cfg, HCLGE_ACCEPT_UNTAG1_B);
+	vlan_cfg->accept_untag2 = hnae3_get_bit(tx_cfg, HCLGE_ACCEPT_UNTAG2_B);
+	vlan_cfg->insert_tag1 = hnae3_get_bit(tx_cfg, HCLGE_PORT_INS_TAG1_EN_B);
+	vlan_cfg->insert_tag2 = hnae3_get_bit(tx_cfg, HCLGE_PORT_INS_TAG2_EN_B);
+	vlan_cfg->shift_tag = hnae3_get_bit(tx_cfg, HCLGE_TAG_SHIFT_MODE_EN_B);
 
-			hclge_dbg_dump_qs_shaper_single(hdev, qsid);
-		}
-	}
+	return 0;
 }
 
-static void hclge_dbg_dump_qs_shaper(struct hclge_dev *hdev,
-				     const char *cmd_buf)
+static int hclge_get_vlan_filter_config_cmd(struct hclge_dev *hdev,
+					    u8 vlan_type, u8 vf_id,
+					    struct hclge_desc *desc)
 {
-	u16 qsid;
+	struct hclge_vlan_filter_ctrl_cmd *req;
 	int ret;
 
-	ret = kstrtou16(cmd_buf, 0, &qsid);
-	if (ret) {
-		hclge_dbg_dump_qs_shaper_all(hdev);
-		return;
-	}
+	hclge_cmd_setup_basic_desc(desc, HCLGE_OPC_VLAN_FILTER_CTRL, true);
+	req = (struct hclge_vlan_filter_ctrl_cmd *)desc->data;
+	req->vlan_type = vlan_type;
+	req->vf_id = vf_id;
 
-	if (qsid >= hdev->ae_dev->dev_specs.max_qset_num) {
-		dev_err(&hdev->pdev->dev, "qsid(%u) out of range[0-%u]\n",
-			qsid, hdev->ae_dev->dev_specs.max_qset_num - 1);
-		return;
-	}
+	ret = hclge_cmd_send(&hdev->hw, desc, 1);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"failed to get vport%u vlan filter config, ret = %d.\n",
+			vf_id, ret);
 
-	hclge_dbg_dump_qs_shaper_single(hdev, qsid);
+	return ret;
 }
 
-static int hclge_dbg_dump_mac_list(struct hclge_dev *hdev, const char *cmd_buf,
-				   bool is_unicast)
+static int hclge_get_vlan_filter_state(struct hclge_dev *hdev, u8 vlan_type,
+				       u8 vf_id, u8 *vlan_fe)
 {
-	struct hclge_mac_node *mac_node, *tmp;
-	struct hclge_vport *vport;
-	struct list_head *list;
-	u32 func_id;
+	struct hclge_vlan_filter_ctrl_cmd *req;
+	struct hclge_desc desc;
 	int ret;
 
-	ret = kstrtouint(cmd_buf, 0, &func_id);
-	if (ret < 0) {
+	ret = hclge_get_vlan_filter_config_cmd(hdev, vlan_type, vf_id, &desc);
+	if (ret)
+		return ret;
+
+	req = (struct hclge_vlan_filter_ctrl_cmd *)desc.data;
+	*vlan_fe = req->vlan_fe;
+
+	return 0;
+}
+
+static int hclge_get_port_vlan_filter_bypass_state(struct hclge_dev *hdev,
+						   u8 vf_id, u8 *bypass_en)
+{
+	struct hclge_port_vlan_filter_bypass_cmd *req;
+	struct hclge_desc desc;
+	int ret;
+
+	if (!test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, hdev->ae_dev->caps))
+		return 0;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PORT_VLAN_BYPASS, true);
+	req = (struct hclge_port_vlan_filter_bypass_cmd *)desc.data;
+	req->vf_id = vf_id;
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
 		dev_err(&hdev->pdev->dev,
-			"dump mac list: bad command string, ret = %d\n", ret);
-		return -EINVAL;
+			"failed to get vport%u port vlan filter bypass state, ret = %d.\n",
+			vf_id, ret);
+		return ret;
 	}
 
-	if (func_id >= hdev->num_alloc_vport) {
-		dev_err(&hdev->pdev->dev,
-			"function id(%u) is out of range(0-%u)\n", func_id,
-			hdev->num_alloc_vport - 1);
-		return -EINVAL;
+	*bypass_en = hnae3_get_bit(req->bypass_state, HCLGE_INGRESS_BYPASS_B);
+
+	return 0;
+}
+
+static const struct hclge_dbg_item vlan_filter_items[] = {
+	{ "FUNC_ID", 2 },
+	{ "I_VF_VLAN_FILTER", 2 },
+	{ "E_VF_VLAN_FILTER", 2 },
+	{ "PORT_VLAN_FILTER_BYPASS", 0 }
+};
+
+static const struct hclge_dbg_item vlan_offload_items[] = {
+	{ "FUNC_ID", 2 },
+	{ "PVID", 4 },
+	{ "ACCEPT_TAG1", 2 },
+	{ "ACCEPT_TAG2", 2 },
+	{ "ACCEPT_UNTAG1", 2 },
+	{ "ACCEPT_UNTAG2", 2 },
+	{ "INSERT_TAG1", 2 },
+	{ "INSERT_TAG2", 2 },
+	{ "SHIFT_TAG", 2 },
+	{ "STRIP_TAG1", 2 },
+	{ "STRIP_TAG2", 2 },
+	{ "DROP_TAG1", 2 },
+	{ "DROP_TAG2", 2 },
+	{ "PRI_ONLY_TAG1", 2 },
+	{ "PRI_ONLY_TAG2", 0 }
+};
+
+static int hclge_dbg_dump_vlan_filter_config(struct hclge_dev *hdev, char *buf,
+					     int len, int *pos)
+{
+	char content[HCLGE_DBG_VLAN_FLTR_INFO_LEN], str_id[HCLGE_DBG_ID_LEN];
+	const char *result[ARRAY_SIZE(vlan_filter_items)];
+	u8 i, j, vlan_fe, bypass, ingress, egress;
+	u8 func_num = pci_num_vf(hdev->pdev) + 1; /* pf and enabled vf num */
+	int ret;
+
+	ret = hclge_get_vlan_filter_state(hdev, HCLGE_FILTER_TYPE_PORT, 0,
+					  &vlan_fe);
+	if (ret)
+		return ret;
+	ingress = vlan_fe & HCLGE_FILTER_FE_NIC_INGRESS_B;
+	egress = vlan_fe & HCLGE_FILTER_FE_NIC_EGRESS_B ? 1 : 0;
+
+	*pos += scnprintf(buf, len, "I_PORT_VLAN_FILTER: %s\n",
+			  state_str[ingress]);
+	*pos += scnprintf(buf + *pos, len - *pos, "E_PORT_VLAN_FILTER: %s\n",
+			  state_str[egress]);
+
+	hclge_dbg_fill_content(content, sizeof(content), vlan_filter_items,
+			       NULL, ARRAY_SIZE(vlan_filter_items));
+	*pos += scnprintf(buf + *pos, len - *pos, "%s", content);
+
+	for (i = 0; i < func_num; i++) {
+		ret = hclge_get_vlan_filter_state(hdev, HCLGE_FILTER_TYPE_VF, i,
+						  &vlan_fe);
+		if (ret)
+			return ret;
+
+		ingress = vlan_fe & HCLGE_FILTER_FE_NIC_INGRESS_B;
+		egress = vlan_fe & HCLGE_FILTER_FE_NIC_EGRESS_B ? 1 : 0;
+		ret = hclge_get_port_vlan_filter_bypass_state(hdev, i, &bypass);
+		if (ret)
+			return ret;
+		j = 0;
+		result[j++] = hclge_dbg_get_func_id_str(str_id, i);
+		result[j++] = state_str[ingress];
+		result[j++] = state_str[egress];
+		result[j++] =
+			test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B,
+				 hdev->ae_dev->caps) ? state_str[bypass] : "NA";
+		hclge_dbg_fill_content(content, sizeof(content),
+				       vlan_filter_items, result,
+				       ARRAY_SIZE(vlan_filter_items));
+		*pos += scnprintf(buf + *pos, len - *pos, "%s", content);
 	}
+	*pos += scnprintf(buf + *pos, len - *pos, "\n");
 
-	vport = &hdev->vport[func_id];
+	return 0;
+}
+
+static int hclge_dbg_dump_vlan_offload_config(struct hclge_dev *hdev, char *buf,
+					      int len, int *pos)
+{
+	char str_id[HCLGE_DBG_ID_LEN], str_pvid[HCLGE_DBG_ID_LEN];
+	const char *result[ARRAY_SIZE(vlan_offload_items)];
+	char content[HCLGE_DBG_VLAN_OFFLOAD_INFO_LEN];
+	u8 func_num = pci_num_vf(hdev->pdev) + 1; /* pf and enabled vf num */
+	struct hclge_dbg_vlan_cfg vlan_cfg;
+	int ret;
+	u8 i, j;
 
-	list = is_unicast ? &vport->uc_mac_list : &vport->mc_mac_list;
+	hclge_dbg_fill_content(content, sizeof(content), vlan_offload_items,
+			       NULL, ARRAY_SIZE(vlan_offload_items));
+	*pos += scnprintf(buf + *pos, len - *pos, "%s", content);
 
-	dev_info(&hdev->pdev->dev, "vport %u %s mac list:\n",
-		 func_id, is_unicast ? "uc" : "mc");
-	dev_info(&hdev->pdev->dev, "mac address              state\n");
+	for (i = 0; i < func_num; i++) {
+		ret = hclge_get_vlan_tx_offload_cfg(hdev, i, &vlan_cfg);
+		if (ret)
+			return ret;
 
-	spin_lock_bh(&vport->mac_list_lock);
+		ret = hclge_get_vlan_rx_offload_cfg(hdev, i, &vlan_cfg);
+		if (ret)
+			return ret;
 
-	list_for_each_entry_safe(mac_node, tmp, list, node) {
-		dev_info(&hdev->pdev->dev, "%pM         %d\n",
-			 mac_node->mac_addr, mac_node->state);
+		sprintf(str_pvid, "%u", vlan_cfg.pvid);
+		j = 0;
+		result[j++] = hclge_dbg_get_func_id_str(str_id, i);
+		result[j++] = str_pvid;
+		result[j++] = state_str[vlan_cfg.accept_tag1];
+		result[j++] = state_str[vlan_cfg.accept_tag2];
+		result[j++] = state_str[vlan_cfg.accept_untag1];
+		result[j++] = state_str[vlan_cfg.accept_untag2];
+		result[j++] = state_str[vlan_cfg.insert_tag1];
+		result[j++] = state_str[vlan_cfg.insert_tag2];
+		result[j++] = state_str[vlan_cfg.shift_tag];
+		result[j++] = state_str[vlan_cfg.strip_tag1];
+		result[j++] = state_str[vlan_cfg.strip_tag2];
+		result[j++] = state_str[vlan_cfg.drop_tag1];
+		result[j++] = state_str[vlan_cfg.drop_tag2];
+		result[j++] = state_str[vlan_cfg.pri_only1];
+		result[j++] = state_str[vlan_cfg.pri_only2];
+
+		hclge_dbg_fill_content(content, sizeof(content),
+				       vlan_offload_items, result,
+				       ARRAY_SIZE(vlan_offload_items));
+		*pos += scnprintf(buf + *pos, len - *pos, "%s", content);
 	}
 
-	spin_unlock_bh(&vport->mac_list_lock);
+	return 0;
+}
+
+static int hclge_dbg_dump_vlan_config(struct hclge_dev *hdev, char *buf,
+				      int len)
+{
+	int pos = 0;
+	int ret;
+
+	ret = hclge_dbg_dump_vlan_filter_config(hdev, buf, len, &pos);
+	if (ret)
+		return ret;
+
+	return hclge_dbg_dump_vlan_offload_config(hdev, buf, len, &pos);
+}
+
+static int hclge_dbg_dump_ptp_info(struct hclge_dev *hdev, char *buf, int len)
+{
+	struct hclge_ptp *ptp = hdev->ptp;
+	u32 sw_cfg = ptp->ptp_cfg;
+	unsigned int tx_start;
+	unsigned int last_rx;
+	int pos = 0;
+	u32 hw_cfg;
+	int ret;
+
+	pos += scnprintf(buf + pos, len - pos, "phc %s's debug info:\n",
+			 ptp->info.name);
+	pos += scnprintf(buf + pos, len - pos, "ptp enable: %s\n",
+			 test_bit(HCLGE_PTP_FLAG_EN, &ptp->flags) ?
+			 "yes" : "no");
+	pos += scnprintf(buf + pos, len - pos, "ptp tx enable: %s\n",
+			 test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags) ?
+			 "yes" : "no");
+	pos += scnprintf(buf + pos, len - pos, "ptp rx enable: %s\n",
+			 test_bit(HCLGE_PTP_FLAG_RX_EN, &ptp->flags) ?
+			 "yes" : "no");
+
+	last_rx = jiffies_to_msecs(ptp->last_rx);
+	pos += scnprintf(buf + pos, len - pos, "last rx time: %lu.%lu\n",
+			 last_rx / MSEC_PER_SEC, last_rx % MSEC_PER_SEC);
+	pos += scnprintf(buf + pos, len - pos, "rx count: %lu\n", ptp->rx_cnt);
+
+	tx_start = jiffies_to_msecs(ptp->tx_start);
+	pos += scnprintf(buf + pos, len - pos, "last tx start time: %lu.%lu\n",
+			 tx_start / MSEC_PER_SEC, tx_start % MSEC_PER_SEC);
+	pos += scnprintf(buf + pos, len - pos, "tx count: %lu\n", ptp->tx_cnt);
+	pos += scnprintf(buf + pos, len - pos, "tx skipped count: %lu\n",
+			 ptp->tx_skipped);
+	pos += scnprintf(buf + pos, len - pos, "tx timeout count: %lu\n",
+			 ptp->tx_timeout);
+	pos += scnprintf(buf + pos, len - pos, "last tx seqid: %u\n",
+			 ptp->last_tx_seqid);
+
+	ret = hclge_ptp_cfg_qry(hdev, &hw_cfg);
+	if (ret)
+		return ret;
+
+	pos += scnprintf(buf + pos, len - pos, "sw_cfg: %#x, hw_cfg: %#x\n",
+			 sw_cfg, hw_cfg);
+
+	pos += scnprintf(buf + pos, len - pos, "tx type: %d, rx filter: %d\n",
+			 ptp->ts_cfg.tx_type, ptp->ts_cfg.rx_filter);
 
 	return 0;
 }
 
-int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf)
+static int hclge_dbg_dump_mac_uc(struct hclge_dev *hdev, char *buf, int len)
 {
-#define DUMP_REG	"dump reg"
-#define DUMP_TM_MAP	"dump tm map"
-#define DUMP_LOOPBACK	"dump loopback"
-#define DUMP_INTERRUPT	"dump intr"
+	hclge_dbg_dump_mac_list(hdev, buf, len, true);
 
-	struct hclge_vport *vport = hclge_get_vport(handle);
-	struct hclge_dev *hdev = vport->back;
+	return 0;
+}
 
-	if (strncmp(cmd_buf, "dump fd tcam", 12) == 0) {
-		hclge_dbg_fd_tcam(hdev);
-	} else if (strncmp(cmd_buf, "dump tc", 7) == 0) {
-		hclge_dbg_dump_tc(hdev);
-	} else if (strncmp(cmd_buf, DUMP_TM_MAP, strlen(DUMP_TM_MAP)) == 0) {
-		hclge_dbg_dump_tm_map(hdev, &cmd_buf[sizeof(DUMP_TM_MAP)]);
-	} else if (strncmp(cmd_buf, "dump tm", 7) == 0) {
-		hclge_dbg_dump_tm(hdev);
-	} else if (strncmp(cmd_buf, "dump qos pause cfg", 18) == 0) {
-		hclge_dbg_dump_qos_pause_cfg(hdev);
-	} else if (strncmp(cmd_buf, "dump qos pri map", 16) == 0) {
-		hclge_dbg_dump_qos_pri_map(hdev);
-	} else if (strncmp(cmd_buf, "dump qos buf cfg", 16) == 0) {
-		hclge_dbg_dump_qos_buf_cfg(hdev);
-	} else if (strncmp(cmd_buf, "dump mng tbl", 12) == 0) {
-		hclge_dbg_dump_mng_table(hdev);
-	} else if (strncmp(cmd_buf, DUMP_REG, strlen(DUMP_REG)) == 0) {
-		hclge_dbg_dump_reg_cmd(hdev, &cmd_buf[sizeof(DUMP_REG)]);
-	} else if (strncmp(cmd_buf, "dump reset info", 15) == 0) {
-		hclge_dbg_dump_rst_info(hdev);
-	} else if (strncmp(cmd_buf, "dump serv info", 14) == 0) {
-		hclge_dbg_dump_serv_info(hdev);
-	} else if (strncmp(cmd_buf, "dump m7 info", 12) == 0) {
-		hclge_dbg_get_m7_stats_info(hdev);
-	} else if (strncmp(cmd_buf, "dump ncl_config", 15) == 0) {
-		hclge_dbg_dump_ncl_config(hdev,
-					  &cmd_buf[sizeof("dump ncl_config")]);
-	} else if (strncmp(cmd_buf, "dump mac tnl status", 19) == 0) {
-		hclge_dbg_dump_mac_tnl_status(hdev);
-	} else if (strncmp(cmd_buf, DUMP_LOOPBACK,
-		   strlen(DUMP_LOOPBACK)) == 0) {
-		hclge_dbg_dump_loopback(hdev);
-	} else if (strncmp(cmd_buf, "dump qs shaper", 14) == 0) {
-		hclge_dbg_dump_qs_shaper(hdev,
-					 &cmd_buf[sizeof("dump qs shaper")]);
-	} else if (strncmp(cmd_buf, "dump uc mac list", 16) == 0) {
-		hclge_dbg_dump_mac_list(hdev,
-					&cmd_buf[sizeof("dump uc mac list")],
-					true);
-	} else if (strncmp(cmd_buf, "dump mc mac list", 16) == 0) {
-		hclge_dbg_dump_mac_list(hdev,
-					&cmd_buf[sizeof("dump mc mac list")],
-					false);
-	} else if (strncmp(cmd_buf, DUMP_INTERRUPT,
-		   strlen(DUMP_INTERRUPT)) == 0) {
-		hclge_dbg_dump_interrupt(hdev);
-	} else {
-		dev_info(&hdev->pdev->dev, "unknown command\n");
-		return -EINVAL;
-	}
+static int hclge_dbg_dump_mac_mc(struct hclge_dev *hdev, char *buf, int len)
+{
+	hclge_dbg_dump_mac_list(hdev, buf, len, false);
 
 	return 0;
 }
 
-int hclge_dbg_read_cmd(struct hnae3_handle *handle, const char *cmd_buf,
+static const struct hclge_dbg_func hclge_dbg_cmd_func[] = {
+	{
+		.cmd = HNAE3_DBG_CMD_TM_NODES,
+		.dbg_dump = hclge_dbg_dump_tm_nodes,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_TM_PRI,
+		.dbg_dump = hclge_dbg_dump_tm_pri,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_TM_QSET,
+		.dbg_dump = hclge_dbg_dump_tm_qset,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_TM_MAP,
+		.dbg_dump = hclge_dbg_dump_tm_map,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_TM_PG,
+		.dbg_dump = hclge_dbg_dump_tm_pg,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_TM_PORT,
+		.dbg_dump = hclge_dbg_dump_tm_port,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_TC_SCH_INFO,
+		.dbg_dump = hclge_dbg_dump_tc,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_QOS_PAUSE_CFG,
+		.dbg_dump = hclge_dbg_dump_qos_pause_cfg,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_QOS_PRI_MAP,
+		.dbg_dump = hclge_dbg_dump_qos_pri_map,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_QOS_BUF_CFG,
+		.dbg_dump = hclge_dbg_dump_qos_buf_cfg,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_MAC_UC,
+		.dbg_dump = hclge_dbg_dump_mac_uc,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_MAC_MC,
+		.dbg_dump = hclge_dbg_dump_mac_mc,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_MNG_TBL,
+		.dbg_dump = hclge_dbg_dump_mng_table,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_LOOPBACK,
+		.dbg_dump = hclge_dbg_dump_loopback,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_PTP_INFO,
+		.dbg_dump = hclge_dbg_dump_ptp_info,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_INTERRUPT_INFO,
+		.dbg_dump = hclge_dbg_dump_interrupt,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_RESET_INFO,
+		.dbg_dump = hclge_dbg_dump_rst_info,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_IMP_INFO,
+		.dbg_dump = hclge_dbg_get_imp_stats_info,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_NCL_CONFIG,
+		.dbg_dump = hclge_dbg_dump_ncl_config,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_REG_BIOS_COMMON,
+		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_REG_SSU,
+		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_REG_IGU_EGU,
+		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_REG_RPU,
+		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_REG_NCSI,
+		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_REG_RTC,
+		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_REG_PPP,
+		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_REG_RCB,
+		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_REG_TQP,
+		.dbg_dump_reg = hclge_dbg_dump_reg_cmd,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_REG_MAC,
+		.dbg_dump = hclge_dbg_dump_mac,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_REG_DCB,
+		.dbg_dump = hclge_dbg_dump_dcb,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_FD_TCAM,
+		.dbg_dump = hclge_dbg_dump_fd_tcam,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_MAC_TNL_STATUS,
+		.dbg_dump = hclge_dbg_dump_mac_tnl_status,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_SERV_INFO,
+		.dbg_dump = hclge_dbg_dump_serv_info,
+	},
+	{
+		.cmd = HNAE3_DBG_CMD_VLAN_CONFIG,
+		.dbg_dump = hclge_dbg_dump_vlan_config,
+	},
+};
+
+int hclge_dbg_read_cmd(struct hnae3_handle *handle, enum hnae3_dbg_cmd cmd,
 		       char *buf, int len)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
+	const struct hclge_dbg_func *cmd_func;
 	struct hclge_dev *hdev = vport->back;
+	u32 i;
 
-	if (strncmp(cmd_buf, HNAE3_DBG_TM_NODES,
-		    strlen(HNAE3_DBG_TM_NODES)) == 0)
-		return hclge_dbg_dump_tm_nodes(hdev, buf, len);
-	else if (strncmp(cmd_buf, HNAE3_DBG_TM_PRI,
-			 strlen(HNAE3_DBG_TM_PRI)) == 0)
-		return hclge_dbg_dump_tm_pri(hdev, buf, len);
-	else if (strncmp(cmd_buf, HNAE3_DBG_TM_QSET,
-			 strlen(HNAE3_DBG_TM_QSET)) == 0)
-		return hclge_dbg_dump_tm_qset(hdev, buf, len);
+	for (i = 0; i < ARRAY_SIZE(hclge_dbg_cmd_func); i++) {
+		if (cmd == hclge_dbg_cmd_func[i].cmd) {
+			cmd_func = &hclge_dbg_cmd_func[i];
+			if (cmd_func->dbg_dump)
+				return cmd_func->dbg_dump(hdev, buf, len);
+			else
+				return cmd_func->dbg_dump_reg(hdev, cmd, buf,
+							      len);
+		}
+	}
 
+	dev_err(&hdev->pdev->dev, "invalid command(%d)\n", cmd);
 	return -EINVAL;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
index ca2ab6cf84d9..c526591a7240 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
@@ -7,7 +7,6 @@
 #include <linux/etherdevice.h>
 #include "hclge_cmd.h"
 
-#define HCLGE_DBG_BUF_LEN	   256
 #define HCLGE_DBG_MNG_TBL_MAX	   64
 
 #define HCLGE_DBG_MNG_VLAN_MASK_B  BIT(0)
@@ -70,6 +69,11 @@ struct hclge_dbg_reg_common_msg {
 	enum hclge_opcode_type cmd;
 };
 
+struct hclge_dbg_tcam_msg {
+	u8 stage;
+	u32 loc;
+};
+
 #define	HCLGE_DBG_MAX_DFX_MSG_LEN	60
 struct hclge_dbg_dfx_message {
 	int flag;
@@ -78,11 +82,18 @@ struct hclge_dbg_dfx_message {
 
 #define HCLGE_DBG_MAC_REG_TYPE_LEN	32
 struct hclge_dbg_reg_type_info {
-	const char *reg_type;
+	enum hnae3_dbg_cmd cmd;
 	const struct hclge_dbg_dfx_message *dfx_msg;
 	struct hclge_dbg_reg_common_msg reg_msg;
 };
 
+struct hclge_dbg_func {
+	enum hnae3_dbg_cmd cmd;
+	int (*dbg_dump)(struct hclge_dev *hdev, char *buf, int len);
+	int (*dbg_dump_reg)(struct hclge_dev *hdev, enum hnae3_dbg_cmd cmd,
+			    char *buf, int len);
+};
+
 static const struct hclge_dbg_dfx_message hclge_dbg_bios_common_reg[] = {
 	{false, "Reserved"},
 	{true,	"BP_CPU_STATE"},
@@ -723,4 +734,36 @@ static const struct hclge_dbg_dfx_message hclge_dbg_tqp_reg[] = {
 	{true, "RCB_CFG_TX_RING_EBDNUM"},
 };
 
+#define HCLGE_DBG_INFO_LEN			256
+#define HCLGE_DBG_VLAN_FLTR_INFO_LEN		256
+#define HCLGE_DBG_VLAN_OFFLOAD_INFO_LEN		512
+#define HCLGE_DBG_ID_LEN			16
+#define HCLGE_DBG_ITEM_NAME_LEN			32
+#define HCLGE_DBG_DATA_STR_LEN			32
+#define HCLGE_DBG_TM_INFO_LEN			256
+
+#define HCLGE_BILLION_NANO_SECONDS	1000000000
+
+struct hclge_dbg_item {
+	char name[HCLGE_DBG_ITEM_NAME_LEN];
+	u16 interval; /* blank numbers after the item */
+};
+
+struct hclge_dbg_vlan_cfg {
+	u16 pvid;
+	u8 accept_tag1;
+	u8 accept_tag2;
+	u8 accept_untag1;
+	u8 accept_untag2;
+	u8 insert_tag1;
+	u8 insert_tag2;
+	u8 shift_tag;
+	u8 strip_tag1;
+	u8 strip_tag2;
+	u8 drop_tag1;
+	u8 drop_tag2;
+	u8 pri_only1;
+	u8 pri_only2;
+};
+
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index 8223d699cd94..bad9fda19398 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -631,6 +631,134 @@ static const struct hclge_hw_error hclge_rocee_qmm_ovf_err_int[] = {
 	{ /* sentinel */ }
 };
 
+static const struct hclge_hw_module_id hclge_hw_module_id_st[] = {
+	{
+		.module_id = MODULE_NONE,
+		.msg = "MODULE_NONE"
+	}, {
+		.module_id = MODULE_BIOS_COMMON,
+		.msg = "MODULE_BIOS_COMMON"
+	}, {
+		.module_id = MODULE_GE,
+		.msg = "MODULE_GE"
+	}, {
+		.module_id = MODULE_IGU_EGU,
+		.msg = "MODULE_IGU_EGU"
+	}, {
+		.module_id = MODULE_LGE,
+		.msg = "MODULE_LGE"
+	}, {
+		.module_id = MODULE_NCSI,
+		.msg = "MODULE_NCSI"
+	}, {
+		.module_id = MODULE_PPP,
+		.msg = "MODULE_PPP"
+	}, {
+		.module_id = MODULE_QCN,
+		.msg = "MODULE_QCN"
+	}, {
+		.module_id = MODULE_RCB_RX,
+		.msg = "MODULE_RCB_RX"
+	}, {
+		.module_id = MODULE_RTC,
+		.msg = "MODULE_RTC"
+	}, {
+		.module_id = MODULE_SSU,
+		.msg = "MODULE_SSU"
+	}, {
+		.module_id = MODULE_TM,
+		.msg = "MODULE_TM"
+	}, {
+		.module_id = MODULE_RCB_TX,
+		.msg = "MODULE_RCB_TX"
+	}, {
+		.module_id = MODULE_TXDMA,
+		.msg = "MODULE_TXDMA"
+	}, {
+		.module_id = MODULE_MASTER,
+		.msg = "MODULE_MASTER"
+	}, {
+		.module_id = MODULE_ROCEE_TOP,
+		.msg = "MODULE_ROCEE_TOP"
+	}, {
+		.module_id = MODULE_ROCEE_TIMER,
+		.msg = "MODULE_ROCEE_TIMER"
+	}, {
+		.module_id = MODULE_ROCEE_MDB,
+		.msg = "MODULE_ROCEE_MDB"
+	}, {
+		.module_id = MODULE_ROCEE_TSP,
+		.msg = "MODULE_ROCEE_TSP"
+	}, {
+		.module_id = MODULE_ROCEE_TRP,
+		.msg = "MODULE_ROCEE_TRP"
+	}, {
+		.module_id = MODULE_ROCEE_SCC,
+		.msg = "MODULE_ROCEE_SCC"
+	}, {
+		.module_id = MODULE_ROCEE_CAEP,
+		.msg = "MODULE_ROCEE_CAEP"
+	}, {
+		.module_id = MODULE_ROCEE_GEN_AC,
+		.msg = "MODULE_ROCEE_GEN_AC"
+	}, {
+		.module_id = MODULE_ROCEE_QMM,
+		.msg = "MODULE_ROCEE_QMM"
+	}, {
+		.module_id = MODULE_ROCEE_LSAN,
+		.msg = "MODULE_ROCEE_LSAN"
+	}
+};
+
+static const struct hclge_hw_type_id hclge_hw_type_id_st[] = {
+	{
+		.type_id = NONE_ERROR,
+		.msg = "none_error"
+	}, {
+		.type_id = FIFO_ERROR,
+		.msg = "fifo_error"
+	}, {
+		.type_id = MEMORY_ERROR,
+		.msg = "memory_error"
+	}, {
+		.type_id = POISON_ERROR,
+		.msg = "poison_error"
+	}, {
+		.type_id = MSIX_ECC_ERROR,
+		.msg = "msix_ecc_error"
+	}, {
+		.type_id = TQP_INT_ECC_ERROR,
+		.msg = "tqp_int_ecc_error"
+	}, {
+		.type_id = PF_ABNORMAL_INT_ERROR,
+		.msg = "pf_abnormal_int_error"
+	}, {
+		.type_id = MPF_ABNORMAL_INT_ERROR,
+		.msg = "mpf_abnormal_int_error"
+	}, {
+		.type_id = COMMON_ERROR,
+		.msg = "common_error"
+	}, {
+		.type_id = PORT_ERROR,
+		.msg = "port_error"
+	}, {
+		.type_id = ETS_ERROR,
+		.msg = "ets_error"
+	}, {
+		.type_id = NCSI_ERROR,
+		.msg = "ncsi_error"
+	}, {
+		.type_id = GLB_ERROR,
+		.msg = "glb_error"
+	}, {
+		.type_id = ROCEE_NORMAL_ERR,
+		.msg = "rocee_normal_error"
+	}, {
+		.type_id = ROCEE_OVF_ERR,
+		.msg = "rocee_ovf_error"
+	}
+};
+
 static void hclge_log_error(struct device *dev, char *reg,
 			    const struct hclge_hw_error *err,
 			    u32 err_sts, unsigned long *reset_requests)
@@ -1611,11 +1739,27 @@ static const struct hclge_hw_blk hw_blk[] = {
 	{ /* sentinel */ }
 };
 
+static void hclge_config_all_msix_error(struct hclge_dev *hdev, bool enable)
+{
+	u32 reg_val;
+
+	reg_val = hclge_read_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG);
+
+	if (enable)
+		reg_val |= BIT(HCLGE_VECTOR0_ALL_MSIX_ERR_B);
+	else
+		reg_val &= ~BIT(HCLGE_VECTOR0_ALL_MSIX_ERR_B);
+
+	hclge_write_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG, reg_val);
+}
+
 int hclge_config_nic_hw_error(struct hclge_dev *hdev, bool state)
 {
 	const struct hclge_hw_blk *module = hw_blk;
 	int ret = 0;
 
+	hclge_config_all_msix_error(hdev, state);
+
 	while (module->name) {
 		if (module->config_err_int) {
 			ret = module->config_err_int(hdev, state);
@@ -1876,11 +2020,8 @@ static int hclge_handle_pf_msix_error(struct hclge_dev *hdev,
 static int hclge_handle_all_hw_msix_error(struct hclge_dev *hdev,
 					  unsigned long *reset_requests)
 {
-	struct hclge_mac_tnl_stats mac_tnl_stats;
-	struct device *dev = &hdev->pdev->dev;
 	u32 mpf_bd_num, pf_bd_num, bd_num;
 	struct hclge_desc *desc;
-	u32 status;
 	int ret;
 
 	/* query the number of bds for the MSIx int status */
@@ -1903,16 +2044,45 @@ static int hclge_handle_all_hw_msix_error(struct hclge_dev *hdev,
 	if (ret)
 		goto msi_error;
 
+	ret = hclge_handle_mac_tnl(hdev);
+
+msi_error:
+	kfree(desc);
+out:
+	return ret;
+}
+
+int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
+			       unsigned long *reset_requests)
+{
+	struct device *dev = &hdev->pdev->dev;
+
+	if (!test_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state)) {
+		dev_err(dev,
+			"failed to handle msix error during dev init\n");
+		return -EAGAIN;
+	}
+
+	return hclge_handle_all_hw_msix_error(hdev, reset_requests);
+}
+
+int hclge_handle_mac_tnl(struct hclge_dev *hdev)
+{
+	struct hclge_mac_tnl_stats mac_tnl_stats;
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_desc desc;
+	u32 status;
+	int ret;
+
 	/* query and clear mac tnl interruptions */
-	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_MAC_TNL_INT,
-				   true);
-	ret = hclge_cmd_send(&hdev->hw, &desc[0], 1);
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_MAC_TNL_INT, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
-		dev_err(dev, "query mac tnl int cmd failed (%d)\n", ret);
-		goto msi_error;
+		dev_err(dev, "failed to query mac tnl int, ret = %d.\n", ret);
+		return ret;
 	}
 
-	status = le32_to_cpu(desc->data[0]);
+	status = le32_to_cpu(desc.data[0]);
 	if (status) {
 		/* When mac tnl interrupt occurs, we record current time and
 		 * register status here in a fifo, then clear the status. So
@@ -1924,33 +2094,15 @@ static int hclge_handle_all_hw_msix_error(struct hclge_dev *hdev,
 		kfifo_put(&hdev->mac_tnl_log, mac_tnl_stats);
 		ret = hclge_clear_mac_tnl_int(hdev);
 		if (ret)
-			dev_err(dev, "clear mac tnl int failed (%d)\n", ret);
+			dev_err(dev, "failed to clear mac tnl int, ret = %d.\n",
+				ret);
 	}
 
-msi_error:
-	kfree(desc);
-out:
 	return ret;
 }
 
-int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
-			       unsigned long *reset_requests)
-{
-	struct device *dev = &hdev->pdev->dev;
-
-	if (!test_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state)) {
-		dev_err(dev,
-			"Can't handle - MSIx error reported during dev init\n");
-		return 0;
-	}
-
-	return hclge_handle_all_hw_msix_error(hdev, reset_requests);
-}
-
 void hclge_handle_all_hns_hw_errors(struct hnae3_ae_dev *ae_dev)
 {
-#define HCLGE_DESC_NO_DATA_LEN 8
-
 	struct hclge_dev *hdev = ae_dev->priv;
 	struct device *dev = &hdev->pdev->dev;
 	u32 mpf_bd_num, pf_bd_num, bd_num;
@@ -1999,3 +2151,205 @@ void hclge_handle_all_hns_hw_errors(struct hnae3_ae_dev *ae_dev)
 msi_error:
 	kfree(desc);
 }
+
+bool hclge_find_error_source(struct hclge_dev *hdev)
+{
+	u32 msix_src_flag, hw_err_src_flag;
+
+	msix_src_flag = hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS) &
+			HCLGE_VECTOR0_REG_MSIX_MASK;
+
+	hw_err_src_flag = hclge_read_dev(&hdev->hw,
+					 HCLGE_RAS_PF_OTHER_INT_STS_REG) &
+			  HCLGE_RAS_REG_ERR_MASK;
+
+	return msix_src_flag || hw_err_src_flag;
+}
+
+void hclge_handle_occurred_error(struct hclge_dev *hdev)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+
+	if (hclge_find_error_source(hdev))
+		hclge_handle_error_info_log(ae_dev);
+}
+
+static void
+hclge_handle_error_type_reg_log(struct device *dev,
+				struct hclge_mod_err_info *mod_info,
+				struct hclge_type_reg_err_info *type_reg_info)
+{
+#define HCLGE_ERR_TYPE_MASK 0x7F
+#define HCLGE_ERR_TYPE_IS_RAS_OFFSET 7
+
+	u8 mod_id, total_module, type_id, total_type, i, is_ras;
+	u8 index_module = MODULE_NONE;
+	u8 index_type = NONE_ERROR;
+
+	mod_id = mod_info->mod_id;
+	type_id = type_reg_info->type_id & HCLGE_ERR_TYPE_MASK;
+	is_ras = type_reg_info->type_id >> HCLGE_ERR_TYPE_IS_RAS_OFFSET;
+
+	total_module = ARRAY_SIZE(hclge_hw_module_id_st);
+	total_type = ARRAY_SIZE(hclge_hw_type_id_st);
+
+	for (i = 0; i < total_module; i++) {
+		if (mod_id == hclge_hw_module_id_st[i].module_id) {
+			index_module = i;
+			break;
+		}
+	}
+
+	for (i = 0; i < total_type; i++) {
+		if (type_id == hclge_hw_type_id_st[i].type_id) {
+			index_type = i;
+			break;
+		}
+	}
+
+	if (index_module != MODULE_NONE && index_type != NONE_ERROR)
+		dev_err(dev,
+			"found %s %s, is %s error.\n",
+			hclge_hw_module_id_st[index_module].msg,
+			hclge_hw_type_id_st[index_type].msg,
+			is_ras ? "ras" : "msix");
+	else
+		dev_err(dev,
+			"unknown module[%u] or type[%u].\n", mod_id, type_id);
+
+	dev_err(dev, "reg_value:\n");
+	for (i = 0; i < type_reg_info->reg_num; i++)
+		dev_err(dev, "0x%08x\n", type_reg_info->hclge_reg[i]);
+}
+
+static void hclge_handle_error_module_log(struct hnae3_ae_dev *ae_dev,
+					  const u32 *buf, u32 buf_size)
+{
+	struct hclge_type_reg_err_info *type_reg_info;
+	struct hclge_dev *hdev = ae_dev->priv;
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_mod_err_info *mod_info;
+	struct hclge_sum_err_info *sum_info;
+	u8 mod_num, err_num, i;
+	u32 offset = 0;
+
+	sum_info = (struct hclge_sum_err_info *)&buf[offset++];
+	if (sum_info->reset_type &&
+	    sum_info->reset_type != HNAE3_NONE_RESET)
+		set_bit(sum_info->reset_type, &ae_dev->hw_err_reset_req);
+	mod_num = sum_info->mod_num;
+
+	while (mod_num--) {
+		if (offset >= buf_size) {
+			dev_err(dev, "The offset(%u) exceeds buf's size(%u).\n",
+				offset, buf_size);
+			return;
+		}
+		mod_info = (struct hclge_mod_err_info *)&buf[offset++];
+		err_num = mod_info->err_num;
+
+		for (i = 0; i < err_num; i++) {
+			if (offset >= buf_size) {
+				dev_err(dev,
+					"The offset(%u) exceeds buf size(%u).\n",
+					offset, buf_size);
+				return;
+			}
+
+			type_reg_info = (struct hclge_type_reg_err_info *)
+					    &buf[offset++];
+			hclge_handle_error_type_reg_log(dev, mod_info,
+							type_reg_info);
+
+			offset += type_reg_info->reg_num;
+		}
+	}
+}
+
+static int hclge_query_all_err_bd_num(struct hclge_dev *hdev, u32 *bd_num)
+{
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_desc desc_bd;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc_bd, HCLGE_QUERY_ALL_ERR_BD_NUM, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc_bd, 1);
+	if (ret) {
+		dev_err(dev, "failed to query error bd_num, ret = %d.\n", ret);
+		return ret;
+	}
+
+	*bd_num = le32_to_cpu(desc_bd.data[0]);
+	if (!(*bd_num)) {
+		dev_err(dev, "The value of bd_num is 0!\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int hclge_query_all_err_info(struct hclge_dev *hdev,
+				    struct hclge_desc *desc, u32 bd_num)
+{
+	struct device *dev = &hdev->pdev->dev;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(desc, HCLGE_QUERY_ALL_ERR_INFO, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, bd_num);
+	if (ret)
+		dev_err(dev, "failed to query error info, ret = %d.\n", ret);
+
+	return ret;
+}
+
+int hclge_handle_error_info_log(struct hnae3_ae_dev *ae_dev)
+{
+	u32 bd_num, desc_len, buf_len, buf_size, i;
+	struct hclge_dev *hdev = ae_dev->priv;
+	struct hclge_desc *desc;
+	__le32 *desc_data;
+	u32 *buf;
+	int ret;
+
+	ret = hclge_query_all_err_bd_num(hdev, &bd_num);
+	if (ret)
+		goto out;
+
+	desc_len = bd_num * sizeof(struct hclge_desc);
+	desc = kzalloc(desc_len, GFP_KERNEL);
+	if (!desc) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = hclge_query_all_err_info(hdev, desc, bd_num);
+	if (ret)
+		goto err_desc;
+
+	buf_len = bd_num * sizeof(struct hclge_desc) - HCLGE_DESC_NO_DATA_LEN;
+	buf_size = buf_len / sizeof(u32);
+
+	desc_data = kzalloc(buf_len, GFP_KERNEL);
+	if (!desc_data)
+		return -ENOMEM;
+
+	buf = kzalloc(buf_len, GFP_KERNEL);
+	if (!buf) {
+		ret = -ENOMEM;
+		goto err_buf_alloc;
+	}
+
+	memcpy(desc_data, &desc[0].data[0], buf_len);
+	for (i = 0; i < buf_size; i++)
+		buf[i] = le32_to_cpu(desc_data[i]);
+
+	hclge_handle_error_module_log(ae_dev, buf, buf_size);
+	kfree(buf);
+
+err_buf_alloc:
+	kfree(desc_data);
+err_desc:
+	kfree(desc);
+out:
+	return ret;
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index d647f3c84134..07987fb8332e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -15,6 +15,8 @@
 #define HCLGE_RAS_PF_OTHER_INT_STS_REG   0x20B00
 #define HCLGE_RAS_REG_NFE_MASK   0xFF00
 #define HCLGE_RAS_REG_ROCEE_ERR_MASK   0x3000000
+#define HCLGE_RAS_REG_ERR_MASK \
+	(HCLGE_RAS_REG_NFE_MASK | HCLGE_RAS_REG_ROCEE_ERR_MASK)
 
 #define HCLGE_VECTOR0_REG_MSIX_MASK   0x1FF00
 
@@ -107,6 +109,10 @@
 #define HCLGE_ROCEE_OVF_ERR_INT_MASK		0x10000
 #define HCLGE_ROCEE_OVF_ERR_TYPE_MASK		0x3F
 
+#define HCLGE_DESC_DATA_MAX			8
+#define HCLGE_REG_NUM_MAX			256
+#define HCLGE_DESC_NO_DATA_LEN			8
+
 enum hclge_err_int_type {
 	HCLGE_ERR_INT_MSIX = 0,
 	HCLGE_ERR_INT_RAS_CE = 1,
@@ -114,6 +120,56 @@ enum hclge_err_int_type {
 	HCLGE_ERR_INT_RAS_FE = 3,
 };
 
+enum hclge_mod_name_list {
+	MODULE_NONE		= 0,
+	MODULE_BIOS_COMMON	= 1,
+	MODULE_GE		= 2,
+	MODULE_IGU_EGU		= 3,
+	MODULE_LGE		= 4,
+	MODULE_NCSI		= 5,
+	MODULE_PPP		= 6,
+	MODULE_QCN		= 7,
+	MODULE_RCB_RX		= 8,
+	MODULE_RTC		= 9,
+	MODULE_SSU		= 10,
+	MODULE_TM		= 11,
+	MODULE_RCB_TX		= 12,
+	MODULE_TXDMA		= 13,
+	MODULE_MASTER		= 14,
+	/* add new MODULE NAME for NIC here in order */
+	MODULE_ROCEE_TOP	= 40,
+	MODULE_ROCEE_TIMER	= 41,
+	MODULE_ROCEE_MDB	= 42,
+	MODULE_ROCEE_TSP	= 43,
+	MODULE_ROCEE_TRP	= 44,
+	MODULE_ROCEE_SCC	= 45,
+	MODULE_ROCEE_CAEP	= 46,
+	MODULE_ROCEE_GEN_AC	= 47,
+	MODULE_ROCEE_QMM	= 48,
+	MODULE_ROCEE_LSAN	= 49,
+	/* add new MODULE NAME for RoCEE here in order */
+};
+
+enum hclge_err_type_list {
+	NONE_ERROR		= 0,
+	FIFO_ERROR		= 1,
+	MEMORY_ERROR		= 2,
+	POISON_ERROR		= 3,
+	MSIX_ECC_ERROR		= 4,
+	TQP_INT_ECC_ERROR	= 5,
+	PF_ABNORMAL_INT_ERROR	= 6,
+	MPF_ABNORMAL_INT_ERROR	= 7,
+	COMMON_ERROR		= 8,
+	PORT_ERROR		= 9,
+	ETS_ERROR		= 10,
+	NCSI_ERROR		= 11,
+	GLB_ERROR		= 12,
+	/* add new ERROR TYPE for NIC here in order */
+	ROCEE_NORMAL_ERR	= 40,
+	ROCEE_OVF_ERR		= 41,
+	/* add new ERROR TYPE for ROCEE here in order */
+};
+
 struct hclge_hw_blk {
 	u32 msk;
 	const char *name;
@@ -126,11 +182,44 @@ struct hclge_hw_error {
 	enum hnae3_reset_type reset_level;
 };
 
+struct hclge_hw_module_id {
+	enum hclge_mod_name_list module_id;
+	const char *msg;
+};
+
+struct hclge_hw_type_id {
+	enum hclge_err_type_list type_id;
+	const char *msg;
+};
+
+struct hclge_sum_err_info {
+	u8 reset_type;
+	u8 mod_num;
+	u8 rsv[2];
+};
+
+struct hclge_mod_err_info {
+	u8 mod_id;
+	u8 err_num;
+	u8 rsv[2];
+};
+
+struct hclge_type_reg_err_info {
+	u8 type_id;
+	u8 reg_num;
+	u8 rsv[2];
+	u32 hclge_reg[HCLGE_REG_NUM_MAX];
+};
+
 int hclge_config_mac_tnl_int(struct hclge_dev *hdev, bool en);
 int hclge_config_nic_hw_error(struct hclge_dev *hdev, bool state);
 int hclge_config_rocee_ras_interrupt(struct hclge_dev *hdev, bool en);
 void hclge_handle_all_hns_hw_errors(struct hnae3_ae_dev *ae_dev);
+bool hclge_find_error_source(struct hclge_dev *hdev);
+void hclge_handle_occurred_error(struct hclge_dev *hdev);
 pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev);
 int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
 			       unsigned long *reset_requests);
+int hclge_handle_error_info_log(struct hnae3_ae_dev *ae_dev);
+int hclge_handle_mac_tnl(struct hclge_dev *hdev);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 6304aed49f22..f3e482ab3c71 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1279,6 +1279,7 @@ static u32 hclge_get_max_speed(u16 speed_ability)
 
 static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc)
 {
+#define HCLGE_TX_SPARE_SIZE_UNIT		4096
 #define SPEED_ABILITY_EXT_SHIFT			8
 
 	struct hclge_cfg_param_cmd *req;
@@ -1334,6 +1335,10 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc)
 					    HCLGE_CFG_SPEED_ABILITY_EXT_S);
 	cfg->speed_ability |= speed_ability_ext << SPEED_ABILITY_EXT_SHIFT;
 
+	cfg->vlan_fliter_cap = hnae3_get_field(__le32_to_cpu(req->param[1]),
+					       HCLGE_CFG_VLAN_FLTR_CAP_M,
+					       HCLGE_CFG_VLAN_FLTR_CAP_S);
+
 	cfg->umv_space = hnae3_get_field(__le32_to_cpu(req->param[1]),
 					 HCLGE_CFG_UMV_TBL_SPACE_M,
 					 HCLGE_CFG_UMV_TBL_SPACE_S);
@@ -1354,6 +1359,15 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc)
 	cfg->pf_rss_size_max = cfg->pf_rss_size_max ?
 			       1U << cfg->pf_rss_size_max :
 			       cfg->vf_rss_size_max;
+
+	/* The unit of the tx spare buffer size queried from configuration
+	 * file is HCLGE_TX_SPARE_SIZE_UNIT(4096) bytes, so a conversion is
+	 * needed here.
+	 */
+	cfg->tx_spare_buf_size = hnae3_get_field(__le32_to_cpu(req->param[2]),
+						 HCLGE_CFG_TX_SPARE_BUF_SIZE_M,
+						 HCLGE_CFG_TX_SPARE_BUF_SIZE_S);
+	cfg->tx_spare_buf_size *= HCLGE_TX_SPARE_SIZE_UNIT;
 }
 
 /* hclge_get_cfg: query the static parameter from flash
@@ -1513,6 +1527,7 @@ static void hclge_init_kdump_kernel_config(struct hclge_dev *hdev)
 
 static int hclge_configure(struct hclge_dev *hdev)
 {
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
 	struct hclge_cfg cfg;
 	unsigned int i;
 	int ret;
@@ -1534,6 +1549,9 @@ static int hclge_configure(struct hclge_dev *hdev)
 	hdev->tc_max = cfg.tc_num;
 	hdev->tm_info.hw_pfc_map = 0;
 	hdev->wanted_umv_size = cfg.umv_space;
+	hdev->tx_spare_buf_size = cfg.tx_spare_buf_size;
+	if (cfg.vlan_fliter_cap == HCLGE_VLAN_FLTR_CAN_MDF)
+		set_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps);
 
 	if (hnae3_dev_fd_supported(hdev)) {
 		hdev->fd_en = true;
@@ -1729,6 +1747,7 @@ static int hclge_knic_setup(struct hclge_vport *vport, u16 num_tqps,
 	kinfo->num_rx_desc = num_rx_desc;
 
 	kinfo->rx_buf_len = hdev->rx_buf_len;
+	kinfo->tx_spare_buf_size = hdev->tx_spare_buf_size;
 
 	kinfo->tqp = devm_kcalloc(&hdev->pdev->dev, num_tqps,
 				  sizeof(struct hnae3_queue *), GFP_KERNEL);
@@ -1843,6 +1862,7 @@ static int hclge_alloc_vport(struct hclge_dev *hdev)
 		vport->mps = HCLGE_MAC_DEFAULT_FRAME;
 		vport->port_base_vlan_cfg.state = HNAE3_PORT_BASE_VLAN_DISABLE;
 		vport->rxvlan_cfg.rx_vlan_offload_en = true;
+		vport->req_vlan_fltr_en = true;
 		INIT_LIST_HEAD(&vport->vlan_list);
 		INIT_LIST_HEAD(&vport->uc_mac_list);
 		INIT_LIST_HEAD(&vport->mc_mac_list);
@@ -2835,6 +2855,14 @@ static void hclge_reset_task_schedule(struct hclge_dev *hdev)
 				    hclge_wq, &hdev->service_task, 0);
 }
 
+static void hclge_errhand_task_schedule(struct hclge_dev *hdev)
+{
+	if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) &&
+	    !test_and_set_bit(HCLGE_STATE_ERR_SERVICE_SCHED, &hdev->state))
+		mod_delayed_work_on(cpumask_first(&hdev->affinity_mask),
+				    hclge_wq, &hdev->service_task, 0);
+}
+
 void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time)
 {
 	if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) &&
@@ -3291,11 +3319,13 @@ static int hclge_set_vf_link_state(struct hnae3_handle *handle, int vf,
 
 static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 {
-	u32 cmdq_src_reg, msix_src_reg;
+	u32 cmdq_src_reg, msix_src_reg, hw_err_src_reg;
 
 	/* fetch the events from their corresponding regs */
 	cmdq_src_reg = hclge_read_dev(&hdev->hw, HCLGE_VECTOR0_CMDQ_SRC_REG);
 	msix_src_reg = hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS);
+	hw_err_src_reg = hclge_read_dev(&hdev->hw,
+					HCLGE_RAS_PF_OTHER_INT_STS_REG);
 
 	/* Assumption: If by any chance reset and mailbox events are reported
 	 * together then we will only process reset event in this go and will
@@ -3323,10 +3353,15 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 		return HCLGE_VECTOR0_EVENT_RST;
 	}
 
-	/* check for vector0 msix event source */
-	if (msix_src_reg & HCLGE_VECTOR0_REG_MSIX_MASK) {
-		*clearval = msix_src_reg;
+	/* check for vector0 msix event and hardware error event source */
+	if (msix_src_reg & HCLGE_VECTOR0_REG_MSIX_MASK ||
+	    hw_err_src_reg & HCLGE_RAS_REG_ERR_MASK)
 		return HCLGE_VECTOR0_EVENT_ERR;
+
+	/* check for vector0 ptp event source */
+	if (BIT(HCLGE_VECTOR0_REG_PTP_INT_B) & msix_src_reg) {
+		*clearval = msix_src_reg;
+		return HCLGE_VECTOR0_EVENT_PTP;
 	}
 
 	/* check for vector0 mailbox(=CMDQ RX) event source */
@@ -3338,9 +3373,8 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 
 	/* print other vector0 event source */
 	dev_info(&hdev->pdev->dev,
-		 "CMDQ INT status:0x%x, other INT status:0x%x\n",
-		 cmdq_src_reg, msix_src_reg);
-	*clearval = msix_src_reg;
+		 "INT status: CMDQ(%#x) HW errors(%#x) other(%#x)\n",
+		 cmdq_src_reg, hw_err_src_reg, msix_src_reg);
 
 	return HCLGE_VECTOR0_EVENT_OTHER;
 }
@@ -3349,6 +3383,7 @@ static void hclge_clear_event_cause(struct hclge_dev *hdev, u32 event_type,
 				    u32 regclr)
 {
 	switch (event_type) {
+	case HCLGE_VECTOR0_EVENT_PTP:
 	case HCLGE_VECTOR0_EVENT_RST:
 		hclge_write_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG, regclr);
 		break;
@@ -3377,6 +3412,7 @@ static void hclge_enable_vector(struct hclge_misc_vector *vector, bool enable)
 static irqreturn_t hclge_misc_irq_handle(int irq, void *data)
 {
 	struct hclge_dev *hdev = data;
+	unsigned long flags;
 	u32 clearval = 0;
 	u32 event_cause;
 
@@ -3386,21 +3422,16 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data)
 	/* vector 0 interrupt is shared with reset and mailbox source events.*/
 	switch (event_cause) {
 	case HCLGE_VECTOR0_EVENT_ERR:
-		/* we do not know what type of reset is required now. This could
-		 * only be decided after we fetch the type of errors which
-		 * caused this event. Therefore, we will do below for now:
-		 * 1. Assert HNAE3_UNKNOWN_RESET type of reset. This means we
-		 *    have defered type of reset to be used.
-		 * 2. Schedule the reset service task.
-		 * 3. When service task receives  HNAE3_UNKNOWN_RESET type it
-		 *    will fetch the correct type of reset.  This would be done
-		 *    by first decoding the types of errors.
-		 */
-		set_bit(HNAE3_UNKNOWN_RESET, &hdev->reset_request);
-		fallthrough;
+		hclge_errhand_task_schedule(hdev);
+		break;
 	case HCLGE_VECTOR0_EVENT_RST:
 		hclge_reset_task_schedule(hdev);
 		break;
+	case HCLGE_VECTOR0_EVENT_PTP:
+		spin_lock_irqsave(&hdev->ptp->lock, flags);
+		hclge_ptp_clean_tx_hwts(hdev);
+		spin_unlock_irqrestore(&hdev->ptp->lock, flags);
+		break;
 	case HCLGE_VECTOR0_EVENT_MBX:
 		/* If we are here then,
 		 * 1. Either we are not handling any mbx task and we are not
@@ -3421,15 +3452,11 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data)
 
 	hclge_clear_event_cause(hdev, event_cause, clearval);
 
-	/* Enable interrupt if it is not cause by reset. And when
-	 * clearval equal to 0, it means interrupt status may be
-	 * cleared by hardware before driver reads status register.
-	 * For this case, vector0 interrupt also should be enabled.
-	 */
-	if (!clearval ||
-	    event_cause == HCLGE_VECTOR0_EVENT_MBX) {
+	/* Enable interrupt if it is not caused by reset event or error event */
+	if (event_cause == HCLGE_VECTOR0_EVENT_PTP ||
+	    event_cause == HCLGE_VECTOR0_EVENT_MBX ||
+	    event_cause == HCLGE_VECTOR0_EVENT_OTHER)
 		hclge_enable_vector(&hdev->misc_vector, true);
-	}
 
 	return IRQ_HANDLED;
 }
@@ -3786,28 +3813,6 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev,
 	enum hnae3_reset_type rst_level = HNAE3_NONE_RESET;
 	struct hclge_dev *hdev = ae_dev->priv;
 
-	/* first, resolve any unknown reset type to the known type(s) */
-	if (test_bit(HNAE3_UNKNOWN_RESET, addr)) {
-		u32 msix_sts_reg = hclge_read_dev(&hdev->hw,
-					HCLGE_MISC_VECTOR_INT_STS);
-		/* we will intentionally ignore any errors from this function
-		 *  as we will end up in *some* reset request in any case
-		 */
-		if (hclge_handle_hw_msix_error(hdev, addr))
-			dev_info(&hdev->pdev->dev, "received msix interrupt 0x%x\n",
-				 msix_sts_reg);
-
-		clear_bit(HNAE3_UNKNOWN_RESET, addr);
-		/* We defered the clearing of the error event which caused
-		 * interrupt since it was not posssible to do that in
-		 * interrupt context (and this is the reason we introduced
-		 * new UNKNOWN reset type). Now, the errors have been
-		 * handled and cleared in hardware we can safely enable
-		 * interrupts. This is an exception to the norm.
-		 */
-		hclge_enable_vector(&hdev->misc_vector, true);
-	}
-
 	/* return the highest priority reset level amongst all */
 	if (test_bit(HNAE3_IMP_RESET, addr)) {
 		rst_level = HNAE3_IMP_RESET;
@@ -3936,6 +3941,21 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
 	return ret;
 }
 
+static void hclge_show_rst_info(struct hclge_dev *hdev)
+{
+	char *buf;
+
+	buf = kzalloc(HCLGE_DBG_RESET_INFO_LEN, GFP_KERNEL);
+	if (!buf)
+		return;
+
+	hclge_dbg_dump_rst_info(hdev, buf, HCLGE_DBG_RESET_INFO_LEN);
+
+	dev_info(&hdev->pdev->dev, "dump reset info:\n%s", buf);
+
+	kfree(buf);
+}
+
 static bool hclge_reset_err_handle(struct hclge_dev *hdev)
 {
 #define MAX_RESET_FAIL_CNT 5
@@ -3966,7 +3986,7 @@ static bool hclge_reset_err_handle(struct hclge_dev *hdev)
 
 	dev_err(&hdev->pdev->dev, "Reset fail!\n");
 
-	hclge_dbg_dump_rst_info(hdev);
+	hclge_show_rst_info(hdev);
 
 	set_bit(HCLGE_STATE_RST_FAIL, &hdev->state);
 
@@ -4241,6 +4261,68 @@ static void hclge_reset_subtask(struct hclge_dev *hdev)
 	hdev->reset_type = HNAE3_NONE_RESET;
 }
 
+static void hclge_handle_err_reset_request(struct hclge_dev *hdev)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+	enum hnae3_reset_type reset_type;
+
+	if (ae_dev->hw_err_reset_req) {
+		reset_type = hclge_get_reset_level(ae_dev,
+						   &ae_dev->hw_err_reset_req);
+		hclge_set_def_reset_request(ae_dev, reset_type);
+	}
+
+	if (hdev->default_reset_request && ae_dev->ops->reset_event)
+		ae_dev->ops->reset_event(hdev->pdev, NULL);
+
+	/* enable interrupt after error handling complete */
+	hclge_enable_vector(&hdev->misc_vector, true);
+}
+
+static void hclge_handle_err_recovery(struct hclge_dev *hdev)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+
+	ae_dev->hw_err_reset_req = 0;
+
+	if (hclge_find_error_source(hdev)) {
+		hclge_handle_error_info_log(ae_dev);
+		hclge_handle_mac_tnl(hdev);
+	}
+
+	hclge_handle_err_reset_request(hdev);
+}
+
+static void hclge_misc_err_recovery(struct hclge_dev *hdev)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+	struct device *dev = &hdev->pdev->dev;
+	u32 msix_sts_reg;
+
+	msix_sts_reg = hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS);
+	if (msix_sts_reg & HCLGE_VECTOR0_REG_MSIX_MASK) {
+		if (hclge_handle_hw_msix_error
+				(hdev, &hdev->default_reset_request))
+			dev_info(dev, "received msix interrupt 0x%x\n",
+				 msix_sts_reg);
+	}
+
+	hclge_handle_hw_ras_error(ae_dev);
+
+	hclge_handle_err_reset_request(hdev);
+}
+
+static void hclge_errhand_service_task(struct hclge_dev *hdev)
+{
+	if (!test_and_clear_bit(HCLGE_STATE_ERR_SERVICE_SCHED, &hdev->state))
+		return;
+
+	if (hnae3_dev_ras_imp_supported(hdev))
+		hclge_handle_err_recovery(hdev);
+	else
+		hclge_misc_err_recovery(hdev);
+}
+
 static void hclge_reset_service_task(struct hclge_dev *hdev)
 {
 	if (!test_and_clear_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state))
@@ -4319,19 +4401,43 @@ out:
 	hclge_task_schedule(hdev, delta);
 }
 
+static void hclge_ptp_service_task(struct hclge_dev *hdev)
+{
+	unsigned long flags;
+
+	if (!test_bit(HCLGE_STATE_PTP_EN, &hdev->state) ||
+	    !test_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state) ||
+	    !time_is_before_jiffies(hdev->ptp->tx_start + HZ))
+		return;
+
+	/* to prevent concurrence with the irq handler */
+	spin_lock_irqsave(&hdev->ptp->lock, flags);
+
+	/* check HCLGE_STATE_PTP_TX_HANDLING here again, since the irq
+	 * handler may handle it just before spin_lock_irqsave().
+	 */
+	if (test_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state))
+		hclge_ptp_clean_tx_hwts(hdev);
+
+	spin_unlock_irqrestore(&hdev->ptp->lock, flags);
+}
+
 static void hclge_service_task(struct work_struct *work)
 {
 	struct hclge_dev *hdev =
 		container_of(work, struct hclge_dev, service_task.work);
 
+	hclge_errhand_service_task(hdev);
 	hclge_reset_service_task(hdev);
+	hclge_ptp_service_task(hdev);
 	hclge_mailbox_service_task(hdev);
 	hclge_periodic_service_task(hdev);
 
-	/* Handle reset and mbx again in case periodical task delays the
-	 * handling by calling hclge_task_schedule() in
+	/* Handle error recovery, reset and mbx again in case periodical task
+	 * delays the handling by calling hclge_task_schedule() in
 	 * hclge_periodic_service_task().
 	 */
+	hclge_errhand_service_task(hdev);
 	hclge_reset_service_task(hdev);
 	hclge_mailbox_service_task(hdev);
 }
@@ -5168,9 +5274,8 @@ static int hclge_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc,
 static void hclge_request_update_promisc_mode(struct hnae3_handle *handle)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
-	struct hclge_dev *hdev = vport->back;
 
-	set_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state);
+	set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
 }
 
 static void hclge_sync_fd_state(struct hclge_dev *hdev)
@@ -8035,6 +8140,7 @@ int hclge_vport_start(struct hclge_vport *vport)
 	struct hclge_dev *hdev = vport->back;
 
 	set_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+	set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
 	vport->last_active_jiffies = jiffies;
 
 	if (test_bit(vport->vport_id, hdev->vport_config_block)) {
@@ -8776,8 +8882,7 @@ static bool hclge_sync_from_add_list(struct list_head *add_list,
 			kfree(mac_node);
 		} else if (mac_node->state == HCLGE_MAC_ACTIVE) {
 			mac_node->state = HCLGE_MAC_TO_DEL;
-			list_del(&mac_node->node);
-			list_add_tail(&mac_node->node, mac_list);
+			list_move_tail(&mac_node->node, mac_list);
 		} else {
 			list_del(&mac_node->node);
 			kfree(mac_node);
@@ -8806,8 +8911,7 @@ static void hclge_sync_from_del_list(struct list_head *del_list,
 			list_del(&mac_node->node);
 			kfree(mac_node);
 		} else {
-			list_del(&mac_node->node);
-			list_add_tail(&mac_node->node, mac_list);
+			list_move_tail(&mac_node->node, mac_list);
 		}
 	}
 }
@@ -8851,8 +8955,7 @@ static void hclge_sync_vport_mac_table(struct hclge_vport *vport,
 	list_for_each_entry_safe(mac_node, tmp, list, node) {
 		switch (mac_node->state) {
 		case HCLGE_MAC_TO_DEL:
-			list_del(&mac_node->node);
-			list_add_tail(&mac_node->node, &tmp_del_list);
+			list_move_tail(&mac_node->node, &tmp_del_list);
 			break;
 		case HCLGE_MAC_TO_ADD:
 			new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC);
@@ -8934,8 +9037,7 @@ static void hclge_build_del_list(struct list_head *list,
 		switch (mac_cfg->state) {
 		case HCLGE_MAC_TO_DEL:
 		case HCLGE_MAC_ACTIVE:
-			list_del(&mac_cfg->node);
-			list_add_tail(&mac_cfg->node, tmp_del_list);
+			list_move_tail(&mac_cfg->node, tmp_del_list);
 			break;
 		case HCLGE_MAC_TO_ADD:
 			if (is_del_list) {
@@ -9030,8 +9132,7 @@ static void hclge_uninit_vport_mac_list(struct hclge_vport *vport,
 		switch (mac_node->state) {
 		case HCLGE_MAC_TO_DEL:
 		case HCLGE_MAC_ACTIVE:
-			list_del(&mac_node->node);
-			list_add_tail(&mac_node->node, &tmp_del_list);
+			list_move_tail(&mac_node->node, &tmp_del_list);
 			break;
 		case HCLGE_MAC_TO_ADD:
 			list_del(&mac_node->node);
@@ -9360,12 +9461,41 @@ static int hclge_do_ioctl(struct hnae3_handle *handle, struct ifreq *ifr,
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 
-	if (!hdev->hw.mac.phydev)
-		return hclge_mii_ioctl(hdev, ifr, cmd);
+	switch (cmd) {
+	case SIOCGHWTSTAMP:
+		return hclge_ptp_get_cfg(hdev, ifr);
+	case SIOCSHWTSTAMP:
+		return hclge_ptp_set_cfg(hdev, ifr);
+	default:
+		if (!hdev->hw.mac.phydev)
+			return hclge_mii_ioctl(hdev, ifr, cmd);
+	}
 
 	return phy_mii_ioctl(hdev->hw.mac.phydev, ifr, cmd);
 }
 
+static int hclge_set_port_vlan_filter_bypass(struct hclge_dev *hdev, u8 vf_id,
+					     bool bypass_en)
+{
+	struct hclge_port_vlan_filter_bypass_cmd *req;
+	struct hclge_desc desc;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PORT_VLAN_BYPASS, false);
+	req = (struct hclge_port_vlan_filter_bypass_cmd *)desc.data;
+	req->vf_id = vf_id;
+	hnae3_set_bit(req->bypass_state, HCLGE_INGRESS_BYPASS_B,
+		      bypass_en ? 1 : 0);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"failed to set vport%u port vlan filter bypass state, ret = %d.\n",
+			vf_id, ret);
+
+	return ret;
+}
+
 static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type,
 				      u8 fe_type, bool filter_en, u8 vf_id)
 {
@@ -9399,37 +9529,99 @@ static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type,
 	return ret;
 }
 
-#define HCLGE_FILTER_TYPE_VF		0
-#define HCLGE_FILTER_TYPE_PORT		1
-#define HCLGE_FILTER_FE_EGRESS_V1_B	BIT(0)
-#define HCLGE_FILTER_FE_NIC_INGRESS_B	BIT(0)
-#define HCLGE_FILTER_FE_NIC_EGRESS_B	BIT(1)
-#define HCLGE_FILTER_FE_ROCE_INGRESS_B	BIT(2)
-#define HCLGE_FILTER_FE_ROCE_EGRESS_B	BIT(3)
-#define HCLGE_FILTER_FE_EGRESS		(HCLGE_FILTER_FE_NIC_EGRESS_B \
-					| HCLGE_FILTER_FE_ROCE_EGRESS_B)
-#define HCLGE_FILTER_FE_INGRESS		(HCLGE_FILTER_FE_NIC_INGRESS_B \
-					| HCLGE_FILTER_FE_ROCE_INGRESS_B)
+static int hclge_set_vport_vlan_filter(struct hclge_vport *vport, bool enable)
+{
+	struct hclge_dev *hdev = vport->back;
+	struct hnae3_ae_dev *ae_dev = hdev->ae_dev;
+	int ret;
+
+	if (hdev->ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2)
+		return hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF,
+						  HCLGE_FILTER_FE_EGRESS_V1_B,
+						  enable, vport->vport_id);
+
+	ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF,
+					 HCLGE_FILTER_FE_EGRESS, enable,
+					 vport->vport_id);
+	if (ret)
+		return ret;
+
+	if (test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, ae_dev->caps))
+		ret = hclge_set_port_vlan_filter_bypass(hdev, vport->vport_id,
+							!enable);
+	else if (!vport->vport_id)
+		ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT,
+						 HCLGE_FILTER_FE_INGRESS,
+						 enable, 0);
+
+	return ret;
+}
 
-static void hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable)
+static bool hclge_need_enable_vport_vlan_filter(struct hclge_vport *vport)
 {
-	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hnae3_handle *handle = &vport->nic;
+	struct hclge_vport_vlan_cfg *vlan, *tmp;
 	struct hclge_dev *hdev = vport->back;
 
-	if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) {
-		hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF,
-					   HCLGE_FILTER_FE_EGRESS, enable, 0);
-		hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT,
-					   HCLGE_FILTER_FE_INGRESS, enable, 0);
-	} else {
-		hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF,
-					   HCLGE_FILTER_FE_EGRESS_V1_B, enable,
-					   0);
+	if (vport->vport_id) {
+		if (vport->port_base_vlan_cfg.state !=
+			HNAE3_PORT_BASE_VLAN_DISABLE)
+			return true;
+
+		if (vport->vf_info.trusted && vport->vf_info.request_uc_en)
+			return false;
+	} else if (handle->netdev_flags & HNAE3_USER_UPE) {
+		return false;
 	}
-	if (enable)
-		handle->netdev_flags |= HNAE3_VLAN_FLTR;
-	else
-		handle->netdev_flags &= ~HNAE3_VLAN_FLTR;
+
+	if (!vport->req_vlan_fltr_en)
+		return false;
+
+	/* compatible with former device, always enable vlan filter */
+	if (!test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, hdev->ae_dev->caps))
+		return true;
+
+	list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node)
+		if (vlan->vlan_id != 0)
+			return true;
+
+	return false;
+}
+
+int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en)
+{
+	struct hclge_dev *hdev = vport->back;
+	bool need_en;
+	int ret;
+
+	mutex_lock(&hdev->vport_lock);
+
+	vport->req_vlan_fltr_en = request_en;
+
+	need_en = hclge_need_enable_vport_vlan_filter(vport);
+	if (need_en == vport->cur_vlan_fltr_en) {
+		mutex_unlock(&hdev->vport_lock);
+		return 0;
+	}
+
+	ret = hclge_set_vport_vlan_filter(vport, need_en);
+	if (ret) {
+		mutex_unlock(&hdev->vport_lock);
+		return ret;
+	}
+
+	vport->cur_vlan_fltr_en = need_en;
+
+	mutex_unlock(&hdev->vport_lock);
+
+	return 0;
+}
+
+static int hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+
+	return hclge_enable_vport_vlan_filter(vport, enable);
 }
 
 static int hclge_set_vf_vlan_filter_cmd(struct hclge_dev *hdev, u16 vfid,
@@ -9709,7 +9901,7 @@ static int hclge_set_vlan_rx_offload_cfg(struct hclge_vport *vport)
 
 static int hclge_vlan_offload_cfg(struct hclge_vport *vport,
 				  u16 port_base_vlan_state,
-				  u16 vlan_tag)
+				  u16 vlan_tag, u8 qos)
 {
 	int ret;
 
@@ -9723,7 +9915,8 @@ static int hclge_vlan_offload_cfg(struct hclge_vport *vport,
 		vport->txvlan_cfg.accept_tag1 =
 			ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3;
 		vport->txvlan_cfg.insert_tag1_en = true;
-		vport->txvlan_cfg.default_tag1 = vlan_tag;
+		vport->txvlan_cfg.default_tag1 = (qos << VLAN_PRIO_SHIFT) |
+						 vlan_tag;
 	}
 
 	vport->txvlan_cfg.accept_untag1 = true;
@@ -9822,6 +10015,7 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev)
 							 vport->vport_id);
 			if (ret)
 				return ret;
+			vport->cur_vlan_fltr_en = true;
 		}
 
 		ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT,
@@ -9837,8 +10031,6 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev)
 			return ret;
 	}
 
-	handle->netdev_flags |= HNAE3_VLAN_FLTR;
-
 	hdev->vlan_type_cfg.rx_in_fst_vlan_type = HCLGE_DEF_VLAN_TYPE;
 	hdev->vlan_type_cfg.rx_in_sec_vlan_type = HCLGE_DEF_VLAN_TYPE;
 	hdev->vlan_type_cfg.rx_ot_fst_vlan_type = HCLGE_DEF_VLAN_TYPE;
@@ -9852,13 +10044,15 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev)
 
 	for (i = 0; i < hdev->num_alloc_vport; i++) {
 		u16 vlan_tag;
+		u8 qos;
 
 		vport = &hdev->vport[i];
 		vlan_tag = vport->port_base_vlan_cfg.vlan_info.vlan_tag;
+		qos = vport->port_base_vlan_cfg.vlan_info.qos;
 
 		ret = hclge_vlan_offload_cfg(vport,
 					     vport->port_base_vlan_cfg.state,
-					     vlan_tag);
+					     vlan_tag, qos);
 		if (ret)
 			return ret;
 	}
@@ -10033,7 +10227,6 @@ static void hclge_restore_hw_table(struct hclge_dev *hdev)
 
 	hclge_restore_mac_table_common(vport);
 	hclge_restore_vport_vlan_table(vport);
-	set_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state);
 	set_bit(HCLGE_STATE_FD_USER_DEF_CHANGED, &hdev->state);
 	hclge_restore_fd_entries(handle);
 }
@@ -10060,6 +10253,14 @@ int hclge_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
 	return hclge_set_vlan_rx_offload_cfg(vport);
 }
 
+static void hclge_set_vport_vlan_fltr_change(struct hclge_vport *vport)
+{
+	struct hclge_dev *hdev = vport->back;
+
+	if (test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, hdev->ae_dev->caps))
+		set_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE, &vport->state);
+}
+
 static int hclge_update_vlan_filter_entries(struct hclge_vport *vport,
 					    u16 port_base_vlan_state,
 					    struct hclge_vlan_info *new_info,
@@ -10070,6 +10271,10 @@ static int hclge_update_vlan_filter_entries(struct hclge_vport *vport,
 
 	if (port_base_vlan_state == HNAE3_PORT_BASE_VLAN_ENABLE) {
 		hclge_rm_vport_all_vlan_table(vport, false);
+		/* force clear VLAN 0 */
+		ret = hclge_set_vf_vlan_common(hdev, vport->vport_id, true, 0);
+		if (ret)
+			return ret;
 		return hclge_set_vlan_filter_hw(hdev,
 						 htons(new_info->vlan_proto),
 						 vport->vport_id,
@@ -10077,6 +10282,11 @@ static int hclge_update_vlan_filter_entries(struct hclge_vport *vport,
 						 false);
 	}
 
+	/* force add VLAN 0 */
+	ret = hclge_set_vf_vlan_common(hdev, vport->vport_id, false, 0);
+	if (ret)
+		return ret;
+
 	ret = hclge_set_vlan_filter_hw(hdev, htons(old_info->vlan_proto),
 				       vport->vport_id, old_info->vlan_tag,
 				       true);
@@ -10086,6 +10296,18 @@ static int hclge_update_vlan_filter_entries(struct hclge_vport *vport,
 	return hclge_add_vport_all_vlan_table(vport);
 }
 
+static bool hclge_need_update_vlan_filter(const struct hclge_vlan_info *new_cfg,
+					  const struct hclge_vlan_info *old_cfg)
+{
+	if (new_cfg->vlan_tag != old_cfg->vlan_tag)
+		return true;
+
+	if (new_cfg->vlan_tag == 0 && (new_cfg->qos == 0 || old_cfg->qos == 0))
+		return true;
+
+	return false;
+}
+
 int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state,
 				    struct hclge_vlan_info *vlan_info)
 {
@@ -10096,10 +10318,14 @@ int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state,
 
 	old_vlan_info = &vport->port_base_vlan_cfg.vlan_info;
 
-	ret = hclge_vlan_offload_cfg(vport, state, vlan_info->vlan_tag);
+	ret = hclge_vlan_offload_cfg(vport, state, vlan_info->vlan_tag,
+				     vlan_info->qos);
 	if (ret)
 		return ret;
 
+	if (!hclge_need_update_vlan_filter(vlan_info, old_vlan_info))
+		goto out;
+
 	if (state == HNAE3_PORT_BASE_VLAN_MODIFY) {
 		/* add new VLAN tag */
 		ret = hclge_set_vlan_filter_hw(hdev,
@@ -10111,15 +10337,23 @@ int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state,
 			return ret;
 
 		/* remove old VLAN tag */
-		ret = hclge_set_vlan_filter_hw(hdev,
-					       htons(old_vlan_info->vlan_proto),
-					       vport->vport_id,
-					       old_vlan_info->vlan_tag,
-					       true);
-		if (ret)
+		if (old_vlan_info->vlan_tag == 0)
+			ret = hclge_set_vf_vlan_common(hdev, vport->vport_id,
+						       true, 0);
+		else
+			ret = hclge_set_vlan_filter_hw(hdev,
+						       htons(ETH_P_8021Q),
+						       vport->vport_id,
+						       old_vlan_info->vlan_tag,
+						       true);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"failed to clear vport%u port base vlan %u, ret = %d.\n",
+				vport->vport_id, old_vlan_info->vlan_tag, ret);
 			return ret;
+		}
 
-		goto update;
+		goto out;
 	}
 
 	ret = hclge_update_vlan_filter_entries(vport, state, vlan_info,
@@ -10127,38 +10361,38 @@ int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state,
 	if (ret)
 		return ret;
 
-	/* update state only when disable/enable port based VLAN */
+out:
 	vport->port_base_vlan_cfg.state = state;
 	if (state == HNAE3_PORT_BASE_VLAN_DISABLE)
 		nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_DISABLE;
 	else
 		nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_ENABLE;
 
-update:
-	vport->port_base_vlan_cfg.vlan_info.vlan_tag = vlan_info->vlan_tag;
-	vport->port_base_vlan_cfg.vlan_info.qos = vlan_info->qos;
-	vport->port_base_vlan_cfg.vlan_info.vlan_proto = vlan_info->vlan_proto;
+	vport->port_base_vlan_cfg.vlan_info = *vlan_info;
+	hclge_set_vport_vlan_fltr_change(vport);
 
 	return 0;
 }
 
 static u16 hclge_get_port_base_vlan_state(struct hclge_vport *vport,
 					  enum hnae3_port_base_vlan_state state,
-					  u16 vlan)
+					  u16 vlan, u8 qos)
 {
 	if (state == HNAE3_PORT_BASE_VLAN_DISABLE) {
-		if (!vlan)
+		if (!vlan && !qos)
 			return HNAE3_PORT_BASE_VLAN_NOCHANGE;
-		else
-			return HNAE3_PORT_BASE_VLAN_ENABLE;
-	} else {
-		if (!vlan)
-			return HNAE3_PORT_BASE_VLAN_DISABLE;
-		else if (vport->port_base_vlan_cfg.vlan_info.vlan_tag == vlan)
-			return HNAE3_PORT_BASE_VLAN_NOCHANGE;
-		else
-			return HNAE3_PORT_BASE_VLAN_MODIFY;
+
+		return HNAE3_PORT_BASE_VLAN_ENABLE;
 	}
+
+	if (!vlan && !qos)
+		return HNAE3_PORT_BASE_VLAN_DISABLE;
+
+	if (vport->port_base_vlan_cfg.vlan_info.vlan_tag == vlan &&
+	    vport->port_base_vlan_cfg.vlan_info.qos == qos)
+		return HNAE3_PORT_BASE_VLAN_NOCHANGE;
+
+	return HNAE3_PORT_BASE_VLAN_MODIFY;
 }
 
 static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid,
@@ -10186,7 +10420,7 @@ static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid,
 
 	state = hclge_get_port_base_vlan_state(vport,
 					       vport->port_base_vlan_cfg.state,
-					       vlan);
+					       vlan, qos);
 	if (state == HNAE3_PORT_BASE_VLAN_NOCHANGE)
 		return 0;
 
@@ -10209,8 +10443,7 @@ static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid,
 	    test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
 		hclge_push_vf_port_base_vlan_info(&hdev->vport[0],
 						  vport->vport_id, state,
-						  vlan, qos,
-						  ntohs(proto));
+						  &vlan_info);
 
 	return 0;
 }
@@ -10280,9 +10513,37 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
 		 */
 		set_bit(vlan_id, vport->vlan_del_fail_bmap);
 	}
+
+	hclge_set_vport_vlan_fltr_change(vport);
+
 	return ret;
 }
 
+static void hclge_sync_vlan_fltr_state(struct hclge_dev *hdev)
+{
+	struct hclge_vport *vport;
+	int ret;
+	u16 i;
+
+	for (i = 0; i < hdev->num_alloc_vport; i++) {
+		vport = &hdev->vport[i];
+		if (!test_and_clear_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE,
+					&vport->state))
+			continue;
+
+		ret = hclge_enable_vport_vlan_filter(vport,
+						     vport->req_vlan_fltr_en);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"failed to sync vlan filter state for vport%u, ret = %d\n",
+				vport->vport_id, ret);
+			set_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE,
+				&vport->state);
+			return;
+		}
+	}
+}
+
 static void hclge_sync_vlan_filter(struct hclge_dev *hdev)
 {
 #define HCLGE_MAX_SYNC_COUNT	60
@@ -10305,6 +10566,7 @@ static void hclge_sync_vlan_filter(struct hclge_dev *hdev)
 
 			clear_bit(vlan_id, vport->vlan_del_fail_bmap);
 			hclge_rm_vport_vlan_table(vport, vlan_id, false);
+			hclge_set_vport_vlan_fltr_change(vport);
 
 			sync_cnt++;
 			if (sync_cnt >= HCLGE_MAX_SYNC_COUNT)
@@ -10314,6 +10576,8 @@ static void hclge_sync_vlan_filter(struct hclge_dev *hdev)
 						 VLAN_N_VID);
 		}
 	}
+
+	hclge_sync_vlan_fltr_state(hdev);
 }
 
 static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps)
@@ -10807,6 +11071,8 @@ static void hclge_info_show(struct hclge_dev *hdev)
 		 hdev->flag & HCLGE_FLAG_DCB_ENABLE ? "enable" : "disable");
 	dev_info(dev, "MQPRIO %s\n",
 		 hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE ? "enable" : "disable");
+	dev_info(dev, "Default tx spare buffer size: %u\n",
+		 hdev->tx_spare_buf_size);
 
 	dev_info(dev, "PF info end.\n");
 }
@@ -11167,6 +11433,18 @@ static void hclge_clear_resetting_state(struct hclge_dev *hdev)
 	}
 }
 
+static void hclge_init_rxd_adv_layout(struct hclge_dev *hdev)
+{
+	if (hnae3_ae_dev_rxd_adv_layout_supported(hdev->ae_dev))
+		hclge_write_dev(&hdev->hw, HCLGE_RXD_ADV_LAYOUT_EN_REG, 1);
+}
+
+static void hclge_uninit_rxd_adv_layout(struct hclge_dev *hdev)
+{
+	if (hnae3_ae_dev_rxd_adv_layout_supported(hdev->ae_dev))
+		hclge_write_dev(&hdev->hw, HCLGE_RXD_ADV_LAYOUT_EN_REG, 0);
+}
+
 static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 {
 	struct pci_dev *pdev = ae_dev->pdev;
@@ -11309,6 +11587,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 		goto err_mdiobus_unreg;
 	}
 
+	ret = hclge_ptp_init(hdev);
+	if (ret)
+		goto err_mdiobus_unreg;
+
 	INIT_KFIFO(hdev->mac_tnl_log);
 
 	hclge_dcb_ops_set(hdev);
@@ -11325,7 +11607,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hclge_clear_resetting_state(hdev);
 
 	/* Log and clear the hw errors those already occurred */
-	hclge_handle_all_hns_hw_errors(ae_dev);
+	if (hnae3_dev_ras_imp_supported(hdev))
+		hclge_handle_occurred_error(hdev);
+	else
+		hclge_handle_all_hns_hw_errors(ae_dev);
 
 	/* request delayed reset for the error recovery because an immediate
 	 * global reset on a PF affecting pending initialization of other PFs
@@ -11339,6 +11624,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 		mod_timer(&hdev->reset_timer, jiffies + HCLGE_RESET_INTERVAL);
 	}
 
+	hclge_init_rxd_adv_layout(hdev);
+
 	/* Enable MISC vector(vector0) */
 	hclge_enable_vector(&hdev->misc_vector, true);
 
@@ -11471,10 +11758,7 @@ static int hclge_set_vf_trust(struct hnae3_handle *handle, int vf, bool enable)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
-	struct hnae3_ae_dev *ae_dev = hdev->ae_dev;
 	u32 new_trusted = enable ? 1 : 0;
-	bool en_bc_pmc;
-	int ret;
 
 	vport = hclge_get_vf_vport(hdev, vf);
 	if (!vport)
@@ -11483,18 +11767,9 @@ static int hclge_set_vf_trust(struct hnae3_handle *handle, int vf, bool enable)
 	if (vport->vf_info.trusted == new_trusted)
 		return 0;
 
-	/* Disable promisc mode for VF if it is not trusted any more. */
-	if (!enable && vport->vf_info.promisc_enable) {
-		en_bc_pmc = ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2;
-		ret = hclge_set_vport_promisc_mode(vport, false, false,
-						   en_bc_pmc);
-		if (ret)
-			return ret;
-		vport->vf_info.promisc_enable = 0;
-		hclge_inform_vf_promisc_info(vport);
-	}
-
 	vport->vf_info.trusted = new_trusted;
+	set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
+	hclge_task_schedule(hdev, 0);
 
 	return 0;
 }
@@ -11687,8 +11962,15 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 		return ret;
 	}
 
+	ret = hclge_ptp_init(hdev);
+	if (ret)
+		return ret;
+
 	/* Log and clear the hw errors those already occurred */
-	hclge_handle_all_hns_hw_errors(ae_dev);
+	if (hnae3_dev_ras_imp_supported(hdev))
+		hclge_handle_occurred_error(hdev);
+	else
+		hclge_handle_all_hns_hw_errors(ae_dev);
 
 	/* Re-enable the hw error interrupts because
 	 * the interrupts get disabled on global reset.
@@ -11720,6 +12002,8 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 	if (ret)
 		return ret;
 
+	hclge_init_rxd_adv_layout(hdev);
+
 	dev_info(&pdev->dev, "Reset done, %s driver initialization finished.\n",
 		 HCLGE_DRIVER_NAME);
 
@@ -11735,6 +12019,8 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hclge_clear_vf_vlan(hdev);
 	hclge_misc_affinity_teardown(hdev);
 	hclge_state_uninit(hdev);
+	hclge_ptp_uninit(hdev);
+	hclge_uninit_rxd_adv_layout(hdev);
 	hclge_uninit_mac_table(hdev);
 	hclge_del_all_fd_entries(hdev);
 
@@ -12385,21 +12671,50 @@ static void hclge_sync_promisc_mode(struct hclge_dev *hdev)
 	struct hnae3_handle *handle = &vport->nic;
 	u8 tmp_flags;
 	int ret;
+	u16 i;
 
 	if (vport->last_promisc_flags != vport->overflow_promisc_flags) {
-		set_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state);
+		set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
 		vport->last_promisc_flags = vport->overflow_promisc_flags;
 	}
 
-	if (test_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state)) {
+	if (test_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state)) {
 		tmp_flags = handle->netdev_flags | vport->last_promisc_flags;
 		ret = hclge_set_promisc_mode(handle, tmp_flags & HNAE3_UPE,
 					     tmp_flags & HNAE3_MPE);
 		if (!ret) {
-			clear_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state);
-			hclge_enable_vlan_filter(handle,
-						 tmp_flags & HNAE3_VLAN_FLTR);
+			clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
+				  &vport->state);
+			set_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE,
+				&vport->state);
+		}
+	}
+
+	for (i = 1; i < hdev->num_alloc_vport; i++) {
+		bool uc_en = false;
+		bool mc_en = false;
+		bool bc_en;
+
+		vport = &hdev->vport[i];
+
+		if (!test_and_clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
+					&vport->state))
+			continue;
+
+		if (vport->vf_info.trusted) {
+			uc_en = vport->vf_info.request_uc_en > 0;
+			mc_en = vport->vf_info.request_mc_en > 0;
+		}
+		bc_en = vport->vf_info.request_bc_en > 0;
+
+		ret = hclge_cmd_set_promisc_mode(hdev, vport->vport_id, uc_en,
+						 mc_en, bc_en);
+		if (ret) {
+			set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
+				&vport->state);
+			return;
 		}
+		hclge_set_vport_vlan_fltr_change(vport);
 	}
 }
 
@@ -12578,7 +12893,6 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.get_fd_all_rules = hclge_get_all_rules,
 	.enable_fd = hclge_enable_fd,
 	.add_arfs_entry = hclge_add_fd_entry_by_arfs,
-	.dbg_run_cmd = hclge_dbg_run_cmd,
 	.dbg_read_cmd = hclge_dbg_read_cmd,
 	.handle_hw_ras_error = hclge_handle_hw_ras_error,
 	.get_hw_reset_stat = hclge_get_hw_reset_stat,
@@ -12602,6 +12916,9 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.cls_flower_active = hclge_is_cls_flower_active,
 	.get_phy_link_ksettings = hclge_get_phy_link_ksettings,
 	.set_phy_link_ksettings = hclge_set_phy_link_ksettings,
+	.set_tx_hwts_info = hclge_ptp_set_tx_info,
+	.get_rx_hwts = hclge_ptp_get_rx_hwts,
+	.get_ts_info = hclge_ptp_get_ts_info,
 };
 
 static struct hnae3_ae_algo ae_algo = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index ff1d47308c2d..3d3352491dba 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -10,6 +10,7 @@
 #include <linux/kfifo.h>
 
 #include "hclge_cmd.h"
+#include "hclge_ptp.h"
 #include "hnae3.h"
 
 #define HCLGE_MOD_VERSION "1.0"
@@ -53,6 +54,7 @@
 /* bar registers for common func */
 #define HCLGE_VECTOR0_OTER_EN_REG	0x20600
 #define HCLGE_GRO_EN_REG		0x28000
+#define HCLGE_RXD_ADV_LAYOUT_EN_REG	0x28008
 
 /* bar registers for rcb */
 #define HCLGE_RING_RX_ADDR_L_REG	0x80000
@@ -147,6 +149,8 @@
 
 #define HCLGE_MAX_QSET_NUM		1024
 
+#define HCLGE_DBG_RESET_INFO_LEN	1024
+
 enum HLCGE_PORT_TYPE {
 	HOST_PORT,
 	NETWORK_PORT
@@ -175,6 +179,7 @@ enum HLCGE_PORT_TYPE {
 #define HCLGE_FUN_RST_ING_B		0
 
 /* Vector0 register bits define */
+#define HCLGE_VECTOR0_REG_PTP_INT_B	0
 #define HCLGE_VECTOR0_GLOBALRESET_INT_B	5
 #define HCLGE_VECTOR0_CORERESET_INT_B	6
 #define HCLGE_VECTOR0_IMPRESET_INT_B	7
@@ -187,6 +192,7 @@ enum HLCGE_PORT_TYPE {
 #define HCLGE_VECTOR0_IMP_RESET_INT_B	1
 #define HCLGE_VECTOR0_IMP_CMDQ_ERR_B	4U
 #define HCLGE_VECTOR0_IMP_RD_POISON_B	5U
+#define HCLGE_VECTOR0_ALL_MSIX_ERR_B	6U
 
 #define HCLGE_MAC_DEFAULT_FRAME \
 	(ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN + ETH_DATA_LEN)
@@ -218,14 +224,16 @@ enum HCLGE_DEV_STATE {
 	HCLGE_STATE_RST_HANDLING,
 	HCLGE_STATE_MBX_SERVICE_SCHED,
 	HCLGE_STATE_MBX_HANDLING,
+	HCLGE_STATE_ERR_SERVICE_SCHED,
 	HCLGE_STATE_STATISTICS_UPDATING,
 	HCLGE_STATE_CMD_DISABLE,
 	HCLGE_STATE_LINK_UPDATING,
-	HCLGE_STATE_PROMISC_CHANGED,
 	HCLGE_STATE_RST_FAIL,
 	HCLGE_STATE_FD_TBL_CHANGED,
 	HCLGE_STATE_FD_CLEAR_ALL,
 	HCLGE_STATE_FD_USER_DEF_CHANGED,
+	HCLGE_STATE_PTP_EN,
+	HCLGE_STATE_PTP_TX_HANDLING,
 	HCLGE_STATE_MAX
 };
 
@@ -233,6 +241,7 @@ enum hclge_evt_cause {
 	HCLGE_VECTOR0_EVENT_RST,
 	HCLGE_VECTOR0_EVENT_MBX,
 	HCLGE_VECTOR0_EVENT_ERR,
+	HCLGE_VECTOR0_EVENT_PTP,
 	HCLGE_VECTOR0_EVENT_OTHER,
 };
 
@@ -319,6 +328,22 @@ enum hclge_fc_mode {
 	HCLGE_FC_DEFAULT
 };
 
+#define HCLGE_FILTER_TYPE_VF		0
+#define HCLGE_FILTER_TYPE_PORT		1
+#define HCLGE_FILTER_FE_EGRESS_V1_B	BIT(0)
+#define HCLGE_FILTER_FE_NIC_INGRESS_B	BIT(0)
+#define HCLGE_FILTER_FE_NIC_EGRESS_B	BIT(1)
+#define HCLGE_FILTER_FE_ROCE_INGRESS_B	BIT(2)
+#define HCLGE_FILTER_FE_ROCE_EGRESS_B	BIT(3)
+#define HCLGE_FILTER_FE_EGRESS		(HCLGE_FILTER_FE_NIC_EGRESS_B \
+					| HCLGE_FILTER_FE_ROCE_EGRESS_B)
+#define HCLGE_FILTER_FE_INGRESS		(HCLGE_FILTER_FE_NIC_INGRESS_B \
+					| HCLGE_FILTER_FE_ROCE_INGRESS_B)
+
+enum hclge_vlan_fltr_cap {
+	HCLGE_VLAN_FLTR_DEF,
+	HCLGE_VLAN_FLTR_CAN_MDF,
+};
 enum hclge_link_fail_code {
 	HCLGE_LF_NORMAL,
 	HCLGE_LF_REF_CLOCK_LOST,
@@ -349,6 +374,7 @@ struct hclge_tc_info {
 
 struct hclge_cfg {
 	u8 tc_num;
+	u8 vlan_fliter_cap;
 	u16 tqp_desc_num;
 	u16 rx_buf_len;
 	u16 vf_rss_size_max;
@@ -358,6 +384,7 @@ struct hclge_cfg {
 	u8 mac_addr[ETH_ALEN];
 	u8 default_speed;
 	u32 numa_node_map;
+	u32 tx_spare_buf_size;
 	u16 speed_ability;
 	u16 umv_space;
 };
@@ -757,9 +784,14 @@ struct hclge_mac_tnl_stats {
 struct hclge_vf_vlan_cfg {
 	u8 mbx_cmd;
 	u8 subcode;
-	u8 is_kill;
-	u16 vlan;
-	u16 proto;
+	union {
+		struct {
+			u8 is_kill;
+			u16 vlan;
+			u16 proto;
+		};
+		u8 enable;
+	};
 };
 
 #pragma pack()
@@ -817,6 +849,7 @@ struct hclge_dev {
 	u16 alloc_rss_size;		/* Allocated RSS task queue */
 	u16 vf_rss_size_max;		/* HW defined VF max RSS task queue */
 	u16 pf_rss_size_max;		/* HW defined PF max RSS task queue */
+	u32 tx_spare_buf_size;		/* HW defined TX spare buffer size */
 
 	u16 fdir_pf_filter_count; /* Num of guaranteed filters for this PF */
 	u16 num_alloc_vport;		/* Num vports this driver supports */
@@ -909,6 +942,7 @@ struct hclge_dev {
 	/* affinity mask and notify for misc interrupt */
 	cpumask_t affinity_mask;
 	struct irq_affinity_notify affinity_notify;
+	struct hclge_ptp *ptp;
 };
 
 /* VPort level vlan tag configuration for TX direction */
@@ -949,6 +983,8 @@ struct hclge_rss_tuple_cfg {
 enum HCLGE_VPORT_STATE {
 	HCLGE_VPORT_STATE_ALIVE,
 	HCLGE_VPORT_STATE_MAC_TBL_CHANGE,
+	HCLGE_VPORT_STATE_PROMISC_CHANGE,
+	HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE,
 	HCLGE_VPORT_STATE_MAX
 };
 
@@ -969,7 +1005,9 @@ struct hclge_vf_info {
 	u32 spoofchk;
 	u32 max_tx_rate;
 	u32 trusted;
-	u16 promisc_enable;
+	u8 request_uc_en;
+	u8 request_mc_en;
+	u8 request_bc_en;
 };
 
 struct hclge_vport {
@@ -988,6 +1026,8 @@ struct hclge_vport {
 	u32 bw_limit;		/* VSI BW Limit (0 = disabled) */
 	u8  dwrr;
 
+	bool req_vlan_fltr_en;
+	bool cur_vlan_fltr_en;
 	unsigned long vlan_del_fail_bmap[BITS_TO_LONGS(VLAN_N_VID)];
 	struct hclge_port_base_vlan_config port_base_vlan_cfg;
 	struct hclge_tx_vtag_cfg  txvlan_cfg;
@@ -1059,8 +1099,7 @@ int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id);
 int hclge_vport_start(struct hclge_vport *vport);
 void hclge_vport_stop(struct hclge_vport *vport);
 int hclge_set_vport_mtu(struct hclge_vport *vport, int new_mtu);
-int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf);
-int hclge_dbg_read_cmd(struct hnae3_handle *handle, const char *cmd_buf,
+int hclge_dbg_read_cmd(struct hnae3_handle *handle, enum hnae3_dbg_cmd cmd,
 		       char *buf, int len);
 u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle, u16 queue_id);
 int hclge_notify_client(struct hclge_dev *hdev,
@@ -1080,14 +1119,15 @@ void hclge_restore_vport_vlan_table(struct hclge_vport *vport);
 int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state,
 				    struct hclge_vlan_info *vlan_info);
 int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid,
-				      u16 state, u16 vlan_tag, u16 qos,
-				      u16 vlan_proto);
+				      u16 state,
+				      struct hclge_vlan_info *vlan_info);
 void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time);
 int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev,
 				struct hclge_desc *desc);
 void hclge_report_hw_error(struct hclge_dev *hdev,
 			   enum hnae3_hw_error_type type);
 void hclge_inform_vf_promisc_info(struct hclge_vport *vport);
-void hclge_dbg_dump_rst_info(struct hclge_dev *hdev);
+int hclge_dbg_dump_rst_info(struct hclge_dev *hdev, char *buf, int len);
 int hclge_push_vf_link_status(struct hclge_vport *vport);
+int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index f1c9f4ada348..e10a2c36b706 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -231,19 +231,15 @@ static int hclge_map_unmap_ring_to_vf_vector(struct hclge_vport *vport, bool en,
 	return ret;
 }
 
-static int hclge_set_vf_promisc_mode(struct hclge_vport *vport,
-				     struct hclge_mbx_vf_to_pf_cmd *req)
+static void hclge_set_vf_promisc_mode(struct hclge_vport *vport,
+				      struct hclge_mbx_vf_to_pf_cmd *req)
 {
-	bool en_bc = req->msg.en_bc ? true : false;
-	bool en_uc = req->msg.en_uc ? true : false;
-	bool en_mc = req->msg.en_mc ? true : false;
 	struct hnae3_handle *handle = &vport->nic;
-	int ret;
+	struct hclge_dev *hdev = vport->back;
 
-	if (!vport->vf_info.trusted) {
-		en_uc = false;
-		en_mc = false;
-	}
+	vport->vf_info.request_uc_en = req->msg.en_uc;
+	vport->vf_info.request_mc_en = req->msg.en_mc;
+	vport->vf_info.request_bc_en = req->msg.en_bc;
 
 	if (req->msg.en_limit_promisc)
 		set_bit(HNAE3_PFLAG_LIMIT_PROMISC, &handle->priv_flags);
@@ -251,22 +247,8 @@ static int hclge_set_vf_promisc_mode(struct hclge_vport *vport,
 		clear_bit(HNAE3_PFLAG_LIMIT_PROMISC,
 			  &handle->priv_flags);
 
-	ret = hclge_set_vport_promisc_mode(vport, en_uc, en_mc, en_bc);
-
-	vport->vf_info.promisc_enable = (en_uc || en_mc) ? 1 : 0;
-
-	return ret;
-}
-
-void hclge_inform_vf_promisc_info(struct hclge_vport *vport)
-{
-	u8 dest_vfid = (u8)vport->vport_id;
-	u8 msg_data[2];
-
-	memcpy(&msg_data[0], &vport->vf_info.promisc_enable, sizeof(u16));
-
-	hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data),
-			   HCLGE_MBX_PUSH_PROMISC_INFO, dest_vfid);
+	set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
+	hclge_task_schedule(hdev, 0);
 }
 
 static int hclge_set_vf_uc_mac_addr(struct hclge_vport *vport,
@@ -336,17 +318,17 @@ static int hclge_set_vf_mc_mac_addr(struct hclge_vport *vport,
 }
 
 int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid,
-				      u16 state, u16 vlan_tag, u16 qos,
-				      u16 vlan_proto)
+				      u16 state,
+				      struct hclge_vlan_info *vlan_info)
 {
 #define MSG_DATA_SIZE	8
 
 	u8 msg_data[MSG_DATA_SIZE];
 
 	memcpy(&msg_data[0], &state, sizeof(u16));
-	memcpy(&msg_data[2], &vlan_proto, sizeof(u16));
-	memcpy(&msg_data[4], &qos, sizeof(u16));
-	memcpy(&msg_data[6], &vlan_tag, sizeof(u16));
+	memcpy(&msg_data[2], &vlan_info->vlan_proto, sizeof(u16));
+	memcpy(&msg_data[4], &vlan_info->qos, sizeof(u16));
+	memcpy(&msg_data[6], &vlan_info->vlan_tag, sizeof(u16));
 
 	return hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data),
 				  HCLGE_MBX_PUSH_VLAN_INFO, vfid);
@@ -359,49 +341,35 @@ static int hclge_set_vf_vlan_cfg(struct hclge_vport *vport,
 #define HCLGE_MBX_VLAN_STATE_OFFSET	0
 #define HCLGE_MBX_VLAN_INFO_OFFSET	2
 
+	struct hnae3_handle *handle = &vport->nic;
+	struct hclge_dev *hdev = vport->back;
 	struct hclge_vf_vlan_cfg *msg_cmd;
-	int status = 0;
 
 	msg_cmd = (struct hclge_vf_vlan_cfg *)&mbx_req->msg;
-	if (msg_cmd->subcode == HCLGE_MBX_VLAN_FILTER) {
-		struct hnae3_handle *handle = &vport->nic;
-		u16 vlan, proto;
-		bool is_kill;
-
-		is_kill = !!msg_cmd->is_kill;
-		vlan =  msg_cmd->vlan;
-		proto =  msg_cmd->proto;
-		status = hclge_set_vlan_filter(handle, cpu_to_be16(proto),
-					       vlan, is_kill);
-	} else if (msg_cmd->subcode == HCLGE_MBX_VLAN_RX_OFF_CFG) {
-		struct hnae3_handle *handle = &vport->nic;
-		bool en = msg_cmd->is_kill ? true : false;
-
-		status = hclge_en_hw_strip_rxvtag(handle, en);
-	} else if (msg_cmd->subcode == HCLGE_MBX_PORT_BASE_VLAN_CFG) {
-		struct hclge_vlan_info *vlan_info;
-		u16 *state;
-
-		state = (u16 *)&mbx_req->msg.data[HCLGE_MBX_VLAN_STATE_OFFSET];
-		vlan_info = (struct hclge_vlan_info *)
-			&mbx_req->msg.data[HCLGE_MBX_VLAN_INFO_OFFSET];
-		status = hclge_update_port_base_vlan_cfg(vport, *state,
-							 vlan_info);
-	} else if (msg_cmd->subcode == HCLGE_MBX_GET_PORT_BASE_VLAN_STATE) {
-		struct hnae3_ae_dev *ae_dev = pci_get_drvdata(vport->nic.pdev);
+	switch (msg_cmd->subcode) {
+	case HCLGE_MBX_VLAN_FILTER:
+		return hclge_set_vlan_filter(handle,
+					     cpu_to_be16(msg_cmd->proto),
+					     msg_cmd->vlan, msg_cmd->is_kill);
+	case HCLGE_MBX_VLAN_RX_OFF_CFG:
+		return hclge_en_hw_strip_rxvtag(handle, msg_cmd->enable);
+	case HCLGE_MBX_GET_PORT_BASE_VLAN_STATE:
 		/* vf does not need to know about the port based VLAN state
 		 * on device HNAE3_DEVICE_VERSION_V3. So always return disable
 		 * on device HNAE3_DEVICE_VERSION_V3 if vf queries the port
 		 * based VLAN state.
 		 */
 		resp_msg->data[0] =
-			ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3 ?
+			hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3 ?
 			HNAE3_PORT_BASE_VLAN_DISABLE :
 			vport->port_base_vlan_cfg.state;
 		resp_msg->len = sizeof(u8);
+		return 0;
+	case HCLGE_MBX_ENABLE_VLAN_FILTER:
+		return hclge_enable_vport_vlan_filter(vport, msg_cmd->enable);
+	default:
+		return 0;
 	}
-
-	return status;
 }
 
 static int hclge_set_vf_alive(struct hclge_vport *vport,
@@ -418,16 +386,23 @@ static int hclge_set_vf_alive(struct hclge_vport *vport,
 	return ret;
 }
 
-static void hclge_get_vf_tcinfo(struct hclge_vport *vport,
-				struct hclge_respond_to_vf_msg *resp_msg)
+static void hclge_get_basic_info(struct hclge_vport *vport,
+				 struct hclge_respond_to_vf_msg *resp_msg)
 {
 	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
+	struct hnae3_ae_dev *ae_dev = vport->back->ae_dev;
+	struct hclge_basic_info *basic_info;
 	unsigned int i;
 
+	basic_info = (struct hclge_basic_info *)resp_msg->data;
 	for (i = 0; i < kinfo->tc_info.num_tc; i++)
-		resp_msg->data[0] |= BIT(i);
+		basic_info->hw_tc_map |= BIT(i);
 
-	resp_msg->len = sizeof(u8);
+	if (test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps))
+		hnae3_set_bit(basic_info->pf_caps,
+			      HNAE3_PF_SUPPORT_VLAN_FLTR_MDF_B, 1);
+
+	resp_msg->len = HCLGE_MBX_MAX_RESP_DATA_SIZE;
 }
 
 static void hclge_get_vf_queue_info(struct hclge_vport *vport,
@@ -750,11 +725,7 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 								req);
 			break;
 		case HCLGE_MBX_SET_PROMISC_MODE:
-			ret = hclge_set_vf_promisc_mode(vport, req);
-			if (ret)
-				dev_err(&hdev->pdev->dev,
-					"PF fail(%d) to set VF promisc mode\n",
-					ret);
+			hclge_set_vf_promisc_mode(vport, req);
 			break;
 		case HCLGE_MBX_SET_UNICAST:
 			ret = hclge_set_vf_uc_mac_addr(vport, req);
@@ -790,8 +761,8 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 		case HCLGE_MBX_GET_QDEPTH:
 			hclge_get_vf_queue_depth(vport, &resp_msg);
 			break;
-		case HCLGE_MBX_GET_TCINFO:
-			hclge_get_vf_tcinfo(vport, &resp_msg);
+		case HCLGE_MBX_GET_BASIC_INFO:
+			hclge_get_basic_info(vport, &resp_msg);
 			break;
 		case HCLGE_MBX_GET_LINK_STATUS:
 			ret = hclge_push_vf_link_status(vport);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
new file mode 100644
index 000000000000..b3eb8f109dbb
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
@@ -0,0 +1,544 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2021 Hisilicon Limited.
+
+#include <linux/skbuff.h>
+#include "hclge_main.h"
+#include "hnae3.h"
+
+static int hclge_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+{
+	struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp);
+	u64 adj_val, adj_base, diff;
+	unsigned long flags;
+	bool is_neg = false;
+	u32 quo, numerator;
+
+	if (ppb < 0) {
+		ppb = -ppb;
+		is_neg = true;
+	}
+
+	adj_base = HCLGE_PTP_CYCLE_ADJ_BASE * HCLGE_PTP_CYCLE_ADJ_UNIT;
+	adj_val = adj_base * ppb;
+	diff = div_u64(adj_val, 1000000000ULL);
+
+	if (is_neg)
+		adj_val = adj_base - diff;
+	else
+		adj_val = adj_base + diff;
+
+	/* This clock cycle is defined by three part: quotient, numerator
+	 * and denominator. For example, 2.5ns, the quotient is 2,
+	 * denominator is fixed to HCLGE_PTP_CYCLE_ADJ_UNIT, and numerator
+	 * is 0.5 * HCLGE_PTP_CYCLE_ADJ_UNIT.
+	 */
+	quo = div_u64_rem(adj_val, HCLGE_PTP_CYCLE_ADJ_UNIT, &numerator);
+
+	spin_lock_irqsave(&hdev->ptp->lock, flags);
+	writel(quo, hdev->ptp->io_base + HCLGE_PTP_CYCLE_QUO_REG);
+	writel(numerator, hdev->ptp->io_base + HCLGE_PTP_CYCLE_NUM_REG);
+	writel(HCLGE_PTP_CYCLE_ADJ_UNIT,
+	       hdev->ptp->io_base + HCLGE_PTP_CYCLE_DEN_REG);
+	writel(HCLGE_PTP_CYCLE_ADJ_EN,
+	       hdev->ptp->io_base + HCLGE_PTP_CYCLE_CFG_REG);
+	spin_unlock_irqrestore(&hdev->ptp->lock, flags);
+
+	return 0;
+}
+
+bool hclge_ptp_set_tx_info(struct hnae3_handle *handle, struct sk_buff *skb)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	struct hclge_ptp *ptp = hdev->ptp;
+
+	if (!test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags) ||
+	    test_and_set_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state)) {
+		ptp->tx_skipped++;
+		return false;
+	}
+
+	ptp->tx_start = jiffies;
+	ptp->tx_skb = skb_get(skb);
+	ptp->tx_cnt++;
+
+	return true;
+}
+
+void hclge_ptp_clean_tx_hwts(struct hclge_dev *hdev)
+{
+	struct sk_buff *skb = hdev->ptp->tx_skb;
+	struct skb_shared_hwtstamps hwts;
+	u32 hi, lo;
+	u64 ns;
+
+	ns = readl(hdev->ptp->io_base + HCLGE_PTP_TX_TS_NSEC_REG) &
+	     HCLGE_PTP_TX_TS_NSEC_MASK;
+	lo = readl(hdev->ptp->io_base + HCLGE_PTP_TX_TS_SEC_L_REG);
+	hi = readl(hdev->ptp->io_base + HCLGE_PTP_TX_TS_SEC_H_REG) &
+	     HCLGE_PTP_TX_TS_SEC_H_MASK;
+	hdev->ptp->last_tx_seqid = readl(hdev->ptp->io_base +
+		HCLGE_PTP_TX_TS_SEQID_REG);
+
+	if (skb) {
+		hdev->ptp->tx_skb = NULL;
+		hdev->ptp->tx_cleaned++;
+
+		ns += (((u64)hi) << 32 | lo) * NSEC_PER_SEC;
+		hwts.hwtstamp = ns_to_ktime(ns);
+		skb_tstamp_tx(skb, &hwts);
+		dev_kfree_skb_any(skb);
+	}
+
+	clear_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state);
+}
+
+void hclge_ptp_get_rx_hwts(struct hnae3_handle *handle, struct sk_buff *skb,
+			   u32 nsec, u32 sec)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	unsigned long flags;
+	u64 ns = nsec;
+	u32 sec_h;
+
+	if (!test_bit(HCLGE_PTP_FLAG_RX_EN, &hdev->ptp->flags))
+		return;
+
+	/* Since the BD does not have enough space for the higher 16 bits of
+	 * second, and this part will not change frequently, so read it
+	 * from register.
+	 */
+	spin_lock_irqsave(&hdev->ptp->lock, flags);
+	sec_h = readl(hdev->ptp->io_base + HCLGE_PTP_CUR_TIME_SEC_H_REG);
+	spin_unlock_irqrestore(&hdev->ptp->lock, flags);
+
+	ns += (((u64)sec_h) << HCLGE_PTP_SEC_H_OFFSET | sec) * NSEC_PER_SEC;
+	skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(ns);
+	hdev->ptp->last_rx = jiffies;
+	hdev->ptp->rx_cnt++;
+}
+
+static int hclge_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
+			      struct ptp_system_timestamp *sts)
+{
+	struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp);
+	unsigned long flags;
+	u32 hi, lo;
+	u64 ns;
+
+	spin_lock_irqsave(&hdev->ptp->lock, flags);
+	ns = readl(hdev->ptp->io_base + HCLGE_PTP_CUR_TIME_NSEC_REG);
+	hi = readl(hdev->ptp->io_base + HCLGE_PTP_CUR_TIME_SEC_H_REG);
+	lo = readl(hdev->ptp->io_base + HCLGE_PTP_CUR_TIME_SEC_L_REG);
+	spin_unlock_irqrestore(&hdev->ptp->lock, flags);
+
+	ns += (((u64)hi) << HCLGE_PTP_SEC_H_OFFSET | lo) * NSEC_PER_SEC;
+	*ts = ns_to_timespec64(ns);
+
+	return 0;
+}
+
+static int hclge_ptp_settime(struct ptp_clock_info *ptp,
+			     const struct timespec64 *ts)
+{
+	struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp);
+	unsigned long flags;
+
+	spin_lock_irqsave(&hdev->ptp->lock, flags);
+	writel(ts->tv_nsec, hdev->ptp->io_base + HCLGE_PTP_TIME_NSEC_REG);
+	writel(ts->tv_sec >> HCLGE_PTP_SEC_H_OFFSET,
+	       hdev->ptp->io_base + HCLGE_PTP_TIME_SEC_H_REG);
+	writel(ts->tv_sec & HCLGE_PTP_SEC_L_MASK,
+	       hdev->ptp->io_base + HCLGE_PTP_TIME_SEC_L_REG);
+	/* synchronize the time of phc */
+	writel(HCLGE_PTP_TIME_SYNC_EN,
+	       hdev->ptp->io_base + HCLGE_PTP_TIME_SYNC_REG);
+	spin_unlock_irqrestore(&hdev->ptp->lock, flags);
+
+	return 0;
+}
+
+static int hclge_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp);
+	unsigned long flags;
+	bool is_neg = false;
+	u32 adj_val = 0;
+
+	if (delta < 0) {
+		adj_val |= HCLGE_PTP_TIME_NSEC_NEG;
+		delta = -delta;
+		is_neg = true;
+	}
+
+	if (delta > HCLGE_PTP_TIME_NSEC_MASK) {
+		struct timespec64 ts;
+		s64 ns;
+
+		hclge_ptp_gettimex(ptp, &ts, NULL);
+		ns = timespec64_to_ns(&ts);
+		ns = is_neg ? ns - delta : ns + delta;
+		ts = ns_to_timespec64(ns);
+		return hclge_ptp_settime(ptp, &ts);
+	}
+
+	adj_val |= delta & HCLGE_PTP_TIME_NSEC_MASK;
+
+	spin_lock_irqsave(&hdev->ptp->lock, flags);
+	writel(adj_val, hdev->ptp->io_base + HCLGE_PTP_TIME_NSEC_REG);
+	writel(HCLGE_PTP_TIME_ADJ_EN,
+	       hdev->ptp->io_base + HCLGE_PTP_TIME_ADJ_REG);
+	spin_unlock_irqrestore(&hdev->ptp->lock, flags);
+
+	return 0;
+}
+
+int hclge_ptp_get_cfg(struct hclge_dev *hdev, struct ifreq *ifr)
+{
+	if (!test_bit(HCLGE_STATE_PTP_EN, &hdev->state))
+		return -EOPNOTSUPP;
+
+	return copy_to_user(ifr->ifr_data, &hdev->ptp->ts_cfg,
+		sizeof(struct hwtstamp_config)) ? -EFAULT : 0;
+}
+
+static int hclge_ptp_int_en(struct hclge_dev *hdev, bool en)
+{
+	struct hclge_ptp_int_cmd *req;
+	struct hclge_desc desc;
+	int ret;
+
+	req = (struct hclge_ptp_int_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PTP_INT_EN, false);
+	req->int_en = en ? 1 : 0;
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"failed to %s ptp interrupt, ret = %d\n",
+			en ? "enable" : "disable", ret);
+
+	return ret;
+}
+
+int hclge_ptp_cfg_qry(struct hclge_dev *hdev, u32 *cfg)
+{
+	struct hclge_ptp_cfg_cmd *req;
+	struct hclge_desc desc;
+	int ret;
+
+	req = (struct hclge_ptp_cfg_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PTP_MODE_CFG, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to query ptp config, ret = %d\n", ret);
+		return ret;
+	}
+
+	*cfg = le32_to_cpu(req->cfg);
+
+	return 0;
+}
+
+static int hclge_ptp_cfg(struct hclge_dev *hdev, u32 cfg)
+{
+	struct hclge_ptp_cfg_cmd *req;
+	struct hclge_desc desc;
+	int ret;
+
+	req = (struct hclge_ptp_cfg_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PTP_MODE_CFG, false);
+	req->cfg = cpu_to_le32(cfg);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"failed to config ptp, ret = %d\n", ret);
+
+	return ret;
+}
+
+static int hclge_ptp_set_tx_mode(struct hwtstamp_config *cfg,
+				 unsigned long *flags, u32 *ptp_cfg)
+{
+	switch (cfg->tx_type) {
+	case HWTSTAMP_TX_OFF:
+		clear_bit(HCLGE_PTP_FLAG_TX_EN, flags);
+		break;
+	case HWTSTAMP_TX_ON:
+		set_bit(HCLGE_PTP_FLAG_TX_EN, flags);
+		*ptp_cfg |= HCLGE_PTP_TX_EN_B;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	return 0;
+}
+
+static int hclge_ptp_set_rx_mode(struct hwtstamp_config *cfg,
+				 unsigned long *flags, u32 *ptp_cfg)
+{
+	int rx_filter = cfg->rx_filter;
+
+	switch (cfg->rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		clear_bit(HCLGE_PTP_FLAG_RX_EN, flags);
+		break;
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+		set_bit(HCLGE_PTP_FLAG_RX_EN, flags);
+		*ptp_cfg |= HCLGE_PTP_RX_EN_B;
+		*ptp_cfg |= HCLGE_PTP_UDP_FULL_TYPE << HCLGE_PTP_UDP_EN_SHIFT;
+		rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+		set_bit(HCLGE_PTP_FLAG_RX_EN, flags);
+		*ptp_cfg |= HCLGE_PTP_RX_EN_B;
+		*ptp_cfg |= HCLGE_PTP_UDP_FULL_TYPE << HCLGE_PTP_UDP_EN_SHIFT;
+		*ptp_cfg |= HCLGE_PTP_MSG1_V2_DEFAULT << HCLGE_PTP_MSG1_SHIFT;
+		*ptp_cfg |= HCLGE_PTP_MSG0_V2_EVENT << HCLGE_PTP_MSG0_SHIFT;
+		*ptp_cfg |= HCLGE_PTP_MSG_TYPE_V2 << HCLGE_PTP_MSG_TYPE_SHIFT;
+		rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		break;
+	case HWTSTAMP_FILTER_ALL:
+	default:
+		return -ERANGE;
+	}
+
+	cfg->rx_filter = rx_filter;
+
+	return 0;
+}
+
+static int hclge_ptp_set_ts_mode(struct hclge_dev *hdev,
+				 struct hwtstamp_config *cfg)
+{
+	unsigned long flags = hdev->ptp->flags;
+	u32 ptp_cfg = 0;
+	int ret;
+
+	if (test_bit(HCLGE_PTP_FLAG_EN, &hdev->ptp->flags))
+		ptp_cfg |= HCLGE_PTP_EN_B;
+
+	ret = hclge_ptp_set_tx_mode(cfg, &flags, &ptp_cfg);
+	if (ret)
+		return ret;
+
+	ret = hclge_ptp_set_rx_mode(cfg, &flags, &ptp_cfg);
+	if (ret)
+		return ret;
+
+	ret = hclge_ptp_cfg(hdev, ptp_cfg);
+	if (ret)
+		return ret;
+
+	hdev->ptp->flags = flags;
+	hdev->ptp->ptp_cfg = ptp_cfg;
+
+	return 0;
+}
+
+int hclge_ptp_set_cfg(struct hclge_dev *hdev, struct ifreq *ifr)
+{
+	struct hwtstamp_config cfg;
+	int ret;
+
+	if (!test_bit(HCLGE_STATE_PTP_EN, &hdev->state)) {
+		dev_err(&hdev->pdev->dev, "phc is unsupported\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
+		return -EFAULT;
+
+	ret = hclge_ptp_set_ts_mode(hdev, &cfg);
+	if (ret)
+		return ret;
+
+	hdev->ptp->ts_cfg = cfg;
+
+	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+}
+
+int hclge_ptp_get_ts_info(struct hnae3_handle *handle,
+			  struct ethtool_ts_info *info)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	if (!test_bit(HCLGE_STATE_PTP_EN, &hdev->state)) {
+		dev_err(&hdev->pdev->dev, "phc is unsupported\n");
+		return -EOPNOTSUPP;
+	}
+
+	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+				SOF_TIMESTAMPING_RX_SOFTWARE |
+				SOF_TIMESTAMPING_SOFTWARE |
+				SOF_TIMESTAMPING_TX_HARDWARE |
+				SOF_TIMESTAMPING_RX_HARDWARE |
+				SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	if (hdev->ptp->clock)
+		info->phc_index = ptp_clock_index(hdev->ptp->clock);
+	else
+		info->phc_index = -1;
+
+	info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON);
+
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L2_SYNC) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ);
+
+	info->rx_filters |= BIT(HWTSTAMP_FILTER_PTP_V1_L4_SYNC) |
+			    BIT(HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) |
+			    BIT(HWTSTAMP_FILTER_PTP_V2_EVENT) |
+			    BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT) |
+			    BIT(HWTSTAMP_FILTER_PTP_V2_SYNC) |
+			    BIT(HWTSTAMP_FILTER_PTP_V2_L4_SYNC) |
+			    BIT(HWTSTAMP_FILTER_PTP_V2_DELAY_REQ) |
+			    BIT(HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ);
+
+	return 0;
+}
+
+static int hclge_ptp_create_clock(struct hclge_dev *hdev)
+{
+#define HCLGE_PTP_NAME_LEN	32
+
+	struct hclge_ptp *ptp;
+
+	ptp = devm_kzalloc(&hdev->pdev->dev, sizeof(*ptp), GFP_KERNEL);
+	if (!ptp)
+		return -ENOMEM;
+
+	ptp->hdev = hdev;
+	snprintf(ptp->info.name, HCLGE_PTP_NAME_LEN, "%s",
+		 HCLGE_DRIVER_NAME);
+	ptp->info.owner = THIS_MODULE;
+	ptp->info.max_adj = HCLGE_PTP_CYCLE_ADJ_MAX;
+	ptp->info.n_ext_ts = 0;
+	ptp->info.pps = 0;
+	ptp->info.adjfreq = hclge_ptp_adjfreq;
+	ptp->info.adjtime = hclge_ptp_adjtime;
+	ptp->info.gettimex64 = hclge_ptp_gettimex;
+	ptp->info.settime64 = hclge_ptp_settime;
+
+	ptp->info.n_alarm = 0;
+	ptp->clock = ptp_clock_register(&ptp->info, &hdev->pdev->dev);
+	if (IS_ERR(ptp->clock)) {
+		dev_err(&hdev->pdev->dev,
+			"%d failed to register ptp clock, ret = %ld\n",
+			ptp->info.n_alarm, PTR_ERR(ptp->clock));
+		return -ENODEV;
+	} else if (!ptp->clock) {
+		dev_err(&hdev->pdev->dev, "failed to register ptp clock\n");
+		return -ENODEV;
+	}
+
+	spin_lock_init(&ptp->lock);
+	ptp->io_base = hdev->hw.io_base + HCLGE_PTP_REG_OFFSET;
+	ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE;
+	ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF;
+	hdev->ptp = ptp;
+
+	return 0;
+}
+
+static void hclge_ptp_destroy_clock(struct hclge_dev *hdev)
+{
+	ptp_clock_unregister(hdev->ptp->clock);
+	hdev->ptp->clock = NULL;
+	devm_kfree(&hdev->pdev->dev, hdev->ptp);
+	hdev->ptp = NULL;
+}
+
+int hclge_ptp_init(struct hclge_dev *hdev)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+	struct timespec64 ts;
+	int ret;
+
+	if (!test_bit(HNAE3_DEV_SUPPORT_PTP_B, ae_dev->caps))
+		return 0;
+
+	if (!hdev->ptp) {
+		ret = hclge_ptp_create_clock(hdev);
+		if (ret)
+			return ret;
+	}
+
+	ret = hclge_ptp_int_en(hdev, true);
+	if (ret)
+		goto out;
+
+	set_bit(HCLGE_PTP_FLAG_EN, &hdev->ptp->flags);
+	ret = hclge_ptp_adjfreq(&hdev->ptp->info, 0);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to init freq, ret = %d\n", ret);
+		goto out;
+	}
+
+	ret = hclge_ptp_set_ts_mode(hdev, &hdev->ptp->ts_cfg);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to init ts mode, ret = %d\n", ret);
+		goto out;
+	}
+
+	ktime_get_real_ts64(&ts);
+	ret = hclge_ptp_settime(&hdev->ptp->info, &ts);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to init ts time, ret = %d\n", ret);
+		goto out;
+	}
+
+	set_bit(HCLGE_STATE_PTP_EN, &hdev->state);
+	dev_info(&hdev->pdev->dev, "phc initializes ok!\n");
+
+	return 0;
+
+out:
+	hclge_ptp_destroy_clock(hdev);
+
+	return ret;
+}
+
+void hclge_ptp_uninit(struct hclge_dev *hdev)
+{
+	struct hclge_ptp *ptp = hdev->ptp;
+
+	if (!ptp)
+		return;
+
+	hclge_ptp_int_en(hdev, false);
+	clear_bit(HCLGE_STATE_PTP_EN, &hdev->state);
+	clear_bit(HCLGE_PTP_FLAG_EN, &ptp->flags);
+	ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE;
+	ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF;
+
+	if (hclge_ptp_set_ts_mode(hdev, &ptp->ts_cfg))
+		dev_err(&hdev->pdev->dev, "failed to disable phc\n");
+
+	if (ptp->tx_skb) {
+		struct sk_buff *skb = ptp->tx_skb;
+
+		ptp->tx_skb = NULL;
+		dev_kfree_skb_any(skb);
+	}
+
+	hclge_ptp_destroy_clock(hdev);
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h
new file mode 100644
index 000000000000..b3ca7afdaaa6
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h
@@ -0,0 +1,134 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+// Copyright (c) 2021 Hisilicon Limited.
+
+#ifndef __HCLGE_PTP_H
+#define __HCLGE_PTP_H
+
+#include <linux/ptp_clock_kernel.h>
+#include <linux/net_tstamp.h>
+#include <linux/types.h>
+
+#define HCLGE_PTP_REG_OFFSET	0x29000
+
+#define HCLGE_PTP_TX_TS_SEQID_REG	0x0
+#define HCLGE_PTP_TX_TS_NSEC_REG	0x4
+#define HCLGE_PTP_TX_TS_NSEC_MASK	GENMASK(29, 0)
+#define HCLGE_PTP_TX_TS_SEC_L_REG	0x8
+#define HCLGE_PTP_TX_TS_SEC_H_REG	0xC
+#define HCLGE_PTP_TX_TS_SEC_H_MASK	GENMASK(15, 0)
+#define HCLGE_PTP_TX_TS_CNT_REG		0x30
+
+#define HCLGE_PTP_TIME_SEC_H_REG	0x50
+#define HCLGE_PTP_TIME_SEC_H_MASK	GENMASK(15, 0)
+#define HCLGE_PTP_TIME_SEC_L_REG	0x54
+#define HCLGE_PTP_TIME_NSEC_REG		0x58
+#define HCLGE_PTP_TIME_NSEC_MASK	GENMASK(29, 0)
+#define HCLGE_PTP_TIME_NSEC_NEG		BIT(31)
+#define HCLGE_PTP_TIME_SYNC_REG		0x5C
+#define HCLGE_PTP_TIME_SYNC_EN		BIT(0)
+#define HCLGE_PTP_TIME_ADJ_REG		0x60
+#define HCLGE_PTP_TIME_ADJ_EN		BIT(0)
+#define HCLGE_PTP_CYCLE_QUO_REG		0x64
+#define HCLGE_PTP_CYCLE_DEN_REG		0x68
+#define HCLGE_PTP_CYCLE_NUM_REG		0x6C
+#define HCLGE_PTP_CYCLE_CFG_REG		0x70
+#define HCLGE_PTP_CYCLE_ADJ_EN		BIT(0)
+#define HCLGE_PTP_CUR_TIME_SEC_H_REG	0x74
+#define HCLGE_PTP_CUR_TIME_SEC_L_REG	0x78
+#define HCLGE_PTP_CUR_TIME_NSEC_REG	0x7C
+
+#define HCLGE_PTP_CYCLE_ADJ_BASE	2
+#define HCLGE_PTP_CYCLE_ADJ_MAX		500000000
+#define HCLGE_PTP_CYCLE_ADJ_UNIT	100000000
+#define HCLGE_PTP_SEC_H_OFFSET		32u
+#define HCLGE_PTP_SEC_L_MASK		GENMASK(31, 0)
+
+#define HCLGE_PTP_FLAG_EN		BIT(0)
+#define HCLGE_PTP_FLAG_TX_EN		BIT(1)
+#define HCLGE_PTP_FLAG_RX_EN		BIT(2)
+
+struct hclge_ptp {
+	struct hclge_dev *hdev;
+	struct ptp_clock *clock;
+	struct sk_buff *tx_skb;
+	unsigned long flags;
+	void __iomem *io_base;
+	struct ptp_clock_info info;
+	struct hwtstamp_config ts_cfg;
+	spinlock_t lock;	/* protects ptp registers */
+	u32 ptp_cfg;
+	u32 last_tx_seqid;
+	unsigned long tx_start;
+	unsigned long tx_cnt;
+	unsigned long tx_skipped;
+	unsigned long tx_cleaned;
+	unsigned long last_rx;
+	unsigned long rx_cnt;
+	unsigned long tx_timeout;
+};
+
+struct hclge_ptp_int_cmd {
+#define HCLGE_PTP_INT_EN_B	BIT(0)
+
+	u8 int_en;
+	u8 rsvd[23];
+};
+
+enum hclge_ptp_udp_type {
+	HCLGE_PTP_UDP_NOT_TYPE,
+	HCLGE_PTP_UDP_P13F_TYPE,
+	HCLGE_PTP_UDP_P140_TYPE,
+	HCLGE_PTP_UDP_FULL_TYPE,
+};
+
+enum hclge_ptp_msg_type {
+	HCLGE_PTP_MSG_TYPE_V2_L2,
+	HCLGE_PTP_MSG_TYPE_V2,
+	HCLGE_PTP_MSG_TYPE_V2_EVENT,
+};
+
+enum hclge_ptp_msg0_type {
+	HCLGE_PTP_MSG0_V2_DELAY_REQ = 1,
+	HCLGE_PTP_MSG0_V2_PDELAY_REQ,
+	HCLGE_PTP_MSG0_V2_DELAY_RESP,
+	HCLGE_PTP_MSG0_V2_EVENT = 0xF,
+};
+
+#define HCLGE_PTP_MSG1_V2_DEFAULT	1
+
+struct hclge_ptp_cfg_cmd {
+#define HCLGE_PTP_EN_B			BIT(0)
+#define HCLGE_PTP_TX_EN_B		BIT(1)
+#define HCLGE_PTP_RX_EN_B		BIT(2)
+#define HCLGE_PTP_UDP_EN_SHIFT		3
+#define HCLGE_PTP_UDP_EN_MASK		GENMASK(4, 3)
+#define HCLGE_PTP_MSG_TYPE_SHIFT	8
+#define HCLGE_PTP_MSG_TYPE_MASK		GENMASK(9, 8)
+#define HCLGE_PTP_MSG1_SHIFT		16
+#define HCLGE_PTP_MSG1_MASK		GENMASK(19, 16)
+#define HCLGE_PTP_MSG0_SHIFT		24
+#define HCLGE_PTP_MSG0_MASK		GENMASK(27, 24)
+
+	__le32 cfg;
+	u8 rsvd[20];
+};
+
+static inline struct hclge_dev *hclge_ptp_get_hdev(struct ptp_clock_info *info)
+{
+	struct hclge_ptp *ptp = container_of(info, struct hclge_ptp, info);
+
+	return ptp->hdev;
+}
+
+bool hclge_ptp_set_tx_info(struct hnae3_handle *handle, struct sk_buff *skb);
+void hclge_ptp_clean_tx_hwts(struct hclge_dev *dev);
+void hclge_ptp_get_rx_hwts(struct hnae3_handle *handle, struct sk_buff *skb,
+			   u32 nsec, u32 sec);
+int hclge_ptp_get_cfg(struct hclge_dev *hdev, struct ifreq *ifr);
+int hclge_ptp_set_cfg(struct hclge_dev *hdev, struct ifreq *ifr);
+int hclge_ptp_init(struct hclge_dev *hdev);
+void hclge_ptp_uninit(struct hclge_dev *hdev);
+int hclge_ptp_get_ts_info(struct hnae3_handle *handle,
+			  struct ethtool_ts_info *info);
+int hclge_ptp_cfg_qry(struct hclge_dev *hdev, u32 *cfg);
+#endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index ebb962bad451..78d5bf1ea561 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -1733,6 +1733,36 @@ int hclge_tm_get_qset_weight(struct hclge_dev *hdev, u16 qset_id, u8 *weight)
 	return 0;
 }
 
+int hclge_tm_get_qset_shaper(struct hclge_dev *hdev, u16 qset_id,
+			     struct hclge_tm_shaper_para *para)
+{
+	struct hclge_qs_shapping_cmd *shap_cfg_cmd;
+	struct hclge_desc desc;
+	u32 shapping_para;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QCN_SHAPPING_CFG, true);
+	shap_cfg_cmd = (struct hclge_qs_shapping_cmd *)desc.data;
+	shap_cfg_cmd->qs_id = cpu_to_le16(qset_id);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to get qset %u shaper, ret = %d\n", qset_id,
+			ret);
+		return ret;
+	}
+
+	shapping_para = le32_to_cpu(shap_cfg_cmd->qs_shapping_para);
+	para->ir_b = hclge_tm_get_field(shapping_para, IR_B);
+	para->ir_u = hclge_tm_get_field(shapping_para, IR_U);
+	para->ir_s = hclge_tm_get_field(shapping_para, IR_S);
+	para->bs_b = hclge_tm_get_field(shapping_para, BS_B);
+	para->bs_s = hclge_tm_get_field(shapping_para, BS_S);
+	para->flag = shap_cfg_cmd->flag;
+	para->rate = le32_to_cpu(shap_cfg_cmd->qs_rate);
+	return 0;
+}
+
 int hclge_tm_get_pri_sch_mode(struct hclge_dev *hdev, u8 pri_id, u8 *mode)
 {
 	struct hclge_pri_sch_mode_cfg_cmd *pri_sch_mode;
@@ -1775,7 +1805,7 @@ int hclge_tm_get_pri_weight(struct hclge_dev *hdev, u8 pri_id, u8 *weight)
 
 int hclge_tm_get_pri_shaper(struct hclge_dev *hdev, u8 pri_id,
 			    enum hclge_opcode_type cmd,
-			    struct hclge_pri_shaper_para *para)
+			    struct hclge_tm_shaper_para *para)
 {
 	struct hclge_pri_shapping_cmd *shap_cfg_cmd;
 	struct hclge_desc desc;
@@ -1807,3 +1837,186 @@ int hclge_tm_get_pri_shaper(struct hclge_dev *hdev, u8 pri_id,
 	para->rate = le32_to_cpu(shap_cfg_cmd->pri_rate);
 	return 0;
 }
+
+int hclge_tm_get_q_to_qs_map(struct hclge_dev *hdev, u16 q_id, u16 *qset_id)
+{
+	struct hclge_nq_to_qs_link_cmd *map;
+	struct hclge_desc desc;
+	u16 qs_id_l;
+	u16 qs_id_h;
+	int ret;
+
+	map = (struct hclge_nq_to_qs_link_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_NQ_TO_QS_LINK, true);
+	map->nq_id = cpu_to_le16(q_id);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to get queue to qset map, ret = %d\n", ret);
+		return ret;
+	}
+	*qset_id = le16_to_cpu(map->qset_id);
+
+	/* convert qset_id to the following format, drop the vld bit
+	 *            | qs_id_h | vld | qs_id_l |
+	 * qset_id:   | 15 ~ 11 |  10 |  9 ~ 0  |
+	 *             \         \   /         /
+	 *              \         \ /         /
+	 * qset_id: | 15 | 14 ~ 10 |  9 ~ 0  |
+	 */
+	qs_id_l = hnae3_get_field(*qset_id, HCLGE_TM_QS_ID_L_MSK,
+				  HCLGE_TM_QS_ID_L_S);
+	qs_id_h = hnae3_get_field(*qset_id, HCLGE_TM_QS_ID_H_EXT_MSK,
+				  HCLGE_TM_QS_ID_H_EXT_S);
+	*qset_id = 0;
+	hnae3_set_field(*qset_id, HCLGE_TM_QS_ID_L_MSK, HCLGE_TM_QS_ID_L_S,
+			qs_id_l);
+	hnae3_set_field(*qset_id, HCLGE_TM_QS_ID_H_MSK, HCLGE_TM_QS_ID_H_S,
+			qs_id_h);
+	return 0;
+}
+
+int hclge_tm_get_q_to_tc(struct hclge_dev *hdev, u16 q_id, u8 *tc_id)
+{
+#define HCLGE_TM_TC_MASK		0x7
+
+	struct hclge_tqp_tx_queue_tc_cmd *tc;
+	struct hclge_desc desc;
+	int ret;
+
+	tc = (struct hclge_tqp_tx_queue_tc_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TQP_TX_QUEUE_TC, true);
+	tc->queue_id = cpu_to_le16(q_id);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to get queue to tc map, ret = %d\n", ret);
+		return ret;
+	}
+
+	*tc_id = tc->tc_id & HCLGE_TM_TC_MASK;
+	return 0;
+}
+
+int hclge_tm_get_pg_to_pri_map(struct hclge_dev *hdev, u8 pg_id,
+			       u8 *pri_bit_map)
+{
+	struct hclge_pg_to_pri_link_cmd *map;
+	struct hclge_desc desc;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PG_TO_PRI_LINK, true);
+	map = (struct hclge_pg_to_pri_link_cmd *)desc.data;
+	map->pg_id = pg_id;
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to get pg to pri map, ret = %d\n", ret);
+		return ret;
+	}
+
+	*pri_bit_map = map->pri_bit_map;
+	return 0;
+}
+
+int hclge_tm_get_pg_weight(struct hclge_dev *hdev, u8 pg_id, u8 *weight)
+{
+	struct hclge_pg_weight_cmd *pg_weight_cmd;
+	struct hclge_desc desc;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PG_WEIGHT, true);
+	pg_weight_cmd = (struct hclge_pg_weight_cmd *)desc.data;
+	pg_weight_cmd->pg_id = pg_id;
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to get pg weight, ret = %d\n", ret);
+		return ret;
+	}
+
+	*weight = pg_weight_cmd->dwrr;
+	return 0;
+}
+
+int hclge_tm_get_pg_sch_mode(struct hclge_dev *hdev, u8 pg_id, u8 *mode)
+{
+	struct hclge_desc desc;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PG_SCH_MODE_CFG, true);
+	desc.data[0] = cpu_to_le32(pg_id);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to get pg sch mode, ret = %d\n", ret);
+		return ret;
+	}
+
+	*mode = (u8)le32_to_cpu(desc.data[1]);
+	return 0;
+}
+
+int hclge_tm_get_pg_shaper(struct hclge_dev *hdev, u8 pg_id,
+			   enum hclge_opcode_type cmd,
+			   struct hclge_tm_shaper_para *para)
+{
+	struct hclge_pg_shapping_cmd *shap_cfg_cmd;
+	struct hclge_desc desc;
+	u32 shapping_para;
+	int ret;
+
+	if (cmd != HCLGE_OPC_TM_PG_C_SHAPPING &&
+	    cmd != HCLGE_OPC_TM_PG_P_SHAPPING)
+		return -EINVAL;
+
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	shap_cfg_cmd = (struct hclge_pg_shapping_cmd *)desc.data;
+	shap_cfg_cmd->pg_id = pg_id;
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to get pg shaper(%#x), ret = %d\n",
+			cmd, ret);
+		return ret;
+	}
+
+	shapping_para = le32_to_cpu(shap_cfg_cmd->pg_shapping_para);
+	para->ir_b = hclge_tm_get_field(shapping_para, IR_B);
+	para->ir_u = hclge_tm_get_field(shapping_para, IR_U);
+	para->ir_s = hclge_tm_get_field(shapping_para, IR_S);
+	para->bs_b = hclge_tm_get_field(shapping_para, BS_B);
+	para->bs_s = hclge_tm_get_field(shapping_para, BS_S);
+	para->flag = shap_cfg_cmd->flag;
+	para->rate = le32_to_cpu(shap_cfg_cmd->pg_rate);
+	return 0;
+}
+
+int hclge_tm_get_port_shaper(struct hclge_dev *hdev,
+			     struct hclge_tm_shaper_para *para)
+{
+	struct hclge_port_shapping_cmd *port_shap_cfg_cmd;
+	struct hclge_desc desc;
+	u32 shapping_para;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PORT_SHAPPING, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to get port shaper, ret = %d\n", ret);
+		return ret;
+	}
+
+	port_shap_cfg_cmd = (struct hclge_port_shapping_cmd *)desc.data;
+	shapping_para = le32_to_cpu(port_shap_cfg_cmd->port_shapping_para);
+	para->ir_b = hclge_tm_get_field(shapping_para, IR_B);
+	para->ir_u = hclge_tm_get_field(shapping_para, IR_U);
+	para->ir_s = hclge_tm_get_field(shapping_para, IR_S);
+	para->bs_b = hclge_tm_get_field(shapping_para, BS_B);
+	para->bs_s = hclge_tm_get_field(shapping_para, BS_S);
+	para->flag = port_shap_cfg_cmd->flag;
+	para->rate = le32_to_cpu(port_shap_cfg_cmd->port_rate);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index b25d76023af0..2ee9b795f71d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -199,14 +199,14 @@ struct hclge_tm_nodes_cmd {
 	__le16 queue_num;
 };
 
-struct hclge_pri_shaper_para {
+struct hclge_tm_shaper_para {
+	u32 rate;
 	u8 ir_b;
 	u8 ir_u;
 	u8 ir_s;
 	u8 bs_b;
 	u8 bs_s;
 	u8 flag;
-	u32 rate;
 };
 
 #define hclge_tm_set_field(dest, string, val) \
@@ -237,9 +237,22 @@ int hclge_tm_get_qset_map_pri(struct hclge_dev *hdev, u16 qset_id, u8 *priority,
 			      u8 *link_vld);
 int hclge_tm_get_qset_sch_mode(struct hclge_dev *hdev, u16 qset_id, u8 *mode);
 int hclge_tm_get_qset_weight(struct hclge_dev *hdev, u16 qset_id, u8 *weight);
+int hclge_tm_get_qset_shaper(struct hclge_dev *hdev, u16 qset_id,
+			     struct hclge_tm_shaper_para *para);
 int hclge_tm_get_pri_sch_mode(struct hclge_dev *hdev, u8 pri_id, u8 *mode);
 int hclge_tm_get_pri_weight(struct hclge_dev *hdev, u8 pri_id, u8 *weight);
 int hclge_tm_get_pri_shaper(struct hclge_dev *hdev, u8 pri_id,
 			    enum hclge_opcode_type cmd,
-			    struct hclge_pri_shaper_para *para);
+			    struct hclge_tm_shaper_para *para);
+int hclge_tm_get_q_to_qs_map(struct hclge_dev *hdev, u16 q_id, u16 *qset_id);
+int hclge_tm_get_q_to_tc(struct hclge_dev *hdev, u16 q_id, u8 *tc_id);
+int hclge_tm_get_pg_to_pri_map(struct hclge_dev *hdev, u8 pg_id,
+			       u8 *pri_bit_map);
+int hclge_tm_get_pg_weight(struct hclge_dev *hdev, u8 pg_id, u8 *weight);
+int hclge_tm_get_pg_sch_mode(struct hclge_dev *hdev, u8 pg_id, u8 *mode);
+int hclge_tm_get_pg_shaper(struct hclge_dev *hdev, u8 pg_id,
+			   enum hclge_opcode_type cmd,
+			   struct hclge_tm_shaper_para *para);
+int hclge_tm_get_port_shaper(struct hclge_dev *hdev,
+			     struct hclge_tm_shaper_para *para);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
index d8c5c5810b99..bd19a2d89f6c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
@@ -359,6 +359,8 @@ static void hclgevf_parse_capability(struct hclgevf_dev *hdev,
 		set_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps);
 	if (hnae3_get_bit(caps, HCLGEVF_CAP_UDP_TUNNEL_CSUM_B))
 		set_bit(HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, ae_dev->caps);
+	if (hnae3_get_bit(caps, HCLGEVF_CAP_RXD_ADV_LAYOUT_B))
+		set_bit(HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B, ae_dev->caps);
 }
 
 static __le32 hclgevf_build_api_caps(void)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
index c6dc11b32aa7..202feb70dba5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
@@ -159,6 +159,7 @@ enum HCLGEVF_CAP_BITS {
 	HCLGEVF_CAP_HW_PAD_B,
 	HCLGEVF_CAP_STASH_B,
 	HCLGEVF_CAP_UDP_TUNNEL_CSUM_B,
+	HCLGEVF_CAP_RXD_ADV_LAYOUT_B = 15,
 };
 
 enum HCLGEVF_API_CAP_BITS {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 0db51ef15ef6..52eaf82b7cd7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -243,23 +243,31 @@ static void hclgevf_build_send_msg(struct hclge_vf_to_pf_msg *msg, u8 code,
 	}
 }
 
-static int hclgevf_get_tc_info(struct hclgevf_dev *hdev)
+static int hclgevf_get_basic_info(struct hclgevf_dev *hdev)
 {
+	struct hnae3_ae_dev *ae_dev = hdev->ae_dev;
+	u8 resp_msg[HCLGE_MBX_MAX_RESP_DATA_SIZE];
+	struct hclge_basic_info *basic_info;
 	struct hclge_vf_to_pf_msg send_msg;
-	u8 resp_msg;
+	unsigned long caps;
 	int status;
 
-	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_GET_TCINFO, 0);
-	status = hclgevf_send_mbx_msg(hdev, &send_msg, true, &resp_msg,
+	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_GET_BASIC_INFO, 0);
+	status = hclgevf_send_mbx_msg(hdev, &send_msg, true, resp_msg,
 				      sizeof(resp_msg));
 	if (status) {
 		dev_err(&hdev->pdev->dev,
-			"VF request to get TC info from PF failed %d",
-			status);
+			"failed to get basic info from pf, ret = %d", status);
 		return status;
 	}
 
-	hdev->hw_tc_map = resp_msg;
+	basic_info = (struct hclge_basic_info *)resp_msg;
+
+	hdev->hw_tc_map = basic_info->hw_tc_map;
+	hdev->mbx_api_version = basic_info->mbx_api_version;
+	caps = basic_info->pf_caps;
+	if (test_bit(HNAE3_PF_SUPPORT_VLAN_FLTR_MDF_B, &caps))
+		set_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps);
 
 	return 0;
 }
@@ -1528,8 +1536,7 @@ static void hclgevf_sync_from_add_list(struct list_head *add_list,
 			kfree(mac_node);
 		} else if (mac_node->state == HCLGEVF_MAC_ACTIVE) {
 			mac_node->state = HCLGEVF_MAC_TO_DEL;
-			list_del(&mac_node->node);
-			list_add_tail(&mac_node->node, mac_list);
+			list_move_tail(&mac_node->node, mac_list);
 		} else {
 			list_del(&mac_node->node);
 			kfree(mac_node);
@@ -1554,8 +1561,7 @@ static void hclgevf_sync_from_del_list(struct list_head *del_list,
 			list_del(&mac_node->node);
 			kfree(mac_node);
 		} else {
-			list_del(&mac_node->node);
-			list_add_tail(&mac_node->node, mac_list);
+			list_move_tail(&mac_node->node, mac_list);
 		}
 	}
 }
@@ -1591,8 +1597,7 @@ static void hclgevf_sync_mac_list(struct hclgevf_dev *hdev,
 	list_for_each_entry_safe(mac_node, tmp, list, node) {
 		switch (mac_node->state) {
 		case HCLGEVF_MAC_TO_DEL:
-			list_del(&mac_node->node);
-			list_add_tail(&mac_node->node, &tmp_del_list);
+			list_move_tail(&mac_node->node, &tmp_del_list);
 			break;
 		case HCLGEVF_MAC_TO_ADD:
 			new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC);
@@ -1642,6 +1647,22 @@ static void hclgevf_uninit_mac_list(struct hclgevf_dev *hdev)
 	spin_unlock_bh(&hdev->mac_table.mac_list_lock);
 }
 
+static int hclgevf_enable_vlan_filter(struct hnae3_handle *handle, bool enable)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	struct hnae3_ae_dev *ae_dev = hdev->ae_dev;
+	struct hclge_vf_to_pf_msg send_msg;
+
+	if (!test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps))
+		return -EOPNOTSUPP;
+
+	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_VLAN,
+			       HCLGE_MBX_ENABLE_VLAN_FILTER);
+	send_msg.data[0] = enable ? 1 : 0;
+
+	return hclgevf_send_mbx_msg(hdev, &send_msg, true, NULL, 0);
+}
+
 static int hclgevf_set_vlan_filter(struct hnae3_handle *handle,
 				   __be16 proto, u16 vlan_id,
 				   bool is_kill)
@@ -2466,6 +2487,10 @@ static int hclgevf_configure(struct hclgevf_dev *hdev)
 {
 	int ret;
 
+	ret = hclgevf_get_basic_info(hdev);
+	if (ret)
+		return ret;
+
 	/* get current port based vlan state from PF */
 	ret = hclgevf_get_port_base_vlan_filter_state(hdev);
 	if (ret)
@@ -2481,12 +2506,7 @@ static int hclgevf_configure(struct hclgevf_dev *hdev)
 	if (ret)
 		return ret;
 
-	ret = hclgevf_get_pf_media_type(hdev);
-	if (ret)
-		return ret;
-
-	/* get tc configuration from PF */
-	return hclgevf_get_tc_info(hdev);
+	return hclgevf_get_pf_media_type(hdev);
 }
 
 static int hclgevf_alloc_hdev(struct hnae3_ae_dev *ae_dev)
@@ -3242,6 +3262,18 @@ static int hclgevf_clear_vport_list(struct hclgevf_dev *hdev)
 	return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0);
 }
 
+static void hclgevf_init_rxd_adv_layout(struct hclgevf_dev *hdev)
+{
+	if (hnae3_ae_dev_rxd_adv_layout_supported(hdev->ae_dev))
+		hclgevf_write_dev(&hdev->hw, HCLGEVF_RXD_ADV_LAYOUT_EN_REG, 1);
+}
+
+static void hclgevf_uninit_rxd_adv_layout(struct hclgevf_dev *hdev)
+{
+	if (hnae3_ae_dev_rxd_adv_layout_supported(hdev->ae_dev))
+		hclgevf_write_dev(&hdev->hw, HCLGEVF_RXD_ADV_LAYOUT_EN_REG, 0);
+}
+
 static int hclgevf_reset_hdev(struct hclgevf_dev *hdev)
 {
 	struct pci_dev *pdev = hdev->pdev;
@@ -3279,6 +3311,8 @@ static int hclgevf_reset_hdev(struct hclgevf_dev *hdev)
 
 	set_bit(HCLGEVF_STATE_PROMISC_CHANGED, &hdev->state);
 
+	hclgevf_init_rxd_adv_layout(hdev);
+
 	dev_info(&hdev->pdev->dev, "Reset done\n");
 
 	return 0;
@@ -3379,6 +3413,8 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		goto err_config;
 	}
 
+	hclgevf_init_rxd_adv_layout(hdev);
+
 	hdev->last_reset_time = jiffies;
 	dev_info(&hdev->pdev->dev, "finished initializing %s driver\n",
 		 HCLGEVF_DRIVER_NAME);
@@ -3405,6 +3441,7 @@ static void hclgevf_uninit_hdev(struct hclgevf_dev *hdev)
 	struct hclge_vf_to_pf_msg send_msg;
 
 	hclgevf_state_uninit(hdev);
+	hclgevf_uninit_rxd_adv_layout(hdev);
 
 	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_VF_UNINIT, 0);
 	hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0);
@@ -3784,6 +3821,7 @@ static const struct hnae3_ae_ops hclgevf_ops = {
 	.get_tc_size = hclgevf_get_tc_size,
 	.get_fw_version = hclgevf_get_fw_version,
 	.set_vlan_filter = hclgevf_set_vlan_filter,
+	.enable_vlan_filter = hclgevf_enable_vlan_filter,
 	.enable_hw_strip_rxvtag = hclgevf_en_hw_strip_rxvtag,
 	.reset_event = hclgevf_reset_event,
 	.set_default_reset_request = hclgevf_set_def_reset_request,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 265c9b0b4728..d7d02848d674 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -47,6 +47,7 @@
 
 /* bar registers for common func */
 #define HCLGEVF_GRO_EN_REG			0x28000
+#define HCLGEVF_RXD_ADV_LAYOUT_EN_REG		0x28008
 
 /* bar registers for rcb */
 #define HCLGEVF_RING_RX_ADDR_L_REG		0x80000
@@ -284,6 +285,7 @@ struct hclgevf_dev {
 	struct semaphore reset_sem;	/* protect reset process */
 
 	u32 fw_version;
+	u16 mbx_api_version;
 	u16 num_tqps;		/* num task queue pairs of this VF */
 
 	u16 alloc_rss_size;	/* allocated RSS task queue */
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
index dc024ef521c0..162d3c330dec 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
@@ -1663,7 +1663,6 @@ static void hinic_diag_test(struct net_device *netdev,
 	err = hinic_port_link_state(nic_dev, &link_state);
 	if (!err && link_state == HINIC_LINK_STATE_UP)
 		netif_carrier_on(netdev);
-
 }
 
 static int hinic_set_phys_id(struct net_device *netdev,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
index 5a6bbee819cd..307a6d4af993 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
@@ -223,7 +223,7 @@ static void cmdq_prepare_wqe_ctrl(struct hinic_cmdq_wqe *wqe, int wrapped,
 	saved_data = CMDQ_WQE_HEADER(wqe)->saved_data;
 	saved_data = HINIC_SAVED_DATA_CLEAR(saved_data, ARM);
 
-	if ((cmd == CMDQ_SET_ARM_CMD) && (mod == HINIC_MOD_COMM))
+	if (cmd == CMDQ_SET_ARM_CMD && mod == HINIC_MOD_COMM)
 		CMDQ_WQE_HEADER(wqe)->saved_data |=
 						HINIC_SAVED_DATA_SET(1, ARM);
 	else
@@ -594,7 +594,7 @@ static void cmdq_update_errcode(struct hinic_cmdq *cmdq, u16 prod_idx,
 }
 
 /**
- * cmdq_arm_ceq_handler - cmdq completion event handler for sync command
+ * cmdq_sync_cmd_handler - cmdq completion event handler for sync command
  * @cmdq: the cmdq of the command
  * @cons_idx: the consumer index to update the error code for
  * @errcode: the error code
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index 0c74f6674634..428108eb10d2 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -48,7 +48,7 @@ enum io_status {
 };
 
 /**
- * get_capability - convert device capabilities to NIC capabilities
+ * parse_capability - convert device capabilities to NIC capabilities
  * @hwdev: the HW device to set and convert device capabilities for
  * @dev_cap: device capabilities from FW
  *
@@ -92,7 +92,7 @@ static int parse_capability(struct hinic_hwdev *hwdev,
 }
 
 /**
- * get_cap_from_fw - get device capabilities from FW
+ * get_capability - get device capabilities from FW
  * @pfhwdev: the PF HW device to get capabilities for
  *
  * Return 0 - Success, negative - Failure
@@ -257,7 +257,7 @@ static int init_fw_ctxt(struct hinic_hwdev *hwdev)
 	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_FWCTXT_INIT,
 				 &fw_ctxt, sizeof(fw_ctxt),
 				 &fw_ctxt, &out_size);
-	if (err || (out_size != sizeof(fw_ctxt)) || fw_ctxt.status) {
+	if (err || out_size != sizeof(fw_ctxt) || fw_ctxt.status) {
 		dev_err(&pdev->dev, "Failed to init FW ctxt, err: %d, status: 0x%x, out size: 0x%x\n",
 			err, fw_ctxt.status, out_size);
 		return -EIO;
@@ -346,7 +346,7 @@ static int wait_for_db_state(struct hinic_hwdev *hwdev)
 }
 
 /**
- * clear_io_resource - set the IO resources as not active in the NIC
+ * clear_io_resources - set the IO resources as not active in the NIC
  * @hwdev: the NIC HW device
  *
  * Return 0 - Success, negative - Failure
@@ -424,7 +424,7 @@ static int get_base_qpn(struct hinic_hwdev *hwdev, u16 *base_qpn)
 	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_GLOBAL_QPN,
 				 &cmd_base_qpn, sizeof(cmd_base_qpn),
 				 &cmd_base_qpn, &out_size);
-	if (err || (out_size != sizeof(cmd_base_qpn)) || cmd_base_qpn.status) {
+	if (err || out_size != sizeof(cmd_base_qpn) || cmd_base_qpn.status) {
 		dev_err(&pdev->dev, "Failed to get base qpn, err: %d, status: 0x%x, out size: 0x%x\n",
 			err, cmd_base_qpn.status, out_size);
 		return -EIO;
@@ -605,8 +605,8 @@ static void nic_mgmt_msg_handler(void *handle, u8 cmd, void *buf_in,
 	hwif = hwdev->hwif;
 	pdev = hwif->pdev;
 
-	if ((cmd < HINIC_MGMT_MSG_CMD_BASE) ||
-	    (cmd >= HINIC_MGMT_MSG_CMD_MAX)) {
+	if (cmd < HINIC_MGMT_MSG_CMD_BASE ||
+	    cmd >= HINIC_MGMT_MSG_CMD_MAX) {
 		dev_err(&pdev->dev, "unknown L2NIC event, cmd = %d\n", cmd);
 		return;
 	}
@@ -619,7 +619,7 @@ static void nic_mgmt_msg_handler(void *handle, u8 cmd, void *buf_in,
 			   HINIC_CB_ENABLED,
 			   HINIC_CB_ENABLED | HINIC_CB_RUNNING);
 
-	if ((cb_state == HINIC_CB_ENABLED) && (nic_cb->handler))
+	if (cb_state == HINIC_CB_ENABLED && nic_cb->handler)
 		nic_cb->handler(nic_cb->handle, buf_in,
 				in_size, buf_out, out_size);
 	else
@@ -1090,7 +1090,7 @@ struct hinic_sq *hinic_hwdev_get_sq(struct hinic_hwdev *hwdev, int i)
 }
 
 /**
- * hinic_hwdev_get_sq - get RQ
+ * hinic_hwdev_get_rq - get RQ
  * @hwdev: the NIC HW device
  * @i: the position of the RQ
  *
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
index 19942fef99d9..d3fc05a07fdb 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
@@ -254,8 +254,8 @@ static void aeq_irq_handler(struct hinic_eq *eq)
 					    HINIC_EQE_ENABLED,
 					    HINIC_EQE_ENABLED |
 					    HINIC_EQE_RUNNING);
-			if ((eqe_state == HINIC_EQE_ENABLED) &&
-			    (hwe_cb->hwe_handler))
+			if (eqe_state == HINIC_EQE_ENABLED &&
+			    hwe_cb->hwe_handler)
 				hwe_cb->hwe_handler(hwe_cb->handle,
 						    aeqe_curr->data, size);
 			else
@@ -299,7 +299,7 @@ static void ceq_event_handler(struct hinic_ceqs *ceqs, u32 ceqe)
 			    HINIC_EQE_ENABLED,
 			    HINIC_EQE_ENABLED | HINIC_EQE_RUNNING);
 
-	if ((eqe_state == HINIC_EQE_ENABLED) && (ceq_cb->handler))
+	if (eqe_state == HINIC_EQE_ENABLED && ceq_cb->handler)
 		ceq_cb->handler(ceq_cb->handle, CEQE_DATA(ceqe));
 	else
 		dev_err(&pdev->dev, "Unhandled CEQ Event %d\n", event);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
index cab38ff0713c..0428faa68e80 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
@@ -334,7 +334,7 @@ static void set_dma_attr(struct hinic_hwif *hwif, u32 entry_idx,
 }
 
 /**
- * dma_attr_table_init - initialize the default dma attributes
+ * dma_attr_init - initialize the default dma attributes
  * @hwif: the HW interface of a pci function device
  **/
 static void dma_attr_init(struct hinic_hwif *hwif)
@@ -395,7 +395,7 @@ static void __print_selftest_reg(struct hinic_hwif *hwif)
 /**
  * hinic_init_hwif - initialize the hw interface
  * @hwif: the HW interface of a pci function device
- * @pdev: the pci device for acessing PCI resources
+ * @pdev: the pci device for accessing PCI resources
  *
  * Return 0 - Success, negative - Failure
  **/
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
index 4ef4008e65bd..a6e43d686293 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
@@ -137,7 +137,7 @@ static int write_sq_ctxts(struct hinic_func_to_io *func_to_io, u16 base_qpn,
 	err = hinic_cmdq_direct_resp(&func_to_io->cmdqs, HINIC_MOD_L2NIC,
 				     IO_CMD_MODIFY_QUEUE_CTXT, &cmdq_buf,
 				     &out_param);
-	if ((err) || (out_param != 0)) {
+	if (err || out_param != 0) {
 		dev_err(&pdev->dev, "Failed to set SQ ctxts\n");
 		err = -EFAULT;
 	}
@@ -181,7 +181,7 @@ static int write_rq_ctxts(struct hinic_func_to_io *func_to_io, u16 base_qpn,
 	err = hinic_cmdq_direct_resp(&func_to_io->cmdqs, HINIC_MOD_L2NIC,
 				     IO_CMD_MODIFY_QUEUE_CTXT, &cmdq_buf,
 				     &out_param);
-	if ((err) || (out_param != 0)) {
+	if (err || out_param != 0) {
 		dev_err(&pdev->dev, "Failed to set RQ ctxts\n");
 		err = -EFAULT;
 	}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
index 817173f1fbb7..ebc77771f5da 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
@@ -294,7 +294,7 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt,
 		goto unlock_sync_msg;
 	}
 
-	if ((buf_out) && (recv_msg->msg_len <= MAX_PF_MGMT_BUF_SIZE)) {
+	if (buf_out && recv_msg->msg_len <= MAX_PF_MGMT_BUF_SIZE) {
 		memcpy(buf_out, recv_msg->msg, recv_msg->msg_len);
 		*out_size = recv_msg->msg_len;
 	}
@@ -411,7 +411,7 @@ static void recv_mgmt_msg_work_handler(struct work_struct *work)
 			   HINIC_MGMT_CB_ENABLED,
 			   HINIC_MGMT_CB_ENABLED | HINIC_MGMT_CB_RUNNING);
 
-	if ((cb_state == HINIC_MGMT_CB_ENABLED) && (mgmt_cb->cb))
+	if (cb_state == HINIC_MGMT_CB_ENABLED && mgmt_cb->cb)
 		mgmt_cb->cb(mgmt_cb->handle, mgmt_work->cmd,
 			    mgmt_work->msg, mgmt_work->msg_len,
 			    buf_out, &out_size);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
index dcba4d009bad..336248aa2e48 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
@@ -894,7 +894,7 @@ struct hinic_rq_wqe *hinic_rq_read_next_wqe(struct hinic_rq *rq,
 }
 
 /**
- * hinic_put_wqe - release the ci for new wqes
+ * hinic_rq_put_wqe - release the ci for new wqes
  * @rq: recv queue
  * @cons_idx: consumer index of the wqe
  * @wqe_size: the size of the wqe
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
index 5dc3743f8091..7f0f1aa3cedd 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
@@ -89,6 +89,7 @@ static inline int WQE_PAGE_NUM(struct hinic_wq *wq, u16 idx)
 	return (((idx) >> ((wq)->wqebbs_per_page_shift))
 		& ((wq)->num_q_pages - 1));
 }
+
 /**
  * queue_alloc_page - allocate page for Queue
  * @hwif: HW interface for allocating DMA
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index 9a9b09401d01..405ee4d2d2b1 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -172,7 +172,6 @@ static int create_txqs(struct hinic_dev *nic_dev)
 				  "Failed to add SQ%d debug\n", i);
 			goto err_add_sq_dbg;
 		}
-
 	}
 
 	return 0;
@@ -233,7 +232,7 @@ static void free_txqs(struct hinic_dev *nic_dev)
 }
 
 /**
- * create_txqs - Create the Logical Rx Queues of specific NIC device
+ * create_rxqs - Create the Logical Rx Queues of specific NIC device
  * @nic_dev: the specific NIC device
  *
  * Return 0 - Success, negative - Failure
@@ -289,7 +288,7 @@ err_init_rxq:
 }
 
 /**
- * free_txqs - Free the Logical Rx Queues of specific NIC device
+ * free_rxqs - Free the Logical Rx Queues of specific NIC device
  * @nic_dev: the specific NIC device
  **/
 static void free_rxqs(struct hinic_dev *nic_dev)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c
index eb97f2d6b1ad..28ae6f1201a8 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c
@@ -128,7 +128,7 @@ int hinic_port_get_mac(struct hinic_dev *nic_dev, u8 *addr)
 	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_MAC,
 				 &port_mac_cmd, sizeof(port_mac_cmd),
 				 &port_mac_cmd, &out_size);
-	if (err || (out_size != sizeof(port_mac_cmd)) || port_mac_cmd.status) {
+	if (err || out_size != sizeof(port_mac_cmd) || port_mac_cmd.status) {
 		dev_err(&pdev->dev, "Failed to get mac, err: %d, status: 0x%x, out size: 0x%x\n",
 			err, port_mac_cmd.status, out_size);
 		return -EFAULT;
@@ -263,7 +263,7 @@ int hinic_port_link_state(struct hinic_dev *nic_dev,
 	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_LINK_STATE,
 				 &link_cmd, sizeof(link_cmd),
 				 &link_cmd, &out_size);
-	if (err || (out_size != sizeof(link_cmd)) || link_cmd.status) {
+	if (err || out_size != sizeof(link_cmd) || link_cmd.status) {
 		dev_err(&pdev->dev, "Failed to get link state, err: %d, status: 0x%x, out size: 0x%x\n",
 			err, link_cmd.status, out_size);
 		return -EINVAL;
@@ -297,7 +297,7 @@ int hinic_port_set_state(struct hinic_dev *nic_dev, enum hinic_port_state state)
 	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_PORT_STATE,
 				 &port_state, sizeof(port_state),
 				 &port_state, &out_size);
-	if (err || (out_size != sizeof(port_state)) || port_state.status) {
+	if (err || out_size != sizeof(port_state) || port_state.status) {
 		dev_err(&pdev->dev, "Failed to set port state, err: %d, status: 0x%x, out size: 0x%x\n",
 			err, port_state.status, out_size);
 		return -EFAULT;
@@ -329,7 +329,7 @@ int hinic_port_set_func_state(struct hinic_dev *nic_dev,
 	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_FUNC_STATE,
 				 &func_state, sizeof(func_state),
 				 &func_state, &out_size);
-	if (err || (out_size != sizeof(func_state)) || func_state.status) {
+	if (err || out_size != sizeof(func_state) || func_state.status) {
 		dev_err(&pdev->dev, "Failed to set port func state, err: %d, status: 0x%x, out size: 0x%x\n",
 			err, func_state.status, out_size);
 		return -EFAULT;
@@ -359,7 +359,7 @@ int hinic_port_get_cap(struct hinic_dev *nic_dev,
 	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_CAP,
 				 port_cap, sizeof(*port_cap),
 				 port_cap, &out_size);
-	if (err || (out_size != sizeof(*port_cap)) || port_cap->status) {
+	if (err || out_size != sizeof(*port_cap) || port_cap->status) {
 		dev_err(&pdev->dev,
 			"Failed to get port capabilities, err: %d, status: 0x%x, out size: 0x%x\n",
 			err, port_cap->status, out_size);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index cce08647b9b2..fed3b6bc0d76 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -118,6 +118,7 @@ static void rx_csum(struct hinic_rxq *rxq, u32 status,
 		skb->ip_summed = CHECKSUM_NONE;
 	}
 }
+
 /**
  * rx_alloc_skb - allocate skb and map it to dma address
  * @rxq: rx queue
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index 710c4ff7bc0e..c5bdb0d374ef 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -660,7 +660,7 @@ static void tx_free_skb(struct hinic_dev *nic_dev, struct sk_buff *skb,
 }
 
 /**
- * free_all_rx_skbs - free all skbs in tx queue
+ * free_all_tx_skbs - free all skbs in tx queue
  * @txq: tx queue
  **/
 static void free_all_tx_skbs(struct hinic_txq *txq)
@@ -717,7 +717,7 @@ static int free_tx_poll(struct napi_struct *napi, int budget)
 
 		/* Reading a WQEBB to get real WQE size and consumer index. */
 		sq_wqe = hinic_sq_read_wqebb(sq, &skb, &wqe_size, &sw_ci);
-		if ((!sq_wqe) ||
+		if (!sq_wqe ||
 		    (((hw_ci - sw_ci) & wq->mask) * wq->wqebb_size < wqe_size))
 			break;
 
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index ea55314b209d..d5df131b183c 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -2618,10 +2618,8 @@ static int ehea_restart_qps(struct net_device *dev)
 	u16 dummy16 = 0;
 
 	cb0 = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!cb0) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!cb0)
+		return -ENOMEM;
 
 	for (i = 0; i < (port->num_def_qps); i++) {
 		struct ehea_port_res *pr =  &port->port_res[i];
@@ -2641,6 +2639,7 @@ static int ehea_restart_qps(struct net_device *dev)
 					    cb0);
 		if (hret != H_SUCCESS) {
 			netdev_err(dev, "query_ehea_qp failed (1)\n");
+			ret = -EFAULT;
 			goto out;
 		}
 
@@ -2653,6 +2652,7 @@ static int ehea_restart_qps(struct net_device *dev)
 					     &dummy64, &dummy16, &dummy16);
 		if (hret != H_SUCCESS) {
 			netdev_err(dev, "modify_ehea_qp failed (1)\n");
+			ret = -EFAULT;
 			goto out;
 		}
 
@@ -2661,6 +2661,7 @@ static int ehea_restart_qps(struct net_device *dev)
 					    cb0);
 		if (hret != H_SUCCESS) {
 			netdev_err(dev, "query_ehea_qp failed (2)\n");
+			ret = -EFAULT;
 			goto out;
 		}
 
@@ -2867,14 +2868,14 @@ out:
 	return ret;
 }
 
-static ssize_t ehea_show_port_id(struct device *dev,
-				 struct device_attribute *attr, char *buf)
+static ssize_t log_port_id_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct ehea_port *port = container_of(dev, struct ehea_port, ofdev.dev);
 	return sprintf(buf, "%d", port->logical_port_id);
 }
 
-static DEVICE_ATTR(log_port_id, 0444, ehea_show_port_id, NULL);
+static DEVICE_ATTR_RO(log_port_id);
 
 static void logical_port_release(struct device *dev)
 {
@@ -3113,7 +3114,7 @@ static struct device_node *ehea_get_eth_dn(struct ehea_adapter *adapter,
 	return NULL;
 }
 
-static ssize_t ehea_probe_port(struct device *dev,
+static ssize_t probe_port_store(struct device *dev,
 			       struct device_attribute *attr,
 			       const char *buf, size_t count)
 {
@@ -3168,9 +3169,9 @@ static ssize_t ehea_probe_port(struct device *dev,
 	return (ssize_t) count;
 }
 
-static ssize_t ehea_remove_port(struct device *dev,
-				struct device_attribute *attr,
-				const char *buf, size_t count)
+static ssize_t remove_port_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
 {
 	struct ehea_adapter *adapter = dev_get_drvdata(dev);
 	struct ehea_port *port;
@@ -3203,8 +3204,8 @@ static ssize_t ehea_remove_port(struct device *dev,
 	return (ssize_t) count;
 }
 
-static DEVICE_ATTR(probe_port, 0200, NULL, ehea_probe_port);
-static DEVICE_ATTR(remove_port, 0200, NULL, ehea_remove_port);
+static DEVICE_ATTR_WO(probe_port);
+static DEVICE_ATTR_WO(remove_port);
 
 static int ehea_create_device_sysfs(struct platform_device *dev)
 {
diff --git a/drivers/net/ethernet/ibm/emac/emac.h b/drivers/net/ethernet/ibm/emac/emac.h
index aa9f651288d5..09d3ac374b2d 100644
--- a/drivers/net/ethernet/ibm/emac/emac.h
+++ b/drivers/net/ethernet/ibm/emac/emac.h
@@ -77,7 +77,7 @@ struct emac_regs {
 		struct {
 			u32 rsvd1;
 			u32 revid;
- 			u32 rsvd2[2];
+			u32 rsvd2[2];
 			u32 iaht1;	/* Reset, R     */
 			u32 iaht2;	/* Reset, R     */
 			u32 iaht3;	/* Reset, R     */
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 7fea9ae60f13..bc67a7ee872b 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1799,8 +1799,7 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr,
 	struct ibmveth_buff_pool *pool = container_of(kobj,
 						      struct ibmveth_buff_pool,
 						      kobj);
-	struct net_device *netdev = dev_get_drvdata(
-	    container_of(kobj->parent, struct device, kobj));
+	struct net_device *netdev = dev_get_drvdata(kobj_to_dev(kobj->parent));
 	struct ibmveth_adapter *adapter = netdev_priv(netdev);
 	long value = simple_strtol(buf, NULL, 10);
 	long rc;
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 5788bb956d73..2d8804ebdf96 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -95,7 +95,7 @@ static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *,
 					struct ibmvnic_sub_crq_queue *);
 static int ibmvnic_poll(struct napi_struct *napi, int data);
 static void send_query_map(struct ibmvnic_adapter *adapter);
-static int send_request_map(struct ibmvnic_adapter *, dma_addr_t, __be32, u8);
+static int send_request_map(struct ibmvnic_adapter *, dma_addr_t, u32, u8);
 static int send_request_unmap(struct ibmvnic_adapter *, u8);
 static int send_login(struct ibmvnic_adapter *adapter);
 static void send_query_cap(struct ibmvnic_adapter *adapter);
@@ -141,6 +141,29 @@ static const struct ibmvnic_stat ibmvnic_stats[] = {
 	{"internal_mac_rx_errors", IBMVNIC_STAT_OFF(internal_mac_rx_errors)},
 };
 
+static int send_crq_init_complete(struct ibmvnic_adapter *adapter)
+{
+	union ibmvnic_crq crq;
+
+	memset(&crq, 0, sizeof(crq));
+	crq.generic.first = IBMVNIC_CRQ_INIT_CMD;
+	crq.generic.cmd = IBMVNIC_CRQ_INIT_COMPLETE;
+
+	return ibmvnic_send_crq(adapter, &crq);
+}
+
+static int send_version_xchg(struct ibmvnic_adapter *adapter)
+{
+	union ibmvnic_crq crq;
+
+	memset(&crq, 0, sizeof(crq));
+	crq.version_exchange.first = IBMVNIC_CRQ_CMD;
+	crq.version_exchange.cmd = VERSION_EXCHANGE;
+	crq.version_exchange.version = cpu_to_be16(ibmvnic_version);
+
+	return ibmvnic_send_crq(adapter, &crq);
+}
+
 static long h_reg_sub_crq(unsigned long unit_address, unsigned long token,
 			  unsigned long length, unsigned long *number,
 			  unsigned long *irq)
@@ -846,9 +869,10 @@ static const char *adapter_state_to_string(enum vnic_state state)
 		return "REMOVING";
 	case VNIC_REMOVED:
 		return "REMOVED";
-	default:
-		return "UNKNOWN";
+	case VNIC_DOWN:
+		return "DOWN";
 	}
+	return "UNKNOWN";
 }
 
 static int ibmvnic_login(struct net_device *netdev)
@@ -1502,7 +1526,8 @@ static int create_hdr_descs(u8 hdr_field, u8 *hdr_data, int len, int *hdr_len,
 
 /**
  * build_hdr_descs_arr - build a header descriptor array
- * @txbuff: tx buffer
+ * @skb: tx socket buffer
+ * @indir_arr: indirect array
  * @num_entries: number of descriptors to be sent
  * @hdr_field: bit field determining which headers will be sent
  *
@@ -1946,9 +1971,10 @@ static const char *reset_reason_to_string(enum ibmvnic_reset_reason reason)
 		return "TIMEOUT";
 	case VNIC_RESET_CHANGE_PARAM:
 		return "CHANGE_PARAM";
-	default:
-		return "UNKNOWN";
+	case VNIC_RESET_PASSIVE_INIT:
+		return "PASSIVE_INIT";
 	}
+	return "UNKNOWN";
 }
 
 /*
@@ -2085,10 +2111,10 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 			goto out;
 		}
 
-		/* If the adapter was in PROBE state prior to the reset,
+		/* If the adapter was in PROBE or DOWN state prior to the reset,
 		 * exit here.
 		 */
-		if (reset_state == VNIC_PROBED) {
+		if (reset_state == VNIC_PROBED || reset_state == VNIC_DOWN) {
 			rc = 0;
 			goto out;
 		}
@@ -2214,10 +2240,10 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter,
 	if (rc)
 		goto out;
 
-	/* If the adapter was in PROBE state prior to the reset,
+	/* If the adapter was in PROBE or DOWN state prior to the reset,
 	 * exit here.
 	 */
-	if (reset_state == VNIC_PROBED)
+	if (reset_state == VNIC_PROBED || reset_state == VNIC_DOWN)
 		goto out;
 
 	rc = ibmvnic_login(netdev);
@@ -2270,6 +2296,76 @@ static struct ibmvnic_rwi *get_next_rwi(struct ibmvnic_adapter *adapter)
 	return rwi;
 }
 
+/**
+ * do_passive_init - complete probing when partner device is detected.
+ * @adapter: ibmvnic_adapter struct
+ *
+ * If the ibmvnic device does not have a partner device to communicate with at boot
+ * and that partner device comes online at a later time, this function is called
+ * to complete the initialization process of ibmvnic device.
+ * Caller is expected to hold rtnl_lock().
+ *
+ * Returns non-zero if sub-CRQs are not initialized properly leaving the device
+ * in the down state.
+ * Returns 0 upon success and the device is in PROBED state.
+ */
+
+static int do_passive_init(struct ibmvnic_adapter *adapter)
+{
+	unsigned long timeout = msecs_to_jiffies(30000);
+	struct net_device *netdev = adapter->netdev;
+	struct device *dev = &adapter->vdev->dev;
+	int rc;
+
+	netdev_dbg(netdev, "Partner device found, probing.\n");
+
+	adapter->state = VNIC_PROBING;
+	reinit_completion(&adapter->init_done);
+	adapter->init_done_rc = 0;
+	adapter->crq.active = true;
+
+	rc = send_crq_init_complete(adapter);
+	if (rc)
+		goto out;
+
+	rc = send_version_xchg(adapter);
+	if (rc)
+		netdev_dbg(adapter->netdev, "send_version_xchg failed, rc=%d\n", rc);
+
+	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
+		dev_err(dev, "Initialization sequence timed out\n");
+		rc = -ETIMEDOUT;
+		goto out;
+	}
+
+	rc = init_sub_crqs(adapter);
+	if (rc) {
+		dev_err(dev, "Initialization of sub crqs failed, rc=%d\n", rc);
+		goto out;
+	}
+
+	rc = init_sub_crq_irqs(adapter);
+	if (rc) {
+		dev_err(dev, "Failed to initialize sub crq irqs\n, rc=%d", rc);
+		goto init_failed;
+	}
+
+	netdev->mtu = adapter->req_mtu - ETH_HLEN;
+	netdev->min_mtu = adapter->min_mtu - ETH_HLEN;
+	netdev->max_mtu = adapter->max_mtu - ETH_HLEN;
+
+	adapter->state = VNIC_PROBED;
+	netdev_dbg(netdev, "Probed successfully. Waiting for signal from partner device.\n");
+
+	return 0;
+
+init_failed:
+	release_sub_crqs(adapter, 1);
+out:
+	adapter->state = VNIC_DOWN;
+	return rc;
+}
+
 static void __ibmvnic_reset(struct work_struct *work)
 {
 	struct ibmvnic_rwi *rwi;
@@ -2306,7 +2402,13 @@ static void __ibmvnic_reset(struct work_struct *work)
 		}
 		spin_unlock_irqrestore(&adapter->state_lock, flags);
 
-		if (adapter->force_reset_recovery) {
+		if (rwi->reset_reason == VNIC_RESET_PASSIVE_INIT) {
+			rtnl_lock();
+			rc = do_passive_init(adapter);
+			rtnl_unlock();
+			if (!rc)
+				netif_carrier_on(adapter->netdev);
+		} else if (adapter->force_reset_recovery) {
 			/* Since we are doing a hard reset now, clear the
 			 * failover_pending flag so we don't ignore any
 			 * future MOBILITY or other resets.
@@ -2402,8 +2504,7 @@ static int ibmvnic_reset(struct ibmvnic_adapter *adapter,
 		goto err;
 	}
 
-	list_for_each(entry, &adapter->rwi_list) {
-		tmp = list_entry(entry, struct ibmvnic_rwi, list);
+	list_for_each_entry(tmp, &adapter->rwi_list, list) {
 		if (tmp->reset_reason == reason) {
 			netdev_dbg(netdev, "Skipping matching reset, reason=%s\n",
 				   reset_reason_to_string(reason));
@@ -3776,18 +3877,6 @@ static int ibmvnic_send_crq_init(struct ibmvnic_adapter *adapter)
 	return 0;
 }
 
-static int send_version_xchg(struct ibmvnic_adapter *adapter)
-{
-	union ibmvnic_crq crq;
-
-	memset(&crq, 0, sizeof(crq));
-	crq.version_exchange.first = IBMVNIC_CRQ_CMD;
-	crq.version_exchange.cmd = VERSION_EXCHANGE;
-	crq.version_exchange.version = cpu_to_be16(ibmvnic_version);
-
-	return ibmvnic_send_crq(adapter, &crq);
-}
-
 struct vnic_login_client_data {
 	u8	type;
 	__be16	len;
@@ -4301,7 +4390,7 @@ static void handle_vpd_rsp(union ibmvnic_crq *crq,
 
 complete:
 	if (adapter->fw_version[0] == '\0')
-		strncpy((char *)adapter->fw_version, "N/A", 3 * sizeof(char));
+		strscpy((char *)adapter->fw_version, "N/A", sizeof(adapter->fw_version));
 	complete(&adapter->fw_done);
 }
 
@@ -4907,7 +4996,12 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 				complete(&adapter->init_done);
 				adapter->init_done_rc = -EIO;
 			}
-			rc = ibmvnic_reset(adapter, VNIC_RESET_FAILOVER);
+
+			if (adapter->state == VNIC_DOWN)
+				rc = ibmvnic_reset(adapter, VNIC_RESET_PASSIVE_INIT);
+			else
+				rc = ibmvnic_reset(adapter, VNIC_RESET_FAILOVER);
+
 			if (rc && rc != -EBUSY) {
 				/* We were unable to schedule the failover
 				 * reset either because the adapter was still
@@ -5330,6 +5424,7 @@ 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;
+	bool init_success;
 	int rc;
 
 	dev_dbg(&dev->dev, "entering ibmvnic_probe for UA 0x%x\n",
@@ -5376,6 +5471,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	init_completion(&adapter->stats_done);
 	clear_bit(0, &adapter->resetting);
 
+	init_success = false;
 	do {
 		rc = init_crq_queue(adapter);
 		if (rc) {
@@ -5385,10 +5481,16 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 		}
 
 		rc = ibmvnic_reset_init(adapter, false);
-		if (rc && rc != EAGAIN)
-			goto ibmvnic_init_fail;
 	} while (rc == EAGAIN);
 
+	/* We are ignoring the error from ibmvnic_reset_init() assuming that the
+	 * partner is not ready. CRQ is not active. When the partner becomes
+	 * ready, we will do the passive init reset.
+	 */
+
+	if (!rc)
+		init_success = true;
+
 	rc = init_stats_buffers(adapter);
 	if (rc)
 		goto ibmvnic_init_fail;
@@ -5397,10 +5499,6 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	if (rc)
 		goto ibmvnic_stats_fail;
 
-	netdev->mtu = adapter->req_mtu - ETH_HLEN;
-	netdev->min_mtu = adapter->min_mtu - ETH_HLEN;
-	netdev->max_mtu = adapter->max_mtu - ETH_HLEN;
-
 	rc = device_create_file(&dev->dev, &dev_attr_failover);
 	if (rc)
 		goto ibmvnic_dev_file_err;
@@ -5413,7 +5511,14 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	}
 	dev_info(&dev->dev, "ibmvnic registered\n");
 
-	adapter->state = VNIC_PROBED;
+	if (init_success) {
+		adapter->state = VNIC_PROBED;
+		netdev->mtu = adapter->req_mtu - ETH_HLEN;
+		netdev->min_mtu = adapter->min_mtu - ETH_HLEN;
+		netdev->max_mtu = adapter->max_mtu - ETH_HLEN;
+	} else {
+		adapter->state = VNIC_DOWN;
+	}
 
 	adapter->wait_for_reset = false;
 	adapter->last_reset_time = jiffies;
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index c1d39a748546..22df602323bc 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -851,14 +851,16 @@ enum vnic_state {VNIC_PROBING = 1,
 		 VNIC_CLOSING,
 		 VNIC_CLOSED,
 		 VNIC_REMOVING,
-		 VNIC_REMOVED};
+		 VNIC_REMOVED,
+		 VNIC_DOWN};
 
 enum ibmvnic_reset_reason {VNIC_RESET_FAILOVER = 1,
 			   VNIC_RESET_MOBILITY,
 			   VNIC_RESET_FATAL,
 			   VNIC_RESET_NON_FATAL,
 			   VNIC_RESET_TIMEOUT,
-			   VNIC_RESET_CHANGE_PARAM};
+			   VNIC_RESET_CHANGE_PARAM,
+			   VNIC_RESET_PASSIVE_INIT};
 
 struct ibmvnic_rwi {
 	enum ibmvnic_reset_reason reset_reason;
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index c1d155690341..82744a7501c7 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -241,6 +241,7 @@ config I40E
 	tristate "Intel(R) Ethernet Controller XL710 Family support"
 	imply PTP_1588_CLOCK
 	depends on PCI
+	select AUXILIARY_BUS
 	help
 	  This driver supports Intel(R) Ethernet Controller XL710 Family of
 	  devices.  For more information on how to identify your adapter, go
@@ -294,9 +295,11 @@ config ICE
 	tristate "Intel(R) Ethernet Connection E800 Series Support"
 	default n
 	depends on PCI_MSI
+	select AUXILIARY_BUS
 	select DIMLIB
 	select NET_DEVLINK
 	select PLDMFW
+	imply PTP_1588_CLOCK
 	help
 	  This driver supports Intel(R) Ethernet Connection E800 Series of
 	  devices.  For more information on how to identify your adapter, go
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index f8d78af76d7d..1b0958bd24f6 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -1395,7 +1395,7 @@ static int e100_phy_check_without_mii(struct nic *nic)
 	u8 phy_type;
 	int without_mii;
 
-	phy_type = (nic->eeprom[eeprom_phy_iface] >> 8) & 0x0f;
+	phy_type = (le16_to_cpu(nic->eeprom[eeprom_phy_iface]) >> 8) & 0x0f;
 
 	switch (phy_type) {
 	case NoSuchPhy: /* Non-MII PHY; UNTESTED! */
@@ -1515,7 +1515,7 @@ static int e100_phy_init(struct nic *nic)
 		mdio_write(netdev, nic->mii.phy_id, MII_BMCR, bmcr);
 	} else if ((nic->mac >= mac_82550_D102) || ((nic->flags & ich) &&
 	   (mdio_read(netdev, nic->mii.phy_id, MII_TPISTATUS) & 0x8000) &&
-		(nic->eeprom[eeprom_cnfg_mdix] & eeprom_mdix_enabled))) {
+	   (le16_to_cpu(nic->eeprom[eeprom_cnfg_mdix]) & eeprom_mdix_enabled))) {
 		/* enable/disable MDI/MDI-X auto-switching. */
 		mdio_write(netdev, nic->mii.phy_id, MII_NCONFIG,
 				nic->mii.force_media ? 0 : NCONFIG_AUTO_SWITCH);
@@ -2269,9 +2269,9 @@ static int e100_asf(struct nic *nic)
 {
 	/* ASF can be enabled from eeprom */
 	return (nic->pdev->device >= 0x1050) && (nic->pdev->device <= 0x1057) &&
-	   (nic->eeprom[eeprom_config_asf] & eeprom_asf) &&
-	   !(nic->eeprom[eeprom_config_asf] & eeprom_gcl) &&
-	   ((nic->eeprom[eeprom_smbus_addr] & 0xFF) != 0xFE);
+	   (le16_to_cpu(nic->eeprom[eeprom_config_asf]) & eeprom_asf) &&
+	   !(le16_to_cpu(nic->eeprom[eeprom_config_asf]) & eeprom_gcl) &&
+	   ((le16_to_cpu(nic->eeprom[eeprom_smbus_addr]) & 0xFF) != 0xFE);
 }
 
 static int e100_up(struct nic *nic)
@@ -2926,7 +2926,7 @@ static int e100_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* Wol magic packet can be enabled from eeprom */
 	if ((nic->mac >= mac_82558_D101_A4) &&
-	   (nic->eeprom[eeprom_id] & eeprom_id_wol)) {
+	   (le16_to_cpu(nic->eeprom[eeprom_id]) & eeprom_id_wol)) {
 		nic->flags |= wol_magic;
 		device_set_wakeup_enable(&pdev->dev, true);
 	}
diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
index f976e9daa3d8..3c51ee94fa00 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
@@ -513,7 +513,7 @@ static int e1000_set_eeprom(struct net_device *netdev,
 	memcpy(ptr, bytes, eeprom->len);
 
 	for (i = 0; i < last_word - first_word + 1; i++)
-		eeprom_buff[i] = cpu_to_le16(eeprom_buff[i]);
+		cpu_to_le16s(&eeprom_buff[i]);
 
 	ret_val = e1000_write_eeprom(hw, first_word,
 				     last_word - first_word + 1, eeprom_buff);
diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c
index 19cf36360933..1042e79a1397 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_hw.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c
@@ -2522,7 +2522,7 @@ s32 e1000_check_for_link(struct e1000_hw *hw)
 				 * turn it on. For compatibility with a TBI link
 				 * partner, we will store bad packets. Some
 				 * frames have an additional byte on the end and
-				 * will look like CRC errors to to the hardware.
+				 * will look like CRC errors to the hardware.
 				 */
 				if (!hw->tbi_compatibility_on) {
 					hw->tbi_compatibility_on = true;
@@ -2723,7 +2723,7 @@ static void e1000_shift_out_mdi_bits(struct e1000_hw *hw, u32 data, u16 count)
  * e1000_shift_in_mdi_bits - Shifts data bits in from the PHY
  * @hw: Struct containing variables accessed by shared code
  *
- * Bits are shifted in in MSB to LSB order.
+ * Bits are shifted in MSB to LSB order.
  */
 static u16 e1000_shift_in_mdi_bits(struct e1000_hw *hw)
 {
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 042de276e632..c2a109126c27 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -5245,7 +5245,7 @@ static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev,
 	if (!test_and_set_bit(__E1000_DISABLED, &adapter->flags))
 		pci_disable_device(pdev);
 
-	/* Request a slot slot reset. */
+	/* Request a slot reset. */
 	return PCI_ERS_RESULT_NEED_RESET;
 }
 
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 590ad110d383..cf7b3887da1d 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -4639,7 +4639,7 @@ static s32 e1000_id_led_init_pchlan(struct e1000_hw *hw)
  *  @hw: pointer to the HW structure
  *
  *  ICH8 use the PCI Express bus, but does not contain a PCI Express Capability
- *  register, so the the bus width is hard coded.
+ *  register, so the bus width is hard coded.
  **/
 static s32 e1000_get_bus_info_ich8lan(struct e1000_hw *hw)
 {
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 88e9035b75cf..5435606149b0 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -7118,7 +7118,7 @@ static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev,
 
 	pci_disable_device(pdev);
 
-	/* Request a slot slot reset. */
+	/* Request a slot reset. */
 	return PCI_ERS_RESULT_NEED_RESET;
 }
 
diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index 1db35b2c7750..0f0efee5fc8e 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -2978,7 +2978,7 @@ static u32 e1000_get_phy_addr_for_hv_page(u32 page)
  *  @data: pointer to the data to be read or written
  *  @read: determines if operation is read or write
  *
- *  Reads the PHY register at offset and stores the retreived information
+ *  Reads the PHY register at offset and stores the retrieved information
  *  in data.  Assumes semaphore already acquired.  Note that the procedure
  *  to access these regs uses the address port and data port to read/write.
  *  These accesses done with PHY address 2 and without using pages.
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index 9e3103fae723..dbcae92bb18d 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -1370,7 +1370,6 @@ static irqreturn_t fm10k_msix_mbx_pf(int __always_unused irq, void *data)
 	struct fm10k_hw *hw = &interface->hw;
 	struct fm10k_mbx_info *mbx = &hw->mbx;
 	u32 eicr;
-	s32 err = 0;
 
 	/* unmask any set bits related to this interrupt */
 	eicr = fm10k_read_reg(hw, FM10K_EICR);
@@ -1386,15 +1385,16 @@ static irqreturn_t fm10k_msix_mbx_pf(int __always_unused irq, void *data)
 
 	/* service mailboxes */
 	if (fm10k_mbx_trylock(interface)) {
-		err = mbx->ops.process(hw, mbx);
+		s32 err = mbx->ops.process(hw, mbx);
+
+		if (err == FM10K_ERR_RESET_REQUESTED)
+			set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
+
 		/* handle VFLRE events */
 		fm10k_iov_event(interface);
 		fm10k_mbx_unlock(interface);
 	}
 
-	if (err == FM10K_ERR_RESET_REQUESTED)
-		set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
-
 	/* if switch toggled state we should reset GLORTs */
 	if (eicr & FM10K_EICR_SWITCHNOTREADY) {
 		/* force link down for at least 4 seconds */
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 85d3dd3a3339..b9417dc0007c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -870,6 +870,8 @@ struct i40e_netdev_priv {
 	struct i40e_vsi *vsi;
 };
 
+extern struct ida i40e_client_ida;
+
 /* struct that defines an interrupt vector */
 struct i40e_q_vector {
 	struct i40e_vsi *vsi;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index 32f3facbed1a..e07ed065d3a4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -12,6 +12,7 @@ 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);
+DEFINE_IDA(i40e_client_ida);
 
 static int i40e_client_virtchnl_send(struct i40e_info *ldev,
 				     struct i40e_client *client,
@@ -275,6 +276,57 @@ void i40e_client_update_msix_info(struct i40e_pf *pf)
 	cdev->lan_info.msix_entries = &pf->msix_entries[pf->iwarp_base_vector];
 }
 
+static void i40e_auxiliary_dev_release(struct device *dev)
+{
+	struct i40e_auxiliary_device *i40e_aux_dev =
+			container_of(dev, struct i40e_auxiliary_device, aux_dev.dev);
+
+	ida_free(&i40e_client_ida, i40e_aux_dev->aux_dev.id);
+	kfree(i40e_aux_dev);
+}
+
+static int i40e_register_auxiliary_dev(struct i40e_info *ldev, const char *name)
+{
+	struct i40e_auxiliary_device *i40e_aux_dev;
+	struct pci_dev *pdev = ldev->pcidev;
+	struct auxiliary_device *aux_dev;
+	int ret;
+
+	i40e_aux_dev = kzalloc(sizeof(*i40e_aux_dev), GFP_KERNEL);
+	if (!i40e_aux_dev)
+		return -ENOMEM;
+
+	i40e_aux_dev->ldev = ldev;
+
+	aux_dev = &i40e_aux_dev->aux_dev;
+	aux_dev->name = name;
+	aux_dev->dev.parent = &pdev->dev;
+	aux_dev->dev.release = i40e_auxiliary_dev_release;
+	ldev->aux_dev = aux_dev;
+
+	ret = ida_alloc(&i40e_client_ida, GFP_KERNEL);
+	if (ret < 0) {
+		kfree(i40e_aux_dev);
+		return ret;
+	}
+	aux_dev->id = ret;
+
+	ret = auxiliary_device_init(aux_dev);
+	if (ret < 0) {
+		ida_free(&i40e_client_ida, aux_dev->id);
+		kfree(i40e_aux_dev);
+		return ret;
+	}
+
+	ret = auxiliary_device_add(aux_dev);
+	if (ret) {
+		auxiliary_device_uninit(aux_dev);
+		return ret;
+	}
+
+	return ret;
+}
+
 /**
  * i40e_client_add_instance - add a client instance struct to the instance list
  * @pf: pointer to the board struct
@@ -286,9 +338,6 @@ static void i40e_client_add_instance(struct i40e_pf *pf)
 	struct netdev_hw_addr *mac = NULL;
 	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 
-	if (!registered_client || pf->cinst)
-		return;
-
 	cdev = kzalloc(sizeof(*cdev), GFP_KERNEL);
 	if (!cdev)
 		return;
@@ -308,11 +357,8 @@ static void i40e_client_add_instance(struct i40e_pf *pf)
 	cdev->lan_info.fw_build = pf->hw.aq.fw_build;
 	set_bit(__I40E_CLIENT_INSTANCE_NONE, &cdev->state);
 
-	if (i40e_client_get_params(vsi, &cdev->lan_info.params)) {
-		kfree(cdev);
-		cdev = NULL;
-		return;
-	}
+	if (i40e_client_get_params(vsi, &cdev->lan_info.params))
+		goto free_cdev;
 
 	mac = list_first_entry(&cdev->lan_info.netdev->dev_addrs.list,
 			       struct netdev_hw_addr, list);
@@ -324,7 +370,17 @@ static void i40e_client_add_instance(struct i40e_pf *pf)
 	cdev->client = registered_client;
 	pf->cinst = cdev;
 
-	i40e_client_update_msix_info(pf);
+	cdev->lan_info.msix_count = pf->num_iwarp_msix;
+	cdev->lan_info.msix_entries = &pf->msix_entries[pf->iwarp_base_vector];
+
+	if (i40e_register_auxiliary_dev(&cdev->lan_info, "iwarp"))
+		goto free_cdev;
+
+	return;
+
+free_cdev:
+	kfree(cdev);
+	pf->cinst = NULL;
 }
 
 /**
@@ -345,7 +401,7 @@ void i40e_client_del_instance(struct i40e_pf *pf)
  **/
 void i40e_client_subtask(struct i40e_pf *pf)
 {
-	struct i40e_client *client = registered_client;
+	struct i40e_client *client;
 	struct i40e_client_instance *cdev;
 	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 	int ret = 0;
@@ -359,9 +415,11 @@ void i40e_client_subtask(struct i40e_pf *pf)
 	    test_bit(__I40E_CONFIG_BUSY, pf->state))
 		return;
 
-	if (!client || !cdev)
+	if (!cdev || !cdev->client)
 		return;
 
+	client = cdev->client;
+
 	/* Here we handle client opens. If the client is down, and
 	 * the netdev is registered, then open the client.
 	 */
@@ -423,16 +481,8 @@ int i40e_lan_add_device(struct i40e_pf *pf)
 		 pf->hw.pf_id, pf->hw.bus.bus_id,
 		 pf->hw.bus.device, pf->hw.bus.func);
 
-	/* If a client has already been registered, we need to add an instance
-	 * of it to our new LAN device.
-	 */
-	if (registered_client)
-		i40e_client_add_instance(pf);
+	i40e_client_add_instance(pf);
 
-	/* Since in some cases register may have happened before a device gets
-	 * added, we can schedule a subtask to go initiate the clients if
-	 * they can be launched at probe time.
-	 */
 	set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state);
 	i40e_service_event_schedule(pf);
 
@@ -449,9 +499,13 @@ out:
  **/
 int i40e_lan_del_device(struct i40e_pf *pf)
 {
+	struct auxiliary_device *aux_dev = pf->cinst->lan_info.aux_dev;
 	struct i40e_device *ldev, *tmp;
 	int ret = -ENODEV;
 
+	auxiliary_device_delete(aux_dev);
+	auxiliary_device_uninit(aux_dev);
+
 	/* First, remove any client instance. */
 	i40e_client_del_instance(pf);
 
@@ -579,7 +633,7 @@ static int i40e_client_setup_qvlist(struct i40e_info *ldev,
 	u32 v_idx, i, reg_idx, reg;
 
 	ldev->qvlist_info = kzalloc(struct_size(ldev->qvlist_info, qv_info,
-				    qvlist_info->num_vectors - 1), GFP_KERNEL);
+				    qvlist_info->num_vectors), GFP_KERNEL);
 	if (!ldev->qvlist_info)
 		return -ENOMEM;
 	ldev->qvlist_info->num_vectors = qvlist_info->num_vectors;
@@ -732,6 +786,42 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev,
 	return err;
 }
 
+void i40e_client_device_register(struct i40e_info *ldev, struct i40e_client *client)
+{
+	struct i40e_pf *pf = ldev->pf;
+
+	pf->cinst->client = client;
+	set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state);
+	i40e_service_event_schedule(pf);
+}
+EXPORT_SYMBOL_GPL(i40e_client_device_register);
+
+void i40e_client_device_unregister(struct i40e_info *ldev)
+{
+	struct i40e_pf *pf = ldev->pf;
+	struct i40e_client_instance *cdev = pf->cinst;
+
+	if (!cdev)
+		return;
+
+	while (test_and_set_bit(__I40E_SERVICE_SCHED, pf->state))
+		usleep_range(500, 1000);
+
+	if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
+		cdev->client->ops->close(&cdev->lan_info, cdev->client, false);
+		clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
+		i40e_client_release_qvlist(&cdev->lan_info);
+	}
+
+	pf->cinst->client = NULL;
+	clear_bit(__I40E_SERVICE_SCHED, pf->state);
+}
+EXPORT_SYMBOL_GPL(i40e_client_device_unregister);
+
+/* Retain these legacy global registration/unregistration calls till i40iw is
+ * removed from the kernel. The irdma unified driver does not use these
+ * exported symbols.
+ */
 /**
  * i40e_register_client - Register a i40e client driver with the L2 driver
  * @client: pointer to the i40e_client struct
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 67cb0b47416a..b4d3fed0d2f2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -552,9 +552,9 @@ i40e_status i40e_aq_set_rss_key(struct i40e_hw *hw,
  * ENDIF
  */
 
-/* macro to make the table lines short */
+/* macro to make the table lines short, use explicit indexing with [PTYPE] */
 #define I40E_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
-	{	PTYPE, \
+	[PTYPE] = { \
 		1, \
 		I40E_RX_PTYPE_OUTER_##OUTER_IP, \
 		I40E_RX_PTYPE_OUTER_##OUTER_IP_VER, \
@@ -565,16 +565,15 @@ i40e_status i40e_aq_set_rss_key(struct i40e_hw *hw,
 		I40E_RX_PTYPE_INNER_PROT_##I, \
 		I40E_RX_PTYPE_PAYLOAD_LAYER_##PL }
 
-#define I40E_PTT_UNUSED_ENTRY(PTYPE) \
-		{ PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 }
+#define I40E_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
 
 /* shorter macros makes the table fit but are terse */
 #define I40E_RX_PTYPE_NOF		I40E_RX_PTYPE_NOT_FRAG
 #define I40E_RX_PTYPE_FRG		I40E_RX_PTYPE_FRAG
 #define I40E_RX_PTYPE_INNER_PROT_TS	I40E_RX_PTYPE_INNER_PROT_TIMESYNC
 
-/* Lookup table mapping the HW PTYPE to the bit field for decoding */
-struct i40e_rx_ptype_decoded i40e_ptype_lookup[] = {
+/* Lookup table mapping in the 8-bit HW PTYPE to the bit field for decoding */
+struct i40e_rx_ptype_decoded i40e_ptype_lookup[BIT(8)] = {
 	/* L2 Packet types */
 	I40E_PTT_UNUSED_ENTRY(0),
 	I40E_PTT(1,  L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
@@ -780,118 +779,7 @@ struct i40e_rx_ptype_decoded i40e_ptype_lookup[] = {
 	I40E_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
 
 	/* unused entries */
-	I40E_PTT_UNUSED_ENTRY(154),
-	I40E_PTT_UNUSED_ENTRY(155),
-	I40E_PTT_UNUSED_ENTRY(156),
-	I40E_PTT_UNUSED_ENTRY(157),
-	I40E_PTT_UNUSED_ENTRY(158),
-	I40E_PTT_UNUSED_ENTRY(159),
-
-	I40E_PTT_UNUSED_ENTRY(160),
-	I40E_PTT_UNUSED_ENTRY(161),
-	I40E_PTT_UNUSED_ENTRY(162),
-	I40E_PTT_UNUSED_ENTRY(163),
-	I40E_PTT_UNUSED_ENTRY(164),
-	I40E_PTT_UNUSED_ENTRY(165),
-	I40E_PTT_UNUSED_ENTRY(166),
-	I40E_PTT_UNUSED_ENTRY(167),
-	I40E_PTT_UNUSED_ENTRY(168),
-	I40E_PTT_UNUSED_ENTRY(169),
-
-	I40E_PTT_UNUSED_ENTRY(170),
-	I40E_PTT_UNUSED_ENTRY(171),
-	I40E_PTT_UNUSED_ENTRY(172),
-	I40E_PTT_UNUSED_ENTRY(173),
-	I40E_PTT_UNUSED_ENTRY(174),
-	I40E_PTT_UNUSED_ENTRY(175),
-	I40E_PTT_UNUSED_ENTRY(176),
-	I40E_PTT_UNUSED_ENTRY(177),
-	I40E_PTT_UNUSED_ENTRY(178),
-	I40E_PTT_UNUSED_ENTRY(179),
-
-	I40E_PTT_UNUSED_ENTRY(180),
-	I40E_PTT_UNUSED_ENTRY(181),
-	I40E_PTT_UNUSED_ENTRY(182),
-	I40E_PTT_UNUSED_ENTRY(183),
-	I40E_PTT_UNUSED_ENTRY(184),
-	I40E_PTT_UNUSED_ENTRY(185),
-	I40E_PTT_UNUSED_ENTRY(186),
-	I40E_PTT_UNUSED_ENTRY(187),
-	I40E_PTT_UNUSED_ENTRY(188),
-	I40E_PTT_UNUSED_ENTRY(189),
-
-	I40E_PTT_UNUSED_ENTRY(190),
-	I40E_PTT_UNUSED_ENTRY(191),
-	I40E_PTT_UNUSED_ENTRY(192),
-	I40E_PTT_UNUSED_ENTRY(193),
-	I40E_PTT_UNUSED_ENTRY(194),
-	I40E_PTT_UNUSED_ENTRY(195),
-	I40E_PTT_UNUSED_ENTRY(196),
-	I40E_PTT_UNUSED_ENTRY(197),
-	I40E_PTT_UNUSED_ENTRY(198),
-	I40E_PTT_UNUSED_ENTRY(199),
-
-	I40E_PTT_UNUSED_ENTRY(200),
-	I40E_PTT_UNUSED_ENTRY(201),
-	I40E_PTT_UNUSED_ENTRY(202),
-	I40E_PTT_UNUSED_ENTRY(203),
-	I40E_PTT_UNUSED_ENTRY(204),
-	I40E_PTT_UNUSED_ENTRY(205),
-	I40E_PTT_UNUSED_ENTRY(206),
-	I40E_PTT_UNUSED_ENTRY(207),
-	I40E_PTT_UNUSED_ENTRY(208),
-	I40E_PTT_UNUSED_ENTRY(209),
-
-	I40E_PTT_UNUSED_ENTRY(210),
-	I40E_PTT_UNUSED_ENTRY(211),
-	I40E_PTT_UNUSED_ENTRY(212),
-	I40E_PTT_UNUSED_ENTRY(213),
-	I40E_PTT_UNUSED_ENTRY(214),
-	I40E_PTT_UNUSED_ENTRY(215),
-	I40E_PTT_UNUSED_ENTRY(216),
-	I40E_PTT_UNUSED_ENTRY(217),
-	I40E_PTT_UNUSED_ENTRY(218),
-	I40E_PTT_UNUSED_ENTRY(219),
-
-	I40E_PTT_UNUSED_ENTRY(220),
-	I40E_PTT_UNUSED_ENTRY(221),
-	I40E_PTT_UNUSED_ENTRY(222),
-	I40E_PTT_UNUSED_ENTRY(223),
-	I40E_PTT_UNUSED_ENTRY(224),
-	I40E_PTT_UNUSED_ENTRY(225),
-	I40E_PTT_UNUSED_ENTRY(226),
-	I40E_PTT_UNUSED_ENTRY(227),
-	I40E_PTT_UNUSED_ENTRY(228),
-	I40E_PTT_UNUSED_ENTRY(229),
-
-	I40E_PTT_UNUSED_ENTRY(230),
-	I40E_PTT_UNUSED_ENTRY(231),
-	I40E_PTT_UNUSED_ENTRY(232),
-	I40E_PTT_UNUSED_ENTRY(233),
-	I40E_PTT_UNUSED_ENTRY(234),
-	I40E_PTT_UNUSED_ENTRY(235),
-	I40E_PTT_UNUSED_ENTRY(236),
-	I40E_PTT_UNUSED_ENTRY(237),
-	I40E_PTT_UNUSED_ENTRY(238),
-	I40E_PTT_UNUSED_ENTRY(239),
-
-	I40E_PTT_UNUSED_ENTRY(240),
-	I40E_PTT_UNUSED_ENTRY(241),
-	I40E_PTT_UNUSED_ENTRY(242),
-	I40E_PTT_UNUSED_ENTRY(243),
-	I40E_PTT_UNUSED_ENTRY(244),
-	I40E_PTT_UNUSED_ENTRY(245),
-	I40E_PTT_UNUSED_ENTRY(246),
-	I40E_PTT_UNUSED_ENTRY(247),
-	I40E_PTT_UNUSED_ENTRY(248),
-	I40E_PTT_UNUSED_ENTRY(249),
-
-	I40E_PTT_UNUSED_ENTRY(250),
-	I40E_PTT_UNUSED_ENTRY(251),
-	I40E_PTT_UNUSED_ENTRY(252),
-	I40E_PTT_UNUSED_ENTRY(253),
-	I40E_PTT_UNUSED_ENTRY(254),
-	I40E_PTT_UNUSED_ENTRY(255)
+	[154 ... 255] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 704e474879c5..9db1968fc491 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -16270,6 +16270,7 @@ static void __exit i40e_exit_module(void)
 {
 	pci_unregister_driver(&i40e_driver);
 	destroy_workqueue(i40e_wq);
+	ida_destroy(&i40e_client_ida);
 	i40e_dbg_exit();
 }
 module_exit(i40e_exit_module);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index c81109a63e90..36a4ca1ffb1a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -804,7 +804,6 @@ enum i40e_rx_l2_ptype {
 };
 
 struct i40e_rx_ptype_decoded {
-	u32 ptype:8;
 	u32 known:1;
 	u32 outer_ip:1;
 	u32 outer_ip_ver:1;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c
index 8547fc8fdfd6..e9cc7f6ddc46 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_common.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_common.c
@@ -522,9 +522,9 @@ enum iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 vsi_id,
  * ENDIF
  */
 
-/* macro to make the table lines short */
+/* macro to make the table lines short, use explicit indexing with [PTYPE] */
 #define IAVF_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
-	{	PTYPE, \
+	[PTYPE] = { \
 		1, \
 		IAVF_RX_PTYPE_OUTER_##OUTER_IP, \
 		IAVF_RX_PTYPE_OUTER_##OUTER_IP_VER, \
@@ -535,16 +535,15 @@ enum iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 vsi_id,
 		IAVF_RX_PTYPE_INNER_PROT_##I, \
 		IAVF_RX_PTYPE_PAYLOAD_LAYER_##PL }
 
-#define IAVF_PTT_UNUSED_ENTRY(PTYPE) \
-		{ PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 }
+#define IAVF_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
 
 /* shorter macros makes the table fit but are terse */
 #define IAVF_RX_PTYPE_NOF		IAVF_RX_PTYPE_NOT_FRAG
 #define IAVF_RX_PTYPE_FRG		IAVF_RX_PTYPE_FRAG
 #define IAVF_RX_PTYPE_INNER_PROT_TS	IAVF_RX_PTYPE_INNER_PROT_TIMESYNC
 
-/* Lookup table mapping the HW PTYPE to the bit field for decoding */
-struct iavf_rx_ptype_decoded iavf_ptype_lookup[] = {
+/* Lookup table mapping the 8-bit HW PTYPE to the bit field for decoding */
+struct iavf_rx_ptype_decoded iavf_ptype_lookup[BIT(8)] = {
 	/* L2 Packet types */
 	IAVF_PTT_UNUSED_ENTRY(0),
 	IAVF_PTT(1,  L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
@@ -750,118 +749,7 @@ struct iavf_rx_ptype_decoded iavf_ptype_lookup[] = {
 	IAVF_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
 
 	/* unused entries */
-	IAVF_PTT_UNUSED_ENTRY(154),
-	IAVF_PTT_UNUSED_ENTRY(155),
-	IAVF_PTT_UNUSED_ENTRY(156),
-	IAVF_PTT_UNUSED_ENTRY(157),
-	IAVF_PTT_UNUSED_ENTRY(158),
-	IAVF_PTT_UNUSED_ENTRY(159),
-
-	IAVF_PTT_UNUSED_ENTRY(160),
-	IAVF_PTT_UNUSED_ENTRY(161),
-	IAVF_PTT_UNUSED_ENTRY(162),
-	IAVF_PTT_UNUSED_ENTRY(163),
-	IAVF_PTT_UNUSED_ENTRY(164),
-	IAVF_PTT_UNUSED_ENTRY(165),
-	IAVF_PTT_UNUSED_ENTRY(166),
-	IAVF_PTT_UNUSED_ENTRY(167),
-	IAVF_PTT_UNUSED_ENTRY(168),
-	IAVF_PTT_UNUSED_ENTRY(169),
-
-	IAVF_PTT_UNUSED_ENTRY(170),
-	IAVF_PTT_UNUSED_ENTRY(171),
-	IAVF_PTT_UNUSED_ENTRY(172),
-	IAVF_PTT_UNUSED_ENTRY(173),
-	IAVF_PTT_UNUSED_ENTRY(174),
-	IAVF_PTT_UNUSED_ENTRY(175),
-	IAVF_PTT_UNUSED_ENTRY(176),
-	IAVF_PTT_UNUSED_ENTRY(177),
-	IAVF_PTT_UNUSED_ENTRY(178),
-	IAVF_PTT_UNUSED_ENTRY(179),
-
-	IAVF_PTT_UNUSED_ENTRY(180),
-	IAVF_PTT_UNUSED_ENTRY(181),
-	IAVF_PTT_UNUSED_ENTRY(182),
-	IAVF_PTT_UNUSED_ENTRY(183),
-	IAVF_PTT_UNUSED_ENTRY(184),
-	IAVF_PTT_UNUSED_ENTRY(185),
-	IAVF_PTT_UNUSED_ENTRY(186),
-	IAVF_PTT_UNUSED_ENTRY(187),
-	IAVF_PTT_UNUSED_ENTRY(188),
-	IAVF_PTT_UNUSED_ENTRY(189),
-
-	IAVF_PTT_UNUSED_ENTRY(190),
-	IAVF_PTT_UNUSED_ENTRY(191),
-	IAVF_PTT_UNUSED_ENTRY(192),
-	IAVF_PTT_UNUSED_ENTRY(193),
-	IAVF_PTT_UNUSED_ENTRY(194),
-	IAVF_PTT_UNUSED_ENTRY(195),
-	IAVF_PTT_UNUSED_ENTRY(196),
-	IAVF_PTT_UNUSED_ENTRY(197),
-	IAVF_PTT_UNUSED_ENTRY(198),
-	IAVF_PTT_UNUSED_ENTRY(199),
-
-	IAVF_PTT_UNUSED_ENTRY(200),
-	IAVF_PTT_UNUSED_ENTRY(201),
-	IAVF_PTT_UNUSED_ENTRY(202),
-	IAVF_PTT_UNUSED_ENTRY(203),
-	IAVF_PTT_UNUSED_ENTRY(204),
-	IAVF_PTT_UNUSED_ENTRY(205),
-	IAVF_PTT_UNUSED_ENTRY(206),
-	IAVF_PTT_UNUSED_ENTRY(207),
-	IAVF_PTT_UNUSED_ENTRY(208),
-	IAVF_PTT_UNUSED_ENTRY(209),
-
-	IAVF_PTT_UNUSED_ENTRY(210),
-	IAVF_PTT_UNUSED_ENTRY(211),
-	IAVF_PTT_UNUSED_ENTRY(212),
-	IAVF_PTT_UNUSED_ENTRY(213),
-	IAVF_PTT_UNUSED_ENTRY(214),
-	IAVF_PTT_UNUSED_ENTRY(215),
-	IAVF_PTT_UNUSED_ENTRY(216),
-	IAVF_PTT_UNUSED_ENTRY(217),
-	IAVF_PTT_UNUSED_ENTRY(218),
-	IAVF_PTT_UNUSED_ENTRY(219),
-
-	IAVF_PTT_UNUSED_ENTRY(220),
-	IAVF_PTT_UNUSED_ENTRY(221),
-	IAVF_PTT_UNUSED_ENTRY(222),
-	IAVF_PTT_UNUSED_ENTRY(223),
-	IAVF_PTT_UNUSED_ENTRY(224),
-	IAVF_PTT_UNUSED_ENTRY(225),
-	IAVF_PTT_UNUSED_ENTRY(226),
-	IAVF_PTT_UNUSED_ENTRY(227),
-	IAVF_PTT_UNUSED_ENTRY(228),
-	IAVF_PTT_UNUSED_ENTRY(229),
-
-	IAVF_PTT_UNUSED_ENTRY(230),
-	IAVF_PTT_UNUSED_ENTRY(231),
-	IAVF_PTT_UNUSED_ENTRY(232),
-	IAVF_PTT_UNUSED_ENTRY(233),
-	IAVF_PTT_UNUSED_ENTRY(234),
-	IAVF_PTT_UNUSED_ENTRY(235),
-	IAVF_PTT_UNUSED_ENTRY(236),
-	IAVF_PTT_UNUSED_ENTRY(237),
-	IAVF_PTT_UNUSED_ENTRY(238),
-	IAVF_PTT_UNUSED_ENTRY(239),
-
-	IAVF_PTT_UNUSED_ENTRY(240),
-	IAVF_PTT_UNUSED_ENTRY(241),
-	IAVF_PTT_UNUSED_ENTRY(242),
-	IAVF_PTT_UNUSED_ENTRY(243),
-	IAVF_PTT_UNUSED_ENTRY(244),
-	IAVF_PTT_UNUSED_ENTRY(245),
-	IAVF_PTT_UNUSED_ENTRY(246),
-	IAVF_PTT_UNUSED_ENTRY(247),
-	IAVF_PTT_UNUSED_ENTRY(248),
-	IAVF_PTT_UNUSED_ENTRY(249),
-
-	IAVF_PTT_UNUSED_ENTRY(250),
-	IAVF_PTT_UNUSED_ENTRY(251),
-	IAVF_PTT_UNUSED_ENTRY(252),
-	IAVF_PTT_UNUSED_ENTRY(253),
-	IAVF_PTT_UNUSED_ENTRY(254),
-	IAVF_PTT_UNUSED_ENTRY(255)
+	[154 ... 255] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h
index de9fda78b43a..9f1f523807c4 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_type.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_type.h
@@ -370,7 +370,6 @@ enum iavf_rx_l2_ptype {
 };
 
 struct iavf_rx_ptype_decoded {
-	u32 ptype:8;
 	u32 known:1;
 	u32 outer_ip:1;
 	u32 outer_ip_ver:1;
diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index 07fe857e9e3a..4f538cdf42c1 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -22,12 +22,14 @@ ice-y := ice_main.o	\
 	 ice_ethtool_fdir.o \
 	 ice_flex_pipe.o \
 	 ice_flow.o	\
+	 ice_idc.o	\
 	 ice_devlink.o	\
 	 ice_fw_update.o \
 	 ice_lag.o	\
 	 ice_ethtool.o
 ice-$(CONFIG_PCI_IOV) += ice_virtchnl_allowlist.o
 ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o ice_virtchnl_fdir.o
+ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o
 ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o
 ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o
 ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 2924c67567b8..a450343fbb92 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -34,6 +34,7 @@
 #include <linux/if_bridge.h>
 #include <linux/ctype.h>
 #include <linux/bpf.h>
+#include <linux/auxiliary_bus.h>
 #include <linux/avf/virtchnl.h>
 #include <linux/cpu_rmap.h>
 #include <linux/dim.h>
@@ -55,8 +56,10 @@
 #include "ice_switch.h"
 #include "ice_common.h"
 #include "ice_sched.h"
+#include "ice_idc_int.h"
 #include "ice_virtchnl_pf.h"
 #include "ice_sriov.h"
+#include "ice_ptp.h"
 #include "ice_fdir.h"
 #include "ice_xsk.h"
 #include "ice_arfs.h"
@@ -72,12 +75,15 @@
 
 #define ICE_DFLT_TRAFFIC_CLASS	BIT(0)
 #define ICE_INT_NAME_STR_LEN	(IFNAMSIZ + 16)
-#define ICE_AQ_LEN		64
+#define ICE_AQ_LEN		192
 #define ICE_MBXSQ_LEN		64
+#define ICE_SBQ_LEN		64
 #define ICE_MIN_LAN_TXRX_MSIX	1
 #define ICE_MIN_LAN_OICR_MSIX	1
 #define ICE_MIN_MSIX		(ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_LAN_OICR_MSIX)
 #define ICE_FDIR_MSIX		2
+#define ICE_RDMA_NUM_AEQ_MSIX	4
+#define ICE_MIN_RDMA_MSIX	2
 #define ICE_NO_VSI		0xffff
 #define ICE_VSI_MAP_CONTIG	0
 #define ICE_VSI_MAP_SCATTER	1
@@ -88,8 +94,9 @@
 #define ICE_MAX_LG_RSS_QS	256
 #define ICE_RES_VALID_BIT	0x8000
 #define ICE_RES_MISC_VEC_ID	(ICE_RES_VALID_BIT - 1)
+#define ICE_RES_RDMA_VEC_ID	(ICE_RES_MISC_VEC_ID - 1)
 /* All VF control VSIs share the same IRQ, so assign a unique ID for them */
-#define ICE_RES_VF_CTRL_VEC_ID	(ICE_RES_MISC_VEC_ID - 1)
+#define ICE_RES_VF_CTRL_VEC_ID	(ICE_RES_RDMA_VEC_ID - 1)
 #define ICE_INVAL_Q_INDEX	0xffff
 #define ICE_INVAL_VFID		256
 
@@ -203,9 +210,9 @@ enum ice_pf_state {
 	ICE_NEEDS_RESTART,
 	ICE_PREPARED_FOR_RESET,	/* set by driver when prepared */
 	ICE_RESET_OICR_RECV,		/* set by driver after rcv reset OICR */
-	ICE_PFR_REQ,			/* set by driver and peers */
-	ICE_CORER_REQ,		/* set by driver and peers */
-	ICE_GLOBR_REQ,		/* set by driver and peers */
+	ICE_PFR_REQ,		/* set by driver */
+	ICE_CORER_REQ,		/* set by driver */
+	ICE_GLOBR_REQ,		/* set by driver */
 	ICE_CORER_RECV,		/* set by OICR handler */
 	ICE_GLOBR_RECV,		/* set by OICR handler */
 	ICE_EMPR_RECV,		/* set by OICR handler */
@@ -222,6 +229,7 @@ enum ice_pf_state {
 	ICE_STATE_NOMINAL_CHECK_BITS,
 	ICE_ADMINQ_EVENT_PENDING,
 	ICE_MAILBOXQ_EVENT_PENDING,
+	ICE_SIDEBANDQ_EVENT_PENDING,
 	ICE_MDD_EVENT_PENDING,
 	ICE_VFLR_EVENT_PENDING,
 	ICE_FLTR_OVERFLOW_PROMISC,
@@ -332,6 +340,7 @@ struct ice_vsi {
 	u16 req_rxq;			 /* User requested Rx queues */
 	u16 num_rx_desc;
 	u16 num_tx_desc;
+	u16 qset_handle[ICE_MAX_TRAFFIC_CLASS];
 	struct ice_tc_cfg tc_cfg;
 	struct bpf_prog *xdp_prog;
 	struct ice_ring **xdp_rings;	 /* XDP ring array */
@@ -374,17 +383,22 @@ struct ice_q_vector {
 
 enum ice_pf_flags {
 	ICE_FLAG_FLTR_SYNC,
+	ICE_FLAG_RDMA_ENA,
 	ICE_FLAG_RSS_ENA,
 	ICE_FLAG_SRIOV_ENA,
 	ICE_FLAG_SRIOV_CAPABLE,
 	ICE_FLAG_DCB_CAPABLE,
 	ICE_FLAG_DCB_ENA,
 	ICE_FLAG_FD_ENA,
+	ICE_FLAG_PTP_SUPPORTED,		/* PTP is supported by NVM */
+	ICE_FLAG_PTP,			/* PTP is enabled by software */
+	ICE_FLAG_AUX_ENA,
 	ICE_FLAG_ADV_FEATURES,
 	ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA,
 	ICE_FLAG_TOTAL_PORT_SHUTDOWN_ENA,
 	ICE_FLAG_NO_MEDIA,
 	ICE_FLAG_FW_LLDP_AGENT,
+	ICE_FLAG_MOD_POWER_UNSUPPORTED,
 	ICE_FLAG_ETHTOOL_CTXT,		/* set when ethtool holds RTNL lock */
 	ICE_FLAG_LEGACY_RX,
 	ICE_FLAG_VF_TRUE_PROMISC_ENA,
@@ -440,12 +454,17 @@ struct ice_pf {
 	struct mutex sw_mutex;		/* lock for protecting VSI alloc flow */
 	struct mutex tc_mutex;		/* lock to protect TC changes */
 	u32 msg_enable;
+	struct ice_ptp ptp;
+	u16 num_rdma_msix;		/* Total MSIX vectors for RDMA driver */
+	u16 rdma_base_vector;
 
 	/* spinlock to protect the AdminQ wait list */
 	spinlock_t aq_wait_lock;
 	struct hlist_head aq_wait_list;
 	wait_queue_head_t aq_wait_queue;
 
+	wait_queue_head_t reset_wait_queue;
+
 	u32 hw_csum_rx_error;
 	u16 oicr_idx;		/* Other interrupt cause MSIX vector index */
 	u16 num_avail_sw_msix;	/* remaining MSIX SW vectors left unclaimed */
@@ -472,6 +491,8 @@ struct ice_pf {
 	unsigned long tx_timeout_last_recovery;
 	u32 tx_timeout_recovery_level;
 	char int_name[ICE_INT_NAME_STR_LEN];
+	struct auxiliary_device *adev;
+	int aux_idx;
 	u32 sw_int_count;
 
 	__le64 nvm_phy_type_lo; /* NVM PHY type low */
@@ -638,6 +659,9 @@ int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed);
 void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size);
 int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset);
 void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
+int ice_plug_aux_dev(struct ice_pf *pf);
+void ice_unplug_aux_dev(struct ice_pf *pf);
+int ice_init_rdma(struct ice_pf *pf);
 const char *ice_stat_str(enum ice_status stat_err);
 const char *ice_aq_str(enum ice_aq_err aq_err);
 bool ice_is_wol_supported(struct ice_hw *hw);
@@ -662,4 +686,25 @@ int ice_open_internal(struct net_device *netdev);
 int ice_stop(struct net_device *netdev);
 void ice_service_task_schedule(struct ice_pf *pf);
 
+/**
+ * ice_set_rdma_cap - enable RDMA support
+ * @pf: PF struct
+ */
+static inline void ice_set_rdma_cap(struct ice_pf *pf)
+{
+	if (pf->hw.func_caps.common_cap.rdma && pf->num_rdma_msix) {
+		set_bit(ICE_FLAG_RDMA_ENA, pf->flags);
+		ice_plug_aux_dev(pf);
+	}
+}
+
+/**
+ * ice_clear_rdma_cap - disable RDMA support
+ * @pf: PF struct
+ */
+static inline void ice_clear_rdma_cap(struct ice_pf *pf)
+{
+	ice_unplug_aux_dev(pf);
+	clear_bit(ICE_FLAG_RDMA_ENA, pf->flags);
+}
 #endif /* _ICE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 5cdfe406af84..21b4c7cd6f05 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -108,6 +108,7 @@ struct ice_aqc_list_caps_elem {
 #define ICE_AQC_CAPS_TXQS				0x0042
 #define ICE_AQC_CAPS_MSIX				0x0043
 #define ICE_AQC_CAPS_FD					0x0045
+#define ICE_AQC_CAPS_1588				0x0046
 #define ICE_AQC_CAPS_MAX_MTU				0x0047
 #define ICE_AQC_CAPS_NVM_VER				0x0048
 #define ICE_AQC_CAPS_PENDING_NVM_VER			0x0049
@@ -115,6 +116,7 @@ struct ice_aqc_list_caps_elem {
 #define ICE_AQC_CAPS_PENDING_OROM_VER			0x004B
 #define ICE_AQC_CAPS_NET_VER				0x004C
 #define ICE_AQC_CAPS_PENDING_NET_VER			0x004D
+#define ICE_AQC_CAPS_RDMA				0x0051
 #define ICE_AQC_CAPS_NVM_MGMT				0x0080
 
 	u8 major_ver;
@@ -1122,7 +1124,9 @@ struct ice_aqc_get_link_status_data {
 #define ICE_AQ_LINK_TOPO_UNDRUTIL_PRT	BIT(5)
 #define ICE_AQ_LINK_TOPO_UNDRUTIL_MEDIA	BIT(6)
 #define ICE_AQ_LINK_TOPO_UNSUPP_MEDIA	BIT(7)
-	u8 reserved1;
+	u8 link_cfg_err;
+#define ICE_AQ_LINK_MODULE_POWER_UNSUPPORTED	BIT(5)
+#define ICE_AQ_LINK_INVAL_MAX_POWER_LIMIT	BIT(7)
 	u8 link_info;
 #define ICE_AQ_LINK_UP			BIT(0)	/* Link Status */
 #define ICE_AQ_LINK_FAULT		BIT(1)
@@ -1165,7 +1169,7 @@ struct ice_aqc_get_link_status_data {
 #define ICE_AQ_CFG_PACING_TYPE_FIXED	ICE_AQ_CFG_PACING_TYPE_M
 	/* External Device Power Ability */
 	u8 power_desc;
-#define ICE_AQ_PWR_CLASS_M		0x3
+#define ICE_AQ_PWR_CLASS_M		0x3F
 #define ICE_AQ_LINK_PWR_BASET_LOW_HIGH	0
 #define ICE_AQ_LINK_PWR_BASET_HIGH	1
 #define ICE_AQ_LINK_PWR_QSFP_CLASS_1	0
@@ -1608,6 +1612,15 @@ struct ice_aqc_get_set_rss_lut {
 	__le32 addr_low;
 };
 
+/* Sideband Control Interface Commands */
+/* Neighbor Device Request (indirect 0x0C00); also used for the response. */
+struct ice_aqc_neigh_dev_req {
+	__le16 sb_data_len;
+	u8 reserved[6];
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
 /* Add Tx LAN Queues (indirect 0x0C30) */
 struct ice_aqc_add_txqs {
 	u8 num_qgrps;
@@ -1684,6 +1697,36 @@ struct ice_aqc_dis_txq_item {
 	__le16 q_id[];
 } __packed;
 
+/* Add Tx RDMA Queue Set (indirect 0x0C33) */
+struct ice_aqc_add_rdma_qset {
+	u8 num_qset_grps;
+	u8 reserved[7];
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* This is the descriptor of each Qset entry for the Add Tx RDMA Queue Set
+ * command (0x0C33). Only used within struct ice_aqc_add_rdma_qset.
+ */
+struct ice_aqc_add_tx_rdma_qset_entry {
+	__le16 tx_qset_id;
+	u8 rsvd[2];
+	__le32 qset_teid;
+	struct ice_aqc_txsched_elem info;
+};
+
+/* The format of the command buffer for Add Tx RDMA Queue Set(0x0C33)
+ * is an array of the following structs. Please note that the length of
+ * each struct ice_aqc_add_rdma_qset is variable due to the variable
+ * number of queues in each group!
+ */
+struct ice_aqc_add_rdma_qset_data {
+	__le32 parent_teid;
+	__le16 num_qsets;
+	u8 rsvd[2];
+	struct ice_aqc_add_tx_rdma_qset_entry rdma_qsets[];
+};
+
 /* Configure Firmware Logging Command (indirect 0xFF09)
  * Logging Information Read Response (indirect 0xFF10)
  * Note: The 0xFF10 command has no input parameters.
@@ -1810,6 +1853,30 @@ struct ice_aqc_get_pkg_info_resp {
 	struct ice_aqc_get_pkg_info pkg_info[];
 };
 
+/* Driver Shared Parameters (direct, 0x0C90) */
+struct ice_aqc_driver_shared_params {
+	u8 set_or_get_op;
+#define ICE_AQC_DRIVER_PARAM_OP_MASK		BIT(0)
+#define ICE_AQC_DRIVER_PARAM_SET		0
+#define ICE_AQC_DRIVER_PARAM_GET		1
+	u8 param_indx;
+#define ICE_AQC_DRIVER_PARAM_MAX_IDX		15
+	u8 rsvd[2];
+	__le32 param_val;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+enum ice_aqc_driver_params {
+	/* OS clock index for PTP timer Domain 0 */
+	ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR0 = 0,
+	/* OS clock index for PTP timer Domain 1 */
+	ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR1,
+
+	/* Add new parameters above */
+	ICE_AQC_DRIVER_PARAM_MAX = 16,
+};
+
 /* Lan Queue Overflow Event (direct, 0x1001) */
 struct ice_aqc_event_lan_overflow {
 	__le32 prtdcb_ruptq;
@@ -1878,13 +1945,16 @@ struct ice_aq_desc {
 		struct ice_aqc_lldp_filter_ctrl lldp_filter_ctrl;
 		struct ice_aqc_get_set_rss_lut get_set_rss_lut;
 		struct ice_aqc_get_set_rss_key get_set_rss_key;
+		struct ice_aqc_neigh_dev_req neigh_dev;
 		struct ice_aqc_add_txqs add_txqs;
 		struct ice_aqc_dis_txqs dis_txqs;
+		struct ice_aqc_add_rdma_qset add_rdma_qset;
 		struct ice_aqc_add_get_update_free_vsi vsi_cmd;
 		struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res;
 		struct ice_aqc_fw_logging fw_logging;
 		struct ice_aqc_get_clear_fw_log get_clear_fw_log;
 		struct ice_aqc_download_pkg download_pkg;
+		struct ice_aqc_driver_shared_params drv_shared_params;
 		struct ice_aqc_set_mac_lb set_mac_lb;
 		struct ice_aqc_alloc_free_res_cmd sw_res_ctrl;
 		struct ice_aqc_set_mac_cfg set_mac_cfg;
@@ -2025,15 +2095,21 @@ enum ice_adminq_opc {
 	ice_aqc_opc_get_rss_key				= 0x0B04,
 	ice_aqc_opc_get_rss_lut				= 0x0B05,
 
+	/* Sideband Control Interface commands */
+	ice_aqc_opc_neighbour_device_request		= 0x0C00,
+
 	/* Tx queue handling commands/events */
 	ice_aqc_opc_add_txqs				= 0x0C30,
 	ice_aqc_opc_dis_txqs				= 0x0C31,
+	ice_aqc_opc_add_rdma_qset			= 0x0C33,
 
 	/* package commands */
 	ice_aqc_opc_download_pkg			= 0x0C40,
 	ice_aqc_opc_update_pkg				= 0x0C42,
 	ice_aqc_opc_get_pkg_info_list			= 0x0C43,
 
+	ice_aqc_opc_driver_shared_params		= 0x0C90,
+
 	/* Standalone Commands/Events */
 	ice_aqc_opc_event_lan_overflow			= 0x1001,
 
diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.h b/drivers/net/ethernet/intel/ice/ice_arfs.h
index f39cd16403ed..80ed76f0cace 100644
--- a/drivers/net/ethernet/intel/ice/ice_arfs.h
+++ b/drivers/net/ethernet/intel/ice/ice_arfs.h
@@ -52,12 +52,12 @@ bool
 ice_is_arfs_using_perfect_flow(struct ice_hw *hw,
 			       enum ice_fltr_ptype flow_type);
 #else
-#define ice_sync_arfs_fltrs(pf) do {} while (0)
-#define ice_init_arfs(vsi) do {} while (0)
-#define ice_clear_arfs(vsi) do {} while (0)
-#define ice_remove_arfs(pf) do {} while (0)
-#define ice_free_cpu_rx_rmap(vsi) do {} while (0)
-#define ice_rebuild_arfs(pf) do {} while (0)
+static inline void ice_clear_arfs(struct ice_vsi *vsi) { }
+static inline void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) { }
+static inline void ice_init_arfs(struct ice_vsi *vsi) { }
+static inline void ice_sync_arfs_fltrs(struct ice_pf *pf) { }
+static inline void ice_remove_arfs(struct ice_pf *pf) { }
+static inline void ice_rebuild_arfs(struct ice_pf *pf) { }
 
 static inline int ice_set_cpu_rx_rmap(struct ice_vsi __always_unused *vsi)
 {
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 5985a7e5ca8a..c36057efc7ae 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -287,6 +287,15 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q)
 	/* make sure the context is associated with the right VSI */
 	tlan_ctx->src_vsi = ice_get_hw_vsi_num(hw, vsi->idx);
 
+	/* Restrict Tx timestamps to the PF VSI */
+	switch (vsi->type) {
+	case ICE_VSI_PF:
+		tlan_ctx->tsyn_ena = 1;
+		break;
+	default:
+		break;
+	}
+
 	tlan_ctx->tso_ena = ICE_TX_LEGACY;
 	tlan_ctx->tso_qnum = pf_q;
 
@@ -319,11 +328,9 @@ static unsigned int ice_rx_offset(struct ice_ring *rx_ring)
  *
  * Configure the Rx descriptor ring in RLAN context.
  */
-int ice_setup_rx_ctx(struct ice_ring *ring)
+static int ice_setup_rx_ctx(struct ice_ring *ring)
 {
-	struct device *dev = ice_pf_to_dev(ring->vsi->back);
 	int chain_len = ICE_MAX_CHAINED_RX_BUFS;
-	u16 num_bufs = ICE_DESC_UNUSED(ring);
 	struct ice_vsi *vsi = ring->vsi;
 	u32 rxdid = ICE_RXDID_FLEX_NIC;
 	struct ice_rlan_ctx rlan_ctx;
@@ -339,48 +346,6 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	/* clear the context structure first */
 	memset(&rlan_ctx, 0, sizeof(rlan_ctx));
 
-	ring->rx_buf_len = vsi->rx_buf_len;
-
-	if (ring->vsi->type == ICE_VSI_PF) {
-		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
-			/* coverity[check_return] */
-			xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
-					 ring->q_index, ring->q_vector->napi.napi_id);
-
-		ring->xsk_pool = ice_xsk_pool(ring);
-		if (ring->xsk_pool) {
-			xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
-
-			ring->rx_buf_len =
-				xsk_pool_get_rx_frame_size(ring->xsk_pool);
-			/* For AF_XDP ZC, we disallow packets to span on
-			 * multiple buffers, thus letting us skip that
-			 * handling in the fast-path.
-			 */
-			chain_len = 1;
-			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
-							 MEM_TYPE_XSK_BUFF_POOL,
-							 NULL);
-			if (err)
-				return err;
-			xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
-
-			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
-				 ring->q_index);
-		} else {
-			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
-				/* coverity[check_return] */
-				xdp_rxq_info_reg(&ring->xdp_rxq,
-						 ring->netdev,
-						 ring->q_index, ring->q_vector->napi.napi_id);
-
-			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
-							 MEM_TYPE_PAGE_SHARED,
-							 NULL);
-			if (err)
-				return err;
-		}
-	}
 	/* Receive Queue Base Address.
 	 * Indicates the starting address of the descriptor queue defined in
 	 * 128 Byte units.
@@ -415,6 +380,12 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	 */
 	rlan_ctx.showiv = 0;
 
+	/* For AF_XDP ZC, we disallow packets to span on
+	 * multiple buffers, thus letting us skip that
+	 * handling in the fast-path.
+	 */
+	if (ring->xsk_pool)
+		chain_len = 1;
 	/* Max packet size for this queue - must not be set to a larger value
 	 * than 5 x DBUF
 	 */
@@ -431,14 +402,15 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	 * of same priority
 	 */
 	if (vsi->type != ICE_VSI_VF)
-		ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x3);
+		ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x3, true);
 	else
-		ice_write_qrxflxp_cntxt(hw, pf_q, ICE_RXDID_LEGACY_1, 0x3);
+		ice_write_qrxflxp_cntxt(hw, pf_q, ICE_RXDID_LEGACY_1, 0x3,
+					false);
 
 	/* Absolute queue number out of 2K needs to be passed */
 	err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q);
 	if (err) {
-		dev_err(dev, "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n",
+		dev_err(ice_pf_to_dev(vsi->back), "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n",
 			pf_q, err);
 		return -EIO;
 	}
@@ -458,6 +430,66 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	ring->tail = hw->hw_addr + QRX_TAIL(pf_q);
 	writel(0, ring->tail);
 
+	return 0;
+}
+
+/**
+ * ice_vsi_cfg_rxq - Configure an Rx queue
+ * @ring: the ring being configured
+ *
+ * Return 0 on success and a negative value on error.
+ */
+int ice_vsi_cfg_rxq(struct ice_ring *ring)
+{
+	struct device *dev = ice_pf_to_dev(ring->vsi->back);
+	u16 num_bufs = ICE_DESC_UNUSED(ring);
+	int err;
+
+	ring->rx_buf_len = ring->vsi->rx_buf_len;
+
+	if (ring->vsi->type == ICE_VSI_PF) {
+		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
+			/* coverity[check_return] */
+			xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+					 ring->q_index, ring->q_vector->napi.napi_id);
+
+		ring->xsk_pool = ice_xsk_pool(ring);
+		if (ring->xsk_pool) {
+			xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+
+			ring->rx_buf_len =
+				xsk_pool_get_rx_frame_size(ring->xsk_pool);
+			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+							 MEM_TYPE_XSK_BUFF_POOL,
+							 NULL);
+			if (err)
+				return err;
+			xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
+
+			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
+				 ring->q_index);
+		} else {
+			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
+				/* coverity[check_return] */
+				xdp_rxq_info_reg(&ring->xdp_rxq,
+						 ring->netdev,
+						 ring->q_index, ring->q_vector->napi.napi_id);
+
+			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+							 MEM_TYPE_PAGE_SHARED,
+							 NULL);
+			if (err)
+				return err;
+		}
+	}
+
+	err = ice_setup_rx_ctx(ring);
+	if (err) {
+		dev_err(dev, "ice_setup_rx_ctx failed for RxQ %d, err %d\n",
+			ring->q_index, err);
+		return err;
+	}
+
 	if (ring->xsk_pool) {
 		bool ok;
 
@@ -470,9 +502,13 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 		}
 
 		ok = ice_alloc_rx_bufs_zc(ring, num_bufs);
-		if (!ok)
+		if (!ok) {
+			u16 pf_q = ring->vsi->rxq_map[ring->q_index];
+
 			dev_info(dev, "Failed to allocate some buffers on XSK buffer pool enabled Rx ring %d (pf_q %d)\n",
 				 ring->q_index, pf_q);
+		}
+
 		return 0;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_base.h b/drivers/net/ethernet/intel/ice/ice_base.h
index 44efdb627043..20e1c29aa68a 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.h
+++ b/drivers/net/ethernet/intel/ice/ice_base.h
@@ -6,7 +6,7 @@
 
 #include "ice.h"
 
-int ice_setup_rx_ctx(struct ice_ring *ring);
+int ice_vsi_cfg_rxq(struct ice_ring *ring);
 int __ice_vsi_get_qs(struct ice_qs_cfg *qs_cfg);
 int
 ice_vsi_ctrl_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx, bool wait);
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index e93b1e40f627..2fb81e359cdf 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2018, Intel Corporation. */
 
 #include "ice_common.h"
+#include "ice_lib.h"
 #include "ice_sched.h"
 #include "ice_adminq_cmd.h"
 #include "ice_flow.h"
@@ -58,6 +59,17 @@ static enum ice_status ice_set_mac_type(struct ice_hw *hw)
 }
 
 /**
+ * ice_is_e810
+ * @hw: pointer to the hardware structure
+ *
+ * returns true if the device is E810 based, false if not.
+ */
+bool ice_is_e810(struct ice_hw *hw)
+{
+	return hw->mac_type == ICE_MAC_E810;
+}
+
+/**
  * ice_clear_pf_cfg - Clear PF configuration
  * @hw: pointer to the hardware structure
  *
@@ -424,6 +436,7 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 	li->phy_type_high = le64_to_cpu(link_data.phy_type_high);
 	*hw_media_type = ice_get_media_type(pi);
 	li->link_info = link_data.link_info;
+	li->link_cfg_err = link_data.link_cfg_err;
 	li->an_info = link_data.an_info;
 	li->ext_info = link_data.ext_info;
 	li->max_frame_size = le16_to_cpu(link_data.max_frame_size);
@@ -454,6 +467,7 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 		  (unsigned long long)li->phy_type_high);
 	ice_debug(hw, ICE_DBG_LINK, "	media_type = 0x%x\n", *hw_media_type);
 	ice_debug(hw, ICE_DBG_LINK, "	link_info = 0x%x\n", li->link_info);
+	ice_debug(hw, ICE_DBG_LINK, "	link_cfg_err = 0x%x\n", li->link_cfg_err);
 	ice_debug(hw, ICE_DBG_LINK, "	an_info = 0x%x\n", li->an_info);
 	ice_debug(hw, ICE_DBG_LINK, "	ext_info = 0x%x\n", li->ext_info);
 	ice_debug(hw, ICE_DBG_LINK, "	fec_info = 0x%x\n", li->fec_info);
@@ -1062,7 +1076,8 @@ enum ice_status ice_check_reset(struct ice_hw *hw)
 				 GLNVM_ULD_POR_DONE_1_M |\
 				 GLNVM_ULD_PCIER_DONE_2_M)
 
-	uld_mask = ICE_RESET_DONE_MASK;
+	uld_mask = ICE_RESET_DONE_MASK | (hw->func_caps.common_cap.rdma ?
+					  GLNVM_ULD_PE_DONE_M : 0);
 
 	/* Device is Active; check Global Reset processes are done */
 	for (cnt = 0; cnt < ICE_PF_RESET_WAIT_COUNT; cnt++) {
@@ -1289,6 +1304,64 @@ const struct ice_ctx_ele ice_tlan_ctx_info[] = {
 	{ 0 }
 };
 
+/* Sideband Queue command wrappers */
+
+/**
+ * ice_sbq_send_cmd - send Sideband Queue command to Sideband Queue
+ * @hw: pointer to the HW struct
+ * @desc: descriptor describing the command
+ * @buf: buffer to use for indirect commands (NULL for direct commands)
+ * @buf_size: size of buffer for indirect commands (0 for direct commands)
+ * @cd: pointer to command details structure
+ */
+static int
+ice_sbq_send_cmd(struct ice_hw *hw, struct ice_sbq_cmd_desc *desc,
+		 void *buf, u16 buf_size, struct ice_sq_cd *cd)
+{
+	return ice_status_to_errno(ice_sq_send_cmd(hw, ice_get_sbq(hw),
+						   (struct ice_aq_desc *)desc,
+						   buf, buf_size, cd));
+}
+
+/**
+ * ice_sbq_rw_reg - Fill Sideband Queue command
+ * @hw: pointer to the HW struct
+ * @in: message info to be filled in descriptor
+ */
+int ice_sbq_rw_reg(struct ice_hw *hw, struct ice_sbq_msg_input *in)
+{
+	struct ice_sbq_cmd_desc desc = {0};
+	struct ice_sbq_msg_req msg = {0};
+	u16 msg_len;
+	int status;
+
+	msg_len = sizeof(msg);
+
+	msg.dest_dev = in->dest_dev;
+	msg.opcode = in->opcode;
+	msg.flags = ICE_SBQ_MSG_FLAGS;
+	msg.sbe_fbe = ICE_SBQ_MSG_SBE_FBE;
+	msg.msg_addr_low = cpu_to_le16(in->msg_addr_low);
+	msg.msg_addr_high = cpu_to_le32(in->msg_addr_high);
+
+	if (in->opcode)
+		msg.data = cpu_to_le32(in->data);
+	else
+		/* data read comes back in completion, so shorten the struct by
+		 * sizeof(msg.data)
+		 */
+		msg_len -= sizeof(msg.data);
+
+	desc.flags = cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.opcode = cpu_to_le16(ice_sbq_opc_neigh_dev_req);
+	desc.param0.cmd_len = cpu_to_le16(msg_len);
+	status = ice_sbq_send_cmd(hw, &desc, &msg, msg_len, NULL);
+	if (!status && !in->opcode)
+		in->data = le32_to_cpu
+			(((struct ice_sbq_msg_cmpl *)&msg)->data);
+	return status;
+}
+
 /* FW Admin Queue command wrappers */
 
 /* Software lock/mutex that is meant to be held while the Global Config Lock
@@ -1938,6 +2011,10 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 		ice_debug(hw, ICE_DBG_INIT, "%s: nvm_unified_update = %d\n", prefix,
 			  caps->nvm_unified_update);
 		break;
+	case ICE_AQC_CAPS_RDMA:
+		caps->rdma = (number == 1);
+		ice_debug(hw, ICE_DBG_INIT, "%s: rdma = %d\n", prefix, caps->rdma);
+		break;
 	case ICE_AQC_CAPS_MAX_MTU:
 		caps->max_mtu = number;
 		ice_debug(hw, ICE_DBG_INIT, "%s: max_mtu = %d\n",
@@ -1971,6 +2048,16 @@ ice_recalc_port_limited_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps)
 		caps->maxtc = 4;
 		ice_debug(hw, ICE_DBG_INIT, "reducing maxtc to %d (based on #ports)\n",
 			  caps->maxtc);
+		if (caps->rdma) {
+			ice_debug(hw, ICE_DBG_INIT, "forcing RDMA off\n");
+			caps->rdma = 0;
+		}
+
+		/* print message only when processing device capabilities
+		 * during initialization.
+		 */
+		if (caps == &hw->dev_caps.common_cap)
+			dev_info(ice_hw_to_dev(hw), "RDMA functionality is not available with the current device configuration.\n");
 	}
 }
 
@@ -2017,6 +2104,48 @@ ice_parse_vsi_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
 }
 
 /**
+ * ice_parse_1588_func_caps - Parse ICE_AQC_CAPS_1588 function caps
+ * @hw: pointer to the HW struct
+ * @func_p: pointer to function capabilities structure
+ * @cap: pointer to the capability element to parse
+ *
+ * Extract function capabilities for ICE_AQC_CAPS_1588.
+ */
+static void
+ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
+			 struct ice_aqc_list_caps_elem *cap)
+{
+	struct ice_ts_func_info *info = &func_p->ts_func_info;
+	u32 number = le32_to_cpu(cap->number);
+
+	info->ena = ((number & ICE_TS_FUNC_ENA_M) != 0);
+	func_p->common_cap.ieee_1588 = info->ena;
+
+	info->src_tmr_owned = ((number & ICE_TS_SRC_TMR_OWND_M) != 0);
+	info->tmr_ena = ((number & ICE_TS_TMR_ENA_M) != 0);
+	info->tmr_index_owned = ((number & ICE_TS_TMR_IDX_OWND_M) != 0);
+	info->tmr_index_assoc = ((number & ICE_TS_TMR_IDX_ASSOC_M) != 0);
+
+	info->clk_freq = (number & ICE_TS_CLK_FREQ_M) >> ICE_TS_CLK_FREQ_S;
+	info->clk_src = ((number & ICE_TS_CLK_SRC_M) != 0);
+
+	ice_debug(hw, ICE_DBG_INIT, "func caps: ieee_1588 = %u\n",
+		  func_p->common_cap.ieee_1588);
+	ice_debug(hw, ICE_DBG_INIT, "func caps: src_tmr_owned = %u\n",
+		  info->src_tmr_owned);
+	ice_debug(hw, ICE_DBG_INIT, "func caps: tmr_ena = %u\n",
+		  info->tmr_ena);
+	ice_debug(hw, ICE_DBG_INIT, "func caps: tmr_index_owned = %u\n",
+		  info->tmr_index_owned);
+	ice_debug(hw, ICE_DBG_INIT, "func caps: tmr_index_assoc = %u\n",
+		  info->tmr_index_assoc);
+	ice_debug(hw, ICE_DBG_INIT, "func caps: clk_freq = %u\n",
+		  info->clk_freq);
+	ice_debug(hw, ICE_DBG_INIT, "func caps: clk_src = %u\n",
+		  info->clk_src);
+}
+
+/**
  * ice_parse_fdir_func_caps - Parse ICE_AQC_CAPS_FD function caps
  * @hw: pointer to the HW struct
  * @func_p: pointer to function capabilities structure
@@ -2082,6 +2211,9 @@ ice_parse_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
 		case ICE_AQC_CAPS_VSI:
 			ice_parse_vsi_func_caps(hw, func_p, &cap_resp[i]);
 			break;
+		case ICE_AQC_CAPS_1588:
+			ice_parse_1588_func_caps(hw, func_p, &cap_resp[i]);
+			break;
 		case ICE_AQC_CAPS_FD:
 			ice_parse_fdir_func_caps(hw, func_p);
 			break;
@@ -2155,6 +2287,57 @@ ice_parse_vsi_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 }
 
 /**
+ * ice_parse_1588_dev_caps - Parse ICE_AQC_CAPS_1588 device caps
+ * @hw: pointer to the HW struct
+ * @dev_p: pointer to device capabilities structure
+ * @cap: capability element to parse
+ *
+ * Parse ICE_AQC_CAPS_1588 for device capabilities.
+ */
+static void
+ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
+			struct ice_aqc_list_caps_elem *cap)
+{
+	struct ice_ts_dev_info *info = &dev_p->ts_dev_info;
+	u32 logical_id = le32_to_cpu(cap->logical_id);
+	u32 phys_id = le32_to_cpu(cap->phys_id);
+	u32 number = le32_to_cpu(cap->number);
+
+	info->ena = ((number & ICE_TS_DEV_ENA_M) != 0);
+	dev_p->common_cap.ieee_1588 = info->ena;
+
+	info->tmr0_owner = number & ICE_TS_TMR0_OWNR_M;
+	info->tmr0_owned = ((number & ICE_TS_TMR0_OWND_M) != 0);
+	info->tmr0_ena = ((number & ICE_TS_TMR0_ENA_M) != 0);
+
+	info->tmr1_owner = (number & ICE_TS_TMR1_OWNR_M) >> ICE_TS_TMR1_OWNR_S;
+	info->tmr1_owned = ((number & ICE_TS_TMR1_OWND_M) != 0);
+	info->tmr1_ena = ((number & ICE_TS_TMR1_ENA_M) != 0);
+
+	info->ena_ports = logical_id;
+	info->tmr_own_map = phys_id;
+
+	ice_debug(hw, ICE_DBG_INIT, "dev caps: ieee_1588 = %u\n",
+		  dev_p->common_cap.ieee_1588);
+	ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr0_owner = %u\n",
+		  info->tmr0_owner);
+	ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr0_owned = %u\n",
+		  info->tmr0_owned);
+	ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr0_ena = %u\n",
+		  info->tmr0_ena);
+	ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr1_owner = %u\n",
+		  info->tmr1_owner);
+	ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr1_owned = %u\n",
+		  info->tmr1_owned);
+	ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr1_ena = %u\n",
+		  info->tmr1_ena);
+	ice_debug(hw, ICE_DBG_INIT, "dev caps: ieee_1588 ena_ports = %u\n",
+		  info->ena_ports);
+	ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr_own_map = %u\n",
+		  info->tmr_own_map);
+}
+
+/**
  * ice_parse_fdir_dev_caps - Parse ICE_AQC_CAPS_FD device caps
  * @hw: pointer to the HW struct
  * @dev_p: pointer to device capabilities structure
@@ -2215,6 +2398,9 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 		case ICE_AQC_CAPS_VSI:
 			ice_parse_vsi_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
+		case ICE_AQC_CAPS_1588:
+			ice_parse_1588_dev_caps(hw, dev_p, &cap_resp[i]);
+			break;
 		case  ICE_AQC_CAPS_FD:
 			ice_parse_fdir_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
@@ -3635,6 +3821,52 @@ do_aq:
 	return status;
 }
 
+/**
+ * ice_aq_add_rdma_qsets
+ * @hw: pointer to the hardware structure
+ * @num_qset_grps: Number of RDMA Qset groups
+ * @qset_list: list of Qset groups to be added
+ * @buf_size: size of buffer for indirect command
+ * @cd: pointer to command details structure or NULL
+ *
+ * Add Tx RDMA Qsets (0x0C33)
+ */
+static int
+ice_aq_add_rdma_qsets(struct ice_hw *hw, u8 num_qset_grps,
+		      struct ice_aqc_add_rdma_qset_data *qset_list,
+		      u16 buf_size, struct ice_sq_cd *cd)
+{
+	struct ice_aqc_add_rdma_qset_data *list;
+	struct ice_aqc_add_rdma_qset *cmd;
+	struct ice_aq_desc desc;
+	u16 i, sum_size = 0;
+
+	cmd = &desc.params.add_rdma_qset;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_rdma_qset);
+
+	if (num_qset_grps > ICE_LAN_TXQ_MAX_QGRPS)
+		return -EINVAL;
+
+	for (i = 0, list = qset_list; i < num_qset_grps; i++) {
+		u16 num_qsets = le16_to_cpu(list->num_qsets);
+
+		sum_size += struct_size(list, rdma_qsets, num_qsets);
+		list = (struct ice_aqc_add_rdma_qset_data *)(list->rdma_qsets +
+							     num_qsets);
+	}
+
+	if (buf_size != sum_size)
+		return -EINVAL;
+
+	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+	cmd->num_qset_grps = num_qset_grps;
+
+	return ice_status_to_errno(ice_aq_send_cmd(hw, &desc, qset_list,
+						   buf_size, cd));
+}
+
 /* End of FW Admin Queue command wrappers */
 
 /**
@@ -4133,6 +4365,162 @@ ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap,
 }
 
 /**
+ * ice_cfg_vsi_rdma - configure the VSI RDMA queues
+ * @pi: port information structure
+ * @vsi_handle: software VSI handle
+ * @tc_bitmap: TC bitmap
+ * @max_rdmaqs: max RDMA queues array per TC
+ *
+ * This function adds/updates the VSI RDMA queues per TC.
+ */
+int
+ice_cfg_vsi_rdma(struct ice_port_info *pi, u16 vsi_handle, u16 tc_bitmap,
+		 u16 *max_rdmaqs)
+{
+	return ice_status_to_errno(ice_cfg_vsi_qs(pi, vsi_handle, tc_bitmap,
+						  max_rdmaqs,
+						  ICE_SCHED_NODE_OWNER_RDMA));
+}
+
+/**
+ * ice_ena_vsi_rdma_qset
+ * @pi: port information structure
+ * @vsi_handle: software VSI handle
+ * @tc: TC number
+ * @rdma_qset: pointer to RDMA Qset
+ * @num_qsets: number of RDMA Qsets
+ * @qset_teid: pointer to Qset node TEIDs
+ *
+ * This function adds RDMA Qset
+ */
+int
+ice_ena_vsi_rdma_qset(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
+		      u16 *rdma_qset, u16 num_qsets, u32 *qset_teid)
+{
+	struct ice_aqc_txsched_elem_data node = { 0 };
+	struct ice_aqc_add_rdma_qset_data *buf;
+	struct ice_sched_node *parent;
+	enum ice_status status;
+	struct ice_hw *hw;
+	u16 i, buf_size;
+	int ret;
+
+	if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY)
+		return -EIO;
+	hw = pi->hw;
+
+	if (!ice_is_vsi_valid(hw, vsi_handle))
+		return -EINVAL;
+
+	buf_size = struct_size(buf, rdma_qsets, num_qsets);
+	buf = kzalloc(buf_size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+	mutex_lock(&pi->sched_lock);
+
+	parent = ice_sched_get_free_qparent(pi, vsi_handle, tc,
+					    ICE_SCHED_NODE_OWNER_RDMA);
+	if (!parent) {
+		ret = -EINVAL;
+		goto rdma_error_exit;
+	}
+	buf->parent_teid = parent->info.node_teid;
+	node.parent_teid = parent->info.node_teid;
+
+	buf->num_qsets = cpu_to_le16(num_qsets);
+	for (i = 0; i < num_qsets; i++) {
+		buf->rdma_qsets[i].tx_qset_id = cpu_to_le16(rdma_qset[i]);
+		buf->rdma_qsets[i].info.valid_sections =
+			ICE_AQC_ELEM_VALID_GENERIC | ICE_AQC_ELEM_VALID_CIR |
+			ICE_AQC_ELEM_VALID_EIR;
+		buf->rdma_qsets[i].info.generic = 0;
+		buf->rdma_qsets[i].info.cir_bw.bw_profile_idx =
+			cpu_to_le16(ICE_SCHED_DFLT_RL_PROF_ID);
+		buf->rdma_qsets[i].info.cir_bw.bw_alloc =
+			cpu_to_le16(ICE_SCHED_DFLT_BW_WT);
+		buf->rdma_qsets[i].info.eir_bw.bw_profile_idx =
+			cpu_to_le16(ICE_SCHED_DFLT_RL_PROF_ID);
+		buf->rdma_qsets[i].info.eir_bw.bw_alloc =
+			cpu_to_le16(ICE_SCHED_DFLT_BW_WT);
+	}
+	ret = ice_aq_add_rdma_qsets(hw, 1, buf, buf_size, NULL);
+	if (ret) {
+		ice_debug(hw, ICE_DBG_RDMA, "add RDMA qset failed\n");
+		goto rdma_error_exit;
+	}
+	node.data.elem_type = ICE_AQC_ELEM_TYPE_LEAF;
+	for (i = 0; i < num_qsets; i++) {
+		node.node_teid = buf->rdma_qsets[i].qset_teid;
+		status = ice_sched_add_node(pi, hw->num_tx_sched_layers - 1,
+					    &node);
+		if (status) {
+			ret = ice_status_to_errno(status);
+			break;
+		}
+		qset_teid[i] = le32_to_cpu(node.node_teid);
+	}
+rdma_error_exit:
+	mutex_unlock(&pi->sched_lock);
+	kfree(buf);
+	return ret;
+}
+
+/**
+ * ice_dis_vsi_rdma_qset - free RDMA resources
+ * @pi: port_info struct
+ * @count: number of RDMA Qsets to free
+ * @qset_teid: TEID of Qset node
+ * @q_id: list of queue IDs being disabled
+ */
+int
+ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid,
+		      u16 *q_id)
+{
+	struct ice_aqc_dis_txq_item *qg_list;
+	enum ice_status status = 0;
+	struct ice_hw *hw;
+	u16 qg_size;
+	int i;
+
+	if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY)
+		return -EIO;
+
+	hw = pi->hw;
+
+	qg_size = struct_size(qg_list, q_id, 1);
+	qg_list = kzalloc(qg_size, GFP_KERNEL);
+	if (!qg_list)
+		return -ENOMEM;
+
+	mutex_lock(&pi->sched_lock);
+
+	for (i = 0; i < count; i++) {
+		struct ice_sched_node *node;
+
+		node = ice_sched_find_node_by_teid(pi->root, qset_teid[i]);
+		if (!node)
+			continue;
+
+		qg_list->parent_teid = node->info.parent_teid;
+		qg_list->num_qs = 1;
+		qg_list->q_id[0] =
+			cpu_to_le16(q_id[i] |
+				    ICE_AQC_Q_DIS_BUF_ELEM_TYPE_RDMA_QSET);
+
+		status = ice_aq_dis_lan_txq(hw, 1, qg_list, qg_size,
+					    ICE_NO_RESET, 0, NULL);
+		if (status)
+			break;
+
+		ice_free_sched_node(pi, node);
+	}
+
+	mutex_unlock(&pi->sched_lock);
+	kfree(qg_list);
+	return ice_status_to_errno(status);
+}
+
+/**
  * ice_replay_pre_init - replay pre initialization
  * @hw: pointer to the HW struct
  *
@@ -4304,6 +4692,81 @@ ice_sched_query_elem(struct ice_hw *hw, u32 node_teid,
 }
 
 /**
+ * ice_aq_set_driver_param - Set driver parameter to share via firmware
+ * @hw: pointer to the HW struct
+ * @idx: parameter index to set
+ * @value: the value to set the parameter to
+ * @cd: pointer to command details structure or NULL
+ *
+ * Set the value of one of the software defined parameters. All PFs connected
+ * to this device can read the value using ice_aq_get_driver_param.
+ *
+ * Note that firmware provides no synchronization or locking, and will not
+ * save the parameter value during a device reset. It is expected that
+ * a single PF will write the parameter value, while all other PFs will only
+ * read it.
+ */
+int
+ice_aq_set_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx,
+			u32 value, struct ice_sq_cd *cd)
+{
+	struct ice_aqc_driver_shared_params *cmd;
+	struct ice_aq_desc desc;
+
+	if (idx >= ICE_AQC_DRIVER_PARAM_MAX)
+		return -EIO;
+
+	cmd = &desc.params.drv_shared_params;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_driver_shared_params);
+
+	cmd->set_or_get_op = ICE_AQC_DRIVER_PARAM_SET;
+	cmd->param_indx = idx;
+	cmd->param_val = cpu_to_le32(value);
+
+	return ice_status_to_errno(ice_aq_send_cmd(hw, &desc, NULL, 0, cd));
+}
+
+/**
+ * ice_aq_get_driver_param - Get driver parameter shared via firmware
+ * @hw: pointer to the HW struct
+ * @idx: parameter index to set
+ * @value: storage to return the shared parameter
+ * @cd: pointer to command details structure or NULL
+ *
+ * Get the value of one of the software defined parameters.
+ *
+ * Note that firmware provides no synchronization or locking. It is expected
+ * that only a single PF will write a given parameter.
+ */
+int
+ice_aq_get_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx,
+			u32 *value, struct ice_sq_cd *cd)
+{
+	struct ice_aqc_driver_shared_params *cmd;
+	struct ice_aq_desc desc;
+	enum ice_status status;
+
+	if (idx >= ICE_AQC_DRIVER_PARAM_MAX)
+		return -EIO;
+
+	cmd = &desc.params.drv_shared_params;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_driver_shared_params);
+
+	cmd->set_or_get_op = ICE_AQC_DRIVER_PARAM_GET;
+	cmd->param_indx = idx;
+
+	status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+	if (status)
+		return ice_status_to_errno(status);
+
+	*value = le32_to_cpu(cmd->param_val);
+
+	return 0;
+}
+
+/**
  * ice_fw_supports_link_override
  * @hw: pointer to the hardware structure
  *
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 7a9d2dfb21a2..fb16070f02e2 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -40,6 +40,8 @@ enum ice_status
 ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries,
 		      struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size,
 		      enum ice_adminq_opc opc, struct ice_sq_cd *cd);
+bool ice_is_sbq_supported(struct ice_hw *hw);
+struct ice_ctl_q_info *ice_get_sbq(struct ice_hw *hw);
 enum ice_status
 ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 		struct ice_aq_desc *desc, void *buf, u16 buf_size,
@@ -97,6 +99,7 @@ ice_update_phy_type(u64 *phy_type_low, u64 *phy_type_high,
 enum ice_status
 ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags,
 			struct ice_sq_cd *cd);
+bool ice_is_e810(struct ice_hw *hw);
 enum ice_status ice_clear_pf_cfg(struct ice_hw *hw);
 enum ice_status
 ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi,
@@ -147,6 +150,15 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr,
 		  u16 mem_addr, u8 page, u8 set_page, u8 *data, u8 length,
 		  bool write, struct ice_sq_cd *cd);
 
+int
+ice_cfg_vsi_rdma(struct ice_port_info *pi, u16 vsi_handle, u16 tc_bitmap,
+		 u16 *max_rdmaqs);
+int
+ice_ena_vsi_rdma_qset(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
+		      u16 *rdma_qset, u16 num_qsets, u32 *qset_teid);
+int
+ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid,
+		      u16 *q_id);
 enum ice_status
 ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues,
 		u16 *q_handle, u16 *q_ids, u32 *q_teids,
@@ -164,6 +176,7 @@ void ice_replay_post(struct ice_hw *hw);
 void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf);
 struct ice_q_ctx *
 ice_get_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 q_handle);
+int ice_sbq_rw_reg(struct ice_hw *hw, struct ice_sbq_msg_input *in);
 void
 ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
 		  u64 *prev_stat, u64 *cur_stat);
@@ -173,6 +186,12 @@ ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
 enum ice_status
 ice_sched_query_elem(struct ice_hw *hw, u32 node_teid,
 		     struct ice_aqc_txsched_elem_data *buf);
+int
+ice_aq_set_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx,
+			u32 value, struct ice_sq_cd *cd);
+int
+ice_aq_get_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx,
+			u32 *value, struct ice_sq_cd *cd);
 enum ice_status
 ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size,
 		    struct ice_sq_cd *cd);
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index 87b33bdd4960..03bdb125be36 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -52,6 +52,19 @@ static void ice_mailbox_init_regs(struct ice_hw *hw)
 }
 
 /**
+ * ice_sb_init_regs - Initialize Sideband registers
+ * @hw: pointer to the hardware structure
+ *
+ * This assumes the alloc_sq and alloc_rq functions have already been called
+ */
+static void ice_sb_init_regs(struct ice_hw *hw)
+{
+	struct ice_ctl_q_info *cq = &hw->sbq;
+
+	ICE_CQ_INIT_REGS(cq, PF_SB);
+}
+
+/**
  * ice_check_sq_alive
  * @hw: pointer to the HW struct
  * @cq: pointer to the specific Control queue
@@ -609,6 +622,10 @@ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type)
 		ice_adminq_init_regs(hw);
 		cq = &hw->adminq;
 		break;
+	case ICE_CTL_Q_SB:
+		ice_sb_init_regs(hw);
+		cq = &hw->sbq;
+		break;
 	case ICE_CTL_Q_MAILBOX:
 		ice_mailbox_init_regs(hw);
 		cq = &hw->mailboxq;
@@ -646,6 +663,32 @@ init_ctrlq_free_sq:
 }
 
 /**
+ * ice_is_sbq_supported - is the sideband queue supported
+ * @hw: pointer to the hardware structure
+ *
+ * Returns true if the sideband control queue interface is
+ * supported for the device, false otherwise
+ */
+bool ice_is_sbq_supported(struct ice_hw *hw)
+{
+	/* The device sideband queue is only supported on devices with the
+	 * generic MAC type.
+	 */
+	return hw->mac_type == ICE_MAC_GENERIC;
+}
+
+/**
+ * ice_get_sbq - returns the right control queue to use for sideband
+ * @hw: pointer to the hardware structure
+ */
+struct ice_ctl_q_info *ice_get_sbq(struct ice_hw *hw)
+{
+	if (ice_is_sbq_supported(hw))
+		return &hw->sbq;
+	return &hw->adminq;
+}
+
+/**
  * ice_shutdown_ctrlq - shutdown routine for any control queue
  * @hw: pointer to the hardware structure
  * @q_type: specific Control queue type
@@ -662,6 +705,9 @@ static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type)
 		if (ice_check_sq_alive(hw, cq))
 			ice_aq_q_shutdown(hw, true);
 		break;
+	case ICE_CTL_Q_SB:
+		cq = &hw->sbq;
+		break;
 	case ICE_CTL_Q_MAILBOX:
 		cq = &hw->mailboxq;
 		break;
@@ -685,6 +731,9 @@ void ice_shutdown_all_ctrlq(struct ice_hw *hw)
 {
 	/* Shutdown FW admin queue */
 	ice_shutdown_ctrlq(hw, ICE_CTL_Q_ADMIN);
+	/* Shutdown PHY Sideband */
+	if (ice_is_sbq_supported(hw))
+		ice_shutdown_ctrlq(hw, ICE_CTL_Q_SB);
 	/* Shutdown PF-VF Mailbox */
 	ice_shutdown_ctrlq(hw, ICE_CTL_Q_MAILBOX);
 }
@@ -724,6 +773,15 @@ enum ice_status ice_init_all_ctrlq(struct ice_hw *hw)
 
 	if (status)
 		return status;
+	/* sideband control queue (SBQ) interface is not supported on some
+	 * devices. Initialize if supported, else fallback to the admin queue
+	 * interface
+	 */
+	if (ice_is_sbq_supported(hw)) {
+		status = ice_init_ctrlq(hw, ICE_CTL_Q_SB);
+		if (status)
+			return status;
+	}
 	/* Init Mailbox queue */
 	return ice_init_ctrlq(hw, ICE_CTL_Q_MAILBOX);
 }
@@ -759,6 +817,8 @@ static void ice_init_ctrlq_locks(struct ice_ctl_q_info *cq)
 enum ice_status ice_create_all_ctrlq(struct ice_hw *hw)
 {
 	ice_init_ctrlq_locks(&hw->adminq);
+	if (ice_is_sbq_supported(hw))
+		ice_init_ctrlq_locks(&hw->sbq);
 	ice_init_ctrlq_locks(&hw->mailboxq);
 
 	return ice_init_all_ctrlq(hw);
@@ -791,6 +851,8 @@ void ice_destroy_all_ctrlq(struct ice_hw *hw)
 	ice_shutdown_all_ctrlq(hw);
 
 	ice_destroy_ctrlq_locks(&hw->adminq);
+	if (ice_is_sbq_supported(hw))
+		ice_destroy_ctrlq_locks(&hw->sbq);
 	ice_destroy_ctrlq_locks(&hw->mailboxq);
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h
index fe75871e48ca..c07e9cc9fc6e 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.h
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.h
@@ -9,6 +9,7 @@
 /* Maximum buffer lengths for all control queue types */
 #define ICE_AQ_MAX_BUF_LEN 4096
 #define ICE_MBXQ_MAX_BUF_LEN 4096
+#define ICE_SBQ_MAX_BUF_LEN 512
 
 #define ICE_CTL_Q_DESC(R, i) \
 	(&(((struct ice_aq_desc *)((R).desc_buf.va))[i]))
@@ -29,6 +30,7 @@ enum ice_ctl_q {
 	ICE_CTL_Q_UNKNOWN = 0,
 	ICE_CTL_Q_ADMIN,
 	ICE_CTL_Q_MAILBOX,
+	ICE_CTL_Q_SB,
 };
 
 /* Control Queue timeout settings - max delay 1s */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index df02cffdf209..857dc62da7a8 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -275,6 +275,7 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked)
 	struct ice_dcbx_cfg *old_cfg, *curr_cfg;
 	struct device *dev = ice_pf_to_dev(pf);
 	int ret = ICE_DCB_NO_HW_CHG;
+	struct iidc_event *event;
 	struct ice_vsi *pf_vsi;
 
 	curr_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
@@ -313,6 +314,15 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked)
 		goto free_cfg;
 	}
 
+	/* Notify AUX drivers about impending change to TCs */
+	event = kzalloc(sizeof(*event), GFP_KERNEL);
+	if (!event)
+		return -ENOMEM;
+
+	set_bit(IIDC_EVENT_BEFORE_TC_CHANGE, event->type);
+	ice_send_event_to_aux(pf, event);
+	kfree(event);
+
 	/* avoid race conditions by holding the lock while disabling and
 	 * re-enabling the VSI
 	 */
@@ -640,6 +650,7 @@ static int ice_dcb_noncontig_cfg(struct ice_pf *pf)
 void ice_pf_dcb_recfg(struct ice_pf *pf)
 {
 	struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
+	struct iidc_event *event;
 	u8 tc_map = 0;
 	int v, ret;
 
@@ -675,6 +686,14 @@ void ice_pf_dcb_recfg(struct ice_pf *pf)
 		if (vsi->type == ICE_VSI_PF)
 			ice_dcbnl_set_all(vsi);
 	}
+	/* Notify the AUX drivers that TC change is finished */
+	event = kzalloc(sizeof(*event), GFP_KERNEL);
+	if (!event)
+		return;
+
+	set_bit(IIDC_EVENT_AFTER_TC_CHANGE, event->type);
+	ice_send_event_to_aux(pf, event);
+	kfree(event);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
index 35c21d9ae009..261b6e2ed7bc 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
@@ -60,7 +60,7 @@ static inline bool ice_is_dcb_active(struct ice_pf *pf)
 		test_bit(ICE_FLAG_DCB_ENA, pf->flags));
 }
 #else
-#define ice_dcb_rebuild(pf) do {} while (0)
+static inline void ice_dcb_rebuild(struct ice_pf *pf) { }
 
 static inline u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg __always_unused *dcbcfg)
 {
@@ -113,11 +113,12 @@ ice_is_pfc_causing_hung_q(struct ice_pf __always_unused *pf,
 	return false;
 }
 
-#define ice_update_dcb_stats(pf) do {} while (0)
-#define ice_pf_dcb_recfg(pf) do {} while (0)
-#define ice_vsi_cfg_dcb_rings(vsi) do {} while (0)
-#define ice_dcb_process_lldp_set_mib_change(pf, event) do {} while (0)
-#define ice_set_cgd_num(tlan_ctx, ring) do {} while (0)
-#define ice_vsi_cfg_netdev_tc(vsi, ena_tc) do {} while (0)
+static inline void ice_pf_dcb_recfg(struct ice_pf *pf) { }
+static inline void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi) { }
+static inline void ice_update_dcb_stats(struct ice_pf *pf) { }
+static inline void
+ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, struct ice_rq_event_info *event) { }
+static inline void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc) { }
+static inline void ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, struct ice_ring *ring) { }
 #endif /* CONFIG_DCB */
 #endif /* _ICE_DCB_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.h b/drivers/net/ethernet/intel/ice/ice_dcb_nl.h
index 6c630a362293..eac2f34bdcdd 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.h
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.h
@@ -11,9 +11,10 @@ void
 ice_dcbnl_flush_apps(struct ice_pf *pf, struct ice_dcbx_cfg *old_cfg,
 		     struct ice_dcbx_cfg *new_cfg);
 #else
-#define ice_dcbnl_setup(vsi) do {} while (0)
-#define ice_dcbnl_set_all(vsi) do {} while (0)
-#define ice_dcbnl_flush_apps(pf, old_cfg, new_cfg) do {} while (0)
+static inline void ice_dcbnl_setup(struct ice_vsi *vsi) { }
+static inline void ice_dcbnl_set_all(struct ice_vsi *vsi) { }
+static inline void
+ice_dcbnl_flush_apps(struct ice_pf *pf, struct ice_dcbx_cfg *old_cfg,
+		     struct ice_dcbx_cfg *new_cfg) { }
 #endif /* CONFIG_DCB */
-
 #endif /* _ICE_DCB_NL_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c
index cf685eeea198..91b545ab8b8f 100644
--- a/drivers/net/ethernet/intel/ice/ice_devlink.c
+++ b/drivers/net/ethernet/intel/ice/ice_devlink.c
@@ -276,6 +276,12 @@ static int ice_devlink_info_get(struct devlink *devlink,
 	size_t i;
 	int err;
 
+	err = ice_wait_for_reset(pf, 10 * HZ);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Device is busy resetting");
+		return err;
+	}
+
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
@@ -283,6 +289,9 @@ static int ice_devlink_info_get(struct devlink *devlink,
 	/* discover capabilities first */
 	status = ice_discover_dev_caps(hw, &ctx->dev_caps);
 	if (status) {
+		dev_dbg(dev, "Failed to discover device capabilities, status %s aq_err %s\n",
+			ice_stat_str(status), ice_aq_str(hw->adminq.sq_last_status));
+		NL_SET_ERR_MSG_MOD(extack, "Unable to discover device capabilities");
 		err = -EIO;
 		goto out_free_ctx;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 99301ad95290..d95a5daca114 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3195,6 +3195,31 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key,
 	return 0;
 }
 
+static int
+ice_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info)
+{
+	struct ice_pf *pf = ice_netdev_to_pf(dev);
+
+	/* only report timestamping if PTP is enabled */
+	if (!test_bit(ICE_FLAG_PTP, pf->flags))
+		return ethtool_op_get_ts_info(dev, info);
+
+	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+				SOF_TIMESTAMPING_RX_SOFTWARE |
+				SOF_TIMESTAMPING_SOFTWARE |
+				SOF_TIMESTAMPING_TX_HARDWARE |
+				SOF_TIMESTAMPING_RX_HARDWARE |
+				SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	info->phc_index = ice_get_ptp_clock_index(pf);
+
+	info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON);
+
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL);
+
+	return 0;
+}
+
 /**
  * ice_get_max_txq - return the maximum number of Tx queues for in a PF
  * @pf: PF structure
@@ -3462,13 +3487,9 @@ static int
 ice_get_rc_coalesce(struct ethtool_coalesce *ec, enum ice_container_type c_type,
 		    struct ice_ring_container *rc)
 {
-	struct ice_pf *pf;
-
 	if (!rc->ring)
 		return -EINVAL;
 
-	pf = rc->ring->vsi->back;
-
 	switch (c_type) {
 	case ICE_RX_CONTAINER:
 		ec->use_adaptive_rx_coalesce = ITR_IS_DYNAMIC(rc);
@@ -3480,7 +3501,7 @@ ice_get_rc_coalesce(struct ethtool_coalesce *ec, enum ice_container_type c_type,
 		ec->tx_coalesce_usecs = rc->itr_setting;
 		break;
 	default:
-		dev_dbg(ice_pf_to_dev(pf), "Invalid c_type %d\n", c_type);
+		dev_dbg(ice_pf_to_dev(rc->ring->vsi->back), "Invalid c_type %d\n", c_type);
 		return -EINVAL;
 	}
 
@@ -3990,7 +4011,7 @@ static const struct ethtool_ops ice_ethtool_ops = {
 	.set_rxfh		= ice_set_rxfh,
 	.get_channels		= ice_get_channels,
 	.set_channels		= ice_set_channels,
-	.get_ts_info		= ethtool_op_get_ts_info,
+	.get_ts_info		= ice_get_ts_info,
 	.get_per_queue_coalesce	= ice_get_per_q_coalesce,
 	.set_per_queue_coalesce	= ice_set_per_q_coalesce,
 	.get_fecparam		= ice_get_fecparam,
diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c
index dcec0360ce55..f8601d5b0b19 100644
--- a/drivers/net/ethernet/intel/ice/ice_fw_update.c
+++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c
@@ -702,6 +702,16 @@ int ice_flash_pldm_image(struct ice_pf *pf, const struct firmware *fw,
 	}
 
 	err = pldmfw_flash_image(&priv.context, fw);
+	if (err == -ENOENT) {
+		dev_err(dev, "Firmware image has no record matching this device\n");
+		NL_SET_ERR_MSG_MOD(extack, "Firmware image has no record matching this device");
+	} else if (err) {
+		/* Do not set a generic extended ACK message here. A more
+		 * specific message may already have been set by one of our
+		 * ops.
+		 */
+		dev_err(dev, "Failed to flash PLDM image, err %d", err);
+	}
 
 	ice_release_nvm(hw);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 9b8300d4a267..6989a76c42a7 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -52,6 +52,54 @@
 #define PF_MBX_ATQLEN_ATQCRIT_M			BIT(30)
 #define PF_MBX_ATQLEN_ATQENABLE_M		BIT(31)
 #define PF_MBX_ATQT				0x0022E300
+#define PF_SB_ARQBAH				0x0022FF00
+#define PF_SB_ARQBAH_ARQBAH_S			0
+#define PF_SB_ARQBAH_ARQBAH_M			ICE_M(0xFFFFFFFF, 0)
+#define PF_SB_ARQBAL				0x0022FE80
+#define PF_SB_ARQBAL_ARQBAL_LSB_S		0
+#define PF_SB_ARQBAL_ARQBAL_LSB_M		ICE_M(0x3F, 0)
+#define PF_SB_ARQBAL_ARQBAL_S			6
+#define PF_SB_ARQBAL_ARQBAL_M			ICE_M(0x3FFFFFF, 6)
+#define PF_SB_ARQH				0x00230000
+#define PF_SB_ARQH_ARQH_S			0
+#define PF_SB_ARQH_ARQH_M			ICE_M(0x3FF, 0)
+#define PF_SB_ARQLEN				0x0022FF80
+#define PF_SB_ARQLEN_ARQLEN_S			0
+#define PF_SB_ARQLEN_ARQLEN_M			ICE_M(0x3FF, 0)
+#define PF_SB_ARQLEN_ARQVFE_S			28
+#define PF_SB_ARQLEN_ARQVFE_M			BIT(28)
+#define PF_SB_ARQLEN_ARQOVFL_S			29
+#define PF_SB_ARQLEN_ARQOVFL_M			BIT(29)
+#define PF_SB_ARQLEN_ARQCRIT_S			30
+#define PF_SB_ARQLEN_ARQCRIT_M			BIT(30)
+#define PF_SB_ARQLEN_ARQENABLE_S		31
+#define PF_SB_ARQLEN_ARQENABLE_M		BIT(31)
+#define PF_SB_ARQT				0x00230080
+#define PF_SB_ARQT_ARQT_S			0
+#define PF_SB_ARQT_ARQT_M			ICE_M(0x3FF, 0)
+#define PF_SB_ATQBAH				0x0022FC80
+#define PF_SB_ATQBAH_ATQBAH_S			0
+#define PF_SB_ATQBAH_ATQBAH_M			ICE_M(0xFFFFFFFF, 0)
+#define PF_SB_ATQBAL				0x0022FC00
+#define PF_SB_ATQBAL_ATQBAL_S			6
+#define PF_SB_ATQBAL_ATQBAL_M			ICE_M(0x3FFFFFF, 6)
+#define PF_SB_ATQH				0x0022FD80
+#define PF_SB_ATQH_ATQH_S			0
+#define PF_SB_ATQH_ATQH_M			ICE_M(0x3FF, 0)
+#define PF_SB_ATQLEN				0x0022FD00
+#define PF_SB_ATQLEN_ATQLEN_S			0
+#define PF_SB_ATQLEN_ATQLEN_M			ICE_M(0x3FF, 0)
+#define PF_SB_ATQLEN_ATQVFE_S			28
+#define PF_SB_ATQLEN_ATQVFE_M			BIT(28)
+#define PF_SB_ATQLEN_ATQOVFL_S			29
+#define PF_SB_ATQLEN_ATQOVFL_M			BIT(29)
+#define PF_SB_ATQLEN_ATQCRIT_S			30
+#define PF_SB_ATQLEN_ATQCRIT_M			BIT(30)
+#define PF_SB_ATQLEN_ATQENABLE_S		31
+#define PF_SB_ATQLEN_ATQENABLE_M		BIT(31)
+#define PF_SB_ATQT				0x0022FE00
+#define PF_SB_ATQT_ATQT_S			0
+#define PF_SB_ATQT_ATQT_M			ICE_M(0x3FF, 0)
 #define PRTDCB_GENC				0x00083000
 #define PRTDCB_GENC_PFCLDA_S			16
 #define PRTDCB_GENC_PFCLDA_M			ICE_M(0xFFFF, 16)
@@ -111,8 +159,6 @@
 #define VPGEN_VFRSTAT_VFRD_M			BIT(0)
 #define VPGEN_VFRTRIG(_VF)			(0x00090000 + ((_VF) * 4))
 #define VPGEN_VFRTRIG_VFSWR_M			BIT(0)
-#define PFHMC_ERRORDATA				0x00520500
-#define PFHMC_ERRORINFO				0x00520400
 #define GLINT_CTL				0x0016CC54
 #define GLINT_CTL_DIS_AUTOMASK_M		BIT(0)
 #define GLINT_CTL_ITR_GRAN_200_S		16
@@ -156,11 +202,13 @@
 #define PFINT_MBX_CTL_ITR_INDX_M		ICE_M(0x3, 11)
 #define PFINT_MBX_CTL_CAUSE_ENA_M		BIT(30)
 #define PFINT_OICR				0x0016CA00
+#define PFINT_OICR_TSYN_TX_M			BIT(11)
 #define PFINT_OICR_ECC_ERR_M			BIT(16)
 #define PFINT_OICR_MAL_DETECT_M			BIT(19)
 #define PFINT_OICR_GRST_M			BIT(20)
 #define PFINT_OICR_PCI_EXCEPTION_M		BIT(21)
 #define PFINT_OICR_HMC_ERR_M			BIT(26)
+#define PFINT_OICR_PE_PUSH_M			BIT(27)
 #define PFINT_OICR_PE_CRITERR_M			BIT(28)
 #define PFINT_OICR_VFLR_M			BIT(29)
 #define PFINT_OICR_SWINT_M			BIT(31)
@@ -170,6 +218,9 @@
 #define PFINT_OICR_CTL_ITR_INDX_M		ICE_M(0x3, 11)
 #define PFINT_OICR_CTL_CAUSE_ENA_M		BIT(30)
 #define PFINT_OICR_ENA				0x0016C900
+#define PFINT_SB_CTL				0x0016B600
+#define PFINT_SB_CTL_MSIX_INDX_M		ICE_M(0x7FF, 0)
+#define PFINT_SB_CTL_CAUSE_ENA_M		BIT(30)
 #define QINT_RQCTL(_QRX)			(0x00150000 + ((_QRX) * 4))
 #define QINT_RQCTL_MSIX_INDX_S			0
 #define QINT_RQCTL_MSIX_INDX_M			ICE_M(0x7FF, 0)
@@ -383,6 +434,23 @@
 #define GLV_UPRCL(_i)				(0x003B2000 + ((_i) * 8))
 #define GLV_UPTCL(_i)				(0x0030A000 + ((_i) * 8))
 #define PRTRPB_RDPC				0x000AC260
+#define GLTSYN_CMD				0x00088810
+#define GLTSYN_CMD_SYNC				0x00088814
+#define GLTSYN_ENA(_i)				(0x00088808 + ((_i) * 4))
+#define GLTSYN_ENA_TSYN_ENA_M			BIT(0)
+#define GLTSYN_INCVAL_H(_i)			(0x00088920 + ((_i) * 4))
+#define GLTSYN_INCVAL_L(_i)			(0x00088918 + ((_i) * 4))
+#define GLTSYN_SHADJ_H(_i)			(0x00088910 + ((_i) * 4))
+#define GLTSYN_SHADJ_L(_i)			(0x00088908 + ((_i) * 4))
+#define GLTSYN_SHTIME_0(_i)			(0x000888E0 + ((_i) * 4))
+#define GLTSYN_SHTIME_H(_i)			(0x000888F0 + ((_i) * 4))
+#define GLTSYN_SHTIME_L(_i)			(0x000888E8 + ((_i) * 4))
+#define GLTSYN_STAT(_i)				(0x000888C0 + ((_i) * 4))
+#define GLTSYN_SYNC_DLAY			0x00088818
+#define GLTSYN_TIME_H(_i)			(0x000888D8 + ((_i) * 4))
+#define GLTSYN_TIME_L(_i)			(0x000888D0 + ((_i) * 4))
+#define PFTSYN_SEM				0x00088880
+#define PFTSYN_SEM_BUSY_M			BIT(0)
 #define VSIQF_FD_CNT(_VSI)			(0x00464000 + ((_VSI) * 4))
 #define VSIQF_FD_CNT_FD_GCNT_S			0
 #define VSIQF_FD_CNT_FD_GCNT_M			ICE_M(0x3FFF, 0)
diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c
new file mode 100644
index 000000000000..1f2afdf6cd48
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_idc.c
@@ -0,0 +1,334 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021, Intel Corporation. */
+
+/* Inter-Driver Communication */
+#include "ice.h"
+#include "ice_lib.h"
+#include "ice_dcb_lib.h"
+
+/**
+ * ice_get_auxiliary_drv - retrieve iidc_auxiliary_drv struct
+ * @pf: pointer to PF struct
+ *
+ * This function has to be called with a device_lock on the
+ * pf->adev.dev to avoid race conditions.
+ */
+static struct iidc_auxiliary_drv *ice_get_auxiliary_drv(struct ice_pf *pf)
+{
+	struct auxiliary_device *adev;
+
+	adev = pf->adev;
+	if (!adev || !adev->dev.driver)
+		return NULL;
+
+	return container_of(adev->dev.driver, struct iidc_auxiliary_drv,
+			    adrv.driver);
+}
+
+/**
+ * ice_send_event_to_aux - send event to RDMA AUX driver
+ * @pf: pointer to PF struct
+ * @event: event struct
+ */
+void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event)
+{
+	struct iidc_auxiliary_drv *iadrv;
+
+	if (!pf->adev)
+		return;
+
+	device_lock(&pf->adev->dev);
+	iadrv = ice_get_auxiliary_drv(pf);
+	if (iadrv && iadrv->event_handler)
+		iadrv->event_handler(pf, event);
+	device_unlock(&pf->adev->dev);
+}
+
+/**
+ * ice_find_vsi - Find the VSI from VSI ID
+ * @pf: The PF pointer to search in
+ * @vsi_num: The VSI ID to search for
+ */
+static struct ice_vsi *ice_find_vsi(struct ice_pf *pf, u16 vsi_num)
+{
+	int i;
+
+	ice_for_each_vsi(pf, i)
+		if (pf->vsi[i] && pf->vsi[i]->vsi_num == vsi_num)
+			return  pf->vsi[i];
+	return NULL;
+}
+
+/**
+ * ice_add_rdma_qset - Add Leaf Node for RDMA Qset
+ * @pf: PF struct
+ * @qset: Resource to be allocated
+ */
+int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset)
+{
+	u16 max_rdmaqs[ICE_MAX_TRAFFIC_CLASS];
+	struct ice_vsi *vsi;
+	struct device *dev;
+	u32 qset_teid;
+	u16 qs_handle;
+	int status;
+	int i;
+
+	if (WARN_ON(!pf || !qset))
+		return -EINVAL;
+
+	dev = ice_pf_to_dev(pf);
+
+	if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags))
+		return -EINVAL;
+
+	vsi = ice_get_main_vsi(pf);
+	if (!vsi) {
+		dev_err(dev, "RDMA QSet invalid VSI\n");
+		return -EINVAL;
+	}
+
+	ice_for_each_traffic_class(i)
+		max_rdmaqs[i] = 0;
+
+	max_rdmaqs[qset->tc]++;
+	qs_handle = qset->qs_handle;
+
+	status = ice_cfg_vsi_rdma(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
+				  max_rdmaqs);
+	if (status) {
+		dev_err(dev, "Failed VSI RDMA Qset config\n");
+		return status;
+	}
+
+	status = ice_ena_vsi_rdma_qset(vsi->port_info, vsi->idx, qset->tc,
+				       &qs_handle, 1, &qset_teid);
+	if (status) {
+		dev_err(dev, "Failed VSI RDMA Qset enable\n");
+		return status;
+	}
+	vsi->qset_handle[qset->tc] = qset->qs_handle;
+	qset->teid = qset_teid;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ice_add_rdma_qset);
+
+/**
+ * ice_del_rdma_qset - Delete leaf node for RDMA Qset
+ * @pf: PF struct
+ * @qset: Resource to be freed
+ */
+int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset)
+{
+	struct ice_vsi *vsi;
+	u32 teid;
+	u16 q_id;
+
+	if (WARN_ON(!pf || !qset))
+		return -EINVAL;
+
+	vsi = ice_find_vsi(pf, qset->vport_id);
+	if (!vsi) {
+		dev_err(ice_pf_to_dev(pf), "RDMA Invalid VSI\n");
+		return -EINVAL;
+	}
+
+	q_id = qset->qs_handle;
+	teid = qset->teid;
+
+	vsi->qset_handle[qset->tc] = 0;
+
+	return ice_dis_vsi_rdma_qset(vsi->port_info, 1, &teid, &q_id);
+}
+EXPORT_SYMBOL_GPL(ice_del_rdma_qset);
+
+/**
+ * ice_rdma_request_reset - accept request from RDMA to perform a reset
+ * @pf: struct for PF
+ * @reset_type: type of reset
+ */
+int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type)
+{
+	enum ice_reset_req reset;
+
+	if (WARN_ON(!pf))
+		return -EINVAL;
+
+	switch (reset_type) {
+	case IIDC_PFR:
+		reset = ICE_RESET_PFR;
+		break;
+	case IIDC_CORER:
+		reset = ICE_RESET_CORER;
+		break;
+	case IIDC_GLOBR:
+		reset = ICE_RESET_GLOBR;
+		break;
+	default:
+		dev_err(ice_pf_to_dev(pf), "incorrect reset request\n");
+		return -EINVAL;
+	}
+
+	return ice_schedule_reset(pf, reset);
+}
+EXPORT_SYMBOL_GPL(ice_rdma_request_reset);
+
+/**
+ * ice_rdma_update_vsi_filter - update main VSI filters for RDMA
+ * @pf: pointer to struct for PF
+ * @vsi_id: VSI HW idx to update filter on
+ * @enable: bool whether to enable or disable filters
+ */
+int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable)
+{
+	struct ice_vsi *vsi;
+	int status;
+
+	if (WARN_ON(!pf))
+		return -EINVAL;
+
+	vsi = ice_find_vsi(pf, vsi_id);
+	if (!vsi)
+		return -EINVAL;
+
+	status = ice_cfg_rdma_fltr(&pf->hw, vsi->idx, enable);
+	if (status) {
+		dev_err(ice_pf_to_dev(pf), "Failed to  %sable RDMA filtering\n",
+			enable ? "en" : "dis");
+	} else {
+		if (enable)
+			vsi->info.q_opt_flags |= ICE_AQ_VSI_Q_OPT_PE_FLTR_EN;
+		else
+			vsi->info.q_opt_flags &= ~ICE_AQ_VSI_Q_OPT_PE_FLTR_EN;
+	}
+
+	return status;
+}
+EXPORT_SYMBOL_GPL(ice_rdma_update_vsi_filter);
+
+/**
+ * ice_get_qos_params - parse QoS params for RDMA consumption
+ * @pf: pointer to PF struct
+ * @qos: set of QoS values
+ */
+void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos)
+{
+	struct ice_dcbx_cfg *dcbx_cfg;
+	unsigned int i;
+	u32 up2tc;
+
+	dcbx_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
+	up2tc = rd32(&pf->hw, PRTDCB_TUP2TC);
+
+	qos->num_tc = ice_dcb_get_num_tc(dcbx_cfg);
+	for (i = 0; i < IIDC_MAX_USER_PRIORITY; i++)
+		qos->up2tc[i] = (up2tc >> (i * 3)) & 0x7;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		qos->tc_info[i].rel_bw = dcbx_cfg->etscfg.tcbwtable[i];
+}
+EXPORT_SYMBOL_GPL(ice_get_qos_params);
+
+/**
+ * ice_reserve_rdma_qvector - Reserve vector resources for RDMA driver
+ * @pf: board private structure to initialize
+ */
+static int ice_reserve_rdma_qvector(struct ice_pf *pf)
+{
+	if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) {
+		int index;
+
+		index = ice_get_res(pf, pf->irq_tracker, pf->num_rdma_msix,
+				    ICE_RES_RDMA_VEC_ID);
+		if (index < 0)
+			return index;
+		pf->num_avail_sw_msix -= pf->num_rdma_msix;
+		pf->rdma_base_vector = (u16)index;
+	}
+	return 0;
+}
+
+/**
+ * ice_adev_release - function to be mapped to AUX dev's release op
+ * @dev: pointer to device to free
+ */
+static void ice_adev_release(struct device *dev)
+{
+	struct iidc_auxiliary_dev *iadev;
+
+	iadev = container_of(dev, struct iidc_auxiliary_dev, adev.dev);
+	kfree(iadev);
+}
+
+/**
+ * ice_plug_aux_dev - allocate and register AUX device
+ * @pf: pointer to pf struct
+ */
+int ice_plug_aux_dev(struct ice_pf *pf)
+{
+	struct iidc_auxiliary_dev *iadev;
+	struct auxiliary_device *adev;
+	int ret;
+
+	iadev = kzalloc(sizeof(*iadev), GFP_KERNEL);
+	if (!iadev)
+		return -ENOMEM;
+
+	adev = &iadev->adev;
+	pf->adev = adev;
+	iadev->pf = pf;
+
+	adev->id = pf->aux_idx;
+	adev->dev.release = ice_adev_release;
+	adev->dev.parent = &pf->pdev->dev;
+	adev->name = IIDC_RDMA_ROCE_NAME;
+
+	ret = auxiliary_device_init(adev);
+	if (ret) {
+		pf->adev = NULL;
+		kfree(iadev);
+		return ret;
+	}
+
+	ret = auxiliary_device_add(adev);
+	if (ret) {
+		pf->adev = NULL;
+		auxiliary_device_uninit(adev);
+		return ret;
+	}
+
+	return 0;
+}
+
+/* ice_unplug_aux_dev - unregister and free AUX device
+ * @pf: pointer to pf struct
+ */
+void ice_unplug_aux_dev(struct ice_pf *pf)
+{
+	if (!pf->adev)
+		return;
+
+	auxiliary_device_delete(pf->adev);
+	auxiliary_device_uninit(pf->adev);
+	pf->adev = NULL;
+}
+
+/**
+ * ice_init_rdma - initializes PF for RDMA use
+ * @pf: ptr to ice_pf
+ */
+int ice_init_rdma(struct ice_pf *pf)
+{
+	struct device *dev = &pf->pdev->dev;
+	int ret;
+
+	/* Reserve vector resources */
+	ret = ice_reserve_rdma_qvector(pf);
+	if (ret < 0) {
+		dev_err(dev, "failed to reserve vectors for RDMA\n");
+		return ret;
+	}
+
+	return ice_plug_aux_dev(pf);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_idc_int.h b/drivers/net/ethernet/intel/ice/ice_idc_int.h
new file mode 100644
index 000000000000..b7796b8aecbd
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_idc_int.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2021, Intel Corporation. */
+
+#ifndef _ICE_IDC_INT_H_
+#define _ICE_IDC_INT_H_
+
+#include <linux/net/intel/iidc.h>
+#include "ice.h"
+
+struct ice_pf;
+
+void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event);
+
+#endif /* !_ICE_IDC_INT_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 4599fc3b4ed8..37c18c66b5c7 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -172,6 +172,7 @@ ice_lag_link(struct ice_lag *lag, struct netdev_notifier_changeupper_info *info)
 	}
 
 	ice_clear_sriov_cap(pf);
+	ice_clear_rdma_cap(pf);
 
 	lag->bonded = true;
 	lag->role = ICE_LAG_UNSET;
@@ -222,6 +223,7 @@ ice_lag_unlink(struct ice_lag *lag,
 	}
 
 	ice_set_sriov_cap(pf);
+	ice_set_rdma_cap(pf);
 	lag->bonded = false;
 	lag->role = ICE_LAG_NONE;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index 21329ed3087e..80736e0ec0dc 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -161,7 +161,6 @@ struct ice_fltr_desc {
 #define ICE_FXD_FLTR_WB_QW1_FAIL_PROF_YES	0x1ULL
 
 struct ice_rx_ptype_decoded {
-	u32 ptype:10;
 	u32 known:1;
 	u32 outer_ip:1;
 	u32 outer_ip_ver:2;
@@ -606,9 +605,32 @@ struct ice_tlan_ctx {
 	u8 int_q_state;	/* width not needed - internal - DO NOT WRITE!!! */
 };
 
-/* macro to make the table lines short */
+/* The ice_ptype_lkup table is used to convert from the 10-bit ptype in the
+ * hardware to a bit-field that can be used by SW to more easily determine the
+ * packet type.
+ *
+ * Macros are used to shorten the table lines and make this table human
+ * readable.
+ *
+ * We store the PTYPE in the top byte of the bit field - this is just so that
+ * we can check that the table doesn't have a row missing, as the index into
+ * the table should be the PTYPE.
+ *
+ * Typical work flow:
+ *
+ * IF NOT ice_ptype_lkup[ptype].known
+ * THEN
+ *      Packet is unknown
+ * ELSE IF ice_ptype_lkup[ptype].outer_ip == ICE_RX_PTYPE_OUTER_IP
+ *      Use the rest of the fields to look at the tunnels, inner protocols, etc
+ * ELSE
+ *      Use the enum ice_rx_l2_ptype to decode the packet type
+ * ENDIF
+ */
+
+/* macro to make the table lines short, use explicit indexing with [PTYPE] */
 #define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
-	{	PTYPE, \
+	[PTYPE] = { \
 		1, \
 		ICE_RX_PTYPE_OUTER_##OUTER_IP, \
 		ICE_RX_PTYPE_OUTER_##OUTER_IP_VER, \
@@ -619,18 +641,18 @@ struct ice_tlan_ctx {
 		ICE_RX_PTYPE_INNER_PROT_##I, \
 		ICE_RX_PTYPE_PAYLOAD_LAYER_##PL }
 
-#define ICE_PTT_UNUSED_ENTRY(PTYPE) { PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 }
+#define ICE_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
 
 /* shorter macros makes the table fit but are terse */
 #define ICE_RX_PTYPE_NOF		ICE_RX_PTYPE_NOT_FRAG
 #define ICE_RX_PTYPE_FRG		ICE_RX_PTYPE_FRAG
 
-/* Lookup table mapping the HW PTYPE to the bit field for decoding */
-static const struct ice_rx_ptype_decoded ice_ptype_lkup[] = {
+/* Lookup table mapping in the 10-bit HW PTYPE to the bit field for decoding */
+static const struct ice_rx_ptype_decoded ice_ptype_lkup[BIT(10)] = {
 	/* L2 Packet types */
 	ICE_PTT_UNUSED_ENTRY(0),
 	ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
-	ICE_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
+	ICE_PTT_UNUSED_ENTRY(2),
 	ICE_PTT_UNUSED_ENTRY(3),
 	ICE_PTT_UNUSED_ENTRY(4),
 	ICE_PTT_UNUSED_ENTRY(5),
@@ -744,7 +766,7 @@ static const struct ice_rx_ptype_decoded ice_ptype_lkup[] = {
 	/* Non Tunneled IPv6 */
 	ICE_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3),
 	ICE_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP,  PAY3),
+	ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP,  PAY4),
 	ICE_PTT_UNUSED_ENTRY(91),
 	ICE_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP,  PAY4),
 	ICE_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4),
@@ -832,118 +854,7 @@ static const struct ice_rx_ptype_decoded ice_ptype_lkup[] = {
 	ICE_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
 
 	/* unused entries */
-	ICE_PTT_UNUSED_ENTRY(154),
-	ICE_PTT_UNUSED_ENTRY(155),
-	ICE_PTT_UNUSED_ENTRY(156),
-	ICE_PTT_UNUSED_ENTRY(157),
-	ICE_PTT_UNUSED_ENTRY(158),
-	ICE_PTT_UNUSED_ENTRY(159),
-
-	ICE_PTT_UNUSED_ENTRY(160),
-	ICE_PTT_UNUSED_ENTRY(161),
-	ICE_PTT_UNUSED_ENTRY(162),
-	ICE_PTT_UNUSED_ENTRY(163),
-	ICE_PTT_UNUSED_ENTRY(164),
-	ICE_PTT_UNUSED_ENTRY(165),
-	ICE_PTT_UNUSED_ENTRY(166),
-	ICE_PTT_UNUSED_ENTRY(167),
-	ICE_PTT_UNUSED_ENTRY(168),
-	ICE_PTT_UNUSED_ENTRY(169),
-
-	ICE_PTT_UNUSED_ENTRY(170),
-	ICE_PTT_UNUSED_ENTRY(171),
-	ICE_PTT_UNUSED_ENTRY(172),
-	ICE_PTT_UNUSED_ENTRY(173),
-	ICE_PTT_UNUSED_ENTRY(174),
-	ICE_PTT_UNUSED_ENTRY(175),
-	ICE_PTT_UNUSED_ENTRY(176),
-	ICE_PTT_UNUSED_ENTRY(177),
-	ICE_PTT_UNUSED_ENTRY(178),
-	ICE_PTT_UNUSED_ENTRY(179),
-
-	ICE_PTT_UNUSED_ENTRY(180),
-	ICE_PTT_UNUSED_ENTRY(181),
-	ICE_PTT_UNUSED_ENTRY(182),
-	ICE_PTT_UNUSED_ENTRY(183),
-	ICE_PTT_UNUSED_ENTRY(184),
-	ICE_PTT_UNUSED_ENTRY(185),
-	ICE_PTT_UNUSED_ENTRY(186),
-	ICE_PTT_UNUSED_ENTRY(187),
-	ICE_PTT_UNUSED_ENTRY(188),
-	ICE_PTT_UNUSED_ENTRY(189),
-
-	ICE_PTT_UNUSED_ENTRY(190),
-	ICE_PTT_UNUSED_ENTRY(191),
-	ICE_PTT_UNUSED_ENTRY(192),
-	ICE_PTT_UNUSED_ENTRY(193),
-	ICE_PTT_UNUSED_ENTRY(194),
-	ICE_PTT_UNUSED_ENTRY(195),
-	ICE_PTT_UNUSED_ENTRY(196),
-	ICE_PTT_UNUSED_ENTRY(197),
-	ICE_PTT_UNUSED_ENTRY(198),
-	ICE_PTT_UNUSED_ENTRY(199),
-
-	ICE_PTT_UNUSED_ENTRY(200),
-	ICE_PTT_UNUSED_ENTRY(201),
-	ICE_PTT_UNUSED_ENTRY(202),
-	ICE_PTT_UNUSED_ENTRY(203),
-	ICE_PTT_UNUSED_ENTRY(204),
-	ICE_PTT_UNUSED_ENTRY(205),
-	ICE_PTT_UNUSED_ENTRY(206),
-	ICE_PTT_UNUSED_ENTRY(207),
-	ICE_PTT_UNUSED_ENTRY(208),
-	ICE_PTT_UNUSED_ENTRY(209),
-
-	ICE_PTT_UNUSED_ENTRY(210),
-	ICE_PTT_UNUSED_ENTRY(211),
-	ICE_PTT_UNUSED_ENTRY(212),
-	ICE_PTT_UNUSED_ENTRY(213),
-	ICE_PTT_UNUSED_ENTRY(214),
-	ICE_PTT_UNUSED_ENTRY(215),
-	ICE_PTT_UNUSED_ENTRY(216),
-	ICE_PTT_UNUSED_ENTRY(217),
-	ICE_PTT_UNUSED_ENTRY(218),
-	ICE_PTT_UNUSED_ENTRY(219),
-
-	ICE_PTT_UNUSED_ENTRY(220),
-	ICE_PTT_UNUSED_ENTRY(221),
-	ICE_PTT_UNUSED_ENTRY(222),
-	ICE_PTT_UNUSED_ENTRY(223),
-	ICE_PTT_UNUSED_ENTRY(224),
-	ICE_PTT_UNUSED_ENTRY(225),
-	ICE_PTT_UNUSED_ENTRY(226),
-	ICE_PTT_UNUSED_ENTRY(227),
-	ICE_PTT_UNUSED_ENTRY(228),
-	ICE_PTT_UNUSED_ENTRY(229),
-
-	ICE_PTT_UNUSED_ENTRY(230),
-	ICE_PTT_UNUSED_ENTRY(231),
-	ICE_PTT_UNUSED_ENTRY(232),
-	ICE_PTT_UNUSED_ENTRY(233),
-	ICE_PTT_UNUSED_ENTRY(234),
-	ICE_PTT_UNUSED_ENTRY(235),
-	ICE_PTT_UNUSED_ENTRY(236),
-	ICE_PTT_UNUSED_ENTRY(237),
-	ICE_PTT_UNUSED_ENTRY(238),
-	ICE_PTT_UNUSED_ENTRY(239),
-
-	ICE_PTT_UNUSED_ENTRY(240),
-	ICE_PTT_UNUSED_ENTRY(241),
-	ICE_PTT_UNUSED_ENTRY(242),
-	ICE_PTT_UNUSED_ENTRY(243),
-	ICE_PTT_UNUSED_ENTRY(244),
-	ICE_PTT_UNUSED_ENTRY(245),
-	ICE_PTT_UNUSED_ENTRY(246),
-	ICE_PTT_UNUSED_ENTRY(247),
-	ICE_PTT_UNUSED_ENTRY(248),
-	ICE_PTT_UNUSED_ENTRY(249),
-
-	ICE_PTT_UNUSED_ENTRY(250),
-	ICE_PTT_UNUSED_ENTRY(251),
-	ICE_PTT_UNUSED_ENTRY(252),
-	ICE_PTT_UNUSED_ENTRY(253),
-	ICE_PTT_UNUSED_ENTRY(254),
-	ICE_PTT_UNUSED_ENTRY(255),
+	[154 ... 1023] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
 };
 
 static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype)
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 27f9dac8719c..dde9802c6c72 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -169,12 +169,13 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id)
 
 	switch (vsi->type) {
 	case ICE_VSI_PF:
-		vsi->alloc_txq = min3(pf->num_lan_msix,
-				      ice_get_avail_txq_count(pf),
-				      (u16)num_online_cpus());
 		if (vsi->req_txq) {
 			vsi->alloc_txq = vsi->req_txq;
 			vsi->num_txq = vsi->req_txq;
+		} else {
+			vsi->alloc_txq = min3(pf->num_lan_msix,
+					      ice_get_avail_txq_count(pf),
+					      (u16)num_online_cpus());
 		}
 
 		pf->num_lan_tx = vsi->alloc_txq;
@@ -183,12 +184,13 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id)
 		if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
 			vsi->alloc_rxq = 1;
 		} else {
-			vsi->alloc_rxq = min3(pf->num_lan_msix,
-					      ice_get_avail_rxq_count(pf),
-					      (u16)num_online_cpus());
 			if (vsi->req_rxq) {
 				vsi->alloc_rxq = vsi->req_rxq;
 				vsi->num_rxq = vsi->req_rxq;
+			} else {
+				vsi->alloc_rxq = min3(pf->num_lan_msix,
+						      ice_get_avail_rxq_count(pf),
+						      (u16)num_online_cpus());
 			}
 		}
 
@@ -629,6 +631,17 @@ bool ice_is_safe_mode(struct ice_pf *pf)
 }
 
 /**
+ * ice_is_aux_ena
+ * @pf: pointer to the PF struct
+ *
+ * returns true if AUX devices/drivers are supported, false otherwise
+ */
+bool ice_is_aux_ena(struct ice_pf *pf)
+{
+	return test_bit(ICE_FLAG_AUX_ENA, pf->flags);
+}
+
+/**
  * ice_vsi_clean_rss_flow_fld - Delete RSS configuration
  * @vsi: the VSI being cleaned up
  *
@@ -1192,11 +1205,11 @@ static int ice_vsi_setup_vector_base(struct ice_vsi *vsi)
 	num_q_vectors = vsi->num_q_vectors;
 	/* reserve slots from OS requested IRQs */
 	if (vsi->type == ICE_VSI_CTRL && vsi->vf_id != ICE_INVAL_VFID) {
-		struct ice_vf *vf;
 		int i;
 
 		ice_for_each_vf(pf, i) {
-			vf = &pf->vf[i];
+			struct ice_vf *vf = &pf->vf[i];
+
 			if (i != vsi->vf_id && vf->ctrl_vsi_idx != ICE_NO_VSI) {
 				base = pf->vsi[vf->ctrl_vsi_idx]->base_vector;
 				break;
@@ -1285,6 +1298,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
 		ring->reg_idx = vsi->txq_map[i];
 		ring->ring_active = false;
 		ring->vsi = vsi;
+		ring->tx_tstamps = &pf->ptp.port.tx;
 		ring->dev = dev;
 		ring->count = vsi->num_tx_desc;
 		WRITE_ONCE(vsi->tx_rings[i], ring);
@@ -1662,9 +1676,11 @@ void ice_vsi_cfg_frame_size(struct ice_vsi *vsi)
  * @pf_q: index of the Rx queue in the PF's queue space
  * @rxdid: flexible descriptor RXDID
  * @prio: priority for the RXDID for this queue
+ * @ena_ts: true to enable timestamp and false to disable timestamp
  */
 void
-ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio)
+ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio,
+			bool ena_ts)
 {
 	int regval = rd32(hw, QRXFLXP_CNTXT(pf_q));
 
@@ -1679,9 +1695,40 @@ ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio)
 	regval |= (prio << QRXFLXP_CNTXT_RXDID_PRIO_S) &
 		QRXFLXP_CNTXT_RXDID_PRIO_M;
 
+	if (ena_ts)
+		/* Enable TimeSync on this queue */
+		regval |= QRXFLXP_CNTXT_TS_M;
+
 	wr32(hw, QRXFLXP_CNTXT(pf_q), regval);
 }
 
+int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx)
+{
+	if (q_idx >= vsi->num_rxq)
+		return -EINVAL;
+
+	return ice_vsi_cfg_rxq(vsi->rx_rings[q_idx]);
+}
+
+int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_ring **tx_rings, u16 q_idx)
+{
+	struct ice_aqc_add_tx_qgrp *qg_buf;
+	int err;
+
+	if (q_idx >= vsi->alloc_txq || !tx_rings || !tx_rings[q_idx])
+		return -EINVAL;
+
+	qg_buf = kzalloc(struct_size(qg_buf, txqs, 1), GFP_KERNEL);
+	if (!qg_buf)
+		return -ENOMEM;
+
+	qg_buf->num_txqs = 1;
+
+	err = ice_vsi_cfg_txq(vsi, tx_rings[q_idx], qg_buf);
+	kfree(qg_buf);
+	return err;
+}
+
 /**
  * ice_vsi_cfg_rxqs - Configure the VSI for Rx
  * @vsi: the VSI being configured
@@ -1699,15 +1746,11 @@ int ice_vsi_cfg_rxqs(struct ice_vsi *vsi)
 	ice_vsi_cfg_frame_size(vsi);
 setup_rings:
 	/* set up individual rings */
-	for (i = 0; i < vsi->num_rxq; i++) {
-		int err;
+	ice_for_each_rxq(vsi, i) {
+		int err = ice_vsi_cfg_rxq(vsi->rx_rings[i]);
 
-		err = ice_setup_rx_ctx(vsi->rx_rings[i]);
-		if (err) {
-			dev_err(ice_pf_to_dev(vsi->back), "ice_setup_rx_ctx failed for RxQ %d, err %d\n",
-				i, err);
+		if (err)
 			return err;
-		}
 	}
 
 	return 0;
@@ -2217,7 +2260,7 @@ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create)
 	}
 
 	if (status)
-		dev_err(dev, "Fail %s %s LLDP rule on VSI %i error: %s\n",
+		dev_dbg(dev, "Fail %s %s LLDP rule on VSI %i error: %s\n",
 			create ? "adding" : "removing", tx ? "TX" : "RX",
 			vsi->vsi_num, ice_stat_str(status));
 }
@@ -2832,11 +2875,11 @@ int ice_vsi_release(struct ice_vsi *vsi)
 	 * cleared in the same manner.
 	 */
 	if (vsi->type == ICE_VSI_CTRL && vsi->vf_id != ICE_INVAL_VFID) {
-		struct ice_vf *vf;
 		int i;
 
 		ice_for_each_vf(pf, i) {
-			vf = &pf->vf[i];
+			struct ice_vf *vf = &pf->vf[i];
+
 			if (i != vsi->vf_id && vf->ctrl_vsi_idx != ICE_NO_VSI)
 				break;
 		}
@@ -3196,6 +3239,34 @@ bool ice_is_reset_in_progress(unsigned long *state)
 	       test_bit(ICE_GLOBR_REQ, state);
 }
 
+/**
+ * ice_wait_for_reset - Wait for driver to finish reset and rebuild
+ * @pf: pointer to the PF structure
+ * @timeout: length of time to wait, in jiffies
+ *
+ * Wait (sleep) for a short time until the driver finishes cleaning up from
+ * a device reset. The caller must be able to sleep. Use this to delay
+ * operations that could fail while the driver is cleaning up after a device
+ * reset.
+ *
+ * Returns 0 on success, -EBUSY if the reset is not finished within the
+ * timeout, and -ERESTARTSYS if the thread was interrupted.
+ */
+int ice_wait_for_reset(struct ice_pf *pf, unsigned long timeout)
+{
+	long ret;
+
+	ret = wait_event_interruptible_timeout(pf->reset_wait_queue,
+					       !ice_is_reset_in_progress(pf->state),
+					       timeout);
+	if (ret < 0)
+		return ret;
+	else if (!ret)
+		return -EBUSY;
+	else
+		return 0;
+}
+
 #ifdef CONFIG_DCB
 /**
  * ice_vsi_update_q_map - update our copy of the VSI info with new queue map
@@ -3330,13 +3401,22 @@ int ice_status_to_errno(enum ice_status err)
 	case ICE_ERR_DOES_NOT_EXIST:
 		return -ENOENT;
 	case ICE_ERR_OUT_OF_RANGE:
-		return -ENOTTY;
+	case ICE_ERR_AQ_ERROR:
+	case ICE_ERR_AQ_TIMEOUT:
+	case ICE_ERR_AQ_EMPTY:
+	case ICE_ERR_AQ_FW_CRITICAL:
+		return -EIO;
 	case ICE_ERR_PARAM:
+	case ICE_ERR_INVAL_SIZE:
 		return -EINVAL;
 	case ICE_ERR_NO_MEMORY:
 		return -ENOMEM;
 	case ICE_ERR_MAX_LIMIT:
 		return -EAGAIN;
+	case ICE_ERR_RESET_ONGOING:
+		return -EBUSY;
+	case ICE_ERR_AQ_FULL:
+		return -ENOSPC;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 511c2316c40c..d5a28bf0fc2c 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -12,6 +12,10 @@ bool ice_pf_state_is_nominal(struct ice_pf *pf);
 
 void ice_update_eth_stats(struct ice_vsi *vsi);
 
+int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx);
+
+int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_ring **tx_rings, u16 q_idx);
+
 int ice_vsi_cfg_rxqs(struct ice_vsi *vsi);
 
 int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi);
@@ -73,9 +77,11 @@ ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id);
 int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi);
 
 bool ice_is_reset_in_progress(unsigned long *state);
+int ice_wait_for_reset(struct ice_pf *pf, unsigned long timeout);
 
 void
-ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio);
+ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio,
+			bool ena_ts);
 
 void ice_vsi_dis_irq(struct ice_vsi *vsi);
 
@@ -102,7 +108,7 @@ enum ice_status
 ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set);
 
 bool ice_is_safe_mode(struct ice_pf *pf);
-
+bool ice_is_aux_ena(struct ice_pf *pf);
 bool ice_is_dflt_vsi_in_use(struct ice_sw *sw);
 
 bool ice_is_vsi_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 0eb2307325d3..5c3ea504770a 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -35,6 +35,8 @@ MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all), hw debug_mask (0x8XXXX
 MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)");
 #endif /* !CONFIG_DYNAMIC_DEBUG */
 
+static DEFINE_IDA(ice_aux_ida);
+
 static struct workqueue_struct *ice_wq;
 static const struct net_device_ops ice_netdev_safe_mode_ops;
 static const struct net_device_ops ice_netdev_ops;
@@ -454,6 +456,8 @@ ice_prepare_for_reset(struct ice_pf *pf)
 	if (test_bit(ICE_PREPARED_FOR_RESET, pf->state))
 		return;
 
+	ice_unplug_aux_dev(pf);
+
 	/* Notify VFs of impending reset */
 	if (ice_check_sq_alive(hw, &hw->mailboxq))
 		ice_vc_notify_reset(pf);
@@ -467,6 +471,9 @@ ice_prepare_for_reset(struct ice_pf *pf)
 	/* disable the VSIs and their queues that are not already DOWN */
 	ice_pf_dis_all_vsi(pf, false);
 
+	if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
+		ice_ptp_release(pf);
+
 	if (hw->port_info)
 		ice_sched_clear_port(hw->port_info);
 
@@ -499,6 +506,7 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 		clear_bit(ICE_PFR_REQ, pf->state);
 		clear_bit(ICE_CORER_REQ, pf->state);
 		clear_bit(ICE_GLOBR_REQ, pf->state);
+		wake_up(&pf->reset_wait_queue);
 		return;
 	}
 
@@ -511,6 +519,7 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 		ice_rebuild(pf, reset_type);
 		clear_bit(ICE_PREPARED_FOR_RESET, pf->state);
 		clear_bit(ICE_PFR_REQ, pf->state);
+		wake_up(&pf->reset_wait_queue);
 		ice_reset_all_vfs(pf, true);
 	}
 }
@@ -561,6 +570,7 @@ static void ice_reset_subtask(struct ice_pf *pf)
 			clear_bit(ICE_PFR_REQ, pf->state);
 			clear_bit(ICE_CORER_REQ, pf->state);
 			clear_bit(ICE_GLOBR_REQ, pf->state);
+			wake_up(&pf->reset_wait_queue);
 			ice_reset_all_vfs(pf, true);
 		}
 
@@ -858,6 +868,38 @@ static void ice_set_dflt_mib(struct ice_pf *pf)
 }
 
 /**
+ * ice_check_module_power
+ * @pf: pointer to PF struct
+ * @link_cfg_err: bitmap from the link info structure
+ *
+ * check module power level returned by a previous call to aq_get_link_info
+ * and print error messages if module power level is not supported
+ */
+static void ice_check_module_power(struct ice_pf *pf, u8 link_cfg_err)
+{
+	/* if module power level is supported, clear the flag */
+	if (!(link_cfg_err & (ICE_AQ_LINK_INVAL_MAX_POWER_LIMIT |
+			      ICE_AQ_LINK_MODULE_POWER_UNSUPPORTED))) {
+		clear_bit(ICE_FLAG_MOD_POWER_UNSUPPORTED, pf->flags);
+		return;
+	}
+
+	/* if ICE_FLAG_MOD_POWER_UNSUPPORTED was previously set and the
+	 * above block didn't clear this bit, there's nothing to do
+	 */
+	if (test_bit(ICE_FLAG_MOD_POWER_UNSUPPORTED, pf->flags))
+		return;
+
+	if (link_cfg_err & ICE_AQ_LINK_INVAL_MAX_POWER_LIMIT) {
+		dev_err(ice_pf_to_dev(pf), "The installed module is incompatible with the device's NVM image. Cannot start link\n");
+		set_bit(ICE_FLAG_MOD_POWER_UNSUPPORTED, pf->flags);
+	} else if (link_cfg_err & ICE_AQ_LINK_MODULE_POWER_UNSUPPORTED) {
+		dev_err(ice_pf_to_dev(pf), "The module's power requirements exceed the device's power supply. Cannot start link\n");
+		set_bit(ICE_FLAG_MOD_POWER_UNSUPPORTED, pf->flags);
+	}
+}
+
+/**
  * ice_link_event - process the link event
  * @pf: PF that the link event is associated with
  * @pi: port_info for the port that the link event is associated with
@@ -892,6 +934,8 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
 			pi->lport, ice_stat_str(status),
 			ice_aq_str(pi->hw->adminq.sq_last_status));
 
+	ice_check_module_power(pf, pi->phy.link_info.link_cfg_err);
+
 	/* Check if the link state is up after updating link info, and treat
 	 * this event as an UP event since the link is actually UP now.
 	 */
@@ -1190,6 +1234,10 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 		cq = &hw->adminq;
 		qtype = "Admin";
 		break;
+	case ICE_CTL_Q_SB:
+		cq = &hw->sbq;
+		qtype = "Sideband";
+		break;
 	case ICE_CTL_Q_MAILBOX:
 		cq = &hw->mailboxq;
 		qtype = "Mailbox";
@@ -1364,6 +1412,34 @@ static void ice_clean_mailboxq_subtask(struct ice_pf *pf)
 }
 
 /**
+ * ice_clean_sbq_subtask - clean the Sideband Queue rings
+ * @pf: board private structure
+ */
+static void ice_clean_sbq_subtask(struct ice_pf *pf)
+{
+	struct ice_hw *hw = &pf->hw;
+
+	/* Nothing to do here if sideband queue is not supported */
+	if (!ice_is_sbq_supported(hw)) {
+		clear_bit(ICE_SIDEBANDQ_EVENT_PENDING, pf->state);
+		return;
+	}
+
+	if (!test_bit(ICE_SIDEBANDQ_EVENT_PENDING, pf->state))
+		return;
+
+	if (__ice_clean_ctrlq(pf, ICE_CTL_Q_SB))
+		return;
+
+	clear_bit(ICE_SIDEBANDQ_EVENT_PENDING, pf->state);
+
+	if (ice_ctrlq_pending(hw, &hw->sbq))
+		__ice_clean_ctrlq(pf, ICE_CTL_Q_SB);
+
+	ice_flush(hw);
+}
+
+/**
  * ice_service_task_schedule - schedule the service task to wake up
  * @pf: board private structure
  *
@@ -2006,6 +2082,8 @@ static void ice_check_media_subtask(struct ice_pf *pf)
 	if (err)
 		return;
 
+	ice_check_module_power(pf, pi->phy.link_info.link_cfg_err);
+
 	if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) {
 		if (!test_bit(ICE_PHY_INIT_COMPLETE, pf->state))
 			ice_init_phy_user_cfg(pi);
@@ -2063,6 +2141,7 @@ static void ice_service_task(struct work_struct *work)
 
 	ice_process_vflr_event(pf);
 	ice_clean_mailboxq_subtask(pf);
+	ice_clean_sbq_subtask(pf);
 	ice_sync_arfs_fltrs(pf);
 	ice_flush_fdir_ctx(pf);
 
@@ -2078,6 +2157,7 @@ static void ice_service_task(struct work_struct *work)
 	    test_bit(ICE_VFLR_EVENT_PENDING, pf->state) ||
 	    test_bit(ICE_MAILBOXQ_EVENT_PENDING, pf->state) ||
 	    test_bit(ICE_FD_VF_FLUSH_CTX, pf->state) ||
+	    test_bit(ICE_SIDEBANDQ_EVENT_PENDING, pf->state) ||
 	    test_bit(ICE_ADMINQ_EVENT_PENDING, pf->state))
 		mod_timer(&pf->serv_tmr, jiffies);
 }
@@ -2096,6 +2176,10 @@ static void ice_set_ctrlq_len(struct ice_hw *hw)
 	hw->mailboxq.num_sq_entries = ICE_MBXSQ_LEN;
 	hw->mailboxq.rq_buf_size = ICE_MBXQ_MAX_BUF_LEN;
 	hw->mailboxq.sq_buf_size = ICE_MBXQ_MAX_BUF_LEN;
+	hw->sbq.num_rq_entries = ICE_SBQ_LEN;
+	hw->sbq.num_sq_entries = ICE_SBQ_LEN;
+	hw->sbq.rq_buf_size = ICE_SBQ_MAX_BUF_LEN;
+	hw->sbq.sq_buf_size = ICE_SBQ_MAX_BUF_LEN;
 }
 
 /**
@@ -2118,6 +2202,8 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset)
 		return -EBUSY;
 	}
 
+	ice_unplug_aux_dev(pf);
+
 	switch (reset) {
 	case ICE_RESET_PFR:
 		set_bit(ICE_PFR_REQ, pf->state);
@@ -2622,6 +2708,7 @@ static void ice_ena_misc_vector(struct ice_pf *pf)
 	       PFINT_OICR_PCI_EXCEPTION_M |
 	       PFINT_OICR_VFLR_M |
 	       PFINT_OICR_HMC_ERR_M |
+	       PFINT_OICR_PE_PUSH_M |
 	       PFINT_OICR_PE_CRITERR_M);
 
 	wr32(hw, PFINT_OICR_ENA, val);
@@ -2647,6 +2734,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 	dev = ice_pf_to_dev(pf);
 	set_bit(ICE_ADMINQ_EVENT_PENDING, pf->state);
 	set_bit(ICE_MAILBOXQ_EVENT_PENDING, pf->state);
+	set_bit(ICE_SIDEBANDQ_EVENT_PENDING, pf->state);
 
 	oicr = rd32(hw, PFINT_OICR);
 	ena_mask = rd32(hw, PFINT_OICR_ENA);
@@ -2692,8 +2780,6 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 
 		/* If a reset cycle isn't already in progress, we set a bit in
 		 * pf->state so that the service task can start a reset/rebuild.
-		 * We also make note of which reset happened so that peer
-		 * devices/drivers can be informed.
 		 */
 		if (!test_and_set_bit(ICE_RESET_OICR_RECV, pf->state)) {
 			if (reset == ICE_RESET_CORER)
@@ -2720,11 +2806,24 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 		}
 	}
 
-	if (oicr & PFINT_OICR_HMC_ERR_M) {
-		ena_mask &= ~PFINT_OICR_HMC_ERR_M;
-		dev_dbg(dev, "HMC Error interrupt - info 0x%x, data 0x%x\n",
-			rd32(hw, PFHMC_ERRORINFO),
-			rd32(hw, PFHMC_ERRORDATA));
+	if (oicr & PFINT_OICR_TSYN_TX_M) {
+		ena_mask &= ~PFINT_OICR_TSYN_TX_M;
+		ice_ptp_process_ts(pf);
+	}
+
+#define ICE_AUX_CRIT_ERR (PFINT_OICR_PE_CRITERR_M | PFINT_OICR_HMC_ERR_M | PFINT_OICR_PE_PUSH_M)
+	if (oicr & ICE_AUX_CRIT_ERR) {
+		struct iidc_event *event;
+
+		ena_mask &= ~ICE_AUX_CRIT_ERR;
+		event = kzalloc(sizeof(*event), GFP_KERNEL);
+		if (event) {
+			set_bit(IIDC_EVENT_CRIT_ERR, event->type);
+			/* report the entire OICR value to AUX driver */
+			event->reg = oicr;
+			ice_send_event_to_aux(pf, event);
+			kfree(event);
+		}
 	}
 
 	/* Report any remaining unexpected interrupts */
@@ -2734,8 +2833,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 		/* If a critical error is pending there is no choice but to
 		 * reset the device.
 		 */
-		if (oicr & (PFINT_OICR_PE_CRITERR_M |
-			    PFINT_OICR_PCI_EXCEPTION_M |
+		if (oicr & (PFINT_OICR_PCI_EXCEPTION_M |
 			    PFINT_OICR_ECC_ERR_M)) {
 			set_bit(ICE_PFR_REQ, pf->state);
 			ice_service_task_schedule(pf);
@@ -2763,6 +2861,9 @@ static void ice_dis_ctrlq_interrupts(struct ice_hw *hw)
 	wr32(hw, PFINT_MBX_CTL,
 	     rd32(hw, PFINT_MBX_CTL) & ~PFINT_MBX_CTL_CAUSE_ENA_M);
 
+	wr32(hw, PFINT_SB_CTL,
+	     rd32(hw, PFINT_SB_CTL) & ~PFINT_SB_CTL_CAUSE_ENA_M);
+
 	/* disable Control queue Interrupt causes */
 	wr32(hw, PFINT_OICR_CTL,
 	     rd32(hw, PFINT_OICR_CTL) & ~PFINT_OICR_CTL_CAUSE_ENA_M);
@@ -2817,6 +2918,11 @@ static void ice_ena_ctrlq_interrupts(struct ice_hw *hw, u16 reg_idx)
 	       PFINT_MBX_CTL_CAUSE_ENA_M);
 	wr32(hw, PFINT_MBX_CTL, val);
 
+	/* This enables Sideband queue Interrupt causes */
+	val = ((reg_idx & PFINT_SB_CTL_MSIX_INDX_M) |
+	       PFINT_SB_CTL_CAUSE_ENA_M);
+	wr32(hw, PFINT_SB_CTL, val);
+
 	ice_flush(hw);
 }
 
@@ -2986,7 +3092,6 @@ static void ice_set_netdev_features(struct net_device *netdev)
  */
 static int ice_cfg_netdev(struct ice_vsi *vsi)
 {
-	struct ice_pf *pf = vsi->back;
 	struct ice_netdev_priv *np;
 	struct net_device *netdev;
 	u8 mac_addr[ETH_ALEN];
@@ -3006,7 +3111,7 @@ static int ice_cfg_netdev(struct ice_vsi *vsi)
 	ice_set_ops(netdev);
 
 	if (vsi->type == ICE_VSI_PF) {
-		SET_NETDEV_DEV(netdev, ice_pf_to_dev(pf));
+		SET_NETDEV_DEV(netdev, ice_pf_to_dev(vsi->back));
 		ether_addr_copy(mac_addr, vsi->port_info->mac.perm_addr);
 		ether_addr_copy(netdev->dev_addr, mac_addr);
 		ether_addr_copy(netdev->perm_addr, mac_addr);
@@ -3280,6 +3385,9 @@ static void ice_deinit_pf(struct ice_pf *pf)
 		bitmap_free(pf->avail_rxqs);
 		pf->avail_rxqs = NULL;
 	}
+
+	if (pf->ptp.clock)
+		ptp_clock_unregister(pf->ptp.clock);
 }
 
 /**
@@ -3290,6 +3398,12 @@ static void ice_set_pf_caps(struct ice_pf *pf)
 {
 	struct ice_hw_func_caps *func_caps = &pf->hw.func_caps;
 
+	clear_bit(ICE_FLAG_RDMA_ENA, pf->flags);
+	clear_bit(ICE_FLAG_AUX_ENA, pf->flags);
+	if (func_caps->common_cap.rdma) {
+		set_bit(ICE_FLAG_RDMA_ENA, pf->flags);
+		set_bit(ICE_FLAG_AUX_ENA, pf->flags);
+	}
 	clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
 	if (func_caps->common_cap.dcb)
 		set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
@@ -3320,6 +3434,10 @@ static void ice_set_pf_caps(struct ice_pf *pf)
 				       func_caps->fd_fltr_best_effort);
 	}
 
+	clear_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags);
+	if (func_caps->common_cap.ieee_1588)
+		set_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags);
+
 	pf->max_pf_txqs = func_caps->common_cap.num_txq;
 	pf->max_pf_rxqs = func_caps->common_cap.num_rxq;
 }
@@ -3339,6 +3457,8 @@ static int ice_init_pf(struct ice_pf *pf)
 	spin_lock_init(&pf->aq_wait_lock);
 	init_waitqueue_head(&pf->aq_wait_queue);
 
+	init_waitqueue_head(&pf->reset_wait_queue);
+
 	/* setup service timer and periodic service task */
 	timer_setup(&pf->serv_tmr, ice_service_timer, 0);
 	pf->serv_tmr_period = HZ;
@@ -3369,11 +3489,12 @@ static int ice_init_pf(struct ice_pf *pf)
  */
 static int ice_ena_msix_range(struct ice_pf *pf)
 {
-	int v_left, v_actual, v_other, v_budget = 0;
+	int num_cpus, v_left, v_actual, v_other, v_budget = 0;
 	struct device *dev = ice_pf_to_dev(pf);
 	int needed, err, i;
 
 	v_left = pf->hw.func_caps.common_cap.num_msix_vectors;
+	num_cpus = num_online_cpus();
 
 	/* reserve for LAN miscellaneous handler */
 	needed = ICE_MIN_LAN_OICR_MSIX;
@@ -3395,13 +3516,23 @@ static int ice_ena_msix_range(struct ice_pf *pf)
 	v_other = v_budget;
 
 	/* reserve vectors for LAN traffic */
-	needed = min_t(int, num_online_cpus(), v_left);
+	needed = num_cpus;
 	if (v_left < needed)
 		goto no_hw_vecs_left_err;
 	pf->num_lan_msix = needed;
 	v_budget += needed;
 	v_left -= needed;
 
+	/* reserve vectors for RDMA auxiliary driver */
+	if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) {
+		needed = num_cpus + ICE_RDMA_NUM_AEQ_MSIX;
+		if (v_left < needed)
+			goto no_hw_vecs_left_err;
+		pf->num_rdma_msix = needed;
+		v_budget += needed;
+		v_left -= needed;
+	}
+
 	pf->msix_entries = devm_kcalloc(dev, v_budget,
 					sizeof(*pf->msix_entries), GFP_KERNEL);
 	if (!pf->msix_entries) {
@@ -3431,16 +3562,46 @@ static int ice_ena_msix_range(struct ice_pf *pf)
 			err = -ERANGE;
 			goto msix_err;
 		} else {
-			int v_traffic = v_actual - v_other;
+			int v_remain = v_actual - v_other;
+			int v_rdma = 0, v_min_rdma = 0;
+
+			if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) {
+				/* Need at least 1 interrupt in addition to
+				 * AEQ MSIX
+				 */
+				v_rdma = ICE_RDMA_NUM_AEQ_MSIX + 1;
+				v_min_rdma = ICE_MIN_RDMA_MSIX;
+			}
 
 			if (v_actual == ICE_MIN_MSIX ||
-			    v_traffic < ICE_MIN_LAN_TXRX_MSIX)
+			    v_remain < ICE_MIN_LAN_TXRX_MSIX + v_min_rdma) {
+				dev_warn(dev, "Not enough MSI-X vectors to support RDMA.\n");
+				clear_bit(ICE_FLAG_RDMA_ENA, pf->flags);
+
+				pf->num_rdma_msix = 0;
 				pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX;
-			else
-				pf->num_lan_msix = v_traffic;
+			} else if ((v_remain < ICE_MIN_LAN_TXRX_MSIX + v_rdma) ||
+				   (v_remain - v_rdma < v_rdma)) {
+				/* Support minimum RDMA and give remaining
+				 * vectors to LAN MSIX
+				 */
+				pf->num_rdma_msix = v_min_rdma;
+				pf->num_lan_msix = v_remain - v_min_rdma;
+			} else {
+				/* Split remaining MSIX with RDMA after
+				 * accounting for AEQ MSIX
+				 */
+				pf->num_rdma_msix = (v_remain - ICE_RDMA_NUM_AEQ_MSIX) / 2 +
+						    ICE_RDMA_NUM_AEQ_MSIX;
+				pf->num_lan_msix = v_remain - pf->num_rdma_msix;
+			}
 
 			dev_notice(dev, "Enabled %d MSI-X vectors for LAN traffic.\n",
 				   pf->num_lan_msix);
+
+			if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags))
+				dev_notice(dev, "Enabled %d MSI-X vectors for RDMA.\n",
+					   pf->num_rdma_msix);
 		}
 	}
 
@@ -3455,6 +3616,7 @@ no_hw_vecs_left_err:
 		needed, v_left);
 	err = -ERANGE;
 exit_err:
+	pf->num_rdma_msix = 0;
 	pf->num_lan_msix = 0;
 	return err;
 }
@@ -4218,6 +4380,8 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 
 	ice_init_link_dflt_override(pf->hw.port_info);
 
+	ice_check_module_power(pf, pf->hw.port_info->phy.link_info.link_cfg_err);
+
 	/* if media available, initialize PHY settings */
 	if (pf->hw.port_info->phy.link_info.link_info &
 	    ICE_AQ_MEDIA_AVAILABLE) {
@@ -4256,6 +4420,8 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 	}
 
 	/* initialize DDP driven features */
+	if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
+		ice_ptp_init(pf);
 
 	/* Note: Flow director init failure is non-fatal to load */
 	if (ice_init_fdir(pf))
@@ -4282,8 +4448,29 @@ probe_done:
 
 	/* ready to go, so clear down state bit */
 	clear_bit(ICE_DOWN, pf->state);
+	if (ice_is_aux_ena(pf)) {
+		pf->aux_idx = ida_alloc(&ice_aux_ida, GFP_KERNEL);
+		if (pf->aux_idx < 0) {
+			dev_err(dev, "Failed to allocate device ID for AUX driver\n");
+			err = -ENOMEM;
+			goto err_netdev_reg;
+		}
+
+		err = ice_init_rdma(pf);
+		if (err) {
+			dev_err(dev, "Failed to initialize RDMA: %d\n", err);
+			err = -EIO;
+			goto err_init_aux_unroll;
+		}
+	} else {
+		dev_warn(dev, "RDMA is not supported on this device\n");
+	}
+
 	return 0;
 
+err_init_aux_unroll:
+	pf->adev = NULL;
+	ida_free(&ice_aux_ida, pf->aux_idx);
 err_netdev_reg:
 err_send_version_unroll:
 	ice_vsi_release_all(pf);
@@ -4393,13 +4580,17 @@ static void ice_remove(struct pci_dev *pdev)
 		ice_free_vfs(pf);
 	}
 
-	set_bit(ICE_DOWN, pf->state);
 	ice_service_task_stop(pf);
 
 	ice_aq_cancel_waiting_tasks(pf);
+	ice_unplug_aux_dev(pf);
+	ida_free(&ice_aux_ida, pf->aux_idx);
+	set_bit(ICE_DOWN, pf->state);
 
 	mutex_destroy(&(&pf->hw)->fdir_fltr_lock);
 	ice_deinit_lag(pf);
+	if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
+		ice_ptp_release(pf);
 	if (!ice_is_safe_mode(pf))
 		ice_remove_arfs(pf);
 	ice_setup_mc_magic_wake(pf);
@@ -4552,6 +4743,8 @@ static int __maybe_unused ice_suspend(struct device *dev)
 	 */
 	disabled = ice_service_task_stop(pf);
 
+	ice_unplug_aux_dev(pf);
+
 	/* Already suspended?, then there is nothing to do */
 	if (test_and_set_bit(ICE_SUSPENDED, pf->state)) {
 		if (!disabled)
@@ -5451,7 +5644,6 @@ ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, struct ice_ring **rings,
 static void ice_update_vsi_ring_stats(struct ice_vsi *vsi)
 {
 	struct rtnl_link_stats64 *vsi_stats = &vsi->net_stats;
-	struct ice_ring *ring;
 	u64 pkts, bytes;
 	int i;
 
@@ -5475,7 +5667,8 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi)
 
 	/* update Rx rings counters */
 	ice_for_each_rxq(vsi, i) {
-		ring = READ_ONCE(vsi->rx_rings[i]);
+		struct ice_ring *ring = READ_ONCE(vsi->rx_rings[i]);
+
 		ice_fetch_u64_stats_per_ring(ring, &pkts, &bytes);
 		vsi_stats->rx_packets += pkts;
 		vsi_stats->rx_bytes += bytes;
@@ -6142,6 +6335,12 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 
 	ice_clear_pxe_mode(hw);
 
+	ret = ice_init_nvm(hw);
+	if (ret) {
+		dev_err(dev, "ice_init_nvm failed %s\n", ice_stat_str(ret));
+		goto err_init_ctrlq;
+	}
+
 	ret = ice_get_caps(hw);
 	if (ret) {
 		dev_err(dev, "ice_get_caps failed %s\n", ice_stat_str(ret));
@@ -6183,6 +6382,13 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 	if (test_bit(ICE_FLAG_DCB_ENA, pf->flags))
 		ice_dcb_rebuild(pf);
 
+	/* If the PF previously had enabled PTP, PTP init needs to happen before
+	 * the VSI rebuild. If not, this causes the PTP link status events to
+	 * fail.
+	 */
+	if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
+		ice_ptp_init(pf);
+
 	/* rebuild PF VSI */
 	err = ice_vsi_rebuild_by_type(pf, ICE_VSI_PF);
 	if (err) {
@@ -6222,6 +6428,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 
 	/* if we get here, reset flow is successful */
 	clear_bit(ICE_RESET_FAILED, pf->state);
+
+	ice_plug_aux_dev(pf);
 	return;
 
 err_vsi_rebuild:
@@ -6260,7 +6468,9 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
+	struct iidc_event *event;
 	u8 count = 0;
+	int err = 0;
 
 	if (new_mtu == (int)netdev->mtu) {
 		netdev_warn(netdev, "MTU is already %u\n", netdev->mtu);
@@ -6293,27 +6503,59 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
 		return -EBUSY;
 	}
 
+	event = kzalloc(sizeof(*event), GFP_KERNEL);
+	if (!event)
+		return -ENOMEM;
+
+	set_bit(IIDC_EVENT_BEFORE_MTU_CHANGE, event->type);
+	ice_send_event_to_aux(pf, event);
+	clear_bit(IIDC_EVENT_BEFORE_MTU_CHANGE, event->type);
+
 	netdev->mtu = (unsigned int)new_mtu;
 
 	/* if VSI is up, bring it down and then back up */
 	if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state)) {
-		int err;
-
 		err = ice_down(vsi);
 		if (err) {
 			netdev_err(netdev, "change MTU if_down err %d\n", err);
-			return err;
+			goto event_after;
 		}
 
 		err = ice_up(vsi);
 		if (err) {
 			netdev_err(netdev, "change MTU if_up err %d\n", err);
-			return err;
+			goto event_after;
 		}
 	}
 
 	netdev_dbg(netdev, "changed MTU to %d\n", new_mtu);
-	return 0;
+event_after:
+	set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type);
+	ice_send_event_to_aux(pf, event);
+	kfree(event);
+
+	return err;
+}
+
+/**
+ * ice_do_ioctl - Access the hwtstamp interface
+ * @netdev: network interface device structure
+ * @ifr: interface request data
+ * @cmd: ioctl command
+ */
+static int ice_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_pf *pf = np->vsi->back;
+
+	switch (cmd) {
+	case SIOCGHWTSTAMP:
+		return ice_ptp_get_ts_config(pf, ifr);
+	case SIOCSHWTSTAMP:
+		return ice_ptp_set_ts_config(pf, ifr);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 /**
@@ -6832,6 +7074,8 @@ int ice_open_internal(struct net_device *netdev)
 		return -EIO;
 	}
 
+	ice_check_module_power(pf, pi->phy.link_info.link_cfg_err);
+
 	/* Set PHY if there is media, otherwise, turn off PHY */
 	if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) {
 		clear_bit(ICE_FLAG_NO_MEDIA, pf->flags);
@@ -6965,6 +7209,7 @@ static const struct net_device_ops ice_netdev_ops = {
 	.ndo_change_mtu = ice_change_mtu,
 	.ndo_get_stats64 = ice_get_stats64,
 	.ndo_set_tx_maxrate = ice_set_tx_maxrate,
+	.ndo_do_ioctl = ice_do_ioctl,
 	.ndo_set_vf_spoofchk = ice_set_vf_spoofchk,
 	.ndo_set_vf_mac = ice_set_vf_mac,
 	.ndo_get_vf_config = ice_get_vf_cfg,
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
new file mode 100644
index 000000000000..609f433a4b96
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -0,0 +1,1265 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021, Intel Corporation. */
+
+#include "ice.h"
+#include "ice_lib.h"
+
+/**
+ * ice_set_tx_tstamp - Enable or disable Tx timestamping
+ * @pf: The PF pointer to search in
+ * @on: bool value for whether timestamps are enabled or disabled
+ */
+static void ice_set_tx_tstamp(struct ice_pf *pf, bool on)
+{
+	struct ice_vsi *vsi;
+	u32 val;
+	u16 i;
+
+	vsi = ice_get_main_vsi(pf);
+	if (!vsi)
+		return;
+
+	/* Set the timestamp enable flag for all the Tx rings */
+	ice_for_each_rxq(vsi, i) {
+		if (!vsi->tx_rings[i])
+			continue;
+		vsi->tx_rings[i]->ptp_tx = on;
+	}
+
+	/* Configure the Tx timestamp interrupt */
+	val = rd32(&pf->hw, PFINT_OICR_ENA);
+	if (on)
+		val |= PFINT_OICR_TSYN_TX_M;
+	else
+		val &= ~PFINT_OICR_TSYN_TX_M;
+	wr32(&pf->hw, PFINT_OICR_ENA, val);
+}
+
+/**
+ * ice_set_rx_tstamp - Enable or disable Rx timestamping
+ * @pf: The PF pointer to search in
+ * @on: bool value for whether timestamps are enabled or disabled
+ */
+static void ice_set_rx_tstamp(struct ice_pf *pf, bool on)
+{
+	struct ice_vsi *vsi;
+	u16 i;
+
+	vsi = ice_get_main_vsi(pf);
+	if (!vsi)
+		return;
+
+	/* Set the timestamp flag for all the Rx rings */
+	ice_for_each_rxq(vsi, i) {
+		if (!vsi->rx_rings[i])
+			continue;
+		vsi->rx_rings[i]->ptp_rx = on;
+	}
+}
+
+/**
+ * ice_ptp_cfg_timestamp - Configure timestamp for init/deinit
+ * @pf: Board private structure
+ * @ena: bool value to enable or disable time stamp
+ *
+ * This function will configure timestamping during PTP initialization
+ * and deinitialization
+ */
+static void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena)
+{
+	ice_set_tx_tstamp(pf, ena);
+	ice_set_rx_tstamp(pf, ena);
+
+	if (ena) {
+		pf->ptp.tstamp_config.rx_filter = HWTSTAMP_FILTER_ALL;
+		pf->ptp.tstamp_config.tx_type = HWTSTAMP_TX_ON;
+	} else {
+		pf->ptp.tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+		pf->ptp.tstamp_config.tx_type = HWTSTAMP_TX_OFF;
+	}
+}
+
+/**
+ * ice_get_ptp_clock_index - Get the PTP clock index
+ * @pf: the PF pointer
+ *
+ * Determine the clock index of the PTP clock associated with this device. If
+ * this is the PF controlling the clock, just use the local access to the
+ * clock device pointer.
+ *
+ * Otherwise, read from the driver shared parameters to determine the clock
+ * index value.
+ *
+ * Returns: the index of the PTP clock associated with this device, or -1 if
+ * there is no associated clock.
+ */
+int ice_get_ptp_clock_index(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	enum ice_aqc_driver_params param_idx;
+	struct ice_hw *hw = &pf->hw;
+	u8 tmr_idx;
+	u32 value;
+	int err;
+
+	/* Use the ptp_clock structure if we're the main PF */
+	if (pf->ptp.clock)
+		return ptp_clock_index(pf->ptp.clock);
+
+	tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc;
+	if (!tmr_idx)
+		param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR0;
+	else
+		param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR1;
+
+	err = ice_aq_get_driver_param(hw, param_idx, &value, NULL);
+	if (err) {
+		dev_err(dev, "Failed to read PTP clock index parameter, err %d aq_err %s\n",
+			err, ice_aq_str(hw->adminq.sq_last_status));
+		return -1;
+	}
+
+	/* The PTP clock index is an integer, and will be between 0 and
+	 * INT_MAX. The highest bit of the driver shared parameter is used to
+	 * indicate whether or not the currently stored clock index is valid.
+	 */
+	if (!(value & PTP_SHARED_CLK_IDX_VALID))
+		return -1;
+
+	return value & ~PTP_SHARED_CLK_IDX_VALID;
+}
+
+/**
+ * ice_set_ptp_clock_index - Set the PTP clock index
+ * @pf: the PF pointer
+ *
+ * Set the PTP clock index for this device into the shared driver parameters,
+ * so that other PFs associated with this device can read it.
+ *
+ * If the PF is unable to store the clock index, it will log an error, but
+ * will continue operating PTP.
+ */
+static void ice_set_ptp_clock_index(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	enum ice_aqc_driver_params param_idx;
+	struct ice_hw *hw = &pf->hw;
+	u8 tmr_idx;
+	u32 value;
+	int err;
+
+	if (!pf->ptp.clock)
+		return;
+
+	tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc;
+	if (!tmr_idx)
+		param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR0;
+	else
+		param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR1;
+
+	value = (u32)ptp_clock_index(pf->ptp.clock);
+	if (value > INT_MAX) {
+		dev_err(dev, "PTP Clock index is too large to store\n");
+		return;
+	}
+	value |= PTP_SHARED_CLK_IDX_VALID;
+
+	err = ice_aq_set_driver_param(hw, param_idx, value, NULL);
+	if (err) {
+		dev_err(dev, "Failed to set PTP clock index parameter, err %d aq_err %s\n",
+			err, ice_aq_str(hw->adminq.sq_last_status));
+	}
+}
+
+/**
+ * ice_clear_ptp_clock_index - Clear the PTP clock index
+ * @pf: the PF pointer
+ *
+ * Clear the PTP clock index for this device. Must be called when
+ * unregistering the PTP clock, in order to ensure other PFs stop reporting
+ * a clock object that no longer exists.
+ */
+static void ice_clear_ptp_clock_index(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	enum ice_aqc_driver_params param_idx;
+	struct ice_hw *hw = &pf->hw;
+	u8 tmr_idx;
+	int err;
+
+	/* Do not clear the index if we don't own the timer */
+	if (!hw->func_caps.ts_func_info.src_tmr_owned)
+		return;
+
+	tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc;
+	if (!tmr_idx)
+		param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR0;
+	else
+		param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR1;
+
+	err = ice_aq_set_driver_param(hw, param_idx, 0, NULL);
+	if (err) {
+		dev_dbg(dev, "Failed to clear PTP clock index parameter, err %d aq_err %s\n",
+			err, ice_aq_str(hw->adminq.sq_last_status));
+	}
+}
+
+/**
+ * ice_ptp_read_src_clk_reg - Read the source clock register
+ * @pf: Board private structure
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *       the system clock. Will be ignored if NULL is given.
+ */
+static u64
+ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts)
+{
+	struct ice_hw *hw = &pf->hw;
+	u32 hi, lo, lo2;
+	u8 tmr_idx;
+
+	tmr_idx = ice_get_ptp_src_clock_index(hw);
+	/* Read the system timestamp pre PHC read */
+	ptp_read_system_prets(sts);
+
+	lo = rd32(hw, GLTSYN_TIME_L(tmr_idx));
+
+	/* Read the system timestamp post PHC read */
+	ptp_read_system_postts(sts);
+
+	hi = rd32(hw, GLTSYN_TIME_H(tmr_idx));
+	lo2 = rd32(hw, GLTSYN_TIME_L(tmr_idx));
+
+	if (lo2 < lo) {
+		/* if TIME_L rolled over read TIME_L again and update
+		 * system timestamps
+		 */
+		ptp_read_system_prets(sts);
+		lo = rd32(hw, GLTSYN_TIME_L(tmr_idx));
+		ptp_read_system_postts(sts);
+		hi = rd32(hw, GLTSYN_TIME_H(tmr_idx));
+	}
+
+	return ((u64)hi << 32) | lo;
+}
+
+/**
+ * ice_ptp_update_cached_phctime - Update the cached PHC time values
+ * @pf: Board specific private structure
+ *
+ * This function updates the system time values which are cached in the PF
+ * structure and the Rx rings.
+ *
+ * This function must be called periodically to ensure that the cached value
+ * is never more than 2 seconds old. It must also be called whenever the PHC
+ * time has been changed.
+ */
+static void ice_ptp_update_cached_phctime(struct ice_pf *pf)
+{
+	u64 systime;
+	int i;
+
+	/* Read the current PHC time */
+	systime = ice_ptp_read_src_clk_reg(pf, NULL);
+
+	/* Update the cached PHC time stored in the PF structure */
+	WRITE_ONCE(pf->ptp.cached_phc_time, systime);
+
+	ice_for_each_vsi(pf, i) {
+		struct ice_vsi *vsi = pf->vsi[i];
+		int j;
+
+		if (!vsi)
+			continue;
+
+		if (vsi->type != ICE_VSI_PF)
+			continue;
+
+		ice_for_each_rxq(vsi, j) {
+			if (!vsi->rx_rings[j])
+				continue;
+			WRITE_ONCE(vsi->rx_rings[j]->cached_phctime, systime);
+		}
+	}
+}
+
+/**
+ * ice_ptp_extend_32b_ts - Convert a 32b nanoseconds timestamp to 64b
+ * @cached_phc_time: recently cached copy of PHC time
+ * @in_tstamp: Ingress/egress 32b nanoseconds timestamp value
+ *
+ * Hardware captures timestamps which contain only 32 bits of nominal
+ * nanoseconds, as opposed to the 64bit timestamps that the stack expects.
+ * Note that the captured timestamp values may be 40 bits, but the lower
+ * 8 bits are sub-nanoseconds and generally discarded.
+ *
+ * Extend the 32bit nanosecond timestamp using the following algorithm and
+ * assumptions:
+ *
+ * 1) have a recently cached copy of the PHC time
+ * 2) assume that the in_tstamp was captured 2^31 nanoseconds (~2.1
+ *    seconds) before or after the PHC time was captured.
+ * 3) calculate the delta between the cached time and the timestamp
+ * 4) if the delta is smaller than 2^31 nanoseconds, then the timestamp was
+ *    captured after the PHC time. In this case, the full timestamp is just
+ *    the cached PHC time plus the delta.
+ * 5) otherwise, if the delta is larger than 2^31 nanoseconds, then the
+ *    timestamp was captured *before* the PHC time, i.e. because the PHC
+ *    cache was updated after the timestamp was captured by hardware. In this
+ *    case, the full timestamp is the cached time minus the inverse delta.
+ *
+ * This algorithm works even if the PHC time was updated after a Tx timestamp
+ * was requested, but before the Tx timestamp event was reported from
+ * hardware.
+ *
+ * This calculation primarily relies on keeping the cached PHC time up to
+ * date. If the timestamp was captured more than 2^31 nanoseconds after the
+ * PHC time, it is possible that the lower 32bits of PHC time have
+ * overflowed more than once, and we might generate an incorrect timestamp.
+ *
+ * This is prevented by (a) periodically updating the cached PHC time once
+ * a second, and (b) discarding any Tx timestamp packet if it has waited for
+ * a timestamp for more than one second.
+ */
+static u64 ice_ptp_extend_32b_ts(u64 cached_phc_time, u32 in_tstamp)
+{
+	u32 delta, phc_time_lo;
+	u64 ns;
+
+	/* Extract the lower 32 bits of the PHC time */
+	phc_time_lo = (u32)cached_phc_time;
+
+	/* Calculate the delta between the lower 32bits of the cached PHC
+	 * time and the in_tstamp value
+	 */
+	delta = (in_tstamp - phc_time_lo);
+
+	/* Do not assume that the in_tstamp is always more recent than the
+	 * cached PHC time. If the delta is large, it indicates that the
+	 * in_tstamp was taken in the past, and should be converted
+	 * forward.
+	 */
+	if (delta > (U32_MAX / 2)) {
+		/* reverse the delta calculation here */
+		delta = (phc_time_lo - in_tstamp);
+		ns = cached_phc_time - delta;
+	} else {
+		ns = cached_phc_time + delta;
+	}
+
+	return ns;
+}
+
+/**
+ * ice_ptp_extend_40b_ts - Convert a 40b timestamp to 64b nanoseconds
+ * @pf: Board private structure
+ * @in_tstamp: Ingress/egress 40b timestamp value
+ *
+ * The Tx and Rx timestamps are 40 bits wide, including 32 bits of nominal
+ * nanoseconds, 7 bits of sub-nanoseconds, and a valid bit.
+ *
+ *  *--------------------------------------------------------------*
+ *  | 32 bits of nanoseconds | 7 high bits of sub ns underflow | v |
+ *  *--------------------------------------------------------------*
+ *
+ * The low bit is an indicator of whether the timestamp is valid. The next
+ * 7 bits are a capture of the upper 7 bits of the sub-nanosecond underflow,
+ * and the remaining 32 bits are the lower 32 bits of the PHC timer.
+ *
+ * It is assumed that the caller verifies the timestamp is valid prior to
+ * calling this function.
+ *
+ * Extract the 32bit nominal nanoseconds and extend them. Use the cached PHC
+ * time stored in the device private PTP structure as the basis for timestamp
+ * extension.
+ *
+ * See ice_ptp_extend_32b_ts for a detailed explanation of the extension
+ * algorithm.
+ */
+static u64 ice_ptp_extend_40b_ts(struct ice_pf *pf, u64 in_tstamp)
+{
+	const u64 mask = GENMASK_ULL(31, 0);
+
+	return ice_ptp_extend_32b_ts(pf->ptp.cached_phc_time,
+				     (in_tstamp >> 8) & mask);
+}
+
+/**
+ * ice_ptp_read_time - Read the time from the device
+ * @pf: Board private structure
+ * @ts: timespec structure to hold the current time value
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *       the system clock. Will be ignored if NULL is given.
+ *
+ * This function reads the source clock registers and stores them in a timespec.
+ * However, since the registers are 64 bits of nanoseconds, we must convert the
+ * result to a timespec before we can return.
+ */
+static void
+ice_ptp_read_time(struct ice_pf *pf, struct timespec64 *ts,
+		  struct ptp_system_timestamp *sts)
+{
+	u64 time_ns = ice_ptp_read_src_clk_reg(pf, sts);
+
+	*ts = ns_to_timespec64(time_ns);
+}
+
+/**
+ * ice_ptp_write_init - Set PHC time to provided value
+ * @pf: Board private structure
+ * @ts: timespec structure that holds the new time value
+ *
+ * Set the PHC time to the specified time provided in the timespec.
+ */
+static int ice_ptp_write_init(struct ice_pf *pf, struct timespec64 *ts)
+{
+	u64 ns = timespec64_to_ns(ts);
+	struct ice_hw *hw = &pf->hw;
+
+	return ice_ptp_init_time(hw, ns);
+}
+
+/**
+ * ice_ptp_write_adj - Adjust PHC clock time atomically
+ * @pf: Board private structure
+ * @adj: Adjustment in nanoseconds
+ *
+ * Perform an atomic adjustment of the PHC time by the specified number of
+ * nanoseconds.
+ */
+static int ice_ptp_write_adj(struct ice_pf *pf, s32 adj)
+{
+	struct ice_hw *hw = &pf->hw;
+
+	return ice_ptp_adj_clock(hw, adj);
+}
+
+/**
+ * ice_ptp_adjfine - Adjust clock increment rate
+ * @info: the driver's PTP info structure
+ * @scaled_ppm: Parts per million with 16-bit fractional field
+ *
+ * Adjust the frequency of the clock by the indicated scaled ppm from the
+ * base frequency.
+ */
+static int ice_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm)
+{
+	struct ice_pf *pf = ptp_info_to_pf(info);
+	u64 freq, divisor = 1000000ULL;
+	struct ice_hw *hw = &pf->hw;
+	s64 incval, diff;
+	int neg_adj = 0;
+	int err;
+
+	incval = ICE_PTP_NOMINAL_INCVAL_E810;
+
+	if (scaled_ppm < 0) {
+		neg_adj = 1;
+		scaled_ppm = -scaled_ppm;
+	}
+
+	while ((u64)scaled_ppm > div_u64(U64_MAX, incval)) {
+		/* handle overflow by scaling down the scaled_ppm and
+		 * the divisor, losing some precision
+		 */
+		scaled_ppm >>= 2;
+		divisor >>= 2;
+	}
+
+	freq = (incval * (u64)scaled_ppm) >> 16;
+	diff = div_u64(freq, divisor);
+
+	if (neg_adj)
+		incval -= diff;
+	else
+		incval += diff;
+
+	err = ice_ptp_write_incval_locked(hw, incval);
+	if (err) {
+		dev_err(ice_pf_to_dev(pf), "PTP failed to set incval, err %d\n",
+			err);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_ptp_gettimex64 - Get the time of the clock
+ * @info: the driver's PTP info structure
+ * @ts: timespec64 structure to hold the current time value
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *       the system clock. Will be ignored if NULL is given.
+ *
+ * Read the device clock and return the correct value on ns, after converting it
+ * into a timespec struct.
+ */
+static int
+ice_ptp_gettimex64(struct ptp_clock_info *info, struct timespec64 *ts,
+		   struct ptp_system_timestamp *sts)
+{
+	struct ice_pf *pf = ptp_info_to_pf(info);
+	struct ice_hw *hw = &pf->hw;
+
+	if (!ice_ptp_lock(hw)) {
+		dev_err(ice_pf_to_dev(pf), "PTP failed to get time\n");
+		return -EBUSY;
+	}
+
+	ice_ptp_read_time(pf, ts, sts);
+	ice_ptp_unlock(hw);
+
+	return 0;
+}
+
+/**
+ * ice_ptp_settime64 - Set the time of the clock
+ * @info: the driver's PTP info structure
+ * @ts: timespec64 structure that holds the new time value
+ *
+ * Set the device clock to the user input value. The conversion from timespec
+ * to ns happens in the write function.
+ */
+static int
+ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts)
+{
+	struct ice_pf *pf = ptp_info_to_pf(info);
+	struct timespec64 ts64 = *ts;
+	struct ice_hw *hw = &pf->hw;
+	int err;
+
+	if (!ice_ptp_lock(hw)) {
+		err = -EBUSY;
+		goto exit;
+	}
+
+	err = ice_ptp_write_init(pf, &ts64);
+	ice_ptp_unlock(hw);
+
+	if (!err)
+		ice_ptp_update_cached_phctime(pf);
+
+exit:
+	if (err) {
+		dev_err(ice_pf_to_dev(pf), "PTP failed to set time %d\n", err);
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_ptp_adjtime_nonatomic - Do a non-atomic clock adjustment
+ * @info: the driver's PTP info structure
+ * @delta: Offset in nanoseconds to adjust the time by
+ */
+static int ice_ptp_adjtime_nonatomic(struct ptp_clock_info *info, s64 delta)
+{
+	struct timespec64 now, then;
+
+	then = ns_to_timespec64(delta);
+	ice_ptp_gettimex64(info, &now, NULL);
+	now = timespec64_add(now, then);
+
+	return ice_ptp_settime64(info, (const struct timespec64 *)&now);
+}
+
+/**
+ * ice_ptp_adjtime - Adjust the time of the clock by the indicated delta
+ * @info: the driver's PTP info structure
+ * @delta: Offset in nanoseconds to adjust the time by
+ */
+static int ice_ptp_adjtime(struct ptp_clock_info *info, s64 delta)
+{
+	struct ice_pf *pf = ptp_info_to_pf(info);
+	struct ice_hw *hw = &pf->hw;
+	struct device *dev;
+	int err;
+
+	dev = ice_pf_to_dev(pf);
+
+	/* Hardware only supports atomic adjustments using signed 32-bit
+	 * integers. For any adjustment outside this range, perform
+	 * a non-atomic get->adjust->set flow.
+	 */
+	if (delta > S32_MAX || delta < S32_MIN) {
+		dev_dbg(dev, "delta = %lld, adjtime non-atomic\n", delta);
+		return ice_ptp_adjtime_nonatomic(info, delta);
+	}
+
+	if (!ice_ptp_lock(hw)) {
+		dev_err(dev, "PTP failed to acquire semaphore in adjtime\n");
+		return -EBUSY;
+	}
+
+	err = ice_ptp_write_adj(pf, delta);
+
+	ice_ptp_unlock(hw);
+
+	if (err) {
+		dev_err(dev, "PTP failed to adjust time, err %d\n", err);
+		return err;
+	}
+
+	ice_ptp_update_cached_phctime(pf);
+
+	return 0;
+}
+
+/**
+ * ice_ptp_get_ts_config - ioctl interface to read the timestamping config
+ * @pf: Board private structure
+ * @ifr: ioctl data
+ *
+ * Copy the timestamping config to user buffer
+ */
+int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr)
+{
+	struct hwtstamp_config *config;
+
+	if (!test_bit(ICE_FLAG_PTP, pf->flags))
+		return -EIO;
+
+	config = &pf->ptp.tstamp_config;
+
+	return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
+		-EFAULT : 0;
+}
+
+/**
+ * ice_ptp_set_timestamp_mode - Setup driver for requested timestamp mode
+ * @pf: Board private structure
+ * @config: hwtstamp settings requested or saved
+ */
+static int
+ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config)
+{
+	/* Reserved for future extensions. */
+	if (config->flags)
+		return -EINVAL;
+
+	switch (config->tx_type) {
+	case HWTSTAMP_TX_OFF:
+		ice_set_tx_tstamp(pf, false);
+		break;
+	case HWTSTAMP_TX_ON:
+		ice_set_tx_tstamp(pf, true);
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	switch (config->rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		ice_set_rx_tstamp(pf, false);
+		break;
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
+	case HWTSTAMP_FILTER_ALL:
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
+		ice_set_rx_tstamp(pf, true);
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_ptp_set_ts_config - ioctl interface to control the timestamping
+ * @pf: Board private structure
+ * @ifr: ioctl data
+ *
+ * Get the user config and store it
+ */
+int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr)
+{
+	struct hwtstamp_config config;
+	int err;
+
+	if (!test_bit(ICE_FLAG_PTP, pf->flags))
+		return -EAGAIN;
+
+	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+		return -EFAULT;
+
+	err = ice_ptp_set_timestamp_mode(pf, &config);
+	if (err)
+		return err;
+
+	/* Save these settings for future reference */
+	pf->ptp.tstamp_config = config;
+
+	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
+		-EFAULT : 0;
+}
+
+/**
+ * ice_ptp_rx_hwtstamp - Check for an Rx timestamp
+ * @rx_ring: Ring to get the VSI info
+ * @rx_desc: Receive descriptor
+ * @skb: Particular skb to send timestamp with
+ *
+ * The driver receives a notification in the receive descriptor with timestamp.
+ * The timestamp is in ns, so we must convert the result first.
+ */
+void
+ice_ptp_rx_hwtstamp(struct ice_ring *rx_ring,
+		    union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb)
+{
+	u32 ts_high;
+	u64 ts_ns;
+
+	/* Populate timesync data into skb */
+	if (rx_desc->wb.time_stamp_low & ICE_PTP_TS_VALID) {
+		struct skb_shared_hwtstamps *hwtstamps;
+
+		/* Use ice_ptp_extend_32b_ts directly, using the ring-specific
+		 * cached PHC value, rather than accessing the PF. This also
+		 * allows us to simply pass the upper 32bits of nanoseconds
+		 * directly. Calling ice_ptp_extend_40b_ts is unnecessary as
+		 * it would just discard these bits itself.
+		 */
+		ts_high = le32_to_cpu(rx_desc->wb.flex_ts.ts_high);
+		ts_ns = ice_ptp_extend_32b_ts(rx_ring->cached_phctime, ts_high);
+
+		hwtstamps = skb_hwtstamps(skb);
+		memset(hwtstamps, 0, sizeof(*hwtstamps));
+		hwtstamps->hwtstamp = ns_to_ktime(ts_ns);
+	}
+}
+
+/**
+ * ice_ptp_set_caps - Set PTP capabilities
+ * @pf: Board private structure
+ */
+static void ice_ptp_set_caps(struct ice_pf *pf)
+{
+	struct ptp_clock_info *info = &pf->ptp.info;
+	struct device *dev = ice_pf_to_dev(pf);
+
+	snprintf(info->name, sizeof(info->name) - 1, "%s-%s-clk",
+		 dev_driver_string(dev), dev_name(dev));
+	info->owner = THIS_MODULE;
+	info->max_adj = 999999999;
+	info->adjtime = ice_ptp_adjtime;
+	info->adjfine = ice_ptp_adjfine;
+	info->gettimex64 = ice_ptp_gettimex64;
+	info->settime64 = ice_ptp_settime64;
+}
+
+/**
+ * ice_ptp_create_clock - Create PTP clock device for userspace
+ * @pf: Board private structure
+ *
+ * This function creates a new PTP clock device. It only creates one if we
+ * don't already have one. Will return error if it can't create one, but success
+ * if we already have a device. Should be used by ice_ptp_init to create clock
+ * initially, and prevent global resets from creating new clock devices.
+ */
+static long ice_ptp_create_clock(struct ice_pf *pf)
+{
+	struct ptp_clock_info *info;
+	struct ptp_clock *clock;
+	struct device *dev;
+
+	/* No need to create a clock device if we already have one */
+	if (pf->ptp.clock)
+		return 0;
+
+	ice_ptp_set_caps(pf);
+
+	info = &pf->ptp.info;
+	dev = ice_pf_to_dev(pf);
+
+	/* Attempt to register the clock before enabling the hardware. */
+	clock = ptp_clock_register(info, dev);
+	if (IS_ERR(clock))
+		return PTR_ERR(clock);
+
+	pf->ptp.clock = clock;
+
+	return 0;
+}
+
+/**
+ * ice_ptp_tx_tstamp_work - Process Tx timestamps for a port
+ * @work: pointer to the kthread_work struct
+ *
+ * Process timestamps captured by the PHY associated with this port. To do
+ * this, loop over each index with a waiting skb.
+ *
+ * If a given index has a valid timestamp, perform the following steps:
+ *
+ * 1) copy the timestamp out of the PHY register
+ * 4) clear the timestamp valid bit in the PHY register
+ * 5) unlock the index by clearing the associated in_use bit.
+ * 2) extend the 40b timestamp value to get a 64bit timestamp
+ * 3) send that timestamp to the stack
+ *
+ * After looping, if we still have waiting SKBs, then re-queue the work. This
+ * may cause us effectively poll even when not strictly necessary. We do this
+ * because it's possible a new timestamp was requested around the same time as
+ * the interrupt. In some cases hardware might not interrupt us again when the
+ * timestamp is captured.
+ *
+ * Note that we only take the tracking lock when clearing the bit and when
+ * checking if we need to re-queue this task. The only place where bits can be
+ * set is the hard xmit routine where an SKB has a request flag set. The only
+ * places where we clear bits are this work function, or the periodic cleanup
+ * thread. If the cleanup thread clears a bit we're processing we catch it
+ * when we lock to clear the bit and then grab the SKB pointer. If a Tx thread
+ * starts a new timestamp, we might not begin processing it right away but we
+ * will notice it at the end when we re-queue the work item. If a Tx thread
+ * starts a new timestamp just after this function exits without re-queuing,
+ * the interrupt when the timestamp finishes should trigger. Avoiding holding
+ * the lock for the entire function is important in order to ensure that Tx
+ * threads do not get blocked while waiting for the lock.
+ */
+static void ice_ptp_tx_tstamp_work(struct kthread_work *work)
+{
+	struct ice_ptp_port *ptp_port;
+	struct ice_ptp_tx *tx;
+	struct ice_pf *pf;
+	struct ice_hw *hw;
+	u8 idx;
+
+	tx = container_of(work, struct ice_ptp_tx, work);
+	if (!tx->init)
+		return;
+
+	ptp_port = container_of(tx, struct ice_ptp_port, tx);
+	pf = ptp_port_to_pf(ptp_port);
+	hw = &pf->hw;
+
+	for_each_set_bit(idx, tx->in_use, tx->len) {
+		struct skb_shared_hwtstamps shhwtstamps = {};
+		u8 phy_idx = idx + tx->quad_offset;
+		u64 raw_tstamp, tstamp;
+		struct sk_buff *skb;
+		int err;
+
+		err = ice_read_phy_tstamp(hw, tx->quad, phy_idx,
+					  &raw_tstamp);
+		if (err)
+			continue;
+
+		/* Check if the timestamp is valid */
+		if (!(raw_tstamp & ICE_PTP_TS_VALID))
+			continue;
+
+		/* clear the timestamp register, so that it won't show valid
+		 * again when re-used.
+		 */
+		ice_clear_phy_tstamp(hw, tx->quad, phy_idx);
+
+		/* The timestamp is valid, so we'll go ahead and clear this
+		 * index and then send the timestamp up to the stack.
+		 */
+		spin_lock(&tx->lock);
+		clear_bit(idx, tx->in_use);
+		skb = tx->tstamps[idx].skb;
+		tx->tstamps[idx].skb = NULL;
+		spin_unlock(&tx->lock);
+
+		/* it's (unlikely but) possible we raced with the cleanup
+		 * thread for discarding old timestamp requests.
+		 */
+		if (!skb)
+			continue;
+
+		/* Extend the timestamp using cached PHC time */
+		tstamp = ice_ptp_extend_40b_ts(pf, raw_tstamp);
+		shhwtstamps.hwtstamp = ns_to_ktime(tstamp);
+
+		skb_tstamp_tx(skb, &shhwtstamps);
+		dev_kfree_skb_any(skb);
+	}
+
+	/* Check if we still have work to do. If so, re-queue this task to
+	 * poll for remaining timestamps.
+	 */
+	spin_lock(&tx->lock);
+	if (!bitmap_empty(tx->in_use, tx->len))
+		kthread_queue_work(pf->ptp.kworker, &tx->work);
+	spin_unlock(&tx->lock);
+}
+
+/**
+ * ice_ptp_request_ts - Request an available Tx timestamp index
+ * @tx: the PTP Tx timestamp tracker to request from
+ * @skb: the SKB to associate with this timestamp request
+ */
+s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb)
+{
+	u8 idx;
+
+	/* Check if this tracker is initialized */
+	if (!tx->init)
+		return -1;
+
+	spin_lock(&tx->lock);
+	/* Find and set the first available index */
+	idx = find_first_zero_bit(tx->in_use, tx->len);
+	if (idx < tx->len) {
+		/* We got a valid index that no other thread could have set. Store
+		 * a reference to the skb and the start time to allow discarding old
+		 * requests.
+		 */
+		set_bit(idx, tx->in_use);
+		tx->tstamps[idx].start = jiffies;
+		tx->tstamps[idx].skb = skb_get(skb);
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+	}
+
+	spin_unlock(&tx->lock);
+
+	/* return the appropriate PHY timestamp register index, -1 if no
+	 * indexes were available.
+	 */
+	if (idx >= tx->len)
+		return -1;
+	else
+		return idx + tx->quad_offset;
+}
+
+/**
+ * ice_ptp_process_ts - Spawn kthread work to handle timestamps
+ * @pf: Board private structure
+ *
+ * Queue work required to process the PTP Tx timestamps outside of interrupt
+ * context.
+ */
+void ice_ptp_process_ts(struct ice_pf *pf)
+{
+	if (pf->ptp.port.tx.init)
+		kthread_queue_work(pf->ptp.kworker, &pf->ptp.port.tx.work);
+}
+
+/**
+ * ice_ptp_alloc_tx_tracker - Initialize tracking for Tx timestamps
+ * @tx: Tx tracking structure to initialize
+ *
+ * Assumes that the length has already been initialized. Do not call directly,
+ * use the ice_ptp_init_tx_e822 or ice_ptp_init_tx_e810 instead.
+ */
+static int
+ice_ptp_alloc_tx_tracker(struct ice_ptp_tx *tx)
+{
+	tx->tstamps = kcalloc(tx->len, sizeof(*tx->tstamps), GFP_KERNEL);
+	if (!tx->tstamps)
+		return -ENOMEM;
+
+	tx->in_use = bitmap_zalloc(tx->len, GFP_KERNEL);
+	if (!tx->in_use) {
+		kfree(tx->tstamps);
+		tx->tstamps = NULL;
+		return -ENOMEM;
+	}
+
+	spin_lock_init(&tx->lock);
+	kthread_init_work(&tx->work, ice_ptp_tx_tstamp_work);
+
+	tx->init = 1;
+
+	return 0;
+}
+
+/**
+ * ice_ptp_flush_tx_tracker - Flush any remaining timestamps from the tracker
+ * @pf: Board private structure
+ * @tx: the tracker to flush
+ */
+static void
+ice_ptp_flush_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx)
+{
+	u8 idx;
+
+	for (idx = 0; idx < tx->len; idx++) {
+		u8 phy_idx = idx + tx->quad_offset;
+
+		/* Clear any potential residual timestamp in the PHY block */
+		if (!pf->hw.reset_ongoing)
+			ice_clear_phy_tstamp(&pf->hw, tx->quad, phy_idx);
+
+		if (tx->tstamps[idx].skb) {
+			dev_kfree_skb_any(tx->tstamps[idx].skb);
+			tx->tstamps[idx].skb = NULL;
+		}
+	}
+}
+
+/**
+ * ice_ptp_release_tx_tracker - Release allocated memory for Tx tracker
+ * @pf: Board private structure
+ * @tx: Tx tracking structure to release
+ *
+ * Free memory associated with the Tx timestamp tracker.
+ */
+static void
+ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx)
+{
+	tx->init = 0;
+
+	kthread_cancel_work_sync(&tx->work);
+
+	ice_ptp_flush_tx_tracker(pf, tx);
+
+	kfree(tx->tstamps);
+	tx->tstamps = NULL;
+
+	kfree(tx->in_use);
+	tx->in_use = NULL;
+
+	tx->len = 0;
+}
+
+/**
+ * ice_ptp_init_tx_e810 - Initialize tracking for Tx timestamps
+ * @pf: Board private structure
+ * @tx: the Tx tracking structure to initialize
+ *
+ * Initialize the Tx timestamp tracker for this PF. For E810 devices, each
+ * port has its own block of timestamps, independent of the other ports.
+ */
+static int
+ice_ptp_init_tx_e810(struct ice_pf *pf, struct ice_ptp_tx *tx)
+{
+	tx->quad = pf->hw.port_info->lport;
+	tx->quad_offset = 0;
+	tx->len = INDEX_PER_QUAD;
+
+	return ice_ptp_alloc_tx_tracker(tx);
+}
+
+/**
+ * ice_ptp_tx_tstamp_cleanup - Cleanup old timestamp requests that got dropped
+ * @tx: PTP Tx tracker to clean up
+ *
+ * Loop through the Tx timestamp requests and see if any of them have been
+ * waiting for a long time. Discard any SKBs that have been waiting for more
+ * than 2 seconds. This is long enough to be reasonably sure that the
+ * timestamp will never be captured. This might happen if the packet gets
+ * discarded before it reaches the PHY timestamping block.
+ */
+static void ice_ptp_tx_tstamp_cleanup(struct ice_ptp_tx *tx)
+{
+	u8 idx;
+
+	if (!tx->init)
+		return;
+
+	for_each_set_bit(idx, tx->in_use, tx->len) {
+		struct sk_buff *skb;
+
+		/* Check if this SKB has been waiting for too long */
+		if (time_is_after_jiffies(tx->tstamps[idx].start + 2 * HZ))
+			continue;
+
+		spin_lock(&tx->lock);
+		skb = tx->tstamps[idx].skb;
+		tx->tstamps[idx].skb = NULL;
+		clear_bit(idx, tx->in_use);
+		spin_unlock(&tx->lock);
+
+		/* Free the SKB after we've cleared the bit */
+		dev_kfree_skb_any(skb);
+	}
+}
+
+static void ice_ptp_periodic_work(struct kthread_work *work)
+{
+	struct ice_ptp *ptp = container_of(work, struct ice_ptp, work.work);
+	struct ice_pf *pf = container_of(ptp, struct ice_pf, ptp);
+
+	if (!test_bit(ICE_FLAG_PTP, pf->flags))
+		return;
+
+	ice_ptp_update_cached_phctime(pf);
+
+	ice_ptp_tx_tstamp_cleanup(&pf->ptp.port.tx);
+
+	/* Run twice a second */
+	kthread_queue_delayed_work(ptp->kworker, &ptp->work,
+				   msecs_to_jiffies(500));
+}
+
+/**
+ * ice_ptp_init_owner - Initialize PTP_1588_CLOCK device
+ * @pf: Board private structure
+ *
+ * Setup and initialize a PTP clock device that represents the device hardware
+ * clock. Save the clock index for other functions connected to the same
+ * hardware resource.
+ */
+static int ice_ptp_init_owner(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	struct ice_hw *hw = &pf->hw;
+	struct timespec64 ts;
+	u8 src_idx;
+	int err;
+
+	wr32(hw, GLTSYN_SYNC_DLAY, 0);
+
+	/* Clear some HW residue and enable source clock */
+	src_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+
+	/* Enable source clocks */
+	wr32(hw, GLTSYN_ENA(src_idx), GLTSYN_ENA_TSYN_ENA_M);
+
+	/* Enable PHY time sync */
+	err = ice_ptp_init_phy_e810(hw);
+	if (err)
+		goto err_exit;
+
+	/* Clear event status indications for auxiliary pins */
+	(void)rd32(hw, GLTSYN_STAT(src_idx));
+
+	/* Acquire the global hardware lock */
+	if (!ice_ptp_lock(hw)) {
+		err = -EBUSY;
+		goto err_exit;
+	}
+
+	/* Write the increment time value to PHY and LAN */
+	err = ice_ptp_write_incval(hw, ICE_PTP_NOMINAL_INCVAL_E810);
+	if (err) {
+		ice_ptp_unlock(hw);
+		goto err_exit;
+	}
+
+	ts = ktime_to_timespec64(ktime_get_real());
+	/* Write the initial Time value to PHY and LAN */
+	err = ice_ptp_write_init(pf, &ts);
+	if (err) {
+		ice_ptp_unlock(hw);
+		goto err_exit;
+	}
+
+	/* Release the global hardware lock */
+	ice_ptp_unlock(hw);
+
+	/* Ensure we have a clock device */
+	err = ice_ptp_create_clock(pf);
+	if (err)
+		goto err_clk;
+
+	/* Store the PTP clock index for other PFs */
+	ice_set_ptp_clock_index(pf);
+
+	return 0;
+
+err_clk:
+	pf->ptp.clock = NULL;
+err_exit:
+	dev_err(dev, "PTP failed to register clock, err %d\n", err);
+
+	return err;
+}
+
+/**
+ * ice_ptp_init - Initialize the PTP support after device probe or reset
+ * @pf: Board private structure
+ *
+ * This function sets device up for PTP support. The first time it is run, it
+ * will create a clock device. It does not create a clock device if one
+ * already exists. It also reconfigures the device after a reset.
+ */
+void ice_ptp_init(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	struct kthread_worker *kworker;
+	struct ice_hw *hw = &pf->hw;
+	int err;
+
+	/* PTP is currently only supported on E810 devices */
+	if (!ice_is_e810(hw))
+		return;
+
+	/* Check if this PF owns the source timer */
+	if (hw->func_caps.ts_func_info.src_tmr_owned) {
+		err = ice_ptp_init_owner(pf);
+		if (err)
+			return;
+	}
+
+	/* Disable timestamping for both Tx and Rx */
+	ice_ptp_cfg_timestamp(pf, false);
+
+	/* Initialize the PTP port Tx timestamp tracker */
+	ice_ptp_init_tx_e810(pf, &pf->ptp.port.tx);
+
+	/* Initialize work functions */
+	kthread_init_delayed_work(&pf->ptp.work, ice_ptp_periodic_work);
+
+	/* Allocate a kworker for handling work required for the ports
+	 * connected to the PTP hardware clock.
+	 */
+	kworker = kthread_create_worker(0, "ice-ptp-%s", dev_name(dev));
+	if (IS_ERR(kworker)) {
+		err = PTR_ERR(kworker);
+		goto err_kworker;
+	}
+	pf->ptp.kworker = kworker;
+
+	set_bit(ICE_FLAG_PTP, pf->flags);
+
+	/* Start periodic work going */
+	kthread_queue_delayed_work(pf->ptp.kworker, &pf->ptp.work, 0);
+
+	dev_info(dev, "PTP init successful\n");
+	return;
+
+err_kworker:
+	/* If we registered a PTP clock, release it */
+	if (pf->ptp.clock) {
+		ptp_clock_unregister(pf->ptp.clock);
+		pf->ptp.clock = NULL;
+	}
+	dev_err(dev, "PTP failed %d\n", err);
+}
+
+/**
+ * ice_ptp_release - Disable the driver/HW support and unregister the clock
+ * @pf: Board private structure
+ *
+ * This function handles the cleanup work required from the initialization by
+ * clearing out the important information and unregistering the clock
+ */
+void ice_ptp_release(struct ice_pf *pf)
+{
+	/* Disable timestamping for both Tx and Rx */
+	ice_ptp_cfg_timestamp(pf, false);
+
+	ice_ptp_release_tx_tracker(pf, &pf->ptp.port.tx);
+
+	clear_bit(ICE_FLAG_PTP, pf->flags);
+
+	kthread_cancel_delayed_work_sync(&pf->ptp.work);
+
+	if (pf->ptp.kworker) {
+		kthread_destroy_worker(pf->ptp.kworker);
+		pf->ptp.kworker = NULL;
+	}
+
+	if (!pf->ptp.clock)
+		return;
+
+	ice_clear_ptp_clock_index(pf);
+	ptp_clock_unregister(pf->ptp.clock);
+	pf->ptp.clock = NULL;
+
+	dev_info(ice_pf_to_dev(pf), "Removed PTP clock\n");
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h
new file mode 100644
index 000000000000..d01507eba036
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.h
@@ -0,0 +1,161 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021, Intel Corporation. */
+
+#ifndef _ICE_PTP_H_
+#define _ICE_PTP_H_
+
+#include <linux/ptp_clock_kernel.h>
+#include <linux/kthread.h>
+
+#include "ice_ptp_hw.h"
+
+/* The ice hardware captures Tx hardware timestamps in the PHY. The timestamp
+ * is stored in a buffer of registers. Depending on the specific hardware,
+ * this buffer might be shared across multiple PHY ports.
+ *
+ * On transmit of a packet to be timestamped, software is responsible for
+ * selecting an open index. Hardware makes no attempt to lock or prevent
+ * re-use of an index for multiple packets.
+ *
+ * To handle this, timestamp indexes must be tracked by software to ensure
+ * that an index is not re-used for multiple transmitted packets. The
+ * structures and functions declared in this file track the available Tx
+ * register indexes, as well as provide storage for the SKB pointers.
+ *
+ * To allow multiple ports to access the shared register block independently,
+ * the blocks are split up so that indexes are assigned to each port based on
+ * hardware logical port number.
+ */
+
+/**
+ * struct ice_tx_tstamp - Tracking for a single Tx timestamp
+ * @skb: pointer to the SKB for this timestamp request
+ * @start: jiffies when the timestamp was first requested
+ *
+ * This structure tracks a single timestamp request. The SKB pointer is
+ * provided when initiating a request. The start time is used to ensure that
+ * we discard old requests that were not fulfilled within a 2 second time
+ * window.
+ */
+struct ice_tx_tstamp {
+	struct sk_buff *skb;
+	unsigned long start;
+};
+
+/**
+ * struct ice_ptp_tx - Tracking structure for all Tx timestamp requests on a port
+ * @work: work function to handle processing of Tx timestamps
+ * @lock: lock to prevent concurrent write to in_use bitmap
+ * @tstamps: array of len to store outstanding requests
+ * @in_use: bitmap of len to indicate which slots are in use
+ * @quad: which quad the timestamps are captured in
+ * @quad_offset: offset into timestamp block of the quad to get the real index
+ * @len: length of the tstamps and in_use fields.
+ * @init: if true, the tracker is initialized;
+ */
+struct ice_ptp_tx {
+	struct kthread_work work;
+	spinlock_t lock; /* lock protecting in_use bitmap */
+	struct ice_tx_tstamp *tstamps;
+	unsigned long *in_use;
+	u8 quad;
+	u8 quad_offset;
+	u8 len;
+	u8 init;
+};
+
+/* Quad and port information for initializing timestamp blocks */
+#define INDEX_PER_QUAD			64
+#define INDEX_PER_PORT			(INDEX_PER_QUAD / ICE_PORTS_PER_QUAD)
+
+/**
+ * struct ice_ptp_port - data used to initialize an external port for PTP
+ *
+ * This structure contains PTP data related to the external ports. Currently
+ * it is used for tracking the Tx timestamps of a port. In the future this
+ * structure will also hold information for the E822 port initialization
+ * logic.
+ *
+ * @tx: Tx timestamp tracking for this port
+ */
+struct ice_ptp_port {
+	struct ice_ptp_tx tx;
+};
+
+/**
+ * struct ice_ptp - data used for integrating with CONFIG_PTP_1588_CLOCK
+ * @port: data for the PHY port initialization procedure
+ * @work: delayed work function for periodic tasks
+ * @cached_phc_time: a cached copy of the PHC time for timestamp extension
+ * @kworker: kwork thread for handling periodic work
+ * @info: structure defining PTP hardware capabilities
+ * @clock: pointer to registered PTP clock device
+ * @tstamp_config: hardware timestamping configuration
+ */
+struct ice_ptp {
+	struct ice_ptp_port port;
+	struct kthread_delayed_work work;
+	u64 cached_phc_time;
+	struct kthread_worker *kworker;
+	struct ptp_clock_info info;
+	struct ptp_clock *clock;
+	struct hwtstamp_config tstamp_config;
+};
+
+#define __ptp_port_to_ptp(p) \
+	container_of((p), struct ice_ptp, port)
+#define ptp_port_to_pf(p) \
+	container_of(__ptp_port_to_ptp((p)), struct ice_pf, ptp)
+
+#define __ptp_info_to_ptp(i) \
+	container_of((i), struct ice_ptp, info)
+#define ptp_info_to_pf(i) \
+	container_of(__ptp_info_to_ptp((i)), struct ice_pf, ptp)
+
+#define PTP_SHARED_CLK_IDX_VALID	BIT(31)
+#define ICE_PTP_TS_VALID		BIT(0)
+
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+struct ice_pf;
+int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr);
+int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr);
+int ice_get_ptp_clock_index(struct ice_pf *pf);
+
+s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb);
+void ice_ptp_process_ts(struct ice_pf *pf);
+
+void
+ice_ptp_rx_hwtstamp(struct ice_ring *rx_ring,
+		    union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb);
+void ice_ptp_init(struct ice_pf *pf);
+void ice_ptp_release(struct ice_pf *pf);
+#else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
+static inline int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int ice_get_ptp_clock_index(struct ice_pf *pf)
+{
+	return -1;
+}
+
+static inline s8
+ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb)
+{
+	return -1;
+}
+
+static inline void ice_ptp_process_ts(struct ice_pf *pf) { }
+static inline void
+ice_ptp_rx_hwtstamp(struct ice_ring *rx_ring,
+		    union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb) { }
+static inline void ice_ptp_init(struct ice_pf *pf) { }
+static inline void ice_ptp_release(struct ice_pf *pf) { }
+#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
+#endif /* _ICE_PTP_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
new file mode 100644
index 000000000000..3eca0e4eab0b
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -0,0 +1,651 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021, Intel Corporation. */
+
+#include "ice_common.h"
+#include "ice_ptp_hw.h"
+
+/* Low level functions for interacting with and managing the device clock used
+ * for the Precision Time Protocol.
+ *
+ * The ice hardware represents the current time using three registers:
+ *
+ *    GLTSYN_TIME_H     GLTSYN_TIME_L     GLTSYN_TIME_R
+ *  +---------------+ +---------------+ +---------------+
+ *  |    32 bits    | |    32 bits    | |    32 bits    |
+ *  +---------------+ +---------------+ +---------------+
+ *
+ * The registers are incremented every clock tick using a 40bit increment
+ * value defined over two registers:
+ *
+ *                     GLTSYN_INCVAL_H   GLTSYN_INCVAL_L
+ *                    +---------------+ +---------------+
+ *                    |    8 bit s    | |    32 bits    |
+ *                    +---------------+ +---------------+
+ *
+ * The increment value is added to the GLSTYN_TIME_R and GLSTYN_TIME_L
+ * registers every clock source tick. Depending on the specific device
+ * configuration, the clock source frequency could be one of a number of
+ * values.
+ *
+ * For E810 devices, the increment frequency is 812.5 MHz
+ *
+ * The hardware captures timestamps in the PHY for incoming packets, and for
+ * outgoing packets on request. To support this, the PHY maintains a timer
+ * that matches the lower 64 bits of the global source timer.
+ *
+ * In order to ensure that the PHY timers and the source timer are equivalent,
+ * shadow registers are used to prepare the desired initial values. A special
+ * sync command is issued to trigger copying from the shadow registers into
+ * the appropriate source and PHY registers simultaneously.
+ */
+
+/**
+ * ice_get_ptp_src_clock_index - determine source clock index
+ * @hw: pointer to HW struct
+ *
+ * Determine the source clock index currently in use, based on device
+ * capabilities reported during initialization.
+ */
+u8 ice_get_ptp_src_clock_index(struct ice_hw *hw)
+{
+	return hw->func_caps.ts_func_info.tmr_index_assoc;
+}
+
+/* E810 functions
+ *
+ * The following functions operate on the E810 series devices which use
+ * a separate external PHY.
+ */
+
+/**
+ * ice_read_phy_reg_e810 - Read register from external PHY on E810
+ * @hw: pointer to the HW struct
+ * @addr: the address to read from
+ * @val: On return, the value read from the PHY
+ *
+ * Read a register from the external PHY on the E810 device.
+ */
+static int ice_read_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 *val)
+{
+	struct ice_sbq_msg_input msg = {0};
+	int status;
+
+	msg.msg_addr_low = lower_16_bits(addr);
+	msg.msg_addr_high = upper_16_bits(addr);
+	msg.opcode = ice_sbq_msg_rd;
+	msg.dest_dev = rmn_0;
+
+	status = ice_sbq_rw_reg(hw, &msg);
+	if (status) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, status %d\n",
+			  status);
+		return status;
+	}
+
+	*val = msg.data;
+
+	return 0;
+}
+
+/**
+ * ice_write_phy_reg_e810 - Write register on external PHY on E810
+ * @hw: pointer to the HW struct
+ * @addr: the address to writem to
+ * @val: the value to write to the PHY
+ *
+ * Write a value to a register of the external PHY on the E810 device.
+ */
+static int ice_write_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 val)
+{
+	struct ice_sbq_msg_input msg = {0};
+	int status;
+
+	msg.msg_addr_low = lower_16_bits(addr);
+	msg.msg_addr_high = upper_16_bits(addr);
+	msg.opcode = ice_sbq_msg_wr;
+	msg.dest_dev = rmn_0;
+	msg.data = val;
+
+	status = ice_sbq_rw_reg(hw, &msg);
+	if (status) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, status %d\n",
+			  status);
+		return status;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_read_phy_tstamp_e810 - Read a PHY timestamp out of the external PHY
+ * @hw: pointer to the HW struct
+ * @lport: the lport to read from
+ * @idx: the timestamp index to read
+ * @tstamp: on return, the 40bit timestamp value
+ *
+ * Read a 40bit timestamp value out of the timestamp block of the external PHY
+ * on the E810 device.
+ */
+static int
+ice_read_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx, u64 *tstamp)
+{
+	u32 lo_addr, hi_addr, lo, hi;
+	int status;
+
+	lo_addr = TS_EXT(LOW_TX_MEMORY_BANK_START, lport, idx);
+	hi_addr = TS_EXT(HIGH_TX_MEMORY_BANK_START, lport, idx);
+
+	status = ice_read_phy_reg_e810(hw, lo_addr, &lo);
+	if (status) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read low PTP timestamp register, status %d\n",
+			  status);
+		return status;
+	}
+
+	status = ice_read_phy_reg_e810(hw, hi_addr, &hi);
+	if (status) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read high PTP timestamp register, status %d\n",
+			  status);
+		return status;
+	}
+
+	/* For E810 devices, the timestamp is reported with the lower 32 bits
+	 * in the low register, and the upper 8 bits in the high register.
+	 */
+	*tstamp = ((u64)hi) << TS_HIGH_S | ((u64)lo & TS_LOW_M);
+
+	return 0;
+}
+
+/**
+ * ice_clear_phy_tstamp_e810 - Clear a timestamp from the external PHY
+ * @hw: pointer to the HW struct
+ * @lport: the lport to read from
+ * @idx: the timestamp index to reset
+ *
+ * Clear a timestamp, resetting its valid bit, from the timestamp block of the
+ * external PHY on the E810 device.
+ */
+static int ice_clear_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx)
+{
+	u32 lo_addr, hi_addr;
+	int status;
+
+	lo_addr = TS_EXT(LOW_TX_MEMORY_BANK_START, lport, idx);
+	hi_addr = TS_EXT(HIGH_TX_MEMORY_BANK_START, lport, idx);
+
+	status = ice_write_phy_reg_e810(hw, lo_addr, 0);
+	if (status) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to clear low PTP timestamp register, status %d\n",
+			  status);
+		return status;
+	}
+
+	status = ice_write_phy_reg_e810(hw, hi_addr, 0);
+	if (status) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to clear high PTP timestamp register, status %d\n",
+			  status);
+		return status;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_ptp_init_phy_e810 - Enable PTP function on the external PHY
+ * @hw: pointer to HW struct
+ *
+ * Enable the timesync PTP functionality for the external PHY connected to
+ * this function.
+ */
+int ice_ptp_init_phy_e810(struct ice_hw *hw)
+{
+	int status;
+	u8 tmr_idx;
+
+	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+	status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_ENA(tmr_idx),
+					GLTSYN_ENA_TSYN_ENA_M);
+	if (status)
+		ice_debug(hw, ICE_DBG_PTP, "PTP failed in ena_phy_time_syn %d\n",
+			  status);
+
+	return status;
+}
+
+/**
+ * ice_ptp_prep_phy_time_e810 - Prepare PHY port with initial time
+ * @hw: Board private structure
+ * @time: Time to initialize the PHY port clock to
+ *
+ * Program the PHY port ETH_GLTSYN_SHTIME registers in preparation setting the
+ * initial clock time. The time will not actually be programmed until the
+ * driver issues an INIT_TIME command.
+ *
+ * The time value is the upper 32 bits of the PHY timer, usually in units of
+ * nominal nanoseconds.
+ */
+static int ice_ptp_prep_phy_time_e810(struct ice_hw *hw, u32 time)
+{
+	int status;
+	u8 tmr_idx;
+
+	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+	status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHTIME_0(tmr_idx), 0);
+	if (status) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write SHTIME_0, status %d\n",
+			  status);
+		return status;
+	}
+
+	status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHTIME_L(tmr_idx), time);
+	if (status) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write SHTIME_L, status %d\n",
+			  status);
+		return status;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_ptp_prep_phy_adj_e810 - Prep PHY port for a time adjustment
+ * @hw: pointer to HW struct
+ * @adj: adjustment value to program
+ *
+ * Prepare the PHY port for an atomic adjustment by programming the PHY
+ * ETH_GLTSYN_SHADJ_L and ETH_GLTSYN_SHADJ_H registers. The actual adjustment
+ * is completed by issuing an ADJ_TIME sync command.
+ *
+ * The adjustment value only contains the portion used for the upper 32bits of
+ * the PHY timer, usually in units of nominal nanoseconds. Negative
+ * adjustments are supported using 2s complement arithmetic.
+ */
+static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj)
+{
+	int status;
+	u8 tmr_idx;
+
+	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+
+	/* Adjustments are represented as signed 2's complement values in
+	 * nanoseconds. Sub-nanosecond adjustment is not supported.
+	 */
+	status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHADJ_L(tmr_idx), 0);
+	if (status) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write adj to PHY SHADJ_L, status %d\n",
+			  status);
+		return status;
+	}
+
+	status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHADJ_H(tmr_idx), adj);
+	if (status) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write adj to PHY SHADJ_H, status %d\n",
+			  status);
+		return status;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_ptp_prep_phy_incval_e810 - Prep PHY port increment value change
+ * @hw: pointer to HW struct
+ * @incval: The new 40bit increment value to prepare
+ *
+ * Prepare the PHY port for a new increment value by programming the PHY
+ * ETH_GLTSYN_SHADJ_L and ETH_GLTSYN_SHADJ_H registers. The actual change is
+ * completed by issuing an INIT_INCVAL command.
+ */
+static int ice_ptp_prep_phy_incval_e810(struct ice_hw *hw, u64 incval)
+{
+	u32 high, low;
+	int status;
+	u8 tmr_idx;
+
+	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+	low = lower_32_bits(incval);
+	high = upper_32_bits(incval);
+
+	status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHADJ_L(tmr_idx), low);
+	if (status) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write incval to PHY SHADJ_L, status %d\n",
+			  status);
+		return status;
+	}
+
+	status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHADJ_H(tmr_idx), high);
+	if (status) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write incval PHY SHADJ_H, status %d\n",
+			  status);
+		return status;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_ptp_port_cmd_e810 - Prepare all external PHYs for a timer command
+ * @hw: pointer to HW struct
+ * @cmd: Command to be sent to the port
+ *
+ * Prepare the external PHYs connected to this device for a timer sync
+ * command.
+ */
+static int ice_ptp_port_cmd_e810(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
+{
+	u32 cmd_val, val;
+	int status;
+
+	switch (cmd) {
+	case INIT_TIME:
+		cmd_val = GLTSYN_CMD_INIT_TIME;
+		break;
+	case INIT_INCVAL:
+		cmd_val = GLTSYN_CMD_INIT_INCVAL;
+		break;
+	case ADJ_TIME:
+		cmd_val = GLTSYN_CMD_ADJ_TIME;
+		break;
+	case READ_TIME:
+		cmd_val = GLTSYN_CMD_READ_TIME;
+		break;
+	case ADJ_TIME_AT_TIME:
+		cmd_val = GLTSYN_CMD_ADJ_INIT_TIME;
+		break;
+	}
+
+	/* Read, modify, write */
+	status = ice_read_phy_reg_e810(hw, ETH_GLTSYN_CMD, &val);
+	if (status) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to read GLTSYN_CMD, status %d\n", status);
+		return status;
+	}
+
+	/* Modify necessary bits only and perform write */
+	val &= ~TS_CMD_MASK_E810;
+	val |= cmd_val;
+
+	status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_CMD, val);
+	if (status) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to write back GLTSYN_CMD, status %d\n", status);
+		return status;
+	}
+
+	return 0;
+}
+
+/* Device agnostic functions
+ *
+ * The following functions implement useful behavior to hide the differences
+ * between E810 and other devices. They call the device-specific
+ * implementations where necessary.
+ *
+ * Currently, the driver only supports E810, but future work will enable
+ * support for E822-based devices.
+ */
+
+/**
+ * ice_ptp_lock - Acquire PTP global semaphore register lock
+ * @hw: pointer to the HW struct
+ *
+ * Acquire the global PTP hardware semaphore lock. Returns true if the lock
+ * was acquired, false otherwise.
+ *
+ * The PFTSYN_SEM register sets the busy bit on read, returning the previous
+ * value. If software sees the busy bit cleared, this means that this function
+ * acquired the lock (and the busy bit is now set). If software sees the busy
+ * bit set, it means that another function acquired the lock.
+ *
+ * Software must clear the busy bit with a write to release the lock for other
+ * functions when done.
+ */
+bool ice_ptp_lock(struct ice_hw *hw)
+{
+	u32 hw_lock;
+	int i;
+
+#define MAX_TRIES 5
+
+	for (i = 0; i < MAX_TRIES; i++) {
+		hw_lock = rd32(hw, PFTSYN_SEM + (PFTSYN_SEM_BYTES * hw->pf_id));
+		hw_lock = hw_lock & PFTSYN_SEM_BUSY_M;
+		if (!hw_lock)
+			break;
+
+		/* Somebody is holding the lock */
+		usleep_range(10000, 20000);
+	}
+
+	return !hw_lock;
+}
+
+/**
+ * ice_ptp_unlock - Release PTP global semaphore register lock
+ * @hw: pointer to the HW struct
+ *
+ * Release the global PTP hardware semaphore lock. This is done by writing to
+ * the PFTSYN_SEM register.
+ */
+void ice_ptp_unlock(struct ice_hw *hw)
+{
+	wr32(hw, PFTSYN_SEM + (PFTSYN_SEM_BYTES * hw->pf_id), 0);
+}
+
+/**
+ * ice_ptp_src_cmd - Prepare source timer for a timer command
+ * @hw: pointer to HW structure
+ * @cmd: Timer command
+ *
+ * Prepare the source timer for an upcoming timer sync command.
+ */
+static void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
+{
+	u32 cmd_val;
+	u8 tmr_idx;
+
+	tmr_idx = ice_get_ptp_src_clock_index(hw);
+	cmd_val = tmr_idx << SEL_CPK_SRC;
+
+	switch (cmd) {
+	case INIT_TIME:
+		cmd_val |= GLTSYN_CMD_INIT_TIME;
+		break;
+	case INIT_INCVAL:
+		cmd_val |= GLTSYN_CMD_INIT_INCVAL;
+		break;
+	case ADJ_TIME:
+		cmd_val |= GLTSYN_CMD_ADJ_TIME;
+		break;
+	case ADJ_TIME_AT_TIME:
+		cmd_val |= GLTSYN_CMD_ADJ_INIT_TIME;
+		break;
+	case READ_TIME:
+		cmd_val |= GLTSYN_CMD_READ_TIME;
+		break;
+	}
+
+	wr32(hw, GLTSYN_CMD, cmd_val);
+}
+
+/**
+ * ice_ptp_tmr_cmd - Prepare and trigger a timer sync command
+ * @hw: pointer to HW struct
+ * @cmd: the command to issue
+ *
+ * Prepare the source timer and PHY timers and then trigger the requested
+ * command. This causes the shadow registers previously written in preparation
+ * for the command to be synchronously applied to both the source and PHY
+ * timers.
+ */
+static int ice_ptp_tmr_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
+{
+	int status;
+
+	/* First, prepare the source timer */
+	ice_ptp_src_cmd(hw, cmd);
+
+	/* Next, prepare the ports */
+	status = ice_ptp_port_cmd_e810(hw, cmd);
+	if (status) {
+		ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY ports for timer command %u, status %d\n",
+			  cmd, status);
+		return status;
+	}
+
+	/* Write the sync command register to drive both source and PHY timer commands
+	 * synchronously
+	 */
+	wr32(hw, GLTSYN_CMD_SYNC, SYNC_EXEC_CMD);
+
+	return 0;
+}
+
+/**
+ * ice_ptp_init_time - Initialize device time to provided value
+ * @hw: pointer to HW struct
+ * @time: 64bits of time (GLTSYN_TIME_L and GLTSYN_TIME_H)
+ *
+ * Initialize the device to the specified time provided. This requires a three
+ * step process:
+ *
+ * 1) write the new init time to the source timer shadow registers
+ * 2) write the new init time to the PHY timer shadow registers
+ * 3) issue an init_time timer command to synchronously switch both the source
+ *    and port timers to the new init time value at the next clock cycle.
+ */
+int ice_ptp_init_time(struct ice_hw *hw, u64 time)
+{
+	int status;
+	u8 tmr_idx;
+
+	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+
+	/* Source timers */
+	wr32(hw, GLTSYN_SHTIME_L(tmr_idx), lower_32_bits(time));
+	wr32(hw, GLTSYN_SHTIME_H(tmr_idx), upper_32_bits(time));
+	wr32(hw, GLTSYN_SHTIME_0(tmr_idx), 0);
+
+	/* PHY timers */
+	/* Fill Rx and Tx ports and send msg to PHY */
+	status = ice_ptp_prep_phy_time_e810(hw, time & 0xFFFFFFFF);
+	if (status)
+		return status;
+
+	return ice_ptp_tmr_cmd(hw, INIT_TIME);
+}
+
+/**
+ * ice_ptp_write_incval - Program PHC with new increment value
+ * @hw: pointer to HW struct
+ * @incval: Source timer increment value per clock cycle
+ *
+ * Program the PHC with a new increment value. This requires a three-step
+ * process:
+ *
+ * 1) Write the increment value to the source timer shadow registers
+ * 2) Write the increment value to the PHY timer shadow registers
+ * 3) Issue an INIT_INCVAL timer command to synchronously switch both the
+ *    source and port timers to the new increment value at the next clock
+ *    cycle.
+ */
+int ice_ptp_write_incval(struct ice_hw *hw, u64 incval)
+{
+	int status;
+	u8 tmr_idx;
+
+	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+
+	/* Shadow Adjust */
+	wr32(hw, GLTSYN_SHADJ_L(tmr_idx), lower_32_bits(incval));
+	wr32(hw, GLTSYN_SHADJ_H(tmr_idx), upper_32_bits(incval));
+
+	status = ice_ptp_prep_phy_incval_e810(hw, incval);
+	if (status)
+		return status;
+
+	return ice_ptp_tmr_cmd(hw, INIT_INCVAL);
+}
+
+/**
+ * ice_ptp_write_incval_locked - Program new incval while holding semaphore
+ * @hw: pointer to HW struct
+ * @incval: Source timer increment value per clock cycle
+ *
+ * Program a new PHC incval while holding the PTP semaphore.
+ */
+int ice_ptp_write_incval_locked(struct ice_hw *hw, u64 incval)
+{
+	int status;
+
+	if (!ice_ptp_lock(hw))
+		return -EBUSY;
+
+	status = ice_ptp_write_incval(hw, incval);
+
+	ice_ptp_unlock(hw);
+
+	return status;
+}
+
+/**
+ * ice_ptp_adj_clock - Adjust PHC clock time atomically
+ * @hw: pointer to HW struct
+ * @adj: Adjustment in nanoseconds
+ *
+ * Perform an atomic adjustment of the PHC time by the specified number of
+ * nanoseconds. This requires a three-step process:
+ *
+ * 1) Write the adjustment to the source timer shadow registers
+ * 2) Write the adjustment to the PHY timer shadow registers
+ * 3) Issue an ADJ_TIME timer command to synchronously apply the adjustment to
+ *    both the source and port timers at the next clock cycle.
+ */
+int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj)
+{
+	int status;
+	u8 tmr_idx;
+
+	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+
+	/* Write the desired clock adjustment into the GLTSYN_SHADJ register.
+	 * For an ADJ_TIME command, this set of registers represents the value
+	 * to add to the clock time. It supports subtraction by interpreting
+	 * the value as a 2's complement integer.
+	 */
+	wr32(hw, GLTSYN_SHADJ_L(tmr_idx), 0);
+	wr32(hw, GLTSYN_SHADJ_H(tmr_idx), adj);
+
+	status = ice_ptp_prep_phy_adj_e810(hw, adj);
+	if (status)
+		return status;
+
+	return ice_ptp_tmr_cmd(hw, ADJ_TIME);
+}
+
+/**
+ * ice_read_phy_tstamp - Read a PHY timestamp from the timestamo block
+ * @hw: pointer to the HW struct
+ * @block: the block to read from
+ * @idx: the timestamp index to read
+ * @tstamp: on return, the 40bit timestamp value
+ *
+ * Read a 40bit timestamp value out of the timestamp block.
+ */
+int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp)
+{
+	return ice_read_phy_tstamp_e810(hw, block, idx, tstamp);
+}
+
+/**
+ * ice_clear_phy_tstamp - Clear a timestamp from the timestamp block
+ * @hw: pointer to the HW struct
+ * @block: the block to read from
+ * @idx: the timestamp index to reset
+ *
+ * Clear a timestamp, resetting its valid bit, from the timestamp block.
+ */
+int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx)
+{
+	return ice_clear_phy_tstamp_e810(hw, block, idx);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
new file mode 100644
index 000000000000..55a414e87018
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021, Intel Corporation. */
+
+#ifndef _ICE_PTP_HW_H_
+#define _ICE_PTP_HW_H_
+
+enum ice_ptp_tmr_cmd {
+	INIT_TIME,
+	INIT_INCVAL,
+	ADJ_TIME,
+	ADJ_TIME_AT_TIME,
+	READ_TIME
+};
+
+/* Increment value to generate nanoseconds in the GLTSYN_TIME_L register for
+ * the E810 devices. Based off of a PLL with an 812.5 MHz frequency.
+ */
+#define ICE_PTP_NOMINAL_INCVAL_E810 0x13b13b13bULL
+
+/* Device agnostic functions */
+u8 ice_get_ptp_src_clock_index(struct ice_hw *hw);
+bool ice_ptp_lock(struct ice_hw *hw);
+void ice_ptp_unlock(struct ice_hw *hw);
+int ice_ptp_init_time(struct ice_hw *hw, u64 time);
+int ice_ptp_write_incval(struct ice_hw *hw, u64 incval);
+int ice_ptp_write_incval_locked(struct ice_hw *hw, u64 incval);
+int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj);
+int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp);
+int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx);
+
+/* E810 family functions */
+int ice_ptp_init_phy_e810(struct ice_hw *hw);
+
+#define PFTSYN_SEM_BYTES	4
+
+/* PHY timer commands */
+#define SEL_CPK_SRC	8
+
+/* Time Sync command Definitions */
+#define GLTSYN_CMD_INIT_TIME		BIT(0)
+#define GLTSYN_CMD_INIT_INCVAL		BIT(1)
+#define GLTSYN_CMD_ADJ_TIME		BIT(2)
+#define GLTSYN_CMD_ADJ_INIT_TIME	(BIT(2) | BIT(3))
+#define GLTSYN_CMD_READ_TIME		BIT(7)
+
+#define TS_CMD_MASK_E810		0xFF
+#define SYNC_EXEC_CMD			0x3
+
+/* E810 timesync enable register */
+#define ETH_GLTSYN_ENA(_i)		(0x03000348 + ((_i) * 4))
+
+/* E810 shadow init time registers */
+#define ETH_GLTSYN_SHTIME_0(i)		(0x03000368 + ((i) * 32))
+#define ETH_GLTSYN_SHTIME_L(i)		(0x0300036C + ((i) * 32))
+
+/* E810 shadow time adjust registers */
+#define ETH_GLTSYN_SHADJ_L(_i)		(0x03000378 + ((_i) * 32))
+#define ETH_GLTSYN_SHADJ_H(_i)		(0x0300037C + ((_i) * 32))
+
+/* E810 timer command register */
+#define ETH_GLTSYN_CMD			0x03000344
+
+/* Source timer incval macros */
+#define INCVAL_HIGH_M			0xFF
+
+/* Timestamp block macros */
+#define TS_LOW_M			0xFFFFFFFF
+#define TS_HIGH_S			32
+
+#define BYTES_PER_IDX_ADDR_L_U		8
+
+/* External PHY timestamp address */
+#define TS_EXT(a, port, idx) ((a) + (0x1000 * (port)) +			\
+				 ((idx) * BYTES_PER_IDX_ADDR_L_U))
+
+#define LOW_TX_MEMORY_BANK_START	0x03090000
+#define HIGH_TX_MEMORY_BANK_START	0x03090004
+
+#endif /* _ICE_PTP_HW_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h
new file mode 100644
index 000000000000..ead75fe2bcda
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h
@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021, Intel Corporation. */
+
+#ifndef _ICE_SBQ_CMD_H_
+#define _ICE_SBQ_CMD_H_
+
+/* This header file defines the Sideband Queue commands, error codes and
+ * descriptor format. It is shared between Firmware and Software.
+ */
+
+/* Sideband Queue command structure and opcodes */
+enum ice_sbq_opc {
+	/* Sideband Queue commands */
+	ice_sbq_opc_neigh_dev_req			= 0x0C00,
+	ice_sbq_opc_neigh_dev_ev			= 0x0C01
+};
+
+/* Sideband Queue descriptor. Indirect command
+ * and non posted
+ */
+struct ice_sbq_cmd_desc {
+	__le16 flags;
+	__le16 opcode;
+	__le16 datalen;
+	__le16 cmd_retval;
+
+	/* Opaque message data */
+	__le32 cookie_high;
+	__le32 cookie_low;
+
+	union {
+		__le16 cmd_len;
+		__le16 cmpl_len;
+	} param0;
+
+	u8 reserved[6];
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+struct ice_sbq_evt_desc {
+	__le16 flags;
+	__le16 opcode;
+	__le16 datalen;
+	__le16 cmd_retval;
+	u8 data[24];
+};
+
+enum ice_sbq_msg_dev {
+	rmn_0	= 0x02,
+	rmn_1	= 0x03,
+	rmn_2	= 0x04,
+	cgu	= 0x06
+};
+
+enum ice_sbq_msg_opcode {
+	ice_sbq_msg_rd	= 0x00,
+	ice_sbq_msg_wr	= 0x01
+};
+
+#define ICE_SBQ_MSG_FLAGS	0x40
+#define ICE_SBQ_MSG_SBE_FBE	0x0F
+
+struct ice_sbq_msg_req {
+	u8 dest_dev;
+	u8 src_dev;
+	u8 opcode;
+	u8 flags;
+	u8 sbe_fbe;
+	u8 func_id;
+	__le16 msg_addr_low;
+	__le32 msg_addr_high;
+	__le32 data;
+};
+
+struct ice_sbq_msg_cmpl {
+	u8 dest_dev;
+	u8 src_dev;
+	u8 opcode;
+	u8 flags;
+	__le32 data;
+};
+
+/* Internal struct */
+struct ice_sbq_msg_input {
+	u8 dest_dev;
+	u8 opcode;
+	u16 msg_addr_low;
+	u32 msg_addr_high;
+	u32 data;
+};
+#endif /* _ICE_SBQ_CMD_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index 2f097637e405..a17e24e54cf3 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -596,6 +596,50 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs)
 }
 
 /**
+ * ice_alloc_rdma_q_ctx - allocate RDMA queue contexts for the given VSI and TC
+ * @hw: pointer to the HW struct
+ * @vsi_handle: VSI handle
+ * @tc: TC number
+ * @new_numqs: number of queues
+ */
+static enum ice_status
+ice_alloc_rdma_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs)
+{
+	struct ice_vsi_ctx *vsi_ctx;
+	struct ice_q_ctx *q_ctx;
+
+	vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle);
+	if (!vsi_ctx)
+		return ICE_ERR_PARAM;
+	/* allocate RDMA queue contexts */
+	if (!vsi_ctx->rdma_q_ctx[tc]) {
+		vsi_ctx->rdma_q_ctx[tc] = devm_kcalloc(ice_hw_to_dev(hw),
+						       new_numqs,
+						       sizeof(*q_ctx),
+						       GFP_KERNEL);
+		if (!vsi_ctx->rdma_q_ctx[tc])
+			return ICE_ERR_NO_MEMORY;
+		vsi_ctx->num_rdma_q_entries[tc] = new_numqs;
+		return 0;
+	}
+	/* num queues are increased, update the queue contexts */
+	if (new_numqs > vsi_ctx->num_rdma_q_entries[tc]) {
+		u16 prev_num = vsi_ctx->num_rdma_q_entries[tc];
+
+		q_ctx = devm_kcalloc(ice_hw_to_dev(hw), new_numqs,
+				     sizeof(*q_ctx), GFP_KERNEL);
+		if (!q_ctx)
+			return ICE_ERR_NO_MEMORY;
+		memcpy(q_ctx, vsi_ctx->rdma_q_ctx[tc],
+		       prev_num * sizeof(*q_ctx));
+		devm_kfree(ice_hw_to_dev(hw), vsi_ctx->rdma_q_ctx[tc]);
+		vsi_ctx->rdma_q_ctx[tc] = q_ctx;
+		vsi_ctx->num_rdma_q_entries[tc] = new_numqs;
+	}
+	return 0;
+}
+
+/**
  * ice_aq_rl_profile - performs a rate limiting task
  * @hw: pointer to the HW struct
  * @opcode: opcode for add, query, or remove profile(s)
@@ -1774,13 +1818,22 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
 	if (!vsi_ctx)
 		return ICE_ERR_PARAM;
 
-	prev_numqs = vsi_ctx->sched.max_lanq[tc];
+	if (owner == ICE_SCHED_NODE_OWNER_LAN)
+		prev_numqs = vsi_ctx->sched.max_lanq[tc];
+	else
+		prev_numqs = vsi_ctx->sched.max_rdmaq[tc];
 	/* num queues are not changed or less than the previous number */
 	if (new_numqs <= prev_numqs)
 		return status;
-	status = ice_alloc_lan_q_ctx(hw, vsi_handle, tc, new_numqs);
-	if (status)
-		return status;
+	if (owner == ICE_SCHED_NODE_OWNER_LAN) {
+		status = ice_alloc_lan_q_ctx(hw, vsi_handle, tc, new_numqs);
+		if (status)
+			return status;
+	} else {
+		status = ice_alloc_rdma_q_ctx(hw, vsi_handle, tc, new_numqs);
+		if (status)
+			return status;
+	}
 
 	if (new_numqs)
 		ice_sched_calc_vsi_child_nodes(hw, new_numqs, new_num_nodes);
@@ -1795,7 +1848,10 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
 					       new_num_nodes, owner);
 	if (status)
 		return status;
-	vsi_ctx->sched.max_lanq[tc] = new_numqs;
+	if (owner == ICE_SCHED_NODE_OWNER_LAN)
+		vsi_ctx->sched.max_lanq[tc] = new_numqs;
+	else
+		vsi_ctx->sched.max_rdmaq[tc] = new_numqs;
 
 	return 0;
 }
@@ -1861,6 +1917,7 @@ ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs,
 		 * recreate the child nodes all the time in these cases.
 		 */
 		vsi_ctx->sched.max_lanq[tc] = 0;
+		vsi_ctx->sched.max_rdmaq[tc] = 0;
 	}
 
 	/* update the VSI child nodes */
@@ -1990,6 +2047,8 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner)
 		}
 		if (owner == ICE_SCHED_NODE_OWNER_LAN)
 			vsi_ctx->sched.max_lanq[i] = 0;
+		else
+			vsi_ctx->sched.max_rdmaq[i] = 0;
 	}
 	status = 0;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 357d3073d814..3b6c1420aa7b 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2018, Intel Corporation. */
 
+#include "ice_lib.h"
 #include "ice_switch.h"
 
 #define ICE_ETH_DA_OFFSET		0
@@ -302,6 +303,10 @@ static void ice_clear_vsi_q_ctx(struct ice_hw *hw, u16 vsi_handle)
 			devm_kfree(ice_hw_to_dev(hw), vsi->lan_q_ctx[i]);
 			vsi->lan_q_ctx[i] = NULL;
 		}
+		if (vsi->rdma_q_ctx[i]) {
+			devm_kfree(ice_hw_to_dev(hw), vsi->rdma_q_ctx[i]);
+			vsi->rdma_q_ctx[i] = NULL;
+		}
 	}
 }
 
@@ -423,6 +428,29 @@ ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx,
 }
 
 /**
+ * ice_cfg_rdma_fltr - enable/disable RDMA filtering on VSI
+ * @hw: pointer to HW struct
+ * @vsi_handle: VSI SW index
+ * @enable: boolean for enable/disable
+ */
+int
+ice_cfg_rdma_fltr(struct ice_hw *hw, u16 vsi_handle, bool enable)
+{
+	struct ice_vsi_ctx *ctx;
+
+	ctx = ice_get_vsi_ctx(hw, vsi_handle);
+	if (!ctx)
+		return -EIO;
+
+	if (enable)
+		ctx->info.q_opt_flags |= ICE_AQ_VSI_Q_OPT_PE_FLTR_EN;
+	else
+		ctx->info.q_opt_flags &= ~ICE_AQ_VSI_Q_OPT_PE_FLTR_EN;
+
+	return ice_status_to_errno(ice_update_vsi(hw, vsi_handle, ctx, NULL));
+}
+
+/**
  * ice_aq_alloc_free_vsi_list
  * @hw: pointer to the HW struct
  * @vsi_list_id: VSI list ID returned or used for lookup
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h
index 8b4f9d35c860..c5db8d56133f 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.h
+++ b/drivers/net/ethernet/intel/ice/ice_switch.h
@@ -26,6 +26,8 @@ struct ice_vsi_ctx {
 	u8 vf_num;
 	u16 num_lan_q_entries[ICE_MAX_TRAFFIC_CLASS];
 	struct ice_q_ctx *lan_q_ctx[ICE_MAX_TRAFFIC_CLASS];
+	u16 num_rdma_q_entries[ICE_MAX_TRAFFIC_CLASS];
+	struct ice_q_ctx *rdma_q_ctx[ICE_MAX_TRAFFIC_CLASS];
 };
 
 enum ice_sw_fwd_act_type {
@@ -223,6 +225,8 @@ enum ice_status
 ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list);
 enum ice_status
 ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list);
+int
+ice_cfg_rdma_fltr(struct ice_hw *hw, u16 vsi_handle, bool enable);
 void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle);
 enum ice_status
 ice_add_vlan(struct ice_hw *hw, struct list_head *m_list);
@@ -243,7 +247,6 @@ ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
 
 enum ice_status ice_init_def_sw_recp(struct ice_hw *hw);
 u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle);
-bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle);
 
 enum ice_status ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle);
 void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 04748aa4c7c8..e9e9edb32c6f 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1082,7 +1082,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		u16 stat_err_bits;
 		int rx_buf_pgcnt;
 		u16 vlan_tag = 0;
-		u8 rx_ptype;
+		u16 rx_ptype;
 
 		/* get the Rx desc from Rx ring based on 'next_to_clean' */
 		rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean);
@@ -2137,6 +2137,41 @@ static bool ice_chk_linearize(struct sk_buff *skb, unsigned int count)
 }
 
 /**
+ * ice_tstamp - set up context descriptor for hardware timestamp
+ * @tx_ring: pointer to the Tx ring to send buffer on
+ * @skb: pointer to the SKB we're sending
+ * @first: Tx buffer
+ * @off: Tx offload parameters
+ */
+static void
+ice_tstamp(struct ice_ring *tx_ring, struct sk_buff *skb,
+	   struct ice_tx_buf *first, struct ice_tx_offload_params *off)
+{
+	s8 idx;
+
+	/* only timestamp the outbound packet if the user has requested it */
+	if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
+		return;
+
+	if (!tx_ring->ptp_tx)
+		return;
+
+	/* Tx timestamps cannot be sampled when doing TSO */
+	if (first->tx_flags & ICE_TX_FLAGS_TSO)
+		return;
+
+	/* Grab an open timestamp slot */
+	idx = ice_ptp_request_ts(tx_ring->tx_tstamps, skb);
+	if (idx < 0)
+		return;
+
+	off->cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |
+			     (ICE_TX_CTX_DESC_TSYN << ICE_TXD_CTX_QW1_CMD_S) |
+			     ((u64)idx << ICE_TXD_CTX_QW1_TSO_LEN_S));
+	first->tx_flags |= ICE_TX_FLAGS_TSYN;
+}
+
+/**
  * ice_xmit_frame_ring - Sends buffer on Tx ring
  * @skb: send buffer
  * @tx_ring: ring to send buffer on
@@ -2205,6 +2240,8 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
 					ICE_TX_CTX_DESC_SWTCH_UPLINK <<
 					ICE_TXD_CTX_QW1_CMD_S);
 
+	ice_tstamp(tx_ring, skb, first, &offload);
+
 	if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) {
 		struct ice_tx_ctx_desc *cdesc;
 		u16 i = tx_ring->next_to_use;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index c5a92ac787d6..1e46e80f3d6f 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -118,6 +118,7 @@ static inline int ice_skb_pad(void)
  * freed instead of returned like skb packets.
  */
 #define ICE_TX_FLAGS_DUMMY_PKT	BIT(3)
+#define ICE_TX_FLAGS_TSYN	BIT(4)
 #define ICE_TX_FLAGS_IPV4	BIT(5)
 #define ICE_TX_FLAGS_IPV6	BIT(6)
 #define ICE_TX_FLAGS_TUNNEL	BIT(7)
@@ -311,6 +312,10 @@ struct ice_ring {
 	u32 txq_teid;			/* Added Tx queue TEID */
 	u16 rx_buf_len;
 	u8 dcb_tc;			/* Traffic class of ring */
+	struct ice_ptp_tx *tx_tstamps;
+	u64 cached_phctime;
+	u8 ptp_rx:1;
+	u8 ptp_tx:1;
 } ____cacheline_internodealigned_in_smp;
 
 static inline bool ice_ring_uses_build_skb(struct ice_ring *ring)
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 207f6ee3a7f6..171397dcf00a 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -38,10 +38,23 @@ void ice_release_rx_desc(struct ice_ring *rx_ring, u16 val)
  * ice_ptype_to_htype - get a hash type
  * @ptype: the ptype value from the descriptor
  *
- * Returns a hash type to be used by skb_set_hash
+ * Returns appropriate hash type (such as PKT_HASH_TYPE_L2/L3/L4) to be used by
+ * skb_set_hash based on PTYPE as parsed by HW Rx pipeline and is part of
+ * Rx desc.
  */
-static enum pkt_hash_types ice_ptype_to_htype(u8 __always_unused ptype)
+static enum pkt_hash_types ice_ptype_to_htype(u16 ptype)
 {
+	struct ice_rx_ptype_decoded decoded = ice_decode_rx_desc_ptype(ptype);
+
+	if (!decoded.known)
+		return PKT_HASH_TYPE_NONE;
+	if (decoded.payload_layer == ICE_RX_PTYPE_PAYLOAD_LAYER_PAY4)
+		return PKT_HASH_TYPE_L4;
+	if (decoded.payload_layer == ICE_RX_PTYPE_PAYLOAD_LAYER_PAY3)
+		return PKT_HASH_TYPE_L3;
+	if (decoded.outer_ip == ICE_RX_PTYPE_OUTER_L2)
+		return PKT_HASH_TYPE_L2;
+
 	return PKT_HASH_TYPE_NONE;
 }
 
@@ -54,7 +67,7 @@ static enum pkt_hash_types ice_ptype_to_htype(u8 __always_unused ptype)
  */
 static void
 ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc,
-	    struct sk_buff *skb, u8 rx_ptype)
+	    struct sk_buff *skb, u16 rx_ptype)
 {
 	struct ice_32b_rx_flex_desc_nic *nic_mdid;
 	u32 hash;
@@ -81,7 +94,7 @@ ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc,
  */
 static void
 ice_rx_csum(struct ice_ring *ring, struct sk_buff *skb,
-	    union ice_32b_rx_flex_desc *rx_desc, u8 ptype)
+	    union ice_32b_rx_flex_desc *rx_desc, u16 ptype)
 {
 	struct ice_rx_ptype_decoded decoded;
 	u16 rx_status0, rx_status1;
@@ -167,7 +180,7 @@ checksum_fail:
 void
 ice_process_skb_fields(struct ice_ring *rx_ring,
 		       union ice_32b_rx_flex_desc *rx_desc,
-		       struct sk_buff *skb, u8 ptype)
+		       struct sk_buff *skb, u16 ptype)
 {
 	ice_rx_hash(rx_ring, rx_desc, skb, ptype);
 
@@ -175,6 +188,9 @@ ice_process_skb_fields(struct ice_ring *rx_ring,
 	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 
 	ice_rx_csum(rx_ring, skb, rx_desc, ptype);
+
+	if (rx_ring->ptp_rx)
+		ice_ptp_rx_hwtstamp(rx_ring, rx_desc, skb);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
index 58ff58f0f972..05ac30752902 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
@@ -53,7 +53,7 @@ void ice_release_rx_desc(struct ice_ring *rx_ring, u16 val);
 void
 ice_process_skb_fields(struct ice_ring *rx_ring,
 		       union ice_32b_rx_flex_desc *rx_desc,
-		       struct sk_buff *skb, u8 ptype);
+		       struct sk_buff *skb, u16 ptype);
 void
 ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag);
 #endif /* !_ICE_TXRX_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 4474dd6a7ba1..d33d1906103c 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -14,6 +14,7 @@
 #include "ice_lan_tx_rx.h"
 #include "ice_flex_type.h"
 #include "ice_protocol_type.h"
+#include "ice_sbq_cmd.h"
 
 static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc)
 {
@@ -45,8 +46,10 @@ static inline u32 ice_round_to_num(u32 N, u32 R)
 #define ICE_DBG_FLOW		BIT_ULL(9)
 #define ICE_DBG_SW		BIT_ULL(13)
 #define ICE_DBG_SCHED		BIT_ULL(14)
+#define ICE_DBG_RDMA		BIT_ULL(15)
 #define ICE_DBG_PKG		BIT_ULL(16)
 #define ICE_DBG_RES		BIT_ULL(17)
+#define ICE_DBG_PTP		BIT_ULL(19)
 #define ICE_DBG_AQ_MSG		BIT_ULL(24)
 #define ICE_DBG_AQ_DESC		BIT_ULL(25)
 #define ICE_DBG_AQ_DESC_BUF	BIT_ULL(26)
@@ -63,7 +66,7 @@ enum ice_aq_res_ids {
 /* FW update timeout definitions are in milliseconds */
 #define ICE_NVM_TIMEOUT			180000
 #define ICE_CHANGE_LOCK_TIMEOUT		1000
-#define ICE_GLOBAL_CFG_LOCK_TIMEOUT	3000
+#define ICE_GLOBAL_CFG_LOCK_TIMEOUT	5000
 
 enum ice_aq_res_access_type {
 	ICE_RES_READ = 1,
@@ -146,6 +149,7 @@ struct ice_link_status {
 	u16 max_frame_size;
 	u16 link_speed;
 	u16 req_speeds;
+	u8 link_cfg_err;
 	u8 lse_ena;	/* Link Status Event notification */
 	u8 link_info;
 	u8 an_info;
@@ -262,6 +266,8 @@ struct ice_hw_common_caps {
 	u8 rss_table_entry_width;	/* RSS Entry width in bits */
 
 	u8 dcb;
+	u8 ieee_1588;
+	u8 rdma;
 
 	bool nvm_update_pending_nvm;
 	bool nvm_update_pending_orom;
@@ -273,6 +279,54 @@ struct ice_hw_common_caps {
 #define ICE_NVM_MGMT_UNIFIED_UPD_SUPPORT	BIT(3)
 };
 
+/* IEEE 1588 TIME_SYNC specific info */
+/* Function specific definitions */
+#define ICE_TS_FUNC_ENA_M		BIT(0)
+#define ICE_TS_SRC_TMR_OWND_M		BIT(1)
+#define ICE_TS_TMR_ENA_M		BIT(2)
+#define ICE_TS_TMR_IDX_OWND_S		4
+#define ICE_TS_TMR_IDX_OWND_M		BIT(4)
+#define ICE_TS_CLK_FREQ_S		16
+#define ICE_TS_CLK_FREQ_M		ICE_M(0x7, ICE_TS_CLK_FREQ_S)
+#define ICE_TS_CLK_SRC_S		20
+#define ICE_TS_CLK_SRC_M		BIT(20)
+#define ICE_TS_TMR_IDX_ASSOC_S		24
+#define ICE_TS_TMR_IDX_ASSOC_M		BIT(24)
+
+struct ice_ts_func_info {
+	/* Function specific info */
+	u32 clk_freq;
+	u8 clk_src;
+	u8 tmr_index_assoc;
+	u8 ena;
+	u8 tmr_index_owned;
+	u8 src_tmr_owned;
+	u8 tmr_ena;
+};
+
+/* Device specific definitions */
+#define ICE_TS_TMR0_OWNR_M		0x7
+#define ICE_TS_TMR0_OWND_M		BIT(3)
+#define ICE_TS_TMR1_OWNR_S		4
+#define ICE_TS_TMR1_OWNR_M		ICE_M(0x7, ICE_TS_TMR1_OWNR_S)
+#define ICE_TS_TMR1_OWND_M		BIT(7)
+#define ICE_TS_DEV_ENA_M		BIT(24)
+#define ICE_TS_TMR0_ENA_M		BIT(25)
+#define ICE_TS_TMR1_ENA_M		BIT(26)
+
+struct ice_ts_dev_info {
+	/* Device specific info */
+	u32 ena_ports;
+	u32 tmr_own_map;
+	u32 tmr0_owner;
+	u32 tmr1_owner;
+	u8 tmr0_owned;
+	u8 tmr1_owned;
+	u8 ena;
+	u8 tmr0_ena;
+	u8 tmr1_ena;
+};
+
 /* Function specific capabilities */
 struct ice_hw_func_caps {
 	struct ice_hw_common_caps common_cap;
@@ -281,6 +335,7 @@ struct ice_hw_func_caps {
 	u32 guar_num_vsi;
 	u32 fd_fltr_guar;		/* Number of filters guaranteed */
 	u32 fd_fltr_best_effort;	/* Number of best effort filters */
+	struct ice_ts_func_info ts_func_info;
 };
 
 /* Device wide capabilities */
@@ -289,6 +344,7 @@ struct ice_hw_dev_caps {
 	u32 num_vfs_exposed;		/* Total number of VFs exposed */
 	u32 num_vsi_allocd_to_host;	/* Excluding EMP VSI */
 	u32 num_flow_director_fltr;	/* Number of FD filters available */
+	struct ice_ts_dev_info ts_dev_info;
 	u32 num_funcs;
 };
 
@@ -440,6 +496,7 @@ struct ice_sched_node {
 	u8 tc_num;
 	u8 owner;
 #define ICE_SCHED_NODE_OWNER_LAN	0
+#define ICE_SCHED_NODE_OWNER_RDMA	2
 };
 
 /* Access Macros for Tx Sched Elements data */
@@ -511,6 +568,7 @@ struct ice_sched_vsi_info {
 	struct ice_sched_node *ag_node[ICE_MAX_TRAFFIC_CLASS];
 	struct list_head list_entry;
 	u16 max_lanq[ICE_MAX_TRAFFIC_CLASS];
+	u16 max_rdmaq[ICE_MAX_TRAFFIC_CLASS];
 };
 
 /* driver defines the policy */
@@ -749,6 +807,7 @@ struct ice_hw {
 
 	/* Control Queue info */
 	struct ice_ctl_q_info adminq;
+	struct ice_ctl_q_info sbq;
 	struct ice_ctl_q_info mailboxq;
 
 	u8 api_branch;		/* API branch version */
@@ -784,6 +843,14 @@ struct ice_hw {
 
 	u8 ucast_shared;	/* true if VSIs can share unicast addr */
 
+#define ICE_PHY_PER_NAC		1
+#define ICE_MAX_QUAD		2
+#define ICE_NUM_QUAD_TYPE	2
+#define ICE_PORTS_PER_QUAD	4
+#define ICE_PHY_0_LAST_QUAD	1
+#define ICE_PORTS_PER_PHY	8
+#define ICE_NUM_EXTERNAL_PORTS		ICE_PORTS_PER_PHY
+
 	/* Active package version (currently active) */
 	struct ice_pkg_ver active_pkg_ver;
 	u32 active_track_id;
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 97a46c616aca..6392e0b31b90 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -939,16 +939,18 @@ static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf)
 
 	vf->num_mac++;
 
-	if (is_valid_ether_addr(vf->dflt_lan_addr.addr)) {
-		status = ice_fltr_add_mac(vsi, vf->dflt_lan_addr.addr,
+	if (is_valid_ether_addr(vf->hw_lan_addr.addr)) {
+		status = ice_fltr_add_mac(vsi, vf->hw_lan_addr.addr,
 					  ICE_FWD_TO_VSI);
 		if (status) {
 			dev_err(dev, "failed to add default unicast MAC filter %pM for VF %u, error %s\n",
-				&vf->dflt_lan_addr.addr[0], vf->vf_id,
+				&vf->hw_lan_addr.addr[0], vf->vf_id,
 				ice_stat_str(status));
 			return ice_status_to_errno(status);
 		}
 		vf->num_mac++;
+
+		ether_addr_copy(vf->dev_lan_addr.addr, vf->hw_lan_addr.addr);
 	}
 
 	return 0;
@@ -2386,7 +2388,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 	vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV;
 	vfres->vsi_res[0].num_queue_pairs = vsi->num_txq;
 	ether_addr_copy(vfres->vsi_res[0].default_mac_addr,
-			vf->dflt_lan_addr.addr);
+			vf->hw_lan_addr.addr);
 
 	/* match guest capabilities */
 	vf->driver_caps = vfres->vf_cap_flags;
@@ -3542,10 +3544,9 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 	struct virtchnl_vsi_queue_config_info *qci =
 	    (struct virtchnl_vsi_queue_config_info *)msg;
 	struct virtchnl_queue_pair_info *qpi;
-	u16 num_rxq = 0, num_txq = 0;
 	struct ice_pf *pf = vf->pf;
 	struct ice_vsi *vsi;
-	int i;
+	int i, q_idx;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
 		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
@@ -3583,18 +3584,31 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 			goto error_param;
 		}
+
+		q_idx = qpi->rxq.queue_id;
+
+		/* make sure selected "q_idx" is in valid range of queues
+		 * for selected "vsi"
+		 */
+		if (q_idx >= vsi->alloc_txq || q_idx >= vsi->alloc_rxq) {
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto error_param;
+		}
+
 		/* copy Tx queue info from VF into VSI */
 		if (qpi->txq.ring_len > 0) {
-			num_txq++;
 			vsi->tx_rings[i]->dma = qpi->txq.dma_ring_addr;
 			vsi->tx_rings[i]->count = qpi->txq.ring_len;
+			if (ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx)) {
+				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+				goto error_param;
+			}
 		}
 
 		/* copy Rx queue info from VF into VSI */
 		if (qpi->rxq.ring_len > 0) {
 			u16 max_frame_size = ice_vc_get_max_frame_size(vf);
 
-			num_rxq++;
 			vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr;
 			vsi->rx_rings[i]->count = qpi->rxq.ring_len;
 
@@ -3611,27 +3625,20 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 				goto error_param;
 			}
-		}
 
-		vsi->max_frame = qpi->rxq.max_pkt_size;
-		/* add space for the port VLAN since the VF driver is not
-		 * expected to account for it in the MTU calculation
-		 */
-		if (vf->port_vlan_info)
-			vsi->max_frame += VLAN_HLEN;
-	}
-
-	/* VF can request to configure less than allocated queues or default
-	 * allocated queues. So update the VSI with new number
-	 */
-	vsi->num_txq = num_txq;
-	vsi->num_rxq = num_rxq;
-	/* All queues of VF VSI are in TC 0 */
-	vsi->tc_cfg.tc_info[0].qcount_tx = num_txq;
-	vsi->tc_cfg.tc_info[0].qcount_rx = num_rxq;
+			vsi->max_frame = qpi->rxq.max_pkt_size;
+			/* add space for the port VLAN since the VF driver is not
+			 * expected to account for it in the MTU calculation
+			 */
+			if (vf->port_vlan_info)
+				vsi->max_frame += VLAN_HLEN;
 
-	if (ice_vsi_cfg_lan_txqs(vsi) || ice_vsi_cfg_rxqs(vsi))
-		v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
+			if (ice_vsi_cfg_single_rxq(vsi, q_idx)) {
+				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+				goto error_param;
+			}
+		}
+	}
 
 error_param:
 	/* send the response to the VF */
@@ -3667,19 +3674,95 @@ static bool ice_can_vf_change_mac(struct ice_vf *vf)
 }
 
 /**
+ * ice_vc_ether_addr_type - get type of virtchnl_ether_addr
+ * @vc_ether_addr: used to extract the type
+ */
+static u8
+ice_vc_ether_addr_type(struct virtchnl_ether_addr *vc_ether_addr)
+{
+	return (vc_ether_addr->type & VIRTCHNL_ETHER_ADDR_TYPE_MASK);
+}
+
+/**
+ * ice_is_vc_addr_legacy - check if the MAC address is from an older VF
+ * @vc_ether_addr: VIRTCHNL structure that contains MAC and type
+ */
+static bool
+ice_is_vc_addr_legacy(struct virtchnl_ether_addr *vc_ether_addr)
+{
+	u8 type = ice_vc_ether_addr_type(vc_ether_addr);
+
+	return (type == VIRTCHNL_ETHER_ADDR_LEGACY);
+}
+
+/**
+ * ice_is_vc_addr_primary - check if the MAC address is the VF's primary MAC
+ * @vc_ether_addr: VIRTCHNL structure that contains MAC and type
+ *
+ * This function should only be called when the MAC address in
+ * virtchnl_ether_addr is a valid unicast MAC
+ */
+static bool
+ice_is_vc_addr_primary(struct virtchnl_ether_addr __maybe_unused *vc_ether_addr)
+{
+	u8 type = ice_vc_ether_addr_type(vc_ether_addr);
+
+	return (type == VIRTCHNL_ETHER_ADDR_PRIMARY);
+}
+
+/**
+ * ice_vfhw_mac_add - update the VF's cached hardware MAC if allowed
+ * @vf: VF to update
+ * @vc_ether_addr: structure from VIRTCHNL with MAC to add
+ */
+static void
+ice_vfhw_mac_add(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr)
+{
+	u8 *mac_addr = vc_ether_addr->addr;
+
+	if (!is_valid_ether_addr(mac_addr))
+		return;
+
+	/* only allow legacy VF drivers to set the device and hardware MAC if it
+	 * is zero and allow new VF drivers to set the hardware MAC if the type
+	 * was correctly specified over VIRTCHNL
+	 */
+	if ((ice_is_vc_addr_legacy(vc_ether_addr) &&
+	     is_zero_ether_addr(vf->hw_lan_addr.addr)) ||
+	    ice_is_vc_addr_primary(vc_ether_addr)) {
+		ether_addr_copy(vf->dev_lan_addr.addr, mac_addr);
+		ether_addr_copy(vf->hw_lan_addr.addr, mac_addr);
+	}
+
+	/* hardware and device MACs are already set, but its possible that the
+	 * VF driver sent the VIRTCHNL_OP_ADD_ETH_ADDR message before the
+	 * VIRTCHNL_OP_DEL_ETH_ADDR when trying to update its MAC, so save it
+	 * away for the legacy VF driver case as it will be updated in the
+	 * delete flow for this case
+	 */
+	if (ice_is_vc_addr_legacy(vc_ether_addr)) {
+		ether_addr_copy(vf->legacy_last_added_umac.addr,
+				mac_addr);
+		vf->legacy_last_added_umac.time_modified = jiffies;
+	}
+}
+
+/**
  * ice_vc_add_mac_addr - attempt to add the MAC address passed in
  * @vf: pointer to the VF info
  * @vsi: pointer to the VF's VSI
- * @mac_addr: MAC address to add
+ * @vc_ether_addr: VIRTCHNL MAC address structure used to add MAC
  */
 static int
-ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr)
+ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi,
+		    struct virtchnl_ether_addr *vc_ether_addr)
 {
 	struct device *dev = ice_pf_to_dev(vf->pf);
+	u8 *mac_addr = vc_ether_addr->addr;
 	enum ice_status status;
 
-	/* default unicast MAC already added */
-	if (ether_addr_equal(mac_addr, vf->dflt_lan_addr.addr))
+	/* device MAC already added */
+	if (ether_addr_equal(mac_addr, vf->dev_lan_addr.addr))
 		return 0;
 
 	if (is_unicast_ether_addr(mac_addr) && !ice_can_vf_change_mac(vf)) {
@@ -3698,12 +3781,7 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr)
 		return -EIO;
 	}
 
-	/* Set the default LAN address to the latest unicast MAC address added
-	 * by the VF. The default LAN address is reported by the PF via
-	 * ndo_get_vf_config.
-	 */
-	if (is_unicast_ether_addr(mac_addr))
-		ether_addr_copy(vf->dflt_lan_addr.addr, mac_addr);
+	ice_vfhw_mac_add(vf, vc_ether_addr);
 
 	vf->num_mac++;
 
@@ -3711,19 +3789,65 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr)
 }
 
 /**
+ * ice_is_legacy_umac_expired - check if last added legacy unicast MAC expired
+ * @last_added_umac: structure used to check expiration
+ */
+static bool ice_is_legacy_umac_expired(struct ice_time_mac *last_added_umac)
+{
+#define ICE_LEGACY_VF_MAC_CHANGE_EXPIRE_TIME	msecs_to_jiffies(3000)
+	return time_is_before_jiffies(last_added_umac->time_modified +
+				      ICE_LEGACY_VF_MAC_CHANGE_EXPIRE_TIME);
+}
+
+/**
+ * ice_vfhw_mac_del - update the VF's cached hardware MAC if allowed
+ * @vf: VF to update
+ * @vc_ether_addr: structure from VIRTCHNL with MAC to delete
+ */
+static void
+ice_vfhw_mac_del(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr)
+{
+	u8 *mac_addr = vc_ether_addr->addr;
+
+	if (!is_valid_ether_addr(mac_addr) ||
+	    !ether_addr_equal(vf->dev_lan_addr.addr, mac_addr))
+		return;
+
+	/* allow the device MAC to be repopulated in the add flow and don't
+	 * clear the hardware MAC (i.e. hw_lan_addr.addr) here as that is meant
+	 * to be persistent on VM reboot and across driver unload/load, which
+	 * won't work if we clear the hardware MAC here
+	 */
+	eth_zero_addr(vf->dev_lan_addr.addr);
+
+	/* only update cached hardware MAC for legacy VF drivers on delete
+	 * because we cannot guarantee order/type of MAC from the VF driver
+	 */
+	if (ice_is_vc_addr_legacy(vc_ether_addr) &&
+	    !ice_is_legacy_umac_expired(&vf->legacy_last_added_umac)) {
+		ether_addr_copy(vf->dev_lan_addr.addr,
+				vf->legacy_last_added_umac.addr);
+		ether_addr_copy(vf->hw_lan_addr.addr,
+				vf->legacy_last_added_umac.addr);
+	}
+}
+
+/**
  * ice_vc_del_mac_addr - attempt to delete the MAC address passed in
  * @vf: pointer to the VF info
  * @vsi: pointer to the VF's VSI
- * @mac_addr: MAC address to delete
+ * @vc_ether_addr: VIRTCHNL MAC address structure used to delete MAC
  */
 static int
-ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr)
+ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi,
+		    struct virtchnl_ether_addr *vc_ether_addr)
 {
 	struct device *dev = ice_pf_to_dev(vf->pf);
+	u8 *mac_addr = vc_ether_addr->addr;
 	enum ice_status status;
 
 	if (!ice_can_vf_change_mac(vf) &&
-	    ether_addr_equal(mac_addr, vf->dflt_lan_addr.addr))
+	    ether_addr_equal(vf->dev_lan_addr.addr, mac_addr))
 		return 0;
 
 	status = ice_fltr_remove_mac(vsi, mac_addr, ICE_FWD_TO_VSI);
@@ -3737,8 +3861,7 @@ ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr)
 		return -EIO;
 	}
 
-	if (ether_addr_equal(mac_addr, vf->dflt_lan_addr.addr))
-		eth_zero_addr(vf->dflt_lan_addr.addr);
+	ice_vfhw_mac_del(vf, vc_ether_addr);
 
 	vf->num_mac--;
 
@@ -3757,7 +3880,8 @@ static int
 ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set)
 {
 	int (*ice_vc_cfg_mac)
-		(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr);
+		(struct ice_vf *vf, struct ice_vsi *vsi,
+		 struct virtchnl_ether_addr *virtchnl_ether_addr);
 	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
 	struct virtchnl_ether_addr_list *al =
 	    (struct virtchnl_ether_addr_list *)msg;
@@ -3806,7 +3930,7 @@ ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set)
 		    is_zero_ether_addr(mac_addr))
 			continue;
 
-		result = ice_vc_cfg_mac(vf, vsi, mac_addr);
+		result = ice_vc_cfg_mac(vf, vsi, &al->list[i]);
 		if (result == -EEXIST || result == -ENOENT) {
 			continue;
 		} else if (result) {
@@ -4444,7 +4568,7 @@ ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi)
 		return -EBUSY;
 
 	ivi->vf = vf_id;
-	ether_addr_copy(ivi->mac, vf->dflt_lan_addr.addr);
+	ether_addr_copy(ivi->mac, vf->hw_lan_addr.addr);
 
 	/* VF configuration for VLAN and applicable QoS */
 	ivi->vlan = vf->port_vlan_info & VLAN_VID_MASK;
@@ -4520,7 +4644,8 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 
 	vf = &pf->vf[vf_id];
 	/* nothing left to do, unicast MAC already set */
-	if (ether_addr_equal(vf->dflt_lan_addr.addr, mac))
+	if (ether_addr_equal(vf->dev_lan_addr.addr, mac) &&
+	    ether_addr_equal(vf->hw_lan_addr.addr, mac))
 		return 0;
 
 	ret = ice_check_vf_ready_for_cfg(vf);
@@ -4536,7 +4661,8 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	/* VF is notified of its new MAC via the PF's response to the
 	 * VIRTCHNL_OP_GET_VF_RESOURCES message after the VF has been reset
 	 */
-	ether_addr_copy(vf->dflt_lan_addr.addr, mac);
+	ether_addr_copy(vf->dev_lan_addr.addr, mac);
+	ether_addr_copy(vf->hw_lan_addr.addr, mac);
 	if (is_zero_ether_addr(mac)) {
 		/* VF will send VIRTCHNL_OP_ADD_ETH_ADDR message with its MAC */
 		vf->pf_set_mac = false;
@@ -4689,7 +4815,7 @@ void ice_print_vf_rx_mdd_event(struct ice_vf *vf)
 
 	dev_info(dev, "%d Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pM. mdd-auto-reset-vfs=%s\n",
 		 vf->mdd_rx_events.count, pf->hw.pf_id, vf->vf_id,
-		 vf->dflt_lan_addr.addr,
+		 vf->dev_lan_addr.addr,
 		 test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags)
 			  ? "on" : "off");
 }
@@ -4733,7 +4859,7 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf)
 
 			dev_info(dev, "%d Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pM.\n",
 				 vf->mdd_tx_events.count, hw->pf_id, i,
-				 vf->dflt_lan_addr.addr);
+				 vf->dev_lan_addr.addr);
 		}
 	}
 }
@@ -4823,7 +4949,7 @@ ice_is_malicious_vf(struct ice_pf *pf, struct ice_rq_event_info *event,
 
 			if (pf_vsi)
 				dev_warn(dev, "VF MAC %pM on PF MAC %pM is generating asynchronous messages and may be overflowing the PF message queue. Please see the Adapter User Guide for more information\n",
-					 &vf->dflt_lan_addr.addr[0],
+					 &vf->dev_lan_addr.addr[0],
 					 pf_vsi->netdev->dev_addr);
 		}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
index d800ed83d6c3..842cb077df86 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
@@ -58,6 +58,11 @@ enum ice_virtchnl_cap {
 	ICE_VIRTCHNL_VF_CAP_PRIVILEGE,
 };
 
+struct ice_time_mac {
+	unsigned long time_modified;
+	u8 addr[ETH_ALEN];
+};
+
 /* VF MDD events print structure */
 struct ice_mdd_vf_events {
 	u16 count;			/* total count of Rx|Tx events */
@@ -78,7 +83,9 @@ struct ice_vf {
 	struct ice_sw *vf_sw_id;	/* switch ID the VF VSIs connect to */
 	struct virtchnl_version_info vf_ver;
 	u32 driver_caps;		/* reported by VF driver */
-	struct virtchnl_ether_addr dflt_lan_addr;
+	struct virtchnl_ether_addr dev_lan_addr;
+	struct virtchnl_ether_addr hw_lan_addr;
+	struct ice_time_mac legacy_last_added_umac;
 	DECLARE_BITMAP(txq_ena, ICE_MAX_RSS_QS_PER_VF);
 	DECLARE_BITMAP(rxq_ena, ICE_MAX_RSS_QS_PER_VF);
 	u16 port_vlan_info;		/* Port VLAN ID and QoS */
@@ -151,16 +158,18 @@ ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode,
 		      enum virtchnl_status_code v_retval, u8 *msg, u16 msglen);
 bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id);
 #else /* CONFIG_PCI_IOV */
-#define ice_process_vflr_event(pf) do {} while (0)
-#define ice_free_vfs(pf) do {} while (0)
-#define ice_vc_process_vf_msg(pf, event) do {} while (0)
-#define ice_vc_notify_link_state(pf) do {} while (0)
-#define ice_vc_notify_reset(pf) do {} while (0)
-#define ice_set_vf_state_qs_dis(vf) do {} while (0)
-#define ice_vf_lan_overflow_event(pf, event) do {} while (0)
-#define ice_print_vfs_mdd_events(pf) do {} while (0)
-#define ice_print_vf_rx_mdd_event(vf) do {} while (0)
-#define ice_restore_all_vfs_msi_state(pdev) do {} while (0)
+static inline void ice_process_vflr_event(struct ice_pf *pf) { }
+static inline void ice_free_vfs(struct ice_pf *pf) { }
+static inline
+void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) { }
+static inline void ice_vc_notify_link_state(struct ice_pf *pf) { }
+static inline void ice_vc_notify_reset(struct ice_pf *pf) { }
+static inline void ice_set_vf_state_qs_dis(struct ice_vf *vf) { }
+static inline
+void ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) { }
+static inline void ice_print_vfs_mdd_events(struct ice_pf *pf) { }
+static inline void ice_print_vf_rx_mdd_event(struct ice_vf *vf) { }
+static inline void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) { }
 
 static inline bool
 ice_is_malicious_vf(struct ice_pf __always_unused *pf,
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index a1f89ea3c2bd..52acbe325db3 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -236,7 +236,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
 		xdp_ring->xsk_pool = ice_xsk_pool(xdp_ring);
 	}
 
-	err = ice_setup_rx_ctx(rx_ring);
+	err = ice_vsi_cfg_rxq(rx_ring);
 	if (err)
 		goto free_buf;
 
@@ -528,7 +528,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget)
 		struct sk_buff *skb;
 		u16 stat_err_bits;
 		u16 vlan_tag = 0;
-		u8 rx_ptype;
+		u16 rx_ptype;
 
 		rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h
index fad783690134..ea208808623a 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.h
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.h
@@ -60,7 +60,7 @@ ice_xsk_wakeup(struct net_device __always_unused *netdev,
 	return -EOPNOTSUPP;
 }
 
-#define ice_xsk_clean_rx_ring(rx_ring) do {} while (0)
-#define ice_xsk_clean_xdp_ring(xdp_ring) do {} while (0)
+static inline void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring) { }
+static inline void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring) { }
 #endif /* CONFIG_XDP_SOCKETS */
 #endif /* !_ICE_XSK_H_ */
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index 50863fd87d53..cbe92fd23a70 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -2756,6 +2756,7 @@ out:
 	return ret_val;
 }
 
+#ifdef CONFIG_IGB_HWMON
 static const u8 e1000_emc_temp_data[4] = {
 	E1000_EMC_INTERNAL_DATA,
 	E1000_EMC_DIODE1_DATA,
@@ -2769,7 +2770,6 @@ static const u8 e1000_emc_therm_limit[4] = {
 	E1000_EMC_DIODE3_THERM_LIMIT
 };
 
-#ifdef CONFIG_IGB_HWMON
 /**
  *  igb_get_thermal_sensor_data_generic - Gathers thermal sensor data
  *  @hw: pointer to hardware structure
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 7545da216d8b..636a1b1fb7e1 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -831,7 +831,7 @@ static int igb_set_eeprom(struct net_device *netdev,
 	memcpy(ptr, bytes, eeprom->len);
 
 	for (i = 0; i < last_word - first_word + 1; i++)
-		eeprom_buff[i] = cpu_to_le16(eeprom_buff[i]);
+		cpu_to_le16s(&eeprom_buff[i]);
 
 	ret_val = hw->nvm.ops.write(hw, first_word,
 				    last_word - first_word + 1, eeprom_buff);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index b2a042f825ff..5db303d64d14 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -356,7 +356,7 @@ static void igb_dump(struct igb_adapter *adapter)
 	struct igb_reg_info *reginfo;
 	struct igb_ring *tx_ring;
 	union e1000_adv_tx_desc *tx_desc;
-	struct my_u0 { u64 a; u64 b; } *u0;
+	struct my_u0 { __le64 a; __le64 b; } *u0;
 	struct igb_ring *rx_ring;
 	union e1000_adv_rx_desc *rx_desc;
 	u32 staterr;
@@ -2643,7 +2643,8 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter,
 			}
 
 			input->filter.match_flags |= IGB_FILTER_FLAG_VLAN_TCI;
-			input->filter.vlan_tci = match.key->vlan_priority;
+			input->filter.vlan_tci =
+				(__force __be16)match.key->vlan_priority;
 		}
 	}
 
@@ -6275,12 +6276,12 @@ int igb_xmit_xdp_ring(struct igb_adapter *adapter,
 	cmd_type |= len | IGB_TXD_DCMD;
 	tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
 
-	olinfo_status = cpu_to_le32(len << E1000_ADVTXD_PAYLEN_SHIFT);
+	olinfo_status = len << E1000_ADVTXD_PAYLEN_SHIFT;
 	/* 82575 requires a unique index per ring */
 	if (test_bit(IGB_RING_FLAG_TX_CTX_IDX, &tx_ring->flags))
 		olinfo_status |= tx_ring->reg_idx << 4;
 
-	tx_desc->read.olinfo_status = olinfo_status;
+	tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
 
 	netdev_tx_sent_queue(txring_txq(tx_ring), tx_buffer->bytecount);
 
@@ -8592,7 +8593,7 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring,
 
 		if (igb_test_staterr(rx_desc, E1000_RXDEXT_STATERR_LB) &&
 		    test_bit(IGB_RING_FLAG_RX_LB_VLAN_BSWAP, &rx_ring->flags))
-			vid = be16_to_cpu(rx_desc->wb.upper.vlan);
+			vid = be16_to_cpu((__force __be16)rx_desc->wb.upper.vlan);
 		else
 			vid = le16_to_cpu(rx_desc->wb.upper.vlan);
 
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index d68cd4466a54..0011b15e678c 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -1131,12 +1131,12 @@ static int igb_ptp_set_timestamp_mode(struct igb_adapter *adapter,
 			| E1000_FTQF_MASK); /* mask all inputs */
 		ftqf &= ~E1000_FTQF_MASK_PROTO_BP; /* enable protocol check */
 
-		wr32(E1000_IMIR(3), htons(PTP_EV_PORT));
+		wr32(E1000_IMIR(3), (__force unsigned int)htons(PTP_EV_PORT));
 		wr32(E1000_IMIREXT(3),
 		     (E1000_IMIREXT_SIZE_BP | E1000_IMIREXT_CTRL_BP));
 		if (hw->mac.type == e1000_82576) {
 			/* enable source port check */
-			wr32(E1000_SPQF(3), htons(PTP_EV_PORT));
+			wr32(E1000_SPQF(3), (__force unsigned int)htons(PTP_EV_PORT));
 			ftqf &= ~E1000_FTQF_MASK_SOURCE_PORT_BP;
 		}
 		wr32(E1000_FTQF(3), ftqf);
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index fb3fbcb13331..1bbe9862a758 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -83,14 +83,14 @@ static int igbvf_desc_unused(struct igbvf_ring *ring)
 static void igbvf_receive_skb(struct igbvf_adapter *adapter,
 			      struct net_device *netdev,
 			      struct sk_buff *skb,
-			      u32 status, u16 vlan)
+			      u32 status, __le16 vlan)
 {
 	u16 vid;
 
 	if (status & E1000_RXD_STAT_VP) {
 		if ((adapter->flags & IGBVF_FLAG_RX_LB_VLAN_BSWAP) &&
 		    (status & E1000_RXDEXT_STATERR_LB))
-			vid = be16_to_cpu(vlan) & E1000_RXD_SPC_VLAN_MASK;
+			vid = be16_to_cpu((__force __be16)vlan) & E1000_RXD_SPC_VLAN_MASK;
 		else
 			vid = le16_to_cpu(vlan) & E1000_RXD_SPC_VLAN_MASK;
 		if (test_bit(vid, adapter->active_vlans))
@@ -2056,7 +2056,7 @@ static int igbvf_tso(struct igbvf_ring *tx_ring,
 
 	/* remove payload length from inner checksum */
 	paylen = skb->len - l4_offset;
-	csum_replace_by_diff(&l4.tcp->check, htonl(paylen));
+	csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen));
 
 	/* MSS L4LEN IDX */
 	mss_l4len_idx = (*hdr_len - l4_offset) << E1000_ADVTXD_L4LEN_SHIFT;
diff --git a/drivers/net/ethernet/intel/igbvf/vf.h b/drivers/net/ethernet/intel/igbvf/vf.h
index c71b0d7dbcee..ba9bb3132d5d 100644
--- a/drivers/net/ethernet/intel/igbvf/vf.h
+++ b/drivers/net/ethernet/intel/igbvf/vf.h
@@ -35,31 +35,31 @@ struct e1000_hw;
 /* Receive Descriptor - Advanced */
 union e1000_adv_rx_desc {
 	struct {
-		u64 pkt_addr; /* Packet buffer address */
-		u64 hdr_addr; /* Header buffer address */
+		__le64 pkt_addr; /* Packet buffer address */
+		__le64 hdr_addr; /* Header buffer address */
 	} read;
 	struct {
 		struct {
 			union {
-				u32 data;
+				__le32 data;
 				struct {
-					u16 pkt_info; /* RSS/Packet type */
+					__le16 pkt_info; /* RSS/Packet type */
 					/* Split Header, hdr buffer length */
-					u16 hdr_info;
+					__le16 hdr_info;
 				} hs_rss;
 			} lo_dword;
 			union {
-				u32 rss; /* RSS Hash */
+				__le32 rss; /* RSS Hash */
 				struct {
-					u16 ip_id; /* IP id */
-					u16 csum;  /* Packet Checksum */
+					__le16 ip_id; /* IP id */
+					__le16 csum;  /* Packet Checksum */
 				} csum_ip;
 			} hi_dword;
 		} lower;
 		struct {
-			u32 status_error; /* ext status/error */
-			u16 length; /* Packet length */
-			u16 vlan;   /* VLAN tag */
+			__le32 status_error; /* ext status/error */
+			__le16 length; /* Packet length */
+			__le16 vlan; /* VLAN tag */
 		} upper;
 	} wb;  /* writeback */
 };
@@ -70,14 +70,14 @@ union e1000_adv_rx_desc {
 /* Transmit Descriptor - Advanced */
 union e1000_adv_tx_desc {
 	struct {
-		u64 buffer_addr; /* Address of descriptor's data buf */
-		u32 cmd_type_len;
-		u32 olinfo_status;
+		__le64 buffer_addr; /* Address of descriptor's data buf */
+		__le32 cmd_type_len;
+		__le32 olinfo_status;
 	} read;
 	struct {
-		u64 rsvd; /* Reserved */
-		u32 nxtseq_seed;
-		u32 status;
+		__le64 rsvd; /* Reserved */
+		__le32 nxtseq_seed;
+		__le32 status;
 	} wb;
 };
 
@@ -94,10 +94,10 @@ union e1000_adv_tx_desc {
 
 /* Context descriptors */
 struct e1000_adv_tx_context_desc {
-	u32 vlan_macip_lens;
-	u32 seqnum_seed;
-	u32 type_tucmd_mlhl;
-	u32 mss_l4len_idx;
+	__le32 vlan_macip_lens;
+	__le32 seqnum_seed;
+	__le32 type_tucmd_mlhl;
+	__le32 mss_l4len_idx;
 };
 
 #define E1000_ADVTXD_MACLEN_SHIFT	9  /* Adv ctxt desc mac len shift */
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 25871351730b..9e0bbb2e55e3 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -118,6 +118,7 @@ struct igc_ring {
 	};
 
 	struct xdp_rxq_info xdp_rxq;
+	struct xsk_buff_pool *xsk_pool;
 } ____cacheline_internodealigned_in_smp;
 
 /* Board specific private data structure */
@@ -255,6 +256,11 @@ bool igc_has_link(struct igc_adapter *adapter);
 void igc_reset(struct igc_adapter *adapter);
 int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx);
 void igc_update_stats(struct igc_adapter *adapter);
+void igc_disable_rx_ring(struct igc_ring *ring);
+void igc_enable_rx_ring(struct igc_ring *ring);
+void igc_disable_tx_ring(struct igc_ring *ring);
+void igc_enable_tx_ring(struct igc_ring *ring);
+int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags);
 
 /* igc_dump declarations */
 void igc_rings_dump(struct igc_adapter *adapter);
@@ -366,6 +372,7 @@ extern char igc_driver_name[];
 
 /* VLAN info */
 #define IGC_TX_FLAGS_VLAN_MASK	0xffff0000
+#define IGC_TX_FLAGS_VLAN_SHIFT	16
 
 /* igc_test_staterr - tests bits within Rx descriptor status and error fields */
 static inline __le32 igc_test_staterr(union igc_adv_rx_desc *rx_desc,
@@ -390,8 +397,6 @@ enum igc_tx_flags {
 	/* olinfo flags */
 	IGC_TX_FLAGS_IPV4	= 0x10,
 	IGC_TX_FLAGS_CSUM	= 0x20,
-
-	IGC_TX_FLAGS_XDP	= 0x100,
 };
 
 enum igc_boards {
@@ -408,12 +413,19 @@ enum igc_boards {
 #define TXD_USE_COUNT(S)	DIV_ROUND_UP((S), IGC_MAX_DATA_PER_TXD)
 #define DESC_NEEDED	(MAX_SKB_FRAGS + 4)
 
+enum igc_tx_buffer_type {
+	IGC_TX_BUFFER_TYPE_SKB,
+	IGC_TX_BUFFER_TYPE_XDP,
+	IGC_TX_BUFFER_TYPE_XSK,
+};
+
 /* wrapper around a pointer to a socket buffer,
  * so a DMA handle can be stored along with the buffer
  */
 struct igc_tx_buffer {
 	union igc_adv_tx_desc *next_to_watch;
 	unsigned long time_stamp;
+	enum igc_tx_buffer_type type;
 	union {
 		struct sk_buff *skb;
 		struct xdp_frame *xdpf;
@@ -428,14 +440,19 @@ struct igc_tx_buffer {
 };
 
 struct igc_rx_buffer {
-	dma_addr_t dma;
-	struct page *page;
+	union {
+		struct {
+			dma_addr_t dma;
+			struct page *page;
 #if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
-	__u32 page_offset;
+			__u32 page_offset;
 #else
-	__u16 page_offset;
+			__u16 page_offset;
 #endif
-	__u16 pagecnt_bias;
+			__u16 pagecnt_bias;
+		};
+		struct xdp_buff *xdp;
+	};
 };
 
 struct igc_q_vector {
@@ -521,7 +538,8 @@ enum igc_ring_flags_t {
 	IGC_RING_FLAG_RX_SCTP_CSUM,
 	IGC_RING_FLAG_RX_LB_VLAN_BSWAP,
 	IGC_RING_FLAG_TX_CTX_IDX,
-	IGC_RING_FLAG_TX_DETECT_HANG
+	IGC_RING_FLAG_TX_DETECT_HANG,
+	IGC_RING_FLAG_AF_XDP_ZC,
 };
 
 #define ring_uses_large_buffer(ring) \
diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h
index ea627ce52525..ce530f5fd7bd 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.h
+++ b/drivers/net/ethernet/intel/igc/igc_base.h
@@ -78,9 +78,11 @@ union igc_adv_rx_desc {
 
 /* Additional Transmit Descriptor Control definitions */
 #define IGC_TXDCTL_QUEUE_ENABLE	0x02000000 /* Ena specific Tx Queue */
+#define IGC_TXDCTL_SWFLUSH	0x04000000 /* Transmit Software Flush */
 
 /* Additional Receive Descriptor Control definitions */
 #define IGC_RXDCTL_QUEUE_ENABLE	0x02000000 /* Ena specific Rx Queue */
+#define IGC_RXDCTL_SWFLUSH		0x04000000 /* Receive Software Flush */
 
 /* SRRCTL bit definitions */
 #define IGC_SRRCTL_BSIZEPKT_SHIFT		10 /* Shift _right_ */
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 0103dda32f39..c3a5a5518790 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -94,12 +94,13 @@
 #define IGC_CTRL_SLU		0x00000040  /* Set link up (Force Link) */
 #define IGC_CTRL_FRCSPD		0x00000800  /* Force Speed */
 #define IGC_CTRL_FRCDPX		0x00001000  /* Force Duplex */
+#define IGC_CTRL_VME		0x40000000  /* IEEE VLAN mode enable */
 
 #define IGC_CTRL_RFCE		0x08000000  /* Receive Flow Control enable */
 #define IGC_CTRL_TFCE		0x10000000  /* Transmit flow control enable */
 
-#define IGC_CTRL_SDP0_DIR 0x00400000	/* SDP0 Data direction */
-#define IGC_CTRL_SDP1_DIR 0x00800000	/* SDP1 Data direction */
+#define IGC_CTRL_SDP0_DIR	0x00400000  /* SDP0 Data direction */
+#define IGC_CTRL_SDP1_DIR	0x00800000  /* SDP1 Data direction */
 
 /* As per the EAS the maximum supported size is 9.5KB (9728 bytes) */
 #define MAX_JUMBO_FRAME_SIZE	0x2600
@@ -128,7 +129,6 @@
 #define NWAY_LPAR_ASM_DIR	0x0800 /* LP Asymmetric Pause Direction bit */
 
 /* 1000BASE-T Control Register */
-#define CR_1000T_ASYM_PAUSE	0x0080 /* Advertise asymmetric pause bit */
 #define CR_1000T_HD_CAPS	0x0100 /* Advertise 1000T HD capability */
 #define CR_1000T_FD_CAPS	0x0200 /* Advertise 1000T FD capability  */
 
@@ -323,6 +323,9 @@
 #define IGC_RXD_STAT_IXSM	0x04	/* Ignore checksum */
 #define IGC_RXD_STAT_UDPCS	0x10	/* UDP xsum calculated */
 #define IGC_RXD_STAT_TCPCS	0x20	/* TCP xsum calculated */
+#define IGC_RXD_STAT_VP		0x08	/* IEEE VLAN Packet */
+
+#define IGC_RXDEXT_STATERR_LB	0x00040000
 
 /* Advanced Receive Descriptor bit definitions */
 #define IGC_RXDADV_STAT_TSIP	0x08000 /* timestamp in packet */
diff --git a/drivers/net/ethernet/intel/igc/igc_dump.c b/drivers/net/ethernet/intel/igc/igc_dump.c
index 495bed47ed0a..c09c95cc5f70 100644
--- a/drivers/net/ethernet/intel/igc/igc_dump.c
+++ b/drivers/net/ethernet/intel/igc/igc_dump.c
@@ -112,7 +112,7 @@ static void igc_regdump(struct igc_hw *hw, struct igc_reg_info *reginfo)
 void igc_rings_dump(struct igc_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
-	struct my_u0 { u64 a; u64 b; } *u0;
+	struct my_u0 { __le64 a; __le64 b; } *u0;
 	union igc_adv_tx_desc *tx_desc;
 	union igc_adv_rx_desc *rx_desc;
 	struct igc_ring *tx_ring;
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 9722449d7633..fa4171860623 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -554,7 +554,7 @@ static int igc_ethtool_set_eeprom(struct net_device *netdev,
 	memcpy(ptr, bytes, eeprom->len);
 
 	for (i = 0; i < last_word - first_word + 1; i++)
-		eeprom_buff[i] = cpu_to_le16(eeprom_buff[i]);
+		cpu_to_le16s(&eeprom_buff[i]);
 
 	ret_val = hw->nvm.ops.write(hw, first_word,
 				    last_word - first_word + 1, eeprom_buff);
@@ -765,35 +765,22 @@ static void igc_ethtool_get_strings(struct net_device *netdev, u32 stringset,
 		       IGC_TEST_LEN * ETH_GSTRING_LEN);
 		break;
 	case ETH_SS_STATS:
-		for (i = 0; i < IGC_GLOBAL_STATS_LEN; i++) {
-			memcpy(p, igc_gstrings_stats[i].stat_string,
-			       ETH_GSTRING_LEN);
-			p += ETH_GSTRING_LEN;
-		}
-		for (i = 0; i < IGC_NETDEV_STATS_LEN; i++) {
-			memcpy(p, igc_gstrings_net_stats[i].stat_string,
-			       ETH_GSTRING_LEN);
-			p += ETH_GSTRING_LEN;
-		}
+		for (i = 0; i < IGC_GLOBAL_STATS_LEN; i++)
+			ethtool_sprintf(&p, igc_gstrings_stats[i].stat_string);
+		for (i = 0; i < IGC_NETDEV_STATS_LEN; i++)
+			ethtool_sprintf(&p,
+					igc_gstrings_net_stats[i].stat_string);
 		for (i = 0; i < adapter->num_tx_queues; i++) {
-			sprintf(p, "tx_queue_%u_packets", i);
-			p += ETH_GSTRING_LEN;
-			sprintf(p, "tx_queue_%u_bytes", i);
-			p += ETH_GSTRING_LEN;
-			sprintf(p, "tx_queue_%u_restart", i);
-			p += ETH_GSTRING_LEN;
+			ethtool_sprintf(&p, "tx_queue_%u_packets", i);
+			ethtool_sprintf(&p, "tx_queue_%u_bytes", i);
+			ethtool_sprintf(&p, "tx_queue_%u_restart", i);
 		}
 		for (i = 0; i < adapter->num_rx_queues; i++) {
-			sprintf(p, "rx_queue_%u_packets", i);
-			p += ETH_GSTRING_LEN;
-			sprintf(p, "rx_queue_%u_bytes", i);
-			p += ETH_GSTRING_LEN;
-			sprintf(p, "rx_queue_%u_drops", i);
-			p += ETH_GSTRING_LEN;
-			sprintf(p, "rx_queue_%u_csum_err", i);
-			p += ETH_GSTRING_LEN;
-			sprintf(p, "rx_queue_%u_alloc_failed", i);
-			p += ETH_GSTRING_LEN;
+			ethtool_sprintf(&p, "rx_queue_%u_packets", i);
+			ethtool_sprintf(&p, "rx_queue_%u_bytes", i);
+			ethtool_sprintf(&p, "rx_queue_%u_drops", i);
+			ethtool_sprintf(&p, "rx_queue_%u_csum_err", i);
+			ethtool_sprintf(&p, "rx_queue_%u_alloc_failed", i);
 		}
 		/* BUG_ON(p - data != IGC_STATS_LEN * ETH_GSTRING_LEN); */
 		break;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index f1adf154ec4a..3f6b6d4543a8 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -11,7 +11,7 @@
 #include <linux/pm_runtime.h>
 #include <net/pkt_sched.h>
 #include <linux/bpf_trace.h>
-
+#include <net/xdp_sock_drv.h>
 #include <net/ipv6.h>
 
 #include "igc.h"
@@ -111,6 +111,9 @@ void igc_reset(struct igc_adapter *adapter)
 	if (!netif_running(adapter->netdev))
 		igc_power_down_phy_copper_base(&adapter->hw);
 
+	/* Enable HW to recognize an 802.1Q VLAN Ethernet packet */
+	wr32(IGC_VET, ETH_P_8021Q);
+
 	/* Re-enable PTP, where applicable. */
 	igc_ptp_reset(adapter);
 
@@ -171,6 +174,14 @@ static void igc_get_hw_control(struct igc_adapter *adapter)
 	     ctrl_ext | IGC_CTRL_EXT_DRV_LOAD);
 }
 
+static void igc_unmap_tx_buffer(struct device *dev, struct igc_tx_buffer *buf)
+{
+	dma_unmap_single(dev, dma_unmap_addr(buf, dma),
+			 dma_unmap_len(buf, len), DMA_TO_DEVICE);
+
+	dma_unmap_len_set(buf, len, 0);
+}
+
 /**
  * igc_clean_tx_ring - Free Tx Buffers
  * @tx_ring: ring to be cleaned
@@ -179,20 +190,27 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring)
 {
 	u16 i = tx_ring->next_to_clean;
 	struct igc_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i];
+	u32 xsk_frames = 0;
 
 	while (i != tx_ring->next_to_use) {
 		union igc_adv_tx_desc *eop_desc, *tx_desc;
 
-		if (tx_buffer->tx_flags & IGC_TX_FLAGS_XDP)
+		switch (tx_buffer->type) {
+		case IGC_TX_BUFFER_TYPE_XSK:
+			xsk_frames++;
+			break;
+		case IGC_TX_BUFFER_TYPE_XDP:
 			xdp_return_frame(tx_buffer->xdpf);
-		else
+			igc_unmap_tx_buffer(tx_ring->dev, tx_buffer);
+			break;
+		case IGC_TX_BUFFER_TYPE_SKB:
 			dev_kfree_skb_any(tx_buffer->skb);
-
-		/* 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);
+			igc_unmap_tx_buffer(tx_ring->dev, tx_buffer);
+			break;
+		default:
+			netdev_warn_once(tx_ring->netdev, "Unknown Tx buffer type\n");
+			break;
+		}
 
 		/* check for eop_desc to determine the end of the packet */
 		eop_desc = tx_buffer->next_to_watch;
@@ -211,10 +229,7 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring)
 
 			/* 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);
+				igc_unmap_tx_buffer(tx_ring->dev, tx_buffer);
 		}
 
 		/* move us one more past the eop_desc for start of next pkt */
@@ -226,6 +241,9 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring)
 		}
 	}
 
+	if (tx_ring->xsk_pool && xsk_frames)
+		xsk_tx_completed(tx_ring->xsk_pool, xsk_frames);
+
 	/* reset BQL for queue */
 	netdev_tx_reset_queue(txring_txq(tx_ring));
 
@@ -346,11 +364,7 @@ static int igc_setup_all_tx_resources(struct igc_adapter *adapter)
 	return err;
 }
 
-/**
- * igc_clean_rx_ring - Free Rx Buffers per Queue
- * @rx_ring: ring to free buffers from
- */
-static void igc_clean_rx_ring(struct igc_ring *rx_ring)
+static void igc_clean_rx_ring_page_shared(struct igc_ring *rx_ring)
 {
 	u16 i = rx_ring->next_to_clean;
 
@@ -383,12 +397,39 @@ static void igc_clean_rx_ring(struct igc_ring *rx_ring)
 		if (i == rx_ring->count)
 			i = 0;
 	}
+}
+
+static void igc_clean_rx_ring_xsk_pool(struct igc_ring *ring)
+{
+	struct igc_rx_buffer *bi;
+	u16 i;
+
+	for (i = 0; i < ring->count; i++) {
+		bi = &ring->rx_buffer_info[i];
+		if (!bi->xdp)
+			continue;
+
+		xsk_buff_free(bi->xdp);
+		bi->xdp = NULL;
+	}
+}
 
-	clear_ring_uses_large_buffer(rx_ring);
+/**
+ * igc_clean_rx_ring - Free Rx Buffers per Queue
+ * @ring: ring to free buffers from
+ */
+static void igc_clean_rx_ring(struct igc_ring *ring)
+{
+	if (ring->xsk_pool)
+		igc_clean_rx_ring_xsk_pool(ring);
+	else
+		igc_clean_rx_ring_page_shared(ring);
 
-	rx_ring->next_to_alloc = 0;
-	rx_ring->next_to_clean = 0;
-	rx_ring->next_to_use = 0;
+	clear_ring_uses_large_buffer(ring);
+
+	ring->next_to_alloc = 0;
+	ring->next_to_clean = 0;
+	ring->next_to_use = 0;
 }
 
 /**
@@ -414,7 +455,7 @@ void igc_free_rx_resources(struct igc_ring *rx_ring)
 {
 	igc_clean_rx_ring(rx_ring);
 
-	igc_xdp_unregister_rxq_info(rx_ring);
+	xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
 
 	vfree(rx_ring->rx_buffer_info);
 	rx_ring->rx_buffer_info = NULL;
@@ -453,11 +494,16 @@ int igc_setup_rx_resources(struct igc_ring *rx_ring)
 {
 	struct net_device *ndev = rx_ring->netdev;
 	struct device *dev = rx_ring->dev;
+	u8 index = rx_ring->queue_index;
 	int size, desc_len, res;
 
-	res = igc_xdp_register_rxq_info(rx_ring);
-	if (res < 0)
+	res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, ndev, index,
+			       rx_ring->q_vector->napi.napi_id);
+	if (res < 0) {
+		netdev_err(ndev, "Failed to register xdp_rxq index %u\n",
+			   index);
 		return res;
+	}
 
 	size = sizeof(struct igc_rx_buffer) * rx_ring->count;
 	rx_ring->rx_buffer_info = vzalloc(size);
@@ -483,7 +529,7 @@ int igc_setup_rx_resources(struct igc_ring *rx_ring)
 	return 0;
 
 err:
-	igc_xdp_unregister_rxq_info(rx_ring);
+	xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
 	vfree(rx_ring->rx_buffer_info);
 	rx_ring->rx_buffer_info = NULL;
 	netdev_err(ndev, "Unable to allocate memory for Rx descriptor ring\n");
@@ -515,9 +561,14 @@ static int igc_setup_all_rx_resources(struct igc_adapter *adapter)
 	return err;
 }
 
-static bool igc_xdp_is_enabled(struct igc_adapter *adapter)
+static struct xsk_buff_pool *igc_get_xsk_pool(struct igc_adapter *adapter,
+					      struct igc_ring *ring)
 {
-	return !!adapter->xdp_prog;
+	if (!igc_xdp_is_enabled(adapter) ||
+	    !test_bit(IGC_RING_FLAG_AF_XDP_ZC, &ring->flags))
+		return NULL;
+
+	return xsk_get_pool_from_qid(ring->netdev, ring->queue_index);
 }
 
 /**
@@ -535,6 +586,20 @@ static void igc_configure_rx_ring(struct igc_adapter *adapter,
 	int reg_idx = ring->reg_idx;
 	u32 srrctl = 0, rxdctl = 0;
 	u64 rdba = ring->dma;
+	u32 buf_size;
+
+	xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+	ring->xsk_pool = igc_get_xsk_pool(adapter, ring);
+	if (ring->xsk_pool) {
+		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+						   MEM_TYPE_XSK_BUFF_POOL,
+						   NULL));
+		xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
+	} else {
+		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+						   MEM_TYPE_PAGE_SHARED,
+						   NULL));
+	}
 
 	if (igc_xdp_is_enabled(adapter))
 		set_ring_uses_large_buffer(ring);
@@ -558,12 +623,15 @@ static void igc_configure_rx_ring(struct igc_adapter *adapter,
 	ring->next_to_clean = 0;
 	ring->next_to_use = 0;
 
-	/* set descriptor configuration */
-	srrctl = IGC_RX_HDR_LEN << IGC_SRRCTL_BSIZEHDRSIZE_SHIFT;
-	if (ring_uses_large_buffer(ring))
-		srrctl |= IGC_RXBUFFER_3072 >> IGC_SRRCTL_BSIZEPKT_SHIFT;
+	if (ring->xsk_pool)
+		buf_size = xsk_pool_get_rx_frame_size(ring->xsk_pool);
+	else if (ring_uses_large_buffer(ring))
+		buf_size = IGC_RXBUFFER_3072;
 	else
-		srrctl |= IGC_RXBUFFER_2048 >> IGC_SRRCTL_BSIZEPKT_SHIFT;
+		buf_size = IGC_RXBUFFER_2048;
+
+	srrctl = IGC_RX_HDR_LEN << IGC_SRRCTL_BSIZEHDRSIZE_SHIFT;
+	srrctl |= buf_size >> IGC_SRRCTL_BSIZEPKT_SHIFT;
 	srrctl |= IGC_SRRCTL_DESCTYPE_ADV_ONEBUF;
 
 	wr32(IGC_SRRCTL(reg_idx), srrctl);
@@ -618,6 +686,8 @@ static void igc_configure_tx_ring(struct igc_adapter *adapter,
 	u64 tdba = ring->dma;
 	u32 txdctl = 0;
 
+	ring->xsk_pool = igc_get_xsk_pool(adapter, ring);
+
 	/* disable the queue */
 	wr32(IGC_TXDCTL(reg_idx), 0);
 	wrfl();
@@ -1055,13 +1125,17 @@ static inline int igc_maybe_stop_tx(struct igc_ring *tx_ring, const u16 size)
 	 ((u32)((_input) & (_flag)) * ((_result) / (_flag))) :	\
 	 ((u32)((_input) & (_flag)) / ((_flag) / (_result))))
 
-static u32 igc_tx_cmd_type(u32 tx_flags)
+static u32 igc_tx_cmd_type(struct sk_buff *skb, u32 tx_flags)
 {
 	/* set type for advanced descriptor with frame checksum insertion */
 	u32 cmd_type = IGC_ADVTXD_DTYP_DATA |
 		       IGC_ADVTXD_DCMD_DEXT |
 		       IGC_ADVTXD_DCMD_IFCS;
 
+	/* set HW vlan bit if vlan is present */
+	cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_VLAN,
+				 IGC_ADVTXD_DCMD_VLE);
+
 	/* set segmentation bits for TSO */
 	cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSO,
 				 (IGC_ADVTXD_DCMD_TSE));
@@ -1070,6 +1144,9 @@ static u32 igc_tx_cmd_type(u32 tx_flags)
 	cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP,
 				 (IGC_ADVTXD_MAC_TSTAMP));
 
+	/* insert frame checksum */
+	cmd_type ^= IGC_SET_FLAG(skb->no_fcs, 1, IGC_ADVTXD_DCMD_IFCS);
+
 	return cmd_type;
 }
 
@@ -1104,8 +1181,9 @@ static int igc_tx_map(struct igc_ring *tx_ring,
 	u16 i = tx_ring->next_to_use;
 	unsigned int data_len, size;
 	dma_addr_t dma;
-	u32 cmd_type = igc_tx_cmd_type(tx_flags);
+	u32 cmd_type;
 
+	cmd_type = igc_tx_cmd_type(skb, tx_flags);
 	tx_desc = IGC_TX_DESC(tx_ring, i);
 
 	igc_tx_olinfo_status(tx_ring, tx_desc, tx_flags, skb->len - hdr_len);
@@ -1211,11 +1289,7 @@ dma_error:
 	/* clear dma mappings for failed tx_buffer_info map */
 	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);
+			igc_unmap_tx_buffer(tx_ring->dev, tx_buffer);
 
 		if (i-- == 0)
 			i += tx_ring->count;
@@ -1223,11 +1297,7 @@ dma_error:
 	}
 
 	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);
+		igc_unmap_tx_buffer(tx_ring->dev, tx_buffer);
 
 	dev_kfree_skb_any(tx_buffer->skb);
 	tx_buffer->skb = NULL;
@@ -1359,6 +1429,7 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 
 	/* record the location of the first descriptor for this packet */
 	first = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
+	first->type = IGC_TX_BUFFER_TYPE_SKB;
 	first->skb = skb;
 	first->bytecount = skb->len;
 	first->gso_segs = 1;
@@ -1383,6 +1454,11 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 		}
 	}
 
+	if (skb_vlan_tag_present(skb)) {
+		tx_flags |= IGC_TX_FLAGS_VLAN;
+		tx_flags |= (skb_vlan_tag_get(skb) << IGC_TX_FLAGS_VLAN_SHIFT);
+	}
+
 	/* record initial flags and protocol */
 	first->tx_flags = tx_flags;
 	first->protocol = protocol;
@@ -1482,6 +1558,25 @@ static inline void igc_rx_hash(struct igc_ring *ring,
 			     PKT_HASH_TYPE_L3);
 }
 
+static void igc_rx_vlan(struct igc_ring *rx_ring,
+			union igc_adv_rx_desc *rx_desc,
+			struct sk_buff *skb)
+{
+	struct net_device *dev = rx_ring->netdev;
+	u16 vid;
+
+	if ((dev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+	    igc_test_staterr(rx_desc, IGC_RXD_STAT_VP)) {
+		if (igc_test_staterr(rx_desc, IGC_RXDEXT_STATERR_LB) &&
+		    test_bit(IGC_RING_FLAG_RX_LB_VLAN_BSWAP, &rx_ring->flags))
+			vid = be16_to_cpu((__force __be16)rx_desc->wb.upper.vlan);
+		else
+			vid = le16_to_cpu(rx_desc->wb.upper.vlan);
+
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
+	}
+}
+
 /**
  * igc_process_skb_fields - Populate skb header fields from Rx descriptor
  * @rx_ring: rx descriptor ring packet is being transacted on
@@ -1500,11 +1595,37 @@ static void igc_process_skb_fields(struct igc_ring *rx_ring,
 
 	igc_rx_checksum(rx_ring, rx_desc, skb);
 
+	igc_rx_vlan(rx_ring, rx_desc, skb);
+
 	skb_record_rx_queue(skb, rx_ring->queue_index);
 
 	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 }
 
+static void igc_vlan_mode(struct net_device *netdev, netdev_features_t features)
+{
+	bool enable = !!(features & NETIF_F_HW_VLAN_CTAG_RX);
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	u32 ctrl;
+
+	ctrl = rd32(IGC_CTRL);
+
+	if (enable) {
+		/* enable VLAN tag insert/strip */
+		ctrl |= IGC_CTRL_VME;
+	} else {
+		/* disable VLAN tag insert/strip */
+		ctrl &= ~IGC_CTRL_VME;
+	}
+	wr32(IGC_CTRL, ctrl);
+}
+
+static void igc_restore_vlan(struct igc_adapter *adapter)
+{
+	igc_vlan_mode(adapter->netdev, adapter->netdev->features);
+}
+
 static struct igc_rx_buffer *igc_get_rx_buffer(struct igc_ring *rx_ring,
 					       const unsigned int size,
 					       int *rx_buffer_pgcnt)
@@ -1930,6 +2051,63 @@ static void igc_alloc_rx_buffers(struct igc_ring *rx_ring, u16 cleaned_count)
 	}
 }
 
+static bool igc_alloc_rx_buffers_zc(struct igc_ring *ring, u16 count)
+{
+	union igc_adv_rx_desc *desc;
+	u16 i = ring->next_to_use;
+	struct igc_rx_buffer *bi;
+	dma_addr_t dma;
+	bool ok = true;
+
+	if (!count)
+		return ok;
+
+	desc = IGC_RX_DESC(ring, i);
+	bi = &ring->rx_buffer_info[i];
+	i -= ring->count;
+
+	do {
+		bi->xdp = xsk_buff_alloc(ring->xsk_pool);
+		if (!bi->xdp) {
+			ok = false;
+			break;
+		}
+
+		dma = xsk_buff_xdp_get_dma(bi->xdp);
+		desc->read.pkt_addr = cpu_to_le64(dma);
+
+		desc++;
+		bi++;
+		i++;
+		if (unlikely(!i)) {
+			desc = IGC_RX_DESC(ring, 0);
+			bi = ring->rx_buffer_info;
+			i -= ring->count;
+		}
+
+		/* Clear the length for the next_to_use descriptor. */
+		desc->wb.upper.length = 0;
+
+		count--;
+	} while (count);
+
+	i += ring->count;
+
+	if (ring->next_to_use != i) {
+		ring->next_to_use = i;
+
+		/* Force memory writes to complete before letting h/w
+		 * know there are new descriptors to fetch.  (Only
+		 * applicable for weak-ordered memory model archs,
+		 * such as IA-64).
+		 */
+		wmb();
+		writel(i, ring->tail);
+	}
+
+	return ok;
+}
+
 static int igc_xdp_init_tx_buffer(struct igc_tx_buffer *buffer,
 				  struct xdp_frame *xdpf,
 				  struct igc_ring *ring)
@@ -1942,8 +2120,8 @@ static int igc_xdp_init_tx_buffer(struct igc_tx_buffer *buffer,
 		return -ENOMEM;
 	}
 
+	buffer->type = IGC_TX_BUFFER_TYPE_XDP;
 	buffer->xdpf = xdpf;
-	buffer->tx_flags = IGC_TX_FLAGS_XDP;
 	buffer->protocol = 0;
 	buffer->bytecount = xdpf->len;
 	buffer->gso_segs = 1;
@@ -2025,35 +2203,24 @@ static int igc_xdp_xmit_back(struct igc_adapter *adapter, struct xdp_buff *xdp)
 	return res;
 }
 
-static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter,
-					struct xdp_buff *xdp)
+/* This function assumes rcu_read_lock() is held by the caller. */
+static int __igc_xdp_run_prog(struct igc_adapter *adapter,
+			      struct bpf_prog *prog,
+			      struct xdp_buff *xdp)
 {
-	struct bpf_prog *prog;
-	int res;
-	u32 act;
+	u32 act = bpf_prog_run_xdp(prog, xdp);
 
-	rcu_read_lock();
-
-	prog = READ_ONCE(adapter->xdp_prog);
-	if (!prog) {
-		res = IGC_XDP_PASS;
-		goto unlock;
-	}
-
-	act = bpf_prog_run_xdp(prog, xdp);
 	switch (act) {
 	case XDP_PASS:
-		res = IGC_XDP_PASS;
-		break;
+		return IGC_XDP_PASS;
 	case XDP_TX:
 		if (igc_xdp_xmit_back(adapter, xdp) < 0)
 			goto out_failure;
-		res = IGC_XDP_TX;
-		break;
+		return IGC_XDP_TX;
 	case XDP_REDIRECT:
 		if (xdp_do_redirect(adapter->netdev, xdp, prog) < 0)
 			goto out_failure;
-		res = IGC_XDP_REDIRECT;
+		return IGC_XDP_REDIRECT;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
@@ -2063,9 +2230,25 @@ out_failure:
 		trace_xdp_exception(adapter->netdev, prog, act);
 		fallthrough;
 	case XDP_DROP:
-		res = IGC_XDP_CONSUMED;
-		break;
+		return IGC_XDP_CONSUMED;
 	}
+}
+
+static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter,
+					struct xdp_buff *xdp)
+{
+	struct bpf_prog *prog;
+	int res;
+
+	rcu_read_lock();
+
+	prog = READ_ONCE(adapter->xdp_prog);
+	if (!prog) {
+		res = IGC_XDP_PASS;
+		goto unlock;
+	}
+
+	res = __igc_xdp_run_prog(adapter, prog, xdp);
 
 unlock:
 	rcu_read_unlock();
@@ -2102,6 +2285,20 @@ static void igc_finalize_xdp(struct igc_adapter *adapter, int status)
 		xdp_do_flush();
 }
 
+static void igc_update_rx_stats(struct igc_q_vector *q_vector,
+				unsigned int packets, unsigned int bytes)
+{
+	struct igc_ring *ring = q_vector->rx.ring;
+
+	u64_stats_update_begin(&ring->rx_syncp);
+	ring->rx_stats.packets += packets;
+	ring->rx_stats.bytes += bytes;
+	u64_stats_update_end(&ring->rx_syncp);
+
+	q_vector->rx.total_packets += packets;
+	q_vector->rx.total_bytes += bytes;
+}
+
 static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 {
 	unsigned int total_bytes = 0, total_packets = 0;
@@ -2150,12 +2347,9 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 		}
 
 		if (!skb) {
-			xdp.data = pktbuf + pkt_offset;
-			xdp.data_end = xdp.data + size;
-			xdp.data_hard_start = pktbuf - igc_rx_offset(rx_ring);
-			xdp_set_data_meta_invalid(&xdp);
-			xdp.frame_sz = truesize;
-			xdp.rxq = &rx_ring->xdp_rxq;
+			xdp_init_buff(&xdp, truesize, &rx_ring->xdp_rxq);
+			xdp_prepare_buff(&xdp, pktbuf - igc_rx_offset(rx_ring),
+					 igc_rx_offset(rx_ring) + pkt_offset, size, false);
 
 			skb = igc_xdp_run_prog(adapter, &xdp);
 		}
@@ -2225,12 +2419,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 	/* place incomplete frames back on ring for completion */
 	rx_ring->skb = skb;
 
-	u64_stats_update_begin(&rx_ring->rx_syncp);
-	rx_ring->rx_stats.packets += total_packets;
-	rx_ring->rx_stats.bytes += total_bytes;
-	u64_stats_update_end(&rx_ring->rx_syncp);
-	q_vector->rx.total_packets += total_packets;
-	q_vector->rx.total_bytes += total_bytes;
+	igc_update_rx_stats(q_vector, total_packets, total_bytes);
 
 	if (cleaned_count)
 		igc_alloc_rx_buffers(rx_ring, cleaned_count);
@@ -2238,6 +2427,221 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 	return total_packets;
 }
 
+static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring,
+					    struct xdp_buff *xdp)
+{
+	unsigned int metasize = xdp->data - xdp->data_meta;
+	unsigned int datasize = xdp->data_end - xdp->data;
+	unsigned int totalsize = metasize + datasize;
+	struct sk_buff *skb;
+
+	skb = __napi_alloc_skb(&ring->q_vector->napi,
+			       xdp->data_end - xdp->data_hard_start,
+			       GFP_ATOMIC | __GFP_NOWARN);
+	if (unlikely(!skb))
+		return NULL;
+
+	skb_reserve(skb, xdp->data_meta - xdp->data_hard_start);
+	memcpy(__skb_put(skb, totalsize), xdp->data_meta, totalsize);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
+
+	return skb;
+}
+
+static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector,
+				union igc_adv_rx_desc *desc,
+				struct xdp_buff *xdp,
+				ktime_t timestamp)
+{
+	struct igc_ring *ring = q_vector->rx.ring;
+	struct sk_buff *skb;
+
+	skb = igc_construct_skb_zc(ring, xdp);
+	if (!skb) {
+		ring->rx_stats.alloc_failed++;
+		return;
+	}
+
+	if (timestamp)
+		skb_hwtstamps(skb)->hwtstamp = timestamp;
+
+	if (igc_cleanup_headers(ring, desc, skb))
+		return;
+
+	igc_process_skb_fields(ring, desc, skb);
+	napi_gro_receive(&q_vector->napi, skb);
+}
+
+static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
+{
+	struct igc_adapter *adapter = q_vector->adapter;
+	struct igc_ring *ring = q_vector->rx.ring;
+	u16 cleaned_count = igc_desc_unused(ring);
+	int total_bytes = 0, total_packets = 0;
+	u16 ntc = ring->next_to_clean;
+	struct bpf_prog *prog;
+	bool failure = false;
+	int xdp_status = 0;
+
+	rcu_read_lock();
+
+	prog = READ_ONCE(adapter->xdp_prog);
+
+	while (likely(total_packets < budget)) {
+		union igc_adv_rx_desc *desc;
+		struct igc_rx_buffer *bi;
+		ktime_t timestamp = 0;
+		unsigned int size;
+		int res;
+
+		desc = IGC_RX_DESC(ring, ntc);
+		size = le16_to_cpu(desc->wb.upper.length);
+		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
+		 * descriptor has been written back
+		 */
+		dma_rmb();
+
+		bi = &ring->rx_buffer_info[ntc];
+
+		if (igc_test_staterr(desc, IGC_RXDADV_STAT_TSIP)) {
+			timestamp = igc_ptp_rx_pktstamp(q_vector->adapter,
+							bi->xdp->data);
+
+			bi->xdp->data += IGC_TS_HDR_LEN;
+
+			/* HW timestamp has been copied into local variable. Metadata
+			 * length when XDP program is called should be 0.
+			 */
+			bi->xdp->data_meta += IGC_TS_HDR_LEN;
+			size -= IGC_TS_HDR_LEN;
+		}
+
+		bi->xdp->data_end = bi->xdp->data + size;
+		xsk_buff_dma_sync_for_cpu(bi->xdp, ring->xsk_pool);
+
+		res = __igc_xdp_run_prog(adapter, prog, bi->xdp);
+		switch (res) {
+		case IGC_XDP_PASS:
+			igc_dispatch_skb_zc(q_vector, desc, bi->xdp, timestamp);
+			fallthrough;
+		case IGC_XDP_CONSUMED:
+			xsk_buff_free(bi->xdp);
+			break;
+		case IGC_XDP_TX:
+		case IGC_XDP_REDIRECT:
+			xdp_status |= res;
+			break;
+		}
+
+		bi->xdp = NULL;
+		total_bytes += size;
+		total_packets++;
+		cleaned_count++;
+		ntc++;
+		if (ntc == ring->count)
+			ntc = 0;
+	}
+
+	ring->next_to_clean = ntc;
+	rcu_read_unlock();
+
+	if (cleaned_count >= IGC_RX_BUFFER_WRITE)
+		failure = !igc_alloc_rx_buffers_zc(ring, cleaned_count);
+
+	if (xdp_status)
+		igc_finalize_xdp(adapter, xdp_status);
+
+	igc_update_rx_stats(q_vector, total_packets, total_bytes);
+
+	if (xsk_uses_need_wakeup(ring->xsk_pool)) {
+		if (failure || ring->next_to_clean == ring->next_to_use)
+			xsk_set_rx_need_wakeup(ring->xsk_pool);
+		else
+			xsk_clear_rx_need_wakeup(ring->xsk_pool);
+		return total_packets;
+	}
+
+	return failure ? budget : total_packets;
+}
+
+static void igc_update_tx_stats(struct igc_q_vector *q_vector,
+				unsigned int packets, unsigned int bytes)
+{
+	struct igc_ring *ring = q_vector->tx.ring;
+
+	u64_stats_update_begin(&ring->tx_syncp);
+	ring->tx_stats.bytes += bytes;
+	ring->tx_stats.packets += packets;
+	u64_stats_update_end(&ring->tx_syncp);
+
+	q_vector->tx.total_bytes += bytes;
+	q_vector->tx.total_packets += packets;
+}
+
+static void igc_xdp_xmit_zc(struct igc_ring *ring)
+{
+	struct xsk_buff_pool *pool = ring->xsk_pool;
+	struct netdev_queue *nq = txring_txq(ring);
+	union igc_adv_tx_desc *tx_desc = NULL;
+	int cpu = smp_processor_id();
+	u16 ntu = ring->next_to_use;
+	struct xdp_desc xdp_desc;
+	u16 budget;
+
+	if (!netif_carrier_ok(ring->netdev))
+		return;
+
+	__netif_tx_lock(nq, cpu);
+
+	budget = igc_desc_unused(ring);
+
+	while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) {
+		u32 cmd_type, olinfo_status;
+		struct igc_tx_buffer *bi;
+		dma_addr_t dma;
+
+		cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT |
+			   IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD |
+			   xdp_desc.len;
+		olinfo_status = xdp_desc.len << IGC_ADVTXD_PAYLEN_SHIFT;
+
+		dma = xsk_buff_raw_get_dma(pool, xdp_desc.addr);
+		xsk_buff_raw_dma_sync_for_device(pool, dma, xdp_desc.len);
+
+		tx_desc = IGC_TX_DESC(ring, ntu);
+		tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
+		tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
+		tx_desc->read.buffer_addr = cpu_to_le64(dma);
+
+		bi = &ring->tx_buffer_info[ntu];
+		bi->type = IGC_TX_BUFFER_TYPE_XSK;
+		bi->protocol = 0;
+		bi->bytecount = xdp_desc.len;
+		bi->gso_segs = 1;
+		bi->time_stamp = jiffies;
+		bi->next_to_watch = tx_desc;
+
+		netdev_tx_sent_queue(txring_txq(ring), xdp_desc.len);
+
+		ntu++;
+		if (ntu == ring->count)
+			ntu = 0;
+	}
+
+	ring->next_to_use = ntu;
+	if (tx_desc) {
+		igc_flush_tx_descriptors(ring);
+		xsk_tx_release(pool);
+	}
+
+	__netif_tx_unlock(nq);
+}
+
 /**
  * igc_clean_tx_irq - Reclaim resources after transmit completes
  * @q_vector: pointer to q_vector containing needed info
@@ -2254,6 +2658,7 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 	unsigned int i = tx_ring->next_to_clean;
 	struct igc_tx_buffer *tx_buffer;
 	union igc_adv_tx_desc *tx_desc;
+	u32 xsk_frames = 0;
 
 	if (test_bit(__IGC_DOWN, &adapter->state))
 		return true;
@@ -2283,19 +2688,22 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 		total_bytes += tx_buffer->bytecount;
 		total_packets += tx_buffer->gso_segs;
 
-		if (tx_buffer->tx_flags & IGC_TX_FLAGS_XDP)
+		switch (tx_buffer->type) {
+		case IGC_TX_BUFFER_TYPE_XSK:
+			xsk_frames++;
+			break;
+		case IGC_TX_BUFFER_TYPE_XDP:
 			xdp_return_frame(tx_buffer->xdpf);
-		else
+			igc_unmap_tx_buffer(tx_ring->dev, tx_buffer);
+			break;
+		case IGC_TX_BUFFER_TYPE_SKB:
 			napi_consume_skb(tx_buffer->skb, napi_budget);
-
-		/* 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);
-
-		/* clear tx_buffer data */
-		dma_unmap_len_set(tx_buffer, len, 0);
+			igc_unmap_tx_buffer(tx_ring->dev, tx_buffer);
+			break;
+		default:
+			netdev_warn_once(tx_ring->netdev, "Unknown Tx buffer type\n");
+			break;
+		}
 
 		/* clear last DMA location and unmap remaining buffers */
 		while (tx_desc != eop_desc) {
@@ -2309,13 +2717,8 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 			}
 
 			/* 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);
-				dma_unmap_len_set(tx_buffer, len, 0);
-			}
+			if (dma_unmap_len(tx_buffer, len))
+				igc_unmap_tx_buffer(tx_ring->dev, tx_buffer);
 		}
 
 		/* move us one more past the eop_desc for start of next pkt */
@@ -2340,12 +2743,16 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 
 	i += tx_ring->count;
 	tx_ring->next_to_clean = i;
-	u64_stats_update_begin(&tx_ring->tx_syncp);
-	tx_ring->tx_stats.bytes += total_bytes;
-	tx_ring->tx_stats.packets += total_packets;
-	u64_stats_update_end(&tx_ring->tx_syncp);
-	q_vector->tx.total_bytes += total_bytes;
-	q_vector->tx.total_packets += total_packets;
+
+	igc_update_tx_stats(q_vector, total_packets, total_bytes);
+
+	if (tx_ring->xsk_pool) {
+		if (xsk_frames)
+			xsk_tx_completed(tx_ring->xsk_pool, xsk_frames);
+		if (xsk_uses_need_wakeup(tx_ring->xsk_pool))
+			xsk_set_tx_need_wakeup(tx_ring->xsk_pool);
+		igc_xdp_xmit_zc(tx_ring);
+	}
 
 	if (test_bit(IGC_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags)) {
 		struct igc_hw *hw = &adapter->hw;
@@ -2906,6 +3313,8 @@ static void igc_configure(struct igc_adapter *adapter)
 	igc_get_hw_control(adapter);
 	igc_set_rx_mode(netdev);
 
+	igc_restore_vlan(adapter);
+
 	igc_setup_tctl(adapter);
 	igc_setup_mrqc(adapter);
 	igc_setup_rctl(adapter);
@@ -2925,7 +3334,10 @@ static void igc_configure(struct igc_adapter *adapter)
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		struct igc_ring *ring = adapter->rx_ring[i];
 
-		igc_alloc_rx_buffers(ring, igc_desc_unused(ring));
+		if (ring->xsk_pool)
+			igc_alloc_rx_buffers_zc(ring, igc_desc_unused(ring));
+		else
+			igc_alloc_rx_buffers(ring, igc_desc_unused(ring));
 	}
 }
 
@@ -3540,14 +3952,17 @@ static int igc_poll(struct napi_struct *napi, int budget)
 	struct igc_q_vector *q_vector = container_of(napi,
 						     struct igc_q_vector,
 						     napi);
+	struct igc_ring *rx_ring = q_vector->rx.ring;
 	bool clean_complete = true;
 	int work_done = 0;
 
 	if (q_vector->tx.ring)
 		clean_complete = igc_clean_tx_irq(q_vector, budget);
 
-	if (q_vector->rx.ring) {
-		int cleaned = igc_clean_rx_irq(q_vector, budget);
+	if (rx_ring) {
+		int cleaned = rx_ring->xsk_pool ?
+			      igc_clean_rx_irq_zc(q_vector, budget) :
+			      igc_clean_rx_irq(q_vector, budget);
 
 		work_done += cleaned;
 		if (cleaned >= budget)
@@ -4199,6 +4614,9 @@ static int igc_set_features(struct net_device *netdev,
 	netdev_features_t changed = netdev->features ^ features;
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
+	if (changed & NETIF_F_HW_VLAN_CTAG_RX)
+		igc_vlan_mode(netdev, features);
+
 	/* Add VLAN support */
 	if (!(changed & (NETIF_F_RXALL | NETIF_F_NTUPLE)))
 		return 0;
@@ -5185,6 +5603,9 @@ static int igc_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 	switch (bpf->command) {
 	case XDP_SETUP_PROG:
 		return igc_xdp_set_prog(adapter, bpf->prog, bpf->extack);
+	case XDP_SETUP_XSK_POOL:
+		return igc_xdp_setup_pool(adapter, bpf->xsk.pool,
+					  bpf->xsk.queue_id);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -5230,6 +5651,43 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames,
 	return num_frames - drops;
 }
 
+static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter,
+					struct igc_q_vector *q_vector)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 eics = 0;
+
+	eics |= q_vector->eims_value;
+	wr32(IGC_EICS, eics);
+}
+
+int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
+{
+	struct igc_adapter *adapter = netdev_priv(dev);
+	struct igc_q_vector *q_vector;
+	struct igc_ring *ring;
+
+	if (test_bit(__IGC_DOWN, &adapter->state))
+		return -ENETDOWN;
+
+	if (!igc_xdp_is_enabled(adapter))
+		return -ENXIO;
+
+	if (queue_id >= adapter->num_rx_queues)
+		return -EINVAL;
+
+	ring = adapter->rx_ring[queue_id];
+
+	if (!ring->xsk_pool)
+		return -ENXIO;
+
+	q_vector = adapter->q_vector[queue_id];
+	if (!napi_if_scheduled_mark_missed(&q_vector->napi))
+		igc_trigger_rxtxq_interrupt(adapter, q_vector);
+
+	return 0;
+}
+
 static const struct net_device_ops igc_netdev_ops = {
 	.ndo_open		= igc_open,
 	.ndo_stop		= igc_close,
@@ -5245,6 +5703,7 @@ static const struct net_device_ops igc_netdev_ops = {
 	.ndo_setup_tc		= igc_setup_tc,
 	.ndo_bpf		= igc_bpf,
 	.ndo_xdp_xmit		= igc_xdp_xmit,
+	.ndo_xsk_wakeup		= igc_xsk_wakeup,
 };
 
 /* PCIe configuration access */
@@ -5484,11 +5943,15 @@ static int igc_probe(struct pci_dev *pdev,
 
 	/* copy netdev features into list of user selectable features */
 	netdev->hw_features |= NETIF_F_NTUPLE;
+	netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX;
+	netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
 	netdev->hw_features |= netdev->features;
 
 	if (pci_using_dac)
 		netdev->features |= NETIF_F_HIGHDMA;
 
+	netdev->vlan_features |= netdev->features;
+
 	/* MTU range: 68 - 9216 */
 	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE;
@@ -5997,6 +6460,61 @@ struct net_device *igc_get_hw_dev(struct igc_hw *hw)
 	return adapter->netdev;
 }
 
+static void igc_disable_rx_ring_hw(struct igc_ring *ring)
+{
+	struct igc_hw *hw = &ring->q_vector->adapter->hw;
+	u8 idx = ring->reg_idx;
+	u32 rxdctl;
+
+	rxdctl = rd32(IGC_RXDCTL(idx));
+	rxdctl &= ~IGC_RXDCTL_QUEUE_ENABLE;
+	rxdctl |= IGC_RXDCTL_SWFLUSH;
+	wr32(IGC_RXDCTL(idx), rxdctl);
+}
+
+void igc_disable_rx_ring(struct igc_ring *ring)
+{
+	igc_disable_rx_ring_hw(ring);
+	igc_clean_rx_ring(ring);
+}
+
+void igc_enable_rx_ring(struct igc_ring *ring)
+{
+	struct igc_adapter *adapter = ring->q_vector->adapter;
+
+	igc_configure_rx_ring(adapter, ring);
+
+	if (ring->xsk_pool)
+		igc_alloc_rx_buffers_zc(ring, igc_desc_unused(ring));
+	else
+		igc_alloc_rx_buffers(ring, igc_desc_unused(ring));
+}
+
+static void igc_disable_tx_ring_hw(struct igc_ring *ring)
+{
+	struct igc_hw *hw = &ring->q_vector->adapter->hw;
+	u8 idx = ring->reg_idx;
+	u32 txdctl;
+
+	txdctl = rd32(IGC_TXDCTL(idx));
+	txdctl &= ~IGC_TXDCTL_QUEUE_ENABLE;
+	txdctl |= IGC_TXDCTL_SWFLUSH;
+	wr32(IGC_TXDCTL(idx), txdctl);
+}
+
+void igc_disable_tx_ring(struct igc_ring *ring)
+{
+	igc_disable_tx_ring_hw(ring);
+	igc_clean_tx_ring(ring);
+}
+
+void igc_enable_tx_ring(struct igc_ring *ring)
+{
+	struct igc_adapter *adapter = ring->q_vector->adapter;
+
+	igc_configure_tx_ring(adapter, ring);
+}
+
 /**
  * igc_init_module - Driver Registration Routine
  *
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index cc174853554b..0f82990567d9 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -10,8 +10,8 @@
 #define IGC_EECD		0x00010  /* EEPROM/Flash Control - RW */
 #define IGC_CTRL_EXT		0x00018  /* Extended Device Control - RW */
 #define IGC_MDIC		0x00020  /* MDI Control - RW */
-#define IGC_MDICNFG		0x00E04  /* MDC/MDIO Configuration - RW */
 #define IGC_CONNSW		0x00034  /* Copper/Fiber switch control - RW */
+#define IGC_VET			0x00038  /* VLAN Ether Type - RW */
 #define IGC_I225_PHPM		0x00E14  /* I225 PHY Power Management */
 #define IGC_GPHY_VERSION	0x0001E  /* I225 gPHY Firmware Version */
 
diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c
index 11133c4619bb..a8cf5374be47 100644
--- a/drivers/net/ethernet/intel/igc/igc_xdp.c
+++ b/drivers/net/ethernet/intel/igc/igc_xdp.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020, Intel Corporation. */
 
+#include <net/xdp_sock_drv.h>
+
 #include "igc.h"
 #include "igc_xdp.h"
 
@@ -32,29 +34,112 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog,
 	return 0;
 }
 
-int igc_xdp_register_rxq_info(struct igc_ring *ring)
+static int igc_xdp_enable_pool(struct igc_adapter *adapter,
+			       struct xsk_buff_pool *pool, u16 queue_id)
 {
-	struct net_device *dev = ring->netdev;
+	struct net_device *ndev = adapter->netdev;
+	struct device *dev = &adapter->pdev->dev;
+	struct igc_ring *rx_ring, *tx_ring;
+	struct napi_struct *napi;
+	bool needs_reset;
+	u32 frame_size;
 	int err;
 
-	err = xdp_rxq_info_reg(&ring->xdp_rxq, dev, ring->queue_index, 0);
-	if (err) {
-		netdev_err(dev, "Failed to register xdp rxq info\n");
-		return err;
+	if (queue_id >= adapter->num_rx_queues ||
+	    queue_id >= adapter->num_tx_queues)
+		return -EINVAL;
+
+	frame_size = xsk_pool_get_rx_frame_size(pool);
+	if (frame_size < ETH_FRAME_LEN + VLAN_HLEN * 2) {
+		/* When XDP is enabled, the driver doesn't support frames that
+		 * span over multiple buffers. To avoid that, we check if xsk
+		 * frame size is big enough to fit the max ethernet frame size
+		 * + vlan double tagging.
+		 */
+		return -EOPNOTSUPP;
 	}
 
-	err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED,
-					 NULL);
+	err = xsk_pool_dma_map(pool, dev, IGC_RX_DMA_ATTR);
 	if (err) {
-		netdev_err(dev, "Failed to register xdp rxq mem model\n");
-		xdp_rxq_info_unreg(&ring->xdp_rxq);
+		netdev_err(ndev, "Failed to map xsk pool\n");
 		return err;
 	}
 
+	needs_reset = netif_running(adapter->netdev) && igc_xdp_is_enabled(adapter);
+
+	rx_ring = adapter->rx_ring[queue_id];
+	tx_ring = adapter->tx_ring[queue_id];
+	/* Rx and Tx rings share the same napi context. */
+	napi = &rx_ring->q_vector->napi;
+
+	if (needs_reset) {
+		igc_disable_rx_ring(rx_ring);
+		igc_disable_tx_ring(tx_ring);
+		napi_disable(napi);
+	}
+
+	set_bit(IGC_RING_FLAG_AF_XDP_ZC, &rx_ring->flags);
+	set_bit(IGC_RING_FLAG_AF_XDP_ZC, &tx_ring->flags);
+
+	if (needs_reset) {
+		napi_enable(napi);
+		igc_enable_rx_ring(rx_ring);
+		igc_enable_tx_ring(tx_ring);
+
+		err = igc_xsk_wakeup(ndev, queue_id, XDP_WAKEUP_RX);
+		if (err) {
+			xsk_pool_dma_unmap(pool, IGC_RX_DMA_ATTR);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static int igc_xdp_disable_pool(struct igc_adapter *adapter, u16 queue_id)
+{
+	struct igc_ring *rx_ring, *tx_ring;
+	struct xsk_buff_pool *pool;
+	struct napi_struct *napi;
+	bool needs_reset;
+
+	if (queue_id >= adapter->num_rx_queues ||
+	    queue_id >= adapter->num_tx_queues)
+		return -EINVAL;
+
+	pool = xsk_get_pool_from_qid(adapter->netdev, queue_id);
+	if (!pool)
+		return -EINVAL;
+
+	needs_reset = netif_running(adapter->netdev) && igc_xdp_is_enabled(adapter);
+
+	rx_ring = adapter->rx_ring[queue_id];
+	tx_ring = adapter->tx_ring[queue_id];
+	/* Rx and Tx rings share the same napi context. */
+	napi = &rx_ring->q_vector->napi;
+
+	if (needs_reset) {
+		igc_disable_rx_ring(rx_ring);
+		igc_disable_tx_ring(tx_ring);
+		napi_disable(napi);
+	}
+
+	xsk_pool_dma_unmap(pool, IGC_RX_DMA_ATTR);
+	clear_bit(IGC_RING_FLAG_AF_XDP_ZC, &rx_ring->flags);
+	clear_bit(IGC_RING_FLAG_AF_XDP_ZC, &tx_ring->flags);
+
+	if (needs_reset) {
+		napi_enable(napi);
+		igc_enable_rx_ring(rx_ring);
+		igc_enable_tx_ring(tx_ring);
+	}
+
 	return 0;
 }
 
-void igc_xdp_unregister_rxq_info(struct igc_ring *ring)
+int igc_xdp_setup_pool(struct igc_adapter *adapter, struct xsk_buff_pool *pool,
+		       u16 queue_id)
 {
-	xdp_rxq_info_unreg(&ring->xdp_rxq);
+	return pool ? igc_xdp_enable_pool(adapter, pool, queue_id) :
+		      igc_xdp_disable_pool(adapter, queue_id);
 }
diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.h b/drivers/net/ethernet/intel/igc/igc_xdp.h
index cfecb515b718..a74e5487d199 100644
--- a/drivers/net/ethernet/intel/igc/igc_xdp.h
+++ b/drivers/net/ethernet/intel/igc/igc_xdp.h
@@ -6,8 +6,12 @@
 
 int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog,
 		     struct netlink_ext_ack *extack);
+int igc_xdp_setup_pool(struct igc_adapter *adapter, struct xsk_buff_pool *pool,
+		       u16 queue_id);
 
-int igc_xdp_register_rxq_info(struct igc_ring *ring);
-void igc_xdp_unregister_rxq_info(struct igc_ring *ring);
+static inline bool igc_xdp_is_enabled(struct igc_adapter *adapter)
+{
+	return !!adapter->xdp_prog;
+}
 
 #endif /* _IGC_XDP_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
index e324e42fab2d..58ea959a4482 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
@@ -1514,8 +1514,7 @@ static u32 ixgbe_get_fdirtcpm_82599(union ixgbe_atr_input *input_mask)
 #define IXGBE_WRITE_REG_BE32(a, reg, value) \
 	IXGBE_WRITE_REG((a), (reg), IXGBE_STORE_AS_BE32(ntohl(value)))
 
-#define IXGBE_STORE_AS_BE16(_value) \
-	ntohs(((u16)(_value) >> 8) | ((u16)(_value) << 8))
+#define IXGBE_STORE_AS_BE16(_value) __swab16(ntohs((_value)))
 
 s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw,
 				    union ixgbe_atr_input *input_mask)
@@ -1651,13 +1650,13 @@ s32 ixgbe_fdir_write_perfect_filter_82599(struct ixgbe_hw *hw,
 	IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRIPDA, input->formatted.dst_ip[0]);
 
 	/* record source and destination port (little-endian)*/
-	fdirport = ntohs(input->formatted.dst_port);
+	fdirport = be16_to_cpu(input->formatted.dst_port);
 	fdirport <<= IXGBE_FDIRPORT_DESTINATION_SHIFT;
-	fdirport |= ntohs(input->formatted.src_port);
+	fdirport |= be16_to_cpu(input->formatted.src_port);
 	IXGBE_WRITE_REG(hw, IXGBE_FDIRPORT, fdirport);
 
 	/* record vlan (little-endian) and flex_bytes(big-endian) */
-	fdirvlan = IXGBE_STORE_AS_BE16((__force u16)input->formatted.flex_bytes);
+	fdirvlan = IXGBE_STORE_AS_BE16(input->formatted.flex_bytes);
 	fdirvlan <<= IXGBE_FDIRVLAN_FLEX_SHIFT;
 	fdirvlan |= ntohs(input->formatted.vlan_id);
 	IXGBE_WRITE_REG(hw, IXGBE_FDIRVLAN, fdirvlan);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 03ccbe6b66d2..e90b5047e695 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -3678,10 +3678,8 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer,
 				 bool return_data)
 {
 	u32 hdr_size = sizeof(struct ixgbe_hic_hdr);
-	union {
-		struct ixgbe_hic_hdr hdr;
-		u32 u32arr[1];
-	} *bp = buffer;
+	struct ixgbe_hic_hdr *hdr = buffer;
+	u32 *u32arr = buffer;
 	u16 buf_len, dword_len;
 	s32 status;
 	u32 bi;
@@ -3707,12 +3705,12 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer,
 
 	/* first pull in the header so we know the buffer length */
 	for (bi = 0; bi < dword_len; bi++) {
-		bp->u32arr[bi] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, bi);
-		le32_to_cpus(&bp->u32arr[bi]);
+		u32arr[bi] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, bi);
+		le32_to_cpus(&u32arr[bi]);
 	}
 
 	/* If there is any thing in data position pull it in */
-	buf_len = bp->hdr.buf_len;
+	buf_len = hdr->buf_len;
 	if (!buf_len)
 		goto rel_out;
 
@@ -3727,8 +3725,8 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer,
 
 	/* Pull in the rest of the buffer (bi is where we left off) */
 	for (; bi <= dword_len; bi++) {
-		bp->u32arr[bi] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, bi);
-		le32_to_cpus(&bp->u32arr[bi]);
+		u32arr[bi] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, bi);
+		le32_to_cpus(&u32arr[bi]);
 	}
 
 rel_out:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index 54d47265a7ac..e596e1a9fc75 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -511,14 +511,14 @@ static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs)
 					continue;
 
 				reg = IXGBE_READ_REG(hw, MIPAF_ARR(3, i));
-				if (reg == xs->id.daddr.a4)
+				if (reg == (__force u32)xs->id.daddr.a4)
 					return 1;
 			}
 		}
 
 		if ((bmcipval & BMCIP_MASK) == BMCIP_V4) {
 			reg = IXGBE_READ_REG(hw, IXGBE_BMCIP(3));
-			if (reg == xs->id.daddr.a4)
+			if (reg == (__force u32)xs->id.daddr.a4)
 				return 1;
 		}
 
@@ -533,7 +533,7 @@ static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs)
 
 			for (j = 0; j < 4; j++) {
 				reg = IXGBE_READ_REG(hw, MIPAF_ARR(i, j));
-				if (reg != xs->id.daddr.a6[j])
+				if (reg != (__force u32)xs->id.daddr.a6[j])
 					break;
 			}
 			if (j == 4)   /* did we match all 4 words? */
@@ -543,7 +543,7 @@ static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs)
 		if ((bmcipval & BMCIP_MASK) == BMCIP_V6) {
 			for (j = 0; j < 4; j++) {
 				reg = IXGBE_READ_REG(hw, IXGBE_BMCIP(j));
-				if (reg != xs->id.daddr.a6[j])
+				if (reg != (__force u32)xs->id.daddr.a6[j])
 					break;
 			}
 			if (j == 4)   /* did we match all 4 words? */
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 0e733cc15c58..dc56931fc1dc 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -3817,7 +3817,7 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring,
 
 	/* remove payload length from inner checksum */
 	paylen = skb->len - l4_offset;
-	csum_replace_by_diff(&l4.tcp->check, htonl(paylen));
+	csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen));
 
 	/* update gso size and bytecount with header size */
 	first->gso_segs = skb_shinfo(skb)->gso_segs;
diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 21ef2f128070..fb78f17d734f 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -437,7 +437,6 @@ static int xrx200_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
-	struct resource *res;
 	struct xrx200_priv *priv;
 	struct net_device *net_dev;
 	int err;
@@ -457,13 +456,7 @@ static int xrx200_probe(struct platform_device *pdev)
 	net_dev->max_mtu = XRX200_DMA_DATA_LEN;
 
 	/* load the memory ranges */
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(dev, "failed to get resources\n");
-		return -ENOENT;
-	}
-
-	priv->pmac_reg = devm_ioremap_resource(dev, res);
+	priv->pmac_reg = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
 	if (IS_ERR(priv->pmac_reg))
 		return PTR_ERR(priv->pmac_reg);
 
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 7d5cd9bc6c99..c15ce06427d0 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2320,7 +2320,7 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp,
 }
 
 static struct sk_buff *
-mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
+mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 		      struct xdp_buff *xdp, u32 desc_status)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
@@ -2331,7 +2331,7 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 
-	page_pool_release_page(rxq->page_pool, virt_to_page(xdp->data));
+	skb_mark_for_recycle(skb, virt_to_page(xdp->data), pool);
 
 	skb_reserve(skb, xdp->data - xdp->data_hard_start);
 	skb_put(skb, xdp->data_end - xdp->data);
@@ -2343,7 +2343,10 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 				skb_frag_page(frag), skb_frag_off(frag),
 				skb_frag_size(frag), PAGE_SIZE);
-		page_pool_release_page(rxq->page_pool, skb_frag_page(frag));
+		/* We don't need to reset pp_recycle here. It's already set, so
+		 * just mark fragments for recycling.
+		 */
+		page_pool_store_mem_info(skb_frag_page(frag), pool);
 	}
 
 	return skb;
@@ -2425,7 +2428,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 		    mvneta_run_xdp(pp, rxq, xdp_prog, &xdp_buf, frame_sz, &ps))
 			goto next;
 
-		skb = mvneta_swbm_build_skb(pp, rxq, &xdp_buf, desc_status);
+		skb = mvneta_swbm_build_skb(pp, rxq->page_pool, &xdp_buf, desc_status);
 		if (IS_ERR(skb)) {
 			struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index d39c7639cdba..9bca8c8f9f8d 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3784,9 +3784,9 @@ mvpp2_xdp_xmit(struct net_device *dev, int num_frame,
 }
 
 static int
-mvpp2_run_xdp(struct mvpp2_port *port, struct mvpp2_rx_queue *rxq,
-	      struct bpf_prog *prog, struct xdp_buff *xdp,
-	      struct page_pool *pp, struct mvpp2_pcpu_stats *stats)
+mvpp2_run_xdp(struct mvpp2_port *port, struct bpf_prog *prog,
+	      struct xdp_buff *xdp, struct page_pool *pp,
+	      struct mvpp2_pcpu_stats *stats)
 {
 	unsigned int len, sync, err;
 	struct page *page;
@@ -3900,15 +3900,19 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 		phys_addr_t phys_addr;
 		u32 rx_status, timestamp;
 		int pool, rx_bytes, err, ret;
+		struct page *page;
 		void *data;
 
+		phys_addr = mvpp2_rxdesc_cookie_get(port, rx_desc);
+		data = (void *)phys_to_virt(phys_addr);
+		page = virt_to_page(data);
+		prefetch(page);
+
 		rx_done++;
 		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);
 
 		pool = (rx_status & MVPP2_RXD_BM_POOL_ID_MASK) >>
 			MVPP2_RXD_BM_POOL_ID_OFFS;
@@ -3938,7 +3942,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 			goto err_drop_frame;
 
 		/* Prefetch header */
-		prefetch(data);
+		prefetch(data + MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM);
 
 		if (bm_pool->frag_size > PAGE_SIZE)
 			frag_size = 0;
@@ -3958,7 +3962,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 					 MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM,
 					 rx_bytes, false);
 
-			ret = mvpp2_run_xdp(port, rxq, xdp_prog, &xdp, pp, &ps);
+			ret = mvpp2_run_xdp(port, xdp_prog, &xdp, pp, &ps);
 
 			if (ret) {
 				xdp_ret |= ret;
@@ -3997,7 +4001,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 		}
 
 		if (pp)
-			page_pool_release_page(pp, virt_to_page(data));
+			skb_mark_for_recycle(skb, page, pp);
 		else
 			dma_unmap_single_attrs(dev->dev.parent, dma_addr,
 					       bm_pool->buf_size, DMA_FROM_DEVICE,
@@ -4008,8 +4012,8 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 
 		skb_reserve(skb, MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM);
 		skb_put(skb, rx_bytes);
-		skb->protocol = eth_type_trans(skb, dev);
 		mvpp2_rx_csum(port, rx_status, skb);
+		skb->protocol = eth_type_trans(skb, dev);
 
 		napi_gro_receive(napi, skb);
 		continue;
@@ -7347,7 +7351,6 @@ static int mvpp2_get_sram(struct platform_device *pdev,
 
 static int mvpp2_probe(struct platform_device *pdev)
 {
-	const struct acpi_device_id *acpi_id;
 	struct fwnode_handle *fwnode = pdev->dev.fwnode;
 	struct fwnode_handle *port_fwnode;
 	struct mvpp2 *priv;
@@ -7360,16 +7363,7 @@ static int mvpp2_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
-	if (has_acpi_companion(&pdev->dev)) {
-		acpi_id = acpi_match_device(pdev->dev.driver->acpi_match_table,
-					    &pdev->dev);
-		if (!acpi_id)
-			return -EINVAL;
-		priv->hw_version = (unsigned long)acpi_id->driver_data;
-	} else {
-		priv->hw_version =
-			(unsigned long)of_device_get_match_data(&pdev->dev);
-	}
+	priv->hw_version = (unsigned long)device_get_match_data(&pdev->dev);
 
 	/* multi queue mode isn't supported on PPV2.1, fallback to single
 	 * mode
@@ -7387,6 +7381,10 @@ static int mvpp2_probe(struct platform_device *pdev)
 			return PTR_ERR(priv->lms_base);
 	} else {
 		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+		if (!res) {
+			dev_err(&pdev->dev, "Invalid resource\n");
+			return -EINVAL;
+		}
 		if (has_acpi_companion(&pdev->dev)) {
 			/* In case the MDIO memory region is declared in
 			 * the ACPI, it can already appear as 'in-use'
@@ -7481,34 +7479,35 @@ static int mvpp2_probe(struct platform_device *pdev)
 			if (err < 0)
 				goto err_gop_clk;
 
-			priv->mg_core_clk = devm_clk_get(&pdev->dev, "mg_core_clk");
+			priv->mg_core_clk = devm_clk_get_optional(&pdev->dev, "mg_core_clk");
 			if (IS_ERR(priv->mg_core_clk)) {
-				priv->mg_core_clk = NULL;
-			} else {
-				err = clk_prepare_enable(priv->mg_core_clk);
-				if (err < 0)
-					goto err_mg_clk;
+				err = PTR_ERR(priv->mg_core_clk);
+				goto err_mg_clk;
 			}
+
+			err = clk_prepare_enable(priv->mg_core_clk);
+			if (err < 0)
+				goto err_mg_clk;
 		}
 
-		priv->axi_clk = devm_clk_get(&pdev->dev, "axi_clk");
+		priv->axi_clk = devm_clk_get_optional(&pdev->dev, "axi_clk");
 		if (IS_ERR(priv->axi_clk)) {
 			err = PTR_ERR(priv->axi_clk);
-			if (err == -EPROBE_DEFER)
-				goto err_mg_core_clk;
-			priv->axi_clk = NULL;
-		} else {
-			err = clk_prepare_enable(priv->axi_clk);
-			if (err < 0)
-				goto err_mg_core_clk;
+			goto err_mg_core_clk;
 		}
 
+		err = clk_prepare_enable(priv->axi_clk);
+		if (err < 0)
+			goto err_mg_core_clk;
+
 		/* Get system's tclk rate */
 		priv->tclk = clk_get_rate(priv->pp_clk);
-	} else if (device_property_read_u32(&pdev->dev, "clock-frequency",
-					    &priv->tclk)) {
-		dev_err(&pdev->dev, "missing clock-frequency value\n");
-		return -EINVAL;
+	} else {
+		err = device_property_read_u32(&pdev->dev, "clock-frequency", &priv->tclk);
+		if (err) {
+			dev_err(&pdev->dev, "missing clock-frequency value\n");
+			return err;
+		}
 	}
 
 	if (priv->hw_version >= MVPP22) {
@@ -7588,6 +7587,8 @@ static int mvpp2_probe(struct platform_device *pdev)
 	return 0;
 
 err_port_probe:
+	fwnode_handle_put(port_fwnode);
+
 	i = 0;
 	fwnode_for_each_available_child_node(fwnode, port_fwnode) {
 		if (priv->port_list[i])
@@ -7596,13 +7597,10 @@ err_port_probe:
 	}
 err_axi_clk:
 	clk_disable_unprepare(priv->axi_clk);
-
 err_mg_core_clk:
-	if (priv->hw_version >= MVPP22)
-		clk_disable_unprepare(priv->mg_core_clk);
+	clk_disable_unprepare(priv->mg_core_clk);
 err_mg_clk:
-	if (priv->hw_version >= MVPP22)
-		clk_disable_unprepare(priv->mg_clk);
+	clk_disable_unprepare(priv->mg_clk);
 err_gop_clk:
 	clk_disable_unprepare(priv->gop_clk);
 err_pp_clk:
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index 7cc7d72d761e..93575800ca92 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -394,9 +394,6 @@ static int mvpp2_prs_tcam_first_free(struct mvpp2 *priv, unsigned char start,
 	if (start > end)
 		swap(start, end);
 
-	if (end >= MVPP2_PRS_TCAM_SRAM_SIZE)
-		end = MVPP2_PRS_TCAM_SRAM_SIZE - 1;
-
 	for (tid = start; tid <= end; tid++) {
 		if (!priv->prs_shadow[tid].valid)
 			return tid;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h
index e66109367487..47f5ed006a93 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h
@@ -197,6 +197,11 @@ enum nix_scheduler {
 
 #define SDP_CHANNELS			256
 
+/* The mask is to extract lower 10-bits of channel number
+ * which CPT will pass to X2P.
+ */
+#define NIX_CHAN_CPT_X2P_MASK          (0x3ffull)
+
 /* NIX LSO format indices.
  * As of now TSO is the only one using, so statically assigning indices.
  */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index cedb2616c509..7d7dfa8d8a3f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -134,6 +134,7 @@ M(MSIX_OFFSET,		0x005, msix_offset, msg_req, msix_offset_rsp)	\
 M(VF_FLR,		0x006, vf_flr, msg_req, msg_rsp)		\
 M(PTP_OP,		0x007, ptp_op, ptp_req, ptp_rsp)		\
 M(GET_HW_CAP,		0x008, get_hw_cap, msg_req, get_hw_cap_rsp)	\
+M(SET_VF_PERM,		0x00b, set_vf_perm, set_vf_perm, msg_rsp)	\
 /* CGX mbox IDs (range 0x200 - 0x3FF) */				\
 M(CGX_START_RXTX,	0x200, cgx_start_rxtx, msg_req, msg_rsp)	\
 M(CGX_STOP_RXTX,	0x201, cgx_stop_rxtx, msg_req, msg_rsp)		\
@@ -259,7 +260,11 @@ M(NIX_BP_DISABLE,	0x8017, nix_bp_disable, nix_bp_cfg_req, msg_rsp) \
 M(NIX_GET_MAC_ADDR, 0x8018, nix_get_mac_addr, msg_req, nix_get_mac_addr_rsp) \
 M(NIX_CN10K_AQ_ENQ,	0x8019, nix_cn10k_aq_enq, nix_cn10k_aq_enq_req, \
 				nix_cn10k_aq_enq_rsp)			\
-M(NIX_GET_HW_INFO,	0x801a, nix_get_hw_info, msg_req, nix_hw_info)
+M(NIX_GET_HW_INFO,	0x801c, nix_get_hw_info, msg_req, nix_hw_info)	\
+M(NIX_BANDPROF_ALLOC,	0x801d, nix_bandprof_alloc, nix_bandprof_alloc_req, \
+				nix_bandprof_alloc_rsp)			    \
+M(NIX_BANDPROF_FREE,	0x801e, nix_bandprof_free, nix_bandprof_free_req,   \
+				msg_rsp)
 
 /* Messages initiated by AF (range 0xC00 - 0xDFF) */
 #define MBOX_UP_CGX_MESSAGES						\
@@ -611,7 +616,12 @@ enum nix_af_status {
 	NIX_AF_INVAL_SSO_PF_FUNC    = -420,
 	NIX_AF_ERR_TX_VTAG_NOSPC    = -421,
 	NIX_AF_ERR_RX_VTAG_INUSE    = -422,
-	NIX_AF_ERR_NPC_KEY_NOT_SUPP = -423,
+	NIX_AF_ERR_PTP_CONFIG_FAIL  = -423,
+	NIX_AF_ERR_NPC_KEY_NOT_SUPP = -424,
+	NIX_AF_ERR_INVALID_NIXBLK   = -425,
+	NIX_AF_ERR_INVALID_BANDPROF = -426,
+	NIX_AF_ERR_IPOLICER_NOTSUPP = -427,
+	NIX_AF_ERR_BANDPROF_INVAL_REQ  = -428,
 };
 
 /* For NIX RX vtag action  */
@@ -680,6 +690,7 @@ struct nix_cn10k_aq_enq_req {
 		struct nix_cq_ctx_s cq;
 		struct nix_rsse_s   rss;
 		struct nix_rx_mce_s mce;
+		struct nix_bandprof_s prof;
 	};
 	union {
 		struct nix_cn10k_rq_ctx_s rq_mask;
@@ -687,6 +698,7 @@ struct nix_cn10k_aq_enq_req {
 		struct nix_cq_ctx_s cq_mask;
 		struct nix_rsse_s   rss_mask;
 		struct nix_rx_mce_s mce_mask;
+		struct nix_bandprof_s prof_mask;
 	};
 };
 
@@ -698,6 +710,7 @@ struct nix_cn10k_aq_enq_rsp {
 		struct nix_cq_ctx_s cq;
 		struct nix_rsse_s   rss;
 		struct nix_rx_mce_s mce;
+		struct nix_bandprof_s prof;
 	};
 };
 
@@ -713,6 +726,7 @@ struct nix_aq_enq_req {
 		struct nix_cq_ctx_s cq;
 		struct nix_rsse_s   rss;
 		struct nix_rx_mce_s mce;
+		u64 prof;
 	};
 	union {
 		struct nix_rq_ctx_s rq_mask;
@@ -720,6 +734,7 @@ struct nix_aq_enq_req {
 		struct nix_cq_ctx_s cq_mask;
 		struct nix_rsse_s   rss_mask;
 		struct nix_rx_mce_s mce_mask;
+		u64 prof_mask;
 	};
 };
 
@@ -731,6 +746,7 @@ struct nix_aq_enq_rsp {
 		struct nix_cq_ctx_s cq;
 		struct nix_rsse_s   rss;
 		struct nix_rx_mce_s mce;
+		u64 prof;
 	};
 };
 
@@ -913,6 +929,7 @@ struct nix_rx_mode {
 #define NIX_RX_MODE_UCAST	BIT(0)
 #define NIX_RX_MODE_PROMISC	BIT(1)
 #define NIX_RX_MODE_ALLMULTI	BIT(2)
+#define NIX_RX_MODE_USE_MCE	BIT(3)
 	u16	mode;
 };
 
@@ -971,6 +988,31 @@ struct nix_hw_info {
 	u16 min_mtu;
 };
 
+struct nix_bandprof_alloc_req {
+	struct mbox_msghdr hdr;
+	/* Count of profiles needed per layer */
+	u16 prof_count[BAND_PROF_NUM_LAYERS];
+};
+
+struct nix_bandprof_alloc_rsp {
+	struct mbox_msghdr hdr;
+	u16 prof_count[BAND_PROF_NUM_LAYERS];
+
+	/* There is no need to allocate morethan 1 bandwidth profile
+	 * per RQ of a PF_FUNC's NIXLF. So limit the maximum
+	 * profiles to 64 per PF_FUNC.
+	 */
+#define MAX_BANDPROF_PER_PFFUNC	64
+	u16 prof_idx[BAND_PROF_NUM_LAYERS][MAX_BANDPROF_PER_PFFUNC];
+};
+
+struct nix_bandprof_free_req {
+	struct mbox_msghdr hdr;
+	u8 free_all;
+	u16 prof_count[BAND_PROF_NUM_LAYERS];
+	u16 prof_idx[BAND_PROF_NUM_LAYERS][MAX_BANDPROF_PER_PFFUNC];
+};
+
 /* NPC mbox message structs */
 
 #define NPC_MCAM_ENTRY_INVALID	0xFFFF
@@ -1228,6 +1270,14 @@ struct ptp_rsp {
 	u64 clk;
 };
 
+struct set_vf_perm  {
+	struct  mbox_msghdr hdr;
+	u16	vf;
+#define RESET_VF_PERM		BIT_ULL(0)
+#define	VF_TRUSTED		BIT_ULL(1)
+	u64	flags;
+};
+
 /* CPT mailbox error codes
  * Range 901 - 1000.
  */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
index 1e012e787260..19bad9a59c8f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
@@ -33,6 +33,10 @@ enum npc_kpu_la_ltype {
 	NPC_LT_LA_IH_2_ETHER,
 	NPC_LT_LA_HIGIG2_ETHER,
 	NPC_LT_LA_IH_NIX_HIGIG2_ETHER,
+	NPC_LT_LA_CUSTOM_L2_90B_ETHER,
+	NPC_LT_LA_CH_LEN_90B_ETHER,
+	NPC_LT_LA_CPT_HDR,
+	NPC_LT_LA_CUSTOM_L2_24B_ETHER,
 	NPC_LT_LA_CUSTOM0 = 0xE,
 	NPC_LT_LA_CUSTOM1 = 0xF,
 };
@@ -42,7 +46,7 @@ enum npc_kpu_lb_ltype {
 	NPC_LT_LB_CTAG,
 	NPC_LT_LB_STAG_QINQ,
 	NPC_LT_LB_BTAG,
-	NPC_LT_LB_ITAG,
+	NPC_LT_LB_PPPOE,
 	NPC_LT_LB_DSA,
 	NPC_LT_LB_DSA_VLAN,
 	NPC_LT_LB_EDSA,
@@ -50,6 +54,7 @@ enum npc_kpu_lb_ltype {
 	NPC_LT_LB_EXDSA,
 	NPC_LT_LB_EXDSA_VLAN,
 	NPC_LT_LB_FDSA,
+	NPC_LT_LB_VLAN_EXDSA,
 	NPC_LT_LB_CUSTOM0 = 0xE,
 	NPC_LT_LB_CUSTOM1 = 0xF,
 };
@@ -65,6 +70,7 @@ enum npc_kpu_lc_ltype {
 	NPC_LT_LC_NSH,
 	NPC_LT_LC_PTP,
 	NPC_LT_LC_FCOE,
+	NPC_LT_LC_NGIO,
 	NPC_LT_LC_CUSTOM0 = 0xE,
 	NPC_LT_LC_CUSTOM1 = 0xF,
 };
@@ -146,7 +152,14 @@ enum npc_kpu_lh_ltype {
  * Ethernet interfaces, LBK interfaces, etc.
  */
 enum npc_pkind_type {
-	NPC_TX_DEF_PKIND = 63ULL,	/* NIX-TX PKIND */
+	NPC_RX_VLAN_EXDSA_PKIND = 56ULL,
+	NPC_RX_CHLEN24B_PKIND = 57ULL,
+	NPC_RX_CPT_HDR_PKIND,
+	NPC_RX_CHLEN90B_PKIND,
+	NPC_TX_HIGIG_PKIND,
+	NPC_RX_HIGIG_PKIND,
+	NPC_RX_EDSA_PKIND,
+	NPC_TX_DEF_PKIND,	/* NIX-TX PKIND */
 };
 
 /* list of known and supported fields in packet header and
@@ -213,7 +226,7 @@ struct npc_kpu_profile_cam {
 	u16 dp1_mask;
 	u16 dp2;
 	u16 dp2_mask;
-};
+} __packed;
 
 struct npc_kpu_profile_action {
 	u8 errlev;
@@ -233,13 +246,13 @@ struct npc_kpu_profile_action {
 	u8 mask;
 	u8 right;
 	u8 shift;
-};
+} __packed;
 
 struct npc_kpu_profile {
 	int cam_entries;
 	int action_entries;
-	const struct npc_kpu_profile_cam *cam;
-	const struct npc_kpu_profile_action *action;
+	struct npc_kpu_profile_cam *cam;
+	struct npc_kpu_profile_action *action;
 };
 
 /* NPC KPU register formats */
@@ -425,7 +438,19 @@ struct nix_tx_action {
 /* NPC MCAM reserved entry index per nixlf */
 #define NIXLF_UCAST_ENTRY	0
 #define NIXLF_BCAST_ENTRY	1
-#define NIXLF_PROMISC_ENTRY	2
+#define NIXLF_ALLMULTI_ENTRY	2
+#define NIXLF_PROMISC_ENTRY	3
+
+struct npc_coalesced_kpu_prfl {
+#define NPC_SIGN	0x00666f727063706e
+#define NPC_PRFL_NAME   "npc_prfls_array"
+#define NPC_NAME_LEN	32
+	__le64 signature; /* "npcprof\0" (8 bytes/ASCII characters) */
+	u8 name[NPC_NAME_LEN]; /* KPU Profile name */
+	u64 version; /* KPU firmware/profile version */
+	u8 num_prfl; /* No of NPC profiles. */
+	u16 prfl_sz[0];
+};
 
 struct npc_mcam_kex {
 	/* MKEX Profle Header */
@@ -445,6 +470,15 @@ struct npc_mcam_kex {
 	u64 intf_ld_flags[NPC_MAX_INTF][NPC_MAX_LD][NPC_MAX_LFL];
 } __packed;
 
+struct npc_kpu_fwdata {
+	int	entries;
+	/* What follows is:
+	 * struct npc_kpu_profile_cam[entries];
+	 * struct npc_kpu_profile_action[entries];
+	 */
+	u8	data[0];
+} __packed;
+
 struct npc_lt_def {
 	u8	ltype_mask;
 	u8	ltype_match;
@@ -459,6 +493,29 @@ struct npc_lt_def_ipsec {
 	u8	spi_nz;
 };
 
+struct npc_lt_def_apad {
+	u8	ltype_mask;
+	u8	ltype_match;
+	u8	lid;
+	u8	valid;
+} __packed;
+
+struct npc_lt_def_color {
+	u8	ltype_mask;
+	u8	ltype_match;
+	u8	lid;
+	u8	noffset;
+	u8	offset;
+} __packed;
+
+struct npc_lt_def_et {
+	u8	ltype_mask;
+	u8	ltype_match;
+	u8	lid;
+	u8	valid;
+	u8	offset;
+} __packed;
+
 struct npc_lt_def_cfg {
 	struct npc_lt_def	rx_ol2;
 	struct npc_lt_def	rx_oip4;
@@ -476,7 +533,41 @@ struct npc_lt_def_cfg {
 	struct npc_lt_def	pck_oip4;
 	struct npc_lt_def	pck_oip6;
 	struct npc_lt_def	pck_iip4;
-};
+	struct npc_lt_def_apad	rx_apad0;
+	struct npc_lt_def_apad	rx_apad1;
+	struct npc_lt_def_color	ovlan;
+	struct npc_lt_def_color	ivlan;
+	struct npc_lt_def_color	rx_gen0_color;
+	struct npc_lt_def_color	rx_gen1_color;
+	struct npc_lt_def_et	rx_et[2];
+} __packed;
+
+/* Loadable KPU profile firmware data */
+struct npc_kpu_profile_fwdata {
+#define KPU_SIGN	0x00666f727075706b
+#define KPU_NAME_LEN	32
+/** Maximum number of custom KPU entries supported by the built-in profile. */
+#define KPU_MAX_CST_ENT	2
+	/* KPU Profle Header */
+	__le64	signature; /* "kpuprof\0" (8 bytes/ASCII characters) */
+	u8	name[KPU_NAME_LEN]; /* KPU Profile name */
+	__le64	version; /* KPU profile version */
+	u8	kpus;
+	u8	reserved[7];
+
+	/* Default MKEX profile to be used with this KPU profile. May be
+	 * overridden with mkex_profile module parameter. Format is same as for
+	 * the MKEX profile to streamline processing.
+	 */
+	struct npc_mcam_kex	mkex;
+	/* LTYPE values for specific HW offloaded protocols. */
+	struct npc_lt_def_cfg	lt_def;
+	/* Dynamically sized data:
+	 *  Custom KPU CAM and ACTION configuration entries.
+	 * struct npc_kpu_fwdata kpu[kpus];
+	 */
+	u8	data[0];
+} __packed;
 
 struct rvu_npc_mcam_rule {
 	struct flow_msg packet;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h
index 5c372d2c24a1..fee655cc7523 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h
@@ -11,7 +11,10 @@
 #ifndef NPC_PROFILE_H
 #define NPC_PROFILE_H
 
-#define NPC_KPU_PROFILE_VER    0x0000000100050000
+#define NPC_KPU_PROFILE_VER	0x0000000100060000
+#define NPC_KPU_VER_MAJ(ver)	((u16)(((ver) >> 32) & 0xFFFF))
+#define NPC_KPU_VER_MIN(ver)	((u16)(((ver) >> 16) & 0xFFFF))
+#define NPC_KPU_VER_PATCH(ver)	((u16)((ver) & 0xFFFF))
 
 #define NPC_IH_W		0x8000
 #define NPC_IH_UTAG		0x2000
@@ -20,6 +23,7 @@
 #define NPC_ETYPE_IP6		0x86dd
 #define NPC_ETYPE_ARP		0x0806
 #define NPC_ETYPE_RARP		0x8035
+#define NPC_ETYPE_NGIO		0x8842
 #define NPC_ETYPE_MPLSU		0x8847
 #define NPC_ETYPE_MPLSM		0x8848
 #define NPC_ETYPE_ETAG		0x893f
@@ -33,6 +37,10 @@
 #define NPC_ETYPE_PPP		0x880b
 #define NPC_ETYPE_NSH		0x894f
 #define NPC_ETYPE_DSA		0xdada
+#define NPC_ETYPE_PPPOE		0x8864
+
+#define NPC_PPP_IP		0x0021
+#define NPC_PPP_IP6		0x0057
 
 #define NPC_IPNH_HOP		0
 #define NPC_IPNH_ICMP		1
@@ -142,14 +150,15 @@
 #define NPC_DSA_EDSA		0x8000
 #define NPC_DSA_FDSA		0xc000
 
-#define NPC_KEXOF_DMAC	8
-#define MKEX_SIGN	0x19bbfdbd15f /* strtoull of "mkexprof" with base:36 */
+#define NPC_KEXOF_DMAC	9
+#define MKEX_SIGN      0x19bbfdbd15f
 #define KEX_LD_CFG(bytesm1, hdr_ofs, ena, flags_ena, key_ofs)		\
 			(((bytesm1) << 16) | ((hdr_ofs) << 8) | ((ena) << 7) | \
 			 ((flags_ena) << 6) | ((key_ofs) & 0x3F))
 
 /* Rx parse key extract nibble enable */
 #define NPC_PARSE_NIBBLE_INTF_RX	(NPC_PARSE_NIBBLE_CHAN | \
+					 NPC_PARSE_NIBBLE_ERRCODE | \
 					 NPC_PARSE_NIBBLE_LA_LTYPE | \
 					 NPC_PARSE_NIBBLE_LB_LTYPE | \
 					 NPC_PARSE_NIBBLE_LC_LTYPE | \
@@ -170,25 +179,31 @@ enum npc_kpu_parser_state {
 	NPC_S_KPU1_EXDSA,
 	NPC_S_KPU1_HIGIG2,
 	NPC_S_KPU1_IH_NIX_HIGIG2,
+	NPC_S_KPU1_CUSTOM_L2_90B,
+	NPC_S_KPU1_CPT_HDR,
+	NPC_S_KPU1_CUSTOM_L2_24B,
+	NPC_S_KPU1_VLAN_EXDSA,
 	NPC_S_KPU2_CTAG,
 	NPC_S_KPU2_CTAG2,
 	NPC_S_KPU2_SBTAG,
 	NPC_S_KPU2_QINQ,
 	NPC_S_KPU2_ETAG,
-	NPC_S_KPU2_ITAG,
 	NPC_S_KPU2_PREHEADER,
 	NPC_S_KPU2_EXDSA,
+	NPC_S_KPU2_NGIO,
 	NPC_S_KPU3_CTAG,
 	NPC_S_KPU3_STAG,
 	NPC_S_KPU3_QINQ,
-	NPC_S_KPU3_ITAG,
 	NPC_S_KPU3_CTAG_C,
 	NPC_S_KPU3_STAG_C,
 	NPC_S_KPU3_QINQ_C,
 	NPC_S_KPU3_DSA,
+	NPC_S_KPU3_VLAN_EXDSA,
 	NPC_S_KPU4_MPLS,
 	NPC_S_KPU4_NSH,
 	NPC_S_KPU4_FDSA,
+	NPC_S_KPU4_VLAN_EXDSA,
+	NPC_S_KPU4_PPPOE,
 	NPC_S_KPU5_IP,
 	NPC_S_KPU5_IP6,
 	NPC_S_KPU5_ARP,
@@ -198,13 +213,19 @@ enum npc_kpu_parser_state {
 	NPC_S_KPU5_MPLS,
 	NPC_S_KPU5_MPLS_PL,
 	NPC_S_KPU5_NSH,
+	NPC_S_KPU5_CPT_IP,
+	NPC_S_KPU5_CPT_IP6,
 	NPC_S_KPU6_IP6_EXT,
 	NPC_S_KPU6_IP6_HOP_DEST,
 	NPC_S_KPU6_IP6_ROUT,
 	NPC_S_KPU6_IP6_FRAG,
+	NPC_S_KPU6_IP6_CPT_FRAG,
+	NPC_S_KPU6_IP6_CPT_HOP_DEST,
+	NPC_S_KPU6_IP6_CPT_ROUT,
 	NPC_S_KPU7_IP6_EXT,
 	NPC_S_KPU7_IP6_ROUT,
 	NPC_S_KPU7_IP6_FRAG,
+	NPC_S_KPU7_CPT_IP6_FRAG,
 	NPC_S_KPU8_TCP,
 	NPC_S_KPU8_UDP,
 	NPC_S_KPU8_SCTP,
@@ -265,7 +286,6 @@ enum npc_kpu_la_lflag {
 	NPC_F_LA_L_UNK_ETYPE = 1,
 	NPC_F_LA_L_WITH_VLAN,
 	NPC_F_LA_L_WITH_ETAG,
-	NPC_F_LA_L_WITH_ITAG,
 	NPC_F_LA_L_WITH_MPLS,
 	NPC_F_LA_L_WITH_NSH,
 };
@@ -442,7 +462,28 @@ enum NPC_ERRLEV_E {
 	NPC_ERRLEV_ENUM_LAST = 16,
 };
 
-static const struct npc_kpu_profile_action ikpu_action_entries[] = {
+#define NPC_KPU_NOP_CAM		\
+	{			\
+		NPC_S_NA, 0xff,	\
+		0x0000,		\
+		0x0000,		\
+		0x0000,		\
+		0x0000,		\
+		0x0000,		\
+		0x0000,		\
+	}
+
+#define NPC_KPU_NOP_ACTION			\
+	{					\
+		NPC_ERRLEV_RE, NPC_EC_NOERR,	\
+		0, 0, 0, 0, 0,			\
+		NPC_S_NA, 0, 0,			\
+		NPC_LID_LA, NPC_LT_NA,		\
+		0,				\
+		0, 0, 0, 0,			\
+	}
+
+static struct npc_kpu_profile_action ikpu_action_entries[] = {
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		12, 16, 20, 0, 0,
@@ -950,7 +991,7 @@ static const struct npc_kpu_profile_action ikpu_action_entries[] = {
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		12, 16, 20, 0, 0,
-		NPC_S_KPU1_ETHER, 0, 0,
+		NPC_S_KPU1_VLAN_EXDSA, 0, 0,
 		NPC_LID_LA, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
@@ -958,8 +999,8 @@ static const struct npc_kpu_profile_action ikpu_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		12, 16, 20, 0, 0,
-		NPC_S_KPU1_ETHER, 0, 0,
+		36, 40, 44, 0, 0,
+		NPC_S_KPU1_CUSTOM_L2_24B, 0, 0,
 		NPC_LID_LA, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
@@ -967,8 +1008,8 @@ static const struct npc_kpu_profile_action ikpu_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		12, 16, 20, 0, 0,
-		NPC_S_KPU1_ETHER, 0, 0,
+		40, 54, 58, 0, 0,
+		NPC_S_KPU1_CPT_HDR, 0, 0,
 		NPC_LID_LA, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
@@ -976,8 +1017,8 @@ static const struct npc_kpu_profile_action ikpu_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		12, 16, 20, 0, 0,
-		NPC_S_KPU1_ETHER, 0, 0,
+		102, 106, 110, 0, 0,
+		NPC_S_KPU1_CUSTOM_L2_90B, 0, 0,
 		NPC_LID_LA, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
@@ -1021,7 +1062,9 @@ static const struct npc_kpu_profile_action ikpu_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
+static struct npc_kpu_profile_cam kpu1_cam_entries[] = {
+	NPC_KPU_NOP_CAM,
+	NPC_KPU_NOP_CAM,
 	{
 		NPC_S_KPU1_ETHER, 0xff,
 		NPC_ETYPE_IP,
@@ -1080,6 +1123,15 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 		NPC_S_KPU1_ETHER, 0xff,
 		NPC_ETYPE_CTAG,
 		0xffff,
+		NPC_ETYPE_NGIO,
+		0xffff,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_ETHER, 0xff,
+		NPC_ETYPE_CTAG,
+		0xffff,
 		NPC_ETYPE_CTAG,
 		0xffff,
 		0x0000,
@@ -1123,7 +1175,7 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 	},
 	{
 		NPC_S_KPU1_ETHER, 0xff,
-		NPC_ETYPE_ITAG,
+		NPC_ETYPE_MPLSU,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -1132,7 +1184,7 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 	},
 	{
 		NPC_S_KPU1_ETHER, 0xff,
-		NPC_ETYPE_MPLSU,
+		NPC_ETYPE_MPLSM,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -1141,7 +1193,7 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 	},
 	{
 		NPC_S_KPU1_ETHER, 0xff,
-		NPC_ETYPE_MPLSM,
+		NPC_ETYPE_NSH,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -1150,7 +1202,7 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 	},
 	{
 		NPC_S_KPU1_ETHER, 0xff,
-		NPC_ETYPE_NSH,
+		NPC_ETYPE_DSA,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -1159,7 +1211,7 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 	},
 	{
 		NPC_S_KPU1_ETHER, 0xff,
-		NPC_ETYPE_DSA,
+		NPC_ETYPE_PPPOE,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -1294,15 +1346,6 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 	},
 	{
 		NPC_S_KPU1_IH_NIX, 0xff,
-		NPC_ETYPE_ITAG,
-		0xffff,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU1_IH_NIX, 0xff,
 		NPC_ETYPE_MPLSU,
 		0xffff,
 		0x0000,
@@ -1339,8 +1382,8 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 	},
 	{
 		NPC_S_KPU1_IH, 0xff,
-		NPC_IH_W|NPC_IH_UTAG,
-		NPC_IH_W|NPC_IH_UTAG,
+		NPC_IH_W | NPC_IH_UTAG,
+		NPC_IH_W | NPC_IH_UTAG,
 		0x0000,
 		0x0000,
 		0x0000,
@@ -1349,7 +1392,7 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 	{
 		NPC_S_KPU1_IH, 0xff,
 		NPC_IH_W,
-		NPC_IH_W|NPC_IH_UTAG,
+		NPC_IH_W | NPC_IH_UTAG,
 		0x0000,
 		0x0000,
 		0x0000,
@@ -1358,7 +1401,7 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 	{
 		NPC_S_KPU1_IH, 0xff,
 		0x0000,
-		NPC_IH_W|NPC_IH_UTAG,
+		NPC_IH_W | NPC_IH_UTAG,
 		0x0000,
 		0x0000,
 		0x0000,
@@ -1501,15 +1544,6 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 	},
 	{
 		NPC_S_KPU1_HIGIG2, 0xff,
-		NPC_ETYPE_ITAG,
-		0xffff,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU1_HIGIG2, 0xff,
 		NPC_ETYPE_MPLSU,
 		0xffff,
 		0x0000,
@@ -1645,7 +1679,7 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 	},
 	{
 		NPC_S_KPU1_IH_NIX_HIGIG2, 0xff,
-		NPC_ETYPE_ITAG,
+		NPC_ETYPE_MPLSU,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -1654,7 +1688,7 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 	},
 	{
 		NPC_S_KPU1_IH_NIX_HIGIG2, 0xff,
-		NPC_ETYPE_MPLSU,
+		NPC_ETYPE_MPLSM,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -1663,7 +1697,7 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 	},
 	{
 		NPC_S_KPU1_IH_NIX_HIGIG2, 0xff,
-		NPC_ETYPE_MPLSM,
+		NPC_ETYPE_NSH,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -1672,6 +1706,132 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 	},
 	{
 		NPC_S_KPU1_IH_NIX_HIGIG2, 0xff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_90B, 0xff,
+		NPC_ETYPE_IP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_90B, 0xff,
+		NPC_ETYPE_IP6,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_90B, 0xff,
+		NPC_ETYPE_ARP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_90B, 0xff,
+		NPC_ETYPE_RARP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_90B, 0xff,
+		NPC_ETYPE_PTP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_90B, 0xff,
+		NPC_ETYPE_FCOE,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_90B, 0xff,
+		NPC_ETYPE_CTAG,
+		0xffff,
+		NPC_ETYPE_CTAG,
+		0xffff,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_90B, 0xff,
+		NPC_ETYPE_CTAG,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_90B, 0xff,
+		NPC_ETYPE_SBTAG,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_90B, 0xff,
+		NPC_ETYPE_QINQ,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_90B, 0xff,
+		NPC_ETYPE_ETAG,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_90B, 0xff,
+		NPC_ETYPE_MPLSU,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_90B, 0xff,
+		NPC_ETYPE_MPLSM,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_90B, 0xff,
 		NPC_ETYPE_NSH,
 		0xffff,
 		0x0000,
@@ -1680,7 +1840,88 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 		0x0000,
 	},
 	{
-		NPC_S_KPU1_IH_NIX_HIGIG2, 0xff,
+		NPC_S_KPU1_CUSTOM_L2_90B, 0xff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CPT_HDR, 0xff,
+		0x0000,
+		0xffff,
+		NPC_ETYPE_IP,
+		0xffff,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CPT_HDR, 0xff,
+		0x0000,
+		0xffff,
+		NPC_ETYPE_IP6,
+		0xffff,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CPT_HDR, 0xff,
+		0x0000,
+		0xffff,
+		NPC_ETYPE_CTAG,
+		0xffff,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CPT_HDR, 0xff,
+		0x0000,
+		0xffff,
+		NPC_ETYPE_QINQ,
+		0xffff,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CPT_HDR, 0xff,
+		0x0000,
+		0xffff,
+		0x0000,
+		0x0000,
+		NPC_ETYPE_IP,
+		0xffff,
+	},
+	{
+		NPC_S_KPU1_CPT_HDR, 0xff,
+		0x0000,
+		0xffff,
+		0x0000,
+		0x0000,
+		NPC_ETYPE_IP6,
+		0xffff,
+	},
+	{
+		NPC_S_KPU1_CPT_HDR, 0xff,
+		0x0000,
+		0xffff,
+		0x0000,
+		0x0000,
+		NPC_ETYPE_CTAG,
+		0xffff,
+	},
+	{
+		NPC_S_KPU1_CPT_HDR, 0xff,
+		0x0000,
+		0xffff,
+		0x0000,
+		0x0000,
+		NPC_ETYPE_QINQ,
+		0xffff,
+	},
+	{
+		NPC_S_KPU1_CPT_HDR, 0xff,
 		0x0000,
 		0x0000,
 		0x0000,
@@ -1689,6 +1930,150 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 		0x0000,
 	},
 	{
+		NPC_S_KPU1_CUSTOM_L2_24B, 0xff,
+		NPC_ETYPE_IP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_24B, 0xff,
+		NPC_ETYPE_IP6,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_24B, 0xff,
+		NPC_ETYPE_ARP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_24B, 0xff,
+		NPC_ETYPE_RARP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_24B, 0xff,
+		NPC_ETYPE_PTP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_24B, 0xff,
+		NPC_ETYPE_FCOE,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_24B, 0xff,
+		NPC_ETYPE_CTAG,
+		0xffff,
+		NPC_ETYPE_CTAG,
+		0xffff,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_24B, 0xff,
+		NPC_ETYPE_CTAG,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_24B, 0xff,
+		NPC_ETYPE_SBTAG,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_24B, 0xff,
+		NPC_ETYPE_QINQ,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_24B, 0xff,
+		NPC_ETYPE_ETAG,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_24B, 0xff,
+		NPC_ETYPE_MPLSU,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_24B, 0xff,
+		NPC_ETYPE_MPLSM,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_24B, 0xff,
+		NPC_ETYPE_NSH,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_CUSTOM_L2_24B, 0xff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU1_VLAN_EXDSA, 0xff,
+		NPC_ETYPE_CTAG,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
 		NPC_S_NA, 0X00,
 		0x0000,
 		0x0000,
@@ -1699,7 +2084,9 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_cam kpu2_cam_entries[] = {
+static struct npc_kpu_profile_cam kpu2_cam_entries[] = {
+	NPC_KPU_NOP_CAM,
+	NPC_KPU_NOP_CAM,
 	{
 		NPC_S_KPU2_CTAG, 0xff,
 		NPC_ETYPE_IP,
@@ -1783,6 +2170,24 @@ static const struct npc_kpu_profile_cam kpu2_cam_entries[] = {
 	},
 	{
 		NPC_S_KPU2_CTAG, 0xff,
+		NPC_ETYPE_PPPOE,
+		0xffff,
+		0x0000,
+		0x0000,
+		NPC_PPP_IP,
+		0xffff,
+	},
+	{
+		NPC_S_KPU2_CTAG, 0xff,
+		NPC_ETYPE_PPPOE,
+		0xffff,
+		0x0000,
+		0x0000,
+		NPC_PPP_IP6,
+		0xffff,
+	},
+	{
+		NPC_S_KPU2_CTAG, 0xff,
 		0x0000,
 		0x0000,
 		0x0000,
@@ -2226,15 +2631,6 @@ static const struct npc_kpu_profile_cam kpu2_cam_entries[] = {
 		NPC_S_KPU2_ETAG, 0xff,
 		NPC_ETYPE_SBTAG,
 		0xffff,
-		NPC_ETYPE_ITAG,
-		0xffff,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU2_ETAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
 		0x0000,
 		0x0000,
 		0x0000,
@@ -2313,159 +2709,6 @@ static const struct npc_kpu_profile_cam kpu2_cam_entries[] = {
 		0x0000,
 	},
 	{
-		NPC_S_KPU2_ITAG, 0xff,
-		NPC_ETYPE_IP,
-		0xffff,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU2_ITAG, 0xff,
-		NPC_ETYPE_IP6,
-		0xffff,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU2_ITAG, 0xff,
-		NPC_ETYPE_ARP,
-		0xffff,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU2_ITAG, 0xff,
-		NPC_ETYPE_RARP,
-		0xffff,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU2_ITAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
-		NPC_ETYPE_CTAG,
-		0xffff,
-		NPC_ETYPE_IP,
-		0xffff,
-	},
-	{
-		NPC_S_KPU2_ITAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
-		NPC_ETYPE_CTAG,
-		0xffff,
-		NPC_ETYPE_IP6,
-		0xffff,
-	},
-	{
-		NPC_S_KPU2_ITAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
-		NPC_ETYPE_CTAG,
-		0xffff,
-		NPC_ETYPE_ARP,
-		0xffff,
-	},
-	{
-		NPC_S_KPU2_ITAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
-		NPC_ETYPE_CTAG,
-		0xffff,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU2_ITAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
-		NPC_ETYPE_IP,
-		0xffff,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU2_ITAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
-		NPC_ETYPE_IP6,
-		0xffff,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU2_ITAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
-		NPC_ETYPE_ARP,
-		0xffff,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU2_ITAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU2_ITAG, 0xff,
-		NPC_ETYPE_CTAG,
-		0xffff,
-		NPC_ETYPE_IP,
-		0xffff,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU2_ITAG, 0xff,
-		NPC_ETYPE_CTAG,
-		0xffff,
-		NPC_ETYPE_IP6,
-		0xffff,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU2_ITAG, 0xff,
-		NPC_ETYPE_CTAG,
-		0xffff,
-		NPC_ETYPE_ARP,
-		0xffff,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU2_ITAG, 0xff,
-		NPC_ETYPE_CTAG,
-		0xffff,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU2_ITAG, 0xff,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-	},
-	{
 		NPC_S_KPU2_CTAG2, 0xff,
 		NPC_ETYPE_IP,
 		0xffff,
@@ -2817,6 +3060,15 @@ static const struct npc_kpu_profile_cam kpu2_cam_entries[] = {
 		0x0000,
 	},
 	{
+		NPC_S_KPU2_NGIO, 0xff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
 		NPC_S_NA, 0X00,
 		0x0000,
 		0x0000,
@@ -2827,7 +3079,9 @@ static const struct npc_kpu_profile_cam kpu2_cam_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_cam kpu3_cam_entries[] = {
+static struct npc_kpu_profile_cam kpu3_cam_entries[] = {
+	NPC_KPU_NOP_CAM,
+	NPC_KPU_NOP_CAM,
 	{
 		NPC_S_KPU3_CTAG, 0xff,
 		NPC_ETYPE_IP,
@@ -3243,159 +3497,6 @@ static const struct npc_kpu_profile_cam kpu3_cam_entries[] = {
 		0x0000,
 	},
 	{
-		NPC_S_KPU3_ITAG, 0xff,
-		NPC_ETYPE_IP,
-		0xffff,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU3_ITAG, 0xff,
-		NPC_ETYPE_IP6,
-		0xffff,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU3_ITAG, 0xff,
-		NPC_ETYPE_ARP,
-		0xffff,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU3_ITAG, 0xff,
-		NPC_ETYPE_RARP,
-		0xffff,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU3_ITAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
-		NPC_ETYPE_CTAG,
-		0xffff,
-		NPC_ETYPE_IP,
-		0xffff,
-	},
-	{
-		NPC_S_KPU3_ITAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
-		NPC_ETYPE_CTAG,
-		0xffff,
-		NPC_ETYPE_IP6,
-		0xffff,
-	},
-	{
-		NPC_S_KPU3_ITAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
-		NPC_ETYPE_CTAG,
-		0xffff,
-		NPC_ETYPE_ARP,
-		0xffff,
-	},
-	{
-		NPC_S_KPU3_ITAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
-		NPC_ETYPE_IP,
-		0xffff,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU3_ITAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
-		NPC_ETYPE_IP6,
-		0xffff,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU3_ITAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
-		NPC_ETYPE_ARP,
-		0xffff,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU3_ITAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
-		NPC_ETYPE_CTAG,
-		0xffff,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU3_ITAG, 0xff,
-		NPC_ETYPE_SBTAG,
-		0xffff,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU3_ITAG, 0xff,
-		NPC_ETYPE_CTAG,
-		0xffff,
-		NPC_ETYPE_IP,
-		0xffff,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU3_ITAG, 0xff,
-		NPC_ETYPE_CTAG,
-		0xffff,
-		NPC_ETYPE_IP6,
-		0xffff,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU3_ITAG, 0xff,
-		NPC_ETYPE_CTAG,
-		0xffff,
-		NPC_ETYPE_ARP,
-		0xffff,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU3_ITAG, 0xff,
-		NPC_ETYPE_CTAG,
-		0xffff,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-	},
-	{
-		NPC_S_KPU3_ITAG, 0xff,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-		0x0000,
-	},
-	{
 		NPC_S_KPU3_CTAG_C, 0xff,
 		NPC_ETYPE_IP,
 		0xffff,
@@ -3936,6 +4037,15 @@ static const struct npc_kpu_profile_cam kpu3_cam_entries[] = {
 		0x0000,
 	},
 	{
+		NPC_S_KPU3_VLAN_EXDSA, 0xff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
 		NPC_S_NA, 0X00,
 		0x0000,
 		0x0000,
@@ -3946,7 +4056,9 @@ static const struct npc_kpu_profile_cam kpu3_cam_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_cam kpu4_cam_entries[] = {
+static struct npc_kpu_profile_cam kpu4_cam_entries[] = {
+	NPC_KPU_NOP_CAM,
+	NPC_KPU_NOP_CAM,
 	{
 		NPC_S_KPU4_MPLS, 0xff,
 		NPC_MPLS_S,
@@ -4084,6 +4196,78 @@ static const struct npc_kpu_profile_cam kpu4_cam_entries[] = {
 	},
 	{
 		NPC_S_KPU4_FDSA, 0xff,
+		NPC_ETYPE_CTAG,
+		0xffff,
+		NPC_ETYPE_IP,
+		0xffff,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_FDSA, 0xff,
+		NPC_ETYPE_CTAG,
+		0xffff,
+		NPC_ETYPE_IP6,
+		0xffff,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_FDSA, 0xff,
+		NPC_ETYPE_CTAG,
+		0xffff,
+		NPC_ETYPE_ARP,
+		0xffff,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_FDSA, 0xff,
+		NPC_ETYPE_CTAG,
+		0xffff,
+		NPC_ETYPE_RARP,
+		0xffff,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_FDSA, 0xff,
+		NPC_ETYPE_CTAG,
+		0xffff,
+		NPC_ETYPE_PTP,
+		0xffff,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_FDSA, 0xff,
+		NPC_ETYPE_CTAG,
+		0xffff,
+		NPC_ETYPE_FCOE,
+		0xffff,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_FDSA, 0xff,
+		NPC_ETYPE_PPPOE,
+		0xffff,
+		0x0000,
+		0x0000,
+		NPC_PPP_IP,
+		0xffff,
+	},
+	{
+		NPC_S_KPU4_FDSA, 0xff,
+		NPC_ETYPE_PPPOE,
+		0xffff,
+		0x0000,
+		0x0000,
+		NPC_PPP_IP6,
+		0xffff,
+	},
+	{
+		NPC_S_KPU4_FDSA, 0xff,
 		0x0000,
 		NPC_DSA_FDSA,
 		0x0000,
@@ -4092,6 +4276,87 @@ static const struct npc_kpu_profile_cam kpu4_cam_entries[] = {
 		0x0000,
 	},
 	{
+		NPC_S_KPU4_VLAN_EXDSA, 0xff,
+		NPC_ETYPE_IP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_VLAN_EXDSA, 0xff,
+		NPC_ETYPE_IP6,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_VLAN_EXDSA, 0xff,
+		NPC_ETYPE_ARP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_VLAN_EXDSA, 0xff,
+		NPC_ETYPE_RARP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_VLAN_EXDSA, 0xff,
+		NPC_ETYPE_PTP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_VLAN_EXDSA, 0xff,
+		NPC_ETYPE_FCOE,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_VLAN_EXDSA, 0xff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_PPPOE, 0xff,
+		NPC_PPP_IP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_PPPOE, 0xff,
+		NPC_PPP_IP6,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
 		NPC_S_NA, 0X00,
 		0x0000,
 		0x0000,
@@ -4102,7 +4367,9 @@ static const struct npc_kpu_profile_cam kpu4_cam_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_cam kpu5_cam_entries[] = {
+static struct npc_kpu_profile_cam kpu5_cam_entries[] = {
+	NPC_KPU_NOP_CAM,
+	NPC_KPU_NOP_CAM,
 	{
 		NPC_S_KPU5_IP, 0xff,
 		0x0000,
@@ -4125,116 +4392,116 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = {
 		NPC_S_KPU5_IP, 0xff,
 		NPC_IPNH_TCP,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
 		NPC_IPNH_UDP,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
 		NPC_IPNH_SCTP,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
 		NPC_IPNH_ICMP,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
 		NPC_IPNH_IGMP,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
 		NPC_IPNH_ESP,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
 		NPC_IPNH_AH,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
 		NPC_IPNH_GRE,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
 		NPC_IPNH_IP,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
 		NPC_IPNH_IP6,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
 		NPC_IPNH_MPLS,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
 		0x0000,
 		0x0000,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
 		0x0000,
 		0x0000,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
 		0x0000,
 	},
@@ -4245,7 +4512,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = {
 		NPC_IP_VER_4,
 		NPC_IP_VER_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
@@ -4254,7 +4521,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = {
 		NPC_IP_VER_4,
 		NPC_IP_VER_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
@@ -4263,7 +4530,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = {
 		NPC_IP_VER_4,
 		NPC_IP_VER_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
@@ -4272,7 +4539,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = {
 		NPC_IP_VER_4,
 		NPC_IP_VER_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
@@ -4281,7 +4548,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = {
 		NPC_IP_VER_4,
 		NPC_IP_VER_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
@@ -4290,7 +4557,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = {
 		NPC_IP_VER_4,
 		NPC_IP_VER_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
@@ -4299,7 +4566,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = {
 		NPC_IP_VER_4,
 		NPC_IP_VER_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
@@ -4308,7 +4575,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = {
 		NPC_IP_VER_4,
 		NPC_IP_VER_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
@@ -4317,7 +4584,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = {
 		NPC_IP_VER_4,
 		NPC_IP_VER_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
@@ -4326,7 +4593,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = {
 		NPC_IP_VER_4,
 		NPC_IP_VER_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
@@ -4335,7 +4602,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = {
 		NPC_IP_VER_4,
 		NPC_IP_VER_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
@@ -4344,7 +4611,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = {
 		NPC_IP_VER_4,
 		NPC_IP_VER_MASK,
 		0x0000,
-		NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF,
+		NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF,
 	},
 	{
 		NPC_S_KPU5_IP, 0xff,
@@ -4662,6 +4929,429 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = {
 		0x0000,
 	},
 	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		0x0000,
+		NPC_IP_TTL_MASK,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0001,
+		NPC_IP_HDR_FRAGOFF,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_TCP,
+		0x00ff,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_UDP,
+		0x00ff,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_SCTP,
+		0x00ff,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_ICMP,
+		0x00ff,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_IGMP,
+		0x00ff,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_ESP,
+		0x00ff,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_AH,
+		0x00ff,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_GRE,
+		0x00ff,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_IP,
+		0x00ff,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_IP6,
+		0x00ff,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_MPLS,
+		0x00ff,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		0x0000,
+		0x0000,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_TCP,
+		0x00ff,
+		NPC_IP_VER_4,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_UDP,
+		0x00ff,
+		NPC_IP_VER_4,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_SCTP,
+		0x00ff,
+		NPC_IP_VER_4,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_ICMP,
+		0x00ff,
+		NPC_IP_VER_4,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_IGMP,
+		0x00ff,
+		NPC_IP_VER_4,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_ESP,
+		0x00ff,
+		NPC_IP_VER_4,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_AH,
+		0x00ff,
+		NPC_IP_VER_4,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_GRE,
+		0x00ff,
+		NPC_IP_VER_4,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_IP,
+		0x00ff,
+		NPC_IP_VER_4,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_IP6,
+		0x00ff,
+		NPC_IP_VER_4,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		NPC_IPNH_MPLS,
+		0x00ff,
+		NPC_IP_VER_4,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		0x0000,
+		0x0000,
+		NPC_IP_VER_4,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP, 0xff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		0x0000,
+		NPC_IP6_HOP_MASK,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_TCP << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_UDP << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_SCTP << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_ICMP << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_ICMP6 << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_GRE << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_IP6 << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_MPLS << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_HOP << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_DEST << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_ROUT << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_FRAG << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_ESP << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_AH << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_MOBILITY << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_HOSTID << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		NPC_IPNH_SHIM6 << 8,
+		0xff00,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		0x0000,
+		0x0000,
+		NPC_IP_VER_6,
+		NPC_IP_VER_MASK,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU5_CPT_IP6, 0xff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
 		NPC_S_NA, 0X00,
 		0x0000,
 		0x0000,
@@ -4672,7 +5362,9 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_cam kpu6_cam_entries[] = {
+static struct npc_kpu_profile_cam kpu6_cam_entries[] = {
+	NPC_KPU_NOP_CAM,
+	NPC_KPU_NOP_CAM,
 	{
 		NPC_S_KPU6_IP6_EXT, 0xff,
 		0x0000,
@@ -5007,6 +5699,330 @@ static const struct npc_kpu_profile_cam kpu6_cam_entries[] = {
 		0x0000,
 	},
 	{
+		NPC_S_KPU6_IP6_CPT_FRAG, 0xff,
+		NPC_IPNH_TCP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_FRAG, 0xff,
+		NPC_IPNH_UDP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_FRAG, 0xff,
+		NPC_IPNH_SCTP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_FRAG, 0xff,
+		NPC_IPNH_ICMP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_FRAG, 0xff,
+		NPC_IPNH_ICMP6 << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_FRAG, 0xff,
+		NPC_IPNH_ESP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_FRAG, 0xff,
+		NPC_IPNH_AH << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_FRAG, 0xff,
+		NPC_IPNH_GRE << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_FRAG, 0xff,
+		NPC_IPNH_IP6 << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_FRAG, 0xff,
+		NPC_IPNH_MPLS << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_FRAG, 0xff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff,
+		NPC_IPNH_TCP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff,
+		NPC_IPNH_UDP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff,
+		NPC_IPNH_SCTP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff,
+		NPC_IPNH_ICMP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff,
+		NPC_IPNH_ICMP6 << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff,
+		NPC_IPNH_ESP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff,
+		NPC_IPNH_AH << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff,
+		NPC_IPNH_GRE << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff,
+		NPC_IPNH_IP6 << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff,
+		NPC_IPNH_MPLS << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff,
+		NPC_IPNH_ROUT << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff,
+		NPC_IPNH_FRAG << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_ROUT, 0xff,
+		NPC_IPNH_TCP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_ROUT, 0xff,
+		NPC_IPNH_UDP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_ROUT, 0xff,
+		NPC_IPNH_SCTP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_ROUT, 0xff,
+		NPC_IPNH_ICMP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_ROUT, 0xff,
+		NPC_IPNH_ICMP6 << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_ROUT, 0xff,
+		NPC_IPNH_ESP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_ROUT, 0xff,
+		NPC_IPNH_AH << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_ROUT, 0xff,
+		NPC_IPNH_GRE << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_ROUT, 0xff,
+		NPC_IPNH_IP6 << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_ROUT, 0xff,
+		NPC_IPNH_MPLS << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_ROUT, 0xff,
+		NPC_IPNH_FRAG << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU6_IP6_CPT_ROUT, 0xff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
 		NPC_S_NA, 0X00,
 		0x0000,
 		0x0000,
@@ -5017,7 +6033,9 @@ static const struct npc_kpu_profile_cam kpu6_cam_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_cam kpu7_cam_entries[] = {
+static struct npc_kpu_profile_cam kpu7_cam_entries[] = {
+	NPC_KPU_NOP_CAM,
+	NPC_KPU_NOP_CAM,
 	{
 		NPC_S_KPU7_IP6_EXT, 0xff,
 		0x0000,
@@ -5226,6 +6244,105 @@ static const struct npc_kpu_profile_cam kpu7_cam_entries[] = {
 		0x0000,
 	},
 	{
+		NPC_S_KPU7_CPT_IP6_FRAG, 0xff,
+		NPC_IPNH_TCP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU7_CPT_IP6_FRAG, 0xff,
+		NPC_IPNH_UDP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU7_CPT_IP6_FRAG, 0xff,
+		NPC_IPNH_SCTP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU7_CPT_IP6_FRAG, 0xff,
+		NPC_IPNH_ICMP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU7_CPT_IP6_FRAG, 0xff,
+		NPC_IPNH_ICMP6 << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU7_CPT_IP6_FRAG, 0xff,
+		NPC_IPNH_ESP << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU7_CPT_IP6_FRAG, 0xff,
+		NPC_IPNH_AH << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU7_CPT_IP6_FRAG, 0xff,
+		NPC_IPNH_GRE << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU7_CPT_IP6_FRAG, 0xff,
+		NPC_IPNH_IP6 << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU7_CPT_IP6_FRAG, 0xff,
+		NPC_IPNH_MPLS << 8,
+		0xff00,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU7_CPT_IP6_FRAG, 0xff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
 		NPC_S_NA, 0X00,
 		0x0000,
 		0x0000,
@@ -5236,7 +6353,9 @@ static const struct npc_kpu_profile_cam kpu7_cam_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
+static struct npc_kpu_profile_cam kpu8_cam_entries[] = {
+	NPC_KPU_NOP_CAM,
+	NPC_KPU_NOP_CAM,
 	{
 		NPC_S_KPU8_TCP, 0xff,
 		0x0000,
@@ -5259,8 +6378,8 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_TCP, 0xff,
 		0x0000,
 		0x0000,
-		NPC_TCP_FLAGS_RST|NPC_TCP_FLAGS_FIN,
-		NPC_TCP_FLAGS_RST|NPC_TCP_FLAGS_FIN,
+		NPC_TCP_FLAGS_RST | NPC_TCP_FLAGS_FIN,
+		NPC_TCP_FLAGS_RST | NPC_TCP_FLAGS_FIN,
 		0x0000,
 		0x0000,
 	},
@@ -5268,8 +6387,8 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_TCP, 0xff,
 		0x0000,
 		0x0000,
-		NPC_TCP_FLAGS_URG|NPC_TCP_FLAGS_SYN,
-		NPC_TCP_FLAGS_URG|NPC_TCP_FLAGS_SYN,
+		NPC_TCP_FLAGS_URG | NPC_TCP_FLAGS_SYN,
+		NPC_TCP_FLAGS_URG | NPC_TCP_FLAGS_SYN,
 		0x0000,
 		0x0000,
 	},
@@ -5277,8 +6396,8 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_TCP, 0xff,
 		0x0000,
 		0x0000,
-		NPC_TCP_FLAGS_RST|NPC_TCP_FLAGS_SYN,
-		NPC_TCP_FLAGS_RST|NPC_TCP_FLAGS_SYN,
+		NPC_TCP_FLAGS_RST | NPC_TCP_FLAGS_SYN,
+		NPC_TCP_FLAGS_RST | NPC_TCP_FLAGS_SYN,
 		0x0000,
 		0x0000,
 	},
@@ -5286,8 +6405,8 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_TCP, 0xff,
 		0x0000,
 		0x0000,
-		NPC_TCP_FLAGS_SYN|NPC_TCP_FLAGS_FIN,
-		NPC_TCP_FLAGS_SYN|NPC_TCP_FLAGS_FIN,
+		NPC_TCP_FLAGS_SYN | NPC_TCP_FLAGS_FIN,
+		NPC_TCP_FLAGS_SYN | NPC_TCP_FLAGS_FIN,
 		0x0000,
 		0x0000,
 	},
@@ -5565,7 +6684,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_MPLSU,
 		0xffff,
-		NPC_GRE_F_CSUM|NPC_GRE_F_KEY,
+		NPC_GRE_F_CSUM | NPC_GRE_F_KEY,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5574,7 +6693,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_MPLSU,
 		0xffff,
-		NPC_GRE_F_CSUM|NPC_GRE_F_SEQ,
+		NPC_GRE_F_CSUM | NPC_GRE_F_SEQ,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5583,7 +6702,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_MPLSU,
 		0xffff,
-		NPC_GRE_F_KEY|NPC_GRE_F_SEQ,
+		NPC_GRE_F_KEY | NPC_GRE_F_SEQ,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5592,7 +6711,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_MPLSU,
 		0xffff,
-		NPC_GRE_F_CSUM|NPC_GRE_F_KEY|NPC_GRE_F_SEQ,
+		NPC_GRE_F_CSUM | NPC_GRE_F_KEY | NPC_GRE_F_SEQ,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5637,7 +6756,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_MPLSM,
 		0xffff,
-		NPC_GRE_F_CSUM|NPC_GRE_F_KEY,
+		NPC_GRE_F_CSUM | NPC_GRE_F_KEY,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5646,7 +6765,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_MPLSM,
 		0xffff,
-		NPC_GRE_F_CSUM|NPC_GRE_F_SEQ,
+		NPC_GRE_F_CSUM | NPC_GRE_F_SEQ,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5655,7 +6774,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_MPLSM,
 		0xffff,
-		NPC_GRE_F_KEY|NPC_GRE_F_SEQ,
+		NPC_GRE_F_KEY | NPC_GRE_F_SEQ,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5664,7 +6783,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_MPLSM,
 		0xffff,
-		NPC_GRE_F_CSUM|NPC_GRE_F_KEY|NPC_GRE_F_SEQ,
+		NPC_GRE_F_CSUM | NPC_GRE_F_KEY | NPC_GRE_F_SEQ,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5709,7 +6828,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_NSH,
 		0xffff,
-		NPC_GRE_F_CSUM|NPC_GRE_F_KEY,
+		NPC_GRE_F_CSUM | NPC_GRE_F_KEY,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5718,7 +6837,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_NSH,
 		0xffff,
-		NPC_GRE_F_CSUM|NPC_GRE_F_SEQ,
+		NPC_GRE_F_CSUM | NPC_GRE_F_SEQ,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5727,7 +6846,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_NSH,
 		0xffff,
-		NPC_GRE_F_KEY|NPC_GRE_F_SEQ,
+		NPC_GRE_F_KEY | NPC_GRE_F_SEQ,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5736,7 +6855,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_NSH,
 		0xffff,
-		NPC_GRE_F_CSUM|NPC_GRE_F_KEY|NPC_GRE_F_SEQ,
+		NPC_GRE_F_CSUM | NPC_GRE_F_KEY | NPC_GRE_F_SEQ,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5781,7 +6900,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_IP,
 		0xffff,
-		NPC_GRE_F_CSUM|NPC_GRE_F_KEY,
+		NPC_GRE_F_CSUM | NPC_GRE_F_KEY,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5790,7 +6909,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_IP,
 		0xffff,
-		NPC_GRE_F_CSUM|NPC_GRE_F_SEQ,
+		NPC_GRE_F_CSUM | NPC_GRE_F_SEQ,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5799,7 +6918,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_IP,
 		0xffff,
-		NPC_GRE_F_KEY|NPC_GRE_F_SEQ,
+		NPC_GRE_F_KEY | NPC_GRE_F_SEQ,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5808,7 +6927,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_IP,
 		0xffff,
-		NPC_GRE_F_CSUM|NPC_GRE_F_KEY|NPC_GRE_F_SEQ,
+		NPC_GRE_F_CSUM | NPC_GRE_F_KEY | NPC_GRE_F_SEQ,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5853,7 +6972,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_IP6,
 		0xffff,
-		NPC_GRE_F_CSUM|NPC_GRE_F_KEY,
+		NPC_GRE_F_CSUM | NPC_GRE_F_KEY,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5862,7 +6981,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_IP6,
 		0xffff,
-		NPC_GRE_F_CSUM|NPC_GRE_F_SEQ,
+		NPC_GRE_F_CSUM | NPC_GRE_F_SEQ,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5871,7 +6990,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_IP6,
 		0xffff,
-		NPC_GRE_F_KEY|NPC_GRE_F_SEQ,
+		NPC_GRE_F_KEY | NPC_GRE_F_SEQ,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5880,7 +6999,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_IP6,
 		0xffff,
-		NPC_GRE_F_CSUM|NPC_GRE_F_KEY|NPC_GRE_F_SEQ,
+		NPC_GRE_F_CSUM | NPC_GRE_F_KEY | NPC_GRE_F_SEQ,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5916,7 +7035,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_PPP,
 		0xffff,
-		NPC_GRE_F_KEY|NPC_GRE_VER_1,
+		NPC_GRE_F_KEY | NPC_GRE_VER_1,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5925,7 +7044,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_PPP,
 		0xffff,
-		NPC_GRE_F_KEY|NPC_GRE_F_SEQ|NPC_GRE_VER_1,
+		NPC_GRE_F_KEY | NPC_GRE_F_SEQ | NPC_GRE_VER_1,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5934,7 +7053,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_PPP,
 		0xffff,
-		NPC_GRE_F_KEY|NPC_GRE_F_ACK|NPC_GRE_VER_1,
+		NPC_GRE_F_KEY | NPC_GRE_F_ACK | NPC_GRE_VER_1,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5943,7 +7062,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		NPC_S_KPU8_GRE, 0xff,
 		NPC_ETYPE_PPP,
 		0xffff,
-		NPC_GRE_F_KEY|NPC_GRE_F_SEQ|NPC_GRE_F_ACK|NPC_GRE_VER_1,
+		NPC_GRE_F_KEY | NPC_GRE_F_SEQ | NPC_GRE_F_ACK | NPC_GRE_VER_1,
 		0xffff,
 		0x0000,
 		0x0000,
@@ -5977,7 +7096,9 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_cam kpu9_cam_entries[] = {
+static struct npc_kpu_profile_cam kpu9_cam_entries[] = {
+	NPC_KPU_NOP_CAM,
+	NPC_KPU_NOP_CAM,
 	{
 		NPC_S_KPU9_TU_MPLS_IN_GRE, 0xff,
 		NPC_MPLS_S,
@@ -6387,8 +7508,8 @@ static const struct npc_kpu_profile_cam kpu9_cam_entries[] = {
 		NPC_S_KPU9_GTPU, 0xff,
 		0x0000,
 		0x0000,
-		0x0000,
-		0x0000,
+		NPC_GTP_PT_GTP | NPC_GTP_VER1,
+		NPC_GTP_PT_MASK | NPC_GTP_VER_MASK,
 		0x0000,
 		0x0000,
 	},
@@ -6448,7 +7569,9 @@ static const struct npc_kpu_profile_cam kpu9_cam_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_cam kpu10_cam_entries[] = {
+static struct npc_kpu_profile_cam kpu10_cam_entries[] = {
+	NPC_KPU_NOP_CAM,
+	NPC_KPU_NOP_CAM,
 	{
 		NPC_S_KPU10_TU_MPLS, 0xff,
 		NPC_MPLS_S,
@@ -6613,7 +7736,9 @@ static const struct npc_kpu_profile_cam kpu10_cam_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_cam kpu11_cam_entries[] = {
+static struct npc_kpu_profile_cam kpu11_cam_entries[] = {
+	NPC_KPU_NOP_CAM,
+	NPC_KPU_NOP_CAM,
 	{
 		NPC_S_KPU11_TU_ETHER, 0xff,
 		NPC_ETYPE_IP,
@@ -6922,13 +8047,15 @@ static const struct npc_kpu_profile_cam kpu11_cam_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_cam kpu12_cam_entries[] = {
+static struct npc_kpu_profile_cam kpu12_cam_entries[] = {
+	NPC_KPU_NOP_CAM,
+	NPC_KPU_NOP_CAM,
 	{
 		NPC_S_KPU12_TU_IP, 0xff,
 		NPC_IPNH_TCP,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
 		0x0000,
 	},
@@ -6936,8 +8063,8 @@ static const struct npc_kpu_profile_cam kpu12_cam_entries[] = {
 		NPC_S_KPU12_TU_IP, 0xff,
 		NPC_IPNH_UDP,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
 		0x0000,
 	},
@@ -6945,8 +8072,8 @@ static const struct npc_kpu_profile_cam kpu12_cam_entries[] = {
 		NPC_S_KPU12_TU_IP, 0xff,
 		NPC_IPNH_SCTP,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
 		0x0000,
 	},
@@ -6954,8 +8081,8 @@ static const struct npc_kpu_profile_cam kpu12_cam_entries[] = {
 		NPC_S_KPU12_TU_IP, 0xff,
 		NPC_IPNH_ICMP,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
 		0x0000,
 	},
@@ -6963,8 +8090,8 @@ static const struct npc_kpu_profile_cam kpu12_cam_entries[] = {
 		NPC_S_KPU12_TU_IP, 0xff,
 		NPC_IPNH_IGMP,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
 		0x0000,
 	},
@@ -6972,8 +8099,8 @@ static const struct npc_kpu_profile_cam kpu12_cam_entries[] = {
 		NPC_S_KPU12_TU_IP, 0xff,
 		NPC_IPNH_ESP,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
 		0x0000,
 	},
@@ -6981,8 +8108,8 @@ static const struct npc_kpu_profile_cam kpu12_cam_entries[] = {
 		NPC_S_KPU12_TU_IP, 0xff,
 		NPC_IPNH_AH,
 		0x00ff,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
 		0x0000,
 	},
@@ -6990,8 +8117,8 @@ static const struct npc_kpu_profile_cam kpu12_cam_entries[] = {
 		NPC_S_KPU12_TU_IP, 0xff,
 		0x0000,
 		0x0000,
-		NPC_IP_VER_4|NPC_IP_HDR_LEN_5,
-		NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK,
+		NPC_IP_VER_4 | NPC_IP_HDR_LEN_5,
+		NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK,
 		0x0000,
 		0x0000,
 	},
@@ -7177,7 +8304,9 @@ static const struct npc_kpu_profile_cam kpu12_cam_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_cam kpu13_cam_entries[] = {
+static struct npc_kpu_profile_cam kpu13_cam_entries[] = {
+	NPC_KPU_NOP_CAM,
+	NPC_KPU_NOP_CAM,
 	{
 		NPC_S_KPU13_TU_IP6_EXT, 0xff,
 		0x0000,
@@ -7189,7 +8318,9 @@ static const struct npc_kpu_profile_cam kpu13_cam_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_cam kpu14_cam_entries[] = {
+static struct npc_kpu_profile_cam kpu14_cam_entries[] = {
+	NPC_KPU_NOP_CAM,
+	NPC_KPU_NOP_CAM,
 	{
 		NPC_S_KPU14_TU_IP6_EXT, 0xff,
 		0x0000,
@@ -7201,7 +8332,9 @@ static const struct npc_kpu_profile_cam kpu14_cam_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_cam kpu15_cam_entries[] = {
+static struct npc_kpu_profile_cam kpu15_cam_entries[] = {
+	NPC_KPU_NOP_CAM,
+	NPC_KPU_NOP_CAM,
 	{
 		NPC_S_KPU15_TU_TCP, 0xff,
 		0x0000,
@@ -7224,8 +8357,8 @@ static const struct npc_kpu_profile_cam kpu15_cam_entries[] = {
 		NPC_S_KPU15_TU_TCP, 0xff,
 		0x0000,
 		0x0000,
-		NPC_TCP_FLAGS_RST|NPC_TCP_FLAGS_FIN,
-		NPC_TCP_FLAGS_RST|NPC_TCP_FLAGS_FIN,
+		NPC_TCP_FLAGS_RST | NPC_TCP_FLAGS_FIN,
+		NPC_TCP_FLAGS_RST | NPC_TCP_FLAGS_FIN,
 		0x0000,
 		0x0000,
 	},
@@ -7233,8 +8366,8 @@ static const struct npc_kpu_profile_cam kpu15_cam_entries[] = {
 		NPC_S_KPU15_TU_TCP, 0xff,
 		0x0000,
 		0x0000,
-		NPC_TCP_FLAGS_URG|NPC_TCP_FLAGS_SYN,
-		NPC_TCP_FLAGS_URG|NPC_TCP_FLAGS_SYN,
+		NPC_TCP_FLAGS_URG | NPC_TCP_FLAGS_SYN,
+		NPC_TCP_FLAGS_URG | NPC_TCP_FLAGS_SYN,
 		0x0000,
 		0x0000,
 	},
@@ -7242,8 +8375,8 @@ static const struct npc_kpu_profile_cam kpu15_cam_entries[] = {
 		NPC_S_KPU15_TU_TCP, 0xff,
 		0x0000,
 		0x0000,
-		NPC_TCP_FLAGS_RST|NPC_TCP_FLAGS_SYN,
-		NPC_TCP_FLAGS_RST|NPC_TCP_FLAGS_SYN,
+		NPC_TCP_FLAGS_RST | NPC_TCP_FLAGS_SYN,
+		NPC_TCP_FLAGS_RST | NPC_TCP_FLAGS_SYN,
 		0x0000,
 		0x0000,
 	},
@@ -7251,8 +8384,8 @@ static const struct npc_kpu_profile_cam kpu15_cam_entries[] = {
 		NPC_S_KPU15_TU_TCP, 0xff,
 		0x0000,
 		0x0000,
-		NPC_TCP_FLAGS_SYN|NPC_TCP_FLAGS_FIN,
-		NPC_TCP_FLAGS_SYN|NPC_TCP_FLAGS_FIN,
+		NPC_TCP_FLAGS_SYN | NPC_TCP_FLAGS_FIN,
+		NPC_TCP_FLAGS_SYN | NPC_TCP_FLAGS_FIN,
 		0x0000,
 		0x0000,
 	},
@@ -7402,7 +8535,9 @@ static const struct npc_kpu_profile_cam kpu15_cam_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_cam kpu16_cam_entries[] = {
+static struct npc_kpu_profile_cam kpu16_cam_entries[] = {
+	NPC_KPU_NOP_CAM,
+	NPC_KPU_NOP_CAM,
 	{
 		NPC_S_KPU16_TCP_DATA, 0xff,
 		0x0000,
@@ -7459,7 +8594,9 @@ static const struct npc_kpu_profile_cam kpu16_cam_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_action kpu1_action_entries[] = {
+static struct npc_kpu_profile_action kpu1_action_entries[] = {
+	NPC_KPU_NOP_ACTION,
+	NPC_KPU_NOP_ACTION,
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		8, 0, 6, 3, 0,
@@ -7511,6 +8648,14 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = {
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		8, 12, 0, 0, 0,
+		NPC_S_KPU2_NGIO, 12, 1,
+		NPC_LID_LA, NPC_LT_LA_ETHER,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 12, 0, 0, 0,
 		NPC_S_KPU2_CTAG2, 12, 1,
 		NPC_LID_LA, NPC_LT_LA_ETHER,
 		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN,
@@ -7518,7 +8663,7 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		4, 8, 0, 0, 0,
+		4, 8, 12, 0, 0,
 		NPC_S_KPU2_CTAG, 12, 1,
 		NPC_LID_LA, NPC_LT_LA_ETHER,
 		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN,
@@ -7550,14 +8695,6 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		18, 22, 26, 0, 0,
-		NPC_S_KPU2_ITAG, 12, 1,
-		NPC_LID_LA, NPC_LT_LA_ETHER,
-		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_ITAG,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		2, 6, 10, 2, 0,
 		NPC_S_KPU4_MPLS, 14, 1,
 		NPC_LID_LA, NPC_LT_LA_ETHER,
@@ -7590,6 +8727,14 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 12, 0, 2, 0,
+		NPC_S_KPU4_PPPOE, 12, 1,
+		NPC_LID_LA, NPC_LT_LA_ETHER,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 1,
 		NPC_LID_LA, NPC_LT_LA_8023,
@@ -7707,15 +8852,6 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		18, 22, 26, 0, 0,
-		NPC_S_KPU2_ITAG, 20, 1,
-		NPC_LID_LA, NPC_LT_LA_IH_NIX_ETHER,
-		NPC_F_LA_U_HAS_IH_NIX | NPC_F_LA_U_HAS_TAG
-			| NPC_F_LA_L_WITH_ITAG,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		2, 6, 10, 2, 0,
 		NPC_S_KPU4_MPLS, 22, 1,
 		NPC_LID_LA, NPC_LT_LA_IH_NIX_ETHER,
@@ -7788,7 +8924,7 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		4, 8, 16, 2, 0,
+		4, 8, 12, 2, 0,
 		NPC_S_KPU4_FDSA, 12, 1,
 		NPC_LID_LA, NPC_LT_LA_ETHER,
 		0,
@@ -7897,15 +9033,6 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		18, 22, 26, 0, 0,
-		NPC_S_KPU2_ITAG, 28, 1,
-		NPC_LID_LA, NPC_LT_LA_HIGIG2_ETHER,
-		NPC_F_LA_U_HAS_HIGIG2 | NPC_F_LA_U_HAS_TAG
-			| NPC_F_LA_L_WITH_ITAG,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		2, 6, 10, 2, 0,
 		NPC_S_KPU4_MPLS, 30, 1,
 		NPC_LID_LA, NPC_LT_LA_HIGIG2_ETHER,
@@ -8031,15 +9158,6 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		18, 22, 26, 0, 0,
-		NPC_S_KPU2_ITAG, 36, 1,
-		NPC_LID_LA, NPC_LT_LA_IH_NIX_HIGIG2_ETHER,
-		NPC_F_LA_U_HAS_IH_NIX | NPC_F_LA_U_HAS_HIGIG2
-			| NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_ITAG,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		2, 6, 10, 2, 0,
 		NPC_S_KPU4_MPLS, 38, 1,
 		NPC_LID_LA, NPC_LT_LA_IH_NIX_HIGIG2_ETHER,
@@ -8075,6 +9193,326 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = {
 		0, 0, 0, 0,
 	},
 	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 0, 6, 3, 0,
+		NPC_S_KPU5_IP, 104, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 3, 0,
+		NPC_S_KPU5_IP6, 104, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 3, 0,
+		NPC_S_KPU5_ARP, 104, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 3, 0,
+		NPC_S_KPU5_RARP, 104, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 3, 0,
+		NPC_S_KPU5_PTP, 104, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 3, 0,
+		NPC_S_KPU5_FCOE, 104, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 12, 0, 0, 0,
+		NPC_S_KPU2_CTAG2, 102, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER,
+		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		4, 8, 0, 0, 0,
+		NPC_S_KPU2_CTAG, 102, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER,
+		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		4, 8, 22, 0, 0,
+		NPC_S_KPU2_SBTAG, 102, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER,
+		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		4, 8, 0, 0, 0,
+		NPC_S_KPU2_QINQ, 102, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER,
+		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 12, 26, 0, 0,
+		NPC_S_KPU2_ETAG, 102, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER,
+		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_ETAG,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 6, 10, 2, 0,
+		NPC_S_KPU4_MPLS, 104, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER,
+		NPC_F_LA_L_WITH_MPLS,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 6, 10, 2, 0,
+		NPC_S_KPU4_MPLS, 104, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER,
+		NPC_F_LA_L_WITH_MPLS,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 0, 0, 2, 0,
+		NPC_S_KPU4_NSH, 104, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER,
+		NPC_F_LA_L_WITH_NSH,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER,
+		NPC_F_LA_L_UNK_ETYPE,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 0, 6, 3, 0,
+		NPC_S_KPU5_CPT_IP, 56, 1,
+		NPC_LID_LA, NPC_LT_LA_CPT_HDR,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 3, 0,
+		NPC_S_KPU5_CPT_IP6, 56, 1,
+		NPC_LID_LA, NPC_LT_LA_CPT_HDR,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		4, 8, 0, 0, 0,
+		NPC_S_KPU2_CTAG, 54, 1,
+		NPC_LID_LA, NPC_LT_LA_CPT_HDR,
+		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		4, 8, 0, 0, 0,
+		NPC_S_KPU2_QINQ, 54, 1,
+		NPC_LID_LA, NPC_LT_LA_CPT_HDR,
+		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 0, 6, 3, 0,
+		NPC_S_KPU5_CPT_IP, 60, 1,
+		NPC_LID_LA, NPC_LT_LA_CPT_HDR,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 3, 0,
+		NPC_S_KPU5_CPT_IP6, 60, 1,
+		NPC_LID_LA, NPC_LT_LA_CPT_HDR,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		4, 8, 0, 0, 0,
+		NPC_S_KPU2_CTAG, 58, 1,
+		NPC_LID_LA, NPC_LT_LA_CPT_HDR,
+		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		4, 8, 0, 0, 0,
+		NPC_S_KPU2_QINQ, 58, 1,
+		NPC_LID_LA, NPC_LT_LA_CPT_HDR,
+		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LA, NPC_LT_LA_CPT_HDR,
+		NPC_F_LA_L_UNK_ETYPE,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 0, 6, 3, 0,
+		NPC_S_KPU5_IP, 38, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 3, 0,
+		NPC_S_KPU5_IP6, 38, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 3, 0,
+		NPC_S_KPU5_ARP, 38, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 3, 0,
+		NPC_S_KPU5_RARP, 38, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 3, 0,
+		NPC_S_KPU5_PTP, 38, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 3, 0,
+		NPC_S_KPU5_FCOE, 38, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 12, 0, 0, 0,
+		NPC_S_KPU2_CTAG2, 36, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER,
+		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		4, 8, 0, 0, 0,
+		NPC_S_KPU2_CTAG, 36, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER,
+		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		4, 8, 22, 0, 0,
+		NPC_S_KPU2_SBTAG, 36, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER,
+		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		4, 8, 0, 0, 0,
+		NPC_S_KPU2_QINQ, 36, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER,
+		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 12, 26, 0, 0,
+		NPC_S_KPU2_ETAG, 36, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER,
+		NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_ETAG,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 6, 10, 2, 0,
+		NPC_S_KPU4_MPLS, 38, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER,
+		NPC_F_LA_L_WITH_MPLS,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 6, 10, 2, 0,
+		NPC_S_KPU4_MPLS, 38, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER,
+		NPC_F_LA_L_WITH_MPLS,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 0, 0, 2, 0,
+		NPC_S_KPU4_NSH, 38, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER,
+		NPC_F_LA_L_WITH_NSH,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER,
+		NPC_F_LA_L_UNK_ETYPE,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		12, 0, 0, 1, 0,
+		NPC_S_KPU3_VLAN_EXDSA, 12, 1,
+		NPC_LID_LA, NPC_LT_LA_ETHER,
+		0,
+		0, 0, 0, 0,
+	},
+	{
 		NPC_ERRLEV_LA, NPC_EC_L2_K1,
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 0,
@@ -8084,7 +9522,9 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_action kpu2_action_entries[] = {
+static struct npc_kpu_profile_action kpu2_action_entries[] = {
+	NPC_KPU_NOP_ACTION,
+	NPC_KPU_NOP_ACTION,
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		8, 0, 6, 2, 0,
@@ -8159,6 +9599,22 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 0, 6, 2, 0,
+		NPC_S_KPU5_IP, 14, 1,
+		NPC_LID_LB, NPC_LT_LB_PPPOE,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 2, 0,
+		NPC_S_KPU5_IP6, 14, 1,
+		NPC_LID_LB, NPC_LT_LB_PPPOE,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 1,
 		NPC_LID_LB, NPC_LT_LB_CTAG,
@@ -8170,7 +9626,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		8, 0, 6, 2, 0,
 		NPC_S_KPU5_IP, 10, 1,
 		NPC_LID_LB, NPC_LT_LB_STAG_QINQ,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8178,7 +9634,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		6, 0, 0, 2, 0,
 		NPC_S_KPU5_IP6, 10, 1,
 		NPC_LID_LB, NPC_LT_LB_STAG_QINQ,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8186,7 +9642,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		0, 0, 0, 2, 0,
 		NPC_S_KPU5_ARP, 10, 1,
 		NPC_LID_LB, NPC_LT_LB_STAG_QINQ,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8194,7 +9650,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		0, 0, 0, 2, 0,
 		NPC_S_KPU5_RARP, 10, 1,
 		NPC_LID_LB, NPC_LT_LB_STAG_QINQ,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8202,7 +9658,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		0, 0, 0, 2, 0,
 		NPC_S_KPU5_PTP, 10, 1,
 		NPC_LID_LB, NPC_LT_LB_STAG_QINQ,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8210,7 +9666,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		0, 0, 0, 2, 0,
 		NPC_S_KPU5_FCOE, 10, 1,
 		NPC_LID_LB, NPC_LT_LB_STAG_QINQ,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8218,7 +9674,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		2, 6, 10, 1, 0,
 		NPC_S_KPU4_MPLS, 10, 1,
 		NPC_LID_LB, NPC_LT_LB_STAG_QINQ,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8226,7 +9682,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		2, 6, 10, 1, 0,
 		NPC_S_KPU4_MPLS, 10, 1,
 		NPC_LID_LB, NPC_LT_LB_STAG_QINQ,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8234,7 +9690,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		2, 0, 0, 1, 0,
 		NPC_S_KPU4_NSH, 10, 1,
 		NPC_LID_LB, NPC_LT_LB_STAG_QINQ,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8242,7 +9698,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 1,
 		NPC_LID_LB, NPC_LT_LB_STAG_QINQ,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG_UNK,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG_UNK,
 		0, 0, 0, 0,
 	},
 	{
@@ -8250,7 +9706,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		2, 6, 0, 0, 0,
 		NPC_S_KPU3_CTAG, 10, 1,
 		NPC_LID_LB, NPC_LT_LB_STAG_QINQ,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG_CTAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_STAG_CTAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8258,7 +9714,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		2, 6, 0, 0, 0,
 		NPC_S_KPU3_STAG, 10, 1,
 		NPC_LID_LB, NPC_LT_LB_STAG_QINQ,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG_STAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_STAG_STAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8266,7 +9722,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		8, 0, 6, 2, 0,
 		NPC_S_KPU5_IP, 24, 1,
 		NPC_LID_LB, NPC_LT_LB_BTAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8274,7 +9730,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		6, 0, 0, 2, 0,
 		NPC_S_KPU5_IP6, 24, 1,
 		NPC_LID_LB, NPC_LT_LB_BTAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8282,7 +9738,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		0, 0, 0, 2, 0,
 		NPC_S_KPU5_ARP, 24, 1,
 		NPC_LID_LB, NPC_LT_LB_BTAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8290,7 +9746,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		0, 0, 0, 2, 0,
 		NPC_S_KPU5_RARP, 24, 1,
 		NPC_LID_LB, NPC_LT_LB_BTAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8298,7 +9754,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		0, 0, 0, 2, 0,
 		NPC_S_KPU5_PTP, 24, 1,
 		NPC_LID_LB, NPC_LT_LB_BTAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8306,7 +9762,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		0, 0, 0, 2, 0,
 		NPC_S_KPU5_FCOE, 24, 1,
 		NPC_LID_LB, NPC_LT_LB_BTAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8314,7 +9770,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		2, 6, 10, 1, 0,
 		NPC_S_KPU4_MPLS, 24, 1,
 		NPC_LID_LB, NPC_LT_LB_BTAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8322,7 +9778,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		2, 6, 10, 1, 0,
 		NPC_S_KPU4_MPLS, 24, 1,
 		NPC_LID_LB, NPC_LT_LB_BTAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8330,7 +9786,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		2, 0, 0, 1, 0,
 		NPC_S_KPU4_NSH, 24, 1,
 		NPC_LID_LB, NPC_LT_LB_BTAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8338,7 +9794,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		2, 0, 0, 0, 0,
 		NPC_S_KPU3_STAG, 24, 1,
 		NPC_LID_LB, NPC_LT_LB_BTAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG_STAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG_STAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8346,7 +9802,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		2, 0, 0, 0, 0,
 		NPC_S_KPU3_CTAG, 24, 1,
 		NPC_LID_LB, NPC_LT_LB_BTAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG_CTAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG_CTAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8354,7 +9810,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 1,
 		NPC_LID_LB, NPC_LT_LB_BTAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG_UNK,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG_UNK,
 		0, 0, 0, 0,
 	},
 	{
@@ -8546,15 +10002,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		2, 0, 0, 0, 0,
 		NPC_S_KPU3_CTAG, 10, 1,
 		NPC_LID_LB, NPC_LT_LB_ETAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		16, 20, 24, 0, 0,
-		NPC_S_KPU3_ITAG, 14, 1,
-		NPC_LID_LB, NPC_LT_LB_ETAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_BTAG_ITAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8562,7 +10010,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		2, 6, 0, 0, 0,
 		NPC_S_KPU3_STAG, 10, 1,
 		NPC_LID_LB, NPC_LT_LB_ETAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_STAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8570,7 +10018,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		2, 6, 0, 0, 0,
 		NPC_S_KPU3_QINQ, 10, 1,
 		NPC_LID_LB, NPC_LT_LB_ETAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_QINQ,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_QINQ,
 		0, 0, 0, 0,
 	},
 	{
@@ -8578,7 +10026,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		8, 0, 6, 2, 0,
 		NPC_S_KPU5_IP, 28, 1,
 		NPC_LID_LB, NPC_LT_LB_ETAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8586,7 +10034,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		6, 0, 0, 2, 0,
 		NPC_S_KPU5_IP6, 28, 1,
 		NPC_LID_LB, NPC_LT_LB_ETAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8594,7 +10042,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		0, 0, 0, 2, 0,
 		NPC_S_KPU5_ARP, 28, 1,
 		NPC_LID_LB, NPC_LT_LB_ETAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8602,7 +10050,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		2, 0, 0, 0, 0,
 		NPC_S_KPU3_STAG, 28, 1,
 		NPC_LID_LB, NPC_LT_LB_ETAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG_STAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG_STAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8610,7 +10058,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		2, 0, 0, 0, 0,
 		NPC_S_KPU3_CTAG, 28, 1,
 		NPC_LID_LB, NPC_LT_LB_ETAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG_CTAG,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG_CTAG,
 		0, 0, 0, 0,
 	},
 	{
@@ -8618,7 +10066,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 1,
 		NPC_LID_LB, NPC_LT_LB_ETAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG_UNK,
+		NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG_UNK,
 		0, 0, 0, 0,
 	},
 	{
@@ -8632,142 +10080,6 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		8, 0, 6, 2, 0,
-		NPC_S_KPU5_IP, 20, 1,
-		NPC_LID_LB, NPC_LT_LB_ITAG,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		6, 0, 0, 2, 0,
-		NPC_S_KPU5_IP6, 20, 1,
-		NPC_LID_LB, NPC_LT_LB_ITAG,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 2, 0,
-		NPC_S_KPU5_ARP, 20, 1,
-		NPC_LID_LB, NPC_LT_LB_ITAG,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 2, 0,
-		NPC_S_KPU5_RARP, 20, 1,
-		NPC_LID_LB, NPC_LT_LB_ITAG,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		8, 0, 6, 2, 0,
-		NPC_S_KPU5_IP, 28, 1,
-		NPC_LID_LB, NPC_LT_LB_ITAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG_CTAG,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		6, 0, 0, 2, 0,
-		NPC_S_KPU5_IP6, 28, 1,
-		NPC_LID_LB, NPC_LT_LB_ITAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG_CTAG,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 2, 0,
-		NPC_S_KPU5_ARP, 28, 1,
-		NPC_LID_LB, NPC_LT_LB_ITAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG_CTAG,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_LB, NPC_EC_L2_K3_ETYPE_UNK,
-		0, 0, 0, 0, 1,
-		NPC_S_NA, 0, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		8, 0, 6, 2, 0,
-		NPC_S_KPU5_IP, 24, 1,
-		NPC_LID_LB, NPC_LT_LB_ITAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		6, 0, 0, 2, 0,
-		NPC_S_KPU5_IP6, 24, 1,
-		NPC_LID_LB, NPC_LT_LB_ITAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 2, 0,
-		NPC_S_KPU5_ARP, 24, 1,
-		NPC_LID_LB, NPC_LT_LB_ITAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_LB, NPC_EC_L2_K3_ETYPE_UNK,
-		0, 0, 0, 0, 1,
-		NPC_S_NA, 0, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		8, 0, 6, 2, 0,
-		NPC_S_KPU5_IP, 24, 1,
-		NPC_LID_LB, NPC_LT_LB_ITAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		6, 0, 0, 2, 0,
-		NPC_S_KPU5_IP6, 24, 1,
-		NPC_LID_LB, NPC_LT_LB_ITAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 2, 0,
-		NPC_S_KPU5_ARP, 24, 1,
-		NPC_LID_LB, NPC_LT_LB_ITAG,
-		NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_LB, NPC_EC_L2_K3_ETYPE_UNK,
-		0, 0, 0, 0, 1,
-		NPC_S_NA, 0, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_LB, NPC_EC_L2_K3_ETYPE_UNK,
-		0, 0, 0, 0, 1,
-		NPC_S_NA, 0, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		8, 0, 6, 2, 0,
 		NPC_S_KPU5_IP, 10, 1,
 		NPC_LID_LB, NPC_LT_LB_STAG_QINQ,
 		0,
@@ -9078,6 +10390,14 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 		0, 0, 0, 0,
 	},
 	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_NGIO,
+		0,
+		0, 0, 0, 0,
+	},
+	{
 		NPC_ERRLEV_LB, NPC_EC_L2_K3,
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 0,
@@ -9087,11 +10407,13 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_action kpu3_action_entries[] = {
+static struct npc_kpu_profile_action kpu3_action_entries[] = {
+	NPC_KPU_NOP_ACTION,
+	NPC_KPU_NOP_ACTION,
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		8, 0, 6, 1, 0,
-		NPC_S_KPU5_IP, 4, 0,
+		NPC_S_KPU5_IP, 6, 0,
 		NPC_LID_LB, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
@@ -9099,7 +10421,7 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = {
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		6, 0, 0, 1, 0,
-		NPC_S_KPU5_IP6, 4, 0,
+		NPC_S_KPU5_IP6, 6, 0,
 		NPC_LID_LB, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
@@ -9107,7 +10429,7 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = {
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		0, 0, 0, 1, 0,
-		NPC_S_KPU5_ARP, 4, 0,
+		NPC_S_KPU5_ARP, 6, 0,
 		NPC_LID_LB, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
@@ -9115,7 +10437,7 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = {
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		0, 0, 0, 1, 0,
-		NPC_S_KPU5_RARP, 4, 0,
+		NPC_S_KPU5_RARP, 6, 0,
 		NPC_LID_LB, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
@@ -9123,7 +10445,7 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = {
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		0, 0, 0, 1, 0,
-		NPC_S_KPU5_PTP, 4, 0,
+		NPC_S_KPU5_PTP, 6, 0,
 		NPC_LID_LB, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
@@ -9131,7 +10453,7 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = {
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		0, 0, 0, 1, 0,
-		NPC_S_KPU5_FCOE, 4, 0,
+		NPC_S_KPU5_FCOE, 6, 0,
 		NPC_LID_LB, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
@@ -9139,7 +10461,7 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = {
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		2, 6, 10, 0, 0,
-		NPC_S_KPU4_MPLS, 4, 0,
+		NPC_S_KPU4_MPLS, 6, 0,
 		NPC_LID_LB, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
@@ -9147,7 +10469,7 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = {
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		2, 6, 10, 0, 0,
-		NPC_S_KPU4_MPLS, 4, 0,
+		NPC_S_KPU4_MPLS, 6, 0,
 		NPC_LID_LB, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
@@ -9155,7 +10477,7 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = {
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		2, 0, 0, 0, 0,
-		NPC_S_KPU4_NSH, 4, 0,
+		NPC_S_KPU4_NSH, 6, 0,
 		NPC_LID_LB, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
@@ -9458,142 +10780,6 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		8, 0, 6, 2, 0,
-		NPC_S_KPU5_IP, 18, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		6, 0, 0, 2, 0,
-		NPC_S_KPU5_IP6, 18, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 2, 0,
-		NPC_S_KPU5_ARP, 18, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 2, 0,
-		NPC_S_KPU5_RARP, 18, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		8, 0, 6, 1, 0,
-		NPC_S_KPU5_IP, 26, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		6, 0, 0, 1, 0,
-		NPC_S_KPU5_IP6, 26, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 1, 0,
-		NPC_S_KPU5_ARP, 26, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		8, 0, 6, 1, 0,
-		NPC_S_KPU5_IP, 22, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		6, 0, 0, 1, 0,
-		NPC_S_KPU5_IP6, 22, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 1, 0,
-		NPC_S_KPU5_ARP, 22, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_LB, NPC_EC_L2_K3_ETYPE_UNK,
-		0, 0, 0, 0, 1,
-		NPC_S_NA, 0, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_LB, NPC_EC_L2_K3_ETYPE_UNK,
-		0, 0, 0, 0, 1,
-		NPC_S_NA, 0, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		8, 0, 6, 1, 0,
-		NPC_S_KPU5_IP, 22, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		6, 0, 0, 1, 0,
-		NPC_S_KPU5_IP6, 22, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 1, 0,
-		NPC_S_KPU5_ARP, 22, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_LB, NPC_EC_L2_K3_ETYPE_UNK,
-		0, 0, 0, 0, 1,
-		NPC_S_NA, 0, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_LB, NPC_EC_L2_K3_ETYPE_UNK,
-		0, 0, 0, 0, 1,
-		NPC_S_NA, 0, 0,
-		NPC_LID_LB, NPC_LT_NA,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		8, 0, 6, 1, 0,
 		NPC_S_KPU5_IP, 4, 1,
 		NPC_LID_LB, NPC_LT_LB_CTAG,
@@ -10073,6 +11259,14 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = {
 		0, 0, 0, 0,
 	},
 	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU4_VLAN_EXDSA, 12, 1,
+		NPC_LID_LB, NPC_LT_LB_VLAN_EXDSA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
 		NPC_ERRLEV_LB, NPC_EC_L2_K3,
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 0,
@@ -10082,7 +11276,9 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_action kpu4_action_entries[] = {
+static struct npc_kpu_profile_action kpu4_action_entries[] = {
+	NPC_KPU_NOP_ACTION,
+	NPC_KPU_NOP_ACTION,
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		0, 0, 0, 0, 0,
@@ -10205,6 +11401,70 @@ static const struct npc_kpu_profile_action kpu4_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 0, 6, 0, 0,
+		NPC_S_KPU5_IP, 10, 1,
+		NPC_LID_LB, NPC_LT_LB_FDSA,
+		NPC_F_LB_L_FDSA,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 0, 0,
+		NPC_S_KPU5_IP6, 10, 1,
+		NPC_LID_LB, NPC_LT_LB_FDSA,
+		NPC_F_LB_L_FDSA,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU5_ARP, 10, 1,
+		NPC_LID_LB, NPC_LT_LB_FDSA,
+		NPC_F_LB_L_FDSA,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 0, 6, 0, 0,
+		NPC_S_KPU5_RARP, 10, 1,
+		NPC_LID_LB, NPC_LT_LB_FDSA,
+		NPC_F_LB_L_FDSA,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 0, 0,
+		NPC_S_KPU5_PTP, 10, 1,
+		NPC_LID_LB, NPC_LT_LB_FDSA,
+		NPC_F_LB_L_FDSA,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU5_FCOE, 10, 1,
+		NPC_LID_LB, NPC_LT_LB_FDSA,
+		NPC_F_LB_L_FDSA,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 0, 6, 0, 0,
+		NPC_S_KPU5_IP, 14, 1,
+		NPC_LID_LB, NPC_LT_LB_PPPOE,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 0, 0,
+		NPC_S_KPU5_IP6, 14, 1,
+		NPC_LID_LB, NPC_LT_LB_PPPOE,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 1,
 		NPC_LID_LB, NPC_LT_LB_FDSA,
@@ -10212,6 +11472,78 @@ static const struct npc_kpu_profile_action kpu4_action_entries[] = {
 		0, 0, 0, 0,
 	},
 	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 0, 6, 0, 0,
+		NPC_S_KPU5_IP, 2, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 0, 0,
+		NPC_S_KPU5_IP6, 2, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU5_ARP, 2, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 0, 6, 0, 0,
+		NPC_S_KPU5_RARP, 2, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 0, 0,
+		NPC_S_KPU5_PTP, 2, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU5_FCOE, 2, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 0, 6, 0, 0,
+		NPC_S_KPU5_IP, 10, 0,
+		NPC_LID_LB, NPC_LT_LB_PPPOE,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 0, 0,
+		NPC_S_KPU5_IP6, 10, 0,
+		NPC_LID_LB, NPC_LT_LB_PPPOE,
+		0,
+		0, 0, 0, 0,
+	},
+	{
 		NPC_ERRLEV_LB, NPC_EC_L2_K4,
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 0,
@@ -10221,7 +11553,9 @@ static const struct npc_kpu_profile_action kpu4_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_action kpu5_action_entries[] = {
+static struct npc_kpu_profile_action kpu5_action_entries[] = {
+	NPC_KPU_NOP_ACTION,
+	NPC_KPU_NOP_ACTION,
 	{
 		NPC_ERRLEV_LC, NPC_EC_IP_TTL_0,
 		0, 0, 0, 0, 1,
@@ -10719,6 +12053,382 @@ static const struct npc_kpu_profile_action kpu5_action_entries[] = {
 		0, 0, 0, 0,
 	},
 	{
+		NPC_ERRLEV_LC, NPC_EC_IP_TTL_0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_LC, NPC_EC_IP_FRAG_OFFSET_1,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP,
+		NPC_F_LC_U_IP_FRAG,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 12, 0, 2, 0,
+		NPC_S_KPU8_TCP, 20, 1,
+		NPC_LID_LC, NPC_LT_LC_IP,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 0, 0, 2, 0,
+		NPC_S_KPU8_UDP, 20, 1,
+		NPC_LID_LC, NPC_LT_LC_IP,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU8_SCTP, 20, 1,
+		NPC_LID_LC, NPC_LT_LC_IP,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU8_ICMP, 20, 1,
+		NPC_LID_LC, NPC_LT_LC_IP,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU8_IGMP, 20, 1,
+		NPC_LID_LC, NPC_LT_LC_IP,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 3, 0,
+		NPC_S_KPU9_ESP, 20, 1,
+		NPC_LID_LC, NPC_LT_LC_IP,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU8_AH, 20, 1,
+		NPC_LID_LC, NPC_LT_LC_IP,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 0, 0, 2, 0,
+		NPC_S_KPU8_GRE, 20, 1,
+		NPC_LID_LC, NPC_LT_LC_IP,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 0, 6, 6, 0,
+		NPC_S_KPU12_TU_IP, 20, 1,
+		NPC_LID_LC, NPC_LT_LC_IP,
+		NPC_F_LC_L_IP_IN_IP,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 6, 0,
+		NPC_S_KPU12_TU_IP6, 20, 1,
+		NPC_LID_LC, NPC_LT_LC_IP,
+		NPC_F_LC_L_6TO4,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 6, 10, 3, 0,
+		NPC_S_KPU9_TU_MPLS_IN_IP, 20, 1,
+		NPC_LID_LC, NPC_LT_LC_IP,
+		NPC_F_LC_L_MPLS_IN_IP,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP,
+		NPC_F_LC_U_UNK_PROTO,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 12, 0, 2, 0,
+		NPC_S_KPU8_TCP, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP_OPT,
+		0,
+		0, 0xf, 0, 2,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 8, 10, 2, 0,
+		NPC_S_KPU8_UDP, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP_OPT,
+		0,
+		0, 0xf, 0, 2,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU8_SCTP, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP_OPT,
+		0,
+		0, 0xf, 0, 2,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU8_ICMP, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP_OPT,
+		0,
+		0, 0xf, 0, 2,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU8_IGMP, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP_OPT,
+		0,
+		0, 0xf, 0, 2,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 3, 0,
+		NPC_S_KPU9_ESP, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP_OPT,
+		0,
+		0, 0xf, 0, 2,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU8_AH, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP_OPT,
+		0,
+		0, 0xf, 0, 2,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 0, 0, 2, 0,
+		NPC_S_KPU8_GRE, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP_OPT,
+		0,
+		0, 0xf, 0, 2,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 0, 6, 6, 0,
+		NPC_S_KPU12_TU_IP, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP_OPT,
+		NPC_F_LC_L_IP_IN_IP,
+		0, 0xf, 0, 2,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 6, 0,
+		NPC_S_KPU12_TU_IP6, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP_OPT,
+		NPC_F_LC_L_6TO4,
+		0, 0xf, 0, 2,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 6, 10, 3, 0,
+		NPC_S_KPU9_TU_MPLS_IN_IP, 20, 1,
+		NPC_LID_LC, NPC_LT_LC_IP_OPT,
+		NPC_F_LC_L_MPLS_IN_IP,
+		0, 0xf, 0, 2,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP_OPT,
+		NPC_F_LC_U_UNK_PROTO,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_LC, NPC_EC_IP_VER,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_LC, NPC_EC_IP6_HOP_0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 12, 0, 2, 0,
+		NPC_S_KPU8_TCP, 40, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 0, 0, 2, 0,
+		NPC_S_KPU8_UDP, 40, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU8_SCTP, 40, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU8_ICMP, 40, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU8_ICMP6, 40, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU8_GRE, 40, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 6, 0,
+		NPC_S_KPU12_TU_IP6, 40, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6,
+		NPC_F_LC_L_IP6_TUN_IP6,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 6, 10, 3, 0,
+		NPC_S_KPU9_TU_MPLS_IN_IP, 40, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6,
+		NPC_F_LC_L_IP6_MPLS_IN_IP,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU6_IP6_CPT_HOP_DEST, 40, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6_EXT,
+		NPC_F_LC_L_EXT_HOP,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU6_IP6_CPT_HOP_DEST, 40, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6_EXT,
+		NPC_F_LC_L_EXT_DEST,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU6_IP6_CPT_ROUT, 40, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6_EXT,
+		NPC_F_LC_L_EXT_ROUT,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 2, 0, 0, 0,
+		NPC_S_KPU6_IP6_CPT_FRAG, 40, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6_EXT,
+		NPC_F_LC_U_IP6_FRAG,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 3, 0,
+		NPC_S_KPU9_ESP, 40, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6_EXT,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU8_AH, 40, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6_EXT,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6_EXT,
+		NPC_F_LC_L_EXT_MOBILITY,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6_EXT,
+		NPC_F_LC_L_EXT_HOSTID,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6_EXT,
+		NPC_F_LC_L_EXT_SHIM6,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6,
+		NPC_F_LC_U_UNK_PROTO,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_LC, NPC_EC_IP6_VER,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LC, NPC_LT_LC_IP6,
+		0,
+		0, 0, 0, 0,
+	},
+	{
 		NPC_ERRLEV_LC, NPC_EC_UNK,
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 0,
@@ -10728,7 +12438,9 @@ static const struct npc_kpu_profile_action kpu5_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_action kpu6_action_entries[] = {
+static struct npc_kpu_profile_action kpu6_action_entries[] = {
+	NPC_KPU_NOP_ACTION,
+	NPC_KPU_NOP_ACTION,
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		0, 0, 0, 0, 1,
@@ -11026,6 +12738,294 @@ static const struct npc_kpu_profile_action kpu6_action_entries[] = {
 		0, 0, 0, 0,
 	},
 	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 12, 0, 1, 0,
+		NPC_S_KPU8_TCP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 8, 10, 1, 0,
+		NPC_S_KPU8_UDP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU8_SCTP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU8_ICMP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU8_ICMP6, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU9_ESP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU8_AH, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU8_GRE, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 5, 0,
+		NPC_S_KPU12_TU_IP6, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 6, 10, 2, 0,
+		NPC_S_KPU9_TU_MPLS_IN_IP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 12, 0, 1, 0,
+		NPC_S_KPU8_TCP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 8, 10, 1, 0,
+		NPC_S_KPU8_UDP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU8_SCTP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU8_ICMP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU8_ICMP6, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU9_ESP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU8_AH, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU8_GRE, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 5, 0,
+		NPC_S_KPU12_TU_IP6, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 6, 10, 2, 0,
+		NPC_S_KPU9_TU_MPLS_IN_IP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU7_IP6_ROUT, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 2, 0, 0, 0,
+		NPC_S_KPU7_CPT_IP6_FRAG, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 12, 0, 1, 0,
+		NPC_S_KPU8_TCP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 8, 10, 1, 0,
+		NPC_S_KPU8_UDP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU8_SCTP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU8_ICMP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU8_ICMP6, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU9_ESP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU8_AH, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU8_GRE, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 5, 0,
+		NPC_S_KPU12_TU_IP6, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 6, 10, 2, 0,
+		NPC_S_KPU9_TU_MPLS_IN_IP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 2, 0, 0, 0,
+		NPC_S_KPU7_CPT_IP6_FRAG, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		1, 0xff, 0, 3,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
 		NPC_ERRLEV_LC, NPC_EC_UNK,
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 0,
@@ -11035,7 +13035,9 @@ static const struct npc_kpu_profile_action kpu6_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_action kpu7_action_entries[] = {
+static struct npc_kpu_profile_action kpu7_action_entries[] = {
+	NPC_KPU_NOP_ACTION,
+	NPC_KPU_NOP_ACTION,
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		0, 0, 0, 0, 1,
@@ -11221,6 +13223,94 @@ static const struct npc_kpu_profile_action kpu7_action_entries[] = {
 		0, 0, 0, 0,
 	},
 	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 12, 0, 0, 0,
+		NPC_S_KPU8_TCP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 8, 10, 0, 0,
+		NPC_S_KPU8_UDP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU8_SCTP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU8_ICMP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU8_ICMP6, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU9_ESP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU8_AH, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU8_GRE, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 4, 0,
+		NPC_S_KPU12_TU_IP6, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		2, 6, 10, 1, 0,
+		NPC_S_KPU9_TU_MPLS_IN_IP, 8, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
+		NPC_LID_LC, NPC_LT_NA,
+		0,
+		0, 0, 0, 0,
+	},
+	{
 		NPC_ERRLEV_LC, NPC_EC_UNK,
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 0,
@@ -11230,7 +13320,9 @@ static const struct npc_kpu_profile_action kpu7_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_action kpu8_action_entries[] = {
+static struct npc_kpu_profile_action kpu8_action_entries[] = {
+	NPC_KPU_NOP_ACTION,
+	NPC_KPU_NOP_ACTION,
 	{
 		NPC_ERRLEV_LD, NPC_EC_TCP_FLAGS_FIN_ONLY,
 		0, 0, 0, 0, 1,
@@ -11889,7 +13981,9 @@ static const struct npc_kpu_profile_action kpu8_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_action kpu9_action_entries[] = {
+static struct npc_kpu_profile_action kpu9_action_entries[] = {
+	NPC_KPU_NOP_ACTION,
+	NPC_KPU_NOP_ACTION,
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		0, 0, 0, 0, 0,
@@ -12252,10 +14346,10 @@ static const struct npc_kpu_profile_action kpu9_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 0, 1,
-		NPC_S_NA, 0, 1,
+		8, 0, 6, 2, 0,
+		NPC_S_KPU12_TU_IP, 8, 1,
 		NPC_LID_LE, NPC_LT_LE_GTPU,
-		NPC_F_LE_L_GTPU_UNK,
+		0,
 		0, 0, 0, 0,
 	},
 	{
@@ -12308,7 +14402,9 @@ static const struct npc_kpu_profile_action kpu9_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_action kpu10_action_entries[] = {
+static struct npc_kpu_profile_action kpu10_action_entries[] = {
+	NPC_KPU_NOP_ACTION,
+	NPC_KPU_NOP_ACTION,
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		8, 0, 6, 1, 0,
@@ -12455,7 +14551,9 @@ static const struct npc_kpu_profile_action kpu10_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_action kpu11_action_entries[] = {
+static struct npc_kpu_profile_action kpu11_action_entries[] = {
+	NPC_KPU_NOP_ACTION,
+	NPC_KPU_NOP_ACTION,
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		8, 0, 6, 0, 0,
@@ -12730,7 +14828,9 @@ static const struct npc_kpu_profile_action kpu11_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_action kpu12_action_entries[] = {
+static struct npc_kpu_profile_action kpu12_action_entries[] = {
+	NPC_KPU_NOP_ACTION,
+	NPC_KPU_NOP_ACTION,
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		2, 12, 0, 2, 0,
@@ -12957,7 +15057,9 @@ static const struct npc_kpu_profile_action kpu12_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_action kpu13_action_entries[] = {
+static struct npc_kpu_profile_action kpu13_action_entries[] = {
+	NPC_KPU_NOP_ACTION,
+	NPC_KPU_NOP_ACTION,
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		0, 0, 0, 0, 1,
@@ -12968,7 +15070,9 @@ static const struct npc_kpu_profile_action kpu13_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_action kpu14_action_entries[] = {
+static struct npc_kpu_profile_action kpu14_action_entries[] = {
+	NPC_KPU_NOP_ACTION,
+	NPC_KPU_NOP_ACTION,
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		0, 0, 0, 0, 1,
@@ -12979,7 +15083,9 @@ static const struct npc_kpu_profile_action kpu14_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_action kpu15_action_entries[] = {
+static struct npc_kpu_profile_action kpu15_action_entries[] = {
+	NPC_KPU_NOP_ACTION,
+	NPC_KPU_NOP_ACTION,
 	{
 		NPC_ERRLEV_LG, NPC_EC_TCP_FLAGS_FIN_ONLY,
 		0, 0, 0, 0, 1,
@@ -13158,7 +15264,9 @@ static const struct npc_kpu_profile_action kpu15_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile_action kpu16_action_entries[] = {
+static struct npc_kpu_profile_action kpu16_action_entries[] = {
+	NPC_KPU_NOP_ACTION,
+	NPC_KPU_NOP_ACTION,
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		0, 0, 0, 0, 1,
@@ -13209,7 +15317,7 @@ static const struct npc_kpu_profile_action kpu16_action_entries[] = {
 	},
 };
 
-static const struct npc_kpu_profile npc_kpu_profiles[] = {
+static struct npc_kpu_profile npc_kpu_profiles[] = {
 	{
 		ARRAY_SIZE(kpu1_cam_entries),
 		ARRAY_SIZE(kpu1_action_entries),
@@ -13308,12 +15416,22 @@ static const struct npc_kpu_profile npc_kpu_profiles[] = {
 	},
 };
 
-static const struct npc_lt_def_cfg npc_lt_defaults = {
+static struct npc_lt_def_cfg npc_lt_defaults = {
 	.rx_ol2 = {
 		.lid = NPC_LID_LA,
 		.ltype_match = NPC_LT_LA_ETHER,
 		.ltype_mask = 0x0F,
 	},
+	.ovlan = {
+		.lid = NPC_LID_LB,
+		.ltype_match = NPC_LT_LB_CTAG,
+		.ltype_mask = 0x0F,
+	},
+	.ivlan = {
+		.lid = NPC_LID_LB,
+		.ltype_match = NPC_LT_LB_STAG_QINQ,
+		.ltype_mask = 0x0F,
+	},
 	.rx_oip4 = {
 		.lid = NPC_LID_LC,
 		.ltype_match = NPC_LT_LC_IP,
@@ -13392,6 +15510,30 @@ static const struct npc_lt_def_cfg npc_lt_defaults = {
 			.ltype_match = NPC_LT_LG_TU_IP,
 			.ltype_mask = 0x0F,
 	},
+	.rx_apad0 = {
+		.valid = 0,
+		.lid = NPC_LID_LC,
+		.ltype_match = NPC_LT_LC_IP6,
+		.ltype_mask = 0x0F,
+	},
+	.rx_apad1 = {
+		.valid = 0,
+		.lid = NPC_LID_LC,
+		.ltype_match = NPC_LT_LC_IP6,
+		.ltype_mask = 0x0F,
+	},
+	.rx_et = {
+		{
+			.lid = NPC_LID_LB,
+			.ltype_match = NPC_LT_NA,
+			.ltype_mask = 0x0,
+		},
+		{
+			.lid = NPC_LID_LB,
+			.ltype_match = NPC_LT_NA,
+			.ltype_mask = 0x0,
+		},
+	},
 };
 
 static struct npc_mcam_kex npc_mkex_default = {
@@ -13399,7 +15541,7 @@ static struct npc_mcam_kex npc_mkex_default = {
 	.name = "default",
 	.kpu_version = NPC_KPU_PROFILE_VER,
 	.keyx_cfg = {
-		/* nibble: LA..LE (ltype only) + channel */
+		/* nibble: LA..LE (ltype only) + Error code + Channel */
 		[NIX_INTF_RX] = ((u64)NPC_MCAM_KEY_X2 << 32) | NPC_PARSE_NIBBLE_INTF_RX,
 		/* nibble: LA..LE (ltype only) */
 		[NIX_INTF_TX] = ((u64)NPC_MCAM_KEY_X2 << 32) | NPC_PARSE_NIBBLE_INTF_TX,
@@ -13410,30 +15552,40 @@ static struct npc_mcam_kex npc_mkex_default = {
 		[NPC_LID_LA] = {
 			/* Layer A: Ethernet: */
 			[NPC_LT_LA_ETHER] = {
-				/* DMAC: 6 bytes, KW1[47:0] */
+				/* DMAC: 6 bytes, KW1[55:8] */
 				KEX_LD_CFG(0x05, 0x0, 0x1, 0x0, NPC_KEXOF_DMAC),
-				/* Ethertype: 2 bytes, KW0[47:32] */
-				KEX_LD_CFG(0x01, 0xc, 0x1, 0x0, 0x4),
+				/* Ethertype: 2 bytes, KW0[55:40] */
+				KEX_LD_CFG(0x01, 0xc, 0x1, 0x0, 0x5),
+			},
+			/* Layer A: HiGig2: */
+			[NPC_LT_LA_HIGIG2_ETHER] = {
+				/* Classification: 2 bytes, KW1[23:8] */
+				KEX_LD_CFG(0x01, 0x8, 0x1, 0x0, NPC_KEXOF_DMAC),
+				/* VID: 2 bytes, KW1[39:24] */
+				KEX_LD_CFG(0x01, 0xc, 0x1, 0x0,
+					   NPC_KEXOF_DMAC + 2),
 			},
 		},
 		[NPC_LID_LB] = {
 			/* Layer B: Single VLAN (CTAG) */
-			/* CTAG VLAN[2..3] + Ethertype, 4 bytes, KW0[63:32] */
 			[NPC_LT_LB_CTAG] = {
-				KEX_LD_CFG(0x03, 0x2, 0x1, 0x0, 0x4),
+				/* CTAG VLAN: 2 bytes, KW1[7:0], KW0[63:56] */
+				KEX_LD_CFG(0x01, 0x2, 0x1, 0x0, 0x7),
+				/* Ethertype: 2 bytes, KW0[55:40] */
+				KEX_LD_CFG(0x01, 0x4, 0x1, 0x0, 0x5),
 			},
 			/* Layer B: Stacked VLAN (STAG|QinQ) */
 			[NPC_LT_LB_STAG_QINQ] = {
-				/* Outer VLAN: 2 bytes, KW0[63:48] */
-				KEX_LD_CFG(0x01, 0x2, 0x1, 0x0, 0x6),
-				/* Ethertype: 2 bytes, KW0[47:32] */
-				KEX_LD_CFG(0x01, 0x8, 0x1, 0x0, 0x4),
+				/* Outer VLAN: 2 bytes, KW1[7:0], KW0[63:56] */
+				KEX_LD_CFG(0x01, 0x2, 0x1, 0x0, 0x7),
+				/* Ethertype: 2 bytes, KW0[55:40] */
+				KEX_LD_CFG(0x01, 0x8, 0x1, 0x0, 0x5),
 			},
 			[NPC_LT_LB_FDSA] = {
-				/* SWITCH PORT: 1 byte, KW0[63:48] */
-				KEX_LD_CFG(0x0, 0x1, 0x1, 0x0, 0x6),
-				/* Ethertype: 2 bytes, KW0[47:32] */
-				KEX_LD_CFG(0x01, 0x4, 0x1, 0x0, 0x4),
+				/* SWITCH PORT: 1 byte, KW0[63:56] */
+				KEX_LD_CFG(0x0, 0x1, 0x1, 0x0, 0x7),
+				/* Ethertype: 2 bytes, KW0[55:40] */
+				KEX_LD_CFG(0x01, 0x4, 0x1, 0x0, 0x5),
 			},
 		},
 		[NPC_LID_LC] = {
@@ -13477,6 +15629,13 @@ static struct npc_mcam_kex npc_mkex_default = {
 				/* DMAC: 6 bytes, KW1[63:16] */
 				KEX_LD_CFG(0x05, 0x8, 0x1, 0x0, 0xa),
 			},
+			/* Layer A: HiGig2: */
+			[NPC_LT_LA_IH_NIX_HIGIG2_ETHER] = {
+				/* PF_FUNC: 2B , KW0 [47:32] */
+				KEX_LD_CFG(0x01, 0x0, 0x1, 0x0, 0x4),
+				/* VID: 2 bytes, KW1[31:16] */
+				KEX_LD_CFG(0x01, 0x10, 0x1, 0x0, 0xa),
+			},
 		},
 		[NPC_LID_LB] = {
 			/* Layer B: Single VLAN (CTAG) */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index ab24a5e8ee8a..0b092949d7ac 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -57,6 +57,10 @@ static char *mkex_profile; /* MKEX profile name */
 module_param(mkex_profile, charp, 0000);
 MODULE_PARM_DESC(mkex_profile, "MKEX profile name string");
 
+static char *kpu_profile; /* KPU profile name */
+module_param(kpu_profile, charp, 0000);
+MODULE_PARM_DESC(kpu_profile, "KPU profile name string");
+
 static void rvu_setup_hw_capabilities(struct rvu *rvu)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
@@ -180,6 +184,14 @@ int rvu_rsrc_free_count(struct rsrc_bmap *rsrc)
 	return (rsrc->max - used);
 }
 
+bool is_rsrc_free(struct rsrc_bmap *rsrc, int id)
+{
+	if (!rsrc->bmap)
+		return false;
+
+	return !test_bit(id, rsrc->bmap);
+}
+
 int rvu_alloc_bitmap(struct rsrc_bmap *rsrc)
 {
 	rsrc->bmap = kcalloc(BITS_TO_LONGS(rsrc->max),
@@ -1754,6 +1766,48 @@ int rvu_mbox_handler_get_hw_cap(struct rvu *rvu, struct msg_req *req,
 	return 0;
 }
 
+int rvu_mbox_handler_set_vf_perm(struct rvu *rvu, struct set_vf_perm *req,
+				 struct msg_rsp *rsp)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	u16 pcifunc = req->hdr.pcifunc;
+	struct rvu_pfvf *pfvf;
+	int blkaddr, nixlf;
+	u16 target;
+
+	/* Only PF can add VF permissions */
+	if ((pcifunc & RVU_PFVF_FUNC_MASK) || is_afvf(pcifunc))
+		return -EOPNOTSUPP;
+
+	target = (pcifunc & ~RVU_PFVF_FUNC_MASK) | (req->vf + 1);
+	pfvf = rvu_get_pfvf(rvu, target);
+
+	if (req->flags & RESET_VF_PERM) {
+		pfvf->flags &= RVU_CLEAR_VF_PERM;
+	} else if (test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) ^
+		 (req->flags & VF_TRUSTED)) {
+		change_bit(PF_SET_VF_TRUSTED, &pfvf->flags);
+		/* disable multicast and promisc entries */
+		if (!test_bit(PF_SET_VF_TRUSTED, &pfvf->flags)) {
+			blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, target);
+			if (blkaddr < 0)
+				return 0;
+			nixlf = rvu_get_lf(rvu, &hw->block[blkaddr],
+					   target, 0);
+			if (nixlf < 0)
+				return 0;
+			npc_enadis_default_mce_entry(rvu, target, nixlf,
+						     NIXLF_ALLMULTI_ENTRY,
+						     false);
+			npc_enadis_default_mce_entry(rvu, target, nixlf,
+						     NIXLF_PROMISC_ENTRY,
+						     false);
+		}
+	}
+
+	return 0;
+}
+
 static int rvu_process_mbox_msg(struct otx2_mbox *mbox, int devid,
 				struct mbox_msghdr *req)
 {
@@ -2842,6 +2896,8 @@ static void rvu_update_module_params(struct rvu *rvu)
 
 	strscpy(rvu->mkex_pfl_name,
 		mkex_profile ? mkex_profile : default_pfl_name, MKEX_NAME_LEN);
+	strscpy(rvu->kpu_pfl_name,
+		kpu_profile ? kpu_profile : default_pfl_name, KPU_NAME_LEN);
 }
 
 static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index c2cc4806d13c..9e5d9ba6f01e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -223,13 +223,17 @@ struct rvu_pfvf {
 	u16		maxlen;
 	u16		minlen;
 
-	u8		pf_set_vf_cfg;
 	u8		mac_addr[ETH_ALEN]; /* MAC address of this PF/VF */
 	u8		default_mac[ETH_ALEN]; /* MAC address from FWdata */
 
-	/* Broadcast pkt replication info */
+	/* Broadcast/Multicast/Promisc pkt replication info */
 	u16			bcast_mce_idx;
+	u16			mcast_mce_idx;
+	u16			promisc_mce_idx;
 	struct nix_mce_list	bcast_mce_list;
+	struct nix_mce_list	mcast_mce_list;
+	struct nix_mce_list	promisc_mce_list;
+	bool			use_mce_list;
 
 	struct rvu_npc_mcam_rule *def_ucast_rule;
 
@@ -239,8 +243,18 @@ struct rvu_pfvf {
 	u8	nix_blkaddr; /* BLKADDR_NIX0/1 assigned to this PF */
 	u8	nix_rx_intf; /* NIX0_RX/NIX1_RX interface to NPC */
 	u8	nix_tx_intf; /* NIX0_TX/NIX1_TX interface to NPC */
+	unsigned long flags;
 };
 
+enum rvu_pfvf_flags {
+	NIXLF_INITIALIZED = 0,
+	PF_SET_VF_MAC,
+	PF_SET_VF_CFG,
+	PF_SET_VF_TRUSTED,
+};
+
+#define RVU_CLEAR_VF_PERM  ~GENMASK(PF_SET_VF_TRUSTED, PF_SET_VF_MAC)
+
 struct nix_txsch {
 	struct rsrc_bmap schq;
 	u8   lvl;
@@ -282,6 +296,13 @@ struct nix_txvlan {
 	struct mutex rsrc_lock; /* Serialize resource alloc/free */
 };
 
+struct nix_ipolicer {
+	struct rsrc_bmap band_prof;
+	u16 *pfvf_map;
+	u16 *match_id;
+	u16 *ref_count;
+};
+
 struct nix_hw {
 	int blkaddr;
 	struct rvu *rvu;
@@ -291,6 +312,7 @@ struct nix_hw {
 	struct nix_mark_format mark_format;
 	struct nix_lso lso;
 	struct nix_txvlan txvlan;
+	struct nix_ipolicer *ipolicer;
 };
 
 /* RVU block's capabilities or functionality,
@@ -308,6 +330,7 @@ struct hw_cap {
 	bool	nix_rx_multicast;	 /* Rx packet replication support */
 	bool	per_pf_mbox_regs; /* PF mbox specified in per PF registers ? */
 	bool	programmable_chans; /* Channels programmable ? */
+	bool	ipolicer;
 };
 
 struct rvu_hwinfo {
@@ -386,6 +409,7 @@ struct npc_kpu_profile_adapter {
 	const struct npc_kpu_profile_action	*ikpu; /* array[pkinds] */
 	const struct npc_kpu_profile	*kpu; /* array[kpus] */
 	struct npc_mcam_kex		*mkex;
+	bool				custom;
 	size_t				pkinds;
 	size_t				kpus;
 };
@@ -435,9 +459,13 @@ struct rvu {
 	struct mutex		cgx_cfg_lock; /* serialize cgx configuration */
 
 	char mkex_pfl_name[MKEX_NAME_LEN]; /* Configured MKEX profile name */
+	char kpu_pfl_name[KPU_NAME_LEN]; /* Configured KPU profile name */
 
 	/* Firmware data */
 	struct rvu_fwdata	*fwdata;
+	void			*kpu_fwdata;
+	size_t			kpu_fwdata_sz;
+	void __iomem		*kpu_prfl_addr;
 
 	/* NPC KPU data */
 	struct npc_kpu_profile_adapter kpu;
@@ -543,11 +571,16 @@ static inline u16 rvu_nix_chan_cpt(struct rvu *rvu, u8 chan)
 /* Function Prototypes
  * RVU
  */
-static inline int is_afvf(u16 pcifunc)
+static inline bool is_afvf(u16 pcifunc)
 {
 	return !(pcifunc & ~RVU_PFVF_FUNC_MASK);
 }
 
+static inline bool is_vf(u16 pcifunc)
+{
+	return !!(pcifunc & RVU_PFVF_FUNC_MASK);
+}
+
 /* check if PF_FUNC is AF */
 static inline bool is_pffunc_af(u16 pcifunc)
 {
@@ -563,6 +596,7 @@ static inline bool is_rvu_fwdata_valid(struct rvu *rvu)
 int rvu_alloc_bitmap(struct rsrc_bmap *rsrc);
 int rvu_alloc_rsrc(struct rsrc_bmap *rsrc);
 void rvu_free_rsrc(struct rsrc_bmap *rsrc, int id);
+bool is_rsrc_free(struct rsrc_bmap *rsrc, int id);
 int rvu_rsrc_free_count(struct rsrc_bmap *rsrc);
 int rvu_alloc_rsrc_contig(struct rsrc_bmap *rsrc, int nrsrc);
 bool rvu_rsrc_check_contig(struct rsrc_bmap *rsrc, int nrsrc);
@@ -603,6 +637,12 @@ static inline void rvu_get_cgx_lmac_id(u8 map, u8 *cgx_id, u8 *lmac_id)
 	*lmac_id = (map & 0xF);
 }
 
+static inline bool is_cgx_vf(struct rvu *rvu, u16 pcifunc)
+{
+	return ((pcifunc & RVU_PFVF_FUNC_MASK) &&
+		is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc)));
+}
+
 #define M(_name, _id, fn_name, req, rsp)				\
 int rvu_mbox_handler_ ## fn_name(struct rvu *, struct req *, struct rsp *);
 MBOX_MESSAGES
@@ -632,10 +672,22 @@ void rvu_nix_freemem(struct rvu *rvu);
 int rvu_get_nixlf_count(struct rvu *rvu);
 void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int npalf);
 int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf, int *nix_blkaddr);
-int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add);
+int nix_update_mce_list(struct rvu *rvu, u16 pcifunc,
+			struct nix_mce_list *mce_list,
+			int mce_idx, int mcam_index, bool add);
+void nix_get_mce_list(struct rvu *rvu, u16 pcifunc, int type,
+		      struct nix_mce_list **mce_list, int *mce_idx);
 struct nix_hw *get_nix_hw(struct rvu_hwinfo *hw, int blkaddr);
 int rvu_get_next_nix_blkaddr(struct rvu *rvu, int blkaddr);
 void rvu_nix_reset_mac(struct rvu_pfvf *pfvf, int pcifunc);
+int nix_get_struct_ptrs(struct rvu *rvu, u16 pcifunc,
+			struct nix_hw **nix_hw, int *blkaddr);
+int rvu_nix_setup_ratelimit_aggr(struct rvu *rvu, u16 pcifunc,
+				 u16 rq_idx, u16 match_id);
+int nix_aq_context_read(struct rvu *rvu, struct nix_hw *nix_hw,
+			struct nix_cn10k_aq_enq_req *aq_req,
+			struct nix_cn10k_aq_enq_rsp *aq_rsp,
+			u16 pcifunc, u8 ctype, u32 qidx);
 
 /* NPC APIs */
 int rvu_npc_init(struct rvu *rvu);
@@ -646,13 +698,19 @@ int npc_config_ts_kpuaction(struct rvu *rvu, int pf, u16 pcifunc, bool en);
 void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc,
 				 int nixlf, u64 chan, u8 *mac_addr);
 void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
-				   int nixlf, u64 chan, u8 chan_cnt,
-				   bool allmulti);
-void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf);
-void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf);
+				   int nixlf, u64 chan, u8 chan_cnt);
+void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
+				  bool enable);
 void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 				       int nixlf, u64 chan);
-void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable);
+void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
+				bool enable);
+void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
+				    u64 chan);
+void rvu_npc_enable_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
+				   bool enable);
+void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc,
+				  int nixlf, int type, bool enable);
 void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
 void rvu_npc_free_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
 void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 9bf8eaabf9ab..3cc3c6fd1d84 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -1632,6 +1632,165 @@ static int rvu_dbg_nix_qsize_display(struct seq_file *filp, void *unused)
 
 RVU_DEBUG_SEQ_FOPS(nix_qsize, nix_qsize_display, nix_qsize_write);
 
+static void print_band_prof_ctx(struct seq_file *m,
+				struct nix_bandprof_s *prof)
+{
+	char *str;
+
+	switch (prof->pc_mode) {
+	case NIX_RX_PC_MODE_VLAN:
+		str = "VLAN";
+		break;
+	case NIX_RX_PC_MODE_DSCP:
+		str = "DSCP";
+		break;
+	case NIX_RX_PC_MODE_GEN:
+		str = "Generic";
+		break;
+	case NIX_RX_PC_MODE_RSVD:
+		str = "Reserved";
+		break;
+	}
+	seq_printf(m, "W0: pc_mode\t\t%s\n", str);
+	str = (prof->icolor == 3) ? "Color blind" :
+		(prof->icolor == 0) ? "Green" :
+		(prof->icolor == 1) ? "Yellow" : "Red";
+	seq_printf(m, "W0: icolor\t\t%s\n", str);
+	seq_printf(m, "W0: tnl_ena\t\t%d\n", prof->tnl_ena);
+	seq_printf(m, "W0: peir_exponent\t%d\n", prof->peir_exponent);
+	seq_printf(m, "W0: pebs_exponent\t%d\n", prof->pebs_exponent);
+	seq_printf(m, "W0: cir_exponent\t%d\n", prof->cir_exponent);
+	seq_printf(m, "W0: cbs_exponent\t%d\n", prof->cbs_exponent);
+	seq_printf(m, "W0: peir_mantissa\t%d\n", prof->peir_mantissa);
+	seq_printf(m, "W0: pebs_mantissa\t%d\n", prof->pebs_mantissa);
+	seq_printf(m, "W0: cir_mantissa\t%d\n", prof->cir_mantissa);
+
+	seq_printf(m, "W1: cbs_mantissa\t%d\n", prof->cbs_mantissa);
+	str = (prof->lmode == 0) ? "byte" : "packet";
+	seq_printf(m, "W1: lmode\t\t%s\n", str);
+	seq_printf(m, "W1: l_select\t\t%d\n", prof->l_sellect);
+	seq_printf(m, "W1: rdiv\t\t%d\n", prof->rdiv);
+	seq_printf(m, "W1: adjust_exponent\t%d\n", prof->adjust_exponent);
+	seq_printf(m, "W1: adjust_mantissa\t%d\n", prof->adjust_mantissa);
+	str = (prof->gc_action == 0) ? "PASS" :
+		(prof->gc_action == 1) ? "DROP" : "RED";
+	seq_printf(m, "W1: gc_action\t\t%s\n", str);
+	str = (prof->yc_action == 0) ? "PASS" :
+		(prof->yc_action == 1) ? "DROP" : "RED";
+	seq_printf(m, "W1: yc_action\t\t%s\n", str);
+	str = (prof->rc_action == 0) ? "PASS" :
+		(prof->rc_action == 1) ? "DROP" : "RED";
+	seq_printf(m, "W1: rc_action\t\t%s\n", str);
+	seq_printf(m, "W1: meter_algo\t\t%d\n", prof->meter_algo);
+	seq_printf(m, "W1: band_prof_id\t%d\n", prof->band_prof_id);
+	seq_printf(m, "W1: hl_en\t\t%d\n", prof->hl_en);
+
+	seq_printf(m, "W2: ts\t\t\t%lld\n", (u64)prof->ts);
+	seq_printf(m, "W3: pe_accum\t\t%d\n", prof->pe_accum);
+	seq_printf(m, "W3: c_accum\t\t%d\n", prof->c_accum);
+	seq_printf(m, "W4: green_pkt_pass\t%lld\n",
+		   (u64)prof->green_pkt_pass);
+	seq_printf(m, "W5: yellow_pkt_pass\t%lld\n",
+		   (u64)prof->yellow_pkt_pass);
+	seq_printf(m, "W6: red_pkt_pass\t%lld\n", (u64)prof->red_pkt_pass);
+	seq_printf(m, "W7: green_octs_pass\t%lld\n",
+		   (u64)prof->green_octs_pass);
+	seq_printf(m, "W8: yellow_octs_pass\t%lld\n",
+		   (u64)prof->yellow_octs_pass);
+	seq_printf(m, "W9: red_octs_pass\t%lld\n", (u64)prof->red_octs_pass);
+	seq_printf(m, "W10: green_pkt_drop\t%lld\n",
+		   (u64)prof->green_pkt_drop);
+	seq_printf(m, "W11: yellow_pkt_drop\t%lld\n",
+		   (u64)prof->yellow_pkt_drop);
+	seq_printf(m, "W12: red_pkt_drop\t%lld\n", (u64)prof->red_pkt_drop);
+	seq_printf(m, "W13: green_octs_drop\t%lld\n",
+		   (u64)prof->green_octs_drop);
+	seq_printf(m, "W14: yellow_octs_drop\t%lld\n",
+		   (u64)prof->yellow_octs_drop);
+	seq_printf(m, "W15: red_octs_drop\t%lld\n", (u64)prof->red_octs_drop);
+	seq_puts(m, "==============================\n");
+}
+
+static int rvu_dbg_nix_band_prof_ctx_display(struct seq_file *m, void *unused)
+{
+	struct nix_hw *nix_hw = m->private;
+	struct nix_cn10k_aq_enq_req aq_req;
+	struct nix_cn10k_aq_enq_rsp aq_rsp;
+	struct rvu *rvu = nix_hw->rvu;
+	struct nix_ipolicer *ipolicer;
+	int layer, prof_idx, idx, rc;
+	u16 pcifunc;
+	char *str;
+
+	for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) {
+		if (layer == BAND_PROF_INVAL_LAYER)
+			continue;
+		str = (layer == BAND_PROF_LEAF_LAYER) ? "Leaf" :
+			(layer == BAND_PROF_MID_LAYER) ? "Mid" : "Top";
+
+		seq_printf(m, "\n%s bandwidth profiles\n", str);
+		seq_puts(m, "=======================\n");
+
+		ipolicer = &nix_hw->ipolicer[layer];
+
+		for (idx = 0; idx < ipolicer->band_prof.max; idx++) {
+			if (is_rsrc_free(&ipolicer->band_prof, idx))
+				continue;
+
+			prof_idx = (idx & 0x3FFF) | (layer << 14);
+			rc = nix_aq_context_read(rvu, nix_hw, &aq_req, &aq_rsp,
+						 0x00, NIX_AQ_CTYPE_BANDPROF,
+						 prof_idx);
+			if (rc) {
+				dev_err(rvu->dev,
+					"%s: Failed to fetch context of %s profile %d, err %d\n",
+					__func__, str, idx, rc);
+				return 0;
+			}
+			seq_printf(m, "\n%s bandwidth profile:: %d\n", str, idx);
+			pcifunc = ipolicer->pfvf_map[idx];
+			if (!(pcifunc & RVU_PFVF_FUNC_MASK))
+				seq_printf(m, "Allocated to :: PF %d\n",
+					   rvu_get_pf(pcifunc));
+			else
+				seq_printf(m, "Allocated to :: PF %d VF %d\n",
+					   rvu_get_pf(pcifunc),
+					   (pcifunc & RVU_PFVF_FUNC_MASK) - 1);
+			print_band_prof_ctx(m, &aq_rsp.prof);
+		}
+	}
+	return 0;
+}
+
+RVU_DEBUG_SEQ_FOPS(nix_band_prof_ctx, nix_band_prof_ctx_display, NULL);
+
+static int rvu_dbg_nix_band_prof_rsrc_display(struct seq_file *m, void *unused)
+{
+	struct nix_hw *nix_hw = m->private;
+	struct nix_ipolicer *ipolicer;
+	int layer;
+	char *str;
+
+	seq_puts(m, "\nBandwidth profile resource free count\n");
+	seq_puts(m, "=====================================\n");
+	for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) {
+		if (layer == BAND_PROF_INVAL_LAYER)
+			continue;
+		str = (layer == BAND_PROF_LEAF_LAYER) ? "Leaf" :
+			(layer == BAND_PROF_MID_LAYER) ? "Mid " : "Top ";
+
+		ipolicer = &nix_hw->ipolicer[layer];
+		seq_printf(m, "%s :: Max: %4d  Free: %4d\n", str,
+			   ipolicer->band_prof.max,
+			   rvu_rsrc_free_count(&ipolicer->band_prof));
+	}
+	seq_puts(m, "=====================================\n");
+
+	return 0;
+}
+
+RVU_DEBUG_SEQ_FOPS(nix_band_prof_rsrc, nix_band_prof_rsrc_display, NULL);
+
 static void rvu_dbg_nix_init(struct rvu *rvu, int blkaddr)
 {
 	struct nix_hw *nix_hw;
@@ -1664,6 +1823,10 @@ static void rvu_dbg_nix_init(struct rvu *rvu, int blkaddr)
 			    &rvu_dbg_nix_ndc_rx_hits_miss_fops);
 	debugfs_create_file("qsize", 0600, rvu->rvu_dbg.nix, rvu,
 			    &rvu_dbg_nix_qsize_fops);
+	debugfs_create_file("ingress_policer_ctx", 0600, rvu->rvu_dbg.nix, nix_hw,
+			    &rvu_dbg_nix_band_prof_ctx_fops);
+	debugfs_create_file("ingress_policer_rsrc", 0600, rvu->rvu_dbg.nix, nix_hw,
+			    &rvu_dbg_nix_band_prof_rsrc_fops);
 }
 
 static void rvu_dbg_npa_init(struct rvu *rvu)
@@ -2132,6 +2295,7 @@ static int rvu_dbg_npc_mcam_show_rules(struct seq_file *s, void *unused)
 	struct rvu *rvu = s->private;
 	struct npc_mcam *mcam;
 	int pf, vf = -1;
+	bool enabled;
 	int blkaddr;
 	u16 target;
 	u64 hits;
@@ -2173,7 +2337,9 @@ static int rvu_dbg_npc_mcam_show_rules(struct seq_file *s, void *unused)
 		}
 
 		rvu_dbg_npc_mcam_show_action(s, iter);
-		seq_printf(s, "\tenabled: %s\n", iter->enable ? "yes" : "no");
+
+		enabled = is_mcam_entry_enabled(rvu, mcam, blkaddr, iter->entry);
+		seq_printf(s, "\tenabled: %s\n", enabled ? "yes" : "no");
 
 		if (!iter->has_cntr)
 			continue;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 0a8bd667cb11..d6f8210652c5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -21,6 +21,16 @@
 static void nix_free_tx_vtag_entries(struct rvu *rvu, u16 pcifunc);
 static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req,
 			    int type, int chan_id);
+static int nix_update_mce_rule(struct rvu *rvu, u16 pcifunc,
+			       int type, bool add);
+static int nix_setup_ipolicers(struct rvu *rvu,
+			       struct nix_hw *nix_hw, int blkaddr);
+static void nix_ipolicer_freemem(struct nix_hw *nix_hw);
+static int nix_verify_bandprof(struct nix_cn10k_aq_enq_req *req,
+			       struct nix_hw *nix_hw, u16 pcifunc);
+static int nix_free_all_bandprof(struct rvu *rvu, u16 pcifunc);
+static void nix_clear_ratelimit_aggr(struct rvu *rvu, struct nix_hw *nix_hw,
+				     u32 leaf_prof);
 
 enum mc_tbl_sz {
 	MC_TBL_SZ_256,
@@ -132,6 +142,22 @@ int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf, int *nix_blkaddr)
 	return 0;
 }
 
+int nix_get_struct_ptrs(struct rvu *rvu, u16 pcifunc,
+			struct nix_hw **nix_hw, int *blkaddr)
+{
+	struct rvu_pfvf *pfvf;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	*blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (!pfvf->nixlf || *blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	*nix_hw = get_nix_hw(rvu->hw, *blkaddr);
+	if (!*nix_hw)
+		return NIX_AF_ERR_INVALID_NIXBLK;
+	return 0;
+}
+
 static void nix_mce_list_init(struct nix_mce_list *list, int max)
 {
 	INIT_HLIST_HEAD(&list->head);
@@ -274,7 +300,7 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf)
 		pfvf->tx_chan_cnt = 1;
 		rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf,
 					      pfvf->rx_chan_base,
-					      pfvf->rx_chan_cnt, false);
+					      pfvf->rx_chan_cnt);
 		break;
 	}
 
@@ -285,16 +311,17 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf)
 				    pfvf->rx_chan_base, pfvf->mac_addr);
 
 	/* Add this PF_FUNC to bcast pkt replication list */
-	err = nix_update_bcast_mce_list(rvu, pcifunc, true);
+	err = nix_update_mce_rule(rvu, pcifunc, NIXLF_BCAST_ENTRY, true);
 	if (err) {
 		dev_err(rvu->dev,
 			"Bcast list, failed to enable PF_FUNC 0x%x\n",
 			pcifunc);
 		return err;
 	}
-
+	/* Install MCAM rule matching Ethernet broadcast mac address */
 	rvu_npc_install_bcast_match_entry(rvu, pcifunc,
 					  nixlf, pfvf->rx_chan_base);
+
 	pfvf->maxlen = NIC_HW_MIN_FRS;
 	pfvf->minlen = NIC_HW_MIN_FRS;
 
@@ -310,7 +337,7 @@ static void nix_interface_deinit(struct rvu *rvu, u16 pcifunc, u8 nixlf)
 	pfvf->minlen = 0;
 
 	/* Remove this PF_FUNC from bcast pkt replication list */
-	err = nix_update_bcast_mce_list(rvu, pcifunc, false);
+	err = nix_update_mce_rule(rvu, pcifunc, NIXLF_BCAST_ENTRY, false);
 	if (err) {
 		dev_err(rvu->dev,
 			"Bcast list, failed to disable PF_FUNC 0x%x\n",
@@ -680,8 +707,11 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
 	nixlf = rvu_get_lf(rvu, block, pcifunc, 0);
 
-	/* Skip NIXLF check for broadcast MCE entry init */
-	if (!(!rsp && req->ctype == NIX_AQ_CTYPE_MCE)) {
+	/* Skip NIXLF check for broadcast MCE entry and bandwidth profile
+	 * operations done by AF itself.
+	 */
+	if (!((!rsp && req->ctype == NIX_AQ_CTYPE_MCE) ||
+	      (req->ctype == NIX_AQ_CTYPE_BANDPROF && !pcifunc))) {
 		if (!pfvf->nixlf || nixlf < 0)
 			return NIX_AF_ERR_AF_LF_INVALID;
 	}
@@ -721,6 +751,11 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
 		if (rsp)
 			rc = NIX_AF_ERR_AQ_ENQUEUE;
 		break;
+	case NIX_AQ_CTYPE_BANDPROF:
+		if (nix_verify_bandprof((struct nix_cn10k_aq_enq_req *)req,
+					nix_hw, pcifunc))
+			rc = NIX_AF_ERR_INVALID_BANDPROF;
+		break;
 	default:
 		rc = NIX_AF_ERR_AQ_ENQUEUE;
 	}
@@ -777,6 +812,9 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
 		else if (req->ctype == NIX_AQ_CTYPE_MCE)
 			memcpy(mask, &req->mce_mask,
 			       sizeof(struct nix_rx_mce_s));
+		else if (req->ctype == NIX_AQ_CTYPE_BANDPROF)
+			memcpy(mask, &req->prof_mask,
+			       sizeof(struct nix_bandprof_s));
 		fallthrough;
 	case NIX_AQ_INSTOP_INIT:
 		if (req->ctype == NIX_AQ_CTYPE_RQ)
@@ -789,6 +827,8 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
 			memcpy(ctx, &req->rss, sizeof(struct nix_rsse_s));
 		else if (req->ctype == NIX_AQ_CTYPE_MCE)
 			memcpy(ctx, &req->mce, sizeof(struct nix_rx_mce_s));
+		else if (req->ctype == NIX_AQ_CTYPE_BANDPROF)
+			memcpy(ctx, &req->prof, sizeof(struct nix_bandprof_s));
 		break;
 	case NIX_AQ_INSTOP_NOP:
 	case NIX_AQ_INSTOP_READ:
@@ -866,6 +906,9 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
 			else if (req->ctype == NIX_AQ_CTYPE_MCE)
 				memcpy(&rsp->mce, ctx,
 				       sizeof(struct nix_rx_mce_s));
+			else if (req->ctype == NIX_AQ_CTYPE_BANDPROF)
+				memcpy(&rsp->prof, ctx,
+				       sizeof(struct nix_bandprof_s));
 		}
 	}
 
@@ -2203,8 +2246,8 @@ static int nix_blk_setup_mce(struct rvu *rvu, struct nix_hw *nix_hw,
 	aq_req.op = op;
 	aq_req.qidx = mce;
 
-	/* Forward bcast pkts to RQ0, RSS not needed */
-	aq_req.mce.op = 0;
+	/* Use RSS with RSS index 0 */
+	aq_req.mce.op = 1;
 	aq_req.mce.index = 0;
 	aq_req.mce.eol = eol;
 	aq_req.mce.pf_func = pcifunc;
@@ -2222,8 +2265,8 @@ static int nix_blk_setup_mce(struct rvu *rvu, struct nix_hw *nix_hw,
 	return 0;
 }
 
-static int nix_update_mce_list(struct nix_mce_list *mce_list,
-			       u16 pcifunc, bool add)
+static int nix_update_mce_list_entry(struct nix_mce_list *mce_list,
+				     u16 pcifunc, bool add)
 {
 	struct mce *mce, *tail = NULL;
 	bool delete = false;
@@ -2234,6 +2277,9 @@ static int nix_update_mce_list(struct nix_mce_list *mce_list,
 		if (mce->pcifunc == pcifunc && !add) {
 			delete = true;
 			break;
+		} else if (mce->pcifunc == pcifunc && add) {
+			/* entry already exists */
+			return 0;
 		}
 		tail = mce;
 	}
@@ -2261,36 +2307,23 @@ static int nix_update_mce_list(struct nix_mce_list *mce_list,
 	return 0;
 }
 
-int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add)
+int nix_update_mce_list(struct rvu *rvu, u16 pcifunc,
+			struct nix_mce_list *mce_list,
+			int mce_idx, int mcam_index, bool add)
 {
-	int err = 0, idx, next_idx, last_idx;
-	struct nix_mce_list *mce_list;
+	int err = 0, idx, next_idx, last_idx, blkaddr, npc_blkaddr;
+	struct npc_mcam *mcam = &rvu->hw->mcam;
 	struct nix_mcast *mcast;
 	struct nix_hw *nix_hw;
-	struct rvu_pfvf *pfvf;
 	struct mce *mce;
-	int blkaddr;
-
-	/* Broadcast pkt replication is not needed for AF's VFs, hence skip */
-	if (is_afvf(pcifunc))
-		return 0;
-
-	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
-	if (blkaddr < 0)
-		return 0;
 
-	nix_hw = get_nix_hw(rvu->hw, blkaddr);
-	if (!nix_hw)
-		return 0;
-
-	mcast = &nix_hw->mcast;
+	if (!mce_list)
+		return -EINVAL;
 
 	/* Get this PF/VF func's MCE index */
-	pfvf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK);
-	idx = pfvf->bcast_mce_idx + (pcifunc & RVU_PFVF_FUNC_MASK);
+	idx = mce_idx + (pcifunc & RVU_PFVF_FUNC_MASK);
 
-	mce_list = &pfvf->bcast_mce_list;
-	if (idx > (pfvf->bcast_mce_idx + mce_list->max)) {
+	if (idx > (mce_idx + mce_list->max)) {
 		dev_err(rvu->dev,
 			"%s: Idx %d > max MCE idx %d, for PF%d bcast list\n",
 			__func__, idx, mce_list->max,
@@ -2298,20 +2331,26 @@ int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add)
 		return -EINVAL;
 	}
 
+	err = nix_get_struct_ptrs(rvu, pcifunc, &nix_hw, &blkaddr);
+	if (err)
+		return err;
+
+	mcast = &nix_hw->mcast;
 	mutex_lock(&mcast->mce_lock);
 
-	err = nix_update_mce_list(mce_list, pcifunc, add);
+	err = nix_update_mce_list_entry(mce_list, pcifunc, add);
 	if (err)
 		goto end;
 
 	/* Disable MCAM entry in NPC */
 	if (!mce_list->count) {
-		rvu_npc_enable_bcast_entry(rvu, pcifunc, false);
+		npc_blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+		npc_enable_mcam_entry(rvu, mcam, npc_blkaddr, mcam_index, false);
 		goto end;
 	}
 
 	/* Dump the updated list to HW */
-	idx = pfvf->bcast_mce_idx;
+	idx = mce_idx;
 	last_idx = idx + mce_list->count - 1;
 	hlist_for_each_entry(mce, &mce_list->head, node) {
 		if (idx > last_idx)
@@ -2332,7 +2371,71 @@ end:
 	return err;
 }
 
-static int nix_setup_bcast_tables(struct rvu *rvu, struct nix_hw *nix_hw)
+void nix_get_mce_list(struct rvu *rvu, u16 pcifunc, int type,
+		      struct nix_mce_list **mce_list, int *mce_idx)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	struct rvu_pfvf *pfvf;
+
+	if (!hw->cap.nix_rx_multicast ||
+	    !is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc & ~RVU_PFVF_FUNC_MASK))) {
+		*mce_list = NULL;
+		*mce_idx = 0;
+		return;
+	}
+
+	/* Get this PF/VF func's MCE index */
+	pfvf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK);
+
+	if (type == NIXLF_BCAST_ENTRY) {
+		*mce_list = &pfvf->bcast_mce_list;
+		*mce_idx = pfvf->bcast_mce_idx;
+	} else if (type == NIXLF_ALLMULTI_ENTRY) {
+		*mce_list = &pfvf->mcast_mce_list;
+		*mce_idx = pfvf->mcast_mce_idx;
+	} else if (type == NIXLF_PROMISC_ENTRY) {
+		*mce_list = &pfvf->promisc_mce_list;
+		*mce_idx = pfvf->promisc_mce_idx;
+	}  else {
+		*mce_list = NULL;
+		*mce_idx = 0;
+	}
+}
+
+static int nix_update_mce_rule(struct rvu *rvu, u16 pcifunc,
+			       int type, bool add)
+{
+	int err = 0, nixlf, blkaddr, mcam_index, mce_idx;
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	struct rvu_hwinfo *hw = rvu->hw;
+	struct nix_mce_list *mce_list;
+
+	/* skip multicast pkt replication for AF's VFs */
+	if (is_afvf(pcifunc))
+		return 0;
+
+	if (!hw->cap.nix_rx_multicast)
+		return 0;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (blkaddr < 0)
+		return -EINVAL;
+
+	nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0);
+	if (nixlf < 0)
+		return -EINVAL;
+
+	nix_get_mce_list(rvu, pcifunc, type, &mce_list, &mce_idx);
+
+	mcam_index = npc_get_nixlf_mcam_index(mcam,
+					      pcifunc & ~RVU_PFVF_FUNC_MASK,
+					      nixlf, type);
+	err = nix_update_mce_list(rvu, pcifunc, mce_list,
+				  mce_idx, mcam_index, add);
+	return err;
+}
+
+static int nix_setup_mce_tables(struct rvu *rvu, struct nix_hw *nix_hw)
 {
 	struct nix_mcast *mcast = &nix_hw->mcast;
 	int err, pf, numvfs, idx;
@@ -2355,11 +2458,18 @@ static int nix_setup_bcast_tables(struct rvu *rvu, struct nix_hw *nix_hw)
 		if (pfvf->nix_blkaddr != nix_hw->blkaddr)
 			continue;
 
-		/* Save the start MCE */
+		/* save start idx of broadcast mce list */
 		pfvf->bcast_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1);
-
 		nix_mce_list_init(&pfvf->bcast_mce_list, numvfs + 1);
 
+		/* save start idx of multicast mce list */
+		pfvf->mcast_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1);
+		nix_mce_list_init(&pfvf->mcast_mce_list, numvfs + 1);
+
+		/* save the start idx of promisc mce list */
+		pfvf->promisc_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1);
+		nix_mce_list_init(&pfvf->promisc_mce_list, numvfs + 1);
+
 		for (idx = 0; idx < (numvfs + 1); idx++) {
 			/* idx-0 is for PF, followed by VFs */
 			pcifunc = (pf << RVU_PFVF_PF_SHIFT);
@@ -2375,6 +2485,22 @@ static int nix_setup_bcast_tables(struct rvu *rvu, struct nix_hw *nix_hw)
 						pcifunc, 0, true);
 			if (err)
 				return err;
+
+			/* add dummy entries to multicast mce list */
+			err = nix_blk_setup_mce(rvu, nix_hw,
+						pfvf->mcast_mce_idx + idx,
+						NIX_AQ_INSTOP_INIT,
+						pcifunc, 0, true);
+			if (err)
+				return err;
+
+			/* add dummy entries to promisc mce list */
+			err = nix_blk_setup_mce(rvu, nix_hw,
+						pfvf->promisc_mce_idx + idx,
+						NIX_AQ_INSTOP_INIT,
+						pcifunc, 0, true);
+			if (err)
+				return err;
 		}
 	}
 	return 0;
@@ -2421,7 +2547,7 @@ static int nix_setup_mcast(struct rvu *rvu, struct nix_hw *nix_hw, int blkaddr)
 
 	mutex_init(&mcast->mce_lock);
 
-	return nix_setup_bcast_tables(rvu, nix_hw);
+	return nix_setup_mce_tables(rvu, nix_hw);
 }
 
 static int nix_setup_txvlan(struct rvu *rvu, struct nix_hw *nix_hw)
@@ -3035,15 +3161,22 @@ int rvu_mbox_handler_nix_set_mac_addr(struct rvu *rvu,
 
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
 
-	/* VF can't overwrite admin(PF) changes */
-	if (from_vf && pfvf->pf_set_vf_cfg)
+	/* untrusted VF can't overwrite admin(PF) changes */
+	if (!test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) &&
+	    (from_vf && test_bit(PF_SET_VF_MAC, &pfvf->flags))) {
+		dev_warn(rvu->dev,
+			 "MAC address set by admin(PF) cannot be overwritten by untrusted VF");
 		return -EPERM;
+	}
 
 	ether_addr_copy(pfvf->mac_addr, req->mac_addr);
 
 	rvu_npc_install_ucast_entry(rvu, pcifunc, nixlf,
 				    pfvf->rx_chan_base, req->mac_addr);
 
+	if (test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) && from_vf)
+		ether_addr_copy(pfvf->default_mac, req->mac_addr);
+
 	return 0;
 }
 
@@ -3067,30 +3200,75 @@ int rvu_mbox_handler_nix_get_mac_addr(struct rvu *rvu,
 int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req,
 				     struct msg_rsp *rsp)
 {
-	bool allmulti = false, disable_promisc = false;
+	bool allmulti, promisc, nix_rx_multicast;
 	u16 pcifunc = req->hdr.pcifunc;
-	int blkaddr, nixlf, err;
 	struct rvu_pfvf *pfvf;
+	int nixlf, err;
 
-	err = nix_get_nixlf(rvu, pcifunc, &nixlf, &blkaddr);
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	promisc = req->mode & NIX_RX_MODE_PROMISC ? true : false;
+	allmulti = req->mode & NIX_RX_MODE_ALLMULTI ? true : false;
+	pfvf->use_mce_list = req->mode & NIX_RX_MODE_USE_MCE ? true : false;
+
+	nix_rx_multicast = rvu->hw->cap.nix_rx_multicast & pfvf->use_mce_list;
+
+	if (is_vf(pcifunc) && !nix_rx_multicast &&
+	    (promisc || allmulti)) {
+		dev_warn_ratelimited(rvu->dev,
+				     "VF promisc/multicast not supported\n");
+		return 0;
+	}
+
+	/* untrusted VF can't configure promisc/allmulti */
+	if (is_vf(pcifunc) && !test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) &&
+	    (promisc || allmulti))
+		return 0;
+
+	err = nix_get_nixlf(rvu, pcifunc, &nixlf, NULL);
 	if (err)
 		return err;
 
-	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	if (nix_rx_multicast) {
+		/* add/del this PF_FUNC to/from mcast pkt replication list */
+		err = nix_update_mce_rule(rvu, pcifunc, NIXLF_ALLMULTI_ENTRY,
+					  allmulti);
+		if (err) {
+			dev_err(rvu->dev,
+				"Failed to update pcifunc 0x%x to multicast list\n",
+				pcifunc);
+			return err;
+		}
 
-	if (req->mode & NIX_RX_MODE_PROMISC)
-		allmulti = false;
-	else if (req->mode & NIX_RX_MODE_ALLMULTI)
-		allmulti = true;
-	else
-		disable_promisc = true;
+		/* add/del this PF_FUNC to/from promisc pkt replication list */
+		err = nix_update_mce_rule(rvu, pcifunc, NIXLF_PROMISC_ENTRY,
+					  promisc);
+		if (err) {
+			dev_err(rvu->dev,
+				"Failed to update pcifunc 0x%x to promisc list\n",
+				pcifunc);
+			return err;
+		}
+	}
 
-	if (disable_promisc)
-		rvu_npc_disable_promisc_entry(rvu, pcifunc, nixlf);
-	else
+	/* install/uninstall allmulti entry */
+	if (allmulti) {
+		rvu_npc_install_allmulti_entry(rvu, pcifunc, nixlf,
+					       pfvf->rx_chan_base);
+	} else {
+		if (!nix_rx_multicast)
+			rvu_npc_enable_allmulti_entry(rvu, pcifunc, nixlf, false);
+	}
+
+	/* install/uninstall promisc entry */
+	if (promisc) {
 		rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf,
 					      pfvf->rx_chan_base,
-					      pfvf->rx_chan_cnt, allmulti);
+					      pfvf->rx_chan_cnt);
+	} else {
+		if (!nix_rx_multicast)
+			rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf, false);
+	}
+
 	return 0;
 }
 
@@ -3470,6 +3648,10 @@ static int rvu_nix_block_init(struct rvu *rvu, struct nix_hw *nix_hw)
 		if (err)
 			return err;
 
+		err = nix_setup_ipolicers(rvu, nix_hw, blkaddr);
+		if (err)
+			return err;
+
 		err = nix_af_mark_format_setup(rvu, nix_hw, blkaddr);
 		if (err)
 			return err;
@@ -3523,6 +3705,40 @@ static int rvu_nix_block_init(struct rvu *rvu, struct nix_hw *nix_hw)
 			    (ltdefs->rx_isctp.lid << 8) | (ltdefs->rx_isctp.ltype_match << 4) |
 			    ltdefs->rx_isctp.ltype_mask);
 
+		if (!is_rvu_otx2(rvu)) {
+			/* Enable APAD calculation for other protocols
+			 * matching APAD0 and APAD1 lt def registers.
+			 */
+			rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_CST_APAD0,
+				    (ltdefs->rx_apad0.valid << 11) |
+				    (ltdefs->rx_apad0.lid << 8) |
+				    (ltdefs->rx_apad0.ltype_match << 4) |
+				    ltdefs->rx_apad0.ltype_mask);
+			rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_CST_APAD1,
+				    (ltdefs->rx_apad1.valid << 11) |
+				    (ltdefs->rx_apad1.lid << 8) |
+				    (ltdefs->rx_apad1.ltype_match << 4) |
+				    ltdefs->rx_apad1.ltype_mask);
+
+			/* Receive ethertype defination register defines layer
+			 * information in NPC_RESULT_S to identify the Ethertype
+			 * location in L2 header. Used for Ethertype overwriting
+			 * in inline IPsec flow.
+			 */
+			rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_ET(0),
+				    (ltdefs->rx_et[0].offset << 12) |
+				    (ltdefs->rx_et[0].valid << 11) |
+				    (ltdefs->rx_et[0].lid << 8) |
+				    (ltdefs->rx_et[0].ltype_match << 4) |
+				    ltdefs->rx_et[0].ltype_mask);
+			rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_ET(1),
+				    (ltdefs->rx_et[1].offset << 12) |
+				    (ltdefs->rx_et[1].valid << 11) |
+				    (ltdefs->rx_et[1].lid << 8) |
+				    (ltdefs->rx_et[1].ltype_match << 4) |
+				    ltdefs->rx_et[1].ltype_mask);
+		}
+
 		err = nix_rx_flowkey_alg_cfg(rvu, blkaddr);
 		if (err)
 			return err;
@@ -3584,6 +3800,8 @@ static void rvu_nix_block_freemem(struct rvu *rvu, int blkaddr,
 			kfree(txsch->schq.bmap);
 		}
 
+		nix_ipolicer_freemem(nix_hw);
+
 		vlan = &nix_hw->txvlan;
 		kfree(vlan->rsrc.bmap);
 		mutex_destroy(&vlan->rsrc_lock);
@@ -3614,6 +3832,7 @@ int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req,
 				     struct msg_rsp *rsp)
 {
 	u16 pcifunc = req->hdr.pcifunc;
+	struct rvu_pfvf *pfvf;
 	int nixlf, err;
 
 	err = nix_get_nixlf(rvu, pcifunc, &nixlf, NULL);
@@ -3624,6 +3843,9 @@ int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req,
 
 	npc_mcam_enable_flows(rvu, pcifunc);
 
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	set_bit(NIXLF_INITIALIZED, &pfvf->flags);
+
 	return rvu_cgx_start_stop_io(rvu, pcifunc, true);
 }
 
@@ -3631,6 +3853,7 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req,
 				    struct msg_rsp *rsp)
 {
 	u16 pcifunc = req->hdr.pcifunc;
+	struct rvu_pfvf *pfvf;
 	int nixlf, err;
 
 	err = nix_get_nixlf(rvu, pcifunc, &nixlf, NULL);
@@ -3639,6 +3862,9 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req,
 
 	rvu_npc_disable_mcam_entries(rvu, pcifunc, nixlf);
 
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	clear_bit(NIXLF_INITIALIZED, &pfvf->flags);
+
 	return rvu_cgx_start_stop_io(rvu, pcifunc, false);
 }
 
@@ -3657,6 +3883,8 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf)
 	nix_rx_sync(rvu, blkaddr);
 	nix_txschq_free(rvu, pcifunc);
 
+	clear_bit(NIXLF_INITIALIZED, &pfvf->flags);
+
 	rvu_cgx_start_stop_io(rvu, pcifunc, false);
 
 	if (pfvf->sq_ctx) {
@@ -3681,6 +3909,8 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf)
 	}
 
 	nix_ctx_free(rvu, pfvf);
+
+	nix_free_all_bandprof(rvu, pcifunc);
 }
 
 #define NIX_AF_LFX_TX_CFG_PTP_EN	BIT_ULL(32)
@@ -3789,3 +4019,586 @@ void rvu_nix_reset_mac(struct rvu_pfvf *pfvf, int pcifunc)
 	if (from_vf)
 		ether_addr_copy(pfvf->mac_addr, pfvf->default_mac);
 }
+
+/* NIX ingress policers or bandwidth profiles APIs */
+static void nix_config_rx_pkt_policer_precolor(struct rvu *rvu, int blkaddr)
+{
+	struct npc_lt_def_cfg defs, *ltdefs;
+
+	ltdefs = &defs;
+	memcpy(ltdefs, rvu->kpu.lt_def, sizeof(struct npc_lt_def_cfg));
+
+	/* Extract PCP and DEI fields from outer VLAN from byte offset
+	 * 2 from the start of LB_PTR (ie TAG).
+	 * VLAN0 is Outer VLAN and VLAN1 is Inner VLAN. Inner VLAN
+	 * fields are considered when 'Tunnel enable' is set in profile.
+	 */
+	rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_VLAN0_PCP_DEI,
+		    (2UL << 12) | (ltdefs->ovlan.lid << 8) |
+		    (ltdefs->ovlan.ltype_match << 4) |
+		    ltdefs->ovlan.ltype_mask);
+	rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_VLAN1_PCP_DEI,
+		    (2UL << 12) | (ltdefs->ivlan.lid << 8) |
+		    (ltdefs->ivlan.ltype_match << 4) |
+		    ltdefs->ivlan.ltype_mask);
+
+	/* DSCP field in outer and tunneled IPv4 packets */
+	rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OIP4_DSCP,
+		    (1UL << 12) | (ltdefs->rx_oip4.lid << 8) |
+		    (ltdefs->rx_oip4.ltype_match << 4) |
+		    ltdefs->rx_oip4.ltype_mask);
+	rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_IIP4_DSCP,
+		    (1UL << 12) | (ltdefs->rx_iip4.lid << 8) |
+		    (ltdefs->rx_iip4.ltype_match << 4) |
+		    ltdefs->rx_iip4.ltype_mask);
+
+	/* DSCP field (traffic class) in outer and tunneled IPv6 packets */
+	rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OIP6_DSCP,
+		    (1UL << 11) | (ltdefs->rx_oip6.lid << 8) |
+		    (ltdefs->rx_oip6.ltype_match << 4) |
+		    ltdefs->rx_oip6.ltype_mask);
+	rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_IIP6_DSCP,
+		    (1UL << 11) | (ltdefs->rx_iip6.lid << 8) |
+		    (ltdefs->rx_iip6.ltype_match << 4) |
+		    ltdefs->rx_iip6.ltype_mask);
+}
+
+static int nix_init_policer_context(struct rvu *rvu, struct nix_hw *nix_hw,
+				    int layer, int prof_idx)
+{
+	struct nix_cn10k_aq_enq_req aq_req;
+	int rc;
+
+	memset(&aq_req, 0, sizeof(struct nix_cn10k_aq_enq_req));
+
+	aq_req.qidx = (prof_idx & 0x3FFF) | (layer << 14);
+	aq_req.ctype = NIX_AQ_CTYPE_BANDPROF;
+	aq_req.op = NIX_AQ_INSTOP_INIT;
+
+	/* Context is all zeros, submit to AQ */
+	rc = rvu_nix_blk_aq_enq_inst(rvu, nix_hw,
+				     (struct nix_aq_enq_req *)&aq_req, NULL);
+	if (rc)
+		dev_err(rvu->dev, "Failed to INIT bandwidth profile layer %d profile %d\n",
+			layer, prof_idx);
+	return rc;
+}
+
+static int nix_setup_ipolicers(struct rvu *rvu,
+			       struct nix_hw *nix_hw, int blkaddr)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	struct nix_ipolicer *ipolicer;
+	int err, layer, prof_idx;
+	u64 cfg;
+
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST);
+	if (!(cfg & BIT_ULL(61))) {
+		hw->cap.ipolicer = false;
+		return 0;
+	}
+
+	hw->cap.ipolicer = true;
+	nix_hw->ipolicer = devm_kcalloc(rvu->dev, BAND_PROF_NUM_LAYERS,
+					sizeof(*ipolicer), GFP_KERNEL);
+	if (!nix_hw->ipolicer)
+		return -ENOMEM;
+
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_PL_CONST);
+
+	for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) {
+		ipolicer = &nix_hw->ipolicer[layer];
+		switch (layer) {
+		case BAND_PROF_LEAF_LAYER:
+			ipolicer->band_prof.max = cfg & 0XFFFF;
+			break;
+		case BAND_PROF_MID_LAYER:
+			ipolicer->band_prof.max = (cfg >> 16) & 0XFFFF;
+			break;
+		case BAND_PROF_TOP_LAYER:
+			ipolicer->band_prof.max = (cfg >> 32) & 0XFFFF;
+			break;
+		}
+
+		if (!ipolicer->band_prof.max)
+			continue;
+
+		err = rvu_alloc_bitmap(&ipolicer->band_prof);
+		if (err)
+			return err;
+
+		ipolicer->pfvf_map = devm_kcalloc(rvu->dev,
+						  ipolicer->band_prof.max,
+						  sizeof(u16), GFP_KERNEL);
+		if (!ipolicer->pfvf_map)
+			return -ENOMEM;
+
+		ipolicer->match_id = devm_kcalloc(rvu->dev,
+						  ipolicer->band_prof.max,
+						  sizeof(u16), GFP_KERNEL);
+		if (!ipolicer->match_id)
+			return -ENOMEM;
+
+		for (prof_idx = 0;
+		     prof_idx < ipolicer->band_prof.max; prof_idx++) {
+			/* Set AF as current owner for INIT ops to succeed */
+			ipolicer->pfvf_map[prof_idx] = 0x00;
+
+			/* There is no enable bit in the profile context,
+			 * so no context disable. So let's INIT them here
+			 * so that PF/VF later on have to just do WRITE to
+			 * setup policer rates and config.
+			 */
+			err = nix_init_policer_context(rvu, nix_hw,
+						       layer, prof_idx);
+			if (err)
+				return err;
+		}
+
+		/* Allocate memory for maintaining ref_counts for MID level
+		 * profiles, this will be needed for leaf layer profiles'
+		 * aggregation.
+		 */
+		if (layer != BAND_PROF_MID_LAYER)
+			continue;
+
+		ipolicer->ref_count = devm_kcalloc(rvu->dev,
+						   ipolicer->band_prof.max,
+						   sizeof(u16), GFP_KERNEL);
+	}
+
+	/* Set policer timeunit to 2us ie  (19 + 1) * 100 nsec = 2us */
+	rvu_write64(rvu, blkaddr, NIX_AF_PL_TS, 19);
+
+	nix_config_rx_pkt_policer_precolor(rvu, blkaddr);
+
+	return 0;
+}
+
+static void nix_ipolicer_freemem(struct nix_hw *nix_hw)
+{
+	struct nix_ipolicer *ipolicer;
+	int layer;
+
+	for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) {
+		ipolicer = &nix_hw->ipolicer[layer];
+
+		if (!ipolicer->band_prof.max)
+			continue;
+
+		kfree(ipolicer->band_prof.bmap);
+	}
+}
+
+static int nix_verify_bandprof(struct nix_cn10k_aq_enq_req *req,
+			       struct nix_hw *nix_hw, u16 pcifunc)
+{
+	struct nix_ipolicer *ipolicer;
+	int layer, hi_layer, prof_idx;
+
+	/* Bits [15:14] in profile index represent layer */
+	layer = (req->qidx >> 14) & 0x03;
+	prof_idx = req->qidx & 0x3FFF;
+
+	ipolicer = &nix_hw->ipolicer[layer];
+	if (prof_idx >= ipolicer->band_prof.max)
+		return -EINVAL;
+
+	/* Check if the profile is allocated to the requesting PCIFUNC or not
+	 * with the exception of AF. AF is allowed to read and update contexts.
+	 */
+	if (pcifunc && ipolicer->pfvf_map[prof_idx] != pcifunc)
+		return -EINVAL;
+
+	/* If this profile is linked to higher layer profile then check
+	 * if that profile is also allocated to the requesting PCIFUNC
+	 * or not.
+	 */
+	if (!req->prof.hl_en)
+		return 0;
+
+	/* Leaf layer profile can link only to mid layer and
+	 * mid layer to top layer.
+	 */
+	if (layer == BAND_PROF_LEAF_LAYER)
+		hi_layer = BAND_PROF_MID_LAYER;
+	else if (layer == BAND_PROF_MID_LAYER)
+		hi_layer = BAND_PROF_TOP_LAYER;
+	else
+		return -EINVAL;
+
+	ipolicer = &nix_hw->ipolicer[hi_layer];
+	prof_idx = req->prof.band_prof_id;
+	if (prof_idx >= ipolicer->band_prof.max ||
+	    ipolicer->pfvf_map[prof_idx] != pcifunc)
+		return -EINVAL;
+
+	return 0;
+}
+
+int rvu_mbox_handler_nix_bandprof_alloc(struct rvu *rvu,
+					struct nix_bandprof_alloc_req *req,
+					struct nix_bandprof_alloc_rsp *rsp)
+{
+	int blkaddr, layer, prof, idx, err;
+	u16 pcifunc = req->hdr.pcifunc;
+	struct nix_ipolicer *ipolicer;
+	struct nix_hw *nix_hw;
+
+	if (!rvu->hw->cap.ipolicer)
+		return NIX_AF_ERR_IPOLICER_NOTSUPP;
+
+	err = nix_get_struct_ptrs(rvu, pcifunc, &nix_hw, &blkaddr);
+	if (err)
+		return err;
+
+	mutex_lock(&rvu->rsrc_lock);
+	for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) {
+		if (layer == BAND_PROF_INVAL_LAYER)
+			continue;
+		if (!req->prof_count[layer])
+			continue;
+
+		ipolicer = &nix_hw->ipolicer[layer];
+		for (idx = 0; idx < req->prof_count[layer]; idx++) {
+			/* Allocate a max of 'MAX_BANDPROF_PER_PFFUNC' profiles */
+			if (idx == MAX_BANDPROF_PER_PFFUNC)
+				break;
+
+			prof = rvu_alloc_rsrc(&ipolicer->band_prof);
+			if (prof < 0)
+				break;
+			rsp->prof_count[layer]++;
+			rsp->prof_idx[layer][idx] = prof;
+			ipolicer->pfvf_map[prof] = pcifunc;
+		}
+	}
+	mutex_unlock(&rvu->rsrc_lock);
+	return 0;
+}
+
+static int nix_free_all_bandprof(struct rvu *rvu, u16 pcifunc)
+{
+	int blkaddr, layer, prof_idx, err;
+	struct nix_ipolicer *ipolicer;
+	struct nix_hw *nix_hw;
+
+	if (!rvu->hw->cap.ipolicer)
+		return NIX_AF_ERR_IPOLICER_NOTSUPP;
+
+	err = nix_get_struct_ptrs(rvu, pcifunc, &nix_hw, &blkaddr);
+	if (err)
+		return err;
+
+	mutex_lock(&rvu->rsrc_lock);
+	/* Free all the profiles allocated to the PCIFUNC */
+	for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) {
+		if (layer == BAND_PROF_INVAL_LAYER)
+			continue;
+		ipolicer = &nix_hw->ipolicer[layer];
+
+		for (prof_idx = 0; prof_idx < ipolicer->band_prof.max; prof_idx++) {
+			if (ipolicer->pfvf_map[prof_idx] != pcifunc)
+				continue;
+
+			/* Clear ratelimit aggregation, if any */
+			if (layer == BAND_PROF_LEAF_LAYER &&
+			    ipolicer->match_id[prof_idx])
+				nix_clear_ratelimit_aggr(rvu, nix_hw, prof_idx);
+
+			ipolicer->pfvf_map[prof_idx] = 0x00;
+			ipolicer->match_id[prof_idx] = 0;
+			rvu_free_rsrc(&ipolicer->band_prof, prof_idx);
+		}
+	}
+	mutex_unlock(&rvu->rsrc_lock);
+	return 0;
+}
+
+int rvu_mbox_handler_nix_bandprof_free(struct rvu *rvu,
+				       struct nix_bandprof_free_req *req,
+				       struct msg_rsp *rsp)
+{
+	int blkaddr, layer, prof_idx, idx, err;
+	u16 pcifunc = req->hdr.pcifunc;
+	struct nix_ipolicer *ipolicer;
+	struct nix_hw *nix_hw;
+
+	if (req->free_all)
+		return nix_free_all_bandprof(rvu, pcifunc);
+
+	if (!rvu->hw->cap.ipolicer)
+		return NIX_AF_ERR_IPOLICER_NOTSUPP;
+
+	err = nix_get_struct_ptrs(rvu, pcifunc, &nix_hw, &blkaddr);
+	if (err)
+		return err;
+
+	mutex_lock(&rvu->rsrc_lock);
+	/* Free the requested profile indices */
+	for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) {
+		if (layer == BAND_PROF_INVAL_LAYER)
+			continue;
+		if (!req->prof_count[layer])
+			continue;
+
+		ipolicer = &nix_hw->ipolicer[layer];
+		for (idx = 0; idx < req->prof_count[layer]; idx++) {
+			prof_idx = req->prof_idx[layer][idx];
+			if (prof_idx >= ipolicer->band_prof.max ||
+			    ipolicer->pfvf_map[prof_idx] != pcifunc)
+				continue;
+
+			/* Clear ratelimit aggregation, if any */
+			if (layer == BAND_PROF_LEAF_LAYER &&
+			    ipolicer->match_id[prof_idx])
+				nix_clear_ratelimit_aggr(rvu, nix_hw, prof_idx);
+
+			ipolicer->pfvf_map[prof_idx] = 0x00;
+			ipolicer->match_id[prof_idx] = 0;
+			rvu_free_rsrc(&ipolicer->band_prof, prof_idx);
+			if (idx == MAX_BANDPROF_PER_PFFUNC)
+				break;
+		}
+	}
+	mutex_unlock(&rvu->rsrc_lock);
+	return 0;
+}
+
+int nix_aq_context_read(struct rvu *rvu, struct nix_hw *nix_hw,
+			struct nix_cn10k_aq_enq_req *aq_req,
+			struct nix_cn10k_aq_enq_rsp *aq_rsp,
+			u16 pcifunc, u8 ctype, u32 qidx)
+{
+	memset(aq_req, 0, sizeof(struct nix_cn10k_aq_enq_req));
+	aq_req->hdr.pcifunc = pcifunc;
+	aq_req->ctype = ctype;
+	aq_req->op = NIX_AQ_INSTOP_READ;
+	aq_req->qidx = qidx;
+
+	return rvu_nix_blk_aq_enq_inst(rvu, nix_hw,
+				       (struct nix_aq_enq_req *)aq_req,
+				       (struct nix_aq_enq_rsp *)aq_rsp);
+}
+
+static int nix_ipolicer_map_leaf_midprofs(struct rvu *rvu,
+					  struct nix_hw *nix_hw,
+					  struct nix_cn10k_aq_enq_req *aq_req,
+					  struct nix_cn10k_aq_enq_rsp *aq_rsp,
+					  u32 leaf_prof, u16 mid_prof)
+{
+	memset(aq_req, 0, sizeof(struct nix_cn10k_aq_enq_req));
+	aq_req->hdr.pcifunc = 0x00;
+	aq_req->ctype = NIX_AQ_CTYPE_BANDPROF;
+	aq_req->op = NIX_AQ_INSTOP_WRITE;
+	aq_req->qidx = leaf_prof;
+
+	aq_req->prof.band_prof_id = mid_prof;
+	aq_req->prof_mask.band_prof_id = GENMASK(6, 0);
+	aq_req->prof.hl_en = 1;
+	aq_req->prof_mask.hl_en = 1;
+
+	return rvu_nix_blk_aq_enq_inst(rvu, nix_hw,
+				       (struct nix_aq_enq_req *)aq_req,
+				       (struct nix_aq_enq_rsp *)aq_rsp);
+}
+
+int rvu_nix_setup_ratelimit_aggr(struct rvu *rvu, u16 pcifunc,
+				 u16 rq_idx, u16 match_id)
+{
+	int leaf_prof, mid_prof, leaf_match;
+	struct nix_cn10k_aq_enq_req aq_req;
+	struct nix_cn10k_aq_enq_rsp aq_rsp;
+	struct nix_ipolicer *ipolicer;
+	struct nix_hw *nix_hw;
+	int blkaddr, idx, rc;
+
+	if (!rvu->hw->cap.ipolicer)
+		return 0;
+
+	rc = nix_get_struct_ptrs(rvu, pcifunc, &nix_hw, &blkaddr);
+	if (rc)
+		return rc;
+
+	/* Fetch the RQ's context to see if policing is enabled */
+	rc = nix_aq_context_read(rvu, nix_hw, &aq_req, &aq_rsp, pcifunc,
+				 NIX_AQ_CTYPE_RQ, rq_idx);
+	if (rc) {
+		dev_err(rvu->dev,
+			"%s: Failed to fetch RQ%d context of PFFUNC 0x%x\n",
+			__func__, rq_idx, pcifunc);
+		return rc;
+	}
+
+	if (!aq_rsp.rq.policer_ena)
+		return 0;
+
+	/* Get the bandwidth profile ID mapped to this RQ */
+	leaf_prof = aq_rsp.rq.band_prof_id;
+
+	ipolicer = &nix_hw->ipolicer[BAND_PROF_LEAF_LAYER];
+	ipolicer->match_id[leaf_prof] = match_id;
+
+	/* Check if any other leaf profile is marked with same match_id */
+	for (idx = 0; idx < ipolicer->band_prof.max; idx++) {
+		if (idx == leaf_prof)
+			continue;
+		if (ipolicer->match_id[idx] != match_id)
+			continue;
+
+		leaf_match = idx;
+		break;
+	}
+
+	if (idx == ipolicer->band_prof.max)
+		return 0;
+
+	/* Fetch the matching profile's context to check if it's already
+	 * mapped to a mid level profile.
+	 */
+	rc = nix_aq_context_read(rvu, nix_hw, &aq_req, &aq_rsp, 0x00,
+				 NIX_AQ_CTYPE_BANDPROF, leaf_match);
+	if (rc) {
+		dev_err(rvu->dev,
+			"%s: Failed to fetch context of leaf profile %d\n",
+			__func__, leaf_match);
+		return rc;
+	}
+
+	ipolicer = &nix_hw->ipolicer[BAND_PROF_MID_LAYER];
+	if (aq_rsp.prof.hl_en) {
+		/* Get Mid layer prof index and map leaf_prof index
+		 * also such that flows that are being steered
+		 * to different RQs and marked with same match_id
+		 * are rate limited in a aggregate fashion
+		 */
+		mid_prof = aq_rsp.prof.band_prof_id;
+		rc = nix_ipolicer_map_leaf_midprofs(rvu, nix_hw,
+						    &aq_req, &aq_rsp,
+						    leaf_prof, mid_prof);
+		if (rc) {
+			dev_err(rvu->dev,
+				"%s: Failed to map leaf(%d) and mid(%d) profiles\n",
+				__func__, leaf_prof, mid_prof);
+			goto exit;
+		}
+
+		mutex_lock(&rvu->rsrc_lock);
+		ipolicer->ref_count[mid_prof]++;
+		mutex_unlock(&rvu->rsrc_lock);
+		goto exit;
+	}
+
+	/* Allocate a mid layer profile and
+	 * map both 'leaf_prof' and 'leaf_match' profiles to it.
+	 */
+	mutex_lock(&rvu->rsrc_lock);
+	mid_prof = rvu_alloc_rsrc(&ipolicer->band_prof);
+	if (mid_prof < 0) {
+		dev_err(rvu->dev,
+			"%s: Unable to allocate mid layer profile\n", __func__);
+		mutex_unlock(&rvu->rsrc_lock);
+		goto exit;
+	}
+	mutex_unlock(&rvu->rsrc_lock);
+	ipolicer->pfvf_map[mid_prof] = 0x00;
+	ipolicer->ref_count[mid_prof] = 0;
+
+	/* Initialize mid layer profile same as 'leaf_prof' */
+	rc = nix_aq_context_read(rvu, nix_hw, &aq_req, &aq_rsp, 0x00,
+				 NIX_AQ_CTYPE_BANDPROF, leaf_prof);
+	if (rc) {
+		dev_err(rvu->dev,
+			"%s: Failed to fetch context of leaf profile %d\n",
+			__func__, leaf_prof);
+		goto exit;
+	}
+
+	memset(&aq_req, 0, sizeof(struct nix_cn10k_aq_enq_req));
+	aq_req.hdr.pcifunc = 0x00;
+	aq_req.qidx = (mid_prof & 0x3FFF) | (BAND_PROF_MID_LAYER << 14);
+	aq_req.ctype = NIX_AQ_CTYPE_BANDPROF;
+	aq_req.op = NIX_AQ_INSTOP_WRITE;
+	memcpy(&aq_req.prof, &aq_rsp.prof, sizeof(struct nix_bandprof_s));
+	/* Clear higher layer enable bit in the mid profile, just in case */
+	aq_req.prof.hl_en = 0;
+	aq_req.prof_mask.hl_en = 1;
+
+	rc = rvu_nix_blk_aq_enq_inst(rvu, nix_hw,
+				     (struct nix_aq_enq_req *)&aq_req, NULL);
+	if (rc) {
+		dev_err(rvu->dev,
+			"%s: Failed to INIT context of mid layer profile %d\n",
+			__func__, mid_prof);
+		goto exit;
+	}
+
+	/* Map both leaf profiles to this mid layer profile */
+	rc = nix_ipolicer_map_leaf_midprofs(rvu, nix_hw,
+					    &aq_req, &aq_rsp,
+					    leaf_prof, mid_prof);
+	if (rc) {
+		dev_err(rvu->dev,
+			"%s: Failed to map leaf(%d) and mid(%d) profiles\n",
+			__func__, leaf_prof, mid_prof);
+		goto exit;
+	}
+
+	mutex_lock(&rvu->rsrc_lock);
+	ipolicer->ref_count[mid_prof]++;
+	mutex_unlock(&rvu->rsrc_lock);
+
+	rc = nix_ipolicer_map_leaf_midprofs(rvu, nix_hw,
+					    &aq_req, &aq_rsp,
+					    leaf_match, mid_prof);
+	if (rc) {
+		dev_err(rvu->dev,
+			"%s: Failed to map leaf(%d) and mid(%d) profiles\n",
+			__func__, leaf_match, mid_prof);
+		ipolicer->ref_count[mid_prof]--;
+		goto exit;
+	}
+
+	mutex_lock(&rvu->rsrc_lock);
+	ipolicer->ref_count[mid_prof]++;
+	mutex_unlock(&rvu->rsrc_lock);
+
+exit:
+	return rc;
+}
+
+/* Called with mutex rsrc_lock */
+static void nix_clear_ratelimit_aggr(struct rvu *rvu, struct nix_hw *nix_hw,
+				     u32 leaf_prof)
+{
+	struct nix_cn10k_aq_enq_req aq_req;
+	struct nix_cn10k_aq_enq_rsp aq_rsp;
+	struct nix_ipolicer *ipolicer;
+	u16 mid_prof;
+	int rc;
+
+	mutex_unlock(&rvu->rsrc_lock);
+
+	rc = nix_aq_context_read(rvu, nix_hw, &aq_req, &aq_rsp, 0x00,
+				 NIX_AQ_CTYPE_BANDPROF, leaf_prof);
+
+	mutex_lock(&rvu->rsrc_lock);
+	if (rc) {
+		dev_err(rvu->dev,
+			"%s: Failed to fetch context of leaf profile %d\n",
+			__func__, leaf_prof);
+		return;
+	}
+
+	if (!aq_rsp.prof.hl_en)
+		return;
+
+	mid_prof = aq_rsp.prof.band_prof_id;
+	ipolicer = &nix_hw->ipolicer[BAND_PROF_MID_LAYER];
+	ipolicer->ref_count[mid_prof]--;
+	/* If ref_count is zero, free mid layer profile */
+	if (!ipolicer->ref_count[mid_prof]) {
+		ipolicer->pfvf_map[mid_prof] = 0x00;
+		rvu_free_rsrc(&ipolicer->band_prof, mid_prof);
+	}
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 0bc4529691ec..3612e0a2cab3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -19,7 +19,7 @@
 #include "cgx.h"
 #include "npc_profile.h"
 
-#define RSVD_MCAM_ENTRIES_PER_PF	2 /* Bcast & Promisc */
+#define RSVD_MCAM_ENTRIES_PER_PF	3 /* Broadcast, Promisc and AllMulticast */
 #define RSVD_MCAM_ENTRIES_PER_NIXLF	1 /* Ucast for LFs */
 
 #define NPC_PARSE_RESULT_DMAC_OFFSET	8
@@ -27,6 +27,8 @@
 #define NPC_KEX_CHAN_MASK		0xFFFULL
 #define NPC_KEX_PF_FUNC_MASK		0xFFFFULL
 
+#define ALIGN_8B_CEIL(__a)	(((__a) + 7) & (-8))
+
 static const char def_pfl_name[] = "default";
 
 static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam,
@@ -212,8 +214,10 @@ int npc_get_nixlf_mcam_index(struct npc_mcam *mcam,
 		 */
 		if (type == NIXLF_BCAST_ENTRY)
 			return index;
-		else if (type == NIXLF_PROMISC_ENTRY)
+		else if (type == NIXLF_ALLMULTI_ENTRY)
 			return index + 1;
+		else if (type == NIXLF_PROMISC_ENTRY)
+			return index + 2;
 	}
 
 	return npc_get_ucast_mcam_index(mcam, pcifunc, nixlf);
@@ -411,37 +415,49 @@ static void npc_fill_entryword(struct mcam_entry *entry, int idx,
 	}
 }
 
-static void npc_get_default_entry_action(struct rvu *rvu, struct npc_mcam *mcam,
-					 int blkaddr, int index,
-					 struct mcam_entry *entry)
+static u64 npc_get_default_entry_action(struct rvu *rvu, struct npc_mcam *mcam,
+					int blkaddr, u16 pf_func)
+{
+	int bank, nixlf, index;
+
+	/* get ucast entry rule entry index */
+	nix_get_nixlf(rvu, pf_func, &nixlf, NULL);
+	index = npc_get_nixlf_mcam_index(mcam, pf_func, nixlf,
+					 NIXLF_UCAST_ENTRY);
+	bank = npc_get_bank(mcam, index);
+	index &= (mcam->banksize - 1);
+
+	return rvu_read64(rvu, blkaddr,
+			  NPC_AF_MCAMEX_BANKX_ACTION(index, bank));
+}
+
+static void npc_fixup_vf_rule(struct rvu *rvu, struct npc_mcam *mcam,
+			      int blkaddr, int index, struct mcam_entry *entry,
+			      bool *enable)
 {
 	u16 owner, target_func;
 	struct rvu_pfvf *pfvf;
-	int bank, nixlf;
 	u64 rx_action;
 
 	owner = mcam->entry2pfvf_map[index];
 	target_func = (entry->action >> 4) & 0xffff;
-	/* return incase target is PF or LBK or rule owner is not PF */
+	/* do nothing when target is LBK/PF or owner is not PF */
 	if (is_afvf(target_func) || (owner & RVU_PFVF_FUNC_MASK) ||
 	    !(target_func & RVU_PFVF_FUNC_MASK))
 		return;
 
+	/* save entry2target_pffunc */
 	pfvf = rvu_get_pfvf(rvu, target_func);
 	mcam->entry2target_pffunc[index] = target_func;
-	/* return if nixlf is not attached or initialized */
-	if (!is_nixlf_attached(rvu, target_func) || !pfvf->def_ucast_rule)
-		return;
 
-	/* get VF ucast entry rule */
-	nix_get_nixlf(rvu, target_func, &nixlf, NULL);
-	index = npc_get_nixlf_mcam_index(mcam, target_func,
-					 nixlf, NIXLF_UCAST_ENTRY);
-	bank = npc_get_bank(mcam, index);
-	index &= (mcam->banksize - 1);
+	/* don't enable rule when nixlf not attached or initialized */
+	if (!(is_nixlf_attached(rvu, target_func) &&
+	      test_bit(NIXLF_INITIALIZED, &pfvf->flags)))
+		*enable = false;
 
-	rx_action = rvu_read64(rvu, blkaddr,
-			       NPC_AF_MCAMEX_BANKX_ACTION(index, bank));
+	/* copy VF default entry action to the VF mcam entry */
+	rx_action = npc_get_default_entry_action(rvu, mcam, blkaddr,
+						 target_func);
 	if (rx_action)
 		entry->action = rx_action;
 }
@@ -493,10 +509,9 @@ static void npc_config_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
 			    NPC_AF_MCAMEX_BANKX_CAMX_W1(index, bank, 0), cam0);
 	}
 
-	/* copy VF default entry action to the VF mcam entry */
+	/* PF installing VF rule */
 	if (intf == NIX_INTF_RX && actindex < mcam->bmap_entries)
-		npc_get_default_entry_action(rvu, mcam, blkaddr, actindex,
-					     entry);
+		npc_fixup_vf_rule(rvu, mcam, blkaddr, index, entry, &enable);
 
 	/* Set 'action' */
 	rvu_write64(rvu, blkaddr,
@@ -647,30 +662,32 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc,
 }
 
 void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
-				   int nixlf, u64 chan, u8 chan_cnt,
-				   bool allmulti)
+				   int nixlf, u64 chan, u8 chan_cnt)
 {
 	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
 	struct npc_install_flow_req req = { 0 };
 	struct npc_install_flow_rsp rsp = { 0 };
 	struct npc_mcam *mcam = &rvu->hw->mcam;
+	struct rvu_hwinfo *hw = rvu->hw;
 	int blkaddr, ucast_idx, index;
-	u8 mac_addr[ETH_ALEN] = { 0 };
 	struct nix_rx_action action;
 	u64 relaxed_mask;
 
-	/* Only PF or AF VF can add a promiscuous entry */
-	if ((pcifunc & RVU_PFVF_FUNC_MASK) && !is_afvf(pcifunc))
+	if (!hw->cap.nix_rx_multicast && is_cgx_vf(rvu, pcifunc))
 		return;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
 	if (blkaddr < 0)
 		return;
 
-	*(u64 *)&action = 0x00;
 	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
 					 nixlf, NIXLF_PROMISC_ENTRY);
 
+	if (is_cgx_vf(rvu, pcifunc))
+		index = npc_get_nixlf_mcam_index(mcam,
+						 pcifunc & ~RVU_PFVF_FUNC_MASK,
+						 nixlf, NIXLF_PROMISC_ENTRY);
+
 	/* If the corresponding PF's ucast action is RSS,
 	 * use the same action for promisc also
 	 */
@@ -678,19 +695,20 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 					     nixlf, NIXLF_UCAST_ENTRY);
 	if (is_mcam_entry_enabled(rvu, mcam, blkaddr, ucast_idx))
 		*(u64 *)&action = npc_get_mcam_action(rvu, mcam,
-							blkaddr, ucast_idx);
+						      blkaddr, ucast_idx);
 
 	if (action.op != NIX_RX_ACTIONOP_RSS) {
 		*(u64 *)&action = 0x00;
 		action.op = NIX_RX_ACTIONOP_UCAST;
-		action.pf_func = pcifunc;
 	}
 
-	if (allmulti) {
-		mac_addr[0] = 0x01;	/* LSB bit of 1st byte in DMAC */
-		ether_addr_copy(req.packet.dmac, mac_addr);
-		ether_addr_copy(req.mask.dmac, mac_addr);
-		req.features = BIT_ULL(NPC_DMAC);
+	/* RX_ACTION set to MCAST for CGX PF's */
+	if (hw->cap.nix_rx_multicast && pfvf->use_mce_list &&
+	    is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) {
+		*(u64 *)&action = 0x00;
+		action.op = NIX_RX_ACTIONOP_MCAST;
+		pfvf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK);
+		action.index = pfvf->promisc_mce_idx;
 	}
 
 	req.chan_mask = 0xFFFU;
@@ -718,8 +736,8 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 	rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
 }
 
-static void npc_enadis_promisc_entry(struct rvu *rvu, u16 pcifunc,
-				     int nixlf, bool enable)
+void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc,
+				  int nixlf, bool enable)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	int blkaddr, index;
@@ -728,25 +746,14 @@ static void npc_enadis_promisc_entry(struct rvu *rvu, u16 pcifunc,
 	if (blkaddr < 0)
 		return;
 
-	/* Only PF's have a promiscuous entry */
-	if (pcifunc & RVU_PFVF_FUNC_MASK)
-		return;
+	/* Get 'pcifunc' of PF device */
+	pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK;
 
 	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
 					 nixlf, NIXLF_PROMISC_ENTRY);
 	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
 }
 
-void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf)
-{
-	npc_enadis_promisc_entry(rvu, pcifunc, nixlf, false);
-}
-
-void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf)
-{
-	npc_enadis_promisc_entry(rvu, pcifunc, nixlf, true);
-}
-
 void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 				       int nixlf, u64 chan)
 {
@@ -756,8 +763,6 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	struct rvu_hwinfo *hw = rvu->hw;
 	int blkaddr, index;
-	u32 req_index = 0;
-	u8 op;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
 	if (blkaddr < 0)
@@ -770,7 +775,7 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 	/* If pkt replication is not supported,
 	 * then only PF is allowed to add a bcast match entry.
 	 */
-	if (!hw->cap.nix_rx_multicast && pcifunc & RVU_PFVF_FUNC_MASK)
+	if (!hw->cap.nix_rx_multicast && is_vf(pcifunc))
 		return;
 
 	/* Get 'pcifunc' of PF device */
@@ -784,10 +789,10 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 		 * so install entry with UCAST action, so that PF
 		 * receives all broadcast packets.
 		 */
-		op = NIX_RX_ACTIONOP_UCAST;
+		req.op = NIX_RX_ACTIONOP_UCAST;
 	} else {
-		op = NIX_RX_ACTIONOP_MCAST;
-		req_index = pfvf->bcast_mce_idx;
+		req.op = NIX_RX_ACTIONOP_MCAST;
+		req.index = pfvf->bcast_mce_idx;
 	}
 
 	eth_broadcast_addr((u8 *)&req.packet.dmac);
@@ -796,15 +801,14 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 	req.channel = chan;
 	req.intf = pfvf->nix_rx_intf;
 	req.entry = index;
-	req.op = op;
 	req.hdr.pcifunc = 0; /* AF is requester */
 	req.vf = pcifunc;
-	req.index = req_index;
 
 	rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
 }
 
-void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable)
+void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
+				bool enable)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	int blkaddr, index;
@@ -816,7 +820,104 @@ void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable)
 	/* Get 'pcifunc' of PF device */
 	pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK;
 
-	index = npc_get_nixlf_mcam_index(mcam, pcifunc, 0, NIXLF_BCAST_ENTRY);
+	index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf,
+					 NIXLF_BCAST_ENTRY);
+	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
+}
+
+void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
+				    u64 chan)
+{
+	struct npc_install_flow_req req = { 0 };
+	struct npc_install_flow_rsp rsp = { 0 };
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	struct rvu_hwinfo *hw = rvu->hw;
+	int blkaddr, ucast_idx, index;
+	u8 mac_addr[ETH_ALEN] = { 0 };
+	struct nix_rx_action action;
+	struct rvu_pfvf *pfvf;
+	u16 vf_func;
+
+	/* Only CGX PF/VF can add allmulticast entry */
+	if (is_afvf(pcifunc))
+		return;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return;
+
+	/* Get 'pcifunc' of PF device */
+	vf_func = pcifunc & RVU_PFVF_FUNC_MASK;
+	pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK;
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+					 nixlf, NIXLF_ALLMULTI_ENTRY);
+
+	/* If the corresponding PF's ucast action is RSS,
+	 * use the same action for multicast entry also
+	 */
+	ucast_idx = npc_get_nixlf_mcam_index(mcam, pcifunc,
+					     nixlf, NIXLF_UCAST_ENTRY);
+	if (is_mcam_entry_enabled(rvu, mcam, blkaddr, ucast_idx))
+		*(u64 *)&action = npc_get_mcam_action(rvu, mcam,
+							blkaddr, ucast_idx);
+
+	if (action.op != NIX_RX_ACTIONOP_RSS) {
+		*(u64 *)&action = 0x00;
+		action.op = NIX_RX_ACTIONOP_UCAST;
+		action.pf_func = pcifunc;
+	}
+
+	/* RX_ACTION set to MCAST for CGX PF's */
+	if (hw->cap.nix_rx_multicast && pfvf->use_mce_list) {
+		*(u64 *)&action = 0x00;
+		action.op = NIX_RX_ACTIONOP_MCAST;
+		action.index = pfvf->mcast_mce_idx;
+	}
+
+	mac_addr[0] = 0x01;	/* LSB bit of 1st byte in DMAC */
+	ether_addr_copy(req.packet.dmac, mac_addr);
+	ether_addr_copy(req.mask.dmac, mac_addr);
+	req.features = BIT_ULL(NPC_DMAC);
+
+	/* For cn10k the upper two bits of the channel number are
+	 * cpt channel number. with masking out these bits in the
+	 * mcam entry, same entry used for NIX will allow packets
+	 * received from cpt for parsing.
+	 */
+	if (!is_rvu_otx2(rvu))
+		req.chan_mask = NIX_CHAN_CPT_X2P_MASK;
+	else
+		req.chan_mask = 0xFFFU;
+
+	req.channel = chan;
+	req.intf = pfvf->nix_rx_intf;
+	req.entry = index;
+	req.op = action.op;
+	req.hdr.pcifunc = 0; /* AF is requester */
+	req.vf = pcifunc | vf_func;
+	req.index = action.index;
+	req.match_id = action.match_id;
+	req.flow_key_alg = action.flow_key_alg;
+
+	rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
+}
+
+void rvu_npc_enable_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
+				   bool enable)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	int blkaddr, index;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return;
+
+	/* Get 'pcifunc' of PF device */
+	pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK;
+
+	index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf,
+					 NIXLF_ALLMULTI_ENTRY);
 	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
 }
 
@@ -858,6 +959,7 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 				    int group, int alg_idx, int mcam_index)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
+	struct rvu_hwinfo *hw = rvu->hw;
 	struct nix_rx_action action;
 	int blkaddr, index, bank;
 	struct rvu_pfvf *pfvf;
@@ -913,7 +1015,8 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 	/* If PF's promiscuous entry is enabled,
 	 * Set RSS action for that entry as well
 	 */
-	if (is_mcam_entry_enabled(rvu, mcam, blkaddr, index)) {
+	if ((!hw->cap.nix_rx_multicast || !pfvf->use_mce_list) &&
+	    is_mcam_entry_enabled(rvu, mcam, blkaddr, index)) {
 		bank = npc_get_bank(mcam, index);
 		index &= (mcam->banksize - 1);
 
@@ -923,12 +1026,47 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 	}
 }
 
+void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc,
+				  int nixlf, int type, bool enable)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	struct rvu_hwinfo *hw = rvu->hw;
+	struct nix_mce_list *mce_list;
+	int index, blkaddr, mce_idx;
+	struct rvu_pfvf *pfvf;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return;
+
+	index = npc_get_nixlf_mcam_index(mcam, pcifunc & ~RVU_PFVF_FUNC_MASK,
+					 nixlf, type);
+
+	/* disable MCAM entry when packet replication is not supported by hw */
+	if (!hw->cap.nix_rx_multicast && !is_vf(pcifunc)) {
+		npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
+		return;
+	}
+
+	/* return incase mce list is not enabled */
+	pfvf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK);
+	if (hw->cap.nix_rx_multicast && is_vf(pcifunc) &&
+	    type != NIXLF_BCAST_ENTRY && !pfvf->use_mce_list)
+		return;
+
+	nix_get_mce_list(rvu, pcifunc, type, &mce_list, &mce_idx);
+
+	nix_update_mce_list(rvu, pcifunc, mce_list,
+			    mce_idx, index, enable);
+	if (enable)
+		npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
+}
+
 static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
 				       int nixlf, bool enable)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
-	struct nix_rx_action action;
-	int index, bank, blkaddr;
+	int index, blkaddr;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
 	if (blkaddr < 0)
@@ -939,48 +1077,33 @@ static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
 					 nixlf, NIXLF_UCAST_ENTRY);
 	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
 
-	/* For PF, ena/dis promisc and bcast MCAM match entries.
-	 * For VFs add/delete from bcast list when RX multicast
-	 * feature is present.
+	/* Nothing to do for VFs, on platforms where pkt replication
+	 * is not supported
 	 */
-	if (pcifunc & RVU_PFVF_FUNC_MASK && !rvu->hw->cap.nix_rx_multicast)
+	if ((pcifunc & RVU_PFVF_FUNC_MASK) && !rvu->hw->cap.nix_rx_multicast)
 		return;
 
-	/* For bcast, enable/disable only if it's action is not
-	 * packet replication, incase if action is replication
-	 * then this PF/VF's nixlf is removed from bcast replication
-	 * list.
-	 */
-	index = npc_get_nixlf_mcam_index(mcam, pcifunc & ~RVU_PFVF_FUNC_MASK,
-					 nixlf, NIXLF_BCAST_ENTRY);
-	bank = npc_get_bank(mcam, index);
-	*(u64 *)&action = rvu_read64(rvu, blkaddr,
-	     NPC_AF_MCAMEX_BANKX_ACTION(index & (mcam->banksize - 1), bank));
-
-	/* VFs will not have BCAST entry */
-	if (action.op != NIX_RX_ACTIONOP_MCAST &&
-	    !(pcifunc & RVU_PFVF_FUNC_MASK)) {
-		npc_enable_mcam_entry(rvu, mcam,
-				      blkaddr, index, enable);
-	} else {
-		nix_update_bcast_mce_list(rvu, pcifunc, enable);
-		/* Enable PF's BCAST entry for packet replication */
-		rvu_npc_enable_bcast_entry(rvu, pcifunc, enable);
-	}
-
-	if (enable)
-		rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf);
-	else
-		rvu_npc_disable_promisc_entry(rvu, pcifunc, nixlf);
+	/* add/delete pf_func to broadcast MCE list */
+	npc_enadis_default_mce_entry(rvu, pcifunc, nixlf,
+				     NIXLF_BCAST_ENTRY, enable);
 }
 
 void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
 {
 	npc_enadis_default_entries(rvu, pcifunc, nixlf, false);
+
+	/* Delete multicast and promisc MCAM entries */
+	npc_enadis_default_mce_entry(rvu, pcifunc, nixlf,
+				     NIXLF_ALLMULTI_ENTRY, false);
+	npc_enadis_default_mce_entry(rvu, pcifunc, nixlf,
+				     NIXLF_PROMISC_ENTRY, false);
 }
 
 void rvu_npc_enable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
 {
+	/* Enables only broadcast match entry. Promisc/Allmulti are enabled
+	 * in set_rx_mode mbox handler.
+	 */
 	npc_enadis_default_entries(rvu, pcifunc, nixlf, true);
 }
 
@@ -1000,7 +1123,8 @@ void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
 	/* Disable MCAM entries directing traffic to this 'pcifunc' */
 	list_for_each_entry_safe(rule, tmp, &mcam->mcam_rules, list) {
 		if (is_npc_intf_rx(rule->intf) &&
-		    rule->rx_action.pf_func == pcifunc) {
+		    rule->rx_action.pf_func == pcifunc &&
+		    rule->rx_action.op != NIX_RX_ACTIONOP_MCAST) {
 			npc_enable_mcam_entry(rvu, mcam, blkaddr,
 					      rule->entry, false);
 			rule->enable = false;
@@ -1134,6 +1258,30 @@ static void npc_program_mkex_profile(struct rvu *rvu, int blkaddr,
 	}
 }
 
+static int npc_fwdb_prfl_img_map(struct rvu *rvu, void __iomem **prfl_img_addr,
+				 u64 *size)
+{
+	u64 prfl_addr, prfl_sz;
+
+	if (!rvu->fwdata)
+		return -EINVAL;
+
+	prfl_addr = rvu->fwdata->mcam_addr;
+	prfl_sz = rvu->fwdata->mcam_sz;
+
+	if (!prfl_addr || !prfl_sz)
+		return -EINVAL;
+
+	*prfl_img_addr = ioremap_wc(prfl_addr, prfl_sz);
+	if (!(*prfl_img_addr))
+		return -ENOMEM;
+
+	*size = prfl_sz;
+
+	return 0;
+}
+
+/* strtoull of "mkexprof" with base:36 */
 #define MKEX_END_SIGN  0xdeadbeef
 
 static void npc_load_mkex_profile(struct rvu *rvu, int blkaddr,
@@ -1141,26 +1289,21 @@ static void npc_load_mkex_profile(struct rvu *rvu, int blkaddr,
 {
 	struct device *dev = &rvu->pdev->dev;
 	struct npc_mcam_kex *mcam_kex;
-	void *mkex_prfl_addr = NULL;
-	u64 prfl_addr, prfl_sz;
+	void __iomem *mkex_prfl_addr = NULL;
+	u64 prfl_sz;
+	int ret;
 
 	/* If user not selected mkex profile */
-	if (!strncmp(mkex_profile, def_pfl_name, MKEX_NAME_LEN))
-		goto program_mkex;
-
-	if (!rvu->fwdata)
-		goto program_mkex;
-	prfl_addr = rvu->fwdata->mcam_addr;
-	prfl_sz = rvu->fwdata->mcam_sz;
-
-	if (!prfl_addr || !prfl_sz)
+	if (rvu->kpu_fwdata_sz ||
+	    !strncmp(mkex_profile, def_pfl_name, MKEX_NAME_LEN))
 		goto program_mkex;
 
-	mkex_prfl_addr = memremap(prfl_addr, prfl_sz, MEMREMAP_WC);
-	if (!mkex_prfl_addr)
+	/* Setting up the mapping for mkex profile image */
+	ret = npc_fwdb_prfl_img_map(rvu, &mkex_prfl_addr, &prfl_sz);
+	if (ret < 0)
 		goto program_mkex;
 
-	mcam_kex = (struct npc_mcam_kex *)mkex_prfl_addr;
+	mcam_kex = (struct npc_mcam_kex __force *)mkex_prfl_addr;
 
 	while (((s64)prfl_sz > 0) && (mcam_kex->mkex_sign != MKEX_END_SIGN)) {
 		/* Compare with mkex mod_param name string */
@@ -1186,7 +1329,7 @@ program_mkex:
 	/* Program selected mkex profile */
 	npc_program_mkex_profile(rvu, blkaddr, rvu->kpu.mkex);
 	if (mkex_prfl_addr)
-		memunmap(mkex_prfl_addr);
+		iounmap(mkex_prfl_addr);
 }
 
 static void npc_config_kpuaction(struct rvu *rvu, int blkaddr,
@@ -1263,6 +1406,7 @@ static void npc_program_kpu_profile(struct rvu *rvu, int blkaddr, int kpu,
 				    const struct npc_kpu_profile *profile)
 {
 	int entry, num_entries, max_entries;
+	u64 entry_mask;
 
 	if (profile->cam_entries != profile->action_entries) {
 		dev_err(rvu->dev,
@@ -1286,8 +1430,12 @@ static void npc_program_kpu_profile(struct rvu *rvu, int blkaddr, int kpu,
 
 	/* Enable all programmed entries */
 	num_entries = min_t(int, profile->action_entries, profile->cam_entries);
+	entry_mask = enable_mask(num_entries);
+	/* Disable first KPU_MAX_CST_ENT entries for built-in profile */
+	if (!rvu->kpu.custom)
+		entry_mask |= GENMASK_ULL(KPU_MAX_CST_ENT - 1, 0);
 	rvu_write64(rvu, blkaddr,
-		    NPC_AF_KPUX_ENTRY_DISX(kpu, 0), enable_mask(num_entries));
+		    NPC_AF_KPUX_ENTRY_DISX(kpu, 0), entry_mask);
 	if (num_entries > 64) {
 		rvu_write64(rvu, blkaddr,
 			    NPC_AF_KPUX_ENTRY_DISX(kpu, 1),
@@ -1300,6 +1448,7 @@ static void npc_program_kpu_profile(struct rvu *rvu, int blkaddr, int kpu,
 
 static int npc_prepare_default_kpu(struct npc_kpu_profile_adapter *profile)
 {
+	profile->custom = 0;
 	profile->name = def_pfl_name;
 	profile->version = NPC_KPU_PROFILE_VER;
 	profile->ikpu = ikpu_action_entries;
@@ -1312,10 +1461,245 @@ static int npc_prepare_default_kpu(struct npc_kpu_profile_adapter *profile)
 	return 0;
 }
 
+static int npc_apply_custom_kpu(struct rvu *rvu,
+				struct npc_kpu_profile_adapter *profile)
+{
+	size_t hdr_sz = sizeof(struct npc_kpu_profile_fwdata), offset = 0;
+	struct npc_kpu_profile_fwdata *fw = rvu->kpu_fwdata;
+	struct npc_kpu_profile_action *action;
+	struct npc_kpu_profile_cam *cam;
+	struct npc_kpu_fwdata *fw_kpu;
+	int entries;
+	u16 kpu, entry;
+
+	if (rvu->kpu_fwdata_sz < hdr_sz) {
+		dev_warn(rvu->dev, "Invalid KPU profile size\n");
+		return -EINVAL;
+	}
+	if (le64_to_cpu(fw->signature) != KPU_SIGN) {
+		dev_warn(rvu->dev, "Invalid KPU profile signature %llx\n",
+			 fw->signature);
+		return -EINVAL;
+	}
+	/* Verify if the using known profile structure */
+	if (NPC_KPU_VER_MAJ(profile->version) >
+	    NPC_KPU_VER_MAJ(NPC_KPU_PROFILE_VER)) {
+		dev_warn(rvu->dev, "Not supported Major version: %d > %d\n",
+			 NPC_KPU_VER_MAJ(profile->version),
+			 NPC_KPU_VER_MAJ(NPC_KPU_PROFILE_VER));
+		return -EINVAL;
+	}
+	/* Verify if profile is aligned with the required kernel changes */
+	if (NPC_KPU_VER_MIN(profile->version) <
+	    NPC_KPU_VER_MIN(NPC_KPU_PROFILE_VER)) {
+		dev_warn(rvu->dev,
+			 "Invalid KPU profile version: %d.%d.%d expected version <= %d.%d.%d\n",
+			 NPC_KPU_VER_MAJ(profile->version),
+			 NPC_KPU_VER_MIN(profile->version),
+			 NPC_KPU_VER_PATCH(profile->version),
+			 NPC_KPU_VER_MAJ(NPC_KPU_PROFILE_VER),
+			 NPC_KPU_VER_MIN(NPC_KPU_PROFILE_VER),
+			 NPC_KPU_VER_PATCH(NPC_KPU_PROFILE_VER));
+		return -EINVAL;
+	}
+	/* Verify if profile fits the HW */
+	if (fw->kpus > profile->kpus) {
+		dev_warn(rvu->dev, "Not enough KPUs: %d > %ld\n", fw->kpus,
+			 profile->kpus);
+		return -EINVAL;
+	}
+
+	profile->custom = 1;
+	profile->name = fw->name;
+	profile->version = le64_to_cpu(fw->version);
+	profile->mkex = &fw->mkex;
+	profile->lt_def = &fw->lt_def;
+
+	for (kpu = 0; kpu < fw->kpus; kpu++) {
+		fw_kpu = (struct npc_kpu_fwdata *)(fw->data + offset);
+		if (fw_kpu->entries > KPU_MAX_CST_ENT)
+			dev_warn(rvu->dev,
+				 "Too many custom entries on KPU%d: %d > %d\n",
+				 kpu, fw_kpu->entries, KPU_MAX_CST_ENT);
+		entries = min(fw_kpu->entries, KPU_MAX_CST_ENT);
+		cam = (struct npc_kpu_profile_cam *)fw_kpu->data;
+		offset += sizeof(*fw_kpu) + fw_kpu->entries * sizeof(*cam);
+		action = (struct npc_kpu_profile_action *)(fw->data + offset);
+		offset += fw_kpu->entries * sizeof(*action);
+		if (rvu->kpu_fwdata_sz < hdr_sz + offset) {
+			dev_warn(rvu->dev,
+				 "Profile size mismatch on KPU%i parsing.\n",
+				 kpu + 1);
+			return -EINVAL;
+		}
+		for (entry = 0; entry < entries; entry++) {
+			profile->kpu[kpu].cam[entry] = cam[entry];
+			profile->kpu[kpu].action[entry] = action[entry];
+		}
+	}
+
+	return 0;
+}
+
+static int npc_load_kpu_prfl_img(struct rvu *rvu, void __iomem *prfl_addr,
+				 u64 prfl_sz, const char *kpu_profile)
+{
+	struct npc_kpu_profile_fwdata *kpu_data = NULL;
+	int rc = -EINVAL;
+
+	kpu_data = (struct npc_kpu_profile_fwdata __force *)prfl_addr;
+	if (le64_to_cpu(kpu_data->signature) == KPU_SIGN &&
+	    !strncmp(kpu_data->name, kpu_profile, KPU_NAME_LEN)) {
+		dev_info(rvu->dev, "Loading KPU profile from firmware db: %s\n",
+			 kpu_profile);
+		rvu->kpu_fwdata = kpu_data;
+		rvu->kpu_fwdata_sz = prfl_sz;
+		rvu->kpu_prfl_addr = prfl_addr;
+		rc = 0;
+	}
+
+	return rc;
+}
+
+static int npc_fwdb_detect_load_prfl_img(struct rvu *rvu, uint64_t prfl_sz,
+					 const char *kpu_profile)
+{
+	struct npc_coalesced_kpu_prfl *img_data = NULL;
+	int i = 0, rc = -EINVAL;
+	void __iomem *kpu_prfl_addr;
+	u16 offset;
+
+	img_data = (struct npc_coalesced_kpu_prfl __force *)rvu->kpu_prfl_addr;
+	if (le64_to_cpu(img_data->signature) == KPU_SIGN &&
+	    !strncmp(img_data->name, kpu_profile, KPU_NAME_LEN)) {
+		/* Loaded profile is a single KPU profile. */
+		rc = npc_load_kpu_prfl_img(rvu, rvu->kpu_prfl_addr,
+					   prfl_sz, kpu_profile);
+		goto done;
+	}
+
+	/* Loaded profile is coalesced image, offset of first KPU profile.*/
+	offset = offsetof(struct npc_coalesced_kpu_prfl, prfl_sz) +
+		(img_data->num_prfl * sizeof(uint16_t));
+	/* Check if mapped image is coalesced image. */
+	while (i < img_data->num_prfl) {
+		/* Profile image offsets are rounded up to next 8 multiple.*/
+		offset = ALIGN_8B_CEIL(offset);
+		kpu_prfl_addr = (void __iomem *)((uintptr_t)rvu->kpu_prfl_addr +
+					 offset);
+		rc = npc_load_kpu_prfl_img(rvu, kpu_prfl_addr,
+					   img_data->prfl_sz[i], kpu_profile);
+		if (!rc)
+			break;
+		/* Calculating offset of profile image based on profile size.*/
+		offset += img_data->prfl_sz[i];
+		i++;
+	}
+done:
+	return rc;
+}
+
+static int npc_load_kpu_profile_fwdb(struct rvu *rvu, const char *kpu_profile)
+{
+	int ret = -EINVAL;
+	u64 prfl_sz;
+
+	/* Setting up the mapping for NPC profile image */
+	ret = npc_fwdb_prfl_img_map(rvu, &rvu->kpu_prfl_addr, &prfl_sz);
+	if (ret < 0)
+		goto done;
+
+	/* Detect if profile is coalesced or single KPU profile and load */
+	ret = npc_fwdb_detect_load_prfl_img(rvu, prfl_sz, kpu_profile);
+	if (ret == 0)
+		goto done;
+
+	/* Cleaning up if KPU profile image from fwdata is not valid. */
+	if (rvu->kpu_prfl_addr) {
+		iounmap(rvu->kpu_prfl_addr);
+		rvu->kpu_prfl_addr = NULL;
+		rvu->kpu_fwdata_sz = 0;
+		rvu->kpu_fwdata = NULL;
+	}
+
+done:
+	return ret;
+}
+
 static void npc_load_kpu_profile(struct rvu *rvu)
 {
 	struct npc_kpu_profile_adapter *profile = &rvu->kpu;
+	const char *kpu_profile = rvu->kpu_pfl_name;
+	const struct firmware *fw = NULL;
+	bool retry_fwdb = false;
+
+	/* If user not specified profile customization */
+	if (!strncmp(kpu_profile, def_pfl_name, KPU_NAME_LEN))
+		goto revert_to_default;
+	/* First prepare default KPU, then we'll customize top entries. */
+	npc_prepare_default_kpu(profile);
 
+	/* Order of preceedence for load loading NPC profile (high to low)
+	 * Firmware binary in filesystem.
+	 * Firmware database method.
+	 * Default KPU profile.
+	 */
+	if (!request_firmware(&fw, kpu_profile, rvu->dev)) {
+		dev_info(rvu->dev, "Loading KPU profile from firmware: %s\n",
+			 kpu_profile);
+		rvu->kpu_fwdata = kzalloc(fw->size, GFP_KERNEL);
+		if (rvu->kpu_fwdata) {
+			memcpy(rvu->kpu_fwdata, fw->data, fw->size);
+			rvu->kpu_fwdata_sz = fw->size;
+		}
+		release_firmware(fw);
+		retry_fwdb = true;
+		goto program_kpu;
+	}
+
+load_image_fwdb:
+	/* Loading the KPU profile using firmware database */
+	if (npc_load_kpu_profile_fwdb(rvu, kpu_profile))
+		goto revert_to_default;
+
+program_kpu:
+	/* Apply profile customization if firmware was loaded. */
+	if (!rvu->kpu_fwdata_sz || npc_apply_custom_kpu(rvu, profile)) {
+		/* If image from firmware filesystem fails to load or invalid
+		 * retry with firmware database method.
+		 */
+		if (rvu->kpu_fwdata || rvu->kpu_fwdata_sz) {
+			/* Loading image from firmware database failed. */
+			if (rvu->kpu_prfl_addr) {
+				iounmap(rvu->kpu_prfl_addr);
+				rvu->kpu_prfl_addr = NULL;
+			} else {
+				kfree(rvu->kpu_fwdata);
+			}
+			rvu->kpu_fwdata = NULL;
+			rvu->kpu_fwdata_sz = 0;
+			if (retry_fwdb) {
+				retry_fwdb = false;
+				goto load_image_fwdb;
+			}
+		}
+
+		dev_warn(rvu->dev,
+			 "Can't load KPU profile %s. Using default.\n",
+			 kpu_profile);
+		kfree(rvu->kpu_fwdata);
+		rvu->kpu_fwdata = NULL;
+		goto revert_to_default;
+	}
+
+	dev_info(rvu->dev, "Using custom profile '%s', version %d.%d.%d\n",
+		 profile->name, NPC_KPU_VER_MAJ(profile->version),
+		 NPC_KPU_VER_MIN(profile->version),
+		 NPC_KPU_VER_PATCH(profile->version));
+
+	return;
+
+revert_to_default:
 	npc_prepare_default_kpu(profile);
 }
 
@@ -1654,6 +2038,10 @@ void rvu_npc_freemem(struct rvu *rvu)
 
 	kfree(pkind->rsrc.bmap);
 	kfree(mcam->counters.bmap);
+	if (rvu->kpu_prfl_addr)
+		iounmap(rvu->kpu_prfl_addr);
+	else
+		kfree(rvu->kpu_fwdata);
 	mutex_destroy(&mcam->lock);
 }
 
@@ -2149,8 +2537,11 @@ int rvu_mbox_handler_npc_mcam_alloc_entry(struct rvu *rvu,
 	rsp->free_count = 0;
 
 	/* Check if ref_entry is within range */
-	if (req->priority && req->ref_entry >= mcam->bmap_entries)
+	if (req->priority && req->ref_entry >= mcam->bmap_entries) {
+		dev_err(rvu->dev, "%s: reference entry %d is out of range\n",
+			__func__, req->ref_entry);
 		return NPC_MCAM_INVALID_REQ;
+	}
 
 	/* ref_entry can't be '0' if requested priority is high.
 	 * Can't be last entry if requested priority is low.
@@ -2163,8 +2554,12 @@ int rvu_mbox_handler_npc_mcam_alloc_entry(struct rvu *rvu,
 	/* Since list of allocated indices needs to be sent to requester,
 	 * max number of non-contiguous entries per mbox msg is limited.
 	 */
-	if (!req->contig && req->count > NPC_MAX_NONCONTIG_ENTRIES)
+	if (!req->contig && req->count > NPC_MAX_NONCONTIG_ENTRIES) {
+		dev_err(rvu->dev,
+			"%s: %d Non-contiguous MCAM entries requested is more than max (%d) allowed\n",
+			__func__, req->count, NPC_MAX_NONCONTIG_ENTRIES);
 		return NPC_MCAM_INVALID_REQ;
+	}
 
 	/* Alloc request from PFFUNC with no NIXLF attached should be denied */
 	if (!is_nixlf_attached(rvu, pcifunc))
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
index 7f35b62eea13..68633145a8b8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
@@ -123,11 +123,8 @@ static bool npc_is_field_present(struct rvu *rvu, enum key_fields type, u8 intf)
 static bool npc_is_same(struct npc_key_field *input,
 			struct npc_key_field *field)
 {
-	int ret;
-
-	ret = memcmp(&input->layer_mdata, &field->layer_mdata,
-		     sizeof(struct npc_layer_mdata));
-	return ret == 0;
+	return memcmp(&input->layer_mdata, &field->layer_mdata,
+		     sizeof(struct npc_layer_mdata)) == 0;
 }
 
 static void npc_set_layer_mdata(struct npc_mcam *mcam, enum key_fields type,
@@ -1103,11 +1100,18 @@ find_rule:
 	if (pf_set_vfs_mac) {
 		ether_addr_copy(pfvf->default_mac, req->packet.dmac);
 		ether_addr_copy(pfvf->mac_addr, req->packet.dmac);
+		set_bit(PF_SET_VF_MAC, &pfvf->flags);
 	}
 
-	if (pfvf->pf_set_vf_cfg && req->vtag0_type == NIX_AF_LFX_RX_VTAG_TYPE7)
+	if (test_bit(PF_SET_VF_CFG, &pfvf->flags) &&
+	    req->vtag0_type == NIX_AF_LFX_RX_VTAG_TYPE7)
 		rule->vfvlan_cfg = true;
 
+	if (is_npc_intf_rx(req->intf) && req->match_id &&
+	    (req->op == NIX_RX_ACTIONOP_UCAST || req->op == NIX_RX_ACTIONOP_RSS))
+		return rvu_nix_setup_ratelimit_aggr(rvu, req->hdr.pcifunc,
+					     req->index, req->match_id);
+
 	return 0;
 }
 
@@ -1167,7 +1171,7 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu,
 
 	/* PF installing for its VF */
 	if (req->hdr.pcifunc && !from_vf && req->vf)
-		pfvf->pf_set_vf_cfg = 1;
+		set_bit(PF_SET_VF_CFG, &pfvf->flags);
 
 	/* update req destination mac addr */
 	if ((req->features & BIT_ULL(NPC_DMAC)) && is_npc_intf_rx(req->intf) &&
@@ -1177,9 +1181,12 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu,
 	}
 
 	err = nix_get_nixlf(rvu, target, &nixlf, NULL);
+	if (err && is_npc_intf_rx(req->intf) && !pf_set_vfs_mac)
+		return -EINVAL;
 
-	/* If interface is uninitialized then do not enable entry */
-	if (err || (!req->default_rule && !pfvf->def_ucast_rule))
+	/* don't enable rule when nixlf not attached or initialized */
+	if (!(is_nixlf_attached(rvu, target) &&
+	      test_bit(NIXLF_INITIALIZED, &pfvf->flags)))
 		enable = false;
 
 	/* Packets reaching NPC in Tx path implies that a
@@ -1193,6 +1200,14 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu,
 	if (from_vf && !enable)
 		return -EINVAL;
 
+	/* PF sets VF mac & VF NIXLF is not attached, update the mac addr */
+	if (pf_set_vfs_mac && !enable) {
+		ether_addr_copy(pfvf->default_mac, req->packet.dmac);
+		ether_addr_copy(pfvf->mac_addr, req->packet.dmac);
+		set_bit(PF_SET_VF_MAC, &pfvf->flags);
+		return 0;
+	}
+
 	/* If message is from VF then its flow should not overlap with
 	 * reserved unicast flow.
 	 */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
index ac71c0f2f960..76837d5e19c6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
@@ -171,6 +171,7 @@
 #define NIX_AF_SQ_CONST			(0x0040)
 #define NIX_AF_CQ_CONST			(0x0048)
 #define NIX_AF_RQ_CONST			(0x0050)
+#define NIX_AF_PL_CONST			(0x0058)
 #define NIX_AF_PSE_CONST		(0x0060)
 #define NIX_AF_TL1_CONST		(0x0070)
 #define NIX_AF_TL2_CONST		(0x0078)
@@ -181,6 +182,7 @@
 #define NIX_AF_LSO_CFG			(0x00A8)
 #define NIX_AF_BLK_RST			(0x00B0)
 #define NIX_AF_TX_TSTMP_CFG		(0x00C0)
+#define NIX_AF_PL_TS			(0x00C8)
 #define NIX_AF_RX_CFG			(0x00D0)
 #define NIX_AF_AVG_DELAY		(0x00E0)
 #define NIX_AF_CINT_DELAY		(0x00F0)
@@ -208,19 +210,27 @@
 #define NIX_AF_RVU_INT_ENA_W1S		(0x01D0)
 #define NIX_AF_RVU_INT_ENA_W1C		(0x01D8)
 #define NIX_AF_TCP_TIMER		(0x01E0)
-#define NIX_AF_RX_WQE_TAG_CTL		(0x01F0)
+#define NIX_AF_RX_DEF_ET(a)		(0x01F0ull | (uint64_t)(a) << 3)
 #define NIX_AF_RX_DEF_OL2		(0x0200)
 #define NIX_AF_RX_DEF_OIP4		(0x0210)
 #define NIX_AF_RX_DEF_IIP4		(0x0220)
+#define NIX_AF_RX_DEF_VLAN0_PCP_DEI	(0x0228)
 #define NIX_AF_RX_DEF_OIP6		(0x0230)
+#define NIX_AF_RX_DEF_VLAN1_PCP_DEI	(0x0238)
 #define NIX_AF_RX_DEF_IIP6		(0x0240)
 #define NIX_AF_RX_DEF_OTCP		(0x0250)
 #define NIX_AF_RX_DEF_ITCP		(0x0260)
 #define NIX_AF_RX_DEF_OUDP		(0x0270)
 #define NIX_AF_RX_DEF_IUDP		(0x0280)
 #define NIX_AF_RX_DEF_OSCTP		(0x0290)
+#define NIX_AF_RX_DEF_CST_APAD0		(0x0298)
 #define NIX_AF_RX_DEF_ISCTP		(0x02A0)
 #define NIX_AF_RX_DEF_IPSECX		(0x02B0)
+#define NIX_AF_RX_DEF_CST_APAD1		(0x02A8)
+#define NIX_AF_RX_DEF_IIP4_DSCP		(0x02E0)
+#define NIX_AF_RX_DEF_OIP4_DSCP		(0x02E8)
+#define NIX_AF_RX_DEF_IIP6_DSCP		(0x02F0)
+#define NIX_AF_RX_DEF_OIP6_DSCP		(0x02F8)
 #define NIX_AF_RX_IPSEC_GEN_CFG		(0x0300)
 #define NIX_AF_RX_CPTX_INST_ADDR	(0x0310)
 #define NIX_AF_NDC_TX_SYNC		(0x03F0)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
index 5e5f45c7eab0..14aa8e37ea41 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
@@ -286,7 +286,7 @@ enum nix_aq_ctype {
 	NIX_AQ_CTYPE_MCE  = 0x3,
 	NIX_AQ_CTYPE_RSS  = 0x4,
 	NIX_AQ_CTYPE_DYNO = 0x5,
-	NIX_AQ_CTYPE_BAND_PROF = 0x6,
+	NIX_AQ_CTYPE_BANDPROF = 0x6,
 };
 
 /* NIX admin queue instruction opcodes */
@@ -665,6 +665,89 @@ struct nix_rx_mce_s {
 	uint64_t next       : 16;
 };
 
+enum nix_band_prof_layers {
+	BAND_PROF_LEAF_LAYER = 0,
+	BAND_PROF_INVAL_LAYER = 1,
+	BAND_PROF_MID_LAYER = 2,
+	BAND_PROF_TOP_LAYER = 3,
+	BAND_PROF_NUM_LAYERS = 4,
+};
+
+enum NIX_RX_BAND_PROF_ACTIONRESULT_E {
+	NIX_RX_BAND_PROF_ACTIONRESULT_PASS = 0x0,
+	NIX_RX_BAND_PROF_ACTIONRESULT_DROP = 0x1,
+	NIX_RX_BAND_PROF_ACTIONRESULT_RED = 0x2,
+};
+
+enum nix_band_prof_pc_mode {
+	NIX_RX_PC_MODE_VLAN = 0,
+	NIX_RX_PC_MODE_DSCP = 1,
+	NIX_RX_PC_MODE_GEN = 2,
+	NIX_RX_PC_MODE_RSVD = 3,
+};
+
+/* NIX ingress policer bandwidth profile structure */
+struct nix_bandprof_s {
+	uint64_t pc_mode                     :  2; /* W0 */
+	uint64_t icolor                      :  2;
+	uint64_t tnl_ena                     :  1;
+	uint64_t reserved_5_7                :  3;
+	uint64_t peir_exponent               :  5;
+	uint64_t reserved_13_15              :  3;
+	uint64_t pebs_exponent               :  5;
+	uint64_t reserved_21_23              :  3;
+	uint64_t cir_exponent                :  5;
+	uint64_t reserved_29_31              :  3;
+	uint64_t cbs_exponent                :  5;
+	uint64_t reserved_37_39              :  3;
+	uint64_t peir_mantissa               :  8;
+	uint64_t pebs_mantissa               :  8;
+	uint64_t cir_mantissa                :  8;
+	uint64_t cbs_mantissa                :  8; /* W1 */
+	uint64_t lmode                       :  1;
+	uint64_t l_sellect                   :  3;
+	uint64_t rdiv                        :  4;
+	uint64_t adjust_exponent             :  5;
+	uint64_t reserved_85_86              :  2;
+	uint64_t adjust_mantissa             :  9;
+	uint64_t gc_action                   :  2;
+	uint64_t yc_action                   :  2;
+	uint64_t rc_action                   :  2;
+	uint64_t meter_algo                  :  2;
+	uint64_t band_prof_id                :  7;
+	uint64_t reserved_111_118            :  8;
+	uint64_t hl_en                       :  1;
+	uint64_t reserved_120_127            :  8;
+	uint64_t ts                          : 48; /* W2 */
+	uint64_t reserved_176_191            : 16;
+	uint64_t pe_accum                    : 32; /* W3 */
+	uint64_t c_accum                     : 32;
+	uint64_t green_pkt_pass              : 48; /* W4 */
+	uint64_t reserved_304_319            : 16;
+	uint64_t yellow_pkt_pass             : 48; /* W5 */
+	uint64_t reserved_368_383            : 16;
+	uint64_t red_pkt_pass                : 48; /* W6 */
+	uint64_t reserved_432_447            : 16;
+	uint64_t green_octs_pass             : 48; /* W7 */
+	uint64_t reserved_496_511            : 16;
+	uint64_t yellow_octs_pass            : 48; /* W8 */
+	uint64_t reserved_560_575            : 16;
+	uint64_t red_octs_pass               : 48; /* W9 */
+	uint64_t reserved_624_639            : 16;
+	uint64_t green_pkt_drop              : 48; /* W10 */
+	uint64_t reserved_688_703            : 16;
+	uint64_t yellow_pkt_drop             : 48; /* W11 */
+	uint64_t reserved_752_767            : 16;
+	uint64_t red_pkt_drop                : 48; /* W12 */
+	uint64_t reserved_816_831            : 16;
+	uint64_t green_octs_drop             : 48; /* W13 */
+	uint64_t reserved_880_895            : 16;
+	uint64_t yellow_octs_drop            : 48; /* W14 */
+	uint64_t reserved_944_959            : 16;
+	uint64_t red_octs_drop               : 48; /* W15 */
+	uint64_t reserved_1008_1023          : 16;
+};
+
 enum nix_lsoalg {
 	NIX_LSOALG_NOP,
 	NIX_LSOALG_ADD_SEGNUM,
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
index 9ec0313f13fc..1b08896b46d2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
@@ -179,3 +179,326 @@ void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx)
 	sq->head++;
 	sq->head &= (sq->sqe_cnt - 1);
 }
+
+int cn10k_free_all_ipolicers(struct otx2_nic *pfvf)
+{
+	struct nix_bandprof_free_req *req;
+	int rc;
+
+	if (is_dev_otx2(pfvf->pdev))
+		return 0;
+
+	mutex_lock(&pfvf->mbox.lock);
+
+	req = otx2_mbox_alloc_msg_nix_bandprof_free(&pfvf->mbox);
+	if (!req) {
+		rc =  -ENOMEM;
+		goto out;
+	}
+
+	/* Free all bandwidth profiles allocated */
+	req->free_all = true;
+
+	rc = otx2_sync_mbox_msg(&pfvf->mbox);
+out:
+	mutex_unlock(&pfvf->mbox.lock);
+	return rc;
+}
+
+int cn10k_alloc_leaf_profile(struct otx2_nic *pfvf, u16 *leaf)
+{
+	struct nix_bandprof_alloc_req *req;
+	struct nix_bandprof_alloc_rsp *rsp;
+	int rc;
+
+	req = otx2_mbox_alloc_msg_nix_bandprof_alloc(&pfvf->mbox);
+	if (!req)
+		return  -ENOMEM;
+
+	req->prof_count[BAND_PROF_LEAF_LAYER] = 1;
+
+	rc = otx2_sync_mbox_msg(&pfvf->mbox);
+	if (rc)
+		goto out;
+
+	rsp = (struct  nix_bandprof_alloc_rsp *)
+	       otx2_mbox_get_rsp(&pfvf->mbox.mbox, 0, &req->hdr);
+	if (!rsp->prof_count[BAND_PROF_LEAF_LAYER]) {
+		rc = -EIO;
+		goto out;
+	}
+
+	*leaf = rsp->prof_idx[BAND_PROF_LEAF_LAYER][0];
+out:
+	if (rc) {
+		dev_warn(pfvf->dev,
+			 "Failed to allocate ingress bandwidth policer\n");
+	}
+
+	return rc;
+}
+
+int cn10k_alloc_matchall_ipolicer(struct otx2_nic *pfvf)
+{
+	struct otx2_hw *hw = &pfvf->hw;
+	int ret;
+
+	mutex_lock(&pfvf->mbox.lock);
+
+	ret = cn10k_alloc_leaf_profile(pfvf, &hw->matchall_ipolicer);
+
+	mutex_unlock(&pfvf->mbox.lock);
+
+	return ret;
+}
+
+#define POLICER_TIMESTAMP	  1  /* 1 second */
+#define MAX_RATE_EXP		  22 /* Valid rate exponent range: 0 - 22 */
+
+static void cn10k_get_ingress_burst_cfg(u32 burst, u32 *burst_exp,
+					u32 *burst_mantissa)
+{
+	int tmp;
+
+	/* Burst is calculated as
+	 * (1+[BURST_MANTISSA]/256)*2^[BURST_EXPONENT]
+	 * This is the upper limit on number tokens (bytes) that
+	 * can be accumulated in the bucket.
+	 */
+	*burst_exp = ilog2(burst);
+	if (burst < 256) {
+		/* No float: can't express mantissa in this case */
+		*burst_mantissa = 0;
+		return;
+	}
+
+	if (*burst_exp > MAX_RATE_EXP)
+		*burst_exp = MAX_RATE_EXP;
+
+	/* Calculate mantissa
+	 * Find remaining bytes 'burst - 2^burst_exp'
+	 * mantissa = (remaining bytes) / 2^ (burst_exp - 8)
+	 */
+	tmp = burst - rounddown_pow_of_two(burst);
+	*burst_mantissa = tmp / (1UL << (*burst_exp - 8));
+}
+
+static void cn10k_get_ingress_rate_cfg(u64 rate, u32 *rate_exp,
+				       u32 *rate_mantissa, u32 *rdiv)
+{
+	u32 div = 0;
+	u32 exp = 0;
+	u64 tmp;
+
+	/* Figure out mantissa, exponent and divider from given max pkt rate
+	 *
+	 * To achieve desired rate HW adds
+	 * (1+[RATE_MANTISSA]/256)*2^[RATE_EXPONENT] tokens (bytes) at every
+	 * policer timeunit * 2^rdiv ie 2 * 2^rdiv usecs, to the token bucket.
+	 * Here policer timeunit is 2 usecs and rate is in bits per sec.
+	 * Since floating point cannot be used below algorithm uses 1000000
+	 * scale factor to support rates upto 100Gbps.
+	 */
+	tmp = rate * 32 * 2;
+	if (tmp < 256000000) {
+		while (tmp < 256000000) {
+			tmp = tmp * 2;
+			div++;
+		}
+	} else {
+		for (exp = 0; tmp >= 512000000 && exp <= MAX_RATE_EXP; exp++)
+			tmp = tmp / 2;
+
+		if (exp > MAX_RATE_EXP)
+			exp = MAX_RATE_EXP;
+	}
+
+	*rate_mantissa = (tmp - 256000000) / 1000000;
+	*rate_exp = exp;
+	*rdiv = div;
+}
+
+int cn10k_map_unmap_rq_policer(struct otx2_nic *pfvf, int rq_idx,
+			       u16 policer, bool map)
+{
+	struct nix_cn10k_aq_enq_req *aq;
+
+	aq = otx2_mbox_alloc_msg_nix_cn10k_aq_enq(&pfvf->mbox);
+	if (!aq)
+		return -ENOMEM;
+
+	/* Enable policing and set the bandwidth profile (policer) index */
+	if (map)
+		aq->rq.policer_ena = 1;
+	else
+		aq->rq.policer_ena = 0;
+	aq->rq_mask.policer_ena = 1;
+
+	aq->rq.band_prof_id = policer;
+	aq->rq_mask.band_prof_id = GENMASK(9, 0);
+
+	/* Fill AQ info */
+	aq->qidx = rq_idx;
+	aq->ctype = NIX_AQ_CTYPE_RQ;
+	aq->op = NIX_AQ_INSTOP_WRITE;
+
+	return otx2_sync_mbox_msg(&pfvf->mbox);
+}
+
+int cn10k_free_leaf_profile(struct otx2_nic *pfvf, u16 leaf)
+{
+	struct nix_bandprof_free_req *req;
+
+	req = otx2_mbox_alloc_msg_nix_bandprof_free(&pfvf->mbox);
+	if (!req)
+		return -ENOMEM;
+
+	req->prof_count[BAND_PROF_LEAF_LAYER] = 1;
+	req->prof_idx[BAND_PROF_LEAF_LAYER][0] = leaf;
+
+	return otx2_sync_mbox_msg(&pfvf->mbox);
+}
+
+int cn10k_free_matchall_ipolicer(struct otx2_nic *pfvf)
+{
+	struct otx2_hw *hw = &pfvf->hw;
+	int qidx, rc;
+
+	mutex_lock(&pfvf->mbox.lock);
+
+	/* Remove RQ's policer mapping */
+	for (qidx = 0; qidx < hw->rx_queues; qidx++)
+		cn10k_map_unmap_rq_policer(pfvf, qidx,
+					   hw->matchall_ipolicer, false);
+
+	rc = cn10k_free_leaf_profile(pfvf, hw->matchall_ipolicer);
+
+	mutex_unlock(&pfvf->mbox.lock);
+	return rc;
+}
+
+int cn10k_set_ipolicer_rate(struct otx2_nic *pfvf, u16 profile,
+			    u32 burst, u64 rate, bool pps)
+{
+	struct nix_cn10k_aq_enq_req *aq;
+	u32 burst_exp, burst_mantissa;
+	u32 rate_exp, rate_mantissa;
+	u32 rdiv;
+
+	/* Get exponent and mantissa values for the desired rate */
+	cn10k_get_ingress_burst_cfg(burst, &burst_exp, &burst_mantissa);
+	cn10k_get_ingress_rate_cfg(rate, &rate_exp, &rate_mantissa, &rdiv);
+
+	/* Init bandwidth profile */
+	aq = otx2_mbox_alloc_msg_nix_cn10k_aq_enq(&pfvf->mbox);
+	if (!aq)
+		return -ENOMEM;
+
+	/* Set initial color mode to blind */
+	aq->prof.icolor = 0x03;
+	aq->prof_mask.icolor = 0x03;
+
+	/* Set rate and burst values */
+	aq->prof.cir_exponent = rate_exp;
+	aq->prof_mask.cir_exponent = 0x1F;
+
+	aq->prof.cir_mantissa = rate_mantissa;
+	aq->prof_mask.cir_mantissa = 0xFF;
+
+	aq->prof.cbs_exponent = burst_exp;
+	aq->prof_mask.cbs_exponent = 0x1F;
+
+	aq->prof.cbs_mantissa = burst_mantissa;
+	aq->prof_mask.cbs_mantissa = 0xFF;
+
+	aq->prof.rdiv = rdiv;
+	aq->prof_mask.rdiv = 0xF;
+
+	if (pps) {
+		/* The amount of decremented tokens is calculated according to
+		 * the following equation:
+		 * max([ LMODE ? 0 : (packet_length - LXPTR)] +
+		 *	     ([ADJUST_MANTISSA]/256 - 1) * 2^[ADJUST_EXPONENT],
+		 *	1/256)
+		 * if LMODE is 1 then rate limiting will be based on
+		 * PPS otherwise bps.
+		 * The aim of the ADJUST value is to specify a token cost per
+		 * packet in contrary to the packet length that specifies a
+		 * cost per byte. To rate limit based on PPS adjust mantissa
+		 * is set as 384 and exponent as 1 so that number of tokens
+		 * decremented becomes 1 i.e, 1 token per packeet.
+		 */
+		aq->prof.adjust_exponent = 1;
+		aq->prof_mask.adjust_exponent = 0x1F;
+
+		aq->prof.adjust_mantissa = 384;
+		aq->prof_mask.adjust_mantissa = 0x1FF;
+
+		aq->prof.lmode = 0x1;
+		aq->prof_mask.lmode = 0x1;
+	}
+
+	/* Two rate three color marker
+	 * With PEIR/EIR set to zero, color will be either green or red
+	 */
+	aq->prof.meter_algo = 2;
+	aq->prof_mask.meter_algo = 0x3;
+
+	aq->prof.rc_action = NIX_RX_BAND_PROF_ACTIONRESULT_DROP;
+	aq->prof_mask.rc_action = 0x3;
+
+	aq->prof.yc_action = NIX_RX_BAND_PROF_ACTIONRESULT_PASS;
+	aq->prof_mask.yc_action = 0x3;
+
+	aq->prof.gc_action = NIX_RX_BAND_PROF_ACTIONRESULT_PASS;
+	aq->prof_mask.gc_action = 0x3;
+
+	/* Setting exponent value as 24 and mantissa as 0 configures
+	 * the bucket with zero values making bucket unused. Peak
+	 * information rate and Excess information rate buckets are
+	 * unused here.
+	 */
+	aq->prof.peir_exponent = 24;
+	aq->prof_mask.peir_exponent = 0x1F;
+
+	aq->prof.peir_mantissa = 0;
+	aq->prof_mask.peir_mantissa = 0xFF;
+
+	aq->prof.pebs_exponent = 24;
+	aq->prof_mask.pebs_exponent = 0x1F;
+
+	aq->prof.pebs_mantissa = 0;
+	aq->prof_mask.pebs_mantissa = 0xFF;
+
+	/* Fill AQ info */
+	aq->qidx = profile;
+	aq->ctype = NIX_AQ_CTYPE_BANDPROF;
+	aq->op = NIX_AQ_INSTOP_WRITE;
+
+	return otx2_sync_mbox_msg(&pfvf->mbox);
+}
+
+int cn10k_set_matchall_ipolicer_rate(struct otx2_nic *pfvf,
+				     u32 burst, u64 rate)
+{
+	struct otx2_hw *hw = &pfvf->hw;
+	int qidx, rc;
+
+	mutex_lock(&pfvf->mbox.lock);
+
+	rc = cn10k_set_ipolicer_rate(pfvf, hw->matchall_ipolicer, burst,
+				     rate, false);
+	if (rc)
+		goto out;
+
+	for (qidx = 0; qidx < hw->rx_queues; qidx++) {
+		rc = cn10k_map_unmap_rq_policer(pfvf, qidx,
+						hw->matchall_ipolicer, true);
+		if (rc)
+			break;
+	}
+
+out:
+	mutex_unlock(&pfvf->mbox.lock);
+	return rc;
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h
index e0bc595cbb78..71292a4cf1f3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h
@@ -14,4 +14,15 @@ void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx);
 int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura);
 int cn10k_pf_lmtst_init(struct otx2_nic *pf);
 int cn10k_vf_lmtst_init(struct otx2_nic *vf);
+int cn10k_free_all_ipolicers(struct otx2_nic *pfvf);
+int cn10k_alloc_matchall_ipolicer(struct otx2_nic *pfvf);
+int cn10k_free_matchall_ipolicer(struct otx2_nic *pfvf);
+int cn10k_set_matchall_ipolicer_rate(struct otx2_nic *pfvf,
+				     u32 burst, u64 rate);
+int cn10k_map_unmap_rq_policer(struct otx2_nic *pfvf, int rq_idx,
+			       u16 policer, bool map);
+int cn10k_alloc_leaf_profile(struct otx2_nic *pfvf, u16 *leaf);
+int cn10k_set_ipolicer_rate(struct otx2_nic *pfvf, u16 profile,
+			    u32 burst, u64 rate, bool pps);
+int cn10k_free_leaf_profile(struct otx2_nic *pfvf, u16 leaf);
 #endif /* CN10K_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 45730d0d92f2..234b330f3183 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -180,6 +180,7 @@ struct otx2_hw {
 
 	/* NIX */
 	u16		txschq_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC];
+	u16			matchall_ipolicer;
 
 	/* HW settings, coalescing etc */
 	u16			rx_chan_base;
@@ -223,6 +224,11 @@ struct otx2_hw {
 	u64			*nix_lmt_base;
 };
 
+enum vfperm {
+	OTX2_RESET_VF_PERM,
+	OTX2_TRUSTED_VF,
+};
+
 struct otx2_vf_config {
 	struct otx2_nic *pf;
 	struct delayed_work link_event_work;
@@ -230,6 +236,7 @@ struct otx2_vf_config {
 	u8 mac[ETH_ALEN];
 	u16 vlan;
 	int tx_vtag_idx;
+	bool trusted;
 };
 
 struct flr_work {
@@ -261,24 +268,26 @@ struct otx2_mac_table {
 
 struct otx2_flow_config {
 	u16			entry[NPC_MAX_NONCONTIG_ENTRIES];
-	u32			nr_flows;
-#define OTX2_MAX_NTUPLE_FLOWS	32
-#define OTX2_MAX_UNICAST_FLOWS	8
-#define OTX2_MAX_VLAN_FLOWS	1
-#define OTX2_MAX_TC_FLOWS	OTX2_MAX_NTUPLE_FLOWS
-#define OTX2_MCAM_COUNT		(OTX2_MAX_NTUPLE_FLOWS + \
+	u16			*flow_ent;
+	u16			*def_ent;
+	u16			nr_flows;
+#define OTX2_DEFAULT_FLOWCOUNT		16
+#define OTX2_MAX_UNICAST_FLOWS		8
+#define OTX2_MAX_VLAN_FLOWS		1
+#define OTX2_MAX_TC_FLOWS	OTX2_DEFAULT_FLOWCOUNT
+#define OTX2_MCAM_COUNT		(OTX2_DEFAULT_FLOWCOUNT + \
 				 OTX2_MAX_UNICAST_FLOWS + \
 				 OTX2_MAX_VLAN_FLOWS)
-	u32			ntuple_offset;
-	u32			unicast_offset;
-	u32			rx_vlan_offset;
-	u32			vf_vlan_offset;
-#define OTX2_PER_VF_VLAN_FLOWS	2 /* rx+tx per VF */
+	u16			ntuple_offset;
+	u16			unicast_offset;
+	u16			rx_vlan_offset;
+	u16			vf_vlan_offset;
+#define OTX2_PER_VF_VLAN_FLOWS	2 /* Rx + Tx per VF */
 #define OTX2_VF_VLAN_RX_INDEX	0
 #define OTX2_VF_VLAN_TX_INDEX	1
-	u32			tc_flower_offset;
-	u32                     ntuple_max_flows;
-	u32			tc_max_flows;
+	u16			tc_flower_offset;
+	u16                     ntuple_max_flows;
+	u16			tc_max_flows;
 	struct list_head	flow_list;
 };
 
@@ -319,6 +328,7 @@ struct otx2_nic {
 #define OTX2_FLAG_TX_PAUSE_ENABLED		BIT_ULL(10)
 #define OTX2_FLAG_TC_FLOWER_SUPPORT		BIT_ULL(11)
 #define OTX2_FLAG_TC_MATCHALL_EGRESS_ENABLED	BIT_ULL(12)
+#define OTX2_FLAG_TC_MATCHALL_INGRESS_ENABLED	BIT_ULL(13)
 	u64			flags;
 
 	struct otx2_qset	qset;
@@ -362,6 +372,7 @@ struct otx2_nic {
 
 	struct otx2_flow_config	*flow_cfg;
 	struct otx2_tc_info	tc_info;
+	unsigned long		rq_bmap;
 };
 
 static inline bool is_otx2_lbkvf(struct pci_dev *pdev)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 9d9a2e438acf..8df748e0677b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -286,6 +286,12 @@ static int otx2_set_channels(struct net_device *dev,
 	if (!channel->rx_count || !channel->tx_count)
 		return -EINVAL;
 
+	if (bitmap_weight(&pfvf->rq_bmap, pfvf->hw.rx_queues) > 1) {
+		netdev_err(dev,
+			   "Receive queues are in use by TC police action\n");
+		return -EINVAL;
+	}
+
 	if (if_up)
 		dev->netdev_ops->ndo_stop(dev);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
index 0b4fa92ba821..8c97106bdd1c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
@@ -20,13 +20,125 @@ struct otx2_flow {
 	int vf;
 };
 
+static void otx2_clear_ntuple_flow_info(struct otx2_nic *pfvf, struct otx2_flow_config *flow_cfg)
+{
+	devm_kfree(pfvf->dev, flow_cfg->flow_ent);
+	flow_cfg->flow_ent = NULL;
+	flow_cfg->ntuple_max_flows = 0;
+	flow_cfg->tc_max_flows = 0;
+}
+
+static int otx2_free_ntuple_mcam_entries(struct otx2_nic *pfvf)
+{
+	struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
+	struct npc_mcam_free_entry_req *req;
+	int ent, err;
+
+	if (!flow_cfg->ntuple_max_flows)
+		return 0;
+
+	mutex_lock(&pfvf->mbox.lock);
+	for (ent = 0; ent < flow_cfg->ntuple_max_flows; ent++) {
+		req = otx2_mbox_alloc_msg_npc_mcam_free_entry(&pfvf->mbox);
+		if (!req)
+			break;
+
+		req->entry = flow_cfg->flow_ent[ent];
+
+		/* Send message to AF to free MCAM entries */
+		err = otx2_sync_mbox_msg(&pfvf->mbox);
+		if (err)
+			break;
+	}
+	mutex_unlock(&pfvf->mbox.lock);
+	otx2_clear_ntuple_flow_info(pfvf, flow_cfg);
+	return 0;
+}
+
+static int otx2_alloc_ntuple_mcam_entries(struct otx2_nic *pfvf, u16 count)
+{
+	struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
+	struct npc_mcam_alloc_entry_req *req;
+	struct npc_mcam_alloc_entry_rsp *rsp;
+	int ent, allocated = 0;
+
+	/* Free current ones and allocate new ones with requested count */
+	otx2_free_ntuple_mcam_entries(pfvf);
+
+	if (!count)
+		return 0;
+
+	flow_cfg->flow_ent = devm_kmalloc_array(pfvf->dev, count,
+						sizeof(u16), GFP_KERNEL);
+	if (!flow_cfg->flow_ent)
+		return -ENOMEM;
+
+	mutex_lock(&pfvf->mbox.lock);
+
+	/* In a single request a max of NPC_MAX_NONCONTIG_ENTRIES MCAM entries
+	 * can only be allocated.
+	 */
+	while (allocated < count) {
+		req = otx2_mbox_alloc_msg_npc_mcam_alloc_entry(&pfvf->mbox);
+		if (!req)
+			goto exit;
+
+		req->contig = false;
+		req->count = (count - allocated) > NPC_MAX_NONCONTIG_ENTRIES ?
+				NPC_MAX_NONCONTIG_ENTRIES : count - allocated;
+		req->priority = NPC_MCAM_HIGHER_PRIO;
+		req->ref_entry = flow_cfg->def_ent[0];
+
+		/* Send message to AF */
+		if (otx2_sync_mbox_msg(&pfvf->mbox))
+			goto exit;
+
+		rsp = (struct npc_mcam_alloc_entry_rsp *)otx2_mbox_get_rsp
+			(&pfvf->mbox.mbox, 0, &req->hdr);
+
+		for (ent = 0; ent < rsp->count; ent++)
+			flow_cfg->flow_ent[ent + allocated] = rsp->entry_list[ent];
+
+		allocated += rsp->count;
+
+		/* If this request is not fulfilled, no need to send
+		 * further requests.
+		 */
+		if (rsp->count != req->count)
+			break;
+	}
+
+exit:
+	mutex_unlock(&pfvf->mbox.lock);
+
+	flow_cfg->ntuple_offset = 0;
+	flow_cfg->ntuple_max_flows = allocated;
+	flow_cfg->tc_max_flows = allocated;
+
+	if (allocated != count)
+		netdev_info(pfvf->netdev,
+			    "Unable to allocate %d MCAM entries for ntuple, got %d\n",
+			    count, allocated);
+
+	return allocated;
+}
+
 int otx2_alloc_mcam_entries(struct otx2_nic *pfvf)
 {
 	struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
 	struct npc_mcam_alloc_entry_req *req;
 	struct npc_mcam_alloc_entry_rsp *rsp;
 	int vf_vlan_max_flows;
-	int i;
+	int ent, count;
+
+	vf_vlan_max_flows = pfvf->total_vfs * OTX2_PER_VF_VLAN_FLOWS;
+	count = OTX2_MAX_UNICAST_FLOWS +
+			OTX2_MAX_VLAN_FLOWS + vf_vlan_max_flows;
+
+	flow_cfg->def_ent = devm_kmalloc_array(pfvf->dev, count,
+					       sizeof(u16), GFP_KERNEL);
+	if (!flow_cfg->def_ent)
+		return -ENOMEM;
 
 	mutex_lock(&pfvf->mbox.lock);
 
@@ -36,9 +148,8 @@ int otx2_alloc_mcam_entries(struct otx2_nic *pfvf)
 		return -ENOMEM;
 	}
 
-	vf_vlan_max_flows = pfvf->total_vfs * OTX2_PER_VF_VLAN_FLOWS;
 	req->contig = false;
-	req->count = OTX2_MCAM_COUNT + vf_vlan_max_flows;
+	req->count = count;
 
 	/* Send message to AF */
 	if (otx2_sync_mbox_msg(&pfvf->mbox)) {
@@ -51,37 +162,36 @@ int otx2_alloc_mcam_entries(struct otx2_nic *pfvf)
 
 	if (rsp->count != req->count) {
 		netdev_info(pfvf->netdev,
-			    "Unable to allocate %d MCAM entries, got %d\n",
-			    req->count, rsp->count);
-		/* support only ntuples here */
-		flow_cfg->ntuple_max_flows = rsp->count;
-		flow_cfg->ntuple_offset = 0;
-		pfvf->flags |= OTX2_FLAG_NTUPLE_SUPPORT;
-		flow_cfg->tc_max_flows = flow_cfg->ntuple_max_flows;
-		pfvf->flags |= OTX2_FLAG_TC_FLOWER_SUPPORT;
-	} else {
-		flow_cfg->vf_vlan_offset = 0;
-		flow_cfg->ntuple_offset = flow_cfg->vf_vlan_offset +
-						vf_vlan_max_flows;
-		flow_cfg->tc_flower_offset = flow_cfg->ntuple_offset;
-		flow_cfg->unicast_offset = flow_cfg->ntuple_offset +
-						OTX2_MAX_NTUPLE_FLOWS;
-		flow_cfg->rx_vlan_offset = flow_cfg->unicast_offset +
-						OTX2_MAX_UNICAST_FLOWS;
-		pfvf->flags |= OTX2_FLAG_NTUPLE_SUPPORT;
-		pfvf->flags |= OTX2_FLAG_UCAST_FLTR_SUPPORT;
-		pfvf->flags |= OTX2_FLAG_RX_VLAN_SUPPORT;
-		pfvf->flags |= OTX2_FLAG_VF_VLAN_SUPPORT;
-		pfvf->flags |= OTX2_FLAG_TC_FLOWER_SUPPORT;
-	}
-
-	for (i = 0; i < rsp->count; i++)
-		flow_cfg->entry[i] = rsp->entry_list[i];
+			    "Unable to allocate MCAM entries for ucast, vlan and vf_vlan\n");
+		mutex_unlock(&pfvf->mbox.lock);
+		devm_kfree(pfvf->dev, flow_cfg->def_ent);
+		return 0;
+	}
 
-	pfvf->flags |= OTX2_FLAG_MCAM_ENTRIES_ALLOC;
+	for (ent = 0; ent < rsp->count; ent++)
+		flow_cfg->def_ent[ent] = rsp->entry_list[ent];
+
+	flow_cfg->vf_vlan_offset = 0;
+	flow_cfg->unicast_offset = vf_vlan_max_flows;
+	flow_cfg->rx_vlan_offset = flow_cfg->unicast_offset +
+					OTX2_MAX_UNICAST_FLOWS;
+	pfvf->flags |= OTX2_FLAG_UCAST_FLTR_SUPPORT;
+	pfvf->flags |= OTX2_FLAG_RX_VLAN_SUPPORT;
+	pfvf->flags |= OTX2_FLAG_VF_VLAN_SUPPORT;
 
+	pfvf->flags |= OTX2_FLAG_MCAM_ENTRIES_ALLOC;
 	mutex_unlock(&pfvf->mbox.lock);
 
+	/* Allocate entries for Ntuple filters */
+	count = otx2_alloc_ntuple_mcam_entries(pfvf, OTX2_DEFAULT_FLOWCOUNT);
+	if (count <= 0) {
+		otx2_clear_ntuple_flow_info(pfvf, flow_cfg);
+		return 0;
+	}
+
+	pfvf->flags |= OTX2_FLAG_NTUPLE_SUPPORT;
+	pfvf->flags |= OTX2_FLAG_TC_FLOWER_SUPPORT;
+
 	return 0;
 }
 
@@ -96,13 +206,14 @@ int otx2_mcam_flow_init(struct otx2_nic *pf)
 
 	INIT_LIST_HEAD(&pf->flow_cfg->flow_list);
 
-	pf->flow_cfg->ntuple_max_flows = OTX2_MAX_NTUPLE_FLOWS;
-	pf->flow_cfg->tc_max_flows = pf->flow_cfg->ntuple_max_flows;
-
 	err = otx2_alloc_mcam_entries(pf);
 	if (err)
 		return err;
 
+	/* Check if MCAM entries are allocate or not */
+	if (!(pf->flags & OTX2_FLAG_UCAST_FLTR_SUPPORT))
+		return 0;
+
 	pf->mac_table = devm_kzalloc(pf->dev, sizeof(struct otx2_mac_table)
 					* OTX2_MAX_UNICAST_FLOWS, GFP_KERNEL);
 	if (!pf->mac_table)
@@ -146,7 +257,7 @@ static int otx2_do_add_macfilter(struct otx2_nic *pf, const u8 *mac)
 		ether_addr_copy(pf->mac_table[i].addr, mac);
 		pf->mac_table[i].inuse = true;
 		pf->mac_table[i].mcam_entry =
-			flow_cfg->entry[i + flow_cfg->unicast_offset];
+			flow_cfg->def_ent[i + flow_cfg->unicast_offset];
 		req->entry =  pf->mac_table[i].mcam_entry;
 		break;
 	}
@@ -551,6 +662,7 @@ static int otx2_prepare_ipv6_flow(struct ethtool_rx_flow_spec *fsp,
 			req->features |= BIT_ULL(NPC_IPPROTO_AH);
 		else
 			req->features |= BIT_ULL(NPC_IPPROTO_ESP);
+		break;
 	default:
 		break;
 	}
@@ -731,8 +843,7 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc)
 		if (!flow)
 			return -ENOMEM;
 		flow->location = fsp->location;
-		flow->entry = flow_cfg->entry[flow_cfg->ntuple_offset +
-						flow->location];
+		flow->entry = flow_cfg->flow_ent[flow->location];
 		new = true;
 	}
 	/* struct copy */
@@ -836,9 +947,8 @@ int otx2_destroy_ntuple_flows(struct otx2_nic *pfvf)
 		return -ENOMEM;
 	}
 
-	req->start = flow_cfg->entry[flow_cfg->ntuple_offset];
-	req->end   = flow_cfg->entry[flow_cfg->ntuple_offset +
-				      flow_cfg->ntuple_max_flows - 1];
+	req->start = flow_cfg->flow_ent[0];
+	req->end   = flow_cfg->flow_ent[flow_cfg->ntuple_max_flows - 1];
 	err = otx2_sync_mbox_msg(&pfvf->mbox);
 	mutex_unlock(&pfvf->mbox.lock);
 
@@ -905,7 +1015,7 @@ int otx2_install_rxvlan_offload_flow(struct otx2_nic *pfvf)
 		return -ENOMEM;
 	}
 
-	req->entry = flow_cfg->entry[flow_cfg->rx_vlan_offset];
+	req->entry = flow_cfg->def_ent[flow_cfg->rx_vlan_offset];
 	req->intf = NIX_INTF_RX;
 	ether_addr_copy(req->packet.dmac, pfvf->netdev->dev_addr);
 	eth_broadcast_addr((u8 *)&req->mask.dmac);
@@ -934,7 +1044,7 @@ static int otx2_delete_rxvlan_offload_flow(struct otx2_nic *pfvf)
 		return -ENOMEM;
 	}
 
-	req->entry = flow_cfg->entry[flow_cfg->rx_vlan_offset];
+	req->entry = flow_cfg->def_ent[flow_cfg->rx_vlan_offset];
 	/* Send message to AF */
 	err = otx2_sync_mbox_msg(&pfvf->mbox);
 	mutex_unlock(&pfvf->mbox.lock);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 03004fdac0c6..59912f73417b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -39,6 +39,8 @@ MODULE_DESCRIPTION(DRV_STRING);
 MODULE_LICENSE("GPL v2");
 MODULE_DEVICE_TABLE(pci, otx2_pf_id_table);
 
+static void otx2_vf_link_event_task(struct work_struct *work);
+
 enum {
 	TYPE_PFAF,
 	TYPE_PFVF,
@@ -1459,6 +1461,9 @@ static void otx2_free_hw_resources(struct otx2_nic *pf)
 
 	otx2_free_cq_res(pf);
 
+	/* Free all ingress bandwidth profiles allocated */
+	cn10k_free_all_ipolicers(pf);
+
 	mutex_lock(&mbox->lock);
 	/* Reset NIX LF */
 	free_req = otx2_mbox_alloc_msg_nix_lf_free(mbox);
@@ -1820,9 +1825,11 @@ static void otx2_do_set_rx_mode(struct work_struct *work)
 
 	if (promisc)
 		req->mode |= NIX_RX_MODE_PROMISC;
-	else if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST))
+	if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST))
 		req->mode |= NIX_RX_MODE_ALLMULTI;
 
+	req->mode |= NIX_RX_MODE_USE_MCE;
+
 	otx2_sync_mbox_msg(&pf->mbox);
 	mutex_unlock(&pf->mbox.lock);
 }
@@ -2044,7 +2051,7 @@ static int otx2_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 	if (!netif_running(netdev))
 		return -EAGAIN;
 
-	if (vf >= pci_num_vf(pdev))
+	if (vf >= pf->total_vfs)
 		return -EINVAL;
 
 	if (!is_valid_ether_addr(mac))
@@ -2055,7 +2062,8 @@ static int otx2_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 
 	ret = otx2_do_set_vf_mac(pf, vf, mac);
 	if (ret == 0)
-		dev_info(&pdev->dev, "Reload VF driver to apply the changes\n");
+		dev_info(&pdev->dev,
+			 "Load/Reload VF driver\n");
 
 	return ret;
 }
@@ -2104,7 +2112,7 @@ static int otx2_do_set_vf_vlan(struct otx2_nic *pf, int vf, u16 vlan, u8 qos,
 		}
 		idx = ((vf * OTX2_PER_VF_VLAN_FLOWS) + OTX2_VF_VLAN_RX_INDEX);
 		del_req->entry =
-			flow_cfg->entry[flow_cfg->vf_vlan_offset + idx];
+			flow_cfg->def_ent[flow_cfg->vf_vlan_offset + idx];
 		err = otx2_sync_mbox_msg(&pf->mbox);
 		if (err)
 			goto out;
@@ -2117,7 +2125,7 @@ static int otx2_do_set_vf_vlan(struct otx2_nic *pf, int vf, u16 vlan, u8 qos,
 		}
 		idx = ((vf * OTX2_PER_VF_VLAN_FLOWS) + OTX2_VF_VLAN_TX_INDEX);
 		del_req->entry =
-			flow_cfg->entry[flow_cfg->vf_vlan_offset + idx];
+			flow_cfg->def_ent[flow_cfg->vf_vlan_offset + idx];
 		err = otx2_sync_mbox_msg(&pf->mbox);
 
 		goto out;
@@ -2131,7 +2139,7 @@ static int otx2_do_set_vf_vlan(struct otx2_nic *pf, int vf, u16 vlan, u8 qos,
 	}
 
 	idx = ((vf * OTX2_PER_VF_VLAN_FLOWS) + OTX2_VF_VLAN_RX_INDEX);
-	req->entry = flow_cfg->entry[flow_cfg->vf_vlan_offset + idx];
+	req->entry = flow_cfg->def_ent[flow_cfg->vf_vlan_offset + idx];
 	req->packet.vlan_tci = htons(vlan);
 	req->mask.vlan_tci = htons(VLAN_VID_MASK);
 	/* af fills the destination mac addr */
@@ -2182,7 +2190,7 @@ static int otx2_do_set_vf_vlan(struct otx2_nic *pf, int vf, u16 vlan, u8 qos,
 
 	eth_zero_addr((u8 *)&req->mask.dmac);
 	idx = ((vf * OTX2_PER_VF_VLAN_FLOWS) + OTX2_VF_VLAN_TX_INDEX);
-	req->entry = flow_cfg->entry[flow_cfg->vf_vlan_offset + idx];
+	req->entry = flow_cfg->def_ent[flow_cfg->vf_vlan_offset + idx];
 	req->features = BIT_ULL(NPC_DMAC);
 	req->channel = pf->hw.tx_chan_base;
 	req->intf = NIX_INTF_TX;
@@ -2241,10 +2249,63 @@ static int otx2_get_vf_config(struct net_device *netdev, int vf,
 	ivi->vf = vf;
 	ether_addr_copy(ivi->mac, config->mac);
 	ivi->vlan = config->vlan;
+	ivi->trusted = config->trusted;
 
 	return 0;
 }
 
+static int otx2_set_vf_permissions(struct otx2_nic *pf, int vf,
+				   int req_perm)
+{
+	struct set_vf_perm *req;
+	int rc;
+
+	mutex_lock(&pf->mbox.lock);
+	req = otx2_mbox_alloc_msg_set_vf_perm(&pf->mbox);
+	if (!req) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	/* Let AF reset VF permissions as sriov is disabled */
+	if (req_perm == OTX2_RESET_VF_PERM) {
+		req->flags |= RESET_VF_PERM;
+	} else if (req_perm == OTX2_TRUSTED_VF) {
+		if (pf->vf_configs[vf].trusted)
+			req->flags |= VF_TRUSTED;
+	}
+
+	req->vf = vf;
+	rc = otx2_sync_mbox_msg(&pf->mbox);
+out:
+	mutex_unlock(&pf->mbox.lock);
+	return rc;
+}
+
+static int otx2_ndo_set_vf_trust(struct net_device *netdev, int vf,
+				 bool enable)
+{
+	struct otx2_nic *pf = netdev_priv(netdev);
+	struct pci_dev *pdev = pf->pdev;
+	int rc;
+
+	if (vf >= pci_num_vf(pdev))
+		return -EINVAL;
+
+	if (pf->vf_configs[vf].trusted == enable)
+		return 0;
+
+	pf->vf_configs[vf].trusted = enable;
+	rc = otx2_set_vf_permissions(pf, vf, OTX2_TRUSTED_VF);
+
+	if (rc)
+		pf->vf_configs[vf].trusted = !enable;
+	else
+		netdev_info(pf->netdev, "VF %d is %strusted\n",
+			    vf, enable ? "" : "not ");
+	return rc;
+}
+
 static const struct net_device_ops otx2_netdev_ops = {
 	.ndo_open		= otx2_open,
 	.ndo_stop		= otx2_stop,
@@ -2261,6 +2322,7 @@ static const struct net_device_ops otx2_netdev_ops = {
 	.ndo_set_vf_vlan	= otx2_set_vf_vlan,
 	.ndo_get_vf_config	= otx2_get_vf_config,
 	.ndo_setup_tc		= otx2_setup_tc,
+	.ndo_set_vf_trust	= otx2_ndo_set_vf_trust,
 };
 
 static int otx2_wq_init(struct otx2_nic *pf)
@@ -2315,6 +2377,40 @@ static int otx2_realloc_msix_vectors(struct otx2_nic *pf)
 	return otx2_register_mbox_intr(pf, false);
 }
 
+static int otx2_sriov_vfcfg_init(struct otx2_nic *pf)
+{
+	int i;
+
+	pf->vf_configs = devm_kcalloc(pf->dev, pf->total_vfs,
+				      sizeof(struct otx2_vf_config),
+				      GFP_KERNEL);
+	if (!pf->vf_configs)
+		return -ENOMEM;
+
+	for (i = 0; i < pf->total_vfs; i++) {
+		pf->vf_configs[i].pf = pf;
+		pf->vf_configs[i].intf_down = true;
+		pf->vf_configs[i].trusted = false;
+		INIT_DELAYED_WORK(&pf->vf_configs[i].link_event_work,
+				  otx2_vf_link_event_task);
+	}
+
+	return 0;
+}
+
+static void otx2_sriov_vfcfg_cleanup(struct otx2_nic *pf)
+{
+	int i;
+
+	if (!pf->vf_configs)
+		return;
+
+	for (i = 0; i < pf->total_vfs; i++) {
+		cancel_delayed_work_sync(&pf->vf_configs[i].link_event_work);
+		otx2_set_vf_permissions(pf, i, OTX2_RESET_VF_PERM);
+	}
+}
+
 static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct device *dev = &pdev->dev;
@@ -2509,6 +2605,11 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_mcam_flow_del;
 
+	/* Initialize SR-IOV resources */
+	err = otx2_sriov_vfcfg_init(pf);
+	if (err)
+		goto err_pf_sriov_init;
+
 	/* Enable link notifications */
 	otx2_cgx_config_linkevents(pf, true);
 
@@ -2518,6 +2619,8 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	return 0;
 
+err_pf_sriov_init:
+	otx2_shutdown_tc(pf);
 err_mcam_flow_del:
 	otx2_mcam_flow_del(pf);
 err_unreg_netdev:
@@ -2576,7 +2679,7 @@ static int otx2_sriov_enable(struct pci_dev *pdev, int numvfs)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct otx2_nic *pf = netdev_priv(netdev);
-	int ret, i;
+	int ret;
 
 	/* Init PF <=> VF mailbox stuff */
 	ret = otx2_pfvf_mbox_init(pf, numvfs);
@@ -2587,23 +2690,9 @@ static int otx2_sriov_enable(struct pci_dev *pdev, int numvfs)
 	if (ret)
 		goto free_mbox;
 
-	pf->vf_configs = kcalloc(numvfs, sizeof(struct otx2_vf_config),
-				 GFP_KERNEL);
-	if (!pf->vf_configs) {
-		ret = -ENOMEM;
-		goto free_intr;
-	}
-
-	for (i = 0; i < numvfs; i++) {
-		pf->vf_configs[i].pf = pf;
-		pf->vf_configs[i].intf_down = true;
-		INIT_DELAYED_WORK(&pf->vf_configs[i].link_event_work,
-				  otx2_vf_link_event_task);
-	}
-
 	ret = otx2_pf_flr_init(pf, numvfs);
 	if (ret)
-		goto free_configs;
+		goto free_intr;
 
 	ret = otx2_register_flr_me_intr(pf, numvfs);
 	if (ret)
@@ -2618,8 +2707,6 @@ free_flr_intr:
 	otx2_disable_flr_me_intr(pf);
 free_flr:
 	otx2_flr_wq_destroy(pf);
-free_configs:
-	kfree(pf->vf_configs);
 free_intr:
 	otx2_disable_pfvf_mbox_intr(pf, numvfs);
 free_mbox:
@@ -2632,17 +2719,12 @@ static int otx2_sriov_disable(struct pci_dev *pdev)
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct otx2_nic *pf = netdev_priv(netdev);
 	int numvfs = pci_num_vf(pdev);
-	int i;
 
 	if (!numvfs)
 		return 0;
 
 	pci_disable_sriov(pdev);
 
-	for (i = 0; i < pci_num_vf(pdev); i++)
-		cancel_delayed_work_sync(&pf->vf_configs[i].link_event_work);
-	kfree(pf->vf_configs);
-
 	otx2_disable_flr_me_intr(pf);
 	otx2_flr_wq_destroy(pf);
 	otx2_disable_pfvf_mbox_intr(pf, numvfs);
@@ -2682,6 +2764,7 @@ static void otx2_remove(struct pci_dev *pdev)
 
 	unregister_netdev(netdev);
 	otx2_sriov_disable(pf->pdev);
+	otx2_sriov_vfcfg_cleanup(pf);
 	if (pf->otx2_wq)
 		destroy_workqueue(pf->otx2_wq);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 51157b283f6f..905fc02a7dfe 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -15,6 +15,7 @@
 #include <net/tc_act/tc_vlan.h>
 #include <net/ipv6.h>
 
+#include "cn10k.h"
 #include "otx2_common.h"
 
 /* Egress rate limiting definitions */
@@ -41,11 +42,14 @@ struct otx2_tc_flow_stats {
 struct otx2_tc_flow {
 	struct rhash_head		node;
 	unsigned long			cookie;
-	u16				entry;
 	unsigned int			bitpos;
 	struct rcu_head			rcu;
 	struct otx2_tc_flow_stats	stats;
 	spinlock_t			lock; /* lock for stats */
+	u16				rq;
+	u16				entry;
+	u16				leaf_profile;
+	bool				is_act_police;
 };
 
 static void otx2_get_egress_burst_cfg(u32 burst, u32 *burst_exp,
@@ -220,17 +224,76 @@ static int otx2_tc_egress_matchall_delete(struct otx2_nic *nic,
 	return err;
 }
 
+static int otx2_tc_act_set_police(struct otx2_nic *nic,
+				  struct otx2_tc_flow *node,
+				  struct flow_cls_offload *f,
+				  u64 rate, u32 burst, u32 mark,
+				  struct npc_install_flow_req *req, bool pps)
+{
+	struct netlink_ext_ack *extack = f->common.extack;
+	struct otx2_hw *hw = &nic->hw;
+	int rq_idx, rc;
+
+	rq_idx = find_first_zero_bit(&nic->rq_bmap, hw->rx_queues);
+	if (rq_idx >= hw->rx_queues) {
+		NL_SET_ERR_MSG_MOD(extack, "Police action rules exceeded");
+		return -EINVAL;
+	}
+
+	mutex_lock(&nic->mbox.lock);
+
+	rc = cn10k_alloc_leaf_profile(nic, &node->leaf_profile);
+	if (rc) {
+		mutex_unlock(&nic->mbox.lock);
+		return rc;
+	}
+
+	rc = cn10k_set_ipolicer_rate(nic, node->leaf_profile, burst, rate, pps);
+	if (rc)
+		goto free_leaf;
+
+	rc = cn10k_map_unmap_rq_policer(nic, rq_idx, node->leaf_profile, true);
+	if (rc)
+		goto free_leaf;
+
+	mutex_unlock(&nic->mbox.lock);
+
+	req->match_id = mark & 0xFFFFULL;
+	req->index = rq_idx;
+	req->op = NIX_RX_ACTIONOP_UCAST;
+	set_bit(rq_idx, &nic->rq_bmap);
+	node->is_act_police = true;
+	node->rq = rq_idx;
+
+	return 0;
+
+free_leaf:
+	if (cn10k_free_leaf_profile(nic, node->leaf_profile))
+		netdev_err(nic->netdev,
+			   "Unable to free leaf bandwidth profile(%d)\n",
+			   node->leaf_profile);
+	mutex_unlock(&nic->mbox.lock);
+	return rc;
+}
+
 static int otx2_tc_parse_actions(struct otx2_nic *nic,
 				 struct flow_action *flow_action,
-				 struct npc_install_flow_req *req)
+				 struct npc_install_flow_req *req,
+				 struct flow_cls_offload *f,
+				 struct otx2_tc_flow *node)
 {
+	struct netlink_ext_ack *extack = f->common.extack;
 	struct flow_action_entry *act;
 	struct net_device *target;
 	struct otx2_nic *priv;
+	u32 burst, mark = 0;
+	u8 nr_police = 0;
+	bool pps;
+	u64 rate;
 	int i;
 
 	if (!flow_action_has_entries(flow_action)) {
-		netdev_info(nic->netdev, "no tc actions specified");
+		NL_SET_ERR_MSG_MOD(extack, "no tc actions specified");
 		return -EINVAL;
 	}
 
@@ -247,8 +310,8 @@ static int otx2_tc_parse_actions(struct otx2_nic *nic,
 			priv = netdev_priv(target);
 			/* npc_install_flow_req doesn't support passing a target pcifunc */
 			if (rvu_get_pf(nic->pcifunc) != rvu_get_pf(priv->pcifunc)) {
-				netdev_info(nic->netdev,
-					    "can't redirect to other pf/vf\n");
+				NL_SET_ERR_MSG_MOD(extack,
+						   "can't redirect to other pf/vf");
 				return -EOPNOTSUPP;
 			}
 			req->vf = priv->pcifunc & RVU_PFVF_FUNC_MASK;
@@ -259,18 +322,55 @@ static int otx2_tc_parse_actions(struct otx2_nic *nic,
 			/* use RX_VTAG_TYPE7 which is initialized to strip vlan tag */
 			req->vtag0_type = NIX_AF_LFX_RX_VTAG_TYPE7;
 			break;
+		case FLOW_ACTION_POLICE:
+			/* Ingress ratelimiting is not supported on OcteonTx2 */
+			if (is_dev_otx2(nic->pdev)) {
+				NL_SET_ERR_MSG_MOD(extack,
+					"Ingress policing not supported on this platform");
+				return -EOPNOTSUPP;
+			}
+
+			if (act->police.rate_bytes_ps > 0) {
+				rate = act->police.rate_bytes_ps * 8;
+				burst = act->police.burst;
+			} else if (act->police.rate_pkt_ps > 0) {
+				/* The algorithm used to calculate rate
+				 * mantissa, exponent values for a given token
+				 * rate (token can be byte or packet) requires
+				 * token rate to be mutiplied by 8.
+				 */
+				rate = act->police.rate_pkt_ps * 8;
+				burst = act->police.burst_pkt;
+				pps = true;
+			}
+			nr_police++;
+			break;
+		case FLOW_ACTION_MARK:
+			mark = act->mark;
+			break;
 		default:
 			return -EOPNOTSUPP;
 		}
 	}
 
+	if (nr_police > 1) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "rate limit police offload requires a single action");
+		return -EOPNOTSUPP;
+	}
+
+	if (nr_police)
+		return otx2_tc_act_set_police(nic, node, f, rate, burst,
+					      mark, req, pps);
+
 	return 0;
 }
 
-static int otx2_tc_prepare_flow(struct otx2_nic *nic,
+static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 				struct flow_cls_offload *f,
 				struct npc_install_flow_req *req)
 {
+	struct netlink_ext_ack *extack = f->common.extack;
 	struct flow_msg *flow_spec = &req->packet;
 	struct flow_msg *flow_mask = &req->mask;
 	struct flow_dissector *dissector;
@@ -335,7 +435,7 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic,
 
 		flow_rule_match_eth_addrs(rule, &match);
 		if (!is_zero_ether_addr(match.mask->src)) {
-			netdev_err(nic->netdev, "src mac match not supported\n");
+			NL_SET_ERR_MSG_MOD(extack, "src mac match not supported");
 			return -EOPNOTSUPP;
 		}
 
@@ -353,11 +453,11 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic,
 		flow_rule_match_ip(rule, &match);
 		if ((ntohs(flow_spec->etype) != ETH_P_IP) &&
 		    match.mask->tos) {
-			netdev_err(nic->netdev, "tos not supported\n");
+			NL_SET_ERR_MSG_MOD(extack, "tos not supported");
 			return -EOPNOTSUPP;
 		}
 		if (match.mask->ttl) {
-			netdev_err(nic->netdev, "ttl not supported\n");
+			NL_SET_ERR_MSG_MOD(extack, "ttl not supported");
 			return -EOPNOTSUPP;
 		}
 		flow_spec->tos = match.key->tos;
@@ -413,8 +513,8 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic,
 
 		if (ipv6_addr_loopback(&match.key->dst) ||
 		    ipv6_addr_loopback(&match.key->src)) {
-			netdev_err(nic->netdev,
-				   "Flow matching on IPv6 loopback addr is not supported\n");
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Flow matching IPv6 loopback addr not supported");
 			return -EOPNOTSUPP;
 		}
 
@@ -463,7 +563,7 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic,
 			req->features |= BIT_ULL(NPC_SPORT_SCTP);
 	}
 
-	return otx2_tc_parse_actions(nic, &rule->action, req);
+	return otx2_tc_parse_actions(nic, &rule->action, req, f, node);
 }
 
 static int otx2_del_mcam_flow_entry(struct otx2_nic *nic, u16 entry)
@@ -498,6 +598,7 @@ static int otx2_tc_del_flow(struct otx2_nic *nic,
 {
 	struct otx2_tc_info *tc_info = &nic->tc_info;
 	struct otx2_tc_flow *flow_node;
+	int err;
 
 	flow_node = rhashtable_lookup_fast(&tc_info->flow_table,
 					   &tc_flow_cmd->cookie,
@@ -508,6 +609,27 @@ static int otx2_tc_del_flow(struct otx2_nic *nic,
 		return -EINVAL;
 	}
 
+	if (flow_node->is_act_police) {
+		mutex_lock(&nic->mbox.lock);
+
+		err = cn10k_map_unmap_rq_policer(nic, flow_node->rq,
+						 flow_node->leaf_profile, false);
+		if (err)
+			netdev_err(nic->netdev,
+				   "Unmapping RQ %d & profile %d failed\n",
+				   flow_node->rq, flow_node->leaf_profile);
+
+		err = cn10k_free_leaf_profile(nic, flow_node->leaf_profile);
+		if (err)
+			netdev_err(nic->netdev,
+				   "Unable to free leaf bandwidth profile(%d)\n",
+				   flow_node->leaf_profile);
+
+		__clear_bit(flow_node->rq, &nic->rq_bmap);
+
+		mutex_unlock(&nic->mbox.lock);
+	}
+
 	otx2_del_mcam_flow_entry(nic, flow_node->entry);
 
 	WARN_ON(rhashtable_remove_fast(&nic->tc_info.flow_table,
@@ -524,14 +646,21 @@ static int otx2_tc_del_flow(struct otx2_nic *nic,
 static int otx2_tc_add_flow(struct otx2_nic *nic,
 			    struct flow_cls_offload *tc_flow_cmd)
 {
+	struct netlink_ext_ack *extack = tc_flow_cmd->common.extack;
 	struct otx2_tc_info *tc_info = &nic->tc_info;
 	struct otx2_tc_flow *new_node, *old_node;
-	struct npc_install_flow_req *req;
-	int rc;
+	struct npc_install_flow_req *req, dummy;
+	int rc, err;
 
 	if (!(nic->flags & OTX2_FLAG_TC_FLOWER_SUPPORT))
 		return -ENOMEM;
 
+	if (bitmap_full(tc_info->tc_entries_bitmap, nic->flow_cfg->tc_max_flows)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Not enough MCAM space to add the flow");
+		return -ENOMEM;
+	}
+
 	/* allocate memory for the new flow and it's node */
 	new_node = kzalloc(sizeof(*new_node), GFP_KERNEL);
 	if (!new_node)
@@ -539,17 +668,11 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 	spin_lock_init(&new_node->lock);
 	new_node->cookie = tc_flow_cmd->cookie;
 
-	mutex_lock(&nic->mbox.lock);
-	req = otx2_mbox_alloc_msg_npc_install_flow(&nic->mbox);
-	if (!req) {
-		mutex_unlock(&nic->mbox.lock);
-		return -ENOMEM;
-	}
+	memset(&dummy, 0, sizeof(struct npc_install_flow_req));
 
-	rc = otx2_tc_prepare_flow(nic, tc_flow_cmd, req);
+	rc = otx2_tc_prepare_flow(nic, new_node, tc_flow_cmd, &dummy);
 	if (rc) {
-		otx2_mbox_reset(&nic->mbox.mbox, 0);
-		mutex_unlock(&nic->mbox.lock);
+		kfree_rcu(new_node, rcu);
 		return rc;
 	}
 
@@ -560,18 +683,22 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 	if (old_node)
 		otx2_tc_del_flow(nic, tc_flow_cmd);
 
-	if (bitmap_full(tc_info->tc_entries_bitmap, nic->flow_cfg->tc_max_flows)) {
-		netdev_err(nic->netdev, "Not enough MCAM space to add the flow\n");
-		otx2_mbox_reset(&nic->mbox.mbox, 0);
+	mutex_lock(&nic->mbox.lock);
+	req = otx2_mbox_alloc_msg_npc_install_flow(&nic->mbox);
+	if (!req) {
 		mutex_unlock(&nic->mbox.lock);
-		return -ENOMEM;
+		rc = -ENOMEM;
+		goto free_leaf;
 	}
 
+	memcpy(&dummy.hdr, &req->hdr, sizeof(struct mbox_msghdr));
+	memcpy(req, &dummy, sizeof(struct npc_install_flow_req));
+
 	new_node->bitpos = find_first_zero_bit(tc_info->tc_entries_bitmap,
 					       nic->flow_cfg->tc_max_flows);
 	req->channel = nic->hw.rx_chan_base;
-	req->entry = nic->flow_cfg->entry[nic->flow_cfg->tc_flower_offset +
-					  nic->flow_cfg->tc_max_flows - new_node->bitpos];
+	req->entry = nic->flow_cfg->flow_ent[nic->flow_cfg->tc_flower_offset +
+				nic->flow_cfg->tc_max_flows - new_node->bitpos];
 	req->intf = NIX_INTF_RX;
 	req->set_cntr = 1;
 	new_node->entry = req->entry;
@@ -579,9 +706,10 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 	/* Send message to AF */
 	rc = otx2_sync_mbox_msg(&nic->mbox);
 	if (rc) {
-		netdev_err(nic->netdev, "Failed to install MCAM flow entry\n");
+		NL_SET_ERR_MSG_MOD(extack, "Failed to install MCAM flow entry");
 		mutex_unlock(&nic->mbox.lock);
-		goto out;
+		kfree_rcu(new_node, rcu);
+		goto free_leaf;
 	}
 	mutex_unlock(&nic->mbox.lock);
 
@@ -591,12 +719,35 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 	if (rc) {
 		otx2_del_mcam_flow_entry(nic, req->entry);
 		kfree_rcu(new_node, rcu);
-		goto out;
+		goto free_leaf;
 	}
 
 	set_bit(new_node->bitpos, tc_info->tc_entries_bitmap);
 	tc_info->num_entries++;
-out:
+
+	return 0;
+
+free_leaf:
+	if (new_node->is_act_police) {
+		mutex_lock(&nic->mbox.lock);
+
+		err = cn10k_map_unmap_rq_policer(nic, new_node->rq,
+						 new_node->leaf_profile, false);
+		if (err)
+			netdev_err(nic->netdev,
+				   "Unmapping RQ %d & profile %d failed\n",
+				   new_node->rq, new_node->leaf_profile);
+		err = cn10k_free_leaf_profile(nic, new_node->leaf_profile);
+		if (err)
+			netdev_err(nic->netdev,
+				   "Unable to free leaf bandwidth profile(%d)\n",
+				   new_node->leaf_profile);
+
+		__clear_bit(new_node->rq, &nic->rq_bmap);
+
+		mutex_unlock(&nic->mbox.lock);
+	}
+
 	return rc;
 }
 
@@ -675,6 +826,87 @@ static int otx2_setup_tc_cls_flower(struct otx2_nic *nic,
 	}
 }
 
+static int otx2_tc_ingress_matchall_install(struct otx2_nic *nic,
+					    struct tc_cls_matchall_offload *cls)
+{
+	struct netlink_ext_ack *extack = cls->common.extack;
+	struct flow_action *actions = &cls->rule->action;
+	struct flow_action_entry *entry;
+	u64 rate;
+	int err;
+
+	err = otx2_tc_validate_flow(nic, actions, extack);
+	if (err)
+		return err;
+
+	if (nic->flags & OTX2_FLAG_TC_MATCHALL_INGRESS_ENABLED) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Only one ingress MATCHALL ratelimitter can be offloaded");
+		return -ENOMEM;
+	}
+
+	entry = &cls->rule->action.entries[0];
+	switch (entry->id) {
+	case FLOW_ACTION_POLICE:
+		/* Ingress ratelimiting is not supported on OcteonTx2 */
+		if (is_dev_otx2(nic->pdev)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Ingress policing not supported on this platform");
+			return -EOPNOTSUPP;
+		}
+
+		err = cn10k_alloc_matchall_ipolicer(nic);
+		if (err)
+			return err;
+
+		/* Convert to bits per second */
+		rate = entry->police.rate_bytes_ps * 8;
+		err = cn10k_set_matchall_ipolicer_rate(nic, entry->police.burst, rate);
+		if (err)
+			return err;
+		nic->flags |= OTX2_FLAG_TC_MATCHALL_INGRESS_ENABLED;
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Only police action supported with Ingress MATCHALL offload");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int otx2_tc_ingress_matchall_delete(struct otx2_nic *nic,
+					   struct tc_cls_matchall_offload *cls)
+{
+	struct netlink_ext_ack *extack = cls->common.extack;
+	int err;
+
+	if (nic->flags & OTX2_FLAG_INTF_DOWN) {
+		NL_SET_ERR_MSG_MOD(extack, "Interface not initialized");
+		return -EINVAL;
+	}
+
+	err = cn10k_free_matchall_ipolicer(nic);
+	nic->flags &= ~OTX2_FLAG_TC_MATCHALL_INGRESS_ENABLED;
+	return err;
+}
+
+static int otx2_setup_tc_ingress_matchall(struct otx2_nic *nic,
+					  struct tc_cls_matchall_offload *cls_matchall)
+{
+	switch (cls_matchall->command) {
+	case TC_CLSMATCHALL_REPLACE:
+		return otx2_tc_ingress_matchall_install(nic, cls_matchall);
+	case TC_CLSMATCHALL_DESTROY:
+		return otx2_tc_ingress_matchall_delete(nic, cls_matchall);
+	case TC_CLSMATCHALL_STATS:
+	default:
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
 static int otx2_setup_tc_block_ingress_cb(enum tc_setup_type type,
 					  void *type_data, void *cb_priv)
 {
@@ -686,6 +918,8 @@ static int otx2_setup_tc_block_ingress_cb(enum tc_setup_type type,
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
 		return otx2_setup_tc_cls_flower(nic, type_data);
+	case TC_SETUP_CLSMATCHALL:
+		return otx2_setup_tc_ingress_matchall(nic, type_data);
 	default:
 		break;
 	}
@@ -775,6 +1009,9 @@ int otx2_init_tc(struct otx2_nic *nic)
 {
 	struct otx2_tc_info *tc = &nic->tc_info;
 
+	/* Exclude receive queue 0 being used for police action */
+	set_bit(0, &nic->rq_bmap);
+
 	tc->flow_ht_params = tc_flow_ht_params;
 	return rhashtable_init(&tc->flow_table, &tc->flow_ht_params);
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
index 085be90a03eb..13a908f75ba0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
@@ -395,6 +395,42 @@ static netdev_tx_t otx2vf_xmit(struct sk_buff *skb, struct net_device *netdev)
 	return NETDEV_TX_OK;
 }
 
+static void otx2vf_set_rx_mode(struct net_device *netdev)
+{
+	struct otx2_nic *vf = netdev_priv(netdev);
+
+	queue_work(vf->otx2_wq, &vf->rx_mode_work);
+}
+
+static void otx2vf_do_set_rx_mode(struct work_struct *work)
+{
+	struct otx2_nic *vf = container_of(work, struct otx2_nic, rx_mode_work);
+	struct net_device *netdev = vf->netdev;
+	unsigned int flags = netdev->flags;
+	struct nix_rx_mode *req;
+
+	mutex_lock(&vf->mbox.lock);
+
+	req = otx2_mbox_alloc_msg_nix_set_rx_mode(&vf->mbox);
+	if (!req) {
+		mutex_unlock(&vf->mbox.lock);
+		return;
+	}
+
+	req->mode = NIX_RX_MODE_UCAST;
+
+	if (flags & IFF_PROMISC)
+		req->mode |= NIX_RX_MODE_PROMISC;
+	if (flags & (IFF_ALLMULTI | IFF_MULTICAST))
+		req->mode |= NIX_RX_MODE_ALLMULTI;
+
+	req->mode |= NIX_RX_MODE_USE_MCE;
+
+	otx2_sync_mbox_msg(&vf->mbox);
+
+	mutex_unlock(&vf->mbox.lock);
+}
+
 static int otx2vf_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	bool if_up = netif_running(netdev);
@@ -432,12 +468,24 @@ static const struct net_device_ops otx2vf_netdev_ops = {
 	.ndo_open = otx2vf_open,
 	.ndo_stop = otx2vf_stop,
 	.ndo_start_xmit = otx2vf_xmit,
+	.ndo_set_rx_mode = otx2vf_set_rx_mode,
 	.ndo_set_mac_address = otx2_set_mac_address,
 	.ndo_change_mtu = otx2vf_change_mtu,
 	.ndo_get_stats64 = otx2_get_stats64,
 	.ndo_tx_timeout = otx2_tx_timeout,
 };
 
+static int otx2_wq_init(struct otx2_nic *vf)
+{
+	vf->otx2_wq = create_singlethread_workqueue("otx2vf_wq");
+	if (!vf->otx2_wq)
+		return -ENOMEM;
+
+	INIT_WORK(&vf->rx_mode_work, otx2vf_do_set_rx_mode);
+	INIT_WORK(&vf->reset_task, otx2vf_reset_task);
+	return 0;
+}
+
 static int otx2vf_realloc_msix_vectors(struct otx2_nic *vf)
 {
 	struct otx2_hw *hw = &vf->hw;
@@ -588,8 +636,6 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	netdev->min_mtu = OTX2_MIN_MTU;
 	netdev->max_mtu = otx2_get_max_mtu(vf);
 
-	INIT_WORK(&vf->reset_task, otx2vf_reset_task);
-
 	/* To distinguish, for LBK VFs set netdev name explicitly */
 	if (is_otx2_lbkvf(vf->pdev)) {
 		int n;
@@ -606,6 +652,10 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_detach_rsrc;
 	}
 
+	err = otx2_wq_init(vf);
+	if (err)
+		goto err_unreg_netdev;
+
 	otx2vf_set_ethtool_ops(netdev);
 
 	/* Enable pause frames by default */
@@ -614,6 +664,8 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	return 0;
 
+err_unreg_netdev:
+	unregister_netdev(netdev);
 err_detach_rsrc:
 	if (hw->lmt_base)
 		iounmap(hw->lmt_base);
@@ -644,6 +696,8 @@ static void otx2vf_remove(struct pci_dev *pdev)
 
 	cancel_work_sync(&vf->reset_task);
 	unregister_netdev(netdev);
+	if (vf->otx2_wq)
+		destroy_workqueue(vf->otx2_wq);
 	otx2vf_disable_mbox_intr(vf);
 	otx2_detach_resources(&vf->mbox);
 
diff --git a/drivers/net/ethernet/marvell/prestera/Makefile b/drivers/net/ethernet/marvell/prestera/Makefile
index 93129e32ebc5..0609df8b913d 100644
--- a/drivers/net/ethernet/marvell/prestera/Makefile
+++ b/drivers/net/ethernet/marvell/prestera/Makefile
@@ -2,6 +2,7 @@
 obj-$(CONFIG_PRESTERA)	+= prestera.o
 prestera-objs		:= prestera_main.o prestera_hw.o prestera_dsa.o \
 			   prestera_rxtx.o prestera_devlink.o prestera_ethtool.o \
-			   prestera_switchdev.o
+			   prestera_switchdev.o prestera_acl.o prestera_flow.o \
+			   prestera_flower.o prestera_span.o
 
 obj-$(CONFIG_PRESTERA_PCI)	+= prestera_pci.o
diff --git a/drivers/net/ethernet/marvell/prestera/prestera.h b/drivers/net/ethernet/marvell/prestera/prestera.h
index 55aa4bf8a27c..f18fe664b373 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera.h
+++ b/drivers/net/ethernet/marvell/prestera/prestera.h
@@ -60,10 +60,22 @@ struct prestera_port_caps {
 	u8 transceiver;
 };
 
+struct prestera_lag {
+	struct net_device *dev;
+	struct list_head members;
+	u16 member_count;
+	u16 lag_id;
+};
+
+struct prestera_flow_block;
+
 struct prestera_port {
 	struct net_device *dev;
 	struct prestera_switch *sw;
+	struct prestera_flow_block *flow_block;
 	struct devlink_port dl_port;
+	struct list_head lag_member;
+	struct prestera_lag *lag;
 	u32 id;
 	u32 hw_id;
 	u32 dev_id;
@@ -127,6 +139,12 @@ struct prestera_port_event {
 	} data;
 };
 
+enum prestera_fdb_entry_type {
+	PRESTERA_FDB_ENTRY_TYPE_REG_PORT,
+	PRESTERA_FDB_ENTRY_TYPE_LAG,
+	PRESTERA_FDB_ENTRY_TYPE_MAX
+};
+
 enum prestera_fdb_event_id {
 	PRESTERA_FDB_EVENT_UNSPEC,
 	PRESTERA_FDB_EVENT_LEARNED,
@@ -134,7 +152,11 @@ enum prestera_fdb_event_id {
 };
 
 struct prestera_fdb_event {
-	u32 port_id;
+	enum prestera_fdb_entry_type type;
+	union {
+		u32 port_id;
+		u16 lag_id;
+	} dest;
 	u32 vid;
 	union {
 		u8 mac[ETH_ALEN];
@@ -150,14 +172,20 @@ struct prestera_event {
 };
 
 struct prestera_switchdev;
+struct prestera_span;
 struct prestera_rxtx;
+struct prestera_trap_data;
+struct prestera_acl;
 
 struct prestera_switch {
 	struct prestera_device *dev;
 	struct prestera_switchdev *swdev;
 	struct prestera_rxtx *rxtx;
+	struct prestera_acl *acl;
+	struct prestera_span *span;
 	struct list_head event_handlers;
 	struct notifier_block netdev_nb;
+	struct prestera_trap_data *trap_data;
 	char base_mac[ETH_ALEN];
 	struct list_head port_list;
 	rwlock_t port_list_lock;
@@ -165,6 +193,9 @@ struct prestera_switch {
 	u32 mtu_min;
 	u32 mtu_max;
 	u8 id;
+	struct prestera_lag *lags;
+	u8 lag_member_max;
+	u8 lag_max;
 };
 
 struct prestera_rxtx_params {
@@ -203,4 +234,10 @@ int prestera_port_pvid_set(struct prestera_port *port, u16 vid);
 
 bool prestera_netdev_check(const struct net_device *dev);
 
+bool prestera_port_is_lag_member(const struct prestera_port *port);
+
+struct prestera_lag *prestera_lag_by_id(struct prestera_switch *sw, u16 id);
+
+u16 prestera_port_lag_id(const struct prestera_port *port);
+
 #endif /* _PRESTERA_H_ */
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_acl.c b/drivers/net/ethernet/marvell/prestera/prestera_acl.c
new file mode 100644
index 000000000000..83c75ffb1a1c
--- /dev/null
+++ b/drivers/net/ethernet/marvell/prestera/prestera_acl.c
@@ -0,0 +1,376 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2020 Marvell International Ltd. All rights reserved */
+
+#include <linux/rhashtable.h>
+
+#include "prestera.h"
+#include "prestera_hw.h"
+#include "prestera_acl.h"
+#include "prestera_span.h"
+
+struct prestera_acl {
+	struct prestera_switch *sw;
+	struct list_head rules;
+};
+
+struct prestera_acl_ruleset {
+	struct rhashtable rule_ht;
+	struct prestera_switch *sw;
+	u16 id;
+};
+
+struct prestera_acl_rule {
+	struct rhash_head ht_node;
+	struct list_head list;
+	struct list_head match_list;
+	struct list_head action_list;
+	struct prestera_flow_block *block;
+	unsigned long cookie;
+	u32 priority;
+	u8 n_actions;
+	u8 n_matches;
+	u32 id;
+};
+
+static const struct rhashtable_params prestera_acl_rule_ht_params = {
+	.key_len = sizeof(unsigned long),
+	.key_offset = offsetof(struct prestera_acl_rule, cookie),
+	.head_offset = offsetof(struct prestera_acl_rule, ht_node),
+	.automatic_shrinking = true,
+};
+
+static struct prestera_acl_ruleset *
+prestera_acl_ruleset_create(struct prestera_switch *sw)
+{
+	struct prestera_acl_ruleset *ruleset;
+	int err;
+
+	ruleset = kzalloc(sizeof(*ruleset), GFP_KERNEL);
+	if (!ruleset)
+		return ERR_PTR(-ENOMEM);
+
+	err = rhashtable_init(&ruleset->rule_ht, &prestera_acl_rule_ht_params);
+	if (err)
+		goto err_rhashtable_init;
+
+	err = prestera_hw_acl_ruleset_create(sw, &ruleset->id);
+	if (err)
+		goto err_ruleset_create;
+
+	ruleset->sw = sw;
+
+	return ruleset;
+
+err_ruleset_create:
+	rhashtable_destroy(&ruleset->rule_ht);
+err_rhashtable_init:
+	kfree(ruleset);
+	return ERR_PTR(err);
+}
+
+static void prestera_acl_ruleset_destroy(struct prestera_acl_ruleset *ruleset)
+{
+	prestera_hw_acl_ruleset_del(ruleset->sw, ruleset->id);
+	rhashtable_destroy(&ruleset->rule_ht);
+	kfree(ruleset);
+}
+
+struct prestera_flow_block *
+prestera_acl_block_create(struct prestera_switch *sw, struct net *net)
+{
+	struct prestera_flow_block *block;
+
+	block = kzalloc(sizeof(*block), GFP_KERNEL);
+	if (!block)
+		return NULL;
+	INIT_LIST_HEAD(&block->binding_list);
+	block->net = net;
+	block->sw = sw;
+
+	block->ruleset = prestera_acl_ruleset_create(sw);
+	if (IS_ERR(block->ruleset)) {
+		kfree(block);
+		return NULL;
+	}
+
+	return block;
+}
+
+void prestera_acl_block_destroy(struct prestera_flow_block *block)
+{
+	prestera_acl_ruleset_destroy(block->ruleset);
+	WARN_ON(!list_empty(&block->binding_list));
+	kfree(block);
+}
+
+static struct prestera_flow_block_binding *
+prestera_acl_block_lookup(struct prestera_flow_block *block,
+			  struct prestera_port *port)
+{
+	struct prestera_flow_block_binding *binding;
+
+	list_for_each_entry(binding, &block->binding_list, list)
+		if (binding->port == port)
+			return binding;
+
+	return NULL;
+}
+
+int prestera_acl_block_bind(struct prestera_flow_block *block,
+			    struct prestera_port *port)
+{
+	struct prestera_flow_block_binding *binding;
+	int err;
+
+	if (WARN_ON(prestera_acl_block_lookup(block, port)))
+		return -EEXIST;
+
+	binding = kzalloc(sizeof(*binding), GFP_KERNEL);
+	if (!binding)
+		return -ENOMEM;
+	binding->span_id = PRESTERA_SPAN_INVALID_ID;
+	binding->port = port;
+
+	err = prestera_hw_acl_port_bind(port, block->ruleset->id);
+	if (err)
+		goto err_rules_bind;
+
+	list_add(&binding->list, &block->binding_list);
+	return 0;
+
+err_rules_bind:
+	kfree(binding);
+	return err;
+}
+
+int prestera_acl_block_unbind(struct prestera_flow_block *block,
+			      struct prestera_port *port)
+{
+	struct prestera_flow_block_binding *binding;
+
+	binding = prestera_acl_block_lookup(block, port);
+	if (!binding)
+		return -ENOENT;
+
+	list_del(&binding->list);
+
+	prestera_hw_acl_port_unbind(port, block->ruleset->id);
+
+	kfree(binding);
+	return 0;
+}
+
+struct prestera_acl_ruleset *
+prestera_acl_block_ruleset_get(struct prestera_flow_block *block)
+{
+	return block->ruleset;
+}
+
+u16 prestera_acl_rule_ruleset_id_get(const struct prestera_acl_rule *rule)
+{
+	return rule->block->ruleset->id;
+}
+
+struct net *prestera_acl_block_net(struct prestera_flow_block *block)
+{
+	return block->net;
+}
+
+struct prestera_switch *prestera_acl_block_sw(struct prestera_flow_block *block)
+{
+	return block->sw;
+}
+
+struct prestera_acl_rule *
+prestera_acl_rule_lookup(struct prestera_acl_ruleset *ruleset,
+			 unsigned long cookie)
+{
+	return rhashtable_lookup_fast(&ruleset->rule_ht, &cookie,
+				      prestera_acl_rule_ht_params);
+}
+
+struct prestera_acl_rule *
+prestera_acl_rule_create(struct prestera_flow_block *block,
+			 unsigned long cookie)
+{
+	struct prestera_acl_rule *rule;
+
+	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
+	if (!rule)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&rule->match_list);
+	INIT_LIST_HEAD(&rule->action_list);
+	rule->cookie = cookie;
+	rule->block = block;
+
+	return rule;
+}
+
+struct list_head *
+prestera_acl_rule_match_list_get(struct prestera_acl_rule *rule)
+{
+	return &rule->match_list;
+}
+
+struct list_head *
+prestera_acl_rule_action_list_get(struct prestera_acl_rule *rule)
+{
+	return &rule->action_list;
+}
+
+int prestera_acl_rule_action_add(struct prestera_acl_rule *rule,
+				 struct prestera_acl_rule_action_entry *entry)
+{
+	struct prestera_acl_rule_action_entry *a_entry;
+
+	a_entry = kmalloc(sizeof(*a_entry), GFP_KERNEL);
+	if (!a_entry)
+		return -ENOMEM;
+
+	memcpy(a_entry, entry, sizeof(*entry));
+	list_add(&a_entry->list, &rule->action_list);
+
+	rule->n_actions++;
+	return 0;
+}
+
+u8 prestera_acl_rule_action_len(struct prestera_acl_rule *rule)
+{
+	return rule->n_actions;
+}
+
+u32 prestera_acl_rule_priority_get(struct prestera_acl_rule *rule)
+{
+	return rule->priority;
+}
+
+void prestera_acl_rule_priority_set(struct prestera_acl_rule *rule,
+				    u32 priority)
+{
+	rule->priority = priority;
+}
+
+int prestera_acl_rule_match_add(struct prestera_acl_rule *rule,
+				struct prestera_acl_rule_match_entry *entry)
+{
+	struct prestera_acl_rule_match_entry *m_entry;
+
+	m_entry = kmalloc(sizeof(*m_entry), GFP_KERNEL);
+	if (!m_entry)
+		return -ENOMEM;
+
+	memcpy(m_entry, entry, sizeof(*entry));
+	list_add(&m_entry->list, &rule->match_list);
+
+	rule->n_matches++;
+	return 0;
+}
+
+u8 prestera_acl_rule_match_len(struct prestera_acl_rule *rule)
+{
+	return rule->n_matches;
+}
+
+void prestera_acl_rule_destroy(struct prestera_acl_rule *rule)
+{
+	struct prestera_acl_rule_action_entry *a_entry;
+	struct prestera_acl_rule_match_entry *m_entry;
+	struct list_head *pos, *n;
+
+	list_for_each_safe(pos, n, &rule->match_list) {
+		m_entry = list_entry(pos, typeof(*m_entry), list);
+		list_del(pos);
+		kfree(m_entry);
+	}
+
+	list_for_each_safe(pos, n, &rule->action_list) {
+		a_entry = list_entry(pos, typeof(*a_entry), list);
+		list_del(pos);
+		kfree(a_entry);
+	}
+
+	kfree(rule);
+}
+
+int prestera_acl_rule_add(struct prestera_switch *sw,
+			  struct prestera_acl_rule *rule)
+{
+	u32 rule_id;
+	int err;
+
+	/* try to add rule to hash table first */
+	err = rhashtable_insert_fast(&rule->block->ruleset->rule_ht,
+				     &rule->ht_node,
+				     prestera_acl_rule_ht_params);
+	if (err)
+		return err;
+
+	/* add rule to hw */
+	err = prestera_hw_acl_rule_add(sw, rule, &rule_id);
+	if (err)
+		goto err_rule_add;
+
+	rule->id = rule_id;
+
+	list_add_tail(&rule->list, &sw->acl->rules);
+
+	return 0;
+
+err_rule_add:
+	rhashtable_remove_fast(&rule->block->ruleset->rule_ht, &rule->ht_node,
+			       prestera_acl_rule_ht_params);
+	return err;
+}
+
+void prestera_acl_rule_del(struct prestera_switch *sw,
+			   struct prestera_acl_rule *rule)
+{
+	rhashtable_remove_fast(&rule->block->ruleset->rule_ht, &rule->ht_node,
+			       prestera_acl_rule_ht_params);
+	list_del(&rule->list);
+	prestera_hw_acl_rule_del(sw, rule->id);
+}
+
+int prestera_acl_rule_get_stats(struct prestera_switch *sw,
+				struct prestera_acl_rule *rule,
+				u64 *packets, u64 *bytes, u64 *last_use)
+{
+	u64 current_packets;
+	u64 current_bytes;
+	int err;
+
+	err = prestera_hw_acl_rule_stats_get(sw, rule->id, &current_packets,
+					     &current_bytes);
+	if (err)
+		return err;
+
+	*packets = current_packets;
+	*bytes = current_bytes;
+	*last_use = jiffies;
+
+	return 0;
+}
+
+int prestera_acl_init(struct prestera_switch *sw)
+{
+	struct prestera_acl *acl;
+
+	acl = kzalloc(sizeof(*acl), GFP_KERNEL);
+	if (!acl)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&acl->rules);
+	sw->acl = acl;
+	acl->sw = sw;
+
+	return 0;
+}
+
+void prestera_acl_fini(struct prestera_switch *sw)
+{
+	struct prestera_acl *acl = sw->acl;
+
+	WARN_ON(!list_empty(&acl->rules));
+	kfree(acl);
+}
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_acl.h b/drivers/net/ethernet/marvell/prestera/prestera_acl.h
new file mode 100644
index 000000000000..39b7869be659
--- /dev/null
+++ b/drivers/net/ethernet/marvell/prestera/prestera_acl.h
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2020 Marvell International Ltd. All rights reserved. */
+
+#ifndef _PRESTERA_ACL_H_
+#define _PRESTERA_ACL_H_
+
+enum prestera_acl_rule_match_entry_type {
+	PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_TYPE = 1,
+	PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_DMAC,
+	PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_SMAC,
+	PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_PROTO,
+	PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_PORT,
+	PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_SRC,
+	PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_DST,
+	PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_SRC,
+	PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_DST,
+	PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_RANGE_SRC,
+	PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_RANGE_DST,
+	PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_VLAN_ID,
+	PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_VLAN_TPID,
+	PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ICMP_TYPE,
+	PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ICMP_CODE
+};
+
+enum prestera_acl_rule_action {
+	PRESTERA_ACL_RULE_ACTION_ACCEPT,
+	PRESTERA_ACL_RULE_ACTION_DROP,
+	PRESTERA_ACL_RULE_ACTION_TRAP
+};
+
+struct prestera_switch;
+struct prestera_port;
+struct prestera_acl_rule;
+struct prestera_acl_ruleset;
+
+struct prestera_flow_block_binding {
+	struct list_head list;
+	struct prestera_port *port;
+	int span_id;
+};
+
+struct prestera_flow_block {
+	struct list_head binding_list;
+	struct prestera_switch *sw;
+	struct net *net;
+	struct prestera_acl_ruleset *ruleset;
+	struct flow_block_cb *block_cb;
+};
+
+struct prestera_acl_rule_action_entry {
+	struct list_head list;
+	enum prestera_acl_rule_action id;
+};
+
+struct prestera_acl_rule_match_entry {
+	struct list_head list;
+	enum prestera_acl_rule_match_entry_type type;
+	union {
+		struct {
+			u8 key;
+			u8 mask;
+		} u8;
+		struct {
+			u16 key;
+			u16 mask;
+		} u16;
+		struct {
+			u32 key;
+			u32 mask;
+		} u32;
+		struct {
+			u64 key;
+			u64 mask;
+		} u64;
+		struct {
+			u8 key[ETH_ALEN];
+			u8 mask[ETH_ALEN];
+		} mac;
+	} keymask;
+};
+
+int prestera_acl_init(struct prestera_switch *sw);
+void prestera_acl_fini(struct prestera_switch *sw);
+struct prestera_flow_block *
+prestera_acl_block_create(struct prestera_switch *sw, struct net *net);
+void prestera_acl_block_destroy(struct prestera_flow_block *block);
+struct net *prestera_acl_block_net(struct prestera_flow_block *block);
+struct prestera_switch *prestera_acl_block_sw(struct prestera_flow_block *block);
+int prestera_acl_block_bind(struct prestera_flow_block *block,
+			    struct prestera_port *port);
+int prestera_acl_block_unbind(struct prestera_flow_block *block,
+			      struct prestera_port *port);
+struct prestera_acl_ruleset *
+prestera_acl_block_ruleset_get(struct prestera_flow_block *block);
+struct prestera_acl_rule *
+prestera_acl_rule_create(struct prestera_flow_block *block,
+			 unsigned long cookie);
+u32 prestera_acl_rule_priority_get(struct prestera_acl_rule *rule);
+void prestera_acl_rule_priority_set(struct prestera_acl_rule *rule,
+				    u32 priority);
+u16 prestera_acl_rule_ruleset_id_get(const struct prestera_acl_rule *rule);
+struct list_head *
+prestera_acl_rule_action_list_get(struct prestera_acl_rule *rule);
+u8 prestera_acl_rule_action_len(struct prestera_acl_rule *rule);
+u8 prestera_acl_rule_match_len(struct prestera_acl_rule *rule);
+int prestera_acl_rule_action_add(struct prestera_acl_rule *rule,
+				 struct prestera_acl_rule_action_entry *entry);
+struct list_head *
+prestera_acl_rule_match_list_get(struct prestera_acl_rule *rule);
+int prestera_acl_rule_match_add(struct prestera_acl_rule *rule,
+				struct prestera_acl_rule_match_entry *entry);
+void prestera_acl_rule_destroy(struct prestera_acl_rule *rule);
+struct prestera_acl_rule *
+prestera_acl_rule_lookup(struct prestera_acl_ruleset *ruleset,
+			 unsigned long cookie);
+int prestera_acl_rule_add(struct prestera_switch *sw,
+			  struct prestera_acl_rule *rule);
+void prestera_acl_rule_del(struct prestera_switch *sw,
+			   struct prestera_acl_rule *rule);
+int prestera_acl_rule_get_stats(struct prestera_switch *sw,
+				struct prestera_acl_rule *rule,
+				u64 *packets, u64 *bytes, u64 *last_use);
+
+#endif /* _PRESTERA_ACL_H_ */
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c
index 94c185a0e2b8..d12e21db9fd6 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c
@@ -4,6 +4,352 @@
 #include <net/devlink.h>
 
 #include "prestera_devlink.h"
+#include "prestera_hw.h"
+
+/* All driver-specific traps must be documented in
+ * Documentation/networking/devlink/prestera.rst
+ */
+enum {
+	DEVLINK_PRESTERA_TRAP_ID_BASE = DEVLINK_TRAP_GENERIC_ID_MAX,
+	DEVLINK_PRESTERA_TRAP_ID_ARP_BC,
+	DEVLINK_PRESTERA_TRAP_ID_IS_IS,
+	DEVLINK_PRESTERA_TRAP_ID_OSPF,
+	DEVLINK_PRESTERA_TRAP_ID_IP_BC_MAC,
+	DEVLINK_PRESTERA_TRAP_ID_ROUTER_MC,
+	DEVLINK_PRESTERA_TRAP_ID_VRRP,
+	DEVLINK_PRESTERA_TRAP_ID_DHCP,
+	DEVLINK_PRESTERA_TRAP_ID_MAC_TO_ME,
+	DEVLINK_PRESTERA_TRAP_ID_IPV4_OPTIONS,
+	DEVLINK_PRESTERA_TRAP_ID_IP_DEFAULT_ROUTE,
+	DEVLINK_PRESTERA_TRAP_ID_IP_TO_ME,
+	DEVLINK_PRESTERA_TRAP_ID_IPV4_ICMP_REDIRECT,
+	DEVLINK_PRESTERA_TRAP_ID_ACL_CODE_0,
+	DEVLINK_PRESTERA_TRAP_ID_ACL_CODE_1,
+	DEVLINK_PRESTERA_TRAP_ID_ACL_CODE_2,
+	DEVLINK_PRESTERA_TRAP_ID_ACL_CODE_3,
+	DEVLINK_PRESTERA_TRAP_ID_ACL_CODE_4,
+	DEVLINK_PRESTERA_TRAP_ID_ACL_CODE_5,
+	DEVLINK_PRESTERA_TRAP_ID_ACL_CODE_6,
+	DEVLINK_PRESTERA_TRAP_ID_ACL_CODE_7,
+	DEVLINK_PRESTERA_TRAP_ID_BGP,
+	DEVLINK_PRESTERA_TRAP_ID_SSH,
+	DEVLINK_PRESTERA_TRAP_ID_TELNET,
+	DEVLINK_PRESTERA_TRAP_ID_ICMP,
+	DEVLINK_PRESTERA_TRAP_ID_MET_RED,
+	DEVLINK_PRESTERA_TRAP_ID_IP_SIP_IS_ZERO,
+	DEVLINK_PRESTERA_TRAP_ID_IP_UC_DIP_DA_MISMATCH,
+	DEVLINK_PRESTERA_TRAP_ID_ILLEGAL_IPV4_HDR,
+	DEVLINK_PRESTERA_TRAP_ID_ILLEGAL_IP_ADDR,
+	DEVLINK_PRESTERA_TRAP_ID_INVALID_SA,
+	DEVLINK_PRESTERA_TRAP_ID_LOCAL_PORT,
+	DEVLINK_PRESTERA_TRAP_ID_PORT_NO_VLAN,
+	DEVLINK_PRESTERA_TRAP_ID_RXDMA_DROP,
+};
+
+#define DEVLINK_PRESTERA_TRAP_NAME_ARP_BC \
+	"arp_bc"
+#define DEVLINK_PRESTERA_TRAP_NAME_IS_IS \
+	"is_is"
+#define DEVLINK_PRESTERA_TRAP_NAME_OSPF \
+	"ospf"
+#define DEVLINK_PRESTERA_TRAP_NAME_IP_BC_MAC \
+	"ip_bc_mac"
+#define DEVLINK_PRESTERA_TRAP_NAME_ROUTER_MC \
+	"router_mc"
+#define DEVLINK_PRESTERA_TRAP_NAME_VRRP \
+	"vrrp"
+#define DEVLINK_PRESTERA_TRAP_NAME_DHCP \
+	"dhcp"
+#define DEVLINK_PRESTERA_TRAP_NAME_MAC_TO_ME \
+	"mac_to_me"
+#define DEVLINK_PRESTERA_TRAP_NAME_IPV4_OPTIONS \
+	"ipv4_options"
+#define DEVLINK_PRESTERA_TRAP_NAME_IP_DEFAULT_ROUTE \
+	"ip_default_route"
+#define DEVLINK_PRESTERA_TRAP_NAME_IP_TO_ME \
+	"ip_to_me"
+#define DEVLINK_PRESTERA_TRAP_NAME_IPV4_ICMP_REDIRECT \
+	"ipv4_icmp_redirect"
+#define DEVLINK_PRESTERA_TRAP_NAME_ACL_CODE_0 \
+	"acl_code_0"
+#define DEVLINK_PRESTERA_TRAP_NAME_ACL_CODE_1 \
+	"acl_code_1"
+#define DEVLINK_PRESTERA_TRAP_NAME_ACL_CODE_2 \
+	"acl_code_2"
+#define DEVLINK_PRESTERA_TRAP_NAME_ACL_CODE_3 \
+	"acl_code_3"
+#define DEVLINK_PRESTERA_TRAP_NAME_ACL_CODE_4 \
+	"acl_code_4"
+#define DEVLINK_PRESTERA_TRAP_NAME_ACL_CODE_5 \
+	"acl_code_5"
+#define DEVLINK_PRESTERA_TRAP_NAME_ACL_CODE_6 \
+	"acl_code_6"
+#define DEVLINK_PRESTERA_TRAP_NAME_ACL_CODE_7 \
+	"acl_code_7"
+#define DEVLINK_PRESTERA_TRAP_NAME_BGP \
+	"bgp"
+#define DEVLINK_PRESTERA_TRAP_NAME_SSH \
+	"ssh"
+#define DEVLINK_PRESTERA_TRAP_NAME_TELNET \
+	"telnet"
+#define DEVLINK_PRESTERA_TRAP_NAME_ICMP \
+	"icmp"
+#define DEVLINK_PRESTERA_TRAP_NAME_RXDMA_DROP \
+	"rxdma_drop"
+#define DEVLINK_PRESTERA_TRAP_NAME_PORT_NO_VLAN \
+	"port_no_vlan"
+#define DEVLINK_PRESTERA_TRAP_NAME_LOCAL_PORT \
+	"local_port"
+#define DEVLINK_PRESTERA_TRAP_NAME_INVALID_SA \
+	"invalid_sa"
+#define DEVLINK_PRESTERA_TRAP_NAME_ILLEGAL_IP_ADDR \
+	"illegal_ip_addr"
+#define DEVLINK_PRESTERA_TRAP_NAME_ILLEGAL_IPV4_HDR \
+	"illegal_ipv4_hdr"
+#define DEVLINK_PRESTERA_TRAP_NAME_IP_UC_DIP_DA_MISMATCH \
+	"ip_uc_dip_da_mismatch"
+#define DEVLINK_PRESTERA_TRAP_NAME_IP_SIP_IS_ZERO \
+	"ip_sip_is_zero"
+#define DEVLINK_PRESTERA_TRAP_NAME_MET_RED \
+	"met_red"
+
+struct prestera_trap {
+	struct devlink_trap trap;
+	u8 cpu_code;
+};
+
+struct prestera_trap_item {
+	enum devlink_trap_action action;
+	void *trap_ctx;
+};
+
+struct prestera_trap_data {
+	struct prestera_switch *sw;
+	struct prestera_trap_item *trap_items_arr;
+	u32 traps_count;
+};
+
+#define PRESTERA_TRAP_METADATA DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT
+
+#define PRESTERA_TRAP_CONTROL(_id, _group_id, _action)			      \
+	DEVLINK_TRAP_GENERIC(CONTROL, _action, _id,			      \
+			     DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id,	      \
+			     PRESTERA_TRAP_METADATA)
+
+#define PRESTERA_TRAP_DRIVER_CONTROL(_id, _group_id)			      \
+	DEVLINK_TRAP_DRIVER(CONTROL, TRAP, DEVLINK_PRESTERA_TRAP_ID_##_id,    \
+			    DEVLINK_PRESTERA_TRAP_NAME_##_id,		      \
+			    DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id,	      \
+			    PRESTERA_TRAP_METADATA)
+
+#define PRESTERA_TRAP_EXCEPTION(_id, _group_id)				      \
+	DEVLINK_TRAP_GENERIC(EXCEPTION, TRAP, _id,			      \
+			     DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id,	      \
+			     PRESTERA_TRAP_METADATA)
+
+#define PRESTERA_TRAP_DRIVER_EXCEPTION(_id, _group_id)			      \
+	DEVLINK_TRAP_DRIVER(EXCEPTION, TRAP, DEVLINK_PRESTERA_TRAP_ID_##_id,  \
+			    DEVLINK_PRESTERA_TRAP_NAME_##_id,		      \
+			    DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id,	      \
+			    PRESTERA_TRAP_METADATA)
+
+#define PRESTERA_TRAP_DRIVER_DROP(_id, _group_id)			      \
+	DEVLINK_TRAP_DRIVER(DROP, DROP, DEVLINK_PRESTERA_TRAP_ID_##_id,	      \
+			    DEVLINK_PRESTERA_TRAP_NAME_##_id,		      \
+			    DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id,	      \
+			    PRESTERA_TRAP_METADATA)
+
+static const struct devlink_trap_group prestera_trap_groups_arr[] = {
+	/* No policer is associated with following groups (policerid == 0)*/
+	DEVLINK_TRAP_GROUP_GENERIC(L2_DROPS, 0),
+	DEVLINK_TRAP_GROUP_GENERIC(L3_DROPS, 0),
+	DEVLINK_TRAP_GROUP_GENERIC(L3_EXCEPTIONS, 0),
+	DEVLINK_TRAP_GROUP_GENERIC(NEIGH_DISCOVERY, 0),
+	DEVLINK_TRAP_GROUP_GENERIC(ACL_TRAP, 0),
+	DEVLINK_TRAP_GROUP_GENERIC(ACL_DROPS, 0),
+	DEVLINK_TRAP_GROUP_GENERIC(ACL_SAMPLE, 0),
+	DEVLINK_TRAP_GROUP_GENERIC(OSPF, 0),
+	DEVLINK_TRAP_GROUP_GENERIC(STP, 0),
+	DEVLINK_TRAP_GROUP_GENERIC(LACP, 0),
+	DEVLINK_TRAP_GROUP_GENERIC(LLDP, 0),
+	DEVLINK_TRAP_GROUP_GENERIC(VRRP, 0),
+	DEVLINK_TRAP_GROUP_GENERIC(DHCP, 0),
+	DEVLINK_TRAP_GROUP_GENERIC(BGP, 0),
+	DEVLINK_TRAP_GROUP_GENERIC(LOCAL_DELIVERY, 0),
+	DEVLINK_TRAP_GROUP_GENERIC(BUFFER_DROPS, 0),
+};
+
+/* Initialize trap list, as well as associate CPU code with them. */
+static struct prestera_trap prestera_trap_items_arr[] = {
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(ARP_BC, NEIGH_DISCOVERY),
+		.cpu_code = 5,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(IS_IS, LOCAL_DELIVERY),
+		.cpu_code = 13,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(OSPF, OSPF),
+		.cpu_code = 16,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(IP_BC_MAC, LOCAL_DELIVERY),
+		.cpu_code = 19,
+	},
+	{
+		.trap = PRESTERA_TRAP_CONTROL(STP, STP, TRAP),
+		.cpu_code = 26,
+	},
+	{
+		.trap = PRESTERA_TRAP_CONTROL(LACP, LACP, TRAP),
+		.cpu_code = 27,
+	},
+	{
+		.trap = PRESTERA_TRAP_CONTROL(LLDP, LLDP, TRAP),
+		.cpu_code = 28,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(ROUTER_MC, LOCAL_DELIVERY),
+		.cpu_code = 29,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(VRRP, VRRP),
+		.cpu_code = 30,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(DHCP, DHCP),
+		.cpu_code = 33,
+	},
+	{
+		.trap = PRESTERA_TRAP_EXCEPTION(MTU_ERROR, L3_EXCEPTIONS),
+		.cpu_code = 63,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(MAC_TO_ME, LOCAL_DELIVERY),
+		.cpu_code = 65,
+	},
+	{
+		.trap = PRESTERA_TRAP_EXCEPTION(TTL_ERROR, L3_EXCEPTIONS),
+		.cpu_code = 133,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_EXCEPTION(IPV4_OPTIONS,
+						       L3_EXCEPTIONS),
+		.cpu_code = 141,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(IP_DEFAULT_ROUTE,
+						     LOCAL_DELIVERY),
+		.cpu_code = 160,
+	},
+	{
+		.trap = PRESTERA_TRAP_CONTROL(LOCAL_ROUTE, LOCAL_DELIVERY,
+					      TRAP),
+		.cpu_code = 161,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_EXCEPTION(IPV4_ICMP_REDIRECT,
+						       L3_EXCEPTIONS),
+		.cpu_code = 180,
+	},
+	{
+		.trap = PRESTERA_TRAP_CONTROL(ARP_RESPONSE, NEIGH_DISCOVERY,
+					      TRAP),
+		.cpu_code = 188,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(ACL_CODE_0, ACL_TRAP),
+		.cpu_code = 192,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(ACL_CODE_1, ACL_TRAP),
+		.cpu_code = 193,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(ACL_CODE_2, ACL_TRAP),
+		.cpu_code = 194,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(ACL_CODE_3, ACL_TRAP),
+		.cpu_code = 195,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(ACL_CODE_4, ACL_TRAP),
+		.cpu_code = 196,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(ACL_CODE_5, ACL_TRAP),
+		.cpu_code = 197,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(ACL_CODE_6, ACL_TRAP),
+		.cpu_code = 198,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(ACL_CODE_7, ACL_TRAP),
+		.cpu_code = 199,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(BGP, BGP),
+		.cpu_code = 206,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(SSH, LOCAL_DELIVERY),
+		.cpu_code = 207,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(TELNET, LOCAL_DELIVERY),
+		.cpu_code = 208,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_CONTROL(ICMP, LOCAL_DELIVERY),
+		.cpu_code = 209,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_DROP(RXDMA_DROP, BUFFER_DROPS),
+		.cpu_code = 37,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_DROP(PORT_NO_VLAN, L2_DROPS),
+		.cpu_code = 39,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_DROP(LOCAL_PORT, L2_DROPS),
+		.cpu_code = 56,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_DROP(INVALID_SA, L2_DROPS),
+		.cpu_code = 60,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_DROP(ILLEGAL_IP_ADDR, L3_DROPS),
+		.cpu_code = 136,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_DROP(ILLEGAL_IPV4_HDR, L3_DROPS),
+		.cpu_code = 137,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_DROP(IP_UC_DIP_DA_MISMATCH,
+						  L3_DROPS),
+		.cpu_code = 138,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_DROP(IP_SIP_IS_ZERO, L3_DROPS),
+		.cpu_code = 145,
+	},
+	{
+		.trap = PRESTERA_TRAP_DRIVER_DROP(MET_RED, BUFFER_DROPS),
+		.cpu_code = 185,
+	},
+};
+
+static void prestera_devlink_traps_fini(struct prestera_switch *sw);
+
+static int prestera_drop_counter_get(struct devlink *devlink,
+				     const struct devlink_trap *trap,
+				     u64 *p_drops);
 
 static int prestera_dl_info_get(struct devlink *dl,
 				struct devlink_info_req *req,
@@ -27,8 +373,21 @@ static int prestera_dl_info_get(struct devlink *dl,
 					       buf);
 }
 
+static int prestera_trap_init(struct devlink *devlink,
+			      const struct devlink_trap *trap, void *trap_ctx);
+
+static int prestera_trap_action_set(struct devlink *devlink,
+				    const struct devlink_trap *trap,
+				    enum devlink_trap_action action,
+				    struct netlink_ext_ack *extack);
+
+static int prestera_devlink_traps_register(struct prestera_switch *sw);
+
 static const struct devlink_ops prestera_dl_ops = {
 	.info_get = prestera_dl_info_get,
+	.trap_init = prestera_trap_init,
+	.trap_action_set = prestera_trap_action_set,
+	.trap_drop_counter_get = prestera_drop_counter_get,
 };
 
 struct prestera_switch *prestera_devlink_alloc(void)
@@ -53,17 +412,32 @@ int prestera_devlink_register(struct prestera_switch *sw)
 	int err;
 
 	err = devlink_register(dl, sw->dev->dev);
-	if (err)
+	if (err) {
 		dev_err(prestera_dev(sw), "devlink_register failed: %d\n", err);
+		return err;
+	}
 
-	return err;
+	err = prestera_devlink_traps_register(sw);
+	if (err) {
+		devlink_unregister(dl);
+		dev_err(sw->dev->dev, "devlink_traps_register failed: %d\n",
+			err);
+		return err;
+	}
+
+	return 0;
 }
 
 void prestera_devlink_unregister(struct prestera_switch *sw)
 {
+	struct prestera_trap_data *trap_data = sw->trap_data;
 	struct devlink *dl = priv_to_devlink(sw);
 
+	prestera_devlink_traps_fini(sw);
 	devlink_unregister(dl);
+
+	kfree(trap_data->trap_items_arr);
+	kfree(trap_data);
 }
 
 int prestera_devlink_port_register(struct prestera_port *port)
@@ -110,3 +484,155 @@ struct devlink_port *prestera_devlink_get_port(struct net_device *dev)
 
 	return &port->dl_port;
 }
+
+static int prestera_devlink_traps_register(struct prestera_switch *sw)
+{
+	const u32 groups_count = ARRAY_SIZE(prestera_trap_groups_arr);
+	const u32 traps_count = ARRAY_SIZE(prestera_trap_items_arr);
+	struct devlink *devlink = priv_to_devlink(sw);
+	struct prestera_trap_data *trap_data;
+	struct prestera_trap *prestera_trap;
+	int err, i;
+
+	trap_data = kzalloc(sizeof(*trap_data), GFP_KERNEL);
+	if (!trap_data)
+		return -ENOMEM;
+
+	trap_data->trap_items_arr = kcalloc(traps_count,
+					    sizeof(struct prestera_trap_item),
+					    GFP_KERNEL);
+	if (!trap_data->trap_items_arr) {
+		err = -ENOMEM;
+		goto err_trap_items_alloc;
+	}
+
+	trap_data->sw = sw;
+	trap_data->traps_count = traps_count;
+	sw->trap_data = trap_data;
+
+	err = devlink_trap_groups_register(devlink, prestera_trap_groups_arr,
+					   groups_count);
+	if (err)
+		goto err_groups_register;
+
+	for (i = 0; i < traps_count; i++) {
+		prestera_trap = &prestera_trap_items_arr[i];
+		err = devlink_traps_register(devlink, &prestera_trap->trap, 1,
+					     sw);
+		if (err)
+			goto err_trap_register;
+	}
+
+	return 0;
+
+err_trap_register:
+	for (i--; i >= 0; i--) {
+		prestera_trap = &prestera_trap_items_arr[i];
+		devlink_traps_unregister(devlink, &prestera_trap->trap, 1);
+	}
+err_groups_register:
+	kfree(trap_data->trap_items_arr);
+err_trap_items_alloc:
+	kfree(trap_data);
+	return err;
+}
+
+static struct prestera_trap_item *
+prestera_get_trap_item_by_cpu_code(struct prestera_switch *sw, u8 cpu_code)
+{
+	struct prestera_trap_data *trap_data = sw->trap_data;
+	struct prestera_trap *prestera_trap;
+	int i;
+
+	for (i = 0; i < trap_data->traps_count; i++) {
+		prestera_trap = &prestera_trap_items_arr[i];
+		if (cpu_code == prestera_trap->cpu_code)
+			return &trap_data->trap_items_arr[i];
+	}
+
+	return NULL;
+}
+
+void prestera_devlink_trap_report(struct prestera_port *port,
+				  struct sk_buff *skb, u8 cpu_code)
+{
+	struct prestera_trap_item *trap_item;
+	struct devlink *devlink;
+
+	devlink = port->dl_port.devlink;
+
+	trap_item = prestera_get_trap_item_by_cpu_code(port->sw, cpu_code);
+	if (unlikely(!trap_item))
+		return;
+
+	devlink_trap_report(devlink, skb, trap_item->trap_ctx,
+			    &port->dl_port, NULL);
+}
+
+static struct prestera_trap_item *
+prestera_devlink_trap_item_lookup(struct prestera_switch *sw, u16 trap_id)
+{
+	struct prestera_trap_data *trap_data = sw->trap_data;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(prestera_trap_items_arr); i++) {
+		if (prestera_trap_items_arr[i].trap.id == trap_id)
+			return &trap_data->trap_items_arr[i];
+	}
+
+	return NULL;
+}
+
+static int prestera_trap_init(struct devlink *devlink,
+			      const struct devlink_trap *trap, void *trap_ctx)
+{
+	struct prestera_switch *sw = devlink_priv(devlink);
+	struct prestera_trap_item *trap_item;
+
+	trap_item = prestera_devlink_trap_item_lookup(sw, trap->id);
+	if (WARN_ON(!trap_item))
+		return -EINVAL;
+
+	trap_item->trap_ctx = trap_ctx;
+	trap_item->action = trap->init_action;
+
+	return 0;
+}
+
+static int prestera_trap_action_set(struct devlink *devlink,
+				    const struct devlink_trap *trap,
+				    enum devlink_trap_action action,
+				    struct netlink_ext_ack *extack)
+{
+	/* Currently, driver does not support trap action altering */
+	return -EOPNOTSUPP;
+}
+
+static int prestera_drop_counter_get(struct devlink *devlink,
+				     const struct devlink_trap *trap,
+				     u64 *p_drops)
+{
+	struct prestera_switch *sw = devlink_priv(devlink);
+	enum prestera_hw_cpu_code_cnt_t cpu_code_type =
+		PRESTERA_HW_CPU_CODE_CNT_TYPE_DROP;
+	struct prestera_trap *prestera_trap =
+		container_of(trap, struct prestera_trap, trap);
+
+	return prestera_hw_cpu_code_counters_get(sw, prestera_trap->cpu_code,
+						 cpu_code_type, p_drops);
+}
+
+static void prestera_devlink_traps_fini(struct prestera_switch *sw)
+{
+	struct devlink *dl = priv_to_devlink(sw);
+	const struct devlink_trap *trap;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(prestera_trap_items_arr); ++i) {
+		trap = &prestera_trap_items_arr[i].trap;
+		devlink_traps_unregister(dl, trap, 1);
+	}
+
+	devlink_trap_groups_unregister(dl, prestera_trap_groups_arr,
+				       ARRAY_SIZE(prestera_trap_groups_arr));
+}
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.h b/drivers/net/ethernet/marvell/prestera/prestera_devlink.h
index 51bee9f75415..5d73aa9db897 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.h
+++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.h
@@ -20,4 +20,7 @@ void prestera_devlink_port_clear(struct prestera_port *port);
 
 struct devlink_port *prestera_devlink_get_port(struct net_device *dev);
 
+void prestera_devlink_trap_report(struct prestera_port *port,
+				  struct sk_buff *skb, u8 cpu_code);
+
 #endif /* _PRESTERA_DEVLINK_H_ */
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_dsa.c b/drivers/net/ethernet/marvell/prestera/prestera_dsa.c
index a5e01c7a307b..b7e89c0ca5c0 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_dsa.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_dsa.c
@@ -19,6 +19,7 @@
 #define PRESTERA_DSA_W1_EXT_BIT		BIT(31)
 #define PRESTERA_DSA_W1_CFI_BIT		BIT(30)
 #define PRESTERA_DSA_W1_PORT_NUM	GENMASK(11, 10)
+#define PRESTERA_DSA_W1_MASK_CPU_CODE	GENMASK(7, 0)
 
 #define PRESTERA_DSA_W2_EXT_BIT		BIT(31)
 #define PRESTERA_DSA_W2_PORT_NUM	BIT(20)
@@ -74,6 +75,8 @@ int prestera_dsa_parse(struct prestera_dsa *dsa, const u8 *dsa_buf)
 			(FIELD_GET(PRESTERA_DSA_W1_PORT_NUM, words[1]) << 5) |
 			(FIELD_GET(PRESTERA_DSA_W2_PORT_NUM, words[2]) << 7);
 
+	dsa->cpu_code = FIELD_GET(PRESTERA_DSA_W1_MASK_CPU_CODE, words[1]);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_dsa.h b/drivers/net/ethernet/marvell/prestera/prestera_dsa.h
index 67018629bdd2..c99342f475cf 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_dsa.h
+++ b/drivers/net/ethernet/marvell/prestera/prestera_dsa.h
@@ -27,6 +27,7 @@ struct prestera_dsa {
 	struct prestera_dsa_vlan vlan;
 	u32 hw_dev_num;
 	u32 port_num;
+	u8 cpu_code;
 };
 
 int prestera_dsa_parse(struct prestera_dsa *dsa, const u8 *dsa_buf);
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flow.c b/drivers/net/ethernet/marvell/prestera/prestera_flow.c
new file mode 100644
index 000000000000..c9891e968259
--- /dev/null
+++ b/drivers/net/ethernet/marvell/prestera/prestera_flow.c
@@ -0,0 +1,194 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2020 Marvell International Ltd. All rights reserved */
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+
+#include "prestera.h"
+#include "prestera_acl.h"
+#include "prestera_flow.h"
+#include "prestera_span.h"
+#include "prestera_flower.h"
+
+static LIST_HEAD(prestera_block_cb_list);
+
+static int prestera_flow_block_mall_cb(struct prestera_flow_block *block,
+				       struct tc_cls_matchall_offload *f)
+{
+	switch (f->command) {
+	case TC_CLSMATCHALL_REPLACE:
+		return prestera_span_replace(block, f);
+	case TC_CLSMATCHALL_DESTROY:
+		prestera_span_destroy(block);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int prestera_flow_block_flower_cb(struct prestera_flow_block *block,
+					 struct flow_cls_offload *f)
+{
+	if (f->common.chain_index != 0)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case FLOW_CLS_REPLACE:
+		return prestera_flower_replace(block, f);
+	case FLOW_CLS_DESTROY:
+		prestera_flower_destroy(block, f);
+		return 0;
+	case FLOW_CLS_STATS:
+		return prestera_flower_stats(block, f);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int prestera_flow_block_cb(enum tc_setup_type type,
+				  void *type_data, void *cb_priv)
+{
+	struct prestera_flow_block *block = cb_priv;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return prestera_flow_block_flower_cb(block, type_data);
+	case TC_SETUP_CLSMATCHALL:
+		return prestera_flow_block_mall_cb(block, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void prestera_flow_block_release(void *cb_priv)
+{
+	struct prestera_flow_block *block = cb_priv;
+
+	prestera_acl_block_destroy(block);
+}
+
+static struct prestera_flow_block *
+prestera_flow_block_get(struct prestera_switch *sw,
+			struct flow_block_offload *f,
+			bool *register_block)
+{
+	struct prestera_flow_block *block;
+	struct flow_block_cb *block_cb;
+
+	block_cb = flow_block_cb_lookup(f->block,
+					prestera_flow_block_cb, sw);
+	if (!block_cb) {
+		block = prestera_acl_block_create(sw, f->net);
+		if (!block)
+			return ERR_PTR(-ENOMEM);
+
+		block_cb = flow_block_cb_alloc(prestera_flow_block_cb,
+					       sw, block,
+					       prestera_flow_block_release);
+		if (IS_ERR(block_cb)) {
+			prestera_acl_block_destroy(block);
+			return ERR_CAST(block_cb);
+		}
+
+		block->block_cb = block_cb;
+		*register_block = true;
+	} else {
+		block = flow_block_cb_priv(block_cb);
+		*register_block = false;
+	}
+
+	flow_block_cb_incref(block_cb);
+
+	return block;
+}
+
+static void prestera_flow_block_put(struct prestera_flow_block *block)
+{
+	struct flow_block_cb *block_cb = block->block_cb;
+
+	if (flow_block_cb_decref(block_cb))
+		return;
+
+	flow_block_cb_free(block_cb);
+	prestera_acl_block_destroy(block);
+}
+
+static int prestera_setup_flow_block_bind(struct prestera_port *port,
+					  struct flow_block_offload *f)
+{
+	struct prestera_switch *sw = port->sw;
+	struct prestera_flow_block *block;
+	struct flow_block_cb *block_cb;
+	bool register_block;
+	int err;
+
+	block = prestera_flow_block_get(sw, f, &register_block);
+	if (IS_ERR(block))
+		return PTR_ERR(block);
+
+	block_cb = block->block_cb;
+
+	err = prestera_acl_block_bind(block, port);
+	if (err)
+		goto err_block_bind;
+
+	if (register_block) {
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &prestera_block_cb_list);
+	}
+
+	port->flow_block = block;
+	return 0;
+
+err_block_bind:
+	prestera_flow_block_put(block);
+
+	return err;
+}
+
+static void prestera_setup_flow_block_unbind(struct prestera_port *port,
+					     struct flow_block_offload *f)
+{
+	struct prestera_switch *sw = port->sw;
+	struct prestera_flow_block *block;
+	struct flow_block_cb *block_cb;
+	int err;
+
+	block_cb = flow_block_cb_lookup(f->block, prestera_flow_block_cb, sw);
+	if (!block_cb)
+		return;
+
+	block = flow_block_cb_priv(block_cb);
+
+	prestera_span_destroy(block);
+
+	err = prestera_acl_block_unbind(block, port);
+	if (err)
+		goto error;
+
+	if (!flow_block_cb_decref(block_cb)) {
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
+	}
+error:
+	port->flow_block = NULL;
+}
+
+int prestera_flow_block_setup(struct prestera_port *port,
+			      struct flow_block_offload *f)
+{
+	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	f->driver_block_list = &prestera_block_cb_list;
+
+	switch (f->command) {
+	case FLOW_BLOCK_BIND:
+		return prestera_setup_flow_block_bind(port, f);
+	case FLOW_BLOCK_UNBIND:
+		prestera_setup_flow_block_unbind(port, f);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flow.h b/drivers/net/ethernet/marvell/prestera/prestera_flow.h
new file mode 100644
index 000000000000..467c7038cace
--- /dev/null
+++ b/drivers/net/ethernet/marvell/prestera/prestera_flow.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2020 Marvell International Ltd. All rights reserved. */
+
+#ifndef _PRESTERA_FLOW_H_
+#define _PRESTERA_FLOW_H_
+
+#include <net/flow_offload.h>
+
+struct prestera_port;
+
+int prestera_flow_block_setup(struct prestera_port *port,
+			      struct flow_block_offload *f);
+
+#endif /* _PRESTERA_FLOW_H_ */
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flower.c b/drivers/net/ethernet/marvell/prestera/prestera_flower.c
new file mode 100644
index 000000000000..e571ba09ec08
--- /dev/null
+++ b/drivers/net/ethernet/marvell/prestera/prestera_flower.c
@@ -0,0 +1,359 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2020 Marvell International Ltd. All rights reserved */
+
+#include "prestera.h"
+#include "prestera_acl.h"
+#include "prestera_flower.h"
+
+static int prestera_flower_parse_actions(struct prestera_flow_block *block,
+					 struct prestera_acl_rule *rule,
+					 struct flow_action *flow_action,
+					 struct netlink_ext_ack *extack)
+{
+	struct prestera_acl_rule_action_entry a_entry;
+	const struct flow_action_entry *act;
+	int err, i;
+
+	if (!flow_action_has_entries(flow_action))
+		return 0;
+
+	flow_action_for_each(i, act, flow_action) {
+		memset(&a_entry, 0, sizeof(a_entry));
+
+		switch (act->id) {
+		case FLOW_ACTION_ACCEPT:
+			a_entry.id = PRESTERA_ACL_RULE_ACTION_ACCEPT;
+			break;
+		case FLOW_ACTION_DROP:
+			a_entry.id = PRESTERA_ACL_RULE_ACTION_DROP;
+			break;
+		case FLOW_ACTION_TRAP:
+			a_entry.id = PRESTERA_ACL_RULE_ACTION_TRAP;
+			break;
+		default:
+			NL_SET_ERR_MSG_MOD(extack, "Unsupported action");
+			pr_err("Unsupported action\n");
+			return -EOPNOTSUPP;
+		}
+
+		err = prestera_acl_rule_action_add(rule, &a_entry);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int prestera_flower_parse_meta(struct prestera_acl_rule *rule,
+				      struct flow_cls_offload *f,
+				      struct prestera_flow_block *block)
+{
+	struct flow_rule *f_rule = flow_cls_offload_flow_rule(f);
+	struct prestera_acl_rule_match_entry m_entry = {0};
+	struct net_device *ingress_dev;
+	struct flow_match_meta match;
+	struct prestera_port *port;
+
+	flow_rule_match_meta(f_rule, &match);
+	if (match.mask->ingress_ifindex != 0xFFFFFFFF) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "Unsupported ingress ifindex mask");
+		return -EINVAL;
+	}
+
+	ingress_dev = __dev_get_by_index(prestera_acl_block_net(block),
+					 match.key->ingress_ifindex);
+	if (!ingress_dev) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "Can't find specified ingress port to match on");
+		return -EINVAL;
+	}
+
+	if (!prestera_netdev_check(ingress_dev)) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "Can't match on switchdev ingress port");
+		return -EINVAL;
+	}
+	port = netdev_priv(ingress_dev);
+
+	m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_PORT;
+	m_entry.keymask.u64.key = port->hw_id | ((u64)port->dev_id << 32);
+	m_entry.keymask.u64.mask = ~(u64)0;
+
+	return prestera_acl_rule_match_add(rule, &m_entry);
+}
+
+static int prestera_flower_parse(struct prestera_flow_block *block,
+				 struct prestera_acl_rule *rule,
+				 struct flow_cls_offload *f)
+{
+	struct flow_rule *f_rule = flow_cls_offload_flow_rule(f);
+	struct flow_dissector *dissector = f_rule->match.dissector;
+	struct prestera_acl_rule_match_entry m_entry;
+	u16 n_proto_mask = 0;
+	u16 n_proto_key = 0;
+	u16 addr_type = 0;
+	u8 ip_proto = 0;
+	int err;
+
+	if (dissector->used_keys &
+	    ~(BIT(FLOW_DISSECTOR_KEY_META) |
+	      BIT(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT(FLOW_DISSECTOR_KEY_ICMP) |
+	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT(FLOW_DISSECTOR_KEY_VLAN))) {
+		NL_SET_ERR_MSG_MOD(f->common.extack, "Unsupported key");
+		return -EOPNOTSUPP;
+	}
+
+	prestera_acl_rule_priority_set(rule, f->common.prio);
+
+	if (flow_rule_match_key(f_rule, FLOW_DISSECTOR_KEY_META)) {
+		err = prestera_flower_parse_meta(rule, f, block);
+		if (err)
+			return err;
+	}
+
+	if (flow_rule_match_key(f_rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
+
+		flow_rule_match_control(f_rule, &match);
+		addr_type = match.key->addr_type;
+	}
+
+	if (flow_rule_match_key(f_rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
+
+		flow_rule_match_basic(f_rule, &match);
+		n_proto_key = ntohs(match.key->n_proto);
+		n_proto_mask = ntohs(match.mask->n_proto);
+
+		if (n_proto_key == ETH_P_ALL) {
+			n_proto_key = 0;
+			n_proto_mask = 0;
+		}
+
+		/* add eth type key,mask */
+		memset(&m_entry, 0, sizeof(m_entry));
+		m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_TYPE;
+		m_entry.keymask.u16.key = n_proto_key;
+		m_entry.keymask.u16.mask = n_proto_mask;
+		err = prestera_acl_rule_match_add(rule, &m_entry);
+		if (err)
+			return err;
+
+		/* add ip proto key,mask */
+		memset(&m_entry, 0, sizeof(m_entry));
+		m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_PROTO;
+		m_entry.keymask.u8.key = match.key->ip_proto;
+		m_entry.keymask.u8.mask = match.mask->ip_proto;
+		err = prestera_acl_rule_match_add(rule, &m_entry);
+		if (err)
+			return err;
+
+		ip_proto = match.key->ip_proto;
+	}
+
+	if (flow_rule_match_key(f_rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
+
+		flow_rule_match_eth_addrs(f_rule, &match);
+
+		/* add ethernet dst key,mask */
+		memset(&m_entry, 0, sizeof(m_entry));
+		m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_DMAC;
+		memcpy(&m_entry.keymask.mac.key,
+		       &match.key->dst, sizeof(match.key->dst));
+		memcpy(&m_entry.keymask.mac.mask,
+		       &match.mask->dst, sizeof(match.mask->dst));
+		err = prestera_acl_rule_match_add(rule, &m_entry);
+		if (err)
+			return err;
+
+		/* add ethernet src key,mask */
+		memset(&m_entry, 0, sizeof(m_entry));
+		m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_SMAC;
+		memcpy(&m_entry.keymask.mac.key,
+		       &match.key->src, sizeof(match.key->src));
+		memcpy(&m_entry.keymask.mac.mask,
+		       &match.mask->src, sizeof(match.mask->src));
+		err = prestera_acl_rule_match_add(rule, &m_entry);
+		if (err)
+			return err;
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+		struct flow_match_ipv4_addrs match;
+
+		flow_rule_match_ipv4_addrs(f_rule, &match);
+
+		memset(&m_entry, 0, sizeof(m_entry));
+		m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_SRC;
+		memcpy(&m_entry.keymask.u32.key,
+		       &match.key->src, sizeof(match.key->src));
+		memcpy(&m_entry.keymask.u32.mask,
+		       &match.mask->src, sizeof(match.mask->src));
+		err = prestera_acl_rule_match_add(rule, &m_entry);
+		if (err)
+			return err;
+
+		memset(&m_entry, 0, sizeof(m_entry));
+		m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_DST;
+		memcpy(&m_entry.keymask.u32.key,
+		       &match.key->dst, sizeof(match.key->dst));
+		memcpy(&m_entry.keymask.u32.mask,
+		       &match.mask->dst, sizeof(match.mask->dst));
+		err = prestera_acl_rule_match_add(rule, &m_entry);
+		if (err)
+			return err;
+	}
+
+	if (flow_rule_match_key(f_rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
+
+		if (ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) {
+			NL_SET_ERR_MSG_MOD
+			    (f->common.extack,
+			     "Only UDP and TCP keys are supported");
+			return -EINVAL;
+		}
+
+		flow_rule_match_ports(f_rule, &match);
+
+		memset(&m_entry, 0, sizeof(m_entry));
+		m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_SRC;
+		m_entry.keymask.u16.key = ntohs(match.key->src);
+		m_entry.keymask.u16.mask = ntohs(match.mask->src);
+		err = prestera_acl_rule_match_add(rule, &m_entry);
+		if (err)
+			return err;
+
+		memset(&m_entry, 0, sizeof(m_entry));
+		m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_DST;
+		m_entry.keymask.u16.key = ntohs(match.key->dst);
+		m_entry.keymask.u16.mask = ntohs(match.mask->dst);
+		err = prestera_acl_rule_match_add(rule, &m_entry);
+		if (err)
+			return err;
+	}
+
+	if (flow_rule_match_key(f_rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
+
+		flow_rule_match_vlan(f_rule, &match);
+
+		if (match.mask->vlan_id != 0) {
+			memset(&m_entry, 0, sizeof(m_entry));
+			m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_VLAN_ID;
+			m_entry.keymask.u16.key = match.key->vlan_id;
+			m_entry.keymask.u16.mask = match.mask->vlan_id;
+			err = prestera_acl_rule_match_add(rule, &m_entry);
+			if (err)
+				return err;
+		}
+
+		memset(&m_entry, 0, sizeof(m_entry));
+		m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_VLAN_TPID;
+		m_entry.keymask.u16.key = ntohs(match.key->vlan_tpid);
+		m_entry.keymask.u16.mask = ntohs(match.mask->vlan_tpid);
+		err = prestera_acl_rule_match_add(rule, &m_entry);
+		if (err)
+			return err;
+	}
+
+	if (flow_rule_match_key(f_rule, FLOW_DISSECTOR_KEY_ICMP)) {
+		struct flow_match_icmp match;
+
+		flow_rule_match_icmp(f_rule, &match);
+
+		memset(&m_entry, 0, sizeof(m_entry));
+		m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ICMP_TYPE;
+		m_entry.keymask.u8.key = match.key->type;
+		m_entry.keymask.u8.mask = match.mask->type;
+		err = prestera_acl_rule_match_add(rule, &m_entry);
+		if (err)
+			return err;
+
+		memset(&m_entry, 0, sizeof(m_entry));
+		m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ICMP_CODE;
+		m_entry.keymask.u8.key = match.key->code;
+		m_entry.keymask.u8.mask = match.mask->code;
+		err = prestera_acl_rule_match_add(rule, &m_entry);
+		if (err)
+			return err;
+	}
+
+	return prestera_flower_parse_actions(block, rule,
+					     &f->rule->action,
+					     f->common.extack);
+}
+
+int prestera_flower_replace(struct prestera_flow_block *block,
+			    struct flow_cls_offload *f)
+{
+	struct prestera_switch *sw = prestera_acl_block_sw(block);
+	struct prestera_acl_rule *rule;
+	int err;
+
+	rule = prestera_acl_rule_create(block, f->cookie);
+	if (IS_ERR(rule))
+		return PTR_ERR(rule);
+
+	err = prestera_flower_parse(block, rule, f);
+	if (err)
+		goto err_flower_parse;
+
+	err = prestera_acl_rule_add(sw, rule);
+	if (err)
+		goto err_rule_add;
+
+	return 0;
+
+err_rule_add:
+err_flower_parse:
+	prestera_acl_rule_destroy(rule);
+	return err;
+}
+
+void prestera_flower_destroy(struct prestera_flow_block *block,
+			     struct flow_cls_offload *f)
+{
+	struct prestera_acl_rule *rule;
+	struct prestera_switch *sw;
+
+	rule = prestera_acl_rule_lookup(prestera_acl_block_ruleset_get(block),
+					f->cookie);
+	if (rule) {
+		sw = prestera_acl_block_sw(block);
+		prestera_acl_rule_del(sw, rule);
+		prestera_acl_rule_destroy(rule);
+	}
+}
+
+int prestera_flower_stats(struct prestera_flow_block *block,
+			  struct flow_cls_offload *f)
+{
+	struct prestera_switch *sw = prestera_acl_block_sw(block);
+	struct prestera_acl_rule *rule;
+	u64 packets;
+	u64 lastuse;
+	u64 bytes;
+	int err;
+
+	rule = prestera_acl_rule_lookup(prestera_acl_block_ruleset_get(block),
+					f->cookie);
+	if (!rule)
+		return -EINVAL;
+
+	err = prestera_acl_rule_get_stats(sw, rule, &packets, &bytes, &lastuse);
+	if (err)
+		return err;
+
+	flow_stats_update(&f->stats, bytes, packets, 0, lastuse,
+			  FLOW_ACTION_HW_STATS_IMMEDIATE);
+	return 0;
+}
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flower.h b/drivers/net/ethernet/marvell/prestera/prestera_flower.h
new file mode 100644
index 000000000000..91e045eec58b
--- /dev/null
+++ b/drivers/net/ethernet/marvell/prestera/prestera_flower.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2020 Marvell International Ltd. All rights reserved. */
+
+#ifndef _PRESTERA_FLOWER_H_
+#define _PRESTERA_FLOWER_H_
+
+#include <net/pkt_cls.h>
+
+struct prestera_flow_block;
+
+int prestera_flower_replace(struct prestera_flow_block *block,
+			    struct flow_cls_offload *f);
+void prestera_flower_destroy(struct prestera_flow_block *block,
+			     struct flow_cls_offload *f);
+int prestera_flower_stats(struct prestera_flow_block *block,
+			  struct flow_cls_offload *f);
+
+#endif /* _PRESTERA_FLOWER_H_ */
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_hw.c b/drivers/net/ethernet/marvell/prestera/prestera_hw.c
index 0424718d5998..c1297859e471 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_hw.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_hw.c
@@ -2,11 +2,13 @@
 /* Copyright (c) 2019-2020 Marvell International Ltd. All rights reserved */
 
 #include <linux/etherdevice.h>
+#include <linux/if_bridge.h>
 #include <linux/ethtool.h>
 #include <linux/list.h>
 
 #include "prestera.h"
 #include "prestera_hw.h"
+#include "prestera_acl.h"
 
 #define PRESTERA_SWITCH_INIT_TIMEOUT_MS (30 * 1000)
 
@@ -36,11 +38,31 @@ enum prestera_cmd_type_t {
 	PRESTERA_CMD_TYPE_BRIDGE_PORT_ADD = 0x402,
 	PRESTERA_CMD_TYPE_BRIDGE_PORT_DELETE = 0x403,
 
+	PRESTERA_CMD_TYPE_ACL_RULE_ADD = 0x500,
+	PRESTERA_CMD_TYPE_ACL_RULE_DELETE = 0x501,
+	PRESTERA_CMD_TYPE_ACL_RULE_STATS_GET = 0x510,
+	PRESTERA_CMD_TYPE_ACL_RULESET_CREATE = 0x520,
+	PRESTERA_CMD_TYPE_ACL_RULESET_DELETE = 0x521,
+	PRESTERA_CMD_TYPE_ACL_PORT_BIND = 0x530,
+	PRESTERA_CMD_TYPE_ACL_PORT_UNBIND = 0x531,
+
 	PRESTERA_CMD_TYPE_RXTX_INIT = 0x800,
 	PRESTERA_CMD_TYPE_RXTX_PORT_INIT = 0x801,
 
+	PRESTERA_CMD_TYPE_LAG_MEMBER_ADD = 0x900,
+	PRESTERA_CMD_TYPE_LAG_MEMBER_DELETE = 0x901,
+	PRESTERA_CMD_TYPE_LAG_MEMBER_ENABLE = 0x902,
+	PRESTERA_CMD_TYPE_LAG_MEMBER_DISABLE = 0x903,
+
 	PRESTERA_CMD_TYPE_STP_PORT_SET = 0x1000,
 
+	PRESTERA_CMD_TYPE_SPAN_GET = 0x1100,
+	PRESTERA_CMD_TYPE_SPAN_BIND = 0x1101,
+	PRESTERA_CMD_TYPE_SPAN_UNBIND = 0x1102,
+	PRESTERA_CMD_TYPE_SPAN_RELEASE = 0x1103,
+
+	PRESTERA_CMD_TYPE_CPU_CODE_COUNTERS_GET = 0x2000,
+
 	PRESTERA_CMD_TYPE_ACK = 0x10000,
 	PRESTERA_CMD_TYPE_MAX
 };
@@ -86,6 +108,11 @@ enum {
 };
 
 enum {
+	PRESTERA_PORT_FLOOD_TYPE_UC = 0,
+	PRESTERA_PORT_FLOOD_TYPE_MC = 1,
+};
+
+enum {
 	PRESTERA_PORT_GOOD_OCTETS_RCV_CNT,
 	PRESTERA_PORT_BAD_OCTETS_RCV_CNT,
 	PRESTERA_PORT_MAC_TRANSMIT_ERR_CNT,
@@ -127,6 +154,12 @@ enum {
 	PRESTERA_FC_SYMM_ASYMM,
 };
 
+enum {
+	PRESTERA_HW_FDB_ENTRY_TYPE_REG_PORT = 0,
+	PRESTERA_HW_FDB_ENTRY_TYPE_LAG = 1,
+	PRESTERA_HW_FDB_ENTRY_TYPE_MAX = 2,
+};
+
 struct prestera_fw_event_handler {
 	struct list_head list;
 	struct rcu_head rcu;
@@ -168,6 +201,8 @@ struct prestera_msg_switch_init_resp {
 	u32 port_count;
 	u32 mtu_max;
 	u8  switch_id;
+	u8  lag_max;
+	u8  lag_member_max;
 };
 
 struct prestera_msg_port_autoneg_param {
@@ -188,6 +223,11 @@ struct prestera_msg_port_mdix_param {
 	u8 admin_mode;
 };
 
+struct prestera_msg_port_flood_param {
+	u8 type;
+	u8 enable;
+};
+
 union prestera_msg_port_param {
 	u8  admin_state;
 	u8  oper_state;
@@ -205,6 +245,7 @@ union prestera_msg_port_param {
 	struct prestera_msg_port_mdix_param mdix;
 	struct prestera_msg_port_autoneg_param autoneg;
 	struct prestera_msg_port_cap_param cap;
+	struct prestera_msg_port_flood_param flood_ext;
 };
 
 struct prestera_msg_port_attr_req {
@@ -249,8 +290,13 @@ struct prestera_msg_vlan_req {
 struct prestera_msg_fdb_req {
 	struct prestera_msg_cmd cmd;
 	u8 dest_type;
-	u32 port;
-	u32 dev;
+	union {
+		struct {
+			u32 port;
+			u32 dev;
+		};
+		u16 lag_id;
+	} dest;
 	u8  mac[ETH_ALEN];
 	u16 vid;
 	u8  dynamic;
@@ -269,6 +315,85 @@ struct prestera_msg_bridge_resp {
 	u16 bridge;
 };
 
+struct prestera_msg_acl_action {
+	u32 id;
+};
+
+struct prestera_msg_acl_match {
+	u32 type;
+	union {
+		struct {
+			u8 key;
+			u8 mask;
+		} u8;
+		struct {
+			u16 key;
+			u16 mask;
+		} u16;
+		struct {
+			u32 key;
+			u32 mask;
+		} u32;
+		struct {
+			u64 key;
+			u64 mask;
+		} u64;
+		struct {
+			u8 key[ETH_ALEN];
+			u8 mask[ETH_ALEN];
+		} mac;
+	} __packed keymask;
+};
+
+struct prestera_msg_acl_rule_req {
+	struct prestera_msg_cmd cmd;
+	u32 id;
+	u32 priority;
+	u16 ruleset_id;
+	u8 n_actions;
+	u8 n_matches;
+};
+
+struct prestera_msg_acl_rule_resp {
+	struct prestera_msg_ret ret;
+	u32 id;
+};
+
+struct prestera_msg_acl_rule_stats_resp {
+	struct prestera_msg_ret ret;
+	u64 packets;
+	u64 bytes;
+};
+
+struct prestera_msg_acl_ruleset_bind_req {
+	struct prestera_msg_cmd cmd;
+	u32 port;
+	u32 dev;
+	u16 ruleset_id;
+};
+
+struct prestera_msg_acl_ruleset_req {
+	struct prestera_msg_cmd cmd;
+	u16 id;
+};
+
+struct prestera_msg_acl_ruleset_resp {
+	struct prestera_msg_ret ret;
+	u16 id;
+};
+
+struct prestera_msg_span_req {
+	struct prestera_msg_cmd cmd;
+	u32 port;
+	u32 dev;
+	u8 id;
+} __packed __aligned(4);
+
+struct prestera_msg_span_resp {
+	struct prestera_msg_ret ret;
+	u8 id;
+} __packed __aligned(4);
+
 struct prestera_msg_stp_req {
 	struct prestera_msg_cmd cmd;
 	u32 port;
@@ -293,6 +418,24 @@ struct prestera_msg_rxtx_port_req {
 	u32 dev;
 };
 
+struct prestera_msg_lag_req {
+	struct prestera_msg_cmd cmd;
+	u32 port;
+	u32 dev;
+	u16 lag_id;
+};
+
+struct prestera_msg_cpu_code_counter_req {
+	struct prestera_msg_cmd cmd;
+	u8 counter_type;
+	u8 code;
+};
+
+struct mvsw_msg_cpu_code_counter_ret {
+	struct prestera_msg_ret ret;
+	u64 packet_count;
+};
+
 struct prestera_msg_event {
 	u16 type;
 	u16 id;
@@ -315,7 +458,10 @@ union prestera_msg_event_fdb_param {
 struct prestera_msg_event_fdb {
 	struct prestera_msg_event id;
 	u8 dest_type;
-	u32 port_id;
+	union {
+		u32 port_id;
+		u16 lag_id;
+	} dest;
 	u32 vid;
 	union prestera_msg_event_fdb_param param;
 };
@@ -386,7 +532,19 @@ static int prestera_fw_parse_fdb_evt(void *msg, struct prestera_event *evt)
 {
 	struct prestera_msg_event_fdb *hw_evt = msg;
 
-	evt->fdb_evt.port_id = hw_evt->port_id;
+	switch (hw_evt->dest_type) {
+	case PRESTERA_HW_FDB_ENTRY_TYPE_REG_PORT:
+		evt->fdb_evt.type = PRESTERA_FDB_ENTRY_TYPE_REG_PORT;
+		evt->fdb_evt.dest.port_id = hw_evt->dest.port_id;
+		break;
+	case PRESTERA_HW_FDB_ENTRY_TYPE_LAG:
+		evt->fdb_evt.type = PRESTERA_FDB_ENTRY_TYPE_LAG;
+		evt->fdb_evt.dest.lag_id = hw_evt->dest.lag_id;
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	evt->fdb_evt.vid = hw_evt->vid;
 
 	ether_addr_copy(evt->fdb_evt.data.mac, hw_evt->param.mac);
@@ -531,6 +689,8 @@ int prestera_hw_switch_init(struct prestera_switch *sw)
 	sw->mtu_min = PRESTERA_MIN_MTU;
 	sw->mtu_max = resp.mtu_max;
 	sw->id = resp.switch_id;
+	sw->lag_member_max = resp.lag_member_max;
+	sw->lag_max = resp.lag_max;
 
 	return 0;
 }
@@ -696,6 +856,274 @@ int prestera_hw_port_remote_fc_get(const struct prestera_port *port,
 	return 0;
 }
 
+int prestera_hw_acl_ruleset_create(struct prestera_switch *sw, u16 *ruleset_id)
+{
+	struct prestera_msg_acl_ruleset_resp resp;
+	struct prestera_msg_acl_ruleset_req req;
+	int err;
+
+	err = prestera_cmd_ret(sw, PRESTERA_CMD_TYPE_ACL_RULESET_CREATE,
+			       &req.cmd, sizeof(req), &resp.ret, sizeof(resp));
+	if (err)
+		return err;
+
+	*ruleset_id = resp.id;
+
+	return 0;
+}
+
+int prestera_hw_acl_ruleset_del(struct prestera_switch *sw, u16 ruleset_id)
+{
+	struct prestera_msg_acl_ruleset_req req = {
+		.id = ruleset_id,
+	};
+
+	return prestera_cmd(sw, PRESTERA_CMD_TYPE_ACL_RULESET_DELETE,
+			    &req.cmd, sizeof(req));
+}
+
+static int prestera_hw_acl_actions_put(struct prestera_msg_acl_action *action,
+				       struct prestera_acl_rule *rule)
+{
+	struct list_head *a_list = prestera_acl_rule_action_list_get(rule);
+	struct prestera_acl_rule_action_entry *a_entry;
+	int i = 0;
+
+	list_for_each_entry(a_entry, a_list, list) {
+		action[i].id = a_entry->id;
+
+		switch (a_entry->id) {
+		case PRESTERA_ACL_RULE_ACTION_ACCEPT:
+		case PRESTERA_ACL_RULE_ACTION_DROP:
+		case PRESTERA_ACL_RULE_ACTION_TRAP:
+			/* just rule action id, no specific data */
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		i++;
+	}
+
+	return 0;
+}
+
+static int prestera_hw_acl_matches_put(struct prestera_msg_acl_match *match,
+				       struct prestera_acl_rule *rule)
+{
+	struct list_head *m_list = prestera_acl_rule_match_list_get(rule);
+	struct prestera_acl_rule_match_entry *m_entry;
+	int i = 0;
+
+	list_for_each_entry(m_entry, m_list, list) {
+		match[i].type = m_entry->type;
+
+		switch (m_entry->type) {
+		case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_TYPE:
+		case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_SRC:
+		case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_DST:
+		case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_VLAN_ID:
+		case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_VLAN_TPID:
+			match[i].keymask.u16.key = m_entry->keymask.u16.key;
+			match[i].keymask.u16.mask = m_entry->keymask.u16.mask;
+			break;
+		case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ICMP_TYPE:
+		case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ICMP_CODE:
+		case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_PROTO:
+			match[i].keymask.u8.key = m_entry->keymask.u8.key;
+			match[i].keymask.u8.mask = m_entry->keymask.u8.mask;
+			break;
+		case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_SMAC:
+		case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_DMAC:
+			memcpy(match[i].keymask.mac.key,
+			       m_entry->keymask.mac.key,
+			       sizeof(match[i].keymask.mac.key));
+			memcpy(match[i].keymask.mac.mask,
+			       m_entry->keymask.mac.mask,
+			       sizeof(match[i].keymask.mac.mask));
+			break;
+		case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_SRC:
+		case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_DST:
+		case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_RANGE_SRC:
+		case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_RANGE_DST:
+			match[i].keymask.u32.key = m_entry->keymask.u32.key;
+			match[i].keymask.u32.mask = m_entry->keymask.u32.mask;
+			break;
+		case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_PORT:
+			match[i].keymask.u64.key = m_entry->keymask.u64.key;
+			match[i].keymask.u64.mask = m_entry->keymask.u64.mask;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		i++;
+	}
+
+	return 0;
+}
+
+int prestera_hw_acl_rule_add(struct prestera_switch *sw,
+			     struct prestera_acl_rule *rule,
+			     u32 *rule_id)
+{
+	struct prestera_msg_acl_action *actions;
+	struct prestera_msg_acl_match *matches;
+	struct prestera_msg_acl_rule_resp resp;
+	struct prestera_msg_acl_rule_req *req;
+	u8 n_actions;
+	u8 n_matches;
+	void *buff;
+	u32 size;
+	int err;
+
+	n_actions = prestera_acl_rule_action_len(rule);
+	n_matches = prestera_acl_rule_match_len(rule);
+
+	size = sizeof(*req) + sizeof(*actions) * n_actions +
+		sizeof(*matches) * n_matches;
+
+	buff = kzalloc(size, GFP_KERNEL);
+	if (!buff)
+		return -ENOMEM;
+
+	req = buff;
+	actions = buff + sizeof(*req);
+	matches = buff + sizeof(*req) + sizeof(*actions) * n_actions;
+
+	/* put acl actions into the message */
+	err = prestera_hw_acl_actions_put(actions, rule);
+	if (err)
+		goto free_buff;
+
+	/* put acl matches into the message */
+	err = prestera_hw_acl_matches_put(matches, rule);
+	if (err)
+		goto free_buff;
+
+	req->ruleset_id = prestera_acl_rule_ruleset_id_get(rule);
+	req->priority = prestera_acl_rule_priority_get(rule);
+	req->n_actions = prestera_acl_rule_action_len(rule);
+	req->n_matches = prestera_acl_rule_match_len(rule);
+
+	err = prestera_cmd_ret(sw, PRESTERA_CMD_TYPE_ACL_RULE_ADD,
+			       &req->cmd, size, &resp.ret, sizeof(resp));
+	if (err)
+		goto free_buff;
+
+	*rule_id = resp.id;
+free_buff:
+	kfree(buff);
+	return err;
+}
+
+int prestera_hw_acl_rule_del(struct prestera_switch *sw, u32 rule_id)
+{
+	struct prestera_msg_acl_rule_req req = {
+		.id = rule_id
+	};
+
+	return prestera_cmd(sw, PRESTERA_CMD_TYPE_ACL_RULE_DELETE,
+			    &req.cmd, sizeof(req));
+}
+
+int prestera_hw_acl_rule_stats_get(struct prestera_switch *sw, u32 rule_id,
+				   u64 *packets, u64 *bytes)
+{
+	struct prestera_msg_acl_rule_stats_resp resp;
+	struct prestera_msg_acl_rule_req req = {
+		.id = rule_id
+	};
+	int err;
+
+	err = prestera_cmd_ret(sw, PRESTERA_CMD_TYPE_ACL_RULE_STATS_GET,
+			       &req.cmd, sizeof(req), &resp.ret, sizeof(resp));
+	if (err)
+		return err;
+
+	*packets = resp.packets;
+	*bytes = resp.bytes;
+
+	return 0;
+}
+
+int prestera_hw_acl_port_bind(const struct prestera_port *port, u16 ruleset_id)
+{
+	struct prestera_msg_acl_ruleset_bind_req req = {
+		.port = port->hw_id,
+		.dev = port->dev_id,
+		.ruleset_id = ruleset_id,
+	};
+
+	return prestera_cmd(port->sw, PRESTERA_CMD_TYPE_ACL_PORT_BIND,
+			    &req.cmd, sizeof(req));
+}
+
+int prestera_hw_acl_port_unbind(const struct prestera_port *port,
+				u16 ruleset_id)
+{
+	struct prestera_msg_acl_ruleset_bind_req req = {
+		.port = port->hw_id,
+		.dev = port->dev_id,
+		.ruleset_id = ruleset_id,
+	};
+
+	return prestera_cmd(port->sw, PRESTERA_CMD_TYPE_ACL_PORT_UNBIND,
+			    &req.cmd, sizeof(req));
+}
+
+int prestera_hw_span_get(const struct prestera_port *port, u8 *span_id)
+{
+	struct prestera_msg_span_resp resp;
+	struct prestera_msg_span_req req = {
+		.port = port->hw_id,
+		.dev = port->dev_id,
+	};
+	int err;
+
+	err = prestera_cmd_ret(port->sw, PRESTERA_CMD_TYPE_SPAN_GET,
+			       &req.cmd, sizeof(req), &resp.ret, sizeof(resp));
+	if (err)
+		return err;
+
+	*span_id = resp.id;
+
+	return 0;
+}
+
+int prestera_hw_span_bind(const struct prestera_port *port, u8 span_id)
+{
+	struct prestera_msg_span_req req = {
+		.port = port->hw_id,
+		.dev = port->dev_id,
+		.id = span_id,
+	};
+
+	return prestera_cmd(port->sw, PRESTERA_CMD_TYPE_SPAN_BIND,
+			    &req.cmd, sizeof(req));
+}
+
+int prestera_hw_span_unbind(const struct prestera_port *port)
+{
+	struct prestera_msg_span_req req = {
+		.port = port->hw_id,
+		.dev = port->dev_id,
+	};
+
+	return prestera_cmd(port->sw, PRESTERA_CMD_TYPE_SPAN_UNBIND,
+			    &req.cmd, sizeof(req));
+}
+
+int prestera_hw_span_release(struct prestera_switch *sw, u8 span_id)
+{
+	struct prestera_msg_span_req req = {
+		.id = span_id
+	};
+
+	return prestera_cmd(sw, PRESTERA_CMD_TYPE_SPAN_RELEASE,
+			    &req.cmd, sizeof(req));
+}
+
 int prestera_hw_port_type_get(const struct prestera_port *port, u8 *type)
 {
 	struct prestera_msg_port_attr_req req = {
@@ -988,7 +1416,43 @@ int prestera_hw_port_learning_set(struct prestera_port *port, bool enable)
 			    &req.cmd, sizeof(req));
 }
 
-int prestera_hw_port_flood_set(struct prestera_port *port, bool flood)
+static int prestera_hw_port_uc_flood_set(struct prestera_port *port, bool flood)
+{
+	struct prestera_msg_port_attr_req req = {
+		.attr = PRESTERA_CMD_PORT_ATTR_FLOOD,
+		.port = port->hw_id,
+		.dev = port->dev_id,
+		.param = {
+			.flood_ext = {
+				.type = PRESTERA_PORT_FLOOD_TYPE_UC,
+				.enable = flood,
+			}
+		}
+	};
+
+	return prestera_cmd(port->sw, PRESTERA_CMD_TYPE_PORT_ATTR_SET,
+			    &req.cmd, sizeof(req));
+}
+
+static int prestera_hw_port_mc_flood_set(struct prestera_port *port, bool flood)
+{
+	struct prestera_msg_port_attr_req req = {
+		.attr = PRESTERA_CMD_PORT_ATTR_FLOOD,
+		.port = port->hw_id,
+		.dev = port->dev_id,
+		.param = {
+			.flood_ext = {
+				.type = PRESTERA_PORT_FLOOD_TYPE_MC,
+				.enable = flood,
+			}
+		}
+	};
+
+	return prestera_cmd(port->sw, PRESTERA_CMD_TYPE_PORT_ATTR_SET,
+			    &req.cmd, sizeof(req));
+}
+
+static int prestera_hw_port_flood_set_v2(struct prestera_port *port, bool flood)
 {
 	struct prestera_msg_port_attr_req req = {
 		.attr = PRESTERA_CMD_PORT_ATTR_FLOOD,
@@ -1003,6 +1467,41 @@ int prestera_hw_port_flood_set(struct prestera_port *port, bool flood)
 			    &req.cmd, sizeof(req));
 }
 
+int prestera_hw_port_flood_set(struct prestera_port *port, unsigned long mask,
+			       unsigned long val)
+{
+	int err;
+
+	if (port->sw->dev->fw_rev.maj <= 2) {
+		if (!(mask & BR_FLOOD))
+			return 0;
+
+		return prestera_hw_port_flood_set_v2(port, val & BR_FLOOD);
+	}
+
+	if (mask & BR_FLOOD) {
+		err = prestera_hw_port_uc_flood_set(port, val & BR_FLOOD);
+		if (err)
+			goto err_uc_flood;
+	}
+
+	if (mask & BR_MCAST_FLOOD) {
+		err = prestera_hw_port_mc_flood_set(port, val & BR_MCAST_FLOOD);
+		if (err)
+			goto err_mc_flood;
+	}
+
+	return 0;
+
+err_mc_flood:
+	prestera_hw_port_mc_flood_set(port, 0);
+err_uc_flood:
+	if (mask & BR_FLOOD)
+		prestera_hw_port_uc_flood_set(port, 0);
+
+	return err;
+}
+
 int prestera_hw_vlan_create(struct prestera_switch *sw, u16 vid)
 {
 	struct prestera_msg_vlan_req req = {
@@ -1067,8 +1566,10 @@ int prestera_hw_fdb_add(struct prestera_port *port, const unsigned char *mac,
 			u16 vid, bool dynamic)
 {
 	struct prestera_msg_fdb_req req = {
-		.port = port->hw_id,
-		.dev = port->dev_id,
+		.dest = {
+			.dev = port->dev_id,
+			.port = port->hw_id,
+		},
 		.vid = vid,
 		.dynamic = dynamic,
 	};
@@ -1083,8 +1584,10 @@ int prestera_hw_fdb_del(struct prestera_port *port, const unsigned char *mac,
 			u16 vid)
 {
 	struct prestera_msg_fdb_req req = {
-		.port = port->hw_id,
-		.dev = port->dev_id,
+		.dest = {
+			.dev = port->dev_id,
+			.port = port->hw_id,
+		},
 		.vid = vid,
 	};
 
@@ -1094,11 +1597,48 @@ int prestera_hw_fdb_del(struct prestera_port *port, const unsigned char *mac,
 			    &req.cmd, sizeof(req));
 }
 
+int prestera_hw_lag_fdb_add(struct prestera_switch *sw, u16 lag_id,
+			    const unsigned char *mac, u16 vid, bool dynamic)
+{
+	struct prestera_msg_fdb_req req = {
+		.dest_type = PRESTERA_HW_FDB_ENTRY_TYPE_LAG,
+		.dest = {
+			.lag_id = lag_id,
+		},
+		.vid = vid,
+		.dynamic = dynamic,
+	};
+
+	ether_addr_copy(req.mac, mac);
+
+	return prestera_cmd(sw, PRESTERA_CMD_TYPE_FDB_ADD,
+			    &req.cmd, sizeof(req));
+}
+
+int prestera_hw_lag_fdb_del(struct prestera_switch *sw, u16 lag_id,
+			    const unsigned char *mac, u16 vid)
+{
+	struct prestera_msg_fdb_req req = {
+		.dest_type = PRESTERA_HW_FDB_ENTRY_TYPE_LAG,
+		.dest = {
+			.lag_id = lag_id,
+		},
+		.vid = vid,
+	};
+
+	ether_addr_copy(req.mac, mac);
+
+	return prestera_cmd(sw, PRESTERA_CMD_TYPE_FDB_DELETE,
+			    &req.cmd, sizeof(req));
+}
+
 int prestera_hw_fdb_flush_port(struct prestera_port *port, u32 mode)
 {
 	struct prestera_msg_fdb_req req = {
-		.port = port->hw_id,
-		.dev = port->dev_id,
+		.dest = {
+			.dev = port->dev_id,
+			.port = port->hw_id,
+		},
 		.flush_mode = mode,
 	};
 
@@ -1121,8 +1661,10 @@ int prestera_hw_fdb_flush_port_vlan(struct prestera_port *port, u16 vid,
 				    u32 mode)
 {
 	struct prestera_msg_fdb_req req = {
-		.port = port->hw_id,
-		.dev = port->dev_id,
+		.dest = {
+			.dev = port->dev_id,
+			.port = port->hw_id,
+		},
 		.vid = vid,
 		.flush_mode = mode,
 	};
@@ -1131,6 +1673,37 @@ int prestera_hw_fdb_flush_port_vlan(struct prestera_port *port, u16 vid,
 			    &req.cmd, sizeof(req));
 }
 
+int prestera_hw_fdb_flush_lag(struct prestera_switch *sw, u16 lag_id,
+			      u32 mode)
+{
+	struct prestera_msg_fdb_req req = {
+		.dest_type = PRESTERA_HW_FDB_ENTRY_TYPE_LAG,
+		.dest = {
+			.lag_id = lag_id,
+		},
+		.flush_mode = mode,
+	};
+
+	return prestera_cmd(sw, PRESTERA_CMD_TYPE_FDB_FLUSH_PORT,
+			    &req.cmd, sizeof(req));
+}
+
+int prestera_hw_fdb_flush_lag_vlan(struct prestera_switch *sw,
+				   u16 lag_id, u16 vid, u32 mode)
+{
+	struct prestera_msg_fdb_req req = {
+		.dest_type = PRESTERA_HW_FDB_ENTRY_TYPE_LAG,
+		.dest = {
+			.lag_id = lag_id,
+		},
+		.vid = vid,
+		.flush_mode = mode,
+	};
+
+	return prestera_cmd(sw, PRESTERA_CMD_TYPE_FDB_FLUSH_PORT_VLAN,
+			    &req.cmd, sizeof(req));
+}
+
 int prestera_hw_bridge_create(struct prestera_switch *sw, u16 *bridge_id)
 {
 	struct prestera_msg_bridge_resp resp;
@@ -1212,6 +1785,68 @@ int prestera_hw_rxtx_port_init(struct prestera_port *port)
 			    &req.cmd, sizeof(req));
 }
 
+int prestera_hw_lag_member_add(struct prestera_port *port, u16 lag_id)
+{
+	struct prestera_msg_lag_req req = {
+		.port = port->hw_id,
+		.dev = port->dev_id,
+		.lag_id = lag_id,
+	};
+
+	return prestera_cmd(port->sw, PRESTERA_CMD_TYPE_LAG_MEMBER_ADD,
+			    &req.cmd, sizeof(req));
+}
+
+int prestera_hw_lag_member_del(struct prestera_port *port, u16 lag_id)
+{
+	struct prestera_msg_lag_req req = {
+		.port = port->hw_id,
+		.dev = port->dev_id,
+		.lag_id = lag_id,
+	};
+
+	return prestera_cmd(port->sw, PRESTERA_CMD_TYPE_LAG_MEMBER_DELETE,
+			    &req.cmd, sizeof(req));
+}
+
+int prestera_hw_lag_member_enable(struct prestera_port *port, u16 lag_id,
+				  bool enable)
+{
+	struct prestera_msg_lag_req req = {
+		.port = port->hw_id,
+		.dev = port->dev_id,
+		.lag_id = lag_id,
+	};
+	u32 cmd;
+
+	cmd = enable ? PRESTERA_CMD_TYPE_LAG_MEMBER_ENABLE :
+			PRESTERA_CMD_TYPE_LAG_MEMBER_DISABLE;
+
+	return prestera_cmd(port->sw, cmd, &req.cmd, sizeof(req));
+}
+
+int
+prestera_hw_cpu_code_counters_get(struct prestera_switch *sw, u8 code,
+				  enum prestera_hw_cpu_code_cnt_t counter_type,
+				  u64 *packet_count)
+{
+	struct prestera_msg_cpu_code_counter_req req = {
+		.counter_type = counter_type,
+		.code = code,
+	};
+	struct mvsw_msg_cpu_code_counter_ret resp;
+	int err;
+
+	err = prestera_cmd_ret(sw, PRESTERA_CMD_TYPE_CPU_CODE_COUNTERS_GET,
+			       &req.cmd, sizeof(req), &resp.ret, sizeof(resp));
+	if (err)
+		return err;
+
+	*packet_count = resp.packet_count;
+
+	return 0;
+}
+
 int prestera_hw_event_handler_register(struct prestera_switch *sw,
 				       enum prestera_event_type type,
 				       prestera_event_cb_t fn,
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_hw.h b/drivers/net/ethernet/marvell/prestera/prestera_hw.h
index b2b5ac95b4e3..546d5fd8240d 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_hw.h
+++ b/drivers/net/ethernet/marvell/prestera/prestera_hw.h
@@ -89,12 +89,18 @@ enum {
 	PRESTERA_STP_FORWARD,
 };
 
+enum prestera_hw_cpu_code_cnt_t {
+	PRESTERA_HW_CPU_CODE_CNT_TYPE_DROP = 0,
+	PRESTERA_HW_CPU_CODE_CNT_TYPE_TRAP = 1,
+};
+
 struct prestera_switch;
 struct prestera_port;
 struct prestera_port_stats;
 struct prestera_port_caps;
 enum prestera_event_type;
 struct prestera_event;
+struct prestera_acl_rule;
 
 typedef void (*prestera_event_cb_t)
 	(struct prestera_switch *sw, struct prestera_event *evt, void *arg);
@@ -138,7 +144,8 @@ int prestera_hw_port_mdix_get(const struct prestera_port *port, u8 *status,
 int prestera_hw_port_mdix_set(const struct prestera_port *port, u8 mode);
 int prestera_hw_port_speed_get(const struct prestera_port *port, u32 *speed);
 int prestera_hw_port_learning_set(struct prestera_port *port, bool enable);
-int prestera_hw_port_flood_set(struct prestera_port *port, bool flood);
+int prestera_hw_port_flood_set(struct prestera_port *port, unsigned long mask,
+			       unsigned long val);
 int prestera_hw_port_accept_frm_type(struct prestera_port *port,
 				     enum prestera_accept_frm_type type);
 /* Vlan API */
@@ -165,6 +172,28 @@ int prestera_hw_bridge_delete(struct prestera_switch *sw, u16 bridge_id);
 int prestera_hw_bridge_port_add(struct prestera_port *port, u16 bridge_id);
 int prestera_hw_bridge_port_delete(struct prestera_port *port, u16 bridge_id);
 
+/* ACL API */
+int prestera_hw_acl_ruleset_create(struct prestera_switch *sw,
+				   u16 *ruleset_id);
+int prestera_hw_acl_ruleset_del(struct prestera_switch *sw,
+				u16 ruleset_id);
+int prestera_hw_acl_rule_add(struct prestera_switch *sw,
+			     struct prestera_acl_rule *rule,
+			     u32 *rule_id);
+int prestera_hw_acl_rule_del(struct prestera_switch *sw, u32 rule_id);
+int prestera_hw_acl_rule_stats_get(struct prestera_switch *sw,
+				   u32 rule_id, u64 *packets, u64 *bytes);
+int prestera_hw_acl_port_bind(const struct prestera_port *port,
+			      u16 ruleset_id);
+int prestera_hw_acl_port_unbind(const struct prestera_port *port,
+				u16 ruleset_id);
+
+/* SPAN API */
+int prestera_hw_span_get(const struct prestera_port *port, u8 *span_id);
+int prestera_hw_span_bind(const struct prestera_port *port, u8 span_id);
+int prestera_hw_span_unbind(const struct prestera_port *port);
+int prestera_hw_span_release(struct prestera_switch *sw, u8 span_id);
+
 /* Event handlers */
 int prestera_hw_event_handler_register(struct prestera_switch *sw,
 				       enum prestera_event_type type,
@@ -179,4 +208,24 @@ int prestera_hw_rxtx_init(struct prestera_switch *sw,
 			  struct prestera_rxtx_params *params);
 int prestera_hw_rxtx_port_init(struct prestera_port *port);
 
+/* LAG API */
+int prestera_hw_lag_member_add(struct prestera_port *port, u16 lag_id);
+int prestera_hw_lag_member_del(struct prestera_port *port, u16 lag_id);
+int prestera_hw_lag_member_enable(struct prestera_port *port, u16 lag_id,
+				  bool enable);
+int prestera_hw_lag_fdb_add(struct prestera_switch *sw, u16 lag_id,
+			    const unsigned char *mac, u16 vid, bool dynamic);
+int prestera_hw_lag_fdb_del(struct prestera_switch *sw, u16 lag_id,
+			    const unsigned char *mac, u16 vid);
+int prestera_hw_fdb_flush_lag(struct prestera_switch *sw, u16 lag_id,
+			      u32 mode);
+int prestera_hw_fdb_flush_lag_vlan(struct prestera_switch *sw,
+				   u16 lag_id, u16 vid, u32 mode);
+
+/* HW trap/drop counters API */
+int
+prestera_hw_cpu_code_counters_get(struct prestera_switch *sw, u8 code,
+				  enum prestera_hw_cpu_code_cnt_t counter_type,
+				  u64 *packet_count);
+
 #endif /* _PRESTERA_HW_H_ */
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c
index 2768c78528a5..226f4ff29f6e 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_main.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c
@@ -8,9 +8,13 @@
 #include <linux/netdev_features.h>
 #include <linux/of.h>
 #include <linux/of_net.h>
+#include <linux/if_vlan.h>
 
 #include "prestera.h"
 #include "prestera_hw.h"
+#include "prestera_acl.h"
+#include "prestera_flow.h"
+#include "prestera_span.h"
 #include "prestera_rxtx.h"
 #include "prestera_devlink.h"
 #include "prestera_ethtool.h"
@@ -199,10 +203,25 @@ static void prestera_port_stats_update(struct work_struct *work)
 			   msecs_to_jiffies(PRESTERA_STATS_DELAY_MS));
 }
 
+static int prestera_port_setup_tc(struct net_device *dev,
+				  enum tc_setup_type type,
+				  void *type_data)
+{
+	struct prestera_port *port = netdev_priv(dev);
+
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return prestera_flow_block_setup(port, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct net_device_ops prestera_netdev_ops = {
 	.ndo_open = prestera_port_open,
 	.ndo_stop = prestera_port_close,
 	.ndo_start_xmit = prestera_port_xmit,
+	.ndo_setup_tc = prestera_port_setup_tc,
 	.ndo_change_mtu = prestera_port_change_mtu,
 	.ndo_get_stats64 = prestera_port_get_stats64,
 	.ndo_set_mac_address = prestera_port_set_mac_address,
@@ -281,6 +300,7 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id)
 
 	INIT_LIST_HEAD(&port->vlans_list);
 	port->pvid = PRESTERA_DEFAULT_VID;
+	port->lag = NULL;
 	port->dev = dev;
 	port->id = id;
 	port->sw = sw;
@@ -296,7 +316,7 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id)
 	if (err)
 		goto err_dl_port_register;
 
-	dev->features |= NETIF_F_NETNS_LOCAL;
+	dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_HW_TC;
 	dev->netdev_ops = &prestera_netdev_ops;
 	dev->ethtool_ops = &prestera_ethtool_ops;
 
@@ -472,6 +492,149 @@ static int prestera_switch_set_base_mac_addr(struct prestera_switch *sw)
 	return prestera_hw_switch_mac_set(sw, sw->base_mac);
 }
 
+struct prestera_lag *prestera_lag_by_id(struct prestera_switch *sw, u16 id)
+{
+	return id < sw->lag_max ? &sw->lags[id] : NULL;
+}
+
+static struct prestera_lag *prestera_lag_by_dev(struct prestera_switch *sw,
+						struct net_device *dev)
+{
+	struct prestera_lag *lag;
+	u16 id;
+
+	for (id = 0; id < sw->lag_max; id++) {
+		lag = &sw->lags[id];
+		if (lag->dev == dev)
+			return lag;
+	}
+
+	return NULL;
+}
+
+static struct prestera_lag *prestera_lag_create(struct prestera_switch *sw,
+						struct net_device *lag_dev)
+{
+	struct prestera_lag *lag = NULL;
+	u16 id;
+
+	for (id = 0; id < sw->lag_max; id++) {
+		lag = &sw->lags[id];
+		if (!lag->dev)
+			break;
+	}
+	if (lag) {
+		INIT_LIST_HEAD(&lag->members);
+		lag->dev = lag_dev;
+	}
+
+	return lag;
+}
+
+static void prestera_lag_destroy(struct prestera_switch *sw,
+				 struct prestera_lag *lag)
+{
+	WARN_ON(!list_empty(&lag->members));
+	lag->member_count = 0;
+	lag->dev = NULL;
+}
+
+static int prestera_lag_port_add(struct prestera_port *port,
+				 struct net_device *lag_dev)
+{
+	struct prestera_switch *sw = port->sw;
+	struct prestera_lag *lag;
+	int err;
+
+	lag = prestera_lag_by_dev(sw, lag_dev);
+	if (!lag) {
+		lag = prestera_lag_create(sw, lag_dev);
+		if (!lag)
+			return -ENOSPC;
+	}
+
+	if (lag->member_count >= sw->lag_member_max)
+		return -ENOSPC;
+
+	err = prestera_hw_lag_member_add(port, lag->lag_id);
+	if (err) {
+		if (!lag->member_count)
+			prestera_lag_destroy(sw, lag);
+		return err;
+	}
+
+	list_add(&port->lag_member, &lag->members);
+	lag->member_count++;
+	port->lag = lag;
+
+	return 0;
+}
+
+static int prestera_lag_port_del(struct prestera_port *port)
+{
+	struct prestera_switch *sw = port->sw;
+	struct prestera_lag *lag = port->lag;
+	int err;
+
+	if (!lag || !lag->member_count)
+		return -EINVAL;
+
+	err = prestera_hw_lag_member_del(port, lag->lag_id);
+	if (err)
+		return err;
+
+	list_del(&port->lag_member);
+	lag->member_count--;
+	port->lag = NULL;
+
+	if (netif_is_bridge_port(lag->dev)) {
+		struct net_device *br_dev;
+
+		br_dev = netdev_master_upper_dev_get(lag->dev);
+
+		prestera_bridge_port_leave(br_dev, port);
+	}
+
+	if (!lag->member_count)
+		prestera_lag_destroy(sw, lag);
+
+	return 0;
+}
+
+bool prestera_port_is_lag_member(const struct prestera_port *port)
+{
+	return !!port->lag;
+}
+
+u16 prestera_port_lag_id(const struct prestera_port *port)
+{
+	return port->lag->lag_id;
+}
+
+static int prestera_lag_init(struct prestera_switch *sw)
+{
+	u16 id;
+
+	sw->lags = kcalloc(sw->lag_max, sizeof(*sw->lags), GFP_KERNEL);
+	if (!sw->lags)
+		return -ENOMEM;
+
+	for (id = 0; id < sw->lag_max; id++)
+		sw->lags[id].lag_id = id;
+
+	return 0;
+}
+
+static void prestera_lag_fini(struct prestera_switch *sw)
+{
+	u8 idx;
+
+	for (idx = 0; idx < sw->lag_max; idx++)
+		WARN_ON(sw->lags[idx].member_count);
+
+	kfree(sw->lags);
+}
+
 bool prestera_netdev_check(const struct net_device *dev)
 {
 	return dev->netdev_ops == &prestera_netdev_ops;
@@ -505,16 +668,119 @@ struct prestera_port *prestera_port_dev_lower_find(struct net_device *dev)
 	return port;
 }
 
-static int prestera_netdev_port_event(struct net_device *dev,
+static int prestera_netdev_port_lower_event(struct net_device *dev,
+					    unsigned long event, void *ptr)
+{
+	struct netdev_notifier_changelowerstate_info *info = ptr;
+	struct netdev_lag_lower_state_info *lower_state_info;
+	struct prestera_port *port = netdev_priv(dev);
+	bool enabled;
+
+	if (!netif_is_lag_port(dev))
+		return 0;
+	if (!prestera_port_is_lag_member(port))
+		return 0;
+
+	lower_state_info = info->lower_state_info;
+	enabled = lower_state_info->link_up && lower_state_info->tx_enabled;
+
+	return prestera_hw_lag_member_enable(port, port->lag->lag_id, enabled);
+}
+
+static bool prestera_lag_master_check(struct net_device *lag_dev,
+				      struct netdev_lag_upper_info *info,
+				      struct netlink_ext_ack *ext_ack)
+{
+	if (info->tx_type != NETDEV_LAG_TX_TYPE_HASH) {
+		NL_SET_ERR_MSG_MOD(ext_ack, "Unsupported LAG Tx type");
+		return false;
+	}
+
+	return true;
+}
+
+static int prestera_netdev_port_event(struct net_device *lower,
+				      struct net_device *dev,
 				      unsigned long event, void *ptr)
 {
+	struct netdev_notifier_changeupper_info *info = ptr;
+	struct prestera_port *port = netdev_priv(dev);
+	struct netlink_ext_ack *extack;
+	struct net_device *upper;
+
+	extack = netdev_notifier_info_to_extack(&info->info);
+	upper = info->upper_dev;
+
 	switch (event) {
 	case NETDEV_PRECHANGEUPPER:
+		if (!netif_is_bridge_master(upper) &&
+		    !netif_is_lag_master(upper)) {
+			NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
+			return -EINVAL;
+		}
+
+		if (!info->linking)
+			break;
+
+		if (netdev_has_any_upper_dev(upper)) {
+			NL_SET_ERR_MSG_MOD(extack, "Upper device is already enslaved");
+			return -EINVAL;
+		}
+
+		if (netif_is_lag_master(upper) &&
+		    !prestera_lag_master_check(upper, info->upper_info, extack))
+			return -EOPNOTSUPP;
+		if (netif_is_lag_master(upper) && vlan_uses_dev(dev)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Master device is a LAG master and port has a VLAN");
+			return -EINVAL;
+		}
+		if (netif_is_lag_port(dev) && is_vlan_dev(upper) &&
+		    !netif_is_lag_master(vlan_dev_real_dev(upper))) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Can not put a VLAN on a LAG port");
+			return -EINVAL;
+		}
+		break;
+
 	case NETDEV_CHANGEUPPER:
-		return prestera_bridge_port_event(dev, event, ptr);
-	default:
-		return 0;
+		if (netif_is_bridge_master(upper)) {
+			if (info->linking)
+				return prestera_bridge_port_join(upper, port);
+			else
+				prestera_bridge_port_leave(upper, port);
+		} else if (netif_is_lag_master(upper)) {
+			if (info->linking)
+				return prestera_lag_port_add(port, upper);
+			else
+				prestera_lag_port_del(port);
+		}
+		break;
+
+	case NETDEV_CHANGELOWERSTATE:
+		return prestera_netdev_port_lower_event(dev, event, ptr);
 	}
+
+	return 0;
+}
+
+static int prestera_netdevice_lag_event(struct net_device *lag_dev,
+					unsigned long event, void *ptr)
+{
+	struct net_device *dev;
+	struct list_head *iter;
+	int err;
+
+	netdev_for_each_lower_dev(lag_dev, dev, iter) {
+		if (prestera_netdev_check(dev)) {
+			err = prestera_netdev_port_event(lag_dev, dev, event,
+							 ptr);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
 }
 
 static int prestera_netdev_event_handler(struct notifier_block *nb,
@@ -524,7 +790,9 @@ static int prestera_netdev_event_handler(struct notifier_block *nb,
 	int err = 0;
 
 	if (prestera_netdev_check(dev))
-		err = prestera_netdev_port_event(dev, event, ptr);
+		err = prestera_netdev_port_event(dev, dev, event, ptr);
+	else if (netif_is_lag_master(dev))
+		err = prestera_netdevice_lag_event(dev, event, ptr);
 
 	return notifier_from_errno(err);
 }
@@ -574,10 +842,22 @@ static int prestera_switch_init(struct prestera_switch *sw)
 	if (err)
 		goto err_handlers_register;
 
+	err = prestera_acl_init(sw);
+	if (err)
+		goto err_acl_init;
+
+	err = prestera_span_init(sw);
+	if (err)
+		goto err_span_init;
+
 	err = prestera_devlink_register(sw);
 	if (err)
 		goto err_dl_register;
 
+	err = prestera_lag_init(sw);
+	if (err)
+		goto err_lag_init;
+
 	err = prestera_create_ports(sw);
 	if (err)
 		goto err_ports_create;
@@ -585,8 +865,14 @@ static int prestera_switch_init(struct prestera_switch *sw)
 	return 0;
 
 err_ports_create:
+	prestera_lag_fini(sw);
+err_lag_init:
 	prestera_devlink_unregister(sw);
 err_dl_register:
+	prestera_span_fini(sw);
+err_span_init:
+	prestera_acl_fini(sw);
+err_acl_init:
 	prestera_event_handlers_unregister(sw);
 err_handlers_register:
 	prestera_rxtx_switch_fini(sw);
@@ -602,7 +888,10 @@ err_swdev_register:
 static void prestera_switch_fini(struct prestera_switch *sw)
 {
 	prestera_destroy_ports(sw);
+	prestera_lag_fini(sw);
 	prestera_devlink_unregister(sw);
+	prestera_span_fini(sw);
+	prestera_acl_fini(sw);
 	prestera_event_handlers_unregister(sw);
 	prestera_rxtx_switch_fini(sw);
 	prestera_switchdev_fini(sw);
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c
index 298110119272..a250d394da38 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
 /* Copyright (c) 2019-2020 Marvell International Ltd. All rights reserved */
 
+#include <linux/bitfield.h>
 #include <linux/circ_buf.h>
 #include <linux/device.h>
 #include <linux/firmware.h>
@@ -13,9 +14,12 @@
 
 #define PRESTERA_MSG_MAX_SIZE 1500
 
-#define PRESTERA_SUPP_FW_MAJ_VER	2
+#define PRESTERA_SUPP_FW_MAJ_VER	3
 #define PRESTERA_SUPP_FW_MIN_VER	0
 
+#define PRESTERA_PREV_FW_MAJ_VER	2
+#define PRESTERA_PREV_FW_MIN_VER	0
+
 #define PRESTERA_FW_PATH_FMT	"mrvl/prestera/mvsw_prestera_fw-v%u.%u.img"
 
 #define PRESTERA_FW_HDR_MAGIC		0x351D9D06
@@ -144,6 +148,11 @@ struct prestera_fw_regs {
 /* PRESTERA_CMD_RCV_CTL_REG flags */
 #define PRESTERA_CMD_F_REPL_SENT	BIT(0)
 
+#define PRESTERA_FW_EVT_CTL_STATUS_MASK	GENMASK(1, 0)
+
+#define PRESTERA_FW_EVT_CTL_STATUS_ON	0
+#define PRESTERA_FW_EVT_CTL_STATUS_OFF	1
+
 #define PRESTERA_EVTQ_REG_OFFSET(q, f)			\
 	(PRESTERA_FW_REG_OFFSET(evtq_list) +		\
 	 (q) * sizeof(struct prestera_fw_evtq_regs) +	\
@@ -166,6 +175,8 @@ struct prestera_fw_evtq {
 };
 
 struct prestera_fw {
+	struct prestera_fw_rev rev_supp;
+	const struct firmware *bin;
 	struct workqueue_struct *wq;
 	struct prestera_device dev;
 	u8 __iomem *ldr_regs;
@@ -260,6 +271,15 @@ static u8 prestera_fw_evtq_pick(struct prestera_fw *fw)
 	return PRESTERA_EVT_QNUM_MAX;
 }
 
+static void prestera_fw_evt_ctl_status_set(struct prestera_fw *fw, u32 val)
+{
+	u32 status = prestera_fw_read(fw, PRESTERA_FW_STATUS_REG);
+
+	u32p_replace_bits(&status, val, PRESTERA_FW_EVT_CTL_STATUS_MASK);
+
+	prestera_fw_write(fw, PRESTERA_FW_STATUS_REG, status);
+}
+
 static void prestera_fw_evt_work_fn(struct work_struct *work)
 {
 	struct prestera_fw *fw;
@@ -269,6 +289,8 @@ static void prestera_fw_evt_work_fn(struct work_struct *work)
 	fw = container_of(work, struct prestera_fw, evt_work);
 	msg = fw->evt_msg;
 
+	prestera_fw_evt_ctl_status_set(fw, PRESTERA_FW_EVT_CTL_STATUS_OFF);
+
 	while ((qid = prestera_fw_evtq_pick(fw)) < PRESTERA_EVT_QNUM_MAX) {
 		u32 idx;
 		u32 len;
@@ -288,6 +310,8 @@ static void prestera_fw_evt_work_fn(struct work_struct *work)
 		if (fw->dev.recv_msg)
 			fw->dev.recv_msg(&fw->dev, msg, len);
 	}
+
+	prestera_fw_evt_ctl_status_set(fw, PRESTERA_FW_EVT_CTL_STATUS_ON);
 }
 
 static int prestera_fw_wait_reg32(struct prestera_fw *fw, u32 reg, u32 cmp,
@@ -576,25 +600,24 @@ static void prestera_fw_rev_parse(const struct prestera_fw_header *hdr,
 static int prestera_fw_rev_check(struct prestera_fw *fw)
 {
 	struct prestera_fw_rev *rev = &fw->dev.fw_rev;
-	u16 maj_supp = PRESTERA_SUPP_FW_MAJ_VER;
-	u16 min_supp = PRESTERA_SUPP_FW_MIN_VER;
 
-	if (rev->maj == maj_supp && rev->min >= min_supp)
+	if (rev->maj == fw->rev_supp.maj && rev->min >= fw->rev_supp.min)
 		return 0;
 
 	dev_err(fw->dev.dev, "Driver supports FW version only '%u.%u.x'",
-		PRESTERA_SUPP_FW_MAJ_VER, PRESTERA_SUPP_FW_MIN_VER);
+		fw->rev_supp.maj, fw->rev_supp.min);
 
 	return -EINVAL;
 }
 
-static int prestera_fw_hdr_parse(struct prestera_fw *fw,
-				 const struct firmware *img)
+static int prestera_fw_hdr_parse(struct prestera_fw *fw)
 {
-	struct prestera_fw_header *hdr = (struct prestera_fw_header *)img->data;
 	struct prestera_fw_rev *rev = &fw->dev.fw_rev;
+	struct prestera_fw_header *hdr;
 	u32 magic;
 
+	hdr = (struct prestera_fw_header *)fw->bin->data;
+
 	magic = be32_to_cpu(hdr->magic_number);
 	if (magic != PRESTERA_FW_HDR_MAGIC) {
 		dev_err(fw->dev.dev, "FW img hdr magic is invalid");
@@ -609,11 +632,52 @@ static int prestera_fw_hdr_parse(struct prestera_fw *fw,
 	return prestera_fw_rev_check(fw);
 }
 
+static int prestera_fw_get(struct prestera_fw *fw)
+{
+	int ver_maj = PRESTERA_SUPP_FW_MAJ_VER;
+	int ver_min = PRESTERA_SUPP_FW_MIN_VER;
+	char fw_path[128];
+	int err;
+
+pick_fw_ver:
+	snprintf(fw_path, sizeof(fw_path), PRESTERA_FW_PATH_FMT,
+		 ver_maj, ver_min);
+
+	err = request_firmware_direct(&fw->bin, fw_path, fw->dev.dev);
+	if (err) {
+		if (ver_maj == PRESTERA_SUPP_FW_MAJ_VER) {
+			ver_maj = PRESTERA_PREV_FW_MAJ_VER;
+			ver_min = PRESTERA_PREV_FW_MIN_VER;
+
+			dev_warn(fw->dev.dev,
+				 "missing latest %s firmware, fall-back to previous %u.%u version\n",
+				 fw_path, ver_maj, ver_min);
+
+			goto pick_fw_ver;
+		} else {
+			dev_err(fw->dev.dev, "failed to request previous firmware: %s\n",
+				fw_path);
+			return err;
+		}
+	}
+
+	dev_info(fw->dev.dev, "Loading %s ...", fw_path);
+
+	fw->rev_supp.maj = ver_maj;
+	fw->rev_supp.min = ver_min;
+	fw->rev_supp.sub = 0;
+
+	return 0;
+}
+
+static void prestera_fw_put(struct prestera_fw *fw)
+{
+	release_firmware(fw->bin);
+}
+
 static int prestera_fw_load(struct prestera_fw *fw)
 {
 	size_t hlen = sizeof(struct prestera_fw_header);
-	const struct firmware *f;
-	char fw_path[128];
 	int err;
 
 	err = prestera_ldr_wait_reg32(fw, PRESTERA_LDR_READY_REG,
@@ -632,30 +696,24 @@ static int prestera_fw_load(struct prestera_fw *fw)
 
 	fw->ldr_wr_idx = 0;
 
-	snprintf(fw_path, sizeof(fw_path), PRESTERA_FW_PATH_FMT,
-		 PRESTERA_SUPP_FW_MAJ_VER, PRESTERA_SUPP_FW_MIN_VER);
-
-	err = request_firmware_direct(&f, fw_path, fw->dev.dev);
-	if (err) {
-		dev_err(fw->dev.dev, "failed to request firmware file\n");
+	err = prestera_fw_get(fw);
+	if (err)
 		return err;
-	}
 
-	err = prestera_fw_hdr_parse(fw, f);
+	err = prestera_fw_hdr_parse(fw);
 	if (err) {
 		dev_err(fw->dev.dev, "FW image header is invalid\n");
 		goto out_release;
 	}
 
-	prestera_ldr_write(fw, PRESTERA_LDR_IMG_SIZE_REG, f->size - hlen);
+	prestera_ldr_write(fw, PRESTERA_LDR_IMG_SIZE_REG, fw->bin->size - hlen);
 	prestera_ldr_write(fw, PRESTERA_LDR_CTL_REG, PRESTERA_LDR_CTL_DL_START);
 
-	dev_info(fw->dev.dev, "Loading %s ...", fw_path);
-
-	err = prestera_ldr_fw_send(fw, f->data + hlen, f->size - hlen);
+	err = prestera_ldr_fw_send(fw, fw->bin->data + hlen,
+				   fw->bin->size - hlen);
 
 out_release:
-	release_firmware(f);
+	prestera_fw_put(fw);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c b/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c
index 2a13c318048c..73d2eba5262f 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c
@@ -14,6 +14,7 @@
 #include "prestera.h"
 #include "prestera_hw.h"
 #include "prestera_rxtx.h"
+#include "prestera_devlink.h"
 
 #define PRESTERA_SDMA_WAIT_MUL		10
 
@@ -214,9 +215,10 @@ static struct sk_buff *prestera_sdma_rx_skb_get(struct prestera_sdma *sdma,
 static int prestera_rxtx_process_skb(struct prestera_sdma *sdma,
 				     struct sk_buff *skb)
 {
-	const struct prestera_port *port;
+	struct prestera_port *port;
 	struct prestera_dsa dsa;
 	u32 hw_port, dev_id;
+	u8 cpu_code;
 	int err;
 
 	skb_pull(skb, ETH_HLEN);
@@ -259,6 +261,9 @@ static int prestera_rxtx_process_skb(struct prestera_sdma *sdma,
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), tci);
 	}
 
+	cpu_code = dsa.cpu_code;
+	prestera_devlink_trap_report(port, skb, cpu_code);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_span.c b/drivers/net/ethernet/marvell/prestera/prestera_span.c
new file mode 100644
index 000000000000..3cafca827bb7
--- /dev/null
+++ b/drivers/net/ethernet/marvell/prestera/prestera_span.c
@@ -0,0 +1,239 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2020 Marvell International Ltd. All rights reserved */
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+
+#include "prestera.h"
+#include "prestera_hw.h"
+#include "prestera_acl.h"
+#include "prestera_span.h"
+
+struct prestera_span_entry {
+	struct list_head list;
+	struct prestera_port *port;
+	refcount_t ref_count;
+	u8 id;
+};
+
+struct prestera_span {
+	struct prestera_switch *sw;
+	struct list_head entries;
+};
+
+static struct prestera_span_entry *
+prestera_span_entry_create(struct prestera_port *port, u8 span_id)
+{
+	struct prestera_span_entry *entry;
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return ERR_PTR(-ENOMEM);
+
+	refcount_set(&entry->ref_count, 1);
+	entry->port = port;
+	entry->id = span_id;
+	list_add_tail(&entry->list, &port->sw->span->entries);
+
+	return entry;
+}
+
+static void prestera_span_entry_del(struct prestera_span_entry *entry)
+{
+	list_del(&entry->list);
+	kfree(entry);
+}
+
+static struct prestera_span_entry *
+prestera_span_entry_find_by_id(struct prestera_span *span, u8 span_id)
+{
+	struct prestera_span_entry *entry;
+
+	list_for_each_entry(entry, &span->entries, list) {
+		if (entry->id == span_id)
+			return entry;
+	}
+
+	return NULL;
+}
+
+static struct prestera_span_entry *
+prestera_span_entry_find_by_port(struct prestera_span *span,
+				 struct prestera_port *port)
+{
+	struct prestera_span_entry *entry;
+
+	list_for_each_entry(entry, &span->entries, list) {
+		if (entry->port == port)
+			return entry;
+	}
+
+	return NULL;
+}
+
+static int prestera_span_get(struct prestera_port *port, u8 *span_id)
+{
+	u8 new_span_id;
+	struct prestera_switch *sw = port->sw;
+	struct prestera_span_entry *entry;
+	int err;
+
+	entry = prestera_span_entry_find_by_port(sw->span, port);
+	if (entry) {
+		refcount_inc(&entry->ref_count);
+		*span_id = entry->id;
+		return 0;
+	}
+
+	err = prestera_hw_span_get(port, &new_span_id);
+	if (err)
+		return err;
+
+	entry = prestera_span_entry_create(port, new_span_id);
+	if (IS_ERR(entry)) {
+		prestera_hw_span_release(sw, new_span_id);
+		return PTR_ERR(entry);
+	}
+
+	*span_id = new_span_id;
+	return 0;
+}
+
+static int prestera_span_put(struct prestera_switch *sw, u8 span_id)
+{
+	struct prestera_span_entry *entry;
+	int err;
+
+	entry = prestera_span_entry_find_by_id(sw->span, span_id);
+	if (!entry)
+		return false;
+
+	if (!refcount_dec_and_test(&entry->ref_count))
+		return 0;
+
+	err = prestera_hw_span_release(sw, span_id);
+	if (err)
+		return err;
+
+	prestera_span_entry_del(entry);
+	return 0;
+}
+
+static int prestera_span_rule_add(struct prestera_flow_block_binding *binding,
+				  struct prestera_port *to_port)
+{
+	struct prestera_switch *sw = binding->port->sw;
+	u8 span_id;
+	int err;
+
+	if (binding->span_id != PRESTERA_SPAN_INVALID_ID)
+		/* port already in mirroring */
+		return -EEXIST;
+
+	err = prestera_span_get(to_port, &span_id);
+	if (err)
+		return err;
+
+	err = prestera_hw_span_bind(binding->port, span_id);
+	if (err) {
+		prestera_span_put(sw, span_id);
+		return err;
+	}
+
+	binding->span_id = span_id;
+	return 0;
+}
+
+static int prestera_span_rule_del(struct prestera_flow_block_binding *binding)
+{
+	int err;
+
+	err = prestera_hw_span_unbind(binding->port);
+	if (err)
+		return err;
+
+	err = prestera_span_put(binding->port->sw, binding->span_id);
+	if (err)
+		return err;
+
+	binding->span_id = PRESTERA_SPAN_INVALID_ID;
+	return 0;
+}
+
+int prestera_span_replace(struct prestera_flow_block *block,
+			  struct tc_cls_matchall_offload *f)
+{
+	struct prestera_flow_block_binding *binding;
+	__be16 protocol = f->common.protocol;
+	struct flow_action_entry *act;
+	struct prestera_port *port;
+	int err;
+
+	if (!flow_offload_has_one_action(&f->rule->action)) {
+		NL_SET_ERR_MSG(f->common.extack,
+			       "Only singular actions are supported");
+		return -EOPNOTSUPP;
+	}
+
+	act = &f->rule->action.entries[0];
+
+	if (!prestera_netdev_check(act->dev)) {
+		NL_SET_ERR_MSG(f->common.extack,
+			       "Only Marvell Prestera port is supported");
+		return -EINVAL;
+	}
+	if (!tc_cls_can_offload_and_chain0(act->dev, &f->common))
+		return -EOPNOTSUPP;
+	if (act->id != FLOW_ACTION_MIRRED)
+		return -EOPNOTSUPP;
+	if (protocol != htons(ETH_P_ALL))
+		return -EOPNOTSUPP;
+
+	port = netdev_priv(act->dev);
+
+	list_for_each_entry(binding, &block->binding_list, list) {
+		err = prestera_span_rule_add(binding, port);
+		if (err)
+			goto rollback;
+	}
+
+	return 0;
+
+rollback:
+	list_for_each_entry_continue_reverse(binding,
+					     &block->binding_list, list)
+		prestera_span_rule_del(binding);
+	return err;
+}
+
+void prestera_span_destroy(struct prestera_flow_block *block)
+{
+	struct prestera_flow_block_binding *binding;
+
+	list_for_each_entry(binding, &block->binding_list, list)
+		prestera_span_rule_del(binding);
+}
+
+int prestera_span_init(struct prestera_switch *sw)
+{
+	struct prestera_span *span;
+
+	span = kzalloc(sizeof(*span), GFP_KERNEL);
+	if (!span)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&span->entries);
+
+	sw->span = span;
+	span->sw = sw;
+
+	return 0;
+}
+
+void prestera_span_fini(struct prestera_switch *sw)
+{
+	struct prestera_span *span = sw->span;
+
+	WARN_ON(!list_empty(&span->entries));
+	kfree(span);
+}
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_span.h b/drivers/net/ethernet/marvell/prestera/prestera_span.h
new file mode 100644
index 000000000000..f0644521f78a
--- /dev/null
+++ b/drivers/net/ethernet/marvell/prestera/prestera_span.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2019-2020 Marvell International Ltd. All rights reserved. */
+
+#ifndef _PRESTERA_SPAN_H_
+#define _PRESTERA_SPAN_H_
+
+#include <net/pkt_cls.h>
+
+#define PRESTERA_SPAN_INVALID_ID -1
+
+struct prestera_switch;
+struct prestera_flow_block;
+
+int prestera_span_init(struct prestera_switch *sw);
+void prestera_span_fini(struct prestera_switch *sw);
+int prestera_span_replace(struct prestera_flow_block *block,
+			  struct tc_cls_matchall_offload *f);
+void prestera_span_destroy(struct prestera_flow_block *block);
+
+#endif /* _PRESTERA_SPAN_H_ */
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c
index cb564890a3dc..74b81b4fbb97 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c
@@ -180,6 +180,45 @@ err_port_vlan_alloc:
 	return ERR_PTR(err);
 }
 
+static int prestera_fdb_add(struct prestera_port *port,
+			    const unsigned char *mac, u16 vid, bool dynamic)
+{
+	if (prestera_port_is_lag_member(port))
+		return prestera_hw_lag_fdb_add(port->sw, prestera_port_lag_id(port),
+					      mac, vid, dynamic);
+
+	return prestera_hw_fdb_add(port, mac, vid, dynamic);
+}
+
+static int prestera_fdb_del(struct prestera_port *port,
+			    const unsigned char *mac, u16 vid)
+{
+	if (prestera_port_is_lag_member(port))
+		return prestera_hw_lag_fdb_del(port->sw, prestera_port_lag_id(port),
+					      mac, vid);
+	else
+		return prestera_hw_fdb_del(port, mac, vid);
+}
+
+static int prestera_fdb_flush_port_vlan(struct prestera_port *port, u16 vid,
+					u32 mode)
+{
+	if (prestera_port_is_lag_member(port))
+		return prestera_hw_fdb_flush_lag_vlan(port->sw, prestera_port_lag_id(port),
+						      vid, mode);
+	else
+		return prestera_hw_fdb_flush_port_vlan(port, vid, mode);
+}
+
+static int prestera_fdb_flush_port(struct prestera_port *port, u32 mode)
+{
+	if (prestera_port_is_lag_member(port))
+		return prestera_hw_fdb_flush_lag(port->sw, prestera_port_lag_id(port),
+						 mode);
+	else
+		return prestera_hw_fdb_flush_port(port, mode);
+}
+
 static void
 prestera_port_vlan_bridge_leave(struct prestera_port_vlan *port_vlan)
 {
@@ -199,11 +238,11 @@ prestera_port_vlan_bridge_leave(struct prestera_port_vlan *port_vlan)
 	last_port = port_count == 1;
 
 	if (last_vlan)
-		prestera_hw_fdb_flush_port(port, fdb_flush_mode);
+		prestera_fdb_flush_port(port, fdb_flush_mode);
 	else if (last_port)
 		prestera_hw_fdb_flush_vlan(port->sw, vid, fdb_flush_mode);
 	else
-		prestera_hw_fdb_flush_port_vlan(port, vid, fdb_flush_mode);
+		prestera_fdb_flush_port_vlan(port, vid, fdb_flush_mode);
 
 	list_del(&port_vlan->br_vlan_head);
 	prestera_bridge_vlan_put(br_vlan);
@@ -312,11 +351,29 @@ __prestera_bridge_port_by_dev(struct prestera_bridge *bridge,
 	return NULL;
 }
 
+static int prestera_match_upper_bridge_dev(struct net_device *dev,
+					   struct netdev_nested_priv *priv)
+{
+	if (netif_is_bridge_master(dev))
+		priv->data = dev;
+
+	return 0;
+}
+
+static struct net_device *prestera_get_upper_bridge_dev(struct net_device *dev)
+{
+	struct netdev_nested_priv priv = { };
+
+	netdev_walk_all_upper_dev_rcu(dev, prestera_match_upper_bridge_dev,
+				      &priv);
+	return priv.data;
+}
+
 static struct prestera_bridge_port *
 prestera_bridge_port_by_dev(struct prestera_switchdev *swdev,
 			    struct net_device *dev)
 {
-	struct net_device *br_dev = netdev_master_upper_dev_get(dev);
+	struct net_device *br_dev = prestera_get_upper_bridge_dev(dev);
 	struct prestera_bridge *bridge;
 
 	if (!br_dev)
@@ -404,7 +461,8 @@ prestera_bridge_1d_port_join(struct prestera_bridge_port *br_port)
 	if (err)
 		return err;
 
-	err = prestera_hw_port_flood_set(port, br_port->flags & BR_FLOOD);
+	err = prestera_hw_port_flood_set(port, BR_FLOOD | BR_MCAST_FLOOD,
+					 br_port->flags);
 	if (err)
 		goto err_port_flood_set;
 
@@ -415,24 +473,23 @@ prestera_bridge_1d_port_join(struct prestera_bridge_port *br_port)
 	return 0;
 
 err_port_learning_set:
-	prestera_hw_port_flood_set(port, false);
 err_port_flood_set:
 	prestera_hw_bridge_port_delete(port, bridge->bridge_id);
 
 	return err;
 }
 
-static int prestera_port_bridge_join(struct prestera_port *port,
-				     struct net_device *upper)
+int prestera_bridge_port_join(struct net_device *br_dev,
+			      struct prestera_port *port)
 {
 	struct prestera_switchdev *swdev = port->sw->swdev;
 	struct prestera_bridge_port *br_port;
 	struct prestera_bridge *bridge;
 	int err;
 
-	bridge = prestera_bridge_by_dev(swdev, upper);
+	bridge = prestera_bridge_by_dev(swdev, br_dev);
 	if (!bridge) {
-		bridge = prestera_bridge_create(swdev, upper);
+		bridge = prestera_bridge_create(swdev, br_dev);
 		if (IS_ERR(bridge))
 			return PTR_ERR(bridge);
 	}
@@ -505,14 +562,14 @@ static int prestera_port_vid_stp_set(struct prestera_port *port, u16 vid,
 	return prestera_hw_vlan_port_stp_set(port, vid, hw_state);
 }
 
-static void prestera_port_bridge_leave(struct prestera_port *port,
-				       struct net_device *upper)
+void prestera_bridge_port_leave(struct net_device *br_dev,
+				struct prestera_port *port)
 {
 	struct prestera_switchdev *swdev = port->sw->swdev;
 	struct prestera_bridge_port *br_port;
 	struct prestera_bridge *bridge;
 
-	bridge = prestera_bridge_by_dev(swdev, upper);
+	bridge = prestera_bridge_by_dev(swdev, br_dev);
 	if (!bridge)
 		return;
 
@@ -528,57 +585,11 @@ static void prestera_port_bridge_leave(struct prestera_port *port,
 		prestera_bridge_1d_port_leave(br_port);
 
 	prestera_hw_port_learning_set(port, false);
-	prestera_hw_port_flood_set(port, false);
+	prestera_hw_port_flood_set(port, BR_FLOOD | BR_MCAST_FLOOD, 0);
 	prestera_port_vid_stp_set(port, PRESTERA_VID_ALL, BR_STATE_FORWARDING);
 	prestera_bridge_port_put(br_port);
 }
 
-int prestera_bridge_port_event(struct net_device *dev, unsigned long event,
-			       void *ptr)
-{
-	struct netdev_notifier_changeupper_info *info = ptr;
-	struct netlink_ext_ack *extack;
-	struct prestera_port *port;
-	struct net_device *upper;
-	int err;
-
-	extack = netdev_notifier_info_to_extack(&info->info);
-	port = netdev_priv(dev);
-	upper = info->upper_dev;
-
-	switch (event) {
-	case NETDEV_PRECHANGEUPPER:
-		if (!netif_is_bridge_master(upper)) {
-			NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
-			return -EINVAL;
-		}
-
-		if (!info->linking)
-			break;
-
-		if (netdev_has_any_upper_dev(upper)) {
-			NL_SET_ERR_MSG_MOD(extack, "Upper device is already enslaved");
-			return -EINVAL;
-		}
-		break;
-
-	case NETDEV_CHANGEUPPER:
-		if (!netif_is_bridge_master(upper))
-			break;
-
-		if (info->linking) {
-			err = prestera_port_bridge_join(port, upper);
-			if (err)
-				return err;
-		} else {
-			prestera_port_bridge_leave(port, upper);
-		}
-		break;
-	}
-
-	return 0;
-}
-
 static int prestera_port_attr_br_flags_set(struct prestera_port *port,
 					   struct net_device *dev,
 					   struct switchdev_brport_flags flags)
@@ -590,11 +601,9 @@ static int prestera_port_attr_br_flags_set(struct prestera_port *port,
 	if (!br_port)
 		return 0;
 
-	if (flags.mask & BR_FLOOD) {
-		err = prestera_hw_port_flood_set(port, flags.val & BR_FLOOD);
-		if (err)
-			return err;
-	}
+	err = prestera_hw_port_flood_set(port, flags.mask, flags.val);
+	if (err)
+		return err;
 
 	if (flags.mask & BR_LEARNING) {
 		err = prestera_hw_port_learning_set(port,
@@ -771,9 +780,9 @@ static int prestera_port_fdb_set(struct prestera_port *port,
 		vid = bridge->bridge_id;
 
 	if (adding)
-		err = prestera_hw_fdb_add(port, fdb_info->addr, vid, false);
+		err = prestera_fdb_add(port, fdb_info->addr, vid, false);
 	else
-		err = prestera_hw_fdb_del(port, fdb_info->addr, vid);
+		err = prestera_fdb_del(port, fdb_info->addr, vid);
 
 	return err;
 }
@@ -901,7 +910,8 @@ prestera_port_vlan_bridge_join(struct prestera_port_vlan *port_vlan,
 	if (port_vlan->br_port)
 		return 0;
 
-	err = prestera_hw_port_flood_set(port, br_port->flags & BR_FLOOD);
+	err = prestera_hw_port_flood_set(port, BR_FLOOD | BR_MCAST_FLOOD,
+					 br_port->flags);
 	if (err)
 		return err;
 
@@ -1009,15 +1019,15 @@ static int prestera_port_vlans_add(struct prestera_port *port,
 {
 	bool flag_untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
 	bool flag_pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
-	struct net_device *dev = vlan->obj.orig_dev;
+	struct net_device *orig_dev = vlan->obj.orig_dev;
 	struct prestera_bridge_port *br_port;
 	struct prestera_switch *sw = port->sw;
 	struct prestera_bridge *bridge;
 
-	if (netif_is_bridge_master(dev))
+	if (netif_is_bridge_master(orig_dev))
 		return 0;
 
-	br_port = prestera_bridge_port_by_dev(sw->swdev, dev);
+	br_port = prestera_bridge_port_by_dev(sw->swdev, port->dev);
 	if (WARN_ON(!br_port))
 		return -EINVAL;
 
@@ -1049,14 +1059,14 @@ static int prestera_port_obj_add(struct net_device *dev,
 static int prestera_port_vlans_del(struct prestera_port *port,
 				   const struct switchdev_obj_port_vlan *vlan)
 {
-	struct net_device *dev = vlan->obj.orig_dev;
+	struct net_device *orig_dev = vlan->obj.orig_dev;
 	struct prestera_bridge_port *br_port;
 	struct prestera_switch *sw = port->sw;
 
-	if (netif_is_bridge_master(dev))
+	if (netif_is_bridge_master(orig_dev))
 		return -EOPNOTSUPP;
 
-	br_port = prestera_bridge_port_by_dev(sw->swdev, dev);
+	br_port = prestera_bridge_port_by_dev(sw->swdev, port->dev);
 	if (WARN_ON(!br_port))
 		return -EINVAL;
 
@@ -1114,10 +1124,26 @@ static void prestera_fdb_event(struct prestera_switch *sw,
 			       struct prestera_event *evt, void *arg)
 {
 	struct switchdev_notifier_fdb_info info;
+	struct net_device *dev = NULL;
 	struct prestera_port *port;
+	struct prestera_lag *lag;
 
-	port = prestera_find_port(sw, evt->fdb_evt.port_id);
-	if (!port)
+	switch (evt->fdb_evt.type) {
+	case PRESTERA_FDB_ENTRY_TYPE_REG_PORT:
+		port = prestera_find_port(sw, evt->fdb_evt.dest.port_id);
+		if (port)
+			dev = port->dev;
+		break;
+	case PRESTERA_FDB_ENTRY_TYPE_LAG:
+		lag = prestera_lag_by_id(sw, evt->fdb_evt.dest.lag_id);
+		if (lag)
+			dev = lag->dev;
+		break;
+	default:
+		return;
+	}
+
+	if (!dev)
 		return;
 
 	info.addr = evt->fdb_evt.data.mac;
@@ -1129,11 +1155,11 @@ static void prestera_fdb_event(struct prestera_switch *sw,
 	switch (evt->id) {
 	case PRESTERA_FDB_EVENT_LEARNED:
 		call_switchdev_notifiers(SWITCHDEV_FDB_ADD_TO_BRIDGE,
-					 port->dev, &info.info, NULL);
+					 dev, &info.info, NULL);
 		break;
 	case PRESTERA_FDB_EVENT_AGED:
 		call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE,
-					 port->dev, &info.info, NULL);
+					 dev, &info.info, NULL);
 		break;
 	}
 
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.h b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.h
index 606e21d2355b..a91bc35d235f 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.h
+++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.h
@@ -7,7 +7,10 @@
 int prestera_switchdev_init(struct prestera_switch *sw);
 void prestera_switchdev_fini(struct prestera_switch *sw);
 
-int prestera_bridge_port_event(struct net_device *dev, unsigned long event,
-			       void *ptr);
+int prestera_bridge_port_join(struct net_device *br_dev,
+			      struct prestera_port *port);
+
+void prestera_bridge_port_leave(struct net_device *br_dev,
+				struct prestera_port *port);
 
 #endif /* _PRESTERA_SWITCHDEV_H_ */
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index e967867828d8..9b48ae4bac39 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1528,6 +1528,7 @@ static int pxa168_eth_remove(struct platform_device *pdev)
 	struct net_device *dev = platform_get_drvdata(pdev);
 	struct pxa168_eth_private *pep = netdev_priv(dev);
 
+	cancel_work_sync(&pep->tx_timeout_task);
 	if (pep->htpr) {
 		dma_free_coherent(pep->dev->dev.parent, HASH_ADDR_TABLE_SIZE,
 				  pep->htpr, pep->htpr_dma);
@@ -1539,7 +1540,6 @@ static int pxa168_eth_remove(struct platform_device *pdev)
 	clk_disable_unprepare(pep->clk);
 	mdiobus_unregister(pep->smi_bus);
 	mdiobus_free(pep->smi_bus);
-	cancel_work_sync(&pep->tx_timeout_task);
 	unregister_netdev(dev);
 	free_netdev(dev);
 	return 0;
diff --git a/drivers/net/ethernet/marvell/skge.h b/drivers/net/ethernet/marvell/skge.h
index 6928abcec0a3..f72217348eb4 100644
--- a/drivers/net/ethernet/marvell/skge.h
+++ b/drivers/net/ethernet/marvell/skge.h
@@ -263,7 +263,7 @@ enum {
 	CHIP_ID_YUKON_LP   = 0xb2, /* Chip ID for YUKON-LP */
 	CHIP_ID_YUKON_XL   = 0xb3, /* Chip ID for YUKON-2 XL */
 	CHIP_ID_YUKON_EC   = 0xb6, /* Chip ID for YUKON-2 EC */
- 	CHIP_ID_YUKON_FE   = 0xb7, /* Chip ID for YUKON-2 FE */
+	CHIP_ID_YUKON_FE   = 0xb7, /* Chip ID for YUKON-2 FE */
 
 	CHIP_REV_YU_LITE_A1  = 3,	/* Chip Rev. for YUKON-Lite A1,A2 */
 	CHIP_REV_YU_LITE_A3  = 7,	/* Chip Rev. for YUKON-Lite A3 */
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 222c32367b2c..8b8bff59c8fe 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -471,7 +471,7 @@ static void sky2_phy_init(struct sky2_hw *hw, unsigned port)
 			adv |= fiber_fc_adv[sky2->flow_mode];
 	} else {
 		reg |= GM_GPCR_AU_FCT_DIS;
- 		reg |= gm_fc_disable[sky2->flow_mode];
+		reg |= gm_fc_disable[sky2->flow_mode];
 
 		/* Forward pause packets to GMAC? */
 		if (sky2->flow_mode & FC_RX)
@@ -1656,16 +1656,16 @@ static void sky2_hw_up(struct sky2_port *sky2)
 	tx_init(sky2);
 
 	/*
- 	 * On dual port PCI-X card, there is an problem where status
+	 * On dual port PCI-X card, there is an problem where status
 	 * can be received out of order due to split transactions
 	 */
 	if (otherdev && netif_running(otherdev) &&
- 	    (cap = pci_find_capability(hw->pdev, PCI_CAP_ID_PCIX))) {
- 		u16 cmd;
+	    (cap = pci_find_capability(hw->pdev, PCI_CAP_ID_PCIX))) {
+		u16 cmd;
 
 		cmd = sky2_pci_read16(hw, cap + PCI_X_CMD);
- 		cmd &= ~PCI_X_CMD_MAX_SPLIT;
- 		sky2_pci_write16(hw, cap + PCI_X_CMD, cmd);
+		cmd &= ~PCI_X_CMD_MAX_SPLIT;
+		sky2_pci_write16(hw, cap + PCI_X_CMD, cmd);
 	}
 
 	sky2_mac_init(hw, port);
@@ -1836,8 +1836,8 @@ static netdev_tx_t sky2_xmit_frame(struct sk_buff *skb,
 	u16 mss;
 	u8 ctrl;
 
- 	if (unlikely(tx_avail(sky2) < tx_le_req(skb)))
-  		return NETDEV_TX_BUSY;
+	if (unlikely(tx_avail(sky2) < tx_le_req(skb)))
+		return NETDEV_TX_BUSY;
 
 	len = skb_headlen(skb);
 	mapping = dma_map_single(&hw->pdev->dev, skb->data, len,
@@ -1866,9 +1866,9 @@ static netdev_tx_t sky2_xmit_frame(struct sk_buff *skb,
 		if (!(hw->flags & SKY2_HW_NEW_LE))
 			mss += ETH_HLEN + ip_hdrlen(skb) + tcp_hdrlen(skb);
 
-  		if (mss != sky2->tx_last_mss) {
+		if (mss != sky2->tx_last_mss) {
 			le = get_tx_le(sky2, &slot);
-  			le->addr = cpu_to_le32(mss);
+			le->addr = cpu_to_le32(mss);
 
 			if (hw->flags & SKY2_HW_NEW_LE)
 				le->opcode = OP_MSS | HW_OWNER;
@@ -1895,8 +1895,8 @@ static netdev_tx_t sky2_xmit_frame(struct sk_buff *skb,
 	/* Handle TCP checksum offload */
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		/* On Yukon EX (some versions) encoding change. */
- 		if (hw->flags & SKY2_HW_AUTO_TX_SUM)
- 			ctrl |= CALSUM;	/* auto checksum */
+		if (hw->flags & SKY2_HW_AUTO_TX_SUM)
+			ctrl |= CALSUM;	/* auto checksum */
 		else {
 			const unsigned offset = skb_transport_offset(skb);
 			u32 tcpsum;
@@ -2503,7 +2503,7 @@ static void skb_put_frags(struct sk_buff *skb, unsigned int hdr_space,
 
 		if (length == 0) {
 			/* don't need this page */
-			__skb_frag_unref(frag);
+			__skb_frag_unref(frag, false);
 			--skb_shinfo(skb)->nr_frags;
 		} else {
 			size = min(length, (unsigned) PAGE_SIZE);
@@ -2557,7 +2557,7 @@ nobuf:
 static struct sk_buff *sky2_receive(struct net_device *dev,
 				    u16 length, u32 status)
 {
- 	struct sky2_port *sky2 = netdev_priv(dev);
+	struct sky2_port *sky2 = netdev_priv(dev);
 	struct rx_ring_info *re = sky2->rx_ring + sky2->rx_next;
 	struct sk_buff *skb = NULL;
 	u16 count = (status & GMR_FS_LEN) >> 16;
@@ -5063,11 +5063,11 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!disable_msi && pci_enable_msi(pdev) == 0) {
 		err = sky2_test_msi(hw);
 		if (err) {
- 			pci_disable_msi(pdev);
+			pci_disable_msi(pdev);
 			if (err != -EOPNOTSUPP)
 				goto err_out_free_netdev;
 		}
- 	}
+	}
 
 	netif_napi_add(dev, &hw->napi, sky2_poll, NAPI_WEIGHT);
 
diff --git a/drivers/net/ethernet/marvell/sky2.h b/drivers/net/ethernet/marvell/sky2.h
index b2dddd8a246c..ddec1627f1a7 100644
--- a/drivers/net/ethernet/marvell/sky2.h
+++ b/drivers/net/ethernet/marvell/sky2.h
@@ -538,8 +538,8 @@ enum {
 	CHIP_ID_YUKON_EC_U = 0xb4, /* YUKON-2 EC Ultra */
 	CHIP_ID_YUKON_EX   = 0xb5, /* YUKON-2 Extreme */
 	CHIP_ID_YUKON_EC   = 0xb6, /* YUKON-2 EC */
- 	CHIP_ID_YUKON_FE   = 0xb7, /* YUKON-2 FE */
- 	CHIP_ID_YUKON_FE_P = 0xb8, /* YUKON-2 FE+ */
+	CHIP_ID_YUKON_FE   = 0xb7, /* YUKON-2 FE */
+	CHIP_ID_YUKON_FE_P = 0xb8, /* YUKON-2 FE+ */
 	CHIP_ID_YUKON_SUPR = 0xb9, /* YUKON-2 Supreme */
 	CHIP_ID_YUKON_UL_2 = 0xba, /* YUKON-2 Ultra 2 */
 	CHIP_ID_YUKON_OPT  = 0xbc, /* YUKON-2 Optima */
@@ -2262,8 +2262,8 @@ struct sky2_port {
 #define SKY2_FLAG_AUTO_SPEED		0x0002
 #define SKY2_FLAG_AUTO_PAUSE		0x0004
 
- 	enum flow_control    flow_mode;
- 	enum flow_control    flow_status;
+	enum flow_control    flow_mode;
+	enum flow_control    flow_status;
 
 #ifdef CONFIG_SKY2_DEBUG
 	struct dentry	     *debugfs;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index e35e4d7ef4d1..cea62b8f554c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -526,7 +526,7 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 fail:
 	while (nr > 0) {
 		nr--;
-		__skb_frag_unref(skb_shinfo(skb)->frags + nr);
+		__skb_frag_unref(skb_shinfo(skb)->frags + nr, false);
 	}
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 461a43f338e6..d62f90aedade 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -79,6 +79,16 @@ config MLX5_ESWITCH
 	        Legacy SRIOV mode (L2 mac vlan steering based).
 	        Switchdev mode (eswitch offloads).
 
+config MLX5_BRIDGE
+	bool
+	depends on MLX5_ESWITCH && BRIDGE
+	default y
+	help
+	  mlx5 ConnectX offloads support for Ethernet Bridging (BRIDGE).
+	  Enable adding representors of mlx5 uplink and VF ports to Bridge and
+	  offloading rules for traffic between such ports. Supports VLANs (trunk and
+	  access modes).
+
 config MLX5_CLS_ACT
 	bool "MLX5 TC classifier action support"
 	depends on MLX5_ESWITCH && NET_CLS_ACT
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index a1223e904190..b5072a3a2585 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o alloc.o port.o mr.o pd.o \
 		transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \
-		fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \
+		fs_counters.o fs_ft_pool.o rl.o lag.o dev.o events.o wq.o lib/gid.o \
 		lib/devcom.o lib/pci_vsc.o lib/dm.o diag/fs_tracepoint.o \
 		diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \
 		fw_reset.o qos.o
@@ -56,6 +56,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH)   += esw/acl/helper.o \
 				      esw/acl/ingress_lgcy.o esw/acl/ingress_ofld.o \
 				      esw/devlink_port.o esw/vporttbl.o
 mlx5_core-$(CONFIG_MLX5_TC_SAMPLE) += esw/sample.o
+mlx5_core-$(CONFIG_MLX5_BRIDGE)    += esw/bridge.o en/rep/bridge.o
 
 mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
 mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 44c458443428..d791d351b489 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -63,6 +63,11 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 	err = devlink_info_version_running_put(req, "fw.version", version_str);
 	if (err)
 		return err;
+	err = devlink_info_version_running_put(req,
+					       DEVLINK_INFO_VERSION_GENERIC_FW,
+					       version_str);
+	if (err)
+		return err;
 
 	/* no pending version, return running (stored) version */
 	if (stored_fw == 0)
@@ -74,8 +79,9 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 	err = devlink_info_version_stored_put(req, "fw.version", version_str);
 	if (err)
 		return err;
-
-	return 0;
+	return devlink_info_version_stored_put(req,
+					       DEVLINK_INFO_VERSION_GENERIC_FW,
+					       version_str);
 }
 
 static int mlx5_devlink_reload_fw_activate(struct devlink *devlink, struct netlink_ext_ack *extack)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index b636d63358d2..b1b51bbba054 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -974,7 +974,6 @@ int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param,
 		  struct mlx5e_xsk_param *xsk, int node,
 		  struct mlx5e_rq *rq);
 int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time);
-void mlx5e_deactivate_rq(struct mlx5e_rq *rq);
 void mlx5e_close_rq(struct mlx5e_rq *rq);
 int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param);
 void mlx5e_destroy_rq(struct mlx5e_rq *rq);
@@ -1163,6 +1162,13 @@ mlx5e_calc_max_nch(struct mlx5e_priv *priv, const struct mlx5e_profile *profile)
 	return priv->netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1);
 }
 
+static inline bool
+mlx5e_tx_mpwqe_supported(struct mlx5_core_dev *mdev)
+{
+	return !is_kdump_kernel() &&
+		MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe);
+}
+
 int mlx5e_priv_init(struct mlx5e_priv *priv,
 		    struct net_device *netdev,
 		    struct mlx5_core_dev *mdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index f410c1268422..150c8e82c738 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -201,7 +201,7 @@ int mlx5e_validate_params(struct mlx5_core_dev *mdev, struct mlx5e_params *param
 
 static struct dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode)
 {
-	struct dim_cq_moder moder;
+	struct dim_cq_moder moder = {};
 
 	moder.cq_period_mode = cq_period_mode;
 	moder.pkts = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
@@ -214,7 +214,7 @@ static struct dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode)
 
 static struct dim_cq_moder mlx5e_get_def_rx_moderation(u8 cq_period_mode)
 {
-	struct dim_cq_moder moder;
+	struct dim_cq_moder moder = {};
 
 	moder.cq_period_mode = cq_period_mode;
 	moder.pkts = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS;
@@ -614,7 +614,7 @@ static u8 mlx5e_build_icosq_log_wq_sz(struct mlx5e_params *params,
 
 static u8 mlx5e_build_async_icosq_log_wq_sz(struct mlx5_core_dev *mdev)
 {
-	if (mlx5_accel_is_ktls_rx(mdev))
+	if (mlx5e_accel_is_ktls_rx(mdev))
 		return MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
 
 	return MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
@@ -643,7 +643,7 @@ static void mlx5e_build_async_icosq_param(struct mlx5_core_dev *mdev,
 
 	mlx5e_build_sq_param_common(mdev, param);
 	param->stop_room = mlx5e_stop_room_for_wqe(1); /* for XSK NOP */
-	param->is_tls = mlx5_accel_is_ktls_rx(mdev);
+	param->is_tls = mlx5e_accel_is_ktls_rx(mdev);
 	if (param->is_tls)
 		param->stop_room += mlx5e_stop_room_for_wqe(1); /* for TLS RX resync NOP */
 	MLX5_SET(sqc, sqc, reg_umr, MLX5_CAP_ETH(mdev, reg_umr_sq));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
new file mode 100644
index 000000000000..7f5efc1b4392
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
@@ -0,0 +1,424 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2021 Mellanox Technologies. */
+
+#include <linux/netdevice.h>
+#include <linux/if_bridge.h>
+#include <net/netevent.h>
+#include <net/switchdev.h>
+#include "bridge.h"
+#include "esw/bridge.h"
+#include "en_rep.h"
+
+#define MLX5_ESW_BRIDGE_UPDATE_INTERVAL 1000
+
+struct mlx5_bridge_switchdev_fdb_work {
+	struct work_struct work;
+	struct switchdev_notifier_fdb_info fdb_info;
+	struct net_device *dev;
+	bool add;
+};
+
+static int mlx5_esw_bridge_port_changeupper(struct notifier_block *nb, void *ptr)
+{
+	struct mlx5_esw_bridge_offloads *br_offloads = container_of(nb,
+								    struct mlx5_esw_bridge_offloads,
+								    netdev_nb);
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct netdev_notifier_changeupper_info *info = ptr;
+	struct netlink_ext_ack *extack;
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5_eswitch *esw;
+	struct mlx5_vport *vport;
+	struct net_device *upper;
+	struct mlx5e_priv *priv;
+	u16 vport_num;
+
+	if (!mlx5e_eswitch_rep(dev))
+		return 0;
+
+	upper = info->upper_dev;
+	if (!netif_is_bridge_master(upper))
+		return 0;
+
+	esw = br_offloads->esw;
+	priv = netdev_priv(dev);
+	if (esw != priv->mdev->priv.eswitch)
+		return 0;
+
+	rpriv = priv->ppriv;
+	vport_num = rpriv->rep->vport;
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
+
+	extack = netdev_notifier_info_to_extack(&info->info);
+
+	return info->linking ?
+		mlx5_esw_bridge_vport_link(upper->ifindex, br_offloads, vport, extack) :
+		mlx5_esw_bridge_vport_unlink(upper->ifindex, br_offloads, vport, extack);
+}
+
+static int mlx5_esw_bridge_switchdev_port_event(struct notifier_block *nb,
+						unsigned long event, void *ptr)
+{
+	int err = 0;
+
+	switch (event) {
+	case NETDEV_PRECHANGEUPPER:
+		break;
+
+	case NETDEV_CHANGEUPPER:
+		err = mlx5_esw_bridge_port_changeupper(nb, ptr);
+		break;
+	}
+
+	return notifier_from_errno(err);
+}
+
+static int mlx5_esw_bridge_port_obj_add(struct net_device *dev,
+					const struct switchdev_obj *obj,
+					struct netlink_ext_ack *extack)
+{
+	const struct switchdev_obj_port_vlan *vlan;
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5_eswitch *esw;
+	struct mlx5_vport *vport;
+	struct mlx5e_priv *priv;
+	u16 vport_num;
+	int err = 0;
+
+	priv = netdev_priv(dev);
+	rpriv = priv->ppriv;
+	vport_num = rpriv->rep->vport;
+	esw = priv->mdev->priv.eswitch;
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
+
+	switch (obj->id) {
+	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
+		err = mlx5_esw_bridge_port_vlan_add(vlan->vid, vlan->flags, esw, vport, extack);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	return err;
+}
+
+static int mlx5_esw_bridge_port_obj_del(struct net_device *dev,
+					const struct switchdev_obj *obj)
+{
+	const struct switchdev_obj_port_vlan *vlan;
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5_eswitch *esw;
+	struct mlx5_vport *vport;
+	struct mlx5e_priv *priv;
+	u16 vport_num;
+
+	priv = netdev_priv(dev);
+	rpriv = priv->ppriv;
+	vport_num = rpriv->rep->vport;
+	esw = priv->mdev->priv.eswitch;
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
+
+	switch (obj->id) {
+	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
+		mlx5_esw_bridge_port_vlan_del(vlan->vid, esw, vport);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static int mlx5_esw_bridge_port_obj_attr_set(struct net_device *dev,
+					     const struct switchdev_attr *attr,
+					     struct netlink_ext_ack *extack)
+{
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5_eswitch *esw;
+	struct mlx5_vport *vport;
+	struct mlx5e_priv *priv;
+	u16 vport_num;
+	int err = 0;
+
+	priv = netdev_priv(dev);
+	rpriv = priv->ppriv;
+	vport_num = rpriv->rep->vport;
+	esw = priv->mdev->priv.eswitch;
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
+
+	switch (attr->id) {
+	case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS:
+		if (attr->u.brport_flags.mask & ~(BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD)) {
+			NL_SET_ERR_MSG_MOD(extack, "Flag is not supported");
+			err = -EINVAL;
+		}
+		break;
+	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
+		break;
+	case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME:
+		err = mlx5_esw_bridge_ageing_time_set(attr->u.ageing_time, esw, vport);
+		break;
+	case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING:
+		err = mlx5_esw_bridge_vlan_filtering_set(attr->u.vlan_filtering, esw, vport);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static int mlx5_esw_bridge_event_blocking(struct notifier_block *unused,
+					  unsigned long event, void *ptr)
+{
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	int err;
+
+	switch (event) {
+	case SWITCHDEV_PORT_OBJ_ADD:
+		err = switchdev_handle_port_obj_add(dev, ptr,
+						    mlx5e_eswitch_rep,
+						    mlx5_esw_bridge_port_obj_add);
+		break;
+	case SWITCHDEV_PORT_OBJ_DEL:
+		err = switchdev_handle_port_obj_del(dev, ptr,
+						    mlx5e_eswitch_rep,
+						    mlx5_esw_bridge_port_obj_del);
+		break;
+	case SWITCHDEV_PORT_ATTR_SET:
+		err = switchdev_handle_port_attr_set(dev, ptr,
+						     mlx5e_eswitch_rep,
+						     mlx5_esw_bridge_port_obj_attr_set);
+		break;
+	default:
+		err = 0;
+	}
+
+	return notifier_from_errno(err);
+}
+
+static void
+mlx5_esw_bridge_cleanup_switchdev_fdb_work(struct mlx5_bridge_switchdev_fdb_work *fdb_work)
+{
+	dev_put(fdb_work->dev);
+	kfree(fdb_work->fdb_info.addr);
+	kfree(fdb_work);
+}
+
+static void mlx5_esw_bridge_switchdev_fdb_event_work(struct work_struct *work)
+{
+	struct mlx5_bridge_switchdev_fdb_work *fdb_work =
+		container_of(work, struct mlx5_bridge_switchdev_fdb_work, work);
+	struct switchdev_notifier_fdb_info *fdb_info =
+		&fdb_work->fdb_info;
+	struct net_device *dev = fdb_work->dev;
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5_eswitch *esw;
+	struct mlx5_vport *vport;
+	struct mlx5e_priv *priv;
+	u16 vport_num;
+
+	rtnl_lock();
+
+	priv = netdev_priv(dev);
+	rpriv = priv->ppriv;
+	vport_num = rpriv->rep->vport;
+	esw = priv->mdev->priv.eswitch;
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		goto out;
+
+	if (fdb_work->add)
+		mlx5_esw_bridge_fdb_create(dev, esw, vport, fdb_info);
+	else
+		mlx5_esw_bridge_fdb_remove(dev, esw, vport, fdb_info);
+
+out:
+	rtnl_unlock();
+	mlx5_esw_bridge_cleanup_switchdev_fdb_work(fdb_work);
+}
+
+static struct mlx5_bridge_switchdev_fdb_work *
+mlx5_esw_bridge_init_switchdev_fdb_work(struct net_device *dev, bool add,
+					struct switchdev_notifier_fdb_info *fdb_info)
+{
+	struct mlx5_bridge_switchdev_fdb_work *work;
+	u8 *addr;
+
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
+	if (!work)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_WORK(&work->work, mlx5_esw_bridge_switchdev_fdb_event_work);
+	memcpy(&work->fdb_info, fdb_info, sizeof(work->fdb_info));
+
+	addr = kzalloc(ETH_ALEN, GFP_ATOMIC);
+	if (!addr) {
+		kfree(work);
+		return ERR_PTR(-ENOMEM);
+	}
+	ether_addr_copy(addr, fdb_info->addr);
+	work->fdb_info.addr = addr;
+
+	dev_hold(dev);
+	work->dev = dev;
+	work->add = add;
+	return work;
+}
+
+static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb,
+					   unsigned long event, void *ptr)
+{
+	struct mlx5_esw_bridge_offloads *br_offloads = container_of(nb,
+								    struct mlx5_esw_bridge_offloads,
+								    nb);
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	struct switchdev_notifier_fdb_info *fdb_info;
+	struct mlx5_bridge_switchdev_fdb_work *work;
+	struct switchdev_notifier_info *info = ptr;
+	struct net_device *upper;
+	struct mlx5e_priv *priv;
+
+	if (!mlx5e_eswitch_rep(dev))
+		return NOTIFY_DONE;
+	priv = netdev_priv(dev);
+	if (priv->mdev->priv.eswitch != br_offloads->esw)
+		return NOTIFY_DONE;
+
+	if (event == SWITCHDEV_PORT_ATTR_SET) {
+		int err = switchdev_handle_port_attr_set(dev, ptr,
+							 mlx5e_eswitch_rep,
+							 mlx5_esw_bridge_port_obj_attr_set);
+		return notifier_from_errno(err);
+	}
+
+	upper = netdev_master_upper_dev_get_rcu(dev);
+	if (!upper)
+		return NOTIFY_DONE;
+	if (!netif_is_bridge_master(upper))
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case SWITCHDEV_FDB_ADD_TO_DEVICE:
+	case SWITCHDEV_FDB_DEL_TO_DEVICE:
+		fdb_info = container_of(info,
+					struct switchdev_notifier_fdb_info,
+					info);
+
+		work = mlx5_esw_bridge_init_switchdev_fdb_work(dev,
+							       event == SWITCHDEV_FDB_ADD_TO_DEVICE,
+							       fdb_info);
+		if (IS_ERR(work)) {
+			WARN_ONCE(1, "Failed to init switchdev work, err=%ld",
+				  PTR_ERR(work));
+			return notifier_from_errno(PTR_ERR(work));
+		}
+
+		queue_work(br_offloads->wq, &work->work);
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static void mlx5_esw_bridge_update_work(struct work_struct *work)
+{
+	struct mlx5_esw_bridge_offloads *br_offloads = container_of(work,
+								    struct mlx5_esw_bridge_offloads,
+								    update_work.work);
+
+	rtnl_lock();
+	mlx5_esw_bridge_update(br_offloads);
+	rtnl_unlock();
+
+	queue_delayed_work(br_offloads->wq, &br_offloads->update_work,
+			   msecs_to_jiffies(MLX5_ESW_BRIDGE_UPDATE_INTERVAL));
+}
+
+void mlx5e_rep_bridge_init(struct mlx5e_priv *priv)
+{
+	struct mlx5_esw_bridge_offloads *br_offloads;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_eswitch *esw =
+		mdev->priv.eswitch;
+	int err;
+
+	rtnl_lock();
+	br_offloads = mlx5_esw_bridge_init(esw);
+	rtnl_unlock();
+	if (IS_ERR(br_offloads)) {
+		esw_warn(mdev, "Failed to init esw bridge (err=%ld)\n", PTR_ERR(br_offloads));
+		return;
+	}
+
+	br_offloads->wq = alloc_ordered_workqueue("mlx5_bridge_wq", 0);
+	if (!br_offloads->wq) {
+		esw_warn(mdev, "Failed to allocate bridge offloads workqueue\n");
+		goto err_alloc_wq;
+	}
+	INIT_DELAYED_WORK(&br_offloads->update_work, mlx5_esw_bridge_update_work);
+	queue_delayed_work(br_offloads->wq, &br_offloads->update_work,
+			   msecs_to_jiffies(MLX5_ESW_BRIDGE_UPDATE_INTERVAL));
+
+	br_offloads->nb.notifier_call = mlx5_esw_bridge_switchdev_event;
+	err = register_switchdev_notifier(&br_offloads->nb);
+	if (err) {
+		esw_warn(mdev, "Failed to register switchdev notifier (err=%d)\n", err);
+		goto err_register_swdev;
+	}
+
+	br_offloads->nb_blk.notifier_call = mlx5_esw_bridge_event_blocking;
+	err = register_switchdev_blocking_notifier(&br_offloads->nb_blk);
+	if (err) {
+		esw_warn(mdev, "Failed to register blocking switchdev notifier (err=%d)\n", err);
+		goto err_register_swdev_blk;
+	}
+
+	br_offloads->netdev_nb.notifier_call = mlx5_esw_bridge_switchdev_port_event;
+	err = register_netdevice_notifier(&br_offloads->netdev_nb);
+	if (err) {
+		esw_warn(mdev, "Failed to register bridge offloads netdevice notifier (err=%d)\n",
+			 err);
+		goto err_register_netdev;
+	}
+	return;
+
+err_register_netdev:
+	unregister_switchdev_blocking_notifier(&br_offloads->nb_blk);
+err_register_swdev_blk:
+	unregister_switchdev_notifier(&br_offloads->nb);
+err_register_swdev:
+	destroy_workqueue(br_offloads->wq);
+err_alloc_wq:
+	mlx5_esw_bridge_cleanup(esw);
+}
+
+void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv)
+{
+	struct mlx5_esw_bridge_offloads *br_offloads;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_eswitch *esw =
+		mdev->priv.eswitch;
+
+	br_offloads = esw->br_offloads;
+	if (!br_offloads)
+		return;
+
+	unregister_netdevice_notifier(&br_offloads->netdev_nb);
+	unregister_switchdev_blocking_notifier(&br_offloads->nb_blk);
+	unregister_switchdev_notifier(&br_offloads->nb);
+	cancel_delayed_work(&br_offloads->update_work);
+	destroy_workqueue(br_offloads->wq);
+	rtnl_lock();
+	mlx5_esw_bridge_cleanup(esw);
+	rtnl_unlock();
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.h
new file mode 100644
index 000000000000..fbeb64242831
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021 Mellanox Technologies. */
+
+#ifndef __MLX5_EN_REP_BRIDGE__
+#define __MLX5_EN_REP_BRIDGE__
+
+#include "en.h"
+
+#if IS_ENABLED(CONFIG_MLX5_BRIDGE)
+
+void mlx5e_rep_bridge_init(struct mlx5e_priv *priv);
+void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv);
+
+#else /* CONFIG_MLX5_BRIDGE */
+
+static inline void mlx5e_rep_bridge_init(struct mlx5e_priv *priv) {}
+static inline void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv) {}
+
+#endif /* CONFIG_MLX5_BRIDGE */
+
+#endif /* __MLX5_EN_REP_BRIDGE__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index 85eaadc989df..059799e4f483 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -613,7 +613,7 @@ static bool mlx5e_restore_skb(struct sk_buff *skb, u32 chain, u32 reg_c1,
 			      struct mlx5e_tc_update_priv *tc_priv)
 {
 	struct mlx5e_priv *priv = netdev_priv(skb->dev);
-	u32 tunnel_id = reg_c1 >> ESW_TUN_OFFSET;
+	u32 tunnel_id = (reg_c1 >> ESW_TUN_OFFSET) & TUNNEL_ID_MASK;
 
 	if (chain) {
 		struct mlx5_rep_uplink_priv *uplink_priv;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index 5da5e5323a44..91e7a01e32be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -23,7 +23,7 @@
 #include "en_tc.h"
 #include "en_rep.h"
 
-#define MLX5_CT_ZONE_BITS (mlx5e_tc_attr_to_reg_mappings[ZONE_TO_REG].mlen * 8)
+#define MLX5_CT_ZONE_BITS (mlx5e_tc_attr_to_reg_mappings[ZONE_TO_REG].mlen)
 #define MLX5_CT_ZONE_MASK GENMASK(MLX5_CT_ZONE_BITS - 1, 0)
 #define MLX5_CT_STATE_ESTABLISHED_BIT BIT(1)
 #define MLX5_CT_STATE_TRK_BIT BIT(2)
@@ -32,11 +32,11 @@
 #define MLX5_CT_STATE_RELATED_BIT BIT(5)
 #define MLX5_CT_STATE_INVALID_BIT BIT(6)
 
-#define MLX5_FTE_ID_BITS (mlx5e_tc_attr_to_reg_mappings[FTEID_TO_REG].mlen * 8)
+#define MLX5_FTE_ID_BITS (mlx5e_tc_attr_to_reg_mappings[FTEID_TO_REG].mlen)
 #define MLX5_FTE_ID_MAX GENMASK(MLX5_FTE_ID_BITS - 1, 0)
 #define MLX5_FTE_ID_MASK MLX5_FTE_ID_MAX
 
-#define MLX5_CT_LABELS_BITS (mlx5e_tc_attr_to_reg_mappings[LABELS_TO_REG].mlen * 8)
+#define MLX5_CT_LABELS_BITS (mlx5e_tc_attr_to_reg_mappings[LABELS_TO_REG].mlen)
 #define MLX5_CT_LABELS_MASK GENMASK(MLX5_CT_LABELS_BITS - 1, 0)
 
 #define ct_dbg(fmt, args...)\
@@ -150,6 +150,11 @@ struct mlx5_ct_entry {
 	unsigned long flags;
 };
 
+static void
+mlx5_tc_ct_entry_destroy_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
+				 struct mlx5_flow_attr *attr,
+				 struct mlx5e_mod_hdr_handle *mh);
+
 static const struct rhashtable_params cts_ht_params = {
 	.head_offset = offsetof(struct mlx5_ct_entry, node),
 	.key_offset = offsetof(struct mlx5_ct_entry, cookie),
@@ -458,8 +463,7 @@ mlx5_tc_ct_entry_del_rule(struct mlx5_tc_ct_priv *ct_priv,
 	ct_dbg("Deleting ct entry rule in zone %d", entry->tuple.zone);
 
 	mlx5_tc_rule_delete(netdev_priv(ct_priv->netdev), zone_rule->rule, attr);
-	mlx5e_mod_hdr_detach(ct_priv->dev,
-			     ct_priv->mod_hdr_tbl, zone_rule->mh);
+	mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, zone_rule->mh);
 	mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
 	kfree(attr);
 }
@@ -686,15 +690,27 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
 	if (err)
 		goto err_mapping;
 
-	*mh = mlx5e_mod_hdr_attach(ct_priv->dev,
-				   ct_priv->mod_hdr_tbl,
-				   ct_priv->ns_type,
-				   &mod_acts);
-	if (IS_ERR(*mh)) {
-		err = PTR_ERR(*mh);
-		goto err_mapping;
+	if (nat) {
+		attr->modify_hdr = mlx5_modify_header_alloc(ct_priv->dev, ct_priv->ns_type,
+							    mod_acts.num_actions,
+							    mod_acts.actions);
+		if (IS_ERR(attr->modify_hdr)) {
+			err = PTR_ERR(attr->modify_hdr);
+			goto err_mapping;
+		}
+
+		*mh = NULL;
+	} else {
+		*mh = mlx5e_mod_hdr_attach(ct_priv->dev,
+					   ct_priv->mod_hdr_tbl,
+					   ct_priv->ns_type,
+					   &mod_acts);
+		if (IS_ERR(*mh)) {
+			err = PTR_ERR(*mh);
+			goto err_mapping;
+		}
+		attr->modify_hdr = mlx5e_mod_hdr_get(*mh);
 	}
-	attr->modify_hdr = mlx5e_mod_hdr_get(*mh);
 
 	dealloc_mod_hdr_actions(&mod_acts);
 	return 0;
@@ -705,6 +721,17 @@ err_mapping:
 	return err;
 }
 
+static void
+mlx5_tc_ct_entry_destroy_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
+				 struct mlx5_flow_attr *attr,
+				 struct mlx5e_mod_hdr_handle *mh)
+{
+	if (mh)
+		mlx5e_mod_hdr_detach(ct_priv->dev, ct_priv->mod_hdr_tbl, mh);
+	else
+		mlx5_modify_header_dealloc(ct_priv->dev, attr->modify_hdr);
+}
+
 static int
 mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 			  struct flow_rule *flow_rule,
@@ -767,8 +794,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 	return 0;
 
 err_rule:
-	mlx5e_mod_hdr_detach(ct_priv->dev,
-			     ct_priv->mod_hdr_tbl, zone_rule->mh);
+	mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, zone_rule->mh);
 	mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
 err_mod_hdr:
 	kfree(attr);
@@ -918,7 +944,7 @@ mlx5_tc_ct_shared_counter_get(struct mlx5_tc_ct_priv *ct_priv,
 	}
 
 	if (rev_entry && refcount_inc_not_zero(&rev_entry->counter->refcount)) {
-		ct_dbg("Using shared counter entry=0x%p rev=0x%p\n", entry, rev_entry);
+		ct_dbg("Using shared counter entry=0x%p rev=0x%p", entry, rev_entry);
 		shared_counter = rev_entry->counter;
 		spin_unlock_bh(&ct_priv->ht_lock);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
index 69e618d17071..644cf1641cde 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
@@ -33,15 +33,15 @@ struct mlx5_ct_attr {
 #define zone_to_reg_ct {\
 	.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_2,\
 	.moffset = 0,\
-	.mlen = 2,\
+	.mlen = 16,\
 	.soffset = MLX5_BYTE_OFF(fte_match_param,\
-				 misc_parameters_2.metadata_reg_c_2) + 2,\
+				 misc_parameters_2.metadata_reg_c_2),\
 }
 
 #define ctstate_to_reg_ct {\
 	.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_2,\
-	.moffset = 2,\
-	.mlen = 2,\
+	.moffset = 16,\
+	.mlen = 16,\
 	.soffset = MLX5_BYTE_OFF(fte_match_param,\
 				 misc_parameters_2.metadata_reg_c_2),\
 }
@@ -49,7 +49,7 @@ struct mlx5_ct_attr {
 #define mark_to_reg_ct {\
 	.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_3,\
 	.moffset = 0,\
-	.mlen = 4,\
+	.mlen = 32,\
 	.soffset = MLX5_BYTE_OFF(fte_match_param,\
 				 misc_parameters_2.metadata_reg_c_3),\
 }
@@ -57,7 +57,7 @@ struct mlx5_ct_attr {
 #define labels_to_reg_ct {\
 	.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_4,\
 	.moffset = 0,\
-	.mlen = 4,\
+	.mlen = 32,\
 	.soffset = MLX5_BYTE_OFF(fte_match_param,\
 				 misc_parameters_2.metadata_reg_c_4),\
 }
@@ -65,7 +65,7 @@ struct mlx5_ct_attr {
 #define fteid_to_reg_ct {\
 	.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_5,\
 	.moffset = 0,\
-	.mlen = 4,\
+	.mlen = 32,\
 	.soffset = MLX5_BYTE_OFF(fte_match_param,\
 				 misc_parameters_2.metadata_reg_c_5),\
 }
@@ -73,20 +73,19 @@ struct mlx5_ct_attr {
 #define zone_restore_to_reg_ct {\
 	.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_1,\
 	.moffset = 0,\
-	.mlen = (ESW_ZONE_ID_BITS / 8),\
+	.mlen = ESW_ZONE_ID_BITS,\
 	.soffset = MLX5_BYTE_OFF(fte_match_param,\
-				 misc_parameters_2.metadata_reg_c_1) + 3,\
+				 misc_parameters_2.metadata_reg_c_1),\
 }
 
 #define nic_zone_restore_to_reg_ct {\
 	.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_B,\
-	.moffset = 2,\
-	.mlen = (ESW_ZONE_ID_BITS / 8),\
+	.moffset = 16,\
+	.mlen = ESW_ZONE_ID_BITS,\
 }
 
 #define REG_MAPPING_MLEN(reg) (mlx5e_tc_attr_to_reg_mappings[reg].mlen)
 #define REG_MAPPING_MOFFSET(reg) (mlx5e_tc_attr_to_reg_mappings[reg].moffset)
-#define REG_MAPPING_SHIFT(reg) (REG_MAPPING_MOFFSET(reg) * 8)
 
 #if IS_ENABLED(CONFIG_MLX5_TC_CT)
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 172e0474f2e6..8f79f04eccd6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -212,6 +212,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
 	const struct ip_tunnel_key *tun_key = &e->tun_info->key;
+	struct mlx5_pkt_reformat_params reformat_params;
 	struct mlx5e_neigh m_neigh = {};
 	TC_TUN_ROUTE_ATTR_INIT(attr);
 	int ipv4_encap_size;
@@ -295,9 +296,12 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 		 */
 		goto release_neigh;
 	}
-	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev,
-						     e->reformat_type,
-						     ipv4_encap_size, encap_header,
+
+	memset(&reformat_params, 0, sizeof(reformat_params));
+	reformat_params.type = e->reformat_type;
+	reformat_params.size = ipv4_encap_size;
+	reformat_params.data = encap_header;
+	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params,
 						     MLX5_FLOW_NAMESPACE_FDB);
 	if (IS_ERR(e->pkt_reformat)) {
 		err = PTR_ERR(e->pkt_reformat);
@@ -324,6 +328,7 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv,
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
 	const struct ip_tunnel_key *tun_key = &e->tun_info->key;
+	struct mlx5_pkt_reformat_params reformat_params;
 	TC_TUN_ROUTE_ATTR_INIT(attr);
 	int ipv4_encap_size;
 	char *encap_header;
@@ -396,9 +401,12 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv,
 		 */
 		goto release_neigh;
 	}
-	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev,
-						     e->reformat_type,
-						     ipv4_encap_size, encap_header,
+
+	memset(&reformat_params, 0, sizeof(reformat_params));
+	reformat_params.type = e->reformat_type;
+	reformat_params.size = ipv4_encap_size;
+	reformat_params.data = encap_header;
+	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params,
 						     MLX5_FLOW_NAMESPACE_FDB);
 	if (IS_ERR(e->pkt_reformat)) {
 		err = PTR_ERR(e->pkt_reformat);
@@ -471,6 +479,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
 	const struct ip_tunnel_key *tun_key = &e->tun_info->key;
+	struct mlx5_pkt_reformat_params reformat_params;
 	struct mlx5e_neigh m_neigh = {};
 	TC_TUN_ROUTE_ATTR_INIT(attr);
 	struct ipv6hdr *ip6h;
@@ -553,9 +562,11 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 		goto release_neigh;
 	}
 
-	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev,
-						     e->reformat_type,
-						     ipv6_encap_size, encap_header,
+	memset(&reformat_params, 0, sizeof(reformat_params));
+	reformat_params.type = e->reformat_type;
+	reformat_params.size = ipv6_encap_size;
+	reformat_params.data = encap_header;
+	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params,
 						     MLX5_FLOW_NAMESPACE_FDB);
 	if (IS_ERR(e->pkt_reformat)) {
 		err = PTR_ERR(e->pkt_reformat);
@@ -582,6 +593,7 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv,
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
 	const struct ip_tunnel_key *tun_key = &e->tun_info->key;
+	struct mlx5_pkt_reformat_params reformat_params;
 	TC_TUN_ROUTE_ATTR_INIT(attr);
 	struct ipv6hdr *ip6h;
 	int ipv6_encap_size;
@@ -654,9 +666,11 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv,
 		goto release_neigh;
 	}
 
-	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev,
-						     e->reformat_type,
-						     ipv6_encap_size, encap_header,
+	memset(&reformat_params, 0, sizeof(reformat_params));
+	reformat_params.type = e->reformat_type;
+	reformat_params.size = ipv6_encap_size;
+	reformat_params.data = encap_header;
+	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params,
 						     MLX5_FLOW_NAMESPACE_FDB);
 	if (IS_ERR(e->pkt_reformat)) {
 		err = PTR_ERR(e->pkt_reformat);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index 490131e06efb..2e846b741280 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -120,6 +120,7 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 			      struct list_head *flow_list)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_pkt_reformat_params reformat_params;
 	struct mlx5_esw_flow_attr *esw_attr;
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_attr *attr;
@@ -130,9 +131,12 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 	if (e->flags & MLX5_ENCAP_ENTRY_NO_ROUTE)
 		return;
 
+	memset(&reformat_params, 0, sizeof(reformat_params));
+	reformat_params.type = e->reformat_type;
+	reformat_params.size = e->encap_size;
+	reformat_params.data = e->encap_header;
 	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev,
-						     e->reformat_type,
-						     e->encap_size, e->encap_header,
+						     &reformat_params,
 						     MLX5_FLOW_NAMESPACE_FDB);
 	if (IS_ERR(e->pkt_reformat)) {
 		mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %lu\n",
@@ -839,6 +843,7 @@ int mlx5e_attach_decap(struct mlx5e_priv *priv,
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5_esw_flow_attr *attr = flow->attr->esw_attr;
+	struct mlx5_pkt_reformat_params reformat_params;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5e_decap_entry *d;
 	struct mlx5e_decap_key key;
@@ -880,10 +885,12 @@ int mlx5e_attach_decap(struct mlx5e_priv *priv,
 	hash_add_rcu(esw->offloads.decap_tbl, &d->hlist, hash_key);
 	mutex_unlock(&esw->offloads.decap_tbl_lock);
 
+	memset(&reformat_params, 0, sizeof(reformat_params));
+	reformat_params.type = MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2;
+	reformat_params.size = sizeof(parse_attr->eth);
+	reformat_params.data = &parse_attr->eth;
 	d->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev,
-						     MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2,
-						     sizeof(parse_attr->eth),
-						     &parse_attr->eth,
+						     &reformat_params,
 						     MLX5_FLOW_NAMESPACE_FDB);
 	if (IS_ERR(d->pkt_reformat)) {
 		err = PTR_ERR(d->pkt_reformat);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index 00af0b831a28..d964665eaa63 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -162,7 +162,7 @@ static inline unsigned int mlx5e_accel_tx_ids_len(struct mlx5e_txqsq *sq,
 /* Part of the eseg touched by TX offloads */
 #define MLX5E_ACCEL_ESEG_LEN offsetof(struct mlx5_wqe_eth_seg, mss)
 
-static inline bool mlx5e_accel_tx_eseg(struct mlx5e_priv *priv,
+static inline void mlx5e_accel_tx_eseg(struct mlx5e_priv *priv,
 				       struct sk_buff *skb,
 				       struct mlx5_wqe_eth_seg *eseg, u16 ihs)
 {
@@ -175,8 +175,6 @@ static inline bool mlx5e_accel_tx_eseg(struct mlx5e_priv *priv,
 	if (skb->encapsulation && skb->ip_summed == CHECKSUM_PARTIAL)
 		mlx5e_tx_tunnel_accel(skb, eseg, ihs);
 #endif
-
-	return true;
 }
 
 static inline void mlx5e_accel_tx_finish(struct mlx5e_txqsq *sq,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
index 95293ee0d38d..d93aadbf10da 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
@@ -59,12 +59,15 @@ void mlx5e_ktls_build_netdev(struct mlx5e_priv *priv)
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
 
-	if (mlx5_accel_is_ktls_tx(mdev)) {
+	if (!mlx5e_accel_is_ktls_tx(mdev) && !mlx5e_accel_is_ktls_rx(mdev))
+		return;
+
+	if (mlx5e_accel_is_ktls_tx(mdev)) {
 		netdev->hw_features |= NETIF_F_HW_TLS_TX;
 		netdev->features    |= NETIF_F_HW_TLS_TX;
 	}
 
-	if (mlx5_accel_is_ktls_rx(mdev))
+	if (mlx5e_accel_is_ktls_rx(mdev))
 		netdev->hw_features |= NETIF_F_HW_TLS_RX;
 
 	netdev->tlsdev_ops = &mlx5e_ktls_ops;
@@ -89,7 +92,7 @@ int mlx5e_ktls_init_rx(struct mlx5e_priv *priv)
 {
 	int err;
 
-	if (!mlx5_accel_is_ktls_rx(priv->mdev))
+	if (!mlx5e_accel_is_ktls_rx(priv->mdev))
 		return 0;
 
 	priv->tls->rx_wq = create_singlethread_workqueue("mlx5e_tls_rx");
@@ -109,7 +112,7 @@ int mlx5e_ktls_init_rx(struct mlx5e_priv *priv)
 
 void mlx5e_ktls_cleanup_rx(struct mlx5e_priv *priv)
 {
-	if (!mlx5_accel_is_ktls_rx(priv->mdev))
+	if (!mlx5e_accel_is_ktls_rx(priv->mdev))
 		return;
 
 	if (priv->netdev->features & NETIF_F_HW_TLS_RX)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
index aaa579bf9a39..5833deb2354c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
@@ -15,6 +15,25 @@ int mlx5e_ktls_set_feature_rx(struct net_device *netdev, bool enable);
 struct mlx5e_ktls_resync_resp *
 mlx5e_ktls_rx_resync_create_resp_list(void);
 void mlx5e_ktls_rx_resync_destroy_resp_list(struct mlx5e_ktls_resync_resp *resp_list);
+
+static inline bool mlx5e_accel_is_ktls_tx(struct mlx5_core_dev *mdev)
+{
+	return !is_kdump_kernel() &&
+		mlx5_accel_is_ktls_tx(mdev);
+}
+
+static inline bool mlx5e_accel_is_ktls_rx(struct mlx5_core_dev *mdev)
+{
+	return !is_kdump_kernel() &&
+		mlx5_accel_is_ktls_rx(mdev);
+}
+
+static inline bool mlx5e_accel_is_ktls_device(struct mlx5_core_dev *mdev)
+{
+	return !is_kdump_kernel() &&
+		mlx5_accel_is_ktls_device(mdev);
+}
+
 #else
 
 static inline void mlx5e_ktls_build_netdev(struct mlx5e_priv *priv)
@@ -44,6 +63,11 @@ mlx5e_ktls_rx_resync_create_resp_list(void)
 
 static inline void
 mlx5e_ktls_rx_resync_destroy_resp_list(struct mlx5e_ktls_resync_resp *resp_list) {}
+
+static inline bool mlx5e_accel_is_ktls_tx(struct mlx5_core_dev *mdev) { return false; }
+static inline bool mlx5e_accel_is_ktls_rx(struct mlx5_core_dev *mdev) { return false; }
+static inline bool mlx5e_accel_is_ktls_device(struct mlx5_core_dev *mdev) { return false; }
+
 #endif
 
 #endif /* __MLX5E_TLS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 51bdf71073f3..2c0a9344338a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -23,10 +23,13 @@ mlx5e_ktls_dumps_num_wqes(struct mlx5e_params *params, unsigned int nfrags,
 	return nfrags + DIV_ROUND_UP(sync_len, MLX5E_SW2HW_MTU(params, params->sw_mtu));
 }
 
-u16 mlx5e_ktls_get_stop_room(struct mlx5e_params *params)
+u16 mlx5e_ktls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
 {
 	u16 num_dumps, stop_room = 0;
 
+	if (!mlx5e_accel_is_ktls_tx(mdev))
+		return 0;
+
 	num_dumps = mlx5e_ktls_dumps_num_wqes(params, MAX_SKB_FRAGS, TLS_MAX_PAYLOAD_SIZE);
 
 	stop_room += mlx5e_stop_room_for_wqe(MLX5E_TLS_SET_STATIC_PARAMS_WQEBBS);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h
index 8f79335057dc..08c9d5134479 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h
@@ -14,7 +14,7 @@ struct mlx5e_accel_tx_tls_state {
 	u32 tls_tisn;
 };
 
-u16 mlx5e_ktls_get_stop_room(struct mlx5e_params *params);
+u16 mlx5e_ktls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params);
 
 bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *sq,
 			      struct sk_buff *skb, int datalen,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
index d6b21b899dbc..b8fc863aa68d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
@@ -192,13 +192,13 @@ void mlx5e_tls_build_netdev(struct mlx5e_priv *priv)
 	struct net_device *netdev = priv->netdev;
 	u32 caps;
 
-	if (mlx5_accel_is_ktls_device(priv->mdev)) {
+	if (mlx5e_accel_is_ktls_device(priv->mdev)) {
 		mlx5e_ktls_build_netdev(priv);
 		return;
 	}
 
 	/* FPGA */
-	if (!mlx5_accel_is_tls_device(priv->mdev))
+	if (!mlx5e_accel_is_tls_device(priv->mdev))
 		return;
 
 	caps = mlx5_accel_tls_device_caps(priv->mdev);
@@ -224,7 +224,7 @@ int mlx5e_tls_init(struct mlx5e_priv *priv)
 {
 	struct mlx5e_tls *tls;
 
-	if (!mlx5_accel_is_tls_device(priv->mdev))
+	if (!mlx5e_accel_is_tls_device(priv->mdev))
 		return 0;
 
 	tls = kzalloc(sizeof(*tls), GFP_KERNEL);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
index 4c9274d390da..3fd6fd69bbd0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
@@ -103,11 +103,18 @@ int mlx5e_tls_get_count(struct mlx5e_priv *priv);
 int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data);
 int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data);
 
+static inline bool mlx5e_accel_is_tls_device(struct mlx5_core_dev *mdev)
+{
+	return !is_kdump_kernel() &&
+		mlx5_accel_is_tls_device(mdev);
+}
+
 #else
 
 static inline void mlx5e_tls_build_netdev(struct mlx5e_priv *priv)
 {
-	if (mlx5_accel_is_ktls_device(priv->mdev))
+	if (!is_kdump_kernel() &&
+	    mlx5_accel_is_ktls_device(priv->mdev))
 		mlx5e_ktls_build_netdev(priv);
 }
 
@@ -117,6 +124,7 @@ static inline void mlx5e_tls_cleanup(struct mlx5e_priv *priv) { }
 static inline int mlx5e_tls_get_count(struct mlx5e_priv *priv) { return 0; }
 static inline int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data) { return 0; }
 static inline int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data) { return 0; }
+static inline bool mlx5e_accel_is_tls_device(struct mlx5_core_dev *mdev) { return false; }
 
 #endif
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index 82dc09aaa7fc..7a700f913582 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -273,7 +273,7 @@ bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
 	if (WARN_ON_ONCE(tls_ctx->netdev != netdev))
 		goto err_out;
 
-	if (mlx5_accel_is_ktls_tx(sq->mdev))
+	if (mlx5e_accel_is_ktls_tx(sq->mdev))
 		return mlx5e_ktls_handle_tx_skb(tls_ctx, sq, skb, datalen, state);
 
 	/* FPGA */
@@ -378,11 +378,11 @@ void mlx5e_tls_handle_rx_skb_metadata(struct mlx5e_rq *rq, struct sk_buff *skb,
 
 u16 mlx5e_tls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
 {
-	if (!mlx5_accel_is_tls_device(mdev))
+	if (!mlx5e_accel_is_tls_device(mdev))
 		return 0;
 
-	if (mlx5_accel_is_ktls_device(mdev))
-		return mlx5e_ktls_get_stop_room(params);
+	if (mlx5e_accel_is_ktls_device(mdev))
+		return mlx5e_ktls_get_stop_room(mdev, params);
 
 	/* FPGA */
 	/* Resync SKB. */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
index 29463bdb7715..ffc84f9b41b0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
@@ -58,7 +58,7 @@ static const struct counter_desc *get_tls_atomic_stats(struct mlx5e_priv *priv)
 {
 	if (!priv->tls)
 		return NULL;
-	if (mlx5_accel_is_ktls_device(priv->mdev))
+	if (mlx5e_accel_is_ktls_device(priv->mdev))
 		return mlx5e_ktls_sw_stats_desc;
 	return mlx5e_tls_sw_stats_desc;
 }
@@ -67,7 +67,7 @@ int mlx5e_tls_get_count(struct mlx5e_priv *priv)
 {
 	if (!priv->tls)
 		return 0;
-	if (mlx5_accel_is_ktls_device(priv->mdev))
+	if (mlx5e_accel_is_ktls_device(priv->mdev))
 		return ARRAY_SIZE(mlx5e_ktls_sw_stats_desc);
 	return ARRAY_SIZE(mlx5e_tls_sw_stats_desc);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index d6513aef5cd4..bd72572e03d1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1992,7 +1992,7 @@ static int set_pflag_tx_mpwqe_common(struct net_device *netdev, u32 flag, bool e
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_params new_params;
 
-	if (enable && !MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe))
+	if (enable && !mlx5e_tx_mpwqe_supported(mdev))
 		return -EOPNOTSUPP;
 
 	new_params = priv->channels.params;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index d26b8ed51195..7d732fac09f0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -91,12 +91,16 @@ void mlx5e_update_carrier(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u8 port_state;
+	bool up;
 
 	port_state = mlx5_query_vport_state(mdev,
 					    MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT,
 					    0);
 
-	if (port_state == VPORT_STATE_UP) {
+	up = port_state == VPORT_STATE_UP;
+	if (up == netif_carrier_ok(priv->netdev))
+		netif_carrier_event(priv->netdev);
+	if (up) {
 		netdev_info(priv->netdev, "Link up\n");
 		netif_carrier_on(priv->netdev);
 	} else {
@@ -853,7 +857,7 @@ int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param,
 	if (err)
 		goto err_destroy_rq;
 
-	if (mlx5e_is_tls_on(rq->priv) && !mlx5_accel_is_ktls_device(mdev))
+	if (mlx5e_is_tls_on(rq->priv) && !mlx5e_accel_is_ktls_device(mdev))
 		__set_bit(MLX5E_RQ_STATE_FPGA_TLS, &rq->state); /* must be FPGA */
 
 	if (MLX5_CAP_ETH(mdev, cqe_checksum_full))
@@ -4661,12 +4665,10 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 	params->log_sq_size = is_kdump_kernel() ?
 		MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE :
 		MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
-	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE,
-			MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe));
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE, mlx5e_tx_mpwqe_supported(mdev));
 
 	/* XDP SQ */
-	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE,
-			MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe));
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE, mlx5e_tx_mpwqe_supported(mdev));
 
 	/* set CQE compression */
 	params->rx_cqe_compress_def = false;
@@ -5103,7 +5105,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	mlx5e_set_netdev_mtu_boundaries(priv);
 	mlx5e_set_dev_port_mtu(priv);
 
-	mlx5_lag_add(mdev, netdev);
+	mlx5_lag_add_netdev(mdev, netdev);
 
 	mlx5e_enable_async_events(priv);
 	mlx5e_enable_blocking_events(priv);
@@ -5151,7 +5153,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 		priv->en_trap = NULL;
 	}
 	mlx5e_disable_async_events(priv);
-	mlx5_lag_remove(mdev);
+	mlx5_lag_remove_netdev(mdev, priv->netdev);
 	mlx5_vxlan_reset_to_default(mdev->vxlan);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 34eb1118670f..2d2cc5f3b03f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -45,6 +45,7 @@
 #include "en_tc.h"
 #include "en/rep/tc.h"
 #include "en/rep/neigh.h"
+#include "en/rep/bridge.h"
 #include "en/devlink.h"
 #include "fs_core.h"
 #include "lib/mlx5.h"
@@ -536,13 +537,13 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = {
 	.ndo_change_carrier      = mlx5e_rep_change_carrier,
 };
 
-bool mlx5e_eswitch_uplink_rep(struct net_device *netdev)
+bool mlx5e_eswitch_uplink_rep(const struct net_device *netdev)
 {
 	return netdev->netdev_ops == &mlx5e_netdev_ops &&
 	       mlx5e_is_uplink_rep(netdev_priv(netdev));
 }
 
-bool mlx5e_eswitch_vf_rep(struct net_device *netdev)
+bool mlx5e_eswitch_vf_rep(const struct net_device *netdev)
 {
 	return netdev->netdev_ops == &mlx5e_netdev_ops_rep;
 }
@@ -975,12 +976,13 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 	if (MLX5_CAP_GEN(mdev, uplink_follow))
 		mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK,
 					      0, 0, MLX5_VPORT_ADMIN_STATE_AUTO);
-	mlx5_lag_add(mdev, netdev);
+	mlx5_lag_add_netdev(mdev, netdev);
 	priv->events_nb.notifier_call = uplink_rep_async_event;
 	mlx5_notifier_register(mdev, &priv->events_nb);
 	mlx5e_dcbnl_initialize(priv);
 	mlx5e_dcbnl_init_app(priv);
 	mlx5e_rep_neigh_init(rpriv);
+	mlx5e_rep_bridge_init(priv);
 
 	netdev->wanted_features |= NETIF_F_HW_TC;
 
@@ -1002,11 +1004,12 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
 	netif_device_detach(priv->netdev);
 	rtnl_unlock();
 
+	mlx5e_rep_bridge_cleanup(priv);
 	mlx5e_rep_neigh_cleanup(rpriv);
 	mlx5e_dcbnl_delete_app(priv);
 	mlx5_notifier_unregister(mdev, &priv->events_nb);
 	mlx5e_rep_tc_disable(priv);
-	mlx5_lag_remove(mdev);
+	mlx5_lag_remove_netdev(mdev, priv->netdev);
 }
 
 static MLX5E_DEFINE_STATS_GRP(sw_rep, 0);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 22585015c7a7..47a2dfb7792a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -231,9 +231,9 @@ void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv);
 
 void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv);
 
-bool mlx5e_eswitch_vf_rep(struct net_device *netdev);
-bool mlx5e_eswitch_uplink_rep(struct net_device *netdev);
-static inline bool mlx5e_eswitch_rep(struct net_device *netdev)
+bool mlx5e_eswitch_vf_rep(const struct net_device *netdev);
+bool mlx5e_eswitch_uplink_rep(const struct net_device *netdev);
+static inline bool mlx5e_eswitch_rep(const struct net_device *netdev)
 {
 	return mlx5e_eswitch_vf_rep(netdev) ||
 	       mlx5e_eswitch_uplink_rep(netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index f90894eea9e0..3c65fd0bcf31 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -579,6 +579,9 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
 	if (mlx5_wq_cyc_missing(wq) < wqe_bulk)
 		return false;
 
+	if (rq->page_pool)
+		page_pool_nid_changed(rq->page_pool, numa_mem_id());
+
 	do {
 		u16 head = mlx5_wq_cyc_get_head(wq);
 
@@ -734,6 +737,9 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 	if (likely(missing < UMR_WQE_BULK))
 		return false;
 
+	if (rq->page_pool)
+		page_pool_nid_changed(rq->page_pool, numa_mem_id());
+
 	head = rq->mpwqe.actual_wq_head;
 	i = missing;
 	do {
@@ -1310,7 +1316,8 @@ static void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	if (rep->vlan && skb_vlan_tag_present(skb))
 		skb_vlan_pop(skb);
 
-	if (!mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv)) {
+	if (unlikely(!mlx5_ipsec_is_rx_flow(cqe) &&
+		     !mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv))) {
 		dev_kfree_skb_any(skb);
 		goto free_wqe;
 	}
@@ -1367,7 +1374,8 @@ static void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq, struct mlx5_cqe64
 
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
 
-	if (!mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv)) {
+	if (unlikely(!mlx5_ipsec_is_rx_flow(cqe) &&
+		     !mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv))) {
 		dev_kfree_skb_any(skb);
 		goto mpwrq_cqe_out;
 	}
@@ -1553,12 +1561,9 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
 		return 0;
 
-	if (rq->page_pool)
-		page_pool_nid_changed(rq->page_pool, numa_mem_id());
-
 	if (rq->cqd.left) {
 		work_done += mlx5e_decompress_cqes_cont(rq, cqwq, 0, budget);
-		if (rq->cqd.left || work_done >= budget)
+		if (work_done >= budget)
 			goto out;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index d4b0f270b6bb..8d84d0712c20 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -83,17 +83,17 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = {
 	[CHAIN_TO_REG] = {
 		.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_0,
 		.moffset = 0,
-		.mlen = 2,
+		.mlen = 16,
 	},
 	[VPORT_TO_REG] = {
 		.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_0,
-		.moffset = 2,
-		.mlen = 2,
+		.moffset = 16,
+		.mlen = 16,
 	},
 	[TUNNEL_TO_REG] = {
 		.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_1,
-		.moffset = 1,
-		.mlen = ((ESW_TUN_OPTS_BITS + ESW_TUN_ID_BITS) / 8),
+		.moffset = 8,
+		.mlen = ESW_TUN_OPTS_BITS + ESW_TUN_ID_BITS,
 		.soffset = MLX5_BYTE_OFF(fte_match_param,
 					 misc_parameters_2.metadata_reg_c_1),
 	},
@@ -110,7 +110,7 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = {
 	[NIC_CHAIN_TO_REG] = {
 		.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_B,
 		.moffset = 0,
-		.mlen = 2,
+		.mlen = 16,
 	},
 	[NIC_ZONE_RESTORE_TO_REG] = nic_zone_restore_to_reg_ct,
 };
@@ -128,23 +128,46 @@ static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow);
 void
 mlx5e_tc_match_to_reg_match(struct mlx5_flow_spec *spec,
 			    enum mlx5e_tc_attr_to_reg type,
-			    u32 data,
+			    u32 val,
 			    u32 mask)
 {
+	void *headers_c = spec->match_criteria, *headers_v = spec->match_value, *fmask, *fval;
 	int soffset = mlx5e_tc_attr_to_reg_mappings[type].soffset;
+	int moffset = mlx5e_tc_attr_to_reg_mappings[type].moffset;
 	int match_len = mlx5e_tc_attr_to_reg_mappings[type].mlen;
-	void *headers_c = spec->match_criteria;
-	void *headers_v = spec->match_value;
-	void *fmask, *fval;
+	u32 max_mask = GENMASK(match_len - 1, 0);
+	__be32 curr_mask_be, curr_val_be;
+	u32 curr_mask, curr_val;
 
 	fmask = headers_c + soffset;
 	fval = headers_v + soffset;
 
-	mask = (__force u32)(cpu_to_be32(mask)) >> (32 - (match_len * 8));
-	data = (__force u32)(cpu_to_be32(data)) >> (32 - (match_len * 8));
+	memcpy(&curr_mask_be, fmask, 4);
+	memcpy(&curr_val_be, fval, 4);
+
+	curr_mask = be32_to_cpu(curr_mask_be);
+	curr_val = be32_to_cpu(curr_val_be);
+
+	//move to correct offset
+	WARN_ON(mask > max_mask);
+	mask <<= moffset;
+	val <<= moffset;
+	max_mask <<= moffset;
+
+	//zero val and mask
+	curr_mask &= ~max_mask;
+	curr_val &= ~max_mask;
 
-	memcpy(fmask, &mask, match_len);
-	memcpy(fval, &data, match_len);
+	//add current to mask
+	curr_mask |= mask;
+	curr_val |= val;
+
+	//back to be32 and write
+	curr_mask_be = cpu_to_be32(curr_mask);
+	curr_val_be = cpu_to_be32(curr_val);
+
+	memcpy(fmask, &curr_mask_be, 4);
+	memcpy(fval, &curr_val_be, 4);
 
 	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
 }
@@ -152,23 +175,28 @@ mlx5e_tc_match_to_reg_match(struct mlx5_flow_spec *spec,
 void
 mlx5e_tc_match_to_reg_get_match(struct mlx5_flow_spec *spec,
 				enum mlx5e_tc_attr_to_reg type,
-				u32 *data,
+				u32 *val,
 				u32 *mask)
 {
+	void *headers_c = spec->match_criteria, *headers_v = spec->match_value, *fmask, *fval;
 	int soffset = mlx5e_tc_attr_to_reg_mappings[type].soffset;
+	int moffset = mlx5e_tc_attr_to_reg_mappings[type].moffset;
 	int match_len = mlx5e_tc_attr_to_reg_mappings[type].mlen;
-	void *headers_c = spec->match_criteria;
-	void *headers_v = spec->match_value;
-	void *fmask, *fval;
+	u32 max_mask = GENMASK(match_len - 1, 0);
+	__be32 curr_mask_be, curr_val_be;
+	u32 curr_mask, curr_val;
 
 	fmask = headers_c + soffset;
 	fval = headers_v + soffset;
 
-	memcpy(mask, fmask, match_len);
-	memcpy(data, fval, match_len);
+	memcpy(&curr_mask_be, fmask, 4);
+	memcpy(&curr_val_be, fval, 4);
+
+	curr_mask = be32_to_cpu(curr_mask_be);
+	curr_val = be32_to_cpu(curr_val_be);
 
-	*mask = be32_to_cpu((__force __be32)(*mask << (32 - (match_len * 8))));
-	*data = be32_to_cpu((__force __be32)(*data << (32 - (match_len * 8))));
+	*mask = (curr_mask >> moffset) & max_mask;
+	*val = (curr_val >> moffset) & max_mask;
 }
 
 int
@@ -192,13 +220,13 @@ mlx5e_tc_match_to_reg_set_and_get_id(struct mlx5_core_dev *mdev,
 		 (mod_hdr_acts->num_actions * MLX5_MH_ACT_SZ);
 
 	/* Firmware has 5bit length field and 0 means 32bits */
-	if (mlen == 4)
+	if (mlen == 32)
 		mlen = 0;
 
 	MLX5_SET(set_action_in, modact, action_type, MLX5_ACTION_TYPE_SET);
 	MLX5_SET(set_action_in, modact, field, mfield);
-	MLX5_SET(set_action_in, modact, offset, moffset * 8);
-	MLX5_SET(set_action_in, modact, length, mlen * 8);
+	MLX5_SET(set_action_in, modact, offset, moffset);
+	MLX5_SET(set_action_in, modact, length, mlen);
 	MLX5_SET(set_action_in, modact, data, data);
 	err = mod_hdr_acts->num_actions;
 	mod_hdr_acts->num_actions++;
@@ -296,13 +324,13 @@ void mlx5e_tc_match_to_reg_mod_hdr_change(struct mlx5_core_dev *mdev,
 	modact = mod_hdr_acts->actions + (act_id * MLX5_MH_ACT_SZ);
 
 	/* Firmware has 5bit length field and 0 means 32bits */
-	if (mlen == 4)
+	if (mlen == 32)
 		mlen = 0;
 
 	MLX5_SET(set_action_in, modact, action_type, MLX5_ACTION_TYPE_SET);
 	MLX5_SET(set_action_in, modact, field, mfield);
-	MLX5_SET(set_action_in, modact, offset, moffset * 8);
-	MLX5_SET(set_action_in, modact, length, mlen * 8);
+	MLX5_SET(set_action_in, modact, offset, moffset);
+	MLX5_SET(set_action_in, modact, length, mlen);
 	MLX5_SET(set_action_in, modact, data, data);
 }
 
@@ -5105,7 +5133,7 @@ bool mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe,
 
 		tc_skb_ext->chain = chain;
 
-		zone_restore_id = (reg_b >> REG_MAPPING_SHIFT(NIC_ZONE_RESTORE_TO_REG)) &
+		zone_restore_id = (reg_b >> REG_MAPPING_MOFFSET(NIC_ZONE_RESTORE_TO_REG)) &
 			ESW_ZONE_ID_MASK;
 
 		if (!mlx5e_tc_ct_restore_flow(tc->ct, skb,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 17027536efba..f7cbeb0b66d2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -129,7 +129,7 @@ struct tunnel_match_enc_opts {
  */
 #define TUNNEL_INFO_BITS 12
 #define TUNNEL_INFO_BITS_MASK GENMASK(TUNNEL_INFO_BITS - 1, 0)
-#define ENC_OPTS_BITS 12
+#define ENC_OPTS_BITS 11
 #define ENC_OPTS_BITS_MASK GENMASK(ENC_OPTS_BITS - 1, 0)
 #define TUNNEL_ID_BITS (TUNNEL_INFO_BITS + ENC_OPTS_BITS)
 #define TUNNEL_ID_MASK GENMASK(TUNNEL_ID_BITS - 1, 0)
@@ -201,10 +201,10 @@ enum mlx5e_tc_attr_to_reg {
 
 struct mlx5e_tc_attr_to_reg_mapping {
 	int mfield; /* rewrite field */
-	int moffset; /* offset of mfield */
-	int mlen; /* bytes to rewrite/match */
+	int moffset; /* bit offset of mfield */
+	int mlen; /* bits to rewrite/match */
 
-	int soffset; /* offset of spec for match */
+	int soffset; /* byte offset of spec for match */
 };
 
 extern struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 320fe0cda917..c63d78eda606 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -687,16 +687,12 @@ void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq)
 		mlx5e_tx_mpwqe_session_complete(sq);
 }
 
-static bool mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq,
+static void mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq,
 				   struct sk_buff *skb, struct mlx5e_accel_tx_state *accel,
 				   struct mlx5_wqe_eth_seg *eseg, u16 ihs)
 {
-	if (unlikely(!mlx5e_accel_tx_eseg(priv, skb, eseg, ihs)))
-		return false;
-
+	mlx5e_accel_tx_eseg(priv, skb, eseg, ihs);
 	mlx5e_txwqe_build_eseg_csum(sq, skb, accel, eseg);
-
-	return true;
 }
 
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -725,10 +721,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (mlx5e_tx_skb_supports_mpwqe(skb, &attr)) {
 			struct mlx5_wqe_eth_seg eseg = {};
 
-			if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &eseg,
-							     attr.ihs)))
-				return NETDEV_TX_OK;
-
+			mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &eseg, attr.ihs);
 			mlx5e_sq_xmit_mpwqe(sq, skb, &eseg, netdev_xmit_more());
 			return NETDEV_TX_OK;
 		}
@@ -743,9 +736,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* May update the WQE, but may not post other WQEs. */
 	mlx5e_accel_tx_finish(sq, wqe, &accel,
 			      (struct mlx5_wqe_inline_seg *)(wqe->data + wqe_attr.ds_cnt_inl));
-	if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &wqe->eth, attr.ihs)))
-		return NETDEV_TX_OK;
-
+	mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &wqe->eth, attr.ihs);
 	mlx5e_sq_xmit_wqe(sq, skb, &attr, &wqe_attr, wqe, pi, netdev_xmit_more());
 
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 940333410267..c7efd177da1f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -1,33 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /*
- * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
+ * Copyright (c) 2013-2021, Mellanox Technologies inc.  All rights reserved.
  */
 
 #include <linux/interrupt.h>
@@ -45,6 +18,7 @@
 #include "eswitch.h"
 #include "lib/clock.h"
 #include "diag/fw_tracer.h"
+#include "mlx5_irq.h"
 
 enum {
 	MLX5_EQE_OWNER_INIT_VAL	= 0x1,
@@ -84,6 +58,9 @@ struct mlx5_eq_table {
 	struct mutex            lock; /* sync async eqs creations */
 	int			num_comp_eqs;
 	struct mlx5_irq_table	*irq_table;
+#ifdef CONFIG_RFS_ACCEL
+	struct cpu_rmap		*rmap;
+#endif
 };
 
 #define MLX5_ASYNC_EVENT_MASK ((1ull << MLX5_EVENT_TYPE_PATH_MIG)	    | \
@@ -288,7 +265,7 @@ create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 	u32 out[MLX5_ST_SZ_DW(create_eq_out)] = {0};
 	u8 log_eq_stride = ilog2(MLX5_EQE_SIZE);
 	struct mlx5_priv *priv = &dev->priv;
-	u8 vecidx = param->irq_index;
+	u16 vecidx = param->irq_index;
 	__be64 *pas;
 	void *eqc;
 	int inlen;
@@ -311,13 +288,20 @@ create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 	mlx5_init_fbc(eq->frag_buf.frags, log_eq_stride, log_eq_size, &eq->fbc);
 	init_eq_buf(eq);
 
+	eq->irq = mlx5_irq_request(dev, vecidx, param->affinity);
+	if (IS_ERR(eq->irq)) {
+		err = PTR_ERR(eq->irq);
+		goto err_buf;
+	}
+
+	vecidx = mlx5_irq_get_index(eq->irq);
 	inlen = MLX5_ST_SZ_BYTES(create_eq_in) +
 		MLX5_FLD_SZ_BYTES(create_eq_in, pas[0]) * eq->frag_buf.npages;
 
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in) {
 		err = -ENOMEM;
-		goto err_buf;
+		goto err_irq;
 	}
 
 	pas = (__be64 *)MLX5_ADDR_OF(create_eq_in, in, pas);
@@ -361,6 +345,8 @@ err_eq:
 err_in:
 	kvfree(in);
 
+err_irq:
+	mlx5_irq_release(eq->irq);
 err_buf:
 	mlx5_frag_buf_free(dev, &eq->frag_buf);
 	return err;
@@ -379,10 +365,9 @@ err_buf:
 int mlx5_eq_enable(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 		   struct notifier_block *nb)
 {
-	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
 	int err;
 
-	err = mlx5_irq_attach_nb(eq_table->irq_table, eq->vecidx, nb);
+	err = mlx5_irq_attach_nb(eq->irq, nb);
 	if (!err)
 		eq_update_ci(eq, 1);
 
@@ -401,9 +386,7 @@ EXPORT_SYMBOL(mlx5_eq_enable);
 void mlx5_eq_disable(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 		     struct notifier_block *nb)
 {
-	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
-
-	mlx5_irq_detach_nb(eq_table->irq_table, eq->vecidx, nb);
+	mlx5_irq_detach_nb(eq->irq, nb);
 }
 EXPORT_SYMBOL(mlx5_eq_disable);
 
@@ -417,10 +400,9 @@ static int destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 	if (err)
 		mlx5_core_warn(dev, "failed to destroy a previously created eq: eqn %d\n",
 			       eq->eqn);
-	synchronize_irq(eq->irqn);
+	mlx5_irq_release(eq->irq);
 
 	mlx5_frag_buf_free(dev, &eq->frag_buf);
-
 	return err;
 }
 
@@ -492,14 +474,7 @@ static int create_async_eq(struct mlx5_core_dev *dev,
 	int err;
 
 	mutex_lock(&eq_table->lock);
-	/* Async EQs must share irq index 0 */
-	if (param->irq_index != 0) {
-		err = -EINVAL;
-		goto unlock;
-	}
-
 	err = create_map_eq(dev, eq, param);
-unlock:
 	mutex_unlock(&eq_table->lock);
 	return err;
 }
@@ -618,8 +593,11 @@ setup_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq_async *eq,
 
 	eq->irq_nb.notifier_call = mlx5_eq_async_int;
 	spin_lock_init(&eq->lock);
+	if (!zalloc_cpumask_var(&param->affinity, GFP_KERNEL))
+		return -ENOMEM;
 
 	err = create_async_eq(dev, &eq->core, param);
+	free_cpumask_var(param->affinity);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create %s EQ %d\n", name, err);
 		return err;
@@ -654,7 +632,6 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 	mlx5_eq_notifier_register(dev, &table->cq_err_nb);
 
 	param = (struct mlx5_eq_param) {
-		.irq_index = 0,
 		.nent = MLX5_NUM_CMD_EQE,
 		.mask[0] = 1ull << MLX5_EVENT_TYPE_CMD,
 	};
@@ -667,7 +644,6 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 	mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL);
 
 	param = (struct mlx5_eq_param) {
-		.irq_index = 0,
 		.nent = MLX5_NUM_ASYNC_EQE,
 	};
 
@@ -677,7 +653,6 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 		goto err2;
 
 	param = (struct mlx5_eq_param) {
-		.irq_index = 0,
 		.nent = /* TODO: sriov max_vf + */ 1,
 		.mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_REQUEST,
 	};
@@ -737,6 +712,9 @@ mlx5_eq_create_generic(struct mlx5_core_dev *dev,
 	struct mlx5_eq *eq = kvzalloc(sizeof(*eq), GFP_KERNEL);
 	int err;
 
+	if (!param->affinity)
+		return ERR_PTR(-EINVAL);
+
 	if (!eq)
 		return ERR_PTR(-ENOMEM);
 
@@ -847,16 +825,21 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 			.irq_index = vecidx,
 			.nent = nent,
 		};
-		err = create_map_eq(dev, &eq->core, &param);
-		if (err) {
-			kfree(eq);
-			goto clean;
+
+		if (!zalloc_cpumask_var(&param.affinity, GFP_KERNEL)) {
+			err = -ENOMEM;
+			goto clean_eq;
 		}
+		cpumask_set_cpu(cpumask_local_spread(i, dev->priv.numa_node),
+				param.affinity);
+		err = create_map_eq(dev, &eq->core, &param);
+		free_cpumask_var(param.affinity);
+		if (err)
+			goto clean_eq;
 		err = mlx5_eq_enable(dev, &eq->core, &eq->irq_nb);
 		if (err) {
 			destroy_unmap_eq(dev, &eq->core);
-			kfree(eq);
-			goto clean;
+			goto clean_eq;
 		}
 
 		mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->core.eqn);
@@ -865,7 +848,8 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 	}
 
 	return 0;
-
+clean_eq:
+	kfree(eq);
 clean:
 	destroy_comp_eqs(dev);
 	return err;
@@ -901,17 +885,23 @@ EXPORT_SYMBOL(mlx5_comp_vectors_count);
 struct cpumask *
 mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector)
 {
-	int vecidx = vector + MLX5_IRQ_VEC_COMP_BASE;
+	struct mlx5_eq_table *table = dev->priv.eq_table;
+	struct mlx5_eq_comp *eq, *n;
+	int i = 0;
 
-	return mlx5_irq_get_affinity_mask(dev->priv.eq_table->irq_table,
-					  vecidx);
+	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
+		if (i++ == vector)
+			break;
+	}
+
+	return mlx5_irq_get_affinity_mask(eq->core.irq);
 }
 EXPORT_SYMBOL(mlx5_comp_irq_get_affinity_mask);
 
 #ifdef CONFIG_RFS_ACCEL
 struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev)
 {
-	return mlx5_irq_get_rmap(dev->priv.eq_table->irq_table);
+	return dev->priv.eq_table->rmap;
 }
 #endif
 
@@ -928,12 +918,57 @@ struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn)
 	return ERR_PTR(-ENOENT);
 }
 
+static void clear_rmap(struct mlx5_core_dev *dev)
+{
+#ifdef CONFIG_RFS_ACCEL
+	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
+
+	free_irq_cpu_rmap(eq_table->rmap);
+#endif
+}
+
+static int set_rmap(struct mlx5_core_dev *mdev)
+{
+	int err = 0;
+#ifdef CONFIG_RFS_ACCEL
+	struct mlx5_eq_table *eq_table = mdev->priv.eq_table;
+	int vecidx;
+
+	eq_table->rmap = alloc_irq_cpu_rmap(eq_table->num_comp_eqs);
+	if (!eq_table->rmap) {
+		err = -ENOMEM;
+		mlx5_core_err(mdev, "Failed to allocate cpu_rmap. err %d", err);
+		goto err_out;
+	}
+
+	vecidx = MLX5_IRQ_VEC_COMP_BASE;
+	for (; vecidx < eq_table->num_comp_eqs + MLX5_IRQ_VEC_COMP_BASE;
+	     vecidx++) {
+		err = irq_cpu_rmap_add(eq_table->rmap,
+				       pci_irq_vector(mdev->pdev, vecidx));
+		if (err) {
+			mlx5_core_err(mdev, "irq_cpu_rmap_add failed. err %d",
+				      err);
+			goto err_irq_cpu_rmap_add;
+		}
+	}
+	return 0;
+
+err_irq_cpu_rmap_add:
+	clear_rmap(mdev);
+err_out:
+#endif
+	return err;
+}
+
 /* This function should only be called after mlx5_cmd_force_teardown_hca */
 void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 
 	mutex_lock(&table->lock); /* sync with create/destroy_async_eq */
+	if (!mlx5_core_is_sf(dev))
+		clear_rmap(dev);
 	mlx5_irq_table_destroy(dev);
 	mutex_unlock(&table->lock);
 }
@@ -950,12 +985,19 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev)
 	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
 		      MLX5_CAP_GEN(dev, max_num_eqs) :
 		      1 << MLX5_CAP_GEN(dev, log_max_eq);
+	int max_eqs_sf;
 	int err;
 
 	eq_table->num_comp_eqs =
 		min_t(int,
-		      mlx5_irq_get_num_comp(eq_table->irq_table),
+		      mlx5_irq_table_get_num_comp(eq_table->irq_table),
 		      num_eqs - MLX5_MAX_ASYNC_EQS);
+	if (mlx5_core_is_sf(dev)) {
+		max_eqs_sf = min_t(int, MLX5_COMP_EQS_PER_SF,
+				   mlx5_irq_table_get_sfs_vec(eq_table->irq_table));
+		eq_table->num_comp_eqs = min_t(int, eq_table->num_comp_eqs,
+					       max_eqs_sf);
+	}
 
 	err = create_async_eqs(dev);
 	if (err) {
@@ -963,6 +1005,18 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev)
 		goto err_async_eqs;
 	}
 
+	if (!mlx5_core_is_sf(dev)) {
+		/* rmap is a mapping between irq number and queue number.
+		 * each irq can be assign only to a single rmap.
+		 * since SFs share IRQs, rmap mapping cannot function correctly
+		 * for irqs that are shared for different core/netdev RX rings.
+		 * Hence we don't allow netdev rmap for SFs
+		 */
+		err = set_rmap(dev);
+		if (err)
+			goto err_rmap;
+	}
+
 	err = create_comp_eqs(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to create completion EQs\n");
@@ -971,6 +1025,9 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev)
 
 	return 0;
 err_comp_eqs:
+	if (!mlx5_core_is_sf(dev))
+		clear_rmap(dev);
+err_rmap:
 	destroy_async_eqs(dev);
 err_async_eqs:
 	return err;
@@ -978,6 +1035,8 @@ err_async_eqs:
 
 void mlx5_eq_table_destroy(struct mlx5_core_dev *dev)
 {
+	if (!mlx5_core_is_sf(dev))
+		clear_rmap(dev);
 	destroy_comp_eqs(dev);
 	destroy_async_eqs(dev);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
new file mode 100644
index 000000000000..a6e1d4f78268
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
@@ -0,0 +1,1299 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2021 Mellanox Technologies. */
+
+#include <linux/list.h>
+#include <linux/notifier.h>
+#include <net/netevent.h>
+#include <net/switchdev.h>
+#include "bridge.h"
+#include "eswitch.h"
+#include "bridge_priv.h"
+#define CREATE_TRACE_POINTS
+#include "diag/bridge_tracepoint.h"
+
+#define MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE 64000
+#define MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_IDX_FROM 0
+#define MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_IDX_TO (MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE / 4 - 1)
+#define MLX5_ESW_BRIDGE_INGRESS_TABLE_FILTER_GRP_IDX_FROM \
+	(MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_IDX_TO + 1)
+#define MLX5_ESW_BRIDGE_INGRESS_TABLE_FILTER_GRP_IDX_TO \
+	(MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE / 2 - 1)
+#define MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_FROM \
+	(MLX5_ESW_BRIDGE_INGRESS_TABLE_FILTER_GRP_IDX_TO + 1)
+#define MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_TO (MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE - 1)
+
+#define MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE 64000
+#define MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_FROM 0
+#define MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_TO (MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE / 2 - 1)
+#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_FROM \
+	(MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_TO + 1)
+#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_TO (MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE - 1)
+
+#define MLX5_ESW_BRIDGE_SKIP_TABLE_SIZE 0
+
+enum {
+	MLX5_ESW_BRIDGE_LEVEL_INGRESS_TABLE,
+	MLX5_ESW_BRIDGE_LEVEL_EGRESS_TABLE,
+	MLX5_ESW_BRIDGE_LEVEL_SKIP_TABLE,
+};
+
+static const struct rhashtable_params fdb_ht_params = {
+	.key_offset = offsetof(struct mlx5_esw_bridge_fdb_entry, key),
+	.key_len = sizeof(struct mlx5_esw_bridge_fdb_key),
+	.head_offset = offsetof(struct mlx5_esw_bridge_fdb_entry, ht_node),
+	.automatic_shrinking = true,
+};
+
+enum {
+	MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG = BIT(0),
+};
+
+struct mlx5_esw_bridge {
+	int ifindex;
+	int refcnt;
+	struct list_head list;
+	struct mlx5_esw_bridge_offloads *br_offloads;
+
+	struct list_head fdb_list;
+	struct rhashtable fdb_ht;
+	struct xarray vports;
+
+	struct mlx5_flow_table *egress_ft;
+	struct mlx5_flow_group *egress_vlan_fg;
+	struct mlx5_flow_group *egress_mac_fg;
+	unsigned long ageing_time;
+	u32 flags;
+};
+
+static void
+mlx5_esw_bridge_fdb_offload_notify(struct net_device *dev, const unsigned char *addr, u16 vid,
+				   unsigned long val)
+{
+	struct switchdev_notifier_fdb_info send_info;
+
+	send_info.addr = addr;
+	send_info.vid = vid;
+	send_info.offloaded = true;
+	call_switchdev_notifiers(val, dev, &send_info.info, NULL);
+}
+
+static struct mlx5_flow_table *
+mlx5_esw_bridge_table_create(int max_fte, u32 level, struct mlx5_eswitch *esw)
+{
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_core_dev *dev = esw->dev;
+	struct mlx5_flow_namespace *ns;
+	struct mlx5_flow_table *fdb;
+
+	ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
+	if (!ns) {
+		esw_warn(dev, "Failed to get FDB namespace\n");
+		return ERR_PTR(-ENOENT);
+	}
+
+	ft_attr.flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
+	ft_attr.max_fte = max_fte;
+	ft_attr.level = level;
+	ft_attr.prio = FDB_BR_OFFLOAD;
+	fdb = mlx5_create_flow_table(ns, &ft_attr);
+	if (IS_ERR(fdb))
+		esw_warn(dev, "Failed to create bridge FDB Table (err=%ld)\n", PTR_ERR(fdb));
+
+	return fdb;
+}
+
+static struct mlx5_flow_group *
+mlx5_esw_bridge_ingress_vlan_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *ingress_ft)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_group *fg;
+	u32 *in, *match;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return ERR_PTR(-ENOMEM);
+
+	MLX5_SET(create_flow_group_in, in, match_criteria_enable,
+		 MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2);
+	match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
+
+	MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_47_16);
+	MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_15_0);
+	MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.cvlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.first_vid);
+
+	MLX5_SET(fte_match_param, match, misc_parameters_2.metadata_reg_c_0,
+		 mlx5_eswitch_get_vport_metadata_mask());
+
+	MLX5_SET(create_flow_group_in, in, start_flow_index,
+		 MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_IDX_FROM);
+	MLX5_SET(create_flow_group_in, in, end_flow_index,
+		 MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_IDX_TO);
+
+	fg = mlx5_create_flow_group(ingress_ft, in);
+	kvfree(in);
+	if (IS_ERR(fg))
+		esw_warn(esw->dev,
+			 "Failed to create VLAN flow group for bridge ingress table (err=%ld)\n",
+			 PTR_ERR(fg));
+
+	return fg;
+}
+
+static struct mlx5_flow_group *
+mlx5_esw_bridge_ingress_filter_fg_create(struct mlx5_eswitch *esw,
+					 struct mlx5_flow_table *ingress_ft)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_group *fg;
+	u32 *in, *match;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return ERR_PTR(-ENOMEM);
+
+	MLX5_SET(create_flow_group_in, in, match_criteria_enable,
+		 MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2);
+	match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
+
+	MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_47_16);
+	MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_15_0);
+	MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.cvlan_tag);
+
+	MLX5_SET(fte_match_param, match, misc_parameters_2.metadata_reg_c_0,
+		 mlx5_eswitch_get_vport_metadata_mask());
+
+	MLX5_SET(create_flow_group_in, in, start_flow_index,
+		 MLX5_ESW_BRIDGE_INGRESS_TABLE_FILTER_GRP_IDX_FROM);
+	MLX5_SET(create_flow_group_in, in, end_flow_index,
+		 MLX5_ESW_BRIDGE_INGRESS_TABLE_FILTER_GRP_IDX_TO);
+
+	fg = mlx5_create_flow_group(ingress_ft, in);
+	if (IS_ERR(fg))
+		esw_warn(esw->dev,
+			 "Failed to create bridge ingress table VLAN filter flow group (err=%ld)\n",
+			 PTR_ERR(fg));
+
+	kvfree(in);
+	return fg;
+}
+
+static struct mlx5_flow_group *
+mlx5_esw_bridge_ingress_mac_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *ingress_ft)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_group *fg;
+	u32 *in, *match;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return ERR_PTR(-ENOMEM);
+
+	MLX5_SET(create_flow_group_in, in, match_criteria_enable,
+		 MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2);
+	match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
+
+	MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_47_16);
+	MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_15_0);
+
+	MLX5_SET(fte_match_param, match, misc_parameters_2.metadata_reg_c_0,
+		 mlx5_eswitch_get_vport_metadata_mask());
+
+	MLX5_SET(create_flow_group_in, in, start_flow_index,
+		 MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_FROM);
+	MLX5_SET(create_flow_group_in, in, end_flow_index,
+		 MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_TO);
+
+	fg = mlx5_create_flow_group(ingress_ft, in);
+	if (IS_ERR(fg))
+		esw_warn(esw->dev,
+			 "Failed to create MAC flow group for bridge ingress table (err=%ld)\n",
+			 PTR_ERR(fg));
+
+	kvfree(in);
+	return fg;
+}
+
+static struct mlx5_flow_group *
+mlx5_esw_bridge_egress_vlan_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *egress_ft)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_group *fg;
+	u32 *in, *match;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return ERR_PTR(-ENOMEM);
+
+	MLX5_SET(create_flow_group_in, in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
+	match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
+
+	MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.dmac_47_16);
+	MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.dmac_15_0);
+	MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.cvlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.first_vid);
+
+	MLX5_SET(create_flow_group_in, in, start_flow_index,
+		 MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_FROM);
+	MLX5_SET(create_flow_group_in, in, end_flow_index,
+		 MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_TO);
+
+	fg = mlx5_create_flow_group(egress_ft, in);
+	if (IS_ERR(fg))
+		esw_warn(esw->dev,
+			 "Failed to create VLAN flow group for bridge egress table (err=%ld)\n",
+			 PTR_ERR(fg));
+	kvfree(in);
+	return fg;
+}
+
+static struct mlx5_flow_group *
+mlx5_esw_bridge_egress_mac_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *egress_ft)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_group *fg;
+	u32 *in, *match;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return ERR_PTR(-ENOMEM);
+
+	MLX5_SET(create_flow_group_in, in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
+	match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
+
+	MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.dmac_47_16);
+	MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.dmac_15_0);
+
+	MLX5_SET(create_flow_group_in, in, start_flow_index,
+		 MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_FROM);
+	MLX5_SET(create_flow_group_in, in, end_flow_index,
+		 MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_TO);
+
+	fg = mlx5_create_flow_group(egress_ft, in);
+	if (IS_ERR(fg))
+		esw_warn(esw->dev,
+			 "Failed to create bridge egress table MAC flow group (err=%ld)\n",
+			 PTR_ERR(fg));
+	kvfree(in);
+	return fg;
+}
+
+static int
+mlx5_esw_bridge_ingress_table_init(struct mlx5_esw_bridge_offloads *br_offloads)
+{
+	struct mlx5_flow_group *mac_fg, *filter_fg, *vlan_fg;
+	struct mlx5_flow_table *ingress_ft, *skip_ft;
+	int err;
+
+	if (!mlx5_eswitch_vport_match_metadata_enabled(br_offloads->esw))
+		return -EOPNOTSUPP;
+
+	ingress_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE,
+						  MLX5_ESW_BRIDGE_LEVEL_INGRESS_TABLE,
+						  br_offloads->esw);
+	if (IS_ERR(ingress_ft))
+		return PTR_ERR(ingress_ft);
+
+	skip_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_SKIP_TABLE_SIZE,
+					       MLX5_ESW_BRIDGE_LEVEL_SKIP_TABLE,
+					       br_offloads->esw);
+	if (IS_ERR(skip_ft)) {
+		err = PTR_ERR(skip_ft);
+		goto err_skip_tbl;
+	}
+
+	vlan_fg = mlx5_esw_bridge_ingress_vlan_fg_create(br_offloads->esw, ingress_ft);
+	if (IS_ERR(vlan_fg)) {
+		err = PTR_ERR(vlan_fg);
+		goto err_vlan_fg;
+	}
+
+	filter_fg = mlx5_esw_bridge_ingress_filter_fg_create(br_offloads->esw, ingress_ft);
+	if (IS_ERR(filter_fg)) {
+		err = PTR_ERR(filter_fg);
+		goto err_filter_fg;
+	}
+
+	mac_fg = mlx5_esw_bridge_ingress_mac_fg_create(br_offloads->esw, ingress_ft);
+	if (IS_ERR(mac_fg)) {
+		err = PTR_ERR(mac_fg);
+		goto err_mac_fg;
+	}
+
+	br_offloads->ingress_ft = ingress_ft;
+	br_offloads->skip_ft = skip_ft;
+	br_offloads->ingress_vlan_fg = vlan_fg;
+	br_offloads->ingress_filter_fg = filter_fg;
+	br_offloads->ingress_mac_fg = mac_fg;
+	return 0;
+
+err_mac_fg:
+	mlx5_destroy_flow_group(filter_fg);
+err_filter_fg:
+	mlx5_destroy_flow_group(vlan_fg);
+err_vlan_fg:
+	mlx5_destroy_flow_table(skip_ft);
+err_skip_tbl:
+	mlx5_destroy_flow_table(ingress_ft);
+	return err;
+}
+
+static void
+mlx5_esw_bridge_ingress_table_cleanup(struct mlx5_esw_bridge_offloads *br_offloads)
+{
+	mlx5_destroy_flow_group(br_offloads->ingress_mac_fg);
+	br_offloads->ingress_mac_fg = NULL;
+	mlx5_destroy_flow_group(br_offloads->ingress_filter_fg);
+	br_offloads->ingress_filter_fg = NULL;
+	mlx5_destroy_flow_group(br_offloads->ingress_vlan_fg);
+	br_offloads->ingress_vlan_fg = NULL;
+	mlx5_destroy_flow_table(br_offloads->skip_ft);
+	br_offloads->skip_ft = NULL;
+	mlx5_destroy_flow_table(br_offloads->ingress_ft);
+	br_offloads->ingress_ft = NULL;
+}
+
+static int
+mlx5_esw_bridge_egress_table_init(struct mlx5_esw_bridge_offloads *br_offloads,
+				  struct mlx5_esw_bridge *bridge)
+{
+	struct mlx5_flow_group *mac_fg, *vlan_fg;
+	struct mlx5_flow_table *egress_ft;
+	int err;
+
+	egress_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE,
+						 MLX5_ESW_BRIDGE_LEVEL_EGRESS_TABLE,
+						 br_offloads->esw);
+	if (IS_ERR(egress_ft))
+		return PTR_ERR(egress_ft);
+
+	vlan_fg = mlx5_esw_bridge_egress_vlan_fg_create(br_offloads->esw, egress_ft);
+	if (IS_ERR(vlan_fg)) {
+		err = PTR_ERR(vlan_fg);
+		goto err_vlan_fg;
+	}
+
+	mac_fg = mlx5_esw_bridge_egress_mac_fg_create(br_offloads->esw, egress_ft);
+	if (IS_ERR(mac_fg)) {
+		err = PTR_ERR(mac_fg);
+		goto err_mac_fg;
+	}
+
+	bridge->egress_ft = egress_ft;
+	bridge->egress_vlan_fg = vlan_fg;
+	bridge->egress_mac_fg = mac_fg;
+	return 0;
+
+err_mac_fg:
+	mlx5_destroy_flow_group(vlan_fg);
+err_vlan_fg:
+	mlx5_destroy_flow_table(egress_ft);
+	return err;
+}
+
+static void
+mlx5_esw_bridge_egress_table_cleanup(struct mlx5_esw_bridge *bridge)
+{
+	mlx5_destroy_flow_group(bridge->egress_mac_fg);
+	mlx5_destroy_flow_group(bridge->egress_vlan_fg);
+	mlx5_destroy_flow_table(bridge->egress_ft);
+}
+
+static struct mlx5_flow_handle *
+mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr,
+				    struct mlx5_esw_bridge_vlan *vlan, u32 counter_id,
+				    struct mlx5_esw_bridge *bridge)
+{
+	struct mlx5_esw_bridge_offloads *br_offloads = bridge->br_offloads;
+	struct mlx5_flow_act flow_act = {
+		.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT,
+		.flags = FLOW_ACT_NO_APPEND,
+	};
+	struct mlx5_flow_destination dests[2] = {};
+	struct mlx5_flow_spec *rule_spec;
+	struct mlx5_flow_handle *handle;
+	u8 *smac_v, *smac_c;
+
+	rule_spec = kvzalloc(sizeof(*rule_spec), GFP_KERNEL);
+	if (!rule_spec)
+		return ERR_PTR(-ENOMEM);
+
+	rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2;
+
+	smac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value,
+			      outer_headers.smac_47_16);
+	ether_addr_copy(smac_v, addr);
+	smac_c = MLX5_ADDR_OF(fte_match_param, rule_spec->match_criteria,
+			      outer_headers.smac_47_16);
+	eth_broadcast_addr(smac_c);
+
+	MLX5_SET(fte_match_param, rule_spec->match_criteria,
+		 misc_parameters_2.metadata_reg_c_0, mlx5_eswitch_get_vport_metadata_mask());
+	MLX5_SET(fte_match_param, rule_spec->match_value, misc_parameters_2.metadata_reg_c_0,
+		 mlx5_eswitch_get_vport_metadata_for_match(br_offloads->esw, vport_num));
+
+	if (vlan && vlan->pkt_reformat_push) {
+		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+		flow_act.pkt_reformat = vlan->pkt_reformat_push;
+	} else if (vlan) {
+		MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria,
+				 outer_headers.cvlan_tag);
+		MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_value,
+				 outer_headers.cvlan_tag);
+		MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria,
+				 outer_headers.first_vid);
+		MLX5_SET(fte_match_param, rule_spec->match_value, outer_headers.first_vid,
+			 vlan->vid);
+	}
+
+	dests[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dests[0].ft = bridge->egress_ft;
+	dests[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dests[1].counter_id = counter_id;
+
+	handle = mlx5_add_flow_rules(br_offloads->ingress_ft, rule_spec, &flow_act, dests,
+				     ARRAY_SIZE(dests));
+
+	kvfree(rule_spec);
+	return handle;
+}
+
+static struct mlx5_flow_handle *
+mlx5_esw_bridge_ingress_filter_flow_create(u16 vport_num, const unsigned char *addr,
+					   struct mlx5_esw_bridge *bridge)
+{
+	struct mlx5_esw_bridge_offloads *br_offloads = bridge->br_offloads;
+	struct mlx5_flow_destination dest = {
+		.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE,
+		.ft = br_offloads->skip_ft,
+	};
+	struct mlx5_flow_act flow_act = {
+		.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+		.flags = FLOW_ACT_NO_APPEND,
+	};
+	struct mlx5_flow_spec *rule_spec;
+	struct mlx5_flow_handle *handle;
+	u8 *smac_v, *smac_c;
+
+	rule_spec = kvzalloc(sizeof(*rule_spec), GFP_KERNEL);
+	if (!rule_spec)
+		return ERR_PTR(-ENOMEM);
+
+	rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2;
+
+	smac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value,
+			      outer_headers.smac_47_16);
+	ether_addr_copy(smac_v, addr);
+	smac_c = MLX5_ADDR_OF(fte_match_param, rule_spec->match_criteria,
+			      outer_headers.smac_47_16);
+	eth_broadcast_addr(smac_c);
+
+	MLX5_SET(fte_match_param, rule_spec->match_criteria,
+		 misc_parameters_2.metadata_reg_c_0, mlx5_eswitch_get_vport_metadata_mask());
+	MLX5_SET(fte_match_param, rule_spec->match_value, misc_parameters_2.metadata_reg_c_0,
+		 mlx5_eswitch_get_vport_metadata_for_match(br_offloads->esw, vport_num));
+
+	MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria,
+			 outer_headers.cvlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_value,
+			 outer_headers.cvlan_tag);
+
+	handle = mlx5_add_flow_rules(br_offloads->ingress_ft, rule_spec, &flow_act, &dest, 1);
+
+	kvfree(rule_spec);
+	return handle;
+}
+
+static struct mlx5_flow_handle *
+mlx5_esw_bridge_egress_flow_create(u16 vport_num, const unsigned char *addr,
+				   struct mlx5_esw_bridge_vlan *vlan,
+				   struct mlx5_esw_bridge *bridge)
+{
+	struct mlx5_flow_destination dest = {
+		.type = MLX5_FLOW_DESTINATION_TYPE_VPORT,
+		.vport.num = vport_num,
+	};
+	struct mlx5_flow_act flow_act = {
+		.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+		.flags = FLOW_ACT_NO_APPEND,
+	};
+	struct mlx5_flow_spec *rule_spec;
+	struct mlx5_flow_handle *handle;
+	u8 *dmac_v, *dmac_c;
+
+	rule_spec = kvzalloc(sizeof(*rule_spec), GFP_KERNEL);
+	if (!rule_spec)
+		return ERR_PTR(-ENOMEM);
+
+	rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+
+	dmac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value,
+			      outer_headers.dmac_47_16);
+	ether_addr_copy(dmac_v, addr);
+	dmac_c = MLX5_ADDR_OF(fte_match_param, rule_spec->match_criteria,
+			      outer_headers.dmac_47_16);
+	eth_broadcast_addr(dmac_c);
+
+	if (vlan) {
+		if (vlan->pkt_reformat_pop) {
+			flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+			flow_act.pkt_reformat = vlan->pkt_reformat_pop;
+		}
+
+		MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria,
+				 outer_headers.cvlan_tag);
+		MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_value,
+				 outer_headers.cvlan_tag);
+		MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria,
+				 outer_headers.first_vid);
+		MLX5_SET(fte_match_param, rule_spec->match_value, outer_headers.first_vid,
+			 vlan->vid);
+	}
+
+	handle = mlx5_add_flow_rules(bridge->egress_ft, rule_spec, &flow_act, &dest, 1);
+
+	kvfree(rule_spec);
+	return handle;
+}
+
+static struct mlx5_esw_bridge *mlx5_esw_bridge_create(int ifindex,
+						      struct mlx5_esw_bridge_offloads *br_offloads)
+{
+	struct mlx5_esw_bridge *bridge;
+	int err;
+
+	bridge = kvzalloc(sizeof(*bridge), GFP_KERNEL);
+	if (!bridge)
+		return ERR_PTR(-ENOMEM);
+
+	bridge->br_offloads = br_offloads;
+	err = mlx5_esw_bridge_egress_table_init(br_offloads, bridge);
+	if (err)
+		goto err_egress_tbl;
+
+	err = rhashtable_init(&bridge->fdb_ht, &fdb_ht_params);
+	if (err)
+		goto err_fdb_ht;
+
+	INIT_LIST_HEAD(&bridge->fdb_list);
+	xa_init(&bridge->vports);
+	bridge->ifindex = ifindex;
+	bridge->refcnt = 1;
+	bridge->ageing_time = BR_DEFAULT_AGEING_TIME;
+	list_add(&bridge->list, &br_offloads->bridges);
+
+	return bridge;
+
+err_fdb_ht:
+	mlx5_esw_bridge_egress_table_cleanup(bridge);
+err_egress_tbl:
+	kvfree(bridge);
+	return ERR_PTR(err);
+}
+
+static void mlx5_esw_bridge_get(struct mlx5_esw_bridge *bridge)
+{
+	bridge->refcnt++;
+}
+
+static void mlx5_esw_bridge_put(struct mlx5_esw_bridge_offloads *br_offloads,
+				struct mlx5_esw_bridge *bridge)
+{
+	if (--bridge->refcnt)
+		return;
+
+	mlx5_esw_bridge_egress_table_cleanup(bridge);
+	WARN_ON(!xa_empty(&bridge->vports));
+	list_del(&bridge->list);
+	rhashtable_destroy(&bridge->fdb_ht);
+	kvfree(bridge);
+
+	if (list_empty(&br_offloads->bridges))
+		mlx5_esw_bridge_ingress_table_cleanup(br_offloads);
+}
+
+static struct mlx5_esw_bridge *
+mlx5_esw_bridge_lookup(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads)
+{
+	struct mlx5_esw_bridge *bridge;
+
+	ASSERT_RTNL();
+
+	list_for_each_entry(bridge, &br_offloads->bridges, list) {
+		if (bridge->ifindex == ifindex) {
+			mlx5_esw_bridge_get(bridge);
+			return bridge;
+		}
+	}
+
+	if (!br_offloads->ingress_ft) {
+		int err = mlx5_esw_bridge_ingress_table_init(br_offloads);
+
+		if (err)
+			return ERR_PTR(err);
+	}
+
+	bridge = mlx5_esw_bridge_create(ifindex, br_offloads);
+	if (IS_ERR(bridge) && list_empty(&br_offloads->bridges))
+		mlx5_esw_bridge_ingress_table_cleanup(br_offloads);
+	return bridge;
+}
+
+static int mlx5_esw_bridge_port_insert(struct mlx5_esw_bridge_port *port,
+				       struct mlx5_esw_bridge *bridge)
+{
+	return xa_insert(&bridge->vports, port->vport_num, port, GFP_KERNEL);
+}
+
+static struct mlx5_esw_bridge_port *
+mlx5_esw_bridge_port_lookup(u16 vport_num, struct mlx5_esw_bridge *bridge)
+{
+	return xa_load(&bridge->vports, vport_num);
+}
+
+static void mlx5_esw_bridge_port_erase(struct mlx5_esw_bridge_port *port,
+				       struct mlx5_esw_bridge *bridge)
+{
+	xa_erase(&bridge->vports, port->vport_num);
+}
+
+static void mlx5_esw_bridge_fdb_entry_refresh(unsigned long lastuse,
+					      struct mlx5_esw_bridge_fdb_entry *entry)
+{
+	trace_mlx5_esw_bridge_fdb_entry_refresh(entry);
+
+	entry->lastuse = lastuse;
+	mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr,
+					   entry->key.vid,
+					   SWITCHDEV_FDB_ADD_TO_BRIDGE);
+}
+
+static void
+mlx5_esw_bridge_fdb_entry_cleanup(struct mlx5_esw_bridge_fdb_entry *entry,
+				  struct mlx5_esw_bridge *bridge)
+{
+	trace_mlx5_esw_bridge_fdb_entry_cleanup(entry);
+
+	rhashtable_remove_fast(&bridge->fdb_ht, &entry->ht_node, fdb_ht_params);
+	mlx5_del_flow_rules(entry->egress_handle);
+	if (entry->filter_handle)
+		mlx5_del_flow_rules(entry->filter_handle);
+	mlx5_del_flow_rules(entry->ingress_handle);
+	mlx5_fc_destroy(bridge->br_offloads->esw->dev, entry->ingress_counter);
+	list_del(&entry->vlan_list);
+	list_del(&entry->list);
+	kvfree(entry);
+}
+
+static void mlx5_esw_bridge_fdb_flush(struct mlx5_esw_bridge *bridge)
+{
+	struct mlx5_esw_bridge_fdb_entry *entry, *tmp;
+
+	list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) {
+		if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER))
+			mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr,
+							   entry->key.vid,
+							   SWITCHDEV_FDB_DEL_TO_BRIDGE);
+		mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
+	}
+}
+
+static struct mlx5_esw_bridge_vlan *
+mlx5_esw_bridge_vlan_lookup(u16 vid, struct mlx5_esw_bridge_port *port)
+{
+	return xa_load(&port->vlans, vid);
+}
+
+static int
+mlx5_esw_bridge_vlan_push_create(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw)
+{
+	struct {
+		__be16	h_vlan_proto;
+		__be16	h_vlan_TCI;
+	} vlan_hdr = { htons(ETH_P_8021Q), htons(vlan->vid) };
+	struct mlx5_pkt_reformat_params reformat_params = {};
+	struct mlx5_pkt_reformat *pkt_reformat;
+
+	if (!BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat_insert)) ||
+	    MLX5_CAP_GEN_2(esw->dev, max_reformat_insert_size) < sizeof(vlan_hdr) ||
+	    MLX5_CAP_GEN_2(esw->dev, max_reformat_insert_offset) <
+	    offsetof(struct vlan_ethhdr, h_vlan_proto)) {
+		esw_warn(esw->dev, "Packet reformat INSERT_HEADER is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	reformat_params.type = MLX5_REFORMAT_TYPE_INSERT_HDR;
+	reformat_params.param_0 = MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START;
+	reformat_params.param_1 = offsetof(struct vlan_ethhdr, h_vlan_proto);
+	reformat_params.size = sizeof(vlan_hdr);
+	reformat_params.data = &vlan_hdr;
+	pkt_reformat = mlx5_packet_reformat_alloc(esw->dev,
+						  &reformat_params,
+						  MLX5_FLOW_NAMESPACE_FDB);
+	if (IS_ERR(pkt_reformat)) {
+		esw_warn(esw->dev, "Failed to alloc packet reformat INSERT_HEADER (err=%ld)\n",
+			 PTR_ERR(pkt_reformat));
+		return PTR_ERR(pkt_reformat);
+	}
+
+	vlan->pkt_reformat_push = pkt_reformat;
+	return 0;
+}
+
+static void
+mlx5_esw_bridge_vlan_push_cleanup(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw)
+{
+	mlx5_packet_reformat_dealloc(esw->dev, vlan->pkt_reformat_push);
+	vlan->pkt_reformat_push = NULL;
+}
+
+static int
+mlx5_esw_bridge_vlan_pop_create(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw)
+{
+	struct mlx5_pkt_reformat_params reformat_params = {};
+	struct mlx5_pkt_reformat *pkt_reformat;
+
+	if (!BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat_remove)) ||
+	    MLX5_CAP_GEN_2(esw->dev, max_reformat_remove_size) < sizeof(struct vlan_hdr) ||
+	    MLX5_CAP_GEN_2(esw->dev, max_reformat_remove_offset) <
+	    offsetof(struct vlan_ethhdr, h_vlan_proto)) {
+		esw_warn(esw->dev, "Packet reformat REMOVE_HEADER is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	reformat_params.type = MLX5_REFORMAT_TYPE_REMOVE_HDR;
+	reformat_params.param_0 = MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START;
+	reformat_params.param_1 = offsetof(struct vlan_ethhdr, h_vlan_proto);
+	reformat_params.size = sizeof(struct vlan_hdr);
+	pkt_reformat = mlx5_packet_reformat_alloc(esw->dev,
+						  &reformat_params,
+						  MLX5_FLOW_NAMESPACE_FDB);
+	if (IS_ERR(pkt_reformat)) {
+		esw_warn(esw->dev, "Failed to alloc packet reformat REMOVE_HEADER (err=%ld)\n",
+			 PTR_ERR(pkt_reformat));
+		return PTR_ERR(pkt_reformat);
+	}
+
+	vlan->pkt_reformat_pop = pkt_reformat;
+	return 0;
+}
+
+static void
+mlx5_esw_bridge_vlan_pop_cleanup(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw)
+{
+	mlx5_packet_reformat_dealloc(esw->dev, vlan->pkt_reformat_pop);
+	vlan->pkt_reformat_pop = NULL;
+}
+
+static struct mlx5_esw_bridge_vlan *
+mlx5_esw_bridge_vlan_create(u16 vid, u16 flags, struct mlx5_esw_bridge_port *port,
+			    struct mlx5_eswitch *esw)
+{
+	struct mlx5_esw_bridge_vlan *vlan;
+	int err;
+
+	vlan = kvzalloc(sizeof(*vlan), GFP_KERNEL);
+	if (!vlan)
+		return ERR_PTR(-ENOMEM);
+
+	vlan->vid = vid;
+	vlan->flags = flags;
+	INIT_LIST_HEAD(&vlan->fdb_list);
+
+	if (flags & BRIDGE_VLAN_INFO_PVID) {
+		err = mlx5_esw_bridge_vlan_push_create(vlan, esw);
+		if (err)
+			goto err_vlan_push;
+	}
+	if (flags & BRIDGE_VLAN_INFO_UNTAGGED) {
+		err = mlx5_esw_bridge_vlan_pop_create(vlan, esw);
+		if (err)
+			goto err_vlan_pop;
+	}
+
+	err = xa_insert(&port->vlans, vid, vlan, GFP_KERNEL);
+	if (err)
+		goto err_xa_insert;
+
+	trace_mlx5_esw_bridge_vlan_create(vlan);
+	return vlan;
+
+err_xa_insert:
+	if (vlan->pkt_reformat_pop)
+		mlx5_esw_bridge_vlan_pop_cleanup(vlan, esw);
+err_vlan_pop:
+	if (vlan->pkt_reformat_push)
+		mlx5_esw_bridge_vlan_push_cleanup(vlan, esw);
+err_vlan_push:
+	kvfree(vlan);
+	return ERR_PTR(err);
+}
+
+static void mlx5_esw_bridge_vlan_erase(struct mlx5_esw_bridge_port *port,
+				       struct mlx5_esw_bridge_vlan *vlan)
+{
+	xa_erase(&port->vlans, vlan->vid);
+}
+
+static void mlx5_esw_bridge_vlan_flush(struct mlx5_esw_bridge_vlan *vlan,
+				       struct mlx5_esw_bridge *bridge)
+{
+	struct mlx5_esw_bridge_fdb_entry *entry, *tmp;
+
+	list_for_each_entry_safe(entry, tmp, &vlan->fdb_list, vlan_list) {
+		if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER))
+			mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr,
+							   entry->key.vid,
+							   SWITCHDEV_FDB_DEL_TO_BRIDGE);
+		mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
+	}
+
+	if (vlan->pkt_reformat_pop)
+		mlx5_esw_bridge_vlan_pop_cleanup(vlan, bridge->br_offloads->esw);
+	if (vlan->pkt_reformat_push)
+		mlx5_esw_bridge_vlan_push_cleanup(vlan, bridge->br_offloads->esw);
+}
+
+static void mlx5_esw_bridge_vlan_cleanup(struct mlx5_esw_bridge_port *port,
+					 struct mlx5_esw_bridge_vlan *vlan,
+					 struct mlx5_esw_bridge *bridge)
+{
+	trace_mlx5_esw_bridge_vlan_cleanup(vlan);
+	mlx5_esw_bridge_vlan_flush(vlan, bridge);
+	mlx5_esw_bridge_vlan_erase(port, vlan);
+	kvfree(vlan);
+}
+
+static void mlx5_esw_bridge_port_vlans_flush(struct mlx5_esw_bridge_port *port,
+					     struct mlx5_esw_bridge *bridge)
+{
+	struct mlx5_esw_bridge_vlan *vlan;
+	unsigned long index;
+
+	xa_for_each(&port->vlans, index, vlan)
+		mlx5_esw_bridge_vlan_cleanup(port, vlan, bridge);
+}
+
+static struct mlx5_esw_bridge_vlan *
+mlx5_esw_bridge_port_vlan_lookup(u16 vid, u16 vport_num, struct mlx5_esw_bridge *bridge,
+				 struct mlx5_eswitch *esw)
+{
+	struct mlx5_esw_bridge_port *port;
+	struct mlx5_esw_bridge_vlan *vlan;
+
+	port = mlx5_esw_bridge_port_lookup(vport_num, bridge);
+	if (!port) {
+		/* FDB is added asynchronously on wq while port might have been deleted
+		 * concurrently. Report on 'info' logging level and skip the FDB offload.
+		 */
+		esw_info(esw->dev, "Failed to lookup bridge port (vport=%u)\n", vport_num);
+		return ERR_PTR(-EINVAL);
+	}
+
+	vlan = mlx5_esw_bridge_vlan_lookup(vid, port);
+	if (!vlan) {
+		/* FDB is added asynchronously on wq while vlan might have been deleted
+		 * concurrently. Report on 'info' logging level and skip the FDB offload.
+		 */
+		esw_info(esw->dev, "Failed to lookup bridge port vlan metadata (vport=%u)\n",
+			 vport_num);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return vlan;
+}
+
+static struct mlx5_esw_bridge_fdb_entry *
+mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, const unsigned char *addr,
+			       u16 vid, bool added_by_user, struct mlx5_eswitch *esw,
+			       struct mlx5_esw_bridge *bridge)
+{
+	struct mlx5_esw_bridge_vlan *vlan = NULL;
+	struct mlx5_esw_bridge_fdb_entry *entry;
+	struct mlx5_flow_handle *handle;
+	struct mlx5_fc *counter;
+	struct mlx5e_priv *priv;
+	int err;
+
+	if (bridge->flags & MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG && vid) {
+		vlan = mlx5_esw_bridge_port_vlan_lookup(vid, vport_num, bridge, esw);
+		if (IS_ERR(vlan))
+			return ERR_CAST(vlan);
+	}
+
+	priv = netdev_priv(dev);
+	entry = kvzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return ERR_PTR(-ENOMEM);
+
+	ether_addr_copy(entry->key.addr, addr);
+	entry->key.vid = vid;
+	entry->dev = dev;
+	entry->vport_num = vport_num;
+	entry->lastuse = jiffies;
+	if (added_by_user)
+		entry->flags |= MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER;
+
+	counter = mlx5_fc_create(priv->mdev, true);
+	if (IS_ERR(counter)) {
+		err = PTR_ERR(counter);
+		goto err_ingress_fc_create;
+	}
+	entry->ingress_counter = counter;
+
+	handle = mlx5_esw_bridge_ingress_flow_create(vport_num, addr, vlan, mlx5_fc_id(counter),
+						     bridge);
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		esw_warn(esw->dev, "Failed to create ingress flow(vport=%u,err=%d)\n",
+			 vport_num, err);
+		goto err_ingress_flow_create;
+	}
+	entry->ingress_handle = handle;
+
+	if (bridge->flags & MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG) {
+		handle = mlx5_esw_bridge_ingress_filter_flow_create(vport_num, addr, bridge);
+		if (IS_ERR(handle)) {
+			err = PTR_ERR(handle);
+			esw_warn(esw->dev, "Failed to create ingress filter(vport=%u,err=%d)\n",
+				 vport_num, err);
+			goto err_ingress_filter_flow_create;
+		}
+		entry->filter_handle = handle;
+	}
+
+	handle = mlx5_esw_bridge_egress_flow_create(vport_num, addr, vlan, bridge);
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		esw_warn(esw->dev, "Failed to create egress flow(vport=%u,err=%d)\n",
+			 vport_num, err);
+		goto err_egress_flow_create;
+	}
+	entry->egress_handle = handle;
+
+	err = rhashtable_insert_fast(&bridge->fdb_ht, &entry->ht_node, fdb_ht_params);
+	if (err) {
+		esw_warn(esw->dev, "Failed to insert FDB flow(vport=%u,err=%d)\n", vport_num, err);
+		goto err_ht_init;
+	}
+
+	if (vlan)
+		list_add(&entry->vlan_list, &vlan->fdb_list);
+	else
+		INIT_LIST_HEAD(&entry->vlan_list);
+	list_add(&entry->list, &bridge->fdb_list);
+
+	trace_mlx5_esw_bridge_fdb_entry_init(entry);
+	return entry;
+
+err_ht_init:
+	mlx5_del_flow_rules(entry->egress_handle);
+err_egress_flow_create:
+	if (entry->filter_handle)
+		mlx5_del_flow_rules(entry->filter_handle);
+err_ingress_filter_flow_create:
+	mlx5_del_flow_rules(entry->ingress_handle);
+err_ingress_flow_create:
+	mlx5_fc_destroy(priv->mdev, entry->ingress_counter);
+err_ingress_fc_create:
+	kvfree(entry);
+	return ERR_PTR(err);
+}
+
+int mlx5_esw_bridge_ageing_time_set(unsigned long ageing_time, struct mlx5_eswitch *esw,
+				    struct mlx5_vport *vport)
+{
+	if (!vport->bridge)
+		return -EINVAL;
+
+	vport->bridge->ageing_time = ageing_time;
+	return 0;
+}
+
+int mlx5_esw_bridge_vlan_filtering_set(bool enable, struct mlx5_eswitch *esw,
+				       struct mlx5_vport *vport)
+{
+	struct mlx5_esw_bridge *bridge;
+	bool filtering;
+
+	if (!vport->bridge)
+		return -EINVAL;
+
+	bridge = vport->bridge;
+	filtering = bridge->flags & MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG;
+	if (filtering == enable)
+		return 0;
+
+	mlx5_esw_bridge_fdb_flush(bridge);
+	if (enable)
+		bridge->flags |= MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG;
+	else
+		bridge->flags &= ~MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG;
+
+	return 0;
+}
+
+static int mlx5_esw_bridge_vport_init(struct mlx5_esw_bridge_offloads *br_offloads,
+				      struct mlx5_esw_bridge *bridge,
+				      struct mlx5_vport *vport)
+{
+	struct mlx5_eswitch *esw = br_offloads->esw;
+	struct mlx5_esw_bridge_port *port;
+	int err;
+
+	port = kvzalloc(sizeof(*port), GFP_KERNEL);
+	if (!port) {
+		err = -ENOMEM;
+		goto err_port_alloc;
+	}
+
+	port->vport_num = vport->vport;
+	xa_init(&port->vlans);
+	err = mlx5_esw_bridge_port_insert(port, bridge);
+	if (err) {
+		esw_warn(esw->dev, "Failed to insert port metadata (vport=%u,err=%d)\n",
+			 vport->vport, err);
+		goto err_port_insert;
+	}
+	trace_mlx5_esw_bridge_vport_init(port);
+
+	vport->bridge = bridge;
+	return 0;
+
+err_port_insert:
+	kvfree(port);
+err_port_alloc:
+	mlx5_esw_bridge_put(br_offloads, bridge);
+	return err;
+}
+
+static int mlx5_esw_bridge_vport_cleanup(struct mlx5_esw_bridge_offloads *br_offloads,
+					 struct mlx5_vport *vport)
+{
+	struct mlx5_esw_bridge *bridge = vport->bridge;
+	struct mlx5_esw_bridge_fdb_entry *entry, *tmp;
+	struct mlx5_esw_bridge_port *port;
+
+	list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list)
+		if (entry->vport_num == vport->vport)
+			mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
+
+	port = mlx5_esw_bridge_port_lookup(vport->vport, bridge);
+	if (!port) {
+		WARN(1, "Vport %u metadata not found on bridge", vport->vport);
+		return -EINVAL;
+	}
+
+	trace_mlx5_esw_bridge_vport_cleanup(port);
+	mlx5_esw_bridge_port_vlans_flush(port, bridge);
+	mlx5_esw_bridge_port_erase(port, bridge);
+	kvfree(port);
+	mlx5_esw_bridge_put(br_offloads, bridge);
+	vport->bridge = NULL;
+	return 0;
+}
+
+int mlx5_esw_bridge_vport_link(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads,
+			       struct mlx5_vport *vport, struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_bridge *bridge;
+	int err;
+
+	WARN_ON(vport->bridge);
+
+	bridge = mlx5_esw_bridge_lookup(ifindex, br_offloads);
+	if (IS_ERR(bridge)) {
+		NL_SET_ERR_MSG_MOD(extack, "Error checking for existing bridge with same ifindex");
+		return PTR_ERR(bridge);
+	}
+
+	err = mlx5_esw_bridge_vport_init(br_offloads, bridge, vport);
+	if (err)
+		NL_SET_ERR_MSG_MOD(extack, "Error initializing port");
+	return err;
+}
+
+int mlx5_esw_bridge_vport_unlink(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads,
+				 struct mlx5_vport *vport, struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_bridge *bridge = vport->bridge;
+	int err;
+
+	if (!bridge) {
+		NL_SET_ERR_MSG_MOD(extack, "Port is not attached to any bridge");
+		return -EINVAL;
+	}
+	if (bridge->ifindex != ifindex) {
+		NL_SET_ERR_MSG_MOD(extack, "Port is attached to another bridge");
+		return -EINVAL;
+	}
+
+	err = mlx5_esw_bridge_vport_cleanup(br_offloads, vport);
+	if (err)
+		NL_SET_ERR_MSG_MOD(extack, "Port cleanup failed");
+	return err;
+}
+
+int mlx5_esw_bridge_port_vlan_add(u16 vid, u16 flags, struct mlx5_eswitch *esw,
+				  struct mlx5_vport *vport, struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_bridge_port *port;
+	struct mlx5_esw_bridge_vlan *vlan;
+
+	port = mlx5_esw_bridge_port_lookup(vport->vport, vport->bridge);
+	if (!port)
+		return -EINVAL;
+
+	vlan = mlx5_esw_bridge_vlan_lookup(vid, port);
+	if (vlan) {
+		if (vlan->flags == flags)
+			return 0;
+		mlx5_esw_bridge_vlan_cleanup(port, vlan, vport->bridge);
+	}
+
+	vlan = mlx5_esw_bridge_vlan_create(vid, flags, port, esw);
+	if (IS_ERR(vlan)) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to create VLAN entry");
+		return PTR_ERR(vlan);
+	}
+	return 0;
+}
+
+void mlx5_esw_bridge_port_vlan_del(u16 vid, struct mlx5_eswitch *esw, struct mlx5_vport *vport)
+{
+	struct mlx5_esw_bridge_port *port;
+	struct mlx5_esw_bridge_vlan *vlan;
+
+	port = mlx5_esw_bridge_port_lookup(vport->vport, vport->bridge);
+	if (!port)
+		return;
+
+	vlan = mlx5_esw_bridge_vlan_lookup(vid, port);
+	if (!vlan)
+		return;
+	mlx5_esw_bridge_vlan_cleanup(port, vlan, vport->bridge);
+}
+
+void mlx5_esw_bridge_fdb_create(struct net_device *dev, struct mlx5_eswitch *esw,
+				struct mlx5_vport *vport,
+				struct switchdev_notifier_fdb_info *fdb_info)
+{
+	struct mlx5_esw_bridge *bridge = vport->bridge;
+	struct mlx5_esw_bridge_fdb_entry *entry;
+	u16 vport_num = vport->vport;
+
+	if (!bridge) {
+		esw_info(esw->dev, "Vport is not assigned to bridge (vport=%u)\n", vport_num);
+		return;
+	}
+
+	entry = mlx5_esw_bridge_fdb_entry_init(dev, vport_num, fdb_info->addr, fdb_info->vid,
+					       fdb_info->added_by_user, esw, bridge);
+	if (IS_ERR(entry))
+		return;
+
+	if (entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER)
+		mlx5_esw_bridge_fdb_offload_notify(dev, entry->key.addr, entry->key.vid,
+						   SWITCHDEV_FDB_OFFLOADED);
+	else
+		/* Take over dynamic entries to prevent kernel bridge from aging them out. */
+		mlx5_esw_bridge_fdb_offload_notify(dev, entry->key.addr, entry->key.vid,
+						   SWITCHDEV_FDB_ADD_TO_BRIDGE);
+}
+
+void mlx5_esw_bridge_fdb_remove(struct net_device *dev, struct mlx5_eswitch *esw,
+				struct mlx5_vport *vport,
+				struct switchdev_notifier_fdb_info *fdb_info)
+{
+	struct mlx5_esw_bridge *bridge = vport->bridge;
+	struct mlx5_esw_bridge_fdb_entry *entry;
+	struct mlx5_esw_bridge_fdb_key key;
+	u16 vport_num = vport->vport;
+
+	if (!bridge) {
+		esw_warn(esw->dev, "Vport is not assigned to bridge (vport=%u)\n", vport_num);
+		return;
+	}
+
+	ether_addr_copy(key.addr, fdb_info->addr);
+	key.vid = fdb_info->vid;
+	entry = rhashtable_lookup_fast(&bridge->fdb_ht, &key, fdb_ht_params);
+	if (!entry) {
+		esw_warn(esw->dev,
+			 "FDB entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n",
+			 key.addr, key.vid, vport_num);
+		return;
+	}
+
+	if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER))
+		mlx5_esw_bridge_fdb_offload_notify(dev, entry->key.addr, entry->key.vid,
+						   SWITCHDEV_FDB_DEL_TO_BRIDGE);
+	mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
+}
+
+void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads)
+{
+	struct mlx5_esw_bridge_fdb_entry *entry, *tmp;
+	struct mlx5_esw_bridge *bridge;
+
+	list_for_each_entry(bridge, &br_offloads->bridges, list) {
+		list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) {
+			unsigned long lastuse =
+				(unsigned long)mlx5_fc_query_lastuse(entry->ingress_counter);
+
+			if (entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER)
+				continue;
+
+			if (time_after(lastuse, entry->lastuse)) {
+				mlx5_esw_bridge_fdb_entry_refresh(lastuse, entry);
+			} else if (time_is_before_jiffies(entry->lastuse + bridge->ageing_time)) {
+				mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr,
+								   entry->key.vid,
+								   SWITCHDEV_FDB_DEL_TO_BRIDGE);
+				mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
+			}
+		}
+	}
+}
+
+static void mlx5_esw_bridge_flush(struct mlx5_esw_bridge_offloads *br_offloads)
+{
+	struct mlx5_eswitch *esw = br_offloads->esw;
+	struct mlx5_vport *vport;
+	unsigned long i;
+
+	mlx5_esw_for_each_vport(esw, i, vport)
+		if (vport->bridge)
+			mlx5_esw_bridge_vport_cleanup(br_offloads, vport);
+
+	WARN_ONCE(!list_empty(&br_offloads->bridges),
+		  "Cleaning up bridge offloads while still having bridges attached\n");
+}
+
+struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw)
+{
+	struct mlx5_esw_bridge_offloads *br_offloads;
+
+	br_offloads = kvzalloc(sizeof(*br_offloads), GFP_KERNEL);
+	if (!br_offloads)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&br_offloads->bridges);
+	br_offloads->esw = esw;
+	esw->br_offloads = br_offloads;
+
+	return br_offloads;
+}
+
+void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw)
+{
+	struct mlx5_esw_bridge_offloads *br_offloads = esw->br_offloads;
+
+	if (!br_offloads)
+		return;
+
+	mlx5_esw_bridge_flush(br_offloads);
+
+	esw->br_offloads = NULL;
+	kvfree(br_offloads);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
new file mode 100644
index 000000000000..d826942b27fc
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021 Mellanox Technologies. */
+
+#ifndef __MLX5_ESW_BRIDGE_H__
+#define __MLX5_ESW_BRIDGE_H__
+
+#include <linux/notifier.h>
+#include <linux/list.h>
+#include <linux/workqueue.h>
+#include "eswitch.h"
+
+struct mlx5_flow_table;
+struct mlx5_flow_group;
+
+struct mlx5_esw_bridge_offloads {
+	struct mlx5_eswitch *esw;
+	struct list_head bridges;
+	struct notifier_block netdev_nb;
+	struct notifier_block nb_blk;
+	struct notifier_block nb;
+	struct workqueue_struct *wq;
+	struct delayed_work update_work;
+
+	struct mlx5_flow_table *ingress_ft;
+	struct mlx5_flow_group *ingress_vlan_fg;
+	struct mlx5_flow_group *ingress_filter_fg;
+	struct mlx5_flow_group *ingress_mac_fg;
+
+	struct mlx5_flow_table *skip_ft;
+};
+
+struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw);
+void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw);
+int mlx5_esw_bridge_vport_link(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads,
+			       struct mlx5_vport *vport, struct netlink_ext_ack *extack);
+int mlx5_esw_bridge_vport_unlink(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads,
+				 struct mlx5_vport *vport, struct netlink_ext_ack *extack);
+void mlx5_esw_bridge_fdb_create(struct net_device *dev, struct mlx5_eswitch *esw,
+				struct mlx5_vport *vport,
+				struct switchdev_notifier_fdb_info *fdb_info);
+void mlx5_esw_bridge_fdb_remove(struct net_device *dev, struct mlx5_eswitch *esw,
+				struct mlx5_vport *vport,
+				struct switchdev_notifier_fdb_info *fdb_info);
+void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads);
+int mlx5_esw_bridge_ageing_time_set(unsigned long ageing_time, struct mlx5_eswitch *esw,
+				    struct mlx5_vport *vport);
+int mlx5_esw_bridge_vlan_filtering_set(bool enable, struct mlx5_eswitch *esw,
+				       struct mlx5_vport *vport);
+int mlx5_esw_bridge_port_vlan_add(u16 vid, u16 flags, struct mlx5_eswitch *esw,
+				  struct mlx5_vport *vport, struct netlink_ext_ack *extack);
+void mlx5_esw_bridge_port_vlan_del(u16 vid, struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+
+#endif /* __MLX5_ESW_BRIDGE_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
new file mode 100644
index 000000000000..d9ab2e8bc2cb
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021 Mellanox Technologies. */
+
+#ifndef _MLX5_ESW_BRIDGE_PRIVATE_
+#define _MLX5_ESW_BRIDGE_PRIVATE_
+
+#include <linux/netdevice.h>
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
+#include <linux/if_ether.h>
+#include <linux/rhashtable.h>
+#include <linux/xarray.h>
+#include "fs_core.h"
+
+struct mlx5_esw_bridge_fdb_key {
+	unsigned char addr[ETH_ALEN];
+	u16 vid;
+};
+
+enum {
+	MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER = BIT(0),
+};
+
+struct mlx5_esw_bridge_fdb_entry {
+	struct mlx5_esw_bridge_fdb_key key;
+	struct rhash_head ht_node;
+	struct net_device *dev;
+	struct list_head list;
+	struct list_head vlan_list;
+	u16 vport_num;
+	u16 flags;
+
+	struct mlx5_flow_handle *ingress_handle;
+	struct mlx5_fc *ingress_counter;
+	unsigned long lastuse;
+	struct mlx5_flow_handle *egress_handle;
+	struct mlx5_flow_handle *filter_handle;
+};
+
+struct mlx5_esw_bridge_vlan {
+	u16 vid;
+	u16 flags;
+	struct list_head fdb_list;
+	struct mlx5_pkt_reformat *pkt_reformat_push;
+	struct mlx5_pkt_reformat *pkt_reformat_pop;
+};
+
+struct mlx5_esw_bridge_port {
+	u16 vport_num;
+	struct xarray vlans;
+};
+
+#endif /* _MLX5_ESW_BRIDGE_PRIVATE_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h
new file mode 100644
index 000000000000..227964b7d3b9
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h
@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021 Mellanox Technologies. */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mlx5
+
+#if !defined(_MLX5_ESW_BRIDGE_TRACEPOINT_) || defined(TRACE_HEADER_MULTI_READ)
+#define _MLX5_ESW_BRIDGE_TRACEPOINT_
+
+#include <linux/tracepoint.h>
+#include "../bridge_priv.h"
+
+DECLARE_EVENT_CLASS(mlx5_esw_bridge_fdb_template,
+		    TP_PROTO(const struct mlx5_esw_bridge_fdb_entry *fdb),
+		    TP_ARGS(fdb),
+		    TP_STRUCT__entry(
+			    __array(char, dev_name, IFNAMSIZ)
+			    __array(unsigned char, addr, ETH_ALEN)
+			    __field(u16, vid)
+			    __field(u16, flags)
+			    __field(unsigned int, used)
+			    ),
+		    TP_fast_assign(
+			    strncpy(__entry->dev_name,
+				    netdev_name(fdb->dev),
+				    IFNAMSIZ);
+			    memcpy(__entry->addr, fdb->key.addr, ETH_ALEN);
+			    __entry->vid = fdb->key.vid;
+			    __entry->flags = fdb->flags;
+			    __entry->used = jiffies_to_msecs(jiffies - fdb->lastuse)
+			    ),
+		    TP_printk("net_device=%s addr=%pM vid=%hu flags=%hx used=%u",
+			      __entry->dev_name,
+			      __entry->addr,
+			      __entry->vid,
+			      __entry->flags,
+			      __entry->used / 1000)
+	);
+
+DEFINE_EVENT(mlx5_esw_bridge_fdb_template,
+	     mlx5_esw_bridge_fdb_entry_init,
+	     TP_PROTO(const struct mlx5_esw_bridge_fdb_entry *fdb),
+	     TP_ARGS(fdb)
+	);
+DEFINE_EVENT(mlx5_esw_bridge_fdb_template,
+	     mlx5_esw_bridge_fdb_entry_refresh,
+	     TP_PROTO(const struct mlx5_esw_bridge_fdb_entry *fdb),
+	     TP_ARGS(fdb)
+	);
+DEFINE_EVENT(mlx5_esw_bridge_fdb_template,
+	     mlx5_esw_bridge_fdb_entry_cleanup,
+	     TP_PROTO(const struct mlx5_esw_bridge_fdb_entry *fdb),
+	     TP_ARGS(fdb)
+	);
+
+DECLARE_EVENT_CLASS(mlx5_esw_bridge_vlan_template,
+		    TP_PROTO(const struct mlx5_esw_bridge_vlan *vlan),
+		    TP_ARGS(vlan),
+		    TP_STRUCT__entry(
+			    __field(u16, vid)
+			    __field(u16, flags)
+			    ),
+		    TP_fast_assign(
+			    __entry->vid = vlan->vid;
+			    __entry->flags = vlan->flags;
+			    ),
+		    TP_printk("vid=%hu flags=%hx",
+			      __entry->vid,
+			      __entry->flags)
+	);
+
+DEFINE_EVENT(mlx5_esw_bridge_vlan_template,
+	     mlx5_esw_bridge_vlan_create,
+	     TP_PROTO(const struct mlx5_esw_bridge_vlan *vlan),
+	     TP_ARGS(vlan)
+	);
+DEFINE_EVENT(mlx5_esw_bridge_vlan_template,
+	     mlx5_esw_bridge_vlan_cleanup,
+	     TP_PROTO(const struct mlx5_esw_bridge_vlan *vlan),
+	     TP_ARGS(vlan)
+	);
+
+DECLARE_EVENT_CLASS(mlx5_esw_bridge_port_template,
+		    TP_PROTO(const struct mlx5_esw_bridge_port *port),
+		    TP_ARGS(port),
+		    TP_STRUCT__entry(
+			    __field(u16, vport_num)
+			    ),
+		    TP_fast_assign(
+			    __entry->vport_num = port->vport_num;
+			    ),
+		    TP_printk("vport_num=%hu", __entry->vport_num)
+	);
+
+DEFINE_EVENT(mlx5_esw_bridge_port_template,
+	     mlx5_esw_bridge_vport_init,
+	     TP_PROTO(const struct mlx5_esw_bridge_port *port),
+	     TP_ARGS(port)
+	);
+DEFINE_EVENT(mlx5_esw_bridge_port_template,
+	     mlx5_esw_bridge_vport_cleanup,
+	     TP_PROTO(const struct mlx5_esw_bridge_port *port),
+	     TP_ARGS(port)
+	);
+
+#endif
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH esw/diag
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE bridge_tracepoint
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 64ccb2bc0b58..48cac5bf606d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -150,6 +150,8 @@ enum mlx5_eswitch_vport_event {
 	MLX5_VPORT_PROMISC_CHANGE = BIT(3),
 };
 
+struct mlx5_esw_bridge;
+
 struct mlx5_vport {
 	struct mlx5_core_dev    *dev;
 	struct hlist_head       uc_list[MLX5_L2_ADDR_HASH_SIZE];
@@ -178,6 +180,7 @@ struct mlx5_vport {
 	enum mlx5_eswitch_vport_event enabled_events;
 	int index;
 	struct devlink_port *dl_port;
+	struct mlx5_esw_bridge *bridge;
 };
 
 struct mlx5_esw_indir_table;
@@ -196,6 +199,7 @@ struct mlx5_eswitch_fdb {
 
 		struct offloads_fdb {
 			struct mlx5_flow_namespace *ns;
+			struct mlx5_flow_table *tc_miss_table;
 			struct mlx5_flow_table *slow_fdb;
 			struct mlx5_flow_group *send_to_vport_grp;
 			struct mlx5_flow_group *send_to_vport_meta_grp;
@@ -270,6 +274,8 @@ enum {
 	MLX5_ESWITCH_REG_C1_LOOPBACK_ENABLED = BIT(1),
 };
 
+struct mlx5_esw_bridge_offloads;
+
 struct mlx5_eswitch {
 	struct mlx5_core_dev    *dev;
 	struct mlx5_nb          nb;
@@ -299,6 +305,7 @@ struct mlx5_eswitch {
 		u32             root_tsar_id;
 	} qos;
 
+	struct mlx5_esw_bridge_offloads *br_offloads;
 	struct mlx5_esw_offload offloads;
 	int                     mode;
 	u16                     manager_vport;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index d18a28a6e9a6..7579f3402776 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1634,7 +1634,21 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	}
 	esw->fdb_table.offloads.slow_fdb = fdb;
 
-	err = esw_chains_create(esw, fdb);
+	/* Create empty TC-miss managed table. This allows plugging in following
+	 * priorities without directly exposing their level 0 table to
+	 * eswitch_offloads and passing it as miss_fdb to following call to
+	 * esw_chains_create().
+	 */
+	memset(&ft_attr, 0, sizeof(ft_attr));
+	ft_attr.prio = FDB_TC_MISS;
+	esw->fdb_table.offloads.tc_miss_table = mlx5_create_flow_table(root_ns, &ft_attr);
+	if (IS_ERR(esw->fdb_table.offloads.tc_miss_table)) {
+		err = PTR_ERR(esw->fdb_table.offloads.tc_miss_table);
+		esw_warn(dev, "Failed to create TC miss FDB Table err %d\n", err);
+		goto tc_miss_table_err;
+	}
+
+	err = esw_chains_create(esw, esw->fdb_table.offloads.tc_miss_table);
 	if (err) {
 		esw_warn(dev, "Failed to open fdb chains err(%d)\n", err);
 		goto fdb_chains_err;
@@ -1779,6 +1793,8 @@ send_vport_meta_err:
 send_vport_err:
 	esw_chains_destroy(esw, esw_chains(esw));
 fdb_chains_err:
+	mlx5_destroy_flow_table(esw->fdb_table.offloads.tc_miss_table);
+tc_miss_table_err:
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
 slow_fdb_err:
 	/* Holds true only as long as DMFS is the default */
@@ -1806,6 +1822,7 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 
 	esw_chains_destroy(esw, esw_chains(esw));
 
+	mlx5_destroy_flow_table(esw->fdb_table.offloads.tc_miss_table);
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
 	/* Holds true only as long as DMFS is the default */
 	mlx5_flow_namespace_set_mode(esw->fdb_table.offloads.ns,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 8e06731d3cb3..896a6c3dbdb7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -36,6 +36,7 @@
 
 #include "fs_core.h"
 #include "fs_cmd.h"
+#include "fs_ft_pool.h"
 #include "mlx5_core.h"
 #include "eswitch.h"
 
@@ -49,9 +50,11 @@ static int mlx5_cmd_stub_update_root_ft(struct mlx5_flow_root_namespace *ns,
 
 static int mlx5_cmd_stub_create_flow_table(struct mlx5_flow_root_namespace *ns,
 					   struct mlx5_flow_table *ft,
-					   unsigned int log_size,
+					   unsigned int size,
 					   struct mlx5_flow_table *next_ft)
 {
+	ft->max_fte = size ? roundup_pow_of_two(size) : 1;
+
 	return 0;
 }
 
@@ -108,9 +111,7 @@ static int mlx5_cmd_stub_delete_fte(struct mlx5_flow_root_namespace *ns,
 }
 
 static int mlx5_cmd_stub_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
-					       int reformat_type,
-					       size_t size,
-					       void *reformat_data,
+					       struct mlx5_pkt_reformat_params *params,
 					       enum mlx5_flow_namespace_type namespace,
 					       struct mlx5_pkt_reformat *pkt_reformat)
 {
@@ -181,7 +182,7 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns,
 
 static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns,
 				      struct mlx5_flow_table *ft,
-				      unsigned int log_size,
+				      unsigned int size,
 				      struct mlx5_flow_table *next_ft)
 {
 	int en_encap = !!(ft->flags & MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT);
@@ -192,12 +193,18 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns,
 	struct mlx5_core_dev *dev = ns->dev;
 	int err;
 
+	if (size != POOL_NEXT_SIZE)
+		size = roundup_pow_of_two(size);
+	size = mlx5_ft_pool_get_avail_sz(dev, ft->type, size);
+	if (!size)
+		return -ENOSPC;
+
 	MLX5_SET(create_flow_table_in, in, opcode,
 		 MLX5_CMD_OP_CREATE_FLOW_TABLE);
 
 	MLX5_SET(create_flow_table_in, in, table_type, ft->type);
 	MLX5_SET(create_flow_table_in, in, flow_table_context.level, ft->level);
-	MLX5_SET(create_flow_table_in, in, flow_table_context.log_size, log_size);
+	MLX5_SET(create_flow_table_in, in, flow_table_context.log_size, size ? ilog2(size) : 0);
 	MLX5_SET(create_flow_table_in, in, vport_number, ft->vport);
 	MLX5_SET(create_flow_table_in, in, other_vport,
 		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
@@ -234,9 +241,14 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns,
 	}
 
 	err = mlx5_cmd_exec_inout(dev, create_flow_table, in, out);
-	if (!err)
+	if (!err) {
 		ft->id = MLX5_GET(create_flow_table_out, out,
 				  table_id);
+		ft->max_fte = size;
+	} else {
+		mlx5_ft_pool_put_sz(ns->dev, size);
+	}
+
 	return err;
 }
 
@@ -245,6 +257,7 @@ static int mlx5_cmd_destroy_flow_table(struct mlx5_flow_root_namespace *ns,
 {
 	u32 in[MLX5_ST_SZ_DW(destroy_flow_table_in)] = {};
 	struct mlx5_core_dev *dev = ns->dev;
+	int err;
 
 	MLX5_SET(destroy_flow_table_in, in, opcode,
 		 MLX5_CMD_OP_DESTROY_FLOW_TABLE);
@@ -254,7 +267,11 @@ static int mlx5_cmd_destroy_flow_table(struct mlx5_flow_root_namespace *ns,
 	MLX5_SET(destroy_flow_table_in, in, other_vport,
 		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
 
-	return mlx5_cmd_exec_in(dev, destroy_flow_table, in);
+	err = mlx5_cmd_exec_in(dev, destroy_flow_table, in);
+	if (!err)
+		mlx5_ft_pool_put_sz(ns->dev, ft->max_fte);
+
+	return err;
 }
 
 static int mlx5_cmd_modify_flow_table(struct mlx5_flow_root_namespace *ns,
@@ -682,9 +699,7 @@ int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len,
 }
 
 static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
-					  int reformat_type,
-					  size_t size,
-					  void *reformat_data,
+					  struct mlx5_pkt_reformat_params *params,
 					  enum mlx5_flow_namespace_type namespace,
 					  struct mlx5_pkt_reformat *pkt_reformat)
 {
@@ -702,14 +717,14 @@ static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
 	else
 		max_encap_size = MLX5_CAP_FLOWTABLE(dev, max_encap_header_size);
 
-	if (size > max_encap_size) {
+	if (params->size > max_encap_size) {
 		mlx5_core_warn(dev, "encap size %zd too big, max supported is %d\n",
-			       size, max_encap_size);
+			       params->size, max_encap_size);
 		return -EINVAL;
 	}
 
-	in = kzalloc(MLX5_ST_SZ_BYTES(alloc_packet_reformat_context_in) + size,
-		     GFP_KERNEL);
+	in = kzalloc(MLX5_ST_SZ_BYTES(alloc_packet_reformat_context_in) +
+		     params->size, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
 
@@ -718,15 +733,20 @@ static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
 	reformat = MLX5_ADDR_OF(packet_reformat_context_in,
 				packet_reformat_context_in,
 				reformat_data);
-	inlen = reformat - (void *)in  + size;
+	inlen = reformat - (void *)in + params->size;
 
 	MLX5_SET(alloc_packet_reformat_context_in, in, opcode,
 		 MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT);
 	MLX5_SET(packet_reformat_context_in, packet_reformat_context_in,
-		 reformat_data_size, size);
+		 reformat_data_size, params->size);
+	MLX5_SET(packet_reformat_context_in, packet_reformat_context_in,
+		 reformat_type, params->type);
+	MLX5_SET(packet_reformat_context_in, packet_reformat_context_in,
+		 reformat_param_0, params->param_0);
 	MLX5_SET(packet_reformat_context_in, packet_reformat_context_in,
-		 reformat_type, reformat_type);
-	memcpy(reformat, reformat_data, size);
+		 reformat_param_1, params->param_1);
+	if (params->data && params->size)
+		memcpy(reformat, params->data, params->size);
 
 	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
index d62de642eca9..5ecd33cdc087 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
@@ -38,7 +38,7 @@
 struct mlx5_flow_cmds {
 	int (*create_flow_table)(struct mlx5_flow_root_namespace *ns,
 				 struct mlx5_flow_table *ft,
-				 unsigned int log_size,
+				 unsigned int size,
 				 struct mlx5_flow_table *next_ft);
 	int (*destroy_flow_table)(struct mlx5_flow_root_namespace *ns,
 				  struct mlx5_flow_table *ft);
@@ -77,9 +77,7 @@ struct mlx5_flow_cmds {
 			      bool disconnect);
 
 	int (*packet_reformat_alloc)(struct mlx5_flow_root_namespace *ns,
-				     int reformat_type,
-				     size_t size,
-				     void *reformat_data,
+				     struct mlx5_pkt_reformat_params *params,
 				     enum mlx5_flow_namespace_type namespace,
 				     struct mlx5_pkt_reformat *pkt_reformat);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index f74d2c834037..2cd7aea5d329 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -38,6 +38,7 @@
 #include "mlx5_core.h"
 #include "fs_core.h"
 #include "fs_cmd.h"
+#include "fs_ft_pool.h"
 #include "diag/fs_tracepoint.h"
 #include "accel/ipsec.h"
 #include "fpga/ipsec.h"
@@ -752,7 +753,7 @@ static struct mlx5_flow_group *alloc_insert_flow_group(struct mlx5_flow_table *f
 	return fg;
 }
 
-static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, int max_fte,
+static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport,
 						enum fs_flow_table_type table_type,
 						enum fs_flow_table_op_mod op_mod,
 						u32 flags)
@@ -775,7 +776,6 @@ static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, int max_ft
 	ft->op_mod = op_mod;
 	ft->type = table_type;
 	ft->vport = vport;
-	ft->max_fte = max_fte;
 	ft->flags = flags;
 	INIT_LIST_HEAD(&ft->fwd_rules);
 	mutex_init(&ft->lock);
@@ -1070,7 +1070,6 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
 	struct mlx5_flow_table *next_ft;
 	struct fs_prio *fs_prio = NULL;
 	struct mlx5_flow_table *ft;
-	int log_table_sz;
 	int err;
 
 	if (!root) {
@@ -1101,7 +1100,6 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
 	 */
 	ft = alloc_flow_table(ft_attr->level,
 			      vport,
-			      ft_attr->max_fte ? roundup_pow_of_two(ft_attr->max_fte) : 0,
 			      root->table_type,
 			      op_mod, ft_attr->flags);
 	if (IS_ERR(ft)) {
@@ -1110,12 +1108,11 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
 	}
 
 	tree_init_node(&ft->node, del_hw_flow_table, del_sw_flow_table);
-	log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0;
 	next_ft = unmanaged ? ft_attr->next_ft :
 			      find_next_chained_ft(fs_prio);
 	ft->def_miss_action = ns->def_miss_action;
 	ft->ns = ns;
-	err = root->cmds->create_flow_table(root, ft, log_table_sz, next_ft);
+	err = root->cmds->create_flow_table(root, ft, ft_attr->max_fte, next_ft);
 	if (err)
 		goto free_ft;
 
@@ -1170,28 +1167,36 @@ mlx5_create_lag_demux_flow_table(struct mlx5_flow_namespace *ns,
 
 	ft_attr.level = level;
 	ft_attr.prio  = prio;
+	ft_attr.max_fte = 1;
+
 	return __mlx5_create_flow_table(ns, &ft_attr, FS_FT_OP_MOD_LAG_DEMUX, 0);
 }
 EXPORT_SYMBOL(mlx5_create_lag_demux_flow_table);
 
+#define MAX_FLOW_GROUP_SIZE BIT(24)
 struct mlx5_flow_table*
 mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
 				    struct mlx5_flow_table_attr *ft_attr)
 {
 	int num_reserved_entries = ft_attr->autogroup.num_reserved_entries;
-	int autogroups_max_fte = ft_attr->max_fte - num_reserved_entries;
 	int max_num_groups = ft_attr->autogroup.max_num_groups;
 	struct mlx5_flow_table *ft;
-
-	if (max_num_groups > autogroups_max_fte)
-		return ERR_PTR(-EINVAL);
-	if (num_reserved_entries > ft_attr->max_fte)
-		return ERR_PTR(-EINVAL);
+	int autogroups_max_fte;
 
 	ft = mlx5_create_flow_table(ns, ft_attr);
 	if (IS_ERR(ft))
 		return ft;
 
+	autogroups_max_fte = ft->max_fte - num_reserved_entries;
+	if (max_num_groups > autogroups_max_fte)
+		goto err_validate;
+	if (num_reserved_entries > ft->max_fte)
+		goto err_validate;
+
+	/* Align the number of groups according to the largest group size */
+	if (autogroups_max_fte / (max_num_groups + 1) > MAX_FLOW_GROUP_SIZE)
+		max_num_groups = (autogroups_max_fte / MAX_FLOW_GROUP_SIZE) - 1;
+
 	ft->autogroup.active = true;
 	ft->autogroup.required_groups = max_num_groups;
 	ft->autogroup.max_fte = autogroups_max_fte;
@@ -1199,6 +1204,10 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
 	ft->autogroup.group_size = autogroups_max_fte / (max_num_groups + 1);
 
 	return ft;
+
+err_validate:
+	mlx5_destroy_flow_table(ft);
+	return ERR_PTR(-ENOSPC);
 }
 EXPORT_SYMBOL(mlx5_create_auto_grouped_flow_table);
 
@@ -2592,6 +2601,7 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev)
 	mlx5_cleanup_fc_stats(dev);
 	kmem_cache_destroy(steering->ftes_cache);
 	kmem_cache_destroy(steering->fgs_cache);
+	mlx5_ft_pool_destroy(dev);
 	kfree(steering);
 }
 
@@ -2770,6 +2780,18 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 	if (err)
 		goto out_err;
 
+	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_TC_MISS, 1);
+	if (IS_ERR(maj_prio)) {
+		err = PTR_ERR(maj_prio);
+		goto out_err;
+	}
+
+	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_BR_OFFLOAD, 3);
+	if (IS_ERR(maj_prio)) {
+		err = PTR_ERR(maj_prio);
+		goto out_err;
+	}
+
 	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_SLOW_PATH, 1);
 	if (IS_ERR(maj_prio)) {
 		err = PTR_ERR(maj_prio);
@@ -2942,9 +2964,13 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 	if (err)
 		return err;
 
+	err = mlx5_ft_pool_init(dev);
+	if (err)
+		return err;
+
 	steering = kzalloc(sizeof(*steering), GFP_KERNEL);
 	if (!steering)
-		return -ENOMEM;
+		goto err;
 	steering->dev = dev;
 	dev->priv.steering = steering;
 
@@ -3151,9 +3177,7 @@ void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev,
 EXPORT_SYMBOL(mlx5_modify_header_dealloc);
 
 struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev,
-						     int reformat_type,
-						     size_t size,
-						     void *reformat_data,
+						     struct mlx5_pkt_reformat_params *params,
 						     enum mlx5_flow_namespace_type ns_type)
 {
 	struct mlx5_pkt_reformat *pkt_reformat;
@@ -3169,9 +3193,8 @@ struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev,
 		return ERR_PTR(-ENOMEM);
 
 	pkt_reformat->ns_type = ns_type;
-	pkt_reformat->reformat_type = reformat_type;
-	err = root->cmds->packet_reformat_alloc(root, reformat_type, size,
-						reformat_data, ns_type,
+	pkt_reformat->reformat_type = params->type;
+	err = root->cmds->packet_reformat_alloc(root, params, ns_type,
 						pkt_reformat);
 	if (err) {
 		kfree(pkt_reformat);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index e577a2c424af..7317cdeab661 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -331,6 +331,7 @@ void mlx5_fs_ingress_acls_cleanup(struct mlx5_core_dev *dev);
 
 #define MLX5_CAP_FLOWTABLE_TYPE(mdev, cap, type) (		\
 	(type == FS_FT_NIC_RX) ? MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) :		\
+	(type == FS_FT_NIC_TX) ? MLX5_CAP_FLOWTABLE_NIC_TX(mdev, cap) :		\
 	(type == FS_FT_ESW_EGRESS_ACL) ? MLX5_CAP_ESW_EGRESS_ACL(mdev, cap) :		\
 	(type == FS_FT_ESW_INGRESS_ACL) ? MLX5_CAP_ESW_INGRESS_ACL(mdev, cap) :		\
 	(type == FS_FT_FDB) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) :		\
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
new file mode 100644
index 000000000000..c14590acc772
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2021 Mellanox Technologies. */
+
+#include "fs_ft_pool.h"
+
+/* Firmware currently has 4 pool of 4 sizes that it supports (FT_POOLS),
+ * and a virtual memory region of 16M (MLX5_FT_SIZE), this region is duplicated
+ * for each flow table pool. We can allocate up to 16M of each pool,
+ * and we keep track of how much we used via mlx5_ft_pool_get_avail_sz.
+ * Firmware doesn't report any of this for now.
+ * ESW_POOL is expected to be sorted from large to small and match firmware
+ * pools.
+ */
+#define FT_SIZE (16 * 1024 * 1024)
+static const unsigned int FT_POOLS[] = { 4 * 1024 * 1024,
+					 1 * 1024 * 1024,
+					 64 * 1024,
+					 128,
+					 1 /* size for termination tables */ };
+struct mlx5_ft_pool {
+	int ft_left[ARRAY_SIZE(FT_POOLS)];
+};
+
+int mlx5_ft_pool_init(struct mlx5_core_dev *dev)
+{
+	struct mlx5_ft_pool *ft_pool;
+	int i;
+
+	ft_pool = kzalloc(sizeof(*ft_pool), GFP_KERNEL);
+	if (!ft_pool)
+		return -ENOMEM;
+
+	for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--)
+		ft_pool->ft_left[i] = FT_SIZE / FT_POOLS[i];
+
+	dev->priv.ft_pool = ft_pool;
+	return 0;
+}
+
+void mlx5_ft_pool_destroy(struct mlx5_core_dev *dev)
+{
+	kfree(dev->priv.ft_pool);
+}
+
+int
+mlx5_ft_pool_get_avail_sz(struct mlx5_core_dev *dev, enum fs_flow_table_type table_type,
+			  int desired_size)
+{
+	u32 max_ft_size = 1 << MLX5_CAP_FLOWTABLE_TYPE(dev, log_max_ft_size, table_type);
+	int i, found_i = -1;
+
+	for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) {
+		if (dev->priv.ft_pool->ft_left[i] && FT_POOLS[i] >= desired_size &&
+		    FT_POOLS[i] <= max_ft_size) {
+			found_i = i;
+			if (desired_size != POOL_NEXT_SIZE)
+				break;
+		}
+	}
+
+	if (found_i != -1) {
+		--dev->priv.ft_pool->ft_left[found_i];
+		return FT_POOLS[found_i];
+	}
+
+	return 0;
+}
+
+void
+mlx5_ft_pool_put_sz(struct mlx5_core_dev *dev, int sz)
+{
+	int i;
+
+	if (!sz)
+		return;
+
+	for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) {
+		if (sz == FT_POOLS[i]) {
+			++dev->priv.ft_pool->ft_left[i];
+			return;
+		}
+	}
+
+	WARN_ONCE(1, "Couldn't find size %d in flow table size pool", sz);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
new file mode 100644
index 000000000000..25f4274b372b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021 Mellanox Technologies. */
+
+#ifndef __MLX5_FS_FT_POOL_H__
+#define __MLX5_FS_FT_POOL_H__
+
+#include <linux/mlx5/driver.h>
+#include "fs_core.h"
+
+#define POOL_NEXT_SIZE 0
+
+int mlx5_ft_pool_init(struct mlx5_core_dev *dev);
+void mlx5_ft_pool_destroy(struct mlx5_core_dev *dev);
+
+int
+mlx5_ft_pool_get_avail_sz(struct mlx5_core_dev *dev, enum fs_flow_table_type table_type,
+			  int desired_size);
+void
+mlx5_ft_pool_put_sz(struct mlx5_core_dev *dev, int sz);
+
+#endif /* __MLX5_FS_FT_POOL_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 02558ac2ace6..016d26f809a5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -148,6 +148,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 	if (err)
 		return err;
 
+	if (MLX5_CAP_GEN(dev, hca_cap_2)) {
+		err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL_2);
+		if (err)
+			return err;
+	}
+
 	if (MLX5_CAP_GEN(dev, eth_net_offloads)) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_ETHERNET_OFFLOADS);
 		if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
index 97d96fc38a65..0e487ec57d5c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
@@ -150,6 +150,7 @@ enum mlx5_ptys_rate {
 	MLX5_PTYS_RATE_FDR	= 1 << 4,
 	MLX5_PTYS_RATE_EDR	= 1 << 5,
 	MLX5_PTYS_RATE_HDR	= 1 << 6,
+	MLX5_PTYS_RATE_NDR	= 1 << 7,
 };
 
 static inline int mlx5_ptys_rate_enum_to_int(enum mlx5_ptys_rate rate)
@@ -162,6 +163,7 @@ static inline int mlx5_ptys_rate_enum_to_int(enum mlx5_ptys_rate rate)
 	case MLX5_PTYS_RATE_FDR:   return 14000;
 	case MLX5_PTYS_RATE_EDR:   return 25000;
 	case MLX5_PTYS_RATE_HDR:   return 50000;
+	case MLX5_PTYS_RATE_NDR:   return 100000;
 	default:		   return -1;
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index b8748390335f..5c043c5cc403 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -93,6 +93,64 @@ int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev)
 }
 EXPORT_SYMBOL(mlx5_cmd_destroy_vport_lag);
 
+static int mlx5_lag_netdev_event(struct notifier_block *this,
+				 unsigned long event, void *ptr);
+static void mlx5_do_bond_work(struct work_struct *work);
+
+static void mlx5_ldev_free(struct kref *ref)
+{
+	struct mlx5_lag *ldev = container_of(ref, struct mlx5_lag, ref);
+
+	if (ldev->nb.notifier_call)
+		unregister_netdevice_notifier_net(&init_net, &ldev->nb);
+	mlx5_lag_mp_cleanup(ldev);
+	cancel_delayed_work_sync(&ldev->bond_work);
+	destroy_workqueue(ldev->wq);
+	kfree(ldev);
+}
+
+static void mlx5_ldev_put(struct mlx5_lag *ldev)
+{
+	kref_put(&ldev->ref, mlx5_ldev_free);
+}
+
+static void mlx5_ldev_get(struct mlx5_lag *ldev)
+{
+	kref_get(&ldev->ref);
+}
+
+static struct mlx5_lag *mlx5_lag_dev_alloc(struct mlx5_core_dev *dev)
+{
+	struct mlx5_lag *ldev;
+	int err;
+
+	ldev = kzalloc(sizeof(*ldev), GFP_KERNEL);
+	if (!ldev)
+		return NULL;
+
+	ldev->wq = create_singlethread_workqueue("mlx5_lag");
+	if (!ldev->wq) {
+		kfree(ldev);
+		return NULL;
+	}
+
+	kref_init(&ldev->ref);
+	INIT_DELAYED_WORK(&ldev->bond_work, mlx5_do_bond_work);
+
+	ldev->nb.notifier_call = mlx5_lag_netdev_event;
+	if (register_netdevice_notifier_net(&init_net, &ldev->nb)) {
+		ldev->nb.notifier_call = NULL;
+		mlx5_core_err(dev, "Failed to register LAG netdev notifier\n");
+	}
+
+	err = mlx5_lag_mp_init(ldev);
+	if (err)
+		mlx5_core_err(dev, "Failed to init multipath lag err=%d\n",
+			      err);
+
+	return ldev;
+}
+
 int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
 				struct net_device *ndev)
 {
@@ -118,17 +176,24 @@ static bool __mlx5_lag_is_sriov(struct mlx5_lag *ldev)
 static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
 					   u8 *port1, u8 *port2)
 {
+	bool p1en;
+	bool p2en;
+
+	p1en = tracker->netdev_state[MLX5_LAG_P1].tx_enabled &&
+	       tracker->netdev_state[MLX5_LAG_P1].link_up;
+
+	p2en = tracker->netdev_state[MLX5_LAG_P2].tx_enabled &&
+	       tracker->netdev_state[MLX5_LAG_P2].link_up;
+
 	*port1 = 1;
 	*port2 = 2;
-	if (!tracker->netdev_state[MLX5_LAG_P1].tx_enabled ||
-	    !tracker->netdev_state[MLX5_LAG_P1].link_up) {
-		*port1 = 2;
+	if ((!p1en && !p2en) || (p1en && p2en))
 		return;
-	}
 
-	if (!tracker->netdev_state[MLX5_LAG_P2].tx_enabled ||
-	    !tracker->netdev_state[MLX5_LAG_P2].link_up)
+	if (p1en)
 		*port2 = 1;
+	else
+		*port1 = 2;
 }
 
 void mlx5_modify_lag(struct mlx5_lag *ldev,
@@ -251,6 +316,10 @@ static void mlx5_lag_add_devices(struct mlx5_lag *ldev)
 		if (!ldev->pf[i].dev)
 			continue;
 
+		if (ldev->pf[i].dev->priv.flags &
+		    MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)
+			continue;
+
 		ldev->pf[i].dev->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
 		mlx5_rescan_drivers_locked(ldev->pf[i].dev);
 	}
@@ -269,6 +338,31 @@ static void mlx5_lag_remove_devices(struct mlx5_lag *ldev)
 	}
 }
 
+static void mlx5_disable_lag(struct mlx5_lag *ldev)
+{
+	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
+	struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev;
+	bool roce_lag;
+	int err;
+
+	roce_lag = __mlx5_lag_is_roce(ldev);
+
+	if (roce_lag) {
+		if (!(dev0->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) {
+			dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
+			mlx5_rescan_drivers_locked(dev0);
+		}
+		mlx5_nic_vport_disable_roce(dev1);
+	}
+
+	err = mlx5_deactivate_lag(ldev);
+	if (err)
+		return;
+
+	if (roce_lag)
+		mlx5_lag_add_devices(ldev);
+}
+
 static void mlx5_do_bond(struct mlx5_lag *ldev)
 {
 	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
@@ -280,9 +374,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	if (!mlx5_lag_is_ready(ldev))
 		return;
 
-	spin_lock(&lag_lock);
 	tracker = ldev->tracker;
-	spin_unlock(&lag_lock);
 
 	do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev);
 
@@ -291,8 +383,9 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 			   !mlx5_sriov_is_enabled(dev1);
 
 #ifdef CONFIG_MLX5_ESWITCH
-		roce_lag &= dev0->priv.eswitch->mode == MLX5_ESWITCH_NONE &&
-			    dev1->priv.eswitch->mode == MLX5_ESWITCH_NONE;
+		roce_lag = roce_lag &&
+			   dev0->priv.eswitch->mode == MLX5_ESWITCH_NONE &&
+			   dev1->priv.eswitch->mode == MLX5_ESWITCH_NONE;
 #endif
 
 		if (roce_lag)
@@ -316,20 +409,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	} else if (do_bond && __mlx5_lag_is_active(ldev)) {
 		mlx5_modify_lag(ldev, &tracker);
 	} else if (!do_bond && __mlx5_lag_is_active(ldev)) {
-		roce_lag = __mlx5_lag_is_roce(ldev);
-
-		if (roce_lag) {
-			dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
-			mlx5_rescan_drivers_locked(dev0);
-			mlx5_nic_vport_disable_roce(dev1);
-		}
-
-		err = mlx5_deactivate_lag(ldev);
-		if (err)
-			return;
-
-		if (roce_lag)
-			mlx5_lag_add_devices(ldev);
+		mlx5_disable_lag(ldev);
 	}
 }
 
@@ -481,9 +561,7 @@ static int mlx5_lag_netdev_event(struct notifier_block *this,
 		break;
 	}
 
-	spin_lock(&lag_lock);
 	ldev->tracker = tracker;
-	spin_unlock(&lag_lock);
 
 	if (changed)
 		mlx5_queue_bond_work(ldev, 0);
@@ -491,55 +569,52 @@ static int mlx5_lag_netdev_event(struct notifier_block *this,
 	return NOTIFY_DONE;
 }
 
-static struct mlx5_lag *mlx5_lag_dev_alloc(void)
+static void mlx5_ldev_add_netdev(struct mlx5_lag *ldev,
+				 struct mlx5_core_dev *dev,
+				 struct net_device *netdev)
 {
-	struct mlx5_lag *ldev;
-
-	ldev = kzalloc(sizeof(*ldev), GFP_KERNEL);
-	if (!ldev)
-		return NULL;
-
-	ldev->wq = create_singlethread_workqueue("mlx5_lag");
-	if (!ldev->wq) {
-		kfree(ldev);
-		return NULL;
-	}
+	unsigned int fn = PCI_FUNC(dev->pdev->devfn);
 
-	INIT_DELAYED_WORK(&ldev->bond_work, mlx5_do_bond_work);
+	if (fn >= MLX5_MAX_PORTS)
+		return;
 
-	return ldev;
+	spin_lock(&lag_lock);
+	ldev->pf[fn].netdev = netdev;
+	ldev->tracker.netdev_state[fn].link_up = 0;
+	ldev->tracker.netdev_state[fn].tx_enabled = 0;
+	spin_unlock(&lag_lock);
 }
 
-static void mlx5_lag_dev_free(struct mlx5_lag *ldev)
+static void mlx5_ldev_remove_netdev(struct mlx5_lag *ldev,
+				    struct net_device *netdev)
 {
-	destroy_workqueue(ldev->wq);
-	kfree(ldev);
+	int i;
+
+	spin_lock(&lag_lock);
+	for (i = 0; i < MLX5_MAX_PORTS; i++) {
+		if (ldev->pf[i].netdev == netdev) {
+			ldev->pf[i].netdev = NULL;
+			break;
+		}
+	}
+	spin_unlock(&lag_lock);
 }
 
-static int mlx5_lag_dev_add_pf(struct mlx5_lag *ldev,
-			       struct mlx5_core_dev *dev,
-			       struct net_device *netdev)
+static void mlx5_ldev_add_mdev(struct mlx5_lag *ldev,
+			       struct mlx5_core_dev *dev)
 {
 	unsigned int fn = PCI_FUNC(dev->pdev->devfn);
 
 	if (fn >= MLX5_MAX_PORTS)
-		return -EPERM;
-
-	spin_lock(&lag_lock);
-	ldev->pf[fn].dev    = dev;
-	ldev->pf[fn].netdev = netdev;
-	ldev->tracker.netdev_state[fn].link_up = 0;
-	ldev->tracker.netdev_state[fn].tx_enabled = 0;
+		return;
 
+	ldev->pf[fn].dev = dev;
 	dev->priv.lag = ldev;
-
-	spin_unlock(&lag_lock);
-
-	return fn;
 }
 
-static void mlx5_lag_dev_remove_pf(struct mlx5_lag *ldev,
-				   struct mlx5_core_dev *dev)
+/* Must be called with intf_mutex held */
+static void mlx5_ldev_remove_mdev(struct mlx5_lag *ldev,
+				  struct mlx5_core_dev *dev)
 {
 	int i;
 
@@ -550,19 +625,15 @@ static void mlx5_lag_dev_remove_pf(struct mlx5_lag *ldev,
 	if (i == MLX5_MAX_PORTS)
 		return;
 
-	spin_lock(&lag_lock);
-	memset(&ldev->pf[i], 0, sizeof(*ldev->pf));
-
+	ldev->pf[i].dev = NULL;
 	dev->priv.lag = NULL;
-	spin_unlock(&lag_lock);
 }
 
 /* Must be called with intf_mutex held */
-void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev)
+static void __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev = NULL;
 	struct mlx5_core_dev *tmp_dev;
-	int i, err;
 
 	if (!MLX5_CAP_GEN(dev, vport_group_manager) ||
 	    !MLX5_CAP_GEN(dev, lag_master) ||
@@ -574,67 +645,77 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev)
 		ldev = tmp_dev->priv.lag;
 
 	if (!ldev) {
-		ldev = mlx5_lag_dev_alloc();
+		ldev = mlx5_lag_dev_alloc(dev);
 		if (!ldev) {
 			mlx5_core_err(dev, "Failed to alloc lag dev\n");
 			return;
 		}
+	} else {
+		mlx5_ldev_get(ldev);
 	}
 
-	if (mlx5_lag_dev_add_pf(ldev, dev, netdev) < 0)
-		return;
+	mlx5_ldev_add_mdev(ldev, dev);
 
-	for (i = 0; i < MLX5_MAX_PORTS; i++)
-		if (!ldev->pf[i].dev)
-			break;
+	return;
+}
 
-	if (i >= MLX5_MAX_PORTS)
-		ldev->flags |= MLX5_LAG_FLAG_READY;
+void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev)
+{
+	struct mlx5_lag *ldev;
 
-	if (!ldev->nb.notifier_call) {
-		ldev->nb.notifier_call = mlx5_lag_netdev_event;
-		if (register_netdevice_notifier_net(&init_net, &ldev->nb)) {
-			ldev->nb.notifier_call = NULL;
-			mlx5_core_err(dev, "Failed to register LAG netdev notifier\n");
-		}
-	}
+	ldev = mlx5_lag_dev(dev);
+	if (!ldev)
+		return;
 
-	err = mlx5_lag_mp_init(ldev);
-	if (err)
-		mlx5_core_err(dev, "Failed to init multipath lag err=%d\n",
-			      err);
+	mlx5_dev_list_lock();
+	mlx5_ldev_remove_mdev(ldev, dev);
+	mlx5_dev_list_unlock();
+	mlx5_ldev_put(ldev);
+}
+
+void mlx5_lag_add_mdev(struct mlx5_core_dev *dev)
+{
+	mlx5_dev_list_lock();
+	__mlx5_lag_dev_add_mdev(dev);
+	mlx5_dev_list_unlock();
 }
 
 /* Must be called with intf_mutex held */
-void mlx5_lag_remove(struct mlx5_core_dev *dev)
+void mlx5_lag_remove_netdev(struct mlx5_core_dev *dev,
+			    struct net_device *netdev)
 {
 	struct mlx5_lag *ldev;
-	int i;
 
-	ldev = mlx5_lag_dev_get(dev);
+	ldev = mlx5_lag_dev(dev);
 	if (!ldev)
 		return;
 
 	if (__mlx5_lag_is_active(ldev))
-		mlx5_deactivate_lag(ldev);
-
-	mlx5_lag_dev_remove_pf(ldev, dev);
+		mlx5_disable_lag(ldev);
 
+	mlx5_ldev_remove_netdev(ldev, netdev);
 	ldev->flags &= ~MLX5_LAG_FLAG_READY;
+}
+
+/* Must be called with intf_mutex held */
+void mlx5_lag_add_netdev(struct mlx5_core_dev *dev,
+			 struct net_device *netdev)
+{
+	struct mlx5_lag *ldev;
+	int i;
+
+	ldev = mlx5_lag_dev(dev);
+	if (!ldev)
+		return;
+
+	mlx5_ldev_add_netdev(ldev, dev, netdev);
 
 	for (i = 0; i < MLX5_MAX_PORTS; i++)
-		if (ldev->pf[i].dev)
+		if (!ldev->pf[i].dev)
 			break;
 
-	if (i == MLX5_MAX_PORTS) {
-		if (ldev->nb.notifier_call) {
-			unregister_netdevice_notifier_net(&init_net, &ldev->nb);
-			ldev->nb.notifier_call = NULL;
-		}
-		mlx5_lag_mp_cleanup(ldev);
-		cancel_delayed_work_sync(&ldev->bond_work);
-		mlx5_lag_dev_free(ldev);
-	}
+	if (i >= MLX5_MAX_PORTS)
+		ldev->flags |= MLX5_LAG_FLAG_READY;
 }
 
 bool mlx5_lag_is_roce(struct mlx5_core_dev *dev)
@@ -643,7 +724,7 @@ bool mlx5_lag_is_roce(struct mlx5_core_dev *dev)
 	bool res;
 
 	spin_lock(&lag_lock);
-	ldev = mlx5_lag_dev_get(dev);
+	ldev = mlx5_lag_dev(dev);
 	res  = ldev && __mlx5_lag_is_roce(ldev);
 	spin_unlock(&lag_lock);
 
@@ -657,7 +738,7 @@ bool mlx5_lag_is_active(struct mlx5_core_dev *dev)
 	bool res;
 
 	spin_lock(&lag_lock);
-	ldev = mlx5_lag_dev_get(dev);
+	ldev = mlx5_lag_dev(dev);
 	res  = ldev && __mlx5_lag_is_active(ldev);
 	spin_unlock(&lag_lock);
 
@@ -671,7 +752,7 @@ bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev)
 	bool res;
 
 	spin_lock(&lag_lock);
-	ldev = mlx5_lag_dev_get(dev);
+	ldev = mlx5_lag_dev(dev);
 	res  = ldev && __mlx5_lag_is_sriov(ldev);
 	spin_unlock(&lag_lock);
 
@@ -684,7 +765,7 @@ void mlx5_lag_update(struct mlx5_core_dev *dev)
 	struct mlx5_lag *ldev;
 
 	mlx5_dev_list_lock();
-	ldev = mlx5_lag_dev_get(dev);
+	ldev = mlx5_lag_dev(dev);
 	if (!ldev)
 		goto unlock;
 
@@ -700,7 +781,7 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
 	struct mlx5_lag *ldev;
 
 	spin_lock(&lag_lock);
-	ldev = mlx5_lag_dev_get(dev);
+	ldev = mlx5_lag_dev(dev);
 
 	if (!(ldev && __mlx5_lag_is_roce(ldev)))
 		goto unlock;
@@ -729,7 +810,7 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
 	u8 port = 0;
 
 	spin_lock(&lag_lock);
-	ldev = mlx5_lag_dev_get(dev);
+	ldev = mlx5_lag_dev(dev);
 	if (!(ldev && __mlx5_lag_is_roce(ldev)))
 		goto unlock;
 
@@ -765,7 +846,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 	memset(values, 0, sizeof(*values) * num_counters);
 
 	spin_lock(&lag_lock);
-	ldev = mlx5_lag_dev_get(dev);
+	ldev = mlx5_lag_dev(dev);
 	if (ldev && __mlx5_lag_is_active(ldev)) {
 		num_ports = MLX5_MAX_PORTS;
 		mdev[MLX5_LAG_P1] = ldev->pf[MLX5_LAG_P1].dev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag.h
index 8d8cf2d0bc6d..191392c37558 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.h
@@ -40,6 +40,7 @@ struct lag_tracker {
 struct mlx5_lag {
 	u8                        flags;
 	u8                        v2p_map[MLX5_MAX_PORTS];
+	struct kref               ref;
 	struct lag_func           pf[MLX5_MAX_PORTS];
 	struct lag_tracker        tracker;
 	struct workqueue_struct   *wq;
@@ -49,7 +50,7 @@ struct mlx5_lag {
 };
 
 static inline struct mlx5_lag *
-mlx5_lag_dev_get(struct mlx5_core_dev *dev)
+mlx5_lag_dev(struct mlx5_core_dev *dev)
 {
 	return dev->priv.lag;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
index fd6196b5e163..c4bf8b679541 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
@@ -28,7 +28,7 @@ bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev)
 	struct mlx5_lag *ldev;
 	bool res;
 
-	ldev = mlx5_lag_dev_get(dev);
+	ldev = mlx5_lag_dev(dev);
 	res  = ldev && __mlx5_lag_is_multipath(ldev);
 
 	return res;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
index f607a3858ef5..624cedebb510 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
-/* Copyright (c) 2018 Mellanox Technologies */
+/* Copyright (c) 2018-2021, Mellanox Technologies inc.  All rights reserved. */
 
 #ifndef __LIB_MLX5_EQ_H__
 #define __LIB_MLX5_EQ_H__
@@ -32,6 +32,7 @@ struct mlx5_eq {
 	unsigned int            irqn;
 	u8                      eqn;
 	struct mlx5_rsc_debug   *dbg;
+	struct mlx5_irq         *irq;
 };
 
 struct mlx5_eq_async {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
index 20a4047f2737..97e5845b4cfd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
@@ -6,6 +6,7 @@
 #include <linux/mlx5/fs.h>
 
 #include "lib/fs_chains.h"
+#include "fs_ft_pool.h"
 #include "en/mapping.h"
 #include "fs_core.h"
 #include "en_tc.h"
@@ -13,25 +14,10 @@
 #define chains_lock(chains) ((chains)->lock)
 #define chains_ht(chains) ((chains)->chains_ht)
 #define prios_ht(chains) ((chains)->prios_ht)
-#define ft_pool_left(chains) ((chains)->ft_left)
 #define tc_default_ft(chains) ((chains)->tc_default_ft)
 #define tc_end_ft(chains) ((chains)->tc_end_ft)
 #define ns_to_chains_fs_prio(ns) ((ns) == MLX5_FLOW_NAMESPACE_FDB ? \
 				  FDB_TC_OFFLOAD : MLX5E_TC_PRIO)
-
-/* Firmware currently has 4 pool of 4 sizes that it supports (FT_POOLS),
- * and a virtual memory region of 16M (MLX5_FT_SIZE), this region is duplicated
- * for each flow table pool. We can allocate up to 16M of each pool,
- * and we keep track of how much we used via get_next_avail_sz_from_pool.
- * Firmware doesn't report any of this for now.
- * ESW_POOL is expected to be sorted from large to small and match firmware
- * pools.
- */
-#define FT_SIZE (16 * 1024 * 1024)
-static const unsigned int FT_POOLS[] = { 4 * 1024 * 1024,
-					  1 * 1024 * 1024,
-					  64 * 1024,
-					  128 };
 #define FT_TBL_SZ (64 * 1024)
 
 struct mlx5_fs_chains {
@@ -49,8 +35,6 @@ struct mlx5_fs_chains {
 	enum mlx5_flow_namespace_type ns;
 	u32 group_num;
 	u32 flags;
-
-	int ft_left[ARRAY_SIZE(FT_POOLS)];
 };
 
 struct fs_chain {
@@ -160,54 +144,6 @@ mlx5_chains_set_end_ft(struct mlx5_fs_chains *chains,
 	tc_end_ft(chains) = ft;
 }
 
-#define POOL_NEXT_SIZE 0
-static int
-mlx5_chains_get_avail_sz_from_pool(struct mlx5_fs_chains *chains,
-				   int desired_size)
-{
-	int i, found_i = -1;
-
-	for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) {
-		if (ft_pool_left(chains)[i] && FT_POOLS[i] > desired_size) {
-			found_i = i;
-			if (desired_size != POOL_NEXT_SIZE)
-				break;
-		}
-	}
-
-	if (found_i != -1) {
-		--ft_pool_left(chains)[found_i];
-		return FT_POOLS[found_i];
-	}
-
-	return 0;
-}
-
-static void
-mlx5_chains_put_sz_to_pool(struct mlx5_fs_chains *chains, int sz)
-{
-	int i;
-
-	for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) {
-		if (sz == FT_POOLS[i]) {
-			++ft_pool_left(chains)[i];
-			return;
-		}
-	}
-
-	WARN_ONCE(1, "Couldn't find size %d in flow table size pool", sz);
-}
-
-static void
-mlx5_chains_init_sz_pool(struct mlx5_fs_chains *chains, u32 ft_max)
-{
-	int i;
-
-	for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--)
-		ft_pool_left(chains)[i] =
-			FT_POOLS[i] <= ft_max ? FT_SIZE / FT_POOLS[i] : 0;
-}
-
 static struct mlx5_flow_table *
 mlx5_chains_create_table(struct mlx5_fs_chains *chains,
 			 u32 chain, u32 prio, u32 level)
@@ -221,11 +157,7 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains,
 		ft_attr.flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
 				  MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
 
-	sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ?
-	     mlx5_chains_get_avail_sz_from_pool(chains, FT_TBL_SZ) :
-	     mlx5_chains_get_avail_sz_from_pool(chains, POOL_NEXT_SIZE);
-	if (!sz)
-		return ERR_PTR(-ENOSPC);
+	sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ? FT_TBL_SZ : POOL_NEXT_SIZE;
 	ft_attr.max_fte = sz;
 
 	/* We use tc_default_ft(chains) as the table's next_ft till
@@ -266,21 +198,12 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains,
 	if (IS_ERR(ft)) {
 		mlx5_core_warn(chains->dev, "Failed to create chains table err %d (chain: %d, prio: %d, level: %d, size: %d)\n",
 			       (int)PTR_ERR(ft), chain, prio, level, sz);
-		mlx5_chains_put_sz_to_pool(chains, sz);
 		return ft;
 	}
 
 	return ft;
 }
 
-static void
-mlx5_chains_destroy_table(struct mlx5_fs_chains *chains,
-			  struct mlx5_flow_table *ft)
-{
-	mlx5_chains_put_sz_to_pool(chains, ft->max_fte);
-	mlx5_destroy_flow_table(ft);
-}
-
 static int
 create_chain_restore(struct fs_chain *chain)
 {
@@ -336,9 +259,10 @@ create_chain_restore(struct fs_chain *chain)
 	MLX5_SET(set_action_in, modact, field,
 		 mlx5e_tc_attr_to_reg_mappings[chain_to_reg].mfield);
 	MLX5_SET(set_action_in, modact, offset,
-		 mlx5e_tc_attr_to_reg_mappings[chain_to_reg].moffset * 8);
+		 mlx5e_tc_attr_to_reg_mappings[chain_to_reg].moffset);
 	MLX5_SET(set_action_in, modact, length,
-		 mlx5e_tc_attr_to_reg_mappings[chain_to_reg].mlen * 8);
+		 mlx5e_tc_attr_to_reg_mappings[chain_to_reg].mlen == 32 ?
+		 0 : mlx5e_tc_attr_to_reg_mappings[chain_to_reg].mlen);
 	MLX5_SET(set_action_in, modact, data, chain->id);
 	mod_hdr = mlx5_modify_header_alloc(chains->dev, chains->ns,
 					   1, modact);
@@ -636,7 +560,7 @@ err_insert:
 err_miss_rule:
 	mlx5_destroy_flow_group(miss_group);
 err_group:
-	mlx5_chains_destroy_table(chains, ft);
+	mlx5_destroy_flow_table(ft);
 err_create:
 err_alloc:
 	kvfree(prio_s);
@@ -659,7 +583,7 @@ mlx5_chains_destroy_prio(struct mlx5_fs_chains *chains,
 			       prio_params);
 	mlx5_del_flow_rules(prio->miss_rule);
 	mlx5_destroy_flow_group(prio->miss_group);
-	mlx5_chains_destroy_table(chains, prio->ft);
+	mlx5_destroy_flow_table(prio->ft);
 	mlx5_chains_put_chain(chain);
 	kvfree(prio);
 }
@@ -784,7 +708,7 @@ void
 mlx5_chains_destroy_global_table(struct mlx5_fs_chains *chains,
 				 struct mlx5_flow_table *ft)
 {
-	mlx5_chains_destroy_table(chains, ft);
+	mlx5_destroy_flow_table(ft);
 }
 
 static struct mlx5_fs_chains *
@@ -816,8 +740,6 @@ mlx5_chains_init(struct mlx5_core_dev *dev, struct mlx5_chains_attr *attr)
 		       mlx5_chains_get_chain_range(chains_priv),
 		       mlx5_chains_get_prio_range(chains_priv));
 
-	mlx5_chains_init_sz_pool(chains_priv, attr->max_ft_sz);
-
 	err = rhashtable_init(&chains_ht(chains_priv), &chain_params);
 	if (err)
 		goto init_chains_ht_err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/sf.h
new file mode 100644
index 000000000000..84e5683861be
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sf.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021 Mellanox Technologies Ltd */
+
+#ifndef __LIB_MLX5_SF_H__
+#define __LIB_MLX5_SF_H__
+
+#include <linux/mlx5/driver.h>
+
+static inline u16 mlx5_sf_start_function_id(const struct mlx5_core_dev *dev)
+{
+	return MLX5_CAP_GEN(dev, sf_base_id);
+}
+
+#ifdef CONFIG_MLX5_SF
+
+static inline bool mlx5_sf_supported(const struct mlx5_core_dev *dev)
+{
+	return MLX5_CAP_GEN(dev, sf);
+}
+
+static inline u16 mlx5_sf_max_functions(const struct mlx5_core_dev *dev)
+{
+	if (!mlx5_sf_supported(dev))
+		return 0;
+	if (MLX5_CAP_GEN(dev, max_num_sf))
+		return MLX5_CAP_GEN(dev, max_num_sf);
+	else
+		return 1 << MLX5_CAP_GEN(dev, log_max_sf);
+}
+
+#else
+
+static inline bool mlx5_sf_supported(const struct mlx5_core_dev *dev)
+{
+	return false;
+}
+
+static inline u16 mlx5_sf_max_functions(const struct mlx5_core_dev *dev)
+{
+	return 0;
+}
+
+#endif
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 0d0f63a27aba..eb1b316560a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -76,6 +76,7 @@
 #include "sf/vhca_event.h"
 #include "sf/dev/dev.h"
 #include "sf/sf.h"
+#include "mlx5_irq.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver");
@@ -1185,6 +1186,7 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 	}
 
 	mlx5_sf_dev_table_create(dev);
+	mlx5_lag_add_mdev(dev);
 
 	return 0;
 
@@ -1220,6 +1222,7 @@ err_irq_table:
 
 static void mlx5_unload(struct mlx5_core_dev *dev)
 {
+	mlx5_lag_remove_mdev(dev);
 	mlx5_sf_dev_table_destroy(dev);
 	mlx5_sriov_detach(dev);
 	mlx5_ec_cleanup(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index a22b706eebd3..343807ac2036 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -164,27 +164,10 @@ int mlx5_query_mcam_reg(struct mlx5_core_dev *dev, u32 *mcap, u8 feature_group,
 int mlx5_query_qcam_reg(struct mlx5_core_dev *mdev, u32 *qcam,
 			u8 feature_group, u8 access_reg_group);
 
-void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev);
-void mlx5_lag_remove(struct mlx5_core_dev *dev);
-
-int mlx5_irq_table_init(struct mlx5_core_dev *dev);
-void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev);
-int mlx5_irq_table_create(struct mlx5_core_dev *dev);
-void mlx5_irq_table_destroy(struct mlx5_core_dev *dev);
-int mlx5_irq_attach_nb(struct mlx5_irq_table *irq_table, int vecidx,
-		       struct notifier_block *nb);
-int mlx5_irq_detach_nb(struct mlx5_irq_table *irq_table, int vecidx,
-		       struct notifier_block *nb);
-
-int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int devfn,
-			    int msix_vec_count);
-int mlx5_get_default_msix_vec_count(struct mlx5_core_dev *dev, int num_vfs);
-
-struct cpumask *
-mlx5_irq_get_affinity_mask(struct mlx5_irq_table *irq_table, int vecidx);
-struct cpu_rmap *mlx5_irq_get_rmap(struct mlx5_irq_table *table);
-int mlx5_irq_get_num_comp(struct mlx5_irq_table *table);
-struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev);
+void mlx5_lag_add_netdev(struct mlx5_core_dev *dev, struct net_device *netdev);
+void mlx5_lag_remove_netdev(struct mlx5_core_dev *dev, struct net_device *netdev);
+void mlx5_lag_add_mdev(struct mlx5_core_dev *dev);
+void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev);
 
 int mlx5_events_init(struct mlx5_core_dev *dev);
 void mlx5_events_cleanup(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
new file mode 100644
index 000000000000..abd024173c42
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021 Mellanox Technologies. */
+
+#ifndef __MLX5_IRQ_H__
+#define __MLX5_IRQ_H__
+
+#include <linux/mlx5/driver.h>
+
+#define MLX5_COMP_EQS_PER_SF 8
+
+#define MLX5_IRQ_EQ_CTRL (0)
+
+struct mlx5_irq;
+
+int mlx5_irq_table_init(struct mlx5_core_dev *dev);
+void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev);
+int mlx5_irq_table_create(struct mlx5_core_dev *dev);
+void mlx5_irq_table_destroy(struct mlx5_core_dev *dev);
+int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table);
+int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table);
+struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev);
+
+int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int devfn,
+			    int msix_vec_count);
+int mlx5_get_default_msix_vec_count(struct mlx5_core_dev *dev, int num_vfs);
+
+struct mlx5_irq *mlx5_irq_request(struct mlx5_core_dev *dev, u16 vecidx,
+				  struct cpumask *affinity);
+void mlx5_irq_release(struct mlx5_irq *irq);
+int mlx5_irq_attach_nb(struct mlx5_irq *irq, struct notifier_block *nb);
+int mlx5_irq_detach_nb(struct mlx5_irq *irq, struct notifier_block *nb);
+struct cpumask *mlx5_irq_get_affinity_mask(struct mlx5_irq *irq);
+int mlx5_irq_get_index(struct mlx5_irq *irq);
+
+#endif /* __MLX5_IRQ_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index c3373fb1cd7f..27de8da8edf7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -6,60 +6,52 @@
 #include <linux/module.h>
 #include <linux/mlx5/driver.h>
 #include "mlx5_core.h"
+#include "mlx5_irq.h"
+#include "lib/sf.h"
 #ifdef CONFIG_RFS_ACCEL
 #include <linux/cpu_rmap.h>
 #endif
 
 #define MLX5_MAX_IRQ_NAME (32)
+/* max irq_index is 255. three chars */
+#define MLX5_MAX_IRQ_IDX_CHARS (3)
+
+#define MLX5_SFS_PER_CTRL_IRQ 64
+#define MLX5_IRQ_CTRL_SF_MAX 8
+/* min num of vectores for SFs to be enabled */
+#define MLX5_IRQ_VEC_COMP_BASE_SF 2
+
+#define MLX5_EQ_SHARE_IRQ_MAX_COMP (8)
+#define MLX5_EQ_SHARE_IRQ_MAX_CTRL (UINT_MAX)
+#define MLX5_EQ_SHARE_IRQ_MIN_COMP (1)
+#define MLX5_EQ_SHARE_IRQ_MIN_CTRL (4)
+#define MLX5_EQ_REFS_PER_IRQ (2)
 
 struct mlx5_irq {
+	u32 index;
 	struct atomic_notifier_head nh;
 	cpumask_var_t mask;
 	char name[MLX5_MAX_IRQ_NAME];
+	struct kref kref;
+	int irqn;
+	struct mlx5_irq_pool *pool;
 };
 
-struct mlx5_irq_table {
-	struct mlx5_irq *irq;
-	int nvec;
-#ifdef CONFIG_RFS_ACCEL
-	struct cpu_rmap *rmap;
-#endif
+struct mlx5_irq_pool {
+	char name[MLX5_MAX_IRQ_NAME - MLX5_MAX_IRQ_IDX_CHARS];
+	struct xa_limit xa_num_irqs;
+	struct mutex lock; /* sync IRQs creations */
+	struct xarray irqs;
+	u32 max_threshold;
+	u32 min_threshold;
+	struct mlx5_core_dev *dev;
 };
 
-int mlx5_irq_table_init(struct mlx5_core_dev *dev)
-{
-	struct mlx5_irq_table *irq_table;
-
-	if (mlx5_core_is_sf(dev))
-		return 0;
-
-	irq_table = kvzalloc(sizeof(*irq_table), GFP_KERNEL);
-	if (!irq_table)
-		return -ENOMEM;
-
-	dev->priv.irq_table = irq_table;
-	return 0;
-}
-
-void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev)
-{
-	if (mlx5_core_is_sf(dev))
-		return;
-
-	kvfree(dev->priv.irq_table);
-}
-
-int mlx5_irq_get_num_comp(struct mlx5_irq_table *table)
-{
-	return table->nvec - MLX5_IRQ_VEC_COMP_BASE;
-}
-
-static struct mlx5_irq *mlx5_irq_get(struct mlx5_core_dev *dev, int vecidx)
-{
-	struct mlx5_irq_table *irq_table = dev->priv.irq_table;
-
-	return &irq_table->irq[vecidx];
-}
+struct mlx5_irq_table {
+	struct mlx5_irq_pool *pf_pool;
+	struct mlx5_irq_pool *sf_ctrl_pool;
+	struct mlx5_irq_pool *sf_comp_pool;
+};
 
 /**
  * mlx5_get_default_msix_vec_count - Get the default number of MSI-X vectors
@@ -146,34 +138,46 @@ out:
 	return ret;
 }
 
-int mlx5_irq_attach_nb(struct mlx5_irq_table *irq_table, int vecidx,
-		       struct notifier_block *nb)
+static void irq_release(struct kref *kref)
 {
-	struct mlx5_irq *irq;
+	struct mlx5_irq *irq = container_of(kref, struct mlx5_irq, kref);
+	struct mlx5_irq_pool *pool = irq->pool;
 
-	irq = &irq_table->irq[vecidx];
-	return atomic_notifier_chain_register(&irq->nh, nb);
+	xa_erase(&pool->irqs, irq->index);
+	/* free_irq requires that affinity and rmap will be cleared
+	 * before calling it. This is why there is asymmetry with set_rmap
+	 * which should be called after alloc_irq but before request_irq.
+	 */
+	irq_set_affinity_hint(irq->irqn, NULL);
+	free_cpumask_var(irq->mask);
+	free_irq(irq->irqn, &irq->nh);
+	kfree(irq);
 }
 
-int mlx5_irq_detach_nb(struct mlx5_irq_table *irq_table, int vecidx,
-		       struct notifier_block *nb)
+static void irq_put(struct mlx5_irq *irq)
 {
-	struct mlx5_irq *irq;
+	struct mlx5_irq_pool *pool = irq->pool;
 
-	irq = &irq_table->irq[vecidx];
-	return atomic_notifier_chain_unregister(&irq->nh, nb);
+	mutex_lock(&pool->lock);
+	kref_put(&irq->kref, irq_release);
+	mutex_unlock(&pool->lock);
 }
 
-static irqreturn_t mlx5_irq_int_handler(int irq, void *nh)
+static irqreturn_t irq_int_handler(int irq, void *nh)
 {
 	atomic_notifier_call_chain(nh, 0, NULL);
 	return IRQ_HANDLED;
 }
 
+static void irq_sf_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx)
+{
+	snprintf(name, MLX5_MAX_IRQ_NAME, "%s%d", pool->name, vecidx);
+}
+
 static void irq_set_name(char *name, int vecidx)
 {
 	if (vecidx == 0) {
-		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_async");
+		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_async%d", vecidx);
 		return;
 	}
 
@@ -181,251 +185,431 @@ static void irq_set_name(char *name, int vecidx)
 		 vecidx - MLX5_IRQ_VEC_COMP_BASE);
 }
 
-static int request_irqs(struct mlx5_core_dev *dev, int nvec)
+static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i)
 {
+	struct mlx5_core_dev *dev = pool->dev;
 	char name[MLX5_MAX_IRQ_NAME];
+	struct mlx5_irq *irq;
 	int err;
-	int i;
-
-	for (i = 0; i < nvec; i++) {
-		struct mlx5_irq *irq = mlx5_irq_get(dev, i);
-		int irqn = pci_irq_vector(dev->pdev, i);
 
+	irq = kzalloc(sizeof(*irq), GFP_KERNEL);
+	if (!irq)
+		return ERR_PTR(-ENOMEM);
+	irq->irqn = pci_irq_vector(dev->pdev, i);
+	if (!pool->name[0])
 		irq_set_name(name, i);
-		ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh);
-		snprintf(irq->name, MLX5_MAX_IRQ_NAME,
-			 "%s@pci:%s", name, pci_name(dev->pdev));
-		err = request_irq(irqn, mlx5_irq_int_handler, 0, irq->name,
-				  &irq->nh);
-		if (err) {
-			mlx5_core_err(dev, "Failed to request irq\n");
-			goto err_request_irq;
-		}
+	else
+		irq_sf_set_name(pool, name, i);
+	ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh);
+	snprintf(irq->name, MLX5_MAX_IRQ_NAME,
+		 "%s@pci:%s", name, pci_name(dev->pdev));
+	err = request_irq(irq->irqn, irq_int_handler, 0, irq->name,
+			  &irq->nh);
+	if (err) {
+		mlx5_core_err(dev, "Failed to request irq. err = %d\n", err);
+		goto err_req_irq;
 	}
-	return 0;
+	if (!zalloc_cpumask_var(&irq->mask, GFP_KERNEL)) {
+		mlx5_core_warn(dev, "zalloc_cpumask_var failed\n");
+		err = -ENOMEM;
+		goto err_cpumask;
+	}
+	kref_init(&irq->kref);
+	irq->index = i;
+	err = xa_err(xa_store(&pool->irqs, irq->index, irq, GFP_KERNEL));
+	if (err) {
+		mlx5_core_err(dev, "Failed to alloc xa entry for irq(%u). err = %d\n",
+			      irq->index, err);
+		goto err_xa;
+	}
+	irq->pool = pool;
+	return irq;
+err_xa:
+	free_cpumask_var(irq->mask);
+err_cpumask:
+	free_irq(irq->irqn, &irq->nh);
+err_req_irq:
+	kfree(irq);
+	return ERR_PTR(err);
+}
 
-err_request_irq:
-	while (i--) {
-		struct mlx5_irq *irq = mlx5_irq_get(dev, i);
-		int irqn = pci_irq_vector(dev->pdev, i);
+int mlx5_irq_attach_nb(struct mlx5_irq *irq, struct notifier_block *nb)
+{
+	int err;
 
-		free_irq(irqn, &irq->nh);
-	}
-	return  err;
+	err = kref_get_unless_zero(&irq->kref);
+	if (WARN_ON_ONCE(!err))
+		/* Something very bad happens here, we are enabling EQ
+		 * on non-existing IRQ.
+		 */
+		return -ENOENT;
+	err = atomic_notifier_chain_register(&irq->nh, nb);
+	if (err)
+		irq_put(irq);
+	return err;
 }
 
-static void irq_clear_rmap(struct mlx5_core_dev *dev)
+int mlx5_irq_detach_nb(struct mlx5_irq *irq, struct notifier_block *nb)
 {
-#ifdef CONFIG_RFS_ACCEL
-	struct mlx5_irq_table *irq_table = dev->priv.irq_table;
+	irq_put(irq);
+	return atomic_notifier_chain_unregister(&irq->nh, nb);
+}
 
-	free_irq_cpu_rmap(irq_table->rmap);
-#endif
+struct cpumask *mlx5_irq_get_affinity_mask(struct mlx5_irq *irq)
+{
+	return irq->mask;
 }
 
-static int irq_set_rmap(struct mlx5_core_dev *mdev)
+int mlx5_irq_get_index(struct mlx5_irq *irq)
 {
-	int err = 0;
-#ifdef CONFIG_RFS_ACCEL
-	struct mlx5_irq_table *irq_table = mdev->priv.irq_table;
-	int num_affinity_vec;
-	int vecidx;
+	return irq->index;
+}
 
-	num_affinity_vec = mlx5_irq_get_num_comp(irq_table);
-	irq_table->rmap = alloc_irq_cpu_rmap(num_affinity_vec);
-	if (!irq_table->rmap) {
-		err = -ENOMEM;
-		mlx5_core_err(mdev, "Failed to allocate cpu_rmap. err %d", err);
-		goto err_out;
+/* irq_pool API */
+
+/* creating an irq from irq_pool */
+static struct mlx5_irq *irq_pool_create_irq(struct mlx5_irq_pool *pool,
+					    struct cpumask *affinity)
+{
+	struct mlx5_irq *irq;
+	u32 irq_index;
+	int err;
+
+	err = xa_alloc(&pool->irqs, &irq_index, NULL, pool->xa_num_irqs,
+		       GFP_KERNEL);
+	if (err)
+		return ERR_PTR(err);
+	irq = irq_request(pool, irq_index);
+	if (IS_ERR(irq))
+		return irq;
+	cpumask_copy(irq->mask, affinity);
+	irq_set_affinity_hint(irq->irqn, irq->mask);
+	return irq;
+}
+
+/* looking for the irq with the smallest refcount and the same affinity */
+static struct mlx5_irq *irq_pool_find_least_loaded(struct mlx5_irq_pool *pool,
+						   struct cpumask *affinity)
+{
+	int start = pool->xa_num_irqs.min;
+	int end = pool->xa_num_irqs.max;
+	struct mlx5_irq *irq = NULL;
+	struct mlx5_irq *iter;
+	unsigned long index;
+
+	lockdep_assert_held(&pool->lock);
+	xa_for_each_range(&pool->irqs, index, iter, start, end) {
+		if (!cpumask_equal(iter->mask, affinity))
+			continue;
+		if (kref_read(&iter->kref) < pool->min_threshold)
+			return iter;
+		if (!irq || kref_read(&iter->kref) <
+		    kref_read(&irq->kref))
+			irq = iter;
 	}
+	return irq;
+}
+
+/* requesting an irq from a given pool according to given affinity */
+static struct mlx5_irq *irq_pool_request_affinity(struct mlx5_irq_pool *pool,
+						  struct cpumask *affinity)
+{
+	struct mlx5_irq *least_loaded_irq, *new_irq;
 
-	vecidx = MLX5_IRQ_VEC_COMP_BASE;
-	for (; vecidx < irq_table->nvec; vecidx++) {
-		err = irq_cpu_rmap_add(irq_table->rmap,
-				       pci_irq_vector(mdev->pdev, vecidx));
-		if (err) {
-			mlx5_core_err(mdev, "irq_cpu_rmap_add failed. err %d",
-				      err);
-			goto err_irq_cpu_rmap_add;
+	mutex_lock(&pool->lock);
+	least_loaded_irq = irq_pool_find_least_loaded(pool, affinity);
+	if (least_loaded_irq &&
+	    kref_read(&least_loaded_irq->kref) < pool->min_threshold)
+		goto out;
+	new_irq = irq_pool_create_irq(pool, affinity);
+	if (IS_ERR(new_irq)) {
+		if (!least_loaded_irq) {
+			mlx5_core_err(pool->dev, "Didn't find IRQ for cpu = %u\n",
+				      cpumask_first(affinity));
+			mutex_unlock(&pool->lock);
+			return new_irq;
 		}
+		/* We failed to create a new IRQ for the requested affinity,
+		 * sharing existing IRQ.
+		 */
+		goto out;
 	}
-	return 0;
+	least_loaded_irq = new_irq;
+	goto unlock;
+out:
+	kref_get(&least_loaded_irq->kref);
+	if (kref_read(&least_loaded_irq->kref) > pool->max_threshold)
+		mlx5_core_dbg(pool->dev, "IRQ %u overloaded, pool_name: %s, %u EQs on this irq\n",
+			      least_loaded_irq->irqn, pool->name,
+			      kref_read(&least_loaded_irq->kref) / MLX5_EQ_REFS_PER_IRQ);
+unlock:
+	mutex_unlock(&pool->lock);
+	return least_loaded_irq;
+}
 
-err_irq_cpu_rmap_add:
-	irq_clear_rmap(mdev);
-err_out:
-#endif
-	return err;
+/* requesting an irq from a given pool according to given index */
+static struct mlx5_irq *
+irq_pool_request_vector(struct mlx5_irq_pool *pool, int vecidx,
+			struct cpumask *affinity)
+{
+	struct mlx5_irq *irq;
+
+	mutex_lock(&pool->lock);
+	irq = xa_load(&pool->irqs, vecidx);
+	if (irq) {
+		kref_get(&irq->kref);
+		goto unlock;
+	}
+	irq = irq_request(pool, vecidx);
+	if (IS_ERR(irq) || !affinity)
+		goto unlock;
+	cpumask_copy(irq->mask, affinity);
+	irq_set_affinity_hint(irq->irqn, irq->mask);
+unlock:
+	mutex_unlock(&pool->lock);
+	return irq;
 }
 
-/* Completion IRQ vectors */
+static struct mlx5_irq_pool *find_sf_irq_pool(struct mlx5_irq_table *irq_table,
+					      int i, struct cpumask *affinity)
+{
+	if (cpumask_empty(affinity) && i == MLX5_IRQ_EQ_CTRL)
+		return irq_table->sf_ctrl_pool;
+	return irq_table->sf_comp_pool;
+}
 
-static int set_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
+/**
+ * mlx5_irq_release - release an IRQ back to the system.
+ * @irq: irq to be released.
+ */
+void mlx5_irq_release(struct mlx5_irq *irq)
 {
-	int vecidx = MLX5_IRQ_VEC_COMP_BASE + i;
+	synchronize_irq(irq->irqn);
+	irq_put(irq);
+}
+
+/**
+ * mlx5_irq_request - request an IRQ for mlx5 device.
+ * @dev: mlx5 device that requesting the IRQ.
+ * @vecidx: vector index of the IRQ. This argument is ignore if affinity is
+ * provided.
+ * @affinity: cpumask requested for this IRQ.
+ *
+ * This function returns a pointer to IRQ, or ERR_PTR in case of error.
+ */
+struct mlx5_irq *mlx5_irq_request(struct mlx5_core_dev *dev, u16 vecidx,
+				  struct cpumask *affinity)
+{
+	struct mlx5_irq_table *irq_table = mlx5_irq_table_get(dev);
+	struct mlx5_irq_pool *pool;
 	struct mlx5_irq *irq;
-	int irqn;
 
-	irq = mlx5_irq_get(mdev, vecidx);
-	irqn = pci_irq_vector(mdev->pdev, vecidx);
-	if (!zalloc_cpumask_var(&irq->mask, GFP_KERNEL)) {
-		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
-		return -ENOMEM;
+	if (mlx5_core_is_sf(dev)) {
+		pool = find_sf_irq_pool(irq_table, vecidx, affinity);
+		if (!pool)
+			/* we don't have IRQs for SFs, using the PF IRQs */
+			goto pf_irq;
+		if (cpumask_empty(affinity) && !strcmp(pool->name, "mlx5_sf_comp"))
+			/* In case an SF user request IRQ with vecidx */
+			irq = irq_pool_request_vector(pool, vecidx, NULL);
+		else
+			irq = irq_pool_request_affinity(pool, affinity);
+		goto out;
 	}
+pf_irq:
+	pool = irq_table->pf_pool;
+	irq = irq_pool_request_vector(pool, vecidx, affinity);
+out:
+	if (IS_ERR(irq))
+		return irq;
+	mlx5_core_dbg(dev, "irq %u mapped to cpu %*pbl, %u EQs on this irq\n",
+		      irq->irqn, cpumask_pr_args(affinity),
+		      kref_read(&irq->kref) / MLX5_EQ_REFS_PER_IRQ);
+	return irq;
+}
 
-	cpumask_set_cpu(cpumask_local_spread(i, mdev->priv.numa_node),
-			irq->mask);
-	if (IS_ENABLED(CONFIG_SMP) &&
-	    irq_set_affinity_hint(irqn, irq->mask))
-		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x",
-			       irqn);
-
-	return 0;
+static struct mlx5_irq_pool *
+irq_pool_alloc(struct mlx5_core_dev *dev, int start, int size, char *name,
+	       u32 min_threshold, u32 max_threshold)
+{
+	struct mlx5_irq_pool *pool = kvzalloc(sizeof(*pool), GFP_KERNEL);
+
+	if (!pool)
+		return ERR_PTR(-ENOMEM);
+	pool->dev = dev;
+	xa_init_flags(&pool->irqs, XA_FLAGS_ALLOC);
+	pool->xa_num_irqs.min = start;
+	pool->xa_num_irqs.max = start + size - 1;
+	if (name)
+		snprintf(pool->name, MLX5_MAX_IRQ_NAME - MLX5_MAX_IRQ_IDX_CHARS,
+			 name);
+	pool->min_threshold = min_threshold * MLX5_EQ_REFS_PER_IRQ;
+	pool->max_threshold = max_threshold * MLX5_EQ_REFS_PER_IRQ;
+	mutex_init(&pool->lock);
+	mlx5_core_dbg(dev, "pool->name = %s, pool->size = %d, pool->start = %d",
+		      name, size, start);
+	return pool;
 }
 
-static void clear_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
+static void irq_pool_free(struct mlx5_irq_pool *pool)
 {
-	int vecidx = MLX5_IRQ_VEC_COMP_BASE + i;
 	struct mlx5_irq *irq;
-	int irqn;
+	unsigned long index;
 
-	irq = mlx5_irq_get(mdev, vecidx);
-	irqn = pci_irq_vector(mdev->pdev, vecidx);
-	irq_set_affinity_hint(irqn, NULL);
-	free_cpumask_var(irq->mask);
+	xa_for_each(&pool->irqs, index, irq)
+		irq_release(&irq->kref);
+	xa_destroy(&pool->irqs);
+	kvfree(pool);
 }
 
-static int set_comp_irq_affinity_hints(struct mlx5_core_dev *mdev)
+static int irq_pools_init(struct mlx5_core_dev *dev, int sf_vec, int pf_vec)
 {
-	int nvec = mlx5_irq_get_num_comp(mdev->priv.irq_table);
+	struct mlx5_irq_table *table = dev->priv.irq_table;
+	int num_sf_ctrl_by_msix;
+	int num_sf_ctrl_by_sfs;
+	int num_sf_ctrl;
 	int err;
-	int i;
 
-	for (i = 0; i < nvec; i++) {
-		err = set_comp_irq_affinity_hint(mdev, i);
-		if (err)
-			goto err_out;
+	/* init pf_pool */
+	table->pf_pool = irq_pool_alloc(dev, 0, pf_vec, NULL,
+					MLX5_EQ_SHARE_IRQ_MIN_COMP,
+					MLX5_EQ_SHARE_IRQ_MAX_COMP);
+	if (IS_ERR(table->pf_pool))
+		return PTR_ERR(table->pf_pool);
+	if (!mlx5_sf_max_functions(dev))
+		return 0;
+	if (sf_vec < MLX5_IRQ_VEC_COMP_BASE_SF) {
+		mlx5_core_err(dev, "Not enught IRQs for SFs. SF may run at lower performance\n");
+		return 0;
 	}
 
+	/* init sf_ctrl_pool */
+	num_sf_ctrl_by_msix = DIV_ROUND_UP(sf_vec, MLX5_COMP_EQS_PER_SF);
+	num_sf_ctrl_by_sfs = DIV_ROUND_UP(mlx5_sf_max_functions(dev),
+					  MLX5_SFS_PER_CTRL_IRQ);
+	num_sf_ctrl = min_t(int, num_sf_ctrl_by_msix, num_sf_ctrl_by_sfs);
+	num_sf_ctrl = min_t(int, MLX5_IRQ_CTRL_SF_MAX, num_sf_ctrl);
+	table->sf_ctrl_pool = irq_pool_alloc(dev, pf_vec, num_sf_ctrl,
+					     "mlx5_sf_ctrl",
+					     MLX5_EQ_SHARE_IRQ_MIN_CTRL,
+					     MLX5_EQ_SHARE_IRQ_MAX_CTRL);
+	if (IS_ERR(table->sf_ctrl_pool)) {
+		err = PTR_ERR(table->sf_ctrl_pool);
+		goto err_pf;
+	}
+	/* init sf_comp_pool */
+	table->sf_comp_pool = irq_pool_alloc(dev, pf_vec + num_sf_ctrl,
+					     sf_vec - num_sf_ctrl, "mlx5_sf_comp",
+					     MLX5_EQ_SHARE_IRQ_MIN_COMP,
+					     MLX5_EQ_SHARE_IRQ_MAX_COMP);
+	if (IS_ERR(table->sf_comp_pool)) {
+		err = PTR_ERR(table->sf_comp_pool);
+		goto err_sf_ctrl;
+	}
 	return 0;
-
-err_out:
-	for (i--; i >= 0; i--)
-		clear_comp_irq_affinity_hint(mdev, i);
-
+err_sf_ctrl:
+	irq_pool_free(table->sf_ctrl_pool);
+err_pf:
+	irq_pool_free(table->pf_pool);
 	return err;
 }
 
-static void clear_comp_irqs_affinity_hints(struct mlx5_core_dev *mdev)
+static void irq_pools_destroy(struct mlx5_irq_table *table)
 {
-	int nvec = mlx5_irq_get_num_comp(mdev->priv.irq_table);
-	int i;
-
-	for (i = 0; i < nvec; i++)
-		clear_comp_irq_affinity_hint(mdev, i);
+	if (table->sf_ctrl_pool) {
+		irq_pool_free(table->sf_comp_pool);
+		irq_pool_free(table->sf_ctrl_pool);
+	}
+	irq_pool_free(table->pf_pool);
 }
 
-struct cpumask *
-mlx5_irq_get_affinity_mask(struct mlx5_irq_table *irq_table, int vecidx)
+/* irq_table API */
+
+int mlx5_irq_table_init(struct mlx5_core_dev *dev)
 {
-	return irq_table->irq[vecidx].mask;
+	struct mlx5_irq_table *irq_table;
+
+	if (mlx5_core_is_sf(dev))
+		return 0;
+
+	irq_table = kvzalloc(sizeof(*irq_table), GFP_KERNEL);
+	if (!irq_table)
+		return -ENOMEM;
+
+	dev->priv.irq_table = irq_table;
+	return 0;
 }
 
-#ifdef CONFIG_RFS_ACCEL
-struct cpu_rmap *mlx5_irq_get_rmap(struct mlx5_irq_table *irq_table)
+void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev)
 {
-	return irq_table->rmap;
+	if (mlx5_core_is_sf(dev))
+		return;
+
+	kvfree(dev->priv.irq_table);
 }
-#endif
 
-static void unrequest_irqs(struct mlx5_core_dev *dev)
+int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table)
 {
-	struct mlx5_irq_table *table = dev->priv.irq_table;
-	int i;
-
-	for (i = 0; i < table->nvec; i++)
-		free_irq(pci_irq_vector(dev->pdev, i),
-			 &mlx5_irq_get(dev, i)->nh);
+	return table->pf_pool->xa_num_irqs.max - table->pf_pool->xa_num_irqs.min;
 }
 
 int mlx5_irq_table_create(struct mlx5_core_dev *dev)
 {
-	struct mlx5_priv *priv = &dev->priv;
-	struct mlx5_irq_table *table = priv->irq_table;
 	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
 		      MLX5_CAP_GEN(dev, max_num_eqs) :
 		      1 << MLX5_CAP_GEN(dev, log_max_eq);
-	int nvec;
+	int total_vec;
+	int pf_vec;
 	int err;
 
 	if (mlx5_core_is_sf(dev))
 		return 0;
 
-	nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
-	       MLX5_IRQ_VEC_COMP_BASE;
-	nvec = min_t(int, nvec, num_eqs);
-	if (nvec <= MLX5_IRQ_VEC_COMP_BASE)
-		return -ENOMEM;
-
-	table->irq = kcalloc(nvec, sizeof(*table->irq), GFP_KERNEL);
-	if (!table->irq)
+	pf_vec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
+		 MLX5_IRQ_VEC_COMP_BASE;
+	pf_vec = min_t(int, pf_vec, num_eqs);
+	if (pf_vec <= MLX5_IRQ_VEC_COMP_BASE)
 		return -ENOMEM;
 
-	nvec = pci_alloc_irq_vectors(dev->pdev, MLX5_IRQ_VEC_COMP_BASE + 1,
-				     nvec, PCI_IRQ_MSIX);
-	if (nvec < 0) {
-		err = nvec;
-		goto err_free_irq;
-	}
-
-	table->nvec = nvec;
+	total_vec = pf_vec;
+	if (mlx5_sf_max_functions(dev))
+		total_vec += MLX5_IRQ_CTRL_SF_MAX +
+			MLX5_COMP_EQS_PER_SF * mlx5_sf_max_functions(dev);
 
-	err = irq_set_rmap(dev);
-	if (err)
-		goto err_set_rmap;
+	total_vec = pci_alloc_irq_vectors(dev->pdev, MLX5_IRQ_VEC_COMP_BASE + 1,
+					  total_vec, PCI_IRQ_MSIX);
+	if (total_vec < 0)
+		return total_vec;
+	pf_vec = min(pf_vec, total_vec);
 
-	err = request_irqs(dev, nvec);
+	err = irq_pools_init(dev, total_vec - pf_vec, pf_vec);
 	if (err)
-		goto err_request_irqs;
-
-	err = set_comp_irq_affinity_hints(dev);
-	if (err) {
-		mlx5_core_err(dev, "Failed to alloc affinity hint cpumask\n");
-		goto err_set_affinity;
-	}
-
-	return 0;
+		pci_free_irq_vectors(dev->pdev);
 
-err_set_affinity:
-	unrequest_irqs(dev);
-err_request_irqs:
-	irq_clear_rmap(dev);
-err_set_rmap:
-	pci_free_irq_vectors(dev->pdev);
-err_free_irq:
-	kfree(table->irq);
 	return err;
 }
 
 void mlx5_irq_table_destroy(struct mlx5_core_dev *dev)
 {
 	struct mlx5_irq_table *table = dev->priv.irq_table;
-	int i;
 
 	if (mlx5_core_is_sf(dev))
 		return;
 
-	/* free_irq requires that affinity and rmap will be cleared
-	 * before calling it. This is why there is asymmetry with set_rmap
-	 * which should be called after alloc_irq but before request_irq.
+	/* There are cases where IRQs still will be in used when we reaching
+	 * to here. Hence, making sure all the irqs are realeased.
 	 */
-	irq_clear_rmap(dev);
-	clear_comp_irqs_affinity_hints(dev);
-	for (i = 0; i < table->nvec; i++)
-		free_irq(pci_irq_vector(dev->pdev, i),
-			 &mlx5_irq_get(dev, i)->nh);
+	irq_pools_destroy(table);
 	pci_free_irq_vectors(dev->pdev);
-	kfree(table->irq);
+}
+
+int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table)
+{
+	if (table->sf_comp_pool)
+		return table->sf_comp_pool->xa_num_irqs.max -
+			table->sf_comp_pool->xa_num_irqs.min + 1;
+	else
+		return mlx5_irq_table_get_num_comp(table);
 }
 
 struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
index ef5f892aafad..500c71fb6f6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
@@ -6,7 +6,6 @@
 #include "sf.h"
 #include "mlx5_ifc_vhca_event.h"
 #include "ecpf.h"
-#include "vhca_event.h"
 #include "mlx5_core.h"
 #include "eswitch.h"
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
index 0b6aea1e6a94..81ce13b19ee8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
@@ -5,42 +5,7 @@
 #define __MLX5_SF_H__
 
 #include <linux/mlx5/driver.h>
-
-static inline u16 mlx5_sf_start_function_id(const struct mlx5_core_dev *dev)
-{
-	return MLX5_CAP_GEN(dev, sf_base_id);
-}
-
-#ifdef CONFIG_MLX5_SF
-
-static inline bool mlx5_sf_supported(const struct mlx5_core_dev *dev)
-{
-	return MLX5_CAP_GEN(dev, sf);
-}
-
-static inline u16 mlx5_sf_max_functions(const struct mlx5_core_dev *dev)
-{
-	if (!mlx5_sf_supported(dev))
-		return 0;
-	if (MLX5_CAP_GEN(dev, max_num_sf))
-		return MLX5_CAP_GEN(dev, max_num_sf);
-	else
-		return 1 << MLX5_CAP_GEN(dev, log_max_sf);
-}
-
-#else
-
-static inline bool mlx5_sf_supported(const struct mlx5_core_dev *dev)
-{
-	return false;
-}
-
-static inline u16 mlx5_sf_max_functions(const struct mlx5_core_dev *dev)
-{
-	return 0;
-}
-
-#endif
+#include "lib/sf.h"
 
 #ifdef CONFIG_MLX5_SF_MANAGER
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index 2338989d4403..e8185b69ac6c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -34,6 +34,7 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/vport.h>
 #include "mlx5_core.h"
+#include "mlx5_irq.h"
 #include "eswitch.h"
 
 static int sriov_restore_guids(struct mlx5_core_dev *dev, int vf)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
index 949879cf2092..de68c0ec2143 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2019 Mellanox Technologies. */
 
 #include "dr_types.h"
+#include "dr_ste.h"
 
 enum dr_action_domain {
 	DR_ACTION_DOMAIN_NIC_INGRESS,
@@ -14,7 +15,8 @@ enum dr_action_domain {
 enum dr_action_valid_state {
 	DR_ACTION_STATE_ERR,
 	DR_ACTION_STATE_NO_ACTION,
-	DR_ACTION_STATE_REFORMAT,
+	DR_ACTION_STATE_ENCAP,
+	DR_ACTION_STATE_DECAP,
 	DR_ACTION_STATE_MODIFY_HDR,
 	DR_ACTION_STATE_MODIFY_VLAN,
 	DR_ACTION_STATE_NON_TERM,
@@ -31,26 +33,42 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_TAG]		= DR_ACTION_STATE_NON_TERM,
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_NON_TERM,
-			[DR_ACTION_TYP_TNL_L2_TO_L2]	= DR_ACTION_STATE_REFORMAT,
-			[DR_ACTION_TYP_TNL_L3_TO_L2]	= DR_ACTION_STATE_REFORMAT,
+			[DR_ACTION_TYP_TNL_L2_TO_L2]	= DR_ACTION_STATE_DECAP,
+			[DR_ACTION_TYP_TNL_L3_TO_L2]	= DR_ACTION_STATE_DECAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
 			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
 		},
-		[DR_ACTION_STATE_REFORMAT] = {
+		[DR_ACTION_STATE_DECAP] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_QP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
-			[DR_ACTION_TYP_TAG]		= DR_ACTION_STATE_REFORMAT,
-			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_REFORMAT,
+			[DR_ACTION_TYP_TAG]		= DR_ACTION_STATE_DECAP,
+			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_DECAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
 			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
 		},
+		[DR_ACTION_STATE_ENCAP] = {
+			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_QP]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_TAG]		= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_ENCAP,
+		},
 		[DR_ACTION_STATE_MODIFY_HDR] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_QP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_TAG]		= DR_ACTION_STATE_MODIFY_HDR,
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_MODIFY_HDR,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 		},
 		[DR_ACTION_STATE_MODIFY_VLAN] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
@@ -60,6 +78,9 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_MODIFY_VLAN,
 			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 		},
 		[DR_ACTION_STATE_NON_TERM] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
@@ -67,8 +88,11 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_TAG]		= DR_ACTION_STATE_NON_TERM,
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_NON_TERM,
-			[DR_ACTION_TYP_TNL_L2_TO_L2]	= DR_ACTION_STATE_REFORMAT,
-			[DR_ACTION_TYP_TNL_L3_TO_L2]	= DR_ACTION_STATE_REFORMAT,
+			[DR_ACTION_TYP_TNL_L2_TO_L2]	= DR_ACTION_STATE_DECAP,
+			[DR_ACTION_TYP_TNL_L3_TO_L2]	= DR_ACTION_STATE_DECAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
 			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
 		},
@@ -81,22 +105,24 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_NON_TERM,
-			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_REFORMAT,
-			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_REFORMAT,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
 			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
 		},
-		[DR_ACTION_STATE_REFORMAT] = {
+		[DR_ACTION_STATE_ENCAP] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
-			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_REFORMAT,
+			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_ENCAP,
 		},
 		[DR_ACTION_STATE_MODIFY_HDR] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_MODIFY_HDR,
-			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_REFORMAT,
-			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_REFORMAT,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
 		},
 		[DR_ACTION_STATE_MODIFY_VLAN] = {
@@ -104,15 +130,17 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_MODIFY_VLAN,
 			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
-			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_REFORMAT,
-			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_REFORMAT,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 		},
 		[DR_ACTION_STATE_NON_TERM] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_NON_TERM,
-			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_REFORMAT,
-			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_REFORMAT,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
 			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
 		},
@@ -125,25 +153,41 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_NON_TERM,
-			[DR_ACTION_TYP_TNL_L2_TO_L2]	= DR_ACTION_STATE_REFORMAT,
-			[DR_ACTION_TYP_TNL_L3_TO_L2]	= DR_ACTION_STATE_REFORMAT,
+			[DR_ACTION_TYP_TNL_L2_TO_L2]	= DR_ACTION_STATE_DECAP,
+			[DR_ACTION_TYP_TNL_L3_TO_L2]	= DR_ACTION_STATE_DECAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
 			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
 		},
-		[DR_ACTION_STATE_REFORMAT] = {
+		[DR_ACTION_STATE_DECAP] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
-			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_REFORMAT,
+			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_DECAP,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
 			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
+		},
+		[DR_ACTION_STATE_ENCAP] = {
+			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_QP]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_ENCAP,
 		},
 		[DR_ACTION_STATE_MODIFY_HDR] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_MODIFY_HDR,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 		},
 		[DR_ACTION_STATE_MODIFY_VLAN] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
@@ -152,13 +196,19 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_MODIFY_VLAN,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 		},
 		[DR_ACTION_STATE_NON_TERM] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_NON_TERM,
-			[DR_ACTION_TYP_TNL_L2_TO_L2]	= DR_ACTION_STATE_REFORMAT,
-			[DR_ACTION_TYP_TNL_L3_TO_L2]	= DR_ACTION_STATE_REFORMAT,
+			[DR_ACTION_TYP_TNL_L2_TO_L2]	= DR_ACTION_STATE_DECAP,
+			[DR_ACTION_TYP_TNL_L3_TO_L2]	= DR_ACTION_STATE_DECAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
 			[DR_ACTION_TYP_POP_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
@@ -173,23 +223,25 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_NON_TERM,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
-			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_REFORMAT,
-			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_REFORMAT,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
 		},
-		[DR_ACTION_STATE_REFORMAT] = {
+		[DR_ACTION_STATE_ENCAP] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
-			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_REFORMAT,
+			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
 		},
 		[DR_ACTION_STATE_MODIFY_HDR] = {
 			[DR_ACTION_TYP_DROP]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_MODIFY_HDR,
-			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_REFORMAT,
-			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_REFORMAT,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
 		},
@@ -198,8 +250,9 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_MODIFY_VLAN,
-			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_REFORMAT,
-			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_REFORMAT,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
 		},
 		[DR_ACTION_STATE_NON_TERM] = {
@@ -207,8 +260,9 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX]
 			[DR_ACTION_TYP_FT]		= DR_ACTION_STATE_TERM,
 			[DR_ACTION_TYP_CTR]		= DR_ACTION_STATE_NON_TERM,
 			[DR_ACTION_TYP_MODIFY_HDR]	= DR_ACTION_STATE_MODIFY_HDR,
-			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_REFORMAT,
-			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_REFORMAT,
+			[DR_ACTION_TYP_L2_TO_TNL_L2]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_L2_TO_TNL_L3]	= DR_ACTION_STATE_ENCAP,
+			[DR_ACTION_TYP_INSERT_HDR]	= DR_ACTION_STATE_ENCAP,
 			[DR_ACTION_TYP_PUSH_VLAN]	= DR_ACTION_STATE_MODIFY_VLAN,
 			[DR_ACTION_TYP_VPORT]		= DR_ACTION_STATE_TERM,
 		},
@@ -235,6 +289,9 @@ dr_action_reformat_to_action_type(enum mlx5dr_action_reformat_type reformat_type
 	case DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3:
 		*action_type = DR_ACTION_TYP_L2_TO_TNL_L3;
 		break;
+	case DR_ACTION_REFORMAT_TYP_INSERT_HDR:
+		*action_type = DR_ACTION_TYP_INSERT_HDR;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -454,8 +511,13 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
 			break;
 		case DR_ACTION_TYP_L2_TO_TNL_L2:
 		case DR_ACTION_TYP_L2_TO_TNL_L3:
-			attr.reformat_size = action->reformat->reformat_size;
-			attr.reformat_id = action->reformat->reformat_id;
+			if (rx_rule &&
+			    !(dmn->ste_ctx->actions_caps & DR_STE_CTX_ACTION_CAP_RX_ENCAP)) {
+				mlx5dr_info(dmn, "Device doesn't support Encap on RX\n");
+				goto out_invalid_arg;
+			}
+			attr.reformat.size = action->reformat->size;
+			attr.reformat.id = action->reformat->id;
 			break;
 		case DR_ACTION_TYP_VPORT:
 			attr.hit_gvmi = action->vport->caps->vhca_gvmi;
@@ -481,6 +543,12 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
 
 			attr.vlans.headers[attr.vlans.count++] = action->push_vlan->vlan_hdr;
 			break;
+		case DR_ACTION_TYP_INSERT_HDR:
+			attr.reformat.size = action->reformat->size;
+			attr.reformat.id = action->reformat->id;
+			attr.reformat.param_0 = action->reformat->param_0;
+			attr.reformat.param_1 = action->reformat->param_1;
+			break;
 		default:
 			goto out_invalid_arg;
 		}
@@ -543,6 +611,7 @@ static unsigned int action_size[DR_ACTION_TYP_MAX] = {
 	[DR_ACTION_TYP_MODIFY_HDR]   = sizeof(struct mlx5dr_action_rewrite),
 	[DR_ACTION_TYP_VPORT]        = sizeof(struct mlx5dr_action_vport),
 	[DR_ACTION_TYP_PUSH_VLAN]    = sizeof(struct mlx5dr_action_push_vlan),
+	[DR_ACTION_TYP_INSERT_HDR]   = sizeof(struct mlx5dr_action_reformat),
 };
 
 static struct mlx5dr_action *
@@ -651,7 +720,7 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn,
 			if (reformat_action) {
 				reformat_req = true;
 				hw_dests[i].vport.reformat_id =
-					reformat_action->reformat->reformat_id;
+					reformat_action->reformat->id;
 				ref_actions[num_of_ref++] = reformat_action;
 				hw_dests[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
 			}
@@ -758,11 +827,15 @@ struct mlx5dr_action *mlx5dr_action_create_tag(u32 tag_value)
 static int
 dr_action_verify_reformat_params(enum mlx5dr_action_type reformat_type,
 				 struct mlx5dr_domain *dmn,
+				 u8 reformat_param_0,
+				 u8 reformat_param_1,
 				 size_t data_sz,
 				 void *data)
 {
-	if ((!data && data_sz) || (data && !data_sz) || reformat_type >
-		DR_ACTION_TYP_L2_TO_TNL_L3) {
+	if ((!data && data_sz) || (data && !data_sz) ||
+	    ((reformat_param_0 || reformat_param_1) &&
+	     reformat_type != DR_ACTION_TYP_INSERT_HDR) ||
+	    reformat_type > DR_ACTION_TYP_INSERT_HDR) {
 		mlx5dr_dbg(dmn, "Invalid reformat parameter!\n");
 		goto out_err;
 	}
@@ -794,6 +867,7 @@ out_err:
 
 static int
 dr_action_create_reformat_action(struct mlx5dr_domain *dmn,
+				 u8 reformat_param_0, u8 reformat_param_1,
 				 size_t data_sz, void *data,
 				 struct mlx5dr_action *action)
 {
@@ -811,13 +885,14 @@ dr_action_create_reformat_action(struct mlx5dr_domain *dmn,
 		else
 			rt = MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL;
 
-		ret = mlx5dr_cmd_create_reformat_ctx(dmn->mdev, rt, data_sz, data,
+		ret = mlx5dr_cmd_create_reformat_ctx(dmn->mdev, rt, 0, 0,
+						     data_sz, data,
 						     &reformat_id);
 		if (ret)
 			return ret;
 
-		action->reformat->reformat_id = reformat_id;
-		action->reformat->reformat_size = data_sz;
+		action->reformat->id = reformat_id;
+		action->reformat->size = data_sz;
 		return 0;
 	}
 	case DR_ACTION_TYP_TNL_L2_TO_L2:
@@ -859,6 +934,23 @@ dr_action_create_reformat_action(struct mlx5dr_domain *dmn,
 		}
 		return 0;
 	}
+	case DR_ACTION_TYP_INSERT_HDR:
+	{
+		ret = mlx5dr_cmd_create_reformat_ctx(dmn->mdev,
+						     MLX5_REFORMAT_TYPE_INSERT_HDR,
+						     reformat_param_0,
+						     reformat_param_1,
+						     data_sz, data,
+						     &reformat_id);
+		if (ret)
+			return ret;
+
+		action->reformat->id = reformat_id;
+		action->reformat->size = data_sz;
+		action->reformat->param_0 = reformat_param_0;
+		action->reformat->param_1 = reformat_param_1;
+		return 0;
+	}
 	default:
 		mlx5dr_info(dmn, "Reformat type is not supported %d\n", action->action_type);
 		return -EINVAL;
@@ -896,6 +988,8 @@ struct mlx5dr_action *mlx5dr_action_create_push_vlan(struct mlx5dr_domain *dmn,
 struct mlx5dr_action *
 mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn,
 				     enum mlx5dr_action_reformat_type reformat_type,
+				     u8 reformat_param_0,
+				     u8 reformat_param_1,
 				     size_t data_sz,
 				     void *data)
 {
@@ -912,7 +1006,9 @@ mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn,
 		goto dec_ref;
 	}
 
-	ret = dr_action_verify_reformat_params(action_type, dmn, data_sz, data);
+	ret = dr_action_verify_reformat_params(action_type, dmn,
+					       reformat_param_0, reformat_param_1,
+					       data_sz, data);
 	if (ret)
 		goto dec_ref;
 
@@ -923,6 +1019,8 @@ mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn,
 	action->reformat->dmn = dmn;
 
 	ret = dr_action_create_reformat_action(dmn,
+					       reformat_param_0,
+					       reformat_param_1,
 					       data_sz,
 					       data,
 					       action);
@@ -1516,8 +1614,9 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action)
 		break;
 	case DR_ACTION_TYP_L2_TO_TNL_L2:
 	case DR_ACTION_TYP_L2_TO_TNL_L3:
+	case DR_ACTION_TYP_INSERT_HDR:
 		mlx5dr_cmd_destroy_reformat_ctx((action->reformat->dmn)->mdev,
-						action->reformat->reformat_id);
+						action->reformat->id);
 		refcount_dec(&action->reformat->dmn->refcount);
 		break;
 	case DR_ACTION_TYP_MODIFY_HDR:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
index 5970cb8fc0c0..6314f50efbd4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
@@ -460,6 +460,8 @@ int mlx5dr_cmd_destroy_flow_table(struct mlx5_core_dev *mdev,
 
 int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev,
 				   enum mlx5_reformat_ctx_type rt,
+				   u8 reformat_param_0,
+				   u8 reformat_param_1,
 				   size_t reformat_size,
 				   void *reformat_data,
 				   u32 *reformat_id)
@@ -486,8 +488,11 @@ int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev,
 	pdata = MLX5_ADDR_OF(packet_reformat_context_in, prctx, reformat_data);
 
 	MLX5_SET(packet_reformat_context_in, prctx, reformat_type, rt);
+	MLX5_SET(packet_reformat_context_in, prctx, reformat_param_0, reformat_param_0);
+	MLX5_SET(packet_reformat_context_in, prctx, reformat_param_1, reformat_param_1);
 	MLX5_SET(packet_reformat_context_in, prctx, reformat_data_size, reformat_size);
-	memcpy(pdata, reformat_data, reformat_size);
+	if (reformat_data && reformat_size)
+		memcpy(pdata, reformat_data, reformat_size);
 
 	err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
 	if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h
index 992b591bf0c5..12a8bbbf944b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h
@@ -156,6 +156,7 @@ struct mlx5dr_ste_ctx {
 	u16  (*get_byte_mask)(u8 *hw_ste_p);
 
 	/* Actions */
+	u32 actions_caps;
 	void (*set_actions_rx)(struct mlx5dr_domain *dmn,
 			       u8 *action_type_set,
 			       u8 *hw_ste_arr,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c
index 0757a4e8540e..f1950e4968da 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c
@@ -437,8 +437,8 @@ dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn,
 						attr->gvmi);
 
 		dr_ste_v0_set_tx_encap(last_ste,
-				       attr->reformat_id,
-				       attr->reformat_size,
+				       attr->reformat.id,
+				       attr->reformat.size,
 				       action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3]);
 		/* Whenever prio_tag_required enabled, we can be sure that the
 		 * previous table (ACL) already push vlan to our packet,
@@ -1893,6 +1893,7 @@ struct mlx5dr_ste_ctx ste_ctx_v0 = {
 	.get_byte_mask			= &dr_ste_v0_get_byte_mask,
 
 	/* Actions */
+	.actions_caps			= DR_STE_CTX_ACTION_CAP_NONE,
 	.set_actions_rx			= &dr_ste_v0_set_actions_rx,
 	.set_actions_tx			= &dr_ste_v0_set_actions_tx,
 	.modify_field_arr_sz		= ARRAY_SIZE(dr_ste_v0_action_modify_field_arr),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
index 7466f016375c..4aaca8eb7597 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c
@@ -116,6 +116,8 @@ enum {
 	DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_3	= 0x4f,
 	DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_0		= 0x5e,
 	DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_1		= 0x5f,
+	DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_0		= 0x6f,
+	DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_1		= 0x70,
 	DR_STE_V1_ACTION_MDFY_FLD_METADATA_2_CQE	= 0x7b,
 	DR_STE_V1_ACTION_MDFY_FLD_GNRL_PURPOSE		= 0x7c,
 	DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2		= 0x8c,
@@ -246,6 +248,12 @@ static const struct mlx5dr_ste_action_modify_field dr_ste_v1_action_modify_field
 	[MLX5_ACTION_IN_FIELD_OUT_FIRST_VID] = {
 		.hw_field = DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_2, .start = 0, .end = 15,
 	},
+	[MLX5_ACTION_IN_FIELD_OUT_EMD_31_0] = {
+		.hw_field = DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_1, .start = 0, .end = 31,
+	},
+	[MLX5_ACTION_IN_FIELD_OUT_EMD_47_32] = {
+		.hw_field = DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_0, .start = 0, .end = 15,
+	},
 };
 
 static void dr_ste_v1_set_entry_type(u8 *hw_ste_p, u8 entry_type)
@@ -361,8 +369,8 @@ static void dr_ste_v1_set_reparse(u8 *hw_ste_p)
 	MLX5_SET(ste_match_bwc_v1, hw_ste_p, reparse, 1);
 }
 
-static void dr_ste_v1_set_tx_encap(u8 *hw_ste_p, u8 *d_action,
-				   u32 reformat_id, int size)
+static void dr_ste_v1_set_encap(u8 *hw_ste_p, u8 *d_action,
+				u32 reformat_id, int size)
 {
 	MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, action_id,
 		 DR_STE_V1_ACTION_ID_INSERT_POINTER);
@@ -374,6 +382,26 @@ static void dr_ste_v1_set_tx_encap(u8 *hw_ste_p, u8 *d_action,
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
+static void dr_ste_v1_set_insert_hdr(u8 *hw_ste_p, u8 *d_action,
+				     u32 reformat_id,
+				     u8 anchor, u8 offset,
+				     int size)
+{
+	MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action,
+		 action_id, DR_STE_V1_ACTION_ID_INSERT_POINTER);
+	MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, start_anchor, anchor);
+
+	/* The hardware expects here size and offset in words (2 byte) */
+	MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, size, size / 2);
+	MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, start_offset, offset / 2);
+
+	MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, pointer, reformat_id);
+	MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, attributes,
+		 DR_STE_V1_ACTION_INSERT_PTR_ATTR_NONE);
+
+	dr_ste_v1_set_reparse(hw_ste_p);
+}
+
 static void dr_ste_v1_set_tx_push_vlan(u8 *hw_ste_p, u8 *d_action,
 				       u32 vlan_hdr)
 {
@@ -401,11 +429,11 @@ static void dr_ste_v1_set_rx_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num)
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
-static void dr_ste_v1_set_tx_encap_l3(u8 *hw_ste_p,
-				      u8 *frst_s_action,
-				      u8 *scnd_d_action,
-				      u32 reformat_id,
-				      int size)
+static void dr_ste_v1_set_encap_l3(u8 *hw_ste_p,
+				   u8 *frst_s_action,
+				   u8 *scnd_d_action,
+				   u32 reformat_id,
+				   int size)
 {
 	/* Remove L2 headers */
 	MLX5_SET(ste_single_action_remove_header_v1, frst_s_action, action_id,
@@ -519,9 +547,9 @@ static void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 			allow_encap = true;
 		}
-		dr_ste_v1_set_tx_encap(last_ste, action,
-				       attr->reformat_id,
-				       attr->reformat_size);
+		dr_ste_v1_set_encap(last_ste, action,
+				    attr->reformat.id,
+				    attr->reformat.size);
 		action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 		action += DR_STE_ACTION_DOUBLE_SZ;
 	} else if (action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3]) {
@@ -532,12 +560,25 @@ static void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn,
 		action_sz = DR_STE_ACTION_TRIPLE_SZ;
 		d_action = action + DR_STE_ACTION_SINGLE_SZ;
 
-		dr_ste_v1_set_tx_encap_l3(last_ste,
-					  action, d_action,
-					  attr->reformat_id,
-					  attr->reformat_size);
+		dr_ste_v1_set_encap_l3(last_ste,
+				       action, d_action,
+				       attr->reformat.id,
+				       attr->reformat.size);
 		action_sz -= DR_STE_ACTION_TRIPLE_SZ;
 		action += DR_STE_ACTION_TRIPLE_SZ;
+	} else if (action_type_set[DR_ACTION_TYP_INSERT_HDR]) {
+		if (!allow_encap || action_sz < DR_STE_ACTION_DOUBLE_SZ) {
+			dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi);
+			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
+			action_sz = DR_STE_ACTION_TRIPLE_SZ;
+		}
+		dr_ste_v1_set_insert_hdr(last_ste, action,
+					 attr->reformat.id,
+					 attr->reformat.param_0,
+					 attr->reformat.param_1,
+					 attr->reformat.size);
+		action_sz -= DR_STE_ACTION_DOUBLE_SZ;
+		action += DR_STE_ACTION_DOUBLE_SZ;
 	}
 
 	dr_ste_v1_set_hit_gvmi(last_ste, attr->hit_gvmi);
@@ -616,7 +657,9 @@ static void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 	}
 
 	if (action_type_set[DR_ACTION_TYP_CTR]) {
-		/* Counter action set after decap to exclude decaped header */
+		/* Counter action set after decap and before insert_hdr
+		 * to exclude decaped / encaped header respectively.
+		 */
 		if (!allow_ctr) {
 			dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi);
 			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
@@ -627,6 +670,52 @@ static void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn,
 		dr_ste_v1_set_counter_id(last_ste, attr->ctr_id);
 	}
 
+	if (action_type_set[DR_ACTION_TYP_L2_TO_TNL_L2]) {
+		if (action_sz < DR_STE_ACTION_DOUBLE_SZ) {
+			dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi);
+			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
+			action_sz = DR_STE_ACTION_TRIPLE_SZ;
+		}
+		dr_ste_v1_set_encap(last_ste, action,
+				    attr->reformat.id,
+				    attr->reformat.size);
+		action_sz -= DR_STE_ACTION_DOUBLE_SZ;
+		action += DR_STE_ACTION_DOUBLE_SZ;
+		allow_modify_hdr = false;
+	} else if (action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3]) {
+		u8 *d_action;
+
+		if (action_sz < DR_STE_ACTION_TRIPLE_SZ) {
+			dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi);
+			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
+			action_sz = DR_STE_ACTION_TRIPLE_SZ;
+		}
+
+		d_action = action + DR_STE_ACTION_SINGLE_SZ;
+
+		dr_ste_v1_set_encap_l3(last_ste,
+				       action, d_action,
+				       attr->reformat.id,
+				       attr->reformat.size);
+		action_sz -= DR_STE_ACTION_TRIPLE_SZ;
+		allow_modify_hdr = false;
+	} else if (action_type_set[DR_ACTION_TYP_INSERT_HDR]) {
+		/* Modify header, decap, and encap must use different STEs */
+		if (!allow_modify_hdr || action_sz < DR_STE_ACTION_DOUBLE_SZ) {
+			dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi);
+			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
+			action_sz = DR_STE_ACTION_TRIPLE_SZ;
+		}
+		dr_ste_v1_set_insert_hdr(last_ste, action,
+					 attr->reformat.id,
+					 attr->reformat.param_0,
+					 attr->reformat.param_1,
+					 attr->reformat.size);
+		action_sz -= DR_STE_ACTION_DOUBLE_SZ;
+		action += DR_STE_ACTION_DOUBLE_SZ;
+		allow_modify_hdr = false;
+	}
+
 	dr_ste_v1_set_hit_gvmi(last_ste, attr->hit_gvmi);
 	dr_ste_v1_set_hit_addr(last_ste, attr->final_icm_addr, 1);
 }
@@ -1871,6 +1960,7 @@ struct mlx5dr_ste_ctx ste_ctx_v1 = {
 	.set_byte_mask			= &dr_ste_v1_set_byte_mask,
 	.get_byte_mask			= &dr_ste_v1_get_byte_mask,
 	/* Actions */
+	.actions_caps			= DR_STE_CTX_ACTION_CAP_RX_ENCAP,
 	.set_actions_rx			= &dr_ste_v1_set_actions_rx,
 	.set_actions_tx			= &dr_ste_v1_set_actions_tx,
 	.modify_field_arr_sz		= ARRAY_SIZE(dr_ste_v1_action_modify_field_arr),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
index 67460c42a99b..60b8c04e165e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
@@ -89,6 +89,11 @@ enum {
 	DR_STE_SIZE_REDUCED = DR_STE_SIZE - DR_STE_SIZE_MASK,
 };
 
+enum mlx5dr_ste_ctx_action_cap {
+	DR_STE_CTX_ACTION_CAP_NONE = 0,
+	DR_STE_CTX_ACTION_CAP_RX_ENCAP = 1 << 0,
+};
+
 enum {
 	DR_MODIFY_ACTION_SIZE = 8,
 };
@@ -118,6 +123,7 @@ enum mlx5dr_action_type {
 	DR_ACTION_TYP_VPORT,
 	DR_ACTION_TYP_POP_VLAN,
 	DR_ACTION_TYP_PUSH_VLAN,
+	DR_ACTION_TYP_INSERT_HDR,
 	DR_ACTION_TYP_MAX,
 };
 
@@ -261,8 +267,12 @@ struct mlx5dr_ste_actions_attr {
 	u32	ctr_id;
 	u16	gvmi;
 	u16	hit_gvmi;
-	u32	reformat_id;
-	u32	reformat_size;
+	struct {
+		u32	id;
+		u32	size;
+		u8	param_0;
+		u8	param_1;
+	} reformat;
 	struct {
 		int	count;
 		u32	headers[MLX5DR_MAX_VLANS];
@@ -903,8 +913,10 @@ struct mlx5dr_action_rewrite {
 
 struct mlx5dr_action_reformat {
 	struct mlx5dr_domain *dmn;
-	u32 reformat_id;
-	u32 reformat_size;
+	u32 id;
+	u32 size;
+	u8 param_0;
+	u8 param_1;
 };
 
 struct mlx5dr_action_dest_tbl {
@@ -1142,6 +1154,8 @@ int mlx5dr_cmd_query_flow_table(struct mlx5_core_dev *dev,
 				struct mlx5dr_cmd_query_flow_table_details *output);
 int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev,
 				   enum mlx5_reformat_ctx_type rt,
+				   u8 reformat_param_0,
+				   u8 reformat_param_1,
 				   size_t reformat_size,
 				   void *reformat_data,
 				   u32 *reformat_id);
@@ -1252,7 +1266,6 @@ struct mlx5dr_send_ring {
 	u32 tx_head;
 	void *buf;
 	u32 buf_size;
-	struct ib_wc wc[MAX_SEND_CQE];
 	u8 sync_buff[MIN_READ_SYNC];
 	struct mlx5dr_mr *sync_mr;
 	spinlock_t lock; /* Protect the data path of the send ring */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
index 96c39a17d026..00b4c753cae2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
@@ -62,7 +62,7 @@ static int set_miss_action(struct mlx5_flow_root_namespace *ns,
 
 static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns,
 					 struct mlx5_flow_table *ft,
-					 unsigned int log_size,
+					 unsigned int size,
 					 struct mlx5_flow_table *next_ft)
 {
 	struct mlx5dr_table *tbl;
@@ -71,7 +71,7 @@ static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns,
 
 	if (mlx5_dr_is_fw_table(ft->flags))
 		return mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft,
-								    log_size,
+								    size,
 								    next_ft);
 	flags = ft->flags;
 	/* turn off encap/decap if not supported for sw-str by fw */
@@ -97,6 +97,8 @@ static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns,
 		}
 	}
 
+	ft->max_fte = INT_MAX;
+
 	return 0;
 }
 
@@ -287,7 +289,8 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 			DR_ACTION_REFORMAT_TYP_TNL_L2_TO_L2;
 
 		tmp_action = mlx5dr_action_create_packet_reformat(domain,
-								  decap_type, 0,
+								  decap_type,
+								  0, 0, 0,
 								  NULL);
 		if (!tmp_action) {
 			err = -ENOMEM;
@@ -520,9 +523,7 @@ out_err:
 }
 
 static int mlx5_cmd_dr_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
-					     int reformat_type,
-					     size_t size,
-					     void *reformat_data,
+					     struct mlx5_pkt_reformat_params *params,
 					     enum mlx5_flow_namespace_type namespace,
 					     struct mlx5_pkt_reformat *pkt_reformat)
 {
@@ -530,7 +531,7 @@ static int mlx5_cmd_dr_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns
 	struct mlx5dr_action *action;
 	int dr_reformat;
 
-	switch (reformat_type) {
+	switch (params->type) {
 	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
 	case MLX5_REFORMAT_TYPE_L2_TO_NVGRE:
 	case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL:
@@ -542,16 +543,21 @@ static int mlx5_cmd_dr_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns
 	case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL:
 		dr_reformat = DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3;
 		break;
+	case MLX5_REFORMAT_TYPE_INSERT_HDR:
+		dr_reformat = DR_ACTION_REFORMAT_TYP_INSERT_HDR;
+		break;
 	default:
 		mlx5_core_err(ns->dev, "Packet-reformat not supported(%d)\n",
-			      reformat_type);
+			      params->type);
 		return -EOPNOTSUPP;
 	}
 
 	action = mlx5dr_action_create_packet_reformat(dr_domain,
 						      dr_reformat,
-						      size,
-						      reformat_data);
+						      params->param_0,
+						      params->param_1,
+						      params->size,
+						      params->data);
 	if (!action) {
 		mlx5_core_err(ns->dev, "Failed allocating packet-reformat action\n");
 		return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
index 9737565cd8d4..b2aa6c93c3a1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
@@ -26,6 +26,7 @@ enum mlx5dr_action_reformat_type {
 	DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L2,
 	DR_ACTION_REFORMAT_TYP_TNL_L3_TO_L2,
 	DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3,
+	DR_ACTION_REFORMAT_TYP_INSERT_HDR,
 };
 
 struct mlx5dr_match_parameters {
@@ -105,6 +106,8 @@ mlx5dr_action_create_flow_counter(u32 counter_id);
 struct mlx5dr_action *
 mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn,
 				     enum mlx5dr_action_reformat_type reformat_type,
+				     u8 reformat_param_0,
+				     u8 reformat_param_1,
 				     size_t data_sz,
 				     void *data);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
index a619d90559f7..12871c8dc7c1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
@@ -49,28 +49,6 @@ config MLXSW_I2C
 	  To compile this driver as a module, choose M here: the
 	  module will be called mlxsw_i2c.
 
-config MLXSW_SWITCHIB
-	tristate "Mellanox Technologies SwitchIB and SwitchIB-2 support"
-	depends on MLXSW_CORE && MLXSW_PCI && NET_SWITCHDEV
-	default m
-	help
-	  This driver supports Mellanox Technologies SwitchIB and SwitchIB-2
-	  Infiniband Switch ASICs.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called mlxsw_switchib.
-
-config MLXSW_SWITCHX2
-	tristate "Mellanox Technologies SwitchX-2 support"
-	depends on MLXSW_CORE && MLXSW_PCI && NET_SWITCHDEV
-	default m
-	help
-	  This driver supports Mellanox Technologies SwitchX-2 Ethernet
-	  Switch ASICs.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called mlxsw_switchx2.
-
 config MLXSW_SPECTRUM
 	tristate "Mellanox Technologies Spectrum family support"
 	depends on MLXSW_CORE && MLXSW_PCI && NET_SWITCHDEV && VLAN_8021Q
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index f545fd2c5896..196adeb33495 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -8,10 +8,6 @@ obj-$(CONFIG_MLXSW_PCI)		+= mlxsw_pci.o
 mlxsw_pci-objs			:= pci.o
 obj-$(CONFIG_MLXSW_I2C)		+= mlxsw_i2c.o
 mlxsw_i2c-objs			:= i2c.o
-obj-$(CONFIG_MLXSW_SWITCHIB)	+= mlxsw_switchib.o
-mlxsw_switchib-objs		:= switchib.o
-obj-$(CONFIG_MLXSW_SWITCHX2)	+= mlxsw_switchx2.o
-mlxsw_switchx2-objs		:= switchx2.o
 obj-$(CONFIG_MLXSW_SPECTRUM)	+= mlxsw_spectrum.o
 mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_switchdev.o spectrum_router.o \
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 7e9a7cb31720..e775f08fb464 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -630,7 +630,7 @@ static int mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core,
 	struct sk_buff *skb;
 	int err;
 
-	skb = skb_copy(trans->tx_skb, GFP_KERNEL);
+	skb = skb_clone(trans->tx_skb, GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;
 
@@ -1444,7 +1444,9 @@ mlxsw_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 	if (err)
 		return err;
 
-	err = devlink_info_version_fixed_put(req, "fw.psid", fw_info_psid);
+	err = devlink_info_version_fixed_put(req,
+					     DEVLINK_INFO_VERSION_GENERIC_FW_PSID,
+					     fw_info_psid);
 	if (err)
 		return err;
 
@@ -1453,7 +1455,9 @@ mlxsw_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 	if (err)
 		return err;
 
-	return 0;
+	return devlink_info_version_running_put(req,
+						DEVLINK_INFO_VERSION_GENERIC_FW,
+						buf);
 }
 
 static int
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
index dd26865bd587..b3ca5bd33a7f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
@@ -125,6 +125,7 @@ mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, int module,
 int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module,
 					 int off, int *temp)
 {
+	unsigned int module_temp, module_crit, module_emerg;
 	char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE];
 	union {
 		u8 buf[MLXSW_REG_MCIA_TH_ITEM_SIZE];
@@ -132,7 +133,6 @@ int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module,
 	} temp_thresh;
 	char mcia_pl[MLXSW_REG_MCIA_LEN] = {0};
 	char mtmp_pl[MLXSW_REG_MTMP_LEN];
-	unsigned int module_temp;
 	bool qsfp, cmis;
 	int page;
 	int err;
@@ -142,12 +142,21 @@ int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module,
 	err = mlxsw_reg_query(core, MLXSW_REG(mtmp), mtmp_pl);
 	if (err)
 		return err;
-	mlxsw_reg_mtmp_unpack(mtmp_pl, &module_temp, NULL, NULL);
+	mlxsw_reg_mtmp_unpack(mtmp_pl, &module_temp, NULL, &module_crit,
+			      &module_emerg, NULL);
 	if (!module_temp) {
 		*temp = 0;
 		return 0;
 	}
 
+	/* Validate if threshold reading is available through MTMP register,
+	 * otherwise fallback to read through MCIA.
+	 */
+	if (module_emerg) {
+		*temp = off == SFP_TEMP_HIGH_WARN ? module_crit : module_emerg;
+		return 0;
+	}
+
 	/* Read Free Side Device Temperature Thresholds from page 03h
 	 * (MSB at lower byte address).
 	 * Bytes:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
index 2196c946698a..d41afdfbd085 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
@@ -72,7 +72,7 @@ static ssize_t mlxsw_hwmon_temp_show(struct device *dev,
 		dev_err(mlxsw_hwmon->bus_info->dev, "Failed to query temp sensor\n");
 		return err;
 	}
-	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
+	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL, NULL, NULL);
 	return sprintf(buf, "%d\n", temp);
 }
 
@@ -95,7 +95,7 @@ static ssize_t mlxsw_hwmon_temp_max_show(struct device *dev,
 		dev_err(mlxsw_hwmon->bus_info->dev, "Failed to query temp sensor\n");
 		return err;
 	}
-	mlxsw_reg_mtmp_unpack(mtmp_pl, NULL, &temp_max, NULL);
+	mlxsw_reg_mtmp_unpack(mtmp_pl, NULL, &temp_max, NULL, NULL, NULL);
 	return sprintf(buf, "%d\n", temp_max);
 }
 
@@ -239,7 +239,7 @@ static int mlxsw_hwmon_module_temp_get(struct device *dev,
 		dev_err(dev, "Failed to query module temperature\n");
 		return err;
 	}
-	mlxsw_reg_mtmp_unpack(mtmp_pl, p_temp, NULL, NULL);
+	mlxsw_reg_mtmp_unpack(mtmp_pl, p_temp, NULL, NULL, NULL, NULL);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 85f0ce285146..0998dcc9cac0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -149,22 +149,27 @@ mlxsw_thermal_module_trips_reset(struct mlxsw_thermal_module *tz)
 
 static int
 mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core,
-				  struct mlxsw_thermal_module *tz)
+				  struct mlxsw_thermal_module *tz,
+				  int crit_temp, int emerg_temp)
 {
-	int crit_temp, emerg_temp;
 	int err;
 
-	err = mlxsw_env_module_temp_thresholds_get(core, tz->module,
-						   SFP_TEMP_HIGH_WARN,
-						   &crit_temp);
-	if (err)
-		return err;
+	/* Do not try to query temperature thresholds directly from the module's
+	 * EEPROM if we got valid thresholds from MTMP.
+	 */
+	if (!emerg_temp || !crit_temp) {
+		err = mlxsw_env_module_temp_thresholds_get(core, tz->module,
+							   SFP_TEMP_HIGH_WARN,
+							   &crit_temp);
+		if (err)
+			return err;
 
-	err = mlxsw_env_module_temp_thresholds_get(core, tz->module,
-						   SFP_TEMP_HIGH_ALARM,
-						   &emerg_temp);
-	if (err)
-		return err;
+		err = mlxsw_env_module_temp_thresholds_get(core, tz->module,
+							   SFP_TEMP_HIGH_ALARM,
+							   &emerg_temp);
+		if (err)
+			return err;
+	}
 
 	if (crit_temp > emerg_temp) {
 		dev_warn(dev, "%s : Critical threshold %d is above emergency threshold %d\n",
@@ -281,7 +286,7 @@ static int mlxsw_thermal_get_temp(struct thermal_zone_device *tzdev,
 		dev_err(dev, "Failed to query temp sensor\n");
 		return err;
 	}
-	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
+	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL, NULL, NULL);
 	if (temp > 0)
 		mlxsw_thermal_tz_score_update(thermal, tzdev, thermal->trips,
 					      temp);
@@ -420,36 +425,57 @@ static int mlxsw_thermal_module_unbind(struct thermal_zone_device *tzdev,
 	return err;
 }
 
-static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
-					 int *p_temp)
+static void
+mlxsw_thermal_module_temp_and_thresholds_get(struct mlxsw_core *core,
+					     u16 sensor_index, int *p_temp,
+					     int *p_crit_temp,
+					     int *p_emerg_temp)
 {
-	struct mlxsw_thermal_module *tz = tzdev->devdata;
-	struct mlxsw_thermal *thermal = tz->parent;
-	struct device *dev = thermal->bus_info->dev;
 	char mtmp_pl[MLXSW_REG_MTMP_LEN];
-	int temp;
 	int err;
 
-	/* Read module temperature. */
-	mlxsw_reg_mtmp_pack(mtmp_pl, MLXSW_REG_MTMP_MODULE_INDEX_MIN +
-			    tz->module, false, false);
-	err = mlxsw_reg_query(thermal->core, MLXSW_REG(mtmp), mtmp_pl);
+	/* Read module temperature and thresholds. */
+	mlxsw_reg_mtmp_pack(mtmp_pl, sensor_index, false, false);
+	err = mlxsw_reg_query(core, MLXSW_REG(mtmp), mtmp_pl);
 	if (err) {
-		/* Do not return error - in case of broken module's sensor
-		 * it will cause error message flooding.
+		/* Set temperature and thresholds to zero to avoid passing
+		 * uninitialized data back to the caller.
 		 */
-		temp = 0;
-		*p_temp = (int) temp;
-		return 0;
+		*p_temp = 0;
+		*p_crit_temp = 0;
+		*p_emerg_temp = 0;
+
+		return;
 	}
-	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
+	mlxsw_reg_mtmp_unpack(mtmp_pl, p_temp, NULL, p_crit_temp, p_emerg_temp,
+			      NULL);
+}
+
+static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
+					 int *p_temp)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+	int temp, crit_temp, emerg_temp;
+	struct device *dev;
+	u16 sensor_index;
+	int err;
+
+	dev = thermal->bus_info->dev;
+	sensor_index = MLXSW_REG_MTMP_MODULE_INDEX_MIN + tz->module;
+
+	/* Read module temperature and thresholds. */
+	mlxsw_thermal_module_temp_and_thresholds_get(thermal->core,
+						     sensor_index, &temp,
+						     &crit_temp, &emerg_temp);
 	*p_temp = temp;
 
 	if (!temp)
 		return 0;
 
 	/* Update trip points. */
-	err = mlxsw_thermal_module_trips_update(dev, thermal->core, tz);
+	err = mlxsw_thermal_module_trips_update(dev, thermal->core, tz,
+						crit_temp, emerg_temp);
 	if (!err && temp > 0)
 		mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp);
 
@@ -560,7 +586,7 @@ static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
 	if (err)
 		return err;
 
-	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
+	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL, NULL, NULL);
 	if (temp > 0)
 		mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp);
 
@@ -717,7 +743,10 @@ mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core,
 			  struct mlxsw_thermal *thermal, u8 module)
 {
 	struct mlxsw_thermal_module *module_tz;
+	int dummy_temp, crit_temp, emerg_temp;
+	u16 sensor_index;
 
+	sensor_index = MLXSW_REG_MTMP_MODULE_INDEX_MIN + module;
 	module_tz = &thermal->tz_module_arr[module];
 	/* Skip if parent is already set (case of port split). */
 	if (module_tz->parent)
@@ -728,8 +757,12 @@ mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core,
 	       sizeof(thermal->trips));
 	/* Initialize all trip point. */
 	mlxsw_thermal_module_trips_reset(module_tz);
+	/* Read module temperature and thresholds. */
+	mlxsw_thermal_module_temp_and_thresholds_get(core, sensor_index, &dummy_temp,
+						     &crit_temp, &emerg_temp);
 	/* Update trip point according to the module data. */
-	return mlxsw_thermal_module_trips_update(dev, core, module_tz);
+	return mlxsw_thermal_module_trips_update(dev, core, module_tz,
+						 crit_temp, emerg_temp);
 }
 
 static void mlxsw_thermal_module_fini(struct mlxsw_thermal_module *module_tz)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/ib.h b/drivers/net/ethernet/mellanox/mlxsw/ib.h
deleted file mode 100644
index 2d0cb0f5eb85..000000000000
--- a/drivers/net/ethernet/mellanox/mlxsw/ib.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
-/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
-
-#ifndef _MLXSW_IB_H
-#define _MLXSW_IB_H
-
-#define MLXSW_IB_DEFAULT_MTU 4096
-
-#endif /* _MLXSW_IB_H */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
index b34c44723f8b..68102726c6a7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
@@ -234,6 +234,7 @@ static void mlxsw_m_port_remove(struct mlxsw_m *mlxsw_m, u8 local_port)
 static int mlxsw_m_port_module_map(struct mlxsw_m *mlxsw_m, u8 local_port,
 				   u8 *last_module)
 {
+	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_m->core);
 	u8 module, width;
 	int err;
 
@@ -249,6 +250,9 @@ static int mlxsw_m_port_module_map(struct mlxsw_m *mlxsw_m, u8 local_port,
 	if (module == *last_module)
 		return 0;
 	*last_module = module;
+
+	if (WARN_ON_ONCE(module >= max_ports))
+		return -EINVAL;
 	mlxsw_m->module_to_port[module] = ++mlxsw_m->max_ports;
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 8e8456811384..13b0259f7ea6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1426,11 +1426,6 @@ static int mlxsw_pci_sys_ready_wait(struct mlxsw_pci *mlxsw_pci,
 	unsigned long end;
 	u32 val;
 
-	if (id->device == PCI_DEVICE_ID_MELLANOX_SWITCHX2) {
-		msleep(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS);
-		return 0;
-	}
-
 	/* We must wait for the HW to become responsive. */
 	msleep(MLXSW_PCI_SW_RESET_WAIT_MSECS);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.h b/drivers/net/ethernet/mellanox/mlxsw/pci.h
index 5b1323645a5d..9899c1a2ea8f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.h
@@ -6,12 +6,9 @@
 
 #include <linux/pci.h>
 
-#define PCI_DEVICE_ID_MELLANOX_SWITCHX2		0xc738
 #define PCI_DEVICE_ID_MELLANOX_SPECTRUM		0xcb84
 #define PCI_DEVICE_ID_MELLANOX_SPECTRUM2	0xcf6c
 #define PCI_DEVICE_ID_MELLANOX_SPECTRUM3	0xcf70
-#define PCI_DEVICE_ID_MELLANOX_SWITCHIB		0xcb20
-#define PCI_DEVICE_ID_MELLANOX_SWITCHIB2	0xcf08
 
 #if IS_ENABLED(CONFIG_MLXSW_PCI)
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 2bc5a9003c6d..93f1db3927af 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -8305,6 +8305,8 @@ enum {
 	MLXSW_REG_RECR2_TCP_UDP_EN_IPV4		= 7,
 	/* Enable TCP/UDP header fields if packet is IPv6 */
 	MLXSW_REG_RECR2_TCP_UDP_EN_IPV6		= 8,
+
+	__MLXSW_REG_RECR2_HEADER_CNT,
 };
 
 /* reg_recr2_outer_header_enables
@@ -8339,6 +8341,8 @@ enum {
 	MLXSW_REG_RECR2_TCP_UDP_SPORT			= 74,
 	/* TCP/UDP Destination Port */
 	MLXSW_REG_RECR2_TCP_UDP_DPORT			= 75,
+
+	__MLXSW_REG_RECR2_FIELD_CNT,
 };
 
 /* reg_recr2_outer_header_fields_enable
@@ -8347,47 +8351,47 @@ enum {
  */
 MLXSW_ITEM_BIT_ARRAY(reg, recr2, outer_header_fields_enable, 0x14, 0x14, 1);
 
-static inline void mlxsw_reg_recr2_ipv4_sip_enable(char *payload)
-{
-	int i;
-
-	for (i = MLXSW_REG_RECR2_IPV4_SIP0; i <= MLXSW_REG_RECR2_IPV4_SIP3; i++)
-		mlxsw_reg_recr2_outer_header_fields_enable_set(payload, i,
-							       true);
-}
-
-static inline void mlxsw_reg_recr2_ipv4_dip_enable(char *payload)
-{
-	int i;
-
-	for (i = MLXSW_REG_RECR2_IPV4_DIP0; i <= MLXSW_REG_RECR2_IPV4_DIP3; i++)
-		mlxsw_reg_recr2_outer_header_fields_enable_set(payload, i,
-							       true);
-}
-
-static inline void mlxsw_reg_recr2_ipv6_sip_enable(char *payload)
-{
-	int i = MLXSW_REG_RECR2_IPV6_SIP0_7;
-
-	mlxsw_reg_recr2_outer_header_fields_enable_set(payload, i, true);
-
-	i = MLXSW_REG_RECR2_IPV6_SIP8;
-	for (; i <= MLXSW_REG_RECR2_IPV6_SIP15; i++)
-		mlxsw_reg_recr2_outer_header_fields_enable_set(payload, i,
-							       true);
-}
-
-static inline void mlxsw_reg_recr2_ipv6_dip_enable(char *payload)
-{
-	int i = MLXSW_REG_RECR2_IPV6_DIP0_7;
-
-	mlxsw_reg_recr2_outer_header_fields_enable_set(payload, i, true);
+/* reg_recr2_inner_header_enables
+ * Bit mask where each bit enables a specific inner layer to be included in the
+ * hash calculation. Same values as reg_recr2_outer_header_enables.
+ * Access: RW
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, recr2, inner_header_enables, 0x2C, 0x04, 1);
 
-	i = MLXSW_REG_RECR2_IPV6_DIP8;
-	for (; i <= MLXSW_REG_RECR2_IPV6_DIP15; i++)
-		mlxsw_reg_recr2_outer_header_fields_enable_set(payload, i,
-							       true);
-}
+enum {
+	/* Inner IPv4 Source IP */
+	MLXSW_REG_RECR2_INNER_IPV4_SIP0			= 3,
+	MLXSW_REG_RECR2_INNER_IPV4_SIP3			= 6,
+	/* Inner IPv4 Destination IP */
+	MLXSW_REG_RECR2_INNER_IPV4_DIP0			= 7,
+	MLXSW_REG_RECR2_INNER_IPV4_DIP3			= 10,
+	/* Inner IP Protocol */
+	MLXSW_REG_RECR2_INNER_IPV4_PROTOCOL		= 11,
+	/* Inner IPv6 Source IP */
+	MLXSW_REG_RECR2_INNER_IPV6_SIP0_7		= 12,
+	MLXSW_REG_RECR2_INNER_IPV6_SIP8			= 20,
+	MLXSW_REG_RECR2_INNER_IPV6_SIP15		= 27,
+	/* Inner IPv6 Destination IP */
+	MLXSW_REG_RECR2_INNER_IPV6_DIP0_7		= 28,
+	MLXSW_REG_RECR2_INNER_IPV6_DIP8			= 36,
+	MLXSW_REG_RECR2_INNER_IPV6_DIP15		= 43,
+	/* Inner IPv6 Next Header */
+	MLXSW_REG_RECR2_INNER_IPV6_NEXT_HEADER		= 44,
+	/* Inner IPv6 Flow Label */
+	MLXSW_REG_RECR2_INNER_IPV6_FLOW_LABEL		= 45,
+	/* Inner TCP/UDP Source Port */
+	MLXSW_REG_RECR2_INNER_TCP_UDP_SPORT		= 46,
+	/* Inner TCP/UDP Destination Port */
+	MLXSW_REG_RECR2_INNER_TCP_UDP_DPORT		= 47,
+
+	__MLXSW_REG_RECR2_INNER_FIELD_CNT,
+};
+
+/* reg_recr2_inner_header_fields_enable
+ * Inner packet fields to enable for ECMP hash subject to inner_header_enables.
+ * Access: RW
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, recr2, inner_header_fields_enable, 0x30, 0x08, 1);
 
 static inline void mlxsw_reg_recr2_pack(char *payload, u32 seed)
 {
@@ -9459,6 +9463,14 @@ MLXSW_ITEM32(reg, mtmp, sensor_index, 0x00, 0, 12);
 					  ((s16)((GENMASK(15, 0) + (v_) + 1) \
 					   * 125)); })
 
+/* reg_mtmp_max_operational_temperature
+ * The highest temperature in the nominal operational range. Reading is in
+ * 0.125 Celsius degrees units.
+ * In case of module this is SFF critical temperature threshold.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mtmp, max_operational_temperature, 0x04, 16, 16);
+
 /* reg_mtmp_temperature
  * Temperature reading from the sensor. Reading is in 0.125 Celsius
  * degrees units.
@@ -9537,7 +9549,9 @@ static inline void mlxsw_reg_mtmp_pack(char *payload, u16 sensor_index,
 }
 
 static inline void mlxsw_reg_mtmp_unpack(char *payload, int *p_temp,
-					 int *p_max_temp, char *sensor_name)
+					 int *p_max_temp, int *p_temp_hi,
+					 int *p_max_oper_temp,
+					 char *sensor_name)
 {
 	s16 temp;
 
@@ -9549,6 +9563,14 @@ static inline void mlxsw_reg_mtmp_unpack(char *payload, int *p_temp,
 		temp = mlxsw_reg_mtmp_max_temperature_get(payload);
 		*p_max_temp = MLXSW_REG_MTMP_TEMP_TO_MC(temp);
 	}
+	if (p_temp_hi) {
+		temp = mlxsw_reg_mtmp_temperature_threshold_hi_get(payload);
+		*p_temp_hi = MLXSW_REG_MTMP_TEMP_TO_MC(temp);
+	}
+	if (p_max_oper_temp) {
+		temp = mlxsw_reg_mtmp_max_operational_temperature_get(payload);
+		*p_max_oper_temp = MLXSW_REG_MTMP_TEMP_TO_MC(temp);
+	}
 	if (sensor_name)
 		mlxsw_reg_mtmp_sensor_name_memcpy_from(payload, sensor_name);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index bca0354482cb..88699e678544 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2125,9 +2125,14 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg,
 	struct mlxsw_sp *mlxsw_sp = priv;
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	enum mlxsw_reg_pude_oper_status status;
+	unsigned int max_ports;
 	u8 local_port;
 
+	max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
 	local_port = mlxsw_reg_pude_local_port_get(pude_pl);
+
+	if (WARN_ON_ONCE(local_port >= max_ports))
+		return;
 	mlxsw_sp_port = mlxsw_sp->ports[local_port];
 	if (!mlxsw_sp_port)
 		return;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index 37ff29a1686e..9de160e740b2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -364,7 +364,7 @@ static u16 mlxsw_sp_hdroom_buf_delay_get(const struct mlxsw_sp *mlxsw_sp,
 
 static u32 mlxsw_sp_hdroom_int_buf_size_get(struct mlxsw_sp *mlxsw_sp, int mtu, u32 speed)
 {
-	u32 buffsize = mlxsw_sp->sb_ops->int_buf_size_get(speed, mtu);
+	u32 buffsize = mlxsw_sp->sb_ops->int_buf_size_get(mtu, speed);
 
 	return mlxsw_sp_bytes_cells(mlxsw_sp, buffsize) + 1;
 }
@@ -388,8 +388,8 @@ void mlxsw_sp_hdroom_bufs_reset_sizes(struct mlxsw_sp_port *mlxsw_sp_port,
 	int i;
 
 	/* Internal buffer. */
-	reserve_cells = mlxsw_sp_hdroom_int_buf_size_get(mlxsw_sp, mlxsw_sp_port->max_speed,
-							 mlxsw_sp_port->max_mtu);
+	reserve_cells = mlxsw_sp_hdroom_int_buf_size_get(mlxsw_sp, mlxsw_sp_port->max_mtu,
+							 mlxsw_sp_port->max_speed);
 	reserve_cells = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, reserve_cells);
 	hdroom->int_buf.reserve_cells = reserve_cells;
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
index d6e9ecb14681..bfef65d1587c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
@@ -568,10 +568,13 @@ void mlxsw_sp1_ptp_got_timestamp(struct mlxsw_sp *mlxsw_sp, bool ingress,
 				 u8 domain_number, u16 sequence_id,
 				 u64 timestamp)
 {
+	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	struct mlxsw_sp1_ptp_key key;
 	u8 types;
 
+	if (WARN_ON_ONCE(local_port >= max_ports))
+		return;
 	mlxsw_sp_port = mlxsw_sp->ports[local_port];
 	if (!mlxsw_sp_port)
 		return;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 41259c0004d1..7e221ef01437 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2282,6 +2282,7 @@ static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp,
 						   char *rauhtd_pl,
 						   int ent_index)
 {
+	u64 max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
 	struct net_device *dev;
 	struct neighbour *n;
 	__be32 dipn;
@@ -2290,6 +2291,8 @@ static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp,
 
 	mlxsw_reg_rauhtd_ent_ipv4_unpack(rauhtd_pl, ent_index, &rif, &dip);
 
+	if (WARN_ON_ONCE(rif >= max_rifs))
+		return;
 	if (!mlxsw_sp->router->rifs[rif]) {
 		dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Incorrect RIF in neighbour entry\n");
 		return;
@@ -3841,8 +3844,8 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 	bool offload_change = false;
 	u32 adj_index;
 	bool old_adj_index_valid;
-	int i, err2, err = 0;
 	u32 old_adj_index;
+	int i, err2, err;
 
 	if (!nhgi->gateway)
 		return mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp);
@@ -3872,11 +3875,13 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 		return 0;
 	}
 	mlxsw_sp_nexthop_group_normalize(nhgi);
-	if (!nhgi->sum_norm_weight)
+	if (!nhgi->sum_norm_weight) {
 		/* No neigh of this group is connected so we just set
 		 * the trap and let everthing flow through kernel.
 		 */
+		err = 0;
 		goto set_trap;
+	}
 
 	ecmp_size = nhgi->sum_norm_weight;
 	err = mlxsw_sp_fix_adj_grp_size(mlxsw_sp, &ecmp_size);
@@ -4307,9 +4312,6 @@ static void mlxsw_sp_nexthop4_event(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_nexthop_key key;
 	struct mlxsw_sp_nexthop *nh;
 
-	if (mlxsw_sp->router->aborted)
-		return;
-
 	key.fib_nh = fib_nh;
 	nh = mlxsw_sp_nexthop_lookup(mlxsw_sp, key);
 	if (!nh)
@@ -5405,7 +5407,6 @@ mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp,
 		    ipv6_addr_equal((const struct in6_addr *) &nh->gw_addr,
 				    &rt->fib6_nh->fib_nh_gw6))
 			return nh;
-		continue;
 	}
 
 	return NULL;
@@ -6417,9 +6418,6 @@ mlxsw_sp_router_fib4_replace(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_fib_node *fib_node;
 	int err;
 
-	if (mlxsw_sp->router->aborted)
-		return 0;
-
 	if (fen_info->fi->nh &&
 	    !mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp, fen_info->fi->nh->id))
 		return 0;
@@ -6480,9 +6478,6 @@ static int mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_fib_node *fib_node;
 	int err;
 
-	if (mlxsw_sp->router->aborted)
-		return 0;
-
 	fib4_entry = mlxsw_sp_fib4_entry_lookup(mlxsw_sp, fen_info);
 	if (!fib4_entry)
 		return 0;
@@ -7065,9 +7060,6 @@ static int mlxsw_sp_router_fib6_replace(struct mlxsw_sp *mlxsw_sp,
 	struct fib6_info *rt = rt_arr[0];
 	int err;
 
-	if (mlxsw_sp->router->aborted)
-		return 0;
-
 	if (rt->fib6_src.plen)
 		return -EINVAL;
 
@@ -7131,9 +7123,6 @@ static int mlxsw_sp_router_fib6_append(struct mlxsw_sp *mlxsw_sp,
 	struct fib6_info *rt = rt_arr[0];
 	int err;
 
-	if (mlxsw_sp->router->aborted)
-		return 0;
-
 	if (rt->fib6_src.plen)
 		return -EINVAL;
 
@@ -7175,9 +7164,6 @@ static int mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp,
 	struct fib6_info *rt = rt_arr[0];
 	int err;
 
-	if (mlxsw_sp->router->aborted)
-		return 0;
-
 	if (mlxsw_sp_fib6_rt_should_ignore(rt))
 		return 0;
 
@@ -7206,55 +7192,6 @@ static int mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp,
 	return err;
 }
 
-static int __mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp,
-					    enum mlxsw_sp_l3proto proto,
-					    u8 tree_id)
-{
-	const struct mlxsw_sp_router_ll_ops *ll_ops = mlxsw_sp->router->proto_ll_ops[proto];
-	enum mlxsw_reg_ralxx_protocol ralxx_proto =
-				(enum mlxsw_reg_ralxx_protocol) proto;
-	struct mlxsw_sp_fib_entry_priv *priv;
-	char xralta_pl[MLXSW_REG_XRALTA_LEN];
-	char xralst_pl[MLXSW_REG_XRALST_LEN];
-	int i, err;
-
-	mlxsw_reg_xralta_pack(xralta_pl, true, ralxx_proto, tree_id);
-	err = ll_ops->ralta_write(mlxsw_sp, xralta_pl);
-	if (err)
-		return err;
-
-	mlxsw_reg_xralst_pack(xralst_pl, 0xff, tree_id);
-	err = ll_ops->ralst_write(mlxsw_sp, xralst_pl);
-	if (err)
-		return err;
-
-	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
-		struct mlxsw_sp_fib_entry_op_ctx *op_ctx = mlxsw_sp->router->ll_op_ctx;
-		struct mlxsw_sp_vr *vr = &mlxsw_sp->router->vrs[i];
-		char xraltb_pl[MLXSW_REG_XRALTB_LEN];
-
-		mlxsw_sp_fib_entry_op_ctx_clear(op_ctx);
-		mlxsw_reg_xraltb_pack(xraltb_pl, vr->id, ralxx_proto, tree_id);
-		err = ll_ops->raltb_write(mlxsw_sp, xraltb_pl);
-		if (err)
-			return err;
-
-		priv = mlxsw_sp_fib_entry_priv_create(ll_ops);
-		if (IS_ERR(priv))
-			return PTR_ERR(priv);
-
-		ll_ops->fib_entry_pack(op_ctx, proto, MLXSW_SP_FIB_ENTRY_OP_WRITE,
-				       vr->id, 0, NULL, priv);
-		ll_ops->fib_entry_act_ip2me_pack(op_ctx);
-		err = ll_ops->fib_entry_commit(mlxsw_sp, op_ctx, NULL);
-		mlxsw_sp_fib_entry_priv_put(priv);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
 static struct mlxsw_sp_mr_table *
 mlxsw_sp_router_fibmr_family_to_table(struct mlxsw_sp_vr *vr, int family)
 {
@@ -7271,9 +7208,6 @@ static int mlxsw_sp_router_fibmr_add(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_mr_table *mrt;
 	struct mlxsw_sp_vr *vr;
 
-	if (mlxsw_sp->router->aborted)
-		return 0;
-
 	vr = mlxsw_sp_vr_get(mlxsw_sp, men_info->tb_id, NULL);
 	if (IS_ERR(vr))
 		return PTR_ERR(vr);
@@ -7288,9 +7222,6 @@ static void mlxsw_sp_router_fibmr_del(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_mr_table *mrt;
 	struct mlxsw_sp_vr *vr;
 
-	if (mlxsw_sp->router->aborted)
-		return;
-
 	vr = mlxsw_sp_vr_find(mlxsw_sp, men_info->tb_id);
 	if (WARN_ON(!vr))
 		return;
@@ -7308,9 +7239,6 @@ mlxsw_sp_router_fibmr_vif_add(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_rif *rif;
 	struct mlxsw_sp_vr *vr;
 
-	if (mlxsw_sp->router->aborted)
-		return 0;
-
 	vr = mlxsw_sp_vr_get(mlxsw_sp, ven_info->tb_id, NULL);
 	if (IS_ERR(vr))
 		return PTR_ERR(vr);
@@ -7329,9 +7257,6 @@ mlxsw_sp_router_fibmr_vif_del(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_mr_table *mrt;
 	struct mlxsw_sp_vr *vr;
 
-	if (mlxsw_sp->router->aborted)
-		return;
-
 	vr = mlxsw_sp_vr_find(mlxsw_sp, ven_info->tb_id);
 	if (WARN_ON(!vr))
 		return;
@@ -7341,25 +7266,6 @@ mlxsw_sp_router_fibmr_vif_del(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_vr_put(mlxsw_sp, vr);
 }
 
-static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
-{
-	enum mlxsw_sp_l3proto proto = MLXSW_SP_L3_PROTO_IPV4;
-	int err;
-
-	err = __mlxsw_sp_router_set_abort_trap(mlxsw_sp, proto,
-					       MLXSW_SP_LPM_TREE_MIN);
-	if (err)
-		return err;
-
-	/* The multicast router code does not need an abort trap as by default,
-	 * packets that don't match any routes are trapped to the CPU.
-	 */
-
-	proto = MLXSW_SP_L3_PROTO_IPV6;
-	return __mlxsw_sp_router_set_abort_trap(mlxsw_sp, proto,
-						MLXSW_SP_LPM_TREE_MIN + 1);
-}
-
 static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp,
 				     struct mlxsw_sp_fib_node *fib_node)
 {
@@ -7446,20 +7352,6 @@ static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp)
 	mlxsw_sp->router->adj_discard_index_valid = false;
 }
 
-static void mlxsw_sp_router_fib_abort(struct mlxsw_sp *mlxsw_sp)
-{
-	int err;
-
-	if (mlxsw_sp->router->aborted)
-		return;
-	dev_warn(mlxsw_sp->bus_info->dev, "FIB abort triggered. Note that FIB entries are no longer being offloaded to this device.\n");
-	mlxsw_sp_router_fib_flush(mlxsw_sp);
-	mlxsw_sp->router->aborted = true;
-	err = mlxsw_sp_router_set_abort_trap(mlxsw_sp);
-	if (err)
-		dev_warn(mlxsw_sp->bus_info->dev, "Failed to set abort trap.\n");
-}
-
 struct mlxsw_sp_fib6_event {
 	struct fib6_info **rt_arr;
 	unsigned int nrt6;
@@ -7541,7 +7433,7 @@ static void mlxsw_sp_router_fib4_event_process(struct mlxsw_sp *mlxsw_sp,
 		err = mlxsw_sp_router_fib4_replace(mlxsw_sp, op_ctx, &fib_event->fen_info);
 		if (err) {
 			mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx);
-			mlxsw_sp_router_fib_abort(mlxsw_sp);
+			dev_warn(mlxsw_sp->bus_info->dev, "FIB replace failed.\n");
 			mlxsw_sp_fib4_offload_failed_flag_set(mlxsw_sp,
 							      &fib_event->fen_info);
 		}
@@ -7576,7 +7468,7 @@ static void mlxsw_sp_router_fib6_event_process(struct mlxsw_sp *mlxsw_sp,
 						   fib_event->fib6_event.nrt6);
 		if (err) {
 			mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx);
-			mlxsw_sp_router_fib_abort(mlxsw_sp);
+			dev_warn(mlxsw_sp->bus_info->dev, "FIB replace failed.\n");
 			mlxsw_sp_fib6_offload_failed_flag_set(mlxsw_sp,
 							      fib6_event->rt_arr,
 							      fib6_event->nrt6);
@@ -7588,7 +7480,7 @@ static void mlxsw_sp_router_fib6_event_process(struct mlxsw_sp *mlxsw_sp,
 						  fib_event->fib6_event.nrt6);
 		if (err) {
 			mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx);
-			mlxsw_sp_router_fib_abort(mlxsw_sp);
+			dev_warn(mlxsw_sp->bus_info->dev, "FIB append failed.\n");
 			mlxsw_sp_fib6_offload_failed_flag_set(mlxsw_sp,
 							      fib6_event->rt_arr,
 							      fib6_event->nrt6);
@@ -7620,7 +7512,7 @@ static void mlxsw_sp_router_fibmr_event_process(struct mlxsw_sp *mlxsw_sp,
 
 		err = mlxsw_sp_router_fibmr_add(mlxsw_sp, &fib_event->men_info, replace);
 		if (err)
-			mlxsw_sp_router_fib_abort(mlxsw_sp);
+			dev_warn(mlxsw_sp->bus_info->dev, "MR entry add failed.\n");
 		mr_cache_put(fib_event->men_info.mfc);
 		break;
 	case FIB_EVENT_ENTRY_DEL:
@@ -7631,7 +7523,7 @@ static void mlxsw_sp_router_fibmr_event_process(struct mlxsw_sp *mlxsw_sp,
 		err = mlxsw_sp_router_fibmr_vif_add(mlxsw_sp,
 						    &fib_event->ven_info);
 		if (err)
-			mlxsw_sp_router_fib_abort(mlxsw_sp);
+			dev_warn(mlxsw_sp->bus_info->dev, "MR VIF add failed.\n");
 		dev_put(fib_event->ven_info.dev);
 		break;
 	case FIB_EVENT_VIF_DEL:
@@ -7795,9 +7687,6 @@ static int mlxsw_sp_router_fib_rule_event(unsigned long event,
 	if (event == FIB_EVENT_RULE_DEL)
 		return 0;
 
-	if (mlxsw_sp->router->aborted)
-		return 0;
-
 	fr_info = container_of(info, struct fib_rule_notifier_info, info);
 	rule = fr_info->rule;
 
@@ -7855,10 +7744,6 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 	case FIB_EVENT_ENTRY_ADD:
 	case FIB_EVENT_ENTRY_REPLACE:
 	case FIB_EVENT_ENTRY_APPEND:
-		if (router->aborted) {
-			NL_SET_ERR_MSG_MOD(info->extack, "FIB offload was aborted. Not configuring route");
-			return notifier_from_errno(-EINVAL);
-		}
 		if (info->family == AF_INET) {
 			struct fib_entry_notifier_info *fen_info = ptr;
 
@@ -9594,66 +9479,229 @@ static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb)
 }
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-static void mlxsw_sp_mp_hash_header_set(char *recr2_pl, int header)
+struct mlxsw_sp_mp_hash_config {
+	DECLARE_BITMAP(headers, __MLXSW_REG_RECR2_HEADER_CNT);
+	DECLARE_BITMAP(fields, __MLXSW_REG_RECR2_FIELD_CNT);
+	DECLARE_BITMAP(inner_headers, __MLXSW_REG_RECR2_HEADER_CNT);
+	DECLARE_BITMAP(inner_fields, __MLXSW_REG_RECR2_INNER_FIELD_CNT);
+};
+
+#define MLXSW_SP_MP_HASH_HEADER_SET(_headers, _header) \
+	bitmap_set(_headers, MLXSW_REG_RECR2_##_header, 1)
+
+#define MLXSW_SP_MP_HASH_FIELD_SET(_fields, _field) \
+	bitmap_set(_fields, MLXSW_REG_RECR2_##_field, 1)
+
+#define MLXSW_SP_MP_HASH_FIELD_RANGE_SET(_fields, _field, _nr) \
+	bitmap_set(_fields, MLXSW_REG_RECR2_##_field, _nr)
+
+static void mlxsw_sp_mp_hash_inner_l3(struct mlxsw_sp_mp_hash_config *config)
 {
-	mlxsw_reg_recr2_outer_header_enables_set(recr2_pl, header, true);
+	unsigned long *inner_headers = config->inner_headers;
+	unsigned long *inner_fields = config->inner_fields;
+
+	/* IPv4 inner */
+	MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, IPV4_EN_NOT_TCP_NOT_UDP);
+	MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, IPV4_EN_TCP_UDP);
+	MLXSW_SP_MP_HASH_FIELD_RANGE_SET(inner_fields, INNER_IPV4_SIP0, 4);
+	MLXSW_SP_MP_HASH_FIELD_RANGE_SET(inner_fields, INNER_IPV4_DIP0, 4);
+	/* IPv6 inner */
+	MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, IPV6_EN_NOT_TCP_NOT_UDP);
+	MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, IPV6_EN_TCP_UDP);
+	MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV6_SIP0_7);
+	MLXSW_SP_MP_HASH_FIELD_RANGE_SET(inner_fields, INNER_IPV6_SIP8, 8);
+	MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV6_DIP0_7);
+	MLXSW_SP_MP_HASH_FIELD_RANGE_SET(inner_fields, INNER_IPV6_DIP8, 8);
+	MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV6_NEXT_HEADER);
+	MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV6_FLOW_LABEL);
 }
 
-static void mlxsw_sp_mp_hash_field_set(char *recr2_pl, int field)
+static void mlxsw_sp_mp4_hash_outer_addr(struct mlxsw_sp_mp_hash_config *config)
 {
-	mlxsw_reg_recr2_outer_header_fields_enable_set(recr2_pl, field, true);
+	unsigned long *headers = config->headers;
+	unsigned long *fields = config->fields;
+
+	MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV4_EN_NOT_TCP_NOT_UDP);
+	MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV4_EN_TCP_UDP);
+	MLXSW_SP_MP_HASH_FIELD_RANGE_SET(fields, IPV4_SIP0, 4);
+	MLXSW_SP_MP_HASH_FIELD_RANGE_SET(fields, IPV4_DIP0, 4);
 }
 
-static void mlxsw_sp_mp4_hash_init(struct mlxsw_sp *mlxsw_sp, char *recr2_pl)
+static void
+mlxsw_sp_mp_hash_inner_custom(struct mlxsw_sp_mp_hash_config *config,
+			      u32 hash_fields)
+{
+	unsigned long *inner_headers = config->inner_headers;
+	unsigned long *inner_fields = config->inner_fields;
+
+	/* IPv4 Inner */
+	MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, IPV4_EN_NOT_TCP_NOT_UDP);
+	MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, IPV4_EN_TCP_UDP);
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP)
+		MLXSW_SP_MP_HASH_FIELD_RANGE_SET(inner_fields, INNER_IPV4_SIP0, 4);
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP)
+		MLXSW_SP_MP_HASH_FIELD_RANGE_SET(inner_fields, INNER_IPV4_DIP0, 4);
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO)
+		MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV4_PROTOCOL);
+	/* IPv6 inner */
+	MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, IPV6_EN_NOT_TCP_NOT_UDP);
+	MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, IPV6_EN_TCP_UDP);
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) {
+		MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV6_SIP0_7);
+		MLXSW_SP_MP_HASH_FIELD_RANGE_SET(inner_fields, INNER_IPV6_SIP8, 8);
+	}
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) {
+		MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV6_DIP0_7);
+		MLXSW_SP_MP_HASH_FIELD_RANGE_SET(inner_fields, INNER_IPV6_DIP8, 8);
+	}
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO)
+		MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV6_NEXT_HEADER);
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL)
+		MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV6_FLOW_LABEL);
+	/* L4 inner */
+	MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, TCP_UDP_EN_IPV4);
+	MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, TCP_UDP_EN_IPV6);
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT)
+		MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_TCP_UDP_SPORT);
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT)
+		MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_TCP_UDP_DPORT);
+}
+
+static void mlxsw_sp_mp4_hash_init(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_mp_hash_config *config)
 {
 	struct net *net = mlxsw_sp_net(mlxsw_sp);
-	bool only_l3 = !net->ipv4.sysctl_fib_multipath_hash_policy;
-
-	mlxsw_sp_mp_hash_header_set(recr2_pl,
-				    MLXSW_REG_RECR2_IPV4_EN_NOT_TCP_NOT_UDP);
-	mlxsw_sp_mp_hash_header_set(recr2_pl, MLXSW_REG_RECR2_IPV4_EN_TCP_UDP);
-	mlxsw_reg_recr2_ipv4_sip_enable(recr2_pl);
-	mlxsw_reg_recr2_ipv4_dip_enable(recr2_pl);
-	if (only_l3)
-		return;
-	mlxsw_sp_mp_hash_header_set(recr2_pl, MLXSW_REG_RECR2_TCP_UDP_EN_IPV4);
-	mlxsw_sp_mp_hash_field_set(recr2_pl, MLXSW_REG_RECR2_IPV4_PROTOCOL);
-	mlxsw_sp_mp_hash_field_set(recr2_pl, MLXSW_REG_RECR2_TCP_UDP_SPORT);
-	mlxsw_sp_mp_hash_field_set(recr2_pl, MLXSW_REG_RECR2_TCP_UDP_DPORT);
+	unsigned long *headers = config->headers;
+	unsigned long *fields = config->fields;
+	u32 hash_fields;
+
+	switch (net->ipv4.sysctl_fib_multipath_hash_policy) {
+	case 0:
+		mlxsw_sp_mp4_hash_outer_addr(config);
+		break;
+	case 1:
+		mlxsw_sp_mp4_hash_outer_addr(config);
+		MLXSW_SP_MP_HASH_HEADER_SET(headers, TCP_UDP_EN_IPV4);
+		MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV4_PROTOCOL);
+		MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_SPORT);
+		MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_DPORT);
+		break;
+	case 2:
+		/* Outer */
+		mlxsw_sp_mp4_hash_outer_addr(config);
+		/* Inner */
+		mlxsw_sp_mp_hash_inner_l3(config);
+		break;
+	case 3:
+		hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields;
+		/* Outer */
+		MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV4_EN_NOT_TCP_NOT_UDP);
+		MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV4_EN_TCP_UDP);
+		MLXSW_SP_MP_HASH_HEADER_SET(headers, TCP_UDP_EN_IPV4);
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP)
+			MLXSW_SP_MP_HASH_FIELD_RANGE_SET(fields, IPV4_SIP0, 4);
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP)
+			MLXSW_SP_MP_HASH_FIELD_RANGE_SET(fields, IPV4_DIP0, 4);
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO)
+			MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV4_PROTOCOL);
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT)
+			MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_SPORT);
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
+			MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_DPORT);
+		/* Inner */
+		mlxsw_sp_mp_hash_inner_custom(config, hash_fields);
+		break;
+	}
 }
 
-static void mlxsw_sp_mp6_hash_init(struct mlxsw_sp *mlxsw_sp, char *recr2_pl)
+static void mlxsw_sp_mp6_hash_outer_addr(struct mlxsw_sp_mp_hash_config *config)
 {
-	bool only_l3 = !ip6_multipath_hash_policy(mlxsw_sp_net(mlxsw_sp));
+	unsigned long *headers = config->headers;
+	unsigned long *fields = config->fields;
 
-	mlxsw_sp_mp_hash_header_set(recr2_pl,
-				    MLXSW_REG_RECR2_IPV6_EN_NOT_TCP_NOT_UDP);
-	mlxsw_sp_mp_hash_header_set(recr2_pl, MLXSW_REG_RECR2_IPV6_EN_TCP_UDP);
-	mlxsw_reg_recr2_ipv6_sip_enable(recr2_pl);
-	mlxsw_reg_recr2_ipv6_dip_enable(recr2_pl);
-	mlxsw_sp_mp_hash_field_set(recr2_pl, MLXSW_REG_RECR2_IPV6_NEXT_HEADER);
-	if (only_l3) {
-		mlxsw_sp_mp_hash_field_set(recr2_pl,
-					   MLXSW_REG_RECR2_IPV6_FLOW_LABEL);
-	} else {
-		mlxsw_sp_mp_hash_header_set(recr2_pl,
-					    MLXSW_REG_RECR2_TCP_UDP_EN_IPV6);
-		mlxsw_sp_mp_hash_field_set(recr2_pl,
-					   MLXSW_REG_RECR2_TCP_UDP_SPORT);
-		mlxsw_sp_mp_hash_field_set(recr2_pl,
-					   MLXSW_REG_RECR2_TCP_UDP_DPORT);
+	MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV6_EN_NOT_TCP_NOT_UDP);
+	MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV6_EN_TCP_UDP);
+	MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_SIP0_7);
+	MLXSW_SP_MP_HASH_FIELD_RANGE_SET(fields, IPV6_SIP8, 8);
+	MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_DIP0_7);
+	MLXSW_SP_MP_HASH_FIELD_RANGE_SET(fields, IPV6_DIP8, 8);
+}
+
+static void mlxsw_sp_mp6_hash_init(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_mp_hash_config *config)
+{
+	u32 hash_fields = ip6_multipath_hash_fields(mlxsw_sp_net(mlxsw_sp));
+	unsigned long *headers = config->headers;
+	unsigned long *fields = config->fields;
+
+	switch (ip6_multipath_hash_policy(mlxsw_sp_net(mlxsw_sp))) {
+	case 0:
+		mlxsw_sp_mp6_hash_outer_addr(config);
+		MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_NEXT_HEADER);
+		MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_FLOW_LABEL);
+		break;
+	case 1:
+		mlxsw_sp_mp6_hash_outer_addr(config);
+		MLXSW_SP_MP_HASH_HEADER_SET(headers, TCP_UDP_EN_IPV6);
+		MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_NEXT_HEADER);
+		MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_SPORT);
+		MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_DPORT);
+		break;
+	case 2:
+		/* Outer */
+		mlxsw_sp_mp6_hash_outer_addr(config);
+		MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_NEXT_HEADER);
+		MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_FLOW_LABEL);
+		/* Inner */
+		mlxsw_sp_mp_hash_inner_l3(config);
+		break;
+	case 3:
+		/* Outer */
+		MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV6_EN_NOT_TCP_NOT_UDP);
+		MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV6_EN_TCP_UDP);
+		MLXSW_SP_MP_HASH_HEADER_SET(headers, TCP_UDP_EN_IPV6);
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) {
+			MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_SIP0_7);
+			MLXSW_SP_MP_HASH_FIELD_RANGE_SET(fields, IPV6_SIP8, 8);
+		}
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) {
+			MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_DIP0_7);
+			MLXSW_SP_MP_HASH_FIELD_RANGE_SET(fields, IPV6_DIP8, 8);
+		}
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO)
+			MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_NEXT_HEADER);
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL)
+			MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_FLOW_LABEL);
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT)
+			MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_SPORT);
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
+			MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_DPORT);
+		/* Inner */
+		mlxsw_sp_mp_hash_inner_custom(config, hash_fields);
+		break;
 	}
 }
 
 static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp)
 {
+	struct mlxsw_sp_mp_hash_config config = {};
 	char recr2_pl[MLXSW_REG_RECR2_LEN];
+	unsigned long bit;
 	u32 seed;
 
 	seed = jhash(mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac), 0);
 	mlxsw_reg_recr2_pack(recr2_pl, seed);
-	mlxsw_sp_mp4_hash_init(mlxsw_sp, recr2_pl);
-	mlxsw_sp_mp6_hash_init(mlxsw_sp, recr2_pl);
+	mlxsw_sp_mp4_hash_init(mlxsw_sp, &config);
+	mlxsw_sp_mp6_hash_init(mlxsw_sp, &config);
+
+	for_each_set_bit(bit, config.headers, __MLXSW_REG_RECR2_HEADER_CNT)
+		mlxsw_reg_recr2_outer_header_enables_set(recr2_pl, bit, 1);
+	for_each_set_bit(bit, config.fields, __MLXSW_REG_RECR2_FIELD_CNT)
+		mlxsw_reg_recr2_outer_header_fields_enable_set(recr2_pl, bit, 1);
+	for_each_set_bit(bit, config.inner_headers, __MLXSW_REG_RECR2_HEADER_CNT)
+		mlxsw_reg_recr2_inner_header_enables_set(recr2_pl, bit, 1);
+	for_each_set_bit(bit, config.inner_fields, __MLXSW_REG_RECR2_INNER_FIELD_CNT)
+		mlxsw_reg_recr2_inner_header_fields_enable_set(recr2_pl, bit, 1);
 
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(recr2), recr2_pl);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index be7708a375e1..c5d7007f9173 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -58,7 +58,6 @@ struct mlxsw_sp_router {
 #define MLXSW_SP_UNRESOLVED_NH_PROBE_INTERVAL 5000 /* ms */
 	struct list_head nexthop_neighs_list;
 	struct list_head ipip_list;
-	bool aborted;
 	struct notifier_block nexthop_nb;
 	struct notifier_block fib_nb;
 	struct notifier_block netevent_nb;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index eeccd586e781..0cfba2986841 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2520,6 +2520,7 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp,
 					    char *sfn_pl, int rec_index,
 					    bool adding)
 {
+	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
 	struct mlxsw_sp_bridge_device *bridge_device;
 	struct mlxsw_sp_bridge_port *bridge_port;
@@ -2532,6 +2533,9 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	mlxsw_reg_sfn_mac_unpack(sfn_pl, rec_index, mac, &fid, &local_port);
+
+	if (WARN_ON_ONCE(local_port >= max_ports))
+		return;
 	mlxsw_sp_port = mlxsw_sp->ports[local_port];
 	if (!mlxsw_sp_port) {
 		dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Incorrect local port in FDB notification\n");
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchib.c b/drivers/net/ethernet/mellanox/mlxsw/switchib.c
deleted file mode 100644
index 1e561132eb1e..000000000000
--- a/drivers/net/ethernet/mellanox/mlxsw/switchib.c
+++ /dev/null
@@ -1,595 +0,0 @@
-// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
-/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/pci.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/slab.h>
-#include <linux/device.h>
-#include <linux/skbuff.h>
-#include <linux/if_vlan.h>
-#include <net/switchdev.h>
-
-#include "pci.h"
-#include "core.h"
-#include "reg.h"
-#include "port.h"
-#include "trap.h"
-#include "txheader.h"
-#include "ib.h"
-
-static const char mlxsw_sib_driver_name[] = "mlxsw_switchib";
-static const char mlxsw_sib2_driver_name[] = "mlxsw_switchib2";
-
-struct mlxsw_sib_port;
-
-struct mlxsw_sib {
-	struct mlxsw_sib_port **ports;
-	struct mlxsw_core *core;
-	const struct mlxsw_bus_info *bus_info;
-	u8 hw_id[ETH_ALEN];
-};
-
-struct mlxsw_sib_port {
-	struct mlxsw_sib *mlxsw_sib;
-	u8 local_port;
-	struct {
-		u8 module;
-	} mapping;
-};
-
-/* tx_v1_hdr_version
- * Tx header version.
- * Must be set to 1.
- */
-MLXSW_ITEM32(tx_v1, hdr, version, 0x00, 28, 4);
-
-/* tx_v1_hdr_ctl
- * Packet control type.
- * 0 - Ethernet control (e.g. EMADs, LACP)
- * 1 - Ethernet data
- */
-MLXSW_ITEM32(tx_v1, hdr, ctl, 0x00, 26, 2);
-
-/* tx_v1_hdr_proto
- * Packet protocol type. Must be set to 1 (Ethernet).
- */
-MLXSW_ITEM32(tx_v1, hdr, proto, 0x00, 21, 3);
-
-/* tx_v1_hdr_swid
- * Switch partition ID. Must be set to 0.
- */
-MLXSW_ITEM32(tx_v1, hdr, swid, 0x00, 12, 3);
-
-/* tx_v1_hdr_control_tclass
- * Indicates if the packet should use the control TClass and not one
- * of the data TClasses.
- */
-MLXSW_ITEM32(tx_v1, hdr, control_tclass, 0x00, 6, 1);
-
-/* tx_v1_hdr_port_mid
- * Destination local port for unicast packets.
- * Destination multicast ID for multicast packets.
- *
- * Control packets are directed to a specific egress port, while data
- * packets are transmitted through the CPU port (0) into the switch partition,
- * where forwarding rules are applied.
- */
-MLXSW_ITEM32(tx_v1, hdr, port_mid, 0x04, 16, 16);
-
-/* tx_v1_hdr_type
- * 0 - Data packets
- * 6 - Control packets
- */
-MLXSW_ITEM32(tx_v1, hdr, type, 0x0C, 0, 4);
-
-static void
-mlxsw_sib_tx_v1_hdr_construct(struct sk_buff *skb,
-			      const struct mlxsw_tx_info *tx_info)
-{
-	char *txhdr = skb_push(skb, MLXSW_TXHDR_LEN);
-
-	memset(txhdr, 0, MLXSW_TXHDR_LEN);
-
-	mlxsw_tx_v1_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_1);
-	mlxsw_tx_v1_hdr_ctl_set(txhdr, MLXSW_TXHDR_ETH_CTL);
-	mlxsw_tx_v1_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH);
-	mlxsw_tx_v1_hdr_swid_set(txhdr, 0);
-	mlxsw_tx_v1_hdr_control_tclass_set(txhdr, 1);
-	mlxsw_tx_v1_hdr_port_mid_set(txhdr, tx_info->local_port);
-	mlxsw_tx_v1_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL);
-}
-
-static int mlxsw_sib_hw_id_get(struct mlxsw_sib *mlxsw_sib)
-{
-	char spad_pl[MLXSW_REG_SPAD_LEN] = {0};
-	int err;
-
-	err = mlxsw_reg_query(mlxsw_sib->core, MLXSW_REG(spad), spad_pl);
-	if (err)
-		return err;
-	mlxsw_reg_spad_base_mac_memcpy_from(spad_pl, mlxsw_sib->hw_id);
-	return 0;
-}
-
-static int
-mlxsw_sib_port_admin_status_set(struct mlxsw_sib_port *mlxsw_sib_port,
-				bool is_up)
-{
-	struct mlxsw_sib *mlxsw_sib = mlxsw_sib_port->mlxsw_sib;
-	char paos_pl[MLXSW_REG_PAOS_LEN];
-
-	mlxsw_reg_paos_pack(paos_pl, mlxsw_sib_port->local_port,
-			    is_up ? MLXSW_PORT_ADMIN_STATUS_UP :
-			    MLXSW_PORT_ADMIN_STATUS_DOWN);
-	return mlxsw_reg_write(mlxsw_sib->core, MLXSW_REG(paos), paos_pl);
-}
-
-static int mlxsw_sib_port_mtu_set(struct mlxsw_sib_port *mlxsw_sib_port,
-				  u16 mtu)
-{
-	struct mlxsw_sib *mlxsw_sib = mlxsw_sib_port->mlxsw_sib;
-	char pmtu_pl[MLXSW_REG_PMTU_LEN];
-	int max_mtu;
-	int err;
-
-	mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sib_port->local_port, 0);
-	err = mlxsw_reg_query(mlxsw_sib->core, MLXSW_REG(pmtu), pmtu_pl);
-	if (err)
-		return err;
-	max_mtu = mlxsw_reg_pmtu_max_mtu_get(pmtu_pl);
-
-	if (mtu > max_mtu)
-		return -EINVAL;
-
-	mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sib_port->local_port, mtu);
-	return mlxsw_reg_write(mlxsw_sib->core, MLXSW_REG(pmtu), pmtu_pl);
-}
-
-static int mlxsw_sib_port_set(struct mlxsw_sib_port *mlxsw_sib_port, u8 port)
-{
-	struct mlxsw_sib *mlxsw_sib = mlxsw_sib_port->mlxsw_sib;
-	char plib_pl[MLXSW_REG_PLIB_LEN] = {0};
-	int err;
-
-	mlxsw_reg_plib_local_port_set(plib_pl, mlxsw_sib_port->local_port);
-	mlxsw_reg_plib_ib_port_set(plib_pl, port);
-	err = mlxsw_reg_write(mlxsw_sib->core, MLXSW_REG(plib), plib_pl);
-	return err;
-}
-
-static int mlxsw_sib_port_swid_set(struct mlxsw_sib_port *mlxsw_sib_port,
-				   u8 swid)
-{
-	struct mlxsw_sib *mlxsw_sib = mlxsw_sib_port->mlxsw_sib;
-	char pspa_pl[MLXSW_REG_PSPA_LEN];
-
-	mlxsw_reg_pspa_pack(pspa_pl, swid, mlxsw_sib_port->local_port);
-	return mlxsw_reg_write(mlxsw_sib->core, MLXSW_REG(pspa), pspa_pl);
-}
-
-static int mlxsw_sib_port_module_info_get(struct mlxsw_sib *mlxsw_sib,
-					  u8 local_port, u8 *p_module,
-					  u8 *p_width)
-{
-	char pmlp_pl[MLXSW_REG_PMLP_LEN];
-	int err;
-
-	mlxsw_reg_pmlp_pack(pmlp_pl, local_port);
-	err = mlxsw_reg_query(mlxsw_sib->core, MLXSW_REG(pmlp), pmlp_pl);
-	if (err)
-		return err;
-	*p_module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0);
-	*p_width = mlxsw_reg_pmlp_width_get(pmlp_pl);
-	return 0;
-}
-
-static int mlxsw_sib_port_speed_set(struct mlxsw_sib_port *mlxsw_sib_port,
-				    u16 speed, u16 width)
-{
-	struct mlxsw_sib *mlxsw_sib = mlxsw_sib_port->mlxsw_sib;
-	char ptys_pl[MLXSW_REG_PTYS_LEN];
-
-	mlxsw_reg_ptys_ib_pack(ptys_pl, mlxsw_sib_port->local_port, speed,
-			       width);
-	return mlxsw_reg_write(mlxsw_sib->core, MLXSW_REG(ptys), ptys_pl);
-}
-
-static bool mlxsw_sib_port_created(struct mlxsw_sib *mlxsw_sib, u8 local_port)
-{
-	return mlxsw_sib->ports[local_port] != NULL;
-}
-
-static int __mlxsw_sib_port_create(struct mlxsw_sib *mlxsw_sib, u8 local_port,
-				   u8 module, u8 width)
-{
-	struct mlxsw_sib_port *mlxsw_sib_port;
-	int err;
-
-	mlxsw_sib_port = kzalloc(sizeof(*mlxsw_sib_port), GFP_KERNEL);
-	if (!mlxsw_sib_port)
-		return -ENOMEM;
-	mlxsw_sib_port->mlxsw_sib = mlxsw_sib;
-	mlxsw_sib_port->local_port = local_port;
-	mlxsw_sib_port->mapping.module = module;
-
-	err = mlxsw_sib_port_swid_set(mlxsw_sib_port, 0);
-	if (err) {
-		dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to set SWID\n",
-			mlxsw_sib_port->local_port);
-		goto err_port_swid_set;
-	}
-
-	/* Expose the IB port number as it's front panel name */
-	err = mlxsw_sib_port_set(mlxsw_sib_port, module + 1);
-	if (err) {
-		dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to set IB port\n",
-			mlxsw_sib_port->local_port);
-		goto err_port_ib_set;
-	}
-
-	/* Supports all speeds from SDR to FDR (bitmask) and support bus width
-	 * of 1x, 2x and 4x (3 bits bitmask)
-	 */
-	err = mlxsw_sib_port_speed_set(mlxsw_sib_port,
-				       MLXSW_REG_PTYS_IB_SPEED_EDR - 1,
-				       BIT(3) - 1);
-	if (err) {
-		dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to set speed\n",
-			mlxsw_sib_port->local_port);
-		goto err_port_speed_set;
-	}
-
-	/* Change to the maximum MTU the device supports, the SMA will take
-	 * care of the active MTU
-	 */
-	err = mlxsw_sib_port_mtu_set(mlxsw_sib_port, MLXSW_IB_DEFAULT_MTU);
-	if (err) {
-		dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to set MTU\n",
-			mlxsw_sib_port->local_port);
-		goto err_port_mtu_set;
-	}
-
-	err = mlxsw_sib_port_admin_status_set(mlxsw_sib_port, true);
-	if (err) {
-		dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to change admin state to UP\n",
-			mlxsw_sib_port->local_port);
-		goto err_port_admin_set;
-	}
-
-	mlxsw_core_port_ib_set(mlxsw_sib->core, mlxsw_sib_port->local_port,
-			       mlxsw_sib_port);
-	mlxsw_sib->ports[local_port] = mlxsw_sib_port;
-	return 0;
-
-err_port_admin_set:
-err_port_mtu_set:
-err_port_speed_set:
-err_port_ib_set:
-	mlxsw_sib_port_swid_set(mlxsw_sib_port, MLXSW_PORT_SWID_DISABLED_PORT);
-err_port_swid_set:
-	kfree(mlxsw_sib_port);
-	return err;
-}
-
-static int mlxsw_sib_port_create(struct mlxsw_sib *mlxsw_sib, u8 local_port,
-				 u8 module, u8 width)
-{
-	int err;
-
-	err = mlxsw_core_port_init(mlxsw_sib->core, local_port,
-				   module + 1, false, 0, false, 0,
-				   mlxsw_sib->hw_id, sizeof(mlxsw_sib->hw_id));
-	if (err) {
-		dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to init core port\n",
-			local_port);
-		return err;
-	}
-	err = __mlxsw_sib_port_create(mlxsw_sib, local_port, module, width);
-	if (err)
-		goto err_port_create;
-
-	return 0;
-
-err_port_create:
-	mlxsw_core_port_fini(mlxsw_sib->core, local_port);
-	return err;
-}
-
-static void __mlxsw_sib_port_remove(struct mlxsw_sib *mlxsw_sib, u8 local_port)
-{
-	struct mlxsw_sib_port *mlxsw_sib_port = mlxsw_sib->ports[local_port];
-
-	mlxsw_core_port_clear(mlxsw_sib->core, local_port, mlxsw_sib);
-	mlxsw_sib->ports[local_port] = NULL;
-	mlxsw_sib_port_admin_status_set(mlxsw_sib_port, false);
-	mlxsw_sib_port_swid_set(mlxsw_sib_port, MLXSW_PORT_SWID_DISABLED_PORT);
-	kfree(mlxsw_sib_port);
-}
-
-static void mlxsw_sib_port_remove(struct mlxsw_sib *mlxsw_sib, u8 local_port)
-{
-	__mlxsw_sib_port_remove(mlxsw_sib, local_port);
-	mlxsw_core_port_fini(mlxsw_sib->core, local_port);
-}
-
-static void mlxsw_sib_ports_remove(struct mlxsw_sib *mlxsw_sib)
-{
-	int i;
-
-	for (i = 1; i < MLXSW_PORT_MAX_IB_PORTS; i++)
-		if (mlxsw_sib_port_created(mlxsw_sib, i))
-			mlxsw_sib_port_remove(mlxsw_sib, i);
-	kfree(mlxsw_sib->ports);
-}
-
-static int mlxsw_sib_ports_create(struct mlxsw_sib *mlxsw_sib)
-{
-	size_t alloc_size;
-	u8 module, width;
-	int i;
-	int err;
-
-	alloc_size = sizeof(struct mlxsw_sib_port *) * MLXSW_PORT_MAX_IB_PORTS;
-	mlxsw_sib->ports = kzalloc(alloc_size, GFP_KERNEL);
-	if (!mlxsw_sib->ports)
-		return -ENOMEM;
-
-	for (i = 1; i < MLXSW_PORT_MAX_IB_PORTS; i++) {
-		err = mlxsw_sib_port_module_info_get(mlxsw_sib, i, &module,
-						     &width);
-		if (err)
-			goto err_port_module_info_get;
-		if (!width)
-			continue;
-		err = mlxsw_sib_port_create(mlxsw_sib, i, module, width);
-		if (err)
-			goto err_port_create;
-	}
-	return 0;
-
-err_port_create:
-err_port_module_info_get:
-	for (i--; i >= 1; i--)
-		if (mlxsw_sib_port_created(mlxsw_sib, i))
-			mlxsw_sib_port_remove(mlxsw_sib, i);
-	kfree(mlxsw_sib->ports);
-	return err;
-}
-
-static void
-mlxsw_sib_pude_ib_event_func(struct mlxsw_sib_port *mlxsw_sib_port,
-			     enum mlxsw_reg_pude_oper_status status)
-{
-	if (status == MLXSW_PORT_OPER_STATUS_UP)
-		pr_info("ib link for port %d - up\n",
-			mlxsw_sib_port->mapping.module + 1);
-	else
-		pr_info("ib link for port %d - down\n",
-			mlxsw_sib_port->mapping.module + 1);
-}
-
-static void mlxsw_sib_pude_event_func(const struct mlxsw_reg_info *reg,
-				      char *pude_pl, void *priv)
-{
-	struct mlxsw_sib *mlxsw_sib = priv;
-	struct mlxsw_sib_port *mlxsw_sib_port;
-	enum mlxsw_reg_pude_oper_status status;
-	u8 local_port;
-
-	local_port = mlxsw_reg_pude_local_port_get(pude_pl);
-	mlxsw_sib_port = mlxsw_sib->ports[local_port];
-	if (!mlxsw_sib_port) {
-		dev_warn(mlxsw_sib->bus_info->dev, "Port %d: Link event received for non-existent port\n",
-			 local_port);
-		return;
-	}
-
-	status = mlxsw_reg_pude_oper_status_get(pude_pl);
-	mlxsw_sib_pude_ib_event_func(mlxsw_sib_port, status);
-}
-
-static const struct mlxsw_listener mlxsw_sib_listener[] = {
-	MLXSW_EVENTL(mlxsw_sib_pude_event_func, PUDE, EMAD),
-};
-
-static int mlxsw_sib_taps_init(struct mlxsw_sib *mlxsw_sib)
-{
-	int i;
-	int err;
-
-	for (i = 0; i < ARRAY_SIZE(mlxsw_sib_listener); i++) {
-		err = mlxsw_core_trap_register(mlxsw_sib->core,
-					       &mlxsw_sib_listener[i],
-					       mlxsw_sib);
-		if (err)
-			goto err_rx_listener_register;
-	}
-
-	return 0;
-
-err_rx_listener_register:
-	for (i--; i >= 0; i--) {
-		mlxsw_core_trap_unregister(mlxsw_sib->core,
-					   &mlxsw_sib_listener[i],
-					   mlxsw_sib);
-	}
-
-	return err;
-}
-
-static void mlxsw_sib_traps_fini(struct mlxsw_sib *mlxsw_sib)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(mlxsw_sib_listener); i++) {
-		mlxsw_core_trap_unregister(mlxsw_sib->core,
-					   &mlxsw_sib_listener[i], mlxsw_sib);
-	}
-}
-
-static int mlxsw_sib_basic_trap_groups_set(struct mlxsw_core *mlxsw_core)
-{
-	char htgt_pl[MLXSW_REG_HTGT_LEN];
-
-	mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_EMAD,
-			    MLXSW_REG_HTGT_INVALID_POLICER,
-			    MLXSW_REG_HTGT_DEFAULT_PRIORITY,
-			    MLXSW_REG_HTGT_DEFAULT_TC);
-	mlxsw_reg_htgt_swid_set(htgt_pl, MLXSW_PORT_SWID_ALL_SWIDS);
-	mlxsw_reg_htgt_local_path_rdq_set(htgt_pl,
-					MLXSW_REG_HTGT_LOCAL_PATH_RDQ_SIB_EMAD);
-	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl);
-}
-
-static int mlxsw_sib_init(struct mlxsw_core *mlxsw_core,
-			  const struct mlxsw_bus_info *mlxsw_bus_info,
-			  struct netlink_ext_ack *extack)
-{
-	struct mlxsw_sib *mlxsw_sib = mlxsw_core_driver_priv(mlxsw_core);
-	int err;
-
-	mlxsw_sib->core = mlxsw_core;
-	mlxsw_sib->bus_info = mlxsw_bus_info;
-
-	err = mlxsw_sib_hw_id_get(mlxsw_sib);
-	if (err) {
-		dev_err(mlxsw_sib->bus_info->dev, "Failed to get switch HW ID\n");
-		return err;
-	}
-
-	err = mlxsw_sib_ports_create(mlxsw_sib);
-	if (err) {
-		dev_err(mlxsw_sib->bus_info->dev, "Failed to create ports\n");
-		return err;
-	}
-
-	err = mlxsw_sib_taps_init(mlxsw_sib);
-	if (err) {
-		dev_err(mlxsw_sib->bus_info->dev, "Failed to set traps\n");
-		goto err_traps_init_err;
-	}
-
-	return 0;
-
-err_traps_init_err:
-	mlxsw_sib_ports_remove(mlxsw_sib);
-	return err;
-}
-
-static void mlxsw_sib_fini(struct mlxsw_core *mlxsw_core)
-{
-	struct mlxsw_sib *mlxsw_sib = mlxsw_core_driver_priv(mlxsw_core);
-
-	mlxsw_sib_traps_fini(mlxsw_sib);
-	mlxsw_sib_ports_remove(mlxsw_sib);
-}
-
-static const struct mlxsw_config_profile mlxsw_sib_config_profile = {
-	.used_max_system_port		= 1,
-	.max_system_port		= 48000,
-	.used_max_ib_mc			= 1,
-	.max_ib_mc			= 27,
-	.used_max_pkey			= 1,
-	.max_pkey			= 32,
-	.swid_config			= {
-		{
-			.used_type	= 1,
-			.type		= MLXSW_PORT_SWID_TYPE_IB,
-		}
-	},
-};
-
-static struct mlxsw_driver mlxsw_sib_driver = {
-	.kind			= mlxsw_sib_driver_name,
-	.priv_size		= sizeof(struct mlxsw_sib),
-	.init			= mlxsw_sib_init,
-	.fini			= mlxsw_sib_fini,
-	.basic_trap_groups_set	= mlxsw_sib_basic_trap_groups_set,
-	.txhdr_construct	= mlxsw_sib_tx_v1_hdr_construct,
-	.txhdr_len		= MLXSW_TXHDR_LEN,
-	.profile		= &mlxsw_sib_config_profile,
-};
-
-static struct mlxsw_driver mlxsw_sib2_driver = {
-	.kind			= mlxsw_sib2_driver_name,
-	.priv_size		= sizeof(struct mlxsw_sib),
-	.init			= mlxsw_sib_init,
-	.fini			= mlxsw_sib_fini,
-	.basic_trap_groups_set	= mlxsw_sib_basic_trap_groups_set,
-	.txhdr_construct	= mlxsw_sib_tx_v1_hdr_construct,
-	.txhdr_len		= MLXSW_TXHDR_LEN,
-	.profile		= &mlxsw_sib_config_profile,
-};
-
-static const struct pci_device_id mlxsw_sib_pci_id_table[] = {
-	{PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SWITCHIB), 0},
-	{0, },
-};
-
-static struct pci_driver mlxsw_sib_pci_driver = {
-	.name = mlxsw_sib_driver_name,
-	.id_table = mlxsw_sib_pci_id_table,
-};
-
-static const struct pci_device_id mlxsw_sib2_pci_id_table[] = {
-	{PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SWITCHIB2), 0},
-	{0, },
-};
-
-static struct pci_driver mlxsw_sib2_pci_driver = {
-	.name = mlxsw_sib2_driver_name,
-	.id_table = mlxsw_sib2_pci_id_table,
-};
-
-static int __init mlxsw_sib_module_init(void)
-{
-	int err;
-
-	err = mlxsw_core_driver_register(&mlxsw_sib_driver);
-	if (err)
-		return err;
-
-	err = mlxsw_core_driver_register(&mlxsw_sib2_driver);
-	if (err)
-		goto err_sib2_driver_register;
-
-	err = mlxsw_pci_driver_register(&mlxsw_sib_pci_driver);
-	if (err)
-		goto err_sib_pci_driver_register;
-
-	err = mlxsw_pci_driver_register(&mlxsw_sib2_pci_driver);
-	if (err)
-		goto err_sib2_pci_driver_register;
-
-	return 0;
-
-err_sib2_pci_driver_register:
-	mlxsw_pci_driver_unregister(&mlxsw_sib_pci_driver);
-err_sib_pci_driver_register:
-	mlxsw_core_driver_unregister(&mlxsw_sib2_driver);
-err_sib2_driver_register:
-	mlxsw_core_driver_unregister(&mlxsw_sib_driver);
-	return err;
-}
-
-static void __exit mlxsw_sib_module_exit(void)
-{
-	mlxsw_pci_driver_unregister(&mlxsw_sib2_pci_driver);
-	mlxsw_pci_driver_unregister(&mlxsw_sib_pci_driver);
-	mlxsw_core_driver_unregister(&mlxsw_sib2_driver);
-	mlxsw_core_driver_unregister(&mlxsw_sib_driver);
-}
-
-module_init(mlxsw_sib_module_init);
-module_exit(mlxsw_sib_module_exit);
-
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_AUTHOR("Elad Raz <eladr@@mellanox.com>");
-MODULE_DESCRIPTION("Mellanox SwitchIB and SwitchIB-2 driver");
-MODULE_ALIAS("mlxsw_switchib2");
-MODULE_DEVICE_TABLE(pci, mlxsw_sib_pci_id_table);
-MODULE_DEVICE_TABLE(pci, mlxsw_sib2_pci_id_table);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
deleted file mode 100644
index 131b2a53d261..000000000000
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ /dev/null
@@ -1,1691 +0,0 @@
-// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
-/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/pci.h>
-#include <linux/netdevice.h>
-#include <linux/ethtool.h>
-#include <linux/etherdevice.h>
-#include <linux/slab.h>
-#include <linux/device.h>
-#include <linux/skbuff.h>
-#include <linux/if_vlan.h>
-
-#include "pci.h"
-#include "core.h"
-#include "reg.h"
-#include "port.h"
-#include "trap.h"
-#include "txheader.h"
-#include "ib.h"
-
-static const char mlxsw_sx_driver_name[] = "mlxsw_switchx2";
-static const char mlxsw_sx_driver_version[] = "1.0";
-
-struct mlxsw_sx_port;
-
-struct mlxsw_sx {
-	struct mlxsw_sx_port **ports;
-	struct mlxsw_core *core;
-	const struct mlxsw_bus_info *bus_info;
-	u8 hw_id[ETH_ALEN];
-};
-
-struct mlxsw_sx_port_pcpu_stats {
-	u64			rx_packets;
-	u64			rx_bytes;
-	u64			tx_packets;
-	u64			tx_bytes;
-	struct u64_stats_sync	syncp;
-	u32			tx_dropped;
-};
-
-struct mlxsw_sx_port {
-	struct net_device *dev;
-	struct mlxsw_sx_port_pcpu_stats __percpu *pcpu_stats;
-	struct mlxsw_sx *mlxsw_sx;
-	u8 local_port;
-	struct {
-		u8 module;
-	} mapping;
-};
-
-/* tx_hdr_version
- * Tx header version.
- * Must be set to 0.
- */
-MLXSW_ITEM32(tx, hdr, version, 0x00, 28, 4);
-
-/* tx_hdr_ctl
- * Packet control type.
- * 0 - Ethernet control (e.g. EMADs, LACP)
- * 1 - Ethernet data
- */
-MLXSW_ITEM32(tx, hdr, ctl, 0x00, 26, 2);
-
-/* tx_hdr_proto
- * Packet protocol type. Must be set to 1 (Ethernet).
- */
-MLXSW_ITEM32(tx, hdr, proto, 0x00, 21, 3);
-
-/* tx_hdr_etclass
- * Egress TClass to be used on the egress device on the egress port.
- * The MSB is specified in the 'ctclass3' field.
- * Range is 0-15, where 15 is the highest priority.
- */
-MLXSW_ITEM32(tx, hdr, etclass, 0x00, 18, 3);
-
-/* tx_hdr_swid
- * Switch partition ID.
- */
-MLXSW_ITEM32(tx, hdr, swid, 0x00, 12, 3);
-
-/* tx_hdr_port_mid
- * Destination local port for unicast packets.
- * Destination multicast ID for multicast packets.
- *
- * Control packets are directed to a specific egress port, while data
- * packets are transmitted through the CPU port (0) into the switch partition,
- * where forwarding rules are applied.
- */
-MLXSW_ITEM32(tx, hdr, port_mid, 0x04, 16, 16);
-
-/* tx_hdr_ctclass3
- * See field 'etclass'.
- */
-MLXSW_ITEM32(tx, hdr, ctclass3, 0x04, 14, 1);
-
-/* tx_hdr_rdq
- * RDQ for control packets sent to remote CPU.
- * Must be set to 0x1F for EMADs, otherwise 0.
- */
-MLXSW_ITEM32(tx, hdr, rdq, 0x04, 9, 5);
-
-/* tx_hdr_cpu_sig
- * Signature control for packets going to CPU. Must be set to 0.
- */
-MLXSW_ITEM32(tx, hdr, cpu_sig, 0x04, 0, 9);
-
-/* tx_hdr_sig
- * Stacking protocl signature. Must be set to 0xE0E0.
- */
-MLXSW_ITEM32(tx, hdr, sig, 0x0C, 16, 16);
-
-/* tx_hdr_stclass
- * Stacking TClass.
- */
-MLXSW_ITEM32(tx, hdr, stclass, 0x0C, 13, 3);
-
-/* tx_hdr_emad
- * EMAD bit. Must be set for EMADs.
- */
-MLXSW_ITEM32(tx, hdr, emad, 0x0C, 5, 1);
-
-/* tx_hdr_type
- * 0 - Data packets
- * 6 - Control packets
- */
-MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4);
-
-static void mlxsw_sx_txhdr_construct(struct sk_buff *skb,
-				     const struct mlxsw_tx_info *tx_info)
-{
-	char *txhdr = skb_push(skb, MLXSW_TXHDR_LEN);
-	bool is_emad = tx_info->is_emad;
-
-	memset(txhdr, 0, MLXSW_TXHDR_LEN);
-
-	/* We currently set default values for the egress tclass (QoS). */
-	mlxsw_tx_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_0);
-	mlxsw_tx_hdr_ctl_set(txhdr, MLXSW_TXHDR_ETH_CTL);
-	mlxsw_tx_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH);
-	mlxsw_tx_hdr_etclass_set(txhdr, is_emad ? MLXSW_TXHDR_ETCLASS_6 :
-						  MLXSW_TXHDR_ETCLASS_5);
-	mlxsw_tx_hdr_swid_set(txhdr, 0);
-	mlxsw_tx_hdr_port_mid_set(txhdr, tx_info->local_port);
-	mlxsw_tx_hdr_ctclass3_set(txhdr, MLXSW_TXHDR_CTCLASS3);
-	mlxsw_tx_hdr_rdq_set(txhdr, is_emad ? MLXSW_TXHDR_RDQ_EMAD :
-					      MLXSW_TXHDR_RDQ_OTHER);
-	mlxsw_tx_hdr_cpu_sig_set(txhdr, MLXSW_TXHDR_CPU_SIG);
-	mlxsw_tx_hdr_sig_set(txhdr, MLXSW_TXHDR_SIG);
-	mlxsw_tx_hdr_stclass_set(txhdr, MLXSW_TXHDR_STCLASS_NONE);
-	mlxsw_tx_hdr_emad_set(txhdr, is_emad ? MLXSW_TXHDR_EMAD :
-					       MLXSW_TXHDR_NOT_EMAD);
-	mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL);
-}
-
-static int mlxsw_sx_port_admin_status_set(struct mlxsw_sx_port *mlxsw_sx_port,
-					  bool is_up)
-{
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-	char paos_pl[MLXSW_REG_PAOS_LEN];
-
-	mlxsw_reg_paos_pack(paos_pl, mlxsw_sx_port->local_port,
-			    is_up ? MLXSW_PORT_ADMIN_STATUS_UP :
-			    MLXSW_PORT_ADMIN_STATUS_DOWN);
-	return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(paos), paos_pl);
-}
-
-static int mlxsw_sx_port_oper_status_get(struct mlxsw_sx_port *mlxsw_sx_port,
-					 bool *p_is_up)
-{
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-	char paos_pl[MLXSW_REG_PAOS_LEN];
-	u8 oper_status;
-	int err;
-
-	mlxsw_reg_paos_pack(paos_pl, mlxsw_sx_port->local_port, 0);
-	err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(paos), paos_pl);
-	if (err)
-		return err;
-	oper_status = mlxsw_reg_paos_oper_status_get(paos_pl);
-	*p_is_up = oper_status == MLXSW_PORT_ADMIN_STATUS_UP;
-	return 0;
-}
-
-static int __mlxsw_sx_port_mtu_set(struct mlxsw_sx_port *mlxsw_sx_port,
-				   u16 mtu)
-{
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-	char pmtu_pl[MLXSW_REG_PMTU_LEN];
-	int max_mtu;
-	int err;
-
-	mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sx_port->local_port, 0);
-	err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(pmtu), pmtu_pl);
-	if (err)
-		return err;
-	max_mtu = mlxsw_reg_pmtu_max_mtu_get(pmtu_pl);
-
-	if (mtu > max_mtu)
-		return -EINVAL;
-
-	mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sx_port->local_port, mtu);
-	return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(pmtu), pmtu_pl);
-}
-
-static int mlxsw_sx_port_mtu_eth_set(struct mlxsw_sx_port *mlxsw_sx_port,
-				     u16 mtu)
-{
-	mtu += MLXSW_TXHDR_LEN + ETH_HLEN;
-	return __mlxsw_sx_port_mtu_set(mlxsw_sx_port, mtu);
-}
-
-static int mlxsw_sx_port_mtu_ib_set(struct mlxsw_sx_port *mlxsw_sx_port,
-				    u16 mtu)
-{
-	return __mlxsw_sx_port_mtu_set(mlxsw_sx_port, mtu);
-}
-
-static int mlxsw_sx_port_ib_port_set(struct mlxsw_sx_port *mlxsw_sx_port,
-				     u8 ib_port)
-{
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-	char plib_pl[MLXSW_REG_PLIB_LEN] = {0};
-	int err;
-
-	mlxsw_reg_plib_local_port_set(plib_pl, mlxsw_sx_port->local_port);
-	mlxsw_reg_plib_ib_port_set(plib_pl, ib_port);
-	err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(plib), plib_pl);
-	return err;
-}
-
-static int mlxsw_sx_port_swid_set(struct mlxsw_sx_port *mlxsw_sx_port, u8 swid)
-{
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-	char pspa_pl[MLXSW_REG_PSPA_LEN];
-
-	mlxsw_reg_pspa_pack(pspa_pl, swid, mlxsw_sx_port->local_port);
-	return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(pspa), pspa_pl);
-}
-
-static int
-mlxsw_sx_port_system_port_mapping_set(struct mlxsw_sx_port *mlxsw_sx_port)
-{
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-	char sspr_pl[MLXSW_REG_SSPR_LEN];
-
-	mlxsw_reg_sspr_pack(sspr_pl, mlxsw_sx_port->local_port);
-	return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sspr), sspr_pl);
-}
-
-static int mlxsw_sx_port_module_info_get(struct mlxsw_sx *mlxsw_sx,
-					 u8 local_port, u8 *p_module,
-					 u8 *p_width)
-{
-	char pmlp_pl[MLXSW_REG_PMLP_LEN];
-	int err;
-
-	mlxsw_reg_pmlp_pack(pmlp_pl, local_port);
-	err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(pmlp), pmlp_pl);
-	if (err)
-		return err;
-	*p_module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0);
-	*p_width = mlxsw_reg_pmlp_width_get(pmlp_pl);
-	return 0;
-}
-
-static int mlxsw_sx_port_open(struct net_device *dev)
-{
-	struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
-	int err;
-
-	err = mlxsw_sx_port_admin_status_set(mlxsw_sx_port, true);
-	if (err)
-		return err;
-	netif_start_queue(dev);
-	return 0;
-}
-
-static int mlxsw_sx_port_stop(struct net_device *dev)
-{
-	struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
-
-	netif_stop_queue(dev);
-	return mlxsw_sx_port_admin_status_set(mlxsw_sx_port, false);
-}
-
-static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb,
-				      struct net_device *dev)
-{
-	struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-	struct mlxsw_sx_port_pcpu_stats *pcpu_stats;
-	const struct mlxsw_tx_info tx_info = {
-		.local_port = mlxsw_sx_port->local_port,
-		.is_emad = false,
-	};
-	u64 len;
-	int err;
-
-	if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) {
-		this_cpu_inc(mlxsw_sx_port->pcpu_stats->tx_dropped);
-		dev_kfree_skb_any(skb);
-		return NETDEV_TX_OK;
-	}
-
-	memset(skb->cb, 0, sizeof(struct mlxsw_skb_cb));
-
-	if (mlxsw_core_skb_transmit_busy(mlxsw_sx->core, &tx_info))
-		return NETDEV_TX_BUSY;
-
-	mlxsw_sx_txhdr_construct(skb, &tx_info);
-	/* TX header is consumed by HW on the way so we shouldn't count its
-	 * bytes as being sent.
-	 */
-	len = skb->len - MLXSW_TXHDR_LEN;
-	/* Due to a race we might fail here because of a full queue. In that
-	 * unlikely case we simply drop the packet.
-	 */
-	err = mlxsw_core_skb_transmit(mlxsw_sx->core, skb, &tx_info);
-
-	if (!err) {
-		pcpu_stats = this_cpu_ptr(mlxsw_sx_port->pcpu_stats);
-		u64_stats_update_begin(&pcpu_stats->syncp);
-		pcpu_stats->tx_packets++;
-		pcpu_stats->tx_bytes += len;
-		u64_stats_update_end(&pcpu_stats->syncp);
-	} else {
-		this_cpu_inc(mlxsw_sx_port->pcpu_stats->tx_dropped);
-		dev_kfree_skb_any(skb);
-	}
-	return NETDEV_TX_OK;
-}
-
-static int mlxsw_sx_port_change_mtu(struct net_device *dev, int mtu)
-{
-	struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
-	int err;
-
-	err = mlxsw_sx_port_mtu_eth_set(mlxsw_sx_port, mtu);
-	if (err)
-		return err;
-	dev->mtu = mtu;
-	return 0;
-}
-
-static void
-mlxsw_sx_port_get_stats64(struct net_device *dev,
-			  struct rtnl_link_stats64 *stats)
-{
-	struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
-	struct mlxsw_sx_port_pcpu_stats *p;
-	u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
-	u32 tx_dropped = 0;
-	unsigned int start;
-	int i;
-
-	for_each_possible_cpu(i) {
-		p = per_cpu_ptr(mlxsw_sx_port->pcpu_stats, i);
-		do {
-			start = u64_stats_fetch_begin_irq(&p->syncp);
-			rx_packets	= p->rx_packets;
-			rx_bytes	= p->rx_bytes;
-			tx_packets	= p->tx_packets;
-			tx_bytes	= p->tx_bytes;
-		} while (u64_stats_fetch_retry_irq(&p->syncp, start));
-
-		stats->rx_packets	+= rx_packets;
-		stats->rx_bytes		+= rx_bytes;
-		stats->tx_packets	+= tx_packets;
-		stats->tx_bytes		+= tx_bytes;
-		/* tx_dropped is u32, updated without syncp protection. */
-		tx_dropped	+= p->tx_dropped;
-	}
-	stats->tx_dropped	= tx_dropped;
-}
-
-static struct devlink_port *
-mlxsw_sx_port_get_devlink_port(struct net_device *dev)
-{
-	struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-
-	return mlxsw_core_port_devlink_port_get(mlxsw_sx->core,
-						mlxsw_sx_port->local_port);
-}
-
-static const struct net_device_ops mlxsw_sx_port_netdev_ops = {
-	.ndo_open		= mlxsw_sx_port_open,
-	.ndo_stop		= mlxsw_sx_port_stop,
-	.ndo_start_xmit		= mlxsw_sx_port_xmit,
-	.ndo_change_mtu		= mlxsw_sx_port_change_mtu,
-	.ndo_get_stats64	= mlxsw_sx_port_get_stats64,
-	.ndo_get_devlink_port	= mlxsw_sx_port_get_devlink_port,
-};
-
-static void mlxsw_sx_port_get_drvinfo(struct net_device *dev,
-				      struct ethtool_drvinfo *drvinfo)
-{
-	struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-
-	strlcpy(drvinfo->driver, mlxsw_sx_driver_name, sizeof(drvinfo->driver));
-	strlcpy(drvinfo->version, mlxsw_sx_driver_version,
-		sizeof(drvinfo->version));
-	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
-		 "%d.%d.%d",
-		 mlxsw_sx->bus_info->fw_rev.major,
-		 mlxsw_sx->bus_info->fw_rev.minor,
-		 mlxsw_sx->bus_info->fw_rev.subminor);
-	strlcpy(drvinfo->bus_info, mlxsw_sx->bus_info->device_name,
-		sizeof(drvinfo->bus_info));
-}
-
-struct mlxsw_sx_port_hw_stats {
-	char str[ETH_GSTRING_LEN];
-	u64 (*getter)(const char *payload);
-};
-
-static const struct mlxsw_sx_port_hw_stats mlxsw_sx_port_hw_stats[] = {
-	{
-		.str = "a_frames_transmitted_ok",
-		.getter = mlxsw_reg_ppcnt_a_frames_transmitted_ok_get,
-	},
-	{
-		.str = "a_frames_received_ok",
-		.getter = mlxsw_reg_ppcnt_a_frames_received_ok_get,
-	},
-	{
-		.str = "a_frame_check_sequence_errors",
-		.getter = mlxsw_reg_ppcnt_a_frame_check_sequence_errors_get,
-	},
-	{
-		.str = "a_alignment_errors",
-		.getter = mlxsw_reg_ppcnt_a_alignment_errors_get,
-	},
-	{
-		.str = "a_octets_transmitted_ok",
-		.getter = mlxsw_reg_ppcnt_a_octets_transmitted_ok_get,
-	},
-	{
-		.str = "a_octets_received_ok",
-		.getter = mlxsw_reg_ppcnt_a_octets_received_ok_get,
-	},
-	{
-		.str = "a_multicast_frames_xmitted_ok",
-		.getter = mlxsw_reg_ppcnt_a_multicast_frames_xmitted_ok_get,
-	},
-	{
-		.str = "a_broadcast_frames_xmitted_ok",
-		.getter = mlxsw_reg_ppcnt_a_broadcast_frames_xmitted_ok_get,
-	},
-	{
-		.str = "a_multicast_frames_received_ok",
-		.getter = mlxsw_reg_ppcnt_a_multicast_frames_received_ok_get,
-	},
-	{
-		.str = "a_broadcast_frames_received_ok",
-		.getter = mlxsw_reg_ppcnt_a_broadcast_frames_received_ok_get,
-	},
-	{
-		.str = "a_in_range_length_errors",
-		.getter = mlxsw_reg_ppcnt_a_in_range_length_errors_get,
-	},
-	{
-		.str = "a_out_of_range_length_field",
-		.getter = mlxsw_reg_ppcnt_a_out_of_range_length_field_get,
-	},
-	{
-		.str = "a_frame_too_long_errors",
-		.getter = mlxsw_reg_ppcnt_a_frame_too_long_errors_get,
-	},
-	{
-		.str = "a_symbol_error_during_carrier",
-		.getter = mlxsw_reg_ppcnt_a_symbol_error_during_carrier_get,
-	},
-	{
-		.str = "a_mac_control_frames_transmitted",
-		.getter = mlxsw_reg_ppcnt_a_mac_control_frames_transmitted_get,
-	},
-	{
-		.str = "a_mac_control_frames_received",
-		.getter = mlxsw_reg_ppcnt_a_mac_control_frames_received_get,
-	},
-	{
-		.str = "a_unsupported_opcodes_received",
-		.getter = mlxsw_reg_ppcnt_a_unsupported_opcodes_received_get,
-	},
-	{
-		.str = "a_pause_mac_ctrl_frames_received",
-		.getter = mlxsw_reg_ppcnt_a_pause_mac_ctrl_frames_received_get,
-	},
-	{
-		.str = "a_pause_mac_ctrl_frames_xmitted",
-		.getter = mlxsw_reg_ppcnt_a_pause_mac_ctrl_frames_transmitted_get,
-	},
-};
-
-#define MLXSW_SX_PORT_HW_STATS_LEN ARRAY_SIZE(mlxsw_sx_port_hw_stats)
-
-static void mlxsw_sx_port_get_strings(struct net_device *dev,
-				      u32 stringset, u8 *data)
-{
-	u8 *p = data;
-	int i;
-
-	switch (stringset) {
-	case ETH_SS_STATS:
-		for (i = 0; i < MLXSW_SX_PORT_HW_STATS_LEN; i++) {
-			memcpy(p, mlxsw_sx_port_hw_stats[i].str,
-			       ETH_GSTRING_LEN);
-			p += ETH_GSTRING_LEN;
-		}
-		break;
-	}
-}
-
-static void mlxsw_sx_port_get_stats(struct net_device *dev,
-				    struct ethtool_stats *stats, u64 *data)
-{
-	struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-	char ppcnt_pl[MLXSW_REG_PPCNT_LEN];
-	int i;
-	int err;
-
-	mlxsw_reg_ppcnt_pack(ppcnt_pl, mlxsw_sx_port->local_port,
-			     MLXSW_REG_PPCNT_IEEE_8023_CNT, 0);
-	err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(ppcnt), ppcnt_pl);
-	for (i = 0; i < MLXSW_SX_PORT_HW_STATS_LEN; i++)
-		data[i] = !err ? mlxsw_sx_port_hw_stats[i].getter(ppcnt_pl) : 0;
-}
-
-static int mlxsw_sx_port_get_sset_count(struct net_device *dev, int sset)
-{
-	switch (sset) {
-	case ETH_SS_STATS:
-		return MLXSW_SX_PORT_HW_STATS_LEN;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-struct mlxsw_sx_port_link_mode {
-	u32 mask;
-	u32 supported;
-	u32 advertised;
-	u32 speed;
-};
-
-static const struct mlxsw_sx_port_link_mode mlxsw_sx_port_link_mode[] = {
-	{
-		.mask		= MLXSW_REG_PTYS_ETH_SPEED_SGMII |
-				  MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX,
-		.supported	= SUPPORTED_1000baseKX_Full,
-		.advertised	= ADVERTISED_1000baseKX_Full,
-		.speed		= 1000,
-	},
-	{
-		.mask		= MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CX4 |
-				  MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4,
-		.supported	= SUPPORTED_10000baseKX4_Full,
-		.advertised	= ADVERTISED_10000baseKX4_Full,
-		.speed		= 10000,
-	},
-	{
-		.mask		= MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KR |
-				  MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR |
-				  MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR |
-				  MLXSW_REG_PTYS_ETH_SPEED_10GBASE_ER_LR,
-		.supported	= SUPPORTED_10000baseKR_Full,
-		.advertised	= ADVERTISED_10000baseKR_Full,
-		.speed		= 10000,
-	},
-	{
-		.mask		= MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4,
-		.supported	= SUPPORTED_40000baseCR4_Full,
-		.advertised	= ADVERTISED_40000baseCR4_Full,
-		.speed		= 40000,
-	},
-	{
-		.mask		= MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4,
-		.supported	= SUPPORTED_40000baseKR4_Full,
-		.advertised	= ADVERTISED_40000baseKR4_Full,
-		.speed		= 40000,
-	},
-	{
-		.mask		= MLXSW_REG_PTYS_ETH_SPEED_40GBASE_SR4,
-		.supported	= SUPPORTED_40000baseSR4_Full,
-		.advertised	= ADVERTISED_40000baseSR4_Full,
-		.speed		= 40000,
-	},
-	{
-		.mask		= MLXSW_REG_PTYS_ETH_SPEED_40GBASE_LR4_ER4,
-		.supported	= SUPPORTED_40000baseLR4_Full,
-		.advertised	= ADVERTISED_40000baseLR4_Full,
-		.speed		= 40000,
-	},
-	{
-		.mask		= MLXSW_REG_PTYS_ETH_SPEED_25GBASE_CR |
-				  MLXSW_REG_PTYS_ETH_SPEED_25GBASE_KR |
-				  MLXSW_REG_PTYS_ETH_SPEED_25GBASE_SR,
-		.speed		= 25000,
-	},
-	{
-		.mask		= MLXSW_REG_PTYS_ETH_SPEED_50GBASE_KR4 |
-				  MLXSW_REG_PTYS_ETH_SPEED_50GBASE_CR2 |
-				  MLXSW_REG_PTYS_ETH_SPEED_50GBASE_KR2,
-		.speed		= 50000,
-	},
-	{
-		.mask		= MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4 |
-				  MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 |
-				  MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 |
-				  MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4,
-		.speed		= 100000,
-	},
-};
-
-#define MLXSW_SX_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sx_port_link_mode)
-#define MLXSW_SX_PORT_BASE_SPEED 10000 /* Mb/s */
-
-static u32 mlxsw_sx_from_ptys_supported_port(u32 ptys_eth_proto)
-{
-	if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR |
-			      MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR |
-			      MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_40GBASE_SR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_SGMII))
-		return SUPPORTED_FIBRE;
-
-	if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KR |
-			      MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX))
-		return SUPPORTED_Backplane;
-	return 0;
-}
-
-static u32 mlxsw_sx_from_ptys_supported_link(u32 ptys_eth_proto)
-{
-	u32 modes = 0;
-	int i;
-
-	for (i = 0; i < MLXSW_SX_PORT_LINK_MODE_LEN; i++) {
-		if (ptys_eth_proto & mlxsw_sx_port_link_mode[i].mask)
-			modes |= mlxsw_sx_port_link_mode[i].supported;
-	}
-	return modes;
-}
-
-static u32 mlxsw_sx_from_ptys_advert_link(u32 ptys_eth_proto)
-{
-	u32 modes = 0;
-	int i;
-
-	for (i = 0; i < MLXSW_SX_PORT_LINK_MODE_LEN; i++) {
-		if (ptys_eth_proto & mlxsw_sx_port_link_mode[i].mask)
-			modes |= mlxsw_sx_port_link_mode[i].advertised;
-	}
-	return modes;
-}
-
-static void mlxsw_sx_from_ptys_speed_duplex(bool carrier_ok, u32 ptys_eth_proto,
-					    struct ethtool_link_ksettings *cmd)
-{
-	u32 speed = SPEED_UNKNOWN;
-	u8 duplex = DUPLEX_UNKNOWN;
-	int i;
-
-	if (!carrier_ok)
-		goto out;
-
-	for (i = 0; i < MLXSW_SX_PORT_LINK_MODE_LEN; i++) {
-		if (ptys_eth_proto & mlxsw_sx_port_link_mode[i].mask) {
-			speed = mlxsw_sx_port_link_mode[i].speed;
-			duplex = DUPLEX_FULL;
-			break;
-		}
-	}
-out:
-	cmd->base.speed = speed;
-	cmd->base.duplex = duplex;
-}
-
-static u8 mlxsw_sx_port_connector_port(u32 ptys_eth_proto)
-{
-	if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR |
-			      MLXSW_REG_PTYS_ETH_SPEED_40GBASE_SR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_SGMII))
-		return PORT_FIBRE;
-
-	if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR |
-			      MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4))
-		return PORT_DA;
-
-	if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KR |
-			      MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4))
-		return PORT_NONE;
-
-	return PORT_OTHER;
-}
-
-static int
-mlxsw_sx_port_get_link_ksettings(struct net_device *dev,
-				 struct ethtool_link_ksettings *cmd)
-{
-	struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-	char ptys_pl[MLXSW_REG_PTYS_LEN];
-	u32 eth_proto_cap;
-	u32 eth_proto_admin;
-	u32 eth_proto_oper;
-	u32 supported, advertising, lp_advertising;
-	int err;
-
-	mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sx_port->local_port, 0, false);
-	err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(ptys), ptys_pl);
-	if (err) {
-		netdev_err(dev, "Failed to get proto");
-		return err;
-	}
-	mlxsw_reg_ptys_eth_unpack(ptys_pl, &eth_proto_cap,
-				  &eth_proto_admin, &eth_proto_oper);
-
-	supported = mlxsw_sx_from_ptys_supported_port(eth_proto_cap) |
-			 mlxsw_sx_from_ptys_supported_link(eth_proto_cap) |
-			 SUPPORTED_Pause | SUPPORTED_Asym_Pause;
-	advertising = mlxsw_sx_from_ptys_advert_link(eth_proto_admin);
-	mlxsw_sx_from_ptys_speed_duplex(netif_carrier_ok(dev),
-					eth_proto_oper, cmd);
-
-	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
-	cmd->base.port = mlxsw_sx_port_connector_port(eth_proto_oper);
-	lp_advertising = mlxsw_sx_from_ptys_advert_link(eth_proto_oper);
-
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
-						supported);
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
-						advertising);
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.lp_advertising,
-						lp_advertising);
-
-	return 0;
-}
-
-static u32 mlxsw_sx_to_ptys_advert_link(u32 advertising)
-{
-	u32 ptys_proto = 0;
-	int i;
-
-	for (i = 0; i < MLXSW_SX_PORT_LINK_MODE_LEN; i++) {
-		if (advertising & mlxsw_sx_port_link_mode[i].advertised)
-			ptys_proto |= mlxsw_sx_port_link_mode[i].mask;
-	}
-	return ptys_proto;
-}
-
-static u32 mlxsw_sx_to_ptys_speed(u32 speed)
-{
-	u32 ptys_proto = 0;
-	int i;
-
-	for (i = 0; i < MLXSW_SX_PORT_LINK_MODE_LEN; i++) {
-		if (speed == mlxsw_sx_port_link_mode[i].speed)
-			ptys_proto |= mlxsw_sx_port_link_mode[i].mask;
-	}
-	return ptys_proto;
-}
-
-static u32 mlxsw_sx_to_ptys_upper_speed(u32 upper_speed)
-{
-	u32 ptys_proto = 0;
-	int i;
-
-	for (i = 0; i < MLXSW_SX_PORT_LINK_MODE_LEN; i++) {
-		if (mlxsw_sx_port_link_mode[i].speed <= upper_speed)
-			ptys_proto |= mlxsw_sx_port_link_mode[i].mask;
-	}
-	return ptys_proto;
-}
-
-static int
-mlxsw_sx_port_set_link_ksettings(struct net_device *dev,
-				 const struct ethtool_link_ksettings *cmd)
-{
-	struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-	char ptys_pl[MLXSW_REG_PTYS_LEN];
-	u32 speed;
-	u32 eth_proto_new;
-	u32 eth_proto_cap;
-	u32 eth_proto_admin;
-	u32 advertising;
-	bool is_up;
-	int err;
-
-	speed = cmd->base.speed;
-
-	ethtool_convert_link_mode_to_legacy_u32(&advertising,
-						cmd->link_modes.advertising);
-
-	eth_proto_new = cmd->base.autoneg == AUTONEG_ENABLE ?
-		mlxsw_sx_to_ptys_advert_link(advertising) :
-		mlxsw_sx_to_ptys_speed(speed);
-
-	mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sx_port->local_port, 0, false);
-	err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(ptys), ptys_pl);
-	if (err) {
-		netdev_err(dev, "Failed to get proto");
-		return err;
-	}
-	mlxsw_reg_ptys_eth_unpack(ptys_pl, &eth_proto_cap, &eth_proto_admin,
-				  NULL);
-
-	eth_proto_new = eth_proto_new & eth_proto_cap;
-	if (!eth_proto_new) {
-		netdev_err(dev, "Not supported proto admin requested");
-		return -EINVAL;
-	}
-	if (eth_proto_new == eth_proto_admin)
-		return 0;
-
-	mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sx_port->local_port,
-				eth_proto_new, true);
-	err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(ptys), ptys_pl);
-	if (err) {
-		netdev_err(dev, "Failed to set proto admin");
-		return err;
-	}
-
-	err = mlxsw_sx_port_oper_status_get(mlxsw_sx_port, &is_up);
-	if (err) {
-		netdev_err(dev, "Failed to get oper status");
-		return err;
-	}
-	if (!is_up)
-		return 0;
-
-	err = mlxsw_sx_port_admin_status_set(mlxsw_sx_port, false);
-	if (err) {
-		netdev_err(dev, "Failed to set admin status");
-		return err;
-	}
-
-	err = mlxsw_sx_port_admin_status_set(mlxsw_sx_port, true);
-	if (err) {
-		netdev_err(dev, "Failed to set admin status");
-		return err;
-	}
-
-	return 0;
-}
-
-static const struct ethtool_ops mlxsw_sx_port_ethtool_ops = {
-	.get_drvinfo		= mlxsw_sx_port_get_drvinfo,
-	.get_link		= ethtool_op_get_link,
-	.get_strings		= mlxsw_sx_port_get_strings,
-	.get_ethtool_stats	= mlxsw_sx_port_get_stats,
-	.get_sset_count		= mlxsw_sx_port_get_sset_count,
-	.get_link_ksettings	= mlxsw_sx_port_get_link_ksettings,
-	.set_link_ksettings	= mlxsw_sx_port_set_link_ksettings,
-};
-
-static int mlxsw_sx_hw_id_get(struct mlxsw_sx *mlxsw_sx)
-{
-	char spad_pl[MLXSW_REG_SPAD_LEN] = {0};
-	int err;
-
-	err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(spad), spad_pl);
-	if (err)
-		return err;
-	mlxsw_reg_spad_base_mac_memcpy_from(spad_pl, mlxsw_sx->hw_id);
-	return 0;
-}
-
-static int mlxsw_sx_port_dev_addr_get(struct mlxsw_sx_port *mlxsw_sx_port)
-{
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-	struct net_device *dev = mlxsw_sx_port->dev;
-	char ppad_pl[MLXSW_REG_PPAD_LEN];
-	int err;
-
-	mlxsw_reg_ppad_pack(ppad_pl, false, 0);
-	err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(ppad), ppad_pl);
-	if (err)
-		return err;
-	mlxsw_reg_ppad_mac_memcpy_from(ppad_pl, dev->dev_addr);
-	/* The last byte value in base mac address is guaranteed
-	 * to be such it does not overflow when adding local_port
-	 * value.
-	 */
-	dev->dev_addr[ETH_ALEN - 1] += mlxsw_sx_port->local_port;
-	return 0;
-}
-
-static int mlxsw_sx_port_stp_state_set(struct mlxsw_sx_port *mlxsw_sx_port,
-				       u16 vid, enum mlxsw_reg_spms_state state)
-{
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-	char *spms_pl;
-	int err;
-
-	spms_pl = kmalloc(MLXSW_REG_SPMS_LEN, GFP_KERNEL);
-	if (!spms_pl)
-		return -ENOMEM;
-	mlxsw_reg_spms_pack(spms_pl, mlxsw_sx_port->local_port);
-	mlxsw_reg_spms_vid_pack(spms_pl, vid, state);
-	err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(spms), spms_pl);
-	kfree(spms_pl);
-	return err;
-}
-
-static int mlxsw_sx_port_ib_speed_set(struct mlxsw_sx_port *mlxsw_sx_port,
-				      u16 speed, u16 width)
-{
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-	char ptys_pl[MLXSW_REG_PTYS_LEN];
-
-	mlxsw_reg_ptys_ib_pack(ptys_pl, mlxsw_sx_port->local_port, speed,
-			       width);
-	return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(ptys), ptys_pl);
-}
-
-static int
-mlxsw_sx_port_speed_by_width_set(struct mlxsw_sx_port *mlxsw_sx_port, u8 width)
-{
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-	u32 upper_speed = MLXSW_SX_PORT_BASE_SPEED * width;
-	char ptys_pl[MLXSW_REG_PTYS_LEN];
-	u32 eth_proto_admin;
-
-	eth_proto_admin = mlxsw_sx_to_ptys_upper_speed(upper_speed);
-	mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sx_port->local_port,
-				eth_proto_admin, true);
-	return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(ptys), ptys_pl);
-}
-
-static int
-mlxsw_sx_port_mac_learning_mode_set(struct mlxsw_sx_port *mlxsw_sx_port,
-				    enum mlxsw_reg_spmlr_learn_mode mode)
-{
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-	char spmlr_pl[MLXSW_REG_SPMLR_LEN];
-
-	mlxsw_reg_spmlr_pack(spmlr_pl, mlxsw_sx_port->local_port, mode);
-	return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(spmlr), spmlr_pl);
-}
-
-static int __mlxsw_sx_port_eth_create(struct mlxsw_sx *mlxsw_sx, u8 local_port,
-				      u8 module, u8 width)
-{
-	struct mlxsw_sx_port *mlxsw_sx_port;
-	struct net_device *dev;
-	int err;
-
-	dev = alloc_etherdev(sizeof(struct mlxsw_sx_port));
-	if (!dev)
-		return -ENOMEM;
-	SET_NETDEV_DEV(dev, mlxsw_sx->bus_info->dev);
-	dev_net_set(dev, mlxsw_core_net(mlxsw_sx->core));
-	mlxsw_sx_port = netdev_priv(dev);
-	mlxsw_sx_port->dev = dev;
-	mlxsw_sx_port->mlxsw_sx = mlxsw_sx;
-	mlxsw_sx_port->local_port = local_port;
-	mlxsw_sx_port->mapping.module = module;
-
-	mlxsw_sx_port->pcpu_stats =
-		netdev_alloc_pcpu_stats(struct mlxsw_sx_port_pcpu_stats);
-	if (!mlxsw_sx_port->pcpu_stats) {
-		err = -ENOMEM;
-		goto err_alloc_stats;
-	}
-
-	dev->netdev_ops = &mlxsw_sx_port_netdev_ops;
-	dev->ethtool_ops = &mlxsw_sx_port_ethtool_ops;
-
-	err = mlxsw_sx_port_dev_addr_get(mlxsw_sx_port);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Unable to get port mac address\n",
-			mlxsw_sx_port->local_port);
-		goto err_dev_addr_get;
-	}
-
-	netif_carrier_off(dev);
-
-	dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_LLTX | NETIF_F_SG |
-			 NETIF_F_VLAN_CHALLENGED;
-
-	dev->min_mtu = 0;
-	dev->max_mtu = ETH_MAX_MTU;
-
-	/* Each packet needs to have a Tx header (metadata) on top all other
-	 * headers.
-	 */
-	dev->needed_headroom = MLXSW_TXHDR_LEN;
-
-	err = mlxsw_sx_port_system_port_mapping_set(mlxsw_sx_port);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set system port mapping\n",
-			mlxsw_sx_port->local_port);
-		goto err_port_system_port_mapping_set;
-	}
-
-	err = mlxsw_sx_port_swid_set(mlxsw_sx_port, 0);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set SWID\n",
-			mlxsw_sx_port->local_port);
-		goto err_port_swid_set;
-	}
-
-	err = mlxsw_sx_port_speed_by_width_set(mlxsw_sx_port, width);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set speed\n",
-			mlxsw_sx_port->local_port);
-		goto err_port_speed_set;
-	}
-
-	err = mlxsw_sx_port_mtu_eth_set(mlxsw_sx_port, ETH_DATA_LEN);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set MTU\n",
-			mlxsw_sx_port->local_port);
-		goto err_port_mtu_set;
-	}
-
-	err = mlxsw_sx_port_admin_status_set(mlxsw_sx_port, false);
-	if (err)
-		goto err_port_admin_status_set;
-
-	err = mlxsw_sx_port_stp_state_set(mlxsw_sx_port,
-					  MLXSW_PORT_DEFAULT_VID,
-					  MLXSW_REG_SPMS_STATE_FORWARDING);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set STP state\n",
-			mlxsw_sx_port->local_port);
-		goto err_port_stp_state_set;
-	}
-
-	err = mlxsw_sx_port_mac_learning_mode_set(mlxsw_sx_port,
-						  MLXSW_REG_SPMLR_LEARN_MODE_DISABLE);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set MAC learning mode\n",
-			mlxsw_sx_port->local_port);
-		goto err_port_mac_learning_mode_set;
-	}
-
-	err = register_netdev(dev);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to register netdev\n",
-			mlxsw_sx_port->local_port);
-		goto err_register_netdev;
-	}
-
-	mlxsw_core_port_eth_set(mlxsw_sx->core, mlxsw_sx_port->local_port,
-				mlxsw_sx_port, dev);
-	mlxsw_sx->ports[local_port] = mlxsw_sx_port;
-	return 0;
-
-err_register_netdev:
-err_port_mac_learning_mode_set:
-err_port_stp_state_set:
-err_port_admin_status_set:
-err_port_mtu_set:
-err_port_speed_set:
-	mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT);
-err_port_swid_set:
-err_port_system_port_mapping_set:
-err_dev_addr_get:
-	free_percpu(mlxsw_sx_port->pcpu_stats);
-err_alloc_stats:
-	free_netdev(dev);
-	return err;
-}
-
-static int mlxsw_sx_port_eth_create(struct mlxsw_sx *mlxsw_sx, u8 local_port,
-				    u8 module, u8 width)
-{
-	int err;
-
-	err = mlxsw_core_port_init(mlxsw_sx->core, local_port,
-				   module + 1, false, 0, false, 0,
-				   mlxsw_sx->hw_id, sizeof(mlxsw_sx->hw_id));
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to init core port\n",
-			local_port);
-		return err;
-	}
-	err = __mlxsw_sx_port_eth_create(mlxsw_sx, local_port, module, width);
-	if (err)
-		goto err_port_create;
-
-	return 0;
-
-err_port_create:
-	mlxsw_core_port_fini(mlxsw_sx->core, local_port);
-	return err;
-}
-
-static void __mlxsw_sx_port_eth_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port)
-{
-	struct mlxsw_sx_port *mlxsw_sx_port = mlxsw_sx->ports[local_port];
-
-	mlxsw_core_port_clear(mlxsw_sx->core, local_port, mlxsw_sx);
-	unregister_netdev(mlxsw_sx_port->dev); /* This calls ndo_stop */
-	mlxsw_sx->ports[local_port] = NULL;
-	mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT);
-	free_percpu(mlxsw_sx_port->pcpu_stats);
-	free_netdev(mlxsw_sx_port->dev);
-}
-
-static bool mlxsw_sx_port_created(struct mlxsw_sx *mlxsw_sx, u8 local_port)
-{
-	return mlxsw_sx->ports[local_port] != NULL;
-}
-
-static int __mlxsw_sx_port_ib_create(struct mlxsw_sx *mlxsw_sx, u8 local_port,
-				     u8 module, u8 width)
-{
-	struct mlxsw_sx_port *mlxsw_sx_port;
-	int err;
-
-	mlxsw_sx_port = kzalloc(sizeof(*mlxsw_sx_port), GFP_KERNEL);
-	if (!mlxsw_sx_port)
-		return -ENOMEM;
-	mlxsw_sx_port->mlxsw_sx = mlxsw_sx;
-	mlxsw_sx_port->local_port = local_port;
-	mlxsw_sx_port->mapping.module = module;
-
-	err = mlxsw_sx_port_system_port_mapping_set(mlxsw_sx_port);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set system port mapping\n",
-			mlxsw_sx_port->local_port);
-		goto err_port_system_port_mapping_set;
-	}
-
-	/* Adding port to Infiniband swid (1) */
-	err = mlxsw_sx_port_swid_set(mlxsw_sx_port, 1);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set SWID\n",
-			mlxsw_sx_port->local_port);
-		goto err_port_swid_set;
-	}
-
-	/* Expose the IB port number as it's front panel name */
-	err = mlxsw_sx_port_ib_port_set(mlxsw_sx_port, module + 1);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set IB port\n",
-			mlxsw_sx_port->local_port);
-		goto err_port_ib_set;
-	}
-
-	/* Supports all speeds from SDR to FDR (bitmask) and support bus width
-	 * of 1x, 2x and 4x (3 bits bitmask)
-	 */
-	err = mlxsw_sx_port_ib_speed_set(mlxsw_sx_port,
-					 MLXSW_REG_PTYS_IB_SPEED_EDR - 1,
-					 BIT(3) - 1);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set speed\n",
-			mlxsw_sx_port->local_port);
-		goto err_port_speed_set;
-	}
-
-	/* Change to the maximum MTU the device supports, the SMA will take
-	 * care of the active MTU
-	 */
-	err = mlxsw_sx_port_mtu_ib_set(mlxsw_sx_port, MLXSW_IB_DEFAULT_MTU);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set MTU\n",
-			mlxsw_sx_port->local_port);
-		goto err_port_mtu_set;
-	}
-
-	err = mlxsw_sx_port_admin_status_set(mlxsw_sx_port, true);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to change admin state to UP\n",
-			mlxsw_sx_port->local_port);
-		goto err_port_admin_set;
-	}
-
-	mlxsw_core_port_ib_set(mlxsw_sx->core, mlxsw_sx_port->local_port,
-			       mlxsw_sx_port);
-	mlxsw_sx->ports[local_port] = mlxsw_sx_port;
-	return 0;
-
-err_port_admin_set:
-err_port_mtu_set:
-err_port_speed_set:
-err_port_ib_set:
-	mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT);
-err_port_swid_set:
-err_port_system_port_mapping_set:
-	kfree(mlxsw_sx_port);
-	return err;
-}
-
-static void __mlxsw_sx_port_ib_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port)
-{
-	struct mlxsw_sx_port *mlxsw_sx_port = mlxsw_sx->ports[local_port];
-
-	mlxsw_core_port_clear(mlxsw_sx->core, local_port, mlxsw_sx);
-	mlxsw_sx->ports[local_port] = NULL;
-	mlxsw_sx_port_admin_status_set(mlxsw_sx_port, false);
-	mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT);
-	kfree(mlxsw_sx_port);
-}
-
-static void __mlxsw_sx_port_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port)
-{
-	enum devlink_port_type port_type =
-		mlxsw_core_port_type_get(mlxsw_sx->core, local_port);
-
-	if (port_type == DEVLINK_PORT_TYPE_ETH)
-		__mlxsw_sx_port_eth_remove(mlxsw_sx, local_port);
-	else if (port_type == DEVLINK_PORT_TYPE_IB)
-		__mlxsw_sx_port_ib_remove(mlxsw_sx, local_port);
-}
-
-static void mlxsw_sx_port_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port)
-{
-	__mlxsw_sx_port_remove(mlxsw_sx, local_port);
-	mlxsw_core_port_fini(mlxsw_sx->core, local_port);
-}
-
-static void mlxsw_sx_ports_remove(struct mlxsw_sx *mlxsw_sx)
-{
-	int 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);
-	mlxsw_sx->ports = NULL;
-}
-
-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 *) * max_ports;
-	mlxsw_sx->ports = kzalloc(alloc_size, GFP_KERNEL);
-	if (!mlxsw_sx->ports)
-		return -ENOMEM;
-
-	for (i = 1; i < max_ports; i++) {
-		err = mlxsw_sx_port_module_info_get(mlxsw_sx, i, &module,
-						    &width);
-		if (err)
-			goto err_port_module_info_get;
-		if (!width)
-			continue;
-		err = mlxsw_sx_port_eth_create(mlxsw_sx, i, module, width);
-		if (err)
-			goto err_port_create;
-	}
-	return 0;
-
-err_port_create:
-err_port_module_info_get:
-	for (i--; i >= 1; i--)
-		if (mlxsw_sx_port_created(mlxsw_sx, i))
-			mlxsw_sx_port_remove(mlxsw_sx, i);
-	kfree(mlxsw_sx->ports);
-	mlxsw_sx->ports = NULL;
-	return err;
-}
-
-static void mlxsw_sx_pude_eth_event_func(struct mlxsw_sx_port *mlxsw_sx_port,
-					 enum mlxsw_reg_pude_oper_status status)
-{
-	if (status == MLXSW_PORT_OPER_STATUS_UP) {
-		netdev_info(mlxsw_sx_port->dev, "link up\n");
-		netif_carrier_on(mlxsw_sx_port->dev);
-	} else {
-		netdev_info(mlxsw_sx_port->dev, "link down\n");
-		netif_carrier_off(mlxsw_sx_port->dev);
-	}
-}
-
-static void mlxsw_sx_pude_ib_event_func(struct mlxsw_sx_port *mlxsw_sx_port,
-					enum mlxsw_reg_pude_oper_status status)
-{
-	if (status == MLXSW_PORT_OPER_STATUS_UP)
-		pr_info("ib link for port %d - up\n",
-			mlxsw_sx_port->mapping.module + 1);
-	else
-		pr_info("ib link for port %d - down\n",
-			mlxsw_sx_port->mapping.module + 1);
-}
-
-static void mlxsw_sx_pude_event_func(const struct mlxsw_reg_info *reg,
-				     char *pude_pl, void *priv)
-{
-	struct mlxsw_sx *mlxsw_sx = priv;
-	struct mlxsw_sx_port *mlxsw_sx_port;
-	enum mlxsw_reg_pude_oper_status status;
-	enum devlink_port_type port_type;
-	u8 local_port;
-
-	local_port = mlxsw_reg_pude_local_port_get(pude_pl);
-	mlxsw_sx_port = mlxsw_sx->ports[local_port];
-	if (!mlxsw_sx_port) {
-		dev_warn(mlxsw_sx->bus_info->dev, "Port %d: Link event received for non-existent port\n",
-			 local_port);
-		return;
-	}
-
-	status = mlxsw_reg_pude_oper_status_get(pude_pl);
-	port_type = mlxsw_core_port_type_get(mlxsw_sx->core, local_port);
-	if (port_type == DEVLINK_PORT_TYPE_ETH)
-		mlxsw_sx_pude_eth_event_func(mlxsw_sx_port, status);
-	else if (port_type == DEVLINK_PORT_TYPE_IB)
-		mlxsw_sx_pude_ib_event_func(mlxsw_sx_port, status);
-}
-
-static void mlxsw_sx_rx_listener_func(struct sk_buff *skb, u8 local_port,
-				      void *priv)
-{
-	struct mlxsw_sx *mlxsw_sx = priv;
-	struct mlxsw_sx_port *mlxsw_sx_port = mlxsw_sx->ports[local_port];
-	struct mlxsw_sx_port_pcpu_stats *pcpu_stats;
-
-	if (unlikely(!mlxsw_sx_port)) {
-		dev_warn_ratelimited(mlxsw_sx->bus_info->dev, "Port %d: skb received for non-existent port\n",
-				     local_port);
-		return;
-	}
-
-	skb->dev = mlxsw_sx_port->dev;
-
-	pcpu_stats = this_cpu_ptr(mlxsw_sx_port->pcpu_stats);
-	u64_stats_update_begin(&pcpu_stats->syncp);
-	pcpu_stats->rx_packets++;
-	pcpu_stats->rx_bytes += skb->len;
-	u64_stats_update_end(&pcpu_stats->syncp);
-
-	skb->protocol = eth_type_trans(skb, skb->dev);
-	netif_receive_skb(skb);
-}
-
-static int mlxsw_sx_port_type_set(struct mlxsw_core *mlxsw_core, u8 local_port,
-				  enum devlink_port_type new_type)
-{
-	struct mlxsw_sx *mlxsw_sx = mlxsw_core_driver_priv(mlxsw_core);
-	u8 module, width;
-	int err;
-
-	if (!mlxsw_sx->ports || !mlxsw_sx->ports[local_port]) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port number \"%d\" does not exist\n",
-			local_port);
-		return -EINVAL;
-	}
-
-	if (new_type == DEVLINK_PORT_TYPE_AUTO)
-		return -EOPNOTSUPP;
-
-	__mlxsw_sx_port_remove(mlxsw_sx, local_port);
-	err = mlxsw_sx_port_module_info_get(mlxsw_sx, local_port, &module,
-					    &width);
-	if (err)
-		goto err_port_module_info_get;
-
-	if (new_type == DEVLINK_PORT_TYPE_ETH)
-		err = __mlxsw_sx_port_eth_create(mlxsw_sx, local_port, module,
-						 width);
-	else if (new_type == DEVLINK_PORT_TYPE_IB)
-		err = __mlxsw_sx_port_ib_create(mlxsw_sx, local_port, module,
-						width);
-
-err_port_module_info_get:
-	return err;
-}
-
-enum {
-	MLXSW_REG_HTGT_TRAP_GROUP_SX2_RX = 1,
-	MLXSW_REG_HTGT_TRAP_GROUP_SX2_CTRL = 2,
-};
-
-#define MLXSW_SX_RXL(_trap_id) \
-	MLXSW_RXL(mlxsw_sx_rx_listener_func, _trap_id, TRAP_TO_CPU,	\
-		  false, SX2_RX, FORWARD)
-
-static const struct mlxsw_listener mlxsw_sx_listener[] = {
-	MLXSW_EVENTL(mlxsw_sx_pude_event_func, PUDE, EMAD),
-	MLXSW_SX_RXL(FDB_MC),
-	MLXSW_SX_RXL(STP),
-	MLXSW_SX_RXL(LACP),
-	MLXSW_SX_RXL(EAPOL),
-	MLXSW_SX_RXL(LLDP),
-	MLXSW_SX_RXL(MMRP),
-	MLXSW_SX_RXL(MVRP),
-	MLXSW_SX_RXL(RPVST),
-	MLXSW_SX_RXL(DHCP),
-	MLXSW_SX_RXL(IGMP_QUERY),
-	MLXSW_SX_RXL(IGMP_V1_REPORT),
-	MLXSW_SX_RXL(IGMP_V2_REPORT),
-	MLXSW_SX_RXL(IGMP_V2_LEAVE),
-	MLXSW_SX_RXL(IGMP_V3_REPORT),
-};
-
-static int mlxsw_sx_traps_init(struct mlxsw_sx *mlxsw_sx)
-{
-	char htgt_pl[MLXSW_REG_HTGT_LEN];
-	int i;
-	int err;
-
-	mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_SX2_RX,
-			    MLXSW_REG_HTGT_INVALID_POLICER,
-			    MLXSW_REG_HTGT_DEFAULT_PRIORITY,
-			    MLXSW_REG_HTGT_DEFAULT_TC);
-	mlxsw_reg_htgt_local_path_rdq_set(htgt_pl,
-					  MLXSW_REG_HTGT_LOCAL_PATH_RDQ_SX2_RX);
-
-	err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(htgt), htgt_pl);
-	if (err)
-		return err;
-
-	mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_SX2_CTRL,
-			    MLXSW_REG_HTGT_INVALID_POLICER,
-			    MLXSW_REG_HTGT_DEFAULT_PRIORITY,
-			    MLXSW_REG_HTGT_DEFAULT_TC);
-	mlxsw_reg_htgt_local_path_rdq_set(htgt_pl,
-					MLXSW_REG_HTGT_LOCAL_PATH_RDQ_SX2_CTRL);
-
-	err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(htgt), htgt_pl);
-	if (err)
-		return err;
-
-	for (i = 0; i < ARRAY_SIZE(mlxsw_sx_listener); i++) {
-		err = mlxsw_core_trap_register(mlxsw_sx->core,
-					       &mlxsw_sx_listener[i],
-					       mlxsw_sx);
-		if (err)
-			goto err_listener_register;
-
-	}
-	return 0;
-
-err_listener_register:
-	for (i--; i >= 0; i--) {
-		mlxsw_core_trap_unregister(mlxsw_sx->core,
-					   &mlxsw_sx_listener[i],
-					   mlxsw_sx);
-	}
-	return err;
-}
-
-static void mlxsw_sx_traps_fini(struct mlxsw_sx *mlxsw_sx)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(mlxsw_sx_listener); i++) {
-		mlxsw_core_trap_unregister(mlxsw_sx->core,
-					   &mlxsw_sx_listener[i],
-					   mlxsw_sx);
-	}
-}
-
-static int mlxsw_sx_flood_init(struct mlxsw_sx *mlxsw_sx)
-{
-	char sfgc_pl[MLXSW_REG_SFGC_LEN];
-	char sgcr_pl[MLXSW_REG_SGCR_LEN];
-	char *sftr_pl;
-	int err;
-
-	/* Configure a flooding table, which includes only CPU port. */
-	sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL);
-	if (!sftr_pl)
-		return -ENOMEM;
-	mlxsw_reg_sftr_pack(sftr_pl, 0, 0, MLXSW_REG_SFGC_TABLE_TYPE_SINGLE, 0,
-			    MLXSW_PORT_CPU_PORT, true);
-	err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sftr), sftr_pl);
-	kfree(sftr_pl);
-	if (err)
-		return err;
-
-	/* Flood different packet types using the flooding table. */
-	mlxsw_reg_sfgc_pack(sfgc_pl,
-			    MLXSW_REG_SFGC_TYPE_UNKNOWN_UNICAST,
-			    MLXSW_REG_SFGC_BRIDGE_TYPE_1Q_FID,
-			    MLXSW_REG_SFGC_TABLE_TYPE_SINGLE,
-			    0);
-	err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sfgc), sfgc_pl);
-	if (err)
-		return err;
-
-	mlxsw_reg_sfgc_pack(sfgc_pl,
-			    MLXSW_REG_SFGC_TYPE_BROADCAST,
-			    MLXSW_REG_SFGC_BRIDGE_TYPE_1Q_FID,
-			    MLXSW_REG_SFGC_TABLE_TYPE_SINGLE,
-			    0);
-	err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sfgc), sfgc_pl);
-	if (err)
-		return err;
-
-	mlxsw_reg_sfgc_pack(sfgc_pl,
-			    MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_NON_IP,
-			    MLXSW_REG_SFGC_BRIDGE_TYPE_1Q_FID,
-			    MLXSW_REG_SFGC_TABLE_TYPE_SINGLE,
-			    0);
-	err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sfgc), sfgc_pl);
-	if (err)
-		return err;
-
-	mlxsw_reg_sfgc_pack(sfgc_pl,
-			    MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV6,
-			    MLXSW_REG_SFGC_BRIDGE_TYPE_1Q_FID,
-			    MLXSW_REG_SFGC_TABLE_TYPE_SINGLE,
-			    0);
-	err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sfgc), sfgc_pl);
-	if (err)
-		return err;
-
-	mlxsw_reg_sfgc_pack(sfgc_pl,
-			    MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV4,
-			    MLXSW_REG_SFGC_BRIDGE_TYPE_1Q_FID,
-			    MLXSW_REG_SFGC_TABLE_TYPE_SINGLE,
-			    0);
-	err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sfgc), sfgc_pl);
-	if (err)
-		return err;
-
-	mlxsw_reg_sgcr_pack(sgcr_pl, true);
-	return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sgcr), sgcr_pl);
-}
-
-static int mlxsw_sx_basic_trap_groups_set(struct mlxsw_core *mlxsw_core)
-{
-	char htgt_pl[MLXSW_REG_HTGT_LEN];
-
-	mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_EMAD,
-			    MLXSW_REG_HTGT_INVALID_POLICER,
-			    MLXSW_REG_HTGT_DEFAULT_PRIORITY,
-			    MLXSW_REG_HTGT_DEFAULT_TC);
-	mlxsw_reg_htgt_swid_set(htgt_pl, MLXSW_PORT_SWID_ALL_SWIDS);
-	mlxsw_reg_htgt_local_path_rdq_set(htgt_pl,
-					MLXSW_REG_HTGT_LOCAL_PATH_RDQ_SX2_EMAD);
-	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl);
-}
-
-static int mlxsw_sx_init(struct mlxsw_core *mlxsw_core,
-			 const struct mlxsw_bus_info *mlxsw_bus_info,
-			 struct netlink_ext_ack *extack)
-{
-	struct mlxsw_sx *mlxsw_sx = mlxsw_core_driver_priv(mlxsw_core);
-	int err;
-
-	mlxsw_sx->core = mlxsw_core;
-	mlxsw_sx->bus_info = mlxsw_bus_info;
-
-	err = mlxsw_sx_hw_id_get(mlxsw_sx);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Failed to get switch HW ID\n");
-		return err;
-	}
-
-	err = mlxsw_sx_ports_create(mlxsw_sx);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Failed to create ports\n");
-		return err;
-	}
-
-	err = mlxsw_sx_traps_init(mlxsw_sx);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Failed to set traps\n");
-		goto err_listener_register;
-	}
-
-	err = mlxsw_sx_flood_init(mlxsw_sx);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Failed to initialize flood tables\n");
-		goto err_flood_init;
-	}
-
-	return 0;
-
-err_flood_init:
-	mlxsw_sx_traps_fini(mlxsw_sx);
-err_listener_register:
-	mlxsw_sx_ports_remove(mlxsw_sx);
-	return err;
-}
-
-static void mlxsw_sx_fini(struct mlxsw_core *mlxsw_core)
-{
-	struct mlxsw_sx *mlxsw_sx = mlxsw_core_driver_priv(mlxsw_core);
-
-	mlxsw_sx_traps_fini(mlxsw_sx);
-	mlxsw_sx_ports_remove(mlxsw_sx);
-}
-
-static const struct mlxsw_config_profile mlxsw_sx_config_profile = {
-	.used_max_vepa_channels		= 1,
-	.max_vepa_channels		= 0,
-	.used_max_mid			= 1,
-	.max_mid			= 7000,
-	.used_max_pgt			= 1,
-	.max_pgt			= 0,
-	.used_max_system_port		= 1,
-	.max_system_port		= 48000,
-	.used_max_vlan_groups		= 1,
-	.max_vlan_groups		= 127,
-	.used_max_regions		= 1,
-	.max_regions			= 400,
-	.used_flood_tables		= 1,
-	.max_flood_tables		= 2,
-	.max_vid_flood_tables		= 1,
-	.used_flood_mode		= 1,
-	.flood_mode			= 3,
-	.used_max_ib_mc			= 1,
-	.max_ib_mc			= 6,
-	.used_max_pkey			= 1,
-	.max_pkey			= 0,
-	.swid_config			= {
-		{
-			.used_type	= 1,
-			.type		= MLXSW_PORT_SWID_TYPE_ETH,
-		},
-		{
-			.used_type	= 1,
-			.type		= MLXSW_PORT_SWID_TYPE_IB,
-		}
-	},
-};
-
-static struct mlxsw_driver mlxsw_sx_driver = {
-	.kind			= mlxsw_sx_driver_name,
-	.priv_size		= sizeof(struct mlxsw_sx),
-	.init			= mlxsw_sx_init,
-	.fini			= mlxsw_sx_fini,
-	.basic_trap_groups_set	= mlxsw_sx_basic_trap_groups_set,
-	.txhdr_construct	= mlxsw_sx_txhdr_construct,
-	.txhdr_len		= MLXSW_TXHDR_LEN,
-	.profile		= &mlxsw_sx_config_profile,
-	.port_type_set		= mlxsw_sx_port_type_set,
-};
-
-static const struct pci_device_id mlxsw_sx_pci_id_table[] = {
-	{PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SWITCHX2), 0},
-	{0, },
-};
-
-static struct pci_driver mlxsw_sx_pci_driver = {
-	.name = mlxsw_sx_driver_name,
-	.id_table = mlxsw_sx_pci_id_table,
-};
-
-static int __init mlxsw_sx_module_init(void)
-{
-	int err;
-
-	err = mlxsw_core_driver_register(&mlxsw_sx_driver);
-	if (err)
-		return err;
-
-	err = mlxsw_pci_driver_register(&mlxsw_sx_pci_driver);
-	if (err)
-		goto err_pci_driver_register;
-
-	return 0;
-
-err_pci_driver_register:
-	mlxsw_core_driver_unregister(&mlxsw_sx_driver);
-	return err;
-}
-
-static void __exit mlxsw_sx_module_exit(void)
-{
-	mlxsw_pci_driver_unregister(&mlxsw_sx_pci_driver);
-	mlxsw_core_driver_unregister(&mlxsw_sx_driver);
-}
-
-module_init(mlxsw_sx_module_init);
-module_exit(mlxsw_sx_module_exit);
-
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>");
-MODULE_DESCRIPTION("Mellanox SwitchX-2 driver");
-MODULE_DEVICE_TABLE(pci, mlxsw_sx_pci_id_table);
diff --git a/drivers/net/ethernet/micrel/ks8842.c b/drivers/net/ethernet/micrel/ks8842.c
index caa251d0e381..b27713906d3a 100644
--- a/drivers/net/ethernet/micrel/ks8842.c
+++ b/drivers/net/ethernet/micrel/ks8842.c
@@ -1135,6 +1135,10 @@ static int ks8842_probe(struct platform_device *pdev)
 	unsigned i;
 
 	iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!iomem) {
+		dev_err(&pdev->dev, "Invalid resource\n");
+		return -EINVAL;
+	}
 	if (!request_mem_region(iomem->start, resource_size(iomem), DRV_NAME))
 		goto err_mem_region;
 
diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c
index 13eef6e9bd2d..831518466de2 100644
--- a/drivers/net/ethernet/micrel/ks8851_common.c
+++ b/drivers/net/ethernet/micrel/ks8851_common.c
@@ -1022,30 +1022,23 @@ static int ks8851_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 val)
  *
  * Read and check the TX/RX memory selftest information.
  */
-static int ks8851_read_selftest(struct ks8851_net *ks)
+static void ks8851_read_selftest(struct ks8851_net *ks)
 {
 	unsigned both_done = MBIR_TXMBF | MBIR_RXMBF;
-	int ret = 0;
 	unsigned rd;
 
 	rd = ks8851_rdreg16(ks, KS_MBIR);
 
 	if ((rd & both_done) != both_done) {
 		netdev_warn(ks->netdev, "Memory selftest not finished\n");
-		return 0;
+		return;
 	}
 
-	if (rd & MBIR_TXMBFA) {
+	if (rd & MBIR_TXMBFA)
 		netdev_err(ks->netdev, "TX memory selftest fail\n");
-		ret |= 1;
-	}
 
-	if (rd & MBIR_RXMBFA) {
+	if (rd & MBIR_RXMBFA)
 		netdev_err(ks->netdev, "RX memory selftest fail\n");
-		ret |= 2;
-	}
-
-	return 0;
 }
 
 /* driver bus management functions */
diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c
index 9ed264ed7070..7945eb5e2fe8 100644
--- a/drivers/net/ethernet/micrel/ksz884x.c
+++ b/drivers/net/ethernet/micrel/ksz884x.c
@@ -25,6 +25,7 @@
 #include <linux/crc32.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/micrel_phy.h>
 
 
 /* DMA Registers */
@@ -271,84 +272,15 @@
 
 #define KS884X_PHY_CTRL_OFFSET		0x00
 
-/* Mode Control Register */
-#define PHY_REG_CTRL			0
-
-#define PHY_RESET			0x8000
-#define PHY_LOOPBACK			0x4000
-#define PHY_SPEED_100MBIT		0x2000
-#define PHY_AUTO_NEG_ENABLE		0x1000
-#define PHY_POWER_DOWN			0x0800
-#define PHY_MII_DISABLE			0x0400
-#define PHY_AUTO_NEG_RESTART		0x0200
-#define PHY_FULL_DUPLEX			0x0100
-#define PHY_COLLISION_TEST		0x0080
-#define PHY_HP_MDIX			0x0020
-#define PHY_FORCE_MDIX			0x0010
-#define PHY_AUTO_MDIX_DISABLE		0x0008
-#define PHY_REMOTE_FAULT_DISABLE	0x0004
-#define PHY_TRANSMIT_DISABLE		0x0002
-#define PHY_LED_DISABLE			0x0001
-
 #define KS884X_PHY_STATUS_OFFSET	0x02
 
-/* Mode Status Register */
-#define PHY_REG_STATUS			1
-
-#define PHY_100BT4_CAPABLE		0x8000
-#define PHY_100BTX_FD_CAPABLE		0x4000
-#define PHY_100BTX_CAPABLE		0x2000
-#define PHY_10BT_FD_CAPABLE		0x1000
-#define PHY_10BT_CAPABLE		0x0800
-#define PHY_MII_SUPPRESS_CAPABLE	0x0040
-#define PHY_AUTO_NEG_ACKNOWLEDGE	0x0020
-#define PHY_REMOTE_FAULT		0x0010
-#define PHY_AUTO_NEG_CAPABLE		0x0008
-#define PHY_LINK_STATUS			0x0004
-#define PHY_JABBER_DETECT		0x0002
-#define PHY_EXTENDED_CAPABILITY		0x0001
-
 #define KS884X_PHY_ID_1_OFFSET		0x04
 #define KS884X_PHY_ID_2_OFFSET		0x06
 
-/* PHY Identifier Registers */
-#define PHY_REG_ID_1			2
-#define PHY_REG_ID_2			3
-
 #define KS884X_PHY_AUTO_NEG_OFFSET	0x08
 
-/* Auto-Negotiation Advertisement Register */
-#define PHY_REG_AUTO_NEGOTIATION	4
-
-#define PHY_AUTO_NEG_NEXT_PAGE		0x8000
-#define PHY_AUTO_NEG_REMOTE_FAULT	0x2000
-/* Not supported. */
-#define PHY_AUTO_NEG_ASYM_PAUSE		0x0800
-#define PHY_AUTO_NEG_SYM_PAUSE		0x0400
-#define PHY_AUTO_NEG_100BT4		0x0200
-#define PHY_AUTO_NEG_100BTX_FD		0x0100
-#define PHY_AUTO_NEG_100BTX		0x0080
-#define PHY_AUTO_NEG_10BT_FD		0x0040
-#define PHY_AUTO_NEG_10BT		0x0020
-#define PHY_AUTO_NEG_SELECTOR		0x001F
-#define PHY_AUTO_NEG_802_3		0x0001
-
-#define PHY_AUTO_NEG_PAUSE  (PHY_AUTO_NEG_SYM_PAUSE | PHY_AUTO_NEG_ASYM_PAUSE)
-
 #define KS884X_PHY_REMOTE_CAP_OFFSET	0x0A
 
-/* Auto-Negotiation Link Partner Ability Register */
-#define PHY_REG_REMOTE_CAPABILITY	5
-
-#define PHY_REMOTE_NEXT_PAGE		0x8000
-#define PHY_REMOTE_ACKNOWLEDGE		0x4000
-#define PHY_REMOTE_REMOTE_FAULT		0x2000
-#define PHY_REMOTE_SYM_PAUSE		0x0400
-#define PHY_REMOTE_100BTX_FD		0x0100
-#define PHY_REMOTE_100BTX		0x0080
-#define PHY_REMOTE_10BT_FD		0x0040
-#define PHY_REMOTE_10BT			0x0020
-
 /* P1VCT */
 #define KS884X_P1VCT_P			0x04F0
 #define KS884X_P1PHYCTRL_P		0x04F2
@@ -2153,7 +2085,7 @@ static void sw_cfg_broad_storm(struct ksz_hw *hw, u8 percent)
 }
 
 /**
- * sw_get_board_storm - get broadcast storm threshold
+ * sw_get_broad_storm - get broadcast storm threshold
  * @hw: 	The hardware instance.
  * @percent:	Buffer to store the broadcast storm threshold percentage.
  *
@@ -2886,15 +2818,6 @@ static void sw_block_addr(struct ksz_hw *hw)
 	}
 }
 
-#define PHY_LINK_SUPPORT		\
-	(PHY_AUTO_NEG_ASYM_PAUSE |	\
-	PHY_AUTO_NEG_SYM_PAUSE |	\
-	PHY_AUTO_NEG_100BT4 |		\
-	PHY_AUTO_NEG_100BTX_FD |	\
-	PHY_AUTO_NEG_100BTX |		\
-	PHY_AUTO_NEG_10BT_FD |		\
-	PHY_AUTO_NEG_10BT)
-
 static inline void hw_r_phy_ctrl(struct ksz_hw *hw, int phy, u16 *data)
 {
 	*data = readw(hw->io + phy + KS884X_PHY_CTRL_OFFSET);
@@ -2973,7 +2896,7 @@ static void hw_r_phy(struct ksz_hw *hw, int port, u16 reg, u16 *val)
 }
 
 /**
- * port_w_phy - write data to PHY register
+ * hw_w_phy - write data to PHY register
  * @hw: 	The hardware instance.
  * @port:	Port to write.
  * @reg:	PHY register to write.
@@ -3238,16 +3161,18 @@ static void determine_flow_ctrl(struct ksz_hw *hw, struct ksz_port *port,
 	rx = tx = 0;
 	if (port->force_link)
 		rx = tx = 1;
-	if (remote & PHY_AUTO_NEG_SYM_PAUSE) {
-		if (local & PHY_AUTO_NEG_SYM_PAUSE) {
+	if (remote & LPA_PAUSE_CAP) {
+		if (local & ADVERTISE_PAUSE_CAP) {
 			rx = tx = 1;
-		} else if ((remote & PHY_AUTO_NEG_ASYM_PAUSE) &&
-				(local & PHY_AUTO_NEG_PAUSE) ==
-				PHY_AUTO_NEG_ASYM_PAUSE) {
+		} else if ((remote & LPA_PAUSE_ASYM) &&
+			   (local &
+			    (ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM)) ==
+			   ADVERTISE_PAUSE_ASYM) {
 			tx = 1;
 		}
-	} else if (remote & PHY_AUTO_NEG_ASYM_PAUSE) {
-		if ((local & PHY_AUTO_NEG_PAUSE) == PHY_AUTO_NEG_PAUSE)
+	} else if (remote & LPA_PAUSE_ASYM) {
+		if ((local & (ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM))
+		    == (ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM))
 			rx = 1;
 	}
 	if (!hw->ksz_switch)
@@ -3428,16 +3353,16 @@ static void port_force_link_speed(struct ksz_port *port)
 		phy = KS884X_PHY_1_CTRL_OFFSET + p * PHY_CTRL_INTERVAL;
 		hw_r_phy_ctrl(hw, phy, &data);
 
-		data &= ~PHY_AUTO_NEG_ENABLE;
+		data &= ~BMCR_ANENABLE;
 
 		if (10 == port->speed)
-			data &= ~PHY_SPEED_100MBIT;
+			data &= ~BMCR_SPEED100;
 		else if (100 == port->speed)
-			data |= PHY_SPEED_100MBIT;
+			data |= BMCR_SPEED100;
 		if (1 == port->duplex)
-			data &= ~PHY_FULL_DUPLEX;
+			data &= ~BMCR_FULLDPLX;
 		else if (2 == port->duplex)
-			data |= PHY_FULL_DUPLEX;
+			data |= BMCR_FULLDPLX;
 		hw_w_phy_ctrl(hw, phy, data);
 	}
 }
@@ -4782,7 +4707,7 @@ static void transmit_cleanup(struct dev_info *hw_priv, int normal)
 }
 
 /**
- * transmit_done - transmit done processing
+ * tx_done - transmit done processing
  * @hw_priv:	Network device.
  *
  * This routine is called when the transmit interrupt is triggered, indicating
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 04d067243457..46aee2c49f1b 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1387,8 +1387,7 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 
 	gc = gd->gdma_context;
 
-	rxq = kzalloc(sizeof(*rxq) +
-		      RX_BUFFERS_PER_QUEUE * sizeof(struct mana_recv_buf_oob),
+	rxq = kzalloc(struct_size(rxq, rx_oobs, RX_BUFFERS_PER_QUEUE),
 		      GFP_KERNEL);
 	if (!rxq)
 		return NULL;
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index b85733942053..5249b64f4fc5 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -481,13 +481,12 @@ static int moxart_mac_probe(struct platform_device *pdev)
 	priv->ndev = ndev;
 	priv->pdev = pdev;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	ndev->base_addr = res->start;
-	priv->base = devm_ioremap_resource(p_dev, res);
+	priv->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(priv->base)) {
 		ret = PTR_ERR(priv->base);
 		goto init_fail;
 	}
+	ndev->base_addr = res->start;
 
 	spin_lock_init(&priv->txlock);
 
diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c
index b81e1487945c..51b4b25d15ad 100644
--- a/drivers/net/ethernet/natsemi/natsemi.c
+++ b/drivers/net/ethernet/natsemi/natsemi.c
@@ -969,7 +969,7 @@ static int natsemi_probe1(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return 0;
 
  err_create_file:
- 	unregister_netdev(dev);
+	unregister_netdev(dev);
 
  err_register_netdev:
 	iounmap(ioaddr);
@@ -3103,14 +3103,14 @@ static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	case SIOCSMIIREG:		/* Write MII PHY register. */
 		if (dev->if_port == PORT_TP) {
 			if ((data->phy_id & 0x1f) == np->phy_addr_external) {
- 				if ((data->reg_num & 0x1f) == MII_ADVERTISE)
+				if ((data->reg_num & 0x1f) == MII_ADVERTISE)
 					np->advertising = data->val_in;
 				mdio_write(dev, data->reg_num & 0x1f,
 							data->val_in);
 			}
 		} else {
 			if ((data->phy_id & 0x1f) == np->phy_addr_external) {
- 				if ((data->reg_num & 0x1f) == MII_ADVERTISE)
+				if ((data->reg_num & 0x1f) == MII_ADVERTISE)
 					np->advertising = data->val_in;
 			}
 			move_int_phy(dev, data->phy_id & 0x1f);
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index 9cfcd5500462..0b017d4f5c08 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -1101,6 +1101,8 @@ static int s2io_print_pci_mode(struct s2io_nic *nic)
  *  @nic: device private variable
  *  @link: link status (UP/DOWN) used to enable/disable continuous
  *  transmit interrupts
+ *  @may_sleep: parameter indicates if sleeping when waiting for
+ *  command complete
  *  Description: The function configures transmit traffic interrupts
  *  Return Value:  SUCCESS on success and
  *  '-1' on failure
@@ -2743,7 +2745,7 @@ static int s2io_chk_rx_buffers(struct s2io_nic *nic, struct ring_info *ring)
 }
 
 /**
- * s2io_poll - Rx interrupt handler for NAPI support
+ * s2io_poll_msix - Rx interrupt handler for NAPI support
  * @napi : pointer to the napi structure.
  * @budget : The number of packets that were budgeted to be processed
  * during  one pass through the 'Poll" function.
@@ -3323,6 +3325,8 @@ static void s2io_updt_xpak_counter(struct net_device *dev)
  *  @addr: address
  *  @busy_bit: bit to check for busy
  *  @bit_state: state to check
+ *  @may_sleep: parameter indicates if sleeping when waiting for
+ *  command complete
  *  Description: Function that waits for a command to Write into RMAC
  *  ADDR DATA registers to be completed and returns either success or
  *  error depending on whether the command was complete or not.
@@ -4868,6 +4872,8 @@ static struct net_device_stats *s2io_get_stats(struct net_device *dev)
 /**
  *  s2io_set_multicast - entry point for multicast address enable/disable.
  *  @dev : pointer to the device structure
+ *  @may_sleep: parameter indicates if sleeping when waiting for command
+ *  complete
  *  Description:
  *  This function is a driver entry point which gets called by the kernel
  *  whenever multicast addresses must be enabled/disabled. This also gets
@@ -5288,7 +5294,7 @@ s2io_ethtool_set_link_ksettings(struct net_device *dev,
 }
 
 /**
- * s2io_ethtol_get_link_ksettings - Return link specific information.
+ * s2io_ethtool_get_link_ksettings - Return link specific information.
  * @dev: pointer to netdev
  * @cmd : pointer to the structure with parameters given by ethtool
  * to return link information.
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c
index 5162b938a1ac..38a273c4d593 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-config.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c
@@ -4884,7 +4884,7 @@ vpath_open_exit1:
 }
 
 /**
- * vxge_hw_vpath_rx_doorbell_post - Close the handle got from previous vpath
+ * vxge_hw_vpath_rx_doorbell_init - Close the handle got from previous vpath
  * (vpath) open
  * @vp: Handle got from previous vpath open
  *
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index 87892bd992b1..82eef4c72f01 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -87,7 +87,7 @@ static unsigned int bw_percentage[VXGE_HW_MAX_VIRTUAL_PATHS] =
 module_param_array(bw_percentage, uint, NULL, 0);
 
 static struct vxge_drv_config *driver_config;
-static enum vxge_hw_status vxge_reset_all_vpaths(struct vxgedev *vdev);
+static void vxge_reset_all_vpaths(struct vxgedev *vdev);
 
 static inline int is_vxge_card_up(struct vxgedev *vdev)
 {
@@ -1606,7 +1606,6 @@ static void vxge_config_ci_for_tti_rti(struct vxgedev *vdev)
 
 static int do_vxge_reset(struct vxgedev *vdev, int event)
 {
-	enum vxge_hw_status status;
 	int ret = 0, vp_id, i;
 
 	vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__);
@@ -1709,14 +1708,7 @@ static int do_vxge_reset(struct vxgedev *vdev, int event)
 		netif_tx_stop_all_queues(vdev->ndev);
 
 	if (event == VXGE_LL_FULL_RESET) {
-		status = vxge_reset_all_vpaths(vdev);
-		if (status != VXGE_HW_OK) {
-			vxge_debug_init(VXGE_ERR,
-				"fatal: %s: can not reset vpaths",
-				vdev->ndev->name);
-			ret = -EPERM;
-			goto out;
-		}
+		vxge_reset_all_vpaths(vdev);
 	}
 
 	if (event == VXGE_LL_COMPL_RESET) {
@@ -1799,7 +1791,7 @@ static void vxge_reset(struct work_struct *work)
 }
 
 /**
- * vxge_poll - Receive handler when Receive Polling is used.
+ * vxge_poll_msix - Receive handler when Receive Polling is used.
  * @napi: pointer to the napi structure.
  * @budget: Number of packets budgeted to be processed in this iteration.
  *
@@ -1969,9 +1961,8 @@ static enum vxge_hw_status vxge_rth_configure(struct vxgedev *vdev)
 }
 
 /* reset vpaths */
-static enum vxge_hw_status vxge_reset_all_vpaths(struct vxgedev *vdev)
+static void vxge_reset_all_vpaths(struct vxgedev *vdev)
 {
-	enum vxge_hw_status status = VXGE_HW_OK;
 	struct vxge_vpath *vpath;
 	int i;
 
@@ -1986,18 +1977,16 @@ static enum vxge_hw_status vxge_reset_all_vpaths(struct vxgedev *vdev)
 						"vxge_hw_vpath_recover_"
 						"from_reset failed for vpath: "
 						"%d", i);
-					return status;
+					return;
 				}
 			} else {
 				vxge_debug_init(VXGE_ERR,
 					"vxge_hw_vpath_reset failed for "
 					"vpath:%d", i);
-				return status;
+				return;
 			}
 		}
 	}
-
-	return status;
 }
 
 /* close vpaths */
@@ -2676,11 +2665,7 @@ static int vxge_set_features(struct net_device *dev, netdev_features_t features)
 	/* !netif_running() ensured by vxge_fix_features() */
 
 	vdev->devh->config.rth_en = !!(features & NETIF_F_RXHASH);
-	if (vxge_reset_all_vpaths(vdev) != VXGE_HW_OK) {
-		dev->features = features ^ NETIF_F_RXHASH;
-		vdev->devh->config.rth_en = !!(dev->features & NETIF_F_RXHASH);
-		return -EIO;
-	}
+	vxge_reset_all_vpaths(vdev);
 
 	return 0;
 }
@@ -3693,10 +3678,9 @@ static int vxge_config_vpaths(struct vxge_hw_device_config *device_config,
 			driver_config->vpath_per_dev = 1;
 
 		for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++)
-			if (!vxge_bVALn(vpath_mask, i, 1))
-				continue;
-			else
+			if (vxge_bVALn(vpath_mask, i, 1))
 				default_no_vpath++;
+
 		if (default_no_vpath < driver_config->vpath_per_dev)
 			driver_config->vpath_per_dev = default_no_vpath;
 
@@ -4752,7 +4736,7 @@ _exit0:
 }
 
 /**
- * vxge_rem_nic - Free the PCI device
+ * vxge_remove - Free the PCI device
  * @pdev: structure containing the PCI related information of the device.
  * Description: This function is called by the Pci subsystem to release a
  * PCI device and free up all resource held up by the device.
diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile
index d31772ae511d..9cff3d48acbc 100644
--- a/drivers/net/ethernet/netronome/nfp/Makefile
+++ b/drivers/net/ethernet/netronome/nfp/Makefile
@@ -51,7 +51,8 @@ nfp-objs += \
 	    flower/metadata.o \
 	    flower/offload.o \
 	    flower/tunnel_conf.o \
-	    flower/qos_conf.o
+	    flower/qos_conf.o \
+	    flower/conntrack.o
 endif
 
 ifeq ($(CONFIG_BPF_SYSCALL),y)
diff --git a/drivers/net/ethernet/netronome/nfp/ccm_mbox.c b/drivers/net/ethernet/netronome/nfp/ccm_mbox.c
index f0783aa9e66e..4247bca09807 100644
--- a/drivers/net/ethernet/netronome/nfp/ccm_mbox.c
+++ b/drivers/net/ethernet/netronome/nfp/ccm_mbox.c
@@ -36,7 +36,7 @@ enum nfp_net_mbox_cmsg_state {
 };
 
 /**
- * struct nfp_ccm_mbox_skb_cb - CCM mailbox specific info
+ * struct nfp_ccm_mbox_cmsg_cb - CCM mailbox specific info
  * @state:	processing state (/stage) of the message
  * @err:	error encountered during processing if any
  * @max_len:	max(request_len, reply_len)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
new file mode 100644
index 000000000000..9ea77bb3b69c
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
@@ -0,0 +1,1178 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2021 Corigine, Inc. */
+
+#include "conntrack.h"
+
+const struct rhashtable_params nfp_tc_ct_merge_params = {
+	.head_offset		= offsetof(struct nfp_fl_ct_tc_merge,
+					   hash_node),
+	.key_len		= sizeof(unsigned long) * 2,
+	.key_offset		= offsetof(struct nfp_fl_ct_tc_merge, cookie),
+	.automatic_shrinking	= true,
+};
+
+const struct rhashtable_params nfp_nft_ct_merge_params = {
+	.head_offset		= offsetof(struct nfp_fl_nft_tc_merge,
+					   hash_node),
+	.key_len		= sizeof(unsigned long) * 3,
+	.key_offset		= offsetof(struct nfp_fl_nft_tc_merge, cookie),
+	.automatic_shrinking	= true,
+};
+
+static struct flow_action_entry *get_flow_act(struct flow_rule *rule,
+					      enum flow_action_id act_id);
+
+/**
+ * get_hashentry() - Wrapper around hashtable lookup.
+ * @ht:		hashtable where entry could be found
+ * @key:	key to lookup
+ * @params:	hashtable params
+ * @size:	size of entry to allocate if not in table
+ *
+ * Returns an entry from a hashtable. If entry does not exist
+ * yet allocate the memory for it and return the new entry.
+ */
+static void *get_hashentry(struct rhashtable *ht, void *key,
+			   const struct rhashtable_params params, size_t size)
+{
+	void *result;
+
+	result = rhashtable_lookup_fast(ht, key, params);
+
+	if (result)
+		return result;
+
+	result = kzalloc(size, GFP_KERNEL);
+	if (!result)
+		return ERR_PTR(-ENOMEM);
+
+	return result;
+}
+
+bool is_pre_ct_flow(struct flow_cls_offload *flow)
+{
+	struct flow_action_entry *act;
+	int i;
+
+	flow_action_for_each(i, act, &flow->rule->action) {
+		if (act->id == FLOW_ACTION_CT && !act->ct.action)
+			return true;
+	}
+	return false;
+}
+
+bool is_post_ct_flow(struct flow_cls_offload *flow)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
+	struct flow_dissector *dissector = rule->match.dissector;
+	struct flow_match_ct ct;
+
+	if (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT)) {
+		flow_rule_match_ct(rule, &ct);
+		if (ct.key->ct_state & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED)
+			return true;
+	}
+	return false;
+}
+
+static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
+			      struct nfp_fl_ct_flow_entry *entry2)
+{
+	unsigned int ovlp_keys = entry1->rule->match.dissector->used_keys &
+				 entry2->rule->match.dissector->used_keys;
+	bool out;
+
+	/* check the overlapped fields one by one, the unmasked part
+	 * should not conflict with each other.
+	 */
+	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match1, match2;
+
+		flow_rule_match_control(entry1->rule, &match1);
+		flow_rule_match_control(entry2->rule, &match2);
+		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
+		if (out)
+			goto check_failed;
+	}
+
+	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match1, match2;
+
+		flow_rule_match_basic(entry1->rule, &match1);
+		flow_rule_match_basic(entry2->rule, &match2);
+		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
+		if (out)
+			goto check_failed;
+	}
+
+	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+		struct flow_match_ipv4_addrs match1, match2;
+
+		flow_rule_match_ipv4_addrs(entry1->rule, &match1);
+		flow_rule_match_ipv4_addrs(entry2->rule, &match2);
+		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
+		if (out)
+			goto check_failed;
+	}
+
+	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+		struct flow_match_ipv6_addrs match1, match2;
+
+		flow_rule_match_ipv6_addrs(entry1->rule, &match1);
+		flow_rule_match_ipv6_addrs(entry2->rule, &match2);
+		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
+		if (out)
+			goto check_failed;
+	}
+
+	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match1, match2;
+
+		flow_rule_match_ports(entry1->rule, &match1);
+		flow_rule_match_ports(entry2->rule, &match2);
+		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
+		if (out)
+			goto check_failed;
+	}
+
+	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match1, match2;
+
+		flow_rule_match_eth_addrs(entry1->rule, &match1);
+		flow_rule_match_eth_addrs(entry2->rule, &match2);
+		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
+		if (out)
+			goto check_failed;
+	}
+
+	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match1, match2;
+
+		flow_rule_match_vlan(entry1->rule, &match1);
+		flow_rule_match_vlan(entry2->rule, &match2);
+		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
+		if (out)
+			goto check_failed;
+	}
+
+	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_MPLS)) {
+		struct flow_match_mpls match1, match2;
+
+		flow_rule_match_mpls(entry1->rule, &match1);
+		flow_rule_match_mpls(entry2->rule, &match2);
+		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
+		if (out)
+			goto check_failed;
+	}
+
+	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_TCP)) {
+		struct flow_match_tcp match1, match2;
+
+		flow_rule_match_tcp(entry1->rule, &match1);
+		flow_rule_match_tcp(entry2->rule, &match2);
+		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
+		if (out)
+			goto check_failed;
+	}
+
+	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IP)) {
+		struct flow_match_ip match1, match2;
+
+		flow_rule_match_ip(entry1->rule, &match1);
+		flow_rule_match_ip(entry2->rule, &match2);
+		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
+		if (out)
+			goto check_failed;
+	}
+
+	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_match_enc_keyid match1, match2;
+
+		flow_rule_match_enc_keyid(entry1->rule, &match1);
+		flow_rule_match_enc_keyid(entry2->rule, &match2);
+		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
+		if (out)
+			goto check_failed;
+	}
+
+	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
+		struct flow_match_ipv4_addrs match1, match2;
+
+		flow_rule_match_enc_ipv4_addrs(entry1->rule, &match1);
+		flow_rule_match_enc_ipv4_addrs(entry2->rule, &match2);
+		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
+		if (out)
+			goto check_failed;
+	}
+
+	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) {
+		struct flow_match_ipv6_addrs match1, match2;
+
+		flow_rule_match_enc_ipv6_addrs(entry1->rule, &match1);
+		flow_rule_match_enc_ipv6_addrs(entry2->rule, &match2);
+		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
+		if (out)
+			goto check_failed;
+	}
+
+	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
+		struct flow_match_control match1, match2;
+
+		flow_rule_match_enc_control(entry1->rule, &match1);
+		flow_rule_match_enc_control(entry2->rule, &match2);
+		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
+		if (out)
+			goto check_failed;
+	}
+
+	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_IP)) {
+		struct flow_match_ip match1, match2;
+
+		flow_rule_match_enc_ip(entry1->rule, &match1);
+		flow_rule_match_enc_ip(entry2->rule, &match2);
+		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
+		if (out)
+			goto check_failed;
+	}
+
+	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_OPTS)) {
+		struct flow_match_enc_opts match1, match2;
+
+		flow_rule_match_enc_opts(entry1->rule, &match1);
+		flow_rule_match_enc_opts(entry2->rule, &match2);
+		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
+		if (out)
+			goto check_failed;
+	}
+
+	return 0;
+
+check_failed:
+	return -EINVAL;
+}
+
+static int nfp_ct_check_mangle_merge(struct flow_action_entry *a_in,
+				     struct flow_rule *rule)
+{
+	enum flow_action_mangle_base htype = a_in->mangle.htype;
+	u32 offset = a_in->mangle.offset;
+
+	switch (htype) {
+	case FLOW_ACT_MANGLE_HDR_TYPE_ETH:
+		if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS))
+			return -EOPNOTSUPP;
+		break;
+	case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
+		if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) {
+			struct flow_match_ip match;
+
+			flow_rule_match_ip(rule, &match);
+			if (offset == offsetof(struct iphdr, ttl) &&
+			    match.mask->ttl)
+				return -EOPNOTSUPP;
+			if (offset == round_down(offsetof(struct iphdr, tos), 4) &&
+			    match.mask->tos)
+				return -EOPNOTSUPP;
+		}
+		if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+			struct flow_match_ipv4_addrs match;
+
+			flow_rule_match_ipv4_addrs(rule, &match);
+			if (offset == offsetof(struct iphdr, saddr) &&
+			    match.mask->src)
+				return -EOPNOTSUPP;
+			if (offset == offsetof(struct iphdr, daddr) &&
+			    match.mask->dst)
+				return -EOPNOTSUPP;
+		}
+		break;
+	case FLOW_ACT_MANGLE_HDR_TYPE_IP6:
+		if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) {
+			struct flow_match_ip match;
+
+			flow_rule_match_ip(rule, &match);
+			if (offset == round_down(offsetof(struct ipv6hdr, hop_limit), 4) &&
+			    match.mask->ttl)
+				return -EOPNOTSUPP;
+			/* for ipv6, tos and flow_lbl are in the same word */
+			if (offset == round_down(offsetof(struct ipv6hdr, flow_lbl), 4) &&
+			    match.mask->tos)
+				return -EOPNOTSUPP;
+		}
+		if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+			struct flow_match_ipv6_addrs match;
+
+			flow_rule_match_ipv6_addrs(rule, &match);
+			if (offset >= offsetof(struct ipv6hdr, saddr) &&
+			    offset < offsetof(struct ipv6hdr, daddr) &&
+			    memchr_inv(&match.mask->src, 0, sizeof(match.mask->src)))
+				return -EOPNOTSUPP;
+			if (offset >= offsetof(struct ipv6hdr, daddr) &&
+			    offset < sizeof(struct ipv6hdr) &&
+			    memchr_inv(&match.mask->dst, 0, sizeof(match.mask->dst)))
+				return -EOPNOTSUPP;
+		}
+		break;
+	case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
+	case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
+		/* currently only can modify ports */
+		if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS))
+			return -EOPNOTSUPP;
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static int nfp_ct_merge_act_check(struct nfp_fl_ct_flow_entry *pre_ct_entry,
+				  struct nfp_fl_ct_flow_entry *post_ct_entry,
+				  struct nfp_fl_ct_flow_entry *nft_entry)
+{
+	struct flow_action_entry *act;
+	int err, i;
+
+	/* Check for pre_ct->action conflicts */
+	flow_action_for_each(i, act, &pre_ct_entry->rule->action) {
+		switch (act->id) {
+		case FLOW_ACTION_MANGLE:
+			err = nfp_ct_check_mangle_merge(act, nft_entry->rule);
+			if (err)
+				return err;
+			err = nfp_ct_check_mangle_merge(act, post_ct_entry->rule);
+			if (err)
+				return err;
+			break;
+		case FLOW_ACTION_VLAN_PUSH:
+		case FLOW_ACTION_VLAN_POP:
+		case FLOW_ACTION_VLAN_MANGLE:
+		case FLOW_ACTION_MPLS_PUSH:
+		case FLOW_ACTION_MPLS_POP:
+		case FLOW_ACTION_MPLS_MANGLE:
+			return -EOPNOTSUPP;
+		default:
+			break;
+		}
+	}
+
+	/* Check for nft->action conflicts */
+	flow_action_for_each(i, act, &nft_entry->rule->action) {
+		switch (act->id) {
+		case FLOW_ACTION_MANGLE:
+			err = nfp_ct_check_mangle_merge(act, post_ct_entry->rule);
+			if (err)
+				return err;
+			break;
+		case FLOW_ACTION_VLAN_PUSH:
+		case FLOW_ACTION_VLAN_POP:
+		case FLOW_ACTION_VLAN_MANGLE:
+		case FLOW_ACTION_MPLS_PUSH:
+		case FLOW_ACTION_MPLS_POP:
+		case FLOW_ACTION_MPLS_MANGLE:
+			return -EOPNOTSUPP;
+		default:
+			break;
+		}
+	}
+	return 0;
+}
+
+static int nfp_ct_check_meta(struct nfp_fl_ct_flow_entry *post_ct_entry,
+			     struct nfp_fl_ct_flow_entry *nft_entry)
+{
+	struct flow_dissector *dissector = post_ct_entry->rule->match.dissector;
+	struct flow_action_entry *ct_met;
+	struct flow_match_ct ct;
+	int i;
+
+	ct_met = get_flow_act(nft_entry->rule, FLOW_ACTION_CT_METADATA);
+	if (ct_met && (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT))) {
+		u32 *act_lbl;
+
+		act_lbl = ct_met->ct_metadata.labels;
+		flow_rule_match_ct(post_ct_entry->rule, &ct);
+		for (i = 0; i < 4; i++) {
+			if ((ct.key->ct_labels[i] & ct.mask->ct_labels[i]) ^
+			    (act_lbl[i] & ct.mask->ct_labels[i]))
+				return -EINVAL;
+		}
+
+		if ((ct.key->ct_mark & ct.mask->ct_mark) ^
+		    (ct_met->ct_metadata.mark & ct.mask->ct_mark))
+			return -EINVAL;
+
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int nfp_fl_ct_add_offload(struct nfp_fl_nft_tc_merge *m_entry)
+{
+	return 0;
+}
+
+static int nfp_fl_ct_del_offload(struct nfp_app *app, unsigned long cookie,
+				 struct net_device *netdev)
+{
+	return 0;
+}
+
+static int nfp_ct_do_nft_merge(struct nfp_fl_ct_zone_entry *zt,
+			       struct nfp_fl_ct_flow_entry *nft_entry,
+			       struct nfp_fl_ct_tc_merge *tc_m_entry)
+{
+	struct nfp_fl_ct_flow_entry *post_ct_entry, *pre_ct_entry;
+	struct nfp_fl_nft_tc_merge *nft_m_entry;
+	unsigned long new_cookie[3];
+	int err;
+
+	pre_ct_entry = tc_m_entry->pre_ct_parent;
+	post_ct_entry = tc_m_entry->post_ct_parent;
+
+	err = nfp_ct_merge_act_check(pre_ct_entry, post_ct_entry, nft_entry);
+	if (err)
+		return err;
+
+	/* Check that the two tc flows are also compatible with
+	 * the nft entry. No need to check the pre_ct and post_ct
+	 * entries as that was already done during pre_merge.
+	 * The nft entry does not have a netdev or chain populated, so
+	 * skip this check.
+	 */
+	err = nfp_ct_merge_check(pre_ct_entry, nft_entry);
+	if (err)
+		return err;
+	err = nfp_ct_merge_check(post_ct_entry, nft_entry);
+	if (err)
+		return err;
+	err = nfp_ct_check_meta(post_ct_entry, nft_entry);
+	if (err)
+		return err;
+
+	/* Combine tc_merge and nft cookies for this cookie. */
+	new_cookie[0] = tc_m_entry->cookie[0];
+	new_cookie[1] = tc_m_entry->cookie[1];
+	new_cookie[2] = nft_entry->cookie;
+	nft_m_entry = get_hashentry(&zt->nft_merge_tb,
+				    &new_cookie,
+				    nfp_nft_ct_merge_params,
+				    sizeof(*nft_m_entry));
+
+	if (IS_ERR(nft_m_entry))
+		return PTR_ERR(nft_m_entry);
+
+	/* nft_m_entry already present, not merging again */
+	if (!memcmp(&new_cookie, nft_m_entry->cookie, sizeof(new_cookie)))
+		return 0;
+
+	memcpy(&nft_m_entry->cookie, &new_cookie, sizeof(new_cookie));
+	nft_m_entry->zt = zt;
+	nft_m_entry->tc_m_parent = tc_m_entry;
+	nft_m_entry->nft_parent = nft_entry;
+	nft_m_entry->tc_flower_cookie = 0;
+	/* Copy the netdev from one the pre_ct entry. When the tc_m_entry was created
+	 * it only combined them if the netdevs were the same, so can use any of them.
+	 */
+	nft_m_entry->netdev = pre_ct_entry->netdev;
+
+	/* Add this entry to the tc_m_list and nft_flow lists */
+	list_add(&nft_m_entry->tc_merge_list, &tc_m_entry->children);
+	list_add(&nft_m_entry->nft_flow_list, &nft_entry->children);
+
+	/* Generate offload structure and send to nfp */
+	err = nfp_fl_ct_add_offload(nft_m_entry);
+	if (err)
+		goto err_nft_ct_offload;
+
+	err = rhashtable_insert_fast(&zt->nft_merge_tb, &nft_m_entry->hash_node,
+				     nfp_nft_ct_merge_params);
+	if (err)
+		goto err_nft_ct_merge_insert;
+
+	zt->nft_merge_count++;
+
+	return err;
+
+err_nft_ct_merge_insert:
+	nfp_fl_ct_del_offload(zt->priv->app, nft_m_entry->tc_flower_cookie,
+			      nft_m_entry->netdev);
+err_nft_ct_offload:
+	list_del(&nft_m_entry->tc_merge_list);
+	list_del(&nft_m_entry->nft_flow_list);
+	kfree(nft_m_entry);
+	return err;
+}
+
+static int nfp_ct_do_tc_merge(struct nfp_fl_ct_zone_entry *zt,
+			      struct nfp_fl_ct_flow_entry *ct_entry1,
+			      struct nfp_fl_ct_flow_entry *ct_entry2)
+{
+	struct nfp_fl_ct_flow_entry *post_ct_entry, *pre_ct_entry;
+	struct nfp_fl_ct_flow_entry *nft_entry, *nft_tmp;
+	struct nfp_fl_ct_tc_merge *m_entry;
+	unsigned long new_cookie[2];
+	int err;
+
+	if (ct_entry1->type == CT_TYPE_PRE_CT) {
+		pre_ct_entry = ct_entry1;
+		post_ct_entry = ct_entry2;
+	} else {
+		post_ct_entry = ct_entry1;
+		pre_ct_entry = ct_entry2;
+	}
+
+	if (post_ct_entry->netdev != pre_ct_entry->netdev)
+		return -EINVAL;
+	/* Checks that the chain_index of the filter matches the
+	 * chain_index of the GOTO action.
+	 */
+	if (post_ct_entry->chain_index != pre_ct_entry->chain_index)
+		return -EINVAL;
+
+	err = nfp_ct_merge_check(post_ct_entry, pre_ct_entry);
+	if (err)
+		return err;
+
+	new_cookie[0] = pre_ct_entry->cookie;
+	new_cookie[1] = post_ct_entry->cookie;
+	m_entry = get_hashentry(&zt->tc_merge_tb, &new_cookie,
+				nfp_tc_ct_merge_params, sizeof(*m_entry));
+	if (IS_ERR(m_entry))
+		return PTR_ERR(m_entry);
+
+	/* m_entry already present, not merging again */
+	if (!memcmp(&new_cookie, m_entry->cookie, sizeof(new_cookie)))
+		return 0;
+
+	memcpy(&m_entry->cookie, &new_cookie, sizeof(new_cookie));
+	m_entry->zt = zt;
+	m_entry->post_ct_parent = post_ct_entry;
+	m_entry->pre_ct_parent = pre_ct_entry;
+
+	/* Add this entry to the pre_ct and post_ct lists */
+	list_add(&m_entry->post_ct_list, &post_ct_entry->children);
+	list_add(&m_entry->pre_ct_list, &pre_ct_entry->children);
+	INIT_LIST_HEAD(&m_entry->children);
+
+	err = rhashtable_insert_fast(&zt->tc_merge_tb, &m_entry->hash_node,
+				     nfp_tc_ct_merge_params);
+	if (err)
+		goto err_ct_tc_merge_insert;
+	zt->tc_merge_count++;
+
+	/* Merge with existing nft flows */
+	list_for_each_entry_safe(nft_entry, nft_tmp, &zt->nft_flows_list,
+				 list_node) {
+		nfp_ct_do_nft_merge(zt, nft_entry, m_entry);
+	}
+
+	return 0;
+
+err_ct_tc_merge_insert:
+	list_del(&m_entry->post_ct_list);
+	list_del(&m_entry->pre_ct_list);
+	kfree(m_entry);
+	return err;
+}
+
+static struct
+nfp_fl_ct_zone_entry *get_nfp_zone_entry(struct nfp_flower_priv *priv,
+					 u16 zone, bool wildcarded)
+{
+	struct nfp_fl_ct_zone_entry *zt;
+	int err;
+
+	if (wildcarded && priv->ct_zone_wc)
+		return priv->ct_zone_wc;
+
+	if (!wildcarded) {
+		zt = get_hashentry(&priv->ct_zone_table, &zone,
+				   nfp_zone_table_params, sizeof(*zt));
+
+		/* If priv is set this is an existing entry, just return it */
+		if (IS_ERR(zt) || zt->priv)
+			return zt;
+	} else {
+		zt = kzalloc(sizeof(*zt), GFP_KERNEL);
+		if (!zt)
+			return ERR_PTR(-ENOMEM);
+	}
+
+	zt->zone = zone;
+	zt->priv = priv;
+	zt->nft = NULL;
+
+	/* init the various hash tables and lists*/
+	INIT_LIST_HEAD(&zt->pre_ct_list);
+	INIT_LIST_HEAD(&zt->post_ct_list);
+	INIT_LIST_HEAD(&zt->nft_flows_list);
+
+	err = rhashtable_init(&zt->tc_merge_tb, &nfp_tc_ct_merge_params);
+	if (err)
+		goto err_tc_merge_tb_init;
+
+	err = rhashtable_init(&zt->nft_merge_tb, &nfp_nft_ct_merge_params);
+	if (err)
+		goto err_nft_merge_tb_init;
+
+	if (wildcarded) {
+		priv->ct_zone_wc = zt;
+	} else {
+		err = rhashtable_insert_fast(&priv->ct_zone_table,
+					     &zt->hash_node,
+					     nfp_zone_table_params);
+		if (err)
+			goto err_zone_insert;
+	}
+
+	return zt;
+
+err_zone_insert:
+	rhashtable_destroy(&zt->nft_merge_tb);
+err_nft_merge_tb_init:
+	rhashtable_destroy(&zt->tc_merge_tb);
+err_tc_merge_tb_init:
+	kfree(zt);
+	return ERR_PTR(err);
+}
+
+static struct
+nfp_fl_ct_flow_entry *nfp_fl_ct_add_flow(struct nfp_fl_ct_zone_entry *zt,
+					 struct net_device *netdev,
+					 struct flow_cls_offload *flow,
+					 bool is_nft, struct netlink_ext_ack *extack)
+{
+	struct nf_flow_match *nft_match = NULL;
+	struct nfp_fl_ct_flow_entry *entry;
+	struct nfp_fl_ct_map_entry *map;
+	struct flow_action_entry *act;
+	int err, i;
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return ERR_PTR(-ENOMEM);
+
+	entry->rule = flow_rule_alloc(flow->rule->action.num_entries);
+	if (!entry->rule) {
+		err = -ENOMEM;
+		goto err_pre_ct_rule;
+	}
+
+	/* nft flows gets destroyed after callback return, so need
+	 * to do a full copy instead of just a reference.
+	 */
+	if (is_nft) {
+		nft_match = kzalloc(sizeof(*nft_match), GFP_KERNEL);
+		if (!nft_match) {
+			err = -ENOMEM;
+			goto err_pre_ct_act;
+		}
+		memcpy(&nft_match->dissector, flow->rule->match.dissector,
+		       sizeof(nft_match->dissector));
+		memcpy(&nft_match->mask, flow->rule->match.mask,
+		       sizeof(nft_match->mask));
+		memcpy(&nft_match->key, flow->rule->match.key,
+		       sizeof(nft_match->key));
+		entry->rule->match.dissector = &nft_match->dissector;
+		entry->rule->match.mask = &nft_match->mask;
+		entry->rule->match.key = &nft_match->key;
+	} else {
+		entry->rule->match.dissector = flow->rule->match.dissector;
+		entry->rule->match.mask = flow->rule->match.mask;
+		entry->rule->match.key = flow->rule->match.key;
+	}
+
+	entry->zt = zt;
+	entry->netdev = netdev;
+	entry->cookie = flow->cookie;
+	entry->chain_index = flow->common.chain_index;
+	entry->tun_offset = NFP_FL_CT_NO_TUN;
+
+	/* Copy over action data. Unfortunately we do not get a handle to the
+	 * original tcf_action data, and the flow objects gets destroyed, so we
+	 * cannot just save a pointer to this either, so need to copy over the
+	 * data unfortunately.
+	 */
+	entry->rule->action.num_entries = flow->rule->action.num_entries;
+	flow_action_for_each(i, act, &flow->rule->action) {
+		struct flow_action_entry *new_act;
+
+		new_act = &entry->rule->action.entries[i];
+		memcpy(new_act, act, sizeof(struct flow_action_entry));
+		/* Entunnel is a special case, need to allocate and copy
+		 * tunnel info.
+		 */
+		if (act->id == FLOW_ACTION_TUNNEL_ENCAP) {
+			struct ip_tunnel_info *tun = act->tunnel;
+			size_t tun_size = sizeof(*tun) + tun->options_len;
+
+			new_act->tunnel = kmemdup(tun, tun_size, GFP_ATOMIC);
+			if (!new_act->tunnel) {
+				err = -ENOMEM;
+				goto err_pre_ct_tun_cp;
+			}
+			entry->tun_offset = i;
+		}
+	}
+
+	INIT_LIST_HEAD(&entry->children);
+
+	/* Now add a ct map entry to flower-priv */
+	map = get_hashentry(&zt->priv->ct_map_table, &flow->cookie,
+			    nfp_ct_map_params, sizeof(*map));
+	if (IS_ERR(map)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "offload error: ct map entry creation failed");
+		err = -ENOMEM;
+		goto err_ct_flow_insert;
+	}
+	map->cookie = flow->cookie;
+	map->ct_entry = entry;
+	err = rhashtable_insert_fast(&zt->priv->ct_map_table,
+				     &map->hash_node,
+				     nfp_ct_map_params);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "offload error: ct map entry table add failed");
+		goto err_map_insert;
+	}
+
+	return entry;
+
+err_map_insert:
+	kfree(map);
+err_ct_flow_insert:
+	if (entry->tun_offset != NFP_FL_CT_NO_TUN)
+		kfree(entry->rule->action.entries[entry->tun_offset].tunnel);
+err_pre_ct_tun_cp:
+	kfree(nft_match);
+err_pre_ct_act:
+	kfree(entry->rule);
+err_pre_ct_rule:
+	kfree(entry);
+	return ERR_PTR(err);
+}
+
+static void cleanup_nft_merge_entry(struct nfp_fl_nft_tc_merge *m_entry)
+{
+	struct nfp_fl_ct_zone_entry *zt;
+	int err;
+
+	zt = m_entry->zt;
+
+	/* Flow is in HW, need to delete */
+	if (m_entry->tc_flower_cookie) {
+		err = nfp_fl_ct_del_offload(zt->priv->app, m_entry->tc_flower_cookie,
+					    m_entry->netdev);
+		if (err)
+			return;
+	}
+
+	WARN_ON_ONCE(rhashtable_remove_fast(&zt->nft_merge_tb,
+					    &m_entry->hash_node,
+					    nfp_nft_ct_merge_params));
+	zt->nft_merge_count--;
+	list_del(&m_entry->tc_merge_list);
+	list_del(&m_entry->nft_flow_list);
+
+	kfree(m_entry);
+}
+
+static void nfp_free_nft_merge_children(void *entry, bool is_nft_flow)
+{
+	struct nfp_fl_nft_tc_merge *m_entry, *tmp;
+
+	/* These post entries are parts of two lists, one is a list of nft_entries
+	 * and the other is of from a list of tc_merge structures. Iterate
+	 * through the relevant list and cleanup the entries.
+	 */
+
+	if (is_nft_flow) {
+		/* Need to iterate through list of nft_flow entries*/
+		struct nfp_fl_ct_flow_entry *ct_entry = entry;
+
+		list_for_each_entry_safe(m_entry, tmp, &ct_entry->children,
+					 nft_flow_list) {
+			cleanup_nft_merge_entry(m_entry);
+		}
+	} else {
+		/* Need to iterate through list of tc_merged_flow entries*/
+		struct nfp_fl_ct_tc_merge *ct_entry = entry;
+
+		list_for_each_entry_safe(m_entry, tmp, &ct_entry->children,
+					 tc_merge_list) {
+			cleanup_nft_merge_entry(m_entry);
+		}
+	}
+}
+
+static void nfp_del_tc_merge_entry(struct nfp_fl_ct_tc_merge *m_ent)
+{
+	struct nfp_fl_ct_zone_entry *zt;
+	int err;
+
+	zt = m_ent->zt;
+	err = rhashtable_remove_fast(&zt->tc_merge_tb,
+				     &m_ent->hash_node,
+				     nfp_tc_ct_merge_params);
+	if (err)
+		pr_warn("WARNING: could not remove merge_entry from hashtable\n");
+	zt->tc_merge_count--;
+	list_del(&m_ent->post_ct_list);
+	list_del(&m_ent->pre_ct_list);
+
+	if (!list_empty(&m_ent->children))
+		nfp_free_nft_merge_children(m_ent, false);
+	kfree(m_ent);
+}
+
+static void nfp_free_tc_merge_children(struct nfp_fl_ct_flow_entry *entry)
+{
+	struct nfp_fl_ct_tc_merge *m_ent, *tmp;
+
+	switch (entry->type) {
+	case CT_TYPE_PRE_CT:
+		list_for_each_entry_safe(m_ent, tmp, &entry->children, pre_ct_list) {
+			nfp_del_tc_merge_entry(m_ent);
+		}
+		break;
+	case CT_TYPE_POST_CT:
+		list_for_each_entry_safe(m_ent, tmp, &entry->children, post_ct_list) {
+			nfp_del_tc_merge_entry(m_ent);
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+void nfp_fl_ct_clean_flow_entry(struct nfp_fl_ct_flow_entry *entry)
+{
+	list_del(&entry->list_node);
+
+	if (!list_empty(&entry->children)) {
+		if (entry->type == CT_TYPE_NFT)
+			nfp_free_nft_merge_children(entry, true);
+		else
+			nfp_free_tc_merge_children(entry);
+	}
+
+	if (entry->tun_offset != NFP_FL_CT_NO_TUN)
+		kfree(entry->rule->action.entries[entry->tun_offset].tunnel);
+
+	if (entry->type == CT_TYPE_NFT) {
+		struct nf_flow_match *nft_match;
+
+		nft_match = container_of(entry->rule->match.dissector,
+					 struct nf_flow_match, dissector);
+		kfree(nft_match);
+	}
+
+	kfree(entry->rule);
+	kfree(entry);
+}
+
+static struct flow_action_entry *get_flow_act(struct flow_rule *rule,
+					      enum flow_action_id act_id)
+{
+	struct flow_action_entry *act = NULL;
+	int i;
+
+	flow_action_for_each(i, act, &rule->action) {
+		if (act->id == act_id)
+			return act;
+	}
+	return NULL;
+}
+
+static void
+nfp_ct_merge_tc_entries(struct nfp_fl_ct_flow_entry *ct_entry1,
+			struct nfp_fl_ct_zone_entry *zt_src,
+			struct nfp_fl_ct_zone_entry *zt_dst)
+{
+	struct nfp_fl_ct_flow_entry *ct_entry2, *ct_tmp;
+	struct list_head *ct_list;
+
+	if (ct_entry1->type == CT_TYPE_PRE_CT)
+		ct_list = &zt_src->post_ct_list;
+	else if (ct_entry1->type == CT_TYPE_POST_CT)
+		ct_list = &zt_src->pre_ct_list;
+	else
+		return;
+
+	list_for_each_entry_safe(ct_entry2, ct_tmp, ct_list,
+				 list_node) {
+		nfp_ct_do_tc_merge(zt_dst, ct_entry2, ct_entry1);
+	}
+}
+
+static void
+nfp_ct_merge_nft_with_tc(struct nfp_fl_ct_flow_entry *nft_entry,
+			 struct nfp_fl_ct_zone_entry *zt)
+{
+	struct nfp_fl_ct_tc_merge *tc_merge_entry;
+	struct rhashtable_iter iter;
+
+	rhashtable_walk_enter(&zt->tc_merge_tb, &iter);
+	rhashtable_walk_start(&iter);
+	while ((tc_merge_entry = rhashtable_walk_next(&iter)) != NULL) {
+		if (IS_ERR(tc_merge_entry))
+			continue;
+		rhashtable_walk_stop(&iter);
+		nfp_ct_do_nft_merge(zt, nft_entry, tc_merge_entry);
+		rhashtable_walk_start(&iter);
+	}
+	rhashtable_walk_stop(&iter);
+	rhashtable_walk_exit(&iter);
+}
+
+int nfp_fl_ct_handle_pre_ct(struct nfp_flower_priv *priv,
+			    struct net_device *netdev,
+			    struct flow_cls_offload *flow,
+			    struct netlink_ext_ack *extack)
+{
+	struct flow_action_entry *ct_act, *ct_goto;
+	struct nfp_fl_ct_flow_entry *ct_entry;
+	struct nfp_fl_ct_zone_entry *zt;
+	int err;
+
+	ct_act = get_flow_act(flow->rule, FLOW_ACTION_CT);
+	if (!ct_act) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "unsupported offload: Conntrack action empty in conntrack offload");
+		return -EOPNOTSUPP;
+	}
+
+	ct_goto = get_flow_act(flow->rule, FLOW_ACTION_GOTO);
+	if (!ct_goto) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "unsupported offload: Conntrack requires ACTION_GOTO");
+		return -EOPNOTSUPP;
+	}
+
+	zt = get_nfp_zone_entry(priv, ct_act->ct.zone, false);
+	if (IS_ERR(zt)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "offload error: Could not create zone table entry");
+		return PTR_ERR(zt);
+	}
+
+	if (!zt->nft) {
+		zt->nft = ct_act->ct.flow_table;
+		err = nf_flow_table_offload_add_cb(zt->nft, nfp_fl_ct_handle_nft_flow, zt);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "offload error: Could not register nft_callback");
+			return err;
+		}
+	}
+
+	/* Add entry to pre_ct_list */
+	ct_entry = nfp_fl_ct_add_flow(zt, netdev, flow, false, extack);
+	if (IS_ERR(ct_entry))
+		return PTR_ERR(ct_entry);
+	ct_entry->type = CT_TYPE_PRE_CT;
+	ct_entry->chain_index = ct_goto->chain_index;
+	list_add(&ct_entry->list_node, &zt->pre_ct_list);
+	zt->pre_ct_count++;
+
+	nfp_ct_merge_tc_entries(ct_entry, zt, zt);
+
+	/* Need to check and merge with tables in the wc_zone as well */
+	if (priv->ct_zone_wc)
+		nfp_ct_merge_tc_entries(ct_entry, priv->ct_zone_wc, zt);
+
+	return 0;
+}
+
+int nfp_fl_ct_handle_post_ct(struct nfp_flower_priv *priv,
+			     struct net_device *netdev,
+			     struct flow_cls_offload *flow,
+			     struct netlink_ext_ack *extack)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
+	struct nfp_fl_ct_flow_entry *ct_entry;
+	struct nfp_fl_ct_zone_entry *zt;
+	bool wildcarded = false;
+	struct flow_match_ct ct;
+
+	flow_rule_match_ct(rule, &ct);
+	if (!ct.mask->ct_zone) {
+		wildcarded = true;
+	} else if (ct.mask->ct_zone != U16_MAX) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "unsupported offload: partially wildcarded ct_zone is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	zt = get_nfp_zone_entry(priv, ct.key->ct_zone, wildcarded);
+	if (IS_ERR(zt)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "offload error: Could not create zone table entry");
+		return PTR_ERR(zt);
+	}
+
+	/* Add entry to post_ct_list */
+	ct_entry = nfp_fl_ct_add_flow(zt, netdev, flow, false, extack);
+	if (IS_ERR(ct_entry))
+		return PTR_ERR(ct_entry);
+
+	ct_entry->type = CT_TYPE_POST_CT;
+	ct_entry->chain_index = flow->common.chain_index;
+	list_add(&ct_entry->list_node, &zt->post_ct_list);
+	zt->post_ct_count++;
+
+	if (wildcarded) {
+		/* Iterate through all zone tables if not empty, look for merges with
+		 * pre_ct entries and merge them.
+		 */
+		struct rhashtable_iter iter;
+		struct nfp_fl_ct_zone_entry *zone_table;
+
+		rhashtable_walk_enter(&priv->ct_zone_table, &iter);
+		rhashtable_walk_start(&iter);
+		while ((zone_table = rhashtable_walk_next(&iter)) != NULL) {
+			if (IS_ERR(zone_table))
+				continue;
+			rhashtable_walk_stop(&iter);
+			nfp_ct_merge_tc_entries(ct_entry, zone_table, zone_table);
+			rhashtable_walk_start(&iter);
+		}
+		rhashtable_walk_stop(&iter);
+		rhashtable_walk_exit(&iter);
+	} else {
+		nfp_ct_merge_tc_entries(ct_entry, zt, zt);
+	}
+
+	return 0;
+}
+
+static int
+nfp_fl_ct_offload_nft_flow(struct nfp_fl_ct_zone_entry *zt, struct flow_cls_offload *flow)
+{
+	struct nfp_fl_ct_map_entry *ct_map_ent;
+	struct nfp_fl_ct_flow_entry *ct_entry;
+	struct netlink_ext_ack *extack = NULL;
+
+	ASSERT_RTNL();
+
+	extack = flow->common.extack;
+	switch (flow->command) {
+	case FLOW_CLS_REPLACE:
+		/* Netfilter can request offload multiple times for the same
+		 * flow - protect against adding duplicates.
+		 */
+		ct_map_ent = rhashtable_lookup_fast(&zt->priv->ct_map_table, &flow->cookie,
+						    nfp_ct_map_params);
+		if (!ct_map_ent) {
+			ct_entry = nfp_fl_ct_add_flow(zt, NULL, flow, true, extack);
+			ct_entry->type = CT_TYPE_NFT;
+			list_add(&ct_entry->list_node, &zt->nft_flows_list);
+			zt->nft_flows_count++;
+			nfp_ct_merge_nft_with_tc(ct_entry, zt);
+		}
+		return 0;
+	case FLOW_CLS_DESTROY:
+		ct_map_ent = rhashtable_lookup_fast(&zt->priv->ct_map_table, &flow->cookie,
+						    nfp_ct_map_params);
+		return nfp_fl_ct_del_flow(ct_map_ent);
+	case FLOW_CLS_STATS:
+		return 0;
+	default:
+		break;
+	}
+	return -EINVAL;
+}
+
+int nfp_fl_ct_handle_nft_flow(enum tc_setup_type type, void *type_data, void *cb_priv)
+{
+	struct flow_cls_offload *flow = type_data;
+	struct nfp_fl_ct_zone_entry *zt = cb_priv;
+	int err = -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		rtnl_lock();
+		err = nfp_fl_ct_offload_nft_flow(zt, flow);
+		rtnl_unlock();
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	return err;
+}
+
+static void
+nfp_fl_ct_clean_nft_entries(struct nfp_fl_ct_zone_entry *zt)
+{
+	struct nfp_fl_ct_flow_entry *nft_entry, *ct_tmp;
+	struct nfp_fl_ct_map_entry *ct_map_ent;
+
+	list_for_each_entry_safe(nft_entry, ct_tmp, &zt->nft_flows_list,
+				 list_node) {
+		ct_map_ent = rhashtable_lookup_fast(&zt->priv->ct_map_table,
+						    &nft_entry->cookie,
+						    nfp_ct_map_params);
+		nfp_fl_ct_del_flow(ct_map_ent);
+	}
+}
+
+int nfp_fl_ct_del_flow(struct nfp_fl_ct_map_entry *ct_map_ent)
+{
+	struct nfp_fl_ct_flow_entry *ct_entry;
+	struct nfp_fl_ct_zone_entry *zt;
+	struct rhashtable *m_table;
+
+	if (!ct_map_ent)
+		return -ENOENT;
+
+	zt = ct_map_ent->ct_entry->zt;
+	ct_entry = ct_map_ent->ct_entry;
+	m_table = &zt->priv->ct_map_table;
+
+	switch (ct_entry->type) {
+	case CT_TYPE_PRE_CT:
+		zt->pre_ct_count--;
+		rhashtable_remove_fast(m_table, &ct_map_ent->hash_node,
+				       nfp_ct_map_params);
+		nfp_fl_ct_clean_flow_entry(ct_entry);
+		kfree(ct_map_ent);
+
+		/* If this is the last pre_ct_rule it means that it is
+		 * very likely that the nft table will be cleaned up next,
+		 * as this happens on the removal of the last act_ct flow.
+		 * However we cannot deregister the callback on the removal
+		 * of the last nft flow as this runs into a deadlock situation.
+		 * So deregister the callback on removal of the last pre_ct flow
+		 * and remove any remaining nft flow entries. We also cannot
+		 * save this state and delete the callback later since the
+		 * nft table would already have been freed at that time.
+		 */
+		if (!zt->pre_ct_count) {
+			nf_flow_table_offload_del_cb(zt->nft,
+						     nfp_fl_ct_handle_nft_flow,
+						     zt);
+			zt->nft = NULL;
+			nfp_fl_ct_clean_nft_entries(zt);
+		}
+		break;
+	case CT_TYPE_POST_CT:
+		zt->post_ct_count--;
+		rhashtable_remove_fast(m_table, &ct_map_ent->hash_node,
+				       nfp_ct_map_params);
+		nfp_fl_ct_clean_flow_entry(ct_entry);
+		kfree(ct_map_ent);
+		break;
+	case CT_TYPE_NFT:
+		zt->nft_flows_count--;
+		rhashtable_remove_fast(m_table, &ct_map_ent->hash_node,
+				       nfp_ct_map_params);
+		nfp_fl_ct_clean_flow_entry(ct_map_ent->ct_entry);
+		kfree(ct_map_ent);
+	default:
+		break;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.h b/drivers/net/ethernet/netronome/nfp/flower/conntrack.h
new file mode 100644
index 000000000000..170b6cdb8cd0
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.h
@@ -0,0 +1,231 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (C) 2021 Corigine, Inc. */
+
+#ifndef __NFP_FLOWER_CONNTRACK_H__
+#define __NFP_FLOWER_CONNTRACK_H__ 1
+
+#include <net/netfilter/nf_flow_table.h>
+#include "main.h"
+
+#define NFP_FL_CT_NO_TUN	0xff
+
+#define COMPARE_UNMASKED_FIELDS(__match1, __match2, __out)	\
+	do {							\
+		typeof(__match1) _match1 = (__match1);		\
+		typeof(__match2) _match2 = (__match2);		\
+		bool *_out = (__out);		\
+		int i, size = sizeof(*(_match1).key);		\
+		char *k1, *m1, *k2, *m2;			\
+		*_out = false;					\
+		k1 = (char *)_match1.key;			\
+		m1 = (char *)_match1.mask;			\
+		k2 = (char *)_match2.key;			\
+		m2 = (char *)_match2.mask;			\
+		for (i = 0; i < size; i++)			\
+			if ((k1[i] & m1[i] & m2[i]) ^		\
+			    (k2[i] & m1[i] & m2[i])) {		\
+				*_out = true;			\
+				break;				\
+			}					\
+	} while (0)						\
+
+extern const struct rhashtable_params nfp_zone_table_params;
+extern const struct rhashtable_params nfp_ct_map_params;
+extern const struct rhashtable_params nfp_tc_ct_merge_params;
+extern const struct rhashtable_params nfp_nft_ct_merge_params;
+
+/**
+ * struct nfp_fl_ct_zone_entry - Zone entry containing conntrack flow information
+ * @zone:	The zone number, used as lookup key in hashtable
+ * @hash_node:	Used by the hashtable
+ * @priv:	Pointer to nfp_flower_priv data
+ * @nft:	Pointer to nf_flowtable for this zone
+ *
+ * @pre_ct_list:	The pre_ct_list of nfp_fl_ct_flow_entry entries
+ * @pre_ct_count:	Keep count of the number of pre_ct entries
+ *
+ * @post_ct_list:	The post_ct_list of nfp_fl_ct_flow_entry entries
+ * @post_ct_count:	Keep count of the number of post_ct entries
+ *
+ * @tc_merge_tb:	The table of merged tc flows
+ * @tc_merge_count:	Keep count of the number of merged tc entries
+ *
+ * @nft_flows_list:	The list of nft relatednfp_fl_ct_flow_entry entries
+ * @nft_flows_count:	Keep count of the number of nft_flow entries
+ *
+ * @nft_merge_tb:	The table of merged tc+nft flows
+ * @nft_merge_count:	Keep count of the number of merged tc+nft entries
+ */
+struct nfp_fl_ct_zone_entry {
+	u16 zone;
+	struct rhash_head hash_node;
+
+	struct nfp_flower_priv *priv;
+	struct nf_flowtable *nft;
+
+	struct list_head pre_ct_list;
+	unsigned int pre_ct_count;
+
+	struct list_head post_ct_list;
+	unsigned int post_ct_count;
+
+	struct rhashtable tc_merge_tb;
+	unsigned int tc_merge_count;
+
+	struct list_head nft_flows_list;
+	unsigned int nft_flows_count;
+
+	struct rhashtable nft_merge_tb;
+	unsigned int nft_merge_count;
+};
+
+enum ct_entry_type {
+	CT_TYPE_PRE_CT,
+	CT_TYPE_NFT,
+	CT_TYPE_POST_CT,
+};
+
+/**
+ * struct nfp_fl_ct_flow_entry - Flow entry containing conntrack flow information
+ * @cookie:	Flow cookie, same as original TC flow, used as key
+ * @list_node:	Used by the list
+ * @chain_index:	Chain index of the original flow
+ * @netdev:	netdev structure.
+ * @type:	Type of pre-entry from enum ct_entry_type
+ * @zt:		Reference to the zone table this belongs to
+ * @children:	List of tc_merge flows this flow forms part of
+ * @rule:	Reference to the original TC flow rule
+ * @stats:	Used to cache stats for updating
+ * @tun_offset: Used to indicate tunnel action offset in action list
+ */
+struct nfp_fl_ct_flow_entry {
+	unsigned long cookie;
+	struct list_head list_node;
+	u32 chain_index;
+	enum ct_entry_type type;
+	struct net_device *netdev;
+	struct nfp_fl_ct_zone_entry *zt;
+	struct list_head children;
+	struct flow_rule *rule;
+	struct flow_stats stats;
+	u8 tun_offset;		// Set to NFP_FL_CT_NO_TUN if no tun
+};
+
+/**
+ * struct nfp_fl_ct_tc_merge - Merge of two flows from tc
+ * @cookie:		Flow cookie, combination of pre and post ct cookies
+ * @hash_node:		Used by the hashtable
+ * @pre_ct_list:	This entry is part of a pre_ct_list
+ * @post_ct_list:	This entry is part of a post_ct_list
+ * @zt:			Reference to the zone table this belongs to
+ * @pre_ct_parent:	The pre_ct_parent
+ * @post_ct_parent:	The post_ct_parent
+ * @children:		List of nft merged entries
+ */
+struct nfp_fl_ct_tc_merge {
+	unsigned long cookie[2];
+	struct rhash_head hash_node;
+	struct list_head pre_ct_list;
+	struct list_head post_ct_list;
+	struct nfp_fl_ct_zone_entry *zt;
+	struct nfp_fl_ct_flow_entry *pre_ct_parent;
+	struct nfp_fl_ct_flow_entry *post_ct_parent;
+	struct list_head children;
+};
+
+/**
+ * struct nfp_fl_nft_tc_merge - Merge of tc_merge flows with nft flow
+ * @netdev:		Ingress netdev name
+ * @cookie:		Flow cookie, combination of tc_merge and nft cookies
+ * @hash_node:		Used by the hashtable
+ * @zt:	Reference to the zone table this belongs to
+ * @nft_flow_list:	This entry is part of a nft_flows_list
+ * @tc_merge_list:	This entry is part of a ct_merge_list
+ * @tc_m_parent:	The tc_merge parent
+ * @nft_parent:	The nft_entry parent
+ * @tc_flower_cookie:	The cookie of the flow offloaded to the nfp
+ * @flow_pay:	Reference to the offloaded flow struct
+ */
+struct nfp_fl_nft_tc_merge {
+	struct net_device *netdev;
+	unsigned long cookie[3];
+	struct rhash_head hash_node;
+	struct nfp_fl_ct_zone_entry *zt;
+	struct list_head nft_flow_list;
+	struct list_head tc_merge_list;
+	struct nfp_fl_ct_tc_merge *tc_m_parent;
+	struct nfp_fl_ct_flow_entry *nft_parent;
+	unsigned long tc_flower_cookie;
+	struct nfp_fl_payload *flow_pay;
+};
+
+/**
+ * struct nfp_fl_ct_map_entry - Map between flow cookie and specific ct_flow
+ * @cookie:	Flow cookie, same as original TC flow, used as key
+ * @hash_node:	Used by the hashtable
+ * @ct_entry:	Pointer to corresponding ct_entry
+ */
+struct nfp_fl_ct_map_entry {
+	unsigned long cookie;
+	struct rhash_head hash_node;
+	struct nfp_fl_ct_flow_entry *ct_entry;
+};
+
+bool is_pre_ct_flow(struct flow_cls_offload *flow);
+bool is_post_ct_flow(struct flow_cls_offload *flow);
+
+/**
+ * nfp_fl_ct_handle_pre_ct() - Handles -trk conntrack rules
+ * @priv:	Pointer to app priv
+ * @netdev:	netdev structure.
+ * @flow:	TC flower classifier offload structure.
+ * @extack:	Extack pointer for errors
+ *
+ * Adds a new entry to the relevant zone table and tries to
+ * merge with other +trk+est entries and offload if possible.
+ *
+ * Return: negative value on error, 0 if configured successfully.
+ */
+int nfp_fl_ct_handle_pre_ct(struct nfp_flower_priv *priv,
+			    struct net_device *netdev,
+			    struct flow_cls_offload *flow,
+			    struct netlink_ext_ack *extack);
+/**
+ * nfp_fl_ct_handle_post_ct() - Handles +trk+est conntrack rules
+ * @priv:	Pointer to app priv
+ * @netdev:	netdev structure.
+ * @flow:	TC flower classifier offload structure.
+ * @extack:	Extack pointer for errors
+ *
+ * Adds a new entry to the relevant zone table and tries to
+ * merge with other -trk entries and offload if possible.
+ *
+ * Return: negative value on error, 0 if configured successfully.
+ */
+int nfp_fl_ct_handle_post_ct(struct nfp_flower_priv *priv,
+			     struct net_device *netdev,
+			     struct flow_cls_offload *flow,
+			     struct netlink_ext_ack *extack);
+
+/**
+ * nfp_fl_ct_clean_flow_entry() - Free a nfp_fl_ct_flow_entry
+ * @entry:	Flow entry to cleanup
+ */
+void nfp_fl_ct_clean_flow_entry(struct nfp_fl_ct_flow_entry *entry);
+
+/**
+ * nfp_fl_ct_del_flow() - Handle flow_del callbacks for conntrack
+ * @ct_map_ent:	ct map entry for the flow that needs deleting
+ */
+int nfp_fl_ct_del_flow(struct nfp_fl_ct_map_entry *ct_map_ent);
+
+/**
+ * nfp_fl_ct_handle_nft_flow() - Handle flower flow callbacks for nft table
+ * @type:	Type provided by callback
+ * @type_data:	Callback data
+ * @cb_priv:	Pointer to data provided when registering the callback, in this
+ *		case it's the zone table.
+ */
+int nfp_fl_ct_handle_nft_flow(enum tc_setup_type type, void *type_data,
+			      void *cb_priv);
+#endif
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index 31377923ea3d..0fbd682ccf72 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -193,6 +193,9 @@ struct nfp_fl_internal_ports {
  * @qos_stats_lock:	Lock on qos stats updates
  * @pre_tun_rule_cnt:	Number of pre-tunnel rules offloaded
  * @merge_table:	Hash table to store merged flows
+ * @ct_zone_table:	Hash table used to store the different zones
+ * @ct_zone_wc:		Special zone entry for wildcarded zone matches
+ * @ct_map_table:	Hash table used to referennce ct flows
  */
 struct nfp_flower_priv {
 	struct nfp_app *app;
@@ -227,6 +230,9 @@ struct nfp_flower_priv {
 	spinlock_t qos_stats_lock; /* Protect the qos stats */
 	int pre_tun_rule_cnt;
 	struct rhashtable merge_table;
+	struct rhashtable ct_zone_table;
+	struct nfp_fl_ct_zone_entry *ct_zone_wc;
+	struct rhashtable ct_map_table;
 };
 
 /**
diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
index 327bb56b3ef5..621113650a9b 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
@@ -9,6 +9,7 @@
 #include <net/pkt_cls.h>
 
 #include "cmsg.h"
+#include "conntrack.h"
 #include "main.h"
 #include "../nfp_app.h"
 
@@ -496,6 +497,20 @@ const struct rhashtable_params merge_table_params = {
 	.key_len	= sizeof(u64),
 };
 
+const struct rhashtable_params nfp_zone_table_params = {
+	.head_offset		= offsetof(struct nfp_fl_ct_zone_entry, hash_node),
+	.key_len		= sizeof(u16),
+	.key_offset		= offsetof(struct nfp_fl_ct_zone_entry, zone),
+	.automatic_shrinking	= false,
+};
+
+const struct rhashtable_params nfp_ct_map_params = {
+	.head_offset		= offsetof(struct nfp_fl_ct_map_entry, hash_node),
+	.key_len		= sizeof(unsigned long),
+	.key_offset		= offsetof(struct nfp_fl_ct_map_entry, cookie),
+	.automatic_shrinking	= true,
+};
+
 int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
 			     unsigned int host_num_mems)
 {
@@ -516,6 +531,14 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
 	if (err)
 		goto err_free_stats_ctx_table;
 
+	err = rhashtable_init(&priv->ct_zone_table, &nfp_zone_table_params);
+	if (err)
+		goto err_free_merge_table;
+
+	err = rhashtable_init(&priv->ct_map_table, &nfp_ct_map_params);
+	if (err)
+		goto err_free_ct_zone_table;
+
 	get_random_bytes(&priv->mask_id_seed, sizeof(priv->mask_id_seed));
 
 	/* Init ring buffer and unallocated mask_ids. */
@@ -523,7 +546,7 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
 		kmalloc_array(NFP_FLOWER_MASK_ENTRY_RS,
 			      NFP_FLOWER_MASK_ELEMENT_RS, GFP_KERNEL);
 	if (!priv->mask_ids.mask_id_free_list.buf)
-		goto err_free_merge_table;
+		goto err_free_ct_map_table;
 
 	priv->mask_ids.init_unallocated = NFP_FLOWER_MASK_ENTRY_RS - 1;
 
@@ -560,6 +583,10 @@ err_free_last_used:
 	kfree(priv->mask_ids.last_used);
 err_free_mask_id:
 	kfree(priv->mask_ids.mask_id_free_list.buf);
+err_free_ct_map_table:
+	rhashtable_destroy(&priv->ct_map_table);
+err_free_ct_zone_table:
+	rhashtable_destroy(&priv->ct_zone_table);
 err_free_merge_table:
 	rhashtable_destroy(&priv->merge_table);
 err_free_stats_ctx_table:
@@ -569,6 +596,100 @@ err_free_flow_table:
 	return -ENOMEM;
 }
 
+static void nfp_zone_table_entry_destroy(struct nfp_fl_ct_zone_entry *zt)
+{
+	if (!zt)
+		return;
+
+	if (!list_empty(&zt->pre_ct_list)) {
+		struct rhashtable *m_table = &zt->priv->ct_map_table;
+		struct nfp_fl_ct_flow_entry *entry, *tmp;
+		struct nfp_fl_ct_map_entry *map;
+
+		WARN_ONCE(1, "pre_ct_list not empty as expected, cleaning up\n");
+		list_for_each_entry_safe(entry, tmp, &zt->pre_ct_list,
+					 list_node) {
+			map = rhashtable_lookup_fast(m_table,
+						     &entry->cookie,
+						     nfp_ct_map_params);
+			WARN_ON_ONCE(rhashtable_remove_fast(m_table,
+							    &map->hash_node,
+							    nfp_ct_map_params));
+			nfp_fl_ct_clean_flow_entry(entry);
+			kfree(map);
+		}
+	}
+
+	if (!list_empty(&zt->post_ct_list)) {
+		struct rhashtable *m_table = &zt->priv->ct_map_table;
+		struct nfp_fl_ct_flow_entry *entry, *tmp;
+		struct nfp_fl_ct_map_entry *map;
+
+		WARN_ONCE(1, "post_ct_list not empty as expected, cleaning up\n");
+		list_for_each_entry_safe(entry, tmp, &zt->post_ct_list,
+					 list_node) {
+			map = rhashtable_lookup_fast(m_table,
+						     &entry->cookie,
+						     nfp_ct_map_params);
+			WARN_ON_ONCE(rhashtable_remove_fast(m_table,
+							    &map->hash_node,
+							    nfp_ct_map_params));
+			nfp_fl_ct_clean_flow_entry(entry);
+			kfree(map);
+		}
+	}
+
+	if (zt->nft) {
+		nf_flow_table_offload_del_cb(zt->nft,
+					     nfp_fl_ct_handle_nft_flow,
+					     zt);
+		zt->nft = NULL;
+	}
+
+	if (!list_empty(&zt->nft_flows_list)) {
+		struct rhashtable *m_table = &zt->priv->ct_map_table;
+		struct nfp_fl_ct_flow_entry *entry, *tmp;
+		struct nfp_fl_ct_map_entry *map;
+
+		WARN_ONCE(1, "nft_flows_list not empty as expected, cleaning up\n");
+		list_for_each_entry_safe(entry, tmp, &zt->nft_flows_list,
+					 list_node) {
+			map = rhashtable_lookup_fast(m_table,
+						     &entry->cookie,
+						     nfp_ct_map_params);
+			WARN_ON_ONCE(rhashtable_remove_fast(m_table,
+							    &map->hash_node,
+							    nfp_ct_map_params));
+			nfp_fl_ct_clean_flow_entry(entry);
+			kfree(map);
+		}
+	}
+
+	rhashtable_free_and_destroy(&zt->tc_merge_tb,
+				    nfp_check_rhashtable_empty, NULL);
+	rhashtable_free_and_destroy(&zt->nft_merge_tb,
+				    nfp_check_rhashtable_empty, NULL);
+
+	kfree(zt);
+}
+
+static void nfp_free_zone_table_entry(void *ptr, void *arg)
+{
+	struct nfp_fl_ct_zone_entry *zt = ptr;
+
+	nfp_zone_table_entry_destroy(zt);
+}
+
+static void nfp_free_map_table_entry(void *ptr, void *arg)
+{
+	struct nfp_fl_ct_map_entry *map = ptr;
+
+	if (!map)
+		return;
+
+	kfree(map);
+}
+
 void nfp_flower_metadata_cleanup(struct nfp_app *app)
 {
 	struct nfp_flower_priv *priv = app->priv;
@@ -582,6 +703,12 @@ void nfp_flower_metadata_cleanup(struct nfp_app *app)
 				    nfp_check_rhashtable_empty, NULL);
 	rhashtable_free_and_destroy(&priv->merge_table,
 				    nfp_check_rhashtable_empty, NULL);
+	rhashtable_free_and_destroy(&priv->ct_zone_table,
+				    nfp_free_zone_table_entry, NULL);
+	nfp_zone_table_entry_destroy(priv->ct_zone_wc);
+
+	rhashtable_free_and_destroy(&priv->ct_map_table,
+				    nfp_free_map_table_entry, NULL);
 	kvfree(priv->stats);
 	kfree(priv->mask_ids.mask_id_free_list.buf);
 	kfree(priv->mask_ids.last_used);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index e95969c462e4..2406d33356ad 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -7,6 +7,7 @@
 
 #include "cmsg.h"
 #include "main.h"
+#include "conntrack.h"
 #include "../nfpcore/nfp_cpp.h"
 #include "../nfpcore/nfp_nsp.h"
 #include "../nfp_app.h"
@@ -1276,6 +1277,20 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app,
 	return 0;
 }
 
+static bool offload_pre_check(struct flow_cls_offload *flow)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
+	struct flow_dissector *dissector = rule->match.dissector;
+
+	if (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT))
+		return false;
+
+	if (flow->common.chain_index)
+		return false;
+
+	return true;
+}
+
 /**
  * nfp_flower_add_offload() - Adds a new flow to hardware.
  * @app:	Pointer to the APP handle
@@ -1302,6 +1317,15 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 	if (nfp_netdev_is_nfp_repr(netdev))
 		port = nfp_port_from_netdev(netdev);
 
+	if (is_pre_ct_flow(flow))
+		return nfp_fl_ct_handle_pre_ct(priv, netdev, flow, extack);
+
+	if (is_post_ct_flow(flow))
+		return nfp_fl_ct_handle_post_ct(priv, netdev, flow, extack);
+
+	if (!offload_pre_check(flow))
+		return -EOPNOTSUPP;
+
 	key_layer = kmalloc(sizeof(*key_layer), GFP_KERNEL);
 	if (!key_layer)
 		return -ENOMEM;
@@ -1481,6 +1505,7 @@ nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev,
 		       struct flow_cls_offload *flow)
 {
 	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_fl_ct_map_entry *ct_map_ent;
 	struct netlink_ext_ack *extack = NULL;
 	struct nfp_fl_payload *nfp_flow;
 	struct nfp_port *port = NULL;
@@ -1490,6 +1515,14 @@ nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev,
 	if (nfp_netdev_is_nfp_repr(netdev))
 		port = nfp_port_from_netdev(netdev);
 
+	/* Check ct_map_table */
+	ct_map_ent = rhashtable_lookup_fast(&priv->ct_map_table, &flow->cookie,
+					    nfp_ct_map_params);
+	if (ct_map_ent) {
+		err = nfp_fl_ct_del_flow(ct_map_ent);
+		return err;
+	}
+
 	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, netdev);
 	if (!nfp_flow) {
 		NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot remove flow that does not exist");
@@ -1646,9 +1679,10 @@ nfp_flower_repr_offload(struct nfp_app *app, struct net_device *netdev,
 static int nfp_flower_setup_tc_block_cb(enum tc_setup_type type,
 					void *type_data, void *cb_priv)
 {
+	struct flow_cls_common_offload *common = type_data;
 	struct nfp_repr *repr = cb_priv;
 
-	if (!tc_cls_can_offload_and_chain0(repr->netdev, type_data))
+	if (!tc_can_offload_extack(repr->netdev, common->extack))
 		return -EOPNOTSUPP;
 
 	switch (type) {
@@ -1746,10 +1780,6 @@ static int nfp_flower_setup_indr_block_cb(enum tc_setup_type type,
 					  void *type_data, void *cb_priv)
 {
 	struct nfp_flower_indr_block_cb_priv *priv = cb_priv;
-	struct flow_cls_offload *flower = type_data;
-
-	if (flower->common.chain_index)
-		return -EOPNOTSUPP;
 
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index d19c02e99114..ab70179728f6 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -21,7 +21,7 @@
 #define NFP_TUN_PRE_TUN_IPV6_BIT	BIT(7)
 
 /**
- * struct nfp_tun_pre_run_rule - rule matched before decap
+ * struct nfp_tun_pre_tun_rule - rule matched before decap
  * @flags:		options for the rule offset
  * @port_idx:		index of destination MAC address for the rule
  * @vlan_tci:		VLAN info associated with MAC
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
index 94994a939277..d7ac0307797f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
@@ -905,8 +905,7 @@ area_cache_put(struct nfp_cpp *cpp, struct nfp_cpp_area_cache *cache)
 		return;
 
 	/* Move to front of LRU */
-	list_del(&cache->entry);
-	list_add(&cache->entry, &cpp->area_cache_list);
+	list_move(&cache->entry, &cpp->area_cache_list);
 
 	mutex_unlock(&cpp->area_cache_mutex);
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c
index d4e02542e2e9..e2e5fd003ad6 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c
@@ -24,7 +24,7 @@
 
 #define NFFW_FWID_ALL   255
 
-/**
+/*
  * NFFW_INFO_VERSION history:
  * 0: This was never actually used (before versioning), but it refers to
  *    the previous struct which had FWINFO_CNT = MEINFO_CNT = 120 that later
diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index a6861df9904f..2d097dcb7bda 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -1224,7 +1224,6 @@ static int nixge_of_get_resources(struct platform_device *pdev)
 	const struct of_device_id *of_id;
 	enum nixge_version version;
 	struct resource *ctrlres;
-	struct resource *dmares;
 	struct net_device *ndev;
 	struct nixge_priv *priv;
 
@@ -1236,12 +1235,9 @@ static int nixge_of_get_resources(struct platform_device *pdev)
 
 	version = (enum nixge_version)of_id->data;
 	if (version <= NIXGE_V2)
-		dmares = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+		priv->dma_regs = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
 	else
-		dmares = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-						      "dma");
-
-	priv->dma_regs = devm_ioremap_resource(&pdev->dev, dmares);
+		priv->dma_regs = devm_platform_ioremap_resource_byname(pdev, "dma");
 	if (IS_ERR(priv->dma_regs)) {
 		netdev_err(ndev, "failed to map dma regs\n");
 		return PTR_ERR(priv->dma_regs);
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
index a6823c4d355d..108f312bc542 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
@@ -596,8 +596,6 @@ struct pch_gbe_adapter {
 
 #define pch_gbe_hw_to_adapter(hw)	container_of(hw, struct pch_gbe_adapter, hw)
 
-extern const char pch_driver_version[];
-
 /* pch_gbe_main.c */
 int pch_gbe_up(struct pch_gbe_adapter *adapter);
 void pch_gbe_down(struct pch_gbe_adapter *adapter);
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
index a58f14aca10c..660b07cb5b92 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
@@ -8,6 +8,8 @@
 #include "pch_gbe.h"
 #include "pch_gbe_phy.h"
 
+static const char pch_driver_version[] = "1.01";
+
 /*
  * pch_gbe_stats - Stats item information
  */
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 334af49e5add..e351f3d1608f 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -8,15 +8,16 @@
 
 #include "pch_gbe.h"
 #include "pch_gbe_phy.h"
+
+#include <linux/gpio/consumer.h>
+#include <linux/gpio/machine.h>
+#include <linux/iopoll.h>
 #include <linux/module.h>
 #include <linux/net_tstamp.h>
 #include <linux/ptp_classify.h>
 #include <linux/ptp_pch.h>
 #include <linux/gpio.h>
 
-#define DRV_VERSION     "1.01"
-const char pch_driver_version[] = DRV_VERSION;
-
 #define PCH_GBE_MAR_ENTRIES		16
 #define PCH_GBE_SHORT_PKT		64
 #define DSC_INIT16			0xC000
@@ -97,8 +98,6 @@ const char pch_driver_version[] = DRV_VERSION;
 #define PTP_L4_MULTICAST_SA "01:00:5e:00:01:81"
 #define PTP_L2_MULTICAST_SA "01:1b:19:00:00:00"
 
-#define MINNOW_PHY_RESET_GPIO		13
-
 static int pch_gbe_mdio_read(struct net_device *netdev, int addr, int reg);
 static void pch_gbe_mdio_write(struct net_device *netdev, int addr, int reg,
 			       int data);
@@ -108,7 +107,7 @@ static int pch_ptp_match(struct sk_buff *skb, u16 uid_hi, u32 uid_lo, u16 seqid)
 {
 	u8 *data = skb->data;
 	unsigned int offset;
-	u16 *hi, *id;
+	u16 hi, id;
 	u32 lo;
 
 	if (ptp_classify_raw(skb) == PTP_CLASS_NONE)
@@ -119,14 +118,11 @@ static int pch_ptp_match(struct sk_buff *skb, u16 uid_hi, u32 uid_lo, u16 seqid)
 	if (skb->len < offset + OFF_PTP_SEQUENCE_ID + sizeof(seqid))
 		return 0;
 
-	hi = (u16 *)(data + offset + OFF_PTP_SOURCE_UUID);
-	id = (u16 *)(data + offset + OFF_PTP_SEQUENCE_ID);
-
-	memcpy(&lo, &hi[1], sizeof(lo));
+	hi = get_unaligned_be16(data + offset + OFF_PTP_SOURCE_UUID + 0);
+	lo = get_unaligned_be32(data + offset + OFF_PTP_SOURCE_UUID + 2);
+	id = get_unaligned_be16(data + offset + OFF_PTP_SEQUENCE_ID);
 
-	return (uid_hi == *hi &&
-		uid_lo == lo &&
-		seqid  == *id);
+	return (uid_hi == hi && uid_lo == lo && seqid == id);
 }
 
 static void
@@ -136,7 +132,6 @@ pch_rx_timestamp(struct pch_gbe_adapter *adapter, struct sk_buff *skb)
 	struct pci_dev *pdev;
 	u64 ns;
 	u32 hi, lo, val;
-	u16 uid, seq;
 
 	if (!adapter->hwts_rx_en)
 		return;
@@ -152,10 +147,7 @@ pch_rx_timestamp(struct pch_gbe_adapter *adapter, struct sk_buff *skb)
 	lo = pch_src_uuid_lo_read(pdev);
 	hi = pch_src_uuid_hi_read(pdev);
 
-	uid = hi & 0xffff;
-	seq = (hi >> 16) & 0xffff;
-
-	if (!pch_ptp_match(skb, htons(uid), htonl(lo), htons(seq)))
+	if (!pch_ptp_match(skb, hi, lo, hi >> 16))
 		goto out;
 
 	ns = pch_rx_snap_read(pdev);
@@ -298,15 +290,12 @@ static s32 pch_gbe_mac_read_mac_addr(struct pch_gbe_hw *hw)
  * @reg:	Pointer of register
  * @bit:	Busy bit
  */
-static void pch_gbe_wait_clr_bit(void *reg, u32 bit)
+static void pch_gbe_wait_clr_bit(void __iomem *reg, u32 bit)
 {
 	u32 tmp;
 
 	/* wait busy */
-	tmp = 1000;
-	while ((ioread32(reg) & bit) && --tmp)
-		cpu_relax();
-	if (!tmp)
+	if (readx_poll_timeout_atomic(ioread32, reg, tmp, !(tmp & bit), 0, 10))
 		pr_err("Error: busy bit is not cleared\n");
 }
 
@@ -490,18 +479,13 @@ u16 pch_gbe_mac_ctrl_miim(struct pch_gbe_hw *hw, u32 addr, u32 dir, u32 reg,
 			u16 data)
 {
 	struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-	u32 data_out = 0;
-	unsigned int i;
 	unsigned long flags;
+	u32 data_out;
 
 	spin_lock_irqsave(&hw->miim_lock, flags);
 
-	for (i = 100; i; --i) {
-		if ((ioread32(&hw->reg->MIIM) & PCH_GBE_MIIM_OPER_READY))
-			break;
-		udelay(20);
-	}
-	if (i == 0) {
+	if (readx_poll_timeout_atomic(ioread32, &hw->reg->MIIM, data_out,
+				      data_out & PCH_GBE_MIIM_OPER_READY, 20, 2000)) {
 		netdev_err(adapter->netdev, "pch-gbe.miim won't go Ready\n");
 		spin_unlock_irqrestore(&hw->miim_lock, flags);
 		return 0;	/* No way to indicate timeout error */
@@ -509,12 +493,8 @@ u16 pch_gbe_mac_ctrl_miim(struct pch_gbe_hw *hw, u32 addr, u32 dir, u32 reg,
 	iowrite32(((reg << PCH_GBE_MIIM_REG_ADDR_SHIFT) |
 		  (addr << PCH_GBE_MIIM_PHY_ADDR_SHIFT) |
 		  dir | data), &hw->reg->MIIM);
-	for (i = 0; i < 100; i++) {
-		udelay(20);
-		data_out = ioread32(&hw->reg->MIIM);
-		if ((data_out & PCH_GBE_MIIM_OPER_READY))
-			break;
-	}
+	readx_poll_timeout_atomic(ioread32, &hw->reg->MIIM, data_out,
+				  data_out & PCH_GBE_MIIM_OPER_READY, 20, 2000);
 	spin_unlock_irqrestore(&hw->miim_lock, flags);
 
 	netdev_dbg(adapter->netdev, "PHY %s: reg=%d, data=0x%04X\n",
@@ -2532,9 +2512,13 @@ static int pch_gbe_probe(struct pci_dev *pdev,
 	adapter->pdev = pdev;
 	adapter->hw.back = adapter;
 	adapter->hw.reg = pcim_iomap_table(pdev)[PCH_GBE_PCI_BAR];
+
 	adapter->pdata = (struct pch_gbe_privdata *)pci_id->driver_data;
-	if (adapter->pdata && adapter->pdata->platform_init)
-		adapter->pdata->platform_init(pdev);
+	if (adapter->pdata && adapter->pdata->platform_init) {
+		ret = adapter->pdata->platform_init(pdev);
+		if (ret)
+			goto err_free_netdev;
+	}
 
 	adapter->ptp_pdev =
 		pci_get_domain_bus_and_slot(pci_domain_nr(adapter->pdev->bus),
@@ -2624,26 +2608,45 @@ err_free_netdev:
 	return ret;
 }
 
+static void pch_gbe_gpio_remove_table(void *table)
+{
+	gpiod_remove_lookup_table(table);
+}
+
+static int pch_gbe_gpio_add_table(struct device *dev, void *table)
+{
+	gpiod_add_lookup_table(table);
+	return devm_add_action_or_reset(dev, pch_gbe_gpio_remove_table, table);
+}
+
+static struct gpiod_lookup_table pch_gbe_minnow_gpio_table = {
+	.dev_id		= "0000:02:00.1",
+	.table		= {
+		GPIO_LOOKUP("sch_gpio.33158", 13, NULL, GPIO_ACTIVE_LOW),
+		{}
+	},
+};
+
 /* The AR803X PHY on the MinnowBoard requires a physical pin to be toggled to
  * ensure it is awake for probe and init. Request the line and reset the PHY.
  */
 static int pch_gbe_minnow_platform_init(struct pci_dev *pdev)
 {
-	unsigned long flags = GPIOF_DIR_OUT | GPIOF_INIT_HIGH | GPIOF_EXPORT;
-	unsigned gpio = MINNOW_PHY_RESET_GPIO;
+	struct gpio_desc *gpiod;
 	int ret;
 
-	ret = devm_gpio_request_one(&pdev->dev, gpio, flags,
-				    "minnow_phy_reset");
-	if (ret) {
-		dev_err(&pdev->dev,
-			"ERR: Can't request PHY reset GPIO line '%d'\n", gpio);
+	ret = pch_gbe_gpio_add_table(&pdev->dev, &pch_gbe_minnow_gpio_table);
+	if (ret)
 		return ret;
-	}
 
-	gpio_set_value(gpio, 0);
+	gpiod = devm_gpiod_get(&pdev->dev, NULL, GPIOD_OUT_HIGH);
+	if (IS_ERR(gpiod))
+		return dev_err_probe(&pdev->dev, PTR_ERR(gpiod),
+				     "Can't request PHY reset GPIO line\n");
+
+	gpiod_set_value(gpiod, 1);
 	usleep_range(1250, 1500);
-	gpio_set_value(gpio, 1);
+	gpiod_set_value(gpiod, 0);
 	usleep_range(1250, 1500);
 
 	return ret;
@@ -2722,7 +2725,6 @@ module_pci_driver(pch_gbe_driver);
 MODULE_DESCRIPTION("EG20T PCH Gigabit ethernet Driver");
 MODULE_AUTHOR("LAPIS SEMICONDUCTOR, <tshimizu818@gmail.com>");
 MODULE_LICENSE("GPL");
-MODULE_VERSION(DRV_VERSION);
 MODULE_DEVICE_TABLE(pci, pch_gbe_pcidev_id);
 
 /* pch_gbe_main.c */
diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig
index 6b5ddb07ee83..98f430905ffa 100644
--- a/drivers/net/ethernet/qlogic/Kconfig
+++ b/drivers/net/ethernet/qlogic/Kconfig
@@ -110,6 +110,9 @@ config QED_RDMA
 config QED_ISCSI
 	bool
 
+config QED_NVMETCP
+	bool
+
 config QED_FCOE
 	bool
 
diff --git a/drivers/net/ethernet/qlogic/qed/Makefile b/drivers/net/ethernet/qlogic/qed/Makefile
index 8251755ec18c..0d9c2fe0245d 100644
--- a/drivers/net/ethernet/qlogic/qed/Makefile
+++ b/drivers/net/ethernet/qlogic/qed/Makefile
@@ -28,6 +28,11 @@ qed-$(CONFIG_QED_ISCSI) += qed_iscsi.o
 qed-$(CONFIG_QED_LL2) += qed_ll2.o
 qed-$(CONFIG_QED_OOO) += qed_ooo.o
 
+qed-$(CONFIG_QED_NVMETCP) +=	\
+	qed_nvmetcp.o		\
+	qed_nvmetcp_fw_funcs.o	\
+	qed_nvmetcp_ip_services.o
+
 qed-$(CONFIG_QED_RDMA) +=	\
 	qed_iwarp.o		\
 	qed_rdma.o		\
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index a20cb8a0c377..b590c70539b5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -49,6 +49,8 @@ extern const struct qed_common_ops qed_common_ops_pass;
 #define QED_MIN_WIDS		(4)
 #define QED_PF_DEMS_SIZE        (4)
 
+#define QED_LLH_DONT_CARE 0
+
 /* cau states */
 enum qed_coalescing_mode {
 	QED_COAL_MODE_DISABLE,
@@ -200,6 +202,7 @@ enum qed_pci_personality {
 	QED_PCI_ETH,
 	QED_PCI_FCOE,
 	QED_PCI_ISCSI,
+	QED_PCI_NVMETCP,
 	QED_PCI_ETH_ROCE,
 	QED_PCI_ETH_IWARP,
 	QED_PCI_ETH_RDMA,
@@ -239,6 +242,7 @@ enum QED_FEATURE {
 	QED_PF_L2_QUE,
 	QED_VF,
 	QED_RDMA_CNQ,
+	QED_NVMETCP_CQ,
 	QED_ISCSI_CQ,
 	QED_FCOE_CQ,
 	QED_VF_L2_QUE,
@@ -284,6 +288,8 @@ struct qed_hw_info {
 	((dev)->hw_info.personality == QED_PCI_FCOE)
 #define QED_IS_ISCSI_PERSONALITY(dev)					\
 	((dev)->hw_info.personality == QED_PCI_ISCSI)
+#define QED_IS_NVMETCP_PERSONALITY(dev)					\
+	((dev)->hw_info.personality == QED_PCI_NVMETCP)
 
 	/* Resource Allocation scheme results */
 	u32				resc_start[QED_MAX_RESC];
@@ -592,6 +598,7 @@ struct qed_hwfn {
 	struct qed_ooo_info		*p_ooo_info;
 	struct qed_rdma_info		*p_rdma_info;
 	struct qed_iscsi_info		*p_iscsi_info;
+	struct qed_nvmetcp_info		*p_nvmetcp_info;
 	struct qed_fcoe_info		*p_fcoe_info;
 	struct qed_pf_params		pf_params;
 
@@ -828,6 +835,7 @@ struct qed_dev {
 		struct qed_eth_cb_ops		*eth;
 		struct qed_fcoe_cb_ops		*fcoe;
 		struct qed_iscsi_cb_ops		*iscsi;
+		struct qed_nvmetcp_cb_ops	*nvmetcp;
 	} protocol_ops;
 	void				*ops_cookie;
 
@@ -999,4 +1007,10 @@ int qed_mfw_fill_tlv_data(struct qed_hwfn *hwfn,
 void qed_hw_info_set_offload_tc(struct qed_hw_info *p_info, u8 tc);
 
 void qed_periodic_db_rec_start(struct qed_hwfn *p_hwfn);
+
+int qed_llh_add_src_tcp_port_filter(struct qed_dev *cdev, u16 src_port);
+int qed_llh_add_dst_tcp_port_filter(struct qed_dev *cdev, u16 dest_port);
+void qed_llh_remove_src_tcp_port_filter(struct qed_dev *cdev, u16 src_port);
+void qed_llh_remove_dst_tcp_port_filter(struct qed_dev *cdev, u16 src_port);
+void qed_llh_clear_all_filters(struct qed_dev *cdev);
 #endif /* _QED_H */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 0a22f8ce9a2c..5a0a3cbcc1c1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -94,14 +94,14 @@ struct src_ent {
 
 static bool src_proto(enum protocol_type type)
 {
-	return type == PROTOCOLID_ISCSI ||
+	return type == PROTOCOLID_TCP_ULP ||
 	       type == PROTOCOLID_FCOE ||
 	       type == PROTOCOLID_IWARP;
 }
 
 static bool tm_cid_proto(enum protocol_type type)
 {
-	return type == PROTOCOLID_ISCSI ||
+	return type == PROTOCOLID_TCP_ULP ||
 	       type == PROTOCOLID_FCOE ||
 	       type == PROTOCOLID_ROCE ||
 	       type == PROTOCOLID_IWARP;
@@ -2072,7 +2072,6 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks)
 						    PROTOCOLID_FCOE,
 						    p_params->num_cons,
 						    0);
-
 			qed_cxt_set_proto_tid_count(p_hwfn, PROTOCOLID_FCOE,
 						    QED_CXT_FCOE_TID_SEG, 0,
 						    p_params->num_tasks, true);
@@ -2090,13 +2089,12 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks)
 
 		if (p_params->num_cons && p_params->num_tasks) {
 			qed_cxt_set_proto_cid_count(p_hwfn,
-						    PROTOCOLID_ISCSI,
+						    PROTOCOLID_TCP_ULP,
 						    p_params->num_cons,
 						    0);
-
 			qed_cxt_set_proto_tid_count(p_hwfn,
-						    PROTOCOLID_ISCSI,
-						    QED_CXT_ISCSI_TID_SEG,
+						    PROTOCOLID_TCP_ULP,
+						    QED_CXT_TCP_ULP_TID_SEG,
 						    0,
 						    p_params->num_tasks,
 						    true);
@@ -2106,6 +2104,29 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks)
 		}
 		break;
 	}
+	case QED_PCI_NVMETCP:
+	{
+		struct qed_nvmetcp_pf_params *p_params;
+
+		p_params = &p_hwfn->pf_params.nvmetcp_pf_params;
+
+		if (p_params->num_cons && p_params->num_tasks) {
+			qed_cxt_set_proto_cid_count(p_hwfn,
+						    PROTOCOLID_TCP_ULP,
+						    p_params->num_cons,
+						    0);
+			qed_cxt_set_proto_tid_count(p_hwfn,
+						    PROTOCOLID_TCP_ULP,
+						    QED_CXT_TCP_ULP_TID_SEG,
+						    0,
+						    p_params->num_tasks,
+						    true);
+		} else {
+			DP_INFO(p_hwfn->cdev,
+				"NvmeTCP personality used without setting params!\n");
+		}
+		break;
+	}
 	default:
 		return -EINVAL;
 	}
@@ -2129,8 +2150,9 @@ int qed_cxt_get_tid_mem_info(struct qed_hwfn *p_hwfn,
 		seg = QED_CXT_FCOE_TID_SEG;
 		break;
 	case QED_PCI_ISCSI:
-		proto = PROTOCOLID_ISCSI;
-		seg = QED_CXT_ISCSI_TID_SEG;
+	case QED_PCI_NVMETCP:
+		proto = PROTOCOLID_TCP_ULP;
+		seg = QED_CXT_TCP_ULP_TID_SEG;
 		break;
 	default:
 		return -EINVAL;
@@ -2455,8 +2477,9 @@ int qed_cxt_get_task_ctx(struct qed_hwfn *p_hwfn,
 		seg = QED_CXT_FCOE_TID_SEG;
 		break;
 	case QED_PCI_ISCSI:
-		proto = PROTOCOLID_ISCSI;
-		seg = QED_CXT_ISCSI_TID_SEG;
+	case QED_PCI_NVMETCP:
+		proto = PROTOCOLID_TCP_ULP;
+		seg = QED_CXT_TCP_ULP_TID_SEG;
 		break;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.h b/drivers/net/ethernet/qlogic/qed/qed_cxt.h
index 056e79620a0e..8adb7ed0c12d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.h
@@ -50,7 +50,7 @@ int qed_cxt_get_cid_info(struct qed_hwfn *p_hwfn,
 int qed_cxt_get_tid_mem_info(struct qed_hwfn *p_hwfn,
 			     struct qed_tid_mem *p_info);
 
-#define QED_CXT_ISCSI_TID_SEG	PROTOCOLID_ISCSI
+#define QED_CXT_TCP_ULP_TID_SEG	PROTOCOLID_TCP_ULP
 #define QED_CXT_ROCE_TID_SEG	PROTOCOLID_ROCE
 #define QED_CXT_FCOE_TID_SEG	PROTOCOLID_FCOE
 enum qed_cxt_elem_type {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index d2f5855b2ea7..0410c3604abd 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -37,6 +37,7 @@
 #include "qed_sriov.h"
 #include "qed_vf.h"
 #include "qed_rdma.h"
+#include "qed_nvmetcp.h"
 
 static DEFINE_SPINLOCK(qm_lock);
 
@@ -667,7 +668,8 @@ qed_llh_set_engine_affin(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	}
 
 	/* Storage PF is bound to a single engine while L2 PF uses both */
-	if (QED_IS_FCOE_PERSONALITY(p_hwfn) || QED_IS_ISCSI_PERSONALITY(p_hwfn))
+	if (QED_IS_FCOE_PERSONALITY(p_hwfn) || QED_IS_ISCSI_PERSONALITY(p_hwfn) ||
+	    QED_IS_NVMETCP_PERSONALITY(p_hwfn))
 		eng = cdev->fir_affin ? QED_ENG1 : QED_ENG0;
 	else			/* L2_PERSONALITY */
 		eng = QED_BOTH_ENG;
@@ -1164,6 +1166,9 @@ void qed_llh_remove_mac_filter(struct qed_dev *cdev,
 	if (!test_bit(QED_MF_LLH_MAC_CLSS, &cdev->mf_bits))
 		goto out;
 
+	if (QED_IS_NVMETCP_PERSONALITY(p_hwfn))
+		return;
+
 	ether_addr_copy(filter.mac.addr, mac_addr);
 	rc = qed_llh_shadow_remove_filter(cdev, ppfid, &filter, &filter_idx,
 					  &ref_cnt);
@@ -1381,6 +1386,11 @@ void qed_resc_free(struct qed_dev *cdev)
 			qed_ooo_free(p_hwfn);
 		}
 
+		if (p_hwfn->hw_info.personality == QED_PCI_NVMETCP) {
+			qed_nvmetcp_free(p_hwfn);
+			qed_ooo_free(p_hwfn);
+		}
+
 		if (QED_IS_RDMA_PERSONALITY(p_hwfn) && rdma_info) {
 			qed_spq_unregister_async_cb(p_hwfn, rdma_info->proto);
 			qed_rdma_info_free(p_hwfn);
@@ -1423,6 +1433,7 @@ static u32 qed_get_pq_flags(struct qed_hwfn *p_hwfn)
 		flags |= PQ_FLAGS_OFLD;
 		break;
 	case QED_PCI_ISCSI:
+	case QED_PCI_NVMETCP:
 		flags |= PQ_FLAGS_ACK | PQ_FLAGS_OOO | PQ_FLAGS_OFLD;
 		break;
 	case QED_PCI_ETH_ROCE:
@@ -2263,10 +2274,11 @@ int qed_resc_alloc(struct qed_dev *cdev)
 			 * at the same time
 			 */
 			n_eqes += num_cons + 2 * MAX_NUM_VFS_BB + n_srq;
-		} else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) {
+		} else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI ||
+			   p_hwfn->hw_info.personality == QED_PCI_NVMETCP) {
 			num_cons =
 			    qed_cxt_get_proto_cid_count(p_hwfn,
-							PROTOCOLID_ISCSI,
+							PROTOCOLID_TCP_ULP,
 							NULL);
 			n_eqes += 2 * num_cons;
 		}
@@ -2313,6 +2325,15 @@ int qed_resc_alloc(struct qed_dev *cdev)
 				goto alloc_err;
 		}
 
+		if (p_hwfn->hw_info.personality == QED_PCI_NVMETCP) {
+			rc = qed_nvmetcp_alloc(p_hwfn);
+			if (rc)
+				goto alloc_err;
+			rc = qed_ooo_alloc(p_hwfn);
+			if (rc)
+				goto alloc_err;
+		}
+
 		if (QED_IS_RDMA_PERSONALITY(p_hwfn)) {
 			rc = qed_rdma_info_alloc(p_hwfn);
 			if (rc)
@@ -2393,6 +2414,11 @@ void qed_resc_setup(struct qed_dev *cdev)
 			qed_iscsi_setup(p_hwfn);
 			qed_ooo_setup(p_hwfn);
 		}
+
+		if (p_hwfn->hw_info.personality == QED_PCI_NVMETCP) {
+			qed_nvmetcp_setup(p_hwfn);
+			qed_ooo_setup(p_hwfn);
+		}
 	}
 }
 
@@ -2854,7 +2880,8 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn,
 
 	/* Protocol Configuration */
 	STORE_RT_REG(p_hwfn, PRS_REG_SEARCH_TCP_RT_OFFSET,
-		     (p_hwfn->hw_info.personality == QED_PCI_ISCSI) ? 1 : 0);
+		     ((p_hwfn->hw_info.personality == QED_PCI_ISCSI) ||
+			 (p_hwfn->hw_info.personality == QED_PCI_NVMETCP)) ? 1 : 0);
 	STORE_RT_REG(p_hwfn, PRS_REG_SEARCH_FCOE_RT_OFFSET,
 		     (p_hwfn->hw_info.personality == QED_PCI_FCOE) ? 1 : 0);
 	STORE_RT_REG(p_hwfn, PRS_REG_SEARCH_ROCE_RT_OFFSET, 0);
@@ -3535,14 +3562,21 @@ static void qed_hw_set_feat(struct qed_hwfn *p_hwfn)
 		feat_num[QED_ISCSI_CQ] = min_t(u32, sb_cnt.cnt,
 					       RESC_NUM(p_hwfn,
 							QED_CMDQS_CQS));
+
+	if (QED_IS_NVMETCP_PERSONALITY(p_hwfn))
+		feat_num[QED_NVMETCP_CQ] = min_t(u32, sb_cnt.cnt,
+						 RESC_NUM(p_hwfn,
+							  QED_CMDQS_CQS));
+
 	DP_VERBOSE(p_hwfn,
 		   NETIF_MSG_PROBE,
-		   "#PF_L2_QUEUES=%d VF_L2_QUEUES=%d #ROCE_CNQ=%d FCOE_CQ=%d ISCSI_CQ=%d #SBS=%d\n",
+		   "#PF_L2_QUEUES=%d VF_L2_QUEUES=%d #ROCE_CNQ=%d FCOE_CQ=%d ISCSI_CQ=%d NVMETCP_CQ=%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),
 		   (int)FEAT_NUM(p_hwfn, QED_FCOE_CQ),
 		   (int)FEAT_NUM(p_hwfn, QED_ISCSI_CQ),
+		   (int)FEAT_NUM(p_hwfn, QED_NVMETCP_CQ),
 		   (int)sb_cnt.cnt);
 }
 
@@ -3734,7 +3768,8 @@ int qed_hw_get_dflt_resc(struct qed_hwfn *p_hwfn,
 		break;
 	case QED_BDQ:
 		if (p_hwfn->hw_info.personality != QED_PCI_ISCSI &&
-		    p_hwfn->hw_info.personality != QED_PCI_FCOE)
+		    p_hwfn->hw_info.personality != QED_PCI_FCOE &&
+			p_hwfn->hw_info.personality != QED_PCI_NVMETCP)
 			*p_resc_num = 0;
 		else
 			*p_resc_num = 1;
@@ -3755,7 +3790,8 @@ int qed_hw_get_dflt_resc(struct qed_hwfn *p_hwfn,
 			*p_resc_start = 0;
 		else if (p_hwfn->cdev->num_ports_in_engine == 4)
 			*p_resc_start = p_hwfn->port_id;
-		else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI)
+		else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI ||
+			 p_hwfn->hw_info.personality == QED_PCI_NVMETCP)
 			*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;
@@ -5326,3 +5362,93 @@ void qed_set_fw_mac_addr(__le16 *fw_msb,
 	((u8 *)fw_lsb)[0] = mac[5];
 	((u8 *)fw_lsb)[1] = mac[4];
 }
+
+static int qed_llh_shadow_remove_all_filters(struct qed_dev *cdev, u8 ppfid)
+{
+	struct qed_llh_info *p_llh_info = cdev->p_llh_info;
+	struct qed_llh_filter_info *p_filters;
+	int rc;
+
+	rc = qed_llh_shadow_sanity(cdev, ppfid, 0, "remove_all");
+	if (rc)
+		return rc;
+
+	p_filters = p_llh_info->pp_filters[ppfid];
+	memset(p_filters, 0, NIG_REG_LLH_FUNC_FILTER_EN_SIZE *
+	       sizeof(*p_filters));
+
+	return 0;
+}
+
+static void qed_llh_clear_ppfid_filters(struct qed_dev *cdev, u8 ppfid)
+{
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn);
+	u8 filter_idx, abs_ppfid;
+	int rc = 0;
+
+	if (!p_ptt)
+		return;
+
+	if (!test_bit(QED_MF_LLH_PROTO_CLSS, &cdev->mf_bits) &&
+	    !test_bit(QED_MF_LLH_MAC_CLSS, &cdev->mf_bits))
+		goto out;
+
+	rc = qed_llh_abs_ppfid(cdev, ppfid, &abs_ppfid);
+	if (rc)
+		goto out;
+
+	rc = qed_llh_shadow_remove_all_filters(cdev, ppfid);
+	if (rc)
+		goto out;
+
+	for (filter_idx = 0; filter_idx < NIG_REG_LLH_FUNC_FILTER_EN_SIZE;
+	     filter_idx++) {
+		rc = qed_llh_remove_filter(p_hwfn, p_ptt,
+					   abs_ppfid, filter_idx);
+		if (rc)
+			goto out;
+	}
+out:
+	qed_ptt_release(p_hwfn, p_ptt);
+}
+
+int qed_llh_add_src_tcp_port_filter(struct qed_dev *cdev, u16 src_port)
+{
+	return qed_llh_add_protocol_filter(cdev, 0,
+					   QED_LLH_FILTER_TCP_SRC_PORT,
+					   src_port, QED_LLH_DONT_CARE);
+}
+
+void qed_llh_remove_src_tcp_port_filter(struct qed_dev *cdev, u16 src_port)
+{
+	qed_llh_remove_protocol_filter(cdev, 0,
+				       QED_LLH_FILTER_TCP_SRC_PORT,
+				       src_port, QED_LLH_DONT_CARE);
+}
+
+int qed_llh_add_dst_tcp_port_filter(struct qed_dev *cdev, u16 dest_port)
+{
+	return qed_llh_add_protocol_filter(cdev, 0,
+					   QED_LLH_FILTER_TCP_DEST_PORT,
+					   QED_LLH_DONT_CARE, dest_port);
+}
+
+void qed_llh_remove_dst_tcp_port_filter(struct qed_dev *cdev, u16 dest_port)
+{
+	qed_llh_remove_protocol_filter(cdev, 0,
+				       QED_LLH_FILTER_TCP_DEST_PORT,
+				       QED_LLH_DONT_CARE, dest_port);
+}
+
+void qed_llh_clear_all_filters(struct qed_dev *cdev)
+{
+	u8 ppfid;
+
+	if (!test_bit(QED_MF_LLH_PROTO_CLSS, &cdev->mf_bits) &&
+	    !test_bit(QED_MF_LLH_MAC_CLSS, &cdev->mf_bits))
+		return;
+
+	for (ppfid = 0; ppfid < cdev->p_llh_info->num_ppfid; ppfid++)
+		qed_llh_clear_ppfid_filters(cdev, ppfid);
+}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 559df9f4d656..fb1baa2da2d0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -20,6 +20,7 @@
 #include <linux/qed/fcoe_common.h>
 #include <linux/qed/eth_common.h>
 #include <linux/qed/iscsi_common.h>
+#include <linux/qed/nvmetcp_common.h>
 #include <linux/qed/iwarp_common.h>
 #include <linux/qed/rdma_common.h>
 #include <linux/qed/roce_common.h>
@@ -1118,7 +1119,7 @@ struct outer_tag_config_struct {
 /* personality per PF */
 enum personality_type {
 	BAD_PERSONALITY_TYP,
-	PERSONALITY_ISCSI,
+	PERSONALITY_TCP_ULP,
 	PERSONALITY_FCOE,
 	PERSONALITY_RDMA_AND_ETH,
 	PERSONALITY_RDMA,
@@ -12147,7 +12148,8 @@ struct public_func {
 #define FUNC_MF_CFG_PROTOCOL_ISCSI              0x00000010
 #define FUNC_MF_CFG_PROTOCOL_FCOE               0x00000020
 #define FUNC_MF_CFG_PROTOCOL_ROCE               0x00000030
-#define FUNC_MF_CFG_PROTOCOL_MAX	0x00000030
+#define FUNC_MF_CFG_PROTOCOL_NVMETCP    0x00000040
+#define FUNC_MF_CFG_PROTOCOL_MAX	0x00000040
 
 #define FUNC_MF_CFG_MIN_BW_MASK		0x0000ff00
 #define FUNC_MF_CFG_MIN_BW_SHIFT	8
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
index 4eae4ee3538f..db926d8b3033 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
@@ -158,7 +158,7 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn,
 
 	rc = qed_sp_init_request(p_hwfn, &p_ent,
 				 ISCSI_RAMROD_CMD_ID_INIT_FUNC,
-				 PROTOCOLID_ISCSI, &init_data);
+				 PROTOCOLID_TCP_ULP, &init_data);
 	if (rc)
 		return rc;
 
@@ -250,7 +250,7 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn,
 	p_hwfn->p_iscsi_info->event_context = event_context;
 	p_hwfn->p_iscsi_info->event_cb = async_event_cb;
 
-	qed_spq_register_async_cb(p_hwfn, PROTOCOLID_ISCSI,
+	qed_spq_register_async_cb(p_hwfn, PROTOCOLID_TCP_ULP,
 				  qed_iscsi_async_event);
 
 	return qed_spq_post(p_hwfn, p_ent, NULL);
@@ -286,7 +286,7 @@ static int qed_sp_iscsi_conn_offload(struct qed_hwfn *p_hwfn,
 
 	rc = qed_sp_init_request(p_hwfn, &p_ent,
 				 ISCSI_RAMROD_CMD_ID_OFFLOAD_CONN,
-				 PROTOCOLID_ISCSI, &init_data);
+				 PROTOCOLID_TCP_ULP, &init_data);
 	if (rc)
 		return rc;
 
@@ -453,7 +453,7 @@ static int qed_sp_iscsi_conn_update(struct qed_hwfn *p_hwfn,
 	struct iscsi_conn_update_ramrod_params *p_ramrod = NULL;
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
-	int rc = -EINVAL;
+	int rc;
 	u32 dval;
 
 	/* Get SPQ entry */
@@ -465,7 +465,7 @@ static int qed_sp_iscsi_conn_update(struct qed_hwfn *p_hwfn,
 
 	rc = qed_sp_init_request(p_hwfn, &p_ent,
 				 ISCSI_RAMROD_CMD_ID_UPDATE_CONN,
-				 PROTOCOLID_ISCSI, &init_data);
+				 PROTOCOLID_TCP_ULP, &init_data);
 	if (rc)
 		return rc;
 
@@ -506,7 +506,7 @@ qed_sp_iscsi_mac_update(struct qed_hwfn *p_hwfn,
 
 	rc = qed_sp_init_request(p_hwfn, &p_ent,
 				 ISCSI_RAMROD_CMD_ID_MAC_UPDATE,
-				 PROTOCOLID_ISCSI, &init_data);
+				 PROTOCOLID_TCP_ULP, &init_data);
 	if (rc)
 		return rc;
 
@@ -548,7 +548,7 @@ static int qed_sp_iscsi_conn_terminate(struct qed_hwfn *p_hwfn,
 
 	rc = qed_sp_init_request(p_hwfn, &p_ent,
 				 ISCSI_RAMROD_CMD_ID_TERMINATION_CONN,
-				 PROTOCOLID_ISCSI, &init_data);
+				 PROTOCOLID_TCP_ULP, &init_data);
 	if (rc)
 		return rc;
 
@@ -582,7 +582,7 @@ static int qed_sp_iscsi_conn_clear_sq(struct qed_hwfn *p_hwfn,
 
 	rc = qed_sp_init_request(p_hwfn, &p_ent,
 				 ISCSI_RAMROD_CMD_ID_CLEAR_SQ,
-				 PROTOCOLID_ISCSI, &init_data);
+				 PROTOCOLID_TCP_ULP, &init_data);
 	if (rc)
 		return rc;
 
@@ -606,13 +606,13 @@ static int qed_sp_iscsi_func_stop(struct qed_hwfn *p_hwfn,
 
 	rc = qed_sp_init_request(p_hwfn, &p_ent,
 				 ISCSI_RAMROD_CMD_ID_DESTROY_FUNC,
-				 PROTOCOLID_ISCSI, &init_data);
+				 PROTOCOLID_TCP_ULP, &init_data);
 	if (rc)
 		return rc;
 
 	rc = qed_spq_post(p_hwfn, p_ent, NULL);
 
-	qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_ISCSI);
+	qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_TCP_ULP);
 	return rc;
 }
 
@@ -786,7 +786,7 @@ static int qed_iscsi_acquire_connection(struct qed_hwfn *p_hwfn,
 	u32 icid;
 
 	spin_lock_bh(&p_hwfn->p_iscsi_info->lock);
-	rc = qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_ISCSI, &icid);
+	rc = qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_TCP_ULP, &icid);
 	spin_unlock_bh(&p_hwfn->p_iscsi_info->lock);
 	if (rc)
 		return rc;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 49783f365079..02a4610d9330 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -960,7 +960,8 @@ static int qed_sp_ll2_rx_queue_start(struct qed_hwfn *p_hwfn,
 
 	if (test_bit(QED_MF_LL2_NON_UNICAST, &p_hwfn->cdev->mf_bits) &&
 	    p_ramrod->main_func_queue && conn_type != QED_LL2_TYPE_ROCE &&
-	    conn_type != QED_LL2_TYPE_IWARP) {
+	    conn_type != QED_LL2_TYPE_IWARP &&
+		(!QED_IS_NVMETCP_PERSONALITY(p_hwfn))) {
 		p_ramrod->mf_si_bcast_accept_all = 1;
 		p_ramrod->mf_si_mcast_accept_all = 1;
 	} else {
@@ -1037,8 +1038,8 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn,
 	case QED_LL2_TYPE_FCOE:
 		p_ramrod->conn_type = PROTOCOLID_FCOE;
 		break;
-	case QED_LL2_TYPE_ISCSI:
-		p_ramrod->conn_type = PROTOCOLID_ISCSI;
+	case QED_LL2_TYPE_TCP_ULP:
+		p_ramrod->conn_type = PROTOCOLID_TCP_ULP;
 		break;
 	case QED_LL2_TYPE_ROCE:
 		p_ramrod->conn_type = PROTOCOLID_ROCE;
@@ -1047,8 +1048,9 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn,
 		p_ramrod->conn_type = PROTOCOLID_IWARP;
 		break;
 	case QED_LL2_TYPE_OOO:
-		if (p_hwfn->hw_info.personality == QED_PCI_ISCSI)
-			p_ramrod->conn_type = PROTOCOLID_ISCSI;
+		if (p_hwfn->hw_info.personality == QED_PCI_ISCSI ||
+		    p_hwfn->hw_info.personality == QED_PCI_NVMETCP)
+			p_ramrod->conn_type = PROTOCOLID_TCP_ULP;
 		else
 			p_ramrod->conn_type = PROTOCOLID_IWARP;
 		break;
@@ -1634,7 +1636,8 @@ int qed_ll2_establish_connection(void *cxt, u8 connection_handle)
 	if (rc)
 		goto out;
 
-	if (!QED_IS_RDMA_PERSONALITY(p_hwfn))
+	if (!QED_IS_RDMA_PERSONALITY(p_hwfn) &&
+	    !QED_IS_NVMETCP_PERSONALITY(p_hwfn))
 		qed_wr(p_hwfn, p_ptt, PRS_REG_USE_LIGHT_L2, 1);
 
 	qed_ll2_establish_connection_ooo(p_hwfn, p_ll2_conn);
@@ -2376,7 +2379,8 @@ out:
 static bool qed_ll2_is_storage_eng1(struct qed_dev *cdev)
 {
 	return (QED_IS_FCOE_PERSONALITY(QED_LEADING_HWFN(cdev)) ||
-		QED_IS_ISCSI_PERSONALITY(QED_LEADING_HWFN(cdev))) &&
+		QED_IS_ISCSI_PERSONALITY(QED_LEADING_HWFN(cdev)) ||
+		QED_IS_NVMETCP_PERSONALITY(QED_LEADING_HWFN(cdev))) &&
 		(QED_AFFIN_HWFN(cdev) != QED_LEADING_HWFN(cdev));
 }
 
@@ -2402,11 +2406,13 @@ static int qed_ll2_stop(struct qed_dev *cdev)
 
 	if (cdev->ll2->handle == QED_LL2_UNUSED_HANDLE)
 		return 0;
+	if (!QED_IS_NVMETCP_PERSONALITY(p_hwfn))
+		qed_llh_remove_mac_filter(cdev, 0, cdev->ll2_mac_address);
 
 	qed_llh_remove_mac_filter(cdev, 0, cdev->ll2_mac_address);
 	eth_zero_addr(cdev->ll2_mac_address);
 
-	if (QED_IS_ISCSI_PERSONALITY(p_hwfn))
+	if (QED_IS_ISCSI_PERSONALITY(p_hwfn) || QED_IS_NVMETCP_PERSONALITY(p_hwfn))
 		qed_ll2_stop_ooo(p_hwfn);
 
 	/* In CMT mode, LL2 is always started on engine 0 for a storage PF */
@@ -2442,7 +2448,8 @@ static int __qed_ll2_start(struct qed_hwfn *p_hwfn,
 		conn_type = QED_LL2_TYPE_FCOE;
 		break;
 	case QED_PCI_ISCSI:
-		conn_type = QED_LL2_TYPE_ISCSI;
+	case QED_PCI_NVMETCP:
+		conn_type = QED_LL2_TYPE_TCP_ULP;
 		break;
 	case QED_PCI_ETH_ROCE:
 		conn_type = QED_LL2_TYPE_ROCE;
@@ -2567,7 +2574,7 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params)
 		}
 	}
 
-	if (QED_IS_ISCSI_PERSONALITY(p_hwfn)) {
+	if (QED_IS_ISCSI_PERSONALITY(p_hwfn) || QED_IS_NVMETCP_PERSONALITY(p_hwfn)) {
 		DP_VERBOSE(cdev, QED_MSG_STORAGE, "Starting OOO LL2 queue\n");
 		rc = qed_ll2_start_ooo(p_hwfn, params);
 		if (rc) {
@@ -2576,10 +2583,13 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params)
 		}
 	}
 
-	rc = qed_llh_add_mac_filter(cdev, 0, params->ll2_mac_address);
-	if (rc) {
-		DP_NOTICE(cdev, "Failed to add an LLH filter\n");
-		goto err3;
+	if (!QED_IS_NVMETCP_PERSONALITY(p_hwfn)) {
+		rc = qed_llh_add_mac_filter(cdev, 0, params->ll2_mac_address);
+		if (rc) {
+			DP_NOTICE(cdev, "Failed to add an LLH filter\n");
+			goto err3;
+		}
+
 	}
 
 	ether_addr_copy(cdev->ll2_mac_address, params->ll2_mac_address);
@@ -2587,7 +2597,7 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params)
 	return 0;
 
 err3:
-	if (QED_IS_ISCSI_PERSONALITY(p_hwfn))
+	if (QED_IS_ISCSI_PERSONALITY(p_hwfn) || QED_IS_NVMETCP_PERSONALITY(p_hwfn))
 		qed_ll2_stop_ooo(p_hwfn);
 err2:
 	if (b_is_storage_eng1)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index cd882c453394..4387292c37e2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -2446,6 +2446,9 @@ qed_mcp_get_shmem_proto(struct qed_hwfn *p_hwfn,
 	case FUNC_MF_CFG_PROTOCOL_ISCSI:
 		*p_proto = QED_PCI_ISCSI;
 		break;
+	case FUNC_MF_CFG_PROTOCOL_NVMETCP:
+		*p_proto = QED_PCI_NVMETCP;
+		break;
 	case FUNC_MF_CFG_PROTOCOL_FCOE:
 		*p_proto = QED_PCI_FCOE;
 		break;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
index 3e3192a3ad9b..6190adf965bc 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
@@ -1306,7 +1306,8 @@ int qed_mfw_process_tlv_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	}
 
 	if ((tlv_group & QED_MFW_TLV_ISCSI) &&
-	    p_hwfn->hw_info.personality != QED_PCI_ISCSI) {
+	    p_hwfn->hw_info.personality != QED_PCI_ISCSI &&
+		p_hwfn->hw_info.personality != QED_PCI_NVMETCP) {
 		DP_VERBOSE(p_hwfn, QED_MSG_SP,
 			   "Skipping iSCSI TLVs for non-iSCSI function\n");
 		tlv_group &= ~QED_MFW_TLV_ISCSI;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c
new file mode 100644
index 000000000000..f19128c8d9cc
--- /dev/null
+++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c
@@ -0,0 +1,829 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/* Copyright 2021 Marvell. All rights reserved. */
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include <asm/param.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/etherdevice.h>
+#include <linux/kernel.h>
+#include <linux/log2.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/list.h>
+#include <linux/qed/qed_nvmetcp_if.h>
+#include "qed.h"
+#include "qed_cxt.h"
+#include "qed_dev_api.h"
+#include "qed_hsi.h"
+#include "qed_hw.h"
+#include "qed_int.h"
+#include "qed_nvmetcp.h"
+#include "qed_ll2.h"
+#include "qed_mcp.h"
+#include "qed_sp.h"
+#include "qed_reg_addr.h"
+#include "qed_nvmetcp_fw_funcs.h"
+
+static int qed_nvmetcp_async_event(struct qed_hwfn *p_hwfn, u8 fw_event_code,
+				   u16 echo, union event_ring_data *data,
+				   u8 fw_return_code)
+{
+	if (p_hwfn->p_nvmetcp_info->event_cb) {
+		struct qed_nvmetcp_info *p_nvmetcp = p_hwfn->p_nvmetcp_info;
+
+		return p_nvmetcp->event_cb(p_nvmetcp->event_context,
+					 fw_event_code, data);
+	} else {
+		DP_NOTICE(p_hwfn, "nvmetcp async completion is not set\n");
+
+		return -EINVAL;
+	}
+}
+
+static int qed_sp_nvmetcp_func_start(struct qed_hwfn *p_hwfn,
+				     enum spq_mode comp_mode,
+				     struct qed_spq_comp_cb *p_comp_addr,
+				     void *event_context,
+				     nvmetcp_event_cb_t async_event_cb)
+{
+	struct nvmetcp_init_ramrod_params *p_ramrod = NULL;
+	struct qed_nvmetcp_pf_params *p_params = NULL;
+	struct scsi_init_func_queues *p_queue = NULL;
+	struct nvmetcp_spe_func_init *p_init = NULL;
+	struct qed_sp_init_data init_data = {};
+	struct qed_spq_entry *p_ent = NULL;
+	int rc = 0;
+	u16 val;
+	u8 i;
+
+	/* Get SPQ entry */
+	init_data.cid = qed_spq_get_cid(p_hwfn);
+	init_data.opaque_fid = p_hwfn->hw_info.opaque_fid;
+	init_data.comp_mode = comp_mode;
+	init_data.p_comp_data = p_comp_addr;
+	rc = qed_sp_init_request(p_hwfn, &p_ent,
+				 NVMETCP_RAMROD_CMD_ID_INIT_FUNC,
+				 PROTOCOLID_TCP_ULP, &init_data);
+	if (rc)
+		return rc;
+
+	p_ramrod = &p_ent->ramrod.nvmetcp_init;
+	p_init = &p_ramrod->nvmetcp_init_spe;
+	p_params = &p_hwfn->pf_params.nvmetcp_pf_params;
+	p_queue = &p_init->q_params;
+	p_init->num_sq_pages_in_ring = p_params->num_sq_pages_in_ring;
+	p_init->num_r2tq_pages_in_ring = p_params->num_r2tq_pages_in_ring;
+	p_init->num_uhq_pages_in_ring = p_params->num_uhq_pages_in_ring;
+	p_init->ll2_rx_queue_id = RESC_START(p_hwfn, QED_LL2_RAM_QUEUE) +
+					p_params->ll2_ooo_queue_id;
+	SET_FIELD(p_init->flags, NVMETCP_SPE_FUNC_INIT_NVMETCP_MODE, 1);
+	p_init->func_params.log_page_size = ilog2(PAGE_SIZE);
+	p_init->func_params.num_tasks = cpu_to_le16(p_params->num_tasks);
+	p_init->debug_flags = p_params->debug_mode;
+	DMA_REGPAIR_LE(p_queue->glbl_q_params_addr,
+		       p_params->glbl_q_params_addr);
+	p_queue->cq_num_entries = cpu_to_le16(QED_NVMETCP_FW_CQ_SIZE);
+	p_queue->num_queues = p_params->num_queues;
+	val = RESC_START(p_hwfn, QED_CMDQS_CQS);
+	p_queue->queue_relative_offset = cpu_to_le16((u16)val);
+	p_queue->cq_sb_pi = p_params->gl_rq_pi;
+
+	for (i = 0; i < p_params->num_queues; i++) {
+		val = qed_get_igu_sb_id(p_hwfn, i);
+		p_queue->cq_cmdq_sb_num_arr[i] = cpu_to_le16(val);
+	}
+
+	SET_FIELD(p_queue->q_validity,
+		  SCSI_INIT_FUNC_QUEUES_CMD_VALID, 0);
+	p_queue->cmdq_num_entries = 0;
+	p_queue->bdq_resource_id = (u8)RESC_START(p_hwfn, QED_BDQ);
+	p_ramrod->tcp_init.two_msl_timer = cpu_to_le32(QED_TCP_TWO_MSL_TIMER);
+	p_ramrod->tcp_init.tx_sws_timer = cpu_to_le16(QED_TCP_SWS_TIMER);
+	p_init->half_way_close_timeout = cpu_to_le16(QED_TCP_HALF_WAY_CLOSE_TIMEOUT);
+	p_ramrod->tcp_init.max_fin_rt = QED_TCP_MAX_FIN_RT;
+	SET_FIELD(p_ramrod->nvmetcp_init_spe.params,
+		  NVMETCP_SPE_FUNC_INIT_MAX_SYN_RT, QED_TCP_MAX_FIN_RT);
+	p_hwfn->p_nvmetcp_info->event_context = event_context;
+	p_hwfn->p_nvmetcp_info->event_cb = async_event_cb;
+	qed_spq_register_async_cb(p_hwfn, PROTOCOLID_TCP_ULP,
+				  qed_nvmetcp_async_event);
+
+	return qed_spq_post(p_hwfn, p_ent, NULL);
+}
+
+static int qed_sp_nvmetcp_func_stop(struct qed_hwfn *p_hwfn,
+				    enum spq_mode comp_mode,
+				    struct qed_spq_comp_cb *p_comp_addr)
+{
+	struct qed_spq_entry *p_ent = NULL;
+	struct qed_sp_init_data init_data;
+	int rc;
+
+	/* Get SPQ entry */
+	memset(&init_data, 0, sizeof(init_data));
+	init_data.cid = qed_spq_get_cid(p_hwfn);
+	init_data.opaque_fid = p_hwfn->hw_info.opaque_fid;
+	init_data.comp_mode = comp_mode;
+	init_data.p_comp_data = p_comp_addr;
+	rc = qed_sp_init_request(p_hwfn, &p_ent,
+				 NVMETCP_RAMROD_CMD_ID_DESTROY_FUNC,
+				 PROTOCOLID_TCP_ULP, &init_data);
+	if (rc)
+		return rc;
+
+	rc = qed_spq_post(p_hwfn, p_ent, NULL);
+	qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_TCP_ULP);
+
+	return rc;
+}
+
+static int qed_fill_nvmetcp_dev_info(struct qed_dev *cdev,
+				     struct qed_dev_nvmetcp_info *info)
+{
+	struct qed_hwfn *hwfn = QED_AFFIN_HWFN(cdev);
+	int rc;
+
+	memset(info, 0, sizeof(*info));
+	rc = qed_fill_dev_info(cdev, &info->common);
+	info->port_id = MFW_PORT(hwfn);
+	info->num_cqs = FEAT_NUM(hwfn, QED_NVMETCP_CQ);
+
+	return rc;
+}
+
+static void qed_register_nvmetcp_ops(struct qed_dev *cdev,
+				     struct qed_nvmetcp_cb_ops *ops,
+				     void *cookie)
+{
+	cdev->protocol_ops.nvmetcp = ops;
+	cdev->ops_cookie = cookie;
+}
+
+static int qed_nvmetcp_stop(struct qed_dev *cdev)
+{
+	int rc;
+
+	if (!(cdev->flags & QED_FLAG_STORAGE_STARTED)) {
+		DP_NOTICE(cdev, "nvmetcp already stopped\n");
+
+		return 0;
+	}
+
+	if (!hash_empty(cdev->connections)) {
+		DP_NOTICE(cdev,
+			  "Can't stop nvmetcp - not all connections were returned\n");
+
+		return -EINVAL;
+	}
+
+	/* Stop the nvmetcp */
+	rc = qed_sp_nvmetcp_func_stop(QED_AFFIN_HWFN(cdev), QED_SPQ_MODE_EBLOCK,
+				      NULL);
+	cdev->flags &= ~QED_FLAG_STORAGE_STARTED;
+
+	return rc;
+}
+
+static int qed_nvmetcp_start(struct qed_dev *cdev,
+			     struct qed_nvmetcp_tid *tasks,
+			     void *event_context,
+			     nvmetcp_event_cb_t async_event_cb)
+{
+	struct qed_tid_mem *tid_info;
+	int rc;
+
+	if (cdev->flags & QED_FLAG_STORAGE_STARTED) {
+		DP_NOTICE(cdev, "nvmetcp already started;\n");
+
+		return 0;
+	}
+
+	rc = qed_sp_nvmetcp_func_start(QED_AFFIN_HWFN(cdev),
+				       QED_SPQ_MODE_EBLOCK, NULL,
+				       event_context, async_event_cb);
+	if (rc) {
+		DP_NOTICE(cdev, "Failed to start nvmetcp\n");
+
+		return rc;
+	}
+
+	cdev->flags |= QED_FLAG_STORAGE_STARTED;
+	hash_init(cdev->connections);
+
+	if (!tasks)
+		return 0;
+
+	tid_info = kzalloc(sizeof(*tid_info), GFP_KERNEL);
+	if (!tid_info) {
+		qed_nvmetcp_stop(cdev);
+
+		return -ENOMEM;
+	}
+
+	rc = qed_cxt_get_tid_mem_info(QED_AFFIN_HWFN(cdev), tid_info);
+	if (rc) {
+		DP_NOTICE(cdev, "Failed to gather task information\n");
+		qed_nvmetcp_stop(cdev);
+		kfree(tid_info);
+
+		return rc;
+	}
+
+	/* Fill task information */
+	tasks->size = tid_info->tid_size;
+	tasks->num_tids_per_block = tid_info->num_tids_per_block;
+	memcpy(tasks->blocks, tid_info->blocks,
+	       MAX_TID_BLOCKS_NVMETCP * sizeof(u8 *));
+	kfree(tid_info);
+
+	return 0;
+}
+
+static struct qed_hash_nvmetcp_con *qed_nvmetcp_get_hash(struct qed_dev *cdev,
+							 u32 handle)
+{
+	struct qed_hash_nvmetcp_con *hash_con = NULL;
+
+	if (!(cdev->flags & QED_FLAG_STORAGE_STARTED))
+		return NULL;
+
+	hash_for_each_possible(cdev->connections, hash_con, node, handle) {
+		if (hash_con->con->icid == handle)
+			break;
+	}
+
+	if (!hash_con || hash_con->con->icid != handle)
+		return NULL;
+
+	return hash_con;
+}
+
+static int qed_sp_nvmetcp_conn_offload(struct qed_hwfn *p_hwfn,
+				       struct qed_nvmetcp_conn *p_conn,
+				       enum spq_mode comp_mode,
+				       struct qed_spq_comp_cb *p_comp_addr)
+{
+	struct nvmetcp_spe_conn_offload *p_ramrod = NULL;
+	struct tcp_offload_params_opt2 *p_tcp = NULL;
+	struct qed_sp_init_data init_data = { 0 };
+	struct qed_spq_entry *p_ent = NULL;
+	dma_addr_t r2tq_pbl_addr;
+	dma_addr_t xhq_pbl_addr;
+	dma_addr_t uhq_pbl_addr;
+	u16 physical_q;
+	int rc = 0;
+	u8 i;
+
+	/* Get SPQ entry */
+	init_data.cid = p_conn->icid;
+	init_data.opaque_fid = p_hwfn->hw_info.opaque_fid;
+	init_data.comp_mode = comp_mode;
+	init_data.p_comp_data = p_comp_addr;
+	rc = qed_sp_init_request(p_hwfn, &p_ent,
+				 NVMETCP_RAMROD_CMD_ID_OFFLOAD_CONN,
+				 PROTOCOLID_TCP_ULP, &init_data);
+	if (rc)
+		return rc;
+
+	p_ramrod = &p_ent->ramrod.nvmetcp_conn_offload;
+
+	/* Transmission PQ is the first of the PF */
+	physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+	p_conn->physical_q0 = cpu_to_le16(physical_q);
+	p_ramrod->nvmetcp.physical_q0 = cpu_to_le16(physical_q);
+
+	/* nvmetcp Pure-ACK PQ */
+	physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_ACK);
+	p_conn->physical_q1 = cpu_to_le16(physical_q);
+	p_ramrod->nvmetcp.physical_q1 = cpu_to_le16(physical_q);
+	p_ramrod->conn_id = cpu_to_le16(p_conn->conn_id);
+	DMA_REGPAIR_LE(p_ramrod->nvmetcp.sq_pbl_addr, p_conn->sq_pbl_addr);
+	r2tq_pbl_addr = qed_chain_get_pbl_phys(&p_conn->r2tq);
+	DMA_REGPAIR_LE(p_ramrod->nvmetcp.r2tq_pbl_addr, r2tq_pbl_addr);
+	xhq_pbl_addr = qed_chain_get_pbl_phys(&p_conn->xhq);
+	DMA_REGPAIR_LE(p_ramrod->nvmetcp.xhq_pbl_addr, xhq_pbl_addr);
+	uhq_pbl_addr = qed_chain_get_pbl_phys(&p_conn->uhq);
+	DMA_REGPAIR_LE(p_ramrod->nvmetcp.uhq_pbl_addr, uhq_pbl_addr);
+	p_ramrod->nvmetcp.flags = p_conn->offl_flags;
+	p_ramrod->nvmetcp.default_cq = p_conn->default_cq;
+	p_ramrod->nvmetcp.initial_ack = 0;
+	DMA_REGPAIR_LE(p_ramrod->nvmetcp.nvmetcp.cccid_itid_table_addr,
+		       p_conn->nvmetcp_cccid_itid_table_addr);
+	p_ramrod->nvmetcp.nvmetcp.cccid_max_range =
+		 cpu_to_le16(p_conn->nvmetcp_cccid_max_range);
+	p_tcp = &p_ramrod->tcp;
+	qed_set_fw_mac_addr(&p_tcp->remote_mac_addr_hi,
+			    &p_tcp->remote_mac_addr_mid,
+			    &p_tcp->remote_mac_addr_lo, p_conn->remote_mac);
+	qed_set_fw_mac_addr(&p_tcp->local_mac_addr_hi,
+			    &p_tcp->local_mac_addr_mid,
+			    &p_tcp->local_mac_addr_lo, p_conn->local_mac);
+	p_tcp->vlan_id = cpu_to_le16(p_conn->vlan_id);
+	p_tcp->flags = cpu_to_le16(p_conn->tcp_flags);
+	p_tcp->ip_version = p_conn->ip_version;
+	if (p_tcp->ip_version == TCP_IPV6) {
+		for (i = 0; i < 4; i++) {
+			p_tcp->remote_ip[i] = cpu_to_le32(p_conn->remote_ip[i]);
+			p_tcp->local_ip[i] = cpu_to_le32(p_conn->local_ip[i]);
+		}
+	} else {
+		p_tcp->remote_ip[0] = cpu_to_le32(p_conn->remote_ip[0]);
+		p_tcp->local_ip[0] = cpu_to_le32(p_conn->local_ip[0]);
+	}
+
+	p_tcp->flow_label = cpu_to_le32(p_conn->flow_label);
+	p_tcp->ttl = p_conn->ttl;
+	p_tcp->tos_or_tc = p_conn->tos_or_tc;
+	p_tcp->remote_port = cpu_to_le16(p_conn->remote_port);
+	p_tcp->local_port = cpu_to_le16(p_conn->local_port);
+	p_tcp->mss = cpu_to_le16(p_conn->mss);
+	p_tcp->rcv_wnd_scale = p_conn->rcv_wnd_scale;
+	p_tcp->connect_mode = p_conn->connect_mode;
+	p_tcp->cwnd = cpu_to_le32(p_conn->cwnd);
+	p_tcp->ka_max_probe_cnt = p_conn->ka_max_probe_cnt;
+	p_tcp->ka_timeout = cpu_to_le32(p_conn->ka_timeout);
+	p_tcp->max_rt_time = cpu_to_le32(p_conn->max_rt_time);
+	p_tcp->ka_interval = cpu_to_le32(p_conn->ka_interval);
+
+	return qed_spq_post(p_hwfn, p_ent, NULL);
+}
+
+static int qed_sp_nvmetcp_conn_update(struct qed_hwfn *p_hwfn,
+				      struct qed_nvmetcp_conn *p_conn,
+				      enum spq_mode comp_mode,
+				      struct qed_spq_comp_cb *p_comp_addr)
+{
+	struct nvmetcp_conn_update_ramrod_params *p_ramrod = NULL;
+	struct qed_spq_entry *p_ent = NULL;
+	struct qed_sp_init_data init_data;
+	int rc = -EINVAL;
+	u32 dval;
+
+	/* Get SPQ entry */
+	memset(&init_data, 0, sizeof(init_data));
+	init_data.cid = p_conn->icid;
+	init_data.opaque_fid = p_hwfn->hw_info.opaque_fid;
+	init_data.comp_mode = comp_mode;
+	init_data.p_comp_data = p_comp_addr;
+
+	rc = qed_sp_init_request(p_hwfn, &p_ent,
+				 NVMETCP_RAMROD_CMD_ID_UPDATE_CONN,
+				 PROTOCOLID_TCP_ULP, &init_data);
+	if (rc)
+		return rc;
+
+	p_ramrod = &p_ent->ramrod.nvmetcp_conn_update;
+	p_ramrod->conn_id = cpu_to_le16(p_conn->conn_id);
+	p_ramrod->flags = p_conn->update_flag;
+	p_ramrod->max_seq_size = cpu_to_le32(p_conn->max_seq_size);
+	dval = p_conn->max_recv_pdu_length;
+	p_ramrod->max_recv_pdu_length = cpu_to_le32(dval);
+	dval = p_conn->max_send_pdu_length;
+	p_ramrod->max_send_pdu_length = cpu_to_le32(dval);
+	p_ramrod->first_seq_length = cpu_to_le32(p_conn->first_seq_length);
+
+	return qed_spq_post(p_hwfn, p_ent, NULL);
+}
+
+static int qed_sp_nvmetcp_conn_terminate(struct qed_hwfn *p_hwfn,
+					 struct qed_nvmetcp_conn *p_conn,
+					 enum spq_mode comp_mode,
+					 struct qed_spq_comp_cb *p_comp_addr)
+{
+	struct nvmetcp_spe_conn_termination *p_ramrod = NULL;
+	struct qed_spq_entry *p_ent = NULL;
+	struct qed_sp_init_data init_data;
+	int rc = -EINVAL;
+
+	/* Get SPQ entry */
+	memset(&init_data, 0, sizeof(init_data));
+	init_data.cid = p_conn->icid;
+	init_data.opaque_fid = p_hwfn->hw_info.opaque_fid;
+	init_data.comp_mode = comp_mode;
+	init_data.p_comp_data = p_comp_addr;
+	rc = qed_sp_init_request(p_hwfn, &p_ent,
+				 NVMETCP_RAMROD_CMD_ID_TERMINATION_CONN,
+				 PROTOCOLID_TCP_ULP, &init_data);
+	if (rc)
+		return rc;
+
+	p_ramrod = &p_ent->ramrod.nvmetcp_conn_terminate;
+	p_ramrod->conn_id = cpu_to_le16(p_conn->conn_id);
+	p_ramrod->abortive = p_conn->abortive_dsconnect;
+
+	return qed_spq_post(p_hwfn, p_ent, NULL);
+}
+
+static int qed_sp_nvmetcp_conn_clear_sq(struct qed_hwfn *p_hwfn,
+					struct qed_nvmetcp_conn *p_conn,
+					enum spq_mode comp_mode,
+					struct qed_spq_comp_cb *p_comp_addr)
+{
+	struct qed_spq_entry *p_ent = NULL;
+	struct qed_sp_init_data init_data;
+	int rc = -EINVAL;
+
+	/* Get SPQ entry */
+	memset(&init_data, 0, sizeof(init_data));
+	init_data.cid = p_conn->icid;
+	init_data.opaque_fid = p_hwfn->hw_info.opaque_fid;
+	init_data.comp_mode = comp_mode;
+	init_data.p_comp_data = p_comp_addr;
+	rc = qed_sp_init_request(p_hwfn, &p_ent,
+				 NVMETCP_RAMROD_CMD_ID_CLEAR_SQ,
+				 PROTOCOLID_TCP_ULP, &init_data);
+	if (rc)
+		return rc;
+
+	return qed_spq_post(p_hwfn, p_ent, NULL);
+}
+
+static void __iomem *qed_nvmetcp_get_db_addr(struct qed_hwfn *p_hwfn, u32 cid)
+{
+	return (u8 __iomem *)p_hwfn->doorbells +
+			     qed_db_addr(cid, DQ_DEMS_LEGACY);
+}
+
+static int qed_nvmetcp_allocate_connection(struct qed_hwfn *p_hwfn,
+					   struct qed_nvmetcp_conn **p_out_conn)
+{
+	struct qed_chain_init_params params = {
+		.mode		= QED_CHAIN_MODE_PBL,
+		.intended_use	= QED_CHAIN_USE_TO_CONSUME_PRODUCE,
+		.cnt_type	= QED_CHAIN_CNT_TYPE_U16,
+	};
+	struct qed_nvmetcp_pf_params *p_params = NULL;
+	struct qed_nvmetcp_conn *p_conn = NULL;
+	int rc = 0;
+
+	/* Try finding a free connection that can be used */
+	spin_lock_bh(&p_hwfn->p_nvmetcp_info->lock);
+	if (!list_empty(&p_hwfn->p_nvmetcp_info->free_list))
+		p_conn = list_first_entry(&p_hwfn->p_nvmetcp_info->free_list,
+					  struct qed_nvmetcp_conn, list_entry);
+	if (p_conn) {
+		list_del(&p_conn->list_entry);
+		spin_unlock_bh(&p_hwfn->p_nvmetcp_info->lock);
+		*p_out_conn = p_conn;
+
+		return 0;
+	}
+	spin_unlock_bh(&p_hwfn->p_nvmetcp_info->lock);
+
+	/* Need to allocate a new connection */
+	p_params = &p_hwfn->pf_params.nvmetcp_pf_params;
+	p_conn = kzalloc(sizeof(*p_conn), GFP_KERNEL);
+	if (!p_conn)
+		return -ENOMEM;
+
+	params.num_elems = p_params->num_r2tq_pages_in_ring *
+			   QED_CHAIN_PAGE_SIZE / sizeof(struct nvmetcp_wqe);
+	params.elem_size = sizeof(struct nvmetcp_wqe);
+	rc = qed_chain_alloc(p_hwfn->cdev, &p_conn->r2tq, &params);
+	if (rc)
+		goto nomem_r2tq;
+
+	params.num_elems = p_params->num_uhq_pages_in_ring *
+			   QED_CHAIN_PAGE_SIZE / sizeof(struct iscsi_uhqe);
+	params.elem_size = sizeof(struct iscsi_uhqe);
+	rc = qed_chain_alloc(p_hwfn->cdev, &p_conn->uhq, &params);
+	if (rc)
+		goto nomem_uhq;
+
+	params.elem_size = sizeof(struct iscsi_xhqe);
+	rc = qed_chain_alloc(p_hwfn->cdev, &p_conn->xhq, &params);
+	if (rc)
+		goto nomem;
+
+	p_conn->free_on_delete = true;
+	*p_out_conn = p_conn;
+
+	return 0;
+
+nomem:
+	qed_chain_free(p_hwfn->cdev, &p_conn->uhq);
+nomem_uhq:
+	qed_chain_free(p_hwfn->cdev, &p_conn->r2tq);
+nomem_r2tq:
+	kfree(p_conn);
+
+	return -ENOMEM;
+}
+
+static int qed_nvmetcp_acquire_connection(struct qed_hwfn *p_hwfn,
+					  struct qed_nvmetcp_conn **p_out_conn)
+{
+	struct qed_nvmetcp_conn *p_conn = NULL;
+	int rc = 0;
+	u32 icid;
+
+	spin_lock_bh(&p_hwfn->p_nvmetcp_info->lock);
+	rc = qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_TCP_ULP, &icid);
+	spin_unlock_bh(&p_hwfn->p_nvmetcp_info->lock);
+
+	if (rc)
+		return rc;
+
+	rc = qed_nvmetcp_allocate_connection(p_hwfn, &p_conn);
+	if (rc) {
+		spin_lock_bh(&p_hwfn->p_nvmetcp_info->lock);
+		qed_cxt_release_cid(p_hwfn, icid);
+		spin_unlock_bh(&p_hwfn->p_nvmetcp_info->lock);
+
+		return rc;
+	}
+
+	p_conn->icid = icid;
+	p_conn->conn_id = (u16)icid;
+	p_conn->fw_cid = (p_hwfn->hw_info.opaque_fid << 16) | icid;
+	*p_out_conn = p_conn;
+
+	return rc;
+}
+
+static void qed_nvmetcp_release_connection(struct qed_hwfn *p_hwfn,
+					   struct qed_nvmetcp_conn *p_conn)
+{
+	spin_lock_bh(&p_hwfn->p_nvmetcp_info->lock);
+	list_add_tail(&p_conn->list_entry, &p_hwfn->p_nvmetcp_info->free_list);
+	qed_cxt_release_cid(p_hwfn, p_conn->icid);
+	spin_unlock_bh(&p_hwfn->p_nvmetcp_info->lock);
+}
+
+static void qed_nvmetcp_free_connection(struct qed_hwfn *p_hwfn,
+					struct qed_nvmetcp_conn *p_conn)
+{
+	qed_chain_free(p_hwfn->cdev, &p_conn->xhq);
+	qed_chain_free(p_hwfn->cdev, &p_conn->uhq);
+	qed_chain_free(p_hwfn->cdev, &p_conn->r2tq);
+	kfree(p_conn);
+}
+
+int qed_nvmetcp_alloc(struct qed_hwfn *p_hwfn)
+{
+	struct qed_nvmetcp_info *p_nvmetcp_info;
+
+	p_nvmetcp_info = kzalloc(sizeof(*p_nvmetcp_info), GFP_KERNEL);
+	if (!p_nvmetcp_info)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&p_nvmetcp_info->free_list);
+	p_hwfn->p_nvmetcp_info = p_nvmetcp_info;
+
+	return 0;
+}
+
+void qed_nvmetcp_setup(struct qed_hwfn *p_hwfn)
+{
+	spin_lock_init(&p_hwfn->p_nvmetcp_info->lock);
+}
+
+void qed_nvmetcp_free(struct qed_hwfn *p_hwfn)
+{
+	struct qed_nvmetcp_conn *p_conn = NULL;
+
+	if (!p_hwfn->p_nvmetcp_info)
+		return;
+
+	while (!list_empty(&p_hwfn->p_nvmetcp_info->free_list)) {
+		p_conn = list_first_entry(&p_hwfn->p_nvmetcp_info->free_list,
+					  struct qed_nvmetcp_conn, list_entry);
+		if (p_conn) {
+			list_del(&p_conn->list_entry);
+			qed_nvmetcp_free_connection(p_hwfn, p_conn);
+		}
+	}
+
+	kfree(p_hwfn->p_nvmetcp_info);
+	p_hwfn->p_nvmetcp_info = NULL;
+}
+
+static int qed_nvmetcp_acquire_conn(struct qed_dev *cdev,
+				    u32 *handle,
+				    u32 *fw_cid, void __iomem **p_doorbell)
+{
+	struct qed_hash_nvmetcp_con *hash_con;
+	int rc;
+
+	/* Allocate a hashed connection */
+	hash_con = kzalloc(sizeof(*hash_con), GFP_ATOMIC);
+	if (!hash_con)
+		return -ENOMEM;
+
+	/* Acquire the connection */
+	rc = qed_nvmetcp_acquire_connection(QED_AFFIN_HWFN(cdev),
+					    &hash_con->con);
+	if (rc) {
+		DP_NOTICE(cdev, "Failed to acquire Connection\n");
+		kfree(hash_con);
+
+		return rc;
+	}
+
+	/* Added the connection to hash table */
+	*handle = hash_con->con->icid;
+	*fw_cid = hash_con->con->fw_cid;
+	hash_add(cdev->connections, &hash_con->node, *handle);
+	if (p_doorbell)
+		*p_doorbell = qed_nvmetcp_get_db_addr(QED_AFFIN_HWFN(cdev),
+						      *handle);
+
+	return 0;
+}
+
+static int qed_nvmetcp_release_conn(struct qed_dev *cdev, u32 handle)
+{
+	struct qed_hash_nvmetcp_con *hash_con;
+
+	hash_con = qed_nvmetcp_get_hash(cdev, handle);
+	if (!hash_con) {
+		DP_NOTICE(cdev, "Failed to find connection for handle %d\n",
+			  handle);
+
+		return -EINVAL;
+	}
+
+	hlist_del(&hash_con->node);
+	qed_nvmetcp_release_connection(QED_AFFIN_HWFN(cdev), hash_con->con);
+	kfree(hash_con);
+
+	return 0;
+}
+
+static int qed_nvmetcp_offload_conn(struct qed_dev *cdev, u32 handle,
+				    struct qed_nvmetcp_params_offload *conn_info)
+{
+	struct qed_hash_nvmetcp_con *hash_con;
+	struct qed_nvmetcp_conn *con;
+
+	hash_con = qed_nvmetcp_get_hash(cdev, handle);
+	if (!hash_con) {
+		DP_NOTICE(cdev, "Failed to find connection for handle %d\n",
+			  handle);
+
+		return -EINVAL;
+	}
+
+	/* Update the connection with information from the params */
+	con = hash_con->con;
+
+	/* FW initializations */
+	con->layer_code = NVMETCP_SLOW_PATH_LAYER_CODE;
+	con->sq_pbl_addr = conn_info->sq_pbl_addr;
+	con->nvmetcp_cccid_max_range = conn_info->nvmetcp_cccid_max_range;
+	con->nvmetcp_cccid_itid_table_addr = conn_info->nvmetcp_cccid_itid_table_addr;
+	con->default_cq = conn_info->default_cq;
+	SET_FIELD(con->offl_flags, NVMETCP_CONN_OFFLOAD_PARAMS_TARGET_MODE, 0);
+	SET_FIELD(con->offl_flags, NVMETCP_CONN_OFFLOAD_PARAMS_NVMETCP_MODE, 1);
+	SET_FIELD(con->offl_flags, NVMETCP_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B, 1);
+
+	/* Networking and TCP stack initializations */
+	ether_addr_copy(con->local_mac, conn_info->src.mac);
+	ether_addr_copy(con->remote_mac, conn_info->dst.mac);
+	memcpy(con->local_ip, conn_info->src.ip, sizeof(con->local_ip));
+	memcpy(con->remote_ip, conn_info->dst.ip, sizeof(con->remote_ip));
+	con->local_port = conn_info->src.port;
+	con->remote_port = conn_info->dst.port;
+	con->vlan_id = conn_info->vlan_id;
+
+	if (conn_info->timestamp_en)
+		SET_FIELD(con->tcp_flags, TCP_OFFLOAD_PARAMS_OPT2_TS_EN, 1);
+
+	if (conn_info->delayed_ack_en)
+		SET_FIELD(con->tcp_flags, TCP_OFFLOAD_PARAMS_OPT2_DA_EN, 1);
+
+	if (conn_info->tcp_keep_alive_en)
+		SET_FIELD(con->tcp_flags, TCP_OFFLOAD_PARAMS_OPT2_KA_EN, 1);
+
+	if (conn_info->ecn_en)
+		SET_FIELD(con->tcp_flags, TCP_OFFLOAD_PARAMS_OPT2_ECN_EN, 1);
+
+	con->ip_version = conn_info->ip_version;
+	con->flow_label = QED_TCP_FLOW_LABEL;
+	con->ka_max_probe_cnt = conn_info->ka_max_probe_cnt;
+	con->ka_timeout = conn_info->ka_timeout;
+	con->ka_interval = conn_info->ka_interval;
+	con->max_rt_time = conn_info->max_rt_time;
+	con->ttl = conn_info->ttl;
+	con->tos_or_tc = conn_info->tos_or_tc;
+	con->mss = conn_info->mss;
+	con->cwnd = conn_info->cwnd;
+	con->rcv_wnd_scale = conn_info->rcv_wnd_scale;
+	con->connect_mode = 0;
+
+	return qed_sp_nvmetcp_conn_offload(QED_AFFIN_HWFN(cdev), con,
+					 QED_SPQ_MODE_EBLOCK, NULL);
+}
+
+static int qed_nvmetcp_update_conn(struct qed_dev *cdev,
+				   u32 handle,
+				   struct qed_nvmetcp_params_update *conn_info)
+{
+	struct qed_hash_nvmetcp_con *hash_con;
+	struct qed_nvmetcp_conn *con;
+
+	hash_con = qed_nvmetcp_get_hash(cdev, handle);
+	if (!hash_con) {
+		DP_NOTICE(cdev, "Failed to find connection for handle %d\n",
+			  handle);
+
+		return -EINVAL;
+	}
+
+	/* Update the connection with information from the params */
+	con = hash_con->con;
+	SET_FIELD(con->update_flag,
+		  ISCSI_CONN_UPDATE_RAMROD_PARAMS_INITIAL_R2T, 0);
+	SET_FIELD(con->update_flag,
+		  ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA, 1);
+	if (conn_info->hdr_digest_en)
+		SET_FIELD(con->update_flag, ISCSI_CONN_UPDATE_RAMROD_PARAMS_HD_EN, 1);
+
+	if (conn_info->data_digest_en)
+		SET_FIELD(con->update_flag, ISCSI_CONN_UPDATE_RAMROD_PARAMS_DD_EN, 1);
+
+	/* Placeholder - initialize pfv, cpda, hpda */
+
+	con->max_seq_size = conn_info->max_io_size;
+	con->max_recv_pdu_length = conn_info->max_recv_pdu_length;
+	con->max_send_pdu_length = conn_info->max_send_pdu_length;
+	con->first_seq_length = conn_info->max_io_size;
+
+	return qed_sp_nvmetcp_conn_update(QED_AFFIN_HWFN(cdev), con,
+					QED_SPQ_MODE_EBLOCK, NULL);
+}
+
+static int qed_nvmetcp_clear_conn_sq(struct qed_dev *cdev, u32 handle)
+{
+	struct qed_hash_nvmetcp_con *hash_con;
+
+	hash_con = qed_nvmetcp_get_hash(cdev, handle);
+	if (!hash_con) {
+		DP_NOTICE(cdev, "Failed to find connection for handle %d\n",
+			  handle);
+
+		return -EINVAL;
+	}
+
+	return qed_sp_nvmetcp_conn_clear_sq(QED_AFFIN_HWFN(cdev), hash_con->con,
+					    QED_SPQ_MODE_EBLOCK, NULL);
+}
+
+static int qed_nvmetcp_destroy_conn(struct qed_dev *cdev,
+				    u32 handle, u8 abrt_conn)
+{
+	struct qed_hash_nvmetcp_con *hash_con;
+
+	hash_con = qed_nvmetcp_get_hash(cdev, handle);
+	if (!hash_con) {
+		DP_NOTICE(cdev, "Failed to find connection for handle %d\n",
+			  handle);
+
+		return -EINVAL;
+	}
+
+	hash_con->con->abortive_dsconnect = abrt_conn;
+
+	return qed_sp_nvmetcp_conn_terminate(QED_AFFIN_HWFN(cdev), hash_con->con,
+					   QED_SPQ_MODE_EBLOCK, NULL);
+}
+
+static const struct qed_nvmetcp_ops qed_nvmetcp_ops_pass = {
+	.common = &qed_common_ops_pass,
+	.ll2 = &qed_ll2_ops_pass,
+	.fill_dev_info = &qed_fill_nvmetcp_dev_info,
+	.register_ops = &qed_register_nvmetcp_ops,
+	.start = &qed_nvmetcp_start,
+	.stop = &qed_nvmetcp_stop,
+	.acquire_conn = &qed_nvmetcp_acquire_conn,
+	.release_conn = &qed_nvmetcp_release_conn,
+	.offload_conn = &qed_nvmetcp_offload_conn,
+	.update_conn = &qed_nvmetcp_update_conn,
+	.destroy_conn = &qed_nvmetcp_destroy_conn,
+	.clear_sq = &qed_nvmetcp_clear_conn_sq,
+	.add_src_tcp_port_filter = &qed_llh_add_src_tcp_port_filter,
+	.remove_src_tcp_port_filter = &qed_llh_remove_src_tcp_port_filter,
+	.add_dst_tcp_port_filter = &qed_llh_add_dst_tcp_port_filter,
+	.remove_dst_tcp_port_filter = &qed_llh_remove_dst_tcp_port_filter,
+	.clear_all_filters = &qed_llh_clear_all_filters,
+	.init_read_io = &init_nvmetcp_host_read_task,
+	.init_write_io = &init_nvmetcp_host_write_task,
+	.init_icreq_exchange = &init_nvmetcp_init_conn_req_task,
+	.init_task_cleanup = &init_cleanup_task_nvmetcp
+};
+
+const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void)
+{
+	return &qed_nvmetcp_ops_pass;
+}
+EXPORT_SYMBOL(qed_get_nvmetcp_ops);
+
+void qed_put_nvmetcp_ops(void)
+{
+}
+EXPORT_SYMBOL(qed_put_nvmetcp_ops);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.h b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.h
new file mode 100644
index 000000000000..e5e9d075bf4f
--- /dev/null
+++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
+/* Copyright 2021 Marvell. All rights reserved. */
+
+#ifndef _QED_NVMETCP_H
+#define _QED_NVMETCP_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/qed/tcp_common.h>
+#include <linux/qed/qed_nvmetcp_if.h>
+#include <linux/qed/qed_chain.h>
+#include "qed.h"
+#include "qed_hsi.h"
+#include "qed_mcp.h"
+#include "qed_sp.h"
+
+#define QED_NVMETCP_FW_CQ_SIZE (4 * 1024)
+
+/* tcp parameters */
+#define QED_TCP_FLOW_LABEL 0
+#define QED_TCP_TWO_MSL_TIMER 4000
+#define QED_TCP_HALF_WAY_CLOSE_TIMEOUT 10
+#define QED_TCP_MAX_FIN_RT 2
+#define QED_TCP_SWS_TIMER 5000
+
+struct qed_nvmetcp_info {
+	spinlock_t lock; /* Connection resources. */
+	struct list_head free_list;
+	u16 max_num_outstanding_tasks;
+	void *event_context;
+	nvmetcp_event_cb_t event_cb;
+};
+
+struct qed_hash_nvmetcp_con {
+	struct hlist_node node;
+	struct qed_nvmetcp_conn *con;
+};
+
+struct qed_nvmetcp_conn {
+	struct list_head list_entry;
+	bool free_on_delete;
+	u16 conn_id;
+	u32 icid;
+	u32 fw_cid;
+	u8 layer_code;
+	u8 offl_flags;
+	u8 connect_mode;
+	dma_addr_t sq_pbl_addr;
+	struct qed_chain r2tq;
+	struct qed_chain xhq;
+	struct qed_chain uhq;
+	u8 local_mac[6];
+	u8 remote_mac[6];
+	u8 ip_version;
+	u8 ka_max_probe_cnt;
+	u16 vlan_id;
+	u16 tcp_flags;
+	u32 remote_ip[4];
+	u32 local_ip[4];
+	u32 flow_label;
+	u32 ka_timeout;
+	u32 ka_interval;
+	u32 max_rt_time;
+	u8 ttl;
+	u8 tos_or_tc;
+	u16 remote_port;
+	u16 local_port;
+	u16 mss;
+	u8 rcv_wnd_scale;
+	u32 rcv_wnd;
+	u32 cwnd;
+	u8 update_flag;
+	u8 default_cq;
+	u8 abortive_dsconnect;
+	u32 max_seq_size;
+	u32 max_recv_pdu_length;
+	u32 max_send_pdu_length;
+	u32 first_seq_length;
+	u16 physical_q0;
+	u16 physical_q1;
+	u16 nvmetcp_cccid_max_range;
+	dma_addr_t nvmetcp_cccid_itid_table_addr;
+};
+
+#if IS_ENABLED(CONFIG_QED_NVMETCP)
+int qed_nvmetcp_alloc(struct qed_hwfn *p_hwfn);
+void qed_nvmetcp_setup(struct qed_hwfn *p_hwfn);
+void qed_nvmetcp_free(struct qed_hwfn *p_hwfn);
+
+#else /* IS_ENABLED(CONFIG_QED_NVMETCP) */
+static inline int qed_nvmetcp_alloc(struct qed_hwfn *p_hwfn)
+{
+	return -EINVAL;
+}
+
+static inline void qed_nvmetcp_setup(struct qed_hwfn *p_hwfn) {}
+static inline void qed_nvmetcp_free(struct qed_hwfn *p_hwfn) {}
+
+#endif /* IS_ENABLED(CONFIG_QED_NVMETCP) */
+
+#endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.c
new file mode 100644
index 000000000000..c1dd71d19f3f
--- /dev/null
+++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.c
@@ -0,0 +1,376 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/* Copyright 2021 Marvell. All rights reserved. */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include <linux/qed/common_hsi.h>
+#include <linux/qed/storage_common.h>
+#include <linux/qed/nvmetcp_common.h>
+#include <linux/qed/qed_nvmetcp_if.h>
+#include "qed_nvmetcp_fw_funcs.h"
+
+#define NVMETCP_NUM_SGES_IN_CACHE 0x4
+
+bool nvmetcp_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 storage_sgl_task_params *sgl_params)
+{
+	u8 num_sges_to_init = (u8)(sgl_params->num_sges > NVMETCP_NUM_SGES_IN_CACHE ?
+				   NVMETCP_NUM_SGES_IN_CACHE : sgl_params->num_sges);
+	u8 sge_index;
+
+	/* sgl params */
+	ctx_sgl_params->sgl_addr.lo = cpu_to_le32(sgl_params->sgl_phys_addr.lo);
+	ctx_sgl_params->sgl_addr.hi = cpu_to_le32(sgl_params->sgl_phys_addr.hi);
+	ctx_sgl_params->sgl_total_length = cpu_to_le32(sgl_params->total_buffer_size);
+	ctx_sgl_params->sgl_num_sges = cpu_to_le16(sgl_params->num_sges);
+
+	for (sge_index = 0; sge_index < num_sges_to_init; sge_index++) {
+		ctx_data_desc->sge[sge_index].sge_addr.lo =
+			cpu_to_le32(sgl_params->sgl[sge_index].sge_addr.lo);
+		ctx_data_desc->sge[sge_index].sge_addr.hi =
+			cpu_to_le32(sgl_params->sgl[sge_index].sge_addr.hi);
+		ctx_data_desc->sge[sge_index].sge_len =
+			cpu_to_le32(sgl_params->sgl[sge_index].sge_len);
+	}
+}
+
+static inline u32 calc_rw_task_size(struct nvmetcp_task_params *task_params,
+				    enum nvmetcp_task_type task_type)
+{
+	u32 io_size;
+
+	if (task_type == NVMETCP_TASK_TYPE_HOST_WRITE)
+		io_size = task_params->tx_io_size;
+	else
+		io_size = task_params->rx_io_size;
+
+	if (unlikely(!io_size))
+		return 0;
+
+	return io_size;
+}
+
+static inline void init_sqe(struct nvmetcp_task_params *task_params,
+			    struct storage_sgl_task_params *sgl_task_params,
+			    enum nvmetcp_task_type task_type)
+{
+	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);
+
+	switch (task_type) {
+	case NVMETCP_TASK_TYPE_HOST_WRITE: {
+		u32 buf_size = 0;
+		u32 num_sges = 0;
+
+		SET_FIELD(task_params->sqe->contlen_cdbsize,
+			  NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD, 1);
+		SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_WQE_TYPE,
+			  NVMETCP_WQE_TYPE_NORMAL);
+		if (task_params->tx_io_size) {
+			if (task_params->send_write_incapsule)
+				buf_size = calc_rw_task_size(task_params, task_type);
+
+			if (nvmetcp_is_slow_sgl(sgl_task_params->num_sges,
+						sgl_task_params->small_mid_sge))
+				num_sges = NVMETCP_WQE_NUM_SGES_SLOWIO;
+			else
+				num_sges = min((u16)sgl_task_params->num_sges,
+					       (u16)SCSI_NUM_SGES_SLOW_SGL_THR);
+		}
+		SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_NUM_SGES, num_sges);
+		SET_FIELD(task_params->sqe->contlen_cdbsize, NVMETCP_WQE_CONT_LEN, buf_size);
+	} break;
+
+	case NVMETCP_TASK_TYPE_HOST_READ: {
+		SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_WQE_TYPE,
+			  NVMETCP_WQE_TYPE_NORMAL);
+		SET_FIELD(task_params->sqe->contlen_cdbsize,
+			  NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD, 1);
+	} break;
+
+	case NVMETCP_TASK_TYPE_INIT_CONN_REQUEST: {
+		SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_WQE_TYPE,
+			  NVMETCP_WQE_TYPE_MIDDLE_PATH);
+
+		if (task_params->tx_io_size) {
+			SET_FIELD(task_params->sqe->contlen_cdbsize, NVMETCP_WQE_CONT_LEN,
+				  task_params->tx_io_size);
+			SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_NUM_SGES,
+				  min((u16)sgl_task_params->num_sges,
+				      (u16)SCSI_NUM_SGES_SLOW_SGL_THR));
+		}
+	} break;
+
+	case NVMETCP_TASK_TYPE_CLEANUP:
+		SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_WQE_TYPE,
+			  NVMETCP_WQE_TYPE_TASK_CLEANUP);
+
+	default:
+		break;
+	}
+}
+
+/* The following function initializes of NVMeTCP task params */
+static inline void
+init_nvmetcp_task_params(struct e5_nvmetcp_task_context *context,
+			 struct nvmetcp_task_params *task_params,
+			 enum nvmetcp_task_type task_type)
+{
+	context->ystorm_st_context.state.cccid = task_params->host_cccid;
+	SET_FIELD(context->ustorm_st_context.error_flags, USTORM_NVMETCP_TASK_ST_CTX_NVME_TCP, 1);
+	context->ustorm_st_context.nvme_tcp_opaque_lo = cpu_to_le32(task_params->opq.lo);
+	context->ustorm_st_context.nvme_tcp_opaque_hi = cpu_to_le32(task_params->opq.hi);
+}
+
+/* The following function initializes default values to all tasks */
+static inline void
+init_default_nvmetcp_task(struct nvmetcp_task_params *task_params,
+			  void *pdu_header, void *nvme_cmd,
+			  enum nvmetcp_task_type task_type)
+{
+	struct e5_nvmetcp_task_context *context = task_params->context;
+	const u8 val_byte = context->mstorm_ag_context.cdu_validation;
+	u8 dw_index;
+
+	memset(context, 0, sizeof(*context));
+	init_nvmetcp_task_params(context, task_params,
+				 (enum nvmetcp_task_type)task_type);
+
+	/* Swapping requirements used below, will be removed in future FW versions */
+	if (task_type == NVMETCP_TASK_TYPE_HOST_WRITE ||
+	    task_type == NVMETCP_TASK_TYPE_HOST_READ) {
+		for (dw_index = 0;
+		     dw_index < QED_NVMETCP_CMN_HDR_SIZE / sizeof(u32);
+		     dw_index++)
+			context->ystorm_st_context.pdu_hdr.task_hdr.reg[dw_index] =
+				cpu_to_le32(__swab32(((u32 *)pdu_header)[dw_index]));
+
+		for (dw_index = QED_NVMETCP_CMN_HDR_SIZE / sizeof(u32);
+		     dw_index < QED_NVMETCP_CMD_HDR_SIZE / sizeof(u32);
+		     dw_index++)
+			context->ystorm_st_context.pdu_hdr.task_hdr.reg[dw_index] =
+				cpu_to_le32(__swab32(((u32 *)nvme_cmd)[dw_index - 2]));
+	} else {
+		for (dw_index = 0;
+		     dw_index < QED_NVMETCP_NON_IO_HDR_SIZE / sizeof(u32);
+		     dw_index++)
+			context->ystorm_st_context.pdu_hdr.task_hdr.reg[dw_index] =
+				cpu_to_le32(__swab32(((u32 *)pdu_header)[dw_index]));
+	}
+
+	/* M-Storm Context: */
+	context->mstorm_ag_context.cdu_validation = val_byte;
+	context->mstorm_st_context.task_type = (u8)(task_type);
+	context->mstorm_ag_context.task_cid = cpu_to_le16(task_params->conn_icid);
+
+	/* Ustorm Context: */
+	SET_FIELD(context->ustorm_ag_context.flags1, E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV, 1);
+	context->ustorm_st_context.task_type = (u8)(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);
+}
+
+/* The following function initializes the U-Storm Task Contexts */
+static inline void
+init_ustorm_task_contexts(struct ustorm_nvmetcp_task_st_ctx *ustorm_st_context,
+			  struct e5_ustorm_nvmetcp_task_ag_ctx *ustorm_ag_context,
+			  u32 remaining_recv_len,
+			  u32 expected_data_transfer_len, u8 num_sges,
+			  bool tx_dif_conn_err_en)
+{
+	/* Remaining data to be received in bytes. Used in validations*/
+	ustorm_st_context->rem_rcv_len = cpu_to_le32(remaining_recv_len);
+	ustorm_ag_context->exp_data_acked = cpu_to_le32(expected_data_transfer_len);
+	ustorm_st_context->exp_data_transfer_len = cpu_to_le32(expected_data_transfer_len);
+	SET_FIELD(ustorm_st_context->reg1_map, REG1_NUM_SGES, num_sges);
+	SET_FIELD(ustorm_ag_context->flags2, E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_EN,
+		  tx_dif_conn_err_en ? 1 : 0);
+}
+
+/* The following function initializes Local Completion Contexts: */
+static inline void
+set_local_completion_context(struct e5_nvmetcp_task_context *context)
+{
+	SET_FIELD(context->ystorm_st_context.state.flags,
+		  YSTORM_NVMETCP_TASK_STATE_LOCAL_COMP, 1);
+	SET_FIELD(context->ustorm_st_context.flags,
+		  USTORM_NVMETCP_TASK_ST_CTX_LOCAL_COMP, 1);
+}
+
+/* Common Fastpath task init function: */
+static inline void
+init_rw_nvmetcp_task(struct nvmetcp_task_params *task_params,
+		     enum nvmetcp_task_type task_type,
+		     void *pdu_header, void *nvme_cmd,
+		     struct storage_sgl_task_params *sgl_task_params)
+{
+	struct e5_nvmetcp_task_context *context = task_params->context;
+	u32 task_size = calc_rw_task_size(task_params, task_type);
+	bool slow_io = false;
+	u8 num_sges = 0;
+
+	init_default_nvmetcp_task(task_params, pdu_header, nvme_cmd, task_type);
+
+	/* Tx/Rx: */
+	if (task_params->tx_io_size) {
+		/* if data to transmit: */
+		init_scsi_sgl_context(&context->ystorm_st_context.state.sgl_params,
+				      &context->ystorm_st_context.state.data_desc,
+				      sgl_task_params);
+		slow_io = nvmetcp_is_slow_sgl(sgl_task_params->num_sges,
+					      sgl_task_params->small_mid_sge);
+		num_sges =
+			(u8)(!slow_io ? min((u32)sgl_task_params->num_sges,
+					    (u32)SCSI_NUM_SGES_SLOW_SGL_THR) :
+					    NVMETCP_WQE_NUM_SGES_SLOWIO);
+		if (slow_io) {
+			SET_FIELD(context->ystorm_st_context.state.flags,
+				  YSTORM_NVMETCP_TASK_STATE_SLOW_IO, 1);
+		}
+	} else if (task_params->rx_io_size) {
+		/* if data to receive: */
+		init_scsi_sgl_context(&context->mstorm_st_context.sgl_params,
+				      &context->mstorm_st_context.data_desc,
+				      sgl_task_params);
+		num_sges =
+			(u8)(!nvmetcp_is_slow_sgl(sgl_task_params->num_sges,
+						  sgl_task_params->small_mid_sge) ?
+						  min((u32)sgl_task_params->num_sges,
+						      (u32)SCSI_NUM_SGES_SLOW_SGL_THR) :
+						      NVMETCP_WQE_NUM_SGES_SLOWIO);
+		context->mstorm_st_context.rem_task_size = cpu_to_le32(task_size);
+	}
+
+	/* Ustorm context: */
+	init_ustorm_task_contexts(&context->ustorm_st_context,
+				  &context->ustorm_ag_context,
+				  /* Remaining Receive length is the Task Size */
+				  task_size,
+				  /* The size of the transmitted task */
+				  task_size,
+				  /* num_sges */
+				  num_sges,
+				  false);
+
+	/* Set exp_data_acked */
+	if (task_type == NVMETCP_TASK_TYPE_HOST_WRITE) {
+		if (task_params->send_write_incapsule)
+			context->ustorm_ag_context.exp_data_acked = task_size;
+		else
+			context->ustorm_ag_context.exp_data_acked = 0;
+	} else if (task_type == NVMETCP_TASK_TYPE_HOST_READ) {
+		context->ustorm_ag_context.exp_data_acked = 0;
+	}
+
+	context->ustorm_ag_context.exp_cont_len = 0;
+	init_sqe(task_params, sgl_task_params, task_type);
+}
+
+static void
+init_common_initiator_read_task(struct nvmetcp_task_params *task_params,
+				struct nvme_tcp_cmd_pdu *cmd_pdu_header,
+				struct nvme_command *nvme_cmd,
+				struct storage_sgl_task_params *sgl_task_params)
+{
+	init_rw_nvmetcp_task(task_params, NVMETCP_TASK_TYPE_HOST_READ,
+			     cmd_pdu_header, nvme_cmd, sgl_task_params);
+}
+
+void init_nvmetcp_host_read_task(struct nvmetcp_task_params *task_params,
+				 struct nvme_tcp_cmd_pdu *cmd_pdu_header,
+				 struct nvme_command *nvme_cmd,
+				 struct storage_sgl_task_params *sgl_task_params)
+{
+	init_common_initiator_read_task(task_params, (void *)cmd_pdu_header,
+					(void *)nvme_cmd, sgl_task_params);
+}
+
+static void
+init_common_initiator_write_task(struct nvmetcp_task_params *task_params,
+				 struct nvme_tcp_cmd_pdu *cmd_pdu_header,
+				 struct nvme_command *nvme_cmd,
+				 struct storage_sgl_task_params *sgl_task_params)
+{
+	init_rw_nvmetcp_task(task_params, NVMETCP_TASK_TYPE_HOST_WRITE,
+			     cmd_pdu_header, nvme_cmd, sgl_task_params);
+}
+
+void init_nvmetcp_host_write_task(struct nvmetcp_task_params *task_params,
+				  struct nvme_tcp_cmd_pdu *cmd_pdu_header,
+				  struct nvme_command *nvme_cmd,
+				  struct storage_sgl_task_params *sgl_task_params)
+{
+	init_common_initiator_write_task(task_params, (void *)cmd_pdu_header,
+					 (void *)nvme_cmd, sgl_task_params);
+}
+
+static void
+init_common_login_request_task(struct nvmetcp_task_params *task_params,
+			       void *login_req_pdu_header,
+			       struct storage_sgl_task_params *tx_sgl_task_params,
+			       struct storage_sgl_task_params *rx_sgl_task_params)
+{
+	struct e5_nvmetcp_task_context *context = task_params->context;
+
+	init_default_nvmetcp_task(task_params, (void *)login_req_pdu_header, NULL,
+				  NVMETCP_TASK_TYPE_INIT_CONN_REQUEST);
+
+	/* Ustorm Context: */
+	init_ustorm_task_contexts(&context->ustorm_st_context,
+				  &context->ustorm_ag_context,
+
+				  /* Remaining Receive length is the Task Size */
+				  task_params->rx_io_size ?
+				  rx_sgl_task_params->total_buffer_size : 0,
+
+				  /* The size of the transmitted task */
+				  task_params->tx_io_size ?
+				  tx_sgl_task_params->total_buffer_size : 0,
+				  0, /* num_sges */
+				  0); /* tx_dif_conn_err_en */
+
+	/* SGL context: */
+	if (task_params->tx_io_size)
+		init_scsi_sgl_context(&context->ystorm_st_context.state.sgl_params,
+				      &context->ystorm_st_context.state.data_desc,
+				      tx_sgl_task_params);
+	if (task_params->rx_io_size)
+		init_scsi_sgl_context(&context->mstorm_st_context.sgl_params,
+				      &context->mstorm_st_context.data_desc,
+				      rx_sgl_task_params);
+
+	context->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, NVMETCP_TASK_TYPE_INIT_CONN_REQUEST);
+}
+
+/* The following function initializes Login task in Host mode: */
+void init_nvmetcp_init_conn_req_task(struct nvmetcp_task_params *task_params,
+				     struct nvme_tcp_icreq_pdu *init_conn_req_pdu_hdr,
+				     struct storage_sgl_task_params *tx_sgl_task_params,
+				     struct storage_sgl_task_params *rx_sgl_task_params)
+{
+	init_common_login_request_task(task_params, init_conn_req_pdu_hdr,
+				       tx_sgl_task_params, rx_sgl_task_params);
+}
+
+void init_cleanup_task_nvmetcp(struct nvmetcp_task_params *task_params)
+{
+	init_sqe(task_params, NULL, NVMETCP_TASK_TYPE_CLEANUP);
+}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.h b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.h
new file mode 100644
index 000000000000..1d5ddc217bdb
--- /dev/null
+++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
+/* Copyright 2021 Marvell. All rights reserved. */
+
+#ifndef _QED_NVMETCP_FW_FUNCS_H
+#define _QED_NVMETCP_FW_FUNCS_H
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include <linux/qed/common_hsi.h>
+#include <linux/qed/storage_common.h>
+#include <linux/qed/nvmetcp_common.h>
+#include <linux/qed/qed_nvmetcp_if.h>
+
+#if IS_ENABLED(CONFIG_QED_NVMETCP)
+
+void init_nvmetcp_host_read_task(struct nvmetcp_task_params *task_params,
+				 struct nvme_tcp_cmd_pdu *cmd_pdu_header,
+				 struct nvme_command *nvme_cmd,
+				 struct storage_sgl_task_params *sgl_task_params);
+void init_nvmetcp_host_write_task(struct nvmetcp_task_params *task_params,
+				  struct nvme_tcp_cmd_pdu *cmd_pdu_header,
+				  struct nvme_command *nvme_cmd,
+				  struct storage_sgl_task_params *sgl_task_params);
+void init_nvmetcp_init_conn_req_task(struct nvmetcp_task_params *task_params,
+				     struct nvme_tcp_icreq_pdu *init_conn_req_pdu_hdr,
+				     struct storage_sgl_task_params *tx_sgl_task_params,
+				     struct storage_sgl_task_params *rx_sgl_task_params);
+void init_cleanup_task_nvmetcp(struct nvmetcp_task_params *task_params);
+
+#else /* IS_ENABLED(CONFIG_QED_NVMETCP) */
+
+#endif /* IS_ENABLED(CONFIG_QED_NVMETCP) */
+
+#endif /* _QED_NVMETCP_FW_FUNCS_H */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_ip_services.c b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_ip_services.c
new file mode 100644
index 000000000000..96a2077fd315
--- /dev/null
+++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_ip_services.c
@@ -0,0 +1,238 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright 2021 Marvell. All rights reserved.
+ */
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include <asm/param.h>
+#include <linux/delay.h>
+#include <linux/pci.h>
+#include <linux/dma-mapping.h>
+#include <linux/etherdevice.h>
+#include <linux/kernel.h>
+#include <linux/stddef.h>
+#include <linux/errno.h>
+
+#include <net/tcp.h>
+
+#include <linux/qed/qed_nvmetcp_ip_services_if.h>
+
+#define QED_IP_RESOL_TIMEOUT  4
+
+int qed_route_ipv4(struct sockaddr_storage *local_addr,
+		   struct sockaddr_storage *remote_addr,
+		   struct sockaddr *hardware_address,
+		   struct net_device **ndev)
+{
+	struct neighbour *neigh = NULL;
+	__be32 *loc_ip, *rem_ip;
+	struct rtable *rt;
+	int rc = -ENXIO;
+	int retry;
+
+	loc_ip = &((struct sockaddr_in *)local_addr)->sin_addr.s_addr;
+	rem_ip = &((struct sockaddr_in *)remote_addr)->sin_addr.s_addr;
+	*ndev = NULL;
+	rt = ip_route_output(&init_net, *rem_ip, *loc_ip, 0/*tos*/, 0/*oif*/);
+	if (IS_ERR(rt)) {
+		pr_err("lookup route failed\n");
+		rc = PTR_ERR(rt);
+		goto return_err;
+	}
+
+	neigh = dst_neigh_lookup(&rt->dst, rem_ip);
+	if (!neigh) {
+		rc = -ENOMEM;
+		ip_rt_put(rt);
+		goto return_err;
+	}
+
+	*ndev = rt->dst.dev;
+	ip_rt_put(rt);
+
+	/* If not resolved, kick-off state machine towards resolution */
+	if (!(neigh->nud_state & NUD_VALID))
+		neigh_event_send(neigh, NULL);
+
+	/* query neighbor until resolved or timeout */
+	retry = QED_IP_RESOL_TIMEOUT;
+	while (!(neigh->nud_state & NUD_VALID) && retry > 0) {
+		msleep(1000);
+		retry--;
+	}
+
+	if (neigh->nud_state & NUD_VALID) {
+		/* copy resolved MAC address */
+		neigh_ha_snapshot(hardware_address->sa_data, neigh, *ndev);
+		hardware_address->sa_family = (*ndev)->type;
+		rc = 0;
+	}
+
+	neigh_release(neigh);
+	if (!(*loc_ip)) {
+		*loc_ip = inet_select_addr(*ndev, *rem_ip, RT_SCOPE_UNIVERSE);
+		local_addr->ss_family = AF_INET;
+	}
+
+return_err:
+
+	return rc;
+}
+EXPORT_SYMBOL(qed_route_ipv4);
+
+int qed_route_ipv6(struct sockaddr_storage *local_addr,
+		   struct sockaddr_storage *remote_addr,
+		   struct sockaddr *hardware_address,
+		   struct net_device **ndev)
+{
+	struct neighbour *neigh = NULL;
+	struct dst_entry *dst;
+	struct flowi6 fl6;
+	int rc = -ENXIO;
+	int retry;
+
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.saddr = ((struct sockaddr_in6 *)local_addr)->sin6_addr;
+	fl6.daddr = ((struct sockaddr_in6 *)remote_addr)->sin6_addr;
+	dst = ip6_route_output(&init_net, NULL, &fl6);
+	if (!dst || dst->error) {
+		if (dst) {
+			dst_release(dst);
+			pr_err("lookup route failed %d\n", dst->error);
+		}
+
+		goto out;
+	}
+
+	neigh = dst_neigh_lookup(dst, &fl6.daddr);
+	if (neigh) {
+		*ndev = ip6_dst_idev(dst)->dev;
+
+		/* If not resolved, kick-off state machine towards resolution */
+		if (!(neigh->nud_state & NUD_VALID))
+			neigh_event_send(neigh, NULL);
+
+		/* query neighbor until resolved or timeout */
+		retry = QED_IP_RESOL_TIMEOUT;
+		while (!(neigh->nud_state & NUD_VALID) && retry > 0) {
+			msleep(1000);
+			retry--;
+		}
+
+		if (neigh->nud_state & NUD_VALID) {
+			neigh_ha_snapshot((u8 *)hardware_address->sa_data,
+					  neigh, *ndev);
+			hardware_address->sa_family = (*ndev)->type;
+			rc = 0;
+		}
+
+		neigh_release(neigh);
+
+		if (ipv6_addr_any(&fl6.saddr)) {
+			if (ipv6_dev_get_saddr(dev_net(*ndev), *ndev,
+					       &fl6.daddr, 0, &fl6.saddr)) {
+				pr_err("Unable to find source IP address\n");
+				goto out;
+			}
+
+			local_addr->ss_family = AF_INET6;
+			((struct sockaddr_in6 *)local_addr)->sin6_addr =
+								fl6.saddr;
+		}
+	}
+
+	dst_release(dst);
+
+out:
+
+	return rc;
+}
+EXPORT_SYMBOL(qed_route_ipv6);
+
+void qed_vlan_get_ndev(struct net_device **ndev, u16 *vlan_id)
+{
+	if (is_vlan_dev(*ndev)) {
+		*vlan_id = vlan_dev_vlan_id(*ndev);
+		*ndev = vlan_dev_real_dev(*ndev);
+	}
+}
+EXPORT_SYMBOL(qed_vlan_get_ndev);
+
+struct pci_dev *qed_validate_ndev(struct net_device *ndev)
+{
+	struct pci_dev *pdev = NULL;
+	struct net_device *upper;
+
+	for_each_pci_dev(pdev) {
+		if (pdev && pdev->driver &&
+		    !strcmp(pdev->driver->name, "qede")) {
+			upper = pci_get_drvdata(pdev);
+			if (upper->ifindex == ndev->ifindex)
+				return pdev;
+		}
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL(qed_validate_ndev);
+
+__be16 qed_get_in_port(struct sockaddr_storage *sa)
+{
+	return sa->ss_family == AF_INET
+		? ((struct sockaddr_in *)sa)->sin_port
+		: ((struct sockaddr_in6 *)sa)->sin6_port;
+}
+EXPORT_SYMBOL(qed_get_in_port);
+
+int qed_fetch_tcp_port(struct sockaddr_storage local_ip_addr,
+		       struct socket **sock, u16 *port)
+{
+	struct sockaddr_storage sa;
+	int rc = 0;
+
+	rc = sock_create(local_ip_addr.ss_family, SOCK_STREAM, IPPROTO_TCP,
+			 sock);
+	if (rc) {
+		pr_warn("failed to create socket: %d\n", rc);
+		goto err;
+	}
+
+	(*sock)->sk->sk_allocation = GFP_KERNEL;
+	sk_set_memalloc((*sock)->sk);
+
+	rc = kernel_bind(*sock, (struct sockaddr *)&local_ip_addr,
+			 sizeof(local_ip_addr));
+
+	if (rc) {
+		pr_warn("failed to bind socket: %d\n", rc);
+		goto err_sock;
+	}
+
+	rc = kernel_getsockname(*sock, (struct sockaddr *)&sa);
+	if (rc < 0) {
+		pr_warn("getsockname() failed: %d\n", rc);
+		goto err_sock;
+	}
+
+	*port = ntohs(qed_get_in_port(&sa));
+
+	return 0;
+
+err_sock:
+	sock_release(*sock);
+	sock = NULL;
+err:
+
+	return rc;
+}
+EXPORT_SYMBOL(qed_fetch_tcp_port);
+
+void qed_return_tcp_port(struct socket *sock)
+{
+	if (sock && sock->sk) {
+		tcp_set_state(sock->sk, TCP_CLOSE);
+		sock_release(sock);
+	}
+}
+EXPORT_SYMBOL(qed_return_tcp_port);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.c b/drivers/net/ethernet/qlogic/qed/qed_ooo.c
index 88353aa404dc..b8c5641b29a8 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ooo.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.c
@@ -16,7 +16,7 @@
 #include "qed_ll2.h"
 #include "qed_ooo.h"
 #include "qed_cxt.h"
-
+#include "qed_nvmetcp.h"
 static struct qed_ooo_archipelago
 *qed_ooo_seek_archipelago(struct qed_hwfn *p_hwfn,
 			  struct qed_ooo_info
@@ -83,7 +83,8 @@ int qed_ooo_alloc(struct qed_hwfn *p_hwfn)
 
 	switch (p_hwfn->hw_info.personality) {
 	case QED_PCI_ISCSI:
-		proto = PROTOCOLID_ISCSI;
+	case QED_PCI_NVMETCP:
+		proto = PROTOCOLID_TCP_ULP;
 		break;
 	case QED_PCI_ETH_RDMA:
 	case QED_PCI_ETH_IWARP:
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h
index 993f1357b6fc..60ff3222bf55 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h
@@ -100,6 +100,11 @@ union ramrod_data {
 	struct iscsi_spe_conn_mac_update iscsi_conn_mac_update;
 	struct iscsi_spe_conn_termination iscsi_conn_terminate;
 
+	struct nvmetcp_init_ramrod_params nvmetcp_init;
+	struct nvmetcp_spe_conn_offload nvmetcp_conn_offload;
+	struct nvmetcp_conn_update_ramrod_params nvmetcp_conn_update;
+	struct nvmetcp_spe_conn_termination nvmetcp_conn_terminate;
+
 	struct vf_start_ramrod_data vf_start;
 	struct vf_stop_ramrod_data vf_stop;
 };
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
index aa71adcf31ee..b4ed54ffef9b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
@@ -385,7 +385,8 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn,
 		p_ramrod->personality = PERSONALITY_FCOE;
 		break;
 	case QED_PCI_ISCSI:
-		p_ramrod->personality = PERSONALITY_ISCSI;
+	case QED_PCI_NVMETCP:
+		p_ramrod->personality = PERSONALITY_TCP_ULP;
 		break;
 	case QED_PCI_ETH_ROCE:
 	case QED_PCI_ETH_IWARP:
diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
index 2f6598086d9b..6304514a6f2c 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
@@ -247,12 +247,10 @@ static struct qede_rdma_event_work *
 qede_rdma_get_free_event_node(struct qede_dev *edev)
 {
 	struct qede_rdma_event_work *event_node = NULL;
-	struct list_head *list_node = NULL;
 	bool found = false;
 
-	list_for_each(list_node, &edev->rdma_info.rdma_event_list) {
-		event_node = list_entry(list_node, struct qede_rdma_event_work,
-					list);
+	list_for_each_entry(event_node, &edev->rdma_info.rdma_event_list,
+			    list) {
 		if (!work_pending(&event_node->work)) {
 			found = true;
 			break;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index d2c190732d3e..0a2f34fc8b24 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -746,7 +746,7 @@ static int qlcnic_83xx_idc_unknown_state(struct qlcnic_adapter *adapter)
 }
 
 /**
- * qlcnic_83xx_idc_cold_state
+ * qlcnic_83xx_idc_cold_state_handler
  *
  * @adapter: adapter structure
  *
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c
index c4297aea7d15..711609503ba6 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c
@@ -180,7 +180,7 @@ static int qlcnic_83xx_init_non_privileged_vnic(struct qlcnic_adapter *adapter)
 }
 
 /**
- * qlcnic_83xx_vnic_opmode
+ * qlcnic_83xx_config_vnic_opmode
  *
  * @adapter: adapter structure
  * Identify virtual NIC operational modes.
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
index e1b8490bed0a..4b8bc46f55c2 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
@@ -460,12 +460,10 @@ int qlcnic_82xx_sre_macaddr_change(struct qlcnic_adapter *adapter, u8 *addr,
 int qlcnic_nic_del_mac(struct qlcnic_adapter *adapter, const u8 *addr)
 {
 	struct qlcnic_mac_vlan_list *cur;
-	struct list_head *head;
 	int err = -EINVAL;
 
 	/* Delete MAC from the existing list */
-	list_for_each(head, &adapter->mac_list) {
-		cur = list_entry(head, struct qlcnic_mac_vlan_list, list);
+	list_for_each_entry(cur, &adapter->mac_list, list) {
 		if (ether_addr_equal(addr, cur->mac_addr)) {
 			err = qlcnic_sre_macaddr_change(adapter, cur->mac_addr,
 							0, QLCNIC_MAC_DEL);
@@ -483,11 +481,9 @@ int qlcnic_nic_add_mac(struct qlcnic_adapter *adapter, const u8 *addr, u16 vlan,
 		       enum qlcnic_mac_type mac_type)
 {
 	struct qlcnic_mac_vlan_list *cur;
-	struct list_head *head;
 
 	/* look up if already exists */
-	list_for_each(head, &adapter->mac_list) {
-		cur = list_entry(head, struct qlcnic_mac_vlan_list, list);
+	list_for_each_entry(cur, &adapter->mac_list, list) {
 		if (ether_addr_equal(addr, cur->mac_addr) &&
 		    cur->vlan_id == vlan)
 			return 0;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h
index 601d22495a88..95ecc84dddcd 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h
@@ -203,7 +203,6 @@ int qlcnic_82xx_set_nic_info(struct qlcnic_adapter *, struct qlcnic_info *);
 int qlcnic_82xx_get_pci_info(struct qlcnic_adapter *, struct qlcnic_pci_info*);
 int qlcnic_82xx_alloc_mbx_args(struct qlcnic_cmd_args *,
 			       struct qlcnic_adapter *, u32);
-int qlcnic_82xx_hw_write_wx_2M(struct qlcnic_adapter *, ulong, u32);
 int qlcnic_82xx_get_board_info(struct qlcnic_adapter *);
 int qlcnic_82xx_config_led(struct qlcnic_adapter *, u32, u32);
 void qlcnic_82xx_get_func_no(struct qlcnic_adapter *);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 3beafc60747e..b307264e59cf 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -319,10 +319,8 @@ int qlcnic_read_mac_addr(struct qlcnic_adapter *adapter)
 static void qlcnic_delete_adapter_mac(struct qlcnic_adapter *adapter)
 {
 	struct qlcnic_mac_vlan_list *cur;
-	struct list_head *head;
 
-	list_for_each(head, &adapter->mac_list) {
-		cur = list_entry(head, struct qlcnic_mac_vlan_list, list);
+	list_for_each_entry(cur, &adapter->mac_list, list) {
 		if (ether_addr_equal_unaligned(adapter->mac_addr, cur->mac_addr)) {
 			qlcnic_sre_macaddr_change(adapter, cur->mac_addr,
 						  0, QLCNIC_MAC_DEL);
@@ -3344,9 +3342,6 @@ qlcnic_can_start_firmware(struct qlcnic_adapter *adapter)
 	do {
 		msleep(1000);
 		prev_state = QLC_SHARED_REG_RD32(adapter, QLCNIC_CRB_DEV_STATE);
-
-		if (prev_state == QLCNIC_DEV_QUISCENT)
-			continue;
 	} while ((prev_state != QLCNIC_DEV_READY) && --dev_init_timeo);
 
 	if (!dev_init_timeo) {
diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c
index 702aa217a27a..d59fff2fbcc6 100644
--- a/drivers/net/ethernet/qualcomm/qca_debug.c
+++ b/drivers/net/ethernet/qualcomm/qca_debug.c
@@ -62,6 +62,7 @@ static const char qcaspi_gstrings_stats[][ETH_GSTRING_LEN] = {
 	"SPI errors",
 	"Write verify errors",
 	"Buffer available errors",
+	"Bad signature",
 };
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index ab9b02574a15..79fe3ec4e581 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -504,8 +504,12 @@ qcaspi_qca7k_sync(struct qcaspi *qca, int event)
 		qcaspi_read_register(qca, SPI_REG_SIGNATURE, &signature);
 		qcaspi_read_register(qca, SPI_REG_SIGNATURE, &signature);
 		if (signature != QCASPI_GOOD_SIGNATURE) {
+			if (qca->sync == QCASPI_SYNC_READY)
+				qca->stats.bad_signature++;
+
 			qca->sync = QCASPI_SYNC_UNKNOWN;
 			netdev_dbg(qca->net_dev, "sync: got CPU on, but signature was invalid, restart\n");
+			return;
 		} else {
 			/* ensure that the WRBUF is empty */
 			qcaspi_read_register(qca, SPI_REG_WRBUF_SPC_AVA,
@@ -523,10 +527,14 @@ qcaspi_qca7k_sync(struct qcaspi *qca, int event)
 
 	switch (qca->sync) {
 	case QCASPI_SYNC_READY:
-		/* Read signature, if not valid go to unknown state. */
+		/* Check signature twice, if not valid go to unknown state. */
 		qcaspi_read_register(qca, SPI_REG_SIGNATURE, &signature);
+		if (signature != QCASPI_GOOD_SIGNATURE)
+			qcaspi_read_register(qca, SPI_REG_SIGNATURE, &signature);
+
 		if (signature != QCASPI_GOOD_SIGNATURE) {
 			qca->sync = QCASPI_SYNC_UNKNOWN;
+			qca->stats.bad_signature++;
 			netdev_dbg(qca->net_dev, "sync: bad signature, restart\n");
 			/* don't reset right away */
 			return;
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h
index d13a67e20d65..3067356106f0 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.h
+++ b/drivers/net/ethernet/qualcomm/qca_spi.h
@@ -75,6 +75,7 @@ struct qcaspi_stats {
 	u64 spi_err;
 	u64 write_verify_failed;
 	u64 buf_avail_err;
+	u64 bad_signature;
 };
 
 struct qcaspi {
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 8d51b0cb545c..27b1663c476e 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -163,7 +163,8 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev,
 		struct ifla_rmnet_flags *flags;
 
 		flags = nla_data(data[IFLA_RMNET_FLAGS]);
-		data_format = flags->flags & flags->mask;
+		data_format &= ~flags->mask;
+		data_format |= flags->flags & flags->mask;
 	}
 
 	netdev_dbg(dev, "data format [0x%08X]\n", data_format);
@@ -336,7 +337,8 @@ static int rmnet_changelink(struct net_device *dev, struct nlattr *tb[],
 
 		old_data_format = port->data_format;
 		flags = nla_data(data[IFLA_RMNET_FLAGS]);
-		port->data_format = flags->flags & flags->mask;
+		port->data_format &= ~flags->mask;
+		port->data_format |= flags->flags & flags->mask;
 
 		if (rmnet_vnd_update_dev_mtu(port, real_dev)) {
 			port->data_format = old_data_format;
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h
index 8d8d4690a074..3d3cba56c516 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h
@@ -1,5 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
-/* Copyright (c) 2013-2014, 2016-2018 The Linux Foundation. All rights reserved.
+/* Copyright (c) 2013-2014, 2016-2018, 2021 The Linux Foundation.
+ * All rights reserved.
  *
  * RMNET Data configuration engine
  */
@@ -48,6 +49,7 @@ struct rmnet_pcpu_stats {
 
 struct rmnet_priv_stats {
 	u64 csum_ok;
+	u64 csum_ip4_header_bad;
 	u64 csum_valid_unset;
 	u64 csum_validation_failed;
 	u64 csum_err_bad_buffer;
@@ -56,6 +58,7 @@ struct rmnet_priv_stats {
 	u64 csum_fragmented_pkt;
 	u64 csum_skipped;
 	u64 csum_sw;
+	u64 csum_hw;
 };
 
 struct rmnet_priv {
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
index 0be5ac7ab261..bfbd7847f946 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/* Copyright (c) 2013-2018, The Linux Foundation. All rights reserved.
+/* Copyright (c) 2013-2018, 2021, The Linux Foundation. All rights reserved.
  *
  * RMNET Data ingress/egress handler
  */
@@ -82,12 +82,18 @@ __rmnet_map_ingress_handler(struct sk_buff *skb,
 
 	skb->dev = ep->egress_dev;
 
-	/* Subtract MAP header */
-	skb_pull(skb, sizeof(struct rmnet_map_header));
-	rmnet_set_skb_proto(skb);
-
-	if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4) {
-		if (!rmnet_map_checksum_downlink_packet(skb, len + pad))
+	if ((port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV5) &&
+	    (map_header->flags & MAP_NEXT_HEADER_FLAG)) {
+		if (rmnet_map_process_next_hdr_packet(skb, len))
+			goto free_skb;
+		skb_pull(skb, sizeof(*map_header));
+		rmnet_set_skb_proto(skb);
+	} else {
+		/* Subtract MAP header */
+		skb_pull(skb, sizeof(*map_header));
+		rmnet_set_skb_proto(skb);
+		if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4 &&
+		    !rmnet_map_checksum_downlink_packet(skb, len + pad))
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 	}
 
@@ -128,7 +134,7 @@ static int rmnet_map_egress_handler(struct sk_buff *skb,
 				    struct rmnet_port *port, u8 mux_id,
 				    struct net_device *orig_dev)
 {
-	int required_headroom, additional_header_len;
+	int required_headroom, additional_header_len, csum_type = 0;
 	struct rmnet_map_header *map_header;
 
 	additional_header_len = 0;
@@ -136,18 +142,23 @@ static int rmnet_map_egress_handler(struct sk_buff *skb,
 
 	if (port->data_format & RMNET_FLAGS_EGRESS_MAP_CKSUMV4) {
 		additional_header_len = sizeof(struct rmnet_map_ul_csum_header);
-		required_headroom += additional_header_len;
+		csum_type = RMNET_FLAGS_EGRESS_MAP_CKSUMV4;
+	} else if (port->data_format & RMNET_FLAGS_EGRESS_MAP_CKSUMV5) {
+		additional_header_len = sizeof(struct rmnet_map_v5_csum_header);
+		csum_type = RMNET_FLAGS_EGRESS_MAP_CKSUMV5;
 	}
 
-	if (skb_headroom(skb) < required_headroom) {
-		if (pskb_expand_head(skb, required_headroom, 0, GFP_ATOMIC))
-			return -ENOMEM;
-	}
+	required_headroom += additional_header_len;
+
+	if (skb_cow_head(skb, required_headroom) < 0)
+		return -ENOMEM;
 
-	if (port->data_format & RMNET_FLAGS_EGRESS_MAP_CKSUMV4)
-		rmnet_map_checksum_uplink_packet(skb, orig_dev);
+	if (csum_type)
+		rmnet_map_checksum_uplink_packet(skb, port, orig_dev,
+						 csum_type);
 
-	map_header = rmnet_map_add_map_header(skb, additional_header_len, 0);
+	map_header = rmnet_map_add_map_header(skb, additional_header_len,
+					      port, 0);
 	if (!map_header)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h
index 2aea153f4247..e5a0b38f7dbe 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
-/* Copyright (c) 2013-2018, The Linux Foundation. All rights reserved.
+/* Copyright (c) 2013-2018, 2021, The Linux Foundation. All rights reserved.
  */
 
 #ifndef _RMNET_MAP_H_
@@ -43,10 +43,15 @@ enum rmnet_map_commands {
 struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb,
 				      struct rmnet_port *port);
 struct rmnet_map_header *rmnet_map_add_map_header(struct sk_buff *skb,
-						  int hdrlen, int pad);
+						  int hdrlen,
+						  struct rmnet_port *port,
+						  int pad);
 void rmnet_map_command(struct sk_buff *skb, struct rmnet_port *port);
 int rmnet_map_checksum_downlink_packet(struct sk_buff *skb, u16 len);
 void rmnet_map_checksum_uplink_packet(struct sk_buff *skb,
-				      struct net_device *orig_dev);
+				      struct rmnet_port *port,
+				      struct net_device *orig_dev,
+				      int csum_type);
+int rmnet_map_process_next_hdr_packet(struct sk_buff *skb, u16 len);
 
 #endif /* _RMNET_MAP_H_ */
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
index 0ac2ff828320..3ee5c1a8b46e 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/* Copyright (c) 2013-2018, The Linux Foundation. All rights reserved.
+/* Copyright (c) 2013-2018, 2021, The Linux Foundation. All rights reserved.
  *
  * RMNET Data MAP protocol
  */
@@ -8,6 +8,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <net/ip6_checksum.h>
+#include <linux/bitfield.h>
 #include "rmnet_config.h"
 #include "rmnet_map.h"
 #include "rmnet_private.h"
@@ -18,23 +19,13 @@
 static __sum16 *rmnet_map_get_csum_field(unsigned char protocol,
 					 const void *txporthdr)
 {
-	__sum16 *check = NULL;
+	if (protocol == IPPROTO_TCP)
+		return &((struct tcphdr *)txporthdr)->check;
 
-	switch (protocol) {
-	case IPPROTO_TCP:
-		check = &(((struct tcphdr *)txporthdr)->check);
-		break;
-
-	case IPPROTO_UDP:
-		check = &(((struct udphdr *)txporthdr)->check);
-		break;
+	if (protocol == IPPROTO_UDP)
+		return &((struct udphdr *)txporthdr)->check;
 
-	default:
-		check = NULL;
-		break;
-	}
-
-	return check;
+	return NULL;
 }
 
 static int
@@ -42,71 +33,74 @@ rmnet_map_ipv4_dl_csum_trailer(struct sk_buff *skb,
 			       struct rmnet_map_dl_csum_trailer *csum_trailer,
 			       struct rmnet_priv *priv)
 {
-	__sum16 *csum_field, csum_temp, pseudo_csum, hdr_csum, ip_payload_csum;
-	u16 csum_value, csum_value_final;
-	struct iphdr *ip4h;
-	void *txporthdr;
-	__be16 addend;
-
-	ip4h = (struct iphdr *)(skb->data);
-	if ((ntohs(ip4h->frag_off) & IP_MF) ||
-	    ((ntohs(ip4h->frag_off) & IP_OFFSET) > 0)) {
+	struct iphdr *ip4h = (struct iphdr *)skb->data;
+	void *txporthdr = skb->data + ip4h->ihl * 4;
+	__sum16 *csum_field, pseudo_csum;
+	__sum16 ip_payload_csum;
+
+	/* Computing the checksum over just the IPv4 header--including its
+	 * checksum field--should yield 0.  If it doesn't, the IP header
+	 * is bad, so return an error and let the IP layer drop it.
+	 */
+	if (ip_fast_csum(ip4h, ip4h->ihl)) {
+		priv->stats.csum_ip4_header_bad++;
+		return -EINVAL;
+	}
+
+	/* We don't support checksum offload on IPv4 fragments */
+	if (ip_is_fragment(ip4h)) {
 		priv->stats.csum_fragmented_pkt++;
 		return -EOPNOTSUPP;
 	}
 
-	txporthdr = skb->data + ip4h->ihl * 4;
-
+	/* Checksum offload is only supported for UDP and TCP protocols */
 	csum_field = rmnet_map_get_csum_field(ip4h->protocol, txporthdr);
-
 	if (!csum_field) {
 		priv->stats.csum_err_invalid_transport++;
 		return -EPROTONOSUPPORT;
 	}
 
-	/* RFC 768 - Skip IPv4 UDP packets where sender checksum field is 0 */
-	if (*csum_field == 0 && ip4h->protocol == IPPROTO_UDP) {
+	/* RFC 768: UDP checksum is optional for IPv4, and is 0 if unused */
+	if (!*csum_field && ip4h->protocol == IPPROTO_UDP) {
 		priv->stats.csum_skipped++;
 		return 0;
 	}
 
-	csum_value = ~ntohs(csum_trailer->csum_value);
-	hdr_csum = ~ip_fast_csum(ip4h, (int)ip4h->ihl);
-	ip_payload_csum = csum16_sub((__force __sum16)csum_value,
-				     (__force __be16)hdr_csum);
-
-	pseudo_csum = ~csum_tcpudp_magic(ip4h->saddr, ip4h->daddr,
-					 ntohs(ip4h->tot_len) - ip4h->ihl * 4,
-					 ip4h->protocol, 0);
-	addend = (__force __be16)ntohs((__force __be16)pseudo_csum);
-	pseudo_csum = csum16_add(ip_payload_csum, addend);
-
-	addend = (__force __be16)ntohs((__force __be16)*csum_field);
-	csum_temp = ~csum16_sub(pseudo_csum, addend);
-	csum_value_final = (__force u16)csum_temp;
-
-	if (unlikely(csum_value_final == 0)) {
-		switch (ip4h->protocol) {
-		case IPPROTO_UDP:
-			/* RFC 768 - DL4 1's complement rule for UDP csum 0 */
-			csum_value_final = ~csum_value_final;
-			break;
-
-		case IPPROTO_TCP:
-			/* DL4 Non-RFC compliant TCP checksum found */
-			if (*csum_field == (__force __sum16)0xFFFF)
-				csum_value_final = ~csum_value_final;
-			break;
-		}
-	}
-
-	if (csum_value_final == ntohs((__force __be16)*csum_field)) {
-		priv->stats.csum_ok++;
-		return 0;
-	} else {
+	/* The checksum value in the trailer is computed over the entire
+	 * IP packet, including the IP header and payload.  To derive the
+	 * transport checksum from this, we first subract the contribution
+	 * of the IP header from the trailer checksum.  We then add the
+	 * checksum computed over the pseudo header.
+	 *
+	 * We verified above that the IP header contributes zero to the
+	 * trailer checksum.  Therefore the checksum in the trailer is
+	 * just the checksum computed over the IP payload.
+
+	 * If the IP payload arrives intact, adding the pseudo header
+	 * checksum to the IP payload checksum will yield 0xffff (negative
+	 * zero).  This means the trailer checksum and the pseudo checksum
+	 * are additive inverses of each other.  Put another way, the
+	 * message passes the checksum test if the trailer checksum value
+	 * is the negated pseudo header checksum.
+	 *
+	 * Knowing this, we don't even need to examine the transport
+	 * header checksum value; it is already accounted for in the
+	 * checksum value found in the trailer.
+	 */
+	ip_payload_csum = csum_trailer->csum_value;
+
+	pseudo_csum = csum_tcpudp_magic(ip4h->saddr, ip4h->daddr,
+					ntohs(ip4h->tot_len) - ip4h->ihl * 4,
+					ip4h->protocol, 0);
+
+	/* The cast is required to ensure only the low 16 bits are examined */
+	if (ip_payload_csum != (__sum16)~pseudo_csum) {
 		priv->stats.csum_validation_failed++;
 		return -EINVAL;
 	}
+
+	priv->stats.csum_ok++;
+	return 0;
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -115,76 +109,66 @@ rmnet_map_ipv6_dl_csum_trailer(struct sk_buff *skb,
 			       struct rmnet_map_dl_csum_trailer *csum_trailer,
 			       struct rmnet_priv *priv)
 {
-	__sum16 *csum_field, ip6_payload_csum, pseudo_csum, csum_temp;
-	u16 csum_value, csum_value_final;
-	__be16 ip6_hdr_csum, addend;
-	struct ipv6hdr *ip6h;
-	void *txporthdr;
-	u32 length;
-
-	ip6h = (struct ipv6hdr *)(skb->data);
-
-	txporthdr = skb->data + sizeof(struct ipv6hdr);
+	struct ipv6hdr *ip6h = (struct ipv6hdr *)skb->data;
+	void *txporthdr = skb->data + sizeof(*ip6h);
+	__sum16 *csum_field, pseudo_csum;
+	__sum16 ip6_payload_csum;
+	__be16 ip_header_csum;
+
+	/* Checksum offload is only supported for UDP and TCP protocols;
+	 * the packet cannot include any IPv6 extension headers
+	 */
 	csum_field = rmnet_map_get_csum_field(ip6h->nexthdr, txporthdr);
-
 	if (!csum_field) {
 		priv->stats.csum_err_invalid_transport++;
 		return -EPROTONOSUPPORT;
 	}
 
-	csum_value = ~ntohs(csum_trailer->csum_value);
-	ip6_hdr_csum = (__force __be16)
-			~ntohs((__force __be16)ip_compute_csum(ip6h,
-			       (int)(txporthdr - (void *)(skb->data))));
-	ip6_payload_csum = csum16_sub((__force __sum16)csum_value,
-				      ip6_hdr_csum);
-
-	length = (ip6h->nexthdr == IPPROTO_UDP) ?
-		 ntohs(((struct udphdr *)txporthdr)->len) :
-		 ntohs(ip6h->payload_len);
-	pseudo_csum = ~(csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
-			     length, ip6h->nexthdr, 0));
-	addend = (__force __be16)ntohs((__force __be16)pseudo_csum);
-	pseudo_csum = csum16_add(ip6_payload_csum, addend);
-
-	addend = (__force __be16)ntohs((__force __be16)*csum_field);
-	csum_temp = ~csum16_sub(pseudo_csum, addend);
-	csum_value_final = (__force u16)csum_temp;
-
-	if (unlikely(csum_value_final == 0)) {
-		switch (ip6h->nexthdr) {
-		case IPPROTO_UDP:
-			/* RFC 2460 section 8.1
-			 * DL6 One's complement rule for UDP checksum 0
-			 */
-			csum_value_final = ~csum_value_final;
-			break;
-
-		case IPPROTO_TCP:
-			/* DL6 Non-RFC compliant TCP checksum found */
-			if (*csum_field == (__force __sum16)0xFFFF)
-				csum_value_final = ~csum_value_final;
-			break;
-		}
-	}
-
-	if (csum_value_final == ntohs((__force __be16)*csum_field)) {
-		priv->stats.csum_ok++;
-		return 0;
-	} else {
+	/* The checksum value in the trailer is computed over the entire
+	 * IP packet, including the IP header and payload.  To derive the
+	 * transport checksum from this, we first subract the contribution
+	 * of the IP header from the trailer checksum.  We then add the
+	 * checksum computed over the pseudo header.
+	 */
+	ip_header_csum = (__force __be16)ip_fast_csum(ip6h, sizeof(*ip6h) / 4);
+	ip6_payload_csum = csum16_sub(csum_trailer->csum_value, ip_header_csum);
+
+	pseudo_csum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
+				      ntohs(ip6h->payload_len),
+				      ip6h->nexthdr, 0);
+
+	/* It's sufficient to compare the IP payload checksum with the
+	 * negated pseudo checksum to determine whether the packet
+	 * checksum was good.  (See further explanation in comments
+	 * in rmnet_map_ipv4_dl_csum_trailer()).
+	 *
+	 * The cast is required to ensure only the low 16 bits are
+	 * examined.
+	 */
+	if (ip6_payload_csum != (__sum16)~pseudo_csum) {
 		priv->stats.csum_validation_failed++;
 		return -EINVAL;
 	}
+
+	priv->stats.csum_ok++;
+	return 0;
+}
+#else
+static int
+rmnet_map_ipv6_dl_csum_trailer(struct sk_buff *skb,
+			       struct rmnet_map_dl_csum_trailer *csum_trailer,
+			       struct rmnet_priv *priv)
+{
+	return 0;
 }
 #endif
 
-static void rmnet_map_complement_ipv4_txporthdr_csum_field(void *iphdr)
+static void rmnet_map_complement_ipv4_txporthdr_csum_field(struct iphdr *ip4h)
 {
-	struct iphdr *ip4h = (struct iphdr *)iphdr;
 	void *txphdr;
 	u16 *csum;
 
-	txphdr = iphdr + ip4h->ihl * 4;
+	txphdr = ip4h + ip4h->ihl * 4;
 
 	if (ip4h->protocol == IPPROTO_TCP || ip4h->protocol == IPPROTO_UDP) {
 		csum = (u16 *)rmnet_map_get_csum_field(ip4h->protocol, txphdr);
@@ -193,15 +177,14 @@ static void rmnet_map_complement_ipv4_txporthdr_csum_field(void *iphdr)
 }
 
 static void
-rmnet_map_ipv4_ul_csum_header(void *iphdr,
+rmnet_map_ipv4_ul_csum_header(struct iphdr *iphdr,
 			      struct rmnet_map_ul_csum_header *ul_header,
 			      struct sk_buff *skb)
 {
-	struct iphdr *ip4h = iphdr;
 	u16 val;
 
 	val = MAP_CSUM_UL_ENABLED_FLAG;
-	if (ip4h->protocol == IPPROTO_UDP)
+	if (iphdr->protocol == IPPROTO_UDP)
 		val |= MAP_CSUM_UL_UDP_FLAG;
 	val |= skb->csum_offset & MAP_CSUM_UL_OFFSET_MASK;
 
@@ -214,13 +197,13 @@ rmnet_map_ipv4_ul_csum_header(void *iphdr,
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static void rmnet_map_complement_ipv6_txporthdr_csum_field(void *ip6hdr)
+static void
+rmnet_map_complement_ipv6_txporthdr_csum_field(struct ipv6hdr *ip6h)
 {
-	struct ipv6hdr *ip6h = (struct ipv6hdr *)ip6hdr;
 	void *txphdr;
 	u16 *csum;
 
-	txphdr = ip6hdr + sizeof(struct ipv6hdr);
+	txphdr = ip6h + sizeof(struct ipv6hdr);
 
 	if (ip6h->nexthdr == IPPROTO_TCP || ip6h->nexthdr == IPPROTO_UDP) {
 		csum = (u16 *)rmnet_map_get_csum_field(ip6h->nexthdr, txphdr);
@@ -229,15 +212,14 @@ static void rmnet_map_complement_ipv6_txporthdr_csum_field(void *ip6hdr)
 }
 
 static void
-rmnet_map_ipv6_ul_csum_header(void *ip6hdr,
+rmnet_map_ipv6_ul_csum_header(struct ipv6hdr *ipv6hdr,
 			      struct rmnet_map_ul_csum_header *ul_header,
 			      struct sk_buff *skb)
 {
-	struct ipv6hdr *ip6h = ip6hdr;
 	u16 val;
 
 	val = MAP_CSUM_UL_ENABLED_FLAG;
-	if (ip6h->nexthdr == IPPROTO_UDP)
+	if (ipv6hdr->nexthdr == IPPROTO_UDP)
 		val |= MAP_CSUM_UL_UDP_FLAG;
 	val |= skb->csum_offset & MAP_CSUM_UL_OFFSET_MASK;
 
@@ -246,16 +228,73 @@ rmnet_map_ipv6_ul_csum_header(void *ip6hdr,
 
 	skb->ip_summed = CHECKSUM_NONE;
 
-	rmnet_map_complement_ipv6_txporthdr_csum_field(ip6hdr);
+	rmnet_map_complement_ipv6_txporthdr_csum_field(ipv6hdr);
+}
+#else
+static void
+rmnet_map_ipv6_ul_csum_header(void *ip6hdr,
+			      struct rmnet_map_ul_csum_header *ul_header,
+			      struct sk_buff *skb)
+{
 }
 #endif
 
+static void rmnet_map_v5_checksum_uplink_packet(struct sk_buff *skb,
+						struct rmnet_port *port,
+						struct net_device *orig_dev)
+{
+	struct rmnet_priv *priv = netdev_priv(orig_dev);
+	struct rmnet_map_v5_csum_header *ul_header;
+
+	ul_header = skb_push(skb, sizeof(*ul_header));
+	memset(ul_header, 0, sizeof(*ul_header));
+	ul_header->header_info = u8_encode_bits(RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD,
+						MAPV5_HDRINFO_HDR_TYPE_FMASK);
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		void *iph = ip_hdr(skb);
+		__sum16 *check;
+		void *trans;
+		u8 proto;
+
+		if (skb->protocol == htons(ETH_P_IP)) {
+			u16 ip_len = ((struct iphdr *)iph)->ihl * 4;
+
+			proto = ((struct iphdr *)iph)->protocol;
+			trans = iph + ip_len;
+		} else if (IS_ENABLED(CONFIG_IPV6) &&
+			   skb->protocol == htons(ETH_P_IPV6)) {
+			u16 ip_len = sizeof(struct ipv6hdr);
+
+			proto = ((struct ipv6hdr *)iph)->nexthdr;
+			trans = iph + ip_len;
+		} else {
+			priv->stats.csum_err_invalid_ip_version++;
+			goto sw_csum;
+		}
+
+		check = rmnet_map_get_csum_field(proto, trans);
+		if (check) {
+			skb->ip_summed = CHECKSUM_NONE;
+			/* Ask for checksum offloading */
+			ul_header->csum_info |= MAPV5_CSUMINFO_VALID_FLAG;
+			priv->stats.csum_hw++;
+			return;
+		}
+	}
+
+sw_csum:
+	priv->stats.csum_sw++;
+}
+
 /* Adds MAP header to front of skb->data
  * Padding is calculated and set appropriately in MAP header. Mux ID is
  * initialized to 0.
  */
 struct rmnet_map_header *rmnet_map_add_map_header(struct sk_buff *skb,
-						  int hdrlen, int pad)
+						  int hdrlen,
+						  struct rmnet_port *port,
+						  int pad)
 {
 	struct rmnet_map_header *map_header;
 	u32 padding, map_datalen;
@@ -266,6 +305,10 @@ struct rmnet_map_header *rmnet_map_add_map_header(struct sk_buff *skb,
 			skb_push(skb, sizeof(struct rmnet_map_header));
 	memset(map_header, 0, sizeof(struct rmnet_map_header));
 
+	/* Set next_hdr bit for csum offload packets */
+	if (port->data_format & RMNET_FLAGS_EGRESS_MAP_CKSUMV5)
+		map_header->flags |= MAP_NEXT_HEADER_FLAG;
+
 	if (pad == RMNET_MAP_NO_PAD_BYTES) {
 		map_header->pkt_len = htons(map_datalen);
 		return map_header;
@@ -300,8 +343,11 @@ done:
 struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb,
 				      struct rmnet_port *port)
 {
+	struct rmnet_map_v5_csum_header *next_hdr = NULL;
 	struct rmnet_map_header *maph;
+	void *data = skb->data;
 	struct sk_buff *skbn;
+	u8 nexthdr_type;
 	u32 packet_len;
 
 	if (skb->len == 0)
@@ -310,8 +356,18 @@ struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb,
 	maph = (struct rmnet_map_header *)skb->data;
 	packet_len = ntohs(maph->pkt_len) + sizeof(*maph);
 
-	if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4)
+	if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4) {
 		packet_len += sizeof(struct rmnet_map_dl_csum_trailer);
+	} else if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV5) {
+		if (!(maph->flags & MAP_CMD_FLAG)) {
+			packet_len += sizeof(*next_hdr);
+			if (maph->flags & MAP_NEXT_HEADER_FLAG)
+				next_hdr = data + sizeof(*maph);
+			else
+				/* Mapv5 data pkt without csum hdr is invalid */
+				return NULL;
+		}
+	}
 
 	if (((int)skb->len - (int)packet_len) < 0)
 		return NULL;
@@ -320,6 +376,13 @@ struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb,
 	if (!maph->pkt_len)
 		return NULL;
 
+	if (next_hdr) {
+		nexthdr_type = u8_get_bits(next_hdr->header_info,
+					   MAPV5_HDRINFO_HDR_TYPE_FMASK);
+		if (nexthdr_type != RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD)
+			return NULL;
+	}
+
 	skbn = alloc_skb(packet_len + RMNET_MAP_DEAGGR_SPACING, GFP_ATOMIC);
 	if (!skbn)
 		return NULL;
@@ -355,28 +418,19 @@ int rmnet_map_checksum_downlink_packet(struct sk_buff *skb, u16 len)
 		return -EINVAL;
 	}
 
-	if (skb->protocol == htons(ETH_P_IP)) {
+	if (skb->protocol == htons(ETH_P_IP))
 		return rmnet_map_ipv4_dl_csum_trailer(skb, csum_trailer, priv);
-	} else if (skb->protocol == htons(ETH_P_IPV6)) {
-#if IS_ENABLED(CONFIG_IPV6)
+
+	if (IS_ENABLED(CONFIG_IPV6) && skb->protocol == htons(ETH_P_IPV6))
 		return rmnet_map_ipv6_dl_csum_trailer(skb, csum_trailer, priv);
-#else
-		priv->stats.csum_err_invalid_ip_version++;
-		return -EPROTONOSUPPORT;
-#endif
-	} else {
-		priv->stats.csum_err_invalid_ip_version++;
-		return -EPROTONOSUPPORT;
-	}
 
-	return 0;
+	priv->stats.csum_err_invalid_ip_version++;
+
+	return -EPROTONOSUPPORT;
 }
 
-/* Generates UL checksum meta info header for IPv4 and IPv6 over TCP and UDP
- * packets that are supported for UL checksum offload.
- */
-void rmnet_map_checksum_uplink_packet(struct sk_buff *skb,
-				      struct net_device *orig_dev)
+static void rmnet_map_v4_checksum_uplink_packet(struct sk_buff *skb,
+						struct net_device *orig_dev)
 {
 	struct rmnet_priv *priv = netdev_priv(orig_dev);
 	struct rmnet_map_ul_csum_header *ul_header;
@@ -389,28 +443,80 @@ void rmnet_map_checksum_uplink_packet(struct sk_buff *skb,
 		     (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM))))
 		goto sw_csum;
 
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		iphdr = (char *)ul_header +
-			sizeof(struct rmnet_map_ul_csum_header);
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		goto sw_csum;
 
-		if (skb->protocol == htons(ETH_P_IP)) {
-			rmnet_map_ipv4_ul_csum_header(iphdr, ul_header, skb);
-			return;
-		} else if (skb->protocol == htons(ETH_P_IPV6)) {
-#if IS_ENABLED(CONFIG_IPV6)
-			rmnet_map_ipv6_ul_csum_header(iphdr, ul_header, skb);
-			return;
-#else
-			priv->stats.csum_err_invalid_ip_version++;
-			goto sw_csum;
-#endif
-		} else {
-			priv->stats.csum_err_invalid_ip_version++;
-		}
+	iphdr = (char *)ul_header +
+		sizeof(struct rmnet_map_ul_csum_header);
+
+	if (skb->protocol == htons(ETH_P_IP)) {
+		rmnet_map_ipv4_ul_csum_header(iphdr, ul_header, skb);
+		priv->stats.csum_hw++;
+		return;
+	}
+
+	if (IS_ENABLED(CONFIG_IPV6) && skb->protocol == htons(ETH_P_IPV6)) {
+		rmnet_map_ipv6_ul_csum_header(iphdr, ul_header, skb);
+		priv->stats.csum_hw++;
+		return;
 	}
 
+	priv->stats.csum_err_invalid_ip_version++;
+
 sw_csum:
 	memset(ul_header, 0, sizeof(*ul_header));
 
 	priv->stats.csum_sw++;
 }
+
+/* Generates UL checksum meta info header for IPv4 and IPv6 over TCP and UDP
+ * packets that are supported for UL checksum offload.
+ */
+void rmnet_map_checksum_uplink_packet(struct sk_buff *skb,
+				      struct rmnet_port *port,
+				      struct net_device *orig_dev,
+				      int csum_type)
+{
+	switch (csum_type) {
+	case RMNET_FLAGS_EGRESS_MAP_CKSUMV4:
+		rmnet_map_v4_checksum_uplink_packet(skb, orig_dev);
+		break;
+	case RMNET_FLAGS_EGRESS_MAP_CKSUMV5:
+		rmnet_map_v5_checksum_uplink_packet(skb, port, orig_dev);
+		break;
+	default:
+		break;
+	}
+}
+
+/* Process a MAPv5 packet header */
+int rmnet_map_process_next_hdr_packet(struct sk_buff *skb,
+				      u16 len)
+{
+	struct rmnet_priv *priv = netdev_priv(skb->dev);
+	struct rmnet_map_v5_csum_header *next_hdr;
+	u8 nexthdr_type;
+
+	next_hdr = (struct rmnet_map_v5_csum_header *)(skb->data +
+			sizeof(struct rmnet_map_header));
+
+	nexthdr_type = u8_get_bits(next_hdr->header_info,
+				   MAPV5_HDRINFO_HDR_TYPE_FMASK);
+
+	if (nexthdr_type != RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD)
+		return -EINVAL;
+
+	if (unlikely(!(skb->dev->features & NETIF_F_RXCSUM))) {
+		priv->stats.csum_sw++;
+	} else if (next_hdr->csum_info & MAPV5_CSUMINFO_VALID_FLAG) {
+		priv->stats.csum_ok++;
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	} else {
+		priv->stats.csum_valid_unset++;
+	}
+
+	/* Pull csum v5 header */
+	skb_pull(skb, sizeof(*next_hdr));
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
index ab1e0fcccabb..13d8eb43a485 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
@@ -166,6 +166,7 @@ static const struct net_device_ops rmnet_vnd_ops = {
 
 static const char rmnet_gstrings_stats[][ETH_GSTRING_LEN] = {
 	"Checksum ok",
+	"Bad IPv4 header checksum",
 	"Checksum valid bit not set",
 	"Checksum validation failed",
 	"Checksum error bad buffer",
@@ -174,6 +175,7 @@ static const char rmnet_gstrings_stats[][ETH_GSTRING_LEN] = {
 	"Checksum skipped on ip fragment",
 	"Checksum skipped",
 	"Checksum computed in software",
+	"Checksum computed in hardware",
 };
 
 static void rmnet_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c
index 7c74318620b1..47e9998b62f0 100644
--- a/drivers/net/ethernet/rdc/r6040.c
+++ b/drivers/net/ethernet/rdc/r6040.c
@@ -200,7 +200,7 @@ static int r6040_phy_read(void __iomem *ioaddr, int phy_addr, int reg)
 	int limit = MAC_DEF_TIMEOUT;
 	u16 cmd;
 
-	iowrite16(MDIO_READ + reg + (phy_addr << 8), ioaddr + MMDIO);
+	iowrite16(MDIO_READ | reg | (phy_addr << 8), ioaddr + MMDIO);
 	/* Wait for the read bit to be cleared */
 	while (limit--) {
 		cmd = ioread16(ioaddr + MMDIO);
@@ -224,7 +224,7 @@ static int r6040_phy_write(void __iomem *ioaddr,
 
 	iowrite16(val, ioaddr + MMWD);
 	/* Write the command to the MDIO bus */
-	iowrite16(MDIO_WRITE + reg + (phy_addr << 8), ioaddr + MMDIO);
+	iowrite16(MDIO_WRITE | reg | (phy_addr << 8), ioaddr + MMDIO);
 	/* Wait for the write bit to be cleared */
 	while (limit--) {
 		cmd = ioread16(ioaddr + MMDIO);
@@ -544,7 +544,7 @@ static int r6040_rx(struct net_device *dev, int limit)
 		skb_ptr->dev = priv->dev;
 
 		/* Do not count the CRC */
-		skb_put(skb_ptr, descptr->len - 4);
+		skb_put(skb_ptr, descptr->len - ETH_FCS_LEN);
 		dma_unmap_single(&priv->pdev->dev, le32_to_cpu(descptr->buf),
 				 MAX_BUF_SIZE, DMA_FROM_DEVICE);
 		skb_ptr->protocol = eth_type_trans(skb_ptr, priv->dev);
@@ -552,7 +552,7 @@ static int r6040_rx(struct net_device *dev, int limit)
 		/* Send to upper layer */
 		netif_receive_skb(skb_ptr);
 		dev->stats.rx_packets++;
-		dev->stats.rx_bytes += descptr->len - 4;
+		dev->stats.rx_bytes += descptr->len - ETH_FCS_LEN;
 
 		/* put new skb into descriptor */
 		descptr->skb_ptr = new_skb;
@@ -943,6 +943,7 @@ static const struct ethtool_ops netdev_ethtool_ops = {
 	.get_ts_info		= ethtool_op_get_ts_info,
 	.get_link_ksettings     = phy_ethtool_get_link_ksettings,
 	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
+	.nway_reset		= phy_ethtool_nway_reset,
 };
 
 static const struct net_device_ops r6040_netdev_ops = {
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index 4e44313b7651..9677e257e9a1 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -6,7 +6,7 @@
 	Copyright (C) 2000, 2001 David S. Miller (davem@redhat.com) [sungem.c]
 	Copyright 2001 Manfred Spraul				    [natsemi.c]
 	Copyright 1999-2001 by Donald Becker.			    [natsemi.c]
-       	Written 1997-2001 by Donald Becker.			    [8139too.c]
+	Written 1997-2001 by Donald Becker.			    [8139too.c]
 	Copyright 1998-2001 by Jes Sorensen, <jes@trained-monkey.org>. [acenic.c]
 
 	This software may be used and distributed according to the terms of
@@ -947,8 +947,8 @@ static struct net_device_stats *cp_get_stats(struct net_device *dev)
 
 	/* The chip only need report frame silently dropped. */
 	spin_lock_irqsave(&cp->lock, flags);
- 	if (netif_running(dev) && netif_device_present(dev))
- 		__cp_get_stats(cp);
+	if (netif_running(dev) && netif_device_present(dev))
+		__cp_get_stats(cp);
 	spin_unlock_irqrestore(&cp->lock, flags);
 
 	return &dev->stats;
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index 1e5a453dea14..f0608f050050 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -11,7 +11,7 @@
 
 	-----<snip>-----
 
-        	Written 1997-2001 by Donald Becker.
+		Written 1997-2001 by Donald Becker.
 		This software may be used and distributed according to the
 		terms of the GNU General Public License (GPL), incorporated
 		herein by reference.  Drivers based on or derived from this
@@ -548,8 +548,8 @@ static const struct {
 
 	{ "RTL-8100",
 	  HW_REVID(1, 1, 1, 1, 0, 1, 0),
- 	  HasLWake,
- 	},
+	  HasLWake,
+	},
 
 	{ "RTL-8100B/8139D",
 	  HW_REVID(1, 1, 1, 0, 1, 0, 1),
diff --git a/drivers/net/ethernet/realtek/atp.c b/drivers/net/ethernet/realtek/atp.c
index 9e3b35c97e63..b6c849b258a0 100644
--- a/drivers/net/ethernet/realtek/atp.c
+++ b/drivers/net/ethernet/realtek/atp.c
@@ -497,8 +497,8 @@ static void write_packet(long ioaddr, int length, unsigned char *packet, int pad
 {
     if (length & 1)
     {
-    	length++;
-    	pad_len++;
+	length++;
+	pad_len++;
     }
 
     outb(EOC+MAR, ioaddr + PAR_DATA);
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 2ee72dc431cd..f744557c33a3 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -34,8 +34,6 @@
 #include "r8169.h"
 #include "r8169_firmware.h"
 
-#define MODULENAME "r8169"
-
 #define FIRMWARE_8168D_1	"rtl_nic/rtl8168d-1.fw"
 #define FIRMWARE_8168D_2	"rtl_nic/rtl8168d-2.fw"
 #define FIRMWARE_8168E_1	"rtl_nic/rtl8168e-1.fw"
@@ -1454,7 +1452,7 @@ static void rtl8169_get_drvinfo(struct net_device *dev,
 	struct rtl8169_private *tp = netdev_priv(dev);
 	struct rtl_fw *rtl_fw = tp->rtl_fw;
 
-	strlcpy(info->driver, MODULENAME, sizeof(info->driver));
+	strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
 	strlcpy(info->bus_info, pci_name(tp->pci_dev), sizeof(info->bus_info));
 	BUILD_BUG_ON(sizeof(info->fw_version) < sizeof(rtl_fw->version));
 	if (rtl_fw)
@@ -3510,7 +3508,6 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp)
 	rtl_eri_write(tp, 0x1b0, ERIAR_MASK_0011, 0x0000);
 
 	rtl_pcie_state_l2l3_disable(tp);
-	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 DECLARE_RTL_COND(rtl_mac_ocp_e00e_cond)
@@ -4117,6 +4114,7 @@ static unsigned int rtl_quirk_packet_padto(struct rtl8169_private *tp,
 	case RTL_GIGA_MAC_VER_61:
 	case RTL_GIGA_MAC_VER_63:
 		padto = max_t(unsigned int, padto, ETH_ZLEN);
+		break;
 	default:
 		break;
 	}
@@ -5305,7 +5303,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return -ENODEV;
 	}
 
-	rc = pcim_iomap_regions(pdev, BIT(region), MODULENAME);
+	rc = pcim_iomap_regions(pdev, BIT(region), KBUILD_MODNAME);
 	if (rc < 0) {
 		dev_err(&pdev->dev, "cannot remap MMIO, aborting\n");
 		return rc;
@@ -5440,7 +5438,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 }
 
 static struct pci_driver rtl8169_pci_driver = {
-	.name		= MODULENAME,
+	.name		= KBUILD_MODNAME,
 	.id_table	= rtl8169_pci_tbl,
 	.probe		= rtl_init_one,
 	.remove		= rtl_remove_one,
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 4afff320dfd0..69c50f81e1cb 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -2047,13 +2047,6 @@ static int ravb_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	/* Get base address */
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "invalid resource\n");
-		return -EINVAL;
-	}
-
 	ndev = alloc_etherdev_mqs(sizeof(struct ravb_private),
 				  NUM_TX_QUEUE, NUM_RX_QUEUE);
 	if (!ndev)
@@ -2065,9 +2058,6 @@ static int ravb_probe(struct platform_device *pdev)
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_get_sync(&pdev->dev);
 
-	/* The Ether-specific entries in the device structure. */
-	ndev->base_addr = res->start;
-
 	chip_id = (enum ravb_chip_id)of_device_get_match_data(&pdev->dev);
 
 	if (chip_id == RCAR_GEN3)
@@ -2089,12 +2079,15 @@ static int ravb_probe(struct platform_device *pdev)
 	priv->num_rx_ring[RAVB_BE] = BE_RX_RING_SIZE;
 	priv->num_tx_ring[RAVB_NC] = NC_TX_RING_SIZE;
 	priv->num_rx_ring[RAVB_NC] = NC_RX_RING_SIZE;
-	priv->addr = devm_ioremap_resource(&pdev->dev, res);
+	priv->addr = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(priv->addr)) {
 		error = PTR_ERR(priv->addr);
 		goto out_release;
 	}
 
+	/* The Ether-specific entries in the device structure. */
+	ndev->base_addr = res->start;
+
 	spin_lock_init(&priv->lock);
 	INIT_WORK(&priv->work, ravb_tx_timeout_work);
 
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 713d3629b4c1..840478692a37 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -3225,9 +3225,6 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
 	struct net_device *ndev;
 	int ret;
 
-	/* get base addr */
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-
 	ndev = alloc_etherdev(sizeof(struct sh_eth_private));
 	if (!ndev)
 		return -ENOMEM;
@@ -3245,7 +3242,7 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
 	mdp = netdev_priv(ndev);
 	mdp->num_tx_ring = TX_RING_SIZE;
 	mdp->num_rx_ring = RX_RING_SIZE;
-	mdp->addr = devm_ioremap_resource(&pdev->dev, res);
+	mdp->addr = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(mdp->addr)) {
 		ret = PTR_ERR(mdp->addr);
 		goto out_release;
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
index 971f1e54b652..090bcd2fb758 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -789,7 +789,7 @@ static void sxgbe_tx_queue_clean(struct sxgbe_tx_queue *tqueue)
 }
 
 /**
- * sxgbe_tx_clean:
+ * sxgbe_tx_all_clean:
  * @priv: driver private structure
  * Description: it reclaims resources after transmission completes.
  */
@@ -1015,7 +1015,7 @@ static void sxgbe_tx_timer(struct timer_list *t)
 }
 
 /**
- * sxgbe_init_tx_coalesce: init tx mitigation options.
+ * sxgbe_tx_init_coalesce: init tx mitigation options.
  * @priv: driver private structure
  * Description:
  * This inits the transmit coalesce parameters: i.e. timer rate,
diff --git a/drivers/net/ethernet/seeq/ether3.c b/drivers/net/ethernet/seeq/ether3.c
index 65c98837ec45..16a4cbae9326 100644
--- a/drivers/net/ethernet/seeq/ether3.c
+++ b/drivers/net/ethernet/seeq/ether3.c
@@ -617,7 +617,7 @@ if (next_ptr < RX_START || next_ptr >= RX_END) {
  break;
 }
 		/*
- 		 * ignore our own packets...
+		 * ignore our own packets...
 	 	 */
 		if (!(*(unsigned long *)&dev->dev_addr[0] ^ *(unsigned long *)&addrs[2+6]) &&
 		    !(*(unsigned short *)&dev->dev_addr[4] ^ *(unsigned short *)&addrs[2+10])) {
@@ -672,7 +672,7 @@ done:
 	 */
 	if (!(ether3_inw(REG_STATUS) & STAT_RXON)) {
 		dev->stats.rx_dropped++;
-    		ether3_outw(next_ptr, REG_RECVPTR);
+		ether3_outw(next_ptr, REG_RECVPTR);
 		ether3_outw(priv(dev)->regs.command | CMD_RXON, REG_COMMAND);
 	}
 
@@ -690,11 +690,11 @@ static void ether3_tx(struct net_device *dev)
 	do {
 	    	unsigned long status;
 
-    		/*
+		/*
 	    	 * Read the packet header
-    		 */
+		 */
 	    	ether3_setbuffer(dev, buffer_read, tx_tail * 0x600);
-    		status = ether3_readlong(dev);
+		status = ether3_readlong(dev);
 
 		/*
 		 * Check to see if this packet has been transmitted
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index c3f35da1b82a..d597c89f00ed 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -370,9 +370,9 @@ static int efx_ef10_get_mac_address_vf(struct efx_nic *efx, u8 *mac_address)
 	return 0;
 }
 
-static ssize_t efx_ef10_show_link_control_flag(struct device *dev,
-					       struct device_attribute *attr,
-					       char *buf)
+static ssize_t link_control_flag_show(struct device *dev,
+				      struct device_attribute *attr,
+				      char *buf)
 {
 	struct efx_nic *efx = dev_get_drvdata(dev);
 
@@ -382,9 +382,9 @@ static ssize_t efx_ef10_show_link_control_flag(struct device *dev,
 		       ? 1 : 0);
 }
 
-static ssize_t efx_ef10_show_primary_flag(struct device *dev,
-					  struct device_attribute *attr,
-					  char *buf)
+static ssize_t primary_flag_show(struct device *dev,
+				 struct device_attribute *attr,
+				 char *buf)
 {
 	struct efx_nic *efx = dev_get_drvdata(dev);
 
@@ -519,9 +519,8 @@ static void efx_ef10_cleanup_vlans(struct efx_nic *efx)
 	mutex_unlock(&nic_data->vlan_lock);
 }
 
-static DEVICE_ATTR(link_control_flag, 0444, efx_ef10_show_link_control_flag,
-		   NULL);
-static DEVICE_ATTR(primary_flag, 0444, efx_ef10_show_primary_flag, NULL);
+static DEVICE_ATTR_RO(link_control_flag);
+static DEVICE_ATTR_RO(primary_flag);
 
 static int efx_ef10_probe(struct efx_nic *efx)
 {
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index c746ca7235f1..37fcf2eb0741 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -689,13 +689,13 @@ static struct notifier_block efx_netdev_notifier = {
 	.notifier_call = efx_netdev_event,
 };
 
-static ssize_t
-show_phy_type(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t phy_type_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct efx_nic *efx = dev_get_drvdata(dev);
 	return sprintf(buf, "%d\n", efx->phy_type);
 }
-static DEVICE_ATTR(phy_type, 0444, show_phy_type, NULL);
+static DEVICE_ATTR_RO(phy_type);
 
 static int efx_register_netdev(struct efx_nic *efx)
 {
@@ -722,8 +722,7 @@ static int efx_register_netdev(struct efx_nic *efx)
 	efx->state = STATE_READY;
 	smp_mb(); /* ensure we change state before checking reset_pending */
 	if (efx->reset_pending) {
-		netif_err(efx, probe, efx->net_dev,
-			  "aborting probe due to scheduled reset\n");
+		pci_err(efx->pci_dev, "aborting probe due to scheduled reset\n");
 		rc = -EIO;
 		goto fail_locked;
 	}
@@ -990,8 +989,7 @@ static int efx_pci_probe_main(struct efx_nic *efx)
 	rc = efx->type->init(efx);
 	up_write(&efx->filter_sem);
 	if (rc) {
-		netif_err(efx, probe, efx->net_dev,
-			  "failed to initialise NIC\n");
+		pci_err(efx->pci_dev, "failed to initialise NIC\n");
 		goto fail3;
 	}
 
@@ -1038,8 +1036,8 @@ static int efx_pci_probe_post_io(struct efx_nic *efx)
 	if (efx->type->sriov_init) {
 		rc = efx->type->sriov_init(efx);
 		if (rc)
-			netif_err(efx, probe, efx->net_dev,
-				  "SR-IOV can't be enabled rc %d\n", rc);
+			pci_err(efx->pci_dev, "SR-IOV can't be enabled rc %d\n",
+				rc);
 	}
 
 	/* Determine netdevice features */
@@ -1106,8 +1104,7 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
 	if (rc)
 		goto fail1;
 
-	netif_info(efx, probe, efx->net_dev,
-		   "Solarflare NIC detected\n");
+	pci_info(pci_dev, "Solarflare NIC detected\n");
 
 	if (!efx->type->is_vf)
 		efx_probe_vpd_strings(efx);
diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c
index de797e1ac5a9..896b59253197 100644
--- a/drivers/net/ethernet/sfc/efx_common.c
+++ b/drivers/net/ethernet/sfc/efx_common.c
@@ -1160,8 +1160,9 @@ void efx_fini_io(struct efx_nic *efx)
 }
 
 #ifdef CONFIG_SFC_MCDI_LOGGING
-static ssize_t show_mcdi_log(struct device *dev, struct device_attribute *attr,
-			     char *buf)
+static ssize_t mcdi_logging_show(struct device *dev,
+				 struct device_attribute *attr,
+				 char *buf)
 {
 	struct efx_nic *efx = dev_get_drvdata(dev);
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
@@ -1169,8 +1170,9 @@ static ssize_t show_mcdi_log(struct device *dev, struct device_attribute *attr,
 	return scnprintf(buf, PAGE_SIZE, "%d\n", mcdi->logging_enabled);
 }
 
-static ssize_t set_mcdi_log(struct device *dev, struct device_attribute *attr,
-			    const char *buf, size_t count)
+static ssize_t mcdi_logging_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
 {
 	struct efx_nic *efx = dev_get_drvdata(dev);
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
@@ -1180,7 +1182,7 @@ static ssize_t set_mcdi_log(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static DEVICE_ATTR(mcdi_logging, 0644, show_mcdi_log, set_mcdi_log);
+static DEVICE_ATTR_RW(mcdi_logging);
 
 void efx_init_mcdi_logging(struct efx_nic *efx)
 {
diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c
index 5e7a57b680ca..9ec752a43c75 100644
--- a/drivers/net/ethernet/sfc/falcon/efx.c
+++ b/drivers/net/ethernet/sfc/falcon/efx.c
@@ -2254,12 +2254,12 @@ static struct notifier_block ef4_netdev_notifier = {
 };
 
 static ssize_t
-show_phy_type(struct device *dev, struct device_attribute *attr, char *buf)
+phy_type_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct ef4_nic *efx = dev_get_drvdata(dev);
 	return sprintf(buf, "%d\n", efx->phy_type);
 }
-static DEVICE_ATTR(phy_type, 0444, show_phy_type, NULL);
+static DEVICE_ATTR_RO(phy_type);
 
 static int ef4_register_netdev(struct ef4_nic *efx)
 {
diff --git a/drivers/net/ethernet/sfc/falcon/falcon_boards.c b/drivers/net/ethernet/sfc/falcon/falcon_boards.c
index 729a05c1b0cf..2d2d8099011e 100644
--- a/drivers/net/ethernet/sfc/falcon/falcon_boards.c
+++ b/drivers/net/ethernet/sfc/falcon/falcon_boards.c
@@ -354,16 +354,16 @@ fail_on:
 	return rc;
 }
 
-static ssize_t show_phy_flash_cfg(struct device *dev,
+static ssize_t phy_flash_cfg_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
 	struct ef4_nic *efx = dev_get_drvdata(dev);
 	return sprintf(buf, "%d\n", !!(efx->phy_mode & PHY_MODE_SPECIAL));
 }
 
-static ssize_t set_phy_flash_cfg(struct device *dev,
-				 struct device_attribute *attr,
-				 const char *buf, size_t count)
+static ssize_t phy_flash_cfg_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t count)
 {
 	struct ef4_nic *efx = dev_get_drvdata(dev);
 	enum ef4_phy_mode old_mode, new_mode;
@@ -396,7 +396,7 @@ static ssize_t set_phy_flash_cfg(struct device *dev,
 	return err ? err : count;
 }
 
-static DEVICE_ATTR(phy_flash_cfg, 0644, show_phy_flash_cfg, set_phy_flash_cfg);
+static DEVICE_ATTR_RW(phy_flash_cfg);
 
 static void sfe4001_fini(struct ef4_nic *efx)
 {
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index 49df02ecee91..148dcd48b58d 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -1668,13 +1668,17 @@ void efx_farch_rx_pull_indir_table(struct efx_nic *efx)
  */
 void efx_farch_dimension_resources(struct efx_nic *efx, unsigned sram_lim_qw)
 {
-	unsigned vi_count, buftbl_min, total_tx_channels;
-
+	unsigned vi_count, total_tx_channels;
 #ifdef CONFIG_SFC_SRIOV
-	struct siena_nic_data *nic_data = efx->nic_data;
+	struct siena_nic_data *nic_data;
+	unsigned buftbl_min;
 #endif
 
 	total_tx_channels = efx->n_tx_channels + efx->n_extra_tx_channels;
+	vi_count = max(efx->n_channels, total_tx_channels * EFX_MAX_TXQ_PER_CHANNEL);
+
+#ifdef CONFIG_SFC_SRIOV
+	nic_data = efx->nic_data;
 	/* Account for the buffer table entries backing the datapath channels
 	 * and the descriptor caches for those channels.
 	 */
@@ -1682,9 +1686,6 @@ void efx_farch_dimension_resources(struct efx_nic *efx, unsigned sram_lim_qw)
 		       total_tx_channels * EFX_MAX_TXQ_PER_CHANNEL * EFX_MAX_DMAQ_SIZE +
 		       efx->n_channels * EFX_MAX_EVQ_SIZE)
 		      * sizeof(efx_qword_t) / EFX_BUF_SIZE);
-	vi_count = max(efx->n_channels, total_tx_channels * EFX_MAX_TXQ_PER_CHANNEL);
-
-#ifdef CONFIG_SFC_SRIOV
 	if (efx->type->sriov_wanted) {
 		if (efx->type->sriov_wanted(efx)) {
 			unsigned vi_dc_entries, buftbl_free;
diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c
index 6eef0f45b133..2b29fd4cbdf4 100644
--- a/drivers/net/ethernet/sgi/ioc3-eth.c
+++ b/drivers/net/ethernet/sgi/ioc3-eth.c
@@ -835,6 +835,10 @@ static int ioc3eth_probe(struct platform_device *pdev)
 	int err;
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!regs) {
+		dev_err(&pdev->dev, "Invalid resource\n");
+		return -EINVAL;
+	}
 	/* get mac addr from one wire prom */
 	if (ioc3eth_get_mac_addr(regs, mac_addr))
 		return -EPROBE_DEFER; /* not available yet */
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index 620c26f71be8..ca9c00b7f588 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -678,12 +678,12 @@ static int sis900_mii_probe(struct net_device *net_dev)
 	/* Reset phy if default phy is internal sis900 */
         if ((sis_priv->mii->phy_id0 == 0x001D) &&
 	    ((sis_priv->mii->phy_id1&0xFFF0) == 0x8000))
-        	status = sis900_reset_phy(net_dev, sis_priv->cur_phy);
+		status = sis900_reset_phy(net_dev, sis_priv->cur_phy);
 
         /* workaround for ICS1893 PHY */
         if ((sis_priv->mii->phy_id0 == 0x0015) &&
             ((sis_priv->mii->phy_id1&0xFFF0) == 0xF440))
-            	mdio_write(net_dev, sis_priv->cur_phy, 0x0018, 0xD200);
+		mdio_write(net_dev, sis_priv->cur_phy, 0x0018, 0xD200);
 
 	if(status & MII_STAT_LINK){
 		while (poll_bit) {
@@ -727,7 +727,7 @@ static int sis900_mii_probe(struct net_device *net_dev)
 static u16 sis900_default_phy(struct net_device * net_dev)
 {
 	struct sis900_private *sis_priv = netdev_priv(net_dev);
- 	struct mii_phy *phy = NULL, *phy_home = NULL,
+	struct mii_phy *phy = NULL, *phy_home = NULL,
 		*default_phy = NULL, *phy_lan = NULL;
 	u16 status;
 
@@ -1339,18 +1339,18 @@ static void sis900_timer(struct timer_list *t)
 	} else {
 	/* Link ON -> OFF */
                 if (!(status & MII_STAT_LINK)){
-                	netif_carrier_off(net_dev);
+			netif_carrier_off(net_dev);
 			if(netif_msg_link(sis_priv))
-                		printk(KERN_INFO "%s: Media Link Off\n", net_dev->name);
+				printk(KERN_INFO "%s: Media Link Off\n", net_dev->name);
 
-                	/* Change mode issue */
-                	if ((mii_phy->phy_id0 == 0x001D) &&
-			    ((mii_phy->phy_id1 & 0xFFF0) == 0x8000))
-               			sis900_reset_phy(net_dev,  sis_priv->cur_phy);
+			/* Change mode issue */
+			if ((mii_phy->phy_id0 == 0x001D) &&
+				((mii_phy->phy_id1 & 0xFFF0) == 0x8000))
+					sis900_reset_phy(net_dev,  sis_priv->cur_phy);
 
 			sis630_set_eq(net_dev, sis_priv->chipset_rev);
 
-                	goto LookForLink;
+			goto LookForLink;
                 }
 	}
 
@@ -2331,7 +2331,7 @@ static int sis900_set_config(struct net_device *dev, struct ifmap *map)
 		case IF_PORT_10BASE2: /* 10Base2 */
 		case IF_PORT_AUI: /* AUI */
 		case IF_PORT_100BASEFX: /* 100BaseFx */
-                	/* These Modes are not supported (are they?)*/
+			/* These Modes are not supported (are they?)*/
 			return -EOPNOTSUPP;
 
 		default:
diff --git a/drivers/net/ethernet/smsc/smc9194.c b/drivers/net/ethernet/smsc/smc9194.c
index 4b2330deed47..bf7c8c8b1350 100644
--- a/drivers/net/ethernet/smsc/smc9194.c
+++ b/drivers/net/ethernet/smsc/smc9194.c
@@ -182,8 +182,8 @@ struct smc_local {
 	struct sk_buff * saved_skb;
 
 	/*
- 	 . This keeps track of how many packets that I have
- 	 . sent out.  When an TX_EMPTY interrupt comes, I know
+	 . This keeps track of how many packets that I have
+	 . sent out.  When an TX_EMPTY interrupt comes, I know
 	 . that all of these have been sent.
 	*/
 	int	packets_waiting;
@@ -343,7 +343,7 @@ static void smc_reset( int ioaddr )
 
 	/* Note:  It doesn't seem that waiting for the MMU busy is needed here,
 	   but this is a place where future chipsets _COULD_ break.  Be wary
- 	   of issuing another MMU command right after this */
+	   of issuing another MMU command right after this */
 
 	outb( 0, ioaddr + INT_MASK );
 }
@@ -521,9 +521,9 @@ static netdev_tx_t smc_wait_to_send_packet(struct sk_buff *skb,
 	SMC_SELECT_BANK( 2 );
 	outw( MC_ALLOC | numPages, ioaddr + MMU_CMD );
 	/*
- 	. Performance Hack
+	. Performance Hack
 	.
- 	. wait a short amount of time.. if I can send a packet now, I send
+	. wait a short amount of time.. if I can send a packet now, I send
 	. it now.  Otherwise, I enable an interrupt and wait for one to be
 	. available.
 	.
@@ -540,17 +540,17 @@ static netdev_tx_t smc_wait_to_send_packet(struct sk_buff *skb,
 		if ( status & IM_ALLOC_INT ) {
 			/* acknowledge the interrupt */
 			outb( IM_ALLOC_INT, ioaddr + INTERRUPT );
-  			break;
+			break;
 		}
-   	} while ( -- time_out );
+	} while ( -- time_out );
 
-   	if ( !time_out ) {
+	if ( !time_out ) {
 		/* oh well, wait until the chip finds memory later */
 		SMC_ENABLE_INT( IM_ALLOC_INT );
 		PRINTK2((CARDNAME": memory allocation deferred.\n"));
 		/* it's deferred, but I'll handle it later */
 		return NETDEV_TX_OK;
-   	}
+	}
 	/* or YES! I can send the packet now.. */
 	smc_hardware_send_packet(dev);
 	netif_wake_queue(dev);
@@ -616,7 +616,7 @@ static void smc_hardware_send_packet( struct net_device * dev )
 #endif
 
 	/* send the packet length ( +6 for status, length and ctl byte )
- 	   and the status word ( set to zeros ) */
+	   and the status word ( set to zeros ) */
 #ifdef USE_32_BIT
 	outl(  (length +6 ) << 16 , ioaddr + DATA_1 );
 #else
@@ -629,8 +629,8 @@ static void smc_hardware_send_packet( struct net_device * dev )
 	/* send the actual data
 	 . I _think_ it's faster to send the longs first, and then
 	 . mop up by sending the last word.  It depends heavily
- 	 . on alignment, at least on the 486.  Maybe it would be
- 	 . a good idea to check which is optimal?  But that could take
+	 . on alignment, at least on the 486.  Maybe it would be
+	 . a good idea to check which is optimal?  But that could take
 	 . almost as much time as is saved?
 	*/
 #ifdef USE_32_BIT
@@ -757,7 +757,7 @@ static int __init smc_findirq(int ioaddr)
 	outb( IM_ALLOC_INT, ioaddr + INT_MASK );
 
 	/*
- 	 . Allocate 512 bytes of memory.  Note that the chip was just
+	 . Allocate 512 bytes of memory.  Note that the chip was just
 	 . reset so all the memory is available
 	*/
 	outw( MC_ALLOC | 1, ioaddr + MMU_CMD );
@@ -871,7 +871,7 @@ static int __init smc_probe(struct net_device *dev, int ioaddr)
 		goto err_out;
 	}
 	/* The above MIGHT indicate a device, but I need to write to further
- 	 	test this.  */
+		test this.  */
 	outw( 0x0, ioaddr + BANK_SELECT );
 	bank = inw( ioaddr + BANK_SELECT );
 	if ( (bank & 0xFF00 ) != 0x3300 ) {
@@ -879,7 +879,7 @@ static int __init smc_probe(struct net_device *dev, int ioaddr)
 		goto err_out;
 	}
 	/* well, we've already written once, so hopefully another time won't
- 	   hurt.  This time, I need to switch the bank register to bank 1,
+	   hurt.  This time, I need to switch the bank register to bank 1,
 	   so I can access the base address register */
 	SMC_SELECT_BANK(1);
 	base_address_register = inw( ioaddr + BASE );
@@ -917,7 +917,7 @@ static int __init smc_probe(struct net_device *dev, int ioaddr)
 	dev->base_addr = ioaddr;
 
 	/*
- 	 . Get the MAC address ( bank 1, regs 4 - 9 )
+	 . Get the MAC address ( bank 1, regs 4 - 9 )
 	*/
 	SMC_SELECT_BANK( 1 );
 	for ( i = 0; i < 6; i += 2 ) {
@@ -938,8 +938,8 @@ static int __init smc_probe(struct net_device *dev, int ioaddr)
 
 	/*
 	 Now, I want to find out more about the chip.  This is sort of
- 	 redundant, but it's cleaner to have it in both, rather than having
- 	 one VERY long probe procedure.
+	 redundant, but it's cleaner to have it in both, rather than having
+	 one VERY long probe procedure.
 	*/
 	SMC_SELECT_BANK(3);
 	revision_register  = inw( ioaddr + REVISION );
@@ -967,7 +967,7 @@ static int __init smc_probe(struct net_device *dev, int ioaddr)
 	/*
 	 . If dev->irq is 0, then the device has to be banged on to see
 	 . what the IRQ is.
- 	 .
+	 .
 	 . This banging doesn't always detect the IRQ, for unknown reasons.
 	 . a workaround is to reset the chip and try again.
 	 .
@@ -978,7 +978,7 @@ static int __init smc_probe(struct net_device *dev, int ioaddr)
 	 .
 	 . Specifying an IRQ is done with the assumption that the user knows
 	 . what (s)he is doing.  No checking is done!!!!
- 	 .
+	 .
 	*/
 	if ( dev->irq < 2 ) {
 		int	trials;
@@ -1070,7 +1070,7 @@ static int smc_open(struct net_device *dev)
 	}
 
 	/*
-  		According to Becker, I have to set the hardware address
+		According to Becker, I have to set the hardware address
 		at this point, because the (l)user can set it with an
 		ioctl.  Easily done...
 	*/
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index cbde83f620a0..813ea941b91a 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -671,19 +671,19 @@ smc_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		status = SMC_GET_INT(lp);
 		if (status & IM_ALLOC_INT) {
 			SMC_ACK_INT(lp, IM_ALLOC_INT);
-  			break;
+			break;
 		}
-   	} while (--poll_count);
+	} while (--poll_count);
 
 	smc_special_unlock(&lp->lock, flags);
 
 	lp->pending_tx_skb = skb;
-   	if (!poll_count) {
+	if (!poll_count) {
 		/* oh well, wait until the chip finds memory later */
 		netif_stop_queue(dev);
 		DBG(2, dev, "TX memory allocation deferred.\n");
 		SMC_ENABLE_INT(lp, IM_ALLOC_INT);
-   	} else {
+	} else {
 		/*
 		 * Allocation succeeded: push packet to the chip's own memory
 		 * immediately.
@@ -1790,7 +1790,7 @@ static int smc_findirq(struct smc_local *lp)
 	SMC_SET_INT_MASK(lp, IM_ALLOC_INT);
 
 	/*
- 	 * Allocate 512 bytes of memory.  Note that the chip was just
+	 * Allocate 512 bytes of memory.  Note that the chip was just
 	 * reset so all the memory is available
 	 */
 	SMC_SET_MMU_CMD(lp, MC_ALLOC | 1);
@@ -1998,8 +1998,8 @@ static int smc_probe(struct net_device *dev, void __iomem *ioaddr,
 
 	/* Grab the IRQ */
 	retval = request_irq(dev->irq, smc_interrupt, irq_flags, dev->name, dev);
-      	if (retval)
-      		goto err_out;
+	if (retval)
+		goto err_out;
 
 #ifdef CONFIG_ARCH_PXA
 #  ifdef SMC_USE_PXA_DMA
diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
index fcbb4bb31408..5eb6bb4f7b6c 100644
--- a/drivers/net/ethernet/socionext/sni_ave.c
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * sni_ave.c - Socionext UniPhier AVE ethernet driver
  * Copyright 2014 Panasonic Corporation
  * Copyright 2015-2017 Socionext Inc.
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 7737e4d0bb9e..ac3c248d4f9b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -66,6 +66,18 @@ config DWMAC_ANARION
 
 	  This selects the Anarion SoC glue layer support for the stmmac driver.
 
+config DWMAC_INGENIC
+	tristate "Ingenic MAC support"
+	default MACH_INGENIC
+	depends on OF && HAS_IOMEM && (MACH_INGENIC || COMPILE_TEST)
+	select MFD_SYSCON
+	help
+	  Support for ethernet controller on Ingenic SoCs.
+
+	  This selects Ingenic SoCs glue layer support for the stmmac
+	  device driver. This driver is used on for the Ingenic SoCs
+	  MAC ethernet controller.
+
 config DWMAC_IPQ806X
 	tristate "QCA IPQ806x DWMAC support"
 	default ARCH_QCOM
@@ -238,6 +250,15 @@ config DWMAC_INTEL
 	  This selects the Intel platform specific bus support for the
 	  stmmac driver. This driver is used for Intel Quark/EHL/TGL.
 
+config DWMAC_LOONGSON
+	tristate "Loongson PCI DWMAC support"
+	default MACH_LOONGSON64
+	depends on STMMAC_ETH && PCI
+	depends on COMMON_CLK
+	help
+	  This selects the LOONGSON PCI bus support for the stmmac driver,
+	  Support for ethernet controller on Loongson-2K1000 SoC and LS7A1000 bridge.
+
 config STMMAC_PCI
 	tristate "STMMAC PCI bus support"
 	depends on STMMAC_ETH && PCI
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index f2e478b884b0..d4e12e9ace4f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -14,6 +14,7 @@ stmmac-$(CONFIG_STMMAC_SELFTESTS) += stmmac_selftests.o
 # Ordering matters. Generic driver must be last.
 obj-$(CONFIG_STMMAC_PLATFORM)	+= stmmac-platform.o
 obj-$(CONFIG_DWMAC_ANARION)	+= dwmac-anarion.o
+obj-$(CONFIG_DWMAC_INGENIC)	+= dwmac-ingenic.o
 obj-$(CONFIG_DWMAC_IPQ806X)	+= dwmac-ipq806x.o
 obj-$(CONFIG_DWMAC_LPC18XX)	+= dwmac-lpc18xx.o
 obj-$(CONFIG_DWMAC_MEDIATEK)	+= dwmac-mediatek.o
@@ -36,4 +37,5 @@ dwmac-altr-socfpga-objs := altr_tse_pcs.o dwmac-socfpga.o
 
 obj-$(CONFIG_STMMAC_PCI)	+= stmmac-pci.o
 obj-$(CONFIG_DWMAC_INTEL)	+= dwmac-intel.o
+obj-$(CONFIG_DWMAC_LOONGSON)	+= dwmac-loongson.o
 stmmac-pci-objs:= stmmac_pci.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 619e3c0760d6..5fecc83f175b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -503,8 +503,7 @@ struct mac_device_info {
 	const struct stmmac_hwtimestamp *ptp;
 	const struct stmmac_tc_ops *tc;
 	const struct stmmac_mmc_ops *mmc;
-	const struct mdio_xpcs_ops *xpcs;
-	struct mdio_xpcs_args xpcs_args;
+	struct dw_xpcs *xpcs;
 	struct mii_regs mii;	/* MII register Addresses */
 	struct mac_link link;
 	void __iomem *pcsr;     /* vpointer to device CSRs */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
new file mode 100644
index 000000000000..9a6d819b84ae
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c
@@ -0,0 +1,398 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * dwmac-ingenic.c - Ingenic SoCs DWMAC specific glue layer
+ *
+ * Copyright (c) 2021 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_net.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/stmmac.h>
+
+#include "stmmac_platform.h"
+
+#define MACPHYC_TXCLK_SEL_MASK		GENMASK(31, 31)
+#define MACPHYC_TXCLK_SEL_OUTPUT	0x1
+#define MACPHYC_TXCLK_SEL_INPUT		0x0
+#define MACPHYC_MODE_SEL_MASK		GENMASK(31, 31)
+#define MACPHYC_MODE_SEL_RMII		0x0
+#define MACPHYC_TX_SEL_MASK			GENMASK(19, 19)
+#define MACPHYC_TX_SEL_ORIGIN		0x0
+#define MACPHYC_TX_SEL_DELAY		0x1
+#define MACPHYC_TX_DELAY_MASK		GENMASK(18, 12)
+#define MACPHYC_RX_SEL_MASK			GENMASK(11, 11)
+#define MACPHYC_RX_SEL_ORIGIN		0x0
+#define MACPHYC_RX_SEL_DELAY		0x1
+#define MACPHYC_RX_DELAY_MASK		GENMASK(10, 4)
+#define MACPHYC_SOFT_RST_MASK		GENMASK(3, 3)
+#define MACPHYC_PHY_INFT_MASK		GENMASK(2, 0)
+#define MACPHYC_PHY_INFT_RMII		0x4
+#define MACPHYC_PHY_INFT_RGMII		0x1
+#define MACPHYC_PHY_INFT_GMII		0x0
+#define MACPHYC_PHY_INFT_MII		0x0
+
+#define MACPHYC_TX_DELAY_PS_MAX		2496
+#define MACPHYC_TX_DELAY_PS_MIN		20
+
+#define MACPHYC_RX_DELAY_PS_MAX		2496
+#define MACPHYC_RX_DELAY_PS_MIN		20
+
+enum ingenic_mac_version {
+	ID_JZ4775,
+	ID_X1000,
+	ID_X1600,
+	ID_X1830,
+	ID_X2000,
+};
+
+struct ingenic_mac {
+	const struct ingenic_soc_info *soc_info;
+	struct device *dev;
+	struct regmap *regmap;
+
+	int rx_delay;
+	int tx_delay;
+};
+
+struct ingenic_soc_info {
+	enum ingenic_mac_version version;
+	u32 mask;
+
+	int (*set_mode)(struct plat_stmmacenet_data *plat_dat);
+};
+
+static int ingenic_mac_init(struct plat_stmmacenet_data *plat_dat)
+{
+	struct ingenic_mac *mac = plat_dat->bsp_priv;
+	int ret;
+
+	if (mac->soc_info->set_mode) {
+		ret = mac->soc_info->set_mode(plat_dat);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int jz4775_mac_set_mode(struct plat_stmmacenet_data *plat_dat)
+{
+	struct ingenic_mac *mac = plat_dat->bsp_priv;
+	unsigned int val;
+
+	switch (plat_dat->interface) {
+	case PHY_INTERFACE_MODE_MII:
+		val = FIELD_PREP(MACPHYC_TXCLK_SEL_MASK, MACPHYC_TXCLK_SEL_INPUT) |
+			  FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_MII);
+		dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_MII\n");
+		break;
+
+	case PHY_INTERFACE_MODE_GMII:
+		val = FIELD_PREP(MACPHYC_TXCLK_SEL_MASK, MACPHYC_TXCLK_SEL_INPUT) |
+			  FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_GMII);
+		dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_GMII\n");
+		break;
+
+	case PHY_INTERFACE_MODE_RMII:
+		val = FIELD_PREP(MACPHYC_TXCLK_SEL_MASK, MACPHYC_TXCLK_SEL_INPUT) |
+			  FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RMII);
+		dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n");
+		break;
+
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+		val = FIELD_PREP(MACPHYC_TXCLK_SEL_MASK, MACPHYC_TXCLK_SEL_INPUT) |
+			  FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RGMII);
+		dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RGMII\n");
+		break;
+
+	default:
+		dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface);
+		return -EINVAL;
+	}
+
+	/* Update MAC PHY control register */
+	return regmap_update_bits(mac->regmap, 0, mac->soc_info->mask, val);
+}
+
+static int x1000_mac_set_mode(struct plat_stmmacenet_data *plat_dat)
+{
+	struct ingenic_mac *mac = plat_dat->bsp_priv;
+
+	switch (plat_dat->interface) {
+	case PHY_INTERFACE_MODE_RMII:
+		dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n");
+		break;
+
+	default:
+		dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface);
+		return -EINVAL;
+	}
+
+	/* Update MAC PHY control register */
+	return regmap_update_bits(mac->regmap, 0, mac->soc_info->mask, 0);
+}
+
+static int x1600_mac_set_mode(struct plat_stmmacenet_data *plat_dat)
+{
+	struct ingenic_mac *mac = plat_dat->bsp_priv;
+	unsigned int val;
+
+	switch (plat_dat->interface) {
+	case PHY_INTERFACE_MODE_RMII:
+		val = FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RMII);
+		dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n");
+		break;
+
+	default:
+		dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface);
+		return -EINVAL;
+	}
+
+	/* Update MAC PHY control register */
+	return regmap_update_bits(mac->regmap, 0, mac->soc_info->mask, val);
+}
+
+static int x1830_mac_set_mode(struct plat_stmmacenet_data *plat_dat)
+{
+	struct ingenic_mac *mac = plat_dat->bsp_priv;
+	unsigned int val;
+
+	switch (plat_dat->interface) {
+	case PHY_INTERFACE_MODE_RMII:
+		val = FIELD_PREP(MACPHYC_MODE_SEL_MASK, MACPHYC_MODE_SEL_RMII) |
+			  FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RMII);
+		dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n");
+		break;
+
+	default:
+		dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface);
+		return -EINVAL;
+	}
+
+	/* Update MAC PHY control register */
+	return regmap_update_bits(mac->regmap, 0, mac->soc_info->mask, val);
+}
+
+static int x2000_mac_set_mode(struct plat_stmmacenet_data *plat_dat)
+{
+	struct ingenic_mac *mac = plat_dat->bsp_priv;
+	unsigned int val;
+
+	switch (plat_dat->interface) {
+	case PHY_INTERFACE_MODE_RMII:
+		val = FIELD_PREP(MACPHYC_TX_SEL_MASK, MACPHYC_TX_SEL_ORIGIN) |
+			  FIELD_PREP(MACPHYC_RX_SEL_MASK, MACPHYC_RX_SEL_ORIGIN) |
+			  FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RMII);
+		dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n");
+		break;
+
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+		val = FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RGMII);
+
+		if (mac->tx_delay == 0)
+			val |= FIELD_PREP(MACPHYC_TX_SEL_MASK, MACPHYC_TX_SEL_ORIGIN);
+		else
+			val |= FIELD_PREP(MACPHYC_TX_SEL_MASK, MACPHYC_TX_SEL_DELAY) |
+				   FIELD_PREP(MACPHYC_TX_DELAY_MASK, (mac->tx_delay + 9750) / 19500 - 1);
+
+		if (mac->rx_delay == 0)
+			val |= FIELD_PREP(MACPHYC_RX_SEL_MASK, MACPHYC_RX_SEL_ORIGIN);
+		else
+			val |= FIELD_PREP(MACPHYC_RX_SEL_MASK, MACPHYC_RX_SEL_DELAY) |
+				   FIELD_PREP(MACPHYC_RX_DELAY_MASK, (mac->rx_delay + 9750) / 19500 - 1);
+
+		dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RGMII\n");
+		break;
+
+	default:
+		dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface);
+		return -EINVAL;
+	}
+
+	/* Update MAC PHY control register */
+	return regmap_update_bits(mac->regmap, 0, mac->soc_info->mask, val);
+}
+
+static int ingenic_mac_probe(struct platform_device *pdev)
+{
+	struct plat_stmmacenet_data *plat_dat;
+	struct stmmac_resources stmmac_res;
+	struct ingenic_mac *mac;
+	const struct ingenic_soc_info *data;
+	u32 tx_delay_ps, rx_delay_ps;
+	int ret;
+
+	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
+	if (ret)
+		return ret;
+
+	plat_dat = stmmac_probe_config_dt(pdev, stmmac_res.mac);
+	if (IS_ERR(plat_dat))
+		return PTR_ERR(plat_dat);
+
+	mac = devm_kzalloc(&pdev->dev, sizeof(*mac), GFP_KERNEL);
+	if (!mac) {
+		ret = -ENOMEM;
+		goto err_remove_config_dt;
+	}
+
+	data = of_device_get_match_data(&pdev->dev);
+	if (!data) {
+		dev_err(&pdev->dev, "No of match data provided\n");
+		ret = -EINVAL;
+		goto err_remove_config_dt;
+	}
+
+	/* Get MAC PHY control register */
+	mac->regmap = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, "mode-reg");
+	if (IS_ERR(mac->regmap)) {
+		dev_err(&pdev->dev, "%s: Failed to get syscon regmap\n", __func__);
+		ret = PTR_ERR(mac->regmap);
+		goto err_remove_config_dt;
+	}
+
+	if (!of_property_read_u32(pdev->dev.of_node, "tx-clk-delay-ps", &tx_delay_ps)) {
+		if (tx_delay_ps >= MACPHYC_TX_DELAY_PS_MIN &&
+			tx_delay_ps <= MACPHYC_TX_DELAY_PS_MAX) {
+			mac->tx_delay = tx_delay_ps * 1000;
+		} else {
+			dev_err(&pdev->dev, "Invalid TX clock delay: %dps\n", tx_delay_ps);
+			return -EINVAL;
+		}
+	}
+
+	if (!of_property_read_u32(pdev->dev.of_node, "rx-clk-delay-ps", &rx_delay_ps)) {
+		if (rx_delay_ps >= MACPHYC_RX_DELAY_PS_MIN &&
+			rx_delay_ps <= MACPHYC_RX_DELAY_PS_MAX) {
+			mac->rx_delay = rx_delay_ps * 1000;
+		} else {
+			dev_err(&pdev->dev, "Invalid RX clock delay: %dps\n", rx_delay_ps);
+			return -EINVAL;
+		}
+	}
+
+	mac->soc_info = data;
+	mac->dev = &pdev->dev;
+
+	plat_dat->bsp_priv = mac;
+
+	ret = ingenic_mac_init(plat_dat);
+	if (ret)
+		goto err_remove_config_dt;
+
+	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
+	if (ret)
+		goto err_remove_config_dt;
+
+	return 0;
+
+err_remove_config_dt:
+	stmmac_remove_config_dt(pdev, plat_dat);
+
+	return ret;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int ingenic_mac_suspend(struct device *dev)
+{
+	int ret;
+
+	ret = stmmac_suspend(dev);
+
+	return ret;
+}
+
+static int ingenic_mac_resume(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	int ret;
+
+	ret = ingenic_mac_init(priv->plat);
+	if (ret)
+		return ret;
+
+	ret = stmmac_resume(dev);
+
+	return ret;
+}
+#endif /* CONFIG_PM_SLEEP */
+
+static SIMPLE_DEV_PM_OPS(ingenic_mac_pm_ops, ingenic_mac_suspend, ingenic_mac_resume);
+
+static struct ingenic_soc_info jz4775_soc_info = {
+	.version = ID_JZ4775,
+	.mask = MACPHYC_TXCLK_SEL_MASK | MACPHYC_SOFT_RST_MASK | MACPHYC_PHY_INFT_MASK,
+
+	.set_mode = jz4775_mac_set_mode,
+};
+
+static struct ingenic_soc_info x1000_soc_info = {
+	.version = ID_X1000,
+	.mask = MACPHYC_SOFT_RST_MASK,
+
+	.set_mode = x1000_mac_set_mode,
+};
+
+static struct ingenic_soc_info x1600_soc_info = {
+	.version = ID_X1600,
+	.mask = MACPHYC_SOFT_RST_MASK | MACPHYC_PHY_INFT_MASK,
+
+	.set_mode = x1600_mac_set_mode,
+};
+
+static struct ingenic_soc_info x1830_soc_info = {
+	.version = ID_X1830,
+	.mask = MACPHYC_MODE_SEL_MASK | MACPHYC_SOFT_RST_MASK | MACPHYC_PHY_INFT_MASK,
+
+	.set_mode = x1830_mac_set_mode,
+};
+
+static struct ingenic_soc_info x2000_soc_info = {
+	.version = ID_X2000,
+	.mask = MACPHYC_TX_SEL_MASK | MACPHYC_TX_DELAY_MASK | MACPHYC_RX_SEL_MASK |
+			MACPHYC_RX_DELAY_MASK | MACPHYC_SOFT_RST_MASK | MACPHYC_PHY_INFT_MASK,
+
+	.set_mode = x2000_mac_set_mode,
+};
+
+static const struct of_device_id ingenic_mac_of_matches[] = {
+	{ .compatible = "ingenic,jz4775-mac", .data = &jz4775_soc_info },
+	{ .compatible = "ingenic,x1000-mac", .data = &x1000_soc_info },
+	{ .compatible = "ingenic,x1600-mac", .data = &x1600_soc_info },
+	{ .compatible = "ingenic,x1830-mac", .data = &x1830_soc_info },
+	{ .compatible = "ingenic,x2000-mac", .data = &x2000_soc_info },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ingenic_mac_of_matches);
+
+static struct platform_driver ingenic_mac_driver = {
+	.probe		= ingenic_mac_probe,
+	.remove		= stmmac_pltfr_remove,
+	.driver		= {
+		.name	= "ingenic-mac",
+		.pm		= pm_ptr(&ingenic_mac_pm_ops),
+		.of_match_table = ingenic_mac_of_matches,
+	},
+};
+module_platform_driver(ingenic_mac_driver);
+
+MODULE_AUTHOR("周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>");
+MODULE_DESCRIPTION("Ingenic SoCs DWMAC specific glue layer");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 80728a4c0e3f..e0a7d2b17921 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -10,22 +10,6 @@
 #include "stmmac.h"
 #include "stmmac_ptp.h"
 
-#define INTEL_MGBE_ADHOC_ADDR	0x15
-#define INTEL_MGBE_XPCS_ADDR	0x16
-
-/* Selection for PTP Clock Freq belongs to PSE & PCH GbE */
-#define PSE_PTP_CLK_FREQ_MASK		(GMAC_GPO0 | GMAC_GPO3)
-#define PSE_PTP_CLK_FREQ_19_2MHZ	(GMAC_GPO0)
-#define PSE_PTP_CLK_FREQ_200MHZ		(GMAC_GPO0 | GMAC_GPO3)
-#define PSE_PTP_CLK_FREQ_256MHZ		(0)
-#define PCH_PTP_CLK_FREQ_MASK		(GMAC_GPO0)
-#define PCH_PTP_CLK_FREQ_19_2MHZ	(GMAC_GPO0)
-#define PCH_PTP_CLK_FREQ_200MHZ		(0)
-
-/* Cross-timestamping defines */
-#define ART_CPUID_LEAF		0x15
-#define EHL_PSE_ART_MHZ		19200000
-
 struct intel_priv_data {
 	int mdio_adhoc_addr;	/* mdio address for serdes & etc */
 	unsigned long crossts_adj;
@@ -102,6 +86,22 @@ static int intel_serdes_powerup(struct net_device *ndev, void *priv_data)
 
 	serdes_phy_addr = intel_priv->mdio_adhoc_addr;
 
+	/* Set the serdes rate and the PCLK rate */
+	data = mdiobus_read(priv->mii, serdes_phy_addr,
+			    SERDES_GCR0);
+
+	data &= ~SERDES_RATE_MASK;
+	data &= ~SERDES_PCLK_MASK;
+
+	if (priv->plat->max_speed == 2500)
+		data |= SERDES_RATE_PCIE_GEN2 << SERDES_RATE_PCIE_SHIFT |
+			SERDES_PCLK_37p5MHZ << SERDES_PCLK_SHIFT;
+	else
+		data |= SERDES_RATE_PCIE_GEN1 << SERDES_RATE_PCIE_SHIFT |
+			SERDES_PCLK_70MHZ << SERDES_PCLK_SHIFT;
+
+	mdiobus_write(priv->mii, serdes_phy_addr, SERDES_GCR0, data);
+
 	/* assert clk_req */
 	data = mdiobus_read(priv->mii, serdes_phy_addr, SERDES_GCR0);
 	data |= SERDES_PLL_CLK;
@@ -230,6 +230,32 @@ static void intel_serdes_powerdown(struct net_device *ndev, void *intel_data)
 	}
 }
 
+static void intel_speed_mode_2500(struct net_device *ndev, void *intel_data)
+{
+	struct intel_priv_data *intel_priv = intel_data;
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	int serdes_phy_addr = 0;
+	u32 data = 0;
+
+	serdes_phy_addr = intel_priv->mdio_adhoc_addr;
+
+	/* Determine the link speed mode: 2.5Gbps/1Gbps */
+	data = mdiobus_read(priv->mii, serdes_phy_addr,
+			    SERDES_GCR);
+
+	if (((data & SERDES_LINK_MODE_MASK) >> SERDES_LINK_MODE_SHIFT) ==
+	    SERDES_LINK_MODE_2G5) {
+		dev_info(priv->device, "Link Speed Mode: 2.5Gbps\n");
+		priv->plat->max_speed = 2500;
+		priv->plat->phy_interface = PHY_INTERFACE_MODE_2500BASEX;
+		priv->plat->mdio_bus_data->xpcs_an_inband = false;
+	} else {
+		priv->plat->max_speed = 1000;
+		priv->plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
+		priv->plat->mdio_bus_data->xpcs_an_inband = true;
+	}
+}
+
 /* Program PTP Clock Frequency for different variant of
  * Intel mGBE that has slightly different GPO mapping
  */
@@ -429,6 +455,17 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 	plat->force_sf_dma_mode = 0;
 	plat->tso_en = 1;
 
+	/* Multiplying factor to the clk_eee_i clock time
+	 * period to make it closer to 100 ns. This value
+	 * should be programmed such that the clk_eee_time_period *
+	 * (MULT_FACT_100NS + 1) should be within 80 ns to 120 ns
+	 * clk_eee frequency is 19.2Mhz
+	 * clk_eee_time_period is 52ns
+	 * 52ns * (1 + 1) = 104ns
+	 * MULT_FACT_100NS = 1
+	 */
+	plat->mult_fact_100ns = 1;
+
 	plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP;
 
 	for (i = 0; i < plat->rx_queues_to_use; i++) {
@@ -557,6 +594,16 @@ static int ehl_common_data(struct pci_dev *pdev,
 	plat->tx_queues_to_use = 8;
 	plat->clk_ptp_rate = 200000000;
 
+	plat->safety_feat_cfg->tsoee = 1;
+	plat->safety_feat_cfg->mrxpee = 1;
+	plat->safety_feat_cfg->mestee = 1;
+	plat->safety_feat_cfg->mrxee = 1;
+	plat->safety_feat_cfg->mtxee = 1;
+	plat->safety_feat_cfg->epsi = 0;
+	plat->safety_feat_cfg->edpp = 0;
+	plat->safety_feat_cfg->prtyen = 0;
+	plat->safety_feat_cfg->tmouten = 0;
+
 	return intel_mgbe_common_data(pdev, plat);
 }
 
@@ -565,7 +612,7 @@ static int ehl_sgmii_data(struct pci_dev *pdev,
 {
 	plat->bus_id = 1;
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
-
+	plat->speed_mode_2500 = intel_speed_mode_2500;
 	plat->serdes_powerup = intel_serdes_powerup;
 	plat->serdes_powerdown = intel_serdes_powerdown;
 
@@ -618,6 +665,7 @@ static int ehl_pse0_sgmii1g_data(struct pci_dev *pdev,
 				 struct plat_stmmacenet_data *plat)
 {
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
+	plat->speed_mode_2500 = intel_speed_mode_2500;
 	plat->serdes_powerup = intel_serdes_powerup;
 	plat->serdes_powerdown = intel_serdes_powerdown;
 	return ehl_pse0_common_data(pdev, plat);
@@ -656,6 +704,7 @@ static int ehl_pse1_sgmii1g_data(struct pci_dev *pdev,
 				 struct plat_stmmacenet_data *plat)
 {
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
+	plat->speed_mode_2500 = intel_speed_mode_2500;
 	plat->serdes_powerup = intel_serdes_powerup;
 	plat->serdes_powerdown = intel_serdes_powerdown;
 	return ehl_pse1_common_data(pdev, plat);
@@ -672,6 +721,16 @@ static int tgl_common_data(struct pci_dev *pdev,
 	plat->tx_queues_to_use = 4;
 	plat->clk_ptp_rate = 200000000;
 
+	plat->safety_feat_cfg->tsoee = 1;
+	plat->safety_feat_cfg->mrxpee = 0;
+	plat->safety_feat_cfg->mestee = 1;
+	plat->safety_feat_cfg->mrxee = 1;
+	plat->safety_feat_cfg->mtxee = 1;
+	plat->safety_feat_cfg->epsi = 0;
+	plat->safety_feat_cfg->edpp = 0;
+	plat->safety_feat_cfg->prtyen = 0;
+	plat->safety_feat_cfg->tmouten = 0;
+
 	return intel_mgbe_common_data(pdev, plat);
 }
 
@@ -680,6 +739,7 @@ static int tgl_sgmii_phy0_data(struct pci_dev *pdev,
 {
 	plat->bus_id = 1;
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
+	plat->speed_mode_2500 = intel_speed_mode_2500;
 	plat->serdes_powerup = intel_serdes_powerup;
 	plat->serdes_powerdown = intel_serdes_powerdown;
 	return tgl_common_data(pdev, plat);
@@ -694,6 +754,7 @@ static int tgl_sgmii_phy1_data(struct pci_dev *pdev,
 {
 	plat->bus_id = 2;
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
+	plat->speed_mode_2500 = intel_speed_mode_2500;
 	plat->serdes_powerup = intel_serdes_powerup;
 	plat->serdes_powerdown = intel_serdes_powerdown;
 	return tgl_common_data(pdev, plat);
@@ -948,6 +1009,12 @@ static int intel_eth_pci_probe(struct pci_dev *pdev,
 	if (!plat->dma_cfg)
 		return -ENOMEM;
 
+	plat->safety_feat_cfg = devm_kzalloc(&pdev->dev,
+					     sizeof(*plat->safety_feat_cfg),
+					     GFP_KERNEL);
+	if (!plat->safety_feat_cfg)
+		return -ENOMEM;
+
 	/* Enable pci device */
 	ret = pcim_enable_device(pdev);
 	if (ret) {
@@ -1020,7 +1087,7 @@ err_alloc_irq:
 /**
  * intel_eth_pci_remove
  *
- * @pdev: platform device pointer
+ * @pdev: pci device pointer
  * Description: this function calls the main to free the net resources
  * and releases the PCI resources.
  */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h
index 542acb8ce467..0a37987478c1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h
@@ -9,6 +9,7 @@
 #define POLL_DELAY_US 8
 
 /* SERDES Register */
+#define SERDES_GCR	0x0	/* Global Conguration */
 #define SERDES_GSR0	0x5	/* Global Status Reg0 */
 #define SERDES_GCR0	0xb	/* Global Configuration Reg0 */
 
@@ -17,8 +18,36 @@
 #define SERDES_PHY_RX_CLK	BIT(1)		/* PSE SGMII PHY rx clk */
 #define SERDES_RST		BIT(2)		/* Serdes Reset */
 #define SERDES_PWR_ST_MASK	GENMASK(6, 4)	/* Serdes Power state*/
+#define SERDES_RATE_MASK	GENMASK(9, 8)
+#define SERDES_PCLK_MASK	GENMASK(14, 12)	/* PCLK rate to PHY */
+#define SERDES_LINK_MODE_MASK	GENMASK(2, 1)
+#define SERDES_LINK_MODE_SHIFT	1
 #define SERDES_PWR_ST_SHIFT	4
 #define SERDES_PWR_ST_P0	0x0
 #define SERDES_PWR_ST_P3	0x3
+#define SERDES_LINK_MODE_2G5	0x3
+#define SERSED_LINK_MODE_1G	0x2
+#define SERDES_PCLK_37p5MHZ	0x0
+#define SERDES_PCLK_70MHZ	0x1
+#define SERDES_RATE_PCIE_GEN1	0x0
+#define SERDES_RATE_PCIE_GEN2	0x1
+#define SERDES_RATE_PCIE_SHIFT	8
+#define SERDES_PCLK_SHIFT	12
+
+#define INTEL_MGBE_ADHOC_ADDR	0x15
+#define INTEL_MGBE_XPCS_ADDR	0x16
+
+/* Cross-timestamping defines */
+#define ART_CPUID_LEAF		0x15
+#define EHL_PSE_ART_MHZ		19200000
+
+/* Selection for PTP Clock Freq belongs to PSE & PCH GbE */
+#define PSE_PTP_CLK_FREQ_MASK		(GMAC_GPO0 | GMAC_GPO3)
+#define PSE_PTP_CLK_FREQ_19_2MHZ	(GMAC_GPO0)
+#define PSE_PTP_CLK_FREQ_200MHZ		(GMAC_GPO0 | GMAC_GPO3)
+#define PSE_PTP_CLK_FREQ_256MHZ		(0)
+#define PCH_PTP_CLK_FREQ_MASK		(GMAC_GPO0)
+#define PCH_PTP_CLK_FREQ_19_2MHZ	(GMAC_GPO0)
+#define PCH_PTP_CLK_FREQ_200MHZ		(0)
 
 #endif /* __DWMAC_INTEL_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
new file mode 100644
index 000000000000..8cd4e2e8ec40
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020, Loongson Corporation
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/pci.h>
+#include <linux/dmi.h>
+#include <linux/device.h>
+#include <linux/of_irq.h>
+#include "stmmac.h"
+
+static int loongson_default_data(struct plat_stmmacenet_data *plat)
+{
+	plat->clk_csr = 2;	/* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */
+	plat->has_gmac = 1;
+	plat->force_sf_dma_mode = 1;
+
+	/* Set default value for multicast hash bins */
+	plat->multicast_filter_bins = HASH_TABLE_SIZE;
+
+	/* Set default value for unicast filter entries */
+	plat->unicast_filter_entries = 1;
+
+	/* 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;
+
+	/* Default to phy auto-detection */
+	plat->phy_addr = -1;
+
+	plat->dma_cfg->pbl = 32;
+	plat->dma_cfg->pblx8 = true;
+
+	plat->multicast_filter_bins = 256;
+	return 0;
+}
+
+static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct plat_stmmacenet_data *plat;
+	struct stmmac_resources res;
+	int ret, i, mdio;
+	struct device_node *np;
+
+	np = dev_of_node(&pdev->dev);
+
+	if (!np) {
+		pr_info("dwmac_loongson_pci: No OF node\n");
+		return -ENODEV;
+	}
+
+	if (!of_device_is_compatible(np, "loongson, pci-gmac")) {
+		pr_info("dwmac_loongson_pci: Incompatible OF node\n");
+		return -ENODEV;
+	}
+
+	plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL);
+	if (!plat)
+		return -ENOMEM;
+
+	if (plat->mdio_node) {
+		dev_err(&pdev->dev, "Found MDIO subnode\n");
+		mdio = true;
+	}
+
+	if (mdio) {
+		plat->mdio_bus_data = devm_kzalloc(&pdev->dev,
+						   sizeof(*plat->mdio_bus_data),
+						   GFP_KERNEL);
+		if (!plat->mdio_bus_data)
+			return -ENOMEM;
+		plat->mdio_bus_data->needs_reset = true;
+	}
+
+	plat->dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*plat->dma_cfg), GFP_KERNEL);
+	if (!plat->dma_cfg)
+		return -ENOMEM;
+
+	/* Enable pci device */
+	ret = pci_enable_device(pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "%s: ERROR: failed to enable device\n", __func__);
+		return ret;
+	}
+
+	/* Get the base address of device */
+	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
+		if (pci_resource_len(pdev, i) == 0)
+			continue;
+		ret = pcim_iomap_regions(pdev, BIT(0), pci_name(pdev));
+		if (ret)
+			return ret;
+		break;
+	}
+
+	plat->bus_id = of_alias_get_id(np, "ethernet");
+	if (plat->bus_id < 0)
+		plat->bus_id = pci_dev_id(pdev);
+
+	plat->phy_interface = device_get_phy_mode(&pdev->dev);
+	if (plat->phy_interface < 0)
+		dev_err(&pdev->dev, "phy_mode not found\n");
+
+	plat->interface = PHY_INTERFACE_MODE_GMII;
+
+	pci_set_master(pdev);
+
+	loongson_default_data(plat);
+	pci_enable_msi(pdev);
+	memset(&res, 0, sizeof(res));
+	res.addr = pcim_iomap_table(pdev)[0];
+
+	res.irq = of_irq_get_byname(np, "macirq");
+	if (res.irq < 0) {
+		dev_err(&pdev->dev, "IRQ macirq not found\n");
+		ret = -ENODEV;
+	}
+
+	res.wol_irq = of_irq_get_byname(np, "eth_wake_irq");
+	if (res.wol_irq < 0) {
+		dev_info(&pdev->dev, "IRQ eth_wake_irq not found, using macirq\n");
+		res.wol_irq = res.irq;
+	}
+
+	res.lpi_irq = of_irq_get_byname(np, "eth_lpi");
+	if (res.lpi_irq < 0) {
+		dev_err(&pdev->dev, "IRQ eth_lpi not found\n");
+		ret = -ENODEV;
+	}
+
+	return stmmac_dvr_probe(&pdev->dev, plat, &res);
+}
+
+static void loongson_dwmac_remove(struct pci_dev *pdev)
+{
+	int i;
+
+	stmmac_dvr_remove(&pdev->dev);
+
+	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
+		if (pci_resource_len(pdev, i) == 0)
+			continue;
+		pcim_iounmap_regions(pdev, BIT(i));
+		break;
+	}
+
+	pci_disable_device(pdev);
+}
+
+static int __maybe_unused loongson_dwmac_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int ret;
+
+	ret = stmmac_suspend(dev);
+	if (ret)
+		return ret;
+
+	ret = pci_save_state(pdev);
+	if (ret)
+		return ret;
+
+	pci_disable_device(pdev);
+	pci_wake_from_d3(pdev, true);
+	return 0;
+}
+
+static int __maybe_unused loongson_dwmac_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int ret;
+
+	pci_restore_state(pdev);
+	pci_set_power_state(pdev, PCI_D0);
+
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	pci_set_master(pdev);
+
+	return stmmac_resume(dev);
+}
+
+static SIMPLE_DEV_PM_OPS(loongson_dwmac_pm_ops, loongson_dwmac_suspend,
+			 loongson_dwmac_resume);
+
+static const struct pci_device_id loongson_dwmac_id_table[] = {
+	{ PCI_VDEVICE(LOONGSON, 0x7a03) },
+	{}
+};
+MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table);
+
+struct pci_driver loongson_dwmac_driver = {
+	.name = "dwmac-loongson-pci",
+	.id_table = loongson_dwmac_id_table,
+	.probe = loongson_dwmac_probe,
+	.remove = loongson_dwmac_remove,
+	.driver = {
+		.pm = &loongson_dwmac_pm_ops,
+	},
+};
+
+module_pci_driver(loongson_dwmac_driver);
+
+MODULE_DESCRIPTION("Loongson DWMAC PCI driver");
+MODULE_AUTHOR("Qing Zhang <zhangqing@loongson.cn>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index 84382fc5cc4d..5c74b6279d69 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -454,7 +454,6 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 	struct stmmac_resources stmmac_res;
 	const struct ethqos_emac_driver_data *data;
 	struct qcom_ethqos *ethqos;
-	struct resource *res;
 	int ret;
 
 	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
@@ -474,8 +473,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 	}
 
 	ethqos->pdev = pdev;
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rgmii");
-	ethqos->rgmii_base = devm_ioremap_resource(&pdev->dev, res);
+	ethqos->rgmii_base = devm_platform_ioremap_resource_byname(pdev, "rgmii");
 	if (IS_ERR(ethqos->rgmii_base)) {
 		ret = PTR_ERR(ethqos->rgmii_base);
 		goto err_mem;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 8d28a536e1bb..280ac0129572 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -33,11 +33,13 @@ struct rk_gmac_ops {
 	void (*set_rgmii_speed)(struct rk_priv_data *bsp_priv, int speed);
 	void (*set_rmii_speed)(struct rk_priv_data *bsp_priv, int speed);
 	void (*integrated_phy_powerup)(struct rk_priv_data *bsp_priv);
+	u32 regs[];
 };
 
 struct rk_priv_data {
 	struct platform_device *pdev;
 	phy_interface_t phy_iface;
+	int id;
 	struct regulator *regulator;
 	bool suspended;
 	const struct rk_gmac_ops *ops;
@@ -482,6 +484,54 @@ static const struct rk_gmac_ops rk3288_ops = {
 	.set_rmii_speed = rk3288_set_rmii_speed,
 };
 
+#define RK3308_GRF_MAC_CON0		0x04a0
+
+/* RK3308_GRF_MAC_CON0 */
+#define RK3308_GMAC_PHY_INTF_SEL_RMII	(GRF_CLR_BIT(2) | GRF_CLR_BIT(3) | \
+					GRF_BIT(4))
+#define RK3308_GMAC_FLOW_CTRL		GRF_BIT(3)
+#define RK3308_GMAC_FLOW_CTRL_CLR	GRF_CLR_BIT(3)
+#define RK3308_GMAC_SPEED_10M		GRF_CLR_BIT(0)
+#define RK3308_GMAC_SPEED_100M		GRF_BIT(0)
+
+static void rk3308_set_to_rmii(struct rk_priv_data *bsp_priv)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "Missing rockchip,grf property\n");
+		return;
+	}
+
+	regmap_write(bsp_priv->grf, RK3308_GRF_MAC_CON0,
+		     RK3308_GMAC_PHY_INTF_SEL_RMII);
+}
+
+static void rk3308_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "Missing rockchip,grf property\n");
+		return;
+	}
+
+	if (speed == 10) {
+		regmap_write(bsp_priv->grf, RK3308_GRF_MAC_CON0,
+			     RK3308_GMAC_SPEED_10M);
+	} else if (speed == 100) {
+		regmap_write(bsp_priv->grf, RK3308_GRF_MAC_CON0,
+			     RK3308_GMAC_SPEED_100M);
+	} else {
+		dev_err(dev, "unknown speed value for RMII! speed=%d", speed);
+	}
+}
+
+static const struct rk_gmac_ops rk3308_ops = {
+	.set_to_rmii = rk3308_set_to_rmii,
+	.set_rmii_speed = rk3308_set_rmii_speed,
+};
+
 #define RK3328_GRF_MAC_CON0	0x0900
 #define RK3328_GRF_MAC_CON1	0x0904
 #define RK3328_GRF_MAC_CON2	0x0908
@@ -948,6 +998,107 @@ static const struct rk_gmac_ops rk3399_ops = {
 	.set_rmii_speed = rk3399_set_rmii_speed,
 };
 
+#define RK3568_GRF_GMAC0_CON0		0x0380
+#define RK3568_GRF_GMAC0_CON1		0x0384
+#define RK3568_GRF_GMAC1_CON0		0x0388
+#define RK3568_GRF_GMAC1_CON1		0x038c
+
+/* RK3568_GRF_GMAC0_CON1 && RK3568_GRF_GMAC1_CON1 */
+#define RK3568_GMAC_PHY_INTF_SEL_RGMII	\
+		(GRF_BIT(4) | GRF_CLR_BIT(5) | GRF_CLR_BIT(6))
+#define RK3568_GMAC_PHY_INTF_SEL_RMII	\
+		(GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | GRF_BIT(6))
+#define RK3568_GMAC_FLOW_CTRL			GRF_BIT(3)
+#define RK3568_GMAC_FLOW_CTRL_CLR		GRF_CLR_BIT(3)
+#define RK3568_GMAC_RXCLK_DLY_ENABLE		GRF_BIT(1)
+#define RK3568_GMAC_RXCLK_DLY_DISABLE		GRF_CLR_BIT(1)
+#define RK3568_GMAC_TXCLK_DLY_ENABLE		GRF_BIT(0)
+#define RK3568_GMAC_TXCLK_DLY_DISABLE		GRF_CLR_BIT(0)
+
+/* RK3568_GRF_GMAC0_CON0 && RK3568_GRF_GMAC1_CON0 */
+#define RK3568_GMAC_CLK_RX_DL_CFG(val)	HIWORD_UPDATE(val, 0x7F, 8)
+#define RK3568_GMAC_CLK_TX_DL_CFG(val)	HIWORD_UPDATE(val, 0x7F, 0)
+
+static void rk3568_set_to_rgmii(struct rk_priv_data *bsp_priv,
+				int tx_delay, int rx_delay)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+	u32 con0, con1;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "Missing rockchip,grf property\n");
+		return;
+	}
+
+	con0 = (bsp_priv->id == 1) ? RK3568_GRF_GMAC1_CON0 :
+				     RK3568_GRF_GMAC0_CON0;
+	con1 = (bsp_priv->id == 1) ? RK3568_GRF_GMAC1_CON1 :
+				     RK3568_GRF_GMAC0_CON1;
+
+	regmap_write(bsp_priv->grf, con0,
+		     RK3568_GMAC_CLK_RX_DL_CFG(rx_delay) |
+		     RK3568_GMAC_CLK_TX_DL_CFG(tx_delay));
+
+	regmap_write(bsp_priv->grf, con1,
+		     RK3568_GMAC_PHY_INTF_SEL_RGMII |
+		     RK3568_GMAC_RXCLK_DLY_ENABLE |
+		     RK3568_GMAC_TXCLK_DLY_ENABLE);
+}
+
+static void rk3568_set_to_rmii(struct rk_priv_data *bsp_priv)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+	u32 con1;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
+		return;
+	}
+
+	con1 = (bsp_priv->id == 1) ? RK3568_GRF_GMAC1_CON1 :
+				     RK3568_GRF_GMAC0_CON1;
+	regmap_write(bsp_priv->grf, con1, RK3568_GMAC_PHY_INTF_SEL_RMII);
+}
+
+static void rk3568_set_gmac_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+	unsigned long rate;
+	int ret;
+
+	switch (speed) {
+	case 10:
+		rate = 2500000;
+		break;
+	case 100:
+		rate = 25000000;
+		break;
+	case 1000:
+		rate = 125000000;
+		break;
+	default:
+		dev_err(dev, "unknown speed value for GMAC speed=%d", speed);
+		return;
+	}
+
+	ret = clk_set_rate(bsp_priv->clk_mac_speed, rate);
+	if (ret)
+		dev_err(dev, "%s: set clk_mac_speed rate %ld failed %d\n",
+			__func__, rate, ret);
+}
+
+static const struct rk_gmac_ops rk3568_ops = {
+	.set_to_rgmii = rk3568_set_to_rgmii,
+	.set_to_rmii = rk3568_set_to_rmii,
+	.set_rgmii_speed = rk3568_set_gmac_speed,
+	.set_rmii_speed = rk3568_set_gmac_speed,
+	.regs = {
+		0xfe2a0000, /* gmac0 */
+		0xfe010000, /* gmac1 */
+		0x0, /* sentinel */
+	},
+};
+
 #define RV1108_GRF_GMAC_CON0		0X0900
 
 /* RV1108_GRF_GMAC_CON0 */
@@ -1216,6 +1367,7 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev,
 {
 	struct rk_priv_data *bsp_priv;
 	struct device *dev = &pdev->dev;
+	struct resource *res;
 	int ret;
 	const char *strings = NULL;
 	int value;
@@ -1227,6 +1379,22 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev,
 	of_get_phy_mode(dev->of_node, &bsp_priv->phy_iface);
 	bsp_priv->ops = ops;
 
+	/* Some SoCs have multiple MAC controllers, which need
+	 * to be distinguished.
+	 */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (res) {
+		int i = 0;
+
+		while (ops->regs[i]) {
+			if (ops->regs[i] == res->start) {
+				bsp_priv->id = i;
+				break;
+			}
+			i++;
+		}
+	}
+
 	bsp_priv->regulator = devm_regulator_get_optional(dev, "phy");
 	if (IS_ERR(bsp_priv->regulator)) {
 		if (PTR_ERR(bsp_priv->regulator) == -EPROBE_DEFER) {
@@ -1294,11 +1462,36 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev,
 	return bsp_priv;
 }
 
+static int rk_gmac_check_ops(struct rk_priv_data *bsp_priv)
+{
+	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:
+		if (!bsp_priv->ops->set_to_rgmii)
+			return -EINVAL;
+		break;
+	case PHY_INTERFACE_MODE_RMII:
+		if (!bsp_priv->ops->set_to_rmii)
+			return -EINVAL;
+		break;
+	default:
+		dev_err(&bsp_priv->pdev->dev,
+			"unsupported interface %d", bsp_priv->phy_iface);
+	}
+	return 0;
+}
+
 static int rk_gmac_powerup(struct rk_priv_data *bsp_priv)
 {
 	int ret;
 	struct device *dev = &bsp_priv->pdev->dev;
 
+	ret = rk_gmac_check_ops(bsp_priv);
+	if (ret)
+		return ret;
+
 	ret = gmac_clk_enable(bsp_priv, true);
 	if (ret)
 		return ret;
@@ -1369,10 +1562,12 @@ static void rk_fix_speed(void *priv, unsigned int speed)
 	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);
+		if (bsp_priv->ops->set_rgmii_speed)
+			bsp_priv->ops->set_rgmii_speed(bsp_priv, speed);
 		break;
 	case PHY_INTERFACE_MODE_RMII:
-		bsp_priv->ops->set_rmii_speed(bsp_priv, speed);
+		if (bsp_priv->ops->set_rmii_speed)
+			bsp_priv->ops->set_rmii_speed(bsp_priv, speed);
 		break;
 	default:
 		dev_err(dev, "unsupported interface %d", bsp_priv->phy_iface);
@@ -1400,7 +1595,11 @@ static int rk_gmac_probe(struct platform_device *pdev)
 	if (IS_ERR(plat_dat))
 		return PTR_ERR(plat_dat);
 
-	plat_dat->has_gmac = true;
+	/* If the stmmac is not already selected as gmac4,
+	 * then make sure we fallback to gmac.
+	 */
+	if (!plat_dat->has_gmac4)
+		plat_dat->has_gmac = true;
 	plat_dat->fix_mac_speed = rk_fix_speed;
 
 	plat_dat->bsp_priv = rk_gmac_setup(pdev, plat_dat, data);
@@ -1477,10 +1676,12 @@ static const struct of_device_id rk_gmac_dwmac_match[] = {
 	{ .compatible = "rockchip,rk3128-gmac", .data = &rk3128_ops },
 	{ .compatible = "rockchip,rk3228-gmac", .data = &rk3228_ops },
 	{ .compatible = "rockchip,rk3288-gmac", .data = &rk3288_ops },
+	{ .compatible = "rockchip,rk3308-gmac", .data = &rk3308_ops },
 	{ .compatible = "rockchip,rk3328-gmac", .data = &rk3328_ops },
 	{ .compatible = "rockchip,rk3366-gmac", .data = &rk3366_ops },
 	{ .compatible = "rockchip,rk3368-gmac", .data = &rk3368_ops },
 	{ .compatible = "rockchip,rk3399-gmac", .data = &rk3399_ops },
+	{ .compatible = "rockchip,rk3568-gmac", .data = &rk3568_ops },
 	{ .compatible = "rockchip,rv1108-gmac", .data = &rv1108_ops },
 	{ }
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index f35c03c9f91e..67ba083eb90c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -1358,6 +1358,7 @@ int dwmac4_setup(struct stmmac_priv *priv)
 	mac->link.speed10 = GMAC_CONFIG_PS;
 	mac->link.speed100 = GMAC_CONFIG_FES | GMAC_CONFIG_PS;
 	mac->link.speed1000 = 0;
+	mac->link.speed2500 = GMAC_CONFIG_FES;
 	mac->link.speed_mask = GMAC_CONFIG_FES | GMAC_CONFIG_PS;
 	mac->mii.addr = GMAC_MDIO_ADDR;
 	mac->mii.data = GMAC_MDIO_DATA;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
index d8c6ff725237..9c2d40f853ed 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
@@ -183,7 +183,8 @@ static void dwmac5_handle_dma_err(struct net_device *ndev,
 			STAT_OFF(dma_errors), stats);
 }
 
-int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp)
+int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp,
+			      struct stmmac_safety_feature_cfg *safety_feat_cfg)
 {
 	u32 value;
 
@@ -193,11 +194,16 @@ int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp)
 	/* 1. Enable Safety Features */
 	value = readl(ioaddr + MTL_ECC_CONTROL);
 	value |= MEEAO; /* MTL ECC Error Addr Status Override */
-	value |= TSOEE; /* TSO ECC */
-	value |= MRXPEE; /* MTL RX Parser ECC */
-	value |= MESTEE; /* MTL EST ECC */
-	value |= MRXEE; /* MTL RX FIFO ECC */
-	value |= MTXEE; /* MTL TX FIFO ECC */
+	if (safety_feat_cfg->tsoee)
+		value |= TSOEE; /* TSO ECC */
+	if (safety_feat_cfg->mrxpee)
+		value |= MRXPEE; /* MTL RX Parser ECC */
+	if (safety_feat_cfg->mestee)
+		value |= MESTEE; /* MTL EST ECC */
+	if (safety_feat_cfg->mrxee)
+		value |= MRXEE; /* MTL RX FIFO ECC */
+	if (safety_feat_cfg->mtxee)
+		value |= MTXEE; /* MTL TX FIFO ECC */
 	writel(value, ioaddr + MTL_ECC_CONTROL);
 
 	/* 2. Enable MTL Safety Interrupts */
@@ -219,13 +225,16 @@ int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp)
 
 	/* 5. Enable Parity and Timeout for FSM */
 	value = readl(ioaddr + MAC_FSM_CONTROL);
-	value |= PRTYEN; /* FSM Parity Feature */
-	value |= TMOUTEN; /* FSM Timeout Feature */
+	if (safety_feat_cfg->prtyen)
+		value |= PRTYEN; /* FSM Parity Feature */
+	if (safety_feat_cfg->tmouten)
+		value |= TMOUTEN; /* FSM Timeout Feature */
 	writel(value, ioaddr + MAC_FSM_CONTROL);
 
 	/* 4. Enable Data Parity Protection */
 	value = readl(ioaddr + MTL_DPP_CONTROL);
-	value |= EDPP;
+	if (safety_feat_cfg->edpp)
+		value |= EDPP;
 	writel(value, ioaddr + MTL_DPP_CONTROL);
 
 	/*
@@ -235,7 +244,8 @@ int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp)
 	if (asp <= 0x2)
 		return 0;
 
-	value |= EPSI;
+	if (safety_feat_cfg->epsi)
+		value |= EPSI;
 	writel(value, ioaddr + MTL_DPP_CONTROL);
 	return 0;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
index 6b2fd37b29ad..53c138d0ff48 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
@@ -137,7 +137,8 @@
 
 #define GMAC_INT_FPE_EN			BIT(17)
 
-int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp);
+int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp,
+			      struct stmmac_safety_feature_cfg *safety_cfg);
 int dwmac5_safety_feat_irq_status(struct net_device *ndev,
 		void __iomem *ioaddr, unsigned int asp,
 		struct stmmac_safety_stats *stats);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index ad4df9bddcf3..c4d78fa93663 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -801,7 +801,9 @@ static void dwxgmac3_handle_dma_err(struct net_device *ndev,
 			   dwxgmac3_dma_errors, STAT_OFF(dma_errors), stats);
 }
 
-static int dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp)
+static int
+dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp,
+			    struct stmmac_safety_feature_cfg *safety_cfg)
 {
 	u32 value;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 6d5e0f2b03ce..6dc1c98ebec8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -348,7 +348,8 @@ struct stmmac_ops {
 	void (*pcs_rane)(void __iomem *ioaddr, bool restart);
 	void (*pcs_get_adv_lp)(void __iomem *ioaddr, struct rgmii_adv *adv);
 	/* Safety Features */
-	int (*safety_feat_config)(void __iomem *ioaddr, unsigned int asp);
+	int (*safety_feat_config)(void __iomem *ioaddr, unsigned int asp,
+				  struct stmmac_safety_feature_cfg *safety_cfg);
 	int (*safety_feat_irq_status)(struct net_device *ndev,
 			void __iomem *ioaddr, unsigned int asp,
 			struct stmmac_safety_stats *stats);
@@ -612,18 +613,6 @@ struct stmmac_mmc_ops {
 #define stmmac_mmc_read(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mmc, read, __args)
 
-/* XPCS callbacks */
-#define stmmac_xpcs_validate(__priv, __args...) \
-	stmmac_do_callback(__priv, xpcs, validate, __args)
-#define stmmac_xpcs_config(__priv, __args...) \
-	stmmac_do_callback(__priv, xpcs, config, __args)
-#define stmmac_xpcs_get_state(__priv, __args...) \
-	stmmac_do_callback(__priv, xpcs, get_state, __args)
-#define stmmac_xpcs_link_up(__priv, __args...) \
-	stmmac_do_callback(__priv, xpcs, link_up, __args)
-#define stmmac_xpcs_probe(__priv, __args...) \
-	stmmac_do_callback(__priv, xpcs, probe, __args)
-
 struct stmmac_regs_off {
 	u32 ptp_off;
 	u32 mmc_off;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index b6cd43eda7ac..e735134e8487 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -75,7 +75,7 @@ struct stmmac_tx_queue {
 	unsigned int cur_tx;
 	unsigned int dirty_tx;
 	dma_addr_t dma_tx_phy;
-	u32 tx_tail_addr;
+	dma_addr_t tx_tail_addr;
 	u32 mss;
 };
 
@@ -311,6 +311,7 @@ enum stmmac_state {
 int stmmac_mdio_unregister(struct net_device *ndev);
 int stmmac_mdio_register(struct net_device *ndev);
 int stmmac_mdio_reset(struct mii_bus *mii);
+int stmmac_xpcs_setup(struct mii_bus *mii);
 void stmmac_set_ethtool_ops(struct net_device *netdev);
 
 void stmmac_ptp_register(struct stmmac_priv *priv);
@@ -338,9 +339,9 @@ static inline bool stmmac_xdp_is_enabled(struct stmmac_priv *priv)
 static inline unsigned int stmmac_rx_offset(struct stmmac_priv *priv)
 {
 	if (stmmac_xdp_is_enabled(priv))
-		return XDP_PACKET_HEADROOM;
+		return XDP_PACKET_HEADROOM + NET_IP_ALIGN;
 
-	return 0;
+	return NET_SKB_PAD + NET_IP_ALIGN;
 }
 
 void stmmac_disable_rx_queue(struct stmmac_priv *priv, u32 queue);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 61b11639ee0c..d0ce608b81c3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -720,6 +720,14 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev,
 		netdev_warn(priv->dev,
 			    "Setting EEE tx-lpi is not supported\n");
 
+	if (priv->hw->xpcs) {
+		ret = xpcs_config_eee(priv->hw->xpcs,
+				      priv->plat->mult_fact_100ns,
+				      edata->eee_enabled);
+		if (ret)
+			return ret;
+	}
+
 	if (!edata->eee_enabled)
 		stmmac_disable_eee_mode(priv);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c87202cbd3d6..16820873b01d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -931,6 +931,11 @@ static void stmmac_validate(struct phylink_config *config,
 	if ((max_speed > 0) && (max_speed < 1000)) {
 		phylink_set(mask, 1000baseT_Full);
 		phylink_set(mask, 1000baseX_Full);
+	} else if (priv->plat->has_gmac4) {
+		if (!max_speed || max_speed >= 2500) {
+			phylink_set(mac_supported, 2500baseT_Full);
+			phylink_set(mac_supported, 2500baseX_Full);
+		}
 	} else if (priv->plat->has_xgmac) {
 		if (!max_speed || (max_speed >= 2500)) {
 			phylink_set(mac_supported, 2500baseT_Full);
@@ -996,29 +1001,14 @@ static void stmmac_validate(struct phylink_config *config,
 	linkmode_andnot(state->advertising, state->advertising, mask);
 
 	/* If PCS is supported, check which modes it supports. */
-	stmmac_xpcs_validate(priv, &priv->hw->xpcs_args, supported, state);
-}
-
-static void stmmac_mac_pcs_get_state(struct phylink_config *config,
-				     struct phylink_link_state *state)
-{
-	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
-
-	state->link = 0;
-	stmmac_xpcs_get_state(priv, &priv->hw->xpcs_args, state);
+	if (priv->hw->xpcs)
+		xpcs_validate(priv->hw->xpcs, supported, state);
 }
 
 static void stmmac_mac_config(struct phylink_config *config, unsigned int mode,
 			      const struct phylink_link_state *state)
 {
-	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
-
-	stmmac_xpcs_config(priv, &priv->hw->xpcs_args, state);
-}
-
-static void stmmac_mac_an_restart(struct phylink_config *config)
-{
-	/* Not Supported */
+	/* Nothing to do, xpcs_config() handles everything */
 }
 
 static void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up)
@@ -1031,8 +1021,8 @@ static void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up)
 	if (is_up && *hs_enable) {
 		stmmac_fpe_send_mpacket(priv, priv->ioaddr, MPACKET_VERIFY);
 	} else {
-		*lo_state = FPE_EVENT_UNKNOWN;
-		*lp_state = FPE_EVENT_UNKNOWN;
+		*lo_state = FPE_STATE_OFF;
+		*lp_state = FPE_STATE_OFF;
 	}
 }
 
@@ -1060,8 +1050,6 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
 	u32 ctrl;
 
-	stmmac_xpcs_link_up(priv, &priv->hw->xpcs_args, speed, interface);
-
 	ctrl = readl(priv->ioaddr + MAC_CTRL_REG);
 	ctrl &= ~priv->hw->link.speed_mask;
 
@@ -1154,9 +1142,7 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 
 static const struct phylink_mac_ops stmmac_phylink_mac_ops = {
 	.validate = stmmac_validate,
-	.mac_pcs_get_state = stmmac_mac_pcs_get_state,
 	.mac_config = stmmac_mac_config,
-	.mac_an_restart = stmmac_mac_an_restart,
 	.mac_link_down = stmmac_mac_link_down,
 	.mac_link_up = stmmac_mac_link_up,
 };
@@ -1233,6 +1219,7 @@ static int stmmac_init_phy(struct net_device *dev)
 
 static int stmmac_phy_setup(struct stmmac_priv *priv)
 {
+	struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data;
 	struct fwnode_handle *fwnode = of_fwnode_handle(priv->plat->phylink_node);
 	int mode = priv->plat->phy_interface;
 	struct phylink *phylink;
@@ -1242,7 +1229,7 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 	priv->phylink_config.pcs_poll = true;
 	if (priv->plat->mdio_bus_data)
 		priv->phylink_config.ovr_an_inband =
-			priv->plat->mdio_bus_data->xpcs_an_inband;
+			mdio_bus_data->xpcs_an_inband;
 
 	if (!fwnode)
 		fwnode = dev_fwnode(priv->device);
@@ -1252,6 +1239,9 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 	if (IS_ERR(phylink))
 		return PTR_ERR(phylink);
 
+	if (priv->hw->xpcs)
+		phylink_set_pcs(phylink, &priv->hw->xpcs->pcs);
+
 	priv->phylink = phylink;
 	return 0;
 }
@@ -3173,7 +3163,8 @@ static void stmmac_safety_feat_configuration(struct stmmac_priv *priv)
 {
 	if (priv->dma_cap.asp) {
 		netdev_info(priv->dev, "Enabling Safety Features\n");
-		stmmac_safety_feat_config(priv, priv->ioaddr, priv->dma_cap.asp);
+		stmmac_safety_feat_config(priv, priv->ioaddr, priv->dma_cap.asp,
+					  priv->plat->safety_feat_cfg);
 	} else {
 		netdev_info(priv->dev, "No Safety Features support found\n");
 	}
@@ -3415,8 +3406,8 @@ static void stmmac_free_irq(struct net_device *dev,
 
 static int stmmac_request_irq_multi_msi(struct net_device *dev)
 {
-	enum request_irq_err irq_err = REQ_IRQ_ERR_NO;
 	struct stmmac_priv *priv = netdev_priv(dev);
+	enum request_irq_err irq_err;
 	cpumask_t cpu_mask;
 	int irq_idx = 0;
 	char *int_name;
@@ -3563,8 +3554,8 @@ irq_error:
 
 static int stmmac_request_irq_single(struct net_device *dev)
 {
-	enum request_irq_err irq_err = REQ_IRQ_ERR_NO;
 	struct stmmac_priv *priv = netdev_priv(dev);
+	enum request_irq_err irq_err;
 	int ret;
 
 	ret = request_irq(dev->irq, stmmac_interrupt,
@@ -3574,7 +3565,7 @@ static int stmmac_request_irq_single(struct net_device *dev)
 			   "%s: ERROR: allocating the IRQ %d (error: %d)\n",
 			   __func__, dev->irq, ret);
 		irq_err = REQ_IRQ_ERR_MAC;
-		return ret;
+		goto irq_error;
 	}
 
 	/* Request the Wake IRQ in case of another line
@@ -3588,7 +3579,7 @@ static int stmmac_request_irq_single(struct net_device *dev)
 				   "%s: ERROR: allocating the WoL IRQ %d (%d)\n",
 				   __func__, priv->wol_irq, ret);
 			irq_err = REQ_IRQ_ERR_WOL;
-			return ret;
+			goto irq_error;
 		}
 	}
 
@@ -3638,6 +3629,7 @@ static int stmmac_request_irq(struct net_device *dev)
 int stmmac_open(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	int mode = priv->plat->phy_interface;
 	int bfsize = 0;
 	u32 chan;
 	int ret;
@@ -3650,7 +3642,8 @@ int stmmac_open(struct net_device *dev)
 
 	if (priv->hw->pcs != STMMAC_PCS_TBI &&
 	    priv->hw->pcs != STMMAC_PCS_RTBI &&
-	    priv->hw->xpcs_args.an_mode != DW_AN_C73) {
+	    (!priv->hw->xpcs ||
+	     xpcs_get_an_mode(priv->hw->xpcs, mode) != DW_AN_C73)) {
 		ret = stmmac_init_phy(dev);
 		if (ret) {
 			netdev_err(priv->dev,
@@ -5138,7 +5131,7 @@ read_again:
 
 		/* Buffer is good. Go on. */
 
-		prefetch(page_address(buf->page));
+		prefetch(page_address(buf->page) + buf->page_offset);
 		if (buf->sec_page)
 			prefetch(page_address(buf->sec_page));
 
@@ -5171,12 +5164,9 @@ read_again:
 			dma_sync_single_for_cpu(priv->device, buf->addr,
 						buf1_len, dma_dir);
 
-			xdp.data = page_address(buf->page) + buf->page_offset;
-			xdp.data_end = xdp.data + buf1_len;
-			xdp.data_hard_start = page_address(buf->page);
-			xdp_set_data_meta_invalid(&xdp);
-			xdp.frame_sz = buf_sz;
-			xdp.rxq = &rx_q->xdp_rxq;
+			xdp_init_buff(&xdp, buf_sz, &rx_q->xdp_rxq);
+			xdp_prepare_buff(&xdp, page_address(buf->page),
+					 buf->page_offset, buf1_len, false);
 
 			pre_len = xdp.data_end - xdp.data_hard_start -
 				  buf->page_offset;
@@ -6854,6 +6844,11 @@ int stmmac_dvr_probe(struct device *device,
 			reset_control_reset(priv->plat->stmmac_rst);
 	}
 
+	ret = reset_control_deassert(priv->plat->stmmac_ahb_rst);
+	if (ret == -ENOTSUPP)
+		dev_err(priv->device, "unable to bring out of ahb reset: %pe\n",
+			ERR_PTR(ret));
+
 	/* Init MAC and get the capabilities */
 	ret = stmmac_hw_init(priv);
 	if (ret)
@@ -7005,6 +7000,15 @@ int stmmac_dvr_probe(struct device *device,
 		}
 	}
 
+	if (priv->plat->speed_mode_2500)
+		priv->plat->speed_mode_2500(ndev, priv->plat->bsp_priv);
+
+	if (priv->plat->mdio_bus_data && priv->plat->mdio_bus_data->has_xpcs) {
+		ret = stmmac_xpcs_setup(priv->mii);
+		if (ret)
+			goto error_xpcs_setup;
+	}
+
 	ret = stmmac_phy_setup(priv);
 	if (ret) {
 		netdev_err(ndev, "failed to setup phy (%d)\n", ret);
@@ -7041,6 +7045,7 @@ error_serdes_powerup:
 	unregister_netdev(ndev);
 error_netdev_register:
 	phylink_destroy(priv->phylink);
+error_xpcs_setup:
 error_phy_setup:
 	if (priv->hw->pcs != STMMAC_PCS_TBI &&
 	    priv->hw->pcs != STMMAC_PCS_RTBI)
@@ -7085,6 +7090,7 @@ int stmmac_dvr_remove(struct device *dev)
 	phylink_destroy(priv->phylink);
 	if (priv->plat->stmmac_rst)
 		reset_control_assert(priv->plat->stmmac_rst);
+	reset_control_assert(priv->plat->stmmac_ahb_rst);
 	pm_runtime_put(dev);
 	pm_runtime_disable(dev);
 	if (priv->hw->pcs != STMMAC_PCS_TBI &&
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index b750074f8f9c..a5d150c5f3d8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -397,6 +397,41 @@ int stmmac_mdio_reset(struct mii_bus *bus)
 	return 0;
 }
 
+int stmmac_xpcs_setup(struct mii_bus *bus)
+{
+	struct net_device *ndev = bus->priv;
+	struct mdio_device *mdiodev;
+	struct stmmac_priv *priv;
+	struct dw_xpcs *xpcs;
+	int mode, addr;
+
+	priv = netdev_priv(ndev);
+	mode = priv->plat->phy_interface;
+
+	/* Try to probe the XPCS by scanning all addresses. */
+	for (addr = 0; addr < PHY_MAX_ADDR; addr++) {
+		mdiodev = mdio_device_create(bus, addr);
+		if (IS_ERR(mdiodev))
+			continue;
+
+		xpcs = xpcs_create(mdiodev, mode);
+		if (IS_ERR_OR_NULL(xpcs)) {
+			mdio_device_free(mdiodev);
+			continue;
+		}
+
+		priv->hw->xpcs = xpcs;
+		break;
+	}
+
+	if (!priv->hw->xpcs) {
+		dev_warn(priv->device, "No xPCS found\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 /**
  * stmmac_mdio_register
  * @ndev: net device structure
@@ -444,14 +479,6 @@ int stmmac_mdio_register(struct net_device *ndev)
 		max_addr = PHY_MAX_ADDR;
 	}
 
-	if (mdio_bus_data->has_xpcs) {
-		priv->hw->xpcs = mdio_xpcs_get_ops();
-		if (!priv->hw->xpcs) {
-			err = -ENODEV;
-			goto bus_register_fail;
-		}
-	}
-
 	if (mdio_bus_data->needs_reset)
 		new_bus->reset = &stmmac_mdio_reset;
 
@@ -503,30 +530,10 @@ int stmmac_mdio_register(struct net_device *ndev)
 		found = 1;
 	}
 
-	/* Try to probe the XPCS by scanning all addresses. */
-	if (priv->hw->xpcs) {
-		struct mdio_xpcs_args *xpcs = &priv->hw->xpcs_args;
-		int ret, mode = priv->plat->phy_interface;
-		max_addr = PHY_MAX_ADDR;
-
-		xpcs->bus = new_bus;
-
-		for (addr = 0; addr < max_addr; addr++) {
-			xpcs->addr = addr;
-
-			ret = stmmac_xpcs_probe(priv, xpcs, mode);
-			if (!ret) {
-				found = 1;
-				break;
-			}
-		}
-	}
-
 	if (!found && !mdio_node) {
 		dev_warn(dev, "No PHY found\n");
-		mdiobus_unregister(new_bus);
-		mdiobus_free(new_bus);
-		return -ENODEV;
+		err = -ENODEV;
+		goto no_phy_found;
 	}
 
 bus_register_done:
@@ -534,6 +541,8 @@ bus_register_done:
 
 	return 0;
 
+no_phy_found:
+	mdiobus_unregister(new_bus);
 bus_register_fail:
 	mdiobus_free(new_bus);
 	return err;
@@ -551,6 +560,11 @@ int stmmac_mdio_unregister(struct net_device *ndev)
 	if (!priv->mii)
 		return 0;
 
+	if (priv->hw->xpcs) {
+		mdio_device_free(priv->hw->xpcs->mdiodev);
+		xpcs_destroy(priv->hw->xpcs);
+	}
+
 	mdiobus_unregister(priv->mii);
 	priv->mii->priv = NULL;
 	mdiobus_free(priv->mii);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index 95e0e4d6f74d..fcf17d8a0494 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -174,6 +174,12 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
 	if (!plat->dma_cfg)
 		return -ENOMEM;
 
+	plat->safety_feat_cfg = devm_kzalloc(&pdev->dev,
+					     sizeof(*plat->safety_feat_cfg),
+					     GFP_KERNEL);
+	if (!plat->safety_feat_cfg)
+		return -ENOMEM;
+
 	/* Enable pci device */
 	ret = pci_enable_device(pdev);
 	if (ret) {
@@ -203,6 +209,16 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
 	res.wol_irq = pdev->irq;
 	res.irq = pdev->irq;
 
+	plat->safety_feat_cfg->tsoee = 1;
+	plat->safety_feat_cfg->mrxpee = 1;
+	plat->safety_feat_cfg->mestee = 1;
+	plat->safety_feat_cfg->mrxee = 1;
+	plat->safety_feat_cfg->mtxee = 1;
+	plat->safety_feat_cfg->epsi = 1;
+	plat->safety_feat_cfg->edpp = 1;
+	plat->safety_feat_cfg->prtyen = 1;
+	plat->safety_feat_cfg->tmouten = 1;
+
 	return stmmac_dvr_probe(&pdev->dev, plat, &res);
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index a696ada013eb..072eff8079d0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -230,8 +230,6 @@ static int stmmac_mtl_setup(struct platform_device *pdev,
 		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;
 
@@ -602,6 +600,13 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 		goto error_hw_init;
 	}
 
+	plat->stmmac_ahb_rst = devm_reset_control_get_optional_shared(
+							&pdev->dev, "ahb");
+	if (IS_ERR(plat->stmmac_ahb_rst)) {
+		ret = plat->stmmac_ahb_rst;
+		goto error_hw_init;
+	}
+
 	return plat;
 
 error_hw_init:
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 4e70efc45458..92dab609d4f8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -573,10 +573,8 @@ static int tc_add_flow(struct stmmac_priv *priv,
 
 	for (i = 0; i < ARRAY_SIZE(tc_flow_parsers); i++) {
 		ret = tc_flow_parsers[i].fn(priv, cls, entry);
-		if (!ret) {
+		if (!ret)
 			entry->in_use = true;
-			continue;
-		}
 	}
 
 	if (!entry->in_use)
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 54f45d8c79a7..981685c88308 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -486,7 +486,7 @@ page_err:
 /* initialize spare pool of rx buffers, but allocate during the open */
 static void cas_spare_init(struct cas *cp)
 {
-  	spin_lock(&cp->rx_inuse_lock);
+	spin_lock(&cp->rx_inuse_lock);
 	INIT_LIST_HEAD(&cp->rx_inuse_list);
 	spin_unlock(&cp->rx_inuse_lock);
 
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index 9790656cf970..cfb9e21b18b7 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -1258,8 +1258,8 @@ static void gem_begin_auto_negotiation(struct gem *gp,
 			&advertising, ep->link_modes.advertising);
 
 	if (gp->phy_type != phy_mii_mdio0 &&
-     	    gp->phy_type != phy_mii_mdio1)
-     	    	goto non_mii;
+	    gp->phy_type != phy_mii_mdio1)
+		goto non_mii;
 
 	/* Setup advertise */
 	if (found_mii_phy(gp))
@@ -1410,7 +1410,7 @@ static int gem_set_link_modes(struct gem *gp)
 
 	if (gp->phy_type == phy_serialink ||
 	    gp->phy_type == phy_serdes) {
- 		u32 pcs_lpa = readl(gp->regs + PCS_MIILP);
+		u32 pcs_lpa = readl(gp->regs + PCS_MIILP);
 
 		if (pcs_lpa & (PCS_MIIADV_SP | PCS_MIIADV_AP))
 			pause = 1;
@@ -1892,7 +1892,7 @@ static void gem_init_mac(struct gem *gp)
 
 static void gem_init_pause_thresholds(struct gem *gp)
 {
-       	u32 cfg;
+	u32 cfg;
 
 	/* Calculate pause thresholds.  Setting the OFF threshold to the
 	 * full RX fifo size effectively disables PAUSE generation which
@@ -1914,15 +1914,15 @@ static void gem_init_pause_thresholds(struct gem *gp)
 	/* Configure the chip "burst" DMA mode & enable some
 	 * HW bug fixes on Apple version
 	 */
-       	cfg  = 0;
-       	if (gp->pdev->vendor == PCI_VENDOR_ID_APPLE)
+	cfg  = 0;
+	if (gp->pdev->vendor == PCI_VENDOR_ID_APPLE)
 		cfg |= GREG_CFG_RONPAULBIT | GREG_CFG_ENBUG2FIX;
 #if !defined(CONFIG_SPARC64) && !defined(CONFIG_ALPHA)
-       	cfg |= GREG_CFG_IBURST;
+	cfg |= GREG_CFG_IBURST;
 #endif
-       	cfg |= ((31 << 1) & GREG_CFG_TXDMALIM);
-       	cfg |= ((31 << 6) & GREG_CFG_RXDMALIM);
-       	writel(cfg, gp->regs + GREG_CFG);
+	cfg |= ((31 << 1) & GREG_CFG_TXDMALIM);
+	cfg |= ((31 << 6) & GREG_CFG_RXDMALIM);
+	writel(cfg, gp->regs + GREG_CFG);
 
 	/* If Infinite Burst didn't stick, then use different
 	 * thresholds (and Apple bug fixes don't exist)
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index 54b53dbdb33c..a2c1a404c52d 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -2286,8 +2286,8 @@ static netdev_tx_t happy_meal_start_xmit(struct sk_buff *skb,
 					 struct net_device *dev)
 {
 	struct happy_meal *hp = netdev_priv(dev);
- 	int entry;
- 	u32 tx_flags;
+	int entry;
+	u32 tx_flags;
 
 	tx_flags = TXFLAG_OWN;
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
@@ -2301,7 +2301,7 @@ static netdev_tx_t happy_meal_start_xmit(struct sk_buff *skb,
 
 	spin_lock_irq(&hp->happy_lock);
 
- 	if (TX_BUFFS_AVAIL(hp) <= (skb_shinfo(skb)->nr_frags + 1)) {
+	if (TX_BUFFS_AVAIL(hp) <= (skb_shinfo(skb)->nr_frags + 1)) {
 		netif_stop_queue(dev);
 		spin_unlock_irq(&hp->happy_lock);
 		printk(KERN_ERR "%s: BUG! Tx Ring full when queue awake!\n",
diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c
index 9caaae79fc95..c30a6e510aa3 100644
--- a/drivers/net/ethernet/ti/am65-cpts.c
+++ b/drivers/net/ethernet/ti/am65-cpts.c
@@ -1037,11 +1037,9 @@ static int am65_cpts_probe(struct platform_device *pdev)
 	struct device_node *node = pdev->dev.of_node;
 	struct device *dev = &pdev->dev;
 	struct am65_cpts *cpts;
-	struct resource *res;
 	void __iomem *base;
 
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cpts");
-	base = devm_ioremap_resource(dev, res);
+	base = devm_platform_ioremap_resource_byname(pdev, "cpts");
 	if (IS_ERR(base))
 		return PTR_ERR(base);
 
diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c
index 6e72ecbe5cf7..e8f38e3f7706 100644
--- a/drivers/net/ethernet/ti/cpsw-phy-sel.c
+++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c
@@ -206,7 +206,6 @@ static const struct of_device_id cpsw_phy_sel_id_table[] = {
 
 static int cpsw_phy_sel_probe(struct platform_device *pdev)
 {
-	struct resource	*res;
 	const struct of_device_id *of_id;
 	struct cpsw_phy_sel_priv *priv;
 
@@ -223,8 +222,7 @@ static int cpsw_phy_sel_probe(struct platform_device *pdev)
 	priv->dev = &pdev->dev;
 	priv->cpsw_phy_sel = of_id->data;
 
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "gmii-sel");
-	priv->gmii_sel = devm_ioremap_resource(&pdev->dev, res);
+	priv->gmii_sel = devm_platform_ioremap_resource_byname(pdev, "gmii-sel");
 	if (IS_ERR(priv->gmii_sel))
 		return PTR_ERR(priv->gmii_sel);
 
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index c0cd7de88316..cbbd0f665796 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -430,8 +430,8 @@ static void cpsw_rx_handler(void *token, int len, int status)
 		cpts_rx_timestamp(cpsw->cpts, skb);
 	skb->protocol = eth_type_trans(skb, ndev);
 
-	/* unmap page as no netstack skb page recycling */
-	page_pool_release_page(pool, page);
+	/* mark skb for recycling */
+	skb_mark_for_recycle(skb, page, pool);
 	netif_receive_skb(skb);
 
 	ndev->stats.rx_bytes += len;
@@ -1532,8 +1532,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	}
 	cpsw->bus_freq_mhz = clk_get_rate(clk) / 1000000;
 
-	ss_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	ss_regs = devm_ioremap_resource(dev, ss_res);
+	ss_regs = devm_platform_get_and_ioremap_resource(pdev, 0, &ss_res);
 	if (IS_ERR(ss_regs))
 		return PTR_ERR(ss_regs);
 	cpsw->regs = ss_regs;
diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index d828f856237a..0c75e0576ee1 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -70,7 +70,7 @@ enum {
 };
 
 /**
- * struct ale_dev_id - The ALE version/SoC specific configuration
+ * struct cpsw_ale_dev_id - The ALE version/SoC specific configuration
  * @dev_id: ALE version/SoC id
  * @features: features supported by ALE
  * @tbl_entries: number of ALE entries
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 69b7a4e0220a..57d279fdcc9f 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -373,8 +373,8 @@ static void cpsw_rx_handler(void *token, int len, int status)
 		cpts_rx_timestamp(cpsw->cpts, skb);
 	skb->protocol = eth_type_trans(skb, ndev);
 
-	/* unmap page as no netstack skb page recycling */
-	page_pool_release_page(pool, page);
+	/* mark skb for recycling */
+	skb_mark_for_recycle(skb, page, pool);
 	netif_receive_skb(skb);
 
 	ndev->stats.rx_bytes += len;
@@ -1883,8 +1883,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	}
 	cpsw->bus_freq_mhz = clk_get_rate(clk) / 1000000;
 
-	ss_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	ss_regs = devm_ioremap_resource(dev, ss_res);
+	ss_regs = devm_platform_get_and_ioremap_resource(pdev, 0, &ss_res);
 	if (IS_ERR(ss_regs)) {
 		ret = PTR_ERR(ss_regs);
 		return ret;
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index f9417b44cae8..c674e34b6839 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -1814,13 +1814,12 @@ static int davinci_emac_probe(struct platform_device *pdev)
 	priv->bus_freq_mhz = (u32)(emac_bus_frequency / 1000000);
 
 	/* Get EMAC platform data */
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->emac_base_phys = res->start + pdata->ctrl_reg_offset;
-	priv->remap_addr = devm_ioremap_resource(&pdev->dev, res);
+	priv->remap_addr = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(priv->remap_addr)) {
 		rc = PTR_ERR(priv->remap_addr);
 		goto no_pdata;
 	}
+	priv->emac_base_phys = res->start + pdata->ctrl_reg_offset;
 
 	res_ctrl = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 	if (res_ctrl) {
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index fecc4d7b00b0..88426b5e410b 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -1897,7 +1897,7 @@ static void velocity_error(struct velocity_info *vptr, int status)
 }
 
 /**
- *	tx_srv		-	transmit interrupt service
+ *	velocity_tx_srv		-	transmit interrupt service
  *	@vptr: Velocity
  *
  *	Scan the queues looking for transmitted packets that
@@ -2453,7 +2453,7 @@ static int velocity_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 }
 
 /**
- *	velocity_get_status	-	statistics callback
+ *	velocity_get_stats	-	statistics callback
  *	@dev: network device
  *
  *	Callback from the network layer to allow driver statistics
@@ -3723,7 +3723,7 @@ static int __init velocity_init_module(void)
 }
 
 /**
- *	velocity_cleanup	-	module unload
+ *	velocity_cleanup_module		-	module unload
  *
  *	When the velocity hardware is unloaded this function is called.
  *	It will clean up the notifiers and the unregister the PCI
diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c
index ec5db481c9cd..811815f8cd3b 100644
--- a/drivers/net/ethernet/wiznet/w5100.c
+++ b/drivers/net/ethernet/wiznet/w5100.c
@@ -263,19 +263,14 @@ static int w5100_writebulk_direct(struct net_device *ndev, u32 addr,
 static int w5100_mmio_init(struct net_device *ndev)
 {
 	struct platform_device *pdev = to_platform_device(ndev->dev.parent);
-	struct w5100_priv *priv = netdev_priv(ndev);
 	struct w5100_mmio_priv *mmio_priv = w5100_mmio_priv(ndev);
-	struct resource *mem;
 
 	spin_lock_init(&mmio_priv->reg_lock);
 
-	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	mmio_priv->base = devm_ioremap_resource(&pdev->dev, mem);
+	mmio_priv->base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
 	if (IS_ERR(mmio_priv->base))
 		return PTR_ERR(mmio_priv->base);
 
-	netdev_info(ndev, "at 0x%llx irq %d\n", (u64)mem->start, priv->irq);
-
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index b508c9453f40..13cd799541aa 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1543,6 +1543,7 @@ static void axienet_validate(struct phylink_config *config,
 	case PHY_INTERFACE_MODE_MII:
 		phylink_set(mask, 100baseT_Full);
 		phylink_set(mask, 10baseT_Full);
+		fallthrough;
 	default:
 		break;
 	}
@@ -1893,8 +1894,7 @@ static int axienet_probe(struct platform_device *pdev)
 		goto cleanup_clk;
 
 	/* Map device registers */
-	ethres = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	lp->regs = devm_ioremap_resource(&pdev->dev, ethres);
+	lp->regs = devm_platform_get_and_ioremap_resource(pdev, 0, &ethres);
 	if (IS_ERR(lp->regs)) {
 		ret = PTR_ERR(lp->regs);
 		goto cleanup_clk;
@@ -2009,9 +2009,7 @@ static int axienet_probe(struct platform_device *pdev)
 		lp->eth_irq = platform_get_irq_optional(pdev, 0);
 	} else {
 		/* Check for these resources directly on the Ethernet node. */
-		struct resource *res = platform_get_resource(pdev,
-							     IORESOURCE_MEM, 1);
-		lp->dma_regs = devm_ioremap_resource(&pdev->dev, res);
+		lp->dma_regs = devm_platform_get_and_ioremap_resource(pdev, 1, NULL);
 		lp->rx_irq = platform_get_irq(pdev, 1);
 		lp->tx_irq = platform_get_irq(pdev, 0);
 		lp->eth_irq = platform_get_irq_optional(pdev, 2);
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index d9d58a7dabee..b06377fe7293 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -1189,9 +1189,8 @@ static int xemaclite_of_probe(struct platform_device *ofdev)
 	}
 
 	dev_info(dev,
-		 "Xilinx EmacLite at 0x%08lX mapped to 0x%08lX, irq=%d\n",
-		 (unsigned long __force)ndev->mem_start,
-		 (unsigned long __force)lp->base_addr, ndev->irq);
+		 "Xilinx EmacLite at 0x%08lX mapped to 0x%p, irq=%d\n",
+		 (unsigned long __force)ndev->mem_start, lp->base_addr, ndev->irq);
 	return 0;
 
 error:
diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c
index 2049d76a0e68..4f6db6f5c272 100644
--- a/drivers/net/ethernet/xircom/xirc2ps_cs.c
+++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c
@@ -1232,7 +1232,7 @@ do_start_xmit(struct sk_buff *skb, struct net_device *dev)
     if (pktlen < ETH_ZLEN)
     {
         if (skb_padto(skb, ETH_ZLEN))
-        	return NETDEV_TX_OK;
+		return NETDEV_TX_OK;
 	pktlen = ETH_ZLEN;
     }
 
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index cb89323855d8..85c66af9e56d 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -1425,7 +1425,6 @@ static int ixp4xx_eth_probe(struct platform_device *pdev)
 	struct device_node *np = dev->of_node;
 	struct eth_plat_info *plat;
 	struct net_device *ndev;
-	struct resource *res;
 	struct port *port;
 	int err;
 
@@ -1482,10 +1481,7 @@ static int ixp4xx_eth_probe(struct platform_device *pdev)
 	port->id = plat->npe;
 
 	/* Get the port resource and remap */
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENODEV;
-	port->regs = devm_ioremap_resource(dev, res);
+	port->regs = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
 	if (IS_ERR(port->regs))
 		return PTR_ERR(port->regs);
 
@@ -1531,8 +1527,8 @@ static int ixp4xx_eth_probe(struct platform_device *pdev)
 		phydev = of_phy_get_and_connect(ndev, np, ixp4xx_adjust_link);
 	} else {
 		phydev = mdiobus_get_phy(mdio_bus, plat->phy);
-		if (IS_ERR(phydev)) {
-			err = PTR_ERR(phydev);
+		if (!phydev) {
+			err = -ENODEV;
 			dev_err(dev, "could not connect phydev (%d)\n", err);
 			goto err_free_mem;
 		}
diff --git a/drivers/net/fddi/skfp/ess.c b/drivers/net/fddi/skfp/ess.c
index 35110c0c00a0..41107338f0c0 100644
--- a/drivers/net/fddi/skfp/ess.c
+++ b/drivers/net/fddi/skfp/ess.c
@@ -379,17 +379,17 @@ static int process_bw_alloc(struct s_smc *smc, long int payload, long int overhe
 	 * if the payload is greater than zero.
 	 * For the SBAPayload and the SBAOverhead we have the following
 	 * unite quations
- 	 *		      _		  _
+	 *		      _		  _
 	 *		     |	     bytes |
 	 *	SBAPayload = | 8000 ------ |
 	 *		     |		s  |
 	 *		      -		  -
- 	 *		       _       _
+	 *		       _       _
 	 *		      |	 bytes	|
 	 *	SBAOverhead = | ------	|
 	 *		      |	 T-NEG	|
 	 *		       -       -
- 	 *
+	 *
 	 * T-NEG is described by the equation:
 	 *
 	 *		     (-) fddiMACT-NEG
diff --git a/drivers/net/fddi/skfp/h/supern_2.h b/drivers/net/fddi/skfp/h/supern_2.h
index 78ae8ea4007c..0bbbd411d000 100644
--- a/drivers/net/fddi/skfp/h/supern_2.h
+++ b/drivers/net/fddi/skfp/h/supern_2.h
@@ -1025,7 +1025,7 @@ struct tx_queue {
 #define	PLC_QELM_A_BIST	0x5b6b		/* BIST signature of QELM Rev. A */
 
 /*
- 	FDDI board recources	
+	FDDI board recources
  */
 
 /*
diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c
index 466622664424..185c8a398681 100644
--- a/drivers/net/fjes/fjes_main.c
+++ b/drivers/net/fjes/fjes_main.c
@@ -90,16 +90,8 @@ static struct platform_driver fjes_driver = {
 };
 
 static struct resource fjes_resource[] = {
-	{
-		.flags = IORESOURCE_MEM,
-		.start = 0,
-		.end = 0,
-	},
-	{
-		.flags = IORESOURCE_IRQ,
-		.start = 0,
-		.end = 0,
-	},
+	DEFINE_RES_MEM(0, 1),
+	DEFINE_RES_IRQ(0)
 };
 
 static bool is_extended_socket_device(struct acpi_device *device)
@@ -1262,6 +1254,10 @@ static int fjes_probe(struct platform_device *plat_dev)
 	adapter->interrupt_watch_enable = false;
 
 	res = platform_get_resource(plat_dev, IORESOURCE_MEM, 0);
+	if (!res) {
+		err = -EINVAL;
+		goto err_free_control_wq;
+	}
 	hw->hw_res.start = res->start;
 	hw->hw_res.size = resource_size(res);
 	hw->hw_res.irq = platform_get_irq(plat_dev, 0);
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 39c00f050fbd..1c9023d47e00 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -436,7 +436,7 @@ static inline void gtp1_push_header(struct sk_buff *skb, struct pdp_ctx *pctx)
 	gtp1->length	= htons(payload_len);
 	gtp1->tid	= htonl(pctx->u.v1.o_tei);
 
-	/* TODO: Suppport for extension header, sequence number and N-PDU.
+	/* TODO: Support for extension header, sequence number and N-PDU.
 	 *	 Update the length field if any of them is available.
 	 */
 }
diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 80f41945709f..a15cc5e50290 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -716,11 +716,11 @@ static int sixpack_ioctl(struct tty_struct *tty, struct file *file,
 		err = 0;
 		break;
 
-	 case SIOCSIFHWADDR: {
-		char addr[AX25_ADDR_LEN];
+	case SIOCSIFHWADDR: {
+			char addr[AX25_ADDR_LEN];
 
-		if (copy_from_user(&addr,
-		                   (void __user *) arg, AX25_ADDR_LEN)) {
+			if (copy_from_user(&addr,
+					   (void __user *)arg, AX25_ADDR_LEN)) {
 				err = -EFAULT;
 				break;
 			}
@@ -728,11 +728,9 @@ static int sixpack_ioctl(struct tty_struct *tty, struct file *file,
 			netif_tx_lock_bh(dev);
 			memcpy(dev->dev_addr, &addr, AX25_ADDR_LEN);
 			netif_tx_unlock_bh(dev);
-
 			err = 0;
 			break;
 		}
-
 	default:
 		err = tty_mode_ioctl(tty, file, cmd, arg);
 	}
diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c
index e4e4981ac1d2..4435a1195194 100644
--- a/drivers/net/hamradio/baycom_epp.c
+++ b/drivers/net/hamradio/baycom_epp.c
@@ -231,7 +231,7 @@ struct baycom_state {
 #if 0
 static inline void append_crc_ccitt(unsigned char *buffer, int len)
 {
- 	unsigned int crc = 0xffff;
+	unsigned int crc = 0xffff;
 
 	for (;len>0;len--)
 		crc = (crc >> 8) ^ crc_ccitt_table[(crc ^ *buffer++) & 0xff];
@@ -390,7 +390,7 @@ static void encode_hdlc(struct baycom_state *bc)
 		for (j = 0; j < 8; j++)
 			if (unlikely(!(notbitstream & (0x1f0 << j)))) {
 				bitstream &= ~(0x100 << j);
- 				bitbuf = (bitbuf & (((2 << j) << numbit) - 1)) |
+				bitbuf = (bitbuf & (((2 << j) << numbit) - 1)) |
 					((bitbuf & ~(((2 << j) << numbit) - 1)) << 1);
 				numbit++;
 				notbitstream = ~bitstream;
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index 1ad6085994b1..0e623c2e8b2d 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -368,7 +368,7 @@ static int bpq_close(struct net_device *dev)
 
 /* ------------------------------------------------------------------------ */
 
-
+#ifdef CONFIG_PROC_FS
 /*
  *	Proc filesystem
  */
@@ -440,7 +440,7 @@ static const struct seq_operations bpq_seqops = {
 	.stop = bpq_seq_stop,
 	.show = bpq_seq_show,
 };
-
+#endif
 /* ------------------------------------------------------------------------ */
 
 static const struct net_device_ops bpq_netdev_ops = {
diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c
index 9e0058154ac3..cbaf1cdde7cb 100644
--- a/drivers/net/hamradio/hdlcdrv.c
+++ b/drivers/net/hamradio/hdlcdrv.c
@@ -74,7 +74,7 @@
 
 static inline void append_crc_ccitt(unsigned char *buffer, int len)
 {
- 	unsigned int crc = crc_ccitt(0xffff, buffer, len) ^ 0xffff;
+	unsigned int crc = crc_ccitt(0xffff, buffer, len) ^ 0xffff;
 	buffer += len;
 	*buffer++ = crc;
 	*buffer++ = crc >> 8;
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index 7685a1721597..b99128669bc8 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -276,7 +276,7 @@ static void ax_bump(struct mkiss *ax)
 			 */
 			*ax->rbuff &= ~0x20;
 		}
- 	}
+	}
 
 	count = ax->rcount;
 
@@ -501,7 +501,7 @@ static void ax_encaps(struct net_device *dev, unsigned char *icp, int len)
 		default:
 			count = kiss_esc(p, ax->xbuff, len);
 		}
-  	}
+	}
 	spin_unlock_bh(&ax->buflock);
 
 	set_bit(TTY_DO_WRITE_WAKEUP, &ax->tty->flags);
@@ -816,7 +816,7 @@ static int mkiss_ioctl(struct tty_struct *tty, struct file *file,
 	dev = ax->dev;
 
 	switch (cmd) {
- 	case SIOCGIFNAME:
+	case SIOCGIFNAME:
 		err = copy_to_user((void __user *) arg, ax->dev->name,
 		                   strlen(ax->dev->name) + 1) ? -EFAULT : 0;
 		break;
diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c
index 4690c6a59054..3f1edd0526a4 100644
--- a/drivers/net/hamradio/scc.c
+++ b/drivers/net/hamradio/scc.c
@@ -1192,18 +1192,18 @@ static void t_tail(struct timer_list *t)
 	unsigned long flags;
 	
 	spin_lock_irqsave(&scc->lock, flags); 
- 	del_timer(&scc->tx_wdog);	
- 	scc_key_trx(scc, TX_OFF);
+	del_timer(&scc->tx_wdog);
+	scc_key_trx(scc, TX_OFF);
 	spin_unlock_irqrestore(&scc->lock, flags);
 
- 	if (scc->stat.tx_state == TXS_TIMEOUT)		/* we had a timeout? */
- 	{
- 		scc->stat.tx_state = TXS_WAIT;
+	if (scc->stat.tx_state == TXS_TIMEOUT)		/* we had a timeout? */
+	{
+		scc->stat.tx_state = TXS_WAIT;
 		scc_start_tx_timer(scc, t_dwait, scc->kiss.mintime*100);
- 		return;
- 	}
- 	
- 	scc->stat.tx_state = TXS_IDLE;
+		return;
+	}
+
+	scc->stat.tx_state = TXS_IDLE;
 	netif_wake_queue(scc->dev);
 }
 
@@ -1580,7 +1580,7 @@ static int scc_net_open(struct net_device *dev)
 {
 	struct scc_channel *scc = (struct scc_channel *) dev->ml_priv;
 
- 	if (!scc->init)
+	if (!scc->init)
 		return -EINVAL;
 
 	scc->tx_buff = NULL;
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index 5ab53e9942f3..d4911041596c 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -668,7 +668,7 @@ static void yam_tx_byte(struct net_device *dev, struct yam_port *yp)
 			}
 			yp->tx_len = skb->len - 1;	/* strip KISS byte */
 			if (yp->tx_len >= YAM_MAX_FRAME || yp->tx_len < 2) {
-        			dev_kfree_skb_any(skb);
+				dev_kfree_skb_any(skb);
 				break;
 			}
 			skb_copy_from_linear_data_offset(skb, 1,
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index ab7022582154..e9258a9f3702 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -16,10 +16,10 @@
 	by Patrick McHardy and then maintained by Andre Correa.
 
 	You need the tc action  mirror or redirect to feed this device
-       	packets.
+	packets.
 
 
-  	Authors:	Jamal Hadi Salim (2005)
+	Authors:	Jamal Hadi Salim (2005)
 
 */
 
diff --git a/drivers/net/ipa/Makefile b/drivers/net/ipa/Makefile
index 1efe1a88104b..bd34fce8f6e6 100644
--- a/drivers/net/ipa/Makefile
+++ b/drivers/net/ipa/Makefile
@@ -7,7 +7,8 @@ ipa-y			:=	ipa_main.o ipa_clock.o ipa_reg.o ipa_mem.o \
 				ipa_table.o ipa_interrupt.o gsi.o gsi_trans.o \
 				ipa_gsi.o ipa_smp2p.o ipa_uc.o \
 				ipa_endpoint.o ipa_cmd.o ipa_modem.o \
-				ipa_resource.o ipa_qmi.o ipa_qmi_msg.o
+				ipa_resource.o ipa_qmi.o ipa_qmi_msg.o \
+				ipa_sysfs.o
 
 ipa-y			+=	ipa_data-v3.5.1.o ipa_data-v4.2.o \
 				ipa_data-v4.5.o ipa_data-v4.9.o \
diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c
index 525cdf28d9ea..af44ca41189e 100644
--- a/drivers/net/ipa/ipa_cmd.c
+++ b/drivers/net/ipa/ipa_cmd.c
@@ -200,41 +200,55 @@ bool ipa_cmd_table_valid(struct ipa *ipa, const struct ipa_mem *mem,
 /* Validate the memory region that holds headers */
 static bool ipa_cmd_header_valid(struct ipa *ipa)
 {
-	const struct ipa_mem *mem = &ipa->mem[IPA_MEM_MODEM_HEADER];
 	struct device *dev = &ipa->pdev->dev;
+	const struct ipa_mem *mem;
 	u32 offset_max;
 	u32 size_max;
+	u32 offset;
 	u32 size;
 
-	/* In ipa_cmd_hdr_init_local_add() we record the offset and size
-	 * of the header table memory area.  Make sure the offset and size
-	 * fit in the fields that need to hold them, and that the entire
-	 * range is within the overall IPA memory range.
+	/* In ipa_cmd_hdr_init_local_add() we record the offset and size of
+	 * the header table memory area in an immediate command.  Make sure
+	 * the offset and size fit in the fields that need to hold them, and
+	 * that the entire range is within the overall IPA memory range.
 	 */
 	offset_max = field_max(HDR_INIT_LOCAL_FLAGS_HDR_ADDR_FMASK);
-	if (mem->offset > offset_max ||
-	    ipa->mem_offset > offset_max - mem->offset) {
+	size_max = field_max(HDR_INIT_LOCAL_FLAGS_TABLE_SIZE_FMASK);
+
+	/* The header memory area contains both the modem and AP header
+	 * regions.  The modem portion defines the address of the region.
+	 */
+	mem = ipa_mem_find(ipa, IPA_MEM_MODEM_HEADER);
+	offset = mem->offset;
+	size = mem->size;
+
+	/* Make sure the offset fits in the IPA command */
+	if (offset > offset_max || ipa->mem_offset > offset_max - offset) {
 		dev_err(dev, "header table region offset too large\n");
 		dev_err(dev, "    (0x%04x + 0x%04x > 0x%04x)\n",
-			ipa->mem_offset, mem->offset, offset_max);
+			ipa->mem_offset, offset, offset_max);
 
 		return false;
 	}
 
-	size_max = field_max(HDR_INIT_LOCAL_FLAGS_TABLE_SIZE_FMASK);
-	size = ipa->mem[IPA_MEM_MODEM_HEADER].size;
-	size += ipa->mem[IPA_MEM_AP_HEADER].size;
+	/* Add the size of the AP portion (if defined) to the combined size */
+	mem = ipa_mem_find(ipa, IPA_MEM_AP_HEADER);
+	if (mem)
+		size += mem->size;
 
+	/* Make sure the combined size fits in the IPA command */
 	if (size > size_max) {
 		dev_err(dev, "header table region size too large\n");
 		dev_err(dev, "    (0x%04x > 0x%08x)\n", size, size_max);
 
 		return false;
 	}
-	if (size > ipa->mem_size || mem->offset > ipa->mem_size - size) {
+
+	/* Make sure the entire combined area fits in IPA memory */
+	if (size > ipa->mem_size || offset > ipa->mem_size - size) {
 		dev_err(dev, "header table region out of range\n");
 		dev_err(dev, "    (0x%04x + 0x%04x > 0x%04x)\n",
-			mem->offset, size, ipa->mem_size);
+			offset, size, ipa->mem_size);
 
 		return false;
 	}
diff --git a/drivers/net/ipa/ipa_data-v3.5.1.c b/drivers/net/ipa/ipa_data-v3.5.1.c
index ead1a82f32f5..af536ef8c120 100644
--- a/drivers/net/ipa/ipa_data-v3.5.1.c
+++ b/drivers/net/ipa/ipa_data-v3.5.1.c
@@ -271,77 +271,92 @@ static const struct ipa_resource_data ipa_resource_data = {
 
 /* IPA-resident memory region data for an SoC having IPA v3.5.1 */
 static const struct ipa_mem ipa_mem_local_data[] = {
-	[IPA_MEM_UC_SHARED] = {
+	{
+		.id		= IPA_MEM_UC_SHARED,
 		.offset		= 0x0000,
 		.size		= 0x0080,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_UC_INFO] = {
+	{
+		.id		= IPA_MEM_UC_INFO,
 		.offset		= 0x0080,
 		.size		= 0x0200,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_V4_FILTER_HASHED] = {
+	{
+		.id		= IPA_MEM_V4_FILTER_HASHED,
 		.offset		= 0x0288,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V4_FILTER] = {
+	{
+		.id		= IPA_MEM_V4_FILTER,
 		.offset		= 0x0308,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_FILTER_HASHED] = {
+	{
+		.id		= IPA_MEM_V6_FILTER_HASHED,
 		.offset		= 0x0388,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_FILTER] = {
+	{
+		.id		= IPA_MEM_V6_FILTER,
 		.offset		= 0x0408,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V4_ROUTE_HASHED] = {
+	{
+		.id		= IPA_MEM_V4_ROUTE_HASHED,
 		.offset		= 0x0488,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V4_ROUTE] = {
+	{
+		.id		= IPA_MEM_V4_ROUTE,
 		.offset		= 0x0508,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_ROUTE_HASHED] = {
+	{
+		.id		= IPA_MEM_V6_ROUTE_HASHED,
 		.offset		= 0x0588,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_ROUTE] = {
+	{
+		.id		= IPA_MEM_V6_ROUTE,
 		.offset		= 0x0608,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_MODEM_HEADER] = {
+	{
+		.id		= IPA_MEM_MODEM_HEADER,
 		.offset		= 0x0688,
 		.size		= 0x0140,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_MODEM_PROC_CTX] = {
+	{
+		.id		= IPA_MEM_MODEM_PROC_CTX,
 		.offset		= 0x07d0,
 		.size		= 0x0200,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_AP_PROC_CTX] = {
+	{
+		.id		= IPA_MEM_AP_PROC_CTX,
 		.offset		= 0x09d0,
 		.size		= 0x0200,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_MODEM] = {
+	{
+		.id		= IPA_MEM_MODEM,
 		.offset		= 0x0bd8,
 		.size		= 0x1024,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_UC_EVENT_RING] = {
+	{
+		.id		= IPA_MEM_UC_EVENT_RING,
 		.offset		= 0x1c00,
 		.size		= 0x0400,
 		.canary_count	= 1,
diff --git a/drivers/net/ipa/ipa_data-v4.11.c b/drivers/net/ipa/ipa_data-v4.11.c
index 05806ceae8b5..9353efbd504f 100644
--- a/drivers/net/ipa/ipa_data-v4.11.c
+++ b/drivers/net/ipa/ipa_data-v4.11.c
@@ -220,112 +220,134 @@ static const struct ipa_resource_data ipa_resource_data = {
 
 /* IPA-resident memory region data for an SoC having IPA v4.11 */
 static const struct ipa_mem ipa_mem_local_data[] = {
-	[IPA_MEM_UC_SHARED] = {
+	{
+		.id		= IPA_MEM_UC_SHARED,
 		.offset		= 0x0000,
 		.size		= 0x0080,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_UC_INFO] = {
+	{
+		.id		= IPA_MEM_UC_INFO,
 		.offset		= 0x0080,
 		.size		= 0x0200,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_V4_FILTER_HASHED] = {
+	{
+		.id		= IPA_MEM_V4_FILTER_HASHED,
 		.offset		= 0x0288,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V4_FILTER] = {
+	{
+		.id		= IPA_MEM_V4_FILTER,
 		.offset		= 0x0308,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_FILTER_HASHED] = {
+	{
+		.id		= IPA_MEM_V6_FILTER_HASHED,
 		.offset		= 0x0388,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_FILTER] = {
+	{
+		.id		= IPA_MEM_V6_FILTER,
 		.offset		= 0x0408,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V4_ROUTE_HASHED] = {
+	{
+		.id		= IPA_MEM_V4_ROUTE_HASHED,
 		.offset		= 0x0488,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V4_ROUTE] = {
+	{
+		.id		= IPA_MEM_V4_ROUTE,
 		.offset		= 0x0508,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_ROUTE_HASHED] = {
+	{
+		.id		= IPA_MEM_V6_ROUTE_HASHED,
 		.offset		= 0x0588,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_ROUTE] = {
+	{
+		.id		= IPA_MEM_V6_ROUTE,
 		.offset		= 0x0608,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_MODEM_HEADER] = {
+	{
+		.id		= IPA_MEM_MODEM_HEADER,
 		.offset		= 0x0688,
 		.size		= 0x0240,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_AP_HEADER] = {
+	{
+		.id		= IPA_MEM_AP_HEADER,
 		.offset		= 0x08c8,
 		.size		= 0x0200,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_MODEM_PROC_CTX] = {
+	{
+		.id		= IPA_MEM_MODEM_PROC_CTX,
 		.offset		= 0x0ad0,
 		.size		= 0x0200,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_AP_PROC_CTX] = {
+	{
+		.id		= IPA_MEM_AP_PROC_CTX,
 		.offset		= 0x0cd0,
 		.size		= 0x0200,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_NAT_TABLE] = {
+	{
+		.id		= IPA_MEM_NAT_TABLE,
 		.offset		= 0x0ee0,
 		.size		= 0x0d00,
 		.canary_count	= 4,
 	},
-	[IPA_MEM_PDN_CONFIG] = {
+	{
+		.id		= IPA_MEM_PDN_CONFIG,
 		.offset		= 0x1be8,
 		.size		= 0x0050,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_STATS_QUOTA_MODEM] = {
+	{
+		.id		= IPA_MEM_STATS_QUOTA_MODEM,
 		.offset		= 0x1c40,
 		.size		= 0x0030,
 		.canary_count	= 4,
 	},
-	[IPA_MEM_STATS_QUOTA_AP] = {
+	{
+		.id		= IPA_MEM_STATS_QUOTA_AP,
 		.offset		= 0x1c70,
 		.size		= 0x0048,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_STATS_TETHERING] = {
+	{
+		.id		= IPA_MEM_STATS_TETHERING,
 		.offset		= 0x1cb8,
 		.size		= 0x0238,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_STATS_DROP] = {
+	{
+		.id		= IPA_MEM_STATS_DROP,
 		.offset		= 0x1ef0,
 		.size		= 0x0020,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_MODEM] = {
+	{
+		.id		= IPA_MEM_MODEM,
 		.offset		= 0x1f18,
 		.size		= 0x100c,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_UC_EVENT_RING] = {
+	{
+		.id		= IPA_MEM_END_MARKER,
 		.offset		= 0x3000,
 		.size		= 0x0000,
 		.canary_count	= 1,
diff --git a/drivers/net/ipa/ipa_data-v4.2.c b/drivers/net/ipa/ipa_data-v4.2.c
index 8744f19c6401..3b09b7baa95f 100644
--- a/drivers/net/ipa/ipa_data-v4.2.c
+++ b/drivers/net/ipa/ipa_data-v4.2.c
@@ -219,92 +219,110 @@ static const struct ipa_resource_data ipa_resource_data = {
 
 /* IPA-resident memory region data for an SoC having IPA v4.2 */
 static const struct ipa_mem ipa_mem_local_data[] = {
-	[IPA_MEM_UC_SHARED] = {
+	{
+		.id		= IPA_MEM_UC_SHARED,
 		.offset		= 0x0000,
 		.size		= 0x0080,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_UC_INFO] = {
+	{
+		.id		= IPA_MEM_UC_INFO,
 		.offset		= 0x0080,
 		.size		= 0x0200,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_V4_FILTER_HASHED] = {
+	{
+		.id		= IPA_MEM_V4_FILTER_HASHED,
 		.offset		= 0x0288,
 		.size		= 0,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V4_FILTER] = {
+	{
+		.id		= IPA_MEM_V4_FILTER,
 		.offset		= 0x0290,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_FILTER_HASHED] = {
+	{
+		.id		= IPA_MEM_V6_FILTER_HASHED,
 		.offset		= 0x0310,
 		.size		= 0,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_FILTER] = {
+	{
+		.id		= IPA_MEM_V6_FILTER,
 		.offset		= 0x0318,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V4_ROUTE_HASHED] = {
+	{
+		.id		= IPA_MEM_V4_ROUTE_HASHED,
 		.offset		= 0x0398,
 		.size		= 0,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V4_ROUTE] = {
+	{
+		.id		= IPA_MEM_V4_ROUTE,
 		.offset		= 0x03a0,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_ROUTE_HASHED] = {
+	{
+		.id		= IPA_MEM_V6_ROUTE_HASHED,
 		.offset		= 0x0420,
 		.size		= 0,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_ROUTE] = {
+	{
+		.id		= IPA_MEM_V6_ROUTE,
 		.offset		= 0x0428,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_MODEM_HEADER] = {
+	{
+		.id		= IPA_MEM_MODEM_HEADER,
 		.offset		= 0x04a8,
 		.size		= 0x0140,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_MODEM_PROC_CTX] = {
+	{
+		.id		= IPA_MEM_MODEM_PROC_CTX,
 		.offset		= 0x05f0,
 		.size		= 0x0200,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_AP_PROC_CTX] = {
+	{
+		.id		= IPA_MEM_AP_PROC_CTX,
 		.offset		= 0x07f0,
 		.size		= 0x0200,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_PDN_CONFIG] = {
+	{
+		.id		= IPA_MEM_PDN_CONFIG,
 		.offset		= 0x09f8,
 		.size		= 0x0050,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_STATS_QUOTA_MODEM] = {
+	{
+		.id		= IPA_MEM_STATS_QUOTA_MODEM,
 		.offset		= 0x0a50,
 		.size		= 0x0060,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_STATS_TETHERING] = {
+	{
+		.id		= IPA_MEM_STATS_TETHERING,
 		.offset		= 0x0ab0,
 		.size		= 0x0140,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_MODEM] = {
+	{
+		.id		= IPA_MEM_MODEM,
 		.offset		= 0x0bf0,
 		.size		= 0x140c,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_UC_EVENT_RING] = {
+	{
+		.id		= IPA_MEM_END_MARKER,
 		.offset		= 0x2000,
 		.size		= 0,
 		.canary_count	= 1,
diff --git a/drivers/net/ipa/ipa_data-v4.5.c b/drivers/net/ipa/ipa_data-v4.5.c
index 5f67a3a909ee..a99b6478fa3a 100644
--- a/drivers/net/ipa/ipa_data-v4.5.c
+++ b/drivers/net/ipa/ipa_data-v4.5.c
@@ -265,117 +265,140 @@ static const struct ipa_resource_data ipa_resource_data = {
 
 /* IPA-resident memory region data for an SoC having IPA v4.5 */
 static const struct ipa_mem ipa_mem_local_data[] = {
-	[IPA_MEM_UC_SHARED] = {
+	{
+		.id		= IPA_MEM_UC_SHARED,
 		.offset		= 0x0000,
 		.size		= 0x0080,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_UC_INFO] = {
+	{
+		.id		= IPA_MEM_UC_INFO,
 		.offset		= 0x0080,
 		.size		= 0x0200,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_V4_FILTER_HASHED] = {
+	{
+		.id		= IPA_MEM_V4_FILTER_HASHED,
 		.offset		= 0x0288,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V4_FILTER] = {
+	{
+		.id		= IPA_MEM_V4_FILTER,
 		.offset		= 0x0308,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_FILTER_HASHED] = {
+	{
+		.id		= IPA_MEM_V6_FILTER_HASHED,
 		.offset		= 0x0388,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_FILTER] = {
+	{
+		.id		= IPA_MEM_V6_FILTER,
 		.offset		= 0x0408,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V4_ROUTE_HASHED] = {
+	{
+		.id		= IPA_MEM_V4_ROUTE_HASHED,
 		.offset		= 0x0488,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V4_ROUTE] = {
+	{
+		.id		= IPA_MEM_V4_ROUTE,
 		.offset		= 0x0508,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_ROUTE_HASHED] = {
+	{
+		.id		= IPA_MEM_V6_ROUTE_HASHED,
 		.offset		= 0x0588,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_ROUTE] = {
+	{
+		.id		= IPA_MEM_V6_ROUTE,
 		.offset		= 0x0608,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_MODEM_HEADER] = {
+	{
+		.id		= IPA_MEM_MODEM_HEADER,
 		.offset		= 0x0688,
 		.size		= 0x0240,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_AP_HEADER] = {
+	{
+		.id		= IPA_MEM_AP_HEADER,
 		.offset		= 0x08c8,
 		.size		= 0x0200,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_MODEM_PROC_CTX] = {
+	{
+		.id		= IPA_MEM_MODEM_PROC_CTX,
 		.offset		= 0x0ad0,
 		.size		= 0x0b20,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_AP_PROC_CTX] = {
+	{
+		.id		= IPA_MEM_AP_PROC_CTX,
 		.offset		= 0x15f0,
 		.size		= 0x0200,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_NAT_TABLE] = {
+	{
+		.id		= IPA_MEM_NAT_TABLE,
 		.offset		= 0x1800,
 		.size		= 0x0d00,
 		.canary_count	= 4,
 	},
-	[IPA_MEM_STATS_QUOTA_MODEM] = {
+	{
+		.id		= IPA_MEM_STATS_QUOTA_MODEM,
 		.offset		= 0x2510,
 		.size		= 0x0030,
 		.canary_count	= 4,
 	},
-	[IPA_MEM_STATS_QUOTA_AP] = {
+	{
+		.id		= IPA_MEM_STATS_QUOTA_AP,
 		.offset		= 0x2540,
 		.size		= 0x0048,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_STATS_TETHERING] = {
+	{
+		.id		= IPA_MEM_STATS_TETHERING,
 		.offset		= 0x2588,
 		.size		= 0x0238,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_STATS_FILTER_ROUTE] = {
+	{
+		.id		= IPA_MEM_STATS_FILTER_ROUTE,
 		.offset		= 0x27c0,
 		.size		= 0x0800,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_STATS_DROP] = {
+	{
+		.id		= IPA_MEM_STATS_DROP,
 		.offset		= 0x2fc0,
 		.size		= 0x0020,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_MODEM] = {
+	{
+		.id		= IPA_MEM_MODEM,
 		.offset		= 0x2fe8,
 		.size		= 0x0800,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_UC_EVENT_RING] = {
+	{
+		.id		= IPA_MEM_UC_EVENT_RING,
 		.offset		= 0x3800,
 		.size		= 0x1000,
 		.canary_count	= 1,
 	},
-	[IPA_MEM_PDN_CONFIG] = {
+	{
+		.id		= IPA_MEM_PDN_CONFIG,
 		.offset		= 0x4800,
 		.size		= 0x0050,
 		.canary_count	= 0,
diff --git a/drivers/net/ipa/ipa_data-v4.9.c b/drivers/net/ipa/ipa_data-v4.9.c
index e41be790f45e..798d43e1eb13 100644
--- a/drivers/net/ipa/ipa_data-v4.9.c
+++ b/drivers/net/ipa/ipa_data-v4.9.c
@@ -263,116 +263,140 @@ static const struct ipa_resource_data ipa_resource_data = {
 
 /* IPA-resident memory region data for an SoC having IPA v4.9 */
 static const struct ipa_mem ipa_mem_local_data[] = {
-	[IPA_MEM_UC_SHARED] = {
+	{
+		.id		= IPA_MEM_UC_SHARED,
 		.offset		= 0x0000,
 		.size		= 0x0080,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_UC_INFO] = {
+	{
+		.id		= IPA_MEM_UC_INFO,
 		.offset		= 0x0080,
 		.size		= 0x0200,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_V4_FILTER_HASHED] = { .offset		= 0x0288,
+	{
+		.id		= IPA_MEM_V4_FILTER_HASHED,
+		.offset		= 0x0288,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V4_FILTER] = {
+	{
+		.id		= IPA_MEM_V4_FILTER,
 		.offset		= 0x0308,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_FILTER_HASHED] = {
+	{
+		.id		= IPA_MEM_V6_FILTER_HASHED,
 		.offset		= 0x0388,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_FILTER] = {
+	{
+		.id		= IPA_MEM_V6_FILTER,
 		.offset		= 0x0408,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V4_ROUTE_HASHED] = {
+	{
+		.id		= IPA_MEM_V4_ROUTE_HASHED,
 		.offset		= 0x0488,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V4_ROUTE] = {
+	{
+		.id		= IPA_MEM_V4_ROUTE,
 		.offset		= 0x0508,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_ROUTE_HASHED] = {
+	{
+		.id		= IPA_MEM_V6_ROUTE_HASHED,
 		.offset		= 0x0588,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_V6_ROUTE] = {
+	{
+		.id		= IPA_MEM_V6_ROUTE,
 		.offset		= 0x0608,
 		.size		= 0x0078,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_MODEM_HEADER] = {
+	{
+		.id		= IPA_MEM_MODEM_HEADER,
 		.offset		= 0x0688,
 		.size		= 0x0240,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_AP_HEADER] = {
+	{
+		.id		= IPA_MEM_AP_HEADER,
 		.offset		= 0x08c8,
 		.size		= 0x0200,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_MODEM_PROC_CTX] = {
+	{
+		.id		= IPA_MEM_MODEM_PROC_CTX,
 		.offset		= 0x0ad0,
 		.size		= 0x0b20,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_AP_PROC_CTX] = {
+	{
+		.id		= IPA_MEM_AP_PROC_CTX,
 		.offset		= 0x15f0,
 		.size		= 0x0200,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_NAT_TABLE] = {
+	{
+		.id		= IPA_MEM_NAT_TABLE,
 		.offset		= 0x1800,
 		.size		= 0x0d00,
 		.canary_count	= 4,
 	},
-	[IPA_MEM_STATS_QUOTA_MODEM] = {
+	{
+		.id		= IPA_MEM_STATS_QUOTA_MODEM,
 		.offset		= 0x2510,
 		.size		= 0x0030,
 		.canary_count	= 4,
 	},
-	[IPA_MEM_STATS_QUOTA_AP] = {
+	{
+		.id		= IPA_MEM_STATS_QUOTA_AP,
 		.offset		= 0x2540,
 		.size		= 0x0048,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_STATS_TETHERING] = {
+	{
+		.id		= IPA_MEM_STATS_TETHERING,
 		.offset		= 0x2588,
 		.size		= 0x0238,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_STATS_FILTER_ROUTE] = {
+	{
+		.id		= IPA_MEM_STATS_FILTER_ROUTE,
 		.offset		= 0x27c0,
 		.size		= 0x0800,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_STATS_DROP] = {
+	{
+		.id		= IPA_MEM_STATS_DROP,
 		.offset		= 0x2fc0,
 		.size		= 0x0020,
 		.canary_count	= 0,
 	},
-	[IPA_MEM_MODEM] = {
+	{
+		.id		= IPA_MEM_MODEM,
 		.offset		= 0x2fe8,
 		.size		= 0x0800,
 		.canary_count	= 2,
 	},
-	[IPA_MEM_UC_EVENT_RING] = {
+	{
+		.id		= IPA_MEM_UC_EVENT_RING,
 		.offset		= 0x3800,
 		.size		= 0x1000,
 		.canary_count	= 1,
 	},
-	[IPA_MEM_PDN_CONFIG] = {
+	{
+		.id		= IPA_MEM_PDN_CONFIG,
 		.offset		= 0x4800,
 		.size		= 0x0050,
 		.canary_count	= 0,
diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c
index ccc99ad983eb..3520852936ed 100644
--- a/drivers/net/ipa/ipa_endpoint.c
+++ b/drivers/net/ipa/ipa_endpoint.c
@@ -75,8 +75,6 @@ struct ipa_status {
 #define IPA_STATUS_FLAGS1_RT_RULE_ID_FMASK	GENMASK(31, 22)
 #define IPA_STATUS_FLAGS2_TAG_FMASK		GENMASK_ULL(63, 16)
 
-#ifdef IPA_VALIDATE
-
 static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count,
 			    const struct ipa_gsi_endpoint_data *all_data,
 			    const struct ipa_gsi_endpoint_data *data)
@@ -88,11 +86,6 @@ static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count,
 	if (ipa_gsi_endpoint_data_empty(data))
 		return true;
 
-	/* IPA v4.5+ uses checksum offload, not yet supported by RMNet */
-	if (ipa->version >= IPA_VERSION_4_5)
-		if (data->endpoint.config.checksum)
-			return false;
-
 	if (!data->toward_ipa) {
 		if (data->endpoint.filter_support) {
 			dev_err(dev, "filtering not supported for "
@@ -230,27 +223,6 @@ static bool ipa_endpoint_data_valid(struct ipa *ipa, u32 count,
 	return true;
 }
 
-#else /* !IPA_VALIDATE */
-
-static bool ipa_endpoint_data_valid(struct ipa *ipa, u32 count,
-				    const struct ipa_gsi_endpoint_data *data)
-{
-	const struct ipa_gsi_endpoint_data *dp = data;
-	enum ipa_endpoint_name name;
-
-	if (ipa->version < IPA_VERSION_4_5)
-		return true;
-
-	/* IPA v4.5+ uses checksum offload, not yet supported by RMNet */
-	for (name = 0; name < count; name++, dp++)
-		if (data->endpoint.config.checksum)
-			return false;
-
-	return true;
-}
-
-#endif /* !IPA_VALIDATE */
-
 /* Allocate a transaction to use on a non-command endpoint */
 static struct gsi_trans *ipa_endpoint_trans_alloc(struct ipa_endpoint *endpoint,
 						  u32 tre_count)
@@ -457,28 +429,34 @@ int ipa_endpoint_modem_exception_reset_all(struct ipa *ipa)
 static void ipa_endpoint_init_cfg(struct ipa_endpoint *endpoint)
 {
 	u32 offset = IPA_REG_ENDP_INIT_CFG_N_OFFSET(endpoint->endpoint_id);
+	enum ipa_cs_offload_en enabled;
 	u32 val = 0;
 
 	/* FRAG_OFFLOAD_EN is 0 */
 	if (endpoint->data->checksum) {
+		enum ipa_version version = endpoint->ipa->version;
+
 		if (endpoint->toward_ipa) {
 			u32 checksum_offset;
 
-			val |= u32_encode_bits(IPA_CS_OFFLOAD_UL,
-					       CS_OFFLOAD_EN_FMASK);
 			/* Checksum header offset is in 4-byte units */
 			checksum_offset = sizeof(struct rmnet_map_header);
 			checksum_offset /= sizeof(u32);
 			val |= u32_encode_bits(checksum_offset,
 					       CS_METADATA_HDR_OFFSET_FMASK);
+
+			enabled = version < IPA_VERSION_4_5
+					? IPA_CS_OFFLOAD_UL
+					: IPA_CS_OFFLOAD_INLINE;
 		} else {
-			val |= u32_encode_bits(IPA_CS_OFFLOAD_DL,
-					       CS_OFFLOAD_EN_FMASK);
+			enabled = version < IPA_VERSION_4_5
+					? IPA_CS_OFFLOAD_DL
+					: IPA_CS_OFFLOAD_INLINE;
 		}
 	} else {
-		val |= u32_encode_bits(IPA_CS_OFFLOAD_NONE,
-				       CS_OFFLOAD_EN_FMASK);
+		enabled = IPA_CS_OFFLOAD_NONE;
 	}
+	val |= u32_encode_bits(enabled, CS_OFFLOAD_EN_FMASK);
 	/* CS_GEN_QMB_MASTER_SEL is 0 */
 
 	iowrite32(val, endpoint->ipa->reg_virt + offset);
@@ -498,6 +476,27 @@ static void ipa_endpoint_init_nat(struct ipa_endpoint *endpoint)
 	iowrite32(val, endpoint->ipa->reg_virt + offset);
 }
 
+static u32
+ipa_qmap_header_size(enum ipa_version version, struct ipa_endpoint *endpoint)
+{
+	u32 header_size = sizeof(struct rmnet_map_header);
+
+	/* Without checksum offload, we just have the MAP header */
+	if (!endpoint->data->checksum)
+		return header_size;
+
+	if (version < IPA_VERSION_4_5) {
+		/* Checksum header inserted for AP TX endpoints only */
+		if (endpoint->toward_ipa)
+			header_size += sizeof(struct rmnet_map_ul_csum_header);
+	} else {
+		/* Checksum header is used in both directions */
+		header_size += sizeof(struct rmnet_map_v5_csum_header);
+	}
+
+	return header_size;
+}
+
 /**
  * ipa_endpoint_init_hdr() - Initialize HDR endpoint configuration register
  * @endpoint:	Endpoint pointer
@@ -526,13 +525,11 @@ static void ipa_endpoint_init_hdr(struct ipa_endpoint *endpoint)
 	u32 val = 0;
 
 	if (endpoint->data->qmap) {
-		size_t header_size = sizeof(struct rmnet_map_header);
 		enum ipa_version version = ipa->version;
+		size_t header_size;
 
-		/* We might supply a checksum header after the QMAP header */
-		if (endpoint->toward_ipa && endpoint->data->checksum)
-			header_size += sizeof(struct rmnet_map_ul_csum_header);
-		val |= ipa_header_size_encoded(version, header_size);
+		header_size = ipa_qmap_header_size(version, endpoint);
+		val = ipa_header_size_encoded(version, header_size);
 
 		/* Define how to fill fields in a received QMAP header */
 		if (!endpoint->toward_ipa) {
diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c
index 9915603ed10b..f82130db32f6 100644
--- a/drivers/net/ipa/ipa_main.c
+++ b/drivers/net/ipa/ipa_main.c
@@ -31,6 +31,7 @@
 #include "ipa_uc.h"
 #include "ipa_interrupt.h"
 #include "gsi_trans.h"
+#include "ipa_sysfs.h"
 
 /**
  * DOC: The IP Accelerator
@@ -529,6 +530,7 @@ static int ipa_firmware_load(struct device *dev)
 	}
 
 	ret = of_address_to_resource(node, 0, &res);
+	of_node_put(node);
 	if (ret) {
 		dev_err(dev, "error %d getting \"memory-region\" resource\n",
 			ret);
@@ -639,6 +641,27 @@ static void ipa_validate_build(void)
 #endif /* IPA_VALIDATE */
 }
 
+static bool ipa_version_valid(enum ipa_version version)
+{
+	switch (version) {
+	case IPA_VERSION_3_0:
+	case IPA_VERSION_3_1:
+	case IPA_VERSION_3_5:
+	case IPA_VERSION_3_5_1:
+	case IPA_VERSION_4_0:
+	case IPA_VERSION_4_1:
+	case IPA_VERSION_4_2:
+	case IPA_VERSION_4_5:
+	case IPA_VERSION_4_7:
+	case IPA_VERSION_4_9:
+	case IPA_VERSION_4_11:
+		return true;
+
+	default:
+		return false;
+	}
+}
+
 /**
  * ipa_probe() - IPA platform driver probe function
  * @pdev:	Platform device pointer
@@ -676,11 +699,15 @@ static int ipa_probe(struct platform_device *pdev)
 	/* Get configuration data early; needed for clock initialization */
 	data = of_device_get_match_data(dev);
 	if (!data) {
-		/* This is really IPA_VALIDATE (should never happen) */
 		dev_err(dev, "matched hardware not supported\n");
 		return -ENODEV;
 	}
 
+	if (!ipa_version_valid(data->version)) {
+		dev_err(dev, "invalid IPA version\n");
+		return -EINVAL;
+	}
+
 	/* If we need Trust Zone, make sure it's available */
 	modem_init = of_property_read_bool(dev->of_node, "modem-init");
 	if (!modem_init)
@@ -881,6 +908,13 @@ static const struct dev_pm_ops ipa_pm_ops = {
 	.resume		= ipa_resume,
 };
 
+static const struct attribute_group *ipa_attribute_groups[] = {
+	&ipa_attribute_group,
+	&ipa_feature_attribute_group,
+	&ipa_modem_attribute_group,
+	NULL,
+};
+
 static struct platform_driver ipa_driver = {
 	.probe		= ipa_probe,
 	.remove		= ipa_remove,
@@ -889,6 +923,7 @@ static struct platform_driver ipa_driver = {
 		.name		= "ipa",
 		.pm		= &ipa_pm_ops,
 		.of_match_table	= ipa_match,
+		.dev_groups	= ipa_attribute_groups,
 	},
 };
 
diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c
index 1624125e7459..4337b0920d3d 100644
--- a/drivers/net/ipa/ipa_mem.c
+++ b/drivers/net/ipa/ipa_mem.c
@@ -26,11 +26,26 @@
 /* SMEM host id representing the modem. */
 #define QCOM_SMEM_HOST_MODEM	1
 
+const struct ipa_mem *ipa_mem_find(struct ipa *ipa, enum ipa_mem_id mem_id)
+{
+	u32 i;
+
+	for (i = 0; i < ipa->mem_count; i++) {
+		const struct ipa_mem *mem = &ipa->mem[i];
+
+		if (mem->id == mem_id)
+			return mem;
+	}
+
+	return NULL;
+}
+
 /* Add an immediate command to a transaction that zeroes a memory region */
 static void
-ipa_mem_zero_region_add(struct gsi_trans *trans, const struct ipa_mem *mem)
+ipa_mem_zero_region_add(struct gsi_trans *trans, enum ipa_mem_id mem_id)
 {
 	struct ipa *ipa = container_of(trans->gsi, struct ipa, gsi);
+	const struct ipa_mem *mem = ipa_mem_find(ipa, mem_id);
 	dma_addr_t addr = ipa->zero_addr;
 
 	if (!mem->size)
@@ -60,6 +75,7 @@ ipa_mem_zero_region_add(struct gsi_trans *trans, const struct ipa_mem *mem)
 int ipa_mem_setup(struct ipa *ipa)
 {
 	dma_addr_t addr = ipa->zero_addr;
+	const struct ipa_mem *mem;
 	struct gsi_trans *trans;
 	u32 offset;
 	u16 size;
@@ -74,39 +90,136 @@ int ipa_mem_setup(struct ipa *ipa)
 		return -EBUSY;
 	}
 
-	/* Initialize IPA-local header memory.  The modem and AP header
-	 * regions are contiguous, and initialized together.
+	/* Initialize IPA-local header memory.  The AP header region, if
+	 * present, is contiguous with and follows the modem header region,
+	 * and they are initialized together.
 	 */
-	offset = ipa->mem[IPA_MEM_MODEM_HEADER].offset;
-	size = ipa->mem[IPA_MEM_MODEM_HEADER].size;
-	size += ipa->mem[IPA_MEM_AP_HEADER].size;
+	mem = ipa_mem_find(ipa, IPA_MEM_MODEM_HEADER);
+	offset = mem->offset;
+	size = mem->size;
+	mem = ipa_mem_find(ipa, IPA_MEM_AP_HEADER);
+	if (mem)
+		size += mem->size;
 
 	ipa_cmd_hdr_init_local_add(trans, offset, size, addr);
 
-	ipa_mem_zero_region_add(trans, &ipa->mem[IPA_MEM_MODEM_PROC_CTX]);
-
-	ipa_mem_zero_region_add(trans, &ipa->mem[IPA_MEM_AP_PROC_CTX]);
-
-	ipa_mem_zero_region_add(trans, &ipa->mem[IPA_MEM_MODEM]);
+	ipa_mem_zero_region_add(trans, IPA_MEM_MODEM_PROC_CTX);
+	ipa_mem_zero_region_add(trans, IPA_MEM_AP_PROC_CTX);
+	ipa_mem_zero_region_add(trans, IPA_MEM_MODEM);
 
 	gsi_trans_commit_wait(trans);
 
 	/* Tell the hardware where the processing context area is located */
-	offset = ipa->mem_offset + ipa->mem[IPA_MEM_MODEM_PROC_CTX].offset;
+	mem = ipa_mem_find(ipa, IPA_MEM_MODEM_PROC_CTX);
+	offset = ipa->mem_offset + mem->offset;
 	val = proc_cntxt_base_addr_encoded(ipa->version, offset);
 	iowrite32(val, ipa->reg_virt + IPA_REG_LOCAL_PKT_PROC_CNTXT_OFFSET);
 
 	return 0;
 }
 
-#ifdef IPA_VALIDATE
+/* Is the given memory region ID is valid for the current IPA version? */
+static bool ipa_mem_id_valid(struct ipa *ipa, enum ipa_mem_id mem_id)
+{
+	enum ipa_version version = ipa->version;
+
+	switch (mem_id) {
+	case IPA_MEM_UC_SHARED:
+	case IPA_MEM_UC_INFO:
+	case IPA_MEM_V4_FILTER_HASHED:
+	case IPA_MEM_V4_FILTER:
+	case IPA_MEM_V6_FILTER_HASHED:
+	case IPA_MEM_V6_FILTER:
+	case IPA_MEM_V4_ROUTE_HASHED:
+	case IPA_MEM_V4_ROUTE:
+	case IPA_MEM_V6_ROUTE_HASHED:
+	case IPA_MEM_V6_ROUTE:
+	case IPA_MEM_MODEM_HEADER:
+	case IPA_MEM_AP_HEADER:
+	case IPA_MEM_MODEM_PROC_CTX:
+	case IPA_MEM_AP_PROC_CTX:
+	case IPA_MEM_MODEM:
+	case IPA_MEM_UC_EVENT_RING:
+	case IPA_MEM_PDN_CONFIG:
+	case IPA_MEM_STATS_QUOTA_MODEM:
+	case IPA_MEM_STATS_QUOTA_AP:
+	case IPA_MEM_END_MARKER:	/* pseudo region */
+		break;
+
+	case IPA_MEM_STATS_TETHERING:
+	case IPA_MEM_STATS_DROP:
+		if (version < IPA_VERSION_4_0)
+			return false;
+		break;
+
+	case IPA_MEM_STATS_V4_FILTER:
+	case IPA_MEM_STATS_V6_FILTER:
+	case IPA_MEM_STATS_V4_ROUTE:
+	case IPA_MEM_STATS_V6_ROUTE:
+		if (version < IPA_VERSION_4_0 || version > IPA_VERSION_4_2)
+			return false;
+		break;
+
+	case IPA_MEM_NAT_TABLE:
+	case IPA_MEM_STATS_FILTER_ROUTE:
+		if (version < IPA_VERSION_4_5)
+			return false;
+		break;
+
+	default:
+		return false;
+	}
+
+	return true;
+}
 
-static bool ipa_mem_valid(struct ipa *ipa, enum ipa_mem_id mem_id)
+/* Must the given memory region be present in the configuration? */
+static bool ipa_mem_id_required(struct ipa *ipa, enum ipa_mem_id mem_id)
+{
+	switch (mem_id) {
+	case IPA_MEM_UC_SHARED:
+	case IPA_MEM_UC_INFO:
+	case IPA_MEM_V4_FILTER_HASHED:
+	case IPA_MEM_V4_FILTER:
+	case IPA_MEM_V6_FILTER_HASHED:
+	case IPA_MEM_V6_FILTER:
+	case IPA_MEM_V4_ROUTE_HASHED:
+	case IPA_MEM_V4_ROUTE:
+	case IPA_MEM_V6_ROUTE_HASHED:
+	case IPA_MEM_V6_ROUTE:
+	case IPA_MEM_MODEM_HEADER:
+	case IPA_MEM_MODEM_PROC_CTX:
+	case IPA_MEM_AP_PROC_CTX:
+	case IPA_MEM_MODEM:
+		return true;
+
+	case IPA_MEM_PDN_CONFIG:
+	case IPA_MEM_STATS_QUOTA_MODEM:
+	case IPA_MEM_STATS_TETHERING:
+		return ipa->version >= IPA_VERSION_4_0;
+
+	default:
+		return false;		/* Anything else is optional */
+	}
+}
+
+static bool ipa_mem_valid_one(struct ipa *ipa, const struct ipa_mem *mem)
 {
-	const struct ipa_mem *mem = &ipa->mem[mem_id];
 	struct device *dev = &ipa->pdev->dev;
+	enum ipa_mem_id mem_id = mem->id;
 	u16 size_multiple;
 
+	/* Make sure the memory region is valid for this version of IPA */
+	if (!ipa_mem_id_valid(ipa, mem_id)) {
+		dev_err(dev, "region id %u not valid\n", mem_id);
+		return false;
+	}
+
+	if (!mem->size && !mem->canary_count) {
+		dev_err(dev, "empty memory region %u\n", mem_id);
+		return false;
+	}
+
 	/* Other than modem memory, sizes must be a multiple of 8 */
 	size_multiple = mem_id == IPA_MEM_MODEM ? 4 : 8;
 	if (mem->size % size_multiple)
@@ -117,23 +230,74 @@ static bool ipa_mem_valid(struct ipa *ipa, enum ipa_mem_id mem_id)
 	else if (mem->offset < mem->canary_count * sizeof(__le32))
 		dev_err(dev, "region %u offset too small for %hu canaries\n",
 			mem_id, mem->canary_count);
-	else if (mem->offset + mem->size > ipa->mem_size)
-		dev_err(dev, "region %u ends beyond memory limit (0x%08x)\n",
-			mem_id, ipa->mem_size);
+	else if (mem_id == IPA_MEM_END_MARKER && mem->size)
+		dev_err(dev, "non-zero end marker region size\n");
 	else
 		return true;
 
 	return false;
 }
 
-#else /* !IPA_VALIDATE */
-
-static bool ipa_mem_valid(struct ipa *ipa, enum ipa_mem_id mem_id)
+/* Verify each defined memory region is valid. */
+static bool ipa_mem_valid(struct ipa *ipa, const struct ipa_mem_data *mem_data)
 {
+	DECLARE_BITMAP(regions, IPA_MEM_COUNT) = { };
+	struct device *dev = &ipa->pdev->dev;
+	enum ipa_mem_id mem_id;
+	u32 i;
+
+	if (mem_data->local_count > IPA_MEM_COUNT) {
+		dev_err(dev, "too many memory regions (%u > %u)\n",
+			mem_data->local_count, IPA_MEM_COUNT);
+		return false;
+	}
+
+	for (i = 0; i < mem_data->local_count; i++) {
+		const struct ipa_mem *mem = &mem_data->local[i];
+
+		if (__test_and_set_bit(mem->id, regions)) {
+			dev_err(dev, "duplicate memory region %u\n", mem->id);
+			return false;
+		}
+
+		/* Defined regions have non-zero size and/or canary count */
+		if (!ipa_mem_valid_one(ipa, mem))
+			return false;
+	}
+
+	/* Now see if any required regions are not defined */
+	for (mem_id = find_first_zero_bit(regions, IPA_MEM_COUNT);
+	     mem_id < IPA_MEM_COUNT;
+	     mem_id = find_next_zero_bit(regions, IPA_MEM_COUNT, mem_id + 1)) {
+		if (ipa_mem_id_required(ipa, mem_id))
+			dev_err(dev, "required memory region %u missing\n",
+				mem_id);
+	}
+
 	return true;
 }
 
-#endif /*! IPA_VALIDATE */
+/* Do all memory regions fit within the IPA local memory? */
+static bool ipa_mem_size_valid(struct ipa *ipa)
+{
+	struct device *dev = &ipa->pdev->dev;
+	u32 limit = ipa->mem_size;
+	u32 i;
+
+	for (i = 0; i < ipa->mem_count; i++) {
+		const struct ipa_mem *mem = &ipa->mem[i];
+
+		if (mem->offset + mem->size <= limit)
+			continue;
+
+		dev_err(dev, "region %u ends beyond memory limit (0x%08x)\n",
+			mem->id, limit);
+
+		return false;
+	}
+
+	return true;
+}
 
 /**
  * ipa_mem_config() - Configure IPA shared memory
@@ -144,11 +308,12 @@ static bool ipa_mem_valid(struct ipa *ipa, enum ipa_mem_id mem_id)
 int ipa_mem_config(struct ipa *ipa)
 {
 	struct device *dev = &ipa->pdev->dev;
-	enum ipa_mem_id mem_id;
+	const struct ipa_mem *mem;
 	dma_addr_t addr;
 	u32 mem_size;
 	void *virt;
 	u32 val;
+	u32 i;
 
 	/* Check the advertised location and size of the shared memory area */
 	val = ioread32(ipa->reg_virt + IPA_REG_SHARED_MEM_SIZE_OFFSET);
@@ -168,6 +333,10 @@ int ipa_mem_config(struct ipa *ipa)
 			mem_size);
 	}
 
+	/* We know our memory size; make sure regions are all in range */
+	if (!ipa_mem_size_valid(ipa))
+		return -EINVAL;
+
 	/* Prealloc DMA memory for zeroing regions */
 	virt = dma_alloc_coherent(dev, IPA_MEM_MAX, &addr, GFP_KERNEL);
 	if (!virt)
@@ -176,29 +345,18 @@ int ipa_mem_config(struct ipa *ipa)
 	ipa->zero_virt = virt;
 	ipa->zero_size = IPA_MEM_MAX;
 
-	/* Verify each defined memory region is valid, and if indicated
-	 * for the region, write "canary" values in the space prior to
-	 * the region's base address.
+	/* For each defined region, write "canary" values in the
+	 * space prior to the region's base address if indicated.
 	 */
-	for (mem_id = 0; mem_id < ipa->mem_count; mem_id++) {
-		const struct ipa_mem *mem = &ipa->mem[mem_id];
-		u16 canary_count;
+	for (i = 0; i < ipa->mem_count; i++) {
+		u16 canary_count = ipa->mem[i].canary_count;
 		__le32 *canary;
 
-		/* Validate all regions (even undefined ones) */
-		if (!ipa_mem_valid(ipa, mem_id))
-			goto err_dma_free;
-
-		/* Skip over undefined regions */
-		if (!mem->offset && !mem->size)
-			continue;
-
-		canary_count = mem->canary_count;
 		if (!canary_count)
 			continue;
 
 		/* Write canary values in the space before the region */
-		canary = ipa->mem_virt + ipa->mem_offset + mem->offset;
+		canary = ipa->mem_virt + ipa->mem_offset + ipa->mem[i].offset;
 		do
 			*--canary = IPA_MEM_CANARY_VAL;
 		while (--canary_count);
@@ -212,8 +370,9 @@ int ipa_mem_config(struct ipa *ipa)
 	if (!ipa_cmd_data_valid(ipa))
 		goto err_dma_free;
 
-	/* Verify the microcontroller ring alignment (0 is OK too) */
-	if (ipa->mem[IPA_MEM_UC_EVENT_RING].offset % 1024) {
+	/* Verify the microcontroller ring alignment (if defined) */
+	mem = ipa_mem_find(ipa, IPA_MEM_UC_EVENT_RING);
+	if (mem && mem->offset % 1024) {
 		dev_err(dev, "microcontroller ring not 1024-byte aligned\n");
 		goto err_dma_free;
 	}
@@ -261,11 +420,9 @@ int ipa_mem_zero_modem(struct ipa *ipa)
 		return -EBUSY;
 	}
 
-	ipa_mem_zero_region_add(trans, &ipa->mem[IPA_MEM_MODEM_HEADER]);
-
-	ipa_mem_zero_region_add(trans, &ipa->mem[IPA_MEM_MODEM_PROC_CTX]);
-
-	ipa_mem_zero_region_add(trans, &ipa->mem[IPA_MEM_MODEM]);
+	ipa_mem_zero_region_add(trans, IPA_MEM_MODEM_HEADER);
+	ipa_mem_zero_region_add(trans, IPA_MEM_MODEM_PROC_CTX);
+	ipa_mem_zero_region_add(trans, IPA_MEM_MODEM);
 
 	gsi_trans_commit_wait(trans);
 
@@ -380,7 +537,7 @@ static int ipa_smem_init(struct ipa *ipa, u32 item, size_t size)
 	 * (in this case, the modem).  An allocation from SMEM is persistent
 	 * until the AP reboots; there is no way to free an allocated SMEM
 	 * region.  Allocation only reserves the space; to use it you need
-	 * to "get" a pointer it (this implies no reference counting).
+	 * to "get" a pointer it (this does not imply reference counting).
 	 * The item might have already been allocated, in which case we
 	 * use it unless the size isn't what we expect.
 	 */
@@ -457,11 +614,12 @@ int ipa_mem_init(struct ipa *ipa, const struct ipa_mem_data *mem_data)
 	struct resource *res;
 	int ret;
 
-	if (mem_data->local_count > IPA_MEM_COUNT) {
-		dev_err(dev, "to many memory regions (%u > %u)\n",
-			mem_data->local_count, IPA_MEM_COUNT);
+	/* Make sure the set of defined memory regions is valid */
+	if (!ipa_mem_valid(ipa, mem_data))
 		return -EINVAL;
-	}
+
+	ipa->mem_count = mem_data->local_count;
+	ipa->mem = mem_data->local;
 
 	ret = dma_set_mask_and_coherent(&ipa->pdev->dev, DMA_BIT_MASK(64));
 	if (ret) {
@@ -486,10 +644,6 @@ int ipa_mem_init(struct ipa *ipa, const struct ipa_mem_data *mem_data)
 	ipa->mem_addr = res->start;
 	ipa->mem_size = resource_size(res);
 
-	/* The ipa->mem[] array is indexed by enum ipa_mem_id values */
-	ipa->mem_count = mem_data->local_count;
-	ipa->mem = mem_data->local;
-
 	ret = ipa_imem_init(ipa, mem_data->imem_addr, mem_data->imem_size);
 	if (ret)
 		goto err_unmap;
diff --git a/drivers/net/ipa/ipa_mem.h b/drivers/net/ipa/ipa_mem.h
index a422aec69e5d..570bfdd99bff 100644
--- a/drivers/net/ipa/ipa_mem.h
+++ b/drivers/net/ipa/ipa_mem.h
@@ -54,37 +54,43 @@ enum ipa_mem_id {
 	IPA_MEM_V6_ROUTE_HASHED,	/* 2 canaries */
 	IPA_MEM_V6_ROUTE,		/* 2 canaries */
 	IPA_MEM_MODEM_HEADER,		/* 2 canaries */
-	IPA_MEM_AP_HEADER,		/* 0 canaries */
+	IPA_MEM_AP_HEADER,		/* 0 canaries, optional */
 	IPA_MEM_MODEM_PROC_CTX,		/* 2 canaries */
 	IPA_MEM_AP_PROC_CTX,		/* 0 canaries */
-	IPA_MEM_NAT_TABLE,		/* 4 canaries (IPA v4.5 and above) */
-	IPA_MEM_PDN_CONFIG,		/* 0/2 canaries (IPA v4.0 and above) */
-	IPA_MEM_STATS_QUOTA_MODEM,	/* 2/4 canaries (IPA v4.0 and above) */
-	IPA_MEM_STATS_QUOTA_AP,		/* 0 canaries (IPA v4.0 and above) */
-	IPA_MEM_STATS_TETHERING,	/* 0 canaries (IPA v4.0 and above) */
+	IPA_MEM_MODEM,			/* 0/2 canaries */
+	IPA_MEM_UC_EVENT_RING,		/* 1 canary, optional */
+	IPA_MEM_PDN_CONFIG,		/* 0/2 canaries (IPA v4.0+) */
+	IPA_MEM_STATS_QUOTA_MODEM,	/* 2/4 canaries (IPA v4.0+) */
+	IPA_MEM_STATS_QUOTA_AP,		/* 0 canaries, optional (IPA v4.0+) */
+	IPA_MEM_STATS_TETHERING,	/* 0 canaries (IPA v4.0+) */
+	IPA_MEM_STATS_DROP,		/* 0 canaries, optional (IPA v4.0+) */
+	/* The next 5 filter and route statistics regions are optional */
 	IPA_MEM_STATS_V4_FILTER,	/* 0 canaries (IPA v4.0-v4.2) */
 	IPA_MEM_STATS_V6_FILTER,	/* 0 canaries (IPA v4.0-v4.2) */
 	IPA_MEM_STATS_V4_ROUTE,		/* 0 canaries (IPA v4.0-v4.2) */
 	IPA_MEM_STATS_V6_ROUTE,		/* 0 canaries (IPA v4.0-v4.2) */
-	IPA_MEM_STATS_FILTER_ROUTE,	/* 0 canaries (IPA v4.5 and above) */
-	IPA_MEM_STATS_DROP,		/* 0 canaries (IPA v4.0 and above) */
-	IPA_MEM_MODEM,			/* 0/2 canaries */
-	IPA_MEM_UC_EVENT_RING,		/* 1 canary */
+	IPA_MEM_STATS_FILTER_ROUTE,	/* 0 canaries (IPA v4.5+) */
+	IPA_MEM_NAT_TABLE,		/* 4 canaries, optional (IPA v4.5+) */
+	IPA_MEM_END_MARKER,		/* 1 canary (not a real region) */
 	IPA_MEM_COUNT,			/* Number of regions (not an index) */
 };
 
 /**
  * struct ipa_mem - IPA local memory region description
+ * @id:			memory region identifier
  * @offset:		offset in IPA memory space to base of the region
  * @size:		size in bytes base of the region
  * @canary_count:	Number of 32-bit "canary" values that precede region
  */
 struct ipa_mem {
+	enum ipa_mem_id id;
 	u32 offset;
 	u16 size;
 	u16 canary_count;
 };
 
+const struct ipa_mem *ipa_mem_find(struct ipa *ipa, enum ipa_mem_id mem_id);
+
 int ipa_mem_config(struct ipa *ipa);
 void ipa_mem_deconfig(struct ipa *ipa);
 
diff --git a/drivers/net/ipa/ipa_qmi.c b/drivers/net/ipa/ipa_qmi.c
index 593665efbcf9..4661105ce7ab 100644
--- a/drivers/net/ipa/ipa_qmi.c
+++ b/drivers/net/ipa/ipa_qmi.c
@@ -298,32 +298,32 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi)
 	req.platform_type_valid = 1;
 	req.platform_type = IPA_QMI_PLATFORM_TYPE_MSM_ANDROID;
 
-	mem = &ipa->mem[IPA_MEM_MODEM_HEADER];
+	mem = ipa_mem_find(ipa, IPA_MEM_MODEM_HEADER);
 	if (mem->size) {
 		req.hdr_tbl_info_valid = 1;
 		req.hdr_tbl_info.start = ipa->mem_offset + mem->offset;
 		req.hdr_tbl_info.end = req.hdr_tbl_info.start + mem->size - 1;
 	}
 
-	mem = &ipa->mem[IPA_MEM_V4_ROUTE];
+	mem = ipa_mem_find(ipa, IPA_MEM_V4_ROUTE);
 	req.v4_route_tbl_info_valid = 1;
 	req.v4_route_tbl_info.start = ipa->mem_offset + mem->offset;
 	req.v4_route_tbl_info.count = mem->size / sizeof(__le64);
 
-	mem = &ipa->mem[IPA_MEM_V6_ROUTE];
+	mem = ipa_mem_find(ipa, IPA_MEM_V6_ROUTE);
 	req.v6_route_tbl_info_valid = 1;
 	req.v6_route_tbl_info.start = ipa->mem_offset + mem->offset;
 	req.v6_route_tbl_info.count = mem->size / sizeof(__le64);
 
-	mem = &ipa->mem[IPA_MEM_V4_FILTER];
+	mem = ipa_mem_find(ipa, IPA_MEM_V4_FILTER);
 	req.v4_filter_tbl_start_valid = 1;
 	req.v4_filter_tbl_start = ipa->mem_offset + mem->offset;
 
-	mem = &ipa->mem[IPA_MEM_V6_FILTER];
+	mem = ipa_mem_find(ipa, IPA_MEM_V6_FILTER);
 	req.v6_filter_tbl_start_valid = 1;
 	req.v6_filter_tbl_start = ipa->mem_offset + mem->offset;
 
-	mem = &ipa->mem[IPA_MEM_MODEM];
+	mem = ipa_mem_find(ipa, IPA_MEM_MODEM);
 	if (mem->size) {
 		req.modem_mem_info_valid = 1;
 		req.modem_mem_info.start = ipa->mem_offset + mem->offset;
@@ -336,7 +336,7 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi)
 
 	/* skip_uc_load_valid and skip_uc_load are set above */
 
-	mem = &ipa->mem[IPA_MEM_MODEM_PROC_CTX];
+	mem = ipa_mem_find(ipa, IPA_MEM_MODEM_PROC_CTX);
 	if (mem->size) {
 		req.hdr_proc_ctx_tbl_info_valid = 1;
 		req.hdr_proc_ctx_tbl_info.start =
@@ -347,7 +347,7 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi)
 
 	/* Nothing to report for the compression table (zip_tbl_info) */
 
-	mem = &ipa->mem[IPA_MEM_V4_ROUTE_HASHED];
+	mem = ipa_mem_find(ipa, IPA_MEM_V4_ROUTE_HASHED);
 	if (mem->size) {
 		req.v4_hash_route_tbl_info_valid = 1;
 		req.v4_hash_route_tbl_info.start =
@@ -355,7 +355,7 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi)
 		req.v4_hash_route_tbl_info.count = mem->size / sizeof(__le64);
 	}
 
-	mem = &ipa->mem[IPA_MEM_V6_ROUTE_HASHED];
+	mem = ipa_mem_find(ipa, IPA_MEM_V6_ROUTE_HASHED);
 	if (mem->size) {
 		req.v6_hash_route_tbl_info_valid = 1;
 		req.v6_hash_route_tbl_info.start =
@@ -363,22 +363,21 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi)
 		req.v6_hash_route_tbl_info.count = mem->size / sizeof(__le64);
 	}
 
-	mem = &ipa->mem[IPA_MEM_V4_FILTER_HASHED];
+	mem = ipa_mem_find(ipa, IPA_MEM_V4_FILTER_HASHED);
 	if (mem->size) {
 		req.v4_hash_filter_tbl_start_valid = 1;
 		req.v4_hash_filter_tbl_start = ipa->mem_offset + mem->offset;
 	}
 
-	mem = &ipa->mem[IPA_MEM_V6_FILTER_HASHED];
+	mem = ipa_mem_find(ipa, IPA_MEM_V6_FILTER_HASHED);
 	if (mem->size) {
 		req.v6_hash_filter_tbl_start_valid = 1;
 		req.v6_hash_filter_tbl_start = ipa->mem_offset + mem->offset;
 	}
 
-	/* None of the stats fields are valid (IPA v4.0 and above) */
-
+	/* The stats fields are only valid for IPA v4.0+ */
 	if (ipa->version >= IPA_VERSION_4_0) {
-		mem = &ipa->mem[IPA_MEM_STATS_QUOTA_MODEM];
+		mem = ipa_mem_find(ipa, IPA_MEM_STATS_QUOTA_MODEM);
 		if (mem->size) {
 			req.hw_stats_quota_base_addr_valid = 1;
 			req.hw_stats_quota_base_addr =
@@ -387,8 +386,9 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi)
 			req.hw_stats_quota_size = ipa->mem_offset + mem->size;
 		}
 
-		mem = &ipa->mem[IPA_MEM_STATS_DROP];
-		if (mem->size) {
+		/* If the DROP stats region is defined, include it */
+		mem = ipa_mem_find(ipa, IPA_MEM_STATS_DROP);
+		if (mem && mem->size) {
 			req.hw_stats_drop_base_addr_valid = 1;
 			req.hw_stats_drop_base_addr =
 				ipa->mem_offset + mem->offset;
diff --git a/drivers/net/ipa/ipa_reg.h b/drivers/net/ipa/ipa_reg.h
index 286ea9634c49..b89dec5865a5 100644
--- a/drivers/net/ipa/ipa_reg.h
+++ b/drivers/net/ipa/ipa_reg.h
@@ -368,6 +368,7 @@ enum ipa_cs_offload_en {
 	IPA_CS_OFFLOAD_NONE		= 0x0,
 	IPA_CS_OFFLOAD_UL		= 0x1,	/* Before IPA v4.5 (TX) */
 	IPA_CS_OFFLOAD_DL		= 0x2,	/* Before IPA v4.5 (RX) */
+	IPA_CS_OFFLOAD_INLINE		= 0x1,	/* IPA v4.5 (TX and RX) */
 };
 
 /* Valid only for TX (IPA consumer) endpoints */
diff --git a/drivers/net/ipa/ipa_smp2p.c b/drivers/net/ipa/ipa_smp2p.c
index a5f7a79a1923..cf709df70d28 100644
--- a/drivers/net/ipa/ipa_smp2p.c
+++ b/drivers/net/ipa/ipa_smp2p.c
@@ -176,11 +176,8 @@ static int ipa_smp2p_irq_init(struct ipa_smp2p *smp2p, const char *name,
 	int ret;
 
 	ret = platform_get_irq_byname(smp2p->ipa->pdev, name);
-	if (ret <= 0) {
-		dev_err(dev, "DT error %d getting \"%s\" IRQ property\n",
-			ret, name);
+	if (ret <= 0)
 		return ret ? : -EINVAL;
-	}
 	irq = ret;
 
 	ret = request_threaded_irq(irq, NULL, handler, 0, name, smp2p);
diff --git a/drivers/net/ipa/ipa_sysfs.c b/drivers/net/ipa/ipa_sysfs.c
new file mode 100644
index 000000000000..ff61dbdd70d8
--- /dev/null
+++ b/drivers/net/ipa/ipa_sysfs.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Copyright (C) 2021 Linaro Ltd. */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/sysfs.h>
+
+#include "ipa.h"
+#include "ipa_version.h"
+#include "ipa_sysfs.h"
+
+static const char *ipa_version_string(struct ipa *ipa)
+{
+	switch (ipa->version) {
+	case IPA_VERSION_3_0:
+		return "3.0";
+	case IPA_VERSION_3_1:
+		return "3.1";
+	case IPA_VERSION_3_5:
+		return "3.5";
+	case IPA_VERSION_3_5_1:
+		return "3.5.1";
+	case IPA_VERSION_4_0:
+		return "4.0";
+	case IPA_VERSION_4_1:
+		return "4.1";
+	case IPA_VERSION_4_2:
+		return "4.2";
+	case IPA_VERSION_4_5:
+		return "4.5";
+	case IPA_VERSION_4_7:
+		return "4.7";
+	case IPA_VERSION_4_9:
+		return "4.9";
+	case IPA_VERSION_4_11:
+		return "4.11";
+	default:
+		return "0.0";	/* Won't happen (checked at probe time) */
+	}
+}
+
+static ssize_t
+version_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct ipa *ipa = dev_get_drvdata(dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%s\n", ipa_version_string(ipa));
+}
+
+static DEVICE_ATTR_RO(version);
+
+static struct attribute *ipa_attrs[] = {
+	&dev_attr_version.attr,
+	NULL
+};
+
+const struct attribute_group ipa_attribute_group = {
+	.attrs		= ipa_attrs,
+};
+
+static const char *ipa_offload_string(struct ipa *ipa)
+{
+	return ipa->version < IPA_VERSION_4_5 ? "MAPv4" : "MAPv5";
+}
+
+static ssize_t rx_offload_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct ipa *ipa = dev_get_drvdata(dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%s\n", ipa_offload_string(ipa));
+}
+
+static DEVICE_ATTR_RO(rx_offload);
+
+static ssize_t tx_offload_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct ipa *ipa = dev_get_drvdata(dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%s\n", ipa_offload_string(ipa));
+}
+
+static DEVICE_ATTR_RO(tx_offload);
+
+static struct attribute *ipa_feature_attrs[] = {
+	&dev_attr_rx_offload.attr,
+	&dev_attr_tx_offload.attr,
+	NULL
+};
+
+const struct attribute_group ipa_feature_attribute_group = {
+	.name		= "feature",
+	.attrs		= ipa_feature_attrs,
+};
+
+static ssize_t
+ipa_endpoint_id_show(struct ipa *ipa, char *buf, enum ipa_endpoint_name name)
+{
+	u32 endpoint_id = ipa->name_map[name]->endpoint_id;
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", endpoint_id);
+}
+
+static ssize_t rx_endpoint_id_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct ipa *ipa = dev_get_drvdata(dev);
+
+	return ipa_endpoint_id_show(ipa, buf, IPA_ENDPOINT_AP_MODEM_RX);
+}
+
+static DEVICE_ATTR_RO(rx_endpoint_id);
+
+static ssize_t tx_endpoint_id_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct ipa *ipa = dev_get_drvdata(dev);
+
+	return ipa_endpoint_id_show(ipa, buf, IPA_ENDPOINT_AP_MODEM_TX);
+}
+
+static DEVICE_ATTR_RO(tx_endpoint_id);
+
+static struct attribute *ipa_modem_attrs[] = {
+	&dev_attr_rx_endpoint_id.attr,
+	&dev_attr_tx_endpoint_id.attr,
+	NULL
+};
+
+const struct attribute_group ipa_modem_attribute_group = {
+	.name		= "modem",
+	.attrs		= ipa_modem_attrs,
+};
diff --git a/drivers/net/ipa/ipa_sysfs.h b/drivers/net/ipa/ipa_sysfs.h
new file mode 100644
index 000000000000..b34e5650bf8c
--- /dev/null
+++ b/drivers/net/ipa/ipa_sysfs.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2019-2021 Linaro Ltd.
+ */
+#ifndef _IPA_SYSFS_H_
+#define _IPA_SYSFS_H_
+
+struct attribute_group;
+
+extern const struct attribute_group ipa_attribute_group;
+extern const struct attribute_group ipa_feature_attribute_group;
+extern const struct attribute_group ipa_modem_attribute_group;
+
+#endif /* _IPA_SYSFS_H_ */
diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c
index 3168d72f4245..c617a9156f26 100644
--- a/drivers/net/ipa/ipa_table.c
+++ b/drivers/net/ipa/ipa_table.c
@@ -150,29 +150,16 @@ static void ipa_table_validate_build(void)
 }
 
 static bool
-ipa_table_valid_one(struct ipa *ipa, bool route, bool ipv6, bool hashed)
+ipa_table_valid_one(struct ipa *ipa, enum ipa_mem_id mem_id, bool route)
 {
+	const struct ipa_mem *mem = ipa_mem_find(ipa, mem_id);
 	struct device *dev = &ipa->pdev->dev;
-	const struct ipa_mem *mem;
 	u32 size;
 
-	if (route) {
-		if (ipv6)
-			mem = hashed ? &ipa->mem[IPA_MEM_V6_ROUTE_HASHED]
-				     : &ipa->mem[IPA_MEM_V6_ROUTE];
-		else
-			mem = hashed ? &ipa->mem[IPA_MEM_V4_ROUTE_HASHED]
-				     : &ipa->mem[IPA_MEM_V4_ROUTE];
+	if (route)
 		size = IPA_ROUTE_COUNT_MAX * sizeof(__le64);
-	} else {
-		if (ipv6)
-			mem = hashed ? &ipa->mem[IPA_MEM_V6_FILTER_HASHED]
-				     : &ipa->mem[IPA_MEM_V6_FILTER];
-		else
-			mem = hashed ? &ipa->mem[IPA_MEM_V4_FILTER_HASHED]
-				     : &ipa->mem[IPA_MEM_V4_FILTER];
+	else
 		size = (1 + IPA_FILTER_COUNT_MAX) * sizeof(__le64);
-	}
 
 	if (!ipa_cmd_table_valid(ipa, mem, route, ipv6, hashed))
 		return false;
@@ -185,9 +172,8 @@ ipa_table_valid_one(struct ipa *ipa, bool route, bool ipv6, bool hashed)
 	if (hashed && !mem->size)
 		return true;
 
-	dev_err(dev, "IPv%c %s%s table region size 0x%02x, expected 0x%02x\n",
-		ipv6 ? '6' : '4', hashed ? "hashed " : "",
-		route ? "route" : "filter", mem->size, size);
+	dev_err(dev, "%s table region %u size 0x%02x, expected 0x%02x\n",
+		route ? "route" : "filter", mem_id, mem->size, size);
 
 	return false;
 }
@@ -195,16 +181,16 @@ ipa_table_valid_one(struct ipa *ipa, bool route, bool ipv6, bool hashed)
 /* Verify the filter and route table memory regions are the expected size */
 bool ipa_table_valid(struct ipa *ipa)
 {
-	bool valid = true;
+	bool valid;
 
-	valid = valid && ipa_table_valid_one(ipa, false, false, false);
-	valid = valid && ipa_table_valid_one(ipa, false, false, true);
-	valid = valid && ipa_table_valid_one(ipa, false, true, false);
-	valid = valid && ipa_table_valid_one(ipa, false, true, true);
-	valid = valid && ipa_table_valid_one(ipa, true, false, false);
-	valid = valid && ipa_table_valid_one(ipa, true, false, true);
-	valid = valid && ipa_table_valid_one(ipa, true, true, false);
-	valid = valid && ipa_table_valid_one(ipa, true, true, true);
+	valid = ipa_table_valid_one(IPA_MEM_V4_FILTER, false);
+	valid = valid && ipa_table_valid_one(IPA_MEM_V4_FILTER_HASHED, false);
+	valid = valid && ipa_table_valid_one(IPA_MEM_V6_FILTER, false);
+	valid = valid && ipa_table_valid_one(IPA_MEM_V6_FILTER_HASHED, false);
+	valid = valid && ipa_table_valid_one(IPA_MEM_V4_ROUTE, true);
+	valid = valid && ipa_table_valid_one(IPA_MEM_V4_ROUTE_HASHED, true);
+	valid = valid && ipa_table_valid_one(IPA_MEM_V6_ROUTE, true);
+	valid = valid && ipa_table_valid_one(IPA_MEM_V6_ROUTE_HASHED, true);
 
 	return valid;
 }
@@ -256,14 +242,15 @@ static dma_addr_t ipa_table_addr(struct ipa *ipa, bool filter_mask, u16 count)
 }
 
 static void ipa_table_reset_add(struct gsi_trans *trans, bool filter,
-				u16 first, u16 count, const struct ipa_mem *mem)
+				u16 first, u16 count, enum ipa_mem_id mem_id)
 {
 	struct ipa *ipa = container_of(trans->gsi, struct ipa, gsi);
+	const struct ipa_mem *mem = ipa_mem_find(ipa, mem_id);
 	dma_addr_t addr;
 	u32 offset;
 	u16 size;
 
-	/* Nothing to do if the table memory regions is empty */
+	/* Nothing to do if the table memory region is empty */
 	if (!mem->size)
 		return;
 
@@ -282,16 +269,13 @@ static void ipa_table_reset_add(struct gsi_trans *trans, bool filter,
  * for the IPv4 and IPv6 non-hashed and hashed filter tables.
  */
 static int
-ipa_filter_reset_table(struct ipa *ipa, const struct ipa_mem *mem, bool modem)
+ipa_filter_reset_table(struct ipa *ipa, enum ipa_mem_id mem_id, bool modem)
 {
 	u32 ep_mask = ipa->filter_map;
 	u32 count = hweight32(ep_mask);
 	struct gsi_trans *trans;
 	enum gsi_ee_id ee_id;
 
-	if (!mem->size)
-		return 0;
-
 	trans = ipa_cmd_trans_alloc(ipa, count);
 	if (!trans) {
 		dev_err(&ipa->pdev->dev,
@@ -311,7 +295,7 @@ ipa_filter_reset_table(struct ipa *ipa, const struct ipa_mem *mem, bool modem)
 		if (endpoint->ee_id != ee_id)
 			continue;
 
-		ipa_table_reset_add(trans, true, endpoint_id, 1, mem);
+		ipa_table_reset_add(trans, true, endpoint_id, 1, mem_id);
 	}
 
 	gsi_trans_commit_wait(trans);
@@ -327,20 +311,18 @@ static int ipa_filter_reset(struct ipa *ipa, bool modem)
 {
 	int ret;
 
-	ret = ipa_filter_reset_table(ipa, &ipa->mem[IPA_MEM_V4_FILTER], modem);
+	ret = ipa_filter_reset_table(ipa, IPA_MEM_V4_FILTER, modem);
 	if (ret)
 		return ret;
 
-	ret = ipa_filter_reset_table(ipa, &ipa->mem[IPA_MEM_V4_FILTER_HASHED],
-				     modem);
+	ret = ipa_filter_reset_table(ipa, IPA_MEM_V4_FILTER_HASHED, modem);
 	if (ret)
 		return ret;
 
-	ret = ipa_filter_reset_table(ipa, &ipa->mem[IPA_MEM_V6_FILTER], modem);
+	ret = ipa_filter_reset_table(ipa, IPA_MEM_V6_FILTER, modem);
 	if (ret)
 		return ret;
-	ret = ipa_filter_reset_table(ipa, &ipa->mem[IPA_MEM_V6_FILTER_HASHED],
-				     modem);
+	ret = ipa_filter_reset_table(ipa, IPA_MEM_V6_FILTER_HASHED, modem);
 
 	return ret;
 }
@@ -371,15 +353,13 @@ static int ipa_route_reset(struct ipa *ipa, bool modem)
 		count = IPA_ROUTE_AP_COUNT;
 	}
 
+	ipa_table_reset_add(trans, false, first, count, IPA_MEM_V4_ROUTE);
 	ipa_table_reset_add(trans, false, first, count,
-			    &ipa->mem[IPA_MEM_V4_ROUTE]);
-	ipa_table_reset_add(trans, false, first, count,
-			    &ipa->mem[IPA_MEM_V4_ROUTE_HASHED]);
+			    IPA_MEM_V4_ROUTE_HASHED);
 
+	ipa_table_reset_add(trans, false, first, count, IPA_MEM_V6_ROUTE);
 	ipa_table_reset_add(trans, false, first, count,
-			    &ipa->mem[IPA_MEM_V6_ROUTE]);
-	ipa_table_reset_add(trans, false, first, count,
-			    &ipa->mem[IPA_MEM_V6_ROUTE_HASHED]);
+			    IPA_MEM_V6_ROUTE_HASHED);
 
 	gsi_trans_commit_wait(trans);
 
@@ -433,10 +413,12 @@ int ipa_table_hash_flush(struct ipa *ipa)
 
 static void ipa_table_init_add(struct gsi_trans *trans, bool filter,
 			       enum ipa_cmd_opcode opcode,
-			       const struct ipa_mem *mem,
-			       const struct ipa_mem *hash_mem)
+			       enum ipa_mem_id mem_id,
+			       enum ipa_mem_id hash_mem_id)
 {
 	struct ipa *ipa = container_of(trans->gsi, struct ipa, gsi);
+	const struct ipa_mem *hash_mem = ipa_mem_find(ipa, hash_mem_id);
+	const struct ipa_mem *mem = ipa_mem_find(ipa, mem_id);
 	dma_addr_t hash_addr;
 	dma_addr_t addr;
 	u16 hash_count;
@@ -477,20 +459,16 @@ int ipa_table_setup(struct ipa *ipa)
 	}
 
 	ipa_table_init_add(trans, false, IPA_CMD_IP_V4_ROUTING_INIT,
-			   &ipa->mem[IPA_MEM_V4_ROUTE],
-			   &ipa->mem[IPA_MEM_V4_ROUTE_HASHED]);
+			   IPA_MEM_V4_ROUTE, IPA_MEM_V4_ROUTE_HASHED);
 
 	ipa_table_init_add(trans, false, IPA_CMD_IP_V6_ROUTING_INIT,
-			   &ipa->mem[IPA_MEM_V6_ROUTE],
-			   &ipa->mem[IPA_MEM_V6_ROUTE_HASHED]);
+			   IPA_MEM_V6_ROUTE, IPA_MEM_V6_ROUTE_HASHED);
 
 	ipa_table_init_add(trans, true, IPA_CMD_IP_V4_FILTER_INIT,
-			   &ipa->mem[IPA_MEM_V4_FILTER],
-			   &ipa->mem[IPA_MEM_V4_FILTER_HASHED]);
+			   IPA_MEM_V4_FILTER, IPA_MEM_V4_FILTER_HASHED);
 
 	ipa_table_init_add(trans, true, IPA_CMD_IP_V6_FILTER_INIT,
-			   &ipa->mem[IPA_MEM_V6_FILTER],
-			   &ipa->mem[IPA_MEM_V6_FILTER_HASHED]);
+			   IPA_MEM_V6_FILTER, IPA_MEM_V6_FILTER_HASHED);
 
 	gsi_trans_commit_wait(trans);
 
diff --git a/drivers/net/ipa/ipa_uc.c b/drivers/net/ipa/ipa_uc.c
index 2756363e6938..fd9219863234 100644
--- a/drivers/net/ipa/ipa_uc.c
+++ b/drivers/net/ipa/ipa_uc.c
@@ -116,7 +116,8 @@ enum ipa_uc_event {
 
 static struct ipa_uc_mem_area *ipa_uc_shared(struct ipa *ipa)
 {
-	u32 offset = ipa->mem_offset + ipa->mem[IPA_MEM_UC_SHARED].offset;
+	const struct ipa_mem *mem = ipa_mem_find(ipa, IPA_MEM_UC_SHARED);
+	u32 offset = ipa->mem_offset + mem->offset;
 
 	return ipa->mem_virt + offset;
 }
diff --git a/drivers/net/ipa/ipa_version.h b/drivers/net/ipa/ipa_version.h
index ee2b3d02f3cd..6c16c895d842 100644
--- a/drivers/net/ipa/ipa_version.h
+++ b/drivers/net/ipa/ipa_version.h
@@ -21,6 +21,8 @@
  * @IPA_VERSION_4_11:	IPA version 4.11/GSI version 2.11 (2.1.1)
  *
  * Defines the version of IPA (and GSI) hardware present on the platform.
+ * Please update ipa_version_valid() and ipa_version_string() whenever a
+ * new version is added.
  */
 enum ipa_version {
 	IPA_VERSION_3_0,
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 1b998aa481f8..80de9768ecd4 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1781,7 +1781,7 @@ static int macvlan_device_event(struct notifier_block *unused,
 		unregister_netdevice_many(&list_kill);
 		break;
 	case NETDEV_PRE_TYPE_CHANGE:
-		/* Forbid underlaying device to change its type. */
+		/* Forbid underlying device to change its type. */
 		return NOTIFY_BAD;
 
 	case NETDEV_NOTIFY_PEERS:
diff --git a/drivers/net/mdio/Kconfig b/drivers/net/mdio/Kconfig
index d06e06f5e31a..99a6c13a11af 100644
--- a/drivers/net/mdio/Kconfig
+++ b/drivers/net/mdio/Kconfig
@@ -19,6 +19,13 @@ config MDIO_BUS
 	  reflects whether the mdio_bus/mdio_device code is built as a
 	  loadable module or built-in.
 
+config FWNODE_MDIO
+	def_tristate PHYLIB
+	depends on (ACPI || OF) || COMPILE_TEST
+	select FIXED_PHY
+	help
+	  FWNODE MDIO bus (Ethernet PHY) accessors
+
 config OF_MDIO
 	def_tristate PHYLIB
 	depends on OF
@@ -27,6 +34,13 @@ config OF_MDIO
 	help
 	  OpenFirmware MDIO bus (Ethernet PHY) accessors
 
+config ACPI_MDIO
+	def_tristate PHYLIB
+	depends on ACPI
+	depends on PHYLIB
+	help
+	  ACPI MDIO bus (Ethernet PHY) accessors
+
 if MDIO_BUS
 
 config MDIO_DEVRES
diff --git a/drivers/net/mdio/Makefile b/drivers/net/mdio/Makefile
index c3ec0ef989df..15f8dc4042ce 100644
--- a/drivers/net/mdio/Makefile
+++ b/drivers/net/mdio/Makefile
@@ -1,7 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for Linux MDIO bus drivers
 
-obj-$(CONFIG_OF_MDIO)	+= of_mdio.o
+obj-$(CONFIG_ACPI_MDIO)		+= acpi_mdio.o
+obj-$(CONFIG_FWNODE_MDIO)	+= fwnode_mdio.o
+obj-$(CONFIG_OF_MDIO)		+= of_mdio.o
 
 obj-$(CONFIG_MDIO_ASPEED)		+= mdio-aspeed.o
 obj-$(CONFIG_MDIO_BCM_IPROC)		+= mdio-bcm-iproc.o
diff --git a/drivers/net/mdio/acpi_mdio.c b/drivers/net/mdio/acpi_mdio.c
new file mode 100644
index 000000000000..d77c987fda9c
--- /dev/null
+++ b/drivers/net/mdio/acpi_mdio.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ACPI helpers for the MDIO (Ethernet PHY) API
+ *
+ * This file provides helper functions for extracting PHY device information
+ * out of the ACPI ASL and using it to populate an mii_bus.
+ */
+
+#include <linux/acpi.h>
+#include <linux/acpi_mdio.h>
+#include <linux/bits.h>
+#include <linux/dev_printk.h>
+#include <linux/fwnode_mdio.h>
+#include <linux/module.h>
+#include <linux/types.h>
+
+MODULE_AUTHOR("Calvin Johnson <calvin.johnson@oss.nxp.com>");
+MODULE_LICENSE("GPL");
+
+/**
+ * acpi_mdiobus_register - Register mii_bus and create PHYs from the ACPI ASL.
+ * @mdio: pointer to mii_bus structure
+ * @fwnode: pointer to fwnode of MDIO bus. This fwnode is expected to represent
+ * an ACPI device object corresponding to the MDIO bus and its children are
+ * expected to correspond to the PHY devices on that bus.
+ *
+ * This function registers the mii_bus structure and registers a phy_device
+ * for each child node of @fwnode.
+ */
+int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode)
+{
+	struct fwnode_handle *child;
+	u32 addr;
+	int ret;
+
+	/* Mask out all PHYs from auto probing. */
+	mdio->phy_mask = GENMASK(31, 0);
+	ret = mdiobus_register(mdio);
+	if (ret)
+		return ret;
+
+	ACPI_COMPANION_SET(&mdio->dev, to_acpi_device_node(fwnode));
+
+	/* Loop over the child nodes and register a phy_device for each PHY */
+	fwnode_for_each_child_node(fwnode, child) {
+		ret = acpi_get_local_address(ACPI_HANDLE_FWNODE(child), &addr);
+		if (ret || addr >= PHY_MAX_ADDR)
+			continue;
+
+		ret = fwnode_mdiobus_register_phy(mdio, child, addr);
+		if (ret == -ENODEV)
+			dev_err(&mdio->dev,
+				"MDIO device at address %d is missing.\n",
+				addr);
+	}
+	return 0;
+}
+EXPORT_SYMBOL(acpi_mdiobus_register);
diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c
new file mode 100644
index 000000000000..1becb1a731f6
--- /dev/null
+++ b/drivers/net/mdio/fwnode_mdio.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * fwnode helpers for the MDIO (Ethernet PHY) API
+ *
+ * This file provides helper functions for extracting PHY device information
+ * out of the fwnode and using it to populate an mii_bus.
+ */
+
+#include <linux/acpi.h>
+#include <linux/fwnode_mdio.h>
+#include <linux/of.h>
+#include <linux/phy.h>
+
+MODULE_AUTHOR("Calvin Johnson <calvin.johnson@oss.nxp.com>");
+MODULE_LICENSE("GPL");
+
+static struct mii_timestamper *
+fwnode_find_mii_timestamper(struct fwnode_handle *fwnode)
+{
+	struct of_phandle_args arg;
+	int err;
+
+	if (is_acpi_node(fwnode))
+		return NULL;
+
+	err = of_parse_phandle_with_fixed_args(to_of_node(fwnode),
+					       "timestamper", 1, 0, &arg);
+	if (err == -ENOENT)
+		return NULL;
+	else if (err)
+		return ERR_PTR(err);
+
+	if (arg.args_count != 1)
+		return ERR_PTR(-EINVAL);
+
+	return register_mii_timestamper(arg.np, arg.args[0]);
+}
+
+int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio,
+				       struct phy_device *phy,
+				       struct fwnode_handle *child, u32 addr)
+{
+	int rc;
+
+	rc = fwnode_irq_get(child, 0);
+	if (rc == -EPROBE_DEFER)
+		return rc;
+
+	if (rc > 0) {
+		phy->irq = rc;
+		mdio->irq[addr] = rc;
+	} else {
+		phy->irq = mdio->irq[addr];
+	}
+
+	if (fwnode_property_read_bool(child, "broken-turn-around"))
+		mdio->phy_ignore_ta_mask |= 1 << addr;
+
+	fwnode_property_read_u32(child, "reset-assert-us",
+				 &phy->mdio.reset_assert_delay);
+	fwnode_property_read_u32(child, "reset-deassert-us",
+				 &phy->mdio.reset_deassert_delay);
+
+	/* Associate the fwnode with the device structure so it
+	 * can be looked up later
+	 */
+	fwnode_handle_get(child);
+	device_set_node(&phy->mdio.dev, child);
+
+	/* All data is now stored in the phy struct;
+	 * register it
+	 */
+	rc = phy_device_register(phy);
+	if (rc) {
+		fwnode_handle_put(child);
+		return rc;
+	}
+
+	dev_dbg(&mdio->dev, "registered phy %p fwnode at address %i\n",
+		child, addr);
+	return 0;
+}
+EXPORT_SYMBOL(fwnode_mdiobus_phy_device_register);
+
+int fwnode_mdiobus_register_phy(struct mii_bus *bus,
+				struct fwnode_handle *child, u32 addr)
+{
+	struct mii_timestamper *mii_ts = NULL;
+	struct phy_device *phy;
+	bool is_c45 = false;
+	u32 phy_id;
+	int rc;
+
+	mii_ts = fwnode_find_mii_timestamper(child);
+	if (IS_ERR(mii_ts))
+		return PTR_ERR(mii_ts);
+
+	rc = fwnode_property_match_string(child, "compatible",
+					  "ethernet-phy-ieee802.3-c45");
+	if (rc >= 0)
+		is_c45 = true;
+
+	if (is_c45 || fwnode_get_phy_id(child, &phy_id))
+		phy = get_phy_device(bus, addr, is_c45);
+	else
+		phy = phy_device_create(bus, addr, phy_id, 0, NULL);
+	if (IS_ERR(phy)) {
+		unregister_mii_timestamper(mii_ts);
+		return PTR_ERR(phy);
+	}
+
+	if (is_acpi_node(child)) {
+		phy->irq = bus->irq[addr];
+
+		/* Associate the fwnode with the device structure so it
+		 * can be looked up later.
+		 */
+		phy->mdio.dev.fwnode = child;
+
+		/* All data is now stored in the phy struct, so register it */
+		rc = phy_device_register(phy);
+		if (rc) {
+			phy_device_free(phy);
+			fwnode_handle_put(phy->mdio.dev.fwnode);
+			return rc;
+		}
+	} else if (is_of_node(child)) {
+		rc = fwnode_mdiobus_phy_device_register(bus, phy, child, addr);
+		if (rc) {
+			unregister_mii_timestamper(mii_ts);
+			phy_device_free(phy);
+			return rc;
+		}
+	}
+
+	/* phy->mii_ts may already be defined by the PHY driver. A
+	 * mii_timestamper probed via the device tree will still have
+	 * precedence.
+	 */
+	if (mii_ts)
+		phy->mii_ts = mii_ts;
+	return 0;
+}
+EXPORT_SYMBOL(fwnode_mdiobus_register_phy);
diff --git a/drivers/net/mdio/mdio-bcm-unimac.c b/drivers/net/mdio/mdio-bcm-unimac.c
index 5d171e7f118d..bfc9be23c973 100644
--- a/drivers/net/mdio/mdio-bcm-unimac.c
+++ b/drivers/net/mdio/mdio-bcm-unimac.c
@@ -203,7 +203,7 @@ static void unimac_mdio_clk_set(struct unimac_mdio_priv *priv)
 		return;
 	}
 
-	/* The MDIO clock is the reference clock (typicaly 250Mhz) divided by
+	/* The MDIO clock is the reference clock (typically 250Mhz) divided by
 	 * 2 x (MDIO_CLK_DIV + 1)
 	 */
 	reg = unimac_mdio_readl(priv, MDIO_CFG);
diff --git a/drivers/net/mdio/mdio-ipq8064.c b/drivers/net/mdio/mdio-ipq8064.c
index 8fe8f0119fc1..bd1aea2d5a26 100644
--- a/drivers/net/mdio/mdio-ipq8064.c
+++ b/drivers/net/mdio/mdio-ipq8064.c
@@ -7,33 +7,33 @@
 
 #include <linux/delay.h>
 #include <linux/kernel.h>
-#include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of_mdio.h>
-#include <linux/phy.h>
+#include <linux/of_address.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 
 /* MII address register definitions */
-#define MII_ADDR_REG_ADDR                       0x10
-#define MII_BUSY                                BIT(0)
-#define MII_WRITE                               BIT(1)
-#define MII_CLKRANGE_60_100M                    (0 << 2)
-#define MII_CLKRANGE_100_150M                   (1 << 2)
-#define MII_CLKRANGE_20_35M                     (2 << 2)
-#define MII_CLKRANGE_35_60M                     (3 << 2)
-#define MII_CLKRANGE_150_250M                   (4 << 2)
-#define MII_CLKRANGE_250_300M                   (5 << 2)
+#define MII_ADDR_REG_ADDR			0x10
+#define MII_BUSY				BIT(0)
+#define MII_WRITE				BIT(1)
+#define MII_CLKRANGE(x)				((x) << 2)
+#define MII_CLKRANGE_60_100M			MII_CLKRANGE(0)
+#define MII_CLKRANGE_100_150M			MII_CLKRANGE(1)
+#define MII_CLKRANGE_20_35M			MII_CLKRANGE(2)
+#define MII_CLKRANGE_35_60M			MII_CLKRANGE(3)
+#define MII_CLKRANGE_150_250M			MII_CLKRANGE(4)
+#define MII_CLKRANGE_250_300M			MII_CLKRANGE(5)
 #define MII_CLKRANGE_MASK			GENMASK(4, 2)
 #define MII_REG_SHIFT				6
 #define MII_REG_MASK				GENMASK(10, 6)
 #define MII_ADDR_SHIFT				11
 #define MII_ADDR_MASK				GENMASK(15, 11)
 
-#define MII_DATA_REG_ADDR                       0x14
+#define MII_DATA_REG_ADDR			0x14
 
-#define MII_MDIO_DELAY_USEC                     (1000)
-#define MII_MDIO_RETRY_MSEC                     (10)
+#define MII_MDIO_DELAY_USEC			(1000)
+#define MII_MDIO_RETRY_MSEC			(10)
 
 struct ipq8064_mdio {
 	struct regmap *base; /* NSS_GMAC0_BASE */
@@ -65,7 +65,7 @@ ipq8064_mdio_read(struct mii_bus *bus, int phy_addr, int reg_offset)
 		   ((reg_offset << MII_REG_SHIFT) & MII_REG_MASK);
 
 	regmap_write(priv->base, MII_ADDR_REG_ADDR, miiaddr);
-	usleep_range(8, 10);
+	usleep_range(10, 13);
 
 	err = ipq8064_mdio_wait_busy(priv);
 	if (err)
@@ -91,19 +91,46 @@ ipq8064_mdio_write(struct mii_bus *bus, int phy_addr, int reg_offset, u16 data)
 		   ((reg_offset << MII_REG_SHIFT) & MII_REG_MASK);
 
 	regmap_write(priv->base, MII_ADDR_REG_ADDR, miiaddr);
-	usleep_range(8, 10);
+
+	/* For the specific reg 31 extra time is needed or the next
+	 * read will produce garbage data.
+	 */
+	if (reg_offset == 31)
+		usleep_range(30, 43);
+	else
+		usleep_range(10, 13);
 
 	return ipq8064_mdio_wait_busy(priv);
 }
 
+static const struct regmap_config ipq8064_mdio_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.can_multi_write = false,
+	/* the mdio lock is used by any user of this mdio driver */
+	.disable_locking = true,
+
+	.cache_type = REGCACHE_NONE,
+};
+
 static int
 ipq8064_mdio_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
 	struct ipq8064_mdio *priv;
+	struct resource res;
 	struct mii_bus *bus;
+	void __iomem *base;
 	int ret;
 
+	if (of_address_to_resource(np, 0, &res))
+		return -ENOMEM;
+
+	base = ioremap(res.start, resource_size(&res));
+	if (!base)
+		return -ENOMEM;
+
 	bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(*priv));
 	if (!bus)
 		return -ENOMEM;
@@ -115,15 +142,10 @@ ipq8064_mdio_probe(struct platform_device *pdev)
 	bus->parent = &pdev->dev;
 
 	priv = bus->priv;
-	priv->base = device_node_to_regmap(np);
-	if (IS_ERR(priv->base)) {
-		if (priv->base == ERR_PTR(-EPROBE_DEFER))
-			return -EPROBE_DEFER;
-
-		dev_err(&pdev->dev, "error getting device regmap, error=%pe\n",
-			priv->base);
+	priv->base = devm_regmap_init_mmio(&pdev->dev, base,
+					   &ipq8064_mdio_regmap_config);
+	if (IS_ERR(priv->base))
 		return PTR_ERR(priv->base);
-	}
 
 	ret = of_mdiobus_register(bus, np);
 	if (ret)
diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c
index b36e5ea04ddf..2d67e12c8262 100644
--- a/drivers/net/mdio/mdio-mscc-miim.c
+++ b/drivers/net/mdio/mdio-mscc-miim.c
@@ -139,10 +139,6 @@ static int mscc_miim_probe(struct platform_device *pdev)
 	struct mscc_miim_dev *dev;
 	int ret;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENODEV;
-
 	bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(*dev));
 	if (!bus)
 		return -ENOMEM;
@@ -155,7 +151,7 @@ static int mscc_miim_probe(struct platform_device *pdev)
 	bus->parent = &pdev->dev;
 
 	dev = bus->priv;
-	dev->regs = devm_ioremap_resource(&pdev->dev, res);
+	dev->regs = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
 	if (IS_ERR(dev->regs)) {
 		dev_err(&pdev->dev, "Unable to map MIIM registers\n");
 		return PTR_ERR(dev->regs);
diff --git a/drivers/net/mdio/mdio-mux-bcm-iproc.c b/drivers/net/mdio/mdio-mux-bcm-iproc.c
index 03261e6b9ceb..014c0baedbd2 100644
--- a/drivers/net/mdio/mdio-mux-bcm-iproc.c
+++ b/drivers/net/mdio/mdio-mux-bcm-iproc.c
@@ -65,7 +65,7 @@ static void mdio_mux_iproc_config(struct iproc_mdiomux_desc *md)
 	writel(val, md->base + MDIO_SCAN_CTRL_OFFSET);
 
 	if (md->core_clk) {
-		/* use rate adjust regs to derrive the mdio's operating
+		/* use rate adjust regs to derive the mdio's operating
 		 * frequency from the specified core clock
 		 */
 		divisor = clk_get_rate(md->core_clk) / MDIO_OPERATING_FREQUENCY;
@@ -187,7 +187,9 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	md->dev = &pdev->dev;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	md->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+	if (IS_ERR(md->base))
+		return PTR_ERR(md->base);
 	if (res->start & 0xfff) {
 		/* For backward compatibility in case the
 		 * base address is specified with an offset.
@@ -196,9 +198,6 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 		res->start &= ~0xfff;
 		res->end = res->start + MDIO_REG_ADDR_SPACE_SIZE - 1;
 	}
-	md->base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(md->base))
-		return PTR_ERR(md->base);
 
 	md->mii_bus = devm_mdiobus_alloc(&pdev->dev);
 	if (!md->mii_bus) {
diff --git a/drivers/net/mdio/mdio-mux-meson-g12a.c b/drivers/net/mdio/mdio-mux-meson-g12a.c
index bf86c9c7a288..b8866bc3f2e8 100644
--- a/drivers/net/mdio/mdio-mux-meson-g12a.c
+++ b/drivers/net/mdio/mdio-mux-meson-g12a.c
@@ -95,7 +95,7 @@ static int g12a_ephy_pll_enable(struct clk_hw *hw)
 
 	/* Poll on the digital lock instead of the usual analog lock
 	 * This is done because bit 31 is unreliable on some SoC. Bit
-	 * 31 may indicate that the PLL is not lock eventhough the clock
+	 * 31 may indicate that the PLL is not lock even though the clock
 	 * is actually running
 	 */
 	return readl_poll_timeout(pll->base + ETH_PLL_CTL0, val,
diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c
index 094494a68ddf..9e3c815a070f 100644
--- a/drivers/net/mdio/of_mdio.c
+++ b/drivers/net/mdio/of_mdio.c
@@ -10,6 +10,7 @@
 
 #include <linux/device.h>
 #include <linux/err.h>
+#include <linux/fwnode_mdio.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
@@ -29,128 +30,28 @@ MODULE_LICENSE("GPL");
  * ethernet-phy-idAAAA.BBBB */
 static int of_get_phy_id(struct device_node *device, u32 *phy_id)
 {
-	struct property *prop;
-	const char *cp;
-	unsigned int upper, lower;
-
-	of_property_for_each_string(device, "compatible", prop, cp) {
-		if (sscanf(cp, "ethernet-phy-id%4x.%4x", &upper, &lower) == 2) {
-			*phy_id = ((upper & 0xFFFF) << 16) | (lower & 0xFFFF);
-			return 0;
-		}
-	}
-	return -EINVAL;
-}
-
-static struct mii_timestamper *of_find_mii_timestamper(struct device_node *node)
-{
-	struct of_phandle_args arg;
-	int err;
-
-	err = of_parse_phandle_with_fixed_args(node, "timestamper", 1, 0, &arg);
-
-	if (err == -ENOENT)
-		return NULL;
-	else if (err)
-		return ERR_PTR(err);
-
-	if (arg.args_count != 1)
-		return ERR_PTR(-EINVAL);
-
-	return register_mii_timestamper(arg.np, arg.args[0]);
+	return fwnode_get_phy_id(of_fwnode_handle(device), phy_id);
 }
 
 int of_mdiobus_phy_device_register(struct mii_bus *mdio, struct phy_device *phy,
-			      struct device_node *child, u32 addr)
+				   struct device_node *child, u32 addr)
 {
-	int rc;
-
-	rc = of_irq_get(child, 0);
-	if (rc == -EPROBE_DEFER)
-		return rc;
-
-	if (rc > 0) {
-		phy->irq = rc;
-		mdio->irq[addr] = rc;
-	} else {
-		phy->irq = mdio->irq[addr];
-	}
-
-	if (of_property_read_bool(child, "broken-turn-around"))
-		mdio->phy_ignore_ta_mask |= 1 << addr;
-
-	of_property_read_u32(child, "reset-assert-us",
-			     &phy->mdio.reset_assert_delay);
-	of_property_read_u32(child, "reset-deassert-us",
-			     &phy->mdio.reset_deassert_delay);
-
-	/* Associate the OF node with the device structure so it
-	 * can be looked up later */
-	of_node_get(child);
-	phy->mdio.dev.of_node = child;
-	phy->mdio.dev.fwnode = of_fwnode_handle(child);
-
-	/* All data is now stored in the phy struct;
-	 * register it */
-	rc = phy_device_register(phy);
-	if (rc) {
-		of_node_put(child);
-		return rc;
-	}
-
-	dev_dbg(&mdio->dev, "registered phy %pOFn at address %i\n",
-		child, addr);
-	return 0;
+	return fwnode_mdiobus_phy_device_register(mdio, phy,
+						  of_fwnode_handle(child),
+						  addr);
 }
 EXPORT_SYMBOL(of_mdiobus_phy_device_register);
 
 static int of_mdiobus_register_phy(struct mii_bus *mdio,
 				    struct device_node *child, u32 addr)
 {
-	struct mii_timestamper *mii_ts;
-	struct phy_device *phy;
-	bool is_c45;
-	int rc;
-	u32 phy_id;
-
-	mii_ts = of_find_mii_timestamper(child);
-	if (IS_ERR(mii_ts))
-		return PTR_ERR(mii_ts);
-
-	is_c45 = of_device_is_compatible(child,
-					 "ethernet-phy-ieee802.3-c45");
-
-	if (!is_c45 && !of_get_phy_id(child, &phy_id))
-		phy = phy_device_create(mdio, addr, phy_id, 0, NULL);
-	else
-		phy = get_phy_device(mdio, addr, is_c45);
-	if (IS_ERR(phy)) {
-		if (mii_ts)
-			unregister_mii_timestamper(mii_ts);
-		return PTR_ERR(phy);
-	}
-
-	rc = of_mdiobus_phy_device_register(mdio, phy, child, addr);
-	if (rc) {
-		if (mii_ts)
-			unregister_mii_timestamper(mii_ts);
-		phy_device_free(phy);
-		return rc;
-	}
-
-	/* phy->mii_ts may already be defined by the PHY driver. A
-	 * mii_timestamper probed via the device tree will still have
-	 * precedence.
-	 */
-	if (mii_ts)
-		phy->mii_ts = mii_ts;
-
-	return 0;
+	return fwnode_mdiobus_register_phy(mdio, of_fwnode_handle(child), addr);
 }
 
 static int of_mdiobus_register_device(struct mii_bus *mdio,
 				      struct device_node *child, u32 addr)
 {
+	struct fwnode_handle *fwnode = of_fwnode_handle(child);
 	struct mdio_device *mdiodev;
 	int rc;
 
@@ -161,9 +62,8 @@ static int of_mdiobus_register_device(struct mii_bus *mdio,
 	/* Associate the OF node with the device structure so it
 	 * can be looked up later.
 	 */
-	of_node_get(child);
-	mdiodev->dev.of_node = child;
-	mdiodev->dev.fwnode = of_fwnode_handle(child);
+	fwnode_handle_get(fwnode);
+	device_set_node(&mdiodev->dev, fwnode);
 
 	/* All data is now stored in the mdiodev struct; register it. */
 	rc = mdio_device_register(mdiodev);
@@ -262,8 +162,7 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 	 * the device tree are populated after the bus has been registered */
 	mdio->phy_mask = ~0;
 
-	mdio->dev.of_node = np;
-	mdio->dev.fwnode = of_fwnode_handle(np);
+	device_set_node(&mdio->dev, of_fwnode_handle(np));
 
 	/* Get bus level PHY reset GPIO details */
 	mdio->reset_delay_us = DEFAULT_GPIO_RESET_DELAY;
@@ -347,16 +246,7 @@ EXPORT_SYMBOL(of_mdiobus_register);
  */
 struct mdio_device *of_mdio_find_device(struct device_node *np)
 {
-	struct device *d;
-
-	if (!np)
-		return NULL;
-
-	d = bus_find_device_by_of_node(&mdio_bus_type, np);
-	if (!d)
-		return NULL;
-
-	return to_mdio_device(d);
+	return fwnode_mdio_find_device(of_fwnode_handle(np));
 }
 EXPORT_SYMBOL(of_mdio_find_device);
 
@@ -369,18 +259,7 @@ EXPORT_SYMBOL(of_mdio_find_device);
  */
 struct phy_device *of_phy_find_device(struct device_node *phy_np)
 {
-	struct mdio_device *mdiodev;
-
-	mdiodev = of_mdio_find_device(phy_np);
-	if (!mdiodev)
-		return NULL;
-
-	if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY)
-		return to_phy_device(&mdiodev->dev);
-
-	put_device(&mdiodev->dev);
-
-	return NULL;
+	return fwnode_phy_find_device(of_fwnode_handle(phy_np));
 }
 EXPORT_SYMBOL(of_phy_find_device);
 
@@ -466,7 +345,7 @@ EXPORT_SYMBOL(of_phy_get_and_connect);
  * of_phy_is_fixed_link() and of_phy_register_fixed_link() must
  * support two DT bindings:
  * - the old DT binding, where 'fixed-link' was a property with 5
- *   cells encoding various informations about the fixed PHY
+ *   cells encoding various information about the fixed PHY
  * - the new DT binding, where 'fixed-link' is a sub-node of the
  *   Ethernet device.
  */
diff --git a/drivers/net/mhi/net.c b/drivers/net/mhi/net.c
index b806f2f8f859..6aa753387372 100644
--- a/drivers/net/mhi/net.c
+++ b/drivers/net/mhi/net.c
@@ -11,6 +11,7 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/u64_stats_sync.h>
+#include <linux/wwan.h>
 
 #include "mhi.h"
 
@@ -18,6 +19,12 @@
 #define MHI_NET_MAX_MTU		0xffff
 #define MHI_NET_DEFAULT_MTU	0x4000
 
+/* When set to false, the default netdev (link 0) is not created, and it's up
+ * to user to create the link (via wwan rtnetlink).
+ */
+static bool create_default_iface = true;
+module_param(create_default_iface, bool, 0);
+
 struct mhi_device_info {
 	const char *netname;
 	const struct mhi_net_proto *proto;
@@ -295,32 +302,33 @@ static void mhi_net_rx_refill_work(struct work_struct *work)
 		schedule_delayed_work(&mhi_netdev->rx_refill, HZ / 2);
 }
 
-static struct device_type wwan_type = {
-	.name = "wwan",
-};
-
-static int mhi_net_probe(struct mhi_device *mhi_dev,
-			 const struct mhi_device_id *id)
+static int mhi_net_newlink(void *ctxt, struct net_device *ndev, u32 if_id,
+			   struct netlink_ext_ack *extack)
 {
-	const struct mhi_device_info *info = (struct mhi_device_info *)id->driver_data;
-	struct device *dev = &mhi_dev->dev;
+	const struct mhi_device_info *info;
+	struct mhi_device *mhi_dev = ctxt;
 	struct mhi_net_dev *mhi_netdev;
-	struct net_device *ndev;
 	int err;
 
-	ndev = alloc_netdev(sizeof(*mhi_netdev), info->netname,
-			    NET_NAME_PREDICTABLE, mhi_net_setup);
-	if (!ndev)
-		return -ENOMEM;
+	info = (struct mhi_device_info *)mhi_dev->id->driver_data;
+
+	/* For now we only support one link (link context 0), driver must be
+	 * reworked to break 1:1 relationship for net MBIM and to forward setup
+	 * call to rmnet(QMAP) otherwise.
+	 */
+	if (if_id != 0)
+		return -EINVAL;
+
+	if (dev_get_drvdata(&mhi_dev->dev))
+		return -EBUSY;
 
 	mhi_netdev = netdev_priv(ndev);
-	dev_set_drvdata(dev, mhi_netdev);
+
+	dev_set_drvdata(&mhi_dev->dev, mhi_netdev);
 	mhi_netdev->ndev = ndev;
 	mhi_netdev->mdev = mhi_dev;
 	mhi_netdev->skbagg_head = NULL;
 	mhi_netdev->proto = info->proto;
-	SET_NETDEV_DEV(ndev, &mhi_dev->dev);
-	SET_NETDEV_DEVTYPE(ndev, &wwan_type);
 
 	INIT_DELAYED_WORK(&mhi_netdev->rx_refill, mhi_net_rx_refill_work);
 	u64_stats_init(&mhi_netdev->stats.rx_syncp);
@@ -334,7 +342,10 @@ static int mhi_net_probe(struct mhi_device *mhi_dev,
 	/* Number of transfer descriptors determines size of the queue */
 	mhi_netdev->rx_queue_sz = mhi_get_free_desc_count(mhi_dev, DMA_FROM_DEVICE);
 
-	err = register_netdev(ndev);
+	if (extack)
+		err = register_netdevice(ndev);
+	else
+		err = register_netdev(ndev);
 	if (err)
 		goto out_err;
 
@@ -347,23 +358,89 @@ static int mhi_net_probe(struct mhi_device *mhi_dev,
 	return 0;
 
 out_err_proto:
-	unregister_netdev(ndev);
+	unregister_netdevice(ndev);
 out_err:
 	free_netdev(ndev);
 	return err;
 }
 
-static void mhi_net_remove(struct mhi_device *mhi_dev)
+static void mhi_net_dellink(void *ctxt, struct net_device *ndev,
+			    struct list_head *head)
 {
-	struct mhi_net_dev *mhi_netdev = dev_get_drvdata(&mhi_dev->dev);
+	struct mhi_net_dev *mhi_netdev = netdev_priv(ndev);
+	struct mhi_device *mhi_dev = ctxt;
 
-	unregister_netdev(mhi_netdev->ndev);
+	if (head)
+		unregister_netdevice_queue(ndev, head);
+	else
+		unregister_netdev(ndev);
 
-	mhi_unprepare_from_transfer(mhi_netdev->mdev);
+	mhi_unprepare_from_transfer(mhi_dev);
 
 	kfree_skb(mhi_netdev->skbagg_head);
 
-	free_netdev(mhi_netdev->ndev);
+	dev_set_drvdata(&mhi_dev->dev, NULL);
+}
+
+static const struct wwan_ops mhi_wwan_ops = {
+	.owner = THIS_MODULE,
+	.priv_size = sizeof(struct mhi_net_dev),
+	.setup = mhi_net_setup,
+	.newlink = mhi_net_newlink,
+	.dellink = mhi_net_dellink,
+};
+
+static int mhi_net_probe(struct mhi_device *mhi_dev,
+			 const struct mhi_device_id *id)
+{
+	const struct mhi_device_info *info = (struct mhi_device_info *)id->driver_data;
+	struct mhi_controller *cntrl = mhi_dev->mhi_cntrl;
+	struct net_device *ndev;
+	int err;
+
+	err = wwan_register_ops(&cntrl->mhi_dev->dev, &mhi_wwan_ops, mhi_dev);
+	if (err)
+		return err;
+
+	if (!create_default_iface)
+		return 0;
+
+	/* Create a default interface which is used as either RMNET real-dev,
+	 * MBIM link 0 or ip link 0)
+	 */
+	ndev = alloc_netdev(sizeof(struct mhi_net_dev), info->netname,
+			    NET_NAME_PREDICTABLE, mhi_net_setup);
+	if (!ndev) {
+		err = -ENOMEM;
+		goto err_unregister;
+	}
+
+	SET_NETDEV_DEV(ndev, &mhi_dev->dev);
+
+	err = mhi_net_newlink(mhi_dev, ndev, 0, NULL);
+	if (err)
+		goto err_release;
+
+	return 0;
+
+err_release:
+	free_netdev(ndev);
+err_unregister:
+	wwan_unregister_ops(&cntrl->mhi_dev->dev);
+
+	return err;
+}
+
+static void mhi_net_remove(struct mhi_device *mhi_dev)
+{
+	struct mhi_net_dev *mhi_netdev = dev_get_drvdata(&mhi_dev->dev);
+	struct mhi_controller *cntrl = mhi_dev->mhi_cntrl;
+
+	/* rtnetlink takes care of removing remaining links */
+	wwan_unregister_ops(&cntrl->mhi_dev->dev);
+
+	if (create_default_iface)
+		mhi_net_dellink(mhi_dev, mhi_netdev->ndev, NULL);
 }
 
 static const struct mhi_device_info mhi_hwip0 = {
diff --git a/drivers/net/mii.c b/drivers/net/mii.c
index e71ebb933266..779c3a96dba7 100644
--- a/drivers/net/mii.c
+++ b/drivers/net/mii.c
@@ -81,7 +81,7 @@ int mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd)
 	bmcr = mii->mdio_read(dev, mii->phy_id, MII_BMCR);
 	bmsr = mii->mdio_read(dev, mii->phy_id, MII_BMSR);
 	if (mii->supports_gmii) {
- 		ctrl1000 = mii->mdio_read(dev, mii->phy_id, MII_CTRL1000);
+		ctrl1000 = mii->mdio_read(dev, mii->phy_id, MII_CTRL1000);
 		stat1000 = mii->mdio_read(dev, mii->phy_id, MII_STAT1000);
 	}
 
diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c
index 0e9511661601..ccec29970d5b 100644
--- a/drivers/net/netdevsim/bus.c
+++ b/drivers/net/netdevsim/bus.c
@@ -27,21 +27,34 @@ static struct nsim_bus_dev *to_nsim_bus_dev(struct device *dev)
 static int nsim_bus_dev_vfs_enable(struct nsim_bus_dev *nsim_bus_dev,
 				   unsigned int num_vfs)
 {
-	nsim_bus_dev->vfconfigs = kcalloc(num_vfs,
-					  sizeof(struct nsim_vf_config),
-					  GFP_KERNEL | __GFP_NOWARN);
+	struct nsim_dev *nsim_dev;
+	int err = 0;
+
+	if (nsim_bus_dev->max_vfs < num_vfs)
+		return -ENOMEM;
+
 	if (!nsim_bus_dev->vfconfigs)
 		return -ENOMEM;
 	nsim_bus_dev->num_vfs = num_vfs;
 
-	return 0;
+	nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev);
+	if (nsim_esw_mode_is_switchdev(nsim_dev)) {
+		err = nsim_esw_switchdev_enable(nsim_dev, NULL);
+		if (err)
+			nsim_bus_dev->num_vfs = 0;
+	}
+
+	return err;
 }
 
-static void nsim_bus_dev_vfs_disable(struct nsim_bus_dev *nsim_bus_dev)
+void nsim_bus_dev_vfs_disable(struct nsim_bus_dev *nsim_bus_dev)
 {
-	kfree(nsim_bus_dev->vfconfigs);
-	nsim_bus_dev->vfconfigs = NULL;
+	struct nsim_dev *nsim_dev;
+
 	nsim_bus_dev->num_vfs = 0;
+	nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev);
+	if (nsim_esw_mode_is_switchdev(nsim_dev))
+		nsim_esw_legacy_enable(nsim_dev, NULL);
 }
 
 static ssize_t
@@ -56,7 +69,7 @@ nsim_bus_dev_numvfs_store(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
-	rtnl_lock();
+	mutex_lock(&nsim_bus_dev->vfs_lock);
 	if (nsim_bus_dev->num_vfs == num_vfs)
 		goto exit_good;
 	if (nsim_bus_dev->num_vfs && num_vfs) {
@@ -74,7 +87,7 @@ nsim_bus_dev_numvfs_store(struct device *dev, struct device_attribute *attr,
 exit_good:
 	ret = count;
 exit_unlock:
-	rtnl_unlock();
+	mutex_unlock(&nsim_bus_dev->vfs_lock);
 
 	return ret;
 }
@@ -92,6 +105,79 @@ static struct device_attribute nsim_bus_dev_numvfs_attr =
 	__ATTR(sriov_numvfs, 0664, nsim_bus_dev_numvfs_show,
 	       nsim_bus_dev_numvfs_store);
 
+ssize_t nsim_bus_dev_max_vfs_read(struct file *file,
+				  char __user *data,
+				  size_t count, loff_t *ppos)
+{
+	struct nsim_bus_dev *nsim_bus_dev = file->private_data;
+	char buf[11];
+	ssize_t len;
+
+	len = snprintf(buf, sizeof(buf), "%u\n", nsim_bus_dev->max_vfs);
+	if (len < 0)
+		return len;
+
+	return simple_read_from_buffer(data, count, ppos, buf, len);
+}
+
+ssize_t nsim_bus_dev_max_vfs_write(struct file *file,
+				   const char __user *data,
+				   size_t count, loff_t *ppos)
+{
+	struct nsim_bus_dev *nsim_bus_dev = file->private_data;
+	struct nsim_vf_config *vfconfigs;
+	ssize_t ret;
+	char buf[10];
+	u32 val;
+
+	if (*ppos != 0)
+		return 0;
+
+	if (count >= sizeof(buf))
+		return -ENOSPC;
+
+	mutex_lock(&nsim_bus_dev->vfs_lock);
+	/* Reject if VFs are configured */
+	if (nsim_bus_dev->num_vfs) {
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	ret = copy_from_user(buf, data, count);
+	if (ret) {
+		ret = -EFAULT;
+		goto unlock;
+	}
+
+	buf[count] = '\0';
+	ret = kstrtouint(buf, 10, &val);
+	if (ret) {
+		ret = -EIO;
+		goto unlock;
+	}
+
+	/* max_vfs limited by the maximum number of provided port indexes */
+	if (val > NSIM_DEV_VF_PORT_INDEX_MAX - NSIM_DEV_VF_PORT_INDEX_BASE) {
+		ret = -ERANGE;
+		goto unlock;
+	}
+
+	vfconfigs = kcalloc(val, sizeof(struct nsim_vf_config), GFP_KERNEL | __GFP_NOWARN);
+	if (!vfconfigs) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	kfree(nsim_bus_dev->vfconfigs);
+	nsim_bus_dev->vfconfigs = vfconfigs;
+	nsim_bus_dev->max_vfs = val;
+	*ppos += count;
+	ret = count;
+unlock:
+	mutex_unlock(&nsim_bus_dev->vfs_lock);
+	return ret;
+}
+
 static ssize_t
 new_port_store(struct device *dev, struct device_attribute *attr,
 	       const char *buf, size_t count)
@@ -113,7 +199,7 @@ new_port_store(struct device *dev, struct device_attribute *attr,
 
 	mutex_lock(&nsim_bus_dev->nsim_bus_reload_lock);
 	devlink_reload_disable(devlink);
-	ret = nsim_dev_port_add(nsim_bus_dev, port_index);
+	ret = nsim_dev_port_add(nsim_bus_dev, NSIM_DEV_PORT_TYPE_PF, port_index);
 	devlink_reload_enable(devlink);
 	mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock);
 	return ret ? ret : count;
@@ -142,7 +228,7 @@ del_port_store(struct device *dev, struct device_attribute *attr,
 
 	mutex_lock(&nsim_bus_dev->nsim_bus_reload_lock);
 	devlink_reload_disable(devlink);
-	ret = nsim_dev_port_del(nsim_bus_dev, port_index);
+	ret = nsim_dev_port_del(nsim_bus_dev, NSIM_DEV_PORT_TYPE_PF, port_index);
 	devlink_reload_enable(devlink);
 	mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock);
 	return ret ? ret : count;
@@ -168,9 +254,6 @@ static const struct attribute_group *nsim_bus_dev_attr_groups[] = {
 
 static void nsim_bus_dev_release(struct device *dev)
 {
-	struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev);
-
-	nsim_bus_dev_vfs_disable(nsim_bus_dev);
 }
 
 static struct device_type nsim_bus_dev_type = {
@@ -311,6 +394,8 @@ static struct bus_type nsim_bus = {
 	.num_vf		= nsim_num_vf,
 };
 
+#define NSIM_BUS_DEV_MAX_VFS 4
+
 static struct nsim_bus_dev *
 nsim_bus_dev_new(unsigned int id, unsigned int port_count)
 {
@@ -329,15 +414,28 @@ nsim_bus_dev_new(unsigned int id, unsigned int port_count)
 	nsim_bus_dev->dev.type = &nsim_bus_dev_type;
 	nsim_bus_dev->port_count = port_count;
 	nsim_bus_dev->initial_net = current->nsproxy->net_ns;
+	nsim_bus_dev->max_vfs = NSIM_BUS_DEV_MAX_VFS;
 	mutex_init(&nsim_bus_dev->nsim_bus_reload_lock);
+	mutex_init(&nsim_bus_dev->vfs_lock);
 	/* Disallow using nsim_bus_dev */
 	smp_store_release(&nsim_bus_dev->init, false);
 
+	nsim_bus_dev->vfconfigs = kcalloc(nsim_bus_dev->max_vfs,
+					  sizeof(struct nsim_vf_config),
+					  GFP_KERNEL | __GFP_NOWARN);
+	if (!nsim_bus_dev->vfconfigs) {
+		err = -ENOMEM;
+		goto err_nsim_bus_dev_id_free;
+	}
+
 	err = device_register(&nsim_bus_dev->dev);
 	if (err)
-		goto err_nsim_bus_dev_id_free;
+		goto err_nsim_vfs_free;
+
 	return nsim_bus_dev;
 
+err_nsim_vfs_free:
+	kfree(nsim_bus_dev->vfconfigs);
 err_nsim_bus_dev_id_free:
 	ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id);
 err_nsim_bus_dev_free:
@@ -351,6 +449,7 @@ static void nsim_bus_dev_del(struct nsim_bus_dev *nsim_bus_dev)
 	smp_store_release(&nsim_bus_dev->init, false);
 	device_unregister(&nsim_bus_dev->dev);
 	ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id);
+	kfree(nsim_bus_dev->vfconfigs);
 	kfree(nsim_bus_dev);
 }
 
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 6189a4c0d39e..6348307bfa84 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -35,6 +35,25 @@
 
 #include "netdevsim.h"
 
+static unsigned int
+nsim_dev_port_index(enum nsim_dev_port_type type, unsigned int port_index)
+{
+	switch (type) {
+	case NSIM_DEV_PORT_TYPE_VF:
+		port_index = NSIM_DEV_VF_PORT_INDEX_BASE + port_index;
+		break;
+	case NSIM_DEV_PORT_TYPE_PF:
+		break;
+	}
+
+	return port_index;
+}
+
+static inline unsigned int nsim_dev_port_index_to_vf_index(unsigned int port_index)
+{
+	return port_index - NSIM_DEV_VF_PORT_INDEX_BASE;
+}
+
 static struct dentry *nsim_dev_ddir;
 
 #define NSIM_DEV_DUMMY_REGION_SIZE (1024 * 32)
@@ -192,9 +211,18 @@ static const struct file_operations nsim_dev_trap_fa_cookie_fops = {
 	.owner = THIS_MODULE,
 };
 
+static const struct file_operations nsim_dev_max_vfs_fops = {
+	.open = simple_open,
+	.read = nsim_bus_dev_max_vfs_read,
+	.write = nsim_bus_dev_max_vfs_write,
+	.llseek = generic_file_llseek,
+	.owner = THIS_MODULE,
+};
+
 static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
 {
 	char dev_ddir_name[sizeof(DRV_NAME) + 10];
+	int err;
 
 	sprintf(dev_ddir_name, DRV_NAME "%u", nsim_dev->nsim_bus_dev->dev.id);
 	nsim_dev->ddir = debugfs_create_dir(dev_ddir_name, nsim_dev_ddir);
@@ -231,30 +259,84 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
 	debugfs_create_bool("fail_trap_policer_counter_get", 0600,
 			    nsim_dev->ddir,
 			    &nsim_dev->fail_trap_policer_counter_get);
+	nsim_dev->max_vfs = debugfs_create_file("max_vfs",
+						0600,
+						nsim_dev->ddir,
+						nsim_dev->nsim_bus_dev,
+						&nsim_dev_max_vfs_fops);
+	nsim_dev->nodes_ddir = debugfs_create_dir("rate_nodes", nsim_dev->ddir);
+	if (IS_ERR(nsim_dev->nodes_ddir)) {
+		err = PTR_ERR(nsim_dev->nodes_ddir);
+		goto err_out;
+	}
+	debugfs_create_bool("fail_trap_drop_counter_get", 0600,
+			    nsim_dev->ddir,
+			    &nsim_dev->fail_trap_drop_counter_get);
 	nsim_udp_tunnels_debugfs_create(nsim_dev);
 	return 0;
+
+err_out:
+	debugfs_remove_recursive(nsim_dev->ports_ddir);
+	debugfs_remove_recursive(nsim_dev->ddir);
+	return err;
 }
 
 static void nsim_dev_debugfs_exit(struct nsim_dev *nsim_dev)
 {
+	debugfs_remove_recursive(nsim_dev->nodes_ddir);
 	debugfs_remove_recursive(nsim_dev->ports_ddir);
 	debugfs_remove_recursive(nsim_dev->ddir);
 }
 
+static ssize_t nsim_dev_rate_parent_read(struct file *file,
+					 char __user *data,
+					 size_t count, loff_t *ppos)
+{
+	char **name_ptr = file->private_data;
+	size_t len;
+
+	if (!*name_ptr)
+		return 0;
+
+	len = strlen(*name_ptr);
+	return simple_read_from_buffer(data, count, ppos, *name_ptr, len);
+}
+
+static const struct file_operations nsim_dev_rate_parent_fops = {
+	.open = simple_open,
+	.read = nsim_dev_rate_parent_read,
+	.llseek = generic_file_llseek,
+	.owner = THIS_MODULE,
+};
+
 static int nsim_dev_port_debugfs_init(struct nsim_dev *nsim_dev,
 				      struct nsim_dev_port *nsim_dev_port)
 {
+	struct nsim_bus_dev *nsim_bus_dev = nsim_dev->nsim_bus_dev;
+	unsigned int port_index = nsim_dev_port->port_index;
 	char port_ddir_name[16];
 	char dev_link_name[32];
 
-	sprintf(port_ddir_name, "%u", nsim_dev_port->port_index);
+	sprintf(port_ddir_name, "%u", port_index);
 	nsim_dev_port->ddir = debugfs_create_dir(port_ddir_name,
 						 nsim_dev->ports_ddir);
 	if (IS_ERR(nsim_dev_port->ddir))
 		return PTR_ERR(nsim_dev_port->ddir);
 
-	sprintf(dev_link_name, "../../../" DRV_NAME "%u",
-		nsim_dev->nsim_bus_dev->dev.id);
+	sprintf(dev_link_name, "../../../" DRV_NAME "%u", nsim_bus_dev->dev.id);
+	if (nsim_dev_port_is_vf(nsim_dev_port)) {
+		unsigned int vf_id = nsim_dev_port_index_to_vf_index(port_index);
+
+		debugfs_create_u16("tx_share", 0400, nsim_dev_port->ddir,
+				   &nsim_bus_dev->vfconfigs[vf_id].min_tx_rate);
+		debugfs_create_u16("tx_max", 0400, nsim_dev_port->ddir,
+				   &nsim_bus_dev->vfconfigs[vf_id].max_tx_rate);
+		nsim_dev_port->rate_parent = debugfs_create_file("rate_parent",
+								 0400,
+								 nsim_dev_port->ddir,
+								 &nsim_dev_port->parent_name,
+								 &nsim_dev_rate_parent_fops);
+	}
 	debugfs_create_symlink("dev", nsim_dev_port->ddir, dev_link_name);
 
 	return 0;
@@ -407,6 +489,74 @@ static void nsim_dev_dummy_region_exit(struct nsim_dev *nsim_dev)
 	devlink_region_destroy(nsim_dev->dummy_region);
 }
 
+static void __nsim_dev_port_del(struct nsim_dev_port *nsim_dev_port);
+int nsim_esw_legacy_enable(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack)
+{
+	struct devlink *devlink = priv_to_devlink(nsim_dev);
+	struct nsim_dev_port *nsim_dev_port, *tmp;
+
+	devlink_rate_nodes_destroy(devlink);
+	mutex_lock(&nsim_dev->port_list_lock);
+	list_for_each_entry_safe(nsim_dev_port, tmp, &nsim_dev->port_list, list)
+		if (nsim_dev_port_is_vf(nsim_dev_port))
+			__nsim_dev_port_del(nsim_dev_port);
+	mutex_unlock(&nsim_dev->port_list_lock);
+	nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+	return 0;
+}
+
+int nsim_esw_switchdev_enable(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack)
+{
+	struct nsim_bus_dev *nsim_bus_dev = nsim_dev->nsim_bus_dev;
+	int i, err;
+
+	for (i = 0; i < nsim_bus_dev->num_vfs; i++) {
+		err = nsim_dev_port_add(nsim_bus_dev, NSIM_DEV_PORT_TYPE_VF, i);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack, "Failed to initialize VFs' netdevsim ports");
+			pr_err("Failed to initialize VF id=%d. %d.\n", i, err);
+			goto err_port_add_vfs;
+		}
+	}
+	nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
+	return 0;
+
+err_port_add_vfs:
+	for (i--; i >= 0; i--)
+		nsim_dev_port_del(nsim_bus_dev, NSIM_DEV_PORT_TYPE_VF, i);
+	return err;
+}
+
+static int nsim_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
+					 struct netlink_ext_ack *extack)
+{
+	struct nsim_dev *nsim_dev = devlink_priv(devlink);
+	int err = 0;
+
+	mutex_lock(&nsim_dev->nsim_bus_dev->vfs_lock);
+	if (mode == nsim_dev->esw_mode)
+		goto unlock;
+
+	if (mode == DEVLINK_ESWITCH_MODE_LEGACY)
+		err = nsim_esw_legacy_enable(nsim_dev, extack);
+	else if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV)
+		err = nsim_esw_switchdev_enable(nsim_dev, extack);
+	else
+		err = -EINVAL;
+
+unlock:
+	mutex_unlock(&nsim_dev->nsim_bus_dev->vfs_lock);
+	return err;
+}
+
+static int nsim_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
+{
+	struct nsim_dev *nsim_dev = devlink_priv(devlink);
+
+	*mode = nsim_dev->esw_mode;
+	return 0;
+}
+
 struct nsim_trap_item {
 	void *trap_ctx;
 	enum devlink_trap_action action;
@@ -416,6 +566,7 @@ struct nsim_trap_data {
 	struct delayed_work trap_report_dw;
 	struct nsim_trap_item *trap_items_arr;
 	u64 *trap_policers_cnt_arr;
+	u64 trap_pkt_cnt;
 	struct nsim_dev *nsim_dev;
 	spinlock_t trap_lock;	/* Protects trap_items_arr */
 };
@@ -892,7 +1043,190 @@ nsim_dev_devlink_trap_policer_counter_get(struct devlink *devlink,
 	return 0;
 }
 
+#define NSIM_LINK_SPEED_MAX     5000 /* Mbps */
+#define NSIM_LINK_SPEED_UNIT    125000 /* 1 Mbps given in bytes/sec to avoid
+					* u64 overflow during conversion from
+					* bytes to bits.
+					*/
+
+static int nsim_rate_bytes_to_units(char *name, u64 *rate, struct netlink_ext_ack *extack)
+{
+	u64 val;
+	u32 rem;
+
+	val = div_u64_rem(*rate, NSIM_LINK_SPEED_UNIT, &rem);
+	if (rem) {
+		pr_err("%s rate value %lluBps not in link speed units of 1Mbps.\n",
+		       name, *rate);
+		NL_SET_ERR_MSG_MOD(extack, "TX rate value not in link speed units of 1Mbps.");
+		return -EINVAL;
+	}
+
+	if (val > NSIM_LINK_SPEED_MAX) {
+		pr_err("%s rate value %lluMbps exceed link maximum speed 5000Mbps.\n",
+		       name, val);
+		NL_SET_ERR_MSG_MOD(extack, "TX rate value exceed link maximum speed 5000Mbps.");
+		return -EINVAL;
+	}
+	*rate = val;
+	return 0;
+}
+
+static int nsim_leaf_tx_share_set(struct devlink_rate *devlink_rate, void *priv,
+				  u64 tx_share, struct netlink_ext_ack *extack)
+{
+	struct nsim_dev_port *nsim_dev_port = priv;
+	struct nsim_bus_dev *nsim_bus_dev = nsim_dev_port->ns->nsim_bus_dev;
+	int vf_id = nsim_dev_port_index_to_vf_index(nsim_dev_port->port_index);
+	int err;
+
+	err = nsim_rate_bytes_to_units("tx_share", &tx_share, extack);
+	if (err)
+		return err;
+
+	nsim_bus_dev->vfconfigs[vf_id].min_tx_rate = tx_share;
+	return 0;
+}
+
+static int nsim_leaf_tx_max_set(struct devlink_rate *devlink_rate, void *priv,
+				u64 tx_max, struct netlink_ext_ack *extack)
+{
+	struct nsim_dev_port *nsim_dev_port = priv;
+	struct nsim_bus_dev *nsim_bus_dev = nsim_dev_port->ns->nsim_bus_dev;
+	int vf_id = nsim_dev_port_index_to_vf_index(nsim_dev_port->port_index);
+	int err;
+
+	err = nsim_rate_bytes_to_units("tx_max", &tx_max, extack);
+	if (err)
+		return err;
+
+	nsim_bus_dev->vfconfigs[vf_id].max_tx_rate = tx_max;
+	return 0;
+}
+
+struct nsim_rate_node {
+	struct dentry *ddir;
+	struct dentry *rate_parent;
+	char *parent_name;
+	u16 tx_share;
+	u16 tx_max;
+};
+
+static int nsim_node_tx_share_set(struct devlink_rate *devlink_rate, void *priv,
+				  u64 tx_share, struct netlink_ext_ack *extack)
+{
+	struct nsim_rate_node *nsim_node = priv;
+	int err;
+
+	err = nsim_rate_bytes_to_units("tx_share", &tx_share, extack);
+	if (err)
+		return err;
+
+	nsim_node->tx_share = tx_share;
+	return 0;
+}
+
+static int nsim_node_tx_max_set(struct devlink_rate *devlink_rate, void *priv,
+				u64 tx_max, struct netlink_ext_ack *extack)
+{
+	struct nsim_rate_node *nsim_node = priv;
+	int err;
+
+	err = nsim_rate_bytes_to_units("tx_max", &tx_max, extack);
+	if (err)
+		return err;
+
+	nsim_node->tx_max = tx_max;
+	return 0;
+}
+
+static int nsim_rate_node_new(struct devlink_rate *node, void **priv,
+			      struct netlink_ext_ack *extack)
+{
+	struct nsim_dev *nsim_dev = devlink_priv(node->devlink);
+	struct nsim_rate_node *nsim_node;
+
+	if (!nsim_esw_mode_is_switchdev(nsim_dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Node creation allowed only in switchdev mode.");
+		return -EOPNOTSUPP;
+	}
+
+	nsim_node = kzalloc(sizeof(*nsim_node), GFP_KERNEL);
+	if (!nsim_node)
+		return -ENOMEM;
+
+	nsim_node->ddir = debugfs_create_dir(node->name, nsim_dev->nodes_ddir);
+
+	debugfs_create_u16("tx_share", 0400, nsim_node->ddir, &nsim_node->tx_share);
+	debugfs_create_u16("tx_max", 0400, nsim_node->ddir, &nsim_node->tx_max);
+	nsim_node->rate_parent = debugfs_create_file("rate_parent", 0400,
+						     nsim_node->ddir,
+						     &nsim_node->parent_name,
+						     &nsim_dev_rate_parent_fops);
+
+	*priv = nsim_node;
+	return 0;
+}
+
+static int nsim_rate_node_del(struct devlink_rate *node, void *priv,
+			      struct netlink_ext_ack *extack)
+{
+	struct nsim_rate_node *nsim_node = priv;
+
+	debugfs_remove(nsim_node->rate_parent);
+	debugfs_remove_recursive(nsim_node->ddir);
+	kfree(nsim_node);
+	return 0;
+}
+
+static int nsim_rate_leaf_parent_set(struct devlink_rate *child,
+				     struct devlink_rate *parent,
+				     void *priv_child, void *priv_parent,
+				     struct netlink_ext_ack *extack)
+{
+	struct nsim_dev_port *nsim_dev_port = priv_child;
+
+	if (parent)
+		nsim_dev_port->parent_name = parent->name;
+	else
+		nsim_dev_port->parent_name = NULL;
+	return 0;
+}
+
+static int nsim_rate_node_parent_set(struct devlink_rate *child,
+				     struct devlink_rate *parent,
+				     void *priv_child, void *priv_parent,
+				     struct netlink_ext_ack *extack)
+{
+	struct nsim_rate_node *nsim_node = priv_child;
+
+	if (parent)
+		nsim_node->parent_name = parent->name;
+	else
+		nsim_node->parent_name = NULL;
+	return 0;
+}
+
+static int
+nsim_dev_devlink_trap_drop_counter_get(struct devlink *devlink,
+				       const struct devlink_trap *trap,
+				       u64 *p_drops)
+{
+	struct nsim_dev *nsim_dev = devlink_priv(devlink);
+	u64 *cnt;
+
+	if (nsim_dev->fail_trap_drop_counter_get)
+		return -EINVAL;
+
+	cnt = &nsim_dev->trap_data->trap_pkt_cnt;
+	*p_drops = (*cnt)++;
+
+	return 0;
+}
+
 static const struct devlink_ops nsim_dev_devlink_ops = {
+	.eswitch_mode_set = nsim_devlink_eswitch_mode_set,
+	.eswitch_mode_get = nsim_devlink_eswitch_mode_get,
 	.supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT |
 					 DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK,
 	.reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT),
@@ -905,32 +1239,52 @@ static const struct devlink_ops nsim_dev_devlink_ops = {
 	.trap_group_set = nsim_dev_devlink_trap_group_set,
 	.trap_policer_set = nsim_dev_devlink_trap_policer_set,
 	.trap_policer_counter_get = nsim_dev_devlink_trap_policer_counter_get,
+	.rate_leaf_tx_share_set = nsim_leaf_tx_share_set,
+	.rate_leaf_tx_max_set = nsim_leaf_tx_max_set,
+	.rate_node_tx_share_set = nsim_node_tx_share_set,
+	.rate_node_tx_max_set = nsim_node_tx_max_set,
+	.rate_node_new = nsim_rate_node_new,
+	.rate_node_del = nsim_rate_node_del,
+	.rate_leaf_parent_set = nsim_rate_leaf_parent_set,
+	.rate_node_parent_set = nsim_rate_node_parent_set,
+	.trap_drop_counter_get = nsim_dev_devlink_trap_drop_counter_get,
 };
 
 #define NSIM_DEV_MAX_MACS_DEFAULT 32
 #define NSIM_DEV_TEST1_DEFAULT true
 
-static int __nsim_dev_port_add(struct nsim_dev *nsim_dev,
+static int __nsim_dev_port_add(struct nsim_dev *nsim_dev, enum nsim_dev_port_type type,
 			       unsigned int port_index)
 {
+	struct nsim_bus_dev *nsim_bus_dev = nsim_dev->nsim_bus_dev;
 	struct devlink_port_attrs attrs = {};
 	struct nsim_dev_port *nsim_dev_port;
 	struct devlink_port *devlink_port;
 	int err;
 
+	if (type == NSIM_DEV_PORT_TYPE_VF && !nsim_bus_dev->num_vfs)
+		return -EINVAL;
+
 	nsim_dev_port = kzalloc(sizeof(*nsim_dev_port), GFP_KERNEL);
 	if (!nsim_dev_port)
 		return -ENOMEM;
-	nsim_dev_port->port_index = port_index;
+	nsim_dev_port->port_index = nsim_dev_port_index(type, port_index);
+	nsim_dev_port->port_type = type;
 
 	devlink_port = &nsim_dev_port->devlink_port;
-	attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
-	attrs.phys.port_number = port_index + 1;
+	if (nsim_dev_port_is_pf(nsim_dev_port)) {
+		attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
+		attrs.phys.port_number = port_index + 1;
+	} else {
+		attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF;
+		attrs.pci_vf.pf = 0;
+		attrs.pci_vf.vf = port_index;
+	}
 	memcpy(attrs.switch_id.id, nsim_dev->switch_id.id, nsim_dev->switch_id.id_len);
 	attrs.switch_id.id_len = nsim_dev->switch_id.id_len;
 	devlink_port_attrs_set(devlink_port, &attrs);
 	err = devlink_port_register(priv_to_devlink(nsim_dev), devlink_port,
-				    port_index);
+				    nsim_dev_port->port_index);
 	if (err)
 		goto err_port_free;
 
@@ -944,11 +1298,20 @@ static int __nsim_dev_port_add(struct nsim_dev *nsim_dev,
 		goto err_port_debugfs_exit;
 	}
 
+	if (nsim_dev_port_is_vf(nsim_dev_port)) {
+		err = devlink_rate_leaf_create(&nsim_dev_port->devlink_port,
+					       nsim_dev_port);
+		if (err)
+			goto err_nsim_destroy;
+	}
+
 	devlink_port_type_eth_set(devlink_port, nsim_dev_port->ns->netdev);
 	list_add(&nsim_dev_port->list, &nsim_dev->port_list);
 
 	return 0;
 
+err_nsim_destroy:
+	nsim_destroy(nsim_dev_port->ns);
 err_port_debugfs_exit:
 	nsim_dev_port_debugfs_exit(nsim_dev_port);
 err_dl_port_unregister:
@@ -963,6 +1326,8 @@ static void __nsim_dev_port_del(struct nsim_dev_port *nsim_dev_port)
 	struct devlink_port *devlink_port = &nsim_dev_port->devlink_port;
 
 	list_del(&nsim_dev_port->list);
+	if (nsim_dev_port_is_vf(nsim_dev_port))
+		devlink_rate_leaf_destroy(&nsim_dev_port->devlink_port);
 	devlink_port_type_clear(devlink_port);
 	nsim_destroy(nsim_dev_port->ns);
 	nsim_dev_port_debugfs_exit(nsim_dev_port);
@@ -987,7 +1352,7 @@ static int nsim_dev_port_add_all(struct nsim_dev *nsim_dev,
 	int i, err;
 
 	for (i = 0; i < port_count; i++) {
-		err = __nsim_dev_port_add(nsim_dev, i);
+		err = __nsim_dev_port_add(nsim_dev, NSIM_DEV_PORT_TYPE_PF, i);
 		if (err)
 			goto err_port_del_all;
 	}
@@ -1134,6 +1499,7 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev)
 
 	devlink_params_publish(devlink);
 	devlink_reload_enable(devlink);
+	nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_LEGACY;
 	return 0;
 
 err_psample_exit:
@@ -1169,6 +1535,12 @@ static void nsim_dev_reload_destroy(struct nsim_dev *nsim_dev)
 	if (devlink_is_reload_failed(devlink))
 		return;
 	debugfs_remove(nsim_dev->take_snapshot);
+
+	mutex_lock(&nsim_dev->nsim_bus_dev->vfs_lock);
+	if (nsim_dev->nsim_bus_dev->num_vfs)
+		nsim_bus_dev_vfs_disable(nsim_dev->nsim_bus_dev);
+	mutex_unlock(&nsim_dev->nsim_bus_dev->vfs_lock);
+
 	nsim_dev_port_del_all(nsim_dev);
 	nsim_dev_psample_exit(nsim_dev);
 	nsim_dev_health_exit(nsim_dev);
@@ -1197,32 +1569,34 @@ void nsim_dev_remove(struct nsim_bus_dev *nsim_bus_dev)
 }
 
 static struct nsim_dev_port *
-__nsim_dev_port_lookup(struct nsim_dev *nsim_dev, unsigned int port_index)
+__nsim_dev_port_lookup(struct nsim_dev *nsim_dev, enum nsim_dev_port_type type,
+		       unsigned int port_index)
 {
 	struct nsim_dev_port *nsim_dev_port;
 
+	port_index = nsim_dev_port_index(type, port_index);
 	list_for_each_entry(nsim_dev_port, &nsim_dev->port_list, list)
 		if (nsim_dev_port->port_index == port_index)
 			return nsim_dev_port;
 	return NULL;
 }
 
-int nsim_dev_port_add(struct nsim_bus_dev *nsim_bus_dev,
+int nsim_dev_port_add(struct nsim_bus_dev *nsim_bus_dev, enum nsim_dev_port_type type,
 		      unsigned int port_index)
 {
 	struct nsim_dev *nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev);
 	int err;
 
 	mutex_lock(&nsim_dev->port_list_lock);
-	if (__nsim_dev_port_lookup(nsim_dev, port_index))
+	if (__nsim_dev_port_lookup(nsim_dev, type, port_index))
 		err = -EEXIST;
 	else
-		err = __nsim_dev_port_add(nsim_dev, port_index);
+		err = __nsim_dev_port_add(nsim_dev, type, port_index);
 	mutex_unlock(&nsim_dev->port_list_lock);
 	return err;
 }
 
-int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev,
+int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev, enum nsim_dev_port_type type,
 		      unsigned int port_index)
 {
 	struct nsim_dev *nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev);
@@ -1230,7 +1604,7 @@ int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev,
 	int err = 0;
 
 	mutex_lock(&nsim_dev->port_list_lock);
-	nsim_dev_port = __nsim_dev_port_lookup(nsim_dev, port_index);
+	nsim_dev_port = __nsim_dev_port_lookup(nsim_dev, type, port_index);
 	if (!nsim_dev_port)
 		err = -ENOENT;
 	else
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 659d3dceb687..c3aeb15843e2 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -113,6 +113,11 @@ static int nsim_set_vf_rate(struct net_device *dev, int vf, int min, int max)
 	struct netdevsim *ns = netdev_priv(dev);
 	struct nsim_bus_dev *nsim_bus_dev = ns->nsim_bus_dev;
 
+	if (nsim_esw_mode_is_switchdev(ns->nsim_dev)) {
+		pr_err("Not supported in switchdev mode. Please use devlink API.\n");
+		return -EOPNOTSUPP;
+	}
+
 	if (vf >= nsim_bus_dev->num_vfs)
 		return -EINVAL;
 
@@ -261,6 +266,18 @@ static const struct net_device_ops nsim_netdev_ops = {
 	.ndo_get_devlink_port	= nsim_get_devlink_port,
 };
 
+static const struct net_device_ops nsim_vf_netdev_ops = {
+	.ndo_start_xmit		= nsim_start_xmit,
+	.ndo_set_rx_mode	= nsim_set_rx_mode,
+	.ndo_set_mac_address	= eth_mac_addr,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_change_mtu		= nsim_change_mtu,
+	.ndo_get_stats64	= nsim_get_stats64,
+	.ndo_setup_tc		= nsim_setup_tc,
+	.ndo_set_features	= nsim_set_features,
+	.ndo_get_devlink_port	= nsim_get_devlink_port,
+};
+
 static void nsim_setup(struct net_device *dev)
 {
 	ether_setup(dev);
@@ -280,6 +297,49 @@ static void nsim_setup(struct net_device *dev)
 	dev->max_mtu = ETH_MAX_MTU;
 }
 
+static int nsim_init_netdevsim(struct netdevsim *ns)
+{
+	int err;
+
+	ns->netdev->netdev_ops = &nsim_netdev_ops;
+
+	err = nsim_udp_tunnels_info_create(ns->nsim_dev, ns->netdev);
+	if (err)
+		return err;
+
+	rtnl_lock();
+	err = nsim_bpf_init(ns);
+	if (err)
+		goto err_utn_destroy;
+
+	nsim_ipsec_init(ns);
+
+	err = register_netdevice(ns->netdev);
+	if (err)
+		goto err_ipsec_teardown;
+	rtnl_unlock();
+	return 0;
+
+err_ipsec_teardown:
+	nsim_ipsec_teardown(ns);
+	nsim_bpf_uninit(ns);
+err_utn_destroy:
+	rtnl_unlock();
+	nsim_udp_tunnels_info_destroy(ns->netdev);
+	return err;
+}
+
+static int nsim_init_netdevsim_vf(struct netdevsim *ns)
+{
+	int err;
+
+	ns->netdev->netdev_ops = &nsim_vf_netdev_ops;
+	rtnl_lock();
+	err = register_netdevice(ns->netdev);
+	rtnl_unlock();
+	return err;
+}
+
 struct netdevsim *
 nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
 {
@@ -299,33 +359,15 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
 	ns->nsim_dev_port = nsim_dev_port;
 	ns->nsim_bus_dev = nsim_dev->nsim_bus_dev;
 	SET_NETDEV_DEV(dev, &ns->nsim_bus_dev->dev);
-	dev->netdev_ops = &nsim_netdev_ops;
 	nsim_ethtool_init(ns);
-
-	err = nsim_udp_tunnels_info_create(nsim_dev, dev);
+	if (nsim_dev_port_is_pf(nsim_dev_port))
+		err = nsim_init_netdevsim(ns);
+	else
+		err = nsim_init_netdevsim_vf(ns);
 	if (err)
 		goto err_free_netdev;
-
-	rtnl_lock();
-	err = nsim_bpf_init(ns);
-	if (err)
-		goto err_utn_destroy;
-
-	nsim_ipsec_init(ns);
-
-	err = register_netdevice(dev);
-	if (err)
-		goto err_ipsec_teardown;
-	rtnl_unlock();
-
 	return ns;
 
-err_ipsec_teardown:
-	nsim_ipsec_teardown(ns);
-	nsim_bpf_uninit(ns);
-err_utn_destroy:
-	rtnl_unlock();
-	nsim_udp_tunnels_info_destroy(dev);
 err_free_netdev:
 	free_netdev(dev);
 	return ERR_PTR(err);
@@ -337,10 +379,13 @@ void nsim_destroy(struct netdevsim *ns)
 
 	rtnl_lock();
 	unregister_netdevice(dev);
-	nsim_ipsec_teardown(ns);
-	nsim_bpf_uninit(ns);
+	if (nsim_dev_port_is_pf(ns->nsim_dev_port)) {
+		nsim_ipsec_teardown(ns);
+		nsim_bpf_uninit(ns);
+	}
 	rtnl_unlock();
-	nsim_udp_tunnels_info_destroy(dev);
+	if (nsim_dev_port_is_pf(ns->nsim_dev_port))
+		nsim_udp_tunnels_info_destroy(dev);
 	free_netdev(dev);
 }
 
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 7ff24e03577b..ae462957dcee 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -197,11 +197,22 @@ static inline void nsim_dev_psample_exit(struct nsim_dev *nsim_dev)
 }
 #endif
 
+enum nsim_dev_port_type {
+	NSIM_DEV_PORT_TYPE_PF,
+	NSIM_DEV_PORT_TYPE_VF,
+};
+
+#define NSIM_DEV_VF_PORT_INDEX_BASE 128
+#define NSIM_DEV_VF_PORT_INDEX_MAX UINT_MAX
+
 struct nsim_dev_port {
 	struct list_head list;
 	struct devlink_port devlink_port;
 	unsigned int port_index;
+	enum nsim_dev_port_type port_type;
 	struct dentry *ddir;
+	struct dentry *rate_parent;
+	char *parent_name;
 	struct netdevsim *ns;
 };
 
@@ -212,6 +223,8 @@ struct nsim_dev {
 	struct dentry *ddir;
 	struct dentry *ports_ddir;
 	struct dentry *take_snapshot;
+	struct dentry *max_vfs;
+	struct dentry *nodes_ddir;
 	struct bpf_offload_dev *bpf_dev;
 	bool bpf_bind_accept;
 	bool bpf_bind_verifier_accept;
@@ -236,6 +249,7 @@ struct nsim_dev {
 	bool fail_trap_group_set;
 	bool fail_trap_policer_set;
 	bool fail_trap_policer_counter_get;
+	bool fail_trap_drop_counter_get;
 	struct {
 		struct udp_tunnel_nic_shared utn_shared;
 		u32 __ports[2][NSIM_UDP_TUNNEL_N_PORTS];
@@ -247,8 +261,22 @@ struct nsim_dev {
 		u32 sleep;
 	} udp_ports;
 	struct nsim_dev_psample *psample;
+	u16 esw_mode;
 };
 
+int nsim_esw_legacy_enable(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack);
+int nsim_esw_switchdev_enable(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack);
+
+static inline bool nsim_esw_mode_is_legacy(struct nsim_dev *nsim_dev)
+{
+	return nsim_dev->esw_mode == DEVLINK_ESWITCH_MODE_LEGACY;
+}
+
+static inline bool nsim_esw_mode_is_switchdev(struct nsim_dev *nsim_dev)
+{
+	return nsim_dev->esw_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV;
+}
+
 static inline struct net *nsim_dev_net(struct nsim_dev *nsim_dev)
 {
 	return devlink_net(priv_to_devlink(nsim_dev));
@@ -259,8 +287,10 @@ void nsim_dev_exit(void);
 int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev);
 void nsim_dev_remove(struct nsim_bus_dev *nsim_bus_dev);
 int nsim_dev_port_add(struct nsim_bus_dev *nsim_bus_dev,
+		      enum nsim_dev_port_type type,
 		      unsigned int port_index);
 int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev,
+		      enum nsim_dev_port_type type,
 		      unsigned int port_index);
 
 struct nsim_fib_data *nsim_fib_create(struct devlink *devlink,
@@ -269,6 +299,23 @@ void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *fib_data);
 u64 nsim_fib_get_val(struct nsim_fib_data *fib_data,
 		     enum nsim_resource_id res_id, bool max);
 
+ssize_t nsim_bus_dev_max_vfs_read(struct file *file,
+				  char __user *data,
+				  size_t count, loff_t *ppos);
+ssize_t nsim_bus_dev_max_vfs_write(struct file *file,
+				   const char __user *data,
+				   size_t count, loff_t *ppos);
+void nsim_bus_dev_vfs_disable(struct nsim_bus_dev *nsim_bus_dev);
+
+static inline bool nsim_dev_port_is_pf(struct nsim_dev_port *nsim_dev_port)
+{
+	return nsim_dev_port->port_type == NSIM_DEV_PORT_TYPE_PF;
+}
+
+static inline bool nsim_dev_port_is_vf(struct nsim_dev_port *nsim_dev_port)
+{
+	return nsim_dev_port->port_type == NSIM_DEV_PORT_TYPE_VF;
+}
 #if IS_ENABLED(CONFIG_XFRM_OFFLOAD)
 void nsim_ipsec_init(struct netdevsim *ns);
 void nsim_ipsec_teardown(struct netdevsim *ns);
@@ -308,7 +355,9 @@ struct nsim_bus_dev {
 	struct net *initial_net; /* Purpose of this is to carry net pointer
 				  * during the probe time only.
 				  */
+	unsigned int max_vfs;
 	unsigned int num_vfs;
+	struct mutex vfs_lock;  /* Protects vfconfigs */
 	struct nsim_vf_config *vfconfigs;
 	/* Lock for devlink->reload_enabled in netdevsim module */
 	struct mutex nsim_bus_reload_lock;
diff --git a/drivers/net/pcs/Makefile b/drivers/net/pcs/Makefile
index c23146755972..0603d469bd57 100644
--- a/drivers/net/pcs/Makefile
+++ b/drivers/net/pcs/Makefile
@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for Linux PCS drivers
 
-obj-$(CONFIG_PCS_XPCS)		+= pcs-xpcs.o
+pcs_xpcs-$(CONFIG_PCS_XPCS)	:= pcs-xpcs.o pcs-xpcs-nxp.o
+
+obj-$(CONFIG_PCS_XPCS)		+= pcs_xpcs.o
 obj-$(CONFIG_PCS_LYNX)		+= pcs-lynx.o
diff --git a/drivers/net/pcs/pcs-xpcs-nxp.c b/drivers/net/pcs/pcs-xpcs-nxp.c
new file mode 100644
index 000000000000..984c9f7f16a8
--- /dev/null
+++ b/drivers/net/pcs/pcs-xpcs-nxp.c
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright 2021 NXP Semiconductors
+ */
+#include <linux/pcs/pcs-xpcs.h>
+#include "pcs-xpcs.h"
+
+/* LANE_DRIVER1_0 register */
+#define SJA1110_LANE_DRIVER1_0		0x8038
+#define SJA1110_TXDRV(x)		(((x) << 12) & GENMASK(14, 12))
+
+/* LANE_DRIVER2_0 register */
+#define SJA1110_LANE_DRIVER2_0		0x803a
+#define SJA1110_TXDRVTRIM_LSB(x)	((x) & GENMASK_ULL(15, 0))
+
+/* LANE_DRIVER2_1 register */
+#define SJA1110_LANE_DRIVER2_1		0x803b
+#define SJA1110_LANE_DRIVER2_1_RSV	BIT(9)
+#define SJA1110_TXDRVTRIM_MSB(x)	(((x) & GENMASK_ULL(23, 16)) >> 16)
+
+/* LANE_TRIM register */
+#define SJA1110_LANE_TRIM		0x8040
+#define SJA1110_TXTEN			BIT(11)
+#define SJA1110_TXRTRIM(x)		(((x) << 8) & GENMASK(10, 8))
+#define SJA1110_TXPLL_BWSEL		BIT(7)
+#define SJA1110_RXTEN			BIT(6)
+#define SJA1110_RXRTRIM(x)		(((x) << 3) & GENMASK(5, 3))
+#define SJA1110_CDR_GAIN		BIT(2)
+#define SJA1110_ACCOUPLE_RXVCM_EN	BIT(0)
+
+/* LANE_DATAPATH_1 register */
+#define SJA1110_LANE_DATAPATH_1		0x8037
+
+/* POWERDOWN_ENABLE register */
+#define SJA1110_POWERDOWN_ENABLE	0x8041
+#define SJA1110_TXPLL_PD		BIT(12)
+#define SJA1110_TXPD			BIT(11)
+#define SJA1110_RXPKDETEN		BIT(10)
+#define SJA1110_RXCH_PD			BIT(9)
+#define SJA1110_RXBIAS_PD		BIT(8)
+#define SJA1110_RESET_SER_EN		BIT(7)
+#define SJA1110_RESET_SER		BIT(6)
+#define SJA1110_RESET_DES		BIT(5)
+#define SJA1110_RCVEN			BIT(4)
+
+/* RXPLL_CTRL0 register */
+#define SJA1110_RXPLL_CTRL0		0x8065
+#define SJA1110_RXPLL_FBDIV(x)		(((x) << 2) & GENMASK(9, 2))
+
+/* RXPLL_CTRL1 register */
+#define SJA1110_RXPLL_CTRL1		0x8066
+#define SJA1110_RXPLL_REFDIV(x)		((x) & GENMASK(4, 0))
+
+/* TXPLL_CTRL0 register */
+#define SJA1110_TXPLL_CTRL0		0x806d
+#define SJA1110_TXPLL_FBDIV(x)		((x) & GENMASK(11, 0))
+
+/* TXPLL_CTRL1 register */
+#define SJA1110_TXPLL_CTRL1		0x806e
+#define SJA1110_TXPLL_REFDIV(x)		((x) & GENMASK(5, 0))
+
+/* RX_DATA_DETECT register */
+#define SJA1110_RX_DATA_DETECT		0x8045
+
+/* RX_CDR_CTLE register */
+#define SJA1110_RX_CDR_CTLE		0x8042
+
+/* In NXP SJA1105, the PCS is integrated with a PMA that has the TX lane
+ * polarity inverted by default (PLUS is MINUS, MINUS is PLUS). To obtain
+ * normal non-inverted behavior, the TX lane polarity must be inverted in the
+ * PCS, via the DIGITAL_CONTROL_2 register.
+ */
+int nxp_sja1105_sgmii_pma_config(struct dw_xpcs *xpcs)
+{
+	return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL2,
+			  DW_VR_MII_DIG_CTRL2_TX_POL_INV);
+}
+
+static int nxp_sja1110_pma_config(struct dw_xpcs *xpcs,
+				  u16 txpll_fbdiv, u16 txpll_refdiv,
+				  u16 rxpll_fbdiv, u16 rxpll_refdiv,
+				  u16 rx_cdr_ctle)
+{
+	u16 val;
+	int ret;
+
+	/* Program TX PLL feedback divider and reference divider settings for
+	 * correct oscillation frequency.
+	 */
+	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_TXPLL_CTRL0,
+			 SJA1110_TXPLL_FBDIV(txpll_fbdiv));
+	if (ret < 0)
+		return ret;
+
+	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_TXPLL_CTRL1,
+			 SJA1110_TXPLL_REFDIV(txpll_refdiv));
+	if (ret < 0)
+		return ret;
+
+	/* Program transmitter amplitude and disable amplitude trimming */
+	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_LANE_DRIVER1_0,
+			 SJA1110_TXDRV(0x5));
+	if (ret < 0)
+		return ret;
+
+	val = SJA1110_TXDRVTRIM_LSB(0xffffffull);
+
+	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_LANE_DRIVER2_0, val);
+	if (ret < 0)
+		return ret;
+
+	val = SJA1110_TXDRVTRIM_MSB(0xffffffull) | SJA1110_LANE_DRIVER2_1_RSV;
+
+	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_LANE_DRIVER2_1, val);
+	if (ret < 0)
+		return ret;
+
+	/* Enable input and output resistor terminations for low BER. */
+	val = SJA1110_ACCOUPLE_RXVCM_EN | SJA1110_CDR_GAIN |
+	      SJA1110_RXRTRIM(4) | SJA1110_RXTEN | SJA1110_TXPLL_BWSEL |
+	      SJA1110_TXRTRIM(3) | SJA1110_TXTEN;
+
+	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_LANE_TRIM, val);
+	if (ret < 0)
+		return ret;
+
+	/* Select PCS as transmitter data source. */
+	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_LANE_DATAPATH_1, 0);
+	if (ret < 0)
+		return ret;
+
+	/* Program RX PLL feedback divider and reference divider for correct
+	 * oscillation frequency.
+	 */
+	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_RXPLL_CTRL0,
+			 SJA1110_RXPLL_FBDIV(rxpll_fbdiv));
+	if (ret < 0)
+		return ret;
+
+	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_RXPLL_CTRL1,
+			 SJA1110_RXPLL_REFDIV(rxpll_refdiv));
+	if (ret < 0)
+		return ret;
+
+	/* Program threshold for receiver signal detector.
+	 * Enable control of RXPLL by receiver signal detector to disable RXPLL
+	 * when an input signal is not present.
+	 */
+	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_RX_DATA_DETECT, 0x0005);
+	if (ret < 0)
+		return ret;
+
+	/* Enable TX and RX PLLs and circuits.
+	 * Release reset of PMA to enable data flow to/from PCS.
+	 */
+	ret = xpcs_read(xpcs, MDIO_MMD_VEND2, SJA1110_POWERDOWN_ENABLE);
+	if (ret < 0)
+		return ret;
+
+	val = ret & ~(SJA1110_TXPLL_PD | SJA1110_TXPD | SJA1110_RXCH_PD |
+		      SJA1110_RXBIAS_PD | SJA1110_RESET_SER_EN |
+		      SJA1110_RESET_SER | SJA1110_RESET_DES);
+	val |= SJA1110_RXPKDETEN | SJA1110_RCVEN;
+
+	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_POWERDOWN_ENABLE, val);
+	if (ret < 0)
+		return ret;
+
+	/* Program continuous-time linear equalizer (CTLE) settings. */
+	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_RX_CDR_CTLE,
+			 rx_cdr_ctle);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+int nxp_sja1110_sgmii_pma_config(struct dw_xpcs *xpcs)
+{
+	return nxp_sja1110_pma_config(xpcs, 0x19, 0x1, 0x19, 0x1, 0x212a);
+}
+
+int nxp_sja1110_2500basex_pma_config(struct dw_xpcs *xpcs)
+{
+	return nxp_sja1110_pma_config(xpcs, 0x7d, 0x2, 0x7d, 0x2, 0x732a);
+}
diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index 944ba105cac1..63fda3fc40aa 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -11,80 +11,10 @@
 #include <linux/mdio.h>
 #include <linux/phylink.h>
 #include <linux/workqueue.h>
+#include "pcs-xpcs.h"
 
-#define SYNOPSYS_XPCS_USXGMII_ID	0x7996ced0
-#define SYNOPSYS_XPCS_10GKR_ID		0x7996ced0
-#define SYNOPSYS_XPCS_XLGMII_ID		0x7996ced0
-#define SYNOPSYS_XPCS_SGMII_ID		0x7996ced0
-#define SYNOPSYS_XPCS_MASK		0xffffffff
-
-/* Vendor regs access */
-#define DW_VENDOR			BIT(15)
-
-/* VR_XS_PCS */
-#define DW_USXGMII_RST			BIT(10)
-#define DW_USXGMII_EN			BIT(9)
-#define DW_VR_XS_PCS_DIG_STS		0x0010
-#define DW_RXFIFO_ERR			GENMASK(6, 5)
-
-/* SR_MII */
-#define DW_USXGMII_FULL			BIT(8)
-#define DW_USXGMII_SS_MASK		(BIT(13) | BIT(6) | BIT(5))
-#define DW_USXGMII_10000		(BIT(13) | BIT(6))
-#define DW_USXGMII_5000			(BIT(13) | BIT(5))
-#define DW_USXGMII_2500			(BIT(5))
-#define DW_USXGMII_1000			(BIT(6))
-#define DW_USXGMII_100			(BIT(13))
-#define DW_USXGMII_10			(0)
-
-/* SR_AN */
-#define DW_SR_AN_ADV1			0x10
-#define DW_SR_AN_ADV2			0x11
-#define DW_SR_AN_ADV3			0x12
-#define DW_SR_AN_LP_ABL1		0x13
-#define DW_SR_AN_LP_ABL2		0x14
-#define DW_SR_AN_LP_ABL3		0x15
-
-/* Clause 73 Defines */
-/* AN_LP_ABL1 */
-#define DW_C73_PAUSE			BIT(10)
-#define DW_C73_ASYM_PAUSE		BIT(11)
-#define DW_C73_AN_ADV_SF		0x1
-/* AN_LP_ABL2 */
-#define DW_C73_1000KX			BIT(5)
-#define DW_C73_10000KX4			BIT(6)
-#define DW_C73_10000KR			BIT(7)
-/* AN_LP_ABL3 */
-#define DW_C73_2500KX			BIT(0)
-#define DW_C73_5000KR			BIT(1)
-
-/* Clause 37 Defines */
-/* VR MII MMD registers offsets */
-#define DW_VR_MII_DIG_CTRL1		0x8000
-#define DW_VR_MII_AN_CTRL		0x8001
-#define DW_VR_MII_AN_INTR_STS		0x8002
-
-/* VR_MII_DIG_CTRL1 */
-#define DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW		BIT(9)
-
-/* VR_MII_AN_CTRL */
-#define DW_VR_MII_AN_CTRL_TX_CONFIG_SHIFT	3
-#define DW_VR_MII_TX_CONFIG_MASK		BIT(3)
-#define DW_VR_MII_TX_CONFIG_PHY_SIDE_SGMII	0x1
-#define DW_VR_MII_TX_CONFIG_MAC_SIDE_SGMII	0x0
-#define DW_VR_MII_AN_CTRL_PCS_MODE_SHIFT	1
-#define DW_VR_MII_PCS_MODE_MASK			GENMASK(2, 1)
-#define DW_VR_MII_PCS_MODE_C37_1000BASEX	0x0
-#define DW_VR_MII_PCS_MODE_C37_SGMII		0x2
-
-/* VR_MII_AN_INTR_STS */
-#define DW_VR_MII_AN_STS_C37_ANSGM_FD		BIT(1)
-#define DW_VR_MII_AN_STS_C37_ANSGM_SP_SHIFT	2
-#define DW_VR_MII_AN_STS_C37_ANSGM_SP		GENMASK(3, 2)
-#define DW_VR_MII_C37_ANSGM_SP_10		0x0
-#define DW_VR_MII_C37_ANSGM_SP_100		0x1
-#define DW_VR_MII_C37_ANSGM_SP_1000		0x2
-#define DW_VR_MII_C37_ANSGM_SP_LNKSTS		BIT(4)
+#define phylink_pcs_to_xpcs(pl_pcs) \
+	container_of((pl_pcs), struct dw_xpcs, pcs)
 
 static const int xpcs_usxgmii_features[] = {
 	ETHTOOL_LINK_MODE_Pause_BIT,
@@ -144,96 +74,141 @@ static const int xpcs_sgmii_features[] = {
 	__ETHTOOL_LINK_MODE_MASK_NBITS,
 };
 
+static const int xpcs_2500basex_features[] = {
+	ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+	ETHTOOL_LINK_MODE_Autoneg_BIT,
+	ETHTOOL_LINK_MODE_2500baseX_Full_BIT,
+	ETHTOOL_LINK_MODE_2500baseT_Full_BIT,
+	__ETHTOOL_LINK_MODE_MASK_NBITS,
+};
+
 static const phy_interface_t xpcs_usxgmii_interfaces[] = {
 	PHY_INTERFACE_MODE_USXGMII,
-	PHY_INTERFACE_MODE_MAX,
 };
 
 static const phy_interface_t xpcs_10gkr_interfaces[] = {
 	PHY_INTERFACE_MODE_10GKR,
-	PHY_INTERFACE_MODE_MAX,
 };
 
 static const phy_interface_t xpcs_xlgmii_interfaces[] = {
 	PHY_INTERFACE_MODE_XLGMII,
-	PHY_INTERFACE_MODE_MAX,
 };
 
 static const phy_interface_t xpcs_sgmii_interfaces[] = {
 	PHY_INTERFACE_MODE_SGMII,
+};
+
+static const phy_interface_t xpcs_2500basex_interfaces[] = {
+	PHY_INTERFACE_MODE_2500BASEX,
 	PHY_INTERFACE_MODE_MAX,
 };
 
-static struct xpcs_id {
-	u32 id;
-	u32 mask;
+enum {
+	DW_XPCS_USXGMII,
+	DW_XPCS_10GKR,
+	DW_XPCS_XLGMII,
+	DW_XPCS_SGMII,
+	DW_XPCS_2500BASEX,
+	DW_XPCS_INTERFACE_MAX,
+};
+
+struct xpcs_compat {
 	const int *supported;
 	const phy_interface_t *interface;
+	int num_interfaces;
 	int an_mode;
-} xpcs_id_list[] = {
-	{
-		.id = SYNOPSYS_XPCS_USXGMII_ID,
-		.mask = SYNOPSYS_XPCS_MASK,
-		.supported = xpcs_usxgmii_features,
-		.interface = xpcs_usxgmii_interfaces,
-		.an_mode = DW_AN_C73,
-	}, {
-		.id = SYNOPSYS_XPCS_10GKR_ID,
-		.mask = SYNOPSYS_XPCS_MASK,
-		.supported = xpcs_10gkr_features,
-		.interface = xpcs_10gkr_interfaces,
-		.an_mode = DW_AN_C73,
-	}, {
-		.id = SYNOPSYS_XPCS_XLGMII_ID,
-		.mask = SYNOPSYS_XPCS_MASK,
-		.supported = xpcs_xlgmii_features,
-		.interface = xpcs_xlgmii_interfaces,
-		.an_mode = DW_AN_C73,
-	}, {
-		.id = SYNOPSYS_XPCS_SGMII_ID,
-		.mask = SYNOPSYS_XPCS_MASK,
-		.supported = xpcs_sgmii_features,
-		.interface = xpcs_sgmii_interfaces,
-		.an_mode = DW_AN_C37_SGMII,
-	},
+	int (*pma_config)(struct dw_xpcs *xpcs);
 };
 
-static int xpcs_read(struct mdio_xpcs_args *xpcs, int dev, u32 reg)
+struct xpcs_id {
+	u32 id;
+	u32 mask;
+	const struct xpcs_compat *compat;
+};
+
+static const struct xpcs_compat *xpcs_find_compat(const struct xpcs_id *id,
+						  phy_interface_t interface)
+{
+	int i, j;
+
+	for (i = 0; i < DW_XPCS_INTERFACE_MAX; i++) {
+		const struct xpcs_compat *compat = &id->compat[i];
+
+		for (j = 0; j < compat->num_interfaces; j++)
+			if (compat->interface[j] == interface)
+				return compat;
+	}
+
+	return NULL;
+}
+
+int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface)
+{
+	const struct xpcs_compat *compat;
+
+	compat = xpcs_find_compat(xpcs->id, interface);
+	if (!compat)
+		return -ENODEV;
+
+	return compat->an_mode;
+}
+EXPORT_SYMBOL_GPL(xpcs_get_an_mode);
+
+static bool __xpcs_linkmode_supported(const struct xpcs_compat *compat,
+				      enum ethtool_link_mode_bit_indices linkmode)
 {
-	u32 reg_addr = MII_ADDR_C45 | dev << 16 | reg;
+	int i;
 
-	return mdiobus_read(xpcs->bus, xpcs->addr, reg_addr);
+	for (i = 0; compat->supported[i] != __ETHTOOL_LINK_MODE_MASK_NBITS; i++)
+		if (compat->supported[i] == linkmode)
+			return true;
+
+	return false;
 }
 
-static int xpcs_write(struct mdio_xpcs_args *xpcs, int dev, u32 reg, u16 val)
+#define xpcs_linkmode_supported(compat, mode) \
+	__xpcs_linkmode_supported(compat, ETHTOOL_LINK_MODE_ ## mode ## _BIT)
+
+int xpcs_read(struct dw_xpcs *xpcs, int dev, u32 reg)
 {
-	u32 reg_addr = MII_ADDR_C45 | dev << 16 | reg;
+	u32 reg_addr = mdiobus_c45_addr(dev, reg);
+	struct mii_bus *bus = xpcs->mdiodev->bus;
+	int addr = xpcs->mdiodev->addr;
 
-	return mdiobus_write(xpcs->bus, xpcs->addr, reg_addr, val);
+	return mdiobus_read(bus, addr, reg_addr);
 }
 
-static int xpcs_read_vendor(struct mdio_xpcs_args *xpcs, int dev, u32 reg)
+int xpcs_write(struct dw_xpcs *xpcs, int dev, u32 reg, u16 val)
+{
+	u32 reg_addr = mdiobus_c45_addr(dev, reg);
+	struct mii_bus *bus = xpcs->mdiodev->bus;
+	int addr = xpcs->mdiodev->addr;
+
+	return mdiobus_write(bus, addr, reg_addr, val);
+}
+
+static int xpcs_read_vendor(struct dw_xpcs *xpcs, int dev, u32 reg)
 {
 	return xpcs_read(xpcs, dev, DW_VENDOR | reg);
 }
 
-static int xpcs_write_vendor(struct mdio_xpcs_args *xpcs, int dev, int reg,
+static int xpcs_write_vendor(struct dw_xpcs *xpcs, int dev, int reg,
 			     u16 val)
 {
 	return xpcs_write(xpcs, dev, DW_VENDOR | reg, val);
 }
 
-static int xpcs_read_vpcs(struct mdio_xpcs_args *xpcs, int reg)
+static int xpcs_read_vpcs(struct dw_xpcs *xpcs, int reg)
 {
 	return xpcs_read_vendor(xpcs, MDIO_MMD_PCS, reg);
 }
 
-static int xpcs_write_vpcs(struct mdio_xpcs_args *xpcs, int reg, u16 val)
+static int xpcs_write_vpcs(struct dw_xpcs *xpcs, int reg, u16 val)
 {
 	return xpcs_write_vendor(xpcs, MDIO_MMD_PCS, reg, val);
 }
 
-static int xpcs_poll_reset(struct mdio_xpcs_args *xpcs, int dev)
+static int xpcs_poll_reset(struct dw_xpcs *xpcs, int dev)
 {
 	/* Poll until the reset bit clears (50ms per retry == 0.6 sec) */
 	unsigned int retries = 12;
@@ -249,15 +224,17 @@ static int xpcs_poll_reset(struct mdio_xpcs_args *xpcs, int dev)
 	return (ret & MDIO_CTRL1_RESET) ? -ETIMEDOUT : 0;
 }
 
-static int xpcs_soft_reset(struct mdio_xpcs_args *xpcs)
+static int xpcs_soft_reset(struct dw_xpcs *xpcs,
+			   const struct xpcs_compat *compat)
 {
 	int ret, dev;
 
-	switch (xpcs->an_mode) {
+	switch (compat->an_mode) {
 	case DW_AN_C73:
 		dev = MDIO_MMD_PCS;
 		break;
 	case DW_AN_C37_SGMII:
+	case DW_2500BASEX:
 		dev = MDIO_MMD_VEND2;
 		break;
 	default:
@@ -274,10 +251,10 @@ static int xpcs_soft_reset(struct mdio_xpcs_args *xpcs)
 #define xpcs_warn(__xpcs, __state, __args...) \
 ({ \
 	if ((__state)->link) \
-		dev_warn(&(__xpcs)->bus->dev, ##__args); \
+		dev_warn(&(__xpcs)->mdiodev->dev, ##__args); \
 })
 
-static int xpcs_read_fault_c73(struct mdio_xpcs_args *xpcs,
+static int xpcs_read_fault_c73(struct dw_xpcs *xpcs,
 			       struct phylink_link_state *state)
 {
 	int ret;
@@ -328,7 +305,7 @@ static int xpcs_read_fault_c73(struct mdio_xpcs_args *xpcs,
 	return 0;
 }
 
-static int xpcs_read_link_c73(struct mdio_xpcs_args *xpcs, bool an)
+static int xpcs_read_link_c73(struct dw_xpcs *xpcs, bool an)
 {
 	bool link = true;
 	int ret;
@@ -368,7 +345,7 @@ static int xpcs_get_max_usxgmii_speed(const unsigned long *supported)
 	return max;
 }
 
-static int xpcs_config_usxgmii(struct mdio_xpcs_args *xpcs, int speed)
+static void xpcs_config_usxgmii(struct dw_xpcs *xpcs, int speed)
 {
 	int ret, speed_sel;
 
@@ -393,36 +370,44 @@ static int xpcs_config_usxgmii(struct mdio_xpcs_args *xpcs, int speed)
 		break;
 	default:
 		/* Nothing to do here */
-		return -EINVAL;
+		return;
 	}
 
 	ret = xpcs_read_vpcs(xpcs, MDIO_CTRL1);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	ret = xpcs_write_vpcs(xpcs, MDIO_CTRL1, ret | DW_USXGMII_EN);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	ret = xpcs_read(xpcs, MDIO_MMD_VEND2, MDIO_CTRL1);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	ret &= ~DW_USXGMII_SS_MASK;
 	ret |= speed_sel | DW_USXGMII_FULL;
 
 	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, MDIO_CTRL1, ret);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	ret = xpcs_read_vpcs(xpcs, MDIO_CTRL1);
 	if (ret < 0)
-		return ret;
+		goto out;
 
-	return xpcs_write_vpcs(xpcs, MDIO_CTRL1, ret | DW_USXGMII_RST);
+	ret = xpcs_write_vpcs(xpcs, MDIO_CTRL1, ret | DW_USXGMII_RST);
+	if (ret < 0)
+		goto out;
+
+	return;
+
+out:
+	pr_err("%s: XPCS access returned %pe\n", __func__, ERR_PTR(ret));
 }
 
-static int _xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs)
+static int _xpcs_config_aneg_c73(struct dw_xpcs *xpcs,
+				 const struct xpcs_compat *compat)
 {
 	int ret, adv;
 
@@ -434,7 +419,7 @@ static int _xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs)
 
 	/* SR_AN_ADV3 */
 	adv = 0;
-	if (phylink_test(xpcs->supported, 2500baseX_Full))
+	if (xpcs_linkmode_supported(compat, 2500baseX_Full))
 		adv |= DW_C73_2500KX;
 
 	/* TODO: 5000baseKR */
@@ -445,11 +430,11 @@ static int _xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs)
 
 	/* SR_AN_ADV2 */
 	adv = 0;
-	if (phylink_test(xpcs->supported, 1000baseKX_Full))
+	if (xpcs_linkmode_supported(compat, 1000baseKX_Full))
 		adv |= DW_C73_1000KX;
-	if (phylink_test(xpcs->supported, 10000baseKX4_Full))
+	if (xpcs_linkmode_supported(compat, 10000baseKX4_Full))
 		adv |= DW_C73_10000KX4;
-	if (phylink_test(xpcs->supported, 10000baseKR_Full))
+	if (xpcs_linkmode_supported(compat, 10000baseKR_Full))
 		adv |= DW_C73_10000KR;
 
 	ret = xpcs_write(xpcs, MDIO_MMD_AN, DW_SR_AN_ADV2, adv);
@@ -458,19 +443,20 @@ static int _xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs)
 
 	/* SR_AN_ADV1 */
 	adv = DW_C73_AN_ADV_SF;
-	if (phylink_test(xpcs->supported, Pause))
+	if (xpcs_linkmode_supported(compat, Pause))
 		adv |= DW_C73_PAUSE;
-	if (phylink_test(xpcs->supported, Asym_Pause))
+	if (xpcs_linkmode_supported(compat, Asym_Pause))
 		adv |= DW_C73_ASYM_PAUSE;
 
 	return xpcs_write(xpcs, MDIO_MMD_AN, DW_SR_AN_ADV1, adv);
 }
 
-static int xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs)
+static int xpcs_config_aneg_c73(struct dw_xpcs *xpcs,
+				const struct xpcs_compat *compat)
 {
 	int ret;
 
-	ret = _xpcs_config_aneg_c73(xpcs);
+	ret = _xpcs_config_aneg_c73(xpcs, compat);
 	if (ret < 0)
 		return ret;
 
@@ -483,8 +469,9 @@ static int xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs)
 	return xpcs_write(xpcs, MDIO_MMD_AN, MDIO_CTRL1, ret);
 }
 
-static int xpcs_aneg_done_c73(struct mdio_xpcs_args *xpcs,
-			      struct phylink_link_state *state)
+static int xpcs_aneg_done_c73(struct dw_xpcs *xpcs,
+			      struct phylink_link_state *state,
+			      const struct xpcs_compat *compat)
 {
 	int ret;
 
@@ -499,7 +486,7 @@ static int xpcs_aneg_done_c73(struct mdio_xpcs_args *xpcs,
 
 		/* Check if Aneg outcome is valid */
 		if (!(ret & DW_C73_AN_ADV_SF)) {
-			xpcs_config_aneg_c73(xpcs);
+			xpcs_config_aneg_c73(xpcs, compat);
 			return 0;
 		}
 
@@ -509,7 +496,7 @@ static int xpcs_aneg_done_c73(struct mdio_xpcs_args *xpcs,
 	return 0;
 }
 
-static int xpcs_read_lpa_c73(struct mdio_xpcs_args *xpcs,
+static int xpcs_read_lpa_c73(struct dw_xpcs *xpcs,
 			     struct phylink_link_state *state)
 {
 	int ret;
@@ -558,7 +545,7 @@ static int xpcs_read_lpa_c73(struct mdio_xpcs_args *xpcs,
 	return 0;
 }
 
-static void xpcs_resolve_lpa_c73(struct mdio_xpcs_args *xpcs,
+static void xpcs_resolve_lpa_c73(struct dw_xpcs *xpcs,
 				 struct phylink_link_state *state)
 {
 	int max_speed = xpcs_get_max_usxgmii_speed(state->lp_advertising);
@@ -568,7 +555,7 @@ static void xpcs_resolve_lpa_c73(struct mdio_xpcs_args *xpcs,
 	state->duplex = DUPLEX_FULL;
 }
 
-static int xpcs_get_max_xlgmii_speed(struct mdio_xpcs_args *xpcs,
+static int xpcs_get_max_xlgmii_speed(struct dw_xpcs *xpcs,
 				     struct phylink_link_state *state)
 {
 	unsigned long *adv = state->advertising;
@@ -622,7 +609,7 @@ static int xpcs_get_max_xlgmii_speed(struct mdio_xpcs_args *xpcs,
 	return speed;
 }
 
-static void xpcs_resolve_pma(struct mdio_xpcs_args *xpcs,
+static void xpcs_resolve_pma(struct dw_xpcs *xpcs,
 			     struct phylink_link_state *state)
 {
 	state->pause = MLO_PAUSE_TX | MLO_PAUSE_RX;
@@ -641,16 +628,70 @@ static void xpcs_resolve_pma(struct mdio_xpcs_args *xpcs,
 	}
 }
 
-static int xpcs_validate(struct mdio_xpcs_args *xpcs,
-			 unsigned long *supported,
-			 struct phylink_link_state *state)
+void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported,
+		   struct phylink_link_state *state)
 {
-	linkmode_and(supported, supported, xpcs->supported);
-	linkmode_and(state->advertising, state->advertising, xpcs->supported);
-	return 0;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(xpcs_supported);
+	const struct xpcs_compat *compat;
+	int i;
+
+	/* phylink expects us to report all supported modes with
+	 * PHY_INTERFACE_MODE_NA, just don't limit the supported and
+	 * advertising masks and exit.
+	 */
+	if (state->interface == PHY_INTERFACE_MODE_NA)
+		return;
+
+	bitmap_zero(xpcs_supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
+
+	compat = xpcs_find_compat(xpcs->id, state->interface);
+
+	/* Populate the supported link modes for this
+	 * PHY interface type
+	 */
+	if (compat)
+		for (i = 0; compat->supported[i] != __ETHTOOL_LINK_MODE_MASK_NBITS; i++)
+			set_bit(compat->supported[i], xpcs_supported);
+
+	linkmode_and(supported, supported, xpcs_supported);
+	linkmode_and(state->advertising, state->advertising, xpcs_supported);
 }
+EXPORT_SYMBOL_GPL(xpcs_validate);
 
-static int xpcs_config_aneg_c37_sgmii(struct mdio_xpcs_args *xpcs)
+int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable)
+{
+	int ret;
+
+	if (enable) {
+	/* Enable EEE */
+		ret = DW_VR_MII_EEE_LTX_EN | DW_VR_MII_EEE_LRX_EN |
+		      DW_VR_MII_EEE_TX_QUIET_EN | DW_VR_MII_EEE_RX_QUIET_EN |
+		      DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL |
+		      mult_fact_100ns << DW_VR_MII_EEE_MULT_FACT_100NS_SHIFT;
+	} else {
+		ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL0);
+		if (ret < 0)
+			return ret;
+		ret &= ~(DW_VR_MII_EEE_LTX_EN | DW_VR_MII_EEE_LRX_EN |
+		       DW_VR_MII_EEE_TX_QUIET_EN | DW_VR_MII_EEE_RX_QUIET_EN |
+		       DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL |
+		       DW_VR_MII_EEE_MULT_FACT_100NS);
+	}
+
+	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL0, ret);
+	if (ret < 0)
+		return ret;
+
+	ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL1);
+	if (ret < 0)
+		return ret;
+
+	ret |= DW_VR_MII_EEE_TRN_LPI;
+	return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL1, ret);
+}
+EXPORT_SYMBOL_GPL(xpcs_config_eee);
+
+static int xpcs_config_aneg_c37_sgmii(struct dw_xpcs *xpcs, unsigned int mode)
 {
 	int ret;
 
@@ -686,26 +727,61 @@ static int xpcs_config_aneg_c37_sgmii(struct mdio_xpcs_args *xpcs)
 	if (ret < 0)
 		return ret;
 
-	ret |= DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW;
+	if (phylink_autoneg_inband(mode))
+		ret |= DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW;
+	else
+		ret &= ~DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW;
 
 	return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL1, ret);
 }
 
-static int xpcs_config(struct mdio_xpcs_args *xpcs,
-		       const struct phylink_link_state *state)
+static int xpcs_config_2500basex(struct dw_xpcs *xpcs)
+{
+	int ret;
+
+	ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL1);
+	if (ret < 0)
+		return ret;
+	ret |= DW_VR_MII_DIG_CTRL1_2G5_EN;
+	ret &= ~DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW;
+	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL1, ret);
+	if (ret < 0)
+		return ret;
+
+	ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_MMD_CTRL);
+	if (ret < 0)
+		return ret;
+	ret &= ~AN_CL37_EN;
+	ret |= SGMII_SPEED_SS6;
+	ret &= ~SGMII_SPEED_SS13;
+	return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_MMD_CTRL, ret);
+}
+
+int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface,
+		   unsigned int mode)
 {
+	const struct xpcs_compat *compat;
 	int ret;
 
-	switch (xpcs->an_mode) {
+	compat = xpcs_find_compat(xpcs->id, interface);
+	if (!compat)
+		return -ENODEV;
+
+	switch (compat->an_mode) {
 	case DW_AN_C73:
-		if (state->an_enabled) {
-			ret = xpcs_config_aneg_c73(xpcs);
+		if (phylink_autoneg_inband(mode)) {
+			ret = xpcs_config_aneg_c73(xpcs, compat);
 			if (ret)
 				return ret;
 		}
 		break;
 	case DW_AN_C37_SGMII:
-		ret = xpcs_config_aneg_c37_sgmii(xpcs);
+		ret = xpcs_config_aneg_c37_sgmii(xpcs, mode);
+		if (ret)
+			return ret;
+		break;
+	case DW_2500BASEX:
+		ret = xpcs_config_2500basex(xpcs);
 		if (ret)
 			return ret;
 		break;
@@ -713,11 +789,29 @@ static int xpcs_config(struct mdio_xpcs_args *xpcs,
 		return -1;
 	}
 
+	if (compat->pma_config) {
+		ret = compat->pma_config(xpcs);
+		if (ret)
+			return ret;
+	}
+
 	return 0;
 }
+EXPORT_SYMBOL_GPL(xpcs_do_config);
+
+static int xpcs_config(struct phylink_pcs *pcs, unsigned int mode,
+		       phy_interface_t interface,
+		       const unsigned long *advertising,
+		       bool permit_pause_to_mac)
+{
+	struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs);
+
+	return xpcs_do_config(xpcs, interface, mode);
+}
 
-static int xpcs_get_state_c73(struct mdio_xpcs_args *xpcs,
-			      struct phylink_link_state *state)
+static int xpcs_get_state_c73(struct dw_xpcs *xpcs,
+			      struct phylink_link_state *state,
+			      const struct xpcs_compat *compat)
 {
 	int ret;
 
@@ -727,16 +821,16 @@ static int xpcs_get_state_c73(struct mdio_xpcs_args *xpcs,
 	/* ... and then we check the faults. */
 	ret = xpcs_read_fault_c73(xpcs, state);
 	if (ret) {
-		ret = xpcs_soft_reset(xpcs);
+		ret = xpcs_soft_reset(xpcs, compat);
 		if (ret)
 			return ret;
 
 		state->link = 0;
 
-		return xpcs_config(xpcs, state);
+		return xpcs_do_config(xpcs, state->interface, MLO_AN_INBAND);
 	}
 
-	if (state->an_enabled && xpcs_aneg_done_c73(xpcs, state)) {
+	if (state->an_enabled && xpcs_aneg_done_c73(xpcs, state, compat)) {
 		state->an_complete = true;
 		xpcs_read_lpa_c73(xpcs, state);
 		xpcs_resolve_lpa_c73(xpcs, state);
@@ -749,7 +843,7 @@ static int xpcs_get_state_c73(struct mdio_xpcs_args *xpcs,
 	return 0;
 }
 
-static int xpcs_get_state_c37_sgmii(struct mdio_xpcs_args *xpcs,
+static int xpcs_get_state_c37_sgmii(struct dw_xpcs *xpcs,
 				    struct phylink_link_state *state)
 {
 	int ret;
@@ -790,39 +884,81 @@ static int xpcs_get_state_c37_sgmii(struct mdio_xpcs_args *xpcs,
 	return 0;
 }
 
-static int xpcs_get_state(struct mdio_xpcs_args *xpcs,
-			  struct phylink_link_state *state)
+static void xpcs_get_state(struct phylink_pcs *pcs,
+			   struct phylink_link_state *state)
 {
+	struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs);
+	const struct xpcs_compat *compat;
 	int ret;
 
-	switch (xpcs->an_mode) {
+	compat = xpcs_find_compat(xpcs->id, state->interface);
+	if (!compat)
+		return;
+
+	switch (compat->an_mode) {
 	case DW_AN_C73:
-		ret = xpcs_get_state_c73(xpcs, state);
-		if (ret)
-			return ret;
+		ret = xpcs_get_state_c73(xpcs, state, compat);
+		if (ret) {
+			pr_err("xpcs_get_state_c73 returned %pe\n",
+			       ERR_PTR(ret));
+			return;
+		}
 		break;
 	case DW_AN_C37_SGMII:
 		ret = xpcs_get_state_c37_sgmii(xpcs, state);
-		if (ret)
-			return ret;
+		if (ret) {
+			pr_err("xpcs_get_state_c37_sgmii returned %pe\n",
+			       ERR_PTR(ret));
+		}
 		break;
 	default:
-		return -1;
+		return;
 	}
+}
 
-	return 0;
+static void xpcs_link_up_sgmii(struct dw_xpcs *xpcs, unsigned int mode,
+			       int speed, int duplex)
+{
+	int val, ret;
+
+	if (phylink_autoneg_inband(mode))
+		return;
+
+	switch (speed) {
+	case SPEED_1000:
+		val = BMCR_SPEED1000;
+		break;
+	case SPEED_100:
+		val = BMCR_SPEED100;
+		break;
+	case SPEED_10:
+		val = BMCR_SPEED10;
+		break;
+	default:
+		return;
+	}
+
+	if (duplex == DUPLEX_FULL)
+		val |= BMCR_FULLDPLX;
+
+	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, MDIO_CTRL1, val);
+	if (ret)
+		pr_err("%s: xpcs_write returned %pe\n", __func__, ERR_PTR(ret));
 }
 
-static int xpcs_link_up(struct mdio_xpcs_args *xpcs, int speed,
-			phy_interface_t interface)
+void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode,
+		  phy_interface_t interface, int speed, int duplex)
 {
+	struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs);
+
 	if (interface == PHY_INTERFACE_MODE_USXGMII)
 		return xpcs_config_usxgmii(xpcs, speed);
-
-	return 0;
+	if (interface == PHY_INTERFACE_MODE_SGMII)
+		return xpcs_link_up_sgmii(xpcs, mode, speed, duplex);
 }
+EXPORT_SYMBOL_GPL(xpcs_link_up);
 
-static u32 xpcs_get_id(struct mdio_xpcs_args *xpcs)
+static u32 xpcs_get_id(struct dw_xpcs *xpcs)
 {
 	int ret;
 	u32 id;
@@ -838,8 +974,10 @@ static u32 xpcs_get_id(struct mdio_xpcs_args *xpcs)
 	if (ret < 0)
 		return 0xffffffff;
 
-	/* If Device IDs are not all zeros, we found C73 AN-type device */
-	if (id | ret)
+	/* If Device IDs are not all zeros or all ones,
+	 * we found C73 AN-type device
+	 */
+	if ((id | ret) && (id | ret) != 0xffffffff)
 		return id | ret;
 
 	/* Next, search C37 PCS using Vendor-Specific MII MMD */
@@ -860,60 +998,141 @@ static u32 xpcs_get_id(struct mdio_xpcs_args *xpcs)
 	return 0xffffffff;
 }
 
-static bool xpcs_check_features(struct mdio_xpcs_args *xpcs,
-				struct xpcs_id *match,
-				phy_interface_t interface)
-{
-	int i;
-
-	for (i = 0; match->interface[i] != PHY_INTERFACE_MODE_MAX; i++) {
-		if (match->interface[i] == interface)
-			break;
-	}
+static const struct xpcs_compat synopsys_xpcs_compat[DW_XPCS_INTERFACE_MAX] = {
+	[DW_XPCS_USXGMII] = {
+		.supported = xpcs_usxgmii_features,
+		.interface = xpcs_usxgmii_interfaces,
+		.num_interfaces = ARRAY_SIZE(xpcs_usxgmii_interfaces),
+		.an_mode = DW_AN_C73,
+	},
+	[DW_XPCS_10GKR] = {
+		.supported = xpcs_10gkr_features,
+		.interface = xpcs_10gkr_interfaces,
+		.num_interfaces = ARRAY_SIZE(xpcs_10gkr_interfaces),
+		.an_mode = DW_AN_C73,
+	},
+	[DW_XPCS_XLGMII] = {
+		.supported = xpcs_xlgmii_features,
+		.interface = xpcs_xlgmii_interfaces,
+		.num_interfaces = ARRAY_SIZE(xpcs_xlgmii_interfaces),
+		.an_mode = DW_AN_C73,
+	},
+	[DW_XPCS_SGMII] = {
+		.supported = xpcs_sgmii_features,
+		.interface = xpcs_sgmii_interfaces,
+		.num_interfaces = ARRAY_SIZE(xpcs_sgmii_interfaces),
+		.an_mode = DW_AN_C37_SGMII,
+	},
+	[DW_XPCS_2500BASEX] = {
+		.supported = xpcs_2500basex_features,
+		.interface = xpcs_2500basex_interfaces,
+		.num_interfaces = ARRAY_SIZE(xpcs_2500basex_features),
+		.an_mode = DW_2500BASEX,
+	},
+};
 
-	if (match->interface[i] == PHY_INTERFACE_MODE_MAX)
-		return false;
+static const struct xpcs_compat nxp_sja1105_xpcs_compat[DW_XPCS_INTERFACE_MAX] = {
+	[DW_XPCS_SGMII] = {
+		.supported = xpcs_sgmii_features,
+		.interface = xpcs_sgmii_interfaces,
+		.num_interfaces = ARRAY_SIZE(xpcs_sgmii_interfaces),
+		.an_mode = DW_AN_C37_SGMII,
+		.pma_config = nxp_sja1105_sgmii_pma_config,
+	},
+};
 
-	for (i = 0; match->supported[i] != __ETHTOOL_LINK_MODE_MASK_NBITS; i++)
-		set_bit(match->supported[i], xpcs->supported);
+static const struct xpcs_compat nxp_sja1110_xpcs_compat[DW_XPCS_INTERFACE_MAX] = {
+	[DW_XPCS_SGMII] = {
+		.supported = xpcs_sgmii_features,
+		.interface = xpcs_sgmii_interfaces,
+		.num_interfaces = ARRAY_SIZE(xpcs_sgmii_interfaces),
+		.an_mode = DW_AN_C37_SGMII,
+		.pma_config = nxp_sja1110_sgmii_pma_config,
+	},
+	[DW_XPCS_2500BASEX] = {
+		.supported = xpcs_2500basex_features,
+		.interface = xpcs_2500basex_interfaces,
+		.num_interfaces = ARRAY_SIZE(xpcs_2500basex_interfaces),
+		.an_mode = DW_2500BASEX,
+		.pma_config = nxp_sja1110_2500basex_pma_config,
+	},
+};
 
-	xpcs->an_mode = match->an_mode;
+static const struct xpcs_id xpcs_id_list[] = {
+	{
+		.id = SYNOPSYS_XPCS_ID,
+		.mask = SYNOPSYS_XPCS_MASK,
+		.compat = synopsys_xpcs_compat,
+	}, {
+		.id = NXP_SJA1105_XPCS_ID,
+		.mask = SYNOPSYS_XPCS_MASK,
+		.compat = nxp_sja1105_xpcs_compat,
+	}, {
+		.id = NXP_SJA1110_XPCS_ID,
+		.mask = SYNOPSYS_XPCS_MASK,
+		.compat = nxp_sja1110_xpcs_compat,
+	},
+};
 
-	return true;
-}
+static const struct phylink_pcs_ops xpcs_phylink_ops = {
+	.pcs_config = xpcs_config,
+	.pcs_get_state = xpcs_get_state,
+	.pcs_link_up = xpcs_link_up,
+};
 
-static int xpcs_probe(struct mdio_xpcs_args *xpcs, phy_interface_t interface)
+struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev,
+			    phy_interface_t interface)
 {
-	u32 xpcs_id = xpcs_get_id(xpcs);
-	struct xpcs_id *match = NULL;
-	int i;
+	struct dw_xpcs *xpcs;
+	u32 xpcs_id;
+	int i, ret;
+
+	xpcs = kzalloc(sizeof(*xpcs), GFP_KERNEL);
+	if (!xpcs)
+		return NULL;
+
+	xpcs->mdiodev = mdiodev;
+
+	xpcs_id = xpcs_get_id(xpcs);
 
 	for (i = 0; i < ARRAY_SIZE(xpcs_id_list); i++) {
-		struct xpcs_id *entry = &xpcs_id_list[i];
+		const struct xpcs_id *entry = &xpcs_id_list[i];
+		const struct xpcs_compat *compat;
+
+		if ((xpcs_id & entry->mask) != entry->id)
+			continue;
 
-		if ((xpcs_id & entry->mask) == entry->id) {
-			match = entry;
+		xpcs->id = entry;
 
-			if (xpcs_check_features(xpcs, match, interface))
-				return xpcs_soft_reset(xpcs);
+		compat = xpcs_find_compat(entry, interface);
+		if (!compat) {
+			ret = -ENODEV;
+			goto out;
 		}
+
+		xpcs->pcs.ops = &xpcs_phylink_ops;
+		xpcs->pcs.poll = true;
+
+		ret = xpcs_soft_reset(xpcs, compat);
+		if (ret)
+			goto out;
+
+		return xpcs;
 	}
 
-	return -ENODEV;
-}
+	ret = -ENODEV;
 
-static struct mdio_xpcs_ops xpcs_ops = {
-	.validate = xpcs_validate,
-	.config = xpcs_config,
-	.get_state = xpcs_get_state,
-	.link_up = xpcs_link_up,
-	.probe = xpcs_probe,
-};
+out:
+	kfree(xpcs);
+
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(xpcs_create);
 
-struct mdio_xpcs_ops *mdio_xpcs_get_ops(void)
+void xpcs_destroy(struct dw_xpcs *xpcs)
 {
-	return &xpcs_ops;
+	kfree(xpcs);
 }
-EXPORT_SYMBOL_GPL(mdio_xpcs_get_ops);
+EXPORT_SYMBOL_GPL(xpcs_destroy);
 
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/pcs/pcs-xpcs.h b/drivers/net/pcs/pcs-xpcs.h
new file mode 100644
index 000000000000..35651d32a224
--- /dev/null
+++ b/drivers/net/pcs/pcs-xpcs.h
@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2020 Synopsys, Inc. and/or its affiliates.
+ * Synopsys DesignWare XPCS helpers
+ *
+ * Author: Jose Abreu <Jose.Abreu@synopsys.com>
+ */
+
+#define SYNOPSYS_XPCS_ID		0x7996ced0
+#define SYNOPSYS_XPCS_MASK		0xffffffff
+
+/* Vendor regs access */
+#define DW_VENDOR			BIT(15)
+
+/* VR_XS_PCS */
+#define DW_USXGMII_RST			BIT(10)
+#define DW_USXGMII_EN			BIT(9)
+#define DW_VR_XS_PCS_DIG_STS		0x0010
+#define DW_RXFIFO_ERR			GENMASK(6, 5)
+
+/* SR_MII */
+#define DW_USXGMII_FULL			BIT(8)
+#define DW_USXGMII_SS_MASK		(BIT(13) | BIT(6) | BIT(5))
+#define DW_USXGMII_10000		(BIT(13) | BIT(6))
+#define DW_USXGMII_5000			(BIT(13) | BIT(5))
+#define DW_USXGMII_2500			(BIT(5))
+#define DW_USXGMII_1000			(BIT(6))
+#define DW_USXGMII_100			(BIT(13))
+#define DW_USXGMII_10			(0)
+
+/* SR_AN */
+#define DW_SR_AN_ADV1			0x10
+#define DW_SR_AN_ADV2			0x11
+#define DW_SR_AN_ADV3			0x12
+#define DW_SR_AN_LP_ABL1		0x13
+#define DW_SR_AN_LP_ABL2		0x14
+#define DW_SR_AN_LP_ABL3		0x15
+
+/* Clause 73 Defines */
+/* AN_LP_ABL1 */
+#define DW_C73_PAUSE			BIT(10)
+#define DW_C73_ASYM_PAUSE		BIT(11)
+#define DW_C73_AN_ADV_SF		0x1
+/* AN_LP_ABL2 */
+#define DW_C73_1000KX			BIT(5)
+#define DW_C73_10000KX4			BIT(6)
+#define DW_C73_10000KR			BIT(7)
+/* AN_LP_ABL3 */
+#define DW_C73_2500KX			BIT(0)
+#define DW_C73_5000KR			BIT(1)
+
+/* Clause 37 Defines */
+/* VR MII MMD registers offsets */
+#define DW_VR_MII_MMD_CTRL		0x0000
+#define DW_VR_MII_DIG_CTRL1		0x8000
+#define DW_VR_MII_AN_CTRL		0x8001
+#define DW_VR_MII_AN_INTR_STS		0x8002
+/* Enable 2.5G Mode */
+#define DW_VR_MII_DIG_CTRL1_2G5_EN	BIT(2)
+/* EEE Mode Control Register */
+#define DW_VR_MII_EEE_MCTRL0		0x8006
+#define DW_VR_MII_EEE_MCTRL1		0x800b
+#define DW_VR_MII_DIG_CTRL2		0x80e1
+
+/* VR_MII_DIG_CTRL1 */
+#define DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW		BIT(9)
+
+/* VR_MII_DIG_CTRL2 */
+#define DW_VR_MII_DIG_CTRL2_TX_POL_INV		BIT(4)
+#define DW_VR_MII_DIG_CTRL2_RX_POL_INV		BIT(0)
+
+/* VR_MII_AN_CTRL */
+#define DW_VR_MII_AN_CTRL_TX_CONFIG_SHIFT	3
+#define DW_VR_MII_TX_CONFIG_MASK		BIT(3)
+#define DW_VR_MII_TX_CONFIG_PHY_SIDE_SGMII	0x1
+#define DW_VR_MII_TX_CONFIG_MAC_SIDE_SGMII	0x0
+#define DW_VR_MII_AN_CTRL_PCS_MODE_SHIFT	1
+#define DW_VR_MII_PCS_MODE_MASK			GENMASK(2, 1)
+#define DW_VR_MII_PCS_MODE_C37_1000BASEX	0x0
+#define DW_VR_MII_PCS_MODE_C37_SGMII		0x2
+
+/* VR_MII_AN_INTR_STS */
+#define DW_VR_MII_AN_STS_C37_ANSGM_FD		BIT(1)
+#define DW_VR_MII_AN_STS_C37_ANSGM_SP_SHIFT	2
+#define DW_VR_MII_AN_STS_C37_ANSGM_SP		GENMASK(3, 2)
+#define DW_VR_MII_C37_ANSGM_SP_10		0x0
+#define DW_VR_MII_C37_ANSGM_SP_100		0x1
+#define DW_VR_MII_C37_ANSGM_SP_1000		0x2
+#define DW_VR_MII_C37_ANSGM_SP_LNKSTS		BIT(4)
+
+/* SR MII MMD Control defines */
+#define AN_CL37_EN			BIT(12)	/* Enable Clause 37 auto-nego */
+#define SGMII_SPEED_SS13		BIT(13)	/* SGMII speed along with SS6 */
+#define SGMII_SPEED_SS6			BIT(6)	/* SGMII speed along with SS13 */
+
+/* VR MII EEE Control 0 defines */
+#define DW_VR_MII_EEE_LTX_EN			BIT(0)  /* LPI Tx Enable */
+#define DW_VR_MII_EEE_LRX_EN			BIT(1)  /* LPI Rx Enable */
+#define DW_VR_MII_EEE_TX_QUIET_EN		BIT(2)  /* Tx Quiet Enable */
+#define DW_VR_MII_EEE_RX_QUIET_EN		BIT(3)  /* Rx Quiet Enable */
+#define DW_VR_MII_EEE_TX_EN_CTRL		BIT(4)  /* Tx Control Enable */
+#define DW_VR_MII_EEE_RX_EN_CTRL		BIT(7)  /* Rx Control Enable */
+
+#define DW_VR_MII_EEE_MULT_FACT_100NS_SHIFT	8
+#define DW_VR_MII_EEE_MULT_FACT_100NS		GENMASK(11, 8)
+
+/* VR MII EEE Control 1 defines */
+#define DW_VR_MII_EEE_TRN_LPI		BIT(0)	/* Transparent Mode Enable */
+
+int xpcs_read(struct dw_xpcs *xpcs, int dev, u32 reg);
+int xpcs_write(struct dw_xpcs *xpcs, int dev, u32 reg, u16 val);
+
+int nxp_sja1105_sgmii_pma_config(struct dw_xpcs *xpcs);
+int nxp_sja1110_sgmii_pma_config(struct dw_xpcs *xpcs);
+int nxp_sja1110_2500basex_pma_config(struct dw_xpcs *xpcs);
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 288bf405ebdb..c56f703ae998 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -207,6 +207,11 @@ config MARVELL_88X2222_PHY
 	  Support for the Marvell 88X2222 Dual-port Multi-speed Ethernet
 	  Transceiver.
 
+config MEDIATEK_GE_PHY
+	tristate "MediaTek Gigabit Ethernet PHYs"
+	help
+	  Supports the MediaTek Gigabit Ethernet PHYs.
+
 config MICREL_PHY
 	tristate "Micrel PHYs"
 	help
@@ -229,6 +234,12 @@ config MICROSEMI_PHY
 	help
 	  Currently supports VSC8514, VSC8530, VSC8531, VSC8540 and VSC8541 PHYs
 
+config MOTORCOMM_PHY
+	tristate "Motorcomm PHYs"
+	help
+	  Enables support for Motorcomm network PHYs.
+	  Currently supports the YT8511 gigabit PHY.
+
 config NATIONAL_PHY
 	tristate "National Semiconductor PHYs"
 	help
@@ -247,10 +258,11 @@ config NXP_TJA11XX_PHY
 	  Currently supports the NXP TJA1100 and TJA1101 PHY.
 
 config AT803X_PHY
-	tristate "Qualcomm Atheros AR803X PHYs"
+	tristate "Qualcomm Atheros AR803X PHYs and QCA833x PHYs"
 	depends on REGULATOR
 	help
-	  Currently supports the AR8030, AR8031, AR8033 and AR8035 model
+	  Currently supports the AR8030, AR8031, AR8033, AR8035 and internal
+	  QCA8337(Internal qca8k PHY) model
 
 config QSEMI_PHY
 	tristate "Quality Semiconductor PHYs"
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index bcda7ed2455d..172bb193ae6a 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -64,12 +64,14 @@ obj-$(CONFIG_LXT_PHY)		+= lxt.o
 obj-$(CONFIG_MARVELL_10G_PHY)	+= marvell10g.o
 obj-$(CONFIG_MARVELL_PHY)	+= marvell.o
 obj-$(CONFIG_MARVELL_88X2222_PHY)	+= marvell-88x2222.o
+obj-$(CONFIG_MEDIATEK_GE_PHY)	+= mediatek-ge.o
 obj-$(CONFIG_MESON_GXL_PHY)	+= meson-gxl.o
 obj-$(CONFIG_MICREL_KS8995MA)	+= spi_ks8995.o
 obj-$(CONFIG_MICREL_PHY)	+= micrel.o
 obj-$(CONFIG_MICROCHIP_PHY)	+= microchip.o
 obj-$(CONFIG_MICROCHIP_T1_PHY)	+= microchip_t1.o
 obj-$(CONFIG_MICROSEMI_PHY)	+= mscc/
+obj-$(CONFIG_MOTORCOMM_PHY)	+= motorcomm.o
 obj-$(CONFIG_NATIONAL_PHY)	+= national.o
 obj-$(CONFIG_NXP_C45_TJA11XX_PHY)	+= nxp-c45-tja11xx.o
 obj-$(CONFIG_NXP_TJA11XX_PHY)	+= nxp-tja11xx.o
diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c
index 55a0b91816e2..5ce6da62cc8e 100644
--- a/drivers/net/phy/adin.c
+++ b/drivers/net/phy/adin.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0+
-/**
+/*
  *  Driver for Analog Devices Industrial Ethernet PHYs
  *
  * Copyright 2019 Analog Devices Inc.
diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index 32af52dd5aed..6697c9368b40 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -83,8 +83,8 @@
 #define AT803X_MODE_CFG_MASK			0x0F
 #define AT803X_MODE_CFG_SGMII			0x01
 
-#define AT803X_PSSR			0x11	/*PHY-Specific Status Register*/
-#define AT803X_PSSR_MR_AN_COMPLETE	0x0200
+#define AT803X_PSSR				0x11	/*PHY-Specific Status Register*/
+#define AT803X_PSSR_MR_AN_COMPLETE		0x0200
 
 #define AT803X_DEBUG_REG_0			0x00
 #define AT803X_DEBUG_RX_CLK_DLY_EN		BIT(15)
@@ -92,10 +92,16 @@
 #define AT803X_DEBUG_REG_5			0x05
 #define AT803X_DEBUG_TX_CLK_DLY_EN		BIT(8)
 
+#define AT803X_DEBUG_REG_3C			0x3C
+
+#define AT803X_DEBUG_REG_3D			0x3D
+
 #define AT803X_DEBUG_REG_1F			0x1F
 #define AT803X_DEBUG_PLL_ON			BIT(2)
 #define AT803X_DEBUG_RGMII_1V8			BIT(3)
 
+#define MDIO_AZ_DEBUG				0x800D
+
 /* AT803x supports either the XTAL input pad, an internal PLL or the
  * DSP as clock reference for the clock output pad. The XTAL reference
  * is only used for 25 MHz output, all other frequencies need the PLL.
@@ -128,33 +134,59 @@
 #define AT803X_CLK_OUT_STRENGTH_HALF		1
 #define AT803X_CLK_OUT_STRENGTH_QUARTER		2
 
-#define AT803X_DEFAULT_DOWNSHIFT 5
-#define AT803X_MIN_DOWNSHIFT 2
-#define AT803X_MAX_DOWNSHIFT 9
+#define AT803X_DEFAULT_DOWNSHIFT		5
+#define AT803X_MIN_DOWNSHIFT			2
+#define AT803X_MAX_DOWNSHIFT			9
 
 #define AT803X_MMD3_SMARTEEE_CTL1		0x805b
 #define AT803X_MMD3_SMARTEEE_CTL2		0x805c
 #define AT803X_MMD3_SMARTEEE_CTL3		0x805d
 #define AT803X_MMD3_SMARTEEE_CTL3_LPI_EN	BIT(8)
 
-#define ATH9331_PHY_ID 0x004dd041
-#define ATH8030_PHY_ID 0x004dd076
-#define ATH8031_PHY_ID 0x004dd074
-#define ATH8032_PHY_ID 0x004dd023
-#define ATH8035_PHY_ID 0x004dd072
+#define ATH9331_PHY_ID				0x004dd041
+#define ATH8030_PHY_ID				0x004dd076
+#define ATH8031_PHY_ID				0x004dd074
+#define ATH8032_PHY_ID				0x004dd023
+#define ATH8035_PHY_ID				0x004dd072
 #define AT8030_PHY_ID_MASK			0xffffffef
 
-#define AT803X_PAGE_FIBER		0
-#define AT803X_PAGE_COPPER		1
+#define QCA8327_PHY_ID				0x004dd034
+#define QCA8337_PHY_ID				0x004dd036
+#define QCA8K_PHY_ID_MASK			0xffffffff
+
+#define QCA8K_DEVFLAGS_REVISION_MASK		GENMASK(2, 0)
+
+#define AT803X_PAGE_FIBER			0
+#define AT803X_PAGE_COPPER			1
+
+/* don't turn off internal PLL */
+#define AT803X_KEEP_PLL_ENABLED			BIT(0)
+#define AT803X_DISABLE_SMARTEEE			BIT(1)
 
 MODULE_DESCRIPTION("Qualcomm Atheros AR803x PHY driver");
 MODULE_AUTHOR("Matus Ujhelyi");
 MODULE_LICENSE("GPL");
 
+enum stat_access_type {
+	PHY,
+	MMD
+};
+
+struct at803x_hw_stat {
+	const char *string;
+	u8 reg;
+	u32 mask;
+	enum stat_access_type access_type;
+};
+
+static struct at803x_hw_stat at803x_hw_stats[] = {
+	{ "phy_idle_errors", 0xa, GENMASK(7, 0), PHY},
+	{ "phy_receive_errors", 0x15, GENMASK(15, 0), PHY},
+	{ "eee_wake_errors", 0x16, GENMASK(15, 0), MMD},
+};
+
 struct at803x_priv {
 	int flags;
-#define AT803X_KEEP_PLL_ENABLED	BIT(0)	/* don't turn off internal PLL */
-#define AT803X_DISABLE_SMARTEEE	BIT(1)
 	u16 clk_25m_reg;
 	u16 clk_25m_mask;
 	u8 smarteee_lpi_tw_1g;
@@ -162,6 +194,7 @@ struct at803x_priv {
 	struct regulator_dev *vddio_rdev;
 	struct regulator_dev *vddh_rdev;
 	struct regulator *vddio;
+	u64 stats[ARRAY_SIZE(at803x_hw_stats)];
 };
 
 struct at803x_context {
@@ -173,6 +206,17 @@ struct at803x_context {
 	u16 led_control;
 };
 
+static int at803x_debug_reg_write(struct phy_device *phydev, u16 reg, u16 data)
+{
+	int ret;
+
+	ret = phy_write(phydev, AT803X_DEBUG_ADDR, reg);
+	if (ret < 0)
+		return ret;
+
+	return phy_write(phydev, AT803X_DEBUG_DATA, data);
+}
+
 static int at803x_debug_reg_read(struct phy_device *phydev, u16 reg)
 {
 	int ret;
@@ -335,6 +379,53 @@ static void at803x_get_wol(struct phy_device *phydev,
 		wol->wolopts |= WAKE_MAGIC;
 }
 
+static int at803x_get_sset_count(struct phy_device *phydev)
+{
+	return ARRAY_SIZE(at803x_hw_stats);
+}
+
+static void at803x_get_strings(struct phy_device *phydev, u8 *data)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(at803x_hw_stats); i++) {
+		strscpy(data + i * ETH_GSTRING_LEN,
+			at803x_hw_stats[i].string, ETH_GSTRING_LEN);
+	}
+}
+
+static u64 at803x_get_stat(struct phy_device *phydev, int i)
+{
+	struct at803x_hw_stat stat = at803x_hw_stats[i];
+	struct at803x_priv *priv = phydev->priv;
+	int val;
+	u64 ret;
+
+	if (stat.access_type == MMD)
+		val = phy_read_mmd(phydev, MDIO_MMD_PCS, stat.reg);
+	else
+		val = phy_read(phydev, stat.reg);
+
+	if (val < 0) {
+		ret = U64_MAX;
+	} else {
+		val = val & stat.mask;
+		priv->stats[i] += val;
+		ret = priv->stats[i];
+	}
+
+	return ret;
+}
+
+static void at803x_get_stats(struct phy_device *phydev,
+			     struct ethtool_stats *stats, u64 *data)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(at803x_hw_stats); i++)
+		data[i] = at803x_get_stat(phydev, i);
+}
+
 static int at803x_suspend(struct phy_device *phydev)
 {
 	int value;
@@ -1170,6 +1261,34 @@ static int at803x_cable_test_start(struct phy_device *phydev)
 	return 0;
 }
 
+static int qca83xx_config_init(struct phy_device *phydev)
+{
+	u8 switch_revision;
+
+	switch_revision = phydev->dev_flags & QCA8K_DEVFLAGS_REVISION_MASK;
+
+	switch (switch_revision) {
+	case 1:
+		/* For 100M waveform */
+		at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_0, 0x02ea);
+		/* Turn on Gigabit clock */
+		at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_3D, 0x68a0);
+		break;
+
+	case 2:
+		phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, 0x0);
+		fallthrough;
+	case 4:
+		phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_AZ_DEBUG, 0x803f);
+		at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_3D, 0x6860);
+		at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_5, 0x2c46);
+		at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_3C, 0x6000);
+		break;
+	}
+
+	return 0;
+}
+
 static struct phy_driver at803x_driver[] = {
 {
 	/* Qualcomm Atheros AR8035 */
@@ -1266,7 +1385,20 @@ static struct phy_driver at803x_driver[] = {
 	.read_status		= at803x_read_status,
 	.soft_reset		= genphy_soft_reset,
 	.config_aneg		= at803x_config_aneg,
-} };
+}, {
+	/* QCA8337 */
+	.phy_id = QCA8337_PHY_ID,
+	.phy_id_mask = QCA8K_PHY_ID_MASK,
+	.name = "QCA PHY 8337",
+	/* PHY_GBIT_FEATURES */
+	.probe = at803x_probe,
+	.flags = PHY_IS_INTERNAL,
+	.config_init = qca83xx_config_init,
+	.soft_reset = genphy_soft_reset,
+	.get_sset_count = at803x_get_sset_count,
+	.get_strings = at803x_get_strings,
+	.get_stats = at803x_get_stats,
+}, };
 
 module_phy_driver(at803x_driver);
 
diff --git a/drivers/net/phy/ax88796b.c b/drivers/net/phy/ax88796b.c
index 79bf7ef1fcfd..457896337505 100644
--- a/drivers/net/phy/ax88796b.c
+++ b/drivers/net/phy/ax88796b.c
@@ -10,6 +10,8 @@
 #include <linux/mii.h>
 #include <linux/phy.h>
 
+#define PHY_ID_ASIX_AX88772A		0x003b1861
+#define PHY_ID_ASIX_AX88772C		0x003b1881
 #define PHY_ID_ASIX_AX88796B		0x003b1841
 
 MODULE_DESCRIPTION("Asix PHY driver");
@@ -39,7 +41,75 @@ static int asix_soft_reset(struct phy_device *phydev)
 	return genphy_soft_reset(phydev);
 }
 
-static struct phy_driver asix_driver[] = { {
+/* AX88772A is not working properly with some old switches (NETGEAR EN 108TP):
+ * after autoneg is done and the link status is reported as active, the MII_LPA
+ * register is 0. This issue is not reproducible on AX88772C.
+ */
+static int asix_ax88772a_read_status(struct phy_device *phydev)
+{
+	int ret, val;
+
+	ret = genphy_update_link(phydev);
+	if (ret)
+		return ret;
+
+	if (!phydev->link)
+		return 0;
+
+	/* If MII_LPA is 0, phy_resolve_aneg_linkmode() will fail to resolve
+	 * linkmode so use MII_BMCR as default values.
+	 */
+	val = phy_read(phydev, MII_BMCR);
+	if (val < 0)
+		return val;
+
+	if (val & BMCR_SPEED100)
+		phydev->speed = SPEED_100;
+	else
+		phydev->speed = SPEED_10;
+
+	if (val & BMCR_FULLDPLX)
+		phydev->duplex = DUPLEX_FULL;
+	else
+		phydev->duplex = DUPLEX_HALF;
+
+	ret = genphy_read_lpa(phydev);
+	if (ret < 0)
+		return ret;
+
+	if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete)
+		phy_resolve_aneg_linkmode(phydev);
+
+	return 0;
+}
+
+static void asix_ax88772a_link_change_notify(struct phy_device *phydev)
+{
+	/* Reset PHY, otherwise MII_LPA will provide outdated information.
+	 * This issue is reproducible only with some link partner PHYs
+	 */
+	if (phydev->state == PHY_NOLINK && phydev->drv->soft_reset)
+		phydev->drv->soft_reset(phydev);
+}
+
+static struct phy_driver asix_driver[] = {
+{
+	PHY_ID_MATCH_EXACT(PHY_ID_ASIX_AX88772A),
+	.name		= "Asix Electronics AX88772A",
+	.flags		= PHY_IS_INTERNAL,
+	.read_status	= asix_ax88772a_read_status,
+	.suspend	= genphy_suspend,
+	.resume		= genphy_resume,
+	.soft_reset	= asix_soft_reset,
+	.link_change_notify	= asix_ax88772a_link_change_notify,
+}, {
+	PHY_ID_MATCH_EXACT(PHY_ID_ASIX_AX88772C),
+	.name		= "Asix Electronics AX88772C",
+	.flags		= PHY_IS_INTERNAL,
+	.suspend	= genphy_suspend,
+	.resume		= genphy_resume,
+	.soft_reset	= asix_soft_reset,
+}, {
 	.phy_id		= PHY_ID_ASIX_AX88796B,
 	.name		= "Asix Electronics AX88796B",
 	.phy_id_mask	= 0xfffffff0,
@@ -50,6 +120,8 @@ static struct phy_driver asix_driver[] = { {
 module_phy_driver(asix_driver);
 
 static struct mdio_device_id __maybe_unused asix_tbl[] = {
+	{ PHY_ID_MATCH_EXACT(PHY_ID_ASIX_AX88772A) },
+	{ PHY_ID_MATCH_EXACT(PHY_ID_ASIX_AX88772C) },
 	{ PHY_ID_ASIX_AX88796B, 0xfffffff0 },
 	{ }
 };
diff --git a/drivers/net/phy/bcm87xx.c b/drivers/net/phy/bcm87xx.c
index 4ac8fd190e9d..313563482690 100644
--- a/drivers/net/phy/bcm87xx.c
+++ b/drivers/net/phy/bcm87xx.c
@@ -54,9 +54,9 @@ static int bcm87xx_of_reg_init(struct phy_device *phydev)
 		u16 reg		= be32_to_cpup(paddr++);
 		u16 mask	= be32_to_cpup(paddr++);
 		u16 val_bits	= be32_to_cpup(paddr++);
-		int val;
 		u32 regnum = mdiobus_c45_addr(devid, reg);
-		val = 0;
+		int val = 0;
+
 		if (mask) {
 			val = phy_read(phydev, regnum);
 			if (val < 0) {
diff --git a/drivers/net/phy/davicom.c b/drivers/net/phy/davicom.c
index a3b3842c67e5..4ac4bce1bf32 100644
--- a/drivers/net/phy/davicom.c
+++ b/drivers/net/phy/davicom.c
@@ -43,10 +43,10 @@
 #define MII_DM9161_INTR_DPLX_CHANGE	0x0010
 #define MII_DM9161_INTR_SPD_CHANGE	0x0008
 #define MII_DM9161_INTR_LINK_CHANGE	0x0004
-#define MII_DM9161_INTR_INIT 		0x0000
+#define MII_DM9161_INTR_INIT		0x0000
 #define MII_DM9161_INTR_STOP	\
-(MII_DM9161_INTR_DPLX_MASK | MII_DM9161_INTR_SPD_MASK \
- | MII_DM9161_INTR_LINK_MASK | MII_DM9161_INTR_MASK)
+	(MII_DM9161_INTR_DPLX_MASK | MII_DM9161_INTR_SPD_MASK |	\
+	 MII_DM9161_INTR_LINK_MASK | MII_DM9161_INTR_MASK)
 #define MII_DM9161_INTR_CHANGE	\
 	(MII_DM9161_INTR_DPLX_CHANGE | \
 	 MII_DM9161_INTR_SPD_CHANGE | \
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 0d79f68f301c..705c16675b80 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -170,9 +170,9 @@ static ushort gpio_tab[GPIO_TABLE_SIZE] = {
 module_param(chosen_phy, int, 0444);
 module_param_array(gpio_tab, ushort, NULL, 0444);
 
-MODULE_PARM_DESC(chosen_phy, \
+MODULE_PARM_DESC(chosen_phy,
 	"The address of the PHY to use for the ancillary clock features");
-MODULE_PARM_DESC(gpio_tab, \
+MODULE_PARM_DESC(gpio_tab,
 	"Which GPIO line to use for which purpose: cal,perout,extts1,...,extts6");
 
 static void dp83640_gpio_defaults(struct ptp_pin_desc *pd)
@@ -615,6 +615,7 @@ static void prune_rx_ts(struct dp83640_private *dp83640)
 static void enable_broadcast(struct phy_device *phydev, int init_page, int on)
 {
 	int val;
+
 	phy_write(phydev, PAGESEL, 0);
 	val = phy_read(phydev, PHYCR2);
 	if (on)
diff --git a/drivers/net/phy/et1011c.c b/drivers/net/phy/et1011c.c
index 09e07b902d3a..be1b71d7cab7 100644
--- a/drivers/net/phy/et1011c.c
+++ b/drivers/net/phy/et1011c.c
@@ -46,8 +46,8 @@ MODULE_LICENSE("GPL");
 
 static int et1011c_config_aneg(struct phy_device *phydev)
 {
-	int ctl = 0;
-	ctl = phy_read(phydev, MII_BMCR);
+	int ctl = phy_read(phydev, MII_BMCR);
+
 	if (ctl < 0)
 		return ctl;
 	ctl &= ~(BMCR_FULLDPLX | BMCR_SPEED100 | BMCR_SPEED1000 |
@@ -60,9 +60,10 @@ static int et1011c_config_aneg(struct phy_device *phydev)
 
 static int et1011c_read_status(struct phy_device *phydev)
 {
+	static int speed;
 	int ret;
 	u32 val;
-	static int speed;
+
 	ret = genphy_read_status(phydev);
 
 	if (speed != phydev->speed) {
@@ -72,10 +73,10 @@ static int et1011c_read_status(struct phy_device *phydev)
 					ET1011C_GIGABIT_SPEED) {
 			val = phy_read(phydev, ET1011C_CONFIG_REG);
 			val &= ~ET1011C_TX_FIFO_MASK;
-			phy_write(phydev, ET1011C_CONFIG_REG, val\
-					| ET1011C_GMII_INTERFACE\
-					| ET1011C_SYS_CLK_EN\
-					| ET1011C_TX_FIFO_DEPTH_16);
+			phy_write(phydev, ET1011C_CONFIG_REG, val |
+					  ET1011C_GMII_INTERFACE |
+					  ET1011C_SYS_CLK_EN |
+					  ET1011C_TX_FIFO_DEPTH_16);
 
 		}
 	}
diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index 18d81f43f2a8..c65fb5f5d2dc 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -161,8 +161,8 @@ static int fixed_phy_add_gpiod(unsigned int irq, int phy_addr,
 }
 
 int fixed_phy_add(unsigned int irq, int phy_addr,
-		  struct fixed_phy_status *status) {
-
+		  struct fixed_phy_status *status)
+{
 	return fixed_phy_add_gpiod(irq, phy_addr, status, NULL);
 }
 EXPORT_SYMBOL_GPL(fixed_phy_add);
diff --git a/drivers/net/phy/lxt.c b/drivers/net/phy/lxt.c
index bde3356a2f86..e3bf827b7959 100644
--- a/drivers/net/phy/lxt.c
+++ b/drivers/net/phy/lxt.c
@@ -242,8 +242,8 @@ static int lxt973a2_read_status(struct phy_device *phydev)
 				return lpa;
 
 			/* If both registers are equal, it is suspect but not
-			* impossible, hence a new try
-			*/
+			 * impossible, hence a new try
+			 */
 		} while (lpa == adv && retry--);
 
 		mii_lpa_to_linkmode_lpa_t(phydev->lp_advertising, lpa);
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index e6721c1c26c2..3de93c9f2744 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -367,39 +367,24 @@ static irqreturn_t marvell_handle_interrupt(struct phy_device *phydev)
 
 static int marvell_set_polarity(struct phy_device *phydev, int polarity)
 {
-	int reg;
-	int err;
-	int val;
-
-	/* get the current settings */
-	reg = phy_read(phydev, MII_M1011_PHY_SCR);
-	if (reg < 0)
-		return reg;
+	u16 val;
 
-	val = reg;
-	val &= ~MII_M1011_PHY_SCR_AUTO_CROSS;
 	switch (polarity) {
 	case ETH_TP_MDI:
-		val |= MII_M1011_PHY_SCR_MDI;
+		val = MII_M1011_PHY_SCR_MDI;
 		break;
 	case ETH_TP_MDI_X:
-		val |= MII_M1011_PHY_SCR_MDI_X;
+		val = MII_M1011_PHY_SCR_MDI_X;
 		break;
 	case ETH_TP_MDI_AUTO:
 	case ETH_TP_MDI_INVALID:
 	default:
-		val |= MII_M1011_PHY_SCR_AUTO_CROSS;
+		val = MII_M1011_PHY_SCR_AUTO_CROSS;
 		break;
 	}
 
-	if (val != reg) {
-		/* Set the new polarity value in the register */
-		err = phy_write(phydev, MII_M1011_PHY_SCR, val);
-		if (err)
-			return err;
-	}
-
-	return val != reg;
+	return phy_modify_changed(phydev, MII_M1011_PHY_SCR,
+				  MII_M1011_PHY_SCR_AUTO_CROSS, val);
 }
 
 static int marvell_config_aneg(struct phy_device *phydev)
@@ -824,14 +809,19 @@ static int m88e1111_config_init_rgmii_delays(struct phy_device *phydev)
 {
 	int delay;
 
-	if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) {
+	switch (phydev->interface) {
+	case PHY_INTERFACE_MODE_RGMII_ID:
 		delay = MII_M1111_RGMII_RX_DELAY | MII_M1111_RGMII_TX_DELAY;
-	} else if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) {
+		break;
+	case PHY_INTERFACE_MODE_RGMII_RXID:
 		delay = MII_M1111_RGMII_RX_DELAY;
-	} else if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) {
+		break;
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		delay = MII_M1111_RGMII_TX_DELAY;
-	} else {
+		break;
+	default:
 		delay = 0;
+		break;
 	}
 
 	return phy_modify(phydev, MII_M1111_PHY_EXT_CR,
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 6045ad3def12..53f034fc2ef7 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -175,6 +175,7 @@ EXPORT_SYMBOL(mdiobus_alloc_size);
 static void mdiobus_release(struct device *d)
 {
 	struct mii_bus *bus = to_mii_bus(d);
+
 	BUG_ON(bus->state != MDIOBUS_RELEASED &&
 	       /* for compatibility with error handling in drivers */
 	       bus->state != MDIOBUS_ALLOCATED);
@@ -458,8 +459,7 @@ static void of_mdiobus_link_mdiodev(struct mii_bus *bus,
 			continue;
 
 		if (addr == mdiodev->addr) {
-			dev->of_node = child;
-			dev->fwnode = of_fwnode_handle(child);
+			device_set_node(dev, of_fwnode_handle(child));
 			return;
 		}
 	}
diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c
index 0837319a52d7..c94cb5382dc9 100644
--- a/drivers/net/phy/mdio_device.c
+++ b/drivers/net/phy/mdio_device.c
@@ -77,7 +77,7 @@ int mdio_device_register(struct mdio_device *mdiodev)
 {
 	int err;
 
-	dev_dbg(&mdiodev->dev, "mdio_device_register\n");
+	dev_dbg(&mdiodev->dev, "%s\n", __func__);
 
 	err = mdiobus_register_device(mdiodev);
 	if (err)
@@ -188,7 +188,7 @@ int mdio_driver_register(struct mdio_driver *drv)
 	struct mdio_driver_common *mdiodrv = &drv->mdiodrv;
 	int retval;
 
-	pr_debug("mdio_driver_register: %s\n", mdiodrv->driver.name);
+	pr_debug("%s: %s\n", __func__, mdiodrv->driver.name);
 
 	mdiodrv->driver.bus = &mdio_bus_type;
 	mdiodrv->driver.probe = mdio_probe;
diff --git a/drivers/net/phy/mediatek-ge.c b/drivers/net/phy/mediatek-ge.c
new file mode 100644
index 000000000000..11ff335d6228
--- /dev/null
+++ b/drivers/net/phy/mediatek-ge.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0+
+#include <linux/bitfield.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+
+#define MTK_EXT_PAGE_ACCESS		0x1f
+#define MTK_PHY_PAGE_STANDARD		0x0000
+#define MTK_PHY_PAGE_EXTENDED		0x0001
+#define MTK_PHY_PAGE_EXTENDED_2		0x0002
+#define MTK_PHY_PAGE_EXTENDED_3		0x0003
+#define MTK_PHY_PAGE_EXTENDED_2A30	0x2a30
+#define MTK_PHY_PAGE_EXTENDED_52B5	0x52b5
+
+static int mtk_gephy_read_page(struct phy_device *phydev)
+{
+	return __phy_read(phydev, MTK_EXT_PAGE_ACCESS);
+}
+
+static int mtk_gephy_write_page(struct phy_device *phydev, int page)
+{
+	return __phy_write(phydev, MTK_EXT_PAGE_ACCESS, page);
+}
+
+static void mtk_gephy_config_init(struct phy_device *phydev)
+{
+	/* Disable EEE */
+	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, 0);
+
+	/* Enable HW auto downshift */
+	phy_modify_paged(phydev, MTK_PHY_PAGE_EXTENDED, 0x14, 0, BIT(4));
+
+	/* Increase SlvDPSready time */
+	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
+	__phy_write(phydev, 0x10, 0xafae);
+	__phy_write(phydev, 0x12, 0x2f);
+	__phy_write(phydev, 0x10, 0x8fae);
+	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
+
+	/* Adjust 100_mse_threshold */
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x123, 0xffff);
+
+	/* Disable mcc */
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, 0xa6, 0x300);
+}
+
+static int mt7530_phy_config_init(struct phy_device *phydev)
+{
+	mtk_gephy_config_init(phydev);
+
+	/* Increase post_update_timer */
+	phy_write_paged(phydev, MTK_PHY_PAGE_EXTENDED_3, 0x11, 0x4b);
+
+	return 0;
+}
+
+static int mt7531_phy_config_init(struct phy_device *phydev)
+{
+	if (phydev->interface != PHY_INTERFACE_MODE_INTERNAL)
+		return -EINVAL;
+
+	mtk_gephy_config_init(phydev);
+
+	/* PHY link down power saving enable */
+	phy_set_bits(phydev, 0x17, BIT(4));
+	phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, 0xc6, 0x300);
+
+	/* Set TX Pair delay selection */
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x13, 0x404);
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x14, 0x404);
+
+	return 0;
+}
+
+static struct phy_driver mtk_gephy_driver[] = {
+	{
+		PHY_ID_MATCH_EXACT(0x03a29412),
+		.name		= "MediaTek MT7530 PHY",
+		.config_init	= mt7530_phy_config_init,
+		/* Interrupts are handled by the switch, not the PHY
+		 * itself.
+		 */
+		.config_intr	= genphy_no_config_intr,
+		.handle_interrupt = genphy_handle_interrupt_no_ack,
+		.read_page	= mtk_gephy_read_page,
+		.write_page	= mtk_gephy_write_page,
+	},
+	{
+		PHY_ID_MATCH_EXACT(0x03a29441),
+		.name		= "MediaTek MT7531 PHY",
+		.config_init	= mt7531_phy_config_init,
+		/* Interrupts are handled by the switch, not the PHY
+		 * itself.
+		 */
+		.config_intr	= genphy_no_config_intr,
+		.handle_interrupt = genphy_handle_interrupt_no_ack,
+		.read_page	= mtk_gephy_read_page,
+		.write_page	= mtk_gephy_write_page,
+	},
+};
+
+module_phy_driver(mtk_gephy_driver);
+
+static struct mdio_device_id __maybe_unused mtk_gephy_tbl[] = {
+	{ PHY_ID_MATCH_VENDOR(0x03a29400) },
+	{ }
+};
+
+MODULE_DESCRIPTION("MediaTek Gigabit Ethernet PHY driver");
+MODULE_AUTHOR("DENG, Qingfang <dqfext@gmail.com>");
+MODULE_LICENSE("GPL");
+
+MODULE_DEVICE_TABLE(mdio, mtk_gephy_tbl);
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index a14a00328fa3..4d53886f7d51 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -20,6 +20,7 @@
  */
 
 #include <linux/bitfield.h>
+#include <linux/ethtool_netlink.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/phy.h>
@@ -38,42 +39,60 @@
 
 /* general Interrupt control/status reg in vendor specific block. */
 #define MII_KSZPHY_INTCS			0x1B
-#define	KSZPHY_INTCS_JABBER			BIT(15)
-#define	KSZPHY_INTCS_RECEIVE_ERR		BIT(14)
-#define	KSZPHY_INTCS_PAGE_RECEIVE		BIT(13)
-#define	KSZPHY_INTCS_PARELLEL			BIT(12)
-#define	KSZPHY_INTCS_LINK_PARTNER_ACK		BIT(11)
-#define	KSZPHY_INTCS_LINK_DOWN			BIT(10)
-#define	KSZPHY_INTCS_REMOTE_FAULT		BIT(9)
-#define	KSZPHY_INTCS_LINK_UP			BIT(8)
-#define	KSZPHY_INTCS_ALL			(KSZPHY_INTCS_LINK_UP |\
+#define KSZPHY_INTCS_JABBER			BIT(15)
+#define KSZPHY_INTCS_RECEIVE_ERR		BIT(14)
+#define KSZPHY_INTCS_PAGE_RECEIVE		BIT(13)
+#define KSZPHY_INTCS_PARELLEL			BIT(12)
+#define KSZPHY_INTCS_LINK_PARTNER_ACK		BIT(11)
+#define KSZPHY_INTCS_LINK_DOWN			BIT(10)
+#define KSZPHY_INTCS_REMOTE_FAULT		BIT(9)
+#define KSZPHY_INTCS_LINK_UP			BIT(8)
+#define KSZPHY_INTCS_ALL			(KSZPHY_INTCS_LINK_UP |\
 						KSZPHY_INTCS_LINK_DOWN)
-#define	KSZPHY_INTCS_LINK_DOWN_STATUS		BIT(2)
-#define	KSZPHY_INTCS_LINK_UP_STATUS		BIT(0)
-#define	KSZPHY_INTCS_STATUS			(KSZPHY_INTCS_LINK_DOWN_STATUS |\
+#define KSZPHY_INTCS_LINK_DOWN_STATUS		BIT(2)
+#define KSZPHY_INTCS_LINK_UP_STATUS		BIT(0)
+#define KSZPHY_INTCS_STATUS			(KSZPHY_INTCS_LINK_DOWN_STATUS |\
 						 KSZPHY_INTCS_LINK_UP_STATUS)
 
+/* LinkMD Control/Status */
+#define KSZ8081_LMD				0x1d
+#define KSZ8081_LMD_ENABLE_TEST			BIT(15)
+#define KSZ8081_LMD_STAT_NORMAL			0
+#define KSZ8081_LMD_STAT_OPEN			1
+#define KSZ8081_LMD_STAT_SHORT			2
+#define KSZ8081_LMD_STAT_FAIL			3
+#define KSZ8081_LMD_STAT_MASK			GENMASK(14, 13)
+/* Short cable (<10 meter) has been detected by LinkMD */
+#define KSZ8081_LMD_SHORT_INDICATOR		BIT(12)
+#define KSZ8081_LMD_DELTA_TIME_MASK		GENMASK(8, 0)
+
 /* PHY Control 1 */
-#define	MII_KSZPHY_CTRL_1			0x1e
+#define MII_KSZPHY_CTRL_1			0x1e
+#define KSZ8081_CTRL1_MDIX_STAT			BIT(4)
 
 /* PHY Control 2 / PHY Control (if no PHY Control 1) */
-#define	MII_KSZPHY_CTRL_2			0x1f
-#define	MII_KSZPHY_CTRL				MII_KSZPHY_CTRL_2
+#define MII_KSZPHY_CTRL_2			0x1f
+#define MII_KSZPHY_CTRL				MII_KSZPHY_CTRL_2
 /* bitmap of PHY register to set interrupt mode */
+#define KSZ8081_CTRL2_HP_MDIX			BIT(15)
+#define KSZ8081_CTRL2_MDI_MDI_X_SELECT		BIT(14)
+#define KSZ8081_CTRL2_DISABLE_AUTO_MDIX		BIT(13)
+#define KSZ8081_CTRL2_FORCE_LINK		BIT(11)
+#define KSZ8081_CTRL2_POWER_SAVING		BIT(10)
 #define KSZPHY_CTRL_INT_ACTIVE_HIGH		BIT(9)
 #define KSZPHY_RMII_REF_CLK_SEL			BIT(7)
 
 /* Write/read to/from extended registers */
-#define MII_KSZPHY_EXTREG                       0x0b
-#define KSZPHY_EXTREG_WRITE                     0x8000
+#define MII_KSZPHY_EXTREG			0x0b
+#define KSZPHY_EXTREG_WRITE			0x8000
 
-#define MII_KSZPHY_EXTREG_WRITE                 0x0c
-#define MII_KSZPHY_EXTREG_READ                  0x0d
+#define MII_KSZPHY_EXTREG_WRITE			0x0c
+#define MII_KSZPHY_EXTREG_READ			0x0d
 
 /* Extended registers */
-#define MII_KSZPHY_CLK_CONTROL_PAD_SKEW         0x104
-#define MII_KSZPHY_RX_DATA_PAD_SKEW             0x105
-#define MII_KSZPHY_TX_DATA_PAD_SKEW             0x106
+#define MII_KSZPHY_CLK_CONTROL_PAD_SKEW		0x104
+#define MII_KSZPHY_RX_DATA_PAD_SKEW		0x105
+#define MII_KSZPHY_TX_DATA_PAD_SKEW		0x106
 
 #define PS_TO_REG				200
 
@@ -422,6 +441,87 @@ static int ksz8081_config_init(struct phy_device *phydev)
 	return kszphy_config_init(phydev);
 }
 
+static int ksz8081_config_mdix(struct phy_device *phydev, u8 ctrl)
+{
+	u16 val;
+
+	switch (ctrl) {
+	case ETH_TP_MDI:
+		val = KSZ8081_CTRL2_DISABLE_AUTO_MDIX;
+		break;
+	case ETH_TP_MDI_X:
+		val = KSZ8081_CTRL2_DISABLE_AUTO_MDIX |
+			KSZ8081_CTRL2_MDI_MDI_X_SELECT;
+		break;
+	case ETH_TP_MDI_AUTO:
+		val = 0;
+		break;
+	default:
+		return 0;
+	}
+
+	return phy_modify(phydev, MII_KSZPHY_CTRL_2,
+			  KSZ8081_CTRL2_HP_MDIX |
+			  KSZ8081_CTRL2_MDI_MDI_X_SELECT |
+			  KSZ8081_CTRL2_DISABLE_AUTO_MDIX,
+			  KSZ8081_CTRL2_HP_MDIX | val);
+}
+
+static int ksz8081_config_aneg(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = genphy_config_aneg(phydev);
+	if (ret)
+		return ret;
+
+	/* The MDI-X configuration is automatically changed by the PHY after
+	 * switching from autoneg off to on. So, take MDI-X configuration under
+	 * own control and set it after autoneg configuration was done.
+	 */
+	return ksz8081_config_mdix(phydev, phydev->mdix_ctrl);
+}
+
+static int ksz8081_mdix_update(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = phy_read(phydev, MII_KSZPHY_CTRL_2);
+	if (ret < 0)
+		return ret;
+
+	if (ret & KSZ8081_CTRL2_DISABLE_AUTO_MDIX) {
+		if (ret & KSZ8081_CTRL2_MDI_MDI_X_SELECT)
+			phydev->mdix_ctrl = ETH_TP_MDI_X;
+		else
+			phydev->mdix_ctrl = ETH_TP_MDI;
+	} else {
+		phydev->mdix_ctrl = ETH_TP_MDI_AUTO;
+	}
+
+	ret = phy_read(phydev, MII_KSZPHY_CTRL_1);
+	if (ret < 0)
+		return ret;
+
+	if (ret & KSZ8081_CTRL1_MDIX_STAT)
+		phydev->mdix = ETH_TP_MDI;
+	else
+		phydev->mdix = ETH_TP_MDI_X;
+
+	return 0;
+}
+
+static int ksz8081_read_status(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = ksz8081_mdix_update(phydev);
+	if (ret < 0)
+		return ret;
+
+	return genphy_read_status(phydev);
+}
+
 static int ksz8061_config_init(struct phy_device *phydev)
 {
 	int ret;
@@ -488,8 +588,7 @@ static int ksz9021_load_values_from_of(struct phy_device *phydev,
 
 static int ksz9021_config_init(struct phy_device *phydev)
 {
-	const struct device *dev = &phydev->mdio.dev;
-	const struct device_node *of_node = dev->of_node;
+	const struct device_node *of_node;
 	const struct device *dev_walker;
 
 	/* The Micrel driver has a deprecated option to place phy OF
@@ -711,8 +810,7 @@ static int ksz9031_config_rgmii_delay(struct phy_device *phydev)
 
 static int ksz9031_config_init(struct phy_device *phydev)
 {
-	const struct device *dev = &phydev->mdio.dev;
-	const struct device_node *of_node = dev->of_node;
+	const struct device_node *of_node;
 	static const char *clk_skews[2] = {"rxc-skew-ps", "txc-skew-ps"};
 	static const char *rx_data_skews[4] = {
 		"rxd0-skew-ps", "rxd1-skew-ps",
@@ -907,8 +1005,7 @@ static int ksz9131_config_rgmii_delay(struct phy_device *phydev)
 
 static int ksz9131_config_init(struct phy_device *phydev)
 {
-	const struct device *dev = &phydev->mdio.dev;
-	struct device_node *of_node = dev->of_node;
+	struct device_node *of_node;
 	char *clk_skews[2] = {"rxc-skew-psec", "txc-skew-psec"};
 	char *rx_data_skews[4] = {
 		"rxd0-skew-psec", "rxd1-skew-psec",
@@ -1048,6 +1145,92 @@ static int ksz8873mll_config_aneg(struct phy_device *phydev)
 	return 0;
 }
 
+static int ksz886x_config_mdix(struct phy_device *phydev, u8 ctrl)
+{
+	u16 val;
+
+	switch (ctrl) {
+	case ETH_TP_MDI:
+		val = KSZ886X_BMCR_DISABLE_AUTO_MDIX;
+		break;
+	case ETH_TP_MDI_X:
+		/* Note: The naming of the bit KSZ886X_BMCR_FORCE_MDI is bit
+		 * counter intuitive, the "-X" in "1 = Force MDI" in the data
+		 * sheet seems to be missing:
+		 * 1 = Force MDI (sic!) (transmit on RX+/RX- pins)
+		 * 0 = Normal operation (transmit on TX+/TX- pins)
+		 */
+		val = KSZ886X_BMCR_DISABLE_AUTO_MDIX | KSZ886X_BMCR_FORCE_MDI;
+		break;
+	case ETH_TP_MDI_AUTO:
+		val = 0;
+		break;
+	default:
+		return 0;
+	}
+
+	return phy_modify(phydev, MII_BMCR,
+			  KSZ886X_BMCR_HP_MDIX | KSZ886X_BMCR_FORCE_MDI |
+			  KSZ886X_BMCR_DISABLE_AUTO_MDIX,
+			  KSZ886X_BMCR_HP_MDIX | val);
+}
+
+static int ksz886x_config_aneg(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = genphy_config_aneg(phydev);
+	if (ret)
+		return ret;
+
+	/* The MDI-X configuration is automatically changed by the PHY after
+	 * switching from autoneg off to on. So, take MDI-X configuration under
+	 * own control and set it after autoneg configuration was done.
+	 */
+	return ksz886x_config_mdix(phydev, phydev->mdix_ctrl);
+}
+
+static int ksz886x_mdix_update(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = phy_read(phydev, MII_BMCR);
+	if (ret < 0)
+		return ret;
+
+	if (ret & KSZ886X_BMCR_DISABLE_AUTO_MDIX) {
+		if (ret & KSZ886X_BMCR_FORCE_MDI)
+			phydev->mdix_ctrl = ETH_TP_MDI_X;
+		else
+			phydev->mdix_ctrl = ETH_TP_MDI;
+	} else {
+		phydev->mdix_ctrl = ETH_TP_MDI_AUTO;
+	}
+
+	ret = phy_read(phydev, MII_KSZPHY_CTRL);
+	if (ret < 0)
+		return ret;
+
+	/* Same reverse logic as KSZ886X_BMCR_FORCE_MDI */
+	if (ret & KSZ886X_CTRL_MDIX_STAT)
+		phydev->mdix = ETH_TP_MDI_X;
+	else
+		phydev->mdix = ETH_TP_MDI;
+
+	return 0;
+}
+
+static int ksz886x_read_status(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = ksz886x_mdix_update(phydev);
+	if (ret < 0)
+		return ret;
+
+	return genphy_read_status(phydev);
+}
+
 static int kszphy_get_sset_count(struct phy_device *phydev)
 {
 	return ARRAY_SIZE(kszphy_hw_stats);
@@ -1193,6 +1376,167 @@ static int kszphy_probe(struct phy_device *phydev)
 	return 0;
 }
 
+static int ksz886x_cable_test_start(struct phy_device *phydev)
+{
+	if (phydev->dev_flags & MICREL_KSZ8_P1_ERRATA)
+		return -EOPNOTSUPP;
+
+	/* If autoneg is enabled, we won't be able to test cross pair
+	 * short. In this case, the PHY will "detect" a link and
+	 * confuse the internal state machine - disable auto neg here.
+	 * If autoneg is disabled, we should set the speed to 10mbit.
+	 */
+	return phy_clear_bits(phydev, MII_BMCR, BMCR_ANENABLE | BMCR_SPEED100);
+}
+
+static int ksz886x_cable_test_result_trans(u16 status)
+{
+	switch (FIELD_GET(KSZ8081_LMD_STAT_MASK, status)) {
+	case KSZ8081_LMD_STAT_NORMAL:
+		return ETHTOOL_A_CABLE_RESULT_CODE_OK;
+	case KSZ8081_LMD_STAT_SHORT:
+		return ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT;
+	case KSZ8081_LMD_STAT_OPEN:
+		return ETHTOOL_A_CABLE_RESULT_CODE_OPEN;
+	case KSZ8081_LMD_STAT_FAIL:
+		fallthrough;
+	default:
+		return ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC;
+	}
+}
+
+static bool ksz886x_cable_test_failed(u16 status)
+{
+	return FIELD_GET(KSZ8081_LMD_STAT_MASK, status) ==
+		KSZ8081_LMD_STAT_FAIL;
+}
+
+static bool ksz886x_cable_test_fault_length_valid(u16 status)
+{
+	switch (FIELD_GET(KSZ8081_LMD_STAT_MASK, status)) {
+	case KSZ8081_LMD_STAT_OPEN:
+		fallthrough;
+	case KSZ8081_LMD_STAT_SHORT:
+		return true;
+	}
+	return false;
+}
+
+static int ksz886x_cable_test_fault_length(u16 status)
+{
+	int dt;
+
+	/* According to the data sheet the distance to the fault is
+	 * DELTA_TIME * 0.4 meters.
+	 */
+	dt = FIELD_GET(KSZ8081_LMD_DELTA_TIME_MASK, status);
+
+	return (dt * 400) / 10;
+}
+
+static int ksz886x_cable_test_wait_for_completion(struct phy_device *phydev)
+{
+	int val, ret;
+
+	ret = phy_read_poll_timeout(phydev, KSZ8081_LMD, val,
+				    !(val & KSZ8081_LMD_ENABLE_TEST),
+				    30000, 100000, true);
+
+	return ret < 0 ? ret : 0;
+}
+
+static int ksz886x_cable_test_one_pair(struct phy_device *phydev, int pair)
+{
+	static const int ethtool_pair[] = {
+		ETHTOOL_A_CABLE_PAIR_A,
+		ETHTOOL_A_CABLE_PAIR_B,
+	};
+	int ret, val, mdix;
+
+	/* There is no way to choice the pair, like we do one ksz9031.
+	 * We can workaround this limitation by using the MDI-X functionality.
+	 */
+	if (pair == 0)
+		mdix = ETH_TP_MDI;
+	else
+		mdix = ETH_TP_MDI_X;
+
+	switch (phydev->phy_id & MICREL_PHY_ID_MASK) {
+	case PHY_ID_KSZ8081:
+		ret = ksz8081_config_mdix(phydev, mdix);
+		break;
+	case PHY_ID_KSZ886X:
+		ret = ksz886x_config_mdix(phydev, mdix);
+		break;
+	default:
+		ret = -ENODEV;
+	}
+
+	if (ret)
+		return ret;
+
+	/* Now we are ready to fire. This command will send a 100ns pulse
+	 * to the pair.
+	 */
+	ret = phy_write(phydev, KSZ8081_LMD, KSZ8081_LMD_ENABLE_TEST);
+	if (ret)
+		return ret;
+
+	ret = ksz886x_cable_test_wait_for_completion(phydev);
+	if (ret)
+		return ret;
+
+	val = phy_read(phydev, KSZ8081_LMD);
+	if (val < 0)
+		return val;
+
+	if (ksz886x_cable_test_failed(val))
+		return -EAGAIN;
+
+	ret = ethnl_cable_test_result(phydev, ethtool_pair[pair],
+				      ksz886x_cable_test_result_trans(val));
+	if (ret)
+		return ret;
+
+	if (!ksz886x_cable_test_fault_length_valid(val))
+		return 0;
+
+	return ethnl_cable_test_fault_length(phydev, ethtool_pair[pair],
+					     ksz886x_cable_test_fault_length(val));
+}
+
+static int ksz886x_cable_test_get_status(struct phy_device *phydev,
+					 bool *finished)
+{
+	unsigned long pair_mask = 0x3;
+	int retries = 20;
+	int pair, ret;
+
+	*finished = false;
+
+	/* Try harder if link partner is active */
+	while (pair_mask && retries--) {
+		for_each_set_bit(pair, &pair_mask, 4) {
+			ret = ksz886x_cable_test_one_pair(phydev, pair);
+			if (ret == -EAGAIN)
+				continue;
+			if (ret < 0)
+				return ret;
+			clear_bit(pair, &pair_mask);
+		}
+		/* If link partner is in autonegotiation mode it will send 2ms
+		 * of FLPs with at least 6ms of silence.
+		 * Add 2ms sleep to have better chances to hit this silence.
+		 */
+		if (pair_mask)
+			msleep(2);
+	}
+
+	*finished = true;
+
+	return ret;
+}
+
 static struct phy_driver ksphy_driver[] = {
 {
 	.phy_id		= PHY_ID_KS8737,
@@ -1299,11 +1643,14 @@ static struct phy_driver ksphy_driver[] = {
 	.phy_id		= PHY_ID_KSZ8081,
 	.name		= "Micrel KSZ8081 or KSZ8091",
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
+	.flags		= PHY_POLL_CABLE_TEST,
 	/* PHY_BASIC_FEATURES */
 	.driver_data	= &ksz8081_type,
 	.probe		= kszphy_probe,
 	.config_init	= ksz8081_config_init,
 	.soft_reset	= genphy_soft_reset,
+	.config_aneg	= ksz8081_config_aneg,
+	.read_status	= ksz8081_read_status,
 	.config_intr	= kszphy_config_intr,
 	.handle_interrupt = kszphy_handle_interrupt,
 	.get_sset_count = kszphy_get_sset_count,
@@ -1311,6 +1658,8 @@ static struct phy_driver ksphy_driver[] = {
 	.get_stats	= kszphy_get_stats,
 	.suspend	= kszphy_suspend,
 	.resume		= kszphy_resume,
+	.cable_test_start	= ksz886x_cable_test_start,
+	.cable_test_get_status	= ksz886x_cable_test_get_status,
 }, {
 	.phy_id		= PHY_ID_KSZ8061,
 	.name		= "Micrel KSZ8061",
@@ -1399,9 +1748,14 @@ static struct phy_driver ksphy_driver[] = {
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.name		= "Micrel KSZ8851 Ethernet MAC or KSZ886X Switch",
 	/* PHY_BASIC_FEATURES */
+	.flags		= PHY_POLL_CABLE_TEST,
 	.config_init	= kszphy_config_init,
+	.config_aneg	= ksz886x_config_aneg,
+	.read_status	= ksz886x_read_status,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
+	.cable_test_start	= ksz886x_cable_test_start,
+	.cable_test_get_status	= ksz886x_cable_test_get_status,
 }, {
 	.name		= "Micrel KSZ87XX Switch",
 	/* PHY_BASIC_FEATURES */
diff --git a/drivers/net/phy/mii_timestamper.c b/drivers/net/phy/mii_timestamper.c
index b71b7456462d..51ae0593a04f 100644
--- a/drivers/net/phy/mii_timestamper.c
+++ b/drivers/net/phy/mii_timestamper.c
@@ -111,6 +111,9 @@ void unregister_mii_timestamper(struct mii_timestamper *mii_ts)
 	struct mii_timestamping_desc *desc;
 	struct list_head *this;
 
+	if (!mii_ts)
+		return;
+
 	/* mii_timestamper statically registered by the PHY driver won't use the
 	 * register_mii_timestamper() and thus don't have ->device set. Don't
 	 * try to unregister these.
diff --git a/drivers/net/phy/motorcomm.c b/drivers/net/phy/motorcomm.c
new file mode 100644
index 000000000000..7e6ac2c5e27e
--- /dev/null
+++ b/drivers/net/phy/motorcomm.c
@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Driver for Motorcomm PHYs
+ *
+ * Author: Peter Geis <pgwipeout@gmail.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+
+#define PHY_ID_YT8511		0x0000010a
+
+#define YT8511_PAGE_SELECT	0x1e
+#define YT8511_PAGE		0x1f
+#define YT8511_EXT_CLK_GATE	0x0c
+#define YT8511_EXT_DELAY_DRIVE	0x0d
+#define YT8511_EXT_SLEEP_CTRL	0x27
+
+/* 2b00 25m from pll
+ * 2b01 25m from xtl *default*
+ * 2b10 62.m from pll
+ * 2b11 125m from pll
+ */
+#define YT8511_CLK_125M		(BIT(2) | BIT(1))
+#define YT8511_PLLON_SLP	BIT(14)
+
+/* RX Delay enabled = 1.8ns 1000T, 8ns 10/100T */
+#define YT8511_DELAY_RX		BIT(0)
+
+/* TX Gig-E Delay is bits 7:4, default 0x5
+ * TX Fast-E Delay is bits 15:12, default 0xf
+ * Delay = 150ps * N - 250ps
+ * On = 2000ps, off = 50ps
+ */
+#define YT8511_DELAY_GE_TX_EN	(0xf << 4)
+#define YT8511_DELAY_GE_TX_DIS	(0x2 << 4)
+#define YT8511_DELAY_FE_TX_EN	(0xf << 12)
+#define YT8511_DELAY_FE_TX_DIS	(0x2 << 12)
+
+static int yt8511_read_page(struct phy_device *phydev)
+{
+	return __phy_read(phydev, YT8511_PAGE_SELECT);
+};
+
+static int yt8511_write_page(struct phy_device *phydev, int page)
+{
+	return __phy_write(phydev, YT8511_PAGE_SELECT, page);
+};
+
+static int yt8511_config_init(struct phy_device *phydev)
+{
+	int oldpage, ret = 0;
+	unsigned int ge, fe;
+
+	oldpage = phy_select_page(phydev, YT8511_EXT_CLK_GATE);
+	if (oldpage < 0)
+		goto err_restore_page;
+
+	/* set rgmii delay mode */
+	switch (phydev->interface) {
+	case PHY_INTERFACE_MODE_RGMII:
+		ge = YT8511_DELAY_GE_TX_DIS;
+		fe = YT8511_DELAY_FE_TX_DIS;
+		break;
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+		ge = YT8511_DELAY_RX | YT8511_DELAY_GE_TX_DIS;
+		fe = YT8511_DELAY_FE_TX_DIS;
+		break;
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		ge = YT8511_DELAY_GE_TX_EN;
+		fe = YT8511_DELAY_FE_TX_EN;
+		break;
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		ge = YT8511_DELAY_RX | YT8511_DELAY_GE_TX_EN;
+		fe = YT8511_DELAY_FE_TX_EN;
+		break;
+	default: /* do not support other modes */
+		ret = -EOPNOTSUPP;
+		goto err_restore_page;
+	}
+
+	ret = __phy_modify(phydev, YT8511_PAGE, (YT8511_DELAY_RX | YT8511_DELAY_GE_TX_EN), ge);
+	if (ret < 0)
+		goto err_restore_page;
+
+	/* set clock mode to 125mhz */
+	ret = __phy_modify(phydev, YT8511_PAGE, 0, YT8511_CLK_125M);
+	if (ret < 0)
+		goto err_restore_page;
+
+	/* fast ethernet delay is in a separate page */
+	ret = __phy_write(phydev, YT8511_PAGE_SELECT, YT8511_EXT_DELAY_DRIVE);
+	if (ret < 0)
+		goto err_restore_page;
+
+	ret = __phy_modify(phydev, YT8511_PAGE, YT8511_DELAY_FE_TX_EN, fe);
+	if (ret < 0)
+		goto err_restore_page;
+
+	/* leave pll enabled in sleep */
+	ret = __phy_write(phydev, YT8511_PAGE_SELECT, YT8511_EXT_SLEEP_CTRL);
+	if (ret < 0)
+		goto err_restore_page;
+
+	ret = __phy_modify(phydev, YT8511_PAGE, 0, YT8511_PLLON_SLP);
+	if (ret < 0)
+		goto err_restore_page;
+
+err_restore_page:
+	return phy_restore_page(phydev, oldpage, ret);
+}
+
+static struct phy_driver motorcomm_phy_drvs[] = {
+	{
+		PHY_ID_MATCH_EXACT(PHY_ID_YT8511),
+		.name		= "YT8511 Gigabit Ethernet",
+		.config_init	= yt8511_config_init,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.read_page	= yt8511_read_page,
+		.write_page	= yt8511_write_page,
+	},
+};
+
+module_phy_driver(motorcomm_phy_drvs);
+
+MODULE_DESCRIPTION("Motorcomm PHY driver");
+MODULE_AUTHOR("Peter Geis");
+MODULE_LICENSE("GPL");
+
+static const struct mdio_device_id __maybe_unused motorcomm_tbl[] = {
+	{ PHY_ID_MATCH_EXACT(PHY_ID_YT8511) },
+	{ /* sentinal */ }
+};
+
+MODULE_DEVICE_TABLE(mdio, motorcomm_tbl);
diff --git a/drivers/net/phy/national.c b/drivers/net/phy/national.c
index 46160baaafe3..9ae9cc6b23c2 100644
--- a/drivers/net/phy/national.c
+++ b/drivers/net/phy/national.c
@@ -68,7 +68,8 @@ static int ns_ack_interrupt(struct phy_device *phydev)
 		return ret;
 
 	/* Clear the interrupt status bit by writing a “1”
-	 * to the corresponding bit in INT_CLEAR (2:0 are reserved) */
+	 * to the corresponding bit in INT_CLEAR (2:0 are reserved)
+	 */
 	ret = phy_write(phydev, DP83865_INT_CLEAR, ret & ~0x7);
 
 	return ret;
@@ -150,7 +151,8 @@ static int ns_config_init(struct phy_device *phydev)
 {
 	ns_giga_speed_fallback(phydev, ALL_FALLBACK_ON);
 	/* In the latest MAC or switches design, the 10 Mbps loopback
-	   is desired to be turned off. */
+	 * is desired to be turned off.
+	 */
 	ns_10_base_t_hdx_loopack(phydev, hdx_loopback_off);
 	return ns_ack_interrupt(phydev);
 }
diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 26b9c0d7cb9d..91a327f67a42 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -13,6 +13,9 @@
 #include <linux/phy.h>
 #include <linux/processor.h>
 #include <linux/property.h>
+#include <linux/ptp_classify.h>
+#include <linux/ptp_clock_kernel.h>
+#include <linux/net_tstamp.h>
 
 #define PHY_ID_TJA_1103			0x001BB010
 
@@ -57,6 +60,9 @@
 #define VEND1_PORT_CONTROL		0x8040
 #define PORT_CONTROL_EN			BIT(14)
 
+#define VEND1_PORT_ABILITIES		0x8046
+#define PTP_ABILITY			BIT(3)
+
 #define VEND1_PORT_INFRA_CONTROL	0xAC00
 #define PORT_INFRA_CONTROL_EN		BIT(14)
 
@@ -91,13 +97,106 @@
 #define VEND1_TX_IPG_LENGTH		0xAFD1
 #define COUNTER_EN			BIT(15)
 
+#define VEND1_LTC_LOAD_CTRL		0x1105
+#define READ_LTC			BIT(2)
+#define LOAD_LTC			BIT(0)
+
+#define VEND1_LTC_WR_NSEC_0		0x1106
+#define VEND1_LTC_WR_NSEC_1		0x1107
+#define VEND1_LTC_WR_SEC_0		0x1108
+#define VEND1_LTC_WR_SEC_1		0x1109
+
+#define VEND1_LTC_RD_NSEC_0		0x110A
+#define VEND1_LTC_RD_NSEC_1		0x110B
+#define VEND1_LTC_RD_SEC_0		0x110C
+#define VEND1_LTC_RD_SEC_1		0x110D
+
+#define VEND1_RATE_ADJ_SUBNS_0		0x110F
+#define VEND1_RATE_ADJ_SUBNS_1		0x1110
+#define CLK_RATE_ADJ_LD			BIT(15)
+#define CLK_RATE_ADJ_DIR		BIT(14)
+
+#define VEND1_HW_LTC_LOCK_CTRL		0x1115
+#define HW_LTC_LOCK_EN			BIT(0)
+
+#define VEND1_PTP_IRQ_EN		0x1131
+#define VEND1_PTP_IRQ_STATUS		0x1132
+#define PTP_IRQ_EGR_TS			BIT(0)
+
+#define VEND1_RX_TS_INSRT_CTRL		0x114D
+#define RX_TS_INSRT_MODE2		0x02
+
+#define VEND1_EGR_RING_DATA_0		0x114E
+#define VEND1_EGR_RING_DATA_1_SEQ_ID	0x114F
+#define VEND1_EGR_RING_DATA_2_NSEC_15_0	0x1150
+#define VEND1_EGR_RING_DATA_3		0x1151
+#define VEND1_EGR_RING_CTRL		0x1154
+
+#define RING_DATA_0_DOMAIN_NUMBER	GENMASK(7, 0)
+#define RING_DATA_0_MSG_TYPE		GENMASK(11, 8)
+#define RING_DATA_0_SEC_4_2		GENMASK(14, 2)
+#define RING_DATA_0_TS_VALID		BIT(15)
+
+#define RING_DATA_3_NSEC_29_16		GENMASK(13, 0)
+#define RING_DATA_3_SEC_1_0		GENMASK(15, 14)
+#define RING_DATA_5_SEC_16_5		GENMASK(15, 4)
+#define RING_DONE			BIT(0)
+
+#define TS_SEC_MASK			GENMASK(1, 0)
+
+#define VEND1_PORT_FUNC_ENABLES		0x8048
+#define PTP_ENABLE			BIT(3)
+
+#define VEND1_PORT_PTP_CONTROL		0x9000
+#define PORT_PTP_CONTROL_BYPASS		BIT(11)
+
+#define VEND1_PTP_CLK_PERIOD		0x1104
+#define PTP_CLK_PERIOD_100BT1		15ULL
+
+#define VEND1_EVENT_MSG_FILT		0x1148
+#define EVENT_MSG_FILT_ALL		0x0F
+#define EVENT_MSG_FILT_NONE		0x00
+
+#define VEND1_TX_PIPE_DLY_NS		0x1149
+#define VEND1_TX_PIPEDLY_SUBNS		0x114A
+#define VEND1_RX_PIPE_DLY_NS		0x114B
+#define VEND1_RX_PIPEDLY_SUBNS		0x114C
+
 #define RGMII_PERIOD_PS			8000U
 #define PS_PER_DEGREE			div_u64(RGMII_PERIOD_PS, 360)
 #define MIN_ID_PS			1644U
 #define MAX_ID_PS			2260U
 #define DEFAULT_ID_PS			2000U
 
+#define PPM_TO_SUBNS_INC(ppb)	div_u64(GENMASK(31, 0) * (ppb) * \
+					PTP_CLK_PERIOD_100BT1, NSEC_PER_SEC)
+
+#define NXP_C45_SKB_CB(skb)	((struct nxp_c45_skb_cb *)(skb)->cb)
+
+struct nxp_c45_skb_cb {
+	struct ptp_header *header;
+	unsigned int type;
+};
+
+struct nxp_c45_hwts {
+	u32	nsec;
+	u32	sec;
+	u8	domain_number;
+	u16	sequence_id;
+	u8	msg_type;
+};
+
 struct nxp_c45_phy {
+	struct phy_device *phydev;
+	struct mii_timestamper mii_ts;
+	struct ptp_clock *ptp_clock;
+	struct ptp_clock_info caps;
+	struct sk_buff_head tx_queue;
+	struct sk_buff_head rx_queue;
+	/* used to access the PTP registers atomic */
+	struct mutex ptp_lock;
+	int hwts_tx;
+	int hwts_rx;
 	u32 tx_delay;
 	u32 rx_delay;
 };
@@ -110,6 +209,382 @@ struct nxp_c45_phy_stats {
 	u16		mask;
 };
 
+static bool nxp_c45_poll_txts(struct phy_device *phydev)
+{
+	return phydev->irq <= 0;
+}
+
+static int _nxp_c45_ptp_gettimex64(struct ptp_clock_info *ptp,
+				   struct timespec64 *ts,
+				   struct ptp_system_timestamp *sts)
+{
+	struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps);
+
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_LOAD_CTRL,
+		      READ_LTC);
+	ts->tv_nsec = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1,
+				   VEND1_LTC_RD_NSEC_0);
+	ts->tv_nsec |= phy_read_mmd(priv->phydev, MDIO_MMD_VEND1,
+				    VEND1_LTC_RD_NSEC_1) << 16;
+	ts->tv_sec = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1,
+				  VEND1_LTC_RD_SEC_0);
+	ts->tv_sec |= phy_read_mmd(priv->phydev, MDIO_MMD_VEND1,
+				   VEND1_LTC_RD_SEC_1) << 16;
+
+	return 0;
+}
+
+static int nxp_c45_ptp_gettimex64(struct ptp_clock_info *ptp,
+				  struct timespec64 *ts,
+				  struct ptp_system_timestamp *sts)
+{
+	struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps);
+
+	mutex_lock(&priv->ptp_lock);
+	_nxp_c45_ptp_gettimex64(ptp, ts, sts);
+	mutex_unlock(&priv->ptp_lock);
+
+	return 0;
+}
+
+static int _nxp_c45_ptp_settime64(struct ptp_clock_info *ptp,
+				  const struct timespec64 *ts)
+{
+	struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps);
+
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_WR_NSEC_0,
+		      ts->tv_nsec);
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_WR_NSEC_1,
+		      ts->tv_nsec >> 16);
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_WR_SEC_0,
+		      ts->tv_sec);
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_WR_SEC_1,
+		      ts->tv_sec >> 16);
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_LOAD_CTRL,
+		      LOAD_LTC);
+
+	return 0;
+}
+
+static int nxp_c45_ptp_settime64(struct ptp_clock_info *ptp,
+				 const struct timespec64 *ts)
+{
+	struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps);
+
+	mutex_lock(&priv->ptp_lock);
+	_nxp_c45_ptp_settime64(ptp, ts);
+	mutex_unlock(&priv->ptp_lock);
+
+	return 0;
+}
+
+static int nxp_c45_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
+{
+	struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps);
+	s32 ppb = scaled_ppm_to_ppb(scaled_ppm);
+	u64 subns_inc_val;
+	bool inc;
+
+	mutex_lock(&priv->ptp_lock);
+	inc = ppb >= 0;
+	ppb = abs(ppb);
+
+	subns_inc_val = PPM_TO_SUBNS_INC(ppb);
+
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_RATE_ADJ_SUBNS_0,
+		      subns_inc_val);
+	subns_inc_val >>= 16;
+	subns_inc_val |= CLK_RATE_ADJ_LD;
+	if (inc)
+		subns_inc_val |= CLK_RATE_ADJ_DIR;
+
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_RATE_ADJ_SUBNS_1,
+		      subns_inc_val);
+	mutex_unlock(&priv->ptp_lock);
+
+	return 0;
+}
+
+static int nxp_c45_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps);
+	struct timespec64 now, then;
+
+	mutex_lock(&priv->ptp_lock);
+	then = ns_to_timespec64(delta);
+	_nxp_c45_ptp_gettimex64(ptp, &now, NULL);
+	now = timespec64_add(now, then);
+	_nxp_c45_ptp_settime64(ptp, &now);
+	mutex_unlock(&priv->ptp_lock);
+
+	return 0;
+}
+
+static void nxp_c45_reconstruct_ts(struct timespec64 *ts,
+				   struct nxp_c45_hwts *hwts)
+{
+	ts->tv_nsec = hwts->nsec;
+	if ((ts->tv_sec & TS_SEC_MASK) < (hwts->sec & TS_SEC_MASK))
+		ts->tv_sec -= TS_SEC_MASK + 1;
+	ts->tv_sec &= ~TS_SEC_MASK;
+	ts->tv_sec |= hwts->sec & TS_SEC_MASK;
+}
+
+static bool nxp_c45_match_ts(struct ptp_header *header,
+			     struct nxp_c45_hwts *hwts,
+			     unsigned int type)
+{
+	return ntohs(header->sequence_id) == hwts->sequence_id &&
+	       ptp_get_msgtype(header, type) == hwts->msg_type &&
+	       header->domain_number  == hwts->domain_number;
+}
+
+static bool nxp_c45_get_hwtxts(struct nxp_c45_phy *priv,
+			       struct nxp_c45_hwts *hwts)
+{
+	bool valid;
+	u16 reg;
+
+	mutex_lock(&priv->ptp_lock);
+	phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_EGR_RING_CTRL,
+		      RING_DONE);
+	reg = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_EGR_RING_DATA_0);
+	valid = !!(reg & RING_DATA_0_TS_VALID);
+	if (!valid)
+		goto nxp_c45_get_hwtxts_out;
+
+	hwts->domain_number = reg;
+	hwts->msg_type = (reg & RING_DATA_0_MSG_TYPE) >> 8;
+	hwts->sec = (reg & RING_DATA_0_SEC_4_2) >> 10;
+	hwts->sequence_id = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1,
+					 VEND1_EGR_RING_DATA_1_SEQ_ID);
+	hwts->nsec = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1,
+				  VEND1_EGR_RING_DATA_2_NSEC_15_0);
+	reg = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_EGR_RING_DATA_3);
+	hwts->nsec |= (reg & RING_DATA_3_NSEC_29_16) << 16;
+	hwts->sec |= (reg & RING_DATA_3_SEC_1_0) >> 14;
+
+nxp_c45_get_hwtxts_out:
+	mutex_unlock(&priv->ptp_lock);
+	return valid;
+}
+
+static void nxp_c45_process_txts(struct nxp_c45_phy *priv,
+				 struct nxp_c45_hwts *txts)
+{
+	struct sk_buff *skb, *tmp, *skb_match = NULL;
+	struct skb_shared_hwtstamps shhwtstamps;
+	struct timespec64 ts;
+	unsigned long flags;
+	bool ts_match;
+	s64 ts_ns;
+
+	spin_lock_irqsave(&priv->tx_queue.lock, flags);
+	skb_queue_walk_safe(&priv->tx_queue, skb, tmp) {
+		ts_match = nxp_c45_match_ts(NXP_C45_SKB_CB(skb)->header, txts,
+					    NXP_C45_SKB_CB(skb)->type);
+		if (!ts_match)
+			continue;
+		skb_match = skb;
+		__skb_unlink(skb, &priv->tx_queue);
+		break;
+	}
+	spin_unlock_irqrestore(&priv->tx_queue.lock, flags);
+
+	if (skb_match) {
+		nxp_c45_ptp_gettimex64(&priv->caps, &ts, NULL);
+		nxp_c45_reconstruct_ts(&ts, txts);
+		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
+		ts_ns = timespec64_to_ns(&ts);
+		shhwtstamps.hwtstamp = ns_to_ktime(ts_ns);
+		skb_complete_tx_timestamp(skb_match, &shhwtstamps);
+	} else {
+		phydev_warn(priv->phydev,
+			    "the tx timestamp doesn't match with any skb\n");
+	}
+}
+
+static long nxp_c45_do_aux_work(struct ptp_clock_info *ptp)
+{
+	struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps);
+	bool poll_txts = nxp_c45_poll_txts(priv->phydev);
+	struct skb_shared_hwtstamps *shhwtstamps_rx;
+	struct nxp_c45_hwts hwts;
+	bool reschedule = false;
+	struct timespec64 ts;
+	struct sk_buff *skb;
+	bool txts_valid;
+	u32 ts_raw;
+
+	while (!skb_queue_empty_lockless(&priv->tx_queue) && poll_txts) {
+		txts_valid = nxp_c45_get_hwtxts(priv, &hwts);
+		if (unlikely(!txts_valid)) {
+			/* Still more skbs in the queue */
+			reschedule = true;
+			break;
+		}
+
+		nxp_c45_process_txts(priv, &hwts);
+	}
+
+	while ((skb = skb_dequeue(&priv->rx_queue)) != NULL) {
+		nxp_c45_ptp_gettimex64(&priv->caps, &ts, NULL);
+		ts_raw = __be32_to_cpu(NXP_C45_SKB_CB(skb)->header->reserved2);
+		hwts.sec = ts_raw >> 30;
+		hwts.nsec = ts_raw & GENMASK(29, 0);
+		nxp_c45_reconstruct_ts(&ts, &hwts);
+		shhwtstamps_rx = skb_hwtstamps(skb);
+		shhwtstamps_rx->hwtstamp = ns_to_ktime(timespec64_to_ns(&ts));
+		NXP_C45_SKB_CB(skb)->header->reserved2 = 0;
+		netif_rx_ni(skb);
+	}
+
+	return reschedule ? 1 : -1;
+}
+
+static int nxp_c45_init_ptp_clock(struct nxp_c45_phy *priv)
+{
+	priv->caps = (struct ptp_clock_info) {
+		.owner		= THIS_MODULE,
+		.name		= "NXP C45 PHC",
+		.max_adj	= 16666666,
+		.adjfine	= nxp_c45_ptp_adjfine,
+		.adjtime	= nxp_c45_ptp_adjtime,
+		.gettimex64	= nxp_c45_ptp_gettimex64,
+		.settime64	= nxp_c45_ptp_settime64,
+		.do_aux_work	= nxp_c45_do_aux_work,
+	};
+
+	priv->ptp_clock = ptp_clock_register(&priv->caps,
+					     &priv->phydev->mdio.dev);
+
+	if (IS_ERR(priv->ptp_clock))
+		return PTR_ERR(priv->ptp_clock);
+
+	if (!priv->ptp_clock)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void nxp_c45_txtstamp(struct mii_timestamper *mii_ts,
+			     struct sk_buff *skb, int type)
+{
+	struct nxp_c45_phy *priv = container_of(mii_ts, struct nxp_c45_phy,
+						mii_ts);
+
+	switch (priv->hwts_tx) {
+	case HWTSTAMP_TX_ON:
+		NXP_C45_SKB_CB(skb)->type = type;
+		NXP_C45_SKB_CB(skb)->header = ptp_parse_header(skb, type);
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+		skb_queue_tail(&priv->tx_queue, skb);
+		if (nxp_c45_poll_txts(priv->phydev))
+			ptp_schedule_worker(priv->ptp_clock, 0);
+		break;
+	case HWTSTAMP_TX_OFF:
+	default:
+		kfree_skb(skb);
+		break;
+	}
+}
+
+static bool nxp_c45_rxtstamp(struct mii_timestamper *mii_ts,
+			     struct sk_buff *skb, int type)
+{
+	struct nxp_c45_phy *priv = container_of(mii_ts, struct nxp_c45_phy,
+						mii_ts);
+	struct ptp_header *header = ptp_parse_header(skb, type);
+
+	if (!header)
+		return false;
+
+	if (!priv->hwts_rx)
+		return false;
+
+	NXP_C45_SKB_CB(skb)->header = header;
+	skb_queue_tail(&priv->rx_queue, skb);
+	ptp_schedule_worker(priv->ptp_clock, 0);
+
+	return true;
+}
+
+static int nxp_c45_hwtstamp(struct mii_timestamper *mii_ts,
+			    struct ifreq *ifreq)
+{
+	struct nxp_c45_phy *priv = container_of(mii_ts, struct nxp_c45_phy,
+						mii_ts);
+	struct phy_device *phydev = priv->phydev;
+	struct hwtstamp_config cfg;
+
+	if (copy_from_user(&cfg, ifreq->ifr_data, sizeof(cfg)))
+		return -EFAULT;
+
+	if (cfg.tx_type < 0 || cfg.tx_type > HWTSTAMP_TX_ON)
+		return -ERANGE;
+
+	priv->hwts_tx = cfg.tx_type;
+
+	switch (cfg.rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		priv->hwts_rx = 0;
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+		priv->hwts_rx = 1;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	if (priv->hwts_rx || priv->hwts_tx) {
+		phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_EVENT_MSG_FILT,
+			      EVENT_MSG_FILT_ALL);
+		phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+				   VEND1_PORT_PTP_CONTROL,
+				   PORT_PTP_CONTROL_BYPASS);
+	} else {
+		phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_EVENT_MSG_FILT,
+			      EVENT_MSG_FILT_NONE);
+		phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PORT_PTP_CONTROL,
+				 PORT_PTP_CONTROL_BYPASS);
+	}
+
+	if (nxp_c45_poll_txts(priv->phydev))
+		goto nxp_c45_no_ptp_irq;
+
+	if (priv->hwts_tx)
+		phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
+				 VEND1_PTP_IRQ_EN, PTP_IRQ_EGR_TS);
+	else
+		phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+				   VEND1_PTP_IRQ_EN, PTP_IRQ_EGR_TS);
+
+nxp_c45_no_ptp_irq:
+	return copy_to_user(ifreq->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+}
+
+static int nxp_c45_ts_info(struct mii_timestamper *mii_ts,
+			   struct ethtool_ts_info *ts_info)
+{
+	struct nxp_c45_phy *priv = container_of(mii_ts, struct nxp_c45_phy,
+						mii_ts);
+
+	ts_info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+			SOF_TIMESTAMPING_RX_HARDWARE |
+			SOF_TIMESTAMPING_RAW_HARDWARE;
+	ts_info->phc_index = ptp_clock_index(priv->ptp_clock);
+	ts_info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON);
+	ts_info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
+			(1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) |
+			(1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) |
+			(1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT);
+
+	return 0;
+}
+
 static const struct nxp_c45_phy_stats nxp_c45_hw_stats[] = {
 	{ "phy_symbol_error_cnt", MDIO_MMD_VEND1,
 		VEND1_SYMBOL_ERROR_COUNTER, 0, GENMASK(15, 0) },
@@ -205,7 +680,9 @@ static int nxp_c45_config_intr(struct phy_device *phydev)
 
 static irqreturn_t nxp_c45_handle_interrupt(struct phy_device *phydev)
 {
+	struct nxp_c45_phy *priv = phydev->priv;
 	irqreturn_t ret = IRQ_NONE;
+	struct nxp_c45_hwts hwts;
 	int irq;
 
 	irq = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_PHY_IRQ_STATUS);
@@ -216,6 +693,18 @@ static irqreturn_t nxp_c45_handle_interrupt(struct phy_device *phydev)
 		ret = IRQ_HANDLED;
 	}
 
+	/* There is no need for ACK.
+	 * The irq signal will be asserted until the EGR TS FIFO will be
+	 * emptied.
+	 */
+	irq = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_PTP_IRQ_STATUS);
+	if (irq & PTP_IRQ_EGR_TS) {
+		while (nxp_c45_get_hwtxts(priv, &hwts))
+			nxp_c45_process_txts(priv, &hwts);
+
+		ret = IRQ_HANDLED;
+	}
+
 	return ret;
 }
 
@@ -546,6 +1035,12 @@ static int nxp_c45_config_init(struct phy_device *phydev)
 		return ret;
 	}
 
+	/* Bug workaround for SJA1110 rev B: enable write access
+	 * to MDIO_MMD_PMAPMD
+	 */
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 1);
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 2);
+
 	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PHY_CONFIG,
 			 PHY_CONFIG_AUTO);
 
@@ -566,20 +1061,60 @@ static int nxp_c45_config_init(struct phy_device *phydev)
 
 	phydev->autoneg = AUTONEG_DISABLE;
 
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_PTP_CLK_PERIOD,
+		      PTP_CLK_PERIOD_100BT1);
+	phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_HW_LTC_LOCK_CTRL,
+			   HW_LTC_LOCK_EN);
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_RX_TS_INSRT_CTRL,
+		      RX_TS_INSRT_MODE2);
+	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PORT_FUNC_ENABLES,
+			 PTP_ENABLE);
+
 	return nxp_c45_start_op(phydev);
 }
 
 static int nxp_c45_probe(struct phy_device *phydev)
 {
 	struct nxp_c45_phy *priv;
+	int ptp_ability;
+	int ret = 0;
 
 	priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
+	skb_queue_head_init(&priv->tx_queue);
+	skb_queue_head_init(&priv->rx_queue);
+
+	priv->phydev = phydev;
+
 	phydev->priv = priv;
 
-	return 0;
+	mutex_init(&priv->ptp_lock);
+
+	ptp_ability = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+				   VEND1_PORT_ABILITIES);
+	ptp_ability = !!(ptp_ability & PTP_ABILITY);
+	if (!ptp_ability) {
+		phydev_dbg(phydev, "the phy does not support PTP");
+		goto no_ptp_support;
+	}
+
+	if (IS_ENABLED(CONFIG_PTP_1588_CLOCK) &&
+	    IS_ENABLED(CONFIG_NETWORK_PHY_TIMESTAMPING)) {
+		priv->mii_ts.rxtstamp = nxp_c45_rxtstamp;
+		priv->mii_ts.txtstamp = nxp_c45_txtstamp;
+		priv->mii_ts.hwtstamp = nxp_c45_hwtstamp;
+		priv->mii_ts.ts_info = nxp_c45_ts_info;
+		phydev->mii_ts = &priv->mii_ts;
+		ret = nxp_c45_init_ptp_clock(priv);
+	} else {
+		phydev_dbg(phydev, "PTP support not enabled even if the phy supports it");
+	}
+
+no_ptp_support:
+
+	return ret;
 }
 
 static struct phy_driver nxp_c45_driver[] = {
diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index f4816b7d31b3..c617dbcad6ea 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -172,7 +172,7 @@ EXPORT_SYMBOL_GPL(genphy_c45_an_config_aneg);
  * @phydev: target phy_device struct
  *
  * Disable auto-negotiation in the Clause 45 PHY. The link parameters
- * parameters are controlled through the PMA/PMD MMD registers.
+ * are controlled through the PMA/PMD MMD registers.
  *
  * Returns zero on success, negative errno code on failure.
  */
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 8d333d3084ed..2870c33b8975 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -76,7 +76,8 @@ EXPORT_SYMBOL_GPL(phy_duplex_to_str);
 
 /* A mapping of all SUPPORTED settings to speed/duplex.  This table
  * must be grouped by speed and sorted in descending match priority
- * - iow, descending speed. */
+ * - iow, descending speed.
+ */
 
 #define PHY_SETTING(s, d, b) { .speed = SPEED_ ## s, .duplex = DUPLEX_ ## d, \
 			       .bit = ETHTOOL_LINK_MODE_ ## b ## _BIT}
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 1f0512e39c65..8eeb26d8aeb7 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -380,8 +380,7 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 					else if (val & BMCR_SPEED100)
 						phydev->speed = SPEED_100;
 					else phydev->speed = SPEED_10;
-				}
-				else {
+				} else {
 					if (phydev->autoneg == AUTONEG_DISABLE)
 						change_autoneg = true;
 					phydev->autoneg = AUTONEG_ENABLE;
@@ -1136,6 +1135,9 @@ void phy_state_machine(struct work_struct *work)
 	else if (do_suspend)
 		phy_suspend(phydev);
 
+	if (err == -ENODEV)
+		return;
+
 	if (err < 0)
 		phy_error(phydev);
 
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 0a2d8bedf73d..5d5f9a9ee768 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -9,6 +9,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/acpi.h>
 #include <linux/bitmap.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
@@ -833,6 +834,27 @@ static int get_phy_c22_id(struct mii_bus *bus, int addr, u32 *phy_id)
 	return 0;
 }
 
+/* Extract the phy ID from the compatible string of the form
+ * ethernet-phy-idAAAA.BBBB.
+ */
+int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id)
+{
+	unsigned int upper, lower;
+	const char *cp;
+	int ret;
+
+	ret = fwnode_property_read_string(fwnode, "compatible", &cp);
+	if (ret)
+		return ret;
+
+	if (sscanf(cp, "ethernet-phy-id%4x.%4x", &upper, &lower) != 2)
+		return -EINVAL;
+
+	*phy_id = ((upper & GENMASK(15, 0)) << 16) | (lower & GENMASK(15, 0));
+	return 0;
+}
+EXPORT_SYMBOL(fwnode_get_phy_id);
+
 /**
  * get_phy_device - reads the specified PHY device and returns its @phy_device
  *		    struct
@@ -870,6 +892,18 @@ struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45)
 	if (r)
 		return ERR_PTR(r);
 
+	/* PHY device such as the Marvell Alaska 88E2110 will return a PHY ID
+	 * of 0 when probed using get_phy_c22_id() with no error. Proceed to
+	 * probe with C45 to see if we're able to get a valid PHY ID in the C45
+	 * space, if successful, create the C45 PHY device.
+	 */
+	if (!is_c45 && phy_id == 0 && bus->probe_capabilities >= MDIOBUS_C45) {
+		r = get_phy_c45_ids(bus, addr, &c45_ids);
+		if (!r)
+			return phy_device_create(bus, addr, phy_id,
+						 true, &c45_ids);
+	}
+
 	return phy_device_create(bus, addr, phy_id, is_c45, &c45_ids);
 }
 EXPORT_SYMBOL(get_phy_device);
@@ -923,8 +957,7 @@ EXPORT_SYMBOL(phy_device_register);
  */
 void phy_device_remove(struct phy_device *phydev)
 {
-	if (phydev->mii_ts)
-		unregister_mii_timestamper(phydev->mii_ts);
+	unregister_mii_timestamper(phydev->mii_ts);
 
 	device_del(&phydev->mdio.dev);
 
@@ -2864,6 +2897,90 @@ static bool phy_drv_supports_irq(struct phy_driver *phydrv)
 }
 
 /**
+ * fwnode_mdio_find_device - Given a fwnode, find the mdio_device
+ * @fwnode: pointer to the mdio_device's fwnode
+ *
+ * If successful, returns a pointer to the mdio_device with the embedded
+ * struct device refcount incremented by one, or NULL on failure.
+ * The caller should call put_device() on the mdio_device after its use.
+ */
+struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode)
+{
+	struct device *d;
+
+	if (!fwnode)
+		return NULL;
+
+	d = bus_find_device_by_fwnode(&mdio_bus_type, fwnode);
+	if (!d)
+		return NULL;
+
+	return to_mdio_device(d);
+}
+EXPORT_SYMBOL(fwnode_mdio_find_device);
+
+/**
+ * fwnode_phy_find_device - For provided phy_fwnode, find phy_device.
+ *
+ * @phy_fwnode: Pointer to the phy's fwnode.
+ *
+ * If successful, returns a pointer to the phy_device with the embedded
+ * struct device refcount incremented by one, or NULL on failure.
+ */
+struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode)
+{
+	struct mdio_device *mdiodev;
+
+	mdiodev = fwnode_mdio_find_device(phy_fwnode);
+	if (!mdiodev)
+		return NULL;
+
+	if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY)
+		return to_phy_device(&mdiodev->dev);
+
+	put_device(&mdiodev->dev);
+
+	return NULL;
+}
+EXPORT_SYMBOL(fwnode_phy_find_device);
+
+/**
+ * device_phy_find_device - For the given device, get the phy_device
+ * @dev: Pointer to the given device
+ *
+ * Refer return conditions of fwnode_phy_find_device().
+ */
+struct phy_device *device_phy_find_device(struct device *dev)
+{
+	return fwnode_phy_find_device(dev_fwnode(dev));
+}
+EXPORT_SYMBOL_GPL(device_phy_find_device);
+
+/**
+ * fwnode_get_phy_node - Get the phy_node using the named reference.
+ * @fwnode: Pointer to fwnode from which phy_node has to be obtained.
+ *
+ * Refer return conditions of fwnode_find_reference().
+ * For ACPI, only "phy-handle" is supported. Legacy DT properties "phy"
+ * and "phy-device" are not supported in ACPI. DT supports all the three
+ * named references to the phy node.
+ */
+struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode)
+{
+	struct fwnode_handle *phy_node;
+
+	/* Only phy-handle is used for ACPI */
+	phy_node = fwnode_find_reference(fwnode, "phy-handle", 0);
+	if (is_acpi_node(fwnode) || !IS_ERR(phy_node))
+		return phy_node;
+	phy_node = fwnode_find_reference(fwnode, "phy", 0);
+	if (IS_ERR(phy_node))
+		phy_node = fwnode_find_reference(fwnode, "phy-device", 0);
+	return phy_node;
+}
+EXPORT_SYMBOL_GPL(fwnode_get_phy_node);
+
+/**
  * phy_probe - probe and init a PHY device
  * @dev: device to probe and init
  *
@@ -2883,7 +3000,7 @@ static int phy_probe(struct device *dev)
 	/* Disable the interrupt if the PHY doesn't support it
 	 * but the interrupt is still a valid one
 	 */
-	 if (!phy_drv_supports_irq(phydrv) && phy_interrupt_is_valid(phydev))
+	if (!phy_drv_supports_irq(phydrv) && phy_interrupt_is_valid(phydev))
 		phydev->irq = PHY_POLL;
 
 	if (phydrv->flags & PHY_IS_INTERNAL)
@@ -2904,15 +3021,14 @@ static int phy_probe(struct device *dev)
 	 * a controller will attach, and may modify one
 	 * or both of these values
 	 */
-	if (phydrv->features) {
+	if (phydrv->features)
 		linkmode_copy(phydev->supported, phydrv->features);
-	} else if (phydrv->get_features) {
+	else if (phydrv->get_features)
 		err = phydrv->get_features(phydev);
-	} else if (phydev->is_c45) {
+	else if (phydev->is_c45)
 		err = genphy_c45_pma_read_abilities(phydev);
-	} else {
+	else
 		err = genphy_read_abilities(phydev);
-	}
 
 	if (err)
 		goto out;
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 96d8e88b4e46..eb29ef53d971 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -5,6 +5,7 @@
  *
  * Copyright (C) 2015 Russell King
  */
+#include <linux/acpi.h>
 #include <linux/ethtool.h>
 #include <linux/export.h>
 #include <linux/gpio/consumer.h>
@@ -181,7 +182,8 @@ static int phylink_parse_fixedlink(struct phylink *pl,
 			pl->link_config.duplex = DUPLEX_FULL;
 
 		/* We treat the "pause" and "asym-pause" terminology as
-		 * defining the link partner's ability. */
+		 * defining the link partner's ability.
+		 */
 		if (fwnode_property_read_bool(fixed_node, "pause"))
 			__set_bit(ETHTOOL_LINK_MODE_Pause_BIT,
 				  pl->link_config.lp_advertising);
@@ -311,6 +313,11 @@ static int phylink_parse_mode(struct phylink *pl, struct fwnode_handle *fwnode)
 			phylink_set(pl->supported, 5000baseT_Full);
 			break;
 
+		case PHY_INTERFACE_MODE_25GBASER:
+			phylink_set(pl->supported, 25000baseCR_Full);
+			phylink_set(pl->supported, 25000baseKR_Full);
+			phylink_set(pl->supported, 25000baseSR_Full);
+			fallthrough;
 		case PHY_INTERFACE_MODE_USXGMII:
 		case PHY_INTERFACE_MODE_10GKR:
 		case PHY_INTERFACE_MODE_10GBASER:
@@ -679,7 +686,8 @@ static void phylink_resolve(struct work_struct *w)
 			phylink_mac_pcs_get_state(pl, &link_state);
 
 			/* If we have a phy, the "up" state is the union of
-			 * both the PHY and the MAC */
+			 * both the PHY and the MAC
+			 */
 			if (pl->phydev)
 				link_state.link &= pl->phy_state.link;
 
@@ -688,7 +696,8 @@ static void phylink_resolve(struct work_struct *w)
 				link_state.interface = pl->phy_state.interface;
 
 				/* If we have a PHY, we need to update with
-				 * the PHY flow control bits. */
+				 * the PHY flow control bits.
+				 */
 				link_state.pause = pl->phy_state.pause;
 				mac_config = true;
 			}
@@ -1084,7 +1093,26 @@ EXPORT_SYMBOL_GPL(phylink_connect_phy);
 int phylink_of_phy_connect(struct phylink *pl, struct device_node *dn,
 			   u32 flags)
 {
-	struct device_node *phy_node;
+	return phylink_fwnode_phy_connect(pl, of_fwnode_handle(dn), flags);
+}
+EXPORT_SYMBOL_GPL(phylink_of_phy_connect);
+
+/**
+ * phylink_fwnode_phy_connect() - connect the PHY specified in the fwnode.
+ * @pl: a pointer to a &struct phylink returned from phylink_create()
+ * @fwnode: a pointer to a &struct fwnode_handle.
+ * @flags: PHY-specific flags to communicate to the PHY device driver
+ *
+ * Connect the phy specified @fwnode to the phylink instance specified
+ * by @pl.
+ *
+ * Returns 0 on success or a negative errno.
+ */
+int phylink_fwnode_phy_connect(struct phylink *pl,
+			       struct fwnode_handle *fwnode,
+			       u32 flags)
+{
+	struct fwnode_handle *phy_fwnode;
 	struct phy_device *phy_dev;
 	int ret;
 
@@ -1094,28 +1122,25 @@ int phylink_of_phy_connect(struct phylink *pl, struct device_node *dn,
 	     phy_interface_mode_is_8023z(pl->link_interface)))
 		return 0;
 
-	phy_node = of_parse_phandle(dn, "phy-handle", 0);
-	if (!phy_node)
-		phy_node = of_parse_phandle(dn, "phy", 0);
-	if (!phy_node)
-		phy_node = of_parse_phandle(dn, "phy-device", 0);
-
-	if (!phy_node) {
+	phy_fwnode = fwnode_get_phy_node(fwnode);
+	if (IS_ERR(phy_fwnode)) {
 		if (pl->cfg_link_an_mode == MLO_AN_PHY)
 			return -ENODEV;
 		return 0;
 	}
 
-	phy_dev = of_phy_find_device(phy_node);
+	phy_dev = fwnode_phy_find_device(phy_fwnode);
 	/* We're done with the phy_node handle */
-	of_node_put(phy_node);
+	fwnode_handle_put(phy_fwnode);
 	if (!phy_dev)
 		return -ENODEV;
 
 	ret = phy_attach_direct(pl->netdev, phy_dev, flags,
 				pl->link_interface);
-	if (ret)
+	if (ret) {
+		phy_device_free(phy_dev);
 		return ret;
+	}
 
 	ret = phylink_bringup_phy(pl, phy_dev, pl->link_config.interface);
 	if (ret)
@@ -1123,7 +1148,7 @@ int phylink_of_phy_connect(struct phylink *pl, struct device_node *dn,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(phylink_of_phy_connect);
+EXPORT_SYMBOL_GPL(phylink_fwnode_phy_connect);
 
 /**
  * phylink_disconnect_phy() - disconnect any PHY attached to the phylink
@@ -1358,11 +1383,10 @@ int phylink_ethtool_ksettings_get(struct phylink *pl,
 
 	ASSERT_RTNL();
 
-	if (pl->phydev) {
+	if (pl->phydev)
 		phy_ethtool_ksettings_get(pl->phydev, kset);
-	} else {
+	else
 		kset->base.port = pl->link_port;
-	}
 
 	linkmode_copy(kset->link_modes.supported, pl->supported);
 
diff --git a/drivers/net/phy/qsemi.c b/drivers/net/phy/qsemi.c
index d5c1aaa8236a..30d15f7c9b03 100644
--- a/drivers/net/phy/qsemi.c
+++ b/drivers/net/phy/qsemi.c
@@ -100,6 +100,7 @@ static int qs6612_ack_interrupt(struct phy_device *phydev)
 static int qs6612_config_intr(struct phy_device *phydev)
 {
 	int err;
+
 	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
 		/* clear any interrupts before enabling them */
 		err = qs6612_ack_interrupt(phydev);
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 821e85a97367..11be60333fa8 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -8,6 +8,7 @@
  * Copyright (c) 2004 Freescale Semiconductor, Inc.
  */
 #include <linux/bitops.h>
+#include <linux/of.h>
 #include <linux/phy.h>
 #include <linux/module.h>
 #include <linux/delay.h>
@@ -27,6 +28,7 @@
 #define RTL821x_PAGE_SELECT			0x1f
 
 #define RTL8211F_PHYCR1				0x18
+#define RTL8211F_PHYCR2				0x19
 #define RTL8211F_INSR				0x1d
 
 #define RTL8211F_TX_DELAY			BIT(8)
@@ -40,6 +42,8 @@
 #define RTL8211E_TX_DELAY			BIT(12)
 #define RTL8211E_RX_DELAY			BIT(11)
 
+#define RTL8211F_CLKOUT_EN			BIT(0)
+
 #define RTL8201F_ISR				0x1e
 #define RTL8201F_ISR_ANERR			BIT(15)
 #define RTL8201F_ISR_DUPLEX			BIT(13)
@@ -71,6 +75,11 @@ MODULE_DESCRIPTION("Realtek PHY driver");
 MODULE_AUTHOR("Johnson Leung");
 MODULE_LICENSE("GPL");
 
+struct rtl821x_priv {
+	u16 phycr1;
+	u16 phycr2;
+};
+
 static int rtl821x_read_page(struct phy_device *phydev)
 {
 	return __phy_read(phydev, RTL821x_PAGE_SELECT);
@@ -81,6 +90,37 @@ static int rtl821x_write_page(struct phy_device *phydev, int page)
 	return __phy_write(phydev, RTL821x_PAGE_SELECT, page);
 }
 
+static int rtl821x_probe(struct phy_device *phydev)
+{
+	struct device *dev = &phydev->mdio.dev;
+	struct rtl821x_priv *priv;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	ret = phy_read_paged(phydev, 0xa43, RTL8211F_PHYCR1);
+	if (ret < 0)
+		return ret;
+
+	priv->phycr1 = ret & (RTL8211F_ALDPS_PLL_OFF | RTL8211F_ALDPS_ENABLE | RTL8211F_ALDPS_XTAL_OFF);
+	if (of_property_read_bool(dev->of_node, "realtek,aldps-enable"))
+		priv->phycr1 |= RTL8211F_ALDPS_PLL_OFF | RTL8211F_ALDPS_ENABLE | RTL8211F_ALDPS_XTAL_OFF;
+
+	ret = phy_read_paged(phydev, 0xa43, RTL8211F_PHYCR2);
+	if (ret < 0)
+		return ret;
+
+	priv->phycr2 = ret & RTL8211F_CLKOUT_EN;
+	if (of_property_read_bool(dev->of_node, "realtek,clkout-disable"))
+		priv->phycr2 &= ~RTL8211F_CLKOUT_EN;
+
+	phydev->priv = priv;
+
+	return 0;
+}
+
 static int rtl8201_ack_interrupt(struct phy_device *phydev)
 {
 	int err;
@@ -291,13 +331,19 @@ static int rtl8211c_config_init(struct phy_device *phydev)
 
 static int rtl8211f_config_init(struct phy_device *phydev)
 {
+	struct rtl821x_priv *priv = phydev->priv;
 	struct device *dev = &phydev->mdio.dev;
 	u16 val_txdly, val_rxdly;
-	u16 val;
 	int ret;
 
-	val = RTL8211F_ALDPS_ENABLE | RTL8211F_ALDPS_PLL_OFF | RTL8211F_ALDPS_XTAL_OFF;
-	phy_modify_paged_changed(phydev, 0xa43, RTL8211F_PHYCR1, val, val);
+	ret = phy_modify_paged_changed(phydev, 0xa43, RTL8211F_PHYCR1,
+				       RTL8211F_ALDPS_PLL_OFF | RTL8211F_ALDPS_ENABLE | RTL8211F_ALDPS_XTAL_OFF,
+				       priv->phycr1);
+	if (ret < 0) {
+		dev_err(dev, "aldps mode  configuration failed: %pe\n",
+			ERR_PTR(ret));
+		return ret;
+	}
 
 	switch (phydev->interface) {
 	case PHY_INTERFACE_MODE_RGMII:
@@ -354,6 +400,27 @@ static int rtl8211f_config_init(struct phy_device *phydev)
 			val_rxdly ? "enabled" : "disabled");
 	}
 
+	ret = phy_modify_paged(phydev, 0xa43, RTL8211F_PHYCR2,
+			       RTL8211F_CLKOUT_EN, priv->phycr2);
+	if (ret < 0) {
+		dev_err(dev, "clkout configuration failed: %pe\n",
+			ERR_PTR(ret));
+		return ret;
+	}
+
+	return genphy_soft_reset(phydev);
+}
+
+static int rtl821x_resume(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = genphy_resume(phydev);
+	if (ret < 0)
+		return ret;
+
+	msleep(20);
+
 	return 0;
 }
 
@@ -847,12 +914,13 @@ static struct phy_driver realtek_drvs[] = {
 	}, {
 		PHY_ID_MATCH_EXACT(0x001cc916),
 		.name		= "RTL8211F Gigabit Ethernet",
+		.probe		= rtl821x_probe,
 		.config_init	= &rtl8211f_config_init,
 		.read_status	= rtlgen_read_status,
 		.config_intr	= &rtl8211f_config_intr,
 		.handle_interrupt = rtl8211f_handle_interrupt,
 		.suspend	= genphy_suspend,
-		.resume		= genphy_resume,
+		.resume		= rtl821x_resume,
 		.read_page	= rtl821x_read_page,
 		.write_page	= rtl821x_write_page,
 	}, {
diff --git a/drivers/net/phy/rockchip.c b/drivers/net/phy/rockchip.c
index 52f1f65320fe..bb13e75183ee 100644
--- a/drivers/net/phy/rockchip.c
+++ b/drivers/net/phy/rockchip.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0+
-/**
+/*
  * drivers/net/phy/rockchip.c
  *
  * Driver for ROCKCHIP Ethernet PHYs
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index e61de66e973b..7362f8c3271c 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -392,6 +392,11 @@ EXPORT_SYMBOL_GPL(sfp_parse_support);
 phy_interface_t sfp_select_interface(struct sfp_bus *bus,
 				     unsigned long *link_modes)
 {
+	if (phylink_test(link_modes, 25000baseCR_Full) ||
+	    phylink_test(link_modes, 25000baseKR_Full) ||
+	    phylink_test(link_modes, 25000baseSR_Full))
+		return PHY_INTERFACE_MODE_25GBASER;
+
 	if (phylink_test(link_modes, 10000baseCR_Full) ||
 	    phylink_test(link_modes, 10000baseSR_Full) ||
 	    phylink_test(link_modes, 10000baseLR_Full) ||
@@ -624,14 +629,14 @@ static void sfp_upstream_clear(struct sfp_bus *bus)
  * be put via sfp_bus_put() when done.
  *
  * Returns:
- * 	    - on success, a pointer to the sfp_bus structure,
- *	    - %NULL if no SFP is specified,
- * 	    - on failure, an error pointer value:
+ *	- on success, a pointer to the sfp_bus structure,
+ *	- %NULL if no SFP is specified,
+ *	- on failure, an error pointer value:
  *
- * 	      - corresponding to the errors detailed for
- * 	        fwnode_property_get_reference_args().
- * 	      - %-ENOMEM if we failed to allocate the bus.
- *	      - an error from the upstream's connect_phy() method.
+ *	- corresponding to the errors detailed for
+ *	  fwnode_property_get_reference_args().
+ *	- %-ENOMEM if we failed to allocate the bus.
+ *	- an error from the upstream's connect_phy() method.
  */
 struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode)
 {
@@ -666,14 +671,14 @@ EXPORT_SYMBOL_GPL(sfp_bus_find_fwnode);
  * bus, so it is safe to put the bus after this call.
  *
  * Returns:
- * 	    - on success, a pointer to the sfp_bus structure,
- *	    - %NULL if no SFP is specified,
- * 	    - on failure, an error pointer value:
+ *	- on success, a pointer to the sfp_bus structure,
+ *	- %NULL if no SFP is specified,
+ *	- on failure, an error pointer value:
  *
- * 	      - corresponding to the errors detailed for
- * 	        fwnode_property_get_reference_args().
- * 	      - %-ENOMEM if we failed to allocate the bus.
- *	      - an error from the upstream's connect_phy() method.
+ *	- corresponding to the errors detailed for
+ *	  fwnode_property_get_reference_args().
+ *	- %-ENOMEM if we failed to allocate the bus.
+ *	- an error from the upstream's connect_phy() method.
  */
 int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream,
 			 const struct sfp_upstream_ops *ops)
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 37f722c763d7..34e90216bd2c 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -2153,7 +2153,7 @@ static void sfp_sm_main(struct sfp *sfp, unsigned int event)
 
 	case SFP_S_INIT:
 		if (event == SFP_E_TIMEOUT && sfp->state & SFP_F_TX_FAULT) {
-			/* TX_FAULT is still asserted after t_init or
+			/* TX_FAULT is still asserted after t_init
 			 * or t_start_up, so assume there is a fault.
 			 */
 			sfp_sm_fault(sfp, SFP_S_INIT_TX_FAULT,
diff --git a/drivers/net/phy/spi_ks8995.c b/drivers/net/phy/spi_ks8995.c
index ca49c1ad3efc..8b5445a724ce 100644
--- a/drivers/net/phy/spi_ks8995.c
+++ b/drivers/net/phy/spi_ks8995.c
@@ -160,11 +160,11 @@ static const struct spi_device_id ks8995_id[] = {
 MODULE_DEVICE_TABLE(spi, ks8995_id);
 
 static const struct of_device_id ks8895_spi_of_match[] = {
-        { .compatible = "micrel,ks8995" },
-        { .compatible = "micrel,ksz8864" },
-        { .compatible = "micrel,ksz8795" },
-        { },
- };
+	{ .compatible = "micrel,ks8995" },
+	{ .compatible = "micrel,ksz8864" },
+	{ .compatible = "micrel,ksz8795" },
+	{ },
+};
 MODULE_DEVICE_TABLE(of, ks8895_spi_of_match);
 
 static inline u8 get_chip_id(u8 val)
diff --git a/drivers/net/phy/ste10Xp.c b/drivers/net/phy/ste10Xp.c
index 431fe5e0ce31..309e4c3496c4 100644
--- a/drivers/net/phy/ste10Xp.c
+++ b/drivers/net/phy/ste10Xp.c
@@ -20,12 +20,12 @@
 #include <linux/mii.h>
 #include <linux/phy.h>
 
-#define MII_XCIIS   	0x11	/* Configuration Info IRQ & Status Reg */
-#define MII_XIE     	0x12	/* Interrupt Enable Register */
+#define MII_XCIIS	0x11	/* Configuration Info IRQ & Status Reg */
+#define MII_XIE		0x12	/* Interrupt Enable Register */
 #define MII_XIE_DEFAULT_MASK 0x0070 /* ANE complete, Remote Fault, Link Down */
 
 #define STE101P_PHY_ID		0x00061c50
-#define STE100P_PHY_ID       	0x1c040011
+#define STE100P_PHY_ID		0x1c040011
 
 static int ste10Xp_config_init(struct phy_device *phydev)
 {
diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index 16704e243162..897b979ec03c 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -249,7 +249,8 @@ static int vsc73xx_config_aneg(struct phy_device *phydev)
 
 /* This adds a skew for both TX and RX clocks, so the skew should only be
  * applied to "rgmii-id" interfaces. It may not work as expected
- * on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces. */
+ * on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces.
+ */
 static int vsc8601_add_skew(struct phy_device *phydev)
 {
 	int ret;
diff --git a/drivers/net/ppp/bsd_comp.c b/drivers/net/ppp/bsd_comp.c
index 61fedb23d3cf..db0dc36d12e3 100644
--- a/drivers/net/ppp/bsd_comp.c
+++ b/drivers/net/ppp/bsd_comp.c
@@ -436,7 +436,7 @@ static void *bsd_alloc (unsigned char *options, int opt_len, int decomp)
  * Initialize the data information for the compression code
  */
     db->totlen     = sizeof (struct bsd_db)   +
-      		    (sizeof (struct bsd_dict) * hsize);
+		    (sizeof (struct bsd_dict) * hsize);
 
     db->hsize      = hsize;
     db->hshift     = hshift;
diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index f78ceba42e57..ba93bab948e0 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -325,7 +325,7 @@ found:
 	 * Found it -- move to the front on the connection list.
 	 */
 	if(lcs == ocs) {
- 		/* found at most recently used */
+		/* found at most recently used */
 	} else if (cs == ocs) {
 		/* found at least recently used */
 		comp->xmit_oldest = lcs->cs_this;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 84f832806313..2ced021f4faf 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2559,15 +2559,15 @@ static int tun_flags(struct tun_struct *tun)
 	return tun->flags & (TUN_FEATURES | IFF_PERSIST | IFF_TUN | IFF_TAP);
 }
 
-static ssize_t tun_show_flags(struct device *dev, struct device_attribute *attr,
+static ssize_t tun_flags_show(struct device *dev, struct device_attribute *attr,
 			      char *buf)
 {
 	struct tun_struct *tun = netdev_priv(to_net_dev(dev));
 	return sprintf(buf, "0x%x\n", tun_flags(tun));
 }
 
-static ssize_t tun_show_owner(struct device *dev, struct device_attribute *attr,
-			      char *buf)
+static ssize_t owner_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
 {
 	struct tun_struct *tun = netdev_priv(to_net_dev(dev));
 	return uid_valid(tun->owner)?
@@ -2576,8 +2576,8 @@ static ssize_t tun_show_owner(struct device *dev, struct device_attribute *attr,
 		sprintf(buf, "-1\n");
 }
 
-static ssize_t tun_show_group(struct device *dev, struct device_attribute *attr,
-			      char *buf)
+static ssize_t group_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
 {
 	struct tun_struct *tun = netdev_priv(to_net_dev(dev));
 	return gid_valid(tun->group) ?
@@ -2586,9 +2586,9 @@ static ssize_t tun_show_group(struct device *dev, struct device_attribute *attr,
 		sprintf(buf, "-1\n");
 }
 
-static DEVICE_ATTR(tun_flags, 0444, tun_show_flags, NULL);
-static DEVICE_ATTR(owner, 0444, tun_show_owner, NULL);
-static DEVICE_ATTR(group, 0444, tun_show_group, NULL);
+static DEVICE_ATTR_RO(tun_flags);
+static DEVICE_ATTR_RO(owner);
+static DEVICE_ATTR_RO(group);
 
 static struct attribute *tun_dev_attrs[] = {
 	&dev_attr_tun_flags.attr,
diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index fbbe78643631..4c5d69732a7e 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -164,12 +164,14 @@ config USB_NET_AX8817X
 	depends on USB_USBNET
 	select CRC32
 	select PHYLIB
+	select AX88796B_PHY
+	imply NET_SELFTESTS
 	default y
 	help
 	  This option adds support for ASIX AX88xxx based USB 2.0
 	  10/100 Ethernet adapters.
 
- 	  This driver should work with at least the following devices:
+	  This driver should work with at least the following devices:
 	    * Aten UC210T
 	    * ASIX AX88172
 	    * Billionton Systems, USB2AR
@@ -220,13 +222,13 @@ config USB_NET_CDCETHER
 	  CDC Ethernet is an implementation option for DOCSIS cable modems
 	  that support USB connectivity, used for non-Microsoft USB hosts.
 	  The Linux-USB CDC Ethernet Gadget driver is an open implementation.
- 	  This driver should work with at least the following devices:
+	  This driver should work with at least the following devices:
 
 	    * Dell Wireless 5530 HSPA
- 	    * Ericsson PipeRider (all variants)
+	    * Ericsson PipeRider (all variants)
 	    * Ericsson Mobile Broadband Module (all variants)
- 	    * Motorola (DM100 and SB4100)
- 	    * Broadcom Cable Modem (reference design)
+	    * Motorola (DM100 and SB4100)
+	    * Broadcom Cable Modem (reference design)
 	    * Toshiba (PCX1100U and F3507g/F3607gw)
 	    * ...
 
diff --git a/drivers/net/usb/asix.h b/drivers/net/usb/asix.h
index 3b53685301de..e1994a246122 100644
--- a/drivers/net/usb/asix.h
+++ b/drivers/net/usb/asix.h
@@ -25,6 +25,8 @@
 #include <linux/usb/usbnet.h>
 #include <linux/slab.h>
 #include <linux/if_vlan.h>
+#include <linux/phy.h>
+#include <net/selftests.h>
 
 #define DRIVER_VERSION "22-Dec-2011"
 #define DRIVER_NAME "asix"
@@ -178,6 +180,10 @@ struct asix_common_private {
 	u16 presvd_phy_advertise;
 	u16 presvd_phy_bmcr;
 	struct asix_rx_fixup_info rx_fixup_info;
+	struct mii_bus *mdio;
+	struct phy_device *phydev;
+	u16 phy_addr;
+	char phy_name[20];
 };
 
 extern const struct driver_info ax88172a_info;
@@ -205,8 +211,7 @@ struct sk_buff *asix_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 int asix_set_sw_mii(struct usbnet *dev, int in_pm);
 int asix_set_hw_mii(struct usbnet *dev, int in_pm);
 
-int asix_read_phy_addr(struct usbnet *dev, int internal);
-int asix_get_phy_addr(struct usbnet *dev);
+int asix_read_phy_addr(struct usbnet *dev, bool internal);
 
 int asix_sw_reset(struct usbnet *dev, u8 flags, int in_pm);
 
@@ -215,6 +220,7 @@ int asix_write_rx_ctl(struct usbnet *dev, u16 mode, int in_pm);
 
 u16 asix_read_medium_status(struct usbnet *dev, int in_pm);
 int asix_write_medium_mode(struct usbnet *dev, u16 mode, int in_pm);
+void asix_adjust_link(struct net_device *netdev);
 
 int asix_write_gpio(struct usbnet *dev, u16 value, int sleep, int in_pm);
 
@@ -223,6 +229,9 @@ void asix_set_multicast(struct net_device *net);
 int asix_mdio_read(struct net_device *netdev, int phy_id, int loc);
 void asix_mdio_write(struct net_device *netdev, int phy_id, int loc, int val);
 
+int asix_mdio_bus_read(struct mii_bus *bus, int phy_id, int regnum);
+int asix_mdio_bus_write(struct mii_bus *bus, int phy_id, int regnum, u16 val);
+
 int asix_mdio_read_nopm(struct net_device *netdev, int phy_id, int loc);
 void asix_mdio_write_nopm(struct net_device *netdev, int phy_id, int loc,
 			  int val);
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c
index 7bc6e8f856fe..ac92bc52a85e 100644
--- a/drivers/net/usb/asix_common.c
+++ b/drivers/net/usb/asix_common.c
@@ -288,32 +288,33 @@ int asix_set_hw_mii(struct usbnet *dev, int in_pm)
 	return ret;
 }
 
-int asix_read_phy_addr(struct usbnet *dev, int internal)
+int asix_read_phy_addr(struct usbnet *dev, bool internal)
 {
-	int offset = (internal ? 1 : 0);
+	int ret, offset;
 	u8 buf[2];
-	int ret = asix_read_cmd(dev, AX_CMD_READ_PHY_ID, 0, 0, 2, buf, 0);
 
-	netdev_dbg(dev->net, "asix_get_phy_addr()\n");
+	ret = asix_read_cmd(dev, AX_CMD_READ_PHY_ID, 0, 0, 2, buf, 0);
+	if (ret < 0)
+		goto error;
 
 	if (ret < 2) {
-		netdev_err(dev->net, "Error reading PHYID register: %02x\n", ret);
-		goto out;
+		ret = -EIO;
+		goto error;
 	}
-	netdev_dbg(dev->net, "asix_get_phy_addr() returning 0x%04x\n",
-		   *((__le16 *)buf));
+
+	offset = (internal ? 1 : 0);
 	ret = buf[offset];
 
-out:
+	netdev_dbg(dev->net, "%s PHY address 0x%x\n",
+		   internal ? "internal" : "external", ret);
+
 	return ret;
-}
 
-int asix_get_phy_addr(struct usbnet *dev)
-{
-	/* return the address of the internal phy */
-	return asix_read_phy_addr(dev, 1);
-}
+error:
+	netdev_err(dev->net, "Error reading PHY_ID register: %02x\n", ret);
 
+	return ret;
+}
 
 int asix_sw_reset(struct usbnet *dev, u8 flags, int in_pm)
 {
@@ -383,6 +384,27 @@ int asix_write_medium_mode(struct usbnet *dev, u16 mode, int in_pm)
 	return ret;
 }
 
+/* set MAC link settings according to information from phylib */
+void asix_adjust_link(struct net_device *netdev)
+{
+	struct phy_device *phydev = netdev->phydev;
+	struct usbnet *dev = netdev_priv(netdev);
+	u16 mode = 0;
+
+	if (phydev->link) {
+		mode = AX88772_MEDIUM_DEFAULT;
+
+		if (phydev->duplex == DUPLEX_HALF)
+			mode &= ~AX_MEDIUM_FD;
+
+		if (phydev->speed != SPEED_100)
+			mode &= ~AX_MEDIUM_PS;
+	}
+
+	asix_write_medium_mode(dev, mode, 0);
+	phy_print_status(phydev);
+}
+
 int asix_write_gpio(struct usbnet *dev, u16 value, int sleep, int in_pm)
 {
 	int ret;
@@ -463,18 +485,23 @@ int asix_mdio_read(struct net_device *netdev, int phy_id, int loc)
 		return ret;
 	}
 
-	asix_read_cmd(dev, AX_CMD_READ_MII_REG, phy_id,
-				(__u16)loc, 2, &res, 0);
-	asix_set_hw_mii(dev, 0);
+	ret = asix_read_cmd(dev, AX_CMD_READ_MII_REG, phy_id, (__u16)loc, 2,
+			    &res, 0);
+	if (ret < 0)
+		goto out;
+
+	ret = asix_set_hw_mii(dev, 0);
+out:
 	mutex_unlock(&dev->phy_mutex);
 
 	netdev_dbg(dev->net, "asix_mdio_read() phy_id=0x%02x, loc=0x%02x, returns=0x%04x\n",
 			phy_id, loc, le16_to_cpu(res));
 
-	return le16_to_cpu(res);
+	return ret < 0 ? ret : le16_to_cpu(res);
 }
 
-void asix_mdio_write(struct net_device *netdev, int phy_id, int loc, int val)
+static int __asix_mdio_write(struct net_device *netdev, int phy_id, int loc,
+			     int val)
 {
 	struct usbnet *dev = netdev_priv(netdev);
 	__le16 res = cpu_to_le16(val);
@@ -494,15 +521,40 @@ void asix_mdio_write(struct net_device *netdev, int phy_id, int loc, int val)
 		ret = asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG,
 				    0, 0, 1, &smsr, 0);
 	} while (!(smsr & AX_HOST_EN) && (i++ < 30) && (ret != -ENODEV));
-	if (ret == -ENODEV) {
-		mutex_unlock(&dev->phy_mutex);
-		return;
-	}
 
-	asix_write_cmd(dev, AX_CMD_WRITE_MII_REG, phy_id,
-		       (__u16)loc, 2, &res, 0);
-	asix_set_hw_mii(dev, 0);
+	if (ret == -ENODEV)
+		goto out;
+
+	ret = asix_write_cmd(dev, AX_CMD_WRITE_MII_REG, phy_id, (__u16)loc, 2,
+			     &res, 0);
+	if (ret < 0)
+		goto out;
+
+	ret = asix_set_hw_mii(dev, 0);
+out:
 	mutex_unlock(&dev->phy_mutex);
+
+	return ret < 0 ? ret : 0;
+}
+
+void asix_mdio_write(struct net_device *netdev, int phy_id, int loc, int val)
+{
+	__asix_mdio_write(netdev, phy_id, loc, val);
+}
+
+/* MDIO read and write wrappers for phylib */
+int asix_mdio_bus_read(struct mii_bus *bus, int phy_id, int regnum)
+{
+	struct usbnet *priv = bus->priv;
+
+	return asix_mdio_read(priv->net, phy_id, regnum);
+}
+
+int asix_mdio_bus_write(struct mii_bus *bus, int phy_id, int regnum, u16 val)
+{
+	struct usbnet *priv = bus->priv;
+
+	return __asix_mdio_write(priv->net, phy_id, regnum, val);
 }
 
 int asix_mdio_read_nopm(struct net_device *netdev, int phy_id, int loc)
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 19a8fafb8f04..aec97b021a73 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -262,7 +262,10 @@ static int ax88172_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->mii.mdio_write = asix_mdio_write;
 	dev->mii.phy_id_mask = 0x3f;
 	dev->mii.reg_num_mask = 0x1f;
-	dev->mii.phy_id = asix_get_phy_addr(dev);
+
+	dev->mii.phy_id = asix_read_phy_addr(dev, true);
+	if (dev->mii.phy_id < 0)
+		return dev->mii.phy_id;
 
 	dev->net->netdev_ops = &ax88172_netdev_ops;
 	dev->net->ethtool_ops = &ax88172_ethtool_ops;
@@ -280,9 +283,29 @@ out:
 	return ret;
 }
 
+static void ax88772_ethtool_get_strings(struct net_device *netdev, u32 sset,
+					u8 *data)
+{
+	switch (sset) {
+	case ETH_SS_TEST:
+		net_selftest_get_strings(data);
+		break;
+	}
+}
+
+static int ax88772_ethtool_get_sset_count(struct net_device *ndev, int sset)
+{
+	switch (sset) {
+	case ETH_SS_TEST:
+		return net_selftest_get_count();
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct ethtool_ops ax88772_ethtool_ops = {
 	.get_drvinfo		= asix_get_drvinfo,
-	.get_link		= asix_get_link,
+	.get_link		= usbnet_get_link,
 	.get_msglevel		= usbnet_get_msglevel,
 	.set_msglevel		= usbnet_set_msglevel,
 	.get_wol		= asix_get_wol,
@@ -290,37 +313,18 @@ 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,
-	.nway_reset		= usbnet_nway_reset,
-	.get_link_ksettings	= usbnet_get_link_ksettings_mii,
-	.set_link_ksettings	= usbnet_set_link_ksettings_mii,
+	.nway_reset		= phy_ethtool_nway_reset,
+	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
+	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
+	.self_test		= net_selftest,
+	.get_strings		= ax88772_ethtool_get_strings,
+	.get_sset_count		= ax88772_ethtool_get_sset_count,
 };
 
-static int ax88772_link_reset(struct usbnet *dev)
-{
-	u16 mode;
-	struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET };
-
-	mii_check_media(&dev->mii, 1, 1);
-	mii_ethtool_gset(&dev->mii, &ecmd);
-	mode = AX88772_MEDIUM_DEFAULT;
-
-	if (ethtool_cmd_speed(&ecmd) != SPEED_100)
-		mode &= ~AX_MEDIUM_PS;
-
-	if (ecmd.duplex != DUPLEX_FULL)
-		mode &= ~AX_MEDIUM_FD;
-
-	netdev_dbg(dev->net, "ax88772_link_reset() speed: %u duplex: %d setting mode to 0x%04x\n",
-		   ethtool_cmd_speed(&ecmd), ecmd.duplex, mode);
-
-	asix_write_medium_mode(dev, mode, 0);
-
-	return 0;
-}
-
 static int ax88772_reset(struct usbnet *dev)
 {
 	struct asix_data *data = (struct asix_data *)&dev->data;
+	struct asix_common_private *priv = dev->driver_priv;
 	int ret;
 
 	/* Rewrite MAC address */
@@ -339,6 +343,8 @@ static int ax88772_reset(struct usbnet *dev)
 	if (ret < 0)
 		goto out;
 
+	phy_start(priv->phydev);
+
 	return 0;
 
 out:
@@ -583,7 +589,7 @@ static const struct net_device_ops ax88772_netdev_ops = {
 	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address 	= asix_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= asix_ioctl,
+	.ndo_do_ioctl		= phy_do_ioctl_running,
 	.ndo_set_rx_mode        = asix_set_multicast,
 };
 
@@ -592,6 +598,9 @@ static void ax88772_suspend(struct usbnet *dev)
 	struct asix_common_private *priv = dev->driver_priv;
 	u16 medium;
 
+	if (netif_running(dev->net))
+		phy_stop(priv->phydev);
+
 	/* Stop MAC operation */
 	medium = asix_read_medium_status(dev, 1);
 	medium &= ~AX_MEDIUM_RE;
@@ -599,14 +608,6 @@ static void ax88772_suspend(struct usbnet *dev)
 
 	netdev_dbg(dev->net, "ax88772_suspend: medium=0x%04x\n",
 		   asix_read_medium_status(dev, 1));
-
-	/* Preserve BMCR for restoring */
-	priv->presvd_phy_bmcr =
-		asix_mdio_read_nopm(dev->net, dev->mii.phy_id, MII_BMCR);
-
-	/* Preserve ANAR for restoring */
-	priv->presvd_phy_advertise =
-		asix_mdio_read_nopm(dev->net, dev->mii.phy_id, MII_ADVERTISE);
 }
 
 static int asix_suspend(struct usb_interface *intf, pm_message_t message)
@@ -620,39 +621,22 @@ static int asix_suspend(struct usb_interface *intf, pm_message_t message)
 	return usbnet_suspend(intf, message);
 }
 
-static void ax88772_restore_phy(struct usbnet *dev)
-{
-	struct asix_common_private *priv = dev->driver_priv;
-
-	if (priv->presvd_phy_advertise) {
-		/* Restore Advertisement control reg */
-		asix_mdio_write_nopm(dev->net, dev->mii.phy_id, MII_ADVERTISE,
-				     priv->presvd_phy_advertise);
-
-		/* Restore BMCR */
-		if (priv->presvd_phy_bmcr & BMCR_ANENABLE)
-			priv->presvd_phy_bmcr |= BMCR_ANRESTART;
-
-		asix_mdio_write_nopm(dev->net, dev->mii.phy_id, MII_BMCR,
-				     priv->presvd_phy_bmcr);
-
-		priv->presvd_phy_advertise = 0;
-		priv->presvd_phy_bmcr = 0;
-	}
-}
-
 static void ax88772_resume(struct usbnet *dev)
 {
+	struct asix_common_private *priv = dev->driver_priv;
 	int i;
 
 	for (i = 0; i < 3; i++)
 		if (!ax88772_hw_reset(dev, 1))
 			break;
-	ax88772_restore_phy(dev);
+
+	if (netif_running(dev->net))
+		phy_start(priv->phydev);
 }
 
 static void ax88772a_resume(struct usbnet *dev)
 {
+	struct asix_common_private *priv = dev->driver_priv;
 	int i;
 
 	for (i = 0; i < 3; i++) {
@@ -660,7 +644,8 @@ static void ax88772a_resume(struct usbnet *dev)
 			break;
 	}
 
-	ax88772_restore_phy(dev);
+	if (netif_running(dev->net))
+		phy_start(priv->phydev);
 }
 
 static int asix_resume(struct usb_interface *intf)
@@ -674,12 +659,61 @@ static int asix_resume(struct usb_interface *intf)
 	return usbnet_resume(intf);
 }
 
+static int ax88772_init_mdio(struct usbnet *dev)
+{
+	struct asix_common_private *priv = dev->driver_priv;
+
+	priv->mdio = devm_mdiobus_alloc(&dev->udev->dev);
+	if (!priv->mdio)
+		return -ENOMEM;
+
+	priv->mdio->priv = dev;
+	priv->mdio->read = &asix_mdio_bus_read;
+	priv->mdio->write = &asix_mdio_bus_write;
+	priv->mdio->name = "Asix MDIO Bus";
+	/* mii bus name is usb-<usb bus number>-<usb device number> */
+	snprintf(priv->mdio->id, MII_BUS_ID_SIZE, "usb-%03d:%03d",
+		 dev->udev->bus->busnum, dev->udev->devnum);
+
+	return devm_mdiobus_register(&dev->udev->dev, priv->mdio);
+}
+
+static int ax88772_init_phy(struct usbnet *dev)
+{
+	struct asix_common_private *priv = dev->driver_priv;
+	int ret;
+
+	ret = asix_read_phy_addr(dev, true);
+	if (ret < 0)
+		return ret;
+
+	priv->phy_addr = ret;
+
+	snprintf(priv->phy_name, sizeof(priv->phy_name), PHY_ID_FMT,
+		 priv->mdio->id, priv->phy_addr);
+
+	priv->phydev = phy_connect(dev->net, priv->phy_name, &asix_adjust_link,
+				   PHY_INTERFACE_MODE_INTERNAL);
+	if (IS_ERR(priv->phydev)) {
+		netdev_err(dev->net, "Could not connect to PHY device %s\n",
+			   priv->phy_name);
+		ret = PTR_ERR(priv->phydev);
+		return ret;
+	}
+
+	priv->phydev->mac_managed_pm = 1;
+
+	phy_attached_info(priv->phydev);
+
+	return 0;
+}
+
 static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf)
 {
-	int ret, i;
 	u8 buf[ETH_ALEN] = {0}, chipcode = 0;
-	u32 phyid;
 	struct asix_common_private *priv;
+	int ret, i;
+	u32 phyid;
 
 	usbnet_get_endpoints(dev, intf);
 
@@ -711,14 +745,6 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf)
 
 	asix_set_netdev_dev_addr(dev, buf);
 
-	/* Initialize MII structure */
-	dev->mii.dev = dev->net;
-	dev->mii.mdio_read = asix_mdio_read;
-	dev->mii.mdio_write = asix_mdio_write;
-	dev->mii.phy_id_mask = 0x1f;
-	dev->mii.reg_num_mask = 0x1f;
-	dev->mii.phy_id = asix_get_phy_addr(dev);
-
 	dev->net->netdev_ops = &ax88772_netdev_ops;
 	dev->net->ethtool_ops = &ax88772_ethtool_ops;
 	dev->net->needed_headroom = 4; /* cf asix_tx_fixup() */
@@ -746,11 +772,11 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf)
 		dev->rx_urb_size = 2048;
 	}
 
-	dev->driver_priv = kzalloc(sizeof(struct asix_common_private), GFP_KERNEL);
-	if (!dev->driver_priv)
+	priv = devm_kzalloc(&dev->udev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
 		return -ENOMEM;
 
-	priv = dev->driver_priv;
+	dev->driver_priv = priv;
 
 	priv->presvd_phy_bmcr = 0;
 	priv->presvd_phy_advertise = 0;
@@ -762,13 +788,32 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf)
 		priv->suspend = ax88772_suspend;
 	}
 
+	ret = ax88772_init_mdio(dev);
+	if (ret)
+		return ret;
+
+	return ax88772_init_phy(dev);
+}
+
+static int ax88772_stop(struct usbnet *dev)
+{
+	struct asix_common_private *priv = dev->driver_priv;
+
+	/* On unplugged USB, we will get MDIO communication errors and the
+	 * PHY will be set in to PHY_HALTED state.
+	 */
+	if (priv->phydev->state != PHY_HALTED)
+		phy_stop(priv->phydev);
+
 	return 0;
 }
 
 static void ax88772_unbind(struct usbnet *dev, struct usb_interface *intf)
 {
+	struct asix_common_private *priv = dev->driver_priv;
+
+	phy_disconnect(priv->phydev);
 	asix_rx_fixup_common_free(dev->driver_priv);
-	kfree(dev->driver_priv);
 }
 
 static const struct ethtool_ops ax88178_ethtool_ops = {
@@ -1081,7 +1126,10 @@ static int ax88178_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->mii.phy_id_mask = 0x1f;
 	dev->mii.reg_num_mask = 0xff;
 	dev->mii.supports_gmii = 1;
-	dev->mii.phy_id = asix_get_phy_addr(dev);
+
+	dev->mii.phy_id = asix_read_phy_addr(dev, true);
+	if (dev->mii.phy_id < 0)
+		return dev->mii.phy_id;
 
 	dev->net->netdev_ops = &ax88178_netdev_ops;
 	dev->net->ethtool_ops = &ax88178_ethtool_ops;
@@ -1153,8 +1201,8 @@ static const struct driver_info ax88772_info = {
 	.bind = ax88772_bind,
 	.unbind = ax88772_unbind,
 	.status = asix_status,
-	.link_reset = ax88772_link_reset,
 	.reset = ax88772_reset,
+	.stop = ax88772_stop,
 	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | FLAG_MULTI_PACKET,
 	.rx_fixup = asix_rx_fixup_common,
 	.tx_fixup = asix_tx_fixup,
@@ -1165,7 +1213,6 @@ static const struct driver_info ax88772b_info = {
 	.bind = ax88772_bind,
 	.unbind = ax88772_unbind,
 	.status = asix_status,
-	.link_reset = ax88772_link_reset,
 	.reset = ax88772_reset,
 	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |
 	         FLAG_MULTI_PACKET,
@@ -1201,7 +1248,6 @@ static const struct driver_info hg20f9_info = {
 	.bind = ax88772_bind,
 	.unbind = ax88772_unbind,
 	.status = asix_status,
-	.link_reset = ax88772_link_reset,
 	.reset = ax88772_reset,
 	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |
 	         FLAG_MULTI_PACKET,
diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index b404c9462dce..530947d7477b 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -25,20 +25,6 @@ struct ax88172a_private {
 	struct asix_rx_fixup_info rx_fixup_info;
 };
 
-/* MDIO read and write wrappers for phylib */
-static int asix_mdio_bus_read(struct mii_bus *bus, int phy_id, int regnum)
-{
-	return asix_mdio_read(((struct usbnet *)bus->priv)->net, phy_id,
-			      regnum);
-}
-
-static int asix_mdio_bus_write(struct mii_bus *bus, int phy_id, int regnum,
-			       u16 val)
-{
-	asix_mdio_write(((struct usbnet *)bus->priv)->net, phy_id, regnum, val);
-	return 0;
-}
-
 /* set MAC link settings according to information from phylib */
 static void ax88172a_adjust_link(struct net_device *netdev)
 {
@@ -219,7 +205,12 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf)
 		goto free;
 	}
 
-	priv->phy_addr = asix_read_phy_addr(dev, priv->use_embdphy);
+	ret = asix_read_phy_addr(dev, priv->use_embdphy);
+	if (ret < 0)
+		goto free;
+
+	priv->phy_addr = ret;
+
 	ax88172a_reset_phy(dev, priv->use_embdphy);
 
 	/* Asix framing packs multiple eth frames into a 2K usb bulk transfer */
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 7eb0109e9baa..eb3817d70f2b 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -217,7 +217,7 @@ int usbnet_generic_cdc_bind(struct usbnet *dev, struct usb_interface *intf)
 		goto bad_desc;
 	}
 skip:
-	/* Communcation class functions with bmCapabilities are not
+	/* Communication class functions with bmCapabilities are not
 	 * RNDIS.  But some Wireless class RNDIS functions use
 	 * bmCapabilities for their own purpose. The failsafe is
 	 * therefore applied only to Communication class RNDIS
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 5db66272fc82..4c4ab7b38d78 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -168,6 +168,7 @@ static int cdc_mbim_bind(struct usbnet *dev, struct usb_interface *intf)
 		subdriver = usb_cdc_wdm_register(ctx->control,
 						 &dev->status->desc,
 						 le16_to_cpu(ctx->mbim_desc->wMaxControlMessage),
+						 WWAN_PORT_MBIM,
 						 cdc_mbim_wdm_manage_power);
 	if (IS_ERR(subdriver)) {
 		ret = PTR_ERR(subdriver);
@@ -300,8 +301,8 @@ error:
 	return NULL;
 }
 
-/* Some devices are known to send Neigbor Solicitation messages and
- * require Neigbor Advertisement replies.  The IPv6 core will not
+/* Some devices are known to send Neighbor Solicitation messages and
+ * require Neighbor Advertisement replies.  The IPv6 core will not
  * respond since IFF_NOARP is set, so we must handle them ourselves.
  */
 static void do_neigh_solicit(struct usbnet *dev, u8 *buf, u16 tci)
@@ -588,7 +589,7 @@ static const struct driver_info cdc_mbim_info_zlp = {
  *
  * Note: The current implementation of this feature restricts each NTB
  * to a single NDP, implying that multiplexed sessions cannot share an
- * NTB. This might affect performace for multiplexed sessions.
+ * NTB. This might affect performance for multiplexed sessions.
  */
 static const struct driver_info cdc_mbim_info_ndp_to_end = {
 	.description = "CDC MBIM",
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index df0d1837e4ed..24753a4da7e6 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -192,7 +192,8 @@ static u32 cdc_ncm_check_tx_max(struct usbnet *dev, u32 new_tx)
 	return val;
 }
 
-static ssize_t cdc_ncm_show_min_tx_pkt(struct device *d, struct device_attribute *attr, char *buf)
+static ssize_t min_tx_pkt_show(struct device *d,
+			       struct device_attribute *attr, char *buf)
 {
 	struct usbnet *dev = netdev_priv(to_net_dev(d));
 	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
@@ -200,7 +201,8 @@ static ssize_t cdc_ncm_show_min_tx_pkt(struct device *d, struct device_attribute
 	return sprintf(buf, "%u\n", ctx->min_tx_pkt);
 }
 
-static ssize_t cdc_ncm_show_rx_max(struct device *d, struct device_attribute *attr, char *buf)
+static ssize_t rx_max_show(struct device *d,
+			   struct device_attribute *attr, char *buf)
 {
 	struct usbnet *dev = netdev_priv(to_net_dev(d));
 	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
@@ -208,7 +210,8 @@ static ssize_t cdc_ncm_show_rx_max(struct device *d, struct device_attribute *at
 	return sprintf(buf, "%u\n", ctx->rx_max);
 }
 
-static ssize_t cdc_ncm_show_tx_max(struct device *d, struct device_attribute *attr, char *buf)
+static ssize_t tx_max_show(struct device *d,
+			   struct device_attribute *attr, char *buf)
 {
 	struct usbnet *dev = netdev_priv(to_net_dev(d));
 	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
@@ -216,7 +219,8 @@ static ssize_t cdc_ncm_show_tx_max(struct device *d, struct device_attribute *at
 	return sprintf(buf, "%u\n", ctx->tx_max);
 }
 
-static ssize_t cdc_ncm_show_tx_timer_usecs(struct device *d, struct device_attribute *attr, char *buf)
+static ssize_t tx_timer_usecs_show(struct device *d,
+				   struct device_attribute *attr, char *buf)
 {
 	struct usbnet *dev = netdev_priv(to_net_dev(d));
 	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
@@ -224,7 +228,9 @@ static ssize_t cdc_ncm_show_tx_timer_usecs(struct device *d, struct device_attri
 	return sprintf(buf, "%u\n", ctx->timer_interval / (u32)NSEC_PER_USEC);
 }
 
-static ssize_t cdc_ncm_store_min_tx_pkt(struct device *d,  struct device_attribute *attr, const char *buf, size_t len)
+static ssize_t min_tx_pkt_store(struct device *d,
+				struct device_attribute *attr,
+				const char *buf, size_t len)
 {
 	struct usbnet *dev = netdev_priv(to_net_dev(d));
 	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
@@ -238,7 +244,9 @@ static ssize_t cdc_ncm_store_min_tx_pkt(struct device *d,  struct device_attribu
 	return len;
 }
 
-static ssize_t cdc_ncm_store_rx_max(struct device *d,  struct device_attribute *attr, const char *buf, size_t len)
+static ssize_t rx_max_store(struct device *d,
+			    struct device_attribute *attr,
+			    const char *buf, size_t len)
 {
 	struct usbnet *dev = netdev_priv(to_net_dev(d));
 	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
@@ -251,7 +259,9 @@ static ssize_t cdc_ncm_store_rx_max(struct device *d,  struct device_attribute *
 	return len;
 }
 
-static ssize_t cdc_ncm_store_tx_max(struct device *d,  struct device_attribute *attr, const char *buf, size_t len)
+static ssize_t tx_max_store(struct device *d,
+			    struct device_attribute *attr,
+			    const char *buf, size_t len)
 {
 	struct usbnet *dev = netdev_priv(to_net_dev(d));
 	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
@@ -264,7 +274,9 @@ static ssize_t cdc_ncm_store_tx_max(struct device *d,  struct device_attribute *
 	return len;
 }
 
-static ssize_t cdc_ncm_store_tx_timer_usecs(struct device *d,  struct device_attribute *attr, const char *buf, size_t len)
+static ssize_t tx_timer_usecs_store(struct device *d,
+				    struct device_attribute *attr,
+				    const char *buf, size_t len)
 {
 	struct usbnet *dev = netdev_priv(to_net_dev(d));
 	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
@@ -285,10 +297,10 @@ static ssize_t cdc_ncm_store_tx_timer_usecs(struct device *d,  struct device_att
 	return len;
 }
 
-static DEVICE_ATTR(min_tx_pkt, 0644, cdc_ncm_show_min_tx_pkt, cdc_ncm_store_min_tx_pkt);
-static DEVICE_ATTR(rx_max, 0644, cdc_ncm_show_rx_max, cdc_ncm_store_rx_max);
-static DEVICE_ATTR(tx_max, 0644, cdc_ncm_show_tx_max, cdc_ncm_store_tx_max);
-static DEVICE_ATTR(tx_timer_usecs, 0644, cdc_ncm_show_tx_timer_usecs, cdc_ncm_store_tx_timer_usecs);
+static DEVICE_ATTR_RW(min_tx_pkt);
+static DEVICE_ATTR_RW(rx_max);
+static DEVICE_ATTR_RW(tx_max);
+static DEVICE_ATTR_RW(tx_timer_usecs);
 
 static ssize_t ndp_to_end_show(struct device *d, struct device_attribute *attr, char *buf)
 {
@@ -628,7 +640,7 @@ out:
 	/* set MTU to max supported by the device if necessary */
 	dev->net->mtu = min_t(int, dev->net->mtu, ctx->max_datagram_size - cdc_ncm_eth_hlen(dev));
 
-	/* do not exceed operater preferred MTU */
+	/* do not exceed operator preferred MTU */
 	if (ctx->mbim_extended_desc) {
 		mbim_mtu = le16_to_cpu(ctx->mbim_extended_desc->wMTU);
 		if (mbim_mtu != 0 && mbim_mtu < dev->net->mtu)
@@ -685,7 +697,7 @@ static int cdc_ncm_setup(struct usbnet *dev)
 	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
 	u32 def_rx, def_tx;
 
-	/* be conservative when selecting intial buffer size to
+	/* be conservative when selecting initial buffer size to
 	 * increase the number of hosts this will work for
 	 */
 	def_rx = min_t(u32, CDC_NCM_NTB_DEF_SIZE_RX,
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 5c779cc0ea11..54ef8492ca01 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -457,9 +457,8 @@ static const struct usb_device_id hso_ids[] = {
 MODULE_DEVICE_TABLE(usb, hso_ids);
 
 /* Sysfs attribute */
-static ssize_t hso_sysfs_show_porttype(struct device *dev,
-				       struct device_attribute *attr,
-				       char *buf)
+static ssize_t hsotype_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
 {
 	struct hso_device *hso_dev = dev_get_drvdata(dev);
 	char *port_name;
@@ -505,7 +504,7 @@ static ssize_t hso_sysfs_show_porttype(struct device *dev,
 
 	return sprintf(buf, "%s\n", port_name);
 }
-static DEVICE_ATTR(hsotype, 0444, hso_sysfs_show_porttype, NULL);
+static DEVICE_ATTR_RO(hsotype);
 
 static struct attribute *hso_serial_dev_attrs[] = {
 	&dev_attr_hsotype.attr,
diff --git a/drivers/net/usb/huawei_cdc_ncm.c b/drivers/net/usb/huawei_cdc_ncm.c
index a87f0dabcdb7..849b77330bf2 100644
--- a/drivers/net/usb/huawei_cdc_ncm.c
+++ b/drivers/net/usb/huawei_cdc_ncm.c
@@ -96,6 +96,7 @@ static int huawei_cdc_ncm_bind(struct usbnet *usbnet_dev,
 		subdriver = usb_cdc_wdm_register(ctx->control,
 						 &usbnet_dev->status->desc,
 						 1024, /* wMaxCommand */
+						 WWAN_PORT_AT,
 						 huawei_cdc_ncm_wdm_manage_power);
 	if (IS_ERR(subdriver)) {
 		ret = PTR_ERR(subdriver);
diff --git a/drivers/net/usb/int51x1.c b/drivers/net/usb/int51x1.c
index ed05f992c612..6fde41550de1 100644
--- a/drivers/net/usb/int51x1.c
+++ b/drivers/net/usb/int51x1.c
@@ -61,7 +61,7 @@ static struct sk_buff *int51x1_tx_fixup(struct usbnet *dev,
 	int need_tail = 0;
 	__le16 *len;
 
-	/* if packet and our header is smaler than 64 pad to 64 (+ ZLP) */
+	/* if packet and our header is smaller than 64 pad to 64 (+ ZLP) */
 	if ((pack_with_header_len) < dev->maxpacket)
 		need_tail = dev->maxpacket - pack_with_header_len + 1;
 	/*
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 02bce40a67e5..25489389ea49 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -298,7 +298,7 @@ struct lan78xx_net;
 struct lan78xx_priv {
 	struct lan78xx_net *dev;
 	u32 rfe_ctl;
-	u32 mchash_table[DP_SEL_VHF_HASH_LEN]; /* multicat hash table */
+	u32 mchash_table[DP_SEL_VHF_HASH_LEN]; /* multicast hash table */
 	u32 pfilter_table[NUM_OF_MAF][2]; /* perfect filter table */
 	u32 vlan_table[DP_SEL_VHF_VLAN_LEN];
 	struct mutex dataport_mutex; /* for dataport access */
diff --git a/drivers/net/usb/lg-vl600.c b/drivers/net/usb/lg-vl600.c
index 217a2d8fa47b..b2495fa80171 100644
--- a/drivers/net/usb/lg-vl600.c
+++ b/drivers/net/usb/lg-vl600.c
@@ -31,7 +31,7 @@
  * Windows/Mac drivers do send a couple of such frames to the device
  * during initialisation, with protocol set to 0x0906 or 0x0b06 and (what
  * seems to be) a flag in the .dummy_flags.  This doesn't seem necessary
- * for modem operation but can possibly be used for GPS or other funcitons.
+ * for modem operation but can possibly be used for GPS or other functions.
  */
 
 struct vl600_frame_hdr {
@@ -72,7 +72,7 @@ static int vl600_bind(struct usbnet *dev, struct usb_interface *intf)
 	/* ARP packets don't go through, but they're also of no use.  The
 	 * subnet has only two hosts anyway: us and the gateway / DHCP
 	 * server (probably simulated by modem firmware or network operator)
-	 * whose address changes everytime we connect to the intarwebz and
+	 * whose address changes every time we connect to the intarwebz and
 	 * who doesn't bother answering ARP requests either.  So hardware
 	 * addresses have no meaning, the destination and the source of every
 	 * packet depend only on whether it is on the IN or OUT endpoint.  */
diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c
index 9f9352a4522f..2469bdcb1a04 100644
--- a/drivers/net/usb/mcs7830.c
+++ b/drivers/net/usb/mcs7830.c
@@ -601,7 +601,7 @@ MODULE_DEVICE_TABLE(usb, products);
 
 static int mcs7830_reset_resume (struct usb_interface *intf)
 {
- 	/* YES, this function is successful enough that ethtool -d
+	/* YES, this function is successful enough that ethtool -d
            does show same output pre-/post-suspend */
 
 	struct usbnet		*dev = usb_get_intfdata(intf);
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index bc55ec739af9..6a2e4f884b12 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -710,7 +710,8 @@ static int qmi_wwan_register_subdriver(struct usbnet *dev)
 
 	/* register subdriver */
 	subdriver = usb_cdc_wdm_register(info->control, &dev->status->desc,
-					 4096, &qmi_wwan_cdc_wdm_manage_power);
+					 4096, WWAN_PORT_QMI,
+					 &qmi_wwan_cdc_wdm_manage_power);
 	if (IS_ERR(subdriver)) {
 		dev_err(&info->control->dev, "subdriver registration failed\n");
 		rv = PTR_ERR(subdriver);
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index e25bfb7021ed..1692d3b1b6e1 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -931,6 +931,8 @@ struct r8152 {
 	u32 rx_pending;
 	u32 fc_pause_on, fc_pause_off;
 
+	unsigned int pipe_in, pipe_out, pipe_intr, pipe_ctrl_in, pipe_ctrl_out;
+
 	u32 support_2500full:1;
 	u32 lenovo_macpassthru:1;
 	u32 dell_tb_rx_agg_bug:1;
@@ -1198,7 +1200,7 @@ int get_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data)
 	if (!tmp)
 		return -ENOMEM;
 
-	ret = usb_control_msg(tp->udev, usb_rcvctrlpipe(tp->udev, 0),
+	ret = usb_control_msg(tp->udev, tp->pipe_ctrl_in,
 			      RTL8152_REQ_GET_REGS, RTL8152_REQT_READ,
 			      value, index, tmp, size, 500);
 	if (ret < 0)
@@ -1221,7 +1223,7 @@ int set_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data)
 	if (!tmp)
 		return -ENOMEM;
 
-	ret = usb_control_msg(tp->udev, usb_sndctrlpipe(tp->udev, 0),
+	ret = usb_control_msg(tp->udev, tp->pipe_ctrl_out,
 			      RTL8152_REQ_SET_REGS, RTL8152_REQT_WRITE,
 			      value, index, tmp, size, 500);
 
@@ -2041,7 +2043,7 @@ static int alloc_all_mem(struct r8152 *tp)
 		goto err1;
 
 	tp->intr_interval = (int)ep_intr->desc.bInterval;
-	usb_fill_int_urb(tp->intr_urb, tp->udev, usb_rcvintpipe(tp->udev, 3),
+	usb_fill_int_urb(tp->intr_urb, tp->udev, tp->pipe_intr,
 			 tp->intr_buff, INTBUFSIZE, intr_callback,
 			 tp, tp->intr_interval);
 
@@ -2305,7 +2307,7 @@ static int r8152_tx_agg_fill(struct r8152 *tp, struct tx_agg *agg)
 	if (ret < 0)
 		goto out_tx_fill;
 
-	usb_fill_bulk_urb(agg->urb, tp->udev, usb_sndbulkpipe(tp->udev, 2),
+	usb_fill_bulk_urb(agg->urb, tp->udev, tp->pipe_out,
 			  agg->head, (int)(tx_data - (u8 *)agg->head),
 			  (usb_complete_t)write_bulk_callback, agg);
 
@@ -2445,7 +2447,7 @@ static int rx_bottom(struct r8152 *tp, int budget)
 			unsigned int pkt_len, rx_frag_head_sz;
 			struct sk_buff *skb;
 
-			/* limite the skb numbers for rx_queue */
+			/* limit the skb numbers for rx_queue */
 			if (unlikely(skb_queue_len(&tp->rx_queue) >= 1000))
 				break;
 
@@ -2620,7 +2622,7 @@ int r8152_submit_rx(struct r8152 *tp, struct rx_agg *agg, gfp_t mem_flags)
 	    !test_bit(WORK_ENABLE, &tp->flags) || !netif_carrier_ok(tp->netdev))
 		return 0;
 
-	usb_fill_bulk_urb(agg->urb, tp->udev, usb_rcvbulkpipe(tp->udev, 1),
+	usb_fill_bulk_urb(agg->urb, tp->udev, tp->pipe_in,
 			  agg->buffer, tp->rx_buf_sz,
 			  (usb_complete_t)read_bulk_callback, agg);
 
@@ -8211,7 +8213,7 @@ static int rtl8152_post_reset(struct usb_interface *intf)
 	if (!tp)
 		return 0;
 
-	/* reset the MAC adddress in case of policy change */
+	/* reset the MAC address in case of policy change */
 	if (determine_ethernet_addr(tp, &sa) >= 0) {
 		rtnl_lock();
 		dev_set_mac_address (tp->netdev, &sa, NULL);
@@ -8967,6 +8969,79 @@ static int rtl8152_set_ringparam(struct net_device *netdev,
 	return 0;
 }
 
+static void rtl8152_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
+{
+	struct r8152 *tp = netdev_priv(netdev);
+	u16 bmcr, lcladv, rmtadv;
+	u8 cap;
+
+	if (usb_autopm_get_interface(tp->intf) < 0)
+		return;
+
+	mutex_lock(&tp->control);
+
+	bmcr = r8152_mdio_read(tp, MII_BMCR);
+	lcladv = r8152_mdio_read(tp, MII_ADVERTISE);
+	rmtadv = r8152_mdio_read(tp, MII_LPA);
+
+	mutex_unlock(&tp->control);
+
+	usb_autopm_put_interface(tp->intf);
+
+	if (!(bmcr & BMCR_ANENABLE)) {
+		pause->autoneg = 0;
+		pause->rx_pause = 0;
+		pause->tx_pause = 0;
+		return;
+	}
+
+	pause->autoneg = 1;
+
+	cap = mii_resolve_flowctrl_fdx(lcladv, rmtadv);
+
+	if (cap & FLOW_CTRL_RX)
+		pause->rx_pause = 1;
+
+	if (cap & FLOW_CTRL_TX)
+		pause->tx_pause = 1;
+}
+
+static int rtl8152_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
+{
+	struct r8152 *tp = netdev_priv(netdev);
+	u16 old, new1;
+	u8 cap = 0;
+	int ret;
+
+	ret = usb_autopm_get_interface(tp->intf);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&tp->control);
+
+	if (pause->autoneg && !(r8152_mdio_read(tp, MII_BMCR) & BMCR_ANENABLE)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (pause->rx_pause)
+		cap |= FLOW_CTRL_RX;
+
+	if (pause->tx_pause)
+		cap |= FLOW_CTRL_TX;
+
+	old = r8152_mdio_read(tp, MII_ADVERTISE);
+	new1 = (old & ~(ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM)) | mii_advertise_flowctrl(cap);
+	if (old != new1)
+		r8152_mdio_write(tp, MII_ADVERTISE, new1);
+
+out:
+	mutex_unlock(&tp->control);
+	usb_autopm_put_interface(tp->intf);
+
+	return ret;
+}
+
 static const struct ethtool_ops ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS,
 	.get_drvinfo = rtl8152_get_drvinfo,
@@ -8989,6 +9064,8 @@ static const struct ethtool_ops ops = {
 	.set_tunable = rtl8152_set_tunable,
 	.get_ringparam = rtl8152_get_ringparam,
 	.set_ringparam = rtl8152_set_ringparam,
+	.get_pauseparam = rtl8152_get_pauseparam,
+	.set_pauseparam = rtl8152_set_pauseparam,
 };
 
 static int rtl8152_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
@@ -9432,6 +9509,12 @@ static int rtl8152_probe(struct usb_interface *intf,
 	tp->intf = intf;
 	tp->version = version;
 
+	tp->pipe_ctrl_in = usb_rcvctrlpipe(udev, 0);
+	tp->pipe_ctrl_out = usb_sndctrlpipe(udev, 0);
+	tp->pipe_in = usb_rcvbulkpipe(udev, 1);
+	tp->pipe_out = usb_sndbulkpipe(udev, 2);
+	tp->pipe_intr = usb_rcvintpipe(udev, 3);
+
 	switch (version) {
 	case RTL_VER_01:
 	case RTL_VER_02:
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index f813ca9dec53..85a8b96e39a6 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -324,7 +324,7 @@ generic_rndis_bind(struct usbnet *dev, struct usb_interface *intf, int flags)
 	 * For RX we handle drivers that zero-pad to end-of-packet.
 	 * Don't let userspace change these settings.
 	 *
-	 * NOTE: there still seems to be wierdness here, as if we need
+	 * NOTE: there still seems to be weirdness here, as if we need
 	 * to do some more things to make sure WinCE targets accept this.
 	 * They default to jumbograms of 8KB or 16KB, which is absurd
 	 * for such low data rates and which is also more than Linux
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index ecf62849f4c1..57a5a025255c 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1597,6 +1597,9 @@ void usbnet_disconnect (struct usb_interface *intf)
 		   xdev->bus->bus_name, xdev->devpath,
 		   dev->driver_info->description);
 
+	if (dev->driver_info->unbind)
+		dev->driver_info->unbind(dev, intf);
+
 	net = dev->net;
 	unregister_netdev (net);
 
@@ -1604,9 +1607,6 @@ void usbnet_disconnect (struct usb_interface *intf)
 
 	usb_scuttle_anchored_urbs(&dev->deferred);
 
-	if (dev->driver_info->unbind)
-		dev->driver_info->unbind (dev, intf);
-
 	usb_kill_urb(dev->interrupt);
 	usb_free_urb(dev->interrupt);
 	kfree(dev->padding_pkt);
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 78a01c71a17c..0416a7e00914 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -380,7 +380,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 				   struct page *page, unsigned int offset,
 				   unsigned int len, unsigned int truesize,
 				   bool hdr_valid, unsigned int metasize,
-				   unsigned int headroom)
+				   bool whole_page)
 {
 	struct sk_buff *skb;
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
@@ -398,16 +398,28 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	else
 		hdr_padded_len = sizeof(struct padded_vnet_hdr);
 
-	/* If headroom is not 0, there is an offset between the beginning of the
+	/* If whole_page, there is an offset between the beginning of the
 	 * data and the allocated space, otherwise the data and the allocated
 	 * space are aligned.
 	 *
 	 * Buffers with headroom use PAGE_SIZE as alloc size, see
 	 * add_recvbuf_mergeable() + get_mergeable_buf_len()
 	 */
-	truesize = headroom ? PAGE_SIZE : truesize;
-	tailroom = truesize - len - headroom - (hdr_padded_len - hdr_len);
-	buf = p - headroom;
+	if (whole_page) {
+		/* Buffers with whole_page use PAGE_SIZE as alloc size,
+		 * see add_recvbuf_mergeable() + get_mergeable_buf_len()
+		 */
+		truesize = PAGE_SIZE;
+
+		/* page maybe head page, so we should get the buf by p, not the
+		 * page
+		 */
+		tailroom = truesize - len - offset_in_page(p);
+		buf = (char *)((unsigned long)p & PAGE_MASK);
+	} else {
+		tailroom = truesize - len;
+		buf = p;
+	}
 
 	len -= hdr_len;
 	offset += hdr_padded_len;
@@ -721,6 +733,12 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	len -= vi->hdr_len;
 	stats->bytes += len;
 
+	if (unlikely(len > GOOD_PACKET_LEN)) {
+		pr_debug("%s: rx error: len %u exceeds max size %d\n",
+			 dev->name, len, GOOD_PACKET_LEN);
+		dev->stats.rx_length_errors++;
+		goto err_len;
+	}
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (xdp_prog) {
@@ -824,6 +842,7 @@ err:
 err_xdp:
 	rcu_read_unlock();
 	stats->xdp_drops++;
+err_len:
 	stats->drops++;
 	put_page(page);
 xdp_xmit:
@@ -877,6 +896,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	head_skb = NULL;
 	stats->bytes += len - vi->hdr_len;
 
+	if (unlikely(len > truesize)) {
+		pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
+			 dev->name, len, (unsigned long)ctx);
+		dev->stats.rx_length_errors++;
+		goto err_skb;
+	}
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (xdp_prog) {
@@ -953,8 +978,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 				put_page(page);
 				head_skb = page_to_skb(vi, rq, xdp_page, offset,
 						       len, PAGE_SIZE, false,
-						       metasize,
-						       VIRTIO_XDP_HEADROOM);
+						       metasize, true);
 				return head_skb;
 			}
 			break;
@@ -1004,15 +1028,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	}
 	rcu_read_unlock();
 
-	if (unlikely(len > truesize)) {
-		pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
-			 dev->name, len, (unsigned long)ctx);
-		dev->stats.rx_length_errors++;
-		goto err_skb;
-	}
-
 	head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog,
-			       metasize, headroom);
+			       metasize, !!headroom);
 	curr_skb = head_skb;
 
 	if (unlikely(!curr_skb))
@@ -1619,7 +1636,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 	if (virtio_net_hdr_from_skb(skb, &hdr->hdr,
 				    virtio_is_little_endian(vi->vdev), false,
 				    0))
-		BUG();
+		return -EPROTO;
 
 	if (vi->mergeable_rx_bufs)
 		hdr->num_buffers = 0;
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 28a6c4cfe9b8..452822f88214 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -274,7 +274,7 @@ vrf_map_register_dev(struct net_device *dev, struct netlink_ext_ack *extack)
 	int res;
 
 	/* we pre-allocate elements used in the spin-locked section (so that we
-	 * keep the spinlock as short as possibile).
+	 * keep the spinlock as short as possible).
 	 */
 	new_me = vrf_map_elem_alloc(GFP_KERNEL);
 	if (!new_me)
diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index 83c9481995dd..473df2505c8e 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -49,7 +49,7 @@ config COSA
 	  network device.
 
 	  You will need user-space utilities COSA or SRP boards for downloading
- 	  the firmware to the cards and to set them up. Look at the
+	  the firmware to the cards and to set them up. Look at the
 	  <http://www.fi.muni.cz/~kas/cosa/> for more information. You can also
 	  read the comment at the top of the <file:drivers/net/wan/cosa.c> for
 	  details about the cards and the driver itself.
@@ -108,7 +108,7 @@ config HDLC
 	  Generic HDLC driver currently supports raw HDLC, Cisco HDLC, Frame
 	  Relay, synchronous Point-to-Point Protocol (PPP) and X.25.
 
- 	  To compile this driver as a module, choose M here: the
+	  To compile this driver as a module, choose M here: the
 	  module will be called hdlc.
 
 	  If unsure, say N.
diff --git a/drivers/net/wan/c101.c b/drivers/net/wan/c101.c
index c354a5143e99..7e431e5b6e85 100644
--- a/drivers/net/wan/c101.c
+++ b/drivers/net/wan/c101.c
@@ -28,9 +28,8 @@
 
 #include "hd64570.h"
 
-
-static const char* version = "Moxa C101 driver version: 1.15";
-static const char* devname = "C101";
+static const char *version = "Moxa C101 driver version: 1.15";
+static const char *devname = "C101";
 
 #undef DEBUG_PKT
 #define DEBUG_RINGS
@@ -51,7 +50,6 @@ static const char* devname = "C101";
 
 static char *hw;		/* pointer to hw=xxx command line string */
 
-
 typedef struct card_s {
 	struct net_device *dev;
 	spinlock_t lock;	/* TX lock */
@@ -72,14 +70,13 @@ typedef struct card_s {
 	u8 page;
 
 	struct card_s *next_card;
-}card_t;
+} card_t;
 
 typedef card_t port_t;
 
 static card_t *first_card;
 static card_t **new_card = &first_card;
 
-
 #define sca_in(reg, card)	   readb((card)->win0base + C101_SCA + (reg))
 #define sca_out(value, reg, card)  writeb(value, (card)->win0base + C101_SCA + (reg))
 #define sca_inw(reg, card)	   readw((card)->win0base + C101_SCA + (reg))
@@ -87,8 +84,8 @@ static card_t **new_card = &first_card;
 /* EDA address register must be set in EDAL, EDAH order - 8 bit ISA bus */
 #define sca_outw(value, reg, card) do { \
 	writeb(value & 0xFF, (card)->win0base + C101_SCA + (reg)); \
-	writeb((value >> 8 ) & 0xFF, (card)->win0base + C101_SCA + (reg + 1));\
-} while(0)
+	writeb((value >> 8) & 0xFF, (card)->win0base + C101_SCA + (reg + 1));\
+} while (0)
 
 #define port_to_card(port)	   (port)
 #define log_node(port)		   (0)
@@ -99,7 +96,6 @@ static card_t **new_card = &first_card;
 #define get_port(card, port)	   (card)
 static void sca_msci_intr(port_t *port);
 
-
 static inline u8 sca_get_page(card_t *card)
 {
 	return card->page;
@@ -111,10 +107,8 @@ static inline void openwin(card_t *card, u8 page)
 	writeb(page, card->win0base + C101_PAGE);
 }
 
-
 #include "hd64570.c"
 
-
 static inline void set_carrier(port_t *port)
 {
 	if (!(sca_in(MSCI1_OFFSET + ST3, port) & ST3_DCD))
@@ -123,7 +117,6 @@ static inline void set_carrier(port_t *port)
 		netif_carrier_off(port_to_dev(port));
 }
 
-
 static void sca_msci_intr(port_t *port)
 {
 	u8 stat = sca_in(MSCI0_OFFSET + ST1, port); /* read MSCI ST1 status */
@@ -145,13 +138,12 @@ static void sca_msci_intr(port_t *port)
 		set_carrier(port);
 }
 
-
 static void c101_set_iface(port_t *port)
 {
 	u8 rxs = port->rxs & CLK_BRG_MASK;
 	u8 txs = port->txs & CLK_BRG_MASK;
 
-	switch(port->settings.clock_type) {
+	switch (port->settings.clock_type) {
 	case CLOCK_INT:
 		rxs |= CLK_BRG_RX; /* TX clock */
 		txs |= CLK_RXCLK_TX; /* BRG output */
@@ -179,7 +171,6 @@ static void c101_set_iface(port_t *port)
 	sca_set_port(port);
 }
 
-
 static int c101_open(struct net_device *dev)
 {
 	port_t *port = dev_to_port(dev);
@@ -206,7 +197,6 @@ static int c101_open(struct net_device *dev)
 	return 0;
 }
 
-
 static int c101_close(struct net_device *dev)
 {
 	port_t *port = dev_to_port(dev);
@@ -218,7 +208,6 @@ static int c101_close(struct net_device *dev)
 	return 0;
 }
 
-
 static int c101_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	const size_t size = sizeof(sync_serial_settings);
@@ -240,7 +229,7 @@ static int c101_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	if (cmd != SIOCWANDEV)
 		return hdlc_ioctl(dev, ifr, cmd);
 
-	switch(ifr->ifr_settings.type) {
+	switch (ifr->ifr_settings.type) {
 	case IF_GET_IFACE:
 		ifr->ifr_settings.type = IF_IFACE_SYNC_SERIAL;
 		if (ifr->ifr_settings.size < size) {
@@ -252,7 +241,7 @@ static int c101_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		return 0;
 
 	case IF_IFACE_SYNC_SERIAL:
-		if(!capable(CAP_NET_ADMIN))
+		if (!capable(CAP_NET_ADMIN))
 			return -EPERM;
 
 		if (copy_from_user(&new_line, line, size))
@@ -276,8 +265,6 @@ static int c101_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	}
 }
 
-
-
 static void c101_destroy_card(card_t *card)
 {
 	readb(card->win0base + C101_PAGE); /* Resets SCA? */
@@ -309,12 +296,12 @@ static int __init c101_run(unsigned long irq, unsigned long winbase)
 	card_t *card;
 	int result;
 
-	if (irq<3 || irq>15 || irq == 6) /* FIXME */ {
+	if (irq < 3 || irq > 15 || irq == 6) /* FIXME */ {
 		pr_err("invalid IRQ value\n");
 		return -ENODEV;
 	}
 
-	if (winbase < 0xC0000 || winbase > 0xDFFFF || (winbase & 0x3FFF) !=0) {
+	if (winbase < 0xC0000 || winbase > 0xDFFFF || (winbase & 0x3FFF) != 0) {
 		pr_err("invalid RAM value\n");
 		return -ENODEV;
 	}
@@ -392,8 +379,6 @@ static int __init c101_run(unsigned long irq, unsigned long winbase)
 	return 0;
 }
 
-
-
 static int __init c101_init(void)
 {
 	if (hw == NULL) {
@@ -419,13 +404,12 @@ static int __init c101_init(void)
 
 		if (*hw == '\x0')
 			return first_card ? 0 : -EINVAL;
-	}while(*hw++ == ':');
+	} while (*hw++ == ':');
 
 	pr_err("invalid hardware parameters\n");
 	return first_card ? 0 : -EINVAL;
 }
 
-
 static void __exit c101_cleanup(void)
 {
 	card_t *card = first_card;
@@ -438,7 +422,6 @@ static void __exit c101_cleanup(void)
 	}
 }
 
-
 module_init(c101_init);
 module_exit(c101_cleanup);
 
diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c
index 2369ca250cd6..43caab0b7dee 100644
--- a/drivers/net/wan/cosa.c
+++ b/drivers/net/wan/cosa.c
@@ -1,13 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /* $Id: cosa.c,v 1.31 2000/03/08 17:47:16 kas Exp $ */
 
-/*
- *  Copyright (C) 1995-1997  Jan "Yenya" Kasprzak <kas@fi.muni.cz>
+/*  Copyright (C) 1995-1997  Jan "Yenya" Kasprzak <kas@fi.muni.cz>
  *  Generic HDLC port Copyright (C) 2008 Krzysztof Halasa <khc@pm.waw.pl>
  */
 
-/*
- * The driver for the SRP and COSA synchronous serial cards.
+/* The driver for the SRP and COSA synchronous serial cards.
  *
  * HARDWARE INFO
  *
@@ -90,7 +88,7 @@
 #define COSA_MAX_ID_STRING	128
 
 /* Maximum length of the channel name */
-#define COSA_MAX_NAME		(sizeof("cosaXXXcXXX")+1)
+#define COSA_MAX_NAME		(sizeof("cosaXXXcXXX") + 1)
 
 /* Per-channel data structure */
 
@@ -124,9 +122,9 @@ struct channel_data {
 };
 
 /* cosa->firmware_status bits */
-#define COSA_FW_RESET		(1<<0)	/* Is the ROM monitor active? */
-#define COSA_FW_DOWNLOAD	(1<<1)	/* Is the microcode downloaded? */
-#define COSA_FW_START		(1<<2)	/* Is the microcode running? */
+#define COSA_FW_RESET		BIT(0)	/* Is the ROM monitor active? */
+#define COSA_FW_DOWNLOAD	BIT(1)	/* Is the microcode downloaded? */
+#define COSA_FW_START		BIT(2)	/* Is the microcode running? */
 
 struct cosa_data {
 	int num;			/* Card number */
@@ -152,28 +150,25 @@ struct cosa_data {
 	char *type;				/* card type */
 };
 
-/*
- * Define this if you want all the possible ports to be autoprobed.
+/* Define this if you want all the possible ports to be autoprobed.
  * It is here but it probably is not a good idea to use this.
  */
-/* #define COSA_ISA_AUTOPROBE	1 */
+/* #define COSA_ISA_AUTOPROBE	1*/
 
-/*
- * Character device major number. 117 was allocated for us.
+/* Character device major number. 117 was allocated for us.
  * The value of 0 means to allocate a first free one.
  */
 static DEFINE_MUTEX(cosa_chardev_mutex);
 static int cosa_major = 117;
 
-/*
- * Encoding of the minor numbers:
+/* Encoding of the minor numbers:
  * The lowest CARD_MINOR_BITS bits means the channel on the single card,
  * the highest bits means the card number.
  */
 #define CARD_MINOR_BITS	4	/* How many bits in minor number are reserved
-				 * for the single card */
-/*
- * The following depends on CARD_MINOR_BITS. Unfortunately, the "MODULE_STRING"
+				 * for the single card
+				 */
+/* The following depends on CARD_MINOR_BITS. Unfortunately, the "MODULE_STRING"
  * macro doesn't like anything other than the raw number as an argument :-(
  */
 #define MAX_CARDS	16
@@ -184,8 +179,7 @@ static int cosa_major = 117;
 #define DRIVER_TXMAP_SHIFT	2
 #define DRIVER_TXMAP_MASK	0x0c	/* FIXME: 0xfc for 8-channel version */
 
-/*
- * for cosa->rxtx - indicates whether either transmit or receive is
+/* for cosa->rxtx - indicates whether either transmit or receive is
  * in progress. These values are mean number of the bit.
  */
 #define TXBIT 0
@@ -198,22 +192,22 @@ static int cosa_major = 117;
 #undef DEBUG_IRQS //1	/* Print the message when the IRQ is received */
 #undef DEBUG_IO   //1	/* Dump the I/O traffic */
 
-#define TX_TIMEOUT	(5*HZ)
+#define TX_TIMEOUT	(5 * HZ)
 
 /* Maybe the following should be allocated dynamically */
 static struct cosa_data cosa_cards[MAX_CARDS];
 static int nr_cards;
 
 #ifdef COSA_ISA_AUTOPROBE
-static int io[MAX_CARDS+1]  = { 0x220, 0x228, 0x210, 0x218, 0, };
+static int io[MAX_CARDS + 1]  = {0x220, 0x228, 0x210, 0x218, 0,};
 /* NOTE: DMA is not autoprobed!!! */
-static int dma[MAX_CARDS+1] = { 1, 7, 1, 7, 1, 7, 1, 7, 0, };
+static int dma[MAX_CARDS + 1] = {1, 7, 1, 7, 1, 7, 1, 7, 0,};
 #else
-static int io[MAX_CARDS+1];
-static int dma[MAX_CARDS+1];
+static int io[MAX_CARDS + 1];
+static int dma[MAX_CARDS + 1];
 #endif
 /* IRQ can be safely autoprobed */
-static int irq[MAX_CARDS+1] = { -1, -1, -1, -1, -1, -1, 0, };
+static int irq[MAX_CARDS + 1] = {-1, -1, -1, -1, -1, -1, 0,};
 
 /* for class stuff*/
 static struct class *cosa_class;
@@ -244,14 +238,14 @@ MODULE_LICENSE("GPL");
 #define cosa_inw  inw
 #endif
 
-#define is_8bit(cosa)		(!(cosa->datareg & 0x08))
+#define is_8bit(cosa)		(!((cosa)->datareg & 0x08))
 
-#define cosa_getstatus(cosa)	(cosa_inb(cosa->statusreg))
-#define cosa_putstatus(cosa, stat)	(cosa_outb(stat, cosa->statusreg))
-#define cosa_getdata16(cosa)	(cosa_inw(cosa->datareg))
-#define cosa_getdata8(cosa)	(cosa_inb(cosa->datareg))
-#define cosa_putdata16(cosa, dt)	(cosa_outw(dt, cosa->datareg))
-#define cosa_putdata8(cosa, dt)	(cosa_outb(dt, cosa->datareg))
+#define cosa_getstatus(cosa)	(cosa_inb((cosa)->statusreg))
+#define cosa_putstatus(cosa, stat)	(cosa_outb(stat, (cosa)->statusreg))
+#define cosa_getdata16(cosa)	(cosa_inw((cosa)->datareg))
+#define cosa_getdata8(cosa)	(cosa_inb((cosa)->datareg))
+#define cosa_putdata16(cosa, dt)	(cosa_outw(dt, (cosa)->datareg))
+#define cosa_putdata8(cosa, dt)	(cosa_outb(dt, (cosa)->datareg))
 
 /* Initialization stuff */
 static int cosa_probe(int ioaddr, int irq, int dma);
@@ -280,14 +274,14 @@ static char *chrdev_setup_rx(struct channel_data *channel, int size);
 static int chrdev_rx_done(struct channel_data *channel);
 static int chrdev_tx_done(struct channel_data *channel, int size);
 static ssize_t cosa_read(struct file *file,
-	char __user *buf, size_t count, loff_t *ppos);
+			 char __user *buf, size_t count, loff_t *ppos);
 static ssize_t cosa_write(struct file *file,
-	const char __user *buf, size_t count, loff_t *ppos);
+			  const char __user *buf, size_t count, loff_t *ppos);
 static unsigned int cosa_poll(struct file *file, poll_table *poll);
 static int cosa_open(struct inode *inode, struct file *file);
 static int cosa_release(struct inode *inode, struct file *file);
 static long cosa_chardev_ioctl(struct file *file, unsigned int cmd,
-				unsigned long arg);
+			       unsigned long arg);
 #ifdef COSA_FASYNC_WORKING
 static int cosa_fasync(struct inode *inode, struct file *file, int on);
 #endif
@@ -337,7 +331,7 @@ static void debug_status_in(struct cosa_data *cosa, int status);
 static void debug_status_out(struct cosa_data *cosa, int status);
 #endif
 
-static inline struct channel_data* dev_to_chan(struct net_device *dev)
+static inline struct channel_data *dev_to_chan(struct net_device *dev)
 {
 	return (struct channel_data *)dev_to_hdlc(dev)->priv;
 }
@@ -355,15 +349,16 @@ static int __init cosa_init(void)
 			goto out;
 		}
 	} else {
-		if (!(cosa_major=register_chrdev(0, "cosa", &cosa_fops))) {
+		cosa_major = register_chrdev(0, "cosa", &cosa_fops);
+		if (!cosa_major) {
 			pr_warn("unable to register chardev\n");
 			err = -EIO;
 			goto out;
 		}
 	}
-	for (i=0; i<MAX_CARDS; i++)
+	for (i = 0; i < MAX_CARDS; i++)
 		cosa_cards[i].num = -1;
-	for (i=0; io[i] != 0 && i < MAX_CARDS; i++)
+	for (i = 0; io[i] != 0 && i < MAX_CARDS; i++)
 		cosa_probe(io[i], irq[i], dma[i]);
 	if (!nr_cards) {
 		pr_warn("no devices found\n");
@@ -426,7 +421,7 @@ static const struct net_device_ops cosa_ops = {
 
 static int cosa_probe(int base, int irq, int dma)
 {
-	struct cosa_data *cosa = cosa_cards+nr_cards;
+	struct cosa_data *cosa = cosa_cards + nr_cards;
 	int i, err = 0;
 
 	memset(cosa, 0, sizeof(struct cosa_data));
@@ -438,7 +433,8 @@ static int cosa_probe(int base, int irq, int dma)
 		return -1;
 	}
 	/* I/O address should be between 0x100 and 0x3ff and should be
-	 * multiple of 8. */
+	 * multiple of 8.
+	 */
 	if (base < 0x100 || base > 0x3ff || base & 0x7) {
 		pr_info("invalid I/O address 0x%x\n", base);
 		return -1;
@@ -448,8 +444,9 @@ static int cosa_probe(int base, int irq, int dma)
 		pr_info("invalid DMA %d\n", dma);
 		return -1;
 	}
-	/* and finally, on 16-bit COSA DMA should be 4-7 and 
-	 * I/O base should not be multiple of 0x10 */
+	/* and finally, on 16-bit COSA DMA should be 4-7 and
+	 * I/O base should not be multiple of 0x10
+	 */
 	if (((base & 0x8) && dma < 4) || (!(base & 0x8) && dma > 3)) {
 		pr_info("8/16 bit base and DMA mismatch (base=0x%x, dma=%d)\n",
 			base, dma);
@@ -458,12 +455,12 @@ static int cosa_probe(int base, int irq, int dma)
 
 	cosa->dma = dma;
 	cosa->datareg = base;
-	cosa->statusreg = is_8bit(cosa)?base+1:base+2;
+	cosa->statusreg = is_8bit(cosa) ? base + 1 : base + 2;
 	spin_lock_init(&cosa->lock);
 
-	if (!request_region(base, is_8bit(cosa)?2:4,"cosa"))
+	if (!request_region(base, is_8bit(cosa) ? 2 : 4, "cosa"))
 		return -1;
-	
+
 	if (cosa_reset_and_read_id(cosa, cosa->id_string) < 0) {
 		printk(KERN_DEBUG "probe at 0x%x failed.\n", base);
 		err = -1;
@@ -471,11 +468,11 @@ static int cosa_probe(int base, int irq, int dma)
 	}
 
 	/* Test the validity of identification string */
-	if (!strncmp(cosa->id_string, "SRP", 3))
+	if (!strncmp(cosa->id_string, "SRP", 3)) {
 		cosa->type = "srp";
-	else if (!strncmp(cosa->id_string, "COSA", 4))
-		cosa->type = is_8bit(cosa)? "cosa8": "cosa16";
-	else {
+	} else if (!strncmp(cosa->id_string, "COSA", 4)) {
+		cosa->type = is_8bit(cosa) ? "cosa8" : "cosa16";
+	} else {
 /* Print a warning only if we are not autoprobing */
 #ifndef COSA_ISA_AUTOPROBE
 		pr_info("valid signature not found at 0x%x\n", base);
@@ -483,9 +480,9 @@ static int cosa_probe(int base, int irq, int dma)
 		err = -1;
 		goto err_out;
 	}
-	/* Update the name of the region now we know the type of card */ 
-	release_region(base, is_8bit(cosa)?2:4);
-	if (!request_region(base, is_8bit(cosa)?2:4, cosa->type)) {
+	/* Update the name of the region now we know the type of card */
+	release_region(base, is_8bit(cosa) ? 2 : 4);
+	if (!request_region(base, is_8bit(cosa) ? 2 : 4, cosa->type)) {
 		printk(KERN_DEBUG "changing name at 0x%x failed.\n", base);
 		return -1;
 	}
@@ -495,8 +492,7 @@ static int cosa_probe(int base, int irq, int dma)
 		unsigned long irqs;
 /*		pr_info("IRQ autoprobe\n"); */
 		irqs = probe_irq_on();
-		/* 
-		 * Enable interrupt on tx buffer empty (it sure is) 
+		/* Enable interrupt on tx buffer empty (it sure is)
 		 * really sure ?
 		 * FIXME: When this code is not used as module, we should
 		 * probably call udelay() instead of the interruptible sleep.
@@ -536,8 +532,8 @@ static int cosa_probe(int base, int irq, int dma)
 		err = -1;
 		goto err_out1;
 	}
-	
-	cosa->bouncebuf = kmalloc(COSA_MTU, GFP_KERNEL|GFP_DMA);
+
+	cosa->bouncebuf = kmalloc(COSA_MTU, GFP_KERNEL | GFP_DMA);
 	if (!cosa->bouncebuf) {
 		err = -ENOMEM;
 		goto err_out2;
@@ -563,7 +559,8 @@ static int cosa_probe(int base, int irq, int dma)
 		sema_init(&chan->wsem, 1);
 
 		/* Register the network interface */
-		if (!(chan->netdev = alloc_hdlcdev(chan))) {
+		chan->netdev = alloc_hdlcdev(chan);
+		if (!chan->netdev) {
 			pr_warn("%s: alloc_hdlcdev failed\n", chan->name);
 			err = -ENOMEM;
 			goto err_hdlcdev;
@@ -603,12 +600,11 @@ err_out2:
 err_out1:
 	free_irq(cosa->irq, cosa);
 err_out:
-	release_region(cosa->datareg,is_8bit(cosa)?2:4);
+	release_region(cosa->datareg, is_8bit(cosa) ? 2 : 4);
 	pr_notice("cosa%d: allocating resources failed\n", cosa->num);
 	return err;
 }
 
-
 /*---------- network device ---------- */
 
 static int cosa_net_attach(struct net_device *dev, unsigned short encoding,
@@ -659,7 +655,7 @@ static int cosa_net_open(struct net_device *dev)
 }
 
 static netdev_tx_t cosa_net_tx(struct sk_buff *skb,
-				     struct net_device *dev)
+			       struct net_device *dev)
 {
 	struct channel_data *chan = dev_to_chan(dev);
 
@@ -714,13 +710,12 @@ static int cosa_net_close(struct net_device *dev)
 
 static char *cosa_net_setup_rx(struct channel_data *chan, int size)
 {
-	/*
-	 * We can safely fall back to non-dma-able memory, because we have
+	/* We can safely fall back to non-dma-able memory, because we have
 	 * the cosa->bouncebuf pre-allocated.
 	 */
 	kfree_skb(chan->rx_skb);
 	chan->rx_skb = dev_alloc_skb(size);
-	if (chan->rx_skb == NULL) {
+	if (!chan->rx_skb) {
 		pr_notice("%s: Memory squeeze, dropping packet\n", chan->name);
 		chan->netdev->stats.rx_dropped++;
 		return NULL;
@@ -767,7 +762,7 @@ static int cosa_net_tx_done(struct channel_data *chan, int size)
 /*---------- Character device ---------- */
 
 static ssize_t cosa_read(struct file *file,
-	char __user *buf, size_t count, loff_t *ppos)
+			 char __user *buf, size_t count, loff_t *ppos)
 {
 	DECLARE_WAITQUEUE(wait, current);
 	unsigned long flags;
@@ -782,9 +777,9 @@ static ssize_t cosa_read(struct file *file,
 	}
 	if (mutex_lock_interruptible(&chan->rlock))
 		return -ERESTARTSYS;
-	
-	chan->rxdata = kmalloc(COSA_MTU, GFP_DMA|GFP_KERNEL);
-	if (chan->rxdata == NULL) {
+
+	chan->rxdata = kmalloc(COSA_MTU, GFP_DMA | GFP_KERNEL);
+	if (!chan->rxdata) {
 		mutex_unlock(&chan->rlock);
 		return -ENOMEM;
 	}
@@ -840,9 +835,8 @@ static int chrdev_rx_done(struct channel_data *chan)
 	return 1;
 }
 
-
 static ssize_t cosa_write(struct file *file,
-	const char __user *buf, size_t count, loff_t *ppos)
+			  const char __user *buf, size_t count, loff_t *ppos)
 {
 	DECLARE_WAITQUEUE(wait, current);
 	struct channel_data *chan = file->private_data;
@@ -860,10 +854,10 @@ static ssize_t cosa_write(struct file *file,
 
 	if (count > COSA_MTU)
 		count = COSA_MTU;
-	
+
 	/* Allocate the buffer */
-	kbuf = kmalloc(count, GFP_KERNEL|GFP_DMA);
-	if (kbuf == NULL) {
+	kbuf = kmalloc(count, GFP_KERNEL | GFP_DMA);
+	if (!kbuf) {
 		up(&chan->wsem);
 		return -ENOMEM;
 	}
@@ -872,7 +866,7 @@ static ssize_t cosa_write(struct file *file,
 		kfree(kbuf);
 		return -EFAULT;
 	}
-	chan->tx_status=0;
+	chan->tx_status = 0;
 	cosa_start_tx(chan, kbuf, count);
 
 	spin_lock_irqsave(&cosa->lock, flags);
@@ -927,20 +921,20 @@ static int cosa_open(struct inode *inode, struct file *file)
 	int ret = 0;
 
 	mutex_lock(&cosa_chardev_mutex);
-	if ((n=iminor(file_inode(file))>>CARD_MINOR_BITS)
-		>= nr_cards) {
+	n = iminor(file_inode(file)) >> CARD_MINOR_BITS;
+	if (n >= nr_cards) {
 		ret = -ENODEV;
 		goto out;
 	}
-	cosa = cosa_cards+n;
+	cosa = cosa_cards + n;
 
-	if ((n=iminor(file_inode(file))
-		& ((1<<CARD_MINOR_BITS)-1)) >= cosa->nchannels) {
+	n = iminor(file_inode(file)) & ((1 << CARD_MINOR_BITS) - 1);
+	if (n >= cosa->nchannels) {
 		ret = -ENODEV;
 		goto out;
 	}
 	chan = cosa->chan + n;
-	
+
 	file->private_data = chan;
 
 	spin_lock_irqsave(&cosa->lock, flags);
@@ -982,26 +976,25 @@ static struct fasync_struct *fasync[256] = { NULL, };
 /* To be done ... */
 static int cosa_fasync(struct inode *inode, struct file *file, int on)
 {
-        int port = iminor(inode);
+	int port = iminor(inode);
 
 	return fasync_helper(inode, file, on, &fasync[port]);
 }
 #endif
 
-
 /* ---------- Ioctls ---------- */
 
-/*
- * Ioctl subroutines can safely be made inline, because they are called
+/* Ioctl subroutines can safely be made inline, because they are called
  * only from cosa_ioctl().
  */
 static inline int cosa_reset(struct cosa_data *cosa)
 {
 	char idstring[COSA_MAX_ID_STRING];
+
 	if (cosa->usage > 1)
 		pr_info("cosa%d: WARNING: reset requested with cosa->usage > 1 (%d). Odd things may happen.\n",
 			cosa->num, cosa->usage);
-	cosa->firmware_status &= ~(COSA_FW_RESET|COSA_FW_START);
+	cosa->firmware_status &= ~(COSA_FW_RESET | COSA_FW_START);
 	if (cosa_reset_and_read_id(cosa, idstring) < 0) {
 		pr_notice("cosa%d: reset failed\n", cosa->num);
 		return -EIO;
@@ -1025,7 +1018,7 @@ static inline int cosa_download(struct cosa_data *cosa, void __user *arg)
 			  cosa->name, cosa->firmware_status);
 		return -EPERM;
 	}
-	
+
 	if (copy_from_user(&d, arg, sizeof(d)))
 		return -EFAULT;
 
@@ -1034,9 +1027,8 @@ static inline int cosa_download(struct cosa_data *cosa, void __user *arg)
 	if (d.len < 0 || d.len > COSA_MAX_FIRMWARE_SIZE)
 		return -EINVAL;
 
-
 	/* If something fails, force the user to reset the card */
-	cosa->firmware_status &= ~(COSA_FW_RESET|COSA_FW_DOWNLOAD);
+	cosa->firmware_status &= ~(COSA_FW_RESET | COSA_FW_DOWNLOAD);
 
 	i = download(cosa, d.code, d.len, d.addr);
 	if (i < 0) {
@@ -1046,7 +1038,7 @@ static inline int cosa_download(struct cosa_data *cosa, void __user *arg)
 	}
 	pr_info("cosa%d: downloading microcode - 0x%04x bytes at 0x%04x\n",
 		cosa->num, d.len, d.addr);
-	cosa->firmware_status |= COSA_FW_RESET|COSA_FW_DOWNLOAD;
+	cosa->firmware_status |= COSA_FW_RESET | COSA_FW_DOWNLOAD;
 	return 0;
 }
 
@@ -1091,14 +1083,15 @@ static inline int cosa_start(struct cosa_data *cosa, int address)
 		pr_info("cosa%d: WARNING: start microcode requested with cosa->usage > 1 (%d). Odd things may happen.\n",
 			cosa->num, cosa->usage);
 
-	if ((cosa->firmware_status & (COSA_FW_RESET|COSA_FW_DOWNLOAD))
-		!= (COSA_FW_RESET|COSA_FW_DOWNLOAD)) {
+	if ((cosa->firmware_status & (COSA_FW_RESET | COSA_FW_DOWNLOAD))
+		!= (COSA_FW_RESET | COSA_FW_DOWNLOAD)) {
 		pr_notice("%s: download the microcode and/or reset the card first (status %d)\n",
 			  cosa->name, cosa->firmware_status);
 		return -EPERM;
 	}
 	cosa->firmware_status &= ~COSA_FW_RESET;
-	if ((i=startmicrocode(cosa, address)) < 0) {
+	i = startmicrocode(cosa, address);
+	if (i < 0) {
 		pr_notice("cosa%d: start microcode at 0x%04x failed: %d\n",
 			  cosa->num, address, i);
 		return -EIO;
@@ -1108,11 +1101,12 @@ static inline int cosa_start(struct cosa_data *cosa, int address)
 	cosa->firmware_status |= COSA_FW_START;
 	return 0;
 }
-		
+
 /* Buffer of size at least COSA_MAX_ID_STRING is expected */
 static inline int cosa_getidstr(struct cosa_data *cosa, char __user *string)
 {
-	int l = strlen(cosa->id_string)+1;
+	int l = strlen(cosa->id_string) + 1;
+
 	if (copy_to_user(string, cosa->id_string, l))
 		return -EFAULT;
 	return l;
@@ -1121,16 +1115,19 @@ static inline int cosa_getidstr(struct cosa_data *cosa, char __user *string)
 /* Buffer of size at least COSA_MAX_ID_STRING is expected */
 static inline int cosa_gettype(struct cosa_data *cosa, char __user *string)
 {
-	int l = strlen(cosa->type)+1;
+	int l = strlen(cosa->type) + 1;
+
 	if (copy_to_user(string, cosa->type, l))
 		return -EFAULT;
 	return l;
 }
 
 static int cosa_ioctl_common(struct cosa_data *cosa,
-	struct channel_data *channel, unsigned int cmd, unsigned long arg)
+			     struct channel_data *channel, unsigned int cmd,
+			     unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
+
 	switch (cmd) {
 	case COSAIORSET:	/* Reset the device */
 		if (!capable(CAP_NET_ADMIN))
@@ -1143,7 +1140,7 @@ static int cosa_ioctl_common(struct cosa_data *cosa,
 	case COSAIODOWNLD:	/* Download the firmware */
 		if (!capable(CAP_SYS_RAWIO))
 			return -EACCES;
-		
+
 		return cosa_download(cosa, argp);
 	case COSAIORMEM:
 		if (!capable(CAP_SYS_RAWIO))
@@ -1176,6 +1173,7 @@ static int cosa_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	int rv;
 	struct channel_data *chan = dev_to_chan(dev);
+
 	rv = cosa_ioctl_common(chan->cosa, chan, cmd,
 			       (unsigned long)ifr->ifr_data);
 	if (rv != -ENOIOCTLCMD)
@@ -1184,7 +1182,7 @@ static int cosa_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 }
 
 static long cosa_chardev_ioctl(struct file *file, unsigned int cmd,
-							unsigned long arg)
+			       unsigned long arg)
 {
 	struct channel_data *channel = file->private_data;
 	struct cosa_data *cosa;
@@ -1197,11 +1195,9 @@ static long cosa_chardev_ioctl(struct file *file, unsigned int cmd,
 	return ret;
 }
 
-
 /*---------- HW layer interface ---------- */
 
-/*
- * The higher layer can bind itself to the HW layer by setting the callbacks
+/* The higher layer can bind itself to the HW layer by setting the callbacks
  * in the channel_data structure and by using these routines.
  */
 static void cosa_enable_rx(struct channel_data *chan)
@@ -1220,8 +1216,7 @@ static void cosa_disable_rx(struct channel_data *chan)
 		put_driver_status(cosa);
 }
 
-/*
- * FIXME: This routine probably should check for cosa_start_tx() called when
+/* FIXME: This routine probably should check for cosa_start_tx() called when
  * the previous transmit is still unfinished. In this case the non-zero
  * return value should indicate to the caller that the queuing(sp?) up
  * the transmit has failed.
@@ -1235,7 +1230,7 @@ static int cosa_start_tx(struct channel_data *chan, char *buf, int len)
 
 	pr_info("cosa%dc%d: starting tx(0x%x)",
 		chan->cosa->num, chan->num, len);
-	for (i=0; i<len; i++)
+	for (i = 0; i < len; i++)
 		pr_cont(" %02x", buf[i]&0xff);
 	pr_cont("\n");
 #endif
@@ -1262,10 +1257,10 @@ static void put_driver_status(struct cosa_data *cosa)
 
 	status = (cosa->rxbitmap ? DRIVER_RX_READY : 0)
 		| (cosa->txbitmap ? DRIVER_TX_READY : 0)
-		| (cosa->txbitmap? ~(cosa->txbitmap<<DRIVER_TXMAP_SHIFT)
-			&DRIVER_TXMAP_MASK : 0);
+		| (cosa->txbitmap ? ~(cosa->txbitmap << DRIVER_TXMAP_SHIFT)
+			& DRIVER_TXMAP_MASK : 0);
 	if (!cosa->rxtx) {
-		if (cosa->rxbitmap|cosa->txbitmap) {
+		if (cosa->rxbitmap | cosa->txbitmap) {
 			if (!cosa->enabled) {
 				cosa_putstatus(cosa, SR_RX_INT_ENA);
 #ifdef DEBUG_IO
@@ -1294,10 +1289,10 @@ static void put_driver_status_nolock(struct cosa_data *cosa)
 
 	status = (cosa->rxbitmap ? DRIVER_RX_READY : 0)
 		| (cosa->txbitmap ? DRIVER_TX_READY : 0)
-		| (cosa->txbitmap? ~(cosa->txbitmap<<DRIVER_TXMAP_SHIFT)
-			&DRIVER_TXMAP_MASK : 0);
+		| (cosa->txbitmap ? ~(cosa->txbitmap << DRIVER_TXMAP_SHIFT)
+			& DRIVER_TXMAP_MASK : 0);
 
-	if (cosa->rxbitmap|cosa->txbitmap) {
+	if (cosa->rxbitmap | cosa->txbitmap) {
 		cosa_putstatus(cosa, SR_RX_INT_ENA);
 #ifdef DEBUG_IO
 		debug_status_out(cosa, SR_RX_INT_ENA);
@@ -1316,8 +1311,7 @@ static void put_driver_status_nolock(struct cosa_data *cosa)
 #endif
 }
 
-/*
- * The "kickme" function: When the DMA times out, this is called to
+/* The "kickme" function: When the DMA times out, this is called to
  * clean up the driver status.
  * FIXME: Preliminary support, the interface is probably wrong.
  */
@@ -1344,7 +1338,7 @@ static void cosa_kick(struct cosa_data *cosa)
 	udelay(100);
 	cosa_putstatus(cosa, 0);
 	udelay(100);
-	(void) cosa_getdata8(cosa);
+	(void)cosa_getdata8(cosa);
 	udelay(100);
 	cosa_putdata8(cosa, 0);
 	udelay(100);
@@ -1352,8 +1346,7 @@ static void cosa_kick(struct cosa_data *cosa)
 	spin_unlock_irqrestore(&cosa->lock, flags);
 }
 
-/*
- * Check if the whole buffer is DMA-able. It means it is below the 16M of
+/* Check if the whole buffer is DMA-able. It means it is below the 16M of
  * physical memory and doesn't span the 64k boundary. For now it seems
  * SKB's never do this, but we'll check this anyway.
  */
@@ -1361,9 +1354,10 @@ static int cosa_dma_able(struct channel_data *chan, char *buf, int len)
 {
 	static int count;
 	unsigned long b = (unsigned long)buf;
-	if (b+len >= MAX_DMA_ADDRESS)
+
+	if (b + len >= MAX_DMA_ADDRESS)
 		return 0;
-	if ((b^ (b+len)) & 0x10000) {
+	if ((b ^ (b + len)) & 0x10000) {
 		if (count++ < 5)
 			pr_info("%s: packet spanning a 64k boundary\n",
 				chan->name);
@@ -1372,11 +1366,9 @@ static int cosa_dma_able(struct channel_data *chan, char *buf, int len)
 	return 1;
 }
 
-
 /* ---------- The SRP/COSA ROM monitor functions ---------- */
 
-/*
- * Downloading SRP microcode: say "w" to SRP monitor, it answers by "w=",
+/* Downloading SRP microcode: say "w" to SRP monitor, it answers by "w=",
  * drivers need to say 4-digit hex number meaning start address of the microcode
  * separated by a single space. Monitor replies by saying " =". Now driver
  * has to write 4-digit hex number meaning the last byte address ended
@@ -1387,18 +1379,27 @@ static int download(struct cosa_data *cosa, const char __user *microcode, int le
 {
 	int i;
 
-	if (put_wait_data(cosa, 'w') == -1) return -1;
+	if (put_wait_data(cosa, 'w') == -1)
+		return -1;
 	if ((i=get_wait_data(cosa)) != 'w') { printk("dnld: 0x%04x\n",i); return -2;}
-	if (get_wait_data(cosa) != '=') return -3;
-
-	if (puthexnumber(cosa, address) < 0) return -4;
-	if (put_wait_data(cosa, ' ') == -1) return -10;
-	if (get_wait_data(cosa) != ' ') return -11;
-	if (get_wait_data(cosa) != '=') return -12;
-
-	if (puthexnumber(cosa, address+length-1) < 0) return -13;
-	if (put_wait_data(cosa, ' ') == -1) return -18;
-	if (get_wait_data(cosa) != ' ') return -19;
+	if (get_wait_data(cosa) != '=')
+		return -3;
+
+	if (puthexnumber(cosa, address) < 0)
+		return -4;
+	if (put_wait_data(cosa, ' ') == -1)
+		return -10;
+	if (get_wait_data(cosa) != ' ')
+		return -11;
+	if (get_wait_data(cosa) != '=')
+		return -12;
+
+	if (puthexnumber(cosa, address + length - 1) < 0)
+		return -13;
+	if (put_wait_data(cosa, ' ') == -1)
+		return -18;
+	if (get_wait_data(cosa) != ' ')
+		return -19;
 
 	while (length--) {
 		char c;
@@ -1413,43 +1414,53 @@ static int download(struct cosa_data *cosa, const char __user *microcode, int le
 		microcode++;
 	}
 
-	if (get_wait_data(cosa) != '\r') return -21;
-	if (get_wait_data(cosa) != '\n') return -22;
-	if (get_wait_data(cosa) != '.') return -23;
+	if (get_wait_data(cosa) != '\r')
+		return -21;
+	if (get_wait_data(cosa) != '\n')
+		return -22;
+	if (get_wait_data(cosa) != '.')
+		return -23;
 #if 0
 	printk(KERN_DEBUG "cosa%d: download completed.\n", cosa->num);
 #endif
 	return 0;
 }
 
-
-/*
- * Starting microcode is done via the "g" command of the SRP monitor.
+/* Starting microcode is done via the "g" command of the SRP monitor.
  * The chat should be the following: "g" "g=" "<addr><CR>"
  * "<CR><CR><LF><CR><LF>".
  */
 static int startmicrocode(struct cosa_data *cosa, int address)
 {
-	if (put_wait_data(cosa, 'g') == -1) return -1;
-	if (get_wait_data(cosa) != 'g') return -2;
-	if (get_wait_data(cosa) != '=') return -3;
-
-	if (puthexnumber(cosa, address) < 0) return -4;
-	if (put_wait_data(cosa, '\r') == -1) return -5;
-	
-	if (get_wait_data(cosa) != '\r') return -6;
-	if (get_wait_data(cosa) != '\r') return -7;
-	if (get_wait_data(cosa) != '\n') return -8;
-	if (get_wait_data(cosa) != '\r') return -9;
-	if (get_wait_data(cosa) != '\n') return -10;
+	if (put_wait_data(cosa, 'g') == -1)
+		return -1;
+	if (get_wait_data(cosa) != 'g')
+		return -2;
+	if (get_wait_data(cosa) != '=')
+		return -3;
+
+	if (puthexnumber(cosa, address) < 0)
+		return -4;
+	if (put_wait_data(cosa, '\r') == -1)
+		return -5;
+
+	if (get_wait_data(cosa) != '\r')
+		return -6;
+	if (get_wait_data(cosa) != '\r')
+		return -7;
+	if (get_wait_data(cosa) != '\n')
+		return -8;
+	if (get_wait_data(cosa) != '\r')
+		return -9;
+	if (get_wait_data(cosa) != '\n')
+		return -10;
 #if 0
 	printk(KERN_DEBUG "cosa%d: microcode started\n", cosa->num);
 #endif
 	return 0;
 }
 
-/*
- * Reading memory is done via the "r" command of the SRP monitor.
+/* Reading memory is done via the "r" command of the SRP monitor.
  * The chat is the following "r" "r=" "<addr> " " =" "<last_byte> " " "
  * Then driver can read the data and the conversation is finished
  * by SRP monitor sending "<CR><LF>." (dot at the end).
@@ -1459,27 +1470,39 @@ static int startmicrocode(struct cosa_data *cosa, int address)
  */
 static int readmem(struct cosa_data *cosa, char __user *microcode, int length, int address)
 {
-	if (put_wait_data(cosa, 'r') == -1) return -1;
-	if ((get_wait_data(cosa)) != 'r') return -2;
-	if ((get_wait_data(cosa)) != '=') return -3;
-
-	if (puthexnumber(cosa, address) < 0) return -4;
-	if (put_wait_data(cosa, ' ') == -1) return -5;
-	if (get_wait_data(cosa) != ' ') return -6;
-	if (get_wait_data(cosa) != '=') return -7;
-
-	if (puthexnumber(cosa, address+length-1) < 0) return -8;
-	if (put_wait_data(cosa, ' ') == -1) return -9;
-	if (get_wait_data(cosa) != ' ') return -10;
+	if (put_wait_data(cosa, 'r') == -1)
+		return -1;
+	if ((get_wait_data(cosa)) != 'r')
+		return -2;
+	if ((get_wait_data(cosa)) != '=')
+		return -3;
+
+	if (puthexnumber(cosa, address) < 0)
+		return -4;
+	if (put_wait_data(cosa, ' ') == -1)
+		return -5;
+	if (get_wait_data(cosa) != ' ')
+		return -6;
+	if (get_wait_data(cosa) != '=')
+		return -7;
+
+	if (puthexnumber(cosa, address + length - 1) < 0)
+		return -8;
+	if (put_wait_data(cosa, ' ') == -1)
+		return -9;
+	if (get_wait_data(cosa) != ' ')
+		return -10;
 
 	while (length--) {
 		char c;
 		int i;
-		if ((i=get_wait_data(cosa)) == -1) {
+
+		i = get_wait_data(cosa);
+		if (i == -1) {
 			pr_info("0x%04x bytes remaining\n", length);
 			return -11;
 		}
-		c=i;
+		c = i;
 #if 1
 		if (put_user(c, microcode))
 			return -23; /* ??? */
@@ -1489,22 +1512,24 @@ static int readmem(struct cosa_data *cosa, char __user *microcode, int length, i
 		microcode++;
 	}
 
-	if (get_wait_data(cosa) != '\r') return -21;
-	if (get_wait_data(cosa) != '\n') return -22;
-	if (get_wait_data(cosa) != '.') return -23;
+	if (get_wait_data(cosa) != '\r')
+		return -21;
+	if (get_wait_data(cosa) != '\n')
+		return -22;
+	if (get_wait_data(cosa) != '.')
+		return -23;
 #if 0
 	printk(KERN_DEBUG "cosa%d: readmem completed.\n", cosa->num);
 #endif
 	return 0;
 }
 
-/*
- * This function resets the device and reads the initial prompt
+/* This function resets the device and reads the initial prompt
  * of the device's ROM monitor.
  */
 static int cosa_reset_and_read_id(struct cosa_data *cosa, char *idstring)
 {
-	int i=0, id=0, prev=0, curr=0;
+	int i = 0, id = 0, prev = 0, curr = 0;
 
 	/* Reset the card ... */
 	cosa_putstatus(cosa, 0);
@@ -1514,18 +1539,18 @@ static int cosa_reset_and_read_id(struct cosa_data *cosa, char *idstring)
 	/* Disable all IRQs from the card */
 	cosa_putstatus(cosa, 0);
 
-	/*
-	 * Try to read the ID string. The card then prints out the
+	/* Try to read the ID string. The card then prints out the
 	 * identification string ended by the "\n\x2e".
 	 *
 	 * The following loop is indexed through i (instead of id)
 	 * to avoid looping forever when for any reason
 	 * the port returns '\r', '\n' or '\x2e' permanently.
 	 */
-	for (i=0; i<COSA_MAX_ID_STRING-1; i++, prev=curr) {
-		if ((curr = get_wait_data(cosa)) == -1) {
+	for (i = 0; i < COSA_MAX_ID_STRING - 1; i++, prev = curr) {
+		curr = get_wait_data(cosa);
+		if (curr == -1)
 			return -1;
-		}
+
 		curr &= 0xff;
 		if (curr != '\r' && curr != '\n' && curr != 0x2e)
 			idstring[id++] = curr;
@@ -1537,11 +1562,9 @@ static int cosa_reset_and_read_id(struct cosa_data *cosa, char *idstring)
 	return id;
 }
 
-
 /* ---------- Auxiliary routines for COSA/SRP monitor ---------- */
 
-/*
- * This routine gets the data byte from the card waiting for the SR_RX_RDY
+/* This routine gets the data byte from the card waiting for the SR_RX_RDY
  * bit to be set in a loop. It should be used in the exceptional cases
  * only (for example when resetting the card or downloading the firmware.
  */
@@ -1553,10 +1576,11 @@ static int get_wait_data(struct cosa_data *cosa)
 		/* read data and return them */
 		if (cosa_getstatus(cosa) & SR_RX_RDY) {
 			short r;
+
 			r = cosa_getdata8(cosa);
 #if 0
 			pr_info("get_wait_data returning after %d retries\n",
-				999-retries);
+				999 - retries);
 #endif
 			return r;
 		}
@@ -1568,20 +1592,20 @@ static int get_wait_data(struct cosa_data *cosa)
 	return -1;
 }
 
-/*
- * This routine puts the data byte to the card waiting for the SR_TX_RDY
+/* This routine puts the data byte to the card waiting for the SR_TX_RDY
  * bit to be set in a loop. It should be used in the exceptional cases
  * only (for example when resetting the card or downloading the firmware).
  */
 static int put_wait_data(struct cosa_data *cosa, int data)
 {
 	int retries = 1000;
+
 	while (--retries) {
 		/* read data and return them */
 		if (cosa_getstatus(cosa) & SR_TX_RDY) {
 			cosa_putdata8(cosa, data);
 #if 0
-			pr_info("Putdata: %d retries\n", 999-retries);
+			pr_info("Putdata: %d retries\n", 999 - retries);
 #endif
 			return 0;
 		}
@@ -1594,9 +1618,8 @@ static int put_wait_data(struct cosa_data *cosa, int data)
 		cosa->num, cosa_getstatus(cosa));
 	return -1;
 }
-	
-/* 
- * The following routine puts the hexadecimal number into the SRP monitor
+
+/* The following routine puts the hexadecimal number into the SRP monitor
  * and verifies the proper echo of the sent bytes. Returns 0 on success,
  * negative number on failure (-1,-3,-5,-7) means that put_wait_data() failed,
  * (-2,-4,-6,-8) means that reading echo failed.
@@ -1608,26 +1631,24 @@ static int puthexnumber(struct cosa_data *cosa, int number)
 
 	/* Well, I should probably replace this by something faster. */
 	sprintf(temp, "%04X", number);
-	for (i=0; i<4; i++) {
+	for (i = 0; i < 4; i++) {
 		if (put_wait_data(cosa, temp[i]) == -1) {
 			pr_notice("cosa%d: puthexnumber failed to write byte %d\n",
 				  cosa->num, i);
-			return -1-2*i;
+			return -1 - 2 * i;
 		}
 		if (get_wait_data(cosa) != temp[i]) {
 			pr_notice("cosa%d: puthexhumber failed to read echo of byte %d\n",
 				  cosa->num, i);
-			return -2-2*i;
+			return -2 - 2 * i;
 		}
 	}
 	return 0;
 }
 
-
 /* ---------- Interrupt routines ---------- */
 
-/*
- * There are three types of interrupt:
+/* There are three types of interrupt:
  * At the beginning of transmit - this handled is in tx_interrupt(),
  * at the beginning of receive - it is in rx_interrupt() and
  * at the end of transmit/receive - it is the eot_interrupt() function.
@@ -1635,14 +1656,13 @@ static int puthexnumber(struct cosa_data *cosa, int number)
  * COSA status byte. I have moved the rx/tx/eot interrupt handling into
  * separate functions to make it more readable. These functions are inline,
  * so there should be no overhead of function call.
- * 
+ *
  * In the COSA bus-master mode, we need to tell the card the address of a
  * buffer. Unfortunately, COSA may be too slow for us, so we must busy-wait.
  * It's time to use the bottom half :-(
  */
 
-/*
- * Transmit interrupt routine - called when COSA is willing to obtain
+/* Transmit interrupt routine - called when COSA is willing to obtain
  * data from the OS. The most tricky part of the routine is selection
  * of channel we (OS) want to send packet for. For SRP we should probably
  * use the round-robin approach. The newer COSA firmwares have a simple
@@ -1667,7 +1687,8 @@ static inline void tx_interrupt(struct cosa_data *cosa, int status)
 	set_bit(TXBIT, &cosa->rxtx);
 	if (!test_bit(IRQBIT, &cosa->rxtx)) {
 		/* flow control, see the comment above */
-		int i=0;
+		int i = 0;
+
 		if (!cosa->txbitmap) {
 			pr_warn("%s: No channel wants data in TX IRQ. Expect DMA timeout.\n",
 				cosa->name);
@@ -1681,9 +1702,10 @@ static inline void tx_interrupt(struct cosa_data *cosa, int status)
 			i++;
 			if (cosa->txchan >= cosa->nchannels)
 				cosa->txchan = 0;
-			if (!(cosa->txbitmap & (1<<cosa->txchan)))
+			if (!(cosa->txbitmap & (1 << cosa->txchan)))
 				continue;
-			if (~status & (1 << (cosa->txchan+DRIVER_TXMAP_SHIFT)))
+			if (~status &
+			    (1 << (cosa->txchan + DRIVER_TXMAP_SHIFT)))
 				break;
 			/* in second pass, accept first ready-to-TX channel */
 			if (i > cosa->nchannels) {
@@ -1698,12 +1720,13 @@ static inline void tx_interrupt(struct cosa_data *cosa, int status)
 		}
 
 		cosa->txsize = cosa->chan[cosa->txchan].txsize;
-		if (cosa_dma_able(cosa->chan+cosa->txchan,
-			cosa->chan[cosa->txchan].txbuf, cosa->txsize)) {
+		if (cosa_dma_able(cosa->chan + cosa->txchan,
+				  cosa->chan[cosa->txchan].txbuf,
+				  cosa->txsize)) {
 			cosa->txbuf = cosa->chan[cosa->txchan].txbuf;
 		} else {
 			memcpy(cosa->bouncebuf, cosa->chan[cosa->txchan].txbuf,
-				cosa->txsize);
+			       cosa->txsize);
 			cosa->txbuf = cosa->bouncebuf;
 		}
 	}
@@ -1711,12 +1734,12 @@ static inline void tx_interrupt(struct cosa_data *cosa, int status)
 	if (is_8bit(cosa)) {
 		if (!test_bit(IRQBIT, &cosa->rxtx)) {
 			cosa_putstatus(cosa, SR_TX_INT_ENA);
-			cosa_putdata8(cosa, ((cosa->txchan << 5) & 0xe0)|
+			cosa_putdata8(cosa, ((cosa->txchan << 5) & 0xe0) |
 				((cosa->txsize >> 8) & 0x1f));
 #ifdef DEBUG_IO
 			debug_status_out(cosa, SR_TX_INT_ENA);
-			debug_data_out(cosa, ((cosa->txchan << 5) & 0xe0)|
-                                ((cosa->txsize >> 8) & 0x1f));
+			debug_data_out(cosa, ((cosa->txchan << 5) & 0xe0) |
+				       ((cosa->txsize >> 8) & 0x1f));
 			debug_data_in(cosa, cosa_getdata8(cosa));
 #else
 			cosa_getdata8(cosa);
@@ -1727,20 +1750,20 @@ static inline void tx_interrupt(struct cosa_data *cosa, int status)
 		} else {
 			clear_bit(IRQBIT, &cosa->rxtx);
 			cosa_putstatus(cosa, 0);
-			cosa_putdata8(cosa, cosa->txsize&0xff);
+			cosa_putdata8(cosa, cosa->txsize & 0xff);
 #ifdef DEBUG_IO
 			debug_status_out(cosa, 0);
-			debug_data_out(cosa, cosa->txsize&0xff);
+			debug_data_out(cosa, cosa->txsize & 0xff);
 #endif
 		}
 	} else {
 		cosa_putstatus(cosa, SR_TX_INT_ENA);
-		cosa_putdata16(cosa, ((cosa->txchan<<13) & 0xe000)
+		cosa_putdata16(cosa, ((cosa->txchan << 13) & 0xe000)
 			| (cosa->txsize & 0x1fff));
 #ifdef DEBUG_IO
 		debug_status_out(cosa, SR_TX_INT_ENA);
-		debug_data_out(cosa, ((cosa->txchan<<13) & 0xe000)
-                        | (cosa->txsize & 0x1fff));
+		debug_data_out(cosa, ((cosa->txchan << 13) & 0xe000) |
+			       (cosa->txsize & 0x1fff));
 		debug_data_in(cosa, cosa_getdata8(cosa));
 		debug_status_out(cosa, 0);
 #else
@@ -1751,25 +1774,28 @@ static inline void tx_interrupt(struct cosa_data *cosa, int status)
 
 	if (cosa->busmaster) {
 		unsigned long addr = virt_to_bus(cosa->txbuf);
-		int count=0;
+		int count = 0;
+
 		pr_info("busmaster IRQ\n");
-		while (!(cosa_getstatus(cosa)&SR_TX_RDY)) {
+		while (!(cosa_getstatus(cosa) & SR_TX_RDY)) {
 			count++;
 			udelay(10);
-			if (count > 1000) break;
+			if (count > 1000)
+				break;
 		}
 		pr_info("status %x\n", cosa_getstatus(cosa));
 		pr_info("ready after %d loops\n", count);
-		cosa_putdata16(cosa, (addr >> 16)&0xffff);
+		cosa_putdata16(cosa, (addr >> 16) & 0xffff);
 
 		count = 0;
-		while (!(cosa_getstatus(cosa)&SR_TX_RDY)) {
+		while (!(cosa_getstatus(cosa) & SR_TX_RDY)) {
 			count++;
-			if (count > 1000) break;
+			if (count > 1000)
+				break;
 			udelay(10);
 		}
 		pr_info("ready after %d loops\n", count);
-		cosa_putdata16(cosa, addr &0xffff);
+		cosa_putdata16(cosa, addr & 0xffff);
 		flags1 = claim_dma_lock();
 		set_dma_mode(cosa->dma, DMA_MODE_CASCADE);
 		enable_dma(cosa->dma);
@@ -1785,9 +1811,9 @@ static inline void tx_interrupt(struct cosa_data *cosa, int status)
 		enable_dma(cosa->dma);
 		release_dma_lock(flags1);
 	}
-	cosa_putstatus(cosa, SR_TX_DMA_ENA|SR_USR_INT_ENA);
+	cosa_putstatus(cosa, SR_TX_DMA_ENA | SR_USR_INT_ENA);
 #ifdef DEBUG_IO
-	debug_status_out(cosa, SR_TX_DMA_ENA|SR_USR_INT_ENA);
+	debug_status_out(cosa, SR_TX_DMA_ENA | SR_USR_INT_ENA);
 #endif
 	spin_unlock_irqrestore(&cosa->lock, flags);
 }
@@ -1806,7 +1832,7 @@ static inline void rx_interrupt(struct cosa_data *cosa, int status)
 		if (!test_bit(IRQBIT, &cosa->rxtx)) {
 			set_bit(IRQBIT, &cosa->rxtx);
 			put_driver_status_nolock(cosa);
-			cosa->rxsize = cosa_getdata8(cosa) <<8;
+			cosa->rxsize = cosa_getdata8(cosa) << 8;
 #ifdef DEBUG_IO
 			debug_data_in(cosa, cosa->rxsize >> 8);
 #endif
@@ -1859,20 +1885,20 @@ reject:		/* Reject the packet */
 	disable_dma(cosa->dma);
 	clear_dma_ff(cosa->dma);
 	set_dma_mode(cosa->dma, DMA_MODE_READ);
-	if (cosa_dma_able(cosa->rxchan, cosa->rxbuf, cosa->rxsize & 0x1fff)) {
+	if (cosa_dma_able(cosa->rxchan, cosa->rxbuf, cosa->rxsize & 0x1fff))
 		set_dma_addr(cosa->dma, virt_to_bus(cosa->rxbuf));
-	} else {
+	else
 		set_dma_addr(cosa->dma, virt_to_bus(cosa->bouncebuf));
-	}
-	set_dma_count(cosa->dma, (cosa->rxsize&0x1fff));
+
+	set_dma_count(cosa->dma, (cosa->rxsize & 0x1fff));
 	enable_dma(cosa->dma);
 	release_dma_lock(flags);
 	spin_lock_irqsave(&cosa->lock, flags);
-	cosa_putstatus(cosa, SR_RX_DMA_ENA|SR_USR_INT_ENA);
+	cosa_putstatus(cosa, SR_RX_DMA_ENA | SR_USR_INT_ENA);
 	if (!is_8bit(cosa) && (status & SR_TX_RDY))
 		cosa_putdata8(cosa, DRIVER_RX_READY);
 #ifdef DEBUG_IO
-	debug_status_out(cosa, SR_RX_DMA_ENA|SR_USR_INT_ENA);
+	debug_status_out(cosa, SR_RX_DMA_ENA | SR_USR_INT_ENA);
 	if (!is_8bit(cosa) && (status & SR_TX_RDY))
 		debug_data_cmd(cosa, DRIVER_RX_READY);
 #endif
@@ -1882,13 +1908,15 @@ reject:		/* Reject the packet */
 static inline void eot_interrupt(struct cosa_data *cosa, int status)
 {
 	unsigned long flags, flags1;
+
 	spin_lock_irqsave(&cosa->lock, flags);
 	flags1 = claim_dma_lock();
 	disable_dma(cosa->dma);
 	clear_dma_ff(cosa->dma);
 	release_dma_lock(flags1);
 	if (test_bit(TXBIT, &cosa->rxtx)) {
-		struct channel_data *chan = cosa->chan+cosa->txchan;
+		struct channel_data *chan = cosa->chan + cosa->txchan;
+
 		if (chan->tx_done)
 			if (chan->tx_done(chan, cosa->txsize))
 				clear_bit(chan->num, &cosa->txbitmap);
@@ -1896,9 +1924,10 @@ static inline void eot_interrupt(struct cosa_data *cosa, int status)
 #ifdef DEBUG_DATA
 	{
 		int i;
+
 		pr_info("cosa%dc%d: done rx(0x%x)",
 			cosa->num, cosa->rxchan->num, cosa->rxsize);
-		for (i=0; i<cosa->rxsize; i++)
+		for (i = 0; i < cosa->rxsize; i++)
 			pr_cont(" %02x", cosa->rxbuf[i]&0xff);
 		pr_cont("\n");
 	}
@@ -1914,8 +1943,7 @@ static inline void eot_interrupt(struct cosa_data *cosa, int status)
 	} else {
 		pr_notice("cosa%d: unexpected EOT interrupt\n", cosa->num);
 	}
-	/*
-	 * Clear the RXBIT, TXBIT and IRQBIT (the latest should be
+	/* Clear the RXBIT, TXBIT and IRQBIT (the latest should be
 	 * cleared anyway). We should do it as soon as possible
 	 * so that we can tell the COSA we are done and to give it a time
 	 * for recovery.
@@ -1968,10 +1996,8 @@ again:
 	return IRQ_HANDLED;
 }
 
-
 /* ---------- I/O debugging routines ---------- */
-/*
- * These routines can be used to monitor COSA/SRP I/O and to printk()
+/* These routines can be used to monitor COSA/SRP I/O and to printk()
  * the data being transferred on the data and status I/O port in a
  * readable way.
  */
@@ -1980,6 +2006,7 @@ again:
 static void debug_status_in(struct cosa_data *cosa, int status)
 {
 	char *s;
+
 	switch (status & SR_CMD_FROM_SRP_MASK) {
 	case SR_UP_REQUEST:
 		s = "RX_REQ";
diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index 5de71e44fc5a..b3466e084e84 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *      FarSync WAN driver for Linux (2.6.x kernel version)
+/*      FarSync WAN driver for Linux (2.6.x kernel version)
  *
  *      Actually sync driver for X.21, V.35 and V.24 on FarSync T-series cards
  *
@@ -30,8 +29,7 @@
 
 #include "farsync.h"
 
-/*
- *      Module info
+/*      Module info
  */
 MODULE_AUTHOR("R.J.Dunlop <bob.dunlop@farsite.co.uk>");
 MODULE_DESCRIPTION("FarSync T-Series WAN driver. FarSite Communications Ltd.");
@@ -49,20 +47,23 @@ MODULE_LICENSE("GPL");
 /*      Default parameters for the link
  */
 #define FST_TX_QUEUE_LEN        100	/* At 8Mbps a longer queue length is
-					 * useful */
+					 * useful
+					 */
 #define FST_TXQ_DEPTH           16	/* This one is for the buffering
 					 * of frames on the way down to the card
 					 * so that we can keep the card busy
 					 * and maximise throughput
 					 */
 #define FST_HIGH_WATER_MARK     12	/* Point at which we flow control
-					 * network layer */
+					 * network layer
+					 */
 #define FST_LOW_WATER_MARK      8	/* Point at which we remove flow
-					 * control from network layer */
+					 * control from network layer
+					 */
 #define FST_MAX_MTU             8000	/* Huge but possible */
 #define FST_DEF_MTU             1500	/* Common sane value */
 
-#define FST_TX_TIMEOUT          (2*HZ)
+#define FST_TX_TIMEOUT          (2 * HZ)
 
 #ifdef ARPHRD_RAWHDLC
 #define ARPHRD_MYTYPE   ARPHRD_RAWHDLC	/* Raw frames */
@@ -70,13 +71,12 @@ MODULE_LICENSE("GPL");
 #define ARPHRD_MYTYPE   ARPHRD_HDLC	/* Cisco-HDLC (keepalives etc) */
 #endif
 
-/*
- * Modules parameters and associated variables
+/* Modules parameters and associated variables
  */
 static int fst_txq_low = FST_LOW_WATER_MARK;
 static int fst_txq_high = FST_HIGH_WATER_MARK;
 static int fst_max_reads = 7;
-static int fst_excluded_cards = 0;
+static int fst_excluded_cards;
 static int fst_excluded_list[FST_MAX_CARDS];
 
 module_param(fst_txq_low, int, 0);
@@ -105,9 +105,11 @@ module_param_array(fst_excluded_list, int, NULL, 0);
 #define FST_MEMSIZE 0x100000	/* Size of card memory (1Mb) */
 
 #define SMC_BASE 0x00002000L	/* Base offset of the shared memory window main
-				 * configuration structure */
+				 * configuration structure
+				 */
 #define BFM_BASE 0x00010000L	/* Base offset of the shared memory window DMA
-				 * buffers */
+				 * buffers
+				 */
 
 #define LEN_TX_BUFFER 8192	/* Size of packet buffers */
 #define LEN_RX_BUFFER 8192
@@ -377,8 +379,7 @@ struct fst_shared {
 #define INTCSR_9054     0x68	/* Interrupt control/status register */
 
 /* 9054 DMA Registers */
-/*
- * Note that we will be using DMA Channel 0 for copying rx data
+/* Note that we will be using DMA Channel 0 for copying rx data
  * and Channel 1 for copying tx data
  */
 #define DMAMODE0        0x80
@@ -421,7 +422,7 @@ struct buf_window {
 /*      Per port (line or channel) information
  */
 struct fst_port_info {
-        struct net_device *dev; /* Device struct - must be first */
+	struct net_device *dev; /* Device struct - must be first */
 	struct fst_card_info *card;	/* Card we're associated with */
 	int index;		/* Port index on the card */
 	int hwif;		/* Line hardware (lineInterface copy) */
@@ -431,8 +432,7 @@ struct fst_port_info {
 	int txpos;		/* Next Tx buffer to use */
 	int txipos;		/* Next Tx buffer to check for free */
 	int start;		/* Indication of start/stop to network */
-	/*
-	 * A sixteen entry transmit queue
+	/* A sixteen entry transmit queue
 	 */
 	int txqs;		/* index to get next buffer to tx */
 	int txqe;		/* index to queue next packet */
@@ -479,9 +479,7 @@ struct fst_card_info {
 #define dev_to_port(D)  (dev_to_hdlc(D)->priv)
 #define port_to_dev(P)  ((P)->dev)
 
-
-/*
- *      Shared memory window access macros
+/*      Shared memory window access macros
  *
  *      We have a nice memory based structure above, which could be directly
  *      mapped on i386 but might not work on other architectures unless we use
@@ -491,16 +489,15 @@ struct fst_card_info {
  */
 #define WIN_OFFSET(X)   ((long)&(((struct fst_shared *)SMC_BASE)->X))
 
-#define FST_RDB(C,E)    readb ((C)->mem + WIN_OFFSET(E))
-#define FST_RDW(C,E)    readw ((C)->mem + WIN_OFFSET(E))
-#define FST_RDL(C,E)    readl ((C)->mem + WIN_OFFSET(E))
+#define FST_RDB(C, E)    (readb((C)->mem + WIN_OFFSET(E)))
+#define FST_RDW(C, E)    (readw((C)->mem + WIN_OFFSET(E)))
+#define FST_RDL(C, E)    (readl((C)->mem + WIN_OFFSET(E)))
 
-#define FST_WRB(C,E,B)  writeb ((B), (C)->mem + WIN_OFFSET(E))
-#define FST_WRW(C,E,W)  writew ((W), (C)->mem + WIN_OFFSET(E))
-#define FST_WRL(C,E,L)  writel ((L), (C)->mem + WIN_OFFSET(E))
+#define FST_WRB(C, E, B)  (writeb((B), (C)->mem + WIN_OFFSET(E)))
+#define FST_WRW(C, E, W)  (writew((W), (C)->mem + WIN_OFFSET(E)))
+#define FST_WRL(C, E, L)  (writel((L), (C)->mem + WIN_OFFSET(E)))
 
-/*
- *      Debug support
+/*      Debug support
  */
 #if FST_DEBUG
 
@@ -524,43 +521,41 @@ do {								\
 } while (0)
 #endif
 
-/*
- *      PCI ID lookup table
+/*      PCI ID lookup table
  */
 static const struct pci_device_id fst_pci_dev_id[] = {
-	{PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T2P, PCI_ANY_ID, 
+	{PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T2P, PCI_ANY_ID,
 	 PCI_ANY_ID, 0, 0, FST_TYPE_T2P},
 
-	{PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T4P, PCI_ANY_ID, 
+	{PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T4P, PCI_ANY_ID,
 	 PCI_ANY_ID, 0, 0, FST_TYPE_T4P},
 
-	{PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T1U, PCI_ANY_ID, 
+	{PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T1U, PCI_ANY_ID,
 	 PCI_ANY_ID, 0, 0, FST_TYPE_T1U},
 
-	{PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T2U, PCI_ANY_ID, 
+	{PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T2U, PCI_ANY_ID,
 	 PCI_ANY_ID, 0, 0, FST_TYPE_T2U},
 
-	{PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T4U, PCI_ANY_ID, 
+	{PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T4U, PCI_ANY_ID,
 	 PCI_ANY_ID, 0, 0, FST_TYPE_T4U},
 
-	{PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_TE1, PCI_ANY_ID, 
+	{PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_TE1, PCI_ANY_ID,
 	 PCI_ANY_ID, 0, 0, FST_TYPE_TE1},
 
-	{PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_TE1C, PCI_ANY_ID, 
+	{PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_TE1C, PCI_ANY_ID,
 	 PCI_ANY_ID, 0, 0, FST_TYPE_TE1},
 	{0,}			/* End */
 };
 
 MODULE_DEVICE_TABLE(pci, fst_pci_dev_id);
 
-/*
- *      Device Driver Work Queues
+/*      Device Driver Work Queues
  *
- *      So that we don't spend too much time processing events in the 
- *      Interrupt Service routine, we will declare a work queue per Card 
+ *      So that we don't spend too much time processing events in the
+ *      Interrupt Service routine, we will declare a work queue per Card
  *      and make the ISR schedule a task in the queue for later execution.
  *      In the 2.4 Kernel we used to use the immediate queue for BH's
- *      Now that they are gone, tasklets seem to be much better than work 
+ *      Now that they are gone, tasklets seem to be much better than work
  *      queues.
  */
 
@@ -578,18 +573,16 @@ static u64 fst_work_txq;
 static u64 fst_work_intq;
 
 static void
-fst_q_work_item(u64 * queue, int card_index)
+fst_q_work_item(u64 *queue, int card_index)
 {
 	unsigned long flags;
 	u64 mask;
 
-	/*
-	 * Grab the queue exclusively
+	/* Grab the queue exclusively
 	 */
 	spin_lock_irqsave(&fst_work_q_lock, flags);
 
-	/*
-	 * Making an entry in the queue is simply a matter of setting
+	/* Making an entry in the queue is simply a matter of setting
 	 * a bit for the card indicating that there is work to do in the
 	 * bottom half for the card.  Note the limitation of 64 cards.
 	 * That ought to be enough
@@ -606,8 +599,7 @@ fst_process_tx_work_q(struct tasklet_struct *unused)
 	u64 work_txq;
 	int i;
 
-	/*
-	 * Grab the queue exclusively
+	/* Grab the queue exclusively
 	 */
 	dbg(DBG_TX, "fst_process_tx_work_q\n");
 	spin_lock_irqsave(&fst_work_q_lock, flags);
@@ -615,12 +607,11 @@ fst_process_tx_work_q(struct tasklet_struct *unused)
 	fst_work_txq = 0;
 	spin_unlock_irqrestore(&fst_work_q_lock, flags);
 
-	/*
-	 * Call the bottom half for each card with work waiting
+	/* Call the bottom half for each card with work waiting
 	 */
 	for (i = 0; i < FST_MAX_CARDS; i++) {
 		if (work_txq & 0x01) {
-			if (fst_card_array[i] != NULL) {
+			if (fst_card_array[i]) {
 				dbg(DBG_TX, "Calling tx bh for card %d\n", i);
 				do_bottom_half_tx(fst_card_array[i]);
 			}
@@ -636,8 +627,7 @@ fst_process_int_work_q(struct tasklet_struct *unused)
 	u64 work_intq;
 	int i;
 
-	/*
-	 * Grab the queue exclusively
+	/* Grab the queue exclusively
 	 */
 	dbg(DBG_INTR, "fst_process_int_work_q\n");
 	spin_lock_irqsave(&fst_work_q_lock, flags);
@@ -645,12 +635,11 @@ fst_process_int_work_q(struct tasklet_struct *unused)
 	fst_work_intq = 0;
 	spin_unlock_irqrestore(&fst_work_q_lock, flags);
 
-	/*
-	 * Call the bottom half for each card with work waiting
+	/* Call the bottom half for each card with work waiting
 	 */
 	for (i = 0; i < FST_MAX_CARDS; i++) {
 		if (work_intq & 0x01) {
-			if (fst_card_array[i] != NULL) {
+			if (fst_card_array[i]) {
 				dbg(DBG_INTR,
 				    "Calling rx & tx bh for card %d\n", i);
 				do_bottom_half_rx(fst_card_array[i]);
@@ -683,19 +672,16 @@ fst_cpureset(struct fst_card_info *card)
 			dbg(DBG_ASS,
 			    "Error in reading interrupt line register\n");
 		}
-		/*
-		 * Assert PLX software reset and Am186 hardware reset
+		/* Assert PLX software reset and Am186 hardware reset
 		 * and then deassert the PLX software reset but 186 still in reset
 		 */
 		outw(0x440f, card->pci_conf + CNTRL_9054 + 2);
 		outw(0x040f, card->pci_conf + CNTRL_9054 + 2);
-		/*
-		 * We are delaying here to allow the 9054 to reset itself
+		/* We are delaying here to allow the 9054 to reset itself
 		 */
 		usleep_range(10, 20);
 		outw(0x240f, card->pci_conf + CNTRL_9054 + 2);
-		/*
-		 * We are delaying here to allow the 9054 to reload its eeprom
+		/* We are delaying here to allow the 9054 to reload its eeprom
 		 */
 		usleep_range(10, 20);
 		outw(0x040f, card->pci_conf + CNTRL_9054 + 2);
@@ -720,19 +706,17 @@ static inline void
 fst_cpurelease(struct fst_card_info *card)
 {
 	if (card->family == FST_FAMILY_TXU) {
-		/*
-		 * Force posted writes to complete
+		/* Force posted writes to complete
 		 */
-		(void) readb(card->mem);
+		(void)readb(card->mem);
 
-		/*
-		 * Release LRESET DO = 1
+		/* Release LRESET DO = 1
 		 * Then release Local Hold, DO = 1
 		 */
 		outw(0x040e, card->pci_conf + CNTRL_9054 + 2);
 		outw(0x040f, card->pci_conf + CNTRL_9054 + 2);
 	} else {
-		(void) readb(card->ctlmem);
+		(void)readb(card->ctlmem);
 	}
 }
 
@@ -742,7 +726,7 @@ static inline void
 fst_clear_intr(struct fst_card_info *card)
 {
 	if (card->family == FST_FAMILY_TXU) {
-		(void) readb(card->ctlmem);
+		(void)readb(card->ctlmem);
 	} else {
 		/* Poke the appropriate PLX chip register (same as enabling interrupts)
 		 */
@@ -755,11 +739,10 @@ fst_clear_intr(struct fst_card_info *card)
 static inline void
 fst_enable_intr(struct fst_card_info *card)
 {
-	if (card->family == FST_FAMILY_TXU) {
+	if (card->family == FST_FAMILY_TXU)
 		outl(0x0f0c0900, card->pci_conf + INTCSR_9054);
-	} else {
+	else
 		outw(0x0543, card->pci_conf + INTCSR_9052);
-	}
 }
 
 /*      Disable card interrupts
@@ -767,11 +750,10 @@ fst_enable_intr(struct fst_card_info *card)
 static inline void
 fst_disable_intr(struct fst_card_info *card)
 {
-	if (card->family == FST_FAMILY_TXU) {
+	if (card->family == FST_FAMILY_TXU)
 		outl(0x00000000, card->pci_conf + INTCSR_9054);
-	} else {
+	else
 		outw(0x0000, card->pci_conf + INTCSR_9052);
-	}
 }
 
 /*      Process the result of trying to pass a received frame up the stack
@@ -782,8 +764,7 @@ fst_process_rx_status(int rx_status, char *name)
 	switch (rx_status) {
 	case NET_RX_SUCCESS:
 		{
-			/*
-			 * Nothing to do here
+			/* Nothing to do here
 			 */
 			break;
 		}
@@ -800,11 +781,10 @@ fst_process_rx_status(int rx_status, char *name)
 static inline void
 fst_init_dma(struct fst_card_info *card)
 {
-	/*
-	 * This is only required for the PLX 9054
+	/* This is only required for the PLX 9054
 	 */
 	if (card->family == FST_FAMILY_TXU) {
-	        pci_set_master(card->device);
+		pci_set_master(card->device);
 		outl(0x00020441, card->pci_conf + DMAMODE0);
 		outl(0x00020441, card->pci_conf + DMAMODE1);
 		outl(0x0, card->pci_conf + DMATHR);
@@ -819,8 +799,7 @@ fst_tx_dma_complete(struct fst_card_info *card, struct fst_port_info *port,
 {
 	struct net_device *dev = port_to_dev(port);
 
-	/*
-	 * Everything is now set, just tell the card to go
+	/* Everything is now set, just tell the card to go
 	 */
 	dbg(DBG_TX, "fst_tx_dma_complete\n");
 	FST_WRB(card, txDescrRing[port->index][txpos].bits,
@@ -830,8 +809,7 @@ fst_tx_dma_complete(struct fst_card_info *card, struct fst_port_info *port,
 	netif_trans_update(dev);
 }
 
-/*
- * Mark it for our own raw sockets interface
+/* Mark it for our own raw sockets interface
  */
 static __be16 farsync_type_trans(struct sk_buff *skb, struct net_device *dev)
 {
@@ -874,55 +852,47 @@ fst_rx_dma_complete(struct fst_card_info *card, struct fst_port_info *port,
 		dev->stats.rx_dropped++;
 }
 
-/*
- *      Receive a frame through the DMA
+/*      Receive a frame through the DMA
  */
 static inline void
 fst_rx_dma(struct fst_card_info *card, dma_addr_t dma, u32 mem, int len)
 {
-	/*
-	 * This routine will setup the DMA and start it
+	/* This routine will setup the DMA and start it
 	 */
 
 	dbg(DBG_RX, "In fst_rx_dma %x %x %d\n", (u32)dma, mem, len);
-	if (card->dmarx_in_progress) {
+	if (card->dmarx_in_progress)
 		dbg(DBG_ASS, "In fst_rx_dma while dma in progress\n");
-	}
 
 	outl(dma, card->pci_conf + DMAPADR0);	/* Copy to here */
 	outl(mem, card->pci_conf + DMALADR0);	/* from here */
 	outl(len, card->pci_conf + DMASIZ0);	/* for this length */
 	outl(0x00000000c, card->pci_conf + DMADPR0);	/* In this direction */
 
-	/*
-	 * We use the dmarx_in_progress flag to flag the channel as busy
+	/* We use the dmarx_in_progress flag to flag the channel as busy
 	 */
 	card->dmarx_in_progress = 1;
 	outb(0x03, card->pci_conf + DMACSR0);	/* Start the transfer */
 }
 
-/*
- *      Send a frame through the DMA
+/*      Send a frame through the DMA
  */
 static inline void
 fst_tx_dma(struct fst_card_info *card, dma_addr_t dma, u32 mem, int len)
 {
-	/*
-	 * This routine will setup the DMA and start it.
+	/* This routine will setup the DMA and start it.
 	 */
 
 	dbg(DBG_TX, "In fst_tx_dma %x %x %d\n", (u32)dma, mem, len);
-	if (card->dmatx_in_progress) {
+	if (card->dmatx_in_progress)
 		dbg(DBG_ASS, "In fst_tx_dma while dma in progress\n");
-	}
 
 	outl(dma, card->pci_conf + DMAPADR1);	/* Copy from here */
 	outl(mem, card->pci_conf + DMALADR1);	/* to here */
 	outl(len, card->pci_conf + DMASIZ1);	/* for this length */
 	outl(0x000000004, card->pci_conf + DMADPR1);	/* In this direction */
 
-	/*
-	 * We use the dmatx_in_progress to flag the channel as busy
+	/* We use the dmatx_in_progress to flag the channel as busy
 	 */
 	card->dmatx_in_progress = 1;
 	outb(0x03, card->pci_conf + DMACSR1);	/* Start the transfer */
@@ -958,12 +928,11 @@ fst_issue_cmd(struct fst_port_info *port, unsigned short cmd)
 
 		mbval = FST_RDW(card, portMailbox[port->index][0]);
 	}
-	if (safety > 0) {
+	if (safety > 0)
 		dbg(DBG_CMD, "Mailbox clear after %d jiffies\n", safety);
-	}
-	if (mbval == NAK) {
+
+	if (mbval == NAK)
 		dbg(DBG_CMD, "issue_cmd: previous command was NAK'd\n");
-	}
 
 	FST_WRW(card, portMailbox[port->index][0], cmd);
 
@@ -998,8 +967,7 @@ fst_op_lower(struct fst_port_info *port, unsigned int outputs)
 		fst_issue_cmd(port, SETV24O);
 }
 
-/*
- *      Setup port Rx buffers
+/*      Setup port Rx buffers
  */
 static void
 fst_rx_config(struct fst_port_info *port)
@@ -1016,8 +984,8 @@ fst_rx_config(struct fst_port_info *port)
 	for (i = 0; i < NUM_RX_BUFFER; i++) {
 		offset = BUF_OFFSET(rxBuffer[pi][i][0]);
 
-		FST_WRW(card, rxDescrRing[pi][i].ladr, (u16) offset);
-		FST_WRB(card, rxDescrRing[pi][i].hadr, (u8) (offset >> 16));
+		FST_WRW(card, rxDescrRing[pi][i].ladr, (u16)offset);
+		FST_WRB(card, rxDescrRing[pi][i].hadr, (u8)(offset >> 16));
 		FST_WRW(card, rxDescrRing[pi][i].bcnt, cnv_bcnt(LEN_RX_BUFFER));
 		FST_WRW(card, rxDescrRing[pi][i].mcnt, LEN_RX_BUFFER);
 		FST_WRB(card, rxDescrRing[pi][i].bits, DMA_OWN);
@@ -1026,8 +994,7 @@ fst_rx_config(struct fst_port_info *port)
 	spin_unlock_irqrestore(&card->card_lock, flags);
 }
 
-/*
- *      Setup port Tx buffers
+/*      Setup port Tx buffers
  */
 static void
 fst_tx_config(struct fst_port_info *port)
@@ -1044,8 +1011,8 @@ fst_tx_config(struct fst_port_info *port)
 	for (i = 0; i < NUM_TX_BUFFER; i++) {
 		offset = BUF_OFFSET(txBuffer[pi][i][0]);
 
-		FST_WRW(card, txDescrRing[pi][i].ladr, (u16) offset);
-		FST_WRB(card, txDescrRing[pi][i].hadr, (u8) (offset >> 16));
+		FST_WRW(card, txDescrRing[pi][i].ladr, (u16)offset);
+		FST_WRB(card, txDescrRing[pi][i].hadr, (u8)(offset >> 16));
 		FST_WRW(card, txDescrRing[pi][i].bcnt, 0);
 		FST_WRB(card, txDescrRing[pi][i].bits, 0);
 	}
@@ -1069,16 +1036,14 @@ fst_intr_te1_alarm(struct fst_card_info *card, struct fst_port_info *port)
 	ais = FST_RDB(card, suStatus.alarmIndicationSignal);
 
 	if (los) {
-		/*
-		 * Lost the link
+		/* Lost the link
 		 */
 		if (netif_carrier_ok(port_to_dev(port))) {
 			dbg(DBG_INTR, "Net carrier off\n");
 			netif_carrier_off(port_to_dev(port));
 		}
 	} else {
-		/*
-		 * Link available
+		/* Link available
 		 */
 		if (!netif_carrier_ok(port_to_dev(port))) {
 			dbg(DBG_INTR, "Net carrier on\n");
@@ -1110,7 +1075,7 @@ fst_intr_ctlchg(struct fst_card_info *card, struct fst_port_info *port)
 
 	signals = FST_RDL(card, v24DebouncedSts[port->index]);
 
-	if (signals & (((port->hwif == X21) || (port->hwif == X21D))
+	if (signals & ((port->hwif == X21 || port->hwif == X21D)
 		       ? IPSTS_INDICATE : IPSTS_DCD)) {
 		if (!netif_carrier_ok(port_to_dev(port))) {
 			dbg(DBG_INTR, "DCD active\n");
@@ -1132,8 +1097,7 @@ fst_log_rx_error(struct fst_card_info *card, struct fst_port_info *port,
 {
 	struct net_device *dev = port_to_dev(port);
 
-	/*
-	 * Increment the appropriate error counter
+	/* Increment the appropriate error counter
 	 */
 	dev->stats.rx_errors++;
 	if (dmabits & RX_OFLO) {
@@ -1168,15 +1132,14 @@ fst_recover_rx_error(struct fst_card_info *card, struct fst_port_info *port,
 	int pi;
 
 	pi = port->index;
-	/* 
-	 * Discard buffer descriptors until we see the start of the
+	/* Discard buffer descriptors until we see the start of the
 	 * next frame.  Note that for long frames this could be in
-	 * a subsequent interrupt. 
+	 * a subsequent interrupt.
 	 */
 	i = 0;
 	while ((dmabits & (DMA_OWN | RX_STP)) == 0) {
 		FST_WRB(card, rxDescrRing[pi][rxp].bits, DMA_OWN);
-		rxp = (rxp+1) % NUM_RX_BUFFER;
+		rxp = (rxp + 1) % NUM_RX_BUFFER;
 		if (++i > NUM_RX_BUFFER) {
 			dbg(DBG_ASS, "intr_rx: Discarding more bufs"
 			    " than we have\n");
@@ -1190,11 +1153,9 @@ fst_recover_rx_error(struct fst_card_info *card, struct fst_port_info *port,
 	/* Discard the terminal buffer */
 	if (!(dmabits & DMA_OWN)) {
 		FST_WRB(card, rxDescrRing[pi][rxp].bits, DMA_OWN);
-		rxp = (rxp+1) % NUM_RX_BUFFER;
+		rxp = (rxp + 1) % NUM_RX_BUFFER;
 	}
 	port->rxpos = rxp;
-	return;
-
 }
 
 /*      Rx complete interrupt
@@ -1219,17 +1180,15 @@ fst_intr_rx(struct fst_card_info *card, struct fst_port_info *port)
 		    pi, rxp);
 		return;
 	}
-	if (card->dmarx_in_progress) {
+	if (card->dmarx_in_progress)
 		return;
-	}
 
 	/* Get buffer length */
 	len = FST_RDW(card, rxDescrRing[pi][rxp].mcnt);
 	/* Discard the CRC */
 	len -= 2;
 	if (len == 0) {
-		/*
-		 * This seems to happen on the TE1 interface sometimes
+		/* This seems to happen on the TE1 interface sometimes
 		 * so throw the frame away and log the event.
 		 */
 		pr_err("Frame received with 0 length. Card %d Port %d\n",
@@ -1237,7 +1196,7 @@ fst_intr_rx(struct fst_card_info *card, struct fst_port_info *port)
 		/* Return descriptor to card */
 		FST_WRB(card, rxDescrRing[pi][rxp].bits, DMA_OWN);
 
-		rxp = (rxp+1) % NUM_RX_BUFFER;
+		rxp = (rxp + 1) % NUM_RX_BUFFER;
 		port->rxpos = rxp;
 		return;
 	}
@@ -1254,7 +1213,8 @@ fst_intr_rx(struct fst_card_info *card, struct fst_port_info *port)
 	}
 
 	/* Allocate SKB */
-	if ((skb = dev_alloc_skb(len)) == NULL) {
+	skb = dev_alloc_skb(len);
+	if (!skb) {
 		dbg(DBG_RX, "intr_rx: can't allocate buffer\n");
 
 		dev->stats.rx_dropped++;
@@ -1262,18 +1222,17 @@ fst_intr_rx(struct fst_card_info *card, struct fst_port_info *port)
 		/* Return descriptor to card */
 		FST_WRB(card, rxDescrRing[pi][rxp].bits, DMA_OWN);
 
-		rxp = (rxp+1) % NUM_RX_BUFFER;
+		rxp = (rxp + 1) % NUM_RX_BUFFER;
 		port->rxpos = rxp;
 		return;
 	}
 
-	/*
-	 * We know the length we need to receive, len.
+	/* We know the length we need to receive, len.
 	 * It's not worth using the DMA for reads of less than
 	 * FST_MIN_DMA_LEN
 	 */
 
-	if ((len < FST_MIN_DMA_LEN) || (card->family == FST_FAMILY_TXP)) {
+	if (len < FST_MIN_DMA_LEN || card->family == FST_FAMILY_TXP) {
 		memcpy_fromio(skb_put(skb, len),
 			      card->mem + BUF_OFFSET(rxBuffer[pi][rxp][0]),
 			      len);
@@ -1307,12 +1266,11 @@ fst_intr_rx(struct fst_card_info *card, struct fst_port_info *port)
 		dbg(DBG_ASS, "About to increment rxpos by more than 1\n");
 		dbg(DBG_ASS, "rxp = %d rxpos = %d\n", rxp, port->rxpos);
 	}
-	rxp = (rxp+1) % NUM_RX_BUFFER;
+	rxp = (rxp + 1) % NUM_RX_BUFFER;
 	port->rxpos = rxp;
 }
 
-/*
- *      The bottom halfs to the ISR
+/*      The bottom half to the ISR
  *
  */
 
@@ -1326,8 +1284,7 @@ do_bottom_half_tx(struct fst_card_info *card)
 	unsigned long flags;
 	struct net_device *dev;
 
-	/*
-	 *  Find a free buffer for the transmit
+	/*  Find a free buffer for the transmit
 	 *  Step through each port on this card
 	 */
 
@@ -1340,39 +1297,36 @@ do_bottom_half_tx(struct fst_card_info *card)
 		while (!(FST_RDB(card, txDescrRing[pi][port->txpos].bits) &
 			 DMA_OWN) &&
 		       !(card->dmatx_in_progress)) {
-			/*
-			 * There doesn't seem to be a txdone event per-se
+			/* There doesn't seem to be a txdone event per-se
 			 * We seem to have to deduce it, by checking the DMA_OWN
 			 * bit on the next buffer we think we can use
 			 */
 			spin_lock_irqsave(&card->card_lock, flags);
-			if ((txq_length = port->txqe - port->txqs) < 0) {
-				/*
-				 * This is the case where one has wrapped and the
+			txq_length = port->txqe - port->txqs;
+			if (txq_length < 0) {
+				/* This is the case where one has wrapped and the
 				 * maths gives us a negative number
 				 */
 				txq_length = txq_length + FST_TXQ_DEPTH;
 			}
 			spin_unlock_irqrestore(&card->card_lock, flags);
 			if (txq_length > 0) {
-				/*
-				 * There is something to send
+				/* There is something to send
 				 */
 				spin_lock_irqsave(&card->card_lock, flags);
 				skb = port->txq[port->txqs];
 				port->txqs++;
-				if (port->txqs == FST_TXQ_DEPTH) {
+				if (port->txqs == FST_TXQ_DEPTH)
 					port->txqs = 0;
-				}
+
 				spin_unlock_irqrestore(&card->card_lock, flags);
-				/*
-				 * copy the data and set the required indicators on the
+				/* copy the data and set the required indicators on the
 				 * card.
 				 */
 				FST_WRW(card, txDescrRing[pi][port->txpos].bcnt,
 					cnv_bcnt(skb->len));
-				if ((skb->len < FST_MIN_DMA_LEN) ||
-				    (card->family == FST_FAMILY_TXP)) {
+				if (skb->len < FST_MIN_DMA_LEN ||
+				    card->family == FST_FAMILY_TXP) {
 					/* Enqueue the packet with normal io */
 					memcpy_toio(card->mem +
 						    BUF_OFFSET(txBuffer[pi]
@@ -1401,8 +1355,7 @@ do_bottom_half_tx(struct fst_card_info *card)
 				}
 				if (++port->txpos >= NUM_TX_BUFFER)
 					port->txpos = 0;
-				/*
-				 * If we have flow control on, can we now release it?
+				/* If we have flow control on, can we now release it?
 				 */
 				if (port->start) {
 					if (txq_length < fst_txq_low) {
@@ -1413,8 +1366,7 @@ do_bottom_half_tx(struct fst_card_info *card)
 				}
 				dev_kfree_skb(skb);
 			} else {
-				/*
-				 * Nothing to send so break out of the while loop
+				/* Nothing to send so break out of the while loop
 				 */
 				break;
 			}
@@ -1438,8 +1390,7 @@ do_bottom_half_rx(struct fst_card_info *card)
 		while (!(FST_RDB(card, rxDescrRing[pi][port->rxpos].bits)
 			 & DMA_OWN) && !(card->dmarx_in_progress)) {
 			if (rx_count > fst_max_reads) {
-				/*
-				 * Don't spend forever in receive processing
+				/* Don't spend forever in receive processing
 				 * Schedule another event
 				 */
 				fst_q_work_item(&fst_work_intq, card->card_no);
@@ -1452,8 +1403,7 @@ do_bottom_half_rx(struct fst_card_info *card)
 	}
 }
 
-/*
- *      The interrupt service routine
+/*      The interrupt service routine
  *      Dev_id is our fst_card_info pointer
  */
 static irqreturn_t
@@ -1468,8 +1418,7 @@ fst_intr(int dummy, void *dev_id)
 	unsigned int do_card_interrupt;
 	unsigned int int_retry_count;
 
-	/*
-	 * Check to see if the interrupt was for this card
+	/* Check to see if the interrupt was for this card
 	 * return if not
 	 * Note that the call to clear the interrupt is important
 	 */
@@ -1478,10 +1427,9 @@ fst_intr(int dummy, void *dev_id)
 		pr_err("Interrupt received for card %d in a non running state (%d)\n",
 		       card->card_no, card->state);
 
-		/* 
-		 * It is possible to really be running, i.e. we have re-loaded
+		/* It is possible to really be running, i.e. we have re-loaded
 		 * a running card
-		 * Clear and reprime the interrupt source 
+		 * Clear and reprime the interrupt source
 		 */
 		fst_clear_intr(card);
 		return IRQ_HANDLED;
@@ -1490,8 +1438,7 @@ fst_intr(int dummy, void *dev_id)
 	/* Clear and reprime the interrupt source */
 	fst_clear_intr(card);
 
-	/*
-	 * Is the interrupt for this card (handshake == 1)
+	/* Is the interrupt for this card (handshake == 1)
 	 */
 	do_card_interrupt = 0;
 	if (FST_RDB(card, interruptHandshake) == 1) {
@@ -1500,13 +1447,11 @@ fst_intr(int dummy, void *dev_id)
 		FST_WRB(card, interruptHandshake, 0xEE);
 	}
 	if (card->family == FST_FAMILY_TXU) {
-		/*
-		 * Is it a DMA Interrupt
+		/* Is it a DMA Interrupt
 		 */
 		dma_intcsr = inl(card->pci_conf + INTCSR_9054);
 		if (dma_intcsr & 0x00200000) {
-			/*
-			 * DMA Channel 0 (Rx transfer complete)
+			/* DMA Channel 0 (Rx transfer complete)
 			 */
 			dbg(DBG_RX, "DMA Rx xfer complete\n");
 			outb(0x8, card->pci_conf + DMACSR0);
@@ -1517,8 +1462,7 @@ fst_intr(int dummy, void *dev_id)
 			do_card_interrupt += FST_RX_DMA_INT;
 		}
 		if (dma_intcsr & 0x00400000) {
-			/*
-			 * DMA Channel 1 (Tx transfer complete)
+			/* DMA Channel 1 (Tx transfer complete)
 			 */
 			dbg(DBG_TX, "DMA Tx xfer complete\n");
 			outb(0x8, card->pci_conf + DMACSR1);
@@ -1529,8 +1473,7 @@ fst_intr(int dummy, void *dev_id)
 		}
 	}
 
-	/*
-	 * Have we been missing Interrupts
+	/* Have we been missing Interrupts
 	 */
 	int_retry_count = FST_RDL(card, interruptRetryCount);
 	if (int_retry_count) {
@@ -1539,9 +1482,8 @@ fst_intr(int dummy, void *dev_id)
 		FST_WRL(card, interruptRetryCount, 0);
 	}
 
-	if (!do_card_interrupt) {
+	if (!do_card_interrupt)
 		return IRQ_HANDLED;
-	}
 
 	/* Scehdule the bottom half of the ISR */
 	fst_q_work_item(&fst_work_intq, card->card_no);
@@ -1611,7 +1553,7 @@ fst_intr(int dummy, void *dev_id)
 			rdidx = 0;
 	}
 	FST_WRB(card, interruptEvent.rdindex, rdidx);
-        return IRQ_HANDLED;
+	return IRQ_HANDLED;
 }
 
 /*      Check that the shared memory configuration is one that we can handle
@@ -1635,7 +1577,8 @@ check_started_ok(struct fst_card_info *card)
 		return;
 	}
 	/* Firmware status flag, 0x00 = initialising, 0x01 = OK, 0xFF = fail */
-	if ((i = FST_RDB(card, taskStatus)) == 0x01) {
+	i = FST_RDB(card, taskStatus);
+	if (i == 0x01) {
 		card->state = FST_RUNNING;
 	} else if (i == 0xFF) {
 		pr_err("Firmware initialisation failed. Card halted\n");
@@ -1665,8 +1608,8 @@ set_conf_from_info(struct fst_card_info *card, struct fst_port_info *port,
 	int err;
 	unsigned char my_framing;
 
-	/* Set things according to the user set valid flags 
-	 * Several of the old options have been invalidated/replaced by the 
+	/* Set things according to the user set valid flags
+	 * Several of the old options have been invalidated/replaced by the
 	 * generic hdlc package.
 	 */
 	err = 0;
@@ -1740,9 +1683,8 @@ set_conf_from_info(struct fst_card_info *card, struct fst_port_info *port,
 #endif
 	}
 #if FST_DEBUG
-	if (info->valid & FSTVAL_DEBUG) {
+	if (info->valid & FSTVAL_DEBUG)
 		fst_debug_mask = info->debug;
-	}
 #endif
 
 	return err;
@@ -1754,7 +1696,7 @@ gather_conf_info(struct fst_card_info *card, struct fst_port_info *port,
 {
 	int i;
 
-	memset(info, 0, sizeof (struct fstioc_info));
+	memset(info, 0, sizeof(struct fstioc_info));
 
 	i = port->index;
 	info->kernelVersion = LINUX_VERSION_CODE;
@@ -1787,27 +1729,23 @@ gather_conf_info(struct fst_card_info *card, struct fst_port_info *port,
 	info->cardMode = FST_RDW(card, cardMode);
 	info->smcFirmwareVersion = FST_RDL(card, smcFirmwareVersion);
 
-	/*
-	 * The T2U can report cable presence for both A or B
-	 * in bits 0 and 1 of cableStatus.  See which port we are and 
+	/* The T2U can report cable presence for both A or B
+	 * in bits 0 and 1 of cableStatus.  See which port we are and
 	 * do the mapping.
 	 */
 	if (card->family == FST_FAMILY_TXU) {
 		if (port->index == 0) {
-			/*
-			 * Port A
+			/* Port A
 			 */
 			info->cableStatus = info->cableStatus & 1;
 		} else {
-			/*
-			 * Port B
+			/* Port B
 			 */
 			info->cableStatus = info->cableStatus >> 1;
 			info->cableStatus = info->cableStatus & 1;
 		}
 	}
-	/*
-	 * Some additional bits if we are TE1
+	/* Some additional bits if we are TE1
 	 */
 	if (card->type == FST_TYPE_TE1) {
 		info->lineSpeed = FST_RDL(card, suConfig.dataRate);
@@ -1851,14 +1789,12 @@ fst_set_iface(struct fst_card_info *card, struct fst_port_info *port,
 	sync_serial_settings sync;
 	int i;
 
-	if (ifr->ifr_settings.size != sizeof (sync)) {
+	if (ifr->ifr_settings.size != sizeof(sync))
 		return -ENOMEM;
-	}
 
 	if (copy_from_user
-	    (&sync, ifr->ifr_settings.ifs_ifsu.sync, sizeof (sync))) {
+	    (&sync, ifr->ifr_settings.ifs_ifsu.sync, sizeof(sync)))
 		return -EFAULT;
-	}
 
 	if (sync.loopback)
 		return -EINVAL;
@@ -1951,12 +1887,11 @@ fst_get_iface(struct fst_card_info *card, struct fst_port_info *port,
 		ifr->ifr_settings.type = IF_IFACE_X21;
 		break;
 	}
-	if (ifr->ifr_settings.size == 0) {
+	if (ifr->ifr_settings.size == 0)
 		return 0;	/* only type requested */
-	}
-	if (ifr->ifr_settings.size < sizeof (sync)) {
+
+	if (ifr->ifr_settings.size < sizeof(sync))
 		return -ENOMEM;
-	}
 
 	i = port->index;
 	memset(&sync, 0, sizeof(sync));
@@ -1966,11 +1901,10 @@ fst_get_iface(struct fst_card_info *card, struct fst_port_info *port,
 	    INTCLK ? CLOCK_INT : CLOCK_EXT;
 	sync.loopback = 0;
 
-	if (copy_to_user(ifr->ifr_settings.ifs_ifsu.sync, &sync, sizeof (sync))) {
+	if (copy_to_user(ifr->ifr_settings.ifs_ifsu.sync, &sync, sizeof(sync)))
 		return -EFAULT;
-	}
 
-	ifr->ifr_settings.size = sizeof (sync);
+	ifr->ifr_settings.size = sizeof(sync);
 	return 0;
 }
 
@@ -2008,21 +1942,19 @@ fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		/* First copy in the header with the length and offset of data
 		 * to write
 		 */
-		if (ifr->ifr_data == NULL) {
+		if (!ifr->ifr_data)
 			return -EINVAL;
-		}
+
 		if (copy_from_user(&wrthdr, ifr->ifr_data,
-				   sizeof (struct fstioc_write))) {
+				   sizeof(struct fstioc_write)))
 			return -EFAULT;
-		}
 
 		/* Sanity check the parameters. We don't support partial writes
 		 * when going over the top
 		 */
 		if (wrthdr.size > FST_MEMSIZE || wrthdr.offset > FST_MEMSIZE ||
-		    wrthdr.size + wrthdr.offset > FST_MEMSIZE) {
+		    wrthdr.size + wrthdr.offset > FST_MEMSIZE)
 			return -ENXIO;
-		}
 
 		/* Now copy the data to the card. */
 
@@ -2037,9 +1969,9 @@ fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		/* Writes to the memory of a card in the reset state constitute
 		 * a download
 		 */
-		if (card->state == FST_RESET) {
+		if (card->state == FST_RESET)
 			card->state = FST_DOWNLOAD;
-		}
+
 		return 0;
 
 	case FSTGETCONF:
@@ -2059,21 +1991,18 @@ fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			}
 		}
 
-		if (ifr->ifr_data == NULL) {
+		if (!ifr->ifr_data)
 			return -EINVAL;
-		}
 
 		gather_conf_info(card, port, &info);
 
-		if (copy_to_user(ifr->ifr_data, &info, sizeof (info))) {
+		if (copy_to_user(ifr->ifr_data, &info, sizeof(info)))
 			return -EFAULT;
-		}
+
 		return 0;
 
 	case FSTSETCONF:
-
-		/*
-		 * Most of the settings have been moved to the generic ioctls
+		/* Most of the settings have been moved to the generic ioctls
 		 * this just covers debug and board ident now
 		 */
 
@@ -2082,9 +2011,8 @@ fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			       card->card_no, card->state);
 			return -EIO;
 		}
-		if (copy_from_user(&info, ifr->ifr_data, sizeof (info))) {
+		if (copy_from_user(&info, ifr->ifr_data, sizeof(info)))
 			return -EFAULT;
-		}
 
 		return set_conf_from_info(card, port, &info);
 
@@ -2150,7 +2078,7 @@ fst_openport(struct fst_port_info *port)
 		port->run = 1;
 
 		signals = FST_RDL(port->card, v24DebouncedSts[port->index]);
-		if (signals & (((port->hwif == X21) || (port->hwif == X21D))
+		if (signals & ((port->hwif == X21 || port->hwif == X21D)
 			       ? IPSTS_INDICATE : IPSTS_DCD))
 			netif_carrier_on(port_to_dev(port));
 		else
@@ -2159,7 +2087,6 @@ fst_openport(struct fst_port_info *port)
 		port->txqe = 0;
 		port->txqs = 0;
 	}
-
 }
 
 static void
@@ -2185,7 +2112,7 @@ fst_open(struct net_device *dev)
 
 	port = dev_to_port(dev);
 	if (!try_module_get(THIS_MODULE))
-          return -EBUSY;
+		return -EBUSY;
 
 	if (port->mode != FST_RAW) {
 		err = hdlc_open(dev);
@@ -2220,9 +2147,9 @@ fst_close(struct net_device *dev)
 
 	netif_stop_queue(dev);
 	fst_closeport(dev_to_port(dev));
-	if (port->mode != FST_RAW) {
+	if (port->mode != FST_RAW)
 		hdlc_close(dev);
-	}
+
 	module_put(THIS_MODULE);
 	return 0;
 }
@@ -2230,8 +2157,7 @@ fst_close(struct net_device *dev)
 static int
 fst_attach(struct net_device *dev, unsigned short encoding, unsigned short parity)
 {
-	/*
-	 * Setting currently fixed in FarSync card so we check and forget
+	/* Setting currently fixed in FarSync card so we check and forget
 	 */
 	if (encoding != ENCODING_NRZ || parity != PARITY_CRC16_PR1_CCITT)
 		return -EINVAL;
@@ -2289,23 +2215,21 @@ fst_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_OK;
 	}
 
-	/*
-	 * We are always going to queue the packet
+	/* We are always going to queue the packet
 	 * so that the bottom half is the only place we tx from
 	 * Check there is room in the port txq
 	 */
 	spin_lock_irqsave(&card->card_lock, flags);
-	if ((txq_length = port->txqe - port->txqs) < 0) {
-		/*
-		 * This is the case where the next free has wrapped but the
+	txq_length = port->txqe - port->txqs;
+	if (txq_length < 0) {
+		/* This is the case where the next free has wrapped but the
 		 * last used hasn't
 		 */
 		txq_length = txq_length + FST_TXQ_DEPTH;
 	}
 	spin_unlock_irqrestore(&card->card_lock, flags);
 	if (txq_length > fst_txq_high) {
-		/*
-		 * We have got enough buffers in the pipeline.  Ask the network
+		/* We have got enough buffers in the pipeline.  Ask the network
 		 * layer to stop sending frames down
 		 */
 		netif_stop_queue(dev);
@@ -2313,8 +2237,7 @@ fst_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	if (txq_length == FST_TXQ_DEPTH - 1) {
-		/*
-		 * This shouldn't have happened but such is life
+		/* This shouldn't have happened but such is life
 		 */
 		dev_kfree_skb(skb);
 		dev->stats.tx_errors++;
@@ -2323,8 +2246,7 @@ fst_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_OK;
 	}
 
-	/*
-	 * queue the buffer
+	/* queue the buffer
 	 */
 	spin_lock_irqsave(&card->card_lock, flags);
 	port->txq[port->txqe] = skb;
@@ -2340,8 +2262,7 @@ fst_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
-/*
- *      Card setup having checked hardware resources.
+/*      Card setup having checked hardware resources.
  *      Should be pretty bizarre if we get an error here (kernel memory
  *      exhaustion is one possibility). If we do see a problem we report it
  *      via a printk and leave the corresponding interface and all that follow
@@ -2371,7 +2292,7 @@ fst_init_card(struct fst_card_info *card)
 		err = register_hdlc_device(card->ports[i].dev);
 		if (err < 0) {
 			pr_err("Cannot register HDLC device for port %d (errno %d)\n",
-				i, -err);
+			       i, -err);
 			while (i--)
 				unregister_hdlc_device(card->ports[i].dev);
 			return err;
@@ -2393,14 +2314,13 @@ static const struct net_device_ops fst_ops = {
 	.ndo_tx_timeout = fst_tx_timeout,
 };
 
-/*
- *      Initialise card when detected.
+/*      Initialise card when detected.
  *      Returns 0 to indicate success, or errno otherwise.
  */
 static int
 fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
-	static int no_of_cards_added = 0;
+	static int no_of_cards_added;
 	struct fst_card_info *card;
 	int err = 0;
 	int i;
@@ -2411,17 +2331,15 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 #if FST_DEBUG
 	dbg(DBG_ASS, "The value of debug mask is %x\n", fst_debug_mask);
 #endif
-	/*
-	 * We are going to be clever and allow certain cards not to be
+	/* We are going to be clever and allow certain cards not to be
 	 * configured.  An exclude list can be provided in /etc/modules.conf
 	 */
 	if (fst_excluded_cards != 0) {
-		/*
-		 * There are cards to exclude
+		/* There are cards to exclude
 		 *
 		 */
 		for (i = 0; i < fst_excluded_cards; i++) {
-			if ((pdev->devfn) >> 3 == fst_excluded_list[i]) {
+			if (pdev->devfn >> 3 == fst_excluded_list[i]) {
 				pr_info("FarSync PCI device %d not assigned\n",
 					(pdev->devfn) >> 3);
 				return -EBUSY;
@@ -2431,16 +2349,18 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* Allocate driver private data */
 	card = kzalloc(sizeof(struct fst_card_info), GFP_KERNEL);
-	if (card == NULL)
+	if (!card)
 		return -ENOMEM;
 
 	/* Try to enable the device */
-	if ((err = pci_enable_device(pdev)) != 0) {
+	err = pci_enable_device(pdev);
+	if (err) {
 		pr_err("Failed to enable card. Err %d\n", -err);
 		goto enable_fail;
 	}
 
-	if ((err = pci_request_regions(pdev, "FarSync")) !=0) {
+	err = pci_request_regions(pdev, "FarSync");
+	if (err) {
 		pr_err("Failed to allocate regions. Err %d\n", -err);
 		goto regions_fail;
 	}
@@ -2449,12 +2369,14 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	card->pci_conf = pci_resource_start(pdev, 1);
 	card->phys_mem = pci_resource_start(pdev, 2);
 	card->phys_ctlmem = pci_resource_start(pdev, 3);
-	if ((card->mem = ioremap(card->phys_mem, FST_MEMSIZE)) == NULL) {
+	card->mem = ioremap(card->phys_mem, FST_MEMSIZE);
+	if (!card->mem) {
 		pr_err("Physical memory remap failed\n");
 		err = -ENODEV;
 		goto ioremap_physmem_fail;
 	}
-	if ((card->ctlmem = ioremap(card->phys_ctlmem, 0x10)) == NULL) {
+	card->ctlmem = ioremap(card->phys_ctlmem, 0x10);
+	if (!card->ctlmem) {
 		pr_err("Control memory remap failed\n");
 		err = -ENODEV;
 		goto ioremap_ctlmem_fail;
@@ -2474,19 +2396,20 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	card->family = ((ent->driver_data == FST_TYPE_T2P) ||
 			(ent->driver_data == FST_TYPE_T4P))
 	    ? FST_FAMILY_TXP : FST_FAMILY_TXU;
-	if ((ent->driver_data == FST_TYPE_T1U) ||
-	    (ent->driver_data == FST_TYPE_TE1))
+	if (ent->driver_data == FST_TYPE_T1U ||
+	    ent->driver_data == FST_TYPE_TE1)
 		card->nports = 1;
 	else
 		card->nports = ((ent->driver_data == FST_TYPE_T2P) ||
 				(ent->driver_data == FST_TYPE_T2U)) ? 2 : 4;
 
 	card->state = FST_UNINIT;
-        spin_lock_init ( &card->card_lock );
+	spin_lock_init(&card->card_lock);
 
-        for ( i = 0 ; i < card->nports ; i++ ) {
+	for (i = 0; i < card->nports; i++) {
 		struct net_device *dev = alloc_hdlcdev(&card->ports[i]);
 		hdlc_device *hdlc;
+
 		if (!dev) {
 			while (i--)
 				free_netdev(card->ports[i].dev);
@@ -2495,29 +2418,29 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			goto hdlcdev_fail;
 		}
 		card->ports[i].dev    = dev;
-                card->ports[i].card   = card;
-                card->ports[i].index  = i;
-                card->ports[i].run    = 0;
+		card->ports[i].card   = card;
+		card->ports[i].index  = i;
+		card->ports[i].run    = 0;
 
 		hdlc = dev_to_hdlc(dev);
 
-                /* Fill in the net device info */
+		/* Fill in the net device info */
 		/* Since this is a PCI setup this is purely
 		 * informational. Give them the buffer addresses
 		 * and basic card I/O.
 		 */
-                dev->mem_start   = card->phys_mem
-                                 + BUF_OFFSET ( txBuffer[i][0][0]);
-                dev->mem_end     = card->phys_mem
-                                 + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER - 1][LEN_RX_BUFFER - 1]);
-                dev->base_addr   = card->pci_conf;
-                dev->irq         = card->irq;
+		dev->mem_start   = card->phys_mem
+				+ BUF_OFFSET(txBuffer[i][0][0]);
+		dev->mem_end     = card->phys_mem
+				+ BUF_OFFSET(txBuffer[i][NUM_TX_BUFFER - 1][LEN_RX_BUFFER - 1]);
+		dev->base_addr   = card->pci_conf;
+		dev->irq         = card->irq;
 
 		dev->netdev_ops = &fst_ops;
 		dev->tx_queue_len = FST_TX_QUEUE_LEN;
 		dev->watchdog_timeo = FST_TX_TIMEOUT;
-                hdlc->attach = fst_attach;
-                hdlc->xmit   = fst_start_xmit;
+		hdlc->attach = fst_attach;
+		hdlc->xmit   = fst_start_xmit;
 	}
 
 	card->device = pdev;
@@ -2549,13 +2472,12 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto init_card_fail;
 	if (card->family == FST_FAMILY_TXU) {
-		/*
-		 * Allocate a dma buffer for transmit and receives
+		/* Allocate a dma buffer for transmit and receives
 		 */
 		card->rx_dma_handle_host =
 		    dma_alloc_coherent(&card->device->dev, FST_MAX_MTU,
 				       &card->rx_dma_handle_card, GFP_KERNEL);
-		if (card->rx_dma_handle_host == NULL) {
+		if (!card->rx_dma_handle_host) {
 			pr_err("Could not allocate rx dma buffer\n");
 			err = -ENOMEM;
 			goto rx_dma_fail;
@@ -2563,7 +2485,7 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		card->tx_dma_handle_host =
 		    dma_alloc_coherent(&card->device->dev, FST_MAX_MTU,
 				       &card->tx_dma_handle_card, GFP_KERNEL);
-		if (card->tx_dma_handle_host == NULL) {
+		if (!card->tx_dma_handle_host) {
 			pr_err("Could not allocate tx dma buffer\n");
 			err = -ENOMEM;
 			goto tx_dma_fail;
@@ -2598,8 +2520,7 @@ enable_fail:
 	return err;
 }
 
-/*
- *      Cleanup and close down a card
+/*      Cleanup and close down a card
  */
 static void
 fst_remove_one(struct pci_dev *pdev)
@@ -2611,6 +2532,7 @@ fst_remove_one(struct pci_dev *pdev)
 
 	for (i = 0; i < card->nports; i++) {
 		struct net_device *dev = port_to_dev(&card->ports[i]);
+
 		unregister_hdlc_device(dev);
 	}
 
@@ -2621,8 +2543,7 @@ fst_remove_one(struct pci_dev *pdev)
 	iounmap(card->mem);
 	pci_release_regions(pdev);
 	if (card->family == FST_FAMILY_TXU) {
-		/*
-		 * Free dma buffers
+		/* Free dma buffers
 		 */
 		dma_free_coherent(&card->device->dev, FST_MAX_MTU,
 				  card->rx_dma_handle_host,
diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index 7eac6a3e1cde..39f05fabbfa4 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -1171,9 +1171,8 @@ static int ucc_hdlc_probe(struct platform_device *pdev)
 	ut_info->uf_info.irq = irq_of_parse_and_map(np, 0);
 
 	uhdlc_priv = kzalloc(sizeof(*uhdlc_priv), GFP_KERNEL);
-	if (!uhdlc_priv) {
+	if (!uhdlc_priv)
 		return -ENOMEM;
-	}
 
 	dev_set_drvdata(&pdev->dev, uhdlc_priv);
 	uhdlc_priv->dev = &pdev->dev;
diff --git a/drivers/net/wan/hd64570.c b/drivers/net/wan/hd64570.c
index 058e48182838..0d19e39fec86 100644
--- a/drivers/net/wan/hd64570.c
+++ b/drivers/net/wan/hd64570.c
@@ -47,7 +47,6 @@
 #define SCA_INTR_DMAC_RX(node) (node ? 0x20 : 0x02)
 #define SCA_INTR_DMAC_TX(node) (node ? 0x40 : 0x04)
 
-
 static inline struct net_device *port_to_dev(port_t *port)
 {
 	return port->dev;
@@ -59,12 +58,18 @@ static inline int sca_intr_status(card_t *card)
 	u8 isr0 = sca_in(ISR0, card);
 	u8 isr1 = sca_in(ISR1, card);
 
-	if (isr1 & 0x03) result |= SCA_INTR_DMAC_RX(0);
-	if (isr1 & 0x0C) result |= SCA_INTR_DMAC_TX(0);
-	if (isr1 & 0x30) result |= SCA_INTR_DMAC_RX(1);
-	if (isr1 & 0xC0) result |= SCA_INTR_DMAC_TX(1);
-	if (isr0 & 0x0F) result |= SCA_INTR_MSCI(0);
-	if (isr0 & 0xF0) result |= SCA_INTR_MSCI(1);
+	if (isr1 & 0x03)
+		result |= SCA_INTR_DMAC_RX(0);
+	if (isr1 & 0x0C)
+		result |= SCA_INTR_DMAC_TX(0);
+	if (isr1 & 0x30)
+		result |= SCA_INTR_DMAC_RX(1);
+	if (isr1 & 0xC0)
+		result |= SCA_INTR_DMAC_TX(1);
+	if (isr0 & 0x0F)
+		result |= SCA_INTR_MSCI(0);
+	if (isr0 & 0xF0)
+		result |= SCA_INTR_MSCI(1);
 
 	if (!(result & SCA_INTR_DMAC_TX(0)))
 		if (sca_in(DSR_TX(0), card) & DSR_EOM)
@@ -76,7 +81,7 @@ static inline int sca_intr_status(card_t *card)
 	return result;
 }
 
-static inline port_t* dev_to_port(struct net_device *dev)
+static inline port_t *dev_to_port(struct net_device *dev)
 {
 	return dev_to_hdlc(dev)->priv;
 }
@@ -87,7 +92,6 @@ static inline u16 next_desc(port_t *port, u16 desc, int transmit)
 			     : port_to_card(port)->rx_ring_buffers);
 }
 
-
 static inline u16 desc_abs_number(port_t *port, u16 desc, int transmit)
 {
 	u16 rx_buffs = port_to_card(port)->rx_ring_buffers;
@@ -98,14 +102,12 @@ static inline u16 desc_abs_number(port_t *port, u16 desc, int transmit)
 		transmit * rx_buffs + desc;
 }
 
-
 static inline u16 desc_offset(port_t *port, u16 desc, int transmit)
 {
 	/* Descriptor offset always fits in 16 bits */
 	return desc_abs_number(port, desc, transmit) * sizeof(pkt_desc);
 }
 
-
 static inline pkt_desc __iomem *desc_address(port_t *port, u16 desc,
 					     int transmit)
 {
@@ -118,14 +120,12 @@ static inline pkt_desc __iomem *desc_address(port_t *port, u16 desc,
 #endif
 }
 
-
 static inline u32 buffer_offset(port_t *port, u16 desc, int transmit)
 {
 	return port_to_card(port)->buff_offset +
 		desc_abs_number(port, desc, transmit) * (u32)HDLC_MAX_MRU;
 }
 
-
 static inline void sca_set_carrier(port_t *port)
 {
 	if (!(sca_in(get_msci(port) + ST3, port_to_card(port)) & ST3_DCD)) {
@@ -143,7 +143,6 @@ static inline void sca_set_carrier(port_t *port)
 	}
 }
 
-
 static void sca_init_port(port_t *port)
 {
 	card_t *card = port_to_card(port);
@@ -213,13 +212,12 @@ static void sca_init_port(port_t *port)
 	sca_set_carrier(port);
 }
 
-
 #ifdef NEED_SCA_MSCI_INTR
 /* MSCI interrupt service */
 static inline void sca_msci_intr(port_t *port)
 {
 	u16 msci = get_msci(port);
-	card_t* card = port_to_card(port);
+	card_t *card = port_to_card(port);
 	u8 stat = sca_in(msci + ST1, card); /* read MSCI ST1 status */
 
 	/* Reset MSCI TX underrun and CDCD status bit */
@@ -236,7 +234,6 @@ static inline void sca_msci_intr(port_t *port)
 }
 #endif
 
-
 static inline void sca_rx(card_t *card, port_t *port, pkt_desc __iomem *desc,
 			  u16 rxin)
 {
@@ -265,8 +262,9 @@ static inline void sca_rx(card_t *card, port_t *port, pkt_desc __iomem *desc,
 		memcpy_fromio(skb->data, winbase(card) + buff, maxlen);
 		openwin(card, page + 1);
 		memcpy_fromio(skb->data + maxlen, winbase(card), len - maxlen);
-	} else
+	} else {
 		memcpy_fromio(skb->data, winbase(card) + buff, len);
+	}
 
 #ifndef PAGE0_ALWAYS_MAPPED
 	openwin(card, 0);	/* select pkt_desc table page back */
@@ -282,7 +280,6 @@ static inline void sca_rx(card_t *card, port_t *port, pkt_desc __iomem *desc,
 	netif_rx(skb);
 }
 
-
 /* Receive DMA interrupt service */
 static inline void sca_rx_intr(port_t *port)
 {
@@ -304,7 +301,7 @@ static inline void sca_rx_intr(port_t *port)
 		pkt_desc __iomem *desc;
 		u32 cda = sca_inw(dmac + CDAL, card);
 
-		if ((cda >= desc_off) && (cda < desc_off + sizeof(pkt_desc)))
+		if (cda >= desc_off && (cda < desc_off + sizeof(pkt_desc)))
 			break;	/* No frame received */
 
 		desc = desc_address(port, port->rxin, 0);
@@ -322,8 +319,9 @@ static inline void sca_rx_intr(port_t *port)
 				dev->stats.rx_crc_errors++;
 			if (stat & ST_RX_EOM)
 				port->rxpart = 0; /* received last fragment */
-		} else
+		} else {
 			sca_rx(card, port, desc, port->rxin);
+		}
 
 		/* Set new error descriptor address */
 		sca_outw(desc_off, dmac + EDAL, card);
@@ -334,13 +332,12 @@ static inline void sca_rx_intr(port_t *port)
 	sca_out(DSR_DE, DSR_RX(phy_node(port)), card);
 }
 
-
 /* Transmit DMA interrupt service */
 static inline void sca_tx_intr(port_t *port)
 {
 	struct net_device *dev = port_to_dev(port);
 	u16 dmac = get_dmac_tx(port);
-	card_t* card = port_to_card(port);
+	card_t *card = port_to_card(port);
 	u8 stat;
 
 	spin_lock(&port->lock);
@@ -356,7 +353,8 @@ static inline void sca_tx_intr(port_t *port)
 
 		u32 desc_off = desc_offset(port, port->txlast, 1);
 		u32 cda = sca_inw(dmac + CDAL, card);
-		if ((cda >= desc_off) && (cda < desc_off + sizeof(pkt_desc)))
+
+		if (cda >= desc_off && (cda < desc_off + sizeof(pkt_desc)))
 			break;	/* Transmitter is/will_be sending this frame */
 
 		desc = desc_address(port, port->txlast, 1);
@@ -370,8 +368,7 @@ static inline void sca_tx_intr(port_t *port)
 	spin_unlock(&port->lock);
 }
 
-
-static irqreturn_t sca_intr(int irq, void* dev_id)
+static irqreturn_t sca_intr(int irq, void *dev_id)
 {
 	card_t *card = dev_id;
 	int i;
@@ -379,10 +376,11 @@ static irqreturn_t sca_intr(int irq, void* dev_id)
 	int handled = 0;
 	u8 page = sca_get_page(card);
 
-	while((stat = sca_intr_status(card)) != 0) {
+	while ((stat = sca_intr_status(card)) != 0) {
 		handled = 1;
 		for (i = 0; i < 2; i++) {
 			port_t *port = get_port(card, i);
+
 			if (port) {
 				if (stat & SCA_INTR_MSCI(i))
 					sca_msci_intr(port);
@@ -400,15 +398,13 @@ static irqreturn_t sca_intr(int irq, void* dev_id)
 	return IRQ_RETVAL(handled);
 }
 
-
 static void sca_set_port(port_t *port)
 {
-	card_t* card = port_to_card(port);
+	card_t *card = port_to_card(port);
 	u16 msci = get_msci(port);
 	u8 md2 = sca_in(msci + MD2, card);
 	unsigned int tmc, br = 10, brv = 1024;
 
-
 	if (port->settings.clock_rate > 0) {
 		/* Try lower br for better accuracy*/
 		do {
@@ -417,14 +413,15 @@ static void sca_set_port(port_t *port)
 
 			/* Baud Rate = CLOCK_BASE / TMC / 2^BR */
 			tmc = CLOCK_BASE / brv / port->settings.clock_rate;
-		}while (br > 1 && tmc <= 128);
+		} while (br > 1 && tmc <= 128);
 
 		if (tmc < 1) {
 			tmc = 1;
 			br = 0;	/* For baud=CLOCK_BASE we use tmc=1 br=0 */
 			brv = 1;
-		} else if (tmc > 255)
+		} else if (tmc > 255) {
 			tmc = 256; /* tmc=0 means 256 - low baud rates */
+		}
 
 		port->settings.clock_rate = CLOCK_BASE / brv / tmc;
 	} else {
@@ -450,34 +447,50 @@ static void sca_set_port(port_t *port)
 		md2 &= ~MD2_LOOPBACK;
 
 	sca_out(md2, msci + MD2, card);
-
 }
 
-
 static void sca_open(struct net_device *dev)
 {
 	port_t *port = dev_to_port(dev);
-	card_t* card = port_to_card(port);
+	card_t *card = port_to_card(port);
 	u16 msci = get_msci(port);
 	u8 md0, md2;
 
-	switch(port->encoding) {
-	case ENCODING_NRZ:	md2 = MD2_NRZ;		break;
-	case ENCODING_NRZI:	md2 = MD2_NRZI;		break;
-	case ENCODING_FM_MARK:	md2 = MD2_FM_MARK;	break;
-	case ENCODING_FM_SPACE:	md2 = MD2_FM_SPACE;	break;
-	default:		md2 = MD2_MANCHESTER;
+	switch (port->encoding) {
+	case ENCODING_NRZ:
+		md2 = MD2_NRZ;
+		break;
+	case ENCODING_NRZI:
+		md2 = MD2_NRZI;
+		break;
+	case ENCODING_FM_MARK:
+		md2 = MD2_FM_MARK;
+		break;
+	case ENCODING_FM_SPACE:
+		md2 = MD2_FM_SPACE;
+		break;
+	default:
+		md2 = MD2_MANCHESTER;
 	}
 
 	if (port->settings.loopback)
 		md2 |= MD2_LOOPBACK;
 
-	switch(port->parity) {
-	case PARITY_CRC16_PR0:	     md0 = MD0_HDLC | MD0_CRC_16_0;  break;
-	case PARITY_CRC16_PR1:	     md0 = MD0_HDLC | MD0_CRC_16;    break;
-	case PARITY_CRC16_PR0_CCITT: md0 = MD0_HDLC | MD0_CRC_ITU_0; break;
-	case PARITY_CRC16_PR1_CCITT: md0 = MD0_HDLC | MD0_CRC_ITU;   break;
-	default:		     md0 = MD0_HDLC | MD0_CRC_NONE;
+	switch (port->parity) {
+	case PARITY_CRC16_PR0:
+		md0 = MD0_HDLC | MD0_CRC_16_0;
+		break;
+	case PARITY_CRC16_PR1:
+		md0 = MD0_HDLC | MD0_CRC_16;
+		break;
+	case PARITY_CRC16_PR0_CCITT:
+		md0 = MD0_HDLC | MD0_CRC_ITU_0;
+		break;
+	case PARITY_CRC16_PR1_CCITT:
+		md0 = MD0_HDLC | MD0_CRC_ITU;
+		break;
+	default:
+		md0 = MD0_HDLC | MD0_CRC_NONE;
 	}
 
 	sca_out(CMD_RESET, msci + CMD, card);
@@ -494,9 +507,9 @@ static void sca_open(struct net_device *dev)
 	sca_out(0x14, msci + TRC1, card); /* +1=TXRDY/DMA deactiv condition */
 
 /* We're using the following interrupts:
-   - TXINT (DMAC completed all transmisions, underrun or DCD change)
-   - all DMA interrupts
-*/
+ * - TXINT (DMAC completed all transmisions, underrun or DCD change)
+ * - all DMA interrupts
+ */
 	sca_set_carrier(port);
 
 	/* MSCI TX INT and RX INT A IRQ enable */
@@ -517,11 +530,10 @@ static void sca_open(struct net_device *dev)
 	netif_start_queue(dev);
 }
 
-
 static void sca_close(struct net_device *dev)
 {
 	port_t *port = dev_to_port(dev);
-	card_t* card = port_to_card(port);
+	card_t *card = port_to_card(port);
 
 	/* reset channel */
 	sca_out(CMD_RESET, get_msci(port) + CMD, port_to_card(port));
@@ -535,7 +547,6 @@ static void sca_close(struct net_device *dev)
 	netif_stop_queue(dev);
 }
 
-
 static int sca_attach(struct net_device *dev, unsigned short encoding,
 		      unsigned short parity)
 {
@@ -558,7 +569,6 @@ static int sca_attach(struct net_device *dev, unsigned short encoding,
 	return 0;
 }
 
-
 #ifdef DEBUG_RINGS
 static void sca_dump_rings(struct net_device *dev)
 {
@@ -613,7 +623,6 @@ static void sca_dump_rings(struct net_device *dev)
 }
 #endif /* DEBUG_RINGS */
 
-
 static netdev_tx_t sca_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	port_t *port = dev_to_port(dev);
@@ -645,8 +654,9 @@ static netdev_tx_t sca_xmit(struct sk_buff *skb, struct net_device *dev)
 		memcpy_toio(winbase(card) + buff, skb->data, maxlen);
 		openwin(card, page + 1);
 		memcpy_toio(winbase(card), skb->data + maxlen, len - maxlen);
-	} else
+	} else {
 		memcpy_toio(winbase(card) + buff, skb->data, len);
+	}
 
 #ifndef PAGE0_ALWAYS_MAPPED
 	openwin(card, 0);	/* select pkt_desc table page back */
@@ -670,7 +680,6 @@ static netdev_tx_t sca_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
-
 #ifdef NEED_DETECT_RAM
 static u32 sca_detect_ram(card_t *card, u8 __iomem *rambase, u32 ramsize)
 {
@@ -699,7 +708,6 @@ static u32 sca_detect_ram(card_t *card, u8 __iomem *rambase, u32 ramsize)
 }
 #endif /* NEED_DETECT_RAM */
 
-
 static void sca_init(card_t *card, int wait_states)
 {
 	sca_out(wait_states, WCRL, card); /* Wait Control */
diff --git a/drivers/net/wan/hd64572.c b/drivers/net/wan/hd64572.c
index 9f60e3969bf8..b89b03a6aba7 100644
--- a/drivers/net/wan/hd64572.c
+++ b/drivers/net/wan/hd64572.c
@@ -41,20 +41,20 @@
 
 #define NAPI_WEIGHT		16
 
-#define get_msci(port)	  (port->chan ?   MSCI1_OFFSET :   MSCI0_OFFSET)
-#define get_dmac_rx(port) (port->chan ? DMAC1RX_OFFSET : DMAC0RX_OFFSET)
-#define get_dmac_tx(port) (port->chan ? DMAC1TX_OFFSET : DMAC0TX_OFFSET)
+#define get_msci(port)	  ((port)->chan ?   MSCI1_OFFSET :   MSCI0_OFFSET)
+#define get_dmac_rx(port) ((port)->chan ? DMAC1RX_OFFSET : DMAC0RX_OFFSET)
+#define get_dmac_tx(port) ((port)->chan ? DMAC1TX_OFFSET : DMAC0TX_OFFSET)
 
-#define sca_in(reg, card)	     readb(card->scabase + (reg))
-#define sca_out(value, reg, card)    writeb(value, card->scabase + (reg))
-#define sca_inw(reg, card)	     readw(card->scabase + (reg))
-#define sca_outw(value, reg, card)   writew(value, card->scabase + (reg))
-#define sca_inl(reg, card)	     readl(card->scabase + (reg))
-#define sca_outl(value, reg, card)   writel(value, card->scabase + (reg))
+#define sca_in(reg, card)	     readb((card)->scabase + (reg))
+#define sca_out(value, reg, card)    writeb(value, (card)->scabase + (reg))
+#define sca_inw(reg, card)	     readw((card)->scabase + (reg))
+#define sca_outw(value, reg, card)   writew(value, (card)->scabase + (reg))
+#define sca_inl(reg, card)	     readl((card)->scabase + (reg))
+#define sca_outl(value, reg, card)   writel(value, (card)->scabase + (reg))
 
 static int sca_poll(struct napi_struct *napi, int budget);
 
-static inline port_t* dev_to_port(struct net_device *dev)
+static inline port_t *dev_to_port(struct net_device *dev)
 {
 	return dev_to_hdlc(dev)->priv;
 }
@@ -81,14 +81,12 @@ static inline u16 desc_abs_number(port_t *port, u16 desc, int transmit)
 	return port->chan * (rx_buffs + tx_buffs) + transmit * rx_buffs + desc;
 }
 
-
 static inline u16 desc_offset(port_t *port, u16 desc, int transmit)
 {
 	/* Descriptor offset always fits in 16 bits */
 	return desc_abs_number(port, desc, transmit) * sizeof(pkt_desc);
 }
 
-
 static inline pkt_desc __iomem *desc_address(port_t *port, u16 desc,
 					     int transmit)
 {
@@ -96,14 +94,12 @@ static inline pkt_desc __iomem *desc_address(port_t *port, u16 desc,
 				    desc_offset(port, desc, transmit));
 }
 
-
 static inline u32 buffer_offset(port_t *port, u16 desc, int transmit)
 {
 	return port->card->buff_offset +
 		desc_abs_number(port, desc, transmit) * (u32)HDLC_MAX_MRU;
 }
 
-
 static inline void sca_set_carrier(port_t *port)
 {
 	if (!(sca_in(get_msci(port) + ST3, port->card) & ST3_DCD)) {
@@ -121,7 +117,6 @@ static inline void sca_set_carrier(port_t *port)
 	}
 }
 
-
 static void sca_init_port(port_t *port)
 {
 	card_t *card = port->card;
@@ -181,12 +176,11 @@ static void sca_init_port(port_t *port)
 	netif_napi_add(port->netdev, &port->napi, sca_poll, NAPI_WEIGHT);
 }
 
-
 /* MSCI interrupt service */
 static inline void sca_msci_intr(port_t *port)
 {
 	u16 msci = get_msci(port);
-	card_t* card = port->card;
+	card_t *card = port->card;
 
 	if (sca_in(msci + ST1, card) & ST1_CDCD) {
 		/* Reset MSCI CDCD status bit */
@@ -195,7 +189,6 @@ static inline void sca_msci_intr(port_t *port)
 	}
 }
 
-
 static inline void sca_rx(card_t *card, port_t *port, pkt_desc __iomem *desc,
 			  u16 rxin)
 {
@@ -225,7 +218,6 @@ static inline void sca_rx(card_t *card, port_t *port, pkt_desc __iomem *desc,
 	netif_receive_skb(skb);
 }
 
-
 /* Receive DMA service */
 static inline int sca_rx_done(port_t *port, int budget)
 {
@@ -281,12 +273,11 @@ static inline int sca_rx_done(port_t *port, int budget)
 	return received;
 }
 
-
 /* Transmit DMA service */
 static inline void sca_tx_done(port_t *port)
 {
 	struct net_device *dev = port->netdev;
-	card_t* card = port->card;
+	card_t *card = port->card;
 	u8 stat;
 	unsigned count = 0;
 
@@ -321,7 +312,6 @@ static inline void sca_tx_done(port_t *port)
 	spin_unlock(&port->lock);
 }
 
-
 static int sca_poll(struct napi_struct *napi, int budget)
 {
 	port_t *port = container_of(napi, port_t, napi);
@@ -363,15 +353,13 @@ static irqreturn_t sca_intr(int irq, void *dev_id)
 	return IRQ_RETVAL(handled);
 }
 
-
 static void sca_set_port(port_t *port)
 {
-	card_t* card = port->card;
+	card_t *card = port->card;
 	u16 msci = get_msci(port);
 	u8 md2 = sca_in(msci + MD2, card);
 	unsigned int tmc, br = 10, brv = 1024;
 
-
 	if (port->settings.clock_rate > 0) {
 		/* Try lower br for better accuracy*/
 		do {
@@ -380,14 +368,15 @@ static void sca_set_port(port_t *port)
 
 			/* Baud Rate = CLOCK_BASE / TMC / 2^BR */
 			tmc = CLOCK_BASE / brv / port->settings.clock_rate;
-		}while (br > 1 && tmc <= 128);
+		} while (br > 1 && tmc <= 128);
 
 		if (tmc < 1) {
 			tmc = 1;
 			br = 0;	/* For baud=CLOCK_BASE we use tmc=1 br=0 */
 			brv = 1;
-		} else if (tmc > 255)
+		} else if (tmc > 255) {
 			tmc = 256; /* tmc=0 means 256 - low baud rates */
+		}
 
 		port->settings.clock_rate = CLOCK_BASE / brv / tmc;
 	} else {
@@ -414,34 +403,50 @@ static void sca_set_port(port_t *port)
 		md2 &= ~MD2_LOOPBACK;
 
 	sca_out(md2, msci + MD2, card);
-
 }
 
-
 static void sca_open(struct net_device *dev)
 {
 	port_t *port = dev_to_port(dev);
-	card_t* card = port->card;
+	card_t *card = port->card;
 	u16 msci = get_msci(port);
 	u8 md0, md2;
 
-	switch(port->encoding) {
-	case ENCODING_NRZ:	md2 = MD2_NRZ;		break;
-	case ENCODING_NRZI:	md2 = MD2_NRZI;		break;
-	case ENCODING_FM_MARK:	md2 = MD2_FM_MARK;	break;
-	case ENCODING_FM_SPACE:	md2 = MD2_FM_SPACE;	break;
-	default:		md2 = MD2_MANCHESTER;
+	switch (port->encoding) {
+	case ENCODING_NRZ:
+		md2 = MD2_NRZ;
+		break;
+	case ENCODING_NRZI:
+		md2 = MD2_NRZI;
+		break;
+	case ENCODING_FM_MARK:
+		md2 = MD2_FM_MARK;
+		break;
+	case ENCODING_FM_SPACE:
+		md2 = MD2_FM_SPACE;
+		break;
+	default:
+		md2 = MD2_MANCHESTER;
 	}
 
 	if (port->settings.loopback)
 		md2 |= MD2_LOOPBACK;
 
-	switch(port->parity) {
-	case PARITY_CRC16_PR0:	     md0 = MD0_HDLC | MD0_CRC_16_0;  break;
-	case PARITY_CRC16_PR1:	     md0 = MD0_HDLC | MD0_CRC_16;    break;
-	case PARITY_CRC32_PR1_CCITT: md0 = MD0_HDLC | MD0_CRC_ITU32; break;
-	case PARITY_CRC16_PR1_CCITT: md0 = MD0_HDLC | MD0_CRC_ITU;   break;
-	default:		     md0 = MD0_HDLC | MD0_CRC_NONE;
+	switch (port->parity) {
+	case PARITY_CRC16_PR0:
+		md0 = MD0_HDLC | MD0_CRC_16_0;
+		break;
+	case PARITY_CRC16_PR1:
+		md0 = MD0_HDLC | MD0_CRC_16;
+		break;
+	case PARITY_CRC32_PR1_CCITT:
+		md0 = MD0_HDLC | MD0_CRC_ITU32;
+		break;
+	case PARITY_CRC16_PR1_CCITT:
+		md0 = MD0_HDLC | MD0_CRC_ITU;
+		break;
+	default:
+		md0 = MD0_HDLC | MD0_CRC_NONE;
 	}
 
 	sca_out(CMD_RESET, msci + CMD, card);
@@ -476,7 +481,6 @@ static void sca_open(struct net_device *dev)
 	netif_start_queue(dev);
 }
 
-
 static void sca_close(struct net_device *dev)
 {
 	port_t *port = dev_to_port(dev);
@@ -488,7 +492,6 @@ static void sca_close(struct net_device *dev)
 	netif_stop_queue(dev);
 }
 
-
 static int sca_attach(struct net_device *dev, unsigned short encoding,
 		      unsigned short parity)
 {
@@ -511,7 +514,6 @@ static int sca_attach(struct net_device *dev, unsigned short encoding,
 	return 0;
 }
 
-
 #ifdef DEBUG_RINGS
 static void sca_dump_rings(struct net_device *dev)
 {
@@ -558,7 +560,6 @@ static void sca_dump_rings(struct net_device *dev)
 }
 #endif /* DEBUG_RINGS */
 
-
 static netdev_tx_t sca_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	port_t *port = dev_to_port(dev);
@@ -600,7 +601,6 @@ static netdev_tx_t sca_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
-
 static u32 sca_detect_ram(card_t *card, u8 __iomem *rambase, u32 ramsize)
 {
 	/* Round RAM size to 32 bits, fill from end to start */
@@ -619,7 +619,6 @@ static u32 sca_detect_ram(card_t *card, u8 __iomem *rambase, u32 ramsize)
 	return i;
 }
 
-
 static void sca_init(card_t *card, int wait_states)
 {
 	sca_out(wait_states, WCRL, card); /* Wait Control */
diff --git a/drivers/net/wan/hdlc.c b/drivers/net/wan/hdlc.c
index 1bdd3df0867a..dd6312b69861 100644
--- a/drivers/net/wan/hdlc.c
+++ b/drivers/net/wan/hdlc.c
@@ -36,8 +36,7 @@
 #include <linux/slab.h>
 #include <net/net_namespace.h>
 
-
-static const char* version = "HDLC support module revision 1.22";
+static const char *version = "HDLC support module revision 1.22";
 
 #undef DEBUG_LINK
 
@@ -74,25 +73,24 @@ netdev_tx_t hdlc_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	return hdlc->xmit(skb, dev); /* call hardware driver directly */
 }
+EXPORT_SYMBOL(hdlc_start_xmit);
 
 static inline void hdlc_proto_start(struct net_device *dev)
 {
 	hdlc_device *hdlc = dev_to_hdlc(dev);
+
 	if (hdlc->proto->start)
 		hdlc->proto->start(dev);
 }
 
-
-
 static inline void hdlc_proto_stop(struct net_device *dev)
 {
 	hdlc_device *hdlc = dev_to_hdlc(dev);
+
 	if (hdlc->proto->stop)
 		hdlc->proto->stop(dev);
 }
 
-
-
 static int hdlc_device_event(struct notifier_block *this, unsigned long event,
 			     void *ptr)
 {
@@ -141,8 +139,6 @@ carrier_exit:
 	return NOTIFY_DONE;
 }
 
-
-
 /* Must be called by hardware driver when HDLC device is being opened */
 int hdlc_open(struct net_device *dev)
 {
@@ -152,11 +148,12 @@ int hdlc_open(struct net_device *dev)
 	       hdlc->carrier, hdlc->open);
 #endif
 
-	if (hdlc->proto == NULL)
+	if (!hdlc->proto)
 		return -ENOSYS;	/* no protocol attached */
 
 	if (hdlc->proto->open) {
 		int result = hdlc->proto->open(dev);
+
 		if (result)
 			return result;
 	}
@@ -166,16 +163,16 @@ int hdlc_open(struct net_device *dev)
 	if (hdlc->carrier) {
 		netdev_info(dev, "Carrier detected\n");
 		hdlc_proto_start(dev);
-	} else
+	} else {
 		netdev_info(dev, "No carrier\n");
+	}
 
 	hdlc->open = 1;
 
 	spin_unlock_irq(&hdlc->state_lock);
 	return 0;
 }
-
-
+EXPORT_SYMBOL(hdlc_open);
 
 /* Must be called by hardware driver when HDLC device is being closed */
 void hdlc_close(struct net_device *dev)
@@ -197,8 +194,7 @@ void hdlc_close(struct net_device *dev)
 	if (hdlc->proto->close)
 		hdlc->proto->close(dev);
 }
-
-
+EXPORT_SYMBOL(hdlc_close);
 
 int hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
@@ -217,12 +213,14 @@ int hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	/* Not handled by currently attached protocol (if any) */
 
 	while (proto) {
-		if ((result = proto->ioctl(dev, ifr)) != -EINVAL)
+		result = proto->ioctl(dev, ifr);
+		if (result != -EINVAL)
 			return result;
 		proto = proto->next;
 	}
 	return -EINVAL;
 }
+EXPORT_SYMBOL(hdlc_ioctl);
 
 static const struct header_ops hdlc_null_ops;
 
@@ -256,12 +254,14 @@ static void hdlc_setup(struct net_device *dev)
 struct net_device *alloc_hdlcdev(void *priv)
 {
 	struct net_device *dev;
+
 	dev = alloc_netdev(sizeof(struct hdlc_device), "hdlc%d",
 			   NET_NAME_UNKNOWN, hdlc_setup);
 	if (dev)
 		dev_to_hdlc(dev)->priv = priv;
 	return dev;
 }
+EXPORT_SYMBOL(alloc_hdlcdev);
 
 void unregister_hdlc_device(struct net_device *dev)
 {
@@ -270,8 +270,7 @@ void unregister_hdlc_device(struct net_device *dev)
 	unregister_netdevice(dev);
 	rtnl_unlock();
 }
-
-
+EXPORT_SYMBOL(unregister_hdlc_device);
 
 int attach_hdlc_protocol(struct net_device *dev, struct hdlc_proto *proto,
 			 size_t size)
@@ -287,7 +286,7 @@ int attach_hdlc_protocol(struct net_device *dev, struct hdlc_proto *proto,
 
 	if (size) {
 		dev_to_hdlc(dev)->state = kmalloc(size, GFP_KERNEL);
-		if (dev_to_hdlc(dev)->state == NULL) {
+		if (!dev_to_hdlc(dev)->state) {
 			module_put(proto->module);
 			return -ENOBUFS;
 		}
@@ -296,7 +295,7 @@ int attach_hdlc_protocol(struct net_device *dev, struct hdlc_proto *proto,
 
 	return 0;
 }
-
+EXPORT_SYMBOL(attach_hdlc_protocol);
 
 int detach_hdlc_protocol(struct net_device *dev)
 {
@@ -322,7 +321,7 @@ int detach_hdlc_protocol(struct net_device *dev)
 
 	return 0;
 }
-
+EXPORT_SYMBOL(detach_hdlc_protocol);
 
 void register_hdlc_protocol(struct hdlc_proto *proto)
 {
@@ -331,7 +330,7 @@ void register_hdlc_protocol(struct hdlc_proto *proto)
 	first_proto = proto;
 	rtnl_unlock();
 }
-
+EXPORT_SYMBOL(register_hdlc_protocol);
 
 void unregister_hdlc_protocol(struct hdlc_proto *proto)
 {
@@ -346,54 +345,38 @@ void unregister_hdlc_protocol(struct hdlc_proto *proto)
 	*p = proto->next;
 	rtnl_unlock();
 }
-
-
+EXPORT_SYMBOL(unregister_hdlc_protocol);
 
 MODULE_AUTHOR("Krzysztof Halasa <khc@pm.waw.pl>");
 MODULE_DESCRIPTION("HDLC support module");
 MODULE_LICENSE("GPL v2");
 
-EXPORT_SYMBOL(hdlc_start_xmit);
-EXPORT_SYMBOL(hdlc_open);
-EXPORT_SYMBOL(hdlc_close);
-EXPORT_SYMBOL(hdlc_ioctl);
-EXPORT_SYMBOL(alloc_hdlcdev);
-EXPORT_SYMBOL(unregister_hdlc_device);
-EXPORT_SYMBOL(register_hdlc_protocol);
-EXPORT_SYMBOL(unregister_hdlc_protocol);
-EXPORT_SYMBOL(attach_hdlc_protocol);
-EXPORT_SYMBOL(detach_hdlc_protocol);
-
 static struct packet_type hdlc_packet_type __read_mostly = {
 	.type = cpu_to_be16(ETH_P_HDLC),
 	.func = hdlc_rcv,
 };
 
-
 static struct notifier_block hdlc_notifier = {
 	.notifier_call = hdlc_device_event,
 };
 
-
 static int __init hdlc_module_init(void)
 {
 	int result;
 
 	pr_info("%s\n", version);
-	if ((result = register_netdevice_notifier(&hdlc_notifier)) != 0)
+	result = register_netdevice_notifier(&hdlc_notifier);
+	if (result)
 		return result;
 	dev_add_pack(&hdlc_packet_type);
 	return 0;
 }
 
-
-
 static void __exit hdlc_module_exit(void)
 {
 	dev_remove_pack(&hdlc_packet_type);
 	unregister_netdevice_notifier(&hdlc_notifier);
 }
 
-
 module_init(hdlc_module_init);
 module_exit(hdlc_module_exit);
diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c
index cb5898f7d68c..349ca18088e8 100644
--- a/drivers/net/wan/hdlc_cisco.c
+++ b/drivers/net/wan/hdlc_cisco.c
@@ -28,13 +28,11 @@
 #define CISCO_ADDR_REPLY	1	/* Cisco address reply */
 #define CISCO_KEEPALIVE_REQ	2	/* Cisco keepalive request */
 
-
 struct hdlc_header {
 	u8 address;
 	u8 control;
 	__be16 protocol;
-}__packed;
-
+} __packed;
 
 struct cisco_packet {
 	__be32 type;		/* code */
@@ -42,11 +40,10 @@ struct cisco_packet {
 	__be32 par2;
 	__be16 rel;		/* reliability */
 	__be32 time;
-}__packed;
+} __packed;
 #define	CISCO_PACKET_LEN	18
 #define	CISCO_BIG_PACKET_LEN	20
 
-
 struct cisco_state {
 	cisco_proto settings;
 
@@ -59,16 +56,13 @@ struct cisco_state {
 	u32 rxseq; /* RX sequence number */
 };
 
-
 static int cisco_ioctl(struct net_device *dev, struct ifreq *ifr);
 
-
-static inline struct cisco_state* state(hdlc_device *hdlc)
+static inline struct cisco_state *state(hdlc_device *hdlc)
 {
 	return (struct cisco_state *)hdlc->state;
 }
 
-
 static int cisco_hard_header(struct sk_buff *skb, struct net_device *dev,
 			     u16 type, const void *daddr, const void *saddr,
 			     unsigned int len)
@@ -79,7 +73,7 @@ static int cisco_hard_header(struct sk_buff *skb, struct net_device *dev,
 #endif
 
 	skb_push(skb, sizeof(struct hdlc_header));
-	data = (struct hdlc_header*)skb->data;
+	data = (struct hdlc_header *)skb->data;
 	if (type == CISCO_KEEPALIVE)
 		data->address = CISCO_MULTICAST;
 	else
@@ -90,8 +84,6 @@ static int cisco_hard_header(struct sk_buff *skb, struct net_device *dev,
 	return sizeof(struct hdlc_header);
 }
 
-
-
 static void cisco_keepalive_send(struct net_device *dev, u32 type,
 				 __be32 par1, __be32 par2)
 {
@@ -100,13 +92,12 @@ static void cisco_keepalive_send(struct net_device *dev, u32 type,
 
 	skb = dev_alloc_skb(sizeof(struct hdlc_header) +
 			    sizeof(struct cisco_packet));
-	if (!skb) {
-		netdev_warn(dev, "Memory squeeze on %s()\n", __func__);
+	if (!skb)
 		return;
-	}
+
 	skb_reserve(skb, 4);
 	cisco_hard_header(skb, dev, CISCO_KEEPALIVE, NULL, NULL, 0);
-	data = (struct cisco_packet*)(skb->data + 4);
+	data = (struct cisco_packet *)(skb->data + 4);
 
 	data->type = htonl(type);
 	data->par1 = par1;
@@ -124,11 +115,9 @@ static void cisco_keepalive_send(struct net_device *dev, u32 type,
 	dev_queue_xmit(skb);
 }
 
-
-
 static __be16 cisco_type_trans(struct sk_buff *skb, struct net_device *dev)
 {
-	struct hdlc_header *data = (struct hdlc_header*)skb->data;
+	struct hdlc_header *data = (struct hdlc_header *)skb->data;
 
 	if (skb->len < sizeof(struct hdlc_header))
 		return cpu_to_be16(ETH_P_HDLC);
@@ -148,13 +137,12 @@ static __be16 cisco_type_trans(struct sk_buff *skb, struct net_device *dev)
 	}
 }
 
-
 static int cisco_rx(struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
 	hdlc_device *hdlc = dev_to_hdlc(dev);
 	struct cisco_state *st = state(hdlc);
-	struct hdlc_header *data = (struct hdlc_header*)skb->data;
+	struct hdlc_header *data = (struct hdlc_header *)skb->data;
 	struct cisco_packet *cisco_data;
 	struct in_device *in_dev;
 	__be32 addr, mask;
@@ -183,10 +171,10 @@ static int cisco_rx(struct sk_buff *skb)
 			goto rx_error;
 		}
 
-		cisco_data = (struct cisco_packet*)(skb->data + sizeof
+		cisco_data = (struct cisco_packet *)(skb->data + sizeof
 						    (struct hdlc_header));
 
-		switch (ntohl (cisco_data->type)) {
+		switch (ntohl(cisco_data->type)) {
 		case CISCO_ADDR_REQ: /* Stolen from syncppp.c :-) */
 			rcu_read_lock();
 			in_dev = __in_dev_get_rcu(dev);
@@ -226,6 +214,7 @@ static int cisco_rx(struct sk_buff *skb)
 				st->last_poll = jiffies;
 				if (!st->up) {
 					u32 sec, min, hrs, days;
+
 					sec = ntohl(cisco_data->time) / 1000;
 					min = sec / 60; sec -= min * 60;
 					hrs = min / 60; min -= hrs * 60;
@@ -253,8 +242,6 @@ rx_error:
 	return NET_RX_DROP;
 }
 
-
-
 static void cisco_timer(struct timer_list *t)
 {
 	struct cisco_state *st = from_timer(st, t, timer);
@@ -276,8 +263,6 @@ static void cisco_timer(struct timer_list *t)
 	add_timer(&st->timer);
 }
 
-
-
 static void cisco_start(struct net_device *dev)
 {
 	hdlc_device *hdlc = dev_to_hdlc(dev);
@@ -294,8 +279,6 @@ static void cisco_start(struct net_device *dev)
 	add_timer(&st->timer);
 }
 
-
-
 static void cisco_stop(struct net_device *dev)
 {
 	hdlc_device *hdlc = dev_to_hdlc(dev);
@@ -310,7 +293,6 @@ static void cisco_stop(struct net_device *dev)
 	spin_unlock_irqrestore(&st->lock, flags);
 }
 
-
 static struct hdlc_proto proto = {
 	.start		= cisco_start,
 	.stop		= cisco_stop,
@@ -359,7 +341,8 @@ static int cisco_ioctl(struct net_device *dev, struct ifreq *ifr)
 		    new_settings.timeout < 2)
 			return -EINVAL;
 
-		result = hdlc->attach(dev, ENCODING_NRZ,PARITY_CRC16_PR1_CCITT);
+		result = hdlc->attach(dev, ENCODING_NRZ,
+				      PARITY_CRC16_PR1_CCITT);
 		if (result)
 			return result;
 
@@ -381,21 +364,17 @@ static int cisco_ioctl(struct net_device *dev, struct ifreq *ifr)
 	return -EINVAL;
 }
 
-
 static int __init mod_init(void)
 {
 	register_hdlc_protocol(&proto);
 	return 0;
 }
 
-
-
 static void __exit mod_exit(void)
 {
 	unregister_hdlc_protocol(&proto);
 }
 
-
 module_init(mod_init);
 module_exit(mod_exit);
 
diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c
index 0720f5f92caa..72250fe0a1df 100644
--- a/drivers/net/wan/hdlc_fr.c
+++ b/drivers/net/wan/hdlc_fr.c
@@ -6,16 +6,16 @@
  * Copyright (C) 1999 - 2006 Krzysztof Halasa <khc@pm.waw.pl>
  *
 
-            Theory of PVC state
+	Theory of PVC state
 
  DCE mode:
 
  (exist,new) -> 0,0 when "PVC create" or if "link unreliable"
-         0,x -> 1,1 if "link reliable" when sending FULL STATUS
-         1,1 -> 1,0 if received FULL STATUS ACK
+	 0,x -> 1,1 if "link reliable" when sending FULL STATUS
+	 1,1 -> 1,0 if received FULL STATUS ACK
 
  (active)    -> 0 when "ifconfig PVC down" or "link unreliable" or "PVC create"
-             -> 1 when "PVC up" and (exist,new) = 1,0
+	     -> 1 when "PVC up" and (exist,new) = 1,0
 
  DTE mode:
  (exist,new,active) = FULL STATUS if "link reliable"
@@ -60,7 +60,6 @@
 #define NLPID_CCITT_ANSI_LMI	0x08
 #define NLPID_CISCO_LMI		0x09
 
-
 #define LMI_CCITT_ANSI_DLCI	   0 /* LMI DLCI */
 #define LMI_CISCO_DLCI		1023
 
@@ -86,7 +85,6 @@
 #define LMI_CCITT_CISCO_LENGTH	  13 /* LMI frame lengths */
 #define LMI_ANSI_LENGTH		  14
 
-
 struct fr_hdr {
 #if defined(__LITTLE_ENDIAN_BITFIELD)
 	unsigned ea1:	1;
@@ -111,7 +109,6 @@ struct fr_hdr {
 #endif
 } __packed;
 
-
 struct pvc_device {
 	struct net_device *frad;
 	struct net_device *main;
@@ -128,7 +125,7 @@ struct pvc_device {
 		unsigned int fecn: 1;
 		unsigned int becn: 1;
 		unsigned int bandwidth;	/* Cisco LMI reporting only */
-	}state;
+	} state;
 };
 
 struct frad_state {
@@ -149,29 +146,24 @@ struct frad_state {
 	u8 rxseq; /* RX sequence number */
 };
 
-
 static int fr_ioctl(struct net_device *dev, struct ifreq *ifr);
 
-
 static inline u16 q922_to_dlci(u8 *hdr)
 {
 	return ((hdr[0] & 0xFC) << 2) | ((hdr[1] & 0xF0) >> 4);
 }
 
-
 static inline void dlci_to_q922(u8 *hdr, u16 dlci)
 {
 	hdr[0] = (dlci >> 2) & 0xFC;
 	hdr[1] = ((dlci << 4) & 0xF0) | 0x01;
 }
 
-
-static inline struct frad_state* state(hdlc_device *hdlc)
+static inline struct frad_state *state(hdlc_device *hdlc)
 {
-	return(struct frad_state *)(hdlc->state);
+	return (struct frad_state *)(hdlc->state);
 }
 
-
 static inline struct pvc_device *find_pvc(hdlc_device *hdlc, u16 dlci)
 {
 	struct pvc_device *pvc = state(hdlc)->first_pvc;
@@ -187,7 +179,6 @@ static inline struct pvc_device *find_pvc(hdlc_device *hdlc, u16 dlci)
 	return NULL;
 }
 
-
 static struct pvc_device *add_pvc(struct net_device *dev, u16 dlci)
 {
 	hdlc_device *hdlc = dev_to_hdlc(dev);
@@ -215,13 +206,11 @@ static struct pvc_device *add_pvc(struct net_device *dev, u16 dlci)
 	return pvc;
 }
 
-
 static inline int pvc_is_used(struct pvc_device *pvc)
 {
 	return pvc->main || pvc->ether;
 }
 
-
 static inline void pvc_carrier(int on, struct pvc_device *pvc)
 {
 	if (on) {
@@ -241,7 +230,6 @@ static inline void pvc_carrier(int on, struct pvc_device *pvc)
 	}
 }
 
-
 static inline void delete_unused_pvcs(hdlc_device *hdlc)
 {
 	struct pvc_device **pvc_p = &state(hdlc)->first_pvc;
@@ -260,7 +248,6 @@ static inline void delete_unused_pvcs(hdlc_device *hdlc)
 	}
 }
 
-
 static inline struct net_device **get_dev_p(struct pvc_device *pvc,
 					    int type)
 {
@@ -270,7 +257,6 @@ static inline struct net_device **get_dev_p(struct pvc_device *pvc,
 		return &pvc->main;
 }
 
-
 static int fr_hard_header(struct sk_buff *skb, u16 dlci)
 {
 	if (!skb->dev) { /* Control packets */
@@ -334,8 +320,6 @@ static int fr_hard_header(struct sk_buff *skb, u16 dlci)
 	return 0;
 }
 
-
-
 static int pvc_open(struct net_device *dev)
 {
 	struct pvc_device *pvc = dev->ml_priv;
@@ -345,6 +329,7 @@ static int pvc_open(struct net_device *dev)
 
 	if (pvc->open_count++ == 0) {
 		hdlc_device *hdlc = dev_to_hdlc(pvc->frad);
+
 		if (state(hdlc)->settings.lmi == LMI_NONE)
 			pvc->state.active = netif_carrier_ok(pvc->frad);
 
@@ -354,14 +339,13 @@ static int pvc_open(struct net_device *dev)
 	return 0;
 }
 
-
-
 static int pvc_close(struct net_device *dev)
 {
 	struct pvc_device *pvc = dev->ml_priv;
 
 	if (--pvc->open_count == 0) {
 		hdlc_device *hdlc = dev_to_hdlc(pvc->frad);
+
 		if (state(hdlc)->settings.lmi == LMI_NONE)
 			pvc->state.active = 0;
 
@@ -373,8 +357,6 @@ static int pvc_close(struct net_device *dev)
 	return 0;
 }
 
-
-
 static int pvc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	struct pvc_device *pvc = dev->ml_priv;
@@ -465,15 +447,12 @@ static inline void fr_log_dlci_active(struct pvc_device *pvc)
 		    pvc->state.active ? "active" : "inactive");
 }
 
-
-
 static inline u8 fr_lmi_nextseq(u8 x)
 {
 	x++;
 	return x ? x : 1;
 }
 
-
 static void fr_lmi_send(struct net_device *dev, int fullrep)
 {
 	hdlc_device *hdlc = dev_to_hdlc(dev);
@@ -495,17 +474,16 @@ static void fr_lmi_send(struct net_device *dev, int fullrep)
 	}
 
 	skb = dev_alloc_skb(len);
-	if (!skb) {
-		netdev_warn(dev, "Memory squeeze on fr_lmi_send()\n");
+	if (!skb)
 		return;
-	}
+
 	memset(skb->data, 0, len);
 	skb_reserve(skb, 4);
-	if (lmi == LMI_CISCO) {
+	if (lmi == LMI_CISCO)
 		fr_hard_header(skb, LMI_CISCO_DLCI);
-	} else {
+	else
 		fr_hard_header(skb, LMI_CCITT_ANSI_DLCI);
-	}
+
 	data = skb_tail_pointer(skb);
 	data[i++] = LMI_CALLREF;
 	data[i++] = dce ? LMI_STATUS : LMI_STATUS_ENQUIRY;
@@ -569,8 +547,6 @@ static void fr_lmi_send(struct net_device *dev, int fullrep)
 	dev_queue_xmit(skb);
 }
 
-
-
 static void fr_set_link_state(int reliable, struct net_device *dev)
 {
 	hdlc_device *hdlc = dev_to_hdlc(dev);
@@ -603,7 +579,6 @@ static void fr_set_link_state(int reliable, struct net_device *dev)
 	}
 }
 
-
 static void fr_timer(struct timer_list *t)
 {
 	struct frad_state *st = from_timer(st, t, timer);
@@ -637,10 +612,10 @@ static void fr_timer(struct timer_list *t)
 		fr_set_link_state(reliable, dev);
 	}
 
-	if (state(hdlc)->settings.dce)
+	if (state(hdlc)->settings.dce) {
 		state(hdlc)->timer.expires = jiffies +
 			state(hdlc)->settings.t392 * HZ;
-	else {
+	} else {
 		if (state(hdlc)->n391cnt)
 			state(hdlc)->n391cnt--;
 
@@ -655,7 +630,6 @@ static void fr_timer(struct timer_list *t)
 	add_timer(&state(hdlc)->timer);
 }
 
-
 static int fr_lmi_recv(struct net_device *dev, struct sk_buff *skb)
 {
 	hdlc_device *hdlc = dev_to_hdlc(dev);
@@ -696,8 +670,9 @@ static int fr_lmi_recv(struct net_device *dev, struct sk_buff *skb)
 			return 1;
 		}
 		i = 7;
-	} else
+	} else {
 		i = 6;
+	}
 
 	if (skb->data[i] != (lmi == LMI_CCITT ? LMI_CCITT_REPTYPE :
 			     LMI_ANSI_CISCO_REPTYPE)) {
@@ -814,8 +789,8 @@ static int fr_lmi_recv(struct net_device *dev, struct sk_buff *skb)
 		}
 		i++;
 
-		new = !! (skb->data[i + 2] & 0x08);
-		active = !! (skb->data[i + 2] & 0x02);
+		new = !!(skb->data[i + 2] & 0x08);
+		active = !!(skb->data[i + 2] & 0x02);
 		if (lmi == LMI_CISCO) {
 			dlci = (skb->data[i] << 8) | skb->data[i + 1];
 			bw = (skb->data[i + 3] << 16) |
@@ -962,8 +937,8 @@ static int fr_rx(struct sk_buff *skb)
 		pvc->state.becn ^= 1;
 	}
 
-
-	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) {
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb) {
 		frad->stats.rx_dropped++;
 		return NET_RX_DROP;
 	}
@@ -1018,8 +993,6 @@ rx_drop:
 	return NET_RX_DROP;
 }
 
-
-
 static void fr_start(struct net_device *dev)
 {
 	hdlc_device *hdlc = dev_to_hdlc(dev);
@@ -1040,11 +1013,11 @@ static void fr_start(struct net_device *dev)
 		/* First poll after 1 s */
 		state(hdlc)->timer.expires = jiffies + HZ;
 		add_timer(&state(hdlc)->timer);
-	} else
+	} else {
 		fr_set_link_state(1, dev);
+	}
 }
 
-
 static void fr_stop(struct net_device *dev)
 {
 	hdlc_device *hdlc = dev_to_hdlc(dev);
@@ -1056,7 +1029,6 @@ static void fr_stop(struct net_device *dev)
 	fr_set_link_state(0, dev);
 }
 
-
 static void fr_close(struct net_device *dev)
 {
 	hdlc_device *hdlc = dev_to_hdlc(dev);
@@ -1071,7 +1043,6 @@ static void fr_close(struct net_device *dev)
 	}
 }
 
-
 static void pvc_setup(struct net_device *dev)
 {
 	dev->type = ARPHRD_DLCI;
@@ -1095,7 +1066,8 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type)
 	struct net_device *dev;
 	int used;
 
-	if ((pvc = add_pvc(frad, dlci)) == NULL) {
+	pvc = add_pvc(frad, dlci);
+	if (!pvc) {
 		netdev_warn(frad, "Memory squeeze on fr_add_pvc()\n");
 		return -ENOBUFS;
 	}
@@ -1121,7 +1093,7 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type)
 		dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 		eth_hw_addr_random(dev);
 	} else {
-		*(__be16*)dev->dev_addr = htons(dlci);
+		*(__be16 *)dev->dev_addr = htons(dlci);
 		dlci_to_q922(dev->broadcast, dlci);
 	}
 	dev->netdev_ops = &pvc_ops;
@@ -1147,17 +1119,17 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type)
 	return 0;
 }
 
-
-
 static int fr_del_pvc(hdlc_device *hdlc, unsigned int dlci, int type)
 {
 	struct pvc_device *pvc;
 	struct net_device *dev;
 
-	if ((pvc = find_pvc(hdlc, dlci)) == NULL)
+	pvc = find_pvc(hdlc, dlci);
+	if (!pvc)
 		return -ENOENT;
 
-	if ((dev = *get_dev_p(pvc, type)) == NULL)
+	dev = *get_dev_p(pvc, type);
+	if (!dev)
 		return -ENOENT;
 
 	if (dev->flags & IFF_UP)
@@ -1174,12 +1146,11 @@ static int fr_del_pvc(hdlc_device *hdlc, unsigned int dlci, int type)
 	return 0;
 }
 
-
-
 static void fr_destroy(struct net_device *frad)
 {
 	hdlc_device *hdlc = dev_to_hdlc(frad);
 	struct pvc_device *pvc = state(hdlc)->first_pvc;
+
 	state(hdlc)->first_pvc = NULL; /* All PVCs destroyed */
 	state(hdlc)->dce_pvc_count = 0;
 	state(hdlc)->dce_changed = 1;
@@ -1198,7 +1169,6 @@ static void fr_destroy(struct net_device *frad)
 	}
 }
 
-
 static struct hdlc_proto proto = {
 	.close		= fr_close,
 	.start		= fr_start,
@@ -1209,7 +1179,6 @@ static struct hdlc_proto proto = {
 	.module		= THIS_MODULE,
 };
 
-
 static int fr_ioctl(struct net_device *dev, struct ifreq *ifr)
 {
 	fr_proto __user *fr_s = ifr->ifr_settings.ifs_ifsu.fr;
@@ -1259,7 +1228,8 @@ static int fr_ioctl(struct net_device *dev, struct ifreq *ifr)
 		     new_settings.dce != 1))
 			return -EINVAL;
 
-		result=hdlc->attach(dev, ENCODING_NRZ,PARITY_CRC16_PR1_CCITT);
+		result = hdlc->attach(dev, ENCODING_NRZ,
+				      PARITY_CRC16_PR1_CCITT);
 		if (result)
 			return result;
 
@@ -1309,20 +1279,17 @@ static int fr_ioctl(struct net_device *dev, struct ifreq *ifr)
 	return -EINVAL;
 }
 
-
 static int __init mod_init(void)
 {
 	register_hdlc_protocol(&proto);
 	return 0;
 }
 
-
 static void __exit mod_exit(void)
 {
 	unregister_hdlc_protocol(&proto);
 }
 
-
 module_init(mod_init);
 module_exit(mod_exit);
 
diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c
index 261b53fc8e04..834be2ae3e9e 100644
--- a/drivers/net/wan/hdlc_ppp.c
+++ b/drivers/net/wan/hdlc_ppp.c
@@ -41,6 +41,7 @@ static const char *const code_names[CP_CODES] = {
 	"0", "ConfReq", "ConfAck", "ConfNak", "ConfRej", "TermReq",
 	"TermAck", "CodeRej", "ProtoRej", "EchoReq", "EchoReply", "Discard"
 };
+
 static char debug_buffer[64 + 3 * DEBUG_CP];
 #endif
 
@@ -58,7 +59,6 @@ struct cp_header {
 	__be16 len;
 };
 
-
 struct proto {
 	struct net_device *dev;
 	struct timer_list timer;
@@ -91,6 +91,7 @@ static const char *const state_names[STATES] = {
 	"Closed", "Stopped", "Stopping", "ReqSent", "AckRecv", "AckSent",
 	"Opened"
 };
+
 static const char *const event_names[EVENTS] = {
 	"Start", "Stop", "TO+", "TO-", "RCR+", "RCR-", "RCA", "RCN",
 	"RTR", "RTA", "RUC", "RXJ+", "RXJ-"
@@ -101,12 +102,12 @@ static struct sk_buff_head tx_queue; /* used when holding the spin lock */
 
 static int ppp_ioctl(struct net_device *dev, struct ifreq *ifr);
 
-static inline struct ppp* get_ppp(struct net_device *dev)
+static inline struct ppp *get_ppp(struct net_device *dev)
 {
 	return (struct ppp *)dev_to_hdlc(dev)->state;
 }
 
-static inline struct proto* get_proto(struct net_device *dev, u16 pid)
+static inline struct proto *get_proto(struct net_device *dev, u16 pid)
 {
 	struct ppp *ppp = get_ppp(dev);
 
@@ -122,7 +123,7 @@ static inline struct proto* get_proto(struct net_device *dev, u16 pid)
 	}
 }
 
-static inline const char* proto_name(u16 pid)
+static inline const char *proto_name(u16 pid)
 {
 	switch (pid) {
 	case PID_LCP:
@@ -138,7 +139,7 @@ static inline const char* proto_name(u16 pid)
 
 static __be16 ppp_type_trans(struct sk_buff *skb, struct net_device *dev)
 {
-	struct hdlc_header *data = (struct hdlc_header*)skb->data;
+	struct hdlc_header *data = (struct hdlc_header *)skb->data;
 
 	if (skb->len < sizeof(struct hdlc_header))
 		return htons(ETH_P_HDLC);
@@ -160,7 +161,6 @@ static __be16 ppp_type_trans(struct sk_buff *skb, struct net_device *dev)
 	}
 }
 
-
 static int ppp_hard_header(struct sk_buff *skb, struct net_device *dev,
 			   u16 type, const void *daddr, const void *saddr,
 			   unsigned int len)
@@ -171,7 +171,7 @@ static int ppp_hard_header(struct sk_buff *skb, struct net_device *dev,
 #endif
 
 	skb_push(skb, sizeof(struct hdlc_header));
-	data = (struct hdlc_header*)skb->data;
+	data = (struct hdlc_header *)skb->data;
 
 	data->address = HDLC_ADDR_ALLSTATIONS;
 	data->control = HDLC_CTRL_UI;
@@ -193,10 +193,10 @@ static int ppp_hard_header(struct sk_buff *skb, struct net_device *dev,
 	return sizeof(struct hdlc_header);
 }
 
-
 static void ppp_tx_flush(void)
 {
 	struct sk_buff *skb;
+
 	while ((skb = skb_dequeue(&tx_queue)) != NULL)
 		dev_queue_xmit(skb);
 }
@@ -219,10 +219,9 @@ static void ppp_tx_cp(struct net_device *dev, u16 pid, u8 code,
 
 	skb = dev_alloc_skb(sizeof(struct hdlc_header) +
 			    sizeof(struct cp_header) + magic_len + len);
-	if (!skb) {
-		netdev_warn(dev, "out of memory in ppp_tx_cp()\n");
+	if (!skb)
 		return;
-	}
+
 	skb_reserve(skb, sizeof(struct hdlc_header));
 
 	cp = skb_put(skb, sizeof(struct cp_header));
@@ -256,7 +255,6 @@ static void ppp_tx_cp(struct net_device *dev, u16 pid, u8 code,
 	skb_queue_tail(&tx_queue, skb);
 }
 
-
 /* State transition table (compare STD-51)
    Events                                   Actions
    TO+  = Timeout with counter > 0          irc = Initialize-Restart-Count
@@ -294,7 +292,6 @@ static int cp_table[EVENTS][STATES] = {
 	{    0    ,      1      ,  1  ,    1    ,  1  ,    1    ,IRC|STR|2}, /* RXJ- */
 };
 
-
 /* SCA: RCR+ must supply id, len and data
    SCN: RCR- must supply code, id, len and data
    STA: RTR must supply id
@@ -369,7 +366,6 @@ static void ppp_cp_event(struct net_device *dev, u16 pid, u16 event, u8 code,
 #endif
 }
 
-
 static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 			    unsigned int req_len, const u8 *data)
 {
@@ -378,7 +374,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 	u8 *out;
 	unsigned int len = req_len, nak_len = 0, rej_len = 0;
 
-	if (!(out = kmalloc(len, GFP_ATOMIC))) {
+	out = kmalloc(len, GFP_ATOMIC);
+	if (!out) {
 		dev->stats.rx_dropped++;
 		return;	/* out of memory, ignore CR packet */
 	}
@@ -435,7 +432,7 @@ err_out:
 
 static int ppp_rx(struct sk_buff *skb)
 {
-	struct hdlc_header *hdr = (struct hdlc_header*)skb->data;
+	struct hdlc_header *hdr = (struct hdlc_header *)skb->data;
 	struct net_device *dev = skb->dev;
 	struct ppp *ppp = get_ppp(dev);
 	struct proto *proto;
@@ -493,7 +490,7 @@ static int ppp_rx(struct sk_buff *skb)
 	if (pid == PID_LCP)
 		switch (cp->code) {
 		case LCP_PROTO_REJ:
-			pid = ntohs(*(__be16*)skb->data);
+			pid = ntohs(*(__be16 *)skb->data);
 			if (pid == PID_LCP || pid == PID_IPCP ||
 			    pid == PID_IPV6CP)
 				ppp_cp_event(dev, pid, RXJ_BAD, 0, 0,
@@ -615,7 +612,6 @@ static void ppp_timer(struct timer_list *t)
 	ppp_tx_flush();
 }
 
-
 static void ppp_start(struct net_device *dev)
 {
 	struct ppp *ppp = get_ppp(dev);
@@ -623,6 +619,7 @@ static void ppp_start(struct net_device *dev)
 
 	for (i = 0; i < IDX_COUNT; i++) {
 		struct proto *proto = &ppp->protos[i];
+
 		proto->dev = dev;
 		timer_setup(&proto->timer, ppp_timer, 0);
 		proto->state = CLOSED;
@@ -680,7 +677,8 @@ static int ppp_ioctl(struct net_device *dev, struct ifreq *ifr)
 
 		/* no settable parameters */
 
-		result = hdlc->attach(dev, ENCODING_NRZ,PARITY_CRC16_PR1_CCITT);
+		result = hdlc->attach(dev, ENCODING_NRZ,
+				      PARITY_CRC16_PR1_CCITT);
 		if (result)
 			return result;
 
@@ -707,7 +705,6 @@ static int ppp_ioctl(struct net_device *dev, struct ifreq *ifr)
 	return -EINVAL;
 }
 
-
 static int __init mod_init(void)
 {
 	skb_queue_head_init(&tx_queue);
@@ -720,7 +717,6 @@ static void __exit mod_exit(void)
 	unregister_hdlc_protocol(&proto);
 }
 
-
 module_init(mod_init);
 module_exit(mod_exit);
 
diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c
index ba8c36c7ea91..d2bf72bf3bd7 100644
--- a/drivers/net/wan/hdlc_x25.c
+++ b/drivers/net/wan/hdlc_x25.c
@@ -56,10 +56,8 @@ static void x25_connect_disconnect(struct net_device *dev, int reason, int code)
 	unsigned char *ptr;
 
 	skb = __dev_alloc_skb(1, GFP_ATOMIC | __GFP_NOMEMALLOC);
-	if (!skb) {
-		netdev_err(dev, "out of memory\n");
+	if (!skb)
 		return;
-	}
 
 	ptr = skb_put(skb, 1);
 	*ptr = code;
@@ -70,22 +68,16 @@ static void x25_connect_disconnect(struct net_device *dev, int reason, int code)
 	tasklet_schedule(&x25st->rx_tasklet);
 }
 
-
-
 static void x25_connected(struct net_device *dev, int reason)
 {
 	x25_connect_disconnect(dev, reason, X25_IFACE_CONNECT);
 }
 
-
-
 static void x25_disconnected(struct net_device *dev, int reason)
 {
 	x25_connect_disconnect(dev, reason, X25_IFACE_DISCONNECT);
 }
 
-
-
 static int x25_data_indication(struct net_device *dev, struct sk_buff *skb)
 {
 	struct x25_state *x25st = state(dev_to_hdlc(dev));
@@ -108,8 +100,6 @@ static int x25_data_indication(struct net_device *dev, struct sk_buff *skb)
 	return NET_RX_SUCCESS;
 }
 
-
-
 static void x25_data_transmit(struct net_device *dev, struct sk_buff *skb)
 {
 	hdlc_device *hdlc = dev_to_hdlc(dev);
@@ -123,8 +113,6 @@ static void x25_data_transmit(struct net_device *dev, struct sk_buff *skb)
 	hdlc->xmit(skb, dev); /* Ignore return value :-( */
 }
 
-
-
 static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	hdlc_device *hdlc = dev_to_hdlc(dev);
@@ -149,13 +137,15 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev)
 	switch (skb->data[0]) {
 	case X25_IFACE_DATA:	/* Data to be transmitted */
 		skb_pull(skb, 1);
-		if ((result = lapb_data_request(dev, skb)) != LAPB_OK)
+		result = lapb_data_request(dev, skb);
+		if (result != LAPB_OK)
 			dev_kfree_skb(skb);
 		spin_unlock_bh(&x25st->up_lock);
 		return NETDEV_TX_OK;
 
 	case X25_IFACE_CONNECT:
-		if ((result = lapb_connect_request(dev))!= LAPB_OK) {
+		result = lapb_connect_request(dev);
+		if (result != LAPB_OK) {
 			if (result == LAPB_CONNECTED)
 				/* Send connect confirm. msg to level 3 */
 				x25_connected(dev, 0);
@@ -166,7 +156,8 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev)
 		break;
 
 	case X25_IFACE_DISCONNECT:
-		if ((result = lapb_disconnect_request(dev)) != LAPB_OK) {
+		result = lapb_disconnect_request(dev);
+		if (result != LAPB_OK) {
 			if (result == LAPB_NOTCONNECTED)
 				/* Send disconnect confirm. msg to level 3 */
 				x25_disconnected(dev, 0);
@@ -185,8 +176,6 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
-
-
 static int x25_open(struct net_device *dev)
 {
 	static const struct lapb_register_struct cb = {
@@ -232,8 +221,6 @@ static int x25_open(struct net_device *dev)
 	return 0;
 }
 
-
-
 static void x25_close(struct net_device *dev)
 {
 	hdlc_device *hdlc = dev_to_hdlc(dev);
@@ -247,15 +234,14 @@ static void x25_close(struct net_device *dev)
 	tasklet_kill(&x25st->rx_tasklet);
 }
 
-
-
 static int x25_rx(struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
 	hdlc_device *hdlc = dev_to_hdlc(dev);
 	struct x25_state *x25st = state(hdlc);
 
-	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) {
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb) {
 		dev->stats.rx_dropped++;
 		return NET_RX_DROP;
 	}
@@ -279,7 +265,6 @@ static int x25_rx(struct sk_buff *skb)
 	return NET_RX_DROP;
 }
 
-
 static struct hdlc_proto proto = {
 	.open		= x25_open,
 	.close		= x25_close,
@@ -289,7 +274,6 @@ static struct hdlc_proto proto = {
 	.module		= THIS_MODULE,
 };
 
-
 static int x25_ioctl(struct net_device *dev, struct ifreq *ifr)
 {
 	x25_hdlc_proto __user *x25_s = ifr->ifr_settings.ifs_ifsu.x25;
@@ -326,35 +310,36 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr)
 			new_settings.t1 = 3;
 			new_settings.t2 = 1;
 			new_settings.n2 = 10;
-		}
-		else {
+		} else {
 			if (copy_from_user(&new_settings, x25_s, size))
 				return -EFAULT;
 
 			if ((new_settings.dce != 0 &&
-			new_settings.dce != 1) ||
-			(new_settings.modulo != 8 &&
-			new_settings.modulo != 128) ||
-			new_settings.window < 1 ||
-			(new_settings.modulo == 8 &&
-			new_settings.window > 7) ||
-			(new_settings.modulo == 128 &&
-			new_settings.window > 127) ||
-			new_settings.t1 < 1 ||
-			new_settings.t1 > 255 ||
-			new_settings.t2 < 1 ||
-			new_settings.t2 > 255 ||
-			new_settings.n2 < 1 ||
-			new_settings.n2 > 255)
+			     new_settings.dce != 1) ||
+			    (new_settings.modulo != 8 &&
+			     new_settings.modulo != 128) ||
+			    new_settings.window < 1 ||
+			    (new_settings.modulo == 8 &&
+			     new_settings.window > 7) ||
+			    (new_settings.modulo == 128 &&
+			     new_settings.window > 127) ||
+			    new_settings.t1 < 1 ||
+			    new_settings.t1 > 255 ||
+			    new_settings.t2 < 1 ||
+			    new_settings.t2 > 255 ||
+			    new_settings.n2 < 1 ||
+			    new_settings.n2 > 255)
 				return -EINVAL;
 		}
 
-		result=hdlc->attach(dev, ENCODING_NRZ,PARITY_CRC16_PR1_CCITT);
+		result = hdlc->attach(dev, ENCODING_NRZ,
+				      PARITY_CRC16_PR1_CCITT);
 		if (result)
 			return result;
 
-		if ((result = attach_hdlc_protocol(dev, &proto,
-						   sizeof(struct x25_state))))
+		result = attach_hdlc_protocol(dev, &proto,
+					      sizeof(struct x25_state));
+		if (result)
 			return result;
 
 		memcpy(&state(hdlc)->settings, &new_settings, size);
@@ -380,21 +365,17 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr)
 	return -EINVAL;
 }
 
-
 static int __init mod_init(void)
 {
 	register_hdlc_protocol(&proto);
 	return 0;
 }
 
-
-
 static void __exit mod_exit(void)
 {
 	unregister_hdlc_protocol(&proto);
 }
 
-
 module_init(mod_init);
 module_exit(mod_exit);
 
diff --git a/drivers/net/wan/hostess_sv11.c b/drivers/net/wan/hostess_sv11.c
index 6c05c4c8914a..fd61a7cc4fdf 100644
--- a/drivers/net/wan/hostess_sv11.c
+++ b/drivers/net/wan/hostess_sv11.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/*
- *	Comtrol SV11 card driver
+/*	Comtrol SV11 card driver
  *
  *	This is a slightly odd Z85230 synchronous driver. All you need to
  *	know basically is
@@ -9,7 +8,7 @@
  *
  *	It supports DMA using two DMA channels in SYNC mode. The driver doesn't
  *	use these facilities
- *	
+ *
  *	The control port is at io+1, the data at io+3 and turning off the DMA
  *	is done by writing 0 to io+4
  *
@@ -44,17 +43,15 @@
 
 static int dma;
 
-/*
- *	Network driver support routines
+/*	Network driver support routines
  */
 
-static inline struct z8530_dev* dev_to_sv(struct net_device *dev)
+static inline struct z8530_dev *dev_to_sv(struct net_device *dev)
 {
 	return (struct z8530_dev *)dev_to_hdlc(dev)->priv;
 }
 
-/*
- *	Frame receive. Simple for our card as we do HDLC and there
+/*	Frame receive. Simple for our card as we do HDLC and there
  *	is no funny garbage involved
  */
 
@@ -65,15 +62,13 @@ static void hostess_input(struct z8530_channel *c, struct sk_buff *skb)
 	skb->protocol = hdlc_type_trans(skb, c->netdevice);
 	skb_reset_mac_header(skb);
 	skb->dev = c->netdevice;
-	/*
-	 *	Send it to the PPP layer. We don't have time to process
+	/*	Send it to the PPP layer. We don't have time to process
 	 *	it right now.
 	 */
 	netif_rx(skb);
 }
 
-/*
- *	We've been placed in the UP state
+/*	We've been placed in the UP state
  */
 
 static int hostess_open(struct net_device *d)
@@ -81,19 +76,18 @@ static int hostess_open(struct net_device *d)
 	struct z8530_dev *sv11 = dev_to_sv(d);
 	int err = -1;
 
-	/*
-	 *	Link layer up
+	/*	Link layer up
 	 */
 	switch (dma) {
-		case 0:
-			err = z8530_sync_open(d, &sv11->chanA);
-			break;
-		case 1:
-			err = z8530_sync_dma_open(d, &sv11->chanA);
-			break;
-		case 2:
-			err = z8530_sync_txdma_open(d, &sv11->chanA);
-			break;
+	case 0:
+		err = z8530_sync_open(d, &sv11->chanA);
+		break;
+	case 1:
+		err = z8530_sync_dma_open(d, &sv11->chanA);
+		break;
+	case 2:
+		err = z8530_sync_txdma_open(d, &sv11->chanA);
+		break;
 	}
 
 	if (err)
@@ -102,15 +96,15 @@ static int hostess_open(struct net_device *d)
 	err = hdlc_open(d);
 	if (err) {
 		switch (dma) {
-			case 0:
-				z8530_sync_close(d, &sv11->chanA);
-				break;
-			case 1:
-				z8530_sync_dma_close(d, &sv11->chanA);
-				break;
-			case 2:
-				z8530_sync_txdma_close(d, &sv11->chanA);
-				break;
+		case 0:
+			z8530_sync_close(d, &sv11->chanA);
+			break;
+		case 1:
+			z8530_sync_dma_close(d, &sv11->chanA);
+			break;
+		case 2:
+			z8530_sync_txdma_close(d, &sv11->chanA);
+			break;
 		}
 		return err;
 	}
@@ -127,8 +121,7 @@ static int hostess_open(struct net_device *d)
 static int hostess_close(struct net_device *d)
 {
 	struct z8530_dev *sv11 = dev_to_sv(d);
-	/*
-	 *	Discard new frames
+	/*	Discard new frames
 	 */
 	sv11->chanA.rx_function = z8530_null_rx;
 
@@ -136,32 +129,29 @@ static int hostess_close(struct net_device *d)
 	netif_stop_queue(d);
 
 	switch (dma) {
-		case 0:
-			z8530_sync_close(d, &sv11->chanA);
-			break;
-		case 1:
-			z8530_sync_dma_close(d, &sv11->chanA);
-			break;
-		case 2:
-			z8530_sync_txdma_close(d, &sv11->chanA);
-			break;
+	case 0:
+		z8530_sync_close(d, &sv11->chanA);
+		break;
+	case 1:
+		z8530_sync_dma_close(d, &sv11->chanA);
+		break;
+	case 2:
+		z8530_sync_txdma_close(d, &sv11->chanA);
+		break;
 	}
 	return 0;
 }
 
 static int hostess_ioctl(struct net_device *d, struct ifreq *ifr, int cmd)
 {
-	/* struct z8530_dev *sv11=dev_to_sv(d);
-	   z8530_ioctl(d,&sv11->chanA,ifr,cmd) */
 	return hdlc_ioctl(d, ifr, cmd);
 }
 
-/*
- *	Passed network frames, fire them downwind.
+/*	Passed network frames, fire them downwind.
  */
 
 static netdev_tx_t hostess_queue_xmit(struct sk_buff *skb,
-					    struct net_device *d)
+				      struct net_device *d)
 {
 	return z8530_queue_xmit(&dev_to_sv(d)->chanA, skb);
 }
@@ -174,8 +164,7 @@ static int hostess_attach(struct net_device *dev, unsigned short encoding,
 	return -EINVAL;
 }
 
-/*
- *	Description block for a Comtrol Hostess SV11 card
+/*	Description block for a Comtrol Hostess SV11 card
  */
 
 static const struct net_device_ops hostess_ops = {
@@ -189,8 +178,7 @@ static struct z8530_dev *sv11_init(int iobase, int irq)
 {
 	struct z8530_dev *sv;
 	struct net_device *netdev;
-	/*
-	 *	Get the needed I/O space
+	/*	Get the needed I/O space
 	 */
 
 	if (!request_region(iobase, 8, "Comtrol SV11")) {
@@ -202,8 +190,7 @@ static struct z8530_dev *sv11_init(int iobase, int irq)
 	if (!sv)
 		goto err_kzalloc;
 
-	/*
-	 *	Stuff in the I/O addressing
+	/*	Stuff in the I/O addressing
 	 */
 
 	sv->active = 0;
@@ -218,7 +205,8 @@ static struct z8530_dev *sv11_init(int iobase, int irq)
 	outb(0, iobase + 4);		/* DMA off */
 
 	/* We want a fast IRQ for this device. Actually we'd like an even faster
-	   IRQ ;) - This is one driver RtLinux is made for */
+	 * IRQ ;) - This is one driver RtLinux is made for
+	 */
 
 	if (request_irq(irq, z8530_interrupt, 0,
 			"Hostess SV11", sv) < 0) {
@@ -232,8 +220,7 @@ static struct z8530_dev *sv11_init(int iobase, int irq)
 	sv->chanB.dev = sv;
 
 	if (dma) {
-		/*
-		 *	You can have DMA off or 1 and 3 thats the lot
+		/*	You can have DMA off or 1 and 3 thats the lot
 		 *	on the Comtrol.
 		 */
 		sv->chanA.txdma = 3;
@@ -248,11 +235,11 @@ static struct z8530_dev *sv11_init(int iobase, int irq)
 	}
 
 	/* Kill our private IRQ line the hostess can end up chattering
-	   until the configuration is set */
+	 * until the configuration is set
+	 */
 	disable_irq(irq);
 
-	/*
-	 *	Begin normal initialise
+	/*	Begin normal initialise
 	 */
 
 	if (z8530_init(sv)) {
@@ -268,8 +255,7 @@ static struct z8530_dev *sv11_init(int iobase, int irq)
 
 	enable_irq(irq);
 
-	/*
-	 *	Now we can take the IRQ
+	/*	Now we can take the IRQ
 	 */
 
 	sv->chanA.netdevice = netdev = alloc_hdlcdev(sv);
@@ -340,7 +326,8 @@ static struct z8530_dev *sv11_unit;
 
 int init_module(void)
 {
-	if ((sv11_unit = sv11_init(io, irq)) == NULL)
+	sv11_unit = sv11_init(io, irq);
+	if (!sv11_unit)
 		return -ENODEV;
 	return 0;
 }
diff --git a/drivers/net/wan/ixp4xx_hss.c b/drivers/net/wan/ixp4xx_hss.c
index ecea09fd21cb..e97521138f7e 100644
--- a/drivers/net/wan/ixp4xx_hss.c
+++ b/drivers/net/wan/ixp4xx_hss.c
@@ -83,7 +83,6 @@
 #define PKT_HDLC_CRC_32			0x2 /* default = CRC-16 */
 #define PKT_HDLC_MSB_ENDIAN		0x4 /* default = LE */
 
-
 /* hss_config, PCRs */
 /* Frame sync sampling, default = active low */
 #define PCR_FRM_SYNC_ACTIVE_HIGH	0x40000000
@@ -150,26 +149,24 @@
 /* HSS number, default = 0 (first) */
 #define CCR_SECOND_HSS			0x01000000
 
-
 /* hss_config, clkCR: main:10, num:10, denom:12 */
-#define CLK42X_SPEED_EXP	((0x3FF << 22) | (  2 << 12) |   15) /*65 KHz*/
-
-#define CLK42X_SPEED_512KHZ	((  130 << 22) | (  2 << 12) |   15)
-#define CLK42X_SPEED_1536KHZ	((   43 << 22) | ( 18 << 12) |   47)
-#define CLK42X_SPEED_1544KHZ	((   43 << 22) | ( 33 << 12) |  192)
-#define CLK42X_SPEED_2048KHZ	((   32 << 22) | ( 34 << 12) |   63)
-#define CLK42X_SPEED_4096KHZ	((   16 << 22) | ( 34 << 12) |  127)
-#define CLK42X_SPEED_8192KHZ	((    8 << 22) | ( 34 << 12) |  255)
-
-#define CLK46X_SPEED_512KHZ	((  130 << 22) | ( 24 << 12) |  127)
-#define CLK46X_SPEED_1536KHZ	((   43 << 22) | (152 << 12) |  383)
-#define CLK46X_SPEED_1544KHZ	((   43 << 22) | ( 66 << 12) |  385)
-#define CLK46X_SPEED_2048KHZ	((   32 << 22) | (280 << 12) |  511)
-#define CLK46X_SPEED_4096KHZ	((   16 << 22) | (280 << 12) | 1023)
-#define CLK46X_SPEED_8192KHZ	((    8 << 22) | (280 << 12) | 2047)
-
-/*
- * HSS_CONFIG_CLOCK_CR register consists of 3 parts:
+#define CLK42X_SPEED_EXP	((0x3FF << 22) | (2 << 12) |   15) /*65 KHz*/
+
+#define CLK42X_SPEED_512KHZ	((130 << 22) | (2 << 12) |   15)
+#define CLK42X_SPEED_1536KHZ	((43 << 22) | (18 << 12) |   47)
+#define CLK42X_SPEED_1544KHZ	((43 << 22) | (33 << 12) |  192)
+#define CLK42X_SPEED_2048KHZ	((32 << 22) | (34 << 12) |   63)
+#define CLK42X_SPEED_4096KHZ	((16 << 22) | (34 << 12) |  127)
+#define CLK42X_SPEED_8192KHZ	((8 << 22) | (34 << 12) |  255)
+
+#define CLK46X_SPEED_512KHZ	((130 << 22) | (24 << 12) |  127)
+#define CLK46X_SPEED_1536KHZ	((43 << 22) | (152 << 12) |  383)
+#define CLK46X_SPEED_1544KHZ	((43 << 22) | (66 << 12) |  385)
+#define CLK46X_SPEED_2048KHZ	((32 << 22) | (280 << 12) |  511)
+#define CLK46X_SPEED_4096KHZ	((16 << 22) | (280 << 12) | 1023)
+#define CLK46X_SPEED_8192KHZ	((8 << 22) | (280 << 12) | 2047)
+
+/* HSS_CONFIG_CLOCK_CR register consists of 3 parts:
  *     A (10 bits), B (10 bits) and C (12 bits).
  * IXP42x HSS clock generator operation (verified with an oscilloscope):
  * Each clock bit takes 7.5 ns (1 / 133.xx MHz).
@@ -208,7 +205,6 @@
 #define HSS_CONFIG_TX_LUT	0x18 /* channel look-up tables */
 #define HSS_CONFIG_RX_LUT	0x38
 
-
 /* NPE command codes */
 /* writes the ConfigWord value to the location specified by offset */
 #define PORT_CONFIG_WRITE		0x40
@@ -220,7 +216,8 @@
 #define PORT_ERROR_READ			0x42
 
 /* triggers the NPE to reset internal status and enable the HssPacketized
-   operation for the flow specified by pPipe */
+ * operation for the flow specified by pPipe
+ */
 #define PKT_PIPE_FLOW_ENABLE		0x50
 #define PKT_PIPE_FLOW_DISABLE		0x51
 #define PKT_NUM_PIPES_WRITE		0x52
@@ -235,12 +232,12 @@
 #define ERR_HDLC_ALIGN		2 /* HDLC alignment error */
 #define ERR_HDLC_FCS		3 /* HDLC Frame Check Sum error */
 #define ERR_RXFREE_Q_EMPTY	4 /* RX-free queue became empty while receiving
-				     this packet (if buf_len < pkt_len) */
+				   * this packet (if buf_len < pkt_len)
+				   */
 #define ERR_HDLC_TOO_LONG	5 /* HDLC frame size too long */
 #define ERR_HDLC_ABORT		6 /* abort sequence received */
 #define ERR_DISCONNECTING	7 /* disconnect is in progress */
 
-
 #ifdef __ARMEB__
 typedef struct sk_buff buffer_t;
 #define free_buffer dev_kfree_skb
@@ -308,7 +305,6 @@ struct desc {
 	u32 __reserved1[4];
 };
 
-
 #define rx_desc_phys(port, n)	((port)->desc_tab_phys +		\
 				 (n) * sizeof(struct desc))
 #define rx_desc_ptr(port, n)	(&(port)->desc_tab[n])
@@ -327,7 +323,7 @@ static DEFINE_SPINLOCK(npe_lock);
 
 static const struct {
 	int tx, txdone, rx, rxfree;
-}queue_ids[2] = {{HSS0_PKT_TX0_QUEUE, HSS0_PKT_TXDONE_QUEUE, HSS0_PKT_RX_QUEUE,
+} queue_ids[2] = {{HSS0_PKT_TX0_QUEUE, HSS0_PKT_TXDONE_QUEUE, HSS0_PKT_RX_QUEUE,
 		  HSS0_PKT_RXFREE0_QUEUE},
 		 {HSS1_PKT_TX0_QUEUE, HSS1_PKT_TXDONE_QUEUE, HSS1_PKT_RX_QUEUE,
 		  HSS1_PKT_RXFREE0_QUEUE},
@@ -337,7 +333,7 @@ static const struct {
  * utility functions
  ****************************************************************************/
 
-static inline struct port* dev_to_port(struct net_device *dev)
+static inline struct port *dev_to_port(struct net_device *dev)
 {
 	return dev_to_hdlc(dev)->priv;
 }
@@ -346,6 +342,7 @@ static inline struct port* dev_to_port(struct net_device *dev)
 static inline void memcpy_swab32(u32 *dest, u32 *src, int cnt)
 {
 	int i;
+
 	for (i = 0; i < cnt; i++)
 		dest[i] = swab32(src[i]);
 }
@@ -355,9 +352,10 @@ static inline void memcpy_swab32(u32 *dest, u32 *src, int cnt)
  * HSS access
  ****************************************************************************/
 
-static void hss_npe_send(struct port *port, struct msg *msg, const char* what)
+static void hss_npe_send(struct port *port, struct msg *msg, const char *what)
 {
-	u32 *val = (u32*)msg;
+	u32 *val = (u32 *)msg;
+
 	if (npe_send_message(port->npe, msg, what)) {
 		pr_crit("HSS-%i: unable to send command [%08X:%08X] to %s\n",
 			port->id, val[0], val[1], npe_name(port->npe));
@@ -513,10 +511,12 @@ static int hss_load_firmware(struct port *port)
 	if (port->initialized)
 		return 0;
 
-	if (!npe_running(port->npe) &&
-	    (err = npe_load_firmware(port->npe, npe_name(port->npe),
-				     port->dev)))
-		return err;
+	if (!npe_running(port->npe)) {
+		err = npe_load_firmware(port->npe, npe_name(port->npe),
+					port->dev);
+		if (err)
+			return err;
+	}
 
 	/* HDLC mode configuration */
 	memset(&msg, 0, sizeof(msg));
@@ -567,7 +567,6 @@ static inline void debug_pkt(struct net_device *dev, const char *func,
 #endif
 }
 
-
 static inline void debug_desc(u32 phys, struct desc *desc)
 {
 #if DEBUG_DESC
@@ -583,7 +582,8 @@ static inline int queue_get_desc(unsigned int queue, struct port *port,
 	u32 phys, tab_phys, n_desc;
 	struct desc *tab;
 
-	if (!(phys = qmgr_get_entry(queue)))
+	phys = qmgr_get_entry(queue);
+	if (!phys)
 		return -1;
 
 	BUG_ON(phys & 0x1F);
@@ -603,10 +603,10 @@ static inline void queue_put_desc(unsigned int queue, u32 phys,
 	BUG_ON(phys & 0x1F);
 	qmgr_put_entry(queue, phys);
 	/* Don't check for queue overflow here, we've allocated sufficient
-	   length and queues >= 32 don't support this check anyway. */
+	 * length and queues >= 32 don't support this check anyway.
+	 */
 }
 
-
 static inline void dma_unmap_tx(struct port *port, struct desc *desc)
 {
 #ifdef __ARMEB__
@@ -619,7 +619,6 @@ static inline void dma_unmap_tx(struct port *port, struct desc *desc)
 #endif
 }
 
-
 static void hss_hdlc_set_carrier(void *pdev, int carrier)
 {
 	struct net_device *netdev = pdev;
@@ -670,7 +669,8 @@ static int hss_hdlc_poll(struct napi_struct *napi, int budget)
 		u32 phys;
 #endif
 
-		if ((n = queue_get_desc(rxq, port, 0)) < 0) {
+		n = queue_get_desc(rxq, port, 0);
+		if (n < 0) {
 #if DEBUG_RX
 			printk(KERN_DEBUG "%s: hss_hdlc_poll"
 			       " napi_complete\n", dev->name);
@@ -705,7 +705,8 @@ static int hss_hdlc_poll(struct napi_struct *napi, int budget)
 		switch (desc->status) {
 		case 0:
 #ifdef __ARMEB__
-			if ((skb = netdev_alloc_skb(dev, RX_SIZE)) != NULL) {
+			skb = netdev_alloc_skb(dev, RX_SIZE);
+			if (skb) {
 				phys = dma_map_single(&dev->dev, skb->data,
 						      RX_SIZE,
 						      DMA_FROM_DEVICE);
@@ -784,7 +785,6 @@ static int hss_hdlc_poll(struct napi_struct *napi, int budget)
 	return received;	/* not all work done */
 }
 
-
 static void hss_hdlc_txdone_irq(void *pdev)
 {
 	struct net_device *dev = pdev;
@@ -854,7 +854,8 @@ static int hss_hdlc_xmit(struct sk_buff *skb, struct net_device *dev)
 #else
 	offset = (int)skb->data & 3; /* keep 32-bit alignment */
 	bytes = ALIGN(offset + len, 4);
-	if (!(mem = kmalloc(bytes, GFP_ATOMIC))) {
+	mem = kmalloc(bytes, GFP_ATOMIC);
+	if (!mem) {
 		dev_kfree_skb(skb);
 		dev->stats.tx_dropped++;
 		return NETDEV_TX_OK;
@@ -910,7 +911,6 @@ static int hss_hdlc_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
-
 static int request_hdlc_queues(struct port *port)
 {
 	int err;
@@ -974,8 +974,9 @@ static int init_hdlc_queues(struct port *port)
 			return -ENOMEM;
 	}
 
-	if (!(port->desc_tab = dma_pool_alloc(dma_pool, GFP_KERNEL,
-					      &port->desc_tab_phys)))
+	port->desc_tab = dma_pool_alloc(dma_pool, GFP_KERNEL,
+					&port->desc_tab_phys);
+	if (!port->desc_tab)
 		return -ENOMEM;
 	memset(port->desc_tab, 0, POOL_ALLOC_SIZE);
 	memset(port->rx_buff_tab, 0, sizeof(port->rx_buff_tab)); /* tables */
@@ -987,11 +988,13 @@ static int init_hdlc_queues(struct port *port)
 		buffer_t *buff;
 		void *data;
 #ifdef __ARMEB__
-		if (!(buff = netdev_alloc_skb(port->netdev, RX_SIZE)))
+		buff = netdev_alloc_skb(port->netdev, RX_SIZE);
+		if (!buff)
 			return -ENOMEM;
 		data = buff->data;
 #else
-		if (!(buff = kmalloc(RX_SIZE, GFP_KERNEL)))
+		buff = kmalloc(RX_SIZE, GFP_KERNEL);
+		if (!buff)
 			return -ENOMEM;
 		data = buff;
 #endif
@@ -1016,6 +1019,7 @@ static void destroy_hdlc_queues(struct port *port)
 		for (i = 0; i < RX_DESCS; i++) {
 			struct desc *desc = rx_desc_ptr(port, i);
 			buffer_t *buff = port->rx_buff_tab[i];
+
 			if (buff) {
 				dma_unmap_single(&port->netdev->dev,
 						 desc->data, RX_SIZE,
@@ -1026,6 +1030,7 @@ static void destroy_hdlc_queues(struct port *port)
 		for (i = 0; i < TX_DESCS; i++) {
 			struct desc *desc = tx_desc_ptr(port, i);
 			buffer_t *buff = port->tx_buff_tab[i];
+
 			if (buff) {
 				dma_unmap_tx(port, desc);
 				free_buffer(buff);
@@ -1047,23 +1052,29 @@ static int hss_hdlc_open(struct net_device *dev)
 	unsigned long flags;
 	int i, err = 0;
 
-	if ((err = hdlc_open(dev)))
+	err = hdlc_open(dev);
+	if (err)
 		return err;
 
-	if ((err = hss_load_firmware(port)))
+	err = hss_load_firmware(port);
+	if (err)
 		goto err_hdlc_close;
 
-	if ((err = request_hdlc_queues(port)))
+	err = request_hdlc_queues(port);
+	if (err)
 		goto err_hdlc_close;
 
-	if ((err = init_hdlc_queues(port)))
+	err = init_hdlc_queues(port);
+	if (err)
 		goto err_destroy_queues;
 
 	spin_lock_irqsave(&npe_lock, flags);
-	if (port->plat->open)
-		if ((err = port->plat->open(port->id, dev,
-					    hss_hdlc_set_carrier)))
+	if (port->plat->open) {
+		err = port->plat->open(port->id, dev, hss_hdlc_set_carrier);
+		if (err)
 			goto err_unlock;
+	}
+
 	spin_unlock_irqrestore(&npe_lock, flags);
 
 	/* Populate queues with buffers, no failure after this point */
@@ -1160,7 +1171,6 @@ static int hss_hdlc_close(struct net_device *dev)
 	return 0;
 }
 
-
 static int hss_hdlc_attach(struct net_device *dev, unsigned short encoding,
 			   unsigned short parity)
 {
@@ -1169,7 +1179,7 @@ static int hss_hdlc_attach(struct net_device *dev, unsigned short encoding,
 	if (encoding != ENCODING_NRZ)
 		return -EINVAL;
 
-	switch(parity) {
+	switch (parity) {
 	case PARITY_CRC16_PR1_CCITT:
 		port->hdlc_cfg = 0;
 		return 0;
@@ -1224,6 +1234,7 @@ static void find_best_clock(u32 timer_freq, u32 rate, u32 *best, u32 *reg)
 
 	for (b = 0; b < 0x400; b++) {
 		u64 c = (b + 1) * (u64)rate;
+
 		do_div(c, timer_freq - rate * a);
 		c--;
 		if (c >= 0xFFF) { /* 12-bit - no need to check more 'b's */
@@ -1255,7 +1266,7 @@ static int hss_hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	if (cmd != SIOCWANDEV)
 		return hdlc_ioctl(dev, ifr, cmd);
 
-	switch(ifr->ifr_settings.type) {
+	switch (ifr->ifr_settings.type) {
 	case IF_GET_IFACE:
 		ifr->ifr_settings.type = IF_IFACE_V35;
 		if (ifr->ifr_settings.size < size) {
@@ -1272,7 +1283,7 @@ static int hss_hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 
 	case IF_IFACE_SYNC_SERIAL:
 	case IF_IFACE_V35:
-		if(!capable(CAP_NET_ADMIN))
+		if (!capable(CAP_NET_ADMIN))
 			return -EPERM;
 		if (copy_from_user(&new_line, line, size))
 			return -EFAULT;
@@ -1288,11 +1299,11 @@ static int hss_hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			return -EINVAL;
 
 		port->clock_type = clk; /* Update settings */
-		if (clk == CLOCK_INT)
+		if (clk == CLOCK_INT) {
 			find_best_clock(port->plat->timer_freq,
 					new_line.clock_rate,
 					&port->clock_rate, &port->clock_reg);
-		else {
+		} else {
 			port->clock_rate = 0;
 			port->clock_reg = CLK42X_SPEED_2048KHZ;
 		}
@@ -1334,15 +1345,19 @@ static int hss_init_one(struct platform_device *pdev)
 	hdlc_device *hdlc;
 	int err;
 
-	if ((port = kzalloc(sizeof(*port), GFP_KERNEL)) == NULL)
+	port = kzalloc(sizeof(*port), GFP_KERNEL);
+	if (!port)
 		return -ENOMEM;
 
-	if ((port->npe = npe_request(0)) == NULL) {
+	port->npe = npe_request(0);
+	if (!port->npe) {
 		err = -ENODEV;
 		goto err_free;
 	}
 
-	if ((port->netdev = dev = alloc_hdlcdev(port)) == NULL) {
+	dev = alloc_hdlcdev(port);
+	port->netdev = alloc_hdlcdev(port);
+	if (!port->netdev) {
 		err = -ENOMEM;
 		goto err_plat;
 	}
@@ -1361,7 +1376,8 @@ static int hss_init_one(struct platform_device *pdev)
 	port->plat = pdev->dev.platform_data;
 	netif_napi_add(dev, &port->napi, hss_hdlc_poll, NAPI_WEIGHT);
 
-	if ((err = register_hdlc_device(dev)))
+	err = register_hdlc_device(dev);
+	if (err)
 		goto err_free_netdev;
 
 	platform_set_drvdata(pdev, port);
diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c
index 59646865a3a4..89d31adc3809 100644
--- a/drivers/net/wan/lapbether.c
+++ b/drivers/net/wan/lapbether.c
@@ -6,7 +6,7 @@
  *
  *	This is a "pseudo" network driver to allow LAPB over Ethernet.
  *
- *	This driver can use any ethernet destination address, and can be 
+ *	This driver can use any ethernet destination address, and can be
  *	limited to accept frames from one dedicated ethernet card only.
  *
  *	History
@@ -44,7 +44,8 @@
 static const u8 bcast_addr[6] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF };
 
 /* If this number is made larger, check that the temporary string buffer
- * in lapbeth_new_device is large enough to store the probe device name.*/
+ * in lapbeth_new_device is large enough to store the probe device name.
+ */
 #define MAXLAPBDEV 100
 
 struct lapbethdev {
@@ -64,15 +65,14 @@ static void lapbeth_disconnected(struct net_device *dev, int reason);
 
 /* ------------------------------------------------------------------------ */
 
-/*
- *	Get the LAPB device for the ethernet device
+/*	Get the LAPB device for the ethernet device
  */
 static struct lapbethdev *lapbeth_get_x25_dev(struct net_device *dev)
 {
 	struct lapbethdev *lapbeth;
 
 	list_for_each_entry_rcu(lapbeth, &lapbeth_devices, node, lockdep_rtnl_is_held()) {
-		if (lapbeth->ethdev == dev) 
+		if (lapbeth->ethdev == dev)
 			return lapbeth;
 	}
 	return NULL;
@@ -105,10 +105,10 @@ static int lapbeth_napi_poll(struct napi_struct *napi, int budget)
 	return processed;
 }
 
-/*
- *	Receive a LAPB frame via an ethernet interface.
+/*	Receive a LAPB frame via an ethernet interface.
  */
-static int lapbeth_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev)
+static int lapbeth_rcv(struct sk_buff *skb, struct net_device *dev,
+		       struct packet_type *ptype, struct net_device *orig_dev)
 {
 	int len, err;
 	struct lapbethdev *lapbeth;
@@ -116,7 +116,8 @@ static int lapbeth_rcv(struct sk_buff *skb, struct net_device *dev, struct packe
 	if (dev_net(dev) != &init_net)
 		goto drop;
 
-	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
 		return NET_RX_DROP;
 
 	if (!pskb_may_pull(skb, 2))
@@ -137,7 +138,8 @@ static int lapbeth_rcv(struct sk_buff *skb, struct net_device *dev, struct packe
 	skb_pull(skb, 2);	/* Remove the length bytes */
 	skb_trim(skb, len);	/* Set the length of the data */
 
-	if ((err = lapb_data_received(lapbeth->axdev, skb)) != LAPB_OK) {
+	err = lapb_data_received(lapbeth->axdev, skb);
+	if (err != LAPB_OK) {
 		printk(KERN_DEBUG "lapbether: lapb_data_received err - %d\n", err);
 		goto drop_unlock;
 	}
@@ -177,11 +179,10 @@ static int lapbeth_data_indication(struct net_device *dev, struct sk_buff *skb)
 	return NET_RX_SUCCESS;
 }
 
-/*
- *	Send a LAPB frame via an ethernet interface
+/*	Send a LAPB frame via an ethernet interface
  */
 static netdev_tx_t lapbeth_xmit(struct sk_buff *skb,
-				      struct net_device *dev)
+				struct net_device *dev)
 {
 	struct lapbethdev *lapbeth = netdev_priv(dev);
 	int err;
@@ -219,7 +220,8 @@ static netdev_tx_t lapbeth_xmit(struct sk_buff *skb,
 
 	skb_pull(skb, 1);
 
-	if ((err = lapb_data_request(dev, skb)) != LAPB_OK) {
+	err = lapb_data_request(dev, skb);
+	if (err != LAPB_OK) {
 		pr_err("lapb_data_request error - %d\n", err);
 		goto drop;
 	}
@@ -263,10 +265,8 @@ static void lapbeth_connected(struct net_device *dev, int reason)
 	unsigned char *ptr;
 	struct sk_buff *skb = __dev_alloc_skb(1, GFP_ATOMIC | __GFP_NOMEMALLOC);
 
-	if (!skb) {
-		pr_err("out of memory\n");
+	if (!skb)
 		return;
-	}
 
 	ptr  = skb_put(skb, 1);
 	*ptr = X25_IFACE_CONNECT;
@@ -283,10 +283,8 @@ static void lapbeth_disconnected(struct net_device *dev, int reason)
 	unsigned char *ptr;
 	struct sk_buff *skb = __dev_alloc_skb(1, GFP_ATOMIC | __GFP_NOMEMALLOC);
 
-	if (!skb) {
-		pr_err("out of memory\n");
+	if (!skb)
 		return;
-	}
 
 	ptr  = skb_put(skb, 1);
 	*ptr = X25_IFACE_DISCONNECT;
@@ -297,17 +295,16 @@ static void lapbeth_disconnected(struct net_device *dev, int reason)
 	napi_schedule(&lapbeth->napi);
 }
 
-/*
- *	Set AX.25 callsign
+/*	Set AX.25 callsign
  */
 static int lapbeth_set_mac_address(struct net_device *dev, void *addr)
 {
 	struct sockaddr *sa = addr;
+
 	memcpy(dev->dev_addr, sa->sa_data, dev->addr_len);
 	return 0;
 }
 
-
 static const struct lapb_register_struct lapbeth_callbacks = {
 	.connect_confirmation    = lapbeth_connected,
 	.connect_indication      = lapbeth_connected,
@@ -317,8 +314,7 @@ static const struct lapb_register_struct lapbeth_callbacks = {
 	.data_transmit           = lapbeth_data_transmit,
 };
 
-/*
- * open/close a device
+/* open/close a device
  */
 static int lapbeth_open(struct net_device *dev)
 {
@@ -327,7 +323,8 @@ static int lapbeth_open(struct net_device *dev)
 
 	napi_enable(&lapbeth->napi);
 
-	if ((err = lapb_register(dev, &lapbeth_callbacks)) != LAPB_OK) {
+	err = lapb_register(dev, &lapbeth_callbacks);
+	if (err != LAPB_OK) {
 		pr_err("lapb_register error: %d\n", err);
 		return -ENODEV;
 	}
@@ -348,7 +345,8 @@ static int lapbeth_close(struct net_device *dev)
 	lapbeth->up = false;
 	spin_unlock_bh(&lapbeth->up_lock);
 
-	if ((err = lapb_unregister(dev)) != LAPB_OK)
+	err = lapb_unregister(dev);
+	if (err != LAPB_OK)
 		pr_err("lapb_unregister error: %d\n", err);
 
 	napi_disable(&lapbeth->napi);
@@ -375,8 +373,7 @@ static void lapbeth_setup(struct net_device *dev)
 	dev->addr_len        = 0;
 }
 
-/*
- *	Setup a new device.
+/*	Setup a new device.
  */
 static int lapbeth_new_device(struct net_device *dev)
 {
@@ -427,8 +424,7 @@ fail:
 	goto out;
 }
 
-/*
- *	Free a lapb network device.
+/*	Free a lapb network device.
  */
 static void lapbeth_free_device(struct lapbethdev *lapbeth)
 {
@@ -437,8 +433,7 @@ static void lapbeth_free_device(struct lapbethdev *lapbeth)
 	unregister_netdevice(lapbeth->axdev);
 }
 
-/*
- *	Handle device status changes.
+/*	Handle device status changes.
  *
  * Called from notifier with RTNL held.
  */
@@ -457,13 +452,13 @@ static int lapbeth_device_event(struct notifier_block *this,
 	switch (event) {
 	case NETDEV_UP:
 		/* New ethernet device -> new LAPB interface	 */
-		if (lapbeth_get_x25_dev(dev) == NULL)
+		if (!lapbeth_get_x25_dev(dev))
 			lapbeth_new_device(dev);
 		break;
 	case NETDEV_GOING_DOWN:
 		/* ethernet device closes -> close LAPB interface */
 		lapbeth = lapbeth_get_x25_dev(dev);
-		if (lapbeth) 
+		if (lapbeth)
 			dev_close(lapbeth->axdev);
 		break;
 	case NETDEV_UNREGISTER:
diff --git a/drivers/net/wan/lmc/lmc.h b/drivers/net/wan/lmc/lmc.h
index 38961793adad..3bd541c868d5 100644
--- a/drivers/net/wan/lmc/lmc.h
+++ b/drivers/net/wan/lmc/lmc.h
@@ -9,7 +9,7 @@
  */
 int lmc_probe(struct net_device * dev);
 unsigned lmc_mii_readreg(lmc_softc_t * const sc, unsigned
-      			  devaddr, unsigned regno);
+			  devaddr, unsigned regno);
 void lmc_mii_writereg(lmc_softc_t * const sc, unsigned devaddr,
 			       unsigned regno, unsigned data);
 void lmc_led_on(lmc_softc_t * const, u32);
diff --git a/drivers/net/wan/n2.c b/drivers/net/wan/n2.c
index 5bf4463873b1..bdb6dc2409bc 100644
--- a/drivers/net/wan/n2.c
+++ b/drivers/net/wan/n2.c
@@ -32,9 +32,8 @@
 #include <asm/io.h>
 #include "hd64570.h"
 
-
-static const char* version = "SDL RISCom/N2 driver version: 1.15";
-static const char* devname = "RISCom/N2";
+static const char *version = "SDL RISCom/N2 driver version: 1.15";
+static const char *devname = "RISCom/N2";
 
 #undef DEBUG_PKT
 #define DEBUG_RINGS
@@ -64,11 +63,9 @@ static char *hw;	/* pointer to hw=xxx command line string */
 #define PCR_ENWIN  4     /* Open window */
 #define PCR_BUS16  8     /* 16-bit bus */
 
-
 /* Memory Base Address Register */
 #define N2_BAR 2
 
-
 /* Page Scan Register  */
 #define N2_PSR 4
 #define WIN16K       0x00
@@ -78,7 +75,6 @@ static char *hw;	/* pointer to hw=xxx command line string */
 #define PSR_DMAEN    0x80
 #define PSR_PAGEBITS 0x0F
 
-
 /* Modem Control Reg */
 #define N2_MCR 6
 #define CLOCK_OUT_PORT1 0x80
@@ -90,7 +86,6 @@ static char *hw;	/* pointer to hw=xxx command line string */
 #define DTR_PORT1       0x02
 #define DTR_PORT0       0x01
 
-
 typedef struct port_s {
 	struct net_device *dev;
 	struct card_s *card;
@@ -106,9 +101,7 @@ typedef struct port_s {
 	u8 rxs, txs, tmc;	/* SCA registers */
 	u8 phy_node;		/* physical port # - 0 or 1 */
 	u8 log_node;		/* logical port # */
-}port_t;
-
-
+} port_t;
 
 typedef struct card_s {
 	u8 __iomem *winbase;		/* ISA window base address */
@@ -122,13 +115,11 @@ typedef struct card_s {
 
 	port_t ports[2];
 	struct card_s *next_card;
-}card_t;
-
+} card_t;
 
 static card_t *first_card;
 static card_t **new_card = &first_card;
 
-
 #define sca_reg(reg, card) (0x8000 | (card)->io | \
 			    ((reg) & 0x0F) | (((reg) & 0xF0) << 6))
 #define sca_in(reg, card)		inb(sca_reg(reg, card))
@@ -144,23 +135,20 @@ static card_t **new_card = &first_card;
 #define get_port(card, port)		((card)->ports[port].valid ? \
 					 &(card)->ports[port] : NULL)
 
-
 static __inline__ u8 sca_get_page(card_t *card)
 {
 	return inb(card->io + N2_PSR) & PSR_PAGEBITS;
 }
 
-
 static __inline__ void openwin(card_t *card, u8 page)
 {
 	u8 psr = inb(card->io + N2_PSR);
+
 	outb((psr & ~PSR_PAGEBITS) | page, card->io + N2_PSR);
 }
 
-
 #include "hd64570.c"
 
-
 static void n2_set_iface(port_t *port)
 {
 	card_t *card = port->card;
@@ -170,7 +158,7 @@ static void n2_set_iface(port_t *port)
 	u8 rxs = port->rxs & CLK_BRG_MASK;
 	u8 txs = port->txs & CLK_BRG_MASK;
 
-	switch(port->settings.clock_type) {
+	switch (port->settings.clock_type) {
 	case CLOCK_INT:
 		mcr |= port->phy_node ? CLOCK_OUT_PORT1 : CLOCK_OUT_PORT0;
 		rxs |= CLK_BRG_RX; /* BRG output */
@@ -203,13 +191,12 @@ static void n2_set_iface(port_t *port)
 	sca_set_port(port);
 }
 
-
-
 static int n2_open(struct net_device *dev)
 {
 	port_t *port = dev_to_port(dev);
 	int io = port->card->io;
-	u8 mcr = inb(io + N2_MCR) | (port->phy_node ? TX422_PORT1:TX422_PORT0);
+	u8 mcr = inb(io + N2_MCR) |
+		(port->phy_node ? TX422_PORT1 : TX422_PORT0);
 	int result;
 
 	result = hdlc_open(dev);
@@ -226,13 +213,12 @@ static int n2_open(struct net_device *dev)
 	return 0;
 }
 
-
-
 static int n2_close(struct net_device *dev)
 {
 	port_t *port = dev_to_port(dev);
 	int io = port->card->io;
-	u8 mcr = inb(io+N2_MCR) | (port->phy_node ? TX422_PORT1 : TX422_PORT0);
+	u8 mcr = inb(io + N2_MCR) |
+		(port->phy_node ? TX422_PORT1 : TX422_PORT0);
 
 	sca_close(dev);
 	mcr |= port->phy_node ? DTR_PORT1 : DTR_PORT0; /* set DTR OFF */
@@ -241,8 +227,6 @@ static int n2_close(struct net_device *dev)
 	return 0;
 }
 
-
-
 static int n2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	const size_t size = sizeof(sync_serial_settings);
@@ -259,7 +243,7 @@ static int n2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	if (cmd != SIOCWANDEV)
 		return hdlc_ioctl(dev, ifr, cmd);
 
-	switch(ifr->ifr_settings.type) {
+	switch (ifr->ifr_settings.type) {
 	case IF_GET_IFACE:
 		ifr->ifr_settings.type = IF_IFACE_SYNC_SERIAL;
 		if (ifr->ifr_settings.size < size) {
@@ -271,7 +255,7 @@ static int n2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		return 0;
 
 	case IF_IFACE_SYNC_SERIAL:
-		if(!capable(CAP_NET_ADMIN))
+		if (!capable(CAP_NET_ADMIN))
 			return -EPERM;
 
 		if (copy_from_user(&new_line, line, size))
@@ -295,8 +279,6 @@ static int n2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	}
 }
 
-
-
 static void n2_destroy_card(card_t *card)
 {
 	int cnt;
@@ -304,6 +286,7 @@ static void n2_destroy_card(card_t *card)
 	for (cnt = 0; cnt < 2; cnt++)
 		if (card->ports[cnt].card) {
 			struct net_device *dev = port_to_dev(&card->ports[cnt]);
+
 			unregister_hdlc_device(dev);
 		}
 
@@ -354,7 +337,7 @@ static int __init n2_run(unsigned long io, unsigned long irq,
 	}
 
 	card = kzalloc(sizeof(card_t), GFP_KERNEL);
-	if (card == NULL)
+	if (!card)
 		return -ENOBUFS;
 
 	card->ports[0].dev = alloc_hdlcdev(&card->ports[0]);
@@ -486,11 +469,9 @@ static int __init n2_run(unsigned long io, unsigned long irq,
 	return 0;
 }
 
-
-
 static int __init n2_init(void)
 {
-	if (hw==NULL) {
+	if (!hw) {
 #ifdef MODULE
 		pr_info("no card initialized\n");
 #endif
@@ -515,7 +496,7 @@ static int __init n2_init(void)
 
 		if (*hw++ != ',')
 			break;
-		while(1) {
+		while (1) {
 			if (*hw == '0' && !valid[0])
 				valid[0] = 1; /* Port 0 enabled */
 			else if (*hw == '1' && !valid[1])
@@ -533,25 +514,24 @@ static int __init n2_init(void)
 
 		if (*hw == '\x0')
 			return first_card ? 0 : -EINVAL;
-	}while(*hw++ == ':');
+	} while (*hw++ == ':');
 
 	pr_err("invalid hardware parameters\n");
 	return first_card ? 0 : -EINVAL;
 }
 
-
 static void __exit n2_cleanup(void)
 {
 	card_t *card = first_card;
 
 	while (card) {
 		card_t *ptr = card;
+
 		card = card->next_card;
 		n2_destroy_card(ptr);
 	}
 }
 
-
 module_init(n2_init);
 module_exit(n2_cleanup);
 
diff --git a/drivers/net/wan/pc300too.c b/drivers/net/wan/pc300too.c
index 001fd378d417..7b123a771aa6 100644
--- a/drivers/net/wan/pc300too.c
+++ b/drivers/net/wan/pc300too.c
@@ -44,7 +44,7 @@
 #define MAX_TX_BUFFERS		10
 
 static int pci_clock_freq = 33000000;
-static int use_crystal_clock = 0;
+static int use_crystal_clock;
 static unsigned int CLOCK_BASE;
 
 /* Masks to access the init_ctrl PLX register */
@@ -52,11 +52,9 @@ static unsigned int CLOCK_BASE;
 #define PC300_CHMEDIA_MASK(port) (0x00000020UL << ((port) * 3))
 #define PC300_CTYPE_MASK	 (0x00000800UL)
 
-
 enum { PC300_RSV = 1, PC300_X21, PC300_TE }; /* card types */
 
-/*
- *      PLX PCI9050-1 local configuration and shared runtime registers.
+/*      PLX PCI9050-1 local configuration and shared runtime registers.
  *      This structure can be used to access 9050 registers (memory mapped).
  */
 typedef struct {
@@ -69,9 +67,7 @@ typedef struct {
 	u32 cs_base[4];		/* 3C-48h : Chip Select Base Addrs */
 	u32 intr_ctrl_stat;	/* 4Ch : Interrupt Control/Status */
 	u32 init_ctrl;		/* 50h : EEPROM ctrl, Init Ctrl, etc */
-}plx9050;
-
-
+} plx9050;
 
 typedef struct port_s {
 	struct napi_struct napi;
@@ -88,9 +84,7 @@ typedef struct port_s {
 	u16 txlast;
 	u8 rxs, txs, tmc;	/* SCA registers */
 	u8 chan;		/* physical port # - 0 or 1 */
-}port_t;
-
-
+} port_t;
 
 typedef struct card_s {
 	int type;		/* RSV, X21, etc. */
@@ -105,26 +99,24 @@ typedef struct card_s {
 	u8 irq;			/* interrupt request level */
 
 	port_t ports[2];
-}card_t;
-
+} card_t;
 
 #define get_port(card, port)	     ((port) < (card)->n_ports ? \
 					 (&(card)->ports[port]) : (NULL))
 
 #include "hd64572.c"
 
-
 static void pc300_set_iface(port_t *port)
 {
 	card_t *card = port->card;
-	u32 __iomem * init_ctrl = &card->plxbase->init_ctrl;
+	u32 __iomem *init_ctrl = &card->plxbase->init_ctrl;
 	u16 msci = get_msci(port);
 	u8 rxs = port->rxs & CLK_BRG_MASK;
 	u8 txs = port->txs & CLK_BRG_MASK;
 
 	sca_out(EXS_TES1, (port->chan ? MSCI1_OFFSET : MSCI0_OFFSET) + EXS,
 		port->card);
-	switch(port->settings.clock_type) {
+	switch (port->settings.clock_type) {
 	case CLOCK_INT:
 		rxs |= CLK_BRG; /* BRG output */
 		txs |= CLK_PIN_OUT | CLK_TX_RXCLK; /* RX clock */
@@ -162,13 +154,11 @@ static void pc300_set_iface(port_t *port)
 	}
 }
 
-
-
 static int pc300_open(struct net_device *dev)
 {
 	port_t *port = dev_to_port(dev);
-
 	int result = hdlc_open(dev);
+
 	if (result)
 		return result;
 
@@ -177,8 +167,6 @@ static int pc300_open(struct net_device *dev)
 	return 0;
 }
 
-
-
 static int pc300_close(struct net_device *dev)
 {
 	sca_close(dev);
@@ -186,8 +174,6 @@ static int pc300_close(struct net_device *dev)
 	return 0;
 }
 
-
-
 static int pc300_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	const size_t size = sizeof(sync_serial_settings);
@@ -214,7 +200,6 @@ static int pc300_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		if (copy_to_user(line, &port->settings, size))
 			return -EFAULT;
 		return 0;
-
 	}
 
 	if (port->card->type == PC300_X21 &&
@@ -255,8 +240,6 @@ static int pc300_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	return 0;
 }
 
-
-
 static void pc300_pci_remove_one(struct pci_dev *pdev)
 {
 	int i;
@@ -314,7 +297,7 @@ static int pc300_pci_init_one(struct pci_dev *pdev,
 	}
 
 	card = kzalloc(sizeof(card_t), GFP_KERNEL);
-	if (card == NULL) {
+	if (!card) {
 		pci_release_regions(pdev);
 		pci_disable_device(pdev);
 		return -ENOBUFS;
@@ -338,9 +321,7 @@ static int pc300_pci_init_one(struct pci_dev *pdev,
 	ramphys = pci_resource_start(pdev, 3) & PCI_BASE_ADDRESS_MEM_MASK;
 	card->rambase = pci_ioremap_bar(pdev, 3);
 
-	if (card->plxbase == NULL ||
-	    card->scabase == NULL ||
-	    card->rambase == NULL) {
+	if (!card->plxbase || !card->scabase || !card->rambase) {
 		pr_err("ioremap() failed\n");
 		pc300_pci_remove_one(pdev);
 		return -ENOMEM;
@@ -365,12 +346,14 @@ static int pc300_pci_init_one(struct pci_dev *pdev,
 	else
 		card->n_ports = 2;
 
-	for (i = 0; i < card->n_ports; i++)
-		if (!(card->ports[i].netdev = alloc_hdlcdev(&card->ports[i]))) {
+	for (i = 0; i < card->n_ports; i++) {
+		card->ports[i].netdev = alloc_hdlcdev(&card->ports[i]);
+		if (!card->ports[i].netdev) {
 			pr_err("unable to allocate memory\n");
 			pc300_pci_remove_one(pdev);
 			return -ENOMEM;
 		}
+	}
 
 	/* Reset PLX */
 	p = &card->plxbase->init_ctrl;
@@ -442,6 +425,7 @@ static int pc300_pci_init_one(struct pci_dev *pdev,
 		port_t *port = &card->ports[i];
 		struct net_device *dev = port->netdev;
 		hdlc_device *hdlc = dev_to_hdlc(dev);
+
 		port->chan = i;
 
 		spin_lock_init(&port->lock);
@@ -472,8 +456,6 @@ static int pc300_pci_init_one(struct pci_dev *pdev,
 	return 0;
 }
 
-
-
 static const struct pci_device_id pc300_pci_tbl[] = {
 	{ PCI_VENDOR_ID_CYCLADES, PCI_DEVICE_ID_PC300_RX_1, PCI_ANY_ID,
 	  PCI_ANY_ID, 0, 0, 0 },
@@ -486,7 +468,6 @@ static const struct pci_device_id pc300_pci_tbl[] = {
 	{ 0, }
 };
 
-
 static struct pci_driver pc300_pci_driver = {
 	.name =          "PC300",
 	.id_table =      pc300_pci_tbl,
@@ -494,7 +475,6 @@ static struct pci_driver pc300_pci_driver = {
 	.remove =        pc300_pci_remove_one,
 };
 
-
 static int __init pc300_init_module(void)
 {
 	if (pci_clock_freq < 1000000 || pci_clock_freq > 80000000) {
@@ -511,8 +491,6 @@ static int __init pc300_init_module(void)
 	return pci_register_driver(&pc300_pci_driver);
 }
 
-
-
 static void __exit pc300_cleanup_module(void)
 {
 	pci_unregister_driver(&pc300_pci_driver);
diff --git a/drivers/net/wan/pci200syn.c b/drivers/net/wan/pci200syn.c
index ba5cc0c53833..dee9c4e15eca 100644
--- a/drivers/net/wan/pci200syn.c
+++ b/drivers/net/wan/pci200syn.c
@@ -42,8 +42,7 @@
 static int pci_clock_freq = 33000000;
 #define CLOCK_BASE pci_clock_freq
 
-/*
- *      PLX PCI9052 local configuration and shared runtime registers.
+/*      PLX PCI9052 local configuration and shared runtime registers.
  *      This structure can be used to access 9052 registers (memory mapped).
  */
 typedef struct {
@@ -56,9 +55,7 @@ typedef struct {
 	u32 cs_base[4];		/* 3C-48h : Chip Select Base Addrs */
 	u32 intr_ctrl_stat;	/* 4Ch : Interrupt Control/Status */
 	u32 init_ctrl;		/* 50h : EEPROM ctrl, Init Ctrl, etc */
-}plx9052;
-
-
+} plx9052;
 
 typedef struct port_s {
 	struct napi_struct napi;
@@ -74,9 +71,7 @@ typedef struct port_s {
 	u16 txlast;
 	u8 rxs, txs, tmc;	/* SCA registers */
 	u8 chan;		/* physical port # - 0 or 1 */
-}port_t;
-
-
+} port_t;
 
 typedef struct card_s {
 	u8 __iomem *rambase;	/* buffer memory base (virtual) */
@@ -88,15 +83,15 @@ typedef struct card_s {
 	u8 irq;			/* interrupt request level */
 
 	port_t ports[2];
-}card_t;
-
+} card_t;
 
-#define get_port(card, port)	     (&card->ports[port])
+#define get_port(card, port)	     (&(card)->ports[port])
 #define sca_flush(card)		     (sca_in(IER0, card))
 
 static inline void new_memcpy_toio(char __iomem *dest, char *src, int length)
 {
 	int len;
+
 	do {
 		len = length > 256 ? 256 : length;
 		memcpy_toio(dest, src, len);
@@ -112,7 +107,6 @@ static inline void new_memcpy_toio(char __iomem *dest, char *src, int length)
 
 #include "hd64572.c"
 
-
 static void pci200_set_iface(port_t *port)
 {
 	card_t *card = port->card;
@@ -122,7 +116,7 @@ static void pci200_set_iface(port_t *port)
 
 	sca_out(EXS_TES1, (port->chan ? MSCI1_OFFSET : MSCI0_OFFSET) + EXS,
 		port->card);
-	switch(port->settings.clock_type) {
+	switch (port->settings.clock_type) {
 	case CLOCK_INT:
 		rxs |= CLK_BRG; /* BRG output */
 		txs |= CLK_PIN_OUT | CLK_TX_RXCLK; /* RX clock */
@@ -151,13 +145,11 @@ static void pci200_set_iface(port_t *port)
 	sca_set_port(port);
 }
 
-
-
 static int pci200_open(struct net_device *dev)
 {
 	port_t *port = dev_to_port(dev);
-
 	int result = hdlc_open(dev);
+
 	if (result)
 		return result;
 
@@ -167,8 +159,6 @@ static int pci200_open(struct net_device *dev)
 	return 0;
 }
 
-
-
 static int pci200_close(struct net_device *dev)
 {
 	sca_close(dev);
@@ -177,8 +167,6 @@ static int pci200_close(struct net_device *dev)
 	return 0;
 }
 
-
-
 static int pci200_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	const size_t size = sizeof(sync_serial_settings);
@@ -195,7 +183,7 @@ static int pci200_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	if (cmd != SIOCWANDEV)
 		return hdlc_ioctl(dev, ifr, cmd);
 
-	switch(ifr->ifr_settings.type) {
+	switch (ifr->ifr_settings.type) {
 	case IF_GET_IFACE:
 		ifr->ifr_settings.type = IF_IFACE_V35;
 		if (ifr->ifr_settings.size < size) {
@@ -233,8 +221,6 @@ static int pci200_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	}
 }
 
-
-
 static void pci200_pci_remove_one(struct pci_dev *pdev)
 {
 	int i;
@@ -292,7 +278,7 @@ static int pci200_pci_init_one(struct pci_dev *pdev,
 	}
 
 	card = kzalloc(sizeof(card_t), GFP_KERNEL);
-	if (card == NULL) {
+	if (!card) {
 		pci_release_regions(pdev);
 		pci_disable_device(pdev);
 		return -ENOBUFS;
@@ -314,18 +300,16 @@ static int pci200_pci_init_one(struct pci_dev *pdev,
 		return -EFAULT;
 	}
 
-	plxphys = pci_resource_start(pdev,0) & PCI_BASE_ADDRESS_MEM_MASK;
+	plxphys = pci_resource_start(pdev, 0) & PCI_BASE_ADDRESS_MEM_MASK;
 	card->plxbase = ioremap(plxphys, PCI200SYN_PLX_SIZE);
 
-	scaphys = pci_resource_start(pdev,2) & PCI_BASE_ADDRESS_MEM_MASK;
+	scaphys = pci_resource_start(pdev, 2) & PCI_BASE_ADDRESS_MEM_MASK;
 	card->scabase = ioremap(scaphys, PCI200SYN_SCA_SIZE);
 
-	ramphys = pci_resource_start(pdev,3) & PCI_BASE_ADDRESS_MEM_MASK;
+	ramphys = pci_resource_start(pdev, 3) & PCI_BASE_ADDRESS_MEM_MASK;
 	card->rambase = pci_ioremap_bar(pdev, 3);
 
-	if (card->plxbase == NULL ||
-	    card->scabase == NULL ||
-	    card->rambase == NULL) {
+	if (!card->plxbase || !card->scabase || !card->rambase) {
 		pr_err("ioremap() failed\n");
 		pci200_pci_remove_one(pdev);
 		return -EFAULT;
@@ -380,6 +364,7 @@ static int pci200_pci_init_one(struct pci_dev *pdev,
 		port_t *port = &card->ports[i];
 		struct net_device *dev = port->netdev;
 		hdlc_device *hdlc = dev_to_hdlc(dev);
+
 		port->chan = i;
 
 		spin_lock_init(&port->lock);
@@ -407,15 +392,12 @@ static int pci200_pci_init_one(struct pci_dev *pdev,
 	return 0;
 }
 
-
-
 static const struct pci_device_id pci200_pci_tbl[] = {
 	{ PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9050, PCI_VENDOR_ID_PLX,
 	  PCI_DEVICE_ID_PLX_PCI200SYN, 0, 0, 0 },
 	{ 0, }
 };
 
-
 static struct pci_driver pci200_pci_driver = {
 	.name		= "PCI200SYN",
 	.id_table	= pci200_pci_tbl,
@@ -423,7 +405,6 @@ static struct pci_driver pci200_pci_driver = {
 	.remove		= pci200_pci_remove_one,
 };
 
-
 static int __init pci200_init_module(void)
 {
 	if (pci_clock_freq < 1000000 || pci_clock_freq > 80000000) {
@@ -433,8 +414,6 @@ static int __init pci200_init_module(void)
 	return pci_register_driver(&pci200_pci_driver);
 }
 
-
-
 static void __exit pci200_cleanup_module(void)
 {
 	pci_unregister_driver(&pci200_pci_driver);
diff --git a/drivers/net/wan/sealevel.c b/drivers/net/wan/sealevel.c
index 7dddc9dcbe23..4403e219ca03 100644
--- a/drivers/net/wan/sealevel.c
+++ b/drivers/net/wan/sealevel.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *	Sealevel Systems 4021 driver.
+/*	Sealevel Systems 4021 driver.
  *
  *	(c) Copyright 1999, 2001 Alan Cox
  *	(c) Copyright 2001 Red Hat Inc.
@@ -29,32 +28,25 @@
 #include <asm/byteorder.h>
 #include "z85230.h"
 
-
-struct slvl_device
-{
+struct slvl_device {
 	struct z8530_channel *chan;
 	int channel;
 };
 
-
-struct slvl_board
-{
+struct slvl_board {
 	struct slvl_device dev[2];
 	struct z8530_dev board;
 	int iobase;
 };
 
-/*
- *	Network driver support routines
- */
+ /*	Network driver support routines */
 
-static inline struct slvl_device* dev_to_chan(struct net_device *dev)
+static inline struct slvl_device *dev_to_chan(struct net_device *dev)
 {
 	return (struct slvl_device *)dev_to_hdlc(dev)->priv;
 }
 
-/*
- *	Frame receive. Simple for our card as we do HDLC and there
+/*	Frame receive. Simple for our card as we do HDLC and there
  *	is no funny garbage involved
  */
 
@@ -68,9 +60,7 @@ static void sealevel_input(struct z8530_channel *c, struct sk_buff *skb)
 	netif_rx(skb);
 }
 
-/*
- *	We've been placed in the UP state
- */
+ /*	We've been placed in the UP state */
 
 static int sealevel_open(struct net_device *d)
 {
@@ -78,17 +68,15 @@ static int sealevel_open(struct net_device *d)
 	int err = -1;
 	int unit = slvl->channel;
 
-	/*
-	 *	Link layer up.
-	 */
+	 /*	Link layer up. */
 
 	switch (unit) {
-		case 0:
-			err = z8530_sync_dma_open(d, slvl->chan);
-			break;
-		case 1:
-			err = z8530_sync_open(d, slvl->chan);
-			break;
+	case 0:
+		err = z8530_sync_dma_open(d, slvl->chan);
+		break;
+	case 1:
+		err = z8530_sync_open(d, slvl->chan);
+		break;
 	}
 
 	if (err)
@@ -97,21 +85,18 @@ static int sealevel_open(struct net_device *d)
 	err = hdlc_open(d);
 	if (err) {
 		switch (unit) {
-			case 0:
-				z8530_sync_dma_close(d, slvl->chan);
-				break;
-			case 1:
-				z8530_sync_close(d, slvl->chan);
-				break;
+		case 0:
+			z8530_sync_dma_close(d, slvl->chan);
+			break;
+		case 1:
+			z8530_sync_close(d, slvl->chan);
+			break;
 		}
 		return err;
 	}
 
 	slvl->chan->rx_function = sealevel_input;
 
-	/*
-	 *	Go go go
-	 */
 	netif_start_queue(d);
 	return 0;
 }
@@ -121,9 +106,7 @@ static int sealevel_close(struct net_device *d)
 	struct slvl_device *slvl = dev_to_chan(d);
 	int unit = slvl->channel;
 
-	/*
-	 *	Discard new frames
-	 */
+	/*	Discard new frames */
 
 	slvl->chan->rx_function = z8530_null_rx;
 
@@ -131,12 +114,12 @@ static int sealevel_close(struct net_device *d)
 	netif_stop_queue(d);
 
 	switch (unit) {
-		case 0:
-			z8530_sync_dma_close(d, slvl->chan);
-			break;
-		case 1:
-			z8530_sync_close(d, slvl->chan);
-			break;
+	case 0:
+		z8530_sync_dma_close(d, slvl->chan);
+		break;
+	case 1:
+		z8530_sync_close(d, slvl->chan);
+		break;
 	}
 	return 0;
 }
@@ -144,16 +127,15 @@ static int sealevel_close(struct net_device *d)
 static int sealevel_ioctl(struct net_device *d, struct ifreq *ifr, int cmd)
 {
 	/* struct slvl_device *slvl=dev_to_chan(d);
-	   z8530_ioctl(d,&slvl->sync.chanA,ifr,cmd) */
+	 * z8530_ioctl(d,&slvl->sync.chanA,ifr,cmd)
+	 */
 	return hdlc_ioctl(d, ifr, cmd);
 }
 
-/*
- *	Passed network frames, fire them downwind.
- */
+/*	Passed network frames, fire them downwind. */
 
 static netdev_tx_t sealevel_queue_xmit(struct sk_buff *skb,
-					     struct net_device *d)
+				       struct net_device *d)
 {
 	return z8530_queue_xmit(dev_to_chan(d)->chan, skb);
 }
@@ -176,6 +158,7 @@ static const struct net_device_ops sealevel_ops = {
 static int slvl_setup(struct slvl_device *sv, int iobase, int irq)
 {
 	struct net_device *dev = alloc_hdlcdev(sv);
+
 	if (!dev)
 		return -1;
 
@@ -195,10 +178,7 @@ static int slvl_setup(struct slvl_device *sv, int iobase, int irq)
 	return 0;
 }
 
-
-/*
- *	Allocate and setup Sealevel board.
- */
+/*	Allocate and setup Sealevel board. */
 
 static __init struct slvl_board *slvl_init(int iobase, int irq,
 					   int txdma, int rxdma, int slow)
@@ -206,9 +186,7 @@ static __init struct slvl_board *slvl_init(int iobase, int irq,
 	struct z8530_dev *dev;
 	struct slvl_board *b;
 
-	/*
-	 *	Get the needed I/O space
-	 */
+	/*	Get the needed I/O space */
 
 	if (!request_region(iobase, 8, "Sealevel 4021")) {
 		pr_warn("I/O 0x%X already in use\n", iobase);
@@ -227,17 +205,13 @@ static __init struct slvl_board *slvl_init(int iobase, int irq,
 
 	dev = &b->board;
 
-	/*
-	 *	Stuff in the I/O addressing
-	 */
+	/*	Stuff in the I/O addressing */
 
 	dev->active = 0;
 
 	b->iobase = iobase;
 
-	/*
-	 *	Select 8530 delays for the old board
-	 */
+	/*	Select 8530 delays for the old board */
 
 	if (slow)
 		iobase |= Z8530_PORT_SLEEP;
@@ -250,15 +224,13 @@ static __init struct slvl_board *slvl_init(int iobase, int irq,
 	dev->chanA.irqs = &z8530_nop;
 	dev->chanB.irqs = &z8530_nop;
 
-	/*
-	 *	Assert DTR enable DMA
-	 */
+	/*	Assert DTR enable DMA */
 
 	outb(3 | (1 << 7), b->iobase + 4);
 
-
 	/* We want a fast IRQ for this device. Actually we'd like an even faster
-	   IRQ ;) - This is one driver RtLinux is made for */
+	 * IRQ ;) - This is one driver RtLinux is made for
+	 */
 
 	if (request_irq(irq, z8530_interrupt, 0,
 			"SeaLevel", dev) < 0) {
@@ -282,9 +254,7 @@ static __init struct slvl_board *slvl_init(int iobase, int irq,
 
 	disable_irq(irq);
 
-	/*
-	 *	Begin normal initialise
-	 */
+	/*	Begin normal initialise */
 
 	if (z8530_init(dev) != 0) {
 		pr_err("Z8530 series device not found\n");
@@ -299,9 +269,7 @@ static __init struct slvl_board *slvl_init(int iobase, int irq,
 		z8530_channel_load(&dev->chanB, z8530_hdlc_kilostream_85230);
 	}
 
-	/*
-	 *	Now we can take the IRQ
-	 */
+	/*	Now we can take the IRQ */
 
 	enable_irq(irq);
 
@@ -338,6 +306,7 @@ static void __exit slvl_shutdown(struct slvl_board *b)
 
 	for (u = 0; u < 2; u++) {
 		struct net_device *d = b->dev[u].chan->netdevice;
+
 		unregister_hdlc_device(d);
 		free_netdev(d);
 	}
@@ -351,12 +320,11 @@ static void __exit slvl_shutdown(struct slvl_board *b)
 	kfree(b);
 }
 
-
-static int io=0x238;
-static int txdma=1;
-static int rxdma=3;
-static int irq=5;
-static bool slow=false;
+static int io = 0x238;
+static int txdma = 1;
+static int rxdma = 3;
+static int irq = 5;
+static bool slow;
 
 module_param_hw(io, int, ioport, 0);
 MODULE_PARM_DESC(io, "The I/O base of the Sealevel card");
diff --git a/drivers/net/wan/wanxl.c b/drivers/net/wan/wanxl.c
index a83133388de9..f22e48415e6f 100644
--- a/drivers/net/wan/wanxl.c
+++ b/drivers/net/wan/wanxl.c
@@ -32,7 +32,7 @@
 
 #include "wanxl.h"
 
-static const char* version = "wanXL serial card driver version: 0.48";
+static const char *version = "wanXL serial card driver version: 0.48";
 
 #define PLX_CTL_RESET   0x40000000 /* adapter reset */
 
@@ -50,24 +50,21 @@ static const char* version = "wanXL serial card driver version: 0.48";
 /* MAILBOX #2 - DRAM SIZE */
 #define MBX2_MEMSZ_MASK 0xFFFF0000 /* PUTS Memory Size Register mask */
 
-
 struct port {
 	struct net_device *dev;
 	struct card *card;
 	spinlock_t lock;	/* for wanxl_xmit */
-        int node;		/* physical port #0 - 3 */
+	int node;		/* physical port #0 - 3 */
 	unsigned int clock_type;
 	int tx_in, tx_out;
 	struct sk_buff *tx_skbs[TX_BUFFERS];
 };
 
-
 struct card_status {
 	desc_t rx_descs[RX_QUEUE_LENGTH];
 	port_status_t port_status[4];
 };
 
-
 struct card {
 	int n_ports;		/* 1, 2 or 4 ports */
 	u8 irq;
@@ -81,25 +78,22 @@ struct card {
 	struct port ports[];	/* 1 - 4 port structures follow */
 };
 
-
-
 static inline struct port *dev_to_port(struct net_device *dev)
 {
 	return (struct port *)dev_to_hdlc(dev)->priv;
 }
 
-
 static inline port_status_t *get_status(struct port *port)
 {
 	return &port->card->status->port_status[port->node];
 }
 
-
 #ifdef DEBUG_PCI
 static inline dma_addr_t pci_map_single_debug(struct pci_dev *pdev, void *ptr,
 					      size_t size, int direction)
 {
 	dma_addr_t addr = dma_map_single(&pdev->dev, ptr, size, direction);
+
 	if (addr + size > 0x100000000LL)
 		pr_crit("%s: pci_map_single() returned memory at 0x%llx!\n",
 			pci_name(pdev), (unsigned long long)addr);
@@ -110,7 +104,6 @@ static inline dma_addr_t pci_map_single_debug(struct pci_dev *pdev, void *ptr,
 #define pci_map_single pci_map_single_debug
 #endif
 
-
 /* Cable and/or personality module change interrupt service */
 static inline void wanxl_cable_intr(struct port *port)
 {
@@ -118,22 +111,46 @@ static inline void wanxl_cable_intr(struct port *port)
 	int valid = 1;
 	const char *cable, *pm, *dte = "", *dsr = "", *dcd = "";
 
-	switch(value & 0x7) {
-	case STATUS_CABLE_V35: cable = "V.35"; break;
-	case STATUS_CABLE_X21: cable = "X.21"; break;
-	case STATUS_CABLE_V24: cable = "V.24"; break;
-	case STATUS_CABLE_EIA530: cable = "EIA530"; break;
-	case STATUS_CABLE_NONE: cable = "no"; break;
-	default: cable = "invalid";
+	switch (value & 0x7) {
+	case STATUS_CABLE_V35:
+		cable = "V.35";
+		break;
+	case STATUS_CABLE_X21:
+		cable = "X.21";
+		break;
+	case STATUS_CABLE_V24:
+		cable = "V.24";
+		break;
+	case STATUS_CABLE_EIA530:
+		cable = "EIA530";
+		break;
+	case STATUS_CABLE_NONE:
+		cable = "no";
+		break;
+	default:
+		cable = "invalid";
 	}
 
-	switch((value >> STATUS_CABLE_PM_SHIFT) & 0x7) {
-	case STATUS_CABLE_V35: pm = "V.35"; break;
-	case STATUS_CABLE_X21: pm = "X.21"; break;
-	case STATUS_CABLE_V24: pm = "V.24"; break;
-	case STATUS_CABLE_EIA530: pm = "EIA530"; break;
-	case STATUS_CABLE_NONE: pm = "no personality"; valid = 0; break;
-	default: pm = "invalid personality"; valid = 0;
+	switch ((value >> STATUS_CABLE_PM_SHIFT) & 0x7) {
+	case STATUS_CABLE_V35:
+		pm = "V.35";
+		break;
+	case STATUS_CABLE_X21:
+		pm = "X.21";
+		break;
+	case STATUS_CABLE_V24:
+		pm = "V.24";
+		break;
+	case STATUS_CABLE_EIA530:
+		pm = "EIA530";
+		break;
+	case STATUS_CABLE_NONE:
+		pm = "no personality";
+		valid = 0;
+		break;
+	default:
+		pm = "invalid personality";
+		valid = 0;
 	}
 
 	if (valid) {
@@ -154,14 +171,13 @@ static inline void wanxl_cable_intr(struct port *port)
 		netif_carrier_off(port->dev);
 }
 
-
-
 /* Transmit complete interrupt service */
 static inline void wanxl_tx_intr(struct port *port)
 {
 	struct net_device *dev = port->dev;
+
 	while (1) {
-                desc_t *desc = &get_status(port)->tx_descs[port->tx_in];
+		desc_t *desc = &get_status(port)->tx_descs[port->tx_in];
 		struct sk_buff *skb = port->tx_skbs[port->tx_in];
 
 		switch (desc->stat) {
@@ -179,34 +195,33 @@ static inline void wanxl_tx_intr(struct port *port)
 			dev->stats.tx_packets++;
 			dev->stats.tx_bytes += skb->len;
 		}
-                desc->stat = PACKET_EMPTY; /* Free descriptor */
+		desc->stat = PACKET_EMPTY; /* Free descriptor */
 		dma_unmap_single(&port->card->pdev->dev, desc->address,
 				 skb->len, DMA_TO_DEVICE);
 		dev_consume_skb_irq(skb);
-                port->tx_in = (port->tx_in + 1) % TX_BUFFERS;
-        }
+		port->tx_in = (port->tx_in + 1) % TX_BUFFERS;
+	}
 }
 
-
-
 /* Receive complete interrupt service */
 static inline void wanxl_rx_intr(struct card *card)
 {
 	desc_t *desc;
+
 	while (desc = &card->status->rx_descs[card->rx_in],
 	       desc->stat != PACKET_EMPTY) {
-		if ((desc->stat & PACKET_PORT_MASK) > card->n_ports)
+		if ((desc->stat & PACKET_PORT_MASK) > card->n_ports) {
 			pr_crit("%s: received packet for nonexistent port\n",
 				pci_name(card->pdev));
-		else {
+		} else {
 			struct sk_buff *skb = card->rx_skbs[card->rx_in];
 			struct port *port = &card->ports[desc->stat &
 						    PACKET_PORT_MASK];
 			struct net_device *dev = port->dev;
 
-			if (!skb)
+			if (!skb) {
 				dev->stats.rx_dropped++;
-			else {
+			} else {
 				dma_unmap_single(&card->pdev->dev,
 						 desc->address, BUFFER_LENGTH,
 						 DMA_FROM_DEVICE);
@@ -239,21 +254,18 @@ static inline void wanxl_rx_intr(struct card *card)
 	}
 }
 
-
-
-static irqreturn_t wanxl_intr(int irq, void* dev_id)
+static irqreturn_t wanxl_intr(int irq, void *dev_id)
 {
 	struct card *card = dev_id;
-        int i;
-        u32 stat;
-        int handled = 0;
-
+	int i;
+	u32 stat;
+	int handled = 0;
 
-        while((stat = readl(card->plx + PLX_DOORBELL_FROM_CARD)) != 0) {
-                handled = 1;
+	while ((stat = readl(card->plx + PLX_DOORBELL_FROM_CARD)) != 0) {
+		handled = 1;
 		writel(stat, card->plx + PLX_DOORBELL_FROM_CARD);
 
-                for (i = 0; i < card->n_ports; i++) {
+		for (i = 0; i < card->n_ports; i++) {
 			if (stat & (1 << (DOORBELL_FROM_CARD_TX_0 + i)))
 				wanxl_tx_intr(&card->ports[i]);
 			if (stat & (1 << (DOORBELL_FROM_CARD_CABLE_0 + i)))
@@ -261,23 +273,21 @@ static irqreturn_t wanxl_intr(int irq, void* dev_id)
 		}
 		if (stat & (1 << DOORBELL_FROM_CARD_RX))
 			wanxl_rx_intr(card);
-        }
+	}
 
-        return IRQ_RETVAL(handled);
+	return IRQ_RETVAL(handled);
 }
 
-
-
 static netdev_tx_t wanxl_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct port *port = dev_to_port(dev);
 	desc_t *desc;
 
-        spin_lock(&port->lock);
+	spin_lock(&port->lock);
 
 	desc = &get_status(port)->tx_descs[port->tx_out];
-        if (desc->stat != PACKET_EMPTY) {
-                /* should never happen - previous xmit should stop queue */
+	if (desc->stat != PACKET_EMPTY) {
+		/* should never happen - previous xmit should stop queue */
 #ifdef DEBUG_PKT
                 printk(KERN_DEBUG "%s: transmitter buffer full\n", dev->name);
 #endif
@@ -312,8 +322,6 @@ static netdev_tx_t wanxl_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
-
-
 static int wanxl_attach(struct net_device *dev, unsigned short encoding,
 			unsigned short parity)
 {
@@ -335,8 +343,6 @@ static int wanxl_attach(struct net_device *dev, unsigned short encoding,
 	return 0;
 }
 
-
-
 static int wanxl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	const size_t size = sizeof(sync_serial_settings);
@@ -384,11 +390,9 @@ static int wanxl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 
 	default:
 		return hdlc_ioctl(dev, ifr, cmd);
-        }
+	}
 }
 
-
-
 static int wanxl_open(struct net_device *dev)
 {
 	struct port *port = dev_to_port(dev);
@@ -400,7 +404,9 @@ static int wanxl_open(struct net_device *dev)
 		netdev_err(dev, "port already open\n");
 		return -EIO;
 	}
-	if ((i = hdlc_open(dev)) != 0)
+
+	i = hdlc_open(dev);
+	if (i)
 		return i;
 
 	port->tx_in = port->tx_out = 0;
@@ -423,8 +429,6 @@ static int wanxl_open(struct net_device *dev)
 	return -EFAULT;
 }
 
-
-
 static int wanxl_close(struct net_device *dev)
 {
 	struct port *port = dev_to_port(dev);
@@ -461,8 +465,6 @@ static int wanxl_close(struct net_device *dev)
 	return 0;
 }
 
-
-
 static struct net_device_stats *wanxl_get_stats(struct net_device *dev)
 {
 	struct port *port = dev_to_port(dev);
@@ -474,8 +476,6 @@ static struct net_device_stats *wanxl_get_stats(struct net_device *dev)
 	return &dev->stats;
 }
 
-
-
 static int wanxl_puts_command(struct card *card, u32 cmd)
 {
 	unsigned long timeout = jiffies + 5 * HZ;
@@ -486,13 +486,11 @@ static int wanxl_puts_command(struct card *card, u32 cmd)
 			return 0;
 
 		schedule();
-	}while (time_after(timeout, jiffies));
+	} while (time_after(timeout, jiffies));
 
 	return -1;
 }
 
-
-
 static void wanxl_reset(struct card *card)
 {
 	u32 old_value = readl(card->plx + PLX_CONTROL) & ~PLX_CTL_RESET;
@@ -505,8 +503,6 @@ static void wanxl_reset(struct card *card)
 	readl(card->plx + PLX_CONTROL); /* wait for posted write */
 }
 
-
-
 static void wanxl_pci_remove_one(struct pci_dev *pdev)
 {
 	struct card *card = pci_get_drvdata(pdev);
@@ -543,7 +539,6 @@ static void wanxl_pci_remove_one(struct pci_dev *pdev)
 	kfree(card);
 }
 
-
 #include "wanxlfw.inc"
 
 static const struct net_device_ops wanxl_ops = {
@@ -574,12 +569,14 @@ static int wanxl_pci_init_one(struct pci_dev *pdev,
 		return i;
 
 	/* QUICC can only access first 256 MB of host RAM directly,
-	   but PLX9060 DMA does 32-bits for actual packet data transfers */
+	 * but PLX9060 DMA does 32-bits for actual packet data transfers
+	 */
 
 	/* FIXME when PCI/DMA subsystems are fixed.
-	   We set both dma_mask and consistent_dma_mask to 28 bits
-	   and pray pci_alloc_consistent() will use this info. It should
-	   work on most platforms */
+	 * We set both dma_mask and consistent_dma_mask to 28 bits
+	 * and pray pci_alloc_consistent() will use this info. It should
+	 * work on most platforms
+	 */
 	if (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(28)) ||
 	    dma_set_mask(&pdev->dev, DMA_BIT_MASK(28))) {
 		pr_err("No usable DMA configuration\n");
@@ -594,13 +591,18 @@ static int wanxl_pci_init_one(struct pci_dev *pdev,
 	}
 
 	switch (pdev->device) {
-	case PCI_DEVICE_ID_SBE_WANXL100: ports = 1; break;
-	case PCI_DEVICE_ID_SBE_WANXL200: ports = 2; break;
-	default: ports = 4;
+	case PCI_DEVICE_ID_SBE_WANXL100:
+		ports = 1;
+		break;
+	case PCI_DEVICE_ID_SBE_WANXL200:
+		ports = 2;
+		break;
+	default:
+		ports = 4;
 	}
 
 	card = kzalloc(struct_size(card, ports, ports), GFP_KERNEL);
-	if (card == NULL) {
+	if (!card) {
 		pci_release_regions(pdev);
 		pci_disable_device(pdev);
 		return -ENOBUFS;
@@ -612,7 +614,7 @@ static int wanxl_pci_init_one(struct pci_dev *pdev,
 	card->status = dma_alloc_coherent(&pdev->dev,
 					  sizeof(struct card_status),
 					  &card->status_address, GFP_KERNEL);
-	if (card->status == NULL) {
+	if (!card->status) {
 		wanxl_pci_remove_one(pdev);
 		return -ENOBUFS;
 	}
@@ -624,8 +626,9 @@ static int wanxl_pci_init_one(struct pci_dev *pdev,
 #endif
 
 	/* FIXME when PCI/DMA subsystems are fixed.
-	   We set both dma_mask and consistent_dma_mask back to 32 bits
-	   to indicate the card can do 32-bit DMA addressing */
+	 * We set both dma_mask and consistent_dma_mask back to 32 bits
+	 * to indicate the card can do 32-bit DMA addressing
+	 */
 	if (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)) ||
 	    dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))) {
 		pr_err("No usable DMA configuration\n");
@@ -639,7 +642,7 @@ static int wanxl_pci_init_one(struct pci_dev *pdev,
 	card->plx = ioremap(plx_phy, 0x70);
 	if (!card->plx) {
 		pr_err("ioremap() failed\n");
- 		wanxl_pci_remove_one(pdev);
+		wanxl_pci_remove_one(pdev);
 		return -EFAULT;
 	}
 
@@ -656,7 +659,7 @@ static int wanxl_pci_init_one(struct pci_dev *pdev,
 			return -ENODEV;
 		}
 
-		switch(stat & 0xC0) {
+		switch (stat & 0xC0) {
 		case 0x00:	/* hmm - PUTS completed with non-zero code? */
 		case 0x80:	/* PUTS still testing the hardware */
 			break;
@@ -677,7 +680,6 @@ static int wanxl_pci_init_one(struct pci_dev *pdev,
 	/* set up on-board RAM mapping */
 	mem_phy = pci_resource_start(pdev, 2);
 
-
 	/* sanity check the board's reported memory size */
 	if (ramsize < BUFFERS_ADDR +
 	    (TX_BUFFERS + RX_BUFFERS) * BUFFER_LENGTH * ports) {
@@ -697,6 +699,7 @@ static int wanxl_pci_init_one(struct pci_dev *pdev,
 
 	for (i = 0; i < RX_QUEUE_LENGTH; i++) {
 		struct sk_buff *skb = dev_alloc_skb(BUFFER_LENGTH);
+
 		card->rx_skbs[i] = skb;
 		if (skb)
 			card->status->rx_descs[i].address =
@@ -707,12 +710,12 @@ static int wanxl_pci_init_one(struct pci_dev *pdev,
 	mem = ioremap(mem_phy, PDM_OFFSET + sizeof(firmware));
 	if (!mem) {
 		pr_err("ioremap() failed\n");
- 		wanxl_pci_remove_one(pdev);
+		wanxl_pci_remove_one(pdev);
 		return -EFAULT;
 	}
 
 	for (i = 0; i < sizeof(firmware); i += 4)
-		writel(ntohl(*(__be32*)(firmware + i)), mem + PDM_OFFSET + i);
+		writel(ntohl(*(__be32 *)(firmware + i)), mem + PDM_OFFSET + i);
 
 	for (i = 0; i < ports; i++)
 		writel(card->status_address +
@@ -732,10 +735,11 @@ static int wanxl_pci_init_one(struct pci_dev *pdev,
 
 	timeout = jiffies + 5 * HZ;
 	do {
-		if ((stat = readl(card->plx + PLX_MAILBOX_5)) != 0)
+		stat = readl(card->plx + PLX_MAILBOX_5);
+		if (stat)
 			break;
 		schedule();
-	}while (time_after(timeout, jiffies));
+	} while (time_after(timeout, jiffies));
 
 	if (!stat) {
 		pr_warn("%s: timeout while initializing card firmware\n",
@@ -764,6 +768,7 @@ static int wanxl_pci_init_one(struct pci_dev *pdev,
 		hdlc_device *hdlc;
 		struct port *port = &card->ports[i];
 		struct net_device *dev = alloc_hdlcdev(port);
+
 		if (!dev) {
 			pr_err("%s: unable to allocate memory\n",
 			       pci_name(pdev));
@@ -813,7 +818,6 @@ static const struct pci_device_id wanxl_pci_tbl[] = {
 	{ 0, }
 };
 
-
 static struct pci_driver wanxl_pci_driver = {
 	.name		= "wanXL",
 	.id_table	= wanxl_pci_tbl,
@@ -821,7 +825,6 @@ static struct pci_driver wanxl_pci_driver = {
 	.remove		= wanxl_pci_remove_one,
 };
 
-
 static int __init wanxl_init_module(void)
 {
 #ifdef MODULE
@@ -835,7 +838,6 @@ static void __exit wanxl_cleanup_module(void)
 	pci_unregister_driver(&wanxl_pci_driver);
 }
 
-
 MODULE_AUTHOR("Krzysztof Halasa <khc@pm.waw.pl>");
 MODULE_DESCRIPTION("SBE Inc. wanXL serial port driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/wan/z85230.c b/drivers/net/wan/z85230.c
index 138930c66ad2..982a03488a00 100644
--- a/drivers/net/wan/z85230.c
+++ b/drivers/net/wan/z85230.c
@@ -1,7 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *
- *	(c) Copyright 1998 Alan Cox <alan@lxorguk.ukuu.org.uk>
+/*	(c) Copyright 1998 Alan Cox <alan@lxorguk.ukuu.org.uk>
  *	(c) Copyright 2000, 2001 Red Hat Inc
  *
  *	Development of this driver was funded by Equiinet Ltd
@@ -12,7 +10,7 @@
  *	Asynchronous mode dropped for 2.2. For 2.5 we will attempt the
  *	unification of all the Z85x30 asynchronous drivers for real.
  *
- *	DMA now uses get_free_page as kmalloc buffers may span a 64K 
+ *	DMA now uses get_free_page as kmalloc buffers may span a 64K
  *	boundary.
  *
  *	Modified for SMP safety and SMP locking by Alan Cox
@@ -55,14 +53,13 @@
 
 #include "z85230.h"
 
-
 /**
  *	z8530_read_port - Architecture specific interface function
  *	@p: port to read
  *
  *	Provided port access methods. The Comtrol SV11 requires no delays
  *	between accesses and uses PC I/O. Some drivers may need a 5uS delay
- *	
+ *
  *	In the longer term this should become an architecture specific
  *	section so that this can become a generic driver interface for all
  *	platforms. For now we only handle PC I/O ports with or without the
@@ -74,8 +71,9 @@
 
 static inline int z8530_read_port(unsigned long p)
 {
-	u8 r=inb(Z8530_PORT_OF(p));
-	if(p&Z8530_PORT_SLEEP)	/* gcc should figure this out efficiently ! */
+	u8 r = inb(Z8530_PORT_OF(p));
+
+	if (p & Z8530_PORT_SLEEP) /* gcc should figure this out efficiently ! */
 		udelay(5);
 	return r;
 }
@@ -95,34 +93,30 @@ static inline int z8530_read_port(unsigned long p)
  *	dread 5uS sanity delay.
  */
 
-
 static inline void z8530_write_port(unsigned long p, u8 d)
 {
-	outb(d,Z8530_PORT_OF(p));
-	if(p&Z8530_PORT_SLEEP)
+	outb(d, Z8530_PORT_OF(p));
+	if (p & Z8530_PORT_SLEEP)
 		udelay(5);
 }
 
-
-
 static void z8530_rx_done(struct z8530_channel *c);
 static void z8530_tx_done(struct z8530_channel *c);
 
-
 /**
- *	read_zsreg - Read a register from a Z85230 
+ *	read_zsreg - Read a register from a Z85230
  *	@c: Z8530 channel to read from (2 per chip)
  *	@reg: Register to read
  *	FIXME: Use a spinlock.
- *	
+ *
  *	Most of the Z8530 registers are indexed off the control registers.
  *	A read is done by writing to the control register and reading the
  *	register back.  The caller must hold the lock
  */
- 
+
 static inline u8 read_zsreg(struct z8530_channel *c, u8 reg)
 {
-	if(reg)
+	if (reg)
 		z8530_write_port(c->ctrlio, reg);
 	return z8530_read_port(c->ctrlio);
 }
@@ -138,7 +132,8 @@ static inline u8 read_zsreg(struct z8530_channel *c, u8 reg)
 static inline u8 read_zsdata(struct z8530_channel *c)
 {
 	u8 r;
-	r=z8530_read_port(c->dataio);
+
+	r = z8530_read_port(c->dataio);
 	return r;
 }
 
@@ -156,10 +151,9 @@ static inline u8 read_zsdata(struct z8530_channel *c)
  */
 static inline void write_zsreg(struct z8530_channel *c, u8 reg, u8 val)
 {
-	if(reg)
+	if (reg)
 		z8530_write_port(c->ctrlio, reg);
 	z8530_write_port(c->ctrlio, val);
-
 }
 
 /**
@@ -182,108 +176,94 @@ static inline void write_zsctrl(struct z8530_channel *c, u8 val)
  *
  *	Write directly to the data register on the Z8530
  */
-
-
 static inline void write_zsdata(struct z8530_channel *c, u8 val)
 {
 	z8530_write_port(c->dataio, val);
 }
 
-/*
- *	Register loading parameters for a dead port
+/*	Register loading parameters for a dead port
  */
- 
-u8 z8530_dead_port[]=
-{
+
+u8 z8530_dead_port[] = {
 	255
 };
-
 EXPORT_SYMBOL(z8530_dead_port);
 
-/*
- *	Register loading parameters for currently supported circuit types
+/*	Register loading parameters for currently supported circuit types
  */
 
-
-/*
- *	Data clocked by telco end. This is the correct data for the UK
+/*	Data clocked by telco end. This is the correct data for the UK
  *	"kilostream" service, and most other similar services.
  */
- 
-u8 z8530_hdlc_kilostream[]=
-{
-	4,	SYNC_ENAB|SDLC|X1CLK,
+
+u8 z8530_hdlc_kilostream[] = {
+	4,	SYNC_ENAB | SDLC | X1CLK,
 	2,	0,	/* No vector */
 	1,	0,
-	3,	ENT_HM|RxCRC_ENAB|Rx8,
-	5,	TxCRC_ENAB|RTS|TxENAB|Tx8|DTR,
+	3,	ENT_HM | RxCRC_ENAB | Rx8,
+	5,	TxCRC_ENAB | RTS | TxENAB | Tx8 | DTR,
 	9,	0,		/* Disable interrupts */
 	6,	0xFF,
 	7,	FLAG,
-	10,	ABUNDER|NRZ|CRCPS,/*MARKIDLE ??*/
+	10,	ABUNDER | NRZ | CRCPS,/*MARKIDLE ??*/
 	11,	TCTRxCP,
 	14,	DISDPLL,
-	15,	DCDIE|SYNCIE|CTSIE|TxUIE|BRKIE,
-	1,	EXT_INT_ENAB|TxINT_ENAB|INT_ALL_Rx,
-	9,	NV|MIE|NORESET,
+	15,	DCDIE | SYNCIE | CTSIE | TxUIE | BRKIE,
+	1,	EXT_INT_ENAB | TxINT_ENAB | INT_ALL_Rx,
+	9,	NV | MIE | NORESET,
 	255
 };
-
 EXPORT_SYMBOL(z8530_hdlc_kilostream);
 
-/*
- *	As above but for enhanced chips.
+/*	As above but for enhanced chips.
  */
- 
-u8 z8530_hdlc_kilostream_85230[]=
-{
-	4,	SYNC_ENAB|SDLC|X1CLK,
+
+u8 z8530_hdlc_kilostream_85230[] = {
+	4,	SYNC_ENAB | SDLC | X1CLK,
 	2,	0,	/* No vector */
 	1,	0,
-	3,	ENT_HM|RxCRC_ENAB|Rx8,
-	5,	TxCRC_ENAB|RTS|TxENAB|Tx8|DTR,
+	3,	ENT_HM | RxCRC_ENAB | Rx8,
+	5,	TxCRC_ENAB | RTS | TxENAB | Tx8 | DTR,
 	9,	0,		/* Disable interrupts */
 	6,	0xFF,
 	7,	FLAG,
-	10,	ABUNDER|NRZ|CRCPS,	/* MARKIDLE?? */
+	10,	ABUNDER | NRZ | CRCPS,	/* MARKIDLE?? */
 	11,	TCTRxCP,
 	14,	DISDPLL,
-	15,	DCDIE|SYNCIE|CTSIE|TxUIE|BRKIE,
-	1,	EXT_INT_ENAB|TxINT_ENAB|INT_ALL_Rx,
-	9,	NV|MIE|NORESET,
+	15,	DCDIE | SYNCIE | CTSIE | TxUIE | BRKIE,
+	1,	EXT_INT_ENAB | TxINT_ENAB | INT_ALL_Rx,
+	9,	NV | MIE | NORESET,
 	23,	3,		/* Extended mode AUTO TX and EOM*/
-	
+
 	255
 };
-
 EXPORT_SYMBOL(z8530_hdlc_kilostream_85230);
 
 /**
  *	z8530_flush_fifo - Flush on chip RX FIFO
  *	@c: Channel to flush
  *
- *	Flush the receive FIFO. There is no specific option for this, we 
+ *	Flush the receive FIFO. There is no specific option for this, we
  *	blindly read bytes and discard them. Reading when there is no data
  *	is harmless. The 8530 has a 4 byte FIFO, the 85230 has 8 bytes.
- *	
+ *
  *	All locking is handled for the caller. On return data may still be
  *	present if it arrived during the flush.
  */
- 
+
 static void z8530_flush_fifo(struct z8530_channel *c)
 {
 	read_zsreg(c, R1);
 	read_zsreg(c, R1);
 	read_zsreg(c, R1);
 	read_zsreg(c, R1);
-	if(c->dev->type==Z85230)
-	{
+	if (c->dev->type == Z85230) {
 		read_zsreg(c, R1);
 		read_zsreg(c, R1);
 		read_zsreg(c, R1);
 		read_zsreg(c, R1);
 	}
-}	
+}
 
 /**
  *	z8530_rtsdtr - Control the outgoing DTS/RTS line
@@ -309,7 +289,7 @@ static void z8530_rtsdtr(struct z8530_channel *c, int set)
  *	z8530_rx - Handle a PIO receive event
  *	@c: Z8530 channel to process
  *
- *	Receive handler for receiving in PIO mode. This is much like the 
+ *	Receive handler for receiving in PIO mode. This is much like the
  *	async one but not quite the same or as complex
  *
  *	Note: Its intended that this handler can easily be separated from
@@ -322,77 +302,63 @@ static void z8530_rtsdtr(struct z8530_channel *c, int set)
  *	other code - this is true in the RT case too.
  *
  *	We only cover the sync cases for this. If you want 2Mbit async
- *	do it yourself but consider medical assistance first. This non DMA 
- *	synchronous mode is portable code. The DMA mode assumes PCI like 
+ *	do it yourself but consider medical assistance first. This non DMA
+ *	synchronous mode is portable code. The DMA mode assumes PCI like
  *	ISA DMA
  *
  *	Called with the device lock held
  */
- 
+
 static void z8530_rx(struct z8530_channel *c)
 {
-	u8 ch,stat;
+	u8 ch, stat;
 
-	while(1)
-	{
+	while (1) {
 		/* FIFO empty ? */
-		if(!(read_zsreg(c, R0)&1))
+		if (!(read_zsreg(c, R0) & 1))
 			break;
-		ch=read_zsdata(c);
-		stat=read_zsreg(c, R1);
-	
-		/*
-		 *	Overrun ?
+		ch = read_zsdata(c);
+		stat = read_zsreg(c, R1);
+
+		/*	Overrun ?
 		 */
-		if(c->count < c->max)
-		{
-			*c->dptr++=ch;
+		if (c->count < c->max) {
+			*c->dptr++ = ch;
 			c->count++;
 		}
 
-		if(stat&END_FR)
-		{
-		
-			/*
-			 *	Error ?
+		if (stat & END_FR) {
+			/*	Error ?
 			 */
-			if(stat&(Rx_OVR|CRC_ERR))
-			{
+			if (stat & (Rx_OVR | CRC_ERR)) {
 				/* Rewind the buffer and return */
-				if(c->skb)
-					c->dptr=c->skb->data;
-				c->count=0;
-				if(stat&Rx_OVR)
-				{
+				if (c->skb)
+					c->dptr = c->skb->data;
+				c->count = 0;
+				if (stat & Rx_OVR) {
 					pr_warn("%s: overrun\n", c->dev->name);
 					c->rx_overrun++;
 				}
-				if(stat&CRC_ERR)
-				{
+				if (stat & CRC_ERR) {
 					c->rx_crc_err++;
 					/* printk("crc error\n"); */
 				}
 				/* Shove the frame upstream */
-			}
-			else
-			{
-				/*
-				 *	Drop the lock for RX processing, or
-		 		 *	there are deadlocks
-		 		 */
+			} else {
+				/*	Drop the lock for RX processing, or
+				 *	there are deadlocks
+				 */
 				z8530_rx_done(c);
 				write_zsctrl(c, RES_Rx_CRC);
 			}
 		}
 	}
-	/*
-	 *	Clear irq
+	/*	Clear irq
 	 */
 	write_zsctrl(c, ERR_RES);
 	write_zsctrl(c, RES_H_IUS);
 }
 
-
 /**
  *	z8530_tx - Handle a PIO transmit event
  *	@c: Z8530 channel to process
@@ -402,35 +368,31 @@ static void z8530_rx(struct z8530_channel *c)
  *	in as possible, its quite possible that we won't keep up with the
  *	data rate otherwise.
  */
- 
+
 static void z8530_tx(struct z8530_channel *c)
 {
-	while(c->txcount) {
+	while (c->txcount) {
 		/* FIFO full ? */
-		if(!(read_zsreg(c, R0)&4))
+		if (!(read_zsreg(c, R0) & 4))
 			return;
 		c->txcount--;
-		/*
-		 *	Shovel out the byte
+		/*	Shovel out the byte
 		 */
 		write_zsreg(c, R8, *c->tx_ptr++);
 		write_zsctrl(c, RES_H_IUS);
 		/* We are about to underflow */
-		if(c->txcount==0)
-		{
+		if (c->txcount == 0) {
 			write_zsctrl(c, RES_EOM_L);
-			write_zsreg(c, R10, c->regs[10]&~ABUNDER);
+			write_zsreg(c, R10, c->regs[10] & ~ABUNDER);
 		}
 	}
 
-	
-	/*
-	 *	End of frame TX - fire another one
+	/*	End of frame TX - fire another one
 	 */
-	 
+
 	write_zsctrl(c, RES_Tx_P);
 
-	z8530_tx_done(c);	 
+	z8530_tx_done(c);
 	write_zsctrl(c, RES_H_IUS);
 }
 
@@ -460,8 +422,7 @@ static void z8530_status(struct z8530_channel *chan)
 		z8530_tx_done(chan);
 	}
 
-	if (altered & chan->dcdcheck)
-	{
+	if (altered & chan->dcdcheck) {
 		if (status & chan->dcdcheck) {
 			pr_info("%s: DCD raised\n", chan->dev->name);
 			write_zsreg(chan, R3, chan->regs[3] | RxENABLE);
@@ -474,7 +435,6 @@ static void z8530_status(struct z8530_channel *chan)
 			if (chan->netdevice)
 				netif_carrier_off(chan->netdevice);
 		}
-
 	}
 	write_zsctrl(chan, RES_EXT_INT);
 	write_zsctrl(chan, RES_H_IUS);
@@ -485,7 +445,6 @@ struct z8530_irqhandler z8530_sync = {
 	.tx = z8530_tx,
 	.status = z8530_status,
 };
-
 EXPORT_SYMBOL(z8530_sync);
 
 /**
@@ -497,31 +456,27 @@ EXPORT_SYMBOL(z8530_sync);
  *	events are handled by the DMA hardware. We get a kick here only if
  *	a frame ended.
  */
- 
+
 static void z8530_dma_rx(struct z8530_channel *chan)
 {
-	if(chan->rxdma_on)
-	{
+	if (chan->rxdma_on) {
 		/* Special condition check only */
 		u8 status;
-	
+
 		read_zsreg(chan, R7);
 		read_zsreg(chan, R6);
-		
-		status=read_zsreg(chan, R1);
-	
-		if(status&END_FR)
-		{
+
+		status = read_zsreg(chan, R1);
+
+		if (status & END_FR)
 			z8530_rx_done(chan);	/* Fire up the next one */
-		}		
+
 		write_zsctrl(chan, ERR_RES);
 		write_zsctrl(chan, RES_H_IUS);
-	}
-	else
-	{
+	} else {
 		/* DMA is off right now, drain the slow way */
 		z8530_rx(chan);
-	}	
+	}
 }
 
 /**
@@ -531,11 +486,9 @@ static void z8530_dma_rx(struct z8530_channel *chan)
  *	We have received an interrupt while doing DMA transmissions. It
  *	shouldn't happen. Scream loudly if it does.
  */
- 
 static void z8530_dma_tx(struct z8530_channel *chan)
 {
-	if(!chan->dma_tx)
-	{
+	if (!chan->dma_tx) {
 		pr_warn("Hey who turned the DMA off?\n");
 		z8530_tx(chan);
 		return;
@@ -548,40 +501,35 @@ static void z8530_dma_tx(struct z8530_channel *chan)
 /**
  *	z8530_dma_status - Handle a DMA status exception
  *	@chan: Z8530 channel to process
- *	
+ *
  *	A status event occurred on the Z8530. We receive these for two reasons
  *	when in DMA mode. Firstly if we finished a packet transfer we get one
  *	and kick the next packet out. Secondly we may see a DCD change.
  *
  */
- 
 static void z8530_dma_status(struct z8530_channel *chan)
 {
 	u8 status, altered;
 
-	status=read_zsreg(chan, R0);
-	altered=chan->status^status;
-	
-	chan->status=status;
+	status = read_zsreg(chan, R0);
+	altered = chan->status ^ status;
 
+	chan->status = status;
 
-	if(chan->dma_tx)
-	{
-		if(status&TxEOM)
-		{
+	if (chan->dma_tx) {
+		if (status & TxEOM) {
 			unsigned long flags;
-	
-			flags=claim_dma_lock();
+
+			flags = claim_dma_lock();
 			disable_dma(chan->txdma);
-			clear_dma_ff(chan->txdma);	
-			chan->txdma_on=0;
+			clear_dma_ff(chan->txdma);
+			chan->txdma_on = 0;
 			release_dma_lock(flags);
 			z8530_tx_done(chan);
 		}
 	}
 
-	if (altered & chan->dcdcheck)
-	{
+	if (altered & chan->dcdcheck) {
 		if (status & chan->dcdcheck) {
 			pr_info("%s: DCD raised\n", chan->dev->name);
 			write_zsreg(chan, R3, chan->regs[3] | RxENABLE);
@@ -621,21 +569,18 @@ static struct z8530_irqhandler z8530_txdma_sync = {
  *	(eg the MacII) we must clear the interrupt cause or die.
  */
 
-
 static void z8530_rx_clear(struct z8530_channel *c)
 {
-	/*
-	 *	Data and status bytes
+	/*	Data and status bytes
 	 */
 	u8 stat;
 
 	read_zsdata(c);
-	stat=read_zsreg(c, R1);
-	
-	if(stat&END_FR)
+	stat = read_zsreg(c, R1);
+
+	if (stat & END_FR)
 		write_zsctrl(c, RES_Rx_CRC);
-	/*
-	 *	Clear irq
+	/*	Clear irq
 	 */
 	write_zsctrl(c, ERR_RES);
 	write_zsctrl(c, RES_H_IUS);
@@ -667,8 +612,9 @@ static void z8530_tx_clear(struct z8530_channel *c)
 
 static void z8530_status_clear(struct z8530_channel *chan)
 {
-	u8 status=read_zsreg(chan, R0);
-	if(status&TxEOM)
+	u8 status = read_zsreg(chan, R0);
+
+	if (status & TxEOM)
 		write_zsctrl(chan, ERR_RES);
 	write_zsctrl(chan, RES_EXT_INT);
 	write_zsctrl(chan, RES_H_IUS);
@@ -679,13 +625,11 @@ struct z8530_irqhandler z8530_nop = {
 	.tx = z8530_tx_clear,
 	.status = z8530_status_clear,
 };
-
-
 EXPORT_SYMBOL(z8530_nop);
 
 /**
  *	z8530_interrupt - Handle an interrupt from a Z8530
- *	@irq: 	Interrupt number
+ *	@irq: Interrupt number
  *	@dev_id: The Z8530 device that is interrupting.
  *
  *	A Z85[2]30 device has stuck its hand in the air for attention.
@@ -701,78 +645,73 @@ EXPORT_SYMBOL(z8530_nop);
 
 irqreturn_t z8530_interrupt(int irq, void *dev_id)
 {
-	struct z8530_dev *dev=dev_id;
+	struct z8530_dev *dev = dev_id;
 	u8 intr;
 	static volatile int locker=0;
-	int work=0;
+	int work = 0;
 	struct z8530_irqhandler *irqs;
-	
-	if(locker)
-	{
+
+	if (locker) {
 		pr_err("IRQ re-enter\n");
 		return IRQ_NONE;
 	}
-	locker=1;
+	locker = 1;
 
 	spin_lock(&dev->lock);
 
-	while(++work<5000)
-	{
-
+	while (++work < 5000) {
 		intr = read_zsreg(&dev->chanA, R3);
-		if(!(intr & (CHARxIP|CHATxIP|CHAEXT|CHBRxIP|CHBTxIP|CHBEXT)))
+		if (!(intr &
+		   (CHARxIP | CHATxIP | CHAEXT | CHBRxIP | CHBTxIP | CHBEXT)))
 			break;
-	
-		/* This holds the IRQ status. On the 8530 you must read it from chan 
-		   A even though it applies to the whole chip */
-		
+
+		/* This holds the IRQ status. On the 8530 you must read it
+		 * from chan A even though it applies to the whole chip
+		 */
+
 		/* Now walk the chip and see what it is wanting - it may be
-		   an IRQ for someone else remember */
-		   
-		irqs=dev->chanA.irqs;
+		 * an IRQ for someone else remember
+		 */
+
+		irqs = dev->chanA.irqs;
 
-		if(intr & (CHARxIP|CHATxIP|CHAEXT))
-		{
-			if(intr&CHARxIP)
+		if (intr & (CHARxIP | CHATxIP | CHAEXT)) {
+			if (intr & CHARxIP)
 				irqs->rx(&dev->chanA);
-			if(intr&CHATxIP)
+			if (intr & CHATxIP)
 				irqs->tx(&dev->chanA);
-			if(intr&CHAEXT)
+			if (intr & CHAEXT)
 				irqs->status(&dev->chanA);
 		}
 
-		irqs=dev->chanB.irqs;
+		irqs = dev->chanB.irqs;
 
-		if(intr & (CHBRxIP|CHBTxIP|CHBEXT))
-		{
-			if(intr&CHBRxIP)
+		if (intr & (CHBRxIP | CHBTxIP | CHBEXT)) {
+			if (intr & CHBRxIP)
 				irqs->rx(&dev->chanB);
-			if(intr&CHBTxIP)
+			if (intr & CHBTxIP)
 				irqs->tx(&dev->chanB);
-			if(intr&CHBEXT)
+			if (intr & CHBEXT)
 				irqs->status(&dev->chanB);
 		}
 	}
 	spin_unlock(&dev->lock);
-	if(work==5000)
+	if (work == 5000)
 		pr_err("%s: interrupt jammed - abort(0x%X)!\n",
 		       dev->name, intr);
 	/* Ok all done */
-	locker=0;
+	locker = 0;
 	return IRQ_HANDLED;
 }
-
 EXPORT_SYMBOL(z8530_interrupt);
 
-static const u8 reg_init[16]=
-{
-	0,0,0,0,
-	0,0,0,0,
-	0,0,0,0,
-	0x55,0,0,0
+static const u8 reg_init[16] = {
+	0, 0, 0, 0,
+	0, 0, 0, 0,
+	0, 0, 0, 0,
+	0x55, 0, 0, 0
 };
 
-
 /**
  *	z8530_sync_open - Open a Z8530 channel for PIO
  *	@dev:	The network interface we are using
@@ -781,7 +720,6 @@ static const u8 reg_init[16]=
  *	Switch a Z8530 into synchronous mode without DMA assist. We
  *	raise the RTS/DTR and commence network operation.
  */
- 
 int z8530_sync_open(struct net_device *dev, struct z8530_channel *c)
 {
 	unsigned long flags;
@@ -789,7 +727,7 @@ int z8530_sync_open(struct net_device *dev, struct z8530_channel *c)
 	spin_lock_irqsave(c->lock, flags);
 
 	c->sync = 1;
-	c->mtu = dev->mtu+64;
+	c->mtu = dev->mtu + 64;
 	c->count = 0;
 	c->skb = NULL;
 	c->skb2 = NULL;
@@ -798,17 +736,15 @@ int z8530_sync_open(struct net_device *dev, struct z8530_channel *c)
 	/* This loads the double buffer up */
 	z8530_rx_done(c);	/* Load the frame ring */
 	z8530_rx_done(c);	/* Load the backup frame */
-	z8530_rtsdtr(c,1);
+	z8530_rtsdtr(c, 1);
 	c->dma_tx = 0;
-	c->regs[R1]|=TxINT_ENAB;
+	c->regs[R1] |= TxINT_ENAB;
 	write_zsreg(c, R1, c->regs[R1]);
-	write_zsreg(c, R3, c->regs[R3]|RxENABLE);
+	write_zsreg(c, R3, c->regs[R3] | RxENABLE);
 
 	spin_unlock_irqrestore(c->lock, flags);
 	return 0;
 }
-
-
 EXPORT_SYMBOL(z8530_sync_open);
 
 /**
@@ -819,25 +755,23 @@ EXPORT_SYMBOL(z8530_sync_open);
  *	Close down a Z8530 interface and switch its interrupt handlers
  *	to discard future events.
  */
- 
 int z8530_sync_close(struct net_device *dev, struct z8530_channel *c)
 {
 	u8 chk;
 	unsigned long flags;
-	
+
 	spin_lock_irqsave(c->lock, flags);
 	c->irqs = &z8530_nop;
 	c->max = 0;
 	c->sync = 0;
-	
-	chk=read_zsreg(c,R0);
+
+	chk = read_zsreg(c, R0);
 	write_zsreg(c, R3, c->regs[R3]);
-	z8530_rtsdtr(c,0);
+	z8530_rtsdtr(c, 0);
 
 	spin_unlock_irqrestore(c->lock, flags);
 	return 0;
 }
-
 EXPORT_SYMBOL(z8530_sync_close);
 
 /**
@@ -849,91 +783,83 @@ EXPORT_SYMBOL(z8530_sync_close);
  *	ISA DMA channels must be available for this to work. We assume ISA
  *	DMA driven I/O and PC limits on access.
  */
- 
 int z8530_sync_dma_open(struct net_device *dev, struct z8530_channel *c)
 {
 	unsigned long cflags, dflags;
-	
+
 	c->sync = 1;
-	c->mtu = dev->mtu+64;
+	c->mtu = dev->mtu + 64;
 	c->count = 0;
 	c->skb = NULL;
 	c->skb2 = NULL;
-	/*
-	 *	Load the DMA interfaces up
+
+	/*	Load the DMA interfaces up
 	 */
 	c->rxdma_on = 0;
 	c->txdma_on = 0;
-	
-	/*
-	 *	Allocate the DMA flip buffers. Limit by page size.
+
+	/*	Allocate the DMA flip buffers. Limit by page size.
 	 *	Everyone runs 1500 mtu or less on wan links so this
 	 *	should be fine.
 	 */
-	 
-	if(c->mtu  > PAGE_SIZE/2)
+
+	if (c->mtu  > PAGE_SIZE / 2)
 		return -EMSGSIZE;
-	 
-	c->rx_buf[0]=(void *)get_zeroed_page(GFP_KERNEL|GFP_DMA);
-	if(c->rx_buf[0]==NULL)
+
+	c->rx_buf[0] = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	if (!c->rx_buf[0])
 		return -ENOBUFS;
-	c->rx_buf[1]=c->rx_buf[0]+PAGE_SIZE/2;
-	
-	c->tx_dma_buf[0]=(void *)get_zeroed_page(GFP_KERNEL|GFP_DMA);
-	if(c->tx_dma_buf[0]==NULL)
-	{
+	c->rx_buf[1] = c->rx_buf[0] + PAGE_SIZE / 2;
+
+	c->tx_dma_buf[0] = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	if (!c->tx_dma_buf[0]) {
 		free_page((unsigned long)c->rx_buf[0]);
-		c->rx_buf[0]=NULL;
+		c->rx_buf[0] = NULL;
 		return -ENOBUFS;
 	}
-	c->tx_dma_buf[1]=c->tx_dma_buf[0]+PAGE_SIZE/2;
+	c->tx_dma_buf[1] = c->tx_dma_buf[0] + PAGE_SIZE / 2;
 
-	c->tx_dma_used=0;
+	c->tx_dma_used = 0;
 	c->dma_tx = 1;
-	c->dma_num=0;
-	c->dma_ready=1;
-	
-	/*
-	 *	Enable DMA control mode
+	c->dma_num = 0;
+	c->dma_ready = 1;
+
+	/*	Enable DMA control mode
 	 */
 
 	spin_lock_irqsave(c->lock, cflags);
-	 
-	/*
-	 *	TX DMA via DIR/REQ
+
+	/*	TX DMA via DIR/REQ
+	 */
+
+	c->regs[R14] |= DTRREQ;
+	write_zsreg(c, R14, c->regs[R14]);
+
+	c->regs[R1] &= ~TxINT_ENAB;
+	write_zsreg(c, R1, c->regs[R1]);
+
+	/*	RX DMA via W/Req
 	 */
-	 
-	c->regs[R14]|= DTRREQ;
-	write_zsreg(c, R14, c->regs[R14]);     
 
-	c->regs[R1]&= ~TxINT_ENAB;
+	c->regs[R1] |= WT_FN_RDYFN;
+	c->regs[R1] |= WT_RDY_RT;
+	c->regs[R1] |= INT_ERR_Rx;
+	c->regs[R1] &= ~TxINT_ENAB;
 	write_zsreg(c, R1, c->regs[R1]);
-	
-	/*
-	 *	RX DMA via W/Req
-	 */	 
-
-	c->regs[R1]|= WT_FN_RDYFN;
-	c->regs[R1]|= WT_RDY_RT;
-	c->regs[R1]|= INT_ERR_Rx;
-	c->regs[R1]&= ~TxINT_ENAB;
+	c->regs[R1] |= WT_RDY_ENAB;
 	write_zsreg(c, R1, c->regs[R1]);
-	c->regs[R1]|= WT_RDY_ENAB;
-	write_zsreg(c, R1, c->regs[R1]);            
-	
-	/*
-	 *	DMA interrupts
+
+	/*	DMA interrupts
+	 */
+
+	/*	Set up the DMA configuration
 	 */
-	 
-	/*
-	 *	Set up the DMA configuration
-	 */	
-	 
-	dflags=claim_dma_lock();
-	 
+
+	dflags = claim_dma_lock();
+
 	disable_dma(c->rxdma);
 	clear_dma_ff(c->rxdma);
-	set_dma_mode(c->rxdma, DMA_MODE_READ|0x10);
+	set_dma_mode(c->rxdma, DMA_MODE_READ | 0x10);
 	set_dma_addr(c->rxdma, virt_to_bus(c->rx_buf[0]));
 	set_dma_count(c->rxdma, c->mtu);
 	enable_dma(c->rxdma);
@@ -942,26 +868,24 @@ int z8530_sync_dma_open(struct net_device *dev, struct z8530_channel *c)
 	clear_dma_ff(c->txdma);
 	set_dma_mode(c->txdma, DMA_MODE_WRITE);
 	disable_dma(c->txdma);
-	
+
 	release_dma_lock(dflags);
-	
-	/*
-	 *	Select the DMA interrupt handlers
+
+	/*	Select the DMA interrupt handlers
 	 */
 
 	c->rxdma_on = 1;
 	c->txdma_on = 1;
 	c->tx_dma_used = 1;
-	 
+
 	c->irqs = &z8530_dma_sync;
-	z8530_rtsdtr(c,1);
-	write_zsreg(c, R3, c->regs[R3]|RxENABLE);
+	z8530_rtsdtr(c, 1);
+	write_zsreg(c, R3, c->regs[R3] | RxENABLE);
 
 	spin_unlock_irqrestore(c->lock, cflags);
-	
+
 	return 0;
 }
-
 EXPORT_SYMBOL(z8530_sync_dma_open);
 
 /**
@@ -972,66 +896,60 @@ EXPORT_SYMBOL(z8530_sync_dma_open);
  *	Shut down a DMA mode synchronous interface. Halt the DMA, and
  *	free the buffers.
  */
- 
 int z8530_sync_dma_close(struct net_device *dev, struct z8530_channel *c)
 {
 	u8 chk;
 	unsigned long flags;
-	
+
 	c->irqs = &z8530_nop;
 	c->max = 0;
 	c->sync = 0;
-	
-	/*
-	 *	Disable the PC DMA channels
+
+	/*	Disable the PC DMA channels
 	 */
-	
-	flags=claim_dma_lock(); 
+
+	flags = claim_dma_lock();
 	disable_dma(c->rxdma);
 	clear_dma_ff(c->rxdma);
-	
+
 	c->rxdma_on = 0;
-	
+
 	disable_dma(c->txdma);
 	clear_dma_ff(c->txdma);
 	release_dma_lock(flags);
-	
+
 	c->txdma_on = 0;
 	c->tx_dma_used = 0;
 
 	spin_lock_irqsave(c->lock, flags);
 
-	/*
-	 *	Disable DMA control mode
+	/*	Disable DMA control mode
 	 */
-	 
-	c->regs[R1]&= ~WT_RDY_ENAB;
-	write_zsreg(c, R1, c->regs[R1]);            
-	c->regs[R1]&= ~(WT_RDY_RT|WT_FN_RDYFN|INT_ERR_Rx);
-	c->regs[R1]|= INT_ALL_Rx;
+
+	c->regs[R1] &= ~WT_RDY_ENAB;
 	write_zsreg(c, R1, c->regs[R1]);
-	c->regs[R14]&= ~DTRREQ;
-	write_zsreg(c, R14, c->regs[R14]);   
-	
-	if(c->rx_buf[0])
-	{
+	c->regs[R1] &= ~(WT_RDY_RT | WT_FN_RDYFN | INT_ERR_Rx);
+	c->regs[R1] |= INT_ALL_Rx;
+	write_zsreg(c, R1, c->regs[R1]);
+	c->regs[R14] &= ~DTRREQ;
+	write_zsreg(c, R14, c->regs[R14]);
+
+	if (c->rx_buf[0]) {
 		free_page((unsigned long)c->rx_buf[0]);
-		c->rx_buf[0]=NULL;
+		c->rx_buf[0] = NULL;
 	}
-	if(c->tx_dma_buf[0])
-	{
+	if (c->tx_dma_buf[0]) {
 		free_page((unsigned  long)c->tx_dma_buf[0]);
-		c->tx_dma_buf[0]=NULL;
+		c->tx_dma_buf[0] = NULL;
 	}
-	chk=read_zsreg(c,R0);
+	chk = read_zsreg(c, R0);
 	write_zsreg(c, R3, c->regs[R3]);
-	z8530_rtsdtr(c,0);
+	z8530_rtsdtr(c, 0);
 
 	spin_unlock_irqrestore(c->lock, flags);
 
 	return 0;
 }
-
 EXPORT_SYMBOL(z8530_sync_dma_close);
 
 /**
@@ -1050,65 +968,58 @@ int z8530_sync_txdma_open(struct net_device *dev, struct z8530_channel *c)
 
 	printk("Opening sync interface for TX-DMA\n");
 	c->sync = 1;
-	c->mtu = dev->mtu+64;
+	c->mtu = dev->mtu + 64;
 	c->count = 0;
 	c->skb = NULL;
 	c->skb2 = NULL;
-	
-	/*
-	 *	Allocate the DMA flip buffers. Limit by page size.
+
+	/*	Allocate the DMA flip buffers. Limit by page size.
 	 *	Everyone runs 1500 mtu or less on wan links so this
 	 *	should be fine.
 	 */
-	 
-	if(c->mtu  > PAGE_SIZE/2)
+
+	if (c->mtu > PAGE_SIZE / 2)
 		return -EMSGSIZE;
-	 
-	c->tx_dma_buf[0]=(void *)get_zeroed_page(GFP_KERNEL|GFP_DMA);
-	if(c->tx_dma_buf[0]==NULL)
-		return -ENOBUFS;
 
-	c->tx_dma_buf[1] = c->tx_dma_buf[0] + PAGE_SIZE/2;
+	c->tx_dma_buf[0] = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	if (!c->tx_dma_buf[0])
+		return -ENOBUFS;
 
+	c->tx_dma_buf[1] = c->tx_dma_buf[0] + PAGE_SIZE / 2;
 
 	spin_lock_irqsave(c->lock, cflags);
 
-	/*
-	 *	Load the PIO receive ring
+	/*	Load the PIO receive ring
 	 */
 
 	z8530_rx_done(c);
 	z8530_rx_done(c);
 
- 	/*
-	 *	Load the DMA interfaces up
+	/*	Load the DMA interfaces up
 	 */
 
 	c->rxdma_on = 0;
 	c->txdma_on = 0;
-	
-	c->tx_dma_used=0;
-	c->dma_num=0;
-	c->dma_ready=1;
+
+	c->tx_dma_used = 0;
+	c->dma_num = 0;
+	c->dma_ready = 1;
 	c->dma_tx = 1;
 
- 	/*
-	 *	Enable DMA control mode
+	/*	Enable DMA control mode
 	 */
 
- 	/*
-	 *	TX DMA via DIR/REQ
- 	 */
-	c->regs[R14]|= DTRREQ;
-	write_zsreg(c, R14, c->regs[R14]);     
-	
-	c->regs[R1]&= ~TxINT_ENAB;
+	/*	TX DMA via DIR/REQ
+	 */
+	c->regs[R14] |= DTRREQ;
+	write_zsreg(c, R14, c->regs[R14]);
+
+	c->regs[R1] &= ~TxINT_ENAB;
 	write_zsreg(c, R1, c->regs[R1]);
-	
-	/*
-	 *	Set up the DMA configuration
-	 */	
-	 
+
+	/*	Set up the DMA configuration
+	 */
+
 	dflags = claim_dma_lock();
 
 	disable_dma(c->txdma);
@@ -1117,23 +1028,21 @@ int z8530_sync_txdma_open(struct net_device *dev, struct z8530_channel *c)
 	disable_dma(c->txdma);
 
 	release_dma_lock(dflags);
-	
-	/*
-	 *	Select the DMA interrupt handlers
+
+	/*	Select the DMA interrupt handlers
 	 */
 
 	c->rxdma_on = 0;
 	c->txdma_on = 1;
 	c->tx_dma_used = 1;
-	 
+
 	c->irqs = &z8530_txdma_sync;
-	z8530_rtsdtr(c,1);
-	write_zsreg(c, R3, c->regs[R3]|RxENABLE);
+	z8530_rtsdtr(c, 1);
+	write_zsreg(c, R3, c->regs[R3] | RxENABLE);
 	spin_unlock_irqrestore(c->lock, cflags);
-	
+
 	return 0;
 }
-
 EXPORT_SYMBOL(z8530_sync_txdma_open);
 
 /**
@@ -1141,7 +1050,7 @@ EXPORT_SYMBOL(z8530_sync_txdma_open);
  *	@dev: Network device to detach
  *	@c: Z8530 channel to move into discard mode
  *
- *	Shut down a DMA/PIO split mode synchronous interface. Halt the DMA, 
+ *	Shut down a DMA/PIO split mode synchronous interface. Halt the DMA,
  *	and  free the buffers.
  */
 
@@ -1150,17 +1059,15 @@ int z8530_sync_txdma_close(struct net_device *dev, struct z8530_channel *c)
 	unsigned long dflags, cflags;
 	u8 chk;
 
-	
 	spin_lock_irqsave(c->lock, cflags);
-	
+
 	c->irqs = &z8530_nop;
 	c->max = 0;
 	c->sync = 0;
-	
-	/*
-	 *	Disable the PC DMA channels
+
+	/*	Disable the PC DMA channels
 	 */
-	 
+
 	dflags = claim_dma_lock();
 
 	disable_dma(c->txdma);
@@ -1170,41 +1077,34 @@ int z8530_sync_txdma_close(struct net_device *dev, struct z8530_channel *c)
 
 	release_dma_lock(dflags);
 
-	/*
-	 *	Disable DMA control mode
+	/*	Disable DMA control mode
 	 */
-	 
-	c->regs[R1]&= ~WT_RDY_ENAB;
-	write_zsreg(c, R1, c->regs[R1]);            
-	c->regs[R1]&= ~(WT_RDY_RT|WT_FN_RDYFN|INT_ERR_Rx);
-	c->regs[R1]|= INT_ALL_Rx;
+
+	c->regs[R1] &= ~WT_RDY_ENAB;
+	write_zsreg(c, R1, c->regs[R1]);
+	c->regs[R1] &= ~(WT_RDY_RT | WT_FN_RDYFN | INT_ERR_Rx);
+	c->regs[R1] |= INT_ALL_Rx;
 	write_zsreg(c, R1, c->regs[R1]);
-	c->regs[R14]&= ~DTRREQ;
-	write_zsreg(c, R14, c->regs[R14]);   
-	
-	if(c->tx_dma_buf[0])
-	{
+	c->regs[R14] &= ~DTRREQ;
+	write_zsreg(c, R14, c->regs[R14]);
+
+	if (c->tx_dma_buf[0]) {
 		free_page((unsigned long)c->tx_dma_buf[0]);
-		c->tx_dma_buf[0]=NULL;
+		c->tx_dma_buf[0] = NULL;
 	}
-	chk=read_zsreg(c,R0);
+	chk = read_zsreg(c, R0);
 	write_zsreg(c, R3, c->regs[R3]);
-	z8530_rtsdtr(c,0);
+	z8530_rtsdtr(c, 0);
 
 	spin_unlock_irqrestore(c->lock, cflags);
 	return 0;
 }
-
-
 EXPORT_SYMBOL(z8530_sync_txdma_close);
 
-
-/*
- *	Name strings for Z8530 chips. SGI claim to have a 130, Zilog deny
+/*	Name strings for Z8530 chips. SGI claim to have a 130, Zilog deny
  *	it exists...
  */
- 
-static const char *z8530_type_name[]={
+static const char * const z8530_type_name[] = {
 	"Z8530",
 	"Z85C30",
 	"Z85230"
@@ -1224,78 +1124,71 @@ static const char *z8530_type_name[]={
 void z8530_describe(struct z8530_dev *dev, char *mapping, unsigned long io)
 {
 	pr_info("%s: %s found at %s 0x%lX, IRQ %d\n",
-		dev->name, 
+		dev->name,
 		z8530_type_name[dev->type],
 		mapping,
 		Z8530_PORT_OF(io),
 		dev->irq);
 }
-
 EXPORT_SYMBOL(z8530_describe);
 
-/*
- *	Locked operation part of the z8530 init code
+/*	Locked operation part of the z8530 init code
  */
- 
 static inline int do_z8530_init(struct z8530_dev *dev)
 {
 	/* NOP the interrupt handlers first - we might get a
-	   floating IRQ transition when we reset the chip */
-	dev->chanA.irqs=&z8530_nop;
-	dev->chanB.irqs=&z8530_nop;
-	dev->chanA.dcdcheck=DCD;
-	dev->chanB.dcdcheck=DCD;
+	 * floating IRQ transition when we reset the chip
+	 */
+	dev->chanA.irqs = &z8530_nop;
+	dev->chanB.irqs = &z8530_nop;
+	dev->chanA.dcdcheck = DCD;
+	dev->chanB.dcdcheck = DCD;
 
 	/* Reset the chip */
 	write_zsreg(&dev->chanA, R9, 0xC0);
 	udelay(200);
 	/* Now check its valid */
 	write_zsreg(&dev->chanA, R12, 0xAA);
-	if(read_zsreg(&dev->chanA, R12)!=0xAA)
+	if (read_zsreg(&dev->chanA, R12) != 0xAA)
 		return -ENODEV;
 	write_zsreg(&dev->chanA, R12, 0x55);
-	if(read_zsreg(&dev->chanA, R12)!=0x55)
+	if (read_zsreg(&dev->chanA, R12) != 0x55)
 		return -ENODEV;
-		
-	dev->type=Z8530;
-	
-	/*
-	 *	See the application note.
+
+	dev->type = Z8530;
+
+	/*	See the application note.
 	 */
-	 
+
 	write_zsreg(&dev->chanA, R15, 0x01);
-	
-	/*
-	 *	If we can set the low bit of R15 then
+
+	/*	If we can set the low bit of R15 then
 	 *	the chip is enhanced.
 	 */
-	 
-	if(read_zsreg(&dev->chanA, R15)==0x01)
-	{
+
+	if (read_zsreg(&dev->chanA, R15) == 0x01) {
 		/* This C30 versus 230 detect is from Klaus Kudielka's dmascc */
 		/* Put a char in the fifo */
 		write_zsreg(&dev->chanA, R8, 0);
-		if(read_zsreg(&dev->chanA, R0)&Tx_BUF_EMP)
+		if (read_zsreg(&dev->chanA, R0) & Tx_BUF_EMP)
 			dev->type = Z85230;	/* Has a FIFO */
 		else
 			dev->type = Z85C30;	/* Z85C30, 1 byte FIFO */
 	}
-		
-	/*
-	 *	The code assumes R7' and friends are
+
+	/*	The code assumes R7' and friends are
 	 *	off. Use write_zsext() for these and keep
 	 *	this bit clear.
 	 */
-	 
+
 	write_zsreg(&dev->chanA, R15, 0);
-		
-	/*
-	 *	At this point it looks like the chip is behaving
+
+	/*	At this point it looks like the chip is behaving
 	 */
-	 
+
 	memcpy(dev->chanA.regs, reg_init, 16);
-	memcpy(dev->chanB.regs, reg_init ,16);
-	
+	memcpy(dev->chanB.regs, reg_init, 16);
+
 	return 0;
 }
 
@@ -1332,36 +1225,32 @@ int z8530_init(struct z8530_dev *dev)
 
 	return ret;
 }
-
-
 EXPORT_SYMBOL(z8530_init);
 
 /**
  *	z8530_shutdown - Shutdown a Z8530 device
  *	@dev: The Z8530 chip to shutdown
  *
- *	We set the interrupt handlers to silence any interrupts. We then 
+ *	We set the interrupt handlers to silence any interrupts. We then
  *	reset the chip and wait 100uS to be sure the reset completed. Just
  *	in case the caller then tries to do stuff.
  *
  *	This is called without the lock held
  */
- 
 int z8530_shutdown(struct z8530_dev *dev)
 {
 	unsigned long flags;
 	/* Reset the chip */
 
 	spin_lock_irqsave(&dev->lock, flags);
-	dev->chanA.irqs=&z8530_nop;
-	dev->chanB.irqs=&z8530_nop;
+	dev->chanA.irqs = &z8530_nop;
+	dev->chanB.irqs = &z8530_nop;
 	write_zsreg(&dev->chanA, R9, 0xC0);
 	/* We must lock the udelay, the chip is offlimits here */
 	udelay(100);
 	spin_unlock_irqrestore(&dev->lock, flags);
 	return 0;
 }
-
 EXPORT_SYMBOL(z8530_shutdown);
 
 /**
@@ -1370,7 +1259,7 @@ EXPORT_SYMBOL(z8530_shutdown);
  *	@rtable: table of register, value pairs
  *	FIXME: ioctl to allow user uploaded tables
  *
- *	Load a Z8530 channel up from the system data. We use +16 to 
+ *	Load a Z8530 channel up from the system data. We use +16 to
  *	indicate the "prime" registers. The value 255 terminates the
  *	table.
  */
@@ -1381,41 +1270,39 @@ int z8530_channel_load(struct z8530_channel *c, u8 *rtable)
 
 	spin_lock_irqsave(c->lock, flags);
 
-	while(*rtable!=255)
-	{
-		int reg=*rtable++;
-		if(reg>0x0F)
-			write_zsreg(c, R15, c->regs[15]|1);
-		write_zsreg(c, reg&0x0F, *rtable);
-		if(reg>0x0F)
-			write_zsreg(c, R15, c->regs[15]&~1);
-		c->regs[reg]=*rtable++;
+	while (*rtable != 255) {
+		int reg = *rtable++;
+
+		if (reg > 0x0F)
+			write_zsreg(c, R15, c->regs[15] | 1);
+		write_zsreg(c, reg & 0x0F, *rtable);
+		if (reg > 0x0F)
+			write_zsreg(c, R15, c->regs[15] & ~1);
+		c->regs[reg] = *rtable++;
 	}
-	c->rx_function=z8530_null_rx;
-	c->skb=NULL;
-	c->tx_skb=NULL;
-	c->tx_next_skb=NULL;
-	c->mtu=1500;
-	c->max=0;
-	c->count=0;
-	c->status=read_zsreg(c, R0);
-	c->sync=1;
-	write_zsreg(c, R3, c->regs[R3]|RxENABLE);
+	c->rx_function = z8530_null_rx;
+	c->skb = NULL;
+	c->tx_skb = NULL;
+	c->tx_next_skb = NULL;
+	c->mtu = 1500;
+	c->max = 0;
+	c->count = 0;
+	c->status = read_zsreg(c, R0);
+	c->sync = 1;
+	write_zsreg(c, R3, c->regs[R3] | RxENABLE);
 
 	spin_unlock_irqrestore(c->lock, flags);
 	return 0;
 }
-
 EXPORT_SYMBOL(z8530_channel_load);
 
-
 /**
  *	z8530_tx_begin - Begin packet transmission
  *	@c: The Z8530 channel to kick
  *
  *	This is the speed sensitive side of transmission. If we are called
  *	and no buffer is being transmitted we commence the next buffer. If
- *	nothing is queued we idle the sync. 
+ *	nothing is queued we idle the sync.
  *
  *	Note: We are handling this code path in the interrupt path, keep it
  *	fast or bad things will happen.
@@ -1426,85 +1313,68 @@ EXPORT_SYMBOL(z8530_channel_load);
 static void z8530_tx_begin(struct z8530_channel *c)
 {
 	unsigned long flags;
-	if(c->tx_skb)
+
+	if (c->tx_skb)
 		return;
-		
-	c->tx_skb=c->tx_next_skb;
-	c->tx_next_skb=NULL;
-	c->tx_ptr=c->tx_next_ptr;
-	
-	if(c->tx_skb==NULL)
-	{
+
+	c->tx_skb = c->tx_next_skb;
+	c->tx_next_skb = NULL;
+	c->tx_ptr = c->tx_next_ptr;
+
+	if (!c->tx_skb) {
 		/* Idle on */
-		if(c->dma_tx)
-		{
-			flags=claim_dma_lock();
+		if (c->dma_tx) {
+			flags = claim_dma_lock();
 			disable_dma(c->txdma);
-			/*
-			 *	Check if we crapped out.
+			/*	Check if we crapped out.
 			 */
-			if (get_dma_residue(c->txdma))
-			{
+			if (get_dma_residue(c->txdma)) {
 				c->netdevice->stats.tx_dropped++;
 				c->netdevice->stats.tx_fifo_errors++;
 			}
 			release_dma_lock(flags);
 		}
-		c->txcount=0;
-	}
-	else
-	{
-		c->txcount=c->tx_skb->len;
-		
-		
-		if(c->dma_tx)
-		{
-			/*
-			 *	FIXME. DMA is broken for the original 8530,
+		c->txcount = 0;
+	} else {
+		c->txcount = c->tx_skb->len;
+
+		if (c->dma_tx) {
+			/*	FIXME. DMA is broken for the original 8530,
 			 *	on the older parts we need to set a flag and
 			 *	wait for a further TX interrupt to fire this
-			 *	stage off	
+			 *	stage off
 			 */
-			 
-			flags=claim_dma_lock();
+
+			flags = claim_dma_lock();
 			disable_dma(c->txdma);
 
-			/*
-			 *	These two are needed by the 8530/85C30
+			/*	These two are needed by the 8530/85C30
 			 *	and must be issued when idling.
 			 */
-			 
-			if(c->dev->type!=Z85230)
-			{
+			if (c->dev->type != Z85230) {
 				write_zsctrl(c, RES_Tx_CRC);
 				write_zsctrl(c, RES_EOM_L);
-			}	
-			write_zsreg(c, R10, c->regs[10]&~ABUNDER);
+			}
+			write_zsreg(c, R10, c->regs[10] & ~ABUNDER);
 			clear_dma_ff(c->txdma);
 			set_dma_addr(c->txdma, virt_to_bus(c->tx_ptr));
 			set_dma_count(c->txdma, c->txcount);
 			enable_dma(c->txdma);
 			release_dma_lock(flags);
 			write_zsctrl(c, RES_EOM_L);
-			write_zsreg(c, R5, c->regs[R5]|TxENAB);
-		}
-		else
-		{
-
+			write_zsreg(c, R5, c->regs[R5] | TxENAB);
+		} else {
 			/* ABUNDER off */
 			write_zsreg(c, R10, c->regs[10]);
 			write_zsctrl(c, RES_Tx_CRC);
-	
-			while(c->txcount && (read_zsreg(c,R0)&Tx_BUF_EMP))
-			{		
+
+			while (c->txcount && (read_zsreg(c, R0) & Tx_BUF_EMP)) {
 				write_zsreg(c, R8, *c->tx_ptr++);
 				c->txcount--;
 			}
-
 		}
 	}
-	/*
-	 *	Since we emptied tx_skb we can ask for more
+	/*	Since we emptied tx_skb we can ask for more
 	 */
 	netif_wake_queue(c->netdevice);
 }
@@ -1525,7 +1395,7 @@ static void z8530_tx_done(struct z8530_channel *c)
 	struct sk_buff *skb;
 
 	/* Actually this can happen.*/
-	if (c->tx_skb == NULL)
+	if (!c->tx_skb)
 		return;
 
 	skb = c->tx_skb;
@@ -1544,12 +1414,10 @@ static void z8530_tx_done(struct z8530_channel *c)
  *	We point the receive handler at this function when idle. Instead
  *	of processing the frames we get to throw them away.
  */
- 
 void z8530_null_rx(struct z8530_channel *c, struct sk_buff *skb)
 {
 	dev_kfree_skb_any(skb);
 }
-
 EXPORT_SYMBOL(z8530_null_rx);
 
 /**
@@ -1564,67 +1432,58 @@ EXPORT_SYMBOL(z8530_null_rx);
  *
  *	Called with the lock held
  */
- 
 static void z8530_rx_done(struct z8530_channel *c)
 {
 	struct sk_buff *skb;
 	int ct;
-	
-	/*
-	 *	Is our receive engine in DMA mode
+
+	/*	Is our receive engine in DMA mode
 	 */
-	 
-	if(c->rxdma_on)
-	{
-		/*
-		 *	Save the ready state and the buffer currently
+	if (c->rxdma_on) {
+		/*	Save the ready state and the buffer currently
 		 *	being used as the DMA target
 		 */
-		 
-		int ready=c->dma_ready;
-		unsigned char *rxb=c->rx_buf[c->dma_num];
+		int ready = c->dma_ready;
+		unsigned char *rxb = c->rx_buf[c->dma_num];
 		unsigned long flags;
-		
-		/*
-		 *	Complete this DMA. Necessary to find the length
-		 */		
-		 
-		flags=claim_dma_lock();
-		
+
+		/*	Complete this DMA. Necessary to find the length
+		 */
+		flags = claim_dma_lock();
+
 		disable_dma(c->rxdma);
 		clear_dma_ff(c->rxdma);
-		c->rxdma_on=0;
-		ct=c->mtu-get_dma_residue(c->rxdma);
-		if(ct<0)
-			ct=2;	/* Shit happens.. */
-		c->dma_ready=0;
-		
-		/*
-		 *	Normal case: the other slot is free, start the next DMA
+		c->rxdma_on = 0;
+		ct = c->mtu - get_dma_residue(c->rxdma);
+		if (ct < 0)
+			ct = 2;	/* Shit happens.. */
+		c->dma_ready = 0;
+
+		/*	Normal case: the other slot is free, start the next DMA
 		 *	into it immediately.
 		 */
-		 
-		if(ready)
-		{
-			c->dma_num^=1;
-			set_dma_mode(c->rxdma, DMA_MODE_READ|0x10);
+
+		if (ready) {
+			c->dma_num ^= 1;
+			set_dma_mode(c->rxdma, DMA_MODE_READ | 0x10);
 			set_dma_addr(c->rxdma, virt_to_bus(c->rx_buf[c->dma_num]));
 			set_dma_count(c->rxdma, c->mtu);
 			c->rxdma_on = 1;
 			enable_dma(c->rxdma);
-			/* Stop any frames that we missed the head of 
-			   from passing */
+			/* Stop any frames that we missed the head of
+			 * from passing
+			 */
 			write_zsreg(c, R0, RES_Rx_CRC);
-		}
-		else
+		} else {
 			/* Can't occur as we dont reenable the DMA irq until
-			   after the flip is done */
+			 * after the flip is done
+			 */
 			netdev_warn(c->netdevice, "DMA flip overrun!\n");
+		}
 
 		release_dma_lock(flags);
 
-		/*
-		 *	Shove the old buffer into an sk_buff. We can't DMA
+		/*	Shove the old buffer into an sk_buff. We can't DMA
 		 *	directly into one on a PC - it might be above the 16Mb
 		 *	boundary. Optimisation - we could check to see if we
 		 *	can avoid the copy. Optimisation 2 - make the memcpy
@@ -1632,7 +1491,7 @@ static void z8530_rx_done(struct z8530_channel *c)
 		 */
 
 		skb = dev_alloc_skb(ct);
-		if (skb == NULL) {
+		if (!skb) {
 			c->netdevice->stats.rx_dropped++;
 			netdev_warn(c->netdevice, "Memory squeeze\n");
 		} else {
@@ -1646,8 +1505,7 @@ static void z8530_rx_done(struct z8530_channel *c)
 		RT_LOCK;
 		skb = c->skb;
 
-		/*
-		 *	The game we play for non DMA is similar. We want to
+		/*	The game we play for non DMA is similar. We want to
 		 *	get the controller set up for the next packet as fast
 		 *	as possible. We potentially only have one byte + the
 		 *	fifo length for this. Thus we want to flip to the new
@@ -1658,7 +1516,7 @@ static void z8530_rx_done(struct z8530_channel *c)
 		 *	sync IRQ for the RT_LOCK area.
 		 *
 		 */
-		ct=c->count;
+		ct = c->count;
 
 		c->skb = c->skb2;
 		c->count = 0;
@@ -1673,15 +1531,13 @@ static void z8530_rx_done(struct z8530_channel *c)
 		RT_UNLOCK;
 
 		c->skb2 = dev_alloc_skb(c->mtu);
-		if (c->skb2 == NULL)
-			netdev_warn(c->netdevice, "memory squeeze\n");
-		else
+		if (c->skb2)
 			skb_put(c->skb2, c->mtu);
+
 		c->netdevice->stats.rx_packets++;
 		c->netdevice->stats.rx_bytes += ct;
 	}
-	/*
-	 *	If we received a frame we must now process it.
+	/*	If we received a frame we must now process it.
 	 */
 	if (skb) {
 		skb_trim(skb, ct);
@@ -1702,9 +1558,10 @@ static void z8530_rx_done(struct z8530_channel *c)
 
 static inline int spans_boundary(struct sk_buff *skb)
 {
-	unsigned long a=(unsigned long)skb->data;
-	a^=(a+skb->len);
-	if(a&0x00010000)	/* If the 64K bit is different.. */
+	unsigned long a = (unsigned long)skb->data;
+
+	a ^= (a + skb->len);
+	if (a & 0x00010000)	/* If the 64K bit is different.. */
 		return 1;
 	return 0;
 }
@@ -1715,60 +1572,54 @@ static inline int spans_boundary(struct sk_buff *skb)
  *	@skb: The packet to kick down the channel
  *
  *	Queue a packet for transmission. Because we have rather
- *	hard to hit interrupt latencies for the Z85230 per packet 
+ *	hard to hit interrupt latencies for the Z85230 per packet
  *	even in DMA mode we do the flip to DMA buffer if needed here
  *	not in the IRQ.
  *
- *	Called from the network code. The lock is not held at this 
+ *	Called from the network code. The lock is not held at this
  *	point.
  */
-
 netdev_tx_t z8530_queue_xmit(struct z8530_channel *c, struct sk_buff *skb)
 {
 	unsigned long flags;
-	
+
 	netif_stop_queue(c->netdevice);
-	if(c->tx_next_skb)
+	if (c->tx_next_skb)
 		return NETDEV_TX_BUSY;
 
-	
 	/* PC SPECIFIC - DMA limits */
-	
-	/*
-	 *	If we will DMA the transmit and its gone over the ISA bus
+	/*	If we will DMA the transmit and its gone over the ISA bus
 	 *	limit, then copy to the flip buffer
 	 */
-	 
-	if(c->dma_tx && ((unsigned long)(virt_to_bus(skb->data+skb->len))>=16*1024*1024 || spans_boundary(skb)))
-	{
-		/* 
-		 *	Send the flip buffer, and flip the flippy bit.
+
+	if (c->dma_tx &&
+	    ((unsigned long)(virt_to_bus(skb->data + skb->len)) >=
+	    16 * 1024 * 1024 || spans_boundary(skb))) {
+		/*	Send the flip buffer, and flip the flippy bit.
 		 *	We don't care which is used when just so long as
 		 *	we never use the same buffer twice in a row. Since
 		 *	only one buffer can be going out at a time the other
 		 *	has to be safe.
 		 */
-		c->tx_next_ptr=c->tx_dma_buf[c->tx_dma_used];
-		c->tx_dma_used^=1;	/* Flip temp buffer */
+		c->tx_next_ptr = c->tx_dma_buf[c->tx_dma_used];
+		c->tx_dma_used ^= 1;	/* Flip temp buffer */
 		skb_copy_from_linear_data(skb, c->tx_next_ptr, skb->len);
+	} else {
+		c->tx_next_ptr = skb->data;
 	}
-	else
-		c->tx_next_ptr=skb->data;	
 	RT_LOCK;
-	c->tx_next_skb=skb;
+	c->tx_next_skb = skb;
 	RT_UNLOCK;
-	
+
 	spin_lock_irqsave(c->lock, flags);
 	z8530_tx_begin(c);
 	spin_unlock_irqrestore(c->lock, flags);
-	
+
 	return NETDEV_TX_OK;
 }
-
 EXPORT_SYMBOL(z8530_queue_xmit);
 
-/*
- *	Module support
+/*	Module support
  */
 static const char banner[] __initconst =
 	KERN_INFO "Generic Z85C30/Z85230 interface driver v0.02\n";
diff --git a/drivers/net/wireless/ath/ath10k/ahb.c b/drivers/net/wireless/ath/ath10k/ahb.c
index 869524852fba..ab8f77ae5e66 100644
--- a/drivers/net/wireless/ath/ath10k/ahb.c
+++ b/drivers/net/wireless/ath/ath10k/ahb.c
@@ -442,14 +442,7 @@ static int ath10k_ahb_resource_init(struct ath10k *ar)
 
 	pdev = ar_ahb->pdev;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		ath10k_err(ar, "failed to get memory resource\n");
-		ret = -ENXIO;
-		goto out;
-	}
-
-	ar_ahb->mem = devm_ioremap_resource(&pdev->dev, res);
+	ar_ahb->mem = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(ar_ahb->mem)) {
 		ath10k_err(ar, "mem ioremap error\n");
 		ret = PTR_ERR(ar_ahb->mem);
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 648ed36f845f..5aeff2d9f6cf 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -301,7 +301,7 @@ struct ath10k_fw_stats_pdev {
 	s32 underrun;
 	u32 hw_paused;
 	s32 tx_abort;
-	s32 mpdus_requed;
+	s32 mpdus_requeued;
 	u32 tx_ko;
 	u32 data_rc;
 	u32 self_triggers;
diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index fd052f6ed019..39378e3f9b2b 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -1105,7 +1105,7 @@ static const char ath10k_gstrings_stats[][ETH_GSTRING_LEN] = {
 	"d_tx_ppdu_reaped",
 	"d_tx_fifo_underrun",
 	"d_tx_ppdu_abort",
-	"d_tx_mpdu_requed",
+	"d_tx_mpdu_requeued",
 	"d_tx_excessive_retries",
 	"d_tx_hw_rate",
 	"d_tx_dropped_sw_retries",
@@ -1205,7 +1205,7 @@ void ath10k_debug_get_et_stats(struct ieee80211_hw *hw,
 	data[i++] = pdev_stats->hw_reaped;
 	data[i++] = pdev_stats->underrun;
 	data[i++] = pdev_stats->tx_abort;
-	data[i++] = pdev_stats->mpdus_requed;
+	data[i++] = pdev_stats->mpdus_requeued;
 	data[i++] = pdev_stats->tx_ko;
 	data[i++] = pdev_stats->data_rc;
 	data[i++] = pdev_stats->sw_retry_failure;
diff --git a/drivers/net/wireless/ath/ath10k/htt.h b/drivers/net/wireless/ath/ath10k/htt.h
index dbc8aef82a65..ec689e3ce48a 100644
--- a/drivers/net/wireless/ath/ath10k/htt.h
+++ b/drivers/net/wireless/ath/ath10k/htt.h
@@ -1283,8 +1283,8 @@ struct htt_dbg_stats_wal_tx_stats {
 	/* Num PPDUs cleaned up in TX abort */
 	__le32 tx_abort;
 
-	/* Num MPDUs requed by SW */
-	__le32 mpdus_requed;
+	/* Num MPDUs requeued by SW */
+	__le32 mpdus_requeued;
 
 	/* excessive retries */
 	__le32 tx_ko;
diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index 7ffb5d5b2a70..adbaeb67eedf 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -1787,7 +1787,6 @@ static bool ath10k_htt_rx_h_frag_pn_check(struct ath10k *ar,
 	struct ath10k_peer *peer;
 	union htt_rx_pn_t *last_pn, new_pn = {0};
 	struct ieee80211_hdr *hdr;
-	bool more_frags;
 	u8 tid, frag_number;
 	u32 seq;
 
@@ -1805,7 +1804,6 @@ static bool ath10k_htt_rx_h_frag_pn_check(struct ath10k *ar,
 
 	last_pn = &peer->frag_tids_last_pn[tid];
 	new_pn.pn48 = ath10k_htt_rx_h_get_pn(ar, skb, offset, enctype);
-	more_frags = ieee80211_has_morefrags(hdr->frame_control);
 	frag_number = le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_FRAG;
 	seq = (__le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_SEQ) >> 4;
 
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 5ce4f8d038b9..c272b290fa73 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -5592,6 +5592,7 @@ static int ath10k_add_interface(struct ieee80211_hw *hw,
 
 	if (arvif->nohwcrypt &&
 	    !test_bit(ATH10K_FLAG_RAW_MODE, &ar->dev_flags)) {
+		ret = -EINVAL;
 		ath10k_warn(ar, "cryptmode module param needed for sw crypto\n");
 		goto err;
 	}
diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index e7fde635e0ee..71878ab35b93 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -3685,8 +3685,10 @@ static int ath10k_pci_probe(struct pci_dev *pdev,
 			ath10k_pci_soc_read32(ar, SOC_CHIP_ID_ADDRESS);
 		if (bus_params.chip_id != 0xffffffff) {
 			if (!ath10k_pci_chip_is_supported(pdev->device,
-							  bus_params.chip_id))
+							  bus_params.chip_id)) {
+				ret = -ENODEV;
 				goto err_unsupported;
+			}
 		}
 	}
 
@@ -3697,11 +3699,15 @@ static int ath10k_pci_probe(struct pci_dev *pdev,
 	}
 
 	bus_params.chip_id = ath10k_pci_soc_read32(ar, SOC_CHIP_ID_ADDRESS);
-	if (bus_params.chip_id == 0xffffffff)
+	if (bus_params.chip_id == 0xffffffff) {
+		ret = -ENODEV;
 		goto err_unsupported;
+	}
 
-	if (!ath10k_pci_chip_is_supported(pdev->device, bus_params.chip_id))
-		goto err_free_irq;
+	if (!ath10k_pci_chip_is_supported(pdev->device, bus_params.chip_id)) {
+		ret = -ENODEV;
+		goto err_unsupported;
+	}
 
 	ret = ath10k_core_register(ar, &bus_params);
 	if (ret) {
diff --git a/drivers/net/wireless/ath/ath10k/pci.h b/drivers/net/wireless/ath/ath10k/pci.h
index 862d0901c5b8..cf64898b9447 100644
--- a/drivers/net/wireless/ath/ath10k/pci.h
+++ b/drivers/net/wireless/ath/ath10k/pci.h
@@ -235,7 +235,6 @@ u16 ath10k_pci_hif_get_free_queue_number(struct ath10k *ar, u8 pipe);
 void ath10k_pci_hif_power_down(struct ath10k *ar);
 int ath10k_pci_alloc_pipes(struct ath10k *ar);
 void ath10k_pci_free_pipes(struct ath10k *ar);
-void ath10k_pci_free_pipes(struct ath10k *ar);
 void ath10k_pci_rx_replenish_retry(struct timer_list *t);
 void ath10k_pci_ce_deinit(struct ath10k *ar);
 void ath10k_pci_init_napi(struct ath10k *ar);
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index d48b922215eb..f42bf2c8f9e7 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -2867,7 +2867,7 @@ void ath10k_wmi_pull_pdev_stats_tx(const struct wmi_pdev_stats_tx *src,
 	dst->hw_reaped = __le32_to_cpu(src->hw_reaped);
 	dst->underrun = __le32_to_cpu(src->underrun);
 	dst->tx_abort = __le32_to_cpu(src->tx_abort);
-	dst->mpdus_requed = __le32_to_cpu(src->mpdus_requed);
+	dst->mpdus_requeued = __le32_to_cpu(src->mpdus_requeued);
 	dst->tx_ko = __le32_to_cpu(src->tx_ko);
 	dst->data_rc = __le32_to_cpu(src->data_rc);
 	dst->self_triggers = __le32_to_cpu(src->self_triggers);
@@ -2895,7 +2895,7 @@ ath10k_wmi_10_4_pull_pdev_stats_tx(const struct wmi_10_4_pdev_stats_tx *src,
 	dst->hw_reaped = __le32_to_cpu(src->hw_reaped);
 	dst->underrun = __le32_to_cpu(src->underrun);
 	dst->tx_abort = __le32_to_cpu(src->tx_abort);
-	dst->mpdus_requed = __le32_to_cpu(src->mpdus_requed);
+	dst->mpdus_requeued = __le32_to_cpu(src->mpdus_requeued);
 	dst->tx_ko = __le32_to_cpu(src->tx_ko);
 	dst->data_rc = __le32_to_cpu(src->data_rc);
 	dst->self_triggers = __le32_to_cpu(src->self_triggers);
@@ -8270,7 +8270,7 @@ ath10k_wmi_fw_pdev_tx_stats_fill(const struct ath10k_fw_stats_pdev *pdev,
 	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
 			 "PPDUs cleaned", pdev->tx_abort);
 	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
-			 "MPDUs requed", pdev->mpdus_requed);
+			 "MPDUs requeued", pdev->mpdus_requeued);
 	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
 			 "Excessive retries", pdev->tx_ko);
 	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index d870f7067cb7..41c1a3d339c2 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -4371,8 +4371,8 @@ struct wmi_pdev_stats_tx {
 	/* Num PPDUs cleaned up in TX abort */
 	__le32 tx_abort;
 
-	/* Num MPDUs requed by SW */
-	__le32 mpdus_requed;
+	/* Num MPDUs requeued by SW */
+	__le32 mpdus_requeued;
 
 	/* excessive retries */
 	__le32 tx_ko;
@@ -4444,8 +4444,8 @@ struct wmi_10_4_pdev_stats_tx {
 	/* Num PPDUs cleaned up in TX abort */
 	__le32 tx_abort;
 
-	/* Num MPDUs requed by SW */
-	__le32 mpdus_requed;
+	/* Num MPDUs requeued by SW */
+	__le32 mpdus_requeued;
 
 	/* excessive retries */
 	__le32 tx_ko;
@@ -7418,7 +7418,6 @@ int ath10k_wmi_wait_for_unified_ready(struct ath10k *ar);
 struct sk_buff *ath10k_wmi_alloc_skb(struct ath10k *ar, u32 len);
 int ath10k_wmi_connect(struct ath10k *ar);
 
-struct sk_buff *ath10k_wmi_alloc_skb(struct ath10k *ar, u32 len);
 int ath10k_wmi_cmd_send(struct ath10k *ar, struct sk_buff *skb, u32 cmd_id);
 int ath10k_wmi_cmd_send_nowait(struct ath10k *ar, struct sk_buff *skb,
 			       u32 cmd_id);
diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index 77ce3347ab86..969bf1a590d9 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -70,6 +70,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.cold_boot_calib = true,
 		.supports_suspend = false,
 		.hal_desc_sz = sizeof(struct hal_rx_desc_ipq8074),
+		.fix_l1ss = true,
 	},
 	{
 		.hw_rev = ATH11K_HW_IPQ6018_HW10,
@@ -110,6 +111,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.cold_boot_calib = true,
 		.supports_suspend = false,
 		.hal_desc_sz = sizeof(struct hal_rx_desc_ipq8074),
+		.fix_l1ss = true,
 	},
 	{
 		.name = "qca6390 hw2.0",
@@ -149,6 +151,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.cold_boot_calib = false,
 		.supports_suspend = true,
 		.hal_desc_sz = sizeof(struct hal_rx_desc_ipq8074),
+		.fix_l1ss = true,
 	},
 	{
 		.name = "qcn9074 hw1.0",
@@ -186,6 +189,47 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.cold_boot_calib = false,
 		.supports_suspend = false,
 		.hal_desc_sz = sizeof(struct hal_rx_desc_qcn9074),
+		.fix_l1ss = true,
+	},
+	{
+		.name = "wcn6855 hw2.0",
+		.hw_rev = ATH11K_HW_WCN6855_HW20,
+		.fw = {
+			.dir = "WCN6855/hw2.0",
+			.board_size = 256 * 1024,
+			.cal_size = 256 * 1024,
+		},
+		.max_radios = 3,
+		.bdf_addr = 0x4B0C0000,
+		.hw_ops = &wcn6855_ops,
+		.ring_mask = &ath11k_hw_ring_mask_qca6390,
+		.internal_sleep_clock = true,
+		.regs = &wcn6855_regs,
+		.qmi_service_ins_id = ATH11K_QMI_WLFW_SERVICE_INS_ID_V01_QCA6390,
+		.host_ce_config = ath11k_host_ce_config_qca6390,
+		.ce_count = 9,
+		.target_ce_config = ath11k_target_ce_config_wlan_qca6390,
+		.target_ce_count = 9,
+		.svc_to_ce_map = ath11k_target_service_to_ce_map_wlan_qca6390,
+		.svc_to_ce_map_len = 14,
+		.single_pdev_only = true,
+		.rxdma1_enable = false,
+		.num_rxmda_per_pdev = 2,
+		.rx_mac_buf_ring = true,
+		.vdev_start_delay = true,
+		.htt_peer_map_v2 = false,
+		.tcl_0_only = true,
+		.spectral_fft_sz = 0,
+
+		.interface_modes = BIT(NL80211_IFTYPE_STATION) |
+					BIT(NL80211_IFTYPE_AP),
+		.supports_monitor = false,
+		.supports_shadow_regs = true,
+		.idle_ps = true,
+		.cold_boot_calib = false,
+		.supports_suspend = true,
+		.hal_desc_sz = sizeof(struct hal_rx_desc_wcn6855),
+		.fix_l1ss = false,
 	},
 };
 
@@ -488,7 +532,8 @@ static int ath11k_core_fetch_board_data_api_n(struct ath11k_base *ab,
 		if (len < ALIGN(ie_len, 4)) {
 			ath11k_err(ab, "invalid length for board ie_id %d ie_len %zu len %zu\n",
 				   ie_id, ie_len, len);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err;
 		}
 
 		switch (ie_id) {
diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 55af982deca7..018fb2385f2a 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -107,6 +107,7 @@ enum ath11k_hw_rev {
 	ATH11K_HW_QCA6390_HW20,
 	ATH11K_HW_IPQ6018_HW10,
 	ATH11K_HW_QCN9074_HW10,
+	ATH11K_HW_WCN6855_HW20,
 };
 
 enum ath11k_firmware_mode {
@@ -795,8 +796,8 @@ struct ath11k_fw_stats_pdev {
 	s32 underrun;
 	/* Num PPDUs cleaned up in TX abort */
 	s32 tx_abort;
-	/* Num MPDUs requed by SW */
-	s32 mpdus_requed;
+	/* Num MPDUs requeued by SW */
+	s32 mpdus_requeued;
 	/* excessive retries */
 	u32 tx_ko;
 	/* data hw rate code */
diff --git a/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.c b/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.c
index ec93f14e6d2a..9e0c90da99d3 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.c
+++ b/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.c
@@ -89,7 +89,7 @@ static inline void htt_print_tx_pdev_stats_cmn_tlv(const void *tag_buf,
 	len += HTT_DBG_OUT(buf + len, buf_len - len, "tx_abort = %u",
 			   htt_stats_buf->tx_abort);
 	len += HTT_DBG_OUT(buf + len, buf_len - len, "mpdu_requeued = %u",
-			   htt_stats_buf->mpdu_requed);
+			   htt_stats_buf->mpdu_requeued);
 	len += HTT_DBG_OUT(buf + len, buf_len - len, "tx_xretry = %u",
 			   htt_stats_buf->tx_xretry);
 	len += HTT_DBG_OUT(buf + len, buf_len - len, "data_rc = %u",
diff --git a/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.h b/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.h
index 567a26d485a9..d428f52003a4 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.h
+++ b/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.h
@@ -147,7 +147,7 @@ struct htt_tx_pdev_stats_cmn_tlv {
 	u32 hw_flush;
 	u32 hw_filt;
 	u32 tx_abort;
-	u32 mpdu_requed;
+	u32 mpdu_requeued;
 	u32 tx_xretry;
 	u32 data_rc;
 	u32 mpdu_dropped_xretry;
diff --git a/drivers/net/wireless/ath/ath11k/dp.c b/drivers/net/wireless/ath/ath11k/dp.c
index 04f6c4e0658b..b0c8f6290099 100644
--- a/drivers/net/wireless/ath/ath11k/dp.c
+++ b/drivers/net/wireless/ath/ath11k/dp.c
@@ -342,7 +342,6 @@ static int ath11k_dp_srng_common_setup(struct ath11k_base *ab)
 	struct ath11k_dp *dp = &ab->dp;
 	struct hal_srng *srng;
 	int i, ret;
-	u32 ring_hash_map;
 
 	ret = ath11k_dp_srng_setup(ab, &dp->wbm_desc_rel_ring,
 				   HAL_SW2WBM_RELEASE, 0, 0,
@@ -439,20 +438,9 @@ static int ath11k_dp_srng_common_setup(struct ath11k_base *ab)
 	}
 
 	/* When hash based routing of rx packet is enabled, 32 entries to map
-	 * the hash values to the ring will be configured. Each hash entry uses
-	 * three bits to map to a particular ring. The ring mapping will be
-	 * 0:TCL, 1:SW1, 2:SW2, 3:SW3, 4:SW4, 5:Release, 6:FW and 7:Not used.
+	 * the hash values to the ring will be configured.
 	 */
-	ring_hash_map = HAL_HASH_ROUTING_RING_SW1 << 0 |
-			HAL_HASH_ROUTING_RING_SW2 << 3 |
-			HAL_HASH_ROUTING_RING_SW3 << 6 |
-			HAL_HASH_ROUTING_RING_SW4 << 9 |
-			HAL_HASH_ROUTING_RING_SW1 << 12 |
-			HAL_HASH_ROUTING_RING_SW2 << 15 |
-			HAL_HASH_ROUTING_RING_SW3 << 18 |
-			HAL_HASH_ROUTING_RING_SW4 << 21;
-
-	ath11k_hal_reo_hw_setup(ab, ring_hash_map);
+	ab->hw_params.hw_ops->reo_setup(ab);
 
 	return 0;
 
diff --git a/drivers/net/wireless/ath/ath11k/hal.c b/drivers/net/wireless/ath/ath11k/hal.c
index 08e3c72d9237..eaa0edca5576 100644
--- a/drivers/net/wireless/ath/ath11k/hal.c
+++ b/drivers/net/wireless/ath/ath11k/hal.c
@@ -382,6 +382,16 @@ static void ath11k_hal_srng_src_hw_init(struct ath11k_base *ab,
 	val = FIELD_PREP(HAL_REO1_RING_ID_ENTRY_SIZE, srng->entry_size);
 	ath11k_hif_write32(ab, reg_base + HAL_TCL1_RING_ID_OFFSET(ab), val);
 
+	if (srng->ring_id == HAL_SRNG_RING_ID_WBM_IDLE_LINK) {
+		ath11k_hif_write32(ab, reg_base, (u32)srng->ring_base_paddr);
+		val = FIELD_PREP(HAL_TCL1_RING_BASE_MSB_RING_BASE_ADDR_MSB,
+				 ((u64)srng->ring_base_paddr >>
+				 HAL_ADDR_MSB_REG_SHIFT)) |
+			FIELD_PREP(HAL_TCL1_RING_BASE_MSB_RING_SIZE,
+				   (srng->entry_size * srng->num_entries));
+		ath11k_hif_write32(ab, reg_base + HAL_TCL1_RING_BASE_MSB_OFFSET(ab), val);
+	}
+
 	/* interrupt setup */
 	/* NOTE: IPQ8074 v2 requires the interrupt timer threshold in the
 	 * unit of 8 usecs instead of 1 usec (as required by v1).
diff --git a/drivers/net/wireless/ath/ath11k/hal.h b/drivers/net/wireless/ath/ath11k/hal.h
index 91d1428b8b94..35ed3a14e200 100644
--- a/drivers/net/wireless/ath/ath11k/hal.h
+++ b/drivers/net/wireless/ath/ath11k/hal.h
@@ -120,6 +120,7 @@ struct ath11k_base;
 #define HAL_REO1_DEST_RING_CTRL_IX_1		0x00000008
 #define HAL_REO1_DEST_RING_CTRL_IX_2		0x0000000c
 #define HAL_REO1_DEST_RING_CTRL_IX_3		0x00000010
+#define HAL_REO1_MISC_CTL			0x00000630
 #define HAL_REO1_RING_BASE_LSB(ab)		ab->hw_params.regs->hal_reo1_ring_base_lsb
 #define HAL_REO1_RING_BASE_MSB(ab)		ab->hw_params.regs->hal_reo1_ring_base_msb
 #define HAL_REO1_RING_ID(ab)			ab->hw_params.regs->hal_reo1_ring_id
@@ -280,6 +281,7 @@ struct ath11k_base;
 #define HAL_REO1_GEN_ENABLE_FRAG_DST_RING		GENMASK(25, 23)
 #define HAL_REO1_GEN_ENABLE_AGING_LIST_ENABLE		BIT(2)
 #define HAL_REO1_GEN_ENABLE_AGING_FLUSH_ENABLE		BIT(3)
+#define HAL_REO1_MISC_CTL_FRAGMENT_DST_RING		GENMASK(20, 17)
 
 /* CE ring bit field mask and shift */
 #define HAL_CE_DST_R0_DEST_CTRL_MAX_LEN			GENMASK(15, 0)
@@ -906,7 +908,6 @@ void ath11k_hal_reo_qdesc_setup(void *vaddr, int tid, u32 ba_window_size,
 				u32 start_seq, enum hal_pn_type type);
 void ath11k_hal_reo_init_cmd_ring(struct ath11k_base *ab,
 				  struct hal_srng *srng);
-void ath11k_hal_reo_hw_setup(struct ath11k_base *ab, u32 ring_hash_map);
 void ath11k_hal_setup_link_idle_list(struct ath11k_base *ab,
 				     struct hal_wbm_idle_scatter_list *sbuf,
 				     u32 nsbufs, u32 tot_link_desc,
diff --git a/drivers/net/wireless/ath/ath11k/hal_rx.c b/drivers/net/wireless/ath/ath11k/hal_rx.c
index fac2396edf32..325055ca41ab 100644
--- a/drivers/net/wireless/ath/ath11k/hal_rx.c
+++ b/drivers/net/wireless/ath/ath11k/hal_rx.c
@@ -801,43 +801,6 @@ void ath11k_hal_reo_init_cmd_ring(struct ath11k_base *ab,
 	}
 }
 
-void ath11k_hal_reo_hw_setup(struct ath11k_base *ab, u32 ring_hash_map)
-{
-	u32 reo_base = HAL_SEQ_WCSS_UMAC_REO_REG;
-	u32 val;
-
-	val = ath11k_hif_read32(ab, reo_base + HAL_REO1_GEN_ENABLE);
-
-	val &= ~HAL_REO1_GEN_ENABLE_FRAG_DST_RING;
-	val |= FIELD_PREP(HAL_REO1_GEN_ENABLE_FRAG_DST_RING,
-			  HAL_SRNG_RING_ID_REO2SW1) |
-	       FIELD_PREP(HAL_REO1_GEN_ENABLE_AGING_LIST_ENABLE, 1) |
-	       FIELD_PREP(HAL_REO1_GEN_ENABLE_AGING_FLUSH_ENABLE, 1);
-	ath11k_hif_write32(ab, reo_base + HAL_REO1_GEN_ENABLE, val);
-
-	ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_0(ab),
-			   HAL_DEFAULT_REO_TIMEOUT_USEC);
-	ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_1(ab),
-			   HAL_DEFAULT_REO_TIMEOUT_USEC);
-	ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_2(ab),
-			   HAL_DEFAULT_REO_TIMEOUT_USEC);
-	ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_3(ab),
-			   HAL_DEFAULT_REO_TIMEOUT_USEC);
-
-	ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_0,
-			   FIELD_PREP(HAL_REO_DEST_RING_CTRL_HASH_RING_MAP,
-				      ring_hash_map));
-	ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_1,
-			   FIELD_PREP(HAL_REO_DEST_RING_CTRL_HASH_RING_MAP,
-				      ring_hash_map));
-	ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_2,
-			   FIELD_PREP(HAL_REO_DEST_RING_CTRL_HASH_RING_MAP,
-				      ring_hash_map));
-	ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_3,
-			   FIELD_PREP(HAL_REO_DEST_RING_CTRL_HASH_RING_MAP,
-				      ring_hash_map));
-}
-
 static enum hal_rx_mon_status
 ath11k_hal_rx_parse_mon_status_tlv(struct ath11k_base *ab,
 				   struct hal_rx_mon_ppdu_info *ppdu_info,
@@ -1128,12 +1091,9 @@ ath11k_hal_rx_parse_mon_status_tlv(struct ath11k_base *ab,
 		break;
 	}
 	case HAL_RX_MPDU_START: {
-		struct hal_rx_mpdu_info *mpdu_info =
-			(struct hal_rx_mpdu_info *)tlv_data;
 		u16 peer_id;
 
-		peer_id = FIELD_GET(HAL_RX_MPDU_INFO_INFO0_PEERID,
-				    __le32_to_cpu(mpdu_info->info0));
+		peer_id = ab->hw_params.hw_ops->mpdu_info_get_peerid(tlv_data);
 		if (peer_id)
 			ppdu_info->peer_id = peer_id;
 		break;
diff --git a/drivers/net/wireless/ath/ath11k/hal_rx.h b/drivers/net/wireless/ath/ath11k/hal_rx.h
index d464a270c049..0f1f04b812b9 100644
--- a/drivers/net/wireless/ath/ath11k/hal_rx.h
+++ b/drivers/net/wireless/ath/ath11k/hal_rx.h
@@ -254,12 +254,20 @@ struct hal_rx_phyrx_rssi_legacy_info {
 } __packed;
 
 #define HAL_RX_MPDU_INFO_INFO0_PEERID	GENMASK(31, 16)
+#define HAL_RX_MPDU_INFO_INFO0_PEERID_WCN6855	GENMASK(15, 0)
+
 struct hal_rx_mpdu_info {
 	__le32 rsvd0;
 	__le32 info0;
 	__le32 rsvd1[21];
 } __packed;
 
+struct hal_rx_mpdu_info_wcn6855 {
+	__le32 rsvd0[8];
+	__le32 info0;
+	__le32 rsvd1[14];
+} __packed;
+
 #define HAL_RX_PPDU_END_DURATION	GENMASK(23, 0)
 struct hal_rx_ppdu_end_duration {
 	__le32 rsvd0[9];
diff --git a/drivers/net/wireless/ath/ath11k/hw.c b/drivers/net/wireless/ath/ath11k/hw.c
index 377ae8d5b58f..d9596903b0a5 100644
--- a/drivers/net/wireless/ath/ath11k/hw.c
+++ b/drivers/net/wireless/ath/ath11k/hw.c
@@ -10,6 +10,7 @@
 #include "hw.h"
 #include "core.h"
 #include "ce.h"
+#include "hif.h"
 
 /* Map from pdev index to hw mac index */
 static u8 ath11k_hw_ipq8074_mac_from_pdev_id(int pdev_idx)
@@ -45,6 +46,13 @@ static void ath11k_hw_qcn9074_tx_mesh_enable(struct ath11k_base *ab,
 				     true);
 }
 
+static void ath11k_hw_wcn6855_tx_mesh_enable(struct ath11k_base *ab,
+					     struct hal_tcl_data_cmd *tcl_cmd)
+{
+	tcl_cmd->info3 |= FIELD_PREP(HAL_QCN9074_TCL_DATA_CMD_INFO3_MESH_ENABLE,
+				     true);
+}
+
 static void ath11k_init_wmi_config_qca6390(struct ath11k_base *ab,
 					   struct target_resource_config *config)
 {
@@ -91,6 +99,52 @@ static void ath11k_init_wmi_config_qca6390(struct ath11k_base *ab,
 	config->num_keep_alive_pattern = 0;
 }
 
+static void ath11k_hw_ipq8074_reo_setup(struct ath11k_base *ab)
+{
+	u32 reo_base = HAL_SEQ_WCSS_UMAC_REO_REG;
+	u32 val;
+	/* Each hash entry uses three bits to map to a particular ring. */
+	u32 ring_hash_map = HAL_HASH_ROUTING_RING_SW1 << 0 |
+		HAL_HASH_ROUTING_RING_SW2 << 3 |
+		HAL_HASH_ROUTING_RING_SW3 << 6 |
+		HAL_HASH_ROUTING_RING_SW4 << 9 |
+		HAL_HASH_ROUTING_RING_SW1 << 12 |
+		HAL_HASH_ROUTING_RING_SW2 << 15 |
+		HAL_HASH_ROUTING_RING_SW3 << 18 |
+		HAL_HASH_ROUTING_RING_SW4 << 21;
+
+	val = ath11k_hif_read32(ab, reo_base + HAL_REO1_GEN_ENABLE);
+
+	val &= ~HAL_REO1_GEN_ENABLE_FRAG_DST_RING;
+	val |= FIELD_PREP(HAL_REO1_GEN_ENABLE_FRAG_DST_RING,
+			HAL_SRNG_RING_ID_REO2SW1) |
+		FIELD_PREP(HAL_REO1_GEN_ENABLE_AGING_LIST_ENABLE, 1) |
+		FIELD_PREP(HAL_REO1_GEN_ENABLE_AGING_FLUSH_ENABLE, 1);
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_GEN_ENABLE, val);
+
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_0(ab),
+			   HAL_DEFAULT_REO_TIMEOUT_USEC);
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_1(ab),
+			   HAL_DEFAULT_REO_TIMEOUT_USEC);
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_2(ab),
+			   HAL_DEFAULT_REO_TIMEOUT_USEC);
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_3(ab),
+			   HAL_DEFAULT_REO_TIMEOUT_USEC);
+
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_0,
+			   FIELD_PREP(HAL_REO_DEST_RING_CTRL_HASH_RING_MAP,
+				      ring_hash_map));
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_1,
+			   FIELD_PREP(HAL_REO_DEST_RING_CTRL_HASH_RING_MAP,
+				      ring_hash_map));
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_2,
+			   FIELD_PREP(HAL_REO_DEST_RING_CTRL_HASH_RING_MAP,
+				      ring_hash_map));
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_3,
+			   FIELD_PREP(HAL_REO_DEST_RING_CTRL_HASH_RING_MAP,
+				      ring_hash_map));
+}
+
 static void ath11k_init_wmi_config_ipq8074(struct ath11k_base *ab,
 					   struct target_resource_config *config)
 {
@@ -489,6 +543,228 @@ static u8 *ath11k_hw_qcn9074_rx_desc_get_msdu_payload(struct hal_rx_desc *desc)
 	return &desc->u.qcn9074.msdu_payload[0];
 }
 
+static bool ath11k_hw_wcn6855_rx_desc_get_first_msdu(struct hal_rx_desc *desc)
+{
+	return !!FIELD_GET(RX_MSDU_END_INFO2_FIRST_MSDU_WCN6855,
+			   __le32_to_cpu(desc->u.wcn6855.msdu_end.info2));
+}
+
+static bool ath11k_hw_wcn6855_rx_desc_get_last_msdu(struct hal_rx_desc *desc)
+{
+	return !!FIELD_GET(RX_MSDU_END_INFO2_LAST_MSDU_WCN6855,
+			   __le32_to_cpu(desc->u.wcn6855.msdu_end.info2));
+}
+
+static u8 ath11k_hw_wcn6855_rx_desc_get_l3_pad_bytes(struct hal_rx_desc *desc)
+{
+	return FIELD_GET(RX_MSDU_END_INFO2_L3_HDR_PADDING,
+			 __le32_to_cpu(desc->u.wcn6855.msdu_end.info2));
+}
+
+static u8 *ath11k_hw_wcn6855_rx_desc_get_hdr_status(struct hal_rx_desc *desc)
+{
+	return desc->u.wcn6855.hdr_status;
+}
+
+static bool ath11k_hw_wcn6855_rx_desc_encrypt_valid(struct hal_rx_desc *desc)
+{
+	return __le32_to_cpu(desc->u.wcn6855.mpdu_start.info1) &
+	       RX_MPDU_START_INFO1_ENCRYPT_INFO_VALID;
+}
+
+static u32 ath11k_hw_wcn6855_rx_desc_get_encrypt_type(struct hal_rx_desc *desc)
+{
+	return FIELD_GET(RX_MPDU_START_INFO2_ENC_TYPE,
+			 __le32_to_cpu(desc->u.wcn6855.mpdu_start.info2));
+}
+
+static u8 ath11k_hw_wcn6855_rx_desc_get_decap_type(struct hal_rx_desc *desc)
+{
+	return FIELD_GET(RX_MSDU_START_INFO2_DECAP_FORMAT,
+			 __le32_to_cpu(desc->u.wcn6855.msdu_start.info2));
+}
+
+static u8 ath11k_hw_wcn6855_rx_desc_get_mesh_ctl(struct hal_rx_desc *desc)
+{
+	return FIELD_GET(RX_MSDU_START_INFO2_MESH_CTRL_PRESENT,
+			 __le32_to_cpu(desc->u.wcn6855.msdu_start.info2));
+}
+
+static bool ath11k_hw_wcn6855_rx_desc_get_mpdu_seq_ctl_vld(struct hal_rx_desc *desc)
+{
+	return !!FIELD_GET(RX_MPDU_START_INFO1_MPDU_SEQ_CTRL_VALID,
+			   __le32_to_cpu(desc->u.wcn6855.mpdu_start.info1));
+}
+
+static bool ath11k_hw_wcn6855_rx_desc_get_mpdu_fc_valid(struct hal_rx_desc *desc)
+{
+	return !!FIELD_GET(RX_MPDU_START_INFO1_MPDU_FCTRL_VALID,
+			   __le32_to_cpu(desc->u.wcn6855.mpdu_start.info1));
+}
+
+static u16 ath11k_hw_wcn6855_rx_desc_get_mpdu_start_seq_no(struct hal_rx_desc *desc)
+{
+	return FIELD_GET(RX_MPDU_START_INFO1_MPDU_SEQ_NUM,
+			 __le32_to_cpu(desc->u.wcn6855.mpdu_start.info1));
+}
+
+static u16 ath11k_hw_wcn6855_rx_desc_get_msdu_len(struct hal_rx_desc *desc)
+{
+	return FIELD_GET(RX_MSDU_START_INFO1_MSDU_LENGTH,
+			 __le32_to_cpu(desc->u.wcn6855.msdu_start.info1));
+}
+
+static u8 ath11k_hw_wcn6855_rx_desc_get_msdu_sgi(struct hal_rx_desc *desc)
+{
+	return FIELD_GET(RX_MSDU_START_INFO3_SGI,
+			 __le32_to_cpu(desc->u.wcn6855.msdu_start.info3));
+}
+
+static u8 ath11k_hw_wcn6855_rx_desc_get_msdu_rate_mcs(struct hal_rx_desc *desc)
+{
+	return FIELD_GET(RX_MSDU_START_INFO3_RATE_MCS,
+			 __le32_to_cpu(desc->u.wcn6855.msdu_start.info3));
+}
+
+static u8 ath11k_hw_wcn6855_rx_desc_get_msdu_rx_bw(struct hal_rx_desc *desc)
+{
+	return FIELD_GET(RX_MSDU_START_INFO3_RECV_BW,
+			 __le32_to_cpu(desc->u.wcn6855.msdu_start.info3));
+}
+
+static u32 ath11k_hw_wcn6855_rx_desc_get_msdu_freq(struct hal_rx_desc *desc)
+{
+	return __le32_to_cpu(desc->u.wcn6855.msdu_start.phy_meta_data);
+}
+
+static u8 ath11k_hw_wcn6855_rx_desc_get_msdu_pkt_type(struct hal_rx_desc *desc)
+{
+	return FIELD_GET(RX_MSDU_START_INFO3_PKT_TYPE,
+			 __le32_to_cpu(desc->u.wcn6855.msdu_start.info3));
+}
+
+static u8 ath11k_hw_wcn6855_rx_desc_get_msdu_nss(struct hal_rx_desc *desc)
+{
+	return FIELD_GET(RX_MSDU_START_INFO3_MIMO_SS_BITMAP,
+			 __le32_to_cpu(desc->u.wcn6855.msdu_start.info3));
+}
+
+static u8 ath11k_hw_wcn6855_rx_desc_get_mpdu_tid(struct hal_rx_desc *desc)
+{
+	return FIELD_GET(RX_MPDU_START_INFO2_TID_WCN6855,
+			 __le32_to_cpu(desc->u.wcn6855.mpdu_start.info2));
+}
+
+static u16 ath11k_hw_wcn6855_rx_desc_get_mpdu_peer_id(struct hal_rx_desc *desc)
+{
+	return __le16_to_cpu(desc->u.wcn6855.mpdu_start.sw_peer_id);
+}
+
+static void ath11k_hw_wcn6855_rx_desc_copy_attn_end(struct hal_rx_desc *fdesc,
+						    struct hal_rx_desc *ldesc)
+{
+	memcpy((u8 *)&fdesc->u.wcn6855.msdu_end, (u8 *)&ldesc->u.wcn6855.msdu_end,
+	       sizeof(struct rx_msdu_end_wcn6855));
+	memcpy((u8 *)&fdesc->u.wcn6855.attention, (u8 *)&ldesc->u.wcn6855.attention,
+	       sizeof(struct rx_attention));
+	memcpy((u8 *)&fdesc->u.wcn6855.mpdu_end, (u8 *)&ldesc->u.wcn6855.mpdu_end,
+	       sizeof(struct rx_mpdu_end));
+}
+
+static u32 ath11k_hw_wcn6855_rx_desc_get_mpdu_start_tag(struct hal_rx_desc *desc)
+{
+	return FIELD_GET(HAL_TLV_HDR_TAG,
+			 __le32_to_cpu(desc->u.wcn6855.mpdu_start_tag));
+}
+
+static u32 ath11k_hw_wcn6855_rx_desc_get_mpdu_ppdu_id(struct hal_rx_desc *desc)
+{
+	return __le16_to_cpu(desc->u.wcn6855.mpdu_start.phy_ppdu_id);
+}
+
+static void ath11k_hw_wcn6855_rx_desc_set_msdu_len(struct hal_rx_desc *desc, u16 len)
+{
+	u32 info = __le32_to_cpu(desc->u.wcn6855.msdu_start.info1);
+
+	info &= ~RX_MSDU_START_INFO1_MSDU_LENGTH;
+	info |= FIELD_PREP(RX_MSDU_START_INFO1_MSDU_LENGTH, len);
+
+	desc->u.wcn6855.msdu_start.info1 = __cpu_to_le32(info);
+}
+
+static
+struct rx_attention *ath11k_hw_wcn6855_rx_desc_get_attention(struct hal_rx_desc *desc)
+{
+	return &desc->u.wcn6855.attention;
+}
+
+static u8 *ath11k_hw_wcn6855_rx_desc_get_msdu_payload(struct hal_rx_desc *desc)
+{
+	return &desc->u.wcn6855.msdu_payload[0];
+}
+
+static void ath11k_hw_wcn6855_reo_setup(struct ath11k_base *ab)
+{
+	u32 reo_base = HAL_SEQ_WCSS_UMAC_REO_REG;
+	u32 val;
+	/* Each hash entry uses four bits to map to a particular ring. */
+	u32 ring_hash_map = HAL_HASH_ROUTING_RING_SW1 << 0 |
+		HAL_HASH_ROUTING_RING_SW2 << 4 |
+		HAL_HASH_ROUTING_RING_SW3 << 8 |
+		HAL_HASH_ROUTING_RING_SW4 << 12 |
+		HAL_HASH_ROUTING_RING_SW1 << 16 |
+		HAL_HASH_ROUTING_RING_SW2 << 20 |
+		HAL_HASH_ROUTING_RING_SW3 << 24 |
+		HAL_HASH_ROUTING_RING_SW4 << 28;
+
+	val = ath11k_hif_read32(ab, reo_base + HAL_REO1_GEN_ENABLE);
+	val |= FIELD_PREP(HAL_REO1_GEN_ENABLE_AGING_LIST_ENABLE, 1) |
+		FIELD_PREP(HAL_REO1_GEN_ENABLE_AGING_FLUSH_ENABLE, 1);
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_GEN_ENABLE, val);
+
+	val = ath11k_hif_read32(ab, reo_base + HAL_REO1_MISC_CTL);
+	val &= ~HAL_REO1_MISC_CTL_FRAGMENT_DST_RING;
+	val |= FIELD_PREP(HAL_REO1_MISC_CTL_FRAGMENT_DST_RING, HAL_SRNG_RING_ID_REO2SW1);
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_MISC_CTL, val);
+
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_0(ab),
+			   HAL_DEFAULT_REO_TIMEOUT_USEC);
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_1(ab),
+			   HAL_DEFAULT_REO_TIMEOUT_USEC);
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_2(ab),
+			   HAL_DEFAULT_REO_TIMEOUT_USEC);
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_3(ab),
+			   HAL_DEFAULT_REO_TIMEOUT_USEC);
+
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_2,
+			   ring_hash_map);
+	ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_3,
+			   ring_hash_map);
+}
+
+static u16 ath11k_hw_ipq8074_mpdu_info_get_peerid(u8 *tlv_data)
+{
+	u16 peer_id = 0;
+	struct hal_rx_mpdu_info *mpdu_info =
+		(struct hal_rx_mpdu_info *)tlv_data;
+
+	peer_id = FIELD_GET(HAL_RX_MPDU_INFO_INFO0_PEERID,
+			    __le32_to_cpu(mpdu_info->info0));
+
+	return peer_id;
+}
+
+static u16 ath11k_hw_wcn6855_mpdu_info_get_peerid(u8 *tlv_data)
+{
+	u16 peer_id = 0;
+	struct hal_rx_mpdu_info_wcn6855 *mpdu_info =
+		(struct hal_rx_mpdu_info_wcn6855 *)tlv_data;
+
+	peer_id = FIELD_GET(HAL_RX_MPDU_INFO_INFO0_PEERID_WCN6855,
+			    __le32_to_cpu(mpdu_info->info0));
+	return peer_id;
+}
+
 const struct ath11k_hw_ops ipq8074_ops = {
 	.get_hw_mac_from_pdev_id = ath11k_hw_ipq8074_mac_from_pdev_id,
 	.wmi_init_config = ath11k_init_wmi_config_ipq8074,
@@ -521,6 +797,8 @@ const struct ath11k_hw_ops ipq8074_ops = {
 	.rx_desc_set_msdu_len = ath11k_hw_ipq8074_rx_desc_set_msdu_len,
 	.rx_desc_get_attention = ath11k_hw_ipq8074_rx_desc_get_attention,
 	.rx_desc_get_msdu_payload = ath11k_hw_ipq8074_rx_desc_get_msdu_payload,
+	.reo_setup = ath11k_hw_ipq8074_reo_setup,
+	.mpdu_info_get_peerid = ath11k_hw_ipq8074_mpdu_info_get_peerid,
 };
 
 const struct ath11k_hw_ops ipq6018_ops = {
@@ -555,6 +833,8 @@ const struct ath11k_hw_ops ipq6018_ops = {
 	.rx_desc_set_msdu_len = ath11k_hw_ipq8074_rx_desc_set_msdu_len,
 	.rx_desc_get_attention = ath11k_hw_ipq8074_rx_desc_get_attention,
 	.rx_desc_get_msdu_payload = ath11k_hw_ipq8074_rx_desc_get_msdu_payload,
+	.reo_setup = ath11k_hw_ipq8074_reo_setup,
+	.mpdu_info_get_peerid = ath11k_hw_ipq8074_mpdu_info_get_peerid,
 };
 
 const struct ath11k_hw_ops qca6390_ops = {
@@ -589,6 +869,8 @@ const struct ath11k_hw_ops qca6390_ops = {
 	.rx_desc_set_msdu_len = ath11k_hw_ipq8074_rx_desc_set_msdu_len,
 	.rx_desc_get_attention = ath11k_hw_ipq8074_rx_desc_get_attention,
 	.rx_desc_get_msdu_payload = ath11k_hw_ipq8074_rx_desc_get_msdu_payload,
+	.reo_setup = ath11k_hw_ipq8074_reo_setup,
+	.mpdu_info_get_peerid = ath11k_hw_ipq8074_mpdu_info_get_peerid,
 };
 
 const struct ath11k_hw_ops qcn9074_ops = {
@@ -623,6 +905,44 @@ const struct ath11k_hw_ops qcn9074_ops = {
 	.rx_desc_set_msdu_len = ath11k_hw_qcn9074_rx_desc_set_msdu_len,
 	.rx_desc_get_attention = ath11k_hw_qcn9074_rx_desc_get_attention,
 	.rx_desc_get_msdu_payload = ath11k_hw_qcn9074_rx_desc_get_msdu_payload,
+	.reo_setup = ath11k_hw_ipq8074_reo_setup,
+	.mpdu_info_get_peerid = ath11k_hw_ipq8074_mpdu_info_get_peerid,
+};
+
+const struct ath11k_hw_ops wcn6855_ops = {
+	.get_hw_mac_from_pdev_id = ath11k_hw_ipq8074_mac_from_pdev_id,
+	.wmi_init_config = ath11k_init_wmi_config_qca6390,
+	.mac_id_to_pdev_id = ath11k_hw_mac_id_to_pdev_id_qca6390,
+	.mac_id_to_srng_id = ath11k_hw_mac_id_to_srng_id_qca6390,
+	.tx_mesh_enable = ath11k_hw_wcn6855_tx_mesh_enable,
+	.rx_desc_get_first_msdu = ath11k_hw_wcn6855_rx_desc_get_first_msdu,
+	.rx_desc_get_last_msdu = ath11k_hw_wcn6855_rx_desc_get_last_msdu,
+	.rx_desc_get_l3_pad_bytes = ath11k_hw_wcn6855_rx_desc_get_l3_pad_bytes,
+	.rx_desc_get_hdr_status = ath11k_hw_wcn6855_rx_desc_get_hdr_status,
+	.rx_desc_encrypt_valid = ath11k_hw_wcn6855_rx_desc_encrypt_valid,
+	.rx_desc_get_encrypt_type = ath11k_hw_wcn6855_rx_desc_get_encrypt_type,
+	.rx_desc_get_decap_type = ath11k_hw_wcn6855_rx_desc_get_decap_type,
+	.rx_desc_get_mesh_ctl = ath11k_hw_wcn6855_rx_desc_get_mesh_ctl,
+	.rx_desc_get_mpdu_seq_ctl_vld = ath11k_hw_wcn6855_rx_desc_get_mpdu_seq_ctl_vld,
+	.rx_desc_get_mpdu_fc_valid = ath11k_hw_wcn6855_rx_desc_get_mpdu_fc_valid,
+	.rx_desc_get_mpdu_start_seq_no = ath11k_hw_wcn6855_rx_desc_get_mpdu_start_seq_no,
+	.rx_desc_get_msdu_len = ath11k_hw_wcn6855_rx_desc_get_msdu_len,
+	.rx_desc_get_msdu_sgi = ath11k_hw_wcn6855_rx_desc_get_msdu_sgi,
+	.rx_desc_get_msdu_rate_mcs = ath11k_hw_wcn6855_rx_desc_get_msdu_rate_mcs,
+	.rx_desc_get_msdu_rx_bw = ath11k_hw_wcn6855_rx_desc_get_msdu_rx_bw,
+	.rx_desc_get_msdu_freq = ath11k_hw_wcn6855_rx_desc_get_msdu_freq,
+	.rx_desc_get_msdu_pkt_type = ath11k_hw_wcn6855_rx_desc_get_msdu_pkt_type,
+	.rx_desc_get_msdu_nss = ath11k_hw_wcn6855_rx_desc_get_msdu_nss,
+	.rx_desc_get_mpdu_tid = ath11k_hw_wcn6855_rx_desc_get_mpdu_tid,
+	.rx_desc_get_mpdu_peer_id = ath11k_hw_wcn6855_rx_desc_get_mpdu_peer_id,
+	.rx_desc_copy_attn_end_tlv = ath11k_hw_wcn6855_rx_desc_copy_attn_end,
+	.rx_desc_get_mpdu_start_tag = ath11k_hw_wcn6855_rx_desc_get_mpdu_start_tag,
+	.rx_desc_get_mpdu_ppdu_id = ath11k_hw_wcn6855_rx_desc_get_mpdu_ppdu_id,
+	.rx_desc_set_msdu_len = ath11k_hw_wcn6855_rx_desc_set_msdu_len,
+	.rx_desc_get_attention = ath11k_hw_wcn6855_rx_desc_get_attention,
+	.rx_desc_get_msdu_payload = ath11k_hw_wcn6855_rx_desc_get_msdu_payload,
+	.reo_setup = ath11k_hw_wcn6855_reo_setup,
+	.mpdu_info_get_peerid = ath11k_hw_wcn6855_mpdu_info_get_peerid,
 };
 
 #define ATH11K_TX_RING_MASK_0 0x1
@@ -1688,3 +2008,74 @@ const struct ath11k_hw_regs qcn9074_regs = {
 	.pcie_qserdes_sysclk_en_sel = 0x01e0e0a8,
 	.pcie_pcs_osc_dtct_config_base = 0x01e0f45c,
 };
+
+const struct ath11k_hw_regs wcn6855_regs = {
+	/* SW2TCL(x) R0 ring configuration address */
+	.hal_tcl1_ring_base_lsb = 0x00000690,
+	.hal_tcl1_ring_base_msb = 0x00000694,
+	.hal_tcl1_ring_id = 0x00000698,
+	.hal_tcl1_ring_misc = 0x000006a0,
+	.hal_tcl1_ring_tp_addr_lsb = 0x000006ac,
+	.hal_tcl1_ring_tp_addr_msb = 0x000006b0,
+	.hal_tcl1_ring_consumer_int_setup_ix0 = 0x000006c0,
+	.hal_tcl1_ring_consumer_int_setup_ix1 = 0x000006c4,
+	.hal_tcl1_ring_msi1_base_lsb = 0x000006d8,
+	.hal_tcl1_ring_msi1_base_msb = 0x000006dc,
+	.hal_tcl1_ring_msi1_data = 0x000006e0,
+	.hal_tcl2_ring_base_lsb = 0x000006e8,
+	.hal_tcl_ring_base_lsb = 0x00000798,
+
+	/* TCL STATUS ring address */
+	.hal_tcl_status_ring_base_lsb = 0x000008a0,
+
+	/* REO2SW(x) R0 ring configuration address */
+	.hal_reo1_ring_base_lsb = 0x00000244,
+	.hal_reo1_ring_base_msb = 0x00000248,
+	.hal_reo1_ring_id = 0x0000024c,
+	.hal_reo1_ring_misc = 0x00000254,
+	.hal_reo1_ring_hp_addr_lsb = 0x00000258,
+	.hal_reo1_ring_hp_addr_msb = 0x0000025c,
+	.hal_reo1_ring_producer_int_setup = 0x00000268,
+	.hal_reo1_ring_msi1_base_lsb = 0x0000028c,
+	.hal_reo1_ring_msi1_base_msb = 0x00000290,
+	.hal_reo1_ring_msi1_data = 0x00000294,
+	.hal_reo2_ring_base_lsb = 0x0000029c,
+	.hal_reo1_aging_thresh_ix_0 = 0x000005bc,
+	.hal_reo1_aging_thresh_ix_1 = 0x000005c0,
+	.hal_reo1_aging_thresh_ix_2 = 0x000005c4,
+	.hal_reo1_aging_thresh_ix_3 = 0x000005c8,
+
+	/* REO2SW(x) R2 ring pointers (head/tail) address */
+	.hal_reo1_ring_hp = 0x00003030,
+	.hal_reo1_ring_tp = 0x00003034,
+	.hal_reo2_ring_hp = 0x00003038,
+
+	/* REO2TCL R0 ring configuration address */
+	.hal_reo_tcl_ring_base_lsb = 0x00000454,
+	.hal_reo_tcl_ring_hp = 0x00003060,
+
+	/* REO status address */
+	.hal_reo_status_ring_base_lsb = 0x0000055c,
+	.hal_reo_status_hp = 0x00003078,
+
+	/* WCSS relative address */
+	.hal_seq_wcss_umac_ce0_src_reg = 0x1b80000,
+	.hal_seq_wcss_umac_ce0_dst_reg = 0x1b81000,
+	.hal_seq_wcss_umac_ce1_src_reg = 0x1b82000,
+	.hal_seq_wcss_umac_ce1_dst_reg = 0x1b83000,
+
+	/* WBM Idle address */
+	.hal_wbm_idle_link_ring_base_lsb = 0x00000870,
+	.hal_wbm_idle_link_ring_misc = 0x00000880,
+
+	/* SW2WBM release address */
+	.hal_wbm_release_ring_base_lsb = 0x000001e8,
+
+	/* WBM2SW release address */
+	.hal_wbm0_release_ring_base_lsb = 0x00000920,
+	.hal_wbm1_release_ring_base_lsb = 0x00000978,
+
+	/* PCIe base address */
+	.pcie_qserdes_sysclk_en_sel = 0x01e0c0ac,
+	.pcie_pcs_osc_dtct_config_base = 0x01e0c628,
+};
diff --git a/drivers/net/wireless/ath/ath11k/hw.h b/drivers/net/wireless/ath/ath11k/hw.h
index c81a6328361d..62f5978b3005 100644
--- a/drivers/net/wireless/ath/ath11k/hw.h
+++ b/drivers/net/wireless/ath/ath11k/hw.h
@@ -162,6 +162,7 @@ struct ath11k_hw_params {
 	bool cold_boot_calib;
 	bool supports_suspend;
 	u32 hal_desc_sz;
+	bool fix_l1ss;
 };
 
 struct ath11k_hw_ops {
@@ -199,12 +200,15 @@ struct ath11k_hw_ops {
 	void (*rx_desc_set_msdu_len)(struct hal_rx_desc *desc, u16 len);
 	struct rx_attention *(*rx_desc_get_attention)(struct hal_rx_desc *desc);
 	u8 *(*rx_desc_get_msdu_payload)(struct hal_rx_desc *desc);
+	void (*reo_setup)(struct ath11k_base *ab);
+	u16 (*mpdu_info_get_peerid)(u8 *tlv_data);
 };
 
 extern const struct ath11k_hw_ops ipq8074_ops;
 extern const struct ath11k_hw_ops ipq6018_ops;
 extern const struct ath11k_hw_ops qca6390_ops;
 extern const struct ath11k_hw_ops qcn9074_ops;
+extern const struct ath11k_hw_ops wcn6855_ops;
 
 extern const struct ath11k_hw_ring_mask ath11k_hw_ring_mask_ipq8074;
 extern const struct ath11k_hw_ring_mask ath11k_hw_ring_mask_qca6390;
@@ -318,5 +322,6 @@ struct ath11k_hw_regs {
 extern const struct ath11k_hw_regs ipq8074_regs;
 extern const struct ath11k_hw_regs qca6390_regs;
 extern const struct ath11k_hw_regs qcn9074_regs;
+extern const struct ath11k_hw_regs wcn6855_regs;
 
 #endif
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 9d0ff150ec30..eb52332dbe3f 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -5379,11 +5379,6 @@ ath11k_mac_update_vif_chan(struct ath11k *ar,
 		if (WARN_ON(!arvif->is_up))
 			continue;
 
-		ret = ath11k_mac_setup_bcn_tmpl(arvif);
-		if (ret)
-			ath11k_warn(ab, "failed to update bcn tmpl during csa: %d\n",
-				    ret);
-
 		ret = ath11k_mac_vdev_restart(arvif, &vifs[i].new_ctx->def);
 		if (ret) {
 			ath11k_warn(ab, "failed to restart vdev %d: %d\n",
@@ -5391,6 +5386,11 @@ ath11k_mac_update_vif_chan(struct ath11k *ar,
 			continue;
 		}
 
+		ret = ath11k_mac_setup_bcn_tmpl(arvif);
+		if (ret)
+			ath11k_warn(ab, "failed to update bcn tmpl during csa: %d\n",
+				    ret);
+
 		ret = ath11k_wmi_vdev_up(arvif->ar, arvif->vdev_id, arvif->aid,
 					 arvif->bssid);
 		if (ret) {
diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c
index 27b394d115e2..75cc2d80fde8 100644
--- a/drivers/net/wireless/ath/ath11k/mhi.c
+++ b/drivers/net/wireless/ath/ath11k/mhi.c
@@ -354,6 +354,7 @@ int ath11k_mhi_register(struct ath11k_pci *ab_pci)
 		ath11k_mhi_config = &ath11k_mhi_config_qcn9074;
 		break;
 	case ATH11K_HW_QCA6390_HW20:
+	case ATH11K_HW_WCN6855_HW20:
 		ath11k_mhi_config = &ath11k_mhi_config_qca6390;
 		break;
 	default:
diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c
index 0f31eb566fb6..f8f6b2090dad 100644
--- a/drivers/net/wireless/ath/ath11k/pci.c
+++ b/drivers/net/wireless/ath/ath11k/pci.c
@@ -36,9 +36,11 @@
 
 #define QCA6390_DEVICE_ID		0x1101
 #define QCN9074_DEVICE_ID		0x1104
+#define WCN6855_DEVICE_ID		0x1103
 
 static const struct pci_device_id ath11k_pci_id_table[] = {
 	{ PCI_VDEVICE(QCOM, QCA6390_DEVICE_ID) },
+	{ PCI_VDEVICE(QCOM, WCN6855_DEVICE_ID) },
 	/* TODO: add QCN9074_DEVICE_ID) once firmware issues are resolved */
 	{0}
 };
@@ -432,7 +434,8 @@ static void ath11k_pci_sw_reset(struct ath11k_base *ab, bool power_on)
 		ath11k_pci_enable_ltssm(ab);
 		ath11k_pci_clear_all_intrs(ab);
 		ath11k_pci_set_wlaon_pwr_ctrl(ab);
-		ath11k_pci_fix_l1ss(ab);
+		if (ab->hw_params.fix_l1ss)
+			ath11k_pci_fix_l1ss(ab);
 	}
 
 	ath11k_mhi_clear_vector(ab);
@@ -1176,12 +1179,26 @@ static const struct ath11k_hif_ops ath11k_pci_hif_ops = {
 	.get_ce_msi_idx = ath11k_pci_get_ce_msi_idx,
 };
 
+static void ath11k_pci_read_hw_version(struct ath11k_base *ab, u32 *major, u32 *minor)
+{
+	u32 soc_hw_version;
+
+	soc_hw_version = ath11k_pci_read32(ab, TCSR_SOC_HW_VERSION);
+	*major = FIELD_GET(TCSR_SOC_HW_VERSION_MAJOR_MASK,
+			   soc_hw_version);
+	*minor = FIELD_GET(TCSR_SOC_HW_VERSION_MINOR_MASK,
+			   soc_hw_version);
+
+	ath11k_dbg(ab, ATH11K_DBG_PCI, "pci tcsr_soc_hw_version major %d minor %d\n",
+		   *major, *minor);
+}
+
 static int ath11k_pci_probe(struct pci_dev *pdev,
 			    const struct pci_device_id *pci_dev)
 {
 	struct ath11k_base *ab;
 	struct ath11k_pci *ab_pci;
-	u32 soc_hw_version, soc_hw_version_major, soc_hw_version_minor;
+	u32 soc_hw_version_major, soc_hw_version_minor;
 	int ret;
 
 	ab = ath11k_core_alloc(&pdev->dev, sizeof(*ab_pci), ATH11K_BUS_PCI,
@@ -1209,15 +1226,8 @@ static int ath11k_pci_probe(struct pci_dev *pdev,
 
 	switch (pci_dev->device) {
 	case QCA6390_DEVICE_ID:
-		soc_hw_version = ath11k_pci_read32(ab, TCSR_SOC_HW_VERSION);
-		soc_hw_version_major = FIELD_GET(TCSR_SOC_HW_VERSION_MAJOR_MASK,
-						 soc_hw_version);
-		soc_hw_version_minor = FIELD_GET(TCSR_SOC_HW_VERSION_MINOR_MASK,
-						 soc_hw_version);
-
-		ath11k_dbg(ab, ATH11K_DBG_PCI, "pci tcsr_soc_hw_version major %d minor %d\n",
-			   soc_hw_version_major, soc_hw_version_minor);
-
+		ath11k_pci_read_hw_version(ab, &soc_hw_version_major,
+					   &soc_hw_version_minor);
 		switch (soc_hw_version_major) {
 		case 2:
 			ab->hw_rev = ATH11K_HW_QCA6390_HW20;
@@ -1235,6 +1245,21 @@ static int ath11k_pci_probe(struct pci_dev *pdev,
 		ab->bus_params.static_window_map = true;
 		ab->hw_rev = ATH11K_HW_QCN9074_HW10;
 		break;
+	case WCN6855_DEVICE_ID:
+		ath11k_pci_read_hw_version(ab, &soc_hw_version_major,
+					   &soc_hw_version_minor);
+		switch (soc_hw_version_major) {
+		case 2:
+			ab->hw_rev = ATH11K_HW_WCN6855_HW20;
+			break;
+		default:
+			dev_err(&pdev->dev, "Unsupported WCN6855 SOC hardware version: %d %d\n",
+				soc_hw_version_major, soc_hw_version_minor);
+			ret = -EOPNOTSUPP;
+			goto err_pci_free_region;
+		}
+		ab_pci->msi_config = &ath11k_msi_config[0];
+		break;
 	default:
 		dev_err(&pdev->dev, "Unknown PCI device found: 0x%x\n",
 			pci_dev->device);
diff --git a/drivers/net/wireless/ath/ath11k/rx_desc.h b/drivers/net/wireless/ath/ath11k/rx_desc.h
index 0cdb4a1f816e..79c50804d7dc 100644
--- a/drivers/net/wireless/ath/ath11k/rx_desc.h
+++ b/drivers/net/wireless/ath/ath11k/rx_desc.h
@@ -368,6 +368,7 @@ struct rx_attention {
 #define RX_MPDU_START_INFO2_BSSID_HIT		BIT(9)
 #define RX_MPDU_START_INFO2_BSSID_NUM		GENMASK(13, 10)
 #define RX_MPDU_START_INFO2_TID			GENMASK(17, 14)
+#define RX_MPDU_START_INFO2_TID_WCN6855		GENMASK(18, 15)
 
 #define RX_MPDU_START_INFO3_REO_DEST_IND		GENMASK(4, 0)
 #define RX_MPDU_START_INFO3_FLOW_ID_TOEPLITZ		BIT(7)
@@ -546,6 +547,31 @@ struct rx_mpdu_start_qcn9074 {
 	__le32 ht_ctrl;
 } __packed;
 
+struct rx_mpdu_start_wcn6855 {
+	__le32 info3;
+	__le32 reo_queue_desc_lo;
+	__le32 info4;
+	__le32 pn[4];
+	__le32 info2;
+	__le32 peer_meta_data;
+	__le16 info0;
+	__le16 phy_ppdu_id;
+	__le16 ast_index;
+	__le16 sw_peer_id;
+	__le32 info1;
+	__le32 info5;
+	__le32 info6;
+	__le16 frame_ctrl;
+	__le16 duration;
+	u8 addr1[ETH_ALEN];
+	u8 addr2[ETH_ALEN];
+	u8 addr3[ETH_ALEN];
+	__le16 seq_ctrl;
+	u8 addr4[ETH_ALEN];
+	__le16 qos_ctrl;
+	__le32 ht_ctrl;
+} __packed;
+
 /* rx_mpdu_start
  *
  * rxpcu_mpdu_filter_in_category
@@ -804,6 +830,20 @@ struct rx_msdu_start_qcn9074 {
 	__le16 vlan_stag_c1;
 } __packed;
 
+struct rx_msdu_start_wcn6855 {
+	__le16 info0;
+	__le16 phy_ppdu_id;
+	__le32 info1;
+	__le32 info2;
+	__le32 toeplitz_hash;
+	__le32 flow_id_toeplitz;
+	__le32 info3;
+	__le32 ppdu_start_timestamp;
+	__le32 phy_meta_data;
+	__le16 vlan_ctag_ci;
+	__le16 vlan_stag_ci;
+} __packed;
+
 /* rx_msdu_start
  *
  * rxpcu_mpdu_filter_in_category
@@ -988,7 +1028,9 @@ struct rx_msdu_start_qcn9074 {
 
 #define RX_MSDU_END_INFO2_REPORTED_MPDU_LEN	GENMASK(13, 0)
 #define RX_MSDU_END_INFO2_FIRST_MSDU		BIT(14)
+#define RX_MSDU_END_INFO2_FIRST_MSDU_WCN6855	BIT(28)
 #define RX_MSDU_END_INFO2_LAST_MSDU		BIT(15)
+#define RX_MSDU_END_INFO2_LAST_MSDU_WCN6855	BIT(29)
 #define RX_MSDU_END_INFO2_SA_IDX_TIMEOUT	BIT(16)
 #define RX_MSDU_END_INFO2_DA_IDX_TIMEOUT	BIT(17)
 #define RX_MSDU_END_INFO2_MSDU_LIMIT_ERR	BIT(18)
@@ -1037,6 +1079,31 @@ struct rx_msdu_end_ipq8074 {
 	__le16 sa_sw_peer_id;
 } __packed;
 
+struct rx_msdu_end_wcn6855 {
+	__le16 info0;
+	__le16 phy_ppdu_id;
+	__le16 ip_hdr_cksum;
+	__le16 reported_mpdu_len;
+	__le32 info1;
+	__le32 ext_wapi_pn[2];
+	__le32 info4;
+	__le32 ipv6_options_crc;
+	__le32 tcp_seq_num;
+	__le32 tcp_ack_num;
+	__le16 info3;
+	__le16 window_size;
+	__le32 info2;
+	__le16 sa_idx;
+	__le16 da_idx;
+	__le32 info5;
+	__le32 fse_metadata;
+	__le16 cce_metadata;
+	__le16 sa_sw_peer_id;
+	__le32 rule_indication[2];
+	__le32 info6;
+	__le32 info7;
+} __packed;
+
 #define RX_MSDU_END_MPDU_LENGTH_INFO		GENMASK(13, 0)
 
 #define RX_MSDU_END_INFO2_DA_OFFSET		GENMASK(5, 0)
@@ -1400,10 +1467,30 @@ struct hal_rx_desc_qcn9074 {
 	u8 msdu_payload[0];
 } __packed;
 
+struct hal_rx_desc_wcn6855 {
+	__le32 msdu_end_tag;
+	struct rx_msdu_end_wcn6855 msdu_end;
+	__le32 rx_attn_tag;
+	struct rx_attention attention;
+	__le32 msdu_start_tag;
+	struct rx_msdu_start_wcn6855 msdu_start;
+	u8 rx_padding0[HAL_RX_DESC_PADDING0_BYTES];
+	__le32 mpdu_start_tag;
+	struct rx_mpdu_start_wcn6855 mpdu_start;
+	__le32 mpdu_end_tag;
+	struct rx_mpdu_end mpdu_end;
+	u8 rx_padding1[HAL_RX_DESC_PADDING1_BYTES];
+	__le32 hdr_status_tag;
+	__le32 phy_ppdu_id;
+	u8 hdr_status[HAL_RX_DESC_HDR_STATUS_LEN];
+	u8 msdu_payload[0];
+} __packed;
+
 struct hal_rx_desc {
 	union {
 		struct hal_rx_desc_ipq8074 ipq8074;
 		struct hal_rx_desc_qcn9074 qcn9074;
+		struct hal_rx_desc_wcn6855 wcn6855;
 	} u;
 } __packed;
 
diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c
index 5ca2d80679b6..6c253eae9d06 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.c
+++ b/drivers/net/wireless/ath/ath11k/wmi.c
@@ -5235,7 +5235,7 @@ ath11k_wmi_pull_pdev_stats_tx(const struct wmi_pdev_stats_tx *src,
 	dst->hw_reaped = src->hw_reaped;
 	dst->underrun = src->underrun;
 	dst->tx_abort = src->tx_abort;
-	dst->mpdus_requed = src->mpdus_requed;
+	dst->mpdus_requeued = src->mpdus_requeued;
 	dst->tx_ko = src->tx_ko;
 	dst->data_rc = src->data_rc;
 	dst->self_triggers = src->self_triggers;
@@ -5505,7 +5505,7 @@ ath11k_wmi_fw_pdev_tx_stats_fill(const struct ath11k_fw_stats_pdev *pdev,
 	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
 			 "PPDUs cleaned", pdev->tx_abort);
 	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
-			 "MPDUs requed", pdev->mpdus_requed);
+			 "MPDUs requeued", pdev->mpdus_requeued);
 	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
 			 "Excessive retries", pdev->tx_ko);
 	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
diff --git a/drivers/net/wireless/ath/ath11k/wmi.h b/drivers/net/wireless/ath/ath11k/wmi.h
index 3ade1ddd35c9..d35c47e0b19d 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.h
+++ b/drivers/net/wireless/ath/ath11k/wmi.h
@@ -4171,8 +4171,8 @@ struct wmi_pdev_stats_tx {
 	/* Num PPDUs cleaned up in TX abort */
 	s32 tx_abort;
 
-	/* Num MPDUs requed by SW */
-	s32 mpdus_requed;
+	/* Num MPDUs requeued by SW */
+	s32 mpdus_requeued;
 
 	/* excessive retries */
 	u32 tx_ko;
diff --git a/drivers/net/wireless/ath/ath5k/pcu.c b/drivers/net/wireless/ath/ath5k/pcu.c
index f2db7cf16566..3f4ce4e9c532 100644
--- a/drivers/net/wireless/ath/ath5k/pcu.c
+++ b/drivers/net/wireless/ath/ath5k/pcu.c
@@ -855,7 +855,7 @@ ath5k_hw_start_rx_pcu(struct ath5k_hw *ah)
 }
 
 /**
- * at5k_hw_stop_rx_pcu() - Stop RX engine
+ * ath5k_hw_stop_rx_pcu() - Stop RX engine
  * @ah: The &struct ath5k_hw
  *
  * Stops RX engine on PCU
diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index 29527e8dcced..fefdc6753acd 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -3303,8 +3303,8 @@ static int ath6kl_cfg80211_sscan_start(struct wiphy *wiphy,
 		if (ret < 0)
 			return ret;
 	} else {
-		 ret = ath6kl_wmi_bssfilter_cmd(ar->wmi, vif->fw_vif_idx,
-						MATCHED_SSID_FILTER, 0);
+		ret = ath6kl_wmi_bssfilter_cmd(ar->wmi, vif->fw_vif_idx,
+					       MATCHED_SSID_FILTER, 0);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_mac.c b/drivers/net/wireless/ath/ath9k/ar9003_mac.c
index 76b538942a79..5184a0aacfe2 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_mac.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_mac.c
@@ -522,6 +522,8 @@ int ath9k_hw_process_rxdesc_edma(struct ath_hw *ah, struct ath_rx_status *rxs,
 	rxs->rs_moreaggr = (rxsp->status11 & AR_RxMoreAggr) ? 1 : 0;
 	rxs->rs_antenna = (MS(rxsp->status4, AR_RxAntenna) & 0x7);
 	rxs->enc_flags |= (rxsp->status4 & AR_GI) ? RX_ENC_FLAG_SHORT_GI : 0;
+	rxs->enc_flags |=
+		(rxsp->status4 & AR_STBC) ? (1 << RX_ENC_FLAG_STBC_SHIFT) : 0;
 	rxs->bw = (rxsp->status4 & AR_2040) ? RATE_INFO_BW_40 : RATE_INFO_BW_20;
 
 	rxs->evm0 = rxsp->status6;
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 45f6402478b5..97c3a53f9cef 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -307,6 +307,11 @@ static int ath_reset_internal(struct ath_softc *sc, struct ath9k_channel *hchan)
 		hchan = ah->curchan;
 	}
 
+	if (!hchan) {
+		fastcc = false;
+		hchan = ath9k_cmn_get_channel(sc->hw, ah, &sc->cur_chan->chandef);
+	}
+
 	if (!ath_prepare_reset(sc))
 		fastcc = false;
 
diff --git a/drivers/net/wireless/ath/carl9170/Kconfig b/drivers/net/wireless/ath/carl9170/Kconfig
index b2d760873992..ba9bea79381c 100644
--- a/drivers/net/wireless/ath/carl9170/Kconfig
+++ b/drivers/net/wireless/ath/carl9170/Kconfig
@@ -16,13 +16,11 @@ config CARL9170
 
 config CARL9170_LEDS
 	bool "SoftLED Support"
-	depends on CARL9170
-	select MAC80211_LEDS
-	select LEDS_CLASS
-	select NEW_LEDS
 	default y
+	depends on CARL9170
+	depends on MAC80211_LEDS
 	help
-	  This option is necessary, if you want your device' LEDs to blink
+	  This option is necessary, if you want your device's LEDs to blink.
 
 	  Say Y, unless you need the LEDs for firmware debugging.
 
diff --git a/drivers/net/wireless/ath/hw.c b/drivers/net/wireless/ath/hw.c
index eae9abf540a7..b53ebb3ac9a2 100644
--- a/drivers/net/wireless/ath/hw.c
+++ b/drivers/net/wireless/ath/hw.c
@@ -24,7 +24,7 @@
 #define REG_WRITE(_ah, _reg, _val)	(common->ops->write)(_ah, _val, _reg)
 
 /**
- * ath_hw_set_bssid_mask - filter out bssids we listen
+ * ath_hw_setbssidmask - filter out bssids we listen
  *
  * @common: the ath_common struct for the device.
  *
diff --git a/drivers/net/wireless/ath/wcn36xx/dxe.c b/drivers/net/wireless/ath/wcn36xx/dxe.c
index 63079231e48e..8e1dbfda6538 100644
--- a/drivers/net/wireless/ath/wcn36xx/dxe.c
+++ b/drivers/net/wireless/ath/wcn36xx/dxe.c
@@ -800,7 +800,7 @@ int wcn36xx_dxe_tx_frame(struct wcn36xx *wcn,
 			 (char *)ctl_skb->skb->data, ctl_skb->skb->len);
 
 	/* Move the head of the ring to the next empty descriptor */
-	 ch->head_blk_ctl = ctl_skb->next;
+	ch->head_blk_ctl = ctl_skb->next;
 
 	/* Commit all previous writes and set descriptors to VALID */
 	wmb();
diff --git a/drivers/net/wireless/ath/wcn36xx/hal.h b/drivers/net/wireless/ath/wcn36xx/hal.h
index 65ef893f2736..455143c4164e 100644
--- a/drivers/net/wireless/ath/wcn36xx/hal.h
+++ b/drivers/net/wireless/ath/wcn36xx/hal.h
@@ -3464,8 +3464,12 @@ struct wcn36xx_hal_rem_bcn_filter_req {
 #define WCN36XX_HAL_OFFLOAD_DISABLE                         0
 #define WCN36XX_HAL_OFFLOAD_ENABLE                          1
 #define WCN36XX_HAL_OFFLOAD_BCAST_FILTER_ENABLE             0x2
+#define WCN36XX_HAL_OFFLOAD_MCAST_FILTER_ENABLE             0x4
+#define WCN36XX_HAL_OFFLOAD_NS_AND_MCAST_FILTER_ENABLE	\
+	(WCN36XX_HAL_OFFLOAD_ENABLE | WCN36XX_HAL_OFFLOAD_MCAST_FILTER_ENABLE)
 #define WCN36XX_HAL_OFFLOAD_ARP_AND_BCAST_FILTER_ENABLE	\
-	(HAL_OFFLOAD_ENABLE|HAL_OFFLOAD_BCAST_FILTER_ENABLE)
+	(WCN36XX_HAL_OFFLOAD_ENABLE | WCN36XX_HAL_OFFLOAD_BCAST_FILTER_ENABLE)
+#define WCN36XX_HAL_IPV6_OFFLOAD_ADDR_MAX		0x02
 
 struct wcn36xx_hal_ns_offload_params {
 	u8 src_ipv6_addr[WCN36XX_HAL_IPV6_ADDR_LEN];
@@ -3487,10 +3491,10 @@ struct wcn36xx_hal_ns_offload_params {
 	/* slot index for this offload */
 	u32 slot_index;
 	u8 bss_index;
-};
+} __packed;
 
 struct wcn36xx_hal_host_offload_req {
-	u8 offload_Type;
+	u8 offload_type;
 
 	/* enable or disable */
 	u8 enable;
@@ -3499,13 +3503,13 @@ struct wcn36xx_hal_host_offload_req {
 		u8 host_ipv4_addr[4];
 		u8 host_ipv6_addr[WCN36XX_HAL_IPV6_ADDR_LEN];
 	} u;
-};
+} __packed;
 
 struct wcn36xx_hal_host_offload_req_msg {
 	struct wcn36xx_hal_msg_header header;
 	struct wcn36xx_hal_host_offload_req host_offload_params;
 	struct wcn36xx_hal_ns_offload_params ns_offload_params;
-};
+} __packed;
 
 /* Packet Types. */
 #define WCN36XX_HAL_KEEP_ALIVE_NULL_PKT              1
@@ -4901,7 +4905,7 @@ struct wcn36xx_hal_gtk_offload_req_msg {
 	u64 key_replay_counter;
 
 	u8 bss_index;
-};
+} __packed;
 
 struct wcn36xx_hal_gtk_offload_rsp_msg {
 	struct wcn36xx_hal_msg_header header;
@@ -4915,7 +4919,7 @@ struct wcn36xx_hal_gtk_offload_rsp_msg {
 struct wcn36xx_hal_gtk_offload_get_info_req_msg {
 	struct wcn36xx_hal_msg_header header;
 	u8 bss_index;
-};
+} __packed;
 
 struct wcn36xx_hal_gtk_offload_get_info_rsp_msg {
 	struct wcn36xx_hal_msg_header header;
@@ -4939,7 +4943,7 @@ struct wcn36xx_hal_gtk_offload_get_info_rsp_msg {
 	u32 igtk_rekey_count;
 
 	u8 bss_index;
-};
+} __packed;
 
 struct dhcp_info {
 	/* Indicates the device mode which indicates about the DHCP activity */
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index afb4877eaad8..d202f2128df2 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -25,6 +25,7 @@
 #include <linux/rpmsg.h>
 #include <linux/soc/qcom/smem_state.h>
 #include <linux/soc/qcom/wcnss_ctrl.h>
+#include <net/ipv6.h>
 #include "wcn36xx.h"
 #include "testmode.h"
 
@@ -172,7 +173,9 @@ static struct ieee80211_supported_band wcn_band_5ghz = {
 #ifdef CONFIG_PM
 
 static const struct wiphy_wowlan_support wowlan_support = {
-	.flags = WIPHY_WOWLAN_ANY
+	.flags = WIPHY_WOWLAN_ANY	|
+		 WIPHY_WOWLAN_MAGIC_PKT	|
+		 WIPHY_WOWLAN_SUPPORTS_GTK_REKEY
 };
 
 #endif
@@ -293,23 +296,16 @@ static int wcn36xx_start(struct ieee80211_hw *hw)
 		goto out_free_dxe_pool;
 	}
 
-	wcn->hal_buf = kmalloc(WCN36XX_HAL_BUF_SIZE, GFP_KERNEL);
-	if (!wcn->hal_buf) {
-		wcn36xx_err("Failed to allocate smd buf\n");
-		ret = -ENOMEM;
-		goto out_free_dxe_ctl;
-	}
-
 	ret = wcn36xx_smd_load_nv(wcn);
 	if (ret) {
 		wcn36xx_err("Failed to push NV to chip\n");
-		goto out_free_smd_buf;
+		goto out_free_dxe_ctl;
 	}
 
 	ret = wcn36xx_smd_start(wcn);
 	if (ret) {
 		wcn36xx_err("Failed to start chip\n");
-		goto out_free_smd_buf;
+		goto out_free_dxe_ctl;
 	}
 
 	if (!wcn36xx_is_fw_version(wcn, 1, 2, 2, 24)) {
@@ -336,8 +332,6 @@ static int wcn36xx_start(struct ieee80211_hw *hw)
 
 out_smd_stop:
 	wcn36xx_smd_stop(wcn);
-out_free_smd_buf:
-	kfree(wcn->hal_buf);
 out_free_dxe_ctl:
 	wcn36xx_dxe_free_ctl_blks(wcn);
 out_free_dxe_pool:
@@ -372,8 +366,6 @@ static void wcn36xx_stop(struct ieee80211_hw *hw)
 
 	wcn36xx_dxe_free_mem_pools(wcn);
 	wcn36xx_dxe_free_ctl_blks(wcn);
-
-	kfree(wcn->hal_buf);
 }
 
 static void wcn36xx_change_ps(struct wcn36xx *wcn, bool enable)
@@ -1088,28 +1080,91 @@ static int wcn36xx_sta_remove(struct ieee80211_hw *hw,
 
 #ifdef CONFIG_PM
 
+static struct ieee80211_vif *wcn36xx_get_first_assoc_vif(struct wcn36xx *wcn)
+{
+	struct wcn36xx_vif *vif_priv = NULL;
+	struct ieee80211_vif *vif = NULL;
+
+	list_for_each_entry(vif_priv, &wcn->vif_list, list) {
+		if (vif_priv->sta_assoc) {
+			vif = wcn36xx_priv_to_vif(vif_priv);
+			break;
+		}
+	}
+	return vif;
+}
+
 static int wcn36xx_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wow)
 {
 	struct wcn36xx *wcn = hw->priv;
+	struct ieee80211_vif *vif = NULL;
+	int ret = 0;
 
 	wcn36xx_dbg(WCN36XX_DBG_MAC, "mac suspend\n");
 
-	flush_workqueue(wcn->hal_ind_wq);
-	wcn36xx_smd_set_power_params(wcn, true);
-	return 0;
+	mutex_lock(&wcn->conf_mutex);
+
+	vif = wcn36xx_get_first_assoc_vif(wcn);
+	if (vif) {
+		ret = wcn36xx_smd_arp_offload(wcn, vif, true);
+		if (ret)
+			goto out;
+		ret = wcn36xx_smd_ipv6_ns_offload(wcn, vif, true);
+		if (ret)
+			goto out;
+		ret = wcn36xx_smd_gtk_offload(wcn, vif, true);
+		if (ret)
+			goto out;
+		ret = wcn36xx_smd_set_power_params(wcn, true);
+		if (ret)
+			goto out;
+		ret = wcn36xx_smd_wlan_host_suspend_ind(wcn);
+	}
+out:
+	mutex_unlock(&wcn->conf_mutex);
+	return ret;
 }
 
 static int wcn36xx_resume(struct ieee80211_hw *hw)
 {
 	struct wcn36xx *wcn = hw->priv;
+	struct ieee80211_vif *vif = NULL;
 
 	wcn36xx_dbg(WCN36XX_DBG_MAC, "mac resume\n");
 
-	flush_workqueue(wcn->hal_ind_wq);
-	wcn36xx_smd_set_power_params(wcn, false);
+	mutex_lock(&wcn->conf_mutex);
+	vif = wcn36xx_get_first_assoc_vif(wcn);
+	if (vif) {
+		wcn36xx_smd_host_resume(wcn);
+		wcn36xx_smd_set_power_params(wcn, false);
+		wcn36xx_smd_gtk_offload_get_info(wcn, vif);
+		wcn36xx_smd_gtk_offload(wcn, vif, false);
+		wcn36xx_smd_ipv6_ns_offload(wcn, vif, false);
+		wcn36xx_smd_arp_offload(wcn, vif, false);
+	}
+	mutex_unlock(&wcn->conf_mutex);
+
 	return 0;
 }
 
+static void wcn36xx_set_rekey_data(struct ieee80211_hw *hw,
+				   struct ieee80211_vif *vif,
+				   struct cfg80211_gtk_rekey_data *data)
+{
+	struct wcn36xx *wcn = hw->priv;
+	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
+
+	mutex_lock(&wcn->conf_mutex);
+
+	memcpy(vif_priv->rekey_data.kek, data->kek, NL80211_KEK_LEN);
+	memcpy(vif_priv->rekey_data.kck, data->kck, NL80211_KCK_LEN);
+	vif_priv->rekey_data.replay_ctr =
+		cpu_to_le64(be64_to_cpup((__be64 *)data->replay_ctr));
+	vif_priv->rekey_data.valid = true;
+
+	mutex_unlock(&wcn->conf_mutex);
+}
+
 #endif
 
 static int wcn36xx_ampdu_action(struct ieee80211_hw *hw,
@@ -1176,6 +1231,34 @@ static int wcn36xx_ampdu_action(struct ieee80211_hw *hw,
 	return ret;
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
+static void wcn36xx_ipv6_addr_change(struct ieee80211_hw *hw,
+				     struct ieee80211_vif *vif,
+				     struct inet6_dev *idev)
+{
+	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
+	struct inet6_ifaddr *ifa;
+	int idx = 0;
+
+	memset(vif_priv->tentative_addrs, 0, sizeof(vif_priv->tentative_addrs));
+
+	read_lock_bh(&idev->lock);
+	list_for_each_entry(ifa, &idev->addr_list, if_list) {
+		vif_priv->target_ipv6_addrs[idx] = ifa->addr;
+		if (ifa->flags & IFA_F_TENTATIVE)
+			__set_bit(idx, vif_priv->tentative_addrs);
+		idx++;
+		if (idx >= WCN36XX_HAL_IPV6_OFFLOAD_ADDR_MAX)
+			break;
+		wcn36xx_dbg(WCN36XX_DBG_MAC, "%pI6 %s\n", &ifa->addr,
+			    (ifa->flags & IFA_F_TENTATIVE) ? "tentative" : NULL);
+	}
+	read_unlock_bh(&idev->lock);
+
+	vif_priv->num_target_ipv6_addrs = idx;
+}
+#endif
+
 static const struct ieee80211_ops wcn36xx_ops = {
 	.start			= wcn36xx_start,
 	.stop			= wcn36xx_stop,
@@ -1184,6 +1267,7 @@ static const struct ieee80211_ops wcn36xx_ops = {
 #ifdef CONFIG_PM
 	.suspend		= wcn36xx_suspend,
 	.resume			= wcn36xx_resume,
+	.set_rekey_data		= wcn36xx_set_rekey_data,
 #endif
 	.config			= wcn36xx_config,
 	.prepare_multicast	= wcn36xx_prepare_multicast,
@@ -1199,6 +1283,9 @@ static const struct ieee80211_ops wcn36xx_ops = {
 	.sta_add		= wcn36xx_sta_add,
 	.sta_remove		= wcn36xx_sta_remove,
 	.ampdu_action		= wcn36xx_ampdu_action,
+#if IS_ENABLED(CONFIG_IPV6)
+	.ipv6_addr_change	= wcn36xx_ipv6_addr_change,
+#endif
 
 	CFG80211_TESTMODE_CMD(wcn36xx_tm_cmd)
 };
@@ -1401,6 +1488,12 @@ static int wcn36xx_probe(struct platform_device *pdev)
 	mutex_init(&wcn->hal_mutex);
 	mutex_init(&wcn->scan_lock);
 
+	wcn->hal_buf = devm_kmalloc(wcn->dev, WCN36XX_HAL_BUF_SIZE, GFP_KERNEL);
+	if (!wcn->hal_buf) {
+		ret = -ENOMEM;
+		goto out_wq;
+	}
+
 	ret = dma_set_mask_and_coherent(wcn->dev, DMA_BIT_MASK(32));
 	if (ret < 0) {
 		wcn36xx_err("failed to set DMA mask: %d\n", ret);
diff --git a/drivers/net/wireless/ath/wcn36xx/smd.c b/drivers/net/wireless/ath/wcn36xx/smd.c
index d0c3a1557e8d..cf8e52cbdd9b 100644
--- a/drivers/net/wireless/ath/wcn36xx/smd.c
+++ b/drivers/net/wireless/ath/wcn36xx/smd.c
@@ -2756,6 +2756,269 @@ out:
 	return ret;
 }
 
+int wcn36xx_smd_arp_offload(struct wcn36xx *wcn, struct ieee80211_vif *vif,
+			    bool enable)
+{
+	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
+	struct wcn36xx_hal_host_offload_req_msg msg_body;
+	int ret;
+
+	mutex_lock(&wcn->hal_mutex);
+
+	INIT_HAL_MSG(msg_body, WCN36XX_HAL_HOST_OFFLOAD_REQ);
+	msg_body.host_offload_params.offload_type =
+		WCN36XX_HAL_IPV4_ARP_REPLY_OFFLOAD;
+	if (enable) {
+		msg_body.host_offload_params.enable =
+			WCN36XX_HAL_OFFLOAD_ARP_AND_BCAST_FILTER_ENABLE;
+		memcpy(&msg_body.host_offload_params.u,
+		       &vif->bss_conf.arp_addr_list[0], sizeof(__be32));
+	}
+	msg_body.ns_offload_params.bss_index = vif_priv->bss_index;
+
+	PREPARE_HAL_BUF(wcn->hal_buf, msg_body);
+
+	ret = wcn36xx_smd_send_and_wait(wcn, msg_body.header.len);
+	if (ret) {
+		wcn36xx_err("Sending host_offload_arp failed\n");
+		goto out;
+	}
+	ret = wcn36xx_smd_rsp_status_check(wcn->hal_buf, wcn->hal_rsp_len);
+	if (ret) {
+		wcn36xx_err("host_offload_arp failed err=%d\n", ret);
+		goto out;
+	}
+out:
+	mutex_unlock(&wcn->hal_mutex);
+	return ret;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+int wcn36xx_smd_ipv6_ns_offload(struct wcn36xx *wcn, struct ieee80211_vif *vif,
+				bool enable)
+{
+	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
+	struct wcn36xx_hal_host_offload_req_msg msg_body;
+	struct wcn36xx_hal_ns_offload_params *ns_params;
+	struct wcn36xx_hal_host_offload_req *ho_params;
+	int ret;
+
+	mutex_lock(&wcn->hal_mutex);
+
+	INIT_HAL_MSG(msg_body, WCN36XX_HAL_HOST_OFFLOAD_REQ);
+	ho_params = &msg_body.host_offload_params;
+	ns_params = &msg_body.ns_offload_params;
+
+	ho_params->offload_type = WCN36XX_HAL_IPV6_NS_OFFLOAD;
+	if (enable) {
+		ho_params->enable =
+			WCN36XX_HAL_OFFLOAD_NS_AND_MCAST_FILTER_ENABLE;
+		if (vif_priv->num_target_ipv6_addrs) {
+			memcpy(&ho_params->u,
+			       &vif_priv->target_ipv6_addrs[0].in6_u,
+			       sizeof(struct in6_addr));
+			memcpy(&ns_params->target_ipv6_addr1,
+			       &vif_priv->target_ipv6_addrs[0].in6_u,
+			       sizeof(struct in6_addr));
+			ns_params->target_ipv6_addr1_valid = 1;
+		}
+		if (vif_priv->num_target_ipv6_addrs > 1) {
+			memcpy(&ns_params->target_ipv6_addr2,
+			       &vif_priv->target_ipv6_addrs[1].in6_u,
+			       sizeof(struct in6_addr));
+			ns_params->target_ipv6_addr2_valid = 1;
+		}
+	}
+	memcpy(&ns_params->self_addr, vif->addr, ETH_ALEN);
+	ns_params->bss_index = vif_priv->bss_index;
+
+	PREPARE_HAL_BUF(wcn->hal_buf, msg_body);
+
+	ret = wcn36xx_smd_send_and_wait(wcn, msg_body.header.len);
+	if (ret) {
+		wcn36xx_err("Sending host_offload_arp failed\n");
+		goto out;
+	}
+	ret = wcn36xx_smd_rsp_status_check(wcn->hal_buf, wcn->hal_rsp_len);
+	if (ret) {
+		wcn36xx_err("host_offload_arp failed err=%d\n", ret);
+		goto out;
+	}
+out:
+	mutex_unlock(&wcn->hal_mutex);
+	return ret;
+}
+#else
+int wcn36xx_smd_ipv6_ns_offload(struct wcn36xx *wcn, struct ieee80211_vif *vif,
+				bool enable)
+{
+	return 0;
+}
+#endif
+
+int wcn36xx_smd_gtk_offload(struct wcn36xx *wcn, struct ieee80211_vif *vif,
+			    bool enable)
+{
+	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
+	struct wcn36xx_hal_gtk_offload_req_msg msg_body;
+	int ret;
+
+	mutex_lock(&wcn->hal_mutex);
+
+	INIT_HAL_MSG(msg_body, WCN36XX_HAL_GTK_OFFLOAD_REQ);
+
+	if (enable) {
+		memcpy(&msg_body.kek, vif_priv->rekey_data.kek, NL80211_KEK_LEN);
+		memcpy(&msg_body.kck, vif_priv->rekey_data.kck, NL80211_KCK_LEN);
+		msg_body.key_replay_counter =
+			le64_to_cpu(vif_priv->rekey_data.replay_ctr);
+		msg_body.bss_index = vif_priv->bss_index;
+	} else {
+		msg_body.flags = WCN36XX_HAL_GTK_OFFLOAD_FLAGS_DISABLE;
+	}
+
+	PREPARE_HAL_BUF(wcn->hal_buf, msg_body);
+
+	ret = wcn36xx_smd_send_and_wait(wcn, msg_body.header.len);
+	if (ret) {
+		wcn36xx_err("Sending host_offload_arp failed\n");
+		goto out;
+	}
+	ret = wcn36xx_smd_rsp_status_check(wcn->hal_buf, wcn->hal_rsp_len);
+	if (ret) {
+		wcn36xx_err("host_offload_arp failed err=%d\n", ret);
+		goto out;
+	}
+out:
+	mutex_unlock(&wcn->hal_mutex);
+	return ret;
+}
+
+static int wcn36xx_smd_gtk_offload_get_info_rsp(struct wcn36xx *wcn,
+						struct ieee80211_vif *vif)
+{
+	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
+	struct wcn36xx_hal_gtk_offload_get_info_rsp_msg *rsp;
+	__be64 replay_ctr;
+
+	if (wcn36xx_smd_rsp_status_check(wcn->hal_buf, wcn->hal_rsp_len))
+		return -EIO;
+
+	rsp = (struct wcn36xx_hal_gtk_offload_get_info_rsp_msg *)wcn->hal_buf;
+
+	if (rsp->bss_index != vif_priv->bss_index) {
+		wcn36xx_err("gtk_offload_info invalid response bss index %d\n",
+			    rsp->bss_index);
+		return -ENOENT;
+	}
+
+	if (vif_priv->rekey_data.replay_ctr != cpu_to_le64(rsp->key_replay_counter)) {
+		replay_ctr = cpu_to_be64(rsp->key_replay_counter);
+		vif_priv->rekey_data.replay_ctr =
+			cpu_to_le64(rsp->key_replay_counter);
+		ieee80211_gtk_rekey_notify(vif, vif->bss_conf.bssid,
+					   (void *)&replay_ctr, GFP_KERNEL);
+		 wcn36xx_dbg(WCN36XX_DBG_HAL,
+			     "GTK replay counter increment %llu\n",
+			     rsp->key_replay_counter);
+	}
+
+	wcn36xx_dbg(WCN36XX_DBG_HAL,
+		    "gtk offload info status %d last_rekey_status %d "
+		    "replay_counter %llu total_rekey_count %d gtk_rekey_count %d "
+		    "igtk_rekey_count %d bss_index %d\n",
+		    rsp->status, rsp->last_rekey_status,
+		    rsp->key_replay_counter, rsp->total_rekey_count,
+		    rsp->gtk_rekey_count, rsp->igtk_rekey_count,
+		    rsp->bss_index);
+
+	return 0;
+}
+
+int wcn36xx_smd_gtk_offload_get_info(struct wcn36xx *wcn,
+				     struct ieee80211_vif *vif)
+{
+	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
+	struct wcn36xx_hal_gtk_offload_get_info_req_msg msg_body;
+	int ret;
+
+	mutex_lock(&wcn->hal_mutex);
+
+	INIT_HAL_MSG(msg_body, WCN36XX_HAL_GTK_OFFLOAD_GETINFO_REQ);
+
+	msg_body.bss_index = vif_priv->bss_index;
+
+	PREPARE_HAL_BUF(wcn->hal_buf, msg_body);
+
+	ret = wcn36xx_smd_send_and_wait(wcn, msg_body.header.len);
+	if (ret) {
+		wcn36xx_err("Sending gtk_offload_get_info failed\n");
+		goto out;
+	}
+	ret = wcn36xx_smd_rsp_status_check(wcn->hal_buf, wcn->hal_rsp_len);
+	if (ret) {
+		wcn36xx_err("gtk_offload_get_info failed err=%d\n", ret);
+		goto out;
+	}
+	ret = wcn36xx_smd_gtk_offload_get_info_rsp(wcn, vif);
+out:
+	mutex_unlock(&wcn->hal_mutex);
+	return ret;
+}
+
+int wcn36xx_smd_wlan_host_suspend_ind(struct wcn36xx *wcn)
+{
+	struct wcn36xx_hal_wlan_host_suspend_ind_msg msg_body;
+	int ret;
+
+	mutex_lock(&wcn->hal_mutex);
+
+	INIT_HAL_MSG(msg_body, WCN36XX_HAL_HOST_SUSPEND_IND);
+	msg_body.configured_mcst_bcst_filter_setting = 0;
+	msg_body.active_session_count = 1;
+	PREPARE_HAL_BUF(wcn->hal_buf, msg_body);
+
+	ret = rpmsg_send(wcn->smd_channel, wcn->hal_buf, msg_body.header.len);
+
+	mutex_unlock(&wcn->hal_mutex);
+
+	return ret;
+}
+
+int wcn36xx_smd_host_resume(struct wcn36xx *wcn)
+{
+	struct wcn36xx_hal_wlan_host_resume_req_msg msg_body;
+	struct wcn36xx_hal_host_resume_rsp_msg *rsp;
+	int ret;
+
+	mutex_lock(&wcn->hal_mutex);
+
+	INIT_HAL_MSG(msg_body, WCN36XX_HAL_HOST_RESUME_REQ);
+	msg_body.configured_mcst_bcst_filter_setting = 0;
+
+	PREPARE_HAL_BUF(wcn->hal_buf, msg_body);
+
+	ret = wcn36xx_smd_send_and_wait(wcn, msg_body.header.len);
+	if (ret) {
+		wcn36xx_err("Sending wlan_host_resume failed\n");
+		goto out;
+	}
+	ret = wcn36xx_smd_rsp_status_check(wcn->hal_buf, wcn->hal_rsp_len);
+	if (ret) {
+		wcn36xx_err("wlan_host_resume err=%d\n", ret);
+		goto out;
+	}
+
+	rsp = (struct wcn36xx_hal_host_resume_rsp_msg *)wcn->hal_buf;
+	if (rsp->status)
+		wcn36xx_warn("wlan_host_resume status=%d\n", rsp->status);
+
+out:
+	mutex_unlock(&wcn->hal_mutex);
+
+	return ret;
+}
+
 int wcn36xx_smd_rsp_process(struct rpmsg_device *rpdev,
 			    void *buf, int len, void *priv, u32 addr)
 {
@@ -2804,6 +3067,10 @@ int wcn36xx_smd_rsp_process(struct rpmsg_device *rpdev,
 	case WCN36XX_HAL_8023_MULTICAST_LIST_RSP:
 	case WCN36XX_HAL_START_SCAN_OFFLOAD_RSP:
 	case WCN36XX_HAL_STOP_SCAN_OFFLOAD_RSP:
+	case WCN36XX_HAL_HOST_OFFLOAD_RSP:
+	case WCN36XX_HAL_GTK_OFFLOAD_RSP:
+	case WCN36XX_HAL_GTK_OFFLOAD_GETINFO_RSP:
+	case WCN36XX_HAL_HOST_RESUME_RSP:
 		memcpy(wcn->hal_buf, buf, len);
 		wcn->hal_rsp_len = len;
 		complete(&wcn->hal_rsp_compl);
diff --git a/drivers/net/wireless/ath/wcn36xx/smd.h b/drivers/net/wireless/ath/wcn36xx/smd.h
index 462860572e1f..d8bded03945d 100644
--- a/drivers/net/wireless/ath/wcn36xx/smd.h
+++ b/drivers/net/wireless/ath/wcn36xx/smd.h
@@ -146,4 +146,21 @@ int wcn36xx_smd_rsp_process(struct rpmsg_device *rpdev,
 int wcn36xx_smd_set_mc_list(struct wcn36xx *wcn,
 			    struct ieee80211_vif *vif,
 			    struct wcn36xx_hal_rcv_flt_mc_addr_list_type *fp);
+
+int wcn36xx_smd_arp_offload(struct wcn36xx *wcn, struct ieee80211_vif *vif,
+			    bool enable);
+
+int wcn36xx_smd_ipv6_ns_offload(struct wcn36xx *wcn, struct ieee80211_vif *vif,
+				bool enable);
+
+int wcn36xx_smd_gtk_offload(struct wcn36xx *wcn, struct ieee80211_vif *vif,
+			    bool enable);
+
+int wcn36xx_smd_gtk_offload_get_info(struct wcn36xx *wcn,
+				     struct ieee80211_vif *vif);
+
+int wcn36xx_smd_wlan_host_suspend_ind(struct wcn36xx *wcn);
+
+int wcn36xx_smd_host_resume(struct wcn36xx *wcn);
+
 #endif	/* _SMD_H_ */
diff --git a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
index 71fa9992b118..6121d8a5641a 100644
--- a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
+++ b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
@@ -18,6 +18,7 @@
 #define _WCN36XX_H_
 
 #include <linux/completion.h>
+#include <linux/in6.h>
 #include <linux/printk.h>
 #include <linux/spinlock.h>
 #include <net/mac80211.h>
@@ -136,6 +137,19 @@ struct wcn36xx_vif {
 	u8 self_dpu_desc_index;
 	u8 self_ucast_dpu_sign;
 
+#if IS_ENABLED(CONFIG_IPV6)
+	/* IPv6 addresses for WoWLAN */
+	struct in6_addr target_ipv6_addrs[WCN36XX_HAL_IPV6_OFFLOAD_ADDR_MAX];
+	unsigned long tentative_addrs[BITS_TO_LONGS(WCN36XX_HAL_IPV6_OFFLOAD_ADDR_MAX)];
+	int num_target_ipv6_addrs;
+#endif
+	/* WoWLAN GTK rekey data */
+	struct {
+		u8 kck[NL80211_KCK_LEN], kek[NL80211_KEK_LEN];
+		__le64 replay_ctr;
+		bool valid;
+	} rekey_data;
+
 	struct list_head sta_list;
 };
 
diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c
index 6746fd206d2a..1ff2679963f0 100644
--- a/drivers/net/wireless/ath/wil6210/cfg80211.c
+++ b/drivers/net/wireless/ath/wil6210/cfg80211.c
@@ -2842,9 +2842,7 @@ void wil_p2p_wdev_free(struct wil6210_priv *wil)
 	wil->radio_wdev = wil->main_ndev->ieee80211_ptr;
 	mutex_unlock(&wil->vif_mutex);
 	if (p2p_wdev) {
-		wiphy_lock(wil->wiphy);
 		cfg80211_unregister_wdev(p2p_wdev);
-		wiphy_unlock(wil->wiphy);
 		kfree(p2p_wdev);
 	}
 }
diff --git a/drivers/net/wireless/ath/wil6210/interrupt.c b/drivers/net/wireless/ath/wil6210/interrupt.c
index d13d081fdcc6..67172385a5d6 100644
--- a/drivers/net/wireless/ath/wil6210/interrupt.c
+++ b/drivers/net/wireless/ath/wil6210/interrupt.c
@@ -9,7 +9,7 @@
 #include "wil6210.h"
 #include "trace.h"
 
-/**
+/*
  * Theory of operation:
  *
  * There is ISR pseudo-cause register,
diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index 02ad44997e87..2dc8406736f4 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -224,7 +224,7 @@ struct auth_no_hdr {
 u8 led_polarity = LED_POLARITY_LOW_ACTIVE;
 
 /**
- * return AHB address for given firmware internal (linker) address
+ * wmi_addr_remap - return AHB address for given firmware internal (linker) address
  * @x: internal address
  * If address have no valid AHB mapping, return 0
  */
@@ -242,7 +242,7 @@ static u32 wmi_addr_remap(u32 x)
 }
 
 /**
- * find fw_mapping entry by section name
+ * wil_find_fw_mapping - find fw_mapping entry by section name
  * @section: section name
  *
  * Return pointer to section or NULL if not found
@@ -260,7 +260,7 @@ struct fw_map *wil_find_fw_mapping(const char *section)
 }
 
 /**
- * Check address validity for WMI buffer; remap if needed
+ * wmi_buffer_block - Check address validity for WMI buffer; remap if needed
  * @wil: driver data
  * @ptr_: internal (linker) fw/ucode address
  * @size: if non zero, validate the block does not
diff --git a/drivers/net/wireless/broadcom/b43/phy_n.c b/drivers/net/wireless/broadcom/b43/phy_n.c
index 665b737fbb0d..cf3ccf4ddfe7 100644
--- a/drivers/net/wireless/broadcom/b43/phy_n.c
+++ b/drivers/net/wireless/broadcom/b43/phy_n.c
@@ -4592,58 +4592,11 @@ static void b43_nphy_spur_workaround(struct b43_wldev *dev)
 {
 	struct b43_phy_n *nphy = dev->phy.n;
 
-	u8 channel = dev->phy.channel;
-	int tone[2] = { 57, 58 };
-	u32 noise[2] = { 0x3FF, 0x3FF };
-
 	B43_WARN_ON(dev->phy.rev < 3);
 
 	if (nphy->hang_avoid)
 		b43_nphy_stay_in_carrier_search(dev, 1);
 
-	if (nphy->gband_spurwar_en) {
-		/* TODO: N PHY Adjust Analog Pfbw (7) */
-		if (channel == 11 && b43_is_40mhz(dev)) {
-			; /* TODO: N PHY Adjust Min Noise Var(2, tone, noise)*/
-		} else {
-			; /* TODO: N PHY Adjust Min Noise Var(0, NULL, NULL)*/
-		}
-		/* TODO: N PHY Adjust CRS Min Power (0x1E) */
-	}
-
-	if (nphy->aband_spurwar_en) {
-		if (channel == 54) {
-			tone[0] = 0x20;
-			noise[0] = 0x25F;
-		} else if (channel == 38 || channel == 102 || channel == 118) {
-			if (0 /* FIXME */) {
-				tone[0] = 0x20;
-				noise[0] = 0x21F;
-			} else {
-				tone[0] = 0;
-				noise[0] = 0;
-			}
-		} else if (channel == 134) {
-			tone[0] = 0x20;
-			noise[0] = 0x21F;
-		} else if (channel == 151) {
-			tone[0] = 0x10;
-			noise[0] = 0x23F;
-		} else if (channel == 153 || channel == 161) {
-			tone[0] = 0x30;
-			noise[0] = 0x23F;
-		} else {
-			tone[0] = 0;
-			noise[0] = 0;
-		}
-
-		if (!tone[0] && !noise[0]) {
-			; /* TODO: N PHY Adjust Min Noise Var(1, tone, noise)*/
-		} else {
-			; /* TODO: N PHY Adjust Min Noise Var(0, NULL, NULL)*/
-		}
-	}
-
 	if (nphy->hang_avoid)
 		b43_nphy_stay_in_carrier_search(dev, 0);
 }
diff --git a/drivers/net/wireless/broadcom/b43legacy/dma.c b/drivers/net/wireless/broadcom/b43legacy/dma.c
index 7e2f70c4207c..6869f2bf1bae 100644
--- a/drivers/net/wireless/broadcom/b43legacy/dma.c
+++ b/drivers/net/wireless/broadcom/b43legacy/dma.c
@@ -213,19 +213,6 @@ return dev->dma.tx_ring1;
 	return ring;
 }
 
-/* Bcm4301-ring to mac80211-queue mapping */
-static inline int txring_to_priority(struct b43legacy_dmaring *ring)
-{
-	static const u8 idx_to_prio[] =
-		{ 3, 2, 1, 0, 4, 5, };
-
-/*FIXME: have only one queue, for now */
-return 0;
-
-	return idx_to_prio[ring->index];
-}
-
-
 static u16 b43legacy_dmacontroller_base(enum b43legacy_dmatype type,
 					int controller_idx)
 {
diff --git a/drivers/net/wireless/broadcom/b43legacy/main.c b/drivers/net/wireless/broadcom/b43legacy/main.c
index f64ebff68308..eec3af9c3745 100644
--- a/drivers/net/wireless/broadcom/b43legacy/main.c
+++ b/drivers/net/wireless/broadcom/b43legacy/main.c
@@ -391,7 +391,7 @@ void b43legacy_tsf_read(struct b43legacy_wldev *dev, u64 *tsf)
 	 * registers, we should take care of register overflows.
 	 * In theory, the whole tsf read process should be atomic.
 	 * We try to be atomic here, by restaring the read process,
-	 * if any of the high registers changed (overflew).
+	 * if any of the high registers changed (overflowed).
 	 */
 	if (dev->dev->id.revision >= 3) {
 		u32 low;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index f4405d7861b6..65fb038d88e7 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -2767,8 +2767,9 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
 	struct brcmf_sta_info_le sta_info_le;
 	u32 sta_flags;
 	u32 is_tdls_peer;
-	s32 total_rssi;
-	s32 count_rssi;
+	s32 total_rssi_avg = 0;
+	s32 total_rssi = 0;
+	s32 count_rssi = 0;
 	int rssi;
 	u32 i;
 
@@ -2834,25 +2835,27 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
 			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES);
 			sinfo->rx_bytes = le64_to_cpu(sta_info_le.rx_tot_bytes);
 		}
-		total_rssi = 0;
-		count_rssi = 0;
 		for (i = 0; i < BRCMF_ANT_MAX; i++) {
-			if (sta_info_le.rssi[i]) {
-				sinfo->chain_signal_avg[count_rssi] =
-					sta_info_le.rssi[i];
-				sinfo->chain_signal[count_rssi] =
-					sta_info_le.rssi[i];
-				total_rssi += sta_info_le.rssi[i];
-				count_rssi++;
-			}
+			if (sta_info_le.rssi[i] == 0 ||
+			    sta_info_le.rx_lastpkt_rssi[i] == 0)
+				continue;
+			sinfo->chains |= BIT(count_rssi);
+			sinfo->chain_signal[count_rssi] =
+				sta_info_le.rx_lastpkt_rssi[i];
+			sinfo->chain_signal_avg[count_rssi] =
+				sta_info_le.rssi[i];
+			total_rssi += sta_info_le.rx_lastpkt_rssi[i];
+			total_rssi_avg += sta_info_le.rssi[i];
+			count_rssi++;
 		}
 		if (count_rssi) {
-			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL);
-			sinfo->chains = count_rssi;
-
 			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
-			total_rssi /= count_rssi;
-			sinfo->signal = total_rssi;
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL);
+			sinfo->filled |=
+				BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL_AVG);
+			sinfo->signal = total_rssi / count_rssi;
+			sinfo->signal_avg = total_rssi_avg / count_rssi;
 		} else if (test_bit(BRCMF_VIF_STATUS_CONNECTED,
 			&ifp->vif->sme_state)) {
 			memset(&scb_val, 0, sizeof(scb_val));
@@ -7442,18 +7445,23 @@ static s32 brcmf_translate_country_code(struct brcmf_pub *drvr, char alpha2[2],
 	s32 found_index;
 	int i;
 
-	country_codes = drvr->settings->country_codes;
-	if (!country_codes) {
-		brcmf_dbg(TRACE, "No country codes configured for device\n");
-		return -EINVAL;
-	}
-
 	if ((alpha2[0] == ccreq->country_abbrev[0]) &&
 	    (alpha2[1] == ccreq->country_abbrev[1])) {
 		brcmf_dbg(TRACE, "Country code already set\n");
 		return -EAGAIN;
 	}
 
+	country_codes = drvr->settings->country_codes;
+	if (!country_codes) {
+		brcmf_dbg(TRACE, "No country codes configured for device, using ISO3166 code and 0 rev\n");
+		memset(ccreq, 0, sizeof(*ccreq));
+		ccreq->country_abbrev[0] = alpha2[0];
+		ccreq->country_abbrev[1] = alpha2[1];
+		ccreq->ccode[0] = alpha2[0];
+		ccreq->ccode[1] = alpha2[1];
+		return 0;
+	}
+
 	found_index = -1;
 	for (i = 0; i < country_codes->table_size; i++) {
 		cc = &country_codes->table[i];
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.h
index 46c66415b4a6..e290dec9c53d 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.h
@@ -32,6 +32,13 @@ static const char BRCM_ ## fw_name ## _FIRMWARE_BASENAME[] = \
 	BRCMF_FW_DEFAULT_PATH fw_base; \
 MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH fw_base ".bin")
 
+/* Firmware and Country Local Matrix files */
+#define BRCMF_FW_CLM_DEF(fw_name, fw_base) \
+static const char BRCM_ ## fw_name ## _FIRMWARE_BASENAME[] = \
+	BRCMF_FW_DEFAULT_PATH fw_base; \
+MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH fw_base ".bin"); \
+MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH fw_base ".clm_blob")
+
 #define BRCMF_FW_ENTRY(chipid, mask, name) \
 	{ chipid, mask, BRCM_ ## name ## _FIRMWARE_BASENAME }
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
index 34cd8a7401fe..9ac0d8c73d5a 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
@@ -2037,7 +2037,7 @@ static void brcmf_p2p_get_current_chanspec(struct brcmf_p2p_info *p2p,
 }
 
 /**
- * Change a P2P Role.
+ * brcmf_p2p_ifchange - Change a P2P Role.
  * @cfg: driver private data for cfg80211 interface.
  * @if_type: interface type.
  * Returns 0 if success.
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
index 143a705b5cb3..c49dd0c36ae4 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
@@ -48,8 +48,8 @@ enum brcmf_pcie_state {
 BRCMF_FW_DEF(43602, "brcmfmac43602-pcie");
 BRCMF_FW_DEF(4350, "brcmfmac4350-pcie");
 BRCMF_FW_DEF(4350C, "brcmfmac4350c2-pcie");
-BRCMF_FW_DEF(4356, "brcmfmac4356-pcie");
-BRCMF_FW_DEF(43570, "brcmfmac43570-pcie");
+BRCMF_FW_CLM_DEF(4356, "brcmfmac4356-pcie");
+BRCMF_FW_CLM_DEF(43570, "brcmfmac43570-pcie");
 BRCMF_FW_DEF(4358, "brcmfmac4358-pcie");
 BRCMF_FW_DEF(4359, "brcmfmac4359-pcie");
 BRCMF_FW_DEF(4364, "brcmfmac4364-pcie");
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index 16ed325795a8..97ee9e2e2e35 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -616,18 +616,18 @@ BRCMF_FW_DEF(43362, "brcmfmac43362-sdio");
 BRCMF_FW_DEF(4339, "brcmfmac4339-sdio");
 BRCMF_FW_DEF(43430A0, "brcmfmac43430a0-sdio");
 /* Note the names are not postfixed with a1 for backward compatibility */
-BRCMF_FW_DEF(43430A1, "brcmfmac43430-sdio");
-BRCMF_FW_DEF(43455, "brcmfmac43455-sdio");
+BRCMF_FW_CLM_DEF(43430A1, "brcmfmac43430-sdio");
+BRCMF_FW_CLM_DEF(43455, "brcmfmac43455-sdio");
 BRCMF_FW_DEF(43456, "brcmfmac43456-sdio");
-BRCMF_FW_DEF(4354, "brcmfmac4354-sdio");
-BRCMF_FW_DEF(4356, "brcmfmac4356-sdio");
+BRCMF_FW_CLM_DEF(4354, "brcmfmac4354-sdio");
+BRCMF_FW_CLM_DEF(4356, "brcmfmac4356-sdio");
 BRCMF_FW_DEF(4359, "brcmfmac4359-sdio");
-BRCMF_FW_DEF(4373, "brcmfmac4373-sdio");
-BRCMF_FW_DEF(43012, "brcmfmac43012-sdio");
+BRCMF_FW_CLM_DEF(4373, "brcmfmac4373-sdio");
+BRCMF_FW_CLM_DEF(43012, "brcmfmac43012-sdio");
 
 /* firmware config files */
-MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcm/brcmfmac*-sdio.*.txt");
-MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcm/brcmfmac*-pcie.*.txt");
+MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcmfmac*-sdio.*.txt");
+MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcmfmac*-pcie.*.txt");
 
 static const struct brcmf_firmware_mapping brcmf_sdio_fwnames[] = {
 	BRCMF_FW_ENTRY(BRCM_CC_43143_CHIP_ID, 0xFFFFFFFF, 43143),
@@ -1291,7 +1291,7 @@ static void brcmf_sdio_free_glom(struct brcmf_sdio *bus)
 	}
 }
 
-/**
+/*
  * brcmfmac sdio bus specific header
  * This is the lowest layer header wrapped on the packets transmitted between
  * host and WiFi dongle which contains information needed for SDIO core and
@@ -4162,7 +4162,6 @@ static int brcmf_sdio_bus_reset(struct device *dev)
 	if (ret) {
 		brcmf_err("Failed to probe after sdio device reset: ret %d\n",
 			  ret);
-		brcmf_sdiod_remove(sdiodev);
 	}
 
 	return ret;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.c
index 53365977bfd6..2084b506a450 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.c
@@ -531,9 +531,6 @@ void ai_detach(struct si_pub *sih)
 
 	sii = container_of(sih, struct si_info, pub);
 
-	if (sii == NULL)
-		return;
-
 	kfree(sii);
 }
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
index 39f3af2d0439..eadac0f5590f 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
@@ -1220,6 +1220,7 @@ static int brcms_bcma_probe(struct bcma_device *pdev)
 {
 	struct brcms_info *wl;
 	struct ieee80211_hw *hw;
+	int ret;
 
 	dev_info(&pdev->dev, "mfg %x core %x rev %d class %d irq %d\n",
 		 pdev->id.manuf, pdev->id.id, pdev->id.rev, pdev->id.class,
@@ -1244,11 +1245,16 @@ static int brcms_bcma_probe(struct bcma_device *pdev)
 	wl = brcms_attach(pdev);
 	if (!wl) {
 		pr_err("%s: brcms_attach failed!\n", __func__);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto err_free_ieee80211;
 	}
 	brcms_led_register(wl);
 
 	return 0;
+
+err_free_ieee80211:
+	ieee80211_free_hw(hw);
+	return ret;
 }
 
 static int brcms_suspend(struct bcma_device *pdev)
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
index 763e0ec583d7..26de1bd7fee9 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
@@ -6607,7 +6607,8 @@ brcms_c_d11hdrs_mac80211(struct brcms_c_info *wlc, struct ieee80211_hw *hw,
 			rts->frame_control = cpu_to_le16(IEEE80211_FTYPE_CTL |
 							 IEEE80211_STYPE_RTS);
 
-			memcpy(&rts->ra, &h->addr1, 2 * ETH_ALEN);
+			memcpy(&rts->ra, &h->addr1, ETH_ALEN);
+			memcpy(&rts->ta, &h->addr2, ETH_ALEN);
 		}
 
 		/* mainrate
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/stf.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/stf.h
index aa4ab53bf634..af86c7fc5112 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/stf.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/stf.h
@@ -29,7 +29,6 @@ void brcms_c_stf_ss_update(struct brcms_c_info *wlc, struct brcms_band *band);
 void brcms_c_stf_phy_txant_upd(struct brcms_c_info *wlc);
 int brcms_c_stf_txchain_set(struct brcms_c_info *wlc, s32 int_val, bool force);
 bool brcms_c_stf_stbc_rx_set(struct brcms_c_info *wlc, s32 int_val);
-void brcms_c_stf_phy_txant_upd(struct brcms_c_info *wlc);
 void brcms_c_stf_phy_chain_calc(struct brcms_c_info *wlc);
 u16 brcms_c_stf_phytxchain_sel(struct brcms_c_info *wlc, u32 rspec);
 u16 brcms_c_stf_d11hdrs_phyctl_txant(struct brcms_c_info *wlc, u32 rspec);
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.c b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
index 23fbddd0c1f8..47eb89b773cf 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
@@ -5356,7 +5356,7 @@ struct ipw2100_wep_key {
 #define WEP_STR_128(x) x[0],x[1],x[2],x[3],x[4],x[5],x[6],x[7],x[8],x[9],x[10]
 
 /**
- * Set a the wep key
+ * ipw2100_set_key() - Set a the wep key
  *
  * @priv: struct to work on
  * @idx: index of the key we want to set
diff --git a/drivers/net/wireless/marvell/libertas/main.c b/drivers/net/wireless/marvell/libertas/main.c
index ee4cf3437e28..64fc5e410864 100644
--- a/drivers/net/wireless/marvell/libertas/main.c
+++ b/drivers/net/wireless/marvell/libertas/main.c
@@ -941,7 +941,7 @@ struct lbs_private *lbs_add_card(void *card, struct device *dmdev)
 	wdev->netdev = dev;
 	priv->dev = dev;
 
- 	dev->netdev_ops = &lbs_netdev_ops;
+	dev->netdev_ops = &lbs_netdev_ops;
 	dev->watchdog_timeo = 5 * HZ;
 	dev->ethtool_ops = &lbs_ethtool_ops;
 	dev->flags |= IFF_BROADCAST | IFF_MULTICAST;
diff --git a/drivers/net/wireless/marvell/libertas/mesh.c b/drivers/net/wireless/marvell/libertas/mesh.c
index c68814841583..6cbba84989b8 100644
--- a/drivers/net/wireless/marvell/libertas/mesh.c
+++ b/drivers/net/wireless/marvell/libertas/mesh.c
@@ -151,13 +151,13 @@ static uint16_t lbs_mesh_get_channel(struct lbs_private *priv)
  */
 
 /**
- * lbs_anycast_get - Get function for sysfs attribute anycast_mask
+ * anycast_mask_show - Get function for sysfs attribute anycast_mask
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer where data will be returned
  */
-static ssize_t lbs_anycast_get(struct device *dev,
-		struct device_attribute *attr, char * buf)
+static ssize_t anycast_mask_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
 {
 	struct lbs_private *priv = to_net_dev(dev)->ml_priv;
 	struct cmd_ds_mesh_access mesh_access;
@@ -173,14 +173,15 @@ static ssize_t lbs_anycast_get(struct device *dev,
 }
 
 /**
- * lbs_anycast_set - Set function for sysfs attribute anycast_mask
+ * anycast_mask_store - Set function for sysfs attribute anycast_mask
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer that contains new attribute value
  * @count: size of buffer
  */
-static ssize_t lbs_anycast_set(struct device *dev,
-		struct device_attribute *attr, const char * buf, size_t count)
+static ssize_t anycast_mask_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
 {
 	struct lbs_private *priv = to_net_dev(dev)->ml_priv;
 	struct cmd_ds_mesh_access mesh_access;
@@ -199,13 +200,13 @@ static ssize_t lbs_anycast_set(struct device *dev,
 }
 
 /**
- * lbs_prb_rsp_limit_get - Get function for sysfs attribute prb_rsp_limit
+ * prb_rsp_limit_show - Get function for sysfs attribute prb_rsp_limit
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer where data will be returned
  */
-static ssize_t lbs_prb_rsp_limit_get(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t prb_rsp_limit_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
 {
 	struct lbs_private *priv = to_net_dev(dev)->ml_priv;
 	struct cmd_ds_mesh_access mesh_access;
@@ -225,14 +226,15 @@ static ssize_t lbs_prb_rsp_limit_get(struct device *dev,
 }
 
 /**
- * lbs_prb_rsp_limit_set - Set function for sysfs attribute prb_rsp_limit
+ * prb_rsp_limit_store - Set function for sysfs attribute prb_rsp_limit
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer that contains new attribute value
  * @count: size of buffer
  */
-static ssize_t lbs_prb_rsp_limit_set(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+static ssize_t prb_rsp_limit_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t count)
 {
 	struct lbs_private *priv = to_net_dev(dev)->ml_priv;
 	struct cmd_ds_mesh_access mesh_access;
@@ -259,27 +261,28 @@ static ssize_t lbs_prb_rsp_limit_set(struct device *dev,
 }
 
 /**
- * lbs_mesh_get - Get function for sysfs attribute mesh
+ * lbs_mesh_show - Get function for sysfs attribute mesh
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer where data will be returned
  */
-static ssize_t lbs_mesh_get(struct device *dev,
-		struct device_attribute *attr, char * buf)
+static ssize_t lbs_mesh_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct lbs_private *priv = to_net_dev(dev)->ml_priv;
 	return snprintf(buf, 5, "0x%X\n", !!priv->mesh_dev);
 }
 
 /**
- * lbs_mesh_set - Set function for sysfs attribute mesh
+ * lbs_mesh_store - Set function for sysfs attribute mesh
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer that contains new attribute value
  * @count: size of buffer
  */
-static ssize_t lbs_mesh_set(struct device *dev,
-		struct device_attribute *attr, const char * buf, size_t count)
+static ssize_t lbs_mesh_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t count)
 {
 	struct lbs_private *priv = to_net_dev(dev)->ml_priv;
 	int enable;
@@ -301,20 +304,19 @@ static ssize_t lbs_mesh_set(struct device *dev,
  * lbs_mesh attribute to be exported per ethX interface
  * through sysfs (/sys/class/net/ethX/lbs_mesh)
  */
-static DEVICE_ATTR(lbs_mesh, 0644, lbs_mesh_get, lbs_mesh_set);
+static DEVICE_ATTR_RW(lbs_mesh);
 
 /*
  * anycast_mask attribute to be exported per mshX interface
  * through sysfs (/sys/class/net/mshX/anycast_mask)
  */
-static DEVICE_ATTR(anycast_mask, 0644, lbs_anycast_get, lbs_anycast_set);
+static DEVICE_ATTR_RW(anycast_mask);
 
 /*
  * prb_rsp_limit attribute to be exported per mshX interface
  * through sysfs (/sys/class/net/mshX/prb_rsp_limit)
  */
-static DEVICE_ATTR(prb_rsp_limit, 0644, lbs_prb_rsp_limit_get,
-		lbs_prb_rsp_limit_set);
+static DEVICE_ATTR_RW(prb_rsp_limit);
 
 static struct attribute *lbs_mesh_sysfs_entries[] = {
 	&dev_attr_anycast_mask.attr,
@@ -351,13 +353,13 @@ static int mesh_get_default_parameters(struct device *dev,
 }
 
 /**
- * bootflag_get - Get function for sysfs attribute bootflag
+ * bootflag_show - Get function for sysfs attribute bootflag
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer where data will be returned
  */
-static ssize_t bootflag_get(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+static ssize_t bootflag_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct mrvl_mesh_defaults defs;
 	int ret;
@@ -371,14 +373,14 @@ static ssize_t bootflag_get(struct device *dev,
 }
 
 /**
- * bootflag_set - Set function for sysfs attribute bootflag
+ * bootflag_store - Set function for sysfs attribute bootflag
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer that contains new attribute value
  * @count: size of buffer
  */
-static ssize_t bootflag_set(struct device *dev, struct device_attribute *attr,
-			    const char *buf, size_t count)
+static ssize_t bootflag_store(struct device *dev, struct device_attribute *attr,
+			      const char *buf, size_t count)
 {
 	struct lbs_private *priv = to_net_dev(dev)->ml_priv;
 	struct cmd_ds_mesh_config cmd;
@@ -401,13 +403,13 @@ static ssize_t bootflag_set(struct device *dev, struct device_attribute *attr,
 }
 
 /**
- * boottime_get - Get function for sysfs attribute boottime
+ * boottime_show - Get function for sysfs attribute boottime
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer where data will be returned
  */
-static ssize_t boottime_get(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+static ssize_t boottime_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct mrvl_mesh_defaults defs;
 	int ret;
@@ -421,14 +423,15 @@ static ssize_t boottime_get(struct device *dev,
 }
 
 /**
- * boottime_set - Set function for sysfs attribute boottime
+ * boottime_store - Set function for sysfs attribute boottime
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer that contains new attribute value
  * @count: size of buffer
  */
-static ssize_t boottime_set(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+static ssize_t boottime_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t count)
 {
 	struct lbs_private *priv = to_net_dev(dev)->ml_priv;
 	struct cmd_ds_mesh_config cmd;
@@ -460,13 +463,13 @@ static ssize_t boottime_set(struct device *dev,
 }
 
 /**
- * channel_get - Get function for sysfs attribute channel
+ * channel_show - Get function for sysfs attribute channel
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer where data will be returned
  */
-static ssize_t channel_get(struct device *dev,
-			   struct device_attribute *attr, char *buf)
+static ssize_t channel_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
 {
 	struct mrvl_mesh_defaults defs;
 	int ret;
@@ -480,14 +483,14 @@ static ssize_t channel_get(struct device *dev,
 }
 
 /**
- * channel_set - Set function for sysfs attribute channel
+ * channel_store - Set function for sysfs attribute channel
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer that contains new attribute value
  * @count: size of buffer
  */
-static ssize_t channel_set(struct device *dev, struct device_attribute *attr,
-			   const char *buf, size_t count)
+static ssize_t channel_store(struct device *dev, struct device_attribute *attr,
+			     const char *buf, size_t count)
 {
 	struct lbs_private *priv = to_net_dev(dev)->ml_priv;
 	struct cmd_ds_mesh_config cmd;
@@ -510,13 +513,13 @@ static ssize_t channel_set(struct device *dev, struct device_attribute *attr,
 }
 
 /**
- * mesh_id_get - Get function for sysfs attribute mesh_id
+ * mesh_id_show - Get function for sysfs attribute mesh_id
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer where data will be returned
  */
-static ssize_t mesh_id_get(struct device *dev, struct device_attribute *attr,
-			   char *buf)
+static ssize_t mesh_id_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
 {
 	struct mrvl_mesh_defaults defs;
 	int ret;
@@ -539,14 +542,14 @@ static ssize_t mesh_id_get(struct device *dev, struct device_attribute *attr,
 }
 
 /**
- * mesh_id_set - Set function for sysfs attribute mesh_id
+ * mesh_id_store - Set function for sysfs attribute mesh_id
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer that contains new attribute value
  * @count: size of buffer
  */
-static ssize_t mesh_id_set(struct device *dev, struct device_attribute *attr,
-			   const char *buf, size_t count)
+static ssize_t mesh_id_store(struct device *dev, struct device_attribute *attr,
+			     const char *buf, size_t count)
 {
 	struct cmd_ds_mesh_config cmd;
 	struct mrvl_mesh_defaults defs;
@@ -585,13 +588,14 @@ static ssize_t mesh_id_set(struct device *dev, struct device_attribute *attr,
 }
 
 /**
- * protocol_id_get - Get function for sysfs attribute protocol_id
+ * protocol_id_show - Get function for sysfs attribute protocol_id
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer where data will be returned
  */
-static ssize_t protocol_id_get(struct device *dev,
-			       struct device_attribute *attr, char *buf)
+static ssize_t protocol_id_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
 {
 	struct mrvl_mesh_defaults defs;
 	int ret;
@@ -605,14 +609,15 @@ static ssize_t protocol_id_get(struct device *dev,
 }
 
 /**
- * protocol_id_set - Set function for sysfs attribute protocol_id
+ * protocol_id_store - Set function for sysfs attribute protocol_id
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer that contains new attribute value
  * @count: size of buffer
  */
-static ssize_t protocol_id_set(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+static ssize_t protocol_id_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
 {
 	struct cmd_ds_mesh_config cmd;
 	struct mrvl_mesh_defaults defs;
@@ -646,13 +651,13 @@ static ssize_t protocol_id_set(struct device *dev,
 }
 
 /**
- * metric_id_get - Get function for sysfs attribute metric_id
+ * metric_id_show - Get function for sysfs attribute metric_id
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer where data will be returned
  */
-static ssize_t metric_id_get(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t metric_id_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
 {
 	struct mrvl_mesh_defaults defs;
 	int ret;
@@ -666,14 +671,15 @@ static ssize_t metric_id_get(struct device *dev,
 }
 
 /**
- * metric_id_set - Set function for sysfs attribute metric_id
+ * metric_id_store - Set function for sysfs attribute metric_id
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer that contains new attribute value
  * @count: size of buffer
  */
-static ssize_t metric_id_set(struct device *dev, struct device_attribute *attr,
-			     const char *buf, size_t count)
+static ssize_t metric_id_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t count)
 {
 	struct cmd_ds_mesh_config cmd;
 	struct mrvl_mesh_defaults defs;
@@ -707,13 +713,13 @@ static ssize_t metric_id_set(struct device *dev, struct device_attribute *attr,
 }
 
 /**
- * capability_get - Get function for sysfs attribute capability
+ * capability_show - Get function for sysfs attribute capability
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer where data will be returned
  */
-static ssize_t capability_get(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t capability_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
 {
 	struct mrvl_mesh_defaults defs;
 	int ret;
@@ -727,14 +733,15 @@ static ssize_t capability_get(struct device *dev,
 }
 
 /**
- * capability_set - Set function for sysfs attribute capability
+ * capability_store - Set function for sysfs attribute capability
  * @dev: the &struct device
  * @attr: device attributes
  * @buf: buffer that contains new attribute value
  * @count: size of buffer
  */
-static ssize_t capability_set(struct device *dev, struct device_attribute *attr,
-			      const char *buf, size_t count)
+static ssize_t capability_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
 {
 	struct cmd_ds_mesh_config cmd;
 	struct mrvl_mesh_defaults defs;
@@ -768,13 +775,13 @@ static ssize_t capability_set(struct device *dev, struct device_attribute *attr,
 }
 
 
-static DEVICE_ATTR(bootflag, 0644, bootflag_get, bootflag_set);
-static DEVICE_ATTR(boottime, 0644, boottime_get, boottime_set);
-static DEVICE_ATTR(channel, 0644, channel_get, channel_set);
-static DEVICE_ATTR(mesh_id, 0644, mesh_id_get, mesh_id_set);
-static DEVICE_ATTR(protocol_id, 0644, protocol_id_get, protocol_id_set);
-static DEVICE_ATTR(metric_id, 0644, metric_id_get, metric_id_set);
-static DEVICE_ATTR(capability, 0644, capability_get, capability_set);
+static DEVICE_ATTR_RW(bootflag);
+static DEVICE_ATTR_RW(boottime);
+static DEVICE_ATTR_RW(channel);
+static DEVICE_ATTR_RW(mesh_id);
+static DEVICE_ATTR_RW(protocol_id);
+static DEVICE_ATTR_RW(metric_id);
+static DEVICE_ATTR_RW(capability);
 
 static struct attribute *boot_opts_attrs[] = {
 	&dev_attr_bootflag.attr,
diff --git a/drivers/net/wireless/marvell/libertas_tf/if_usb.c b/drivers/net/wireless/marvell/libertas_tf/if_usb.c
index a92916dc81a9..fe0a69e804d8 100644
--- a/drivers/net/wireless/marvell/libertas_tf/if_usb.c
+++ b/drivers/net/wireless/marvell/libertas_tf/if_usb.c
@@ -48,7 +48,7 @@ static int if_usb_submit_rx_urb(struct if_usb_card *cardp);
 static int if_usb_reset_device(struct lbtf_private *priv);
 
 /**
- *  if_usb_wrike_bulk_callback -  call back to handle URB status
+ *  if_usb_write_bulk_callback -  call back to handle URB status
  *
  *  @urb:		pointer to urb structure
  */
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/soc.c b/drivers/net/wireless/mediatek/mt76/mt7615/soc.c
index be9a69fe1b38..f13d1b418742 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/soc.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/soc.c
@@ -31,7 +31,6 @@ int mt7622_wmac_init(struct mt7615_dev *dev)
 
 static int mt7622_wmac_probe(struct platform_device *pdev)
 {
-	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	void __iomem *mem_base;
 	int irq;
 
@@ -39,7 +38,7 @@ static int mt7622_wmac_probe(struct platform_device *pdev)
 	if (irq < 0)
 		return irq;
 
-	mem_base = devm_ioremap_resource(&pdev->dev, res);
+	mem_base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
 	if (IS_ERR(mem_base))
 		return PTR_ERR(mem_base);
 
diff --git a/drivers/net/wireless/microchip/wilc1000/spi.c b/drivers/net/wireless/microchip/wilc1000/spi.c
index 1472e9843896..8e9aaf03a6fa 100644
--- a/drivers/net/wireless/microchip/wilc1000/spi.c
+++ b/drivers/net/wireless/microchip/wilc1000/spi.c
@@ -164,7 +164,7 @@ static int wilc_bus_probe(struct spi_device *spi)
 	wilc->bus_data = spi_priv;
 	wilc->dev_irq_num = spi->irq;
 
-	wilc->rtc_clk = devm_clk_get(&spi->dev, "rtc_clk");
+	wilc->rtc_clk = devm_clk_get(&spi->dev, "rtc");
 	if (PTR_ERR_OR_ZERO(wilc->rtc_clk) == -EPROBE_DEFER) {
 		kfree(spi_priv);
 		return -EPROBE_DEFER;
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
index 5264b0a1f098..deddb0afd312 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
@@ -1037,7 +1037,7 @@ void rt2800_txdone_entry(struct queue_entry *entry, u32 status, __le32 *txwi,
 	 * FIXME: if we do not find matching entry, we tell that frame was
 	 * posted without any retries. We need to find a way to fix that
 	 * and provide retry count.
- 	 */
+	 */
 	if (unlikely((aggr == 1 && ampdu == 0 && real_mcs != mcs)) || !match) {
 		rt2800_rate_from_status(skbdesc, status, rt2x00dev->curr_band);
 		mcs = real_mcs;
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
index d4d389e8f1b4..fb1d31b2d52a 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
@@ -446,8 +446,9 @@ static void rt2x00queue_create_tx_descriptor(struct rt2x00_dev *rt2x00dev,
 	 * Beacons and probe responses require the tsf timestamp
 	 * to be inserted into the frame.
 	 */
-	if (ieee80211_is_beacon(hdr->frame_control) ||
-	    ieee80211_is_probe_resp(hdr->frame_control))
+	if ((ieee80211_is_beacon(hdr->frame_control) ||
+	     ieee80211_is_probe_resp(hdr->frame_control)) &&
+	    !(tx_info->flags & IEEE80211_TX_CTL_INJECTED))
 		__set_bit(ENTRY_TXD_REQ_TIMESTAMP, &txdesc->flags);
 
 	if ((tx_info->flags & IEEE80211_TX_CTL_FIRST_FRAGMENT) &&
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a2ant.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a2ant.c
index 447caa4aad32..c5b8df58d4a2 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a2ant.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a2ant.c
@@ -1721,10 +1721,6 @@ static void btc8821a2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 					btc8821a2ant_ps_tdma(btcoexist,
 							NORMAL_EXEC, true, 14);
 					coex_dm->ps_tdma_du_adj_type = 14;
-				} else if (max_interval == 3) {
-					btc8821a2ant_ps_tdma(btcoexist,
-							NORMAL_EXEC, true, 15);
-					coex_dm->ps_tdma_du_adj_type = 15;
 				} else {
 					btc8821a2ant_ps_tdma(btcoexist,
 							NORMAL_EXEC, true, 15);
@@ -1739,10 +1735,6 @@ static void btc8821a2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 					btc8821a2ant_ps_tdma(btcoexist,
 							NORMAL_EXEC, true, 10);
 					coex_dm->ps_tdma_du_adj_type = 10;
-				} else if (max_interval == 3) {
-					btc8821a2ant_ps_tdma(btcoexist,
-							NORMAL_EXEC, true, 11);
-					coex_dm->ps_tdma_du_adj_type = 11;
 				} else {
 					btc8821a2ant_ps_tdma(btcoexist,
 							NORMAL_EXEC, true, 11);
@@ -1759,10 +1751,6 @@ static void btc8821a2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 					btc8821a2ant_ps_tdma(btcoexist,
 							NORMAL_EXEC, true, 6);
 					coex_dm->ps_tdma_du_adj_type = 6;
-				} else if (max_interval == 3) {
-					btc8821a2ant_ps_tdma(btcoexist,
-							NORMAL_EXEC, true, 7);
-					coex_dm->ps_tdma_du_adj_type = 7;
 				} else {
 					btc8821a2ant_ps_tdma(btcoexist,
 							NORMAL_EXEC, true, 7);
@@ -1777,10 +1765,6 @@ static void btc8821a2ant_tdma_duration_adjust(struct btc_coexist *btcoexist,
 					btc8821a2ant_ps_tdma(btcoexist,
 							NORMAL_EXEC, true, 2);
 					coex_dm->ps_tdma_du_adj_type = 2;
-				} else if (max_interval == 3) {
-					btc8821a2ant_ps_tdma(btcoexist,
-							NORMAL_EXEC, true, 3);
-					coex_dm->ps_tdma_du_adj_type = 3;
 				} else {
 					btc8821a2ant_ps_tdma(btcoexist,
 							NORMAL_EXEC, true, 3);
@@ -2810,6 +2794,7 @@ static void btc8821a2ant_action_a2dp(struct btc_coexist *btcoexist)
 					      0x4);
 	}
 
+	/* preserve identical branches for further fine-tuning */
 	if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
 	    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
 		btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 23);
@@ -2944,6 +2929,7 @@ static void btc8821a2ant_action_pan_edr(struct btc_coexist *btcoexist)
 					      0x4);
 	}
 
+	/* preserve identical branches for further fine-tuning */
 	if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
 	    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH))
 		btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 26);
@@ -3132,6 +3118,7 @@ static void btc8821a2ant_action_pan_edr_hid(struct btc_coexist *btcoexist)
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 
+	/* preserve identical branches for further fine-tuning */
 	if (wifi_bw == BTC_WIFI_BW_LEGACY) {
 		/* for HID at 11b/g mode */
 		btc8821a2ant_coex_table(btcoexist, NORMAL_EXEC, 0x55ff55ff,
@@ -3321,6 +3308,7 @@ static void btc8821a2ant_action_hid_a2dp(struct btc_coexist *btcoexist)
 					      0x4);
 	}
 
+	/* preserve identical branches for further fine-tuning */
 	if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) ||
 	    (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
 		btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 23);
diff --git a/drivers/net/wireless/realtek/rtlwifi/cam.c b/drivers/net/wireless/realtek/rtlwifi/cam.c
index 7aa28da39409..7a0355dc6bab 100644
--- a/drivers/net/wireless/realtek/rtlwifi/cam.c
+++ b/drivers/net/wireless/realtek/rtlwifi/cam.c
@@ -167,7 +167,7 @@ void rtl_cam_mark_invalid(struct ieee80211_hw *hw, u8 uc_index)
 
 	u32 ul_command;
 	u32 ul_content;
-	u32 ul_enc_algo = rtlpriv->cfg->maps[SEC_CAM_AES];
+	u32 ul_enc_algo;
 
 	switch (rtlpriv->sec.pairwise_enc_algorithm) {
 	case WEP40_ENCRYPTION:
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/mac.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/mac.c
index 8d2c6d8d32d9..4ff0d4118193 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/mac.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/mac.c
@@ -112,7 +112,7 @@ void rtl92c_read_chip_version(struct ieee80211_hw *hw)
 }
 
 /**
- * writeLLT - LLT table write access
+ * rtl92c_llt_write - LLT table write access
  * @hw: Pointer to the ieee80211_hw structure.
  * @address: LLT logical address.
  * @data: LLT data content
@@ -144,7 +144,7 @@ bool rtl92c_llt_write(struct ieee80211_hw *hw, u32 address, u32 data)
 }
 
 /**
- * rtl92c_init_LLT_table - Init LLT table
+ * rtl92c_init_llt_table - Init LLT table
  * @hw: Pointer to the ieee80211_hw structure.
  * @boundary: Page boundary.
  *
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c
index 38034102aacb..e474b4ec17f3 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c
@@ -513,7 +513,7 @@ void rtl92se_tx_fill_cmddesc(struct ieee80211_hw *hw, u8 *pdesc8,
 
 	/* This bit indicate this packet is used for FW download. */
 	if (tcb_desc->cmd_or_init == DESC_PACKET_TYPE_INIT) {
-		/* For firmware downlaod we only need to set LINIP */
+		/* For firmware download we only need to set LINIP */
 		set_tx_desc_linip(pdesc, tcb_desc->last_inipkt);
 
 		/* 92SE must set as 1 for firmware download HW DMA error */
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c
index f8a1de6e9849..c98f2216734f 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c
@@ -915,7 +915,7 @@ int rtl8723e_hw_init(struct ieee80211_hw *hw)
 	struct rtl_phy *rtlphy = &(rtlpriv->phy);
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
-	bool rtstatus = true;
+	bool rtstatus;
 	int err;
 	u8 tmp_u1b;
 	unsigned long flags;
diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c
index 9fe77556858e..63ce2443f136 100644
--- a/drivers/net/wireless/rndis_wlan.c
+++ b/drivers/net/wireless/rndis_wlan.c
@@ -1036,14 +1036,11 @@ static bool is_associated(struct usbnet *usbdev)
 {
 	struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev);
 	u8 bssid[ETH_ALEN];
-	int ret;
 
 	if (!priv->radio_on)
 		return false;
 
-	ret = get_bssid(usbdev, bssid);
-
-	return (ret == 0 && !is_zero_ether_addr(bssid));
+	return (get_bssid(usbdev, bssid) == 0 && !is_zero_ether_addr(bssid));
 }
 
 static int disassociate(struct usbnet *usbdev, bool reset_ssid)
diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c
index ce9892152f4d..99b21a2c8386 100644
--- a/drivers/net/wireless/rsi/rsi_91x_hal.c
+++ b/drivers/net/wireless/rsi/rsi_91x_hal.c
@@ -203,7 +203,7 @@ int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb)
 		wh->frame_control |= cpu_to_le16(RSI_SET_PS_ENABLE);
 
 	if ((!(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT)) &&
-	    (common->secinfo.security_enable)) {
+	    info->control.hw_key) {
 		if (rsi_is_cipher_wep(common))
 			ieee80211_size += 4;
 		else
@@ -470,9 +470,9 @@ int rsi_prepare_beacon(struct rsi_common *common, struct sk_buff *skb)
 	}
 
 	if (common->band == NL80211_BAND_2GHZ)
-		bcn_frm->bbp_info |= cpu_to_le16(RSI_RATE_1);
+		bcn_frm->rate_info |= cpu_to_le16(RSI_RATE_1);
 	else
-		bcn_frm->bbp_info |= cpu_to_le16(RSI_RATE_6);
+		bcn_frm->rate_info |= cpu_to_le16(RSI_RATE_6);
 
 	if (mac_bcn->data[tim_offset + 2] == 0)
 		bcn_frm->frame_info |= cpu_to_le16(RSI_DATA_DESC_DTIM_BEACON);
diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
index 16025300cddb..b66975f54567 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
@@ -837,6 +837,23 @@ static void rsi_mac80211_bss_info_changed(struct ieee80211_hw *hw,
 			common->cqm_info.rssi_hyst);
 	}
 
+	if (changed & BSS_CHANGED_BEACON_INT) {
+		rsi_dbg(INFO_ZONE, "%s: Changed Beacon interval: %d\n",
+			__func__, bss_conf->beacon_int);
+		if (common->beacon_interval != bss->beacon_int) {
+			common->beacon_interval = bss->beacon_int;
+			if (vif->type == NL80211_IFTYPE_AP) {
+				struct vif_priv *vif_info = (struct vif_priv *)vif->drv_priv;
+
+				rsi_set_vap_capabilities(common, RSI_OPMODE_AP,
+							 vif->addr, vif_info->vap_id,
+							 VAP_UPDATE);
+			}
+		}
+		adapter->ps_info.listen_interval =
+			bss->beacon_int * adapter->ps_info.num_bcns_per_lis_int;
+	}
+
 	if ((changed & BSS_CHANGED_BEACON_ENABLED) &&
 	    ((vif->type == NL80211_IFTYPE_AP) ||
 	     (vif->type == NL80211_IFTYPE_P2P_GO))) {
@@ -1028,7 +1045,6 @@ static int rsi_mac80211_set_key(struct ieee80211_hw *hw,
 	mutex_lock(&common->mutex);
 	switch (cmd) {
 	case SET_KEY:
-		secinfo->security_enable = true;
 		status = rsi_hal_key_config(hw, vif, key, sta);
 		if (status) {
 			mutex_unlock(&common->mutex);
@@ -1047,8 +1063,6 @@ static int rsi_mac80211_set_key(struct ieee80211_hw *hw,
 		break;
 
 	case DISABLE_KEY:
-		if (vif->type == NL80211_IFTYPE_STATION)
-			secinfo->security_enable = false;
 		rsi_dbg(ERR_ZONE, "%s: RSI del key\n", __func__);
 		memset(key, 0, sizeof(struct ieee80211_key_conf));
 		status = rsi_hal_key_config(hw, vif, key, sta);
diff --git a/drivers/net/wireless/rsi/rsi_91x_mgmt.c b/drivers/net/wireless/rsi/rsi_91x_mgmt.c
index 33c76d39a8e9..891fd5f0fa76 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mgmt.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mgmt.c
@@ -1547,8 +1547,8 @@ static int rsi_eeprom_read(struct rsi_common *common)
 }
 
 /**
- * This function sends a frame to block/unblock
- * data queues in the firmware
+ * rsi_send_block_unblock_frame() - This function sends a frame to block/unblock
+ *                                  data queues in the firmware
  *
  * @common: Pointer to the driver private structure.
  * @block_event: Event block if true, unblock if false
@@ -1803,8 +1803,7 @@ int rsi_send_wowlan_request(struct rsi_common *common, u16 flags,
 			RSI_WIFI_MGMT_Q);
 	cmd_frame->desc.desc_dword0.frame_type = WOWLAN_CONFIG_PARAMS;
 	cmd_frame->host_sleep_status = sleep_status;
-	if (common->secinfo.security_enable &&
-	    common->secinfo.gtk_cipher)
+	if (common->secinfo.gtk_cipher)
 		flags |= RSI_WOW_GTK_REKEY;
 	if (sleep_status)
 		cmd_frame->wow_flags = flags;
diff --git a/drivers/net/wireless/rsi/rsi_main.h b/drivers/net/wireless/rsi/rsi_main.h
index a1065e5a92b4..0f535850a383 100644
--- a/drivers/net/wireless/rsi/rsi_main.h
+++ b/drivers/net/wireless/rsi/rsi_main.h
@@ -151,7 +151,6 @@ enum edca_queue {
 };
 
 struct security_info {
-	bool security_enable;
 	u32 ptk_cipher;
 	u32 gtk_cipher;
 };
diff --git a/drivers/net/wireless/st/cw1200/cw1200_sdio.c b/drivers/net/wireless/st/cw1200/cw1200_sdio.c
index b65ec14136c7..4c30b5772ce0 100644
--- a/drivers/net/wireless/st/cw1200/cw1200_sdio.c
+++ b/drivers/net/wireless/st/cw1200/cw1200_sdio.c
@@ -53,6 +53,7 @@ static const struct sdio_device_id cw1200_sdio_ids[] = {
 	{ SDIO_DEVICE(SDIO_VENDOR_ID_STE, SDIO_DEVICE_ID_STE_CW1200) },
 	{ /* end: all zeroes */			},
 };
+MODULE_DEVICE_TABLE(sdio, cw1200_sdio_ids);
 
 /* hwbus_ops implemetation */
 
diff --git a/drivers/net/wireless/st/cw1200/scan.c b/drivers/net/wireless/st/cw1200/scan.c
index 988581cc134b..1f856fbbc0ea 100644
--- a/drivers/net/wireless/st/cw1200/scan.c
+++ b/drivers/net/wireless/st/cw1200/scan.c
@@ -75,30 +75,27 @@ int cw1200_hw_scan(struct ieee80211_hw *hw,
 	if (req->n_ssids > WSM_SCAN_MAX_NUM_OF_SSIDS)
 		return -EINVAL;
 
-	/* will be unlocked in cw1200_scan_work() */
-	down(&priv->scan.lock);
-	mutex_lock(&priv->conf_mutex);
-
 	frame.skb = ieee80211_probereq_get(hw, priv->vif->addr, NULL, 0,
 		req->ie_len);
-	if (!frame.skb) {
-		mutex_unlock(&priv->conf_mutex);
-		up(&priv->scan.lock);
+	if (!frame.skb)
 		return -ENOMEM;
-	}
 
 	if (req->ie_len)
 		skb_put_data(frame.skb, req->ie, req->ie_len);
 
+	/* will be unlocked in cw1200_scan_work() */
+	down(&priv->scan.lock);
+	mutex_lock(&priv->conf_mutex);
+
 	ret = wsm_set_template_frame(priv, &frame);
 	if (!ret) {
 		/* Host want to be the probe responder. */
 		ret = wsm_set_probe_responder(priv, true);
 	}
 	if (ret) {
-		dev_kfree_skb(frame.skb);
 		mutex_unlock(&priv->conf_mutex);
 		up(&priv->scan.lock);
+		dev_kfree_skb(frame.skb);
 		return ret;
 	}
 
@@ -120,8 +117,8 @@ int cw1200_hw_scan(struct ieee80211_hw *hw,
 		++priv->scan.n_ssids;
 	}
 
-	dev_kfree_skb(frame.skb);
 	mutex_unlock(&priv->conf_mutex);
+	dev_kfree_skb(frame.skb);
 	queue_work(priv->workqueue, &priv->scan.work);
 	return 0;
 }
diff --git a/drivers/net/wireless/ti/wl1251/cmd.c b/drivers/net/wireless/ti/wl1251/cmd.c
index 498c8db2eb48..c3be81dc7970 100644
--- a/drivers/net/wireless/ti/wl1251/cmd.c
+++ b/drivers/net/wireless/ti/wl1251/cmd.c
@@ -12,7 +12,7 @@
 #include "acx.h"
 
 /**
- * send command to firmware
+ * wl1251_cmd_send - Send command to firmware
  *
  * @wl: wl struct
  * @id: command id
@@ -59,7 +59,7 @@ out:
 }
 
 /**
- * send test command to firmware
+ * wl1251_cmd_test - Send test command to firmware
  *
  * @wl: wl struct
  * @buf: buffer containing the command, with all headers, must work with dma
@@ -100,7 +100,7 @@ int wl1251_cmd_test(struct wl1251 *wl, void *buf, size_t buf_len, u8 answer)
 }
 
 /**
- * read acx from firmware
+ * wl1251_cmd_interrogate - Read acx from firmware
  *
  * @wl: wl struct
  * @id: acx id
@@ -138,7 +138,7 @@ out:
 }
 
 /**
- * write acx value to firmware
+ * wl1251_cmd_configure - Write acx value to firmware
  *
  * @wl: wl struct
  * @id: acx id
@@ -454,9 +454,12 @@ int wl1251_cmd_scan(struct wl1251 *wl, u8 *ssid, size_t ssid_len,
 		cmd->channels[i].channel = channels[i]->hw_value;
 	}
 
-	cmd->params.ssid_len = ssid_len;
-	if (ssid)
-		memcpy(cmd->params.ssid, ssid, ssid_len);
+	if (ssid) {
+		int len = clamp_val(ssid_len, 0, IEEE80211_MAX_SSID_LEN);
+
+		cmd->params.ssid_len = len;
+		memcpy(cmd->params.ssid, ssid, len);
+	}
 
 	ret = wl1251_cmd_send(wl, CMD_SCAN, cmd, sizeof(*cmd));
 	if (ret < 0) {
diff --git a/drivers/net/wireless/ti/wl12xx/main.c b/drivers/net/wireless/ti/wl12xx/main.c
index 9d7dbfe7fe0c..c6da0cfb4afb 100644
--- a/drivers/net/wireless/ti/wl12xx/main.c
+++ b/drivers/net/wireless/ti/wl12xx/main.c
@@ -1503,6 +1503,13 @@ static int wl12xx_get_fuse_mac(struct wl1271 *wl)
 	u32 mac1, mac2;
 	int ret;
 
+	/* Device may be in ELP from the bootloader or kexec */
+	ret = wlcore_write32(wl, WL12XX_WELP_ARM_COMMAND, WELP_ARM_COMMAND_VAL);
+	if (ret < 0)
+		goto out;
+
+	usleep_range(500000, 700000);
+
 	ret = wlcore_set_partition(wl, &wl->ptable[PART_DRPW]);
 	if (ret < 0)
 		goto out;
diff --git a/drivers/net/wireless/ti/wlcore/cmd.c b/drivers/net/wireless/ti/wlcore/cmd.c
index 32a2e27cc561..8b798b5fcaf5 100644
--- a/drivers/net/wireless/ti/wlcore/cmd.c
+++ b/drivers/net/wireless/ti/wlcore/cmd.c
@@ -821,7 +821,7 @@ out:
 
 
 /**
- * send test command to firmware
+ * wl1271_cmd_test - send test command to firmware
  *
  * @wl: wl struct
  * @buf: buffer containing the command, with all headers, must work with dma
@@ -850,7 +850,7 @@ int wl1271_cmd_test(struct wl1271 *wl, void *buf, size_t buf_len, u8 answer)
 EXPORT_SYMBOL_GPL(wl1271_cmd_test);
 
 /**
- * read acx from firmware
+ * wl1271_cmd_interrogate - read acx from firmware
  *
  * @wl: wl struct
  * @id: acx id
@@ -879,7 +879,7 @@ int wl1271_cmd_interrogate(struct wl1271 *wl, u16 id, void *buf,
 }
 
 /**
- * write acx value to firmware
+ * wlcore_cmd_configure_failsafe - write acx value to firmware
  *
  * @wl: wl struct
  * @id: acx id
diff --git a/drivers/net/wireless/ti/wlcore/event.c b/drivers/net/wireless/ti/wlcore/event.c
index a68bbadae043..46ab69eab26a 100644
--- a/drivers/net/wireless/ti/wlcore/event.c
+++ b/drivers/net/wireless/ti/wlcore/event.c
@@ -29,18 +29,20 @@ int wlcore_event_fw_logger(struct wl1271 *wl)
 	u8  *buffer;
 	u32 internal_fw_addrbase = WL18XX_DATA_RAM_BASE_ADDRESS;
 	u32 addr = WL18XX_LOGGER_SDIO_BUFF_ADDR;
-	u32 end_buff_addr = WL18XX_LOGGER_SDIO_BUFF_ADDR +
-				WL18XX_LOGGER_BUFF_OFFSET;
+	u32 addr_ptr;
+	u32 buff_start_ptr;
+	u32 buff_read_ptr;
+	u32 buff_end_ptr;
 	u32 available_len;
 	u32 actual_len;
-	u32 clear_addr;
+	u32 clear_ptr;
 	size_t len;
 	u32 start_loc;
 
 	buffer = kzalloc(WL18XX_LOGGER_SDIO_BUFF_MAX, GFP_KERNEL);
 	if (!buffer) {
 		wl1271_error("Fail to allocate fw logger memory");
-		fw_log.actual_buff_size = cpu_to_le32(0);
+		actual_len = 0;
 		goto out;
 	}
 
@@ -49,51 +51,58 @@ int wlcore_event_fw_logger(struct wl1271 *wl)
 	if (ret < 0) {
 		wl1271_error("Fail to read logger buffer, error_id = %d",
 			     ret);
-		fw_log.actual_buff_size = cpu_to_le32(0);
+		actual_len = 0;
 		goto free_out;
 	}
 
 	memcpy(&fw_log, buffer, sizeof(fw_log));
 
-	if (le32_to_cpu(fw_log.actual_buff_size) == 0)
+	actual_len = le32_to_cpu(fw_log.actual_buff_size);
+	if (actual_len == 0)
 		goto free_out;
 
-	actual_len = le32_to_cpu(fw_log.actual_buff_size);
-	start_loc = (le32_to_cpu(fw_log.buff_read_ptr) -
-			internal_fw_addrbase) - addr;
-	end_buff_addr += le32_to_cpu(fw_log.max_buff_size);
-	available_len = end_buff_addr -
-			(le32_to_cpu(fw_log.buff_read_ptr) -
-				 internal_fw_addrbase);
-	actual_len = min(actual_len, available_len);
-	len = actual_len;
+	/* Calculate the internal pointer to the fwlog structure */
+	addr_ptr = internal_fw_addrbase + addr;
+
+	/* Calculate the internal pointers to the start and end of log buffer */
+	buff_start_ptr = addr_ptr + WL18XX_LOGGER_BUFF_OFFSET;
+	buff_end_ptr = buff_start_ptr + le32_to_cpu(fw_log.max_buff_size);
 
+	/* Read the read pointer and validate it */
+	buff_read_ptr = le32_to_cpu(fw_log.buff_read_ptr);
+	if (buff_read_ptr < buff_start_ptr ||
+	    buff_read_ptr >= buff_end_ptr) {
+		wl1271_error("buffer read pointer out of bounds: %x not in (%x-%x)\n",
+			     buff_read_ptr, buff_start_ptr, buff_end_ptr);
+		goto free_out;
+	}
+
+	start_loc = buff_read_ptr - addr_ptr;
+	available_len = buff_end_ptr - buff_read_ptr;
+
+	/* Copy initial part up to the end of ring buffer */
+	len = min(actual_len, available_len);
 	wl12xx_copy_fwlog(wl, &buffer[start_loc], len);
-	clear_addr = addr + start_loc + le32_to_cpu(fw_log.actual_buff_size) +
-			internal_fw_addrbase;
+	clear_ptr = addr_ptr + start_loc + actual_len;
+	if (clear_ptr == buff_end_ptr)
+		clear_ptr = buff_start_ptr;
 
-	len = le32_to_cpu(fw_log.actual_buff_size) - len;
+	/* Copy any remaining part from beginning of ring buffer */
+	len = actual_len - len;
 	if (len) {
 		wl12xx_copy_fwlog(wl,
 				  &buffer[WL18XX_LOGGER_BUFF_OFFSET],
 				  len);
-		clear_addr = addr + WL18XX_LOGGER_BUFF_OFFSET + len +
-				internal_fw_addrbase;
-	}
-
-	/* double check that clear address and write pointer are the same */
-	if (clear_addr != le32_to_cpu(fw_log.buff_write_ptr)) {
-		wl1271_error("Calculate of clear addr Clear = %x, write = %x",
-			     clear_addr, le32_to_cpu(fw_log.buff_write_ptr));
+		clear_ptr = addr_ptr + WL18XX_LOGGER_BUFF_OFFSET + len;
 	}
 
-	/* indicate FW about Clear buffer */
+	/* Update the read pointer */
 	ret = wlcore_write32(wl, addr + WL18XX_LOGGER_READ_POINT_OFFSET,
-			     fw_log.buff_write_ptr);
+			     clear_ptr);
 free_out:
 	kfree(buffer);
 out:
-	return le32_to_cpu(fw_log.actual_buff_size);
+	return actual_len;
 }
 EXPORT_SYMBOL_GPL(wlcore_event_fw_logger);
 
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 8509b989940c..e500b8405f8f 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -3242,8 +3242,8 @@ static void wl1271_op_configure_filter(struct ieee80211_hw *hw,
 		 * the firmware filters so that all multicast packets are passed
 		 * This is mandatory for MDNS based discovery protocols 
 		 */
- 		if (wlvif->bss_type == BSS_TYPE_AP_BSS) {
- 			if (*total & FIF_ALLMULTI) {
+		if (wlvif->bss_type == BSS_TYPE_AP_BSS) {
+			if (*total & FIF_ALLMULTI) {
 				ret = wl1271_acx_group_address_tbl(wl, wlvif,
 							false,
 							NULL, 0);
diff --git a/drivers/net/wireless/ti/wlcore/sysfs.c b/drivers/net/wireless/ti/wlcore/sysfs.c
index 5cf0379b88b6..35b535c125b6 100644
--- a/drivers/net/wireless/ti/wlcore/sysfs.c
+++ b/drivers/net/wireless/ti/wlcore/sysfs.c
@@ -12,9 +12,9 @@
 #include "debug.h"
 #include "sysfs.h"
 
-static ssize_t wl1271_sysfs_show_bt_coex_state(struct device *dev,
-					       struct device_attribute *attr,
-					       char *buf)
+static ssize_t bt_coex_state_show(struct device *dev,
+				  struct device_attribute *attr,
+				  char *buf)
 {
 	struct wl1271 *wl = dev_get_drvdata(dev);
 	ssize_t len;
@@ -30,9 +30,9 @@ static ssize_t wl1271_sysfs_show_bt_coex_state(struct device *dev,
 
 }
 
-static ssize_t wl1271_sysfs_store_bt_coex_state(struct device *dev,
-						struct device_attribute *attr,
-						const char *buf, size_t count)
+static ssize_t bt_coex_state_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t count)
 {
 	struct wl1271 *wl = dev_get_drvdata(dev);
 	unsigned long res;
@@ -71,13 +71,11 @@ static ssize_t wl1271_sysfs_store_bt_coex_state(struct device *dev,
 	return count;
 }
 
-static DEVICE_ATTR(bt_coex_state, 0644,
-		   wl1271_sysfs_show_bt_coex_state,
-		   wl1271_sysfs_store_bt_coex_state);
+static DEVICE_ATTR_RW(bt_coex_state);
 
-static ssize_t wl1271_sysfs_show_hw_pg_ver(struct device *dev,
-					   struct device_attribute *attr,
-					   char *buf)
+static ssize_t hw_pg_ver_show(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
 {
 	struct wl1271 *wl = dev_get_drvdata(dev);
 	ssize_t len;
@@ -94,7 +92,7 @@ static ssize_t wl1271_sysfs_show_hw_pg_ver(struct device *dev,
 	return len;
 }
 
-static DEVICE_ATTR(hw_pg_ver, 0444, wl1271_sysfs_show_hw_pg_ver, NULL);
+static DEVICE_ATTR_RO(hw_pg_ver);
 
 static ssize_t wl1271_sysfs_read_fwlog(struct file *filp, struct kobject *kobj,
 				       struct bin_attribute *bin_attr,
diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
index 5c4cd0e1adeb..a7ceef10bf6a 100644
--- a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
+++ b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
@@ -1544,14 +1544,14 @@ static int __init usb_init(void)
 
 	zd_workqueue = create_singlethread_workqueue(driver.name);
 	if (zd_workqueue == NULL) {
-		printk(KERN_ERR "%s couldn't create workqueue\n", driver.name);
+		pr_err("%s couldn't create workqueue\n", driver.name);
 		return -ENOMEM;
 	}
 
 	r = usb_register(&driver);
 	if (r) {
 		destroy_workqueue(zd_workqueue);
-		printk(KERN_ERR "%s usb_register() failed. Error number %d\n",
+		pr_err("%s usb_register() failed. Error number %d\n",
 		       driver.name, r);
 		return r;
 	}
diff --git a/drivers/net/wwan/Kconfig b/drivers/net/wwan/Kconfig
index 7ad1920120bc..de9384326bc8 100644
--- a/drivers/net/wwan/Kconfig
+++ b/drivers/net/wwan/Kconfig
@@ -3,15 +3,9 @@
 # Wireless WAN device configuration
 #
 
-menuconfig WWAN
-	bool "Wireless WAN"
-	help
-	  This section contains Wireless WAN configuration for WWAN framework
-	  and drivers.
-
-if WWAN
+menu "Wireless WAN"
 
-config WWAN_CORE
+config WWAN
 	tristate "WWAN Driver Core"
 	help
 	  Say Y here if you want to use the WWAN driver core. This driver
@@ -20,9 +14,19 @@ config WWAN_CORE
 	  To compile this driver as a module, choose M here: the module will be
 	  called wwan.
 
+if WWAN
+
+config WWAN_HWSIM
+	tristate "Simulated WWAN device"
+	help
+	  This driver is a developer testing tool that can be used to test WWAN
+	  framework.
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called wwan_hwsim.  If unsure, say N.
+
 config MHI_WWAN_CTRL
 	tristate "MHI WWAN control driver for QCOM-based PCIe modems"
-	select WWAN_CORE
 	depends on MHI_BUS
 	help
 	  MHI WWAN CTRL allows QCOM-based PCIe modems to expose different modem
@@ -34,4 +38,35 @@ config MHI_WWAN_CTRL
 	  To compile this driver as a module, choose M here: the module will be
 	  called mhi_wwan_ctrl.
 
+config RPMSG_WWAN_CTRL
+	tristate "RPMSG WWAN control driver"
+	depends on RPMSG
+	help
+	  RPMSG WWAN CTRL allows modems available via RPMSG channels to expose
+	  different modem protocols/ports to userspace, including AT and QMI.
+	  These protocols can be accessed directly from userspace
+	  (e.g. AT commands) or via libraries/tools (e.g. libqmi, libqcdm...).
+
+	  This is mainly used for modems integrated into many Qualcomm SoCs,
+	  e.g. for AT and QMI on Qualcomm MSM8916 or MSM8974. Note that many
+	  newer Qualcomm SoCs (e.g. SDM845) still provide an AT port through
+	  this driver but the QMI messages can only be sent through
+	  QRTR network sockets (CONFIG_QRTR).
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called rpmsg_wwan_ctrl.
+
+config IOSM
+	tristate "IOSM Driver for Intel M.2 WWAN Device"
+	depends on INTEL_IOMMU
+	help
+	  This driver enables Intel M.2 WWAN Device communication.
+
+	  If you have one of those Intel M.2 WWAN Modules and wish to use it in
+	  Linux say Y/M here.
+
+	  If unsure, say N.
+
 endif # WWAN
+
+endmenu
diff --git a/drivers/net/wwan/Makefile b/drivers/net/wwan/Makefile
index 556cd90958ca..d90ac33abaef 100644
--- a/drivers/net/wwan/Makefile
+++ b/drivers/net/wwan/Makefile
@@ -3,7 +3,11 @@
 # Makefile for the Linux WWAN device drivers.
 #
 
-obj-$(CONFIG_WWAN_CORE) += wwan.o
+obj-$(CONFIG_WWAN) += wwan.o
 wwan-objs += wwan_core.o
 
+obj-$(CONFIG_WWAN_HWSIM) += wwan_hwsim.o
+
 obj-$(CONFIG_MHI_WWAN_CTRL) += mhi_wwan_ctrl.o
+obj-$(CONFIG_RPMSG_WWAN_CTRL) += rpmsg_wwan_ctrl.o
+obj-$(CONFIG_IOSM) += iosm/
diff --git a/drivers/net/wwan/iosm/Makefile b/drivers/net/wwan/iosm/Makefile
new file mode 100644
index 000000000000..4f9f0ae398e1
--- /dev/null
+++ b/drivers/net/wwan/iosm/Makefile
@@ -0,0 +1,23 @@
+# SPDX-License-Identifier: (GPL-2.0-only)
+#
+# Copyright (C) 2020-21 Intel Corporation.
+#
+
+iosm-y = \
+	iosm_ipc_task_queue.o	\
+	iosm_ipc_imem.o			\
+	iosm_ipc_imem_ops.o		\
+	iosm_ipc_mmio.o			\
+	iosm_ipc_port.o			\
+	iosm_ipc_wwan.o			\
+	iosm_ipc_uevent.o		\
+	iosm_ipc_pm.o			\
+	iosm_ipc_pcie.o			\
+	iosm_ipc_irq.o			\
+	iosm_ipc_chnl_cfg.o		\
+	iosm_ipc_protocol.o		\
+	iosm_ipc_protocol_ops.o	\
+	iosm_ipc_mux.o			\
+	iosm_ipc_mux_codec.o
+
+obj-$(CONFIG_IOSM) := iosm.o
diff --git a/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.c b/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.c
new file mode 100644
index 000000000000..804e6c4f2c78
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#include <linux/wwan.h>
+
+#include "iosm_ipc_chnl_cfg.h"
+
+/* Max. sizes of a downlink buffers */
+#define IPC_MEM_MAX_DL_FLASH_BUF_SIZE (16 * 1024)
+#define IPC_MEM_MAX_DL_LOOPBACK_SIZE (1 * 1024 * 1024)
+#define IPC_MEM_MAX_DL_AT_BUF_SIZE 2048
+#define IPC_MEM_MAX_DL_RPC_BUF_SIZE (32 * 1024)
+#define IPC_MEM_MAX_DL_MBIM_BUF_SIZE IPC_MEM_MAX_DL_RPC_BUF_SIZE
+
+/* Max. transfer descriptors for a pipe. */
+#define IPC_MEM_MAX_TDS_FLASH_DL 3
+#define IPC_MEM_MAX_TDS_FLASH_UL 6
+#define IPC_MEM_MAX_TDS_AT 4
+#define IPC_MEM_MAX_TDS_RPC 4
+#define IPC_MEM_MAX_TDS_MBIM IPC_MEM_MAX_TDS_RPC
+#define IPC_MEM_MAX_TDS_LOOPBACK 11
+
+/* Accumulation backoff usec */
+#define IRQ_ACC_BACKOFF_OFF 0
+
+/* MUX acc backoff 1ms */
+#define IRQ_ACC_BACKOFF_MUX 1000
+
+/* Modem channel configuration table
+ * Always reserve element zero for flash channel.
+ */
+static struct ipc_chnl_cfg modem_cfg[] = {
+	/* IP Mux */
+	{ IPC_MEM_IP_CHL_ID_0, IPC_MEM_PIPE_0, IPC_MEM_PIPE_1,
+	  IPC_MEM_MAX_TDS_MUX_LITE_UL, IPC_MEM_MAX_TDS_MUX_LITE_DL,
+	  IPC_MEM_MAX_DL_MUX_LITE_BUF_SIZE, WWAN_PORT_UNKNOWN },
+	/* RPC - 0 */
+	{ IPC_MEM_CTRL_CHL_ID_1, IPC_MEM_PIPE_2, IPC_MEM_PIPE_3,
+	  IPC_MEM_MAX_TDS_RPC, IPC_MEM_MAX_TDS_RPC,
+	  IPC_MEM_MAX_DL_RPC_BUF_SIZE, WWAN_PORT_UNKNOWN },
+	/* IAT0 */
+	{ IPC_MEM_CTRL_CHL_ID_2, IPC_MEM_PIPE_4, IPC_MEM_PIPE_5,
+	  IPC_MEM_MAX_TDS_AT, IPC_MEM_MAX_TDS_AT, IPC_MEM_MAX_DL_AT_BUF_SIZE,
+	  WWAN_PORT_AT },
+	/* Trace */
+	{ IPC_MEM_CTRL_CHL_ID_3, IPC_MEM_PIPE_6, IPC_MEM_PIPE_7,
+	  IPC_MEM_TDS_TRC, IPC_MEM_TDS_TRC, IPC_MEM_MAX_DL_TRC_BUF_SIZE,
+	  WWAN_PORT_UNKNOWN },
+	/* IAT1 */
+	{ IPC_MEM_CTRL_CHL_ID_4, IPC_MEM_PIPE_8, IPC_MEM_PIPE_9,
+	  IPC_MEM_MAX_TDS_AT, IPC_MEM_MAX_TDS_AT, IPC_MEM_MAX_DL_AT_BUF_SIZE,
+	  WWAN_PORT_AT },
+	/* Loopback */
+	{ IPC_MEM_CTRL_CHL_ID_5, IPC_MEM_PIPE_10, IPC_MEM_PIPE_11,
+	  IPC_MEM_MAX_TDS_LOOPBACK, IPC_MEM_MAX_TDS_LOOPBACK,
+	  IPC_MEM_MAX_DL_LOOPBACK_SIZE, WWAN_PORT_UNKNOWN },
+	/* MBIM Channel */
+	{ IPC_MEM_CTRL_CHL_ID_6, IPC_MEM_PIPE_12, IPC_MEM_PIPE_13,
+	  IPC_MEM_MAX_TDS_MBIM, IPC_MEM_MAX_TDS_MBIM,
+	  IPC_MEM_MAX_DL_MBIM_BUF_SIZE, WWAN_PORT_MBIM },
+};
+
+int ipc_chnl_cfg_get(struct ipc_chnl_cfg *chnl_cfg, int index)
+{
+	int array_size = ARRAY_SIZE(modem_cfg);
+
+	if (index >= array_size) {
+		pr_err("index: %d and array_size %d", index, array_size);
+		return -ECHRNG;
+	}
+
+	if (index == IPC_MEM_MUX_IP_CH_IF_ID)
+		chnl_cfg->accumulation_backoff = IRQ_ACC_BACKOFF_MUX;
+	else
+		chnl_cfg->accumulation_backoff = IRQ_ACC_BACKOFF_OFF;
+
+	chnl_cfg->ul_nr_of_entries = modem_cfg[index].ul_nr_of_entries;
+	chnl_cfg->dl_nr_of_entries = modem_cfg[index].dl_nr_of_entries;
+	chnl_cfg->dl_buf_size = modem_cfg[index].dl_buf_size;
+	chnl_cfg->id = modem_cfg[index].id;
+	chnl_cfg->ul_pipe = modem_cfg[index].ul_pipe;
+	chnl_cfg->dl_pipe = modem_cfg[index].dl_pipe;
+	chnl_cfg->wwan_port_type = modem_cfg[index].wwan_port_type;
+
+	return 0;
+}
diff --git a/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.h b/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.h
new file mode 100644
index 000000000000..422471367f78
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (C) 2020-21 Intel Corporation
+ */
+
+#ifndef IOSM_IPC_CHNL_CFG_H
+#define IOSM_IPC_CHNL_CFG_H
+
+#include "iosm_ipc_mux.h"
+
+/* Number of TDs on the trace channel */
+#define IPC_MEM_TDS_TRC 32
+
+/* Trace channel TD buffer size. */
+#define IPC_MEM_MAX_DL_TRC_BUF_SIZE 8192
+
+/* Channel ID */
+enum ipc_channel_id {
+	IPC_MEM_IP_CHL_ID_0 = 0,
+	IPC_MEM_CTRL_CHL_ID_1,
+	IPC_MEM_CTRL_CHL_ID_2,
+	IPC_MEM_CTRL_CHL_ID_3,
+	IPC_MEM_CTRL_CHL_ID_4,
+	IPC_MEM_CTRL_CHL_ID_5,
+	IPC_MEM_CTRL_CHL_ID_6,
+};
+
+/**
+ * struct ipc_chnl_cfg - IPC channel configuration structure
+ * @id:				Interface ID
+ * @ul_pipe:			Uplink datastream
+ * @dl_pipe:			Downlink datastream
+ * @ul_nr_of_entries:		Number of Transfer descriptor uplink pipe
+ * @dl_nr_of_entries:		Number of Transfer descriptor downlink pipe
+ * @dl_buf_size:		Downlink buffer size
+ * @wwan_port_type:		Wwan subsystem port type
+ * @accumulation_backoff:	Time in usec for data accumalation
+ */
+struct ipc_chnl_cfg {
+	u32 id;
+	u32 ul_pipe;
+	u32 dl_pipe;
+	u32 ul_nr_of_entries;
+	u32 dl_nr_of_entries;
+	u32 dl_buf_size;
+	u32 wwan_port_type;
+	u32 accumulation_backoff;
+};
+
+/**
+ * ipc_chnl_cfg_get - Get pipe configuration.
+ * @chnl_cfg:		Array of ipc_chnl_cfg struct
+ * @index:		Channel index (upto MAX_CHANNELS)
+ *
+ * Return: 0 on success and failure value on error
+ */
+int ipc_chnl_cfg_get(struct ipc_chnl_cfg *chnl_cfg, int index);
+
+#endif
diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.c b/drivers/net/wwan/iosm/iosm_ipc_imem.c
new file mode 100644
index 000000000000..9f00e36b7f79
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_imem.c
@@ -0,0 +1,1363 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#include <linux/delay.h>
+
+#include "iosm_ipc_chnl_cfg.h"
+#include "iosm_ipc_imem.h"
+#include "iosm_ipc_port.h"
+
+/* Check the wwan ips if it is valid with Channel as input. */
+static int ipc_imem_check_wwan_ips(struct ipc_mem_channel *chnl)
+{
+	if (chnl)
+		return chnl->ctype == IPC_CTYPE_WWAN &&
+		       chnl->if_id == IPC_MEM_MUX_IP_CH_IF_ID;
+	return false;
+}
+
+static int ipc_imem_msg_send_device_sleep(struct iosm_imem *ipc_imem, u32 state)
+{
+	union ipc_msg_prep_args prep_args = {
+		.sleep.target = 1,
+		.sleep.state = state,
+	};
+
+	ipc_imem->device_sleep = state;
+
+	return ipc_protocol_tq_msg_send(ipc_imem->ipc_protocol,
+					IPC_MSG_PREP_SLEEP, &prep_args, NULL);
+}
+
+static bool ipc_imem_dl_skb_alloc(struct iosm_imem *ipc_imem,
+				  struct ipc_pipe *pipe)
+{
+	/* limit max. nr of entries */
+	if (pipe->nr_of_queued_entries >= pipe->max_nr_of_queued_entries)
+		return false;
+
+	return ipc_protocol_dl_td_prepare(ipc_imem->ipc_protocol, pipe);
+}
+
+/* This timer handler will retry DL buff allocation if a pipe has no free buf
+ * and gives doorbell if TD is available
+ */
+static int ipc_imem_tq_td_alloc_timer(struct iosm_imem *ipc_imem, int arg,
+				      void *msg, size_t size)
+{
+	bool new_buffers_available = false;
+	bool retry_allocation = false;
+	int i;
+
+	for (i = 0; i < IPC_MEM_MAX_CHANNELS; i++) {
+		struct ipc_pipe *pipe = &ipc_imem->channels[i].dl_pipe;
+
+		if (!pipe->is_open || pipe->nr_of_queued_entries > 0)
+			continue;
+
+		while (ipc_imem_dl_skb_alloc(ipc_imem, pipe))
+			new_buffers_available = true;
+
+		if (pipe->nr_of_queued_entries == 0)
+			retry_allocation = true;
+	}
+
+	if (new_buffers_available)
+		ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol,
+					      IPC_HP_DL_PROCESS);
+
+	if (retry_allocation) {
+		ipc_imem->hrtimer_period =
+		ktime_set(0, IPC_TD_ALLOC_TIMER_PERIOD_MS * 1000 * 1000ULL);
+		if (!hrtimer_active(&ipc_imem->td_alloc_timer))
+			hrtimer_start(&ipc_imem->td_alloc_timer,
+				      ipc_imem->hrtimer_period,
+				      HRTIMER_MODE_REL);
+	}
+	return 0;
+}
+
+static enum hrtimer_restart ipc_imem_td_alloc_timer_cb(struct hrtimer *hr_timer)
+{
+	struct iosm_imem *ipc_imem =
+		container_of(hr_timer, struct iosm_imem, td_alloc_timer);
+	/* Post an async tasklet event to trigger HP update Doorbell */
+	ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_td_alloc_timer, 0, NULL,
+				 0, false);
+	return HRTIMER_NORESTART;
+}
+
+/* Fast update timer tasklet handler to trigger HP update */
+static int ipc_imem_tq_fast_update_timer_cb(struct iosm_imem *ipc_imem, int arg,
+					    void *msg, size_t size)
+{
+	ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol,
+				      IPC_HP_FAST_TD_UPD_TMR);
+
+	return 0;
+}
+
+static enum hrtimer_restart
+ipc_imem_fast_update_timer_cb(struct hrtimer *hr_timer)
+{
+	struct iosm_imem *ipc_imem =
+		container_of(hr_timer, struct iosm_imem, fast_update_timer);
+	/* Post an async tasklet event to trigger HP update Doorbell */
+	ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_fast_update_timer_cb, 0,
+				 NULL, 0, false);
+	return HRTIMER_NORESTART;
+}
+
+static int ipc_imem_setup_cp_mux_cap_init(struct iosm_imem *ipc_imem,
+					  struct ipc_mux_config *cfg)
+{
+	ipc_mmio_update_cp_capability(ipc_imem->mmio);
+
+	if (!ipc_imem->mmio->has_mux_lite) {
+		dev_err(ipc_imem->dev, "Failed to get Mux capability.");
+		return -EINVAL;
+	}
+
+	cfg->protocol = MUX_LITE;
+
+	cfg->ul_flow = (ipc_imem->mmio->has_ul_flow_credit == 1) ?
+			       MUX_UL_ON_CREDITS :
+			       MUX_UL;
+
+	/* The instance ID is same as channel ID because this is been reused
+	 * for channel alloc function.
+	 */
+	cfg->instance_id = IPC_MEM_MUX_IP_CH_IF_ID;
+	cfg->nr_sessions = IPC_MEM_MUX_IP_SESSION_ENTRIES;
+
+	return 0;
+}
+
+void ipc_imem_msg_send_feature_set(struct iosm_imem *ipc_imem,
+				   unsigned int reset_enable, bool atomic_ctx)
+{
+	union ipc_msg_prep_args prep_args = { .feature_set.reset_enable =
+						      reset_enable };
+
+	if (atomic_ctx)
+		ipc_protocol_tq_msg_send(ipc_imem->ipc_protocol,
+					 IPC_MSG_PREP_FEATURE_SET, &prep_args,
+					 NULL);
+	else
+		ipc_protocol_msg_send(ipc_imem->ipc_protocol,
+				      IPC_MSG_PREP_FEATURE_SET, &prep_args);
+}
+
+void ipc_imem_td_update_timer_start(struct iosm_imem *ipc_imem)
+{
+	/* Use the TD update timer only in the runtime phase */
+	if (!ipc_imem->enter_runtime || ipc_imem->td_update_timer_suspended) {
+		/* trigger the doorbell irq on CP directly. */
+		ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol,
+					      IPC_HP_TD_UPD_TMR_START);
+		return;
+	}
+
+	if (!hrtimer_active(&ipc_imem->tdupdate_timer)) {
+		ipc_imem->hrtimer_period =
+		ktime_set(0, TD_UPDATE_DEFAULT_TIMEOUT_USEC * 1000ULL);
+		if (!hrtimer_active(&ipc_imem->tdupdate_timer))
+			hrtimer_start(&ipc_imem->tdupdate_timer,
+				      ipc_imem->hrtimer_period,
+				      HRTIMER_MODE_REL);
+	}
+}
+
+void ipc_imem_hrtimer_stop(struct hrtimer *hr_timer)
+{
+	if (hrtimer_active(hr_timer))
+		hrtimer_cancel(hr_timer);
+}
+
+bool ipc_imem_ul_write_td(struct iosm_imem *ipc_imem)
+{
+	struct ipc_mem_channel *channel;
+	struct sk_buff_head *ul_list;
+	bool hpda_pending = false;
+	bool forced_hpdu = false;
+	struct ipc_pipe *pipe;
+	int i;
+
+	/* Analyze the uplink pipe of all active channels. */
+	for (i = 0; i < ipc_imem->nr_of_channels; i++) {
+		channel = &ipc_imem->channels[i];
+
+		if (channel->state != IMEM_CHANNEL_ACTIVE)
+			continue;
+
+		pipe = &channel->ul_pipe;
+
+		/* Get the reference to the skbuf accumulator list. */
+		ul_list = &channel->ul_list;
+
+		/* Fill the transfer descriptor with the uplink buffer info. */
+		hpda_pending |= ipc_protocol_ul_td_send(ipc_imem->ipc_protocol,
+							pipe, ul_list);
+
+		/* forced HP update needed for non data channels */
+		if (hpda_pending && !ipc_imem_check_wwan_ips(channel))
+			forced_hpdu = true;
+	}
+
+	if (forced_hpdu) {
+		hpda_pending = false;
+		ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol,
+					      IPC_HP_UL_WRITE_TD);
+	}
+
+	return hpda_pending;
+}
+
+void ipc_imem_ipc_init_check(struct iosm_imem *ipc_imem)
+{
+	int timeout = IPC_MODEM_BOOT_TIMEOUT;
+
+	ipc_imem->ipc_requested_state = IPC_MEM_DEVICE_IPC_INIT;
+
+	/* Trigger the CP interrupt to enter the init state. */
+	ipc_doorbell_fire(ipc_imem->pcie, IPC_DOORBELL_IRQ_IPC,
+			  IPC_MEM_DEVICE_IPC_INIT);
+	/* Wait for the CP update. */
+	do {
+		if (ipc_mmio_get_ipc_state(ipc_imem->mmio) ==
+		    ipc_imem->ipc_requested_state) {
+			/* Prepare the MMIO space */
+			ipc_mmio_config(ipc_imem->mmio);
+
+			/* Trigger the CP irq to enter the running state. */
+			ipc_imem->ipc_requested_state =
+				IPC_MEM_DEVICE_IPC_RUNNING;
+			ipc_doorbell_fire(ipc_imem->pcie, IPC_DOORBELL_IRQ_IPC,
+					  IPC_MEM_DEVICE_IPC_RUNNING);
+
+			return;
+		}
+		msleep(20);
+	} while (--timeout);
+
+	/* timeout */
+	dev_err(ipc_imem->dev, "%s: ipc_status(%d) ne. IPC_MEM_DEVICE_IPC_INIT",
+		ipc_imem_phase_get_string(ipc_imem->phase),
+		ipc_mmio_get_ipc_state(ipc_imem->mmio));
+
+	ipc_uevent_send(ipc_imem->dev, UEVENT_MDM_TIMEOUT);
+}
+
+/* Analyze the packet type and distribute it. */
+static void ipc_imem_dl_skb_process(struct iosm_imem *ipc_imem,
+				    struct ipc_pipe *pipe, struct sk_buff *skb)
+{
+	u16 port_id;
+
+	if (!skb)
+		return;
+
+	/* An AT/control or IP packet is expected. */
+	switch (pipe->channel->ctype) {
+	case IPC_CTYPE_CTRL:
+		port_id = pipe->channel->channel_id;
+
+		/* Pass the packet to the wwan layer. */
+		wwan_port_rx(ipc_imem->ipc_port[port_id]->iosm_port, skb);
+		break;
+
+	case IPC_CTYPE_WWAN:
+		if (pipe->channel->if_id == IPC_MEM_MUX_IP_CH_IF_ID)
+			ipc_mux_dl_decode(ipc_imem->mux, skb);
+		break;
+	default:
+		dev_err(ipc_imem->dev, "Invalid channel type");
+		break;
+	}
+}
+
+/* Process the downlink data and pass them to the char or net layer. */
+static void ipc_imem_dl_pipe_process(struct iosm_imem *ipc_imem,
+				     struct ipc_pipe *pipe)
+{
+	s32 cnt = 0, processed_td_cnt = 0;
+	struct ipc_mem_channel *channel;
+	u32 head = 0, tail = 0;
+	bool processed = false;
+	struct sk_buff *skb;
+
+	channel = pipe->channel;
+
+	ipc_protocol_get_head_tail_index(ipc_imem->ipc_protocol, pipe, &head,
+					 &tail);
+	if (pipe->old_tail != tail) {
+		if (pipe->old_tail < tail)
+			cnt = tail - pipe->old_tail;
+		else
+			cnt = pipe->nr_of_entries - pipe->old_tail + tail;
+	}
+
+	processed_td_cnt = cnt;
+
+	/* Seek for pipes with pending DL data. */
+	while (cnt--) {
+		skb = ipc_protocol_dl_td_process(ipc_imem->ipc_protocol, pipe);
+
+		/* Analyze the packet type and distribute it. */
+		ipc_imem_dl_skb_process(ipc_imem, pipe, skb);
+	}
+
+	/* try to allocate new empty DL SKbs from head..tail - 1*/
+	while (ipc_imem_dl_skb_alloc(ipc_imem, pipe))
+		processed = true;
+
+	if (processed && !ipc_imem_check_wwan_ips(channel)) {
+		/* Force HP update for non IP channels */
+		ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol,
+					      IPC_HP_DL_PROCESS);
+		processed = false;
+
+		/* If Fast Update timer is already running then stop */
+		ipc_imem_hrtimer_stop(&ipc_imem->fast_update_timer);
+	}
+
+	/* Any control channel process will get immediate HP update.
+	 * Start Fast update timer only for IP channel if all the TDs were
+	 * used in last process.
+	 */
+	if (processed && (processed_td_cnt == pipe->nr_of_entries - 1)) {
+		ipc_imem->hrtimer_period =
+		ktime_set(0, FORCE_UPDATE_DEFAULT_TIMEOUT_USEC * 1000ULL);
+		hrtimer_start(&ipc_imem->fast_update_timer,
+			      ipc_imem->hrtimer_period, HRTIMER_MODE_REL);
+	}
+
+	if (ipc_imem->app_notify_dl_pend)
+		complete(&ipc_imem->dl_pend_sem);
+}
+
+/* process open uplink pipe */
+static void ipc_imem_ul_pipe_process(struct iosm_imem *ipc_imem,
+				     struct ipc_pipe *pipe)
+{
+	struct ipc_mem_channel *channel;
+	u32 tail = 0, head = 0;
+	struct sk_buff *skb;
+	s32 cnt = 0;
+
+	channel = pipe->channel;
+
+	/* Get the internal phase. */
+	ipc_protocol_get_head_tail_index(ipc_imem->ipc_protocol, pipe, &head,
+					 &tail);
+
+	if (pipe->old_tail != tail) {
+		if (pipe->old_tail < tail)
+			cnt = tail - pipe->old_tail;
+		else
+			cnt = pipe->nr_of_entries - pipe->old_tail + tail;
+	}
+
+	/* Free UL buffers. */
+	while (cnt--) {
+		skb = ipc_protocol_ul_td_process(ipc_imem->ipc_protocol, pipe);
+
+		if (!skb)
+			continue;
+
+		/* If the user app was suspended in uplink direction - blocking
+		 * write, resume it.
+		 */
+		if (IPC_CB(skb)->op_type == UL_USR_OP_BLOCKED)
+			complete(&channel->ul_sem);
+
+		/* Free the skbuf element. */
+		if (IPC_CB(skb)->op_type == UL_MUX_OP_ADB) {
+			if (channel->if_id == IPC_MEM_MUX_IP_CH_IF_ID)
+				ipc_mux_ul_encoded_process(ipc_imem->mux, skb);
+			else
+				dev_err(ipc_imem->dev,
+					"OP Type is UL_MUX, unknown if_id %d",
+					channel->if_id);
+		} else {
+			ipc_pcie_kfree_skb(ipc_imem->pcie, skb);
+		}
+	}
+
+	/* Trace channel stats for IP UL pipe. */
+	if (ipc_imem_check_wwan_ips(pipe->channel))
+		ipc_mux_check_n_restart_tx(ipc_imem->mux);
+
+	if (ipc_imem->app_notify_ul_pend)
+		complete(&ipc_imem->ul_pend_sem);
+}
+
+/* Executes the irq. */
+static void ipc_imem_rom_irq_exec(struct iosm_imem *ipc_imem)
+{
+	struct ipc_mem_channel *channel;
+
+	if (ipc_imem->flash_channel_id < 0) {
+		ipc_imem->rom_exit_code = IMEM_ROM_EXIT_FAIL;
+		dev_err(ipc_imem->dev, "Missing flash app:%d",
+			ipc_imem->flash_channel_id);
+		return;
+	}
+
+	ipc_imem->rom_exit_code = ipc_mmio_get_rom_exit_code(ipc_imem->mmio);
+
+	/* Wake up the flash app to continue or to terminate depending
+	 * on the CP ROM exit code.
+	 */
+	channel = &ipc_imem->channels[ipc_imem->flash_channel_id];
+	complete(&channel->ul_sem);
+}
+
+/* Execute the UL bundle timer actions, generating the doorbell irq. */
+static int ipc_imem_tq_td_update_timer_cb(struct iosm_imem *ipc_imem, int arg,
+					  void *msg, size_t size)
+{
+	ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol,
+				      IPC_HP_TD_UPD_TMR);
+	return 0;
+}
+
+/* Consider link power management in the runtime phase. */
+static void ipc_imem_slp_control_exec(struct iosm_imem *ipc_imem)
+{
+	    /* link will go down, Test pending UL packets.*/
+	if (ipc_protocol_pm_dev_sleep_handle(ipc_imem->ipc_protocol) &&
+	    hrtimer_active(&ipc_imem->tdupdate_timer)) {
+		/* Generate the doorbell irq. */
+		ipc_imem_tq_td_update_timer_cb(ipc_imem, 0, NULL, 0);
+		/* Stop the TD update timer. */
+		ipc_imem_hrtimer_stop(&ipc_imem->tdupdate_timer);
+		/* Stop the fast update timer. */
+		ipc_imem_hrtimer_stop(&ipc_imem->fast_update_timer);
+	}
+}
+
+/* Execute startup timer and wait for delayed start (e.g. NAND) */
+static int ipc_imem_tq_startup_timer_cb(struct iosm_imem *ipc_imem, int arg,
+					void *msg, size_t size)
+{
+	/* Update & check the current operation phase. */
+	if (ipc_imem_phase_update(ipc_imem) != IPC_P_RUN)
+		return -EIO;
+
+	if (ipc_mmio_get_ipc_state(ipc_imem->mmio) ==
+	    IPC_MEM_DEVICE_IPC_UNINIT) {
+		ipc_imem->ipc_requested_state = IPC_MEM_DEVICE_IPC_INIT;
+
+		ipc_doorbell_fire(ipc_imem->pcie, IPC_DOORBELL_IRQ_IPC,
+				  IPC_MEM_DEVICE_IPC_INIT);
+
+		ipc_imem->hrtimer_period = ktime_set(0, 100 * 1000UL * 1000ULL);
+		/* reduce period to 100 ms to check for mmio init state */
+		if (!hrtimer_active(&ipc_imem->startup_timer))
+			hrtimer_start(&ipc_imem->startup_timer,
+				      ipc_imem->hrtimer_period,
+				      HRTIMER_MODE_REL);
+	} else if (ipc_mmio_get_ipc_state(ipc_imem->mmio) ==
+		   IPC_MEM_DEVICE_IPC_INIT) {
+		/* Startup complete  - disable timer */
+		ipc_imem_hrtimer_stop(&ipc_imem->startup_timer);
+
+		/* Prepare the MMIO space */
+		ipc_mmio_config(ipc_imem->mmio);
+		ipc_imem->ipc_requested_state = IPC_MEM_DEVICE_IPC_RUNNING;
+		ipc_doorbell_fire(ipc_imem->pcie, IPC_DOORBELL_IRQ_IPC,
+				  IPC_MEM_DEVICE_IPC_RUNNING);
+	}
+
+	return 0;
+}
+
+static enum hrtimer_restart ipc_imem_startup_timer_cb(struct hrtimer *hr_timer)
+{
+	enum hrtimer_restart result = HRTIMER_NORESTART;
+	struct iosm_imem *ipc_imem =
+		container_of(hr_timer, struct iosm_imem, startup_timer);
+
+	if (ktime_to_ns(ipc_imem->hrtimer_period)) {
+		hrtimer_forward(&ipc_imem->startup_timer, ktime_get(),
+				ipc_imem->hrtimer_period);
+		result = HRTIMER_RESTART;
+	}
+
+	ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_startup_timer_cb, 0,
+				 NULL, 0, false);
+	return result;
+}
+
+/* Get the CP execution stage */
+static enum ipc_mem_exec_stage
+ipc_imem_get_exec_stage_buffered(struct iosm_imem *ipc_imem)
+{
+	return (ipc_imem->phase == IPC_P_RUN &&
+		ipc_imem->ipc_status == IPC_MEM_DEVICE_IPC_RUNNING) ?
+		       ipc_protocol_get_ap_exec_stage(ipc_imem->ipc_protocol) :
+		       ipc_mmio_get_exec_stage(ipc_imem->mmio);
+}
+
+/* Callback to send the modem ready uevent */
+static int ipc_imem_send_mdm_rdy_cb(struct iosm_imem *ipc_imem, int arg,
+				    void *msg, size_t size)
+{
+	enum ipc_mem_exec_stage exec_stage =
+		ipc_imem_get_exec_stage_buffered(ipc_imem);
+
+	if (exec_stage == IPC_MEM_EXEC_STAGE_RUN)
+		ipc_uevent_send(ipc_imem->dev, UEVENT_MDM_READY);
+
+	return 0;
+}
+
+/* This function is executed in a task context via an ipc_worker object,
+ * as the creation or removal of device can't be done from tasklet.
+ */
+static void ipc_imem_run_state_worker(struct work_struct *instance)
+{
+	struct ipc_chnl_cfg chnl_cfg_port = { 0 };
+	struct ipc_mux_config mux_cfg;
+	struct iosm_imem *ipc_imem;
+	u8 ctrl_chl_idx = 0;
+
+	ipc_imem = container_of(instance, struct iosm_imem, run_state_worker);
+
+	if (ipc_imem->phase != IPC_P_RUN) {
+		dev_err(ipc_imem->dev,
+			"Modem link down. Exit run state worker.");
+		return;
+	}
+
+	if (!ipc_imem_setup_cp_mux_cap_init(ipc_imem, &mux_cfg))
+		ipc_imem->mux = ipc_mux_init(&mux_cfg, ipc_imem);
+
+	ipc_imem_wwan_channel_init(ipc_imem, mux_cfg.protocol);
+	if (ipc_imem->mux)
+		ipc_imem->mux->wwan = ipc_imem->wwan;
+
+	while (ctrl_chl_idx < IPC_MEM_MAX_CHANNELS) {
+		if (!ipc_chnl_cfg_get(&chnl_cfg_port, ctrl_chl_idx)) {
+			ipc_imem->ipc_port[ctrl_chl_idx] = NULL;
+			if (chnl_cfg_port.wwan_port_type != WWAN_PORT_UNKNOWN) {
+				ipc_imem_channel_init(ipc_imem, IPC_CTYPE_CTRL,
+						      chnl_cfg_port,
+						      IRQ_MOD_OFF);
+				ipc_imem->ipc_port[ctrl_chl_idx] =
+					ipc_port_init(ipc_imem, chnl_cfg_port);
+			}
+		}
+		ctrl_chl_idx++;
+	}
+
+	ipc_task_queue_send_task(ipc_imem, ipc_imem_send_mdm_rdy_cb, 0, NULL, 0,
+				 false);
+
+	/* Complete all memory stores before setting bit */
+	smp_mb__before_atomic();
+
+	set_bit(FULLY_FUNCTIONAL, &ipc_imem->flag);
+
+	/* Complete all memory stores after setting bit */
+	smp_mb__after_atomic();
+}
+
+static void ipc_imem_handle_irq(struct iosm_imem *ipc_imem, int irq)
+{
+	enum ipc_mem_device_ipc_state curr_ipc_status;
+	enum ipc_phase old_phase, phase;
+	bool retry_allocation = false;
+	bool ul_pending = false;
+	int ch_id, i;
+
+	if (irq != IMEM_IRQ_DONT_CARE)
+		ipc_imem->ev_irq_pending[irq] = false;
+
+	/* Get the internal phase. */
+	old_phase = ipc_imem->phase;
+
+	if (old_phase == IPC_P_OFF_REQ) {
+		dev_dbg(ipc_imem->dev,
+			"[%s]: Ignoring MSI. Deinit sequence in progress!",
+			ipc_imem_phase_get_string(old_phase));
+		return;
+	}
+
+	/* Update the phase controlled by CP. */
+	phase = ipc_imem_phase_update(ipc_imem);
+
+	switch (phase) {
+	case IPC_P_RUN:
+		if (!ipc_imem->enter_runtime) {
+			/* Excute the transition from flash/boot to runtime. */
+			ipc_imem->enter_runtime = 1;
+
+			/* allow device to sleep, default value is
+			 * IPC_HOST_SLEEP_ENTER_SLEEP
+			 */
+			ipc_imem_msg_send_device_sleep(ipc_imem,
+						       ipc_imem->device_sleep);
+
+			ipc_imem_msg_send_feature_set(ipc_imem,
+						      IPC_MEM_INBAND_CRASH_SIG,
+						  true);
+		}
+
+		curr_ipc_status =
+			ipc_protocol_get_ipc_status(ipc_imem->ipc_protocol);
+
+		/* check ipc_status change */
+		if (ipc_imem->ipc_status != curr_ipc_status) {
+			ipc_imem->ipc_status = curr_ipc_status;
+
+			if (ipc_imem->ipc_status ==
+			    IPC_MEM_DEVICE_IPC_RUNNING) {
+				schedule_work(&ipc_imem->run_state_worker);
+			}
+		}
+
+		/* Consider power management in the runtime phase. */
+		ipc_imem_slp_control_exec(ipc_imem);
+		break; /* Continue with skbuf processing. */
+
+		/* Unexpected phases. */
+	case IPC_P_OFF:
+	case IPC_P_OFF_REQ:
+		dev_err(ipc_imem->dev, "confused phase %s",
+			ipc_imem_phase_get_string(phase));
+		return;
+
+	case IPC_P_PSI:
+		if (old_phase != IPC_P_ROM)
+			break;
+
+		fallthrough;
+		/* On CP the PSI phase is already active. */
+
+	case IPC_P_ROM:
+		/* Before CP ROM driver starts the PSI image, it sets
+		 * the exit_code field on the doorbell scratchpad and
+		 * triggers the irq.
+		 */
+		ipc_imem_rom_irq_exec(ipc_imem);
+		return;
+
+	default:
+		break;
+	}
+
+	/* process message ring */
+	ipc_protocol_msg_process(ipc_imem, irq);
+
+	/* process all open pipes */
+	for (i = 0; i < IPC_MEM_MAX_CHANNELS; i++) {
+		struct ipc_pipe *ul_pipe = &ipc_imem->channels[i].ul_pipe;
+		struct ipc_pipe *dl_pipe = &ipc_imem->channels[i].dl_pipe;
+
+		if (dl_pipe->is_open &&
+		    (irq == IMEM_IRQ_DONT_CARE || irq == dl_pipe->irq)) {
+			ipc_imem_dl_pipe_process(ipc_imem, dl_pipe);
+
+			if (dl_pipe->nr_of_queued_entries == 0)
+				retry_allocation = true;
+		}
+
+		if (ul_pipe->is_open)
+			ipc_imem_ul_pipe_process(ipc_imem, ul_pipe);
+	}
+
+	/* Try to generate new ADB or ADGH. */
+	if (ipc_mux_ul_data_encode(ipc_imem->mux))
+		ipc_imem_td_update_timer_start(ipc_imem);
+
+	/* Continue the send procedure with accumulated SIO or NETIF packets.
+	 * Reset the debounce flags.
+	 */
+	ul_pending |= ipc_imem_ul_write_td(ipc_imem);
+
+	/* if UL data is pending restart TD update timer */
+	if (ul_pending) {
+		ipc_imem->hrtimer_period =
+		ktime_set(0, TD_UPDATE_DEFAULT_TIMEOUT_USEC * 1000ULL);
+		if (!hrtimer_active(&ipc_imem->tdupdate_timer))
+			hrtimer_start(&ipc_imem->tdupdate_timer,
+				      ipc_imem->hrtimer_period,
+				      HRTIMER_MODE_REL);
+	}
+
+	/* If CP has executed the transition
+	 * from IPC_INIT to IPC_RUNNING in the PSI
+	 * phase, wake up the flash app to open the pipes.
+	 */
+	if ((phase == IPC_P_PSI || phase == IPC_P_EBL) &&
+	    ipc_imem->ipc_requested_state == IPC_MEM_DEVICE_IPC_RUNNING &&
+	    ipc_mmio_get_ipc_state(ipc_imem->mmio) ==
+		    IPC_MEM_DEVICE_IPC_RUNNING &&
+	    ipc_imem->flash_channel_id >= 0) {
+		/* Wake up the flash app to open the pipes. */
+		ch_id = ipc_imem->flash_channel_id;
+		complete(&ipc_imem->channels[ch_id].ul_sem);
+	}
+
+	/* Reset the expected CP state. */
+	ipc_imem->ipc_requested_state = IPC_MEM_DEVICE_IPC_DONT_CARE;
+
+	if (retry_allocation) {
+		ipc_imem->hrtimer_period =
+		ktime_set(0, IPC_TD_ALLOC_TIMER_PERIOD_MS * 1000 * 1000ULL);
+		if (!hrtimer_active(&ipc_imem->td_alloc_timer))
+			hrtimer_start(&ipc_imem->td_alloc_timer,
+				      ipc_imem->hrtimer_period,
+				      HRTIMER_MODE_REL);
+	}
+}
+
+/* Callback by tasklet for handling interrupt events. */
+static int ipc_imem_tq_irq_cb(struct iosm_imem *ipc_imem, int arg, void *msg,
+			      size_t size)
+{
+	ipc_imem_handle_irq(ipc_imem, arg);
+
+	return 0;
+}
+
+void ipc_imem_ul_send(struct iosm_imem *ipc_imem)
+{
+	/* start doorbell irq delay timer if UL is pending */
+	if (ipc_imem_ul_write_td(ipc_imem))
+		ipc_imem_td_update_timer_start(ipc_imem);
+}
+
+/* Check the execution stage and update the AP phase */
+static enum ipc_phase ipc_imem_phase_update_check(struct iosm_imem *ipc_imem,
+						  enum ipc_mem_exec_stage stage)
+{
+	switch (stage) {
+	case IPC_MEM_EXEC_STAGE_BOOT:
+		if (ipc_imem->phase != IPC_P_ROM) {
+			/* Send this event only once */
+			ipc_uevent_send(ipc_imem->dev, UEVENT_ROM_READY);
+		}
+
+		ipc_imem->phase = IPC_P_ROM;
+		break;
+
+	case IPC_MEM_EXEC_STAGE_PSI:
+		ipc_imem->phase = IPC_P_PSI;
+		break;
+
+	case IPC_MEM_EXEC_STAGE_EBL:
+		ipc_imem->phase = IPC_P_EBL;
+		break;
+
+	case IPC_MEM_EXEC_STAGE_RUN:
+		if (ipc_imem->phase != IPC_P_RUN &&
+		    ipc_imem->ipc_status == IPC_MEM_DEVICE_IPC_RUNNING) {
+			ipc_uevent_send(ipc_imem->dev, UEVENT_MDM_READY);
+		}
+		ipc_imem->phase = IPC_P_RUN;
+		break;
+
+	case IPC_MEM_EXEC_STAGE_CRASH:
+		if (ipc_imem->phase != IPC_P_CRASH)
+			ipc_uevent_send(ipc_imem->dev, UEVENT_CRASH);
+
+		ipc_imem->phase = IPC_P_CRASH;
+		break;
+
+	case IPC_MEM_EXEC_STAGE_CD_READY:
+		if (ipc_imem->phase != IPC_P_CD_READY)
+			ipc_uevent_send(ipc_imem->dev, UEVENT_CD_READY);
+		ipc_imem->phase = IPC_P_CD_READY;
+		break;
+
+	default:
+		/* unknown exec stage:
+		 * assume that link is down and send info to listeners
+		 */
+		ipc_uevent_send(ipc_imem->dev, UEVENT_CD_READY_LINK_DOWN);
+		break;
+	}
+
+	return ipc_imem->phase;
+}
+
+/* Send msg to device to open pipe */
+static bool ipc_imem_pipe_open(struct iosm_imem *ipc_imem,
+			       struct ipc_pipe *pipe)
+{
+	union ipc_msg_prep_args prep_args = {
+		.pipe_open.pipe = pipe,
+	};
+
+	if (ipc_protocol_msg_send(ipc_imem->ipc_protocol,
+				  IPC_MSG_PREP_PIPE_OPEN, &prep_args) == 0)
+		pipe->is_open = true;
+
+	return pipe->is_open;
+}
+
+/* Allocates the TDs for the given pipe along with firing HP update DB. */
+static int ipc_imem_tq_pipe_td_alloc(struct iosm_imem *ipc_imem, int arg,
+				     void *msg, size_t size)
+{
+	struct ipc_pipe *dl_pipe = msg;
+	bool processed = false;
+	int i;
+
+	for (i = 0; i < dl_pipe->nr_of_entries - 1; i++)
+		processed |= ipc_imem_dl_skb_alloc(ipc_imem, dl_pipe);
+
+	/* Trigger the doorbell irq to inform CP that new downlink buffers are
+	 * available.
+	 */
+	if (processed)
+		ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol, arg);
+
+	return 0;
+}
+
+static enum hrtimer_restart
+ipc_imem_td_update_timer_cb(struct hrtimer *hr_timer)
+{
+	struct iosm_imem *ipc_imem =
+		container_of(hr_timer, struct iosm_imem, tdupdate_timer);
+
+	ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_td_update_timer_cb, 0,
+				 NULL, 0, false);
+	return HRTIMER_NORESTART;
+}
+
+/* Get the CP execution state and map it to the AP phase. */
+enum ipc_phase ipc_imem_phase_update(struct iosm_imem *ipc_imem)
+{
+	enum ipc_mem_exec_stage exec_stage =
+				ipc_imem_get_exec_stage_buffered(ipc_imem);
+	/* If the CP stage is undef, return the internal precalculated phase. */
+	return ipc_imem->phase == IPC_P_OFF_REQ ?
+		       ipc_imem->phase :
+		       ipc_imem_phase_update_check(ipc_imem, exec_stage);
+}
+
+const char *ipc_imem_phase_get_string(enum ipc_phase phase)
+{
+	switch (phase) {
+	case IPC_P_RUN:
+		return "A-RUN";
+
+	case IPC_P_OFF:
+		return "A-OFF";
+
+	case IPC_P_ROM:
+		return "A-ROM";
+
+	case IPC_P_PSI:
+		return "A-PSI";
+
+	case IPC_P_EBL:
+		return "A-EBL";
+
+	case IPC_P_CRASH:
+		return "A-CRASH";
+
+	case IPC_P_CD_READY:
+		return "A-CD_READY";
+
+	case IPC_P_OFF_REQ:
+		return "A-OFF_REQ";
+
+	default:
+		return "A-???";
+	}
+}
+
+void ipc_imem_pipe_close(struct iosm_imem *ipc_imem, struct ipc_pipe *pipe)
+{
+	union ipc_msg_prep_args prep_args = { .pipe_close.pipe = pipe };
+
+	pipe->is_open = false;
+	ipc_protocol_msg_send(ipc_imem->ipc_protocol, IPC_MSG_PREP_PIPE_CLOSE,
+			      &prep_args);
+
+	ipc_imem_pipe_cleanup(ipc_imem, pipe);
+}
+
+void ipc_imem_channel_close(struct iosm_imem *ipc_imem, int channel_id)
+{
+	struct ipc_mem_channel *channel;
+
+	if (channel_id < 0 || channel_id >= ipc_imem->nr_of_channels) {
+		dev_err(ipc_imem->dev, "invalid channel id %d", channel_id);
+		return;
+	}
+
+	channel = &ipc_imem->channels[channel_id];
+
+	if (channel->state == IMEM_CHANNEL_FREE) {
+		dev_err(ipc_imem->dev, "ch[%d]: invalid channel state %d",
+			channel_id, channel->state);
+		return;
+	}
+
+	/* Free only the channel id in the CP power off mode. */
+	if (channel->state == IMEM_CHANNEL_RESERVED)
+		/* Release only the channel id. */
+		goto channel_free;
+
+	if (ipc_imem->phase == IPC_P_RUN) {
+		ipc_imem_pipe_close(ipc_imem, &channel->ul_pipe);
+		ipc_imem_pipe_close(ipc_imem, &channel->dl_pipe);
+	}
+
+	ipc_imem_pipe_cleanup(ipc_imem, &channel->ul_pipe);
+	ipc_imem_pipe_cleanup(ipc_imem, &channel->dl_pipe);
+
+channel_free:
+	ipc_imem_channel_free(channel);
+}
+
+struct ipc_mem_channel *ipc_imem_channel_open(struct iosm_imem *ipc_imem,
+					      int channel_id, u32 db_id)
+{
+	struct ipc_mem_channel *channel;
+
+	if (channel_id < 0 || channel_id >= IPC_MEM_MAX_CHANNELS) {
+		dev_err(ipc_imem->dev, "invalid channel ID: %d", channel_id);
+		return NULL;
+	}
+
+	channel = &ipc_imem->channels[channel_id];
+
+	channel->state = IMEM_CHANNEL_ACTIVE;
+
+	if (!ipc_imem_pipe_open(ipc_imem, &channel->ul_pipe))
+		goto ul_pipe_err;
+
+	if (!ipc_imem_pipe_open(ipc_imem, &channel->dl_pipe))
+		goto dl_pipe_err;
+
+	/* Allocate the downlink buffers in tasklet context. */
+	if (ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_pipe_td_alloc, db_id,
+				     &channel->dl_pipe, 0, false)) {
+		dev_err(ipc_imem->dev, "td allocation failed : %d", channel_id);
+		goto task_failed;
+	}
+
+	/* Active channel. */
+	return channel;
+task_failed:
+	ipc_imem_pipe_close(ipc_imem, &channel->dl_pipe);
+dl_pipe_err:
+	ipc_imem_pipe_close(ipc_imem, &channel->ul_pipe);
+ul_pipe_err:
+	ipc_imem_channel_free(channel);
+	return NULL;
+}
+
+void ipc_imem_pm_suspend(struct iosm_imem *ipc_imem)
+{
+	ipc_protocol_suspend(ipc_imem->ipc_protocol);
+}
+
+void ipc_imem_pm_s2idle_sleep(struct iosm_imem *ipc_imem, bool sleep)
+{
+	ipc_protocol_s2idle_sleep(ipc_imem->ipc_protocol, sleep);
+}
+
+void ipc_imem_pm_resume(struct iosm_imem *ipc_imem)
+{
+	enum ipc_mem_exec_stage stage;
+
+	if (ipc_protocol_resume(ipc_imem->ipc_protocol)) {
+		stage = ipc_mmio_get_exec_stage(ipc_imem->mmio);
+		ipc_imem_phase_update_check(ipc_imem, stage);
+	}
+}
+
+void ipc_imem_channel_free(struct ipc_mem_channel *channel)
+{
+	/* Reset dynamic channel elements. */
+	channel->state = IMEM_CHANNEL_FREE;
+}
+
+int ipc_imem_channel_alloc(struct iosm_imem *ipc_imem, int index,
+			   enum ipc_ctype ctype)
+{
+	struct ipc_mem_channel *channel;
+	int i;
+
+	/* Find channel of given type/index */
+	for (i = 0; i < ipc_imem->nr_of_channels; i++) {
+		channel = &ipc_imem->channels[i];
+		if (channel->ctype == ctype && channel->index == index)
+			break;
+	}
+
+	if (i >= ipc_imem->nr_of_channels) {
+		dev_dbg(ipc_imem->dev,
+			"no channel definition for index=%d ctype=%d", index,
+			ctype);
+		return -ECHRNG;
+	}
+
+	if (ipc_imem->channels[i].state != IMEM_CHANNEL_FREE) {
+		dev_dbg(ipc_imem->dev, "channel is in use");
+		return -EBUSY;
+	}
+
+	if (channel->ctype == IPC_CTYPE_WWAN &&
+	    index == IPC_MEM_MUX_IP_CH_IF_ID)
+		channel->if_id = index;
+
+	channel->channel_id = index;
+	channel->state = IMEM_CHANNEL_RESERVED;
+
+	return i;
+}
+
+void ipc_imem_channel_init(struct iosm_imem *ipc_imem, enum ipc_ctype ctype,
+			   struct ipc_chnl_cfg chnl_cfg, u32 irq_moderation)
+{
+	struct ipc_mem_channel *channel;
+
+	if (chnl_cfg.ul_pipe >= IPC_MEM_MAX_PIPES ||
+	    chnl_cfg.dl_pipe >= IPC_MEM_MAX_PIPES) {
+		dev_err(ipc_imem->dev, "invalid pipe: ul_pipe=%d, dl_pipe=%d",
+			chnl_cfg.ul_pipe, chnl_cfg.dl_pipe);
+		return;
+	}
+
+	if (ipc_imem->nr_of_channels >= IPC_MEM_MAX_CHANNELS) {
+		dev_err(ipc_imem->dev, "too many channels");
+		return;
+	}
+
+	channel = &ipc_imem->channels[ipc_imem->nr_of_channels];
+	channel->channel_id = ipc_imem->nr_of_channels;
+	channel->ctype = ctype;
+	channel->index = chnl_cfg.id;
+	channel->net_err_count = 0;
+	channel->state = IMEM_CHANNEL_FREE;
+	ipc_imem->nr_of_channels++;
+
+	ipc_imem_channel_update(ipc_imem, channel->channel_id, chnl_cfg,
+				IRQ_MOD_OFF);
+
+	skb_queue_head_init(&channel->ul_list);
+
+	init_completion(&channel->ul_sem);
+}
+
+void ipc_imem_channel_update(struct iosm_imem *ipc_imem, int id,
+			     struct ipc_chnl_cfg chnl_cfg, u32 irq_moderation)
+{
+	struct ipc_mem_channel *channel;
+
+	if (id < 0 || id >= ipc_imem->nr_of_channels) {
+		dev_err(ipc_imem->dev, "invalid channel id %d", id);
+		return;
+	}
+
+	channel = &ipc_imem->channels[id];
+
+	if (channel->state != IMEM_CHANNEL_FREE &&
+	    channel->state != IMEM_CHANNEL_RESERVED) {
+		dev_err(ipc_imem->dev, "invalid channel state %d",
+			channel->state);
+		return;
+	}
+
+	channel->ul_pipe.nr_of_entries = chnl_cfg.ul_nr_of_entries;
+	channel->ul_pipe.pipe_nr = chnl_cfg.ul_pipe;
+	channel->ul_pipe.is_open = false;
+	channel->ul_pipe.irq = IPC_UL_PIPE_IRQ_VECTOR;
+	channel->ul_pipe.channel = channel;
+	channel->ul_pipe.dir = IPC_MEM_DIR_UL;
+	channel->ul_pipe.accumulation_backoff = chnl_cfg.accumulation_backoff;
+	channel->ul_pipe.irq_moderation = irq_moderation;
+	channel->ul_pipe.buf_size = 0;
+
+	channel->dl_pipe.nr_of_entries = chnl_cfg.dl_nr_of_entries;
+	channel->dl_pipe.pipe_nr = chnl_cfg.dl_pipe;
+	channel->dl_pipe.is_open = false;
+	channel->dl_pipe.irq = IPC_DL_PIPE_IRQ_VECTOR;
+	channel->dl_pipe.channel = channel;
+	channel->dl_pipe.dir = IPC_MEM_DIR_DL;
+	channel->dl_pipe.accumulation_backoff = chnl_cfg.accumulation_backoff;
+	channel->dl_pipe.irq_moderation = irq_moderation;
+	channel->dl_pipe.buf_size = chnl_cfg.dl_buf_size;
+}
+
+static void ipc_imem_channel_reset(struct iosm_imem *ipc_imem)
+{
+	int i;
+
+	for (i = 0; i < ipc_imem->nr_of_channels; i++) {
+		struct ipc_mem_channel *channel;
+
+		channel = &ipc_imem->channels[i];
+
+		ipc_imem_pipe_cleanup(ipc_imem, &channel->dl_pipe);
+		ipc_imem_pipe_cleanup(ipc_imem, &channel->ul_pipe);
+
+		ipc_imem_channel_free(channel);
+	}
+}
+
+void ipc_imem_pipe_cleanup(struct iosm_imem *ipc_imem, struct ipc_pipe *pipe)
+{
+	struct sk_buff *skb;
+
+	/* Force pipe to closed state also when not explicitly closed through
+	 * ipc_imem_pipe_close()
+	 */
+	pipe->is_open = false;
+
+	/* Empty the uplink skb accumulator. */
+	while ((skb = skb_dequeue(&pipe->channel->ul_list)))
+		ipc_pcie_kfree_skb(ipc_imem->pcie, skb);
+
+	ipc_protocol_pipe_cleanup(ipc_imem->ipc_protocol, pipe);
+}
+
+/* Send IPC protocol uninit to the modem when Link is active. */
+static void ipc_imem_device_ipc_uninit(struct iosm_imem *ipc_imem)
+{
+	int timeout = IPC_MODEM_UNINIT_TIMEOUT_MS;
+	enum ipc_mem_device_ipc_state ipc_state;
+
+	/* When PCIe link is up set IPC_UNINIT
+	 * of the modem otherwise ignore it when PCIe link down happens.
+	 */
+	if (ipc_pcie_check_data_link_active(ipc_imem->pcie)) {
+		/* set modem to UNINIT
+		 * (in case we want to reload the AP driver without resetting
+		 * the modem)
+		 */
+		ipc_doorbell_fire(ipc_imem->pcie, IPC_DOORBELL_IRQ_IPC,
+				  IPC_MEM_DEVICE_IPC_UNINIT);
+		ipc_state = ipc_mmio_get_ipc_state(ipc_imem->mmio);
+
+		/* Wait for maximum 30ms to allow the Modem to uninitialize the
+		 * protocol.
+		 */
+		while ((ipc_state <= IPC_MEM_DEVICE_IPC_DONT_CARE) &&
+		       (ipc_state != IPC_MEM_DEVICE_IPC_UNINIT) &&
+		       (timeout > 0)) {
+			usleep_range(1000, 1250);
+			timeout--;
+			ipc_state = ipc_mmio_get_ipc_state(ipc_imem->mmio);
+		}
+	}
+}
+
+void ipc_imem_cleanup(struct iosm_imem *ipc_imem)
+{
+	ipc_imem->phase = IPC_P_OFF_REQ;
+
+	/* forward MDM_NOT_READY to listeners */
+	ipc_uevent_send(ipc_imem->dev, UEVENT_MDM_NOT_READY);
+
+	hrtimer_cancel(&ipc_imem->td_alloc_timer);
+	hrtimer_cancel(&ipc_imem->tdupdate_timer);
+	hrtimer_cancel(&ipc_imem->fast_update_timer);
+	hrtimer_cancel(&ipc_imem->startup_timer);
+
+	/* cancel the workqueue */
+	cancel_work_sync(&ipc_imem->run_state_worker);
+
+	if (test_and_clear_bit(FULLY_FUNCTIONAL, &ipc_imem->flag)) {
+		ipc_mux_deinit(ipc_imem->mux);
+		ipc_wwan_deinit(ipc_imem->wwan);
+		ipc_port_deinit(ipc_imem->ipc_port);
+	}
+
+	ipc_imem_device_ipc_uninit(ipc_imem);
+	ipc_imem_channel_reset(ipc_imem);
+
+	ipc_protocol_deinit(ipc_imem->ipc_protocol);
+	ipc_task_deinit(ipc_imem->ipc_task);
+
+	kfree(ipc_imem->ipc_task);
+	kfree(ipc_imem->mmio);
+
+	ipc_imem->phase = IPC_P_OFF;
+}
+
+/* After CP has unblocked the PCIe link, save the start address of the doorbell
+ * scratchpad and prepare the shared memory region. If the flashing to RAM
+ * procedure shall be executed, copy the chip information from the doorbell
+ * scratchtpad to the application buffer and wake up the flash app.
+ */
+static int ipc_imem_config(struct iosm_imem *ipc_imem)
+{
+	enum ipc_phase phase;
+
+	/* Initialize the semaphore for the blocking read UL/DL transfer. */
+	init_completion(&ipc_imem->ul_pend_sem);
+
+	init_completion(&ipc_imem->dl_pend_sem);
+
+	/* clear internal flags */
+	ipc_imem->ipc_status = IPC_MEM_DEVICE_IPC_UNINIT;
+	ipc_imem->enter_runtime = 0;
+
+	phase = ipc_imem_phase_update(ipc_imem);
+
+	/* Either CP shall be in the power off or power on phase. */
+	switch (phase) {
+	case IPC_P_ROM:
+		ipc_imem->hrtimer_period = ktime_set(0, 1000 * 1000 * 1000ULL);
+		/* poll execution stage (for delayed start, e.g. NAND) */
+		if (!hrtimer_active(&ipc_imem->startup_timer))
+			hrtimer_start(&ipc_imem->startup_timer,
+				      ipc_imem->hrtimer_period,
+				      HRTIMER_MODE_REL);
+		return 0;
+
+	case IPC_P_PSI:
+	case IPC_P_EBL:
+	case IPC_P_RUN:
+		/* The initial IPC state is IPC_MEM_DEVICE_IPC_UNINIT. */
+		ipc_imem->ipc_requested_state = IPC_MEM_DEVICE_IPC_UNINIT;
+
+		/* Verify the exepected initial state. */
+		if (ipc_imem->ipc_requested_state ==
+		    ipc_mmio_get_ipc_state(ipc_imem->mmio)) {
+			ipc_imem_ipc_init_check(ipc_imem);
+
+			return 0;
+		}
+		dev_err(ipc_imem->dev,
+			"ipc_status(%d) != IPC_MEM_DEVICE_IPC_UNINIT",
+			ipc_mmio_get_ipc_state(ipc_imem->mmio));
+		break;
+	case IPC_P_CRASH:
+	case IPC_P_CD_READY:
+		dev_dbg(ipc_imem->dev,
+			"Modem is in phase %d, reset Modem to collect CD",
+			phase);
+		return 0;
+	default:
+		dev_err(ipc_imem->dev, "unexpected operation phase %d", phase);
+		break;
+	}
+
+	complete(&ipc_imem->dl_pend_sem);
+	complete(&ipc_imem->ul_pend_sem);
+	ipc_imem->phase = IPC_P_OFF;
+	return -EIO;
+}
+
+/* Pass the dev ptr to the shared memory driver and request the entry points */
+struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id,
+				void __iomem *mmio, struct device *dev)
+{
+	struct iosm_imem *ipc_imem = kzalloc(sizeof(*pcie->imem), GFP_KERNEL);
+
+	if (!ipc_imem)
+		return NULL;
+
+	/* Save the device address. */
+	ipc_imem->pcie = pcie;
+	ipc_imem->dev = dev;
+
+	ipc_imem->pci_device_id = device_id;
+
+	ipc_imem->ev_cdev_write_pending = false;
+	ipc_imem->cp_version = 0;
+	ipc_imem->device_sleep = IPC_HOST_SLEEP_ENTER_SLEEP;
+
+	/* Reset the flash channel id. */
+	ipc_imem->flash_channel_id = -1;
+
+	/* Reset the max number of configured channels */
+	ipc_imem->nr_of_channels = 0;
+
+	/* allocate IPC MMIO */
+	ipc_imem->mmio = ipc_mmio_init(mmio, ipc_imem->dev);
+	if (!ipc_imem->mmio) {
+		dev_err(ipc_imem->dev, "failed to initialize mmio region");
+		goto mmio_init_fail;
+	}
+
+	ipc_imem->ipc_task = kzalloc(sizeof(*ipc_imem->ipc_task),
+				     GFP_KERNEL);
+
+	/* Create tasklet for event handling*/
+	if (!ipc_imem->ipc_task)
+		goto ipc_task_fail;
+
+	if (ipc_task_init(ipc_imem->ipc_task))
+		goto ipc_task_init_fail;
+
+	ipc_imem->ipc_task->dev = ipc_imem->dev;
+
+	INIT_WORK(&ipc_imem->run_state_worker, ipc_imem_run_state_worker);
+
+	ipc_imem->ipc_protocol = ipc_protocol_init(ipc_imem);
+
+	if (!ipc_imem->ipc_protocol)
+		goto protocol_init_fail;
+
+	/* The phase is set to power off. */
+	ipc_imem->phase = IPC_P_OFF;
+
+	hrtimer_init(&ipc_imem->startup_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
+	ipc_imem->startup_timer.function = ipc_imem_startup_timer_cb;
+
+	hrtimer_init(&ipc_imem->tdupdate_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
+	ipc_imem->tdupdate_timer.function = ipc_imem_td_update_timer_cb;
+
+	hrtimer_init(&ipc_imem->fast_update_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
+	ipc_imem->fast_update_timer.function = ipc_imem_fast_update_timer_cb;
+
+	hrtimer_init(&ipc_imem->td_alloc_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
+	ipc_imem->td_alloc_timer.function = ipc_imem_td_alloc_timer_cb;
+
+	if (ipc_imem_config(ipc_imem)) {
+		dev_err(ipc_imem->dev, "failed to initialize the imem");
+		goto imem_config_fail;
+	}
+
+	return ipc_imem;
+
+imem_config_fail:
+	hrtimer_cancel(&ipc_imem->td_alloc_timer);
+	hrtimer_cancel(&ipc_imem->fast_update_timer);
+	hrtimer_cancel(&ipc_imem->tdupdate_timer);
+	hrtimer_cancel(&ipc_imem->startup_timer);
+protocol_init_fail:
+	cancel_work_sync(&ipc_imem->run_state_worker);
+	ipc_task_deinit(ipc_imem->ipc_task);
+ipc_task_init_fail:
+	kfree(ipc_imem->ipc_task);
+ipc_task_fail:
+	kfree(ipc_imem->mmio);
+mmio_init_fail:
+	kfree(ipc_imem);
+	return NULL;
+}
+
+void ipc_imem_irq_process(struct iosm_imem *ipc_imem, int irq)
+{
+	/* Debounce IPC_EV_IRQ. */
+	if (ipc_imem && !ipc_imem->ev_irq_pending[irq]) {
+		ipc_imem->ev_irq_pending[irq] = true;
+		ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_irq_cb, irq,
+					 NULL, 0, false);
+	}
+}
+
+void ipc_imem_td_update_timer_suspend(struct iosm_imem *ipc_imem, bool suspend)
+{
+	ipc_imem->td_update_timer_suspended = suspend;
+}
diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.h b/drivers/net/wwan/iosm/iosm_ipc_imem.h
new file mode 100644
index 000000000000..0d2f10e4cbc8
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_imem.h
@@ -0,0 +1,579 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#ifndef IOSM_IPC_IMEM_H
+#define IOSM_IPC_IMEM_H
+
+#include <linux/skbuff.h>
+#include <stdbool.h>
+
+#include "iosm_ipc_mmio.h"
+#include "iosm_ipc_pcie.h"
+#include "iosm_ipc_uevent.h"
+#include "iosm_ipc_wwan.h"
+#include "iosm_ipc_task_queue.h"
+
+struct ipc_chnl_cfg;
+
+/* IRQ moderation in usec */
+#define IRQ_MOD_OFF 0
+#define IRQ_MOD_NET 1000
+#define IRQ_MOD_TRC 4000
+
+/* Either the PSI image is accepted by CP or the suspended flash tool is waken,
+ * informed that the CP ROM driver is not ready to process the PSI image.
+ * unit : milliseconds
+ */
+#define IPC_PSI_TRANSFER_TIMEOUT 3000
+
+/* Timeout in 20 msec to wait for the modem to boot up to
+ * IPC_MEM_DEVICE_IPC_INIT state.
+ * unit : milliseconds (500 * ipc_util_msleep(20))
+ */
+#define IPC_MODEM_BOOT_TIMEOUT 500
+
+/* Wait timeout for ipc status reflects IPC_MEM_DEVICE_IPC_UNINIT
+ * unit : milliseconds
+ */
+#define IPC_MODEM_UNINIT_TIMEOUT_MS 30
+
+/* Pending time for processing data.
+ * unit : milliseconds
+ */
+#define IPC_PEND_DATA_TIMEOUT 500
+
+/* The timeout in milliseconds for application to wait for remote time. */
+#define IPC_REMOTE_TS_TIMEOUT_MS 10
+
+/* Timeout for TD allocation retry.
+ * unit : milliseconds
+ */
+#define IPC_TD_ALLOC_TIMER_PERIOD_MS 100
+
+/* Host sleep target is host */
+#define IPC_HOST_SLEEP_HOST 0
+
+/* Host sleep target is device */
+#define IPC_HOST_SLEEP_DEVICE 1
+
+/* Sleep message, target host: AP enters sleep / target device: CP is
+ * allowed to enter sleep and shall use the host sleep protocol
+ */
+#define IPC_HOST_SLEEP_ENTER_SLEEP 0
+
+/* Sleep_message, target host: AP exits  sleep / target device: CP is
+ * NOT allowed to enter sleep
+ */
+#define IPC_HOST_SLEEP_EXIT_SLEEP 1
+
+#define IMEM_IRQ_DONT_CARE (-1)
+
+#define IPC_MEM_MAX_CHANNELS 7
+
+#define IPC_MEM_MUX_IP_SESSION_ENTRIES 8
+
+#define IPC_MEM_MUX_IP_CH_IF_ID 0
+
+#define TD_UPDATE_DEFAULT_TIMEOUT_USEC 1900
+
+#define FORCE_UPDATE_DEFAULT_TIMEOUT_USEC 500
+
+/* Sleep_message, target host: not applicable  / target device: CP is
+ * allowed to enter sleep and shall NOT use the device sleep protocol
+ */
+#define IPC_HOST_SLEEP_ENTER_SLEEP_NO_PROTOCOL 2
+
+/* in_band_crash_signal IPC_MEM_INBAND_CRASH_SIG
+ * Modem crash notification configuration. If this value is non-zero then
+ * FEATURE_SET message will be sent to the Modem as a result the Modem will
+ * signal Crash via Execution Stage register. If this value is zero then Modem
+ * will use out-of-band method to notify about it's Crash.
+ */
+#define IPC_MEM_INBAND_CRASH_SIG 1
+
+/* Extra headroom to be allocated for DL SKBs to allow addition of Ethernet
+ * header
+ */
+#define IPC_MEM_DL_ETH_OFFSET 16
+
+#define IPC_CB(skb) ((struct ipc_skb_cb *)((skb)->cb))
+
+#define FULLY_FUNCTIONAL 0
+
+/* List of the supported UL/DL pipes. */
+enum ipc_mem_pipes {
+	IPC_MEM_PIPE_0 = 0,
+	IPC_MEM_PIPE_1,
+	IPC_MEM_PIPE_2,
+	IPC_MEM_PIPE_3,
+	IPC_MEM_PIPE_4,
+	IPC_MEM_PIPE_5,
+	IPC_MEM_PIPE_6,
+	IPC_MEM_PIPE_7,
+	IPC_MEM_PIPE_8,
+	IPC_MEM_PIPE_9,
+	IPC_MEM_PIPE_10,
+	IPC_MEM_PIPE_11,
+	IPC_MEM_PIPE_12,
+	IPC_MEM_PIPE_13,
+	IPC_MEM_PIPE_14,
+	IPC_MEM_PIPE_15,
+	IPC_MEM_PIPE_16,
+	IPC_MEM_PIPE_17,
+	IPC_MEM_PIPE_18,
+	IPC_MEM_PIPE_19,
+	IPC_MEM_PIPE_20,
+	IPC_MEM_PIPE_21,
+	IPC_MEM_PIPE_22,
+	IPC_MEM_PIPE_23,
+	IPC_MEM_MAX_PIPES
+};
+
+/* Enum defining channel states. */
+enum ipc_channel_state {
+	IMEM_CHANNEL_FREE,
+	IMEM_CHANNEL_RESERVED,
+	IMEM_CHANNEL_ACTIVE,
+	IMEM_CHANNEL_CLOSING,
+};
+
+/* Time Unit */
+enum ipc_time_unit {
+	IPC_SEC = 0,
+	IPC_MILLI_SEC = 1,
+	IPC_MICRO_SEC = 2,
+	IPC_NANO_SEC = 3,
+	IPC_PICO_SEC = 4,
+	IPC_FEMTO_SEC = 5,
+	IPC_ATTO_SEC = 6,
+};
+
+/**
+ * enum ipc_ctype - Enum defining supported channel type needed for control
+ *		    /IP traffic.
+ * @IPC_CTYPE_WWAN:		Used for IP traffic
+ * @IPC_CTYPE_CTRL:		Used for Control Communication
+ */
+enum ipc_ctype {
+	IPC_CTYPE_WWAN,
+	IPC_CTYPE_CTRL,
+};
+
+/* Pipe direction. */
+enum ipc_mem_pipe_dir {
+	IPC_MEM_DIR_UL,
+	IPC_MEM_DIR_DL,
+};
+
+/* HP update identifier. To be used as data for ipc_cp_irq_hpda_update() */
+enum ipc_hp_identifier {
+	IPC_HP_MR = 0,
+	IPC_HP_PM_TRIGGER,
+	IPC_HP_WAKEUP_SPEC_TMR,
+	IPC_HP_TD_UPD_TMR_START,
+	IPC_HP_TD_UPD_TMR,
+	IPC_HP_FAST_TD_UPD_TMR,
+	IPC_HP_UL_WRITE_TD,
+	IPC_HP_DL_PROCESS,
+	IPC_HP_NET_CHANNEL_INIT,
+	IPC_HP_CDEV_OPEN,
+};
+
+/**
+ * struct ipc_pipe - Structure for Pipe.
+ * @tdr_start:			Ipc private protocol Transfer Descriptor Ring
+ * @channel:			Id of the sio device, set by imem_sio_open,
+ *				needed to pass DL char to the user terminal
+ * @skbr_start:			Circular buffer for skbuf and the buffer
+ *				reference in a tdr_start entry.
+ * @phy_tdr_start:		Transfer descriptor start address
+ * @old_head:			last head pointer reported to CP.
+ * @old_tail:			AP read position before CP moves the read
+ *				position to write/head. If CP has consumed the
+ *				buffers, AP has to freed the skbuf starting at
+ *				tdr_start[old_tail].
+ * @nr_of_entries:		Number of elements of skb_start and tdr_start.
+ * @max_nr_of_queued_entries:	Maximum number of queued entries in TDR
+ * @accumulation_backoff:	Accumulation in usec for accumulation
+ *				backoff (0 = no acc backoff)
+ * @irq_moderation:		timer in usec for irq_moderation
+ *				(0=no irq moderation)
+ * @pipe_nr:			Pipe identification number
+ * @irq:			Interrupt vector
+ * @dir:			Direction of data stream in pipe
+ * @td_tag:			Unique tag of the buffer queued
+ * @buf_size:			Buffer size (in bytes) for preallocated
+ *				buffers (for DL pipes)
+ * @nr_of_queued_entries:	Aueued number of entries
+ * @is_open:			Check for open pipe status
+ */
+struct ipc_pipe {
+	struct ipc_protocol_td *tdr_start;
+	struct ipc_mem_channel *channel;
+	struct sk_buff **skbr_start;
+	dma_addr_t phy_tdr_start;
+	u32 old_head;
+	u32 old_tail;
+	u32 nr_of_entries;
+	u32 max_nr_of_queued_entries;
+	u32 accumulation_backoff;
+	u32 irq_moderation;
+	u32 pipe_nr;
+	u32 irq;
+	enum ipc_mem_pipe_dir dir;
+	u32 td_tag;
+	u32 buf_size;
+	u16 nr_of_queued_entries;
+	u8 is_open:1;
+};
+
+/**
+ * struct ipc_mem_channel - Structure for Channel.
+ * @channel_id:		Instance of the channel list and is return to the user
+ *			at the end of the open operation.
+ * @ctype:		Control or netif channel.
+ * @index:		unique index per ctype
+ * @ul_pipe:		pipe objects
+ * @dl_pipe:		pipe objects
+ * @if_id:		Interface ID
+ * @net_err_count:	Number of downlink errors returned by ipc_wwan_receive
+ *			interface at the entry point of the IP stack.
+ * @state:		Free, reserved or busy (in use).
+ * @ul_sem:		Needed for the blocking write or uplink transfer.
+ * @ul_list:		Uplink accumulator which is filled by the uplink
+ *			char app or IP stack. The socket buffer pointer are
+ *			added to the descriptor list in the kthread context.
+ */
+struct ipc_mem_channel {
+	int channel_id;
+	enum ipc_ctype ctype;
+	int index;
+	struct ipc_pipe ul_pipe;
+	struct ipc_pipe dl_pipe;
+	int if_id;
+	u32 net_err_count;
+	enum ipc_channel_state state;
+	struct completion ul_sem;
+	struct sk_buff_head ul_list;
+};
+
+/**
+ * enum ipc_phase - Different AP and CP phases.
+ *		    The enums defined after "IPC_P_ROM" and before
+ *		    "IPC_P_RUN" indicates the operating state where CP can
+ *		    respond to any requests. So while introducing new phase
+ *		    this shall be taken into consideration.
+ * @IPC_P_OFF:		On host PC, the PCIe device link settings are known
+ *			about the combined power on. PC is running, the driver
+ *			is loaded and CP is in power off mode. The PCIe bus
+ *			driver call the device power mode D3hot. In this phase
+ *			the driver the polls the device, until the device is in
+ *			the power on state and signals the power mode D0.
+ * @IPC_P_OFF_REQ:	The intermediate phase between cleanup activity starts
+ *			and ends.
+ * @IPC_P_CRASH:	The phase indicating CP crash
+ * @IPC_P_CD_READY:	The phase indicating CP core dump is ready
+ * @IPC_P_ROM:		After power on, CP starts in ROM mode and the IPC ROM
+ *			driver is waiting 150 ms for the AP active notification
+ *			saved in the PCI link status register.
+ * @IPC_P_PSI:		Primary signed image download phase
+ * @IPC_P_EBL:		Extended bootloader pahse
+ * @IPC_P_RUN:		The phase after flashing to RAM is the RUNTIME phase.
+ */
+enum ipc_phase {
+	IPC_P_OFF,
+	IPC_P_OFF_REQ,
+	IPC_P_CRASH,
+	IPC_P_CD_READY,
+	IPC_P_ROM,
+	IPC_P_PSI,
+	IPC_P_EBL,
+	IPC_P_RUN,
+};
+
+/**
+ * struct iosm_imem - Current state of the IPC shared memory.
+ * @mmio:			mmio instance to access CP MMIO area /
+ *				doorbell scratchpad.
+ * @ipc_protocol:		IPC Protocol instance
+ * @ipc_task:			Task for entry into ipc task queue
+ * @wwan:			WWAN device pointer
+ * @mux:			IP Data multiplexing state.
+ * @sio:			IPC SIO data structure pointer
+ * @ipc_port:			IPC PORT data structure pointer
+ * @pcie:			IPC PCIe
+ * @dev:			Pointer to device structure
+ * @flash_channel_id:		Reserved channel id for flashing to RAM.
+ * @ipc_requested_state:	Expected IPC state on CP.
+ * @channels:			Channel list with UL/DL pipe pairs.
+ * @ipc_status:			local ipc_status
+ * @nr_of_channels:		number of configured channels
+ * @startup_timer:		startup timer for NAND support.
+ * @hrtimer_period:		Hr timer period
+ * @tdupdate_timer:		Delay the TD update doorbell.
+ * @fast_update_timer:		forced head pointer update delay timer.
+ * @td_alloc_timer:		Timer for DL pipe TD allocation retry
+ * @rom_exit_code:		Mapped boot rom exit code.
+ * @enter_runtime:		1 means the transition to runtime phase was
+ *				executed.
+ * @ul_pend_sem:		Semaphore to wait/complete of UL TDs
+ *				before closing pipe.
+ * @app_notify_ul_pend:		Signal app if UL TD is pending
+ * @dl_pend_sem:		Semaphore to wait/complete of DL TDs
+ *				before closing pipe.
+ * @app_notify_dl_pend:		Signal app if DL TD is pending
+ * @phase:			Operating phase like runtime.
+ * @pci_device_id:		Device ID
+ * @cp_version:			CP version
+ * @device_sleep:		Device sleep state
+ * @run_state_worker:		Pointer to worker component for device
+ *				setup operations to be called when modem
+ *				reaches RUN state
+ * @ev_irq_pending:		0 means inform the IPC tasklet to
+ *				process the irq actions.
+ * @flag:			Flag to monitor the state of driver
+ * @td_update_timer_suspended:	if true then td update timer suspend
+ * @ev_cdev_write_pending:	0 means inform the IPC tasklet to pass
+ *				the accumulated uplink buffers to CP.
+ * @ev_mux_net_transmit_pending:0 means inform the IPC tasklet to pass
+ * @reset_det_n:		Reset detect flag
+ * @pcie_wake_n:		Pcie wake flag
+ */
+struct iosm_imem {
+	struct iosm_mmio *mmio;
+	struct iosm_protocol *ipc_protocol;
+	struct ipc_task *ipc_task;
+	struct iosm_wwan *wwan;
+	struct iosm_mux *mux;
+	struct iosm_cdev *ipc_port[IPC_MEM_MAX_CHANNELS];
+	struct iosm_pcie *pcie;
+	struct device *dev;
+	int flash_channel_id;
+	enum ipc_mem_device_ipc_state ipc_requested_state;
+	struct ipc_mem_channel channels[IPC_MEM_MAX_CHANNELS];
+	u32 ipc_status;
+	u32 nr_of_channels;
+	struct hrtimer startup_timer;
+	ktime_t hrtimer_period;
+	struct hrtimer tdupdate_timer;
+	struct hrtimer fast_update_timer;
+	struct hrtimer td_alloc_timer;
+	enum rom_exit_code rom_exit_code;
+	u32 enter_runtime;
+	struct completion ul_pend_sem;
+	u32 app_notify_ul_pend;
+	struct completion dl_pend_sem;
+	u32 app_notify_dl_pend;
+	enum ipc_phase phase;
+	u16 pci_device_id;
+	int cp_version;
+	int device_sleep;
+	struct work_struct run_state_worker;
+	u8 ev_irq_pending[IPC_IRQ_VECTORS];
+	unsigned long flag;
+	u8 td_update_timer_suspended:1,
+	   ev_cdev_write_pending:1,
+	   ev_mux_net_transmit_pending:1,
+	   reset_det_n:1,
+	   pcie_wake_n:1;
+};
+
+/**
+ * ipc_imem_init - Initialize the shared memory region
+ * @pcie:	Pointer to core driver data-struct
+ * @device_id:	PCI device ID
+ * @mmio:	Pointer to the mmio area
+ * @dev:	Pointer to device structure
+ *
+ * Returns:  Initialized imem pointer on success else NULL
+ */
+struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id,
+				void __iomem *mmio, struct device *dev);
+
+/**
+ * ipc_imem_pm_s2idle_sleep - Set PM variables to sleep/active for
+ *			      s2idle sleep/active
+ * @ipc_imem:	Pointer to imem data-struct
+ * @sleep:	Set PM Variable to sleep/active
+ */
+void ipc_imem_pm_s2idle_sleep(struct iosm_imem *ipc_imem, bool sleep);
+
+/**
+ * ipc_imem_pm_suspend - The HAL shall ask the shared memory layer
+ *			 whether D3 is allowed.
+ * @ipc_imem:	Pointer to imem data-struct
+ */
+void ipc_imem_pm_suspend(struct iosm_imem *ipc_imem);
+
+/**
+ * ipc_imem_pm_resume - The HAL shall inform the shared memory layer
+ *			that the device is active.
+ * @ipc_imem:	Pointer to imem data-struct
+ */
+void ipc_imem_pm_resume(struct iosm_imem *ipc_imem);
+
+/**
+ * ipc_imem_cleanup -	Inform CP and free the shared memory resources.
+ * @ipc_imem:	Pointer to imem data-struct
+ */
+void ipc_imem_cleanup(struct iosm_imem *ipc_imem);
+
+/**
+ * ipc_imem_irq_process - Shift the IRQ actions to the IPC thread.
+ * @ipc_imem:	Pointer to imem data-struct
+ * @irq:	Irq number
+ */
+void ipc_imem_irq_process(struct iosm_imem *ipc_imem, int irq);
+
+/**
+ * imem_get_device_sleep_state - Get the device sleep state value.
+ * @ipc_imem:	Pointer to imem instance
+ *
+ * Returns: device sleep state
+ */
+int imem_get_device_sleep_state(struct iosm_imem *ipc_imem);
+
+/**
+ * ipc_imem_td_update_timer_suspend - Updates the TD Update Timer suspend flag.
+ * @ipc_imem:	Pointer to imem data-struct
+ * @suspend:	Flag to update. If TRUE then HP update doorbell is triggered to
+ *		device without any wait. If FALSE then HP update doorbell is
+ *		delayed until timeout.
+ */
+void ipc_imem_td_update_timer_suspend(struct iosm_imem *ipc_imem, bool suspend);
+
+/**
+ * ipc_imem_channel_close - Release the channel resources.
+ * @ipc_imem:		Pointer to imem data-struct
+ * @channel_id:		Channel ID to be cleaned up.
+ */
+void ipc_imem_channel_close(struct iosm_imem *ipc_imem, int channel_id);
+
+/**
+ * ipc_imem_channel_alloc - Reserves a channel
+ * @ipc_imem:	Pointer to imem data-struct
+ * @index:	ID to lookup from the preallocated list.
+ * @ctype:	Channel type.
+ *
+ * Returns: Index on success and failure value on error
+ */
+int ipc_imem_channel_alloc(struct iosm_imem *ipc_imem, int index,
+			   enum ipc_ctype ctype);
+
+/**
+ * ipc_imem_channel_open - Establish the pipes.
+ * @ipc_imem:		Pointer to imem data-struct
+ * @channel_id:		Channel ID returned during alloc.
+ * @db_id:		Doorbell ID for trigger identifier.
+ *
+ * Returns: Pointer of ipc_mem_channel on success and NULL on failure.
+ */
+struct ipc_mem_channel *ipc_imem_channel_open(struct iosm_imem *ipc_imem,
+					      int channel_id, u32 db_id);
+
+/**
+ * ipc_imem_td_update_timer_start - Starts the TD Update Timer if not running.
+ * @ipc_imem:	Pointer to imem data-struct
+ */
+void ipc_imem_td_update_timer_start(struct iosm_imem *ipc_imem);
+
+/**
+ * ipc_imem_ul_write_td - Pass the channel UL list to protocol layer for TD
+ *		      preparation and sending them to the device.
+ * @ipc_imem:	Pointer to imem data-struct
+ *
+ * Returns: TRUE of HP Doorbell trigger is pending. FALSE otherwise.
+ */
+bool ipc_imem_ul_write_td(struct iosm_imem *ipc_imem);
+
+/**
+ * ipc_imem_ul_send - Dequeue SKB from channel list and start with
+ *		  the uplink transfer.If HP Doorbell is pending to be
+ *		  triggered then starts the TD Update Timer.
+ * @ipc_imem:	Pointer to imem data-struct
+ */
+void ipc_imem_ul_send(struct iosm_imem *ipc_imem);
+
+/**
+ * ipc_imem_channel_update - Set or modify pipe config of an existing channel
+ * @ipc_imem:		Pointer to imem data-struct
+ * @id:			Channel config index
+ * @chnl_cfg:		Channel config struct
+ * @irq_moderation:	Timer in usec for irq_moderation
+ */
+void ipc_imem_channel_update(struct iosm_imem *ipc_imem, int id,
+			     struct ipc_chnl_cfg chnl_cfg, u32 irq_moderation);
+
+/**
+ * ipc_imem_channel_free -Free an IPC channel.
+ * @channel:	Channel to be freed
+ */
+void ipc_imem_channel_free(struct ipc_mem_channel *channel);
+
+/**
+ * ipc_imem_hrtimer_stop - Stop the hrtimer
+ * @hr_timer:	Pointer to hrtimer instance
+ */
+void ipc_imem_hrtimer_stop(struct hrtimer *hr_timer);
+
+/**
+ * ipc_imem_pipe_cleanup - Reset volatile pipe content for all channels
+ * @ipc_imem:	Pointer to imem data-struct
+ * @pipe:	Pipe to cleaned up
+ */
+void ipc_imem_pipe_cleanup(struct iosm_imem *ipc_imem, struct ipc_pipe *pipe);
+
+/**
+ * ipc_imem_pipe_close - Send msg to device to close pipe
+ * @ipc_imem:	Pointer to imem data-struct
+ * @pipe:	Pipe to be closed
+ */
+void ipc_imem_pipe_close(struct iosm_imem *ipc_imem, struct ipc_pipe *pipe);
+
+/**
+ * ipc_imem_phase_update - Get the CP execution state
+ *			  and map it to the AP phase.
+ * @ipc_imem:	Pointer to imem data-struct
+ *
+ * Returns: Current ap updated phase
+ */
+enum ipc_phase ipc_imem_phase_update(struct iosm_imem *ipc_imem);
+
+/**
+ * ipc_imem_phase_get_string - Return the current operation
+ *			     phase as string.
+ * @phase:	AP phase
+ *
+ * Returns: AP phase string
+ */
+const char *ipc_imem_phase_get_string(enum ipc_phase phase);
+
+/**
+ * ipc_imem_msg_send_feature_set - Send feature set message to modem
+ * @ipc_imem:		Pointer to imem data-struct
+ * @reset_enable:	0 = out-of-band, 1 = in-band-crash notification
+ * @atomic_ctx:		if disabled call in tasklet context
+ *
+ */
+void ipc_imem_msg_send_feature_set(struct iosm_imem *ipc_imem,
+				   unsigned int reset_enable, bool atomic_ctx);
+
+/**
+ * ipc_imem_ipc_init_check - Send the init event to CP, wait a certain time and
+ *			     set CP to runtime with the context information
+ * @ipc_imem:	Pointer to imem data-struct
+ */
+void ipc_imem_ipc_init_check(struct iosm_imem *ipc_imem);
+
+/**
+ * ipc_imem_channel_init - Initialize the channel list with UL/DL pipe pairs.
+ * @ipc_imem:		Pointer to imem data-struct
+ * @ctype:		Channel type
+ * @chnl_cfg:		Channel configuration struct
+ * @irq_moderation:	Timer in usec for irq_moderation
+ */
+void ipc_imem_channel_init(struct iosm_imem *ipc_imem, enum ipc_ctype ctype,
+			   struct ipc_chnl_cfg chnl_cfg, u32 irq_moderation);
+#endif
diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c
new file mode 100644
index 000000000000..46f76e8aae92
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c
@@ -0,0 +1,346 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#include <linux/delay.h>
+
+#include "iosm_ipc_chnl_cfg.h"
+#include "iosm_ipc_imem.h"
+#include "iosm_ipc_imem_ops.h"
+#include "iosm_ipc_port.h"
+#include "iosm_ipc_task_queue.h"
+
+/* Open a packet data online channel between the network layer and CP. */
+int ipc_imem_sys_wwan_open(struct iosm_imem *ipc_imem, int if_id)
+{
+	dev_dbg(ipc_imem->dev, "%s if id: %d",
+		ipc_imem_phase_get_string(ipc_imem->phase), if_id);
+
+	/* The network interface is only supported in the runtime phase. */
+	if (ipc_imem_phase_update(ipc_imem) != IPC_P_RUN) {
+		dev_err(ipc_imem->dev, "net:%d : refused phase %s", if_id,
+			ipc_imem_phase_get_string(ipc_imem->phase));
+		return -EIO;
+	}
+
+	/* check for the interafce id
+	 * if if_id 1 to 8 then create IP MUX channel sessions.
+	 * To start MUX session from 0 as network interface id would start
+	 * from 1 so map it to if_id = if_id - 1
+	 */
+	if (if_id >= IP_MUX_SESSION_START && if_id <= IP_MUX_SESSION_END)
+		return ipc_mux_open_session(ipc_imem->mux, if_id - 1);
+
+	return -EINVAL;
+}
+
+/* Release a net link to CP. */
+void ipc_imem_sys_wwan_close(struct iosm_imem *ipc_imem, int if_id,
+			     int channel_id)
+{
+	if (ipc_imem->mux && if_id >= IP_MUX_SESSION_START &&
+	    if_id <= IP_MUX_SESSION_END)
+		ipc_mux_close_session(ipc_imem->mux, if_id - 1);
+}
+
+/* Tasklet call to do uplink transfer. */
+static int ipc_imem_tq_cdev_write(struct iosm_imem *ipc_imem, int arg,
+				  void *msg, size_t size)
+{
+	ipc_imem->ev_cdev_write_pending = false;
+	ipc_imem_ul_send(ipc_imem);
+
+	return 0;
+}
+
+/* Through tasklet to do sio write. */
+static int ipc_imem_call_cdev_write(struct iosm_imem *ipc_imem)
+{
+	if (ipc_imem->ev_cdev_write_pending)
+		return -1;
+
+	ipc_imem->ev_cdev_write_pending = true;
+
+	return ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_cdev_write, 0,
+					NULL, 0, false);
+}
+
+/* Function for transfer UL data */
+int ipc_imem_sys_wwan_transmit(struct iosm_imem *ipc_imem,
+			       int if_id, int channel_id, struct sk_buff *skb)
+{
+	int ret = -EINVAL;
+
+	if (!ipc_imem || channel_id < 0)
+		goto out;
+
+	/* Is CP Running? */
+	if (ipc_imem->phase != IPC_P_RUN) {
+		dev_dbg(ipc_imem->dev, "phase %s transmit",
+			ipc_imem_phase_get_string(ipc_imem->phase));
+		ret = -EIO;
+		goto out;
+	}
+
+	if (if_id >= IP_MUX_SESSION_START && if_id <= IP_MUX_SESSION_END)
+		/* Route the UL packet through IP MUX Layer */
+		ret = ipc_mux_ul_trigger_encode(ipc_imem->mux,
+						if_id - 1, skb);
+	else
+		dev_err(ipc_imem->dev,
+			"invalid if_id %d: ", if_id);
+out:
+	return ret;
+}
+
+/* Initialize wwan channel */
+void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem,
+				enum ipc_mux_protocol mux_type)
+{
+	struct ipc_chnl_cfg chnl_cfg = { 0 };
+
+	ipc_imem->cp_version = ipc_mmio_get_cp_version(ipc_imem->mmio);
+
+	/* If modem version is invalid (0xffffffff), do not initialize WWAN. */
+	if (ipc_imem->cp_version == -1) {
+		dev_err(ipc_imem->dev, "invalid CP version");
+		return;
+	}
+
+	ipc_chnl_cfg_get(&chnl_cfg, ipc_imem->nr_of_channels);
+	ipc_imem_channel_init(ipc_imem, IPC_CTYPE_WWAN, chnl_cfg,
+			      IRQ_MOD_OFF);
+
+	/* WWAN registration. */
+	ipc_imem->wwan = ipc_wwan_init(ipc_imem, ipc_imem->dev);
+	if (!ipc_imem->wwan)
+		dev_err(ipc_imem->dev,
+			"failed to register the ipc_wwan interfaces");
+}
+
+/* Map SKB to DMA for transfer */
+static int ipc_imem_map_skb_to_dma(struct iosm_imem *ipc_imem,
+				   struct sk_buff *skb)
+{
+	struct iosm_pcie *ipc_pcie = ipc_imem->pcie;
+	char *buf = skb->data;
+	int len = skb->len;
+	dma_addr_t mapping;
+	int ret;
+
+	ret = ipc_pcie_addr_map(ipc_pcie, buf, len, &mapping, DMA_TO_DEVICE);
+
+	if (ret)
+		goto err;
+
+	BUILD_BUG_ON(sizeof(*IPC_CB(skb)) > sizeof(skb->cb));
+
+	IPC_CB(skb)->mapping = mapping;
+	IPC_CB(skb)->direction = DMA_TO_DEVICE;
+	IPC_CB(skb)->len = len;
+	IPC_CB(skb)->op_type = (u8)UL_DEFAULT;
+
+err:
+	return ret;
+}
+
+/* return true if channel is ready for use */
+static bool ipc_imem_is_channel_active(struct iosm_imem *ipc_imem,
+				       struct ipc_mem_channel *channel)
+{
+	enum ipc_phase phase;
+
+	/* Update the current operation phase. */
+	phase = ipc_imem->phase;
+
+	/* Select the operation depending on the execution stage. */
+	switch (phase) {
+	case IPC_P_RUN:
+	case IPC_P_PSI:
+	case IPC_P_EBL:
+		break;
+
+	case IPC_P_ROM:
+		/* Prepare the PSI image for the CP ROM driver and
+		 * suspend the flash app.
+		 */
+		if (channel->state != IMEM_CHANNEL_RESERVED) {
+			dev_err(ipc_imem->dev,
+				"ch[%d]:invalid channel state %d,expected %d",
+				channel->channel_id, channel->state,
+				IMEM_CHANNEL_RESERVED);
+			goto channel_unavailable;
+		}
+		goto channel_available;
+
+	default:
+		/* Ignore uplink actions in all other phases. */
+		dev_err(ipc_imem->dev, "ch[%d]: confused phase %d",
+			channel->channel_id, phase);
+		goto channel_unavailable;
+	}
+	/* Check the full availability of the channel. */
+	if (channel->state != IMEM_CHANNEL_ACTIVE) {
+		dev_err(ipc_imem->dev, "ch[%d]: confused channel state %d",
+			channel->channel_id, channel->state);
+		goto channel_unavailable;
+	}
+
+channel_available:
+	return true;
+
+channel_unavailable:
+	return false;
+}
+
+/* Release a sio link to CP. */
+void ipc_imem_sys_cdev_close(struct iosm_cdev *ipc_cdev)
+{
+	struct iosm_imem *ipc_imem = ipc_cdev->ipc_imem;
+	struct ipc_mem_channel *channel = ipc_cdev->channel;
+	enum ipc_phase curr_phase;
+	int status = 0;
+	u32 tail = 0;
+
+	curr_phase = ipc_imem->phase;
+
+	/* If current phase is IPC_P_OFF or SIO ID is -ve then
+	 * channel is already freed. Nothing to do.
+	 */
+	if (curr_phase == IPC_P_OFF) {
+		dev_err(ipc_imem->dev,
+			"nothing to do. Current Phase: %s",
+			ipc_imem_phase_get_string(curr_phase));
+		return;
+	}
+
+	if (channel->state == IMEM_CHANNEL_FREE) {
+		dev_err(ipc_imem->dev, "ch[%d]: invalid channel state %d",
+			channel->channel_id, channel->state);
+		return;
+	}
+
+	/* If there are any pending TDs then wait for Timeout/Completion before
+	 * closing pipe.
+	 */
+	if (channel->ul_pipe.old_tail != channel->ul_pipe.old_head) {
+		ipc_imem->app_notify_ul_pend = 1;
+
+		/* Suspend the user app and wait a certain time for processing
+		 * UL Data.
+		 */
+		status = wait_for_completion_interruptible_timeout
+			 (&ipc_imem->ul_pend_sem,
+			  msecs_to_jiffies(IPC_PEND_DATA_TIMEOUT));
+		if (status == 0) {
+			dev_dbg(ipc_imem->dev,
+				"Pend data Timeout UL-Pipe:%d Head:%d Tail:%d",
+				channel->ul_pipe.pipe_nr,
+				channel->ul_pipe.old_head,
+				channel->ul_pipe.old_tail);
+		}
+
+		ipc_imem->app_notify_ul_pend = 0;
+	}
+
+	/* If there are any pending TDs then wait for Timeout/Completion before
+	 * closing pipe.
+	 */
+	ipc_protocol_get_head_tail_index(ipc_imem->ipc_protocol,
+					 &channel->dl_pipe, NULL, &tail);
+
+	if (tail != channel->dl_pipe.old_tail) {
+		ipc_imem->app_notify_dl_pend = 1;
+
+		/* Suspend the user app and wait a certain time for processing
+		 * DL Data.
+		 */
+		status = wait_for_completion_interruptible_timeout
+			 (&ipc_imem->dl_pend_sem,
+			  msecs_to_jiffies(IPC_PEND_DATA_TIMEOUT));
+		if (status == 0) {
+			dev_dbg(ipc_imem->dev,
+				"Pend data Timeout DL-Pipe:%d Head:%d Tail:%d",
+				channel->dl_pipe.pipe_nr,
+				channel->dl_pipe.old_head,
+				channel->dl_pipe.old_tail);
+		}
+
+		ipc_imem->app_notify_dl_pend = 0;
+	}
+
+	/* Due to wait for completion in messages, there is a small window
+	 * between closing the pipe and updating the channel is closed. In this
+	 * small window there could be HP update from Host Driver. Hence update
+	 * the channel state as CLOSING to aviod unnecessary interrupt
+	 * towards CP.
+	 */
+	channel->state = IMEM_CHANNEL_CLOSING;
+
+	ipc_imem_pipe_close(ipc_imem, &channel->ul_pipe);
+	ipc_imem_pipe_close(ipc_imem, &channel->dl_pipe);
+
+	ipc_imem_channel_free(channel);
+}
+
+/* Open a PORT link to CP and return the channel */
+struct ipc_mem_channel *ipc_imem_sys_port_open(struct iosm_imem *ipc_imem,
+					       int chl_id, int hp_id)
+{
+	struct ipc_mem_channel *channel;
+	int ch_id;
+
+	/* The PORT interface is only supported in the runtime phase. */
+	if (ipc_imem_phase_update(ipc_imem) != IPC_P_RUN) {
+		dev_err(ipc_imem->dev, "PORT open refused, phase %s",
+			ipc_imem_phase_get_string(ipc_imem->phase));
+		return NULL;
+	}
+
+	ch_id = ipc_imem_channel_alloc(ipc_imem, chl_id, IPC_CTYPE_CTRL);
+
+	if (ch_id < 0) {
+		dev_err(ipc_imem->dev, "reservation of an PORT chnl id failed");
+		return NULL;
+	}
+
+	channel = ipc_imem_channel_open(ipc_imem, ch_id, hp_id);
+
+	if (!channel) {
+		dev_err(ipc_imem->dev, "PORT channel id open failed");
+		return NULL;
+	}
+
+	return channel;
+}
+
+/* transfer skb to modem */
+int ipc_imem_sys_cdev_write(struct iosm_cdev *ipc_cdev, struct sk_buff *skb)
+{
+	struct ipc_mem_channel *channel = ipc_cdev->channel;
+	struct iosm_imem *ipc_imem = ipc_cdev->ipc_imem;
+	int ret = -EIO;
+
+	if (!ipc_imem_is_channel_active(ipc_imem, channel) ||
+	    ipc_imem->phase == IPC_P_OFF_REQ)
+		goto out;
+
+	ret = ipc_imem_map_skb_to_dma(ipc_imem, skb);
+
+	if (ret)
+		goto out;
+
+	/* Add skb to the uplink skbuf accumulator. */
+	skb_queue_tail(&channel->ul_list, skb);
+
+	ret = ipc_imem_call_cdev_write(ipc_imem);
+
+	if (ret) {
+		skb_dequeue_tail(&channel->ul_list);
+		dev_err(ipc_cdev->dev, "channel id[%d] write failed\n",
+			ipc_cdev->channel->channel_id);
+	}
+out:
+	return ret;
+}
diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h
new file mode 100644
index 000000000000..84087cf33329
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h
@@ -0,0 +1,98 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#ifndef IOSM_IPC_IMEM_OPS_H
+#define IOSM_IPC_IMEM_OPS_H
+
+#include "iosm_ipc_mux_codec.h"
+
+/* Maximum wait time for blocking read */
+#define IPC_READ_TIMEOUT 500
+
+/* The delay in ms for defering the unregister */
+#define SIO_UNREGISTER_DEFER_DELAY_MS 1
+
+/* Default delay till CP PSI image is running and modem updates the
+ * execution stage.
+ * unit : milliseconds
+ */
+#define PSI_START_DEFAULT_TIMEOUT 3000
+
+/* Default time out when closing SIO, till the modem is in
+ * running state.
+ * unit : milliseconds
+ */
+#define BOOT_CHECK_DEFAULT_TIMEOUT 400
+
+/* IP MUX channel range */
+#define IP_MUX_SESSION_START 1
+#define IP_MUX_SESSION_END 8
+
+/**
+ * ipc_imem_sys_port_open - Open a port link to CP.
+ * @ipc_imem:	Imem instance.
+ * @chl_id:	Channel Indentifier.
+ * @hp_id:	HP Indentifier.
+ *
+ * Return: channel instance on success, NULL for failure
+ */
+struct ipc_mem_channel *ipc_imem_sys_port_open(struct iosm_imem *ipc_imem,
+					       int chl_id, int hp_id);
+
+/**
+ * ipc_imem_sys_cdev_close - Release a sio link to CP.
+ * @ipc_cdev:		iosm sio instance.
+ */
+void ipc_imem_sys_cdev_close(struct iosm_cdev *ipc_cdev);
+
+/**
+ * ipc_imem_sys_cdev_write - Route the uplink buffer to CP.
+ * @ipc_cdev:		iosm_cdev instance.
+ * @skb:		Pointer to skb.
+ *
+ * Return: 0 on success and failure value on error
+ */
+int ipc_imem_sys_cdev_write(struct iosm_cdev *ipc_cdev, struct sk_buff *skb);
+
+/**
+ * ipc_imem_sys_wwan_open - Open packet data online channel between network
+ *			layer and CP.
+ * @ipc_imem:		Imem instance.
+ * @if_id:		ip link tag of the net device.
+ *
+ * Return: Channel ID on success and failure value on error
+ */
+int ipc_imem_sys_wwan_open(struct iosm_imem *ipc_imem, int if_id);
+
+/**
+ * ipc_imem_sys_wwan_close - Close packet data online channel between network
+ *			 layer and CP.
+ * @ipc_imem:		Imem instance.
+ * @if_id:		IP link id net device.
+ * @channel_id:		Channel ID to be closed.
+ */
+void ipc_imem_sys_wwan_close(struct iosm_imem *ipc_imem, int if_id,
+			     int channel_id);
+
+/**
+ * ipc_imem_sys_wwan_transmit - Function for transfer UL data
+ * @ipc_imem:		Imem instance.
+ * @if_id:		link ID of the device.
+ * @channel_id:		Channel ID used
+ * @skb:		Pointer to sk buffer
+ *
+ * Return: 0 on success and failure value on error
+ */
+int ipc_imem_sys_wwan_transmit(struct iosm_imem *ipc_imem, int if_id,
+			       int channel_id, struct sk_buff *skb);
+/**
+ * ipc_imem_wwan_channel_init - Initializes WWAN channels and the channel for
+ *				MUX.
+ * @ipc_imem:		Pointer to iosm_imem struct.
+ * @mux_type:		Type of mux protocol.
+ */
+void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem,
+				enum ipc_mux_protocol mux_type);
+#endif
diff --git a/drivers/net/wwan/iosm/iosm_ipc_irq.c b/drivers/net/wwan/iosm/iosm_ipc_irq.c
new file mode 100644
index 000000000000..702f50a48151
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_irq.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#include "iosm_ipc_pcie.h"
+#include "iosm_ipc_protocol.h"
+
+static void ipc_write_dbell_reg(struct iosm_pcie *ipc_pcie, int irq_n, u32 data)
+{
+	void __iomem *write_reg;
+
+	/* Select the first doorbell register, which is only currently needed
+	 * by CP.
+	 */
+	write_reg = (void __iomem *)((u8 __iomem *)ipc_pcie->ipc_regs +
+				     ipc_pcie->doorbell_write +
+				     (irq_n * ipc_pcie->doorbell_reg_offset));
+
+	/* Fire the doorbell irq by writing data on the doorbell write pointer
+	 * register.
+	 */
+	iowrite32(data, write_reg);
+}
+
+void ipc_doorbell_fire(struct iosm_pcie *ipc_pcie, int irq_n, u32 data)
+{
+	ipc_write_dbell_reg(ipc_pcie, irq_n, data);
+}
+
+/* Threaded Interrupt handler for MSI interrupts */
+static irqreturn_t ipc_msi_interrupt(int irq, void *dev_id)
+{
+	struct iosm_pcie *ipc_pcie = dev_id;
+	int instance = irq - ipc_pcie->pci->irq;
+
+	/* Shift the MSI irq actions to the IPC tasklet. IRQ_NONE means the
+	 * irq was not from the IPC device or could not be served.
+	 */
+	if (instance >= ipc_pcie->nvec)
+		return IRQ_NONE;
+
+	if (!test_bit(0, &ipc_pcie->suspend))
+		ipc_imem_irq_process(ipc_pcie->imem, instance);
+
+	return IRQ_HANDLED;
+}
+
+void ipc_release_irq(struct iosm_pcie *ipc_pcie)
+{
+	struct pci_dev *pdev = ipc_pcie->pci;
+
+	if (pdev->msi_enabled) {
+		while (--ipc_pcie->nvec >= 0)
+			free_irq(pdev->irq + ipc_pcie->nvec, ipc_pcie);
+	}
+	pci_free_irq_vectors(pdev);
+}
+
+int ipc_acquire_irq(struct iosm_pcie *ipc_pcie)
+{
+	struct pci_dev *pdev = ipc_pcie->pci;
+	int i, rc = -EINVAL;
+
+	ipc_pcie->nvec = pci_alloc_irq_vectors(pdev, IPC_MSI_VECTORS,
+					       IPC_MSI_VECTORS, PCI_IRQ_MSI);
+
+	if (ipc_pcie->nvec < 0) {
+		rc = ipc_pcie->nvec;
+		goto error;
+	}
+
+	if (!pdev->msi_enabled)
+		goto error;
+
+	for (i = 0; i < ipc_pcie->nvec; ++i) {
+		rc = request_threaded_irq(pdev->irq + i, NULL,
+					  ipc_msi_interrupt, IRQF_ONESHOT,
+					  KBUILD_MODNAME, ipc_pcie);
+		if (rc) {
+			dev_err(ipc_pcie->dev, "unable to grab IRQ, rc=%d", rc);
+			ipc_pcie->nvec = i;
+			ipc_release_irq(ipc_pcie);
+			goto error;
+		}
+	}
+
+error:
+	return rc;
+}
diff --git a/drivers/net/wwan/iosm/iosm_ipc_irq.h b/drivers/net/wwan/iosm/iosm_ipc_irq.h
new file mode 100644
index 000000000000..a8ed596cb6a5
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_irq.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#ifndef IOSM_IPC_IRQ_H
+#define IOSM_IPC_IRQ_H
+
+struct iosm_pcie;
+
+/**
+ * ipc_doorbell_fire - fire doorbell to CP
+ * @ipc_pcie:	Pointer to iosm_pcie
+ * @irq_n:	Doorbell type
+ * @data:	ipc state
+ */
+void ipc_doorbell_fire(struct iosm_pcie *ipc_pcie, int irq_n, u32 data);
+
+/**
+ * ipc_release_irq - Release the IRQ handler.
+ * @ipc_pcie:	Pointer to iosm_pcie struct
+ */
+void ipc_release_irq(struct iosm_pcie *ipc_pcie);
+
+/**
+ * ipc_acquire_irq - acquire IRQ & register IRQ handler.
+ * @ipc_pcie:	Pointer to iosm_pcie struct
+ *
+ * Return: 0 on success and failure value on error
+ */
+int ipc_acquire_irq(struct iosm_pcie *ipc_pcie);
+
+#endif
diff --git a/drivers/net/wwan/iosm/iosm_ipc_mmio.c b/drivers/net/wwan/iosm/iosm_ipc_mmio.c
new file mode 100644
index 000000000000..06c94b1720b6
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_mmio.c
@@ -0,0 +1,223 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/slab.h>
+
+#include "iosm_ipc_mmio.h"
+
+/* Definition of MMIO offsets
+ * note that MMIO_CI offsets are relative to end of chip info structure
+ */
+
+/* MMIO chip info size in bytes */
+#define MMIO_CHIP_INFO_SIZE 60
+
+/* CP execution stage */
+#define MMIO_OFFSET_EXECUTION_STAGE 0x00
+
+/* Boot ROM Chip Info struct */
+#define MMIO_OFFSET_CHIP_INFO 0x04
+
+#define MMIO_OFFSET_ROM_EXIT_CODE 0x40
+
+#define MMIO_OFFSET_PSI_ADDRESS 0x54
+
+#define MMIO_OFFSET_PSI_SIZE 0x5C
+
+#define MMIO_OFFSET_IPC_STATUS 0x60
+
+#define MMIO_OFFSET_CONTEXT_INFO 0x64
+
+#define MMIO_OFFSET_BASE_ADDR 0x6C
+
+#define MMIO_OFFSET_END_ADDR 0x74
+
+#define MMIO_OFFSET_CP_VERSION 0xF0
+
+#define MMIO_OFFSET_CP_CAPABILITIES 0xF4
+
+/* Timeout in 50 msec to wait for the modem boot code to write a valid
+ * execution stage into mmio area
+ */
+#define IPC_MMIO_EXEC_STAGE_TIMEOUT 50
+
+/* check if exec stage has one of the valid values */
+static bool ipc_mmio_is_valid_exec_stage(enum ipc_mem_exec_stage stage)
+{
+	switch (stage) {
+	case IPC_MEM_EXEC_STAGE_BOOT:
+	case IPC_MEM_EXEC_STAGE_PSI:
+	case IPC_MEM_EXEC_STAGE_EBL:
+	case IPC_MEM_EXEC_STAGE_RUN:
+	case IPC_MEM_EXEC_STAGE_CRASH:
+	case IPC_MEM_EXEC_STAGE_CD_READY:
+		return true;
+	default:
+		return false;
+	}
+}
+
+void ipc_mmio_update_cp_capability(struct iosm_mmio *ipc_mmio)
+{
+	u32 cp_cap;
+	unsigned int ver;
+
+	ver = ipc_mmio_get_cp_version(ipc_mmio);
+	cp_cap = readl(ipc_mmio->base + ipc_mmio->offset.cp_capability);
+
+	ipc_mmio->has_mux_lite = (ver >= IOSM_CP_VERSION) &&
+				 !(cp_cap & DL_AGGR) && !(cp_cap & UL_AGGR);
+
+	ipc_mmio->has_ul_flow_credit =
+		(ver >= IOSM_CP_VERSION) && (cp_cap & UL_FLOW_CREDIT);
+}
+
+struct iosm_mmio *ipc_mmio_init(void __iomem *mmio, struct device *dev)
+{
+	struct iosm_mmio *ipc_mmio = kzalloc(sizeof(*ipc_mmio), GFP_KERNEL);
+	int retries = IPC_MMIO_EXEC_STAGE_TIMEOUT;
+	enum ipc_mem_exec_stage stage;
+
+	if (!ipc_mmio)
+		return NULL;
+
+	ipc_mmio->dev = dev;
+
+	ipc_mmio->base = mmio;
+
+	ipc_mmio->offset.exec_stage = MMIO_OFFSET_EXECUTION_STAGE;
+
+	/* Check for a valid execution stage to make sure that the boot code
+	 * has correctly initialized the MMIO area.
+	 */
+	do {
+		stage = ipc_mmio_get_exec_stage(ipc_mmio);
+		if (ipc_mmio_is_valid_exec_stage(stage))
+			break;
+
+		msleep(20);
+	} while (retries-- > 0);
+
+	if (!retries) {
+		dev_err(ipc_mmio->dev, "invalid exec stage %X", stage);
+		goto init_fail;
+	}
+
+	ipc_mmio->offset.chip_info = MMIO_OFFSET_CHIP_INFO;
+
+	/* read chip info size and version from chip info structure */
+	ipc_mmio->chip_info_version =
+		ioread8(ipc_mmio->base + ipc_mmio->offset.chip_info);
+
+	/* Increment of 2 is needed as the size value in the chip info
+	 * excludes the version and size field, which are always present
+	 */
+	ipc_mmio->chip_info_size =
+		ioread8(ipc_mmio->base + ipc_mmio->offset.chip_info + 1) + 2;
+
+	if (ipc_mmio->chip_info_size != MMIO_CHIP_INFO_SIZE) {
+		dev_err(ipc_mmio->dev, "Unexpected Chip Info");
+		goto init_fail;
+	}
+
+	ipc_mmio->offset.rom_exit_code = MMIO_OFFSET_ROM_EXIT_CODE;
+
+	ipc_mmio->offset.psi_address = MMIO_OFFSET_PSI_ADDRESS;
+	ipc_mmio->offset.psi_size = MMIO_OFFSET_PSI_SIZE;
+	ipc_mmio->offset.ipc_status = MMIO_OFFSET_IPC_STATUS;
+	ipc_mmio->offset.context_info = MMIO_OFFSET_CONTEXT_INFO;
+	ipc_mmio->offset.ap_win_base = MMIO_OFFSET_BASE_ADDR;
+	ipc_mmio->offset.ap_win_end = MMIO_OFFSET_END_ADDR;
+
+	ipc_mmio->offset.cp_version = MMIO_OFFSET_CP_VERSION;
+	ipc_mmio->offset.cp_capability = MMIO_OFFSET_CP_CAPABILITIES;
+
+	return ipc_mmio;
+
+init_fail:
+	kfree(ipc_mmio);
+	return NULL;
+}
+
+enum ipc_mem_exec_stage ipc_mmio_get_exec_stage(struct iosm_mmio *ipc_mmio)
+{
+	if (!ipc_mmio)
+		return IPC_MEM_EXEC_STAGE_INVALID;
+
+	return (enum ipc_mem_exec_stage)readl(ipc_mmio->base +
+					      ipc_mmio->offset.exec_stage);
+}
+
+void ipc_mmio_copy_chip_info(struct iosm_mmio *ipc_mmio, void *dest,
+			     size_t size)
+{
+	if (ipc_mmio && dest)
+		memcpy_fromio(dest, ipc_mmio->base + ipc_mmio->offset.chip_info,
+			      size);
+}
+
+enum ipc_mem_device_ipc_state ipc_mmio_get_ipc_state(struct iosm_mmio *ipc_mmio)
+{
+	if (!ipc_mmio)
+		return IPC_MEM_DEVICE_IPC_INVALID;
+
+	return (enum ipc_mem_device_ipc_state)
+		readl(ipc_mmio->base + ipc_mmio->offset.ipc_status);
+}
+
+enum rom_exit_code ipc_mmio_get_rom_exit_code(struct iosm_mmio *ipc_mmio)
+{
+	if (!ipc_mmio)
+		return IMEM_ROM_EXIT_FAIL;
+
+	return (enum rom_exit_code)readl(ipc_mmio->base +
+					 ipc_mmio->offset.rom_exit_code);
+}
+
+void ipc_mmio_config(struct iosm_mmio *ipc_mmio)
+{
+	if (!ipc_mmio)
+		return;
+
+	/* AP memory window (full window is open and active so that modem checks
+	 * each AP address) 0 means don't check on modem side.
+	 */
+	iowrite64_lo_hi(0, ipc_mmio->base + ipc_mmio->offset.ap_win_base);
+	iowrite64_lo_hi(0, ipc_mmio->base + ipc_mmio->offset.ap_win_end);
+
+	iowrite64_lo_hi(ipc_mmio->context_info_addr,
+			ipc_mmio->base + ipc_mmio->offset.context_info);
+}
+
+void ipc_mmio_set_psi_addr_and_size(struct iosm_mmio *ipc_mmio, dma_addr_t addr,
+				    u32 size)
+{
+	if (!ipc_mmio)
+		return;
+
+	iowrite64_lo_hi(addr, ipc_mmio->base + ipc_mmio->offset.psi_address);
+	writel(size, ipc_mmio->base + ipc_mmio->offset.psi_size);
+}
+
+void ipc_mmio_set_contex_info_addr(struct iosm_mmio *ipc_mmio, phys_addr_t addr)
+{
+	if (!ipc_mmio)
+		return;
+
+	/* store context_info address. This will be stored in the mmio area
+	 * during IPC_MEM_DEVICE_IPC_INIT state via ipc_mmio_config()
+	 */
+	ipc_mmio->context_info_addr = addr;
+}
+
+int ipc_mmio_get_cp_version(struct iosm_mmio *ipc_mmio)
+{
+	return ipc_mmio ? readl(ipc_mmio->base + ipc_mmio->offset.cp_version) :
+			  -EFAULT;
+}
diff --git a/drivers/net/wwan/iosm/iosm_ipc_mmio.h b/drivers/net/wwan/iosm/iosm_ipc_mmio.h
new file mode 100644
index 000000000000..45e6923da78f
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_mmio.h
@@ -0,0 +1,183 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#ifndef IOSM_IPC_MMIO_H
+#define IOSM_IPC_MMIO_H
+
+/* Minimal IOSM CP VERSION which has valid CP_CAPABILITIES field */
+#define IOSM_CP_VERSION 0x0100UL
+
+/* DL dir Aggregation support mask */
+#define DL_AGGR BIT(23)
+
+/* UL dir Aggregation support mask */
+#define UL_AGGR BIT(22)
+
+/* UL flow credit support mask */
+#define UL_FLOW_CREDIT BIT(21)
+
+/* Possible states of the IPC finite state machine. */
+enum ipc_mem_device_ipc_state {
+	IPC_MEM_DEVICE_IPC_UNINIT,
+	IPC_MEM_DEVICE_IPC_INIT,
+	IPC_MEM_DEVICE_IPC_RUNNING,
+	IPC_MEM_DEVICE_IPC_RECOVERY,
+	IPC_MEM_DEVICE_IPC_ERROR,
+	IPC_MEM_DEVICE_IPC_DONT_CARE,
+	IPC_MEM_DEVICE_IPC_INVALID = -1
+};
+
+/* Boot ROM exit status. */
+enum rom_exit_code {
+	IMEM_ROM_EXIT_OPEN_EXT = 0x01,
+	IMEM_ROM_EXIT_OPEN_MEM = 0x02,
+	IMEM_ROM_EXIT_CERT_EXT = 0x10,
+	IMEM_ROM_EXIT_CERT_MEM = 0x20,
+	IMEM_ROM_EXIT_FAIL = 0xFF
+};
+
+/* Boot stages */
+enum ipc_mem_exec_stage {
+	IPC_MEM_EXEC_STAGE_RUN = 0x600DF00D,
+	IPC_MEM_EXEC_STAGE_CRASH = 0x8BADF00D,
+	IPC_MEM_EXEC_STAGE_CD_READY = 0xBADC0DED,
+	IPC_MEM_EXEC_STAGE_BOOT = 0xFEEDB007,
+	IPC_MEM_EXEC_STAGE_PSI = 0xFEEDBEEF,
+	IPC_MEM_EXEC_STAGE_EBL = 0xFEEDCAFE,
+	IPC_MEM_EXEC_STAGE_INVALID = 0xFFFFFFFF
+};
+
+/* mmio scratchpad info */
+struct mmio_offset {
+	int exec_stage;
+	int chip_info;
+	int rom_exit_code;
+	int psi_address;
+	int psi_size;
+	int ipc_status;
+	int context_info;
+	int ap_win_base;
+	int ap_win_end;
+	int cp_version;
+	int cp_capability;
+};
+
+/**
+ * struct iosm_mmio - MMIO region mapped to the doorbell scratchpad.
+ * @base:		Base address of MMIO region
+ * @dev:		Pointer to device structure
+ * @offset:		Start offset
+ * @context_info_addr:	Physical base address of context info structure
+ * @chip_info_version:	Version of chip info structure
+ * @chip_info_size:	Size of chip info structure
+ * @has_mux_lite:	It doesn't support mux aggergation
+ * @has_ul_flow_credit:	Ul flow credit support
+ * @has_slp_no_prot:	Device sleep no protocol support
+ * @has_mcr_support:	Usage of mcr support
+ */
+struct iosm_mmio {
+	unsigned char __iomem *base;
+	struct device *dev;
+	struct mmio_offset offset;
+	phys_addr_t context_info_addr;
+	unsigned int chip_info_version;
+	unsigned int chip_info_size;
+	u8 has_mux_lite:1,
+	   has_ul_flow_credit:1,
+	   has_slp_no_prot:1,
+	   has_mcr_support:1;
+};
+
+/**
+ * ipc_mmio_init - Allocate mmio instance data
+ * @mmio_addr:	Mapped AP base address of the MMIO area.
+ * @dev:	Pointer to device structure
+ *
+ * Returns: address of mmio instance data or NULL if fails.
+ */
+struct iosm_mmio *ipc_mmio_init(void __iomem *mmio_addr, struct device *dev);
+
+/**
+ * ipc_mmio_set_psi_addr_and_size - Set start address and size of the
+ *				    primary system image (PSI) for the
+ *				    FW dowload.
+ * @ipc_mmio:	Pointer to mmio instance
+ * @addr:	PSI address
+ * @size:	PSI immage size
+ */
+void ipc_mmio_set_psi_addr_and_size(struct iosm_mmio *ipc_mmio, dma_addr_t addr,
+				    u32 size);
+
+/**
+ * ipc_mmio_set_contex_info_addr - Stores the Context Info Address in
+ *				   MMIO instance to share it with CP during
+ *				   mmio_init.
+ * @ipc_mmio:	Pointer to mmio instance
+ * @addr:	64-bit address of AP context information.
+ */
+void ipc_mmio_set_contex_info_addr(struct iosm_mmio *ipc_mmio,
+				   phys_addr_t addr);
+
+/**
+ * ipc_mmio_get_cp_version - Get the CP IPC version
+ * @ipc_mmio:	Pointer to mmio instance
+ *
+ * Returns: version number on success and failure value on error.
+ */
+int ipc_mmio_get_cp_version(struct iosm_mmio *ipc_mmio);
+
+/**
+ * ipc_mmio_get_rom_exit_code - Get exit code from CP boot rom download app
+ * @ipc_mmio:	Pointer to mmio instance
+ *
+ * Returns: exit code from CP boot rom download APP
+ */
+enum rom_exit_code ipc_mmio_get_rom_exit_code(struct iosm_mmio *ipc_mmio);
+
+/**
+ * ipc_mmio_get_exec_stage - Query CP execution stage
+ * @ipc_mmio:	Pointer to mmio instance
+ *
+ * Returns: CP execution stage
+ */
+enum ipc_mem_exec_stage ipc_mmio_get_exec_stage(struct iosm_mmio *ipc_mmio);
+
+/**
+ * ipc_mmio_get_ipc_state - Query CP IPC state
+ * @ipc_mmio:	Pointer to mmio instance
+ *
+ * Returns: CP IPC state
+ */
+enum ipc_mem_device_ipc_state
+ipc_mmio_get_ipc_state(struct iosm_mmio *ipc_mmio);
+
+/**
+ * ipc_mmio_copy_chip_info - Copy size bytes of CP chip info structure
+ *			     into caller provided buffer
+ * @ipc_mmio:	Pointer to mmio instance
+ * @dest:	Pointer to caller provided buff
+ * @size:	Number of bytes to copy
+ */
+void ipc_mmio_copy_chip_info(struct iosm_mmio *ipc_mmio, void *dest,
+			     size_t size);
+
+/**
+ * ipc_mmio_config - Write context info and AP memory range addresses.
+ *		     This needs to be called when CP is in
+ *		     IPC_MEM_DEVICE_IPC_INIT state
+ *
+ * @ipc_mmio:	Pointer to mmio instance
+ */
+void ipc_mmio_config(struct iosm_mmio *ipc_mmio);
+
+/**
+ * ipc_mmio_update_cp_capability - Read and update modem capability, from mmio
+ *				   capability offset
+ *
+ * @ipc_mmio:	Pointer to mmio instance
+ */
+void ipc_mmio_update_cp_capability(struct iosm_mmio *ipc_mmio);
+
+#endif
diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux.c b/drivers/net/wwan/iosm/iosm_ipc_mux.c
new file mode 100644
index 000000000000..c1c77ce699da
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_mux.c
@@ -0,0 +1,455 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#include "iosm_ipc_mux_codec.h"
+
+/* At the begin of the runtime phase the IP MUX channel shall created. */
+static int ipc_mux_channel_create(struct iosm_mux *ipc_mux)
+{
+	int channel_id;
+
+	channel_id = ipc_imem_channel_alloc(ipc_mux->imem, ipc_mux->instance_id,
+					    IPC_CTYPE_WWAN);
+
+	if (channel_id < 0) {
+		dev_err(ipc_mux->dev,
+			"allocation of the MUX channel id failed");
+		ipc_mux->state = MUX_S_ERROR;
+		ipc_mux->event = MUX_E_NOT_APPLICABLE;
+		goto no_channel;
+	}
+
+	/* Establish the MUX channel in blocking mode. */
+	ipc_mux->channel = ipc_imem_channel_open(ipc_mux->imem, channel_id,
+						 IPC_HP_NET_CHANNEL_INIT);
+
+	if (!ipc_mux->channel) {
+		dev_err(ipc_mux->dev, "ipc_imem_channel_open failed");
+		ipc_mux->state = MUX_S_ERROR;
+		ipc_mux->event = MUX_E_NOT_APPLICABLE;
+		return -ENODEV; /* MUX channel is not available. */
+	}
+
+	/* Define the MUX active state properties. */
+	ipc_mux->state = MUX_S_ACTIVE;
+	ipc_mux->event = MUX_E_NO_ORDERS;
+
+no_channel:
+	return channel_id;
+}
+
+/* Reset the session/if id state. */
+static void ipc_mux_session_free(struct iosm_mux *ipc_mux, int if_id)
+{
+	struct mux_session *if_entry;
+
+	if_entry = &ipc_mux->session[if_id];
+	/* Reset the session state. */
+	if_entry->wwan = NULL;
+}
+
+/* Create and send the session open command. */
+static struct mux_cmd_open_session_resp *
+ipc_mux_session_open_send(struct iosm_mux *ipc_mux, int if_id)
+{
+	struct mux_cmd_open_session_resp *open_session_resp;
+	struct mux_acb *acb = &ipc_mux->acb;
+	union mux_cmd_param param;
+
+	/* open_session commands to one ACB and start transmission. */
+	param.open_session.flow_ctrl = 0;
+	param.open_session.ipv4v6_hints = 0;
+	param.open_session.reserved2 = 0;
+	param.open_session.dl_head_pad_len = cpu_to_le32(IPC_MEM_DL_ETH_OFFSET);
+
+	/* Finish and transfer ACB. The user thread is suspended.
+	 * It is a blocking function call, until CP responds or timeout.
+	 */
+	acb->wanted_response = MUX_CMD_OPEN_SESSION_RESP;
+	if (ipc_mux_dl_acb_send_cmds(ipc_mux, MUX_CMD_OPEN_SESSION, if_id, 0,
+				     &param, sizeof(param.open_session), true,
+				 false) ||
+	    acb->got_response != MUX_CMD_OPEN_SESSION_RESP) {
+		dev_err(ipc_mux->dev, "if_id %d: OPEN_SESSION send failed",
+			if_id);
+		return NULL;
+	}
+
+	open_session_resp = &ipc_mux->acb.got_param.open_session_resp;
+	if (open_session_resp->response != cpu_to_le32(MUX_CMD_RESP_SUCCESS)) {
+		dev_err(ipc_mux->dev,
+			"if_id %d,session open failed,response=%d", if_id,
+			open_session_resp->response);
+		return NULL;
+	}
+
+	return open_session_resp;
+}
+
+/* Open the first IP session. */
+static bool ipc_mux_session_open(struct iosm_mux *ipc_mux,
+				 struct mux_session_open *session_open)
+{
+	struct mux_cmd_open_session_resp *open_session_resp;
+	int if_id;
+
+	/* Search for a free session interface id. */
+	if_id = le32_to_cpu(session_open->if_id);
+	if (if_id < 0 || if_id >= ipc_mux->nr_sessions) {
+		dev_err(ipc_mux->dev, "invalid interface id=%d", if_id);
+		return false;
+	}
+
+	/* Create and send the session open command.
+	 * It is a blocking function call, until CP responds or timeout.
+	 */
+	open_session_resp = ipc_mux_session_open_send(ipc_mux, if_id);
+	if (!open_session_resp) {
+		ipc_mux_session_free(ipc_mux, if_id);
+		session_open->if_id = cpu_to_le32(-1);
+		return false;
+	}
+
+	/* Initialize the uplink skb accumulator. */
+	skb_queue_head_init(&ipc_mux->session[if_id].ul_list);
+
+	ipc_mux->session[if_id].dl_head_pad_len = IPC_MEM_DL_ETH_OFFSET;
+	ipc_mux->session[if_id].ul_head_pad_len =
+		le32_to_cpu(open_session_resp->ul_head_pad_len);
+	ipc_mux->session[if_id].wwan = ipc_mux->wwan;
+
+	/* Reset the flow ctrl stats of the session */
+	ipc_mux->session[if_id].flow_ctl_en_cnt = 0;
+	ipc_mux->session[if_id].flow_ctl_dis_cnt = 0;
+	ipc_mux->session[if_id].ul_flow_credits = 0;
+	ipc_mux->session[if_id].net_tx_stop = false;
+	ipc_mux->session[if_id].flow_ctl_mask = 0;
+
+	/* Save and return the assigned if id. */
+	session_open->if_id = cpu_to_le32(if_id);
+
+	return true;
+}
+
+/* Free pending session UL packet. */
+static void ipc_mux_session_reset(struct iosm_mux *ipc_mux, int if_id)
+{
+	/* Reset the session/if id state. */
+	ipc_mux_session_free(ipc_mux, if_id);
+
+	/* Empty the uplink skb accumulator. */
+	skb_queue_purge(&ipc_mux->session[if_id].ul_list);
+}
+
+static void ipc_mux_session_close(struct iosm_mux *ipc_mux,
+				  struct mux_session_close *msg)
+{
+	int if_id;
+
+	/* Copy the session interface id. */
+	if_id = le32_to_cpu(msg->if_id);
+
+	if (if_id < 0 || if_id >= ipc_mux->nr_sessions) {
+		dev_err(ipc_mux->dev, "invalid session id %d", if_id);
+		return;
+	}
+
+	/* Create and send the session close command.
+	 * It is a blocking function call, until CP responds or timeout.
+	 */
+	if (ipc_mux_dl_acb_send_cmds(ipc_mux, MUX_CMD_CLOSE_SESSION, if_id, 0,
+				     NULL, 0, true, false))
+		dev_err(ipc_mux->dev, "if_id %d: CLOSE_SESSION send failed",
+			if_id);
+
+	/* Reset the flow ctrl stats of the session */
+	ipc_mux->session[if_id].flow_ctl_en_cnt = 0;
+	ipc_mux->session[if_id].flow_ctl_dis_cnt = 0;
+	ipc_mux->session[if_id].flow_ctl_mask = 0;
+
+	ipc_mux_session_reset(ipc_mux, if_id);
+}
+
+static void ipc_mux_channel_close(struct iosm_mux *ipc_mux,
+				  struct mux_channel_close *channel_close_p)
+{
+	int i;
+
+	/* Free pending session UL packet. */
+	for (i = 0; i < ipc_mux->nr_sessions; i++)
+		if (ipc_mux->session[i].wwan)
+			ipc_mux_session_reset(ipc_mux, i);
+
+	ipc_imem_channel_close(ipc_mux->imem, ipc_mux->channel_id);
+
+	/* Reset the MUX object. */
+	ipc_mux->state = MUX_S_INACTIVE;
+	ipc_mux->event = MUX_E_INACTIVE;
+}
+
+/* CP has interrupted AP. If AP is in IP MUX mode, execute the pending ops. */
+static int ipc_mux_schedule(struct iosm_mux *ipc_mux, union mux_msg *msg)
+{
+	enum mux_event order;
+	bool success;
+	int ret = -EIO;
+
+	if (!ipc_mux->initialized) {
+		ret = -EAGAIN;
+		goto out;
+	}
+
+	order = msg->common.event;
+
+	switch (ipc_mux->state) {
+	case MUX_S_INACTIVE:
+		if (order != MUX_E_MUX_SESSION_OPEN)
+			goto out; /* Wait for the request to open a session */
+
+		if (ipc_mux->event == MUX_E_INACTIVE)
+			/* Establish the MUX channel and the new state. */
+			ipc_mux->channel_id = ipc_mux_channel_create(ipc_mux);
+
+		if (ipc_mux->state != MUX_S_ACTIVE) {
+			ret = ipc_mux->channel_id; /* Missing the MUX channel */
+			goto out;
+		}
+
+		/* Disable the TD update timer and open the first IP session. */
+		ipc_imem_td_update_timer_suspend(ipc_mux->imem, true);
+		ipc_mux->event = MUX_E_MUX_SESSION_OPEN;
+		success = ipc_mux_session_open(ipc_mux, &msg->session_open);
+
+		ipc_imem_td_update_timer_suspend(ipc_mux->imem, false);
+		if (success)
+			ret = ipc_mux->channel_id;
+		goto out;
+
+	case MUX_S_ACTIVE:
+		switch (order) {
+		case MUX_E_MUX_SESSION_OPEN:
+			/* Disable the TD update timer and open a session */
+			ipc_imem_td_update_timer_suspend(ipc_mux->imem, true);
+			ipc_mux->event = MUX_E_MUX_SESSION_OPEN;
+			success = ipc_mux_session_open(ipc_mux,
+						       &msg->session_open);
+			ipc_imem_td_update_timer_suspend(ipc_mux->imem, false);
+			if (success)
+				ret = ipc_mux->channel_id;
+			goto out;
+
+		case MUX_E_MUX_SESSION_CLOSE:
+			/* Release an IP session. */
+			ipc_mux->event = MUX_E_MUX_SESSION_CLOSE;
+			ipc_mux_session_close(ipc_mux, &msg->session_close);
+			ret = ipc_mux->channel_id;
+			goto out;
+
+		case MUX_E_MUX_CHANNEL_CLOSE:
+			/* Close the MUX channel pipes. */
+			ipc_mux->event = MUX_E_MUX_CHANNEL_CLOSE;
+			ipc_mux_channel_close(ipc_mux, &msg->channel_close);
+			ret = ipc_mux->channel_id;
+			goto out;
+
+		default:
+			/* Invalid order. */
+			goto out;
+		}
+
+	default:
+		dev_err(ipc_mux->dev,
+			"unexpected MUX transition: state=%d, event=%d",
+			ipc_mux->state, ipc_mux->event);
+	}
+out:
+	return ret;
+}
+
+struct iosm_mux *ipc_mux_init(struct ipc_mux_config *mux_cfg,
+			      struct iosm_imem *imem)
+{
+	struct iosm_mux *ipc_mux = kzalloc(sizeof(*ipc_mux), GFP_KERNEL);
+	int i, ul_tds, ul_td_size;
+	struct sk_buff_head *free_list;
+	struct sk_buff *skb;
+
+	if (!ipc_mux)
+		return NULL;
+
+	ipc_mux->protocol = mux_cfg->protocol;
+	ipc_mux->ul_flow = mux_cfg->ul_flow;
+	ipc_mux->nr_sessions = mux_cfg->nr_sessions;
+	ipc_mux->instance_id = mux_cfg->instance_id;
+	ipc_mux->wwan_q_offset = 0;
+
+	ipc_mux->pcie = imem->pcie;
+	ipc_mux->imem = imem;
+	ipc_mux->ipc_protocol = imem->ipc_protocol;
+	ipc_mux->dev = imem->dev;
+	ipc_mux->wwan = imem->wwan;
+
+	/* Get the reference to the UL ADB list. */
+	free_list = &ipc_mux->ul_adb.free_list;
+
+	/* Initialize the list with free ADB. */
+	skb_queue_head_init(free_list);
+
+	ul_td_size = IPC_MEM_MAX_DL_MUX_LITE_BUF_SIZE;
+
+	ul_tds = IPC_MEM_MAX_TDS_MUX_LITE_UL;
+
+	ipc_mux->ul_adb.dest_skb = NULL;
+
+	ipc_mux->initialized = true;
+	ipc_mux->adb_prep_ongoing = false;
+	ipc_mux->size_needed = 0;
+	ipc_mux->ul_data_pend_bytes = 0;
+	ipc_mux->state = MUX_S_INACTIVE;
+	ipc_mux->ev_mux_net_transmit_pending = false;
+	ipc_mux->tx_transaction_id = 0;
+	ipc_mux->rr_next_session = 0;
+	ipc_mux->event = MUX_E_INACTIVE;
+	ipc_mux->channel_id = -1;
+	ipc_mux->channel = NULL;
+
+	/* Allocate the list of UL ADB. */
+	for (i = 0; i < ul_tds; i++) {
+		dma_addr_t mapping;
+
+		skb = ipc_pcie_alloc_skb(ipc_mux->pcie, ul_td_size, GFP_ATOMIC,
+					 &mapping, DMA_TO_DEVICE, 0);
+		if (!skb) {
+			ipc_mux_deinit(ipc_mux);
+			return NULL;
+		}
+		/* Extend the UL ADB list. */
+		skb_queue_tail(free_list, skb);
+	}
+
+	return ipc_mux;
+}
+
+/* Informs the network stack to restart transmission for all opened session if
+ * Flow Control is not ON for that session.
+ */
+static void ipc_mux_restart_tx_for_all_sessions(struct iosm_mux *ipc_mux)
+{
+	struct mux_session *session;
+	int idx;
+
+	for (idx = 0; idx < ipc_mux->nr_sessions; idx++) {
+		session = &ipc_mux->session[idx];
+
+		if (!session->wwan)
+			continue;
+
+		/* If flow control of the session is OFF and if there was tx
+		 * stop then restart. Inform the network interface to restart
+		 * sending data.
+		 */
+		if (session->flow_ctl_mask == 0) {
+			session->net_tx_stop = false;
+			ipc_mux_netif_tx_flowctrl(session, idx, false);
+		}
+	}
+}
+
+/* Informs the network stack to stop sending further pkt for all opened
+ * sessions
+ */
+static void ipc_mux_stop_netif_for_all_sessions(struct iosm_mux *ipc_mux)
+{
+	struct mux_session *session;
+	int idx;
+
+	for (idx = 0; idx < ipc_mux->nr_sessions; idx++) {
+		session = &ipc_mux->session[idx];
+
+		if (!session->wwan)
+			continue;
+
+		ipc_mux_netif_tx_flowctrl(session, session->if_id, true);
+	}
+}
+
+void ipc_mux_check_n_restart_tx(struct iosm_mux *ipc_mux)
+{
+	if (ipc_mux->ul_flow == MUX_UL) {
+		int low_thresh = IPC_MEM_MUX_UL_FLOWCTRL_LOW_B;
+
+		if (ipc_mux->ul_data_pend_bytes < low_thresh)
+			ipc_mux_restart_tx_for_all_sessions(ipc_mux);
+	}
+}
+
+int ipc_mux_get_max_sessions(struct iosm_mux *ipc_mux)
+{
+	return ipc_mux ? ipc_mux->nr_sessions : -EFAULT;
+}
+
+enum ipc_mux_protocol ipc_mux_get_active_protocol(struct iosm_mux *ipc_mux)
+{
+	return ipc_mux ? ipc_mux->protocol : MUX_UNKNOWN;
+}
+
+int ipc_mux_open_session(struct iosm_mux *ipc_mux, int session_nr)
+{
+	struct mux_session_open *session_open;
+	union mux_msg mux_msg;
+
+	session_open = &mux_msg.session_open;
+	session_open->event = MUX_E_MUX_SESSION_OPEN;
+
+	session_open->if_id = cpu_to_le32(session_nr);
+	ipc_mux->session[session_nr].flags |= IPC_MEM_WWAN_MUX;
+	return ipc_mux_schedule(ipc_mux, &mux_msg);
+}
+
+int ipc_mux_close_session(struct iosm_mux *ipc_mux, int session_nr)
+{
+	struct mux_session_close *session_close;
+	union mux_msg mux_msg;
+	int ret_val;
+
+	session_close = &mux_msg.session_close;
+	session_close->event = MUX_E_MUX_SESSION_CLOSE;
+
+	session_close->if_id = cpu_to_le32(session_nr);
+	ret_val = ipc_mux_schedule(ipc_mux, &mux_msg);
+	ipc_mux->session[session_nr].flags &= ~IPC_MEM_WWAN_MUX;
+
+	return ret_val;
+}
+
+void ipc_mux_deinit(struct iosm_mux *ipc_mux)
+{
+	struct mux_channel_close *channel_close;
+	struct sk_buff_head *free_list;
+	union mux_msg mux_msg;
+	struct sk_buff *skb;
+
+	if (!ipc_mux->initialized)
+		return;
+	ipc_mux_stop_netif_for_all_sessions(ipc_mux);
+
+	channel_close = &mux_msg.channel_close;
+	channel_close->event = MUX_E_MUX_CHANNEL_CLOSE;
+	ipc_mux_schedule(ipc_mux, &mux_msg);
+
+	/* Empty the ADB free list. */
+	free_list = &ipc_mux->ul_adb.free_list;
+
+	/* Remove from the head of the downlink queue. */
+	while ((skb = skb_dequeue(free_list)))
+		ipc_pcie_kfree_skb(ipc_mux->pcie, skb);
+
+	if (ipc_mux->channel) {
+		ipc_mux->channel->ul_pipe.is_open = false;
+		ipc_mux->channel->dl_pipe.is_open = false;
+	}
+
+	kfree(ipc_mux);
+}
diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux.h b/drivers/net/wwan/iosm/iosm_ipc_mux.h
new file mode 100644
index 000000000000..ddd2cd0bd911
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_mux.h
@@ -0,0 +1,343 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#ifndef IOSM_IPC_MUX_H
+#define IOSM_IPC_MUX_H
+
+#include "iosm_ipc_protocol.h"
+
+/* Size of the buffer for the IP MUX data buffer. */
+#define IPC_MEM_MAX_DL_MUX_BUF_SIZE (16 * 1024)
+#define IPC_MEM_MAX_UL_ADB_BUF_SIZE IPC_MEM_MAX_DL_MUX_BUF_SIZE
+
+/* Size of the buffer for the IP MUX Lite data buffer. */
+#define IPC_MEM_MAX_DL_MUX_LITE_BUF_SIZE (2 * 1024)
+
+/* TD counts for IP MUX Lite */
+#define IPC_MEM_MAX_TDS_MUX_LITE_UL 800
+#define IPC_MEM_MAX_TDS_MUX_LITE_DL 1200
+
+/* open session request (AP->CP) */
+#define MUX_CMD_OPEN_SESSION 1
+
+/* response to open session request (CP->AP) */
+#define MUX_CMD_OPEN_SESSION_RESP 2
+
+/* close session request (AP->CP) */
+#define MUX_CMD_CLOSE_SESSION 3
+
+/* response to close session request (CP->AP) */
+#define MUX_CMD_CLOSE_SESSION_RESP 4
+
+/* Flow control command with mask of the flow per queue/flow. */
+#define MUX_LITE_CMD_FLOW_CTL 5
+
+/* ACK the flow control command. Shall have the same Transaction ID as the
+ * matching FLOW_CTL command.
+ */
+#define MUX_LITE_CMD_FLOW_CTL_ACK 6
+
+/* Command for report packet indicating link quality metrics. */
+#define MUX_LITE_CMD_LINK_STATUS_REPORT 7
+
+/* Response to a report packet */
+#define MUX_LITE_CMD_LINK_STATUS_REPORT_RESP 8
+
+/* Used to reset a command/response state. */
+#define MUX_CMD_INVALID 255
+
+/* command response : command processed successfully */
+#define MUX_CMD_RESP_SUCCESS 0
+
+/* MUX for route link devices */
+#define IPC_MEM_WWAN_MUX BIT(0)
+
+/* Initiated actions to change the state of the MUX object. */
+enum mux_event {
+	MUX_E_INACTIVE, /* No initiated actions. */
+	MUX_E_MUX_SESSION_OPEN, /* Create the MUX channel and a session. */
+	MUX_E_MUX_SESSION_CLOSE, /* Release a session. */
+	MUX_E_MUX_CHANNEL_CLOSE, /* Release the MUX channel. */
+	MUX_E_NO_ORDERS, /* No MUX order. */
+	MUX_E_NOT_APPLICABLE, /* Defect IP MUX. */
+};
+
+/* MUX session open command. */
+struct mux_session_open {
+	enum mux_event event;
+	__le32 if_id;
+};
+
+/* MUX session close command. */
+struct mux_session_close {
+	enum mux_event event;
+	__le32 if_id;
+};
+
+/* MUX channel close command. */
+struct mux_channel_close {
+	enum mux_event event;
+};
+
+/* Default message type to find out the right message type. */
+struct mux_common {
+	enum mux_event event;
+};
+
+/* List of ops in MUX mode. */
+union mux_msg {
+	struct mux_session_open session_open;
+	struct mux_session_close session_close;
+	struct mux_channel_close channel_close;
+	struct mux_common common;
+};
+
+/* Parameter definition of the open session command. */
+struct mux_cmd_open_session {
+	u8 flow_ctrl; /* 0: Flow control disabled (flow allowed). */
+	/* 1: Flow control enabled (flow not allowed)*/
+	u8 ipv4v6_hints; /* 0: IPv4/IPv6 hints not supported.*/
+	/* 1: IPv4/IPv6 hints supported*/
+	__le16 reserved2; /* Reserved. Set to zero. */
+	__le32 dl_head_pad_len; /* Maximum length supported */
+	/* for DL head padding on a datagram. */
+};
+
+/* Parameter definition of the open session response. */
+struct mux_cmd_open_session_resp {
+	__le32 response; /* Response code */
+	u8 flow_ctrl; /* 0: Flow control disabled (flow allowed). */
+	/* 1: Flow control enabled (flow not allowed) */
+	u8 ipv4v6_hints; /* 0: IPv4/IPv6 hints not supported */
+	/* 1: IPv4/IPv6 hints supported */
+	__le16 reserved2; /* Reserved. Set to zero. */
+	__le32 ul_head_pad_len; /* Actual length supported for */
+	/* UL head padding on adatagram.*/
+};
+
+/* Parameter definition of the close session response code */
+struct mux_cmd_close_session_resp {
+	__le32 response;
+};
+
+/* Parameter definition of the flow control command. */
+struct mux_cmd_flow_ctl {
+	__le32 mask; /* indicating the desired flow control */
+	/* state for various flows/queues */
+};
+
+/* Parameter definition of the link status report code*/
+struct mux_cmd_link_status_report {
+	u8 payload;
+};
+
+/* Parameter definition of the link status report response code. */
+struct mux_cmd_link_status_report_resp {
+	__le32 response;
+};
+
+/**
+ * union mux_cmd_param - Union-definition of the command parameters.
+ * @open_session:	Inband command for open session
+ * @open_session_resp:	Inband command for open session response
+ * @close_session_resp:	Inband command for close session response
+ * @flow_ctl:		In-band flow control on the opened interfaces
+ * @link_status:	In-band Link Status Report
+ * @link_status_resp:	In-band command for link status report response
+ */
+union mux_cmd_param {
+	struct mux_cmd_open_session open_session;
+	struct mux_cmd_open_session_resp open_session_resp;
+	struct mux_cmd_close_session_resp close_session_resp;
+	struct mux_cmd_flow_ctl flow_ctl;
+	struct mux_cmd_link_status_report link_status;
+	struct mux_cmd_link_status_report_resp link_status_resp;
+};
+
+/* States of the MUX object.. */
+enum mux_state {
+	MUX_S_INACTIVE, /* IP MUX is unused. */
+	MUX_S_ACTIVE, /* IP MUX channel is available. */
+	MUX_S_ERROR, /* Defect IP MUX. */
+};
+
+/* Supported MUX protocols. */
+enum ipc_mux_protocol {
+	MUX_UNKNOWN,
+	MUX_LITE,
+};
+
+/* Supported UL data transfer methods. */
+enum ipc_mux_ul_flow {
+	MUX_UL_UNKNOWN,
+	MUX_UL, /* Normal UL data transfer */
+	MUX_UL_ON_CREDITS, /* UL data transfer will be based on credits */
+};
+
+/* List of the MUX session. */
+struct mux_session {
+	struct iosm_wwan *wwan; /*Network i/f used for communication*/
+	int if_id; /* i/f id for session open message.*/
+	u32 flags;
+	u32 ul_head_pad_len; /* Nr of bytes for UL head padding. */
+	u32 dl_head_pad_len; /* Nr of bytes for DL head padding. */
+	struct sk_buff_head ul_list; /* skb entries for an ADT. */
+	u32 flow_ctl_mask; /* UL flow control */
+	u32 flow_ctl_en_cnt; /* Flow control Enable cmd count */
+	u32 flow_ctl_dis_cnt; /* Flow Control Disable cmd count */
+	int ul_flow_credits; /* UL flow credits */
+	u8 net_tx_stop:1,
+	   flush:1; /* flush net interface ? */
+};
+
+/* State of a single UL data block. */
+struct mux_adb {
+	struct sk_buff *dest_skb; /* Current UL skb for the data block. */
+	u8 *buf; /* ADB memory. */
+	struct mux_adgh *adgh; /* ADGH pointer */
+	struct sk_buff *qlth_skb; /* QLTH pointer */
+	u32 *next_table_index; /* Pointer to next table index. */
+	struct sk_buff_head free_list; /* List of alloc. ADB for the UL sess.*/
+	int size; /* Size of the ADB memory. */
+	u32 if_cnt; /* Statistic counter */
+	u32 dg_cnt_total;
+	u32 payload_size;
+};
+
+/* Temporary ACB state. */
+struct mux_acb {
+	struct sk_buff *skb; /* Used UL skb. */
+	int if_id; /* Session id. */
+	u32 wanted_response;
+	u32 got_response;
+	u32 cmd;
+	union mux_cmd_param got_param; /* Received command/response parameter */
+};
+
+/**
+ * struct iosm_mux - Structure of the data multiplexing over an IP channel.
+ * @dev:		Pointer to device structure
+ * @session:		Array of the MUX sessions.
+ * @channel:		Reference to the IP MUX channel
+ * @pcie:		Pointer to iosm_pcie struct
+ * @imem:		Pointer to iosm_imem
+ * @wwan:		Poinetr to iosm_wwan
+ * @ipc_protocol:	Pointer to iosm_protocol
+ * @channel_id:		Channel ID for MUX
+ * @protocol:		Type of the MUX protocol
+ * @ul_flow:		UL Flow type
+ * @nr_sessions:	Number of sessions
+ * @instance_id:	Instance ID
+ * @state:		States of the MUX object
+ * @event:		Initiated actions to change the state of the MUX object
+ * @tx_transaction_id:	Transaction id for the ACB command.
+ * @rr_next_session:	Next session number for round robin.
+ * @ul_adb:		State of the UL ADB/ADGH.
+ * @size_needed:	Variable to store the size needed during ADB preparation
+ * @ul_data_pend_bytes:	Pending UL data to be processed in bytes
+ * @acb:		Temporary ACB state
+ * @wwan_q_offset:	This will hold the offset of the given instance
+ *			Useful while passing or receiving packets from
+ *			wwan/imem layer.
+ * @initialized:	MUX object is initialized
+ * @ev_mux_net_transmit_pending:
+ *			0 means inform the IPC tasklet to pass the
+ *			accumulated uplink ADB to CP.
+ * @adb_prep_ongoing:	Flag for ADB preparation status
+ */
+struct iosm_mux {
+	struct device *dev;
+	struct mux_session session[IPC_MEM_MUX_IP_SESSION_ENTRIES];
+	struct ipc_mem_channel *channel;
+	struct iosm_pcie *pcie;
+	struct iosm_imem *imem;
+	struct iosm_wwan *wwan;
+	struct iosm_protocol *ipc_protocol;
+	int channel_id;
+	enum ipc_mux_protocol protocol;
+	enum ipc_mux_ul_flow ul_flow;
+	int nr_sessions;
+	int instance_id;
+	enum mux_state state;
+	enum mux_event event;
+	u32 tx_transaction_id;
+	int rr_next_session;
+	struct mux_adb ul_adb;
+	int size_needed;
+	long long ul_data_pend_bytes;
+	struct mux_acb acb;
+	int wwan_q_offset;
+	u8 initialized:1,
+	   ev_mux_net_transmit_pending:1,
+	   adb_prep_ongoing:1;
+};
+
+/* MUX configuration structure */
+struct ipc_mux_config {
+	enum ipc_mux_protocol protocol;
+	enum ipc_mux_ul_flow ul_flow;
+	int nr_sessions;
+	int instance_id;
+};
+
+/**
+ * ipc_mux_init - Allocates and Init MUX instance
+ * @mux_cfg:	Pointer to MUX configuration structure
+ * @ipc_imem:	Pointer to imem data-struct
+ *
+ * Returns: Initialized mux pointer on success else NULL
+ */
+struct iosm_mux *ipc_mux_init(struct ipc_mux_config *mux_cfg,
+			      struct iosm_imem *ipc_imem);
+
+/**
+ * ipc_mux_deinit - Deallocates MUX instance
+ * @ipc_mux:	Pointer to the MUX instance.
+ */
+void ipc_mux_deinit(struct iosm_mux *ipc_mux);
+
+/**
+ * ipc_mux_check_n_restart_tx - Checks for pending UL date bytes and then
+ *				it restarts the net interface tx queue if
+ *				device has set flow control as off.
+ * @ipc_mux:	Pointer to MUX data-struct
+ */
+void ipc_mux_check_n_restart_tx(struct iosm_mux *ipc_mux);
+
+/**
+ * ipc_mux_get_active_protocol - Returns the active MUX protocol type.
+ * @ipc_mux:	Pointer to MUX data-struct
+ *
+ * Returns: enum of type ipc_mux_protocol
+ */
+enum ipc_mux_protocol ipc_mux_get_active_protocol(struct iosm_mux *ipc_mux);
+
+/**
+ * ipc_mux_open_session - Opens a MUX session for IP traffic.
+ * @ipc_mux:	Pointer to MUX data-struct
+ * @session_nr:	Interface ID or session number
+ *
+ * Returns: channel id on success, failure value on error
+ */
+int ipc_mux_open_session(struct iosm_mux *ipc_mux, int session_nr);
+
+/**
+ * ipc_mux_close_session - Closes a MUX session.
+ * @ipc_mux:	Pointer to MUX data-struct
+ * @session_nr:	Interface ID or session number
+ *
+ * Returns: channel id on success, failure value on error
+ */
+int ipc_mux_close_session(struct iosm_mux *ipc_mux, int session_nr);
+
+/**
+ * ipc_mux_get_max_sessions - Retuns the maximum sessions supported on the
+ *			      provided MUX instance..
+ * @ipc_mux:	Pointer to MUX data-struct
+ *
+ * Returns: Number of sessions supported on Success and failure value on error
+ */
+int ipc_mux_get_max_sessions(struct iosm_mux *ipc_mux);
+#endif
diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c
new file mode 100644
index 000000000000..fbf3cab3394c
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c
@@ -0,0 +1,910 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#include <linux/nospec.h>
+
+#include "iosm_ipc_imem_ops.h"
+#include "iosm_ipc_mux_codec.h"
+#include "iosm_ipc_task_queue.h"
+
+/* Test the link power state and send a MUX command in blocking mode. */
+static int ipc_mux_tq_cmd_send(struct iosm_imem *ipc_imem, int arg, void *msg,
+			       size_t size)
+{
+	struct iosm_mux *ipc_mux = ipc_imem->mux;
+	const struct mux_acb *acb = msg;
+
+	skb_queue_tail(&ipc_mux->channel->ul_list, acb->skb);
+	ipc_imem_ul_send(ipc_mux->imem);
+
+	return 0;
+}
+
+static int ipc_mux_acb_send(struct iosm_mux *ipc_mux, bool blocking)
+{
+	struct completion *completion = &ipc_mux->channel->ul_sem;
+	int ret = ipc_task_queue_send_task(ipc_mux->imem, ipc_mux_tq_cmd_send,
+					   0, &ipc_mux->acb,
+					   sizeof(ipc_mux->acb), false);
+	if (ret) {
+		dev_err(ipc_mux->dev, "unable to send mux command");
+		return ret;
+	}
+
+	/* if blocking, suspend the app and wait for irq in the flash or
+	 * crash phase. return false on timeout to indicate failure.
+	 */
+	if (blocking) {
+		u32 wait_time_milliseconds = IPC_MUX_CMD_RUN_DEFAULT_TIMEOUT;
+
+		reinit_completion(completion);
+
+		if (wait_for_completion_interruptible_timeout
+		   (completion, msecs_to_jiffies(wait_time_milliseconds)) ==
+		   0) {
+			dev_err(ipc_mux->dev, "ch[%d] timeout",
+				ipc_mux->channel_id);
+			ipc_uevent_send(ipc_mux->imem->dev, UEVENT_MDM_TIMEOUT);
+			return -ETIMEDOUT;
+		}
+	}
+
+	return 0;
+}
+
+/* Prepare mux Command */
+static struct mux_lite_cmdh *ipc_mux_lite_add_cmd(struct iosm_mux *ipc_mux,
+						  u32 cmd, struct mux_acb *acb,
+						  void *param, u32 param_size)
+{
+	struct mux_lite_cmdh *cmdh = (struct mux_lite_cmdh *)acb->skb->data;
+
+	cmdh->signature = cpu_to_le32(MUX_SIG_CMDH);
+	cmdh->command_type = cpu_to_le32(cmd);
+	cmdh->if_id = acb->if_id;
+
+	acb->cmd = cmd;
+
+	cmdh->cmd_len = cpu_to_le16(offsetof(struct mux_lite_cmdh, param) +
+				    param_size);
+	cmdh->transaction_id = cpu_to_le32(ipc_mux->tx_transaction_id++);
+
+	if (param)
+		memcpy(&cmdh->param, param, param_size);
+
+	skb_put(acb->skb, le16_to_cpu(cmdh->cmd_len));
+
+	return cmdh;
+}
+
+static int ipc_mux_acb_alloc(struct iosm_mux *ipc_mux)
+{
+	struct mux_acb *acb = &ipc_mux->acb;
+	struct sk_buff *skb;
+	dma_addr_t mapping;
+
+	/* Allocate skb memory for the uplink buffer. */
+	skb = ipc_pcie_alloc_skb(ipc_mux->pcie, MUX_MAX_UL_ACB_BUF_SIZE,
+				 GFP_ATOMIC, &mapping, DMA_TO_DEVICE, 0);
+	if (!skb)
+		return -ENOMEM;
+
+	/* Save the skb address. */
+	acb->skb = skb;
+
+	memset(skb->data, 0, MUX_MAX_UL_ACB_BUF_SIZE);
+
+	return 0;
+}
+
+int ipc_mux_dl_acb_send_cmds(struct iosm_mux *ipc_mux, u32 cmd_type, u8 if_id,
+			     u32 transaction_id, union mux_cmd_param *param,
+			     size_t res_size, bool blocking, bool respond)
+{
+	struct mux_acb *acb = &ipc_mux->acb;
+	struct mux_lite_cmdh *ack_lite;
+	int ret = 0;
+
+	acb->if_id = if_id;
+	ret = ipc_mux_acb_alloc(ipc_mux);
+	if (ret)
+		return ret;
+
+	ack_lite = ipc_mux_lite_add_cmd(ipc_mux, cmd_type, acb, param,
+					res_size);
+	if (respond)
+		ack_lite->transaction_id = cpu_to_le32(transaction_id);
+
+	ret = ipc_mux_acb_send(ipc_mux, blocking);
+
+	return ret;
+}
+
+void ipc_mux_netif_tx_flowctrl(struct mux_session *session, int idx, bool on)
+{
+	/* Inform the network interface to start/stop flow ctrl */
+	ipc_wwan_tx_flowctrl(session->wwan, idx, on);
+}
+
+static int ipc_mux_dl_cmdresps_decode_process(struct iosm_mux *ipc_mux,
+					      struct mux_lite_cmdh *cmdh)
+{
+	struct mux_acb *acb = &ipc_mux->acb;
+
+	switch (le32_to_cpu(cmdh->command_type)) {
+	case MUX_CMD_OPEN_SESSION_RESP:
+	case MUX_CMD_CLOSE_SESSION_RESP:
+		/* Resume the control application. */
+		acb->got_param = cmdh->param;
+		break;
+
+	case MUX_LITE_CMD_FLOW_CTL_ACK:
+		/* This command type is not expected as response for
+		 * Aggregation version of the protocol. So return non-zero.
+		 */
+		if (ipc_mux->protocol != MUX_LITE)
+			return -EINVAL;
+
+		dev_dbg(ipc_mux->dev, "if %u FLOW_CTL_ACK %u received",
+			cmdh->if_id, le32_to_cpu(cmdh->transaction_id));
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	acb->wanted_response = MUX_CMD_INVALID;
+	acb->got_response = le32_to_cpu(cmdh->command_type);
+	complete(&ipc_mux->channel->ul_sem);
+
+	return 0;
+}
+
+static int ipc_mux_dl_dlcmds_decode_process(struct iosm_mux *ipc_mux,
+					    struct mux_lite_cmdh *cmdh)
+{
+	union mux_cmd_param *param = &cmdh->param;
+	struct mux_session *session;
+	int new_size;
+
+	dev_dbg(ipc_mux->dev, "if_id[%d]: dlcmds decode process %d",
+		cmdh->if_id, le32_to_cpu(cmdh->command_type));
+
+	switch (le32_to_cpu(cmdh->command_type)) {
+	case MUX_LITE_CMD_FLOW_CTL:
+
+		if (cmdh->if_id >= ipc_mux->nr_sessions) {
+			dev_err(ipc_mux->dev, "if_id [%d] not valid",
+				cmdh->if_id);
+			return -EINVAL; /* No session interface id. */
+		}
+
+		session = &ipc_mux->session[cmdh->if_id];
+
+		new_size = offsetof(struct mux_lite_cmdh, param) +
+			   sizeof(param->flow_ctl);
+		if (param->flow_ctl.mask == cpu_to_le32(0xFFFFFFFF)) {
+			/* Backward Compatibility */
+			if (cmdh->cmd_len == cpu_to_le16(new_size))
+				session->flow_ctl_mask =
+					le32_to_cpu(param->flow_ctl.mask);
+			else
+				session->flow_ctl_mask = ~0;
+			/* if CP asks for FLOW CTRL Enable
+			 * then set our internal flow control Tx flag
+			 * to limit uplink session queueing
+			 */
+			session->net_tx_stop = true;
+			/* Update the stats */
+			session->flow_ctl_en_cnt++;
+		} else if (param->flow_ctl.mask == 0) {
+			/* Just reset the Flow control mask and let
+			 * mux_flow_ctrl_low_thre_b take control on
+			 * our internal Tx flag and enabling kernel
+			 * flow control
+			 */
+			/* Backward Compatibility */
+			if (cmdh->cmd_len == cpu_to_le16(new_size))
+				session->flow_ctl_mask =
+					le32_to_cpu(param->flow_ctl.mask);
+			else
+				session->flow_ctl_mask = 0;
+			/* Update the stats */
+			session->flow_ctl_dis_cnt++;
+		} else {
+			break;
+		}
+
+		dev_dbg(ipc_mux->dev, "if[%u] FLOW CTRL 0x%08X", cmdh->if_id,
+			le32_to_cpu(param->flow_ctl.mask));
+		break;
+
+	case MUX_LITE_CMD_LINK_STATUS_REPORT:
+		break;
+
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/* Decode and Send appropriate response to a command block. */
+static void ipc_mux_dl_cmd_decode(struct iosm_mux *ipc_mux, struct sk_buff *skb)
+{
+	struct mux_lite_cmdh *cmdh = (struct mux_lite_cmdh *)skb->data;
+	__le32 trans_id = cmdh->transaction_id;
+
+	if (ipc_mux_dl_cmdresps_decode_process(ipc_mux, cmdh)) {
+		/* Unable to decode command response indicates the cmd_type
+		 * may be a command instead of response. So try to decoding it.
+		 */
+		if (!ipc_mux_dl_dlcmds_decode_process(ipc_mux, cmdh)) {
+			/* Decoded command may need a response. Give the
+			 * response according to the command type.
+			 */
+			union mux_cmd_param *mux_cmd = NULL;
+			size_t size = 0;
+			u32 cmd = MUX_LITE_CMD_LINK_STATUS_REPORT_RESP;
+
+			if (cmdh->command_type ==
+			    cpu_to_le32(MUX_LITE_CMD_LINK_STATUS_REPORT)) {
+				mux_cmd = &cmdh->param;
+				mux_cmd->link_status_resp.response =
+					cpu_to_le32(MUX_CMD_RESP_SUCCESS);
+				/* response field is u32 */
+				size = sizeof(u32);
+			} else if (cmdh->command_type ==
+				   cpu_to_le32(MUX_LITE_CMD_FLOW_CTL)) {
+				cmd = MUX_LITE_CMD_FLOW_CTL_ACK;
+			} else {
+				return;
+			}
+
+			if (ipc_mux_dl_acb_send_cmds(ipc_mux, cmd, cmdh->if_id,
+						     le32_to_cpu(trans_id),
+						     mux_cmd, size, false,
+						     true))
+				dev_err(ipc_mux->dev,
+					"if_id %d: cmd send failed",
+					cmdh->if_id);
+		}
+	}
+}
+
+/* Pass the DL packet to the netif layer. */
+static int ipc_mux_net_receive(struct iosm_mux *ipc_mux, int if_id,
+			       struct iosm_wwan *wwan, u32 offset,
+			       u8 service_class, struct sk_buff *skb)
+{
+	struct sk_buff *dest_skb = skb_clone(skb, GFP_ATOMIC);
+
+	if (!dest_skb)
+		return -ENOMEM;
+
+	skb_pull(dest_skb, offset);
+	skb_set_tail_pointer(dest_skb, dest_skb->len);
+	/* Pass the packet to the netif layer. */
+	dest_skb->priority = service_class;
+
+	return ipc_wwan_receive(wwan, dest_skb, false, if_id + 1);
+}
+
+/* Decode Flow Credit Table in the block */
+static void ipc_mux_dl_fcth_decode(struct iosm_mux *ipc_mux,
+				   unsigned char *block)
+{
+	struct ipc_mem_lite_gen_tbl *fct = (struct ipc_mem_lite_gen_tbl *)block;
+	struct iosm_wwan *wwan;
+	int ul_credits;
+	int if_id;
+
+	if (fct->vfl_length != sizeof(fct->vfl.nr_of_bytes)) {
+		dev_err(ipc_mux->dev, "unexpected FCT length: %d",
+			fct->vfl_length);
+		return;
+	}
+
+	if_id = fct->if_id;
+	if (if_id >= ipc_mux->nr_sessions) {
+		dev_err(ipc_mux->dev, "not supported if_id: %d", if_id);
+		return;
+	}
+
+	/* Is the session active ? */
+	if_id = array_index_nospec(if_id, ipc_mux->nr_sessions);
+	wwan = ipc_mux->session[if_id].wwan;
+	if (!wwan) {
+		dev_err(ipc_mux->dev, "session Net ID is NULL");
+		return;
+	}
+
+	ul_credits = fct->vfl.nr_of_bytes;
+
+	dev_dbg(ipc_mux->dev, "Flow_Credit:: if_id[%d] Old: %d Grants: %d",
+		if_id, ipc_mux->session[if_id].ul_flow_credits, ul_credits);
+
+	/* Update the Flow Credit information from ADB */
+	ipc_mux->session[if_id].ul_flow_credits += ul_credits;
+
+	/* Check whether the TX can be started */
+	if (ipc_mux->session[if_id].ul_flow_credits > 0) {
+		ipc_mux->session[if_id].net_tx_stop = false;
+		ipc_mux_netif_tx_flowctrl(&ipc_mux->session[if_id],
+					  ipc_mux->session[if_id].if_id, false);
+	}
+}
+
+/* Decode non-aggregated datagram */
+static void ipc_mux_dl_adgh_decode(struct iosm_mux *ipc_mux,
+				   struct sk_buff *skb)
+{
+	u32 pad_len, packet_offset;
+	struct iosm_wwan *wwan;
+	struct mux_adgh *adgh;
+	u8 *block = skb->data;
+	int rc = 0;
+	u8 if_id;
+
+	adgh = (struct mux_adgh *)block;
+
+	if (adgh->signature != cpu_to_le32(MUX_SIG_ADGH)) {
+		dev_err(ipc_mux->dev, "invalid ADGH signature received");
+		return;
+	}
+
+	if_id = adgh->if_id;
+	if (if_id >= ipc_mux->nr_sessions) {
+		dev_err(ipc_mux->dev, "invalid if_id while decoding %d", if_id);
+		return;
+	}
+
+	/* Is the session active ? */
+	if_id = array_index_nospec(if_id, ipc_mux->nr_sessions);
+	wwan = ipc_mux->session[if_id].wwan;
+	if (!wwan) {
+		dev_err(ipc_mux->dev, "session Net ID is NULL");
+		return;
+	}
+
+	/* Store the pad len for the corresponding session
+	 * Pad bytes as negotiated in the open session less the header size
+	 * (see session management chapter for details).
+	 * If resulting padding is zero or less, the additional head padding is
+	 * omitted. For e.g., if HEAD_PAD_LEN = 16 or less, this field is
+	 * omitted if HEAD_PAD_LEN = 20, then this field will have 4 bytes
+	 * set to zero
+	 */
+	pad_len =
+		ipc_mux->session[if_id].dl_head_pad_len - IPC_MEM_DL_ETH_OFFSET;
+	packet_offset = sizeof(*adgh) + pad_len;
+
+	if_id += ipc_mux->wwan_q_offset;
+
+	/* Pass the packet to the netif layer */
+	rc = ipc_mux_net_receive(ipc_mux, if_id, wwan, packet_offset,
+				 adgh->service_class, skb);
+	if (rc) {
+		dev_err(ipc_mux->dev, "mux adgh decoding error");
+		return;
+	}
+	ipc_mux->session[if_id].flush = 1;
+}
+
+void ipc_mux_dl_decode(struct iosm_mux *ipc_mux, struct sk_buff *skb)
+{
+	u32 signature;
+
+	if (!skb->data)
+		return;
+
+	/* Decode the MUX header type. */
+	signature = le32_to_cpup((__le32 *)skb->data);
+
+	switch (signature) {
+	case MUX_SIG_ADGH:
+		ipc_mux_dl_adgh_decode(ipc_mux, skb);
+		break;
+
+	case MUX_SIG_FCTH:
+		ipc_mux_dl_fcth_decode(ipc_mux, skb->data);
+		break;
+
+	case MUX_SIG_CMDH:
+		ipc_mux_dl_cmd_decode(ipc_mux, skb);
+		break;
+
+	default:
+		dev_err(ipc_mux->dev, "invalid ABH signature");
+	}
+
+	ipc_pcie_kfree_skb(ipc_mux->pcie, skb);
+}
+
+static int ipc_mux_ul_skb_alloc(struct iosm_mux *ipc_mux,
+				struct mux_adb *ul_adb, u32 type)
+{
+	/* Take the first element of the free list. */
+	struct sk_buff *skb = skb_dequeue(&ul_adb->free_list);
+	int qlt_size;
+
+	if (!skb)
+		return -EBUSY; /* Wait for a free ADB skb. */
+
+	/* Mark it as UL ADB to select the right free operation. */
+	IPC_CB(skb)->op_type = (u8)UL_MUX_OP_ADB;
+
+	switch (type) {
+	case MUX_SIG_ADGH:
+		/* Save the ADB memory settings. */
+		ul_adb->dest_skb = skb;
+		ul_adb->buf = skb->data;
+		ul_adb->size = IPC_MEM_MAX_DL_MUX_LITE_BUF_SIZE;
+		/* reset statistic counter */
+		ul_adb->if_cnt = 0;
+		ul_adb->payload_size = 0;
+		ul_adb->dg_cnt_total = 0;
+
+		ul_adb->adgh = (struct mux_adgh *)skb->data;
+		memset(ul_adb->adgh, 0, sizeof(struct mux_adgh));
+		break;
+
+	case MUX_SIG_QLTH:
+		qlt_size = offsetof(struct ipc_mem_lite_gen_tbl, vfl) +
+			   (MUX_QUEUE_LEVEL * sizeof(struct mux_lite_vfl));
+
+		if (qlt_size > IPC_MEM_MAX_DL_MUX_LITE_BUF_SIZE) {
+			dev_err(ipc_mux->dev,
+				"can't support. QLT size:%d SKB size: %d",
+				qlt_size, IPC_MEM_MAX_DL_MUX_LITE_BUF_SIZE);
+			return -ERANGE;
+		}
+
+		ul_adb->qlth_skb = skb;
+		memset((ul_adb->qlth_skb)->data, 0, qlt_size);
+		skb_put(skb, qlt_size);
+		break;
+	}
+
+	return 0;
+}
+
+static void ipc_mux_ul_adgh_finish(struct iosm_mux *ipc_mux)
+{
+	struct mux_adb *ul_adb = &ipc_mux->ul_adb;
+	u16 adgh_len;
+	long long bytes;
+	char *str;
+
+	if (!ul_adb || !ul_adb->dest_skb) {
+		dev_err(ipc_mux->dev, "no dest skb");
+		return;
+	}
+
+	adgh_len = le16_to_cpu(ul_adb->adgh->length);
+	skb_put(ul_adb->dest_skb, adgh_len);
+	skb_queue_tail(&ipc_mux->channel->ul_list, ul_adb->dest_skb);
+	ul_adb->dest_skb = NULL;
+
+	if (ipc_mux->ul_flow == MUX_UL_ON_CREDITS) {
+		struct mux_session *session;
+
+		session = &ipc_mux->session[ul_adb->adgh->if_id];
+		str = "available_credits";
+		bytes = (long long)session->ul_flow_credits;
+
+	} else {
+		str = "pend_bytes";
+		bytes = ipc_mux->ul_data_pend_bytes;
+		ipc_mux->ul_data_pend_bytes = ipc_mux->ul_data_pend_bytes +
+					      adgh_len;
+	}
+
+	dev_dbg(ipc_mux->dev, "UL ADGH: size=%u, if_id=%d, payload=%d, %s=%lld",
+		adgh_len, ul_adb->adgh->if_id, ul_adb->payload_size,
+		str, bytes);
+}
+
+/* Allocates an ADB from the free list and initializes it with ADBH  */
+static bool ipc_mux_ul_adb_allocate(struct iosm_mux *ipc_mux,
+				    struct mux_adb *adb, int *size_needed,
+				    u32 type)
+{
+	bool ret_val = false;
+	int status;
+
+	if (!adb->dest_skb) {
+		/* Allocate memory for the ADB including of the
+		 * datagram table header.
+		 */
+		status = ipc_mux_ul_skb_alloc(ipc_mux, adb, type);
+		if (status)
+			/* Is a pending ADB available ? */
+			ret_val = true; /* None. */
+
+		/* Update size need to zero only for new ADB memory */
+		*size_needed = 0;
+	}
+
+	return ret_val;
+}
+
+/* Informs the network stack to stop sending further packets for all opened
+ * sessions
+ */
+static void ipc_mux_stop_tx_for_all_sessions(struct iosm_mux *ipc_mux)
+{
+	struct mux_session *session;
+	int idx;
+
+	for (idx = 0; idx < ipc_mux->nr_sessions; idx++) {
+		session = &ipc_mux->session[idx];
+
+		if (!session->wwan)
+			continue;
+
+		session->net_tx_stop = true;
+	}
+}
+
+/* Sends Queue Level Table of all opened sessions */
+static bool ipc_mux_lite_send_qlt(struct iosm_mux *ipc_mux)
+{
+	struct ipc_mem_lite_gen_tbl *qlt;
+	struct mux_session *session;
+	bool qlt_updated = false;
+	int i;
+	int qlt_size;
+
+	if (!ipc_mux->initialized || ipc_mux->state != MUX_S_ACTIVE)
+		return qlt_updated;
+
+	qlt_size = offsetof(struct ipc_mem_lite_gen_tbl, vfl) +
+		   MUX_QUEUE_LEVEL * sizeof(struct mux_lite_vfl);
+
+	for (i = 0; i < ipc_mux->nr_sessions; i++) {
+		session = &ipc_mux->session[i];
+
+		if (!session->wwan || session->flow_ctl_mask)
+			continue;
+
+		if (ipc_mux_ul_skb_alloc(ipc_mux, &ipc_mux->ul_adb,
+					 MUX_SIG_QLTH)) {
+			dev_err(ipc_mux->dev,
+				"no reserved mem to send QLT of if_id: %d", i);
+			break;
+		}
+
+		/* Prepare QLT */
+		qlt = (struct ipc_mem_lite_gen_tbl *)(ipc_mux->ul_adb.qlth_skb)
+			      ->data;
+		qlt->signature = cpu_to_le32(MUX_SIG_QLTH);
+		qlt->length = cpu_to_le16(qlt_size);
+		qlt->if_id = i;
+		qlt->vfl_length = MUX_QUEUE_LEVEL * sizeof(struct mux_lite_vfl);
+		qlt->reserved[0] = 0;
+		qlt->reserved[1] = 0;
+
+		qlt->vfl.nr_of_bytes = session->ul_list.qlen;
+
+		/* Add QLT to the transfer list. */
+		skb_queue_tail(&ipc_mux->channel->ul_list,
+			       ipc_mux->ul_adb.qlth_skb);
+
+		qlt_updated = true;
+		ipc_mux->ul_adb.qlth_skb = NULL;
+	}
+
+	if (qlt_updated)
+		/* Updates the TDs with ul_list */
+		(void)ipc_imem_ul_write_td(ipc_mux->imem);
+
+	return qlt_updated;
+}
+
+/* Checks the available credits for the specified session and returns
+ * number of packets for which credits are available.
+ */
+static int ipc_mux_ul_bytes_credits_check(struct iosm_mux *ipc_mux,
+					  struct mux_session *session,
+					  struct sk_buff_head *ul_list,
+					  int max_nr_of_pkts)
+{
+	int pkts_to_send = 0;
+	struct sk_buff *skb;
+	int credits = 0;
+
+	if (ipc_mux->ul_flow == MUX_UL_ON_CREDITS) {
+		credits = session->ul_flow_credits;
+		if (credits <= 0) {
+			dev_dbg(ipc_mux->dev,
+				"FC::if_id[%d] Insuff.Credits/Qlen:%d/%u",
+				session->if_id, session->ul_flow_credits,
+				session->ul_list.qlen); /* nr_of_bytes */
+			return 0;
+		}
+	} else {
+		credits = IPC_MEM_MUX_UL_FLOWCTRL_HIGH_B -
+			  ipc_mux->ul_data_pend_bytes;
+		if (credits <= 0) {
+			ipc_mux_stop_tx_for_all_sessions(ipc_mux);
+
+			dev_dbg(ipc_mux->dev,
+				"if_id[%d] encod. fail Bytes: %llu, thresh: %d",
+				session->if_id, ipc_mux->ul_data_pend_bytes,
+				IPC_MEM_MUX_UL_FLOWCTRL_HIGH_B);
+			return 0;
+		}
+	}
+
+	/* Check if there are enough credits/bytes available to send the
+	 * requested max_nr_of_pkts. Otherwise restrict the nr_of_pkts
+	 * depending on available credits.
+	 */
+	skb_queue_walk(ul_list, skb)
+	{
+		if (!(credits >= skb->len && pkts_to_send < max_nr_of_pkts))
+			break;
+		credits -= skb->len;
+		pkts_to_send++;
+	}
+
+	return pkts_to_send;
+}
+
+/* Encode the UL IP packet according to Lite spec. */
+static int ipc_mux_ul_adgh_encode(struct iosm_mux *ipc_mux, int session_id,
+				  struct mux_session *session,
+				  struct sk_buff_head *ul_list,
+				  struct mux_adb *adb, int nr_of_pkts)
+{
+	int offset = sizeof(struct mux_adgh);
+	int adb_updated = -EINVAL;
+	struct sk_buff *src_skb;
+	int aligned_size = 0;
+	int nr_of_skb = 0;
+	u32 pad_len = 0;
+
+	/* Re-calculate the number of packets depending on number of bytes to be
+	 * processed/available credits.
+	 */
+	nr_of_pkts = ipc_mux_ul_bytes_credits_check(ipc_mux, session, ul_list,
+						    nr_of_pkts);
+
+	/* If calculated nr_of_pkts from available credits is <= 0
+	 * then nothing to do.
+	 */
+	if (nr_of_pkts <= 0)
+		return 0;
+
+	/* Read configured UL head_pad_length for session.*/
+	if (session->ul_head_pad_len > IPC_MEM_DL_ETH_OFFSET)
+		pad_len = session->ul_head_pad_len - IPC_MEM_DL_ETH_OFFSET;
+
+	/* Process all pending UL packets for this session
+	 * depending on the allocated datagram table size.
+	 */
+	while (nr_of_pkts > 0) {
+		/* get destination skb allocated */
+		if (ipc_mux_ul_adb_allocate(ipc_mux, adb, &ipc_mux->size_needed,
+					    MUX_SIG_ADGH)) {
+			dev_err(ipc_mux->dev, "no reserved memory for ADGH");
+			return -ENOMEM;
+		}
+
+		/* Peek at the head of the list. */
+		src_skb = skb_peek(ul_list);
+		if (!src_skb) {
+			dev_err(ipc_mux->dev,
+				"skb peek return NULL with count : %d",
+				nr_of_pkts);
+			break;
+		}
+
+		/* Calculate the memory value. */
+		aligned_size = ALIGN((pad_len + src_skb->len), 4);
+
+		ipc_mux->size_needed = sizeof(struct mux_adgh) + aligned_size;
+
+		if (ipc_mux->size_needed > adb->size) {
+			dev_dbg(ipc_mux->dev, "size needed %d, adgh size %d",
+				ipc_mux->size_needed, adb->size);
+			/* Return 1 if any IP packet is added to the transfer
+			 * list.
+			 */
+			return nr_of_skb ? 1 : 0;
+		}
+
+		/* Add buffer (without head padding to next pending transfer) */
+		memcpy(adb->buf + offset + pad_len, src_skb->data,
+		       src_skb->len);
+
+		adb->adgh->signature = cpu_to_le32(MUX_SIG_ADGH);
+		adb->adgh->if_id = session_id;
+		adb->adgh->length =
+			cpu_to_le16(sizeof(struct mux_adgh) + pad_len +
+				    src_skb->len);
+		adb->adgh->service_class = src_skb->priority;
+		adb->adgh->next_count = --nr_of_pkts;
+		adb->dg_cnt_total++;
+		adb->payload_size += src_skb->len;
+
+		if (ipc_mux->ul_flow == MUX_UL_ON_CREDITS)
+			/* Decrement the credit value as we are processing the
+			 * datagram from the UL list.
+			 */
+			session->ul_flow_credits -= src_skb->len;
+
+		/* Remove the processed elements and free it. */
+		src_skb = skb_dequeue(ul_list);
+		dev_kfree_skb(src_skb);
+		nr_of_skb++;
+
+		ipc_mux_ul_adgh_finish(ipc_mux);
+	}
+
+	if (nr_of_skb) {
+		/* Send QLT info to modem if pending bytes > high watermark
+		 * in case of mux lite
+		 */
+		if (ipc_mux->ul_flow == MUX_UL_ON_CREDITS ||
+		    ipc_mux->ul_data_pend_bytes >=
+			    IPC_MEM_MUX_UL_FLOWCTRL_LOW_B)
+			adb_updated = ipc_mux_lite_send_qlt(ipc_mux);
+		else
+			adb_updated = 1;
+
+		/* Updates the TDs with ul_list */
+		(void)ipc_imem_ul_write_td(ipc_mux->imem);
+	}
+
+	return adb_updated;
+}
+
+bool ipc_mux_ul_data_encode(struct iosm_mux *ipc_mux)
+{
+	struct sk_buff_head *ul_list;
+	struct mux_session *session;
+	int updated = 0;
+	int session_id;
+	int dg_n;
+	int i;
+
+	if (!ipc_mux || ipc_mux->state != MUX_S_ACTIVE ||
+	    ipc_mux->adb_prep_ongoing)
+		return false;
+
+	ipc_mux->adb_prep_ongoing = true;
+
+	for (i = 0; i < ipc_mux->nr_sessions; i++) {
+		session_id = ipc_mux->rr_next_session;
+		session = &ipc_mux->session[session_id];
+
+		/* Go to next handle rr_next_session overflow */
+		ipc_mux->rr_next_session++;
+		if (ipc_mux->rr_next_session >= ipc_mux->nr_sessions)
+			ipc_mux->rr_next_session = 0;
+
+		if (!session->wwan || session->flow_ctl_mask ||
+		    session->net_tx_stop)
+			continue;
+
+		ul_list = &session->ul_list;
+
+		/* Is something pending in UL and flow ctrl off */
+		dg_n = skb_queue_len(ul_list);
+		if (dg_n > MUX_MAX_UL_DG_ENTRIES)
+			dg_n = MUX_MAX_UL_DG_ENTRIES;
+
+		if (dg_n == 0)
+			/* Nothing to do for ipc_mux session
+			 * -> try next session id.
+			 */
+			continue;
+
+		updated = ipc_mux_ul_adgh_encode(ipc_mux, session_id, session,
+						 ul_list, &ipc_mux->ul_adb,
+						 dg_n);
+	}
+
+	ipc_mux->adb_prep_ongoing = false;
+	return updated == 1;
+}
+
+void ipc_mux_ul_encoded_process(struct iosm_mux *ipc_mux, struct sk_buff *skb)
+{
+	struct mux_adgh *adgh;
+	u16 adgh_len;
+
+	adgh = (struct mux_adgh *)skb->data;
+	adgh_len = le16_to_cpu(adgh->length);
+
+	if (adgh->signature == cpu_to_le32(MUX_SIG_ADGH) &&
+	    ipc_mux->ul_flow == MUX_UL)
+		ipc_mux->ul_data_pend_bytes = ipc_mux->ul_data_pend_bytes -
+					      adgh_len;
+
+	if (ipc_mux->ul_flow == MUX_UL)
+		dev_dbg(ipc_mux->dev, "ul_data_pend_bytes: %lld",
+			ipc_mux->ul_data_pend_bytes);
+
+	/* Reset the skb settings. */
+	skb->tail = 0;
+	skb->len = 0;
+
+	/* Add the consumed ADB to the free list. */
+	skb_queue_tail((&ipc_mux->ul_adb.free_list), skb);
+}
+
+/* Start the NETIF uplink send transfer in MUX mode. */
+static int ipc_mux_tq_ul_trigger_encode(struct iosm_imem *ipc_imem, int arg,
+					void *msg, size_t size)
+{
+	struct iosm_mux *ipc_mux = ipc_imem->mux;
+	bool ul_data_pend = false;
+
+	/* Add session UL data to a ADB and ADGH */
+	ul_data_pend = ipc_mux_ul_data_encode(ipc_mux);
+	if (ul_data_pend)
+		/* Delay the doorbell irq */
+		ipc_imem_td_update_timer_start(ipc_mux->imem);
+
+	/* reset the debounce flag */
+	ipc_mux->ev_mux_net_transmit_pending = false;
+
+	return 0;
+}
+
+int ipc_mux_ul_trigger_encode(struct iosm_mux *ipc_mux, int if_id,
+			      struct sk_buff *skb)
+{
+	struct mux_session *session = &ipc_mux->session[if_id];
+	int ret = -EINVAL;
+
+	if (ipc_mux->channel &&
+	    ipc_mux->channel->state != IMEM_CHANNEL_ACTIVE) {
+		dev_err(ipc_mux->dev,
+			"channel state is not IMEM_CHANNEL_ACTIVE");
+		goto out;
+	}
+
+	if (!session->wwan) {
+		dev_err(ipc_mux->dev, "session net ID is NULL");
+		ret = -EFAULT;
+		goto out;
+	}
+
+	/* Session is under flow control.
+	 * Check if packet can be queued in session list, if not
+	 * suspend net tx
+	 */
+	if (skb_queue_len(&session->ul_list) >=
+	    (session->net_tx_stop ?
+		     IPC_MEM_MUX_UL_SESS_FCON_THRESHOLD :
+		     (IPC_MEM_MUX_UL_SESS_FCON_THRESHOLD *
+		      IPC_MEM_MUX_UL_SESS_FCOFF_THRESHOLD_FACTOR))) {
+		ipc_mux_netif_tx_flowctrl(session, session->if_id, true);
+		ret = -EBUSY;
+		goto out;
+	}
+
+	/* Add skb to the uplink skb accumulator. */
+	skb_queue_tail(&session->ul_list, skb);
+
+	/* Inform the IPC kthread to pass uplink IP packets to CP. */
+	if (!ipc_mux->ev_mux_net_transmit_pending) {
+		ipc_mux->ev_mux_net_transmit_pending = true;
+		ret = ipc_task_queue_send_task(ipc_mux->imem,
+					       ipc_mux_tq_ul_trigger_encode, 0,
+					       NULL, 0, false);
+		if (ret)
+			goto out;
+	}
+	dev_dbg(ipc_mux->dev, "mux ul if[%d] qlen=%d/%u, len=%d/%d, prio=%d",
+		if_id, skb_queue_len(&session->ul_list), session->ul_list.qlen,
+		skb->len, skb->truesize, skb->priority);
+	ret = 0;
+out:
+	return ret;
+}
diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h
new file mode 100644
index 000000000000..4a74e3c9457f
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h
@@ -0,0 +1,193 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#ifndef IOSM_IPC_MUX_CODEC_H
+#define IOSM_IPC_MUX_CODEC_H
+
+#include "iosm_ipc_mux.h"
+
+/* Queue level size and reporting
+ * >1 is enable, 0 is disable
+ */
+#define MUX_QUEUE_LEVEL 1
+
+/* Size of the buffer for the IP MUX commands. */
+#define MUX_MAX_UL_ACB_BUF_SIZE 256
+
+/* Maximum number of packets in a go per session */
+#define MUX_MAX_UL_DG_ENTRIES 100
+
+/* ADGH: Signature of the Datagram Header. */
+#define MUX_SIG_ADGH 0x48474441
+
+/* CMDH: Signature of the Command Header. */
+#define MUX_SIG_CMDH 0x48444D43
+
+/* QLTH: Signature of the Queue Level Table */
+#define MUX_SIG_QLTH 0x48544C51
+
+/* FCTH: Signature of the Flow Credit Table */
+#define MUX_SIG_FCTH 0x48544346
+
+/* MUX UL session threshold factor */
+#define IPC_MEM_MUX_UL_SESS_FCOFF_THRESHOLD_FACTOR (4)
+
+/* Size of the buffer for the IP MUX Lite data buffer. */
+#define IPC_MEM_MAX_DL_MUX_LITE_BUF_SIZE (2 * 1024)
+
+/* MUX UL session threshold in number of packets */
+#define IPC_MEM_MUX_UL_SESS_FCON_THRESHOLD (64)
+
+/* Default time out for sending IPC session commands like
+ * open session, close session etc
+ * unit : milliseconds
+ */
+#define IPC_MUX_CMD_RUN_DEFAULT_TIMEOUT 1000 /* 1 second */
+
+/* MUX UL flow control lower threshold in bytes */
+#define IPC_MEM_MUX_UL_FLOWCTRL_LOW_B 10240 /* 10KB */
+
+/* MUX UL flow control higher threshold in bytes (5ms worth of data)*/
+#define IPC_MEM_MUX_UL_FLOWCTRL_HIGH_B (110 * 1024)
+
+/**
+ * struct mux_adgh - Aggregated Datagram Header.
+ * @signature:		Signature of the Aggregated Datagram Header(0x48474441)
+ * @length:		Length (in bytes) of the datagram header. This length
+ *			shall include the header size. Min value: 0x10
+ * @if_id:		ID of the interface the datagrams belong to
+ * @opt_ipv4v6:		Indicates IPv4(=0)/IPv6(=1), It is optional if not
+ *			used set it to zero.
+ * @reserved:		Reserved bits. Set to zero.
+ * @service_class:	Service class identifier for the datagram.
+ * @next_count:		Count of the datagrams that shall be following this
+ *			datagrams for this interface. A count of zero means
+ *			the next datagram may not belong to this interface.
+ * @reserved1:		Reserved bytes, Set to zero
+ */
+struct mux_adgh {
+	__le32 signature;
+	__le16 length;
+	u8 if_id;
+	u8 opt_ipv4v6;
+	u8 service_class;
+	u8 next_count;
+	u8 reserved1[6];
+};
+
+/**
+ * struct mux_lite_cmdh - MUX Lite Command Header
+ * @signature:		Signature of the Command Header(0x48444D43)
+ * @cmd_len:		Length (in bytes) of the command. This length shall
+ *			include the header size. Minimum value: 0x10
+ * @if_id:		ID of the interface the commands in the table belong to.
+ * @reserved:		Reserved Set to zero.
+ * @command_type:	Command Enum.
+ * @transaction_id:	4 byte value shall be generated and sent along with a
+ *			command Responses and ACKs shall have the same
+ *			Transaction ID as their commands. It shall be unique to
+ *			the command transaction on the given interface.
+ * @param:		Optional parameters used with the command.
+ */
+struct mux_lite_cmdh {
+	__le32 signature;
+	__le16 cmd_len;
+	u8 if_id;
+	u8 reserved;
+	__le32 command_type;
+	__le32 transaction_id;
+	union mux_cmd_param param;
+};
+
+/**
+ * struct mux_lite_vfl - value field in generic table
+ * @nr_of_bytes:	Number of bytes available to transmit in the queue.
+ */
+struct mux_lite_vfl {
+	u32 nr_of_bytes;
+};
+
+/**
+ * struct ipc_mem_lite_gen_tbl - Generic table format for Queue Level
+ *				 and Flow Credit
+ * @signature:	Signature of the table
+ * @length:	Length of the table
+ * @if_id:	ID of the interface the table belongs to
+ * @vfl_length:	Value field length
+ * @reserved:	Reserved
+ * @vfl:	Value field of variable length
+ */
+struct ipc_mem_lite_gen_tbl {
+	__le32 signature;
+	__le16 length;
+	u8 if_id;
+	u8 vfl_length;
+	u32 reserved[2];
+	struct mux_lite_vfl vfl;
+};
+
+/**
+ * ipc_mux_dl_decode -Route the DL packet through the IP MUX layer
+ *		      depending on Header.
+ * @ipc_mux:	Pointer to MUX data-struct
+ * @skb:	Pointer to ipc_skb.
+ */
+void ipc_mux_dl_decode(struct iosm_mux *ipc_mux, struct sk_buff *skb);
+
+/**
+ * ipc_mux_dl_acb_send_cmds - Respond to the Command blocks.
+ * @ipc_mux:		Pointer to MUX data-struct
+ * @cmd_type:		Command
+ * @if_id:		Session interface id.
+ * @transaction_id:	Command transaction id.
+ * @param:		Pointer to command params.
+ * @res_size:		Response size
+ * @blocking:		True for blocking send
+ * @respond:		If true return transaction ID
+ *
+ * Returns: 0 in success and failure value on error
+ */
+int ipc_mux_dl_acb_send_cmds(struct iosm_mux *ipc_mux, u32 cmd_type, u8 if_id,
+			     u32 transaction_id, union mux_cmd_param *param,
+			     size_t res_size, bool blocking, bool respond);
+
+/**
+ * ipc_mux_netif_tx_flowctrl - Enable/Disable TX flow control on MUX sessions.
+ * @session:	Pointer to mux_session struct
+ * @idx:	Session ID
+ * @on:		true for Enable and false for disable flow control
+ */
+void ipc_mux_netif_tx_flowctrl(struct mux_session *session, int idx, bool on);
+
+/**
+ * ipc_mux_ul_trigger_encode - Route the UL packet through the IP MUX layer
+ *			       for encoding.
+ * @ipc_mux:	Pointer to MUX data-struct
+ * @if_id:	Session ID.
+ * @skb:	Pointer to ipc_skb.
+ *
+ * Returns: 0 if successfully encoded
+ *	    failure value on error
+ *	    -EBUSY if packet has to be retransmitted.
+ */
+int ipc_mux_ul_trigger_encode(struct iosm_mux *ipc_mux, int if_id,
+			      struct sk_buff *skb);
+/**
+ * ipc_mux_ul_data_encode - UL encode function for calling from Tasklet context.
+ * @ipc_mux:	Pointer to MUX data-struct
+ *
+ * Returns: TRUE if any packet of any session is encoded FALSE otherwise.
+ */
+bool ipc_mux_ul_data_encode(struct iosm_mux *ipc_mux);
+
+/**
+ * ipc_mux_ul_encoded_process - Handles the Modem processed UL data by adding
+ *				the SKB to the UL free list.
+ * @ipc_mux:	Pointer to MUX data-struct
+ * @skb:	Pointer to ipc_skb.
+ */
+void ipc_mux_ul_encoded_process(struct iosm_mux *ipc_mux, struct sk_buff *skb);
+
+#endif
diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c
new file mode 100644
index 000000000000..7f7d364d3a51
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c
@@ -0,0 +1,580 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#include <linux/acpi.h>
+#include <linux/bitfield.h>
+#include <linux/module.h>
+#include <net/rtnetlink.h>
+
+#include "iosm_ipc_imem.h"
+#include "iosm_ipc_pcie.h"
+#include "iosm_ipc_protocol.h"
+
+MODULE_DESCRIPTION("IOSM Driver");
+MODULE_LICENSE("GPL v2");
+
+/* WWAN GUID */
+static guid_t wwan_acpi_guid = GUID_INIT(0xbad01b75, 0x22a8, 0x4f48, 0x87, 0x92,
+				       0xbd, 0xde, 0x94, 0x67, 0x74, 0x7d);
+
+static void ipc_pcie_resources_release(struct iosm_pcie *ipc_pcie)
+{
+	/* Free the MSI resources. */
+	ipc_release_irq(ipc_pcie);
+
+	/* Free mapped doorbell scratchpad bus memory into CPU space. */
+	iounmap(ipc_pcie->scratchpad);
+
+	/* Free mapped IPC_REGS bus memory into CPU space. */
+	iounmap(ipc_pcie->ipc_regs);
+
+	/* Releases all PCI I/O and memory resources previously reserved by a
+	 * successful call to pci_request_regions.  Call this function only
+	 * after all use of the PCI regions has ceased.
+	 */
+	pci_release_regions(ipc_pcie->pci);
+}
+
+static void ipc_pcie_cleanup(struct iosm_pcie *ipc_pcie)
+{
+	/* Free the shared memory resources. */
+	ipc_imem_cleanup(ipc_pcie->imem);
+
+	ipc_pcie_resources_release(ipc_pcie);
+
+	/* Signal to the system that the PCI device is not in use. */
+	pci_disable_device(ipc_pcie->pci);
+}
+
+static void ipc_pcie_deinit(struct iosm_pcie *ipc_pcie)
+{
+	kfree(ipc_pcie->imem);
+	kfree(ipc_pcie);
+}
+
+static void ipc_pcie_remove(struct pci_dev *pci)
+{
+	struct iosm_pcie *ipc_pcie = pci_get_drvdata(pci);
+
+	ipc_pcie_cleanup(ipc_pcie);
+
+	ipc_pcie_deinit(ipc_pcie);
+}
+
+static int ipc_pcie_resources_request(struct iosm_pcie *ipc_pcie)
+{
+	struct pci_dev *pci = ipc_pcie->pci;
+	u32 cap = 0;
+	u32 ret;
+
+	/* Reserved PCI I/O and memory resources.
+	 * Mark all PCI regions associated with PCI device pci as
+	 * being reserved by owner IOSM_IPC.
+	 */
+	ret = pci_request_regions(pci, "IOSM_IPC");
+	if (ret) {
+		dev_err(ipc_pcie->dev, "failed pci request regions");
+		goto pci_request_region_fail;
+	}
+
+	/* Reserve the doorbell IPC REGS memory resources.
+	 * Remap the memory into CPU space. Arrange for the physical address
+	 * (BAR) to be visible from this driver.
+	 * pci_ioremap_bar() ensures that the memory is marked uncachable.
+	 */
+	ipc_pcie->ipc_regs = pci_ioremap_bar(pci, ipc_pcie->ipc_regs_bar_nr);
+
+	if (!ipc_pcie->ipc_regs) {
+		dev_err(ipc_pcie->dev, "IPC REGS ioremap error");
+		ret = -EBUSY;
+		goto ipc_regs_remap_fail;
+	}
+
+	/* Reserve the MMIO scratchpad memory resources.
+	 * Remap the memory into CPU space. Arrange for the physical address
+	 * (BAR) to be visible from this driver.
+	 * pci_ioremap_bar() ensures that the memory is marked uncachable.
+	 */
+	ipc_pcie->scratchpad =
+		pci_ioremap_bar(pci, ipc_pcie->scratchpad_bar_nr);
+
+	if (!ipc_pcie->scratchpad) {
+		dev_err(ipc_pcie->dev, "doorbell scratchpad ioremap error");
+		ret = -EBUSY;
+		goto scratch_remap_fail;
+	}
+
+	/* Install the irq handler triggered by CP. */
+	ret = ipc_acquire_irq(ipc_pcie);
+	if (ret) {
+		dev_err(ipc_pcie->dev, "acquiring MSI irq failed!");
+		goto irq_acquire_fail;
+	}
+
+	/* Enable bus-mastering for the IOSM IPC device. */
+	pci_set_master(pci);
+
+	/* Enable LTR if possible
+	 * This is needed for L1.2!
+	 */
+	pcie_capability_read_dword(ipc_pcie->pci, PCI_EXP_DEVCAP2, &cap);
+	if (cap & PCI_EXP_DEVCAP2_LTR)
+		pcie_capability_set_word(ipc_pcie->pci, PCI_EXP_DEVCTL2,
+					 PCI_EXP_DEVCTL2_LTR_EN);
+
+	dev_dbg(ipc_pcie->dev, "link between AP and CP is fully on");
+
+	return ret;
+
+irq_acquire_fail:
+	iounmap(ipc_pcie->scratchpad);
+scratch_remap_fail:
+	iounmap(ipc_pcie->ipc_regs);
+ipc_regs_remap_fail:
+	pci_release_regions(pci);
+pci_request_region_fail:
+	return ret;
+}
+
+bool ipc_pcie_check_aspm_enabled(struct iosm_pcie *ipc_pcie,
+				 bool parent)
+{
+	struct pci_dev *pdev;
+	u16 value = 0;
+	u32 enabled;
+
+	if (parent)
+		pdev = ipc_pcie->pci->bus->self;
+	else
+		pdev = ipc_pcie->pci;
+
+	pcie_capability_read_word(pdev, PCI_EXP_LNKCTL, &value);
+	enabled = value & PCI_EXP_LNKCTL_ASPMC;
+	dev_dbg(ipc_pcie->dev, "ASPM L1: 0x%04X 0x%03X", pdev->device, value);
+
+	return (enabled == PCI_EXP_LNKCTL_ASPM_L1 ||
+		enabled == PCI_EXP_LNKCTL_ASPMC);
+}
+
+bool ipc_pcie_check_data_link_active(struct iosm_pcie *ipc_pcie)
+{
+	struct pci_dev *parent;
+	u16 link_status = 0;
+
+	if (!ipc_pcie->pci->bus || !ipc_pcie->pci->bus->self) {
+		dev_err(ipc_pcie->dev, "root port not found");
+		return false;
+	}
+
+	parent = ipc_pcie->pci->bus->self;
+
+	pcie_capability_read_word(parent, PCI_EXP_LNKSTA, &link_status);
+	dev_dbg(ipc_pcie->dev, "Link status: 0x%04X", link_status);
+
+	return link_status & PCI_EXP_LNKSTA_DLLLA;
+}
+
+static bool ipc_pcie_check_aspm_supported(struct iosm_pcie *ipc_pcie,
+					  bool parent)
+{
+	struct pci_dev *pdev;
+	u32 support;
+	u32 cap = 0;
+
+	if (parent)
+		pdev = ipc_pcie->pci->bus->self;
+	else
+		pdev = ipc_pcie->pci;
+	pcie_capability_read_dword(pdev, PCI_EXP_LNKCAP, &cap);
+	support = u32_get_bits(cap, PCI_EXP_LNKCAP_ASPMS);
+	if (support < PCI_EXP_LNKCTL_ASPM_L1) {
+		dev_dbg(ipc_pcie->dev, "ASPM L1 not supported: 0x%04X",
+			pdev->device);
+		return false;
+	}
+	return true;
+}
+
+void ipc_pcie_config_aspm(struct iosm_pcie *ipc_pcie)
+{
+	bool parent_aspm_enabled, dev_aspm_enabled;
+
+	/* check if both root port and child supports ASPM L1 */
+	if (!ipc_pcie_check_aspm_supported(ipc_pcie, true) ||
+	    !ipc_pcie_check_aspm_supported(ipc_pcie, false))
+		return;
+
+	parent_aspm_enabled = ipc_pcie_check_aspm_enabled(ipc_pcie, true);
+	dev_aspm_enabled = ipc_pcie_check_aspm_enabled(ipc_pcie, false);
+
+	dev_dbg(ipc_pcie->dev, "ASPM parent: %s device: %s",
+		parent_aspm_enabled ? "Enabled" : "Disabled",
+		dev_aspm_enabled ? "Enabled" : "Disabled");
+}
+
+/* Initializes PCIe endpoint configuration */
+static void ipc_pcie_config_init(struct iosm_pcie *ipc_pcie)
+{
+	/* BAR0 is used for doorbell */
+	ipc_pcie->ipc_regs_bar_nr = IPC_DOORBELL_BAR0;
+
+	/* update HW configuration */
+	ipc_pcie->scratchpad_bar_nr = IPC_SCRATCHPAD_BAR2;
+	ipc_pcie->doorbell_reg_offset = IPC_DOORBELL_CH_OFFSET;
+	ipc_pcie->doorbell_write = IPC_WRITE_PTR_REG_0;
+	ipc_pcie->doorbell_capture = IPC_CAPTURE_PTR_REG_0;
+}
+
+/* This will read the BIOS WWAN RTD3 settings:
+ * D0L1.2/D3L2/Disabled
+ */
+static enum ipc_pcie_sleep_state ipc_pcie_read_bios_cfg(struct device *dev)
+{
+	union acpi_object *object;
+	acpi_handle handle_acpi;
+
+	handle_acpi = ACPI_HANDLE(dev);
+	if (!handle_acpi) {
+		pr_debug("pci device is NOT ACPI supporting device\n");
+		goto default_ret;
+	}
+
+	object = acpi_evaluate_dsm(handle_acpi, &wwan_acpi_guid, 0, 3, NULL);
+
+	if (object && object->integer.value == 3)
+		return IPC_PCIE_D3L2;
+
+default_ret:
+	return IPC_PCIE_D0L12;
+}
+
+static int ipc_pcie_probe(struct pci_dev *pci,
+			  const struct pci_device_id *pci_id)
+{
+	struct iosm_pcie *ipc_pcie = kzalloc(sizeof(*ipc_pcie), GFP_KERNEL);
+
+	pr_debug("Probing device 0x%X from the vendor 0x%X", pci_id->device,
+		 pci_id->vendor);
+
+	if (!ipc_pcie)
+		goto ret_fail;
+
+	/* Initialize ipc dbg component for the PCIe device */
+	ipc_pcie->dev = &pci->dev;
+
+	/* Set the driver specific data. */
+	pci_set_drvdata(pci, ipc_pcie);
+
+	/* Save the address of the PCI device configuration. */
+	ipc_pcie->pci = pci;
+
+	/* Update platform configuration */
+	ipc_pcie_config_init(ipc_pcie);
+
+	/* Initialize the device before it is used. Ask low-level code
+	 * to enable I/O and memory. Wake up the device if it was suspended.
+	 */
+	if (pci_enable_device(pci)) {
+		dev_err(ipc_pcie->dev, "failed to enable the AP PCIe device");
+		/* If enable of PCIe device has failed then calling
+		 * ipc_pcie_cleanup will panic the system. More over
+		 * ipc_pcie_cleanup() is required to be called after
+		 * ipc_imem_mount()
+		 */
+		goto pci_enable_fail;
+	}
+
+	ipc_pcie_config_aspm(ipc_pcie);
+	dev_dbg(ipc_pcie->dev, "PCIe device enabled.");
+
+	/* Read WWAN RTD3 BIOS Setting
+	 */
+	ipc_pcie->d3l2_support = ipc_pcie_read_bios_cfg(&pci->dev);
+
+	ipc_pcie->suspend = 0;
+
+	if (ipc_pcie_resources_request(ipc_pcie))
+		goto resources_req_fail;
+
+	/* Establish the link to the imem layer. */
+	ipc_pcie->imem = ipc_imem_init(ipc_pcie, pci->device,
+				       ipc_pcie->scratchpad, ipc_pcie->dev);
+	if (!ipc_pcie->imem) {
+		dev_err(ipc_pcie->dev, "failed to init imem");
+		goto imem_init_fail;
+	}
+
+	return 0;
+
+imem_init_fail:
+	ipc_pcie_resources_release(ipc_pcie);
+resources_req_fail:
+	pci_disable_device(pci);
+pci_enable_fail:
+	kfree(ipc_pcie);
+ret_fail:
+	return -EIO;
+}
+
+static const struct pci_device_id iosm_ipc_ids[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, INTEL_CP_DEVICE_7560_ID) },
+	{}
+};
+MODULE_DEVICE_TABLE(pci, iosm_ipc_ids);
+
+/* Enter sleep in s2idle case
+ */
+static int __maybe_unused ipc_pcie_suspend_s2idle(struct iosm_pcie *ipc_pcie)
+{
+	ipc_cp_irq_sleep_control(ipc_pcie, IPC_MEM_DEV_PM_FORCE_SLEEP);
+
+	/* Complete all memory stores before setting bit */
+	smp_mb__before_atomic();
+
+	set_bit(0, &ipc_pcie->suspend);
+
+	/* Complete all memory stores after setting bit */
+	smp_mb__after_atomic();
+
+	ipc_imem_pm_s2idle_sleep(ipc_pcie->imem, true);
+
+	return 0;
+}
+
+/* Resume from sleep in s2idle case
+ */
+static int __maybe_unused ipc_pcie_resume_s2idle(struct iosm_pcie *ipc_pcie)
+{
+	ipc_cp_irq_sleep_control(ipc_pcie, IPC_MEM_DEV_PM_FORCE_ACTIVE);
+
+	ipc_imem_pm_s2idle_sleep(ipc_pcie->imem, false);
+
+	/* Complete all memory stores before clearing bit. */
+	smp_mb__before_atomic();
+
+	clear_bit(0, &ipc_pcie->suspend);
+
+	/* Complete all memory stores after clearing bit. */
+	smp_mb__after_atomic();
+	return 0;
+}
+
+int __maybe_unused ipc_pcie_suspend(struct iosm_pcie *ipc_pcie)
+{
+	struct pci_dev *pdev;
+	int ret;
+
+	pdev = ipc_pcie->pci;
+
+	/* Execute D3 one time. */
+	if (pdev->current_state != PCI_D0) {
+		dev_dbg(ipc_pcie->dev, "done for PM=%d", pdev->current_state);
+		return 0;
+	}
+
+	/* The HAL shall ask the shared memory layer whether D3 is allowed. */
+	ipc_imem_pm_suspend(ipc_pcie->imem);
+
+	/* Save the PCI configuration space of a device before suspending. */
+	ret = pci_save_state(pdev);
+
+	if (ret) {
+		dev_err(ipc_pcie->dev, "pci_save_state error=%d", ret);
+		return ret;
+	}
+
+	/* Set the power state of a PCI device.
+	 * Transition a device to a new power state, using the device's PCI PM
+	 * registers.
+	 */
+	ret = pci_set_power_state(pdev, PCI_D3cold);
+
+	if (ret) {
+		dev_err(ipc_pcie->dev, "pci_set_power_state error=%d", ret);
+		return ret;
+	}
+
+	dev_dbg(ipc_pcie->dev, "SUSPEND done");
+	return ret;
+}
+
+int __maybe_unused ipc_pcie_resume(struct iosm_pcie *ipc_pcie)
+{
+	int ret;
+
+	/* Set the power state of a PCI device.
+	 * Transition a device to a new power state, using the device's PCI PM
+	 * registers.
+	 */
+	ret = pci_set_power_state(ipc_pcie->pci, PCI_D0);
+
+	if (ret) {
+		dev_err(ipc_pcie->dev, "pci_set_power_state error=%d", ret);
+		return ret;
+	}
+
+	pci_restore_state(ipc_pcie->pci);
+
+	/* The HAL shall inform the shared memory layer that the device is
+	 * active.
+	 */
+	ipc_imem_pm_resume(ipc_pcie->imem);
+
+	dev_dbg(ipc_pcie->dev, "RESUME done");
+	return ret;
+}
+
+static int __maybe_unused ipc_pcie_suspend_cb(struct device *dev)
+{
+	struct iosm_pcie *ipc_pcie;
+	struct pci_dev *pdev;
+
+	pdev = to_pci_dev(dev);
+
+	ipc_pcie = pci_get_drvdata(pdev);
+
+	switch (ipc_pcie->d3l2_support) {
+	case IPC_PCIE_D0L12:
+		ipc_pcie_suspend_s2idle(ipc_pcie);
+		break;
+	case IPC_PCIE_D3L2:
+		ipc_pcie_suspend(ipc_pcie);
+		break;
+	}
+
+	return 0;
+}
+
+static int __maybe_unused ipc_pcie_resume_cb(struct device *dev)
+{
+	struct iosm_pcie *ipc_pcie;
+	struct pci_dev *pdev;
+
+	pdev = to_pci_dev(dev);
+
+	ipc_pcie = pci_get_drvdata(pdev);
+
+	switch (ipc_pcie->d3l2_support) {
+	case IPC_PCIE_D0L12:
+		ipc_pcie_resume_s2idle(ipc_pcie);
+		break;
+	case IPC_PCIE_D3L2:
+		ipc_pcie_resume(ipc_pcie);
+		break;
+	}
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(iosm_ipc_pm, ipc_pcie_suspend_cb, ipc_pcie_resume_cb);
+
+static struct pci_driver iosm_ipc_driver = {
+	.name = KBUILD_MODNAME,
+	.probe = ipc_pcie_probe,
+	.remove = ipc_pcie_remove,
+	.driver = {
+		.pm = &iosm_ipc_pm,
+	},
+	.id_table = iosm_ipc_ids,
+};
+
+int ipc_pcie_addr_map(struct iosm_pcie *ipc_pcie, unsigned char *data,
+		      size_t size, dma_addr_t *mapping, int direction)
+{
+	if (ipc_pcie->pci) {
+		*mapping = dma_map_single(&ipc_pcie->pci->dev, data, size,
+					  direction);
+		if (dma_mapping_error(&ipc_pcie->pci->dev, *mapping)) {
+			dev_err(ipc_pcie->dev, "dma mapping failed");
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+void ipc_pcie_addr_unmap(struct iosm_pcie *ipc_pcie, size_t size,
+			 dma_addr_t mapping, int direction)
+{
+	if (!mapping)
+		return;
+	if (ipc_pcie->pci)
+		dma_unmap_single(&ipc_pcie->pci->dev, mapping, size, direction);
+}
+
+struct sk_buff *ipc_pcie_alloc_local_skb(struct iosm_pcie *ipc_pcie,
+					 gfp_t flags, size_t size)
+{
+	struct sk_buff *skb;
+
+	if (!ipc_pcie || !size) {
+		pr_err("invalid pcie object or size");
+		return NULL;
+	}
+
+	skb = __netdev_alloc_skb(NULL, size, flags);
+	if (!skb)
+		return NULL;
+
+	IPC_CB(skb)->op_type = (u8)UL_DEFAULT;
+	IPC_CB(skb)->mapping = 0;
+
+	return skb;
+}
+
+struct sk_buff *ipc_pcie_alloc_skb(struct iosm_pcie *ipc_pcie, size_t size,
+				   gfp_t flags, dma_addr_t *mapping,
+				   int direction, size_t headroom)
+{
+	struct sk_buff *skb = ipc_pcie_alloc_local_skb(ipc_pcie, flags,
+						       size + headroom);
+	if (!skb)
+		return NULL;
+
+	if (headroom)
+		skb_reserve(skb, headroom);
+
+	if (ipc_pcie_addr_map(ipc_pcie, skb->data, size, mapping, direction)) {
+		dev_kfree_skb(skb);
+		return NULL;
+	}
+
+	BUILD_BUG_ON(sizeof(*IPC_CB(skb)) > sizeof(skb->cb));
+
+	/* Store the mapping address in skb scratch pad for later usage */
+	IPC_CB(skb)->mapping = *mapping;
+	IPC_CB(skb)->direction = direction;
+	IPC_CB(skb)->len = size;
+
+	return skb;
+}
+
+void ipc_pcie_kfree_skb(struct iosm_pcie *ipc_pcie, struct sk_buff *skb)
+{
+	if (!skb)
+		return;
+
+	ipc_pcie_addr_unmap(ipc_pcie, IPC_CB(skb)->len, IPC_CB(skb)->mapping,
+			    IPC_CB(skb)->direction);
+	IPC_CB(skb)->mapping = 0;
+	dev_kfree_skb(skb);
+}
+
+static int __init iosm_ipc_driver_init(void)
+{
+	if (pci_register_driver(&iosm_ipc_driver)) {
+		pr_err("registering of IOSM PCIe driver failed");
+		return -1;
+	}
+
+	return 0;
+}
+
+static void __exit iosm_ipc_driver_exit(void)
+{
+	pci_unregister_driver(&iosm_ipc_driver);
+}
+
+module_init(iosm_ipc_driver_init);
+module_exit(iosm_ipc_driver_exit);
diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.h b/drivers/net/wwan/iosm/iosm_ipc_pcie.h
new file mode 100644
index 000000000000..7d1f0cd7364c
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.h
@@ -0,0 +1,209 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#ifndef IOSM_IPC_PCIE_H
+#define IOSM_IPC_PCIE_H
+
+#include <linux/device.h>
+#include <linux/pci.h>
+#include <linux/skbuff.h>
+
+#include "iosm_ipc_irq.h"
+
+/* Device ID */
+#define INTEL_CP_DEVICE_7560_ID 0x7560
+
+/* Define for BAR area usage */
+#define IPC_DOORBELL_BAR0 0
+#define IPC_SCRATCHPAD_BAR2 2
+
+/* Defines for DOORBELL registers information */
+#define IPC_DOORBELL_CH_OFFSET BIT(5)
+#define IPC_WRITE_PTR_REG_0 BIT(4)
+#define IPC_CAPTURE_PTR_REG_0 BIT(3)
+
+/* Number of MSI used for IPC */
+#define IPC_MSI_VECTORS 1
+
+/* Total number of Maximum IPC IRQ vectors used for IPC */
+#define IPC_IRQ_VECTORS IPC_MSI_VECTORS
+
+/**
+ * enum ipc_pcie_sleep_state - Enum type to different sleep state transitions
+ * @IPC_PCIE_D0L12:	Put the sleep state in D0L12
+ * @IPC_PCIE_D3L2:	Put the sleep state in D3L2
+ */
+enum ipc_pcie_sleep_state {
+	IPC_PCIE_D0L12,
+	IPC_PCIE_D3L2,
+};
+
+/**
+ * struct iosm_pcie - IPC_PCIE struct.
+ * @pci:			Address of the device description
+ * @dev:			Pointer to generic device structure
+ * @ipc_regs:			Remapped CP doorbell address of the irq register
+ *				set, to fire the doorbell irq.
+ * @scratchpad:			Remapped CP scratchpad address, to send the
+ *				configuration. tuple and the IPC descriptors
+ *				to CP in the ROM phase. The config tuple
+ *				information are saved on the MSI scratchpad.
+ * @imem:			Pointer to imem data struct
+ * @ipc_regs_bar_nr:		BAR number to be used for IPC doorbell
+ * @scratchpad_bar_nr:		BAR number to be used for Scratchpad
+ * @nvec:			number of requested irq vectors
+ * @doorbell_reg_offset:	doorbell_reg_offset
+ * @doorbell_write:		doorbell write register
+ * @doorbell_capture:		doorbell capture resgister
+ * @suspend:			S2IDLE sleep/active
+ * @d3l2_support:		Read WWAN RTD3 BIOS setting for D3L2 support
+ */
+struct iosm_pcie {
+	struct pci_dev *pci;
+	struct device *dev;
+	void __iomem *ipc_regs;
+	void __iomem *scratchpad;
+	struct iosm_imem *imem;
+	int ipc_regs_bar_nr;
+	int scratchpad_bar_nr;
+	int nvec;
+	u32 doorbell_reg_offset;
+	u32 doorbell_write;
+	u32 doorbell_capture;
+	unsigned long suspend;
+	enum ipc_pcie_sleep_state d3l2_support;
+};
+
+/**
+ * struct ipc_skb_cb - Struct definition of the socket buffer which is mapped to
+ *		       the cb field of sbk
+ * @mapping:	Store physical or IOVA mapped address of skb virtual add.
+ * @direction:	DMA direction
+ * @len:	Length of the DMA mapped region
+ * @op_type:    Expected values are defined about enum ipc_ul_usr_op.
+ */
+struct ipc_skb_cb {
+	dma_addr_t mapping;
+	int direction;
+	int len;
+	u8 op_type;
+};
+
+/**
+ * enum ipc_ul_usr_op - Control operation to execute the right action on
+ *			the user interface.
+ * @UL_USR_OP_BLOCKED:	The uplink app was blocked until CP confirms that the
+ *			uplink buffer was consumed triggered by the IRQ.
+ * @UL_MUX_OP_ADB:	In MUX mode the UL ADB shall be addedd to the free list.
+ * @UL_DEFAULT:		SKB in non muxing mode
+ */
+enum ipc_ul_usr_op {
+	UL_USR_OP_BLOCKED,
+	UL_MUX_OP_ADB,
+	UL_DEFAULT,
+};
+
+/**
+ * ipc_pcie_addr_map - Maps the kernel's virtual address to either IOVA
+ *		       address space or Physical address space, the mapping is
+ *		       stored in the skb's cb.
+ * @ipc_pcie:	Pointer to struct iosm_pcie
+ * @data:	Skb mem containing data
+ * @size:	Data size
+ * @mapping:	Dma mapping address
+ * @direction:	Data direction
+ *
+ * Returns: 0 on success and failure value on error
+ */
+int ipc_pcie_addr_map(struct iosm_pcie *ipc_pcie, unsigned char *data,
+		      size_t size, dma_addr_t *mapping, int direction);
+
+/**
+ * ipc_pcie_addr_unmap - Unmaps the skb memory region from IOVA address space
+ * @ipc_pcie:	Pointer to struct iosm_pcie
+ * @size:	Data size
+ * @mapping:	Dma mapping address
+ * @direction:	Data direction
+ */
+void ipc_pcie_addr_unmap(struct iosm_pcie *ipc_pcie, size_t size,
+			 dma_addr_t mapping, int direction);
+
+/**
+ * ipc_pcie_alloc_skb - Allocate an uplink SKB for the given size.
+ * @ipc_pcie:	Pointer to struct iosm_pcie
+ * @size:	Size of the SKB required.
+ * @flags:	Allocation flags
+ * @mapping:	Copies either mapped IOVA add. or converted Phy address
+ * @direction:	DMA data direction
+ * @headroom:	Header data offset
+ *
+ * Returns: Pointer to ipc_skb on Success, NULL on failure.
+ */
+struct sk_buff *ipc_pcie_alloc_skb(struct iosm_pcie *ipc_pcie, size_t size,
+				   gfp_t flags, dma_addr_t *mapping,
+				   int direction, size_t headroom);
+
+/**
+ * ipc_pcie_alloc_local_skb - Allocate a local SKB for the given size.
+ * @ipc_pcie:	Pointer to struct iosm_pcie
+ * @flags:	Allocation flags
+ * @size:	Size of the SKB required.
+ *
+ * Returns: Pointer to ipc_skb on Success, NULL on failure.
+ */
+struct sk_buff *ipc_pcie_alloc_local_skb(struct iosm_pcie *ipc_pcie,
+					 gfp_t flags, size_t size);
+
+/**
+ * ipc_pcie_kfree_skb - Free skb allocated by ipc_pcie_alloc_*_skb().
+ * @ipc_pcie:	Pointer to struct iosm_pcie
+ * @skb:	Pointer to the skb
+ */
+void ipc_pcie_kfree_skb(struct iosm_pcie *ipc_pcie, struct sk_buff *skb);
+
+/**
+ * ipc_pcie_check_data_link_active - Check Data Link Layer Active
+ * @ipc_pcie:	Pointer to struct iosm_pcie
+ *
+ * Returns: true if active, otherwise false
+ */
+bool ipc_pcie_check_data_link_active(struct iosm_pcie *ipc_pcie);
+
+/**
+ * ipc_pcie_suspend - Callback invoked by pm_runtime_suspend. It decrements
+ *		     the device's usage count then, carry out a suspend,
+ *		     either synchronous or asynchronous.
+ * @ipc_pcie:	Pointer to struct iosm_pcie
+ *
+ * Returns: 0 on success and failure value on error
+ */
+int ipc_pcie_suspend(struct iosm_pcie *ipc_pcie);
+
+/**
+ * ipc_pcie_resume - Callback invoked by pm_runtime_resume. It increments
+ *		    the device's usage count then, carry out a resume,
+ *		    either synchronous or asynchronous.
+ * @ipc_pcie:	Pointer to struct iosm_pcie
+ *
+ * Returns: 0 on success and failure value on error
+ */
+int ipc_pcie_resume(struct iosm_pcie *ipc_pcie);
+
+/**
+ * ipc_pcie_check_aspm_enabled - Check if ASPM L1 is already enabled
+ * @ipc_pcie:			 Pointer to struct iosm_pcie
+ * @parent:			 True if checking ASPM L1 for parent else false
+ *
+ * Returns: true if ASPM is already enabled else false
+ */
+bool ipc_pcie_check_aspm_enabled(struct iosm_pcie *ipc_pcie,
+				 bool parent);
+/**
+ * ipc_pcie_config_aspm - Configure ASPM L1
+ * @ipc_pcie:	Pointer to struct iosm_pcie
+ */
+void ipc_pcie_config_aspm(struct iosm_pcie *ipc_pcie);
+
+#endif
diff --git a/drivers/net/wwan/iosm/iosm_ipc_pm.c b/drivers/net/wwan/iosm/iosm_ipc_pm.c
new file mode 100644
index 000000000000..413601c72dcd
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_pm.c
@@ -0,0 +1,333 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#include "iosm_ipc_protocol.h"
+
+/* Timeout value in MS for the PM to wait for device to reach active state */
+#define IPC_PM_ACTIVE_TIMEOUT_MS (500)
+
+/* Note that here "active" has the value 1, as compared to the enums
+ * ipc_mem_host_pm_state or ipc_mem_dev_pm_state, where "active" is 0
+ */
+#define IPC_PM_SLEEP (0)
+#define CONSUME_STATE (0)
+#define IPC_PM_ACTIVE (1)
+
+void ipc_pm_signal_hpda_doorbell(struct iosm_pm *ipc_pm, u32 identifier,
+				 bool host_slp_check)
+{
+	if (host_slp_check && ipc_pm->host_pm_state != IPC_MEM_HOST_PM_ACTIVE &&
+	    ipc_pm->host_pm_state != IPC_MEM_HOST_PM_ACTIVE_WAIT) {
+		ipc_pm->pending_hpda_update = true;
+		dev_dbg(ipc_pm->dev,
+			"Pend HPDA update set. Host PM_State: %d identifier:%d",
+			ipc_pm->host_pm_state, identifier);
+		return;
+	}
+
+	if (!ipc_pm_trigger(ipc_pm, IPC_PM_UNIT_IRQ, true)) {
+		ipc_pm->pending_hpda_update = true;
+		dev_dbg(ipc_pm->dev, "Pending HPDA update set. identifier:%d",
+			identifier);
+		return;
+	}
+	ipc_pm->pending_hpda_update = false;
+
+	/* Trigger the irq towards CP */
+	ipc_cp_irq_hpda_update(ipc_pm->pcie, identifier);
+
+	ipc_pm_trigger(ipc_pm, IPC_PM_UNIT_IRQ, false);
+}
+
+/* Wake up the device if it is in low power mode. */
+static bool ipc_pm_link_activate(struct iosm_pm *ipc_pm)
+{
+	if (ipc_pm->cp_state == IPC_MEM_DEV_PM_ACTIVE)
+		return true;
+
+	if (ipc_pm->cp_state == IPC_MEM_DEV_PM_SLEEP) {
+		if (ipc_pm->ap_state == IPC_MEM_DEV_PM_SLEEP) {
+			/* Wake up the device. */
+			ipc_cp_irq_sleep_control(ipc_pm->pcie,
+						 IPC_MEM_DEV_PM_WAKEUP);
+			ipc_pm->ap_state = IPC_MEM_DEV_PM_ACTIVE_WAIT;
+
+			goto not_active;
+		}
+
+		if (ipc_pm->ap_state == IPC_MEM_DEV_PM_ACTIVE_WAIT)
+			goto not_active;
+
+		return true;
+	}
+
+not_active:
+	/* link is not ready */
+	return false;
+}
+
+bool ipc_pm_wait_for_device_active(struct iosm_pm *ipc_pm)
+{
+	bool ret_val = false;
+
+	if (ipc_pm->ap_state != IPC_MEM_DEV_PM_ACTIVE) {
+		/* Complete all memory stores before setting bit */
+		smp_mb__before_atomic();
+
+		/* Wait for IPC_PM_ACTIVE_TIMEOUT_MS for Device sleep state
+		 * machine to enter ACTIVE state.
+		 */
+		set_bit(0, &ipc_pm->host_sleep_pend);
+
+		/* Complete all memory stores after setting bit */
+		smp_mb__after_atomic();
+
+		if (!wait_for_completion_interruptible_timeout
+		   (&ipc_pm->host_sleep_complete,
+		    msecs_to_jiffies(IPC_PM_ACTIVE_TIMEOUT_MS))) {
+			dev_err(ipc_pm->dev,
+				"PM timeout. Expected State:%d. Actual: %d",
+				IPC_MEM_DEV_PM_ACTIVE, ipc_pm->ap_state);
+			goto  active_timeout;
+		}
+	}
+
+	ret_val = true;
+active_timeout:
+	/* Complete all memory stores before clearing bit */
+	smp_mb__before_atomic();
+
+	/* Reset the atomic variable in any case as device sleep
+	 * state machine change is no longer of interest.
+	 */
+	clear_bit(0, &ipc_pm->host_sleep_pend);
+
+	/* Complete all memory stores after clearing bit */
+	smp_mb__after_atomic();
+
+	return ret_val;
+}
+
+static void ipc_pm_on_link_sleep(struct iosm_pm *ipc_pm)
+{
+	/* pending sleep ack and all conditions are cleared
+	 * -> signal SLEEP__ACK to CP
+	 */
+	ipc_pm->cp_state = IPC_MEM_DEV_PM_SLEEP;
+	ipc_pm->ap_state = IPC_MEM_DEV_PM_SLEEP;
+
+	ipc_cp_irq_sleep_control(ipc_pm->pcie, IPC_MEM_DEV_PM_SLEEP);
+}
+
+static void ipc_pm_on_link_wake(struct iosm_pm *ipc_pm, bool ack)
+{
+	ipc_pm->ap_state = IPC_MEM_DEV_PM_ACTIVE;
+
+	if (ack) {
+		ipc_pm->cp_state = IPC_MEM_DEV_PM_ACTIVE;
+
+		ipc_cp_irq_sleep_control(ipc_pm->pcie, IPC_MEM_DEV_PM_ACTIVE);
+
+		/* check the consume state !!! */
+		if (test_bit(CONSUME_STATE, &ipc_pm->host_sleep_pend))
+			complete(&ipc_pm->host_sleep_complete);
+	}
+
+	/* Check for pending HPDA update.
+	 * Pending HP update could be because of sending message was
+	 * put on hold due to Device sleep state or due to TD update
+	 * which could be because of Device Sleep and Host Sleep
+	 * states.
+	 */
+	if (ipc_pm->pending_hpda_update &&
+	    ipc_pm->host_pm_state == IPC_MEM_HOST_PM_ACTIVE)
+		ipc_pm_signal_hpda_doorbell(ipc_pm, IPC_HP_PM_TRIGGER, true);
+}
+
+bool ipc_pm_trigger(struct iosm_pm *ipc_pm, enum ipc_pm_unit unit, bool active)
+{
+	union ipc_pm_cond old_cond;
+	union ipc_pm_cond new_cond;
+	bool link_active;
+
+	/* Save the current D3 state. */
+	new_cond = ipc_pm->pm_cond;
+	old_cond = ipc_pm->pm_cond;
+
+	/* Calculate the power state only in the runtime phase. */
+	switch (unit) {
+	case IPC_PM_UNIT_IRQ: /* CP irq */
+		new_cond.irq = active;
+		break;
+
+	case IPC_PM_UNIT_LINK: /* Device link state. */
+		new_cond.link = active;
+		break;
+
+	case IPC_PM_UNIT_HS: /* Host sleep trigger requires Link. */
+		new_cond.hs = active;
+		break;
+
+	default:
+		break;
+	}
+
+	/* Something changed ? */
+	if (old_cond.raw == new_cond.raw) {
+		/* Stay in the current PM state. */
+		link_active = old_cond.link == IPC_PM_ACTIVE;
+		goto ret;
+	}
+
+	ipc_pm->pm_cond = new_cond;
+
+	if (new_cond.link)
+		ipc_pm_on_link_wake(ipc_pm, unit == IPC_PM_UNIT_LINK);
+	else if (unit == IPC_PM_UNIT_LINK)
+		ipc_pm_on_link_sleep(ipc_pm);
+
+	if (old_cond.link == IPC_PM_SLEEP && new_cond.raw) {
+		link_active = ipc_pm_link_activate(ipc_pm);
+		goto ret;
+	}
+
+	link_active = old_cond.link == IPC_PM_ACTIVE;
+
+ret:
+	return link_active;
+}
+
+bool ipc_pm_prepare_host_sleep(struct iosm_pm *ipc_pm)
+{
+	/* suspend not allowed if host_pm_state is not IPC_MEM_HOST_PM_ACTIVE */
+	if (ipc_pm->host_pm_state != IPC_MEM_HOST_PM_ACTIVE) {
+		dev_err(ipc_pm->dev, "host_pm_state=%d\tExpected to be: %d",
+			ipc_pm->host_pm_state, IPC_MEM_HOST_PM_ACTIVE);
+		return false;
+	}
+
+	ipc_pm->host_pm_state = IPC_MEM_HOST_PM_SLEEP_WAIT_D3;
+
+	return true;
+}
+
+bool ipc_pm_prepare_host_active(struct iosm_pm *ipc_pm)
+{
+	if (ipc_pm->host_pm_state != IPC_MEM_HOST_PM_SLEEP) {
+		dev_err(ipc_pm->dev, "host_pm_state=%d\tExpected to be: %d",
+			ipc_pm->host_pm_state, IPC_MEM_HOST_PM_SLEEP);
+		return false;
+	}
+
+	/* Sending Sleep Exit message to CP. Update the state */
+	ipc_pm->host_pm_state = IPC_MEM_HOST_PM_ACTIVE_WAIT;
+
+	return true;
+}
+
+void ipc_pm_set_s2idle_sleep(struct iosm_pm *ipc_pm, bool sleep)
+{
+	if (sleep) {
+		ipc_pm->ap_state = IPC_MEM_DEV_PM_SLEEP;
+		ipc_pm->cp_state = IPC_MEM_DEV_PM_SLEEP;
+		ipc_pm->device_sleep_notification = IPC_MEM_DEV_PM_SLEEP;
+	} else {
+		ipc_pm->ap_state = IPC_MEM_DEV_PM_ACTIVE;
+		ipc_pm->cp_state = IPC_MEM_DEV_PM_ACTIVE;
+		ipc_pm->device_sleep_notification = IPC_MEM_DEV_PM_ACTIVE;
+		ipc_pm->pm_cond.link = IPC_PM_ACTIVE;
+	}
+}
+
+bool ipc_pm_dev_slp_notification(struct iosm_pm *ipc_pm, u32 cp_pm_req)
+{
+	if (cp_pm_req == ipc_pm->device_sleep_notification)
+		return false;
+
+	ipc_pm->device_sleep_notification = cp_pm_req;
+
+	/* Evaluate the PM request. */
+	switch (ipc_pm->cp_state) {
+	case IPC_MEM_DEV_PM_ACTIVE:
+		switch (cp_pm_req) {
+		case IPC_MEM_DEV_PM_ACTIVE:
+			break;
+
+		case IPC_MEM_DEV_PM_SLEEP:
+			/* Inform the PM that the device link can go down. */
+			ipc_pm_trigger(ipc_pm, IPC_PM_UNIT_LINK, false);
+			return true;
+
+		default:
+			dev_err(ipc_pm->dev,
+				"loc-pm=%d active: confused req-pm=%d",
+				ipc_pm->cp_state, cp_pm_req);
+			break;
+		}
+		break;
+
+	case IPC_MEM_DEV_PM_SLEEP:
+		switch (cp_pm_req) {
+		case IPC_MEM_DEV_PM_ACTIVE:
+			/* Inform the PM that the device link is active. */
+			ipc_pm_trigger(ipc_pm, IPC_PM_UNIT_LINK, true);
+			break;
+
+		case IPC_MEM_DEV_PM_SLEEP:
+			break;
+
+		default:
+			dev_err(ipc_pm->dev,
+				"loc-pm=%d sleep: confused req-pm=%d",
+				ipc_pm->cp_state, cp_pm_req);
+			break;
+		}
+		break;
+
+	default:
+		dev_err(ipc_pm->dev, "confused loc-pm=%d, req-pm=%d",
+			ipc_pm->cp_state, cp_pm_req);
+		break;
+	}
+
+	return false;
+}
+
+void ipc_pm_init(struct iosm_protocol *ipc_protocol)
+{
+	struct iosm_imem *ipc_imem = ipc_protocol->imem;
+	struct iosm_pm *ipc_pm = &ipc_protocol->pm;
+
+	ipc_pm->pcie = ipc_imem->pcie;
+	ipc_pm->dev = ipc_imem->dev;
+
+	ipc_pm->pm_cond.irq = IPC_PM_SLEEP;
+	ipc_pm->pm_cond.hs = IPC_PM_SLEEP;
+	ipc_pm->pm_cond.link = IPC_PM_ACTIVE;
+
+	ipc_pm->cp_state = IPC_MEM_DEV_PM_ACTIVE;
+	ipc_pm->ap_state = IPC_MEM_DEV_PM_ACTIVE;
+	ipc_pm->host_pm_state = IPC_MEM_HOST_PM_ACTIVE;
+
+	/* Create generic wait-for-completion handler for Host Sleep
+	 * and device sleep coordination.
+	 */
+	init_completion(&ipc_pm->host_sleep_complete);
+
+	/* Complete all memory stores before clearing bit */
+	smp_mb__before_atomic();
+
+	clear_bit(0, &ipc_pm->host_sleep_pend);
+
+	/* Complete all memory stores after clearing bit */
+	smp_mb__after_atomic();
+}
+
+void ipc_pm_deinit(struct iosm_protocol *proto)
+{
+	struct iosm_pm *ipc_pm = &proto->pm;
+
+	complete(&ipc_pm->host_sleep_complete);
+}
diff --git a/drivers/net/wwan/iosm/iosm_ipc_pm.h b/drivers/net/wwan/iosm/iosm_ipc_pm.h
new file mode 100644
index 000000000000..e7c00f388cb0
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_pm.h
@@ -0,0 +1,207 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#ifndef IOSM_IPC_PM_H
+#define IOSM_IPC_PM_H
+
+/* Trigger the doorbell interrupt on cp to change the PM sleep/active status */
+#define ipc_cp_irq_sleep_control(ipc_pcie, data)                               \
+	ipc_doorbell_fire(ipc_pcie, IPC_DOORBELL_IRQ_SLEEP, data)
+
+/* Trigger the doorbell interrupt on CP to do hpda update */
+#define ipc_cp_irq_hpda_update(ipc_pcie, data)                                 \
+	ipc_doorbell_fire(ipc_pcie, IPC_DOORBELL_IRQ_HPDA, 0xFF & (data))
+
+/**
+ * union ipc_pm_cond - Conditions for D3 and the sleep message to CP.
+ * @raw:	raw/combined value for faster check
+ * @irq:	IRQ towards CP
+ * @hs:		Host Sleep
+ * @link:	Device link state.
+ */
+union ipc_pm_cond {
+	unsigned int raw;
+
+	struct {
+		unsigned int irq:1,
+			     hs:1,
+			     link:1;
+	};
+};
+
+/**
+ * enum ipc_mem_host_pm_state - Possible states of the HOST SLEEP finite state
+ *				machine.
+ * @IPC_MEM_HOST_PM_ACTIVE:		   Host is active
+ * @IPC_MEM_HOST_PM_ACTIVE_WAIT:	   Intermediate state before going to
+ *					   active
+ * @IPC_MEM_HOST_PM_SLEEP_WAIT_IDLE:	   Intermediate state to wait for idle
+ *					   before going into sleep
+ * @IPC_MEM_HOST_PM_SLEEP_WAIT_D3:	   Intermediate state to wait for D3
+ *					   before going to sleep
+ * @IPC_MEM_HOST_PM_SLEEP:		   after this state the interface is not
+ *					   accessible host is in suspend to RAM
+ * @IPC_MEM_HOST_PM_SLEEP_WAIT_EXIT_SLEEP: Intermediate state before exiting
+ *					   sleep
+ */
+enum ipc_mem_host_pm_state {
+	IPC_MEM_HOST_PM_ACTIVE,
+	IPC_MEM_HOST_PM_ACTIVE_WAIT,
+	IPC_MEM_HOST_PM_SLEEP_WAIT_IDLE,
+	IPC_MEM_HOST_PM_SLEEP_WAIT_D3,
+	IPC_MEM_HOST_PM_SLEEP,
+	IPC_MEM_HOST_PM_SLEEP_WAIT_EXIT_SLEEP,
+};
+
+/**
+ * enum ipc_mem_dev_pm_state - Possible states of the DEVICE SLEEP finite state
+ *			       machine.
+ * @IPC_MEM_DEV_PM_ACTIVE:		IPC_MEM_DEV_PM_ACTIVE is the initial
+ *					power management state.
+ *					IRQ(struct ipc_mem_device_info:
+ *					device_sleep_notification)
+ *					and DOORBELL-IRQ-HPDA(data) values.
+ * @IPC_MEM_DEV_PM_SLEEP:		IPC_MEM_DEV_PM_SLEEP is PM state for
+ *					sleep.
+ * @IPC_MEM_DEV_PM_WAKEUP:		DOORBELL-IRQ-DEVICE_WAKE(data).
+ * @IPC_MEM_DEV_PM_HOST_SLEEP:		DOORBELL-IRQ-HOST_SLEEP(data).
+ * @IPC_MEM_DEV_PM_ACTIVE_WAIT:		Local intermediate states.
+ * @IPC_MEM_DEV_PM_FORCE_SLEEP:		DOORBELL-IRQ-FORCE_SLEEP.
+ * @IPC_MEM_DEV_PM_FORCE_ACTIVE:	DOORBELL-IRQ-FORCE_ACTIVE.
+ */
+enum ipc_mem_dev_pm_state {
+	IPC_MEM_DEV_PM_ACTIVE,
+	IPC_MEM_DEV_PM_SLEEP,
+	IPC_MEM_DEV_PM_WAKEUP,
+	IPC_MEM_DEV_PM_HOST_SLEEP,
+	IPC_MEM_DEV_PM_ACTIVE_WAIT,
+	IPC_MEM_DEV_PM_FORCE_SLEEP = 7,
+	IPC_MEM_DEV_PM_FORCE_ACTIVE,
+};
+
+/**
+ * struct iosm_pm - Power management instance
+ * @pcie:			Pointer to iosm_pcie structure
+ * @dev:			Pointer to device structure
+ * @host_pm_state:		PM states for host
+ * @host_sleep_pend:		Variable to indicate Host Sleep Pending
+ * @host_sleep_complete:	Generic wait-for-completion used in
+ *				case of Host Sleep
+ * @pm_cond:			Conditions for power management
+ * @ap_state:			Current power management state, the
+ *				initial state is IPC_MEM_DEV_PM_ACTIVE eq. 0.
+ * @cp_state:			PM State of CP
+ * @device_sleep_notification:	last handled device_sleep_notfication
+ * @pending_hpda_update:	is a HPDA update pending?
+ */
+struct iosm_pm {
+	struct iosm_pcie *pcie;
+	struct device *dev;
+	enum ipc_mem_host_pm_state host_pm_state;
+	unsigned long host_sleep_pend;
+	struct completion host_sleep_complete;
+	union ipc_pm_cond pm_cond;
+	enum ipc_mem_dev_pm_state ap_state;
+	enum ipc_mem_dev_pm_state cp_state;
+	u32 device_sleep_notification;
+	u8 pending_hpda_update:1;
+};
+
+/**
+ * enum ipc_pm_unit - Power management units.
+ * @IPC_PM_UNIT_IRQ:	IRQ towards CP
+ * @IPC_PM_UNIT_HS:	Host Sleep for converged protocol
+ * @IPC_PM_UNIT_LINK:	Link state controlled by CP.
+ */
+enum ipc_pm_unit {
+	IPC_PM_UNIT_IRQ,
+	IPC_PM_UNIT_HS,
+	IPC_PM_UNIT_LINK,
+};
+
+/**
+ * ipc_pm_init - Allocate power management component
+ * @ipc_protocol:	Pointer to iosm_protocol structure
+ */
+void ipc_pm_init(struct iosm_protocol *ipc_protocol);
+
+/**
+ * ipc_pm_deinit - Free power management component, invalidating its pointer.
+ * @ipc_protocol:	Pointer to iosm_protocol structure
+ */
+void ipc_pm_deinit(struct iosm_protocol *ipc_protocol);
+
+/**
+ * ipc_pm_dev_slp_notification - Handle a sleep notification message from the
+ *				 device. This can be called from interrupt state
+ *				 This function handles Host Sleep requests too
+ *				 if the Host Sleep protocol is register based.
+ * @ipc_pm:			Pointer to power management component
+ * @sleep_notification:		Actual notification from device
+ *
+ * Returns: true if dev sleep state has to be checked, false otherwise.
+ */
+bool ipc_pm_dev_slp_notification(struct iosm_pm *ipc_pm,
+				 u32 sleep_notification);
+
+/**
+ * ipc_pm_set_s2idle_sleep - Set PM variables to sleep/active
+ * @ipc_pm:	Pointer to power management component
+ * @sleep:	true to enter sleep/false to exit sleep
+ */
+void ipc_pm_set_s2idle_sleep(struct iosm_pm *ipc_pm, bool sleep);
+
+/**
+ * ipc_pm_prepare_host_sleep - Prepare the PM for sleep by entering
+ *			       IPC_MEM_HOST_PM_SLEEP_WAIT_D3 state.
+ * @ipc_pm:	Pointer to power management component
+ *
+ * Returns: true on success, false if the host was not active.
+ */
+bool ipc_pm_prepare_host_sleep(struct iosm_pm *ipc_pm);
+
+/**
+ * ipc_pm_prepare_host_active - Prepare the PM for wakeup by entering
+ *				IPC_MEM_HOST_PM_ACTIVE_WAIT state.
+ * @ipc_pm:	Pointer to power management component
+ *
+ * Returns: true on success, false if the host was not sleeping.
+ */
+bool ipc_pm_prepare_host_active(struct iosm_pm *ipc_pm);
+
+/**
+ * ipc_pm_wait_for_device_active - Wait upto IPC_PM_ACTIVE_TIMEOUT_MS ms
+ *				   for the device to reach active state
+ * @ipc_pm:	Pointer to power management component
+ *
+ * Returns: true if device is active, false on timeout
+ */
+bool ipc_pm_wait_for_device_active(struct iosm_pm *ipc_pm);
+
+/**
+ * ipc_pm_signal_hpda_doorbell - Wake up the device if it is in low power mode
+ *				 and trigger a head pointer update interrupt.
+ * @ipc_pm:		Pointer to power management component
+ * @identifier:		specifies what component triggered hpda update irq
+ * @host_slp_check:	if set to true then Host Sleep state machine check will
+ *			be performed. If Host Sleep state machine allows HP
+ *			update then only doorbell is triggered otherwise pending
+ *			flag will be set. If set to false then Host Sleep check
+ *			will not be performed. This is helpful for Host Sleep
+ *			negotiation through message ring.
+ */
+void ipc_pm_signal_hpda_doorbell(struct iosm_pm *ipc_pm, u32 identifier,
+				 bool host_slp_check);
+/**
+ * ipc_pm_trigger - Update power manager and wake up the link if needed
+ * @ipc_pm:	Pointer to power management component
+ * @unit:	Power management units
+ * @active:	Device link state
+ *
+ * Returns: true if link is unchanged or active, false otherwise
+ */
+bool ipc_pm_trigger(struct iosm_pm *ipc_pm, enum ipc_pm_unit unit, bool active);
+
+#endif
diff --git a/drivers/net/wwan/iosm/iosm_ipc_port.c b/drivers/net/wwan/iosm/iosm_ipc_port.c
new file mode 100644
index 000000000000..beb944847398
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_port.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#include "iosm_ipc_chnl_cfg.h"
+#include "iosm_ipc_imem_ops.h"
+#include "iosm_ipc_port.h"
+
+/* open logical channel for control communication */
+static int ipc_port_ctrl_start(struct wwan_port *port)
+{
+	struct iosm_cdev *ipc_port = wwan_port_get_drvdata(port);
+	int ret = 0;
+
+	ipc_port->channel = ipc_imem_sys_port_open(ipc_port->ipc_imem,
+						   ipc_port->chl_id,
+						   IPC_HP_CDEV_OPEN);
+	if (!ipc_port->channel)
+		ret = -EIO;
+
+	return ret;
+}
+
+/* close logical channel */
+static void ipc_port_ctrl_stop(struct wwan_port *port)
+{
+	struct iosm_cdev *ipc_port = wwan_port_get_drvdata(port);
+
+	ipc_imem_sys_cdev_close(ipc_port);
+}
+
+/* transfer control data to modem */
+static int ipc_port_ctrl_tx(struct wwan_port *port, struct sk_buff *skb)
+{
+	struct iosm_cdev *ipc_port = wwan_port_get_drvdata(port);
+
+	return ipc_imem_sys_cdev_write(ipc_port, skb);
+}
+
+static const struct wwan_port_ops ipc_wwan_ctrl_ops = {
+	.start = ipc_port_ctrl_start,
+	.stop = ipc_port_ctrl_stop,
+	.tx = ipc_port_ctrl_tx,
+};
+
+/* Port init func */
+struct iosm_cdev *ipc_port_init(struct iosm_imem *ipc_imem,
+				struct ipc_chnl_cfg ipc_port_cfg)
+{
+	struct iosm_cdev *ipc_port = kzalloc(sizeof(*ipc_port), GFP_KERNEL);
+	enum wwan_port_type port_type = ipc_port_cfg.wwan_port_type;
+	enum ipc_channel_id chl_id = ipc_port_cfg.id;
+
+	if (!ipc_port)
+		return NULL;
+
+	ipc_port->dev = ipc_imem->dev;
+	ipc_port->pcie = ipc_imem->pcie;
+
+	ipc_port->port_type = port_type;
+	ipc_port->chl_id = chl_id;
+	ipc_port->ipc_imem = ipc_imem;
+
+	ipc_port->iosm_port = wwan_create_port(ipc_port->dev, port_type,
+					       &ipc_wwan_ctrl_ops, ipc_port);
+
+	return ipc_port;
+}
+
+/* Port deinit func */
+void ipc_port_deinit(struct iosm_cdev *port[])
+{
+	struct iosm_cdev *ipc_port;
+	u8 ctrl_chl_nr;
+
+	for (ctrl_chl_nr = 0; ctrl_chl_nr < IPC_MEM_MAX_CHANNELS;
+	     ctrl_chl_nr++) {
+		if (port[ctrl_chl_nr]) {
+			ipc_port = port[ctrl_chl_nr];
+			wwan_remove_port(ipc_port->iosm_port);
+			kfree(ipc_port);
+		}
+	}
+}
diff --git a/drivers/net/wwan/iosm/iosm_ipc_port.h b/drivers/net/wwan/iosm/iosm_ipc_port.h
new file mode 100644
index 000000000000..11bc8ed21616
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_port.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#ifndef IOSM_IPC_PORT_H
+#define IOSM_IPC_PORT_H
+
+#include <linux/wwan.h>
+
+#include "iosm_ipc_imem_ops.h"
+
+/**
+ * struct iosm_cdev - State of the char driver layer.
+ * @iosm_port:		Pointer of type wwan_port
+ * @ipc_imem:		imem instance
+ * @dev:		Pointer to device struct
+ * @pcie:		PCIe component
+ * @port_type:		WWAN port type
+ * @channel:		Channel instance
+ * @chl_id:		Channel Indentifier
+ */
+struct iosm_cdev {
+	struct wwan_port *iosm_port;
+	struct iosm_imem *ipc_imem;
+	struct device *dev;
+	struct iosm_pcie *pcie;
+	enum wwan_port_type port_type;
+	struct ipc_mem_channel *channel;
+	enum ipc_channel_id chl_id;
+};
+
+/**
+ * ipc_port_init - Allocate IPC port & register to wwan subsystem for AT/MBIM
+ *		   communication.
+ * @ipc_imem:		Pointer to iosm_imem structure
+ * @ipc_port_cfg:	IPC Port Config
+ *
+ * Returns: 0 on success & NULL on failure
+ */
+struct iosm_cdev *ipc_port_init(struct iosm_imem *ipc_imem,
+				struct ipc_chnl_cfg ipc_port_cfg);
+
+/**
+ * ipc_port_deinit - Free IPC port & unregister port with wwan subsystem.
+ * @ipc_port:	Array of pointer to the ipc port data-struct
+ */
+void ipc_port_deinit(struct iosm_cdev *ipc_port[]);
+
+#endif
diff --git a/drivers/net/wwan/iosm/iosm_ipc_protocol.c b/drivers/net/wwan/iosm/iosm_ipc_protocol.c
new file mode 100644
index 000000000000..834d8b146a94
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_protocol.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#include "iosm_ipc_imem.h"
+#include "iosm_ipc_protocol.h"
+#include "iosm_ipc_protocol_ops.h"
+#include "iosm_ipc_pm.h"
+#include "iosm_ipc_task_queue.h"
+
+int ipc_protocol_tq_msg_send(struct iosm_protocol *ipc_protocol,
+			     enum ipc_msg_prep_type msg_type,
+			     union ipc_msg_prep_args *prep_args,
+			     struct ipc_rsp *response)
+{
+	int index = ipc_protocol_msg_prep(ipc_protocol->imem, msg_type,
+					  prep_args);
+
+	/* Store reference towards caller specified response in response ring
+	 * and signal CP
+	 */
+	if (index >= 0 && index < IPC_MEM_MSG_ENTRIES) {
+		ipc_protocol->rsp_ring[index] = response;
+		ipc_protocol_msg_hp_update(ipc_protocol->imem);
+	}
+
+	return index;
+}
+
+/* Callback for message send */
+static int ipc_protocol_tq_msg_send_cb(struct iosm_imem *ipc_imem, int arg,
+				       void *msg, size_t size)
+{
+	struct ipc_call_msg_send_args *send_args = msg;
+	struct iosm_protocol *ipc_protocol = ipc_imem->ipc_protocol;
+
+	return ipc_protocol_tq_msg_send(ipc_protocol, send_args->msg_type,
+					send_args->prep_args,
+					send_args->response);
+}
+
+/* Remove reference to a response. This is typically used when a requestor timed
+ * out and is no longer interested in the response.
+ */
+static int ipc_protocol_tq_msg_remove(struct iosm_imem *ipc_imem, int arg,
+				      void *msg, size_t size)
+{
+	struct iosm_protocol *ipc_protocol = ipc_imem->ipc_protocol;
+
+	ipc_protocol->rsp_ring[arg] = NULL;
+	return 0;
+}
+
+int ipc_protocol_msg_send(struct iosm_protocol *ipc_protocol,
+			  enum ipc_msg_prep_type prep,
+			  union ipc_msg_prep_args *prep_args)
+{
+	struct ipc_call_msg_send_args send_args;
+	unsigned int exec_timeout;
+	struct ipc_rsp response;
+	int index;
+
+	exec_timeout = (ipc_protocol_get_ap_exec_stage(ipc_protocol) ==
+					IPC_MEM_EXEC_STAGE_RUN ?
+				IPC_MSG_COMPLETE_RUN_DEFAULT_TIMEOUT :
+				IPC_MSG_COMPLETE_BOOT_DEFAULT_TIMEOUT);
+
+	/* Trap if called from non-preemptible context */
+	might_sleep();
+
+	response.status = IPC_MEM_MSG_CS_INVALID;
+	init_completion(&response.completion);
+
+	send_args.msg_type = prep;
+	send_args.prep_args = prep_args;
+	send_args.response = &response;
+
+	/* Allocate and prepare message to be sent in tasklet context.
+	 * A positive index returned form tasklet_call references the message
+	 * in case it needs to be cancelled when there is a timeout.
+	 */
+	index = ipc_task_queue_send_task(ipc_protocol->imem,
+					 ipc_protocol_tq_msg_send_cb, 0,
+					 &send_args, 0, true);
+
+	if (index < 0) {
+		dev_err(ipc_protocol->dev, "msg %d failed", prep);
+		return index;
+	}
+
+	/* Wait for the device to respond to the message */
+	switch (wait_for_completion_timeout(&response.completion,
+					    msecs_to_jiffies(exec_timeout))) {
+	case 0:
+		/* Timeout, there was no response from the device.
+		 * Remove the reference to the local response completion
+		 * object as we are no longer interested in the response.
+		 */
+		ipc_task_queue_send_task(ipc_protocol->imem,
+					 ipc_protocol_tq_msg_remove, index,
+					 NULL, 0, true);
+		dev_err(ipc_protocol->dev, "msg timeout");
+		ipc_uevent_send(ipc_protocol->pcie->dev, UEVENT_MDM_TIMEOUT);
+		break;
+	default:
+		/* We got a response in time; check completion status: */
+		if (response.status != IPC_MEM_MSG_CS_SUCCESS) {
+			dev_err(ipc_protocol->dev,
+				"msg completion status error %d",
+				response.status);
+			return -EIO;
+		}
+	}
+
+	return 0;
+}
+
+static int ipc_protocol_msg_send_host_sleep(struct iosm_protocol *ipc_protocol,
+					    u32 state)
+{
+	union ipc_msg_prep_args prep_args = {
+		.sleep.target = 0,
+		.sleep.state = state,
+	};
+
+	return ipc_protocol_msg_send(ipc_protocol, IPC_MSG_PREP_SLEEP,
+				     &prep_args);
+}
+
+void ipc_protocol_doorbell_trigger(struct iosm_protocol *ipc_protocol,
+				   u32 identifier)
+{
+	ipc_pm_signal_hpda_doorbell(&ipc_protocol->pm, identifier, true);
+}
+
+bool ipc_protocol_pm_dev_sleep_handle(struct iosm_protocol *ipc_protocol)
+{
+	u32 ipc_status = ipc_protocol_get_ipc_status(ipc_protocol);
+	u32 requested;
+
+	if (ipc_status != IPC_MEM_DEVICE_IPC_RUNNING) {
+		dev_err(ipc_protocol->dev,
+			"irq ignored, CP IPC state is %d, should be RUNNING",
+			ipc_status);
+
+		/* Stop further processing. */
+		return false;
+	}
+
+	/* Get a copy of the requested PM state by the device and the local
+	 * device PM state.
+	 */
+	requested = ipc_protocol_pm_dev_get_sleep_notification(ipc_protocol);
+
+	return ipc_pm_dev_slp_notification(&ipc_protocol->pm, requested);
+}
+
+static int ipc_protocol_tq_wakeup_dev_slp(struct iosm_imem *ipc_imem, int arg,
+					  void *msg, size_t size)
+{
+	struct iosm_pm *ipc_pm = &ipc_imem->ipc_protocol->pm;
+
+	/* Wakeup from device sleep if it is not ACTIVE */
+	ipc_pm_trigger(ipc_pm, IPC_PM_UNIT_HS, true);
+
+	ipc_pm_trigger(ipc_pm, IPC_PM_UNIT_HS, false);
+
+	return 0;
+}
+
+void ipc_protocol_s2idle_sleep(struct iosm_protocol *ipc_protocol, bool sleep)
+{
+	ipc_pm_set_s2idle_sleep(&ipc_protocol->pm, sleep);
+}
+
+bool ipc_protocol_suspend(struct iosm_protocol *ipc_protocol)
+{
+	if (!ipc_pm_prepare_host_sleep(&ipc_protocol->pm))
+		goto err;
+
+	ipc_task_queue_send_task(ipc_protocol->imem,
+				 ipc_protocol_tq_wakeup_dev_slp, 0, NULL, 0,
+				 true);
+
+	if (!ipc_pm_wait_for_device_active(&ipc_protocol->pm)) {
+		ipc_uevent_send(ipc_protocol->pcie->dev, UEVENT_MDM_TIMEOUT);
+		goto err;
+	}
+
+	/* Send the sleep message for sync sys calls. */
+	dev_dbg(ipc_protocol->dev, "send TARGET_HOST, ENTER_SLEEP");
+	if (ipc_protocol_msg_send_host_sleep(ipc_protocol,
+					     IPC_HOST_SLEEP_ENTER_SLEEP)) {
+		/* Sending ENTER_SLEEP message failed, we are still active */
+		ipc_protocol->pm.host_pm_state = IPC_MEM_HOST_PM_ACTIVE;
+		goto err;
+	}
+
+	ipc_protocol->pm.host_pm_state = IPC_MEM_HOST_PM_SLEEP;
+	return true;
+err:
+	return false;
+}
+
+bool ipc_protocol_resume(struct iosm_protocol *ipc_protocol)
+{
+	if (!ipc_pm_prepare_host_active(&ipc_protocol->pm))
+		return false;
+
+	dev_dbg(ipc_protocol->dev, "send TARGET_HOST, EXIT_SLEEP");
+	if (ipc_protocol_msg_send_host_sleep(ipc_protocol,
+					     IPC_HOST_SLEEP_EXIT_SLEEP)) {
+		ipc_protocol->pm.host_pm_state = IPC_MEM_HOST_PM_SLEEP;
+		return false;
+	}
+
+	ipc_protocol->pm.host_pm_state = IPC_MEM_HOST_PM_ACTIVE;
+
+	return true;
+}
+
+struct iosm_protocol *ipc_protocol_init(struct iosm_imem *ipc_imem)
+{
+	struct iosm_protocol *ipc_protocol =
+		kzalloc(sizeof(*ipc_protocol), GFP_KERNEL);
+	struct ipc_protocol_context_info *p_ci;
+	u64 addr;
+
+	if (!ipc_protocol)
+		return NULL;
+
+	ipc_protocol->dev = ipc_imem->dev;
+	ipc_protocol->pcie = ipc_imem->pcie;
+	ipc_protocol->imem = ipc_imem;
+	ipc_protocol->p_ap_shm = NULL;
+	ipc_protocol->phy_ap_shm = 0;
+
+	ipc_protocol->old_msg_tail = 0;
+
+	ipc_protocol->p_ap_shm =
+		pci_alloc_consistent(ipc_protocol->pcie->pci,
+				     sizeof(*ipc_protocol->p_ap_shm),
+				     &ipc_protocol->phy_ap_shm);
+
+	if (!ipc_protocol->p_ap_shm) {
+		dev_err(ipc_protocol->dev, "pci shm alloc error");
+		kfree(ipc_protocol);
+		return NULL;
+	}
+
+	/* Prepare the context info for CP. */
+	addr = ipc_protocol->phy_ap_shm;
+	p_ci = &ipc_protocol->p_ap_shm->ci;
+	p_ci->device_info_addr =
+		addr + offsetof(struct ipc_protocol_ap_shm, device_info);
+	p_ci->head_array =
+		addr + offsetof(struct ipc_protocol_ap_shm, head_array);
+	p_ci->tail_array =
+		addr + offsetof(struct ipc_protocol_ap_shm, tail_array);
+	p_ci->msg_head = addr + offsetof(struct ipc_protocol_ap_shm, msg_head);
+	p_ci->msg_tail = addr + offsetof(struct ipc_protocol_ap_shm, msg_tail);
+	p_ci->msg_ring_addr =
+		addr + offsetof(struct ipc_protocol_ap_shm, msg_ring);
+	p_ci->msg_ring_entries = cpu_to_le16(IPC_MEM_MSG_ENTRIES);
+	p_ci->msg_irq_vector = IPC_MSG_IRQ_VECTOR;
+	p_ci->device_info_irq_vector = IPC_DEVICE_IRQ_VECTOR;
+
+	ipc_mmio_set_contex_info_addr(ipc_imem->mmio, addr);
+
+	ipc_pm_init(ipc_protocol);
+
+	return ipc_protocol;
+}
+
+void ipc_protocol_deinit(struct iosm_protocol *proto)
+{
+	pci_free_consistent(proto->pcie->pci, sizeof(*proto->p_ap_shm),
+			    proto->p_ap_shm, proto->phy_ap_shm);
+
+	ipc_pm_deinit(proto);
+	kfree(proto);
+}
diff --git a/drivers/net/wwan/iosm/iosm_ipc_protocol.h b/drivers/net/wwan/iosm/iosm_ipc_protocol.h
new file mode 100644
index 000000000000..9b3a6d86ece7
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_protocol.h
@@ -0,0 +1,237 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#ifndef IOSM_IPC_PROTOCOL_H
+#define IOSM_IPC_PROTOCOL_H
+
+#include "iosm_ipc_imem.h"
+#include "iosm_ipc_pm.h"
+#include "iosm_ipc_protocol_ops.h"
+
+/* Trigger the doorbell interrupt on CP. */
+#define IPC_DOORBELL_IRQ_HPDA 0
+#define IPC_DOORBELL_IRQ_IPC 1
+#define IPC_DOORBELL_IRQ_SLEEP 2
+
+/* IRQ vector number. */
+#define IPC_DEVICE_IRQ_VECTOR 0
+#define IPC_MSG_IRQ_VECTOR 0
+#define IPC_UL_PIPE_IRQ_VECTOR 0
+#define IPC_DL_PIPE_IRQ_VECTOR 0
+
+#define IPC_MEM_MSG_ENTRIES 128
+
+/* Default time out for sending IPC messages like open pipe, close pipe etc.
+ * during run mode.
+ *
+ * If the message interface lock to CP times out, the link to CP is broken.
+ * mode : run mode (IPC_MEM_EXEC_STAGE_RUN)
+ * unit : milliseconds
+ */
+#define IPC_MSG_COMPLETE_RUN_DEFAULT_TIMEOUT 500 /* 0.5 seconds */
+
+/* Default time out for sending IPC messages like open pipe, close pipe etc.
+ * during boot mode.
+ *
+ * If the message interface lock to CP times out, the link to CP is broken.
+ * mode : boot mode
+ * (IPC_MEM_EXEC_STAGE_BOOT | IPC_MEM_EXEC_STAGE_PSI | IPC_MEM_EXEC_STAGE_EBL)
+ * unit : milliseconds
+ */
+#define IPC_MSG_COMPLETE_BOOT_DEFAULT_TIMEOUT 500 /* 0.5 seconds */
+
+/**
+ * struct ipc_protocol_context_info - Structure of the context info
+ * @device_info_addr:		64 bit address to device info
+ * @head_array:			64 bit address to head pointer arr for the pipes
+ * @tail_array:			64 bit address to tail pointer arr for the pipes
+ * @msg_head:			64 bit address to message head pointer
+ * @msg_tail:			64 bit address to message tail pointer
+ * @msg_ring_addr:		64 bit pointer to the message ring buffer
+ * @msg_ring_entries:		This field provides the number of entries which
+ *				the MR can hold
+ * @msg_irq_vector:		This field provides the IRQ which shall be
+ *				generated by the EP device when generating
+ *				completion for Messages.
+ * @device_info_irq_vector:	This field provides the IRQ which shall be
+ *				generated by the EP dev after updating Dev. Info
+ */
+struct ipc_protocol_context_info {
+	phys_addr_t device_info_addr;
+	phys_addr_t head_array;
+	phys_addr_t tail_array;
+	phys_addr_t msg_head;
+	phys_addr_t msg_tail;
+	phys_addr_t msg_ring_addr;
+	__le16 msg_ring_entries;
+	u8 msg_irq_vector;
+	u8 device_info_irq_vector;
+};
+
+/**
+ * struct ipc_protocol_device_info - Structure for the device information
+ * @execution_stage:		CP execution stage
+ * @ipc_status:			IPC states
+ * @device_sleep_notification:	Requested device pm states
+ */
+struct ipc_protocol_device_info {
+	__le32 execution_stage;
+	__le32 ipc_status;
+	__le32 device_sleep_notification;
+};
+
+/**
+ * struct ipc_protocol_ap_shm - Protocol Shared Memory Structure
+ * @ci:			Context information struct
+ * @device_info:	Device information struct
+ * @msg_head:		Point to msg head
+ * @head_array:		Array of head pointer
+ * @msg_tail:		Point to msg tail
+ * @tail_array:		Array of tail pointer
+ * @msg_ring:		Circular buffers for the read/tail and write/head
+ *			indeces.
+ */
+struct ipc_protocol_ap_shm {
+	struct ipc_protocol_context_info ci;
+	struct ipc_protocol_device_info device_info;
+	__le32 msg_head;
+	__le32 head_array[IPC_MEM_MAX_PIPES];
+	__le32 msg_tail;
+	__le32 tail_array[IPC_MEM_MAX_PIPES];
+	union ipc_mem_msg_entry msg_ring[IPC_MEM_MSG_ENTRIES];
+};
+
+/**
+ * struct iosm_protocol - Structure for IPC protocol.
+ * @p_ap_shm:		Pointer to Protocol Shared Memory Structure
+ * @pm:			Instance to struct iosm_pm
+ * @pcie:		Pointer to struct iosm_pcie
+ * @imem:		Pointer to struct iosm_imem
+ * @rsp_ring:		Array of OS completion objects to be triggered once CP
+ *			acknowledges a request in the message ring
+ * @dev:		Pointer to device structure
+ * @phy_ap_shm:		Physical/Mapped representation of the shared memory info
+ * @old_msg_tail:	Old msg tail ptr, until AP has handled ACK's from CP
+ */
+struct iosm_protocol {
+	struct ipc_protocol_ap_shm *p_ap_shm;
+	struct iosm_pm pm;
+	struct iosm_pcie *pcie;
+	struct iosm_imem *imem;
+	struct ipc_rsp *rsp_ring[IPC_MEM_MSG_ENTRIES];
+	struct device *dev;
+	phys_addr_t phy_ap_shm;
+	u32 old_msg_tail;
+};
+
+/**
+ * struct ipc_call_msg_send_args - Structure for message argument for
+ *				   tasklet function.
+ * @prep_args:		Arguments for message preparation function
+ * @response:		Can be NULL if result can be ignored
+ * @msg_type:		Message Type
+ */
+struct ipc_call_msg_send_args {
+	union ipc_msg_prep_args *prep_args;
+	struct ipc_rsp *response;
+	enum ipc_msg_prep_type msg_type;
+};
+
+/**
+ * ipc_protocol_tq_msg_send - prepare the msg and send to CP
+ * @ipc_protocol:	Pointer to ipc_protocol instance
+ * @msg_type:		Message type
+ * @prep_args:		Message arguments
+ * @response:		Pointer to a response object which has a
+ *			completion object and return code.
+ *
+ * Returns: 0 on success and failure value on error
+ */
+int ipc_protocol_tq_msg_send(struct iosm_protocol *ipc_protocol,
+			     enum ipc_msg_prep_type msg_type,
+			     union ipc_msg_prep_args *prep_args,
+			     struct ipc_rsp *response);
+
+/**
+ * ipc_protocol_msg_send - Send ipc control message to CP and wait for response
+ * @ipc_protocol:	Pointer to ipc_protocol instance
+ * @prep:		Message type
+ * @prep_args:		Message arguments
+ *
+ * Returns: 0 on success and failure value on error
+ */
+int ipc_protocol_msg_send(struct iosm_protocol *ipc_protocol,
+			  enum ipc_msg_prep_type prep,
+			  union ipc_msg_prep_args *prep_args);
+
+/**
+ * ipc_protocol_suspend - Signal to CP that host wants to go to sleep (suspend).
+ * @ipc_protocol:	Pointer to ipc_protocol instance
+ *
+ * Returns: true if host can suspend, false if suspend must be aborted.
+ */
+bool ipc_protocol_suspend(struct iosm_protocol *ipc_protocol);
+
+/**
+ * ipc_protocol_s2idle_sleep - Call PM function to set PM variables in s2idle
+ *			       sleep/active case
+ * @ipc_protocol:	Pointer to ipc_protocol instance
+ * @sleep:		True for sleep/False for active
+ */
+void ipc_protocol_s2idle_sleep(struct iosm_protocol *ipc_protocol, bool sleep);
+
+/**
+ * ipc_protocol_resume - Signal to CP that host wants to resume operation.
+ * @ipc_protocol:	Pointer to ipc_protocol instance
+ *
+ * Returns: true if host can resume, false if there is a problem.
+ */
+bool ipc_protocol_resume(struct iosm_protocol *ipc_protocol);
+
+/**
+ * ipc_protocol_pm_dev_sleep_handle - Handles the Device Sleep state change
+ *				      notification.
+ * @ipc_protocol:	Pointer to ipc_protocol instance.
+ *
+ * Returns: true if sleep notification handled, false otherwise.
+ */
+bool ipc_protocol_pm_dev_sleep_handle(struct iosm_protocol *ipc_protocol);
+
+/**
+ * ipc_protocol_doorbell_trigger - Wrapper for PM function which wake up the
+ *				   device if it is in low power mode
+ *				   and trigger a head pointer update interrupt.
+ * @ipc_protocol:	Pointer to ipc_protocol instance.
+ * @identifier:		Specifies what component triggered hpda
+ *			update irq
+ */
+void ipc_protocol_doorbell_trigger(struct iosm_protocol *ipc_protocol,
+				   u32 identifier);
+
+/**
+ * ipc_protocol_sleep_notification_string - Returns last Sleep Notification as
+ *					    string.
+ * @ipc_protocol:	Instance pointer of Protocol module.
+ *
+ * Returns: Pointer to string.
+ */
+const char *
+ipc_protocol_sleep_notification_string(struct iosm_protocol *ipc_protocol);
+
+/**
+ * ipc_protocol_init - Allocates IPC protocol instance
+ * @ipc_imem:		Pointer to iosm_imem structure
+ *
+ * Returns: Address of IPC  protocol instance on success & NULL on failure.
+ */
+struct iosm_protocol *ipc_protocol_init(struct iosm_imem *ipc_imem);
+
+/**
+ * ipc_protocol_deinit - Deallocates IPC protocol instance
+ * @ipc_protocol:	pointer to the IPC protocol instance
+ */
+void ipc_protocol_deinit(struct iosm_protocol *ipc_protocol);
+
+#endif
diff --git a/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c b/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c
new file mode 100644
index 000000000000..91109e27efd3
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c
@@ -0,0 +1,552 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#include "iosm_ipc_protocol.h"
+#include "iosm_ipc_protocol_ops.h"
+
+/* Get the next free message element.*/
+static union ipc_mem_msg_entry *
+ipc_protocol_free_msg_get(struct iosm_protocol *ipc_protocol, int *index)
+{
+	u32 head = le32_to_cpu(ipc_protocol->p_ap_shm->msg_head);
+	u32 new_head = (head + 1) % IPC_MEM_MSG_ENTRIES;
+	union ipc_mem_msg_entry *msg;
+
+	if (new_head == le32_to_cpu(ipc_protocol->p_ap_shm->msg_tail)) {
+		dev_err(ipc_protocol->dev, "message ring is full");
+		return NULL;
+	}
+
+	/* Get the pointer to the next free message element,
+	 * reset the fields and mark is as invalid.
+	 */
+	msg = &ipc_protocol->p_ap_shm->msg_ring[head];
+	memset(msg, 0, sizeof(*msg));
+
+	/* return index in message ring */
+	*index = head;
+
+	return msg;
+}
+
+/* Updates the message ring Head pointer */
+void ipc_protocol_msg_hp_update(struct iosm_imem *ipc_imem)
+{
+	struct iosm_protocol *ipc_protocol = ipc_imem->ipc_protocol;
+	u32 head = le32_to_cpu(ipc_protocol->p_ap_shm->msg_head);
+	u32 new_head = (head + 1) % IPC_MEM_MSG_ENTRIES;
+
+	/* Update head pointer and fire doorbell. */
+	ipc_protocol->p_ap_shm->msg_head = cpu_to_le32(new_head);
+	ipc_protocol->old_msg_tail =
+		le32_to_cpu(ipc_protocol->p_ap_shm->msg_tail);
+
+	ipc_pm_signal_hpda_doorbell(&ipc_protocol->pm, IPC_HP_MR, false);
+}
+
+/* Allocate and prepare a OPEN_PIPE message.
+ * This also allocates the memory for the new TDR structure and
+ * updates the pipe structure referenced in the preparation arguments.
+ */
+static int ipc_protocol_msg_prepipe_open(struct iosm_protocol *ipc_protocol,
+					 union ipc_msg_prep_args *args)
+{
+	int index;
+	union ipc_mem_msg_entry *msg =
+		ipc_protocol_free_msg_get(ipc_protocol, &index);
+	struct ipc_pipe *pipe = args->pipe_open.pipe;
+	struct ipc_protocol_td *tdr;
+	struct sk_buff **skbr;
+
+	if (!msg) {
+		dev_err(ipc_protocol->dev, "failed to get free message");
+		return -EIO;
+	}
+
+	/* Allocate the skbuf elements for the skbuf which are on the way.
+	 * SKB ring is internal memory allocation for driver. No need to
+	 * re-calculate the start and end addresses.
+	 */
+	skbr = kcalloc(pipe->nr_of_entries, sizeof(*skbr), GFP_ATOMIC);
+	if (!skbr)
+		return -ENOMEM;
+
+	/* Allocate the transfer descriptors for the pipe. */
+	tdr = pci_alloc_consistent(ipc_protocol->pcie->pci,
+				   pipe->nr_of_entries * sizeof(*tdr),
+				   &pipe->phy_tdr_start);
+	if (!tdr) {
+		kfree(skbr);
+		dev_err(ipc_protocol->dev, "tdr alloc error");
+		return -ENOMEM;
+	}
+
+	pipe->max_nr_of_queued_entries = pipe->nr_of_entries - 1;
+	pipe->nr_of_queued_entries = 0;
+	pipe->tdr_start = tdr;
+	pipe->skbr_start = skbr;
+	pipe->old_tail = 0;
+
+	ipc_protocol->p_ap_shm->head_array[pipe->pipe_nr] = 0;
+
+	msg->open_pipe.type_of_message = IPC_MEM_MSG_OPEN_PIPE;
+	msg->open_pipe.pipe_nr = pipe->pipe_nr;
+	msg->open_pipe.tdr_addr = cpu_to_le64(pipe->phy_tdr_start);
+	msg->open_pipe.tdr_entries = cpu_to_le16(pipe->nr_of_entries);
+	msg->open_pipe.accumulation_backoff =
+				cpu_to_le32(pipe->accumulation_backoff);
+	msg->open_pipe.irq_vector = cpu_to_le32(pipe->irq);
+
+	return index;
+}
+
+static int ipc_protocol_msg_prepipe_close(struct iosm_protocol *ipc_protocol,
+					  union ipc_msg_prep_args *args)
+{
+	int index = -1;
+	union ipc_mem_msg_entry *msg =
+		ipc_protocol_free_msg_get(ipc_protocol, &index);
+	struct ipc_pipe *pipe = args->pipe_close.pipe;
+
+	if (!msg)
+		return -EIO;
+
+	msg->close_pipe.type_of_message = IPC_MEM_MSG_CLOSE_PIPE;
+	msg->close_pipe.pipe_nr = pipe->pipe_nr;
+
+	dev_dbg(ipc_protocol->dev, "IPC_MEM_MSG_CLOSE_PIPE(pipe_nr=%d)",
+		msg->close_pipe.pipe_nr);
+
+	return index;
+}
+
+static int ipc_protocol_msg_prep_sleep(struct iosm_protocol *ipc_protocol,
+				       union ipc_msg_prep_args *args)
+{
+	int index = -1;
+	union ipc_mem_msg_entry *msg =
+		ipc_protocol_free_msg_get(ipc_protocol, &index);
+
+	if (!msg) {
+		dev_err(ipc_protocol->dev, "failed to get free message");
+		return -EIO;
+	}
+
+	/* Prepare and send the host sleep message to CP to enter or exit D3. */
+	msg->host_sleep.type_of_message = IPC_MEM_MSG_SLEEP;
+	msg->host_sleep.target = args->sleep.target; /* 0=host, 1=device */
+
+	/* state; 0=enter, 1=exit 2=enter w/o protocol */
+	msg->host_sleep.state = args->sleep.state;
+
+	dev_dbg(ipc_protocol->dev, "IPC_MEM_MSG_SLEEP(target=%d; state=%d)",
+		msg->host_sleep.target, msg->host_sleep.state);
+
+	return index;
+}
+
+static int ipc_protocol_msg_prep_feature_set(struct iosm_protocol *ipc_protocol,
+					     union ipc_msg_prep_args *args)
+{
+	int index = -1;
+	union ipc_mem_msg_entry *msg =
+		ipc_protocol_free_msg_get(ipc_protocol, &index);
+
+	if (!msg) {
+		dev_err(ipc_protocol->dev, "failed to get free message");
+		return -EIO;
+	}
+
+	msg->feature_set.type_of_message = IPC_MEM_MSG_FEATURE_SET;
+	msg->feature_set.reset_enable = args->feature_set.reset_enable <<
+					RESET_BIT;
+
+	dev_dbg(ipc_protocol->dev, "IPC_MEM_MSG_FEATURE_SET(reset_enable=%d)",
+		msg->feature_set.reset_enable >> RESET_BIT);
+
+	return index;
+}
+
+/* Processes the message consumed by CP. */
+bool ipc_protocol_msg_process(struct iosm_imem *ipc_imem, int irq)
+{
+	struct iosm_protocol *ipc_protocol = ipc_imem->ipc_protocol;
+	struct ipc_rsp **rsp_ring = ipc_protocol->rsp_ring;
+	bool msg_processed = false;
+	u32 i;
+
+	if (le32_to_cpu(ipc_protocol->p_ap_shm->msg_tail) >=
+			IPC_MEM_MSG_ENTRIES) {
+		dev_err(ipc_protocol->dev, "msg_tail out of range: %d",
+			le32_to_cpu(ipc_protocol->p_ap_shm->msg_tail));
+		return msg_processed;
+	}
+
+	if (irq != IMEM_IRQ_DONT_CARE &&
+	    irq != ipc_protocol->p_ap_shm->ci.msg_irq_vector)
+		return msg_processed;
+
+	for (i = ipc_protocol->old_msg_tail;
+	     i != le32_to_cpu(ipc_protocol->p_ap_shm->msg_tail);
+	     i = (i + 1) % IPC_MEM_MSG_ENTRIES) {
+		union ipc_mem_msg_entry *msg =
+			&ipc_protocol->p_ap_shm->msg_ring[i];
+
+		dev_dbg(ipc_protocol->dev, "msg[%d]: type=%u status=%d", i,
+			msg->common.type_of_message,
+			msg->common.completion_status);
+
+		/* Update response with status and wake up waiting requestor */
+		if (rsp_ring[i]) {
+			rsp_ring[i]->status =
+				le32_to_cpu(msg->common.completion_status);
+			complete(&rsp_ring[i]->completion);
+			rsp_ring[i] = NULL;
+		}
+		msg_processed = true;
+	}
+
+	ipc_protocol->old_msg_tail = i;
+	return msg_processed;
+}
+
+/* Sends data from UL list to CP for the provided pipe by updating the Head
+ * pointer of given pipe.
+ */
+bool ipc_protocol_ul_td_send(struct iosm_protocol *ipc_protocol,
+			     struct ipc_pipe *pipe,
+			     struct sk_buff_head *p_ul_list)
+{
+	struct ipc_protocol_td *td;
+	bool hpda_pending = false;
+	struct sk_buff *skb;
+	s32 free_elements;
+	u32 head;
+	u32 tail;
+
+	if (!ipc_protocol->p_ap_shm) {
+		dev_err(ipc_protocol->dev, "driver is not initialized");
+		return false;
+	}
+
+	/* Get head and tail of the td list and calculate
+	 * the number of free elements.
+	 */
+	head = le32_to_cpu(ipc_protocol->p_ap_shm->head_array[pipe->pipe_nr]);
+	tail = pipe->old_tail;
+
+	while (!skb_queue_empty(p_ul_list)) {
+		if (head < tail)
+			free_elements = tail - head - 1;
+		else
+			free_elements =
+				pipe->nr_of_entries - head + ((s32)tail - 1);
+
+		if (free_elements <= 0) {
+			dev_dbg(ipc_protocol->dev,
+				"no free td elements for UL pipe %d",
+				pipe->pipe_nr);
+			break;
+		}
+
+		/* Get the td address. */
+		td = &pipe->tdr_start[head];
+
+		/* Take the first element of the uplink list and add it
+		 * to the td list.
+		 */
+		skb = skb_dequeue(p_ul_list);
+		if (WARN_ON(!skb))
+			break;
+
+		/* Save the reference to the uplink skbuf. */
+		pipe->skbr_start[head] = skb;
+
+		td->buffer.address = IPC_CB(skb)->mapping;
+		td->scs = cpu_to_le32(skb->len) & cpu_to_le32(SIZE_MASK);
+		td->next = 0;
+
+		pipe->nr_of_queued_entries++;
+
+		/* Calculate the new head and save it. */
+		head++;
+		if (head >= pipe->nr_of_entries)
+			head = 0;
+
+		ipc_protocol->p_ap_shm->head_array[pipe->pipe_nr] =
+			cpu_to_le32(head);
+	}
+
+	if (pipe->old_head != head) {
+		dev_dbg(ipc_protocol->dev, "New UL TDs Pipe:%d", pipe->pipe_nr);
+
+		pipe->old_head = head;
+		/* Trigger doorbell because of pending UL packets. */
+		hpda_pending = true;
+	}
+
+	return hpda_pending;
+}
+
+/* Checks for Tail pointer update from CP and returns the data as SKB. */
+struct sk_buff *ipc_protocol_ul_td_process(struct iosm_protocol *ipc_protocol,
+					   struct ipc_pipe *pipe)
+{
+	struct ipc_protocol_td *p_td = &pipe->tdr_start[pipe->old_tail];
+	struct sk_buff *skb = pipe->skbr_start[pipe->old_tail];
+
+	pipe->nr_of_queued_entries--;
+	pipe->old_tail++;
+	if (pipe->old_tail >= pipe->nr_of_entries)
+		pipe->old_tail = 0;
+
+	if (!p_td->buffer.address) {
+		dev_err(ipc_protocol->dev, "Td buffer address is NULL");
+		return NULL;
+	}
+
+	if (p_td->buffer.address != IPC_CB(skb)->mapping) {
+		dev_err(ipc_protocol->dev,
+			"pipe %d: invalid buf_addr or skb_data",
+			pipe->pipe_nr);
+		return NULL;
+	}
+
+	return skb;
+}
+
+/* Allocates an SKB for CP to send data and updates the Head Pointer
+ * of the given Pipe#.
+ */
+bool ipc_protocol_dl_td_prepare(struct iosm_protocol *ipc_protocol,
+				struct ipc_pipe *pipe)
+{
+	struct ipc_protocol_td *td;
+	dma_addr_t mapping = 0;
+	u32 head, new_head;
+	struct sk_buff *skb;
+	u32 tail;
+
+	/* Get head and tail of the td list and calculate
+	 * the number of free elements.
+	 */
+	head = le32_to_cpu(ipc_protocol->p_ap_shm->head_array[pipe->pipe_nr]);
+	tail = le32_to_cpu(ipc_protocol->p_ap_shm->tail_array[pipe->pipe_nr]);
+
+	new_head = head + 1;
+	if (new_head >= pipe->nr_of_entries)
+		new_head = 0;
+
+	if (new_head == tail)
+		return false;
+
+	/* Get the td address. */
+	td = &pipe->tdr_start[head];
+
+	/* Allocate the skbuf for the descriptor. */
+	skb = ipc_pcie_alloc_skb(ipc_protocol->pcie, pipe->buf_size, GFP_ATOMIC,
+				 &mapping, DMA_FROM_DEVICE,
+				 IPC_MEM_DL_ETH_OFFSET);
+	if (!skb)
+		return false;
+
+	td->buffer.address = mapping;
+	td->scs = cpu_to_le32(pipe->buf_size) & cpu_to_le32(SIZE_MASK);
+	td->next = 0;
+
+	/* store the new head value. */
+	ipc_protocol->p_ap_shm->head_array[pipe->pipe_nr] =
+		cpu_to_le32(new_head);
+
+	/* Save the reference to the skbuf. */
+	pipe->skbr_start[head] = skb;
+
+	pipe->nr_of_queued_entries++;
+
+	return true;
+}
+
+/* Processes DL TD's */
+struct sk_buff *ipc_protocol_dl_td_process(struct iosm_protocol *ipc_protocol,
+					   struct ipc_pipe *pipe)
+{
+	u32 tail =
+		le32_to_cpu(ipc_protocol->p_ap_shm->tail_array[pipe->pipe_nr]);
+	struct ipc_protocol_td *p_td;
+	struct sk_buff *skb;
+
+	if (!pipe->tdr_start)
+		return NULL;
+
+	/* Copy the reference to the downlink buffer. */
+	p_td = &pipe->tdr_start[pipe->old_tail];
+	skb = pipe->skbr_start[pipe->old_tail];
+
+	/* Reset the ring elements. */
+	pipe->skbr_start[pipe->old_tail] = NULL;
+
+	pipe->nr_of_queued_entries--;
+
+	pipe->old_tail++;
+	if (pipe->old_tail >= pipe->nr_of_entries)
+		pipe->old_tail = 0;
+
+	if (!skb) {
+		dev_err(ipc_protocol->dev, "skb is null");
+		goto ret;
+	} else if (!p_td->buffer.address) {
+		dev_err(ipc_protocol->dev, "td/buffer address is null");
+		ipc_pcie_kfree_skb(ipc_protocol->pcie, skb);
+		skb = NULL;
+		goto ret;
+	}
+
+	if (!IPC_CB(skb)) {
+		dev_err(ipc_protocol->dev, "pipe# %d, tail: %d skb_cb is NULL",
+			pipe->pipe_nr, tail);
+		ipc_pcie_kfree_skb(ipc_protocol->pcie, skb);
+		skb = NULL;
+		goto ret;
+	}
+
+	if (p_td->buffer.address != IPC_CB(skb)->mapping) {
+		dev_err(ipc_protocol->dev, "invalid buf=%p or skb=%p",
+			(void *)p_td->buffer.address, skb->data);
+		ipc_pcie_kfree_skb(ipc_protocol->pcie, skb);
+		skb = NULL;
+		goto ret;
+	} else if ((le32_to_cpu(p_td->scs) & SIZE_MASK) > pipe->buf_size) {
+		dev_err(ipc_protocol->dev, "invalid buffer size %d > %d",
+			le32_to_cpu(p_td->scs) & SIZE_MASK,
+			pipe->buf_size);
+		ipc_pcie_kfree_skb(ipc_protocol->pcie, skb);
+		skb = NULL;
+		goto ret;
+	} else if (le32_to_cpu(p_td->scs) >> COMPLETION_STATUS ==
+		  IPC_MEM_TD_CS_ABORT) {
+		/* Discard aborted buffers. */
+		dev_dbg(ipc_protocol->dev, "discard 'aborted' buffers");
+		ipc_pcie_kfree_skb(ipc_protocol->pcie, skb);
+		skb = NULL;
+		goto ret;
+	}
+
+	/* Set the length field in skbuf. */
+	skb_put(skb, le32_to_cpu(p_td->scs) & SIZE_MASK);
+
+ret:
+	return skb;
+}
+
+void ipc_protocol_get_head_tail_index(struct iosm_protocol *ipc_protocol,
+				      struct ipc_pipe *pipe, u32 *head,
+				      u32 *tail)
+{
+	struct ipc_protocol_ap_shm *ipc_ap_shm = ipc_protocol->p_ap_shm;
+
+	if (head)
+		*head = le32_to_cpu(ipc_ap_shm->head_array[pipe->pipe_nr]);
+
+	if (tail)
+		*tail = le32_to_cpu(ipc_ap_shm->tail_array[pipe->pipe_nr]);
+}
+
+/* Frees the TDs given to CP.  */
+void ipc_protocol_pipe_cleanup(struct iosm_protocol *ipc_protocol,
+			       struct ipc_pipe *pipe)
+{
+	struct sk_buff *skb;
+	u32 head;
+	u32 tail;
+
+	/* Get the start and the end of the buffer list. */
+	head = le32_to_cpu(ipc_protocol->p_ap_shm->head_array[pipe->pipe_nr]);
+	tail = pipe->old_tail;
+
+	/* Reset tail and head to 0. */
+	ipc_protocol->p_ap_shm->tail_array[pipe->pipe_nr] = 0;
+	ipc_protocol->p_ap_shm->head_array[pipe->pipe_nr] = 0;
+
+	/* Free pending uplink and downlink buffers. */
+	if (pipe->skbr_start) {
+		while (head != tail) {
+			/* Get the reference to the skbuf,
+			 * which is on the way and free it.
+			 */
+			skb = pipe->skbr_start[tail];
+			if (skb)
+				ipc_pcie_kfree_skb(ipc_protocol->pcie, skb);
+
+			tail++;
+			if (tail >= pipe->nr_of_entries)
+				tail = 0;
+		}
+
+		kfree(pipe->skbr_start);
+		pipe->skbr_start = NULL;
+	}
+
+	pipe->old_tail = 0;
+
+	/* Free and reset the td and skbuf circular buffers. kfree is save! */
+	if (pipe->tdr_start) {
+		pci_free_consistent(ipc_protocol->pcie->pci,
+				    sizeof(*pipe->tdr_start) *
+					    pipe->nr_of_entries,
+				    pipe->tdr_start, pipe->phy_tdr_start);
+
+		pipe->tdr_start = NULL;
+	}
+}
+
+enum ipc_mem_device_ipc_state ipc_protocol_get_ipc_status(struct iosm_protocol
+							  *ipc_protocol)
+{
+	return (enum ipc_mem_device_ipc_state)
+		le32_to_cpu(ipc_protocol->p_ap_shm->device_info.ipc_status);
+}
+
+enum ipc_mem_exec_stage
+ipc_protocol_get_ap_exec_stage(struct iosm_protocol *ipc_protocol)
+{
+	return le32_to_cpu(ipc_protocol->p_ap_shm->device_info.execution_stage);
+}
+
+int ipc_protocol_msg_prep(struct iosm_imem *ipc_imem,
+			  enum ipc_msg_prep_type msg_type,
+			  union ipc_msg_prep_args *args)
+{
+	struct iosm_protocol *ipc_protocol = ipc_imem->ipc_protocol;
+
+	switch (msg_type) {
+	case IPC_MSG_PREP_SLEEP:
+		return ipc_protocol_msg_prep_sleep(ipc_protocol, args);
+
+	case IPC_MSG_PREP_PIPE_OPEN:
+		return ipc_protocol_msg_prepipe_open(ipc_protocol, args);
+
+	case IPC_MSG_PREP_PIPE_CLOSE:
+		return ipc_protocol_msg_prepipe_close(ipc_protocol, args);
+
+	case IPC_MSG_PREP_FEATURE_SET:
+		return ipc_protocol_msg_prep_feature_set(ipc_protocol, args);
+
+		/* Unsupported messages in protocol */
+	case IPC_MSG_PREP_MAP:
+	case IPC_MSG_PREP_UNMAP:
+	default:
+		dev_err(ipc_protocol->dev,
+			"unsupported message type: %d in protocol", msg_type);
+		return -EINVAL;
+	}
+}
+
+u32
+ipc_protocol_pm_dev_get_sleep_notification(struct iosm_protocol *ipc_protocol)
+{
+	struct ipc_protocol_ap_shm *ipc_ap_shm = ipc_protocol->p_ap_shm;
+
+	return le32_to_cpu(ipc_ap_shm->device_info.device_sleep_notification);
+}
diff --git a/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.h b/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.h
new file mode 100644
index 000000000000..35aa1387306e
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.h
@@ -0,0 +1,444 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#ifndef IOSM_IPC_PROTOCOL_OPS_H
+#define IOSM_IPC_PROTOCOL_OPS_H
+
+#define SIZE_MASK 0x00FFFFFF
+#define COMPLETION_STATUS 24
+#define RESET_BIT 7
+
+/**
+ * enum ipc_mem_td_cs - Completion status of a TD
+ * @IPC_MEM_TD_CS_INVALID:	      Initial status - td not yet used.
+ * @IPC_MEM_TD_CS_PARTIAL_TRANSFER:   More data pending -> next TD used for this
+ * @IPC_MEM_TD_CS_END_TRANSFER:	      IO transfer is complete.
+ * @IPC_MEM_TD_CS_OVERFLOW:	      IO transfer to small for the buff to write
+ * @IPC_MEM_TD_CS_ABORT:	      TD marked as abort and shall be discarded
+ *				      by AP.
+ * @IPC_MEM_TD_CS_ERROR:	      General error.
+ */
+enum ipc_mem_td_cs {
+	IPC_MEM_TD_CS_INVALID,
+	IPC_MEM_TD_CS_PARTIAL_TRANSFER,
+	IPC_MEM_TD_CS_END_TRANSFER,
+	IPC_MEM_TD_CS_OVERFLOW,
+	IPC_MEM_TD_CS_ABORT,
+	IPC_MEM_TD_CS_ERROR,
+};
+
+/**
+ * enum ipc_mem_msg_cs - Completion status of IPC Message
+ * @IPC_MEM_MSG_CS_INVALID:	Initial status.
+ * @IPC_MEM_MSG_CS_SUCCESS:	IPC Message completion success.
+ * @IPC_MEM_MSG_CS_ERROR:	Message send error.
+ */
+enum ipc_mem_msg_cs {
+	IPC_MEM_MSG_CS_INVALID,
+	IPC_MEM_MSG_CS_SUCCESS,
+	IPC_MEM_MSG_CS_ERROR,
+};
+
+/**
+ * struct ipc_msg_prep_args_pipe - struct for pipe args for message preparation
+ * @pipe:	Pipe to open/close
+ */
+struct ipc_msg_prep_args_pipe {
+	struct ipc_pipe *pipe;
+};
+
+/**
+ * struct ipc_msg_prep_args_sleep - struct for sleep args for message
+ *				    preparation
+ * @target:	0=host, 1=device
+ * @state:	0=enter sleep, 1=exit sleep
+ */
+struct ipc_msg_prep_args_sleep {
+	unsigned int target;
+	unsigned int state;
+};
+
+/**
+ * struct ipc_msg_prep_feature_set - struct for feature set argument for
+ *				     message preparation
+ * @reset_enable:	0=out-of-band, 1=in-band-crash notification
+ */
+struct ipc_msg_prep_feature_set {
+	u8 reset_enable;
+};
+
+/**
+ * struct ipc_msg_prep_map - struct for map argument for message preparation
+ * @region_id:	Region to map
+ * @addr:	Pcie addr of region to map
+ * @size:	Size of the region to map
+ */
+struct ipc_msg_prep_map {
+	unsigned int region_id;
+	unsigned long addr;
+	size_t size;
+};
+
+/**
+ * struct ipc_msg_prep_unmap - struct for unmap argument for message preparation
+ * @region_id:	Region to unmap
+ */
+struct ipc_msg_prep_unmap {
+	unsigned int region_id;
+};
+
+/**
+ * struct ipc_msg_prep_args - Union to handle different message types
+ * @pipe_open:		Pipe open message preparation struct
+ * @pipe_close:		Pipe close message preparation struct
+ * @sleep:		Sleep message preparation struct
+ * @feature_set:	Feature set message preparation struct
+ * @map:		Memory map message preparation struct
+ * @unmap:		Memory unmap message preparation struct
+ */
+union ipc_msg_prep_args {
+	struct ipc_msg_prep_args_pipe pipe_open;
+	struct ipc_msg_prep_args_pipe pipe_close;
+	struct ipc_msg_prep_args_sleep sleep;
+	struct ipc_msg_prep_feature_set feature_set;
+	struct ipc_msg_prep_map map;
+	struct ipc_msg_prep_unmap unmap;
+};
+
+/**
+ * enum ipc_msg_prep_type - Enum for message prepare actions
+ * @IPC_MSG_PREP_SLEEP:		Sleep message preparation type
+ * @IPC_MSG_PREP_PIPE_OPEN:	Pipe open message preparation type
+ * @IPC_MSG_PREP_PIPE_CLOSE:	Pipe close message preparation type
+ * @IPC_MSG_PREP_FEATURE_SET:	Feature set message preparation type
+ * @IPC_MSG_PREP_MAP:		Memory map message preparation type
+ * @IPC_MSG_PREP_UNMAP:		Memory unmap message preparation type
+ */
+enum ipc_msg_prep_type {
+	IPC_MSG_PREP_SLEEP,
+	IPC_MSG_PREP_PIPE_OPEN,
+	IPC_MSG_PREP_PIPE_CLOSE,
+	IPC_MSG_PREP_FEATURE_SET,
+	IPC_MSG_PREP_MAP,
+	IPC_MSG_PREP_UNMAP,
+};
+
+/**
+ * struct ipc_rsp - Response to sent message
+ * @completion:	For waking up requestor
+ * @status:	Completion status
+ */
+struct ipc_rsp {
+	struct completion completion;
+	enum ipc_mem_msg_cs status;
+};
+
+/**
+ * enum ipc_mem_msg - Type-definition of the messages.
+ * @IPC_MEM_MSG_OPEN_PIPE:	AP ->CP: Open a pipe
+ * @IPC_MEM_MSG_CLOSE_PIPE:	AP ->CP: Close a pipe
+ * @IPC_MEM_MSG_ABORT_PIPE:	AP ->CP: wait for completion of the
+ *				running transfer and abort all pending
+ *				IO-transfers for the pipe
+ * @IPC_MEM_MSG_SLEEP:		AP ->CP: host enter or exit sleep
+ * @IPC_MEM_MSG_FEATURE_SET:	AP ->CP: Intel feature configuration
+ */
+enum ipc_mem_msg {
+	IPC_MEM_MSG_OPEN_PIPE = 0x01,
+	IPC_MEM_MSG_CLOSE_PIPE = 0x02,
+	IPC_MEM_MSG_ABORT_PIPE = 0x03,
+	IPC_MEM_MSG_SLEEP = 0x04,
+	IPC_MEM_MSG_FEATURE_SET = 0xF0,
+};
+
+/**
+ * struct ipc_mem_msg_open_pipe - Message structure for open pipe
+ * @tdr_addr:			Tdr address
+ * @tdr_entries:		Tdr entries
+ * @pipe_nr:			Pipe number
+ * @type_of_message:		Message type
+ * @irq_vector:			MSI vector number
+ * @accumulation_backoff:	Time in usec for data accumalation
+ * @completion_status:		Message Completion Status
+ */
+struct ipc_mem_msg_open_pipe {
+	__le64 tdr_addr;
+	__le16 tdr_entries;
+	u8 pipe_nr;
+	u8 type_of_message;
+	__le32 irq_vector;
+	__le32 accumulation_backoff;
+	__le32 completion_status;
+};
+
+/**
+ * struct ipc_mem_msg_close_pipe - Message structure for close pipe
+ * @reserved1:			Reserved
+ * @reserved2:			Reserved
+ * @pipe_nr:			Pipe number
+ * @type_of_message:		Message type
+ * @reserved3:			Reserved
+ * @reserved4:			Reserved
+ * @completion_status:		Message Completion Status
+ */
+struct ipc_mem_msg_close_pipe {
+	__le32 reserved1[2];
+	__le16 reserved2;
+	u8 pipe_nr;
+	u8 type_of_message;
+	__le32  reserved3;
+	__le32 reserved4;
+	__le32 completion_status;
+};
+
+/**
+ * struct ipc_mem_msg_abort_pipe - Message structure for abort pipe
+ * @reserved1:			Reserved
+ * @reserved2:			Reserved
+ * @pipe_nr:			Pipe number
+ * @type_of_message:		Message type
+ * @reserved3:			Reserved
+ * @reserved4:			Reserved
+ * @completion_status:		Message Completion Status
+ */
+struct ipc_mem_msg_abort_pipe {
+	__le32  reserved1[2];
+	__le16 reserved2;
+	u8 pipe_nr;
+	u8 type_of_message;
+	__le32 reserved3;
+	__le32 reserved4;
+	__le32 completion_status;
+};
+
+/**
+ * struct ipc_mem_msg_host_sleep - Message structure for sleep message.
+ * @reserved1:		Reserved
+ * @target:		0=host, 1=device, host or EP devie
+ *			is the message target
+ * @state:		0=enter sleep, 1=exit sleep,
+ *			2=enter sleep no protocol
+ * @reserved2:		Reserved
+ * @type_of_message:	Message type
+ * @reserved3:		Reserved
+ * @reserved4:		Reserved
+ * @completion_status:	Message Completion Status
+ */
+struct ipc_mem_msg_host_sleep {
+	__le32 reserved1[2];
+	u8 target;
+	u8 state;
+	u8 reserved2;
+	u8 type_of_message;
+	__le32 reserved3;
+	__le32 reserved4;
+	__le32 completion_status;
+};
+
+/**
+ * struct ipc_mem_msg_feature_set - Message structure for feature_set message
+ * @reserved1:			Reserved
+ * @reserved2:			Reserved
+ * @reset_enable:		0=out-of-band, 1=in-band-crash notification
+ * @type_of_message:		Message type
+ * @reserved3:			Reserved
+ * @reserved4:			Reserved
+ * @completion_status:		Message Completion Status
+ */
+struct ipc_mem_msg_feature_set {
+	__le32 reserved1[2];
+	__le16 reserved2;
+	u8 reset_enable;
+	u8 type_of_message;
+	__le32 reserved3;
+	__le32 reserved4;
+	__le32 completion_status;
+};
+
+/**
+ * struct ipc_mem_msg_common - Message structure for completion status update.
+ * @reserved1:			Reserved
+ * @reserved2:			Reserved
+ * @type_of_message:		Message type
+ * @reserved3:			Reserved
+ * @reserved4:			Reserved
+ * @completion_status:		Message Completion Status
+ */
+struct ipc_mem_msg_common {
+	__le32 reserved1[2];
+	u8 reserved2[3];
+	u8 type_of_message;
+	__le32 reserved3;
+	__le32 reserved4;
+	__le32 completion_status;
+};
+
+/**
+ * union ipc_mem_msg_entry - Union with all possible messages.
+ * @open_pipe:		Open pipe message struct
+ * @close_pipe:		Close pipe message struct
+ * @abort_pipe:		Abort pipe message struct
+ * @host_sleep:		Host sleep message struct
+ * @feature_set:	Featuer set message struct
+ * @common:		Used to access msg_type and to set the completion status
+ */
+union ipc_mem_msg_entry {
+	struct ipc_mem_msg_open_pipe open_pipe;
+	struct ipc_mem_msg_close_pipe close_pipe;
+	struct ipc_mem_msg_abort_pipe abort_pipe;
+	struct ipc_mem_msg_host_sleep host_sleep;
+	struct ipc_mem_msg_feature_set feature_set;
+	struct ipc_mem_msg_common common;
+};
+
+/* Transfer descriptor definition. */
+struct ipc_protocol_td {
+	union {
+		/*   0 :  63 - 64-bit address of a buffer in host memory. */
+		dma_addr_t address;
+		struct {
+			/*   0 :  31 - 32 bit address */
+			__le32 address;
+			/*  32 :  63 - corresponding descriptor */
+			__le32 desc;
+		} __packed shm;
+	} buffer;
+
+	/*	0 - 2nd byte - Size of the buffer.
+	 *	The host provides the size of the buffer queued.
+	 *	The EP device reads this value and shall update
+	 *	it for downlink transfers to indicate the
+	 *	amount of data written in buffer.
+	 *	3rd byte - This field provides the completion status
+	 *	of the TD. When queuing the TD, the host sets
+	 *	the status to 0. The EP device updates this
+	 *	field when completing the TD.
+	 */
+	__le32 scs;
+
+	/*	0th - nr of following descriptors
+	 *	1 - 3rd byte - reserved
+	 */
+	__le32 next;
+} __packed;
+
+/**
+ * ipc_protocol_msg_prep - Prepare message based upon message type
+ * @ipc_imem:	iosm_protocol instance
+ * @msg_type:	message prepare type
+ * @args:	message arguments
+ *
+ * Return: 0 on success and failure value on error
+ */
+int ipc_protocol_msg_prep(struct iosm_imem *ipc_imem,
+			  enum ipc_msg_prep_type msg_type,
+			  union ipc_msg_prep_args *args);
+
+/**
+ * ipc_protocol_msg_hp_update - Function for head pointer update
+ *				of message ring
+ * @ipc_imem:	iosm_protocol instance
+ */
+void ipc_protocol_msg_hp_update(struct iosm_imem *ipc_imem);
+
+/**
+ * ipc_protocol_msg_process - Function for processing responses
+ *			      to IPC messages
+ * @ipc_imem:	iosm_protocol instance
+ * @irq:	IRQ vector
+ *
+ * Return:	True on success, false if error
+ */
+bool ipc_protocol_msg_process(struct iosm_imem *ipc_imem, int irq);
+
+/**
+ * ipc_protocol_ul_td_send - Function for sending the data to CP
+ * @ipc_protocol:	iosm_protocol instance
+ * @pipe:		Pipe instance
+ * @p_ul_list:		uplink sk_buff list
+ *
+ * Return: true in success, false in case of error
+ */
+bool ipc_protocol_ul_td_send(struct iosm_protocol *ipc_protocol,
+			     struct ipc_pipe *pipe,
+			     struct sk_buff_head *p_ul_list);
+
+/**
+ * ipc_protocol_ul_td_process - Function for processing the sent data
+ * @ipc_protocol:	iosm_protocol instance
+ * @pipe:		Pipe instance
+ *
+ * Return: sk_buff instance
+ */
+struct sk_buff *ipc_protocol_ul_td_process(struct iosm_protocol *ipc_protocol,
+					   struct ipc_pipe *pipe);
+
+/**
+ * ipc_protocol_dl_td_prepare - Function for providing DL TDs to CP
+ * @ipc_protocol:	iosm_protocol instance
+ * @pipe:		Pipe instance
+ *
+ * Return: true in success, false in case of error
+ */
+bool ipc_protocol_dl_td_prepare(struct iosm_protocol *ipc_protocol,
+				struct ipc_pipe *pipe);
+
+/**
+ * ipc_protocol_dl_td_process - Function for processing the DL data
+ * @ipc_protocol:	iosm_protocol instance
+ * @pipe:		Pipe instance
+ *
+ * Return: sk_buff instance
+ */
+struct sk_buff *ipc_protocol_dl_td_process(struct iosm_protocol *ipc_protocol,
+					   struct ipc_pipe *pipe);
+
+/**
+ * ipc_protocol_get_head_tail_index - Function for getting Head and Tail
+ *				      pointer index of given pipe
+ * @ipc_protocol:	iosm_protocol instance
+ * @pipe:		Pipe Instance
+ * @head:		head pointer index of the given pipe
+ * @tail:		tail pointer index of the given pipe
+ */
+void ipc_protocol_get_head_tail_index(struct iosm_protocol *ipc_protocol,
+				      struct ipc_pipe *pipe, u32 *head,
+				      u32 *tail);
+/**
+ * ipc_protocol_get_ipc_status - Function for getting the IPC Status
+ * @ipc_protocol:	iosm_protocol instance
+ *
+ * Return: Returns IPC State
+ */
+enum ipc_mem_device_ipc_state ipc_protocol_get_ipc_status(struct iosm_protocol
+							  *ipc_protocol);
+
+/**
+ * ipc_protocol_pipe_cleanup - Function to cleanup pipe resources
+ * @ipc_protocol:	iosm_protocol instance
+ * @pipe:		Pipe instance
+ */
+void ipc_protocol_pipe_cleanup(struct iosm_protocol *ipc_protocol,
+			       struct ipc_pipe *pipe);
+
+/**
+ * ipc_protocol_get_ap_exec_stage - Function for getting AP Exec Stage
+ * @ipc_protocol:	pointer to struct iosm protocol
+ *
+ * Return: returns BOOT Stages
+ */
+enum ipc_mem_exec_stage
+ipc_protocol_get_ap_exec_stage(struct iosm_protocol *ipc_protocol);
+
+/**
+ * ipc_protocol_pm_dev_get_sleep_notification - Function for getting Dev Sleep
+ *						notification
+ * @ipc_protocol:	iosm_protocol instance
+ *
+ * Return: Returns dev PM State
+ */
+u32 ipc_protocol_pm_dev_get_sleep_notification(struct iosm_protocol
+					       *ipc_protocol);
+#endif
diff --git a/drivers/net/wwan/iosm/iosm_ipc_task_queue.c b/drivers/net/wwan/iosm/iosm_ipc_task_queue.c
new file mode 100644
index 000000000000..852a99166144
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_task_queue.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#include "iosm_ipc_imem.h"
+#include "iosm_ipc_task_queue.h"
+
+/* Actual tasklet function, will be called whenever tasklet is scheduled.
+ * Calls event handler involves callback for each element in the message queue
+ */
+static void ipc_task_queue_handler(unsigned long data)
+{
+	struct ipc_task_queue *ipc_task = (struct ipc_task_queue *)data;
+	unsigned int q_rpos = ipc_task->q_rpos;
+
+	/* Loop over the input queue contents. */
+	while (q_rpos != ipc_task->q_wpos) {
+		/* Get the current first queue element. */
+		struct ipc_task_queue_args *args = &ipc_task->args[q_rpos];
+
+		/* Process the input message. */
+		if (args->func)
+			args->response = args->func(args->ipc_imem, args->arg,
+						    args->msg, args->size);
+
+		/* Signal completion for synchronous calls */
+		if (args->completion)
+			complete(args->completion);
+
+		/* Free message if copy was allocated. */
+		if (args->is_copy)
+			kfree(args->msg);
+
+		/* Set invalid queue element. Technically
+		 * spin_lock_irqsave is not required here as
+		 * the array element has been processed already
+		 * so we can assume that immediately after processing
+		 * ipc_task element, queue will not rotate again to
+		 * ipc_task same element within such short time.
+		 */
+		args->completion = NULL;
+		args->func = NULL;
+		args->msg = NULL;
+		args->size = 0;
+		args->is_copy = false;
+
+		/* calculate the new read ptr and update the volatile read
+		 * ptr
+		 */
+		q_rpos = (q_rpos + 1) % IPC_THREAD_QUEUE_SIZE;
+		ipc_task->q_rpos = q_rpos;
+	}
+}
+
+/* Free memory alloc and trigger completions left in the queue during dealloc */
+static void ipc_task_queue_cleanup(struct ipc_task_queue *ipc_task)
+{
+	unsigned int q_rpos = ipc_task->q_rpos;
+
+	while (q_rpos != ipc_task->q_wpos) {
+		struct ipc_task_queue_args *args = &ipc_task->args[q_rpos];
+
+		if (args->completion)
+			complete(args->completion);
+
+		if (args->is_copy)
+			kfree(args->msg);
+
+		q_rpos = (q_rpos + 1) % IPC_THREAD_QUEUE_SIZE;
+		ipc_task->q_rpos = q_rpos;
+	}
+}
+
+/* Add a message to the queue and trigger the ipc_task. */
+static int
+ipc_task_queue_add_task(struct iosm_imem *ipc_imem,
+			int arg, void *msg,
+			int (*func)(struct iosm_imem *ipc_imem, int arg,
+				    void *msg, size_t size),
+			size_t size, bool is_copy, bool wait)
+{
+	struct tasklet_struct *ipc_tasklet = ipc_imem->ipc_task->ipc_tasklet;
+	struct ipc_task_queue *ipc_task = &ipc_imem->ipc_task->ipc_queue;
+	struct completion completion;
+	unsigned int pos, nextpos;
+	unsigned long flags;
+	int result = -EIO;
+
+	init_completion(&completion);
+
+	/* tasklet send may be called from both interrupt or thread
+	 * context, therefore protect queue operation by spinlock
+	 */
+	spin_lock_irqsave(&ipc_task->q_lock, flags);
+
+	pos = ipc_task->q_wpos;
+	nextpos = (pos + 1) % IPC_THREAD_QUEUE_SIZE;
+
+	/* Get next queue position. */
+	if (nextpos != ipc_task->q_rpos) {
+		/* Get the reference to the queue element and save the passed
+		 * values.
+		 */
+		ipc_task->args[pos].arg = arg;
+		ipc_task->args[pos].msg = msg;
+		ipc_task->args[pos].func = func;
+		ipc_task->args[pos].ipc_imem = ipc_imem;
+		ipc_task->args[pos].size = size;
+		ipc_task->args[pos].is_copy = is_copy;
+		ipc_task->args[pos].completion = wait ? &completion : NULL;
+		ipc_task->args[pos].response = -1;
+
+		/* apply write barrier so that ipc_task->q_rpos elements
+		 * are updated before ipc_task->q_wpos is being updated.
+		 */
+		smp_wmb();
+
+		/* Update the status of the free queue space. */
+		ipc_task->q_wpos = nextpos;
+		result = 0;
+	}
+
+	spin_unlock_irqrestore(&ipc_task->q_lock, flags);
+
+	if (result == 0) {
+		tasklet_schedule(ipc_tasklet);
+
+		if (wait) {
+			wait_for_completion(&completion);
+			result = ipc_task->args[pos].response;
+		}
+	} else {
+		dev_err(ipc_imem->ipc_task->dev, "queue is full");
+	}
+
+	return result;
+}
+
+int ipc_task_queue_send_task(struct iosm_imem *imem,
+			     int (*func)(struct iosm_imem *ipc_imem, int arg,
+					 void *msg, size_t size),
+			     int arg, void *msg, size_t size, bool wait)
+{
+	bool is_copy = false;
+	void *copy = msg;
+	int ret = -ENOMEM;
+
+	if (size > 0) {
+		copy = kmemdup(msg, size, GFP_ATOMIC);
+		if (!copy)
+			goto out;
+
+		is_copy = true;
+	}
+
+	ret = ipc_task_queue_add_task(imem, arg, copy, func,
+				      size, is_copy, wait);
+	if (ret < 0) {
+		dev_err(imem->ipc_task->dev,
+			"add task failed for %ps %d, %p, %zu, %d", func, arg,
+			copy, size, is_copy);
+		if (is_copy)
+			kfree(copy);
+		goto out;
+	}
+
+	ret = 0;
+out:
+	return ret;
+}
+
+int ipc_task_init(struct ipc_task *ipc_task)
+{
+	struct ipc_task_queue *ipc_queue = &ipc_task->ipc_queue;
+
+	ipc_task->ipc_tasklet = kzalloc(sizeof(*ipc_task->ipc_tasklet),
+					GFP_KERNEL);
+
+	if (!ipc_task->ipc_tasklet)
+		return -ENOMEM;
+
+	/* Initialize the spinlock needed to protect the message queue of the
+	 * ipc_task
+	 */
+	spin_lock_init(&ipc_queue->q_lock);
+
+	tasklet_init(ipc_task->ipc_tasklet, ipc_task_queue_handler,
+		     (unsigned long)ipc_queue);
+	return 0;
+}
+
+void ipc_task_deinit(struct ipc_task *ipc_task)
+{
+	tasklet_kill(ipc_task->ipc_tasklet);
+
+	kfree(ipc_task->ipc_tasklet);
+	/* This will free/complete any outstanding messages,
+	 * without calling the actual handler
+	 */
+	ipc_task_queue_cleanup(&ipc_task->ipc_queue);
+}
diff --git a/drivers/net/wwan/iosm/iosm_ipc_task_queue.h b/drivers/net/wwan/iosm/iosm_ipc_task_queue.h
new file mode 100644
index 000000000000..df6e9cd925a9
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_task_queue.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#ifndef IOSM_IPC_TASK_QUEUE_H
+#define IOSM_IPC_TASK_QUEUE_H
+
+/* Number of available element for the input message queue of the IPC
+ * ipc_task
+ */
+#define IPC_THREAD_QUEUE_SIZE 256
+
+/**
+ * struct ipc_task_queue_args - Struct for Task queue elements
+ * @ipc_imem:   Pointer to struct iosm_imem
+ * @msg:        Message argument for tasklet function. (optional, can be NULL)
+ * @completion: OS object used to wait for the tasklet function to finish for
+ *              synchronous calls
+ * @func:       Function to be called in tasklet (tl) context
+ * @arg:        Generic integer argument for tasklet function (optional)
+ * @size:       Message size argument for tasklet function (optional)
+ * @response:   Return code of tasklet function for synchronous calls
+ * @is_copy:    Is true if msg contains a pointer to a copy of the original msg
+ *              for async. calls that needs to be freed once the tasklet returns
+ */
+struct ipc_task_queue_args {
+	struct iosm_imem *ipc_imem;
+	void *msg;
+	struct completion *completion;
+	int (*func)(struct iosm_imem *ipc_imem, int arg, void *msg,
+		    size_t size);
+	int arg;
+	size_t size;
+	int response;
+	u8 is_copy:1;
+};
+
+/**
+ * struct ipc_task_queue - Struct for Task queue
+ * @q_lock:     Protect the message queue of the ipc ipc_task
+ * @args:       Message queue of the IPC ipc_task
+ * @q_rpos:     First queue element to process.
+ * @q_wpos:     First free element of the input queue.
+ */
+struct ipc_task_queue {
+	spinlock_t q_lock; /* for atomic operation on queue */
+	struct ipc_task_queue_args args[IPC_THREAD_QUEUE_SIZE];
+	unsigned int q_rpos;
+	unsigned int q_wpos;
+};
+
+/**
+ * struct ipc_task - Struct for Task
+ * @dev:	 Pointer to device structure
+ * @ipc_tasklet: Tasklet for serialized work offload
+ *		 from interrupts and OS callbacks
+ * @ipc_queue:	 Task for entry into ipc task queue
+ */
+struct ipc_task {
+	struct device *dev;
+	struct tasklet_struct *ipc_tasklet;
+	struct ipc_task_queue ipc_queue;
+};
+
+/**
+ * ipc_task_init - Allocate a tasklet
+ * @ipc_task:	Pointer to ipc_task structure
+ * Returns: 0 on success and failure value on error.
+ */
+int ipc_task_init(struct ipc_task *ipc_task);
+
+/**
+ * ipc_task_deinit - Free a tasklet, invalidating its pointer.
+ * @ipc_task:	Pointer to ipc_task structure
+ */
+void ipc_task_deinit(struct ipc_task *ipc_task);
+
+/**
+ * ipc_task_queue_send_task - Synchronously/Asynchronously call a function in
+ *			      tasklet context.
+ * @imem:		Pointer to iosm_imem struct
+ * @func:		Function to be called in tasklet context
+ * @arg:		Integer argument for func
+ * @msg:		Message pointer argument for func
+ * @size:		Size argument for func
+ * @wait:		if true wait for result
+ *
+ * Returns: Result value returned by func or failure value if func could not
+ *	    be called.
+ */
+int ipc_task_queue_send_task(struct iosm_imem *imem,
+			     int (*func)(struct iosm_imem *ipc_imem, int arg,
+					 void *msg, size_t size),
+			     int arg, void *msg, size_t size, bool wait);
+
+#endif
diff --git a/drivers/net/wwan/iosm/iosm_ipc_uevent.c b/drivers/net/wwan/iosm/iosm_ipc_uevent.c
new file mode 100644
index 000000000000..2229d752926c
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_uevent.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#include <linux/device.h>
+#include <linux/kobject.h>
+#include <linux/slab.h>
+
+#include "iosm_ipc_uevent.h"
+
+/* Update the uevent in work queue context */
+static void ipc_uevent_work(struct work_struct *data)
+{
+	struct ipc_uevent_info *info;
+	char *envp[2] = { NULL, NULL };
+
+	info = container_of(data, struct ipc_uevent_info, work);
+
+	envp[0] = info->uevent;
+
+	if (kobject_uevent_env(&info->dev->kobj, KOBJ_CHANGE, envp))
+		pr_err("uevent %s failed to sent", info->uevent);
+
+	kfree(info);
+}
+
+void ipc_uevent_send(struct device *dev, char *uevent)
+{
+	struct ipc_uevent_info *info = kzalloc(sizeof(*info), GFP_ATOMIC);
+
+	if (!info)
+		return;
+
+	/* Initialize the kernel work queue */
+	INIT_WORK(&info->work, ipc_uevent_work);
+
+	/* Store the device and event information */
+	info->dev = dev;
+	snprintf(info->uevent, MAX_UEVENT_LEN, "%s: %s", dev_name(dev), uevent);
+
+	/* Schedule uevent in process context using work queue */
+	schedule_work(&info->work);
+}
diff --git a/drivers/net/wwan/iosm/iosm_ipc_uevent.h b/drivers/net/wwan/iosm/iosm_ipc_uevent.h
new file mode 100644
index 000000000000..2e45c051b5f4
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_uevent.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#ifndef IOSM_IPC_UEVENT_H
+#define IOSM_IPC_UEVENT_H
+
+/* Baseband event strings */
+#define UEVENT_MDM_NOT_READY "MDM_NOT_READY"
+#define UEVENT_ROM_READY "ROM_READY"
+#define UEVENT_MDM_READY "MDM_READY"
+#define UEVENT_CRASH "CRASH"
+#define UEVENT_CD_READY "CD_READY"
+#define UEVENT_CD_READY_LINK_DOWN "CD_READY_LINK_DOWN"
+#define UEVENT_MDM_TIMEOUT "MDM_TIMEOUT"
+
+/* Maximum length of user events */
+#define MAX_UEVENT_LEN 64
+
+/**
+ * struct ipc_uevent_info - Uevent information structure.
+ * @dev:	Pointer to device structure
+ * @uevent:	Uevent information
+ * @work:	Uevent work struct
+ */
+struct ipc_uevent_info {
+	struct device *dev;
+	char uevent[MAX_UEVENT_LEN];
+	struct work_struct work;
+};
+
+/**
+ * ipc_uevent_send - Send modem event to user space.
+ * @dev:	Generic device pointer
+ * @uevent:	Uevent information
+ *
+ */
+void ipc_uevent_send(struct device *dev, char *uevent);
+
+#endif
diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.c b/drivers/net/wwan/iosm/iosm_ipc_wwan.c
new file mode 100644
index 000000000000..1711b79fc616
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.c
@@ -0,0 +1,351 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/if_arp.h>
+#include <linux/if_link.h>
+#include <linux/rtnetlink.h>
+#include <linux/wwan.h>
+
+#include "iosm_ipc_chnl_cfg.h"
+#include "iosm_ipc_imem_ops.h"
+#include "iosm_ipc_wwan.h"
+
+#define IOSM_IP_TYPE_MASK 0xF0
+#define IOSM_IP_TYPE_IPV4 0x40
+#define IOSM_IP_TYPE_IPV6 0x60
+
+#define IOSM_IF_ID_PAYLOAD 2
+
+/**
+ * struct iosm_netdev_priv - netdev private data
+ * @ipc_wwan:	Pointer to iosm_wwan struct
+ * @netdev:	Pointer to network interface device structure
+ * @if_id:	Interface id for device.
+ * @ch_id:	IPC channel number for which interface device is created.
+ */
+struct iosm_netdev_priv {
+	struct iosm_wwan *ipc_wwan;
+	struct net_device *netdev;
+	int if_id;
+	int ch_id;
+};
+
+/**
+ * struct iosm_wwan - This structure contains information about WWAN root device
+ *		      and interface to the IPC layer.
+ * @ipc_imem:		Pointer to imem data-struct
+ * @sub_netlist:	List of active netdevs
+ * @dev:		Pointer device structure
+ * @if_mutex:		Mutex used for add and remove interface id
+ */
+struct iosm_wwan {
+	struct iosm_imem *ipc_imem;
+	struct iosm_netdev_priv __rcu *sub_netlist[IP_MUX_SESSION_END + 1];
+	struct device *dev;
+	struct mutex if_mutex; /* Mutex used for add and remove interface id */
+};
+
+/* Bring-up the wwan net link */
+static int ipc_wwan_link_open(struct net_device *netdev)
+{
+	struct iosm_netdev_priv *priv = netdev_priv(netdev);
+	struct iosm_wwan *ipc_wwan = priv->ipc_wwan;
+	int if_id = priv->if_id;
+	int ret;
+
+	if (if_id < IP_MUX_SESSION_START ||
+	    if_id >= ARRAY_SIZE(ipc_wwan->sub_netlist))
+		return -EINVAL;
+
+	mutex_lock(&ipc_wwan->if_mutex);
+
+	/* get channel id */
+	priv->ch_id = ipc_imem_sys_wwan_open(ipc_wwan->ipc_imem, if_id);
+
+	if (priv->ch_id < 0) {
+		dev_err(ipc_wwan->dev,
+			"cannot connect wwan0 & id %d to the IPC mem layer",
+			if_id);
+		ret = -ENODEV;
+		goto out;
+	}
+
+	/* enable tx path, DL data may follow */
+	netif_start_queue(netdev);
+
+	dev_dbg(ipc_wwan->dev, "Channel id %d allocated to if_id %d",
+		priv->ch_id, priv->if_id);
+
+	ret = 0;
+out:
+	mutex_unlock(&ipc_wwan->if_mutex);
+	return ret;
+}
+
+/* Bring-down the wwan net link */
+static int ipc_wwan_link_stop(struct net_device *netdev)
+{
+	struct iosm_netdev_priv *priv = netdev_priv(netdev);
+
+	netif_stop_queue(netdev);
+
+	mutex_lock(&priv->ipc_wwan->if_mutex);
+	ipc_imem_sys_wwan_close(priv->ipc_wwan->ipc_imem, priv->if_id,
+				priv->ch_id);
+	priv->ch_id = -1;
+	mutex_unlock(&priv->ipc_wwan->if_mutex);
+
+	return 0;
+}
+
+/* Transmit a packet */
+static int ipc_wwan_link_transmit(struct sk_buff *skb,
+				  struct net_device *netdev)
+{
+	struct iosm_netdev_priv *priv = netdev_priv(netdev);
+	struct iosm_wwan *ipc_wwan = priv->ipc_wwan;
+	int if_id = priv->if_id;
+	int ret;
+
+	/* Interface IDs from 1 to 8 are for IP data
+	 * & from 257 to 261 are for non-IP data
+	 */
+	if (if_id < IP_MUX_SESSION_START ||
+	    if_id >= ARRAY_SIZE(ipc_wwan->sub_netlist))
+		return -EINVAL;
+
+	/* Send the SKB to device for transmission */
+	ret = ipc_imem_sys_wwan_transmit(ipc_wwan->ipc_imem,
+					 if_id, priv->ch_id, skb);
+
+	/* Return code of zero is success */
+	if (ret == 0) {
+		ret = NETDEV_TX_OK;
+	} else if (ret == -EBUSY) {
+		ret = NETDEV_TX_BUSY;
+		dev_err(ipc_wwan->dev, "unable to push packets");
+	} else {
+		goto exit;
+	}
+
+	return ret;
+
+exit:
+	/* Log any skb drop */
+	if (if_id)
+		dev_dbg(ipc_wwan->dev, "skb dropped. IF_ID: %d, ret: %d", if_id,
+			ret);
+
+	dev_kfree_skb_any(skb);
+	return ret;
+}
+
+/* Ops structure for wwan net link */
+static const struct net_device_ops ipc_inm_ops = {
+	.ndo_open = ipc_wwan_link_open,
+	.ndo_stop = ipc_wwan_link_stop,
+	.ndo_start_xmit = ipc_wwan_link_transmit,
+};
+
+/* Setup function for creating new net link */
+static void ipc_wwan_setup(struct net_device *iosm_dev)
+{
+	iosm_dev->header_ops = NULL;
+	iosm_dev->hard_header_len = 0;
+	iosm_dev->priv_flags |= IFF_NO_QUEUE;
+
+	iosm_dev->type = ARPHRD_NONE;
+	iosm_dev->min_mtu = ETH_MIN_MTU;
+	iosm_dev->max_mtu = ETH_MAX_MTU;
+
+	iosm_dev->flags = IFF_POINTOPOINT | IFF_NOARP;
+
+	iosm_dev->netdev_ops = &ipc_inm_ops;
+}
+
+/* Create new wwan net link */
+static int ipc_wwan_newlink(void *ctxt, struct net_device *dev,
+			    u32 if_id, struct netlink_ext_ack *extack)
+{
+	struct iosm_wwan *ipc_wwan = ctxt;
+	struct iosm_netdev_priv *priv;
+	int err;
+
+	if (if_id < IP_MUX_SESSION_START ||
+	    if_id >= ARRAY_SIZE(ipc_wwan->sub_netlist))
+		return -EINVAL;
+
+	priv = netdev_priv(dev);
+	priv->if_id = if_id;
+	priv->netdev = dev;
+	priv->ipc_wwan = ipc_wwan;
+
+	mutex_lock(&ipc_wwan->if_mutex);
+	if (rcu_access_pointer(ipc_wwan->sub_netlist[if_id])) {
+		err = -EBUSY;
+		goto out_unlock;
+	}
+
+	err = register_netdevice(dev);
+	if (err)
+		goto out_unlock;
+
+	rcu_assign_pointer(ipc_wwan->sub_netlist[if_id], priv);
+	mutex_unlock(&ipc_wwan->if_mutex);
+
+	netif_device_attach(dev);
+
+	return 0;
+
+out_unlock:
+	mutex_unlock(&ipc_wwan->if_mutex);
+	return err;
+}
+
+static void ipc_wwan_dellink(void *ctxt, struct net_device *dev,
+			     struct list_head *head)
+{
+	struct iosm_wwan *ipc_wwan = ctxt;
+	struct iosm_netdev_priv *priv = netdev_priv(dev);
+	int if_id = priv->if_id;
+
+	if (WARN_ON(if_id < IP_MUX_SESSION_START ||
+		    if_id >= ARRAY_SIZE(ipc_wwan->sub_netlist)))
+		return;
+
+	mutex_lock(&ipc_wwan->if_mutex);
+
+	if (WARN_ON(rcu_access_pointer(ipc_wwan->sub_netlist[if_id]) != priv))
+		goto unlock;
+
+	RCU_INIT_POINTER(ipc_wwan->sub_netlist[if_id], NULL);
+	/* unregistering includes synchronize_net() */
+	unregister_netdevice(dev);
+
+unlock:
+	mutex_unlock(&ipc_wwan->if_mutex);
+}
+
+static const struct wwan_ops iosm_wwan_ops = {
+	.priv_size = sizeof(struct iosm_netdev_priv),
+	.setup = ipc_wwan_setup,
+	.newlink = ipc_wwan_newlink,
+	.dellink = ipc_wwan_dellink,
+};
+
+int ipc_wwan_receive(struct iosm_wwan *ipc_wwan, struct sk_buff *skb_arg,
+		     bool dss, int if_id)
+{
+	struct sk_buff *skb = skb_arg;
+	struct net_device_stats *stats;
+	struct iosm_netdev_priv *priv;
+	int ret;
+
+	if ((skb->data[0] & IOSM_IP_TYPE_MASK) == IOSM_IP_TYPE_IPV4)
+		skb->protocol = htons(ETH_P_IP);
+	else if ((skb->data[0] & IOSM_IP_TYPE_MASK) ==
+		 IOSM_IP_TYPE_IPV6)
+		skb->protocol = htons(ETH_P_IPV6);
+
+	skb->pkt_type = PACKET_HOST;
+
+	if (if_id < (IP_MUX_SESSION_START - 1) ||
+	    if_id > (IP_MUX_SESSION_END - 1)) {
+		ret = -EINVAL;
+		goto free;
+	}
+
+	rcu_read_lock();
+	priv = rcu_dereference(ipc_wwan->sub_netlist[if_id]);
+	if (!priv) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+	skb->dev = priv->netdev;
+	stats = &priv->netdev->stats;
+	stats->rx_packets++;
+	stats->rx_bytes += skb->len;
+
+	ret = netif_rx(skb);
+	skb = NULL;
+unlock:
+	rcu_read_unlock();
+free:
+	dev_kfree_skb(skb);
+	return ret;
+}
+
+void ipc_wwan_tx_flowctrl(struct iosm_wwan *ipc_wwan, int if_id, bool on)
+{
+	struct net_device *netdev;
+	struct iosm_netdev_priv *priv;
+	bool is_tx_blk;
+
+	rcu_read_lock();
+	priv = rcu_dereference(ipc_wwan->sub_netlist[if_id]);
+	if (!priv) {
+		rcu_read_unlock();
+		return;
+	}
+
+	netdev = priv->netdev;
+
+	is_tx_blk = netif_queue_stopped(netdev);
+
+	if (on)
+		dev_dbg(ipc_wwan->dev, "session id[%d]: flowctrl enable",
+			if_id);
+
+	if (on && !is_tx_blk)
+		netif_stop_queue(netdev);
+	else if (!on && is_tx_blk)
+		netif_wake_queue(netdev);
+	rcu_read_unlock();
+}
+
+struct iosm_wwan *ipc_wwan_init(struct iosm_imem *ipc_imem, struct device *dev)
+{
+	struct iosm_wwan *ipc_wwan;
+
+	ipc_wwan = kzalloc(sizeof(*ipc_wwan), GFP_KERNEL);
+	if (!ipc_wwan)
+		return NULL;
+
+	ipc_wwan->dev = dev;
+	ipc_wwan->ipc_imem = ipc_imem;
+
+	if (wwan_register_ops(ipc_wwan->dev, &iosm_wwan_ops, ipc_wwan)) {
+		kfree(ipc_wwan);
+		return NULL;
+	}
+
+	mutex_init(&ipc_wwan->if_mutex);
+
+	return ipc_wwan;
+}
+
+void ipc_wwan_deinit(struct iosm_wwan *ipc_wwan)
+{
+	int if_id;
+
+	wwan_unregister_ops(ipc_wwan->dev);
+
+	for (if_id = 0; if_id < ARRAY_SIZE(ipc_wwan->sub_netlist); if_id++) {
+		struct iosm_netdev_priv *priv;
+
+		priv = rcu_access_pointer(ipc_wwan->sub_netlist[if_id]);
+		if (!priv)
+			continue;
+
+		rtnl_lock();
+		ipc_wwan_dellink(ipc_wwan, priv->netdev, NULL);
+		rtnl_unlock();
+	}
+
+	mutex_destroy(&ipc_wwan->if_mutex);
+
+	kfree(ipc_wwan);
+}
diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.h b/drivers/net/wwan/iosm/iosm_ipc_wwan.h
new file mode 100644
index 000000000000..4925f22dff0a
--- /dev/null
+++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (C) 2020-21 Intel Corporation.
+ */
+
+#ifndef IOSM_IPC_WWAN_H
+#define IOSM_IPC_WWAN_H
+
+/**
+ * ipc_wwan_init - Allocate, Init and register WWAN device
+ * @ipc_imem:		Pointer to imem data-struct
+ * @dev:		Pointer to device structure
+ *
+ * Returns: Pointer to instance on success else NULL
+ */
+struct iosm_wwan *ipc_wwan_init(struct iosm_imem *ipc_imem, struct device *dev);
+
+/**
+ * ipc_wwan_deinit - Unregister and free WWAN device, clear pointer
+ * @ipc_wwan:	Pointer to wwan instance data
+ */
+void ipc_wwan_deinit(struct iosm_wwan *ipc_wwan);
+
+/**
+ * ipc_wwan_receive - Receive a downlink packet from CP.
+ * @ipc_wwan:	Pointer to wwan instance
+ * @skb_arg:	Pointer to struct sk_buff
+ * @dss:	Set to true if interafce id is from 257 to 261,
+ *		else false
+ * @if_id:	Interface ID
+ *
+ * Return: 0 on success and failure value on error
+ */
+int ipc_wwan_receive(struct iosm_wwan *ipc_wwan, struct sk_buff *skb_arg,
+		     bool dss, int if_id);
+
+/**
+ * ipc_wwan_tx_flowctrl - Enable/Disable TX flow control
+ * @ipc_wwan:	Pointer to wwan instance
+ * @id:		Ipc mux channel session id
+ * @on:		if true then flow ctrl would be enabled else disable
+ *
+ */
+void ipc_wwan_tx_flowctrl(struct iosm_wwan *ipc_wwan, int id, bool on);
+
+/**
+ * ipc_wwan_is_tx_stopped - Checks if Tx stopped for a Interface id.
+ * @ipc_wwan:	Pointer to wwan instance
+ * @id:		Ipc mux channel session id
+ *
+ * Return: true if stopped, false otherwise
+ */
+bool ipc_wwan_is_tx_stopped(struct iosm_wwan *ipc_wwan, int id);
+
+#endif
diff --git a/drivers/net/wwan/rpmsg_wwan_ctrl.c b/drivers/net/wwan/rpmsg_wwan_ctrl.c
new file mode 100644
index 000000000000..31c24420ab2e
--- /dev/null
+++ b/drivers/net/wwan/rpmsg_wwan_ctrl.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2021, Stephan Gerhold <stephan@gerhold.net> */
+#include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/rpmsg.h>
+#include <linux/wwan.h>
+
+struct rpmsg_wwan_dev {
+	/* Lower level is a rpmsg dev, upper level is a wwan port */
+	struct rpmsg_device *rpdev;
+	struct wwan_port *wwan_port;
+	struct rpmsg_endpoint *ept;
+};
+
+static int rpmsg_wwan_ctrl_callback(struct rpmsg_device *rpdev,
+				    void *buf, int len, void *priv, u32 src)
+{
+	struct rpmsg_wwan_dev *rpwwan = priv;
+	struct sk_buff *skb;
+
+	skb = alloc_skb(len, GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_put_data(skb, buf, len);
+	wwan_port_rx(rpwwan->wwan_port, skb);
+	return 0;
+}
+
+static int rpmsg_wwan_ctrl_start(struct wwan_port *port)
+{
+	struct rpmsg_wwan_dev *rpwwan = wwan_port_get_drvdata(port);
+	struct rpmsg_channel_info chinfo = {
+		.src = rpwwan->rpdev->src,
+		.dst = RPMSG_ADDR_ANY,
+	};
+
+	strncpy(chinfo.name, rpwwan->rpdev->id.name, RPMSG_NAME_SIZE);
+	rpwwan->ept = rpmsg_create_ept(rpwwan->rpdev, rpmsg_wwan_ctrl_callback,
+				       rpwwan, chinfo);
+	if (!rpwwan->ept)
+		return -EREMOTEIO;
+
+	return 0;
+}
+
+static void rpmsg_wwan_ctrl_stop(struct wwan_port *port)
+{
+	struct rpmsg_wwan_dev *rpwwan = wwan_port_get_drvdata(port);
+
+	rpmsg_destroy_ept(rpwwan->ept);
+	rpwwan->ept = NULL;
+}
+
+static int rpmsg_wwan_ctrl_tx(struct wwan_port *port, struct sk_buff *skb)
+{
+	struct rpmsg_wwan_dev *rpwwan = wwan_port_get_drvdata(port);
+	int ret;
+
+	ret = rpmsg_trysend(rpwwan->ept, skb->data, skb->len);
+	if (ret)
+		return ret;
+
+	consume_skb(skb);
+	return 0;
+}
+
+static int rpmsg_wwan_ctrl_tx_blocking(struct wwan_port *port, struct sk_buff *skb)
+{
+	struct rpmsg_wwan_dev *rpwwan = wwan_port_get_drvdata(port);
+	int ret;
+
+	ret = rpmsg_send(rpwwan->ept, skb->data, skb->len);
+	if (ret)
+		return ret;
+
+	consume_skb(skb);
+	return 0;
+}
+
+static __poll_t rpmsg_wwan_ctrl_tx_poll(struct wwan_port *port,
+					struct file *filp, poll_table *wait)
+{
+	struct rpmsg_wwan_dev *rpwwan = wwan_port_get_drvdata(port);
+
+	return rpmsg_poll(rpwwan->ept, filp, wait);
+}
+
+static const struct wwan_port_ops rpmsg_wwan_pops = {
+	.start = rpmsg_wwan_ctrl_start,
+	.stop = rpmsg_wwan_ctrl_stop,
+	.tx = rpmsg_wwan_ctrl_tx,
+	.tx_blocking = rpmsg_wwan_ctrl_tx_blocking,
+	.tx_poll = rpmsg_wwan_ctrl_tx_poll,
+};
+
+static struct device *rpmsg_wwan_find_parent(struct device *dev)
+{
+	/* Select first platform device as parent for the WWAN ports.
+	 * On Qualcomm platforms this is usually the platform device that
+	 * represents the modem remote processor. This might need to be
+	 * adjusted when adding device IDs for other platforms.
+	 */
+	for (dev = dev->parent; dev; dev = dev->parent) {
+		if (dev_is_platform(dev))
+			return dev;
+	}
+	return NULL;
+}
+
+static int rpmsg_wwan_ctrl_probe(struct rpmsg_device *rpdev)
+{
+	struct rpmsg_wwan_dev *rpwwan;
+	struct wwan_port *port;
+	struct device *parent;
+
+	parent = rpmsg_wwan_find_parent(&rpdev->dev);
+	if (!parent)
+		return -ENODEV;
+
+	rpwwan = devm_kzalloc(&rpdev->dev, sizeof(*rpwwan), GFP_KERNEL);
+	if (!rpwwan)
+		return -ENOMEM;
+
+	rpwwan->rpdev = rpdev;
+	dev_set_drvdata(&rpdev->dev, rpwwan);
+
+	/* Register as a wwan port, id.driver_data contains wwan port type */
+	port = wwan_create_port(parent, rpdev->id.driver_data,
+				&rpmsg_wwan_pops, rpwwan);
+	if (IS_ERR(port))
+		return PTR_ERR(port);
+
+	rpwwan->wwan_port = port;
+
+	return 0;
+};
+
+static void rpmsg_wwan_ctrl_remove(struct rpmsg_device *rpdev)
+{
+	struct rpmsg_wwan_dev *rpwwan = dev_get_drvdata(&rpdev->dev);
+
+	wwan_remove_port(rpwwan->wwan_port);
+}
+
+static const struct rpmsg_device_id rpmsg_wwan_ctrl_id_table[] = {
+	/* RPMSG channels for Qualcomm SoCs with integrated modem */
+	{ .name = "DATA5_CNTL", .driver_data = WWAN_PORT_QMI },
+	{ .name = "DATA4", .driver_data = WWAN_PORT_AT },
+	{},
+};
+MODULE_DEVICE_TABLE(rpmsg, rpmsg_wwan_ctrl_id_table);
+
+static struct rpmsg_driver rpmsg_wwan_ctrl_driver = {
+	.drv.name = "rpmsg_wwan_ctrl",
+	.id_table = rpmsg_wwan_ctrl_id_table,
+	.probe = rpmsg_wwan_ctrl_probe,
+	.remove = rpmsg_wwan_ctrl_remove,
+};
+module_rpmsg_driver(rpmsg_wwan_ctrl_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("RPMSG WWAN CTRL Driver");
+MODULE_AUTHOR("Stephan Gerhold <stephan@gerhold.net>");
diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c
index cff04e532c1e..165afec1dbd1 100644
--- a/drivers/net/wwan/wwan_core.c
+++ b/drivers/net/wwan/wwan_core.c
@@ -12,9 +12,13 @@
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/types.h>
+#include <linux/termios.h>
 #include <linux/wwan.h>
+#include <net/rtnetlink.h>
+#include <uapi/linux/wwan.h>
 
-#define WWAN_MAX_MINORS 256 /* 256 minors allowed with register_chrdev() */
+/* Maximum number of minors in use */
+#define WWAN_MAX_MINORS		(1 << MINORBITS)
 
 static DEFINE_MUTEX(wwan_register_lock); /* WWAN device create|remove lock */
 static DEFINE_IDA(minors); /* minors for WWAN port chardevs */
@@ -34,11 +38,15 @@ static int wwan_major;
  * @id: WWAN device unique ID.
  * @dev: Underlying device.
  * @port_id: Current available port ID to pick.
+ * @ops: wwan device ops
+ * @ops_ctxt: context to pass to ops
  */
 struct wwan_device {
 	unsigned int id;
 	struct device dev;
 	atomic_t port_id;
+	const struct wwan_ops *ops;
+	void *ops_ctxt;
 };
 
 /**
@@ -51,6 +59,8 @@ struct wwan_device {
  * @dev: Underlying device
  * @rxq: Buffer inbound queue
  * @waitqueue: The waitqueue for port fops (read/write/poll)
+ * @data_lock: Port specific data access serialization
+ * @at_data: AT port specific data
  */
 struct wwan_port {
 	enum wwan_port_type type;
@@ -61,8 +71,29 @@ struct wwan_port {
 	struct device dev;
 	struct sk_buff_head rxq;
 	wait_queue_head_t waitqueue;
+	struct mutex data_lock;	/* Port specific data access serialization */
+	union {
+		struct {
+			struct ktermios termios;
+			int mdmbits;
+		} at_data;
+	};
 };
 
+static ssize_t index_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct wwan_device *wwan = to_wwan_dev(dev);
+
+	return sprintf(buf, "%d\n", wwan->id);
+}
+static DEVICE_ATTR_RO(index);
+
+static struct attribute *wwan_dev_attrs[] = {
+	&dev_attr_index.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(wwan_dev);
+
 static void wwan_dev_destroy(struct device *dev)
 {
 	struct wwan_device *wwandev = to_wwan_dev(dev);
@@ -74,11 +105,13 @@ static void wwan_dev_destroy(struct device *dev)
 static const struct device_type wwan_dev_type = {
 	.name    = "wwan_dev",
 	.release = wwan_dev_destroy,
+	.groups = wwan_dev_groups,
 };
 
 static int wwan_dev_parent_match(struct device *dev, const void *parent)
 {
-	return (dev->type == &wwan_dev_type && dev->parent == parent);
+	return (dev->type == &wwan_dev_type &&
+		(dev->parent == parent || dev == parent));
 }
 
 static struct wwan_device *wwan_dev_get_by_parent(struct device *parent)
@@ -92,6 +125,23 @@ static struct wwan_device *wwan_dev_get_by_parent(struct device *parent)
 	return to_wwan_dev(dev);
 }
 
+static int wwan_dev_name_match(struct device *dev, const void *name)
+{
+	return dev->type == &wwan_dev_type &&
+	       strcmp(dev_name(dev), name) == 0;
+}
+
+static struct wwan_device *wwan_dev_get_by_name(const char *name)
+{
+	struct device *dev;
+
+	dev = class_find_device(wwan_class, NULL, name, wwan_dev_name_match);
+	if (!dev)
+		return ERR_PTR(-ENODEV);
+
+	return to_wwan_dev(dev);
+}
+
 /* This function allocates and registers a new WWAN device OR if a WWAN device
  * already exist for the given parent, it gets a reference and return it.
  * This function is not exported (for now), it is called indirectly via
@@ -156,9 +206,14 @@ static void wwan_remove_dev(struct wwan_device *wwandev)
 	/* WWAN device is created and registered (get+add) along with its first
 	 * child port, and subsequent port registrations only grab a reference
 	 * (get). The WWAN device must then be unregistered (del+put) along with
-	 * its latest port, and reference simply dropped (put) otherwise.
+	 * its last port, and reference simply dropped (put) otherwise. In the
+	 * same fashion, we must not unregister it when the ops are still there.
 	 */
-	ret = device_for_each_child(&wwandev->dev, NULL, is_wwan_child);
+	if (wwandev->ops)
+		ret = 1;
+	else
+		ret = device_for_each_child(&wwandev->dev, NULL, is_wwan_child);
+
 	if (!ret)
 		device_unregister(&wwandev->dev);
 	else
@@ -169,12 +224,53 @@ static void wwan_remove_dev(struct wwan_device *wwandev)
 
 /* ------- WWAN port management ------- */
 
+static const struct {
+	const char * const name;	/* Port type name */
+	const char * const devsuf;	/* Port devce name suffix */
+} wwan_port_types[WWAN_PORT_MAX + 1] = {
+	[WWAN_PORT_AT] = {
+		.name = "AT",
+		.devsuf = "at",
+	},
+	[WWAN_PORT_MBIM] = {
+		.name = "MBIM",
+		.devsuf = "mbim",
+	},
+	[WWAN_PORT_QMI] = {
+		.name = "QMI",
+		.devsuf = "qmi",
+	},
+	[WWAN_PORT_QCDM] = {
+		.name = "QCDM",
+		.devsuf = "qcdm",
+	},
+	[WWAN_PORT_FIREHOSE] = {
+		.name = "FIREHOSE",
+		.devsuf = "firehose",
+	},
+};
+
+static ssize_t type_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct wwan_port *port = to_wwan_port(dev);
+
+	return sprintf(buf, "%s\n", wwan_port_types[port->type].name);
+}
+static DEVICE_ATTR_RO(type);
+
+static struct attribute *wwan_port_attrs[] = {
+	&dev_attr_type.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(wwan_port);
+
 static void wwan_port_destroy(struct device *dev)
 {
 	struct wwan_port *port = to_wwan_port(dev);
 
 	ida_free(&minors, MINOR(port->dev.devt));
-	skb_queue_purge(&port->rxq);
+	mutex_destroy(&port->data_lock);
 	mutex_destroy(&port->ops_lock);
 	kfree(port);
 }
@@ -182,6 +278,7 @@ static void wwan_port_destroy(struct device *dev)
 static const struct device_type wwan_port_dev_type = {
 	.name = "wwan_port",
 	.release = wwan_port_destroy,
+	.groups = wwan_port_groups,
 };
 
 static int wwan_port_minor_match(struct device *dev, const void *minor)
@@ -201,14 +298,55 @@ static struct wwan_port *wwan_port_get_by_minor(unsigned int minor)
 	return to_wwan_port(dev);
 }
 
-/* Keep aligned with wwan_port_type enum */
-static const char * const wwan_port_type_str[] = {
-	"AT",
-	"MBIM",
-	"QMI",
-	"QCDM",
-	"FIREHOSE"
-};
+/* Allocate and set unique name based on passed format
+ *
+ * Name allocation approach is highly inspired by the __dev_alloc_name()
+ * function.
+ *
+ * To avoid names collision, the caller must prevent the new port device
+ * registration as well as concurrent invocation of this function.
+ */
+static int __wwan_port_dev_assign_name(struct wwan_port *port, const char *fmt)
+{
+	struct wwan_device *wwandev = to_wwan_dev(port->dev.parent);
+	const unsigned int max_ports = PAGE_SIZE * 8;
+	struct class_dev_iter iter;
+	unsigned long *idmap;
+	struct device *dev;
+	char buf[0x20];
+	int id;
+
+	idmap = (unsigned long *)get_zeroed_page(GFP_KERNEL);
+	if (!idmap)
+		return -ENOMEM;
+
+	/* Collect ids of same name format ports */
+	class_dev_iter_init(&iter, wwan_class, NULL, &wwan_port_dev_type);
+	while ((dev = class_dev_iter_next(&iter))) {
+		if (dev->parent != &wwandev->dev)
+			continue;
+		if (sscanf(dev_name(dev), fmt, &id) != 1)
+			continue;
+		if (id < 0 || id >= max_ports)
+			continue;
+		set_bit(id, idmap);
+	}
+	class_dev_iter_exit(&iter);
+
+	/* Allocate unique id */
+	id = find_first_zero_bit(idmap, max_ports);
+	free_page((unsigned long)idmap);
+
+	snprintf(buf, sizeof(buf), fmt, id);	/* Name generation */
+
+	dev = device_find_child_by_name(&wwandev->dev, buf);
+	if (dev) {
+		put_device(dev);
+		return -ENFILE;
+	}
+
+	return dev_set_name(&port->dev, buf);
+}
 
 struct wwan_port *wwan_create_port(struct device *parent,
 				   enum wwan_port_type type,
@@ -218,8 +356,9 @@ struct wwan_port *wwan_create_port(struct device *parent,
 	struct wwan_device *wwandev;
 	struct wwan_port *port;
 	int minor, err = -ENOMEM;
+	char namefmt[0x20];
 
-	if (type >= WWAN_PORT_MAX || !ops)
+	if (type > WWAN_PORT_MAX || !ops)
 		return ERR_PTR(-EINVAL);
 
 	/* A port is always a child of a WWAN device, retrieve (allocate or
@@ -245,6 +384,7 @@ struct wwan_port *wwan_create_port(struct device *parent,
 	mutex_init(&port->ops_lock);
 	skb_queue_head_init(&port->rxq);
 	init_waitqueue_head(&port->waitqueue);
+	mutex_init(&port->data_lock);
 
 	port->dev.parent = &wwandev->dev;
 	port->dev.class = wwan_class;
@@ -252,12 +392,18 @@ struct wwan_port *wwan_create_port(struct device *parent,
 	port->dev.devt = MKDEV(wwan_major, minor);
 	dev_set_drvdata(&port->dev, drvdata);
 
-	/* create unique name based on wwan device id, port index and type */
-	dev_set_name(&port->dev, "wwan%up%u%s", wwandev->id,
-		     atomic_inc_return(&wwandev->port_id),
-		     wwan_port_type_str[port->type]);
+	/* allocate unique name based on wwan device id, port type and number */
+	snprintf(namefmt, sizeof(namefmt), "wwan%u%s%%d", wwandev->id,
+		 wwan_port_types[port->type].devsuf);
 
+	/* Serialize ports registration */
+	mutex_lock(&wwan_register_lock);
+
+	__wwan_port_dev_assign_name(port, namefmt);
 	err = device_register(&port->dev);
+
+	mutex_unlock(&wwan_register_lock);
+
 	if (err)
 		goto error_put_device;
 
@@ -346,12 +492,16 @@ static void wwan_port_op_stop(struct wwan_port *port)
 {
 	mutex_lock(&port->ops_lock);
 	port->start_count--;
-	if (port->ops && !port->start_count)
-		port->ops->stop(port);
+	if (!port->start_count) {
+		if (port->ops)
+			port->ops->stop(port);
+		skb_queue_purge(&port->rxq);
+	}
 	mutex_unlock(&port->ops_lock);
 }
 
-static int wwan_port_op_tx(struct wwan_port *port, struct sk_buff *skb)
+static int wwan_port_op_tx(struct wwan_port *port, struct sk_buff *skb,
+			   bool nonblock)
 {
 	int ret;
 
@@ -361,7 +511,10 @@ static int wwan_port_op_tx(struct wwan_port *port, struct sk_buff *skb)
 		goto out_unlock;
 	}
 
-	ret = port->ops->tx(port, skb);
+	if (nonblock || !port->ops->tx_blocking)
+		ret = port->ops->tx(port, skb);
+	else
+		ret = port->ops->tx_blocking(port, skb);
 
 out_unlock:
 	mutex_unlock(&port->ops_lock);
@@ -488,7 +641,7 @@ static ssize_t wwan_port_fops_write(struct file *filp, const char __user *buf,
 		return -EFAULT;
 	}
 
-	ret = wwan_port_op_tx(port, skb);
+	ret = wwan_port_op_tx(port, skb, !!(filp->f_flags & O_NONBLOCK));
 	if (ret) {
 		kfree_skb(skb);
 		return ret;
@@ -504,16 +657,124 @@ static __poll_t wwan_port_fops_poll(struct file *filp, poll_table *wait)
 
 	poll_wait(filp, &port->waitqueue, wait);
 
-	if (!is_write_blocked(port))
+	mutex_lock(&port->ops_lock);
+	if (port->ops && port->ops->tx_poll)
+		mask |= port->ops->tx_poll(port, filp, wait);
+	else if (!is_write_blocked(port))
 		mask |= EPOLLOUT | EPOLLWRNORM;
 	if (!is_read_blocked(port))
 		mask |= EPOLLIN | EPOLLRDNORM;
 	if (!port->ops)
 		mask |= EPOLLHUP | EPOLLERR;
+	mutex_unlock(&port->ops_lock);
 
 	return mask;
 }
 
+/* Implements minimalistic stub terminal IOCTLs support */
+static long wwan_port_fops_at_ioctl(struct wwan_port *port, unsigned int cmd,
+				    unsigned long arg)
+{
+	int ret = 0;
+
+	mutex_lock(&port->data_lock);
+
+	switch (cmd) {
+	case TCFLSH:
+		break;
+
+	case TCGETS:
+		if (copy_to_user((void __user *)arg, &port->at_data.termios,
+				 sizeof(struct termios)))
+			ret = -EFAULT;
+		break;
+
+	case TCSETS:
+	case TCSETSW:
+	case TCSETSF:
+		if (copy_from_user(&port->at_data.termios, (void __user *)arg,
+				   sizeof(struct termios)))
+			ret = -EFAULT;
+		break;
+
+#ifdef TCGETS2
+	case TCGETS2:
+		if (copy_to_user((void __user *)arg, &port->at_data.termios,
+				 sizeof(struct termios2)))
+			ret = -EFAULT;
+		break;
+
+	case TCSETS2:
+	case TCSETSW2:
+	case TCSETSF2:
+		if (copy_from_user(&port->at_data.termios, (void __user *)arg,
+				   sizeof(struct termios2)))
+			ret = -EFAULT;
+		break;
+#endif
+
+	case TIOCMGET:
+		ret = put_user(port->at_data.mdmbits, (int __user *)arg);
+		break;
+
+	case TIOCMSET:
+	case TIOCMBIC:
+	case TIOCMBIS: {
+		int mdmbits;
+
+		if (copy_from_user(&mdmbits, (int __user *)arg, sizeof(int))) {
+			ret = -EFAULT;
+			break;
+		}
+		if (cmd == TIOCMBIC)
+			port->at_data.mdmbits &= ~mdmbits;
+		else if (cmd == TIOCMBIS)
+			port->at_data.mdmbits |= mdmbits;
+		else
+			port->at_data.mdmbits = mdmbits;
+		break;
+	}
+
+	default:
+		ret = -ENOIOCTLCMD;
+	}
+
+	mutex_unlock(&port->data_lock);
+
+	return ret;
+}
+
+static long wwan_port_fops_ioctl(struct file *filp, unsigned int cmd,
+				 unsigned long arg)
+{
+	struct wwan_port *port = filp->private_data;
+	int res;
+
+	if (port->type == WWAN_PORT_AT) {	/* AT port specific IOCTLs */
+		res = wwan_port_fops_at_ioctl(port, cmd, arg);
+		if (res != -ENOIOCTLCMD)
+			return res;
+	}
+
+	switch (cmd) {
+	case TIOCINQ: {	/* aka SIOCINQ aka FIONREAD */
+		unsigned long flags;
+		struct sk_buff *skb;
+		int amount = 0;
+
+		spin_lock_irqsave(&port->rxq.lock, flags);
+		skb_queue_walk(&port->rxq, skb)
+			amount += skb->len;
+		spin_unlock_irqrestore(&port->rxq.lock, flags);
+
+		return put_user(amount, (int __user *)arg);
+	}
+
+	default:
+		return -ENOIOCTLCMD;
+	}
+}
+
 static const struct file_operations wwan_port_fops = {
 	.owner = THIS_MODULE,
 	.open = wwan_port_fops_open,
@@ -521,28 +782,233 @@ static const struct file_operations wwan_port_fops = {
 	.read = wwan_port_fops_read,
 	.write = wwan_port_fops_write,
 	.poll = wwan_port_fops_poll,
+	.unlocked_ioctl = wwan_port_fops_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = compat_ptr_ioctl,
+#endif
 	.llseek = noop_llseek,
 };
 
+/**
+ * wwan_register_ops - register WWAN device ops
+ * @parent: Device to use as parent and shared by all WWAN ports and
+ *	created netdevs
+ * @ops: operations to register
+ * @ctxt: context to pass to operations
+ *
+ * Returns: 0 on success, a negative error code on failure
+ */
+int wwan_register_ops(struct device *parent, const struct wwan_ops *ops,
+		      void *ctxt)
+{
+	struct wwan_device *wwandev;
+
+	if (WARN_ON(!parent || !ops))
+		return -EINVAL;
+
+	wwandev = wwan_create_dev(parent);
+	if (!wwandev)
+		return -ENOMEM;
+
+	if (WARN_ON(wwandev->ops)) {
+		wwan_remove_dev(wwandev);
+		return -EBUSY;
+	}
+
+	if (!try_module_get(ops->owner)) {
+		wwan_remove_dev(wwandev);
+		return -ENODEV;
+	}
+
+	wwandev->ops = ops;
+	wwandev->ops_ctxt = ctxt;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(wwan_register_ops);
+
+/**
+ * wwan_unregister_ops - remove WWAN device ops
+ * @parent: Device to use as parent and shared by all WWAN ports and
+ *	created netdevs
+ */
+void wwan_unregister_ops(struct device *parent)
+{
+	struct wwan_device *wwandev = wwan_dev_get_by_parent(parent);
+	bool has_ops;
+
+	if (WARN_ON(IS_ERR(wwandev)))
+		return;
+
+	has_ops = wwandev->ops;
+
+	/* put the reference obtained by wwan_dev_get_by_parent(),
+	 * we should still have one (that the owner is giving back
+	 * now) due to the ops being assigned, check that below
+	 * and return if not.
+	 */
+	put_device(&wwandev->dev);
+
+	if (WARN_ON(!has_ops))
+		return;
+
+	module_put(wwandev->ops->owner);
+
+	wwandev->ops = NULL;
+	wwandev->ops_ctxt = NULL;
+	wwan_remove_dev(wwandev);
+}
+EXPORT_SYMBOL_GPL(wwan_unregister_ops);
+
+static int wwan_rtnl_validate(struct nlattr *tb[], struct nlattr *data[],
+			      struct netlink_ext_ack *extack)
+{
+	if (!data)
+		return -EINVAL;
+
+	if (!tb[IFLA_PARENT_DEV_NAME])
+		return -EINVAL;
+
+	if (!data[IFLA_WWAN_LINK_ID])
+		return -EINVAL;
+
+	return 0;
+}
+
+static struct device_type wwan_type = { .name = "wwan" };
+
+static struct net_device *wwan_rtnl_alloc(struct nlattr *tb[],
+					  const char *ifname,
+					  unsigned char name_assign_type,
+					  unsigned int num_tx_queues,
+					  unsigned int num_rx_queues)
+{
+	const char *devname = nla_data(tb[IFLA_PARENT_DEV_NAME]);
+	struct wwan_device *wwandev = wwan_dev_get_by_name(devname);
+	struct net_device *dev;
+
+	if (IS_ERR(wwandev))
+		return ERR_CAST(wwandev);
+
+	/* only supported if ops were registered (not just ports) */
+	if (!wwandev->ops) {
+		dev = ERR_PTR(-EOPNOTSUPP);
+		goto out;
+	}
+
+	dev = alloc_netdev_mqs(wwandev->ops->priv_size, ifname, name_assign_type,
+			       wwandev->ops->setup, num_tx_queues, num_rx_queues);
+
+	if (dev) {
+		SET_NETDEV_DEV(dev, &wwandev->dev);
+		SET_NETDEV_DEVTYPE(dev, &wwan_type);
+	}
+
+out:
+	/* release the reference */
+	put_device(&wwandev->dev);
+	return dev;
+}
+
+static int wwan_rtnl_newlink(struct net *src_net, struct net_device *dev,
+			     struct nlattr *tb[], struct nlattr *data[],
+			     struct netlink_ext_ack *extack)
+{
+	struct wwan_device *wwandev = wwan_dev_get_by_parent(dev->dev.parent);
+	u32 link_id = nla_get_u32(data[IFLA_WWAN_LINK_ID]);
+	int ret;
+
+	if (IS_ERR(wwandev))
+		return PTR_ERR(wwandev);
+
+	/* shouldn't have a netdev (left) with us as parent so WARN */
+	if (WARN_ON(!wwandev->ops)) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (wwandev->ops->newlink)
+		ret = wwandev->ops->newlink(wwandev->ops_ctxt, dev,
+					    link_id, extack);
+	else
+		ret = register_netdevice(dev);
+
+out:
+	/* release the reference */
+	put_device(&wwandev->dev);
+	return ret;
+}
+
+static void wwan_rtnl_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct wwan_device *wwandev = wwan_dev_get_by_parent(dev->dev.parent);
+
+	if (IS_ERR(wwandev))
+		return;
+
+	/* shouldn't have a netdev (left) with us as parent so WARN */
+	if (WARN_ON(!wwandev->ops))
+		goto out;
+
+	if (wwandev->ops->dellink)
+		wwandev->ops->dellink(wwandev->ops_ctxt, dev, head);
+	else
+		unregister_netdevice(dev);
+
+out:
+	/* release the reference */
+	put_device(&wwandev->dev);
+}
+
+static const struct nla_policy wwan_rtnl_policy[IFLA_WWAN_MAX + 1] = {
+	[IFLA_WWAN_LINK_ID] = { .type = NLA_U32 },
+};
+
+static struct rtnl_link_ops wwan_rtnl_link_ops __read_mostly = {
+	.kind = "wwan",
+	.maxtype = __IFLA_WWAN_MAX,
+	.alloc = wwan_rtnl_alloc,
+	.validate = wwan_rtnl_validate,
+	.newlink = wwan_rtnl_newlink,
+	.dellink = wwan_rtnl_dellink,
+	.policy = wwan_rtnl_policy,
+};
+
 static int __init wwan_init(void)
 {
+	int err;
+
+	err = rtnl_link_register(&wwan_rtnl_link_ops);
+	if (err)
+		return err;
+
 	wwan_class = class_create(THIS_MODULE, "wwan");
-	if (IS_ERR(wwan_class))
-		return PTR_ERR(wwan_class);
+	if (IS_ERR(wwan_class)) {
+		err = PTR_ERR(wwan_class);
+		goto unregister;
+	}
 
 	/* chrdev used for wwan ports */
-	wwan_major = register_chrdev(0, "wwan_port", &wwan_port_fops);
+	wwan_major = __register_chrdev(0, 0, WWAN_MAX_MINORS, "wwan_port",
+				       &wwan_port_fops);
 	if (wwan_major < 0) {
-		class_destroy(wwan_class);
-		return wwan_major;
+		err = wwan_major;
+		goto destroy;
 	}
 
 	return 0;
+
+destroy:
+	class_destroy(wwan_class);
+unregister:
+	rtnl_link_unregister(&wwan_rtnl_link_ops);
+	return err;
 }
 
 static void __exit wwan_exit(void)
 {
-	unregister_chrdev(wwan_major, "wwan_port");
+	__unregister_chrdev(wwan_major, 0, WWAN_MAX_MINORS, "wwan_port");
+	rtnl_link_unregister(&wwan_rtnl_link_ops);
 	class_destroy(wwan_class);
 }
 
diff --git a/drivers/net/wwan/wwan_hwsim.c b/drivers/net/wwan/wwan_hwsim.c
new file mode 100644
index 000000000000..472cae544a2b
--- /dev/null
+++ b/drivers/net/wwan/wwan_hwsim.c
@@ -0,0 +1,500 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * WWAN device simulator for WWAN framework testing.
+ *
+ * Copyright (c) 2021, Sergey Ryazanov <ryazanov.s.a@gmail.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/device.h>
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <linux/skbuff.h>
+#include <linux/wwan.h>
+#include <linux/debugfs.h>
+#include <linux/workqueue.h>
+
+static int wwan_hwsim_devsnum = 2;
+module_param_named(devices, wwan_hwsim_devsnum, int, 0444);
+MODULE_PARM_DESC(devices, "Number of simulated devices");
+
+static struct class *wwan_hwsim_class;
+
+static struct dentry *wwan_hwsim_debugfs_topdir;
+static struct dentry *wwan_hwsim_debugfs_devcreate;
+
+static DEFINE_SPINLOCK(wwan_hwsim_devs_lock);
+static LIST_HEAD(wwan_hwsim_devs);
+static unsigned int wwan_hwsim_dev_idx;
+
+struct wwan_hwsim_dev {
+	struct list_head list;
+	unsigned int id;
+	struct device dev;
+	struct work_struct del_work;
+	struct dentry *debugfs_topdir;
+	struct dentry *debugfs_portcreate;
+	spinlock_t ports_lock;	/* Serialize ports creation/deletion */
+	unsigned int port_idx;
+	struct list_head ports;
+};
+
+struct wwan_hwsim_port {
+	struct list_head list;
+	unsigned int id;
+	struct wwan_hwsim_dev *dev;
+	struct wwan_port *wwan;
+	struct work_struct del_work;
+	struct dentry *debugfs_topdir;
+	enum {			/* AT command parser state */
+		AT_PARSER_WAIT_A,
+		AT_PARSER_WAIT_T,
+		AT_PARSER_WAIT_TERM,
+		AT_PARSER_SKIP_LINE,
+	} pstate;
+};
+
+static const struct file_operations wwan_hwsim_debugfs_portdestroy_fops;
+static const struct file_operations wwan_hwsim_debugfs_portcreate_fops;
+static const struct file_operations wwan_hwsim_debugfs_devdestroy_fops;
+static void wwan_hwsim_port_del_work(struct work_struct *work);
+static void wwan_hwsim_dev_del_work(struct work_struct *work);
+
+static int wwan_hwsim_port_start(struct wwan_port *wport)
+{
+	struct wwan_hwsim_port *port = wwan_port_get_drvdata(wport);
+
+	port->pstate = AT_PARSER_WAIT_A;
+
+	return 0;
+}
+
+static void wwan_hwsim_port_stop(struct wwan_port *wport)
+{
+}
+
+/* Implements a minimalistic AT commands parser that echo input back and
+ * reply with 'OK' to each input command. See AT command protocol details in the
+ * ITU-T V.250 recomendations document.
+ *
+ * Be aware that this processor is not fully V.250 compliant.
+ */
+static int wwan_hwsim_port_tx(struct wwan_port *wport, struct sk_buff *in)
+{
+	struct wwan_hwsim_port *port = wwan_port_get_drvdata(wport);
+	struct sk_buff *out;
+	int i, n, s;
+
+	/* Estimate a max possible number of commands by counting the number of
+	 * termination chars (S3 param, CR by default). And then allocate the
+	 * output buffer that will be enough to fit the echo and result codes of
+	 * all commands.
+	 */
+	for (i = 0, n = 0; i < in->len; ++i)
+		if (in->data[i] == '\r')
+			n++;
+	n = in->len + n * (2 + 2 + 2);	/* Output buffer size */
+	out = alloc_skb(n, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	for (i = 0, s = 0; i < in->len; ++i) {
+		char c = in->data[i];
+
+		if (port->pstate == AT_PARSER_WAIT_A) {
+			if (c == 'A' || c == 'a')
+				port->pstate = AT_PARSER_WAIT_T;
+			else if (c != '\n')	/* Ignore formating char */
+				port->pstate = AT_PARSER_SKIP_LINE;
+		} else if (port->pstate == AT_PARSER_WAIT_T) {
+			if (c == 'T' || c == 't')
+				port->pstate = AT_PARSER_WAIT_TERM;
+			else
+				port->pstate = AT_PARSER_SKIP_LINE;
+		} else if (port->pstate == AT_PARSER_WAIT_TERM) {
+			if (c != '\r')
+				continue;
+			/* Consume the trailing formatting char as well */
+			if ((i + 1) < in->len && in->data[i + 1] == '\n')
+				i++;
+			n = i - s + 1;
+			memcpy(skb_put(out, n), &in->data[s], n);/* Echo */
+			memcpy(skb_put(out, 6), "\r\nOK\r\n", 6);
+			s = i + 1;
+			port->pstate = AT_PARSER_WAIT_A;
+		} else if (port->pstate == AT_PARSER_SKIP_LINE) {
+			if (c != '\r')
+				continue;
+			port->pstate = AT_PARSER_WAIT_A;
+		}
+	}
+
+	if (i > s) {
+		/* Echo the processed portion of a not yet completed command */
+		n = i - s;
+		memcpy(skb_put(out, n), &in->data[s], n);
+	}
+
+	consume_skb(in);
+
+	wwan_port_rx(wport, out);
+
+	return 0;
+}
+
+static const struct wwan_port_ops wwan_hwsim_port_ops = {
+	.start = wwan_hwsim_port_start,
+	.stop = wwan_hwsim_port_stop,
+	.tx = wwan_hwsim_port_tx,
+};
+
+static struct wwan_hwsim_port *wwan_hwsim_port_new(struct wwan_hwsim_dev *dev)
+{
+	struct wwan_hwsim_port *port;
+	char name[0x10];
+	int err;
+
+	port = kzalloc(sizeof(*port), GFP_KERNEL);
+	if (!port)
+		return ERR_PTR(-ENOMEM);
+
+	port->dev = dev;
+
+	spin_lock(&dev->ports_lock);
+	port->id = dev->port_idx++;
+	spin_unlock(&dev->ports_lock);
+
+	port->wwan = wwan_create_port(&dev->dev, WWAN_PORT_AT,
+				      &wwan_hwsim_port_ops,
+				      port);
+	if (IS_ERR(port->wwan)) {
+		err = PTR_ERR(port->wwan);
+		goto err_free_port;
+	}
+
+	INIT_WORK(&port->del_work, wwan_hwsim_port_del_work);
+
+	snprintf(name, sizeof(name), "port%u", port->id);
+	port->debugfs_topdir = debugfs_create_dir(name, dev->debugfs_topdir);
+	debugfs_create_file("destroy", 0200, port->debugfs_topdir, port,
+			    &wwan_hwsim_debugfs_portdestroy_fops);
+
+	return port;
+
+err_free_port:
+	kfree(port);
+
+	return ERR_PTR(err);
+}
+
+static void wwan_hwsim_port_del(struct wwan_hwsim_port *port)
+{
+	debugfs_remove(port->debugfs_topdir);
+
+	/* Make sure that there is no pending deletion work */
+	if (current_work() != &port->del_work)
+		cancel_work_sync(&port->del_work);
+
+	wwan_remove_port(port->wwan);
+	kfree(port);
+}
+
+static void wwan_hwsim_port_del_work(struct work_struct *work)
+{
+	struct wwan_hwsim_port *port =
+				container_of(work, typeof(*port), del_work);
+	struct wwan_hwsim_dev *dev = port->dev;
+
+	spin_lock(&dev->ports_lock);
+	if (list_empty(&port->list)) {
+		/* Someone else deleting port at the moment */
+		spin_unlock(&dev->ports_lock);
+		return;
+	}
+	list_del_init(&port->list);
+	spin_unlock(&dev->ports_lock);
+
+	wwan_hwsim_port_del(port);
+}
+
+static void wwan_hwsim_dev_release(struct device *sysdev)
+{
+	struct wwan_hwsim_dev *dev = container_of(sysdev, typeof(*dev), dev);
+
+	kfree(dev);
+}
+
+static struct wwan_hwsim_dev *wwan_hwsim_dev_new(void)
+{
+	struct wwan_hwsim_dev *dev;
+	int err;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock(&wwan_hwsim_devs_lock);
+	dev->id = wwan_hwsim_dev_idx++;
+	spin_unlock(&wwan_hwsim_devs_lock);
+
+	dev->dev.release = wwan_hwsim_dev_release;
+	dev->dev.class = wwan_hwsim_class;
+	dev_set_name(&dev->dev, "hwsim%u", dev->id);
+
+	spin_lock_init(&dev->ports_lock);
+	INIT_LIST_HEAD(&dev->ports);
+
+	err = device_register(&dev->dev);
+	if (err)
+		goto err_free_dev;
+
+	INIT_WORK(&dev->del_work, wwan_hwsim_dev_del_work);
+
+	dev->debugfs_topdir = debugfs_create_dir(dev_name(&dev->dev),
+						 wwan_hwsim_debugfs_topdir);
+	debugfs_create_file("destroy", 0200, dev->debugfs_topdir, dev,
+			    &wwan_hwsim_debugfs_devdestroy_fops);
+	dev->debugfs_portcreate =
+		debugfs_create_file("portcreate", 0200,
+				    dev->debugfs_topdir, dev,
+				    &wwan_hwsim_debugfs_portcreate_fops);
+
+	return dev;
+
+err_free_dev:
+	kfree(dev);
+
+	return ERR_PTR(err);
+}
+
+static void wwan_hwsim_dev_del(struct wwan_hwsim_dev *dev)
+{
+	debugfs_remove(dev->debugfs_portcreate);	/* Avoid new ports */
+
+	spin_lock(&dev->ports_lock);
+	while (!list_empty(&dev->ports)) {
+		struct wwan_hwsim_port *port;
+
+		port = list_first_entry(&dev->ports, struct wwan_hwsim_port,
+					list);
+		list_del_init(&port->list);
+		spin_unlock(&dev->ports_lock);
+		wwan_hwsim_port_del(port);
+		spin_lock(&dev->ports_lock);
+	}
+	spin_unlock(&dev->ports_lock);
+
+	debugfs_remove(dev->debugfs_topdir);
+
+	/* Make sure that there is no pending deletion work */
+	if (current_work() != &dev->del_work)
+		cancel_work_sync(&dev->del_work);
+
+	device_unregister(&dev->dev);
+	/* Memory will be freed in the device release callback */
+}
+
+static void wwan_hwsim_dev_del_work(struct work_struct *work)
+{
+	struct wwan_hwsim_dev *dev = container_of(work, typeof(*dev), del_work);
+
+	spin_lock(&wwan_hwsim_devs_lock);
+	if (list_empty(&dev->list)) {
+		/* Someone else deleting device at the moment */
+		spin_unlock(&wwan_hwsim_devs_lock);
+		return;
+	}
+	list_del_init(&dev->list);
+	spin_unlock(&wwan_hwsim_devs_lock);
+
+	wwan_hwsim_dev_del(dev);
+}
+
+static ssize_t wwan_hwsim_debugfs_portdestroy_write(struct file *file,
+						    const char __user *usrbuf,
+						    size_t count, loff_t *ppos)
+{
+	struct wwan_hwsim_port *port = file->private_data;
+
+	/* We can not delete port here since it will cause a deadlock due to
+	 * waiting this callback to finish in the debugfs_remove() call. So,
+	 * use workqueue.
+	 */
+	schedule_work(&port->del_work);
+
+	return count;
+}
+
+static const struct file_operations wwan_hwsim_debugfs_portdestroy_fops = {
+	.write = wwan_hwsim_debugfs_portdestroy_write,
+	.open = simple_open,
+	.llseek = noop_llseek,
+};
+
+static ssize_t wwan_hwsim_debugfs_portcreate_write(struct file *file,
+						   const char __user *usrbuf,
+						   size_t count, loff_t *ppos)
+{
+	struct wwan_hwsim_dev *dev = file->private_data;
+	struct wwan_hwsim_port *port;
+
+	port = wwan_hwsim_port_new(dev);
+	if (IS_ERR(port))
+		return PTR_ERR(port);
+
+	spin_lock(&dev->ports_lock);
+	list_add_tail(&port->list, &dev->ports);
+	spin_unlock(&dev->ports_lock);
+
+	return count;
+}
+
+static const struct file_operations wwan_hwsim_debugfs_portcreate_fops = {
+	.write = wwan_hwsim_debugfs_portcreate_write,
+	.open = simple_open,
+	.llseek = noop_llseek,
+};
+
+static ssize_t wwan_hwsim_debugfs_devdestroy_write(struct file *file,
+						   const char __user *usrbuf,
+						   size_t count, loff_t *ppos)
+{
+	struct wwan_hwsim_dev *dev = file->private_data;
+
+	/* We can not delete device here since it will cause a deadlock due to
+	 * waiting this callback to finish in the debugfs_remove() call. So,
+	 * use workqueue.
+	 */
+	schedule_work(&dev->del_work);
+
+	return count;
+}
+
+static const struct file_operations wwan_hwsim_debugfs_devdestroy_fops = {
+	.write = wwan_hwsim_debugfs_devdestroy_write,
+	.open = simple_open,
+	.llseek = noop_llseek,
+};
+
+static ssize_t wwan_hwsim_debugfs_devcreate_write(struct file *file,
+						  const char __user *usrbuf,
+						  size_t count, loff_t *ppos)
+{
+	struct wwan_hwsim_dev *dev;
+
+	dev = wwan_hwsim_dev_new();
+	if (IS_ERR(dev))
+		return PTR_ERR(dev);
+
+	spin_lock(&wwan_hwsim_devs_lock);
+	list_add_tail(&dev->list, &wwan_hwsim_devs);
+	spin_unlock(&wwan_hwsim_devs_lock);
+
+	return count;
+}
+
+static const struct file_operations wwan_hwsim_debugfs_devcreate_fops = {
+	.write = wwan_hwsim_debugfs_devcreate_write,
+	.open = simple_open,
+	.llseek = noop_llseek,
+};
+
+static int __init wwan_hwsim_init_devs(void)
+{
+	struct wwan_hwsim_dev *dev;
+	int i, j;
+
+	for (i = 0; i < wwan_hwsim_devsnum; ++i) {
+		dev = wwan_hwsim_dev_new();
+		if (IS_ERR(dev))
+			return PTR_ERR(dev);
+
+		spin_lock(&wwan_hwsim_devs_lock);
+		list_add_tail(&dev->list, &wwan_hwsim_devs);
+		spin_unlock(&wwan_hwsim_devs_lock);
+
+		/* Create a couple of ports per each device to accelerate
+		 * the simulator readiness time.
+		 */
+		for (j = 0; j < 2; ++j) {
+			struct wwan_hwsim_port *port;
+
+			port = wwan_hwsim_port_new(dev);
+			if (IS_ERR(port))
+				return PTR_ERR(port);
+
+			spin_lock(&dev->ports_lock);
+			list_add_tail(&port->list, &dev->ports);
+			spin_unlock(&dev->ports_lock);
+		}
+	}
+
+	return 0;
+}
+
+static void wwan_hwsim_free_devs(void)
+{
+	struct wwan_hwsim_dev *dev;
+
+	spin_lock(&wwan_hwsim_devs_lock);
+	while (!list_empty(&wwan_hwsim_devs)) {
+		dev = list_first_entry(&wwan_hwsim_devs, struct wwan_hwsim_dev,
+				       list);
+		list_del_init(&dev->list);
+		spin_unlock(&wwan_hwsim_devs_lock);
+		wwan_hwsim_dev_del(dev);
+		spin_lock(&wwan_hwsim_devs_lock);
+	}
+	spin_unlock(&wwan_hwsim_devs_lock);
+}
+
+static int __init wwan_hwsim_init(void)
+{
+	int err;
+
+	if (wwan_hwsim_devsnum < 0 || wwan_hwsim_devsnum > 128)
+		return -EINVAL;
+
+	wwan_hwsim_class = class_create(THIS_MODULE, "wwan_hwsim");
+	if (IS_ERR(wwan_hwsim_class))
+		return PTR_ERR(wwan_hwsim_class);
+
+	wwan_hwsim_debugfs_topdir = debugfs_create_dir("wwan_hwsim", NULL);
+	wwan_hwsim_debugfs_devcreate =
+			debugfs_create_file("devcreate", 0200,
+					    wwan_hwsim_debugfs_topdir, NULL,
+					    &wwan_hwsim_debugfs_devcreate_fops);
+
+	err = wwan_hwsim_init_devs();
+	if (err)
+		goto err_clean_devs;
+
+	return 0;
+
+err_clean_devs:
+	wwan_hwsim_free_devs();
+	debugfs_remove(wwan_hwsim_debugfs_topdir);
+	class_destroy(wwan_hwsim_class);
+
+	return err;
+}
+
+static void __exit wwan_hwsim_exit(void)
+{
+	debugfs_remove(wwan_hwsim_debugfs_devcreate);	/* Avoid new devs */
+	wwan_hwsim_free_devs();
+	flush_scheduled_work();		/* Wait deletion works completion */
+	debugfs_remove(wwan_hwsim_debugfs_topdir);
+	class_destroy(wwan_hwsim_class);
+}
+
+module_init(wwan_hwsim_init);
+module_exit(wwan_hwsim_exit);
+
+MODULE_AUTHOR("Sergey Ryazanov");
+MODULE_DESCRIPTION("Device simulator for WWAN framework");
+MODULE_LICENSE("GPL");
diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c
index fe0719ed81a0..528745862738 100644
--- a/drivers/nfc/fdp/fdp.c
+++ b/drivers/nfc/fdp/fdp.c
@@ -149,7 +149,7 @@ static void fdp_nci_send_patch_cb(struct nci_dev *ndev)
 	wake_up(&info->setup_wq);
 }
 
-/**
+/*
  * Register a packet sent counter and a callback
  *
  * We have no other way of knowing when all firmware packets were sent out
@@ -167,7 +167,7 @@ static void fdp_nci_set_data_pkt_counter(struct nci_dev *ndev,
 	info->data_pkt_counter_cb = cb;
 }
 
-/**
+/*
  * The device is expecting a stream of packets. All packets need to
  * have the PBF flag set to 0x0 (last packet) even if the firmware
  * file is segmented and there are multiple packets. If we give the
@@ -237,28 +237,18 @@ static int fdp_nci_send_patch(struct nci_dev *ndev, u8 conn_id, u8 type)
 static int fdp_nci_open(struct nci_dev *ndev)
 {
 	struct fdp_nci_info *info = nci_get_drvdata(ndev);
-	struct device *dev = &info->phy->i2c_dev->dev;
-
-	dev_dbg(dev, "%s\n", __func__);
 
 	return info->phy_ops->enable(info->phy);
 }
 
 static int fdp_nci_close(struct nci_dev *ndev)
 {
-	struct fdp_nci_info *info = nci_get_drvdata(ndev);
-	struct device *dev = &info->phy->i2c_dev->dev;
-
-	dev_dbg(dev, "%s\n", __func__);
 	return 0;
 }
 
 static int fdp_nci_send(struct nci_dev *ndev, struct sk_buff *skb)
 {
 	struct fdp_nci_info *info = nci_get_drvdata(ndev);
-	struct device *dev = &info->phy->i2c_dev->dev;
-
-	dev_dbg(dev, "%s\n", __func__);
 
 	if (atomic_dec_and_test(&info->data_pkt_counter))
 		info->data_pkt_counter_cb(ndev);
@@ -266,16 +256,6 @@ static int fdp_nci_send(struct nci_dev *ndev, struct sk_buff *skb)
 	return info->phy_ops->write(info->phy, skb);
 }
 
-int fdp_nci_recv_frame(struct nci_dev *ndev, struct sk_buff *skb)
-{
-	struct fdp_nci_info *info = nci_get_drvdata(ndev);
-	struct device *dev = &info->phy->i2c_dev->dev;
-
-	dev_dbg(dev, "%s\n", __func__);
-	return nci_recv_frame(ndev, skb);
-}
-EXPORT_SYMBOL(fdp_nci_recv_frame);
-
 static int fdp_nci_request_firmware(struct nci_dev *ndev)
 {
 	struct fdp_nci_info *info = nci_get_drvdata(ndev);
@@ -286,7 +266,7 @@ static int fdp_nci_request_firmware(struct nci_dev *ndev)
 	r = request_firmware(&info->ram_patch, FDP_RAM_PATCH_NAME, dev);
 	if (r < 0) {
 		nfc_err(dev, "RAM patch request error\n");
-		goto error;
+		return r;
 	}
 
 	data = (u8 *) info->ram_patch->data;
@@ -303,7 +283,7 @@ static int fdp_nci_request_firmware(struct nci_dev *ndev)
 	r = request_firmware(&info->otp_patch, FDP_OTP_PATCH_NAME, dev);
 	if (r < 0) {
 		nfc_err(dev, "OTP patch request error\n");
-		goto out;
+		return 0;
 	}
 
 	data = (u8 *) info->otp_patch->data;
@@ -315,10 +295,7 @@ static int fdp_nci_request_firmware(struct nci_dev *ndev)
 
 	dev_dbg(dev, "OTP patch version: %d, size: %d\n",
 		 info->otp_patch_version, (int) info->otp_patch->size);
-out:
 	return 0;
-error:
-	return r;
 }
 
 static void fdp_nci_release_firmware(struct nci_dev *ndev)
@@ -476,8 +453,6 @@ static int fdp_nci_setup(struct nci_dev *ndev)
 	int r;
 	u8 patched = 0;
 
-	dev_dbg(dev, "%s\n", __func__);
-
 	r = nci_core_init(ndev);
 	if (r)
 		goto error;
@@ -585,9 +560,7 @@ static int fdp_nci_core_reset_ntf_packet(struct nci_dev *ndev,
 					  struct sk_buff *skb)
 {
 	struct fdp_nci_info *info = nci_get_drvdata(ndev);
-	struct device *dev = &info->phy->i2c_dev->dev;
 
-	dev_dbg(dev, "%s\n", __func__);
 	info->setup_reset_ntf = 1;
 	wake_up(&info->setup_wq);
 
@@ -598,9 +571,7 @@ static int fdp_nci_prop_patch_ntf_packet(struct nci_dev *ndev,
 					  struct sk_buff *skb)
 {
 	struct fdp_nci_info *info = nci_get_drvdata(ndev);
-	struct device *dev = &info->phy->i2c_dev->dev;
 
-	dev_dbg(dev, "%s\n", __func__);
 	info->setup_patch_ntf = 1;
 	info->setup_patch_status = skb->data[0];
 	wake_up(&info->setup_wq);
@@ -773,11 +744,6 @@ EXPORT_SYMBOL(fdp_nci_probe);
 
 void fdp_nci_remove(struct nci_dev *ndev)
 {
-	struct fdp_nci_info *info = nci_get_drvdata(ndev);
-	struct device *dev = &info->phy->i2c_dev->dev;
-
-	dev_dbg(dev, "%s\n", __func__);
-
 	nci_unregister_device(ndev);
 	nci_free_device(ndev);
 }
diff --git a/drivers/nfc/fdp/fdp.h b/drivers/nfc/fdp/fdp.h
index 9bd1f3f23e2d..ead3b21ccae6 100644
--- a/drivers/nfc/fdp/fdp.h
+++ b/drivers/nfc/fdp/fdp.h
@@ -25,6 +25,5 @@ int fdp_nci_probe(struct fdp_i2c_phy *phy, struct nfc_phy_ops *phy_ops,
 		  struct nci_dev **ndev, int tx_headroom, int tx_tailroom,
 		  u8 clock_type, u32 clock_freq, u8 *fw_vsc_cfg);
 void fdp_nci_remove(struct nci_dev *ndev);
-int fdp_nci_recv_frame(struct nci_dev *ndev, struct sk_buff *skb);
 
 #endif /* __LOCAL_FDP_H_ */
diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c
index adaa1a7147f9..c5596e514648 100644
--- a/drivers/nfc/fdp/i2c.c
+++ b/drivers/nfc/fdp/i2c.c
@@ -49,7 +49,6 @@ static int fdp_nci_i2c_enable(void *phy_id)
 {
 	struct fdp_i2c_phy *phy = phy_id;
 
-	dev_dbg(&phy->i2c_dev->dev, "%s\n", __func__);
 	fdp_nci_i2c_reset(phy);
 
 	return 0;
@@ -59,7 +58,6 @@ static void fdp_nci_i2c_disable(void *phy_id)
 {
 	struct fdp_i2c_phy *phy = phy_id;
 
-	dev_dbg(&phy->i2c_dev->dev, "%s\n", __func__);
 	fdp_nci_i2c_reset(phy);
 }
 
@@ -197,7 +195,6 @@ flush:
 static irqreturn_t fdp_nci_i2c_irq_thread_fn(int irq, void *phy_id)
 {
 	struct fdp_i2c_phy *phy = phy_id;
-	struct i2c_client *client;
 	struct sk_buff *skb;
 	int r;
 
@@ -206,9 +203,6 @@ static irqreturn_t fdp_nci_i2c_irq_thread_fn(int irq, void *phy_id)
 		return IRQ_NONE;
 	}
 
-	client = phy->i2c_dev;
-	dev_dbg(&client->dev, "%s\n", __func__);
-
 	r = fdp_nci_i2c_read(phy, &skb);
 
 	if (r == -EREMOTEIO)
@@ -217,7 +211,7 @@ static irqreturn_t fdp_nci_i2c_irq_thread_fn(int irq, void *phy_id)
 		return IRQ_HANDLED;
 
 	if (skb != NULL)
-		fdp_nci_recv_frame(phy->ndev, skb);
+		nci_recv_frame(phy->ndev, skb);
 
 	return IRQ_HANDLED;
 }
@@ -288,8 +282,6 @@ static int fdp_nci_i2c_probe(struct i2c_client *client)
 	u32 clock_freq;
 	int r = 0;
 
-	dev_dbg(dev, "%s\n", __func__);
-
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
 		nfc_err(dev, "No I2C_FUNC_I2C support\n");
 		return -ENODEV;
@@ -351,8 +343,6 @@ static int fdp_nci_i2c_remove(struct i2c_client *client)
 {
 	struct fdp_i2c_phy *phy = i2c_get_clientdata(client);
 
-	dev_dbg(&client->dev, "%s\n", __func__);
-
 	fdp_nci_remove(phy->ndev);
 	fdp_nci_i2c_disable(phy);
 
@@ -368,7 +358,7 @@ MODULE_DEVICE_TABLE(acpi, fdp_nci_i2c_acpi_match);
 static struct i2c_driver fdp_nci_i2c_driver = {
 	.driver = {
 		   .name = FDP_I2C_DRIVER_NAME,
-		   .acpi_match_table = ACPI_PTR(fdp_nci_i2c_acpi_match),
+		   .acpi_match_table = fdp_nci_i2c_acpi_match,
 		  },
 	.probe_new = fdp_nci_i2c_probe,
 	.remove = fdp_nci_i2c_remove,
diff --git a/drivers/nfc/mei_phy.c b/drivers/nfc/mei_phy.c
index 0f43bb389566..e56cea716cd2 100644
--- a/drivers/nfc/mei_phy.c
+++ b/drivers/nfc/mei_phy.c
@@ -98,8 +98,6 @@ static int mei_nfc_if_version(struct nfc_mei_phy *phy)
 	size_t if_version_length;
 	int bytes_recv, r;
 
-	pr_info("%s\n", __func__);
-
 	memset(&cmd, 0, sizeof(struct mei_nfc_cmd));
 	cmd.hdr.cmd = MEI_NFC_CMD_MAINTENANCE;
 	cmd.hdr.data_size = 1;
@@ -146,8 +144,6 @@ static int mei_nfc_connect(struct nfc_mei_phy *phy)
 	size_t connect_length, connect_resp_length;
 	int bytes_recv, r;
 
-	pr_info("%s\n", __func__);
-
 	connect_length = sizeof(struct mei_nfc_cmd) +
 			sizeof(struct mei_nfc_connect);
 
@@ -320,8 +316,6 @@ static int nfc_mei_phy_enable(void *phy_id)
 	int r;
 	struct nfc_mei_phy *phy = phy_id;
 
-	pr_info("%s\n", __func__);
-
 	if (phy->powered == 1)
 		return 0;
 
@@ -363,8 +357,6 @@ static void nfc_mei_phy_disable(void *phy_id)
 {
 	struct nfc_mei_phy *phy = phy_id;
 
-	pr_info("%s\n", __func__);
-
 	mei_cldev_disable(phy->cldev);
 
 	phy->powered = 0;
diff --git a/drivers/nfc/microread/microread.c b/drivers/nfc/microread/microread.c
index 8d3988457c58..b1d3975e8a81 100644
--- a/drivers/nfc/microread/microread.c
+++ b/drivers/nfc/microread/microread.c
@@ -364,7 +364,6 @@ static void microread_im_transceive_cb(void *context, struct sk_buff *skb,
 	case MICROREAD_CB_TYPE_READER_ALL:
 		if (err == 0) {
 			if (skb->len == 0) {
-				err = -EPROTO;
 				kfree_skb(skb);
 				info->async_cb(info->async_cb_context, NULL,
 					       -EPROTO);
diff --git a/drivers/nfc/nfcmrvl/fw_dnld.c b/drivers/nfc/nfcmrvl/fw_dnld.c
index 52c8ae504e32..aaccb8b76b3e 100644
--- a/drivers/nfc/nfcmrvl/fw_dnld.c
+++ b/drivers/nfc/nfcmrvl/fw_dnld.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Marvell NFC driver: Firmware downloader
  *
  * Copyright (C) 2015, Marvell International Ltd.
- *
- * This software file (the "File") is distributed by Marvell International
- * Ltd. under the terms of the GNU General Public License Version 2, June 1991
- * (the "License").  You may use, redistribute and/or modify this File in
- * accordance with the terms and conditions of the License, a copy of which
- * is available on the worldwide web at
- * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt.
- *
- * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE
- * ARE EXPRESSLY DISCLAIMED.  The License provides additional details about
- * this warranty disclaimer.
  */
 
 #include <linux/module.h>
@@ -50,8 +39,8 @@ enum {
 };
 
 /*
-** Patterns for responses
-*/
+ * Patterns for responses
+ */
 
 static const uint8_t nci_pattern_core_reset_ntf[] = {
 	0x60, 0x00, 0x02, 0xA0, 0x01
@@ -451,7 +440,7 @@ static void fw_dnld_rx_work(struct work_struct *work)
 	}
 }
 
-int	nfcmrvl_fw_dnld_init(struct nfcmrvl_private *priv)
+int nfcmrvl_fw_dnld_init(struct nfcmrvl_private *priv)
 {
 	char name[32];
 
@@ -465,13 +454,13 @@ int	nfcmrvl_fw_dnld_init(struct nfcmrvl_private *priv)
 	return 0;
 }
 
-void	nfcmrvl_fw_dnld_deinit(struct nfcmrvl_private *priv)
+void nfcmrvl_fw_dnld_deinit(struct nfcmrvl_private *priv)
 {
 	destroy_workqueue(priv->fw_dnld.rx_wq);
 }
 
-void	nfcmrvl_fw_dnld_recv_frame(struct nfcmrvl_private *priv,
-				   struct sk_buff *skb)
+void nfcmrvl_fw_dnld_recv_frame(struct nfcmrvl_private *priv,
+				struct sk_buff *skb)
 {
 	/* Discard command timer */
 	if (timer_pending(&priv->ndev->cmd_timer))
diff --git a/drivers/nfc/nfcmrvl/fw_dnld.h b/drivers/nfc/nfcmrvl/fw_dnld.h
index 058ce77b3cbc..7c4d91b01910 100644
--- a/drivers/nfc/nfcmrvl/fw_dnld.h
+++ b/drivers/nfc/nfcmrvl/fw_dnld.h
@@ -1,20 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Marvell NFC driver: Firmware downloader
  *
  * Copyright (C) 2015, Marvell International Ltd.
- *
- * This software file (the "File") is distributed by Marvell International
- * Ltd. under the terms of the GNU General Public License Version 2, June 1991
- * (the "License").  You may use, redistribute and/or modify this File in
- * accordance with the terms and conditions of the License, a copy of which
- * is available on the worldwide web at
- * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt.
- *
- * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE
- * ARE EXPRESSLY DISCLAIMED.  The License provides additional details about
- * this warranty disclaimer.
- **/
+ */
 
 #ifndef __NFCMRVL_FW_DNLD_H__
 #define __NFCMRVL_FW_DNLD_H__
diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c
index c5420616b7bc..59a529e72d96 100644
--- a/drivers/nfc/nfcmrvl/i2c.c
+++ b/drivers/nfc/nfcmrvl/i2c.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Marvell NFC-over-I2C driver: I2C interface related functions
  *
  * Copyright (C) 2015, Marvell International Ltd.
- *
- * This software file (the "File") is distributed by Marvell International
- * Ltd. under the terms of the GNU General Public License Version 2, June 1991
- * (the "License").  You may use, redistribute and/or modify this File in
- * accordance with the terms and conditions of the License, a copy of which
- * is available on the worldwide web at
- * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt.
- *
- * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE
- * ARE EXPRESSLY DISCLAIMED.  The License provides additional details about
- * this warranty disclaimer.
- **/
+ */
 
 #include <linux/module.h>
 #include <linux/interrupt.h>
@@ -49,11 +38,6 @@ static int nfcmrvl_i2c_read(struct nfcmrvl_i2c_drv_data *drv_data,
 		return -EBADMSG;
 	}
 
-	if (nci_hdr.plen > NCI_MAX_PAYLOAD_SIZE) {
-		nfc_err(&drv_data->i2c->dev, "invalid packet payload size\n");
-		return -EBADMSG;
-	}
-
 	*skb = nci_skb_alloc(drv_data->priv->ndev,
 			     nci_hdr.plen + NCI_CTRL_HDR_SIZE, GFP_KERNEL);
 	if (!*skb)
@@ -260,7 +244,7 @@ static int nfcmrvl_i2c_remove(struct i2c_client *client)
 }
 
 
-static const struct of_device_id of_nfcmrvl_i2c_match[] = {
+static const struct of_device_id of_nfcmrvl_i2c_match[] __maybe_unused = {
 	{ .compatible = "marvell,nfc-i2c", },
 	{},
 };
diff --git a/drivers/nfc/nfcmrvl/main.c b/drivers/nfc/nfcmrvl/main.c
index 529be35ac178..a4620b480c4f 100644
--- a/drivers/nfc/nfcmrvl/main.c
+++ b/drivers/nfc/nfcmrvl/main.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Marvell NFC driver: major functions
  *
  * Copyright (C) 2014-2015 Marvell International Ltd.
- *
- * This software file (the "File") is distributed by Marvell International
- * Ltd. under the terms of the GNU General Public License Version 2, June 1991
- * (the "License").  You may use, redistribute and/or modify this File in
- * accordance with the terms and conditions of the License, a copy of which
- * is available on the worldwide web at
- * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt.
- *
- * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE
- * ARE EXPRESSLY DISCLAIMED.  The License provides additional details about
- * this warranty disclaimer.
  */
 
 #include <linux/module.h>
diff --git a/drivers/nfc/nfcmrvl/nfcmrvl.h b/drivers/nfc/nfcmrvl/nfcmrvl.h
index e84ee18c73ae..a715543bc9bf 100644
--- a/drivers/nfc/nfcmrvl/nfcmrvl.h
+++ b/drivers/nfc/nfcmrvl/nfcmrvl.h
@@ -1,20 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Marvell NFC driver
  *
  * Copyright (C) 2014-2015, Marvell International Ltd.
- *
- * This software file (the "File") is distributed by Marvell International
- * Ltd. under the terms of the GNU General Public License Version 2, June 1991
- * (the "License").  You may use, redistribute and/or modify this File in
- * accordance with the terms and conditions of the License, a copy of which
- * is available on the worldwide web at
- * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt.
- *
- * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE
- * ARE EXPRESSLY DISCLAIMED.  The License provides additional details about
- * this warranty disclaimer.
- **/
+ */
 
 #ifndef _NFCMRVL_H_
 #define _NFCMRVL_H_
@@ -36,16 +25,16 @@
 #define NFCMRVL_NCI_MAX_EVENT_SIZE		260
 
 /*
-** NCI FW Parmaters
-*/
+ * NCI FW Parameters
+ */
 
 #define NFCMRVL_PB_BAIL_OUT			0x11
 #define NFCMRVL_PROP_REF_CLOCK			0xF0
 #define NFCMRVL_PROP_SET_HI_CONFIG		0xF1
 
 /*
-** HCI defines
-*/
+ * HCI defines
+ */
 
 #define NFCMRVL_HCI_EVENT_HEADER_SIZE		0x04
 #define NFCMRVL_HCI_EVENT_CODE			0x04
@@ -78,8 +67,8 @@ struct nfcmrvl_private {
 	bool support_fw_dnld;
 
 	/*
-	** PHY related information
-	*/
+	 * PHY related information
+	 */
 
 	/* PHY driver context */
 	void *drv_data;
diff --git a/drivers/nfc/nfcmrvl/spi.c b/drivers/nfc/nfcmrvl/spi.c
index dec0d3eb3648..66696321c645 100644
--- a/drivers/nfc/nfcmrvl/spi.c
+++ b/drivers/nfc/nfcmrvl/spi.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Marvell NFC-over-SPI driver: SPI interface related functions
  *
  * Copyright (C) 2015, Marvell International Ltd.
- *
- * This software file (the "File") is distributed by Marvell International
- * Ltd. under the terms of the GNU General Public License Version 2, June 1991
- * (the "License").  You may use, redistribute and/or modify this File in
- * accordance with the terms and conditions of the License, a copy of which
- * is available on the worldwide web at
- * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt.
- *
- * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE
- * ARE EXPRESSLY DISCLAIMED.  The License provides additional details about
- * this warranty disclaimer.
- **/
+ */
 
 #include <linux/module.h>
 #include <linux/interrupt.h>
@@ -196,7 +185,7 @@ static int nfcmrvl_spi_remove(struct spi_device *spi)
 	return 0;
 }
 
-static const struct of_device_id of_nfcmrvl_spi_match[] = {
+static const struct of_device_id of_nfcmrvl_spi_match[] __maybe_unused = {
 	{ .compatible = "marvell,nfc-spi", },
 	{},
 };
diff --git a/drivers/nfc/nfcmrvl/uart.c b/drivers/nfc/nfcmrvl/uart.c
index 7194dd7ef0f1..50d86c90b9dd 100644
--- a/drivers/nfc/nfcmrvl/uart.c
+++ b/drivers/nfc/nfcmrvl/uart.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Marvell NFC-over-UART driver
  *
  * Copyright (C) 2015, Marvell International Ltd.
- *
- * This software file (the "File") is distributed by Marvell International
- * Ltd. under the terms of the GNU General Public License Version 2, June 1991
- * (the "License").  You may use, redistribute and/or modify this File in
- * accordance with the terms and conditions of the License, a copy of which
- * is available on the worldwide web at
- * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt.
- *
- * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE
- * ARE EXPRESSLY DISCLAIMED.  The License provides additional details about
- * this warranty disclaimer.
  */
 
 #include <linux/module.h>
@@ -29,8 +18,8 @@ static unsigned int break_control;
 static int reset_n_io = -EINVAL;
 
 /*
-** NFCMRVL NCI OPS
-*/
+ * NFCMRVL NCI OPS
+ */
 
 static int nfcmrvl_uart_nci_open(struct nfcmrvl_private *priv)
 {
@@ -103,8 +92,8 @@ static int nfcmrvl_uart_parse_dt(struct device_node *node,
 }
 
 /*
-** NCI UART OPS
-*/
+ * NCI UART OPS
+ */
 
 static int nfcmrvl_nci_uart_open(struct nci_uart *nu)
 {
@@ -178,10 +167,10 @@ static void nfcmrvl_nci_uart_tx_done(struct nci_uart *nu)
 		return;
 
 	/*
-	** To ensure that if the NFCC goes in DEEP SLEEP sate we can wake him
-	** up. we set BREAK. Once we will be ready to send again we will remove
-	** it.
-	*/
+	 * To ensure that if the NFCC goes in DEEP SLEEP sate we can wake him
+	 * up. we set BREAK. Once we will be ready to send again we will remove
+	 * it.
+	 */
 	if (priv->config.break_control && nu->tty->ops->break_ctl) {
 		nu->tty->ops->break_ctl(nu->tty, -1);
 		usleep_range(1000, 3000);
@@ -200,23 +189,7 @@ static struct nci_uart nfcmrvl_nci_uart = {
 		.tx_done	= nfcmrvl_nci_uart_tx_done,
 	}
 };
-
-/*
-** Module init
-*/
-
-static int nfcmrvl_uart_init_module(void)
-{
-	return nci_uart_register(&nfcmrvl_nci_uart);
-}
-
-static void nfcmrvl_uart_exit_module(void)
-{
-	nci_uart_unregister(&nfcmrvl_nci_uart);
-}
-
-module_init(nfcmrvl_uart_init_module);
-module_exit(nfcmrvl_uart_exit_module);
+module_driver(nfcmrvl_nci_uart, nci_uart_register, nci_uart_unregister);
 
 MODULE_AUTHOR("Marvell International Ltd.");
 MODULE_DESCRIPTION("Marvell NFC-over-UART");
diff --git a/drivers/nfc/nfcmrvl/usb.c b/drivers/nfc/nfcmrvl/usb.c
index bcd563cb556c..9d649b45300b 100644
--- a/drivers/nfc/nfcmrvl/usb.c
+++ b/drivers/nfc/nfcmrvl/usb.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Marvell NFC-over-USB driver: USB interface related functions
  *
  * Copyright (C) 2014, Marvell International Ltd.
- *
- * This software file (the "File") is distributed by Marvell International
- * Ltd. under the terms of the GNU General Public License Version 2, June 1991
- * (the "License").  You may use, redistribute and/or modify this File in
- * accordance with the terms and conditions of the License, a copy of which
- * is available on the worldwide web at
- * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt.
- *
- * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE
- * ARE EXPRESSLY DISCLAIMED.  The License provides additional details about
- * this warranty disclaimer.
- **/
+ */
 
 #include <linux/module.h>
 #include <linux/usb.h>
@@ -68,7 +57,6 @@ static int nfcmrvl_inc_tx(struct nfcmrvl_usb_drv_data *drv_data)
 static void nfcmrvl_bulk_complete(struct urb *urb)
 {
 	struct nfcmrvl_usb_drv_data *drv_data = urb->context;
-	struct sk_buff *skb;
 	int err;
 
 	dev_dbg(&drv_data->udev->dev, "urb %p status %d count %d\n",
@@ -78,6 +66,8 @@ static void nfcmrvl_bulk_complete(struct urb *urb)
 		return;
 
 	if (!urb->status) {
+		struct sk_buff *skb;
+
 		skb = nci_skb_alloc(drv_data->priv->ndev, urb->actual_length,
 				    GFP_ATOMIC);
 		if (!skb) {
@@ -296,7 +286,6 @@ static void nfcmrvl_waker(struct work_struct *work)
 static int nfcmrvl_probe(struct usb_interface *intf,
 			 const struct usb_device_id *id)
 {
-	struct usb_endpoint_descriptor *ep_desc;
 	struct nfcmrvl_usb_drv_data *drv_data;
 	struct nfcmrvl_private *priv;
 	int i;
@@ -314,18 +303,16 @@ static int nfcmrvl_probe(struct usb_interface *intf,
 		return -ENOMEM;
 
 	for (i = 0; i < intf->cur_altsetting->desc.bNumEndpoints; i++) {
+		struct usb_endpoint_descriptor *ep_desc;
+
 		ep_desc = &intf->cur_altsetting->endpoint[i].desc;
 
 		if (!drv_data->bulk_tx_ep &&
 		    usb_endpoint_is_bulk_out(ep_desc)) {
 			drv_data->bulk_tx_ep = ep_desc;
-			continue;
-		}
-
-		if (!drv_data->bulk_rx_ep &&
-		    usb_endpoint_is_bulk_in(ep_desc)) {
+		} else if (!drv_data->bulk_rx_ep &&
+			   usb_endpoint_is_bulk_in(ep_desc)) {
 			drv_data->bulk_rx_ep = ep_desc;
-			continue;
 		}
 	}
 
diff --git a/drivers/nfc/nxp-nci/core.c b/drivers/nfc/nxp-nci/core.c
index a0ce95a287c5..2b0c7232e91f 100644
--- a/drivers/nfc/nxp-nci/core.c
+++ b/drivers/nfc/nxp-nci/core.c
@@ -70,21 +70,16 @@ static int nxp_nci_send(struct nci_dev *ndev, struct sk_buff *skb)
 	struct nxp_nci_info *info = nci_get_drvdata(ndev);
 	int r;
 
-	if (!info->phy_ops->write) {
-		r = -ENOTSUPP;
-		goto send_exit;
-	}
+	if (!info->phy_ops->write)
+		return -EOPNOTSUPP;
 
-	if (info->mode != NXP_NCI_MODE_NCI) {
-		r = -EINVAL;
-		goto send_exit;
-	}
+	if (info->mode != NXP_NCI_MODE_NCI)
+		return -EINVAL;
 
 	r = info->phy_ops->write(info->phy_id, skb);
 	if (r < 0)
 		kfree_skb(skb);
 
-send_exit:
 	return r;
 }
 
@@ -104,10 +99,8 @@ int nxp_nci_probe(void *phy_id, struct device *pdev,
 	int r;
 
 	info = devm_kzalloc(pdev, sizeof(struct nxp_nci_info), GFP_KERNEL);
-	if (!info) {
-		r = -ENOMEM;
-		goto probe_exit;
-	}
+	if (!info)
+		return -ENOMEM;
 
 	info->phy_id = phy_id;
 	info->pdev = pdev;
@@ -120,31 +113,25 @@ int nxp_nci_probe(void *phy_id, struct device *pdev,
 	if (info->phy_ops->set_mode) {
 		r = info->phy_ops->set_mode(info->phy_id, NXP_NCI_MODE_COLD);
 		if (r < 0)
-			goto probe_exit;
+			return r;
 	}
 
 	info->mode = NXP_NCI_MODE_COLD;
 
 	info->ndev = nci_allocate_device(&nxp_nci_ops, NXP_NCI_NFC_PROTOCOLS,
 					 NXP_NCI_HDR_LEN, 0);
-	if (!info->ndev) {
-		r = -ENOMEM;
-		goto probe_exit;
-	}
+	if (!info->ndev)
+		return -ENOMEM;
 
 	nci_set_parent_dev(info->ndev, pdev);
 	nci_set_drvdata(info->ndev, info);
 	r = nci_register_device(info->ndev);
-	if (r < 0)
-		goto probe_exit_free_nci;
+	if (r < 0) {
+		nci_free_device(info->ndev);
+		return r;
+	}
 
 	*ndev = info->ndev;
-
-	goto probe_exit;
-
-probe_exit_free_nci:
-	nci_free_device(info->ndev);
-probe_exit:
 	return r;
 }
 EXPORT_SYMBOL(nxp_nci_probe);
diff --git a/drivers/nfc/nxp-nci/firmware.c b/drivers/nfc/nxp-nci/firmware.c
index dae0c8030e95..119bf305c642 100644
--- a/drivers/nfc/nxp-nci/firmware.c
+++ b/drivers/nfc/nxp-nci/firmware.c
@@ -95,10 +95,8 @@ static int nxp_nci_fw_send_chunk(struct nxp_nci_info *info)
 	int r;
 
 	skb = nci_skb_alloc(info->ndev, info->max_payload, GFP_KERNEL);
-	if (!skb) {
-		r = -ENOMEM;
-		goto chunk_exit;
-	}
+	if (!skb)
+		return -ENOMEM;
 
 	chunk_len = info->max_payload - NXP_NCI_FW_HDR_LEN - NXP_NCI_FW_CRC_LEN;
 	remaining_len = fw_info->frame_size - fw_info->written;
@@ -124,7 +122,6 @@ static int nxp_nci_fw_send_chunk(struct nxp_nci_info *info)
 
 	kfree_skb(skb);
 
-chunk_exit:
 	return r;
 }
 
diff --git a/drivers/nfc/pn533/i2c.c b/drivers/nfc/pn533/i2c.c
index 795da9b85d56..e6bf8cfe3aa7 100644
--- a/drivers/nfc/pn533/i2c.c
+++ b/drivers/nfc/pn533/i2c.c
@@ -174,9 +174,6 @@ static int pn533_i2c_probe(struct i2c_client *client,
 	struct pn533 *priv;
 	int r = 0;
 
-	dev_dbg(&client->dev, "%s\n", __func__);
-	dev_dbg(&client->dev, "IRQ: %d\n", client->irq);
-
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
 		nfc_err(&client->dev, "Need I2C_FUNC_I2C\n");
 		return -ENODEV;
@@ -195,9 +192,8 @@ static int pn533_i2c_probe(struct i2c_client *client,
 				phy, &i2c_phy_ops, NULL,
 				&phy->i2c_dev->dev);
 
-	if (IS_ERR(priv)) {
+	if (IS_ERR(priv))
 		return PTR_ERR(priv);
-	}
 
 	phy->priv = priv;
 	r = pn532_i2c_nfc_alloc(priv, PN533_NO_TYPE_B_PROTOCOLS, &client->dev);
@@ -239,8 +235,6 @@ static int pn533_i2c_remove(struct i2c_client *client)
 {
 	struct pn533_i2c_phy *phy = i2c_get_clientdata(client);
 
-	dev_dbg(&client->dev, "%s\n", __func__);
-
 	free_irq(client->irq, phy);
 
 	pn53x_unregister_nfc(phy->priv);
@@ -249,7 +243,7 @@ static int pn533_i2c_remove(struct i2c_client *client)
 	return 0;
 }
 
-static const struct of_device_id of_pn533_i2c_match[] = {
+static const struct of_device_id of_pn533_i2c_match[] __maybe_unused = {
 	{ .compatible = "nxp,pn532", },
 	/*
 	 * NOTE: The use of the compatibles with the trailing "...-i2c" is
diff --git a/drivers/nfc/pn533/pn533.c b/drivers/nfc/pn533/pn533.c
index 2c7f9916f206..cd64bfe20402 100644
--- a/drivers/nfc/pn533/pn533.c
+++ b/drivers/nfc/pn533/pn533.c
@@ -1075,8 +1075,6 @@ static int pn533_tm_get_data_complete(struct pn533 *dev, void *arg,
 	u8 status, ret, mi;
 	int rc;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	if (IS_ERR(resp)) {
 		skb_queue_purge(&dev->resp_q);
 		return PTR_ERR(resp);
@@ -1124,8 +1122,6 @@ static void pn533_wq_tm_mi_recv(struct work_struct *work)
 	struct sk_buff *skb;
 	int rc;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	skb = pn533_alloc_skb(dev, 0);
 	if (!skb)
 		return;
@@ -1148,8 +1144,6 @@ static void pn533_wq_tm_mi_send(struct work_struct *work)
 	struct sk_buff *skb;
 	int rc;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	/* Grab the first skb in the queue */
 	skb = skb_dequeue(&dev->fragment_skb);
 	if (skb == NULL) {	/* No more data */
@@ -1186,8 +1180,6 @@ static void pn533_wq_tg_get_data(struct work_struct *work)
 	struct sk_buff *skb;
 	int rc;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	skb = pn533_alloc_skb(dev, 0);
 	if (!skb)
 		return;
@@ -1206,8 +1198,6 @@ static int pn533_init_target_complete(struct pn533 *dev, struct sk_buff *resp)
 	size_t gb_len;
 	int rc;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	if (resp->len < ATR_REQ_GB_OFFSET + 1)
 		return -EINVAL;
 
@@ -1260,8 +1250,6 @@ static int pn533_rf_complete(struct pn533 *dev, void *arg,
 {
 	int rc = 0;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	if (IS_ERR(resp)) {
 		rc = PTR_ERR(resp);
 
@@ -1283,8 +1271,6 @@ static void pn533_wq_rf(struct work_struct *work)
 	struct sk_buff *skb;
 	int rc;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	skb = pn533_alloc_skb(dev, 2);
 	if (!skb)
 		return;
@@ -1360,8 +1346,6 @@ static int pn533_poll_dep(struct nfc_dev *nfc_dev)
 	u8 *next, nfcid3[NFC_NFCID3_MAXSIZE];
 	u8 passive_data[PASSIVE_DATA_LEN] = {0x00, 0xff, 0xff, 0x00, 0x3};
 
-	dev_dbg(dev->dev, "%s", __func__);
-
 	if (!dev->gb) {
 		dev->gb = nfc_get_local_general_bytes(nfc_dev, &dev->gb_len);
 
@@ -1511,8 +1495,6 @@ static int pn533_poll_complete(struct pn533 *dev, void *arg,
 	struct pn533_poll_modulations *cur_mod;
 	int rc;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	if (IS_ERR(resp)) {
 		rc = PTR_ERR(resp);
 
@@ -1783,8 +1765,6 @@ static int pn533_activate_target_nfcdep(struct pn533 *dev)
 	struct sk_buff *skb;
 	struct sk_buff *resp;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	skb = pn533_alloc_skb(dev, sizeof(u8) * 2); /*TG + Next*/
 	if (!skb)
 		return -ENOMEM;
@@ -1866,8 +1846,6 @@ static int pn533_deactivate_target_complete(struct pn533 *dev, void *arg,
 {
 	int rc = 0;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	if (IS_ERR(resp)) {
 		rc = PTR_ERR(resp);
 
@@ -1892,8 +1870,6 @@ static void pn533_deactivate_target(struct nfc_dev *nfc_dev,
 	struct sk_buff *skb;
 	int rc;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	if (!dev->tgt_active_prot) {
 		nfc_err(dev->dev, "There is no active target\n");
 		return;
@@ -1988,8 +1964,6 @@ static int pn533_dep_link_up(struct nfc_dev *nfc_dev, struct nfc_target *target,
 	u8 *next, *arg, nfcid3[NFC_NFCID3_MAXSIZE];
 	u8 passive_data[PASSIVE_DATA_LEN] = {0x00, 0xff, 0xff, 0x00, 0x3};
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	if (dev->poll_mod_count) {
 		nfc_err(dev->dev,
 			"Cannot bring the DEP link up while polling\n");
@@ -2067,8 +2041,6 @@ static int pn533_dep_link_down(struct nfc_dev *nfc_dev)
 {
 	struct pn533 *dev = nfc_get_drvdata(nfc_dev);
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	pn533_poll_reset_mod_list(dev);
 
 	if (dev->tgt_mode || dev->tgt_active_prot)
@@ -2092,8 +2064,6 @@ static struct sk_buff *pn533_build_response(struct pn533 *dev)
 	struct sk_buff *skb, *tmp, *t;
 	unsigned int skb_len = 0, tmp_len = 0;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	if (skb_queue_empty(&dev->resp_q))
 		return NULL;
 
@@ -2133,8 +2103,6 @@ static int pn533_data_exchange_complete(struct pn533 *dev, void *_arg,
 	int rc = 0;
 	u8 status, ret, mi;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	if (IS_ERR(resp)) {
 		rc = PTR_ERR(resp);
 		goto _error;
@@ -2288,8 +2256,6 @@ static int pn533_transceive(struct nfc_dev *nfc_dev,
 	struct pn533_data_exchange_arg *arg = NULL;
 	int rc;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	if (!dev->tgt_active_prot) {
 		nfc_err(dev->dev,
 			"Can't exchange data if there is no active target\n");
@@ -2356,8 +2322,6 @@ static int pn533_tm_send_complete(struct pn533 *dev, void *arg,
 {
 	u8 status;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	if (IS_ERR(resp))
 		return PTR_ERR(resp);
 
@@ -2388,8 +2352,6 @@ static int pn533_tm_send(struct nfc_dev *nfc_dev, struct sk_buff *skb)
 	struct pn533 *dev = nfc_get_drvdata(nfc_dev);
 	int rc;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	/* let's split in multiple chunks if size's too big */
 	if (skb->len > PN533_CMD_DATAEXCH_DATA_MAXLEN) {
 		rc = pn533_fill_fragment_skbs(dev, skb);
@@ -2426,8 +2388,6 @@ static void pn533_wq_mi_recv(struct work_struct *work)
 	struct sk_buff *skb;
 	int rc;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	skb = pn533_alloc_skb(dev, PN533_CMD_DATAEXCH_HEAD_LEN);
 	if (!skb)
 		goto error;
@@ -2476,8 +2436,6 @@ static void pn533_wq_mi_send(struct work_struct *work)
 	struct sk_buff *skb;
 	int rc;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	/* Grab the first skb in the queue */
 	skb = skb_dequeue(&dev->fragment_skb);
 
@@ -2533,8 +2491,6 @@ static int pn533_set_configuration(struct pn533 *dev, u8 cfgitem, u8 *cfgdata,
 	struct sk_buff *resp;
 	int skb_len;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	skb_len = sizeof(cfgitem) + cfgdata_len; /* cfgitem + cfgdata */
 
 	skb = pn533_alloc_skb(dev, skb_len);
@@ -2580,8 +2536,6 @@ static int pn533_pasori_fw_reset(struct pn533 *dev)
 	struct sk_buff *skb;
 	struct sk_buff *resp;
 
-	dev_dbg(dev->dev, "%s\n", __func__);
-
 	skb = pn533_alloc_skb(dev, sizeof(u8));
 	if (!skb)
 		return -ENOMEM;
diff --git a/drivers/nfc/pn533/uart.c b/drivers/nfc/pn533/uart.c
index a0665d8ea85b..7bdaf8263070 100644
--- a/drivers/nfc/pn533/uart.c
+++ b/drivers/nfc/pn533/uart.c
@@ -319,7 +319,7 @@ static struct serdev_device_driver pn532_uart_driver = {
 	.remove = pn532_uart_remove,
 	.driver = {
 		.name = "pn532_uart",
-		.of_match_table = of_match_ptr(pn532_uart_of_match),
+		.of_match_table = pn532_uart_of_match,
 	},
 };
 
diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c
index 84d2bfabf42b..bd7f7478d189 100644
--- a/drivers/nfc/pn533/usb.c
+++ b/drivers/nfc/pn533/usb.c
@@ -354,8 +354,6 @@ static void pn533_acr122_poweron_rdr_resp(struct urb *urb)
 {
 	struct pn533_acr122_poweron_rdr_arg *arg = urb->context;
 
-	dev_dbg(&urb->dev->dev, "%s\n", __func__);
-
 	print_hex_dump_debug("ACR122 RX: ", DUMP_PREFIX_NONE, 16, 1,
 		       urb->transfer_buffer, urb->transfer_buffer_length,
 		       false);
@@ -375,8 +373,6 @@ static int pn533_acr122_poweron_rdr(struct pn533_usb_phy *phy)
 	void *cntx;
 	struct pn533_acr122_poweron_rdr_arg arg;
 
-	dev_dbg(&phy->udev->dev, "%s\n", __func__);
-
 	buffer = kmemdup(cmd, sizeof(cmd), GFP_KERNEL);
 	if (!buffer)
 		return -ENOMEM;
diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c
index 4ac8cb262559..de59e439c369 100644
--- a/drivers/nfc/pn544/i2c.c
+++ b/drivers/nfc/pn544/i2c.c
@@ -50,7 +50,7 @@ static const struct i2c_device_id pn544_hci_i2c_id_table[] = {
 
 MODULE_DEVICE_TABLE(i2c, pn544_hci_i2c_id_table);
 
-static const struct acpi_device_id pn544_hci_i2c_acpi_match[] = {
+static const struct acpi_device_id pn544_hci_i2c_acpi_match[] __maybe_unused = {
 	{"NXP5440", 0},
 	{}
 };
@@ -241,8 +241,6 @@ static int pn544_hci_i2c_enable(void *phy_id)
 {
 	struct pn544_i2c_phy *phy = phy_id;
 
-	pr_info("%s\n", __func__);
-
 	pn544_hci_i2c_enable_mode(phy, PN544_HCI_MODE);
 
 	phy->powered = 1;
@@ -875,9 +873,6 @@ static int pn544_hci_i2c_probe(struct i2c_client *client,
 	struct pn544_i2c_phy *phy;
 	int r = 0;
 
-	dev_dbg(&client->dev, "%s\n", __func__);
-	dev_dbg(&client->dev, "IRQ: %d\n", client->irq);
-
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
 		nfc_err(&client->dev, "Need I2C_FUNC_I2C\n");
 		return -ENODEV;
@@ -937,8 +932,6 @@ static int pn544_hci_i2c_remove(struct i2c_client *client)
 {
 	struct pn544_i2c_phy *phy = i2c_get_clientdata(client);
 
-	dev_dbg(&client->dev, "%s\n", __func__);
-
 	cancel_work_sync(&phy->fw_work);
 	if (phy->fw_work_state != FW_WORK_STATE_IDLE)
 		pn544_hci_i2c_fw_work_complete(phy, -ENODEV);
@@ -951,7 +944,7 @@ static int pn544_hci_i2c_remove(struct i2c_client *client)
 	return 0;
 }
 
-static const struct of_device_id of_pn544_i2c_match[] = {
+static const struct of_device_id of_pn544_i2c_match[] __maybe_unused = {
 	{ .compatible = "nxp,pn544-i2c", },
 	{},
 };
diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c
index 8e4d355dc3ae..4df926cc37d0 100644
--- a/drivers/nfc/port100.c
+++ b/drivers/nfc/port100.c
@@ -94,7 +94,7 @@ struct port100;
 typedef void (*port100_send_async_complete_t)(struct port100 *dev, void *arg,
 					      struct sk_buff *resp);
 
-/**
+/*
  * Setting sets structure for in_set_rf command
  *
  * @in_*_set_number: Represent the entry indexes in the port-100 RF Base Table.
@@ -145,7 +145,7 @@ static const struct port100_in_rf_setting in_rf_settings[] = {
 };
 
 /**
- * Setting sets structure for tg_set_rf command
+ * struct port100_tg_rf_setting - Setting sets structure for tg_set_rf command
  *
  * @tg_set_number: Represents the entry index in the port-100 RF Base Table.
  *                 This table contains multiple RF setting sets required for RF
diff --git a/drivers/nfc/s3fwrn5/i2c.c b/drivers/nfc/s3fwrn5/i2c.c
index 897394167522..4d1cf1bb55b0 100644
--- a/drivers/nfc/s3fwrn5/i2c.c
+++ b/drivers/nfc/s3fwrn5/i2c.c
@@ -6,6 +6,7 @@
  * Robert Baldyga <r.baldyga@samsung.com>
  */
 
+#include <linux/clk.h>
 #include <linux/i2c.h>
 #include <linux/gpio.h>
 #include <linux/delay.h>
@@ -22,6 +23,7 @@
 struct s3fwrn5_i2c_phy {
 	struct phy_common common;
 	struct i2c_client *i2c_dev;
+	struct clk *clk;
 
 	unsigned int irq_skip:1;
 };
@@ -207,17 +209,40 @@ static int s3fwrn5_i2c_probe(struct i2c_client *client,
 	if (ret < 0)
 		return ret;
 
+	phy->clk = devm_clk_get_optional(&client->dev, NULL);
+	if (IS_ERR(phy->clk))
+		return dev_err_probe(&client->dev, PTR_ERR(phy->clk),
+				     "failed to get clock\n");
+
+	/*
+	 * S3FWRN5 depends on a clock input ("XI" pin) to function properly.
+	 * Depending on the hardware configuration this could be an always-on
+	 * oscillator or some external clock that must be explicitly enabled.
+	 * Make sure the clock is running before starting S3FWRN5.
+	 */
+	ret = clk_prepare_enable(phy->clk);
+	if (ret < 0) {
+		dev_err(&client->dev, "failed to enable clock: %d\n", ret);
+		return ret;
+	}
+
 	ret = s3fwrn5_probe(&phy->common.ndev, phy, &phy->i2c_dev->dev,
 			    &i2c_phy_ops);
 	if (ret < 0)
-		return ret;
+		goto disable_clk;
 
 	ret = devm_request_threaded_irq(&client->dev, phy->i2c_dev->irq, NULL,
 		s3fwrn5_i2c_irq_thread_fn, IRQF_ONESHOT,
 		S3FWRN5_I2C_DRIVER_NAME, phy);
 	if (ret)
-		s3fwrn5_remove(phy->common.ndev);
+		goto s3fwrn5_remove;
 
+	return 0;
+
+s3fwrn5_remove:
+	s3fwrn5_remove(phy->common.ndev);
+disable_clk:
+	clk_disable_unprepare(phy->clk);
 	return ret;
 }
 
@@ -226,6 +251,7 @@ static int s3fwrn5_i2c_remove(struct i2c_client *client)
 	struct s3fwrn5_i2c_phy *phy = i2c_get_clientdata(client);
 
 	s3fwrn5_remove(phy->common.ndev);
+	clk_disable_unprepare(phy->clk);
 
 	return 0;
 }
@@ -236,7 +262,7 @@ static const struct i2c_device_id s3fwrn5_i2c_id_table[] = {
 };
 MODULE_DEVICE_TABLE(i2c, s3fwrn5_i2c_id_table);
 
-static const struct of_device_id of_s3fwrn5_i2c_match[] = {
+static const struct of_device_id of_s3fwrn5_i2c_match[] __maybe_unused = {
 	{ .compatible = "samsung,s3fwrn5-i2c", },
 	{}
 };
diff --git a/drivers/nfc/st-nci/i2c.c b/drivers/nfc/st-nci/i2c.c
index 55d600cd3861..46981405e8b1 100644
--- a/drivers/nfc/st-nci/i2c.c
+++ b/drivers/nfc/st-nci/i2c.c
@@ -206,9 +206,6 @@ static int st_nci_i2c_probe(struct i2c_client *client,
 	struct st_nci_i2c_phy *phy;
 	int r;
 
-	dev_dbg(&client->dev, "%s\n", __func__);
-	dev_dbg(&client->dev, "IRQ: %d\n", client->irq);
-
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
 		nfc_err(&client->dev, "Need I2C_FUNC_I2C\n");
 		return -ENODEV;
@@ -261,8 +258,6 @@ static int st_nci_i2c_remove(struct i2c_client *client)
 {
 	struct st_nci_i2c_phy *phy = i2c_get_clientdata(client);
 
-	dev_dbg(&client->dev, "%s\n", __func__);
-
 	ndlc_remove(phy->ndlc);
 
 	return 0;
@@ -274,14 +269,14 @@ static const struct i2c_device_id st_nci_i2c_id_table[] = {
 };
 MODULE_DEVICE_TABLE(i2c, st_nci_i2c_id_table);
 
-static const struct acpi_device_id st_nci_i2c_acpi_match[] = {
+static const struct acpi_device_id st_nci_i2c_acpi_match[] __maybe_unused = {
 	{"SMO2101"},
 	{"SMO2102"},
 	{}
 };
 MODULE_DEVICE_TABLE(acpi, st_nci_i2c_acpi_match);
 
-static const struct of_device_id of_st_nci_i2c_match[] = {
+static const struct of_device_id of_st_nci_i2c_match[] __maybe_unused = {
 	{ .compatible = "st,st21nfcb-i2c", },
 	{ .compatible = "st,st21nfcb_i2c", },
 	{ .compatible = "st,st21nfcc-i2c", },
diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c
index 1cba8f69d3ae..5fd89f72969d 100644
--- a/drivers/nfc/st-nci/se.c
+++ b/drivers/nfc/st-nci/se.c
@@ -470,8 +470,6 @@ int st_nci_disable_se(struct nci_dev *ndev, u32 se_idx)
 {
 	int r;
 
-	pr_debug("st_nci_disable_se\n");
-
 	/*
 	 * According to upper layer, se_idx == NFC_SE_UICC when
 	 * info->se_info.se_status->is_uicc_enable is true should never happen
@@ -496,8 +494,6 @@ int st_nci_enable_se(struct nci_dev *ndev, u32 se_idx)
 {
 	int r;
 
-	pr_debug("st_nci_enable_se\n");
-
 	/*
 	 * According to upper layer, se_idx == NFC_SE_UICC when
 	 * info->se_info.se_status->is_uicc_enable is true should never happen.
@@ -534,10 +530,8 @@ static int st_nci_hci_network_init(struct nci_dev *ndev)
 	dest_params =
 		kzalloc(sizeof(struct core_conn_create_dest_spec_params) +
 			sizeof(struct dest_spec_params), GFP_KERNEL);
-	if (dest_params == NULL) {
-		r = -ENOMEM;
-		goto exit;
-	}
+	if (dest_params == NULL)
+		return -ENOMEM;
 
 	dest_params->type = NCI_DESTINATION_SPECIFIC_PARAM_NFCEE_TYPE;
 	dest_params->length = sizeof(struct dest_spec_params);
@@ -594,8 +588,6 @@ static int st_nci_hci_network_init(struct nci_dev *ndev)
 
 free_dest_params:
 	kfree(dest_params);
-
-exit:
 	return r;
 }
 
@@ -606,8 +598,6 @@ int st_nci_discover_se(struct nci_dev *ndev)
 	int se_count = 0;
 	struct st_nci_info *info = nci_get_drvdata(ndev);
 
-	pr_debug("st_nci_discover_se\n");
-
 	r = st_nci_hci_network_init(ndev);
 	if (r != 0)
 		return r;
diff --git a/drivers/nfc/st-nci/spi.c b/drivers/nfc/st-nci/spi.c
index 09df6ea65840..250d56f204c3 100644
--- a/drivers/nfc/st-nci/spi.c
+++ b/drivers/nfc/st-nci/spi.c
@@ -216,9 +216,6 @@ static int st_nci_spi_probe(struct spi_device *dev)
 	struct st_nci_spi_phy *phy;
 	int r;
 
-	dev_dbg(&dev->dev, "%s\n", __func__);
-	dev_dbg(&dev->dev, "IRQ: %d\n", dev->irq);
-
 	/* Check SPI platform functionnalities */
 	if (!dev) {
 		pr_debug("%s: dev is NULL. Device is not accessible.\n",
@@ -274,8 +271,6 @@ static int st_nci_spi_remove(struct spi_device *dev)
 {
 	struct st_nci_spi_phy *phy = spi_get_drvdata(dev);
 
-	dev_dbg(&dev->dev, "%s\n", __func__);
-
 	ndlc_remove(phy->ndlc);
 
 	return 0;
@@ -287,13 +282,13 @@ static struct spi_device_id st_nci_spi_id_table[] = {
 };
 MODULE_DEVICE_TABLE(spi, st_nci_spi_id_table);
 
-static const struct acpi_device_id st_nci_spi_acpi_match[] = {
+static const struct acpi_device_id st_nci_spi_acpi_match[] __maybe_unused = {
 	{"SMO2101", 0},
 	{}
 };
 MODULE_DEVICE_TABLE(acpi, st_nci_spi_acpi_match);
 
-static const struct of_device_id of_st_nci_spi_match[] = {
+static const struct of_device_id of_st_nci_spi_match[] __maybe_unused = {
 	{ .compatible = "st,st21nfcb-spi", },
 	{}
 };
diff --git a/drivers/nfc/st-nci/vendor_cmds.c b/drivers/nfc/st-nci/vendor_cmds.c
index c6a9d30a4dba..94b600029a2a 100644
--- a/drivers/nfc/st-nci/vendor_cmds.c
+++ b/drivers/nfc/st-nci/vendor_cmds.c
@@ -98,7 +98,7 @@ static int st_nci_hci_dm_get_info(struct nfc_dev *dev, void *data,
 	r = nci_hci_send_cmd(ndev, ST_NCI_DEVICE_MGNT_GATE, ST_NCI_HCI_DM_GETINFO,
 			     data, data_len, &skb);
 	if (r)
-		goto exit;
+		return r;
 
 	msg = nfc_vendor_cmd_alloc_reply_skb(dev, ST_NCI_VENDOR_OUI,
 					     HCI_DM_GET_INFO, skb->len);
@@ -117,7 +117,6 @@ static int st_nci_hci_dm_get_info(struct nfc_dev *dev, void *data,
 
 free_skb:
 	kfree_skb(skb);
-exit:
 	return r;
 }
 
@@ -131,7 +130,7 @@ static int st_nci_hci_dm_get_data(struct nfc_dev *dev, void *data,
 	r = nci_hci_send_cmd(ndev, ST_NCI_DEVICE_MGNT_GATE, ST_NCI_HCI_DM_GETDATA,
 			     data, data_len, &skb);
 	if (r)
-		goto exit;
+		return r;
 
 	msg = nfc_vendor_cmd_alloc_reply_skb(dev, ST_NCI_VENDOR_OUI,
 					     HCI_DM_GET_DATA, skb->len);
@@ -150,7 +149,6 @@ static int st_nci_hci_dm_get_data(struct nfc_dev *dev, void *data,
 
 free_skb:
 	kfree_skb(skb);
-exit:
 	return r;
 }
 
@@ -216,7 +214,7 @@ static int st_nci_hci_get_param(struct nfc_dev *dev, void *data,
 
 	r = nci_hci_get_param(ndev, param->gate, param->data, &skb);
 	if (r)
-		goto exit;
+		return r;
 
 	msg = nfc_vendor_cmd_alloc_reply_skb(dev, ST_NCI_VENDOR_OUI,
 					     HCI_GET_PARAM, skb->len);
@@ -235,7 +233,6 @@ static int st_nci_hci_get_param(struct nfc_dev *dev, void *data,
 
 free_skb:
 	kfree_skb(skb);
-exit:
 	return r;
 }
 
@@ -262,7 +259,7 @@ static int st_nci_hci_dm_vdc_measurement_value(struct nfc_dev *dev, void *data,
 			     ST_NCI_HCI_DM_VDC_MEASUREMENT_VALUE,
 			     data, data_len, &skb);
 	if (r)
-		goto exit;
+		return r;
 
 	msg = nfc_vendor_cmd_alloc_reply_skb(dev, ST_NCI_VENDOR_OUI,
 				HCI_DM_VDC_MEASUREMENT_VALUE, skb->len);
@@ -281,7 +278,6 @@ static int st_nci_hci_dm_vdc_measurement_value(struct nfc_dev *dev, void *data,
 
 free_skb:
 	kfree_skb(skb);
-exit:
 	return r;
 }
 
@@ -299,7 +295,7 @@ static int st_nci_hci_dm_vdc_value_comparison(struct nfc_dev *dev, void *data,
 			     ST_NCI_HCI_DM_VDC_VALUE_COMPARISON,
 			     data, data_len, &skb);
 	if (r)
-		goto exit;
+		return r;
 
 	msg = nfc_vendor_cmd_alloc_reply_skb(dev, ST_NCI_VENDOR_OUI,
 					HCI_DM_VDC_VALUE_COMPARISON, skb->len);
@@ -318,7 +314,6 @@ static int st_nci_hci_dm_vdc_value_comparison(struct nfc_dev *dev, void *data,
 
 free_skb:
 	kfree_skb(skb);
-exit:
 	return r;
 }
 
diff --git a/drivers/nfc/st21nfca/dep.c b/drivers/nfc/st21nfca/dep.c
index 8874d605b14f..1ec651e31064 100644
--- a/drivers/nfc/st21nfca/dep.c
+++ b/drivers/nfc/st21nfca/dep.c
@@ -196,38 +196,29 @@ static int st21nfca_tm_recv_atr_req(struct nfc_hci_dev *hdev,
 
 	skb_trim(skb, skb->len - 1);
 
-	if (!skb->len) {
-		r = -EIO;
-		goto exit;
-	}
+	if (!skb->len)
+		return -EIO;
 
-	if (skb->len < ST21NFCA_ATR_REQ_MIN_SIZE) {
-		r = -EPROTO;
-		goto exit;
-	}
+	if (skb->len < ST21NFCA_ATR_REQ_MIN_SIZE)
+		return -EPROTO;
 
 	atr_req = (struct st21nfca_atr_req *)skb->data;
 
-	if (atr_req->length < sizeof(struct st21nfca_atr_req)) {
-		r = -EPROTO;
-		goto exit;
-	}
+	if (atr_req->length < sizeof(struct st21nfca_atr_req))
+		return -EPROTO;
 
 	r = st21nfca_tm_send_atr_res(hdev, atr_req);
 	if (r)
-		goto exit;
+		return r;
 
 	gb_len = skb->len - sizeof(struct st21nfca_atr_req);
 
 	r = nfc_tm_activated(hdev->ndev, NFC_PROTO_NFC_DEP_MASK,
 			      NFC_COMM_PASSIVE, atr_req->gbi, gb_len);
 	if (r)
-		goto exit;
-
-	r = 0;
+		return r;
 
-exit:
-	return r;
+	return 0;
 }
 
 static int st21nfca_tm_send_psl_res(struct nfc_hci_dev *hdev,
@@ -280,25 +271,18 @@ static int st21nfca_tm_recv_psl_req(struct nfc_hci_dev *hdev,
 				    struct sk_buff *skb)
 {
 	struct st21nfca_psl_req *psl_req;
-	int r;
 
 	skb_trim(skb, skb->len - 1);
 
-	if (!skb->len) {
-		r = -EIO;
-		goto exit;
-	}
+	if (!skb->len)
+		return -EIO;
 
 	psl_req = (struct st21nfca_psl_req *)skb->data;
 
-	if (skb->len < sizeof(struct st21nfca_psl_req)) {
-		r = -EIO;
-		goto exit;
-	}
+	if (skb->len < sizeof(struct st21nfca_psl_req))
+		return -EIO;
 
-	r = st21nfca_tm_send_psl_res(hdev, psl_req);
-exit:
-	return r;
+	return st21nfca_tm_send_psl_res(hdev, psl_req);
 }
 
 int st21nfca_tm_send_dep_res(struct nfc_hci_dev *hdev, struct sk_buff *skb)
@@ -324,7 +308,6 @@ static int st21nfca_tm_recv_dep_req(struct nfc_hci_dev *hdev,
 {
 	struct st21nfca_dep_req_res *dep_req;
 	u8 size;
-	int r;
 	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
 
 	skb_trim(skb, skb->len - 1);
@@ -332,20 +315,16 @@ static int st21nfca_tm_recv_dep_req(struct nfc_hci_dev *hdev,
 	size = 4;
 
 	dep_req = (struct st21nfca_dep_req_res *)skb->data;
-	if (skb->len < size) {
-		r = -EIO;
-		goto exit;
-	}
+	if (skb->len < size)
+		return -EIO;
 
 	if (ST21NFCA_NFC_DEP_DID_BIT_SET(dep_req->pfb))
 		size++;
 	if (ST21NFCA_NFC_DEP_NAD_BIT_SET(dep_req->pfb))
 		size++;
 
-	if (skb->len < size) {
-		r = -EIO;
-		goto exit;
-	}
+	if (skb->len < size)
+		return -EIO;
 
 	/* Receiving DEP_REQ - Decoding */
 	switch (ST21NFCA_NFC_DEP_PFB_TYPE(dep_req->pfb)) {
@@ -364,8 +343,6 @@ static int st21nfca_tm_recv_dep_req(struct nfc_hci_dev *hdev,
 	skb_pull(skb, size);
 
 	return nfc_tm_data_received(hdev->ndev, skb);
-exit:
-	return r;
 }
 
 static int st21nfca_tm_event_send_data(struct nfc_hci_dev *hdev,
diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c
index 23ed11f91213..7a9f4d71707e 100644
--- a/drivers/nfc/st21nfca/i2c.c
+++ b/drivers/nfc/st21nfca/i2c.c
@@ -502,9 +502,6 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
 	struct st21nfca_i2c_phy *phy;
 	int r;
 
-	dev_dbg(&client->dev, "%s\n", __func__);
-	dev_dbg(&client->dev, "IRQ: %d\n", client->irq);
-
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
 		nfc_err(&client->dev, "Need I2C_FUNC_I2C\n");
 		return -ENODEV;
@@ -568,8 +565,6 @@ static int st21nfca_hci_i2c_remove(struct i2c_client *client)
 {
 	struct st21nfca_i2c_phy *phy = i2c_get_clientdata(client);
 
-	dev_dbg(&client->dev, "%s\n", __func__);
-
 	st21nfca_hci_remove(phy->hdev);
 
 	if (phy->powered)
@@ -584,13 +579,13 @@ static const struct i2c_device_id st21nfca_hci_i2c_id_table[] = {
 };
 MODULE_DEVICE_TABLE(i2c, st21nfca_hci_i2c_id_table);
 
-static const struct acpi_device_id st21nfca_hci_i2c_acpi_match[] = {
+static const struct acpi_device_id st21nfca_hci_i2c_acpi_match[] __maybe_unused = {
 	{"SMO2100", 0},
 	{}
 };
 MODULE_DEVICE_TABLE(acpi, st21nfca_hci_i2c_acpi_match);
 
-static const struct of_device_id of_st21nfca_i2c_match[] = {
+static const struct of_device_id of_st21nfca_i2c_match[] __maybe_unused = {
 	{ .compatible = "st,st21nfca-i2c", },
 	{ .compatible = "st,st21nfca_i2c", },
 	{}
diff --git a/drivers/nfc/st95hf/core.c b/drivers/nfc/st95hf/core.c
index 457854765983..2dc788c363fd 100644
--- a/drivers/nfc/st95hf/core.c
+++ b/drivers/nfc/st95hf/core.c
@@ -926,10 +926,8 @@ static int st95hf_in_send_cmd(struct nfc_digital_dev *ddev,
 	int len_data_to_tag = 0;
 
 	skb_resp = nfc_alloc_recv_skb(MAX_RESPONSE_BUFFER_SIZE, GFP_KERNEL);
-	if (!skb_resp) {
-		rc = -ENOMEM;
-		goto error;
-	}
+	if (!skb_resp)
+		return -ENOMEM;
 
 	switch (stcontext->current_rf_tech) {
 	case NFC_DIGITAL_RF_TECH_106A:
@@ -986,7 +984,6 @@ static int st95hf_in_send_cmd(struct nfc_digital_dev *ddev,
 
 free_skb_resp:
 	kfree_skb(skb_resp);
-error:
 	return rc;
 }
 
@@ -1059,9 +1056,9 @@ static const struct spi_device_id st95hf_id[] = {
 };
 MODULE_DEVICE_TABLE(spi, st95hf_id);
 
-static const struct of_device_id st95hf_spi_of_match[] = {
-        { .compatible = "st,st95hf" },
-        { },
+static const struct of_device_id st95hf_spi_of_match[] __maybe_unused = {
+	{ .compatible = "st,st95hf" },
+	{},
 };
 MODULE_DEVICE_TABLE(of, st95hf_spi_of_match);
 
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index 21c4c34c52d8..841d8900504d 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -63,27 +63,6 @@ static void enqueue_external_timestamp(struct timestamp_event_queue *queue,
 	spin_unlock_irqrestore(&queue->lock, flags);
 }
 
-long scaled_ppm_to_ppb(long ppm)
-{
-	/*
-	 * The 'freq' field in the 'struct timex' is in parts per
-	 * million, but with a 16 bit binary fractional field.
-	 *
-	 * We want to calculate
-	 *
-	 *    ppb = scaled_ppm * 1000 / 2^16
-	 *
-	 * which simplifies to
-	 *
-	 *    ppb = scaled_ppm * 125 / 2^13
-	 */
-	s64 ppb = 1 + ppm;
-	ppb *= 125;
-	ppb >>= 13;
-	return (long) ppb;
-}
-EXPORT_SYMBOL(scaled_ppm_to_ppb);
-
 /* posix clock implementation */
 
 static int ptp_clock_getres(struct posix_clock *pc, struct timespec64 *tp)
diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c
index e5daee4f9373..c1404d3dae2c 100644
--- a/drivers/rpmsg/rpmsg_core.c
+++ b/drivers/rpmsg/rpmsg_core.c
@@ -459,8 +459,10 @@ static int rpmsg_dev_match(struct device *dev, struct device_driver *drv)
 
 	if (ids)
 		for (i = 0; ids[i].name[0]; i++)
-			if (rpmsg_id_match(rpdev, &ids[i]))
+			if (rpmsg_id_match(rpdev, &ids[i])) {
+				rpdev->id.driver_data = ids[i].driver_data;
 				return 1;
+			}
 
 	return of_driver_match_device(dev, drv);
 }
diff --git a/drivers/s390/net/netiucv.c b/drivers/s390/net/netiucv.c
index 260860cf3aa1..5a0c2f07a3a2 100644
--- a/drivers/s390/net/netiucv.c
+++ b/drivers/s390/net/netiucv.c
@@ -118,24 +118,6 @@ static struct device_driver netiucv_driver = {
 	.bus  = &iucv_bus,
 };
 
-static int netiucv_callback_connreq(struct iucv_path *, u8 *, u8 *);
-static void netiucv_callback_connack(struct iucv_path *, u8 *);
-static void netiucv_callback_connrej(struct iucv_path *, u8 *);
-static void netiucv_callback_connsusp(struct iucv_path *, u8 *);
-static void netiucv_callback_connres(struct iucv_path *, u8 *);
-static void netiucv_callback_rx(struct iucv_path *, struct iucv_message *);
-static void netiucv_callback_txdone(struct iucv_path *, struct iucv_message *);
-
-static struct iucv_handler netiucv_handler = {
-	.path_pending	  = netiucv_callback_connreq,
-	.path_complete	  = netiucv_callback_connack,
-	.path_severed	  = netiucv_callback_connrej,
-	.path_quiesced	  = netiucv_callback_connsusp,
-	.path_resumed	  = netiucv_callback_connres,
-	.message_pending  = netiucv_callback_rx,
-	.message_complete = netiucv_callback_txdone
-};
-
 /**
  * Per connection profiling data
  */
@@ -774,6 +756,16 @@ static void conn_action_txdone(fsm_instance *fi, int event, void *arg)
 	}
 }
 
+static struct iucv_handler netiucv_handler = {
+	.path_pending	  = netiucv_callback_connreq,
+	.path_complete	  = netiucv_callback_connack,
+	.path_severed	  = netiucv_callback_connrej,
+	.path_quiesced	  = netiucv_callback_connsusp,
+	.path_resumed	  = netiucv_callback_connres,
+	.message_pending  = netiucv_callback_rx,
+	.message_complete = netiucv_callback_txdone,
+};
+
 static void conn_action_connaccept(fsm_instance *fi, int event, void *arg)
 {
 	struct iucv_event *ev = arg;
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index fd9b869d278e..f4d554ea0c93 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -417,13 +417,17 @@ enum qeth_qdio_out_buffer_state {
 	QETH_QDIO_BUF_EMPTY,
 	/* Filled by driver; owned by hardware in order to be sent. */
 	QETH_QDIO_BUF_PRIMED,
-	/* Discovered by the TX completion code: */
-	QETH_QDIO_BUF_PENDING,
-	/* Finished by the TX completion code: */
-	QETH_QDIO_BUF_NEED_QAOB,
-	/* Received QAOB notification on CQ: */
-	QETH_QDIO_BUF_QAOB_OK,
-	QETH_QDIO_BUF_QAOB_ERROR,
+};
+
+enum qeth_qaob_state {
+	QETH_QAOB_ISSUED,
+	QETH_QAOB_PENDING,
+	QETH_QAOB_DONE,
+};
+
+struct qeth_qaob_priv1 {
+	unsigned int state;
+	u8 queue_no;
 };
 
 struct qeth_qdio_out_buffer {
@@ -433,9 +437,8 @@ struct qeth_qdio_out_buffer {
 	unsigned int frames;
 	unsigned int bytes;
 	struct sk_buff_head skb_list;
-	int is_header[QDIO_MAX_ELEMENTS_PER_BUFFER];
+	DECLARE_BITMAP(from_kmem_cache, QDIO_MAX_ELEMENTS_PER_BUFFER);
 
-	struct qeth_qdio_out_q *q;
 	struct list_head list_entry;
 	struct qaob *aob;
 };
@@ -483,6 +486,7 @@ struct qeth_out_q_stats {
 	u64 stopped;
 	u64 doorbell;
 	u64 coal_frames;
+	u64 completion_irq;
 	u64 completion_yield;
 	u64 completion_timer;
 
@@ -526,6 +530,7 @@ struct qeth_qdio_out_q {
 
 	unsigned int coalesce_usecs;
 	unsigned int max_coalesced_frames;
+	unsigned int rescan_usecs;
 };
 
 #define qeth_for_each_output_queue(card, q, i)		\
@@ -612,7 +617,6 @@ struct qeth_channel {
 	struct ccw_device *ccwdev;
 	struct qeth_cmd_buffer *active_cmd;
 	enum qeth_channel_states state;
-	atomic_t irq_pending;
 };
 
 struct qeth_reply {
@@ -662,11 +666,6 @@ static inline struct ccw1 *__ccw_from_cmd(struct qeth_cmd_buffer *iob)
 	return (struct ccw1 *)(iob->data + ALIGN(iob->length, 8));
 }
 
-static inline bool qeth_trylock_channel(struct qeth_channel *channel)
-{
-	return atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0;
-}
-
 /**
  *  OSA card related definitions
  */
@@ -886,13 +885,24 @@ static inline bool qeth_card_hw_is_reachable(struct qeth_card *card)
 	return card->state == CARD_STATE_SOFTSETUP;
 }
 
+static inline bool qeth_use_tx_irqs(struct qeth_card *card)
+{
+	return !IS_IQD(card);
+}
+
 static inline void qeth_unlock_channel(struct qeth_card *card,
 				       struct qeth_channel *channel)
 {
-	atomic_set(&channel->irq_pending, 0);
+	xchg(&channel->active_cmd, NULL);
 	wake_up(&card->wait_q);
 }
 
+static inline bool qeth_trylock_channel(struct qeth_channel *channel,
+					struct qeth_cmd_buffer *cmd)
+{
+	return cmpxchg(&channel->active_cmd, NULL, cmd) == NULL;
+}
+
 struct qeth_trap_id {
 	__u16 lparnr;
 	char vmname[8];
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index a1f08e9aa064..62f88ccbd03f 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -70,9 +70,6 @@ static void qeth_issue_next_read_cb(struct qeth_card *card,
 				    unsigned int data_length);
 static int qeth_qdio_establish(struct qeth_card *);
 static void qeth_free_qdio_queues(struct qeth_card *card);
-static void qeth_notify_skbs(struct qeth_qdio_out_q *queue,
-		struct qeth_qdio_out_buffer *buf,
-		enum iucv_tx_notify notification);
 
 static void qeth_close_dev_handler(struct work_struct *work)
 {
@@ -434,65 +431,6 @@ static enum iucv_tx_notify qeth_compute_cq_notification(int sbalf15,
 	return n;
 }
 
-static void qeth_qdio_handle_aob(struct qeth_card *card,
-				 unsigned long phys_aob_addr)
-{
-	enum qeth_qdio_out_buffer_state new_state = QETH_QDIO_BUF_QAOB_OK;
-	struct qaob *aob;
-	struct qeth_qdio_out_buffer *buffer;
-	enum iucv_tx_notify notification;
-	struct qeth_qdio_out_q *queue;
-	unsigned int i;
-
-	aob = (struct qaob *) phys_to_virt(phys_aob_addr);
-	QETH_CARD_TEXT(card, 5, "haob");
-	QETH_CARD_TEXT_(card, 5, "%lx", phys_aob_addr);
-	buffer = (struct qeth_qdio_out_buffer *) aob->user1;
-	QETH_CARD_TEXT_(card, 5, "%lx", aob->user1);
-
-	if (aob->aorc) {
-		QETH_CARD_TEXT_(card, 2, "aorc%02X", aob->aorc);
-		new_state = QETH_QDIO_BUF_QAOB_ERROR;
-	}
-
-	switch (atomic_xchg(&buffer->state, new_state)) {
-	case QETH_QDIO_BUF_PRIMED:
-		/* Faster than TX completion code, let it handle the async
-		 * completion for us. It will also recycle the QAOB.
-		 */
-		break;
-	case QETH_QDIO_BUF_PENDING:
-		/* TX completion code is active and will handle the async
-		 * completion for us. It will also recycle the QAOB.
-		 */
-		break;
-	case QETH_QDIO_BUF_NEED_QAOB:
-		/* TX completion code is already finished. */
-		notification = qeth_compute_cq_notification(aob->aorc, 1);
-		qeth_notify_skbs(buffer->q, buffer, notification);
-
-		/* Free dangling allocations. The attached skbs are handled by
-		 * qeth_tx_complete_pending_bufs(), and so is the QAOB.
-		 */
-		for (i = 0;
-		     i < aob->sb_count && i < QETH_MAX_BUFFER_ELEMENTS(card);
-		     i++) {
-			void *data = phys_to_virt(aob->sba[i]);
-
-			if (data && buffer->is_header[i])
-				kmem_cache_free(qeth_core_header_cache, data);
-			buffer->is_header[i] = 0;
-		}
-
-		queue = buffer->q;
-		atomic_set(&buffer->state, QETH_QDIO_BUF_EMPTY);
-		napi_schedule(&queue->napi);
-		break;
-	default:
-		WARN_ON_ONCE(1);
-	}
-}
-
 static void qeth_setup_ccw(struct ccw1 *ccw, u8 cmd_code, u8 flags, u32 len,
 			   void *data)
 {
@@ -1268,7 +1206,6 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
 		iob = (struct qeth_cmd_buffer *) (addr_t)intparm;
 	}
 
-	channel->active_cmd = NULL;
 	qeth_unlock_channel(card, channel);
 
 	rc = qeth_check_irb_error(card, cdev, irb);
@@ -1353,10 +1290,10 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *q,
 	}
 }
 
-static void qeth_tx_complete_buf(struct qeth_qdio_out_buffer *buf, bool error,
+static void qeth_tx_complete_buf(struct qeth_qdio_out_q *queue,
+				 struct qeth_qdio_out_buffer *buf, bool error,
 				 int budget)
 {
-	struct qeth_qdio_out_q *queue = buf->q;
 	struct sk_buff *skb;
 
 	/* Empty buffer? */
@@ -1400,17 +1337,18 @@ static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
 	int i;
 
 	/* is PCI flag set on buffer? */
-	if (buf->buffer->element[0].sflags & SBAL_SFLAGS0_PCI_REQ)
+	if (buf->buffer->element[0].sflags & SBAL_SFLAGS0_PCI_REQ) {
 		atomic_dec(&queue->set_pci_flags_count);
+		QETH_TXQ_STAT_INC(queue, completion_irq);
+	}
 
-	qeth_tx_complete_buf(buf, error, budget);
+	qeth_tx_complete_buf(queue, buf, error, budget);
 
 	for (i = 0; i < queue->max_elements; ++i) {
 		void *data = phys_to_virt(buf->buffer->element[i].addr);
 
-		if (data && buf->is_header[i])
+		if (__test_and_clear_bit(i, buf->from_kmem_cache) && data)
 			kmem_cache_free(qeth_core_header_cache, data);
-		buf->is_header[i] = 0;
 	}
 
 	qeth_scrub_qdio_buffer(buf->buffer, queue->max_elements);
@@ -1434,14 +1372,30 @@ static void qeth_tx_complete_pending_bufs(struct qeth_card *card,
 	struct qeth_qdio_out_buffer *buf, *tmp;
 
 	list_for_each_entry_safe(buf, tmp, &queue->pending_bufs, list_entry) {
-		if (drain || atomic_read(&buf->state) == QETH_QDIO_BUF_EMPTY) {
+		struct qeth_qaob_priv1 *priv;
+		struct qaob *aob = buf->aob;
+		enum iucv_tx_notify notify;
+		unsigned int i;
+
+		priv = (struct qeth_qaob_priv1 *)&aob->user1;
+		if (drain || READ_ONCE(priv->state) == QETH_QAOB_DONE) {
 			QETH_CARD_TEXT(card, 5, "fp");
 			QETH_CARD_TEXT_(card, 5, "%lx", (long) buf);
 
-			if (drain)
-				qeth_notify_skbs(queue, buf,
-						 TX_NOTIFY_GENERALERROR);
-			qeth_tx_complete_buf(buf, drain, budget);
+			notify = drain ? TX_NOTIFY_GENERALERROR :
+					 qeth_compute_cq_notification(aob->aorc, 1);
+			qeth_notify_skbs(queue, buf, notify);
+			qeth_tx_complete_buf(queue, buf, drain, budget);
+
+			for (i = 0;
+			     i < aob->sb_count && i < queue->max_elements;
+			     i++) {
+				void *data = phys_to_virt(aob->sba[i]);
+
+				if (test_bit(i, buf->from_kmem_cache) && data)
+					kmem_cache_free(qeth_core_header_cache,
+							data);
+			}
 
 			list_del(&buf->list_entry);
 			qeth_free_out_buf(buf);
@@ -1713,11 +1667,10 @@ static int qeth_stop_channel(struct qeth_channel *channel)
 	rc = ccw_device_set_offline(cdev);
 
 	spin_lock_irq(get_ccwdev_lock(cdev));
-	if (channel->active_cmd) {
+	if (channel->active_cmd)
 		dev_err(&cdev->dev, "Stopped channel while cmd %px was still active\n",
 			channel->active_cmd);
-		channel->active_cmd = NULL;
-	}
+
 	cdev->handler = NULL;
 	spin_unlock_irq(get_ccwdev_lock(cdev));
 
@@ -1730,7 +1683,7 @@ static int qeth_start_channel(struct qeth_channel *channel)
 	int rc;
 
 	channel->state = CH_STATE_DOWN;
-	atomic_set(&channel->irq_pending, 0);
+	xchg(&channel->active_cmd, NULL);
 
 	spin_lock_irq(get_ccwdev_lock(cdev));
 	cdev->handler = qeth_irq;
@@ -2037,7 +1990,7 @@ static int qeth_send_control_data(struct qeth_card *card,
 	reply->param = reply_param;
 
 	timeout = wait_event_interruptible_timeout(card->wait_q,
-						   qeth_trylock_channel(channel),
+						   qeth_trylock_channel(channel, iob),
 						   timeout);
 	if (timeout <= 0) {
 		qeth_put_cmd(iob);
@@ -2057,8 +2010,6 @@ static int qeth_send_control_data(struct qeth_card *card,
 	spin_lock_irq(get_ccwdev_lock(channel->ccwdev));
 	rc = ccw_device_start_timeout(channel->ccwdev, __ccw_from_cmd(iob),
 				      (addr_t) iob, 0, 0, timeout);
-	if (!rc)
-		channel->active_cmd = iob;
 	spin_unlock_irq(get_ccwdev_lock(channel->ccwdev));
 	if (rc) {
 		QETH_DBF_MESSAGE(2, "qeth_send_control_data on device %x: ccw_device_start rc = %i\n",
@@ -2578,7 +2529,6 @@ static int qeth_alloc_out_buf(struct qeth_qdio_out_q *q, unsigned int bidx,
 	newbuf->buffer = q->qdio_bufs[bidx];
 	skb_queue_head_init(&newbuf->skb_list);
 	lockdep_set_class(&newbuf->skb_list.lock, &qdio_out_skb_queue_key);
-	newbuf->q = q;
 	atomic_set(&newbuf->state, QETH_QDIO_BUF_EMPTY);
 	q->bufs[bidx] = newbuf;
 	return 0;
@@ -2663,8 +2613,15 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card)
 		INIT_LIST_HEAD(&queue->pending_bufs);
 		spin_lock_init(&queue->lock);
 		timer_setup(&queue->timer, qeth_tx_completion_timer, 0);
-		queue->coalesce_usecs = QETH_TX_COALESCE_USECS;
-		queue->max_coalesced_frames = QETH_TX_MAX_COALESCED_FRAMES;
+		if (IS_IQD(card)) {
+			queue->coalesce_usecs = QETH_TX_COALESCE_USECS;
+			queue->max_coalesced_frames = QETH_TX_MAX_COALESCED_FRAMES;
+			queue->rescan_usecs = QETH_TX_TIMER_USECS;
+		} else {
+			queue->coalesce_usecs = USEC_PER_SEC;
+			queue->max_coalesced_frames = 0;
+			queue->rescan_usecs = 10 * USEC_PER_SEC;
+		}
 		queue->priority = QETH_QIB_PQUE_PRIO_DEFAULT;
 	}
 
@@ -3601,8 +3558,8 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
 			       int count)
 {
 	struct qeth_qdio_out_buffer *buf = queue->bufs[index];
-	unsigned int qdio_flags = QDIO_FLAG_SYNC_OUTPUT;
 	struct qeth_card *card = queue->card;
+	unsigned int frames, usecs;
 	struct qaob *aob = NULL;
 	int rc;
 	int i;
@@ -3629,8 +3586,12 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
 			if (!buf->aob)
 				buf->aob = qdio_allocate_aob();
 			if (buf->aob) {
+				struct qeth_qaob_priv1 *priv;
+
 				aob = buf->aob;
-				aob->user1 = (u64) buf;
+				priv = (struct qeth_qaob_priv1 *)&aob->user1;
+				priv->state = QETH_QAOB_ISSUED;
+				priv->queue_no = queue->queue_no;
 			}
 		}
 	} else {
@@ -3658,14 +3619,11 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
 				buf->buffer->element[0].sflags |= SBAL_SFLAGS0_PCI_REQ;
 			}
 		}
-
-		if (atomic_read(&queue->set_pci_flags_count))
-			qdio_flags |= QDIO_FLAG_PCI_OUT;
 	}
 
 	QETH_TXQ_STAT_INC(queue, doorbell);
-	rc = do_QDIO(CARD_DDEV(card), qdio_flags, queue->queue_no, index, count,
-		     aob);
+	rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_OUTPUT, queue->queue_no,
+		     index, count, aob);
 
 	switch (rc) {
 	case 0:
@@ -3673,17 +3631,20 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
 		/* ignore temporary SIGA errors without busy condition */
 
 		/* Fake the TX completion interrupt: */
-		if (IS_IQD(card)) {
-			unsigned int frames = READ_ONCE(queue->max_coalesced_frames);
-			unsigned int usecs = READ_ONCE(queue->coalesce_usecs);
+		frames = READ_ONCE(queue->max_coalesced_frames);
+		usecs = READ_ONCE(queue->coalesce_usecs);
 
-			if (frames && queue->coalesced_frames >= frames) {
-				napi_schedule(&queue->napi);
-				queue->coalesced_frames = 0;
-				QETH_TXQ_STAT_INC(queue, coal_frames);
-			} else if (usecs) {
-				qeth_tx_arm_timer(queue, usecs);
-			}
+		if (frames && queue->coalesced_frames >= frames) {
+			napi_schedule(&queue->napi);
+			queue->coalesced_frames = 0;
+			QETH_TXQ_STAT_INC(queue, coal_frames);
+		} else if (qeth_use_tx_irqs(card) &&
+			   atomic_read(&queue->used_buffers) >= 32) {
+			/* Old behaviour carried over from the qdio layer: */
+			napi_schedule(&queue->napi);
+			QETH_TXQ_STAT_INC(queue, coal_frames);
+		} else if (usecs) {
+			qeth_tx_arm_timer(queue, usecs);
 		}
 
 		break;
@@ -3769,6 +3730,18 @@ out:
 }
 EXPORT_SYMBOL_GPL(qeth_configure_cq);
 
+static void qeth_qdio_handle_aob(struct qeth_card *card, struct qaob *aob)
+{
+	struct qeth_qaob_priv1 *priv = (struct qeth_qaob_priv1 *)&aob->user1;
+	unsigned int queue_no = priv->queue_no;
+
+	BUILD_BUG_ON(sizeof(*priv) > ARRAY_SIZE(aob->user1));
+
+	if (xchg(&priv->state, QETH_QAOB_DONE) == QETH_QAOB_PENDING &&
+	    queue_no < card->qdio.no_out_queues)
+		napi_schedule(&card->qdio.out_qs[queue_no]->napi);
+}
+
 static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err,
 				 unsigned int queue, int first_element,
 				 int count)
@@ -3795,7 +3768,7 @@ static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err,
 		       buffer->element[e].addr) {
 			unsigned long phys_aob_addr = buffer->element[e].addr;
 
-			qeth_qdio_handle_aob(card, phys_aob_addr);
+			qeth_qdio_handle_aob(card, phys_to_virt(phys_aob_addr));
 			++e;
 		}
 		qeth_scrub_qdio_buffer(buffer, QDIO_MAX_ELEMENTS_PER_BUFFER);
@@ -3831,36 +3804,14 @@ static void qeth_qdio_output_handler(struct ccw_device *ccwdev,
 				     unsigned long card_ptr)
 {
 	struct qeth_card *card        = (struct qeth_card *) card_ptr;
-	struct qeth_qdio_out_q *queue = card->qdio.out_qs[__queue];
 	struct net_device *dev = card->dev;
-	struct netdev_queue *txq;
-	int i;
 
 	QETH_CARD_TEXT(card, 6, "qdouhdl");
 	if (qdio_error & QDIO_ERROR_FATAL) {
 		QETH_CARD_TEXT(card, 2, "achkcond");
 		netif_tx_stop_all_queues(dev);
 		qeth_schedule_recovery(card);
-		return;
 	}
-
-	for (i = first_element; i < (first_element + count); ++i) {
-		struct qeth_qdio_out_buffer *buf = queue->bufs[QDIO_BUFNR(i)];
-
-		qeth_handle_send_error(card, buf, qdio_error);
-		qeth_clear_output_buffer(queue, buf, qdio_error, 0);
-	}
-
-	atomic_sub(count, &queue->used_buffers);
-	qeth_check_outbound_queue(queue);
-
-	txq = netdev_get_tx_queue(dev, __queue);
-	/* xmit may have observed the full-condition, but not yet stopped the
-	 * txq. In which case the code below won't trigger. So before returning,
-	 * xmit will re-check the txq's fill level and wake it up if needed.
-	 */
-	if (netif_tx_queue_stopped(txq) && !qeth_out_queue_is_full(queue))
-		netif_tx_wake_queue(txq);
 }
 
 /**
@@ -4101,7 +4052,7 @@ static unsigned int qeth_fill_buffer(struct qeth_qdio_out_buffer *buf,
 
 		/* HW header is allocated from cache: */
 		if ((void *)hdr != skb->data)
-			buf->is_header[element] = 1;
+			__set_bit(element, buf->from_kmem_cache);
 		/* HW header was pushed and is contiguous with linear part: */
 		else if (length > 0 && !PAGE_ALIGNED(data) &&
 			 (data == (char *)hdr + hd_len))
@@ -5256,7 +5207,6 @@ static int qeth_qdio_establish(struct qeth_card *card)
 	init_data.int_parm               = (unsigned long) card;
 	init_data.input_sbal_addr_array  = in_sbal_ptrs;
 	init_data.output_sbal_addr_array = out_sbal_ptrs;
-	init_data.scan_threshold	 = IS_IQD(card) ? 0 : 32;
 
 	if (atomic_cmpxchg(&card->qdio.state, QETH_QDIO_ALLOCATED,
 		QETH_QDIO_ESTABLISHED) == QETH_QDIO_ALLOCATED) {
@@ -5956,9 +5906,10 @@ static unsigned int qeth_rx_poll(struct qeth_card *card, int budget)
 		/* Fetch completed RX buffers: */
 		if (!card->rx.b_count) {
 			card->rx.qdio_err = 0;
-			card->rx.b_count = qdio_get_next_buffers(
-				card->data.ccwdev, 0, &card->rx.b_index,
-				&card->rx.qdio_err);
+			card->rx.b_count = qdio_inspect_queue(CARD_DDEV(card),
+							      0, true,
+							      &card->rx.b_index,
+							      &card->rx.qdio_err);
 			if (card->rx.b_count <= 0) {
 				card->rx.b_count = 0;
 				break;
@@ -6022,6 +5973,16 @@ int qeth_poll(struct napi_struct *napi, int budget)
 
 	work_done = qeth_rx_poll(card, budget);
 
+	if (qeth_use_tx_irqs(card)) {
+		struct qeth_qdio_out_q *queue;
+		unsigned int i;
+
+		qeth_for_each_output_queue(card, queue, i) {
+			if (!qeth_out_queue_is_empty(queue))
+				napi_schedule(&queue->napi);
+		}
+	}
+
 	if (card->options.cq == QETH_CQ_ENABLED)
 		qeth_cq_poll(card);
 
@@ -6055,6 +6016,8 @@ static void qeth_iqd_tx_complete(struct qeth_qdio_out_q *queue,
 
 	if (qdio_error == QDIO_ERROR_SLSB_PENDING) {
 		struct qaob *aob = buffer->aob;
+		struct qeth_qaob_priv1 *priv;
+		enum iucv_tx_notify notify;
 
 		if (!aob) {
 			netdev_WARN_ONCE(card->dev,
@@ -6066,60 +6029,27 @@ static void qeth_iqd_tx_complete(struct qeth_qdio_out_q *queue,
 
 		QETH_CARD_TEXT_(card, 5, "pel%u", bidx);
 
-		switch (atomic_cmpxchg(&buffer->state,
-				       QETH_QDIO_BUF_PRIMED,
-				       QETH_QDIO_BUF_PENDING)) {
-		case QETH_QDIO_BUF_PRIMED:
-			/* We have initial ownership, no QAOB (yet): */
+		priv = (struct qeth_qaob_priv1 *)&aob->user1;
+		/* QAOB hasn't completed yet: */
+		if (xchg(&priv->state, QETH_QAOB_PENDING) != QETH_QAOB_DONE) {
 			qeth_notify_skbs(queue, buffer, TX_NOTIFY_PENDING);
 
-			/* Handle race with qeth_qdio_handle_aob(): */
-			switch (atomic_xchg(&buffer->state,
-					    QETH_QDIO_BUF_NEED_QAOB)) {
-			case QETH_QDIO_BUF_PENDING:
-				/* No concurrent QAOB notification. */
-
-				/* Prepare the queue slot for immediate re-use: */
-				qeth_scrub_qdio_buffer(buffer->buffer, queue->max_elements);
-				if (qeth_alloc_out_buf(queue, bidx,
-						       GFP_ATOMIC)) {
-					QETH_CARD_TEXT(card, 2, "outofbuf");
-					qeth_schedule_recovery(card);
-				}
-
-				list_add(&buffer->list_entry,
-					 &queue->pending_bufs);
-				/* Skip clearing the buffer: */
-				return;
-			case QETH_QDIO_BUF_QAOB_OK:
-				qeth_notify_skbs(queue, buffer,
-						 TX_NOTIFY_DELAYED_OK);
-				error = false;
-				break;
-			case QETH_QDIO_BUF_QAOB_ERROR:
-				qeth_notify_skbs(queue, buffer,
-						 TX_NOTIFY_DELAYED_GENERALERROR);
-				error = true;
-				break;
-			default:
-				WARN_ON_ONCE(1);
+			/* Prepare the queue slot for immediate re-use: */
+			qeth_scrub_qdio_buffer(buffer->buffer, queue->max_elements);
+			if (qeth_alloc_out_buf(queue, bidx, GFP_ATOMIC)) {
+				QETH_CARD_TEXT(card, 2, "outofbuf");
+				qeth_schedule_recovery(card);
 			}
 
-			break;
-		case QETH_QDIO_BUF_QAOB_OK:
-			/* qeth_qdio_handle_aob() already received a QAOB: */
-			qeth_notify_skbs(queue, buffer, TX_NOTIFY_OK);
-			error = false;
-			break;
-		case QETH_QDIO_BUF_QAOB_ERROR:
-			/* qeth_qdio_handle_aob() already received a QAOB: */
-			qeth_notify_skbs(queue, buffer, TX_NOTIFY_GENERALERROR);
-			error = true;
-			break;
-		default:
-			WARN_ON_ONCE(1);
+			list_add(&buffer->list_entry, &queue->pending_bufs);
+			/* Skip clearing the buffer: */
+			return;
 		}
 
+		/* QAOB already completed: */
+		notify = qeth_compute_cq_notification(aob->aorc, 0);
+		qeth_notify_skbs(queue, buffer, notify);
+		error = !!aob->aorc;
 		memset(aob, 0, sizeof(*aob));
 	} else if (card->options.cq == QETH_CQ_ENABLED) {
 		qeth_notify_skbs(queue, buffer,
@@ -6138,7 +6068,10 @@ static int qeth_tx_poll(struct napi_struct *napi, int budget)
 	unsigned int work_done = 0;
 	struct netdev_queue *txq;
 
-	txq = netdev_get_tx_queue(dev, qeth_iqd_translate_txq(dev, queue_no));
+	if (IS_IQD(card))
+		txq = netdev_get_tx_queue(dev, qeth_iqd_translate_txq(dev, queue_no));
+	else
+		txq = netdev_get_tx_queue(dev, queue_no);
 
 	while (1) {
 		unsigned int start, error, i;
@@ -6165,8 +6098,9 @@ static int qeth_tx_poll(struct napi_struct *napi, int budget)
 					       &start, &error);
 		if (completed <= 0) {
 			/* Ensure we see TX completion for pending work: */
-			if (napi_complete_done(napi, 0))
-				qeth_tx_arm_timer(queue, QETH_TX_TIMER_USECS);
+			if (napi_complete_done(napi, 0) &&
+			    !atomic_read(&queue->set_pci_flags_count))
+				qeth_tx_arm_timer(queue, queue->rescan_usecs);
 			return 0;
 		}
 
@@ -6179,12 +6113,19 @@ static int qeth_tx_poll(struct napi_struct *napi, int budget)
 			bytes += buffer->bytes;
 
 			qeth_handle_send_error(card, buffer, error);
-			qeth_iqd_tx_complete(queue, bidx, error, budget);
+			if (IS_IQD(card))
+				qeth_iqd_tx_complete(queue, bidx, error, budget);
+			else
+				qeth_clear_output_buffer(queue, buffer, error,
+							 budget);
 		}
 
-		netdev_tx_completed_queue(txq, packets, bytes);
 		atomic_sub(completed, &queue->used_buffers);
 		work_done += completed;
+		if (IS_IQD(card))
+			netdev_tx_completed_queue(txq, packets, bytes);
+		else
+			qeth_check_outbound_queue(queue);
 
 		/* xmit may have observed the full-condition, but not yet
 		 * stopped the txq. In which case the code below won't trigger.
@@ -7228,6 +7169,8 @@ EXPORT_SYMBOL_GPL(qeth_iqd_select_queue);
 int qeth_open(struct net_device *dev)
 {
 	struct qeth_card *card = dev->ml_priv;
+	struct qeth_qdio_out_q *queue;
+	unsigned int i;
 
 	QETH_CARD_TEXT(card, 4, "qethopen");
 
@@ -7235,16 +7178,11 @@ int qeth_open(struct net_device *dev)
 	netif_tx_start_all_queues(dev);
 
 	local_bh_disable();
-	if (IS_IQD(card)) {
-		struct qeth_qdio_out_q *queue;
-		unsigned int i;
-
-		qeth_for_each_output_queue(card, queue, i) {
-			netif_tx_napi_add(dev, &queue->napi, qeth_tx_poll,
-					  QETH_NAPI_WEIGHT);
-			napi_enable(&queue->napi);
-			napi_schedule(&queue->napi);
-		}
+	qeth_for_each_output_queue(card, queue, i) {
+		netif_tx_napi_add(dev, &queue->napi, qeth_tx_poll,
+				  QETH_NAPI_WEIGHT);
+		napi_enable(&queue->napi);
+		napi_schedule(&queue->napi);
 	}
 
 	napi_enable(&card->napi);
@@ -7259,6 +7197,8 @@ EXPORT_SYMBOL_GPL(qeth_open);
 int qeth_stop(struct net_device *dev)
 {
 	struct qeth_card *card = dev->ml_priv;
+	struct qeth_qdio_out_q *queue;
+	unsigned int i;
 
 	QETH_CARD_TEXT(card, 4, "qethstop");
 
@@ -7266,24 +7206,17 @@ int qeth_stop(struct net_device *dev)
 	cancel_delayed_work_sync(&card->buffer_reclaim_work);
 	qdio_stop_irq(CARD_DDEV(card));
 
-	if (IS_IQD(card)) {
-		struct qeth_qdio_out_q *queue;
-		unsigned int i;
-
-		/* Quiesce the NAPI instances: */
-		qeth_for_each_output_queue(card, queue, i)
-			napi_disable(&queue->napi);
+	/* Quiesce the NAPI instances: */
+	qeth_for_each_output_queue(card, queue, i)
+		napi_disable(&queue->napi);
 
-		/* Stop .ndo_start_xmit, might still access queue->napi. */
-		netif_tx_disable(dev);
+	/* Stop .ndo_start_xmit, might still access queue->napi. */
+	netif_tx_disable(dev);
 
-		qeth_for_each_output_queue(card, queue, i) {
-			del_timer_sync(&queue->timer);
-			/* Queues may get re-allocated, so remove the NAPIs. */
-			netif_napi_del(&queue->napi);
-		}
-	} else {
-		netif_tx_disable(dev);
+	qeth_for_each_output_queue(card, queue, i) {
+		del_timer_sync(&queue->timer);
+		/* Queues may get re-allocated, so remove the NAPIs. */
+		netif_napi_del(&queue->napi);
 	}
 
 	return 0;
diff --git a/drivers/s390/net/qeth_ethtool.c b/drivers/s390/net/qeth_ethtool.c
index 3a51bbff0ffe..2c4cb300a8fc 100644
--- a/drivers/s390/net/qeth_ethtool.c
+++ b/drivers/s390/net/qeth_ethtool.c
@@ -41,6 +41,7 @@ static const struct qeth_stats txq_stats[] = {
 	QETH_TXQ_STAT("Queue stopped", stopped),
 	QETH_TXQ_STAT("Doorbell", doorbell),
 	QETH_TXQ_STAT("IRQ for frames", coal_frames),
+	QETH_TXQ_STAT("Completion IRQ", completion_irq),
 	QETH_TXQ_STAT("Completion yield", completion_yield),
 	QETH_TXQ_STAT("Completion timer", completion_timer),
 };
@@ -79,10 +80,8 @@ static void qeth_add_stat_strings(u8 **data, const char *prefix,
 {
 	unsigned int i;
 
-	for (i = 0; i < size; i++) {
-		snprintf(*data, ETH_GSTRING_LEN, "%s%s", prefix, stats[i].name);
-		*data += ETH_GSTRING_LEN;
-	}
+	for (i = 0; i < size; i++)
+		ethtool_sprintf(data, "%s%s", prefix, stats[i].name);
 }
 
 static int qeth_get_sset_count(struct net_device *dev, int stringset)
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index ca44421a6d6e..2abf86c104d5 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -805,8 +805,6 @@ static int qeth_l2_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 
 	if (!netif_device_present(dev))
 		return -ENODEV;
-	if (!(priv->brport_hw_features))
-		return -EOPNOTSUPP;
 
 	nlmsg_for_each_attr(attr, nlh, sizeof(struct ifinfomsg), rem1) {
 		if (nla_type(attr) == IFLA_PROTINFO) {
@@ -832,6 +830,16 @@ static int qeth_l2_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 		return 0;
 	if (!bp_tb[IFLA_BRPORT_LEARNING_SYNC])
 		return -EINVAL;
+	if (!(priv->brport_hw_features & BR_LEARNING_SYNC)) {
+		NL_SET_ERR_MSG_ATTR(extack, bp_tb[IFLA_BRPORT_LEARNING_SYNC],
+				    "Operation not supported by HW");
+		return -EOPNOTSUPP;
+	}
+	if (!IS_ENABLED(CONFIG_NET_SWITCHDEV)) {
+		NL_SET_ERR_MSG_ATTR(extack, bp_tb[IFLA_BRPORT_LEARNING_SYNC],
+				    "Requires NET_SWITCHDEV");
+		return -EOPNOTSUPP;
+	}
 	enable = !!nla_get_u8(bp_tb[IFLA_BRPORT_LEARNING_SYNC]);
 
 	if (enable == !!(priv->brport_features & BR_LEARNING_SYNC))
diff --git a/drivers/ssb/driver_gpio.c b/drivers/ssb/driver_gpio.c
index 66a76fd83248..2de3896489c8 100644
--- a/drivers/ssb/driver_gpio.c
+++ b/drivers/ssb/driver_gpio.c
@@ -231,7 +231,8 @@ static int ssb_gpio_chipco_init(struct ssb_bus *bus)
 	chip->ngpio		= 16;
 	/* There is just one SoC in one device and its GPIO addresses should be
 	 * deterministic to address them more easily. The other buses could get
-	 * a random base number. */
+	 * a random base number.
+	 */
 	if (bus->bustype == SSB_BUSTYPE_SSB)
 		chip->base		= 0;
 	else
@@ -424,7 +425,8 @@ static int ssb_gpio_extif_init(struct ssb_bus *bus)
 	chip->ngpio		= 5;
 	/* There is just one SoC in one device and its GPIO addresses should be
 	 * deterministic to address them more easily. The other buses could get
-	 * a random base number. */
+	 * a random base number.
+	 */
 	if (bus->bustype == SSB_BUSTYPE_SSB)
 		chip->base		= 0;
 	else
diff --git a/drivers/ssb/driver_pcicore.c b/drivers/ssb/driver_pcicore.c
index c1186415896b..d11b4242b6d2 100644
--- a/drivers/ssb/driver_pcicore.c
+++ b/drivers/ssb/driver_pcicore.c
@@ -55,7 +55,8 @@ void pcicore_write16(struct ssb_pcicore *pc, u16 offset, u16 value)
 #include <asm/paccess.h>
 /* Probe a 32bit value on the bus and catch bus exceptions.
  * Returns nonzero on a bus exception.
- * This is MIPS specific */
+ * This is MIPS specific
+ */
 #define mips_busprobe32(val, addr)	get_dbe((val), ((u32 *)(addr)))
 
 /* Assume one-hot slot wiring */
@@ -255,7 +256,8 @@ static struct pci_controller ssb_pcicore_controller = {
 };
 
 /* This function is called when doing a pci_enable_device().
- * We must first check if the device is a device on the PCI-core bridge. */
+ * We must first check if the device is a device on the PCI-core bridge.
+ */
 int ssb_pcicore_plat_dev_init(struct pci_dev *d)
 {
 	if (d->bus->ops != &ssb_pcicore_pciops) {
@@ -381,11 +383,13 @@ static void ssb_pcicore_init_hostmode(struct ssb_pcicore *pc)
 
 	/* Ok, ready to run, register it to the system.
 	 * The following needs change, if we want to port hostmode
-	 * to non-MIPS platform. */
+	 * to non-MIPS platform.
+	 */
 	ssb_pcicore_controller.io_map_base = (unsigned long)ioremap(SSB_PCI_MEM, 0x04000000);
 	set_io_port_base(ssb_pcicore_controller.io_map_base);
 	/* Give some time to the PCI controller to configure itself with the new
-	 * values. Not waiting at this point causes crashes of the machine. */
+	 * values. Not waiting at this point causes crashes of the machine.
+	 */
 	mdelay(10);
 	register_pci_controller(&ssb_pcicore_controller);
 }
@@ -405,7 +409,8 @@ static int pcicore_is_in_hostmode(struct ssb_pcicore *pc)
 		return 0;
 
 	/* The 200-pin BCM4712 package does not bond out PCI. Even when
-	 * PCI is bonded out, some boards may leave the pins floating. */
+	 * PCI is bonded out, some boards may leave the pins floating.
+	 */
 	if (bus->chip_id == 0x4712) {
 		if (bus->chip_package == SSB_CHIPPACK_BCM4712S)
 			return 0;
@@ -685,7 +690,8 @@ int ssb_pcicore_dev_irqvecs_enable(struct ssb_pcicore *pc,
 	if (dev->bus->bustype != SSB_BUSTYPE_PCI) {
 		/* This SSB device is not on a PCI host-bus. So the IRQs are
 		 * not routed through the PCI core.
-		 * So we must not enable routing through the PCI core. */
+		 * So we must not enable routing through the PCI core.
+		 */
 		goto out;
 	}
 
diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c
index 0a26984acb2c..3a29b5570f9f 100644
--- a/drivers/ssb/main.c
+++ b/drivers/ssb/main.c
@@ -37,7 +37,8 @@ static LIST_HEAD(buses);
 /* Software ID counter */
 static unsigned int next_busnumber;
 /* buses_mutes locks the two buslists and the next_busnumber.
- * Don't lock this directly, but use ssb_buses_[un]lock() below. */
+ * Don't lock this directly, but use ssb_buses_[un]lock() below.
+ */
 static DEFINE_MUTEX(buses_mutex);
 
 /* There are differences in the codeflow, if the bus is
@@ -45,7 +46,8 @@ static DEFINE_MUTEX(buses_mutex);
  * are not available early. This is a mechanism to delay
  * these initializations to after early boot has finished.
  * It's also used to avoid mutex locking, as that's not
- * available and needed early. */
+ * available and needed early.
+ */
 static bool ssb_is_early_boot = 1;
 
 static void ssb_buses_lock(void);
@@ -161,7 +163,8 @@ int ssb_bus_resume(struct ssb_bus *bus)
 	int err;
 
 	/* Reset HW state information in memory, so that HW is
-	 * completely reinitialized. */
+	 * completely reinitialized.
+	 */
 	bus->mapped_device = NULL;
 #ifdef CONFIG_SSB_DRIVER_PCICORE
 	bus->pcicore.setup_done = 0;
@@ -431,9 +434,7 @@ void ssb_bus_unregister(struct ssb_bus *bus)
 	int err;
 
 	err = ssb_gpio_unregister(bus);
-	if (err == -EBUSY)
-		pr_debug("Some GPIOs are still in use\n");
-	else if (err)
+	if (err)
 		pr_debug("Can not unregister GPIO driver: %i\n", err);
 
 	ssb_buses_lock();
@@ -467,7 +468,8 @@ static int ssb_devices_register(struct ssb_bus *bus)
 		sdev = &(bus->devices[i]);
 
 		/* We don't register SSB-system devices to the kernel,
-		 * as the drivers for them are built into SSB. */
+		 * as the drivers for them are built into SSB.
+		 */
 		switch (sdev->id.coreid) {
 		case SSB_DEV_CHIPCOMMON:
 		case SSB_DEV_PCI:
@@ -521,7 +523,8 @@ static int ssb_devices_register(struct ssb_bus *bus)
 		if (err) {
 			pr_err("Could not register %s\n", dev_name(dev));
 			/* Set dev to NULL to not unregister
-			 * dev on error unwinding. */
+			 * dev on error unwinding.
+			 */
 			sdev->dev = NULL;
 			put_device(dev);
 			goto error;
@@ -667,7 +670,8 @@ ssb_bus_register(struct ssb_bus *bus,
 	ssb_bus_may_powerdown(bus);
 
 	/* Queue it for attach.
-	 * See the comment at the ssb_is_early_boot definition. */
+	 * See the comment at the ssb_is_early_boot definition.
+	 */
 	list_add_tail(&bus->list, &attach_queue);
 	if (!ssb_is_early_boot) {
 		/* This is not early boot, so we must attach the bus now */
@@ -1007,7 +1011,8 @@ static void ssb_flush_tmslow(struct ssb_device *dev)
 	 * a machine check exception otherwise.
 	 * Do this by reading the register back to commit the
 	 * PCI write and delay an additional usec for the device
-	 * to react to the change. */
+	 * to react to the change.
+	 */
 	ssb_read32(dev, SSB_TMSLOW);
 	udelay(1);
 }
@@ -1044,7 +1049,8 @@ void ssb_device_enable(struct ssb_device *dev, u32 core_specific_flags)
 EXPORT_SYMBOL(ssb_device_enable);
 
 /* Wait for bitmask in a register to get set or cleared.
- * timeout is in units of ten-microseconds */
+ * timeout is in units of ten-microseconds
+ */
 static int ssb_wait_bits(struct ssb_device *dev, u16 reg, u32 bitmask,
 			 int timeout, int set)
 {
@@ -1153,7 +1159,8 @@ int ssb_bus_may_powerdown(struct ssb_bus *bus)
 
 	/* On buses where more than one core may be working
 	 * at a time, we must not powerdown stuff if there are
-	 * still cores that may want to run. */
+	 * still cores that may want to run.
+	 */
 	if (bus->bustype == SSB_BUSTYPE_SSB)
 		goto out;
 
@@ -1303,13 +1310,11 @@ static int __init ssb_modinit(void)
 	if (err) {
 		pr_err("Broadcom 43xx PCI-SSB-bridge initialization failed\n");
 		/* don't fail SSB init because of this */
-		err = 0;
 	}
 	err = ssb_host_pcmcia_init();
 	if (err) {
 		pr_err("PCMCIA host initialization failed\n");
 		/* don't fail SSB init because of this */
-		err = 0;
 	}
 	err = ssb_gige_init();
 	if (err) {
@@ -1322,7 +1327,8 @@ out:
 }
 /* ssb must be initialized after PCI but before the ssb drivers.
  * That means we must use some initcall between subsys_initcall
- * and device_initcall. */
+ * and device_initcall.
+ */
 fs_initcall(ssb_modinit);
 
 static void __exit ssb_modexit(void)
diff --git a/drivers/ssb/pci.c b/drivers/ssb/pci.c
index dac54041ad8d..148bcb99c212 100644
--- a/drivers/ssb/pci.c
+++ b/drivers/ssb/pci.c
@@ -1117,9 +1117,9 @@ const struct ssb_bus_ops ssb_pci_ops = {
 #endif
 };
 
-static ssize_t ssb_pci_attr_sprom_show(struct device *pcidev,
-				       struct device_attribute *attr,
-				       char *buf)
+static ssize_t ssb_sprom_show(struct device *pcidev,
+			      struct device_attribute *attr,
+			      char *buf)
 {
 	struct pci_dev *pdev = container_of(pcidev, struct pci_dev, dev);
 	struct ssb_bus *bus;
@@ -1131,9 +1131,9 @@ static ssize_t ssb_pci_attr_sprom_show(struct device *pcidev,
 	return ssb_attr_sprom_show(bus, buf, sprom_do_read);
 }
 
-static ssize_t ssb_pci_attr_sprom_store(struct device *pcidev,
-					struct device_attribute *attr,
-					const char *buf, size_t count)
+static ssize_t ssb_sprom_store(struct device *pcidev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t count)
 {
 	struct pci_dev *pdev = container_of(pcidev, struct pci_dev, dev);
 	struct ssb_bus *bus;
@@ -1146,9 +1146,7 @@ static ssize_t ssb_pci_attr_sprom_store(struct device *pcidev,
 				    sprom_check_crc, sprom_do_write);
 }
 
-static DEVICE_ATTR(ssb_sprom, 0600,
-		   ssb_pci_attr_sprom_show,
-		   ssb_pci_attr_sprom_store);
+static DEVICE_ATTR_ADMIN_RW(ssb_sprom);
 
 void ssb_pci_exit(struct ssb_bus *bus)
 {
diff --git a/drivers/ssb/pcmcia.c b/drivers/ssb/pcmcia.c
index d7d730c245c5..45502098e0c7 100644
--- a/drivers/ssb/pcmcia.c
+++ b/drivers/ssb/pcmcia.c
@@ -723,9 +723,9 @@ int ssb_pcmcia_get_invariants(struct ssb_bus *bus,
 	return -ENODEV;
 }
 
-static ssize_t ssb_pcmcia_attr_sprom_show(struct device *pcmciadev,
-					  struct device_attribute *attr,
-					  char *buf)
+static ssize_t ssb_sprom_show(struct device *pcmciadev,
+			      struct device_attribute *attr,
+			      char *buf)
 {
 	struct pcmcia_device *pdev =
 		container_of(pcmciadev, struct pcmcia_device, dev);
@@ -739,9 +739,9 @@ static ssize_t ssb_pcmcia_attr_sprom_show(struct device *pcmciadev,
 				   ssb_pcmcia_sprom_read_all);
 }
 
-static ssize_t ssb_pcmcia_attr_sprom_store(struct device *pcmciadev,
-					   struct device_attribute *attr,
-					   const char *buf, size_t count)
+static ssize_t ssb_sprom_store(struct device *pcmciadev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t count)
 {
 	struct pcmcia_device *pdev =
 		container_of(pcmciadev, struct pcmcia_device, dev);
@@ -756,9 +756,7 @@ static ssize_t ssb_pcmcia_attr_sprom_store(struct device *pcmciadev,
 				    ssb_pcmcia_sprom_write_all);
 }
 
-static DEVICE_ATTR(ssb_sprom, 0600,
-		   ssb_pcmcia_attr_sprom_show,
-		   ssb_pcmcia_attr_sprom_store);
+static DEVICE_ATTR_ADMIN_RW(ssb_sprom);
 
 static int ssb_pcmcia_cor_setup(struct ssb_bus *bus, u8 cor)
 {
diff --git a/drivers/ssb/scan.c b/drivers/ssb/scan.c
index f49ab1aa2149..4161e5d1f276 100644
--- a/drivers/ssb/scan.c
+++ b/drivers/ssb/scan.c
@@ -325,6 +325,7 @@ int ssb_bus_scan(struct ssb_bus *bus,
 	if (bus->nr_devices > ARRAY_SIZE(bus->devices)) {
 		pr_err("More than %d ssb cores found (%d)\n",
 		       SSB_MAX_NR_CORES, bus->nr_devices);
+		err = -EINVAL;
 		goto err_unmap;
 	}
 	if (bus->bustype == SSB_BUSTYPE_SSB) {
diff --git a/drivers/ssb/sdio.c b/drivers/ssb/sdio.c
index 7fe0afb42234..66c5c2169704 100644
--- a/drivers/ssb/sdio.c
+++ b/drivers/ssb/sdio.c
@@ -411,7 +411,6 @@ static void ssb_sdio_block_write(struct ssb_device *dev, const void *buffer,
 	sdio_claim_host(bus->host_sdio);
 	if (unlikely(ssb_sdio_switch_core(bus, dev))) {
 		error = -EIO;
-		memset((void *)buffer, 0xff, count);
 		goto err_out;
 	}
 	offset |= bus->sdio_sbaddr & 0xffff;
diff --git a/drivers/staging/mt7621-dts/mt7621.dtsi b/drivers/staging/mt7621-dts/mt7621.dtsi
index f0c9ae757bcd..093a7f8091b5 100644
--- a/drivers/staging/mt7621-dts/mt7621.dtsi
+++ b/drivers/staging/mt7621-dts/mt7621.dtsi
@@ -437,6 +437,10 @@
 				mediatek,mcm;
 				resets = <&rstctrl 2>;
 				reset-names = "mcm";
+				interrupt-controller;
+				#interrupt-cells = <1>;
+				interrupt-parent = <&gic>;
+				interrupts = <GIC_SHARED 23 IRQ_TYPE_LEVEL_HIGH>;
 
 				ports {
 					#address-cells = <1>;
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index d1e4a7379beb..8e5490ac13a2 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -21,8 +21,10 @@
 #include <linux/uaccess.h>
 #include <linux/bitops.h>
 #include <linux/poll.h>
+#include <linux/skbuff.h>
 #include <linux/usb.h>
 #include <linux/usb/cdc.h>
+#include <linux/wwan.h>
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
 #include <linux/usb/cdc-wdm.h>
@@ -55,6 +57,7 @@ MODULE_DEVICE_TABLE (usb, wdm_ids);
 #define WDM_SUSPENDING		8
 #define WDM_RESETTING		9
 #define WDM_OVERFLOW		10
+#define WDM_WWAN_IN_USE		11
 
 #define WDM_MAX			16
 
@@ -106,6 +109,9 @@ struct wdm_device {
 
 	struct list_head	device_list;
 	int			(*manage_power)(struct usb_interface *, int);
+
+	enum wwan_port_type	wwanp_type;
+	struct wwan_port	*wwanp;
 };
 
 static struct usb_driver wdm_driver;
@@ -157,6 +163,8 @@ static void wdm_out_callback(struct urb *urb)
 	wake_up_all(&desc->wait);
 }
 
+static void wdm_wwan_rx(struct wdm_device *desc, int length);
+
 static void wdm_in_callback(struct urb *urb)
 {
 	unsigned long flags;
@@ -192,6 +200,11 @@ static void wdm_in_callback(struct urb *urb)
 		}
 	}
 
+	if (test_bit(WDM_WWAN_IN_USE, &desc->flags)) {
+		wdm_wwan_rx(desc, length);
+		goto out;
+	}
+
 	/*
 	 * only set a new error if there is no previous error.
 	 * Errors are only cleared during read/open
@@ -226,6 +239,7 @@ skip_error:
 		set_bit(WDM_READ, &desc->flags);
 		wake_up(&desc->wait);
 	}
+out:
 	spin_unlock_irqrestore(&desc->iuspin, flags);
 }
 
@@ -708,6 +722,11 @@ static int wdm_open(struct inode *inode, struct file *file)
 		goto out;
 	file->private_data = desc;
 
+	if (test_bit(WDM_WWAN_IN_USE, &desc->flags)) {
+		rv = -EBUSY;
+		goto out;
+	}
+
 	rv = usb_autopm_get_interface(desc->intf);
 	if (rv < 0) {
 		dev_err(&desc->intf->dev, "Error autopm - %d\n", rv);
@@ -804,6 +823,152 @@ static struct usb_class_driver wdm_class = {
 	.minor_base =	WDM_MINOR_BASE,
 };
 
+/* --- WWAN framework integration --- */
+#ifdef CONFIG_WWAN
+static int wdm_wwan_port_start(struct wwan_port *port)
+{
+	struct wdm_device *desc = wwan_port_get_drvdata(port);
+
+	/* The interface is both exposed via the WWAN framework and as a
+	 * legacy usbmisc chardev. If chardev is already open, just fail
+	 * to prevent concurrent usage. Otherwise, switch to WWAN mode.
+	 */
+	mutex_lock(&wdm_mutex);
+	if (desc->count) {
+		mutex_unlock(&wdm_mutex);
+		return -EBUSY;
+	}
+	set_bit(WDM_WWAN_IN_USE, &desc->flags);
+	mutex_unlock(&wdm_mutex);
+
+	desc->manage_power(desc->intf, 1);
+
+	/* tx is allowed */
+	wwan_port_txon(port);
+
+	/* Start getting events */
+	return usb_submit_urb(desc->validity, GFP_KERNEL);
+}
+
+static void wdm_wwan_port_stop(struct wwan_port *port)
+{
+	struct wdm_device *desc = wwan_port_get_drvdata(port);
+
+	/* Stop all transfers and disable WWAN mode */
+	poison_urbs(desc);
+	desc->manage_power(desc->intf, 0);
+	clear_bit(WDM_READ, &desc->flags);
+	clear_bit(WDM_WWAN_IN_USE, &desc->flags);
+	unpoison_urbs(desc);
+}
+
+static void wdm_wwan_port_tx_complete(struct urb *urb)
+{
+	struct sk_buff *skb = urb->context;
+	struct wdm_device *desc = skb_shinfo(skb)->destructor_arg;
+
+	usb_autopm_put_interface(desc->intf);
+	wwan_port_txon(desc->wwanp);
+	kfree_skb(skb);
+}
+
+static int wdm_wwan_port_tx(struct wwan_port *port, struct sk_buff *skb)
+{
+	struct wdm_device *desc = wwan_port_get_drvdata(port);
+	struct usb_interface *intf = desc->intf;
+	struct usb_ctrlrequest *req = desc->orq;
+	int rv;
+
+	rv = usb_autopm_get_interface(intf);
+	if (rv)
+		return rv;
+
+	usb_fill_control_urb(
+		desc->command,
+		interface_to_usbdev(intf),
+		usb_sndctrlpipe(interface_to_usbdev(intf), 0),
+		(unsigned char *)req,
+		skb->data,
+		skb->len,
+		wdm_wwan_port_tx_complete,
+		skb
+	);
+
+	req->bRequestType = (USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE);
+	req->bRequest = USB_CDC_SEND_ENCAPSULATED_COMMAND;
+	req->wValue = 0;
+	req->wIndex = desc->inum;
+	req->wLength = cpu_to_le16(skb->len);
+
+	skb_shinfo(skb)->destructor_arg = desc;
+
+	rv = usb_submit_urb(desc->command, GFP_KERNEL);
+	if (rv)
+		usb_autopm_put_interface(intf);
+	else /* One transfer at a time, stop TX until URB completion */
+		wwan_port_txoff(port);
+
+	return rv;
+}
+
+static struct wwan_port_ops wdm_wwan_port_ops = {
+	.start = wdm_wwan_port_start,
+	.stop = wdm_wwan_port_stop,
+	.tx = wdm_wwan_port_tx,
+};
+
+static void wdm_wwan_init(struct wdm_device *desc)
+{
+	struct usb_interface *intf = desc->intf;
+	struct wwan_port *port;
+
+	/* Only register to WWAN core if protocol/type is known */
+	if (desc->wwanp_type == WWAN_PORT_UNKNOWN) {
+		dev_info(&intf->dev, "Unknown control protocol\n");
+		return;
+	}
+
+	port = wwan_create_port(&intf->dev, desc->wwanp_type, &wdm_wwan_port_ops, desc);
+	if (IS_ERR(port)) {
+		dev_err(&intf->dev, "%s: Unable to create WWAN port\n",
+			dev_name(intf->usb_dev));
+		return;
+	}
+
+	desc->wwanp = port;
+}
+
+static void wdm_wwan_deinit(struct wdm_device *desc)
+{
+	if (!desc->wwanp)
+		return;
+
+	wwan_remove_port(desc->wwanp);
+	desc->wwanp = NULL;
+}
+
+static void wdm_wwan_rx(struct wdm_device *desc, int length)
+{
+	struct wwan_port *port = desc->wwanp;
+	struct sk_buff *skb;
+
+	/* Forward data to WWAN port */
+	skb = alloc_skb(length, GFP_ATOMIC);
+	if (!skb)
+		return;
+
+	memcpy(skb_put(skb, length), desc->inbuf, length);
+	wwan_port_rx(port, skb);
+
+	/* inbuf has been copied, it is safe to check for outstanding data */
+	schedule_work(&desc->service_outs_intr);
+}
+#else /* CONFIG_WWAN */
+static void wdm_wwan_init(struct wdm_device *desc) {}
+static void wdm_wwan_deinit(struct wdm_device *desc) {}
+static void wdm_wwan_rx(struct wdm_device *desc, int length) {}
+#endif /* CONFIG_WWAN */
+
 /* --- error handling --- */
 static void wdm_rxwork(struct work_struct *work)
 {
@@ -848,7 +1013,8 @@ static void service_interrupt_work(struct work_struct *work)
 /* --- hotplug --- */
 
 static int wdm_create(struct usb_interface *intf, struct usb_endpoint_descriptor *ep,
-		u16 bufsize, int (*manage_power)(struct usb_interface *, int))
+		      u16 bufsize, enum wwan_port_type type,
+		      int (*manage_power)(struct usb_interface *, int))
 {
 	int rv = -ENOMEM;
 	struct wdm_device *desc;
@@ -865,6 +1031,7 @@ static int wdm_create(struct usb_interface *intf, struct usb_endpoint_descriptor
 	/* this will be expanded and needed in hardware endianness */
 	desc->inum = cpu_to_le16((u16)intf->cur_altsetting->desc.bInterfaceNumber);
 	desc->intf = intf;
+	desc->wwanp_type = type;
 	INIT_WORK(&desc->rxwork, wdm_rxwork);
 	INIT_WORK(&desc->service_outs_intr, service_interrupt_work);
 
@@ -945,6 +1112,9 @@ static int wdm_create(struct usb_interface *intf, struct usb_endpoint_descriptor
 		goto err;
 	else
 		dev_info(&intf->dev, "%s: USB WDM device\n", dev_name(intf->usb_dev));
+
+	wdm_wwan_init(desc);
+
 out:
 	return rv;
 err:
@@ -989,7 +1159,7 @@ static int wdm_probe(struct usb_interface *intf, const struct usb_device_id *id)
 		goto err;
 	ep = &iface->endpoint[0].desc;
 
-	rv = wdm_create(intf, ep, maxcom, &wdm_manage_power);
+	rv = wdm_create(intf, ep, maxcom, WWAN_PORT_UNKNOWN, &wdm_manage_power);
 
 err:
 	return rv;
@@ -1000,6 +1170,7 @@ err:
  * @intf: usb interface the subdriver will associate with
  * @ep: interrupt endpoint to monitor for notifications
  * @bufsize: maximum message size to support for read/write
+ * @type: Type/protocol of the transported data (MBIM, QMI...)
  * @manage_power: call-back invoked during open and release to
  *                manage the device's power
  * Create WDM usb class character device and associate it with intf
@@ -1017,12 +1188,12 @@ err:
  */
 struct usb_driver *usb_cdc_wdm_register(struct usb_interface *intf,
 					struct usb_endpoint_descriptor *ep,
-					int bufsize,
+					int bufsize, enum wwan_port_type type,
 					int (*manage_power)(struct usb_interface *, int))
 {
 	int rv;
 
-	rv = wdm_create(intf, ep, bufsize, manage_power);
+	rv = wdm_create(intf, ep, bufsize, type, manage_power);
 	if (rv < 0)
 		goto err;
 
@@ -1041,6 +1212,8 @@ static void wdm_disconnect(struct usb_interface *intf)
 	desc = wdm_find_device(intf);
 	mutex_lock(&wdm_mutex);
 
+	wdm_wwan_deinit(desc);
+
 	/* the spinlock makes sure no new urbs are generated in the callbacks */
 	spin_lock_irqsave(&desc->iuspin, flags);
 	set_bit(WDM_DISCONNECTING, &desc->flags);
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index df82b124170e..6414bd5741b8 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -744,11 +744,9 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
 	if (copied != len)
 		return -EFAULT;
 
-	xdp->data_hard_start = buf;
-	xdp->data = buf + pad;
-	xdp->data_end = xdp->data + len;
+	xdp_init_buff(xdp, buflen, NULL);
+	xdp_prepare_buff(xdp, buf, pad, len, true);
 	hdr->buflen = buflen;
-	xdp->frame_sz = buflen;
 
 	--net->refcnt_bias;
 	alloc_frag->offset += buflen;
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 5e78fb719602..119f08491d3c 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -31,7 +31,8 @@
 
 enum {
 	VHOST_VSOCK_FEATURES = VHOST_FEATURES |
-			       (1ULL << VIRTIO_F_ACCESS_PLATFORM)
+			       (1ULL << VIRTIO_F_ACCESS_PLATFORM) |
+			       (1ULL << VIRTIO_VSOCK_F_SEQPACKET)
 };
 
 enum {
@@ -56,6 +57,7 @@ struct vhost_vsock {
 	atomic_t queued_replies;
 
 	u32 guest_cid;
+	bool seqpacket_allow;
 };
 
 static u32 vhost_transport_get_local_cid(void)
@@ -112,6 +114,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 		size_t nbytes;
 		size_t iov_len, payload_len;
 		int head;
+		bool restore_flag = false;
 
 		spin_lock_bh(&vsock->send_pkt_list_lock);
 		if (list_empty(&vsock->send_pkt_list)) {
@@ -168,9 +171,26 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 		/* If the packet is greater than the space available in the
 		 * buffer, we split it using multiple buffers.
 		 */
-		if (payload_len > iov_len - sizeof(pkt->hdr))
+		if (payload_len > iov_len - sizeof(pkt->hdr)) {
 			payload_len = iov_len - sizeof(pkt->hdr);
 
+			/* As we are copying pieces of large packet's buffer to
+			 * small rx buffers, headers of packets in rx queue are
+			 * created dynamically and are initialized with header
+			 * of current packet(except length). But in case of
+			 * SOCK_SEQPACKET, we also must clear record delimeter
+			 * bit(VIRTIO_VSOCK_SEQ_EOR). Otherwise, instead of one
+			 * packet with delimeter(which marks end of record),
+			 * there will be sequence of packets with delimeter
+			 * bit set. After initialized header will be copied to
+			 * rx buffer, this bit will be restored.
+			 */
+			if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) {
+				pkt->hdr.flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR);
+				restore_flag = true;
+			}
+		}
+
 		/* Set the correct length in the header */
 		pkt->hdr.len = cpu_to_le32(payload_len);
 
@@ -204,6 +224,9 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 		 * to send it with the next available buffer.
 		 */
 		if (pkt->off < pkt->len) {
+			if (restore_flag)
+				pkt->hdr.flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR);
+
 			/* We are queueing the same virtio_vsock_pkt to handle
 			 * the remaining bytes, and we want to deliver it
 			 * to monitoring devices in the next iteration.
@@ -354,8 +377,7 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq,
 		return NULL;
 	}
 
-	if (le16_to_cpu(pkt->hdr.type) == VIRTIO_VSOCK_TYPE_STREAM)
-		pkt->len = le32_to_cpu(pkt->hdr.len);
+	pkt->len = le32_to_cpu(pkt->hdr.len);
 
 	/* No payload */
 	if (!pkt->len)
@@ -398,6 +420,8 @@ static bool vhost_vsock_more_replies(struct vhost_vsock *vsock)
 	return val < vq->num;
 }
 
+static bool vhost_transport_seqpacket_allow(u32 remote_cid);
+
 static struct virtio_transport vhost_transport = {
 	.transport = {
 		.module                   = THIS_MODULE,
@@ -424,6 +448,11 @@ static struct virtio_transport vhost_transport = {
 		.stream_is_active         = virtio_transport_stream_is_active,
 		.stream_allow             = virtio_transport_stream_allow,
 
+		.seqpacket_dequeue        = virtio_transport_seqpacket_dequeue,
+		.seqpacket_enqueue        = virtio_transport_seqpacket_enqueue,
+		.seqpacket_allow          = vhost_transport_seqpacket_allow,
+		.seqpacket_has_data       = virtio_transport_seqpacket_has_data,
+
 		.notify_poll_in           = virtio_transport_notify_poll_in,
 		.notify_poll_out          = virtio_transport_notify_poll_out,
 		.notify_recv_init         = virtio_transport_notify_recv_init,
@@ -441,6 +470,22 @@ static struct virtio_transport vhost_transport = {
 	.send_pkt = vhost_transport_send_pkt,
 };
 
+static bool vhost_transport_seqpacket_allow(u32 remote_cid)
+{
+	struct vhost_vsock *vsock;
+	bool seqpacket_allow = false;
+
+	rcu_read_lock();
+	vsock = vhost_vsock_get(remote_cid);
+
+	if (vsock)
+		seqpacket_allow = vsock->seqpacket_allow;
+
+	rcu_read_unlock();
+
+	return seqpacket_allow;
+}
+
 static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 {
 	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
@@ -785,6 +830,9 @@ static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features)
 			goto err;
 	}
 
+	if (features & (1ULL << VIRTIO_VSOCK_F_SEQPACKET))
+		vsock->seqpacket_allow = true;
+
 	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
 		vq = &vsock->vqs[i];
 		mutex_lock(&vq->mutex);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index c60745f657e9..6ace3a0f1415 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -710,6 +710,8 @@ static inline u64 acpi_arch_get_root_pointer(void)
 }
 #endif
 
+int acpi_get_local_address(acpi_handle handle, u32 *addr);
+
 #else	/* !CONFIG_ACPI */
 
 #define acpi_disabled 1
@@ -965,6 +967,11 @@ static inline struct acpi_device *acpi_resource_consumer(struct resource *res)
 	return NULL;
 }
 
+static inline int acpi_get_local_address(acpi_handle handle, u32 *addr)
+{
+	return -ENODEV;
+}
+
 #endif	/* !CONFIG_ACPI */
 
 #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
diff --git a/include/linux/acpi_mdio.h b/include/linux/acpi_mdio.h
new file mode 100644
index 000000000000..0a24ab7cb66f
--- /dev/null
+++ b/include/linux/acpi_mdio.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * ACPI helper for the MDIO (Ethernet PHY) API
+ */
+
+#ifndef __LINUX_ACPI_MDIO_H
+#define __LINUX_ACPI_MDIO_H
+
+#include <linux/phy.h>
+
+#if IS_ENABLED(CONFIG_ACPI_MDIO)
+int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode);
+#else /* CONFIG_ACPI_MDIO */
+static inline int
+acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode)
+{
+	/*
+	 * Fall back to mdiobus_register() function to register a bus.
+	 * This way, we don't have to keep compat bits around in drivers.
+	 */
+
+	return mdiobus_register(mdio);
+}
+#endif
+
+#endif /* __LINUX_ACPI_MDIO_H */
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 8612f8fc86c1..db0e099c2399 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -412,9 +412,36 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_queue_select);
  * PF removes the filters and returns status.
  */
 
+/* VIRTCHNL_ETHER_ADDR_LEGACY
+ * Prior to adding the @type member to virtchnl_ether_addr, there were 2 pad
+ * bytes. Moving forward all VF drivers should not set type to
+ * VIRTCHNL_ETHER_ADDR_LEGACY. This is only here to not break previous/legacy
+ * behavior. The control plane function (i.e. PF) can use a best effort method
+ * of tracking the primary/device unicast in this case, but there is no
+ * guarantee and functionality depends on the implementation of the PF.
+ */
+
+/* VIRTCHNL_ETHER_ADDR_PRIMARY
+ * All VF drivers should set @type to VIRTCHNL_ETHER_ADDR_PRIMARY for the
+ * primary/device unicast MAC address filter for VIRTCHNL_OP_ADD_ETH_ADDR and
+ * VIRTCHNL_OP_DEL_ETH_ADDR. This allows for the underlying control plane
+ * function (i.e. PF) to accurately track and use this MAC address for
+ * displaying on the host and for VM/function reset.
+ */
+
+/* VIRTCHNL_ETHER_ADDR_EXTRA
+ * All VF drivers should set @type to VIRTCHNL_ETHER_ADDR_EXTRA for any extra
+ * unicast and/or multicast filters that are being added/deleted via
+ * VIRTCHNL_OP_DEL_ETH_ADDR/VIRTCHNL_OP_ADD_ETH_ADDR respectively.
+ */
 struct virtchnl_ether_addr {
 	u8 addr[ETH_ALEN];
-	u8 pad[2];
+	u8 type;
+#define VIRTCHNL_ETHER_ADDR_LEGACY	0
+#define VIRTCHNL_ETHER_ADDR_PRIMARY	1
+#define VIRTCHNL_ETHER_ADDR_EXTRA	2
+#define VIRTCHNL_ETHER_ADDR_TYPE_MASK	3 /* first two bits of type are valid */
+	u8 pad;
 };
 
 VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_ether_addr);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 02b02cb29ce2..f309fc1509f2 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -22,6 +22,7 @@
 #include <linux/sched/mm.h>
 #include <linux/slab.h>
 #include <linux/percpu-refcount.h>
+#include <linux/bpfptr.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -69,6 +70,8 @@ struct bpf_map_ops {
 	void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key);
 	int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr,
 				union bpf_attr __user *uattr);
+	int (*map_lookup_and_delete_elem)(struct bpf_map *map, void *key,
+					  void *value, u64 flags);
 	int (*map_lookup_and_delete_batch)(struct bpf_map *map,
 					   const union bpf_attr *attr,
 					   union bpf_attr __user *uattr);
@@ -1428,7 +1431,7 @@ struct bpf_iter__bpf_map_elem {
 int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info);
 void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info);
 bool bpf_iter_prog_supported(struct bpf_prog *prog);
-int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog);
 int bpf_iter_new_fd(struct bpf_link *link);
 bool bpf_link_is_iter(struct bpf_link *link);
 struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop);
@@ -1459,7 +1462,7 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
 int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
 
 int bpf_get_file_flag(int flags);
-int bpf_check_uarg_tail_zero(void __user *uaddr, size_t expected_size,
+int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size,
 			     size_t actual_size);
 
 /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
@@ -1479,8 +1482,7 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
 }
 
 /* verify correctness of eBPF program */
-int bpf_check(struct bpf_prog **fp, union bpf_attr *attr,
-	      union bpf_attr __user *uattr);
+int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr);
 
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
@@ -1499,8 +1501,13 @@ int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
 int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
+int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+			  struct bpf_map *map, bool exclude_ingress);
 int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 			     struct bpf_prog *xdp_prog);
+int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
+			   struct bpf_prog *xdp_prog, struct bpf_map *map,
+			   bool exclude_ingress);
 bool dev_map_can_have_prog(struct bpf_map *map);
 
 void __cpu_map_flush(void);
@@ -1668,6 +1675,13 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 	return 0;
 }
 
+static inline
+int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+			  struct bpf_map *map, bool exclude_ingress)
+{
+	return 0;
+}
+
 struct sk_buff;
 
 static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
@@ -1677,6 +1691,14 @@ static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
 	return 0;
 }
 
+static inline
+int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
+			   struct bpf_prog *xdp_prog, struct bpf_map *map,
+			   bool exclude_ingress)
+{
+	return 0;
+}
+
 static inline void __cpu_map_flush(void)
 {
 }
@@ -1826,6 +1848,9 @@ static inline bool bpf_map_is_dev_bound(struct bpf_map *map)
 
 struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr);
 void bpf_map_offload_map_free(struct bpf_map *map);
+int bpf_prog_test_run_syscall(struct bpf_prog *prog,
+			      const union bpf_attr *kattr,
+			      union bpf_attr __user *uattr);
 #else
 static inline int bpf_prog_offload_init(struct bpf_prog *prog,
 					union bpf_attr *attr)
@@ -1851,6 +1876,13 @@ static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 static inline void bpf_map_offload_map_free(struct bpf_map *map)
 {
 }
+
+static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog,
+					    const union bpf_attr *kattr,
+					    union bpf_attr __user *uattr)
+{
+	return -ENOTSUPP;
+}
 #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
 
 #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
@@ -1964,6 +1996,7 @@ extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto;
 extern const struct bpf_func_proto bpf_task_storage_get_proto;
 extern const struct bpf_func_proto bpf_task_storage_delete_proto;
 extern const struct bpf_func_proto bpf_for_each_map_elem_proto;
+extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
@@ -2015,6 +2048,7 @@ struct sk_reuseport_kern {
 	struct sk_buff *skb;
 	struct sock *sk;
 	struct sock *selected_sk;
+	struct sock *migrating_sk;
 	void *data_end;
 	u32 hash;
 	u32 reuseport_id;
diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h
index b902c580c48d..24496bc28e7b 100644
--- a/include/linux/bpf_local_storage.h
+++ b/include/linux/bpf_local_storage.h
@@ -58,7 +58,7 @@ struct bpf_local_storage_data {
 	 * from the object's bpf_local_storage.
 	 *
 	 * Put it in the same cacheline as the data to minimize
-	 * the number of cachelines access during the cache hit case.
+	 * the number of cachelines accessed during the cache hit case.
 	 */
 	struct bpf_local_storage_map __rcu *smap;
 	u8 data[] __aligned(8);
@@ -71,7 +71,7 @@ struct bpf_local_storage_elem {
 	struct bpf_local_storage __rcu *local_storage;
 	struct rcu_head rcu;
 	/* 8 bytes hole */
-	/* The data is stored in aother cacheline to minimize
+	/* The data is stored in another cacheline to minimize
 	 * the number of cachelines access during a cache hit.
 	 */
 	struct bpf_local_storage_data sdata ____cacheline_aligned;
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index f883f01a5061..a9db1eae6796 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -77,6 +77,8 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LSM, lsm,
 	       void *, void *)
 #endif /* CONFIG_BPF_LSM */
 #endif
+BPF_PROG_TYPE(BPF_PROG_TYPE_SYSCALL, bpf_syscall,
+	      void *, void *)
 
 BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 06841517ab1e..e774ecc1cd1f 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -215,6 +215,13 @@ struct bpf_idx_pair {
 	u32 idx;
 };
 
+struct bpf_id_pair {
+	u32 old;
+	u32 cur;
+};
+
+/* Maximum number of register states that can exist at once */
+#define BPF_ID_MAP_SIZE (MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE)
 #define MAX_CALL_FRAMES 8
 struct bpf_verifier_state {
 	/* call stack tracking */
@@ -418,6 +425,7 @@ struct bpf_verifier_env {
 	const struct bpf_line_info *prev_linfo;
 	struct bpf_verifier_log log;
 	struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1];
+	struct bpf_id_pair idmap_scratch[BPF_ID_MAP_SIZE];
 	struct {
 		int *insn_state;
 		int *insn_stack;
@@ -442,6 +450,7 @@ struct bpf_verifier_env {
 	u32 peak_states;
 	/* longest register parentage chain walked for liveness marking */
 	u32 longest_mark_read_walk;
+	bpfptr_t fd_array;
 };
 
 __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,
diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h
new file mode 100644
index 000000000000..5cdeab497cb3
--- /dev/null
+++ b/include/linux/bpfptr.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* A pointer that can point to either kernel or userspace memory. */
+#ifndef _LINUX_BPFPTR_H
+#define _LINUX_BPFPTR_H
+
+#include <linux/sockptr.h>
+
+typedef sockptr_t bpfptr_t;
+
+static inline bool bpfptr_is_kernel(bpfptr_t bpfptr)
+{
+	return bpfptr.is_kernel;
+}
+
+static inline bpfptr_t KERNEL_BPFPTR(void *p)
+{
+	return (bpfptr_t) { .kernel = p, .is_kernel = true };
+}
+
+static inline bpfptr_t USER_BPFPTR(void __user *p)
+{
+	return (bpfptr_t) { .user = p };
+}
+
+static inline bpfptr_t make_bpfptr(u64 addr, bool is_kernel)
+{
+	if (is_kernel)
+		return KERNEL_BPFPTR((void*) (uintptr_t) addr);
+	else
+		return USER_BPFPTR(u64_to_user_ptr(addr));
+}
+
+static inline bool bpfptr_is_null(bpfptr_t bpfptr)
+{
+	if (bpfptr_is_kernel(bpfptr))
+		return !bpfptr.kernel;
+	return !bpfptr.user;
+}
+
+static inline void bpfptr_add(bpfptr_t *bpfptr, size_t val)
+{
+	if (bpfptr_is_kernel(*bpfptr))
+		bpfptr->kernel += val;
+	else
+		bpfptr->user += val;
+}
+
+static inline int copy_from_bpfptr_offset(void *dst, bpfptr_t src,
+					  size_t offset, size_t size)
+{
+	return copy_from_sockptr_offset(dst, (sockptr_t) src, offset, size);
+}
+
+static inline int copy_from_bpfptr(void *dst, bpfptr_t src, size_t size)
+{
+	return copy_from_bpfptr_offset(dst, src, 0, size);
+}
+
+static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset,
+					const void *src, size_t size)
+{
+	return copy_to_sockptr_offset((sockptr_t) dst, offset, src, size);
+}
+
+static inline void *memdup_bpfptr(bpfptr_t src, size_t len)
+{
+	return memdup_sockptr((sockptr_t) src, len);
+}
+
+static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count)
+{
+	return strncpy_from_sockptr(dst, (sockptr_t) src, count);
+}
+
+#endif /* _LINUX_BPFPTR_H */
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 3bac66e0183a..94a0c976c90f 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -21,7 +21,7 @@ extern const struct file_operations btf_fops;
 
 void btf_get(struct btf *btf);
 void btf_put(struct btf *btf);
-int btf_new_fd(const union bpf_attr *attr);
+int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr);
 struct btf *btf_get_by_fd(int fd);
 int btf_get_info_by_fd(const struct btf *btf,
 		       const union bpf_attr *attr,
diff --git a/include/linux/device.h b/include/linux/device.h
index f1a00040fa53..8f0ec3081a24 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -817,6 +817,7 @@ int device_online(struct device *dev);
 void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode);
 void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode);
 void device_set_of_node_from_dev(struct device *dev, const struct device *dev2);
+void device_set_node(struct device *dev, struct fwnode_handle *fwnode);
 
 static inline int dev_num_vf(struct device *dev)
 {
diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h
index b12b05f1c8b4..1587961f1a7b 100644
--- a/include/linux/dsa/8021q.h
+++ b/include/linux/dsa/8021q.h
@@ -37,8 +37,6 @@ struct dsa_8021q_context {
 
 #define DSA_8021Q_N_SUBVLAN			8
 
-#if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q)
-
 int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled);
 
 int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port,
@@ -52,6 +50,9 @@ int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port,
 struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev,
 			       u16 tpid, u16 tci);
 
+void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id,
+		   int *subvlan);
+
 u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port);
 
 u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port);
@@ -70,78 +71,4 @@ bool vid_is_dsa_8021q_txvlan(u16 vid);
 
 bool vid_is_dsa_8021q(u16 vid);
 
-#else
-
-int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled)
-{
-	return 0;
-}
-
-int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port,
-				    struct dsa_8021q_context *other_ctx,
-				    int other_port)
-{
-	return 0;
-}
-
-int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port,
-				     struct dsa_8021q_context *other_ctx,
-				     int other_port)
-{
-	return 0;
-}
-
-struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev,
-			       u16 tpid, u16 tci)
-{
-	return NULL;
-}
-
-u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port)
-{
-	return 0;
-}
-
-u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port)
-{
-	return 0;
-}
-
-u16 dsa_8021q_rx_vid_subvlan(struct dsa_switch *ds, int port, u16 subvlan)
-{
-	return 0;
-}
-
-int dsa_8021q_rx_switch_id(u16 vid)
-{
-	return 0;
-}
-
-int dsa_8021q_rx_source_port(u16 vid)
-{
-	return 0;
-}
-
-u16 dsa_8021q_rx_subvlan(u16 vid)
-{
-	return 0;
-}
-
-bool vid_is_dsa_8021q_rxvlan(u16 vid)
-{
-	return false;
-}
-
-bool vid_is_dsa_8021q_txvlan(u16 vid)
-{
-	return false;
-}
-
-bool vid_is_dsa_8021q(u16 vid)
-{
-	return false;
-}
-
-#endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */
-
 #endif /* _NET_DSA_8021Q_H */
diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h
index 1eb84562b311..b6089b88314c 100644
--- a/include/linux/dsa/sja1105.h
+++ b/include/linux/dsa/sja1105.h
@@ -14,6 +14,7 @@
 
 #define ETH_P_SJA1105				ETH_P_DSA_8021Q
 #define ETH_P_SJA1105_META			0x0008
+#define ETH_P_SJA1110				0xdadc
 
 /* IEEE 802.3 Annex 57A: Slow Protocols PDUs (01:80:C2:xx:xx:xx) */
 #define SJA1105_LINKLOCAL_FILTER_A		0x0180C2000000ull
@@ -44,11 +45,14 @@ struct sja1105_tagger_data {
 	 */
 	spinlock_t meta_lock;
 	unsigned long state;
+	u8 ts_id;
 };
 
 struct sja1105_skb_cb {
 	struct sk_buff *clone;
-	u32 meta_tstamp;
+	u64 tstamp;
+	/* Only valid for packets cloned for 2-step TX timestamping */
+	u8 ts_id;
 };
 
 #define SJA1105_SKB_CB(skb) \
@@ -65,4 +69,24 @@ struct sja1105_port {
 	u16 xmit_tpid;
 };
 
+enum sja1110_meta_tstamp {
+	SJA1110_META_TSTAMP_TX = 0,
+	SJA1110_META_TSTAMP_RX = 1,
+};
+
+#if IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP)
+
+void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id,
+				 enum sja1110_meta_tstamp dir, u64 tstamp);
+
+#else
+
+static inline void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port,
+					       u8 ts_id, enum sja1110_meta_tstamp dir,
+					       u64 tstamp)
+{
+}
+
+#endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */
+
 #endif /* _NET_DSA_SJA1105_H */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 9a09547bc7ba..688856e0b28a 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -646,6 +646,7 @@ struct bpf_redirect_info {
 	u32 flags;
 	u32 tgt_index;
 	void *tgt_value;
+	struct bpf_map *map;
 	u32 map_id;
 	enum bpf_map_type map_type;
 	u32 kern_flags;
@@ -995,11 +996,13 @@ void bpf_warn_invalid_xdp_action(u32 act);
 #ifdef CONFIG_INET
 struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
 				  struct bpf_prog *prog, struct sk_buff *skb,
+				  struct sock *migrating_sk,
 				  u32 hash);
 #else
 static inline struct sock *
 bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
 		     struct bpf_prog *prog, struct sk_buff *skb,
+		     struct sock *migrating_sk,
 		     u32 hash)
 {
 	return NULL;
@@ -1464,17 +1467,19 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol,
 }
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 
-static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, u64 flags,
+static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex,
+						  u64 flags, const u64 flag_mask,
 						  void *lookup_elem(struct bpf_map *map, u32 key))
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX;
 
 	/* Lower bits of the flags are used as return code on lookup failure */
-	if (unlikely(flags > XDP_TX))
+	if (unlikely(flags & ~(action_mask | flag_mask)))
 		return XDP_ABORTED;
 
 	ri->tgt_value = lookup_elem(map, ifindex);
-	if (unlikely(!ri->tgt_value)) {
+	if (unlikely(!ri->tgt_value) && !(flags & BPF_F_BROADCAST)) {
 		/* If the lookup fails we want to clear out the state in the
 		 * redirect_info struct completely, so that if an eBPF program
 		 * performs multiple lookups, the last one always takes
@@ -1482,13 +1487,21 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifind
 		 */
 		ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */
 		ri->map_type = BPF_MAP_TYPE_UNSPEC;
-		return flags;
+		return flags & action_mask;
 	}
 
 	ri->tgt_index = ifindex;
 	ri->map_id = map->id;
 	ri->map_type = map->map_type;
 
+	if (flags & BPF_F_BROADCAST) {
+		WRITE_ONCE(ri->map, map);
+		ri->flags = flags;
+	} else {
+		WRITE_ONCE(ri->map, NULL);
+		ri->flags = 0;
+	}
+
 	return XDP_REDIRECT;
 }
 
diff --git a/include/linux/fwnode_mdio.h b/include/linux/fwnode_mdio.h
new file mode 100644
index 000000000000..faf603c48c86
--- /dev/null
+++ b/include/linux/fwnode_mdio.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * FWNODE helper for the MDIO (Ethernet PHY) API
+ */
+
+#ifndef __LINUX_FWNODE_MDIO_H
+#define __LINUX_FWNODE_MDIO_H
+
+#include <linux/phy.h>
+
+#if IS_ENABLED(CONFIG_FWNODE_MDIO)
+int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio,
+				       struct phy_device *phy,
+				       struct fwnode_handle *child, u32 addr);
+
+int fwnode_mdiobus_register_phy(struct mii_bus *bus,
+				struct fwnode_handle *child, u32 addr);
+
+#else /* CONFIG_FWNODE_MDIO */
+int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio,
+				       struct phy_device *phy,
+				       struct fwnode_handle *child, u32 addr)
+{
+	return -EINVAL;
+}
+
+static inline int fwnode_mdiobus_register_phy(struct mii_bus *bus,
+					      struct fwnode_handle *child,
+					      u32 addr)
+{
+	return -EINVAL;
+}
+#endif
+
+#endif /* __LINUX_FWNODE_MDIO_H */
diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 2cc35038a8ca..12e9a32dbca0 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -67,6 +67,7 @@ int br_multicast_list_adjacent(struct net_device *dev,
 			       struct list_head *br_ip_list);
 bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto);
 bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto);
+bool br_multicast_has_router_adjacent(struct net_device *dev, int proto);
 bool br_multicast_enabled(const struct net_device *dev);
 bool br_multicast_router(const struct net_device *dev);
 int br_mdb_replay(struct net_device *br_dev, struct net_device *dev,
@@ -87,6 +88,13 @@ static inline bool br_multicast_has_querier_adjacent(struct net_device *dev,
 {
 	return false;
 }
+
+static inline bool br_multicast_has_router_adjacent(struct net_device *dev,
+						    int proto)
+{
+	return true;
+}
+
 static inline bool br_multicast_enabled(const struct net_device *dev)
 {
 	return false;
diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h
index 4efb537f57f3..10e7521ecb6c 100644
--- a/include/linux/if_rmnet.h
+++ b/include/linux/if_rmnet.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0-only
- * Copyright (c) 2013-2019, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2013-2019, 2021 The Linux Foundation. All rights reserved.
  */
 
 #ifndef _LINUX_IF_RMNET_H_
@@ -12,10 +12,12 @@ struct rmnet_map_header {
 }  __aligned(1);
 
 /* rmnet_map_header flags field:
- *  PAD_LEN:	number of pad bytes following packet data
- *  CMD:	1 = packet contains a MAP command; 0 = packet contains data
+ *  PAD_LEN:	  number of pad bytes following packet data
+ *  CMD:	  1 = packet contains a MAP command; 0 = packet contains data
+ *  NEXT_HEADER: 1 = packet contains V5 CSUM header 0 = no V5 CSUM header
  */
 #define MAP_PAD_LEN_MASK		GENMASK(5, 0)
+#define MAP_NEXT_HEADER_FLAG		BIT(6)
 #define MAP_CMD_FLAG			BIT(7)
 
 struct rmnet_map_dl_csum_trailer {
@@ -23,7 +25,7 @@ struct rmnet_map_dl_csum_trailer {
 	u8 flags;			/* MAP_CSUM_DL_VALID_FLAG */
 	__be16 csum_start_offset;
 	__be16 csum_length;
-	__be16 csum_value;
+	__sum16 csum_value;
 } __aligned(1);
 
 /* rmnet_map_dl_csum_trailer flags field:
@@ -45,4 +47,26 @@ struct rmnet_map_ul_csum_header {
 #define MAP_CSUM_UL_UDP_FLAG		BIT(14)
 #define MAP_CSUM_UL_ENABLED_FLAG	BIT(15)
 
+/* MAP CSUM headers */
+struct rmnet_map_v5_csum_header {
+	u8 header_info;
+	u8 csum_info;
+	__be16 reserved;
+} __aligned(1);
+
+/* v5 header_info field
+ * NEXT_HEADER: represents whether there is any next header
+ * HEADER_TYPE: represents the type of this header
+ *
+ * csum_info field
+ * CSUM_VALID_OR_REQ:
+ * 1 = for UL, checksum computation is requested.
+ * 1 = for DL, validated the checksum and has found it valid
+ */
+
+#define MAPV5_HDRINFO_NXT_HDR_FLAG	BIT(0)
+#define MAPV5_HDRINFO_HDR_TYPE_FMASK	GENMASK(7, 1)
+#define MAPV5_CSUMINFO_VALID_FLAG	BIT(7)
+
+#define RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD 2
 #endif /* !(_LINUX_IF_RMNET_H_) */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 15d8bad3d2f2..e73f3bc3dba5 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -71,6 +71,18 @@
  */
 #define lower_32_bits(n) ((u32)((n) & 0xffffffff))
 
+/**
+ * upper_16_bits - return bits 16-31 of a number
+ * @n: the number we're accessing
+ */
+#define upper_16_bits(n) ((u16)((n) >> 16))
+
+/**
+ * lower_16_bits - return bits 0-15 of a number
+ * @n: the number we're accessing
+ */
+#define lower_16_bits(n) ((u16)((n) & 0xffff))
+
 struct completion;
 struct pt_regs;
 struct user;
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index 416ee6dd2574..3d43c60b49fa 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -39,10 +39,26 @@
 /* struct phy_device dev_flags definitions */
 #define MICREL_PHY_50MHZ_CLK	0x00000001
 #define MICREL_PHY_FXEN		0x00000002
+#define MICREL_KSZ8_P1_ERRATA	0x00000003
 
 #define MICREL_KSZ9021_EXTREG_CTRL	0xB
 #define MICREL_KSZ9021_EXTREG_DATA_WRITE	0xC
 #define MICREL_KSZ9021_RGMII_CLK_CTRL_PAD_SCEW	0x104
 #define MICREL_KSZ9021_RGMII_RX_DATA_PAD_SCEW	0x105
 
+/* Device specific MII_BMCR (Reg 0) bits */
+/* 1 = HP Auto MDI/MDI-X mode, 0 = Microchip Auto MDI/MDI-X mode */
+#define KSZ886X_BMCR_HP_MDIX			BIT(5)
+/* 1 = Force MDI (transmit on RXP/RXM pins), 0 = Normal operation
+ * (transmit on TXP/TXM pins)
+ */
+#define KSZ886X_BMCR_FORCE_MDI			BIT(4)
+/* 1 = Disable auto MDI-X */
+#define KSZ886X_BMCR_DISABLE_AUTO_MDIX		BIT(3)
+#define KSZ886X_BMCR_DISABLE_FAR_END_FAULT	BIT(2)
+#define KSZ886X_BMCR_DISABLE_TRANSMIT		BIT(1)
+#define KSZ886X_BMCR_DISABLE_LED		BIT(0)
+
+#define KSZ886X_CTRL_MDIX_STAT			BIT(4)
+
 #endif /* _MICREL_PHY_H */
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 578c4ccae91c..0025913505ab 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1179,6 +1179,7 @@ enum mlx5_cap_type {
 	MLX5_CAP_VDPA_EMULATION = 0x13,
 	MLX5_CAP_DEV_EVENT = 0x14,
 	MLX5_CAP_IPSEC,
+	MLX5_CAP_GENERAL_2 = 0x20,
 	/* NUM OF CAP Types */
 	MLX5_CAP_NUM
 };
@@ -1220,6 +1221,15 @@ enum mlx5_qcam_feature_groups {
 #define MLX5_CAP_GEN_MAX(mdev, cap) \
 	MLX5_GET(cmd_hca_cap, mdev->caps.hca_max[MLX5_CAP_GENERAL], cap)
 
+#define MLX5_CAP_GEN_2(mdev, cap) \
+	MLX5_GET(cmd_hca_cap_2, mdev->caps.hca_cur[MLX5_CAP_GENERAL_2], cap)
+
+#define MLX5_CAP_GEN_2_64(mdev, cap) \
+	MLX5_GET64(cmd_hca_cap_2, mdev->caps.hca_cur[MLX5_CAP_GENERAL_2], cap)
+
+#define MLX5_CAP_GEN_2_MAX(mdev, cap) \
+	MLX5_GET(cmd_hca_cap_2, mdev->caps.hca_max[MLX5_CAP_GENERAL_2], cap)
+
 #define MLX5_CAP_ETH(mdev, cap) \
 	MLX5_GET(per_protocol_networking_offload_caps,\
 		 mdev->caps.hca_cur[MLX5_CAP_ETHERNET_OFFLOADS], cap)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f8902bcd91e2..1efe37466969 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -554,6 +554,7 @@ struct mlx5_adev {
 	int idx;
 };
 
+struct mlx5_ft_pool;
 struct mlx5_priv {
 	/* IRQ table valid only for real pci devices PF or VF */
 	struct mlx5_irq_table   *irq_table;
@@ -606,6 +607,7 @@ struct mlx5_priv {
 	struct mlx5_core_roce	roce;
 	struct mlx5_fc_stats		fc_stats;
 	struct mlx5_rl_table            rl_table;
+	struct mlx5_ft_pool		*ft_pool;
 
 	struct mlx5_bfreg_data		bfregs;
 	struct mlx5_uars_page	       *uar;
diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h
index e49d8c0d4f26..cea6ecb4b73e 100644
--- a/include/linux/mlx5/eq.h
+++ b/include/linux/mlx5/eq.h
@@ -16,6 +16,7 @@ struct mlx5_eq_param {
 	u8             irq_index;
 	int            nent;
 	u64            mask[4];
+	cpumask_var_t  affinity;
 };
 
 struct mlx5_eq *
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index 17109b65c1ac..bc7db2e059eb 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -98,10 +98,11 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw,
 					    u16 vport_num);
 
 /* Reg C1 usage:
- * Reg C1 = < ESW_TUN_ID(12) | ESW_TUN_OPTS(12) | ESW_ZONE_ID(8) >
+ * Reg C1 = < Reserved(1) | ESW_TUN_ID(12) | ESW_TUN_OPTS(11) | ESW_ZONE_ID(8) >
  *
- * Highest 12 bits of reg c1 is the encapsulation tunnel id, next 12 bits is
- * encapsulation tunnel options, and the lowest 8 bits are used for zone id.
+ * Highest bit is reserved for other offloads as marker bit, next 12 bits of reg c1
+ * is the encapsulation tunnel id, next 11 bits is encapsulation tunnel options,
+ * and the lowest 8 bits are used for zone id.
  *
  * Zone id is used to restore CT flow when packet misses on chain.
  *
@@ -109,16 +110,18 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw,
  * on miss and to support inner header rewrite by means of implicit chain 0
  * flows.
  */
+#define ESW_RESERVED_BITS 1
 #define ESW_ZONE_ID_BITS 8
-#define ESW_TUN_OPTS_BITS 12
+#define ESW_TUN_OPTS_BITS 11
 #define ESW_TUN_ID_BITS 12
 #define ESW_TUN_OPTS_OFFSET ESW_ZONE_ID_BITS
 #define ESW_TUN_OFFSET ESW_TUN_OPTS_OFFSET
 #define ESW_ZONE_ID_MASK GENMASK(ESW_ZONE_ID_BITS - 1, 0)
-#define ESW_TUN_OPTS_MASK GENMASK(32 - ESW_TUN_ID_BITS - 1, ESW_TUN_OPTS_OFFSET)
-#define ESW_TUN_MASK GENMASK(31, ESW_TUN_OFFSET)
+#define ESW_TUN_OPTS_MASK GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, ESW_TUN_OPTS_OFFSET)
+#define ESW_TUN_MASK GENMASK(31 - ESW_RESERVED_BITS, ESW_TUN_OFFSET)
 #define ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT 0 /* 0 is not a valid tunnel id */
-#define ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT 0xFFF /* 0xFFF is a reserved mapping */
+/* 0x7FF is a reserved mapping */
+#define ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT GENMASK(ESW_TUN_OPTS_BITS - 1, 0)
 #define ESW_TUN_SLOW_TABLE_GOTO_VPORT ((ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT << ESW_TUN_OPTS_BITS) | \
 				       ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT)
 #define ESW_TUN_SLOW_TABLE_GOTO_VPORT_MARK ESW_TUN_OPTS_MASK
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 1f51f4c3b1af..77746f7e35b8 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -87,6 +87,8 @@ enum {
 	FDB_BYPASS_PATH,
 	FDB_TC_OFFLOAD,
 	FDB_FT_OFFLOAD,
+	FDB_TC_MISS,
+	FDB_BR_OFFLOAD,
 	FDB_SLOW_PATH,
 	FDB_PER_VPORT,
 };
@@ -254,10 +256,16 @@ struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
 void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev,
 				struct mlx5_modify_hdr *modify_hdr);
 
+struct mlx5_pkt_reformat_params {
+	int type;
+	u8 param_0;
+	u8 param_1;
+	size_t size;
+	void *data;
+};
+
 struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev,
-						     int reformat_type,
-						     size_t size,
-						     void *reformat_data,
+						     struct mlx5_pkt_reformat_params *params,
 						     enum mlx5_flow_namespace_type ns_type);
 void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev,
 				  struct mlx5_pkt_reformat *reformat);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index eb86e80e4643..2d1ed78289ff 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -435,7 +435,10 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 
 	u8         reserved_at_40[0x20];
 
-	u8         reserved_at_60[0x18];
+	u8         reserved_at_60[0x2];
+	u8         reformat_insert[0x1];
+	u8         reformat_remove[0x1];
+	u8         reserver_at_64[0x14];
 	u8         log_max_ft_num[0x8];
 
 	u8         reserved_at_80[0x10];
@@ -1312,7 +1315,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_0[0x1f];
 	u8         vhca_resource_manager[0x1];
 
-	u8         reserved_at_20[0x3];
+	u8         hca_cap_2[0x1];
+	u8         reserved_at_21[0x2];
 	u8         event_on_vhca_state_teardown_request[0x1];
 	u8         event_on_vhca_state_in_use[0x1];
 	u8         event_on_vhca_state_active[0x1];
@@ -1732,6 +1736,17 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8	   reserved_at_7c0[0x40];
 };
 
+struct mlx5_ifc_cmd_hca_cap_2_bits {
+	u8	   reserved_at_0[0xa0];
+
+	u8	   max_reformat_insert_size[0x8];
+	u8	   max_reformat_insert_offset[0x8];
+	u8	   max_reformat_remove_size[0x8];
+	u8	   max_reformat_remove_offset[0x8];
+
+	u8	   reserved_at_c0[0x740];
+};
+
 enum mlx5_flow_destination_type {
 	MLX5_FLOW_DESTINATION_TYPE_VPORT        = 0x0,
 	MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE   = 0x1,
@@ -3105,6 +3120,7 @@ struct mlx5_ifc_roce_addr_layout_bits {
 
 union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_cmd_hca_cap_bits cmd_hca_cap;
+	struct mlx5_ifc_cmd_hca_cap_2_bits cmd_hca_cap_2;
 	struct mlx5_ifc_odp_cap_bits odp_cap;
 	struct mlx5_ifc_atomic_caps_bits atomic_caps;
 	struct mlx5_ifc_roce_cap_bits roce_cap;
@@ -3790,8 +3806,8 @@ struct mlx5_ifc_eqc_bits {
 
 	u8         reserved_at_80[0x20];
 
-	u8         reserved_at_a0[0x18];
-	u8         intr[0x8];
+	u8         reserved_at_a0[0x14];
+	u8         intr[0xc];
 
 	u8         reserved_at_c0[0x3];
 	u8         log_page_size[0x5];
@@ -5785,12 +5801,14 @@ struct mlx5_ifc_query_eq_in_bits {
 };
 
 struct mlx5_ifc_packet_reformat_context_in_bits {
-	u8         reserved_at_0[0x5];
-	u8         reformat_type[0x3];
-	u8         reserved_at_8[0xe];
+	u8         reformat_type[0x8];
+	u8         reserved_at_8[0x4];
+	u8         reformat_param_0[0x4];
+	u8         reserved_at_10[0x6];
 	u8         reformat_data_size[0xa];
 
-	u8         reserved_at_20[0x10];
+	u8         reformat_param_1[0x8];
+	u8         reserved_at_28[0x8];
 	u8         reformat_data[2][0x8];
 
 	u8         more_reformat_data[][0x8];
@@ -5830,12 +5848,20 @@ struct mlx5_ifc_alloc_packet_reformat_context_out_bits {
 	u8         reserved_at_60[0x20];
 };
 
+enum {
+	MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START = 0x1,
+	MLX5_REFORMAT_CONTEXT_ANCHOR_IP_START = 0x7,
+	MLX5_REFORMAT_CONTEXT_ANCHOR_TCP_UDP_START = 0x9,
+};
+
 enum mlx5_reformat_ctx_type {
 	MLX5_REFORMAT_TYPE_L2_TO_VXLAN = 0x0,
 	MLX5_REFORMAT_TYPE_L2_TO_NVGRE = 0x1,
 	MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL = 0x2,
 	MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2 = 0x3,
 	MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4,
+	MLX5_REFORMAT_TYPE_INSERT_HDR = 0xf,
+	MLX5_REFORMAT_TYPE_REMOVE_HDR = 0x10,
 };
 
 struct mlx5_ifc_alloc_packet_reformat_context_in_bits {
@@ -5956,6 +5982,8 @@ enum {
 	MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM   = 0x59,
 	MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM   = 0x5B,
 	MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME    = 0x5D,
+	MLX5_ACTION_IN_FIELD_OUT_EMD_47_32     = 0x6F,
+	MLX5_ACTION_IN_FIELD_OUT_EMD_31_0      = 0x70,
 };
 
 struct mlx5_ifc_alloc_modify_header_context_out_bits {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8ae31622deef..6cf4c6842ff0 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1668,10 +1668,11 @@ struct address_space *page_mapping(struct page *page);
 static inline bool page_is_pfmemalloc(const struct page *page)
 {
 	/*
-	 * Page index cannot be this large so this must be
-	 * a pfmemalloc page.
+	 * lru.next has bit 1 set if the page is allocated from the
+	 * pfmemalloc reserves.  Callers may simply overwrite it if
+	 * they do not need to preserve that information.
 	 */
-	return page->index == -1UL;
+	return (uintptr_t)page->lru.next & BIT(1);
 }
 
 /*
@@ -1680,12 +1681,12 @@ static inline bool page_is_pfmemalloc(const struct page *page)
  */
 static inline void set_page_pfmemalloc(struct page *page)
 {
-	page->index = -1UL;
+	page->lru.next = (void *)BIT(1);
 }
 
 static inline void clear_page_pfmemalloc(struct page *page)
 {
-	page->index = 0;
+	page->lru.next = NULL;
 }
 
 /*
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 8f0fb62e8975..862f88a8c28a 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -97,6 +97,13 @@ struct page {
 		};
 		struct {	/* page_pool used by netstack */
 			/**
+			 * @pp_magic: magic value to avoid recycling non
+			 * page_pool allocated pages.
+			 */
+			unsigned long pp_magic;
+			struct page_pool *pp;
+			unsigned long _pp_mapping_pad;
+			/**
 			 * @dma_addr: might require a 64-bit value on
 			 * 32-bit architectures.
 			 */
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 7d45b5f989b0..8e291cfdaf06 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -447,6 +447,7 @@ struct hv_vmbus_device_id {
 
 struct rpmsg_device_id {
 	char name[RPMSG_NAME_SIZE];
+	kernel_ulong_t driver_data;
 };
 
 /* i2c */
diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h
index f41387a8969f..41f24b5241ab 100644
--- a/include/linux/net/intel/i40e_client.h
+++ b/include/linux/net/intel/i40e_client.h
@@ -4,6 +4,8 @@
 #ifndef _I40E_CLIENT_H_
 #define _I40E_CLIENT_H_
 
+#include <linux/auxiliary_bus.h>
+
 #define I40E_CLIENT_STR_LENGTH 10
 
 /* Client interface version should be updated anytime there is a change in the
@@ -48,7 +50,7 @@ struct i40e_qv_info {
 
 struct i40e_qvlist_info {
 	u32 num_vectors;
-	struct i40e_qv_info qv_info[1];
+	struct i40e_qv_info qv_info[];
 };
 
 
@@ -78,6 +80,7 @@ struct i40e_info {
 	u8 lanmac[6];
 	struct net_device *netdev;
 	struct pci_dev *pcidev;
+	struct auxiliary_device *aux_dev;
 	u8 __iomem *hw_addr;
 	u8 fid;	/* function id, PF id or VF id */
 #define I40E_CLIENT_FTYPE_PF 0
@@ -100,6 +103,11 @@ struct i40e_info {
 	u32 fw_build;                   /* firmware build number */
 };
 
+struct i40e_auxiliary_device {
+	struct auxiliary_device aux_dev;
+	struct i40e_info *ldev;
+};
+
 #define I40E_CLIENT_RESET_LEVEL_PF   1
 #define I40E_CLIENT_RESET_LEVEL_CORE 2
 #define I40E_CLIENT_VSI_FLAG_TCP_ENABLE  BIT(1)
@@ -187,6 +195,8 @@ static inline bool i40e_client_is_registered(struct i40e_client *client)
 	return test_bit(__I40E_CLIENT_REGISTERED, &client->state);
 }
 
+void i40e_client_device_register(struct i40e_info *ldev, struct i40e_client *client);
+void i40e_client_device_unregister(struct i40e_info *ldev);
 /* used by clients */
 int i40e_register_client(struct i40e_client *client);
 int i40e_unregister_client(struct i40e_client *client);
diff --git a/include/linux/net/intel/iidc.h b/include/linux/net/intel/iidc.h
new file mode 100644
index 000000000000..e32f6712aee0
--- /dev/null
+++ b/include/linux/net/intel/iidc.h
@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021, Intel Corporation. */
+
+#ifndef _IIDC_H_
+#define _IIDC_H_
+
+#include <linux/auxiliary_bus.h>
+#include <linux/dcbnl.h>
+#include <linux/device.h>
+#include <linux/if_ether.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+
+enum iidc_event_type {
+	IIDC_EVENT_BEFORE_MTU_CHANGE,
+	IIDC_EVENT_AFTER_MTU_CHANGE,
+	IIDC_EVENT_BEFORE_TC_CHANGE,
+	IIDC_EVENT_AFTER_TC_CHANGE,
+	IIDC_EVENT_CRIT_ERR,
+	IIDC_EVENT_NBITS		/* must be last */
+};
+
+enum iidc_reset_type {
+	IIDC_PFR,
+	IIDC_CORER,
+	IIDC_GLOBR,
+};
+
+#define IIDC_MAX_USER_PRIORITY		8
+
+/* Struct to hold per RDMA Qset info */
+struct iidc_rdma_qset_params {
+	/* Qset TEID returned to the RDMA driver in
+	 * ice_add_rdma_qset and used by RDMA driver
+	 * for calls to ice_del_rdma_qset
+	 */
+	u32 teid;	/* Qset TEID */
+	u16 qs_handle; /* RDMA driver provides this */
+	u16 vport_id; /* VSI index */
+	u8 tc; /* TC branch the Qset should belong to */
+};
+
+struct iidc_qos_info {
+	u64 tc_ctx;
+	u8 rel_bw;
+	u8 prio_type;
+	u8 egress_virt_up;
+	u8 ingress_virt_up;
+};
+
+/* Struct to pass QoS info */
+struct iidc_qos_params {
+	struct iidc_qos_info tc_info[IEEE_8021QAZ_MAX_TCS];
+	u8 up2tc[IIDC_MAX_USER_PRIORITY];
+	u8 vport_relative_bw;
+	u8 vport_priority_type;
+	u8 num_tc;
+};
+
+struct iidc_event {
+	DECLARE_BITMAP(type, IIDC_EVENT_NBITS);
+	u32 reg;
+};
+
+struct ice_pf;
+
+int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset);
+int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset);
+int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type);
+int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable);
+void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos);
+
+#define IIDC_RDMA_ROCE_NAME	"roce"
+
+/* Structure representing auxiliary driver tailored information about the core
+ * PCI dev, each auxiliary driver using the IIDC interface will have an
+ * instance of this struct dedicated to it.
+ */
+
+struct iidc_auxiliary_dev {
+	struct auxiliary_device adev;
+	struct ice_pf *pf;
+};
+
+/* structure representing the auxiliary driver. This struct is to be
+ * allocated and populated by the auxiliary driver's owner. The core PCI
+ * driver will access these ops by performing a container_of on the
+ * auxiliary_device->dev.driver.
+ */
+struct iidc_auxiliary_drv {
+	struct auxiliary_driver adrv;
+	/* This event_handler is meant to be a blocking call.  For instance,
+	 * when a BEFORE_MTU_CHANGE event comes in, the event_handler will not
+	 * return until the auxiliary driver is ready for the MTU change to
+	 * happen.
+	 */
+	void (*event_handler)(struct ice_pf *pf, struct iidc_event *event);
+};
+
+#endif /* _IIDC_H_*/
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 3de38d6a0aea..2c6b9e416225 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -93,7 +93,7 @@ enum {
 
 	/*
 	 * Add your fresh new feature above and remember to update
-	 * netdev_features_strings[] in net/core/ethtool.c and maybe
+	 * netdev_features_strings[] in net/ethtool/common.c and maybe
 	 * some feature mask #defines below. Please also describe it
 	 * in Documentation/networking/netdev-features.rst.
 	 */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5cbc950b34df..be1dcceda5e4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4187,8 +4187,8 @@ unsigned long dev_trans_start(struct net_device *dev);
 void __netdev_watchdog_up(struct net_device *dev);
 
 void netif_carrier_on(struct net_device *dev);
-
 void netif_carrier_off(struct net_device *dev);
+void netif_carrier_event(struct net_device *dev);
 
 /**
  *	netif_dormant_on - mark device as dormant.
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index f0f3a8354c3c..3fda1a508733 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -65,8 +65,8 @@ struct nf_hook_ops;
 struct sock;
 
 struct nf_hook_state {
-	unsigned int hook;
-	u_int8_t pf;
+	u8 hook;
+	u8 pf;
 	struct net_device *in;
 	struct net_device *out;
 	struct sock *sk;
@@ -77,12 +77,18 @@ struct nf_hook_state {
 typedef unsigned int nf_hookfn(void *priv,
 			       struct sk_buff *skb,
 			       const struct nf_hook_state *state);
+enum nf_hook_ops_type {
+	NF_HOOK_OP_UNDEFINED,
+	NF_HOOK_OP_NF_TABLES,
+};
+
 struct nf_hook_ops {
 	/* User fills in from here down. */
 	nf_hookfn		*hook;
 	struct net_device	*dev;
 	void			*priv;
-	u_int8_t		pf;
+	u8			pf;
+	enum nf_hook_ops_type	hook_ops_type:8;
 	unsigned int		hooknum;
 	/* Hooks are ordered in ascending priority. */
 	int			priority;
diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 515ce53aa20d..241e005f290a 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -11,6 +11,7 @@ struct nfnl_info {
 	struct net		*net;
 	struct sock		*sk;
 	const struct nlmsghdr	*nlh;
+	const struct nfgenmsg	*nfmsg;
 	struct netlink_ext_ack	*extack;
 };
 
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 07c6ad8f2a02..28d7027cd460 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -36,8 +36,8 @@ struct xt_action_param {
 		const void *matchinfo, *targinfo;
 	};
 	const struct nf_hook_state *state;
-	int fragoff;
 	unsigned int thoff;
+	u16 fragoff;
 	bool hotdrop;
 };
 
diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h
index 2b05e7f7c238..da633d34ab86 100644
--- a/include/linux/of_mdio.h
+++ b/include/linux/of_mdio.h
@@ -72,6 +72,13 @@ static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *
 	return mdiobus_register(mdio);
 }
 
+static inline int devm_of_mdiobus_register(struct device *dev,
+					   struct mii_bus *mdio,
+					   struct device_node *np)
+{
+	return devm_mdiobus_register(dev, mdio);
+}
+
 static inline struct mdio_device *of_mdio_find_device(struct device_node *np)
 {
 	return NULL;
diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h
index 2cb5188a7ef1..add077a81b21 100644
--- a/include/linux/pcs/pcs-xpcs.h
+++ b/include/linux/pcs/pcs-xpcs.h
@@ -10,37 +10,33 @@
 #include <linux/phy.h>
 #include <linux/phylink.h>
 
+#define NXP_SJA1105_XPCS_ID		0x00000010
+#define NXP_SJA1110_XPCS_ID		0x00000020
+
 /* AN mode */
 #define DW_AN_C73			1
 #define DW_AN_C37_SGMII			2
+#define DW_2500BASEX			3
 
-struct mdio_xpcs_args {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported);
-	struct mii_bus *bus;
-	int addr;
-	int an_mode;
-};
+struct xpcs_id;
 
-struct mdio_xpcs_ops {
-	int (*validate)(struct mdio_xpcs_args *xpcs,
-			unsigned long *supported,
-			struct phylink_link_state *state);
-	int (*config)(struct mdio_xpcs_args *xpcs,
-		      const struct phylink_link_state *state);
-	int (*get_state)(struct mdio_xpcs_args *xpcs,
-			 struct phylink_link_state *state);
-	int (*link_up)(struct mdio_xpcs_args *xpcs, int speed,
-		       phy_interface_t interface);
-	int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface);
+struct dw_xpcs {
+	struct mdio_device *mdiodev;
+	const struct xpcs_id *id;
+	struct phylink_pcs pcs;
 };
 
-#if IS_ENABLED(CONFIG_PCS_XPCS)
-struct mdio_xpcs_ops *mdio_xpcs_get_ops(void);
-#else
-static inline struct mdio_xpcs_ops *mdio_xpcs_get_ops(void)
-{
-	return NULL;
-}
-#endif
+int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface);
+void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode,
+		  phy_interface_t interface, int speed, int duplex);
+int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface,
+		   unsigned int mode);
+void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported,
+		   struct phylink_link_state *state);
+int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns,
+		    int enable);
+struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev,
+			    phy_interface_t interface);
+void xpcs_destroy(struct dw_xpcs *xpcs);
 
 #endif /* __LINUX_PCS_XPCS_H */
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 852743f07e3e..3b80dc3ed68b 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -93,6 +93,7 @@ extern const int phy_10gbit_features_array[1];
  * @PHY_INTERFACE_MODE_TBI: Ten Bit Interface
  * @PHY_INTERFACE_MODE_REVMII: Reverse Media Independent Interface
  * @PHY_INTERFACE_MODE_RMII: Reduced Media Independent Interface
+ * @PHY_INTERFACE_MODE_REVRMII: Reduced Media Independent Interface in PHY role
  * @PHY_INTERFACE_MODE_RGMII: Reduced gigabit media-independent interface
  * @PHY_INTERFACE_MODE_RGMII_ID: RGMII with Internal RX+TX delay
  * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay
@@ -111,6 +112,7 @@ extern const int phy_10gbit_features_array[1];
  * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI
  * @PHY_INTERFACE_MODE_XAUI: 10 Gigabit Attachment Unit Interface
  * @PHY_INTERFACE_MODE_10GBASER: 10G BaseR
+ * @PHY_INTERFACE_MODE_25GBASER: 25G BaseR
  * @PHY_INTERFACE_MODE_USXGMII:  Universal Serial 10GE MII
  * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN
  * @PHY_INTERFACE_MODE_MAX: Book keeping
@@ -126,6 +128,7 @@ typedef enum {
 	PHY_INTERFACE_MODE_TBI,
 	PHY_INTERFACE_MODE_REVMII,
 	PHY_INTERFACE_MODE_RMII,
+	PHY_INTERFACE_MODE_REVRMII,
 	PHY_INTERFACE_MODE_RGMII,
 	PHY_INTERFACE_MODE_RGMII_ID,
 	PHY_INTERFACE_MODE_RGMII_RXID,
@@ -145,6 +148,7 @@ typedef enum {
 	PHY_INTERFACE_MODE_XAUI,
 	/* 10GBASE-R, XFI, SFI - single lane 10G Serdes */
 	PHY_INTERFACE_MODE_10GBASER,
+	PHY_INTERFACE_MODE_25GBASER,
 	PHY_INTERFACE_MODE_USXGMII,
 	/* 10GBASE-KR - with Clause 73 AN */
 	PHY_INTERFACE_MODE_10GKR,
@@ -185,6 +189,8 @@ static inline const char *phy_modes(phy_interface_t interface)
 		return "rev-mii";
 	case PHY_INTERFACE_MODE_RMII:
 		return "rmii";
+	case PHY_INTERFACE_MODE_REVRMII:
+		return "rev-rmii";
 	case PHY_INTERFACE_MODE_RGMII:
 		return "rgmii";
 	case PHY_INTERFACE_MODE_RGMII_ID:
@@ -219,6 +225,8 @@ static inline const char *phy_modes(phy_interface_t interface)
 		return "xaui";
 	case PHY_INTERFACE_MODE_10GBASER:
 		return "10gbase-r";
+	case PHY_INTERFACE_MODE_25GBASER:
+		return "25gbase-r";
 	case PHY_INTERFACE_MODE_USXGMII:
 		return "usxgmii";
 	case PHY_INTERFACE_MODE_10GKR:
@@ -1373,10 +1381,42 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id,
 				     bool is_c45,
 				     struct phy_c45_device_ids *c45_ids);
 #if IS_ENABLED(CONFIG_PHYLIB)
+int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id);
+struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode);
+struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode);
+struct phy_device *device_phy_find_device(struct device *dev);
+struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode);
 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 int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id)
+{
+	return 0;
+}
+static inline
+struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode)
+{
+	return 0;
+}
+
+static inline
+struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode)
+{
+	return NULL;
+}
+
+static inline struct phy_device *device_phy_find_device(struct device *dev)
+{
+	return NULL;
+}
+
+static inline
+struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode)
+{
+	return NULL;
+}
+
 static inline
 struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45)
 {
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index fd2acfd9b597..afb3ded0b691 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -441,6 +441,9 @@ void phylink_destroy(struct phylink *);
 
 int phylink_connect_phy(struct phylink *, struct phy_device *);
 int phylink_of_phy_connect(struct phylink *, struct device_node *, u32 flags);
+int phylink_fwnode_phy_connect(struct phylink *pl,
+			       struct fwnode_handle *fwnode,
+			       u32 flags);
 void phylink_disconnect_phy(struct phylink *);
 
 void phylink_mac_change(struct phylink *, bool up);
diff --git a/include/linux/poison.h b/include/linux/poison.h
index aff1c9250c82..d62ef5a6b4e9 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -78,4 +78,7 @@
 /********** security/ **********/
 #define KEY_DESTROY		0xbd
 
+/********** net/core/page_pool.c **********/
+#define PP_SIGNATURE		(0x40 + POISON_POINTER_DELTA)
+
 #endif
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index 51d7f1b8b32a..aba237c0b3a2 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -186,6 +186,32 @@ struct ptp_clock_event {
 	};
 };
 
+/**
+ * scaled_ppm_to_ppb() - convert scaled ppm to ppb
+ *
+ * @ppm:    Parts per million, but with a 16 bit binary fractional field
+ */
+static inline long scaled_ppm_to_ppb(long ppm)
+{
+	/*
+	 * The 'freq' field in the 'struct timex' is in parts per
+	 * million, but with a 16 bit binary fractional field.
+	 *
+	 * We want to calculate
+	 *
+	 *    ppb = scaled_ppm * 1000 / 2^16
+	 *
+	 * which simplifies to
+	 *
+	 *    ppb = scaled_ppm * 125 / 2^13
+	 */
+	s64 ppb = 1 + ppm;
+
+	ppb *= 125;
+	ppb >>= 13;
+	return (long)ppb;
+}
+
 #if IS_REACHABLE(CONFIG_PTP_1588_CLOCK)
 
 /**
@@ -230,14 +256,6 @@ extern void ptp_clock_event(struct ptp_clock *ptp,
 extern int ptp_clock_index(struct ptp_clock *ptp);
 
 /**
- * scaled_ppm_to_ppb() - convert scaled ppm to ppb
- *
- * @ppm:    Parts per million, but with a 16 bit binary fractional field
- */
-
-extern long scaled_ppm_to_ppb(long ppm);
-
-/**
  * ptp_find_pin() - obtain the pin index of a given auxiliary function
  *
  * The caller must hold ptp_clock::pincfg_mux.  Drivers do not have
diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h
index 977807e1be53..0a3807e927c5 100644
--- a/include/linux/qed/common_hsi.h
+++ b/include/linux/qed/common_hsi.h
@@ -702,7 +702,7 @@ enum mf_mode {
 
 /* Per-protocol connection types */
 enum protocol_type {
-	PROTOCOLID_ISCSI,
+	PROTOCOLID_TCP_ULP,
 	PROTOCOLID_FCOE,
 	PROTOCOLID_ROCE,
 	PROTOCOLID_CORE,
diff --git a/include/linux/qed/nvmetcp_common.h b/include/linux/qed/nvmetcp_common.h
new file mode 100644
index 000000000000..5a2ab0606308
--- /dev/null
+++ b/include/linux/qed/nvmetcp_common.h
@@ -0,0 +1,531 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
+/* Copyright 2021 Marvell. All rights reserved. */
+
+#ifndef __NVMETCP_COMMON__
+#define __NVMETCP_COMMON__
+
+#include "tcp_common.h"
+#include <linux/nvme-tcp.h>
+
+#define NVMETCP_SLOW_PATH_LAYER_CODE (6)
+#define NVMETCP_WQE_NUM_SGES_SLOWIO (0xf)
+
+/* NVMeTCP firmware function init parameters */
+struct nvmetcp_spe_func_init {
+	__le16 half_way_close_timeout;
+	u8 num_sq_pages_in_ring;
+	u8 num_r2tq_pages_in_ring;
+	u8 num_uhq_pages_in_ring;
+	u8 ll2_rx_queue_id;
+	u8 flags;
+#define NVMETCP_SPE_FUNC_INIT_COUNTERS_EN_MASK 0x1
+#define NVMETCP_SPE_FUNC_INIT_COUNTERS_EN_SHIFT 0
+#define NVMETCP_SPE_FUNC_INIT_NVMETCP_MODE_MASK 0x1
+#define NVMETCP_SPE_FUNC_INIT_NVMETCP_MODE_SHIFT 1
+#define NVMETCP_SPE_FUNC_INIT_RESERVED0_MASK 0x3F
+#define NVMETCP_SPE_FUNC_INIT_RESERVED0_SHIFT 2
+	u8 debug_flags;
+	__le16 reserved1;
+	u8 params;
+#define NVMETCP_SPE_FUNC_INIT_MAX_SYN_RT_MASK	0xF
+#define NVMETCP_SPE_FUNC_INIT_MAX_SYN_RT_SHIFT	0
+#define NVMETCP_SPE_FUNC_INIT_RESERVED1_MASK	0xF
+#define NVMETCP_SPE_FUNC_INIT_RESERVED1_SHIFT	4
+	u8 reserved2[5];
+	struct scsi_init_func_params func_params;
+	struct scsi_init_func_queues q_params;
+};
+
+/* NVMeTCP init params passed by driver to FW in NVMeTCP init ramrod. */
+struct nvmetcp_init_ramrod_params {
+	struct nvmetcp_spe_func_init nvmetcp_init_spe;
+	struct tcp_init_params tcp_init;
+};
+
+/* NVMeTCP Ramrod Command IDs */
+enum nvmetcp_ramrod_cmd_id {
+	NVMETCP_RAMROD_CMD_ID_UNUSED = 0,
+	NVMETCP_RAMROD_CMD_ID_INIT_FUNC = 1,
+	NVMETCP_RAMROD_CMD_ID_DESTROY_FUNC = 2,
+	NVMETCP_RAMROD_CMD_ID_OFFLOAD_CONN = 3,
+	NVMETCP_RAMROD_CMD_ID_UPDATE_CONN = 4,
+	NVMETCP_RAMROD_CMD_ID_TERMINATION_CONN = 5,
+	NVMETCP_RAMROD_CMD_ID_CLEAR_SQ = 6,
+	MAX_NVMETCP_RAMROD_CMD_ID
+};
+
+struct nvmetcp_glbl_queue_entry {
+	struct regpair cq_pbl_addr;
+	struct regpair reserved;
+};
+
+/* NVMeTCP conn level EQEs */
+enum nvmetcp_eqe_opcode {
+	NVMETCP_EVENT_TYPE_INIT_FUNC = 0, /* Response after init Ramrod */
+	NVMETCP_EVENT_TYPE_DESTROY_FUNC, /* Response after destroy Ramrod */
+	NVMETCP_EVENT_TYPE_OFFLOAD_CONN,/* Response after option 2 offload Ramrod */
+	NVMETCP_EVENT_TYPE_UPDATE_CONN, /* Response after update Ramrod */
+	NVMETCP_EVENT_TYPE_CLEAR_SQ, /* Response after clear sq Ramrod */
+	NVMETCP_EVENT_TYPE_TERMINATE_CONN, /* Response after termination Ramrod */
+	NVMETCP_EVENT_TYPE_RESERVED0,
+	NVMETCP_EVENT_TYPE_RESERVED1,
+	NVMETCP_EVENT_TYPE_ASYN_CONNECT_COMPLETE, /* Connect completed (A-syn EQE) */
+	NVMETCP_EVENT_TYPE_ASYN_TERMINATE_DONE, /* Termination completed (A-syn EQE) */
+	NVMETCP_EVENT_TYPE_START_OF_ERROR_TYPES = 10, /* Separate EQs from err EQs */
+	NVMETCP_EVENT_TYPE_ASYN_ABORT_RCVD, /* TCP RST packet receive (A-syn EQE) */
+	NVMETCP_EVENT_TYPE_ASYN_CLOSE_RCVD, /* TCP FIN packet receive (A-syn EQE) */
+	NVMETCP_EVENT_TYPE_ASYN_SYN_RCVD, /* TCP SYN+ACK packet receive (A-syn EQE) */
+	NVMETCP_EVENT_TYPE_ASYN_MAX_RT_TIME, /* TCP max retransmit time (A-syn EQE) */
+	NVMETCP_EVENT_TYPE_ASYN_MAX_RT_CNT, /* TCP max retransmit count (A-syn EQE) */
+	NVMETCP_EVENT_TYPE_ASYN_MAX_KA_PROBES_CNT, /* TCP ka probes count (A-syn EQE) */
+	NVMETCP_EVENT_TYPE_ASYN_FIN_WAIT2, /* TCP fin wait 2 (A-syn EQE) */
+	NVMETCP_EVENT_TYPE_NVMETCP_CONN_ERROR, /* NVMeTCP error response (A-syn EQE) */
+	NVMETCP_EVENT_TYPE_TCP_CONN_ERROR, /* NVMeTCP error - tcp error (A-syn EQE) */
+	MAX_NVMETCP_EQE_OPCODE
+};
+
+struct nvmetcp_conn_offload_section {
+	struct regpair cccid_itid_table_addr; /* CCCID to iTID table address */
+	__le16 cccid_max_range; /* CCCID max value - used for validation */
+	__le16 reserved[3];
+};
+
+/* NVMe TCP connection offload params passed by driver to FW in NVMeTCP offload ramrod */
+struct nvmetcp_conn_offload_params {
+	struct regpair sq_pbl_addr;
+	struct regpair r2tq_pbl_addr;
+	struct regpair xhq_pbl_addr;
+	struct regpair uhq_pbl_addr;
+	__le16 physical_q0;
+	__le16 physical_q1;
+	u8 flags;
+#define NVMETCP_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_MASK 0x1
+#define NVMETCP_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_SHIFT 0
+#define NVMETCP_CONN_OFFLOAD_PARAMS_TARGET_MODE_MASK 0x1
+#define NVMETCP_CONN_OFFLOAD_PARAMS_TARGET_MODE_SHIFT 1
+#define NVMETCP_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_MASK 0x1
+#define NVMETCP_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_SHIFT 2
+#define NVMETCP_CONN_OFFLOAD_PARAMS_NVMETCP_MODE_MASK 0x1
+#define NVMETCP_CONN_OFFLOAD_PARAMS_NVMETCP_MODE_SHIFT 3
+#define NVMETCP_CONN_OFFLOAD_PARAMS_RESERVED1_MASK 0xF
+#define NVMETCP_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT 4
+	u8 default_cq;
+	__le16 reserved0;
+	__le32 reserved1;
+	__le32 initial_ack;
+
+	struct nvmetcp_conn_offload_section nvmetcp; /* NVMe/TCP section */
+};
+
+/* NVMe TCP and TCP connection offload params passed by driver to FW in NVMeTCP offload ramrod. */
+struct nvmetcp_spe_conn_offload {
+	__le16 reserved;
+	__le16 conn_id;
+	__le32 fw_cid;
+	struct nvmetcp_conn_offload_params nvmetcp;
+	struct tcp_offload_params_opt2 tcp;
+};
+
+/* NVMeTCP connection update params passed by driver to FW in NVMETCP update ramrod. */
+struct nvmetcp_conn_update_ramrod_params {
+	__le16 reserved0;
+	__le16 conn_id;
+	__le32 reserved1;
+	u8 flags;
+#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_HD_EN_MASK 0x1
+#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_HD_EN_SHIFT 0
+#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_DD_EN_MASK 0x1
+#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_DD_EN_SHIFT 1
+#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED0_MASK 0x1
+#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED0_SHIFT 2
+#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK 0x1
+#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_DATA_SHIFT 3
+#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED2_MASK 0x1
+#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED2_SHIFT 4
+#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED3_MASK 0x1
+#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED3_SHIFT 5
+#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED4_MASK 0x1
+#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED4_SHIFT 6
+#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED5_MASK 0x1
+#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED5_SHIFT 7
+	u8 reserved3[3];
+	__le32 max_seq_size;
+	__le32 max_send_pdu_length;
+	__le32 max_recv_pdu_length;
+	__le32 first_seq_length;
+	__le32 reserved4[5];
+};
+
+/* NVMeTCP connection termination request */
+struct nvmetcp_spe_conn_termination {
+	__le16 reserved0;
+	__le16 conn_id;
+	__le32 reserved1;
+	u8 abortive;
+	u8 reserved2[7];
+	struct regpair reserved3;
+	struct regpair reserved4;
+};
+
+struct nvmetcp_dif_flags {
+	u8 flags;
+};
+
+enum nvmetcp_wqe_type {
+	NVMETCP_WQE_TYPE_NORMAL,
+	NVMETCP_WQE_TYPE_TASK_CLEANUP,
+	NVMETCP_WQE_TYPE_MIDDLE_PATH,
+	NVMETCP_WQE_TYPE_IC,
+	MAX_NVMETCP_WQE_TYPE
+};
+
+struct nvmetcp_wqe {
+	__le16 task_id;
+	u8 flags;
+#define NVMETCP_WQE_WQE_TYPE_MASK 0x7 /* [use nvmetcp_wqe_type] */
+#define NVMETCP_WQE_WQE_TYPE_SHIFT 0
+#define NVMETCP_WQE_NUM_SGES_MASK 0xF
+#define NVMETCP_WQE_NUM_SGES_SHIFT 3
+#define NVMETCP_WQE_RESPONSE_MASK 0x1
+#define NVMETCP_WQE_RESPONSE_SHIFT 7
+	struct nvmetcp_dif_flags prot_flags;
+	__le32 contlen_cdbsize;
+#define NVMETCP_WQE_CONT_LEN_MASK 0xFFFFFF
+#define NVMETCP_WQE_CONT_LEN_SHIFT 0
+#define NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD_MASK 0xFF
+#define NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD_SHIFT 24
+};
+
+struct nvmetcp_host_cccid_itid_entry {
+	__le16 itid;
+};
+
+struct nvmetcp_connect_done_results {
+	__le16 icid;
+	__le16 conn_id;
+	struct tcp_ulp_connect_done_params params;
+};
+
+struct nvmetcp_eqe_data {
+	__le16 icid;
+	__le16 conn_id;
+	__le16 reserved;
+	u8 error_code;
+	u8 error_pdu_opcode_reserved;
+#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_MASK 0x3F
+#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_SHIFT  0
+#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_VALID_MASK  0x1
+#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_VALID_SHIFT  6
+#define NVMETCP_EQE_DATA_RESERVED0_MASK 0x1
+#define NVMETCP_EQE_DATA_RESERVED0_SHIFT 7
+};
+
+enum nvmetcp_task_type {
+	NVMETCP_TASK_TYPE_HOST_WRITE,
+	NVMETCP_TASK_TYPE_HOST_READ,
+	NVMETCP_TASK_TYPE_INIT_CONN_REQUEST,
+	NVMETCP_TASK_TYPE_RESERVED0,
+	NVMETCP_TASK_TYPE_CLEANUP,
+	NVMETCP_TASK_TYPE_HOST_READ_NO_CQE,
+	MAX_NVMETCP_TASK_TYPE
+};
+
+struct nvmetcp_db_data {
+	u8 params;
+#define NVMETCP_DB_DATA_DEST_MASK 0x3 /* destination of doorbell (use enum db_dest) */
+#define NVMETCP_DB_DATA_DEST_SHIFT 0
+#define NVMETCP_DB_DATA_AGG_CMD_MASK 0x3 /* aggregative command to CM (use enum db_agg_cmd_sel) */
+#define NVMETCP_DB_DATA_AGG_CMD_SHIFT 2
+#define NVMETCP_DB_DATA_BYPASS_EN_MASK 0x1 /* enable QM bypass */
+#define NVMETCP_DB_DATA_BYPASS_EN_SHIFT 4
+#define NVMETCP_DB_DATA_RESERVED_MASK 0x1
+#define NVMETCP_DB_DATA_RESERVED_SHIFT 5
+#define NVMETCP_DB_DATA_AGG_VAL_SEL_MASK 0x3 /* aggregative value selection */
+#define NVMETCP_DB_DATA_AGG_VAL_SEL_SHIFT 6
+	u8 agg_flags; /* bit for every DQ counter flags in CM context that DQ can increment */
+	__le16 sq_prod;
+};
+
+struct nvmetcp_fw_nvmf_cqe {
+	__le32 reserved[4];
+};
+
+struct nvmetcp_icresp_mdata {
+	u8  digest;
+	u8  cpda;
+	__le16  pfv;
+	__le32 maxdata;
+	__le16 rsvd[4];
+};
+
+union nvmetcp_fw_cqe_data {
+	struct nvmetcp_fw_nvmf_cqe nvme_cqe;
+	struct nvmetcp_icresp_mdata icresp_mdata;
+};
+
+struct nvmetcp_fw_cqe {
+	__le16 conn_id;
+	u8 cqe_type;
+	u8 cqe_error_status_bits;
+#define CQE_ERROR_BITMAP_DIF_ERR_BITS_MASK 0x7
+#define CQE_ERROR_BITMAP_DIF_ERR_BITS_SHIFT 0
+#define CQE_ERROR_BITMAP_DATA_DIGEST_ERR_MASK 0x1
+#define CQE_ERROR_BITMAP_DATA_DIGEST_ERR_SHIFT 3
+#define CQE_ERROR_BITMAP_RCV_ON_INVALID_CONN_MASK 0x1
+#define CQE_ERROR_BITMAP_RCV_ON_INVALID_CONN_SHIFT 4
+	__le16 itid;
+	u8 task_type;
+	u8 fw_dbg_field;
+	u8 caused_conn_err;
+	u8 reserved0[3];
+	__le32 reserved1;
+	union nvmetcp_fw_cqe_data cqe_data;
+	struct regpair task_opaque;
+	__le32 reserved[6];
+};
+
+enum nvmetcp_fw_cqes_type {
+	NVMETCP_FW_CQE_TYPE_NORMAL = 1,
+	NVMETCP_FW_CQE_TYPE_RESERVED0,
+	NVMETCP_FW_CQE_TYPE_RESERVED1,
+	NVMETCP_FW_CQE_TYPE_CLEANUP,
+	NVMETCP_FW_CQE_TYPE_DUMMY,
+	MAX_NVMETCP_FW_CQES_TYPE
+};
+
+struct ystorm_nvmetcp_task_state {
+	struct scsi_cached_sges data_desc;
+	struct scsi_sgl_params sgl_params;
+	__le32 resrved0;
+	__le32 buffer_offset;
+	__le16 cccid;
+	struct nvmetcp_dif_flags dif_flags;
+	u8 flags;
+#define YSTORM_NVMETCP_TASK_STATE_LOCAL_COMP_MASK 0x1
+#define YSTORM_NVMETCP_TASK_STATE_LOCAL_COMP_SHIFT 0
+#define YSTORM_NVMETCP_TASK_STATE_SLOW_IO_MASK 0x1
+#define YSTORM_NVMETCP_TASK_STATE_SLOW_IO_SHIFT 1
+#define YSTORM_NVMETCP_TASK_STATE_SET_DIF_OFFSET_MASK 0x1
+#define YSTORM_NVMETCP_TASK_STATE_SET_DIF_OFFSET_SHIFT 2
+#define YSTORM_NVMETCP_TASK_STATE_SEND_W_RSP_MASK 0x1
+#define YSTORM_NVMETCP_TASK_STATE_SEND_W_RSP_SHIFT 3
+};
+
+struct ystorm_nvmetcp_task_rxmit_opt {
+	__le32 reserved[4];
+};
+
+struct nvmetcp_task_hdr {
+	__le32 reg[18];
+};
+
+struct nvmetcp_task_hdr_aligned {
+	struct nvmetcp_task_hdr task_hdr;
+	__le32 reserved[2];	/* HSI_COMMENT: Align to QREG */
+};
+
+struct e5_tdif_task_context {
+	__le32 reserved[16];
+};
+
+struct e5_rdif_task_context {
+	__le32 reserved[12];
+};
+
+struct ystorm_nvmetcp_task_st_ctx {
+	struct ystorm_nvmetcp_task_state state;
+	struct ystorm_nvmetcp_task_rxmit_opt rxmit_opt;
+	struct nvmetcp_task_hdr_aligned pdu_hdr;
+};
+
+struct mstorm_nvmetcp_task_st_ctx {
+	struct scsi_cached_sges data_desc;
+	struct scsi_sgl_params sgl_params;
+	__le32 rem_task_size;
+	__le32 data_buffer_offset;
+	u8 task_type;
+	struct nvmetcp_dif_flags dif_flags;
+	__le16 dif_task_icid;
+	struct regpair reserved0;
+	__le32 expected_itt;
+	__le32 reserved1;
+};
+
+struct ustorm_nvmetcp_task_st_ctx {
+	__le32 rem_rcv_len;
+	__le32 exp_data_transfer_len;
+	__le32 exp_data_sn;
+	struct regpair reserved0;
+	__le32 reg1_map;
+#define REG1_NUM_SGES_MASK 0xF
+#define REG1_NUM_SGES_SHIFT 0
+#define REG1_RESERVED1_MASK 0xFFFFFFF
+#define REG1_RESERVED1_SHIFT 4
+	u8 flags2;
+#define USTORM_NVMETCP_TASK_ST_CTX_AHS_EXIST_MASK 0x1
+#define USTORM_NVMETCP_TASK_ST_CTX_AHS_EXIST_SHIFT 0
+#define USTORM_NVMETCP_TASK_ST_CTX_RESERVED1_MASK 0x7F
+#define USTORM_NVMETCP_TASK_ST_CTX_RESERVED1_SHIFT 1
+	struct nvmetcp_dif_flags dif_flags;
+	__le16 reserved3;
+	__le16 tqe_opaque[2];
+	__le32 reserved5;
+	__le32 nvme_tcp_opaque_lo;
+	__le32 nvme_tcp_opaque_hi;
+	u8 task_type;
+	u8 error_flags;
+#define USTORM_NVMETCP_TASK_ST_CTX_DATA_DIGEST_ERROR_MASK 0x1
+#define USTORM_NVMETCP_TASK_ST_CTX_DATA_DIGEST_ERROR_SHIFT 0
+#define USTORM_NVMETCP_TASK_ST_CTX_DATA_TRUNCATED_ERROR_MASK 0x1
+#define USTORM_NVMETCP_TASK_ST_CTX_DATA_TRUNCATED_ERROR_SHIFT 1
+#define USTORM_NVMETCP_TASK_ST_CTX_UNDER_RUN_ERROR_MASK 0x1
+#define USTORM_NVMETCP_TASK_ST_CTX_UNDER_RUN_ERROR_SHIFT 2
+#define USTORM_NVMETCP_TASK_ST_CTX_NVME_TCP_MASK 0x1
+#define USTORM_NVMETCP_TASK_ST_CTX_NVME_TCP_SHIFT 3
+	u8 flags;
+#define USTORM_NVMETCP_TASK_ST_CTX_CQE_WRITE_MASK 0x3
+#define USTORM_NVMETCP_TASK_ST_CTX_CQE_WRITE_SHIFT 0
+#define USTORM_NVMETCP_TASK_ST_CTX_LOCAL_COMP_MASK 0x1
+#define USTORM_NVMETCP_TASK_ST_CTX_LOCAL_COMP_SHIFT 2
+#define USTORM_NVMETCP_TASK_ST_CTX_Q0_R2TQE_WRITE_MASK 0x1
+#define USTORM_NVMETCP_TASK_ST_CTX_Q0_R2TQE_WRITE_SHIFT 3
+#define USTORM_NVMETCP_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_MASK 0x1
+#define USTORM_NVMETCP_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_SHIFT 4
+#define USTORM_NVMETCP_TASK_ST_CTX_HQ_SCANNED_DONE_MASK 0x1
+#define USTORM_NVMETCP_TASK_ST_CTX_HQ_SCANNED_DONE_SHIFT 5
+#define USTORM_NVMETCP_TASK_ST_CTX_R2T2RECV_DONE_MASK 0x1
+#define USTORM_NVMETCP_TASK_ST_CTX_R2T2RECV_DONE_SHIFT 6
+	u8 cq_rss_number;
+};
+
+struct e5_ystorm_nvmetcp_task_ag_ctx {
+	u8 reserved /* cdu_validation */;
+	u8 byte1 /* state_and_core_id */;
+	__le16 word0 /* icid */;
+	u8 flags0;
+	u8 flags1;
+	u8 flags2;
+	u8 flags3;
+	__le32 TTT;
+	u8 byte2;
+	u8 byte3;
+	u8 byte4;
+	u8 e4_reserved7;
+};
+
+struct e5_mstorm_nvmetcp_task_ag_ctx {
+	u8 cdu_validation;
+	u8 byte1;
+	__le16 task_cid;
+	u8 flags0;
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_MASK 0x1
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_SHIFT 5
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_VALID_MASK 0x1
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_VALID_SHIFT 6
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_FLAG_MASK 0x1
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_FLAG_SHIFT 7
+	u8 flags1;
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_MASK 0x3
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_SHIFT 0
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1_MASK 0x3
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1_SHIFT 2
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF2_MASK 0x3
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF2_SHIFT 4
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_EN_MASK 0x1
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_EN_SHIFT 6
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1EN_MASK 0x1
+#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1EN_SHIFT 7
+	u8 flags2;
+	u8 flags3;
+	__le32 reg0;
+	u8 byte2;
+	u8 byte3;
+	u8 byte4;
+	u8 e4_reserved7;
+};
+
+struct e5_ustorm_nvmetcp_task_ag_ctx {
+	u8 reserved;
+	u8 state_and_core_id;
+	__le16 icid;
+	u8 flags0;
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_MASK 0x1
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_SHIFT 5
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_MASK 0x3
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_SHIFT 6
+	u8 flags1;
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_RESERVED1_MASK 0x3
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_RESERVED1_SHIFT 0
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_MASK 0x3
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_SHIFT 2
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3_MASK 0x3
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3_SHIFT 4
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_MASK 0x3
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_SHIFT 6
+	u8 flags2;
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_EN_MASK 0x1
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_EN_SHIFT 0
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_DISABLE_DATA_ACKED_MASK 0x1
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_DISABLE_DATA_ACKED_SHIFT 1
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_EN_MASK 0x1
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_EN_SHIFT 2
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3EN_MASK 0x1
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3EN_SHIFT 3
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_EN_MASK 0x1
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_EN_SHIFT 4
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_DATA_TOTAL_EXP_EN_MASK 0x1
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_DATA_TOTAL_EXP_EN_SHIFT 5
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_RULE1EN_MASK 0x1
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_RULE1EN_SHIFT 6
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_MASK 0x1
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_SHIFT 7
+	u8 flags3;
+	u8 flags4;
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED5_MASK 0x3
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED5_SHIFT 0
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED6_MASK 0x1
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED6_SHIFT 2
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED7_MASK 0x1
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED7_SHIFT 3
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_TYPE_MASK 0xF
+#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_TYPE_SHIFT 4
+	u8 byte2;
+	u8 byte3;
+	u8 e4_reserved8;
+	__le32 dif_err_intervals;
+	__le32 dif_error_1st_interval;
+	__le32 rcv_cont_len;
+	__le32 exp_cont_len;
+	__le32 total_data_acked;
+	__le32 exp_data_acked;
+	__le16 word1;
+	__le16 next_tid;
+	__le32 hdr_residual_count;
+	__le32 exp_r2t_sn;
+};
+
+struct e5_nvmetcp_task_context {
+	struct ystorm_nvmetcp_task_st_ctx ystorm_st_context;
+	struct e5_ystorm_nvmetcp_task_ag_ctx ystorm_ag_context;
+	struct regpair ystorm_ag_padding[2];
+	struct e5_tdif_task_context tdif_context;
+	struct e5_mstorm_nvmetcp_task_ag_ctx mstorm_ag_context;
+	struct regpair mstorm_ag_padding[2];
+	struct e5_ustorm_nvmetcp_task_ag_ctx ustorm_ag_context;
+	struct regpair ustorm_ag_padding[2];
+	struct mstorm_nvmetcp_task_st_ctx mstorm_st_context;
+	struct regpair mstorm_st_padding[2];
+	struct ustorm_nvmetcp_task_st_ctx ustorm_st_context;
+	struct regpair ustorm_st_padding[2];
+	struct e5_rdif_task_context rdif_context;
+};
+
+#endif /* __NVMETCP_COMMON__*/
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index 68d17a4fbf20..850b98991670 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -542,6 +542,22 @@ struct qed_iscsi_pf_params {
 	u8 bdq_pbl_num_entries[3];
 };
 
+struct qed_nvmetcp_pf_params {
+	u64 glbl_q_params_addr;
+	u16 cq_num_entries;
+	u16 num_cons;
+	u16 num_tasks;
+	u8 num_sq_pages_in_ring;
+	u8 num_r2tq_pages_in_ring;
+	u8 num_uhq_pages_in_ring;
+	u8 num_queues;
+	u8 gl_rq_pi;
+	u8 gl_cmd_pi;
+	u8 debug_mode;
+	u8 ll2_ooo_queue_id;
+	u16 min_rto;
+};
+
 struct qed_rdma_pf_params {
 	/* Supplied to QED during resource allocation (may affect the ILT and
 	 * the doorbell BAR).
@@ -560,6 +576,7 @@ struct qed_pf_params {
 	struct qed_eth_pf_params eth_pf_params;
 	struct qed_fcoe_pf_params fcoe_pf_params;
 	struct qed_iscsi_pf_params iscsi_pf_params;
+	struct qed_nvmetcp_pf_params nvmetcp_pf_params;
 	struct qed_rdma_pf_params rdma_pf_params;
 };
 
@@ -662,6 +679,7 @@ enum qed_sb_type {
 enum qed_protocol {
 	QED_PROTOCOL_ETH,
 	QED_PROTOCOL_ISCSI,
+	QED_PROTOCOL_NVMETCP = QED_PROTOCOL_ISCSI,
 	QED_PROTOCOL_FCOE,
 };
 
diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h
index ea273ba1c991..ff808d248883 100644
--- a/include/linux/qed/qed_ll2_if.h
+++ b/include/linux/qed/qed_ll2_if.h
@@ -18,7 +18,7 @@
 
 enum qed_ll2_conn_type {
 	QED_LL2_TYPE_FCOE,
-	QED_LL2_TYPE_ISCSI,
+	QED_LL2_TYPE_TCP_ULP,
 	QED_LL2_TYPE_TEST,
 	QED_LL2_TYPE_OOO,
 	QED_LL2_TYPE_RESERVED2,
diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h
new file mode 100644
index 000000000000..14671bc19ed1
--- /dev/null
+++ b/include/linux/qed/qed_nvmetcp_if.h
@@ -0,0 +1,240 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
+/* Copyright 2021 Marvell. All rights reserved. */
+
+#ifndef _QED_NVMETCP_IF_H
+#define _QED_NVMETCP_IF_H
+#include <linux/types.h>
+#include <linux/qed/qed_if.h>
+#include <linux/qed/storage_common.h>
+#include <linux/qed/nvmetcp_common.h>
+
+#define QED_NVMETCP_MAX_IO_SIZE	0x800000
+#define QED_NVMETCP_CMN_HDR_SIZE (sizeof(struct nvme_tcp_hdr))
+#define QED_NVMETCP_CMD_HDR_SIZE (sizeof(struct nvme_tcp_cmd_pdu))
+#define QED_NVMETCP_NON_IO_HDR_SIZE ((QED_NVMETCP_CMN_HDR_SIZE + 16))
+
+typedef int (*nvmetcp_event_cb_t) (void *context,
+				   u8 fw_event_code, void *fw_handle);
+
+struct qed_dev_nvmetcp_info {
+	struct qed_dev_info common;
+	u8 port_id;  /* Physical port */
+	u8 num_cqs;
+};
+
+#define MAX_TID_BLOCKS_NVMETCP (512)
+struct qed_nvmetcp_tid {
+	u32 size;		/* In bytes per task */
+	u32 num_tids_per_block;
+	u8 *blocks[MAX_TID_BLOCKS_NVMETCP];
+};
+
+struct qed_nvmetcp_id_params {
+	u8 mac[ETH_ALEN];
+	u32 ip[4];
+	u16 port;
+};
+
+struct qed_nvmetcp_params_offload {
+	/* FW initializations */
+	dma_addr_t sq_pbl_addr;
+	dma_addr_t nvmetcp_cccid_itid_table_addr;
+	u16 nvmetcp_cccid_max_range;
+	u8 default_cq;
+
+	/* Networking and TCP stack initializations */
+	struct qed_nvmetcp_id_params src;
+	struct qed_nvmetcp_id_params dst;
+	u32 ka_timeout;
+	u32 ka_interval;
+	u32 max_rt_time;
+	u32 cwnd;
+	u16 mss;
+	u16 vlan_id;
+	bool timestamp_en;
+	bool delayed_ack_en;
+	bool tcp_keep_alive_en;
+	bool ecn_en;
+	u8 ip_version;
+	u8 ka_max_probe_cnt;
+	u8 ttl;
+	u8 tos_or_tc;
+	u8 rcv_wnd_scale;
+};
+
+struct qed_nvmetcp_params_update {
+	u32 max_io_size;
+	u32 max_recv_pdu_length;
+	u32 max_send_pdu_length;
+
+	/* Placeholder: pfv, cpda, hpda */
+
+	bool hdr_digest_en;
+	bool data_digest_en;
+};
+
+struct qed_nvmetcp_cb_ops {
+	struct qed_common_cb_ops common;
+};
+
+struct nvmetcp_sge {
+	struct regpair sge_addr; /* SGE address */
+	__le32 sge_len; /* SGE length */
+	__le32 reserved;
+};
+
+/* IO path HSI function SGL params */
+struct storage_sgl_task_params {
+	struct nvmetcp_sge *sgl;
+	struct regpair sgl_phys_addr;
+	u32 total_buffer_size;
+	u16 num_sges;
+	bool small_mid_sge;
+};
+
+/* IO path HSI function FW task context params */
+struct nvmetcp_task_params {
+	void *context; /* Output parameter - set/filled by the HSI function */
+	struct nvmetcp_wqe *sqe;
+	u32 tx_io_size; /* in bytes (Without DIF, if exists) */
+	u32 rx_io_size; /* in bytes (Without DIF, if exists) */
+	u16 conn_icid;
+	u16 itid;
+	struct regpair opq; /* qedn_task_ctx address */
+	u16 host_cccid;
+	u8 cq_rss_number;
+	bool send_write_incapsule;
+};
+
+/**
+ * struct qed_nvmetcp_ops - qed NVMeTCP operations.
+ * @common:		common operations pointer
+ * @ll2:		light L2 operations pointer
+ * @fill_dev_info:	fills NVMeTCP specific information
+ *			@param cdev
+ *			@param info
+ *			@return 0 on success, otherwise error value.
+ * @register_ops:	register nvmetcp operations
+ *			@param cdev
+ *			@param ops - specified using qed_nvmetcp_cb_ops
+ *			@param cookie - driver private
+ * @start:		nvmetcp in FW
+ *			@param cdev
+ *			@param tasks - qed will fill information about tasks
+ *			return 0 on success, otherwise error value.
+ * @stop:		nvmetcp in FW
+ *			@param cdev
+ *			return 0 on success, otherwise error value.
+ * @acquire_conn:	acquire a new nvmetcp connection
+ *			@param cdev
+ *			@param handle - qed will fill handle that should be
+ *				used henceforth as identifier of the
+ *				connection.
+ *			@param p_doorbell - qed will fill the address of the
+ *				doorbell.
+ *			@return 0 on sucesss, otherwise error value.
+ * @release_conn:	release a previously acquired nvmetcp connection
+ *			@param cdev
+ *			@param handle - the connection handle.
+ *			@return 0 on success, otherwise error value.
+ * @offload_conn:	configures an offloaded connection
+ *			@param cdev
+ *			@param handle - the connection handle.
+ *			@param conn_info - the configuration to use for the
+ *				offload.
+ *			@return 0 on success, otherwise error value.
+ * @update_conn:	updates an offloaded connection
+ *			@param cdev
+ *			@param handle - the connection handle.
+ *			@param conn_info - the configuration to use for the
+ *				offload.
+ *			@return 0 on success, otherwise error value.
+ * @destroy_conn:	stops an offloaded connection
+ *			@param cdev
+ *			@param handle - the connection handle.
+ *			@return 0 on success, otherwise error value.
+ * @clear_sq:		clear all task in sq
+ *			@param cdev
+ *			@param handle - the connection handle.
+ *			@return 0 on success, otherwise error value.
+ * @add_src_tcp_port_filter: Add source tcp port filter
+ *			@param cdev
+ *			@param src_port
+ * @remove_src_tcp_port_filter: Remove source tcp port filter
+ *			@param cdev
+ *			@param src_port
+ * @add_dst_tcp_port_filter: Add destination tcp port filter
+ *			@param cdev
+ *			@param dest_port
+ * @remove_dst_tcp_port_filter: Remove destination tcp port filter
+ *			@param cdev
+ *			@param dest_port
+ * @clear_all_filters: Clear all filters.
+ *			@param cdev
+ */
+struct qed_nvmetcp_ops {
+	const struct qed_common_ops *common;
+
+	const struct qed_ll2_ops *ll2;
+
+	int (*fill_dev_info)(struct qed_dev *cdev,
+			     struct qed_dev_nvmetcp_info *info);
+
+	void (*register_ops)(struct qed_dev *cdev,
+			     struct qed_nvmetcp_cb_ops *ops, void *cookie);
+
+	int (*start)(struct qed_dev *cdev,
+		     struct qed_nvmetcp_tid *tasks,
+		     void *event_context, nvmetcp_event_cb_t async_event_cb);
+
+	int (*stop)(struct qed_dev *cdev);
+
+	int (*acquire_conn)(struct qed_dev *cdev,
+			    u32 *handle,
+			    u32 *fw_cid, void __iomem **p_doorbell);
+
+	int (*release_conn)(struct qed_dev *cdev, u32 handle);
+
+	int (*offload_conn)(struct qed_dev *cdev,
+			    u32 handle,
+			    struct qed_nvmetcp_params_offload *conn_info);
+
+	int (*update_conn)(struct qed_dev *cdev,
+			   u32 handle,
+			   struct qed_nvmetcp_params_update *conn_info);
+
+	int (*destroy_conn)(struct qed_dev *cdev, u32 handle, u8 abrt_conn);
+
+	int (*clear_sq)(struct qed_dev *cdev, u32 handle);
+
+	int (*add_src_tcp_port_filter)(struct qed_dev *cdev, u16 src_port);
+
+	void (*remove_src_tcp_port_filter)(struct qed_dev *cdev, u16 src_port);
+
+	int (*add_dst_tcp_port_filter)(struct qed_dev *cdev, u16 dest_port);
+
+	void (*remove_dst_tcp_port_filter)(struct qed_dev *cdev, u16 dest_port);
+
+	void (*clear_all_filters)(struct qed_dev *cdev);
+
+	void (*init_read_io)(struct nvmetcp_task_params *task_params,
+			     struct nvme_tcp_cmd_pdu *cmd_pdu_header,
+			     struct nvme_command *nvme_cmd,
+			     struct storage_sgl_task_params *sgl_task_params);
+
+	void (*init_write_io)(struct nvmetcp_task_params *task_params,
+			      struct nvme_tcp_cmd_pdu *cmd_pdu_header,
+			      struct nvme_command *nvme_cmd,
+			      struct storage_sgl_task_params *sgl_task_params);
+
+	void (*init_icreq_exchange)(struct nvmetcp_task_params *task_params,
+				    struct nvme_tcp_icreq_pdu *init_conn_req_pdu_hdr,
+				    struct storage_sgl_task_params *tx_sgl_task_params,
+				    struct storage_sgl_task_params *rx_sgl_task_params);
+
+	void (*init_task_cleanup)(struct nvmetcp_task_params *task_params);
+};
+
+const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void);
+void qed_put_nvmetcp_ops(void);
+#endif
diff --git a/include/linux/qed/qed_nvmetcp_ip_services_if.h b/include/linux/qed/qed_nvmetcp_ip_services_if.h
new file mode 100644
index 000000000000..3604aee53796
--- /dev/null
+++ b/include/linux/qed/qed_nvmetcp_ip_services_if.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
+/*
+ * Copyright 2021 Marvell. All rights reserved.
+ */
+
+#ifndef _QED_IP_SERVICES_IF_H
+#define _QED_IP_SERVICES_IF_H
+
+#include <linux/types.h>
+#include <net/route.h>
+#include <net/ip6_route.h>
+#include <linux/inetdevice.h>
+
+int qed_route_ipv4(struct sockaddr_storage *local_addr,
+		   struct sockaddr_storage *remote_addr,
+		   struct sockaddr *hardware_address,
+		   struct net_device **ndev);
+int qed_route_ipv6(struct sockaddr_storage *local_addr,
+		   struct sockaddr_storage *remote_addr,
+		   struct sockaddr *hardware_address,
+		   struct net_device **ndev);
+void qed_vlan_get_ndev(struct net_device **ndev, u16 *vlan_id);
+struct pci_dev *qed_validate_ndev(struct net_device *ndev);
+void qed_return_tcp_port(struct socket *sock);
+int qed_fetch_tcp_port(struct sockaddr_storage local_ip_addr,
+		       struct socket **sock, u16 *port);
+__be16 qed_get_in_port(struct sockaddr_storage *sa);
+
+#endif /* _QED_IP_SERVICES_IF_H */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index dbf820a50a39..b2db9cd9a73f 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -37,6 +37,7 @@
 #include <linux/in6.h>
 #include <linux/if_packet.h>
 #include <net/flow.h>
+#include <net/page_pool.h>
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <linux/netfilter/nf_conntrack_common.h>
 #endif
@@ -667,6 +668,8 @@ typedef unsigned char *sk_buff_data_t;
  *	@head_frag: skb was allocated from page fragments,
  *		not allocated by kmalloc() or vmalloc().
  *	@pfmemalloc: skbuff was allocated from PFMEMALLOC reserves
+ *	@pp_recycle: mark the packet for recycling instead of freeing (implies
+ *		page_pool support on driver)
  *	@active_extensions: active extensions (skb_ext_id types)
  *	@ndisc_nodetype: router type (from link layer)
  *	@ooo_okay: allow the mapping of a socket to a queue to be changed
@@ -791,10 +794,12 @@ struct sk_buff {
 				fclone:2,
 				peeked:1,
 				head_frag:1,
-				pfmemalloc:1;
+				pfmemalloc:1,
+				pp_recycle:1; /* page_pool recycle indicator */
 #ifdef CONFIG_SKB_EXTENSIONS
 	__u8			active_extensions;
 #endif
+
 	/* fields enclosed in headers_start/headers_end are copied
 	 * using a single memcpy() in __copy_skb_header()
 	 */
@@ -3081,12 +3086,20 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f)
 /**
  * __skb_frag_unref - release a reference on a paged fragment.
  * @frag: the paged fragment
+ * @recycle: recycle the page if allocated via page_pool
  *
- * Releases a reference on the paged fragment @frag.
+ * Releases a reference on the paged fragment @frag
+ * or recycles the page via the page_pool API.
  */
-static inline void __skb_frag_unref(skb_frag_t *frag)
+static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle)
 {
-	put_page(skb_frag_page(frag));
+	struct page *page = skb_frag_page(frag);
+
+#ifdef CONFIG_PAGE_POOL
+	if (recycle && page_pool_return_skb_page(page))
+		return;
+#endif
+	put_page(page);
 }
 
 /**
@@ -3098,7 +3111,7 @@ static inline void __skb_frag_unref(skb_frag_t *frag)
  */
 static inline void skb_frag_unref(struct sk_buff *skb, int f)
 {
-	__skb_frag_unref(&skb_shinfo(skb)->frags[f]);
+	__skb_frag_unref(&skb_shinfo(skb)->frags[f], skb->pp_recycle);
 }
 
 /**
@@ -4697,5 +4710,21 @@ static inline u64 skb_get_kcov_handle(struct sk_buff *skb)
 #endif
 }
 
+#ifdef CONFIG_PAGE_POOL
+static inline void skb_mark_for_recycle(struct sk_buff *skb, struct page *page,
+					struct page_pool *pp)
+{
+	skb->pp_recycle = 1;
+	page_pool_store_mem_info(page, pp);
+}
+#endif
+
+static inline bool skb_pp_recycle(struct sk_buff *skb, void *data)
+{
+	if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle)
+		return false;
+	return page_pool_return_skb_page(virt_to_page(data));
+}
+
 #endif	/* __KERNEL__ */
 #endif	/* _LINUX_SKBUFF_H */
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index aba0f0f429be..fcaa9a7996c8 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -126,8 +126,7 @@ int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
 			      struct sk_msg *msg, u32 bytes);
 int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
 			     struct sk_msg *msg, u32 bytes);
-int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags,
-		     long timeo, int *err);
+int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, long timeo);
 int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 		   int len, int flags);
 
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 0db36360ef21..3867980d1447 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -172,6 +172,18 @@ struct stmmac_fpe_cfg {
 	enum stmmac_fpe_state lo_fpe_state;	/* Local station FPE state */
 };
 
+struct stmmac_safety_feature_cfg {
+	u32 tsoee;
+	u32 mrxpee;
+	u32 mestee;
+	u32 mrxee;
+	u32 mtxee;
+	u32 epsi;
+	u32 edpp;
+	u32 prtyen;
+	u32 tmouten;
+};
+
 struct plat_stmmacenet_data {
 	int bus_id;
 	int phy_addr;
@@ -184,6 +196,7 @@ struct plat_stmmacenet_data {
 	struct stmmac_dma_cfg *dma_cfg;
 	struct stmmac_est *est;
 	struct stmmac_fpe_cfg *fpe_cfg;
+	struct stmmac_safety_feature_cfg *safety_feat_cfg;
 	int clk_csr;
 	int has_gmac;
 	int enh_desc;
@@ -210,6 +223,7 @@ struct plat_stmmacenet_data {
 	void (*fix_mac_speed)(void *priv, unsigned int speed);
 	int (*serdes_powerup)(struct net_device *ndev, void *priv);
 	void (*serdes_powerdown)(struct net_device *ndev, void *priv);
+	void (*speed_mode_2500)(struct net_device *ndev, void *priv);
 	void (*ptp_clk_freq_config)(void *priv);
 	int (*init)(struct platform_device *pdev, void *priv);
 	void (*exit)(struct platform_device *pdev, void *priv);
@@ -223,8 +237,10 @@ struct plat_stmmacenet_data {
 	struct clk *clk_ptp_ref;
 	unsigned int clk_ptp_rate;
 	unsigned int clk_ref_rate;
+	unsigned int mult_fact_100ns;
 	s32 ptp_max_adj;
 	struct reset_control *stmmac_rst;
+	struct reset_control *stmmac_ahb_rst;
 	struct stmmac_axi *axi;
 	int has_gmac4;
 	bool has_sun8i;
diff --git a/include/linux/usb/cdc-wdm.h b/include/linux/usb/cdc-wdm.h
index 9b895f93d8de..9f5a51f79ba5 100644
--- a/include/linux/usb/cdc-wdm.h
+++ b/include/linux/usb/cdc-wdm.h
@@ -12,11 +12,12 @@
 #ifndef __LINUX_USB_CDC_WDM_H
 #define __LINUX_USB_CDC_WDM_H
 
+#include <linux/wwan.h>
 #include <uapi/linux/usb/cdc-wdm.h>
 
 extern struct usb_driver *usb_cdc_wdm_register(struct usb_interface *intf,
 					struct usb_endpoint_descriptor *ep,
-					int bufsize,
+					int bufsize, enum wwan_port_type type,
 					int (*manage_power)(struct usb_interface *, int));
 
 #endif /* __LINUX_USB_CDC_WDM_H */
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index dc636b727179..35d7eedb5e8e 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -36,6 +36,7 @@ struct virtio_vsock_sock {
 	u32 rx_bytes;
 	u32 buf_alloc;
 	struct list_head rx_queue;
+	u32 msg_count;
 };
 
 struct virtio_vsock_pkt {
@@ -80,8 +81,17 @@ virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
 			       struct msghdr *msg,
 			       size_t len, int flags);
 
+int
+virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk,
+				   struct msghdr *msg,
+				   size_t len);
+ssize_t
+virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk,
+				   struct msghdr *msg,
+				   int flags);
 s64 virtio_transport_stream_has_data(struct vsock_sock *vsk);
 s64 virtio_transport_stream_has_space(struct vsock_sock *vsk);
+u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk);
 
 int virtio_transport_do_socket_init(struct vsock_sock *vsk,
 				 struct vsock_sock *psk);
diff --git a/include/linux/wwan.h b/include/linux/wwan.h
index aa05a253dcf9..34222230360c 100644
--- a/include/linux/wwan.h
+++ b/include/linux/wwan.h
@@ -6,7 +6,9 @@
 
 #include <linux/device.h>
 #include <linux/kernel.h>
+#include <linux/poll.h>
 #include <linux/skbuff.h>
+#include <linux/netlink.h>
 
 /**
  * enum wwan_port_type - WWAN port types
@@ -15,7 +17,10 @@
  * @WWAN_PORT_QMI: Qcom modem/MSM interface for modem control
  * @WWAN_PORT_QCDM: Qcom Modem diagnostic interface
  * @WWAN_PORT_FIREHOSE: XML based command protocol
- * @WWAN_PORT_MAX: Number of supported port types
+ *
+ * @WWAN_PORT_MAX: Highest supported port types
+ * @WWAN_PORT_UNKNOWN: Special value to indicate an unknown port type
+ * @__WWAN_PORT_MAX: Internal use
  */
 enum wwan_port_type {
 	WWAN_PORT_AT,
@@ -23,7 +28,12 @@ enum wwan_port_type {
 	WWAN_PORT_QMI,
 	WWAN_PORT_QCDM,
 	WWAN_PORT_FIREHOSE,
-	WWAN_PORT_MAX,
+
+	/* Add new port types above this line */
+
+	__WWAN_PORT_MAX,
+	WWAN_PORT_MAX = __WWAN_PORT_MAX - 1,
+	WWAN_PORT_UNKNOWN,
 };
 
 struct wwan_port;
@@ -31,15 +41,23 @@ struct wwan_port;
 /** struct wwan_port_ops - The WWAN port operations
  * @start: The routine for starting the WWAN port device.
  * @stop: The routine for stopping the WWAN port device.
- * @tx: The routine that sends WWAN port protocol data to the device.
+ * @tx: Non-blocking routine that sends WWAN port protocol data to the device.
+ * @tx_blocking: Optional blocking routine that sends WWAN port protocol data
+ *               to the device.
+ * @tx_poll: Optional routine that sets additional TX poll flags.
  *
  * The wwan_port_ops structure contains a list of low-level operations
- * that control a WWAN port device. All functions are mandatory.
+ * that control a WWAN port device. All functions are mandatory unless specified.
  */
 struct wwan_port_ops {
 	int (*start)(struct wwan_port *port);
 	void (*stop)(struct wwan_port *port);
 	int (*tx)(struct wwan_port *port, struct sk_buff *skb);
+
+	/* Optional operations */
+	int (*tx_blocking)(struct wwan_port *port, struct sk_buff *skb);
+	__poll_t (*tx_poll)(struct wwan_port *port, struct file *filp,
+			    poll_table *wait);
 };
 
 /**
@@ -108,4 +126,27 @@ void wwan_port_txon(struct wwan_port *port);
  */
 void *wwan_port_get_drvdata(struct wwan_port *port);
 
+/**
+ * struct wwan_ops - WWAN device ops
+ * @owner: module owner of the WWAN ops
+ * @priv_size: size of private netdev data area
+ * @setup: set up a new netdev
+ * @newlink: register the new netdev
+ * @dellink: remove the given netdev
+ */
+struct wwan_ops {
+	struct module *owner;
+	unsigned int priv_size;
+	void (*setup)(struct net_device *dev);
+	int (*newlink)(void *ctxt, struct net_device *dev,
+		       u32 if_id, struct netlink_ext_ack *extack);
+	void (*dellink)(void *ctxt, struct net_device *dev,
+			struct list_head *head);
+};
+
+int wwan_register_ops(struct device *parent, const struct wwan_ops *ops,
+		      void *ctxt);
+
+void wwan_unregister_ops(struct device *parent);
+
 #endif /* __WWAN_H */
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index b1c717286993..ab207677e0a8 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -135,6 +135,14 @@ struct vsock_transport {
 	bool (*stream_is_active)(struct vsock_sock *);
 	bool (*stream_allow)(u32 cid, u32 port);
 
+	/* SEQ_PACKET. */
+	ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg,
+				     int flags);
+	int (*seqpacket_enqueue)(struct vsock_sock *vsk, struct msghdr *msg,
+				 size_t len);
+	bool (*seqpacket_allow)(u32 remote_cid);
+	u32 (*seqpacket_has_data)(struct vsock_sock *vsk);
+
 	/* Notification. */
 	int (*notify_poll_in)(struct vsock_sock *, size_t, bool *);
 	int (*notify_poll_out)(struct vsock_sock *, size_t, bool *);
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 019e998d944a..15335732e166 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -232,7 +232,7 @@ struct bonding {
 	char     proc_file_name[IFNAMSIZ];
 #endif /* CONFIG_PROC_FS */
 	struct   list_head bond_list;
-	u32      rr_tx_counter;
+	u32 __percpu *rr_tx_counter;
 	struct   ad_bond_info ad_info;
 	struct   alb_bond_info alb_info;
 	struct   bond_params params;
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 7c984cadfec4..57b738b78073 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -34,6 +34,7 @@ struct devlink_ops;
 struct devlink {
 	struct list_head list;
 	struct list_head port_list;
+	struct list_head rate_list;
 	struct list_head sb_list;
 	struct list_head dpipe_table_list;
 	struct list_head resource_list;
@@ -133,6 +134,24 @@ struct devlink_port_attrs {
 	};
 };
 
+struct devlink_rate {
+	struct list_head list;
+	enum devlink_rate_type type;
+	struct devlink *devlink;
+	void *priv;
+	u64 tx_share;
+	u64 tx_max;
+
+	struct devlink_rate *parent;
+	union {
+		struct devlink_port *devlink_port;
+		struct {
+			char *name;
+			refcount_t refcnt;
+		};
+	};
+};
+
 struct devlink_port {
 	struct list_head list;
 	struct list_head param_list;
@@ -152,6 +171,8 @@ struct devlink_port {
 	struct delayed_work type_warn_dw;
 	struct list_head reporter_list;
 	struct mutex reporters_lock; /* Protects reporter_list */
+
+	struct devlink_rate *devlink_rate;
 };
 
 struct devlink_port_new_attrs {
@@ -1327,6 +1348,16 @@ struct devlink_ops {
 				     enum devlink_trap_action action,
 				     struct netlink_ext_ack *extack);
 	/**
+	 * @trap_drop_counter_get: Trap drop counter get function.
+	 *
+	 * Should be used by device drivers to report number of packets
+	 * that have been dropped, and cannot be passed to the devlink
+	 * subsystem by the underlying device.
+	 */
+	int (*trap_drop_counter_get)(struct devlink *devlink,
+				     const struct devlink_trap *trap,
+				     u64 *p_drops);
+	/**
 	 * @trap_policer_init: Trap policer initialization function.
 	 *
 	 * Should be used by device drivers to initialize the trap policer in
@@ -1453,6 +1484,30 @@ struct devlink_ops {
 				 struct devlink_port *port,
 				 enum devlink_port_fn_state state,
 				 struct netlink_ext_ack *extack);
+
+	/**
+	 * Rate control callbacks.
+	 */
+	int (*rate_leaf_tx_share_set)(struct devlink_rate *devlink_rate, void *priv,
+				      u64 tx_share, struct netlink_ext_ack *extack);
+	int (*rate_leaf_tx_max_set)(struct devlink_rate *devlink_rate, void *priv,
+				    u64 tx_max, struct netlink_ext_ack *extack);
+	int (*rate_node_tx_share_set)(struct devlink_rate *devlink_rate, void *priv,
+				      u64 tx_share, struct netlink_ext_ack *extack);
+	int (*rate_node_tx_max_set)(struct devlink_rate *devlink_rate, void *priv,
+				    u64 tx_max, struct netlink_ext_ack *extack);
+	int (*rate_node_new)(struct devlink_rate *rate_node, void **priv,
+			     struct netlink_ext_ack *extack);
+	int (*rate_node_del)(struct devlink_rate *rate_node, void *priv,
+			     struct netlink_ext_ack *extack);
+	int (*rate_leaf_parent_set)(struct devlink_rate *child,
+				    struct devlink_rate *parent,
+				    void *priv_child, void *priv_parent,
+				    struct netlink_ext_ack *extack);
+	int (*rate_node_parent_set)(struct devlink_rate *child,
+				    struct devlink_rate *parent,
+				    void *priv_child, void *priv_parent,
+				    struct netlink_ext_ack *extack);
 };
 
 static inline void *devlink_priv(struct devlink *devlink)
@@ -1512,6 +1567,9 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro
 void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port,
 				   u32 controller, u16 pf, u32 sf,
 				   bool external);
+int devlink_rate_leaf_create(struct devlink_port *port, void *priv);
+void devlink_rate_leaf_destroy(struct devlink_port *devlink_port);
+void devlink_rate_nodes_destroy(struct devlink *devlink);
 int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
 			u32 size, u16 ingress_pools_count,
 			u16 egress_pools_count, u16 ingress_tc_count,
diff --git a/include/net/dsa.h b/include/net/dsa.h
index e1a2610a0e06..289d68e82da0 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -50,6 +50,7 @@ struct phylink_link_state;
 #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE	20
 #define DSA_TAG_PROTO_SEVILLE_VALUE		21
 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE		22
+#define DSA_TAG_PROTO_SJA1110_VALUE		23
 
 enum dsa_tag_protocol {
 	DSA_TAG_PROTO_NONE		= DSA_TAG_PROTO_NONE_VALUE,
@@ -75,6 +76,7 @@ enum dsa_tag_protocol {
 	DSA_TAG_PROTO_XRS700X		= DSA_TAG_PROTO_XRS700X_VALUE,
 	DSA_TAG_PROTO_OCELOT_8021Q	= DSA_TAG_PROTO_OCELOT_8021Q_VALUE,
 	DSA_TAG_PROTO_SEVILLE		= DSA_TAG_PROTO_SEVILLE_VALUE,
+	DSA_TAG_PROTO_SJA1110		= DSA_TAG_PROTO_SJA1110_VALUE,
 };
 
 struct packet_type;
@@ -91,7 +93,8 @@ struct dsa_device_ops {
 	 * as regular on the master net device.
 	 */
 	bool (*filter)(const struct sk_buff *skb, struct net_device *dev);
-	unsigned int overhead;
+	unsigned int needed_headroom;
+	unsigned int needed_tailroom;
 	const char *name;
 	enum dsa_tag_protocol proto;
 	/* Some tagging protocols either mangle or shift the destination MAC
@@ -100,7 +103,6 @@ struct dsa_device_ops {
 	 * its RX filter.
 	 */
 	bool promisc_on_master;
-	bool tail_tag;
 };
 
 /* This structure defines the control interfaces that are overlayed by the
@@ -926,7 +928,7 @@ static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb,
 {
 #if IS_ENABLED(CONFIG_NET_DSA)
 	const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops;
-	int tag_len = ops->overhead;
+	int tag_len = ops->needed_headroom;
 
 	*offset = tag_len;
 	*proto = ((__be16 *)skb->data)[(tag_len / 2) - 1];
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index a914f33f3ed5..3ab2563b1a23 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -466,6 +466,49 @@ int fib_sync_up(struct net_device *dev, unsigned char nh_flags);
 void fib_sync_mtu(struct net_device *dev, u32 orig_mtu);
 void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig);
 
+/* Fields used for sysctl_fib_multipath_hash_fields.
+ * Common to IPv4 and IPv6.
+ *
+ * Add new fields at the end. This is user API.
+ */
+#define FIB_MULTIPATH_HASH_FIELD_SRC_IP			BIT(0)
+#define FIB_MULTIPATH_HASH_FIELD_DST_IP			BIT(1)
+#define FIB_MULTIPATH_HASH_FIELD_IP_PROTO		BIT(2)
+#define FIB_MULTIPATH_HASH_FIELD_FLOWLABEL		BIT(3)
+#define FIB_MULTIPATH_HASH_FIELD_SRC_PORT		BIT(4)
+#define FIB_MULTIPATH_HASH_FIELD_DST_PORT		BIT(5)
+#define FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP		BIT(6)
+#define FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP		BIT(7)
+#define FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO		BIT(8)
+#define FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL	BIT(9)
+#define FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT		BIT(10)
+#define FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT		BIT(11)
+
+#define FIB_MULTIPATH_HASH_FIELD_OUTER_MASK		\
+	(FIB_MULTIPATH_HASH_FIELD_SRC_IP |		\
+	 FIB_MULTIPATH_HASH_FIELD_DST_IP |		\
+	 FIB_MULTIPATH_HASH_FIELD_IP_PROTO |		\
+	 FIB_MULTIPATH_HASH_FIELD_FLOWLABEL |		\
+	 FIB_MULTIPATH_HASH_FIELD_SRC_PORT |		\
+	 FIB_MULTIPATH_HASH_FIELD_DST_PORT)
+
+#define FIB_MULTIPATH_HASH_FIELD_INNER_MASK		\
+	(FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP |	\
+	 FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP |	\
+	 FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO |	\
+	 FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL |	\
+	 FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT |	\
+	 FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT)
+
+#define FIB_MULTIPATH_HASH_FIELD_ALL_MASK		\
+	(FIB_MULTIPATH_HASH_FIELD_OUTER_MASK |		\
+	 FIB_MULTIPATH_HASH_FIELD_INNER_MASK)
+
+#define FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK		\
+	(FIB_MULTIPATH_HASH_FIELD_SRC_IP |		\
+	 FIB_MULTIPATH_HASH_FIELD_DST_IP |		\
+	 FIB_MULTIPATH_HASH_FIELD_IP_PROTO)
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
 		       const struct sk_buff *skb, struct flow_keys *flkeys);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 448bf2b34759..f2d0ecc257bb 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -926,11 +926,19 @@ static inline int ip6_multipath_hash_policy(const struct net *net)
 {
 	return net->ipv6.sysctl.multipath_hash_policy;
 }
+static inline u32 ip6_multipath_hash_fields(const struct net *net)
+{
+	return net->ipv6.sysctl.multipath_hash_fields;
+}
 #else
 static inline int ip6_multipath_hash_policy(const struct net *net)
 {
 	return 0;
 }
+static inline u32 ip6_multipath_hash_fields(const struct net *net)
+{
+	return 0;
+}
 #endif
 
 /*
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 83f23774b908..d61bbbf11979 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -23,6 +23,7 @@ struct mptcp_ext {
 	u64		data_seq;
 	u32		subflow_seq;
 	u16		data_len;
+	__sum16		csum;
 	u8		use_map:1,
 			dsn64:1,
 			data_fin:1,
@@ -31,7 +32,8 @@ struct mptcp_ext {
 			mpc_map:1,
 			frozen:1,
 			reset_transient:1;
-	u8		reset_reason:4;
+	u8		reset_reason:4,
+			csum_reqd:1;
 };
 
 #define MPTCP_RM_IDS_MAX	8
@@ -63,8 +65,9 @@ struct mptcp_out_options {
 	struct mptcp_rm_list rm_list;
 	u8 join_id;
 	u8 backup;
-	u8 reset_reason:4;
-	u8 reset_transient:1;
+	u8 reset_reason:4,
+	   reset_transient:1,
+	   csum_reqd:1;
 	u32 nonce;
 	u64 thmac;
 	u32 token;
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index bdc0459a595e..12cf6d7ea62c 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -32,6 +32,7 @@
 #include <net/netns/mpls.h>
 #include <net/netns/can.h>
 #include <net/netns/xdp.h>
+#include <net/netns/smc.h>
 #include <net/netns/bpf.h>
 #include <linux/ns_common.h>
 #include <linux/idr.h>
@@ -170,6 +171,9 @@ struct net {
 	struct sock		*crypto_nlsk;
 #endif
 	struct sock		*diag_nlsk;
+#if IS_ENABLED(CONFIG_SMC)
+	struct netns_smc	smc;
+#endif
 } __randomize_layout;
 
 #include <linux/seq_file_net.h>
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 06dc6db70d18..cc663c68ddc4 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -346,6 +346,13 @@ nf_ct_set(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info info)
 	skb_set_nfct(skb, (unsigned long)ct | info);
 }
 
+extern unsigned int nf_conntrack_net_id;
+
+static inline struct nf_conntrack_net *nf_ct_pernet(const struct net *net)
+{
+	return net_generic(net, nf_conntrack_net_id);
+}
+
 #define NF_CT_STAT_INC(net, count)	  __this_cpu_inc((net)->ct.stat->count)
 #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count)
 #define NF_CT_STAT_ADD_ATOMIC(net, count, v) this_cpu_add((net)->ct.stat->count, (v))
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 48ef7460ff30..a3647fadf1cc 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -177,6 +177,8 @@ struct flow_offload {
 #define NF_FLOW_TIMEOUT (30 * HZ)
 #define nf_flowtable_time_stamp	(u32)jiffies
 
+unsigned long flow_offload_get_timeout(struct flow_offload *flow);
+
 static inline __s32 nf_flow_timeout_delta(unsigned int timeout)
 {
 	return (__s32)(timeout - nf_flowtable_time_stamp);
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 0a5655e300b5..148f5d8ee5ab 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -23,35 +23,46 @@ struct module;
 
 struct nft_pktinfo {
 	struct sk_buff			*skb;
+	const struct nf_hook_state	*state;
 	bool				tprot_set;
 	u8				tprot;
-	/* for x_tables compatibility */
-	struct xt_action_param		xt;
+	u16				fragoff;
+	unsigned int			thoff;
 };
 
+static inline struct sock *nft_sk(const struct nft_pktinfo *pkt)
+{
+	return pkt->state->sk;
+}
+
+static inline unsigned int nft_thoff(const struct nft_pktinfo *pkt)
+{
+	return pkt->thoff;
+}
+
 static inline struct net *nft_net(const struct nft_pktinfo *pkt)
 {
-	return pkt->xt.state->net;
+	return pkt->state->net;
 }
 
 static inline unsigned int nft_hook(const struct nft_pktinfo *pkt)
 {
-	return pkt->xt.state->hook;
+	return pkt->state->hook;
 }
 
 static inline u8 nft_pf(const struct nft_pktinfo *pkt)
 {
-	return pkt->xt.state->pf;
+	return pkt->state->pf;
 }
 
 static inline const struct net_device *nft_in(const struct nft_pktinfo *pkt)
 {
-	return pkt->xt.state->in;
+	return pkt->state->in;
 }
 
 static inline const struct net_device *nft_out(const struct nft_pktinfo *pkt)
 {
-	return pkt->xt.state->out;
+	return pkt->state->out;
 }
 
 static inline void nft_set_pktinfo(struct nft_pktinfo *pkt,
@@ -59,16 +70,15 @@ static inline void nft_set_pktinfo(struct nft_pktinfo *pkt,
 				   const struct nf_hook_state *state)
 {
 	pkt->skb = skb;
-	pkt->xt.state = state;
+	pkt->state = state;
 }
 
-static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt,
-					  struct sk_buff *skb)
+static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt)
 {
 	pkt->tprot_set = false;
 	pkt->tprot = 0;
-	pkt->xt.thoff = 0;
-	pkt->xt.fragoff = 0;
+	pkt->thoff = 0;
+	pkt->fragoff = 0;
 }
 
 /**
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index fd10a7862fdc..46c8d5bb5d8d 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -3,6 +3,7 @@
 #define _NET_NF_TABLES_CORE_H
 
 #include <net/netfilter/nf_tables.h>
+#include <linux/indirect_call_wrapper.h>
 
 extern struct nft_expr_type nft_imm_type;
 extern struct nft_expr_type nft_cmp_type;
@@ -88,6 +89,36 @@ extern const struct nft_set_type nft_set_bitmap_type;
 extern const struct nft_set_type nft_set_pipapo_type;
 extern const struct nft_set_type nft_set_pipapo_avx2_type;
 
+#ifdef CONFIG_RETPOLINE
+bool nft_rhash_lookup(const struct net *net, const struct nft_set *set,
+		      const u32 *key, const struct nft_set_ext **ext);
+bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
+		       const u32 *key, const struct nft_set_ext **ext);
+bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set,
+		       const u32 *key, const struct nft_set_ext **ext);
+bool nft_hash_lookup_fast(const struct net *net,
+			  const struct nft_set *set,
+			  const u32 *key, const struct nft_set_ext **ext);
+bool nft_hash_lookup(const struct net *net, const struct nft_set *set,
+		     const u32 *key, const struct nft_set_ext **ext);
+bool nft_set_do_lookup(const struct net *net, const struct nft_set *set,
+		       const u32 *key, const struct nft_set_ext **ext);
+#else
+static inline bool
+nft_set_do_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key, const struct nft_set_ext **ext)
+{
+	return set->ops->lookup(net, set, key, ext);
+}
+#endif
+
+/* called from nft_pipapo_avx2.c */
+bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
+		       const u32 *key, const struct nft_set_ext **ext);
+/* called from nft_set_pipapo.c */
+bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
+			    const u32 *key, const struct nft_set_ext **ext);
+
 struct nft_expr;
 struct nft_regs;
 struct nft_pktinfo;
diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h
index 1f7bea39ad1b..eb4c094cd54d 100644
--- a/include/net/netfilter/nf_tables_ipv4.h
+++ b/include/net/netfilter/nf_tables_ipv4.h
@@ -5,26 +5,24 @@
 #include <net/netfilter/nf_tables.h>
 #include <net/ip.h>
 
-static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt,
-					struct sk_buff *skb)
+static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt)
 {
 	struct iphdr *ip;
 
 	ip = ip_hdr(pkt->skb);
 	pkt->tprot_set = true;
 	pkt->tprot = ip->protocol;
-	pkt->xt.thoff = ip_hdrlen(pkt->skb);
-	pkt->xt.fragoff = ntohs(ip->frag_off) & IP_OFFSET;
+	pkt->thoff = ip_hdrlen(pkt->skb);
+	pkt->fragoff = ntohs(ip->frag_off) & IP_OFFSET;
 }
 
-static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt,
-						  struct sk_buff *skb)
+static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt)
 {
 	struct iphdr *iph, _iph;
 	u32 len, thoff;
 
-	iph = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*iph),
-				 &_iph);
+	iph = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb),
+				 sizeof(*iph), &_iph);
 	if (!iph)
 		return -1;
 
@@ -33,42 +31,40 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt,
 
 	len = ntohs(iph->tot_len);
 	thoff = iph->ihl * 4;
-	if (skb->len < len)
+	if (pkt->skb->len < len)
 		return -1;
 	else if (len < thoff)
 		return -1;
 
 	pkt->tprot_set = true;
 	pkt->tprot = iph->protocol;
-	pkt->xt.thoff = thoff;
-	pkt->xt.fragoff = ntohs(iph->frag_off) & IP_OFFSET;
+	pkt->thoff = thoff;
+	pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET;
 
 	return 0;
 }
 
-static inline void nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt,
-						 struct sk_buff *skb)
+static inline void nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt)
 {
-	if (__nft_set_pktinfo_ipv4_validate(pkt, skb) < 0)
-		nft_set_pktinfo_unspec(pkt, skb);
+	if (__nft_set_pktinfo_ipv4_validate(pkt) < 0)
+		nft_set_pktinfo_unspec(pkt);
 }
 
-static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt,
-					       struct sk_buff *skb)
+static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt)
 {
 	struct iphdr *iph;
 	u32 len, thoff;
 
-	if (!pskb_may_pull(skb, sizeof(*iph)))
+	if (!pskb_may_pull(pkt->skb, sizeof(*iph)))
 		return -1;
 
-	iph = ip_hdr(skb);
+	iph = ip_hdr(pkt->skb);
 	if (iph->ihl < 5 || iph->version != 4)
 		goto inhdr_error;
 
 	len = ntohs(iph->tot_len);
 	thoff = iph->ihl * 4;
-	if (skb->len < len) {
+	if (pkt->skb->len < len) {
 		__IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INTRUNCATEDPKTS);
 		return -1;
 	} else if (len < thoff) {
@@ -77,8 +73,8 @@ static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt,
 
 	pkt->tprot_set = true;
 	pkt->tprot = iph->protocol;
-	pkt->xt.thoff = thoff;
-	pkt->xt.fragoff = ntohs(iph->frag_off) & IP_OFFSET;
+	pkt->thoff = thoff;
+	pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET;
 
 	return 0;
 
diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h
index 867de29f3f7a..7595e02b00ba 100644
--- a/include/net/netfilter/nf_tables_ipv6.h
+++ b/include/net/netfilter/nf_tables_ipv6.h
@@ -6,8 +6,7 @@
 #include <net/ipv6.h>
 #include <net/netfilter/nf_tables.h>
 
-static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt,
-					struct sk_buff *skb)
+static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt)
 {
 	unsigned int flags = IP6_FH_F_AUTH;
 	int protohdr, thoff = 0;
@@ -15,18 +14,17 @@ static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt,
 
 	protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags);
 	if (protohdr < 0) {
-		nft_set_pktinfo_unspec(pkt, skb);
+		nft_set_pktinfo_unspec(pkt);
 		return;
 	}
 
 	pkt->tprot_set = true;
 	pkt->tprot = protohdr;
-	pkt->xt.thoff = thoff;
-	pkt->xt.fragoff = frag_off;
+	pkt->thoff = thoff;
+	pkt->fragoff = frag_off;
 }
 
-static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt,
-						  struct sk_buff *skb)
+static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt)
 {
 #if IS_ENABLED(CONFIG_IPV6)
 	unsigned int flags = IP6_FH_F_AUTH;
@@ -36,8 +34,8 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt,
 	int protohdr;
 	u32 pkt_len;
 
-	ip6h = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*ip6h),
-				  &_ip6h);
+	ip6h = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb),
+				  sizeof(*ip6h), &_ip6h);
 	if (!ip6h)
 		return -1;
 
@@ -45,7 +43,7 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt,
 		return -1;
 
 	pkt_len = ntohs(ip6h->payload_len);
-	if (pkt_len + sizeof(*ip6h) > skb->len)
+	if (pkt_len + sizeof(*ip6h) > pkt->skb->len)
 		return -1;
 
 	protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags);
@@ -54,8 +52,8 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt,
 
 	pkt->tprot_set = true;
 	pkt->tprot = protohdr;
-	pkt->xt.thoff = thoff;
-	pkt->xt.fragoff = frag_off;
+	pkt->thoff = thoff;
+	pkt->fragoff = frag_off;
 
 	return 0;
 #else
@@ -63,15 +61,13 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt,
 #endif
 }
 
-static inline void nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt,
-						 struct sk_buff *skb)
+static inline void nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt)
 {
-	if (__nft_set_pktinfo_ipv6_validate(pkt, skb) < 0)
-		nft_set_pktinfo_unspec(pkt, skb);
+	if (__nft_set_pktinfo_ipv6_validate(pkt) < 0)
+		nft_set_pktinfo_unspec(pkt);
 }
 
-static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt,
-					       struct sk_buff *skb)
+static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt)
 {
 #if IS_ENABLED(CONFIG_IPV6)
 	unsigned int flags = IP6_FH_F_AUTH;
@@ -82,15 +78,15 @@ static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt,
 	int protohdr;
 	u32 pkt_len;
 
-	if (!pskb_may_pull(skb, sizeof(*ip6h)))
+	if (!pskb_may_pull(pkt->skb, sizeof(*ip6h)))
 		return -1;
 
-	ip6h = ipv6_hdr(skb);
+	ip6h = ipv6_hdr(pkt->skb);
 	if (ip6h->version != 6)
 		goto inhdr_error;
 
 	pkt_len = ntohs(ip6h->payload_len);
-	if (pkt_len + sizeof(*ip6h) > skb->len) {
+	if (pkt_len + sizeof(*ip6h) > pkt->skb->len) {
 		idev = __in6_dev_get(nft_in(pkt));
 		__IP6_INC_STATS(nft_net(pkt), idev, IPSTATS_MIB_INTRUNCATEDPKTS);
 		return -1;
@@ -102,8 +98,8 @@ static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt,
 
 	pkt->tprot_set = true;
 	pkt->tprot = protohdr;
-	pkt->xt.thoff = thoff;
-	pkt->xt.fragoff = frag_off;
+	pkt->thoff = thoff;
+	pkt->fragoff = frag_off;
 
 	return 0;
 
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index ad0a95c2335e..c3094b83a525 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -27,6 +27,10 @@ struct nf_tcp_net {
 	u8 tcp_loose;
 	u8 tcp_be_liberal;
 	u8 tcp_max_retrans;
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	unsigned int offload_timeout;
+	unsigned int offload_pickup;
+#endif
 };
 
 enum udp_conntrack {
@@ -37,6 +41,10 @@ enum udp_conntrack {
 
 struct nf_udp_net {
 	unsigned int timeouts[UDP_CT_MAX];
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	unsigned int offload_timeout;
+	unsigned int offload_pickup;
+#endif
 };
 
 struct nf_icmp_net {
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index f6af8d96d3c6..b8620519eace 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -126,6 +126,7 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_syn_retries;
 	u8 sysctl_tcp_synack_retries;
 	u8 sysctl_tcp_syncookies;
+	u8 sysctl_tcp_migrate_req;
 	int sysctl_tcp_reordering;
 	u8 sysctl_tcp_retries1;
 	u8 sysctl_tcp_retries2;
@@ -210,6 +211,7 @@ struct netns_ipv4 {
 #endif
 #endif
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
+	u32 sysctl_fib_multipath_hash_fields;
 	u8 sysctl_fib_multipath_use_neigh;
 	u8 sysctl_fib_multipath_hash_policy;
 #endif
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 6153c8067009..bde0b7adb4a3 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -28,8 +28,9 @@ struct netns_sysctl_ipv6 {
 	int ip6_rt_gc_elasticity;
 	int ip6_rt_mtu_expires;
 	int ip6_rt_min_advmss;
-	u8 bindv6only;
+	u32 multipath_hash_fields;
 	u8 multipath_hash_policy;
+	u8 bindv6only;
 	u8 flowlabel_consistency;
 	u8 auto_flowlabels;
 	int icmpv6_time;
diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h
new file mode 100644
index 000000000000..ea8a9cf2619b
--- /dev/null
+++ b/include/net/netns/smc.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NETNS_SMC_H__
+#define __NETNS_SMC_H__
+#include <linux/mutex.h>
+#include <linux/percpu.h>
+
+struct smc_stats_rsn;
+struct smc_stats;
+struct netns_smc {
+	/* per cpu counters for SMC */
+	struct smc_stats __percpu	*smc_stats;
+	/* protect fback_rsn */
+	struct mutex			mutex_fback_rsn;
+	struct smc_stats_rsn		*fback_rsn;
+};
+#endif
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index b4b6de909c93..3dd62dd73027 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -146,6 +146,8 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool)
 	return pool->p.dma_dir;
 }
 
+bool page_pool_return_skb_page(struct page *page);
+
 struct page_pool *page_pool_create(const struct page_pool_params *params);
 
 #ifdef CONFIG_PAGE_POOL
@@ -251,4 +253,11 @@ static inline void page_pool_ring_unlock(struct page_pool *pool)
 		spin_unlock_bh(&pool->ring.producer_lock);
 }
 
+/* Store mem_info on struct page and use it while recycling skb frags */
+static inline
+void page_pool_store_mem_info(struct page *page, struct page_pool *pp)
+{
+	page->pp = pp;
+}
+
 #endif /* _NET_PAGE_POOL_H */
diff --git a/include/net/protocol.h b/include/net/protocol.h
index 2b778e1d2d8f..f51c06ae365f 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -43,7 +43,6 @@ struct net_protocol {
 	int			(*err_handler)(struct sk_buff *skb, u32 info);
 
 	unsigned int		no_policy:1,
-				netns_ok:1,
 				/* does the protocol do more stringent
 				 * icmp tag validation than simple
 				 * socket lookup?
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 479f60ef54c0..384e800665f2 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -37,6 +37,9 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh)
  *	@maxtype: Highest device specific netlink attribute number
  *	@policy: Netlink policy for device specific attribute validation
  *	@validate: Optional validation function for netlink/changelink parameters
+ *	@alloc: netdev allocation function, can be %NULL and is then used
+ *		in place of alloc_netdev_mqs(), in this case @priv_size
+ *		and @setup are unused. Returns a netdev or ERR_PTR().
  *	@priv_size: sizeof net_device private space
  *	@setup: net_device setup function
  *	@newlink: Function for configuring and registering a new device
@@ -63,6 +66,11 @@ struct rtnl_link_ops {
 	const char		*kind;
 
 	size_t			priv_size;
+	struct net_device	*(*alloc)(struct nlattr *tb[],
+					  const char *ifname,
+					  unsigned char name_assign_type,
+					  unsigned int num_tx_queues,
+					  unsigned int num_rx_queues);
 	void			(*setup)(struct net_device *dev);
 
 	bool			netns_refund;
diff --git a/include/net/sock.h b/include/net/sock.h
index 7a7058f4f265..ced2fc965ec7 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2752,6 +2752,9 @@ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif)
 void sock_def_readable(struct sock *sk);
 
 int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk);
+void sock_set_timestamp(struct sock *sk, int optname, bool valbool);
+int sock_set_timestamping(struct sock *sk, int optname, int val);
+
 void sock_enable_timestamps(struct sock *sk);
 void sock_no_linger(struct sock *sk);
 void sock_set_keepalive(struct sock *sk);
diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h
index 505f1e18e9bf..473b0b0fa4ab 100644
--- a/include/net/sock_reuseport.h
+++ b/include/net/sock_reuseport.h
@@ -13,8 +13,9 @@ extern spinlock_t reuseport_lock;
 struct sock_reuseport {
 	struct rcu_head		rcu;
 
-	u16			max_socks;	/* length of socks */
-	u16			num_socks;	/* elements in socks */
+	u16			max_socks;		/* length of socks */
+	u16			num_socks;		/* elements in socks */
+	u16			num_closed_socks;	/* closed elements in socks */
 	/* The last synq overflow event timestamp of this
 	 * reuse->socks[] group.
 	 */
@@ -31,10 +32,14 @@ extern int reuseport_alloc(struct sock *sk, bool bind_inany);
 extern int reuseport_add_sock(struct sock *sk, struct sock *sk2,
 			      bool bind_inany);
 extern void reuseport_detach_sock(struct sock *sk);
+void reuseport_stop_listen_sock(struct sock *sk);
 extern struct sock *reuseport_select_sock(struct sock *sk,
 					  u32 hash,
 					  struct sk_buff *skb,
 					  int hdr_len);
+struct sock *reuseport_migrate_sock(struct sock *sk,
+				    struct sock *migrating_sk,
+				    struct sk_buff *skb);
 extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog);
 extern int reuseport_detach_prog(struct sock *sk);
 
diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h
index f051046ba034..f94b8bc26f9e 100644
--- a/include/net/tc_act/tc_vlan.h
+++ b/include/net/tc_act/tc_vlan.h
@@ -16,6 +16,7 @@ struct tcf_vlan_params {
 	u16               tcfv_push_vid;
 	__be16            tcfv_push_proto;
 	u8                tcfv_push_prio;
+	bool              tcfv_push_prio_exists;
 	struct rcu_head   rcu;
 };
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index d05193cb0d99..e668f1bf780d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -412,6 +412,10 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 		int flags, int *addr_len);
 int tcp_set_rcvlowat(struct sock *sk, int val);
 int tcp_set_window_clamp(struct sock *sk, int val);
+void tcp_update_recv_tstamps(struct sk_buff *skb,
+			     struct scm_timestamping_internal *tss);
+void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
+			struct scm_timestamping_internal *tss);
 void tcp_data_ready(struct sock *sk);
 #ifdef CONFIG_MMU
 int tcp_mmap(struct file *file, struct socket *sock,
diff --git a/include/net/xdp.h b/include/net/xdp.h
index a5bc214a49d9..5533f0ab2afc 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -170,6 +170,7 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 					 struct net_device *dev);
 int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp);
+struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf);
 
 static inline
 void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h
index 775a46d0b0f0..6bf43176f14c 100644
--- a/include/trace/events/mptcp.h
+++ b/include/trace/events/mptcp.h
@@ -73,6 +73,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext,
 		__field(u64, data_seq)
 		__field(u32, subflow_seq)
 		__field(u16, data_len)
+		__field(u16, csum)
 		__field(u8, use_map)
 		__field(u8, dsn64)
 		__field(u8, data_fin)
@@ -82,6 +83,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext,
 		__field(u8, frozen)
 		__field(u8, reset_transient)
 		__field(u8, reset_reason)
+		__field(u8, csum_reqd)
 	),
 
 	TP_fast_assign(
@@ -89,6 +91,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext,
 		__entry->data_seq = mpext->data_seq;
 		__entry->subflow_seq = mpext->subflow_seq;
 		__entry->data_len = mpext->data_len;
+		__entry->csum = (__force u16)mpext->csum;
 		__entry->use_map = mpext->use_map;
 		__entry->dsn64 = mpext->dsn64;
 		__entry->data_fin = mpext->data_fin;
@@ -98,16 +101,18 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext,
 		__entry->frozen = mpext->frozen;
 		__entry->reset_transient = mpext->reset_transient;
 		__entry->reset_reason = mpext->reset_reason;
+		__entry->csum_reqd = mpext->csum_reqd;
 	),
 
-	TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u",
+	TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u csum=%x use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u csum_reqd=%u",
 		  __entry->data_ack, __entry->data_seq,
 		  __entry->subflow_seq, __entry->data_len,
-		  __entry->use_map, __entry->dsn64,
-		  __entry->data_fin, __entry->use_ack,
-		  __entry->ack64, __entry->mpc_map,
-		  __entry->frozen, __entry->reset_transient,
-		  __entry->reset_reason)
+		  __entry->csum, __entry->use_map,
+		  __entry->dsn64, __entry->data_fin,
+		  __entry->use_ack, __entry->ack64,
+		  __entry->mpc_map, __entry->frozen,
+		  __entry->reset_transient, __entry->reset_reason,
+		  __entry->csum_reqd)
 );
 
 DEFINE_EVENT(mptcp_dump_mpext, get_mapping_status,
diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index ba94857eea11..521059d8dc0a 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -295,6 +295,82 @@ TRACE_EVENT(tcp_probe,
 		  __entry->srtt, __entry->rcv_wnd, __entry->sock_cookie)
 );
 
+#define TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb)			\
+	do {								\
+		const struct tcphdr *th = (const struct tcphdr *)skb->data; \
+		struct sockaddr_in *v4 = (void *)__entry->saddr;	\
+									\
+		v4->sin_family = AF_INET;				\
+		v4->sin_port = th->source;				\
+		v4->sin_addr.s_addr = ip_hdr(skb)->saddr;		\
+		v4 = (void *)__entry->daddr;				\
+		v4->sin_family = AF_INET;				\
+		v4->sin_port = th->dest;				\
+		v4->sin_addr.s_addr = ip_hdr(skb)->daddr;		\
+	} while (0)
+
+#if IS_ENABLED(CONFIG_IPV6)
+
+#define TP_STORE_ADDR_PORTS_SKB(__entry, skb)				\
+	do {								\
+		const struct iphdr *iph = ip_hdr(skb);			\
+									\
+		if (iph->version == 6) {				\
+			const struct tcphdr *th = (const struct tcphdr *)skb->data; \
+			struct sockaddr_in6 *v6 = (void *)__entry->saddr; \
+									\
+			v6->sin6_family = AF_INET6;			\
+			v6->sin6_port = th->source;			\
+			v6->sin6_addr = ipv6_hdr(skb)->saddr;		\
+			v6 = (void *)__entry->daddr;			\
+			v6->sin6_family = AF_INET6;			\
+			v6->sin6_port = th->dest;			\
+			v6->sin6_addr = ipv6_hdr(skb)->daddr;		\
+		} else							\
+			TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb);	\
+	} while (0)
+
+#else
+
+#define TP_STORE_ADDR_PORTS_SKB(__entry, skb)		\
+	TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb)
+
+#endif
+
+/*
+ * tcp event with only skb
+ */
+DECLARE_EVENT_CLASS(tcp_event_skb,
+
+	TP_PROTO(const struct sk_buff *skb),
+
+	TP_ARGS(skb),
+
+	TP_STRUCT__entry(
+		__field(const void *, skbaddr)
+		__array(__u8, saddr, sizeof(struct sockaddr_in6))
+		__array(__u8, daddr, sizeof(struct sockaddr_in6))
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+
+		memset(__entry->saddr, 0, sizeof(struct sockaddr_in6));
+		memset(__entry->daddr, 0, sizeof(struct sockaddr_in6));
+
+		TP_STORE_ADDR_PORTS_SKB(__entry, skb);
+	),
+
+	TP_printk("src=%pISpc dest=%pISpc", __entry->saddr, __entry->daddr)
+);
+
+DEFINE_EVENT(tcp_event_skb, tcp_bad_csum,
+
+	TP_PROTO(const struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+
 #endif /* _TRACE_TCP_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/vsock_virtio_transport_common.h b/include/trace/events/vsock_virtio_transport_common.h
index 6782213778be..d0b3f0ea9ba1 100644
--- a/include/trace/events/vsock_virtio_transport_common.h
+++ b/include/trace/events/vsock_virtio_transport_common.h
@@ -9,9 +9,12 @@
 #include <linux/tracepoint.h>
 
 TRACE_DEFINE_ENUM(VIRTIO_VSOCK_TYPE_STREAM);
+TRACE_DEFINE_ENUM(VIRTIO_VSOCK_TYPE_SEQPACKET);
 
 #define show_type(val) \
-	__print_symbolic(val, { VIRTIO_VSOCK_TYPE_STREAM, "STREAM" })
+	__print_symbolic(val, \
+			 { VIRTIO_VSOCK_TYPE_STREAM, "STREAM" }, \
+			 { VIRTIO_VSOCK_TYPE_SEQPACKET, "SEQPACKET" })
 
 TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_INVALID);
 TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_REQUEST);
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index fcad3645a70b..c40fc97f9417 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -110,7 +110,11 @@ DECLARE_EVENT_CLASS(xdp_redirect_template,
 		u32 ifindex = 0, map_index = index;
 
 		if (map_type == BPF_MAP_TYPE_DEVMAP || map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
-			ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex;
+			/* Just leave to_ifindex to 0 if do broadcast redirect,
+			 * as tgt will be NULL.
+			 */
+			if (tgt)
+				ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex;
 		} else if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) {
 			ifindex = index;
 			map_index = 0;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index ec6d85a81744..bf9252c7381e 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -527,6 +527,15 @@ union bpf_iter_link_info {
  *		Look up an element with the given *key* in the map referred to
  *		by the file descriptor *fd*, and if found, delete the element.
  *
+ *		For **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map
+ *		types, the *flags* argument needs to be set to 0, but for other
+ *		map types, it may be specified as:
+ *
+ *		**BPF_F_LOCK**
+ *			Look up and delete the value of a spin-locked map
+ *			without returning the lock. This must be specified if
+ *			the elements contain a spinlock.
+ *
  *		The **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map types
  *		implement this command as a "pop" operation, deleting the top
  *		element rather than one corresponding to *key*.
@@ -536,6 +545,10 @@ union bpf_iter_link_info {
  *		This command is only valid for the following map types:
  *		* **BPF_MAP_TYPE_QUEUE**
  *		* **BPF_MAP_TYPE_STACK**
+ *		* **BPF_MAP_TYPE_HASH**
+ *		* **BPF_MAP_TYPE_PERCPU_HASH**
+ *		* **BPF_MAP_TYPE_LRU_HASH**
+ *		* **BPF_MAP_TYPE_LRU_PERCPU_HASH**
  *
  *	Return
  *		Returns zero on success. On error, -1 is returned and *errno*
@@ -837,6 +850,7 @@ enum bpf_cmd {
 	BPF_PROG_ATTACH,
 	BPF_PROG_DETACH,
 	BPF_PROG_TEST_RUN,
+	BPF_PROG_RUN = BPF_PROG_TEST_RUN,
 	BPF_PROG_GET_NEXT_ID,
 	BPF_MAP_GET_NEXT_ID,
 	BPF_PROG_GET_FD_BY_ID,
@@ -937,6 +951,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_EXT,
 	BPF_PROG_TYPE_LSM,
 	BPF_PROG_TYPE_SK_LOOKUP,
+	BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
 };
 
 enum bpf_attach_type {
@@ -979,6 +994,8 @@ enum bpf_attach_type {
 	BPF_SK_LOOKUP,
 	BPF_XDP,
 	BPF_SK_SKB_VERDICT,
+	BPF_SK_REUSEPORT_SELECT,
+	BPF_SK_REUSEPORT_SELECT_OR_MIGRATE,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1097,8 +1114,8 @@ enum bpf_link_type {
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * the following extensions:
  *
- * insn[0].src_reg:  BPF_PSEUDO_MAP_FD
- * insn[0].imm:      map fd
+ * insn[0].src_reg:  BPF_PSEUDO_MAP_[FD|IDX]
+ * insn[0].imm:      map fd or fd_idx
  * insn[1].imm:      0
  * insn[0].off:      0
  * insn[1].off:      0
@@ -1106,15 +1123,19 @@ enum bpf_link_type {
  * verifier type:    CONST_PTR_TO_MAP
  */
 #define BPF_PSEUDO_MAP_FD	1
-/* insn[0].src_reg:  BPF_PSEUDO_MAP_VALUE
- * insn[0].imm:      map fd
+#define BPF_PSEUDO_MAP_IDX	5
+
+/* insn[0].src_reg:  BPF_PSEUDO_MAP_[IDX_]VALUE
+ * insn[0].imm:      map fd or fd_idx
  * insn[1].imm:      offset into value
  * insn[0].off:      0
  * insn[1].off:      0
  * ldimm64 rewrite:  address of map[0]+offset
  * verifier type:    PTR_TO_MAP_VALUE
  */
-#define BPF_PSEUDO_MAP_VALUE	2
+#define BPF_PSEUDO_MAP_VALUE		2
+#define BPF_PSEUDO_MAP_IDX_VALUE	6
+
 /* insn[0].src_reg:  BPF_PSEUDO_BTF_ID
  * insn[0].imm:      kernel btd id of VAR
  * insn[1].imm:      0
@@ -1314,6 +1335,8 @@ union bpf_attr {
 			/* or valid module BTF object fd or 0 to attach to vmlinux */
 			__u32		attach_btf_obj_fd;
 		};
+		__u32		:32;		/* pad */
+		__aligned_u64	fd_array;	/* array of FDs */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -2534,8 +2557,12 @@ union bpf_attr {
  * 		The lower two bits of *flags* are used as the return code if
  * 		the map lookup fails. This is so that the return value can be
  * 		one of the XDP program return codes up to **XDP_TX**, as chosen
- * 		by the caller. Any higher bits in the *flags* argument must be
- * 		unset.
+ * 		by the caller. The higher bits of *flags* can be set to
+ * 		BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below.
+ *
+ * 		With BPF_F_BROADCAST the packet will be broadcasted to all the
+ * 		interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress
+ * 		interface will be excluded when do broadcasting.
  *
  * 		See also **bpf_redirect**\ (), which only supports redirecting
  * 		to an ifindex, but doesn't require a map to do so.
@@ -4735,6 +4762,24 @@ union bpf_attr {
  *		be zero-terminated except when **str_size** is 0.
  *
  *		Or **-EBUSY** if the per-CPU memory copy buffer is busy.
+ *
+ * long bpf_sys_bpf(u32 cmd, void *attr, u32 attr_size)
+ * 	Description
+ * 		Execute bpf syscall with given arguments.
+ * 	Return
+ * 		A syscall result.
+ *
+ * long bpf_btf_find_by_name_kind(char *name, int name_sz, u32 kind, int flags)
+ * 	Description
+ * 		Find BTF type with given name and kind in vmlinux BTF or in module's BTFs.
+ * 	Return
+ * 		Returns btf_id and btf_obj_fd in lower and upper 32 bits.
+ *
+ * long bpf_sys_close(u32 fd)
+ * 	Description
+ * 		Execute close syscall for given FD.
+ * 	Return
+ * 		A syscall result.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -4903,6 +4948,9 @@ union bpf_attr {
 	FN(check_mtu),			\
 	FN(for_each_map_elem),		\
 	FN(snprintf),			\
+	FN(sys_bpf),			\
+	FN(btf_find_by_name_kind),	\
+	FN(sys_close),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5080,6 +5128,12 @@ enum {
 	BPF_F_BPRM_SECUREEXEC	= (1ULL << 0),
 };
 
+/* Flags for bpf_redirect_map helper */
+enum {
+	BPF_F_BROADCAST		= (1ULL << 3),
+	BPF_F_EXCLUDE_INGRESS	= (1ULL << 4),
+};
+
 #define __bpf_md_ptr(type, name)	\
 union {					\
 	type name;			\
@@ -5364,6 +5418,20 @@ struct sk_reuseport_md {
 	__u32 ip_protocol;	/* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
 	__u32 bind_inany;	/* Is sock bound to an INANY address? */
 	__u32 hash;		/* A hash of the packet 4 tuples */
+	/* When reuse->migrating_sk is NULL, it is selecting a sk for the
+	 * new incoming connection request (e.g. selecting a listen sk for
+	 * the received SYN in the TCP case).  reuse->sk is one of the sk
+	 * in the reuseport group. The bpf prog can use reuse->sk to learn
+	 * the local listening ip/port without looking into the skb.
+	 *
+	 * When reuse->migrating_sk is not NULL, reuse->sk is closed and
+	 * reuse->migrating_sk is the socket that needs to be migrated
+	 * to another listening socket.  migrating_sk could be a fullsock
+	 * sk that is fully established or a reqsk that is in-the-middle
+	 * of 3-way handshake.
+	 */
+	__bpf_md_ptr(struct bpf_sock *, sk);
+	__bpf_md_ptr(struct bpf_sock *, migrating_sk);
 };
 
 #define BPF_TAG_SIZE	8
diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h
index c7535352fef6..90801ada2bbe 100644
--- a/include/uapi/linux/can.h
+++ b/include/uapi/linux/can.h
@@ -123,8 +123,8 @@ struct can_frame {
 /*
  * defined bits for canfd_frame.flags
  *
- * The use of struct canfd_frame implies the Extended Data Length (EDL) bit to
- * be set in the CAN frame bitstream on the wire. The EDL bit switch turns
+ * The use of struct canfd_frame implies the FD Frame (FDF) bit to
+ * be set in the CAN frame bitstream on the wire. The FDF bit switch turns
  * the CAN controllers bitstream processor into the CAN FD mode which creates
  * two new options within the CAN FD frame specification:
  *
@@ -135,9 +135,18 @@ struct can_frame {
  * controller only the CANFD_BRS bit is relevant for real CAN controllers when
  * building a CAN FD frame for transmission. Setting the CANFD_ESI bit can make
  * sense for virtual CAN interfaces to test applications with echoed frames.
+ *
+ * The struct can_frame and struct canfd_frame intentionally share the same
+ * layout to be able to write CAN frame content into a CAN FD frame structure.
+ * When this is done the former differentiation via CAN_MTU / CANFD_MTU gets
+ * lost. CANFD_FDF allows programmers to mark CAN FD frames in the case of
+ * using struct canfd_frame for mixed CAN / CAN FD content (dual use).
+ * N.B. the Kernel APIs do NOT provide mixed CAN / CAN FD content inside of
+ * struct canfd_frame therefore the CANFD_FDF flag is disregarded by Linux.
  */
 #define CANFD_BRS 0x01 /* bit rate switch (second bitrate for payload data) */
 #define CANFD_ESI 0x02 /* error state indicator of the transmitting node */
+#define CANFD_FDF 0x04 /* mark CAN FD for dual use of struct canfd_frame */
 
 /**
  * struct canfd_frame - CAN flexible data rate frame structure
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index f6008b2fa60f..32f53a0069d6 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -126,6 +126,11 @@ enum devlink_command {
 
 	DEVLINK_CMD_HEALTH_REPORTER_TEST,
 
+	DEVLINK_CMD_RATE_GET,		/* can dump */
+	DEVLINK_CMD_RATE_SET,
+	DEVLINK_CMD_RATE_NEW,
+	DEVLINK_CMD_RATE_DEL,
+
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -206,6 +211,11 @@ enum devlink_port_flavour {
 				      */
 };
 
+enum devlink_rate_type {
+	DEVLINK_RATE_TYPE_LEAF,
+	DEVLINK_RATE_TYPE_NODE,
+};
+
 enum devlink_param_cmode {
 	DEVLINK_PARAM_CMODE_RUNTIME,
 	DEVLINK_PARAM_CMODE_DRIVERINIT,
@@ -534,6 +544,13 @@ enum devlink_attr {
 	DEVLINK_ATTR_RELOAD_ACTION_STATS,       /* nested */
 
 	DEVLINK_ATTR_PORT_PCI_SF_NUMBER,	/* u32 */
+
+	DEVLINK_ATTR_RATE_TYPE,			/* u16 */
+	DEVLINK_ATTR_RATE_TX_SHARE,		/* u64 */
+	DEVLINK_ATTR_RATE_TX_MAX,		/* u64 */
+	DEVLINK_ATTR_RATE_NODE_NAME,		/* string */
+	DEVLINK_ATTR_RATE_PARENT_NODE_NAME,	/* string */
+
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index cfef6b08169a..67aa7134b301 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -233,7 +233,7 @@ enum tunable_id {
 	ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */
 	/*
 	 * Add your fresh new tunable attribute above and remember to update
-	 * tunable_strings[] in net/core/ethtool.c
+	 * tunable_strings[] in net/ethtool/common.c
 	 */
 	__ETHTOOL_TUNABLE_COUNT,
 };
@@ -297,7 +297,7 @@ enum phy_tunable_id {
 	ETHTOOL_PHY_EDPD,
 	/*
 	 * Add your fresh new phy tunable attribute above and remember to update
-	 * phy_tunable_strings[] in net/core/ethtool.c
+	 * phy_tunable_strings[] in net/ethtool/common.c
 	 */
 	__ETHTOOL_PHY_TUNABLE_COUNT,
 };
diff --git a/include/uapi/linux/icmp.h b/include/uapi/linux/icmp.h
index c1da8244c5e1..163c0998aec9 100644
--- a/include/uapi/linux/icmp.h
+++ b/include/uapi/linux/icmp.h
@@ -20,7 +20,6 @@
 
 #include <linux/types.h>
 #include <asm/byteorder.h>
-#include <linux/in.h>
 #include <linux/if.h>
 #include <linux/in6.h>
 
@@ -154,7 +153,7 @@ struct icmp_ext_echo_iio {
 		struct {
 			struct icmp_ext_echo_ctype3_hdr ctype3_hdr;
 			union {
-				struct in_addr	ipv4_addr;
+				__be32		ipv4_addr;
 				struct in6_addr	ipv6_addr;
 			} ip_addr;
 		} addr;
diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index 13d59c51ef5b..6b56a7549531 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -627,6 +627,8 @@ enum {
 	MDBA_ROUTER_PATTR_UNSPEC,
 	MDBA_ROUTER_PATTR_TIMER,
 	MDBA_ROUTER_PATTR_TYPE,
+	MDBA_ROUTER_PATTR_INET_TIMER,
+	MDBA_ROUTER_PATTR_INET6_TIMER,
 	__MDBA_ROUTER_PATTR_MAX
 };
 #define MDBA_ROUTER_PATTR_MAX (__MDBA_ROUTER_PATTR_MAX - 1)
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index cd5b382a4138..4882e81514b6 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -341,6 +341,13 @@ enum {
 	IFLA_ALT_IFNAME, /* Alternative ifname */
 	IFLA_PERM_ADDRESS,
 	IFLA_PROTO_DOWN_REASON,
+
+	/* device (sysfs) name as parent, used instead
+	 * of IFLA_LINK where there's no parent netdev
+	 */
+	IFLA_PARENT_DEV_NAME,
+	IFLA_PARENT_DEV_BUS_NAME,
+
 	__IFLA_MAX
 };
 
@@ -1236,6 +1243,8 @@ enum {
 #define RMNET_FLAGS_INGRESS_MAP_COMMANDS          (1U << 1)
 #define RMNET_FLAGS_INGRESS_MAP_CKSUMV4           (1U << 2)
 #define RMNET_FLAGS_EGRESS_MAP_CKSUMV4            (1U << 3)
+#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5           (1U << 4)
+#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5            (1U << 5)
 
 enum {
 	IFLA_RMNET_UNSPEC,
diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h
index 8eb3c0844bff..7b05f7102321 100644
--- a/include/uapi/linux/mptcp.h
+++ b/include/uapi/linux/mptcp.h
@@ -105,6 +105,7 @@ struct mptcp_info {
 	__u64	mptcpi_rcv_nxt;
 	__u8	mptcpi_local_addr_used;
 	__u8	mptcpi_local_addr_max;
+	__u8	mptcpi_csum_enabled;
 };
 
 /*
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 1fb4ca18ffbb..19715e2679d1 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -813,11 +813,13 @@ enum nft_exthdr_flags {
  * @NFT_EXTHDR_OP_IPV6: match against ipv6 extension headers
  * @NFT_EXTHDR_OP_TCP: match against tcp options
  * @NFT_EXTHDR_OP_IPV4: match against ipv4 options
+ * @NFT_EXTHDR_OP_SCTP: match against sctp chunks
  */
 enum nft_exthdr_op {
 	NFT_EXTHDR_OP_IPV6,
 	NFT_EXTHDR_OP_TCPOPT,
 	NFT_EXTHDR_OP_IPV4,
+	NFT_EXTHDR_OP_SCTP,
 	__NFT_EXTHDR_OP_MAX
 };
 #define NFT_EXTHDR_OP_MAX	(__NFT_EXTHDR_OP_MAX - 1)
diff --git a/include/uapi/linux/netfilter/nfnetlink.h b/include/uapi/linux/netfilter/nfnetlink.h
index 5bc960f220b3..6cd58cd2a6f0 100644
--- a/include/uapi/linux/netfilter/nfnetlink.h
+++ b/include/uapi/linux/netfilter/nfnetlink.h
@@ -60,7 +60,8 @@ struct nfgenmsg {
 #define NFNL_SUBSYS_CTHELPER		9
 #define NFNL_SUBSYS_NFTABLES		10
 #define NFNL_SUBSYS_NFT_COMPAT		11
-#define NFNL_SUBSYS_COUNT		12
+#define NFNL_SUBSYS_HOOK		12
+#define NFNL_SUBSYS_COUNT		13
 
 /* Reserved control nfnetlink messages */
 #define NFNL_MSG_BATCH_BEGIN		NLMSG_MIN_TYPE
diff --git a/include/uapi/linux/netfilter/nfnetlink_hook.h b/include/uapi/linux/netfilter/nfnetlink_hook.h
new file mode 100644
index 000000000000..912ec60b26b0
--- /dev/null
+++ b/include/uapi/linux/netfilter/nfnetlink_hook.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _NFNL_HOOK_H_
+#define _NFNL_HOOK_H_
+
+enum nfnl_hook_msg_types {
+	NFNL_MSG_HOOK_GET,
+	NFNL_MSG_HOOK_MAX,
+};
+
+/**
+ * enum nfnl_hook_attributes - netfilter hook netlink attributes
+ *
+ * @NFNLA_HOOK_HOOKNUM: netfilter hook number (NLA_U32)
+ * @NFNLA_HOOK_PRIORITY: netfilter hook priority (NLA_U32)
+ * @NFNLA_HOOK_DEV: netdevice name (NLA_STRING)
+ * @NFNLA_HOOK_FUNCTION_NAME: hook function name (NLA_STRING)
+ * @NFNLA_HOOK_MODULE_NAME: kernel module that registered this hook (NLA_STRING)
+ * @NFNLA_HOOK_CHAIN_INFO: basechain hook metadata (NLA_NESTED)
+ */
+enum nfnl_hook_attributes {
+	NFNLA_HOOK_UNSPEC,
+	NFNLA_HOOK_HOOKNUM,
+	NFNLA_HOOK_PRIORITY,
+	NFNLA_HOOK_DEV,
+	NFNLA_HOOK_FUNCTION_NAME,
+	NFNLA_HOOK_MODULE_NAME,
+	NFNLA_HOOK_CHAIN_INFO,
+	__NFNLA_HOOK_MAX
+};
+#define NFNLA_HOOK_MAX		(__NFNLA_HOOK_MAX - 1)
+
+/**
+ * enum nfnl_hook_chain_info_attributes - chain description
+ *
+ * NFNLA_HOOK_INFO_DESC: nft chain and table name (enum nft_table_attributes) (NLA_NESTED)
+ * NFNLA_HOOK_INFO_TYPE: chain type (enum nfnl_hook_chaintype) (NLA_U32)
+ */
+enum nfnl_hook_chain_info_attributes {
+	NFNLA_HOOK_INFO_UNSPEC,
+	NFNLA_HOOK_INFO_DESC,
+	NFNLA_HOOK_INFO_TYPE,
+	__NFNLA_HOOK_INFO_MAX,
+};
+#define NFNLA_HOOK_INFO_MAX (__NFNLA_HOOK_INFO_MAX - 1)
+
+/**
+ * enum nfnl_hook_chaintype - chain type
+ *
+ * @NFNL_HOOK_TYPE_NFTABLES nf_tables base chain
+ */
+enum nfnl_hook_chaintype {
+	NFNL_HOOK_TYPE_NFTABLES = 0x1,
+};
+
+#endif /* _NFNL_HOOK_H */
diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
index 3d94269bbfa8..4c0cde075c27 100644
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -91,9 +91,10 @@ struct nlmsghdr {
 #define NLMSG_HDRLEN	 ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr)))
 #define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN)
 #define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len))
-#define NLMSG_DATA(nlh)  ((void*)(((char*)nlh) + NLMSG_LENGTH(0)))
+#define NLMSG_DATA(nlh)  ((void *)(((char *)nlh) + NLMSG_HDRLEN))
 #define NLMSG_NEXT(nlh,len)	 ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \
-				  (struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len)))
+				  (struct nlmsghdr *)(((char *)(nlh)) + \
+				  NLMSG_ALIGN((nlh)->nlmsg_len)))
 #define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \
 			   (nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \
 			   (nlh)->nlmsg_len <= (len))
diff --git a/include/uapi/linux/seg6_local.h b/include/uapi/linux/seg6_local.h
index 5ae3ace84de0..332b18f318f8 100644
--- a/include/uapi/linux/seg6_local.h
+++ b/include/uapi/linux/seg6_local.h
@@ -64,6 +64,8 @@ enum {
 	SEG6_LOCAL_ACTION_END_AM	= 14,
 	/* custom BPF action */
 	SEG6_LOCAL_ACTION_END_BPF	= 15,
+	/* decap and lookup of DA in v4 or v6 table */
+	SEG6_LOCAL_ACTION_END_DT46	= 16,
 
 	__SEG6_LOCAL_ACTION_MAX,
 };
diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h
index 3e68da07fba2..0f7f87c70baf 100644
--- a/include/uapi/linux/smc.h
+++ b/include/uapi/linux/smc.h
@@ -47,6 +47,8 @@ enum {
 	SMC_NETLINK_GET_LGR_SMCD,
 	SMC_NETLINK_GET_DEV_SMCD,
 	SMC_NETLINK_GET_DEV_SMCR,
+	SMC_NETLINK_GET_STATS,
+	SMC_NETLINK_GET_FBACK_STATS,
 };
 
 /* SMC_GENL_FAMILY top level attributes */
@@ -58,6 +60,8 @@ enum {
 	SMC_GEN_LGR_SMCD,		/* nest */
 	SMC_GEN_DEV_SMCD,		/* nest */
 	SMC_GEN_DEV_SMCR,		/* nest */
+	SMC_GEN_STATS,			/* nest */
+	SMC_GEN_FBACK_STATS,		/* nest */
 	__SMC_GEN_MAX,
 	SMC_GEN_MAX = __SMC_GEN_MAX - 1
 };
@@ -159,4 +163,83 @@ enum {
 	SMC_NLA_DEV_MAX = __SMC_NLA_DEV_MAX - 1
 };
 
+/* SMC_NLA_STATS_T_TX(RX)_RMB_SIZE nested attributes */
+/* SMC_NLA_STATS_TX(RX)PLOAD_SIZE nested attributes */
+enum {
+	SMC_NLA_STATS_PLOAD_PAD,
+	SMC_NLA_STATS_PLOAD_8K,		/* u64 */
+	SMC_NLA_STATS_PLOAD_16K,	/* u64 */
+	SMC_NLA_STATS_PLOAD_32K,	/* u64 */
+	SMC_NLA_STATS_PLOAD_64K,	/* u64 */
+	SMC_NLA_STATS_PLOAD_128K,	/* u64 */
+	SMC_NLA_STATS_PLOAD_256K,	/* u64 */
+	SMC_NLA_STATS_PLOAD_512K,	/* u64 */
+	SMC_NLA_STATS_PLOAD_1024K,	/* u64 */
+	SMC_NLA_STATS_PLOAD_G_1024K,	/* u64 */
+	__SMC_NLA_STATS_PLOAD_MAX,
+	SMC_NLA_STATS_PLOAD_MAX = __SMC_NLA_STATS_PLOAD_MAX - 1
+};
+
+/* SMC_NLA_STATS_T_TX(RX)_RMB_STATS nested attributes */
+enum {
+	SMC_NLA_STATS_RMB_PAD,
+	SMC_NLA_STATS_RMB_SIZE_SM_PEER_CNT,	/* u64 */
+	SMC_NLA_STATS_RMB_SIZE_SM_CNT,		/* u64 */
+	SMC_NLA_STATS_RMB_FULL_PEER_CNT,	/* u64 */
+	SMC_NLA_STATS_RMB_FULL_CNT,		/* u64 */
+	SMC_NLA_STATS_RMB_REUSE_CNT,		/* u64 */
+	SMC_NLA_STATS_RMB_ALLOC_CNT,		/* u64 */
+	SMC_NLA_STATS_RMB_DGRADE_CNT,		/* u64 */
+	__SMC_NLA_STATS_RMB_MAX,
+	SMC_NLA_STATS_RMB_MAX = __SMC_NLA_STATS_RMB_MAX - 1
+};
+
+/* SMC_NLA_STATS_SMCD_TECH and _SMCR_TECH nested attributes */
+enum {
+	SMC_NLA_STATS_T_PAD,
+	SMC_NLA_STATS_T_TX_RMB_SIZE,	/* nest */
+	SMC_NLA_STATS_T_RX_RMB_SIZE,	/* nest */
+	SMC_NLA_STATS_T_TXPLOAD_SIZE,	/* nest */
+	SMC_NLA_STATS_T_RXPLOAD_SIZE,	/* nest */
+	SMC_NLA_STATS_T_TX_RMB_STATS,	/* nest */
+	SMC_NLA_STATS_T_RX_RMB_STATS,	/* nest */
+	SMC_NLA_STATS_T_CLNT_V1_SUCC,	/* u64 */
+	SMC_NLA_STATS_T_CLNT_V2_SUCC,	/* u64 */
+	SMC_NLA_STATS_T_SRV_V1_SUCC,	/* u64 */
+	SMC_NLA_STATS_T_SRV_V2_SUCC,	/* u64 */
+	SMC_NLA_STATS_T_SENDPAGE_CNT,	/* u64 */
+	SMC_NLA_STATS_T_SPLICE_CNT,	/* u64 */
+	SMC_NLA_STATS_T_CORK_CNT,	/* u64 */
+	SMC_NLA_STATS_T_NDLY_CNT,	/* u64 */
+	SMC_NLA_STATS_T_URG_DATA_CNT,	/* u64 */
+	SMC_NLA_STATS_T_RX_BYTES,	/* u64 */
+	SMC_NLA_STATS_T_TX_BYTES,	/* u64 */
+	SMC_NLA_STATS_T_RX_CNT,		/* u64 */
+	SMC_NLA_STATS_T_TX_CNT,		/* u64 */
+	__SMC_NLA_STATS_T_MAX,
+	SMC_NLA_STATS_T_MAX = __SMC_NLA_STATS_T_MAX - 1
+};
+
+/* SMC_GEN_STATS attributes */
+enum {
+	SMC_NLA_STATS_PAD,
+	SMC_NLA_STATS_SMCD_TECH,	/* nest */
+	SMC_NLA_STATS_SMCR_TECH,	/* nest */
+	SMC_NLA_STATS_CLNT_HS_ERR_CNT,	/* u64 */
+	SMC_NLA_STATS_SRV_HS_ERR_CNT,	/* u64 */
+	__SMC_NLA_STATS_MAX,
+	SMC_NLA_STATS_MAX = __SMC_NLA_STATS_MAX - 1
+};
+
+/* SMC_GEN_FBACK_STATS attributes */
+enum {
+	SMC_NLA_FBACK_STATS_PAD,
+	SMC_NLA_FBACK_STATS_TYPE,	/* u8 */
+	SMC_NLA_FBACK_STATS_SRV_CNT,	/* u64 */
+	SMC_NLA_FBACK_STATS_CLNT_CNT,	/* u64 */
+	SMC_NLA_FBACK_STATS_RSN_CODE,	/* u32 */
+	SMC_NLA_FBACK_STATS_RSN_CNT,	/* u16 */
+	__SMC_NLA_FBACK_STATS_MAX,
+	SMC_NLA_FBACK_STATS_MAX = __SMC_NLA_FBACK_STATS_MAX - 1
+};
 #endif /* _UAPI_LINUX_SMC_H */
diff --git a/include/uapi/linux/virtio_vsock.h b/include/uapi/linux/virtio_vsock.h
index 1d57ed3d84d2..3dd3555b2740 100644
--- a/include/uapi/linux/virtio_vsock.h
+++ b/include/uapi/linux/virtio_vsock.h
@@ -38,6 +38,9 @@
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
 
+/* The feature bitmap for virtio vsock */
+#define VIRTIO_VSOCK_F_SEQPACKET	1	/* SOCK_SEQPACKET supported */
+
 struct virtio_vsock_config {
 	__le64 guest_cid;
 } __attribute__((packed));
@@ -65,6 +68,7 @@ struct virtio_vsock_hdr {
 
 enum virtio_vsock_type {
 	VIRTIO_VSOCK_TYPE_STREAM = 1,
+	VIRTIO_VSOCK_TYPE_SEQPACKET = 2,
 };
 
 enum virtio_vsock_op {
@@ -91,4 +95,9 @@ enum virtio_vsock_shutdown {
 	VIRTIO_VSOCK_SHUTDOWN_SEND = 2,
 };
 
+/* VIRTIO_VSOCK_OP_RW flags values */
+enum virtio_vsock_rw {
+	VIRTIO_VSOCK_SEQ_EOR = 1,
+};
+
 #endif /* _UAPI_LINUX_VIRTIO_VSOCK_H */
diff --git a/include/uapi/linux/wwan.h b/include/uapi/linux/wwan.h
new file mode 100644
index 000000000000..32a2720b4d11
--- /dev/null
+++ b/include/uapi/linux/wwan.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2021 Intel Corporation.
+ */
+#ifndef _UAPI_WWAN_H_
+#define _UAPI_WWAN_H_
+
+enum {
+	IFLA_WWAN_UNSPEC,
+	IFLA_WWAN_LINK_ID, /* u32 */
+
+	__IFLA_WWAN_MAX
+};
+#define IFLA_WWAN_MAX (__IFLA_WWAN_MAX - 1)
+
+#endif /* _UAPI_WWAN_H_ */
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index 2921ca39a93e..96ceed0e0fb5 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -72,7 +72,7 @@ void bpf_inode_storage_free(struct inode *inode)
 		return;
 	}
 
-	/* Netiher the bpf_prog nor the bpf-map's syscall
+	/* Neither the bpf_prog nor the bpf-map's syscall
 	 * could be modifying the local_storage->list now.
 	 * Thus, no elem can be added-to or deleted-from the
 	 * local_storage->list by the bpf_prog or by the bpf-map's syscall.
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 931870f9cf56..2d4fbdbb194e 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -473,15 +473,16 @@ bool bpf_link_is_iter(struct bpf_link *link)
 	return link->ops == &bpf_iter_link_lops;
 }
 
-int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr,
+			 struct bpf_prog *prog)
 {
-	union bpf_iter_link_info __user *ulinfo;
 	struct bpf_link_primer link_primer;
 	struct bpf_iter_target_info *tinfo;
 	union bpf_iter_link_info linfo;
 	struct bpf_iter_link *link;
 	u32 prog_btf_id, linfo_len;
 	bool existed = false;
+	bpfptr_t ulinfo;
 	int err;
 
 	if (attr->link_create.target_fd || attr->link_create.flags)
@@ -489,18 +490,18 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 
 	memset(&linfo, 0, sizeof(union bpf_iter_link_info));
 
-	ulinfo = u64_to_user_ptr(attr->link_create.iter_info);
+	ulinfo = make_bpfptr(attr->link_create.iter_info, uattr.is_kernel);
 	linfo_len = attr->link_create.iter_info_len;
-	if (!ulinfo ^ !linfo_len)
+	if (bpfptr_is_null(ulinfo) ^ !linfo_len)
 		return -EINVAL;
 
-	if (ulinfo) {
+	if (!bpfptr_is_null(ulinfo)) {
 		err = bpf_check_uarg_tail_zero(ulinfo, sizeof(linfo),
 					       linfo_len);
 		if (err)
 			return err;
 		linfo_len = min_t(u32, linfo_len, sizeof(linfo));
-		if (copy_from_user(&linfo, ulinfo, linfo_len))
+		if (copy_from_bpfptr(&linfo, ulinfo, linfo_len))
 			return -EFAULT;
 	}
 
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index da471bf01b97..06062370c3b8 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -127,7 +127,7 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 }
 
 /* The set of hooks which are called without pagefaults disabled and are allowed
- * to "sleep" and thus can be used for sleeable BPF programs.
+ * to "sleep" and thus can be used for sleepable BPF programs.
  */
 BTF_SET_START(sleepable_lsm_hooks)
 BTF_ID(func, bpf_lsm_bpf)
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index f982a9f0dbc4..cb4b72997d9b 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -51,7 +51,7 @@
  * The BTF type section contains a list of 'struct btf_type' objects.
  * Each one describes a C type.  Recall from the above section
  * that a 'struct btf_type' object could be immediately followed by extra
- * data in order to desribe some particular C types.
+ * data in order to describe some particular C types.
  *
  * type_id:
  * ~~~~~~~
@@ -1143,7 +1143,7 @@ static void *btf_show_obj_safe(struct btf_show *show,
 
 	/*
 	 * We need a new copy to our safe object, either because we haven't
-	 * yet copied and are intializing safe data, or because the data
+	 * yet copied and are initializing safe data, or because the data
 	 * we want falls outside the boundaries of the safe object.
 	 */
 	if (!safe) {
@@ -3417,7 +3417,7 @@ static struct btf_kind_operations func_proto_ops = {
 	 * BTF_KIND_FUNC_PROTO cannot be directly referred by
 	 * a struct's member.
 	 *
-	 * It should be a funciton pointer instead.
+	 * It should be a function pointer instead.
 	 * (i.e. struct's member -> BTF_KIND_PTR -> BTF_KIND_FUNC_PROTO)
 	 *
 	 * Hence, there is no btf_func_check_member().
@@ -4257,7 +4257,7 @@ static int btf_parse_hdr(struct btf_verifier_env *env)
 	return 0;
 }
 
-static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size,
+static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size,
 			     u32 log_level, char __user *log_ubuf, u32 log_size)
 {
 	struct btf_verifier_env *env = NULL;
@@ -4306,7 +4306,7 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size,
 	btf->data = data;
 	btf->data_size = btf_data_size;
 
-	if (copy_from_user(data, btf_data, btf_data_size)) {
+	if (copy_from_bpfptr(data, btf_data, btf_data_size)) {
 		err = -EFAULT;
 		goto errout;
 	}
@@ -5792,12 +5792,12 @@ static int __btf_new_fd(struct btf *btf)
 	return anon_inode_getfd("btf", &btf_fops, btf, O_RDONLY | O_CLOEXEC);
 }
 
-int btf_new_fd(const union bpf_attr *attr)
+int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr)
 {
 	struct btf *btf;
 	int ret;
 
-	btf = btf_parse(u64_to_user_ptr(attr->btf),
+	btf = btf_parse(make_bpfptr(attr->btf, uattr.is_kernel),
 			attr->btf_size, attr->btf_log_level,
 			u64_to_user_ptr(attr->btf_log_buf),
 			attr->btf_log_size);
@@ -6097,3 +6097,65 @@ struct module *btf_try_get_module(const struct btf *btf)
 
 	return res;
 }
+
+BPF_CALL_4(bpf_btf_find_by_name_kind, char *, name, int, name_sz, u32, kind, int, flags)
+{
+	struct btf *btf;
+	long ret;
+
+	if (flags)
+		return -EINVAL;
+
+	if (name_sz <= 1 || name[name_sz - 1])
+		return -EINVAL;
+
+	btf = bpf_get_btf_vmlinux();
+	if (IS_ERR(btf))
+		return PTR_ERR(btf);
+
+	ret = btf_find_by_name_kind(btf, name, kind);
+	/* ret is never zero, since btf_find_by_name_kind returns
+	 * positive btf_id or negative error.
+	 */
+	if (ret < 0) {
+		struct btf *mod_btf;
+		int id;
+
+		/* If name is not found in vmlinux's BTF then search in module's BTFs */
+		spin_lock_bh(&btf_idr_lock);
+		idr_for_each_entry(&btf_idr, mod_btf, id) {
+			if (!btf_is_module(mod_btf))
+				continue;
+			/* linear search could be slow hence unlock/lock
+			 * the IDR to avoiding holding it for too long
+			 */
+			btf_get(mod_btf);
+			spin_unlock_bh(&btf_idr_lock);
+			ret = btf_find_by_name_kind(mod_btf, name, kind);
+			if (ret > 0) {
+				int btf_obj_fd;
+
+				btf_obj_fd = __btf_new_fd(mod_btf);
+				if (btf_obj_fd < 0) {
+					btf_put(mod_btf);
+					return btf_obj_fd;
+				}
+				return ret | (((u64)btf_obj_fd) << 32);
+			}
+			spin_lock_bh(&btf_idr_lock);
+			btf_put(mod_btf);
+		}
+		spin_unlock_bh(&btf_idr_lock);
+	}
+	return ret;
+}
+
+const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = {
+	.func		= bpf_btf_find_by_name_kind,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_ANYTHING,
+};
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 5e31ee9f7512..034ad93a1ad7 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1392,29 +1392,54 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn)
 select_insn:
 	goto *jumptable[insn->code];
 
-	/* ALU */
-#define ALU(OPCODE, OP)			\
-	ALU64_##OPCODE##_X:		\
-		DST = DST OP SRC;	\
-		CONT;			\
-	ALU_##OPCODE##_X:		\
-		DST = (u32) DST OP (u32) SRC;	\
-		CONT;			\
-	ALU64_##OPCODE##_K:		\
-		DST = DST OP IMM;		\
-		CONT;			\
-	ALU_##OPCODE##_K:		\
-		DST = (u32) DST OP (u32) IMM;	\
+	/* Explicitly mask the register-based shift amounts with 63 or 31
+	 * to avoid undefined behavior. Normally this won't affect the
+	 * generated code, for example, in case of native 64 bit archs such
+	 * as x86-64 or arm64, the compiler is optimizing the AND away for
+	 * the interpreter. In case of JITs, each of the JIT backends compiles
+	 * the BPF shift operations to machine instructions which produce
+	 * implementation-defined results in such a case; the resulting
+	 * contents of the register may be arbitrary, but program behaviour
+	 * as a whole remains defined. In other words, in case of JIT backends,
+	 * the AND must /not/ be added to the emitted LSH/RSH/ARSH translation.
+	 */
+	/* ALU (shifts) */
+#define SHT(OPCODE, OP)					\
+	ALU64_##OPCODE##_X:				\
+		DST = DST OP (SRC & 63);		\
+		CONT;					\
+	ALU_##OPCODE##_X:				\
+		DST = (u32) DST OP ((u32) SRC & 31);	\
+		CONT;					\
+	ALU64_##OPCODE##_K:				\
+		DST = DST OP IMM;			\
+		CONT;					\
+	ALU_##OPCODE##_K:				\
+		DST = (u32) DST OP (u32) IMM;		\
+		CONT;
+	/* ALU (rest) */
+#define ALU(OPCODE, OP)					\
+	ALU64_##OPCODE##_X:				\
+		DST = DST OP SRC;			\
+		CONT;					\
+	ALU_##OPCODE##_X:				\
+		DST = (u32) DST OP (u32) SRC;		\
+		CONT;					\
+	ALU64_##OPCODE##_K:				\
+		DST = DST OP IMM;			\
+		CONT;					\
+	ALU_##OPCODE##_K:				\
+		DST = (u32) DST OP (u32) IMM;		\
 		CONT;
-
 	ALU(ADD,  +)
 	ALU(SUB,  -)
 	ALU(AND,  &)
 	ALU(OR,   |)
-	ALU(LSH, <<)
-	ALU(RSH, >>)
 	ALU(XOR,  ^)
 	ALU(MUL,  *)
+	SHT(LSH, <<)
+	SHT(RSH, >>)
+#undef SHT
 #undef ALU
 	ALU_NEG:
 		DST = (u32) -DST;
@@ -1439,13 +1464,13 @@ select_insn:
 		insn++;
 		CONT;
 	ALU_ARSH_X:
-		DST = (u64) (u32) (((s32) DST) >> SRC);
+		DST = (u64) (u32) (((s32) DST) >> (SRC & 31));
 		CONT;
 	ALU_ARSH_K:
 		DST = (u64) (u32) (((s32) DST) >> IMM);
 		CONT;
 	ALU64_ARSH_X:
-		(*(s64 *) &DST) >>= SRC;
+		(*(s64 *) &DST) >>= (SRC & 63);
 		CONT;
 	ALU64_ARSH_K:
 		(*(s64 *) &DST) >>= IMM;
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 5dd3e866599a..a1a0c4e791c6 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -601,7 +601,8 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 
 static int cpu_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
 {
-	return __bpf_xdp_redirect_map(map, ifindex, flags, __cpu_map_lookup_elem);
+	return __bpf_xdp_redirect_map(map, ifindex, flags, 0,
+				      __cpu_map_lookup_elem);
 }
 
 static int cpu_map_btf_id;
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index aa516472ce46..2a75e6c2d27d 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -57,6 +57,7 @@ struct xdp_dev_bulk_queue {
 	struct list_head flush_node;
 	struct net_device *dev;
 	struct net_device *dev_rx;
+	struct bpf_prog *xdp_prog;
 	unsigned int count;
 };
 
@@ -197,6 +198,7 @@ static void dev_map_free(struct bpf_map *map)
 	list_del_rcu(&dtab->list);
 	spin_unlock(&dev_map_lock);
 
+	bpf_clear_redirect_map(map);
 	synchronize_rcu();
 
 	/* Make sure prior __dev_map_entry_free() have completed. */
@@ -326,22 +328,69 @@ bool dev_map_can_have_prog(struct bpf_map *map)
 	return false;
 }
 
+static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog,
+				struct xdp_frame **frames, int n,
+				struct net_device *dev)
+{
+	struct xdp_txq_info txq = { .dev = dev };
+	struct xdp_buff xdp;
+	int i, nframes = 0;
+
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *xdpf = frames[i];
+		u32 act;
+		int err;
+
+		xdp_convert_frame_to_buff(xdpf, &xdp);
+		xdp.txq = &txq;
+
+		act = bpf_prog_run_xdp(xdp_prog, &xdp);
+		switch (act) {
+		case XDP_PASS:
+			err = xdp_update_frame_from_buff(&xdp, xdpf);
+			if (unlikely(err < 0))
+				xdp_return_frame_rx_napi(xdpf);
+			else
+				frames[nframes++] = xdpf;
+			break;
+		default:
+			bpf_warn_invalid_xdp_action(act);
+			fallthrough;
+		case XDP_ABORTED:
+			trace_xdp_exception(dev, xdp_prog, act);
+			fallthrough;
+		case XDP_DROP:
+			xdp_return_frame_rx_napi(xdpf);
+			break;
+		}
+	}
+	return nframes; /* sent frames count */
+}
+
 static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
 {
 	struct net_device *dev = bq->dev;
+	unsigned int cnt = bq->count;
 	int sent = 0, err = 0;
+	int to_send = cnt;
 	int i;
 
-	if (unlikely(!bq->count))
+	if (unlikely(!cnt))
 		return;
 
-	for (i = 0; i < bq->count; i++) {
+	for (i = 0; i < cnt; i++) {
 		struct xdp_frame *xdpf = bq->q[i];
 
 		prefetch(xdpf);
 	}
 
-	sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q, flags);
+	if (bq->xdp_prog) {
+		to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev);
+		if (!to_send)
+			goto out;
+	}
+
+	sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags);
 	if (sent < 0) {
 		/* If ndo_xdp_xmit fails with an errno, no frames have
 		 * been xmit'ed.
@@ -353,13 +402,12 @@ static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
 	/* If not all frames have been transmitted, it is our
 	 * responsibility to free them
 	 */
-	for (i = sent; unlikely(i < bq->count); i++)
+	for (i = sent; unlikely(i < to_send); i++)
 		xdp_return_frame_rx_napi(bq->q[i]);
 
-	trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, bq->count - sent, err);
-	bq->dev_rx = NULL;
+out:
 	bq->count = 0;
-	__list_del_clearprev(&bq->flush_node);
+	trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err);
 }
 
 /* __dev_flush is called from xdp_do_flush() which _must_ be signaled
@@ -377,13 +425,17 @@ void __dev_flush(void)
 	struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
 	struct xdp_dev_bulk_queue *bq, *tmp;
 
-	list_for_each_entry_safe(bq, tmp, flush_list, flush_node)
+	list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
 		bq_xmit_all(bq, XDP_XMIT_FLUSH);
+		bq->dev_rx = NULL;
+		bq->xdp_prog = NULL;
+		__list_del_clearprev(&bq->flush_node);
+	}
 }
 
 /* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or
- * update happens in parallel here a dev_put wont happen until after reading the
- * ifindex.
+ * update happens in parallel here a dev_put won't happen until after reading
+ * the ifindex.
  */
 static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
 {
@@ -401,7 +453,7 @@ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
  * Thus, safe percpu variable access.
  */
 static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
-		       struct net_device *dev_rx)
+		       struct net_device *dev_rx, struct bpf_prog *xdp_prog)
 {
 	struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
 	struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
@@ -412,18 +464,22 @@ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
 	/* Ingress dev_rx will be the same for all xdp_frame's in
 	 * bulk_queue, because bq stored per-CPU and must be flushed
 	 * from net_device drivers NAPI func end.
+	 *
+	 * Do the same with xdp_prog and flush_list since these fields
+	 * are only ever modified together.
 	 */
-	if (!bq->dev_rx)
+	if (!bq->dev_rx) {
 		bq->dev_rx = dev_rx;
+		bq->xdp_prog = xdp_prog;
+		list_add(&bq->flush_node, flush_list);
+	}
 
 	bq->q[bq->count++] = xdpf;
-
-	if (!bq->flush_node.prev)
-		list_add(&bq->flush_node, flush_list);
 }
 
 static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
-			       struct net_device *dev_rx)
+				struct net_device *dev_rx,
+				struct bpf_prog *xdp_prog)
 {
 	struct xdp_frame *xdpf;
 	int err;
@@ -439,55 +495,115 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
 	if (unlikely(!xdpf))
 		return -EOVERFLOW;
 
-	bq_enqueue(dev, xdpf, dev_rx);
+	bq_enqueue(dev, xdpf, dev_rx, xdp_prog);
 	return 0;
 }
 
-static struct xdp_buff *dev_map_run_prog(struct net_device *dev,
-					 struct xdp_buff *xdp,
-					 struct bpf_prog *xdp_prog)
+int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+		    struct net_device *dev_rx)
 {
-	struct xdp_txq_info txq = { .dev = dev };
-	u32 act;
+	return __xdp_enqueue(dev, xdp, dev_rx, NULL);
+}
 
-	xdp_set_data_meta_invalid(xdp);
-	xdp->txq = &txq;
+int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
+		    struct net_device *dev_rx)
+{
+	struct net_device *dev = dst->dev;
 
-	act = bpf_prog_run_xdp(xdp_prog, xdp);
-	switch (act) {
-	case XDP_PASS:
-		return xdp;
-	case XDP_DROP:
-		break;
-	default:
-		bpf_warn_invalid_xdp_action(act);
-		fallthrough;
-	case XDP_ABORTED:
-		trace_xdp_exception(dev, xdp_prog, act);
-		break;
-	}
+	return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog);
+}
 
-	xdp_return_buff(xdp);
-	return NULL;
+static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_buff *xdp,
+			 int exclude_ifindex)
+{
+	if (!obj || obj->dev->ifindex == exclude_ifindex ||
+	    !obj->dev->netdev_ops->ndo_xdp_xmit)
+		return false;
+
+	if (xdp_ok_fwd_dev(obj->dev, xdp->data_end - xdp->data))
+		return false;
+
+	return true;
 }
 
-int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
-		    struct net_device *dev_rx)
+static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj,
+				 struct net_device *dev_rx,
+				 struct xdp_frame *xdpf)
 {
-	return __xdp_enqueue(dev, xdp, dev_rx);
+	struct xdp_frame *nxdpf;
+
+	nxdpf = xdpf_clone(xdpf);
+	if (!nxdpf)
+		return -ENOMEM;
+
+	bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog);
+
+	return 0;
 }
 
-int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
-		    struct net_device *dev_rx)
+int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+			  struct bpf_map *map, bool exclude_ingress)
 {
-	struct net_device *dev = dst->dev;
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	int exclude_ifindex = exclude_ingress ? dev_rx->ifindex : 0;
+	struct bpf_dtab_netdev *dst, *last_dst = NULL;
+	struct hlist_head *head;
+	struct xdp_frame *xdpf;
+	unsigned int i;
+	int err;
 
-	if (dst->xdp_prog) {
-		xdp = dev_map_run_prog(dev, xdp, dst->xdp_prog);
-		if (!xdp)
-			return 0;
+	xdpf = xdp_convert_buff_to_frame(xdp);
+	if (unlikely(!xdpf))
+		return -EOVERFLOW;
+
+	if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+		for (i = 0; i < map->max_entries; i++) {
+			dst = READ_ONCE(dtab->netdev_map[i]);
+			if (!is_valid_dst(dst, xdp, exclude_ifindex))
+				continue;
+
+			/* we only need n-1 clones; last_dst enqueued below */
+			if (!last_dst) {
+				last_dst = dst;
+				continue;
+			}
+
+			err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf);
+			if (err)
+				return err;
+
+			last_dst = dst;
+		}
+	} else { /* BPF_MAP_TYPE_DEVMAP_HASH */
+		for (i = 0; i < dtab->n_buckets; i++) {
+			head = dev_map_index_hash(dtab, i);
+			hlist_for_each_entry_rcu(dst, head, index_hlist,
+						 lockdep_is_held(&dtab->index_lock)) {
+				if (!is_valid_dst(dst, xdp, exclude_ifindex))
+					continue;
+
+				/* we only need n-1 clones; last_dst enqueued below */
+				if (!last_dst) {
+					last_dst = dst;
+					continue;
+				}
+
+				err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf);
+				if (err)
+					return err;
+
+				last_dst = dst;
+			}
+		}
 	}
-	return __xdp_enqueue(dev, xdp, dev_rx);
+
+	/* consume the last copy of the frame */
+	if (last_dst)
+		bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog);
+	else
+		xdp_return_frame_rx_napi(xdpf); /* dtab is empty */
+
+	return 0;
 }
 
 int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
@@ -504,6 +620,87 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 	return 0;
 }
 
+static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst,
+				  struct sk_buff *skb,
+				  struct bpf_prog *xdp_prog)
+{
+	struct sk_buff *nskb;
+	int err;
+
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (!nskb)
+		return -ENOMEM;
+
+	err = dev_map_generic_redirect(dst, nskb, xdp_prog);
+	if (unlikely(err)) {
+		consume_skb(nskb);
+		return err;
+	}
+
+	return 0;
+}
+
+int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
+			   struct bpf_prog *xdp_prog, struct bpf_map *map,
+			   bool exclude_ingress)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	int exclude_ifindex = exclude_ingress ? dev->ifindex : 0;
+	struct bpf_dtab_netdev *dst, *last_dst = NULL;
+	struct hlist_head *head;
+	struct hlist_node *next;
+	unsigned int i;
+	int err;
+
+	if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+		for (i = 0; i < map->max_entries; i++) {
+			dst = READ_ONCE(dtab->netdev_map[i]);
+			if (!dst || dst->dev->ifindex == exclude_ifindex)
+				continue;
+
+			/* we only need n-1 clones; last_dst enqueued below */
+			if (!last_dst) {
+				last_dst = dst;
+				continue;
+			}
+
+			err = dev_map_redirect_clone(last_dst, skb, xdp_prog);
+			if (err)
+				return err;
+
+			last_dst = dst;
+		}
+	} else { /* BPF_MAP_TYPE_DEVMAP_HASH */
+		for (i = 0; i < dtab->n_buckets; i++) {
+			head = dev_map_index_hash(dtab, i);
+			hlist_for_each_entry_safe(dst, next, head, index_hlist) {
+				if (!dst || dst->dev->ifindex == exclude_ifindex)
+					continue;
+
+				/* we only need n-1 clones; last_dst enqueued below */
+				if (!last_dst) {
+					last_dst = dst;
+					continue;
+				}
+
+				err = dev_map_redirect_clone(last_dst, skb, xdp_prog);
+				if (err)
+					return err;
+
+				last_dst = dst;
+			}
+		}
+	}
+
+	/* consume the first skb and return */
+	if (last_dst)
+		return dev_map_generic_redirect(last_dst, skb, xdp_prog);
+
+	/* dtab is empty */
+	consume_skb(skb);
+	return 0;
+}
+
 static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
@@ -730,12 +927,16 @@ static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value,
 
 static int dev_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
 {
-	return __bpf_xdp_redirect_map(map, ifindex, flags, __dev_map_lookup_elem);
+	return __bpf_xdp_redirect_map(map, ifindex, flags,
+				      BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS,
+				      __dev_map_lookup_elem);
 }
 
 static int dev_hash_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
 {
-	return __bpf_xdp_redirect_map(map, ifindex, flags, __dev_map_hash_lookup_elem);
+	return __bpf_xdp_redirect_map(map, ifindex, flags,
+				      BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS,
+				      __dev_map_hash_lookup_elem);
 }
 
 static int dev_map_btf_id;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index d7ebb12ffffc..6f6681b07364 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -46,12 +46,12 @@
  * events, kprobes and tracing to be invoked before the prior invocation
  * from one of these contexts completed. sys_bpf() uses the same mechanism
  * by pinning the task to the current CPU and incrementing the recursion
- * protection accross the map operation.
+ * protection across the map operation.
  *
  * This has subtle implications on PREEMPT_RT. PREEMPT_RT forbids certain
  * operations like memory allocations (even with GFP_ATOMIC) from atomic
  * contexts. This is required because even with GFP_ATOMIC the memory
- * allocator calls into code pathes which acquire locks with long held lock
+ * allocator calls into code paths which acquire locks with long held lock
  * sections. To ensure the deterministic behaviour these locks are regular
  * spinlocks, which are converted to 'sleepable' spinlocks on RT. The only
  * true atomic contexts on an RT kernel are the low level hardware
@@ -1401,6 +1401,100 @@ static void htab_map_seq_show_elem(struct bpf_map *map, void *key,
 	rcu_read_unlock();
 }
 
+static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
+					     void *value, bool is_lru_map,
+					     bool is_percpu, u64 flags)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct hlist_nulls_head *head;
+	unsigned long bflags;
+	struct htab_elem *l;
+	u32 hash, key_size;
+	struct bucket *b;
+	int ret;
+
+	key_size = map->key_size;
+
+	hash = htab_map_hash(key, key_size, htab->hashrnd);
+	b = __select_bucket(htab, hash);
+	head = &b->head;
+
+	ret = htab_lock_bucket(htab, b, hash, &bflags);
+	if (ret)
+		return ret;
+
+	l = lookup_elem_raw(head, hash, key, key_size);
+	if (!l) {
+		ret = -ENOENT;
+	} else {
+		if (is_percpu) {
+			u32 roundup_value_size = round_up(map->value_size, 8);
+			void __percpu *pptr;
+			int off = 0, cpu;
+
+			pptr = htab_elem_get_ptr(l, key_size);
+			for_each_possible_cpu(cpu) {
+				bpf_long_memcpy(value + off,
+						per_cpu_ptr(pptr, cpu),
+						roundup_value_size);
+				off += roundup_value_size;
+			}
+		} else {
+			u32 roundup_key_size = round_up(map->key_size, 8);
+
+			if (flags & BPF_F_LOCK)
+				copy_map_value_locked(map, value, l->key +
+						      roundup_key_size,
+						      true);
+			else
+				copy_map_value(map, value, l->key +
+					       roundup_key_size);
+			check_and_init_map_lock(map, value);
+		}
+
+		hlist_nulls_del_rcu(&l->hash_node);
+		if (!is_lru_map)
+			free_htab_elem(htab, l);
+	}
+
+	htab_unlock_bucket(htab, b, hash, bflags);
+
+	if (is_lru_map && l)
+		bpf_lru_push_free(&htab->lru, &l->lru_node);
+
+	return ret;
+}
+
+static int htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
+					   void *value, u64 flags)
+{
+	return __htab_map_lookup_and_delete_elem(map, key, value, false, false,
+						 flags);
+}
+
+static int htab_percpu_map_lookup_and_delete_elem(struct bpf_map *map,
+						  void *key, void *value,
+						  u64 flags)
+{
+	return __htab_map_lookup_and_delete_elem(map, key, value, false, true,
+						 flags);
+}
+
+static int htab_lru_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
+					       void *value, u64 flags)
+{
+	return __htab_map_lookup_and_delete_elem(map, key, value, true, false,
+						 flags);
+}
+
+static int htab_lru_percpu_map_lookup_and_delete_elem(struct bpf_map *map,
+						      void *key, void *value,
+						      u64 flags)
+{
+	return __htab_map_lookup_and_delete_elem(map, key, value, true, true,
+						 flags);
+}
+
 static int
 __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 				   const union bpf_attr *attr,
@@ -1934,6 +2028,7 @@ const struct bpf_map_ops htab_map_ops = {
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
 	.map_lookup_elem = htab_map_lookup_elem,
+	.map_lookup_and_delete_elem = htab_map_lookup_and_delete_elem,
 	.map_update_elem = htab_map_update_elem,
 	.map_delete_elem = htab_map_delete_elem,
 	.map_gen_lookup = htab_map_gen_lookup,
@@ -1954,6 +2049,7 @@ const struct bpf_map_ops htab_lru_map_ops = {
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
 	.map_lookup_elem = htab_lru_map_lookup_elem,
+	.map_lookup_and_delete_elem = htab_lru_map_lookup_and_delete_elem,
 	.map_lookup_elem_sys_only = htab_lru_map_lookup_elem_sys,
 	.map_update_elem = htab_lru_map_update_elem,
 	.map_delete_elem = htab_lru_map_delete_elem,
@@ -2077,6 +2173,7 @@ const struct bpf_map_ops htab_percpu_map_ops = {
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
 	.map_lookup_elem = htab_percpu_map_lookup_elem,
+	.map_lookup_and_delete_elem = htab_percpu_map_lookup_and_delete_elem,
 	.map_update_elem = htab_percpu_map_update_elem,
 	.map_delete_elem = htab_map_delete_elem,
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
@@ -2096,6 +2193,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = {
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
 	.map_lookup_elem = htab_lru_percpu_map_lookup_elem,
+	.map_lookup_and_delete_elem = htab_lru_percpu_map_lookup_and_delete_elem,
 	.map_update_elem = htab_lru_percpu_map_update_elem,
 	.map_delete_elem = htab_lru_map_delete_elem,
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
diff --git a/kernel/bpf/preload/iterators/iterators.bpf.c b/kernel/bpf/preload/iterators/iterators.bpf.c
index 52aa7b38e8b8..03af863314ea 100644
--- a/kernel/bpf/preload/iterators/iterators.bpf.c
+++ b/kernel/bpf/preload/iterators/iterators.bpf.c
@@ -2,7 +2,6 @@
 /* Copyright (c) 2020 Facebook */
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
 #include <bpf/bpf_core_read.h>
 
 #pragma clang attribute push (__attribute__((preserve_access_index)), apply_to = record)
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 4838922f723d..93a55391791a 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -102,7 +102,7 @@ static void reuseport_array_free(struct bpf_map *map)
 	/*
 	 * ops->map_*_elem() will not be able to access this
 	 * array now. Hence, this function only races with
-	 * bpf_sk_reuseport_detach() which was triggerred by
+	 * bpf_sk_reuseport_detach() which was triggered by
 	 * close() or disconnect().
 	 *
 	 * This function and bpf_sk_reuseport_detach() are
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ea04b0deb5ce..e343f158e556 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -73,11 +73,10 @@ static const struct bpf_map_ops * const bpf_map_types[] = {
  * copy_from_user() call. However, this is not a concern since this function is
  * meant to be a future-proofing of bits.
  */
-int bpf_check_uarg_tail_zero(void __user *uaddr,
+int bpf_check_uarg_tail_zero(bpfptr_t uaddr,
 			     size_t expected_size,
 			     size_t actual_size)
 {
-	unsigned char __user *addr = uaddr + expected_size;
 	int res;
 
 	if (unlikely(actual_size > PAGE_SIZE))	/* silly large */
@@ -86,7 +85,12 @@ int bpf_check_uarg_tail_zero(void __user *uaddr,
 	if (actual_size <= expected_size)
 		return 0;
 
-	res = check_zeroed_user(addr, actual_size - expected_size);
+	if (uaddr.is_kernel)
+		res = memchr_inv(uaddr.kernel + expected_size, 0,
+				 actual_size - expected_size) == NULL;
+	else
+		res = check_zeroed_user(uaddr.user + expected_size,
+					actual_size - expected_size);
 	if (res < 0)
 		return res;
 	return res ? 0 : -E2BIG;
@@ -1005,6 +1009,17 @@ static void *__bpf_copy_key(void __user *ukey, u64 key_size)
 	return NULL;
 }
 
+static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size)
+{
+	if (key_size)
+		return memdup_bpfptr(ukey, key_size);
+
+	if (!bpfptr_is_null(ukey))
+		return ERR_PTR(-EINVAL);
+
+	return NULL;
+}
+
 /* last field in 'union bpf_attr' used by this command */
 #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags
 
@@ -1075,10 +1090,10 @@ err_put:
 
 #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags
 
-static int map_update_elem(union bpf_attr *attr)
+static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
 {
-	void __user *ukey = u64_to_user_ptr(attr->key);
-	void __user *uvalue = u64_to_user_ptr(attr->value);
+	bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel);
+	bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel);
 	int ufd = attr->map_fd;
 	struct bpf_map *map;
 	void *key, *value;
@@ -1104,7 +1119,7 @@ static int map_update_elem(union bpf_attr *attr)
 		goto err_put;
 	}
 
-	key = __bpf_copy_key(ukey, map->key_size);
+	key = ___bpf_copy_key(ukey, map->key_size);
 	if (IS_ERR(key)) {
 		err = PTR_ERR(key);
 		goto err_put;
@@ -1124,7 +1139,7 @@ static int map_update_elem(union bpf_attr *attr)
 		goto free_key;
 
 	err = -EFAULT;
-	if (copy_from_user(value, uvalue, value_size) != 0)
+	if (copy_from_bpfptr(value, uvalue, value_size) != 0)
 		goto free_value;
 
 	err = bpf_map_update_value(map, f, key, value, attr->flags);
@@ -1469,7 +1484,7 @@ free_buf:
 	return err;
 }
 
-#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value
+#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD flags
 
 static int map_lookup_and_delete_elem(union bpf_attr *attr)
 {
@@ -1485,6 +1500,9 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM))
 		return -EINVAL;
 
+	if (attr->flags & ~BPF_F_LOCK)
+		return -EINVAL;
+
 	f = fdget(ufd);
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
@@ -1495,24 +1513,47 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 		goto err_put;
 	}
 
+	if (attr->flags &&
+	    (map->map_type == BPF_MAP_TYPE_QUEUE ||
+	     map->map_type == BPF_MAP_TYPE_STACK)) {
+		err = -EINVAL;
+		goto err_put;
+	}
+
+	if ((attr->flags & BPF_F_LOCK) &&
+	    !map_value_has_spin_lock(map)) {
+		err = -EINVAL;
+		goto err_put;
+	}
+
 	key = __bpf_copy_key(ukey, map->key_size);
 	if (IS_ERR(key)) {
 		err = PTR_ERR(key);
 		goto err_put;
 	}
 
-	value_size = map->value_size;
+	value_size = bpf_map_value_size(map);
 
 	err = -ENOMEM;
 	value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
 	if (!value)
 		goto free_key;
 
+	err = -ENOTSUPP;
 	if (map->map_type == BPF_MAP_TYPE_QUEUE ||
 	    map->map_type == BPF_MAP_TYPE_STACK) {
 		err = map->ops->map_pop_elem(map, value);
-	} else {
-		err = -ENOTSUPP;
+	} else if (map->map_type == BPF_MAP_TYPE_HASH ||
+		   map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+		   map->map_type == BPF_MAP_TYPE_LRU_HASH ||
+		   map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
+		if (!bpf_map_is_dev_bound(map)) {
+			bpf_disable_instrumentation();
+			rcu_read_lock();
+			err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags);
+			rcu_read_unlock();
+			bpf_enable_instrumentation();
+		}
 	}
 
 	if (err)
@@ -1932,6 +1973,11 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr)
 			attr->expected_attach_type =
 				BPF_CGROUP_INET_SOCK_CREATE;
 		break;
+	case BPF_PROG_TYPE_SK_REUSEPORT:
+		if (!attr->expected_attach_type)
+			attr->expected_attach_type =
+				BPF_SK_REUSEPORT_SELECT;
+		break;
 	}
 }
 
@@ -2015,6 +2061,15 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 		if (expected_attach_type == BPF_SK_LOOKUP)
 			return 0;
 		return -EINVAL;
+	case BPF_PROG_TYPE_SK_REUSEPORT:
+		switch (expected_attach_type) {
+		case BPF_SK_REUSEPORT_SELECT:
+		case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE:
+			return 0;
+		default:
+			return -EINVAL;
+		}
+	case BPF_PROG_TYPE_SYSCALL:
 	case BPF_PROG_TYPE_EXT:
 		if (expected_attach_type)
 			return -EINVAL;
@@ -2074,9 +2129,9 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD attach_prog_fd
+#define	BPF_PROG_LOAD_LAST_FIELD fd_array
 
-static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
+static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 {
 	enum bpf_prog_type type = attr->prog_type;
 	struct bpf_prog *prog, *dst_prog = NULL;
@@ -2101,8 +2156,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 		return -EPERM;
 
 	/* copy eBPF program license from user space */
-	if (strncpy_from_user(license, u64_to_user_ptr(attr->license),
-			      sizeof(license) - 1) < 0)
+	if (strncpy_from_bpfptr(license,
+				make_bpfptr(attr->license, uattr.is_kernel),
+				sizeof(license) - 1) < 0)
 		return -EFAULT;
 	license[sizeof(license) - 1] = 0;
 
@@ -2186,8 +2242,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	prog->len = attr->insn_cnt;
 
 	err = -EFAULT;
-	if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns),
-			   bpf_prog_insn_size(prog)) != 0)
+	if (copy_from_bpfptr(prog->insns,
+			     make_bpfptr(attr->insns, uattr.is_kernel),
+			     bpf_prog_insn_size(prog)) != 0)
 		goto free_prog_sec;
 
 	prog->orig_prog = NULL;
@@ -3423,7 +3480,7 @@ static int bpf_prog_get_info_by_fd(struct file *file,
 	u32 ulen;
 	int err;
 
-	err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+	err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len);
 	if (err)
 		return err;
 	info_len = min_t(u32, sizeof(info), info_len);
@@ -3702,7 +3759,7 @@ static int bpf_map_get_info_by_fd(struct file *file,
 	u32 info_len = attr->info.info_len;
 	int err;
 
-	err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+	err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len);
 	if (err)
 		return err;
 	info_len = min_t(u32, sizeof(info), info_len);
@@ -3745,7 +3802,7 @@ static int bpf_btf_get_info_by_fd(struct file *file,
 	u32 info_len = attr->info.info_len;
 	int err;
 
-	err = bpf_check_uarg_tail_zero(uinfo, sizeof(*uinfo), info_len);
+	err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len);
 	if (err)
 		return err;
 
@@ -3762,7 +3819,7 @@ static int bpf_link_get_info_by_fd(struct file *file,
 	u32 info_len = attr->info.info_len;
 	int err;
 
-	err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+	err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len);
 	if (err)
 		return err;
 	info_len = min_t(u32, sizeof(info), info_len);
@@ -3825,7 +3882,7 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 
 #define BPF_BTF_LOAD_LAST_FIELD btf_log_level
 
-static int bpf_btf_load(const union bpf_attr *attr)
+static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr)
 {
 	if (CHECK_ATTR(BPF_BTF_LOAD))
 		return -EINVAL;
@@ -3833,7 +3890,7 @@ static int bpf_btf_load(const union bpf_attr *attr)
 	if (!bpf_capable())
 		return -EPERM;
 
-	return btf_new_fd(attr);
+	return btf_new_fd(attr, uattr);
 }
 
 #define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id
@@ -4023,13 +4080,14 @@ err_put:
 	return err;
 }
 
-static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+static int tracing_bpf_link_attach(const union bpf_attr *attr, bpfptr_t uattr,
+				   struct bpf_prog *prog)
 {
 	if (attr->link_create.attach_type != prog->expected_attach_type)
 		return -EINVAL;
 
 	if (prog->expected_attach_type == BPF_TRACE_ITER)
-		return bpf_iter_link_attach(attr, prog);
+		return bpf_iter_link_attach(attr, uattr, prog);
 	else if (prog->type == BPF_PROG_TYPE_EXT)
 		return bpf_tracing_prog_attach(prog,
 					       attr->link_create.target_fd,
@@ -4038,7 +4096,7 @@ static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *
 }
 
 #define BPF_LINK_CREATE_LAST_FIELD link_create.iter_info_len
-static int link_create(union bpf_attr *attr)
+static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 {
 	enum bpf_prog_type ptype;
 	struct bpf_prog *prog;
@@ -4057,7 +4115,7 @@ static int link_create(union bpf_attr *attr)
 		goto out;
 
 	if (prog->type == BPF_PROG_TYPE_EXT) {
-		ret = tracing_bpf_link_attach(attr, prog);
+		ret = tracing_bpf_link_attach(attr, uattr, prog);
 		goto out;
 	}
 
@@ -4078,7 +4136,7 @@ static int link_create(union bpf_attr *attr)
 		ret = cgroup_bpf_link_attach(attr, prog);
 		break;
 	case BPF_PROG_TYPE_TRACING:
-		ret = tracing_bpf_link_attach(attr, prog);
+		ret = tracing_bpf_link_attach(attr, uattr, prog);
 		break;
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 	case BPF_PROG_TYPE_SK_LOOKUP:
@@ -4366,7 +4424,7 @@ out_prog_put:
 	return ret;
 }
 
-SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
+static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size)
 {
 	union bpf_attr attr;
 	int err;
@@ -4381,7 +4439,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 
 	/* copy attributes from user space, may be less than sizeof(bpf_attr) */
 	memset(&attr, 0, sizeof(attr));
-	if (copy_from_user(&attr, uattr, size) != 0)
+	if (copy_from_bpfptr(&attr, uattr, size) != 0)
 		return -EFAULT;
 
 	err = security_bpf(cmd, &attr, size);
@@ -4396,7 +4454,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 		err = map_lookup_elem(&attr);
 		break;
 	case BPF_MAP_UPDATE_ELEM:
-		err = map_update_elem(&attr);
+		err = map_update_elem(&attr, uattr);
 		break;
 	case BPF_MAP_DELETE_ELEM:
 		err = map_delete_elem(&attr);
@@ -4423,21 +4481,21 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 		err = bpf_prog_detach(&attr);
 		break;
 	case BPF_PROG_QUERY:
-		err = bpf_prog_query(&attr, uattr);
+		err = bpf_prog_query(&attr, uattr.user);
 		break;
 	case BPF_PROG_TEST_RUN:
-		err = bpf_prog_test_run(&attr, uattr);
+		err = bpf_prog_test_run(&attr, uattr.user);
 		break;
 	case BPF_PROG_GET_NEXT_ID:
-		err = bpf_obj_get_next_id(&attr, uattr,
+		err = bpf_obj_get_next_id(&attr, uattr.user,
 					  &prog_idr, &prog_idr_lock);
 		break;
 	case BPF_MAP_GET_NEXT_ID:
-		err = bpf_obj_get_next_id(&attr, uattr,
+		err = bpf_obj_get_next_id(&attr, uattr.user,
 					  &map_idr, &map_idr_lock);
 		break;
 	case BPF_BTF_GET_NEXT_ID:
-		err = bpf_obj_get_next_id(&attr, uattr,
+		err = bpf_obj_get_next_id(&attr, uattr.user,
 					  &btf_idr, &btf_idr_lock);
 		break;
 	case BPF_PROG_GET_FD_BY_ID:
@@ -4447,38 +4505,38 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 		err = bpf_map_get_fd_by_id(&attr);
 		break;
 	case BPF_OBJ_GET_INFO_BY_FD:
-		err = bpf_obj_get_info_by_fd(&attr, uattr);
+		err = bpf_obj_get_info_by_fd(&attr, uattr.user);
 		break;
 	case BPF_RAW_TRACEPOINT_OPEN:
 		err = bpf_raw_tracepoint_open(&attr);
 		break;
 	case BPF_BTF_LOAD:
-		err = bpf_btf_load(&attr);
+		err = bpf_btf_load(&attr, uattr);
 		break;
 	case BPF_BTF_GET_FD_BY_ID:
 		err = bpf_btf_get_fd_by_id(&attr);
 		break;
 	case BPF_TASK_FD_QUERY:
-		err = bpf_task_fd_query(&attr, uattr);
+		err = bpf_task_fd_query(&attr, uattr.user);
 		break;
 	case BPF_MAP_LOOKUP_AND_DELETE_ELEM:
 		err = map_lookup_and_delete_elem(&attr);
 		break;
 	case BPF_MAP_LOOKUP_BATCH:
-		err = bpf_map_do_batch(&attr, uattr, BPF_MAP_LOOKUP_BATCH);
+		err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_BATCH);
 		break;
 	case BPF_MAP_LOOKUP_AND_DELETE_BATCH:
-		err = bpf_map_do_batch(&attr, uattr,
+		err = bpf_map_do_batch(&attr, uattr.user,
 				       BPF_MAP_LOOKUP_AND_DELETE_BATCH);
 		break;
 	case BPF_MAP_UPDATE_BATCH:
-		err = bpf_map_do_batch(&attr, uattr, BPF_MAP_UPDATE_BATCH);
+		err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_UPDATE_BATCH);
 		break;
 	case BPF_MAP_DELETE_BATCH:
-		err = bpf_map_do_batch(&attr, uattr, BPF_MAP_DELETE_BATCH);
+		err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_DELETE_BATCH);
 		break;
 	case BPF_LINK_CREATE:
-		err = link_create(&attr);
+		err = link_create(&attr, uattr);
 		break;
 	case BPF_LINK_UPDATE:
 		err = link_update(&attr);
@@ -4487,7 +4545,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 		err = bpf_link_get_fd_by_id(&attr);
 		break;
 	case BPF_LINK_GET_NEXT_ID:
-		err = bpf_obj_get_next_id(&attr, uattr,
+		err = bpf_obj_get_next_id(&attr, uattr.user,
 					  &link_idr, &link_idr_lock);
 		break;
 	case BPF_ENABLE_STATS:
@@ -4509,3 +4567,94 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 
 	return err;
 }
+
+SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
+{
+	return __sys_bpf(cmd, USER_BPFPTR(uattr), size);
+}
+
+static bool syscall_prog_is_valid_access(int off, int size,
+					 enum bpf_access_type type,
+					 const struct bpf_prog *prog,
+					 struct bpf_insn_access_aux *info)
+{
+	if (off < 0 || off >= U16_MAX)
+		return false;
+	if (off % size != 0)
+		return false;
+	return true;
+}
+
+BPF_CALL_3(bpf_sys_bpf, int, cmd, void *, attr, u32, attr_size)
+{
+	switch (cmd) {
+	case BPF_MAP_CREATE:
+	case BPF_MAP_UPDATE_ELEM:
+	case BPF_MAP_FREEZE:
+	case BPF_PROG_LOAD:
+	case BPF_BTF_LOAD:
+		break;
+	/* case BPF_PROG_TEST_RUN:
+	 * is not part of this list to prevent recursive test_run
+	 */
+	default:
+		return -EINVAL;
+	}
+	return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size);
+}
+
+static const struct bpf_func_proto bpf_sys_bpf_proto = {
+	.func		= bpf_sys_bpf,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+};
+
+const struct bpf_func_proto * __weak
+tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	return bpf_base_func_proto(func_id);
+}
+
+BPF_CALL_1(bpf_sys_close, u32, fd)
+{
+	/* When bpf program calls this helper there should not be
+	 * an fdget() without matching completed fdput().
+	 * This helper is allowed in the following callchain only:
+	 * sys_bpf->prog_test_run->bpf_prog->bpf_sys_close
+	 */
+	return close_fd(fd);
+}
+
+static const struct bpf_func_proto bpf_sys_close_proto = {
+	.func		= bpf_sys_close,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *
+syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	switch (func_id) {
+	case BPF_FUNC_sys_bpf:
+		return &bpf_sys_bpf_proto;
+	case BPF_FUNC_btf_find_by_name_kind:
+		return &bpf_btf_find_by_name_kind_proto;
+	case BPF_FUNC_sys_close:
+		return &bpf_sys_close_proto;
+	default:
+		return tracing_prog_func_proto(func_id, prog);
+	}
+}
+
+const struct bpf_verifier_ops bpf_syscall_verifier_ops = {
+	.get_func_proto  = syscall_prog_func_proto,
+	.is_valid_access = syscall_prog_is_valid_access,
+};
+
+const struct bpf_prog_ops bpf_syscall_prog_ops = {
+	.test_run = bpf_prog_test_run_syscall,
+};
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index ceac5281bd31..3d7127f439a1 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -111,28 +111,31 @@ struct tnum tnum_xor(struct tnum a, struct tnum b)
 	return TNUM(v & ~mu, mu);
 }
 
-/* half-multiply add: acc += (unknown * mask * value).
- * An intermediate step in the multiply algorithm.
+/* Generate partial products by multiplying each bit in the multiplier (tnum a)
+ * with the multiplicand (tnum b), and add the partial products after
+ * appropriately bit-shifting them. Instead of directly performing tnum addition
+ * on the generated partial products, equivalenty, decompose each partial
+ * product into two tnums, consisting of the value-sum (acc_v) and the
+ * mask-sum (acc_m) and then perform tnum addition on them. The following paper
+ * explains the algorithm in more detail: https://arxiv.org/abs/2105.05398.
  */
-static struct tnum hma(struct tnum acc, u64 value, u64 mask)
-{
-	while (mask) {
-		if (mask & 1)
-			acc = tnum_add(acc, TNUM(0, value));
-		mask >>= 1;
-		value <<= 1;
-	}
-	return acc;
-}
-
 struct tnum tnum_mul(struct tnum a, struct tnum b)
 {
-	struct tnum acc;
-	u64 pi;
-
-	pi = a.value * b.value;
-	acc = hma(TNUM(pi, 0), a.mask, b.mask | b.value);
-	return hma(acc, b.mask, a.value);
+	u64 acc_v = a.value * b.value;
+	struct tnum acc_m = TNUM(0, 0);
+
+	while (a.value || a.mask) {
+		/* LSB of tnum a is a certain 1 */
+		if (a.value & 1)
+			acc_m = tnum_add(acc_m, TNUM(0, b.mask));
+		/* LSB of tnum a is uncertain */
+		else if (a.mask & 1)
+			acc_m = tnum_add(acc_m, TNUM(0, b.value | b.mask));
+		/* Note: no case for LSB is certain 0 */
+		a = tnum_rshift(a, 1);
+		b = tnum_lshift(b, 1);
+	}
+	return tnum_add(TNUM(acc_v, 0), acc_m);
 }
 
 /* Note that if a and b disagree - i.e. one has a 'known 1' where the other has
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 2d44b5aa0057..28a3630c48ee 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -552,7 +552,7 @@ static void notrace inc_misses_counter(struct bpf_prog *prog)
  * __bpf_prog_enter returns:
  * 0 - skip execution of the bpf prog
  * 1 - execute bpf prog
- * [2..MAX_U64] - excute bpf prog and record execution time.
+ * [2..MAX_U64] - execute bpf prog and record execution time.
  *     This is start time.
  */
 u64 notrace __bpf_prog_enter(struct bpf_prog *prog)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c6a27574242d..e04e33893cff 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -47,7 +47,7 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
  * - unreachable insns exist (shouldn't be a forest. program = one function)
  * - out of bounds or malformed jumps
  * The second pass is all possible path descent from the 1st insn.
- * Since it's analyzing all pathes through the program, the length of the
+ * Since it's analyzing all paths through the program, the length of the
  * analysis is limited to 64k insn, which may be hit even if total number of
  * insn is less then 4K, but there are too many branches that change stack/regs.
  * Number of 'branches to be analyzed' is limited to 1k
@@ -132,7 +132,7 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
  * If it's ok, then verifier allows this BPF_CALL insn and looks at
  * .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets
  * R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function
- * returns ether pointer to map value or NULL.
+ * returns either pointer to map value or NULL.
  *
  * When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off'
  * insn, the register holding that pointer in the true branch changes state to
@@ -737,81 +737,104 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 	verbose(env, "\n");
 }
 
-#define COPY_STATE_FN(NAME, COUNT, FIELD, SIZE)				\
-static int copy_##NAME##_state(struct bpf_func_state *dst,		\
-			       const struct bpf_func_state *src)	\
-{									\
-	if (!src->FIELD)						\
-		return 0;						\
-	if (WARN_ON_ONCE(dst->COUNT < src->COUNT)) {			\
-		/* internal bug, make state invalid to reject the program */ \
-		memset(dst, 0, sizeof(*dst));				\
-		return -EFAULT;						\
-	}								\
-	memcpy(dst->FIELD, src->FIELD,					\
-	       sizeof(*src->FIELD) * (src->COUNT / SIZE));		\
-	return 0;							\
-}
-/* copy_reference_state() */
-COPY_STATE_FN(reference, acquired_refs, refs, 1)
-/* copy_stack_state() */
-COPY_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE)
-#undef COPY_STATE_FN
-
-#define REALLOC_STATE_FN(NAME, COUNT, FIELD, SIZE)			\
-static int realloc_##NAME##_state(struct bpf_func_state *state, int size, \
-				  bool copy_old)			\
-{									\
-	u32 old_size = state->COUNT;					\
-	struct bpf_##NAME##_state *new_##FIELD;				\
-	int slot = size / SIZE;						\
-									\
-	if (size <= old_size || !size) {				\
-		if (copy_old)						\
-			return 0;					\
-		state->COUNT = slot * SIZE;				\
-		if (!size && old_size) {				\
-			kfree(state->FIELD);				\
-			state->FIELD = NULL;				\
-		}							\
-		return 0;						\
-	}								\
-	new_##FIELD = kmalloc_array(slot, sizeof(struct bpf_##NAME##_state), \
-				    GFP_KERNEL);			\
-	if (!new_##FIELD)						\
-		return -ENOMEM;						\
-	if (copy_old) {							\
-		if (state->FIELD)					\
-			memcpy(new_##FIELD, state->FIELD,		\
-			       sizeof(*new_##FIELD) * (old_size / SIZE)); \
-		memset(new_##FIELD + old_size / SIZE, 0,		\
-		       sizeof(*new_##FIELD) * (size - old_size) / SIZE); \
-	}								\
-	state->COUNT = slot * SIZE;					\
-	kfree(state->FIELD);						\
-	state->FIELD = new_##FIELD;					\
-	return 0;							\
-}
-/* realloc_reference_state() */
-REALLOC_STATE_FN(reference, acquired_refs, refs, 1)
-/* realloc_stack_state() */
-REALLOC_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE)
-#undef REALLOC_STATE_FN
-
-/* do_check() starts with zero-sized stack in struct bpf_verifier_state to
- * make it consume minimal amount of memory. check_stack_write() access from
- * the program calls into realloc_func_state() to grow the stack size.
- * Note there is a non-zero 'parent' pointer inside bpf_verifier_state
- * which realloc_stack_state() copies over. It points to previous
- * bpf_verifier_state which is never reallocated.
+/* copy array src of length n * size bytes to dst. dst is reallocated if it's too
+ * small to hold src. This is different from krealloc since we don't want to preserve
+ * the contents of dst.
+ *
+ * Leaves dst untouched if src is NULL or length is zero. Returns NULL if memory could
+ * not be allocated.
  */
-static int realloc_func_state(struct bpf_func_state *state, int stack_size,
-			      int refs_size, bool copy_old)
+static void *copy_array(void *dst, const void *src, size_t n, size_t size, gfp_t flags)
 {
-	int err = realloc_reference_state(state, refs_size, copy_old);
-	if (err)
-		return err;
-	return realloc_stack_state(state, stack_size, copy_old);
+	size_t bytes;
+
+	if (ZERO_OR_NULL_PTR(src))
+		goto out;
+
+	if (unlikely(check_mul_overflow(n, size, &bytes)))
+		return NULL;
+
+	if (ksize(dst) < bytes) {
+		kfree(dst);
+		dst = kmalloc_track_caller(bytes, flags);
+		if (!dst)
+			return NULL;
+	}
+
+	memcpy(dst, src, bytes);
+out:
+	return dst ? dst : ZERO_SIZE_PTR;
+}
+
+/* resize an array from old_n items to new_n items. the array is reallocated if it's too
+ * small to hold new_n items. new items are zeroed out if the array grows.
+ *
+ * Contrary to krealloc_array, does not free arr if new_n is zero.
+ */
+static void *realloc_array(void *arr, size_t old_n, size_t new_n, size_t size)
+{
+	if (!new_n || old_n == new_n)
+		goto out;
+
+	arr = krealloc_array(arr, new_n, size, GFP_KERNEL);
+	if (!arr)
+		return NULL;
+
+	if (new_n > old_n)
+		memset(arr + old_n * size, 0, (new_n - old_n) * size);
+
+out:
+	return arr ? arr : ZERO_SIZE_PTR;
+}
+
+static int copy_reference_state(struct bpf_func_state *dst, const struct bpf_func_state *src)
+{
+	dst->refs = copy_array(dst->refs, src->refs, src->acquired_refs,
+			       sizeof(struct bpf_reference_state), GFP_KERNEL);
+	if (!dst->refs)
+		return -ENOMEM;
+
+	dst->acquired_refs = src->acquired_refs;
+	return 0;
+}
+
+static int copy_stack_state(struct bpf_func_state *dst, const struct bpf_func_state *src)
+{
+	size_t n = src->allocated_stack / BPF_REG_SIZE;
+
+	dst->stack = copy_array(dst->stack, src->stack, n, sizeof(struct bpf_stack_state),
+				GFP_KERNEL);
+	if (!dst->stack)
+		return -ENOMEM;
+
+	dst->allocated_stack = src->allocated_stack;
+	return 0;
+}
+
+static int resize_reference_state(struct bpf_func_state *state, size_t n)
+{
+	state->refs = realloc_array(state->refs, state->acquired_refs, n,
+				    sizeof(struct bpf_reference_state));
+	if (!state->refs)
+		return -ENOMEM;
+
+	state->acquired_refs = n;
+	return 0;
+}
+
+static int grow_stack_state(struct bpf_func_state *state, int size)
+{
+	size_t old_n = state->allocated_stack / BPF_REG_SIZE, n = size / BPF_REG_SIZE;
+
+	if (old_n >= n)
+		return 0;
+
+	state->stack = realloc_array(state->stack, old_n, n, sizeof(struct bpf_stack_state));
+	if (!state->stack)
+		return -ENOMEM;
+
+	state->allocated_stack = size;
+	return 0;
 }
 
 /* Acquire a pointer id from the env and update the state->refs to include
@@ -825,7 +848,7 @@ static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx)
 	int new_ofs = state->acquired_refs;
 	int id, err;
 
-	err = realloc_reference_state(state, state->acquired_refs + 1, true);
+	err = resize_reference_state(state, state->acquired_refs + 1);
 	if (err)
 		return err;
 	id = ++env->id_gen;
@@ -854,18 +877,6 @@ static int release_reference_state(struct bpf_func_state *state, int ptr_id)
 	return -EINVAL;
 }
 
-static int transfer_reference_state(struct bpf_func_state *dst,
-				    struct bpf_func_state *src)
-{
-	int err = realloc_reference_state(dst, src->acquired_refs, false);
-	if (err)
-		return err;
-	err = copy_reference_state(dst, src);
-	if (err)
-		return err;
-	return 0;
-}
-
 static void free_func_state(struct bpf_func_state *state)
 {
 	if (!state)
@@ -904,10 +915,6 @@ static int copy_func_state(struct bpf_func_state *dst,
 {
 	int err;
 
-	err = realloc_func_state(dst, src->allocated_stack, src->acquired_refs,
-				 false);
-	if (err)
-		return err;
 	memcpy(dst, src, offsetof(struct bpf_func_state, acquired_refs));
 	err = copy_reference_state(dst, src);
 	if (err)
@@ -919,16 +926,13 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
 			       const struct bpf_verifier_state *src)
 {
 	struct bpf_func_state *dst;
-	u32 jmp_sz = sizeof(struct bpf_idx_pair) * src->jmp_history_cnt;
 	int i, err;
 
-	if (dst_state->jmp_history_cnt < src->jmp_history_cnt) {
-		kfree(dst_state->jmp_history);
-		dst_state->jmp_history = kmalloc(jmp_sz, GFP_USER);
-		if (!dst_state->jmp_history)
-			return -ENOMEM;
-	}
-	memcpy(dst_state->jmp_history, src->jmp_history, jmp_sz);
+	dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history,
+					    src->jmp_history_cnt, sizeof(struct bpf_idx_pair),
+					    GFP_USER);
+	if (!dst_state->jmp_history)
+		return -ENOMEM;
 	dst_state->jmp_history_cnt = src->jmp_history_cnt;
 
 	/* if dst has more stack frames then src frame, free them */
@@ -2590,8 +2594,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 	u32 dst_reg = env->prog->insnsi[insn_idx].dst_reg;
 	struct bpf_reg_state *reg = NULL;
 
-	err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE),
-				 state->acquired_refs, true);
+	err = grow_stack_state(state, round_up(slot + 1, BPF_REG_SIZE));
 	if (err)
 		return err;
 	/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
@@ -2613,7 +2616,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 		if (dst_reg != BPF_REG_FP) {
 			/* The backtracking logic can only recognize explicit
 			 * stack slot address like [fp - 8]. Other spill of
-			 * scalar via different register has to be conervative.
+			 * scalar via different register has to be conservative.
 			 * Backtrack from here and mark all registers as precise
 			 * that contributed into 'reg' being a constant.
 			 */
@@ -2753,8 +2756,7 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env,
 	if (value_reg && register_is_null(value_reg))
 		writing_zero = true;
 
-	err = realloc_func_state(state, round_up(-min_off, BPF_REG_SIZE),
-				 state->acquired_refs, true);
+	err = grow_stack_state(state, round_up(-min_off, BPF_REG_SIZE));
 	if (err)
 		return err;
 
@@ -5629,7 +5631,7 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 			subprog /* subprog number within this prog */);
 
 	/* Transfer references to the callee */
-	err = transfer_reference_state(callee, caller);
+	err = copy_reference_state(callee, caller);
 	if (err)
 		return err;
 
@@ -5780,7 +5782,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 	}
 
 	/* Transfer references to the caller */
-	err = transfer_reference_state(caller, callee);
+	err = copy_reference_state(caller, callee);
 	if (err)
 		return err;
 
@@ -8968,12 +8970,14 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	mark_reg_known_zero(env, regs, insn->dst_reg);
 	dst_reg->map_ptr = map;
 
-	if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) {
+	if (insn->src_reg == BPF_PSEUDO_MAP_VALUE ||
+	    insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) {
 		dst_reg->type = PTR_TO_MAP_VALUE;
 		dst_reg->off = aux->map_off;
 		if (map_value_has_spin_lock(map))
 			dst_reg->id = ++env->id_gen;
-	} else if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
+	} else if (insn->src_reg == BPF_PSEUDO_MAP_FD ||
+		   insn->src_reg == BPF_PSEUDO_MAP_IDX) {
 		dst_reg->type = CONST_PTR_TO_MAP;
 	} else {
 		verbose(env, "bpf verifier is misconfigured\n");
@@ -9104,7 +9108,7 @@ static int check_return_code(struct bpf_verifier_env *env)
 	    !prog->aux->attach_func_proto->type)
 		return 0;
 
-	/* eBPF calling convetion is such that R0 is used
+	/* eBPF calling convention is such that R0 is used
 	 * to return the value from eBPF program.
 	 * Make sure that it's readable at this time
 	 * of bpf_exit, which means that program wrote
@@ -9489,7 +9493,7 @@ static int check_abnormal_return(struct bpf_verifier_env *env)
 
 static int check_btf_func(struct bpf_verifier_env *env,
 			  const union bpf_attr *attr,
-			  union bpf_attr __user *uattr)
+			  bpfptr_t uattr)
 {
 	const struct btf_type *type, *func_proto, *ret_type;
 	u32 i, nfuncs, urec_size, min_size;
@@ -9498,7 +9502,7 @@ static int check_btf_func(struct bpf_verifier_env *env,
 	struct bpf_func_info_aux *info_aux = NULL;
 	struct bpf_prog *prog;
 	const struct btf *btf;
-	void __user *urecord;
+	bpfptr_t urecord;
 	u32 prev_offset = 0;
 	bool scalar_return;
 	int ret = -ENOMEM;
@@ -9526,7 +9530,7 @@ static int check_btf_func(struct bpf_verifier_env *env,
 	prog = env->prog;
 	btf = prog->aux->btf;
 
-	urecord = u64_to_user_ptr(attr->func_info);
+	urecord = make_bpfptr(attr->func_info, uattr.is_kernel);
 	min_size = min_t(u32, krec_size, urec_size);
 
 	krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN);
@@ -9544,13 +9548,15 @@ static int check_btf_func(struct bpf_verifier_env *env,
 				/* set the size kernel expects so loader can zero
 				 * out the rest of the record.
 				 */
-				if (put_user(min_size, &uattr->func_info_rec_size))
+				if (copy_to_bpfptr_offset(uattr,
+							  offsetof(union bpf_attr, func_info_rec_size),
+							  &min_size, sizeof(min_size)))
 					ret = -EFAULT;
 			}
 			goto err_free;
 		}
 
-		if (copy_from_user(&krecord[i], urecord, min_size)) {
+		if (copy_from_bpfptr(&krecord[i], urecord, min_size)) {
 			ret = -EFAULT;
 			goto err_free;
 		}
@@ -9602,7 +9608,7 @@ static int check_btf_func(struct bpf_verifier_env *env,
 		}
 
 		prev_offset = krecord[i].insn_off;
-		urecord += urec_size;
+		bpfptr_add(&urecord, urec_size);
 	}
 
 	prog->aux->func_info = krecord;
@@ -9634,14 +9640,14 @@ static void adjust_btf_func(struct bpf_verifier_env *env)
 
 static int check_btf_line(struct bpf_verifier_env *env,
 			  const union bpf_attr *attr,
-			  union bpf_attr __user *uattr)
+			  bpfptr_t uattr)
 {
 	u32 i, s, nr_linfo, ncopy, expected_size, rec_size, prev_offset = 0;
 	struct bpf_subprog_info *sub;
 	struct bpf_line_info *linfo;
 	struct bpf_prog *prog;
 	const struct btf *btf;
-	void __user *ulinfo;
+	bpfptr_t ulinfo;
 	int err;
 
 	nr_linfo = attr->line_info_cnt;
@@ -9667,7 +9673,7 @@ static int check_btf_line(struct bpf_verifier_env *env,
 
 	s = 0;
 	sub = env->subprog_info;
-	ulinfo = u64_to_user_ptr(attr->line_info);
+	ulinfo = make_bpfptr(attr->line_info, uattr.is_kernel);
 	expected_size = sizeof(struct bpf_line_info);
 	ncopy = min_t(u32, expected_size, rec_size);
 	for (i = 0; i < nr_linfo; i++) {
@@ -9675,14 +9681,15 @@ static int check_btf_line(struct bpf_verifier_env *env,
 		if (err) {
 			if (err == -E2BIG) {
 				verbose(env, "nonzero tailing record in line_info");
-				if (put_user(expected_size,
-					     &uattr->line_info_rec_size))
+				if (copy_to_bpfptr_offset(uattr,
+							  offsetof(union bpf_attr, line_info_rec_size),
+							  &expected_size, sizeof(expected_size)))
 					err = -EFAULT;
 			}
 			goto err_free;
 		}
 
-		if (copy_from_user(&linfo[i], ulinfo, ncopy)) {
+		if (copy_from_bpfptr(&linfo[i], ulinfo, ncopy)) {
 			err = -EFAULT;
 			goto err_free;
 		}
@@ -9734,7 +9741,7 @@ static int check_btf_line(struct bpf_verifier_env *env,
 		}
 
 		prev_offset = linfo[i].insn_off;
-		ulinfo += rec_size;
+		bpfptr_add(&ulinfo, rec_size);
 	}
 
 	if (s != env->subprog_cnt) {
@@ -9756,7 +9763,7 @@ err_free:
 
 static int check_btf_info(struct bpf_verifier_env *env,
 			  const union bpf_attr *attr,
-			  union bpf_attr __user *uattr)
+			  bpfptr_t uattr)
 {
 	struct btf *btf;
 	int err;
@@ -9801,13 +9808,6 @@ static bool range_within(struct bpf_reg_state *old,
 	       old->s32_max_value >= cur->s32_max_value;
 }
 
-/* Maximum number of register states that can exist at once */
-#define ID_MAP_SIZE	(MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE)
-struct idpair {
-	u32 old;
-	u32 cur;
-};
-
 /* If in the old state two registers had the same id, then they need to have
  * the same id in the new state as well.  But that id could be different from
  * the old state, so we need to track the mapping from old to new ids.
@@ -9818,11 +9818,11 @@ struct idpair {
  * So we look through our idmap to see if this old id has been seen before.  If
  * so, we require the new id to match; otherwise, we add the id pair to the map.
  */
-static bool check_ids(u32 old_id, u32 cur_id, struct idpair *idmap)
+static bool check_ids(u32 old_id, u32 cur_id, struct bpf_id_pair *idmap)
 {
 	unsigned int i;
 
-	for (i = 0; i < ID_MAP_SIZE; i++) {
+	for (i = 0; i < BPF_ID_MAP_SIZE; i++) {
 		if (!idmap[i].old) {
 			/* Reached an empty slot; haven't seen this id before */
 			idmap[i].old = old_id;
@@ -9899,7 +9899,7 @@ static void clean_verifier_state(struct bpf_verifier_env *env,
  * Since the verifier pushes the branch states as it sees them while exploring
  * the program the condition of walking the branch instruction for the second
  * time means that all states below this branch were already explored and
- * their final liveness markes are already propagated.
+ * their final liveness marks are already propagated.
  * Hence when the verifier completes the search of state list in is_state_visited()
  * we can call this clean_live_states() function to mark all liveness states
  * as REG_LIVE_DONE to indicate that 'parent' pointers of 'struct bpf_reg_state'
@@ -9935,7 +9935,7 @@ next:
 
 /* Returns true if (rold safe implies rcur safe) */
 static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
-		    struct idpair *idmap)
+		    struct bpf_id_pair *idmap)
 {
 	bool equal;
 
@@ -10053,7 +10053,7 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
 
 static bool stacksafe(struct bpf_func_state *old,
 		      struct bpf_func_state *cur,
-		      struct idpair *idmap)
+		      struct bpf_id_pair *idmap)
 {
 	int i, spi;
 
@@ -10150,32 +10150,23 @@ static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur)
  * whereas register type in current state is meaningful, it means that
  * the current state will reach 'bpf_exit' instruction safely
  */
-static bool func_states_equal(struct bpf_func_state *old,
+static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_state *old,
 			      struct bpf_func_state *cur)
 {
-	struct idpair *idmap;
-	bool ret = false;
 	int i;
 
-	idmap = kcalloc(ID_MAP_SIZE, sizeof(struct idpair), GFP_KERNEL);
-	/* If we failed to allocate the idmap, just say it's not safe */
-	if (!idmap)
-		return false;
-
-	for (i = 0; i < MAX_BPF_REG; i++) {
-		if (!regsafe(&old->regs[i], &cur->regs[i], idmap))
-			goto out_free;
-	}
+	memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch));
+	for (i = 0; i < MAX_BPF_REG; i++)
+		if (!regsafe(&old->regs[i], &cur->regs[i], env->idmap_scratch))
+			return false;
 
-	if (!stacksafe(old, cur, idmap))
-		goto out_free;
+	if (!stacksafe(old, cur, env->idmap_scratch))
+		return false;
 
 	if (!refsafe(old, cur))
-		goto out_free;
-	ret = true;
-out_free:
-	kfree(idmap);
-	return ret;
+		return false;
+
+	return true;
 }
 
 static bool states_equal(struct bpf_verifier_env *env,
@@ -10202,7 +10193,7 @@ static bool states_equal(struct bpf_verifier_env *env,
 	for (i = 0; i <= old->curframe; i++) {
 		if (old->frame[i]->callsite != cur->frame[i]->callsite)
 			return false;
-		if (!func_states_equal(old->frame[i], cur->frame[i]))
+		if (!func_states_equal(env, old->frame[i], cur->frame[i]))
 			return false;
 	}
 	return true;
@@ -11239,6 +11230,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
 			struct bpf_map *map;
 			struct fd f;
 			u64 addr;
+			u32 fd;
 
 			if (i == insn_cnt - 1 || insn[1].code != 0 ||
 			    insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
@@ -11268,16 +11260,38 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
 			/* In final convert_pseudo_ld_imm64() step, this is
 			 * converted into regular 64-bit imm load insn.
 			 */
-			if ((insn[0].src_reg != BPF_PSEUDO_MAP_FD &&
-			     insn[0].src_reg != BPF_PSEUDO_MAP_VALUE) ||
-			    (insn[0].src_reg == BPF_PSEUDO_MAP_FD &&
-			     insn[1].imm != 0)) {
-				verbose(env,
-					"unrecognized bpf_ld_imm64 insn\n");
+			switch (insn[0].src_reg) {
+			case BPF_PSEUDO_MAP_VALUE:
+			case BPF_PSEUDO_MAP_IDX_VALUE:
+				break;
+			case BPF_PSEUDO_MAP_FD:
+			case BPF_PSEUDO_MAP_IDX:
+				if (insn[1].imm == 0)
+					break;
+				fallthrough;
+			default:
+				verbose(env, "unrecognized bpf_ld_imm64 insn\n");
 				return -EINVAL;
 			}
 
-			f = fdget(insn[0].imm);
+			switch (insn[0].src_reg) {
+			case BPF_PSEUDO_MAP_IDX_VALUE:
+			case BPF_PSEUDO_MAP_IDX:
+				if (bpfptr_is_null(env->fd_array)) {
+					verbose(env, "fd_idx without fd_array is invalid\n");
+					return -EPROTO;
+				}
+				if (copy_from_bpfptr_offset(&fd, env->fd_array,
+							    insn[0].imm * sizeof(fd),
+							    sizeof(fd)))
+					return -EFAULT;
+				break;
+			default:
+				fd = insn[0].imm;
+				break;
+			}
+
+			f = fdget(fd);
 			map = __bpf_map_get(f);
 			if (IS_ERR(map)) {
 				verbose(env, "fd %d is not pointing to valid bpf_map\n",
@@ -11292,7 +11306,8 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
 			}
 
 			aux = &env->insn_aux_data[i];
-			if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
+			if (insn[0].src_reg == BPF_PSEUDO_MAP_FD ||
+			    insn[0].src_reg == BPF_PSEUDO_MAP_IDX) {
 				addr = (unsigned long)map;
 			} else {
 				u32 off = insn[1].imm;
@@ -12506,7 +12521,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 			prog->aux->max_pkt_offset = MAX_PACKET_OFF;
 
 			/* mark bpf_tail_call as different opcode to avoid
-			 * conditional branch in the interpeter for every normal
+			 * conditional branch in the interpreter for every normal
 			 * call and to prevent accidental JITing by JIT compiler
 			 * that doesn't support bpf_tail_call yet
 			 */
@@ -13281,6 +13296,14 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	int ret;
 	u64 key;
 
+	if (prog->type == BPF_PROG_TYPE_SYSCALL) {
+		if (prog->aux->sleepable)
+			/* attach_btf_id checked to be zero already */
+			return 0;
+		verbose(env, "Syscall programs can only be sleepable\n");
+		return -EINVAL;
+	}
+
 	if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING &&
 	    prog->type != BPF_PROG_TYPE_LSM) {
 		verbose(env, "Only fentry/fexit/fmod_ret and lsm programs can be sleepable\n");
@@ -13355,8 +13378,7 @@ struct btf *bpf_get_btf_vmlinux(void)
 	return btf_vmlinux;
 }
 
-int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
-	      union bpf_attr __user *uattr)
+int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr)
 {
 	u64 start_time = ktime_get_ns();
 	struct bpf_verifier_env *env;
@@ -13386,6 +13408,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 		env->insn_aux_data[i].orig_idx = i;
 	env->prog = *prog;
 	env->ops = bpf_verifier_ops[env->prog->type];
+	env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel);
 	is_priv = bpf_capable();
 
 	bpf_get_btf_vmlinux();
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index fb3d3262dc1a..4cdf8416869d 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -638,7 +638,8 @@ static int vlan_ioctl_handler(struct net *net, void __user *arg)
 
 	case GET_VLAN_REALDEV_NAME_CMD:
 		err = 0;
-		vlan_dev_get_realdev_name(dev, args.u.device2);
+		vlan_dev_get_realdev_name(dev, args.u.device2,
+					  sizeof(args.u.device2));
 		if (copy_to_user(arg, &args,
 				 sizeof(struct vlan_ioctl_args)))
 			err = -EFAULT;
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index fa3ad3d4d58c..1a705a4ef7fa 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -108,7 +108,8 @@ static inline netdev_features_t vlan_tnl_features(struct net_device *real_dev)
 	netdev_features_t ret;
 
 	ret = real_dev->hw_enc_features &
-	      (NETIF_F_CSUM_MASK | NETIF_F_ALL_TSO | NETIF_F_GSO_ENCAP_ALL);
+	      (NETIF_F_CSUM_MASK | NETIF_F_GSO_SOFTWARE |
+	       NETIF_F_GSO_ENCAP_ALL);
 
 	if ((ret & NETIF_F_GSO_ENCAP_ALL) && (ret & NETIF_F_CSUM_MASK))
 		return (ret & ~NETIF_F_CSUM_MASK) | NETIF_F_HW_CSUM;
@@ -129,7 +130,8 @@ void vlan_dev_set_ingress_priority(const struct net_device *dev,
 int vlan_dev_set_egress_priority(const struct net_device *dev,
 				 u32 skb_prio, u16 vlan_prio);
 int vlan_dev_change_flags(const struct net_device *dev, u32 flag, u32 mask);
-void vlan_dev_get_realdev_name(const struct net_device *dev, char *result);
+void vlan_dev_get_realdev_name(const struct net_device *dev, char *result,
+			       size_t size);
 
 int vlan_check_real_dev(struct net_device *real_dev,
 			__be16 protocol, u16 vlan_id,
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 4db3f0621959..a0367b37512d 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -239,9 +239,9 @@ int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask)
 	return 0;
 }
 
-void vlan_dev_get_realdev_name(const struct net_device *dev, char *result)
+void vlan_dev_get_realdev_name(const struct net_device *dev, char *result, size_t size)
 {
-	strncpy(result, vlan_dev_priv(dev)->real_dev->name, 23);
+	strscpy_pad(result, vlan_dev_priv(dev)->real_dev->name, size);
 }
 
 bool vlan_dev_inherit_address(struct net_device *dev,
@@ -360,7 +360,7 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	struct ifreq ifrr;
 	int err = -EOPNOTSUPP;
 
-	strncpy(ifrr.ifr_name, real_dev->name, IFNAMSIZ);
+	strscpy_pad(ifrr.ifr_name, real_dev->name, IFNAMSIZ);
 	ifrr.ifr_ifru = ifr->ifr_ifru;
 
 	switch (cmd) {
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 93f2f8654882..2bbd7dce0f1d 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -99,7 +99,7 @@ static unsigned int rest_of_page(void *data)
  * @client: client instance
  *
  * This reclaims a channel by freeing its resources and
- * reseting its inuse flag.
+ * resetting its inuse flag.
  *
  */
 
@@ -463,7 +463,7 @@ req_retry_pinned:
 	 * For example TREAD have 11.
 	 * 11 is the read/write header = PDU Header(7) + IO Size (4).
 	 * Arrange in such a way that server places header in the
-	 * alloced memory and payload onto the user buffer.
+	 * allocated memory and payload onto the user buffer.
 	 */
 	in = pack_sg_list(chan->sg, out,
 			  VIRTQUEUE_NUM, req->rc.sdata, in_hdr_len);
@@ -760,7 +760,7 @@ static struct p9_trans_module p9_virtio_trans = {
 	.cancelled = p9_virtio_cancelled,
 	/*
 	 * We leave one entry for input and one entry for response
-	 * headers. We also skip one more entry to accomodate, address
+	 * headers. We also skip one more entry to accommodate, address
 	 * that are not at page boundary, that can result in an extra
 	 * page in zero copy.
 	 */
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index ebda397fa95a..8ade5a4ceaf5 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -707,7 +707,7 @@ static int atif_ioctl(int cmd, void __user *arg)
 
 		/*
 		 * Phase 1 is fine on LocalTalk but we don't do
-		 * EtherTalk phase 1. Anyone wanting to add it go ahead.
+		 * EtherTalk phase 1. Anyone wanting to add it, go ahead.
 		 */
 		if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2)
 			return -EPROTONOSUPPORT;
@@ -828,7 +828,7 @@ static int atif_ioctl(int cmd, void __user *arg)
 		nr = (struct atalk_netrange *)&(atif->nets);
 		/*
 		 * Phase 1 is fine on Localtalk but we don't do
-		 * Ethertalk phase 1. Anyone wanting to add it go ahead.
+		 * Ethertalk phase 1. Anyone wanting to add it, go ahead.
 		 */
 		if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2)
 			return -EPROTONOSUPPORT;
@@ -2018,7 +2018,7 @@ module_init(atalk_init);
  * by the network device layer.
  *
  * Ergo, before the AppleTalk module can be removed, all AppleTalk
- * sockets be closed from user space.
+ * sockets should be closed from user space.
  */
 static void __exit atalk_exit(void)
 {
diff --git a/net/atm/atm_sysfs.c b/net/atm/atm_sysfs.c
index aa1b57161f3b..0fdbdfd19474 100644
--- a/net/atm/atm_sysfs.c
+++ b/net/atm/atm_sysfs.c
@@ -11,7 +11,7 @@
 
 #define to_atm_dev(cldev) container_of(cldev, struct atm_dev, class_dev)
 
-static ssize_t show_type(struct device *cdev,
+static ssize_t type_show(struct device *cdev,
 			 struct device_attribute *attr, char *buf)
 {
 	struct atm_dev *adev = to_atm_dev(cdev);
@@ -19,7 +19,7 @@ static ssize_t show_type(struct device *cdev,
 	return scnprintf(buf, PAGE_SIZE, "%s\n", adev->type);
 }
 
-static ssize_t show_address(struct device *cdev,
+static ssize_t address_show(struct device *cdev,
 			    struct device_attribute *attr, char *buf)
 {
 	struct atm_dev *adev = to_atm_dev(cdev);
@@ -27,7 +27,7 @@ static ssize_t show_address(struct device *cdev,
 	return scnprintf(buf, PAGE_SIZE, "%pM\n", adev->esi);
 }
 
-static ssize_t show_atmaddress(struct device *cdev,
+static ssize_t atmaddress_show(struct device *cdev,
 			       struct device_attribute *attr, char *buf)
 {
 	unsigned long flags;
@@ -50,7 +50,7 @@ static ssize_t show_atmaddress(struct device *cdev,
 	return count;
 }
 
-static ssize_t show_atmindex(struct device *cdev,
+static ssize_t atmindex_show(struct device *cdev,
 			     struct device_attribute *attr, char *buf)
 {
 	struct atm_dev *adev = to_atm_dev(cdev);
@@ -58,7 +58,7 @@ static ssize_t show_atmindex(struct device *cdev,
 	return scnprintf(buf, PAGE_SIZE, "%d\n", adev->number);
 }
 
-static ssize_t show_carrier(struct device *cdev,
+static ssize_t carrier_show(struct device *cdev,
 			    struct device_attribute *attr, char *buf)
 {
 	struct atm_dev *adev = to_atm_dev(cdev);
@@ -67,7 +67,7 @@ static ssize_t show_carrier(struct device *cdev,
 			 adev->signal == ATM_PHY_SIG_LOST ? 0 : 1);
 }
 
-static ssize_t show_link_rate(struct device *cdev,
+static ssize_t link_rate_show(struct device *cdev,
 			      struct device_attribute *attr, char *buf)
 {
 	struct atm_dev *adev = to_atm_dev(cdev);
@@ -90,12 +90,12 @@ static ssize_t show_link_rate(struct device *cdev,
 	return scnprintf(buf, PAGE_SIZE, "%d\n", link_rate);
 }
 
-static DEVICE_ATTR(address, 0444, show_address, NULL);
-static DEVICE_ATTR(atmaddress, 0444, show_atmaddress, NULL);
-static DEVICE_ATTR(atmindex, 0444, show_atmindex, NULL);
-static DEVICE_ATTR(carrier, 0444, show_carrier, NULL);
-static DEVICE_ATTR(type, 0444, show_type, NULL);
-static DEVICE_ATTR(link_rate, 0444, show_link_rate, NULL);
+static DEVICE_ATTR_RO(address);
+static DEVICE_ATTR_RO(atmaddress);
+static DEVICE_ATTR_RO(atmindex);
+static DEVICE_ATTR_RO(carrier);
+static DEVICE_ATTR_RO(type);
+static DEVICE_ATTR_RO(link_rate);
 
 static struct device_attribute *atm_attrs[] = {
 	&dev_attr_atmaddress,
diff --git a/net/atm/br2684.c b/net/atm/br2684.c
index 3e17a5ecaa94..dd2a8dabed84 100644
--- a/net/atm/br2684.c
+++ b/net/atm/br2684.c
@@ -93,8 +93,8 @@ struct br2684_dev {
  * This lock should be held for writing any time the list of devices or
  * their attached vcc's could be altered.  It should be held for reading
  * any time these are being queried.  Note that we sometimes need to
- * do read-locking under interrupt context, so write locking must block
- * the current CPU's interrupts
+ * do read-locking under interrupting context, so write locking must block
+ * the current CPU's interrupts.
  */
 static DEFINE_RWLOCK(devs_lock);
 
diff --git a/net/atm/resources.c b/net/atm/resources.c
index 53236986dfe0..2b2d33eeaf20 100644
--- a/net/atm/resources.c
+++ b/net/atm/resources.c
@@ -52,10 +52,8 @@ static struct atm_dev *__alloc_atm_dev(const char *type)
 static struct atm_dev *__atm_dev_lookup(int number)
 {
 	struct atm_dev *dev;
-	struct list_head *p;
 
-	list_for_each(p, &atm_devs) {
-		dev = list_entry(p, struct atm_dev, dev_list);
+	list_for_each_entry(dev, &atm_devs, dev_list) {
 		if (dev->number == number) {
 			atm_dev_hold(dev);
 			return dev;
@@ -215,8 +213,7 @@ int atm_getnames(void __user *buf, int __user *iobuf_len)
 		return -ENOMEM;
 	}
 	tmp_p = tmp_buf;
-	list_for_each(p, &atm_devs) {
-		dev = list_entry(p, struct atm_dev, dev_list);
+	list_for_each_entry(dev, &atm_devs, dev_list) {
 		*tmp_p++ = dev->number;
 	}
 	mutex_unlock(&atm_dev_mutex);
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index fc8be49010b9..12022378f892 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -1851,6 +1851,8 @@ batadv_iv_ogm_orig_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq,
 		    orig_node->orig) ||
 	    nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN,
 		    neigh_node->addr) ||
+	    nla_put_string(msg, BATADV_ATTR_HARD_IFNAME,
+			   neigh_node->if_incoming->net_dev->name) ||
 	    nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX,
 			neigh_node->if_incoming->net_dev->ifindex) ||
 	    nla_put_u8(msg, BATADV_ATTR_TQ, tq_avg) ||
@@ -2080,6 +2082,8 @@ batadv_iv_ogm_neigh_dump_neigh(struct sk_buff *msg, u32 portid, u32 seq,
 
 	if (nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN,
 		    hardif_neigh->addr) ||
+	    nla_put_string(msg, BATADV_ATTR_HARD_IFNAME,
+			   hardif_neigh->if_incoming->net_dev->name) ||
 	    nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX,
 			hardif_neigh->if_incoming->net_dev->ifindex) ||
 	    nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS,
@@ -2461,6 +2465,8 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid,
 		    router->addr) ||
 	    nla_put_string(msg, BATADV_ATTR_HARD_IFNAME,
 			   router->if_incoming->net_dev->name) ||
+	    nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX,
+			router->if_incoming->net_dev->ifindex) ||
 	    nla_put_u32(msg, BATADV_ATTR_BANDWIDTH_DOWN,
 			gw_node->bandwidth_down) ||
 	    nla_put_u32(msg, BATADV_ATTR_BANDWIDTH_UP,
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index e1ca2b8c3152..b98aea958e3d 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -146,6 +146,8 @@ batadv_v_neigh_dump_neigh(struct sk_buff *msg, u32 portid, u32 seq,
 
 	if (nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN,
 		    hardif_neigh->addr) ||
+	    nla_put_string(msg, BATADV_ATTR_HARD_IFNAME,
+			   hardif_neigh->if_incoming->net_dev->name) ||
 	    nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX,
 			hardif_neigh->if_incoming->net_dev->ifindex) ||
 	    nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS,
@@ -298,6 +300,8 @@ batadv_v_orig_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq,
 	if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, orig_node->orig) ||
 	    nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN,
 		    neigh_node->addr) ||
+	    nla_put_string(msg, BATADV_ATTR_HARD_IFNAME,
+			   neigh_node->if_incoming->net_dev->name) ||
 	    nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX,
 			neigh_node->if_incoming->net_dev->ifindex) ||
 	    nla_put_u32(msg, BATADV_ATTR_THROUGHPUT, throughput) ||
@@ -739,6 +743,12 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid,
 		goto out;
 	}
 
+	if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX,
+			router->if_incoming->net_dev->ifindex)) {
+		genlmsg_cancel(msg, hdr);
+		goto out;
+	}
+
 	if (nla_put_u32(msg, BATADV_ATTR_BANDWIDTH_DOWN,
 			gw_node->bandwidth_down)) {
 		genlmsg_cancel(msg, hdr);
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 7dc133cfc363..63d42dcc9324 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -395,7 +395,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac,
 		break;
 	case BATADV_CLAIM_TYPE_ANNOUNCE:
 		/* announcement frame
-		 * set HW SRC to the special mac containg the crc
+		 * set HW SRC to the special mac containing the crc
 		 */
 		ether_addr_copy(hw_src, mac);
 		batadv_dbg(BATADV_DBG_BLA, bat_priv,
@@ -1040,7 +1040,7 @@ static int batadv_check_claim_group(struct batadv_priv *bat_priv,
 	/* lets see if this originator is in our mesh */
 	orig_node = batadv_orig_hash_find(bat_priv, backbone_addr);
 
-	/* dont accept claims from gateways which are not in
+	/* don't accept claims from gateways which are not in
 	 * the same mesh or group.
 	 */
 	if (!orig_node)
diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h
index 5c22955bb9d5..8673a265995f 100644
--- a/net/batman-adv/bridge_loop_avoidance.h
+++ b/net/batman-adv/bridge_loop_avoidance.h
@@ -52,7 +52,6 @@ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv,
 void batadv_bla_status_update(struct net_device *net_dev);
 int batadv_bla_init(struct batadv_priv *bat_priv);
 void batadv_bla_free(struct batadv_priv *bat_priv);
-int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb);
 #ifdef CONFIG_BATMAN_ADV_DAT
 bool batadv_bla_check_claim(struct batadv_priv *bat_priv, u8 *addr,
 			    unsigned short vid);
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 4a6a25d551a8..55d97e18aa4a 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -9,7 +9,6 @@
 
 #include <linux/atomic.h>
 #include <linux/byteorder/generic.h>
-#include <linux/errno.h>
 #include <linux/gfp.h>
 #include <linux/if.h>
 #include <linux/if_arp.h>
@@ -403,7 +402,7 @@ int batadv_hardif_no_broadcast(struct batadv_hard_iface *if_outgoing,
 		goto out;
 	}
 
-	/* >1 neighbors -> (re)brodcast */
+	/* >1 neighbors -> (re)broadcast */
 	if (rcu_dereference(hlist_next_rcu(first)))
 		goto out;
 
@@ -678,43 +677,16 @@ batadv_hardif_deactivate_interface(struct batadv_hard_iface *hard_iface)
 }
 
 /**
- * batadv_master_del_slave() - remove hard_iface from the current master iface
- * @slave: the interface enslaved in another master
- * @master: the master from which slave has to be removed
- *
- * Invoke ndo_del_slave on master passing slave as argument. In this way the
- * slave is free'd and the master can correctly change its internal state.
- *
- * Return: 0 on success, a negative value representing the error otherwise
- */
-static int batadv_master_del_slave(struct batadv_hard_iface *slave,
-				   struct net_device *master)
-{
-	int ret;
-
-	if (!master)
-		return 0;
-
-	ret = -EBUSY;
-	if (master->netdev_ops->ndo_del_slave)
-		ret = master->netdev_ops->ndo_del_slave(master, slave->net_dev);
-
-	return ret;
-}
-
-/**
  * batadv_hardif_enable_interface() - Enslave hard interface to soft interface
  * @hard_iface: hard interface to add to soft interface
- * @net: the applicable net namespace
- * @iface_name: name of the soft interface
+ * @soft_iface: netdev struct of the mesh interface
  *
  * Return: 0 on success or negative error number in case of failure
  */
 int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
-				   struct net *net, const char *iface_name)
+				   struct net_device *soft_iface)
 {
 	struct batadv_priv *bat_priv;
-	struct net_device *soft_iface, *master;
 	__be16 ethertype = htons(ETH_P_BATMAN);
 	int max_header_len = batadv_max_header_len();
 	int ret;
@@ -724,35 +696,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 
 	kref_get(&hard_iface->refcount);
 
-	soft_iface = dev_get_by_name(net, iface_name);
-
-	if (!soft_iface) {
-		soft_iface = batadv_softif_create(net, iface_name);
-
-		if (!soft_iface) {
-			ret = -ENOMEM;
-			goto err;
-		}
-
-		/* dev_get_by_name() increases the reference counter for us */
-		dev_hold(soft_iface);
-	}
-
-	if (!batadv_softif_is_valid(soft_iface)) {
-		pr_err("Can't create batman mesh interface %s: already exists as regular interface\n",
-		       soft_iface->name);
-		ret = -EINVAL;
-		goto err_dev;
-	}
-
-	/* check if the interface is enslaved in another virtual one and
-	 * in that case unlink it first
-	 */
-	master = netdev_master_upper_dev_get(hard_iface->net_dev);
-	ret = batadv_master_del_slave(hard_iface, master);
-	if (ret)
-		goto err_dev;
-
+	dev_hold(soft_iface);
 	hard_iface->soft_iface = soft_iface;
 	bat_priv = netdev_priv(hard_iface->soft_iface);
 
@@ -810,7 +754,6 @@ err_upper:
 err_dev:
 	hard_iface->soft_iface = NULL;
 	dev_put(soft_iface);
-err:
 	batadv_hardif_put(hard_iface);
 	return ret;
 }
diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h
index 83d11b46a9d8..8cb2a1f10080 100644
--- a/net/batman-adv/hard-interface.h
+++ b/net/batman-adv/hard-interface.h
@@ -16,7 +16,6 @@
 #include <linux/rcupdate.h>
 #include <linux/stddef.h>
 #include <linux/types.h>
-#include <net/net_namespace.h>
 
 /**
  * enum batadv_hard_if_state - State of a hard interface
@@ -75,7 +74,7 @@ bool batadv_is_wifi_hardif(struct batadv_hard_iface *hard_iface);
 struct batadv_hard_iface*
 batadv_hardif_get_by_netdev(const struct net_device *net_dev);
 int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
-				   struct net *net, const char *iface_name);
+				   struct net_device *soft_iface);
 void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface);
 int batadv_hardif_min_mtu(struct net_device *soft_iface);
 void batadv_update_min_mtu(struct net_device *soft_iface);
diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h
index 46696759f194..fb251c385a1b 100644
--- a/net/batman-adv/hash.h
+++ b/net/batman-adv/hash.h
@@ -18,7 +18,7 @@
 #include <linux/stddef.h>
 #include <linux/types.h>
 
-/* callback to a compare function.  should compare 2 element datas for their
+/* callback to a compare function.  should compare 2 element data for their
  * keys
  *
  * Return: true if same and false if not same
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 8f0102b71656..014235fd4681 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -13,7 +13,7 @@
 #define BATADV_DRIVER_DEVICE "batman-adv"
 
 #ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2021.1"
+#define BATADV_SOURCE_VERSION "2021.2"
 #endif
 
 /* B.A.T.M.A.N. parameters */
@@ -88,7 +88,6 @@
 /* number of packets to send for broadcasts on different interface types */
 #define BATADV_NUM_BCASTS_DEFAULT 1
 #define BATADV_NUM_BCASTS_WIRELESS 3
-#define BATADV_NUM_BCASTS_MAX 3
 
 /* length of the single packet used by the TP meter */
 #define BATADV_TP_PACKET_LEN ETH_DATA_LEN
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 1d63c8cbbfe7..923e2197c2db 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -193,53 +193,22 @@ static u8 batadv_mcast_mla_rtr_flags_softif_get(struct batadv_priv *bat_priv,
  *	BATADV_MCAST_WANT_NO_RTR6: No IPv6 multicast router is present
  *	The former two OR'd: no multicast router is present
  */
-#if IS_ENABLED(CONFIG_IPV6)
 static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv,
 						struct net_device *bridge)
 {
-	struct list_head bridge_mcast_list = LIST_HEAD_INIT(bridge_mcast_list);
 	struct net_device *dev = bat_priv->soft_iface;
-	struct br_ip_list *br_ip_entry, *tmp;
-	u8 flags = BATADV_MCAST_WANT_NO_RTR6;
-	int ret;
+	u8 flags = BATADV_NO_FLAGS;
 
 	if (!bridge)
 		return BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6;
 
-	/* TODO: ask the bridge if a multicast router is present (the bridge
-	 * is capable of performing proper RFC4286 multicast router
-	 * discovery) instead of searching for a ff02::2 listener here
-	 */
-	ret = br_multicast_list_adjacent(dev, &bridge_mcast_list);
-	if (ret < 0)
-		return BATADV_NO_FLAGS;
-
-	list_for_each_entry_safe(br_ip_entry, tmp, &bridge_mcast_list, list) {
-		/* the bridge snooping does not maintain IPv4 link-local
-		 * addresses - therefore we won't find any IPv4 multicast router
-		 * address here, only IPv6 ones
-		 */
-		if (br_ip_entry->addr.proto == htons(ETH_P_IPV6) &&
-		    ipv6_addr_is_ll_all_routers(&br_ip_entry->addr.dst.ip6))
-			flags &= ~BATADV_MCAST_WANT_NO_RTR6;
-
-		list_del(&br_ip_entry->list);
-		kfree(br_ip_entry);
-	}
+	if (!br_multicast_has_router_adjacent(dev, ETH_P_IP))
+		flags |= BATADV_MCAST_WANT_NO_RTR4;
+	if (!br_multicast_has_router_adjacent(dev, ETH_P_IPV6))
+		flags |= BATADV_MCAST_WANT_NO_RTR6;
 
 	return flags;
 }
-#else
-static inline u8
-batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv,
-				      struct net_device *bridge)
-{
-	if (bridge)
-		return BATADV_NO_FLAGS;
-	else
-		return BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6;
-}
-#endif
 
 /**
  * batadv_mcast_mla_rtr_flags_get() - get multicast router flags
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index f317d206b411..b6cc746e01a6 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -814,6 +814,10 @@ static int batadv_netlink_hardif_fill(struct sk_buff *msg,
 			bat_priv->soft_iface->ifindex))
 		goto nla_put_failure;
 
+	if (nla_put_string(msg, BATADV_ATTR_MESH_IFNAME,
+			   bat_priv->soft_iface->name))
+		goto nla_put_failure;
+
 	if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX,
 			net_dev->ifindex) ||
 	    nla_put_string(msg, BATADV_ATTR_HARD_IFNAME,
@@ -1045,6 +1049,10 @@ static int batadv_netlink_vlan_fill(struct sk_buff *msg,
 			bat_priv->soft_iface->ifindex))
 		goto nla_put_failure;
 
+	if (nla_put_string(msg, BATADV_ATTR_MESH_IFNAME,
+			   bat_priv->soft_iface->name))
+		goto nla_put_failure;
+
 	if (nla_put_u32(msg, BATADV_ATTR_VLANID, vlan->vid & VLAN_VID_MASK))
 		goto nla_put_failure;
 
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 40f5cffde6a3..bb9e93e3d98c 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -1182,9 +1182,9 @@ int batadv_recv_bcast_packet(struct sk_buff *skb,
 	struct batadv_bcast_packet *bcast_packet;
 	struct ethhdr *ethhdr;
 	int hdr_size = sizeof(*bcast_packet);
-	int ret = NET_RX_DROP;
 	s32 seq_diff;
 	u32 seqno;
+	int ret;
 
 	/* drop packet if it has not necessary minimum size */
 	if (unlikely(!pskb_may_pull(skb, hdr_size)))
@@ -1210,7 +1210,7 @@ int batadv_recv_bcast_packet(struct sk_buff *skb,
 	if (batadv_is_my_mac(bat_priv, bcast_packet->orig))
 		goto free_skb;
 
-	if (bcast_packet->ttl < 2)
+	if (bcast_packet->ttl-- < 2)
 		goto free_skb;
 
 	orig_node = batadv_orig_hash_find(bat_priv, bcast_packet->orig);
@@ -1249,7 +1249,9 @@ int batadv_recv_bcast_packet(struct sk_buff *skb,
 	batadv_skb_set_priority(skb, sizeof(struct batadv_bcast_packet));
 
 	/* rebroadcast packet */
-	batadv_add_bcast_packet_to_list(bat_priv, skb, 1, false);
+	ret = batadv_forw_bcast_packet(bat_priv, skb, 0, false);
+	if (ret == NETDEV_TX_BUSY)
+		goto free_skb;
 
 	/* don't hand the broadcast up if it is from an originator
 	 * from the same backbone.
@@ -1275,6 +1277,7 @@ spin_unlock:
 	spin_unlock_bh(&orig_node->bcast_seqno_lock);
 free_skb:
 	kfree_skb(skb);
+	ret = NET_RX_DROP;
 out:
 	if (orig_node)
 		batadv_orig_node_put(orig_node);
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 157abe92d827..0b9dd29d3b6a 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -737,57 +737,48 @@ void batadv_forw_packet_ogmv1_queue(struct batadv_priv *bat_priv,
 }
 
 /**
- * batadv_add_bcast_packet_to_list() - queue broadcast packet for multiple sends
+ * batadv_forw_bcast_packet_to_list() - queue broadcast packet for transmissions
  * @bat_priv: the bat priv with all the soft interface information
  * @skb: broadcast packet to add
  * @delay: number of jiffies to wait before sending
  * @own_packet: true if it is a self-generated broadcast packet
+ * @if_in: the interface where the packet was received on
+ * @if_out: the outgoing interface to queue on
  *
- * add a broadcast packet to the queue and setup timers. broadcast packets
+ * Adds a broadcast packet to the queue and sets up timers. Broadcast packets
  * are sent multiple times to increase probability for being received.
  *
- * The skb is not consumed, so the caller should make sure that the
- * skb is freed.
- *
  * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors.
  */
-int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv,
-				    const struct sk_buff *skb,
-				    unsigned long delay,
-				    bool own_packet)
+static int batadv_forw_bcast_packet_to_list(struct batadv_priv *bat_priv,
+					    struct sk_buff *skb,
+					    unsigned long delay,
+					    bool own_packet,
+					    struct batadv_hard_iface *if_in,
+					    struct batadv_hard_iface *if_out)
 {
-	struct batadv_hard_iface *primary_if;
 	struct batadv_forw_packet *forw_packet;
-	struct batadv_bcast_packet *bcast_packet;
+	unsigned long send_time = jiffies;
 	struct sk_buff *newskb;
 
-	primary_if = batadv_primary_if_get_selected(bat_priv);
-	if (!primary_if)
-		goto err;
-
 	newskb = skb_copy(skb, GFP_ATOMIC);
-	if (!newskb) {
-		batadv_hardif_put(primary_if);
+	if (!newskb)
 		goto err;
-	}
 
-	forw_packet = batadv_forw_packet_alloc(primary_if, NULL,
+	forw_packet = batadv_forw_packet_alloc(if_in, if_out,
 					       &bat_priv->bcast_queue_left,
 					       bat_priv, newskb);
-	batadv_hardif_put(primary_if);
 	if (!forw_packet)
 		goto err_packet_free;
 
-	/* as we have a copy now, it is safe to decrease the TTL */
-	bcast_packet = (struct batadv_bcast_packet *)newskb->data;
-	bcast_packet->ttl--;
-
 	forw_packet->own = own_packet;
 
 	INIT_DELAYED_WORK(&forw_packet->delayed_work,
 			  batadv_send_outstanding_bcast_packet);
 
-	batadv_forw_packet_bcast_queue(bat_priv, forw_packet, jiffies + delay);
+	send_time += delay ? delay : msecs_to_jiffies(5);
+
+	batadv_forw_packet_bcast_queue(bat_priv, forw_packet, send_time);
 	return NETDEV_TX_OK;
 
 err_packet_free:
@@ -797,9 +788,219 @@ err:
 }
 
 /**
+ * batadv_forw_bcast_packet_if() - forward and queue a broadcast packet
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: broadcast packet to add
+ * @delay: number of jiffies to wait before sending
+ * @own_packet: true if it is a self-generated broadcast packet
+ * @if_in: the interface where the packet was received on
+ * @if_out: the outgoing interface to forward to
+ *
+ * Transmits a broadcast packet on the specified interface either immediately
+ * or if a delay is given after that. Furthermore, queues additional
+ * retransmissions if this interface is a wireless one.
+ *
+ * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors.
+ */
+static int batadv_forw_bcast_packet_if(struct batadv_priv *bat_priv,
+				       struct sk_buff *skb,
+				       unsigned long delay,
+				       bool own_packet,
+				       struct batadv_hard_iface *if_in,
+				       struct batadv_hard_iface *if_out)
+{
+	unsigned int num_bcasts = if_out->num_bcasts;
+	struct sk_buff *newskb;
+	int ret = NETDEV_TX_OK;
+
+	if (!delay) {
+		newskb = skb_copy(skb, GFP_ATOMIC);
+		if (!newskb)
+			return NETDEV_TX_BUSY;
+
+		batadv_send_broadcast_skb(newskb, if_out);
+		num_bcasts--;
+	}
+
+	/* delayed broadcast or rebroadcasts? */
+	if (num_bcasts >= 1) {
+		BATADV_SKB_CB(skb)->num_bcasts = num_bcasts;
+
+		ret = batadv_forw_bcast_packet_to_list(bat_priv, skb, delay,
+						       own_packet, if_in,
+						       if_out);
+	}
+
+	return ret;
+}
+
+/**
+ * batadv_send_no_broadcast() - check whether (re)broadcast is necessary
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: broadcast packet to check
+ * @own_packet: true if it is a self-generated broadcast packet
+ * @if_out: the outgoing interface checked and considered for (re)broadcast
+ *
+ * Return: False if a packet needs to be (re)broadcasted on the given interface,
+ * true otherwise.
+ */
+static bool batadv_send_no_broadcast(struct batadv_priv *bat_priv,
+				     struct sk_buff *skb, bool own_packet,
+				     struct batadv_hard_iface *if_out)
+{
+	struct batadv_hardif_neigh_node *neigh_node = NULL;
+	struct batadv_bcast_packet *bcast_packet;
+	u8 *orig_neigh;
+	u8 *neigh_addr;
+	char *type;
+	int ret;
+
+	if (!own_packet) {
+		neigh_addr = eth_hdr(skb)->h_source;
+		neigh_node = batadv_hardif_neigh_get(if_out,
+						     neigh_addr);
+	}
+
+	bcast_packet = (struct batadv_bcast_packet *)skb->data;
+	orig_neigh = neigh_node ? neigh_node->orig : NULL;
+
+	ret = batadv_hardif_no_broadcast(if_out, bcast_packet->orig,
+					 orig_neigh);
+
+	if (neigh_node)
+		batadv_hardif_neigh_put(neigh_node);
+
+	/* ok, may broadcast */
+	if (!ret)
+		return false;
+
+	/* no broadcast */
+	switch (ret) {
+	case BATADV_HARDIF_BCAST_NORECIPIENT:
+		type = "no neighbor";
+		break;
+	case BATADV_HARDIF_BCAST_DUPFWD:
+		type = "single neighbor is source";
+		break;
+	case BATADV_HARDIF_BCAST_DUPORIG:
+		type = "single neighbor is originator";
+		break;
+	default:
+		type = "unknown";
+	}
+
+	batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+		   "BCAST packet from orig %pM on %s suppressed: %s\n",
+		   bcast_packet->orig,
+		   if_out->net_dev->name, type);
+
+	return true;
+}
+
+/**
+ * __batadv_forw_bcast_packet() - forward and queue a broadcast packet
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: broadcast packet to add
+ * @delay: number of jiffies to wait before sending
+ * @own_packet: true if it is a self-generated broadcast packet
+ *
+ * Transmits a broadcast packet either immediately or if a delay is given
+ * after that. Furthermore, queues additional retransmissions on wireless
+ * interfaces.
+ *
+ * This call clones the given skb, hence the caller needs to take into
+ * account that the data segment of the given skb might not be
+ * modifiable anymore.
+ *
+ * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors.
+ */
+static int __batadv_forw_bcast_packet(struct batadv_priv *bat_priv,
+				      struct sk_buff *skb,
+				      unsigned long delay,
+				      bool own_packet)
+{
+	struct batadv_hard_iface *hard_iface;
+	struct batadv_hard_iface *primary_if;
+	int ret = NETDEV_TX_OK;
+
+	primary_if = batadv_primary_if_get_selected(bat_priv);
+	if (!primary_if)
+		return NETDEV_TX_BUSY;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
+		if (hard_iface->soft_iface != bat_priv->soft_iface)
+			continue;
+
+		if (!kref_get_unless_zero(&hard_iface->refcount))
+			continue;
+
+		if (batadv_send_no_broadcast(bat_priv, skb, own_packet,
+					     hard_iface)) {
+			batadv_hardif_put(hard_iface);
+			continue;
+		}
+
+		ret = batadv_forw_bcast_packet_if(bat_priv, skb, delay,
+						  own_packet, primary_if,
+						  hard_iface);
+		batadv_hardif_put(hard_iface);
+
+		if (ret == NETDEV_TX_BUSY)
+			break;
+	}
+	rcu_read_unlock();
+
+	batadv_hardif_put(primary_if);
+	return ret;
+}
+
+/**
+ * batadv_forw_bcast_packet() - forward and queue a broadcast packet
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: broadcast packet to add
+ * @delay: number of jiffies to wait before sending
+ * @own_packet: true if it is a self-generated broadcast packet
+ *
+ * Transmits a broadcast packet either immediately or if a delay is given
+ * after that. Furthermore, queues additional retransmissions on wireless
+ * interfaces.
+ *
+ * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors.
+ */
+int batadv_forw_bcast_packet(struct batadv_priv *bat_priv,
+			     struct sk_buff *skb,
+			     unsigned long delay,
+			     bool own_packet)
+{
+	return __batadv_forw_bcast_packet(bat_priv, skb, delay, own_packet);
+}
+
+/**
+ * batadv_send_bcast_packet() - send and queue a broadcast packet
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: broadcast packet to add
+ * @delay: number of jiffies to wait before sending
+ * @own_packet: true if it is a self-generated broadcast packet
+ *
+ * Transmits a broadcast packet either immediately or if a delay is given
+ * after that. Furthermore, queues additional retransmissions on wireless
+ * interfaces.
+ *
+ * Consumes the provided skb.
+ */
+void batadv_send_bcast_packet(struct batadv_priv *bat_priv,
+			      struct sk_buff *skb,
+			      unsigned long delay,
+			      bool own_packet)
+{
+	__batadv_forw_bcast_packet(bat_priv, skb, delay, own_packet);
+	consume_skb(skb);
+}
+
+/**
  * batadv_forw_packet_bcasts_left() - check if a retransmission is necessary
  * @forw_packet: the forwarding packet to check
- * @hard_iface: the interface to check on
  *
  * Checks whether a given packet has any (re)transmissions left on the provided
  * interface.
@@ -811,28 +1012,20 @@ err:
  * Return: True if (re)transmissions are left, false otherwise.
  */
 static bool
-batadv_forw_packet_bcasts_left(struct batadv_forw_packet *forw_packet,
-			       struct batadv_hard_iface *hard_iface)
+batadv_forw_packet_bcasts_left(struct batadv_forw_packet *forw_packet)
 {
-	unsigned int max;
-
-	if (hard_iface)
-		max = hard_iface->num_bcasts;
-	else
-		max = BATADV_NUM_BCASTS_MAX;
-
-	return BATADV_SKB_CB(forw_packet->skb)->num_bcasts < max;
+	return BATADV_SKB_CB(forw_packet->skb)->num_bcasts;
 }
 
 /**
- * batadv_forw_packet_bcasts_inc() - increment retransmission counter of a
+ * batadv_forw_packet_bcasts_dec() - decrement retransmission counter of a
  *  packet
- * @forw_packet: the packet to increase the counter for
+ * @forw_packet: the packet to decrease the counter for
  */
 static void
-batadv_forw_packet_bcasts_inc(struct batadv_forw_packet *forw_packet)
+batadv_forw_packet_bcasts_dec(struct batadv_forw_packet *forw_packet)
 {
-	BATADV_SKB_CB(forw_packet->skb)->num_bcasts++;
+	BATADV_SKB_CB(forw_packet->skb)->num_bcasts--;
 }
 
 /**
@@ -843,30 +1036,30 @@ batadv_forw_packet_bcasts_inc(struct batadv_forw_packet *forw_packet)
  */
 bool batadv_forw_packet_is_rebroadcast(struct batadv_forw_packet *forw_packet)
 {
-	return BATADV_SKB_CB(forw_packet->skb)->num_bcasts > 0;
+	unsigned char num_bcasts = BATADV_SKB_CB(forw_packet->skb)->num_bcasts;
+
+	return num_bcasts != forw_packet->if_outgoing->num_bcasts;
 }
 
+/**
+ * batadv_send_outstanding_bcast_packet() - transmit a queued broadcast packet
+ * @work: work queue item
+ *
+ * Transmits a queued broadcast packet and if necessary reschedules it.
+ */
 static void batadv_send_outstanding_bcast_packet(struct work_struct *work)
 {
-	struct batadv_hard_iface *hard_iface;
-	struct batadv_hardif_neigh_node *neigh_node;
-	struct delayed_work *delayed_work;
+	unsigned long send_time = jiffies + msecs_to_jiffies(5);
 	struct batadv_forw_packet *forw_packet;
-	struct batadv_bcast_packet *bcast_packet;
-	struct sk_buff *skb1;
-	struct net_device *soft_iface;
+	struct delayed_work *delayed_work;
 	struct batadv_priv *bat_priv;
-	unsigned long send_time = jiffies + msecs_to_jiffies(5);
+	struct sk_buff *skb1;
 	bool dropped = false;
-	u8 *neigh_addr;
-	u8 *orig_neigh;
-	int ret = 0;
 
 	delayed_work = to_delayed_work(work);
 	forw_packet = container_of(delayed_work, struct batadv_forw_packet,
 				   delayed_work);
-	soft_iface = forw_packet->if_incoming->soft_iface;
-	bat_priv = netdev_priv(soft_iface);
+	bat_priv = netdev_priv(forw_packet->if_incoming->soft_iface);
 
 	if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) {
 		dropped = true;
@@ -878,76 +1071,15 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work)
 		goto out;
 	}
 
-	bcast_packet = (struct batadv_bcast_packet *)forw_packet->skb->data;
-
-	/* rebroadcast packet */
-	rcu_read_lock();
-	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
-		if (hard_iface->soft_iface != soft_iface)
-			continue;
-
-		if (!batadv_forw_packet_bcasts_left(forw_packet, hard_iface))
-			continue;
-
-		if (forw_packet->own) {
-			neigh_node = NULL;
-		} else {
-			neigh_addr = eth_hdr(forw_packet->skb)->h_source;
-			neigh_node = batadv_hardif_neigh_get(hard_iface,
-							     neigh_addr);
-		}
-
-		orig_neigh = neigh_node ? neigh_node->orig : NULL;
-
-		ret = batadv_hardif_no_broadcast(hard_iface, bcast_packet->orig,
-						 orig_neigh);
-
-		if (ret) {
-			char *type;
-
-			switch (ret) {
-			case BATADV_HARDIF_BCAST_NORECIPIENT:
-				type = "no neighbor";
-				break;
-			case BATADV_HARDIF_BCAST_DUPFWD:
-				type = "single neighbor is source";
-				break;
-			case BATADV_HARDIF_BCAST_DUPORIG:
-				type = "single neighbor is originator";
-				break;
-			default:
-				type = "unknown";
-			}
-
-			batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "BCAST packet from orig %pM on %s suppressed: %s\n",
-				   bcast_packet->orig,
-				   hard_iface->net_dev->name, type);
-
-			if (neigh_node)
-				batadv_hardif_neigh_put(neigh_node);
-
-			continue;
-		}
-
-		if (neigh_node)
-			batadv_hardif_neigh_put(neigh_node);
-
-		if (!kref_get_unless_zero(&hard_iface->refcount))
-			continue;
-
-		/* send a copy of the saved skb */
-		skb1 = skb_clone(forw_packet->skb, GFP_ATOMIC);
-		if (skb1)
-			batadv_send_broadcast_skb(skb1, hard_iface);
-
-		batadv_hardif_put(hard_iface);
-	}
-	rcu_read_unlock();
+	/* send a copy of the saved skb */
+	skb1 = skb_clone(forw_packet->skb, GFP_ATOMIC);
+	if (!skb1)
+		goto out;
 
-	batadv_forw_packet_bcasts_inc(forw_packet);
+	batadv_send_broadcast_skb(skb1, forw_packet->if_outgoing);
+	batadv_forw_packet_bcasts_dec(forw_packet);
 
-	/* if we still have some more bcasts to send */
-	if (batadv_forw_packet_bcasts_left(forw_packet, NULL)) {
+	if (batadv_forw_packet_bcasts_left(forw_packet)) {
 		batadv_forw_packet_bcast_queue(bat_priv, forw_packet,
 					       send_time);
 		return;
diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h
index 2b0daf8b2bc4..08af251b765c 100644
--- a/net/batman-adv/send.h
+++ b/net/batman-adv/send.h
@@ -39,10 +39,14 @@ int batadv_send_broadcast_skb(struct sk_buff *skb,
 			      struct batadv_hard_iface *hard_iface);
 int batadv_send_unicast_skb(struct sk_buff *skb,
 			    struct batadv_neigh_node *neigh_node);
-int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv,
-				    const struct sk_buff *skb,
-				    unsigned long delay,
-				    bool own_packet);
+int batadv_forw_bcast_packet(struct batadv_priv *bat_priv,
+			     struct sk_buff *skb,
+			     unsigned long delay,
+			     bool own_packet);
+void batadv_send_bcast_packet(struct batadv_priv *bat_priv,
+			      struct sk_buff *skb,
+			      unsigned long delay,
+			      bool own_packet);
 void
 batadv_purge_outstanding_packets(struct batadv_priv *bat_priv,
 				 const struct batadv_hard_iface *hard_iface);
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 6b8181bc3122..ae368a42a4ad 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -26,7 +26,6 @@
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
 #include <linux/percpu.h>
-#include <linux/printk.h>
 #include <linux/random.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
@@ -37,6 +36,7 @@
 #include <linux/stddef.h>
 #include <linux/string.h>
 #include <linux/types.h>
+#include <net/net_namespace.h>
 #include <net/netlink.h>
 #include <uapi/linux/batadv_packet.h>
 #include <uapi/linux/batman_adv.h>
@@ -191,7 +191,7 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb,
 	struct vlan_ethhdr *vhdr;
 	unsigned int header_len = 0;
 	int data_len = skb->len, ret;
-	unsigned long brd_delay = 1;
+	unsigned long brd_delay = 0;
 	bool do_bcast = false, client_added;
 	unsigned short vid;
 	u32 seqno;
@@ -330,7 +330,7 @@ send:
 
 		bcast_packet = (struct batadv_bcast_packet *)skb->data;
 		bcast_packet->version = BATADV_COMPAT_VERSION;
-		bcast_packet->ttl = BATADV_TTL;
+		bcast_packet->ttl = BATADV_TTL - 1;
 
 		/* batman packet type: broadcast */
 		bcast_packet->packet_type = BATADV_BCAST;
@@ -346,13 +346,7 @@ send:
 		seqno = atomic_inc_return(&bat_priv->bcast_seqno);
 		bcast_packet->seqno = htonl(seqno);
 
-		batadv_add_bcast_packet_to_list(bat_priv, skb, brd_delay, true);
-
-		/* a copy is stored in the bcast list, therefore removing
-		 * the original skb.
-		 */
-		consume_skb(skb);
-
+		batadv_send_bcast_packet(bat_priv, skb, brd_delay, true);
 	/* unicast packet */
 	} else {
 		/* DHCP packets going to a server will use the GW feature */
@@ -848,14 +842,13 @@ static int batadv_softif_slave_add(struct net_device *dev,
 				   struct netlink_ext_ack *extack)
 {
 	struct batadv_hard_iface *hard_iface;
-	struct net *net = dev_net(dev);
 	int ret = -EINVAL;
 
 	hard_iface = batadv_hardif_get_by_netdev(slave_dev);
 	if (!hard_iface || hard_iface->soft_iface)
 		goto out;
 
-	ret = batadv_hardif_enable_interface(hard_iface, net, dev->name);
+	ret = batadv_hardif_enable_interface(hard_iface, dev);
 
 out:
 	if (hard_iface)
@@ -1093,38 +1086,6 @@ static int batadv_softif_newlink(struct net *src_net, struct net_device *dev,
 }
 
 /**
- * batadv_softif_create() - Create and register soft interface
- * @net: the applicable net namespace
- * @name: name of the new soft interface
- *
- * Return: newly allocated soft_interface, NULL on errors
- */
-struct net_device *batadv_softif_create(struct net *net, const char *name)
-{
-	struct net_device *soft_iface;
-	int ret;
-
-	soft_iface = alloc_netdev(sizeof(struct batadv_priv), name,
-				  NET_NAME_UNKNOWN, batadv_softif_init_early);
-	if (!soft_iface)
-		return NULL;
-
-	dev_net_set(soft_iface, net);
-
-	soft_iface->rtnl_link_ops = &batadv_link_ops;
-
-	ret = register_netdevice(soft_iface);
-	if (ret < 0) {
-		pr_err("Unable to register the batman interface '%s': %i\n",
-		       name, ret);
-		free_netdev(soft_iface);
-		return NULL;
-	}
-
-	return soft_iface;
-}
-
-/**
  * batadv_softif_destroy_netlink() - deletion of batadv_soft_interface via
  *  netlink
  * @soft_iface: the to-be-removed batman-adv interface
diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h
index 38b0ad182584..67a2ddd6832f 100644
--- a/net/batman-adv/soft-interface.h
+++ b/net/batman-adv/soft-interface.h
@@ -12,14 +12,12 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/types.h>
-#include <net/net_namespace.h>
 #include <net/rtnetlink.h>
 
 int batadv_skb_head_push(struct sk_buff *skb, unsigned int len);
 void batadv_interface_rx(struct net_device *soft_iface,
 			 struct sk_buff *skb, int hdr_size,
 			 struct batadv_orig_node *orig_node);
-struct net_device *batadv_softif_create(struct net *net, const char *name);
 bool batadv_softif_is_valid(const struct net_device *net_dev);
 extern struct rtnl_link_ops batadv_link_ops;
 int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 88ec08978ff4..0ceb72d32208 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -758,7 +758,7 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status)
 	conn->state = BT_CLOSED;
 
 	/* If the status indicates successful cancellation of
-	 * the attempt (i.e. Unkown Connection Id) there's no point of
+	 * the attempt (i.e. Unknown Connection Id) there's no point of
 	 * notifying failure since we'll go back to keep trying to
 	 * connect. The only exception is explicit connect requests
 	 * where a timeout + cancel does indicate an actual failure.
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 7d71d104fdfd..25484bb0773d 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -648,7 +648,7 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt)
 						 */
 
 		/* If the controller supports Extended Scanner Filter
-		 * Policies, enable the correspondig event.
+		 * Policies, enable the corresponding event.
 		 */
 		if (hdev->le_features[0] & HCI_LE_EXT_SCAN_POLICY)
 			events[1] |= 0x04;	/* LE Direct Advertising
@@ -1454,7 +1454,7 @@ static int hci_dev_do_open(struct hci_dev *hdev)
 		}
 
 		/* Check for valid public address or a configured static
-		 * random adddress, but let the HCI setup proceed to
+		 * random address, but let the HCI setup proceed to
 		 * be able to determine if there is a public address
 		 * or not.
 		 *
@@ -3549,7 +3549,7 @@ void hci_conn_params_clear_disabled(struct hci_dev *hdev)
 		if (params->auto_connect != HCI_AUTO_CONN_DISABLED)
 			continue;
 
-		/* If trying to estabilish one time connection to disabled
+		/* If trying to establish one time connection to disabled
 		 * device, leave the params, but mark them as just once.
 		 */
 		if (params->explicit_connect) {
@@ -4284,7 +4284,7 @@ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode)
 	return hdev->sent_cmd->data + HCI_COMMAND_HDR_SIZE;
 }
 
-/* Send HCI command and wait for command commplete event */
+/* Send HCI command and wait for command complete event */
 struct sk_buff *hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen,
 			     const void *param, u32 timeout)
 {
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 016b2999f219..ea06b010ccad 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -6032,7 +6032,7 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode,
 		return true;
 	}
 
-	/* Check if request ended in Command Status - no way to retreive
+	/* Check if request ended in Command Status - no way to retrieve
 	 * any extra parameters in this case.
 	 */
 	if (hdr->evt == HCI_EV_CMD_STATUS)
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index eed0dd066e12..e8d53af7c6a6 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -1130,7 +1130,7 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr,
 		if (!hci_sock_gen_cookie(sk)) {
 			/* In the case when a cookie has already been assigned,
 			 * then there has been already an ioctl issued against
-			 * an unbound socket and with that triggerd an open
+			 * an unbound socket and with that triggered an open
 			 * notification. Send a close notification first to
 			 * allow the state transition to bounded.
 			 */
@@ -1326,9 +1326,9 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr,
 		if (hci_pi(sk)->channel == HCI_CHANNEL_CONTROL) {
 			if (!hci_sock_gen_cookie(sk)) {
 				/* In the case when a cookie has already been
-				 * assigned, this socket will transtion from
+				 * assigned, this socket will transition from
 				 * a raw socket into a control socket. To
-				 * allow for a clean transtion, send the
+				 * allow for a clean transition, send the
 				 * close notification first.
 				 */
 				skb = create_monitor_ctrl_close(sk);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index f9be7f9084d6..f290d0c54d32 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3341,7 +3341,7 @@ static int set_local_name(struct sock *sk, struct hci_dev *hdev, void *data,
 	}
 
 	/* The name is stored in the scan response data and so
-	 * no need to udpate the advertising data here.
+	 * no need to update the advertising data here.
 	 */
 	if (lmp_le_capable(hdev) && hci_dev_test_flag(hdev, HCI_ADVERTISING))
 		__hci_req_update_scan_rsp_data(&req, hdev->cur_adv_instance);
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 7dd51da73845..4d93c6c32a71 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -40,7 +40,7 @@
 	((struct smp_dev *)((struct l2cap_chan *)((hdev)->smp_data))->data)
 
 /* Low-level debug macros to be used for stuff that we don't want
- * accidentially in dmesg, i.e. the values of the various crypto keys
+ * accidentally in dmesg, i.e. the values of the various crypto keys
  * and the inputs & outputs of crypto functions.
  */
 #ifdef DEBUG
@@ -560,7 +560,7 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16])
 				return err;
 
 			/* This is unlikely, but we need to check that
-			 * we didn't accidentially generate a debug key.
+			 * we didn't accidentally generate a debug key.
 			 */
 			if (crypto_memneq(smp->local_pk, debug_pk, 64))
 				break;
@@ -1902,7 +1902,7 @@ static u8 sc_send_public_key(struct smp_chan *smp)
 				return SMP_UNSPECIFIED;
 
 			/* This is unlikely, but we need to check that
-			 * we didn't accidentially generate a debug key.
+			 * we didn't accidentally generate a debug key.
 			 */
 			if (crypto_memneq(smp->local_pk, debug_pk, 64))
 				break;
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index a5d72c48fb66..aa47af349ba8 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -409,7 +409,7 @@ static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size)
 		return ERR_PTR(-ENOMEM);
 
 	if (data_in) {
-		err = bpf_check_uarg_tail_zero(data_in, max_size, size);
+		err = bpf_check_uarg_tail_zero(USER_BPFPTR(data_in), max_size, size);
 		if (err) {
 			kfree(data);
 			return ERR_PTR(err);
@@ -918,3 +918,46 @@ out:
 	kfree(user_ctx);
 	return ret;
 }
+
+int bpf_prog_test_run_syscall(struct bpf_prog *prog,
+			      const union bpf_attr *kattr,
+			      union bpf_attr __user *uattr)
+{
+	void __user *ctx_in = u64_to_user_ptr(kattr->test.ctx_in);
+	__u32 ctx_size_in = kattr->test.ctx_size_in;
+	void *ctx = NULL;
+	u32 retval;
+	int err = 0;
+
+	/* doesn't support data_in/out, ctx_out, duration, or repeat or flags */
+	if (kattr->test.data_in || kattr->test.data_out ||
+	    kattr->test.ctx_out || kattr->test.duration ||
+	    kattr->test.repeat || kattr->test.flags)
+		return -EINVAL;
+
+	if (ctx_size_in < prog->aux->max_ctx_offset ||
+	    ctx_size_in > U16_MAX)
+		return -EINVAL;
+
+	if (ctx_size_in) {
+		ctx = kzalloc(ctx_size_in, GFP_USER);
+		if (!ctx)
+			return -ENOMEM;
+		if (copy_from_user(ctx, ctx_in, ctx_size_in)) {
+			err = -EFAULT;
+			goto out;
+		}
+	}
+	retval = bpf_prog_run_pin_on_cpu(prog, ctx);
+
+	if (copy_to_user(&uattr->test.retval, &retval, sizeof(u32))) {
+		err = -EFAULT;
+		goto out;
+	}
+	if (ctx_size_in)
+		if (copy_to_user(ctx_in, ctx, ctx_size_in))
+			err = -EFAULT;
+out:
+	kfree(ctx);
+	return err;
+}
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 6e9b049ae521..07856362538f 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -276,7 +276,8 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
 	bool allow_mode_include = true;
 	struct hlist_node *rp;
 
-	rp = rcu_dereference(hlist_first_rcu(&br->router_list));
+	rp = br_multicast_get_first_rport_node(br, skb);
+
 	if (mdst) {
 		p = rcu_dereference(mdst->ports);
 		if (br_multicast_should_handle_mode(br, mdst->addr.proto) &&
@@ -290,7 +291,7 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
 		struct net_bridge_port *port, *lport, *rport;
 
 		lport = p ? p->key.port : NULL;
-		rport = hlist_entry_safe(rp, struct net_bridge_port, rlist);
+		rport = br_multicast_rport_from_node_skb(rp, skb);
 
 		if ((unsigned long)lport > (unsigned long)rport) {
 			port = lport;
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 8875e953ac53..1f506309efa8 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -132,7 +132,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 		if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
 		    br_multicast_querier_exists(br, eth_hdr(skb), mdst)) {
 			if ((mdst && mdst->host_joined) ||
-			    br_multicast_is_router(br)) {
+			    br_multicast_is_router(br, skb)) {
 				local_rcv = true;
 				br->dev->stats.multicast++;
 			}
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 95fa4af0e8dd..3f839a8cc9fb 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -16,31 +16,76 @@
 
 #include "br_private.h"
 
+static bool br_rports_have_mc_router(struct net_bridge *br)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	return !hlist_empty(&br->ip4_mc_router_list) ||
+	       !hlist_empty(&br->ip6_mc_router_list);
+#else
+	return !hlist_empty(&br->ip4_mc_router_list);
+#endif
+}
+
+static bool
+br_ip4_rports_get_timer(struct net_bridge_port *port, unsigned long *timer)
+{
+	*timer = br_timer_value(&port->ip4_mc_router_timer);
+	return !hlist_unhashed(&port->ip4_rlist);
+}
+
+static bool
+br_ip6_rports_get_timer(struct net_bridge_port *port, unsigned long *timer)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	*timer = br_timer_value(&port->ip6_mc_router_timer);
+	return !hlist_unhashed(&port->ip6_rlist);
+#else
+	*timer = 0;
+	return false;
+#endif
+}
+
 static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
 			       struct net_device *dev)
 {
 	struct net_bridge *br = netdev_priv(dev);
-	struct net_bridge_port *p;
+	bool have_ip4_mc_rtr, have_ip6_mc_rtr;
+	unsigned long ip4_timer, ip6_timer;
 	struct nlattr *nest, *port_nest;
+	struct net_bridge_port *p;
 
-	if (!br->multicast_router || hlist_empty(&br->router_list))
+	if (!br->multicast_router)
+		return 0;
+
+	if (!br_rports_have_mc_router(br))
 		return 0;
 
 	nest = nla_nest_start_noflag(skb, MDBA_ROUTER);
 	if (nest == NULL)
 		return -EMSGSIZE;
 
-	hlist_for_each_entry_rcu(p, &br->router_list, rlist) {
-		if (!p)
+	list_for_each_entry_rcu(p, &br->port_list, list) {
+		have_ip4_mc_rtr = br_ip4_rports_get_timer(p, &ip4_timer);
+		have_ip6_mc_rtr = br_ip6_rports_get_timer(p, &ip6_timer);
+
+		if (!have_ip4_mc_rtr && !have_ip6_mc_rtr)
 			continue;
+
 		port_nest = nla_nest_start_noflag(skb, MDBA_ROUTER_PORT);
 		if (!port_nest)
 			goto fail;
+
 		if (nla_put_nohdr(skb, sizeof(u32), &p->dev->ifindex) ||
 		    nla_put_u32(skb, MDBA_ROUTER_PATTR_TIMER,
-				br_timer_value(&p->multicast_router_timer)) ||
+				max(ip4_timer, ip6_timer)) ||
 		    nla_put_u8(skb, MDBA_ROUTER_PATTR_TYPE,
-			       p->multicast_router)) {
+			       p->multicast_router) ||
+		    (have_ip4_mc_rtr &&
+		     nla_put_u32(skb, MDBA_ROUTER_PATTR_INET_TIMER,
+				 ip4_timer)) ||
+		    (have_ip6_mc_rtr &&
+		     nla_put_u32(skb, MDBA_ROUTER_PATTR_INET6_TIMER,
+				 ip6_timer))) {
 			nla_nest_cancel(skb, port_nest);
 			goto fail;
 		}
diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c
index cd2b1e424e54..f7012b7d7ce4 100644
--- a/net/bridge/br_mrp.c
+++ b/net/bridge/br_mrp.c
@@ -627,8 +627,7 @@ int br_mrp_set_ring_state(struct net_bridge *br,
 	if (!mrp)
 		return -EINVAL;
 
-	if (mrp->ring_state == BR_MRP_RING_STATE_CLOSED &&
-	    state->ring_state != BR_MRP_RING_STATE_CLOSED)
+	if (mrp->ring_state != state->ring_state)
 		mrp->ring_transitions++;
 
 	mrp->ring_state = state->ring_state;
@@ -715,8 +714,7 @@ int br_mrp_set_in_state(struct net_bridge *br, struct br_mrp_in_state *state)
 	if (!mrp)
 		return -EINVAL;
 
-	if (mrp->in_state == BR_MRP_IN_STATE_CLOSED &&
-	    state->in_state != BR_MRP_IN_STATE_CLOSED)
+	if (mrp->in_state != state->in_state)
 		mrp->in_transitions++;
 
 	mrp->in_state = state->in_state;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 226bb05c3b42..53c3a9d80d9c 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -51,8 +51,8 @@ static const struct rhashtable_params br_sg_port_rht_params = {
 
 static void br_multicast_start_querier(struct net_bridge *br,
 				       struct bridge_mcast_own_query *query);
-static void br_multicast_add_router(struct net_bridge *br,
-				    struct net_bridge_port *port);
+static void br_ip4_multicast_add_router(struct net_bridge *br,
+					struct net_bridge_port *port);
 static void br_ip4_multicast_leave_group(struct net_bridge *br,
 					 struct net_bridge_port *port,
 					 __be32 group,
@@ -60,7 +60,10 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br,
 					 const unsigned char *src);
 static void br_multicast_port_group_rexmit(struct timer_list *t);
 
-static void __del_port_router(struct net_bridge_port *p);
+static void
+br_multicast_rport_del_notify(struct net_bridge_port *p, bool deleted);
+static void br_ip6_multicast_add_router(struct net_bridge *br,
+					struct net_bridge_port *port);
 #if IS_ENABLED(CONFIG_IPV6)
 static void br_ip6_multicast_leave_group(struct net_bridge *br,
 					 struct net_bridge_port *port,
@@ -1354,23 +1357,64 @@ static int br_ip6_multicast_add_group(struct net_bridge *br,
 }
 #endif
 
-static void br_multicast_router_expired(struct timer_list *t)
+static bool br_multicast_rport_del(struct hlist_node *rlist)
+{
+	if (hlist_unhashed(rlist))
+		return false;
+
+	hlist_del_init_rcu(rlist);
+	return true;
+}
+
+static bool br_ip4_multicast_rport_del(struct net_bridge_port *p)
+{
+	return br_multicast_rport_del(&p->ip4_rlist);
+}
+
+static bool br_ip6_multicast_rport_del(struct net_bridge_port *p)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	return br_multicast_rport_del(&p->ip6_rlist);
+#else
+	return false;
+#endif
+}
+
+static void br_multicast_router_expired(struct net_bridge_port *port,
+					struct timer_list *t,
+					struct hlist_node *rlist)
 {
-	struct net_bridge_port *port =
-			from_timer(port, t, multicast_router_timer);
 	struct net_bridge *br = port->br;
+	bool del;
 
 	spin_lock(&br->multicast_lock);
 	if (port->multicast_router == MDB_RTR_TYPE_DISABLED ||
 	    port->multicast_router == MDB_RTR_TYPE_PERM ||
-	    timer_pending(&port->multicast_router_timer))
+	    timer_pending(t))
 		goto out;
 
-	__del_port_router(port);
+	del = br_multicast_rport_del(rlist);
+	br_multicast_rport_del_notify(port, del);
 out:
 	spin_unlock(&br->multicast_lock);
 }
 
+static void br_ip4_multicast_router_expired(struct timer_list *t)
+{
+	struct net_bridge_port *port = from_timer(port, t, ip4_mc_router_timer);
+
+	br_multicast_router_expired(port, t, &port->ip4_rlist);
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static void br_ip6_multicast_router_expired(struct timer_list *t)
+{
+	struct net_bridge_port *port = from_timer(port, t, ip6_mc_router_timer);
+
+	br_multicast_router_expired(port, t, &port->ip6_rlist);
+}
+#endif
+
 static void br_mc_router_state_change(struct net_bridge *p,
 				      bool is_mc_router)
 {
@@ -1384,14 +1428,14 @@ static void br_mc_router_state_change(struct net_bridge *p,
 	switchdev_port_attr_set(p->dev, &attr, NULL);
 }
 
-static void br_multicast_local_router_expired(struct timer_list *t)
+static void br_multicast_local_router_expired(struct net_bridge *br,
+					      struct timer_list *timer)
 {
-	struct net_bridge *br = from_timer(br, t, multicast_router_timer);
-
 	spin_lock(&br->multicast_lock);
 	if (br->multicast_router == MDB_RTR_TYPE_DISABLED ||
 	    br->multicast_router == MDB_RTR_TYPE_PERM ||
-	    timer_pending(&br->multicast_router_timer))
+	    br_ip4_multicast_is_router(br) ||
+	    br_ip6_multicast_is_router(br))
 		goto out;
 
 	br_mc_router_state_change(br, false);
@@ -1399,6 +1443,22 @@ out:
 	spin_unlock(&br->multicast_lock);
 }
 
+static void br_ip4_multicast_local_router_expired(struct timer_list *t)
+{
+	struct net_bridge *br = from_timer(br, t, ip4_mc_router_timer);
+
+	br_multicast_local_router_expired(br, t);
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static void br_ip6_multicast_local_router_expired(struct timer_list *t)
+{
+	struct net_bridge *br = from_timer(br, t, ip6_mc_router_timer);
+
+	br_multicast_local_router_expired(br, t);
+}
+#endif
+
 static void br_multicast_querier_expired(struct net_bridge *br,
 					 struct bridge_mcast_own_query *query)
 {
@@ -1613,11 +1673,13 @@ int br_multicast_add_port(struct net_bridge_port *port)
 	port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY;
 	port->multicast_eht_hosts_limit = BR_MCAST_DEFAULT_EHT_HOSTS_LIMIT;
 
-	timer_setup(&port->multicast_router_timer,
-		    br_multicast_router_expired, 0);
+	timer_setup(&port->ip4_mc_router_timer,
+		    br_ip4_multicast_router_expired, 0);
 	timer_setup(&port->ip4_own_query.timer,
 		    br_ip4_multicast_port_query_expired, 0);
 #if IS_ENABLED(CONFIG_IPV6)
+	timer_setup(&port->ip6_mc_router_timer,
+		    br_ip6_multicast_router_expired, 0);
 	timer_setup(&port->ip6_own_query.timer,
 		    br_ip6_multicast_port_query_expired, 0);
 #endif
@@ -1649,7 +1711,10 @@ void br_multicast_del_port(struct net_bridge_port *port)
 	hlist_move_list(&br->mcast_gc_list, &deleted_head);
 	spin_unlock_bh(&br->multicast_lock);
 	br_multicast_gc(&deleted_head);
-	del_timer_sync(&port->multicast_router_timer);
+	del_timer_sync(&port->ip4_mc_router_timer);
+#if IS_ENABLED(CONFIG_IPV6)
+	del_timer_sync(&port->ip6_mc_router_timer);
+#endif
 	free_percpu(port->mcast_stats);
 }
 
@@ -1673,9 +1738,10 @@ static void __br_multicast_enable_port(struct net_bridge_port *port)
 #if IS_ENABLED(CONFIG_IPV6)
 	br_multicast_enable(&port->ip6_own_query);
 #endif
-	if (port->multicast_router == MDB_RTR_TYPE_PERM &&
-	    hlist_unhashed(&port->rlist))
-		br_multicast_add_router(br, port);
+	if (port->multicast_router == MDB_RTR_TYPE_PERM) {
+		br_ip4_multicast_add_router(br, port);
+		br_ip6_multicast_add_router(br, port);
+	}
 }
 
 void br_multicast_enable_port(struct net_bridge_port *port)
@@ -1692,19 +1758,22 @@ void br_multicast_disable_port(struct net_bridge_port *port)
 	struct net_bridge *br = port->br;
 	struct net_bridge_port_group *pg;
 	struct hlist_node *n;
+	bool del = false;
 
 	spin_lock(&br->multicast_lock);
 	hlist_for_each_entry_safe(pg, n, &port->mglist, mglist)
 		if (!(pg->flags & MDB_PG_FLAGS_PERMANENT))
 			br_multicast_find_del_pg(br, pg);
 
-	__del_port_router(port);
-
-	del_timer(&port->multicast_router_timer);
+	del |= br_ip4_multicast_rport_del(port);
+	del_timer(&port->ip4_mc_router_timer);
 	del_timer(&port->ip4_own_query.timer);
+	del |= br_ip6_multicast_rport_del(port);
 #if IS_ENABLED(CONFIG_IPV6)
+	del_timer(&port->ip6_mc_router_timer);
 	del_timer(&port->ip6_own_query.timer);
 #endif
+	br_multicast_rport_del_notify(port, del);
 	spin_unlock(&br->multicast_lock);
 }
 
@@ -2615,22 +2684,6 @@ update:
 }
 #endif
 
-static bool br_multicast_select_querier(struct net_bridge *br,
-					struct net_bridge_port *port,
-					struct br_ip *saddr)
-{
-	switch (saddr->proto) {
-	case htons(ETH_P_IP):
-		return br_ip4_multicast_select_querier(br, port, saddr->src.ip4);
-#if IS_ENABLED(CONFIG_IPV6)
-	case htons(ETH_P_IPV6):
-		return br_ip6_multicast_select_querier(br, port, &saddr->src.ip6);
-#endif
-	}
-
-	return false;
-}
-
 static void
 br_multicast_update_query_timer(struct net_bridge *br,
 				struct bridge_mcast_other_query *query,
@@ -2655,45 +2708,122 @@ static void br_port_mc_router_state_change(struct net_bridge_port *p,
 	switchdev_port_attr_set(p->dev, &attr, NULL);
 }
 
-/*
- * Add port to router_list
+static struct net_bridge_port *
+br_multicast_rport_from_node(struct net_bridge *br,
+			     struct hlist_head *mc_router_list,
+			     struct hlist_node *rlist)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	if (mc_router_list == &br->ip6_mc_router_list)
+		return hlist_entry(rlist, struct net_bridge_port, ip6_rlist);
+#endif
+	return hlist_entry(rlist, struct net_bridge_port, ip4_rlist);
+}
+
+static struct hlist_node *
+br_multicast_get_rport_slot(struct net_bridge *br,
+			    struct net_bridge_port *port,
+			    struct hlist_head *mc_router_list)
+
+{
+	struct hlist_node *slot = NULL;
+	struct net_bridge_port *p;
+	struct hlist_node *rlist;
+
+	hlist_for_each(rlist, mc_router_list) {
+		p = br_multicast_rport_from_node(br, mc_router_list, rlist);
+
+		if ((unsigned long)port >= (unsigned long)p)
+			break;
+
+		slot = rlist;
+	}
+
+	return slot;
+}
+
+static bool br_multicast_no_router_otherpf(struct net_bridge_port *port,
+					   struct hlist_node *rnode)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	if (rnode != &port->ip6_rlist)
+		return hlist_unhashed(&port->ip6_rlist);
+	else
+		return hlist_unhashed(&port->ip4_rlist);
+#else
+	return true;
+#endif
+}
+
+/* Add port to router_list
  *  list is maintained ordered by pointer value
  *  and locked by br->multicast_lock and RCU
  */
 static void br_multicast_add_router(struct net_bridge *br,
-				    struct net_bridge_port *port)
+				    struct net_bridge_port *port,
+				    struct hlist_node *rlist,
+				    struct hlist_head *mc_router_list)
 {
-	struct net_bridge_port *p;
-	struct hlist_node *slot = NULL;
+	struct hlist_node *slot;
 
-	if (!hlist_unhashed(&port->rlist))
+	if (!hlist_unhashed(rlist))
 		return;
 
-	hlist_for_each_entry(p, &br->router_list, rlist) {
-		if ((unsigned long) port >= (unsigned long) p)
-			break;
-		slot = &p->rlist;
-	}
+	slot = br_multicast_get_rport_slot(br, port, mc_router_list);
 
 	if (slot)
-		hlist_add_behind_rcu(&port->rlist, slot);
+		hlist_add_behind_rcu(rlist, slot);
 	else
-		hlist_add_head_rcu(&port->rlist, &br->router_list);
-	br_rtr_notify(br->dev, port, RTM_NEWMDB);
-	br_port_mc_router_state_change(port, true);
+		hlist_add_head_rcu(rlist, mc_router_list);
+
+	/* For backwards compatibility for now, only notify if we
+	 * switched from no IPv4/IPv6 multicast router to a new
+	 * IPv4 or IPv6 multicast router.
+	 */
+	if (br_multicast_no_router_otherpf(port, rlist)) {
+		br_rtr_notify(br->dev, port, RTM_NEWMDB);
+		br_port_mc_router_state_change(port, true);
+	}
+}
+
+/* Add port to router_list
+ *  list is maintained ordered by pointer value
+ *  and locked by br->multicast_lock and RCU
+ */
+static void br_ip4_multicast_add_router(struct net_bridge *br,
+					struct net_bridge_port *port)
+{
+	br_multicast_add_router(br, port, &port->ip4_rlist,
+				&br->ip4_mc_router_list);
+}
+
+/* Add port to router_list
+ *  list is maintained ordered by pointer value
+ *  and locked by br->multicast_lock and RCU
+ */
+static void br_ip6_multicast_add_router(struct net_bridge *br,
+					struct net_bridge_port *port)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	br_multicast_add_router(br, port, &port->ip6_rlist,
+				&br->ip6_mc_router_list);
+#endif
 }
 
 static void br_multicast_mark_router(struct net_bridge *br,
-				     struct net_bridge_port *port)
+				     struct net_bridge_port *port,
+				     struct timer_list *timer,
+				     struct hlist_node *rlist,
+				     struct hlist_head *mc_router_list)
 {
 	unsigned long now = jiffies;
 
 	if (!port) {
 		if (br->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) {
-			if (!timer_pending(&br->multicast_router_timer))
+			if (!br_ip4_multicast_is_router(br) &&
+			    !br_ip6_multicast_is_router(br))
 				br_mc_router_state_change(br, true);
-			mod_timer(&br->multicast_router_timer,
-				  now + br->multicast_querier_interval);
+			mod_timer(timer, now + br->multicast_querier_interval);
 		}
 		return;
 	}
@@ -2702,24 +2832,71 @@ static void br_multicast_mark_router(struct net_bridge *br,
 	    port->multicast_router == MDB_RTR_TYPE_PERM)
 		return;
 
-	br_multicast_add_router(br, port);
+	br_multicast_add_router(br, port, rlist, mc_router_list);
+	mod_timer(timer, now + br->multicast_querier_interval);
+}
+
+static void br_ip4_multicast_mark_router(struct net_bridge *br,
+					 struct net_bridge_port *port)
+{
+	struct timer_list *timer = &br->ip4_mc_router_timer;
+	struct hlist_node *rlist = NULL;
+
+	if (port) {
+		timer = &port->ip4_mc_router_timer;
+		rlist = &port->ip4_rlist;
+	}
 
-	mod_timer(&port->multicast_router_timer,
-		  now + br->multicast_querier_interval);
+	br_multicast_mark_router(br, port, timer, rlist,
+				 &br->ip4_mc_router_list);
 }
 
-static void br_multicast_query_received(struct net_bridge *br,
-					struct net_bridge_port *port,
-					struct bridge_mcast_other_query *query,
-					struct br_ip *saddr,
-					unsigned long max_delay)
+static void br_ip6_multicast_mark_router(struct net_bridge *br,
+					 struct net_bridge_port *port)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	struct timer_list *timer = &br->ip6_mc_router_timer;
+	struct hlist_node *rlist = NULL;
+
+	if (port) {
+		timer = &port->ip6_mc_router_timer;
+		rlist = &port->ip6_rlist;
+	}
+
+	br_multicast_mark_router(br, port, timer, rlist,
+				 &br->ip6_mc_router_list);
+#endif
+}
+
+static void
+br_ip4_multicast_query_received(struct net_bridge *br,
+				struct net_bridge_port *port,
+				struct bridge_mcast_other_query *query,
+				struct br_ip *saddr,
+				unsigned long max_delay)
+{
+	if (!br_ip4_multicast_select_querier(br, port, saddr->src.ip4))
+		return;
+
+	br_multicast_update_query_timer(br, query, max_delay);
+	br_ip4_multicast_mark_router(br, port);
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static void
+br_ip6_multicast_query_received(struct net_bridge *br,
+				struct net_bridge_port *port,
+				struct bridge_mcast_other_query *query,
+				struct br_ip *saddr,
+				unsigned long max_delay)
 {
-	if (!br_multicast_select_querier(br, port, saddr))
+	if (!br_ip6_multicast_select_querier(br, port, &saddr->src.ip6))
 		return;
 
 	br_multicast_update_query_timer(br, query, max_delay);
-	br_multicast_mark_router(br, port);
+	br_ip6_multicast_mark_router(br, port);
 }
+#endif
 
 static void br_ip4_multicast_query(struct net_bridge *br,
 				   struct net_bridge_port *port,
@@ -2768,8 +2945,8 @@ static void br_ip4_multicast_query(struct net_bridge *br,
 		saddr.proto = htons(ETH_P_IP);
 		saddr.src.ip4 = iph->saddr;
 
-		br_multicast_query_received(br, port, &br->ip4_other_query,
-					    &saddr, max_delay);
+		br_ip4_multicast_query_received(br, port, &br->ip4_other_query,
+						&saddr, max_delay);
 		goto out;
 	}
 
@@ -2856,8 +3033,8 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 		saddr.proto = htons(ETH_P_IPV6);
 		saddr.src.ip6 = ipv6_hdr(skb)->saddr;
 
-		br_multicast_query_received(br, port, &br->ip6_other_query,
-					    &saddr, max_delay);
+		br_ip6_multicast_query_received(br, port, &br->ip6_other_query,
+						&saddr, max_delay);
 		goto out;
 	} else if (!group) {
 		goto out;
@@ -3087,7 +3264,7 @@ static void br_multicast_pim(struct net_bridge *br,
 	    pim_hdr_type(pimhdr) != PIM_TYPE_HELLO)
 		return;
 
-	br_multicast_mark_router(br, port);
+	br_ip4_multicast_mark_router(br, port);
 }
 
 static int br_ip4_multicast_mrd_rcv(struct net_bridge *br,
@@ -3098,7 +3275,7 @@ static int br_ip4_multicast_mrd_rcv(struct net_bridge *br,
 	    igmp_hdr(skb)->type != IGMP_MRDISC_ADV)
 		return -ENOMSG;
 
-	br_multicast_mark_router(br, port);
+	br_ip4_multicast_mark_router(br, port);
 
 	return 0;
 }
@@ -3166,7 +3343,7 @@ static void br_ip6_multicast_mrd_rcv(struct net_bridge *br,
 	if (icmp6_hdr(skb)->icmp6_type != ICMPV6_MRDISC_ADV)
 		return;
 
-	br_multicast_mark_router(br, port);
+	br_ip6_multicast_mark_router(br, port);
 }
 
 static int br_multicast_ipv6_rcv(struct net_bridge *br,
@@ -3316,13 +3493,15 @@ void br_multicast_init(struct net_bridge *br)
 	br_opt_toggle(br, BROPT_HAS_IPV6_ADDR, true);
 
 	spin_lock_init(&br->multicast_lock);
-	timer_setup(&br->multicast_router_timer,
-		    br_multicast_local_router_expired, 0);
+	timer_setup(&br->ip4_mc_router_timer,
+		    br_ip4_multicast_local_router_expired, 0);
 	timer_setup(&br->ip4_other_query.timer,
 		    br_ip4_multicast_querier_expired, 0);
 	timer_setup(&br->ip4_own_query.timer,
 		    br_ip4_multicast_query_expired, 0);
 #if IS_ENABLED(CONFIG_IPV6)
+	timer_setup(&br->ip6_mc_router_timer,
+		    br_ip6_multicast_local_router_expired, 0);
 	timer_setup(&br->ip6_other_query.timer,
 		    br_ip6_multicast_querier_expired, 0);
 	timer_setup(&br->ip6_own_query.timer,
@@ -3416,10 +3595,11 @@ void br_multicast_open(struct net_bridge *br)
 
 void br_multicast_stop(struct net_bridge *br)
 {
-	del_timer_sync(&br->multicast_router_timer);
+	del_timer_sync(&br->ip4_mc_router_timer);
 	del_timer_sync(&br->ip4_other_query.timer);
 	del_timer_sync(&br->ip4_own_query.timer);
 #if IS_ENABLED(CONFIG_IPV6)
+	del_timer_sync(&br->ip6_mc_router_timer);
 	del_timer_sync(&br->ip6_other_query.timer);
 	del_timer_sync(&br->ip6_own_query.timer);
 #endif
@@ -3453,7 +3633,10 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val)
 	case MDB_RTR_TYPE_DISABLED:
 	case MDB_RTR_TYPE_PERM:
 		br_mc_router_state_change(br, val == MDB_RTR_TYPE_PERM);
-		del_timer(&br->multicast_router_timer);
+		del_timer(&br->ip4_mc_router_timer);
+#if IS_ENABLED(CONFIG_IPV6)
+		del_timer(&br->ip6_mc_router_timer);
+#endif
 		br->multicast_router = val;
 		err = 0;
 		break;
@@ -3470,11 +3653,22 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val)
 	return err;
 }
 
-static void __del_port_router(struct net_bridge_port *p)
+static void
+br_multicast_rport_del_notify(struct net_bridge_port *p, bool deleted)
 {
-	if (hlist_unhashed(&p->rlist))
+	if (!deleted)
+		return;
+
+	/* For backwards compatibility for now, only notify if there is
+	 * no multicast router anymore for both IPv4 and IPv6.
+	 */
+	if (!hlist_unhashed(&p->ip4_rlist))
 		return;
-	hlist_del_init_rcu(&p->rlist);
+#if IS_ENABLED(CONFIG_IPV6)
+	if (!hlist_unhashed(&p->ip6_rlist))
+		return;
+#endif
+
 	br_rtr_notify(p->br->dev, p, RTM_DELMDB);
 	br_port_mc_router_state_change(p, false);
 
@@ -3488,34 +3682,52 @@ int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val)
 	struct net_bridge *br = p->br;
 	unsigned long now = jiffies;
 	int err = -EINVAL;
+	bool del = false;
 
 	spin_lock(&br->multicast_lock);
 	if (p->multicast_router == val) {
 		/* Refresh the temp router port timer */
-		if (p->multicast_router == MDB_RTR_TYPE_TEMP)
-			mod_timer(&p->multicast_router_timer,
+		if (p->multicast_router == MDB_RTR_TYPE_TEMP) {
+			mod_timer(&p->ip4_mc_router_timer,
 				  now + br->multicast_querier_interval);
+#if IS_ENABLED(CONFIG_IPV6)
+			mod_timer(&p->ip6_mc_router_timer,
+				  now + br->multicast_querier_interval);
+#endif
+		}
 		err = 0;
 		goto unlock;
 	}
 	switch (val) {
 	case MDB_RTR_TYPE_DISABLED:
 		p->multicast_router = MDB_RTR_TYPE_DISABLED;
-		__del_port_router(p);
-		del_timer(&p->multicast_router_timer);
+		del |= br_ip4_multicast_rport_del(p);
+		del_timer(&p->ip4_mc_router_timer);
+		del |= br_ip6_multicast_rport_del(p);
+#if IS_ENABLED(CONFIG_IPV6)
+		del_timer(&p->ip6_mc_router_timer);
+#endif
+		br_multicast_rport_del_notify(p, del);
 		break;
 	case MDB_RTR_TYPE_TEMP_QUERY:
 		p->multicast_router = MDB_RTR_TYPE_TEMP_QUERY;
-		__del_port_router(p);
+		del |= br_ip4_multicast_rport_del(p);
+		del |= br_ip6_multicast_rport_del(p);
+		br_multicast_rport_del_notify(p, del);
 		break;
 	case MDB_RTR_TYPE_PERM:
 		p->multicast_router = MDB_RTR_TYPE_PERM;
-		del_timer(&p->multicast_router_timer);
-		br_multicast_add_router(br, p);
+		del_timer(&p->ip4_mc_router_timer);
+		br_ip4_multicast_add_router(br, p);
+#if IS_ENABLED(CONFIG_IPV6)
+		del_timer(&p->ip6_mc_router_timer);
+#endif
+		br_ip6_multicast_add_router(br, p);
 		break;
 	case MDB_RTR_TYPE_TEMP:
 		p->multicast_router = MDB_RTR_TYPE_TEMP;
-		br_multicast_mark_router(br, p);
+		br_ip4_multicast_mark_router(br, p);
+		br_ip6_multicast_mark_router(br, p);
 		break;
 	default:
 		goto unlock;
@@ -3621,7 +3833,7 @@ bool br_multicast_router(const struct net_device *dev)
 	bool is_router;
 
 	spin_lock_bh(&br->multicast_lock);
-	is_router = br_multicast_is_router(br);
+	is_router = br_multicast_is_router(br, NULL);
 	spin_unlock_bh(&br->multicast_lock);
 	return is_router;
 }
@@ -3842,6 +4054,61 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(br_multicast_has_querier_adjacent);
 
+/**
+ * br_multicast_has_router_adjacent - Checks for a router behind a bridge port
+ * @dev: The bridge port adjacent to which to check for a multicast router
+ * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6
+ *
+ * Checks whether the given interface has a bridge on top and if so returns
+ * true if a multicast router is behind one of the other ports of this
+ * bridge. Otherwise returns false.
+ */
+bool br_multicast_has_router_adjacent(struct net_device *dev, int proto)
+{
+	struct net_bridge_port *port, *p;
+	bool ret = false;
+
+	rcu_read_lock();
+	port = br_port_get_check_rcu(dev);
+	if (!port)
+		goto unlock;
+
+	switch (proto) {
+	case ETH_P_IP:
+		hlist_for_each_entry_rcu(p, &port->br->ip4_mc_router_list,
+					 ip4_rlist) {
+			if (p == port)
+				continue;
+
+			ret = true;
+			goto unlock;
+		}
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case ETH_P_IPV6:
+		hlist_for_each_entry_rcu(p, &port->br->ip6_mc_router_list,
+					 ip6_rlist) {
+			if (p == port)
+				continue;
+
+			ret = true;
+			goto unlock;
+		}
+		break;
+#endif
+	default:
+		/* when compiled without IPv6 support, be conservative and
+		 * always assume presence of an IPv6 multicast router
+		 */
+		ret = true;
+	}
+
+unlock:
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(br_multicast_has_router_adjacent);
+
 static void br_mcast_stats_add(struct bridge_mcast_stats __percpu *stats,
 			       const struct sk_buff *skb, u8 type, u8 dir)
 {
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index e4e6e991313e..8642e56059fb 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1644,7 +1644,6 @@ static size_t br_get_linkxstats_size(const struct net_device *dev, int attr)
 		p = br_port_get_rtnl(dev);
 		if (!p)
 			return 0;
-		br = p->br;
 		vg = nbp_vlan_group(p);
 		break;
 	default:
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index e013d33f1c7c..a684d0cfc58c 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -307,16 +307,18 @@ struct net_bridge_port {
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 	struct bridge_mcast_own_query	ip4_own_query;
+	struct timer_list		ip4_mc_router_timer;
+	struct hlist_node		ip4_rlist;
 #if IS_ENABLED(CONFIG_IPV6)
 	struct bridge_mcast_own_query	ip6_own_query;
+	struct timer_list		ip6_mc_router_timer;
+	struct hlist_node		ip6_rlist;
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 	u32				multicast_eht_hosts_limit;
 	u32				multicast_eht_hosts_cnt;
 	unsigned char			multicast_router;
 	struct bridge_mcast_stats	__percpu *mcast_stats;
-	struct timer_list		multicast_router_timer;
 	struct hlist_head		mglist;
-	struct hlist_node		rlist;
 #endif
 
 #ifdef CONFIG_SYSFS
@@ -449,14 +451,16 @@ struct net_bridge {
 
 	struct hlist_head		mcast_gc_list;
 	struct hlist_head		mdb_list;
-	struct hlist_head		router_list;
 
-	struct timer_list		multicast_router_timer;
+	struct hlist_head		ip4_mc_router_list;
+	struct timer_list		ip4_mc_router_timer;
 	struct bridge_mcast_other_query	ip4_other_query;
 	struct bridge_mcast_own_query	ip4_own_query;
 	struct bridge_mcast_querier	ip4_querier;
 	struct bridge_mcast_stats	__percpu *mcast_stats;
 #if IS_ENABLED(CONFIG_IPV6)
+	struct hlist_head		ip6_mc_router_list;
+	struct timer_list		ip6_mc_router_timer;
 	struct bridge_mcast_other_query	ip6_other_query;
 	struct bridge_mcast_own_query	ip6_own_query;
 	struct bridge_mcast_querier	ip6_querier;
@@ -864,11 +868,58 @@ static inline bool br_group_is_l2(const struct br_ip *group)
 #define mlock_dereference(X, br) \
 	rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
 
-static inline bool br_multicast_is_router(struct net_bridge *br)
+static inline struct hlist_node *
+br_multicast_get_first_rport_node(struct net_bridge *b, struct sk_buff *skb) {
+#if IS_ENABLED(CONFIG_IPV6)
+	if (skb->protocol == htons(ETH_P_IPV6))
+		return rcu_dereference(hlist_first_rcu(&b->ip6_mc_router_list));
+#endif
+	return rcu_dereference(hlist_first_rcu(&b->ip4_mc_router_list));
+}
+
+static inline struct net_bridge_port *
+br_multicast_rport_from_node_skb(struct hlist_node *rp, struct sk_buff *skb) {
+#if IS_ENABLED(CONFIG_IPV6)
+	if (skb->protocol == htons(ETH_P_IPV6))
+		return hlist_entry_safe(rp, struct net_bridge_port, ip6_rlist);
+#endif
+	return hlist_entry_safe(rp, struct net_bridge_port, ip4_rlist);
+}
+
+static inline bool br_ip4_multicast_is_router(struct net_bridge *br)
+{
+	return timer_pending(&br->ip4_mc_router_timer);
+}
+
+static inline bool br_ip6_multicast_is_router(struct net_bridge *br)
 {
-	return br->multicast_router == 2 ||
-	       (br->multicast_router == 1 &&
-		timer_pending(&br->multicast_router_timer));
+#if IS_ENABLED(CONFIG_IPV6)
+	return timer_pending(&br->ip6_mc_router_timer);
+#else
+	return false;
+#endif
+}
+
+static inline bool
+br_multicast_is_router(struct net_bridge *br, struct sk_buff *skb)
+{
+	switch (br->multicast_router) {
+	case MDB_RTR_TYPE_PERM:
+		return true;
+	case MDB_RTR_TYPE_TEMP_QUERY:
+		if (skb) {
+			if (skb->protocol == htons(ETH_P_IP))
+				return br_ip4_multicast_is_router(br);
+			else if (skb->protocol == htons(ETH_P_IPV6))
+				return br_ip6_multicast_is_router(br);
+		} else {
+			return br_ip4_multicast_is_router(br) ||
+			       br_ip6_multicast_is_router(br);
+		}
+		fallthrough;
+	default:
+		return false;
+	}
 }
 
 static inline bool
@@ -1017,7 +1068,8 @@ static inline void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
 {
 }
 
-static inline bool br_multicast_is_router(struct net_bridge *br)
+static inline bool br_multicast_is_router(struct net_bridge *br,
+					  struct sk_buff *skb)
 {
 	return false;
 }
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index da3256a3eed0..8789a57af543 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -113,9 +113,7 @@ static void __vlan_add_list(struct net_bridge_vlan *v)
 	headp = &vg->vlan_list;
 	list_for_each_prev(hpos, headp) {
 		vent = list_entry(hpos, struct net_bridge_vlan, vlist);
-		if (v->vid < vent->vid)
-			continue;
-		else
+		if (v->vid >= vent->vid)
 			break;
 	}
 	list_add_rcu(&v->vlist, hpos);
diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c
index cac30e676ac9..23267c8db7c4 100644
--- a/net/caif/cfcnfg.c
+++ b/net/caif/cfcnfg.c
@@ -480,7 +480,7 @@ got_phyid:
 	phyinfo = kzalloc(sizeof(struct cfcnfg_phyinfo), GFP_ATOMIC);
 	if (!phyinfo) {
 		res = -ENOMEM;
-		goto out_err;
+		goto out;
 	}
 
 	phy_layer->id = phyid;
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index fadc7c8a3107..37b67194c0df 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -76,8 +76,6 @@ static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt)
 	u8 buf;
 
 	priv = container_of(layr, struct chnl_net, chnl);
-	if (!priv)
-		return -EINVAL;
 
 	skb = (struct sk_buff *) cfpkt_tonative(pkt);
 
diff --git a/net/can/isotp.c b/net/can/isotp.c
index be6183f8ca11..bd49299319a1 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -225,8 +225,8 @@ static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus)
 
 	can_send_ret = can_send(nskb, 1);
 	if (can_send_ret)
-		pr_notice_once("can-isotp: %s: can_send_ret %d\n",
-			       __func__, can_send_ret);
+		pr_notice_once("can-isotp: %s: can_send_ret %pe\n",
+			       __func__, ERR_PTR(can_send_ret));
 
 	dev_put(dev);
 
@@ -801,10 +801,12 @@ isotp_tx_burst:
 		can_skb_set_owner(skb, sk);
 
 		can_send_ret = can_send(skb, 1);
-		if (can_send_ret)
-			pr_notice_once("can-isotp: %s: can_send_ret %d\n",
-				       __func__, can_send_ret);
-
+		if (can_send_ret) {
+			pr_notice_once("can-isotp: %s: can_send_ret %pe\n",
+				       __func__, ERR_PTR(can_send_ret));
+			if (can_send_ret == -ENOBUFS)
+				pr_notice_once("can-isotp: tx queue is full, increasing txqueuelen may prevent this error\n");
+		}
 		if (so->tx.idx >= so->tx.len) {
 			/* we are done */
 			so->tx.state = ISOTP_IDLE;
@@ -950,8 +952,8 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	err = can_send(skb, 1);
 	dev_put(dev);
 	if (err) {
-		pr_notice_once("can-isotp: %s: can_send_ret %d\n",
-			       __func__, err);
+		pr_notice_once("can-isotp: %s: can_send_ret %pe\n",
+			       __func__, ERR_PTR(err));
 		return err;
 	}
 
@@ -1482,7 +1484,7 @@ static __init int isotp_module_init(void)
 
 	err = can_proto_register(&isotp_can_proto);
 	if (err < 0)
-		pr_err("can: registration of isotp protocol failed\n");
+		pr_err("can: registration of isotp protocol failed %pe\n", ERR_PTR(err));
 	else
 		register_netdevice_notifier(&canisotp_notifier);
 
diff --git a/net/can/proc.c b/net/can/proc.c
index d1fe49e6f16d..b3099f0a3cb8 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -99,8 +99,6 @@ static void can_init_stats(struct net *net)
 static unsigned long calc_rate(unsigned long oldjif, unsigned long newjif,
 			       unsigned long count)
 {
-	unsigned long rate;
-
 	if (oldjif == newjif)
 		return 0;
 
@@ -111,9 +109,7 @@ static unsigned long calc_rate(unsigned long oldjif, unsigned long newjif,
 		return 99999999;
 	}
 
-	rate = (count * HZ) / (newjif - oldjif);
-
-	return rate;
+	return (count * HZ) / (newjif - oldjif);
 }
 
 void can_stat_update(struct timer_list *t)
diff --git a/net/ceph/auth_x_protocol.h b/net/ceph/auth_x_protocol.h
index 792fcb974dc3..9c60feeb1bcb 100644
--- a/net/ceph/auth_x_protocol.h
+++ b/net/ceph/auth_x_protocol.h
@@ -87,7 +87,7 @@ struct ceph_x_authorize_reply {
 
 
 /*
- * encyption bundle
+ * encryption bundle
  */
 #define CEPHX_ENC_MAGIC 0xff009cad8826aa55ull
 
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 195ceb8afb06..013cbdb6cfe2 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -1508,7 +1508,7 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
 			return get_generic_reply(con, hdr, skip);
 
 		/*
-		 * Older OSDs don't set reply tid even if the orignal
+		 * Older OSDs don't set reply tid even if the original
 		 * request had a non-zero tid.  Work around this weirdness
 		 * by allocating a new message.
 		 */
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index c959320c4775..75b738083523 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1309,7 +1309,7 @@ static int get_osdmap_client_data_v(void **p, void *end,
 			return -EINVAL;
 		}
 
-		/* old osdmap enconding */
+		/* old osdmap encoding */
 		struct_v = 0;
 	}
 
@@ -3010,7 +3010,7 @@ static bool is_valid_crush_name(const char *name)
  * parent, returns 0.
  *
  * Does a linear search, as there are no parent pointers of any
- * kind.  Note that the result is ambigous for items that occur
+ * kind.  Note that the result is ambiguous for items that occur
  * multiple times in the map.
  */
 static int get_immediate_parent(struct crush_map *c, int id,
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index cc3712ad8716..f564f82e91d9 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -524,8 +524,7 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs)
 			nr_maps++;
 	}
 
-	diag = kzalloc(sizeof(*diag) + sizeof(diag->maps[0]) * nr_maps,
-		       GFP_KERNEL);
+	diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL);
 	if (!diag)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index ef8cf7619baf..50531a2d0b20 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6520,11 +6520,18 @@ EXPORT_SYMBOL(napi_schedule_prep);
  * __napi_schedule_irqoff - schedule for receive
  * @n: entry to schedule
  *
- * Variant of __napi_schedule() assuming hard irqs are masked
+ * Variant of __napi_schedule() assuming hard irqs are masked.
+ *
+ * On PREEMPT_RT enabled kernels this maps to __napi_schedule()
+ * because the interrupt disabled assumption might not be true
+ * due to force-threaded interrupts and spinlock substitution.
  */
 void __napi_schedule_irqoff(struct napi_struct *n)
 {
-	____napi_schedule(this_cpu_ptr(&softnet_data), n);
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		____napi_schedule(this_cpu_ptr(&softnet_data), n);
+	else
+		__napi_schedule(n);
 }
 EXPORT_SYMBOL(__napi_schedule_irqoff);
 
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 051432ea4f69..566ddd147633 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -190,6 +190,80 @@ static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink,
 	return devlink_port_get_from_attrs(devlink, info->attrs);
 }
 
+static inline bool
+devlink_rate_is_leaf(struct devlink_rate *devlink_rate)
+{
+	return devlink_rate->type == DEVLINK_RATE_TYPE_LEAF;
+}
+
+static inline bool
+devlink_rate_is_node(struct devlink_rate *devlink_rate)
+{
+	return devlink_rate->type == DEVLINK_RATE_TYPE_NODE;
+}
+
+static struct devlink_rate *
+devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info)
+{
+	struct devlink_rate *devlink_rate;
+	struct devlink_port *devlink_port;
+
+	devlink_port = devlink_port_get_from_attrs(devlink, info->attrs);
+	if (IS_ERR(devlink_port))
+		return ERR_CAST(devlink_port);
+	devlink_rate = devlink_port->devlink_rate;
+	return devlink_rate ?: ERR_PTR(-ENODEV);
+}
+
+static struct devlink_rate *
+devlink_rate_node_get_by_name(struct devlink *devlink, const char *node_name)
+{
+	static struct devlink_rate *devlink_rate;
+
+	list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
+		if (devlink_rate_is_node(devlink_rate) &&
+		    !strcmp(node_name, devlink_rate->name))
+			return devlink_rate;
+	}
+	return ERR_PTR(-ENODEV);
+}
+
+static struct devlink_rate *
+devlink_rate_node_get_from_attrs(struct devlink *devlink, struct nlattr **attrs)
+{
+	const char *rate_node_name;
+	size_t len;
+
+	if (!attrs[DEVLINK_ATTR_RATE_NODE_NAME])
+		return ERR_PTR(-EINVAL);
+	rate_node_name = nla_data(attrs[DEVLINK_ATTR_RATE_NODE_NAME]);
+	len = strlen(rate_node_name);
+	/* Name cannot be empty or decimal number */
+	if (!len || strspn(rate_node_name, "0123456789") == len)
+		return ERR_PTR(-EINVAL);
+
+	return devlink_rate_node_get_by_name(devlink, rate_node_name);
+}
+
+static struct devlink_rate *
+devlink_rate_node_get_from_info(struct devlink *devlink, struct genl_info *info)
+{
+	return devlink_rate_node_get_from_attrs(devlink, info->attrs);
+}
+
+static struct devlink_rate *
+devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info)
+{
+	struct nlattr **attrs = info->attrs;
+
+	if (attrs[DEVLINK_ATTR_PORT_INDEX])
+		return devlink_rate_leaf_get_from_info(devlink, info);
+	else if (attrs[DEVLINK_ATTR_RATE_NODE_NAME])
+		return devlink_rate_node_get_from_info(devlink, info);
+	else
+		return ERR_PTR(-EINVAL);
+}
+
 struct devlink_sb {
 	struct list_head list;
 	unsigned int index;
@@ -408,12 +482,14 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id)
 
 #define DEVLINK_NL_FLAG_NEED_PORT		BIT(0)
 #define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT	BIT(1)
+#define DEVLINK_NL_FLAG_NEED_RATE		BIT(2)
+#define DEVLINK_NL_FLAG_NEED_RATE_NODE		BIT(3)
 
 /* The per devlink instance lock is taken by default in the pre-doit
  * operation, yet several commands do not require this. The global
  * devlink lock is taken and protects from disruption by user-calls.
  */
-#define DEVLINK_NL_FLAG_NO_LOCK			BIT(2)
+#define DEVLINK_NL_FLAG_NO_LOCK			BIT(4)
 
 static int devlink_nl_pre_doit(const struct genl_ops *ops,
 			       struct sk_buff *skb, struct genl_info *info)
@@ -442,6 +518,24 @@ static int devlink_nl_pre_doit(const struct genl_ops *ops,
 		devlink_port = devlink_port_get_from_info(devlink, info);
 		if (!IS_ERR(devlink_port))
 			info->user_ptr[1] = devlink_port;
+	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE) {
+		struct devlink_rate *devlink_rate;
+
+		devlink_rate = devlink_rate_get_from_info(devlink, info);
+		if (IS_ERR(devlink_rate)) {
+			err = PTR_ERR(devlink_rate);
+			goto unlock;
+		}
+		info->user_ptr[1] = devlink_rate;
+	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE_NODE) {
+		struct devlink_rate *rate_node;
+
+		rate_node = devlink_rate_node_get_from_info(devlink, info);
+		if (IS_ERR(rate_node)) {
+			err = PTR_ERR(rate_node);
+			goto unlock;
+		}
+		info->user_ptr[1] = rate_node;
 	}
 	return 0;
 
@@ -748,6 +842,56 @@ devlink_port_fn_hw_addr_fill(struct devlink *devlink, const struct devlink_ops *
 	return 0;
 }
 
+static int devlink_nl_rate_fill(struct sk_buff *msg,
+				struct devlink *devlink,
+				struct devlink_rate *devlink_rate,
+				enum devlink_command cmd, u32 portid,
+				u32 seq, int flags,
+				struct netlink_ext_ack *extack)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+
+	if (nla_put_u16(msg, DEVLINK_ATTR_RATE_TYPE, devlink_rate->type))
+		goto nla_put_failure;
+
+	if (devlink_rate_is_leaf(devlink_rate)) {
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+				devlink_rate->devlink_port->index))
+			goto nla_put_failure;
+	} else if (devlink_rate_is_node(devlink_rate)) {
+		if (nla_put_string(msg, DEVLINK_ATTR_RATE_NODE_NAME,
+				   devlink_rate->name))
+			goto nla_put_failure;
+	}
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_SHARE,
+			      devlink_rate->tx_share, DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_MAX,
+			      devlink_rate->tx_max, DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	if (devlink_rate->parent)
+		if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME,
+				   devlink_rate->parent->name))
+			goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
 static bool
 devlink_port_fn_state_valid(enum devlink_port_fn_state state)
 {
@@ -919,6 +1063,111 @@ static void devlink_port_notify(struct devlink_port *devlink_port,
 				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
 }
 
+static void devlink_rate_notify(struct devlink_rate *devlink_rate,
+				enum devlink_command cmd)
+{
+	struct devlink *devlink = devlink_rate->devlink;
+	struct sk_buff *msg;
+	int err;
+
+	WARN_ON(cmd != DEVLINK_CMD_RATE_NEW &&
+		cmd != DEVLINK_CMD_RATE_DEL);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	err = devlink_nl_rate_fill(msg, devlink, devlink_rate,
+				   cmd, 0, 0, 0, NULL);
+	if (err) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+static int devlink_nl_cmd_rate_get_dumpit(struct sk_buff *msg,
+					  struct netlink_callback *cb)
+{
+	struct devlink_rate *devlink_rate;
+	struct devlink *devlink;
+	int start = cb->args[0];
+	int idx = 0;
+	int err = 0;
+
+	mutex_lock(&devlink_mutex);
+	list_for_each_entry(devlink, &devlink_list, list) {
+		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
+			continue;
+		mutex_lock(&devlink->lock);
+		list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
+			enum devlink_command cmd = DEVLINK_CMD_RATE_NEW;
+			u32 id = NETLINK_CB(cb->skb).portid;
+
+			if (idx < start) {
+				idx++;
+				continue;
+			}
+			err = devlink_nl_rate_fill(msg, devlink,
+						   devlink_rate,
+						   cmd, id,
+						   cb->nlh->nlmsg_seq,
+						   NLM_F_MULTI, NULL);
+			if (err) {
+				mutex_unlock(&devlink->lock);
+				goto out;
+			}
+			idx++;
+		}
+		mutex_unlock(&devlink->lock);
+	}
+out:
+	mutex_unlock(&devlink_mutex);
+	if (err != -EMSGSIZE)
+		return err;
+
+	cb->args[0] = idx;
+	return msg->len;
+}
+
+static int devlink_nl_cmd_rate_get_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct devlink_rate *devlink_rate = info->user_ptr[1];
+	struct devlink *devlink = devlink_rate->devlink;
+	struct sk_buff *msg;
+	int err;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_rate_fill(msg, devlink, devlink_rate,
+				   DEVLINK_CMD_RATE_NEW,
+				   info->snd_portid, info->snd_seq, 0,
+				   info->extack);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static bool
+devlink_rate_is_parent_node(struct devlink_rate *devlink_rate,
+			    struct devlink_rate *parent)
+{
+	while (parent) {
+		if (parent == devlink_rate)
+			return true;
+		parent = parent->parent;
+	}
+	return false;
+}
+
 static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
@@ -1339,6 +1588,255 @@ static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb,
 	return devlink->ops->port_del(devlink, port_index, extack);
 }
 
+static int
+devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate,
+				struct genl_info *info,
+				struct nlattr *nla_parent)
+{
+	struct devlink *devlink = devlink_rate->devlink;
+	const char *parent_name = nla_data(nla_parent);
+	const struct devlink_ops *ops = devlink->ops;
+	size_t len = strlen(parent_name);
+	struct devlink_rate *parent;
+	int err = -EOPNOTSUPP;
+
+	parent = devlink_rate->parent;
+	if (parent && len) {
+		NL_SET_ERR_MSG_MOD(info->extack, "Rate object already has parent.");
+		return -EBUSY;
+	} else if (parent && !len) {
+		if (devlink_rate_is_leaf(devlink_rate))
+			err = ops->rate_leaf_parent_set(devlink_rate, NULL,
+							devlink_rate->priv, NULL,
+							info->extack);
+		else if (devlink_rate_is_node(devlink_rate))
+			err = ops->rate_node_parent_set(devlink_rate, NULL,
+							devlink_rate->priv, NULL,
+							info->extack);
+		if (err)
+			return err;
+
+		refcount_dec(&parent->refcnt);
+		devlink_rate->parent = NULL;
+	} else if (!parent && len) {
+		parent = devlink_rate_node_get_by_name(devlink, parent_name);
+		if (IS_ERR(parent))
+			return -ENODEV;
+
+		if (parent == devlink_rate) {
+			NL_SET_ERR_MSG_MOD(info->extack, "Parent to self is not allowed");
+			return -EINVAL;
+		}
+
+		if (devlink_rate_is_node(devlink_rate) &&
+		    devlink_rate_is_parent_node(devlink_rate, parent->parent)) {
+			NL_SET_ERR_MSG_MOD(info->extack, "Node is already a parent of parent node.");
+			return -EEXIST;
+		}
+
+		if (devlink_rate_is_leaf(devlink_rate))
+			err = ops->rate_leaf_parent_set(devlink_rate, parent,
+							devlink_rate->priv, parent->priv,
+							info->extack);
+		else if (devlink_rate_is_node(devlink_rate))
+			err = ops->rate_node_parent_set(devlink_rate, parent,
+							devlink_rate->priv, parent->priv,
+							info->extack);
+		if (err)
+			return err;
+
+		refcount_inc(&parent->refcnt);
+		devlink_rate->parent = parent;
+	}
+
+	return 0;
+}
+
+static int devlink_nl_rate_set(struct devlink_rate *devlink_rate,
+			       const struct devlink_ops *ops,
+			       struct genl_info *info)
+{
+	struct nlattr *nla_parent, **attrs = info->attrs;
+	int err = -EOPNOTSUPP;
+	u64 rate;
+
+	if (attrs[DEVLINK_ATTR_RATE_TX_SHARE]) {
+		rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_SHARE]);
+		if (devlink_rate_is_leaf(devlink_rate))
+			err = ops->rate_leaf_tx_share_set(devlink_rate, devlink_rate->priv,
+							  rate, info->extack);
+		else if (devlink_rate_is_node(devlink_rate))
+			err = ops->rate_node_tx_share_set(devlink_rate, devlink_rate->priv,
+							  rate, info->extack);
+		if (err)
+			return err;
+		devlink_rate->tx_share = rate;
+	}
+
+	if (attrs[DEVLINK_ATTR_RATE_TX_MAX]) {
+		rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_MAX]);
+		if (devlink_rate_is_leaf(devlink_rate))
+			err = ops->rate_leaf_tx_max_set(devlink_rate, devlink_rate->priv,
+							rate, info->extack);
+		else if (devlink_rate_is_node(devlink_rate))
+			err = ops->rate_node_tx_max_set(devlink_rate, devlink_rate->priv,
+							rate, info->extack);
+		if (err)
+			return err;
+		devlink_rate->tx_max = rate;
+	}
+
+	nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME];
+	if (nla_parent) {
+		err = devlink_nl_rate_parent_node_set(devlink_rate, info,
+						      nla_parent);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops,
+					   struct genl_info *info,
+					   enum devlink_rate_type type)
+{
+	struct nlattr **attrs = info->attrs;
+
+	if (type == DEVLINK_RATE_TYPE_LEAF) {
+		if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_leaf_tx_share_set) {
+			NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the leafs");
+			return false;
+		}
+		if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_leaf_tx_max_set) {
+			NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the leafs");
+			return false;
+		}
+		if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] &&
+		    !ops->rate_leaf_parent_set) {
+			NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the leafs");
+			return false;
+		}
+	} else if (type == DEVLINK_RATE_TYPE_NODE) {
+		if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) {
+			NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the nodes");
+			return false;
+		}
+		if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_node_tx_max_set) {
+			NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the nodes");
+			return false;
+		}
+		if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] &&
+		    !ops->rate_node_parent_set) {
+			NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the nodes");
+			return false;
+		}
+	} else {
+		WARN(1, "Unknown type of rate object");
+		return false;
+	}
+
+	return true;
+}
+
+static int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct devlink_rate *devlink_rate = info->user_ptr[1];
+	struct devlink *devlink = devlink_rate->devlink;
+	const struct devlink_ops *ops = devlink->ops;
+	int err;
+
+	if (!ops || !devlink_rate_set_ops_supported(ops, info, devlink_rate->type))
+		return -EOPNOTSUPP;
+
+	err = devlink_nl_rate_set(devlink_rate, ops, info);
+
+	if (!err)
+		devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW);
+	return err;
+}
+
+static int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_rate *rate_node;
+	const struct devlink_ops *ops;
+	int err;
+
+	ops = devlink->ops;
+	if (!ops || !ops->rate_node_new || !ops->rate_node_del) {
+		NL_SET_ERR_MSG_MOD(info->extack, "Rate nodes aren't supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (!devlink_rate_set_ops_supported(ops, info, DEVLINK_RATE_TYPE_NODE))
+		return -EOPNOTSUPP;
+
+	rate_node = devlink_rate_node_get_from_attrs(devlink, info->attrs);
+	if (!IS_ERR(rate_node))
+		return -EEXIST;
+	else if (rate_node == ERR_PTR(-EINVAL))
+		return -EINVAL;
+
+	rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL);
+	if (!rate_node)
+		return -ENOMEM;
+
+	rate_node->devlink = devlink;
+	rate_node->type = DEVLINK_RATE_TYPE_NODE;
+	rate_node->name = nla_strdup(info->attrs[DEVLINK_ATTR_RATE_NODE_NAME], GFP_KERNEL);
+	if (!rate_node->name) {
+		err = -ENOMEM;
+		goto err_strdup;
+	}
+
+	err = ops->rate_node_new(rate_node, &rate_node->priv, info->extack);
+	if (err)
+		goto err_node_new;
+
+	err = devlink_nl_rate_set(rate_node, ops, info);
+	if (err)
+		goto err_rate_set;
+
+	refcount_set(&rate_node->refcnt, 1);
+	list_add(&rate_node->list, &devlink->rate_list);
+	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
+	return 0;
+
+err_rate_set:
+	ops->rate_node_del(rate_node, rate_node->priv, info->extack);
+err_node_new:
+	kfree(rate_node->name);
+err_strdup:
+	kfree(rate_node);
+	return err;
+}
+
+static int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct devlink_rate *rate_node = info->user_ptr[1];
+	struct devlink *devlink = rate_node->devlink;
+	const struct devlink_ops *ops = devlink->ops;
+	int err;
+
+	if (refcount_read(&rate_node->refcnt) > 1) {
+		NL_SET_ERR_MSG_MOD(info->extack, "Node has children. Cannot delete node.");
+		return -EBUSY;
+	}
+
+	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL);
+	err = ops->rate_node_del(rate_node, rate_node->priv, info->extack);
+	if (rate_node->parent)
+		refcount_dec(&rate_node->parent->refcnt);
+	list_del(&rate_node->list);
+	kfree(rate_node->name);
+	kfree(rate_node);
+	return err;
+}
+
 static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink,
 			      struct devlink_sb *devlink_sb,
 			      enum devlink_command cmd, u32 portid,
@@ -2207,6 +2705,30 @@ static int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb,
 	return genlmsg_reply(msg, info);
 }
 
+static int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
+				    struct netlink_ext_ack *extack)
+{
+	struct devlink_rate *devlink_rate;
+	u16 old_mode;
+	int err;
+
+	if (!devlink->ops->eswitch_mode_get)
+		return -EOPNOTSUPP;
+	err = devlink->ops->eswitch_mode_get(devlink, &old_mode);
+	if (err)
+		return err;
+
+	if (old_mode == mode)
+		return 0;
+
+	list_for_each_entry(devlink_rate, &devlink->rate_list, list)
+		if (devlink_rate_is_node(devlink_rate)) {
+			NL_SET_ERR_MSG_MOD(extack, "Rate node(s) exists.");
+			return -EBUSY;
+		}
+	return 0;
+}
+
 static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
 					   struct genl_info *info)
 {
@@ -2221,6 +2743,9 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
 		if (!ops->eswitch_mode_set)
 			return -EOPNOTSUPP;
 		mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]);
+		err = devlink_rate_nodes_check(devlink, mode, info->extack);
+		if (err)
+			return err;
 		err = ops->eswitch_mode_set(devlink, mode, info->extack);
 		if (err)
 			return err;
@@ -6994,8 +7519,9 @@ static void devlink_trap_stats_read(struct devlink_stats __percpu *trap_stats,
 	}
 }
 
-static int devlink_trap_stats_put(struct sk_buff *msg,
-				  struct devlink_stats __percpu *trap_stats)
+static int
+devlink_trap_group_stats_put(struct sk_buff *msg,
+			     struct devlink_stats __percpu *trap_stats)
 {
 	struct devlink_stats stats;
 	struct nlattr *attr;
@@ -7023,6 +7549,50 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static int devlink_trap_stats_put(struct sk_buff *msg, struct devlink *devlink,
+				  const struct devlink_trap_item *trap_item)
+{
+	struct devlink_stats stats;
+	struct nlattr *attr;
+	u64 drops = 0;
+	int err;
+
+	if (devlink->ops->trap_drop_counter_get) {
+		err = devlink->ops->trap_drop_counter_get(devlink,
+							  trap_item->trap,
+							  &drops);
+		if (err)
+			return err;
+	}
+
+	devlink_trap_stats_read(trap_item->stats, &stats);
+
+	attr = nla_nest_start(msg, DEVLINK_ATTR_STATS);
+	if (!attr)
+		return -EMSGSIZE;
+
+	if (devlink->ops->trap_drop_counter_get &&
+	    nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_DROPPED, drops,
+			      DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS,
+			      stats.rx_packets, DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES,
+			      stats.rx_bytes, DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+
+	nla_nest_end(msg, attr);
+
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(msg, attr);
+	return -EMSGSIZE;
+}
+
 static int devlink_nl_trap_fill(struct sk_buff *msg, struct devlink *devlink,
 				const struct devlink_trap_item *trap_item,
 				enum devlink_command cmd, u32 portid, u32 seq,
@@ -7060,7 +7630,7 @@ static int devlink_nl_trap_fill(struct sk_buff *msg, struct devlink *devlink,
 	if (err)
 		goto nla_put_failure;
 
-	err = devlink_trap_stats_put(msg, trap_item->stats);
+	err = devlink_trap_stats_put(msg, devlink, trap_item);
 	if (err)
 		goto nla_put_failure;
 
@@ -7277,7 +7847,7 @@ devlink_nl_trap_group_fill(struct sk_buff *msg, struct devlink *devlink,
 			group_item->policer_item->policer->id))
 		goto nla_put_failure;
 
-	err = devlink_trap_stats_put(msg, group_item->stats);
+	err = devlink_trap_group_stats_put(msg, group_item->stats);
 	if (err)
 		goto nla_put_failure;
 
@@ -7801,6 +8371,11 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 },
 	[DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 },
 	[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_RATE_TYPE] = { .type = NLA_U16 },
+	[DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64 },
+	[DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64 },
+	[DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING },
 };
 
 static const struct genl_small_ops devlink_nl_ops[] = {
@@ -7827,6 +8402,30 @@ static const struct genl_small_ops devlink_nl_ops[] = {
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 	},
 	{
+		.cmd = DEVLINK_CMD_RATE_GET,
+		.doit = devlink_nl_cmd_rate_get_doit,
+		.dumpit = devlink_nl_cmd_rate_get_dumpit,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_RATE,
+		/* can be retrieved by unprivileged users */
+	},
+	{
+		.cmd = DEVLINK_CMD_RATE_SET,
+		.doit = devlink_nl_cmd_rate_set_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_RATE,
+	},
+	{
+		.cmd = DEVLINK_CMD_RATE_NEW,
+		.doit = devlink_nl_cmd_rate_new_doit,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_RATE_DEL,
+		.doit = devlink_nl_cmd_rate_del_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_RATE_NODE,
+	},
+	{
 		.cmd = DEVLINK_CMD_PORT_SPLIT,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_port_split_doit,
@@ -8201,6 +8800,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
 	xa_init_flags(&devlink->snapshot_ids, XA_FLAGS_ALLOC);
 	__devlink_net_set(devlink, &init_net);
 	INIT_LIST_HEAD(&devlink->port_list);
+	INIT_LIST_HEAD(&devlink->rate_list);
 	INIT_LIST_HEAD(&devlink->sb_list);
 	INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list);
 	INIT_LIST_HEAD(&devlink->resource_list);
@@ -8303,6 +8903,7 @@ void devlink_free(struct devlink *devlink)
 	WARN_ON(!list_empty(&devlink->resource_list));
 	WARN_ON(!list_empty(&devlink->dpipe_table_list));
 	WARN_ON(!list_empty(&devlink->sb_list));
+	WARN_ON(!list_empty(&devlink->rate_list));
 	WARN_ON(!list_empty(&devlink->port_list));
 
 	xa_destroy(&devlink->snapshot_ids);
@@ -8619,6 +9220,108 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 contro
 }
 EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set);
 
+/**
+ * devlink_rate_leaf_create - create devlink rate leaf
+ *
+ * @devlink_port: devlink port object to create rate object on
+ * @priv: driver private data
+ *
+ * Create devlink rate object of type leaf on provided @devlink_port.
+ * Throws call trace if @devlink_port already has a devlink rate object.
+ *
+ * Context: Takes and release devlink->lock <mutex>.
+ *
+ * Return: -ENOMEM if failed to allocate rate object, 0 otherwise.
+ */
+int
+devlink_rate_leaf_create(struct devlink_port *devlink_port, void *priv)
+{
+	struct devlink *devlink = devlink_port->devlink;
+	struct devlink_rate *devlink_rate;
+
+	devlink_rate = kzalloc(sizeof(*devlink_rate), GFP_KERNEL);
+	if (!devlink_rate)
+		return -ENOMEM;
+
+	mutex_lock(&devlink->lock);
+	WARN_ON(devlink_port->devlink_rate);
+	devlink_rate->type = DEVLINK_RATE_TYPE_LEAF;
+	devlink_rate->devlink = devlink;
+	devlink_rate->devlink_port = devlink_port;
+	devlink_rate->priv = priv;
+	list_add_tail(&devlink_rate->list, &devlink->rate_list);
+	devlink_port->devlink_rate = devlink_rate;
+	devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW);
+	mutex_unlock(&devlink->lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_rate_leaf_create);
+
+/**
+ * devlink_rate_leaf_destroy - destroy devlink rate leaf
+ *
+ * @devlink_port: devlink port linked to the rate object
+ *
+ * Context: Takes and release devlink->lock <mutex>.
+ */
+void devlink_rate_leaf_destroy(struct devlink_port *devlink_port)
+{
+	struct devlink_rate *devlink_rate = devlink_port->devlink_rate;
+	struct devlink *devlink = devlink_port->devlink;
+
+	if (!devlink_rate)
+		return;
+
+	mutex_lock(&devlink->lock);
+	devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_DEL);
+	list_del(&devlink_rate->list);
+	devlink_port->devlink_rate = NULL;
+	mutex_unlock(&devlink->lock);
+	kfree(devlink_rate);
+}
+EXPORT_SYMBOL_GPL(devlink_rate_leaf_destroy);
+
+/**
+ * devlink_rate_nodes_destroy - destroy all devlink rate nodes on device
+ *
+ * @devlink: devlink instance
+ *
+ * Unset parent for all rate objects and destroy all rate nodes
+ * on specified device.
+ *
+ * Context: Takes and release devlink->lock <mutex>.
+ */
+void devlink_rate_nodes_destroy(struct devlink *devlink)
+{
+	static struct devlink_rate *devlink_rate, *tmp;
+	const struct devlink_ops *ops = devlink->ops;
+
+	mutex_lock(&devlink->lock);
+	list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
+		if (!devlink_rate->parent)
+			continue;
+
+		refcount_dec(&devlink_rate->parent->refcnt);
+		if (devlink_rate_is_leaf(devlink_rate))
+			ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv,
+						  NULL, NULL);
+		else if (devlink_rate_is_node(devlink_rate))
+			ops->rate_node_parent_set(devlink_rate, NULL, devlink_rate->priv,
+						  NULL, NULL);
+	}
+	list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) {
+		if (devlink_rate_is_node(devlink_rate)) {
+			ops->rate_node_del(devlink_rate, devlink_rate->priv, NULL);
+			list_del(&devlink_rate->list);
+			kfree(devlink_rate->name);
+			kfree(devlink_rate);
+		}
+	}
+	mutex_unlock(&devlink->lock);
+}
+EXPORT_SYMBOL_GPL(devlink_rate_nodes_destroy);
+
 static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
 					     char *name, size_t len)
 {
@@ -8630,12 +9333,18 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
 
 	switch (attrs->flavour) {
 	case DEVLINK_PORT_FLAVOUR_PHYSICAL:
+	case DEVLINK_PORT_FLAVOUR_VIRTUAL:
+		n = snprintf(name, len, "p%u", attrs->phys.port_number);
+		if (n < len && attrs->split)
+			n += snprintf(name + n, len - n, "s%u",
+				      attrs->phys.split_subport_number);
 		if (!attrs->split)
 			n = snprintf(name, len, "p%u", attrs->phys.port_number);
 		else
 			n = snprintf(name, len, "p%us%u",
 				     attrs->phys.port_number,
 				     attrs->phys.split_subport_number);
+
 		break;
 	case DEVLINK_PORT_FLAVOUR_CPU:
 	case DEVLINK_PORT_FLAVOUR_DSA:
@@ -8677,8 +9386,6 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
 		n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf,
 			     attrs->pci_sf.sf);
 		break;
-	case DEVLINK_PORT_FLAVOUR_VIRTUAL:
-		return -EOPNOTSUPP;
 	}
 
 	if (n >= len)
diff --git a/net/core/filter.c b/net/core/filter.c
index 65ab4e21c087..0b13d8157a8f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3235,7 +3235,7 @@ static int bpf_skb_net_hdr_pop(struct sk_buff *skb, u32 off, u32 len)
 	return ret;
 }
 
-static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
+static int bpf_skb_proto_4_to_6(struct sk_buff *skb, u64 flags)
 {
 	const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr);
 	u32 off = skb_mac_header_len(skb);
@@ -3264,7 +3264,9 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
 		}
 
 		/* Due to IPv6 header, MSS needs to be downgraded. */
-		skb_decrease_gso_size(shinfo, len_diff);
+		if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
+			skb_decrease_gso_size(shinfo, len_diff);
+
 		/* Header must be checked, and gso_segs recomputed. */
 		shinfo->gso_type |= SKB_GSO_DODGY;
 		shinfo->gso_segs = 0;
@@ -3276,7 +3278,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
 	return 0;
 }
 
-static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
+static int bpf_skb_proto_6_to_4(struct sk_buff *skb, u64 flags)
 {
 	const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr);
 	u32 off = skb_mac_header_len(skb);
@@ -3305,7 +3307,9 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
 		}
 
 		/* Due to IPv4 header, MSS can be upgraded. */
-		skb_increase_gso_size(shinfo, len_diff);
+		if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
+			skb_increase_gso_size(shinfo, len_diff);
+
 		/* Header must be checked, and gso_segs recomputed. */
 		shinfo->gso_type |= SKB_GSO_DODGY;
 		shinfo->gso_segs = 0;
@@ -3317,17 +3321,17 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
 	return 0;
 }
 
-static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto)
+static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto, u64 flags)
 {
 	__be16 from_proto = skb->protocol;
 
 	if (from_proto == htons(ETH_P_IP) &&
 	      to_proto == htons(ETH_P_IPV6))
-		return bpf_skb_proto_4_to_6(skb);
+		return bpf_skb_proto_4_to_6(skb, flags);
 
 	if (from_proto == htons(ETH_P_IPV6) &&
 	      to_proto == htons(ETH_P_IP))
-		return bpf_skb_proto_6_to_4(skb);
+		return bpf_skb_proto_6_to_4(skb, flags);
 
 	return -ENOTSUPP;
 }
@@ -3337,7 +3341,7 @@ BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto,
 {
 	int ret;
 
-	if (unlikely(flags))
+	if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO)))
 		return -EINVAL;
 
 	/* General idea is that this helper does the basic groundwork
@@ -3357,7 +3361,7 @@ BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto,
 	 * that. For offloads, we mark packet as dodgy, so that headers
 	 * need to be verified first.
 	 */
-	ret = bpf_skb_proto_xlat(skb, proto);
+	ret = bpf_skb_proto_xlat(skb, proto, flags);
 	bpf_compute_data_pointers(skb);
 	return ret;
 }
@@ -3927,6 +3931,23 @@ void xdp_do_flush(void)
 }
 EXPORT_SYMBOL_GPL(xdp_do_flush);
 
+void bpf_clear_redirect_map(struct bpf_map *map)
+{
+	struct bpf_redirect_info *ri;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		ri = per_cpu_ptr(&bpf_redirect_info, cpu);
+		/* Avoid polluting remote cacheline due to writes if
+		 * not needed. Once we pass this test, we need the
+		 * cmpxchg() to make sure it hasn't been changed in
+		 * the meantime by remote CPU.
+		 */
+		if (unlikely(READ_ONCE(ri->map) == map))
+			cmpxchg(&ri->map, map, NULL);
+	}
+}
+
 int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 		    struct bpf_prog *xdp_prog)
 {
@@ -3934,6 +3955,7 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 	enum bpf_map_type map_type = ri->map_type;
 	void *fwd = ri->tgt_value;
 	u32 map_id = ri->map_id;
+	struct bpf_map *map;
 	int err;
 
 	ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */
@@ -3943,7 +3965,14 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 	case BPF_MAP_TYPE_DEVMAP:
 		fallthrough;
 	case BPF_MAP_TYPE_DEVMAP_HASH:
-		err = dev_map_enqueue(fwd, xdp, dev);
+		map = READ_ONCE(ri->map);
+		if (unlikely(map)) {
+			WRITE_ONCE(ri->map, NULL);
+			err = dev_map_enqueue_multi(xdp, dev, map,
+						    ri->flags & BPF_F_EXCLUDE_INGRESS);
+		} else {
+			err = dev_map_enqueue(fwd, xdp, dev);
+		}
 		break;
 	case BPF_MAP_TYPE_CPUMAP:
 		err = cpu_map_enqueue(fwd, xdp, dev);
@@ -3985,13 +4014,21 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 				       enum bpf_map_type map_type, u32 map_id)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_map *map;
 	int err;
 
 	switch (map_type) {
 	case BPF_MAP_TYPE_DEVMAP:
 		fallthrough;
 	case BPF_MAP_TYPE_DEVMAP_HASH:
-		err = dev_map_generic_redirect(fwd, skb, xdp_prog);
+		map = READ_ONCE(ri->map);
+		if (unlikely(map)) {
+			WRITE_ONCE(ri->map, NULL);
+			err = dev_map_redirect_multi(dev, skb, xdp_prog, map,
+						     ri->flags & BPF_F_EXCLUDE_INGRESS);
+		} else {
+			err = dev_map_generic_redirect(fwd, skb, xdp_prog);
+		}
 		if (unlikely(err))
 			goto err;
 		break;
@@ -10008,11 +10045,13 @@ out:
 static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern,
 				    struct sock_reuseport *reuse,
 				    struct sock *sk, struct sk_buff *skb,
+				    struct sock *migrating_sk,
 				    u32 hash)
 {
 	reuse_kern->skb = skb;
 	reuse_kern->sk = sk;
 	reuse_kern->selected_sk = NULL;
+	reuse_kern->migrating_sk = migrating_sk;
 	reuse_kern->data_end = skb->data + skb_headlen(skb);
 	reuse_kern->hash = hash;
 	reuse_kern->reuseport_id = reuse->reuseport_id;
@@ -10021,12 +10060,13 @@ static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern,
 
 struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
 				  struct bpf_prog *prog, struct sk_buff *skb,
+				  struct sock *migrating_sk,
 				  u32 hash)
 {
 	struct sk_reuseport_kern reuse_kern;
 	enum sk_action action;
 
-	bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash);
+	bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, migrating_sk, hash);
 	action = BPF_PROG_RUN(prog, &reuse_kern);
 
 	if (action == SK_PASS)
@@ -10136,6 +10176,8 @@ sk_reuseport_func_proto(enum bpf_func_id func_id,
 		return &sk_reuseport_load_bytes_proto;
 	case BPF_FUNC_skb_load_bytes_relative:
 		return &sk_reuseport_load_bytes_relative_proto;
+	case BPF_FUNC_get_socket_cookie:
+		return &bpf_get_socket_ptr_cookie_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -10165,6 +10207,14 @@ sk_reuseport_is_valid_access(int off, int size,
 	case offsetof(struct sk_reuseport_md, hash):
 		return size == size_default;
 
+	case offsetof(struct sk_reuseport_md, sk):
+		info->reg_type = PTR_TO_SOCKET;
+		return size == sizeof(__u64);
+
+	case offsetof(struct sk_reuseport_md, migrating_sk):
+		info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL;
+		return size == sizeof(__u64);
+
 	/* Fields that allow narrowing */
 	case bpf_ctx_range(struct sk_reuseport_md, eth_protocol):
 		if (size < sizeof_field(struct sk_buff, protocol))
@@ -10237,6 +10287,14 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type,
 	case offsetof(struct sk_reuseport_md, bind_inany):
 		SK_REUSEPORT_LOAD_FIELD(bind_inany);
 		break;
+
+	case offsetof(struct sk_reuseport_md, sk):
+		SK_REUSEPORT_LOAD_FIELD(sk);
+		break;
+
+	case offsetof(struct sk_reuseport_md, migrating_sk):
+		SK_REUSEPORT_LOAD_FIELD(migrating_sk);
+		break;
 	}
 
 	return insn - insn_buf;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 3ed7c98a98e1..2aadbfc5193b 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -943,8 +943,8 @@ bool __skb_flow_dissect(const struct net *net,
 			int offset = 0;
 
 			ops = skb->dev->dsa_ptr->tag_ops;
-			/* Tail taggers don't break flow dissection */
-			if (!ops->tail_tag) {
+			/* Only DSA header taggers break flow dissection */
+			if (ops->needed_headroom) {
 				if (ops->flow_dissect)
 					ops->flow_dissect(skb, &proto, &offset);
 				else
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index bf774575ad71..53e85c70c6e5 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -3142,7 +3142,7 @@ static struct pneigh_entry *pneigh_get_first(struct seq_file *seq)
 	struct net *net = seq_file_net(seq);
 	struct neigh_table *tbl = state->tbl;
 	struct pneigh_entry *pn = NULL;
-	int bucket = state->bucket;
+	int bucket;
 
 	state->flags |= NEIGH_SEQ_IS_PNEIGH;
 	for (bucket = 0; bucket <= PNEIGH_HASHMASK; bucket++) {
diff --git a/net/core/net-traces.c b/net/core/net-traces.c
index 283ddb2dbc7d..c40cd8dd75c7 100644
--- a/net/core/net-traces.c
+++ b/net/core/net-traces.c
@@ -60,3 +60,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
 EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll);
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_send_reset);
+EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_bad_csum);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index c310c7c1cef7..0a6b04714558 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -36,6 +36,7 @@
 #include <net/ip6_checksum.h>
 #include <asm/unaligned.h>
 #include <trace/events/napi.h>
+#include <linux/kconfig.h>
 
 /*
  * We maintain a small pool of fully-sized skbs, to make sure the
@@ -389,7 +390,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
 	static atomic_t ip_ident;
 	struct ipv6hdr *ip6h;
 
-	WARN_ON_ONCE(!irqs_disabled());
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		WARN_ON_ONCE(!irqs_disabled());
 
 	udp_len = len + sizeof(*udph);
 	if (np->ipv6)
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 3c4c4c7a0402..5e4eb45b139c 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -17,6 +17,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/page-flags.h>
 #include <linux/mm.h> /* for __put_page() */
+#include <linux/poison.h>
 
 #include <trace/events/page_pool.h>
 
@@ -221,6 +222,8 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
 		return NULL;
 	}
 
+	page->pp_magic |= PP_SIGNATURE;
+
 	/* Track how many pages are held 'in-flight' */
 	pool->pages_state_hold_cnt++;
 	trace_page_pool_state_hold(pool, page, pool->pages_state_hold_cnt);
@@ -263,6 +266,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
 			put_page(page);
 			continue;
 		}
+		page->pp_magic |= PP_SIGNATURE;
 		pool->alloc.cache[pool->alloc.count++] = page;
 		/* Track how many pages are held 'in-flight' */
 		pool->pages_state_hold_cnt++;
@@ -341,6 +345,8 @@ void page_pool_release_page(struct page_pool *pool, struct page *page)
 			     DMA_ATTR_SKIP_CPU_SYNC);
 	page_pool_set_dma_addr(page, 0);
 skip_dma_unmap:
+	page->pp_magic = 0;
+
 	/* This may be the last page returned, releasing the pool, so
 	 * it is not safe to reference pool afterwards.
 	 */
@@ -622,3 +628,25 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid)
 	}
 }
 EXPORT_SYMBOL(page_pool_update_nid);
+
+bool page_pool_return_skb_page(struct page *page)
+{
+	struct page_pool *pp;
+
+	page = compound_head(page);
+	if (unlikely(page->pp_magic != PP_SIGNATURE))
+		return false;
+
+	pp = page->pp;
+
+	/* Driver set this to memory recycling info. Reset it on recycle.
+	 * This will *not* work for NIC using a split-page memory model.
+	 * The page will be returned to the pool here regardless of the
+	 * 'flipped' fragment being in use or not.
+	 */
+	page->pp = NULL;
+	page_pool_put_full_page(pp, page, false);
+
+	return true;
+}
+EXPORT_SYMBOL(page_pool_return_skb_page);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 3fba429f1f57..7e258d255e90 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -467,7 +467,7 @@ static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t,
 static int pktgen_device_event(struct notifier_block *, unsigned long, void *);
 static void pktgen_run_all_threads(struct pktgen_net *pn);
 static void pktgen_reset_all_threads(struct pktgen_net *pn);
-static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn);
+static void pktgen_stop_all_threads(struct pktgen_net *pn);
 
 static void pktgen_stop(struct pktgen_thread *t);
 static void pktgen_clear_counters(struct pktgen_dev *pkt_dev);
@@ -516,14 +516,11 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf,
 	data[count - 1] = 0;	/* Strip trailing '\n' and terminate string */
 
 	if (!strcmp(data, "stop"))
-		pktgen_stop_all_threads_ifs(pn);
-
+		pktgen_stop_all_threads(pn);
 	else if (!strcmp(data, "start"))
 		pktgen_run_all_threads(pn);
-
 	else if (!strcmp(data, "reset"))
 		pktgen_reset_all_threads(pn);
-
 	else
 		return -EINVAL;
 
@@ -3027,20 +3024,25 @@ static void pktgen_run(struct pktgen_thread *t)
 		t->control &= ~(T_STOP);
 }
 
-static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn)
+static void pktgen_handle_all_threads(struct pktgen_net *pn, u32 flags)
 {
 	struct pktgen_thread *t;
 
-	func_enter();
-
 	mutex_lock(&pktgen_thread_lock);
 
 	list_for_each_entry(t, &pn->pktgen_threads, th_list)
-		t->control |= T_STOP;
+		t->control |= (flags);
 
 	mutex_unlock(&pktgen_thread_lock);
 }
 
+static void pktgen_stop_all_threads(struct pktgen_net *pn)
+{
+	func_enter();
+
+	pktgen_handle_all_threads(pn, T_STOP);
+}
+
 static int thread_is_running(const struct pktgen_thread *t)
 {
 	const struct pktgen_dev *pkt_dev;
@@ -3103,16 +3105,9 @@ static int pktgen_wait_all_threads_run(struct pktgen_net *pn)
 
 static void pktgen_run_all_threads(struct pktgen_net *pn)
 {
-	struct pktgen_thread *t;
-
 	func_enter();
 
-	mutex_lock(&pktgen_thread_lock);
-
-	list_for_each_entry(t, &pn->pktgen_threads, th_list)
-		t->control |= (T_RUN);
-
-	mutex_unlock(&pktgen_thread_lock);
+	pktgen_handle_all_threads(pn, T_RUN);
 
 	/* Propagate thread->control  */
 	schedule_timeout_interruptible(msecs_to_jiffies(125));
@@ -3122,16 +3117,9 @@ static void pktgen_run_all_threads(struct pktgen_net *pn)
 
 static void pktgen_reset_all_threads(struct pktgen_net *pn)
 {
-	struct pktgen_thread *t;
-
 	func_enter();
 
-	mutex_lock(&pktgen_thread_lock);
-
-	list_for_each_entry(t, &pn->pktgen_threads, th_list)
-		t->control |= (T_REMDEVALL);
-
-	mutex_unlock(&pktgen_thread_lock);
+	pktgen_handle_all_threads(pn, T_REMDEVALL);
 
 	/* Propagate thread->control  */
 	schedule_timeout_interruptible(msecs_to_jiffies(125));
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index ec931b080156..745965e49f78 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -9,7 +9,7 @@
  * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
  *
  *	Fixes:
- *	Vitaly E. Lavrov		RTA_OK arithmetics was wrong.
+ *	Vitaly E. Lavrov		RTA_OK arithmetic was wrong.
  */
 
 #include <linux/bitops.h>
@@ -234,7 +234,7 @@ unlock:
  * @msgtype: rtnetlink message type
  * @doit: Function pointer called for each request message
  * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message
- * @flags: rtnl_link_flags to modifiy behaviour of doit/dumpit functions
+ * @flags: rtnl_link_flags to modify behaviour of doit/dumpit functions
  *
  * Like rtnl_register, but for use by removable modules.
  */
@@ -254,7 +254,7 @@ EXPORT_SYMBOL_GPL(rtnl_register_module);
  * @msgtype: rtnetlink message type
  * @doit: Function pointer called for each request message
  * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message
- * @flags: rtnl_link_flags to modifiy behaviour of doit/dumpit functions
+ * @flags: rtnl_link_flags to modify behaviour of doit/dumpit functions
  *
  * Registers the specified function pointers (at least one of them has
  * to be non-NULL) to be called whenever a request message for the
@@ -376,12 +376,12 @@ int __rtnl_link_register(struct rtnl_link_ops *ops)
 	if (rtnl_link_ops_get(ops->kind))
 		return -EEXIST;
 
-	/* The check for setup is here because if ops
+	/* The check for alloc/setup is here because if ops
 	 * does not have that filled up, it is not possible
 	 * to use the ops for creating device. So do not
 	 * fill up dellink as well. That disables rtnl_dellink.
 	 */
-	if (ops->setup && !ops->dellink)
+	if ((ops->alloc || ops->setup) && !ops->dellink)
 		ops->dellink = unregister_netdevice_queue;
 
 	list_add_tail(&ops->list, &link_ops);
@@ -543,7 +543,9 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family)
 {
 	const struct rtnl_af_ops *ops;
 
-	list_for_each_entry_rcu(ops, &rtnl_af_ops, list) {
+	ASSERT_RTNL();
+
+	list_for_each_entry(ops, &rtnl_af_ops, list) {
 		if (ops->family == family)
 			return ops;
 	}
@@ -1819,6 +1821,16 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	if (rtnl_fill_prop_list(skb, dev))
 		goto nla_put_failure;
 
+	if (dev->dev.parent &&
+	    nla_put_string(skb, IFLA_PARENT_DEV_NAME,
+			   dev_name(dev->dev.parent)))
+		goto nla_put_failure;
+
+	if (dev->dev.parent && dev->dev.parent->bus &&
+	    nla_put_string(skb, IFLA_PARENT_DEV_BUS_NAME,
+			   dev->dev.parent->bus->name))
+		goto nla_put_failure;
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -1878,6 +1890,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_PERM_ADDRESS]	= { .type = NLA_REJECT },
 	[IFLA_PROTO_DOWN_REASON] = { .type = NLA_NESTED },
 	[IFLA_NEW_IFINDEX]	= NLA_POLICY_MIN(NLA_S32, 1),
+	[IFLA_PARENT_DEV_NAME]	= { .type = NLA_NUL_STRING },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2274,27 +2287,18 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[])
 		nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) {
 			const struct rtnl_af_ops *af_ops;
 
-			rcu_read_lock();
 			af_ops = rtnl_af_lookup(nla_type(af));
-			if (!af_ops) {
-				rcu_read_unlock();
+			if (!af_ops)
 				return -EAFNOSUPPORT;
-			}
 
-			if (!af_ops->set_link_af) {
-				rcu_read_unlock();
+			if (!af_ops->set_link_af)
 				return -EOPNOTSUPP;
-			}
 
 			if (af_ops->validate_link_af) {
 				err = af_ops->validate_link_af(dev, af);
-				if (err < 0) {
-					rcu_read_unlock();
+				if (err < 0)
 					return err;
-				}
 			}
-
-			rcu_read_unlock();
 		}
 	}
 
@@ -2574,7 +2578,7 @@ static int do_set_proto_down(struct net_device *dev,
 	if (nl_proto_down) {
 		proto_down = nla_get_u8(nl_proto_down);
 
-		/* Dont turn off protodown if there are active reasons */
+		/* Don't turn off protodown if there are active reasons */
 		if (!proto_down && dev->proto_down_reason) {
 			NL_SET_ERR_MSG(extack, "Cannot clear protodown, active reasons");
 			return -EBUSY;
@@ -2868,17 +2872,12 @@ static int do_setlink(const struct sk_buff *skb,
 		nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) {
 			const struct rtnl_af_ops *af_ops;
 
-			rcu_read_lock();
-
 			BUG_ON(!(af_ops = rtnl_af_lookup(nla_type(af))));
 
 			err = af_ops->set_link_af(dev, af, extack);
-			if (err < 0) {
-				rcu_read_unlock();
+			if (err < 0)
 				goto errout;
-			}
 
-			rcu_read_unlock();
 			status |= DO_SETLINK_NOTIFY;
 		}
 	}
@@ -3177,8 +3176,17 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 		return ERR_PTR(-EINVAL);
 	}
 
-	dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type,
-			       ops->setup, num_tx_queues, num_rx_queues);
+	if (ops->alloc) {
+		dev = ops->alloc(tb, ifname, name_assign_type,
+				 num_tx_queues, num_rx_queues);
+		if (IS_ERR(dev))
+			return dev;
+	} else {
+		dev = alloc_netdev_mqs(ops->priv_size, ifname,
+				       name_assign_type, ops->setup,
+				       num_tx_queues, num_rx_queues);
+	}
+
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
@@ -3411,7 +3419,7 @@ replay:
 		return -EOPNOTSUPP;
 	}
 
-	if (!ops->setup)
+	if (!ops->alloc && !ops->setup)
 		return -EOPNOTSUPP;
 
 	if (!ifname[0]) {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index bbc3b4b62032..2531ac4ffa69 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -70,6 +70,7 @@
 #include <net/xfrm.h>
 #include <net/mpls.h>
 #include <net/mptcp.h>
+#include <net/page_pool.h>
 
 #include <linux/uaccess.h>
 #include <trace/events/skb.h>
@@ -645,10 +646,13 @@ static void skb_free_head(struct sk_buff *skb)
 {
 	unsigned char *head = skb->head;
 
-	if (skb->head_frag)
+	if (skb->head_frag) {
+		if (skb_pp_recycle(skb, head))
+			return;
 		skb_free_frag(head);
-	else
+	} else {
 		kfree(head);
+	}
 }
 
 static void skb_release_data(struct sk_buff *skb)
@@ -664,7 +668,7 @@ static void skb_release_data(struct sk_buff *skb)
 	skb_zcopy_clear(skb, true);
 
 	for (i = 0; i < shinfo->nr_frags; i++)
-		__skb_frag_unref(&shinfo->frags[i]);
+		__skb_frag_unref(&shinfo->frags[i], skb->pp_recycle);
 
 	if (shinfo->frag_list)
 		kfree_skb_list(shinfo->frag_list);
@@ -1046,6 +1050,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
 	n->nohdr = 0;
 	n->peeked = 0;
 	C(pfmemalloc);
+	C(pp_recycle);
 	n->destructor = NULL;
 	C(tail);
 	C(end);
@@ -3497,7 +3502,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen)
 		fragto = &skb_shinfo(tgt)->frags[merge];
 
 		skb_frag_size_add(fragto, skb_frag_size(fragfrom));
-		__skb_frag_unref(fragfrom);
+		__skb_frag_unref(fragfrom, skb->pp_recycle);
 	}
 
 	/* Reposition in the original skb */
@@ -5287,6 +5292,13 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 	if (skb_cloned(to))
 		return false;
 
+	/* The page pool signature of struct page will eventually figure out
+	 * which pages can be recycled or not but for now let's prohibit slab
+	 * allocated and page_pool allocated SKBs from being coalesced.
+	 */
+	if (to->pp_recycle != from->pp_recycle)
+		return false;
+
 	if (len <= skb_tailroom(to)) {
 		if (len)
 			BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len));
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 43ce17a6a585..f0b9decdf279 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -399,8 +399,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);
 
-int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags,
-		     long timeo, int *err)
+int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, long timeo)
 {
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	int ret = 0;
diff --git a/net/core/sock.c b/net/core/sock.c
index 946888afef88..ddfa88082a2b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -776,6 +776,58 @@ void sock_enable_timestamps(struct sock *sk)
 }
 EXPORT_SYMBOL(sock_enable_timestamps);
 
+void sock_set_timestamp(struct sock *sk, int optname, bool valbool)
+{
+	switch (optname) {
+	case SO_TIMESTAMP_OLD:
+		__sock_set_timestamps(sk, valbool, false, false);
+		break;
+	case SO_TIMESTAMP_NEW:
+		__sock_set_timestamps(sk, valbool, true, false);
+		break;
+	case SO_TIMESTAMPNS_OLD:
+		__sock_set_timestamps(sk, valbool, false, true);
+		break;
+	case SO_TIMESTAMPNS_NEW:
+		__sock_set_timestamps(sk, valbool, true, true);
+		break;
+	}
+}
+
+int sock_set_timestamping(struct sock *sk, int optname, int val)
+{
+	if (val & ~SOF_TIMESTAMPING_MASK)
+		return -EINVAL;
+
+	if (val & SOF_TIMESTAMPING_OPT_ID &&
+	    !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
+		if (sk->sk_protocol == IPPROTO_TCP &&
+		    sk->sk_type == SOCK_STREAM) {
+			if ((1 << sk->sk_state) &
+			    (TCPF_CLOSE | TCPF_LISTEN))
+				return -EINVAL;
+			sk->sk_tskey = tcp_sk(sk)->snd_una;
+		} else {
+			sk->sk_tskey = 0;
+		}
+	}
+
+	if (val & SOF_TIMESTAMPING_OPT_STATS &&
+	    !(val & SOF_TIMESTAMPING_OPT_TSONLY))
+		return -EINVAL;
+
+	sk->sk_tsflags = val;
+	sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);
+
+	if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
+		sock_enable_timestamp(sk,
+				      SOCK_TIMESTAMPING_RX_SOFTWARE);
+	else
+		sock_disable_timestamp(sk,
+				       (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
+	return 0;
+}
+
 void sock_set_keepalive(struct sock *sk)
 {
 	lock_sock(sk);
@@ -997,54 +1049,15 @@ set_sndbuf:
 		break;
 
 	case SO_TIMESTAMP_OLD:
-		__sock_set_timestamps(sk, valbool, false, false);
-		break;
 	case SO_TIMESTAMP_NEW:
-		__sock_set_timestamps(sk, valbool, true, false);
-		break;
 	case SO_TIMESTAMPNS_OLD:
-		__sock_set_timestamps(sk, valbool, false, true);
-		break;
 	case SO_TIMESTAMPNS_NEW:
-		__sock_set_timestamps(sk, valbool, true, true);
+		sock_set_timestamp(sk, valbool, optname);
 		break;
+
 	case SO_TIMESTAMPING_NEW:
 	case SO_TIMESTAMPING_OLD:
-		if (val & ~SOF_TIMESTAMPING_MASK) {
-			ret = -EINVAL;
-			break;
-		}
-
-		if (val & SOF_TIMESTAMPING_OPT_ID &&
-		    !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
-			if (sk->sk_protocol == IPPROTO_TCP &&
-			    sk->sk_type == SOCK_STREAM) {
-				if ((1 << sk->sk_state) &
-				    (TCPF_CLOSE | TCPF_LISTEN)) {
-					ret = -EINVAL;
-					break;
-				}
-				sk->sk_tskey = tcp_sk(sk)->snd_una;
-			} else {
-				sk->sk_tskey = 0;
-			}
-		}
-
-		if (val & SOF_TIMESTAMPING_OPT_STATS &&
-		    !(val & SOF_TIMESTAMPING_OPT_TSONLY)) {
-			ret = -EINVAL;
-			break;
-		}
-
-		sk->sk_tsflags = val;
-		sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);
-
-		if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
-			sock_enable_timestamp(sk,
-					      SOCK_TIMESTAMPING_RX_SOFTWARE);
-		else
-			sock_disable_timestamp(sk,
-					       (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
+		ret = sock_set_timestamping(sk, optname, val);
 		break;
 
 	case SO_RCVLOWAT:
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index b065f0a103ed..de5ee3ae86d5 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -17,6 +17,74 @@
 DEFINE_SPINLOCK(reuseport_lock);
 
 static DEFINE_IDA(reuseport_ida);
+static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse,
+			       struct sock_reuseport *reuse, bool bind_inany);
+
+static int reuseport_sock_index(struct sock *sk,
+				const struct sock_reuseport *reuse,
+				bool closed)
+{
+	int left, right;
+
+	if (!closed) {
+		left = 0;
+		right = reuse->num_socks;
+	} else {
+		left = reuse->max_socks - reuse->num_closed_socks;
+		right = reuse->max_socks;
+	}
+
+	for (; left < right; left++)
+		if (reuse->socks[left] == sk)
+			return left;
+	return -1;
+}
+
+static void __reuseport_add_sock(struct sock *sk,
+				 struct sock_reuseport *reuse)
+{
+	reuse->socks[reuse->num_socks] = sk;
+	/* paired with smp_rmb() in reuseport_(select|migrate)_sock() */
+	smp_wmb();
+	reuse->num_socks++;
+}
+
+static bool __reuseport_detach_sock(struct sock *sk,
+				    struct sock_reuseport *reuse)
+{
+	int i = reuseport_sock_index(sk, reuse, false);
+
+	if (i == -1)
+		return false;
+
+	reuse->socks[i] = reuse->socks[reuse->num_socks - 1];
+	reuse->num_socks--;
+
+	return true;
+}
+
+static void __reuseport_add_closed_sock(struct sock *sk,
+					struct sock_reuseport *reuse)
+{
+	reuse->socks[reuse->max_socks - reuse->num_closed_socks - 1] = sk;
+	/* paired with READ_ONCE() in inet_csk_bind_conflict() */
+	WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks + 1);
+}
+
+static bool __reuseport_detach_closed_sock(struct sock *sk,
+					   struct sock_reuseport *reuse)
+{
+	int i = reuseport_sock_index(sk, reuse, true);
+
+	if (i == -1)
+		return false;
+
+	reuse->socks[i] = reuse->socks[reuse->max_socks - reuse->num_closed_socks];
+	/* paired with READ_ONCE() in inet_csk_bind_conflict() */
+	WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks - 1);
+
+	return true;
+}
 
 static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks)
 {
@@ -49,6 +117,12 @@ int reuseport_alloc(struct sock *sk, bool bind_inany)
 	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
 					  lockdep_is_held(&reuseport_lock));
 	if (reuse) {
+		if (reuse->num_closed_socks) {
+			/* sk was shutdown()ed before */
+			ret = reuseport_resurrect(sk, reuse, NULL, bind_inany);
+			goto out;
+		}
+
 		/* Only set reuse->bind_inany if the bind_inany is true.
 		 * Otherwise, it will overwrite the reuse->bind_inany
 		 * which was set by the bind/hash path.
@@ -72,9 +146,9 @@ int reuseport_alloc(struct sock *sk, bool bind_inany)
 	}
 
 	reuse->reuseport_id = id;
+	reuse->bind_inany = bind_inany;
 	reuse->socks[0] = sk;
 	reuse->num_socks = 1;
-	reuse->bind_inany = bind_inany;
 	rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
 
 out:
@@ -90,14 +164,30 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
 	u32 more_socks_size, i;
 
 	more_socks_size = reuse->max_socks * 2U;
-	if (more_socks_size > U16_MAX)
+	if (more_socks_size > U16_MAX) {
+		if (reuse->num_closed_socks) {
+			/* Make room by removing a closed sk.
+			 * The child has already been migrated.
+			 * Only reqsk left at this point.
+			 */
+			struct sock *sk;
+
+			sk = reuse->socks[reuse->max_socks - reuse->num_closed_socks];
+			RCU_INIT_POINTER(sk->sk_reuseport_cb, NULL);
+			__reuseport_detach_closed_sock(sk, reuse);
+
+			return reuse;
+		}
+
 		return NULL;
+	}
 
 	more_reuse = __reuseport_alloc(more_socks_size);
 	if (!more_reuse)
 		return NULL;
 
 	more_reuse->num_socks = reuse->num_socks;
+	more_reuse->num_closed_socks = reuse->num_closed_socks;
 	more_reuse->prog = reuse->prog;
 	more_reuse->reuseport_id = reuse->reuseport_id;
 	more_reuse->bind_inany = reuse->bind_inany;
@@ -105,9 +195,13 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
 
 	memcpy(more_reuse->socks, reuse->socks,
 	       reuse->num_socks * sizeof(struct sock *));
+	memcpy(more_reuse->socks +
+	       (more_reuse->max_socks - more_reuse->num_closed_socks),
+	       reuse->socks + (reuse->max_socks - reuse->num_closed_socks),
+	       reuse->num_closed_socks * sizeof(struct sock *));
 	more_reuse->synq_overflow_ts = READ_ONCE(reuse->synq_overflow_ts);
 
-	for (i = 0; i < reuse->num_socks; ++i)
+	for (i = 0; i < reuse->max_socks; ++i)
 		rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb,
 				   more_reuse);
 
@@ -152,13 +246,21 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany)
 	reuse = rcu_dereference_protected(sk2->sk_reuseport_cb,
 					  lockdep_is_held(&reuseport_lock));
 	old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
-					     lockdep_is_held(&reuseport_lock));
+					      lockdep_is_held(&reuseport_lock));
+	if (old_reuse && old_reuse->num_closed_socks) {
+		/* sk was shutdown()ed before */
+		int err = reuseport_resurrect(sk, old_reuse, reuse, reuse->bind_inany);
+
+		spin_unlock_bh(&reuseport_lock);
+		return err;
+	}
+
 	if (old_reuse && old_reuse->num_socks != 1) {
 		spin_unlock_bh(&reuseport_lock);
 		return -EBUSY;
 	}
 
-	if (reuse->num_socks == reuse->max_socks) {
+	if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) {
 		reuse = reuseport_grow(reuse);
 		if (!reuse) {
 			spin_unlock_bh(&reuseport_lock);
@@ -166,10 +268,7 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany)
 		}
 	}
 
-	reuse->socks[reuse->num_socks] = sk;
-	/* paired with smp_rmb() in reuseport_select_sock() */
-	smp_wmb();
-	reuse->num_socks++;
+	__reuseport_add_sock(sk, reuse);
 	rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
 
 	spin_unlock_bh(&reuseport_lock);
@@ -180,15 +279,77 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany)
 }
 EXPORT_SYMBOL(reuseport_add_sock);
 
+static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse,
+			       struct sock_reuseport *reuse, bool bind_inany)
+{
+	if (old_reuse == reuse) {
+		/* If sk was in the same reuseport group, just pop sk out of
+		 * the closed section and push sk into the listening section.
+		 */
+		__reuseport_detach_closed_sock(sk, old_reuse);
+		__reuseport_add_sock(sk, old_reuse);
+		return 0;
+	}
+
+	if (!reuse) {
+		/* In bind()/listen() path, we cannot carry over the eBPF prog
+		 * for the shutdown()ed socket. In setsockopt() path, we should
+		 * not change the eBPF prog of listening sockets by attaching a
+		 * prog to the shutdown()ed socket. Thus, we will allocate a new
+		 * reuseport group and detach sk from the old group.
+		 */
+		int id;
+
+		reuse = __reuseport_alloc(INIT_SOCKS);
+		if (!reuse)
+			return -ENOMEM;
+
+		id = ida_alloc(&reuseport_ida, GFP_ATOMIC);
+		if (id < 0) {
+			kfree(reuse);
+			return id;
+		}
+
+		reuse->reuseport_id = id;
+		reuse->bind_inany = bind_inany;
+	} else {
+		/* Move sk from the old group to the new one if
+		 * - all the other listeners in the old group were close()d or
+		 *   shutdown()ed, and then sk2 has listen()ed on the same port
+		 * OR
+		 * - sk listen()ed without bind() (or with autobind), was
+		 *   shutdown()ed, and then listen()s on another port which
+		 *   sk2 listen()s on.
+		 */
+		if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) {
+			reuse = reuseport_grow(reuse);
+			if (!reuse)
+				return -ENOMEM;
+		}
+	}
+
+	__reuseport_detach_closed_sock(sk, old_reuse);
+	__reuseport_add_sock(sk, reuse);
+	rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
+
+	if (old_reuse->num_socks + old_reuse->num_closed_socks == 0)
+		call_rcu(&old_reuse->rcu, reuseport_free_rcu);
+
+	return 0;
+}
+
 void reuseport_detach_sock(struct sock *sk)
 {
 	struct sock_reuseport *reuse;
-	int i;
 
 	spin_lock_bh(&reuseport_lock);
 	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
 					  lockdep_is_held(&reuseport_lock));
 
+	/* reuseport_grow() has detached a closed sk */
+	if (!reuse)
+		goto out;
+
 	/* Notify the bpf side. The sk may be added to a sockarray
 	 * map. If so, sockarray logic will remove it from the map.
 	 *
@@ -201,19 +362,52 @@ void reuseport_detach_sock(struct sock *sk)
 
 	rcu_assign_pointer(sk->sk_reuseport_cb, NULL);
 
-	for (i = 0; i < reuse->num_socks; i++) {
-		if (reuse->socks[i] == sk) {
-			reuse->socks[i] = reuse->socks[reuse->num_socks - 1];
-			reuse->num_socks--;
-			if (reuse->num_socks == 0)
-				call_rcu(&reuse->rcu, reuseport_free_rcu);
-			break;
-		}
-	}
+	if (!__reuseport_detach_closed_sock(sk, reuse))
+		__reuseport_detach_sock(sk, reuse);
+
+	if (reuse->num_socks + reuse->num_closed_socks == 0)
+		call_rcu(&reuse->rcu, reuseport_free_rcu);
+
+out:
 	spin_unlock_bh(&reuseport_lock);
 }
 EXPORT_SYMBOL(reuseport_detach_sock);
 
+void reuseport_stop_listen_sock(struct sock *sk)
+{
+	if (sk->sk_protocol == IPPROTO_TCP) {
+		struct sock_reuseport *reuse;
+		struct bpf_prog *prog;
+
+		spin_lock_bh(&reuseport_lock);
+
+		reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+						  lockdep_is_held(&reuseport_lock));
+		prog = rcu_dereference_protected(reuse->prog,
+						 lockdep_is_held(&reuseport_lock));
+
+		if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req ||
+		    (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) {
+			/* Migration capable, move sk from the listening section
+			 * to the closed section.
+			 */
+			bpf_sk_reuseport_detach(sk);
+
+			__reuseport_detach_sock(sk, reuse);
+			__reuseport_add_closed_sock(sk, reuse);
+
+			spin_unlock_bh(&reuseport_lock);
+			return;
+		}
+
+		spin_unlock_bh(&reuseport_lock);
+	}
+
+	/* Not capable to do migration, detach immediately */
+	reuseport_detach_sock(sk);
+}
+EXPORT_SYMBOL(reuseport_stop_listen_sock);
+
 static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks,
 				   struct bpf_prog *prog, struct sk_buff *skb,
 				   int hdr_len)
@@ -244,6 +438,23 @@ static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks,
 	return reuse->socks[index];
 }
 
+static struct sock *reuseport_select_sock_by_hash(struct sock_reuseport *reuse,
+						  u32 hash, u16 num_socks)
+{
+	int i, j;
+
+	i = j = reciprocal_scale(hash, num_socks);
+	while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) {
+		i++;
+		if (i >= num_socks)
+			i = 0;
+		if (i == j)
+			return NULL;
+	}
+
+	return reuse->socks[i];
+}
+
 /**
  *  reuseport_select_sock - Select a socket from an SO_REUSEPORT group.
  *  @sk: First socket in the group.
@@ -274,32 +485,21 @@ struct sock *reuseport_select_sock(struct sock *sk,
 	prog = rcu_dereference(reuse->prog);
 	socks = READ_ONCE(reuse->num_socks);
 	if (likely(socks)) {
-		/* paired with smp_wmb() in reuseport_add_sock() */
+		/* paired with smp_wmb() in __reuseport_add_sock() */
 		smp_rmb();
 
 		if (!prog || !skb)
 			goto select_by_hash;
 
 		if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT)
-			sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash);
+			sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, NULL, hash);
 		else
 			sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len);
 
 select_by_hash:
 		/* no bpf or invalid bpf result: fall back to hash usage */
-		if (!sk2) {
-			int i, j;
-
-			i = j = reciprocal_scale(hash, socks);
-			while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) {
-				i++;
-				if (i >= socks)
-					i = 0;
-				if (i == j)
-					goto out;
-			}
-			sk2 = reuse->socks[i];
-		}
+		if (!sk2)
+			sk2 = reuseport_select_sock_by_hash(reuse, hash, socks);
 	}
 
 out:
@@ -308,14 +508,84 @@ out:
 }
 EXPORT_SYMBOL(reuseport_select_sock);
 
+/**
+ *  reuseport_migrate_sock - Select a socket from an SO_REUSEPORT group.
+ *  @sk: close()ed or shutdown()ed socket in the group.
+ *  @migrating_sk: ESTABLISHED/SYN_RECV full socket in the accept queue or
+ *    NEW_SYN_RECV request socket during 3WHS.
+ *  @skb: skb to run through BPF filter.
+ *  Returns a socket (with sk_refcnt +1) that should accept the child socket
+ *  (or NULL on error).
+ */
+struct sock *reuseport_migrate_sock(struct sock *sk,
+				    struct sock *migrating_sk,
+				    struct sk_buff *skb)
+{
+	struct sock_reuseport *reuse;
+	struct sock *nsk = NULL;
+	bool allocated = false;
+	struct bpf_prog *prog;
+	u16 socks;
+	u32 hash;
+
+	rcu_read_lock();
+
+	reuse = rcu_dereference(sk->sk_reuseport_cb);
+	if (!reuse)
+		goto out;
+
+	socks = READ_ONCE(reuse->num_socks);
+	if (unlikely(!socks))
+		goto out;
+
+	/* paired with smp_wmb() in __reuseport_add_sock() */
+	smp_rmb();
+
+	hash = migrating_sk->sk_hash;
+	prog = rcu_dereference(reuse->prog);
+	if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) {
+		if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req)
+			goto select_by_hash;
+		goto out;
+	}
+
+	if (!skb) {
+		skb = alloc_skb(0, GFP_ATOMIC);
+		if (!skb)
+			goto out;
+		allocated = true;
+	}
+
+	nsk = bpf_run_sk_reuseport(reuse, sk, prog, skb, migrating_sk, hash);
+
+	if (allocated)
+		kfree_skb(skb);
+
+select_by_hash:
+	if (!nsk)
+		nsk = reuseport_select_sock_by_hash(reuse, hash, socks);
+
+	if (IS_ERR_OR_NULL(nsk) || unlikely(!refcount_inc_not_zero(&nsk->sk_refcnt)))
+		nsk = NULL;
+
+out:
+	rcu_read_unlock();
+	return nsk;
+}
+EXPORT_SYMBOL(reuseport_migrate_sock);
+
 int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog)
 {
 	struct sock_reuseport *reuse;
 	struct bpf_prog *old_prog;
 
-	if (sk_unhashed(sk) && sk->sk_reuseport) {
-		int err = reuseport_alloc(sk, false);
+	if (sk_unhashed(sk)) {
+		int err;
 
+		if (!sk->sk_reuseport)
+			return -EINVAL;
+
+		err = reuseport_alloc(sk, false);
 		if (err)
 			return err;
 	} else if (!rcu_access_pointer(sk->sk_reuseport_cb)) {
@@ -341,13 +611,24 @@ int reuseport_detach_prog(struct sock *sk)
 	struct sock_reuseport *reuse;
 	struct bpf_prog *old_prog;
 
-	if (!rcu_access_pointer(sk->sk_reuseport_cb))
-		return sk->sk_reuseport ? -ENOENT : -EINVAL;
-
 	old_prog = NULL;
 	spin_lock_bh(&reuseport_lock);
 	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
 					  lockdep_is_held(&reuseport_lock));
+
+	/* reuse must be checked after acquiring the reuseport_lock
+	 * because reuseport_grow() can detach a closed sk.
+	 */
+	if (!reuse) {
+		spin_unlock_bh(&reuseport_lock);
+		return sk->sk_reuseport ? -ENOENT : -EINVAL;
+	}
+
+	if (sk_unhashed(sk) && reuse->num_closed_socks) {
+		spin_unlock_bh(&reuseport_lock);
+		return -ENOENT;
+	}
+
 	old_prog = rcu_replace_pointer(reuse->prog, old_prog,
 				       lockdep_is_held(&reuseport_lock));
 	spin_unlock_bh(&reuseport_lock);
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 858276e72c68..725d20f1b100 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -584,3 +584,31 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 	return __xdp_build_skb_from_frame(xdpf, skb, dev);
 }
 EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame);
+
+struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf)
+{
+	unsigned int headroom, totalsize;
+	struct xdp_frame *nxdpf;
+	struct page *page;
+	void *addr;
+
+	headroom = xdpf->headroom + sizeof(*xdpf);
+	totalsize = headroom + xdpf->len;
+
+	if (unlikely(totalsize > PAGE_SIZE))
+		return NULL;
+	page = dev_alloc_page();
+	if (!page)
+		return NULL;
+	addr = page_to_virt(page);
+
+	memcpy(addr, xdpf, totalsize);
+
+	nxdpf = addr;
+	nxdpf->data = addr + headroom;
+	nxdpf->frame_sz = PAGE_SIZE;
+	nxdpf->mem.type = MEM_TYPE_PAGE_ORDER0;
+	nxdpf->mem.id = 0;
+
+	return nxdpf;
+}
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 653e3bc9c87b..b441ab330fd3 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1381,7 +1381,7 @@ static int dcbnl_notify(struct net_device *dev, int event, int cmd,
 
 	skb = dcbnl_newmsg(event, cmd, portid, seq, 0, &nlh);
 	if (!skb)
-		return -ENOBUFS;
+		return -ENOMEM;
 
 	if (dcbx_ver == DCB_CAP_DCBX_VER_IEEE)
 		err = dcbnl_ieee_fill(skb, dev);
@@ -1781,7 +1781,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	reply_skb = dcbnl_newmsg(fn->type, dcb->cmd, portid, nlh->nlmsg_seq,
 				 nlh->nlmsg_flags, &reply_nlh);
 	if (!reply_skb)
-		return -ENOBUFS;
+		return -ENOMEM;
 
 	ret = fn->cb(netdev, nlh, nlh->nlmsg_seq, tb, reply_skb);
 	if (ret < 0) {
@@ -2075,8 +2075,6 @@ EXPORT_SYMBOL(dcb_ieee_getapp_default_prio_mask);
 
 static int __init dcbnl_init(void)
 {
-	INIT_LIST_HEAD(&dcb_app_list);
-
 	rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL, 0);
 
diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c
index e2a337fa9ff7..92a8c6bea316 100644
--- a/net/dccp/ccids/lib/tfrc_equation.c
+++ b/net/dccp/ccids/lib/tfrc_equation.c
@@ -688,6 +688,7 @@ u32 tfrc_calc_x_reverse_lookup(u32 fvalue)
 
 /**
  * tfrc_invert_loss_event_rate  -  Compute p so that 10^6 corresponds to 100%
+ * @loss_event_rate: loss event rate to invert
  * When @loss_event_rate is large, there is a chance that p is truncated to 0.
  * To avoid re-entering slow-start in that case, we set p = TFRC_SMALLEST_P > 0.
  */
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index ffc601a3b329..f81c1df761d3 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -977,7 +977,6 @@ static const struct net_protocol dccp_v4_protocol = {
 	.handler	= dccp_v4_rcv,
 	.err_handler	= dccp_v4_err,
 	.no_policy	= 1,
-	.netns_ok	= 1,
 	.icmp_strict_tag_validation = 1,
 };
 
diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c
index 1a12912b88d6..7ab788f41a3f 100644
--- a/net/decnet/dn_nsp_in.c
+++ b/net/decnet/dn_nsp_in.c
@@ -870,7 +870,7 @@ int dn_nsp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 
 		/*
 		 * Read out ack data here, this applies equally
-		 * to data, other data, link serivce and both
+		 * to data, other data, link service and both
 		 * ack data and ack otherdata.
 		 */
 		dn_process_ack(sk, skb, other);
diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c
index 00f2ed721ec1..eadc89583168 100644
--- a/net/decnet/dn_nsp_out.c
+++ b/net/decnet/dn_nsp_out.c
@@ -179,7 +179,7 @@ static void dn_nsp_rtt(struct sock *sk, long rtt)
 		scp->nsp_srtt = 1;
 
 	/*
-	 * Add new rtt varience to smoothed varience
+	 * Add new rtt variance to smoothed varience
 	 */
 	delta >>= 1;
 	rttvar += ((((delta>0)?(delta):(-delta)) - rttvar) >> 2);
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 32b1bed8ae51..729d3de6020d 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -604,7 +604,7 @@ drop_it:
 static int dn_route_discard(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	/*
-	 * I know we drop the packet here, but thats considered success in
+	 * I know we drop the packet here, but that's considered success in
 	 * this case
 	 */
 	kfree_skb(skb);
diff --git a/net/devres.c b/net/devres.c
index 1f9be2133787..5ccf6ca311dc 100644
--- a/net/devres.c
+++ b/net/devres.c
@@ -60,7 +60,7 @@ static int netdev_devres_match(struct device *dev, void *this, void *match_data)
  *	@ndev: device to register
  *
  *	This is a devres variant of register_netdev() for which the unregister
- *	function will be call automatically when the managing device is
+ *	function will be called automatically when the managing device is
  *	detached. Note: the net_device used must also be resource managed by
  *	the same struct device.
  */
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 92282de54230..b8b17474b72b 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -154,6 +154,11 @@ const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf);
 bool dsa_schedule_work(struct work_struct *work);
 const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops);
 
+static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops)
+{
+	return ops->needed_headroom + ops->needed_tailroom;
+}
+
 /* master.c */
 int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp);
 void dsa_master_teardown(struct net_device *dev);
diff --git a/net/dsa/master.c b/net/dsa/master.c
index 63adbc21a735..3fc90e36772d 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -346,10 +346,12 @@ static struct lock_class_key dsa_master_addr_list_lock_key;
 
 int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 {
-	int mtu = ETH_DATA_LEN + cpu_dp->tag_ops->overhead;
+	const struct dsa_device_ops *tag_ops = cpu_dp->tag_ops;
 	struct dsa_switch *ds = cpu_dp->ds;
 	struct device_link *consumer_link;
-	int ret;
+	int mtu, ret;
+
+	mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops);
 
 	/* The DSA master must use SET_NETDEV_DEV for this to work. */
 	consumer_link = device_link_add(ds->dev, dev->dev.parent,
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index d4756b920108..798944aa847a 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1569,7 +1569,7 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu)
 
 	mtu_limit = min_t(int, master->max_mtu, dev->max_mtu);
 	old_master_mtu = master->mtu;
-	new_master_mtu = largest_mtu + cpu_dp->tag_ops->overhead;
+	new_master_mtu = largest_mtu + dsa_tag_protocol_overhead(cpu_dp->tag_ops);
 	if (new_master_mtu > mtu_limit)
 		return -ERANGE;
 
@@ -1605,7 +1605,7 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu)
 out_port_failed:
 	if (new_master_mtu != old_master_mtu)
 		dsa_port_mtu_change(cpu_dp, old_master_mtu -
-				    cpu_dp->tag_ops->overhead,
+				    dsa_tag_protocol_overhead(cpu_dp->tag_ops),
 				    true);
 out_cpu_failed:
 	if (new_master_mtu != old_master_mtu)
@@ -1749,7 +1749,8 @@ static void dsa_slave_phylink_fixed_state(struct phylink_config *config,
 }
 
 /* slave device setup *******************************************************/
-static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr)
+static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr,
+				 u32 flags)
 {
 	struct dsa_port *dp = dsa_slave_to_port(slave_dev);
 	struct dsa_switch *ds = dp->ds;
@@ -1760,6 +1761,8 @@ static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr)
 		return -ENODEV;
 	}
 
+	slave_dev->phydev->dev_flags |= flags;
+
 	return phylink_connect_phy(dp->pl, slave_dev->phydev);
 }
 
@@ -1804,7 +1807,7 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev)
 		/* We could not connect to a designated PHY or SFP, so try to
 		 * use the switch internal MDIO bus instead
 		 */
-		ret = dsa_slave_phy_connect(slave_dev, dp->index);
+		ret = dsa_slave_phy_connect(slave_dev, dp->index, phy_flags);
 		if (ret) {
 			netdev_err(slave_dev,
 				   "failed to connect to port %d: %d\n",
@@ -1824,10 +1827,8 @@ void dsa_slave_setup_tagger(struct net_device *slave)
 	const struct dsa_port *cpu_dp = dp->cpu_dp;
 	struct net_device *master = cpu_dp->master;
 
-	if (cpu_dp->tag_ops->tail_tag)
-		slave->needed_tailroom = cpu_dp->tag_ops->overhead;
-	else
-		slave->needed_headroom = cpu_dp->tag_ops->overhead;
+	slave->needed_headroom = cpu_dp->tag_ops->needed_headroom;
+	slave->needed_tailroom = cpu_dp->tag_ops->needed_tailroom;
 	/* Try to save one extra realloc later in the TX path (in the master)
 	 * by also inheriting the master's needed headroom and tailroom.
 	 * The 8021q driver also does this.
diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
index 122ad5833fb1..4aa29f90ecea 100644
--- a/net/dsa/tag_8021q.c
+++ b/net/dsa/tag_8021q.c
@@ -471,4 +471,27 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev,
 }
 EXPORT_SYMBOL_GPL(dsa_8021q_xmit);
 
+void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id,
+		   int *subvlan)
+{
+	u16 vid, tci;
+
+	skb_push_rcsum(skb, ETH_HLEN);
+	if (skb_vlan_tag_present(skb)) {
+		tci = skb_vlan_tag_get(skb);
+		__vlan_hwaccel_clear_tag(skb);
+	} else {
+		__skb_vlan_pop(skb, &tci);
+	}
+	skb_pull_rcsum(skb, ETH_HLEN);
+
+	vid = tci & VLAN_VID_MASK;
+
+	*source_port = dsa_8021q_rx_source_port(vid);
+	*switch_id = dsa_8021q_rx_switch_id(vid);
+	*subvlan = dsa_8021q_rx_subvlan(vid);
+	skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+}
+EXPORT_SYMBOL_GPL(dsa_8021q_rcv);
+
 MODULE_LICENSE("GPL v2");
diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c
index 002cf7f952e2..0efae1a372b3 100644
--- a/net/dsa/tag_ar9331.c
+++ b/net/dsa/tag_ar9331.c
@@ -85,7 +85,7 @@ static const struct dsa_device_ops ar9331_netdev_ops = {
 	.proto	= DSA_TAG_PROTO_AR9331,
 	.xmit	= ar9331_tag_xmit,
 	.rcv	= ar9331_tag_rcv,
-	.overhead = AR9331_HDR_LEN,
+	.needed_headroom = AR9331_HDR_LEN,
 };
 
 MODULE_LICENSE("GPL v2");
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index 40e9f3098c8d..0750af951fc9 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -205,7 +205,7 @@ static const struct dsa_device_ops brcm_netdev_ops = {
 	.proto	= DSA_TAG_PROTO_BRCM,
 	.xmit	= brcm_tag_xmit,
 	.rcv	= brcm_tag_rcv,
-	.overhead = BRCM_TAG_LEN,
+	.needed_headroom = BRCM_TAG_LEN,
 };
 
 DSA_TAG_DRIVER(brcm_netdev_ops);
@@ -286,7 +286,7 @@ static const struct dsa_device_ops brcm_legacy_netdev_ops = {
 	.proto = DSA_TAG_PROTO_BRCM_LEGACY,
 	.xmit = brcm_leg_tag_xmit,
 	.rcv = brcm_leg_tag_rcv,
-	.overhead = BRCM_LEG_TAG_LEN,
+	.needed_headroom = BRCM_LEG_TAG_LEN,
 };
 
 DSA_TAG_DRIVER(brcm_legacy_netdev_ops);
@@ -314,7 +314,7 @@ static const struct dsa_device_ops brcm_prepend_netdev_ops = {
 	.proto	= DSA_TAG_PROTO_BRCM_PREPEND,
 	.xmit	= brcm_tag_xmit_prepend,
 	.rcv	= brcm_tag_rcv_prepend,
-	.overhead = BRCM_TAG_LEN,
+	.needed_headroom = BRCM_TAG_LEN,
 };
 
 DSA_TAG_DRIVER(brcm_prepend_netdev_ops);
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index 7e7b7decdf39..a822355afc90 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -303,7 +303,7 @@ static const struct dsa_device_ops dsa_netdev_ops = {
 	.proto	  = DSA_TAG_PROTO_DSA,
 	.xmit	  = dsa_xmit,
 	.rcv	  = dsa_rcv,
-	.overhead = DSA_HLEN,
+	.needed_headroom = DSA_HLEN,
 };
 
 DSA_TAG_DRIVER(dsa_netdev_ops);
@@ -346,7 +346,7 @@ static const struct dsa_device_ops edsa_netdev_ops = {
 	.proto	  = DSA_TAG_PROTO_EDSA,
 	.xmit	  = edsa_xmit,
 	.rcv	  = edsa_rcv,
-	.overhead = EDSA_HLEN,
+	.needed_headroom = EDSA_HLEN,
 };
 
 DSA_TAG_DRIVER(edsa_netdev_ops);
diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c
index 2f5bd5e338ab..5985dab06ab8 100644
--- a/net/dsa/tag_gswip.c
+++ b/net/dsa/tag_gswip.c
@@ -103,7 +103,7 @@ static const struct dsa_device_ops gswip_netdev_ops = {
 	.proto	= DSA_TAG_PROTO_GSWIP,
 	.xmit = gswip_tag_xmit,
 	.rcv = gswip_tag_rcv,
-	.overhead = GSWIP_RX_HEADER_LEN,
+	.needed_headroom = GSWIP_RX_HEADER_LEN,
 };
 
 MODULE_LICENSE("GPL");
diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c
index a09805c8e1ab..424130f85f59 100644
--- a/net/dsa/tag_hellcreek.c
+++ b/net/dsa/tag_hellcreek.c
@@ -54,8 +54,7 @@ static const struct dsa_device_ops hellcreek_netdev_ops = {
 	.proto	  = DSA_TAG_PROTO_HELLCREEK,
 	.xmit	  = hellcreek_xmit,
 	.rcv	  = hellcreek_rcv,
-	.overhead = HELLCREEK_TAG_LEN,
-	.tail_tag = true,
+	.needed_tailroom = HELLCREEK_TAG_LEN,
 };
 
 MODULE_LICENSE("Dual MIT/GPL");
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 4820dbcedfa2..53565f48934c 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -77,8 +77,7 @@ static const struct dsa_device_ops ksz8795_netdev_ops = {
 	.proto	= DSA_TAG_PROTO_KSZ8795,
 	.xmit	= ksz8795_xmit,
 	.rcv	= ksz8795_rcv,
-	.overhead = KSZ_INGRESS_TAG_LEN,
-	.tail_tag = true,
+	.needed_tailroom = KSZ_INGRESS_TAG_LEN,
 };
 
 DSA_TAG_DRIVER(ksz8795_netdev_ops);
@@ -149,8 +148,7 @@ static const struct dsa_device_ops ksz9477_netdev_ops = {
 	.proto	= DSA_TAG_PROTO_KSZ9477,
 	.xmit	= ksz9477_xmit,
 	.rcv	= ksz9477_rcv,
-	.overhead = KSZ9477_INGRESS_TAG_LEN,
-	.tail_tag = true,
+	.needed_tailroom = KSZ9477_INGRESS_TAG_LEN,
 };
 
 DSA_TAG_DRIVER(ksz9477_netdev_ops);
@@ -183,8 +181,7 @@ static const struct dsa_device_ops ksz9893_netdev_ops = {
 	.proto	= DSA_TAG_PROTO_KSZ9893,
 	.xmit	= ksz9893_xmit,
 	.rcv	= ksz9477_rcv,
-	.overhead = KSZ_INGRESS_TAG_LEN,
-	.tail_tag = true,
+	.needed_tailroom = KSZ_INGRESS_TAG_LEN,
 };
 
 DSA_TAG_DRIVER(ksz9893_netdev_ops);
diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c
index aa1318dccaf0..26207ef39ebc 100644
--- a/net/dsa/tag_lan9303.c
+++ b/net/dsa/tag_lan9303.c
@@ -125,7 +125,7 @@ static const struct dsa_device_ops lan9303_netdev_ops = {
 	.proto	= DSA_TAG_PROTO_LAN9303,
 	.xmit = lan9303_xmit,
 	.rcv = lan9303_rcv,
-	.overhead = LAN9303_TAG_LEN,
+	.needed_headroom = LAN9303_TAG_LEN,
 };
 
 MODULE_LICENSE("GPL");
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index f9b2966d1936..cc3ba864ad5b 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -102,7 +102,7 @@ static const struct dsa_device_ops mtk_netdev_ops = {
 	.proto		= DSA_TAG_PROTO_MTK,
 	.xmit		= mtk_tag_xmit,
 	.rcv		= mtk_tag_rcv,
-	.overhead	= MTK_HDR_LEN,
+	.needed_headroom = MTK_HDR_LEN,
 };
 
 MODULE_LICENSE("GPL");
diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c
index 91f0fd1242cd..190f4bfd3bef 100644
--- a/net/dsa/tag_ocelot.c
+++ b/net/dsa/tag_ocelot.c
@@ -143,7 +143,7 @@ static const struct dsa_device_ops ocelot_netdev_ops = {
 	.proto			= DSA_TAG_PROTO_OCELOT,
 	.xmit			= ocelot_xmit,
 	.rcv			= ocelot_rcv,
-	.overhead		= OCELOT_TOTAL_TAG_LEN,
+	.needed_headroom	= OCELOT_TOTAL_TAG_LEN,
 	.promisc_on_master	= true,
 };
 
@@ -155,7 +155,7 @@ static const struct dsa_device_ops seville_netdev_ops = {
 	.proto			= DSA_TAG_PROTO_SEVILLE,
 	.xmit			= seville_xmit,
 	.rcv			= ocelot_rcv,
-	.overhead		= OCELOT_TOTAL_TAG_LEN,
+	.needed_headroom	= OCELOT_TOTAL_TAG_LEN,
 	.promisc_on_master	= true,
 };
 
diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c
index 62a93303bd63..85ac85c3af8c 100644
--- a/net/dsa/tag_ocelot_8021q.c
+++ b/net/dsa/tag_ocelot_8021q.c
@@ -41,29 +41,15 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb,
 				  struct net_device *netdev,
 				  struct packet_type *pt)
 {
-	int src_port, switch_id, qos_class;
-	u16 vid, tci;
+	int src_port, switch_id, subvlan;
 
-	skb_push_rcsum(skb, ETH_HLEN);
-	if (skb_vlan_tag_present(skb)) {
-		tci = skb_vlan_tag_get(skb);
-		__vlan_hwaccel_clear_tag(skb);
-	} else {
-		__skb_vlan_pop(skb, &tci);
-	}
-	skb_pull_rcsum(skb, ETH_HLEN);
-
-	vid = tci & VLAN_VID_MASK;
-	src_port = dsa_8021q_rx_source_port(vid);
-	switch_id = dsa_8021q_rx_switch_id(vid);
-	qos_class = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+	dsa_8021q_rcv(skb, &src_port, &switch_id, &subvlan);
 
 	skb->dev = dsa_master_find_slave(netdev, switch_id, src_port);
 	if (!skb->dev)
 		return NULL;
 
 	skb->offload_fwd_mark = 1;
-	skb->priority = qos_class;
 
 	return skb;
 }
@@ -73,7 +59,7 @@ static const struct dsa_device_ops ocelot_8021q_netdev_ops = {
 	.proto			= DSA_TAG_PROTO_OCELOT_8021Q,
 	.xmit			= ocelot_xmit,
 	.rcv			= ocelot_rcv,
-	.overhead		= VLAN_HLEN,
+	.needed_headroom	= VLAN_HLEN,
 	.promisc_on_master	= true,
 };
 
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index 88181b52f480..693bda013065 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -91,7 +91,7 @@ static const struct dsa_device_ops qca_netdev_ops = {
 	.proto	= DSA_TAG_PROTO_QCA,
 	.xmit	= qca_tag_xmit,
 	.rcv	= qca_tag_rcv,
-	.overhead = QCA_HDR_LEN,
+	.needed_headroom = QCA_HDR_LEN,
 };
 
 MODULE_LICENSE("GPL");
diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c
index cf8ac316f4c7..57c46b4ab2b3 100644
--- a/net/dsa/tag_rtl4_a.c
+++ b/net/dsa/tag_rtl4_a.c
@@ -124,7 +124,7 @@ static const struct dsa_device_ops rtl4a_netdev_ops = {
 	.proto	= DSA_TAG_PROTO_RTL4_A,
 	.xmit	= rtl4a_tag_xmit,
 	.rcv	= rtl4a_tag_rcv,
-	.overhead = RTL4_A_HDR_LEN,
+	.needed_headroom = RTL4_A_HDR_LEN,
 };
 module_dsa_tag_driver(rtl4a_netdev_ops);
 
diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c
index 50496013cdb7..9c2df9ece01b 100644
--- a/net/dsa/tag_sja1105.c
+++ b/net/dsa/tag_sja1105.c
@@ -7,6 +7,52 @@
 #include <linux/packing.h>
 #include "dsa_priv.h"
 
+/* Is this a TX or an RX header? */
+#define SJA1110_HEADER_HOST_TO_SWITCH		BIT(15)
+
+/* RX header */
+#define SJA1110_RX_HEADER_IS_METADATA		BIT(14)
+#define SJA1110_RX_HEADER_HOST_ONLY		BIT(13)
+#define SJA1110_RX_HEADER_HAS_TRAILER		BIT(12)
+
+/* Trap-to-host format (no trailer present) */
+#define SJA1110_RX_HEADER_SRC_PORT(x)		(((x) & GENMASK(7, 4)) >> 4)
+#define SJA1110_RX_HEADER_SWITCH_ID(x)		((x) & GENMASK(3, 0))
+
+/* Timestamp format (trailer present) */
+#define SJA1110_RX_HEADER_TRAILER_POS(x)	((x) & GENMASK(11, 0))
+
+#define SJA1110_RX_TRAILER_SWITCH_ID(x)		(((x) & GENMASK(7, 4)) >> 4)
+#define SJA1110_RX_TRAILER_SRC_PORT(x)		((x) & GENMASK(3, 0))
+
+/* Meta frame format (for 2-step TX timestamps) */
+#define SJA1110_RX_HEADER_N_TS(x)		(((x) & GENMASK(8, 4)) >> 4)
+
+/* TX header */
+#define SJA1110_TX_HEADER_UPDATE_TC		BIT(14)
+#define SJA1110_TX_HEADER_TAKE_TS		BIT(13)
+#define SJA1110_TX_HEADER_TAKE_TS_CASC		BIT(12)
+#define SJA1110_TX_HEADER_HAS_TRAILER		BIT(11)
+
+/* Only valid if SJA1110_TX_HEADER_HAS_TRAILER is false */
+#define SJA1110_TX_HEADER_PRIO(x)		(((x) << 7) & GENMASK(10, 7))
+#define SJA1110_TX_HEADER_TSTAMP_ID(x)		((x) & GENMASK(7, 0))
+
+/* Only valid if SJA1110_TX_HEADER_HAS_TRAILER is true */
+#define SJA1110_TX_HEADER_TRAILER_POS(x)	((x) & GENMASK(10, 0))
+
+#define SJA1110_TX_TRAILER_TSTAMP_ID(x)		(((x) << 24) & GENMASK(31, 24))
+#define SJA1110_TX_TRAILER_PRIO(x)		(((x) << 21) & GENMASK(23, 21))
+#define SJA1110_TX_TRAILER_SWITCHID(x)		(((x) << 12) & GENMASK(15, 12))
+#define SJA1110_TX_TRAILER_DESTPORTS(x)		(((x) << 1) & GENMASK(11, 1))
+
+#define SJA1110_META_TSTAMP_SIZE		10
+
+#define SJA1110_HEADER_LEN			4
+#define SJA1110_RX_TRAILER_LEN			13
+#define SJA1110_TX_TRAILER_LEN			4
+#define SJA1110_MAX_PADDING_LEN			15
+
 /* Similar to is_link_local_ether_addr(hdr->h_dest) but also covers PTP */
 static inline bool sja1105_is_link_local(const struct sk_buff *skb)
 {
@@ -140,6 +186,57 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb,
 			     ((pcp << VLAN_PRIO_SHIFT) | tx_vid));
 }
 
+static struct sk_buff *sja1110_xmit(struct sk_buff *skb,
+				    struct net_device *netdev)
+{
+	struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone;
+	struct dsa_port *dp = dsa_slave_to_port(netdev);
+	u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index);
+	u16 queue_mapping = skb_get_queue_mapping(skb);
+	u8 pcp = netdev_txq_to_tc(netdev, queue_mapping);
+	struct ethhdr *eth_hdr;
+	__be32 *tx_trailer;
+	__be16 *tx_header;
+	int trailer_pos;
+
+	/* Transmitting control packets is done using in-band control
+	 * extensions, while data packets are transmitted using
+	 * tag_8021q TX VLANs.
+	 */
+	if (likely(!sja1105_is_link_local(skb)))
+		return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp->priv),
+				     ((pcp << VLAN_PRIO_SHIFT) | tx_vid));
+
+	skb_push(skb, SJA1110_HEADER_LEN);
+
+	/* Move Ethernet header to the left, making space for DSA tag */
+	memmove(skb->data, skb->data + SJA1110_HEADER_LEN, 2 * ETH_ALEN);
+
+	trailer_pos = skb->len;
+
+	/* On TX, skb->data points to skb_mac_header(skb) */
+	eth_hdr = (struct ethhdr *)skb->data;
+	tx_header = (__be16 *)(eth_hdr + 1);
+	tx_trailer = skb_put(skb, SJA1110_TX_TRAILER_LEN);
+
+	eth_hdr->h_proto = htons(ETH_P_SJA1110);
+
+	*tx_header = htons(SJA1110_HEADER_HOST_TO_SWITCH |
+			   SJA1110_TX_HEADER_HAS_TRAILER |
+			   SJA1110_TX_HEADER_TRAILER_POS(trailer_pos));
+	*tx_trailer = cpu_to_be32(SJA1110_TX_TRAILER_PRIO(pcp) |
+				  SJA1110_TX_TRAILER_SWITCHID(dp->ds->index) |
+				  SJA1110_TX_TRAILER_DESTPORTS(BIT(dp->index)));
+	if (clone) {
+		u8 ts_id = SJA1105_SKB_CB(clone)->ts_id;
+
+		*tx_header |= htons(SJA1110_TX_HEADER_TAKE_TS);
+		*tx_trailer |= cpu_to_be32(SJA1110_TX_TRAILER_TSTAMP_ID(ts_id));
+	}
+
+	return skb;
+}
+
 static void sja1105_transfer_meta(struct sk_buff *skb,
 				  const struct sja1105_meta *meta)
 {
@@ -147,7 +244,7 @@ static void sja1105_transfer_meta(struct sk_buff *skb,
 
 	hdr->h_dest[3] = meta->dmac_byte_3;
 	hdr->h_dest[4] = meta->dmac_byte_4;
-	SJA1105_SKB_CB(skb)->meta_tstamp = meta->tstamp;
+	SJA1105_SKB_CB(skb)->tstamp = meta->tstamp;
 }
 
 /* This is a simple state machine which follows the hardware mechanism of
@@ -275,46 +372,38 @@ static void sja1105_decode_subvlan(struct sk_buff *skb, u16 subvlan)
 	__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
 }
 
+static bool sja1105_skb_has_tag_8021q(const struct sk_buff *skb)
+{
+	u16 tpid = ntohs(eth_hdr(skb)->h_proto);
+
+	return tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q ||
+	       skb_vlan_tag_present(skb);
+}
+
+static bool sja1110_skb_has_inband_control_extension(const struct sk_buff *skb)
+{
+	return ntohs(eth_hdr(skb)->h_proto) == ETH_P_SJA1110;
+}
+
 static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 				   struct net_device *netdev,
 				   struct packet_type *pt)
 {
+	int source_port, switch_id, subvlan = 0;
 	struct sja1105_meta meta = {0};
-	int source_port, switch_id;
 	struct ethhdr *hdr;
-	u16 tpid, vid, tci;
 	bool is_link_local;
-	u16 subvlan = 0;
-	bool is_tagged;
 	bool is_meta;
 
 	hdr = eth_hdr(skb);
-	tpid = ntohs(hdr->h_proto);
-	is_tagged = (tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q ||
-		     skb_vlan_tag_present(skb));
 	is_link_local = sja1105_is_link_local(skb);
 	is_meta = sja1105_is_meta_frame(skb);
 
 	skb->offload_fwd_mark = 1;
 
-	if (is_tagged) {
+	if (sja1105_skb_has_tag_8021q(skb)) {
 		/* Normal traffic path. */
-		skb_push_rcsum(skb, ETH_HLEN);
-		if (skb_vlan_tag_present(skb)) {
-			tci = skb_vlan_tag_get(skb);
-			__vlan_hwaccel_clear_tag(skb);
-		} else {
-			__skb_vlan_pop(skb, &tci);
-		}
-		skb_pull_rcsum(skb, ETH_HLEN);
-		skb_reset_network_header(skb);
-		skb_reset_transport_header(skb);
-
-		vid = tci & VLAN_VID_MASK;
-		source_port = dsa_8021q_rx_source_port(vid);
-		switch_id = dsa_8021q_rx_switch_id(vid);
-		skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
-		subvlan = dsa_8021q_rx_subvlan(vid);
+		dsa_8021q_rcv(skb, &source_port, &switch_id, &subvlan);
 	} else if (is_link_local) {
 		/* Management traffic path. Switch embeds the switch ID and
 		 * port ID into bytes of the destination MAC, courtesy of
@@ -346,6 +435,138 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 					      is_meta);
 }
 
+static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header)
+{
+	int switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header);
+	int n_ts = SJA1110_RX_HEADER_N_TS(rx_header);
+	struct net_device *master = skb->dev;
+	struct dsa_port *cpu_dp;
+	u8 *buf = skb->data + 2;
+	struct dsa_switch *ds;
+	int i;
+
+	cpu_dp = master->dsa_ptr;
+	ds = dsa_switch_find(cpu_dp->dst->index, switch_id);
+	if (!ds) {
+		net_err_ratelimited("%s: cannot find switch id %d\n",
+				    master->name, switch_id);
+		return NULL;
+	}
+
+	for (i = 0; i <= n_ts; i++) {
+		u8 ts_id, source_port, dir;
+		u64 tstamp;
+
+		ts_id = buf[0];
+		source_port = (buf[1] & GENMASK(7, 4)) >> 4;
+		dir = (buf[1] & BIT(3)) >> 3;
+		tstamp = be64_to_cpu(*(__be64 *)(buf + 2));
+
+		sja1110_process_meta_tstamp(ds, source_port, ts_id, dir,
+					    tstamp);
+
+		buf += SJA1110_META_TSTAMP_SIZE;
+	}
+
+	/* Discard the meta frame, we've consumed the timestamps it contained */
+	return NULL;
+}
+
+static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb,
+							    int *source_port,
+							    int *switch_id)
+{
+	u16 rx_header;
+
+	if (unlikely(!pskb_may_pull(skb, SJA1110_HEADER_LEN)))
+		return NULL;
+
+	/* skb->data points to skb_mac_header(skb) + ETH_HLEN, which is exactly
+	 * what we need because the caller has checked the EtherType (which is
+	 * located 2 bytes back) and we just need a pointer to the header that
+	 * comes afterwards.
+	 */
+	rx_header = ntohs(*(__be16 *)skb->data);
+
+	if (rx_header & SJA1110_RX_HEADER_IS_METADATA)
+		return sja1110_rcv_meta(skb, rx_header);
+
+	/* Timestamp frame, we have a trailer */
+	if (rx_header & SJA1110_RX_HEADER_HAS_TRAILER) {
+		int start_of_padding = SJA1110_RX_HEADER_TRAILER_POS(rx_header);
+		u8 *rx_trailer = skb_tail_pointer(skb) - SJA1110_RX_TRAILER_LEN;
+		u64 *tstamp = &SJA1105_SKB_CB(skb)->tstamp;
+		u8 last_byte = rx_trailer[12];
+
+		/* The timestamp is unaligned, so we need to use packing()
+		 * to get it
+		 */
+		packing(rx_trailer, tstamp, 63, 0, 8, UNPACK, 0);
+
+		*source_port = SJA1110_RX_TRAILER_SRC_PORT(last_byte);
+		*switch_id = SJA1110_RX_TRAILER_SWITCH_ID(last_byte);
+
+		/* skb->len counts from skb->data, while start_of_padding
+		 * counts from the destination MAC address. Right now skb->data
+		 * is still as set by the DSA master, so to trim away the
+		 * padding and trailer we need to account for the fact that
+		 * skb->data points to skb_mac_header(skb) + ETH_HLEN.
+		 */
+		pskb_trim_rcsum(skb, start_of_padding - ETH_HLEN);
+	/* Trap-to-host frame, no timestamp trailer */
+	} else {
+		*source_port = SJA1110_RX_HEADER_SRC_PORT(rx_header);
+		*switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header);
+	}
+
+	/* Advance skb->data past the DSA header */
+	skb_pull_rcsum(skb, SJA1110_HEADER_LEN);
+
+	/* Remove the DSA header */
+	memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - SJA1110_HEADER_LEN,
+		2 * ETH_ALEN);
+
+	/* With skb->data in its final place, update the MAC header
+	 * so that eth_hdr() continues to works properly.
+	 */
+	skb_set_mac_header(skb, -ETH_HLEN);
+
+	return skb;
+}
+
+static struct sk_buff *sja1110_rcv(struct sk_buff *skb,
+				   struct net_device *netdev,
+				   struct packet_type *pt)
+{
+	int source_port = -1, switch_id = -1, subvlan = 0;
+
+	skb->offload_fwd_mark = 1;
+
+	if (sja1110_skb_has_inband_control_extension(skb)) {
+		skb = sja1110_rcv_inband_control_extension(skb, &source_port,
+							   &switch_id);
+		if (!skb)
+			return NULL;
+	}
+
+	/* Packets with in-band control extensions might still have RX VLANs */
+	if (likely(sja1105_skb_has_tag_8021q(skb)))
+		dsa_8021q_rcv(skb, &source_port, &switch_id, &subvlan);
+
+	skb->dev = dsa_master_find_slave(netdev, switch_id, source_port);
+	if (!skb->dev) {
+		netdev_warn(netdev,
+			    "Couldn't decode source port %d and switch id %d\n",
+			    source_port, switch_id);
+		return NULL;
+	}
+
+	if (subvlan)
+		sja1105_decode_subvlan(skb, subvlan);
+
+	return skb;
+}
+
 static void sja1105_flow_dissect(const struct sk_buff *skb, __be16 *proto,
 				 int *offset)
 {
@@ -356,18 +577,53 @@ static void sja1105_flow_dissect(const struct sk_buff *skb, __be16 *proto,
 	dsa_tag_generic_flow_dissect(skb, proto, offset);
 }
 
+static void sja1110_flow_dissect(const struct sk_buff *skb, __be16 *proto,
+				 int *offset)
+{
+	/* Management frames have 2 DSA tags on RX, so the needed_headroom we
+	 * declared is fine for the generic dissector adjustment procedure.
+	 */
+	if (unlikely(sja1105_is_link_local(skb)))
+		return dsa_tag_generic_flow_dissect(skb, proto, offset);
+
+	/* For the rest, there is a single DSA tag, the tag_8021q one */
+	*offset = VLAN_HLEN;
+	*proto = ((__be16 *)skb->data)[(VLAN_HLEN / 2) - 1];
+}
+
 static const struct dsa_device_ops sja1105_netdev_ops = {
 	.name = "sja1105",
 	.proto = DSA_TAG_PROTO_SJA1105,
 	.xmit = sja1105_xmit,
 	.rcv = sja1105_rcv,
 	.filter = sja1105_filter,
-	.overhead = VLAN_HLEN,
+	.needed_headroom = VLAN_HLEN,
 	.flow_dissect = sja1105_flow_dissect,
 	.promisc_on_master = true,
 };
 
-MODULE_LICENSE("GPL v2");
+DSA_TAG_DRIVER(sja1105_netdev_ops);
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1105);
 
-module_dsa_tag_driver(sja1105_netdev_ops);
+static const struct dsa_device_ops sja1110_netdev_ops = {
+	.name = "sja1110",
+	.proto = DSA_TAG_PROTO_SJA1110,
+	.xmit = sja1110_xmit,
+	.rcv = sja1110_rcv,
+	.filter = sja1105_filter,
+	.flow_dissect = sja1110_flow_dissect,
+	.needed_headroom = SJA1110_HEADER_LEN + VLAN_HLEN,
+	.needed_tailroom = SJA1110_RX_TRAILER_LEN + SJA1110_MAX_PADDING_LEN,
+};
+
+DSA_TAG_DRIVER(sja1110_netdev_ops);
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1110);
+
+static struct dsa_tag_driver *sja1105_tag_driver_array[] = {
+	&DSA_TAG_DRIVER_NAME(sja1105_netdev_ops),
+	&DSA_TAG_DRIVER_NAME(sja1110_netdev_ops),
+};
+
+module_dsa_tag_drivers(sja1105_tag_driver_array);
+
+MODULE_LICENSE("GPL v2");
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 5b97ede56a0f..ba73804340a5 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -55,8 +55,7 @@ static const struct dsa_device_ops trailer_netdev_ops = {
 	.proto	= DSA_TAG_PROTO_TRAILER,
 	.xmit	= trailer_xmit,
 	.rcv	= trailer_rcv,
-	.overhead = 4,
-	.tail_tag = true,
+	.needed_tailroom = 4,
 };
 
 MODULE_LICENSE("GPL");
diff --git a/net/dsa/tag_xrs700x.c b/net/dsa/tag_xrs700x.c
index 858cdf9d2913..a31ff7fcb45f 100644
--- a/net/dsa/tag_xrs700x.c
+++ b/net/dsa/tag_xrs700x.c
@@ -56,8 +56,7 @@ static const struct dsa_device_ops xrs700x_netdev_ops = {
 	.proto	= DSA_TAG_PROTO_XRS700X,
 	.xmit	= xrs700x_xmit,
 	.rcv	= xrs700x_rcv,
-	.overhead = 1,
-	.tail_tag = true,
+	.needed_tailroom = 1,
 };
 
 MODULE_LICENSE("GPL");
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 88d8a0243f35..a7346346114f 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -315,9 +315,9 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info)
 	struct ethnl_req_info *req_info = NULL;
 	const u8 cmd = info->genlhdr->cmd;
 	const struct ethnl_request_ops *ops;
+	int hdr_len, reply_len;
 	struct sk_buff *rskb;
 	void *reply_payload;
-	int reply_len;
 	int ret;
 
 	ops = ethnl_default_requests[cmd];
@@ -346,15 +346,20 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info)
 	ret = ops->reply_size(req_info, reply_data);
 	if (ret < 0)
 		goto err_cleanup;
-	reply_len = ret + ethnl_reply_header_size();
+	reply_len = ret;
 	ret = -ENOMEM;
-	rskb = ethnl_reply_init(reply_len, req_info->dev, ops->reply_cmd,
+	rskb = ethnl_reply_init(reply_len + ethnl_reply_header_size(),
+				req_info->dev, ops->reply_cmd,
 				ops->hdr_attr, info, &reply_payload);
 	if (!rskb)
 		goto err_cleanup;
+	hdr_len = rskb->len;
 	ret = ops->fill_reply(rskb, req_info, reply_data);
 	if (ret < 0)
 		goto err_msg;
+	WARN_ONCE(rskb->len - hdr_len > reply_len,
+		  "ethnl cmd %d: calculated reply length %d, but consumed %d\n",
+		  cmd, reply_len, rskb->len - hdr_len);
 	if (ops->cleanup_data)
 		ops->cleanup_data(reply_data);
 
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 8abcbc10796c..90b10966b16b 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -138,7 +138,7 @@ static inline void ethnl_update_bool32(u32 *dst, const struct nlattr *attr,
 }
 
 /**
- * ethnl_update_binary() - update binary data from NLA_BINARY atribute
+ * ethnl_update_binary() - update binary data from NLA_BINARY attribute
  * @dst:  value to update
  * @len:  destination buffer length
  * @attr: netlink attribute with new value or null
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index bb1351c38397..e31949479305 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -397,7 +397,8 @@ void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port,
 	 * ensures entries of restarted nodes gets pruned so that they can
 	 * re-register and resume communications.
 	 */
-	if (seq_nr_before(sequence_nr, node->seq_out[port->type]))
+	if (!(port->dev->features & NETIF_F_HW_HSR_TAG_RM) &&
+	    seq_nr_before(sequence_nr, node->seq_out[port->type]))
 		return;
 
 	node->time_in[port->type] = jiffies;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 2f94d221c00e..54648181dd56 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -318,7 +318,7 @@ lookup_protocol:
 
 	WARN_ON(!answer_prot->slab);
 
-	err = -ENOBUFS;
+	err = -ENOMEM;
 	sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot, kern);
 	if (!sk)
 		goto out;
@@ -1720,7 +1720,6 @@ EXPORT_SYMBOL_GPL(snmp_fold_field64);
 #ifdef CONFIG_IP_MULTICAST
 static const struct net_protocol igmp_protocol = {
 	.handler =	igmp_rcv,
-	.netns_ok =	1,
 };
 #endif
 
@@ -1733,7 +1732,6 @@ static struct net_protocol tcp_protocol = {
 	.handler	=	tcp_v4_rcv,
 	.err_handler	=	tcp_v4_err,
 	.no_policy	=	1,
-	.netns_ok	=	1,
 	.icmp_strict_tag_validation = 1,
 };
 
@@ -1746,14 +1744,12 @@ static struct net_protocol udp_protocol = {
 	.handler =	udp_rcv,
 	.err_handler =	udp_err,
 	.no_policy =	1,
-	.netns_ok =	1,
 };
 
 static const struct net_protocol icmp_protocol = {
 	.handler =	icmp_rcv,
 	.err_handler =	icmp_err,
 	.no_policy =	1,
-	.netns_ok =	1,
 };
 
 static __net_init int ipv4_mib_init_net(struct net *net)
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index e0480c6cebaa..099259fc826a 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -187,8 +187,7 @@ static int __init cipso_v4_cache_init(void)
  * cipso_v4_cache_invalidate - Invalidates the current CIPSO cache
  *
  * Description:
- * Invalidates and frees any entries in the CIPSO cache.  Returns zero on
- * success and negative values on failure.
+ * Invalidates and frees any entries in the CIPSO cache.
  *
  */
 void cipso_v4_cache_invalidate(void)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 1c6429c353a9..73721a4448bd 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1955,7 +1955,7 @@ static int inet_validate_link_af(const struct net_device *dev,
 	struct nlattr *a, *tb[IFLA_INET_MAX+1];
 	int err, rem;
 
-	if (dev && !__in_dev_get_rcu(dev))
+	if (dev && !__in_dev_get_rtnl(dev))
 		return -EAFNOSUPPORT;
 
 	err = nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla,
@@ -1981,7 +1981,7 @@ static int inet_validate_link_af(const struct net_device *dev,
 static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla,
 			    struct netlink_ext_ack *extack)
 {
-	struct in_device *in_dev = __in_dev_get_rcu(dev);
+	struct in_device *in_dev = __in_dev_get_rtnl(dev);
 	struct nlattr *a, *tb[IFLA_INET_MAX+1];
 	int rem;
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 84bb707bd88d..af8814a11378 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1122,10 +1122,8 @@ void fib_add_ifaddr(struct in_ifaddr *ifa)
 				  prefix, ifa->ifa_prefixlen, prim,
 				  ifa->ifa_rt_priority);
 
-		/* Add network specific broadcasts, when it takes a sense */
+		/* Add the network broadcast address, when it makes sense */
 		if (ifa->ifa_prefixlen < 31) {
-			fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix, 32,
-				  prim, 0);
 			fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask,
 				  32, prim, 0);
 		}
@@ -1516,6 +1514,12 @@ static int __net_init ip_fib_net_init(struct net *net)
 	if (err)
 		return err;
 
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+	/* Default to 3-tuple */
+	net->ipv4.sysctl_fib_multipath_hash_fields =
+		FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK;
+#endif
+
 	/* Avoid false sharing : Use at least a full cache line */
 	size = max_t(size_t, size, L1_CACHE_BYTES);
 
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index b58db1ca4bfb..e184bcb19943 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -25,7 +25,7 @@ struct fib_alias {
 
 #define FA_S_ACCESSED	0x01
 
-/* Dont write on fa_state unless needed, to keep it shared on all cpus */
+/* Don't write on fa_state unless needed, to keep it shared on all cpus */
 static inline void fib_alias_accessed(struct fib_alias *fa)
 {
 	if (!(fa->fa_state & FA_S_ACCESSED))
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 5d1e6fe9d838..cbb2b4bb0dfa 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -195,7 +195,6 @@ static int gre_err(struct sk_buff *skb, u32 info)
 static const struct net_protocol net_gre_protocol = {
 	.handler     = gre_rcv,
 	.err_handler = gre_err,
-	.netns_ok    = 1,
 };
 
 static int __init gre_init(void)
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 752e392083e6..0a57f1892e7e 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1066,7 +1066,7 @@ static bool icmp_echo(struct sk_buff *skb)
 			if (ident_len != sizeof(iio->ident.addr.ctype3_hdr) +
 					 sizeof(struct in_addr))
 				goto send_mal_query;
-			dev = ip_dev_find(net, iio->ident.addr.ip_addr.ipv4_addr.s_addr);
+			dev = ip_dev_find(net, iio->ident.addr.ip_addr.ipv4_addr);
 			break;
 #if IS_ENABLED(CONFIG_IPV6)
 		case ICMP_AFI_IP6:
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index fd472eae4f5c..0eea878edc30 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -135,10 +135,18 @@ static int inet_csk_bind_conflict(const struct sock *sk,
 				  bool relax, bool reuseport_ok)
 {
 	struct sock *sk2;
+	bool reuseport_cb_ok;
 	bool reuse = sk->sk_reuse;
 	bool reuseport = !!sk->sk_reuseport;
+	struct sock_reuseport *reuseport_cb;
 	kuid_t uid = sock_i_uid((struct sock *)sk);
 
+	rcu_read_lock();
+	reuseport_cb = rcu_dereference(sk->sk_reuseport_cb);
+	/* paired with WRITE_ONCE() in __reuseport_(add|detach)_closed_sock */
+	reuseport_cb_ok = !reuseport_cb || READ_ONCE(reuseport_cb->num_closed_socks);
+	rcu_read_unlock();
+
 	/*
 	 * Unlike other sk lookup places we do not check
 	 * for sk_net here, since _all_ the socks listed
@@ -156,14 +164,14 @@ static int inet_csk_bind_conflict(const struct sock *sk,
 				if ((!relax ||
 				     (!reuseport_ok &&
 				      reuseport && sk2->sk_reuseport &&
-				      !rcu_access_pointer(sk->sk_reuseport_cb) &&
+				      reuseport_cb_ok &&
 				      (sk2->sk_state == TCP_TIME_WAIT ||
 				       uid_eq(uid, sock_i_uid(sk2))))) &&
 				    inet_rcv_saddr_equal(sk, sk2, true))
 					break;
 			} else if (!reuseport_ok ||
 				   !reuseport || !sk2->sk_reuseport ||
-				   rcu_access_pointer(sk->sk_reuseport_cb) ||
+				   !reuseport_cb_ok ||
 				   (sk2->sk_state != TCP_TIME_WAIT &&
 				    !uid_eq(uid, sock_i_uid(sk2)))) {
 				if (inet_rcv_saddr_equal(sk, sk2, true))
@@ -687,6 +695,64 @@ int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req)
 }
 EXPORT_SYMBOL(inet_rtx_syn_ack);
 
+static struct request_sock *inet_reqsk_clone(struct request_sock *req,
+					     struct sock *sk)
+{
+	struct sock *req_sk, *nreq_sk;
+	struct request_sock *nreq;
+
+	nreq = kmem_cache_alloc(req->rsk_ops->slab, GFP_ATOMIC | __GFP_NOWARN);
+	if (!nreq) {
+		/* paired with refcount_inc_not_zero() in reuseport_migrate_sock() */
+		sock_put(sk);
+		return NULL;
+	}
+
+	req_sk = req_to_sk(req);
+	nreq_sk = req_to_sk(nreq);
+
+	memcpy(nreq_sk, req_sk,
+	       offsetof(struct sock, sk_dontcopy_begin));
+	memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end,
+	       req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end));
+
+	sk_node_init(&nreq_sk->sk_node);
+	nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping;
+#ifdef CONFIG_XPS
+	nreq_sk->sk_rx_queue_mapping = req_sk->sk_rx_queue_mapping;
+#endif
+	nreq_sk->sk_incoming_cpu = req_sk->sk_incoming_cpu;
+
+	nreq->rsk_listener = sk;
+
+	/* We need not acquire fastopenq->lock
+	 * because the child socket is locked in inet_csk_listen_stop().
+	 */
+	if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(nreq)->tfo_listener)
+		rcu_assign_pointer(tcp_sk(nreq->sk)->fastopen_rsk, nreq);
+
+	return nreq;
+}
+
+static void reqsk_queue_migrated(struct request_sock_queue *queue,
+				 const struct request_sock *req)
+{
+	if (req->num_timeout == 0)
+		atomic_inc(&queue->young);
+	atomic_inc(&queue->qlen);
+}
+
+static void reqsk_migrate_reset(struct request_sock *req)
+{
+	req->saved_syn = NULL;
+#if IS_ENABLED(CONFIG_IPV6)
+	inet_rsk(req)->ipv6_opt = NULL;
+	inet_rsk(req)->pktopts = NULL;
+#else
+	inet_rsk(req)->ireq_opt = NULL;
+#endif
+}
+
 /* return true if req was found in the ehash table */
 static bool reqsk_queue_unlink(struct request_sock *req)
 {
@@ -727,15 +793,39 @@ EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put);
 static void reqsk_timer_handler(struct timer_list *t)
 {
 	struct request_sock *req = from_timer(req, t, rsk_timer);
+	struct request_sock *nreq = NULL, *oreq = req;
 	struct sock *sk_listener = req->rsk_listener;
-	struct net *net = sock_net(sk_listener);
-	struct inet_connection_sock *icsk = inet_csk(sk_listener);
-	struct request_sock_queue *queue = &icsk->icsk_accept_queue;
+	struct inet_connection_sock *icsk;
+	struct request_sock_queue *queue;
+	struct net *net;
 	int max_syn_ack_retries, qlen, expire = 0, resend = 0;
 
-	if (inet_sk_state_load(sk_listener) != TCP_LISTEN)
-		goto drop;
+	if (inet_sk_state_load(sk_listener) != TCP_LISTEN) {
+		struct sock *nsk;
+
+		nsk = reuseport_migrate_sock(sk_listener, req_to_sk(req), NULL);
+		if (!nsk)
+			goto drop;
+
+		nreq = inet_reqsk_clone(req, nsk);
+		if (!nreq)
+			goto drop;
 
+		/* The new timer for the cloned req can decrease the 2
+		 * by calling inet_csk_reqsk_queue_drop_and_put(), so
+		 * hold another count to prevent use-after-free and
+		 * call reqsk_put() just before return.
+		 */
+		refcount_set(&nreq->rsk_refcnt, 2 + 1);
+		timer_setup(&nreq->rsk_timer, reqsk_timer_handler, TIMER_PINNED);
+		reqsk_queue_migrated(&inet_csk(nsk)->icsk_accept_queue, req);
+
+		req = nreq;
+		sk_listener = nsk;
+	}
+
+	icsk = inet_csk(sk_listener);
+	net = sock_net(sk_listener);
 	max_syn_ack_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries;
 	/* Normally all the openreqs are young and become mature
 	 * (i.e. converted to established socket) for first timeout.
@@ -754,6 +844,7 @@ static void reqsk_timer_handler(struct timer_list *t)
 	 * embrions; and abort old ones without pity, if old
 	 * ones are about to clog our table.
 	 */
+	queue = &icsk->icsk_accept_queue;
 	qlen = reqsk_queue_len(queue);
 	if ((qlen << 1) > max(8U, READ_ONCE(sk_listener->sk_max_ack_backlog))) {
 		int young = reqsk_queue_len_young(queue) << 1;
@@ -778,10 +869,36 @@ static void reqsk_timer_handler(struct timer_list *t)
 			atomic_dec(&queue->young);
 		timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX);
 		mod_timer(&req->rsk_timer, jiffies + timeo);
+
+		if (!nreq)
+			return;
+
+		if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) {
+			/* delete timer */
+			inet_csk_reqsk_queue_drop(sk_listener, nreq);
+			goto drop;
+		}
+
+		reqsk_migrate_reset(oreq);
+		reqsk_queue_removed(&inet_csk(oreq->rsk_listener)->icsk_accept_queue, oreq);
+		reqsk_put(oreq);
+
+		reqsk_put(nreq);
 		return;
 	}
+
 drop:
-	inet_csk_reqsk_queue_drop_and_put(sk_listener, req);
+	/* Even if we can clone the req, we may need not retransmit any more
+	 * SYN+ACKs (nreq->num_timeout > max_syn_ack_retries, etc), or another
+	 * CPU may win the "own_req" race so that inet_ehash_insert() fails.
+	 */
+	if (nreq) {
+		reqsk_migrate_reset(nreq);
+		reqsk_queue_removed(queue, nreq);
+		__reqsk_free(nreq);
+	}
+
+	inet_csk_reqsk_queue_drop_and_put(oreq->rsk_listener, oreq);
 }
 
 static void reqsk_queue_hash_req(struct request_sock *req,
@@ -997,12 +1114,40 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
 					 struct request_sock *req, bool own_req)
 {
 	if (own_req) {
-		inet_csk_reqsk_queue_drop(sk, req);
-		reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
-		if (inet_csk_reqsk_queue_add(sk, req, child))
+		inet_csk_reqsk_queue_drop(req->rsk_listener, req);
+		reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req);
+
+		if (sk != req->rsk_listener) {
+			/* another listening sk has been selected,
+			 * migrate the req to it.
+			 */
+			struct request_sock *nreq;
+
+			/* hold a refcnt for the nreq->rsk_listener
+			 * which is assigned in inet_reqsk_clone()
+			 */
+			sock_hold(sk);
+			nreq = inet_reqsk_clone(req, sk);
+			if (!nreq) {
+				inet_child_forget(sk, req, child);
+				goto child_put;
+			}
+
+			refcount_set(&nreq->rsk_refcnt, 1);
+			if (inet_csk_reqsk_queue_add(sk, nreq, child)) {
+				reqsk_migrate_reset(req);
+				reqsk_put(req);
+				return child;
+			}
+
+			reqsk_migrate_reset(nreq);
+			__reqsk_free(nreq);
+		} else if (inet_csk_reqsk_queue_add(sk, req, child)) {
 			return child;
+		}
 	}
 	/* Too bad, another child took ownership of the request, undo. */
+child_put:
 	bh_unlock_sock(child);
 	sock_put(child);
 	return NULL;
@@ -1028,14 +1173,36 @@ void inet_csk_listen_stop(struct sock *sk)
 	 * of the variants now.			--ANK
 	 */
 	while ((req = reqsk_queue_remove(queue, sk)) != NULL) {
-		struct sock *child = req->sk;
+		struct sock *child = req->sk, *nsk;
+		struct request_sock *nreq;
 
 		local_bh_disable();
 		bh_lock_sock(child);
 		WARN_ON(sock_owned_by_user(child));
 		sock_hold(child);
 
+		nsk = reuseport_migrate_sock(sk, child, NULL);
+		if (nsk) {
+			nreq = inet_reqsk_clone(req, nsk);
+			if (nreq) {
+				refcount_set(&nreq->rsk_refcnt, 1);
+
+				if (inet_csk_reqsk_queue_add(nsk, nreq, child)) {
+					reqsk_migrate_reset(req);
+				} else {
+					reqsk_migrate_reset(nreq);
+					__reqsk_free(nreq);
+				}
+
+				/* inet_csk_reqsk_queue_add() has already
+				 * called inet_child_forget() on failure case.
+				 */
+				goto skip_child_forget;
+			}
+		}
+
 		inet_child_forget(sk, req, child);
+skip_child_forget:
 		reqsk_put(req);
 		bh_unlock_sock(child);
 		local_bh_enable();
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 93474b1bea4e..e65f4ef024a4 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -416,7 +416,7 @@ EXPORT_SYMBOL_GPL(inet_sk_diag_fill);
 static int inet_twsk_diag_fill(struct sock *sk,
 			       struct sk_buff *skb,
 			       struct netlink_callback *cb,
-			       u16 nlmsg_flags)
+			       u16 nlmsg_flags, bool net_admin)
 {
 	struct inet_timewait_sock *tw = inet_twsk(sk);
 	struct inet_diag_msg *r;
@@ -444,6 +444,12 @@ static int inet_twsk_diag_fill(struct sock *sk,
 	r->idiag_uid	      = 0;
 	r->idiag_inode	      = 0;
 
+	if (net_admin && nla_put_u32(skb, INET_DIAG_MARK,
+				     tw->tw_mark)) {
+		nlmsg_cancel(skb, nlh);
+		return -EMSGSIZE;
+	}
+
 	nlmsg_end(skb, nlh);
 	return 0;
 }
@@ -494,7 +500,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 			u16 nlmsg_flags, bool net_admin)
 {
 	if (sk->sk_state == TCP_TIME_WAIT)
-		return inet_twsk_diag_fill(sk, skb, cb, nlmsg_flags);
+		return inet_twsk_diag_fill(sk, skb, cb, nlmsg_flags, net_admin);
 
 	if (sk->sk_state == TCP_NEW_SYN_RECV)
 		return inet_req_diag_fill(sk, skb, cb, nlmsg_flags, net_admin);
@@ -801,6 +807,8 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk)
 		entry.mark = sk->sk_mark;
 	else if (sk->sk_state == TCP_NEW_SYN_RECV)
 		entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark;
+	else if (sk->sk_state == TCP_TIME_WAIT)
+		entry.mark = inet_twsk(sk)->tw_mark;
 	else
 		entry.mark = 0;
 #ifdef CONFIG_SOCK_CGROUP_DATA
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index c96866a53a66..80aeaf9e6e16 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -697,7 +697,7 @@ void inet_unhash(struct sock *sk)
 		goto unlock;
 
 	if (rcu_access_pointer(sk->sk_reuseport_cb))
-		reuseport_detach_sock(sk);
+		reuseport_stop_listen_sock(sk);
 	if (ilb) {
 		inet_unhash2(hashinfo, sk);
 		ilb->count--;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 939792a38814..7b12a40dd465 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1317,7 +1317,7 @@ static void mroute_clean_tables(struct mr_table *mrt, int flags)
 }
 
 /* called from ip_ra_control(), before an RCU grace period,
- * we dont need to call synchronize_rcu() here
+ * we don't need to call synchronize_rcu() here
  */
 static void mrtsock_destruct(struct sock *sk)
 {
@@ -1938,7 +1938,7 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt,
 	if (c->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) {
 		struct mfc_cache *cache_proxy;
 
-		/* For an (*,G) entry, we only check that the incomming
+		/* For an (*,G) entry, we only check that the incoming
 		 * interface is part of the static tree.
 		 */
 		cache_proxy = mr_mfc_find_any_parent(mrt, vif);
@@ -3007,7 +3007,6 @@ static const struct seq_operations ipmr_mfc_seq_ops = {
 #ifdef CONFIG_IP_PIMSM_V2
 static const struct net_protocol pim_protocol = {
 	.handler	=	pim_rcv,
-	.netns_ok	=	1,
 };
 #endif
 
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
index ff437e4ed6db..55fc23a8f7a7 100644
--- a/net/ipv4/netfilter/nft_reject_ipv4.c
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -27,7 +27,7 @@ static void nft_reject_ipv4_eval(const struct nft_expr *expr,
 		nf_send_unreach(pkt->skb, priv->icmp_code, nft_hook(pkt));
 		break;
 	case NFT_REJECT_TCP_RST:
-		nf_send_reset(nft_net(pkt), pkt->xt.state->sk, pkt->skb,
+		nf_send_reset(nft_net(pkt), nft_sk(pkt), pkt->skb,
 			      nft_hook(pkt));
 		break;
 	default:
diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index 9a8c0892622b..6913979948d7 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -31,12 +31,6 @@ EXPORT_SYMBOL(inet_offloads);
 
 int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol)
 {
-	if (!prot->netns_ok) {
-		pr_err("Protocol %u is not namespace aware, cannot register.\n",
-			protocol);
-		return -EINVAL;
-	}
-
 	return !cmpxchg((const struct net_protocol **)&inet_protos[protocol],
 			NULL, prot) ? 0 : -1;
 }
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6a36ac98476f..66aacb939d3e 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1906,13 +1906,128 @@ out:
 	hash_keys->addrs.v4addrs.dst = key_iph->daddr;
 }
 
+static u32 fib_multipath_custom_hash_outer(const struct net *net,
+					   const struct sk_buff *skb,
+					   bool *p_has_inner)
+{
+	u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields;
+	struct flow_keys keys, hash_keys;
+
+	if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK))
+		return 0;
+
+	memset(&hash_keys, 0, sizeof(hash_keys));
+	skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_ENCAP);
+
+	hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP)
+		hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP)
+		hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO)
+		hash_keys.basic.ip_proto = keys.basic.ip_proto;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT)
+		hash_keys.ports.src = keys.ports.src;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
+		hash_keys.ports.dst = keys.ports.dst;
+
+	*p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION);
+	return flow_hash_from_keys(&hash_keys);
+}
+
+static u32 fib_multipath_custom_hash_inner(const struct net *net,
+					   const struct sk_buff *skb,
+					   bool has_inner)
+{
+	u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields;
+	struct flow_keys keys, hash_keys;
+
+	/* We assume the packet carries an encapsulation, but if none was
+	 * encountered during dissection of the outer flow, then there is no
+	 * point in calling the flow dissector again.
+	 */
+	if (!has_inner)
+		return 0;
+
+	if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK))
+		return 0;
+
+	memset(&hash_keys, 0, sizeof(hash_keys));
+	skb_flow_dissect_flow_keys(skb, &keys, 0);
+
+	if (!(keys.control.flags & FLOW_DIS_ENCAPSULATION))
+		return 0;
+
+	if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+		hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP)
+			hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP)
+			hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
+	} else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+		hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP)
+			hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src;
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP)
+			hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst;
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL)
+			hash_keys.tags.flow_label = keys.tags.flow_label;
+	}
+
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO)
+		hash_keys.basic.ip_proto = keys.basic.ip_proto;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT)
+		hash_keys.ports.src = keys.ports.src;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT)
+		hash_keys.ports.dst = keys.ports.dst;
+
+	return flow_hash_from_keys(&hash_keys);
+}
+
+static u32 fib_multipath_custom_hash_skb(const struct net *net,
+					 const struct sk_buff *skb)
+{
+	u32 mhash, mhash_inner;
+	bool has_inner = true;
+
+	mhash = fib_multipath_custom_hash_outer(net, skb, &has_inner);
+	mhash_inner = fib_multipath_custom_hash_inner(net, skb, has_inner);
+
+	return jhash_2words(mhash, mhash_inner, 0);
+}
+
+static u32 fib_multipath_custom_hash_fl4(const struct net *net,
+					 const struct flowi4 *fl4)
+{
+	u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields;
+	struct flow_keys hash_keys;
+
+	if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK))
+		return 0;
+
+	memset(&hash_keys, 0, sizeof(hash_keys));
+	hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP)
+		hash_keys.addrs.v4addrs.src = fl4->saddr;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP)
+		hash_keys.addrs.v4addrs.dst = fl4->daddr;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO)
+		hash_keys.basic.ip_proto = fl4->flowi4_proto;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT)
+		hash_keys.ports.src = fl4->fl4_sport;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
+		hash_keys.ports.dst = fl4->fl4_dport;
+
+	return flow_hash_from_keys(&hash_keys);
+}
+
 /* if skb is set it will be used and fl4 can be NULL */
 int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
 		       const struct sk_buff *skb, struct flow_keys *flkeys)
 {
 	u32 multipath_hash = fl4 ? fl4->flowi4_multipath_hash : 0;
 	struct flow_keys hash_keys;
-	u32 mhash;
+	u32 mhash = 0;
 
 	switch (net->ipv4.sysctl_fib_multipath_hash_policy) {
 	case 0:
@@ -1924,6 +2039,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
 			hash_keys.addrs.v4addrs.src = fl4->saddr;
 			hash_keys.addrs.v4addrs.dst = fl4->daddr;
 		}
+		mhash = flow_hash_from_keys(&hash_keys);
 		break;
 	case 1:
 		/* skb is currently provided only when forwarding */
@@ -1957,6 +2073,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
 			hash_keys.ports.dst = fl4->fl4_dport;
 			hash_keys.basic.ip_proto = fl4->flowi4_proto;
 		}
+		mhash = flow_hash_from_keys(&hash_keys);
 		break;
 	case 2:
 		memset(&hash_keys, 0, sizeof(hash_keys));
@@ -1987,9 +2104,15 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
 			hash_keys.addrs.v4addrs.src = fl4->saddr;
 			hash_keys.addrs.v4addrs.dst = fl4->daddr;
 		}
+		mhash = flow_hash_from_keys(&hash_keys);
+		break;
+	case 3:
+		if (skb)
+			mhash = fib_multipath_custom_hash_skb(net, skb);
+		else
+			mhash = fib_multipath_custom_hash_fl4(net, fl4);
 		break;
 	}
-	mhash = flow_hash_from_keys(&hash_keys);
 
 	if (multipath_hash)
 		mhash = jhash_2words(mhash, multipath_hash, 0);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index a62934b9f15a..6f1e64d49232 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -19,6 +19,7 @@
 #include <net/snmp.h>
 #include <net/icmp.h>
 #include <net/ip.h>
+#include <net/ip_fib.h>
 #include <net/route.h>
 #include <net/tcp.h>
 #include <net/udp.h>
@@ -29,6 +30,7 @@
 #include <net/netevent.h>
 
 static int two = 2;
+static int three __maybe_unused = 3;
 static int four = 4;
 static int thousand = 1000;
 static int tcp_retr1_max = 255;
@@ -48,6 +50,8 @@ static int ip_ping_group_range_min[] = { 0, 0 };
 static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 static u32 u32_max_div_HZ = UINT_MAX / HZ;
 static int one_day_secs = 24 * 3600;
+static u32 fib_multipath_hash_fields_all_mask __maybe_unused =
+	FIB_MULTIPATH_HASH_FIELD_ALL_MASK;
 
 /* obsolete */
 static int sysctl_tcp_low_latency __read_mostly;
@@ -461,6 +465,22 @@ static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write,
 
 	return ret;
 }
+
+static int proc_fib_multipath_hash_fields(struct ctl_table *table, int write,
+					  void *buffer, size_t *lenp,
+					  loff_t *ppos)
+{
+	struct net *net;
+	int ret;
+
+	net = container_of(table->data, struct net,
+			   ipv4.sysctl_fib_multipath_hash_fields);
+	ret = proc_douintvec_minmax(table, write, buffer, lenp, ppos);
+	if (write && ret == 0)
+		call_netevent_notifiers(NETEVENT_IPV4_MPATH_HASH_UPDATE, net);
+
+	return ret;
+}
 #endif
 
 static struct ctl_table ipv4_table[] = {
@@ -941,6 +961,15 @@ static struct ctl_table ipv4_net_table[] = {
 	},
 #endif
 	{
+		.procname	= "tcp_migrate_req",
+		.data		= &init_net.ipv4.sysctl_tcp_migrate_req,
+		.maxlen		= sizeof(u8),
+		.mode		= 0644,
+		.proc_handler	= proc_dou8vec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE
+	},
+	{
 		.procname	= "tcp_reordering",
 		.data		= &init_net.ipv4.sysctl_tcp_reordering,
 		.maxlen		= sizeof(int),
@@ -1050,7 +1079,16 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_fib_multipath_hash_policy,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &two,
+		.extra2		= &three,
+	},
+	{
+		.procname	= "fib_multipath_hash_fields",
+		.data		= &init_net.ipv4.sysctl_fib_multipath_hash_fields,
+		.maxlen		= sizeof(u32),
+		.mode		= 0644,
+		.proc_handler	= proc_fib_multipath_hash_fields,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= &fib_multipath_hash_fields_all_mask,
 	},
 #endif
 	{
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f1c1f9e3de72..0e3f0e0e5b51 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1738,8 +1738,8 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
 }
 EXPORT_SYMBOL(tcp_set_rcvlowat);
 
-static void tcp_update_recv_tstamps(struct sk_buff *skb,
-				    struct scm_timestamping_internal *tss)
+void tcp_update_recv_tstamps(struct sk_buff *skb,
+			     struct scm_timestamping_internal *tss)
 {
 	if (skb->tstamp)
 		tss->ts[0] = ktime_to_timespec64(skb->tstamp);
@@ -2024,8 +2024,6 @@ static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma,
 }
 
 #define TCP_VALID_ZC_MSG_FLAGS   (TCP_CMSG_TS)
-static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
-			       struct scm_timestamping_internal *tss);
 static void tcp_zc_finalize_rx_tstamp(struct sock *sk,
 				      struct tcp_zerocopy_receive *zc,
 				      struct scm_timestamping_internal *tss)
@@ -2197,8 +2195,8 @@ out:
 #endif
 
 /* Similar to __sock_recv_timestamp, but does not require an skb */
-static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
-			       struct scm_timestamping_internal *tss)
+void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
+			struct scm_timestamping_internal *tss)
 {
 	int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW);
 	bool has_timestamping = false;
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index ad9d17923fc5..a80de92ea3b6 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -184,11 +184,11 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 msg_bytes_ready:
 	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
 	if (!copied) {
-		int data, err = 0;
 		long timeo;
+		int data;
 
 		timeo = sock_rcvtimeo(sk, nonblock);
-		data = sk_msg_wait_data(sk, psock, flags, timeo, &err);
+		data = sk_msg_wait_data(sk, psock, timeo);
 		if (data) {
 			if (!sk_psock_queue_empty(psock))
 				goto msg_bytes_ready;
@@ -196,14 +196,9 @@ msg_bytes_ready:
 			sk_psock_put(sk, psock);
 			return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 		}
-		if (err) {
-			ret = err;
-			goto out;
-		}
 		copied = -EAGAIN;
 	}
 	ret = copied;
-out:
 	release_sock(sk);
 	sk_psock_put(sk, psock);
 	return ret;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index af2814c9342a..47c32604d38f 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -526,7 +526,7 @@ bool tcp_fastopen_active_should_disable(struct sock *sk)
 	if (!tfo_da_times)
 		return false;
 
-	/* Limit timout to max: 2^6 * initial timeout */
+	/* Limit timeout to max: 2^6 * initial timeout */
 	multiplier = 1 << min(tfo_da_times - 1, 6);
 	timeout = multiplier * tfo_bh_timeout * HZ;
 	if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout))
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4cf4dd532d1c..7d5e59f688de 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2816,8 +2816,17 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack,
 	*rexmit = REXMIT_LOST;
 }
 
+static bool tcp_force_fast_retransmit(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	return after(tcp_highest_sack_seq(tp),
+		     tp->snd_una + tp->reordering * tp->mss_cache);
+}
+
 /* Undo during fast recovery after partial ACK. */
-static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una)
+static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una,
+				 bool *do_lost)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -2842,7 +2851,9 @@ static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una)
 		tcp_undo_cwnd_reduction(sk, true);
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO);
 		tcp_try_keep_open(sk);
-		return true;
+	} else {
+		/* Partial ACK arrived. Force fast retransmit. */
+		*do_lost = tcp_force_fast_retransmit(sk);
 	}
 	return false;
 }
@@ -2866,14 +2877,6 @@ static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag)
 	}
 }
 
-static bool tcp_force_fast_retransmit(struct sock *sk)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	return after(tcp_highest_sack_seq(tp),
-		     tp->snd_una + tp->reordering * tp->mss_cache);
-}
-
 /* Process an event, which can update packets-in-flight not trivially.
  * Main goal of this function is to calculate new estimate for left_out,
  * taking into account both packets sitting in receiver's buffer and
@@ -2943,17 +2946,21 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 		if (!(flag & FLAG_SND_UNA_ADVANCED)) {
 			if (tcp_is_reno(tp))
 				tcp_add_reno_sack(sk, num_dupack, ece_ack);
-		} else {
-			if (tcp_try_undo_partial(sk, prior_snd_una))
-				return;
-			/* Partial ACK arrived. Force fast retransmit. */
-			do_lost = tcp_force_fast_retransmit(sk);
-		}
-		if (tcp_try_undo_dsack(sk)) {
-			tcp_try_keep_open(sk);
+		} else if (tcp_try_undo_partial(sk, prior_snd_una, &do_lost))
 			return;
-		}
+
+		if (tcp_try_undo_dsack(sk))
+			tcp_try_keep_open(sk);
+
 		tcp_identify_packet_loss(sk, ack_flag);
+		if (icsk->icsk_ca_state != TCP_CA_Recovery) {
+			if (!tcp_time_to_recover(sk, flag))
+				return;
+			/* Undo reverts the recovery state. If loss is evident,
+			 * starts a new recovery (e.g. reordering then loss);
+			 */
+			tcp_enter_recovery(sk, ece_ack);
+		}
 		break;
 	case TCP_CA_Loss:
 		tcp_process_loss(sk, flag, num_dupack, rexmit);
@@ -5885,6 +5892,7 @@ step5:
 	return;
 
 csum_error:
+	trace_tcp_bad_csum(skb);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 312184cead57..6cb8e269f1ab 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1731,6 +1731,7 @@ discard:
 	return 0;
 
 csum_err:
+	trace_tcp_bad_csum(skb);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
 	goto discard;
@@ -1801,6 +1802,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 
 	if (unlikely(tcp_checksum_complete(skb))) {
 		bh_unlock_sock(sk);
+		trace_tcp_bad_csum(skb);
 		__TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
 		__TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
 		return true;
@@ -2000,13 +2002,21 @@ process:
 			goto csum_error;
 		}
 		if (unlikely(sk->sk_state != TCP_LISTEN)) {
-			inet_csk_reqsk_queue_drop_and_put(sk, req);
-			goto lookup;
+			nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb);
+			if (!nsk) {
+				inet_csk_reqsk_queue_drop_and_put(sk, req);
+				goto lookup;
+			}
+			sk = nsk;
+			/* reuseport_migrate_sock() has already held one sk_refcnt
+			 * before returning.
+			 */
+		} else {
+			/* We own a reference on the listener, increase it again
+			 * as we might lose it too soon.
+			 */
+			sock_hold(sk);
 		}
-		/* We own a reference on the listener, increase it again
-		 * as we might lose it too soon.
-		 */
-		sock_hold(sk);
 		refcounted = true;
 		nsk = NULL;
 		if (!tcp_filter(sk, skb)) {
@@ -2098,6 +2108,7 @@ no_tcp_socket:
 
 	if (tcp_checksum_complete(skb)) {
 csum_error:
+		trace_tcp_bad_csum(skb);
 		__TCP_INC_STATS(net, TCP_MIB_CSUMERRORS);
 bad_packet:
 		__TCP_INC_STATS(net, TCP_MIB_INERRS);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 7513ba45553d..f258a4c0da71 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -775,8 +775,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 		goto listen_overflow;
 
 	if (own_req && rsk_drop_req(req)) {
-		reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
-		inet_csk_reqsk_queue_drop_and_put(sk, req);
+		reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req);
+		inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req);
 		return child;
 	}
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 4ef08079ccfa..56b9d648f054 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -441,7 +441,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
  *  This function gets called when the kernel timer for a TCP packet
  *  of this socket expires.
  *
- *  It handles retransmission, timer adjustment and other necesarry measures.
+ *  It handles retransmission, timer adjustment and other necessary measures.
  *
  *  Returns: Nothing (void)
  */
@@ -766,7 +766,7 @@ static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer)
 	if (!sock_owned_by_user(sk)) {
 		if (tp->compressed_ack) {
 			/* Since we have to send one ack finally,
-			 * substract one from tp->compressed_ack to keep
+			 * subtract one from tp->compressed_ack to keep
 			 * LINUX_MIB_TCPACKCOMPRESSED accurate.
 			 */
 			tp->compressed_ack--;
diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c
index e44aaf41a138..5048c47c79b2 100644
--- a/net/ipv4/tunnel4.c
+++ b/net/ipv4/tunnel4.c
@@ -218,7 +218,6 @@ static const struct net_protocol tunnel4_protocol = {
 	.handler	=	tunnel4_rcv,
 	.err_handler	=	tunnel4_err,
 	.no_policy	=	1,
-	.netns_ok	=	1,
 };
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -226,7 +225,6 @@ static const struct net_protocol tunnel64_protocol = {
 	.handler	=	tunnel64_rcv,
 	.err_handler	=	tunnel64_err,
 	.no_policy	=	1,
-	.netns_ok	=	1,
 };
 #endif
 
@@ -235,7 +233,6 @@ static const struct net_protocol tunnelmpls4_protocol = {
 	.handler	=	tunnelmpls4_rcv,
 	.err_handler	=	tunnelmpls4_err,
 	.no_policy	=	1,
-	.netns_ok	=	1,
 };
 #endif
 
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 954c4591a6fd..b07e4b6dda25 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -43,21 +43,17 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 msg_bytes_ready:
 	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
 	if (!copied) {
-		int data, err = 0;
 		long timeo;
+		int data;
 
 		timeo = sock_rcvtimeo(sk, nonblock);
-		data = sk_msg_wait_data(sk, psock, flags, timeo, &err);
+		data = sk_msg_wait_data(sk, psock, timeo);
 		if (data) {
 			if (!sk_psock_queue_empty(psock))
 				goto msg_bytes_ready;
 			ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 			goto out;
 		}
-		if (err) {
-			ret = err;
-			goto out;
-		}
 		copied = -EAGAIN;
 	}
 	ret = copied;
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index bd8773b49e72..cd1cd68adeec 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -31,7 +31,6 @@ static const struct net_protocol udplite_protocol = {
 	.handler	= udplite_rcv,
 	.err_handler	= udplite_err,
 	.no_policy	= 1,
-	.netns_ok	= 1,
 };
 
 struct proto 	udplite_prot = {
diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c
index ea595c8549c7..2fe5860c21d6 100644
--- a/net/ipv4/xfrm4_protocol.c
+++ b/net/ipv4/xfrm4_protocol.c
@@ -181,21 +181,18 @@ static const struct net_protocol esp4_protocol = {
 	.handler	=	xfrm4_esp_rcv,
 	.err_handler	=	xfrm4_esp_err,
 	.no_policy	=	1,
-	.netns_ok	=	1,
 };
 
 static const struct net_protocol ah4_protocol = {
 	.handler	=	xfrm4_ah_rcv,
 	.err_handler	=	xfrm4_ah_err,
 	.no_policy	=	1,
-	.netns_ok	=	1,
 };
 
 static const struct net_protocol ipcomp4_protocol = {
 	.handler	=	xfrm4_ipcomp_rcv,
 	.err_handler	=	xfrm4_ipcomp_err,
 	.no_policy	=	1,
-	.netns_ok	=	1,
 };
 
 static const struct xfrm_input_afinfo xfrm4_input_afinfo = {
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 701eb82acd1c..3bf685fe64b9 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -6903,10 +6903,10 @@ static const struct ctl_table addrconf_sysctl[] = {
 		.proc_handler   = proc_dointvec,
 	},
 	{
-		.procname		= "addr_gen_mode",
-		.data			= &ipv6_devconf.addr_gen_mode,
-		.maxlen			= sizeof(int),
-		.mode			= 0644,
+		.procname	= "addr_gen_mode",
+		.data		= &ipv6_devconf.addr_gen_mode,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
 		.proc_handler	= addrconf_sysctl_addr_gen_mode,
 	},
 	{
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 8f9a83314de7..40f3e4f9f33a 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -467,7 +467,7 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = {
 static int __net_init fib6_rules_net_init(struct net *net)
 {
 	struct fib_rules_ops *ops;
-	int err = -ENOMEM;
+	int err;
 
 	ops = fib_rules_register(&fib6_rules_ops_template, net);
 	if (IS_ERR(ops))
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 679699e953f1..2d650dc24349 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -32,6 +32,7 @@
 #include <net/lwtunnel.h>
 #include <net/fib_notifier.h>
 
+#include <net/ip_fib.h>
 #include <net/ip6_fib.h>
 #include <net/ip6_route.h>
 
@@ -2355,6 +2356,10 @@ static int __net_init fib6_net_init(struct net *net)
 	if (err)
 		return err;
 
+	/* Default to 3-tuple */
+	net->ipv6.sysctl.multipath_hash_fields =
+		FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK;
+
 	spin_lock_init(&net->ipv6.fib6_gc_lock);
 	rwlock_init(&net->ipv6.fib6_walker_lock);
 	INIT_LIST_HEAD(&net->ipv6.fib6_walkers);
@@ -2362,7 +2367,7 @@ static int __net_init fib6_net_init(struct net *net)
 
 	net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL);
 	if (!net->ipv6.rt6_stats)
-		goto out_timer;
+		goto out_notifier;
 
 	/* Avoid false sharing : Use at least a full cache line */
 	size = max_t(size_t, size, L1_CACHE_BYTES);
@@ -2407,7 +2412,7 @@ out_fib_table_hash:
 	kfree(net->ipv6.fib_table_hash);
 out_rt6_stats:
 	kfree(net->ipv6.rt6_stats);
-out_timer:
+out_notifier:
 	fib6_notifier_exit(net);
 	return -ENOMEM;
 }
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index d36ef9d25e73..54ec163fbafa 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1729,22 +1729,25 @@ static void ip6_mc_hdr(struct sock *sk, struct sk_buff *skb,
 
 static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu)
 {
+	u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT,
+		     2, 0, 0, IPV6_TLV_PADN, 0 };
 	struct net_device *dev = idev->dev;
-	struct net *net = dev_net(dev);
-	struct sock *sk = net->ipv6.igmp_sk;
-	struct sk_buff *skb;
-	struct mld2_report *pmr;
-	struct in6_addr addr_buf;
-	const struct in6_addr *saddr;
 	int hlen = LL_RESERVED_SPACE(dev);
 	int tlen = dev->needed_tailroom;
-	unsigned int size = mtu + hlen + tlen;
+	struct net *net = dev_net(dev);
+	const struct in6_addr *saddr;
+	struct in6_addr addr_buf;
+	struct mld2_report *pmr;
+	struct sk_buff *skb;
+	unsigned int size;
+	struct sock *sk;
 	int err;
-	u8 ra[8] = { IPPROTO_ICMPV6, 0,
-		     IPV6_TLV_ROUTERALERT, 2, 0, 0,
-		     IPV6_TLV_PADN, 0 };
 
-	/* we assume size > sizeof(ra) here */
+	sk = net->ipv6.igmp_sk;
+	/* we assume size > sizeof(ra) here
+	 * Also try to not allocate high-order pages for big MTU
+	 */
+	size = min_t(int, mtu, PAGE_SIZE / 2) + hlen + tlen;
 	skb = sock_alloc_send_skb(sk, size, 1, &err);
 	if (!skb)
 		return NULL;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index e810a23baf99..de2cf3943b91 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -51,7 +51,7 @@ ip6_packet_match(const struct sk_buff *skb,
 		 const char *outdev,
 		 const struct ip6t_ip6 *ip6info,
 		 unsigned int *protoff,
-		 int *fragoff, bool *hotdrop)
+		 u16 *fragoff, bool *hotdrop)
 {
 	unsigned long ret;
 	const struct ipv6hdr *ipv6 = ipv6_hdr(skb);
diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c
index 7969d1f3018d..ed69c768797e 100644
--- a/net/ipv6/netfilter/nft_reject_ipv6.c
+++ b/net/ipv6/netfilter/nft_reject_ipv6.c
@@ -28,7 +28,7 @@ static void nft_reject_ipv6_eval(const struct nft_expr *expr,
 				 nft_hook(pkt));
 		break;
 	case NFT_REJECT_TCP_RST:
-		nf_send_reset6(nft_net(pkt), pkt->xt.state->sk, pkt->skb,
+		nf_send_reset6(nft_net(pkt), nft_sk(pkt), pkt->skb,
 			       nft_hook(pkt));
 		break;
 	default:
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index af36acc1a644..2880dc7d9a49 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -15,29 +15,11 @@ static u32 __ipv6_select_ident(struct net *net,
 			       const struct in6_addr *dst,
 			       const struct in6_addr *src)
 {
-	const struct {
-		struct in6_addr dst;
-		struct in6_addr src;
-	} __aligned(SIPHASH_ALIGNMENT) combined = {
-		.dst = *dst,
-		.src = *src,
-	};
-	u32 hash, id;
-
-	/* Note the following code is not safe, but this is okay. */
-	if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key)))
-		get_random_bytes(&net->ipv4.ip_id_key,
-				 sizeof(net->ipv4.ip_id_key));
-
-	hash = siphash(&combined, sizeof(combined), &net->ipv4.ip_id_key);
-
-	/* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve,
-	 * set the hight order instead thus minimizing possible future
-	 * collisions.
-	 */
-	id = ip_idents_reserve(hash, 1);
-	if (unlikely(!id))
-		id = 1 << 31;
+	u32 id;
+
+	do {
+		id = prandom_u32();
+	} while (!id);
 
 	return id;
 }
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d417e514bd52..7b756a7dc036 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2326,12 +2326,131 @@ out:
 	}
 }
 
+static u32 rt6_multipath_custom_hash_outer(const struct net *net,
+					   const struct sk_buff *skb,
+					   bool *p_has_inner)
+{
+	u32 hash_fields = ip6_multipath_hash_fields(net);
+	struct flow_keys keys, hash_keys;
+
+	if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK))
+		return 0;
+
+	memset(&hash_keys, 0, sizeof(hash_keys));
+	skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_ENCAP);
+
+	hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP)
+		hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP)
+		hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO)
+		hash_keys.basic.ip_proto = keys.basic.ip_proto;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL)
+		hash_keys.tags.flow_label = keys.tags.flow_label;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT)
+		hash_keys.ports.src = keys.ports.src;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
+		hash_keys.ports.dst = keys.ports.dst;
+
+	*p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION);
+	return flow_hash_from_keys(&hash_keys);
+}
+
+static u32 rt6_multipath_custom_hash_inner(const struct net *net,
+					   const struct sk_buff *skb,
+					   bool has_inner)
+{
+	u32 hash_fields = ip6_multipath_hash_fields(net);
+	struct flow_keys keys, hash_keys;
+
+	/* We assume the packet carries an encapsulation, but if none was
+	 * encountered during dissection of the outer flow, then there is no
+	 * point in calling the flow dissector again.
+	 */
+	if (!has_inner)
+		return 0;
+
+	if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK))
+		return 0;
+
+	memset(&hash_keys, 0, sizeof(hash_keys));
+	skb_flow_dissect_flow_keys(skb, &keys, 0);
+
+	if (!(keys.control.flags & FLOW_DIS_ENCAPSULATION))
+		return 0;
+
+	if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+		hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP)
+			hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP)
+			hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
+	} else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+		hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP)
+			hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src;
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP)
+			hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst;
+		if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL)
+			hash_keys.tags.flow_label = keys.tags.flow_label;
+	}
+
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO)
+		hash_keys.basic.ip_proto = keys.basic.ip_proto;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT)
+		hash_keys.ports.src = keys.ports.src;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT)
+		hash_keys.ports.dst = keys.ports.dst;
+
+	return flow_hash_from_keys(&hash_keys);
+}
+
+static u32 rt6_multipath_custom_hash_skb(const struct net *net,
+					 const struct sk_buff *skb)
+{
+	u32 mhash, mhash_inner;
+	bool has_inner = true;
+
+	mhash = rt6_multipath_custom_hash_outer(net, skb, &has_inner);
+	mhash_inner = rt6_multipath_custom_hash_inner(net, skb, has_inner);
+
+	return jhash_2words(mhash, mhash_inner, 0);
+}
+
+static u32 rt6_multipath_custom_hash_fl6(const struct net *net,
+					 const struct flowi6 *fl6)
+{
+	u32 hash_fields = ip6_multipath_hash_fields(net);
+	struct flow_keys hash_keys;
+
+	if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK))
+		return 0;
+
+	memset(&hash_keys, 0, sizeof(hash_keys));
+	hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP)
+		hash_keys.addrs.v6addrs.src = fl6->saddr;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP)
+		hash_keys.addrs.v6addrs.dst = fl6->daddr;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO)
+		hash_keys.basic.ip_proto = fl6->flowi6_proto;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL)
+		hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT)
+		hash_keys.ports.src = fl6->fl6_sport;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
+		hash_keys.ports.dst = fl6->fl6_dport;
+
+	return flow_hash_from_keys(&hash_keys);
+}
+
 /* if skb is set it will be used and fl6 can be NULL */
 u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
 		       const struct sk_buff *skb, struct flow_keys *flkeys)
 {
 	struct flow_keys hash_keys;
-	u32 mhash;
+	u32 mhash = 0;
 
 	switch (ip6_multipath_hash_policy(net)) {
 	case 0:
@@ -2345,6 +2464,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
 			hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
 			hash_keys.basic.ip_proto = fl6->flowi6_proto;
 		}
+		mhash = flow_hash_from_keys(&hash_keys);
 		break;
 	case 1:
 		if (skb) {
@@ -2376,6 +2496,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
 			hash_keys.ports.dst = fl6->fl6_dport;
 			hash_keys.basic.ip_proto = fl6->flowi6_proto;
 		}
+		mhash = flow_hash_from_keys(&hash_keys);
 		break;
 	case 2:
 		memset(&hash_keys, 0, sizeof(hash_keys));
@@ -2412,9 +2533,15 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
 			hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
 			hash_keys.basic.ip_proto = fl6->flowi6_proto;
 		}
+		mhash = flow_hash_from_keys(&hash_keys);
+		break;
+	case 3:
+		if (skb)
+			mhash = rt6_multipath_custom_hash_skb(net, skb);
+		else
+			mhash = rt6_multipath_custom_hash_fl6(net, fl6);
 		break;
 	}
-	mhash = flow_hash_from_keys(&hash_keys);
 
 	return mhash >> 1;
 }
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 4ff38cb08f4b..60bf3b877957 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -87,10 +87,10 @@ struct seg6_end_dt_info {
 	int vrf_ifindex;
 	int vrf_table;
 
-	/* tunneled packet proto and family (IPv4 or IPv6) */
-	__be16 proto;
+	/* tunneled packet family (IPv4 or IPv6).
+	 * Protocol and header length are inferred from family.
+	 */
 	u16 family;
-	int hdrlen;
 };
 
 struct pcpu_seg6_local_counters {
@@ -521,19 +521,6 @@ static int __seg6_end_dt_vrf_build(struct seg6_local_lwt *slwt, const void *cfg,
 	info->net = net;
 	info->vrf_ifindex = vrf_ifindex;
 
-	switch (family) {
-	case AF_INET:
-		info->proto = htons(ETH_P_IP);
-		info->hdrlen = sizeof(struct iphdr);
-		break;
-	case AF_INET6:
-		info->proto = htons(ETH_P_IPV6);
-		info->hdrlen = sizeof(struct ipv6hdr);
-		break;
-	default:
-		return -EINVAL;
-	}
-
 	info->family = family;
 	info->mode = DT_VRF_MODE;
 
@@ -622,22 +609,44 @@ error:
 }
 
 static struct sk_buff *end_dt_vrf_core(struct sk_buff *skb,
-				       struct seg6_local_lwt *slwt)
+				       struct seg6_local_lwt *slwt, u16 family)
 {
 	struct seg6_end_dt_info *info = &slwt->dt_info;
 	struct net_device *vrf;
+	__be16 protocol;
+	int hdrlen;
 
 	vrf = end_dt_get_vrf_rcu(skb, info);
 	if (unlikely(!vrf))
 		goto drop;
 
-	skb->protocol = info->proto;
+	switch (family) {
+	case AF_INET:
+		protocol = htons(ETH_P_IP);
+		hdrlen = sizeof(struct iphdr);
+		break;
+	case AF_INET6:
+		protocol = htons(ETH_P_IPV6);
+		hdrlen = sizeof(struct ipv6hdr);
+		break;
+	case AF_UNSPEC:
+		fallthrough;
+	default:
+		goto drop;
+	}
+
+	if (unlikely(info->family != AF_UNSPEC && info->family != family)) {
+		pr_warn_once("seg6local: SRv6 End.DT* family mismatch");
+		goto drop;
+	}
+
+	skb->protocol = protocol;
 
 	skb_dst_drop(skb);
 
-	skb_set_transport_header(skb, info->hdrlen);
+	skb_set_transport_header(skb, hdrlen);
 
-	return end_dt_vrf_rcv(skb, info->family, vrf);
+	return end_dt_vrf_rcv(skb, family, vrf);
 
 drop:
 	kfree_skb(skb);
@@ -656,7 +665,7 @@ static int input_action_end_dt4(struct sk_buff *skb,
 	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
 		goto drop;
 
-	skb = end_dt_vrf_core(skb, slwt);
+	skb = end_dt_vrf_core(skb, slwt, AF_INET);
 	if (!skb)
 		/* packet has been processed and consumed by the VRF */
 		return 0;
@@ -739,7 +748,7 @@ static int input_action_end_dt6(struct sk_buff *skb,
 		goto legacy_mode;
 
 	/* DT6_VRF_MODE */
-	skb = end_dt_vrf_core(skb, slwt);
+	skb = end_dt_vrf_core(skb, slwt, AF_INET6);
 	if (!skb)
 		/* packet has been processed and consumed by the VRF */
 		return 0;
@@ -767,6 +776,36 @@ drop:
 	return -EINVAL;
 }
 
+#ifdef CONFIG_NET_L3_MASTER_DEV
+static int seg6_end_dt46_build(struct seg6_local_lwt *slwt, const void *cfg,
+			       struct netlink_ext_ack *extack)
+{
+	return __seg6_end_dt_vrf_build(slwt, cfg, AF_UNSPEC, extack);
+}
+
+static int input_action_end_dt46(struct sk_buff *skb,
+				 struct seg6_local_lwt *slwt)
+{
+	unsigned int off = 0;
+	int nexthdr;
+
+	nexthdr = ipv6_find_hdr(skb, &off, -1, NULL, NULL);
+	if (unlikely(nexthdr < 0))
+		goto drop;
+
+	switch (nexthdr) {
+	case IPPROTO_IPIP:
+		return input_action_end_dt4(skb, slwt);
+	case IPPROTO_IPV6:
+		return input_action_end_dt6(skb, slwt);
+	}
+
+drop:
+	kfree_skb(skb);
+	return -EINVAL;
+}
+#endif
+
 /* push an SRH on top of the current one */
 static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt)
 {
@@ -969,6 +1008,17 @@ static struct seg6_action_desc seg6_action_table[] = {
 		.input		= input_action_end_dt6,
 	},
 	{
+		.action		= SEG6_LOCAL_ACTION_END_DT46,
+		.attrs		= SEG6_F_ATTR(SEG6_LOCAL_VRFTABLE),
+		.optattrs	= SEG6_F_LOCAL_COUNTERS,
+#ifdef CONFIG_NET_L3_MASTER_DEV
+		.input		= input_action_end_dt46,
+		.slwt_ops	= {
+					.build_state = seg6_end_dt46_build,
+				  },
+#endif
+	},
+	{
 		.action		= SEG6_LOCAL_ACTION_END_B6,
 		.attrs		= SEG6_F_ATTR(SEG6_LOCAL_SRH),
 		.optattrs	= SEG6_F_LOCAL_COUNTERS,
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index f7c8110ece5f..e0a39b0bb4c1 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -973,7 +973,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	if (df) {
 		mtu = dst_mtu(&rt->dst) - t_hlen;
 
-		if (mtu < 68) {
+		if (mtu < IPV4_MIN_MTU) {
 			dev->stats.collisions++;
 			ip_rt_put(rt);
 			goto tx_error;
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index 27102c3d6e1d..d7cf26f730d7 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -17,13 +17,17 @@
 #include <net/addrconf.h>
 #include <net/inet_frag.h>
 #include <net/netevent.h>
+#include <net/ip_fib.h>
 #ifdef CONFIG_NETLABEL
 #include <net/calipso.h>
 #endif
 
 static int two = 2;
+static int three = 3;
 static int flowlabel_reflect_max = 0x7;
 static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX;
+static u32 rt6_multipath_hash_fields_all_mask =
+	FIB_MULTIPATH_HASH_FIELD_ALL_MASK;
 
 static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write,
 					  void *buffer, size_t *lenp, loff_t *ppos)
@@ -40,6 +44,22 @@ static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write,
 	return ret;
 }
 
+static int
+proc_rt6_multipath_hash_fields(struct ctl_table *table, int write, void *buffer,
+			       size_t *lenp, loff_t *ppos)
+{
+	struct net *net;
+	int ret;
+
+	net = container_of(table->data, struct net,
+			   ipv6.sysctl.multipath_hash_fields);
+	ret = proc_douintvec_minmax(table, write, buffer, lenp, ppos);
+	if (write && ret == 0)
+		call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net);
+
+	return ret;
+}
+
 static struct ctl_table ipv6_table_template[] = {
 	{
 		.procname	= "bindv6only",
@@ -149,7 +169,16 @@ static struct ctl_table ipv6_table_template[] = {
 		.mode		= 0644,
 		.proc_handler   = proc_rt6_multipath_hash_policy,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &two,
+		.extra2		= &three,
+	},
+	{
+		.procname	= "fib_multipath_hash_fields",
+		.data		= &init_net.ipv6.sysctl.multipath_hash_fields,
+		.maxlen		= sizeof(u32),
+		.mode		= 0644,
+		.proc_handler	= proc_rt6_multipath_hash_fields,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= &rt6_multipath_hash_fields_all_mask,
 	},
 	{
 		.procname	= "seg6_flowlabel",
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5f47c0b6e3de..4d71464094b3 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1538,6 +1538,7 @@ discard:
 	kfree_skb(skb);
 	return 0;
 csum_err:
+	trace_tcp_bad_csum(skb);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
 	goto discard;
@@ -1663,10 +1664,18 @@ process:
 			goto csum_error;
 		}
 		if (unlikely(sk->sk_state != TCP_LISTEN)) {
-			inet_csk_reqsk_queue_drop_and_put(sk, req);
-			goto lookup;
+			nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb);
+			if (!nsk) {
+				inet_csk_reqsk_queue_drop_and_put(sk, req);
+				goto lookup;
+			}
+			sk = nsk;
+			/* reuseport_migrate_sock() has already held one sk_refcnt
+			 * before returning.
+			 */
+		} else {
+			sock_hold(sk);
 		}
-		sock_hold(sk);
 		refcounted = true;
 		nsk = NULL;
 		if (!tcp_filter(sk, skb)) {
@@ -1754,6 +1763,7 @@ no_tcp_socket:
 
 	if (tcp_checksum_complete(skb)) {
 csum_error:
+		trace_tcp_bad_csum(skb);
 		__TCP_INC_STATS(net, TCP_MIB_CSUMERRORS);
 bad_packet:
 		__TCP_INC_STATS(net, TCP_MIB_INERRS);
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 0fdb389c3390..44453b35c7b7 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -44,6 +44,7 @@ static struct proto iucv_proto = {
 };
 
 static struct iucv_interface *pr_iucv;
+static struct iucv_handler af_iucv_handler;
 
 /* special AF_IUCV IPRM messages */
 static const u8 iprm_shutdown[8] =
@@ -91,28 +92,11 @@ static void iucv_sock_close(struct sock *sk);
 
 static void afiucv_hs_callback_txnotify(struct sock *sk, enum iucv_tx_notify);
 
-/* Call Back functions */
-static void iucv_callback_rx(struct iucv_path *, struct iucv_message *);
-static void iucv_callback_txdone(struct iucv_path *, struct iucv_message *);
-static void iucv_callback_connack(struct iucv_path *, u8 *);
-static int iucv_callback_connreq(struct iucv_path *, u8 *, u8 *);
-static void iucv_callback_connrej(struct iucv_path *, u8 *);
-static void iucv_callback_shutdown(struct iucv_path *, u8 *);
-
 static struct iucv_sock_list iucv_sk_list = {
 	.lock = __RW_LOCK_UNLOCKED(iucv_sk_list.lock),
 	.autobind_name = ATOMIC_INIT(0)
 };
 
-static struct iucv_handler af_iucv_handler = {
-	.path_pending	  = iucv_callback_connreq,
-	.path_complete	  = iucv_callback_connack,
-	.path_severed	  = iucv_callback_connrej,
-	.message_pending  = iucv_callback_rx,
-	.message_complete = iucv_callback_txdone,
-	.path_quiesced	  = iucv_callback_shutdown,
-};
-
 static inline void high_nmcpy(unsigned char *dst, char *src)
 {
        memcpy(dst, src, 8);
@@ -1817,6 +1801,15 @@ static void iucv_callback_shutdown(struct iucv_path *path, u8 ipuser[16])
 	bh_unlock_sock(sk);
 }
 
+static struct iucv_handler af_iucv_handler = {
+	.path_pending		= iucv_callback_connreq,
+	.path_complete		= iucv_callback_connack,
+	.path_severed		= iucv_callback_connrej,
+	.message_pending	= iucv_callback_rx,
+	.message_complete	= iucv_callback_txdone,
+	.path_quiesced		= iucv_callback_shutdown,
+};
+
 /***************** HiperSockets transport callbacks ********************/
 static void afiucv_swap_src_dest(struct sk_buff *skb)
 {
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 97ae1255fcb6..b3edafa5fba4 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -488,7 +488,7 @@ static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		}
 	}
 
-	/* We dont need to clone dst here, it is guaranteed to not disappear.
+	/* We don't need to clone dst here, it is guaranteed to not disappear.
 	 *  __dev_xmit_skb() might force a refcount if needed.
 	 */
 	skb_dst_set_noref(skb, &rt->dst);
@@ -635,7 +635,6 @@ static struct inet_protosw l2tp_ip_protosw = {
 
 static struct net_protocol l2tp_ip_protocol __read_mostly = {
 	.handler	= l2tp_ip_recv,
-	.netns_ok	= 1,
 };
 
 static int __init l2tp_ip_init(void)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index aea85f91f059..bf35710127dd 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -226,7 +226,7 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int
 	/* If the first two bytes are 0xFF03, consider that it is the PPP's
 	 * Address and Control fields and skip them. The L2TP module has always
 	 * worked this way, although, in theory, the use of these fields should
-	 * be negociated and handled at the PPP layer. These fields are
+	 * be negotiated and handled at the PPP layer. These fields are
 	 * constant: 0xFF is the All-Stations Address and 0x03 the Unnumbered
 	 * Information command with Poll/Final bit set to zero (RFC 1662).
 	 */
diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c
index 1078e14f1acf..0971ca48ba15 100644
--- a/net/lapb/lapb_iface.c
+++ b/net/lapb/lapb_iface.c
@@ -80,11 +80,9 @@ static void __lapb_insert_cb(struct lapb_cb *lapb)
 
 static struct lapb_cb *__lapb_devtostruct(struct net_device *dev)
 {
-	struct list_head *entry;
 	struct lapb_cb *lapb, *use = NULL;
 
-	list_for_each(entry, &lapb_list) {
-		lapb = list_entry(entry, struct lapb_cb, node);
+	list_for_each_entry(lapb, &lapb_list, node) {
 		if (lapb->dev == dev) {
 			use = lapb;
 			break;
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 96ba616f59bf..6c2639bb9c19 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -4,7 +4,9 @@
  * Copyright (c) 2019, Tessares SA.
  */
 
+#ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
+#endif
 
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
@@ -15,10 +17,13 @@
 
 static int mptcp_pernet_id;
 struct mptcp_pernet {
+#ifdef CONFIG_SYSCTL
 	struct ctl_table_header *ctl_table_hdr;
+#endif
 
-	int mptcp_enabled;
+	u8 mptcp_enabled;
 	unsigned int add_addr_timeout;
+	u8 checksum_enabled;
 };
 
 static struct mptcp_pernet *mptcp_get_pernet(struct net *net)
@@ -36,15 +41,30 @@ unsigned int mptcp_get_add_addr_timeout(struct net *net)
 	return mptcp_get_pernet(net)->add_addr_timeout;
 }
 
+int mptcp_is_checksum_enabled(struct net *net)
+{
+	return mptcp_get_pernet(net)->checksum_enabled;
+}
+
+static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
+{
+	pernet->mptcp_enabled = 1;
+	pernet->add_addr_timeout = TCP_RTO_MAX;
+	pernet->checksum_enabled = 0;
+}
+
+#ifdef CONFIG_SYSCTL
 static struct ctl_table mptcp_sysctl_table[] = {
 	{
 		.procname = "enabled",
-		.maxlen = sizeof(int),
+		.maxlen = sizeof(u8),
 		.mode = 0644,
 		/* users with CAP_NET_ADMIN or root (not and) can change this
 		 * value, same as other sysctl or the 'net' tree.
 		 */
-		.proc_handler = proc_dointvec,
+		.proc_handler = proc_dou8vec_minmax,
+		.extra1       = SYSCTL_ZERO,
+		.extra2       = SYSCTL_ONE
 	},
 	{
 		.procname = "add_addr_timeout",
@@ -52,15 +72,17 @@ static struct ctl_table mptcp_sysctl_table[] = {
 		.mode = 0644,
 		.proc_handler = proc_dointvec_jiffies,
 	},
+	{
+		.procname = "checksum_enabled",
+		.maxlen = sizeof(u8),
+		.mode = 0644,
+		.proc_handler = proc_dou8vec_minmax,
+		.extra1       = SYSCTL_ZERO,
+		.extra2       = SYSCTL_ONE
+	},
 	{}
 };
 
-static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
-{
-	pernet->mptcp_enabled = 1;
-	pernet->add_addr_timeout = TCP_RTO_MAX;
-}
-
 static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
 {
 	struct ctl_table_header *hdr;
@@ -75,6 +97,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
 
 	table[0].data = &pernet->mptcp_enabled;
 	table[1].data = &pernet->add_addr_timeout;
+	table[2].data = &pernet->checksum_enabled;
 
 	hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table);
 	if (!hdr)
@@ -100,6 +123,17 @@ static void mptcp_pernet_del_table(struct mptcp_pernet *pernet)
 	kfree(table);
 }
 
+#else
+
+static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
+{
+	return 0;
+}
+
+static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) {}
+
+#endif /* CONFIG_SYSCTL */
+
 static int __net_init mptcp_net_init(struct net *net)
 {
 	struct mptcp_pernet *pernet = mptcp_get_pernet(net);
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index eb2dc6dbe212..e7e60bc1fb96 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -25,6 +25,7 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC),
 	SNMP_MIB_ITEM("DSSNotMatching", MPTCP_MIB_DSSNOMATCH),
 	SNMP_MIB_ITEM("InfiniteMapRx", MPTCP_MIB_INFINITEMAPRX),
+	SNMP_MIB_ITEM("DataCsumErr", MPTCP_MIB_DATACSUMERR),
 	SNMP_MIB_ITEM("OFOQueueTail", MPTCP_MIB_OFOQUEUETAIL),
 	SNMP_MIB_ITEM("OFOQueue", MPTCP_MIB_OFOQUEUE),
 	SNMP_MIB_ITEM("OFOMerge", MPTCP_MIB_OFOMERGE),
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index f0da4f060fe1..92e56c0cfbdd 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -18,6 +18,7 @@ enum linux_mptcp_mib_field {
 	MPTCP_MIB_JOINACKMAC,		/* HMAC was wrong on ACK + MP_JOIN */
 	MPTCP_MIB_DSSNOMATCH,		/* Received a new mapping that did not match the previous one */
 	MPTCP_MIB_INFINITEMAPRX,	/* Received an infinite mapping */
+	MPTCP_MIB_DATACSUMERR,		/* The data checksum fail */
 	MPTCP_MIB_OFOQUEUETAIL,	/* Segments inserted into OoO queue tail */
 	MPTCP_MIB_OFOQUEUE,		/* Segments inserted into OoO queue */
 	MPTCP_MIB_OFOMERGE,		/* Segments merged in OoO queue */
diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c
index f16d9b5ee978..8f88ddeab6a2 100644
--- a/net/mptcp/mptcp_diag.c
+++ b/net/mptcp/mptcp_diag.c
@@ -144,6 +144,7 @@ static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 	info->mptcpi_write_seq = READ_ONCE(msk->write_seq);
 	info->mptcpi_snd_una = READ_ONCE(msk->snd_una);
 	info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq);
+	info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled);
 	unlock_sock_fast(sk, slow);
 }
 
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 9b263f27ce9b..25189595ed1d 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -44,7 +44,20 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 			else
 				expected_opsize = TCPOLEN_MPTCP_MPC_SYN;
 		}
-		if (opsize != expected_opsize)
+
+		/* Cfr RFC 8684 Section 3.3.0:
+		 * If a checksum is present but its use had
+		 * not been negotiated in the MP_CAPABLE handshake, the receiver MUST
+		 * close the subflow with a RST, as it is not behaving as negotiated.
+		 * If a checksum is not present when its use has been negotiated, the
+		 * receiver MUST close the subflow with a RST, as it is considered
+		 * broken
+		 * We parse even option with mismatching csum presence, so that
+		 * later in subflow_data_ready we can trigger the reset.
+		 */
+		if (opsize != expected_opsize &&
+		    (expected_opsize != TCPOLEN_MPTCP_MPC_ACK_DATA ||
+		     opsize != TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM))
 			break;
 
 		/* try to be gentle vs future versions on the initial syn */
@@ -66,16 +79,9 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		 * host requires the use of checksums, checksums MUST be used.
 		 * In other words, the only way for checksums not to be used
 		 * is if both hosts in their SYNs set A=0."
-		 *
-		 * Section 3.3.0:
-		 * "If a checksum is not present when its use has been
-		 * negotiated, the receiver MUST close the subflow with a RST as
-		 * it is considered broken."
-		 *
-		 * We don't implement DSS checksum - fall back to TCP.
 		 */
 		if (flags & MPTCP_CAP_CHECKSUM_REQD)
-			break;
+			mp_opt->csum_reqd = 1;
 
 		mp_opt->mp_capable = 1;
 		if (opsize >= TCPOLEN_MPTCP_MPC_SYNACK) {
@@ -86,7 +92,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 			mp_opt->rcvr_key = get_unaligned_be64(ptr);
 			ptr += 8;
 		}
-		if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA) {
+		if (opsize >= TCPOLEN_MPTCP_MPC_ACK_DATA) {
 			/* Section 3.1.:
 			 * "the data parameters in a MP_CAPABLE are semantically
 			 * equivalent to those in a DSS option and can be used
@@ -98,9 +104,14 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 			mp_opt->data_len = get_unaligned_be16(ptr);
 			ptr += 2;
 		}
-		pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d",
+		if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM) {
+			mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr);
+			mp_opt->csum_reqd = 1;
+			ptr += 2;
+		}
+		pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u",
 			 version, flags, opsize, mp_opt->sndr_key,
-			 mp_opt->rcvr_key, mp_opt->data_len);
+			 mp_opt->rcvr_key, mp_opt->data_len, mp_opt->csum);
 		break;
 
 	case MPTCPOPT_MP_JOIN:
@@ -171,10 +182,8 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 				expected_opsize += TCPOLEN_MPTCP_DSS_MAP32;
 		}
 
-		/* RFC 6824, Section 3.3:
-		 * If a checksum is present, but its use had
-		 * not been negotiated in the MP_CAPABLE handshake,
-		 * the checksum field MUST be ignored.
+		/* Always parse any csum presence combination, we will enforce
+		 * RFC 8684 Section 3.3.0 checks later in subflow_data_ready
 		 */
 		if (opsize != expected_opsize &&
 		    opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM)
@@ -209,9 +218,15 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 			mp_opt->data_len = get_unaligned_be16(ptr);
 			ptr += 2;
 
-			pr_debug("data_seq=%llu subflow_seq=%u data_len=%u",
+			if (opsize == expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) {
+				mp_opt->csum_reqd = 1;
+				mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr);
+				ptr += 2;
+			}
+
+			pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u",
 				 mp_opt->data_seq, mp_opt->subflow_seq,
-				 mp_opt->data_len);
+				 mp_opt->data_len, mp_opt->csum_reqd, mp_opt->csum);
 		}
 
 		break;
@@ -323,9 +338,12 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 	}
 }
 
-void mptcp_get_options(const struct sk_buff *skb,
+void mptcp_get_options(const struct sock *sk,
+		       const struct sk_buff *skb,
 		       struct mptcp_options_received *mp_opt)
 {
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
 	const struct tcphdr *th = tcp_hdr(skb);
 	const unsigned char *ptr;
 	int length;
@@ -341,6 +359,7 @@ void mptcp_get_options(const struct sk_buff *skb,
 	mp_opt->dss = 0;
 	mp_opt->mp_prio = 0;
 	mp_opt->reset = 0;
+	mp_opt->csum_reqd = READ_ONCE(msk->csum_enabled);
 
 	length = (th->doff * 4) - sizeof(struct tcphdr);
 	ptr = (const unsigned char *)(th + 1);
@@ -382,6 +401,7 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
 	subflow->snd_isn = TCP_SKB_CB(skb)->end_seq;
 	if (subflow->request_mptcp) {
 		opts->suboptions = OPTION_MPTCP_MPC_SYN;
+		opts->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk));
 		*size = TCPOLEN_MPTCP_MPC_SYN;
 		return true;
 	} else if (subflow->request_join) {
@@ -437,8 +457,10 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
 					 struct mptcp_out_options *opts)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
 	struct mptcp_ext *mpext;
 	unsigned int data_len;
+	u8 len;
 
 	/* When skb is not available, we better over-estimate the emitted
 	 * options len. A full DSS option (28 bytes) is longer than
@@ -467,16 +489,26 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
 		opts->suboptions = OPTION_MPTCP_MPC_ACK;
 		opts->sndr_key = subflow->local_key;
 		opts->rcvr_key = subflow->remote_key;
+		opts->csum_reqd = READ_ONCE(msk->csum_enabled);
 
 		/* Section 3.1.
 		 * The MP_CAPABLE option is carried on the SYN, SYN/ACK, and ACK
 		 * packets that start the first subflow of an MPTCP connection,
 		 * as well as the first packet that carries data
 		 */
-		if (data_len > 0)
-			*size = ALIGN(TCPOLEN_MPTCP_MPC_ACK_DATA, 4);
-		else
+		if (data_len > 0) {
+			len = TCPOLEN_MPTCP_MPC_ACK_DATA;
+			if (opts->csum_reqd) {
+				/* we need to propagate more info to csum the pseudo hdr */
+				opts->ext_copy.data_seq = mpext->data_seq;
+				opts->ext_copy.subflow_seq = mpext->subflow_seq;
+				opts->ext_copy.csum = mpext->csum;
+				len += TCPOLEN_MPTCP_DSS_CHECKSUM;
+			}
+			*size = ALIGN(len, 4);
+		} else {
 			*size = TCPOLEN_MPTCP_MPC_ACK;
+		}
 
 		pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d",
 			 subflow, subflow->local_key, subflow->remote_key,
@@ -537,18 +569,21 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 	bool ret = false;
 	u64 ack_seq;
 
+	opts->csum_reqd = READ_ONCE(msk->csum_enabled);
 	mpext = skb ? mptcp_get_ext(skb) : NULL;
 
 	if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) {
-		unsigned int map_size;
+		unsigned int map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64;
 
-		map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64;
+		if (mpext) {
+			if (opts->csum_reqd)
+				map_size += TCPOLEN_MPTCP_DSS_CHECKSUM;
 
-		remaining -= map_size;
-		dss_size = map_size;
-		if (mpext)
 			opts->ext_copy = *mpext;
+		}
 
+		remaining -= map_size;
+		dss_size = map_size;
 		if (skb && snd_data_fin_enable)
 			mptcp_write_data_fin(subflow, skb, &opts->ext_copy);
 		ret = true;
@@ -791,6 +826,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
 	if (subflow_req->mp_capable) {
 		opts->suboptions = OPTION_MPTCP_MPC_SYNACK;
 		opts->sndr_key = subflow_req->local_key;
+		opts->csum_reqd = subflow_req->csum_reqd;
 		*size = TCPOLEN_MPTCP_MPC_SYNACK;
 		pr_debug("subflow_req=%p, local_key=%llu",
 			 subflow_req, subflow_req->local_key);
@@ -1009,7 +1045,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 		return;
 	}
 
-	mptcp_get_options(skb, &mp_opt);
+	mptcp_get_options(sk, skb, &mp_opt);
 	if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
 		return;
 
@@ -1101,6 +1137,10 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 		}
 		mpext->data_len = mp_opt.data_len;
 		mpext->use_map = 1;
+		mpext->csum_reqd = mp_opt.csum_reqd;
+
+		if (mpext->csum_reqd)
+			mpext->csum = mp_opt.csum;
 	}
 }
 
@@ -1120,25 +1160,50 @@ static void mptcp_set_rwin(const struct tcp_sock *tp)
 		WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
 }
 
+static u16 mptcp_make_csum(const struct mptcp_ext *mpext)
+{
+	struct csum_pseudo_header header;
+	__wsum csum;
+
+	/* cfr RFC 8684 3.3.1.:
+	 * the data sequence number used in the pseudo-header is
+	 * always the 64-bit value, irrespective of what length is used in the
+	 * DSS option itself.
+	 */
+	header.data_seq = cpu_to_be64(mpext->data_seq);
+	header.subflow_seq = htonl(mpext->subflow_seq);
+	header.data_len = htons(mpext->data_len);
+	header.csum = 0;
+
+	csum = csum_partial(&header, sizeof(header), ~csum_unfold(mpext->csum));
+	return (__force u16)csum_fold(csum);
+}
+
 void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 			 struct mptcp_out_options *opts)
 {
 	if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
 	     OPTION_MPTCP_MPC_ACK) & opts->suboptions) {
-		u8 len;
+		u8 len, flag = MPTCP_CAP_HMAC_SHA256;
 
-		if (OPTION_MPTCP_MPC_SYN & opts->suboptions)
+		if (OPTION_MPTCP_MPC_SYN & opts->suboptions) {
 			len = TCPOLEN_MPTCP_MPC_SYN;
-		else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions)
+		} else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions) {
 			len = TCPOLEN_MPTCP_MPC_SYNACK;
-		else if (opts->ext_copy.data_len)
+		} else if (opts->ext_copy.data_len) {
 			len = TCPOLEN_MPTCP_MPC_ACK_DATA;
-		else
+			if (opts->csum_reqd)
+				len += TCPOLEN_MPTCP_DSS_CHECKSUM;
+		} else {
 			len = TCPOLEN_MPTCP_MPC_ACK;
+		}
+
+		if (opts->csum_reqd)
+			flag |= MPTCP_CAP_CHECKSUM_REQD;
 
 		*ptr++ = mptcp_option(MPTCPOPT_MP_CAPABLE, len,
 				      MPTCP_SUPPORTED_VERSION,
-				      MPTCP_CAP_HMAC_SHA256);
+				      flag);
 
 		if (!((OPTION_MPTCP_MPC_SYNACK | OPTION_MPTCP_MPC_ACK) &
 		    opts->suboptions))
@@ -1154,8 +1219,13 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 		if (!opts->ext_copy.data_len)
 			goto mp_capable_done;
 
-		put_unaligned_be32(opts->ext_copy.data_len << 16 |
-				   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
+		if (opts->csum_reqd) {
+			put_unaligned_be32(opts->ext_copy.data_len << 16 |
+					   mptcp_make_csum(&opts->ext_copy), ptr);
+		} else {
+			put_unaligned_be32(opts->ext_copy.data_len << 16 |
+					   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
+		}
 		ptr += 1;
 	}
 
@@ -1307,6 +1377,9 @@ mp_capable_done:
 			flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64;
 			if (mpext->data_fin)
 				flags |= MPTCP_DSS_DATA_FIN;
+
+			if (opts->csum_reqd)
+				len += TCPOLEN_MPTCP_DSS_CHECKSUM;
 		}
 
 		*ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags);
@@ -1326,8 +1399,13 @@ mp_capable_done:
 			ptr += 2;
 			put_unaligned_be32(mpext->subflow_seq, ptr);
 			ptr += 1;
-			put_unaligned_be32(mpext->data_len << 16 |
-					   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
+			if (opts->csum_reqd) {
+				put_unaligned_be32(mpext->data_len << 16 |
+						   mptcp_make_csum(mpext), ptr);
+			} else {
+				put_unaligned_be32(mpext->data_len << 16 |
+						   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
+			}
 		}
 	}
 
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 2469e06a3a9d..09722598994d 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -971,8 +971,14 @@ skip_family:
 	if (tb[MPTCP_PM_ADDR_ATTR_FLAGS])
 		entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]);
 
-	if (tb[MPTCP_PM_ADDR_ATTR_PORT])
+	if (tb[MPTCP_PM_ADDR_ATTR_PORT]) {
+		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
+			NL_SET_ERR_MSG_ATTR(info->extack, attr,
+					    "flags must have signal when using port");
+			return -EINVAL;
+		}
 		entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT]));
+	}
 
 	return 0;
 }
@@ -1913,10 +1919,13 @@ static int __net_init pm_nl_init_net(struct net *net)
 	struct pm_nl_pernet *pernet = net_generic(net, pm_nl_pernet_id);
 
 	INIT_LIST_HEAD_RCU(&pernet->local_addr_list);
-	__reset_counters(pernet);
 	pernet->next_id = 1;
-	bitmap_zero(pernet->id_bitmap, MAX_ADDR_ID + 1);
 	spin_lock_init(&pernet->lock);
+
+	/* No need to initialize other pernet fields, the struct is zeroed at
+	 * allocation time.
+	 */
+
 	return 0;
 }
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 632350018fb6..b5f2f504b85b 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -39,10 +39,15 @@ struct mptcp_skb_cb {
 	u64 map_seq;
 	u64 end_seq;
 	u32 offset;
+	u8  has_rxtstamp:1;
 };
 
 #define MPTCP_SKB_CB(__skb)	((struct mptcp_skb_cb *)&((__skb)->cb[0]))
 
+enum {
+	MPTCP_CMSG_TS = BIT(0),
+};
+
 static struct percpu_counter mptcp_sockets_allocated;
 
 static void __mptcp_destroy_sock(struct sock *sk);
@@ -272,6 +277,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	struct sock *sk = (struct sock *)msk;
 	struct sk_buff *tail;
+	bool has_rxtstamp;
 
 	__skb_unlink(skb, &ssk->sk_receive_queue);
 
@@ -289,6 +295,8 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
 		sk->sk_forward_alloc += amount;
 	}
 
+	has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
+
 	/* the skb map_seq accounts for the skb offset:
 	 * mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq
 	 * value
@@ -296,6 +304,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
 	MPTCP_SKB_CB(skb)->map_seq = mptcp_subflow_get_mapped_dsn(subflow);
 	MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + copy_len;
 	MPTCP_SKB_CB(skb)->offset = offset;
+	MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp;
 
 	if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) {
 		/* in sequence */
@@ -1298,6 +1307,18 @@ static bool mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk)
 	return __mptcp_alloc_tx_skb(sk, ssk, sk->sk_allocation);
 }
 
+/* note: this always recompute the csum on the whole skb, even
+ * if we just appended a single frag. More status info needed
+ */
+static void mptcp_update_data_checksum(struct sk_buff *skb, int added)
+{
+	struct mptcp_ext *mpext = mptcp_get_ext(skb);
+	__wsum csum = ~csum_unfold(mpext->csum);
+	int offset = skb->len - added;
+
+	mpext->csum = csum_fold(csum_block_add(csum, skb_checksum(skb, offset, added, 0), offset));
+}
+
 static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 			      struct mptcp_data_frag *dfrag,
 			      struct mptcp_sendmsg_info *info)
@@ -1392,10 +1413,14 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 	if (zero_window_probe) {
 		mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
 		mpext->frozen = 1;
-		ret = 0;
+		if (READ_ONCE(msk->csum_enabled))
+			mptcp_update_data_checksum(tail, ret);
 		tcp_push_pending_frames(ssk);
+		return 0;
 	}
 out:
+	if (READ_ONCE(msk->csum_enabled))
+		mptcp_update_data_checksum(tail, ret);
 	mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
 	return ret;
 }
@@ -1770,7 +1795,9 @@ static void mptcp_wait_data(struct sock *sk, long *timeo)
 
 static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 				struct msghdr *msg,
-				size_t len, int flags)
+				size_t len, int flags,
+				struct scm_timestamping_internal *tss,
+				int *cmsg_flags)
 {
 	struct sk_buff *skb, *tmp;
 	int copied = 0;
@@ -1790,6 +1817,11 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 			}
 		}
 
+		if (MPTCP_SKB_CB(skb)->has_rxtstamp) {
+			tcp_update_recv_tstamps(skb, tss);
+			*cmsg_flags |= MPTCP_CMSG_TS;
+		}
+
 		copied += count;
 
 		if (count < data_len) {
@@ -1980,7 +2012,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 			 int nonblock, int flags, int *addr_len)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	int copied = 0;
+	struct scm_timestamping_internal tss;
+	int copied = 0, cmsg_flags = 0;
 	int target;
 	long timeo;
 
@@ -2002,7 +2035,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	while (copied < len) {
 		int bytes_read;
 
-		bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags);
+		bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags, &tss, &cmsg_flags);
 		if (unlikely(bytes_read < 0)) {
 			if (!copied)
 				copied = bytes_read;
@@ -2083,6 +2116,11 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		set_bit(MPTCP_DATA_READY, &msk->flags);
 	}
 out_err:
+	if (cmsg_flags && copied >= 0) {
+		if (cmsg_flags & MPTCP_CMSG_TS)
+			tcp_recv_timestamp(msg, sk, &tss);
+	}
+
 	pr_debug("msk=%p data_ready=%d rx queue empty=%d copied=%d",
 		 msk, test_bit(MPTCP_DATA_READY, &msk->flags),
 		 skb_queue_empty_lockless(&sk->sk_receive_queue), copied);
@@ -2339,8 +2377,8 @@ static void __mptcp_retrans(struct sock *sk)
 
 	/* limit retransmission to the bytes already sent on some subflows */
 	info.sent = 0;
-	info.limit = dfrag->already_sent;
-	while (info.sent < dfrag->already_sent) {
+	info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent;
+	while (info.sent < info.limit) {
 		if (!mptcp_alloc_tx_skb(sk, ssk))
 			break;
 
@@ -2352,9 +2390,11 @@ static void __mptcp_retrans(struct sock *sk)
 		copied += ret;
 		info.sent += ret;
 	}
-	if (copied)
+	if (copied) {
+		dfrag->already_sent = max(dfrag->already_sent, info.sent);
 		tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
 			 info.size_goal);
+	}
 
 	mptcp_set_timeout(sk, ssk);
 	release_sock(ssk);
@@ -2433,6 +2473,7 @@ static int __mptcp_init_sock(struct sock *sk)
 	msk->ack_hint = NULL;
 	msk->first = NULL;
 	inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
+	WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));
 
 	mptcp_pm_data_init(msk);
 
@@ -2773,6 +2814,8 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 	msk->token = subflow_req->token;
 	msk->subflow = NULL;
 	WRITE_ONCE(msk->fully_established, false);
+	if (mp_opt->csum_reqd)
+		WRITE_ONCE(msk->csum_enabled, true);
 
 	msk->write_seq = subflow_req->idsn + 1;
 	msk->snd_nxt = msk->write_seq;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 385796f0ef19..160d716ebc2b 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -68,6 +68,8 @@
 #define TCPOLEN_MPTCP_FASTCLOSE		12
 #define TCPOLEN_MPTCP_RST		4
 
+#define TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM	(TCPOLEN_MPTCP_DSS_CHECKSUM + TCPOLEN_MPTCP_MPC_ACK_DATA)
+
 /* MPTCP MP_JOIN flags */
 #define MPTCPOPT_BACKUP		BIT(0)
 #define MPTCPOPT_HMAC_LEN	20
@@ -124,6 +126,7 @@ struct mptcp_options_received {
 	u64	data_seq;
 	u32	subflow_seq;
 	u16	data_len;
+	__sum16	csum;
 	u16	mp_capable : 1,
 		mp_join : 1,
 		fastclose : 1,
@@ -133,6 +136,7 @@ struct mptcp_options_received {
 		rm_addr : 1,
 		mp_prio : 1,
 		echo : 1,
+		csum_reqd : 1,
 		backup : 1;
 	u32	token;
 	u32	nonce;
@@ -234,6 +238,7 @@ struct mptcp_sock {
 	bool		snd_data_fin_enable;
 	bool		rcv_fastclose;
 	bool		use_64bit_ack; /* Set when we received a 64-bit DSN */
+	bool		csum_enabled;
 	spinlock_t	join_list_lock;
 	struct sock	*ack_hint;
 	struct work_struct work;
@@ -335,11 +340,19 @@ static inline struct mptcp_data_frag *mptcp_rtx_head(const struct sock *sk)
 	return list_first_entry_or_null(&msk->rtx_queue, struct mptcp_data_frag, list);
 }
 
+struct csum_pseudo_header {
+	__be64 data_seq;
+	__be32 subflow_seq;
+	__be16 data_len;
+	__sum16 csum;
+};
+
 struct mptcp_subflow_request_sock {
 	struct	tcp_request_sock sk;
 	u16	mp_capable : 1,
 		mp_join : 1,
-		backup : 1;
+		backup : 1,
+		csum_reqd : 1;
 	u8	local_id;
 	u8	remote_id;
 	u64	local_key;
@@ -386,6 +399,8 @@ struct mptcp_subflow_context {
 	u32	map_subflow_seq;
 	u32	ssn_offset;
 	u32	map_data_len;
+	__wsum	map_data_csum;
+	u32	map_csum_len;
 	u32	request_mptcp : 1,  /* send MP_CAPABLE */
 		request_join : 1,   /* send MP_JOIN */
 		request_bkup : 1,
@@ -395,6 +410,8 @@ struct mptcp_subflow_context {
 		pm_notified : 1,    /* PM hook called for established status */
 		conn_finished : 1,
 		map_valid : 1,
+		map_csum_reqd : 1,
+		map_data_fin : 1,
 		mpc_map : 1,
 		backup : 1,
 		send_mp_prio : 1,
@@ -524,6 +541,7 @@ static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *su
 
 int mptcp_is_enabled(struct net *net);
 unsigned int mptcp_get_add_addr_timeout(struct net *net);
+int mptcp_is_checksum_enabled(struct net *net);
 void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
 				     struct mptcp_options_received *mp_opt);
 bool mptcp_subflow_data_available(struct sock *sk);
@@ -575,7 +593,8 @@ int __init mptcp_proto_v6_init(void);
 struct sock *mptcp_sk_clone(const struct sock *sk,
 			    const struct mptcp_options_received *mp_opt,
 			    struct request_sock *req);
-void mptcp_get_options(const struct sk_buff *skb,
+void mptcp_get_options(const struct sock *sk,
+		       const struct sk_buff *skb,
 		       struct mptcp_options_received *mp_opt);
 
 void mptcp_finish_connect(struct sock *sk);
@@ -626,6 +645,8 @@ static inline void mptcp_write_space(struct sock *sk)
 
 void mptcp_destroy_common(struct mptcp_sock *msk);
 
+#define MPTCP_TOKEN_MAX_RETRIES	4
+
 void __init mptcp_token_init(void);
 static inline void mptcp_token_init_request(struct request_sock *req)
 {
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index a79798189599..092d1f635d27 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -140,6 +140,43 @@ static void mptcp_so_incoming_cpu(struct mptcp_sock *msk, int val)
 	mptcp_sol_socket_sync_intval(msk, SO_INCOMING_CPU, val);
 }
 
+static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optname, int val)
+{
+	sockptr_t optval = KERNEL_SOCKPTR(&val);
+	struct mptcp_subflow_context *subflow;
+	struct sock *sk = (struct sock *)msk;
+	int ret;
+
+	ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname,
+			      optval, sizeof(val));
+	if (ret)
+		return ret;
+
+	lock_sock(sk);
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		bool slow = lock_sock_fast(ssk);
+
+		switch (optname) {
+		case SO_TIMESTAMP_OLD:
+		case SO_TIMESTAMP_NEW:
+		case SO_TIMESTAMPNS_OLD:
+		case SO_TIMESTAMPNS_NEW:
+			sock_set_timestamp(sk, optname, !!val);
+			break;
+		case SO_TIMESTAMPING_NEW:
+		case SO_TIMESTAMPING_OLD:
+			sock_set_timestamping(sk, optname, val);
+			break;
+		}
+
+		unlock_sock_fast(ssk, slow);
+	}
+
+	release_sock(sk);
+	return 0;
+}
+
 static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname,
 					   sockptr_t optval, unsigned int optlen)
 {
@@ -164,6 +201,13 @@ static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname,
 	case SO_INCOMING_CPU:
 		mptcp_so_incoming_cpu(msk, val);
 		return 0;
+	case SO_TIMESTAMP_OLD:
+	case SO_TIMESTAMP_NEW:
+	case SO_TIMESTAMPNS_OLD:
+	case SO_TIMESTAMPNS_NEW:
+	case SO_TIMESTAMPING_OLD:
+	case SO_TIMESTAMPING_NEW:
+		return mptcp_setsockopt_sol_socket_tstamp(msk, optname, val);
 	}
 
 	return -ENOPROTOOPT;
@@ -251,9 +295,23 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
 	case SO_MARK:
 	case SO_INCOMING_CPU:
 	case SO_DEBUG:
+	case SO_TIMESTAMP_OLD:
+	case SO_TIMESTAMP_NEW:
+	case SO_TIMESTAMPNS_OLD:
+	case SO_TIMESTAMPNS_NEW:
+	case SO_TIMESTAMPING_OLD:
+	case SO_TIMESTAMPING_NEW:
 		return mptcp_setsockopt_sol_socket_int(msk, optname, optval, optlen);
 	case SO_LINGER:
 		return mptcp_setsockopt_sol_socket_linger(msk, optval, optlen);
+	case SO_RCVLOWAT:
+	case SO_RCVTIMEO_OLD:
+	case SO_RCVTIMEO_NEW:
+	case SO_BUSY_POLL:
+	case SO_PREFER_BUSY_POLL:
+	case SO_BUSY_POLL_BUDGET:
+		/* No need to copy: only relevant for msk */
+		return sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, optlen);
 	case SO_NO_CHECK:
 	case SO_DONTROUTE:
 	case SO_BROADCAST:
@@ -267,7 +325,24 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
 		return 0;
 	}
 
-	return sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, optlen);
+	/* SO_OOBINLINE is not supported, let's avoid the related mess
+	 * SO_ATTACH_FILTER, SO_ATTACH_BPF, SO_ATTACH_REUSEPORT_CBPF,
+	 * SO_DETACH_REUSEPORT_BPF, SO_DETACH_FILTER, SO_LOCK_FILTER,
+	 * we must be careful with subflows
+	 *
+	 * SO_ATTACH_REUSEPORT_EBPF is not supported, at it checks
+	 * explicitly the sk_protocol field
+	 *
+	 * SO_PEEK_OFF is unsupported, as it is for plain TCP
+	 * SO_MAX_PACING_RATE is unsupported, we must be careful with subflows
+	 * SO_CNX_ADVICE is currently unsupported, could possibly be relevant,
+	 * but likely needs careful design
+	 *
+	 * SO_ZEROCOPY is currently unsupported, TODO in sndmsg
+	 * SO_TXTIME is currently unsupported
+	 */
+
+	return -EOPNOTSUPP;
 }
 
 static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
@@ -299,72 +374,6 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
 
 static bool mptcp_supported_sockopt(int level, int optname)
 {
-	if (level == SOL_SOCKET) {
-		switch (optname) {
-		case SO_DEBUG:
-		case SO_REUSEPORT:
-		case SO_REUSEADDR:
-
-		/* the following ones need a better implementation,
-		 * but are quite common we want to preserve them
-		 */
-		case SO_BINDTODEVICE:
-		case SO_SNDBUF:
-		case SO_SNDBUFFORCE:
-		case SO_RCVBUF:
-		case SO_RCVBUFFORCE:
-		case SO_KEEPALIVE:
-		case SO_PRIORITY:
-		case SO_LINGER:
-		case SO_TIMESTAMP_OLD:
-		case SO_TIMESTAMP_NEW:
-		case SO_TIMESTAMPNS_OLD:
-		case SO_TIMESTAMPNS_NEW:
-		case SO_TIMESTAMPING_OLD:
-		case SO_TIMESTAMPING_NEW:
-		case SO_RCVLOWAT:
-		case SO_RCVTIMEO_OLD:
-		case SO_RCVTIMEO_NEW:
-		case SO_SNDTIMEO_OLD:
-		case SO_SNDTIMEO_NEW:
-		case SO_MARK:
-		case SO_INCOMING_CPU:
-		case SO_BINDTOIFINDEX:
-		case SO_BUSY_POLL:
-		case SO_PREFER_BUSY_POLL:
-		case SO_BUSY_POLL_BUDGET:
-
-		/* next ones are no-op for plain TCP */
-		case SO_NO_CHECK:
-		case SO_DONTROUTE:
-		case SO_BROADCAST:
-		case SO_BSDCOMPAT:
-		case SO_PASSCRED:
-		case SO_PASSSEC:
-		case SO_RXQ_OVFL:
-		case SO_WIFI_STATUS:
-		case SO_NOFCS:
-		case SO_SELECT_ERR_QUEUE:
-			return true;
-		}
-
-		/* SO_OOBINLINE is not supported, let's avoid the related mess */
-		/* SO_ATTACH_FILTER, SO_ATTACH_BPF, SO_ATTACH_REUSEPORT_CBPF,
-		 * SO_DETACH_REUSEPORT_BPF, SO_DETACH_FILTER, SO_LOCK_FILTER,
-		 * we must be careful with subflows
-		 */
-		/* SO_ATTACH_REUSEPORT_EBPF is not supported, at it checks
-		 * explicitly the sk_protocol field
-		 */
-		/* SO_PEEK_OFF is unsupported, as it is for plain TCP */
-		/* SO_MAX_PACING_RATE is unsupported, we must be careful with subflows */
-		/* SO_CNX_ADVICE is currently unsupported, could possibly be relevant,
-		 * but likely needs careful design
-		 */
-		/* SO_ZEROCOPY is currently unsupported, TODO in sndmsg */
-		/* SO_TXTIME is currently unsupported */
-		return false;
-	}
 	if (level == SOL_IP) {
 		switch (optname) {
 		/* should work fine */
@@ -574,12 +583,12 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname,
 
 	pr_debug("msk=%p", msk);
 
-	if (!mptcp_supported_sockopt(level, optname))
-		return -ENOPROTOOPT;
-
 	if (level == SOL_SOCKET)
 		return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen);
 
+	if (!mptcp_supported_sockopt(level, optname))
+		return -ENOPROTOOPT;
+
 	/* @@ the meaning of setsockopt() when the socket is connected and
 	 * there are multiple subflows is not yet defined. It is up to the
 	 * MPTCP-level socket to configure the subflows until the subflow
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index be1de4084196..8976ff586b87 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -108,6 +108,7 @@ static void subflow_init_req(struct request_sock *req, const struct sock *sk_lis
 
 	subflow_req->mp_capable = 0;
 	subflow_req->mp_join = 0;
+	subflow_req->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk_listener));
 	subflow_req->msk = NULL;
 	mptcp_token_init_request(req);
 }
@@ -150,7 +151,7 @@ static int subflow_check_req(struct request_sock *req,
 		return -EINVAL;
 #endif
 
-	mptcp_get_options(skb, &mp_opt);
+	mptcp_get_options(sk_listener, skb, &mp_opt);
 
 	if (mp_opt.mp_capable) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
@@ -162,7 +163,7 @@ static int subflow_check_req(struct request_sock *req,
 	}
 
 	if (mp_opt.mp_capable && listener->request_mptcp) {
-		int err, retries = 4;
+		int err, retries = MPTCP_TOKEN_MAX_RETRIES;
 
 		subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
 again:
@@ -247,7 +248,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req,
 	int err;
 
 	subflow_init_req(req, sk_listener);
-	mptcp_get_options(skb, &mp_opt);
+	mptcp_get_options(sk_listener, skb, &mp_opt);
 
 	if (mp_opt.mp_capable && mp_opt.mp_join)
 		return -EINVAL;
@@ -394,7 +395,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 	subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
 	pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset);
 
-	mptcp_get_options(skb, &mp_opt);
+	mptcp_get_options(sk, skb, &mp_opt);
 	if (subflow->request_mptcp) {
 		if (!mp_opt.mp_capable) {
 			MPTCP_INC_STATS(sock_net(sk),
@@ -404,6 +405,8 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 			goto fallback;
 		}
 
+		if (mp_opt.csum_reqd)
+			WRITE_ONCE(mptcp_sk(parent)->csum_enabled, true);
 		subflow->mp_capable = 1;
 		subflow->can_ack = 1;
 		subflow->remote_key = mp_opt.sndr_key;
@@ -430,15 +433,15 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 			goto do_reset;
 		}
 
+		if (!mptcp_finish_join(sk))
+			goto do_reset;
+
 		subflow_generate_hmac(subflow->local_key, subflow->remote_key,
 				      subflow->local_nonce,
 				      subflow->remote_nonce,
 				      hmac);
 		memcpy(subflow->hmac, hmac, MPTCPOPT_HMAC_LEN);
 
-		if (!mptcp_finish_join(sk))
-			goto do_reset;
-
 		subflow->mp_join = 1;
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);
 
@@ -638,7 +641,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 		 * reordered MPC will cause fallback, but we don't have other
 		 * options.
 		 */
-		mptcp_get_options(skb, &mp_opt);
+		mptcp_get_options(sk, skb, &mp_opt);
 		if (!mp_opt.mp_capable) {
 			fallback = true;
 			goto create_child;
@@ -648,7 +651,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 		if (!new_msk)
 			fallback = true;
 	} else if (subflow_req->mp_join) {
-		mptcp_get_options(skb, &mp_opt);
+		mptcp_get_options(sk, skb, &mp_opt);
 		if (!mp_opt.mp_join || !subflow_hmac_valid(req, &mp_opt) ||
 		    !mptcp_can_accept_new_subflow(subflow_req->msk)) {
 			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
@@ -824,10 +827,92 @@ static bool validate_mapping(struct sock *ssk, struct sk_buff *skb)
 	return true;
 }
 
+static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *skb,
+					      bool csum_reqd)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	struct csum_pseudo_header header;
+	u32 offset, seq, delta;
+	__wsum csum;
+	int len;
+
+	if (!csum_reqd)
+		return MAPPING_OK;
+
+	/* mapping already validated on previous traversal */
+	if (subflow->map_csum_len == subflow->map_data_len)
+		return MAPPING_OK;
+
+	/* traverse the receive queue, ensuring it contains a full
+	 * DSS mapping and accumulating the related csum.
+	 * Preserve the accoumlate csum across multiple calls, to compute
+	 * the csum only once
+	 */
+	delta = subflow->map_data_len - subflow->map_csum_len;
+	for (;;) {
+		seq = tcp_sk(ssk)->copied_seq + subflow->map_csum_len;
+		offset = seq - TCP_SKB_CB(skb)->seq;
+
+		/* if the current skb has not been accounted yet, csum its contents
+		 * up to the amount covered by the current DSS
+		 */
+		if (offset < skb->len) {
+			__wsum csum;
+
+			len = min(skb->len - offset, delta);
+			csum = skb_checksum(skb, offset, len, 0);
+			subflow->map_data_csum = csum_block_add(subflow->map_data_csum, csum,
+								subflow->map_csum_len);
+
+			delta -= len;
+			subflow->map_csum_len += len;
+		}
+		if (delta == 0)
+			break;
+
+		if (skb_queue_is_last(&ssk->sk_receive_queue, skb)) {
+			/* if this subflow is closed, the partial mapping
+			 * will be never completed; flush the pending skbs, so
+			 * that subflow_sched_work_if_closed() can kick in
+			 */
+			if (unlikely(ssk->sk_state == TCP_CLOSE))
+				while ((skb = skb_peek(&ssk->sk_receive_queue)))
+					sk_eat_skb(ssk, skb);
+
+			/* not enough data to validate the csum */
+			return MAPPING_EMPTY;
+		}
+
+		/* the DSS mapping for next skbs will be validated later,
+		 * when a get_mapping_status call will process such skb
+		 */
+		skb = skb->next;
+	}
+
+	/* note that 'map_data_len' accounts only for the carried data, does
+	 * not include the eventual seq increment due to the data fin,
+	 * while the pseudo header requires the original DSS data len,
+	 * including that
+	 */
+	header.data_seq = cpu_to_be64(subflow->map_seq);
+	header.subflow_seq = htonl(subflow->map_subflow_seq);
+	header.data_len = htons(subflow->map_data_len + subflow->map_data_fin);
+	header.csum = 0;
+
+	csum = csum_partial(&header, sizeof(header), subflow->map_data_csum);
+	if (unlikely(csum_fold(csum))) {
+		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR);
+		return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY;
+	}
+
+	return MAPPING_OK;
+}
+
 static enum mapping_status get_mapping_status(struct sock *ssk,
 					      struct mptcp_sock *msk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	bool csum_reqd = READ_ONCE(msk->csum_enabled);
 	struct mptcp_ext *mpext;
 	struct sk_buff *skb;
 	u16 data_len;
@@ -920,9 +1005,10 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 		/* Allow replacing only with an identical map */
 		if (subflow->map_seq == map_seq &&
 		    subflow->map_subflow_seq == mpext->subflow_seq &&
-		    subflow->map_data_len == data_len) {
+		    subflow->map_data_len == data_len &&
+		    subflow->map_csum_reqd == mpext->csum_reqd) {
 			skb_ext_del(skb, SKB_EXT_MPTCP);
-			return MAPPING_OK;
+			goto validate_csum;
 		}
 
 		/* If this skb data are fully covered by the current mapping,
@@ -934,17 +1020,27 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 		}
 
 		/* will validate the next map after consuming the current one */
-		return MAPPING_OK;
+		goto validate_csum;
 	}
 
 	subflow->map_seq = map_seq;
 	subflow->map_subflow_seq = mpext->subflow_seq;
 	subflow->map_data_len = data_len;
 	subflow->map_valid = 1;
+	subflow->map_data_fin = mpext->data_fin;
 	subflow->mpc_map = mpext->mpc_map;
-	pr_debug("new map seq=%llu subflow_seq=%u data_len=%u",
+	subflow->map_csum_reqd = mpext->csum_reqd;
+	subflow->map_csum_len = 0;
+	subflow->map_data_csum = csum_unfold(mpext->csum);
+
+	/* Cfr RFC 8684 Section 3.3.0 */
+	if (unlikely(subflow->map_csum_reqd != csum_reqd))
+		return MAPPING_INVALID;
+
+	pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u",
 		 subflow->map_seq, subflow->map_subflow_seq,
-		 subflow->map_data_len);
+		 subflow->map_data_len, subflow->map_csum_reqd,
+		 subflow->map_data_csum);
 
 validate_seq:
 	/* we revalidate valid mapping on new skb, because we must ensure
@@ -954,7 +1050,9 @@ validate_seq:
 		return MAPPING_INVALID;
 
 	skb_ext_del(skb, SKB_EXT_MPTCP);
-	return MAPPING_OK;
+
+validate_csum:
+	return validate_data_csum(ssk, skb, csum_reqd);
 }
 
 static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
diff --git a/net/mptcp/token.c b/net/mptcp/token.c
index 8f0270a780ce..a98e554b034f 100644
--- a/net/mptcp/token.c
+++ b/net/mptcp/token.c
@@ -33,7 +33,6 @@
 #include <net/mptcp.h>
 #include "protocol.h"
 
-#define TOKEN_MAX_RETRIES	4
 #define TOKEN_MAX_CHAIN_LEN	4
 
 struct token_bucket {
@@ -153,12 +152,9 @@ int mptcp_token_new_connect(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
-	int retries = TOKEN_MAX_RETRIES;
+	int retries = MPTCP_TOKEN_MAX_RETRIES;
 	struct token_bucket *bucket;
 
-	pr_debug("ssk=%p, local_key=%llu, token=%u, idsn=%llu\n",
-		 sk, subflow->local_key, subflow->token, subflow->idsn);
-
 again:
 	mptcp_crypto_key_gen_sha(&subflow->local_key, &subflow->token,
 				 &subflow->idsn);
@@ -172,6 +168,9 @@ again:
 		goto again;
 	}
 
+	pr_debug("ssk=%p, local_key=%llu, token=%u, idsn=%llu\n",
+		 sk, subflow->local_key, subflow->token, subflow->idsn);
+
 	WRITE_ONCE(msk->token, subflow->token);
 	__sk_nulls_add_node_rcu((struct sock *)msk, &bucket->msk_chain);
 	bucket->chain_len++;
diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index 49031f804276..cbbb0de4750a 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -238,7 +238,7 @@ struct ncsi_package {
 	struct ncsi_dev_priv *ndp;        /* NCSI device            */
 	spinlock_t           lock;        /* Protect the package    */
 	unsigned int         channel_num; /* Number of channels     */
-	struct list_head     channels;    /* List of chanels        */
+	struct list_head     channels;    /* List of channels        */
 	struct list_head     node;        /* Form list of packages  */
 
 	bool                 multi_channel; /* Enable multiple channels  */
@@ -339,7 +339,7 @@ struct ncsi_cmd_arg {
 	unsigned char        type;        /* Command in the NCSI packet    */
 	unsigned char        id;          /* Request ID (sequence number)  */
 	unsigned char        package;     /* Destination package ID        */
-	unsigned char        channel;     /* Detination channel ID or 0x1f */
+	unsigned char        channel;     /* Destination channel ID or 0x1f */
 	unsigned short       payload;     /* Command packet payload length */
 	unsigned int         req_flags;   /* NCSI request properties       */
 	union {
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index ffff8da707b8..ca04b6df1341 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -627,7 +627,7 @@ static int clear_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc,
 	return 0;
 }
 
-/* Find an outstanding VLAN tag and constuct a "Set VLAN Filter - Enable"
+/* Find an outstanding VLAN tag and construct a "Set VLAN Filter - Enable"
  * packet.
  */
 static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc,
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 56a2531a3402..54395266339d 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -19,6 +19,16 @@ config NETFILTER_FAMILY_BRIDGE
 config NETFILTER_FAMILY_ARP
 	bool
 
+config NETFILTER_NETLINK_HOOK
+	tristate "Netfilter base hook dump support"
+	depends on NETFILTER_ADVANCED
+	depends on NF_TABLES
+	select NETFILTER_NETLINK
+	help
+	  If this option is enabled, the kernel will include support
+	  to list the base netfilter hooks via NFNETLINK.
+	  This is helpful for debugging.
+
 config NETFILTER_NETLINK_ACCT
 	tristate "Netfilter NFACCT over NFNETLINK interface"
 	depends on NETFILTER_ADVANCED
@@ -816,7 +826,7 @@ config NETFILTER_XT_TARGET_CLASSIFY
 	  the priority of a packet. Some qdiscs can use this value for
 	  classification, among these are:
 
-  	  atm, cbq, dsmark, pfifo_fast, htb, prio
+	  atm, cbq, dsmark, pfifo_fast, htb, prio
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index e80e010354b1..87112dad1fd4 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -22,6 +22,7 @@ obj-$(CONFIG_NETFILTER_NETLINK_ACCT) += nfnetlink_acct.o
 obj-$(CONFIG_NETFILTER_NETLINK_QUEUE) += nfnetlink_queue.o
 obj-$(CONFIG_NETFILTER_NETLINK_LOG) += nfnetlink_log.o
 obj-$(CONFIG_NETFILTER_NETLINK_OSF) += nfnetlink_osf.o
+obj-$(CONFIG_NETFILTER_NETLINK_HOOK) += nfnetlink_hook.o
 
 # connection tracking
 obj-$(CONFIG_NF_CONNTRACK) += nf_conntrack.o
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index de2d20c37cda..16ae92054baa 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1685,8 +1685,8 @@ static const struct nla_policy ip_set_adt_policy[IPSET_ATTR_CMD_MAX + 1] = {
 };
 
 static int
-call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set,
-	struct nlattr *tb[], enum ipset_adt adt,
+call_ad(struct net *net, struct sock *ctnl, struct sk_buff *skb,
+	struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt,
 	u32 flags, bool use_lineno)
 {
 	int ret;
@@ -1738,8 +1738,7 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set,
 
 		*errline = lineno;
 
-		netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid,
-				MSG_DONTWAIT);
+		nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid);
 		/* Signal netlink not to send its ACK/errmsg.  */
 		return -EINTR;
 	}
@@ -1783,7 +1782,7 @@ static int ip_set_ad(struct net *net, struct sock *ctnl,
 				     attr[IPSET_ATTR_DATA],
 				     set->type->adt_policy, NULL))
 			return -IPSET_ERR_PROTOCOL;
-		ret = call_ad(ctnl, skb, set, tb, adt, flags,
+		ret = call_ad(net, ctnl, skb, set, tb, adt, flags,
 			      use_lineno);
 	} else {
 		int nla_rem;
@@ -1794,7 +1793,7 @@ static int ip_set_ad(struct net *net, struct sock *ctnl,
 			    nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, nla,
 					     set->type->adt_policy, NULL))
 				return -IPSET_ERR_PROTOCOL;
-			ret = call_ad(ctnl, skb, set, tb, adt,
+			ret = call_ad(net, ctnl, skb, set, tb, adt,
 				      flags, use_lineno);
 			if (ret < 0)
 				return ret;
@@ -1859,7 +1858,6 @@ static int ip_set_header(struct sk_buff *skb, const struct nfnl_info *info,
 	const struct ip_set *set;
 	struct sk_buff *skb2;
 	struct nlmsghdr *nlh2;
-	int ret = 0;
 
 	if (unlikely(protocol_min_failed(attr) ||
 		     !attr[IPSET_ATTR_SETNAME]))
@@ -1885,12 +1883,7 @@ static int ip_set_header(struct sk_buff *skb, const struct nfnl_info *info,
 		goto nla_put_failure;
 	nlmsg_end(skb2, nlh2);
 
-	ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid,
-			      MSG_DONTWAIT);
-	if (ret < 0)
-		return ret;
-
-	return 0;
+	return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid);
 
 nla_put_failure:
 	nlmsg_cancel(skb2, nlh2);
@@ -1945,12 +1938,7 @@ static int ip_set_type(struct sk_buff *skb, const struct nfnl_info *info,
 	nlmsg_end(skb2, nlh2);
 
 	pr_debug("Send TYPE, nlmsg_len: %u\n", nlh2->nlmsg_len);
-	ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid,
-			      MSG_DONTWAIT);
-	if (ret < 0)
-		return ret;
-
-	return 0;
+	return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid);
 
 nla_put_failure:
 	nlmsg_cancel(skb2, nlh2);
@@ -1971,7 +1959,6 @@ static int ip_set_protocol(struct sk_buff *skb, const struct nfnl_info *info,
 {
 	struct sk_buff *skb2;
 	struct nlmsghdr *nlh2;
-	int ret = 0;
 
 	if (unlikely(!attr[IPSET_ATTR_PROTOCOL]))
 		return -IPSET_ERR_PROTOCOL;
@@ -1990,12 +1977,7 @@ static int ip_set_protocol(struct sk_buff *skb, const struct nfnl_info *info,
 		goto nla_put_failure;
 	nlmsg_end(skb2, nlh2);
 
-	ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid,
-			      MSG_DONTWAIT);
-	if (ret < 0)
-		return ret;
-
-	return 0;
+	return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid);
 
 nla_put_failure:
 	nlmsg_cancel(skb2, nlh2);
@@ -2014,7 +1996,6 @@ static int ip_set_byname(struct sk_buff *skb, const struct nfnl_info *info,
 	struct nlmsghdr *nlh2;
 	ip_set_id_t id = IPSET_INVALID_ID;
 	const struct ip_set *set;
-	int ret = 0;
 
 	if (unlikely(protocol_failed(attr) ||
 		     !attr[IPSET_ATTR_SETNAME]))
@@ -2038,12 +2019,7 @@ static int ip_set_byname(struct sk_buff *skb, const struct nfnl_info *info,
 		goto nla_put_failure;
 	nlmsg_end(skb2, nlh2);
 
-	ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid,
-			      MSG_DONTWAIT);
-	if (ret < 0)
-		return ret;
-
-	return 0;
+	return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid);
 
 nla_put_failure:
 	nlmsg_cancel(skb2, nlh2);
@@ -2065,7 +2041,6 @@ static int ip_set_byindex(struct sk_buff *skb, const struct nfnl_info *info,
 	struct nlmsghdr *nlh2;
 	ip_set_id_t id = IPSET_INVALID_ID;
 	const struct ip_set *set;
-	int ret = 0;
 
 	if (unlikely(protocol_failed(attr) ||
 		     !attr[IPSET_ATTR_INDEX]))
@@ -2091,12 +2066,7 @@ static int ip_set_byindex(struct sk_buff *skb, const struct nfnl_info *info,
 		goto nla_put_failure;
 	nlmsg_end(skb2, nlh2);
 
-	ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid,
-			      MSG_DONTWAIT);
-	if (ret < 0)
-		return ret;
-
-	return 0;
+	return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid);
 
 nla_put_failure:
 	nlmsg_cancel(skb2, nlh2);
diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index d61886874940..271da8447b29 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -318,7 +318,7 @@ config IP_VS_MH_TAB_INDEX
 comment 'IPVS application helper'
 
 config	IP_VS_FTP
-  	tristate "FTP protocol helper"
+	tristate "FTP protocol helper"
 	depends on IP_VS_PROTO_TCP && NF_CONNTRACK && NF_NAT && \
 		NF_CONNTRACK_FTP
 	select IP_VS_NFCT
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index e0befcf8113a..96ba19fc8155 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -55,8 +55,6 @@
 
 #include "nf_internals.h"
 
-extern unsigned int nf_conntrack_net_id;
-
 __cacheline_aligned_in_smp spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS];
 EXPORT_SYMBOL_GPL(nf_conntrack_locks);
 
@@ -87,8 +85,6 @@ static __read_mostly bool nf_conntrack_locks_all;
 
 static struct conntrack_gc_work conntrack_gc_work;
 
-extern unsigned int nf_conntrack_net_id;
-
 void nf_conntrack_lock(spinlock_t *lock) __acquires(lock)
 {
 	/* 1) Acquire the lock */
@@ -1404,7 +1400,7 @@ static void gc_worker(struct work_struct *work)
 				continue;
 
 			net = nf_ct_net(tmp);
-			cnet = net_generic(net, nf_conntrack_net_id);
+			cnet = nf_ct_pernet(net);
 			if (atomic_read(&cnet->count) < nf_conntrack_max95)
 				continue;
 
@@ -1484,7 +1480,7 @@ __nf_conntrack_alloc(struct net *net,
 		     const struct nf_conntrack_tuple *repl,
 		     gfp_t gfp, u32 hash)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	unsigned int ct_count;
 	struct nf_conn *ct;
 
@@ -1556,7 +1552,7 @@ void nf_conntrack_free(struct nf_conn *ct)
 
 	nf_ct_ext_destroy(ct);
 	kmem_cache_free(nf_conntrack_cachep, ct);
-	cnet = net_generic(net, nf_conntrack_net_id);
+	cnet = nf_ct_pernet(net);
 
 	smp_mb__before_atomic();
 	atomic_dec(&cnet->count);
@@ -1614,7 +1610,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 			     GFP_ATOMIC);
 
 	local_bh_disable();
-	cnet = net_generic(net, nf_conntrack_net_id);
+	cnet = nf_ct_pernet(net);
 	if (cnet->expect_count) {
 		spin_lock(&nf_conntrack_expect_lock);
 		exp = nf_ct_find_expectation(net, zone, tuple);
@@ -2317,7 +2313,7 @@ __nf_ct_unconfirmed_destroy(struct net *net)
 
 void nf_ct_unconfirmed_destroy(struct net *net)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 	might_sleep();
 
@@ -2333,7 +2329,7 @@ void nf_ct_iterate_cleanup_net(struct net *net,
 			       int (*iter)(struct nf_conn *i, void *data),
 			       void *data, u32 portid, int report)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	struct iter_data d;
 
 	might_sleep();
@@ -2367,7 +2363,7 @@ nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), void *data)
 
 	down_read(&net_rwsem);
 	for_each_net(net) {
-		struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+		struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 		if (atomic_read(&cnet->count) == 0)
 			continue;
@@ -2449,7 +2445,7 @@ void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list)
 i_see_dead_people:
 	busy = 0;
 	list_for_each_entry(net, net_exit_list, exit_list) {
-		struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+		struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 		nf_ct_iterate_cleanup(kill_all, net, 0, 0);
 		if (atomic_read(&cnet->count) != 0)
@@ -2733,7 +2729,7 @@ void nf_conntrack_init_end(void)
 
 int nf_conntrack_init_net(struct net *net)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	int ret = -ENOMEM;
 	int cpu;
 
diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c
index 759d87aef95f..296e4a171bd1 100644
--- a/net/netfilter/nf_conntrack_ecache.c
+++ b/net/netfilter/nf_conntrack_ecache.c
@@ -27,8 +27,6 @@
 #include <net/netfilter/nf_conntrack_ecache.h>
 #include <net/netfilter/nf_conntrack_extend.h>
 
-extern unsigned int nf_conntrack_net_id;
-
 static DEFINE_MUTEX(nf_ct_ecache_mutex);
 
 #define ECACHE_RETRY_WAIT (HZ/10)
@@ -348,7 +346,7 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier);
 
 void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 	if (state == NFCT_ECACHE_DESTROY_FAIL &&
 	    !delayed_work_pending(&cnet->ecache_dwork)) {
@@ -371,7 +369,7 @@ static const struct nf_ct_ext_type event_extend = {
 
 void nf_conntrack_ecache_pernet_init(struct net *net)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 	net->ct.sysctl_events = nf_ct_events;
 	cnet->ct_net = &net->ct;
@@ -380,7 +378,7 @@ void nf_conntrack_ecache_pernet_init(struct net *net)
 
 void nf_conntrack_ecache_pernet_fini(struct net *net)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 	cancel_delayed_work_sync(&cnet->ecache_dwork);
 }
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index efdd391b3f72..1e851bc2e61a 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -43,8 +43,6 @@ unsigned int nf_ct_expect_max __read_mostly;
 static struct kmem_cache *nf_ct_expect_cachep __read_mostly;
 static unsigned int nf_ct_expect_hashrnd __read_mostly;
 
-extern unsigned int nf_conntrack_net_id;
-
 /* nf_conntrack_expect helper functions */
 void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
 				u32 portid, int report)
@@ -58,7 +56,7 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
 
 	hlist_del_rcu(&exp->hnode);
 
-	cnet = net_generic(net, nf_conntrack_net_id);
+	cnet = nf_ct_pernet(net);
 	cnet->expect_count--;
 
 	hlist_del_rcu(&exp->lnode);
@@ -123,7 +121,7 @@ __nf_ct_expect_find(struct net *net,
 		    const struct nf_conntrack_zone *zone,
 		    const struct nf_conntrack_tuple *tuple)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	struct nf_conntrack_expect *i;
 	unsigned int h;
 
@@ -164,7 +162,7 @@ nf_ct_find_expectation(struct net *net,
 		       const struct nf_conntrack_zone *zone,
 		       const struct nf_conntrack_tuple *tuple)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	struct nf_conntrack_expect *i, *exp = NULL;
 	unsigned int h;
 
@@ -397,7 +395,7 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp)
 	master_help->expecting[exp->class]++;
 
 	hlist_add_head_rcu(&exp->hnode, &nf_ct_expect_hash[h]);
-	cnet = net_generic(net, nf_conntrack_net_id);
+	cnet = nf_ct_pernet(net);
 	cnet->expect_count++;
 
 	NF_CT_STAT_INC(net, expect_create);
@@ -468,7 +466,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect,
 		}
 	}
 
-	cnet = net_generic(net, nf_conntrack_net_id);
+	cnet = nf_ct_pernet(net);
 	if (cnet->expect_count >= nf_ct_expect_max) {
 		net_warn_ratelimited("nf_conntrack: expectation table full\n");
 		ret = -EMFILE;
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index aafaff00baf1..2eb31ffb3d14 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -194,7 +194,7 @@ static int get_tpkt_data(struct sk_buff *skb, unsigned int protoff,
 		if (tcpdatalen == 4) {	/* Separate TPKT header */
 			/* Netmeeting sends TPKT header and data separately */
 			pr_debug("nf_ct_h323: separate TPKT header indicates "
-				 "there will be TPKT data of %hu bytes\n",
+				 "there will be TPKT data of %d bytes\n",
 				 tpktlen - 4);
 			info->tpkt_len[dir] = tpktlen - 4;
 			return 0;
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index ac396cc8bfae..ae4488a13c70 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -43,8 +43,6 @@ MODULE_PARM_DESC(nf_conntrack_helper,
 static DEFINE_MUTEX(nf_ct_nat_helpers_mutex);
 static struct list_head nf_ct_nat_helpers __read_mostly;
 
-extern unsigned int nf_conntrack_net_id;
-
 /* Stupid hash, but collision free for the default registrations of the
  * helpers currently in the kernel. */
 static unsigned int helper_hash(const struct nf_conntrack_tuple *tuple)
@@ -214,7 +212,7 @@ EXPORT_SYMBOL_GPL(nf_ct_helper_ext_add);
 static struct nf_conntrack_helper *
 nf_ct_lookup_helper(struct nf_conn *ct, struct net *net)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 	if (!cnet->sysctl_auto_assign_helper) {
 		if (cnet->auto_assign_helper_warned)
@@ -560,7 +558,7 @@ static const struct nf_ct_ext_type helper_extend = {
 
 void nf_conntrack_helper_pernet_init(struct net *net)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 	cnet->sysctl_auto_assign_helper = nf_ct_auto_assign_helper;
 }
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 8690fc07030f..4e1a9dba7077 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1528,7 +1528,7 @@ static int ctnetlink_del_conntrack(struct sk_buff *skb,
 				   const struct nfnl_info *info,
 				   const struct nlattr * const cda[])
 {
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
+	u8 family = info->nfmsg->nfgen_family;
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_zone zone;
@@ -1541,12 +1541,12 @@ static int ctnetlink_del_conntrack(struct sk_buff *skb,
 
 	if (cda[CTA_TUPLE_ORIG])
 		err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG,
-					    nfmsg->nfgen_family, &zone);
+					    family, &zone);
 	else if (cda[CTA_TUPLE_REPLY])
 		err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY,
-					    nfmsg->nfgen_family, &zone);
+					    family, &zone);
 	else {
-		u_int8_t u3 = nfmsg->version ? nfmsg->nfgen_family : AF_UNSPEC;
+		u_int8_t u3 = info->nfmsg->version ? family : AF_UNSPEC;
 
 		return ctnetlink_flush_conntrack(info->net, cda,
 						 NETLINK_CB(skb).portid,
@@ -1586,8 +1586,7 @@ static int ctnetlink_get_conntrack(struct sk_buff *skb,
 				   const struct nfnl_info *info,
 				   const struct nlattr * const cda[])
 {
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
-	u_int8_t u3 = nfmsg->nfgen_family;
+	u_int8_t u3 = info->nfmsg->nfgen_family;
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_zone zone;
@@ -1628,9 +1627,8 @@ static int ctnetlink_get_conntrack(struct sk_buff *skb,
 
 	ct = nf_ct_tuplehash_to_ctrack(h);
 
-	err = -ENOMEM;
 	skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (skb2 == NULL) {
+	if (!skb2) {
 		nf_ct_put(ct);
 		return -ENOMEM;
 	}
@@ -1640,21 +1638,12 @@ static int ctnetlink_get_conntrack(struct sk_buff *skb,
 				  NFNL_MSG_TYPE(info->nlh->nlmsg_type), ct,
 				  true, 0);
 	nf_ct_put(ct);
-	if (err <= 0)
-		goto free;
-
-	err = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid,
-			      MSG_DONTWAIT);
-	if (err < 0)
-		goto out;
-
-	return 0;
+	if (err <= 0) {
+		kfree_skb(skb2);
+		return -ENOMEM;
+	}
 
-free:
-	kfree_skb(skb2);
-out:
-	/* this avoids a loop in nfnetlink. */
-	return err == -EAGAIN ? -ENOBUFS : err;
+	return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid);
 }
 
 static int ctnetlink_done_list(struct netlink_callback *cb)
@@ -2373,10 +2362,9 @@ static int ctnetlink_new_conntrack(struct sk_buff *skb,
 				   const struct nfnl_info *info,
 				   const struct nlattr * const cda[])
 {
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct nf_conntrack_tuple otuple, rtuple;
 	struct nf_conntrack_tuple_hash *h = NULL;
-	u_int8_t u3 = nfmsg->nfgen_family;
+	u_int8_t u3 = info->nfmsg->nfgen_family;
 	struct nf_conntrack_zone zone;
 	struct nf_conn *ct;
 	int err;
@@ -2590,21 +2578,12 @@ static int ctnetlink_stat_ct(struct sk_buff *skb, const struct nfnl_info *info,
 					  info->nlh->nlmsg_seq,
 					  NFNL_MSG_TYPE(info->nlh->nlmsg_type),
 					  sock_net(skb->sk));
-	if (err <= 0)
-		goto free;
-
-	err = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid,
-			      MSG_DONTWAIT);
-	if (err < 0)
-		goto out;
-
-	return 0;
+	if (err <= 0) {
+		kfree_skb(skb2);
+		return -ENOMEM;
+	}
 
-free:
-	kfree_skb(skb2);
-out:
-	/* this avoids a loop in nfnetlink. */
-	return err == -EAGAIN ? -ENOBUFS : err;
+	return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid);
 }
 
 static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = {
@@ -3278,8 +3257,7 @@ static int ctnetlink_get_expect(struct sk_buff *skb,
 				const struct nfnl_info *info,
 				const struct nlattr * const cda[])
 {
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
-	u_int8_t u3 = nfmsg->nfgen_family;
+	u_int8_t u3 = info->nfmsg->nfgen_family;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_expect *exp;
 	struct nf_conntrack_zone zone;
@@ -3329,11 +3307,10 @@ static int ctnetlink_get_expect(struct sk_buff *skb,
 		}
 	}
 
-	err = -ENOMEM;
 	skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (skb2 == NULL) {
+	if (!skb2) {
 		nf_ct_expect_put(exp);
-		goto out;
+		return -ENOMEM;
 	}
 
 	rcu_read_lock();
@@ -3342,21 +3319,12 @@ static int ctnetlink_get_expect(struct sk_buff *skb,
 				      exp);
 	rcu_read_unlock();
 	nf_ct_expect_put(exp);
-	if (err <= 0)
-		goto free;
-
-	err = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid,
-			      MSG_DONTWAIT);
-	if (err < 0)
-		goto out;
-
-	return 0;
+	if (err <= 0) {
+		kfree_skb(skb2);
+		return -ENOMEM;
+	}
 
-free:
-	kfree_skb(skb2);
-out:
-	/* this avoids a loop in nfnetlink. */
-	return err == -EAGAIN ? -ENOBUFS : err;
+	return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid);
 }
 
 static bool expect_iter_name(struct nf_conntrack_expect *exp, void *data)
@@ -3378,8 +3346,7 @@ static int ctnetlink_del_expect(struct sk_buff *skb,
 				const struct nfnl_info *info,
 				const struct nlattr * const cda[])
 {
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
-	u_int8_t u3 = nfmsg->nfgen_family;
+	u_int8_t u3 = info->nfmsg->nfgen_family;
 	struct nf_conntrack_expect *exp;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_zone zone;
@@ -3630,8 +3597,7 @@ static int ctnetlink_new_expect(struct sk_buff *skb,
 				const struct nfnl_info *info,
 				const struct nlattr * const cda[])
 {
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
-	u_int8_t u3 = nfmsg->nfgen_family;
+	u_int8_t u3 = info->nfmsg->nfgen_family;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_expect *exp;
 	struct nf_conntrack_zone zone;
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index dc9ca12b0489..be14e0bea4c8 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -42,8 +42,6 @@
 #include <net/ipv6.h>
 #include <net/inet_frag.h>
 
-extern unsigned int nf_conntrack_net_id;
-
 static DEFINE_MUTEX(nf_ct_proto_mutex);
 
 #ifdef CONFIG_SYSCTL
@@ -446,7 +444,7 @@ static struct nf_ct_bridge_info *nf_ct_bridge_info;
 
 static int nf_ct_netns_do_get(struct net *net, u8 nfproto)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	bool fixup_needed = false, retry = true;
 	int err = 0;
 retry:
@@ -531,7 +529,7 @@ retry:
 
 static void nf_ct_netns_do_put(struct net *net, u8 nfproto)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 	mutex_lock(&nf_ct_proto_mutex);
 	switch (nfproto) {
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 34e22416a721..de840fc41a2e 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -1441,6 +1441,11 @@ void nf_conntrack_tcp_init_net(struct net *net)
 	 * will be started.
 	 */
 	tn->tcp_max_retrans = 3;
+
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	tn->offload_timeout = 30 * HZ;
+	tn->offload_pickup = 120 * HZ;
+#endif
 }
 
 const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp =
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index af402f458ee0..68911fcaa0f1 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -270,6 +270,11 @@ void nf_conntrack_udp_init_net(struct net *net)
 
 	for (i = 0; i < UDP_CT_MAX; i++)
 		un->timeouts[i] = udp_timeouts[i];
+
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	un->offload_timeout = 30 * HZ;
+	un->offload_pickup = 30 * HZ;
+#endif
 }
 
 const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp =
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index aaa55246d0ca..f57a951c9b5e 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -512,9 +512,7 @@ static void nf_conntrack_standalone_fini_proc(struct net *net)
 
 u32 nf_conntrack_count(const struct net *net)
 {
-	const struct nf_conntrack_net *cnet;
-
-	cnet = net_generic(net, nf_conntrack_net_id);
+	const struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 
 	return atomic_read(&cnet->count);
 }
@@ -575,11 +573,19 @@ enum nf_ct_sysctl_index {
 	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_RETRANS,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK,
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD,
+	NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP,
+#endif
 	NF_SYSCTL_CT_PROTO_TCP_LOOSE,
 	NF_SYSCTL_CT_PROTO_TCP_LIBERAL,
 	NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_UDP,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM,
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD,
+	NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP,
+#endif
 	NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6,
 #ifdef CONFIG_NF_CT_PROTO_SCTP
@@ -762,6 +768,20 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD] = {
+		.procname	= "nf_flowtable_tcp_timeout",
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP] = {
+		.procname	= "nf_flowtable_tcp_pickup",
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+#endif
 	[NF_SYSCTL_CT_PROTO_TCP_LOOSE] = {
 		.procname	= "nf_conntrack_tcp_loose",
 		.maxlen		= sizeof(u8),
@@ -796,6 +816,20 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
+#if IS_ENABLED(CONFIG_NFT_FLOW_OFFLOAD)
+	[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD] = {
+		.procname	= "nf_flowtable_udp_timeout",
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP] = {
+		.procname	= "nf_flowtable_udp_pickup",
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+#endif
 	[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP] = {
 		.procname	= "nf_conntrack_icmp_timeout",
 		.maxlen		= sizeof(unsigned int),
@@ -971,6 +1005,12 @@ static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net,
 	XASSIGN(LIBERAL, &tn->tcp_be_liberal);
 	XASSIGN(MAX_RETRANS, &tn->tcp_max_retrans);
 #undef XASSIGN
+
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD].data = &tn->offload_timeout;
+	table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP].data = &tn->offload_pickup;
+#endif
+
 }
 
 static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net,
@@ -1032,7 +1072,7 @@ static void nf_conntrack_standalone_init_gre_sysctl(struct net *net,
 
 static int nf_conntrack_standalone_init_sysctl(struct net *net)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	struct nf_udp_net *un = nf_udp_pernet(net);
 	struct ctl_table *table;
 
@@ -1059,6 +1099,10 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
 	table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6].data = &nf_icmpv6_pernet(net)->timeout;
 	table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP].data = &un->timeouts[UDP_CT_UNREPLIED];
 	table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM].data = &un->timeouts[UDP_CT_REPLIED];
+#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
+	table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD].data = &un->offload_timeout;
+	table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP].data = &un->offload_pickup;
+#endif
 
 	nf_conntrack_standalone_init_tcp_sysctl(net, table);
 	nf_conntrack_standalone_init_sctp_sysctl(net, table);
@@ -1085,7 +1129,7 @@ out_unregister_netfilter:
 
 static void nf_conntrack_standalone_fini_sysctl(struct net *net)
 {
-	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
 	struct ctl_table *table;
 
 	table = cnet->sysctl_header->ctl_table_arg;
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 1d02650dd715..1e50908b1b7e 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -178,12 +178,10 @@ static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)
 	tcp->seen[1].td_maxwin = 0;
 }
 
-#define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT	(120 * HZ)
-#define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT	(30 * HZ)
-
 static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
 {
 	const struct nf_conntrack_l4proto *l4proto;
+	struct net *net = nf_ct_net(ct);
 	int l4num = nf_ct_protonum(ct);
 	unsigned int timeout;
 
@@ -191,12 +189,17 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
 	if (!l4proto)
 		return;
 
-	if (l4num == IPPROTO_TCP)
-		timeout = NF_FLOWTABLE_TCP_PICKUP_TIMEOUT;
-	else if (l4num == IPPROTO_UDP)
-		timeout = NF_FLOWTABLE_UDP_PICKUP_TIMEOUT;
-	else
+	if (l4num == IPPROTO_TCP) {
+		struct nf_tcp_net *tn = nf_tcp_pernet(net);
+
+		timeout = tn->offload_pickup;
+	} else if (l4num == IPPROTO_UDP) {
+		struct nf_udp_net *tn = nf_udp_pernet(net);
+
+		timeout = tn->offload_pickup;
+	} else {
 		return;
+	}
 
 	if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout)
 		ct->timeout = nfct_time_stamp + timeout;
@@ -268,11 +271,35 @@ static const struct rhashtable_params nf_flow_offload_rhash_params = {
 	.automatic_shrinking	= true,
 };
 
+unsigned long flow_offload_get_timeout(struct flow_offload *flow)
+{
+	const struct nf_conntrack_l4proto *l4proto;
+	unsigned long timeout = NF_FLOW_TIMEOUT;
+	struct net *net = nf_ct_net(flow->ct);
+	int l4num = nf_ct_protonum(flow->ct);
+
+	l4proto = nf_ct_l4proto_find(l4num);
+	if (!l4proto)
+		return timeout;
+
+	if (l4num == IPPROTO_TCP) {
+		struct nf_tcp_net *tn = nf_tcp_pernet(net);
+
+		timeout = tn->offload_timeout;
+	} else if (l4num == IPPROTO_UDP) {
+		struct nf_udp_net *tn = nf_udp_pernet(net);
+
+		timeout = tn->offload_timeout;
+	}
+
+	return timeout;
+}
+
 int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
 {
 	int err;
 
-	flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT;
+	flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow);
 
 	err = rhashtable_insert_fast(&flow_table->rhashtable,
 				     &flow->tuplehash[0].node,
@@ -304,7 +331,7 @@ EXPORT_SYMBOL_GPL(flow_offload_add);
 void flow_offload_refresh(struct nf_flowtable *flow_table,
 			  struct flow_offload *flow)
 {
-	flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT;
+	flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow);
 
 	if (likely(!nf_flowtable_hw_offload(flow_table)))
 		return;
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index 528b2f172684..f92006cec94c 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -937,7 +937,7 @@ static void flow_offload_work_stats(struct flow_offload_work *offload)
 
 	lastused = max_t(u64, stats[0].lastused, stats[1].lastused);
 	offload->flow->timeout = max_t(u64, offload->flow->timeout,
-				       lastused + NF_FLOW_TIMEOUT);
+				       lastused + flow_offload_get_timeout(offload->flow));
 
 	if (offload->flowtable->flags & NF_FLOWTABLE_COUNTER) {
 		if (stats[0].pkts)
@@ -1041,7 +1041,7 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable,
 	__s32 delta;
 
 	delta = nf_flow_timeout_delta(flow->timeout);
-	if ((delta >= (9 * NF_FLOW_TIMEOUT) / 10))
+	if ((delta >= (9 * flow_offload_get_timeout(flow)) / 10))
 		return;
 
 	offload = nf_flow_offload_work_alloc(flowtable, flow, FLOW_CLS_STATS);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index bf4d6ec9fc55..d6214242fe7f 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -862,10 +862,9 @@ static int nft_netlink_dump_start_rcu(struct sock *nlsk, struct sk_buff *skb,
 static int nf_tables_gettable(struct sk_buff *skb, const struct nfnl_info *info,
 			      const struct nlattr * const nla[])
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_cur(info->net);
-	int family = nfmsg->nfgen_family;
+	u8 family = info->nfmsg->nfgen_family;
 	const struct nft_table *table;
 	struct net *net = info->net;
 	struct sk_buff *skb2;
@@ -1068,10 +1067,9 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info,
 			      const struct nlattr * const nla[])
 {
 	struct nftables_pernet *nft_net = nft_pernet(info->net);
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_next(info->net);
-	int family = nfmsg->nfgen_family;
+	u8 family = info->nfmsg->nfgen_family;
 	struct net *net = info->net;
 	const struct nlattr *attr;
 	struct nft_table *table;
@@ -1263,10 +1261,9 @@ out:
 static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info,
 			      const struct nlattr * const nla[])
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_next(info->net);
-	int family = nfmsg->nfgen_family;
+	u8 family = info->nfmsg->nfgen_family;
 	struct net *net = info->net;
 	const struct nlattr *attr;
 	struct nft_table *table;
@@ -1636,10 +1633,9 @@ done:
 static int nf_tables_getchain(struct sk_buff *skb, const struct nfnl_info *info,
 			      const struct nlattr * const nla[])
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_cur(info->net);
-	int family = nfmsg->nfgen_family;
+	u8 family = info->nfmsg->nfgen_family;
 	const struct nft_chain *chain;
 	struct net *net = info->net;
 	struct nft_table *table;
@@ -2015,11 +2011,12 @@ static void nft_basechain_hook_init(struct nf_hook_ops *ops, u8 family,
 				    const struct nft_chain_hook *hook,
 				    struct nft_chain *chain)
 {
-	ops->pf		= family;
-	ops->hooknum	= hook->num;
-	ops->priority	= hook->priority;
-	ops->priv	= chain;
-	ops->hook	= hook->type->hooks[ops->hooknum];
+	ops->pf			= family;
+	ops->hooknum		= hook->num;
+	ops->priority		= hook->priority;
+	ops->priv		= chain;
+	ops->hook		= hook->type->hooks[ops->hooknum];
+	ops->hook_ops_type	= NF_HOOK_OP_NF_TABLES;
 }
 
 static int nft_basechain_init(struct nft_base_chain *basechain, u8 family,
@@ -2371,10 +2368,9 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info,
 			      const struct nlattr * const nla[])
 {
 	struct nftables_pernet *nft_net = nft_pernet(info->net);
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_next(info->net);
-	int family = nfmsg->nfgen_family;
+	u8 family = info->nfmsg->nfgen_family;
 	struct nft_chain *chain = NULL;
 	struct net *net = info->net;
 	const struct nlattr *attr;
@@ -2469,10 +2465,9 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info,
 static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info,
 			      const struct nlattr * const nla[])
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_next(info->net);
-	int family = nfmsg->nfgen_family;
+	u8 family = info->nfmsg->nfgen_family;
 	struct net *net = info->net;
 	const struct nlattr *attr;
 	struct nft_table *table;
@@ -3096,10 +3091,9 @@ static int nf_tables_dump_rules_done(struct netlink_callback *cb)
 static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info,
 			     const struct nlattr * const nla[])
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_cur(info->net);
-	int family = nfmsg->nfgen_family;
+	u8 family = info->nfmsg->nfgen_family;
 	const struct nft_chain *chain;
 	const struct nft_rule *rule;
 	struct net *net = info->net;
@@ -3237,13 +3231,12 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info,
 			     const struct nlattr * const nla[])
 {
 	struct nftables_pernet *nft_net = nft_pernet(info->net);
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct netlink_ext_ack *extack = info->extack;
 	unsigned int size, i, n, ulen = 0, usize = 0;
 	u8 genmask = nft_genmask_next(info->net);
 	struct nft_rule *rule, *old_rule = NULL;
 	struct nft_expr_info *expr_info = NULL;
-	int family = nfmsg->nfgen_family;
+	u8 family = info->nfmsg->nfgen_family;
 	struct net *net = info->net;
 	struct nft_flow_rule *flow;
 	struct nft_userdata *udata;
@@ -3477,15 +3470,15 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net,
 static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info,
 			     const struct nlattr * const nla[])
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct netlink_ext_ack *extack = info->extack;
-	int family = nfmsg->nfgen_family, err = 0;
 	u8 genmask = nft_genmask_next(info->net);
+	u8 family = info->nfmsg->nfgen_family;
 	struct nft_chain *chain = NULL;
 	struct net *net = info->net;
 	struct nft_table *table;
 	struct nft_rule *rule;
 	struct nft_ctx ctx;
+	int err = 0;
 
 	table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask,
 				 NETLINK_CB(skb).portid);
@@ -3665,30 +3658,6 @@ static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = {
 	[NFTA_SET_DESC_CONCAT]		= { .type = NLA_NESTED },
 };
 
-static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net,
-				     const struct sk_buff *skb,
-				     const struct nlmsghdr *nlh,
-				     const struct nlattr * const nla[],
-				     struct netlink_ext_ack *extack,
-				     u8 genmask, u32 nlpid)
-{
-	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	int family = nfmsg->nfgen_family;
-	struct nft_table *table = NULL;
-
-	if (nla[NFTA_SET_TABLE] != NULL) {
-		table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family,
-					 genmask, nlpid);
-		if (IS_ERR(table)) {
-			NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]);
-			return PTR_ERR(table);
-		}
-	}
-
-	nft_ctx_init(ctx, net, skb, nlh, family, table, NULL, nla);
-	return 0;
-}
-
 static struct nft_set *nft_set_lookup(const struct nft_table *table,
 				      const struct nlattr *nla, u8 genmask)
 {
@@ -4068,20 +4037,26 @@ static int nf_tables_dump_sets_done(struct netlink_callback *cb)
 static int nf_tables_getset(struct sk_buff *skb, const struct nfnl_info *info,
 			    const struct nlattr * const nla[])
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_cur(info->net);
+	u8 family = info->nfmsg->nfgen_family;
+	struct nft_table *table = NULL;
 	struct net *net = info->net;
 	const struct nft_set *set;
 	struct sk_buff *skb2;
 	struct nft_ctx ctx;
 	int err;
 
-	/* Verify existence before starting dump */
-	err = nft_ctx_init_from_setattr(&ctx, net, skb, info->nlh, nla, extack,
-					genmask, 0);
-	if (err < 0)
-		return err;
+	if (nla[NFTA_SET_TABLE]) {
+		table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family,
+					 genmask, 0);
+		if (IS_ERR(table)) {
+			NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]);
+			return PTR_ERR(table);
+		}
+	}
+
+	nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla);
 
 	if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
@@ -4096,12 +4071,12 @@ static int nf_tables_getset(struct sk_buff *skb, const struct nfnl_info *info,
 	}
 
 	/* Only accept unspec with dump */
-	if (nfmsg->nfgen_family == NFPROTO_UNSPEC)
+	if (info->nfmsg->nfgen_family == NFPROTO_UNSPEC)
 		return -EAFNOSUPPORT;
 	if (!nla[NFTA_SET_TABLE])
 		return -EINVAL;
 
-	set = nft_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask);
+	set = nft_set_lookup(table, nla[NFTA_SET_NAME], genmask);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
 
@@ -4189,11 +4164,10 @@ static int nf_tables_set_desc_parse(struct nft_set_desc *desc,
 static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
 			    const struct nlattr * const nla[])
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	u32 ktype, dtype, flags, policy, gc_int, objtype;
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_next(info->net);
-	int family = nfmsg->nfgen_family;
+	u8 family = info->nfmsg->nfgen_family;
 	const struct nft_set_ops *ops;
 	struct nft_expr *expr = NULL;
 	struct net *net = info->net;
@@ -4494,31 +4468,31 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set)
 static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info,
 			    const struct nlattr * const nla[])
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_next(info->net);
+	u8 family = info->nfmsg->nfgen_family;
 	struct net *net = info->net;
 	const struct nlattr *attr;
+	struct nft_table *table;
 	struct nft_set *set;
 	struct nft_ctx ctx;
-	int err;
 
-	if (nfmsg->nfgen_family == NFPROTO_UNSPEC)
+	if (info->nfmsg->nfgen_family == NFPROTO_UNSPEC)
 		return -EAFNOSUPPORT;
-	if (nla[NFTA_SET_TABLE] == NULL)
-		return -EINVAL;
 
-	err = nft_ctx_init_from_setattr(&ctx, net, skb, info->nlh, nla, extack,
-					genmask, NETLINK_CB(skb).portid);
-	if (err < 0)
-		return err;
+	table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family,
+				 genmask, NETLINK_CB(skb).portid);
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]);
+		return PTR_ERR(table);
+	}
 
 	if (nla[NFTA_SET_HANDLE]) {
 		attr = nla[NFTA_SET_HANDLE];
-		set = nft_set_lookup_byhandle(ctx.table, attr, genmask);
+		set = nft_set_lookup_byhandle(table, attr, genmask);
 	} else {
 		attr = nla[NFTA_SET_NAME];
-		set = nft_set_lookup(ctx.table, attr, genmask);
+		set = nft_set_lookup(table, attr, genmask);
 	}
 
 	if (IS_ERR(set)) {
@@ -4532,6 +4506,8 @@ static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info,
 		return -EBUSY;
 	}
 
+	nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla);
+
 	return nft_delset(&ctx, set);
 }
 
@@ -4733,28 +4709,6 @@ static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX +
 	[NFTA_SET_ELEM_LIST_SET_ID]	= { .type = NLA_U32 },
 };
 
-static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net,
-				      const struct sk_buff *skb,
-				      const struct nlmsghdr *nlh,
-				      const struct nlattr * const nla[],
-				      struct netlink_ext_ack *extack,
-				      u8 genmask, u32 nlpid)
-{
-	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	int family = nfmsg->nfgen_family;
-	struct nft_table *table;
-
-	table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family,
-				 genmask, nlpid);
-	if (IS_ERR(table)) {
-		NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]);
-		return PTR_ERR(table);
-	}
-
-	nft_ctx_init(ctx, net, skb, nlh, family, table, NULL, nla);
-	return 0;
-}
-
 static int nft_set_elem_expr_dump(struct sk_buff *skb,
 				  const struct nft_set *set,
 				  const struct nft_set_ext *ext)
@@ -5212,21 +5166,27 @@ static int nf_tables_getsetelem(struct sk_buff *skb,
 {
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_cur(info->net);
+	u8 family = info->nfmsg->nfgen_family;
 	struct net *net = info->net;
+	struct nft_table *table;
 	struct nft_set *set;
 	struct nlattr *attr;
 	struct nft_ctx ctx;
 	int rem, err = 0;
 
-	err = nft_ctx_init_from_elemattr(&ctx, net, skb, info->nlh, nla, extack,
-					 genmask, NETLINK_CB(skb).portid);
-	if (err < 0)
-		return err;
+	table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family,
+				 genmask, NETLINK_CB(skb).portid);
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]);
+		return PTR_ERR(table);
+	}
 
-	set = nft_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], genmask);
+	set = nft_set_lookup(table, nla[NFTA_SET_ELEM_LIST_SET], genmask);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
 
+	nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla);
+
 	if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
 			.start = nf_tables_dump_set_start,
@@ -5995,8 +5955,10 @@ static int nf_tables_newsetelem(struct sk_buff *skb,
 	struct nftables_pernet *nft_net = nft_pernet(info->net);
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_next(info->net);
+	u8 family = info->nfmsg->nfgen_family;
 	struct net *net = info->net;
 	const struct nlattr *attr;
+	struct nft_table *table;
 	struct nft_set *set;
 	struct nft_ctx ctx;
 	int rem, err;
@@ -6004,12 +5966,14 @@ static int nf_tables_newsetelem(struct sk_buff *skb,
 	if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL)
 		return -EINVAL;
 
-	err = nft_ctx_init_from_elemattr(&ctx, net, skb, info->nlh, nla, extack,
-					 genmask, NETLINK_CB(skb).portid);
-	if (err < 0)
-		return err;
+	table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family,
+				 genmask, NETLINK_CB(skb).portid);
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]);
+		return PTR_ERR(table);
+	}
 
-	set = nft_set_lookup_global(net, ctx.table, nla[NFTA_SET_ELEM_LIST_SET],
+	set = nft_set_lookup_global(net, table, nla[NFTA_SET_ELEM_LIST_SET],
 				    nla[NFTA_SET_ELEM_LIST_SET_ID], genmask);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
@@ -6017,6 +5981,8 @@ static int nf_tables_newsetelem(struct sk_buff *skb,
 	if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT)
 		return -EBUSY;
 
+	nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla);
+
 	nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
 		err = nft_add_set_elem(&ctx, set, attr, info->nlh->nlmsg_flags);
 		if (err < 0)
@@ -6024,7 +5990,7 @@ static int nf_tables_newsetelem(struct sk_buff *skb,
 	}
 
 	if (nft_net->validate_state == NFT_VALIDATE_DO)
-		return nft_table_validate(net, ctx.table);
+		return nft_table_validate(net, table);
 
 	return 0;
 }
@@ -6262,23 +6228,29 @@ static int nf_tables_delsetelem(struct sk_buff *skb,
 {
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_next(info->net);
+	u8 family = info->nfmsg->nfgen_family;
 	struct net *net = info->net;
 	const struct nlattr *attr;
+	struct nft_table *table;
 	struct nft_set *set;
 	struct nft_ctx ctx;
 	int rem, err = 0;
 
-	err = nft_ctx_init_from_elemattr(&ctx, net, skb, info->nlh, nla, extack,
-					 genmask, NETLINK_CB(skb).portid);
-	if (err < 0)
-		return err;
+	table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family,
+				 genmask, NETLINK_CB(skb).portid);
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]);
+		return PTR_ERR(table);
+	}
 
-	set = nft_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], genmask);
+	set = nft_set_lookup(table, nla[NFTA_SET_ELEM_LIST_SET], genmask);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
 	if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT)
 		return -EBUSY;
 
+	nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla);
+
 	if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS])
 		return nft_set_flush(&ctx, set, genmask);
 
@@ -6546,11 +6518,10 @@ err_free_trans:
 static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info,
 			    const struct nlattr * const nla[])
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_next(info->net);
+	u8 family = info->nfmsg->nfgen_family;
 	const struct nft_object_type *type;
-	int family = nfmsg->nfgen_family;
 	struct net *net = info->net;
 	struct nft_table *table;
 	struct nft_object *obj;
@@ -6802,10 +6773,9 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb)
 static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,
 			    const struct nlattr * const nla[])
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_cur(info->net);
-	int family = nfmsg->nfgen_family;
+	u8 family = info->nfmsg->nfgen_family;
 	const struct nft_table *table;
 	struct net *net = info->net;
 	struct nft_object *obj;
@@ -6892,10 +6862,9 @@ static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj)
 static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info,
 			    const struct nlattr * const nla[])
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_next(info->net);
-	int family = nfmsg->nfgen_family;
+	u8 family = info->nfmsg->nfgen_family;
 	struct net *net = info->net;
 	const struct nlattr *attr;
 	struct nft_table *table;
@@ -7323,12 +7292,11 @@ static int nf_tables_newflowtable(struct sk_buff *skb,
 				  const struct nfnl_info *info,
 				  const struct nlattr * const nla[])
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct netlink_ext_ack *extack = info->extack;
 	struct nft_flowtable_hook flowtable_hook;
 	u8 genmask = nft_genmask_next(info->net);
+	u8 family = info->nfmsg->nfgen_family;
 	const struct nf_flowtable_type *type;
-	int family = nfmsg->nfgen_family;
 	struct nft_flowtable *flowtable;
 	struct nft_hook *hook, *next;
 	struct net *net = info->net;
@@ -7512,10 +7480,9 @@ static int nf_tables_delflowtable(struct sk_buff *skb,
 				  const struct nfnl_info *info,
 				  const struct nlattr * const nla[])
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_next(info->net);
-	int family = nfmsg->nfgen_family;
+	u8 family = info->nfmsg->nfgen_family;
 	struct nft_flowtable *flowtable;
 	struct net *net = info->net;
 	const struct nlattr *attr;
@@ -7707,9 +7674,8 @@ static int nf_tables_getflowtable(struct sk_buff *skb,
 				  const struct nfnl_info *info,
 				  const struct nlattr * const nla[])
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
 	u8 genmask = nft_genmask_cur(info->net);
-	int family = nfmsg->nfgen_family;
+	u8 family = info->nfmsg->nfgen_family;
 	struct nft_flowtable *flowtable;
 	const struct nft_table *table;
 	struct net *net = info->net;
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index dbc2e945c98e..7780342e2f2d 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -81,7 +81,7 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr,
 	else {
 		if (!pkt->tprot_set)
 			return false;
-		ptr = skb_network_header(skb) + pkt->xt.thoff;
+		ptr = skb_network_header(skb) + nft_thoff(pkt);
 	}
 
 	ptr += priv->offset;
diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c
index 0cf3278007ba..e4fe2f0780eb 100644
--- a/net/netfilter/nf_tables_trace.c
+++ b/net/netfilter/nf_tables_trace.c
@@ -113,17 +113,17 @@ static int nf_trace_fill_pkt_info(struct sk_buff *nlskb,
 	int off = skb_network_offset(skb);
 	unsigned int len, nh_end;
 
-	nh_end = pkt->tprot_set ? pkt->xt.thoff : skb->len;
+	nh_end = pkt->tprot_set ? nft_thoff(pkt) : skb->len;
 	len = min_t(unsigned int, nh_end - skb_network_offset(skb),
 		    NFT_TRACETYPE_NETWORK_HSIZE);
 	if (trace_fill_header(nlskb, NFTA_TRACE_NETWORK_HEADER, skb, off, len))
 		return -1;
 
 	if (pkt->tprot_set) {
-		len = min_t(unsigned int, skb->len - pkt->xt.thoff,
+		len = min_t(unsigned int, skb->len - nft_thoff(pkt),
 			    NFT_TRACETYPE_TRANSPORT_HSIZE);
 		if (trace_fill_header(nlskb, NFTA_TRACE_TRANSPORT_HEADER, skb,
-				      pkt->xt.thoff, len))
+				      nft_thoff(pkt), len))
 			return -1;
 	}
 
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index e8dbd8379027..7e2c8dd01408 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -68,6 +68,7 @@ static const char *const nfnl_lockdep_names[NFNL_SUBSYS_COUNT] = {
 	[NFNL_SUBSYS_CTHELPER] = "nfnl_subsys_cthelper",
 	[NFNL_SUBSYS_NFTABLES] = "nfnl_subsys_nftables",
 	[NFNL_SUBSYS_NFT_COMPAT] = "nfnl_subsys_nftcompat",
+	[NFNL_SUBSYS_HOOK] = "nfnl_subsys_hook",
 };
 
 static const int nfnl_group2type[NFNLGRP_MAX+1] = {
@@ -256,6 +257,7 @@ replay:
 			.net	= net,
 			.sk	= nfnlnet->nfnl,
 			.nlh	= nlh,
+			.nfmsg	= nlmsg_data(nlh),
 			.extack	= extack,
 		};
 
@@ -491,6 +493,7 @@ replay_abort:
 				.net	= net,
 				.sk	= nfnlnet->nfnl,
 				.nlh	= nlh,
+				.nfmsg	= nlmsg_data(nlh),
 				.extack	= &extack,
 			};
 
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index 3c8cf8748cfb..505f46a32173 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -314,14 +314,11 @@ static int nfnl_acct_get(struct sk_buff *skb, const struct nfnl_info *info,
 			kfree_skb(skb2);
 			break;
 		}
-		ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid,
-				      MSG_DONTWAIT);
-		if (ret > 0)
-			ret = 0;
 
-		/* this avoids a loop in nfnetlink. */
-		return ret == -EAGAIN ? -ENOBUFS : ret;
+		ret = nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid);
+		break;
 	}
+
 	return ret;
 }
 
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 752b10cae524..5c622f55c9d6 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -667,14 +667,10 @@ static int nfnl_cthelper_get(struct sk_buff *skb, const struct nfnl_info *info,
 			break;
 		}
 
-		ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid,
-				      MSG_DONTWAIT);
-		if (ret > 0)
-			ret = 0;
-
-		/* this avoids a loop in nfnetlink. */
-		return ret == -EAGAIN ? -ENOBUFS : ret;
+		ret = nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid);
+		break;
 	}
+
 	return ret;
 }
 
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 38848ad68899..c57673d499be 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -287,14 +287,11 @@ static int cttimeout_get_timeout(struct sk_buff *skb,
 			kfree_skb(skb2);
 			break;
 		}
-		ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid,
-				      MSG_DONTWAIT);
-		if (ret > 0)
-			ret = 0;
 
-		/* this avoids a loop in nfnetlink. */
-		return ret == -EAGAIN ? -ENOBUFS : ret;
+		ret = nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid);
+		break;
 	}
+
 	return ret;
 }
 
@@ -427,9 +424,9 @@ static int cttimeout_default_get(struct sk_buff *skb,
 	const struct nf_conntrack_l4proto *l4proto;
 	unsigned int *timeouts = NULL;
 	struct sk_buff *skb2;
-	int ret, err;
 	__u16 l3num;
 	__u8 l4num;
+	int ret;
 
 	if (!cda[CTA_TIMEOUT_L3PROTO] || !cda[CTA_TIMEOUT_L4PROTO])
 		return -EINVAL;
@@ -438,9 +435,8 @@ static int cttimeout_default_get(struct sk_buff *skb,
 	l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]);
 	l4proto = nf_ct_l4proto_find(l4num);
 
-	err = -EOPNOTSUPP;
 	if (l4proto->l4proto != l4num)
-		goto err;
+		return -EOPNOTSUPP;
 
 	switch (l4proto->l4proto) {
 	case IPPROTO_ICMP:
@@ -480,13 +476,11 @@ static int cttimeout_default_get(struct sk_buff *skb,
 	}
 
 	if (!timeouts)
-		goto err;
+		return -EOPNOTSUPP;
 
 	skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (skb2 == NULL) {
-		err = -ENOMEM;
-		goto err;
-	}
+	if (!skb2)
+		return -ENOMEM;
 
 	ret = cttimeout_default_fill_info(info->net, skb2,
 					  NETLINK_CB(skb).portid,
@@ -496,18 +490,10 @@ static int cttimeout_default_get(struct sk_buff *skb,
 					  l3num, l4proto, timeouts);
 	if (ret <= 0) {
 		kfree_skb(skb2);
-		err = -ENOMEM;
-		goto err;
+		return -ENOMEM;
 	}
-	ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid,
-			      MSG_DONTWAIT);
-	if (ret > 0)
-		ret = 0;
 
-	/* this avoids a loop in nfnetlink. */
-	return ret == -EAGAIN ? -ENOBUFS : ret;
-err:
-	return err;
+	return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid);
 }
 
 static struct nf_ct_timeout *ctnl_timeout_find_get(struct net *net,
diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c
new file mode 100644
index 000000000000..58fda6ac663b
--- /dev/null
+++ b/net/netfilter/nfnetlink_hook.c
@@ -0,0 +1,375 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2021 Red Hat GmbH
+ *
+ * Author: Florian Westphal <fw@strlen.de>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/skbuff.h>
+#include <linux/errno.h>
+#include <linux/netlink.h>
+#include <linux/slab.h>
+
+#include <linux/netfilter.h>
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_hook.h>
+
+#include <net/netfilter/nf_tables.h>
+#include <net/sock.h>
+
+static const struct nla_policy nfnl_hook_nla_policy[NFNLA_HOOK_MAX + 1] = {
+	[NFNLA_HOOK_HOOKNUM]	= { .type = NLA_U32 },
+	[NFNLA_HOOK_PRIORITY]	= { .type = NLA_U32 },
+	[NFNLA_HOOK_DEV]	= { .type = NLA_STRING,
+				    .len = IFNAMSIZ - 1 },
+	[NFNLA_HOOK_FUNCTION_NAME] = { .type = NLA_NUL_STRING,
+				       .len = KSYM_NAME_LEN, },
+	[NFNLA_HOOK_MODULE_NAME] = { .type = NLA_NUL_STRING,
+				     .len = MODULE_NAME_LEN, },
+	[NFNLA_HOOK_CHAIN_INFO] = { .type = NLA_NESTED, },
+};
+
+static int nf_netlink_dump_start_rcu(struct sock *nlsk, struct sk_buff *skb,
+				     const struct nlmsghdr *nlh,
+				     struct netlink_dump_control *c)
+{
+	int err;
+
+	if (!try_module_get(THIS_MODULE))
+		return -EINVAL;
+
+	rcu_read_unlock();
+	err = netlink_dump_start(nlsk, skb, nlh, c);
+	rcu_read_lock();
+	module_put(THIS_MODULE);
+
+	return err;
+}
+
+struct nfnl_dump_hook_data {
+	char devname[IFNAMSIZ];
+	unsigned long headv;
+	u8 hook;
+};
+
+static int nfnl_hook_put_nft_chain_info(struct sk_buff *nlskb,
+					const struct nfnl_dump_hook_data *ctx,
+					unsigned int seq,
+					const struct nf_hook_ops *ops)
+{
+	struct net *net = sock_net(nlskb->sk);
+	struct nlattr *nest, *nest2;
+	struct nft_chain *chain;
+	int ret = 0;
+
+	if (ops->hook_ops_type != NF_HOOK_OP_NF_TABLES)
+		return 0;
+
+	chain = ops->priv;
+	if (WARN_ON_ONCE(!chain))
+		return 0;
+
+	if (!nft_is_active(net, chain))
+		return 0;
+
+	nest = nla_nest_start(nlskb, NFNLA_HOOK_CHAIN_INFO);
+	if (!nest)
+		return -EMSGSIZE;
+
+	ret = nla_put_be32(nlskb, NFNLA_HOOK_INFO_TYPE,
+			   htonl(NFNL_HOOK_TYPE_NFTABLES));
+	if (ret)
+		goto cancel_nest;
+
+	nest2 = nla_nest_start(nlskb, NFNLA_HOOK_INFO_DESC);
+	if (!nest2)
+		goto cancel_nest;
+
+	ret = nla_put_string(nlskb, NFTA_CHAIN_TABLE, chain->table->name);
+	if (ret)
+		goto cancel_nest;
+
+	ret = nla_put_string(nlskb, NFTA_CHAIN_NAME, chain->name);
+	if (ret)
+		goto cancel_nest;
+
+	nla_nest_end(nlskb, nest2);
+	nla_nest_end(nlskb, nest);
+	return ret;
+
+cancel_nest:
+	nla_nest_cancel(nlskb, nest);
+	return -EMSGSIZE;
+}
+
+static int nfnl_hook_dump_one(struct sk_buff *nlskb,
+			      const struct nfnl_dump_hook_data *ctx,
+			      const struct nf_hook_ops *ops,
+			      unsigned int seq)
+{
+	u16 event = nfnl_msg_type(NFNL_SUBSYS_HOOK, NFNL_MSG_HOOK_GET);
+	unsigned int portid = NETLINK_CB(nlskb).portid;
+	struct nlmsghdr *nlh;
+	int ret = -EMSGSIZE;
+#ifdef CONFIG_KALLSYMS
+	char sym[KSYM_SYMBOL_LEN];
+	char *module_name;
+#endif
+	nlh = nfnl_msg_put(nlskb, portid, seq, event,
+			   NLM_F_MULTI, ops->pf, NFNETLINK_V0, 0);
+	if (!nlh)
+		goto nla_put_failure;
+
+#ifdef CONFIG_KALLSYMS
+	ret = snprintf(sym, sizeof(sym), "%ps", ops->hook);
+	if (ret < 0 || ret > (int)sizeof(sym))
+		goto nla_put_failure;
+
+	module_name = strstr(sym, " [");
+	if (module_name) {
+		char *end;
+
+		module_name += 2;
+		end = strchr(module_name, ']');
+		if (end) {
+			*end = 0;
+
+			ret = nla_put_string(nlskb, NFNLA_HOOK_MODULE_NAME, module_name);
+			if (ret)
+				goto nla_put_failure;
+		}
+	}
+
+	ret = nla_put_string(nlskb, NFNLA_HOOK_FUNCTION_NAME, sym);
+	if (ret)
+		goto nla_put_failure;
+#endif
+
+	ret = nla_put_be32(nlskb, NFNLA_HOOK_HOOKNUM, htonl(ops->hooknum));
+	if (ret)
+		goto nla_put_failure;
+
+	ret = nla_put_be32(nlskb, NFNLA_HOOK_PRIORITY, htonl(ops->priority));
+	if (ret)
+		goto nla_put_failure;
+
+	ret = nfnl_hook_put_nft_chain_info(nlskb, ctx, seq, ops);
+	if (ret)
+		goto nla_put_failure;
+
+	nlmsg_end(nlskb, nlh);
+	return 0;
+nla_put_failure:
+	nlmsg_trim(nlskb, nlh);
+	return ret;
+}
+
+static const struct nf_hook_entries *
+nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev)
+{
+	const struct nf_hook_entries *hook_head = NULL;
+	struct net_device *netdev;
+
+	switch (pf) {
+	case NFPROTO_IPV4:
+		if (hook >= ARRAY_SIZE(net->nf.hooks_ipv4))
+			return ERR_PTR(-EINVAL);
+		hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]);
+		break;
+	case NFPROTO_IPV6:
+		if (hook >= ARRAY_SIZE(net->nf.hooks_ipv6))
+			return ERR_PTR(-EINVAL);
+		hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]);
+		break;
+	case NFPROTO_ARP:
+#ifdef CONFIG_NETFILTER_FAMILY_ARP
+		if (hook >= ARRAY_SIZE(net->nf.hooks_arp))
+			return ERR_PTR(-EINVAL);
+		hook_head = rcu_dereference(net->nf.hooks_arp[hook]);
+#endif
+		break;
+	case NFPROTO_BRIDGE:
+#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
+		if (hook >= ARRAY_SIZE(net->nf.hooks_bridge))
+			return ERR_PTR(-EINVAL);
+		hook_head = rcu_dereference(net->nf.hooks_bridge[hook]);
+#endif
+		break;
+#if IS_ENABLED(CONFIG_DECNET)
+	case NFPROTO_DECNET:
+		if (hook >= ARRAY_SIZE(net->nf.hooks_decnet))
+			return ERR_PTR(-EINVAL);
+		hook_head = rcu_dereference(net->nf.hooks_decnet[hook]);
+		break;
+#endif
+#ifdef CONFIG_NETFILTER_INGRESS
+	case NFPROTO_NETDEV:
+		if (hook != NF_NETDEV_INGRESS)
+			return ERR_PTR(-EOPNOTSUPP);
+
+		if (!dev)
+			return ERR_PTR(-ENODEV);
+
+		netdev = dev_get_by_name_rcu(net, dev);
+		if (!netdev)
+			return ERR_PTR(-ENODEV);
+
+		return rcu_dereference(netdev->nf_hooks_ingress);
+#endif
+	default:
+		return ERR_PTR(-EPROTONOSUPPORT);
+	}
+
+	return hook_head;
+}
+
+static int nfnl_hook_dump(struct sk_buff *nlskb,
+			  struct netlink_callback *cb)
+{
+	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
+	struct nfnl_dump_hook_data *ctx = cb->data;
+	int err, family = nfmsg->nfgen_family;
+	struct net *net = sock_net(nlskb->sk);
+	struct nf_hook_ops * const *ops;
+	const struct nf_hook_entries *e;
+	unsigned int i = cb->args[0];
+
+	rcu_read_lock();
+
+	e = nfnl_hook_entries_head(family, ctx->hook, net, ctx->devname);
+	if (!e)
+		goto done;
+
+	if (IS_ERR(e)) {
+		cb->seq++;
+		goto done;
+	}
+
+	if ((unsigned long)e != ctx->headv || i >= e->num_hook_entries)
+		cb->seq++;
+
+	ops = nf_hook_entries_get_hook_ops(e);
+
+	for (; i < e->num_hook_entries; i++) {
+		err = nfnl_hook_dump_one(nlskb, ctx, ops[i], cb->seq);
+		if (err)
+			break;
+	}
+
+done:
+	nl_dump_check_consistent(cb, nlmsg_hdr(nlskb));
+	rcu_read_unlock();
+	cb->args[0] = i;
+	return nlskb->len;
+}
+
+static int nfnl_hook_dump_start(struct netlink_callback *cb)
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
+	const struct nlattr * const *nla = cb->data;
+	struct nfnl_dump_hook_data *ctx = NULL;
+	struct net *net = sock_net(cb->skb->sk);
+	u8 family = nfmsg->nfgen_family;
+	char name[IFNAMSIZ] = "";
+	const void *head;
+	u32 hooknum;
+
+	hooknum = ntohl(nla_get_be32(nla[NFNLA_HOOK_HOOKNUM]));
+	if (hooknum > 255)
+		return -EINVAL;
+
+	if (family == NFPROTO_NETDEV) {
+		if (!nla[NFNLA_HOOK_DEV])
+			return -EINVAL;
+
+		nla_strscpy(name, nla[NFNLA_HOOK_DEV], sizeof(name));
+	}
+
+	rcu_read_lock();
+	/* Not dereferenced; for consistency check only */
+	head = nfnl_hook_entries_head(family, hooknum, net, name);
+	rcu_read_unlock();
+
+	if (head && IS_ERR(head))
+		return PTR_ERR(head);
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	strscpy(ctx->devname, name, sizeof(ctx->devname));
+	ctx->headv = (unsigned long)head;
+	ctx->hook = hooknum;
+
+	cb->seq = 1;
+	cb->data = ctx;
+
+	return 0;
+}
+
+static int nfnl_hook_dump_stop(struct netlink_callback *cb)
+{
+	kfree(cb->data);
+	return 0;
+}
+
+static int nfnl_hook_get(struct sk_buff *skb,
+			 const struct nfnl_info *info,
+			 const struct nlattr * const nla[])
+{
+	if (!nla[NFNLA_HOOK_HOOKNUM])
+		return -EINVAL;
+
+	if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.start = nfnl_hook_dump_start,
+			.done = nfnl_hook_dump_stop,
+			.dump = nfnl_hook_dump,
+			.module = THIS_MODULE,
+			.data = (void *)nla,
+		};
+
+		return nf_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c);
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static const struct nfnl_callback nfnl_hook_cb[NFNL_MSG_HOOK_MAX] = {
+	[NFNL_MSG_HOOK_GET] = {
+		.call		= nfnl_hook_get,
+		.type		= NFNL_CB_RCU,
+		.attr_count	= NFNLA_HOOK_MAX,
+		.policy		= nfnl_hook_nla_policy
+	},
+};
+
+static const struct nfnetlink_subsystem nfhook_subsys = {
+	.name				= "nfhook",
+	.subsys_id			= NFNL_SUBSYS_HOOK,
+	.cb_count			= NFNL_MSG_HOOK_MAX,
+	.cb				= nfnl_hook_cb,
+};
+
+MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_HOOK);
+
+static int __init nfnetlink_hook_init(void)
+{
+	return nfnetlink_subsys_register(&nfhook_subsys);
+}
+
+static void __exit nfnetlink_hook_exit(void)
+{
+	nfnetlink_subsys_unregister(&nfhook_subsys);
+}
+
+module_init(nfnetlink_hook_init);
+module_exit(nfnetlink_hook_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
+MODULE_DESCRIPTION("nfnetlink_hook: list registered netfilter hooks");
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 587086b18c36..691ef4cffdd9 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -871,15 +871,14 @@ static int nfulnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info,
 			      const struct nlattr * const nfula[])
 {
 	struct nfnl_log_net *log = nfnl_log_pernet(info->net);
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
-	u_int16_t group_num = ntohs(nfmsg->res_id);
+	u_int16_t group_num = ntohs(info->nfmsg->res_id);
 	struct nfulnl_msg_config_cmd *cmd = NULL;
 	struct nfulnl_instance *inst;
 	u16 flags = 0;
 	int ret = 0;
 
 	if (nfula[NFULA_CFG_CMD]) {
-		u_int8_t pf = nfmsg->nfgen_family;
+		u_int8_t pf = info->nfmsg->nfgen_family;
 		cmd = nla_data(nfula[NFULA_CFG_CMD]);
 
 		/* Commands without queue context */
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index f37a575ebd7f..f774de0fc24f 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -1051,8 +1051,7 @@ static int nfqnl_recv_verdict_batch(struct sk_buff *skb,
 				    const struct nlattr * const nfqa[])
 {
 	struct nfnl_queue_net *q = nfnl_queue_pernet(info->net);
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
-	u16 queue_num = ntohs(nfmsg->res_id);
+	u16 queue_num = ntohs(info->nfmsg->res_id);
 	struct nf_queue_entry *entry, *tmp;
 	struct nfqnl_msg_verdict_hdr *vhdr;
 	struct nfqnl_instance *queue;
@@ -1160,8 +1159,7 @@ static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info,
 			      const struct nlattr * const nfqa[])
 {
 	struct nfnl_queue_net *q = nfnl_queue_pernet(info->net);
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
-	u_int16_t queue_num = ntohs(nfmsg->res_id);
+	u_int16_t queue_num = ntohs(info->nfmsg->res_id);
 	struct nfqnl_msg_verdict_hdr *vhdr;
 	enum ip_conntrack_info ctinfo;
 	struct nfqnl_instance *queue;
@@ -1243,8 +1241,7 @@ static int nfqnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info,
 			     const struct nlattr * const nfqa[])
 {
 	struct nfnl_queue_net *q = nfnl_queue_pernet(info->net);
-	struct nfgenmsg *nfmsg = nlmsg_data(info->nlh);
-	u_int16_t queue_num = ntohs(nfmsg->res_id);
+	u_int16_t queue_num = ntohs(info->nfmsg->res_id);
 	struct nfqnl_msg_config_cmd *cmd = NULL;
 	struct nfqnl_instance *queue;
 	__u32 flags = 0, mask = 0;
diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index 363bdd7044ec..5b02408a920b 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -18,7 +18,7 @@ static unsigned int nft_do_chain_ipv4(void *priv,
 	struct nft_pktinfo pkt;
 
 	nft_set_pktinfo(&pkt, skb, state);
-	nft_set_pktinfo_ipv4(&pkt, skb);
+	nft_set_pktinfo_ipv4(&pkt);
 
 	return nft_do_chain(&pkt, priv);
 }
@@ -62,7 +62,7 @@ static unsigned int nft_do_chain_arp(void *priv, struct sk_buff *skb,
 	struct nft_pktinfo pkt;
 
 	nft_set_pktinfo(&pkt, skb, state);
-	nft_set_pktinfo_unspec(&pkt, skb);
+	nft_set_pktinfo_unspec(&pkt);
 
 	return nft_do_chain(&pkt, priv);
 }
@@ -102,7 +102,7 @@ static unsigned int nft_do_chain_ipv6(void *priv,
 	struct nft_pktinfo pkt;
 
 	nft_set_pktinfo(&pkt, skb, state);
-	nft_set_pktinfo_ipv6(&pkt, skb);
+	nft_set_pktinfo_ipv6(&pkt);
 
 	return nft_do_chain(&pkt, priv);
 }
@@ -149,10 +149,10 @@ static unsigned int nft_do_chain_inet(void *priv, struct sk_buff *skb,
 
 	switch (state->pf) {
 	case NFPROTO_IPV4:
-		nft_set_pktinfo_ipv4(&pkt, skb);
+		nft_set_pktinfo_ipv4(&pkt);
 		break;
 	case NFPROTO_IPV6:
-		nft_set_pktinfo_ipv6(&pkt, skb);
+		nft_set_pktinfo_ipv6(&pkt);
 		break;
 	default:
 		break;
@@ -174,7 +174,7 @@ static unsigned int nft_do_chain_inet_ingress(void *priv, struct sk_buff *skb,
 		ingress_state.hook = NF_INET_INGRESS;
 		nft_set_pktinfo(&pkt, skb, &ingress_state);
 
-		if (nft_set_pktinfo_ipv4_ingress(&pkt, skb) < 0)
+		if (nft_set_pktinfo_ipv4_ingress(&pkt) < 0)
 			return NF_DROP;
 		break;
 	case htons(ETH_P_IPV6):
@@ -182,7 +182,7 @@ static unsigned int nft_do_chain_inet_ingress(void *priv, struct sk_buff *skb,
 		ingress_state.hook = NF_INET_INGRESS;
 		nft_set_pktinfo(&pkt, skb, &ingress_state);
 
-		if (nft_set_pktinfo_ipv6_ingress(&pkt, skb) < 0)
+		if (nft_set_pktinfo_ipv6_ingress(&pkt) < 0)
 			return NF_DROP;
 		break;
 	default:
@@ -238,13 +238,13 @@ nft_do_chain_bridge(void *priv,
 
 	switch (eth_hdr(skb)->h_proto) {
 	case htons(ETH_P_IP):
-		nft_set_pktinfo_ipv4_validate(&pkt, skb);
+		nft_set_pktinfo_ipv4_validate(&pkt);
 		break;
 	case htons(ETH_P_IPV6):
-		nft_set_pktinfo_ipv6_validate(&pkt, skb);
+		nft_set_pktinfo_ipv6_validate(&pkt);
 		break;
 	default:
-		nft_set_pktinfo_unspec(&pkt, skb);
+		nft_set_pktinfo_unspec(&pkt);
 		break;
 	}
 
@@ -293,13 +293,13 @@ static unsigned int nft_do_chain_netdev(void *priv, struct sk_buff *skb,
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
-		nft_set_pktinfo_ipv4_validate(&pkt, skb);
+		nft_set_pktinfo_ipv4_validate(&pkt);
 		break;
 	case htons(ETH_P_IPV6):
-		nft_set_pktinfo_ipv6_validate(&pkt, skb);
+		nft_set_pktinfo_ipv6_validate(&pkt);
 		break;
 	default:
-		nft_set_pktinfo_unspec(&pkt, skb);
+		nft_set_pktinfo_unspec(&pkt);
 		break;
 	}
 
diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c
index eac4a901233f..98e4946100c5 100644
--- a/net/netfilter/nft_chain_nat.c
+++ b/net/netfilter/nft_chain_nat.c
@@ -17,12 +17,12 @@ static unsigned int nft_nat_do_chain(void *priv, struct sk_buff *skb,
 	switch (state->pf) {
 #ifdef CONFIG_NF_TABLES_IPV4
 	case NFPROTO_IPV4:
-		nft_set_pktinfo_ipv4(&pkt, skb);
+		nft_set_pktinfo_ipv4(&pkt);
 		break;
 #endif
 #ifdef CONFIG_NF_TABLES_IPV6
 	case NFPROTO_IPV6:
-		nft_set_pktinfo_ipv6(&pkt, skb);
+		nft_set_pktinfo_ipv6(&pkt);
 		break;
 #endif
 	default:
diff --git a/net/netfilter/nft_chain_route.c b/net/netfilter/nft_chain_route.c
index edd02cda57fc..925db0dce48d 100644
--- a/net/netfilter/nft_chain_route.c
+++ b/net/netfilter/nft_chain_route.c
@@ -26,7 +26,7 @@ static unsigned int nf_route_table_hook4(void *priv,
 	u8 tos;
 
 	nft_set_pktinfo(&pkt, skb, state);
-	nft_set_pktinfo_ipv4(&pkt, skb);
+	nft_set_pktinfo_ipv4(&pkt);
 
 	mark = skb->mark;
 	iph = ip_hdr(skb);
@@ -74,7 +74,7 @@ static unsigned int nf_route_table_hook6(void *priv,
 	int err;
 
 	nft_set_pktinfo(&pkt, skb, state);
-	nft_set_pktinfo_ipv6(&pkt, skb);
+	nft_set_pktinfo_ipv6(&pkt);
 
 	/* save source/dest address, mark, hoplimit, flowlabel, priority */
 	memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr));
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 5415ab14400d..639c337c885b 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -57,8 +57,13 @@ union nft_entry {
 };
 
 static inline void
-nft_compat_set_par(struct xt_action_param *par, void *xt, const void *xt_info)
+nft_compat_set_par(struct xt_action_param *par,
+		   const struct nft_pktinfo *pkt,
+		   const void *xt, const void *xt_info)
 {
+	par->state	= pkt->state;
+	par->thoff	= nft_thoff(pkt);
+	par->fragoff	= pkt->fragoff;
 	par->target	= xt;
 	par->targinfo	= xt_info;
 	par->hotdrop	= false;
@@ -71,13 +76,14 @@ static void nft_target_eval_xt(const struct nft_expr *expr,
 	void *info = nft_expr_priv(expr);
 	struct xt_target *target = expr->ops->data;
 	struct sk_buff *skb = pkt->skb;
+	struct xt_action_param xt;
 	int ret;
 
-	nft_compat_set_par((struct xt_action_param *)&pkt->xt, target, info);
+	nft_compat_set_par(&xt, pkt, target, info);
 
-	ret = target->target(skb, &pkt->xt);
+	ret = target->target(skb, &xt);
 
-	if (pkt->xt.hotdrop)
+	if (xt.hotdrop)
 		ret = NF_DROP;
 
 	switch (ret) {
@@ -97,13 +103,14 @@ static void nft_target_eval_bridge(const struct nft_expr *expr,
 	void *info = nft_expr_priv(expr);
 	struct xt_target *target = expr->ops->data;
 	struct sk_buff *skb = pkt->skb;
+	struct xt_action_param xt;
 	int ret;
 
-	nft_compat_set_par((struct xt_action_param *)&pkt->xt, target, info);
+	nft_compat_set_par(&xt, pkt, target, info);
 
-	ret = target->target(skb, &pkt->xt);
+	ret = target->target(skb, &xt);
 
-	if (pkt->xt.hotdrop)
+	if (xt.hotdrop)
 		ret = NF_DROP;
 
 	switch (ret) {
@@ -350,13 +357,14 @@ static void __nft_match_eval(const struct nft_expr *expr,
 {
 	struct xt_match *match = expr->ops->data;
 	struct sk_buff *skb = pkt->skb;
+	struct xt_action_param xt;
 	bool ret;
 
-	nft_compat_set_par((struct xt_action_param *)&pkt->xt, match, info);
+	nft_compat_set_par(&xt, pkt, match, info);
 
-	ret = match->match(skb, (struct xt_action_param *)&pkt->xt);
+	ret = match->match(skb, &xt);
 
-	if (pkt->xt.hotdrop) {
+	if (xt.hotdrop) {
 		regs->verdict.code = NF_DROP;
 		return;
 	}
@@ -617,7 +625,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb,
 			       const struct nfnl_info *info,
 			       const struct nlattr * const tb[])
 {
-	struct nfgenmsg *nfmsg;
+	u8 family = info->nfmsg->nfgen_family;
 	const char *name, *fmt;
 	struct sk_buff *skb2;
 	int ret = 0, target;
@@ -632,9 +640,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb,
 	rev = ntohl(nla_get_be32(tb[NFTA_COMPAT_REV]));
 	target = ntohl(nla_get_be32(tb[NFTA_COMPAT_TYPE]));
 
-	nfmsg = nlmsg_data(info->nlh);
-
-	switch(nfmsg->nfgen_family) {
+	switch(family) {
 	case AF_INET:
 		fmt = "ipt_%s";
 		break;
@@ -648,8 +654,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb,
 		fmt = "arpt_%s";
 		break;
 	default:
-		pr_err("nft_compat: unsupported protocol %d\n",
-			nfmsg->nfgen_family);
+		pr_err("nft_compat: unsupported protocol %d\n", family);
 		return -EINVAL;
 	}
 
@@ -657,9 +662,8 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb,
 		return -EINVAL;
 
 	rcu_read_unlock();
-	try_then_request_module(xt_find_revision(nfmsg->nfgen_family, name,
-						 rev, target, &ret),
-						 fmt, name);
+	try_then_request_module(xt_find_revision(family, name, rev, target, &ret),
+				fmt, name);
 	if (ret < 0)
 		goto out_put;
 
@@ -674,8 +678,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb,
 				  info->nlh->nlmsg_seq,
 				  NFNL_MSG_TYPE(info->nlh->nlmsg_type),
 				  NFNL_MSG_COMPAT_GET,
-				  nfmsg->nfgen_family,
-				  name, ret, target) <= 0) {
+				  family, name, ret, target) <= 0) {
 		kfree_skb(skb2);
 		goto out_put;
 	}
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index f64f0017e9a5..7f705b5c09de 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -10,8 +10,10 @@
 #include <linux/netlink.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
+#include <linux/sctp.h>
 #include <net/netfilter/nf_tables_core.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/sctp/sctp.h>
 #include <net/tcp.h>
 
 struct nft_exthdr {
@@ -165,7 +167,7 @@ nft_tcp_header_pointer(const struct nft_pktinfo *pkt,
 	if (!pkt->tprot_set || pkt->tprot != IPPROTO_TCP)
 		return NULL;
 
-	tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff, sizeof(*tcph), buffer);
+	tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(*tcph), buffer);
 	if (!tcph)
 		return NULL;
 
@@ -173,7 +175,7 @@ nft_tcp_header_pointer(const struct nft_pktinfo *pkt,
 	if (*tcphdr_len < sizeof(*tcph) || *tcphdr_len > len)
 		return NULL;
 
-	return skb_header_pointer(pkt->skb, pkt->xt.thoff, *tcphdr_len, buffer);
+	return skb_header_pointer(pkt->skb, nft_thoff(pkt), *tcphdr_len, buffer);
 }
 
 static void nft_exthdr_tcp_eval(const struct nft_expr *expr,
@@ -249,7 +251,7 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr,
 			return;
 
 		if (skb_ensure_writable(pkt->skb,
-					pkt->xt.thoff + i + priv->len))
+					nft_thoff(pkt) + i + priv->len))
 			return;
 
 		tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff,
@@ -300,6 +302,45 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr,
 	}
 }
 
+static void nft_exthdr_sctp_eval(const struct nft_expr *expr,
+				 struct nft_regs *regs,
+				 const struct nft_pktinfo *pkt)
+{
+	unsigned int offset = nft_thoff(pkt) + sizeof(struct sctphdr);
+	struct nft_exthdr *priv = nft_expr_priv(expr);
+	u32 *dest = &regs->data[priv->dreg];
+	const struct sctp_chunkhdr *sch;
+	struct sctp_chunkhdr _sch;
+
+	do {
+		sch = skb_header_pointer(pkt->skb, offset, sizeof(_sch), &_sch);
+		if (!sch || !sch->length)
+			break;
+
+		if (sch->type == priv->type) {
+			if (priv->flags & NFT_EXTHDR_F_PRESENT) {
+				nft_reg_store8(dest, true);
+				return;
+			}
+			if (priv->offset + priv->len > ntohs(sch->length) ||
+			    offset + ntohs(sch->length) > pkt->skb->len)
+				break;
+
+			dest[priv->len / NFT_REG32_SIZE] = 0;
+			if (skb_copy_bits(pkt->skb, offset + priv->offset,
+					  dest, priv->len) < 0)
+				break;
+			return;
+		}
+		offset += SCTP_PAD4(ntohs(sch->length));
+	} while (offset < pkt->skb->len);
+
+	if (priv->flags & NFT_EXTHDR_F_PRESENT)
+		nft_reg_store8(dest, false);
+	else
+		regs->verdict.code = NFT_BREAK;
+}
+
 static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = {
 	[NFTA_EXTHDR_DREG]		= { .type = NLA_U32 },
 	[NFTA_EXTHDR_TYPE]		= { .type = NLA_U8 },
@@ -499,6 +540,14 @@ static const struct nft_expr_ops nft_exthdr_tcp_set_ops = {
 	.dump		= nft_exthdr_dump_set,
 };
 
+static const struct nft_expr_ops nft_exthdr_sctp_ops = {
+	.type		= &nft_exthdr_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_exthdr)),
+	.eval		= nft_exthdr_sctp_eval,
+	.init		= nft_exthdr_init,
+	.dump		= nft_exthdr_dump,
+};
+
 static const struct nft_expr_ops *
 nft_exthdr_select_ops(const struct nft_ctx *ctx,
 		      const struct nlattr * const tb[])
@@ -529,6 +578,10 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx,
 				return &nft_exthdr_ipv4_ops;
 		}
 		break;
+	case NFT_EXTHDR_OP_SCTP:
+		if (tb[NFTA_EXTHDR_DREG])
+			return &nft_exthdr_sctp_ops;
+		break;
 	}
 
 	return ERR_PTR(-EOPNOTSUPP);
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index 4843dd2b410c..0af34ad41479 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -291,7 +291,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 
 	switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) {
 	case IPPROTO_TCP:
-		tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff,
+		tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt),
 					  sizeof(_tcph), &_tcph);
 		if (unlikely(!tcph || tcph->fin || tcph->rst))
 			goto out;
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index a479f8a1270c..90becbf5bff3 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -23,6 +23,37 @@ struct nft_lookup {
 	struct nft_set_binding		binding;
 };
 
+#ifdef CONFIG_RETPOLINE
+bool nft_set_do_lookup(const struct net *net, const struct nft_set *set,
+		       const u32 *key, const struct nft_set_ext **ext)
+{
+	if (set->ops == &nft_set_hash_fast_type.ops)
+		return nft_hash_lookup_fast(net, set, key, ext);
+	if (set->ops == &nft_set_hash_type.ops)
+		return nft_hash_lookup(net, set, key, ext);
+
+	if (set->ops == &nft_set_rhash_type.ops)
+		return nft_rhash_lookup(net, set, key, ext);
+
+	if (set->ops == &nft_set_bitmap_type.ops)
+		return nft_bitmap_lookup(net, set, key, ext);
+
+	if (set->ops == &nft_set_pipapo_type.ops)
+		return nft_pipapo_lookup(net, set, key, ext);
+#if defined(CONFIG_X86_64) && !defined(CONFIG_UML)
+	if (set->ops == &nft_set_pipapo_avx2_type.ops)
+		return nft_pipapo_avx2_lookup(net, set, key, ext);
+#endif
+
+	if (set->ops == &nft_set_rbtree_type.ops)
+		return nft_rbtree_lookup(net, set, key, ext);
+
+	WARN_ON_ONCE(1);
+	return set->ops->lookup(net, set, key, ext);
+}
+EXPORT_SYMBOL_GPL(nft_set_do_lookup);
+#endif
+
 void nft_lookup_eval(const struct nft_expr *expr,
 		     struct nft_regs *regs,
 		     const struct nft_pktinfo *pkt)
@@ -33,8 +64,8 @@ void nft_lookup_eval(const struct nft_expr *expr,
 	const struct net *net = nft_net(pkt);
 	bool found;
 
-	found = set->ops->lookup(net, set, &regs->data[priv->sreg], &ext) ^
-				 priv->invert;
+	found =	nft_set_do_lookup(net, set, &regs->data[priv->sreg], &ext) ^
+				  priv->invert;
 	if (!found) {
 		ext = nft_set_catchall_lookup(net, set);
 		if (!ext) {
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index 7e47edee88ee..94b2327e71dc 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -9,7 +9,7 @@
 #include <linux/netlink.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
 
 #define nft_objref_priv(expr)	*((struct nft_object **)nft_expr_priv(expr))
 
@@ -110,7 +110,7 @@ static void nft_objref_map_eval(const struct nft_expr *expr,
 	struct nft_object *obj;
 	bool found;
 
-	found = set->ops->lookup(net, set, &regs->data[priv->sreg], &ext);
+	found = nft_set_do_lookup(net, set, &regs->data[priv->sreg], &ext);
 	if (!found) {
 		ext = nft_set_catchall_lookup(net, set);
 		if (!ext) {
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 501c5b24cc39..a44b14f6c0dc 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -110,7 +110,7 @@ void nft_payload_eval(const struct nft_expr *expr,
 	case NFT_PAYLOAD_TRANSPORT_HEADER:
 		if (!pkt->tprot_set)
 			goto err;
-		offset = pkt->xt.thoff;
+		offset = nft_thoff(pkt);
 		break;
 	default:
 		BUG();
@@ -507,7 +507,7 @@ static int nft_payload_l4csum_offset(const struct nft_pktinfo *pkt,
 		*l4csum_offset = offsetof(struct tcphdr, check);
 		break;
 	case IPPROTO_UDP:
-		if (!nft_payload_udp_checksum(skb, pkt->xt.thoff))
+		if (!nft_payload_udp_checksum(skb, nft_thoff(pkt)))
 			return -1;
 		fallthrough;
 	case IPPROTO_UDPLITE:
@@ -520,7 +520,7 @@ static int nft_payload_l4csum_offset(const struct nft_pktinfo *pkt,
 		return -1;
 	}
 
-	*l4csum_offset += pkt->xt.thoff;
+	*l4csum_offset += nft_thoff(pkt);
 	return 0;
 }
 
@@ -612,7 +612,7 @@ static void nft_payload_set_eval(const struct nft_expr *expr,
 	case NFT_PAYLOAD_TRANSPORT_HEADER:
 		if (!pkt->tprot_set)
 			goto err;
-		offset = pkt->xt.thoff;
+		offset = nft_thoff(pkt);
 		break;
 	default:
 		BUG();
@@ -643,7 +643,7 @@ static void nft_payload_set_eval(const struct nft_expr *expr,
 	if (priv->csum_type == NFT_PAYLOAD_CSUM_SCTP &&
 	    pkt->tprot == IPPROTO_SCTP &&
 	    skb->ip_summed != CHECKSUM_PARTIAL) {
-		if (nft_payload_csum_sctp(skb, pkt->xt.thoff))
+		if (nft_payload_csum_sctp(skb, nft_thoff(pkt)))
 			goto err;
 	}
 
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
index 95090186ee90..554caf967baa 100644
--- a/net/netfilter/nft_reject_inet.c
+++ b/net/netfilter/nft_reject_inet.c
@@ -28,7 +28,7 @@ static void nft_reject_inet_eval(const struct nft_expr *expr,
 					nft_hook(pkt));
 			break;
 		case NFT_REJECT_TCP_RST:
-			nf_send_reset(nft_net(pkt), pkt->xt.state->sk,
+			nf_send_reset(nft_net(pkt), nft_sk(pkt),
 				      pkt->skb, nft_hook(pkt));
 			break;
 		case NFT_REJECT_ICMPX_UNREACH:
@@ -45,7 +45,7 @@ static void nft_reject_inet_eval(const struct nft_expr *expr,
 					 priv->icmp_code, nft_hook(pkt));
 			break;
 		case NFT_REJECT_TCP_RST:
-			nf_send_reset6(nft_net(pkt), pkt->xt.state->sk,
+			nf_send_reset6(nft_net(pkt), nft_sk(pkt),
 				       pkt->skb, nft_hook(pkt));
 			break;
 		case NFT_REJECT_ICMPX_UNREACH:
diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c
index 2a81ea421819..e7ae5914971e 100644
--- a/net/netfilter/nft_set_bitmap.c
+++ b/net/netfilter/nft_set_bitmap.c
@@ -73,8 +73,9 @@ nft_bitmap_active(const u8 *bitmap, u32 idx, u32 off, u8 genmask)
 	return (bitmap[idx] & (0x3 << off)) & (genmask << off);
 }
 
-static bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set,
-			      const u32 *key, const struct nft_set_ext **ext)
+INDIRECT_CALLABLE_SCOPE
+bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set,
+		       const u32 *key, const struct nft_set_ext **ext)
 {
 	const struct nft_bitmap *priv = nft_set_priv(set);
 	u8 genmask = nft_genmask_cur(net);
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 7b3d0a78c569..df40314de21f 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -74,8 +74,9 @@ static const struct rhashtable_params nft_rhash_params = {
 	.automatic_shrinking	= true,
 };
 
-static bool nft_rhash_lookup(const struct net *net, const struct nft_set *set,
-			     const u32 *key, const struct nft_set_ext **ext)
+INDIRECT_CALLABLE_SCOPE
+bool nft_rhash_lookup(const struct net *net, const struct nft_set *set,
+		      const u32 *key, const struct nft_set_ext **ext)
 {
 	struct nft_rhash *priv = nft_set_priv(set);
 	const struct nft_rhash_elem *he;
@@ -446,8 +447,9 @@ struct nft_hash_elem {
 	struct nft_set_ext		ext;
 };
 
-static bool nft_hash_lookup(const struct net *net, const struct nft_set *set,
-			    const u32 *key, const struct nft_set_ext **ext)
+INDIRECT_CALLABLE_SCOPE
+bool nft_hash_lookup(const struct net *net, const struct nft_set *set,
+		     const u32 *key, const struct nft_set_ext **ext)
 {
 	struct nft_hash *priv = nft_set_priv(set);
 	u8 genmask = nft_genmask_cur(net);
@@ -484,9 +486,10 @@ static void *nft_hash_get(const struct net *net, const struct nft_set *set,
 	return ERR_PTR(-ENOENT);
 }
 
-static bool nft_hash_lookup_fast(const struct net *net,
-				 const struct nft_set *set,
-				 const u32 *key, const struct nft_set_ext **ext)
+INDIRECT_CALLABLE_SCOPE
+bool nft_hash_lookup_fast(const struct net *net,
+			  const struct nft_set *set,
+			  const u32 *key, const struct nft_set_ext **ext)
 {
 	struct nft_hash *priv = nft_set_priv(set);
 	u8 genmask = nft_genmask_cur(net);
diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
index d84afb8fa79a..25a75591583e 100644
--- a/net/netfilter/nft_set_pipapo.h
+++ b/net/netfilter/nft_set_pipapo.h
@@ -178,8 +178,6 @@ struct nft_pipapo_elem {
 
 int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst,
 		  union nft_pipapo_map_bucket *mt, bool match_only);
-bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
-		       const u32 *key, const struct nft_set_ext **ext);
 
 /**
  * pipapo_and_field_buckets_4bit() - Intersect 4-bit buckets
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index eabdb8d552ee..e517663e0cd1 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -142,7 +142,6 @@ static void nft_pipapo_avx2_fill(unsigned long *data, int start, int len)
  * @map:	Bitmap to be scanned for set bits
  * @dst:	Destination bitmap
  * @mt:		Mapping table containing bit set specifiers
- * @len:	Length of bitmap in longs
  * @last:	Return index of first set bit, if this is the last field
  *
  * This is an alternative implementation of pipapo_refill() suitable for usage
@@ -1109,7 +1108,7 @@ bool nft_pipapo_avx2_estimate(const struct nft_set_desc *desc, u32 features,
  * nft_pipapo_avx2_lookup() - Lookup function for AVX2 implementation
  * @net:	Network namespace
  * @set:	nftables API set representation
- * @elem:	nftables API element representation containing key data
+ * @key:	nftables API element representation containing key data
  * @ext:	nftables API extension pointer, filled with matching reference
  *
  * For more details, see DOC: Theory of Operation in nft_set_pipapo.c.
@@ -1136,8 +1135,13 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 
 	m = rcu_dereference(priv->match);
 
-	/* This also protects access to all data related to scratch maps */
-	kernel_fpu_begin();
+	/* This also protects access to all data related to scratch maps.
+	 *
+	 * Note that we don't need a valid MXCSR state for any of the
+	 * operations we use here, so pass 0 as mask and spare a LDMXCSR
+	 * instruction.
+	 */
+	kernel_fpu_begin_mask(0);
 
 	scratch = *raw_cpu_ptr(m->scratch_aligned);
 	if (unlikely(!scratch)) {
diff --git a/net/netfilter/nft_set_pipapo_avx2.h b/net/netfilter/nft_set_pipapo_avx2.h
index 394bcb704db7..dbb6aaca8a7a 100644
--- a/net/netfilter/nft_set_pipapo_avx2.h
+++ b/net/netfilter/nft_set_pipapo_avx2.h
@@ -5,8 +5,6 @@
 #include <asm/fpu/xstate.h>
 #define NFT_PIPAPO_ALIGN	(XSAVE_YMM_SIZE / BITS_PER_BYTE)
 
-bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
-			    const u32 *key, const struct nft_set_ext **ext);
 bool nft_pipapo_avx2_estimate(const struct nft_set_desc *desc, u32 features,
 			      struct nft_set_estimate *est);
 #endif /* defined(CONFIG_X86_64) && !defined(CONFIG_UML) */
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 9e36eb4a7429..d600a566da32 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -107,8 +107,9 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 	return false;
 }
 
-static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
-			      const u32 *key, const struct nft_set_ext **ext)
+INDIRECT_CALLABLE_SCOPE
+bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
+		       const u32 *key, const struct nft_set_ext **ext)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	unsigned int seq = read_seqcount_begin(&priv->count);
diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c
index 4fda8b3f1762..a0109fa1e92d 100644
--- a/net/netfilter/nft_synproxy.c
+++ b/net/netfilter/nft_synproxy.c
@@ -109,7 +109,7 @@ static void nft_synproxy_do_eval(const struct nft_synproxy *priv,
 {
 	struct synproxy_options opts = {};
 	struct sk_buff *skb = pkt->skb;
-	int thoff = pkt->xt.thoff;
+	int thoff = nft_thoff(pkt);
 	const struct tcphdr *tcp;
 	struct tcphdr _tcph;
 
@@ -123,7 +123,7 @@ static void nft_synproxy_do_eval(const struct nft_synproxy *priv,
 		return;
 	}
 
-	tcp = skb_header_pointer(skb, pkt->xt.thoff,
+	tcp = skb_header_pointer(skb, thoff,
 				 sizeof(struct tcphdr),
 				 &_tcph);
 	if (!tcp) {
diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c
index accef672088c..18e79c0fd3cf 100644
--- a/net/netfilter/nft_tproxy.c
+++ b/net/netfilter/nft_tproxy.c
@@ -82,9 +82,9 @@ static void nft_tproxy_eval_v6(const struct nft_expr *expr,
 	const struct nft_tproxy *priv = nft_expr_priv(expr);
 	struct sk_buff *skb = pkt->skb;
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
-	struct in6_addr taddr;
-	int thoff = pkt->xt.thoff;
+	int thoff = nft_thoff(pkt);
 	struct udphdr _hdr, *hp;
+	struct in6_addr taddr;
 	__be16 tport = 0;
 	struct sock *sk;
 	int l4proto;
diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c
index 9cdc16b0d0d8..b6a015aee0ce 100644
--- a/net/netfilter/xt_AUDIT.c
+++ b/net/netfilter/xt_AUDIT.c
@@ -117,7 +117,7 @@ static int audit_tg_check(const struct xt_tgchk_param *par)
 	const struct xt_audit_info *info = par->targinfo;
 
 	if (info->type > XT_AUDIT_TYPE_MAX) {
-		pr_info_ratelimited("Audit type out of range (valid range: 0..%hhu)\n",
+		pr_info_ratelimited("Audit type out of range (valid range: 0..%u)\n",
 				    XT_AUDIT_TYPE_MAX);
 		return -ERANGE;
 	}
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index d4deee39158b..12404d221026 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -172,7 +172,6 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 		goto err2;
 	}
 
-	ret = 0;
 	if ((info->ct_events || info->exp_events) &&
 	    !nf_ct_ecache_ext_add(ct, info->ct_events, info->exp_events,
 				  GFP_KERNEL)) {
diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c
index 24d4afb9988d..8b4fd27857f2 100644
--- a/net/netfilter/xt_limit.c
+++ b/net/netfilter/xt_limit.c
@@ -8,16 +8,14 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/skbuff.h>
-#include <linux/spinlock.h>
 #include <linux/interrupt.h>
 
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/xt_limit.h>
 
 struct xt_limit_priv {
-	spinlock_t lock;
 	unsigned long prev;
-	uint32_t credit;
+	u32 credit;
 };
 
 MODULE_LICENSE("GPL");
@@ -66,22 +64,31 @@ limit_mt(const struct sk_buff *skb, struct xt_action_param *par)
 {
 	const struct xt_rateinfo *r = par->matchinfo;
 	struct xt_limit_priv *priv = r->master;
-	unsigned long now = jiffies;
-
-	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;
-
-	if (priv->credit >= r->cost) {
-		/* We're not limited. */
-		priv->credit -= r->cost;
-		spin_unlock_bh(&priv->lock);
-		return true;
-	}
-
-	spin_unlock_bh(&priv->lock);
-	return false;
+	unsigned long now;
+	u32 old_credit, new_credit, credit_increase = 0;
+	bool ret;
+
+	/* fastpath if there is nothing to update */
+	if ((READ_ONCE(priv->credit) < r->cost) && (READ_ONCE(priv->prev) == jiffies))
+		return false;
+
+	do {
+		now = jiffies;
+		credit_increase += (now - xchg(&priv->prev, now)) * CREDITS_PER_JIFFY;
+		old_credit = READ_ONCE(priv->credit);
+		new_credit = old_credit;
+		new_credit += credit_increase;
+		if (new_credit > r->credit_cap)
+			new_credit = r->credit_cap;
+		if (new_credit >= r->cost) {
+			ret = true;
+			new_credit -= r->cost;
+		} else {
+			ret = false;
+		}
+	} while (cmpxchg(&priv->credit, old_credit, new_credit) != old_credit);
+
+	return ret;
 }
 
 /* Precision saver. */
@@ -122,7 +129,6 @@ 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/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c
index f28c8947c730..91a19c3ea1a3 100644
--- a/net/netlabel/netlabel_calipso.c
+++ b/net/netlabel/netlabel_calipso.c
@@ -105,7 +105,7 @@ static int netlbl_calipso_add(struct sk_buff *skb, struct genl_info *info)
 	    !info->attrs[NLBL_CALIPSO_A_MTYPE])
 		return -EINVAL;
 
-	netlbl_netlink_auditinfo(skb, &audit_info);
+	netlbl_netlink_auditinfo(&audit_info);
 	switch (nla_get_u32(info->attrs[NLBL_CALIPSO_A_MTYPE])) {
 	case CALIPSO_MAP_PASS:
 		ret_val = netlbl_calipso_add_pass(info, &audit_info);
@@ -287,7 +287,7 @@ static int netlbl_calipso_remove(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[NLBL_CALIPSO_A_DOI])
 		return -EINVAL;
 
-	netlbl_netlink_auditinfo(skb, &audit_info);
+	netlbl_netlink_auditinfo(&audit_info);
 	cb_arg.doi = nla_get_u32(info->attrs[NLBL_CALIPSO_A_DOI]);
 	cb_arg.audit_info = &audit_info;
 	ret_val = netlbl_domhsh_walk(&skip_bkt, &skip_chain,
diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c
index 4f50a64315cf..baf235721c43 100644
--- a/net/netlabel/netlabel_cipso_v4.c
+++ b/net/netlabel/netlabel_cipso_v4.c
@@ -410,7 +410,7 @@ static int netlbl_cipsov4_add(struct sk_buff *skb, struct genl_info *info)
 	    !info->attrs[NLBL_CIPSOV4_A_MTYPE])
 		return -EINVAL;
 
-	netlbl_netlink_auditinfo(skb, &audit_info);
+	netlbl_netlink_auditinfo(&audit_info);
 	switch (nla_get_u32(info->attrs[NLBL_CIPSOV4_A_MTYPE])) {
 	case CIPSO_V4_MAP_TRANS:
 		ret_val = netlbl_cipsov4_add_std(info, &audit_info);
@@ -709,7 +709,7 @@ static int netlbl_cipsov4_remove(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[NLBL_CIPSOV4_A_DOI])
 		return -EINVAL;
 
-	netlbl_netlink_auditinfo(skb, &audit_info);
+	netlbl_netlink_auditinfo(&audit_info);
 	cb_arg.doi = nla_get_u32(info->attrs[NLBL_CIPSOV4_A_DOI]);
 	cb_arg.audit_info = &audit_info;
 	ret_val = netlbl_domhsh_walk(&skip_bkt, &skip_chain,
diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c
index dc8c39f51f7d..8158a25972b4 100644
--- a/net/netlabel/netlabel_domainhash.c
+++ b/net/netlabel/netlabel_domainhash.c
@@ -929,7 +929,7 @@ struct netlbl_dommap_def *netlbl_domhsh_getentry_af6(const char *domain,
  * @cb_arg: argument for the callback function
  *
  * Description:
- * Interate over the domain mapping hash table, skipping the first @skip_bkt
+ * Iterate over the domain mapping hash table, skipping the first @skip_bkt
  * buckets and @skip_chain entries.  For each entry in the table call
  * @callback, if @callback returns a negative value stop 'walking' through the
  * table and return.  Updates the values in @skip_bkt and @skip_chain on
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index 5e1239cef000..beb0e573266d 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -719,7 +719,7 @@ int netlbl_catmap_walkrng(struct netlbl_lsm_catmap *catmap, u32 offset)
  * it in @bitmap.  The @offset must be aligned to an unsigned long and will be
  * updated on return if different from what was requested; if the catmap is
  * empty at the requested offset and beyond, the @offset is set to (u32)-1.
- * Returns zero on sucess, negative values on failure.
+ * Returns zero on success, negative values on failure.
  *
  */
 int netlbl_catmap_getlong(struct netlbl_lsm_catmap *catmap,
diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c
index ca52f5085989..032b7d7b32c7 100644
--- a/net/netlabel/netlabel_mgmt.c
+++ b/net/netlabel/netlabel_mgmt.c
@@ -76,6 +76,7 @@ static const struct nla_policy netlbl_mgmt_genl_policy[NLBL_MGMT_A_MAX + 1] = {
 static int netlbl_mgmt_add_common(struct genl_info *info,
 				  struct netlbl_audit *audit_info)
 {
+	void *pmap = NULL;
 	int ret_val = -EINVAL;
 	struct netlbl_domaddr_map *addrmap = NULL;
 	struct cipso_v4_doi *cipsov4 = NULL;
@@ -175,6 +176,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 			ret_val = -ENOMEM;
 			goto add_free_addrmap;
 		}
+		pmap = map;
 		map->list.addr = addr->s_addr & mask->s_addr;
 		map->list.mask = mask->s_addr;
 		map->list.valid = 1;
@@ -183,10 +185,8 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 			map->def.cipso = cipsov4;
 
 		ret_val = netlbl_af4list_add(&map->list, &addrmap->list4);
-		if (ret_val != 0) {
-			kfree(map);
-			goto add_free_addrmap;
-		}
+		if (ret_val != 0)
+			goto add_free_map;
 
 		entry->family = AF_INET;
 		entry->def.type = NETLBL_NLTYPE_ADDRSELECT;
@@ -223,6 +223,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 			ret_val = -ENOMEM;
 			goto add_free_addrmap;
 		}
+		pmap = map;
 		map->list.addr = *addr;
 		map->list.addr.s6_addr32[0] &= mask->s6_addr32[0];
 		map->list.addr.s6_addr32[1] &= mask->s6_addr32[1];
@@ -235,10 +236,8 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 			map->def.calipso = calipso;
 
 		ret_val = netlbl_af6list_add(&map->list, &addrmap->list6);
-		if (ret_val != 0) {
-			kfree(map);
-			goto add_free_addrmap;
-		}
+		if (ret_val != 0)
+			goto add_free_map;
 
 		entry->family = AF_INET6;
 		entry->def.type = NETLBL_NLTYPE_ADDRSELECT;
@@ -248,10 +247,12 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 
 	ret_val = netlbl_domhsh_add(entry, audit_info);
 	if (ret_val != 0)
-		goto add_free_addrmap;
+		goto add_free_map;
 
 	return 0;
 
+add_free_map:
+	kfree(pmap);
 add_free_addrmap:
 	kfree(addrmap);
 add_doi_put_def:
@@ -434,7 +435,7 @@ static int netlbl_mgmt_add(struct sk_buff *skb, struct genl_info *info)
 	     (info->attrs[NLBL_MGMT_A_IPV6MASK] != NULL)))
 		return -EINVAL;
 
-	netlbl_netlink_auditinfo(skb, &audit_info);
+	netlbl_netlink_auditinfo(&audit_info);
 
 	return netlbl_mgmt_add_common(info, &audit_info);
 }
@@ -457,7 +458,7 @@ static int netlbl_mgmt_remove(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[NLBL_MGMT_A_DOMAIN])
 		return -EINVAL;
 
-	netlbl_netlink_auditinfo(skb, &audit_info);
+	netlbl_netlink_auditinfo(&audit_info);
 
 	domain = nla_data(info->attrs[NLBL_MGMT_A_DOMAIN]);
 	return netlbl_domhsh_remove(domain, AF_UNSPEC, &audit_info);
@@ -557,7 +558,7 @@ static int netlbl_mgmt_adddef(struct sk_buff *skb, struct genl_info *info)
 	     (info->attrs[NLBL_MGMT_A_IPV6MASK] != NULL)))
 		return -EINVAL;
 
-	netlbl_netlink_auditinfo(skb, &audit_info);
+	netlbl_netlink_auditinfo(&audit_info);
 
 	return netlbl_mgmt_add_common(info, &audit_info);
 }
@@ -576,7 +577,7 @@ static int netlbl_mgmt_removedef(struct sk_buff *skb, struct genl_info *info)
 {
 	struct netlbl_audit audit_info;
 
-	netlbl_netlink_auditinfo(skb, &audit_info);
+	netlbl_netlink_auditinfo(&audit_info);
 
 	return netlbl_domhsh_remove_default(AF_UNSPEC, &audit_info);
 }
diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c
index 3e6ac9b790b1..2483df0bbd7c 100644
--- a/net/netlabel/netlabel_unlabeled.c
+++ b/net/netlabel/netlabel_unlabeled.c
@@ -814,7 +814,7 @@ static int netlbl_unlabel_accept(struct sk_buff *skb, struct genl_info *info)
 	if (info->attrs[NLBL_UNLABEL_A_ACPTFLG]) {
 		value = nla_get_u8(info->attrs[NLBL_UNLABEL_A_ACPTFLG]);
 		if (value == 1 || value == 0) {
-			netlbl_netlink_auditinfo(skb, &audit_info);
+			netlbl_netlink_auditinfo(&audit_info);
 			netlbl_unlabel_acceptflg_set(value, &audit_info);
 			return 0;
 		}
@@ -897,7 +897,7 @@ static int netlbl_unlabel_staticadd(struct sk_buff *skb,
 	       !info->attrs[NLBL_UNLABEL_A_IPV6MASK])))
 		return -EINVAL;
 
-	netlbl_netlink_auditinfo(skb, &audit_info);
+	netlbl_netlink_auditinfo(&audit_info);
 
 	ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len);
 	if (ret_val != 0)
@@ -947,7 +947,7 @@ static int netlbl_unlabel_staticadddef(struct sk_buff *skb,
 	       !info->attrs[NLBL_UNLABEL_A_IPV6MASK])))
 		return -EINVAL;
 
-	netlbl_netlink_auditinfo(skb, &audit_info);
+	netlbl_netlink_auditinfo(&audit_info);
 
 	ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len);
 	if (ret_val != 0)
@@ -994,7 +994,7 @@ static int netlbl_unlabel_staticremove(struct sk_buff *skb,
 	       !info->attrs[NLBL_UNLABEL_A_IPV6MASK])))
 		return -EINVAL;
 
-	netlbl_netlink_auditinfo(skb, &audit_info);
+	netlbl_netlink_auditinfo(&audit_info);
 
 	ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len);
 	if (ret_val != 0)
@@ -1034,7 +1034,7 @@ static int netlbl_unlabel_staticremovedef(struct sk_buff *skb,
 	       !info->attrs[NLBL_UNLABEL_A_IPV6MASK])))
 		return -EINVAL;
 
-	netlbl_netlink_auditinfo(skb, &audit_info);
+	netlbl_netlink_auditinfo(&audit_info);
 
 	ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len);
 	if (ret_val != 0)
diff --git a/net/netlabel/netlabel_user.h b/net/netlabel/netlabel_user.h
index b9ba8112b3c5..6190cbf94bf0 100644
--- a/net/netlabel/netlabel_user.h
+++ b/net/netlabel/netlabel_user.h
@@ -28,11 +28,9 @@
 
 /**
  * netlbl_netlink_auditinfo - Fetch the audit information from a NETLINK msg
- * @skb: the packet
  * @audit_info: NetLabel audit information
  */
-static inline void netlbl_netlink_auditinfo(struct sk_buff *skb,
-					    struct netlbl_audit *audit_info)
+static inline void netlbl_netlink_auditinfo(struct netlbl_audit *audit_info)
 {
 	security_task_getsecid_subj(current, &audit_info->secid);
 	audit_info->loginuid = audit_get_loginuid(current);
diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c
index e02b9befce0b..3a89bd9b89fc 100644
--- a/net/nfc/hci/command.c
+++ b/net/nfc/hci/command.c
@@ -34,7 +34,7 @@ static int nfc_hci_execute_cmd_async(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
  * HCI command execution completion callback.
  * err will be a standard linux error (may be converted from HCI response)
  * skb contains the response data and must be disposed, or may be NULL if
- * an error occured
+ * an error occurred
  */
 static void nfc_hci_execute_cb(void *context, struct sk_buff *skb, int err)
 {
diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index 43811b5219b5..3481941be70b 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -705,7 +705,7 @@ static void hci_transceive_cb(void *context, struct sk_buff *skb, int err)
 		/*
 		 * TODO: Check RF Error indicator to make sure data is valid.
 		 * It seems that HCI cmd can complete without error, but data
-		 * can be invalid if an RF error occured? Ignore for now.
+		 * can be invalid if an RF error occurred? Ignore for now.
 		 */
 		if (err == 0)
 			skb_trim(skb, skb->len - 1); /* RF Err ind */
diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c
index c0c8fea3a186..1e3a90049da9 100644
--- a/net/nfc/hci/llc_shdlc.c
+++ b/net/nfc/hci/llc_shdlc.c
@@ -406,7 +406,7 @@ static void llc_shdlc_rcv_u_frame(struct llc_shdlc *shdlc,
 		case SHDLC_NEGOTIATING:
 		case SHDLC_CONNECTING:
 			/*
-			 * We sent RSET, but chip wants to negociate or we
+			 * We sent RSET, but chip wants to negotiate or we
 			 * got RSET before we managed to send out our.
 			 */
 			if (skb->len > 0)
diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c
index 96865142104f..d6732e5e8958 100644
--- a/net/nfc/nci/hci.c
+++ b/net/nfc/nci/hci.c
@@ -161,8 +161,6 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe,
 	*(u8 *)skb_push(skb, 1) = data_type;
 
 	do {
-		len = conn_info->max_pkt_payload_len;
-
 		/* If last packet add NCI_HFP_NO_CHAINING */
 		if (i + conn_info->max_pkt_payload_len -
 		    (skb->len + 1) >= data_len) {
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index cadb6a29b285..1b5eae57bc90 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -967,8 +967,7 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
 
 		/* Associate skb with specified zone. */
 		if (tmpl) {
-			if (skb_nfct(skb))
-				nf_conntrack_put(skb_nfct(skb));
+			nf_conntrack_put(skb_nfct(skb));
 			nf_conntrack_get(&tmpl->ct_general);
 			nf_ct_set(skb, tmpl, IP_CT_NEW);
 		}
@@ -1329,11 +1328,9 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
 
 int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key)
 {
-	if (skb_nfct(skb)) {
-		nf_conntrack_put(skb_nfct(skb));
-		nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
-		ovs_ct_fill_key(skb, key, false);
-	}
+	nf_conntrack_put(skb_nfct(skb));
+	nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
+	ovs_ct_fill_key(skb, key, false);
 
 	return 0;
 }
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 330ba68828e7..77b0cdab3810 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3934,12 +3934,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval,
 			return -EFAULT;
 
 		lock_sock(sk);
-		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
-			ret = -EBUSY;
-		} else {
+		if (!po->rx_ring.pg_vec && !po->tx_ring.pg_vec)
 			po->tp_tx_has_off = !!val;
-			ret = 0;
-		}
+
 		release_sock(sk);
 		return 0;
 	}
diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c
index 8d00dfe8139e..1990d496fcfc 100644
--- a/net/qrtr/ns.c
+++ b/net/qrtr/ns.c
@@ -775,8 +775,10 @@ int qrtr_ns_init(void)
 	}
 
 	qrtr_ns.workqueue = alloc_workqueue("qrtr_ns_handler", WQ_UNBOUND, 1);
-	if (!qrtr_ns.workqueue)
+	if (!qrtr_ns.workqueue) {
+		ret = -ENOMEM;
 		goto err_sock;
+	}
 
 	qrtr_ns.sock->sk->sk_data_ready = qrtr_ns_data_ready;
 
diff --git a/net/rds/ib_ring.c b/net/rds/ib_ring.c
index ff97e8eda858..006b2e441418 100644
--- a/net/rds/ib_ring.c
+++ b/net/rds/ib_ring.c
@@ -141,7 +141,7 @@ int rds_ib_ring_low(struct rds_ib_work_ring *ring)
 }
 
 /*
- * returns the oldest alloced ring entry.  This will be the next one
+ * returns the oldest allocated ring entry.  This will be the next one
  * freed.  This can't be called if there are none allocated.
  */
 u32 rds_ib_ring_oldest(struct rds_ib_work_ring *ring)
diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index 42c5ff1eda95..f4ee13da90c7 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -177,7 +177,7 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
 				goto out;
 			}
 			tc->t_tinc = tinc;
-			rdsdebug("alloced tinc %p\n", tinc);
+			rdsdebug("allocated tinc %p\n", tinc);
 			rds_inc_path_init(&tinc->ti_inc, cp,
 					  &cp->cp_conn->c_faddr);
 			tinc->ti_inc.i_rx_lat_trace[RDS_MSG_RX_HDR] =
diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c
index 3ce6d628cd75..19e929c7c38b 100644
--- a/net/rxrpc/local_event.c
+++ b/net/rxrpc/local_event.c
@@ -77,7 +77,7 @@ static void rxrpc_send_version_request(struct rxrpc_local *local,
 }
 
 /*
- * Process event packets targetted at a local endpoint.
+ * Process event packets targeted at a local endpoint.
  */
 void rxrpc_process_local_events(struct rxrpc_local *local)
 {
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index f6d5755d669e..d17a66aab8ee 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -381,7 +381,8 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
 	}
 	mutex_unlock(&idrinfo->lock);
 
-	if (nla_put_u32(skb, TCA_FCNT, n_i))
+	ret = nla_put_u32(skb, TCA_FCNT, n_i);
+	if (ret)
 		goto nla_put_failure;
 	nla_nest_end(skb, nest);
 
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 1cac3c6fbb49..71f2015c70ca 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -70,7 +70,7 @@ static int tcf_vlan_act(struct sk_buff *skb, const struct tc_action *a,
 		/* replace the vid */
 		tci = (tci & ~VLAN_VID_MASK) | p->tcfv_push_vid;
 		/* replace prio bits, if tcfv_push_prio specified */
-		if (p->tcfv_push_prio) {
+		if (p->tcfv_push_prio_exists) {
 			tci &= ~VLAN_PRIO_MASK;
 			tci |= p->tcfv_push_prio << VLAN_PRIO_SHIFT;
 		}
@@ -121,6 +121,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	struct tc_action_net *tn = net_generic(net, vlan_net_id);
 	struct nlattr *tb[TCA_VLAN_MAX + 1];
 	struct tcf_chain *goto_ch = NULL;
+	bool push_prio_exists = false;
 	struct tcf_vlan_params *p;
 	struct tc_vlan *parm;
 	struct tcf_vlan *v;
@@ -189,7 +190,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 			push_proto = htons(ETH_P_8021Q);
 		}
 
-		if (tb[TCA_VLAN_PUSH_VLAN_PRIORITY])
+		push_prio_exists = !!tb[TCA_VLAN_PUSH_VLAN_PRIORITY];
+		if (push_prio_exists)
 			push_prio = nla_get_u8(tb[TCA_VLAN_PUSH_VLAN_PRIORITY]);
 		break;
 	case TCA_VLAN_ACT_POP_ETH:
@@ -241,6 +243,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	p->tcfv_action = action;
 	p->tcfv_push_vid = push_vid;
 	p->tcfv_push_prio = push_prio;
+	p->tcfv_push_prio_exists = push_prio_exists || action == TCA_VLAN_ACT_PUSH;
 	p->tcfv_push_proto = push_proto;
 
 	if (action == TCA_VLAN_ACT_PUSH_ETH) {
@@ -304,8 +307,8 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
 	    (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, p->tcfv_push_vid) ||
 	     nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL,
 			  p->tcfv_push_proto) ||
-	     (nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY,
-					      p->tcfv_push_prio))))
+	     (p->tcfv_push_prio_exists &&
+	      nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY, p->tcfv_push_prio))))
 		goto nla_put_failure;
 
 	if (p->tcfv_action == TCA_VLAN_ACT_PUSH_ETH) {
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 279f9e2a2319..d73b5c5514a9 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1531,7 +1531,7 @@ static inline int __tcf_classify(struct sk_buff *skb,
 				 u32 *last_executed_chain)
 {
 #ifdef CONFIG_NET_CLS_ACT
-	const int max_reclassify_loop = 4;
+	const int max_reclassify_loop = 16;
 	const struct tcf_proto *first_tp;
 	int limit = 0;
 
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index d7869a984881..2e704c7a105a 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1531,14 +1531,13 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 						       &mask->basic.n_proto,
 						       TCA_FLOWER_UNSPEC,
 						       sizeof(key->basic.n_proto));
+					mask->basic.n_proto = cpu_to_be16(0);
 				} else {
 					key->basic.n_proto = ethertype;
-					mask->basic.n_proto = cpu_to_be16(~0);
 				}
 			}
 		} else {
 			key->basic.n_proto = ethertype;
-			mask->basic.n_proto = cpu_to_be16(~0);
 		}
 	}
 
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index 2e288f88ff02..27a4b6dbcf57 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -7,7 +7,7 @@
 
 /*
    Comparing to general packet classification problem,
-   RSVP needs only sevaral relatively simple rules:
+   RSVP needs only several relatively simple rules:
 
    * (dst, protocol) are always specified,
      so that we are able to hash them.
diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index f885bea5b452..4ce681361851 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -141,7 +141,7 @@ errout:
 EXPORT_SYMBOL(tcf_em_register);
 
 /**
- * tcf_em_unregister - unregster and extended match
+ * tcf_em_unregister - unregister and extended match
  *
  * @ops: ematch operations lookup table
  *
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index fc8b56bcabf3..e9c0afc8becc 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -540,6 +540,24 @@ void netif_carrier_off(struct net_device *dev)
 }
 EXPORT_SYMBOL(netif_carrier_off);
 
+/**
+ *	netif_carrier_event - report carrier state event
+ *	@dev: network device
+ *
+ * Device has detected a carrier event but the carrier state wasn't changed.
+ * Use in drivers when querying carrier state asynchronously, to avoid missing
+ * events (link flaps) if link recovers before it's queried.
+ */
+void netif_carrier_event(struct net_device *dev)
+{
+	if (dev->reg_state == NETREG_UNINITIALIZED)
+		return;
+	atomic_inc(&dev->carrier_up_count);
+	atomic_inc(&dev->carrier_down_count);
+	linkwatch_fire_event(dev);
+}
+EXPORT_SYMBOL_GPL(netif_carrier_event);
+
 /* "NOOP" scheduler: the best scheduler, recommended for all interfaces
    under all circumstances. It is difficult to invent anything faster or
    cheaper.
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index f4132dc25ac0..621dc6afde8f 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -6,7 +6,7 @@
  *
  *             991129: -  Bug fix with grio mode
  *		       - a better sing. AvgQ mode with Grio(WRED)
- *		       - A finer grained VQ dequeue based on sugestion
+ *		       - A finer grained VQ dequeue based on suggestion
  *		         from Ren Liu
  *		       - More error checks
  *
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 8827987ba903..5f7ac27a5264 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -52,7 +52,7 @@
 */
 
 static int htb_hysteresis __read_mostly = 0; /* whether to use mode hysteresis for speedup */
-#define HTB_VER 0x30011		/* major must be matched with number suplied by TC as version */
+#define HTB_VER 0x30011		/* major must be matched with number supplied by TC as version */
 
 #if HTB_VER >> 16 != TC_HTB_PROTOVER
 #error "Mismatched sch_htb.c and pkt_sch.h"
@@ -273,6 +273,9 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch,
 
 /**
  * htb_add_to_id_tree - adds class to the round robin list
+ * @root: the root of the tree
+ * @cl: the class to add
+ * @prio: the give prio in class
  *
  * Routine adds class to the list (actually tree) sorted by classid.
  * Make sure that class is not already on such list for given prio.
@@ -298,6 +301,9 @@ static void htb_add_to_id_tree(struct rb_root *root,
 
 /**
  * htb_add_to_wait_tree - adds class to the event queue with delay
+ * @q: the priority event queue
+ * @cl: the class to add
+ * @delay: delay in microseconds
  *
  * The class is added to priority event queue to indicate that class will
  * change its mode in cl->pq_key microseconds. Make sure that class is not
@@ -331,6 +337,7 @@ static void htb_add_to_wait_tree(struct htb_sched *q,
 
 /**
  * htb_next_rb_node - finds next node in binary tree
+ * @n: the current node in binary tree
  *
  * When we are past last key we return NULL.
  * Average complexity is 2 steps per call.
@@ -342,6 +349,9 @@ static inline void htb_next_rb_node(struct rb_node **n)
 
 /**
  * htb_add_class_to_row - add class to its row
+ * @q: the priority event queue
+ * @cl: the class to add
+ * @mask: the given priorities in class in bitmap
  *
  * The class is added to row at priorities marked in mask.
  * It does nothing if mask == 0.
@@ -371,6 +381,9 @@ static void htb_safe_rb_erase(struct rb_node *rb, struct rb_root *root)
 
 /**
  * htb_remove_class_from_row - removes class from its row
+ * @q: the priority event queue
+ * @cl: the class to add
+ * @mask: the given priorities in class in bitmap
  *
  * The class is removed from row at priorities marked in mask.
  * It does nothing if mask == 0.
@@ -398,6 +411,8 @@ static inline void htb_remove_class_from_row(struct htb_sched *q,
 
 /**
  * htb_activate_prios - creates active classe's feed chain
+ * @q: the priority event queue
+ * @cl: the class to activate
  *
  * The class is connected to ancestors and/or appropriate rows
  * for priorities it is participating on. cl->cmode must be new
@@ -433,6 +448,8 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl)
 
 /**
  * htb_deactivate_prios - remove class from feed chain
+ * @q: the priority event queue
+ * @cl: the class to deactivate
  *
  * cl->cmode must represent old mode (before deactivation). It does
  * nothing if cl->prio_activity == 0. Class is removed from all feed
@@ -493,6 +510,8 @@ static inline s64 htb_hiwater(const struct htb_class *cl)
 
 /**
  * htb_class_mode - computes and returns current class mode
+ * @cl: the target class
+ * @diff: diff time in microseconds
  *
  * It computes cl's mode at time cl->t_c+diff and returns it. If mode
  * is not HTB_CAN_SEND then cl->pq_key is updated to time difference
@@ -521,9 +540,12 @@ htb_class_mode(struct htb_class *cl, s64 *diff)
 
 /**
  * htb_change_class_mode - changes classe's mode
+ * @q: the priority event queue
+ * @cl: the target class
+ * @diff: diff time in microseconds
  *
  * This should be the only way how to change classe's mode under normal
- * cirsumstances. Routine will update feed lists linkage, change mode
+ * circumstances. Routine will update feed lists linkage, change mode
  * and add class to the wait event queue if appropriate. New mode should
  * be different from old one and cl->pq_key has to be valid if changing
  * to mode other than HTB_CAN_SEND (see htb_add_to_wait_tree).
@@ -553,6 +575,8 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff)
 
 /**
  * htb_activate - inserts leaf cl into appropriate active feeds
+ * @q: the priority event queue
+ * @cl: the target class
  *
  * Routine learns (new) priority of leaf and activates feed chain
  * for the prio. It can be called on already active leaf safely.
@@ -570,6 +594,8 @@ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl)
 
 /**
  * htb_deactivate - remove leaf cl from active feeds
+ * @q: the priority event queue
+ * @cl: the target class
  *
  * Make sure that leaf is active. In the other words it can't be called
  * with non-active leaf. It also removes class from the drop list.
@@ -649,6 +675,10 @@ static inline void htb_accnt_ctokens(struct htb_class *cl, int bytes, s64 diff)
 
 /**
  * htb_charge_class - charges amount "bytes" to leaf and ancestors
+ * @q: the priority event queue
+ * @cl: the class to start iterate
+ * @level: the minimum level to account
+ * @skb: the socket buffer
  *
  * Routine assumes that packet "bytes" long was dequeued from leaf cl
  * borrowing from "level". It accounts bytes to ceil leaky bucket for
@@ -698,6 +728,9 @@ static void htb_charge_class(struct htb_sched *q, struct htb_class *cl,
 
 /**
  * htb_do_events - make mode changes to classes at the level
+ * @q: the priority event queue
+ * @level: which wait_pq in 'q->hlevel'
+ * @start: start jiffies
  *
  * Scans event queue for pending events and applies them. Returns time of
  * next pending event (0 for no event in pq, q->now for too many events).
@@ -766,6 +799,8 @@ static struct rb_node *htb_id_find_next_upper(int prio, struct rb_node *n,
 
 /**
  * htb_lookup_leaf - returns next leaf class in DRR order
+ * @hprio: the current one
+ * @prio: which prio in class
  *
  * Find leaf where current feed pointers points to.
  */
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 5c91df52b8c2..66fe2b82af9a 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -114,9 +114,6 @@ static void taprio_free_sched_cb(struct rcu_head *head)
 	struct sched_gate_list *sched = container_of(head, struct sched_gate_list, rcu);
 	struct sched_entry *entry, *n;
 
-	if (!sched)
-		return;
-
 	list_for_each_entry_safe(entry, n, &sched->entries, list) {
 		list_del(&entry->list);
 		kfree(entry);
@@ -438,6 +435,11 @@ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	struct Qdisc *child;
 	int queue;
 
+	if (unlikely(FULL_OFFLOAD_IS_ENABLED(q->flags))) {
+		WARN_ONCE(1, "Trying to enqueue skb into the root of a taprio qdisc configured with full offload\n");
+		return qdisc_drop(skb, sch, to_free);
+	}
+
 	queue = skb_get_queue_mapping(skb);
 
 	child = q->qdiscs[queue];
@@ -529,23 +531,7 @@ static struct sk_buff *taprio_peek_soft(struct Qdisc *sch)
 
 static struct sk_buff *taprio_peek_offload(struct Qdisc *sch)
 {
-	struct taprio_sched *q = qdisc_priv(sch);
-	struct net_device *dev = qdisc_dev(sch);
-	struct sk_buff *skb;
-	int i;
-
-	for (i = 0; i < dev->num_tx_queues; i++) {
-		struct Qdisc *child = q->qdiscs[i];
-
-		if (unlikely(!child))
-			continue;
-
-		skb = child->ops->peek(child);
-		if (!skb)
-			continue;
-
-		return skb;
-	}
+	WARN_ONCE(1, "Trying to peek into the root of a taprio qdisc configured with full offload\n");
 
 	return NULL;
 }
@@ -654,27 +640,7 @@ done:
 
 static struct sk_buff *taprio_dequeue_offload(struct Qdisc *sch)
 {
-	struct taprio_sched *q = qdisc_priv(sch);
-	struct net_device *dev = qdisc_dev(sch);
-	struct sk_buff *skb;
-	int i;
-
-	for (i = 0; i < dev->num_tx_queues; i++) {
-		struct Qdisc *child = q->qdiscs[i];
-
-		if (unlikely(!child))
-			continue;
-
-		skb = child->ops->dequeue(child);
-		if (unlikely(!skb))
-			continue;
-
-		qdisc_bstats_update(sch, skb);
-		qdisc_qstats_backlog_dec(sch, skb);
-		sch->q.qlen--;
-
-		return skb;
-	}
+	WARN_ONCE(1, "Trying to dequeue from the root of a taprio qdisc configured with full offload\n");
 
 	return NULL;
 }
@@ -1759,6 +1725,37 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt,
 	return taprio_change(sch, opt, extack);
 }
 
+static void taprio_attach(struct Qdisc *sch)
+{
+	struct taprio_sched *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	unsigned int ntx;
+
+	/* Attach underlying qdisc */
+	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
+		struct Qdisc *qdisc = q->qdiscs[ntx];
+		struct Qdisc *old;
+
+		if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
+			qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
+			old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
+			if (ntx < dev->real_num_tx_queues)
+				qdisc_hash_add(qdisc, false);
+		} else {
+			old = dev_graft_qdisc(qdisc->dev_queue, sch);
+			qdisc_refcount_inc(sch);
+		}
+		if (old)
+			qdisc_put(old);
+	}
+
+	/* access to the child qdiscs is not needed in offload mode */
+	if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
+		kfree(q->qdiscs);
+		q->qdiscs = NULL;
+	}
+}
+
 static struct netdev_queue *taprio_queue_get(struct Qdisc *sch,
 					     unsigned long cl)
 {
@@ -1785,8 +1782,12 @@ static int taprio_graft(struct Qdisc *sch, unsigned long cl,
 	if (dev->flags & IFF_UP)
 		dev_deactivate(dev);
 
-	*old = q->qdiscs[cl - 1];
-	q->qdiscs[cl - 1] = new;
+	if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
+		*old = dev_graft_qdisc(dev_queue, new);
+	} else {
+		*old = q->qdiscs[cl - 1];
+		q->qdiscs[cl - 1] = new;
+	}
 
 	if (new)
 		new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
@@ -2020,6 +2021,7 @@ static struct Qdisc_ops taprio_qdisc_ops __read_mostly = {
 	.change		= taprio_change,
 	.destroy	= taprio_destroy,
 	.reset		= taprio_reset,
+	.attach		= taprio_attach,
 	.peek		= taprio_peek,
 	.dequeue	= taprio_dequeue,
 	.enqueue	= taprio_enqueue,
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 6f2bbfeec3a4..baa4e770e4ba 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1171,7 +1171,6 @@ static const struct net_protocol sctp_protocol = {
 	.handler     = sctp4_rcv,
 	.err_handler = sctp_v4_err,
 	.no_policy   = 1,
-	.netns_ok    = 1,
 	.icmp_strict_tag_validation = 1,
 };
 
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index fd1e319eda00..4f30388a0dd0 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -361,7 +361,7 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net,
 
 	/* If the INIT is coming toward a closing socket, we'll send back
 	 * and ABORT.  Essentially, this catches the race of INIT being
-	 * backloged to the socket at the same time as the user isses close().
+	 * backloged to the socket at the same time as the user issues close().
 	 * Since the socket and all its associations are going away, we
 	 * can treat this OOTB
 	 */
@@ -608,8 +608,8 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net,
 	sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
 			SCTP_STATE(SCTP_STATE_COOKIE_ECHOED));
 
-	/* SCTP-AUTH: genereate the assocition shared keys so that
-	 * we can potentially signe the COOKIE-ECHO.
+	/* SCTP-AUTH: generate the association shared keys so that
+	 * we can potentially sign the COOKIE-ECHO.
 	 */
 	sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_SHKEY, SCTP_NULL());
 
@@ -787,7 +787,7 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
 		goto nomem_init;
 
 	/* SCTP-AUTH:  Now that we've populate required fields in
-	 * sctp_process_init, set up the assocaition shared keys as
+	 * sctp_process_init, set up the association shared keys as
 	 * necessary so that we can potentially authenticate the ACK
 	 */
 	error = sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC);
@@ -838,7 +838,7 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
 
 	/* Add all the state machine commands now since we've created
 	 * everything.  This way we don't introduce memory corruptions
-	 * during side-effect processing and correclty count established
+	 * during side-effect processing and correctly count established
 	 * associations.
 	 */
 	sctp_add_cmd_sf(commands, SCTP_CMD_NEW_ASOC, SCTP_ASOC(new_asoc));
@@ -923,7 +923,7 @@ enum sctp_disposition sctp_sf_do_5_1E_ca(struct net *net,
 						  commands);
 
 	/* Reset init error count upon receipt of COOKIE-ACK,
-	 * to avoid problems with the managemement of this
+	 * to avoid problems with the management of this
 	 * counter in stale cookie situations when a transition back
 	 * from the COOKIE-ECHOED state to the COOKIE-WAIT
 	 * state is performed.
@@ -2950,7 +2950,7 @@ enum sctp_disposition sctp_sf_do_9_2_reshutack(
 						  commands);
 
 	/* Since we are not going to really process this INIT, there
-	 * is no point in verifying chunk boundries.  Just generate
+	 * is no point in verifying chunk boundaries.  Just generate
 	 * the SHUTDOWN ACK.
 	 */
 	reply = sctp_make_shutdown_ack(asoc, chunk);
@@ -3560,7 +3560,7 @@ enum sctp_disposition sctp_sf_do_9_2_final(struct net *net,
 		goto nomem_chunk;
 
 	/* Do all the commands now (after allocation), so that we
-	 * have consistent state if memory allocation failes
+	 * have consistent state if memory allocation fails
 	 */
 	sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev));
 
@@ -3747,7 +3747,7 @@ static enum sctp_disposition sctp_sf_shut_8_4_5(
 		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
 
 	/* We need to discard the rest of the packet to prevent
-	 * potential bomming attacks from additional bundled chunks.
+	 * potential boomming attacks from additional bundled chunks.
 	 * This is documented in SCTP Threats ID.
 	 */
 	return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -4257,7 +4257,7 @@ gen_shutdown:
 }
 
 /*
- * SCTP-AUTH Section 6.3 Receiving authenticated chukns
+ * SCTP-AUTH Section 6.3 Receiving authenticated chunks
  *
  *    The receiver MUST use the HMAC algorithm indicated in the HMAC
  *    Identifier field.  If this algorithm was not specified by the
@@ -4812,7 +4812,7 @@ static enum sctp_disposition sctp_sf_violation_ctsn(
 
 /* Handle protocol violation of an invalid chunk bundling.  For example,
  * when we have an association and we receive bundled INIT-ACK, or
- * SHUDOWN-COMPLETE, our peer is clearly violationg the "MUST NOT bundle"
+ * SHUTDOWN-COMPLETE, our peer is clearly violating the "MUST NOT bundle"
  * statement from the specs.  Additionally, there might be an attacker
  * on the path and we may not want to continue this communication.
  */
@@ -5208,7 +5208,7 @@ enum sctp_disposition sctp_sf_cookie_wait_prm_shutdown(
  * Inputs
  * (endpoint, asoc)
  *
- * The RFC does not explcitly address this issue, but is the route through the
+ * The RFC does not explicitly address this issue, but is the route through the
  * state table when someone issues a shutdown while in COOKIE_ECHOED state.
  *
  * Outputs
@@ -5932,7 +5932,7 @@ enum sctp_disposition sctp_sf_t1_cookie_timer_expire(
 /* RFC2960 9.2 If the timer expires, the endpoint must re-send the SHUTDOWN
  * with the updated last sequential TSN received from its peer.
  *
- * An endpoint should limit the number of retransmissions of the
+ * An endpoint should limit the number of retransmission of the
  * SHUTDOWN chunk to the protocol parameter 'Association.Max.Retrans'.
  * If this threshold is exceeded the endpoint should destroy the TCB and
  * MUST report the peer endpoint unreachable to the upper layer (and
@@ -6010,7 +6010,7 @@ nomem:
 }
 
 /*
- * ADDIP Section 4.1 ASCONF CHunk Procedures
+ * ADDIP Section 4.1 ASCONF Chunk Procedures
  * If the T4 RTO timer expires the endpoint should do B1 to B5
  */
 enum sctp_disposition sctp_sf_t4_timer_expire(
@@ -6441,7 +6441,7 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 		chunk->ecn_ce_done = 1;
 
 		if (af->is_ce(sctp_gso_headskb(chunk->skb))) {
-			/* Do real work as sideffect. */
+			/* Do real work as side effect. */
 			sctp_add_cmd_sf(commands, SCTP_CMD_ECN_CE,
 					SCTP_U32(tsn));
 		}
diff --git a/net/smc/Makefile b/net/smc/Makefile
index 77e54fe42b1c..99a0186cba5b 100644
--- a/net/smc/Makefile
+++ b/net/smc/Makefile
@@ -2,4 +2,4 @@
 obj-$(CONFIG_SMC)	+= smc.o
 obj-$(CONFIG_SMC_DIAG)	+= smc_diag.o
 smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o
-smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o
+smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o smc_stats.o
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 5eff7cccceff..e41fdac606d4 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -49,6 +49,7 @@
 #include "smc_tx.h"
 #include "smc_rx.h"
 #include "smc_close.h"
+#include "smc_stats.h"
 
 static DEFINE_MUTEX(smc_server_lgr_pending);	/* serialize link group
 						 * creation on server
@@ -508,9 +509,44 @@ static void smc_link_save_peer_info(struct smc_link *link,
 	link->peer_mtu = clc->r0.qp_mtu;
 }
 
-static void smc_switch_to_fallback(struct smc_sock *smc)
+static void smc_stat_inc_fback_rsn_cnt(struct smc_sock *smc,
+				       struct smc_stats_fback *fback_arr)
+{
+	int cnt;
+
+	for (cnt = 0; cnt < SMC_MAX_FBACK_RSN_CNT; cnt++) {
+		if (fback_arr[cnt].fback_code == smc->fallback_rsn) {
+			fback_arr[cnt].count++;
+			break;
+		}
+		if (!fback_arr[cnt].fback_code) {
+			fback_arr[cnt].fback_code = smc->fallback_rsn;
+			fback_arr[cnt].count++;
+			break;
+		}
+	}
+}
+
+static void smc_stat_fallback(struct smc_sock *smc)
+{
+	struct net *net = sock_net(&smc->sk);
+
+	mutex_lock(&net->smc.mutex_fback_rsn);
+	if (smc->listen_smc) {
+		smc_stat_inc_fback_rsn_cnt(smc, net->smc.fback_rsn->srv);
+		net->smc.fback_rsn->srv_fback_cnt++;
+	} else {
+		smc_stat_inc_fback_rsn_cnt(smc, net->smc.fback_rsn->clnt);
+		net->smc.fback_rsn->clnt_fback_cnt++;
+	}
+	mutex_unlock(&net->smc.mutex_fback_rsn);
+}
+
+static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
 {
 	smc->use_fallback = true;
+	smc->fallback_rsn = reason_code;
+	smc_stat_fallback(smc);
 	if (smc->sk.sk_socket && smc->sk.sk_socket->file) {
 		smc->clcsock->file = smc->sk.sk_socket->file;
 		smc->clcsock->file->private_data = smc->clcsock;
@@ -522,8 +558,7 @@ static void smc_switch_to_fallback(struct smc_sock *smc)
 /* fall back during connect */
 static int smc_connect_fallback(struct smc_sock *smc, int reason_code)
 {
-	smc_switch_to_fallback(smc);
-	smc->fallback_rsn = reason_code;
+	smc_switch_to_fallback(smc, reason_code);
 	smc_copy_sock_settings_to_clc(smc);
 	smc->connect_nonblock = 0;
 	if (smc->sk.sk_state == SMC_INIT)
@@ -535,9 +570,11 @@ static int smc_connect_fallback(struct smc_sock *smc, int reason_code)
 static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code,
 					u8 version)
 {
+	struct net *net = sock_net(&smc->sk);
 	int rc;
 
 	if (reason_code < 0) { /* error, fallback is not possible */
+		this_cpu_inc(net->smc.smc_stats->clnt_hshake_err_cnt);
 		if (smc->sk.sk_state == SMC_INIT)
 			sock_put(&smc->sk); /* passive closing */
 		return reason_code;
@@ -545,6 +582,7 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code,
 	if (reason_code != SMC_CLC_DECL_PEERDECL) {
 		rc = smc_clc_send_decline(smc, reason_code, version);
 		if (rc < 0) {
+			this_cpu_inc(net->smc.smc_stats->clnt_hshake_err_cnt);
 			if (smc->sk.sk_state == SMC_INIT)
 				sock_put(&smc->sk); /* passive closing */
 			return rc;
@@ -992,6 +1030,7 @@ static int __smc_connect(struct smc_sock *smc)
 	if (rc)
 		goto vlan_cleanup;
 
+	SMC_STAT_CLNT_SUCC_INC(sock_net(smc->clcsock->sk), aclc);
 	smc_connect_ism_vlan_cleanup(smc, ini);
 	kfree(buf);
 	kfree(ini);
@@ -1307,7 +1346,9 @@ static void smc_listen_out_connected(struct smc_sock *new_smc)
 static void smc_listen_out_err(struct smc_sock *new_smc)
 {
 	struct sock *newsmcsk = &new_smc->sk;
+	struct net *net = sock_net(newsmcsk);
 
+	this_cpu_inc(net->smc.smc_stats->srv_hshake_err_cnt);
 	if (newsmcsk->sk_state == SMC_INIT)
 		sock_put(&new_smc->sk); /* passive closing */
 	newsmcsk->sk_state = SMC_CLOSED;
@@ -1325,8 +1366,7 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
 		smc_listen_out_err(new_smc);
 		return;
 	}
-	smc_switch_to_fallback(new_smc);
-	new_smc->fallback_rsn = reason_code;
+	smc_switch_to_fallback(new_smc, reason_code);
 	if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) {
 		if (smc_clc_send_decline(new_smc, reason_code, version) < 0) {
 			smc_listen_out_err(new_smc);
@@ -1699,8 +1739,7 @@ static void smc_listen_work(struct work_struct *work)
 
 	/* check if peer is smc capable */
 	if (!tcp_sk(newclcsock->sk)->syn_smc) {
-		smc_switch_to_fallback(new_smc);
-		new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC;
+		smc_switch_to_fallback(new_smc, SMC_CLC_DECL_PEERNOSMC);
 		smc_listen_out_connected(new_smc);
 		return;
 	}
@@ -1778,6 +1817,7 @@ static void smc_listen_work(struct work_struct *work)
 	}
 	smc_conn_save_peer_info(new_smc, cclc);
 	smc_listen_out_connected(new_smc);
+	SMC_STAT_SERV_SUCC_INC(sock_net(newclcsock->sk), ini);
 	goto out_free;
 
 out_unlock:
@@ -1984,18 +2024,19 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 
 	if (msg->msg_flags & MSG_FASTOPEN) {
 		if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) {
-			smc_switch_to_fallback(smc);
-			smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
+			smc_switch_to_fallback(smc, SMC_CLC_DECL_OPTUNSUPP);
 		} else {
 			rc = -EINVAL;
 			goto out;
 		}
 	}
 
-	if (smc->use_fallback)
+	if (smc->use_fallback) {
 		rc = smc->clcsock->ops->sendmsg(smc->clcsock, msg, len);
-	else
+	} else {
 		rc = smc_tx_sendmsg(smc, msg, len);
+		SMC_STAT_TX_PAYLOAD(smc, len, rc);
+	}
 out:
 	release_sock(sk);
 	return rc;
@@ -2030,6 +2071,7 @@ static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	} else {
 		msg->msg_namelen = 0;
 		rc = smc_rx_recvmsg(smc, msg, NULL, len, flags);
+		SMC_STAT_RX_PAYLOAD(smc, rc, rc);
 	}
 
 out:
@@ -2194,8 +2236,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 	case TCP_FASTOPEN_NO_COOKIE:
 		/* option not supported by SMC */
 		if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) {
-			smc_switch_to_fallback(smc);
-			smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
+			smc_switch_to_fallback(smc, SMC_CLC_DECL_OPTUNSUPP);
 		} else {
 			rc = -EINVAL;
 		}
@@ -2204,18 +2245,22 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 		if (sk->sk_state != SMC_INIT &&
 		    sk->sk_state != SMC_LISTEN &&
 		    sk->sk_state != SMC_CLOSED) {
-			if (val)
+			if (val) {
+				SMC_STAT_INC(smc, ndly_cnt);
 				mod_delayed_work(smc->conn.lgr->tx_wq,
 						 &smc->conn.tx_work, 0);
+			}
 		}
 		break;
 	case TCP_CORK:
 		if (sk->sk_state != SMC_INIT &&
 		    sk->sk_state != SMC_LISTEN &&
 		    sk->sk_state != SMC_CLOSED) {
-			if (!val)
+			if (!val) {
+				SMC_STAT_INC(smc, cork_cnt);
 				mod_delayed_work(smc->conn.lgr->tx_wq,
 						 &smc->conn.tx_work, 0);
+			}
 		}
 		break;
 	case TCP_DEFER_ACCEPT:
@@ -2338,11 +2383,13 @@ static ssize_t smc_sendpage(struct socket *sock, struct page *page,
 		goto out;
 	}
 	release_sock(sk);
-	if (smc->use_fallback)
+	if (smc->use_fallback) {
 		rc = kernel_sendpage(smc->clcsock, page, offset,
 				     size, flags);
-	else
+	} else {
+		SMC_STAT_INC(smc, sendpage_cnt);
 		rc = sock_no_sendpage(sock, page, offset, size, flags);
+	}
 
 out:
 	return rc;
@@ -2391,6 +2438,7 @@ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos,
 			flags = MSG_DONTWAIT;
 		else
 			flags = 0;
+		SMC_STAT_INC(smc, splice_cnt);
 		rc = smc_rx_recvmsg(smc, NULL, pipe, len, flags);
 	}
 out:
@@ -2479,6 +2527,16 @@ static void __net_exit smc_net_exit(struct net *net)
 	smc_pnet_net_exit(net);
 }
 
+static __net_init int smc_net_stat_init(struct net *net)
+{
+	return smc_stats_init(net);
+}
+
+static void __net_exit smc_net_stat_exit(struct net *net)
+{
+	smc_stats_exit(net);
+}
+
 static struct pernet_operations smc_net_ops = {
 	.init = smc_net_init,
 	.exit = smc_net_exit,
@@ -2486,6 +2544,11 @@ static struct pernet_operations smc_net_ops = {
 	.size = sizeof(struct smc_net),
 };
 
+static struct pernet_operations smc_net_stat_ops = {
+	.init = smc_net_stat_init,
+	.exit = smc_net_stat_exit,
+};
+
 static int __init smc_init(void)
 {
 	int rc;
@@ -2494,6 +2557,10 @@ static int __init smc_init(void)
 	if (rc)
 		return rc;
 
+	rc = register_pernet_subsys(&smc_net_stat_ops);
+	if (rc)
+		return rc;
+
 	smc_ism_init();
 	smc_clc_init();
 
@@ -2595,6 +2662,7 @@ static void __exit smc_exit(void)
 	proto_unregister(&smc_proto);
 	smc_pnet_exit();
 	smc_nl_exit();
+	unregister_pernet_subsys(&smc_net_stat_ops);
 	unregister_pernet_subsys(&smc_net_ops);
 	rcu_barrier();
 }
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 0df85a12651e..cd0d7c908b2a 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -33,6 +33,7 @@
 #include "smc_close.h"
 #include "smc_ism.h"
 #include "smc_netlink.h"
+#include "smc_stats.h"
 
 #define SMC_LGR_NUM_INCR		256
 #define SMC_LGR_FREE_DELAY_SERV		(600 * HZ)
@@ -1235,20 +1236,6 @@ static void smc_lgr_free(struct smc_link_group *lgr)
 	kfree(lgr);
 }
 
-static void smcd_unregister_all_dmbs(struct smc_link_group *lgr)
-{
-	int i;
-
-	for (i = 0; i < SMC_RMBE_SIZES; i++) {
-		struct smc_buf_desc *buf_desc;
-
-		list_for_each_entry(buf_desc, &lgr->rmbs[i], list) {
-			buf_desc->len += sizeof(struct smcd_cdc_msg);
-			smc_ism_unregister_dmb(lgr->smcd, buf_desc);
-		}
-	}
-}
-
 static void smc_sk_wake_ups(struct smc_sock *smc)
 {
 	smc->sk.sk_write_space(&smc->sk);
@@ -1285,7 +1272,6 @@ static void smc_lgr_cleanup(struct smc_link_group *lgr)
 {
 	if (lgr->is_smcd) {
 		smc_ism_signal_shutdown(lgr);
-		smcd_unregister_all_dmbs(lgr);
 	} else {
 		u32 rsn = lgr->llc_termination_rsn;
 
@@ -2044,6 +2030,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 	struct smc_link_group *lgr = conn->lgr;
 	struct list_head *buf_list;
 	int bufsize, bufsize_short;
+	bool is_dgraded = false;
 	struct mutex *lock;	/* lock buffer list */
 	int sk_buf_size;
 
@@ -2071,6 +2058,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 		/* check for reusable slot in the link group */
 		buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list);
 		if (buf_desc) {
+			SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize);
+			SMC_STAT_BUF_REUSE(smc, is_smcd, is_rmb);
 			memset(buf_desc->cpu_addr, 0, bufsize);
 			break; /* found reusable slot */
 		}
@@ -2082,9 +2071,16 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 
 		if (PTR_ERR(buf_desc) == -ENOMEM)
 			break;
-		if (IS_ERR(buf_desc))
+		if (IS_ERR(buf_desc)) {
+			if (!is_dgraded) {
+				is_dgraded = true;
+				SMC_STAT_RMB_DOWNGRADED(smc, is_smcd, is_rmb);
+			}
 			continue;
+		}
 
+		SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb);
+		SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize);
 		buf_desc->used = 1;
 		mutex_lock(lock);
 		list_add(&buf_desc->list, buf_list);
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index 967712ba52a0..9cb2df289963 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -470,7 +470,6 @@ void smcd_unregister_dev(struct smcd_dev *smcd)
 	mutex_unlock(&smcd_dev_list.mutex);
 	smcd->going_away = 1;
 	smc_smcd_terminate_all(smcd);
-	flush_workqueue(smcd->event_wq);
 	destroy_workqueue(smcd->event_wq);
 
 	device_del(&smcd->dev);
diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c
index 140419a19dbf..6fb6f96c1d17 100644
--- a/net/smc/smc_netlink.c
+++ b/net/smc/smc_netlink.c
@@ -19,6 +19,7 @@
 #include "smc_core.h"
 #include "smc_ism.h"
 #include "smc_ib.h"
+#include "smc_stats.h"
 #include "smc_netlink.h"
 
 #define SMC_CMD_MAX_ATTR 1
@@ -55,6 +56,16 @@ static const struct genl_ops smc_gen_nl_ops[] = {
 		/* can be retrieved by unprivileged users */
 		.dumpit = smcr_nl_get_device,
 	},
+	{
+		.cmd = SMC_NETLINK_GET_STATS,
+		/* can be retrieved by unprivileged users */
+		.dumpit = smc_nl_get_stats,
+	},
+	{
+		.cmd = SMC_NETLINK_GET_FBACK_STATS,
+		/* can be retrieved by unprivileged users */
+		.dumpit = smc_nl_get_fback_stats,
+	},
 };
 
 static const struct nla_policy smc_gen_nl_policy[2] = {
diff --git a/net/smc/smc_netlink.h b/net/smc/smc_netlink.h
index 3477265cba6c..5ce2c0a89ccd 100644
--- a/net/smc/smc_netlink.h
+++ b/net/smc/smc_netlink.h
@@ -18,7 +18,7 @@
 extern struct genl_family smc_gen_nl_family;
 
 struct smc_nl_dmp_ctx {
-	int pos[2];
+	int pos[3];
 };
 
 static inline struct smc_nl_dmp_ctx *smc_nl_dmp_ctx(struct netlink_callback *c)
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index fcfac59f8b72..170b733bc736 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -21,6 +21,7 @@
 #include "smc_cdc.h"
 #include "smc_tx.h" /* smc_tx_consumer_update() */
 #include "smc_rx.h"
+#include "smc_stats.h"
 
 /* callback implementation to wakeup consumers blocked with smc_rx_wait().
  * indirectly called by smc_cdc_msg_recv_action().
@@ -227,6 +228,7 @@ static int smc_rx_recv_urg(struct smc_sock *smc, struct msghdr *msg, int len,
 	    conn->urg_state == SMC_URG_READ)
 		return -EINVAL;
 
+	SMC_STAT_INC(smc, urg_data_cnt);
 	if (conn->urg_state == SMC_URG_VALID) {
 		if (!(flags & MSG_PEEK))
 			smc->conn.urg_state = SMC_URG_READ;
@@ -303,6 +305,12 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
 	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
 
+	readable = atomic_read(&conn->bytes_to_rcv);
+	if (readable >= conn->rmb_desc->len)
+		SMC_STAT_RMB_RX_FULL(smc, !conn->lnk);
+
+	if (len < readable)
+		SMC_STAT_RMB_RX_SIZE_SMALL(smc, !conn->lnk);
 	/* we currently use 1 RMBE per RMB, so RMBE == RMB base addr */
 	rcvbuf_base = conn->rx_off + conn->rmb_desc->cpu_addr;
 
diff --git a/net/smc/smc_stats.c b/net/smc/smc_stats.c
new file mode 100644
index 000000000000..614013e3b574
--- /dev/null
+++ b/net/smc/smc_stats.c
@@ -0,0 +1,413 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * SMC statistics netlink routines
+ *
+ * Copyright IBM Corp. 2021
+ *
+ * Author(s):  Guvenc Gulce
+ */
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/percpu.h>
+#include <linux/ctype.h>
+#include <linux/smc.h>
+#include <net/genetlink.h>
+#include <net/sock.h>
+#include "smc_netlink.h"
+#include "smc_stats.h"
+
+int smc_stats_init(struct net *net)
+{
+	net->smc.fback_rsn = kzalloc(sizeof(*net->smc.fback_rsn), GFP_KERNEL);
+	if (!net->smc.fback_rsn)
+		goto err_fback;
+	net->smc.smc_stats = alloc_percpu(struct smc_stats);
+	if (!net->smc.smc_stats)
+		goto err_stats;
+	mutex_init(&net->smc.mutex_fback_rsn);
+	return 0;
+
+err_stats:
+	kfree(net->smc.fback_rsn);
+err_fback:
+	return -ENOMEM;
+}
+
+void smc_stats_exit(struct net *net)
+{
+	kfree(net->smc.fback_rsn);
+	if (net->smc.smc_stats)
+		free_percpu(net->smc.smc_stats);
+}
+
+static int smc_nl_fill_stats_rmb_data(struct sk_buff *skb,
+				      struct smc_stats *stats, int tech,
+				      int type)
+{
+	struct smc_stats_rmbcnt *stats_rmb_cnt;
+	struct nlattr *attrs;
+
+	if (type == SMC_NLA_STATS_T_TX_RMB_STATS)
+		stats_rmb_cnt = &stats->smc[tech].rmb_tx;
+	else
+		stats_rmb_cnt = &stats->smc[tech].rmb_rx;
+
+	attrs = nla_nest_start(skb, type);
+	if (!attrs)
+		goto errout;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_REUSE_CNT,
+			      stats_rmb_cnt->reuse_cnt,
+			      SMC_NLA_STATS_RMB_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_SIZE_SM_PEER_CNT,
+			      stats_rmb_cnt->buf_size_small_peer_cnt,
+			      SMC_NLA_STATS_RMB_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_SIZE_SM_CNT,
+			      stats_rmb_cnt->buf_size_small_cnt,
+			      SMC_NLA_STATS_RMB_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_FULL_PEER_CNT,
+			      stats_rmb_cnt->buf_full_peer_cnt,
+			      SMC_NLA_STATS_RMB_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_FULL_CNT,
+			      stats_rmb_cnt->buf_full_cnt,
+			      SMC_NLA_STATS_RMB_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_ALLOC_CNT,
+			      stats_rmb_cnt->alloc_cnt,
+			      SMC_NLA_STATS_RMB_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_DGRADE_CNT,
+			      stats_rmb_cnt->dgrade_cnt,
+			      SMC_NLA_STATS_RMB_PAD))
+		goto errattr;
+
+	nla_nest_end(skb, attrs);
+	return 0;
+
+errattr:
+	nla_nest_cancel(skb, attrs);
+errout:
+	return -EMSGSIZE;
+}
+
+static int smc_nl_fill_stats_bufsize_data(struct sk_buff *skb,
+					  struct smc_stats *stats, int tech,
+					  int type)
+{
+	struct smc_stats_memsize *stats_pload;
+	struct nlattr *attrs;
+
+	if (type == SMC_NLA_STATS_T_TXPLOAD_SIZE)
+		stats_pload = &stats->smc[tech].tx_pd;
+	else if (type == SMC_NLA_STATS_T_RXPLOAD_SIZE)
+		stats_pload = &stats->smc[tech].rx_pd;
+	else if (type == SMC_NLA_STATS_T_TX_RMB_SIZE)
+		stats_pload = &stats->smc[tech].tx_rmbsize;
+	else if (type == SMC_NLA_STATS_T_RX_RMB_SIZE)
+		stats_pload = &stats->smc[tech].rx_rmbsize;
+	else
+		goto errout;
+
+	attrs = nla_nest_start(skb, type);
+	if (!attrs)
+		goto errout;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_8K,
+			      stats_pload->buf[SMC_BUF_8K],
+			      SMC_NLA_STATS_PLOAD_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_16K,
+			      stats_pload->buf[SMC_BUF_16K],
+			      SMC_NLA_STATS_PLOAD_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_32K,
+			      stats_pload->buf[SMC_BUF_32K],
+			      SMC_NLA_STATS_PLOAD_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_64K,
+			      stats_pload->buf[SMC_BUF_64K],
+			      SMC_NLA_STATS_PLOAD_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_128K,
+			      stats_pload->buf[SMC_BUF_128K],
+			      SMC_NLA_STATS_PLOAD_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_256K,
+			      stats_pload->buf[SMC_BUF_256K],
+			      SMC_NLA_STATS_PLOAD_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_512K,
+			      stats_pload->buf[SMC_BUF_512K],
+			      SMC_NLA_STATS_PLOAD_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_1024K,
+			      stats_pload->buf[SMC_BUF_1024K],
+			      SMC_NLA_STATS_PLOAD_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_G_1024K,
+			      stats_pload->buf[SMC_BUF_G_1024K],
+			      SMC_NLA_STATS_PLOAD_PAD))
+		goto errattr;
+
+	nla_nest_end(skb, attrs);
+	return 0;
+
+errattr:
+	nla_nest_cancel(skb, attrs);
+errout:
+	return -EMSGSIZE;
+}
+
+static int smc_nl_fill_stats_tech_data(struct sk_buff *skb,
+				       struct smc_stats *stats, int tech)
+{
+	struct smc_stats_tech *smc_tech;
+	struct nlattr *attrs;
+
+	smc_tech = &stats->smc[tech];
+	if (tech == SMC_TYPE_D)
+		attrs = nla_nest_start(skb, SMC_NLA_STATS_SMCD_TECH);
+	else
+		attrs = nla_nest_start(skb, SMC_NLA_STATS_SMCR_TECH);
+
+	if (!attrs)
+		goto errout;
+	if (smc_nl_fill_stats_rmb_data(skb, stats, tech,
+				       SMC_NLA_STATS_T_TX_RMB_STATS))
+		goto errattr;
+	if (smc_nl_fill_stats_rmb_data(skb, stats, tech,
+				       SMC_NLA_STATS_T_RX_RMB_STATS))
+		goto errattr;
+	if (smc_nl_fill_stats_bufsize_data(skb, stats, tech,
+					   SMC_NLA_STATS_T_TXPLOAD_SIZE))
+		goto errattr;
+	if (smc_nl_fill_stats_bufsize_data(skb, stats, tech,
+					   SMC_NLA_STATS_T_RXPLOAD_SIZE))
+		goto errattr;
+	if (smc_nl_fill_stats_bufsize_data(skb, stats, tech,
+					   SMC_NLA_STATS_T_TX_RMB_SIZE))
+		goto errattr;
+	if (smc_nl_fill_stats_bufsize_data(skb, stats, tech,
+					   SMC_NLA_STATS_T_RX_RMB_SIZE))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CLNT_V1_SUCC,
+			      smc_tech->clnt_v1_succ_cnt,
+			      SMC_NLA_STATS_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CLNT_V2_SUCC,
+			      smc_tech->clnt_v2_succ_cnt,
+			      SMC_NLA_STATS_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SRV_V1_SUCC,
+			      smc_tech->srv_v1_succ_cnt,
+			      SMC_NLA_STATS_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SRV_V2_SUCC,
+			      smc_tech->srv_v2_succ_cnt,
+			      SMC_NLA_STATS_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_RX_BYTES,
+			      smc_tech->rx_bytes,
+			      SMC_NLA_STATS_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_TX_BYTES,
+			      smc_tech->tx_bytes,
+			      SMC_NLA_STATS_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_RX_CNT,
+			      smc_tech->rx_cnt,
+			      SMC_NLA_STATS_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_TX_CNT,
+			      smc_tech->tx_cnt,
+			      SMC_NLA_STATS_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SENDPAGE_CNT,
+			      smc_tech->sendpage_cnt,
+			      SMC_NLA_STATS_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CORK_CNT,
+			      smc_tech->cork_cnt,
+			      SMC_NLA_STATS_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_NDLY_CNT,
+			      smc_tech->ndly_cnt,
+			      SMC_NLA_STATS_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SPLICE_CNT,
+			      smc_tech->splice_cnt,
+			      SMC_NLA_STATS_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_URG_DATA_CNT,
+			      smc_tech->urg_data_cnt,
+			      SMC_NLA_STATS_PAD))
+		goto errattr;
+
+	nla_nest_end(skb, attrs);
+	return 0;
+
+errattr:
+	nla_nest_cancel(skb, attrs);
+errout:
+	return -EMSGSIZE;
+}
+
+int smc_nl_get_stats(struct sk_buff *skb,
+		     struct netlink_callback *cb)
+{
+	struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+	struct net *net = sock_net(skb->sk);
+	struct smc_stats *stats;
+	struct nlattr *attrs;
+	int cpu, i, size;
+	void *nlh;
+	u64 *src;
+	u64 *sum;
+
+	if (cb_ctx->pos[0])
+		goto errmsg;
+	nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &smc_gen_nl_family, NLM_F_MULTI,
+			  SMC_NETLINK_GET_STATS);
+	if (!nlh)
+		goto errmsg;
+
+	attrs = nla_nest_start(skb, SMC_GEN_STATS);
+	if (!attrs)
+		goto errnest;
+	stats = kzalloc(sizeof(*stats), GFP_KERNEL);
+	if (!stats)
+		goto erralloc;
+	size = sizeof(*stats) / sizeof(u64);
+	for_each_possible_cpu(cpu) {
+		src = (u64 *)per_cpu_ptr(net->smc.smc_stats, cpu);
+		sum = (u64 *)stats;
+		for (i = 0; i < size; i++)
+			*(sum++) += *(src++);
+	}
+	if (smc_nl_fill_stats_tech_data(skb, stats, SMC_TYPE_D))
+		goto errattr;
+	if (smc_nl_fill_stats_tech_data(skb, stats, SMC_TYPE_R))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_CLNT_HS_ERR_CNT,
+			      stats->clnt_hshake_err_cnt,
+			      SMC_NLA_STATS_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_SRV_HS_ERR_CNT,
+			      stats->srv_hshake_err_cnt,
+			      SMC_NLA_STATS_PAD))
+		goto errattr;
+
+	nla_nest_end(skb, attrs);
+	genlmsg_end(skb, nlh);
+	cb_ctx->pos[0] = 1;
+	kfree(stats);
+	return skb->len;
+
+errattr:
+	kfree(stats);
+erralloc:
+	nla_nest_cancel(skb, attrs);
+errnest:
+	genlmsg_cancel(skb, nlh);
+errmsg:
+	return skb->len;
+}
+
+static int smc_nl_get_fback_details(struct sk_buff *skb,
+				    struct netlink_callback *cb, int pos,
+				    bool is_srv)
+{
+	struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+	struct net *net = sock_net(skb->sk);
+	int cnt_reported = cb_ctx->pos[2];
+	struct smc_stats_fback *trgt_arr;
+	struct nlattr *attrs;
+	int rc = 0;
+	void *nlh;
+
+	if (is_srv)
+		trgt_arr = &net->smc.fback_rsn->srv[0];
+	else
+		trgt_arr = &net->smc.fback_rsn->clnt[0];
+	if (!trgt_arr[pos].fback_code)
+		return -ENODATA;
+	nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &smc_gen_nl_family, NLM_F_MULTI,
+			  SMC_NETLINK_GET_FBACK_STATS);
+	if (!nlh)
+		goto errmsg;
+	attrs = nla_nest_start(skb, SMC_GEN_FBACK_STATS);
+	if (!attrs)
+		goto errout;
+	if (nla_put_u8(skb, SMC_NLA_FBACK_STATS_TYPE, is_srv))
+		goto errattr;
+	if (!cnt_reported) {
+		if (nla_put_u64_64bit(skb, SMC_NLA_FBACK_STATS_SRV_CNT,
+				      net->smc.fback_rsn->srv_fback_cnt,
+				      SMC_NLA_FBACK_STATS_PAD))
+			goto errattr;
+		if (nla_put_u64_64bit(skb, SMC_NLA_FBACK_STATS_CLNT_CNT,
+				      net->smc.fback_rsn->clnt_fback_cnt,
+				      SMC_NLA_FBACK_STATS_PAD))
+			goto errattr;
+		cnt_reported = 1;
+	}
+
+	if (nla_put_u32(skb, SMC_NLA_FBACK_STATS_RSN_CODE,
+			trgt_arr[pos].fback_code))
+		goto errattr;
+	if (nla_put_u16(skb, SMC_NLA_FBACK_STATS_RSN_CNT,
+			trgt_arr[pos].count))
+		goto errattr;
+
+	cb_ctx->pos[2] = cnt_reported;
+	nla_nest_end(skb, attrs);
+	genlmsg_end(skb, nlh);
+	return rc;
+
+errattr:
+	nla_nest_cancel(skb, attrs);
+errout:
+	genlmsg_cancel(skb, nlh);
+errmsg:
+	return -EMSGSIZE;
+}
+
+int smc_nl_get_fback_stats(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+	struct net *net = sock_net(skb->sk);
+	int rc_srv = 0, rc_clnt = 0, k;
+	int skip_serv = cb_ctx->pos[1];
+	int snum = cb_ctx->pos[0];
+	bool is_srv = true;
+
+	mutex_lock(&net->smc.mutex_fback_rsn);
+	for (k = 0; k < SMC_MAX_FBACK_RSN_CNT; k++) {
+		if (k < snum)
+			continue;
+		if (!skip_serv) {
+			rc_srv = smc_nl_get_fback_details(skb, cb, k, is_srv);
+			if (rc_srv && rc_srv != ENODATA)
+				break;
+		} else {
+			skip_serv = 0;
+		}
+		rc_clnt = smc_nl_get_fback_details(skb, cb, k, !is_srv);
+		if (rc_clnt && rc_clnt != ENODATA) {
+			skip_serv = 1;
+			break;
+		}
+		if (rc_clnt == ENODATA && rc_srv == ENODATA)
+			break;
+	}
+	mutex_unlock(&net->smc.mutex_fback_rsn);
+	cb_ctx->pos[1] = skip_serv;
+	cb_ctx->pos[0] = k;
+	return skb->len;
+}
diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h
new file mode 100644
index 000000000000..84b7ecd8c05c
--- /dev/null
+++ b/net/smc/smc_stats.h
@@ -0,0 +1,266 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * Macros for SMC statistics
+ *
+ * Copyright IBM Corp. 2021
+ *
+ * Author(s):  Guvenc Gulce
+ */
+
+#ifndef NET_SMC_SMC_STATS_H_
+#define NET_SMC_SMC_STATS_H_
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/percpu.h>
+#include <linux/ctype.h>
+#include <linux/smc.h>
+
+#include "smc_clc.h"
+
+#define SMC_MAX_FBACK_RSN_CNT 30
+
+enum {
+	SMC_BUF_8K,
+	SMC_BUF_16K,
+	SMC_BUF_32K,
+	SMC_BUF_64K,
+	SMC_BUF_128K,
+	SMC_BUF_256K,
+	SMC_BUF_512K,
+	SMC_BUF_1024K,
+	SMC_BUF_G_1024K,
+	SMC_BUF_MAX,
+};
+
+struct smc_stats_fback {
+	int	fback_code;
+	u16	count;
+};
+
+struct smc_stats_rsn {
+	struct	smc_stats_fback srv[SMC_MAX_FBACK_RSN_CNT];
+	struct	smc_stats_fback clnt[SMC_MAX_FBACK_RSN_CNT];
+	u64			srv_fback_cnt;
+	u64			clnt_fback_cnt;
+};
+
+struct smc_stats_rmbcnt {
+	u64	buf_size_small_peer_cnt;
+	u64	buf_size_small_cnt;
+	u64	buf_full_peer_cnt;
+	u64	buf_full_cnt;
+	u64	reuse_cnt;
+	u64	alloc_cnt;
+	u64	dgrade_cnt;
+};
+
+struct smc_stats_memsize {
+	u64	buf[SMC_BUF_MAX];
+};
+
+struct smc_stats_tech {
+	struct smc_stats_memsize tx_rmbsize;
+	struct smc_stats_memsize rx_rmbsize;
+	struct smc_stats_memsize tx_pd;
+	struct smc_stats_memsize rx_pd;
+	struct smc_stats_rmbcnt rmb_tx;
+	struct smc_stats_rmbcnt rmb_rx;
+	u64			clnt_v1_succ_cnt;
+	u64			clnt_v2_succ_cnt;
+	u64			srv_v1_succ_cnt;
+	u64			srv_v2_succ_cnt;
+	u64			sendpage_cnt;
+	u64			urg_data_cnt;
+	u64			splice_cnt;
+	u64			cork_cnt;
+	u64			ndly_cnt;
+	u64			rx_bytes;
+	u64			tx_bytes;
+	u64			rx_cnt;
+	u64			tx_cnt;
+};
+
+struct smc_stats {
+	struct smc_stats_tech	smc[2];
+	u64			clnt_hshake_err_cnt;
+	u64			srv_hshake_err_cnt;
+};
+
+#define SMC_STAT_PAYLOAD_SUB(_smc_stats, _tech, key, _len, _rc) \
+do { \
+	typeof(_smc_stats) stats = (_smc_stats); \
+	typeof(_tech) t = (_tech); \
+	typeof(_len) l = (_len); \
+	int _pos = fls64((l) >> 13); \
+	typeof(_rc) r = (_rc); \
+	int m = SMC_BUF_MAX - 1; \
+	this_cpu_inc((*stats).smc[t].key ## _cnt); \
+	if (r <= 0) \
+		break; \
+	_pos = (_pos < m) ? ((l == 1 << (_pos + 12)) ? _pos - 1 : _pos) : m; \
+	this_cpu_inc((*stats).smc[t].key ## _pd.buf[_pos]); \
+	this_cpu_add((*stats).smc[t].key ## _bytes, r); \
+} \
+while (0)
+
+#define SMC_STAT_TX_PAYLOAD(_smc, length, rcode) \
+do { \
+	typeof(_smc) __smc = _smc; \
+	struct net *_net = sock_net(&__smc->sk); \
+	struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \
+	typeof(length) _len = (length); \
+	typeof(rcode) _rc = (rcode); \
+	bool is_smcd = !__smc->conn.lnk; \
+	if (is_smcd) \
+		SMC_STAT_PAYLOAD_SUB(_smc_stats, SMC_TYPE_D, tx, _len, _rc); \
+	else \
+		SMC_STAT_PAYLOAD_SUB(_smc_stats, SMC_TYPE_R, tx, _len, _rc); \
+} \
+while (0)
+
+#define SMC_STAT_RX_PAYLOAD(_smc, length, rcode) \
+do { \
+	typeof(_smc) __smc = _smc; \
+	struct net *_net = sock_net(&__smc->sk); \
+	struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \
+	typeof(length) _len = (length); \
+	typeof(rcode) _rc = (rcode); \
+	bool is_smcd = !__smc->conn.lnk; \
+	if (is_smcd) \
+		SMC_STAT_PAYLOAD_SUB(_smc_stats, SMC_TYPE_D, rx, _len, _rc); \
+	else \
+		SMC_STAT_PAYLOAD_SUB(_smc_stats, SMC_TYPE_R, rx, _len, _rc); \
+} \
+while (0)
+
+#define SMC_STAT_RMB_SIZE_SUB(_smc_stats, _tech, k, _len) \
+do { \
+	typeof(_len) _l = (_len); \
+	typeof(_tech) t = (_tech); \
+	int _pos = fls((_l) >> 13); \
+	int m = SMC_BUF_MAX - 1; \
+	_pos = (_pos < m) ? ((_l == 1 << (_pos + 12)) ? _pos - 1 : _pos) : m; \
+	this_cpu_inc((*(_smc_stats)).smc[t].k ## _rmbsize.buf[_pos]); \
+} \
+while (0)
+
+#define SMC_STAT_RMB_SUB(_smc_stats, type, t, key) \
+	this_cpu_inc((*(_smc_stats)).smc[t].rmb ## _ ## key.type ## _cnt)
+
+#define SMC_STAT_RMB_SIZE(_smc, _is_smcd, _is_rx, _len) \
+do { \
+	struct net *_net = sock_net(&(_smc)->sk); \
+	struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \
+	typeof(_is_smcd) is_d = (_is_smcd); \
+	typeof(_is_rx) is_r = (_is_rx); \
+	typeof(_len) l = (_len); \
+	if ((is_d) && (is_r)) \
+		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, rx, l); \
+	if ((is_d) && !(is_r)) \
+		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, tx, l); \
+	if (!(is_d) && (is_r)) \
+		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, rx, l); \
+	if (!(is_d) && !(is_r)) \
+		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, tx, l); \
+} \
+while (0)
+
+#define SMC_STAT_RMB(_smc, type, _is_smcd, _is_rx) \
+do { \
+	struct net *net = sock_net(&(_smc)->sk); \
+	struct smc_stats __percpu *_smc_stats = net->smc.smc_stats; \
+	typeof(_is_smcd) is_d = (_is_smcd); \
+	typeof(_is_rx) is_r = (_is_rx); \
+	if ((is_d) && (is_r)) \
+		SMC_STAT_RMB_SUB(_smc_stats, type, SMC_TYPE_D, rx); \
+	if ((is_d) && !(is_r)) \
+		SMC_STAT_RMB_SUB(_smc_stats, type, SMC_TYPE_D, tx); \
+	if (!(is_d) && (is_r)) \
+		SMC_STAT_RMB_SUB(_smc_stats, type, SMC_TYPE_R, rx); \
+	if (!(is_d) && !(is_r)) \
+		SMC_STAT_RMB_SUB(_smc_stats, type, SMC_TYPE_R, tx); \
+} \
+while (0)
+
+#define SMC_STAT_BUF_REUSE(smc, is_smcd, is_rx) \
+	SMC_STAT_RMB(smc, reuse, is_smcd, is_rx)
+
+#define SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rx) \
+	SMC_STAT_RMB(smc, alloc, is_smcd, is_rx)
+
+#define SMC_STAT_RMB_DOWNGRADED(smc, is_smcd, is_rx) \
+	SMC_STAT_RMB(smc, dgrade, is_smcd, is_rx)
+
+#define SMC_STAT_RMB_TX_PEER_FULL(smc, is_smcd) \
+	SMC_STAT_RMB(smc, buf_full_peer, is_smcd, false)
+
+#define SMC_STAT_RMB_TX_FULL(smc, is_smcd) \
+	SMC_STAT_RMB(smc, buf_full, is_smcd, false)
+
+#define SMC_STAT_RMB_TX_PEER_SIZE_SMALL(smc, is_smcd) \
+	SMC_STAT_RMB(smc, buf_size_small_peer, is_smcd, false)
+
+#define SMC_STAT_RMB_TX_SIZE_SMALL(smc, is_smcd) \
+	SMC_STAT_RMB(smc, buf_size_small, is_smcd, false)
+
+#define SMC_STAT_RMB_RX_SIZE_SMALL(smc, is_smcd) \
+	SMC_STAT_RMB(smc, buf_size_small, is_smcd, true)
+
+#define SMC_STAT_RMB_RX_FULL(smc, is_smcd) \
+	SMC_STAT_RMB(smc, buf_full, is_smcd, true)
+
+#define SMC_STAT_INC(_smc, type) \
+do { \
+	typeof(_smc) __smc = _smc; \
+	bool is_smcd = !(__smc)->conn.lnk; \
+	struct net *net = sock_net(&(__smc)->sk); \
+	struct smc_stats __percpu *smc_stats = net->smc.smc_stats; \
+	if ((is_smcd)) \
+		this_cpu_inc(smc_stats->smc[SMC_TYPE_D].type); \
+	else \
+		this_cpu_inc(smc_stats->smc[SMC_TYPE_R].type); \
+} \
+while (0)
+
+#define SMC_STAT_CLNT_SUCC_INC(net, _aclc) \
+do { \
+	typeof(_aclc) acl = (_aclc); \
+	bool is_v2 = (acl->hdr.version == SMC_V2); \
+	bool is_smcd = (acl->hdr.typev1 == SMC_TYPE_D); \
+	struct smc_stats __percpu *smc_stats = (net)->smc.smc_stats; \
+	if (is_v2 && is_smcd) \
+		this_cpu_inc(smc_stats->smc[SMC_TYPE_D].clnt_v2_succ_cnt); \
+	else if (is_v2 && !is_smcd) \
+		this_cpu_inc(smc_stats->smc[SMC_TYPE_R].clnt_v2_succ_cnt); \
+	else if (!is_v2 && is_smcd) \
+		this_cpu_inc(smc_stats->smc[SMC_TYPE_D].clnt_v1_succ_cnt); \
+	else if (!is_v2 && !is_smcd) \
+		this_cpu_inc(smc_stats->smc[SMC_TYPE_R].clnt_v1_succ_cnt); \
+} \
+while (0)
+
+#define SMC_STAT_SERV_SUCC_INC(net, _ini) \
+do { \
+	typeof(_ini) i = (_ini); \
+	bool is_v2 = (i->smcd_version & SMC_V2); \
+	bool is_smcd = (i->is_smcd); \
+	typeof(net->smc.smc_stats) smc_stats = (net)->smc.smc_stats; \
+	if (is_v2 && is_smcd) \
+		this_cpu_inc(smc_stats->smc[SMC_TYPE_D].srv_v2_succ_cnt); \
+	else if (is_v2 && !is_smcd) \
+		this_cpu_inc(smc_stats->smc[SMC_TYPE_R].srv_v2_succ_cnt); \
+	else if (!is_v2 && is_smcd) \
+		this_cpu_inc(smc_stats->smc[SMC_TYPE_D].srv_v1_succ_cnt); \
+	else if (!is_v2 && !is_smcd) \
+		this_cpu_inc(smc_stats->smc[SMC_TYPE_R].srv_v1_succ_cnt); \
+} \
+while (0)
+
+int smc_nl_get_stats(struct sk_buff *skb, struct netlink_callback *cb);
+int smc_nl_get_fback_stats(struct sk_buff *skb, struct netlink_callback *cb);
+int smc_stats_init(struct net *net);
+void smc_stats_exit(struct net *net);
+
+#endif /* NET_SMC_SMC_STATS_H_ */
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 4532c16bf85e..075c4f4b41cf 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -27,6 +27,7 @@
 #include "smc_close.h"
 #include "smc_ism.h"
 #include "smc_tx.h"
+#include "smc_stats.h"
 
 #define SMC_TX_WORK_DELAY	0
 #define SMC_TX_CORK_DELAY	(HZ >> 2)	/* 250 ms */
@@ -45,6 +46,8 @@ static void smc_tx_write_space(struct sock *sk)
 
 	/* similar to sk_stream_write_space */
 	if (atomic_read(&smc->conn.sndbuf_space) && sock) {
+		if (test_bit(SOCK_NOSPACE, &sock->flags))
+			SMC_STAT_RMB_TX_FULL(smc, !smc->conn.lnk);
 		clear_bit(SOCK_NOSPACE, &sock->flags);
 		rcu_read_lock();
 		wq = rcu_dereference(sk->sk_wq);
@@ -151,6 +154,15 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
 		goto out_err;
 	}
 
+	if (len > conn->sndbuf_desc->len)
+		SMC_STAT_RMB_TX_SIZE_SMALL(smc, !conn->lnk);
+
+	if (len > conn->peer_rmbe_size)
+		SMC_STAT_RMB_TX_PEER_SIZE_SMALL(smc, !conn->lnk);
+
+	if (msg->msg_flags & MSG_OOB)
+		SMC_STAT_INC(smc, urg_data_cnt);
+
 	while (msg_data_left(msg)) {
 		if (sk->sk_state == SMC_INIT)
 			return -ENOTCONN;
@@ -419,8 +431,12 @@ static int smc_tx_rdma_writes(struct smc_connection *conn,
 	/* destination: RMBE */
 	/* cf. snd_wnd */
 	rmbespace = atomic_read(&conn->peer_rmbe_space);
-	if (rmbespace <= 0)
+	if (rmbespace <= 0) {
+		struct smc_sock *smc = container_of(conn, struct smc_sock,
+						    conn);
+		SMC_STAT_RMB_TX_PEER_FULL(smc, !conn->lnk);
 		return 0;
+	}
 	smc_curs_copy(&prod, &conn->local_tx_ctrl.prod, conn);
 	smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn);
 
diff --git a/net/tipc/link.c b/net/tipc/link.c
index c44b4bfaaee6..5b6181277cc5 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -912,7 +912,7 @@ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr)
 	skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0,
 			      dnode, l->addr, dport, 0, 0);
 	if (!skb)
-		return -ENOBUFS;
+		return -ENOMEM;
 	msg_set_dest_droppable(buf_msg(skb), true);
 	TIPC_SKB_CB(skb)->chain_imp = msg_importance(hdr);
 	skb_queue_tail(&l->wakeupq, skb);
@@ -1030,7 +1030,7 @@ void tipc_link_reset(struct tipc_link *l)
  *
  * Consumes the buffer chain.
  * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted
- * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS
+ * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS or -ENOMEM
  */
 int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 		   struct sk_buff_head *xmitq)
@@ -1088,7 +1088,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 			if (!_skb) {
 				kfree_skb(skb);
 				__skb_queue_purge(list);
-				return -ENOBUFS;
+				return -ENOMEM;
 			}
 			__skb_queue_tail(transmq, skb);
 			tipc_link_set_skb_retransmit_time(skb, l);
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index fecab516bf41..01396dd1c899 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -673,12 +673,12 @@ exit:
  * Returns a list of local sockets
  */
 void tipc_nametbl_lookup_mcast_sockets(struct net *net, struct tipc_uaddr *ua,
-				       bool exact, struct list_head *dports)
+				       struct list_head *dports)
 {
 	struct service_range *sr;
 	struct tipc_service *sc;
 	struct publication *p;
-	u32 scope = ua->scope;
+	u8 scope = ua->scope;
 
 	rcu_read_lock();
 	sc = tipc_service_find(net, ua);
@@ -688,7 +688,7 @@ void tipc_nametbl_lookup_mcast_sockets(struct net *net, struct tipc_uaddr *ua,
 	spin_lock_bh(&sc->lock);
 	service_range_foreach_match(sr, sc, ua->sr.lower, ua->sr.upper) {
 		list_for_each_entry(p, &sr->local_publ, local_publ) {
-			if (p->scope == scope || (!exact && p->scope < scope))
+			if (scope == p->scope || scope == TIPC_ANY_SCOPE)
 				tipc_dest_push(dports, 0, p->sk.ref);
 		}
 	}
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index c7c9a3ddd420..259f95e3d99c 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -51,6 +51,8 @@ struct tipc_uaddr;
 #define TIPC_PUBL_SCOPE_NUM	(TIPC_NODE_SCOPE + 1)
 #define TIPC_NAMETBL_SIZE	1024	/* must be a power of 2 */
 
+#define TIPC_ANY_SCOPE 10      /* Both node and cluster scope will match */
+
 /**
  * struct publication - info about a published service address or range
  * @sr: service range represented by this publication
@@ -113,7 +115,7 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb);
 bool tipc_nametbl_lookup_anycast(struct net *net, struct tipc_uaddr *ua,
 				 struct tipc_socket_addr *sk);
 void tipc_nametbl_lookup_mcast_sockets(struct net *net, struct tipc_uaddr *ua,
-				       bool exact, struct list_head *dports);
+				       struct list_head *dports);
 void tipc_nametbl_lookup_mcast_nodes(struct net *net, struct tipc_uaddr *ua,
 				     struct tipc_nlist *nodes);
 bool tipc_nametbl_lookup_group(struct net *net, struct tipc_uaddr *ua,
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 81af92954c6c..9947b7dfe1d2 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1214,7 +1214,7 @@ void tipc_node_check_dest(struct net *net, u32 addr,
 		/* Peer has changed i/f address without rebooting.
 		 * If so, the link will reset soon, and the next
 		 * discovery will be accepted. So we can ignore it.
-		 * It may also be an cloned or malicious peer having
+		 * It may also be a cloned or malicious peer having
 		 * chosen the same node address and signature as an
 		 * existing one.
 		 * Ignore requests until the link goes down, if ever.
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 53af72824c9c..34a97ea36cc8 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -73,9 +73,6 @@ struct sockaddr_pair {
 /**
  * struct tipc_sock - TIPC socket structure
  * @sk: socket - interacts with 'port' and with user via the socket API
- * @conn_type: TIPC type used when connection was established
- * @conn_instance: TIPC instance used when connection was established
- * @published: non-zero if port has one or more associated names
  * @max_pkt: maximum packet size "hint" used when building messages sent by port
  * @maxnagle: maximum size of msg which can be subject to nagle
  * @portid: unique port identity in TIPC socket hash table
@@ -106,11 +103,11 @@ struct sockaddr_pair {
  * @expect_ack: whether this TIPC socket is expecting an ack
  * @nodelay: setsockopt() TIPC_NODELAY setting
  * @group_is_open: TIPC socket group is fully open (FIXME)
+ * @published: true if port has one or more associated names
+ * @conn_addrtype: address type used when establishing connection
  */
 struct tipc_sock {
 	struct sock sk;
-	u32 conn_type;
-	u32 conn_instance;
 	u32 max_pkt;
 	u32 maxnagle;
 	u32 portid;
@@ -141,6 +138,7 @@ struct tipc_sock {
 	bool nodelay;
 	bool group_is_open;
 	bool published;
+	u8 conn_addrtype;
 };
 
 static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
@@ -664,7 +662,7 @@ static int tipc_release(struct socket *sock)
  * @skaddr: socket address describing name(s) and desired operation
  * @alen: size of socket address data structure
  *
- * Name and name sequence binding is indicated using a positive scope value;
+ * Name and name sequence binding are indicated using a positive scope value;
  * a negative scope value unbinds the specified name.  Specifying no name
  * (i.e. a socket address length of 0) unbinds all names from the socket.
  *
@@ -1202,12 +1200,12 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
 	struct tipc_msg *hdr;
 	struct tipc_uaddr ua;
 	int user, mtyp, hlen;
-	bool exact;
 
 	__skb_queue_head_init(&tmpq);
 	INIT_LIST_HEAD(&dports);
 	ua.addrtype = TIPC_SERVICE_RANGE;
 
+	/* tipc_skb_peek() increments the head skb's reference counter */
 	skb = tipc_skb_peek(arrvq, &inputq->lock);
 	for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) {
 		hdr = buf_msg(skb);
@@ -1216,6 +1214,12 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
 		hlen = skb_headroom(skb) + msg_hdr_sz(hdr);
 		onode = msg_orignode(hdr);
 		ua.sr.type = msg_nametype(hdr);
+		ua.sr.lower = msg_namelower(hdr);
+		ua.sr.upper = msg_nameupper(hdr);
+		if (onode == self)
+			ua.scope = TIPC_ANY_SCOPE;
+		else
+			ua.scope = TIPC_CLUSTER_SCOPE;
 
 		if (mtyp == TIPC_GRP_UCAST_MSG || user == GROUP_PROTOCOL) {
 			spin_lock_bh(&inputq->lock);
@@ -1233,20 +1237,10 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
 			ua.sr.lower = 0;
 			ua.sr.upper = ~0;
 			ua.scope = msg_lookup_scope(hdr);
-			exact = true;
-		} else {
-			/* TIPC_NODE_SCOPE means "any scope" in this context */
-			if (onode == self)
-				ua.scope = TIPC_NODE_SCOPE;
-			else
-				ua.scope = TIPC_CLUSTER_SCOPE;
-			exact = false;
-			ua.sr.lower = msg_namelower(hdr);
-			ua.sr.upper = msg_nameupper(hdr);
 		}
 
 		/* Create destination port list: */
-		tipc_nametbl_lookup_mcast_sockets(net, &ua, exact, &dports);
+		tipc_nametbl_lookup_mcast_sockets(net, &ua, &dports);
 
 		/* Clone message per destination */
 		while (tipc_dest_pop(&dports, NULL, &portid)) {
@@ -1258,13 +1252,11 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
 			}
 			pr_warn("Failed to clone mcast rcv buffer\n");
 		}
-		/* Append to inputq if not already done by other thread */
+		/* Append clones to inputq only if skb is still head of arrvq */
 		spin_lock_bh(&inputq->lock);
 		if (skb_peek(arrvq) == skb) {
 			skb_queue_splice_tail_init(&tmpq, inputq);
-			/* Decrease the skb's refcnt as increasing in the
-			 * function tipc_skb_peek
-			 */
+			/* Decrement the skb's refcnt */
 			kfree_skb(__skb_dequeue(arrvq));
 		}
 		spin_unlock_bh(&inputq->lock);
@@ -1463,10 +1455,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 			return -EISCONN;
 		if (tsk->published)
 			return -EOPNOTSUPP;
-		if (atype == TIPC_SERVICE_ADDR) {
-			tsk->conn_type = ua->sa.type;
-			tsk->conn_instance = ua->sa.instance;
-		}
+		if (atype == TIPC_SERVICE_ADDR)
+			tsk->conn_addrtype = atype;
 		msg_set_syn(hdr, 1);
 	}
 
@@ -1737,67 +1727,58 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
 static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb,
 				 struct tipc_sock *tsk)
 {
-	struct tipc_msg *msg;
-	u32 anc_data[3];
-	u32 err;
-	u32 dest_type;
-	int has_name;
-	int res;
+	struct tipc_msg *hdr;
+	u32 data[3] = {0,};
+	bool has_addr;
+	int dlen, rc;
 
 	if (likely(m->msg_controllen == 0))
 		return 0;
-	msg = buf_msg(skb);
 
-	/* Optionally capture errored message object(s) */
-	err = msg ? msg_errcode(msg) : 0;
-	if (unlikely(err)) {
-		anc_data[0] = err;
-		anc_data[1] = msg_data_sz(msg);
-		res = put_cmsg(m, SOL_TIPC, TIPC_ERRINFO, 8, anc_data);
-		if (res)
-			return res;
-		if (anc_data[1]) {
-			if (skb_linearize(skb))
-				return -ENOMEM;
-			msg = buf_msg(skb);
-			res = put_cmsg(m, SOL_TIPC, TIPC_RETDATA, anc_data[1],
-				       msg_data(msg));
-			if (res)
-				return res;
-		}
+	hdr = buf_msg(skb);
+	dlen = msg_data_sz(hdr);
+
+	/* Capture errored message object, if any */
+	if (msg_errcode(hdr)) {
+		if (skb_linearize(skb))
+			return -ENOMEM;
+		hdr = buf_msg(skb);
+		data[0] = msg_errcode(hdr);
+		data[1] = dlen;
+		rc = put_cmsg(m, SOL_TIPC, TIPC_ERRINFO, 8, data);
+		if (rc || !dlen)
+			return rc;
+		rc = put_cmsg(m, SOL_TIPC, TIPC_RETDATA, dlen, msg_data(hdr));
+		if (rc)
+			return rc;
 	}
 
-	/* Optionally capture message destination object */
-	dest_type = msg ? msg_type(msg) : TIPC_DIRECT_MSG;
-	switch (dest_type) {
+	/* Capture TIPC_SERVICE_ADDR/RANGE destination address, if any */
+	switch (msg_type(hdr)) {
 	case TIPC_NAMED_MSG:
-		has_name = 1;
-		anc_data[0] = msg_nametype(msg);
-		anc_data[1] = msg_namelower(msg);
-		anc_data[2] = msg_namelower(msg);
+		has_addr = true;
+		data[0] = msg_nametype(hdr);
+		data[1] = msg_namelower(hdr);
+		data[2] = data[1];
 		break;
 	case TIPC_MCAST_MSG:
-		has_name = 1;
-		anc_data[0] = msg_nametype(msg);
-		anc_data[1] = msg_namelower(msg);
-		anc_data[2] = msg_nameupper(msg);
+		has_addr = true;
+		data[0] = msg_nametype(hdr);
+		data[1] = msg_namelower(hdr);
+		data[2] = msg_nameupper(hdr);
 		break;
 	case TIPC_CONN_MSG:
-		has_name = (tsk->conn_type != 0);
-		anc_data[0] = tsk->conn_type;
-		anc_data[1] = tsk->conn_instance;
-		anc_data[2] = tsk->conn_instance;
+		has_addr = !!tsk->conn_addrtype;
+		data[0] = msg_nametype(&tsk->phdr);
+		data[1] = msg_nameinst(&tsk->phdr);
+		data[2] = data[1];
 		break;
 	default:
-		has_name = 0;
+		has_addr = false;
 	}
-	if (has_name) {
-		res = put_cmsg(m, SOL_TIPC, TIPC_DESTNAME, 12, anc_data);
-		if (res)
-			return res;
-	}
-
-	return 0;
+	if (!has_addr)
+		return 0;
+	return put_cmsg(m, SOL_TIPC, TIPC_DESTNAME, 12, data);
 }
 
 static struct sk_buff *tipc_sk_build_ack(struct tipc_sock *tsk)
@@ -2750,8 +2731,9 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
 
 	tsk_set_importance(new_sk, msg_importance(msg));
 	if (msg_named(msg)) {
-		new_tsock->conn_type = msg_nametype(msg);
-		new_tsock->conn_instance = msg_nameinst(msg);
+		new_tsock->conn_addrtype = TIPC_SERVICE_ADDR;
+		msg_set_nametype(&new_tsock->phdr, msg_nametype(msg));
+		msg_set_nameinst(&new_tsock->phdr, msg_nameinst(msg));
 	}
 
 	/*
@@ -3455,13 +3437,14 @@ void tipc_socket_stop(void)
 /* Caller should hold socket lock for the passed tipc socket. */
 static int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk)
 {
-	u32 peer_node;
-	u32 peer_port;
+	u32 peer_node, peer_port;
+	u32 conn_type, conn_instance;
 	struct nlattr *nest;
 
 	peer_node = tsk_peer_node(tsk);
 	peer_port = tsk_peer_port(tsk);
-
+	conn_type = msg_nametype(&tsk->phdr);
+	conn_instance = msg_nameinst(&tsk->phdr);
 	nest = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_CON);
 	if (!nest)
 		return -EMSGSIZE;
@@ -3471,12 +3454,12 @@ static int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk)
 	if (nla_put_u32(skb, TIPC_NLA_CON_SOCK, peer_port))
 		goto msg_full;
 
-	if (tsk->conn_type != 0) {
+	if (tsk->conn_addrtype != 0) {
 		if (nla_put_flag(skb, TIPC_NLA_CON_FLAG))
 			goto msg_full;
-		if (nla_put_u32(skb, TIPC_NLA_CON_TYPE, tsk->conn_type))
+		if (nla_put_u32(skb, TIPC_NLA_CON_TYPE, conn_type))
 			goto msg_full;
-		if (nla_put_u32(skb, TIPC_NLA_CON_INST, tsk->conn_instance))
+		if (nla_put_u32(skb, TIPC_NLA_CON_INST, conn_instance))
 			goto msg_full;
 	}
 	nla_nest_end(skb, nest);
@@ -3866,9 +3849,9 @@ bool tipc_sk_filtering(struct sock *sk)
 	}
 
 	if (!tipc_sk_type_connectionless(sk)) {
-		type = tsk->conn_type;
-		lower = tsk->conn_instance;
-		upper = tsk->conn_instance;
+		type = msg_nametype(&tsk->phdr);
+		lower = msg_nameinst(&tsk->phdr);
+		upper = lower;
 	}
 
 	if ((_type && _type != type) || (_lower && _lower != lower) ||
@@ -3933,6 +3916,7 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf)
 {
 	int i = 0;
 	size_t sz = (dqueues) ? SK_LMAX : SK_LMIN;
+	u32 conn_type, conn_instance;
 	struct tipc_sock *tsk;
 	struct publication *p;
 	bool tsk_connected;
@@ -3953,8 +3937,10 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf)
 	if (tsk_connected) {
 		i += scnprintf(buf + i, sz - i, " %x", tsk_peer_node(tsk));
 		i += scnprintf(buf + i, sz - i, " %u", tsk_peer_port(tsk));
-		i += scnprintf(buf + i, sz - i, " %u", tsk->conn_type);
-		i += scnprintf(buf + i, sz - i, " %u", tsk->conn_instance);
+		conn_type = msg_nametype(&tsk->phdr);
+		conn_instance = msg_nameinst(&tsk->phdr);
+		i += scnprintf(buf + i, sz - i, " %u", conn_type);
+		i += scnprintf(buf + i, sz - i, " %u", conn_instance);
 	}
 	i += scnprintf(buf + i, sz - i, " | %u", tsk->published);
 	if (tsk->published) {
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 8e00d739f03a..05d49ad81290 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -66,7 +66,7 @@ static void tipc_sub_send_event(struct tipc_subscription *sub,
 /**
  * tipc_sub_check_overlap - test for subscription overlap with the given values
  * @subscribed: the service range subscribed for
- * @found: the service range we are checning for match
+ * @found: the service range we are checking for match
  *
  * Returns true if there is overlap, otherwise false.
  */
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index bd9f1567aa39..b932469ee69c 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -128,7 +128,7 @@ static void destroy_record(struct tls_record_info *record)
 	int i;
 
 	for (i = 0; i < record->num_frags; i++)
-		__skb_frag_unref(&record->frags[i]);
+		__skb_frag_unref(&record->frags[i], false);
 	kfree(record);
 }
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 694de024d0ee..f0fbb079cbaa 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2019,8 +2019,7 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 	if (copied < 0)
 		goto splice_read_end;
 
-	if (likely(!(flags & MSG_PEEK)))
-		tls_sw_advance_skb(sk, skb, copied);
+	tls_sw_advance_skb(sk, skb, copied);
 
 splice_read_end:
 	release_sock(sk);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 5d1192ceb139..c9dfec7b71e7 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1393,7 +1393,7 @@ restart:
 
 	unix_state_unlock(sk);
 
-	/* take ten and and send info to listening sock */
+	/* take ten and send info to listening sock */
 	spin_lock(&other->sk_receive_queue.lock);
 	__skb_queue_tail(&other->sk_receive_queue, skb);
 	spin_unlock(&other->sk_receive_queue.lock);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 92a72f0e0d94..21ccf450e249 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -415,8 +415,8 @@ static void vsock_deassign_transport(struct vsock_sock *vsk)
 
 /* Assign a transport to a socket and call the .init transport callback.
  *
- * Note: for stream socket this must be called when vsk->remote_addr is set
- * (e.g. during the connect() or when a connection request on a listener
+ * Note: for connection oriented socket this must be called when vsk->remote_addr
+ * is set (e.g. during the connect() or when a connection request on a listener
  * socket is received).
  * The vsk->remote_addr is used to decide which transport to use:
  *  - remote CID == VMADDR_CID_LOCAL or g2h->local_cid or VMADDR_CID_HOST if
@@ -452,6 +452,7 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 		new_transport = transport_dgram;
 		break;
 	case SOCK_STREAM:
+	case SOCK_SEQPACKET:
 		if (vsock_use_local_transport(remote_cid))
 			new_transport = transport_local;
 		else if (remote_cid <= VMADDR_CID_HOST || !transport_h2g ||
@@ -469,10 +470,10 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 			return 0;
 
 		/* transport->release() must be called with sock lock acquired.
-		 * This path can only be taken during vsock_stream_connect(),
-		 * where we have already held the sock lock.
-		 * In the other cases, this function is called on a new socket
-		 * which is not assigned to any transport.
+		 * This path can only be taken during vsock_connect(), where we
+		 * have already held the sock lock. In the other cases, this
+		 * function is called on a new socket which is not assigned to
+		 * any transport.
 		 */
 		vsk->transport->release(vsk);
 		vsock_deassign_transport(vsk);
@@ -484,6 +485,14 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 	if (!new_transport || !try_module_get(new_transport->module))
 		return -ENODEV;
 
+	if (sk->sk_type == SOCK_SEQPACKET) {
+		if (!new_transport->seqpacket_allow ||
+		    !new_transport->seqpacket_allow(remote_cid)) {
+			module_put(new_transport->module);
+			return -ESOCKTNOSUPPORT;
+		}
+	}
+
 	ret = new_transport->init(vsk, psk);
 	if (ret) {
 		module_put(new_transport->module);
@@ -604,8 +613,8 @@ out:
 
 /**** SOCKET OPERATIONS ****/
 
-static int __vsock_bind_stream(struct vsock_sock *vsk,
-			       struct sockaddr_vm *addr)
+static int __vsock_bind_connectible(struct vsock_sock *vsk,
+				    struct sockaddr_vm *addr)
 {
 	static u32 port;
 	struct sockaddr_vm new_addr;
@@ -649,9 +658,10 @@ static int __vsock_bind_stream(struct vsock_sock *vsk,
 
 	vsock_addr_init(&vsk->local_addr, new_addr.svm_cid, new_addr.svm_port);
 
-	/* Remove stream sockets from the unbound list and add them to the hash
-	 * table for easy lookup by its address.  The unbound list is simply an
-	 * extra entry at the end of the hash table, a trick used by AF_UNIX.
+	/* Remove connection oriented sockets from the unbound list and add them
+	 * to the hash table for easy lookup by its address.  The unbound list
+	 * is simply an extra entry at the end of the hash table, a trick used
+	 * by AF_UNIX.
 	 */
 	__vsock_remove_bound(vsk);
 	__vsock_insert_bound(vsock_bound_sockets(&vsk->local_addr), vsk);
@@ -684,8 +694,9 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr)
 
 	switch (sk->sk_socket->type) {
 	case SOCK_STREAM:
+	case SOCK_SEQPACKET:
 		spin_lock_bh(&vsock_table_lock);
-		retval = __vsock_bind_stream(vsk, addr);
+		retval = __vsock_bind_connectible(vsk, addr);
 		spin_unlock_bh(&vsock_table_lock);
 		break;
 
@@ -768,6 +779,11 @@ static struct sock *__vsock_create(struct net *net,
 	return sk;
 }
 
+static bool sock_type_connectible(u16 type)
+{
+	return (type == SOCK_STREAM) || (type == SOCK_SEQPACKET);
+}
+
 static void __vsock_release(struct sock *sk, int level)
 {
 	if (sk) {
@@ -786,7 +802,7 @@ static void __vsock_release(struct sock *sk, int level)
 
 		if (vsk->transport)
 			vsk->transport->release(vsk);
-		else if (sk->sk_type == SOCK_STREAM)
+		else if (sock_type_connectible(sk->sk_type))
 			vsock_remove_sock(vsk);
 
 		sock_orphan(sk);
@@ -844,6 +860,16 @@ s64 vsock_stream_has_data(struct vsock_sock *vsk)
 }
 EXPORT_SYMBOL_GPL(vsock_stream_has_data);
 
+static s64 vsock_connectible_has_data(struct vsock_sock *vsk)
+{
+	struct sock *sk = sk_vsock(vsk);
+
+	if (sk->sk_type == SOCK_SEQPACKET)
+		return vsk->transport->seqpacket_has_data(vsk);
+	else
+		return vsock_stream_has_data(vsk);
+}
+
 s64 vsock_stream_has_space(struct vsock_sock *vsk)
 {
 	return vsk->transport->stream_has_space(vsk);
@@ -937,10 +963,10 @@ static int vsock_shutdown(struct socket *sock, int mode)
 	if ((mode & ~SHUTDOWN_MASK) || !mode)
 		return -EINVAL;
 
-	/* If this is a STREAM socket and it is not connected then bail out
-	 * immediately.  If it is a DGRAM socket then we must first kick the
-	 * socket so that it wakes up from any sleeping calls, for example
-	 * recv(), and then afterwards return the error.
+	/* If this is a connection oriented socket and it is not connected then
+	 * bail out immediately.  If it is a DGRAM socket then we must first
+	 * kick the socket so that it wakes up from any sleeping calls, for
+	 * example recv(), and then afterwards return the error.
 	 */
 
 	sk = sock->sk;
@@ -948,7 +974,7 @@ static int vsock_shutdown(struct socket *sock, int mode)
 	lock_sock(sk);
 	if (sock->state == SS_UNCONNECTED) {
 		err = -ENOTCONN;
-		if (sk->sk_type == SOCK_STREAM)
+		if (sock_type_connectible(sk->sk_type))
 			goto out;
 	} else {
 		sock->state = SS_DISCONNECTING;
@@ -961,7 +987,7 @@ static int vsock_shutdown(struct socket *sock, int mode)
 		sk->sk_shutdown |= mode;
 		sk->sk_state_change(sk);
 
-		if (sk->sk_type == SOCK_STREAM) {
+		if (sock_type_connectible(sk->sk_type)) {
 			sock_reset_flag(sk, SOCK_DONE);
 			vsock_send_shutdown(sk, mode);
 		}
@@ -1016,7 +1042,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock,
 		if (!(sk->sk_shutdown & SEND_SHUTDOWN))
 			mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
 
-	} else if (sock->type == SOCK_STREAM) {
+	} else if (sock_type_connectible(sk->sk_type)) {
 		const struct vsock_transport *transport;
 
 		lock_sock(sk);
@@ -1263,8 +1289,8 @@ static void vsock_connect_timeout(struct work_struct *work)
 	sock_put(sk);
 }
 
-static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
-				int addr_len, int flags)
+static int vsock_connect(struct socket *sock, struct sockaddr *addr,
+			 int addr_len, int flags)
 {
 	int err;
 	struct sock *sk;
@@ -1414,7 +1440,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags,
 
 	lock_sock(listener);
 
-	if (sock->type != SOCK_STREAM) {
+	if (!sock_type_connectible(sock->type)) {
 		err = -EOPNOTSUPP;
 		goto out;
 	}
@@ -1491,7 +1517,7 @@ static int vsock_listen(struct socket *sock, int backlog)
 
 	lock_sock(sk);
 
-	if (sock->type != SOCK_STREAM) {
+	if (!sock_type_connectible(sk->sk_type)) {
 		err = -EOPNOTSUPP;
 		goto out;
 	}
@@ -1535,11 +1561,11 @@ static void vsock_update_buffer_size(struct vsock_sock *vsk,
 	vsk->buffer_size = val;
 }
 
-static int vsock_stream_setsockopt(struct socket *sock,
-				   int level,
-				   int optname,
-				   sockptr_t optval,
-				   unsigned int optlen)
+static int vsock_connectible_setsockopt(struct socket *sock,
+					int level,
+					int optname,
+					sockptr_t optval,
+					unsigned int optlen)
 {
 	int err;
 	struct sock *sk;
@@ -1617,10 +1643,10 @@ exit:
 	return err;
 }
 
-static int vsock_stream_getsockopt(struct socket *sock,
-				   int level, int optname,
-				   char __user *optval,
-				   int __user *optlen)
+static int vsock_connectible_getsockopt(struct socket *sock,
+					int level, int optname,
+					char __user *optval,
+					int __user *optlen)
 {
 	int err;
 	int len;
@@ -1688,8 +1714,8 @@ static int vsock_stream_getsockopt(struct socket *sock,
 	return 0;
 }
 
-static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
-				size_t len)
+static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg,
+				     size_t len)
 {
 	struct sock *sk;
 	struct vsock_sock *vsk;
@@ -1712,7 +1738,9 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	transport = vsk->transport;
 
-	/* Callers should not provide a destination with stream sockets. */
+	/* Callers should not provide a destination with connection oriented
+	 * sockets.
+	 */
 	if (msg->msg_namelen) {
 		err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
 		goto out;
@@ -1803,9 +1831,13 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 		 * responsibility to check how many bytes we were able to send.
 		 */
 
-		written = transport->stream_enqueue(
-				vsk, msg,
-				len - total_written);
+		if (sk->sk_type == SOCK_SEQPACKET) {
+			written = transport->seqpacket_enqueue(vsk,
+						msg, len - total_written);
+		} else {
+			written = transport->stream_enqueue(vsk,
+					msg, len - total_written);
+		}
 		if (written < 0) {
 			err = -ENOMEM;
 			goto out_err;
@@ -1821,72 +1853,98 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 	}
 
 out_err:
-	if (total_written > 0)
-		err = total_written;
+	if (total_written > 0) {
+		/* Return number of written bytes only if:
+		 * 1) SOCK_STREAM socket.
+		 * 2) SOCK_SEQPACKET socket when whole buffer is sent.
+		 */
+		if (sk->sk_type == SOCK_STREAM || total_written == len)
+			err = total_written;
+	}
 out:
 	release_sock(sk);
 	return err;
 }
 
-
-static int
-vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
-		     int flags)
+static int vsock_connectible_wait_data(struct sock *sk,
+				       struct wait_queue_entry *wait,
+				       long timeout,
+				       struct vsock_transport_recv_notify_data *recv_data,
+				       size_t target)
 {
-	struct sock *sk;
-	struct vsock_sock *vsk;
 	const struct vsock_transport *transport;
+	struct vsock_sock *vsk;
+	s64 data;
 	int err;
-	size_t target;
-	ssize_t copied;
-	long timeout;
-	struct vsock_transport_recv_notify_data recv_data;
-
-	DEFINE_WAIT(wait);
 
-	sk = sock->sk;
 	vsk = vsock_sk(sk);
 	err = 0;
+	transport = vsk->transport;
 
-	lock_sock(sk);
+	while ((data = vsock_connectible_has_data(vsk)) == 0) {
+		prepare_to_wait(sk_sleep(sk), wait, TASK_INTERRUPTIBLE);
 
-	transport = vsk->transport;
+		if (sk->sk_err != 0 ||
+		    (sk->sk_shutdown & RCV_SHUTDOWN) ||
+		    (vsk->peer_shutdown & SEND_SHUTDOWN)) {
+			break;
+		}
 
-	if (!transport || sk->sk_state != TCP_ESTABLISHED) {
-		/* Recvmsg is supposed to return 0 if a peer performs an
-		 * orderly shutdown. Differentiate between that case and when a
-		 * peer has not connected or a local shutdown occurred with the
-		 * SOCK_DONE flag.
-		 */
-		if (sock_flag(sk, SOCK_DONE))
-			err = 0;
-		else
-			err = -ENOTCONN;
+		/* Don't wait for non-blocking sockets. */
+		if (timeout == 0) {
+			err = -EAGAIN;
+			break;
+		}
 
-		goto out;
-	}
+		if (recv_data) {
+			err = transport->notify_recv_pre_block(vsk, target, recv_data);
+			if (err < 0)
+				break;
+		}
 
-	if (flags & MSG_OOB) {
-		err = -EOPNOTSUPP;
-		goto out;
-	}
+		release_sock(sk);
+		timeout = schedule_timeout(timeout);
+		lock_sock(sk);
 
-	/* We don't check peer_shutdown flag here since peer may actually shut
-	 * down, but there can be data in the queue that a local socket can
-	 * receive.
-	 */
-	if (sk->sk_shutdown & RCV_SHUTDOWN) {
-		err = 0;
-		goto out;
+		if (signal_pending(current)) {
+			err = sock_intr_errno(timeout);
+			break;
+		} else if (timeout == 0) {
+			err = -EAGAIN;
+			break;
+		}
 	}
 
-	/* It is valid on Linux to pass in a zero-length receive buffer.  This
-	 * is not an error.  We may as well bail out now.
+	finish_wait(sk_sleep(sk), wait);
+
+	if (err)
+		return err;
+
+	/* Internal transport error when checking for available
+	 * data. XXX This should be changed to a connection
+	 * reset in a later change.
 	 */
-	if (!len) {
-		err = 0;
-		goto out;
-	}
+	if (data < 0)
+		return -ENOMEM;
+
+	return data;
+}
+
+static int __vsock_stream_recvmsg(struct sock *sk, struct msghdr *msg,
+				  size_t len, int flags)
+{
+	struct vsock_transport_recv_notify_data recv_data;
+	const struct vsock_transport *transport;
+	struct vsock_sock *vsk;
+	ssize_t copied;
+	size_t target;
+	long timeout;
+	int err;
+
+	DEFINE_WAIT(wait);
+
+	vsk = vsock_sk(sk);
+	transport = vsk->transport;
 
 	/* We must not copy less than target bytes into the user's buffer
 	 * before returning successfully, so we wait for the consume queue to
@@ -1908,94 +1966,158 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 
 	while (1) {
-		s64 ready;
+		ssize_t read;
 
-		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-		ready = vsock_stream_has_data(vsk);
+		err = vsock_connectible_wait_data(sk, &wait, timeout,
+						  &recv_data, target);
+		if (err <= 0)
+			break;
 
-		if (ready == 0) {
-			if (sk->sk_err != 0 ||
-			    (sk->sk_shutdown & RCV_SHUTDOWN) ||
-			    (vsk->peer_shutdown & SEND_SHUTDOWN)) {
-				finish_wait(sk_sleep(sk), &wait);
-				break;
-			}
-			/* Don't wait for non-blocking sockets. */
-			if (timeout == 0) {
-				err = -EAGAIN;
-				finish_wait(sk_sleep(sk), &wait);
-				break;
-			}
+		err = transport->notify_recv_pre_dequeue(vsk, target,
+							 &recv_data);
+		if (err < 0)
+			break;
 
-			err = transport->notify_recv_pre_block(
-					vsk, target, &recv_data);
-			if (err < 0) {
-				finish_wait(sk_sleep(sk), &wait);
-				break;
-			}
-			release_sock(sk);
-			timeout = schedule_timeout(timeout);
-			lock_sock(sk);
+		read = transport->stream_dequeue(vsk, msg, len - copied, flags);
+		if (read < 0) {
+			err = -ENOMEM;
+			break;
+		}
 
-			if (signal_pending(current)) {
-				err = sock_intr_errno(timeout);
-				finish_wait(sk_sleep(sk), &wait);
-				break;
-			} else if (timeout == 0) {
-				err = -EAGAIN;
-				finish_wait(sk_sleep(sk), &wait);
-				break;
-			}
-		} else {
-			ssize_t read;
+		copied += read;
 
-			finish_wait(sk_sleep(sk), &wait);
+		err = transport->notify_recv_post_dequeue(vsk, target, read,
+						!(flags & MSG_PEEK), &recv_data);
+		if (err < 0)
+			goto out;
 
-			if (ready < 0) {
-				/* Invalid queue pair content. XXX This should
-				* be changed to a connection reset in a later
-				* change.
-				*/
+		if (read >= target || flags & MSG_PEEK)
+			break;
 
-				err = -ENOMEM;
-				goto out;
-			}
+		target -= read;
+	}
 
-			err = transport->notify_recv_pre_dequeue(
-					vsk, target, &recv_data);
-			if (err < 0)
-				break;
+	if (sk->sk_err)
+		err = -sk->sk_err;
+	else if (sk->sk_shutdown & RCV_SHUTDOWN)
+		err = 0;
 
-			read = transport->stream_dequeue(
-					vsk, msg,
-					len - copied, flags);
-			if (read < 0) {
-				err = -ENOMEM;
-				break;
-			}
+	if (copied > 0)
+		err = copied;
+
+out:
+	return err;
+}
 
-			copied += read;
+static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg,
+				     size_t len, int flags)
+{
+	const struct vsock_transport *transport;
+	struct vsock_sock *vsk;
+	ssize_t record_len;
+	long timeout;
+	int err = 0;
+	DEFINE_WAIT(wait);
 
-			err = transport->notify_recv_post_dequeue(
-					vsk, target, read,
-					!(flags & MSG_PEEK), &recv_data);
-			if (err < 0)
-				goto out;
+	vsk = vsock_sk(sk);
+	transport = vsk->transport;
 
-			if (read >= target || flags & MSG_PEEK)
-				break;
+	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 
-			target -= read;
-		}
+	err = vsock_connectible_wait_data(sk, &wait, timeout, NULL, 0);
+	if (err <= 0)
+		goto out;
+
+	record_len = transport->seqpacket_dequeue(vsk, msg, flags);
+
+	if (record_len < 0) {
+		err = -ENOMEM;
+		goto out;
 	}
 
-	if (sk->sk_err)
+	if (sk->sk_err) {
 		err = -sk->sk_err;
-	else if (sk->sk_shutdown & RCV_SHUTDOWN)
+	} else if (sk->sk_shutdown & RCV_SHUTDOWN) {
 		err = 0;
+	} else {
+		/* User sets MSG_TRUNC, so return real length of
+		 * packet.
+		 */
+		if (flags & MSG_TRUNC)
+			err = record_len;
+		else
+			err = len - msg_data_left(msg);
 
-	if (copied > 0)
-		err = copied;
+		/* Always set MSG_TRUNC if real length of packet is
+		 * bigger than user's buffer.
+		 */
+		if (record_len > len)
+			msg->msg_flags |= MSG_TRUNC;
+	}
+
+out:
+	return err;
+}
+
+static int
+vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+			  int flags)
+{
+	struct sock *sk;
+	struct vsock_sock *vsk;
+	const struct vsock_transport *transport;
+	int err;
+
+	DEFINE_WAIT(wait);
+
+	sk = sock->sk;
+	vsk = vsock_sk(sk);
+	err = 0;
+
+	lock_sock(sk);
+
+	transport = vsk->transport;
+
+	if (!transport || sk->sk_state != TCP_ESTABLISHED) {
+		/* Recvmsg is supposed to return 0 if a peer performs an
+		 * orderly shutdown. Differentiate between that case and when a
+		 * peer has not connected or a local shutdown occurred with the
+		 * SOCK_DONE flag.
+		 */
+		if (sock_flag(sk, SOCK_DONE))
+			err = 0;
+		else
+			err = -ENOTCONN;
+
+		goto out;
+	}
+
+	if (flags & MSG_OOB) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+	/* We don't check peer_shutdown flag here since peer may actually shut
+	 * down, but there can be data in the queue that a local socket can
+	 * receive.
+	 */
+	if (sk->sk_shutdown & RCV_SHUTDOWN) {
+		err = 0;
+		goto out;
+	}
+
+	/* It is valid on Linux to pass in a zero-length receive buffer.  This
+	 * is not an error.  We may as well bail out now.
+	 */
+	if (!len) {
+		err = 0;
+		goto out;
+	}
+
+	if (sk->sk_type == SOCK_STREAM)
+		err = __vsock_stream_recvmsg(sk, msg, len, flags);
+	else
+		err = __vsock_seqpacket_recvmsg(sk, msg, len, flags);
 
 out:
 	release_sock(sk);
@@ -2007,7 +2129,7 @@ static const struct proto_ops vsock_stream_ops = {
 	.owner = THIS_MODULE,
 	.release = vsock_release,
 	.bind = vsock_bind,
-	.connect = vsock_stream_connect,
+	.connect = vsock_connect,
 	.socketpair = sock_no_socketpair,
 	.accept = vsock_accept,
 	.getname = vsock_getname,
@@ -2015,10 +2137,31 @@ static const struct proto_ops vsock_stream_ops = {
 	.ioctl = sock_no_ioctl,
 	.listen = vsock_listen,
 	.shutdown = vsock_shutdown,
-	.setsockopt = vsock_stream_setsockopt,
-	.getsockopt = vsock_stream_getsockopt,
-	.sendmsg = vsock_stream_sendmsg,
-	.recvmsg = vsock_stream_recvmsg,
+	.setsockopt = vsock_connectible_setsockopt,
+	.getsockopt = vsock_connectible_getsockopt,
+	.sendmsg = vsock_connectible_sendmsg,
+	.recvmsg = vsock_connectible_recvmsg,
+	.mmap = sock_no_mmap,
+	.sendpage = sock_no_sendpage,
+};
+
+static const struct proto_ops vsock_seqpacket_ops = {
+	.family = PF_VSOCK,
+	.owner = THIS_MODULE,
+	.release = vsock_release,
+	.bind = vsock_bind,
+	.connect = vsock_connect,
+	.socketpair = sock_no_socketpair,
+	.accept = vsock_accept,
+	.getname = vsock_getname,
+	.poll = vsock_poll,
+	.ioctl = sock_no_ioctl,
+	.listen = vsock_listen,
+	.shutdown = vsock_shutdown,
+	.setsockopt = vsock_connectible_setsockopt,
+	.getsockopt = vsock_connectible_getsockopt,
+	.sendmsg = vsock_connectible_sendmsg,
+	.recvmsg = vsock_connectible_recvmsg,
 	.mmap = sock_no_mmap,
 	.sendpage = sock_no_sendpage,
 };
@@ -2043,6 +2186,9 @@ static int vsock_create(struct net *net, struct socket *sock,
 	case SOCK_STREAM:
 		sock->ops = &vsock_stream_ops;
 		break;
+	case SOCK_SEQPACKET:
+		sock->ops = &vsock_seqpacket_ops;
+		break;
 	default:
 		return -ESOCKTNOSUPPORT;
 	}
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 2700a63ab095..e73ce652bf3c 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -62,6 +62,7 @@ struct virtio_vsock {
 	struct virtio_vsock_event event_list[8];
 
 	u32 guest_cid;
+	bool seqpacket_allow;
 };
 
 static u32 virtio_transport_get_local_cid(void)
@@ -443,6 +444,8 @@ static void virtio_vsock_rx_done(struct virtqueue *vq)
 	queue_work(virtio_vsock_workqueue, &vsock->rx_work);
 }
 
+static bool virtio_transport_seqpacket_allow(u32 remote_cid);
+
 static struct virtio_transport virtio_transport = {
 	.transport = {
 		.module                   = THIS_MODULE,
@@ -469,6 +472,11 @@ static struct virtio_transport virtio_transport = {
 		.stream_is_active         = virtio_transport_stream_is_active,
 		.stream_allow             = virtio_transport_stream_allow,
 
+		.seqpacket_dequeue        = virtio_transport_seqpacket_dequeue,
+		.seqpacket_enqueue        = virtio_transport_seqpacket_enqueue,
+		.seqpacket_allow          = virtio_transport_seqpacket_allow,
+		.seqpacket_has_data       = virtio_transport_seqpacket_has_data,
+
 		.notify_poll_in           = virtio_transport_notify_poll_in,
 		.notify_poll_out          = virtio_transport_notify_poll_out,
 		.notify_recv_init         = virtio_transport_notify_recv_init,
@@ -485,6 +493,19 @@ static struct virtio_transport virtio_transport = {
 	.send_pkt = virtio_transport_send_pkt,
 };
 
+static bool virtio_transport_seqpacket_allow(u32 remote_cid)
+{
+	struct virtio_vsock *vsock;
+	bool seqpacket_allow;
+
+	rcu_read_lock();
+	vsock = rcu_dereference(the_virtio_vsock);
+	seqpacket_allow = vsock->seqpacket_allow;
+	rcu_read_unlock();
+
+	return seqpacket_allow;
+}
+
 static void virtio_transport_rx_work(struct work_struct *work)
 {
 	struct virtio_vsock *vsock =
@@ -608,10 +629,14 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
 	vsock->event_run = true;
 	mutex_unlock(&vsock->event_lock);
 
+	if (virtio_has_feature(vdev, VIRTIO_VSOCK_F_SEQPACKET))
+		vsock->seqpacket_allow = true;
+
 	vdev->priv = vsock;
 	rcu_assign_pointer(the_virtio_vsock, vsock);
 
 	mutex_unlock(&the_virtio_vsock_mutex);
+
 	return 0;
 
 out:
@@ -695,6 +720,7 @@ static struct virtio_device_id id_table[] = {
 };
 
 static unsigned int features[] = {
+	VIRTIO_VSOCK_F_SEQPACKET
 };
 
 static struct virtio_driver virtio_vsock_driver = {
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 902cb6dd710b..f014ccfdd9c2 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -74,6 +74,10 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info,
 		err = memcpy_from_msg(pkt->buf, info->msg, len);
 		if (err)
 			goto out;
+
+		if (msg_data_left(info->msg) == 0 &&
+		    info->type == VIRTIO_VSOCK_TYPE_SEQPACKET)
+			pkt->hdr.flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR);
 	}
 
 	trace_virtio_transport_alloc_pkt(src_cid, src_port,
@@ -165,6 +169,14 @@ void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt)
 }
 EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt);
 
+static u16 virtio_transport_get_type(struct sock *sk)
+{
+	if (sk->sk_type == SOCK_STREAM)
+		return VIRTIO_VSOCK_TYPE_STREAM;
+	else
+		return VIRTIO_VSOCK_TYPE_SEQPACKET;
+}
+
 /* This function can only be used on connecting/connected sockets,
  * since a socket assigned to a transport is required.
  *
@@ -179,6 +191,8 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
 	struct virtio_vsock_pkt *pkt;
 	u32 pkt_len = info->pkt_len;
 
+	info->type = virtio_transport_get_type(sk_vsock(vsk));
+
 	t_ops = virtio_transport_get_ops(vsk);
 	if (unlikely(!t_ops))
 		return -EFAULT;
@@ -269,13 +283,10 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit)
 }
 EXPORT_SYMBOL_GPL(virtio_transport_put_credit);
 
-static int virtio_transport_send_credit_update(struct vsock_sock *vsk,
-					       int type,
-					       struct virtio_vsock_hdr *hdr)
+static int virtio_transport_send_credit_update(struct vsock_sock *vsk)
 {
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_CREDIT_UPDATE,
-		.type = type,
 		.vsk = vsk,
 	};
 
@@ -383,11 +394,8 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
 	 * messages, we set the limit to a high value. TODO: experiment
 	 * with different values.
 	 */
-	if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) {
-		virtio_transport_send_credit_update(vsk,
-						    VIRTIO_VSOCK_TYPE_STREAM,
-						    NULL);
-	}
+	if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE)
+		virtio_transport_send_credit_update(vsk);
 
 	return total;
 
@@ -397,6 +405,75 @@ out:
 	return err;
 }
 
+static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk,
+						 struct msghdr *msg,
+						 int flags)
+{
+	struct virtio_vsock_sock *vvs = vsk->trans;
+	struct virtio_vsock_pkt *pkt;
+	int dequeued_len = 0;
+	size_t user_buf_len = msg_data_left(msg);
+	bool msg_ready = false;
+
+	spin_lock_bh(&vvs->rx_lock);
+
+	if (vvs->msg_count == 0) {
+		spin_unlock_bh(&vvs->rx_lock);
+		return 0;
+	}
+
+	while (!msg_ready) {
+		pkt = list_first_entry(&vvs->rx_queue, struct virtio_vsock_pkt, list);
+
+		if (dequeued_len >= 0) {
+			size_t pkt_len;
+			size_t bytes_to_copy;
+
+			pkt_len = (size_t)le32_to_cpu(pkt->hdr.len);
+			bytes_to_copy = min(user_buf_len, pkt_len);
+
+			if (bytes_to_copy) {
+				int err;
+
+				/* sk_lock is held by caller so no one else can dequeue.
+				 * Unlock rx_lock since memcpy_to_msg() may sleep.
+				 */
+				spin_unlock_bh(&vvs->rx_lock);
+
+				err = memcpy_to_msg(msg, pkt->buf, bytes_to_copy);
+				if (err) {
+					/* Copy of message failed. Rest of
+					 * fragments will be freed without copy.
+					 */
+					dequeued_len = err;
+				} else {
+					user_buf_len -= bytes_to_copy;
+				}
+
+				spin_lock_bh(&vvs->rx_lock);
+			}
+
+			if (dequeued_len >= 0)
+				dequeued_len += pkt_len;
+		}
+
+		if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) {
+			msg_ready = true;
+			vvs->msg_count--;
+		}
+
+		virtio_transport_dec_rx_pkt(vvs, pkt);
+		list_del(&pkt->list);
+		virtio_transport_free_pkt(pkt);
+	}
+
+	spin_unlock_bh(&vvs->rx_lock);
+
+	virtio_transport_send_credit_update(vsk);
+
+	return dequeued_len;
+}
+
 ssize_t
 virtio_transport_stream_dequeue(struct vsock_sock *vsk,
 				struct msghdr *msg,
@@ -409,6 +486,38 @@ virtio_transport_stream_dequeue(struct vsock_sock *vsk,
 }
 EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue);
 
+ssize_t
+virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk,
+				   struct msghdr *msg,
+				   int flags)
+{
+	if (flags & MSG_PEEK)
+		return -EOPNOTSUPP;
+
+	return virtio_transport_seqpacket_do_dequeue(vsk, msg, flags);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue);
+
+int
+virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk,
+				   struct msghdr *msg,
+				   size_t len)
+{
+	struct virtio_vsock_sock *vvs = vsk->trans;
+
+	spin_lock_bh(&vvs->tx_lock);
+
+	if (len > vvs->peer_buf_alloc) {
+		spin_unlock_bh(&vvs->tx_lock);
+		return -EMSGSIZE;
+	}
+
+	spin_unlock_bh(&vvs->tx_lock);
+
+	return virtio_transport_stream_enqueue(vsk, msg, len);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_enqueue);
+
 int
 virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
 			       struct msghdr *msg,
@@ -431,6 +540,19 @@ s64 virtio_transport_stream_has_data(struct vsock_sock *vsk)
 }
 EXPORT_SYMBOL_GPL(virtio_transport_stream_has_data);
 
+u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk)
+{
+	struct virtio_vsock_sock *vvs = vsk->trans;
+	u32 msg_count;
+
+	spin_lock_bh(&vvs->rx_lock);
+	msg_count = vvs->msg_count;
+	spin_unlock_bh(&vvs->rx_lock);
+
+	return msg_count;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_has_data);
+
 static s64 virtio_transport_has_space(struct vsock_sock *vsk)
 {
 	struct virtio_vsock_sock *vvs = vsk->trans;
@@ -496,8 +618,7 @@ void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val)
 
 	vvs->buf_alloc = *val;
 
-	virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM,
-					    NULL);
+	virtio_transport_send_credit_update(vsk);
 }
 EXPORT_SYMBOL_GPL(virtio_transport_notify_buffer_size);
 
@@ -624,7 +745,6 @@ int virtio_transport_connect(struct vsock_sock *vsk)
 {
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_REQUEST,
-		.type = VIRTIO_VSOCK_TYPE_STREAM,
 		.vsk = vsk,
 	};
 
@@ -636,7 +756,6 @@ int virtio_transport_shutdown(struct vsock_sock *vsk, int mode)
 {
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_SHUTDOWN,
-		.type = VIRTIO_VSOCK_TYPE_STREAM,
 		.flags = (mode & RCV_SHUTDOWN ?
 			  VIRTIO_VSOCK_SHUTDOWN_RCV : 0) |
 			 (mode & SEND_SHUTDOWN ?
@@ -665,7 +784,6 @@ virtio_transport_stream_enqueue(struct vsock_sock *vsk,
 {
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_RW,
-		.type = VIRTIO_VSOCK_TYPE_STREAM,
 		.msg = msg,
 		.pkt_len = len,
 		.vsk = vsk,
@@ -688,7 +806,6 @@ static int virtio_transport_reset(struct vsock_sock *vsk,
 {
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_RST,
-		.type = VIRTIO_VSOCK_TYPE_STREAM,
 		.reply = !!pkt,
 		.vsk = vsk,
 	};
@@ -848,7 +965,7 @@ void virtio_transport_release(struct vsock_sock *vsk)
 	struct sock *sk = &vsk->sk;
 	bool remove_sock = true;
 
-	if (sk->sk_type == SOCK_STREAM)
+	if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)
 		remove_sock = virtio_transport_close(vsk);
 
 	if (remove_sock) {
@@ -912,6 +1029,9 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk,
 		goto out;
 	}
 
+	if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR)
+		vvs->msg_count++;
+
 	/* Try to copy small packets into the buffer of last packet queued,
 	 * to avoid wasting memory queueing the entire buffer with a small
 	 * payload.
@@ -923,13 +1043,18 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk,
 					   struct virtio_vsock_pkt, list);
 
 		/* If there is space in the last packet queued, we copy the
-		 * new packet in its buffer.
+		 * new packet in its buffer. We avoid this if the last packet
+		 * queued has VIRTIO_VSOCK_SEQ_EOR set, because this is
+		 * delimiter of SEQPACKET record, so 'pkt' is the first packet
+		 * of a new record.
 		 */
-		if (pkt->len <= last_pkt->buf_len - last_pkt->len) {
+		if ((pkt->len <= last_pkt->buf_len - last_pkt->len) &&
+		    !(le32_to_cpu(last_pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR)) {
 			memcpy(last_pkt->buf + last_pkt->len, pkt->buf,
 			       pkt->len);
 			last_pkt->len += pkt->len;
 			free_pkt = true;
+			last_pkt->hdr.flags |= pkt->hdr.flags;
 			goto out;
 		}
 	}
@@ -1000,7 +1125,6 @@ virtio_transport_send_response(struct vsock_sock *vsk,
 {
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_RESPONSE,
-		.type = VIRTIO_VSOCK_TYPE_STREAM,
 		.remote_cid = le64_to_cpu(pkt->hdr.src_cid),
 		.remote_port = le32_to_cpu(pkt->hdr.src_port),
 		.reply = true,
@@ -1096,6 +1220,12 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt,
 	return 0;
 }
 
+static bool virtio_transport_valid_type(u16 type)
+{
+	return (type == VIRTIO_VSOCK_TYPE_STREAM) ||
+	       (type == VIRTIO_VSOCK_TYPE_SEQPACKET);
+}
+
 /* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex
  * lock.
  */
@@ -1121,7 +1251,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
 					le32_to_cpu(pkt->hdr.buf_alloc),
 					le32_to_cpu(pkt->hdr.fwd_cnt));
 
-	if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) {
+	if (!virtio_transport_valid_type(le16_to_cpu(pkt->hdr.type))) {
 		(void)virtio_transport_reset_no_sock(t, pkt);
 		goto free_pkt;
 	}
@@ -1138,6 +1268,12 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
 		}
 	}
 
+	if (virtio_transport_get_type(sk) != le16_to_cpu(pkt->hdr.type)) {
+		(void)virtio_transport_reset_no_sock(t, pkt);
+		sock_put(sk);
+		goto free_pkt;
+	}
+
 	vsk = vsock_sk(sk);
 
 	lock_sock(sk);
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index c99bc4ce78e2..e617ed93f06b 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1248,7 +1248,7 @@ vmci_transport_recv_connecting_server(struct sock *listener,
 	vsock_remove_pending(listener, pending);
 	vsock_enqueue_accept(listener, pending);
 
-	/* Callers of accept() will be be waiting on the listening socket, not
+	/* Callers of accept() will be waiting on the listening socket, not
 	 * the pending socket.
 	 */
 	listener->sk_data_ready(listener);
diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
index a45f7ffca8c5..169a8cf65b39 100644
--- a/net/vmw_vsock/vsock_loopback.c
+++ b/net/vmw_vsock/vsock_loopback.c
@@ -63,6 +63,8 @@ static int vsock_loopback_cancel_pkt(struct vsock_sock *vsk)
 	return 0;
 }
 
+static bool vsock_loopback_seqpacket_allow(u32 remote_cid);
+
 static struct virtio_transport loopback_transport = {
 	.transport = {
 		.module                   = THIS_MODULE,
@@ -89,6 +91,11 @@ static struct virtio_transport loopback_transport = {
 		.stream_is_active         = virtio_transport_stream_is_active,
 		.stream_allow             = virtio_transport_stream_allow,
 
+		.seqpacket_dequeue        = virtio_transport_seqpacket_dequeue,
+		.seqpacket_enqueue        = virtio_transport_seqpacket_enqueue,
+		.seqpacket_allow          = vsock_loopback_seqpacket_allow,
+		.seqpacket_has_data       = virtio_transport_seqpacket_has_data,
+
 		.notify_poll_in           = virtio_transport_notify_poll_in,
 		.notify_poll_out          = virtio_transport_notify_poll_out,
 		.notify_recv_init         = virtio_transport_notify_recv_init,
@@ -105,6 +112,11 @@ static struct virtio_transport loopback_transport = {
 	.send_pkt = vsock_loopback_send_pkt,
 };
 
+static bool vsock_loopback_seqpacket_allow(u32 remote_cid)
+{
+	return true;
+}
+
 static void vsock_loopback_work(struct work_struct *work)
 {
 	struct vsock_loopback *vsock =
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 1816899499ce..3583354a7d7f 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -366,7 +366,7 @@ static void x25_destroy_timer(struct timer_list *t)
 
 /*
  *	This is called from user mode and the timers. Thus it protects itself
- *	against interrupt users but doesn't worry about being called during
+ *	against interrupting users but doesn't worry about being called during
  *	work. Once it is removed from the queue no interrupt or bottom half
  *	will touch it and we are (fairly 8-) ) safe.
  *	Not static as it's used by the timer
diff --git a/net/x25/x25_forward.c b/net/x25/x25_forward.c
index d48ad6d29197..21b30b56e889 100644
--- a/net/x25/x25_forward.c
+++ b/net/x25/x25_forward.c
@@ -19,7 +19,6 @@ int x25_forward_call(struct x25_address *dest_addr, struct x25_neigh *from,
 {
 	struct x25_route *rt;
 	struct x25_neigh *neigh_new = NULL;
-	struct list_head *entry;
 	struct x25_forward *x25_frwd, *new_frwd;
 	struct sk_buff *skbn;
 	short same_lci = 0;
@@ -46,8 +45,7 @@ int x25_forward_call(struct x25_address *dest_addr, struct x25_neigh *from,
 	 * established LCI? It shouldn't happen, just in case..
 	 */
 	read_lock_bh(&x25_forward_list_lock);
-	list_for_each(entry, &x25_forward_list) {
-		x25_frwd = list_entry(entry, struct x25_forward, node);
+	list_for_each_entry(x25_frwd, &x25_forward_list, node) {
 		if (x25_frwd->lci == lci) {
 			pr_warn("call request for lci which is already registered!, transmitting but not registering new pair\n");
 			same_lci = 1;
@@ -92,15 +90,13 @@ out_no_route:
 int x25_forward_data(int lci, struct x25_neigh *from, struct sk_buff *skb) {
 
 	struct x25_forward *frwd;
-	struct list_head *entry;
 	struct net_device *peer = NULL;
 	struct x25_neigh *nb;
 	struct sk_buff *skbn;
 	int rc = 0;
 
 	read_lock_bh(&x25_forward_list_lock);
-	list_for_each(entry, &x25_forward_list) {
-		frwd = list_entry(entry, struct x25_forward, node);
+	list_for_each_entry(frwd, &x25_forward_list, node) {
 		if (frwd->lci == lci) {
 			/* The call is established, either side can send */
 			if (from->dev == frwd->dev1) {
diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c
index 57a81100c5da..5460b9146dd8 100644
--- a/net/x25/x25_link.c
+++ b/net/x25/x25_link.c
@@ -332,12 +332,9 @@ void x25_link_device_down(struct net_device *dev)
 struct x25_neigh *x25_get_neigh(struct net_device *dev)
 {
 	struct x25_neigh *nb, *use = NULL;
-	struct list_head *entry;
 
 	read_lock_bh(&x25_neigh_list_lock);
-	list_for_each(entry, &x25_neigh_list) {
-		nb = list_entry(entry, struct x25_neigh, node);
-
+	list_for_each_entry(nb, &x25_neigh_list, node) {
 		if (nb->dev == dev) {
 			use = nb;
 			break;
diff --git a/net/x25/x25_route.c b/net/x25/x25_route.c
index 9fbe4bb38d94..647f325ed867 100644
--- a/net/x25/x25_route.c
+++ b/net/x25/x25_route.c
@@ -27,14 +27,11 @@ static int x25_add_route(struct x25_address *address, unsigned int sigdigits,
 			 struct net_device *dev)
 {
 	struct x25_route *rt;
-	struct list_head *entry;
 	int rc = -EINVAL;
 
 	write_lock_bh(&x25_route_list_lock);
 
-	list_for_each(entry, &x25_route_list) {
-		rt = list_entry(entry, struct x25_route, node);
-
+	list_for_each_entry(rt, &x25_route_list, node) {
 		if (!memcmp(&rt->address, address, sigdigits) &&
 		    rt->sigdigits == sigdigits)
 			goto out;
@@ -78,14 +75,11 @@ static int x25_del_route(struct x25_address *address, unsigned int sigdigits,
 			 struct net_device *dev)
 {
 	struct x25_route *rt;
-	struct list_head *entry;
 	int rc = -EINVAL;
 
 	write_lock_bh(&x25_route_list_lock);
 
-	list_for_each(entry, &x25_route_list) {
-		rt = list_entry(entry, struct x25_route, node);
-
+	list_for_each_entry(rt, &x25_route_list, node) {
 		if (!memcmp(&rt->address, address, sigdigits) &&
 		    rt->sigdigits == sigdigits && rt->dev == dev) {
 			__x25_remove_route(rt);
@@ -141,13 +135,10 @@ struct net_device *x25_dev_get(char *devname)
 struct x25_route *x25_get_route(struct x25_address *addr)
 {
 	struct x25_route *rt, *use = NULL;
-	struct list_head *entry;
 
 	read_lock_bh(&x25_route_list_lock);
 
-	list_for_each(entry, &x25_route_list) {
-		rt = list_entry(entry, struct x25_route, node);
-
+	list_for_each_entry(rt, &x25_route_list, node) {
 		if (!memcmp(&rt->address, addr, rt->sigdigits)) {
 			if (!use)
 				use = rt;
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 56a28a686988..f01ef6bda390 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -27,7 +27,7 @@ static void xdp_umem_unpin_pages(struct xdp_umem *umem)
 {
 	unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true);
 
-	kfree(umem->pgs);
+	kvfree(umem->pgs);
 	umem->pgs = NULL;
 }
 
@@ -99,8 +99,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address)
 	long npgs;
 	int err;
 
-	umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs),
-			    GFP_KERNEL | __GFP_NOWARN);
+	umem->pgs = kvcalloc(umem->npgs, sizeof(*umem->pgs), GFP_KERNEL | __GFP_NOWARN);
 	if (!umem->pgs)
 		return -ENOMEM;
 
@@ -123,7 +122,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address)
 out_pin:
 	xdp_umem_unpin_pages(umem);
 out_pgs:
-	kfree(umem->pgs);
+	kvfree(umem->pgs);
 	umem->pgs = NULL;
 	return err;
 }
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 67b4ce504852..9df75ea4a567 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -226,7 +226,8 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key)
 
 static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
 {
-	return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem);
+	return __bpf_xdp_redirect_map(map, ifindex, flags, 0,
+				      __xsk_map_lookup_elem);
 }
 
 void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 45ceca4e2c70..520434ea966f 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -41,6 +41,7 @@ tprogs-y += test_map_in_map
 tprogs-y += per_socket_stats_example
 tprogs-y += xdp_redirect
 tprogs-y += xdp_redirect_map
+tprogs-y += xdp_redirect_map_multi
 tprogs-y += xdp_redirect_cpu
 tprogs-y += xdp_monitor
 tprogs-y += xdp_rxq_info
@@ -99,6 +100,7 @@ test_map_in_map-objs := test_map_in_map_user.o
 per_socket_stats_example-objs := cookie_uid_helper_example.o
 xdp_redirect-objs := xdp_redirect_user.o
 xdp_redirect_map-objs := xdp_redirect_map_user.o
+xdp_redirect_map_multi-objs := xdp_redirect_map_multi_user.o
 xdp_redirect_cpu-objs := xdp_redirect_cpu_user.o
 xdp_monitor-objs := xdp_monitor_user.o
 xdp_rxq_info-objs := xdp_rxq_info_user.o
@@ -160,6 +162,7 @@ always-y += tcp_tos_reflect_kern.o
 always-y += tcp_dumpstats_kern.o
 always-y += xdp_redirect_kern.o
 always-y += xdp_redirect_map_kern.o
+always-y += xdp_redirect_map_multi_kern.o
 always-y += xdp_redirect_cpu_kern.o
 always-y += xdp_monitor_kern.o
 always-y += xdp_rxq_info_kern.o
diff --git a/samples/bpf/ibumad_kern.c b/samples/bpf/ibumad_kern.c
index 26dcd4dde946..9b193231024a 100644
--- a/samples/bpf/ibumad_kern.c
+++ b/samples/bpf/ibumad_kern.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 
-/**
+/*
  * ibumad BPF sample kernel side
  *
  * This program is free software; you can redistribute it and/or
diff --git a/samples/bpf/ibumad_user.c b/samples/bpf/ibumad_user.c
index d83d8102f489..0746ca516097 100644
--- a/samples/bpf/ibumad_user.c
+++ b/samples/bpf/ibumad_user.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 
-/**
+/*
  * ibumad BPF sample user side
  *
  * This program is free software; you can redistribute it and/or
diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c
index a78025b0026b..c9a0ca8351fd 100644
--- a/samples/bpf/task_fd_query_user.c
+++ b/samples/bpf/task_fd_query_user.c
@@ -396,7 +396,7 @@ int main(int argc, char **argv)
 	 * on different systems with different compilers. The right way is
 	 * to parse the ELF file. We took a shortcut here.
 	 */
-	uprobe_file_offset = (__u64)main - (__u64)&__executable_start;
+	uprobe_file_offset = (unsigned long)main - (unsigned long)&__executable_start;
 	CHECK_AND_RET(test_nondebug_fs_probe("uprobe", (char *)argv[0],
 					     uprobe_file_offset, 0x0, false,
 					     BPF_FD_TYPE_UPROBE,
diff --git a/samples/bpf/xdp_fwd_user.c b/samples/bpf/xdp_fwd_user.c
index 74a4583d0d86..00061261a8da 100644
--- a/samples/bpf/xdp_fwd_user.c
+++ b/samples/bpf/xdp_fwd_user.c
@@ -67,6 +67,8 @@ static void usage(const char *prog)
 		"usage: %s [OPTS] interface-list\n"
 		"\nOPTS:\n"
 		"    -d    detach program\n"
+		"    -S    use skb-mode\n"
+		"    -F    force loading prog\n"
 		"    -D    direct table lookups (skip fib rules)\n",
 		prog);
 }
diff --git a/samples/bpf/xdp_redirect_map_multi_kern.c b/samples/bpf/xdp_redirect_map_multi_kern.c
new file mode 100644
index 000000000000..71aa23d1cb2b
--- /dev/null
+++ b/samples/bpf/xdp_redirect_map_multi_kern.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+#define KBUILD_MODNAME "foo"
+#include <uapi/linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP_HASH);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+	__uint(max_entries, 32);
+} forward_map_general SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP_HASH);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(struct bpf_devmap_val));
+	__uint(max_entries, 32);
+} forward_map_native SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, 1);
+} rxcnt SEC(".maps");
+
+/* map to store egress interfaces mac addresses, set the
+ * max_entries to 1 and extend it in user sapce prog.
+ */
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, __be64);
+	__uint(max_entries, 1);
+} mac_map SEC(".maps");
+
+static int xdp_redirect_map(struct xdp_md *ctx, void *forward_map)
+{
+	long *value;
+	u32 key = 0;
+
+	/* count packet in global counter */
+	value = bpf_map_lookup_elem(&rxcnt, &key);
+	if (value)
+		*value += 1;
+
+	return bpf_redirect_map(forward_map, key,
+				BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
+}
+
+SEC("xdp_redirect_general")
+int xdp_redirect_map_general(struct xdp_md *ctx)
+{
+	return xdp_redirect_map(ctx, &forward_map_general);
+}
+
+SEC("xdp_redirect_native")
+int xdp_redirect_map_native(struct xdp_md *ctx)
+{
+	return xdp_redirect_map(ctx, &forward_map_native);
+}
+
+SEC("xdp_devmap/map_prog")
+int xdp_devmap_prog(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	u32 key = ctx->egress_ifindex;
+	struct ethhdr *eth = data;
+	__be64 *mac;
+	u64 nh_off;
+
+	nh_off = sizeof(*eth);
+	if (data + nh_off > data_end)
+		return XDP_DROP;
+
+	mac = bpf_map_lookup_elem(&mac_map, &key);
+	if (mac)
+		__builtin_memcpy(eth->h_source, mac, ETH_ALEN);
+
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_redirect_map_multi_user.c b/samples/bpf/xdp_redirect_map_multi_user.c
new file mode 100644
index 000000000000..84cdbbed20b7
--- /dev/null
+++ b/samples/bpf/xdp_redirect_map_multi_user.c
@@ -0,0 +1,302 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/if_link.h>
+#include <assert.h>
+#include <errno.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <net/if.h>
+#include <unistd.h>
+#include <libgen.h>
+#include <sys/resource.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include "bpf_util.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#define MAX_IFACE_NUM 32
+
+static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static int ifaces[MAX_IFACE_NUM] = {};
+static int rxcnt_map_fd;
+
+static void int_exit(int sig)
+{
+	__u32 prog_id = 0;
+	int i;
+
+	for (i = 0; ifaces[i] > 0; i++) {
+		if (bpf_get_link_xdp_id(ifaces[i], &prog_id, xdp_flags)) {
+			printf("bpf_get_link_xdp_id failed\n");
+			exit(1);
+		}
+		if (prog_id)
+			bpf_set_link_xdp_fd(ifaces[i], -1, xdp_flags);
+	}
+
+	exit(0);
+}
+
+static void poll_stats(int interval)
+{
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	__u64 values[nr_cpus], prev[nr_cpus];
+
+	memset(prev, 0, sizeof(prev));
+
+	while (1) {
+		__u64 sum = 0;
+		__u32 key = 0;
+		int i;
+
+		sleep(interval);
+		assert(bpf_map_lookup_elem(rxcnt_map_fd, &key, values) == 0);
+		for (i = 0; i < nr_cpus; i++)
+			sum += (values[i] - prev[i]);
+		if (sum)
+			printf("Forwarding %10llu pkt/s\n", sum / interval);
+		memcpy(prev, values, sizeof(values));
+	}
+}
+
+static int get_mac_addr(unsigned int ifindex, void *mac_addr)
+{
+	char ifname[IF_NAMESIZE];
+	struct ifreq ifr;
+	int fd, ret = -1;
+
+	fd = socket(AF_INET, SOCK_DGRAM, 0);
+	if (fd < 0)
+		return ret;
+
+	if (!if_indextoname(ifindex, ifname))
+		goto err_out;
+
+	strcpy(ifr.ifr_name, ifname);
+
+	if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
+		goto err_out;
+
+	memcpy(mac_addr, ifr.ifr_hwaddr.sa_data, 6 * sizeof(char));
+	ret = 0;
+
+err_out:
+	close(fd);
+	return ret;
+}
+
+static int update_mac_map(struct bpf_object *obj)
+{
+	int i, ret = -1, mac_map_fd;
+	unsigned char mac_addr[6];
+	unsigned int ifindex;
+
+	mac_map_fd = bpf_object__find_map_fd_by_name(obj, "mac_map");
+	if (mac_map_fd < 0) {
+		printf("find mac map fd failed\n");
+		return ret;
+	}
+
+	for (i = 0; ifaces[i] > 0; i++) {
+		ifindex = ifaces[i];
+
+		ret = get_mac_addr(ifindex, mac_addr);
+		if (ret < 0) {
+			printf("get interface %d mac failed\n", ifindex);
+			return ret;
+		}
+
+		ret = bpf_map_update_elem(mac_map_fd, &ifindex, mac_addr, 0);
+		if (ret) {
+			perror("bpf_update_elem mac_map_fd");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static void usage(const char *prog)
+{
+	fprintf(stderr,
+		"usage: %s [OPTS] <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n"
+		"OPTS:\n"
+		"    -S    use skb-mode\n"
+		"    -N    enforce native mode\n"
+		"    -F    force loading prog\n"
+		"    -X    load xdp program on egress\n",
+		prog);
+}
+
+int main(int argc, char **argv)
+{
+	int i, ret, opt, forward_map_fd, max_ifindex = 0;
+	struct bpf_program *ingress_prog, *egress_prog;
+	int ingress_prog_fd, egress_prog_fd = 0;
+	struct bpf_devmap_val devmap_val;
+	bool attach_egress_prog = false;
+	char ifname[IF_NAMESIZE];
+	struct bpf_map *mac_map;
+	struct bpf_object *obj;
+	unsigned int ifindex;
+	char filename[256];
+
+	while ((opt = getopt(argc, argv, "SNFX")) != -1) {
+		switch (opt) {
+		case 'S':
+			xdp_flags |= XDP_FLAGS_SKB_MODE;
+			break;
+		case 'N':
+			/* default, set below */
+			break;
+		case 'F':
+			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+			break;
+		case 'X':
+			attach_egress_prog = true;
+			break;
+		default:
+			usage(basename(argv[0]));
+			return 1;
+		}
+	}
+
+	if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) {
+		xdp_flags |= XDP_FLAGS_DRV_MODE;
+	} else if (attach_egress_prog) {
+		printf("Load xdp program on egress with SKB mode not supported yet\n");
+		return 1;
+	}
+
+	if (optind == argc) {
+		printf("usage: %s <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n", argv[0]);
+		return 1;
+	}
+
+	printf("Get interfaces");
+	for (i = 0; i < MAX_IFACE_NUM && argv[optind + i]; i++) {
+		ifaces[i] = if_nametoindex(argv[optind + i]);
+		if (!ifaces[i])
+			ifaces[i] = strtoul(argv[optind + i], NULL, 0);
+		if (!if_indextoname(ifaces[i], ifname)) {
+			perror("Invalid interface name or i");
+			return 1;
+		}
+
+		/* Find the largest index number */
+		if (ifaces[i] > max_ifindex)
+			max_ifindex = ifaces[i];
+
+		printf(" %d", ifaces[i]);
+	}
+	printf("\n");
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	obj = bpf_object__open(filename);
+	if (libbpf_get_error(obj)) {
+		printf("ERROR: opening BPF object file failed\n");
+		obj = NULL;
+		goto err_out;
+	}
+
+	/* Reset the map size to max ifindex + 1 */
+	if (attach_egress_prog) {
+		mac_map = bpf_object__find_map_by_name(obj, "mac_map");
+		ret = bpf_map__resize(mac_map, max_ifindex + 1);
+		if (ret < 0) {
+			printf("ERROR: reset mac map size failed\n");
+			goto err_out;
+		}
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		printf("ERROR: loading BPF object file failed\n");
+		goto err_out;
+	}
+
+	if (xdp_flags & XDP_FLAGS_SKB_MODE) {
+		ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_general");
+		forward_map_fd = bpf_object__find_map_fd_by_name(obj, "forward_map_general");
+	} else {
+		ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_native");
+		forward_map_fd = bpf_object__find_map_fd_by_name(obj, "forward_map_native");
+	}
+	if (!ingress_prog || forward_map_fd < 0) {
+		printf("finding ingress_prog/forward_map in obj file failed\n");
+		goto err_out;
+	}
+
+	ingress_prog_fd = bpf_program__fd(ingress_prog);
+	if (ingress_prog_fd < 0) {
+		printf("find ingress_prog fd failed\n");
+		goto err_out;
+	}
+
+	rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt");
+	if (rxcnt_map_fd < 0) {
+		printf("bpf_object__find_map_fd_by_name failed\n");
+		goto err_out;
+	}
+
+	if (attach_egress_prog) {
+		/* Update mac_map with all egress interfaces' mac addr */
+		if (update_mac_map(obj) < 0) {
+			printf("Error: update mac map failed");
+			goto err_out;
+		}
+
+		/* Find egress prog fd */
+		egress_prog = bpf_object__find_program_by_name(obj, "xdp_devmap_prog");
+		if (!egress_prog) {
+			printf("finding egress_prog in obj file failed\n");
+			goto err_out;
+		}
+		egress_prog_fd = bpf_program__fd(egress_prog);
+		if (egress_prog_fd < 0) {
+			printf("find egress_prog fd failed\n");
+			goto err_out;
+		}
+	}
+
+	/* Remove attached program when program is interrupted or killed */
+	signal(SIGINT, int_exit);
+	signal(SIGTERM, int_exit);
+
+	/* Init forward multicast groups */
+	for (i = 0; ifaces[i] > 0; i++) {
+		ifindex = ifaces[i];
+
+		/* bind prog_fd to each interface */
+		ret = bpf_set_link_xdp_fd(ifindex, ingress_prog_fd, xdp_flags);
+		if (ret) {
+			printf("Set xdp fd failed on %d\n", ifindex);
+			goto err_out;
+		}
+
+		/* Add all the interfaces to forward group and attach
+		 * egress devmap programe if exist
+		 */
+		devmap_val.ifindex = ifindex;
+		devmap_val.bpf_prog.fd = egress_prog_fd;
+		ret = bpf_map_update_elem(forward_map_fd, &ifindex, &devmap_val, 0);
+		if (ret) {
+			perror("bpf_map_update_elem forward_map");
+			goto err_out;
+		}
+	}
+
+	poll_stats(2);
+
+	return 0;
+
+err_out:
+	return 1;
+}
diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c
index 706475e004cb..495e09897bd3 100644
--- a/samples/bpf/xdp_sample_pkts_user.c
+++ b/samples/bpf/xdp_sample_pkts_user.c
@@ -103,7 +103,8 @@ static void usage(const char *prog)
 	fprintf(stderr,
 		"%s: %s [OPTS] <ifname|ifindex>\n\n"
 		"OPTS:\n"
-		"    -F    force loading prog\n",
+		"    -F    force loading prog\n"
+		"    -S    use skb-mode\n",
 		__func__, prog);
 }
 
diff --git a/samples/pktgen/parameters.sh b/samples/pktgen/parameters.sh
index b4c1b371e4b8..81906f199454 100644
--- a/samples/pktgen/parameters.sh
+++ b/samples/pktgen/parameters.sh
@@ -11,6 +11,7 @@ function usage() {
     echo "  -d : (\$DEST_IP)   destination IP. CIDR (e.g. 198.18.0.0/15) is also allowed"
     echo "  -m : (\$DST_MAC)   destination MAC-addr"
     echo "  -p : (\$DST_PORT)  destination PORT range (e.g. 433-444) is also allowed"
+    echo "  -k : (\$UDP_CSUM)  enable UDP tx checksum"
     echo "  -t : (\$THREADS)   threads to start"
     echo "  -f : (\$F_THREAD)  index of first thread (zero indexed CPU number)"
     echo "  -c : (\$SKB_CLONE) SKB clones send before alloc new SKB"
@@ -26,7 +27,7 @@ function usage() {
 
 ##  --- Parse command line arguments / parameters ---
 ## echo "Commandline options:"
-while getopts "s:i:d:m:p:f:t:c:n:b:w:vxh6a" option; do
+while getopts "s:i:d:m:p:f:t:c:n:b:w:vxh6ak" option; do
     case $option in
         i) # interface
           export DEV=$OPTARG
@@ -88,6 +89,10 @@ while getopts "s:i:d:m:p:f:t:c:n:b:w:vxh6a" option; do
           export APPEND=yes
           info "Append mode: APPEND=$APPEND"
           ;;
+        k)
+          export UDP_CSUM=yes
+          info "UDP tx checksum: UDP_CSUM=$UDP_CSUM"
+          ;;
         h|?|*)
           usage;
           err 2 "[ERROR] Unknown parameters!!!"
diff --git a/samples/pktgen/pktgen_sample01_simple.sh b/samples/pktgen/pktgen_sample01_simple.sh
index a09f3422fbcc..246cfe02bb82 100755
--- a/samples/pktgen/pktgen_sample01_simple.sh
+++ b/samples/pktgen/pktgen_sample01_simple.sh
@@ -72,6 +72,8 @@ if [ -n "$DST_PORT" ]; then
     pg_set $DEV "udp_dst_max $UDP_DST_MAX"
 fi
 
+[ ! -z "$UDP_CSUM" ] && pg_set $dev "flag UDPCSUM"
+
 # Setup random UDP port src range
 pg_set $DEV "flag UDPSRC_RND"
 pg_set $DEV "udp_src_min $UDP_SRC_MIN"
diff --git a/samples/pktgen/pktgen_sample02_multiqueue.sh b/samples/pktgen/pktgen_sample02_multiqueue.sh
index acae8ede0d6c..c6af3d9d5171 100755
--- a/samples/pktgen/pktgen_sample02_multiqueue.sh
+++ b/samples/pktgen/pktgen_sample02_multiqueue.sh
@@ -75,6 +75,8 @@ for ((thread = $F_THREAD; thread <= $L_THREAD; thread++)); do
 	pg_set $dev "udp_dst_max $UDP_DST_MAX"
     fi
 
+    [ ! -z "$UDP_CSUM" ] && pg_set $dev "flag UDPCSUM"
+
     # Setup random UDP port src range
     pg_set $dev "flag UDPSRC_RND"
     pg_set $dev "udp_src_min $UDP_SRC_MIN"
diff --git a/samples/pktgen/pktgen_sample03_burst_single_flow.sh b/samples/pktgen/pktgen_sample03_burst_single_flow.sh
index 5adcf954de73..ab87de440277 100755
--- a/samples/pktgen/pktgen_sample03_burst_single_flow.sh
+++ b/samples/pktgen/pktgen_sample03_burst_single_flow.sh
@@ -73,6 +73,8 @@ for ((thread = $F_THREAD; thread <= $L_THREAD; thread++)); do
 	pg_set $dev "udp_dst_max $UDP_DST_MAX"
     fi
 
+    [ ! -z "$UDP_CSUM" ] && pg_set $dev "flag UDPCSUM"
+
     # Setup burst, for easy testing -b 0 disable bursting
     # (internally in pktgen default and minimum burst=1)
     if [[ ${BURST} -ne 0 ]]; then
diff --git a/samples/pktgen/pktgen_sample04_many_flows.sh b/samples/pktgen/pktgen_sample04_many_flows.sh
index ddce876635aa..56c5f5af350f 100755
--- a/samples/pktgen/pktgen_sample04_many_flows.sh
+++ b/samples/pktgen/pktgen_sample04_many_flows.sh
@@ -72,6 +72,8 @@ for ((thread = $F_THREAD; thread <= $L_THREAD; thread++)); do
 	pg_set $dev "udp_dst_max $UDP_DST_MAX"
     fi
 
+    [ ! -z "$UDP_CSUM" ] && pg_set $dev "flag UDPCSUM"
+
     # Randomize source IP-addresses
     pg_set $dev "flag IPSRC_RND"
     pg_set $dev "src_min $SRC_MIN"
diff --git a/samples/pktgen/pktgen_sample05_flow_per_thread.sh b/samples/pktgen/pktgen_sample05_flow_per_thread.sh
index 4a65fe2fcee9..6e0effabca59 100755
--- a/samples/pktgen/pktgen_sample05_flow_per_thread.sh
+++ b/samples/pktgen/pktgen_sample05_flow_per_thread.sh
@@ -62,6 +62,8 @@ for ((thread = $F_THREAD; thread <= $L_THREAD; thread++)); do
 	pg_set $dev "udp_dst_max $UDP_DST_MAX"
     fi
 
+    [ ! -z "$UDP_CSUM" ] && pg_set $dev "flag UDPCSUM"
+
     # Setup source IP-addresses based on thread number
     pg_set $dev "src_min 198.18.$((thread+1)).1"
     pg_set $dev "src_max 198.18.$((thread+1)).1"
diff --git a/samples/pktgen/pktgen_sample06_numa_awared_queue_irq_affinity.sh b/samples/pktgen/pktgen_sample06_numa_awared_queue_irq_affinity.sh
index 10f1da571f40..7c27923083a6 100755
--- a/samples/pktgen/pktgen_sample06_numa_awared_queue_irq_affinity.sh
+++ b/samples/pktgen/pktgen_sample06_numa_awared_queue_irq_affinity.sh
@@ -92,6 +92,8 @@ for ((i = 0; i < $THREADS; i++)); do
 	pg_set $dev "udp_dst_max $UDP_DST_MAX"
     fi
 
+    [ ! -z "$UDP_CSUM" ] && pg_set $dev "flag UDPCSUM"
+
     # Setup random UDP port src range
     pg_set $dev "flag UDPSRC_RND"
     pg_set $dev "udp_src_min $UDP_SRC_MIN"
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index b3073ae84018..d73232be1e99 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -136,7 +136,7 @@ endif
 
 BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool
 
-BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o)
+BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o xlated_dumper.o btf_dumper.o disasm.o)
 OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
 
 VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux)				\
@@ -180,6 +180,9 @@ endif
 
 CFLAGS += $(if $(BUILD_BPF_SKELS),,-DBPFTOOL_WITHOUT_SKELETONS)
 
+$(BOOTSTRAP_OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
+	$(QUIET_CC)$(HOSTCC) $(CFLAGS) -c -MMD -o $@ $<
+
 $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
 	$(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $<
 
diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index 31ade77f5ef8..1d71ff8c52fa 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -18,6 +18,7 @@
 #include <sys/stat.h>
 #include <sys/mman.h>
 #include <bpf/btf.h>
+#include <bpf/bpf_gen_internal.h>
 
 #include "json_writer.h"
 #include "main.h"
@@ -106,8 +107,10 @@ static int codegen_datasec_def(struct bpf_object *obj,
 
 	if (strcmp(sec_name, ".data") == 0) {
 		sec_ident = "data";
+		strip_mods = true;
 	} else if (strcmp(sec_name, ".bss") == 0) {
 		sec_ident = "bss";
+		strip_mods = true;
 	} else if (strcmp(sec_name, ".rodata") == 0) {
 		sec_ident = "rodata";
 		strip_mods = true;
@@ -129,6 +132,10 @@ static int codegen_datasec_def(struct bpf_object *obj,
 		int need_off = sec_var->offset, align_off, align;
 		__u32 var_type_id = var->type;
 
+		/* static variables are not exposed through BPF skeleton */
+		if (btf_var(var)->linkage == BTF_VAR_STATIC)
+			continue;
+
 		if (off > need_off) {
 			p_err("Something is wrong for %s's variable #%d: need offset %d, already at %d.\n",
 			      sec_name, i, need_off, off);
@@ -268,6 +275,327 @@ static void codegen(const char *template, ...)
 	free(s);
 }
 
+static void print_hex(const char *data, int data_sz)
+{
+	int i, len;
+
+	for (i = 0, len = 0; i < data_sz; i++) {
+		int w = data[i] ? 4 : 2;
+
+		len += w;
+		if (len > 78) {
+			printf("\\\n");
+			len = w;
+		}
+		if (!data[i])
+			printf("\\0");
+		else
+			printf("\\x%02x", (unsigned char)data[i]);
+	}
+}
+
+static size_t bpf_map_mmap_sz(const struct bpf_map *map)
+{
+	long page_sz = sysconf(_SC_PAGE_SIZE);
+	size_t map_sz;
+
+	map_sz = (size_t)roundup(bpf_map__value_size(map), 8) * bpf_map__max_entries(map);
+	map_sz = roundup(map_sz, page_sz);
+	return map_sz;
+}
+
+static void codegen_attach_detach(struct bpf_object *obj, const char *obj_name)
+{
+	struct bpf_program *prog;
+
+	bpf_object__for_each_program(prog, obj) {
+		const char *tp_name;
+
+		codegen("\
+			\n\
+			\n\
+			static inline int					    \n\
+			%1$s__%2$s__attach(struct %1$s *skel)			    \n\
+			{							    \n\
+				int prog_fd = skel->progs.%2$s.prog_fd;		    \n\
+			", obj_name, bpf_program__name(prog));
+
+		switch (bpf_program__get_type(prog)) {
+		case BPF_PROG_TYPE_RAW_TRACEPOINT:
+			tp_name = strchr(bpf_program__section_name(prog), '/') + 1;
+			printf("\tint fd = bpf_raw_tracepoint_open(\"%s\", prog_fd);\n", tp_name);
+			break;
+		case BPF_PROG_TYPE_TRACING:
+			printf("\tint fd = bpf_raw_tracepoint_open(NULL, prog_fd);\n");
+			break;
+		default:
+			printf("\tint fd = ((void)prog_fd, 0); /* auto-attach not supported */\n");
+			break;
+		}
+		codegen("\
+			\n\
+										    \n\
+				if (fd > 0)					    \n\
+					skel->links.%1$s_fd = fd;		    \n\
+				return fd;					    \n\
+			}							    \n\
+			", bpf_program__name(prog));
+	}
+
+	codegen("\
+		\n\
+									    \n\
+		static inline int					    \n\
+		%1$s__attach(struct %1$s *skel)				    \n\
+		{							    \n\
+			int ret = 0;					    \n\
+									    \n\
+		", obj_name);
+
+	bpf_object__for_each_program(prog, obj) {
+		codegen("\
+			\n\
+				ret = ret < 0 ? ret : %1$s__%2$s__attach(skel);   \n\
+			", obj_name, bpf_program__name(prog));
+	}
+
+	codegen("\
+		\n\
+			return ret < 0 ? ret : 0;			    \n\
+		}							    \n\
+									    \n\
+		static inline void					    \n\
+		%1$s__detach(struct %1$s *skel)				    \n\
+		{							    \n\
+		", obj_name);
+
+	bpf_object__for_each_program(prog, obj) {
+		codegen("\
+			\n\
+				skel_closenz(skel->links.%1$s_fd);	    \n\
+			", bpf_program__name(prog));
+	}
+
+	codegen("\
+		\n\
+		}							    \n\
+		");
+}
+
+static void codegen_destroy(struct bpf_object *obj, const char *obj_name)
+{
+	struct bpf_program *prog;
+	struct bpf_map *map;
+
+	codegen("\
+		\n\
+		static void						    \n\
+		%1$s__destroy(struct %1$s *skel)			    \n\
+		{							    \n\
+			if (!skel)					    \n\
+				return;					    \n\
+			%1$s__detach(skel);				    \n\
+		",
+		obj_name);
+
+	bpf_object__for_each_program(prog, obj) {
+		codegen("\
+			\n\
+				skel_closenz(skel->progs.%1$s.prog_fd);	    \n\
+			", bpf_program__name(prog));
+	}
+
+	bpf_object__for_each_map(map, obj) {
+		const char * ident;
+
+		ident = get_map_ident(map);
+		if (!ident)
+			continue;
+		if (bpf_map__is_internal(map) &&
+		    (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
+			printf("\tmunmap(skel->%1$s, %2$zd);\n",
+			       ident, bpf_map_mmap_sz(map));
+		codegen("\
+			\n\
+				skel_closenz(skel->maps.%1$s.map_fd);	    \n\
+			", ident);
+	}
+	codegen("\
+		\n\
+			free(skel);					    \n\
+		}							    \n\
+		",
+		obj_name);
+}
+
+static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *header_guard)
+{
+	struct bpf_object_load_attr load_attr = {};
+	DECLARE_LIBBPF_OPTS(gen_loader_opts, opts);
+	struct bpf_map *map;
+	int err = 0;
+
+	err = bpf_object__gen_loader(obj, &opts);
+	if (err)
+		return err;
+
+	load_attr.obj = obj;
+	if (verifier_logs)
+		/* log_level1 + log_level2 + stats, but not stable UAPI */
+		load_attr.log_level = 1 + 2 + 4;
+
+	err = bpf_object__load_xattr(&load_attr);
+	if (err) {
+		p_err("failed to load object file");
+		goto out;
+	}
+	/* If there was no error during load then gen_loader_opts
+	 * are populated with the loader program.
+	 */
+
+	/* finish generating 'struct skel' */
+	codegen("\
+		\n\
+		};							    \n\
+		", obj_name);
+
+
+	codegen_attach_detach(obj, obj_name);
+
+	codegen_destroy(obj, obj_name);
+
+	codegen("\
+		\n\
+		static inline struct %1$s *				    \n\
+		%1$s__open(void)					    \n\
+		{							    \n\
+			struct %1$s *skel;				    \n\
+									    \n\
+			skel = calloc(sizeof(*skel), 1);		    \n\
+			if (!skel)					    \n\
+				goto cleanup;				    \n\
+			skel->ctx.sz = (void *)&skel->links - (void *)skel; \n\
+		",
+		obj_name, opts.data_sz);
+	bpf_object__for_each_map(map, obj) {
+		const char *ident;
+		const void *mmap_data = NULL;
+		size_t mmap_size = 0;
+
+		ident = get_map_ident(map);
+		if (!ident)
+			continue;
+
+		if (!bpf_map__is_internal(map) ||
+		    !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
+			continue;
+
+		codegen("\
+			\n\
+				skel->%1$s =					 \n\
+					mmap(NULL, %2$zd, PROT_READ | PROT_WRITE,\n\
+					     MAP_SHARED | MAP_ANONYMOUS, -1, 0); \n\
+				if (skel->%1$s == (void *) -1)			 \n\
+					goto cleanup;				 \n\
+				memcpy(skel->%1$s, (void *)\"\\			 \n\
+			", ident, bpf_map_mmap_sz(map));
+		mmap_data = bpf_map__initial_value(map, &mmap_size);
+		print_hex(mmap_data, mmap_size);
+		printf("\", %2$zd);\n"
+		       "\tskel->maps.%1$s.initial_value = (__u64)(long)skel->%1$s;\n",
+		       ident, mmap_size);
+	}
+	codegen("\
+		\n\
+			return skel;					    \n\
+		cleanup:						    \n\
+			%1$s__destroy(skel);				    \n\
+			return NULL;					    \n\
+		}							    \n\
+									    \n\
+		static inline int					    \n\
+		%1$s__load(struct %1$s *skel)				    \n\
+		{							    \n\
+			struct bpf_load_and_run_opts opts = {};		    \n\
+			int err;					    \n\
+									    \n\
+			opts.ctx = (struct bpf_loader_ctx *)skel;	    \n\
+			opts.data_sz = %2$d;				    \n\
+			opts.data = (void *)\"\\			    \n\
+		",
+		obj_name, opts.data_sz);
+	print_hex(opts.data, opts.data_sz);
+	codegen("\
+		\n\
+		\";							    \n\
+		");
+
+	codegen("\
+		\n\
+			opts.insns_sz = %d;				    \n\
+			opts.insns = (void *)\"\\			    \n\
+		",
+		opts.insns_sz);
+	print_hex(opts.insns, opts.insns_sz);
+	codegen("\
+		\n\
+		\";							    \n\
+			err = bpf_load_and_run(&opts);			    \n\
+			if (err < 0)					    \n\
+				return err;				    \n\
+		", obj_name);
+	bpf_object__for_each_map(map, obj) {
+		const char *ident, *mmap_flags;
+
+		ident = get_map_ident(map);
+		if (!ident)
+			continue;
+
+		if (!bpf_map__is_internal(map) ||
+		    !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
+			continue;
+		if (bpf_map__def(map)->map_flags & BPF_F_RDONLY_PROG)
+			mmap_flags = "PROT_READ";
+		else
+			mmap_flags = "PROT_READ | PROT_WRITE";
+
+		printf("\tskel->%1$s =\n"
+		       "\t\tmmap(skel->%1$s, %2$zd, %3$s, MAP_SHARED | MAP_FIXED,\n"
+		       "\t\t\tskel->maps.%1$s.map_fd, 0);\n",
+		       ident, bpf_map_mmap_sz(map), mmap_flags);
+	}
+	codegen("\
+		\n\
+			return 0;					    \n\
+		}							    \n\
+									    \n\
+		static inline struct %1$s *				    \n\
+		%1$s__open_and_load(void)				    \n\
+		{							    \n\
+			struct %1$s *skel;				    \n\
+									    \n\
+			skel = %1$s__open();				    \n\
+			if (!skel)					    \n\
+				return NULL;				    \n\
+			if (%1$s__load(skel)) {				    \n\
+				%1$s__destroy(skel);			    \n\
+				return NULL;				    \n\
+			}						    \n\
+			return skel;					    \n\
+		}							    \n\
+		", obj_name);
+
+	codegen("\
+		\n\
+									    \n\
+		#endif /* %s */						    \n\
+		",
+		header_guard);
+	err = 0;
+out:
+	return err;
+}
+
 static int do_skeleton(int argc, char **argv)
 {
 	char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")];
@@ -277,7 +605,7 @@ static int do_skeleton(int argc, char **argv)
 	struct bpf_object *obj = NULL;
 	const char *file, *ident;
 	struct bpf_program *prog;
-	int fd, len, err = -1;
+	int fd, err = -1;
 	struct bpf_map *map;
 	struct btf *btf;
 	struct stat st;
@@ -359,7 +687,25 @@ static int do_skeleton(int argc, char **argv)
 	}
 
 	get_header_guard(header_guard, obj_name);
-	codegen("\
+	if (use_loader) {
+		codegen("\
+		\n\
+		/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */   \n\
+		/* THIS FILE IS AUTOGENERATED! */			    \n\
+		#ifndef %2$s						    \n\
+		#define %2$s						    \n\
+									    \n\
+		#include <stdlib.h>					    \n\
+		#include <bpf/bpf.h>					    \n\
+		#include <bpf/skel_internal.h>				    \n\
+									    \n\
+		struct %1$s {						    \n\
+			struct bpf_loader_ctx ctx;			    \n\
+		",
+		obj_name, header_guard
+		);
+	} else {
+		codegen("\
 		\n\
 		/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */   \n\
 									    \n\
@@ -367,6 +713,7 @@ static int do_skeleton(int argc, char **argv)
 		#ifndef %2$s						    \n\
 		#define %2$s						    \n\
 									    \n\
+		#include <errno.h>					    \n\
 		#include <stdlib.h>					    \n\
 		#include <bpf/libbpf.h>					    \n\
 									    \n\
@@ -375,7 +722,8 @@ static int do_skeleton(int argc, char **argv)
 			struct bpf_object *obj;				    \n\
 		",
 		obj_name, header_guard
-	);
+		);
+	}
 
 	if (map_cnt) {
 		printf("\tstruct {\n");
@@ -383,7 +731,10 @@ static int do_skeleton(int argc, char **argv)
 			ident = get_map_ident(map);
 			if (!ident)
 				continue;
-			printf("\t\tstruct bpf_map *%s;\n", ident);
+			if (use_loader)
+				printf("\t\tstruct bpf_map_desc %s;\n", ident);
+			else
+				printf("\t\tstruct bpf_map *%s;\n", ident);
 		}
 		printf("\t} maps;\n");
 	}
@@ -391,14 +742,22 @@ static int do_skeleton(int argc, char **argv)
 	if (prog_cnt) {
 		printf("\tstruct {\n");
 		bpf_object__for_each_program(prog, obj) {
-			printf("\t\tstruct bpf_program *%s;\n",
-			       bpf_program__name(prog));
+			if (use_loader)
+				printf("\t\tstruct bpf_prog_desc %s;\n",
+				       bpf_program__name(prog));
+			else
+				printf("\t\tstruct bpf_program *%s;\n",
+				       bpf_program__name(prog));
 		}
 		printf("\t} progs;\n");
 		printf("\tstruct {\n");
 		bpf_object__for_each_program(prog, obj) {
-			printf("\t\tstruct bpf_link *%s;\n",
-			       bpf_program__name(prog));
+			if (use_loader)
+				printf("\t\tint %s_fd;\n",
+				       bpf_program__name(prog));
+			else
+				printf("\t\tstruct bpf_link *%s;\n",
+				       bpf_program__name(prog));
 		}
 		printf("\t} links;\n");
 	}
@@ -409,6 +768,10 @@ static int do_skeleton(int argc, char **argv)
 		if (err)
 			goto out;
 	}
+	if (use_loader) {
+		err = gen_trace(obj, obj_name, header_guard);
+		goto out;
+	}
 
 	codegen("\
 		\n\
@@ -431,18 +794,23 @@ static int do_skeleton(int argc, char **argv)
 		%1$s__open_opts(const struct bpf_object_open_opts *opts)    \n\
 		{							    \n\
 			struct %1$s *obj;				    \n\
+			int err;					    \n\
 									    \n\
 			obj = (struct %1$s *)calloc(1, sizeof(*obj));	    \n\
-			if (!obj)					    \n\
+			if (!obj) {					    \n\
+				errno = ENOMEM;				    \n\
 				return NULL;				    \n\
-			if (%1$s__create_skeleton(obj))			    \n\
-				goto err;				    \n\
-			if (bpf_object__open_skeleton(obj->skeleton, opts)) \n\
-				goto err;				    \n\
+			}						    \n\
+									    \n\
+			err = %1$s__create_skeleton(obj);		    \n\
+			err = err ?: bpf_object__open_skeleton(obj->skeleton, opts);\n\
+			if (err)					    \n\
+				goto err_out;				    \n\
 									    \n\
 			return obj;					    \n\
-		err:							    \n\
+		err_out:						    \n\
 			%1$s__destroy(obj);				    \n\
+			errno = -err;					    \n\
 			return NULL;					    \n\
 		}							    \n\
 									    \n\
@@ -462,12 +830,15 @@ static int do_skeleton(int argc, char **argv)
 		%1$s__open_and_load(void)				    \n\
 		{							    \n\
 			struct %1$s *obj;				    \n\
+			int err;					    \n\
 									    \n\
 			obj = %1$s__open();				    \n\
 			if (!obj)					    \n\
 				return NULL;				    \n\
-			if (%1$s__load(obj)) {				    \n\
+			err = %1$s__load(obj);				    \n\
+			if (err) {					    \n\
 				%1$s__destroy(obj);			    \n\
+				errno = -err;				    \n\
 				return NULL;				    \n\
 			}						    \n\
 			return obj;					    \n\
@@ -498,7 +869,7 @@ static int do_skeleton(int argc, char **argv)
 									    \n\
 			s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\
 			if (!s)						    \n\
-				return -1;				    \n\
+				goto err;				    \n\
 			obj->skeleton = s;				    \n\
 									    \n\
 			s->sz = sizeof(*s);				    \n\
@@ -578,19 +949,7 @@ static int do_skeleton(int argc, char **argv)
 		file_sz);
 
 	/* embed contents of BPF object file */
-	for (i = 0, len = 0; i < file_sz; i++) {
-		int w = obj_data[i] ? 4 : 2;
-
-		len += w;
-		if (len > 78) {
-			printf("\\\n");
-			len = w;
-		}
-		if (!obj_data[i])
-			printf("\\0");
-		else
-			printf("\\x%02x", (unsigned char)obj_data[i]);
-	}
+	print_hex(obj_data, file_sz);
 
 	codegen("\
 		\n\
@@ -599,7 +958,7 @@ static int do_skeleton(int argc, char **argv)
 			return 0;					    \n\
 		err:							    \n\
 			bpf_object__destroy_skeleton(s);		    \n\
-			return -1;					    \n\
+			return -ENOMEM;					    \n\
 		}							    \n\
 									    \n\
 		#endif /* %s */						    \n\
@@ -636,7 +995,7 @@ static int do_object(int argc, char **argv)
 	while (argc) {
 		file = GET_ARG();
 
-		err = bpf_linker__add_file(linker, file);
+		err = bpf_linker__add_file(linker, file, NULL);
 		if (err) {
 			p_err("failed to link '%s': %s (%d)", file, strerror(err), err);
 			goto out;
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index d9afb730136a..3ddfd4843738 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -29,6 +29,7 @@ bool show_pinned;
 bool block_mount;
 bool verifier_logs;
 bool relaxed_maps;
+bool use_loader;
 struct btf *base_btf;
 struct pinned_obj_table prog_table;
 struct pinned_obj_table map_table;
@@ -340,8 +341,10 @@ static int do_batch(int argc, char **argv)
 		n_argc = make_args(buf, n_argv, BATCH_ARG_NB_MAX, lines);
 		if (!n_argc)
 			continue;
-		if (n_argc < 0)
+		if (n_argc < 0) {
+			err = n_argc;
 			goto err_close;
+		}
 
 		if (json_output) {
 			jsonw_start_object(json_wtr);
@@ -392,6 +395,7 @@ int main(int argc, char **argv)
 		{ "mapcompat",	no_argument,	NULL,	'm' },
 		{ "nomount",	no_argument,	NULL,	'n' },
 		{ "debug",	no_argument,	NULL,	'd' },
+		{ "use-loader",	no_argument,	NULL,	'L' },
 		{ "base-btf",	required_argument, NULL, 'B' },
 		{ 0 }
 	};
@@ -409,7 +413,7 @@ int main(int argc, char **argv)
 	hash_init(link_table.table);
 
 	opterr = 0;
-	while ((opt = getopt_long(argc, argv, "VhpjfmndB:",
+	while ((opt = getopt_long(argc, argv, "VhpjfLmndB:",
 				  options, NULL)) >= 0) {
 		switch (opt) {
 		case 'V':
@@ -452,6 +456,9 @@ int main(int argc, char **argv)
 				return -1;
 			}
 			break;
+		case 'L':
+			use_loader = true;
+			break;
 		default:
 			p_err("unrecognized option '%s'", argv[optind - 1]);
 			if (json_output)
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 76e91641262b..c1cf29798b99 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -90,6 +90,7 @@ extern bool show_pids;
 extern bool block_mount;
 extern bool verifier_logs;
 extern bool relaxed_maps;
+extern bool use_loader;
 extern struct btf *base_btf;
 extern struct pinned_obj_table prog_table;
 extern struct pinned_obj_table map_table;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index da4846c9856a..cc48726740ad 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -16,6 +16,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/syscall.h>
+#include <dirent.h>
 
 #include <linux/err.h>
 #include <linux/perf_event.h>
@@ -24,6 +25,8 @@
 #include <bpf/bpf.h>
 #include <bpf/btf.h>
 #include <bpf/libbpf.h>
+#include <bpf/bpf_gen_internal.h>
+#include <bpf/skel_internal.h>
 
 #include "cfg.h"
 #include "main.h"
@@ -1499,7 +1502,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 	set_max_rlimit();
 
 	obj = bpf_object__open_file(file, &open_opts);
-	if (IS_ERR_OR_NULL(obj)) {
+	if (libbpf_get_error(obj)) {
 		p_err("failed to open object file");
 		goto err_free_reuse_maps;
 	}
@@ -1645,8 +1648,110 @@ err_free_reuse_maps:
 	return -1;
 }
 
+static int count_open_fds(void)
+{
+	DIR *dp = opendir("/proc/self/fd");
+	struct dirent *de;
+	int cnt = -3;
+
+	if (!dp)
+		return -1;
+
+	while ((de = readdir(dp)))
+		cnt++;
+
+	closedir(dp);
+	return cnt;
+}
+
+static int try_loader(struct gen_loader_opts *gen)
+{
+	struct bpf_load_and_run_opts opts = {};
+	struct bpf_loader_ctx *ctx;
+	int ctx_sz = sizeof(*ctx) + 64 * max(sizeof(struct bpf_map_desc),
+					     sizeof(struct bpf_prog_desc));
+	int log_buf_sz = (1u << 24) - 1;
+	int err, fds_before, fd_delta;
+	char *log_buf;
+
+	ctx = alloca(ctx_sz);
+	memset(ctx, 0, ctx_sz);
+	ctx->sz = ctx_sz;
+	ctx->log_level = 1;
+	ctx->log_size = log_buf_sz;
+	log_buf = malloc(log_buf_sz);
+	if (!log_buf)
+		return -ENOMEM;
+	ctx->log_buf = (long) log_buf;
+	opts.ctx = ctx;
+	opts.data = gen->data;
+	opts.data_sz = gen->data_sz;
+	opts.insns = gen->insns;
+	opts.insns_sz = gen->insns_sz;
+	fds_before = count_open_fds();
+	err = bpf_load_and_run(&opts);
+	fd_delta = count_open_fds() - fds_before;
+	if (err < 0) {
+		fprintf(stderr, "err %d\n%s\n%s", err, opts.errstr, log_buf);
+		if (fd_delta)
+			fprintf(stderr, "loader prog leaked %d FDs\n",
+				fd_delta);
+	}
+	free(log_buf);
+	return err;
+}
+
+static int do_loader(int argc, char **argv)
+{
+	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts);
+	DECLARE_LIBBPF_OPTS(gen_loader_opts, gen);
+	struct bpf_object_load_attr load_attr = {};
+	struct bpf_object *obj;
+	const char *file;
+	int err = 0;
+
+	if (!REQ_ARGS(1))
+		return -1;
+	file = GET_ARG();
+
+	obj = bpf_object__open_file(file, &open_opts);
+	if (libbpf_get_error(obj)) {
+		p_err("failed to open object file");
+		goto err_close_obj;
+	}
+
+	err = bpf_object__gen_loader(obj, &gen);
+	if (err)
+		goto err_close_obj;
+
+	load_attr.obj = obj;
+	if (verifier_logs)
+		/* log_level1 + log_level2 + stats, but not stable UAPI */
+		load_attr.log_level = 1 + 2 + 4;
+
+	err = bpf_object__load_xattr(&load_attr);
+	if (err) {
+		p_err("failed to load object file");
+		goto err_close_obj;
+	}
+
+	if (verifier_logs) {
+		struct dump_data dd = {};
+
+		kernel_syms_load(&dd);
+		dump_xlated_plain(&dd, (void *)gen.insns, gen.insns_sz, false, false);
+		kernel_syms_destroy(&dd);
+	}
+	err = try_loader(&gen);
+err_close_obj:
+	bpf_object__close(obj);
+	return err;
+}
+
 static int do_load(int argc, char **argv)
 {
+	if (use_loader)
+		return do_loader(argc, argv);
 	return load_with_options(argc, argv, true);
 }
 
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index 6fc3e6f7f40c..f1f32e21d5cd 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -196,6 +196,9 @@ static const char *print_imm(void *private_data,
 	else if (insn->src_reg == BPF_PSEUDO_MAP_VALUE)
 		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
 			 "map[id:%u][0]+%u", insn->imm, (insn + 1)->imm);
+	else if (insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE)
+		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
+			 "map[idx:%u]+%u", insn->imm, (insn + 1)->imm);
 	else if (insn->src_reg == BPF_PSEUDO_FUNC)
 		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
 			 "subprog[%+d]", insn->imm);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index ec6d85a81744..bf9252c7381e 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -527,6 +527,15 @@ union bpf_iter_link_info {
  *		Look up an element with the given *key* in the map referred to
  *		by the file descriptor *fd*, and if found, delete the element.
  *
+ *		For **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map
+ *		types, the *flags* argument needs to be set to 0, but for other
+ *		map types, it may be specified as:
+ *
+ *		**BPF_F_LOCK**
+ *			Look up and delete the value of a spin-locked map
+ *			without returning the lock. This must be specified if
+ *			the elements contain a spinlock.
+ *
  *		The **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map types
  *		implement this command as a "pop" operation, deleting the top
  *		element rather than one corresponding to *key*.
@@ -536,6 +545,10 @@ union bpf_iter_link_info {
  *		This command is only valid for the following map types:
  *		* **BPF_MAP_TYPE_QUEUE**
  *		* **BPF_MAP_TYPE_STACK**
+ *		* **BPF_MAP_TYPE_HASH**
+ *		* **BPF_MAP_TYPE_PERCPU_HASH**
+ *		* **BPF_MAP_TYPE_LRU_HASH**
+ *		* **BPF_MAP_TYPE_LRU_PERCPU_HASH**
  *
  *	Return
  *		Returns zero on success. On error, -1 is returned and *errno*
@@ -837,6 +850,7 @@ enum bpf_cmd {
 	BPF_PROG_ATTACH,
 	BPF_PROG_DETACH,
 	BPF_PROG_TEST_RUN,
+	BPF_PROG_RUN = BPF_PROG_TEST_RUN,
 	BPF_PROG_GET_NEXT_ID,
 	BPF_MAP_GET_NEXT_ID,
 	BPF_PROG_GET_FD_BY_ID,
@@ -937,6 +951,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_EXT,
 	BPF_PROG_TYPE_LSM,
 	BPF_PROG_TYPE_SK_LOOKUP,
+	BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
 };
 
 enum bpf_attach_type {
@@ -979,6 +994,8 @@ enum bpf_attach_type {
 	BPF_SK_LOOKUP,
 	BPF_XDP,
 	BPF_SK_SKB_VERDICT,
+	BPF_SK_REUSEPORT_SELECT,
+	BPF_SK_REUSEPORT_SELECT_OR_MIGRATE,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1097,8 +1114,8 @@ enum bpf_link_type {
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * the following extensions:
  *
- * insn[0].src_reg:  BPF_PSEUDO_MAP_FD
- * insn[0].imm:      map fd
+ * insn[0].src_reg:  BPF_PSEUDO_MAP_[FD|IDX]
+ * insn[0].imm:      map fd or fd_idx
  * insn[1].imm:      0
  * insn[0].off:      0
  * insn[1].off:      0
@@ -1106,15 +1123,19 @@ enum bpf_link_type {
  * verifier type:    CONST_PTR_TO_MAP
  */
 #define BPF_PSEUDO_MAP_FD	1
-/* insn[0].src_reg:  BPF_PSEUDO_MAP_VALUE
- * insn[0].imm:      map fd
+#define BPF_PSEUDO_MAP_IDX	5
+
+/* insn[0].src_reg:  BPF_PSEUDO_MAP_[IDX_]VALUE
+ * insn[0].imm:      map fd or fd_idx
  * insn[1].imm:      offset into value
  * insn[0].off:      0
  * insn[1].off:      0
  * ldimm64 rewrite:  address of map[0]+offset
  * verifier type:    PTR_TO_MAP_VALUE
  */
-#define BPF_PSEUDO_MAP_VALUE	2
+#define BPF_PSEUDO_MAP_VALUE		2
+#define BPF_PSEUDO_MAP_IDX_VALUE	6
+
 /* insn[0].src_reg:  BPF_PSEUDO_BTF_ID
  * insn[0].imm:      kernel btd id of VAR
  * insn[1].imm:      0
@@ -1314,6 +1335,8 @@ union bpf_attr {
 			/* or valid module BTF object fd or 0 to attach to vmlinux */
 			__u32		attach_btf_obj_fd;
 		};
+		__u32		:32;		/* pad */
+		__aligned_u64	fd_array;	/* array of FDs */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -2534,8 +2557,12 @@ union bpf_attr {
  * 		The lower two bits of *flags* are used as the return code if
  * 		the map lookup fails. This is so that the return value can be
  * 		one of the XDP program return codes up to **XDP_TX**, as chosen
- * 		by the caller. Any higher bits in the *flags* argument must be
- * 		unset.
+ * 		by the caller. The higher bits of *flags* can be set to
+ * 		BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below.
+ *
+ * 		With BPF_F_BROADCAST the packet will be broadcasted to all the
+ * 		interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress
+ * 		interface will be excluded when do broadcasting.
  *
  * 		See also **bpf_redirect**\ (), which only supports redirecting
  * 		to an ifindex, but doesn't require a map to do so.
@@ -4735,6 +4762,24 @@ union bpf_attr {
  *		be zero-terminated except when **str_size** is 0.
  *
  *		Or **-EBUSY** if the per-CPU memory copy buffer is busy.
+ *
+ * long bpf_sys_bpf(u32 cmd, void *attr, u32 attr_size)
+ * 	Description
+ * 		Execute bpf syscall with given arguments.
+ * 	Return
+ * 		A syscall result.
+ *
+ * long bpf_btf_find_by_name_kind(char *name, int name_sz, u32 kind, int flags)
+ * 	Description
+ * 		Find BTF type with given name and kind in vmlinux BTF or in module's BTFs.
+ * 	Return
+ * 		Returns btf_id and btf_obj_fd in lower and upper 32 bits.
+ *
+ * long bpf_sys_close(u32 fd)
+ * 	Description
+ * 		Execute close syscall for given FD.
+ * 	Return
+ * 		A syscall result.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -4903,6 +4948,9 @@ union bpf_attr {
 	FN(check_mtu),			\
 	FN(for_each_map_elem),		\
 	FN(snprintf),			\
+	FN(sys_bpf),			\
+	FN(btf_find_by_name_kind),	\
+	FN(sys_close),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5080,6 +5128,12 @@ enum {
 	BPF_F_BPRM_SECUREEXEC	= (1ULL << 0),
 };
 
+/* Flags for bpf_redirect_map helper */
+enum {
+	BPF_F_BROADCAST		= (1ULL << 3),
+	BPF_F_EXCLUDE_INGRESS	= (1ULL << 4),
+};
+
 #define __bpf_md_ptr(type, name)	\
 union {					\
 	type name;			\
@@ -5364,6 +5418,20 @@ struct sk_reuseport_md {
 	__u32 ip_protocol;	/* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
 	__u32 bind_inany;	/* Is sock bound to an INANY address? */
 	__u32 hash;		/* A hash of the packet 4 tuples */
+	/* When reuse->migrating_sk is NULL, it is selecting a sk for the
+	 * new incoming connection request (e.g. selecting a listen sk for
+	 * the received SYN in the TCP case).  reuse->sk is one of the sk
+	 * in the reuseport group. The bpf prog can use reuse->sk to learn
+	 * the local listening ip/port without looking into the skb.
+	 *
+	 * When reuse->migrating_sk is not NULL, reuse->sk is closed and
+	 * reuse->migrating_sk is the socket that needs to be migrated
+	 * to another listening socket.  migrating_sk could be a fullsock
+	 * sk that is fully established or a reqsk that is in-the-middle
+	 * of 3-way handshake.
+	 */
+	__bpf_md_ptr(struct bpf_sock *, sk);
+	__bpf_md_ptr(struct bpf_sock *, migrating_sk);
 };
 
 #define BPF_TAG_SIZE	8
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 9b057cc7650a..430f6874fa41 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1,3 +1,3 @@
 libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \
 	    netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o hashmap.o \
-	    btf_dump.o ringbuf.o strset.o linker.o
+	    btf_dump.o ringbuf.o strset.o linker.o gen_loader.o
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index e43e1896cb4b..ec14aa725bb0 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -223,18 +223,14 @@ install_lib: all_cmd
 		$(call do_install_mkdir,$(libdir_SQ)); \
 		cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ)
 
+INSTALL_HEADERS = bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \
+		  bpf_helpers.h $(BPF_HELPER_DEFS) bpf_tracing.h	     \
+		  bpf_endian.h bpf_core_read.h skel_internal.h
+
 install_headers: $(BPF_HELPER_DEFS)
-	$(call QUIET_INSTALL, headers) \
-		$(call do_install,bpf.h,$(prefix)/include/bpf,644); \
-		$(call do_install,libbpf.h,$(prefix)/include/bpf,644); \
-		$(call do_install,btf.h,$(prefix)/include/bpf,644); \
-		$(call do_install,libbpf_common.h,$(prefix)/include/bpf,644); \
-		$(call do_install,xsk.h,$(prefix)/include/bpf,644); \
-		$(call do_install,bpf_helpers.h,$(prefix)/include/bpf,644); \
-		$(call do_install,$(BPF_HELPER_DEFS),$(prefix)/include/bpf,644); \
-		$(call do_install,bpf_tracing.h,$(prefix)/include/bpf,644); \
-		$(call do_install,bpf_endian.h,$(prefix)/include/bpf,644); \
-		$(call do_install,bpf_core_read.h,$(prefix)/include/bpf,644);
+	$(call QUIET_INSTALL, headers)					     \
+		$(foreach hdr,$(INSTALL_HEADERS),			     \
+			$(call do_install,$(hdr),$(prefix)/include/bpf,644);)
 
 install_pkgconfig: $(PC_FILE)
 	$(call QUIET_INSTALL, $(PC_FILE)) \
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index bba48ff4c5c0..86dcac44f32f 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -80,6 +80,7 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size)
 int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, '\0', sizeof(attr));
 
@@ -102,7 +103,8 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
 	else
 		attr.inner_map_fd = create_attr->inner_map_fd;
 
-	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
@@ -160,6 +162,7 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
 			       __u32 map_flags, int node)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, '\0', sizeof(attr));
 
@@ -178,7 +181,8 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
 		attr.numa_node = node;
 	}
 
-	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name,
@@ -222,10 +226,10 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr)
 	int fd;
 
 	if (!load_attr->log_buf != !load_attr->log_buf_sz)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (load_attr->log_level > (4 | 2 | 1) || (load_attr->log_level && !load_attr->log_buf))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = load_attr->prog_type;
@@ -281,8 +285,10 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr)
 							load_attr->func_info_cnt,
 							load_attr->func_info_rec_size,
 							attr.func_info_rec_size);
-			if (!finfo)
+			if (!finfo) {
+				errno = E2BIG;
 				goto done;
+			}
 
 			attr.func_info = ptr_to_u64(finfo);
 			attr.func_info_rec_size = load_attr->func_info_rec_size;
@@ -293,8 +299,10 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr)
 							load_attr->line_info_cnt,
 							load_attr->line_info_rec_size,
 							attr.line_info_rec_size);
-			if (!linfo)
+			if (!linfo) {
+				errno = E2BIG;
 				goto done;
+			}
 
 			attr.line_info = ptr_to_u64(linfo);
 			attr.line_info_rec_size = load_attr->line_info_rec_size;
@@ -318,9 +326,10 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr)
 
 	fd = sys_bpf_prog_load(&attr, sizeof(attr));
 done:
+	/* free() doesn't affect errno, so we don't need to restore it */
 	free(finfo);
 	free(linfo);
-	return fd;
+	return libbpf_err_errno(fd);
 }
 
 int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
@@ -329,7 +338,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	struct bpf_prog_load_params p = {};
 
 	if (!load_attr || !log_buf != !log_buf_sz)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	p.prog_type = load_attr->prog_type;
 	p.expected_attach_type = load_attr->expected_attach_type;
@@ -391,6 +400,7 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 		       int log_level)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = type;
@@ -404,13 +414,15 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 	attr.kern_version = kern_version;
 	attr.prog_flags = prog_flags;
 
-	return sys_bpf_prog_load(&attr, sizeof(attr));
+	fd = sys_bpf_prog_load(&attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_map_update_elem(int fd, const void *key, const void *value,
 			__u64 flags)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
@@ -418,24 +430,28 @@ int bpf_map_update_elem(int fd, const void *key, const void *value,
 	attr.value = ptr_to_u64(value);
 	attr.flags = flags;
 
-	return sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_map_lookup_elem(int fd, const void *key, void *value)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
 
-	return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
@@ -443,17 +459,33 @@ int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags)
 	attr.value = ptr_to_u64(value);
 	attr.flags = flags;
 
-	return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
 {
 	union bpf_attr attr;
+	int ret;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.map_fd = fd;
+	attr.key = ptr_to_u64(key);
+	attr.value = ptr_to_u64(value);
+
+	ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
+}
+
+int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, void *value, __u64 flags)
+{
+	union bpf_attr attr;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
+	attr.flags = flags;
 
 	return sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
 }
@@ -461,34 +493,40 @@ int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
 int bpf_map_delete_elem(int fd, const void *key)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 
-	return sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_map_get_next_key(int fd, const void *key, void *next_key)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.next_key = ptr_to_u64(next_key);
 
-	return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_map_freeze(int fd)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 
-	return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 static int bpf_map_batch_common(int cmd, int fd, void  *in_batch,
@@ -500,7 +538,7 @@ static int bpf_map_batch_common(int cmd, int fd, void  *in_batch,
 	int ret;
 
 	if (!OPTS_VALID(opts, bpf_map_batch_opts))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.batch.map_fd = fd;
@@ -515,7 +553,7 @@ static int bpf_map_batch_common(int cmd, int fd, void  *in_batch,
 	ret = sys_bpf(cmd, &attr, sizeof(attr));
 	*count = attr.batch.count;
 
-	return ret;
+	return libbpf_err_errno(ret);
 }
 
 int bpf_map_delete_batch(int fd, void *keys, __u32 *count,
@@ -552,22 +590,26 @@ int bpf_map_update_batch(int fd, void *keys, void *values, __u32 *count,
 int bpf_obj_pin(int fd, const char *pathname)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.pathname = ptr_to_u64((void *)pathname);
 	attr.bpf_fd = fd;
 
-	return sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_obj_get(const char *pathname)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.pathname = ptr_to_u64((void *)pathname);
 
-	return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
@@ -585,9 +627,10 @@ int bpf_prog_attach_xattr(int prog_fd, int target_fd,
 			  const struct bpf_prog_attach_opts *opts)
 {
 	union bpf_attr attr;
+	int ret;
 
 	if (!OPTS_VALID(opts, bpf_prog_attach_opts))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.target_fd	   = target_fd;
@@ -596,30 +639,35 @@ int bpf_prog_attach_xattr(int prog_fd, int target_fd,
 	attr.attach_flags  = OPTS_GET(opts, flags, 0);
 	attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0);
 
-	return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.target_fd	 = target_fd;
 	attr.attach_type = type;
 
-	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.target_fd	 = target_fd;
 	attr.attach_bpf_fd = prog_fd;
 	attr.attach_type = type;
 
-	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_link_create(int prog_fd, int target_fd,
@@ -628,15 +676,16 @@ int bpf_link_create(int prog_fd, int target_fd,
 {
 	__u32 target_btf_id, iter_info_len;
 	union bpf_attr attr;
+	int fd;
 
 	if (!OPTS_VALID(opts, bpf_link_create_opts))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	iter_info_len = OPTS_GET(opts, iter_info_len, 0);
 	target_btf_id = OPTS_GET(opts, target_btf_id, 0);
 
 	if (iter_info_len && target_btf_id)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.link_create.prog_fd = prog_fd;
@@ -652,26 +701,30 @@ int bpf_link_create(int prog_fd, int target_fd,
 		attr.link_create.target_btf_id = target_btf_id;
 	}
 
-	return sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_link_detach(int link_fd)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.link_detach.link_fd = link_fd;
 
-	return sys_bpf(BPF_LINK_DETACH, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_LINK_DETACH, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_link_update(int link_fd, int new_prog_fd,
 		    const struct bpf_link_update_opts *opts)
 {
 	union bpf_attr attr;
+	int ret;
 
 	if (!OPTS_VALID(opts, bpf_link_update_opts))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.link_update.link_fd = link_fd;
@@ -679,17 +732,20 @@ int bpf_link_update(int link_fd, int new_prog_fd,
 	attr.link_update.flags = OPTS_GET(opts, flags, 0);
 	attr.link_update.old_prog_fd = OPTS_GET(opts, old_prog_fd, 0);
 
-	return sys_bpf(BPF_LINK_UPDATE, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_LINK_UPDATE, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_iter_create(int link_fd)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.iter_create.link_fd = link_fd;
 
-	return sys_bpf(BPF_ITER_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_ITER_CREATE, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
@@ -706,10 +762,12 @@ int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
 	attr.query.prog_ids	= ptr_to_u64(prog_ids);
 
 	ret = sys_bpf(BPF_PROG_QUERY, &attr, sizeof(attr));
+
 	if (attach_flags)
 		*attach_flags = attr.query.attach_flags;
 	*prog_cnt = attr.query.prog_cnt;
-	return ret;
+
+	return libbpf_err_errno(ret);
 }
 
 int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
@@ -727,13 +785,15 @@ int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 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;
+
+	return libbpf_err_errno(ret);
 }
 
 int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr)
@@ -742,7 +802,7 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr)
 	int ret;
 
 	if (!test_attr->data_out && test_attr->data_size_out > 0)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.test.prog_fd = test_attr->prog_fd;
@@ -757,11 +817,13 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr)
 	attr.test.repeat = test_attr->repeat;
 
 	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
+
 	test_attr->data_size_out = attr.test.data_size_out;
 	test_attr->ctx_size_out = attr.test.ctx_size_out;
 	test_attr->retval = attr.test.retval;
 	test_attr->duration = attr.test.duration;
-	return ret;
+
+	return libbpf_err_errno(ret);
 }
 
 int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts)
@@ -770,7 +832,7 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts)
 	int ret;
 
 	if (!OPTS_VALID(opts, bpf_test_run_opts))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.test.prog_fd = prog_fd;
@@ -788,11 +850,13 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts)
 	attr.test.data_out = ptr_to_u64(OPTS_GET(opts, data_out, NULL));
 
 	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
+
 	OPTS_SET(opts, data_size_out, attr.test.data_size_out);
 	OPTS_SET(opts, ctx_size_out, attr.test.ctx_size_out);
 	OPTS_SET(opts, duration, attr.test.duration);
 	OPTS_SET(opts, retval, attr.test.retval);
-	return ret;
+
+	return libbpf_err_errno(ret);
 }
 
 static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd)
@@ -807,7 +871,7 @@ static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd)
 	if (!err)
 		*next_id = attr.next_id;
 
-	return err;
+	return libbpf_err_errno(err);
 }
 
 int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id)
@@ -833,41 +897,49 @@ int bpf_link_get_next_id(__u32 start_id, __u32 *next_id)
 int bpf_prog_get_fd_by_id(__u32 id)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_id = id;
 
-	return sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_map_get_fd_by_id(__u32 id)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_id = id;
 
-	return sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_btf_get_fd_by_id(__u32 id)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.btf_id = id;
 
-	return sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_link_get_fd_by_id(__u32 id)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.link_id = id;
 
-	return sys_bpf(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len)
@@ -881,21 +953,24 @@ int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len)
 	attr.info.info = ptr_to_u64(info);
 
 	err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, sizeof(attr));
+
 	if (!err)
 		*info_len = attr.info.info_len;
 
-	return err;
+	return libbpf_err_errno(err);
 }
 
 int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.raw_tracepoint.name = ptr_to_u64(name);
 	attr.raw_tracepoint.prog_fd = prog_fd;
 
-	return sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
@@ -915,12 +990,13 @@ retry:
 	}
 
 	fd = sys_bpf(BPF_BTF_LOAD, &attr, sizeof(attr));
-	if (fd == -1 && !do_log && log_buf && log_buf_size) {
+
+	if (fd < 0 && !do_log && log_buf && log_buf_size) {
 		do_log = true;
 		goto retry;
 	}
 
-	return fd;
+	return libbpf_err_errno(fd);
 }
 
 int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
@@ -937,37 +1013,42 @@ int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
 	attr.task_fd_query.buf_len = *buf_len;
 
 	err = sys_bpf(BPF_TASK_FD_QUERY, &attr, sizeof(attr));
+
 	*buf_len = attr.task_fd_query.buf_len;
 	*prog_id = attr.task_fd_query.prog_id;
 	*fd_type = attr.task_fd_query.fd_type;
 	*probe_offset = attr.task_fd_query.probe_offset;
 	*probe_addr = attr.task_fd_query.probe_addr;
 
-	return err;
+	return libbpf_err_errno(err);
 }
 
 int bpf_enable_stats(enum bpf_stats_type type)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.enable_stats.type = type;
 
-	return sys_bpf(BPF_ENABLE_STATS, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_ENABLE_STATS, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_prog_bind_map(int prog_fd, int map_fd,
 		      const struct bpf_prog_bind_opts *opts)
 {
 	union bpf_attr attr;
+	int ret;
 
 	if (!OPTS_VALID(opts, bpf_prog_bind_opts))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_bind_map.prog_fd = prog_fd;
 	attr.prog_bind_map.map_fd = map_fd;
 	attr.prog_bind_map.flags = OPTS_GET(opts, flags, 0);
 
-	return sys_bpf(BPF_PROG_BIND_MAP, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 875dde20d56e..4f758f8f50cd 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -124,6 +124,8 @@ LIBBPF_API int bpf_map_lookup_elem_flags(int fd, const void *key, void *value,
 					 __u64 flags);
 LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
 					      void *value);
+LIBBPF_API int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key,
+						    void *value, __u64 flags);
 LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
 LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
 LIBBPF_API int bpf_map_freeze(int fd);
diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h
new file mode 100644
index 000000000000..615400391e57
--- /dev/null
+++ b/tools/lib/bpf/bpf_gen_internal.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/* Copyright (c) 2021 Facebook */
+#ifndef __BPF_GEN_INTERNAL_H
+#define __BPF_GEN_INTERNAL_H
+
+struct ksym_relo_desc {
+	const char *name;
+	int kind;
+	int insn_idx;
+};
+
+struct bpf_gen {
+	struct gen_loader_opts *opts;
+	void *data_start;
+	void *data_cur;
+	void *insn_start;
+	void *insn_cur;
+	ssize_t cleanup_label;
+	__u32 nr_progs;
+	__u32 nr_maps;
+	int log_level;
+	int error;
+	struct ksym_relo_desc *relos;
+	int relo_cnt;
+	char attach_target[128];
+	int attach_kind;
+};
+
+void bpf_gen__init(struct bpf_gen *gen, int log_level);
+int bpf_gen__finish(struct bpf_gen *gen);
+void bpf_gen__free(struct bpf_gen *gen);
+void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size);
+void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_attr *map_attr, int map_idx);
+struct bpf_prog_load_params;
+void bpf_gen__prog_load(struct bpf_gen *gen, struct bpf_prog_load_params *load_attr, int prog_idx);
+void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u32 value_size);
+void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx);
+void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *name, enum bpf_attach_type type);
+void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind, int insn_idx);
+
+#endif
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index 9720dc0b4605..b9987c3efa3c 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -158,4 +158,70 @@ enum libbpf_tristate {
 #define __kconfig __attribute__((section(".kconfig")))
 #define __ksym __attribute__((section(".ksyms")))
 
+#ifndef ___bpf_concat
+#define ___bpf_concat(a, b) a ## b
+#endif
+#ifndef ___bpf_apply
+#define ___bpf_apply(fn, n) ___bpf_concat(fn, n)
+#endif
+#ifndef ___bpf_nth
+#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
+#endif
+#ifndef ___bpf_narg
+#define ___bpf_narg(...) \
+	___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#endif
+
+#define ___bpf_fill0(arr, p, x) do {} while (0)
+#define ___bpf_fill1(arr, p, x) arr[p] = x
+#define ___bpf_fill2(arr, p, x, args...) arr[p] = x; ___bpf_fill1(arr, p + 1, args)
+#define ___bpf_fill3(arr, p, x, args...) arr[p] = x; ___bpf_fill2(arr, p + 1, args)
+#define ___bpf_fill4(arr, p, x, args...) arr[p] = x; ___bpf_fill3(arr, p + 1, args)
+#define ___bpf_fill5(arr, p, x, args...) arr[p] = x; ___bpf_fill4(arr, p + 1, args)
+#define ___bpf_fill6(arr, p, x, args...) arr[p] = x; ___bpf_fill5(arr, p + 1, args)
+#define ___bpf_fill7(arr, p, x, args...) arr[p] = x; ___bpf_fill6(arr, p + 1, args)
+#define ___bpf_fill8(arr, p, x, args...) arr[p] = x; ___bpf_fill7(arr, p + 1, args)
+#define ___bpf_fill9(arr, p, x, args...) arr[p] = x; ___bpf_fill8(arr, p + 1, args)
+#define ___bpf_fill10(arr, p, x, args...) arr[p] = x; ___bpf_fill9(arr, p + 1, args)
+#define ___bpf_fill11(arr, p, x, args...) arr[p] = x; ___bpf_fill10(arr, p + 1, args)
+#define ___bpf_fill12(arr, p, x, args...) arr[p] = x; ___bpf_fill11(arr, p + 1, args)
+#define ___bpf_fill(arr, args...) \
+	___bpf_apply(___bpf_fill, ___bpf_narg(args))(arr, 0, args)
+
+/*
+ * BPF_SEQ_PRINTF to wrap bpf_seq_printf to-be-printed values
+ * in a structure.
+ */
+#define BPF_SEQ_PRINTF(seq, fmt, args...)			\
+({								\
+	static const char ___fmt[] = fmt;			\
+	unsigned long long ___param[___bpf_narg(args)];		\
+								\
+	_Pragma("GCC diagnostic push")				\
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
+	___bpf_fill(___param, args);				\
+	_Pragma("GCC diagnostic pop")				\
+								\
+	bpf_seq_printf(seq, ___fmt, sizeof(___fmt),		\
+		       ___param, sizeof(___param));		\
+})
+
+/*
+ * BPF_SNPRINTF wraps the bpf_snprintf helper with variadic arguments instead of
+ * an array of u64.
+ */
+#define BPF_SNPRINTF(out, out_size, fmt, args...)		\
+({								\
+	static const char ___fmt[] = fmt;			\
+	unsigned long long ___param[___bpf_narg(args)];		\
+								\
+	_Pragma("GCC diagnostic push")				\
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
+	___bpf_fill(___param, args);				\
+	_Pragma("GCC diagnostic pop")				\
+								\
+	bpf_snprintf(out, out_size, ___fmt,			\
+		     ___param, sizeof(___param));		\
+})
+
 #endif
diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c
index 3ed1a27b5f7c..5c503096ef43 100644
--- a/tools/lib/bpf/bpf_prog_linfo.c
+++ b/tools/lib/bpf/bpf_prog_linfo.c
@@ -106,7 +106,7 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 	nr_linfo = info->nr_line_info;
 
 	if (!nr_linfo)
-		return NULL;
+		return errno = EINVAL, NULL;
 
 	/*
 	 * The min size that bpf_prog_linfo has to access for
@@ -114,11 +114,11 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 	 */
 	if (info->line_info_rec_size <
 	    offsetof(struct bpf_line_info, file_name_off))
-		return NULL;
+		return errno = EINVAL, NULL;
 
 	prog_linfo = calloc(1, sizeof(*prog_linfo));
 	if (!prog_linfo)
-		return NULL;
+		return errno = ENOMEM, NULL;
 
 	/* Copy xlated line_info */
 	prog_linfo->nr_linfo = nr_linfo;
@@ -174,7 +174,7 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 
 err_free:
 	bpf_prog_linfo__free(prog_linfo);
-	return NULL;
+	return errno = EINVAL, NULL;
 }
 
 const struct bpf_line_info *
@@ -186,11 +186,11 @@ bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo,
 	const __u64 *jited_linfo;
 
 	if (func_idx >= prog_linfo->nr_jited_func)
-		return NULL;
+		return errno = ENOENT, NULL;
 
 	nr_linfo = prog_linfo->nr_jited_linfo_per_func[func_idx];
 	if (nr_skip >= nr_linfo)
-		return NULL;
+		return errno = ENOENT, NULL;
 
 	start = prog_linfo->jited_linfo_func_idx[func_idx] + nr_skip;
 	jited_rec_size = prog_linfo->jited_rec_size;
@@ -198,7 +198,7 @@ bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo,
 		(start * jited_rec_size);
 	jited_linfo = raw_jited_linfo;
 	if (addr < *jited_linfo)
-		return NULL;
+		return errno = ENOENT, NULL;
 
 	nr_linfo -= nr_skip;
 	rec_size = prog_linfo->rec_size;
@@ -225,13 +225,13 @@ bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo,
 
 	nr_linfo = prog_linfo->nr_linfo;
 	if (nr_skip >= nr_linfo)
-		return NULL;
+		return errno = ENOENT, NULL;
 
 	rec_size = prog_linfo->rec_size;
 	raw_linfo = prog_linfo->raw_linfo + (nr_skip * rec_size);
 	linfo = raw_linfo;
 	if (insn_off < linfo->insn_off)
-		return NULL;
+		return errno = ENOENT, NULL;
 
 	nr_linfo -= nr_skip;
 	for (i = 0; i < nr_linfo; i++) {
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index 8c954ebc0c7c..d6bfbe009296 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -25,26 +25,35 @@
 	#define bpf_target_sparc
 	#define bpf_target_defined
 #else
-	#undef bpf_target_defined
-#endif
 
 /* Fall back to what the compiler says */
-#ifndef bpf_target_defined
 #if defined(__x86_64__)
 	#define bpf_target_x86
+	#define bpf_target_defined
 #elif defined(__s390__)
 	#define bpf_target_s390
+	#define bpf_target_defined
 #elif defined(__arm__)
 	#define bpf_target_arm
+	#define bpf_target_defined
 #elif defined(__aarch64__)
 	#define bpf_target_arm64
+	#define bpf_target_defined
 #elif defined(__mips__)
 	#define bpf_target_mips
+	#define bpf_target_defined
 #elif defined(__powerpc__)
 	#define bpf_target_powerpc
+	#define bpf_target_defined
 #elif defined(__sparc__)
 	#define bpf_target_sparc
+	#define bpf_target_defined
+#endif /* no compiler target */
+
 #endif
+
+#ifndef __BPF_TARGET_MISSING
+#define __BPF_TARGET_MISSING "GCC error \"Must specify a BPF target arch via __TARGET_ARCH_xxx\""
 #endif
 
 #if defined(bpf_target_x86)
@@ -287,7 +296,7 @@ struct pt_regs;
 #elif defined(bpf_target_sparc)
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
-#else
+#elif defined(bpf_target_defined)
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)					    \
 	({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); })
 #define BPF_KRETPROBE_READ_RET_IP(ip, ctx)				    \
@@ -295,13 +304,48 @@ struct pt_regs;
 			  (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
 #endif
 
+#if !defined(bpf_target_defined)
+
+#define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM2(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM3(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM4(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM5(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_RET(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_FP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_RC(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_SP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_IP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
+#define PT_REGS_PARM1_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM2_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM3_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM4_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM5_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_RET_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_FP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_RC_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_SP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_IP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
+#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
+#endif /* !defined(bpf_target_defined) */
+
+#ifndef ___bpf_concat
 #define ___bpf_concat(a, b) a ## b
+#endif
+#ifndef ___bpf_apply
 #define ___bpf_apply(fn, n) ___bpf_concat(fn, n)
+#endif
+#ifndef ___bpf_nth
 #define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
+#endif
+#ifndef ___bpf_narg
 #define ___bpf_narg(...) \
 	___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
-#define ___bpf_empty(...) \
-	___bpf_nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0)
+#endif
 
 #define ___bpf_ctx_cast0() ctx
 #define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0]
@@ -413,56 +457,4 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
 }									    \
 static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
 
-#define ___bpf_fill0(arr, p, x) do {} while (0)
-#define ___bpf_fill1(arr, p, x) arr[p] = x
-#define ___bpf_fill2(arr, p, x, args...) arr[p] = x; ___bpf_fill1(arr, p + 1, args)
-#define ___bpf_fill3(arr, p, x, args...) arr[p] = x; ___bpf_fill2(arr, p + 1, args)
-#define ___bpf_fill4(arr, p, x, args...) arr[p] = x; ___bpf_fill3(arr, p + 1, args)
-#define ___bpf_fill5(arr, p, x, args...) arr[p] = x; ___bpf_fill4(arr, p + 1, args)
-#define ___bpf_fill6(arr, p, x, args...) arr[p] = x; ___bpf_fill5(arr, p + 1, args)
-#define ___bpf_fill7(arr, p, x, args...) arr[p] = x; ___bpf_fill6(arr, p + 1, args)
-#define ___bpf_fill8(arr, p, x, args...) arr[p] = x; ___bpf_fill7(arr, p + 1, args)
-#define ___bpf_fill9(arr, p, x, args...) arr[p] = x; ___bpf_fill8(arr, p + 1, args)
-#define ___bpf_fill10(arr, p, x, args...) arr[p] = x; ___bpf_fill9(arr, p + 1, args)
-#define ___bpf_fill11(arr, p, x, args...) arr[p] = x; ___bpf_fill10(arr, p + 1, args)
-#define ___bpf_fill12(arr, p, x, args...) arr[p] = x; ___bpf_fill11(arr, p + 1, args)
-#define ___bpf_fill(arr, args...) \
-	___bpf_apply(___bpf_fill, ___bpf_narg(args))(arr, 0, args)
-
-/*
- * BPF_SEQ_PRINTF to wrap bpf_seq_printf to-be-printed values
- * in a structure.
- */
-#define BPF_SEQ_PRINTF(seq, fmt, args...)			\
-({								\
-	static const char ___fmt[] = fmt;			\
-	unsigned long long ___param[___bpf_narg(args)];		\
-								\
-	_Pragma("GCC diagnostic push")				\
-	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
-	___bpf_fill(___param, args);				\
-	_Pragma("GCC diagnostic pop")				\
-								\
-	bpf_seq_printf(seq, ___fmt, sizeof(___fmt),		\
-		       ___param, sizeof(___param));		\
-})
-
-/*
- * BPF_SNPRINTF wraps the bpf_snprintf helper with variadic arguments instead of
- * an array of u64.
- */
-#define BPF_SNPRINTF(out, out_size, fmt, args...)		\
-({								\
-	static const char ___fmt[] = fmt;			\
-	unsigned long long ___param[___bpf_narg(args)];		\
-								\
-	_Pragma("GCC diagnostic push")				\
-	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
-	___bpf_fill(___param, args);				\
-	_Pragma("GCC diagnostic pop")				\
-								\
-	bpf_snprintf(out, out_size, ___fmt,			\
-		     ___param, sizeof(___param));		\
-})
-
 #endif
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index d57e13a13798..b46760b93bb4 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -443,7 +443,7 @@ struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id)
 const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id)
 {
 	if (type_id >= btf->start_id + btf->nr_types)
-		return NULL;
+		return errno = EINVAL, NULL;
 	return btf_type_by_id((struct btf *)btf, type_id);
 }
 
@@ -510,7 +510,7 @@ size_t btf__pointer_size(const struct btf *btf)
 int btf__set_pointer_size(struct btf *btf, size_t ptr_sz)
 {
 	if (ptr_sz != 4 && ptr_sz != 8)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	btf->ptr_sz = ptr_sz;
 	return 0;
 }
@@ -537,7 +537,7 @@ enum btf_endianness btf__endianness(const struct btf *btf)
 int btf__set_endianness(struct btf *btf, enum btf_endianness endian)
 {
 	if (endian != BTF_LITTLE_ENDIAN && endian != BTF_BIG_ENDIAN)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	btf->swapped_endian = is_host_big_endian() != (endian == BTF_BIG_ENDIAN);
 	if (!btf->swapped_endian) {
@@ -568,8 +568,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 	int i;
 
 	t = btf__type_by_id(btf, type_id);
-	for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t);
-	     i++) {
+	for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); i++) {
 		switch (btf_kind(t)) {
 		case BTF_KIND_INT:
 		case BTF_KIND_STRUCT:
@@ -592,12 +591,12 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 		case BTF_KIND_ARRAY:
 			array = btf_array(t);
 			if (nelems && array->nelems > UINT32_MAX / nelems)
-				return -E2BIG;
+				return libbpf_err(-E2BIG);
 			nelems *= array->nelems;
 			type_id = array->type;
 			break;
 		default:
-			return -EINVAL;
+			return libbpf_err(-EINVAL);
 		}
 
 		t = btf__type_by_id(btf, type_id);
@@ -605,9 +604,9 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 
 done:
 	if (size < 0)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	if (nelems && size > UINT32_MAX / nelems)
-		return -E2BIG;
+		return libbpf_err(-E2BIG);
 
 	return nelems * size;
 }
@@ -640,7 +639,7 @@ int btf__align_of(const struct btf *btf, __u32 id)
 		for (i = 0; i < vlen; i++, m++) {
 			align = btf__align_of(btf, m->type);
 			if (align <= 0)
-				return align;
+				return libbpf_err(align);
 			max_align = max(max_align, align);
 		}
 
@@ -648,7 +647,7 @@ int btf__align_of(const struct btf *btf, __u32 id)
 	}
 	default:
 		pr_warn("unsupported BTF_KIND:%u\n", btf_kind(t));
-		return 0;
+		return errno = EINVAL, 0;
 	}
 }
 
@@ -667,7 +666,7 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id)
 	}
 
 	if (depth == MAX_RESOLVE_DEPTH || btf_type_is_void_or_null(t))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	return type_id;
 }
@@ -687,7 +686,7 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 			return i;
 	}
 
-	return -ENOENT;
+	return libbpf_err(-ENOENT);
 }
 
 __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
@@ -709,7 +708,7 @@ __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
 			return i;
 	}
 
-	return -ENOENT;
+	return libbpf_err(-ENOENT);
 }
 
 static bool btf_is_modifiable(const struct btf *btf)
@@ -785,12 +784,12 @@ static struct btf *btf_new_empty(struct btf *base_btf)
 
 struct btf *btf__new_empty(void)
 {
-	return btf_new_empty(NULL);
+	return libbpf_ptr(btf_new_empty(NULL));
 }
 
 struct btf *btf__new_empty_split(struct btf *base_btf)
 {
-	return btf_new_empty(base_btf);
+	return libbpf_ptr(btf_new_empty(base_btf));
 }
 
 static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
@@ -846,7 +845,7 @@ done:
 
 struct btf *btf__new(const void *data, __u32 size)
 {
-	return btf_new(data, size, NULL);
+	return libbpf_ptr(btf_new(data, size, NULL));
 }
 
 static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
@@ -937,7 +936,8 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 		goto done;
 	}
 	btf = btf_new(btf_data->d_buf, btf_data->d_size, base_btf);
-	if (IS_ERR(btf))
+	err = libbpf_get_error(btf);
+	if (err)
 		goto done;
 
 	switch (gelf_getclass(elf)) {
@@ -953,9 +953,9 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 	}
 
 	if (btf_ext && btf_ext_data) {
-		*btf_ext = btf_ext__new(btf_ext_data->d_buf,
-					btf_ext_data->d_size);
-		if (IS_ERR(*btf_ext))
+		*btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size);
+		err = libbpf_get_error(*btf_ext);
+		if (err)
 			goto done;
 	} else if (btf_ext) {
 		*btf_ext = NULL;
@@ -965,30 +965,24 @@ done:
 		elf_end(elf);
 	close(fd);
 
-	if (err)
-		return ERR_PTR(err);
-	/*
-	 * btf is always parsed before btf_ext, so no need to clean up
-	 * btf_ext, if btf loading failed
-	 */
-	if (IS_ERR(btf))
+	if (!err)
 		return btf;
-	if (btf_ext && IS_ERR(*btf_ext)) {
-		btf__free(btf);
-		err = PTR_ERR(*btf_ext);
-		return ERR_PTR(err);
-	}
-	return btf;
+
+	if (btf_ext)
+		btf_ext__free(*btf_ext);
+	btf__free(btf);
+
+	return ERR_PTR(err);
 }
 
 struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
 {
-	return btf_parse_elf(path, NULL, btf_ext);
+	return libbpf_ptr(btf_parse_elf(path, NULL, btf_ext));
 }
 
 struct btf *btf__parse_elf_split(const char *path, struct btf *base_btf)
 {
-	return btf_parse_elf(path, base_btf, NULL);
+	return libbpf_ptr(btf_parse_elf(path, base_btf, NULL));
 }
 
 static struct btf *btf_parse_raw(const char *path, struct btf *base_btf)
@@ -1056,36 +1050,39 @@ err_out:
 
 struct btf *btf__parse_raw(const char *path)
 {
-	return btf_parse_raw(path, NULL);
+	return libbpf_ptr(btf_parse_raw(path, NULL));
 }
 
 struct btf *btf__parse_raw_split(const char *path, struct btf *base_btf)
 {
-	return btf_parse_raw(path, base_btf);
+	return libbpf_ptr(btf_parse_raw(path, base_btf));
 }
 
 static struct btf *btf_parse(const char *path, struct btf *base_btf, struct btf_ext **btf_ext)
 {
 	struct btf *btf;
+	int err;
 
 	if (btf_ext)
 		*btf_ext = NULL;
 
 	btf = btf_parse_raw(path, base_btf);
-	if (!IS_ERR(btf) || PTR_ERR(btf) != -EPROTO)
+	err = libbpf_get_error(btf);
+	if (!err)
 		return btf;
-
+	if (err != -EPROTO)
+		return ERR_PTR(err);
 	return btf_parse_elf(path, base_btf, btf_ext);
 }
 
 struct btf *btf__parse(const char *path, struct btf_ext **btf_ext)
 {
-	return btf_parse(path, NULL, btf_ext);
+	return libbpf_ptr(btf_parse(path, NULL, btf_ext));
 }
 
 struct btf *btf__parse_split(const char *path, struct btf *base_btf)
 {
-	return btf_parse(path, base_btf, NULL);
+	return libbpf_ptr(btf_parse(path, base_btf, NULL));
 }
 
 static int compare_vsi_off(const void *_a, const void *_b)
@@ -1178,7 +1175,7 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
 		}
 	}
 
-	return err;
+	return libbpf_err(err);
 }
 
 static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian);
@@ -1191,13 +1188,13 @@ int btf__load(struct btf *btf)
 	int err = 0;
 
 	if (btf->fd >= 0)
-		return -EEXIST;
+		return libbpf_err(-EEXIST);
 
 retry_load:
 	if (log_buf_size) {
 		log_buf = malloc(log_buf_size);
 		if (!log_buf)
-			return -ENOMEM;
+			return libbpf_err(-ENOMEM);
 
 		*log_buf = 0;
 	}
@@ -1229,7 +1226,7 @@ retry_load:
 
 done:
 	free(log_buf);
-	return err;
+	return libbpf_err(err);
 }
 
 int btf__fd(const struct btf *btf)
@@ -1305,7 +1302,7 @@ const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
 
 	data = btf_get_raw_data(btf, &data_sz, btf->swapped_endian);
 	if (!data)
-		return NULL;
+		return errno = -ENOMEM, NULL;
 
 	btf->raw_size = data_sz;
 	if (btf->swapped_endian)
@@ -1323,7 +1320,7 @@ const char *btf__str_by_offset(const struct btf *btf, __u32 offset)
 	else if (offset - btf->start_str_off < btf->hdr->str_len)
 		return btf_strs_data(btf) + (offset - btf->start_str_off);
 	else
-		return NULL;
+		return errno = EINVAL, NULL;
 }
 
 const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
@@ -1388,17 +1385,20 @@ exit_free:
 int btf__get_from_id(__u32 id, struct btf **btf)
 {
 	struct btf *res;
-	int btf_fd;
+	int err, btf_fd;
 
 	*btf = NULL;
 	btf_fd = bpf_btf_get_fd_by_id(id);
 	if (btf_fd < 0)
-		return -errno;
+		return libbpf_err(-errno);
 
 	res = btf_get_from_fd(btf_fd, NULL);
+	err = libbpf_get_error(res);
+
 	close(btf_fd);
-	if (IS_ERR(res))
-		return PTR_ERR(res);
+
+	if (err)
+		return libbpf_err(err);
 
 	*btf = res;
 	return 0;
@@ -1415,31 +1415,30 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
 	__s64 key_size, value_size;
 	__s32 container_id;
 
-	if (snprintf(container_name, max_name, "____btf_map_%s", map_name) ==
-	    max_name) {
+	if (snprintf(container_name, max_name, "____btf_map_%s", map_name) == max_name) {
 		pr_warn("map:%s length of '____btf_map_%s' is too long\n",
 			map_name, map_name);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	container_id = btf__find_by_name(btf, container_name);
 	if (container_id < 0) {
 		pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n",
 			 map_name, container_name);
-		return container_id;
+		return libbpf_err(container_id);
 	}
 
 	container_type = btf__type_by_id(btf, container_id);
 	if (!container_type) {
 		pr_warn("map:%s cannot find BTF type for container_id:%u\n",
 			map_name, container_id);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (!btf_is_struct(container_type) || btf_vlen(container_type) < 2) {
 		pr_warn("map:%s container_name:%s is an invalid container struct\n",
 			map_name, container_name);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	key = btf_members(container_type);
@@ -1448,25 +1447,25 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
 	key_size = btf__resolve_size(btf, key->type);
 	if (key_size < 0) {
 		pr_warn("map:%s invalid BTF key_type_size\n", map_name);
-		return key_size;
+		return libbpf_err(key_size);
 	}
 
 	if (expected_key_size != key_size) {
 		pr_warn("map:%s btf_key_type_size:%u != map_def_key_size:%u\n",
 			map_name, (__u32)key_size, expected_key_size);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	value_size = btf__resolve_size(btf, value->type);
 	if (value_size < 0) {
 		pr_warn("map:%s invalid BTF value_type_size\n", map_name);
-		return value_size;
+		return libbpf_err(value_size);
 	}
 
 	if (expected_value_size != value_size) {
 		pr_warn("map:%s btf_value_type_size:%u != map_def_value_size:%u\n",
 			map_name, (__u32)value_size, expected_value_size);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	*key_type_id = key->type;
@@ -1563,11 +1562,11 @@ int btf__find_str(struct btf *btf, const char *s)
 
 	/* BTF needs to be in a modifiable state to build string lookup index */
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	off = strset__find_str(btf->strs_set, s);
 	if (off < 0)
-		return off;
+		return libbpf_err(off);
 
 	return btf->start_str_off + off;
 }
@@ -1588,11 +1587,11 @@ int btf__add_str(struct btf *btf, const char *s)
 	}
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	off = strset__add_str(btf->strs_set, s);
 	if (off < 0)
-		return off;
+		return libbpf_err(off);
 
 	btf->hdr->str_len = strset__data_size(btf->strs_set);
 
@@ -1616,7 +1615,7 @@ static int btf_commit_type(struct btf *btf, int data_sz)
 
 	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	btf->hdr->type_len += data_sz;
 	btf->hdr->str_off += data_sz;
@@ -1653,21 +1652,21 @@ int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_t
 
 	sz = btf_type_size(src_type);
 	if (sz < 0)
-		return sz;
+		return libbpf_err(sz);
 
 	/* deconstruct BTF, if necessary, and invalidate raw_data */
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	memcpy(t, src_type, sz);
 
 	err = btf_type_visit_str_offs(t, btf_rewrite_str, &p);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	return btf_commit_type(btf, sz);
 }
@@ -1688,21 +1687,21 @@ int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding
 
 	/* non-empty name */
 	if (!name || !name[0])
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	/* byte_sz must be power of 2 */
 	if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 16)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	if (encoding & ~(BTF_INT_SIGNED | BTF_INT_CHAR | BTF_INT_BOOL))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* deconstruct BTF, if necessary, and invalidate raw_data */
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type) + sizeof(int);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	/* if something goes wrong later, we might end up with an extra string,
 	 * but that shouldn't be a problem, because BTF can't be constructed
@@ -1736,20 +1735,20 @@ int btf__add_float(struct btf *btf, const char *name, size_t byte_sz)
 
 	/* non-empty name */
 	if (!name || !name[0])
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* byte_sz must be one of the explicitly allowed values */
 	if (byte_sz != 2 && byte_sz != 4 && byte_sz != 8 && byte_sz != 12 &&
 	    byte_sz != 16)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	name_off = btf__add_str(btf, name);
 	if (name_off < 0)
@@ -1780,15 +1779,15 @@ static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref
 	int sz, name_off = 0;
 
 	if (validate_type_id(ref_type_id))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	if (name && name[0]) {
 		name_off = btf__add_str(btf, name);
@@ -1831,15 +1830,15 @@ int btf__add_array(struct btf *btf, int index_type_id, int elem_type_id, __u32 n
 	int sz;
 
 	if (validate_type_id(index_type_id) || validate_type_id(elem_type_id))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type) + sizeof(struct btf_array);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	t->name_off = 0;
 	t->info = btf_type_info(BTF_KIND_ARRAY, 0, 0);
@@ -1860,12 +1859,12 @@ static int btf_add_composite(struct btf *btf, int kind, const char *name, __u32
 	int sz, name_off = 0;
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	if (name && name[0]) {
 		name_off = btf__add_str(btf, name);
@@ -1943,30 +1942,30 @@ int btf__add_field(struct btf *btf, const char *name, int type_id,
 
 	/* last type should be union/struct */
 	if (btf->nr_types == 0)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	t = btf_last_type(btf);
 	if (!btf_is_composite(t))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (validate_type_id(type_id))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	/* best-effort bit field offset/size enforcement */
 	is_bitfield = bit_size || (bit_offset % 8 != 0);
 	if (is_bitfield && (bit_size == 0 || bit_size > 255 || bit_offset > 0xffffff))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* only offset 0 is allowed for unions */
 	if (btf_is_union(t) && bit_offset)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* decompose and invalidate raw data */
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_member);
 	m = btf_add_type_mem(btf, sz);
 	if (!m)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	if (name && name[0]) {
 		name_off = btf__add_str(btf, name);
@@ -2008,15 +2007,15 @@ int btf__add_enum(struct btf *btf, const char *name, __u32 byte_sz)
 
 	/* byte_sz must be power of 2 */
 	if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 8)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	if (name && name[0]) {
 		name_off = btf__add_str(btf, name);
@@ -2048,25 +2047,25 @@ int btf__add_enum_value(struct btf *btf, const char *name, __s64 value)
 
 	/* last type should be BTF_KIND_ENUM */
 	if (btf->nr_types == 0)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	t = btf_last_type(btf);
 	if (!btf_is_enum(t))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* non-empty name */
 	if (!name || !name[0])
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	if (value < INT_MIN || value > UINT_MAX)
-		return -E2BIG;
+		return libbpf_err(-E2BIG);
 
 	/* decompose and invalidate raw data */
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_enum);
 	v = btf_add_type_mem(btf, sz);
 	if (!v)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	name_off = btf__add_str(btf, name);
 	if (name_off < 0)
@@ -2096,7 +2095,7 @@ int btf__add_enum_value(struct btf *btf, const char *name, __s64 value)
 int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind)
 {
 	if (!name || !name[0])
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	switch (fwd_kind) {
 	case BTF_FWD_STRUCT:
@@ -2117,7 +2116,7 @@ int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind)
 		 */
 		return btf__add_enum(btf, name, sizeof(int));
 	default:
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 }
 
@@ -2132,7 +2131,7 @@ int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind)
 int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id)
 {
 	if (!name || !name[0])
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	return btf_add_ref_kind(btf, BTF_KIND_TYPEDEF, name, ref_type_id);
 }
@@ -2187,10 +2186,10 @@ int btf__add_func(struct btf *btf, const char *name,
 	int id;
 
 	if (!name || !name[0])
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	if (linkage != BTF_FUNC_STATIC && linkage != BTF_FUNC_GLOBAL &&
 	    linkage != BTF_FUNC_EXTERN)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	id = btf_add_ref_kind(btf, BTF_KIND_FUNC, name, proto_type_id);
 	if (id > 0) {
@@ -2198,7 +2197,7 @@ int btf__add_func(struct btf *btf, const char *name,
 
 		t->info = btf_type_info(BTF_KIND_FUNC, linkage, 0);
 	}
-	return id;
+	return libbpf_err(id);
 }
 
 /*
@@ -2219,15 +2218,15 @@ int btf__add_func_proto(struct btf *btf, int ret_type_id)
 	int sz;
 
 	if (validate_type_id(ret_type_id))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	/* start out with vlen=0; this will be adjusted when adding enum
 	 * values, if necessary
@@ -2254,23 +2253,23 @@ int btf__add_func_param(struct btf *btf, const char *name, int type_id)
 	int sz, name_off = 0;
 
 	if (validate_type_id(type_id))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* last type should be BTF_KIND_FUNC_PROTO */
 	if (btf->nr_types == 0)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	t = btf_last_type(btf);
 	if (!btf_is_func_proto(t))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* decompose and invalidate raw data */
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_param);
 	p = btf_add_type_mem(btf, sz);
 	if (!p)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	if (name && name[0]) {
 		name_off = btf__add_str(btf, name);
@@ -2308,21 +2307,21 @@ int btf__add_var(struct btf *btf, const char *name, int linkage, int type_id)
 
 	/* non-empty name */
 	if (!name || !name[0])
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	if (linkage != BTF_VAR_STATIC && linkage != BTF_VAR_GLOBAL_ALLOCATED &&
 	    linkage != BTF_VAR_GLOBAL_EXTERN)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	if (validate_type_id(type_id))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* deconstruct BTF, if necessary, and invalidate raw_data */
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type) + sizeof(struct btf_var);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	name_off = btf__add_str(btf, name);
 	if (name_off < 0)
@@ -2357,15 +2356,15 @@ int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz)
 
 	/* non-empty name */
 	if (!name || !name[0])
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	name_off = btf__add_str(btf, name);
 	if (name_off < 0)
@@ -2397,22 +2396,22 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __
 
 	/* last type should be BTF_KIND_DATASEC */
 	if (btf->nr_types == 0)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	t = btf_last_type(btf);
 	if (!btf_is_datasec(t))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (validate_type_id(var_type_id))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* decompose and invalidate raw data */
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_var_secinfo);
 	v = btf_add_type_mem(btf, sz);
 	if (!v)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	v->type = var_type_id;
 	v->offset = offset;
@@ -2614,11 +2613,11 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
 
 	err = btf_ext_parse_hdr(data, size);
 	if (err)
-		return ERR_PTR(err);
+		return libbpf_err_ptr(err);
 
 	btf_ext = calloc(1, sizeof(struct btf_ext));
 	if (!btf_ext)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 
 	btf_ext->data_size = size;
 	btf_ext->data = malloc(size);
@@ -2628,9 +2627,11 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
 	}
 	memcpy(btf_ext->data, data, size);
 
-	if (btf_ext->hdr->hdr_len <
-	    offsetofend(struct btf_ext_header, line_info_len))
+	if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, line_info_len)) {
+		err = -EINVAL;
 		goto done;
+	}
+
 	err = btf_ext_setup_func_info(btf_ext);
 	if (err)
 		goto done;
@@ -2639,8 +2640,11 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
 	if (err)
 		goto done;
 
-	if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len))
+	if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) {
+		err = -EINVAL;
 		goto done;
+	}
+
 	err = btf_ext_setup_core_relos(btf_ext);
 	if (err)
 		goto done;
@@ -2648,7 +2652,7 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
 done:
 	if (err) {
 		btf_ext__free(btf_ext);
-		return ERR_PTR(err);
+		return libbpf_err_ptr(err);
 	}
 
 	return btf_ext;
@@ -2687,7 +2691,7 @@ static int btf_ext_reloc_info(const struct btf *btf,
 		existing_len = (*cnt) * record_size;
 		data = realloc(*info, existing_len + records_len);
 		if (!data)
-			return -ENOMEM;
+			return libbpf_err(-ENOMEM);
 
 		memcpy(data + existing_len, sinfo->data, records_len);
 		/* adjust insn_off only, the rest data will be passed
@@ -2697,15 +2701,14 @@ static int btf_ext_reloc_info(const struct btf *btf,
 			__u32 *insn_off;
 
 			insn_off = data + existing_len + (i * record_size);
-			*insn_off = *insn_off / sizeof(struct bpf_insn) +
-				insns_cnt;
+			*insn_off = *insn_off / sizeof(struct bpf_insn) + insns_cnt;
 		}
 		*info = data;
 		*cnt += sinfo->num_info;
 		return 0;
 	}
 
-	return -ENOENT;
+	return libbpf_err(-ENOENT);
 }
 
 int btf_ext__reloc_func_info(const struct btf *btf,
@@ -2894,11 +2897,11 @@ int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
 
 	if (IS_ERR(d)) {
 		pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d));
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	err = btf_dedup_prep(d);
 	if (err) {
@@ -2938,7 +2941,7 @@ int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
 
 done:
 	btf_dedup_free(d);
-	return err;
+	return libbpf_err(err);
 }
 
 #define BTF_UNPROCESSED_ID ((__u32)-1)
@@ -4411,7 +4414,7 @@ struct btf *libbpf_find_kernel_btf(void)
 	char path[PATH_MAX + 1];
 	struct utsname buf;
 	struct btf *btf;
-	int i;
+	int i, err;
 
 	uname(&buf);
 
@@ -4425,17 +4428,16 @@ struct btf *libbpf_find_kernel_btf(void)
 			btf = btf__parse_raw(path);
 		else
 			btf = btf__parse_elf(path, NULL);
-
-		pr_debug("loading kernel BTF '%s': %ld\n",
-			 path, IS_ERR(btf) ? PTR_ERR(btf) : 0);
-		if (IS_ERR(btf))
+		err = libbpf_get_error(btf);
+		pr_debug("loading kernel BTF '%s': %d\n", path, err);
+		if (err)
 			continue;
 
 		return btf;
 	}
 
 	pr_warn("failed to find valid kernel BTF\n");
-	return ERR_PTR(-ESRCH);
+	return libbpf_err_ptr(-ESRCH);
 }
 
 int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx)
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 5e2809d685bf..5dc6b5172bb3 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -128,7 +128,7 @@ struct btf_dump *btf_dump__new(const struct btf *btf,
 
 	d = calloc(1, sizeof(struct btf_dump));
 	if (!d)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 
 	d->btf = btf;
 	d->btf_ext = btf_ext;
@@ -156,7 +156,7 @@ struct btf_dump *btf_dump__new(const struct btf *btf,
 	return d;
 err:
 	btf_dump__free(d);
-	return ERR_PTR(err);
+	return libbpf_err_ptr(err);
 }
 
 static int btf_dump_resize(struct btf_dump *d)
@@ -236,16 +236,16 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
 	int err, i;
 
 	if (id > btf__get_nr_types(d->btf))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	err = btf_dump_resize(d);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	d->emit_queue_cnt = 0;
 	err = btf_dump_order_type(d, id, false);
 	if (err < 0)
-		return err;
+		return libbpf_err(err);
 
 	for (i = 0; i < d->emit_queue_cnt; i++)
 		btf_dump_emit_type(d, d->emit_queue[i], 0 /*top-level*/);
@@ -1075,11 +1075,11 @@ int btf_dump__emit_type_decl(struct btf_dump *d, __u32 id,
 	int lvl, err;
 
 	if (!OPTS_VALID(opts, btf_dump_emit_type_decl_opts))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	err = btf_dump_resize(d);
 	if (err)
-		return -EINVAL;
+		return libbpf_err(err);
 
 	fname = OPTS_GET(opts, field_name, "");
 	lvl = OPTS_GET(opts, indent_level, 0);
diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
new file mode 100644
index 000000000000..8df718a6b142
--- /dev/null
+++ b/tools/lib/bpf/gen_loader.c
@@ -0,0 +1,729 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (c) 2021 Facebook */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <linux/filter.h>
+#include "btf.h"
+#include "bpf.h"
+#include "libbpf.h"
+#include "libbpf_internal.h"
+#include "hashmap.h"
+#include "bpf_gen_internal.h"
+#include "skel_internal.h"
+
+#define MAX_USED_MAPS 64
+#define MAX_USED_PROGS 32
+
+/* The following structure describes the stack layout of the loader program.
+ * In addition R6 contains the pointer to context.
+ * R7 contains the result of the last sys_bpf command (typically error or FD).
+ * R9 contains the result of the last sys_close command.
+ *
+ * Naming convention:
+ * ctx - bpf program context
+ * stack - bpf program stack
+ * blob - bpf_attr-s, strings, insns, map data.
+ *        All the bytes that loader prog will use for read/write.
+ */
+struct loader_stack {
+	__u32 btf_fd;
+	__u32 map_fd[MAX_USED_MAPS];
+	__u32 prog_fd[MAX_USED_PROGS];
+	__u32 inner_map_fd;
+};
+
+#define stack_off(field) \
+	(__s16)(-sizeof(struct loader_stack) + offsetof(struct loader_stack, field))
+
+#define attr_field(attr, field) (attr + offsetof(union bpf_attr, field))
+
+static int realloc_insn_buf(struct bpf_gen *gen, __u32 size)
+{
+	size_t off = gen->insn_cur - gen->insn_start;
+	void *insn_start;
+
+	if (gen->error)
+		return gen->error;
+	if (size > INT32_MAX || off + size > INT32_MAX) {
+		gen->error = -ERANGE;
+		return -ERANGE;
+	}
+	insn_start = realloc(gen->insn_start, off + size);
+	if (!insn_start) {
+		gen->error = -ENOMEM;
+		free(gen->insn_start);
+		gen->insn_start = NULL;
+		return -ENOMEM;
+	}
+	gen->insn_start = insn_start;
+	gen->insn_cur = insn_start + off;
+	return 0;
+}
+
+static int realloc_data_buf(struct bpf_gen *gen, __u32 size)
+{
+	size_t off = gen->data_cur - gen->data_start;
+	void *data_start;
+
+	if (gen->error)
+		return gen->error;
+	if (size > INT32_MAX || off + size > INT32_MAX) {
+		gen->error = -ERANGE;
+		return -ERANGE;
+	}
+	data_start = realloc(gen->data_start, off + size);
+	if (!data_start) {
+		gen->error = -ENOMEM;
+		free(gen->data_start);
+		gen->data_start = NULL;
+		return -ENOMEM;
+	}
+	gen->data_start = data_start;
+	gen->data_cur = data_start + off;
+	return 0;
+}
+
+static void emit(struct bpf_gen *gen, struct bpf_insn insn)
+{
+	if (realloc_insn_buf(gen, sizeof(insn)))
+		return;
+	memcpy(gen->insn_cur, &insn, sizeof(insn));
+	gen->insn_cur += sizeof(insn);
+}
+
+static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn insn2)
+{
+	emit(gen, insn1);
+	emit(gen, insn2);
+}
+
+void bpf_gen__init(struct bpf_gen *gen, int log_level)
+{
+	size_t stack_sz = sizeof(struct loader_stack);
+	int i;
+
+	gen->log_level = log_level;
+	/* save ctx pointer into R6 */
+	emit(gen, BPF_MOV64_REG(BPF_REG_6, BPF_REG_1));
+
+	/* bzero stack */
+	emit(gen, BPF_MOV64_REG(BPF_REG_1, BPF_REG_10));
+	emit(gen, BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -stack_sz));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_2, stack_sz));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel));
+
+	/* jump over cleanup code */
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0,
+			      /* size of cleanup code below */
+			      (stack_sz / 4) * 3 + 2));
+
+	/* remember the label where all error branches will jump to */
+	gen->cleanup_label = gen->insn_cur - gen->insn_start;
+	/* emit cleanup code: close all temp FDs */
+	for (i = 0; i < stack_sz; i += 4) {
+		emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -stack_sz + i));
+		emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, 1));
+		emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close));
+	}
+	/* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */
+	emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
+	emit(gen, BPF_EXIT_INSN());
+}
+
+static int add_data(struct bpf_gen *gen, const void *data, __u32 size)
+{
+	void *prev;
+
+	if (realloc_data_buf(gen, size))
+		return 0;
+	prev = gen->data_cur;
+	memcpy(gen->data_cur, data, size);
+	gen->data_cur += size;
+	return prev - gen->data_start;
+}
+
+static int insn_bytes_to_bpf_size(__u32 sz)
+{
+	switch (sz) {
+	case 8: return BPF_DW;
+	case 4: return BPF_W;
+	case 2: return BPF_H;
+	case 1: return BPF_B;
+	default: return -1;
+	}
+}
+
+/* *(u64 *)(blob + off) = (u64)(void *)(blob + data) */
+static void emit_rel_store(struct bpf_gen *gen, int off, int data)
+{
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, data));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, off));
+	emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0));
+}
+
+/* *(u64 *)(blob + off) = (u64)(void *)(%sp + stack_off) */
+static void emit_rel_store_sp(struct bpf_gen *gen, int off, int stack_off)
+{
+	emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_10));
+	emit(gen, BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, stack_off));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, off));
+	emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0));
+}
+
+static void move_ctx2blob(struct bpf_gen *gen, int off, int size, int ctx_off,
+				   bool check_non_zero)
+{
+	emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_6, ctx_off));
+	if (check_non_zero)
+		/* If value in ctx is zero don't update the blob.
+		 * For example: when ctx->map.max_entries == 0, keep default max_entries from bpf.c
+		 */
+		emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, off));
+	emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_1, BPF_REG_0, 0));
+}
+
+static void move_stack2blob(struct bpf_gen *gen, int off, int size, int stack_off)
+{
+	emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_10, stack_off));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, off));
+	emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_1, BPF_REG_0, 0));
+}
+
+static void move_stack2ctx(struct bpf_gen *gen, int ctx_off, int size, int stack_off)
+{
+	emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_10, stack_off));
+	emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_6, BPF_REG_0, ctx_off));
+}
+
+static void emit_sys_bpf(struct bpf_gen *gen, int cmd, int attr, int attr_size)
+{
+	emit(gen, BPF_MOV64_IMM(BPF_REG_1, cmd));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_2, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, attr));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_3, attr_size));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_bpf));
+	/* remember the result in R7 */
+	emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0));
+}
+
+static bool is_simm16(__s64 value)
+{
+	return value == (__s64)(__s16)value;
+}
+
+static void emit_check_err(struct bpf_gen *gen)
+{
+	__s64 off = -(gen->insn_cur - gen->insn_start - gen->cleanup_label) / 8 - 1;
+
+	/* R7 contains result of last sys_bpf command.
+	 * if (R7 < 0) goto cleanup;
+	 */
+	if (is_simm16(off)) {
+		emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, off));
+	} else {
+		gen->error = -ERANGE;
+		emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, -1));
+	}
+}
+
+/* reg1 and reg2 should not be R1 - R5. They can be R0, R6 - R10 */
+static void emit_debug(struct bpf_gen *gen, int reg1, int reg2,
+		       const char *fmt, va_list args)
+{
+	char buf[1024];
+	int addr, len, ret;
+
+	if (!gen->log_level)
+		return;
+	ret = vsnprintf(buf, sizeof(buf), fmt, args);
+	if (ret < 1024 - 7 && reg1 >= 0 && reg2 < 0)
+		/* The special case to accommodate common debug_ret():
+		 * to avoid specifying BPF_REG_7 and adding " r=%%d" to
+		 * prints explicitly.
+		 */
+		strcat(buf, " r=%d");
+	len = strlen(buf) + 1;
+	addr = add_data(gen, buf, len);
+
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, addr));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_2, len));
+	if (reg1 >= 0)
+		emit(gen, BPF_MOV64_REG(BPF_REG_3, reg1));
+	if (reg2 >= 0)
+		emit(gen, BPF_MOV64_REG(BPF_REG_4, reg2));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_trace_printk));
+}
+
+static void debug_regs(struct bpf_gen *gen, int reg1, int reg2, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	emit_debug(gen, reg1, reg2, fmt, args);
+	va_end(args);
+}
+
+static void debug_ret(struct bpf_gen *gen, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	emit_debug(gen, BPF_REG_7, -1, fmt, args);
+	va_end(args);
+}
+
+static void __emit_sys_close(struct bpf_gen *gen)
+{
+	emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0,
+			      /* 2 is the number of the following insns
+			       * * 6 is additional insns in debug_regs
+			       */
+			      2 + (gen->log_level ? 6 : 0)));
+	emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_1));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close));
+	debug_regs(gen, BPF_REG_9, BPF_REG_0, "close(%%d) = %%d");
+}
+
+static void emit_sys_close_stack(struct bpf_gen *gen, int stack_off)
+{
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, stack_off));
+	__emit_sys_close(gen);
+}
+
+static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off)
+{
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, blob_off));
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0));
+	__emit_sys_close(gen);
+}
+
+int bpf_gen__finish(struct bpf_gen *gen)
+{
+	int i;
+
+	emit_sys_close_stack(gen, stack_off(btf_fd));
+	for (i = 0; i < gen->nr_progs; i++)
+		move_stack2ctx(gen,
+			       sizeof(struct bpf_loader_ctx) +
+			       sizeof(struct bpf_map_desc) * gen->nr_maps +
+			       sizeof(struct bpf_prog_desc) * i +
+			       offsetof(struct bpf_prog_desc, prog_fd), 4,
+			       stack_off(prog_fd[i]));
+	for (i = 0; i < gen->nr_maps; i++)
+		move_stack2ctx(gen,
+			       sizeof(struct bpf_loader_ctx) +
+			       sizeof(struct bpf_map_desc) * i +
+			       offsetof(struct bpf_map_desc, map_fd), 4,
+			       stack_off(map_fd[i]));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_0, 0));
+	emit(gen, BPF_EXIT_INSN());
+	pr_debug("gen: finish %d\n", gen->error);
+	if (!gen->error) {
+		struct gen_loader_opts *opts = gen->opts;
+
+		opts->insns = gen->insn_start;
+		opts->insns_sz = gen->insn_cur - gen->insn_start;
+		opts->data = gen->data_start;
+		opts->data_sz = gen->data_cur - gen->data_start;
+	}
+	return gen->error;
+}
+
+void bpf_gen__free(struct bpf_gen *gen)
+{
+	if (!gen)
+		return;
+	free(gen->data_start);
+	free(gen->insn_start);
+	free(gen);
+}
+
+void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data,
+		       __u32 btf_raw_size)
+{
+	int attr_size = offsetofend(union bpf_attr, btf_log_level);
+	int btf_data, btf_load_attr;
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_size);
+	pr_debug("gen: load_btf: size %d\n", btf_raw_size);
+	btf_data = add_data(gen, btf_raw_data, btf_raw_size);
+
+	attr.btf_size = btf_raw_size;
+	btf_load_attr = add_data(gen, &attr, attr_size);
+
+	/* populate union bpf_attr with user provided log details */
+	move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_level), 4,
+		      offsetof(struct bpf_loader_ctx, log_level), false);
+	move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_size), 4,
+		      offsetof(struct bpf_loader_ctx, log_size), false);
+	move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_buf), 8,
+		      offsetof(struct bpf_loader_ctx, log_buf), false);
+	/* populate union bpf_attr with a pointer to the BTF data */
+	emit_rel_store(gen, attr_field(btf_load_attr, btf), btf_data);
+	/* emit BTF_LOAD command */
+	emit_sys_bpf(gen, BPF_BTF_LOAD, btf_load_attr, attr_size);
+	debug_ret(gen, "btf_load size %d", btf_raw_size);
+	emit_check_err(gen);
+	/* remember btf_fd in the stack, if successful */
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, stack_off(btf_fd)));
+}
+
+void bpf_gen__map_create(struct bpf_gen *gen,
+			 struct bpf_create_map_attr *map_attr, int map_idx)
+{
+	int attr_size = offsetofend(union bpf_attr, btf_vmlinux_value_type_id);
+	bool close_inner_map_fd = false;
+	int map_create_attr;
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_size);
+	attr.map_type = map_attr->map_type;
+	attr.key_size = map_attr->key_size;
+	attr.value_size = map_attr->value_size;
+	attr.map_flags = map_attr->map_flags;
+	memcpy(attr.map_name, map_attr->name,
+	       min((unsigned)strlen(map_attr->name), BPF_OBJ_NAME_LEN - 1));
+	attr.numa_node = map_attr->numa_node;
+	attr.map_ifindex = map_attr->map_ifindex;
+	attr.max_entries = map_attr->max_entries;
+	switch (attr.map_type) {
+	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+	case BPF_MAP_TYPE_CGROUP_ARRAY:
+	case BPF_MAP_TYPE_STACK_TRACE:
+	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
+	case BPF_MAP_TYPE_HASH_OF_MAPS:
+	case BPF_MAP_TYPE_DEVMAP:
+	case BPF_MAP_TYPE_DEVMAP_HASH:
+	case BPF_MAP_TYPE_CPUMAP:
+	case BPF_MAP_TYPE_XSKMAP:
+	case BPF_MAP_TYPE_SOCKMAP:
+	case BPF_MAP_TYPE_SOCKHASH:
+	case BPF_MAP_TYPE_QUEUE:
+	case BPF_MAP_TYPE_STACK:
+	case BPF_MAP_TYPE_RINGBUF:
+		break;
+	default:
+		attr.btf_key_type_id = map_attr->btf_key_type_id;
+		attr.btf_value_type_id = map_attr->btf_value_type_id;
+	}
+
+	pr_debug("gen: map_create: %s idx %d type %d value_type_id %d\n",
+		 attr.map_name, map_idx, map_attr->map_type, attr.btf_value_type_id);
+
+	map_create_attr = add_data(gen, &attr, attr_size);
+	if (attr.btf_value_type_id)
+		/* populate union bpf_attr with btf_fd saved in the stack earlier */
+		move_stack2blob(gen, attr_field(map_create_attr, btf_fd), 4,
+				stack_off(btf_fd));
+	switch (attr.map_type) {
+	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
+	case BPF_MAP_TYPE_HASH_OF_MAPS:
+		move_stack2blob(gen, attr_field(map_create_attr, inner_map_fd), 4,
+				stack_off(inner_map_fd));
+		close_inner_map_fd = true;
+		break;
+	default:
+		break;
+	}
+	/* conditionally update max_entries */
+	if (map_idx >= 0)
+		move_ctx2blob(gen, attr_field(map_create_attr, max_entries), 4,
+			      sizeof(struct bpf_loader_ctx) +
+			      sizeof(struct bpf_map_desc) * map_idx +
+			      offsetof(struct bpf_map_desc, max_entries),
+			      true /* check that max_entries != 0 */);
+	/* emit MAP_CREATE command */
+	emit_sys_bpf(gen, BPF_MAP_CREATE, map_create_attr, attr_size);
+	debug_ret(gen, "map_create %s idx %d type %d value_size %d value_btf_id %d",
+		  attr.map_name, map_idx, map_attr->map_type, attr.value_size,
+		  attr.btf_value_type_id);
+	emit_check_err(gen);
+	/* remember map_fd in the stack, if successful */
+	if (map_idx < 0) {
+		/* This bpf_gen__map_create() function is called with map_idx >= 0
+		 * for all maps that libbpf loading logic tracks.
+		 * It's called with -1 to create an inner map.
+		 */
+		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7,
+				      stack_off(inner_map_fd)));
+	} else if (map_idx != gen->nr_maps) {
+		gen->error = -EDOM; /* internal bug */
+		return;
+	} else {
+		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7,
+				      stack_off(map_fd[map_idx])));
+		gen->nr_maps++;
+	}
+	if (close_inner_map_fd)
+		emit_sys_close_stack(gen, stack_off(inner_map_fd));
+}
+
+void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *attach_name,
+				   enum bpf_attach_type type)
+{
+	const char *prefix;
+	int kind, ret;
+
+	btf_get_kernel_prefix_kind(type, &prefix, &kind);
+	gen->attach_kind = kind;
+	ret = snprintf(gen->attach_target, sizeof(gen->attach_target), "%s%s",
+		       prefix, attach_name);
+	if (ret == sizeof(gen->attach_target))
+		gen->error = -ENOSPC;
+}
+
+static void emit_find_attach_target(struct bpf_gen *gen)
+{
+	int name, len = strlen(gen->attach_target) + 1;
+
+	pr_debug("gen: find_attach_tgt %s %d\n", gen->attach_target, gen->attach_kind);
+	name = add_data(gen, gen->attach_target, len);
+
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, name));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_2, len));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_3, gen->attach_kind));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_4, 0));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_btf_find_by_name_kind));
+	emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0));
+	debug_ret(gen, "find_by_name_kind(%s,%d)",
+		  gen->attach_target, gen->attach_kind);
+	emit_check_err(gen);
+	/* if successful, btf_id is in lower 32-bit of R7 and
+	 * btf_obj_fd is in upper 32-bit
+	 */
+}
+
+void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind,
+			    int insn_idx)
+{
+	struct ksym_relo_desc *relo;
+
+	relo = libbpf_reallocarray(gen->relos, gen->relo_cnt + 1, sizeof(*relo));
+	if (!relo) {
+		gen->error = -ENOMEM;
+		return;
+	}
+	gen->relos = relo;
+	relo += gen->relo_cnt;
+	relo->name = name;
+	relo->kind = kind;
+	relo->insn_idx = insn_idx;
+	gen->relo_cnt++;
+}
+
+static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns)
+{
+	int name, insn, len = strlen(relo->name) + 1;
+
+	pr_debug("gen: emit_relo: %s at %d\n", relo->name, relo->insn_idx);
+	name = add_data(gen, relo->name, len);
+
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, name));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_2, len));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_3, relo->kind));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_4, 0));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_btf_find_by_name_kind));
+	emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0));
+	debug_ret(gen, "find_by_name_kind(%s,%d)", relo->name, relo->kind);
+	emit_check_err(gen);
+	/* store btf_id into insn[insn_idx].imm */
+	insn = insns + sizeof(struct bpf_insn) * relo->insn_idx +
+		offsetof(struct bpf_insn, imm);
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, insn));
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, 0));
+	if (relo->kind == BTF_KIND_VAR) {
+		/* store btf_obj_fd into insn[insn_idx + 1].imm */
+		emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32));
+		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7,
+				      sizeof(struct bpf_insn)));
+	}
+}
+
+static void emit_relos(struct bpf_gen *gen, int insns)
+{
+	int i;
+
+	for (i = 0; i < gen->relo_cnt; i++)
+		emit_relo(gen, gen->relos + i, insns);
+}
+
+static void cleanup_relos(struct bpf_gen *gen, int insns)
+{
+	int i, insn;
+
+	for (i = 0; i < gen->relo_cnt; i++) {
+		if (gen->relos[i].kind != BTF_KIND_VAR)
+			continue;
+		/* close fd recorded in insn[insn_idx + 1].imm */
+		insn = insns +
+			sizeof(struct bpf_insn) * (gen->relos[i].insn_idx + 1) +
+			offsetof(struct bpf_insn, imm);
+		emit_sys_close_blob(gen, insn);
+	}
+	if (gen->relo_cnt) {
+		free(gen->relos);
+		gen->relo_cnt = 0;
+		gen->relos = NULL;
+	}
+}
+
+void bpf_gen__prog_load(struct bpf_gen *gen,
+			struct bpf_prog_load_params *load_attr, int prog_idx)
+{
+	int attr_size = offsetofend(union bpf_attr, fd_array);
+	int prog_load_attr, license, insns, func_info, line_info;
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_size);
+	pr_debug("gen: prog_load: type %d insns_cnt %zd\n",
+		 load_attr->prog_type, load_attr->insn_cnt);
+	/* add license string to blob of bytes */
+	license = add_data(gen, load_attr->license, strlen(load_attr->license) + 1);
+	/* add insns to blob of bytes */
+	insns = add_data(gen, load_attr->insns,
+			 load_attr->insn_cnt * sizeof(struct bpf_insn));
+
+	attr.prog_type = load_attr->prog_type;
+	attr.expected_attach_type = load_attr->expected_attach_type;
+	attr.attach_btf_id = load_attr->attach_btf_id;
+	attr.prog_ifindex = load_attr->prog_ifindex;
+	attr.kern_version = 0;
+	attr.insn_cnt = (__u32)load_attr->insn_cnt;
+	attr.prog_flags = load_attr->prog_flags;
+
+	attr.func_info_rec_size = load_attr->func_info_rec_size;
+	attr.func_info_cnt = load_attr->func_info_cnt;
+	func_info = add_data(gen, load_attr->func_info,
+			     attr.func_info_cnt * attr.func_info_rec_size);
+
+	attr.line_info_rec_size = load_attr->line_info_rec_size;
+	attr.line_info_cnt = load_attr->line_info_cnt;
+	line_info = add_data(gen, load_attr->line_info,
+			     attr.line_info_cnt * attr.line_info_rec_size);
+
+	memcpy(attr.prog_name, load_attr->name,
+	       min((unsigned)strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1));
+	prog_load_attr = add_data(gen, &attr, attr_size);
+
+	/* populate union bpf_attr with a pointer to license */
+	emit_rel_store(gen, attr_field(prog_load_attr, license), license);
+
+	/* populate union bpf_attr with a pointer to instructions */
+	emit_rel_store(gen, attr_field(prog_load_attr, insns), insns);
+
+	/* populate union bpf_attr with a pointer to func_info */
+	emit_rel_store(gen, attr_field(prog_load_attr, func_info), func_info);
+
+	/* populate union bpf_attr with a pointer to line_info */
+	emit_rel_store(gen, attr_field(prog_load_attr, line_info), line_info);
+
+	/* populate union bpf_attr fd_array with a pointer to stack where map_fds are saved */
+	emit_rel_store_sp(gen, attr_field(prog_load_attr, fd_array),
+			  stack_off(map_fd[0]));
+
+	/* populate union bpf_attr with user provided log details */
+	move_ctx2blob(gen, attr_field(prog_load_attr, log_level), 4,
+		      offsetof(struct bpf_loader_ctx, log_level), false);
+	move_ctx2blob(gen, attr_field(prog_load_attr, log_size), 4,
+		      offsetof(struct bpf_loader_ctx, log_size), false);
+	move_ctx2blob(gen, attr_field(prog_load_attr, log_buf), 8,
+		      offsetof(struct bpf_loader_ctx, log_buf), false);
+	/* populate union bpf_attr with btf_fd saved in the stack earlier */
+	move_stack2blob(gen, attr_field(prog_load_attr, prog_btf_fd), 4,
+			stack_off(btf_fd));
+	if (gen->attach_kind) {
+		emit_find_attach_target(gen);
+		/* populate union bpf_attr with btf_id and btf_obj_fd found by helper */
+		emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
+						 0, 0, 0, prog_load_attr));
+		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7,
+				      offsetof(union bpf_attr, attach_btf_id)));
+		emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32));
+		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7,
+				      offsetof(union bpf_attr, attach_btf_obj_fd)));
+	}
+	emit_relos(gen, insns);
+	/* emit PROG_LOAD command */
+	emit_sys_bpf(gen, BPF_PROG_LOAD, prog_load_attr, attr_size);
+	debug_ret(gen, "prog_load %s insn_cnt %d", attr.prog_name, attr.insn_cnt);
+	/* successful or not, close btf module FDs used in extern ksyms and attach_btf_obj_fd */
+	cleanup_relos(gen, insns);
+	if (gen->attach_kind)
+		emit_sys_close_blob(gen,
+				    attr_field(prog_load_attr, attach_btf_obj_fd));
+	emit_check_err(gen);
+	/* remember prog_fd in the stack, if successful */
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7,
+			      stack_off(prog_fd[gen->nr_progs])));
+	gen->nr_progs++;
+}
+
+void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
+			      __u32 value_size)
+{
+	int attr_size = offsetofend(union bpf_attr, flags);
+	int map_update_attr, value, key;
+	union bpf_attr attr;
+	int zero = 0;
+
+	memset(&attr, 0, attr_size);
+	pr_debug("gen: map_update_elem: idx %d\n", map_idx);
+
+	value = add_data(gen, pvalue, value_size);
+	key = add_data(gen, &zero, sizeof(zero));
+
+	/* if (map_desc[map_idx].initial_value)
+	 *    copy_from_user(value, initial_value, value_size);
+	 */
+	emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_6,
+			      sizeof(struct bpf_loader_ctx) +
+			      sizeof(struct bpf_map_desc) * map_idx +
+			      offsetof(struct bpf_map_desc, initial_value)));
+	emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 4));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, value));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_2, value_size));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_copy_from_user));
+
+	map_update_attr = add_data(gen, &attr, attr_size);
+	move_stack2blob(gen, attr_field(map_update_attr, map_fd), 4,
+			stack_off(map_fd[map_idx]));
+	emit_rel_store(gen, attr_field(map_update_attr, key), key);
+	emit_rel_store(gen, attr_field(map_update_attr, value), value);
+	/* emit MAP_UPDATE_ELEM command */
+	emit_sys_bpf(gen, BPF_MAP_UPDATE_ELEM, map_update_attr, attr_size);
+	debug_ret(gen, "update_elem idx %d value_size %d", map_idx, value_size);
+	emit_check_err(gen);
+}
+
+void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx)
+{
+	int attr_size = offsetofend(union bpf_attr, map_fd);
+	int map_freeze_attr;
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_size);
+	pr_debug("gen: map_freeze: idx %d\n", map_idx);
+	map_freeze_attr = add_data(gen, &attr, attr_size);
+	move_stack2blob(gen, attr_field(map_freeze_attr, map_fd), 4,
+			stack_off(map_fd[map_idx]));
+	/* emit MAP_FREEZE command */
+	emit_sys_bpf(gen, BPF_MAP_FREEZE, map_freeze_attr, attr_size);
+	debug_ret(gen, "map_freeze");
+	emit_check_err(gen);
+}
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index c41d9b2b59ac..48c0ade05ab1 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -54,6 +54,7 @@
 #include "str_error.h"
 #include "libbpf_internal.h"
 #include "hashmap.h"
+#include "bpf_gen_internal.h"
 
 #ifndef BPF_FS_MAGIC
 #define BPF_FS_MAGIC		0xcafe4a11
@@ -150,6 +151,23 @@ static inline __u64 ptr_to_u64(const void *ptr)
 	return (__u64) (unsigned long) ptr;
 }
 
+/* this goes away in libbpf 1.0 */
+enum libbpf_strict_mode libbpf_mode = LIBBPF_STRICT_NONE;
+
+int libbpf_set_strict_mode(enum libbpf_strict_mode mode)
+{
+	/* __LIBBPF_STRICT_LAST is the last power-of-2 value used + 1, so to
+	 * get all possible values we compensate last +1, and then (2*x - 1)
+	 * to get the bit mask
+	 */
+	if (mode != LIBBPF_STRICT_ALL
+	    && (mode & ~((__LIBBPF_STRICT_LAST - 1) * 2 - 1)))
+		return errno = EINVAL, -EINVAL;
+
+	libbpf_mode = mode;
+	return 0;
+}
+
 enum kern_feature_id {
 	/* v4.14: kernel support for program & map names. */
 	FEAT_PROG_NAME,
@@ -178,7 +196,7 @@ enum kern_feature_id {
 	__FEAT_CNT,
 };
 
-static bool kernel_supports(enum kern_feature_id feat_id);
+static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id);
 
 enum reloc_type {
 	RELO_LD64,
@@ -432,6 +450,8 @@ struct bpf_object {
 	bool loaded;
 	bool has_subcalls;
 
+	struct bpf_gen *gen_loader;
+
 	/*
 	 * Information when doing elf related work. Only valid if fd
 	 * is valid.
@@ -677,6 +697,11 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
+		if (sec_idx != obj->efile.text_shndx && GELF_ST_BIND(sym.st_info) == STB_LOCAL) {
+			pr_warn("sec '%s': program '%s' is static and not supported\n", sec_name, name);
+			return -ENOTSUP;
+		}
+
 		pr_debug("sec '%s': found program '%s' at insn offset %zu (%zu bytes), code size %zu insns (%zu bytes)\n",
 			 sec_name, name, sec_off / BPF_INSN_SZ, sec_off, prog_sz / BPF_INSN_SZ, prog_sz);
 
@@ -700,13 +725,14 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
 		if (err)
 			return err;
 
-		/* if function is a global/weak symbol, but has hidden
-		 * visibility (STV_HIDDEN), mark its BTF FUNC as static to
-		 * enable more permissive BPF verification mode with more
-		 * outside context available to BPF verifier
+		/* if function is a global/weak symbol, but has restricted
+		 * (STV_HIDDEN or STV_INTERNAL) visibility, mark its BTF FUNC
+		 * as static to enable more permissive BPF verification mode
+		 * with more outside context available to BPF verifier
 		 */
 		if (GELF_ST_BIND(sym.st_info) != STB_LOCAL
-		    && GELF_ST_VISIBILITY(sym.st_other) == STV_HIDDEN)
+		    && (GELF_ST_VISIBILITY(sym.st_other) == STV_HIDDEN
+			|| GELF_ST_VISIBILITY(sym.st_other) == STV_INTERNAL))
 			prog->mark_btf_static = true;
 
 		nr_progs++;
@@ -1794,7 +1820,6 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 	if (!symbols)
 		return -EINVAL;
 
-
 	scn = elf_sec_by_idx(obj, obj->efile.maps_shndx);
 	data = elf_sec_data(obj, scn);
 	if (!scn || !data) {
@@ -1854,6 +1879,12 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
+		if (GELF_ST_TYPE(sym.st_info) == STT_SECTION
+		    || GELF_ST_BIND(sym.st_info) == STB_LOCAL) {
+			pr_warn("map '%s' (legacy): static maps are not supported\n", map_name);
+			return -ENOTSUP;
+		}
+
 		map->libbpf_type = LIBBPF_MAP_UNSPEC;
 		map->sec_idx = sym.st_shndx;
 		map->sec_offset = sym.st_value;
@@ -2261,6 +2292,16 @@ static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def
 		pr_debug("map '%s': found inner map definition.\n", map->name);
 }
 
+static const char *btf_var_linkage_str(__u32 linkage)
+{
+	switch (linkage) {
+	case BTF_VAR_STATIC: return "static";
+	case BTF_VAR_GLOBAL_ALLOCATED: return "global";
+	case BTF_VAR_GLOBAL_EXTERN: return "extern";
+	default: return "unknown";
+	}
+}
+
 static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 					 const struct btf_type *sec,
 					 int var_idx, int sec_idx,
@@ -2293,10 +2334,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 			map_name, btf_kind_str(var));
 		return -EINVAL;
 	}
-	if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED &&
-	    var_extra->linkage != BTF_VAR_STATIC) {
-		pr_warn("map '%s': unsupported var linkage %u.\n",
-			map_name, var_extra->linkage);
+	if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED) {
+		pr_warn("map '%s': unsupported map linkage %s.\n",
+			map_name, btf_var_linkage_str(var_extra->linkage));
 		return -EOPNOTSUPP;
 	}
 
@@ -2425,10 +2465,8 @@ static int bpf_object__init_maps(struct bpf_object *obj,
 	err = err ?: bpf_object__init_global_data_maps(obj);
 	err = err ?: bpf_object__init_kconfig_map(obj);
 	err = err ?: bpf_object__init_struct_ops_maps(obj);
-	if (err)
-		return err;
 
-	return 0;
+	return err;
 }
 
 static bool section_have_execinstr(struct bpf_object *obj, int idx)
@@ -2443,20 +2481,20 @@ static bool section_have_execinstr(struct bpf_object *obj, int idx)
 
 static bool btf_needs_sanitization(struct bpf_object *obj)
 {
-	bool has_func_global = kernel_supports(FEAT_BTF_GLOBAL_FUNC);
-	bool has_datasec = kernel_supports(FEAT_BTF_DATASEC);
-	bool has_float = kernel_supports(FEAT_BTF_FLOAT);
-	bool has_func = kernel_supports(FEAT_BTF_FUNC);
+	bool has_func_global = kernel_supports(obj, FEAT_BTF_GLOBAL_FUNC);
+	bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC);
+	bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT);
+	bool has_func = kernel_supports(obj, FEAT_BTF_FUNC);
 
 	return !has_func || !has_datasec || !has_func_global || !has_float;
 }
 
 static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf)
 {
-	bool has_func_global = kernel_supports(FEAT_BTF_GLOBAL_FUNC);
-	bool has_datasec = kernel_supports(FEAT_BTF_DATASEC);
-	bool has_float = kernel_supports(FEAT_BTF_FLOAT);
-	bool has_func = kernel_supports(FEAT_BTF_FUNC);
+	bool has_func_global = kernel_supports(obj, FEAT_BTF_GLOBAL_FUNC);
+	bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC);
+	bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT);
+	bool has_func = kernel_supports(obj, FEAT_BTF_FUNC);
 	struct btf_type *t;
 	int i, j, vlen;
 
@@ -2539,16 +2577,14 @@ static int bpf_object__init_btf(struct bpf_object *obj,
 
 	if (btf_data) {
 		obj->btf = btf__new(btf_data->d_buf, btf_data->d_size);
-		if (IS_ERR(obj->btf)) {
-			err = PTR_ERR(obj->btf);
+		err = libbpf_get_error(obj->btf);
+		if (err) {
 			obj->btf = NULL;
-			pr_warn("Error loading ELF section %s: %d.\n",
-				BTF_ELF_SEC, err);
+			pr_warn("Error loading ELF section %s: %d.\n", BTF_ELF_SEC, err);
 			goto out;
 		}
 		/* enforce 8-byte pointers for BPF-targeted BTFs */
 		btf__set_pointer_size(obj->btf, 8);
-		err = 0;
 	}
 	if (btf_ext_data) {
 		if (!obj->btf) {
@@ -2556,11 +2592,11 @@ static int bpf_object__init_btf(struct bpf_object *obj,
 				 BTF_EXT_ELF_SEC, BTF_ELF_SEC);
 			goto out;
 		}
-		obj->btf_ext = btf_ext__new(btf_ext_data->d_buf,
-					    btf_ext_data->d_size);
-		if (IS_ERR(obj->btf_ext)) {
-			pr_warn("Error loading ELF section %s: %ld. Ignored and continue.\n",
-				BTF_EXT_ELF_SEC, PTR_ERR(obj->btf_ext));
+		obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size);
+		err = libbpf_get_error(obj->btf_ext);
+		if (err) {
+			pr_warn("Error loading ELF section %s: %d. Ignored and continue.\n",
+				BTF_EXT_ELF_SEC, err);
 			obj->btf_ext = NULL;
 			goto out;
 		}
@@ -2637,15 +2673,15 @@ static int bpf_object__load_vmlinux_btf(struct bpf_object *obj, bool force)
 	int err;
 
 	/* btf_vmlinux could be loaded earlier */
-	if (obj->btf_vmlinux)
+	if (obj->btf_vmlinux || obj->gen_loader)
 		return 0;
 
 	if (!force && !obj_needs_vmlinux_btf(obj))
 		return 0;
 
 	obj->btf_vmlinux = libbpf_find_kernel_btf();
-	if (IS_ERR(obj->btf_vmlinux)) {
-		err = PTR_ERR(obj->btf_vmlinux);
+	err = libbpf_get_error(obj->btf_vmlinux);
+	if (err) {
 		pr_warn("Error loading vmlinux BTF: %d\n", err);
 		obj->btf_vmlinux = NULL;
 		return err;
@@ -2662,7 +2698,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 	if (!obj->btf)
 		return 0;
 
-	if (!kernel_supports(FEAT_BTF)) {
+	if (!kernel_supports(obj, FEAT_BTF)) {
 		if (kernel_needs_btf(obj)) {
 			err = -EOPNOTSUPP;
 			goto report;
@@ -2711,15 +2747,29 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 		/* clone BTF to sanitize a copy and leave the original intact */
 		raw_data = btf__get_raw_data(obj->btf, &sz);
 		kern_btf = btf__new(raw_data, sz);
-		if (IS_ERR(kern_btf))
-			return PTR_ERR(kern_btf);
+		err = libbpf_get_error(kern_btf);
+		if (err)
+			return err;
 
 		/* enforce 8-byte pointers for BPF-targeted BTFs */
 		btf__set_pointer_size(obj->btf, 8);
 		bpf_object__sanitize_btf(obj, kern_btf);
 	}
 
-	err = btf__load(kern_btf);
+	if (obj->gen_loader) {
+		__u32 raw_size = 0;
+		const void *raw_data = btf__get_raw_data(kern_btf, &raw_size);
+
+		if (!raw_data)
+			return -ENOMEM;
+		bpf_gen__load_btf(obj->gen_loader, raw_data, raw_size);
+		/* Pretend to have valid FD to pass various fd >= 0 checks.
+		 * This fd == 0 will not be used with any syscall and will be reset to -1 eventually.
+		 */
+		btf__set_fd(kern_btf, 0);
+	} else {
+		err = btf__load(kern_btf);
+	}
 	if (sanitize) {
 		if (!err) {
 			/* move fd to libbpf's BTF */
@@ -3473,7 +3523,7 @@ bpf_object__find_program_by_title(const struct bpf_object *obj,
 		if (pos->sec_name && !strcmp(pos->sec_name, title))
 			return pos;
 	}
-	return NULL;
+	return errno = ENOENT, NULL;
 }
 
 static bool prog_is_subprog(const struct bpf_object *obj,
@@ -3506,7 +3556,7 @@ bpf_object__find_program_by_name(const struct bpf_object *obj,
 		if (!strcmp(prog->name, name))
 			return prog;
 	}
-	return NULL;
+	return errno = ENOENT, NULL;
 }
 
 static bool bpf_object__shndx_is_data(const struct bpf_object *obj,
@@ -3853,11 +3903,11 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 
 	err = bpf_obj_get_info_by_fd(fd, &info, &len);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	new_name = strdup(info.name);
 	if (!new_name)
-		return -errno;
+		return libbpf_err(-errno);
 
 	new_fd = open("/", O_RDONLY | O_CLOEXEC);
 	if (new_fd < 0) {
@@ -3895,7 +3945,7 @@ err_close_new_fd:
 	close(new_fd);
 err_free_new_name:
 	free(new_name);
-	return err;
+	return libbpf_err(err);
 }
 
 __u32 bpf_map__max_entries(const struct bpf_map *map)
@@ -3906,7 +3956,7 @@ __u32 bpf_map__max_entries(const struct bpf_map *map)
 struct bpf_map *bpf_map__inner_map(struct bpf_map *map)
 {
 	if (!bpf_map_type__is_map_in_map(map->def.type))
-		return NULL;
+		return errno = EINVAL, NULL;
 
 	return map->inner_map;
 }
@@ -3914,7 +3964,7 @@ struct bpf_map *bpf_map__inner_map(struct bpf_map *map)
 int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries)
 {
 	if (map->fd >= 0)
-		return -EBUSY;
+		return libbpf_err(-EBUSY);
 	map->def.max_entries = max_entries;
 	return 0;
 }
@@ -3922,7 +3972,7 @@ int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries)
 int bpf_map__resize(struct bpf_map *map, __u32 max_entries)
 {
 	if (!map || !max_entries)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	return bpf_map__set_max_entries(map, max_entries);
 }
@@ -3938,6 +3988,9 @@ bpf_object__probe_loading(struct bpf_object *obj)
 	};
 	int ret;
 
+	if (obj->gen_loader)
+		return 0;
+
 	/* make sure basic loading works */
 
 	memset(&attr, 0, sizeof(attr));
@@ -4293,11 +4346,17 @@ static struct kern_feature_desc {
 	},
 };
 
-static bool kernel_supports(enum kern_feature_id feat_id)
+static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
 {
 	struct kern_feature_desc *feat = &feature_probes[feat_id];
 	int ret;
 
+	if (obj->gen_loader)
+		/* To generate loader program assume the latest kernel
+		 * to avoid doing extra prog_load, map_create syscalls.
+		 */
+		return true;
+
 	if (READ_ONCE(feat->res) == FEAT_UNKNOWN) {
 		ret = feat->probe();
 		if (ret > 0) {
@@ -4380,6 +4439,13 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
 	char *cp, errmsg[STRERR_BUFSIZE];
 	int err, zero = 0;
 
+	if (obj->gen_loader) {
+		bpf_gen__map_update_elem(obj->gen_loader, map - obj->maps,
+					 map->mmaped, map->def.value_size);
+		if (map_type == LIBBPF_MAP_RODATA || map_type == LIBBPF_MAP_KCONFIG)
+			bpf_gen__map_freeze(obj->gen_loader, map - obj->maps);
+		return 0;
+	}
 	err = bpf_map_update_elem(map->fd, &zero, map->mmaped, 0);
 	if (err) {
 		err = -errno;
@@ -4405,14 +4471,14 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
 
 static void bpf_map__destroy(struct bpf_map *map);
 
-static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map)
+static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner)
 {
 	struct bpf_create_map_attr create_attr;
 	struct bpf_map_def *def = &map->def;
 
 	memset(&create_attr, 0, sizeof(create_attr));
 
-	if (kernel_supports(FEAT_PROG_NAME))
+	if (kernel_supports(obj, FEAT_PROG_NAME))
 		create_attr.name = map->name;
 	create_attr.map_ifindex = map->map_ifindex;
 	create_attr.map_type = def->type;
@@ -4453,7 +4519,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map)
 		if (map->inner_map) {
 			int err;
 
-			err = bpf_object__create_map(obj, map->inner_map);
+			err = bpf_object__create_map(obj, map->inner_map, true);
 			if (err) {
 				pr_warn("map '%s': failed to create inner map: %d\n",
 					map->name, err);
@@ -4465,7 +4531,15 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map)
 			create_attr.inner_map_fd = map->inner_map_fd;
 	}
 
-	map->fd = bpf_create_map_xattr(&create_attr);
+	if (obj->gen_loader) {
+		bpf_gen__map_create(obj->gen_loader, &create_attr, is_inner ? -1 : map - obj->maps);
+		/* Pretend to have valid FD to pass various fd >= 0 checks.
+		 * This fd == 0 will not be used with any syscall and will be reset to -1 eventually.
+		 */
+		map->fd = 0;
+	} else {
+		map->fd = bpf_create_map_xattr(&create_attr);
+	}
 	if (map->fd < 0 && (create_attr.btf_key_type_id ||
 			    create_attr.btf_value_type_id)) {
 		char *cp, errmsg[STRERR_BUFSIZE];
@@ -4486,6 +4560,8 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map)
 		return -errno;
 
 	if (bpf_map_type__is_map_in_map(def->type) && map->inner_map) {
+		if (obj->gen_loader)
+			map->inner_map->fd = -1;
 		bpf_map__destroy(map->inner_map);
 		zfree(&map->inner_map);
 	}
@@ -4493,11 +4569,11 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map)
 	return 0;
 }
 
-static int init_map_slots(struct bpf_map *map)
+static int init_map_slots(struct bpf_object *obj, struct bpf_map *map)
 {
 	const struct bpf_map *targ_map;
 	unsigned int i;
-	int fd, err;
+	int fd, err = 0;
 
 	for (i = 0; i < map->init_slots_sz; i++) {
 		if (!map->init_slots[i])
@@ -4505,7 +4581,13 @@ static int init_map_slots(struct bpf_map *map)
 
 		targ_map = map->init_slots[i];
 		fd = bpf_map__fd(targ_map);
-		err = bpf_map_update_elem(map->fd, &i, &fd, 0);
+		if (obj->gen_loader) {
+			pr_warn("// TODO map_update_elem: idx %td key %d value==map_idx %td\n",
+				map - obj->maps, i, targ_map - obj->maps);
+			return -ENOTSUP;
+		} else {
+			err = bpf_map_update_elem(map->fd, &i, &fd, 0);
+		}
 		if (err) {
 			err = -errno;
 			pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %d\n",
@@ -4547,7 +4629,7 @@ bpf_object__create_maps(struct bpf_object *obj)
 			pr_debug("map '%s': skipping creation (preset fd=%d)\n",
 				 map->name, map->fd);
 		} else {
-			err = bpf_object__create_map(obj, map);
+			err = bpf_object__create_map(obj, map, false);
 			if (err)
 				goto err_out;
 
@@ -4563,7 +4645,7 @@ bpf_object__create_maps(struct bpf_object *obj)
 			}
 
 			if (map->init_slots_sz) {
-				err = init_map_slots(map);
+				err = init_map_slots(obj, map);
 				if (err < 0) {
 					zclose(map->fd);
 					goto err_out;
@@ -4973,11 +5055,14 @@ static int load_module_btfs(struct bpf_object *obj)
 	if (obj->btf_modules_loaded)
 		return 0;
 
+	if (obj->gen_loader)
+		return 0;
+
 	/* don't do this again, even if we find no module BTFs */
 	obj->btf_modules_loaded = true;
 
 	/* kernel too old to support module BTFs */
-	if (!kernel_supports(FEAT_MODULE_BTF))
+	if (!kernel_supports(obj, FEAT_MODULE_BTF))
 		return 0;
 
 	while (true) {
@@ -5018,10 +5103,10 @@ static int load_module_btfs(struct bpf_object *obj)
 		}
 
 		btf = btf_get_from_fd(fd, obj->btf_vmlinux);
-		if (IS_ERR(btf)) {
-			pr_warn("failed to load module [%s]'s BTF object #%d: %ld\n",
-				name, id, PTR_ERR(btf));
-			err = PTR_ERR(btf);
+		err = libbpf_get_error(btf);
+		if (err) {
+			pr_warn("failed to load module [%s]'s BTF object #%d: %d\n",
+				name, id, err);
 			goto err_out;
 		}
 
@@ -6120,6 +6205,12 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 	if (str_is_empty(spec_str))
 		return -EINVAL;
 
+	if (prog->obj->gen_loader) {
+		pr_warn("// TODO core_relo: prog %td insn[%d] %s %s kind %d\n",
+			prog - prog->obj->programs, relo->insn_off / 8,
+			local_name, spec_str, relo->kind);
+		return -ENOTSUP;
+	}
 	err = bpf_core_parse_spec(local_btf, local_id, spec_str, relo->kind, &local_spec);
 	if (err) {
 		pr_warn("prog '%s': relo #%d: parsing [%d] %s %s + %s failed: %d\n",
@@ -6275,8 +6366,8 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
 
 	if (targ_btf_path) {
 		obj->btf_vmlinux_override = btf__parse(targ_btf_path, NULL);
-		if (IS_ERR_OR_NULL(obj->btf_vmlinux_override)) {
-			err = PTR_ERR(obj->btf_vmlinux_override);
+		err = libbpf_get_error(obj->btf_vmlinux_override);
+		if (err) {
 			pr_warn("failed to parse target BTF: %d\n", err);
 			return err;
 		}
@@ -6371,19 +6462,34 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
 
 		switch (relo->type) {
 		case RELO_LD64:
-			insn[0].src_reg = BPF_PSEUDO_MAP_FD;
-			insn[0].imm = obj->maps[relo->map_idx].fd;
+			if (obj->gen_loader) {
+				insn[0].src_reg = BPF_PSEUDO_MAP_IDX;
+				insn[0].imm = relo->map_idx;
+			} else {
+				insn[0].src_reg = BPF_PSEUDO_MAP_FD;
+				insn[0].imm = obj->maps[relo->map_idx].fd;
+			}
 			break;
 		case RELO_DATA:
-			insn[0].src_reg = BPF_PSEUDO_MAP_VALUE;
 			insn[1].imm = insn[0].imm + relo->sym_off;
-			insn[0].imm = obj->maps[relo->map_idx].fd;
+			if (obj->gen_loader) {
+				insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE;
+				insn[0].imm = relo->map_idx;
+			} else {
+				insn[0].src_reg = BPF_PSEUDO_MAP_VALUE;
+				insn[0].imm = obj->maps[relo->map_idx].fd;
+			}
 			break;
 		case RELO_EXTERN_VAR:
 			ext = &obj->externs[relo->sym_off];
 			if (ext->type == EXT_KCFG) {
-				insn[0].src_reg = BPF_PSEUDO_MAP_VALUE;
-				insn[0].imm = obj->maps[obj->kconfig_map_idx].fd;
+				if (obj->gen_loader) {
+					insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE;
+					insn[0].imm = obj->kconfig_map_idx;
+				} else {
+					insn[0].src_reg = BPF_PSEUDO_MAP_VALUE;
+					insn[0].imm = obj->maps[obj->kconfig_map_idx].fd;
+				}
 				insn[1].imm = ext->kcfg.data_off;
 			} else /* EXT_KSYM */ {
 				if (ext->ksym.type_id) { /* typed ksyms */
@@ -6402,11 +6508,15 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
 			insn[0].imm = ext->ksym.kernel_btf_id;
 			break;
 		case RELO_SUBPROG_ADDR:
-			insn[0].src_reg = BPF_PSEUDO_FUNC;
-			/* will be handled as a follow up pass */
+			if (insn[0].src_reg != BPF_PSEUDO_FUNC) {
+				pr_warn("prog '%s': relo #%d: bad insn\n",
+					prog->name, i);
+				return -EINVAL;
+			}
+			/* handled already */
 			break;
 		case RELO_CALL:
-			/* will be handled as a follow up pass */
+			/* handled already */
 			break;
 		default:
 			pr_warn("prog '%s': relo #%d: bad relo type %d\n",
@@ -6497,7 +6607,7 @@ reloc_prog_func_and_line_info(const struct bpf_object *obj,
 	/* no .BTF.ext relocation if .BTF.ext is missing or kernel doesn't
 	 * supprot func/line info
 	 */
-	if (!obj->btf_ext || !kernel_supports(FEAT_BTF_FUNC))
+	if (!obj->btf_ext || !kernel_supports(obj, FEAT_BTF_FUNC))
 		return 0;
 
 	/* only attempt func info relocation if main program's func_info
@@ -6575,6 +6685,30 @@ static struct reloc_desc *find_prog_insn_relo(const struct bpf_program *prog, si
 		       sizeof(*prog->reloc_desc), cmp_relo_by_insn_idx);
 }
 
+static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_program *subprog)
+{
+	int new_cnt = main_prog->nr_reloc + subprog->nr_reloc;
+	struct reloc_desc *relos;
+	int i;
+
+	if (main_prog == subprog)
+		return 0;
+	relos = libbpf_reallocarray(main_prog->reloc_desc, new_cnt, sizeof(*relos));
+	if (!relos)
+		return -ENOMEM;
+	memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc,
+	       sizeof(*relos) * subprog->nr_reloc);
+
+	for (i = main_prog->nr_reloc; i < new_cnt; i++)
+		relos[i].insn_idx += subprog->sub_insn_off;
+	/* After insn_idx adjustment the 'relos' array is still sorted
+	 * by insn_idx and doesn't break bsearch.
+	 */
+	main_prog->reloc_desc = relos;
+	main_prog->nr_reloc = new_cnt;
+	return 0;
+}
+
 static int
 bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
 		       struct bpf_program *prog)
@@ -6595,6 +6729,11 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
 			continue;
 
 		relo = find_prog_insn_relo(prog, insn_idx);
+		if (relo && relo->type == RELO_EXTERN_FUNC)
+			/* kfunc relocations will be handled later
+			 * in bpf_object__relocate_data()
+			 */
+			continue;
 		if (relo && relo->type != RELO_CALL && relo->type != RELO_SUBPROG_ADDR) {
 			pr_warn("prog '%s': unexpected relo for insn #%zu, type %d\n",
 				prog->name, insn_idx, relo->type);
@@ -6669,6 +6808,10 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
 			pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n",
 				 main_prog->name, subprog->insns_cnt, subprog->name);
 
+			/* The subprog insns are now appended. Append its relos too. */
+			err = append_subprog_relos(main_prog, subprog);
+			if (err)
+				return err;
 			err = bpf_object__reloc_code(obj, main_prog, subprog);
 			if (err)
 				return err;
@@ -6798,11 +6941,25 @@ bpf_object__relocate_calls(struct bpf_object *obj, struct bpf_program *prog)
 	return 0;
 }
 
+static void
+bpf_object__free_relocs(struct bpf_object *obj)
+{
+	struct bpf_program *prog;
+	int i;
+
+	/* free up relocation descriptors */
+	for (i = 0; i < obj->nr_programs; i++) {
+		prog = &obj->programs[i];
+		zfree(&prog->reloc_desc);
+		prog->nr_reloc = 0;
+	}
+}
+
 static int
 bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 {
 	struct bpf_program *prog;
-	size_t i;
+	size_t i, j;
 	int err;
 
 	if (obj->btf_ext) {
@@ -6813,23 +6970,32 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 			return err;
 		}
 	}
-	/* relocate data references first for all programs and sub-programs,
-	 * as they don't change relative to code locations, so subsequent
-	 * subprogram processing won't need to re-calculate any of them
+
+	/* Before relocating calls pre-process relocations and mark
+	 * few ld_imm64 instructions that points to subprogs.
+	 * Otherwise bpf_object__reloc_code() later would have to consider
+	 * all ld_imm64 insns as relocation candidates. That would
+	 * reduce relocation speed, since amount of find_prog_insn_relo()
+	 * would increase and most of them will fail to find a relo.
 	 */
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
-		err = bpf_object__relocate_data(obj, prog);
-		if (err) {
-			pr_warn("prog '%s': failed to relocate data references: %d\n",
-				prog->name, err);
-			return err;
+		for (j = 0; j < prog->nr_reloc; j++) {
+			struct reloc_desc *relo = &prog->reloc_desc[j];
+			struct bpf_insn *insn = &prog->insns[relo->insn_idx];
+
+			/* mark the insn, so it's recognized by insn_is_pseudo_func() */
+			if (relo->type == RELO_SUBPROG_ADDR)
+				insn[0].src_reg = BPF_PSEUDO_FUNC;
 		}
 	}
-	/* now relocate subprogram calls and append used subprograms to main
+
+	/* relocate subprogram calls and append used subprograms to main
 	 * programs; each copy of subprogram code needs to be relocated
 	 * differently for each main program, because its code location might
-	 * have changed
+	 * have changed.
+	 * Append subprog relos to main programs to allow data relos to be
+	 * processed after text is completely relocated.
 	 */
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
@@ -6846,12 +7012,20 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 			return err;
 		}
 	}
-	/* free up relocation descriptors */
+	/* Process data relos for main programs */
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
-		zfree(&prog->reloc_desc);
-		prog->nr_reloc = 0;
+		if (prog_is_subprog(obj, prog))
+			continue;
+		err = bpf_object__relocate_data(obj, prog);
+		if (err) {
+			pr_warn("prog '%s': failed to relocate data references: %d\n",
+				prog->name, err);
+			return err;
+		}
 	}
+	if (!obj->gen_loader)
+		bpf_object__free_relocs(obj);
 	return 0;
 }
 
@@ -7040,6 +7214,9 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program
 	enum bpf_func_id func_id;
 	int i;
 
+	if (obj->gen_loader)
+		return 0;
+
 	for (i = 0; i < prog->insns_cnt; i++, insn++) {
 		if (!insn_is_helper_call(insn, &func_id))
 			continue;
@@ -7051,12 +7228,12 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program
 		switch (func_id) {
 		case BPF_FUNC_probe_read_kernel:
 		case BPF_FUNC_probe_read_user:
-			if (!kernel_supports(FEAT_PROBE_READ_KERN))
+			if (!kernel_supports(obj, FEAT_PROBE_READ_KERN))
 				insn->imm = BPF_FUNC_probe_read;
 			break;
 		case BPF_FUNC_probe_read_kernel_str:
 		case BPF_FUNC_probe_read_user_str:
-			if (!kernel_supports(FEAT_PROBE_READ_KERN))
+			if (!kernel_supports(obj, FEAT_PROBE_READ_KERN))
 				insn->imm = BPF_FUNC_probe_read_str;
 			break;
 		default:
@@ -7091,12 +7268,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 
 	load_attr.prog_type = prog->type;
 	/* old kernels might not support specifying expected_attach_type */
-	if (!kernel_supports(FEAT_EXP_ATTACH_TYPE) && prog->sec_def &&
+	if (!kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE) && prog->sec_def &&
 	    prog->sec_def->is_exp_attach_type_optional)
 		load_attr.expected_attach_type = 0;
 	else
 		load_attr.expected_attach_type = prog->expected_attach_type;
-	if (kernel_supports(FEAT_PROG_NAME))
+	if (kernel_supports(prog->obj, FEAT_PROG_NAME))
 		load_attr.name = prog->name;
 	load_attr.insns = insns;
 	load_attr.insn_cnt = insns_cnt;
@@ -7112,7 +7289,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 
 	/* specify func_info/line_info only if kernel supports them */
 	btf_fd = bpf_object__btf_fd(prog->obj);
-	if (btf_fd >= 0 && kernel_supports(FEAT_BTF_FUNC)) {
+	if (btf_fd >= 0 && kernel_supports(prog->obj, FEAT_BTF_FUNC)) {
 		load_attr.prog_btf_fd = btf_fd;
 		load_attr.func_info = prog->func_info;
 		load_attr.func_info_rec_size = prog->func_info_rec_size;
@@ -7124,6 +7301,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	load_attr.log_level = prog->log_level;
 	load_attr.prog_flags = prog->prog_flags;
 
+	if (prog->obj->gen_loader) {
+		bpf_gen__prog_load(prog->obj->gen_loader, &load_attr,
+				   prog - prog->obj->programs);
+		*pfd = -1;
+		return 0;
+	}
 retry_load:
 	if (log_buf_size) {
 		log_buf = malloc(log_buf_size);
@@ -7142,7 +7325,7 @@ retry_load:
 			pr_debug("verifier log:\n%s", log_buf);
 
 		if (prog->obj->rodata_map_idx >= 0 &&
-		    kernel_supports(FEAT_PROG_BIND_MAP)) {
+		    kernel_supports(prog->obj, FEAT_PROG_BIND_MAP)) {
 			struct bpf_map *rodata_map =
 				&prog->obj->maps[prog->obj->rodata_map_idx];
 
@@ -7201,6 +7384,38 @@ out:
 	return ret;
 }
 
+static int bpf_program__record_externs(struct bpf_program *prog)
+{
+	struct bpf_object *obj = prog->obj;
+	int i;
+
+	for (i = 0; i < prog->nr_reloc; i++) {
+		struct reloc_desc *relo = &prog->reloc_desc[i];
+		struct extern_desc *ext = &obj->externs[relo->sym_off];
+
+		switch (relo->type) {
+		case RELO_EXTERN_VAR:
+			if (ext->type != EXT_KSYM)
+				continue;
+			if (!ext->ksym.type_id) {
+				pr_warn("typeless ksym %s is not supported yet\n",
+					ext->name);
+				return -ENOTSUP;
+			}
+			bpf_gen__record_extern(obj->gen_loader, ext->name, BTF_KIND_VAR,
+					       relo->insn_idx);
+			break;
+		case RELO_EXTERN_FUNC:
+			bpf_gen__record_extern(obj->gen_loader, ext->name, BTF_KIND_FUNC,
+					       relo->insn_idx);
+			break;
+		default:
+			continue;
+		}
+	}
+	return 0;
+}
+
 static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id);
 
 int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
@@ -7209,7 +7424,7 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 
 	if (prog->obj->loaded) {
 		pr_warn("prog '%s': can't load after object was loaded\n", prog->name);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if ((prog->type == BPF_PROG_TYPE_TRACING ||
@@ -7219,7 +7434,7 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 
 		err = libbpf_find_attach_btf_id(prog, &btf_obj_fd, &btf_type_id);
 		if (err)
-			return err;
+			return libbpf_err(err);
 
 		prog->attach_btf_obj_fd = btf_obj_fd;
 		prog->attach_btf_id = btf_type_id;
@@ -7229,13 +7444,13 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 		if (prog->preprocessor) {
 			pr_warn("Internal error: can't load program '%s'\n",
 				prog->name);
-			return -LIBBPF_ERRNO__INTERNAL;
+			return libbpf_err(-LIBBPF_ERRNO__INTERNAL);
 		}
 
 		prog->instances.fds = malloc(sizeof(int));
 		if (!prog->instances.fds) {
 			pr_warn("Not enough memory for BPF fds\n");
-			return -ENOMEM;
+			return libbpf_err(-ENOMEM);
 		}
 		prog->instances.nr = 1;
 		prog->instances.fds[0] = -1;
@@ -7246,6 +7461,8 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 			pr_warn("prog '%s': inconsistent nr(%d) != 1\n",
 				prog->name, prog->instances.nr);
 		}
+		if (prog->obj->gen_loader)
+			bpf_program__record_externs(prog);
 		err = load_program(prog, prog->insns, prog->insns_cnt,
 				   license, kern_ver, &fd);
 		if (!err)
@@ -7292,7 +7509,7 @@ out:
 		pr_warn("failed to load program '%s'\n", prog->name);
 	zfree(&prog->insns);
 	prog->insns_cnt = 0;
-	return err;
+	return libbpf_err(err);
 }
 
 static int
@@ -7322,6 +7539,8 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level)
 		if (err)
 			return err;
 	}
+	if (obj->gen_loader)
+		bpf_object__free_relocs(obj);
 	return 0;
 }
 
@@ -7423,7 +7642,7 @@ __bpf_object__open_xattr(struct bpf_object_open_attr *attr, int flags)
 
 struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr)
 {
-	return __bpf_object__open_xattr(attr, 0);
+	return libbpf_ptr(__bpf_object__open_xattr(attr, 0));
 }
 
 struct bpf_object *bpf_object__open(const char *path)
@@ -7433,18 +7652,18 @@ struct bpf_object *bpf_object__open(const char *path)
 		.prog_type	= BPF_PROG_TYPE_UNSPEC,
 	};
 
-	return bpf_object__open_xattr(&attr);
+	return libbpf_ptr(__bpf_object__open_xattr(&attr, 0));
 }
 
 struct bpf_object *
 bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts)
 {
 	if (!path)
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 
 	pr_debug("loading %s\n", path);
 
-	return __bpf_object__open(path, NULL, 0, opts);
+	return libbpf_ptr(__bpf_object__open(path, NULL, 0, opts));
 }
 
 struct bpf_object *
@@ -7452,9 +7671,9 @@ bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz,
 		     const struct bpf_object_open_opts *opts)
 {
 	if (!obj_buf || obj_buf_sz == 0)
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 
-	return __bpf_object__open(NULL, obj_buf, obj_buf_sz, opts);
+	return libbpf_ptr(__bpf_object__open(NULL, obj_buf, obj_buf_sz, opts));
 }
 
 struct bpf_object *
@@ -7469,9 +7688,9 @@ bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz,
 
 	/* returning NULL is wrong, but backwards-compatible */
 	if (!obj_buf || obj_buf_sz == 0)
-		return NULL;
+		return errno = EINVAL, NULL;
 
-	return bpf_object__open_mem(obj_buf, obj_buf_sz, &opts);
+	return libbpf_ptr(__bpf_object__open(NULL, obj_buf, obj_buf_sz, &opts));
 }
 
 int bpf_object__unload(struct bpf_object *obj)
@@ -7479,7 +7698,7 @@ int bpf_object__unload(struct bpf_object *obj)
 	size_t i;
 
 	if (!obj)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	for (i = 0; i < obj->nr_maps; i++) {
 		zclose(obj->maps[i].fd);
@@ -7500,11 +7719,11 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj)
 	bpf_object__for_each_map(m, obj) {
 		if (!bpf_map__is_internal(m))
 			continue;
-		if (!kernel_supports(FEAT_GLOBAL_DATA)) {
+		if (!kernel_supports(obj, FEAT_GLOBAL_DATA)) {
 			pr_warn("kernel doesn't support global data\n");
 			return -ENOTSUP;
 		}
-		if (!kernel_supports(FEAT_ARRAY_MMAP))
+		if (!kernel_supports(obj, FEAT_ARRAY_MMAP))
 			m->def.map_flags ^= BPF_F_MMAPABLE;
 	}
 
@@ -7702,6 +7921,12 @@ static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj)
 		if (ext->type != EXT_KSYM || !ext->ksym.type_id)
 			continue;
 
+		if (obj->gen_loader) {
+			ext->is_set = true;
+			ext->ksym.kernel_btf_obj_fd = 0;
+			ext->ksym.kernel_btf_id = 0;
+			continue;
+		}
 		t = btf__type_by_id(obj->btf, ext->btf_id);
 		if (btf_is_var(t))
 			err = bpf_object__resolve_ksym_var_btf_id(obj, ext);
@@ -7806,16 +8031,19 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 	int err, i;
 
 	if (!attr)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	obj = attr->obj;
 	if (!obj)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (obj->loaded) {
 		pr_warn("object '%s': load can't be attempted twice\n", obj->name);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
+	if (obj->gen_loader)
+		bpf_gen__init(obj->gen_loader, attr->log_level);
+
 	err = bpf_object__probe_loading(obj);
 	err = err ? : bpf_object__load_vmlinux_btf(obj, false);
 	err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
@@ -7826,6 +8054,15 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 	err = err ? : bpf_object__relocate(obj, attr->target_btf_path);
 	err = err ? : bpf_object__load_progs(obj, attr->log_level);
 
+	if (obj->gen_loader) {
+		/* reset FDs */
+		btf__set_fd(obj->btf, -1);
+		for (i = 0; i < obj->nr_maps; i++)
+			obj->maps[i].fd = -1;
+		if (!err)
+			err = bpf_gen__finish(obj->gen_loader);
+	}
+
 	/* clean up module BTFs */
 	for (i = 0; i < obj->btf_module_cnt; i++) {
 		close(obj->btf_modules[i].fd);
@@ -7852,7 +8089,7 @@ out:
 
 	bpf_object__unload(obj);
 	pr_warn("failed to load object '%s'\n", obj->path);
-	return err;
+	return libbpf_err(err);
 }
 
 int bpf_object__load(struct bpf_object *obj)
@@ -7924,28 +8161,28 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 
 	err = make_parent_dir(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	err = check_path(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	if (prog == NULL) {
 		pr_warn("invalid program pointer\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (instance < 0 || instance >= prog->instances.nr) {
 		pr_warn("invalid prog instance %d of prog %s (max %d)\n",
 			instance, prog->name, prog->instances.nr);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (bpf_obj_pin(prog->instances.fds[instance], path)) {
 		err = -errno;
 		cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
 		pr_warn("failed to pin program: %s\n", cp);
-		return err;
+		return libbpf_err(err);
 	}
 	pr_debug("pinned program '%s'\n", path);
 
@@ -7959,22 +8196,23 @@ int bpf_program__unpin_instance(struct bpf_program *prog, const char *path,
 
 	err = check_path(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	if (prog == NULL) {
 		pr_warn("invalid program pointer\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (instance < 0 || instance >= prog->instances.nr) {
 		pr_warn("invalid prog instance %d of prog %s (max %d)\n",
 			instance, prog->name, prog->instances.nr);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	err = unlink(path);
 	if (err != 0)
-		return -errno;
+		return libbpf_err(-errno);
+
 	pr_debug("unpinned program '%s'\n", path);
 
 	return 0;
@@ -7986,20 +8224,20 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
 
 	err = make_parent_dir(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	err = check_path(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	if (prog == NULL) {
 		pr_warn("invalid program pointer\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (prog->instances.nr <= 0) {
 		pr_warn("no instances of prog %s to pin\n", prog->name);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (prog->instances.nr == 1) {
@@ -8043,7 +8281,7 @@ err_unpin:
 
 	rmdir(path);
 
-	return err;
+	return libbpf_err(err);
 }
 
 int bpf_program__unpin(struct bpf_program *prog, const char *path)
@@ -8052,16 +8290,16 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path)
 
 	err = check_path(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	if (prog == NULL) {
 		pr_warn("invalid program pointer\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (prog->instances.nr <= 0) {
 		pr_warn("no instances of prog %s to pin\n", prog->name);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (prog->instances.nr == 1) {
@@ -8075,9 +8313,9 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path)
 
 		len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
 		if (len < 0)
-			return -EINVAL;
+			return libbpf_err(-EINVAL);
 		else if (len >= PATH_MAX)
-			return -ENAMETOOLONG;
+			return libbpf_err(-ENAMETOOLONG);
 
 		err = bpf_program__unpin_instance(prog, buf, i);
 		if (err)
@@ -8086,7 +8324,7 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path)
 
 	err = rmdir(path);
 	if (err)
-		return -errno;
+		return libbpf_err(-errno);
 
 	return 0;
 }
@@ -8098,14 +8336,14 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 
 	if (map == NULL) {
 		pr_warn("invalid map pointer\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (map->pin_path) {
 		if (path && strcmp(path, map->pin_path)) {
 			pr_warn("map '%s' already has pin path '%s' different from '%s'\n",
 				bpf_map__name(map), map->pin_path, path);
-			return -EINVAL;
+			return libbpf_err(-EINVAL);
 		} else if (map->pinned) {
 			pr_debug("map '%s' already pinned at '%s'; not re-pinning\n",
 				 bpf_map__name(map), map->pin_path);
@@ -8115,10 +8353,10 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 		if (!path) {
 			pr_warn("missing a path to pin map '%s' at\n",
 				bpf_map__name(map));
-			return -EINVAL;
+			return libbpf_err(-EINVAL);
 		} else if (map->pinned) {
 			pr_warn("map '%s' already pinned\n", bpf_map__name(map));
-			return -EEXIST;
+			return libbpf_err(-EEXIST);
 		}
 
 		map->pin_path = strdup(path);
@@ -8130,11 +8368,11 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 
 	err = make_parent_dir(map->pin_path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	err = check_path(map->pin_path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	if (bpf_obj_pin(map->fd, map->pin_path)) {
 		err = -errno;
@@ -8149,7 +8387,7 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 out_err:
 	cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
 	pr_warn("failed to pin map: %s\n", cp);
-	return err;
+	return libbpf_err(err);
 }
 
 int bpf_map__unpin(struct bpf_map *map, const char *path)
@@ -8158,29 +8396,29 @@ int bpf_map__unpin(struct bpf_map *map, const char *path)
 
 	if (map == NULL) {
 		pr_warn("invalid map pointer\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (map->pin_path) {
 		if (path && strcmp(path, map->pin_path)) {
 			pr_warn("map '%s' already has pin path '%s' different from '%s'\n",
 				bpf_map__name(map), map->pin_path, path);
-			return -EINVAL;
+			return libbpf_err(-EINVAL);
 		}
 		path = map->pin_path;
 	} else if (!path) {
 		pr_warn("no path to unpin map '%s' from\n",
 			bpf_map__name(map));
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	err = check_path(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	err = unlink(path);
 	if (err != 0)
-		return -errno;
+		return libbpf_err(-errno);
 
 	map->pinned = false;
 	pr_debug("unpinned map '%s' from '%s'\n", bpf_map__name(map), path);
@@ -8195,7 +8433,7 @@ int bpf_map__set_pin_path(struct bpf_map *map, const char *path)
 	if (path) {
 		new = strdup(path);
 		if (!new)
-			return -errno;
+			return libbpf_err(-errno);
 	}
 
 	free(map->pin_path);
@@ -8229,11 +8467,11 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path)
 	int err;
 
 	if (!obj)
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 
 	if (!obj->loaded) {
 		pr_warn("object not yet loaded; load it first\n");
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 	}
 
 	bpf_object__for_each_map(map, obj) {
@@ -8273,7 +8511,7 @@ err_unpin_maps:
 		bpf_map__unpin(map, NULL);
 	}
 
-	return err;
+	return libbpf_err(err);
 }
 
 int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
@@ -8282,7 +8520,7 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
 	int err;
 
 	if (!obj)
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 
 	bpf_object__for_each_map(map, obj) {
 		char *pin_path = NULL;
@@ -8294,9 +8532,9 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
 			len = snprintf(buf, PATH_MAX, "%s/%s", path,
 				       bpf_map__name(map));
 			if (len < 0)
-				return -EINVAL;
+				return libbpf_err(-EINVAL);
 			else if (len >= PATH_MAX)
-				return -ENAMETOOLONG;
+				return libbpf_err(-ENAMETOOLONG);
 			sanitize_pin_path(buf);
 			pin_path = buf;
 		} else if (!map->pin_path) {
@@ -8305,7 +8543,7 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
 
 		err = bpf_map__unpin(map, pin_path);
 		if (err)
-			return err;
+			return libbpf_err(err);
 	}
 
 	return 0;
@@ -8317,11 +8555,11 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path)
 	int err;
 
 	if (!obj)
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 
 	if (!obj->loaded) {
 		pr_warn("object not yet loaded; load it first\n");
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 	}
 
 	bpf_object__for_each_program(prog, obj) {
@@ -8360,7 +8598,7 @@ err_unpin_programs:
 		bpf_program__unpin(prog, buf);
 	}
 
-	return err;
+	return libbpf_err(err);
 }
 
 int bpf_object__unpin_programs(struct bpf_object *obj, const char *path)
@@ -8369,7 +8607,7 @@ int bpf_object__unpin_programs(struct bpf_object *obj, const char *path)
 	int err;
 
 	if (!obj)
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 
 	bpf_object__for_each_program(prog, obj) {
 		char buf[PATH_MAX];
@@ -8378,13 +8616,13 @@ int bpf_object__unpin_programs(struct bpf_object *obj, const char *path)
 		len = snprintf(buf, PATH_MAX, "%s/%s", path,
 			       prog->pin_name);
 		if (len < 0)
-			return -EINVAL;
+			return libbpf_err(-EINVAL);
 		else if (len >= PATH_MAX)
-			return -ENAMETOOLONG;
+			return libbpf_err(-ENAMETOOLONG);
 
 		err = bpf_program__unpin(prog, buf);
 		if (err)
-			return err;
+			return libbpf_err(err);
 	}
 
 	return 0;
@@ -8396,12 +8634,12 @@ int bpf_object__pin(struct bpf_object *obj, const char *path)
 
 	err = bpf_object__pin_maps(obj, path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	err = bpf_object__pin_programs(obj, path);
 	if (err) {
 		bpf_object__unpin_maps(obj, path);
-		return err;
+		return libbpf_err(err);
 	}
 
 	return 0;
@@ -8451,6 +8689,7 @@ void bpf_object__close(struct bpf_object *obj)
 	if (obj->clear_priv)
 		obj->clear_priv(obj, obj->priv);
 
+	bpf_gen__free(obj->gen_loader);
 	bpf_object__elf_finish(obj);
 	bpf_object__unload(obj);
 	btf__free(obj->btf);
@@ -8497,7 +8736,7 @@ bpf_object__next(struct bpf_object *prev)
 
 const char *bpf_object__name(const struct bpf_object *obj)
 {
-	return obj ? obj->name : ERR_PTR(-EINVAL);
+	return obj ? obj->name : libbpf_err_ptr(-EINVAL);
 }
 
 unsigned int bpf_object__kversion(const struct bpf_object *obj)
@@ -8518,7 +8757,7 @@ int bpf_object__btf_fd(const struct bpf_object *obj)
 int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version)
 {
 	if (obj->loaded)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	obj->kern_version = kern_version;
 
@@ -8538,7 +8777,23 @@ int bpf_object__set_priv(struct bpf_object *obj, void *priv,
 
 void *bpf_object__priv(const struct bpf_object *obj)
 {
-	return obj ? obj->priv : ERR_PTR(-EINVAL);
+	return obj ? obj->priv : libbpf_err_ptr(-EINVAL);
+}
+
+int bpf_object__gen_loader(struct bpf_object *obj, struct gen_loader_opts *opts)
+{
+	struct bpf_gen *gen;
+
+	if (!opts)
+		return -EFAULT;
+	if (!OPTS_VALID(opts, gen_loader_opts))
+		return -EINVAL;
+	gen = calloc(sizeof(*gen), 1);
+	if (!gen)
+		return -ENOMEM;
+	gen->opts = opts;
+	obj->gen_loader = gen;
+	return 0;
 }
 
 static struct bpf_program *
@@ -8558,7 +8813,7 @@ __bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj,
 
 	if (p->obj != obj) {
 		pr_warn("error: program handler doesn't match object\n");
-		return NULL;
+		return errno = EINVAL, NULL;
 	}
 
 	idx = (p - obj->programs) + (forward ? 1 : -1);
@@ -8604,7 +8859,7 @@ int bpf_program__set_priv(struct bpf_program *prog, void *priv,
 
 void *bpf_program__priv(const struct bpf_program *prog)
 {
-	return prog ? prog->priv : ERR_PTR(-EINVAL);
+	return prog ? prog->priv : libbpf_err_ptr(-EINVAL);
 }
 
 void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex)
@@ -8631,7 +8886,7 @@ const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy)
 		title = strdup(title);
 		if (!title) {
 			pr_warn("failed to strdup program title\n");
-			return ERR_PTR(-ENOMEM);
+			return libbpf_err_ptr(-ENOMEM);
 		}
 	}
 
@@ -8646,7 +8901,7 @@ bool bpf_program__autoload(const struct bpf_program *prog)
 int bpf_program__set_autoload(struct bpf_program *prog, bool autoload)
 {
 	if (prog->obj->loaded)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	prog->load = autoload;
 	return 0;
@@ -8668,17 +8923,17 @@ int bpf_program__set_prep(struct bpf_program *prog, int nr_instances,
 	int *instances_fds;
 
 	if (nr_instances <= 0 || !prep)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (prog->instances.nr > 0 || prog->instances.fds) {
 		pr_warn("Can't set pre-processor after loading\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	instances_fds = malloc(sizeof(int) * nr_instances);
 	if (!instances_fds) {
 		pr_warn("alloc memory failed for fds\n");
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 	}
 
 	/* fill all fd with -1 */
@@ -8695,19 +8950,19 @@ int bpf_program__nth_fd(const struct bpf_program *prog, int n)
 	int fd;
 
 	if (!prog)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (n >= prog->instances.nr || n < 0) {
 		pr_warn("Can't get the %dth fd from program %s: only %d instances\n",
 			n, prog->name, prog->instances.nr);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	fd = prog->instances.fds[n];
 	if (fd < 0) {
 		pr_warn("%dth instance of program '%s' is invalid\n",
 			n, prog->name);
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 	}
 
 	return fd;
@@ -8733,7 +8988,7 @@ static bool bpf_program__is_type(const struct bpf_program *prog,
 int bpf_program__set_##NAME(struct bpf_program *prog)		\
 {								\
 	if (!prog)						\
-		return -EINVAL;					\
+		return libbpf_err(-EINVAL);			\
 	bpf_program__set_type(prog, TYPE);			\
 	return 0;						\
 }								\
@@ -8823,7 +9078,10 @@ static struct bpf_link *attach_iter(const struct bpf_sec_def *sec,
 
 static const struct bpf_sec_def section_defs[] = {
 	BPF_PROG_SEC("socket",			BPF_PROG_TYPE_SOCKET_FILTER),
-	BPF_PROG_SEC("sk_reuseport",		BPF_PROG_TYPE_SK_REUSEPORT),
+	BPF_EAPROG_SEC("sk_reuseport/migrate",	BPF_PROG_TYPE_SK_REUSEPORT,
+						BPF_SK_REUSEPORT_SELECT_OR_MIGRATE),
+	BPF_EAPROG_SEC("sk_reuseport",		BPF_PROG_TYPE_SK_REUSEPORT,
+						BPF_SK_REUSEPORT_SELECT),
 	SEC_DEF("kprobe/", KPROBE,
 		.attach_fn = attach_kprobe),
 	BPF_PROG_SEC("uprobe/",			BPF_PROG_TYPE_KPROBE),
@@ -8887,6 +9145,8 @@ static const struct bpf_sec_def section_defs[] = {
 		.expected_attach_type = BPF_TRACE_ITER,
 		.is_attach_btf = true,
 		.attach_fn = attach_iter),
+	SEC_DEF("syscall", SYSCALL,
+		.is_sleepable = true),
 	BPF_EAPROG_SEC("xdp_devmap/",		BPF_PROG_TYPE_XDP,
 						BPF_XDP_DEVMAP),
 	BPF_EAPROG_SEC("xdp_cpumap/",		BPF_PROG_TYPE_XDP,
@@ -9018,7 +9278,7 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 	char *type_names;
 
 	if (!name)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	sec_def = find_sec_def(name);
 	if (sec_def) {
@@ -9034,7 +9294,7 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 		free(type_names);
 	}
 
-	return -ESRCH;
+	return libbpf_err(-ESRCH);
 }
 
 static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj,
@@ -9176,6 +9436,28 @@ invalid_prog:
 #define BTF_ITER_PREFIX "bpf_iter_"
 #define BTF_MAX_NAME_SIZE 128
 
+void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type,
+				const char **prefix, int *kind)
+{
+	switch (attach_type) {
+	case BPF_TRACE_RAW_TP:
+		*prefix = BTF_TRACE_PREFIX;
+		*kind = BTF_KIND_TYPEDEF;
+		break;
+	case BPF_LSM_MAC:
+		*prefix = BTF_LSM_PREFIX;
+		*kind = BTF_KIND_FUNC;
+		break;
+	case BPF_TRACE_ITER:
+		*prefix = BTF_ITER_PREFIX;
+		*kind = BTF_KIND_FUNC;
+		break;
+	default:
+		*prefix = "";
+		*kind = BTF_KIND_FUNC;
+	}
+}
+
 static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix,
 				   const char *name, __u32 kind)
 {
@@ -9196,21 +9478,11 @@ static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix,
 static inline int find_attach_btf_id(struct btf *btf, const char *name,
 				     enum bpf_attach_type attach_type)
 {
-	int err;
-
-	if (attach_type == BPF_TRACE_RAW_TP)
-		err = find_btf_by_prefix_kind(btf, BTF_TRACE_PREFIX, name,
-					      BTF_KIND_TYPEDEF);
-	else if (attach_type == BPF_LSM_MAC)
-		err = find_btf_by_prefix_kind(btf, BTF_LSM_PREFIX, name,
-					      BTF_KIND_FUNC);
-	else if (attach_type == BPF_TRACE_ITER)
-		err = find_btf_by_prefix_kind(btf, BTF_ITER_PREFIX, name,
-					      BTF_KIND_FUNC);
-	else
-		err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC);
+	const char *prefix;
+	int kind;
 
-	return err;
+	btf_get_kernel_prefix_kind(attach_type, &prefix, &kind);
+	return find_btf_by_prefix_kind(btf, prefix, name, kind);
 }
 
 int libbpf_find_vmlinux_btf_id(const char *name,
@@ -9220,9 +9492,10 @@ int libbpf_find_vmlinux_btf_id(const char *name,
 	int err;
 
 	btf = libbpf_find_kernel_btf();
-	if (IS_ERR(btf)) {
+	err = libbpf_get_error(btf);
+	if (err) {
 		pr_warn("vmlinux BTF is not found\n");
-		return -EINVAL;
+		return libbpf_err(err);
 	}
 
 	err = find_attach_btf_id(btf, name, attach_type);
@@ -9230,7 +9503,7 @@ int libbpf_find_vmlinux_btf_id(const char *name,
 		pr_warn("%s is not found in vmlinux BTF\n", name);
 
 	btf__free(btf);
-	return err;
+	return libbpf_err(err);
 }
 
 static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
@@ -9241,10 +9514,11 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
 	int err = -EINVAL;
 
 	info_linear = bpf_program__get_prog_info_linear(attach_prog_fd, 0);
-	if (IS_ERR_OR_NULL(info_linear)) {
+	err = libbpf_get_error(info_linear);
+	if (err) {
 		pr_warn("failed get_prog_info_linear for FD %d\n",
 			attach_prog_fd);
-		return -EINVAL;
+		return err;
 	}
 	info = &info_linear->info;
 	if (!info->btf_id) {
@@ -9309,7 +9583,7 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd,
 	__u32 attach_prog_fd = prog->attach_prog_fd;
 	const char *name = prog->sec_name, *attach_name;
 	const struct bpf_sec_def *sec = NULL;
-	int i, err;
+	int i, err = 0;
 
 	if (!name)
 		return -EINVAL;
@@ -9344,7 +9618,13 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd,
 	}
 
 	/* kernel/module BTF ID */
-	err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id);
+	if (prog->obj->gen_loader) {
+		bpf_gen__record_attach_target(prog->obj->gen_loader, attach_name, attach_type);
+		*btf_obj_fd = 0;
+		*btf_type_id = 1;
+	} else {
+		err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id);
+	}
 	if (err) {
 		pr_warn("failed to find kernel BTF type ID of '%s': %d\n", attach_name, err);
 		return err;
@@ -9359,13 +9639,13 @@ int libbpf_attach_type_by_name(const char *name,
 	int i;
 
 	if (!name)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	for (i = 0; i < ARRAY_SIZE(section_defs); i++) {
 		if (strncmp(name, section_defs[i].sec, section_defs[i].len))
 			continue;
 		if (!section_defs[i].is_attachable)
-			return -EINVAL;
+			return libbpf_err(-EINVAL);
 		*attach_type = section_defs[i].expected_attach_type;
 		return 0;
 	}
@@ -9376,17 +9656,17 @@ int libbpf_attach_type_by_name(const char *name,
 		free(type_names);
 	}
 
-	return -EINVAL;
+	return libbpf_err(-EINVAL);
 }
 
 int bpf_map__fd(const struct bpf_map *map)
 {
-	return map ? map->fd : -EINVAL;
+	return map ? map->fd : libbpf_err(-EINVAL);
 }
 
 const struct bpf_map_def *bpf_map__def(const struct bpf_map *map)
 {
-	return map ? &map->def : ERR_PTR(-EINVAL);
+	return map ? &map->def : libbpf_err_ptr(-EINVAL);
 }
 
 const char *bpf_map__name(const struct bpf_map *map)
@@ -9402,7 +9682,7 @@ enum bpf_map_type bpf_map__type(const struct bpf_map *map)
 int bpf_map__set_type(struct bpf_map *map, enum bpf_map_type type)
 {
 	if (map->fd >= 0)
-		return -EBUSY;
+		return libbpf_err(-EBUSY);
 	map->def.type = type;
 	return 0;
 }
@@ -9415,7 +9695,7 @@ __u32 bpf_map__map_flags(const struct bpf_map *map)
 int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags)
 {
 	if (map->fd >= 0)
-		return -EBUSY;
+		return libbpf_err(-EBUSY);
 	map->def.map_flags = flags;
 	return 0;
 }
@@ -9428,7 +9708,7 @@ __u32 bpf_map__numa_node(const struct bpf_map *map)
 int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node)
 {
 	if (map->fd >= 0)
-		return -EBUSY;
+		return libbpf_err(-EBUSY);
 	map->numa_node = numa_node;
 	return 0;
 }
@@ -9441,7 +9721,7 @@ __u32 bpf_map__key_size(const struct bpf_map *map)
 int bpf_map__set_key_size(struct bpf_map *map, __u32 size)
 {
 	if (map->fd >= 0)
-		return -EBUSY;
+		return libbpf_err(-EBUSY);
 	map->def.key_size = size;
 	return 0;
 }
@@ -9454,7 +9734,7 @@ __u32 bpf_map__value_size(const struct bpf_map *map)
 int bpf_map__set_value_size(struct bpf_map *map, __u32 size)
 {
 	if (map->fd >= 0)
-		return -EBUSY;
+		return libbpf_err(-EBUSY);
 	map->def.value_size = size;
 	return 0;
 }
@@ -9473,7 +9753,7 @@ int bpf_map__set_priv(struct bpf_map *map, void *priv,
 		     bpf_map_clear_priv_t clear_priv)
 {
 	if (!map)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (map->priv) {
 		if (map->clear_priv)
@@ -9487,7 +9767,7 @@ int bpf_map__set_priv(struct bpf_map *map, void *priv,
 
 void *bpf_map__priv(const struct bpf_map *map)
 {
-	return map ? map->priv : ERR_PTR(-EINVAL);
+	return map ? map->priv : libbpf_err_ptr(-EINVAL);
 }
 
 int bpf_map__set_initial_value(struct bpf_map *map,
@@ -9495,12 +9775,20 @@ int bpf_map__set_initial_value(struct bpf_map *map,
 {
 	if (!map->mmaped || map->libbpf_type == LIBBPF_MAP_KCONFIG ||
 	    size != map->def.value_size || map->fd >= 0)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memcpy(map->mmaped, data, size);
 	return 0;
 }
 
+const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize)
+{
+	if (!map->mmaped)
+		return NULL;
+	*psize = map->def.value_size;
+	return map->mmaped;
+}
+
 bool bpf_map__is_offload_neutral(const struct bpf_map *map)
 {
 	return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
@@ -9519,7 +9807,7 @@ __u32 bpf_map__ifindex(const struct bpf_map *map)
 int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
 {
 	if (map->fd >= 0)
-		return -EBUSY;
+		return libbpf_err(-EBUSY);
 	map->map_ifindex = ifindex;
 	return 0;
 }
@@ -9528,11 +9816,11 @@ int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd)
 {
 	if (!bpf_map_type__is_map_in_map(map->def.type)) {
 		pr_warn("error: unsupported map type\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 	if (map->inner_map_fd != -1) {
 		pr_warn("error: inner_map_fd already specified\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 	zfree(&map->inner_map);
 	map->inner_map_fd = fd;
@@ -9546,7 +9834,7 @@ __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i)
 	struct bpf_map *s, *e;
 
 	if (!obj || !obj->maps)
-		return NULL;
+		return errno = EINVAL, NULL;
 
 	s = obj->maps;
 	e = obj->maps + obj->nr_maps;
@@ -9554,7 +9842,7 @@ __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i)
 	if ((m < s) || (m >= e)) {
 		pr_warn("error in %s: map handler doesn't belong to object\n",
 			 __func__);
-		return NULL;
+		return errno = EINVAL, NULL;
 	}
 
 	idx = (m - obj->maps) + i;
@@ -9593,7 +9881,7 @@ bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name)
 		if (pos->name && !strcmp(pos->name, name))
 			return pos;
 	}
-	return NULL;
+	return errno = ENOENT, NULL;
 }
 
 int
@@ -9605,12 +9893,23 @@ bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name)
 struct bpf_map *
 bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset)
 {
-	return ERR_PTR(-ENOTSUP);
+	return libbpf_err_ptr(-ENOTSUP);
 }
 
 long libbpf_get_error(const void *ptr)
 {
-	return PTR_ERR_OR_ZERO(ptr);
+	if (!IS_ERR_OR_NULL(ptr))
+		return 0;
+
+	if (IS_ERR(ptr))
+		errno = -PTR_ERR(ptr);
+
+	/* If ptr == NULL, then errno should be already set by the failing
+	 * API, because libbpf never returns NULL on success and it now always
+	 * sets errno on error. So no extra errno handling for ptr == NULL
+	 * case.
+	 */
+	return -errno;
 }
 
 int bpf_prog_load(const char *file, enum bpf_prog_type type,
@@ -9636,16 +9935,17 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 	int err;
 
 	if (!attr)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	if (!attr->file)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	open_attr.file = attr->file;
 	open_attr.prog_type = attr->prog_type;
 
 	obj = bpf_object__open_xattr(&open_attr);
-	if (IS_ERR_OR_NULL(obj))
-		return -ENOENT;
+	err = libbpf_get_error(obj);
+	if (err)
+		return libbpf_err(-ENOENT);
 
 	bpf_object__for_each_program(prog, obj) {
 		enum bpf_attach_type attach_type = attr->expected_attach_type;
@@ -9665,7 +9965,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 			 * didn't provide a fallback type, too bad...
 			 */
 			bpf_object__close(obj);
-			return -EINVAL;
+			return libbpf_err(-EINVAL);
 		}
 
 		prog->prog_ifindex = attr->ifindex;
@@ -9683,13 +9983,13 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 	if (!first_prog) {
 		pr_warn("object file doesn't contain bpf program\n");
 		bpf_object__close(obj);
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 	}
 
 	err = bpf_object__load(obj);
 	if (err) {
 		bpf_object__close(obj);
-		return err;
+		return libbpf_err(err);
 	}
 
 	*pobj = obj;
@@ -9708,7 +10008,10 @@ struct bpf_link {
 /* Replace link's underlying BPF program with the new one */
 int bpf_link__update_program(struct bpf_link *link, struct bpf_program *prog)
 {
-	return bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), NULL);
+	int ret;
+	
+	ret = bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), NULL);
+	return libbpf_err_errno(ret);
 }
 
 /* Release "ownership" of underlying BPF resource (typically, BPF program
@@ -9741,7 +10044,7 @@ int bpf_link__destroy(struct bpf_link *link)
 		free(link->pin_path);
 	free(link);
 
-	return err;
+	return libbpf_err(err);
 }
 
 int bpf_link__fd(const struct bpf_link *link)
@@ -9756,7 +10059,7 @@ const char *bpf_link__pin_path(const struct bpf_link *link)
 
 static int bpf_link__detach_fd(struct bpf_link *link)
 {
-	return close(link->fd);
+	return libbpf_err_errno(close(link->fd));
 }
 
 struct bpf_link *bpf_link__open(const char *path)
@@ -9768,13 +10071,13 @@ struct bpf_link *bpf_link__open(const char *path)
 	if (fd < 0) {
 		fd = -errno;
 		pr_warn("failed to open link at %s: %d\n", path, fd);
-		return ERR_PTR(fd);
+		return libbpf_err_ptr(fd);
 	}
 
 	link = calloc(1, sizeof(*link));
 	if (!link) {
 		close(fd);
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 	}
 	link->detach = &bpf_link__detach_fd;
 	link->fd = fd;
@@ -9782,7 +10085,7 @@ struct bpf_link *bpf_link__open(const char *path)
 	link->pin_path = strdup(path);
 	if (!link->pin_path) {
 		bpf_link__destroy(link);
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 	}
 
 	return link;
@@ -9798,22 +10101,22 @@ int bpf_link__pin(struct bpf_link *link, const char *path)
 	int err;
 
 	if (link->pin_path)
-		return -EBUSY;
+		return libbpf_err(-EBUSY);
 	err = make_parent_dir(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 	err = check_path(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	link->pin_path = strdup(path);
 	if (!link->pin_path)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	if (bpf_obj_pin(link->fd, link->pin_path)) {
 		err = -errno;
 		zfree(&link->pin_path);
-		return err;
+		return libbpf_err(err);
 	}
 
 	pr_debug("link fd=%d: pinned at %s\n", link->fd, link->pin_path);
@@ -9825,11 +10128,11 @@ int bpf_link__unpin(struct bpf_link *link)
 	int err;
 
 	if (!link->pin_path)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	err = unlink(link->pin_path);
 	if (err != 0)
-		return -errno;
+		return libbpf_err_errno(err);
 
 	pr_debug("link fd=%d: unpinned from %s\n", link->fd, link->pin_path);
 	zfree(&link->pin_path);
@@ -9845,11 +10148,10 @@ static int bpf_link__detach_perf_event(struct bpf_link *link)
 		err = -errno;
 
 	close(link->fd);
-	return err;
+	return libbpf_err(err);
 }
 
-struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
-						int pfd)
+struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, int pfd)
 {
 	char errmsg[STRERR_BUFSIZE];
 	struct bpf_link *link;
@@ -9858,18 +10160,18 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
 	if (pfd < 0) {
 		pr_warn("prog '%s': invalid perf event FD %d\n",
 			prog->name, pfd);
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 	}
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
 		pr_warn("prog '%s': can't attach BPF program w/o FD (did you load it?)\n",
 			prog->name);
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 	}
 
 	link = calloc(1, sizeof(*link));
 	if (!link)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 	link->detach = &bpf_link__detach_perf_event;
 	link->fd = pfd;
 
@@ -9881,14 +10183,14 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
 		if (err == -EPROTO)
 			pr_warn("prog '%s': try add PERF_SAMPLE_CALLCHAIN to or remove exclude_callchain_[kernel|user] from pfd %d\n",
 				prog->name, pfd);
-		return ERR_PTR(err);
+		return libbpf_err_ptr(err);
 	}
 	if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
 		err = -errno;
 		free(link);
 		pr_warn("prog '%s': failed to enable pfd %d: %s\n",
 			prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
-		return ERR_PTR(err);
+		return libbpf_err_ptr(err);
 	}
 	return link;
 }
@@ -10012,16 +10314,16 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
 		pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n",
 			prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
 			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
-		return ERR_PTR(pfd);
+		return libbpf_err_ptr(pfd);
 	}
 	link = bpf_program__attach_perf_event(prog, pfd);
-	if (IS_ERR(link)) {
+	err = libbpf_get_error(link);
+	if (err) {
 		close(pfd);
-		err = PTR_ERR(link);
 		pr_warn("prog '%s': failed to attach to %s '%s': %s\n",
 			prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
-		return link;
+		return libbpf_err_ptr(err);
 	}
 	return link;
 }
@@ -10054,17 +10356,17 @@ struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
 			prog->name, retprobe ? "uretprobe" : "uprobe",
 			binary_path, func_offset,
 			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
-		return ERR_PTR(pfd);
+		return libbpf_err_ptr(pfd);
 	}
 	link = bpf_program__attach_perf_event(prog, pfd);
-	if (IS_ERR(link)) {
+	err = libbpf_get_error(link);
+	if (err) {
 		close(pfd);
-		err = PTR_ERR(link);
 		pr_warn("prog '%s': failed to attach to %s '%s:0x%zx': %s\n",
 			prog->name, retprobe ? "uretprobe" : "uprobe",
 			binary_path, func_offset,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
-		return link;
+		return libbpf_err_ptr(err);
 	}
 	return link;
 }
@@ -10132,16 +10434,16 @@ struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
 		pr_warn("prog '%s': failed to create tracepoint '%s/%s' perf event: %s\n",
 			prog->name, tp_category, tp_name,
 			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
-		return ERR_PTR(pfd);
+		return libbpf_err_ptr(pfd);
 	}
 	link = bpf_program__attach_perf_event(prog, pfd);
-	if (IS_ERR(link)) {
+	err = libbpf_get_error(link);
+	if (err) {
 		close(pfd);
-		err = PTR_ERR(link);
 		pr_warn("prog '%s': failed to attach to tracepoint '%s/%s': %s\n",
 			prog->name, tp_category, tp_name,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
-		return link;
+		return libbpf_err_ptr(err);
 	}
 	return link;
 }
@@ -10154,20 +10456,19 @@ static struct bpf_link *attach_tp(const struct bpf_sec_def *sec,
 
 	sec_name = strdup(prog->sec_name);
 	if (!sec_name)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 
 	/* extract "tp/<category>/<name>" */
 	tp_cat = sec_name + sec->len;
 	tp_name = strchr(tp_cat, '/');
 	if (!tp_name) {
-		link = ERR_PTR(-EINVAL);
-		goto out;
+		free(sec_name);
+		return libbpf_err_ptr(-EINVAL);
 	}
 	*tp_name = '\0';
 	tp_name++;
 
 	link = bpf_program__attach_tracepoint(prog, tp_cat, tp_name);
-out:
 	free(sec_name);
 	return link;
 }
@@ -10182,12 +10483,12 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
 		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 	}
 
 	link = calloc(1, sizeof(*link));
 	if (!link)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 	link->detach = &bpf_link__detach_fd;
 
 	pfd = bpf_raw_tracepoint_open(tp_name, prog_fd);
@@ -10196,7 +10497,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 		free(link);
 		pr_warn("prog '%s': failed to attach to raw tracepoint '%s': %s\n",
 			prog->name, tp_name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
-		return ERR_PTR(pfd);
+		return libbpf_err_ptr(pfd);
 	}
 	link->fd = pfd;
 	return link;
@@ -10220,12 +10521,12 @@ static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog)
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
 		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 	}
 
 	link = calloc(1, sizeof(*link));
 	if (!link)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 	link->detach = &bpf_link__detach_fd;
 
 	pfd = bpf_raw_tracepoint_open(NULL, prog_fd);
@@ -10234,7 +10535,7 @@ static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog)
 		free(link);
 		pr_warn("prog '%s': failed to attach: %s\n",
 			prog->name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
-		return ERR_PTR(pfd);
+		return libbpf_err_ptr(pfd);
 	}
 	link->fd = pfd;
 	return (struct bpf_link *)link;
@@ -10262,12 +10563,6 @@ static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec,
 	return bpf_program__attach_lsm(prog);
 }
 
-static struct bpf_link *attach_iter(const struct bpf_sec_def *sec,
-				    struct bpf_program *prog)
-{
-	return bpf_program__attach_iter(prog, NULL);
-}
-
 static struct bpf_link *
 bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id,
 		       const char *target_name)
@@ -10282,12 +10577,12 @@ bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id,
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
 		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 	}
 
 	link = calloc(1, sizeof(*link));
 	if (!link)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 	link->detach = &bpf_link__detach_fd;
 
 	attach_type = bpf_program__get_expected_attach_type(prog);
@@ -10298,7 +10593,7 @@ bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id,
 		pr_warn("prog '%s': failed to attach to %s: %s\n",
 			prog->name, target_name,
 			libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg)));
-		return ERR_PTR(link_fd);
+		return libbpf_err_ptr(link_fd);
 	}
 	link->fd = link_fd;
 	return link;
@@ -10331,19 +10626,19 @@ struct bpf_link *bpf_program__attach_freplace(struct bpf_program *prog,
 	if (!!target_fd != !!attach_func_name) {
 		pr_warn("prog '%s': supply none or both of target_fd and attach_func_name\n",
 			prog->name);
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 	}
 
 	if (prog->type != BPF_PROG_TYPE_EXT) {
 		pr_warn("prog '%s': only BPF_PROG_TYPE_EXT can attach as freplace",
 			prog->name);
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 	}
 
 	if (target_fd) {
 		btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd);
 		if (btf_id < 0)
-			return ERR_PTR(btf_id);
+			return libbpf_err_ptr(btf_id);
 
 		return bpf_program__attach_fd(prog, target_fd, btf_id, "freplace");
 	} else {
@@ -10365,7 +10660,7 @@ bpf_program__attach_iter(struct bpf_program *prog,
 	__u32 target_fd = 0;
 
 	if (!OPTS_VALID(opts, bpf_iter_attach_opts))
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 
 	link_create_opts.iter_info = OPTS_GET(opts, link_info, (void *)0);
 	link_create_opts.iter_info_len = OPTS_GET(opts, link_info_len, 0);
@@ -10373,12 +10668,12 @@ bpf_program__attach_iter(struct bpf_program *prog,
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
 		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 	}
 
 	link = calloc(1, sizeof(*link));
 	if (!link)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 	link->detach = &bpf_link__detach_fd;
 
 	link_fd = bpf_link_create(prog_fd, target_fd, BPF_TRACE_ITER,
@@ -10388,19 +10683,25 @@ bpf_program__attach_iter(struct bpf_program *prog,
 		free(link);
 		pr_warn("prog '%s': failed to attach to iterator: %s\n",
 			prog->name, libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg)));
-		return ERR_PTR(link_fd);
+		return libbpf_err_ptr(link_fd);
 	}
 	link->fd = link_fd;
 	return link;
 }
 
+static struct bpf_link *attach_iter(const struct bpf_sec_def *sec,
+				    struct bpf_program *prog)
+{
+	return bpf_program__attach_iter(prog, NULL);
+}
+
 struct bpf_link *bpf_program__attach(struct bpf_program *prog)
 {
 	const struct bpf_sec_def *sec_def;
 
 	sec_def = find_sec_def(prog->sec_name);
 	if (!sec_def || !sec_def->attach_fn)
-		return ERR_PTR(-ESRCH);
+		return libbpf_err_ptr(-ESRCH);
 
 	return sec_def->attach_fn(sec_def, prog);
 }
@@ -10423,11 +10724,11 @@ struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
 	int err;
 
 	if (!bpf_map__is_struct_ops(map) || map->fd == -1)
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 
 	link = calloc(1, sizeof(*link));
 	if (!link)
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 
 	st_ops = map->st_ops;
 	for (i = 0; i < btf_vlen(st_ops->type); i++) {
@@ -10447,7 +10748,7 @@ struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
 	if (err) {
 		err = -errno;
 		free(link);
-		return ERR_PTR(err);
+		return libbpf_err_ptr(err);
 	}
 
 	link->detach = bpf_link__detach_struct_ops;
@@ -10501,7 +10802,7 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
 	}
 
 	ring_buffer_write_tail(header, data_tail);
-	return ret;
+	return libbpf_err(ret);
 }
 
 struct perf_buffer;
@@ -10654,7 +10955,7 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt,
 	p.lost_cb = opts ? opts->lost_cb : NULL;
 	p.ctx = opts ? opts->ctx : NULL;
 
-	return __perf_buffer__new(map_fd, page_cnt, &p);
+	return libbpf_ptr(__perf_buffer__new(map_fd, page_cnt, &p));
 }
 
 struct perf_buffer *
@@ -10670,7 +10971,7 @@ perf_buffer__new_raw(int map_fd, size_t page_cnt,
 	p.cpus = opts->cpus;
 	p.map_keys = opts->map_keys;
 
-	return __perf_buffer__new(map_fd, page_cnt, &p);
+	return libbpf_ptr(__perf_buffer__new(map_fd, page_cnt, &p));
 }
 
 static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt,
@@ -10891,16 +11192,19 @@ int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms)
 	int i, cnt, err;
 
 	cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, timeout_ms);
+	if (cnt < 0)
+		return libbpf_err_errno(cnt);
+
 	for (i = 0; i < cnt; i++) {
 		struct perf_cpu_buf *cpu_buf = pb->events[i].data.ptr;
 
 		err = perf_buffer__process_records(pb, cpu_buf);
 		if (err) {
 			pr_warn("error while processing records: %d\n", err);
-			return err;
+			return libbpf_err(err);
 		}
 	}
-	return cnt < 0 ? -errno : cnt;
+	return cnt;
 }
 
 /* Return number of PERF_EVENT_ARRAY map slots set up by this perf_buffer
@@ -10921,11 +11225,11 @@ int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_idx)
 	struct perf_cpu_buf *cpu_buf;
 
 	if (buf_idx >= pb->cpu_cnt)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	cpu_buf = pb->cpu_bufs[buf_idx];
 	if (!cpu_buf)
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 
 	return cpu_buf->fd;
 }
@@ -10943,11 +11247,11 @@ int perf_buffer__consume_buffer(struct perf_buffer *pb, size_t buf_idx)
 	struct perf_cpu_buf *cpu_buf;
 
 	if (buf_idx >= pb->cpu_cnt)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	cpu_buf = pb->cpu_bufs[buf_idx];
 	if (!cpu_buf)
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 
 	return perf_buffer__process_records(pb, cpu_buf);
 }
@@ -10965,7 +11269,7 @@ int perf_buffer__consume(struct perf_buffer *pb)
 		err = perf_buffer__process_records(pb, cpu_buf);
 		if (err) {
 			pr_warn("perf_buffer: failed to process records in buffer #%d: %d\n", i, err);
-			return err;
+			return libbpf_err(err);
 		}
 	}
 	return 0;
@@ -11077,13 +11381,13 @@ bpf_program__get_prog_info_linear(int fd, __u64 arrays)
 	void *ptr;
 
 	if (arrays >> BPF_PROG_INFO_LAST_ARRAY)
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 
 	/* step 1: get array dimensions */
 	err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
 	if (err) {
 		pr_debug("can't get prog info: %s", strerror(errno));
-		return ERR_PTR(-EFAULT);
+		return libbpf_err_ptr(-EFAULT);
 	}
 
 	/* step 2: calculate total size of all arrays */
@@ -11115,7 +11419,7 @@ bpf_program__get_prog_info_linear(int fd, __u64 arrays)
 	data_len = roundup(data_len, sizeof(__u64));
 	info_linear = malloc(sizeof(struct bpf_prog_info_linear) + data_len);
 	if (!info_linear)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 
 	/* step 4: fill data to info_linear->info */
 	info_linear->arrays = arrays;
@@ -11147,7 +11451,7 @@ bpf_program__get_prog_info_linear(int fd, __u64 arrays)
 	if (err) {
 		pr_debug("can't get prog info: %s", strerror(errno));
 		free(info_linear);
-		return ERR_PTR(-EFAULT);
+		return libbpf_err_ptr(-EFAULT);
 	}
 
 	/* step 6: verify the data */
@@ -11226,26 +11530,26 @@ int bpf_program__set_attach_target(struct bpf_program *prog,
 	int btf_obj_fd = 0, btf_id = 0, err;
 
 	if (!prog || attach_prog_fd < 0 || !attach_func_name)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (prog->obj->loaded)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (attach_prog_fd) {
 		btf_id = libbpf_find_prog_btf_id(attach_func_name,
 						 attach_prog_fd);
 		if (btf_id < 0)
-			return btf_id;
+			return libbpf_err(btf_id);
 	} else {
 		/* load btf_vmlinux, if not yet */
 		err = bpf_object__load_vmlinux_btf(prog->obj, true);
 		if (err)
-			return err;
+			return libbpf_err(err);
 		err = find_kernel_btf_id(prog->obj, attach_func_name,
 					 prog->expected_attach_type,
 					 &btf_obj_fd, &btf_id);
 		if (err)
-			return err;
+			return libbpf_err(err);
 	}
 
 	prog->attach_btf_id = btf_id;
@@ -11344,7 +11648,7 @@ int libbpf_num_possible_cpus(void)
 
 	err = parse_cpu_mask_file(fcpu, &mask, &n);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	tmp_cpus = 0;
 	for (i = 0; i < n; i++) {
@@ -11364,7 +11668,7 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s,
 		.object_name = s->name,
 	);
 	struct bpf_object *obj;
-	int i;
+	int i, err;
 
 	/* Attempt to preserve opts->object_name, unless overriden by user
 	 * explicitly. Overwriting object name for skeletons is discouraged,
@@ -11379,10 +11683,11 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s,
 	}
 
 	obj = bpf_object__open_mem(s->data, s->data_sz, &skel_opts);
-	if (IS_ERR(obj)) {
-		pr_warn("failed to initialize skeleton BPF object '%s': %ld\n",
-			s->name, PTR_ERR(obj));
-		return PTR_ERR(obj);
+	err = libbpf_get_error(obj);
+	if (err) {
+		pr_warn("failed to initialize skeleton BPF object '%s': %d\n",
+			s->name, err);
+		return libbpf_err(err);
 	}
 
 	*s->obj = obj;
@@ -11395,7 +11700,7 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s,
 		*map = bpf_object__find_map_by_name(obj, name);
 		if (!*map) {
 			pr_warn("failed to find skeleton map '%s'\n", name);
-			return -ESRCH;
+			return libbpf_err(-ESRCH);
 		}
 
 		/* externs shouldn't be pre-setup from user code */
@@ -11410,7 +11715,7 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s,
 		*prog = bpf_object__find_program_by_name(obj, name);
 		if (!*prog) {
 			pr_warn("failed to find skeleton program '%s'\n", name);
-			return -ESRCH;
+			return libbpf_err(-ESRCH);
 		}
 	}
 
@@ -11424,7 +11729,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s)
 	err = bpf_object__load(*s->obj);
 	if (err) {
 		pr_warn("failed to load BPF skeleton '%s': %d\n", s->name, err);
-		return err;
+		return libbpf_err(err);
 	}
 
 	for (i = 0; i < s->map_cnt; i++) {
@@ -11463,7 +11768,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s)
 			*mmaped = NULL;
 			pr_warn("failed to re-mmap() map '%s': %d\n",
 				 bpf_map__name(map), err);
-			return err;
+			return libbpf_err(err);
 		}
 	}
 
@@ -11472,7 +11777,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s)
 
 int bpf_object__attach_skeleton(struct bpf_object_skeleton *s)
 {
-	int i;
+	int i, err;
 
 	for (i = 0; i < s->prog_cnt; i++) {
 		struct bpf_program *prog = *s->progs[i].prog;
@@ -11487,10 +11792,11 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s)
 			continue;
 
 		*link = sec_def->attach_fn(sec_def, prog);
-		if (IS_ERR(*link)) {
-			pr_warn("failed to auto-attach program '%s': %ld\n",
-				bpf_program__name(prog), PTR_ERR(*link));
-			return PTR_ERR(*link);
+		err = libbpf_get_error(*link);
+		if (err) {
+			pr_warn("failed to auto-attach program '%s': %d\n",
+				bpf_program__name(prog), err);
+			return libbpf_err(err);
 		}
 	}
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index bec4e6a6e31d..6e61342ba56c 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -18,6 +18,7 @@
 #include <linux/bpf.h>
 
 #include "libbpf_common.h"
+#include "libbpf_legacy.h"
 
 #ifdef __cplusplus
 extern "C" {
@@ -471,6 +472,7 @@ LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv,
 LIBBPF_API void *bpf_map__priv(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map,
 					  const void *data, size_t size);
+LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize);
 LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map);
 LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path);
@@ -498,6 +500,7 @@ LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type,
 			     struct bpf_object **pobj, int *prog_fd);
 
+/* XDP related API */
 struct xdp_link_info {
 	__u32 prog_id;
 	__u32 drv_prog_id;
@@ -520,6 +523,49 @@ LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags);
 LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
 				     size_t info_size, __u32 flags);
 
+/* TC related API */
+enum bpf_tc_attach_point {
+	BPF_TC_INGRESS = 1 << 0,
+	BPF_TC_EGRESS  = 1 << 1,
+	BPF_TC_CUSTOM  = 1 << 2,
+};
+
+#define BPF_TC_PARENT(a, b) 	\
+	((((a) << 16) & 0xFFFF0000U) | ((b) & 0x0000FFFFU))
+
+enum bpf_tc_flags {
+	BPF_TC_F_REPLACE = 1 << 0,
+};
+
+struct bpf_tc_hook {
+	size_t sz;
+	int ifindex;
+	enum bpf_tc_attach_point attach_point;
+	__u32 parent;
+	size_t :0;
+};
+#define bpf_tc_hook__last_field parent
+
+struct bpf_tc_opts {
+	size_t sz;
+	int prog_fd;
+	__u32 flags;
+	__u32 prog_id;
+	__u32 handle;
+	__u32 priority;
+	size_t :0;
+};
+#define bpf_tc_opts__last_field priority
+
+LIBBPF_API int bpf_tc_hook_create(struct bpf_tc_hook *hook);
+LIBBPF_API int bpf_tc_hook_destroy(struct bpf_tc_hook *hook);
+LIBBPF_API int bpf_tc_attach(const struct bpf_tc_hook *hook,
+			     struct bpf_tc_opts *opts);
+LIBBPF_API int bpf_tc_detach(const struct bpf_tc_hook *hook,
+			     const struct bpf_tc_opts *opts);
+LIBBPF_API int bpf_tc_query(const struct bpf_tc_hook *hook,
+			    struct bpf_tc_opts *opts);
+
 /* Ring buffer APIs */
 struct ring_buffer;
 
@@ -756,6 +802,18 @@ LIBBPF_API int bpf_object__attach_skeleton(struct bpf_object_skeleton *s);
 LIBBPF_API void bpf_object__detach_skeleton(struct bpf_object_skeleton *s);
 LIBBPF_API void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s);
 
+struct gen_loader_opts {
+	size_t sz; /* size of this struct, for forward/backward compatiblity */
+	const char *data;
+	const char *insns;
+	__u32 data_sz;
+	__u32 insns_sz;
+};
+
+#define gen_loader_opts__last_field insns_sz
+LIBBPF_API int bpf_object__gen_loader(struct bpf_object *obj,
+				      struct gen_loader_opts *opts);
+
 enum libbpf_tristate {
 	TRI_NO = 0,
 	TRI_YES = 1,
@@ -768,10 +826,18 @@ struct bpf_linker_opts {
 };
 #define bpf_linker_opts__last_field sz
 
+struct bpf_linker_file_opts {
+	/* size of this struct, for forward/backward compatiblity */
+	size_t sz;
+};
+#define bpf_linker_file_opts__last_field sz
+
 struct bpf_linker;
 
 LIBBPF_API struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts *opts);
-LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker, const char *filename);
+LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker,
+				    const char *filename,
+				    const struct bpf_linker_file_opts *opts);
 LIBBPF_API int bpf_linker__finalize(struct bpf_linker *linker);
 LIBBPF_API void bpf_linker__free(struct bpf_linker *linker);
 
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index b9b29baf1df8..944c99d1ded3 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -361,4 +361,17 @@ LIBBPF_0.4.0 {
 		bpf_linker__new;
 		bpf_map__inner_map;
 		bpf_object__set_kversion;
+		bpf_tc_attach;
+		bpf_tc_detach;
+		bpf_tc_hook_create;
+		bpf_tc_hook_destroy;
+		bpf_tc_query;
 } LIBBPF_0.3.0;
+
+LIBBPF_0.5.0 {
+	global:
+		bpf_map__initial_value;
+		bpf_map_lookup_and_delete_elem_flags;
+		bpf_object__gen_loader;
+		libbpf_set_strict_mode;
+} LIBBPF_0.4.0;
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
index 0afb51f7a919..96f67a772a1b 100644
--- a/tools/lib/bpf/libbpf_errno.c
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -12,6 +12,7 @@
 #include <string.h>
 
 #include "libbpf.h"
+#include "libbpf_internal.h"
 
 /* make sure libbpf doesn't use kernel-only integer typedefs */
 #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
@@ -39,7 +40,7 @@ static const char *libbpf_strerror_table[NR_ERRNO] = {
 int libbpf_strerror(int err, char *buf, size_t size)
 {
 	if (!buf || !size)
-		return -1;
+		return libbpf_err(-EINVAL);
 
 	err = err > 0 ? err : -err;
 
@@ -48,7 +49,7 @@ int libbpf_strerror(int err, char *buf, size_t size)
 
 		ret = strerror_r(err, buf, size);
 		buf[size - 1] = '\0';
-		return ret;
+		return libbpf_err_errno(ret);
 	}
 
 	if (err < __LIBBPF_ERRNO__END) {
@@ -62,5 +63,5 @@ int libbpf_strerror(int err, char *buf, size_t size)
 
 	snprintf(buf, size, "Unknown libbpf error %d", err);
 	buf[size - 1] = '\0';
-	return -1;
+	return libbpf_err(-ENOENT);
 }
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index acbcf6c7bdf8..016ca7cb4f8a 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -11,6 +11,9 @@
 
 #include <stdlib.h>
 #include <limits.h>
+#include <errno.h>
+#include <linux/err.h>
+#include "libbpf_legacy.h"
 
 /* make sure libbpf doesn't use kernel-only integer typedefs */
 #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
@@ -28,6 +31,12 @@
 #ifndef R_BPF_64_64
 #define R_BPF_64_64 1
 #endif
+#ifndef R_BPF_64_ABS64
+#define R_BPF_64_ABS64 2
+#endif
+#ifndef R_BPF_64_ABS32
+#define R_BPF_64_ABS32 3
+#endif
 #ifndef R_BPF_64_32
 #define R_BPF_64_32 10
 #endif
@@ -263,6 +272,8 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name,
 int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
 				__u32 *off);
 struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf);
+void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type,
+				const char **prefix, int *kind);
 
 struct btf_ext_info {
 	/*
@@ -433,4 +444,54 @@ int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ct
 int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx);
 int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx);
 
+extern enum libbpf_strict_mode libbpf_mode;
+
+/* handle direct returned errors */
+static inline int libbpf_err(int ret)
+{
+	if (ret < 0)
+		errno = -ret;
+	return ret;
+}
+
+/* handle errno-based (e.g., syscall or libc) errors according to libbpf's
+ * strict mode settings
+ */
+static inline int libbpf_err_errno(int ret)
+{
+	if (libbpf_mode & LIBBPF_STRICT_DIRECT_ERRS)
+		/* errno is already assumed to be set on error */
+		return ret < 0 ? -errno : ret;
+
+	/* legacy: on error return -1 directly and don't touch errno */
+	return ret;
+}
+
+/* handle error for pointer-returning APIs, err is assumed to be < 0 always */
+static inline void *libbpf_err_ptr(int err)
+{
+	/* set errno on error, this doesn't break anything */
+	errno = -err;
+
+	if (libbpf_mode & LIBBPF_STRICT_CLEAN_PTRS)
+		return NULL;
+
+	/* legacy: encode err as ptr */
+	return ERR_PTR(err);
+}
+
+/* handle pointer-returning APIs' error handling */
+static inline void *libbpf_ptr(void *ret)
+{
+	/* set errno on error, this doesn't break anything */
+	if (IS_ERR(ret))
+		errno = -PTR_ERR(ret);
+
+	if (libbpf_mode & LIBBPF_STRICT_CLEAN_PTRS)
+		return IS_ERR(ret) ? NULL : ret;
+
+	/* legacy: pass-through original pointer */
+	return ret;
+}
+
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */
diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h
new file mode 100644
index 000000000000..df0d03dcffab
--- /dev/null
+++ b/tools/lib/bpf/libbpf_legacy.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+/*
+ * Libbpf legacy APIs (either discouraged or deprecated, as mentioned in [0])
+ *
+ *   [0] https://docs.google.com/document/d/1UyjTZuPFWiPFyKk1tV5an11_iaRuec6U-ZESZ54nNTY
+ *
+ * Copyright (C) 2021 Facebook
+ */
+#ifndef __LIBBPF_LEGACY_BPF_H
+#define __LIBBPF_LEGACY_BPF_H
+
+#include <linux/bpf.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+#include "libbpf_common.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+enum libbpf_strict_mode {
+	/* Turn on all supported strict features of libbpf to simulate libbpf
+	 * v1.0 behavior.
+	 * This will be the default behavior in libbpf v1.0.
+	 */
+	LIBBPF_STRICT_ALL = 0xffffffff,
+
+	/*
+	 * Disable any libbpf 1.0 behaviors. This is the default before libbpf
+	 * v1.0. It won't be supported anymore in v1.0, please update your
+	 * code so that it handles LIBBPF_STRICT_ALL mode before libbpf v1.0.
+	 */
+	LIBBPF_STRICT_NONE = 0x00,
+	/*
+	 * Return NULL pointers on error, not ERR_PTR(err).
+	 * Additionally, libbpf also always sets errno to corresponding Exx
+	 * (positive) error code.
+	 */
+	LIBBPF_STRICT_CLEAN_PTRS = 0x01,
+	/*
+	 * Return actual error codes from low-level APIs directly, not just -1.
+	 * Additionally, libbpf also always sets errno to corresponding Exx
+	 * (positive) error code.
+	 */
+	LIBBPF_STRICT_DIRECT_ERRS = 0x02,
+
+	__LIBBPF_STRICT_LAST,
+};
+
+LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode);
+
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
+#endif /* __LIBBPF_LEGACY_BPF_H */
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index 9de084b1c699..10911a8cad0f 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -158,7 +158,9 @@ struct bpf_linker {
 
 static int init_output_elf(struct bpf_linker *linker, const char *file);
 
-static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, struct src_obj *obj);
+static int linker_load_obj_file(struct bpf_linker *linker, const char *filename,
+				const struct bpf_linker_file_opts *opts,
+				struct src_obj *obj);
 static int linker_sanity_check_elf(struct src_obj *obj);
 static int linker_sanity_check_elf_symtab(struct src_obj *obj, struct src_sec *sec);
 static int linker_sanity_check_elf_relos(struct src_obj *obj, struct src_sec *sec);
@@ -218,16 +220,16 @@ struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts
 	int err;
 
 	if (!OPTS_VALID(opts, bpf_linker_opts))
-		return NULL;
+		return errno = EINVAL, NULL;
 
 	if (elf_version(EV_CURRENT) == EV_NONE) {
 		pr_warn_elf("libelf initialization failed");
-		return NULL;
+		return errno = EINVAL, NULL;
 	}
 
 	linker = calloc(1, sizeof(*linker));
 	if (!linker)
-		return NULL;
+		return errno = ENOMEM, NULL;
 
 	linker->fd = -1;
 
@@ -239,7 +241,7 @@ struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts
 
 err_out:
 	bpf_linker__free(linker);
-	return NULL;
+	return errno = -err, NULL;
 }
 
 static struct dst_sec *add_dst_sec(struct bpf_linker *linker, const char *sec_name)
@@ -435,15 +437,19 @@ static int init_output_elf(struct bpf_linker *linker, const char *file)
 	return 0;
 }
 
-int bpf_linker__add_file(struct bpf_linker *linker, const char *filename)
+int bpf_linker__add_file(struct bpf_linker *linker, const char *filename,
+			 const struct bpf_linker_file_opts *opts)
 {
 	struct src_obj obj = {};
 	int err = 0;
 
+	if (!OPTS_VALID(opts, bpf_linker_file_opts))
+		return libbpf_err(-EINVAL);
+
 	if (!linker->elf)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
-	err = err ?: linker_load_obj_file(linker, filename, &obj);
+	err = err ?: linker_load_obj_file(linker, filename, opts, &obj);
 	err = err ?: linker_append_sec_data(linker, &obj);
 	err = err ?: linker_append_elf_syms(linker, &obj);
 	err = err ?: linker_append_elf_relos(linker, &obj);
@@ -461,7 +467,7 @@ int bpf_linker__add_file(struct bpf_linker *linker, const char *filename)
 	if (obj.fd >= 0)
 		close(obj.fd);
 
-	return err;
+	return libbpf_err(err);
 }
 
 static bool is_dwarf_sec_name(const char *name)
@@ -529,7 +535,9 @@ static struct src_sec *add_src_sec(struct src_obj *obj, const char *sec_name)
 	return sec;
 }
 
-static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, struct src_obj *obj)
+static int linker_load_obj_file(struct bpf_linker *linker, const char *filename,
+				const struct bpf_linker_file_opts *opts,
+				struct src_obj *obj)
 {
 #if __BYTE_ORDER == __LITTLE_ENDIAN
 	const int host_endianness = ELFDATA2LSB;
@@ -884,7 +892,8 @@ static int linker_sanity_check_elf_relos(struct src_obj *obj, struct src_sec *se
 		size_t sym_idx = ELF64_R_SYM(relo->r_info);
 		size_t sym_type = ELF64_R_TYPE(relo->r_info);
 
-		if (sym_type != R_BPF_64_64 && sym_type != R_BPF_64_32) {
+		if (sym_type != R_BPF_64_64 && sym_type != R_BPF_64_32 &&
+		    sym_type != R_BPF_64_ABS64 && sym_type != R_BPF_64_ABS32) {
 			pr_warn("ELF relo #%d in section #%zu has unexpected type %zu in %s\n",
 				i, sec->sec_idx, sym_type, obj->filename);
 			return -EINVAL;
@@ -1780,7 +1789,7 @@ static void sym_update_visibility(Elf64_Sym *sym, int sym_vis)
 	/* libelf doesn't provide setters for ST_VISIBILITY,
 	 * but it is stored in the lower 2 bits of st_other
 	 */
-	sym->st_other &= 0x03;
+	sym->st_other &= ~0x03;
 	sym->st_other |= sym_vis;
 }
 
@@ -2539,11 +2548,11 @@ int bpf_linker__finalize(struct bpf_linker *linker)
 	int err, i;
 
 	if (!linker->elf)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	err = finalize_btf(linker);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	/* Finalize strings */
 	strs_sz = strset__data_size(linker->strtab_strs);
@@ -2575,14 +2584,14 @@ int bpf_linker__finalize(struct bpf_linker *linker)
 	if (elf_update(linker->elf, ELF_C_NULL) < 0) {
 		err = -errno;
 		pr_warn_elf("failed to finalize ELF layout");
-		return err;
+		return libbpf_err(err);
 	}
 
 	/* Write out final ELF contents */
 	if (elf_update(linker->elf, ELF_C_WRITE) < 0) {
 		err = -errno;
 		pr_warn_elf("failed to write ELF contents");
-		return err;
+		return libbpf_err(err);
 	}
 
 	elf_end(linker->elf);
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index d2cb28e9ef52..cf9381f03b16 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -4,7 +4,10 @@
 #include <stdlib.h>
 #include <memory.h>
 #include <unistd.h>
+#include <arpa/inet.h>
 #include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/pkt_cls.h>
 #include <linux/rtnetlink.h>
 #include <sys/socket.h>
 #include <errno.h>
@@ -73,9 +76,20 @@ cleanup:
 	return ret;
 }
 
-static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
-			    __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn,
-			    void *cookie)
+static void libbpf_netlink_close(int sock)
+{
+	close(sock);
+}
+
+enum {
+	NL_CONT,
+	NL_NEXT,
+	NL_DONE,
+};
+
+static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq,
+			       __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn,
+			       void *cookie)
 {
 	bool multipart = true;
 	struct nlmsgerr *err;
@@ -84,6 +98,7 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 	int len, ret;
 
 	while (multipart) {
+start:
 		multipart = false;
 		len = recv(sock, buf, sizeof(buf), 0);
 		if (len < 0) {
@@ -121,8 +136,16 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 			}
 			if (_fn) {
 				ret = _fn(nh, fn, cookie);
-				if (ret)
+				switch (ret) {
+				case NL_CONT:
+					break;
+				case NL_NEXT:
+					goto start;
+				case NL_DONE:
+					return 0;
+				default:
 					return ret;
+				}
 			}
 		}
 	}
@@ -131,95 +154,97 @@ done:
 	return ret;
 }
 
+static int libbpf_netlink_send_recv(struct nlmsghdr *nh,
+				    __dump_nlmsg_t parse_msg,
+				    libbpf_dump_nlmsg_t parse_attr,
+				    void *cookie)
+{
+	__u32 nl_pid = 0;
+	int sock, ret;
+
+	sock = libbpf_netlink_open(&nl_pid);
+	if (sock < 0)
+		return sock;
+
+	nh->nlmsg_pid = 0;
+	nh->nlmsg_seq = time(NULL);
+
+	if (send(sock, nh, nh->nlmsg_len, 0) < 0) {
+		ret = -errno;
+		goto out;
+	}
+
+	ret = libbpf_netlink_recv(sock, nl_pid, nh->nlmsg_seq,
+				  parse_msg, parse_attr, cookie);
+out:
+	libbpf_netlink_close(sock);
+	return ret;
+}
+
 static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd,
 					 __u32 flags)
 {
-	int sock, seq = 0, ret;
-	struct nlattr *nla, *nla_xdp;
+	struct nlattr *nla;
+	int ret;
 	struct {
 		struct nlmsghdr  nh;
 		struct ifinfomsg ifinfo;
 		char             attrbuf[64];
 	} req;
-	__u32 nl_pid = 0;
-
-	sock = libbpf_netlink_open(&nl_pid);
-	if (sock < 0)
-		return sock;
 
 	memset(&req, 0, sizeof(req));
-	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
-	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
-	req.nh.nlmsg_type = RTM_SETLINK;
-	req.nh.nlmsg_pid = 0;
-	req.nh.nlmsg_seq = ++seq;
+	req.nh.nlmsg_len      = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+	req.nh.nlmsg_flags    = NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_type     = RTM_SETLINK;
 	req.ifinfo.ifi_family = AF_UNSPEC;
-	req.ifinfo.ifi_index = ifindex;
-
-	/* started nested attribute for XDP */
-	nla = (struct nlattr *)(((char *)&req)
-				+ NLMSG_ALIGN(req.nh.nlmsg_len));
-	nla->nla_type = NLA_F_NESTED | IFLA_XDP;
-	nla->nla_len = NLA_HDRLEN;
-
-	/* add XDP fd */
-	nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-	nla_xdp->nla_type = IFLA_XDP_FD;
-	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
-	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
-	nla->nla_len += nla_xdp->nla_len;
-
-	/* if user passed in any flags, add those too */
+	req.ifinfo.ifi_index  = ifindex;
+
+	nla = nlattr_begin_nested(&req.nh, sizeof(req), IFLA_XDP);
+	if (!nla)
+		return -EMSGSIZE;
+	ret = nlattr_add(&req.nh, sizeof(req), IFLA_XDP_FD, &fd, sizeof(fd));
+	if (ret < 0)
+		return ret;
 	if (flags) {
-		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-		nla_xdp->nla_type = IFLA_XDP_FLAGS;
-		nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
-		memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
-		nla->nla_len += nla_xdp->nla_len;
+		ret = nlattr_add(&req.nh, sizeof(req), IFLA_XDP_FLAGS, &flags,
+				 sizeof(flags));
+		if (ret < 0)
+			return ret;
 	}
-
 	if (flags & XDP_FLAGS_REPLACE) {
-		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-		nla_xdp->nla_type = IFLA_XDP_EXPECTED_FD;
-		nla_xdp->nla_len = NLA_HDRLEN + sizeof(old_fd);
-		memcpy((char *)nla_xdp + NLA_HDRLEN, &old_fd, sizeof(old_fd));
-		nla->nla_len += nla_xdp->nla_len;
+		ret = nlattr_add(&req.nh, sizeof(req), IFLA_XDP_EXPECTED_FD,
+				 &old_fd, sizeof(old_fd));
+		if (ret < 0)
+			return ret;
 	}
+	nlattr_end_nested(&req.nh, nla);
 
-	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
-
-	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
-		ret = -errno;
-		goto cleanup;
-	}
-	ret = bpf_netlink_recv(sock, nl_pid, seq, NULL, NULL, NULL);
-
-cleanup:
-	close(sock);
-	return ret;
+	return libbpf_netlink_send_recv(&req.nh, NULL, NULL, NULL);
 }
 
 int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags,
 			     const struct bpf_xdp_set_link_opts *opts)
 {
-	int old_fd = -1;
+	int old_fd = -1, ret;
 
 	if (!OPTS_VALID(opts, bpf_xdp_set_link_opts))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (OPTS_HAS(opts, old_fd)) {
 		old_fd = OPTS_GET(opts, old_fd, -1);
 		flags |= XDP_FLAGS_REPLACE;
 	}
 
-	return __bpf_set_link_xdp_fd_replace(ifindex, fd,
-					     old_fd,
-					     flags);
+	ret = __bpf_set_link_xdp_fd_replace(ifindex, fd, old_fd, flags);
+	return libbpf_err(ret);
 }
 
 int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 {
-	return __bpf_set_link_xdp_fd_replace(ifindex, fd, 0, flags);
+	int ret;
+
+	ret = __bpf_set_link_xdp_fd_replace(ifindex, fd, 0, flags);
+	return libbpf_err(ret);
 }
 
 static int __dump_link_nlmsg(struct nlmsghdr *nlh,
@@ -231,6 +256,7 @@ static int __dump_link_nlmsg(struct nlmsghdr *nlh,
 
 	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi));
 	attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi)));
+
 	if (libbpf_nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
@@ -282,34 +308,36 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb)
 	return 0;
 }
 
-static int libbpf_nl_get_link(int sock, unsigned int nl_pid,
-			      libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie);
-
 int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
 			  size_t info_size, __u32 flags)
 {
 	struct xdp_id_md xdp_id = {};
-	int sock, ret;
-	__u32 nl_pid = 0;
 	__u32 mask;
+	int ret;
+	struct {
+		struct nlmsghdr  nh;
+		struct ifinfomsg ifm;
+	} req = {
+		.nh.nlmsg_len   = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
+		.nh.nlmsg_type  = RTM_GETLINK,
+		.nh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+		.ifm.ifi_family = AF_PACKET,
+	};
 
 	if (flags & ~XDP_FLAGS_MASK || !info_size)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* Check whether the single {HW,DRV,SKB} mode is set */
 	flags &= (XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE);
 	mask = flags - 1;
 	if (flags && flags & mask)
-		return -EINVAL;
-
-	sock = libbpf_netlink_open(&nl_pid);
-	if (sock < 0)
-		return sock;
+		return libbpf_err(-EINVAL);
 
 	xdp_id.ifindex = ifindex;
 	xdp_id.flags = flags;
 
-	ret = libbpf_nl_get_link(sock, nl_pid, get_xdp_info, &xdp_id);
+	ret = libbpf_netlink_send_recv(&req.nh, __dump_link_nlmsg,
+				       get_xdp_info, &xdp_id);
 	if (!ret) {
 		size_t sz = min(info_size, sizeof(xdp_id.info));
 
@@ -317,8 +345,7 @@ int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
 		memset((void *) info + sz, 0, info_size - sz);
 	}
 
-	close(sock);
-	return ret;
+	return libbpf_err(ret);
 }
 
 static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags)
@@ -346,27 +373,413 @@ int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
 	if (!ret)
 		*prog_id = get_xdp_id(&info, flags);
 
-	return ret;
+	return libbpf_err(ret);
+}
+
+typedef int (*qdisc_config_t)(struct nlmsghdr *nh, struct tcmsg *t,
+			      size_t maxsz);
+
+static int clsact_config(struct nlmsghdr *nh, struct tcmsg *t, size_t maxsz)
+{
+	t->tcm_parent = TC_H_CLSACT;
+	t->tcm_handle = TC_H_MAKE(TC_H_CLSACT, 0);
+
+	return nlattr_add(nh, maxsz, TCA_KIND, "clsact", sizeof("clsact"));
+}
+
+static int attach_point_to_config(struct bpf_tc_hook *hook,
+				  qdisc_config_t *config)
+{
+	switch (OPTS_GET(hook, attach_point, 0)) {
+	case BPF_TC_INGRESS:
+	case BPF_TC_EGRESS:
+	case BPF_TC_INGRESS | BPF_TC_EGRESS:
+		if (OPTS_GET(hook, parent, 0))
+			return -EINVAL;
+		*config = &clsact_config;
+		return 0;
+	case BPF_TC_CUSTOM:
+		return -EOPNOTSUPP;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int tc_get_tcm_parent(enum bpf_tc_attach_point attach_point,
+			     __u32 *parent)
+{
+	switch (attach_point) {
+	case BPF_TC_INGRESS:
+	case BPF_TC_EGRESS:
+		if (*parent)
+			return -EINVAL;
+		*parent = TC_H_MAKE(TC_H_CLSACT,
+				    attach_point == BPF_TC_INGRESS ?
+				    TC_H_MIN_INGRESS : TC_H_MIN_EGRESS);
+		break;
+	case BPF_TC_CUSTOM:
+		if (!*parent)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
 }
 
-int libbpf_nl_get_link(int sock, unsigned int nl_pid,
-		       libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
+static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags)
 {
+	qdisc_config_t config;
+	int ret;
 	struct {
-		struct nlmsghdr nlh;
-		struct ifinfomsg ifm;
-	} req = {
-		.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
-		.nlh.nlmsg_type = RTM_GETLINK,
-		.nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
-		.ifm.ifi_family = AF_PACKET,
-	};
-	int seq = time(NULL);
+		struct nlmsghdr nh;
+		struct tcmsg tc;
+		char buf[256];
+	} req;
+
+	ret = attach_point_to_config(hook, &config);
+	if (ret < 0)
+		return ret;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len   = NLMSG_LENGTH(sizeof(struct tcmsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | flags;
+	req.nh.nlmsg_type  = cmd;
+	req.tc.tcm_family  = AF_UNSPEC;
+	req.tc.tcm_ifindex = OPTS_GET(hook, ifindex, 0);
+
+	ret = config(&req.nh, &req.tc, sizeof(req));
+	if (ret < 0)
+		return ret;
+
+	return libbpf_netlink_send_recv(&req.nh, NULL, NULL, NULL);
+}
 
-	req.nlh.nlmsg_seq = seq;
-	if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+static int tc_qdisc_create_excl(struct bpf_tc_hook *hook)
+{
+	return tc_qdisc_modify(hook, RTM_NEWQDISC, NLM_F_CREATE | NLM_F_EXCL);
+}
+
+static int tc_qdisc_delete(struct bpf_tc_hook *hook)
+{
+	return tc_qdisc_modify(hook, RTM_DELQDISC, 0);
+}
+
+int bpf_tc_hook_create(struct bpf_tc_hook *hook)
+{
+	int ret;
+
+	if (!hook || !OPTS_VALID(hook, bpf_tc_hook) ||
+	    OPTS_GET(hook, ifindex, 0) <= 0)
+		return libbpf_err(-EINVAL);
+
+	ret = tc_qdisc_create_excl(hook);
+	return libbpf_err(ret);
+}
+
+static int __bpf_tc_detach(const struct bpf_tc_hook *hook,
+			   const struct bpf_tc_opts *opts,
+			   const bool flush);
+
+int bpf_tc_hook_destroy(struct bpf_tc_hook *hook)
+{
+	if (!hook || !OPTS_VALID(hook, bpf_tc_hook) ||
+	    OPTS_GET(hook, ifindex, 0) <= 0)
+		return libbpf_err(-EINVAL);
+
+	switch (OPTS_GET(hook, attach_point, 0)) {
+	case BPF_TC_INGRESS:
+	case BPF_TC_EGRESS:
+		return libbpf_err(__bpf_tc_detach(hook, NULL, true));
+	case BPF_TC_INGRESS | BPF_TC_EGRESS:
+		return libbpf_err(tc_qdisc_delete(hook));
+	case BPF_TC_CUSTOM:
+		return libbpf_err(-EOPNOTSUPP);
+	default:
+		return libbpf_err(-EINVAL);
+	}
+}
+
+struct bpf_cb_ctx {
+	struct bpf_tc_opts *opts;
+	bool processed;
+};
+
+static int __get_tc_info(void *cookie, struct tcmsg *tc, struct nlattr **tb,
+			 bool unicast)
+{
+	struct nlattr *tbb[TCA_BPF_MAX + 1];
+	struct bpf_cb_ctx *info = cookie;
+
+	if (!info || !info->opts)
+		return -EINVAL;
+	if (unicast && info->processed)
+		return -EINVAL;
+	if (!tb[TCA_OPTIONS])
+		return NL_CONT;
+
+	libbpf_nla_parse_nested(tbb, TCA_BPF_MAX, tb[TCA_OPTIONS], NULL);
+	if (!tbb[TCA_BPF_ID])
+		return -EINVAL;
+
+	OPTS_SET(info->opts, prog_id, libbpf_nla_getattr_u32(tbb[TCA_BPF_ID]));
+	OPTS_SET(info->opts, handle, tc->tcm_handle);
+	OPTS_SET(info->opts, priority, TC_H_MAJ(tc->tcm_info) >> 16);
+
+	info->processed = true;
+	return unicast ? NL_NEXT : NL_DONE;
+}
+
+static int get_tc_info(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn,
+		       void *cookie)
+{
+	struct tcmsg *tc = NLMSG_DATA(nh);
+	struct nlattr *tb[TCA_MAX + 1];
+
+	libbpf_nla_parse(tb, TCA_MAX,
+			 (struct nlattr *)((char *)tc + NLMSG_ALIGN(sizeof(*tc))),
+			 NLMSG_PAYLOAD(nh, sizeof(*tc)), NULL);
+	if (!tb[TCA_KIND])
+		return NL_CONT;
+	return __get_tc_info(cookie, tc, tb, nh->nlmsg_flags & NLM_F_ECHO);
+}
+
+static int tc_add_fd_and_name(struct nlmsghdr *nh, size_t maxsz, int fd)
+{
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	char name[256];
+	int len, ret;
+
+	ret = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+	if (ret < 0)
+		return ret;
+
+	ret = nlattr_add(nh, maxsz, TCA_BPF_FD, &fd, sizeof(fd));
+	if (ret < 0)
+		return ret;
+	len = snprintf(name, sizeof(name), "%s:[%u]", info.name, info.id);
+	if (len < 0)
 		return -errno;
+	if (len >= sizeof(name))
+		return -ENAMETOOLONG;
+	return nlattr_add(nh, maxsz, TCA_BPF_NAME, name, len + 1);
+}
+
+int bpf_tc_attach(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts)
+{
+	__u32 protocol, bpf_flags, handle, priority, parent, prog_id, flags;
+	int ret, ifindex, attach_point, prog_fd;
+	struct bpf_cb_ctx info = {};
+	struct nlattr *nla;
+	struct {
+		struct nlmsghdr nh;
+		struct tcmsg tc;
+		char buf[256];
+	} req;
+
+	if (!hook || !opts ||
+	    !OPTS_VALID(hook, bpf_tc_hook) ||
+	    !OPTS_VALID(opts, bpf_tc_opts))
+		return libbpf_err(-EINVAL);
+
+	ifindex      = OPTS_GET(hook, ifindex, 0);
+	parent       = OPTS_GET(hook, parent, 0);
+	attach_point = OPTS_GET(hook, attach_point, 0);
+
+	handle       = OPTS_GET(opts, handle, 0);
+	priority     = OPTS_GET(opts, priority, 0);
+	prog_fd      = OPTS_GET(opts, prog_fd, 0);
+	prog_id      = OPTS_GET(opts, prog_id, 0);
+	flags        = OPTS_GET(opts, flags, 0);
 
-	return bpf_netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg,
-				dump_link_nlmsg, cookie);
+	if (ifindex <= 0 || !prog_fd || prog_id)
+		return libbpf_err(-EINVAL);
+	if (priority > UINT16_MAX)
+		return libbpf_err(-EINVAL);
+	if (flags & ~BPF_TC_F_REPLACE)
+		return libbpf_err(-EINVAL);
+
+	flags = (flags & BPF_TC_F_REPLACE) ? NLM_F_REPLACE : NLM_F_EXCL;
+	protocol = ETH_P_ALL;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len   = NLMSG_LENGTH(sizeof(struct tcmsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_CREATE |
+			     NLM_F_ECHO | flags;
+	req.nh.nlmsg_type  = RTM_NEWTFILTER;
+	req.tc.tcm_family  = AF_UNSPEC;
+	req.tc.tcm_ifindex = ifindex;
+	req.tc.tcm_handle  = handle;
+	req.tc.tcm_info    = TC_H_MAKE(priority << 16, htons(protocol));
+
+	ret = tc_get_tcm_parent(attach_point, &parent);
+	if (ret < 0)
+		return libbpf_err(ret);
+	req.tc.tcm_parent = parent;
+
+	ret = nlattr_add(&req.nh, sizeof(req), TCA_KIND, "bpf", sizeof("bpf"));
+	if (ret < 0)
+		return libbpf_err(ret);
+	nla = nlattr_begin_nested(&req.nh, sizeof(req), TCA_OPTIONS);
+	if (!nla)
+		return libbpf_err(-EMSGSIZE);
+	ret = tc_add_fd_and_name(&req.nh, sizeof(req), prog_fd);
+	if (ret < 0)
+		return libbpf_err(ret);
+	bpf_flags = TCA_BPF_FLAG_ACT_DIRECT;
+	ret = nlattr_add(&req.nh, sizeof(req), TCA_BPF_FLAGS, &bpf_flags,
+			 sizeof(bpf_flags));
+	if (ret < 0)
+		return libbpf_err(ret);
+	nlattr_end_nested(&req.nh, nla);
+
+	info.opts = opts;
+
+	ret = libbpf_netlink_send_recv(&req.nh, get_tc_info, NULL, &info);
+	if (ret < 0)
+		return libbpf_err(ret);
+	if (!info.processed)
+		return libbpf_err(-ENOENT);
+	return ret;
+}
+
+static int __bpf_tc_detach(const struct bpf_tc_hook *hook,
+			   const struct bpf_tc_opts *opts,
+			   const bool flush)
+{
+	__u32 protocol = 0, handle, priority, parent, prog_id, flags;
+	int ret, ifindex, attach_point, prog_fd;
+	struct {
+		struct nlmsghdr nh;
+		struct tcmsg tc;
+		char buf[256];
+	} req;
+
+	if (!hook ||
+	    !OPTS_VALID(hook, bpf_tc_hook) ||
+	    !OPTS_VALID(opts, bpf_tc_opts))
+		return -EINVAL;
+
+	ifindex      = OPTS_GET(hook, ifindex, 0);
+	parent       = OPTS_GET(hook, parent, 0);
+	attach_point = OPTS_GET(hook, attach_point, 0);
+
+	handle       = OPTS_GET(opts, handle, 0);
+	priority     = OPTS_GET(opts, priority, 0);
+	prog_fd      = OPTS_GET(opts, prog_fd, 0);
+	prog_id      = OPTS_GET(opts, prog_id, 0);
+	flags        = OPTS_GET(opts, flags, 0);
+
+	if (ifindex <= 0 || flags || prog_fd || prog_id)
+		return -EINVAL;
+	if (priority > UINT16_MAX)
+		return -EINVAL;
+	if (!flush) {
+		if (!handle || !priority)
+			return -EINVAL;
+		protocol = ETH_P_ALL;
+	} else {
+		if (handle || priority)
+			return -EINVAL;
+	}
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len   = NLMSG_LENGTH(sizeof(struct tcmsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_type  = RTM_DELTFILTER;
+	req.tc.tcm_family  = AF_UNSPEC;
+	req.tc.tcm_ifindex = ifindex;
+	if (!flush) {
+		req.tc.tcm_handle = handle;
+		req.tc.tcm_info   = TC_H_MAKE(priority << 16, htons(protocol));
+	}
+
+	ret = tc_get_tcm_parent(attach_point, &parent);
+	if (ret < 0)
+		return ret;
+	req.tc.tcm_parent = parent;
+
+	if (!flush) {
+		ret = nlattr_add(&req.nh, sizeof(req), TCA_KIND,
+				 "bpf", sizeof("bpf"));
+		if (ret < 0)
+			return ret;
+	}
+
+	return libbpf_netlink_send_recv(&req.nh, NULL, NULL, NULL);
+}
+
+int bpf_tc_detach(const struct bpf_tc_hook *hook,
+		  const struct bpf_tc_opts *opts)
+{
+	int ret;
+
+	if (!opts)
+		return libbpf_err(-EINVAL);
+
+	ret = __bpf_tc_detach(hook, opts, false);
+	return libbpf_err(ret);
+}
+
+int bpf_tc_query(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts)
+{
+	__u32 protocol, handle, priority, parent, prog_id, flags;
+	int ret, ifindex, attach_point, prog_fd;
+	struct bpf_cb_ctx info = {};
+	struct {
+		struct nlmsghdr nh;
+		struct tcmsg tc;
+		char buf[256];
+	} req;
+
+	if (!hook || !opts ||
+	    !OPTS_VALID(hook, bpf_tc_hook) ||
+	    !OPTS_VALID(opts, bpf_tc_opts))
+		return libbpf_err(-EINVAL);
+
+	ifindex      = OPTS_GET(hook, ifindex, 0);
+	parent       = OPTS_GET(hook, parent, 0);
+	attach_point = OPTS_GET(hook, attach_point, 0);
+
+	handle       = OPTS_GET(opts, handle, 0);
+	priority     = OPTS_GET(opts, priority, 0);
+	prog_fd      = OPTS_GET(opts, prog_fd, 0);
+	prog_id      = OPTS_GET(opts, prog_id, 0);
+	flags        = OPTS_GET(opts, flags, 0);
+
+	if (ifindex <= 0 || flags || prog_fd || prog_id ||
+	    !handle || !priority)
+		return libbpf_err(-EINVAL);
+	if (priority > UINT16_MAX)
+		return libbpf_err(-EINVAL);
+
+	protocol = ETH_P_ALL;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len   = NLMSG_LENGTH(sizeof(struct tcmsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST;
+	req.nh.nlmsg_type  = RTM_GETTFILTER;
+	req.tc.tcm_family  = AF_UNSPEC;
+	req.tc.tcm_ifindex = ifindex;
+	req.tc.tcm_handle  = handle;
+	req.tc.tcm_info    = TC_H_MAKE(priority << 16, htons(protocol));
+
+	ret = tc_get_tcm_parent(attach_point, &parent);
+	if (ret < 0)
+		return libbpf_err(ret);
+	req.tc.tcm_parent = parent;
+
+	ret = nlattr_add(&req.nh, sizeof(req), TCA_KIND, "bpf", sizeof("bpf"));
+	if (ret < 0)
+		return libbpf_err(ret);
+
+	info.opts = opts;
+
+	ret = libbpf_netlink_send_recv(&req.nh, get_tc_info, NULL, &info);
+	if (ret < 0)
+		return libbpf_err(ret);
+	if (!info.processed)
+		return libbpf_err(-ENOENT);
+	return ret;
 }
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
index 6cc3ac91690f..3c780ab6d022 100644
--- a/tools/lib/bpf/nlattr.h
+++ b/tools/lib/bpf/nlattr.h
@@ -10,7 +10,10 @@
 #define __LIBBPF_NLATTR_H
 
 #include <stdint.h>
+#include <string.h>
+#include <errno.h>
 #include <linux/netlink.h>
+
 /* avoid multiple definition of netlink features */
 #define __LINUX_NETLINK_H
 
@@ -103,4 +106,49 @@ int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype,
 
 int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh);
 
+static inline struct nlattr *nla_data(struct nlattr *nla)
+{
+	return (struct nlattr *)((char *)nla + NLA_HDRLEN);
+}
+
+static inline struct nlattr *nh_tail(struct nlmsghdr *nh)
+{
+	return (struct nlattr *)((char *)nh + NLMSG_ALIGN(nh->nlmsg_len));
+}
+
+static inline int nlattr_add(struct nlmsghdr *nh, size_t maxsz, int type,
+			     const void *data, int len)
+{
+	struct nlattr *nla;
+
+	if (NLMSG_ALIGN(nh->nlmsg_len) + NLA_ALIGN(NLA_HDRLEN + len) > maxsz)
+		return -EMSGSIZE;
+	if (!!data != !!len)
+		return -EINVAL;
+
+	nla = nh_tail(nh);
+	nla->nla_type = type;
+	nla->nla_len = NLA_HDRLEN + len;
+	if (data)
+		memcpy(nla_data(nla), data, len);
+	nh->nlmsg_len = NLMSG_ALIGN(nh->nlmsg_len) + NLA_ALIGN(nla->nla_len);
+	return 0;
+}
+
+static inline struct nlattr *nlattr_begin_nested(struct nlmsghdr *nh,
+						 size_t maxsz, int type)
+{
+	struct nlattr *tail;
+
+	tail = nh_tail(nh);
+	if (nlattr_add(nh, maxsz, type | NLA_F_NESTED, NULL, 0))
+		return NULL;
+	return tail;
+}
+
+static inline void nlattr_end_nested(struct nlmsghdr *nh, struct nlattr *tail)
+{
+	tail->nla_len = (char *)nh_tail(nh) - (char *)tail;
+}
+
 #endif /* __LIBBPF_NLATTR_H */
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 1d80ad4e0de8..8bc117bcc7bc 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -69,23 +69,23 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 		err = -errno;
 		pr_warn("ringbuf: failed to get map info for fd=%d: %d\n",
 			map_fd, err);
-		return err;
+		return libbpf_err(err);
 	}
 
 	if (info.type != BPF_MAP_TYPE_RINGBUF) {
 		pr_warn("ringbuf: map fd=%d is not BPF_MAP_TYPE_RINGBUF\n",
 			map_fd);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	tmp = libbpf_reallocarray(rb->rings, rb->ring_cnt + 1, sizeof(*rb->rings));
 	if (!tmp)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 	rb->rings = tmp;
 
 	tmp = libbpf_reallocarray(rb->events, rb->ring_cnt + 1, sizeof(*rb->events));
 	if (!tmp)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 	rb->events = tmp;
 
 	r = &rb->rings[rb->ring_cnt];
@@ -103,7 +103,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 		err = -errno;
 		pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
 			map_fd, err);
-		return err;
+		return libbpf_err(err);
 	}
 	r->consumer_pos = tmp;
 
@@ -118,7 +118,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 		ringbuf_unmap_ring(rb, r);
 		pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %d\n",
 			map_fd, err);
-		return err;
+		return libbpf_err(err);
 	}
 	r->producer_pos = tmp;
 	r->data = tmp + rb->page_size;
@@ -133,7 +133,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 		ringbuf_unmap_ring(rb, r);
 		pr_warn("ringbuf: failed to epoll add map fd=%d: %d\n",
 			map_fd, err);
-		return err;
+		return libbpf_err(err);
 	}
 
 	rb->ring_cnt++;
@@ -165,11 +165,11 @@ ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx,
 	int err;
 
 	if (!OPTS_VALID(opts, ring_buffer_opts))
-		return NULL;
+		return errno = EINVAL, NULL;
 
 	rb = calloc(1, sizeof(*rb));
 	if (!rb)
-		return NULL;
+		return errno = ENOMEM, NULL;
 
 	rb->page_size = getpagesize();
 
@@ -188,7 +188,7 @@ ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx,
 
 err_out:
 	ring_buffer__free(rb);
-	return NULL;
+	return errno = -err, NULL;
 }
 
 static inline int roundup_len(__u32 len)
@@ -260,7 +260,7 @@ int ring_buffer__consume(struct ring_buffer *rb)
 
 		err = ringbuf_process_ring(ring);
 		if (err < 0)
-			return err;
+			return libbpf_err(err);
 		res += err;
 	}
 	if (res > INT_MAX)
@@ -279,7 +279,7 @@ int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms)
 
 	cnt = epoll_wait(rb->epoll_fd, rb->events, rb->ring_cnt, timeout_ms);
 	if (cnt < 0)
-		return -errno;
+		return libbpf_err(-errno);
 
 	for (i = 0; i < cnt; i++) {
 		__u32 ring_id = rb->events[i].data.fd;
@@ -287,7 +287,7 @@ int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms)
 
 		err = ringbuf_process_ring(ring);
 		if (err < 0)
-			return err;
+			return libbpf_err(err);
 		res += err;
 	}
 	if (res > INT_MAX)
diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h
new file mode 100644
index 000000000000..b22b50c1b173
--- /dev/null
+++ b/tools/lib/bpf/skel_internal.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/* Copyright (c) 2021 Facebook */
+#ifndef __SKEL_INTERNAL_H
+#define __SKEL_INTERNAL_H
+
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/mman.h>
+
+/* This file is a base header for auto-generated *.lskel.h files.
+ * Its contents will change and may become part of auto-generation in the future.
+ *
+ * The layout of bpf_[map|prog]_desc and bpf_loader_ctx is feature dependent
+ * and will change from one version of libbpf to another and features
+ * requested during loader program generation.
+ */
+struct bpf_map_desc {
+	union {
+		/* input for the loader prog */
+		struct {
+			__aligned_u64 initial_value;
+			__u32 max_entries;
+		};
+		/* output of the loader prog */
+		struct {
+			int map_fd;
+		};
+	};
+};
+struct bpf_prog_desc {
+	int prog_fd;
+};
+
+struct bpf_loader_ctx {
+	size_t sz;
+	__u32 log_level;
+	__u32 log_size;
+	__u64 log_buf;
+};
+
+struct bpf_load_and_run_opts {
+	struct bpf_loader_ctx *ctx;
+	const void *data;
+	const void *insns;
+	__u32 data_sz;
+	__u32 insns_sz;
+	const char *errstr;
+};
+
+static inline int skel_sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
+			  unsigned int size)
+{
+	return syscall(__NR_bpf, cmd, attr, size);
+}
+
+static inline int skel_closenz(int fd)
+{
+	if (fd > 0)
+		return close(fd);
+	return -EINVAL;
+}
+
+static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
+{
+	int map_fd = -1, prog_fd = -1, key = 0, err;
+	union bpf_attr attr;
+
+	map_fd = bpf_create_map_name(BPF_MAP_TYPE_ARRAY, "__loader.map", 4,
+				     opts->data_sz, 1, 0);
+	if (map_fd < 0) {
+		opts->errstr = "failed to create loader map";
+		err = -errno;
+		goto out;
+	}
+
+	err = bpf_map_update_elem(map_fd, &key, opts->data, 0);
+	if (err < 0) {
+		opts->errstr = "failed to update loader map";
+		err = -errno;
+		goto out;
+	}
+
+	memset(&attr, 0, sizeof(attr));
+	attr.prog_type = BPF_PROG_TYPE_SYSCALL;
+	attr.insns = (long) opts->insns;
+	attr.insn_cnt = opts->insns_sz / sizeof(struct bpf_insn);
+	attr.license = (long) "Dual BSD/GPL";
+	memcpy(attr.prog_name, "__loader.prog", sizeof("__loader.prog"));
+	attr.fd_array = (long) &map_fd;
+	attr.log_level = opts->ctx->log_level;
+	attr.log_size = opts->ctx->log_size;
+	attr.log_buf = opts->ctx->log_buf;
+	attr.prog_flags = BPF_F_SLEEPABLE;
+	prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+	if (prog_fd < 0) {
+		opts->errstr = "failed to load loader prog";
+		err = -errno;
+		goto out;
+	}
+
+	memset(&attr, 0, sizeof(attr));
+	attr.test.prog_fd = prog_fd;
+	attr.test.ctx_in = (long) opts->ctx;
+	attr.test.ctx_size_in = opts->ctx->sz;
+	err = skel_sys_bpf(BPF_PROG_RUN, &attr, sizeof(attr));
+	if (err < 0 || (int)attr.test.retval < 0) {
+		opts->errstr = "failed to execute loader prog";
+		if (err < 0)
+			err = -errno;
+		else
+			err = (int)attr.test.retval;
+		goto out;
+	}
+	err = 0;
+out:
+	if (map_fd >= 0)
+		close(map_fd);
+	if (prog_fd >= 0)
+		close(prog_fd);
+	return err;
+}
+
+#endif
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 4866f6a21901..addcfd8b615e 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -10,6 +10,7 @@ FEATURE-DUMP.libbpf
 fixdep
 test_dev_cgroup
 /test_progs*
+!test_progs.h
 test_verifier_log
 feature
 test_sock
@@ -30,10 +31,13 @@ test_sysctl
 xdping
 test_cpp
 *.skel.h
+*.lskel.h
 /no_alu32
 /bpf_gcc
 /tools
 /runqslower
 /bench
 *.ko
+*.tmp
 xdpxceiver
+xdp_redirect_multi
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 511259c2c6c5..f405b20c1e6c 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -54,6 +54,7 @@ TEST_FILES = xsk_prereqs.sh \
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
 	test_xdp_redirect.sh \
+	test_xdp_redirect_multi.sh \
 	test_xdp_meta.sh \
 	test_xdp_veth.sh \
 	test_offload.py \
@@ -84,7 +85,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \
 TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
 	flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
 	test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
-	xdpxceiver
+	xdpxceiver xdp_redirect_multi
 
 TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read
 
@@ -312,6 +313,10 @@ SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c
 LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h		\
 		linked_vars.skel.h linked_maps.skel.h
 
+LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \
+	test_ksyms_module.c test_ringbuf.c atomics.c trace_printk.c
+SKEL_BLACKLIST += $$(LSKELS)
+
 test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o
 linked_funcs.skel.h-deps := linked_funcs1.o linked_funcs2.o
 linked_vars.skel.h-deps := linked_vars1.o linked_vars2.o
@@ -339,6 +344,7 @@ TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS)
 TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h,	\
 				 $$(filter-out $(SKEL_BLACKLIST) $(LINKED_BPF_SRCS),\
 					       $$(TRUNNER_BPF_SRCS)))
+TRUNNER_BPF_LSKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.lskel.h, $$(LSKELS))
 TRUNNER_BPF_SKELS_LINKED := $$(addprefix $$(TRUNNER_OUTPUT)/,$(LINKED_SKELS))
 TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS)
 
@@ -380,6 +386,14 @@ $(TRUNNER_BPF_SKELS): %.skel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$(Q)diff $$(<:.o=.linked2.o) $$(<:.o=.linked3.o)
 	$(Q)$$(BPFTOOL) gen skeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$@
 
+$(TRUNNER_BPF_LSKELS): %.lskel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
+	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
+	$(Q)$$(BPFTOOL) gen object $$(<:.o=.linked1.o) $$<
+	$(Q)$$(BPFTOOL) gen object $$(<:.o=.linked2.o) $$(<:.o=.linked1.o)
+	$(Q)$$(BPFTOOL) gen object $$(<:.o=.linked3.o) $$(<:.o=.linked2.o)
+	$(Q)diff $$(<:.o=.linked2.o) $$(<:.o=.linked3.o)
+	$(Q)$$(BPFTOOL) gen skeleton -L $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$@
+
 $(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_BPF_OBJS) $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$$(call msg,LINK-BPF,$(TRUNNER_BINARY),$$(@:.skel.h=.o))
 	$(Q)$$(BPFTOOL) gen object $$(@:.skel.h=.linked1.o) $$(addprefix $(TRUNNER_OUTPUT)/,$$($$(@F)-deps))
@@ -409,6 +423,7 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o:			\
 		      $(TRUNNER_EXTRA_HDRS)				\
 		      $(TRUNNER_BPF_OBJS)				\
 		      $(TRUNNER_BPF_SKELS)				\
+		      $(TRUNNER_BPF_LSKELS)				\
 		      $(TRUNNER_BPF_SKELS_LINKED)			\
 		      $$(BPFOBJ) | $(TRUNNER_OUTPUT)
 	$$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@)
@@ -516,6 +531,6 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \
 EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR)	\
 	prog_tests/tests.h map_tests/tests.h verifier/tests.h		\
 	feature								\
-	$(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32 bpf_gcc bpf_testmod.ko)
+	$(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h no_alu32 bpf_gcc bpf_testmod.ko)
 
 .PHONY: docs docs-clean
diff --git a/tools/testing/selftests/bpf/Makefile.docs b/tools/testing/selftests/bpf/Makefile.docs
index ccf260021e83..eb6a4fea8c79 100644
--- a/tools/testing/selftests/bpf/Makefile.docs
+++ b/tools/testing/selftests/bpf/Makefile.docs
@@ -52,7 +52,8 @@ $(OUTPUT)%.$2: $(OUTPUT)%.rst
 ifndef RST2MAN_DEP
 	$$(error "rst2man not found, but required to generate man pages")
 endif
-	$$(QUIET_GEN)rst2man $$< > $$@
+	$$(QUIET_GEN)rst2man --exit-status=1 $$< > $$@.tmp
+	$$(QUIET_GEN)mv $$@.tmp $$@
 
 docs-clean-$1:
 	$$(call QUIET_CLEAN, eBPF_$1-manpage)
diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index 3353778c30f8..8deec1ca9150 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -202,3 +202,22 @@ generate valid BTF information for weak variables. Please make sure you use
 Clang that contains the fix.
 
 __ https://reviews.llvm.org/D100362
+
+Clang relocation changes
+========================
+
+Clang 13 patch `clang reloc patch`_  made some changes on relocations such
+that existing relocation types are broken into more types and
+each new type corresponds to only one way to resolve relocation.
+See `kernel llvm reloc`_ for more explanation and some examples.
+Using clang 13 to compile old libbpf which has static linker support,
+there will be a compilation failure::
+
+  libbpf: ELF relo #0 in section #6 has unexpected type 2 in .../bpf_tcp_nogpl.o
+
+Here, ``type 2`` refers to new relocation type ``R_BPF_64_ABS64``.
+To fix this issue, user newer libbpf.
+
+.. Links
+.. _clang reloc patch: https://reviews.llvm.org/D102712
+.. _kernel llvm reloc: /Documentation/bpf/llvm_reloc.rst
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index 332ed2f7b402..6ea15b93a2f8 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -43,6 +43,7 @@ void setup_libbpf()
 {
 	int err;
 
+	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
 	libbpf_set_print(libbpf_print_fn);
 
 	err = bump_memlock_rlimit();
diff --git a/tools/testing/selftests/bpf/benchs/bench_rename.c b/tools/testing/selftests/bpf/benchs/bench_rename.c
index a967674098ad..c7ec114eca56 100644
--- a/tools/testing/selftests/bpf/benchs/bench_rename.c
+++ b/tools/testing/selftests/bpf/benchs/bench_rename.c
@@ -65,7 +65,7 @@ static void attach_bpf(struct bpf_program *prog)
 	struct bpf_link *link;
 
 	link = bpf_program__attach(prog);
-	if (IS_ERR(link)) {
+	if (!link) {
 		fprintf(stderr, "failed to attach program!\n");
 		exit(1);
 	}
diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
index bde6c9d4cbd4..d167bffac679 100644
--- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
+++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
@@ -181,7 +181,7 @@ static void ringbuf_libbpf_setup()
 	}
 
 	link = bpf_program__attach(ctx->skel->progs.bench_ringbuf);
-	if (IS_ERR(link)) {
+	if (!link) {
 		fprintf(stderr, "failed to attach program!\n");
 		exit(1);
 	}
@@ -271,7 +271,7 @@ static void ringbuf_custom_setup()
 	}
 
 	link = bpf_program__attach(ctx->skel->progs.bench_ringbuf);
-	if (IS_ERR(link)) {
+	if (!link) {
 		fprintf(stderr, "failed to attach program\n");
 		exit(1);
 	}
@@ -430,7 +430,7 @@ static void perfbuf_libbpf_setup()
 	}
 
 	link = bpf_program__attach(ctx->skel->progs.bench_perfbuf);
-	if (IS_ERR(link)) {
+	if (!link) {
 		fprintf(stderr, "failed to attach program\n");
 		exit(1);
 	}
diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
index 2a0b6c9885a4..f41a491a8cc0 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -60,7 +60,7 @@ static void attach_bpf(struct bpf_program *prog)
 	struct bpf_link *link;
 
 	link = bpf_program__attach(prog);
-	if (IS_ERR(link)) {
+	if (!link) {
 		fprintf(stderr, "failed to attach program!\n");
 		exit(1);
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c
index 21efe7bbf10d..ba0e1efe5a45 100644
--- a/tools/testing/selftests/bpf/prog_tests/atomics.c
+++ b/tools/testing/selftests/bpf/prog_tests/atomics.c
@@ -2,19 +2,19 @@
 
 #include <test_progs.h>
 
-#include "atomics.skel.h"
+#include "atomics.lskel.h"
 
 static void test_add(struct atomics *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
-	struct bpf_link *link;
+	int link_fd;
 
-	link = bpf_program__attach(skel->progs.add);
-	if (CHECK(IS_ERR(link), "attach(add)", "err: %ld\n", PTR_ERR(link)))
+	link_fd = atomics__add__attach(skel);
+	if (!ASSERT_GT(link_fd, 0, "attach(add)"))
 		return;
 
-	prog_fd = bpf_program__fd(skel->progs.add);
+	prog_fd = skel->progs.add.prog_fd;
 	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
 	if (CHECK(err || retval, "test_run add",
@@ -33,20 +33,20 @@ static void test_add(struct atomics *skel)
 	ASSERT_EQ(skel->data->add_noreturn_value, 3, "add_noreturn_value");
 
 cleanup:
-	bpf_link__destroy(link);
+	close(link_fd);
 }
 
 static void test_sub(struct atomics *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
-	struct bpf_link *link;
+	int link_fd;
 
-	link = bpf_program__attach(skel->progs.sub);
-	if (CHECK(IS_ERR(link), "attach(sub)", "err: %ld\n", PTR_ERR(link)))
+	link_fd = atomics__sub__attach(skel);
+	if (!ASSERT_GT(link_fd, 0, "attach(sub)"))
 		return;
 
-	prog_fd = bpf_program__fd(skel->progs.sub);
+	prog_fd = skel->progs.sub.prog_fd;
 	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
 	if (CHECK(err || retval, "test_run sub",
@@ -66,20 +66,20 @@ static void test_sub(struct atomics *skel)
 	ASSERT_EQ(skel->data->sub_noreturn_value, -1, "sub_noreturn_value");
 
 cleanup:
-	bpf_link__destroy(link);
+	close(link_fd);
 }
 
 static void test_and(struct atomics *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
-	struct bpf_link *link;
+	int link_fd;
 
-	link = bpf_program__attach(skel->progs.and);
-	if (CHECK(IS_ERR(link), "attach(and)", "err: %ld\n", PTR_ERR(link)))
+	link_fd = atomics__and__attach(skel);
+	if (!ASSERT_GT(link_fd, 0, "attach(and)"))
 		return;
 
-	prog_fd = bpf_program__fd(skel->progs.and);
+	prog_fd = skel->progs.and.prog_fd;
 	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
 	if (CHECK(err || retval, "test_run and",
@@ -94,20 +94,20 @@ static void test_and(struct atomics *skel)
 
 	ASSERT_EQ(skel->data->and_noreturn_value, 0x010ull << 32, "and_noreturn_value");
 cleanup:
-	bpf_link__destroy(link);
+	close(link_fd);
 }
 
 static void test_or(struct atomics *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
-	struct bpf_link *link;
+	int link_fd;
 
-	link = bpf_program__attach(skel->progs.or);
-	if (CHECK(IS_ERR(link), "attach(or)", "err: %ld\n", PTR_ERR(link)))
+	link_fd = atomics__or__attach(skel);
+	if (!ASSERT_GT(link_fd, 0, "attach(or)"))
 		return;
 
-	prog_fd = bpf_program__fd(skel->progs.or);
+	prog_fd = skel->progs.or.prog_fd;
 	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
 	if (CHECK(err || retval, "test_run or",
@@ -123,20 +123,20 @@ static void test_or(struct atomics *skel)
 
 	ASSERT_EQ(skel->data->or_noreturn_value, 0x111ull << 32, "or_noreturn_value");
 cleanup:
-	bpf_link__destroy(link);
+	close(link_fd);
 }
 
 static void test_xor(struct atomics *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
-	struct bpf_link *link;
+	int link_fd;
 
-	link = bpf_program__attach(skel->progs.xor);
-	if (CHECK(IS_ERR(link), "attach(xor)", "err: %ld\n", PTR_ERR(link)))
+	link_fd = atomics__xor__attach(skel);
+	if (!ASSERT_GT(link_fd, 0, "attach(xor)"))
 		return;
 
-	prog_fd = bpf_program__fd(skel->progs.xor);
+	prog_fd = skel->progs.xor.prog_fd;
 	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
 	if (CHECK(err || retval, "test_run xor",
@@ -151,20 +151,20 @@ static void test_xor(struct atomics *skel)
 
 	ASSERT_EQ(skel->data->xor_noreturn_value, 0x101ull << 32, "xor_nxoreturn_value");
 cleanup:
-	bpf_link__destroy(link);
+	close(link_fd);
 }
 
 static void test_cmpxchg(struct atomics *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
-	struct bpf_link *link;
+	int link_fd;
 
-	link = bpf_program__attach(skel->progs.cmpxchg);
-	if (CHECK(IS_ERR(link), "attach(cmpxchg)", "err: %ld\n", PTR_ERR(link)))
+	link_fd = atomics__cmpxchg__attach(skel);
+	if (!ASSERT_GT(link_fd, 0, "attach(cmpxchg)"))
 		return;
 
-	prog_fd = bpf_program__fd(skel->progs.cmpxchg);
+	prog_fd = skel->progs.cmpxchg.prog_fd;
 	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
 	if (CHECK(err || retval, "test_run add",
@@ -180,20 +180,20 @@ static void test_cmpxchg(struct atomics *skel)
 	ASSERT_EQ(skel->bss->cmpxchg32_result_succeed, 1, "cmpxchg_result_succeed");
 
 cleanup:
-	bpf_link__destroy(link);
+	close(link_fd);
 }
 
 static void test_xchg(struct atomics *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
-	struct bpf_link *link;
+	int link_fd;
 
-	link = bpf_program__attach(skel->progs.xchg);
-	if (CHECK(IS_ERR(link), "attach(xchg)", "err: %ld\n", PTR_ERR(link)))
+	link_fd = atomics__xchg__attach(skel);
+	if (!ASSERT_GT(link_fd, 0, "attach(xchg)"))
 		return;
 
-	prog_fd = bpf_program__fd(skel->progs.xchg);
+	prog_fd = skel->progs.xchg.prog_fd;
 	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
 	if (CHECK(err || retval, "test_run add",
@@ -207,7 +207,7 @@ static void test_xchg(struct atomics *skel)
 	ASSERT_EQ(skel->bss->xchg32_result, 1, "xchg32_result");
 
 cleanup:
-	bpf_link__destroy(link);
+	close(link_fd);
 }
 
 void test_atomics(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index 9dc4e3dfbcf3..ec11e20d2b92 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -85,16 +85,14 @@ void test_attach_probe(void)
 	kprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kprobe,
 						 false /* retprobe */,
 						 SYS_NANOSLEEP_KPROBE_NAME);
-	if (CHECK(IS_ERR(kprobe_link), "attach_kprobe",
-		  "err %ld\n", PTR_ERR(kprobe_link)))
+	if (!ASSERT_OK_PTR(kprobe_link, "attach_kprobe"))
 		goto cleanup;
 	skel->links.handle_kprobe = kprobe_link;
 
 	kretprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kretprobe,
 						    true /* retprobe */,
 						    SYS_NANOSLEEP_KPROBE_NAME);
-	if (CHECK(IS_ERR(kretprobe_link), "attach_kretprobe",
-		  "err %ld\n", PTR_ERR(kretprobe_link)))
+	if (!ASSERT_OK_PTR(kretprobe_link, "attach_kretprobe"))
 		goto cleanup;
 	skel->links.handle_kretprobe = kretprobe_link;
 
@@ -103,8 +101,7 @@ void test_attach_probe(void)
 						 0 /* self pid */,
 						 "/proc/self/exe",
 						 uprobe_offset);
-	if (CHECK(IS_ERR(uprobe_link), "attach_uprobe",
-		  "err %ld\n", PTR_ERR(uprobe_link)))
+	if (!ASSERT_OK_PTR(uprobe_link, "attach_uprobe"))
 		goto cleanup;
 	skel->links.handle_uprobe = uprobe_link;
 
@@ -113,8 +110,7 @@ void test_attach_probe(void)
 						    -1 /* any pid */,
 						    "/proc/self/exe",
 						    uprobe_offset);
-	if (CHECK(IS_ERR(uretprobe_link), "attach_uretprobe",
-		  "err %ld\n", PTR_ERR(uretprobe_link)))
+	if (!ASSERT_OK_PTR(uretprobe_link, "attach_uretprobe"))
 		goto cleanup;
 	skel->links.handle_uretprobe = uretprobe_link;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 2d3590cfb5e1..1f1aade56504 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -47,7 +47,7 @@ static void do_dummy_read(struct bpf_program *prog)
 	int iter_fd, len;
 
 	link = bpf_program__attach_iter(prog, NULL);
-	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+	if (!ASSERT_OK_PTR(link, "attach_iter"))
 		return;
 
 	iter_fd = bpf_iter_create(bpf_link__fd(link));
@@ -201,7 +201,7 @@ static int do_btf_read(struct bpf_iter_task_btf *skel)
 	int ret = 0;
 
 	link = bpf_program__attach_iter(prog, NULL);
-	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+	if (!ASSERT_OK_PTR(link, "attach_iter"))
 		return ret;
 
 	iter_fd = bpf_iter_create(bpf_link__fd(link));
@@ -396,7 +396,7 @@ static void test_file_iter(void)
 		return;
 
 	link = bpf_program__attach_iter(skel1->progs.dump_task, NULL);
-	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+	if (!ASSERT_OK_PTR(link, "attach_iter"))
 		goto out;
 
 	/* unlink this path if it exists. */
@@ -502,7 +502,7 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 	skel->bss->map2_id = map_info.id;
 
 	link = bpf_program__attach_iter(skel->progs.dump_bpf_map, NULL);
-	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+	if (!ASSERT_OK_PTR(link, "attach_iter"))
 		goto free_map2;
 
 	iter_fd = bpf_iter_create(bpf_link__fd(link));
@@ -607,14 +607,12 @@ static void test_bpf_hash_map(void)
 	opts.link_info = &linfo;
 	opts.link_info_len = sizeof(linfo);
 	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
-	if (CHECK(!IS_ERR(link), "attach_iter",
-		  "attach_iter for hashmap2 unexpected succeeded\n"))
+	if (!ASSERT_ERR_PTR(link, "attach_iter"))
 		goto out;
 
 	linfo.map.map_fd = bpf_map__fd(skel->maps.hashmap3);
 	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
-	if (CHECK(!IS_ERR(link), "attach_iter",
-		  "attach_iter for hashmap3 unexpected succeeded\n"))
+	if (!ASSERT_ERR_PTR(link, "attach_iter"))
 		goto out;
 
 	/* hashmap1 should be good, update map values here */
@@ -636,7 +634,7 @@ static void test_bpf_hash_map(void)
 
 	linfo.map.map_fd = map_fd;
 	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
-	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+	if (!ASSERT_OK_PTR(link, "attach_iter"))
 		goto out;
 
 	iter_fd = bpf_iter_create(bpf_link__fd(link));
@@ -727,7 +725,7 @@ static void test_bpf_percpu_hash_map(void)
 	opts.link_info = &linfo;
 	opts.link_info_len = sizeof(linfo);
 	link = bpf_program__attach_iter(skel->progs.dump_bpf_percpu_hash_map, &opts);
-	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+	if (!ASSERT_OK_PTR(link, "attach_iter"))
 		goto out;
 
 	iter_fd = bpf_iter_create(bpf_link__fd(link));
@@ -798,7 +796,7 @@ static void test_bpf_array_map(void)
 	opts.link_info = &linfo;
 	opts.link_info_len = sizeof(linfo);
 	link = bpf_program__attach_iter(skel->progs.dump_bpf_array_map, &opts);
-	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+	if (!ASSERT_OK_PTR(link, "attach_iter"))
 		goto out;
 
 	iter_fd = bpf_iter_create(bpf_link__fd(link));
@@ -894,7 +892,7 @@ static void test_bpf_percpu_array_map(void)
 	opts.link_info = &linfo;
 	opts.link_info_len = sizeof(linfo);
 	link = bpf_program__attach_iter(skel->progs.dump_bpf_percpu_array_map, &opts);
-	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+	if (!ASSERT_OK_PTR(link, "attach_iter"))
 		goto out;
 
 	iter_fd = bpf_iter_create(bpf_link__fd(link));
@@ -957,7 +955,7 @@ static void test_bpf_sk_storage_delete(void)
 	opts.link_info_len = sizeof(linfo);
 	link = bpf_program__attach_iter(skel->progs.delete_bpf_sk_storage_map,
 					&opts);
-	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+	if (!ASSERT_OK_PTR(link, "attach_iter"))
 		goto out;
 
 	iter_fd = bpf_iter_create(bpf_link__fd(link));
@@ -1075,7 +1073,7 @@ static void test_bpf_sk_storage_map(void)
 	opts.link_info = &linfo;
 	opts.link_info_len = sizeof(linfo);
 	link = bpf_program__attach_iter(skel->progs.dump_bpf_sk_storage_map, &opts);
-	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+	if (!ASSERT_OK_PTR(link, "attach_iter"))
 		goto out;
 
 	iter_fd = bpf_iter_create(bpf_link__fd(link));
@@ -1128,7 +1126,7 @@ static void test_rdonly_buf_out_of_bound(void)
 	opts.link_info = &linfo;
 	opts.link_info_len = sizeof(linfo);
 	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
-	if (CHECK(!IS_ERR(link), "attach_iter", "unexpected success\n"))
+	if (!ASSERT_ERR_PTR(link, "attach_iter"))
 		bpf_link__destroy(link);
 
 	bpf_iter_test_kern5__destroy(skel);
@@ -1186,8 +1184,7 @@ static void test_task_vma(void)
 	skel->links.proc_maps = bpf_program__attach_iter(
 		skel->progs.proc_maps, NULL);
 
-	if (CHECK(IS_ERR(skel->links.proc_maps), "bpf_program__attach_iter",
-		  "attach iterator failed\n")) {
+	if (!ASSERT_OK_PTR(skel->links.proc_maps, "bpf_program__attach_iter")) {
 		skel->links.proc_maps = NULL;
 		goto out;
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index e25917f04602..efe1e979affb 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -82,7 +82,7 @@ static void *server(void *arg)
 	      bytes, total_bytes, nr_sent, errno);
 
 done:
-	if (fd != -1)
+	if (fd >= 0)
 		close(fd);
 	if (err) {
 		WRITE_ONCE(stop, 1);
@@ -191,8 +191,7 @@ static void test_cubic(void)
 		return;
 
 	link = bpf_map__attach_struct_ops(cubic_skel->maps.cubic);
-	if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n",
-		  PTR_ERR(link))) {
+	if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops")) {
 		bpf_cubic__destroy(cubic_skel);
 		return;
 	}
@@ -213,8 +212,7 @@ static void test_dctcp(void)
 		return;
 
 	link = bpf_map__attach_struct_ops(dctcp_skel->maps.dctcp);
-	if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n",
-		  PTR_ERR(link))) {
+	if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops")) {
 		bpf_dctcp__destroy(dctcp_skel);
 		return;
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 0457ae32b270..857e3f26086f 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -3811,7 +3811,7 @@ static void do_test_raw(unsigned int test_num)
 			      always_log);
 	free(raw_btf);
 
-	err = ((btf_fd == -1) != test->btf_load_err);
+	err = ((btf_fd < 0) != test->btf_load_err);
 	if (CHECK(err, "btf_fd:%d test->btf_load_err:%u",
 		  btf_fd, test->btf_load_err) ||
 	    CHECK(test->err_str && !strstr(btf_log_buf, test->err_str),
@@ -3820,7 +3820,7 @@ static void do_test_raw(unsigned int test_num)
 		goto done;
 	}
 
-	if (err || btf_fd == -1)
+	if (err || btf_fd < 0)
 		goto done;
 
 	create_attr.name = test->map_name;
@@ -3834,16 +3834,16 @@ static void do_test_raw(unsigned int test_num)
 
 	map_fd = bpf_create_map_xattr(&create_attr);
 
-	err = ((map_fd == -1) != test->map_create_err);
+	err = ((map_fd < 0) != test->map_create_err);
 	CHECK(err, "map_fd:%d test->map_create_err:%u",
 	      map_fd, test->map_create_err);
 
 done:
 	if (*btf_log_buf && (err || always_log))
 		fprintf(stderr, "\n%s", btf_log_buf);
-	if (btf_fd != -1)
+	if (btf_fd >= 0)
 		close(btf_fd);
-	if (map_fd != -1)
+	if (map_fd >= 0)
 		close(map_fd);
 }
 
@@ -3941,7 +3941,7 @@ static int test_big_btf_info(unsigned int test_num)
 	btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
 			      btf_log_buf, BTF_LOG_BUF_SIZE,
 			      always_log);
-	if (CHECK(btf_fd == -1, "errno:%d", errno)) {
+	if (CHECK(btf_fd < 0, "errno:%d", errno)) {
 		err = -1;
 		goto done;
 	}
@@ -3987,7 +3987,7 @@ done:
 	free(raw_btf);
 	free(user_btf);
 
-	if (btf_fd != -1)
+	if (btf_fd >= 0)
 		close(btf_fd);
 
 	return err;
@@ -4029,7 +4029,7 @@ static int test_btf_id(unsigned int test_num)
 	btf_fd[0] = bpf_load_btf(raw_btf, raw_btf_size,
 				 btf_log_buf, BTF_LOG_BUF_SIZE,
 				 always_log);
-	if (CHECK(btf_fd[0] == -1, "errno:%d", errno)) {
+	if (CHECK(btf_fd[0] < 0, "errno:%d", errno)) {
 		err = -1;
 		goto done;
 	}
@@ -4043,7 +4043,7 @@ static int test_btf_id(unsigned int test_num)
 	}
 
 	btf_fd[1] = bpf_btf_get_fd_by_id(info[0].id);
-	if (CHECK(btf_fd[1] == -1, "errno:%d", errno)) {
+	if (CHECK(btf_fd[1] < 0, "errno:%d", errno)) {
 		err = -1;
 		goto done;
 	}
@@ -4071,7 +4071,7 @@ static int test_btf_id(unsigned int test_num)
 	create_attr.btf_value_type_id = 2;
 
 	map_fd = bpf_create_map_xattr(&create_attr);
-	if (CHECK(map_fd == -1, "errno:%d", errno)) {
+	if (CHECK(map_fd < 0, "errno:%d", errno)) {
 		err = -1;
 		goto done;
 	}
@@ -4094,7 +4094,7 @@ static int test_btf_id(unsigned int test_num)
 
 	/* Test BTF ID is removed from the kernel */
 	btf_fd[0] = bpf_btf_get_fd_by_id(map_info.btf_id);
-	if (CHECK(btf_fd[0] == -1, "errno:%d", errno)) {
+	if (CHECK(btf_fd[0] < 0, "errno:%d", errno)) {
 		err = -1;
 		goto done;
 	}
@@ -4105,7 +4105,7 @@ static int test_btf_id(unsigned int test_num)
 	close(map_fd);
 	map_fd = -1;
 	btf_fd[0] = bpf_btf_get_fd_by_id(map_info.btf_id);
-	if (CHECK(btf_fd[0] != -1, "BTF lingers")) {
+	if (CHECK(btf_fd[0] >= 0, "BTF lingers")) {
 		err = -1;
 		goto done;
 	}
@@ -4117,11 +4117,11 @@ done:
 		fprintf(stderr, "\n%s", btf_log_buf);
 
 	free(raw_btf);
-	if (map_fd != -1)
+	if (map_fd >= 0)
 		close(map_fd);
 	for (i = 0; i < 2; i++) {
 		free(user_btf[i]);
-		if (btf_fd[i] != -1)
+		if (btf_fd[i] >= 0)
 			close(btf_fd[i]);
 	}
 
@@ -4166,7 +4166,7 @@ static void do_test_get_info(unsigned int test_num)
 	btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
 			      btf_log_buf, BTF_LOG_BUF_SIZE,
 			      always_log);
-	if (CHECK(btf_fd == -1, "errno:%d", errno)) {
+	if (CHECK(btf_fd <= 0, "errno:%d", errno)) {
 		err = -1;
 		goto done;
 	}
@@ -4212,7 +4212,7 @@ done:
 	free(raw_btf);
 	free(user_btf);
 
-	if (btf_fd != -1)
+	if (btf_fd >= 0)
 		close(btf_fd);
 }
 
@@ -4249,8 +4249,9 @@ static void do_test_file(unsigned int test_num)
 		return;
 
 	btf = btf__parse_elf(test->file, &btf_ext);
-	if (IS_ERR(btf)) {
-		if (PTR_ERR(btf) == -ENOENT) {
+	err = libbpf_get_error(btf);
+	if (err) {
+		if (err == -ENOENT) {
 			printf("%s:SKIP: No ELF %s found", __func__, BTF_ELF_SEC);
 			test__skip();
 			return;
@@ -4263,7 +4264,8 @@ static void do_test_file(unsigned int test_num)
 	btf_ext__free(btf_ext);
 
 	obj = bpf_object__open(test->file);
-	if (CHECK(IS_ERR(obj), "obj: %ld", PTR_ERR(obj)))
+	err = libbpf_get_error(obj);
+	if (CHECK(err, "obj: %d", err))
 		return;
 
 	prog = bpf_program__next(NULL, obj);
@@ -4298,7 +4300,7 @@ static void do_test_file(unsigned int test_num)
 	info_len = sizeof(struct bpf_prog_info);
 	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
 
-	if (CHECK(err == -1, "invalid get info (1st) errno:%d", errno)) {
+	if (CHECK(err < 0, "invalid get info (1st) errno:%d", errno)) {
 		fprintf(stderr, "%s\n", btf_log_buf);
 		err = -1;
 		goto done;
@@ -4330,7 +4332,7 @@ static void do_test_file(unsigned int test_num)
 
 	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
 
-	if (CHECK(err == -1, "invalid get info (2nd) errno:%d", errno)) {
+	if (CHECK(err < 0, "invalid get info (2nd) errno:%d", errno)) {
 		fprintf(stderr, "%s\n", btf_log_buf);
 		err = -1;
 		goto done;
@@ -4886,7 +4888,7 @@ static void do_test_pprint(int test_num)
 			      always_log);
 	free(raw_btf);
 
-	if (CHECK(btf_fd == -1, "errno:%d", errno)) {
+	if (CHECK(btf_fd < 0, "errno:%d", errno)) {
 		err = -1;
 		goto done;
 	}
@@ -4901,7 +4903,7 @@ static void do_test_pprint(int test_num)
 	create_attr.btf_value_type_id = test->value_type_id;
 
 	map_fd = bpf_create_map_xattr(&create_attr);
-	if (CHECK(map_fd == -1, "errno:%d", errno)) {
+	if (CHECK(map_fd < 0, "errno:%d", errno)) {
 		err = -1;
 		goto done;
 	}
@@ -4982,7 +4984,7 @@ static void do_test_pprint(int test_num)
 
 					err = check_line(expected_line, nexpected_line,
 							 sizeof(expected_line), line);
-					if (err == -1)
+					if (err < 0)
 						goto done;
 				}
 
@@ -4998,7 +5000,7 @@ static void do_test_pprint(int test_num)
 								  cpu, cmapv);
 			err = check_line(expected_line, nexpected_line,
 					 sizeof(expected_line), line);
-			if (err == -1)
+			if (err < 0)
 				goto done;
 
 			cmapv = cmapv + rounded_value_size;
@@ -5036,9 +5038,9 @@ done:
 		fprintf(stderr, "OK");
 	if (*btf_log_buf && (err || always_log))
 		fprintf(stderr, "\n%s", btf_log_buf);
-	if (btf_fd != -1)
+	if (btf_fd >= 0)
 		close(btf_fd);
-	if (map_fd != -1)
+	if (map_fd >= 0)
 		close(map_fd);
 	if (pin_file)
 		fclose(pin_file);
@@ -5950,7 +5952,7 @@ static int test_get_finfo(const struct prog_info_raw_test *test,
 	/* get necessary lens */
 	info_len = sizeof(struct bpf_prog_info);
 	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
-	if (CHECK(err == -1, "invalid get info (1st) errno:%d", errno)) {
+	if (CHECK(err < 0, "invalid get info (1st) errno:%d", errno)) {
 		fprintf(stderr, "%s\n", btf_log_buf);
 		return -1;
 	}
@@ -5980,7 +5982,7 @@ static int test_get_finfo(const struct prog_info_raw_test *test,
 	info.func_info_rec_size = rec_size;
 	info.func_info = ptr_to_u64(func_info);
 	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
-	if (CHECK(err == -1, "invalid get info (2nd) errno:%d", errno)) {
+	if (CHECK(err < 0, "invalid get info (2nd) errno:%d", errno)) {
 		fprintf(stderr, "%s\n", btf_log_buf);
 		err = -1;
 		goto done;
@@ -6044,7 +6046,7 @@ static int test_get_linfo(const struct prog_info_raw_test *test,
 
 	info_len = sizeof(struct bpf_prog_info);
 	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
-	if (CHECK(err == -1, "err:%d errno:%d", err, errno)) {
+	if (CHECK(err < 0, "err:%d errno:%d", err, errno)) {
 		err = -1;
 		goto done;
 	}
@@ -6123,7 +6125,7 @@ static int test_get_linfo(const struct prog_info_raw_test *test,
 	 * Only recheck the info.*line_info* fields.
 	 * Other fields are not the concern of this test.
 	 */
-	if (CHECK(err == -1 ||
+	if (CHECK(err < 0 ||
 		  info.nr_line_info != cnt ||
 		  (jited_cnt && !info.jited_line_info) ||
 		  info.nr_jited_line_info != jited_cnt ||
@@ -6260,7 +6262,7 @@ static void do_test_info_raw(unsigned int test_num)
 			      always_log);
 	free(raw_btf);
 
-	if (CHECK(btf_fd == -1, "invalid btf_fd errno:%d", errno)) {
+	if (CHECK(btf_fd < 0, "invalid btf_fd errno:%d", errno)) {
 		err = -1;
 		goto done;
 	}
@@ -6273,7 +6275,8 @@ static void do_test_info_raw(unsigned int test_num)
 	patched_linfo = patch_name_tbd(test->line_info,
 				       test->str_sec, linfo_str_off,
 				       test->str_sec_size, &linfo_size);
-	if (IS_ERR(patched_linfo)) {
+	err = libbpf_get_error(patched_linfo);
+	if (err) {
 		fprintf(stderr, "error in creating raw bpf_line_info");
 		err = -1;
 		goto done;
@@ -6297,7 +6300,7 @@ static void do_test_info_raw(unsigned int test_num)
 	}
 
 	prog_fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
-	err = ((prog_fd == -1) != test->expected_prog_load_failure);
+	err = ((prog_fd < 0) != test->expected_prog_load_failure);
 	if (CHECK(err, "prog_fd:%d expected_prog_load_failure:%u errno:%d",
 		  prog_fd, test->expected_prog_load_failure, errno) ||
 	    CHECK(test->err_str && !strstr(btf_log_buf, test->err_str),
@@ -6306,7 +6309,7 @@ static void do_test_info_raw(unsigned int test_num)
 		goto done;
 	}
 
-	if (prog_fd == -1)
+	if (prog_fd < 0)
 		goto done;
 
 	err = test_get_finfo(test, prog_fd);
@@ -6323,12 +6326,12 @@ done:
 	if (*btf_log_buf && (err || always_log))
 		fprintf(stderr, "\n%s", btf_log_buf);
 
-	if (btf_fd != -1)
+	if (btf_fd >= 0)
 		close(btf_fd);
-	if (prog_fd != -1)
+	if (prog_fd >= 0)
 		close(prog_fd);
 
-	if (!IS_ERR(patched_linfo))
+	if (!libbpf_get_error(patched_linfo))
 		free(patched_linfo);
 }
 
@@ -6839,9 +6842,9 @@ static void do_test_dedup(unsigned int test_num)
 		return;
 
 	test_btf = btf__new((__u8 *)raw_btf, raw_btf_size);
+	err = libbpf_get_error(test_btf);
 	free(raw_btf);
-	if (CHECK(IS_ERR(test_btf), "invalid test_btf errno:%ld",
-		  PTR_ERR(test_btf))) {
+	if (CHECK(err, "invalid test_btf errno:%d", err)) {
 		err = -1;
 		goto done;
 	}
@@ -6853,9 +6856,9 @@ static void do_test_dedup(unsigned int test_num)
 	if (!raw_btf)
 		return;
 	expect_btf = btf__new((__u8 *)raw_btf, raw_btf_size);
+	err = libbpf_get_error(expect_btf);
 	free(raw_btf);
-	if (CHECK(IS_ERR(expect_btf), "invalid expect_btf errno:%ld",
-		  PTR_ERR(expect_btf))) {
+	if (CHECK(err, "invalid expect_btf errno:%d", err)) {
 		err = -1;
 		goto done;
 	}
@@ -6966,10 +6969,8 @@ static void do_test_dedup(unsigned int test_num)
 	}
 
 done:
-	if (!IS_ERR(test_btf))
-		btf__free(test_btf);
-	if (!IS_ERR(expect_btf))
-		btf__free(expect_btf);
+	btf__free(test_btf);
+	btf__free(expect_btf);
 }
 
 void test_btf(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index 5e129dc2073c..1b90e684ff13 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -32,8 +32,9 @@ static int btf_dump_all_types(const struct btf *btf,
 	int err = 0, id;
 
 	d = btf_dump__new(btf, NULL, opts, btf_dump_printf);
-	if (IS_ERR(d))
-		return PTR_ERR(d);
+	err = libbpf_get_error(d);
+	if (err)
+		return err;
 
 	for (id = 1; id <= type_cnt; id++) {
 		err = btf_dump__dump_type(d, id);
@@ -56,8 +57,7 @@ static int test_btf_dump_case(int n, struct btf_dump_test_case *t)
 	snprintf(test_file, sizeof(test_file), "%s.o", t->file);
 
 	btf = btf__parse_elf(test_file, NULL);
-	if (CHECK(IS_ERR(btf), "btf_parse_elf",
-	    "failed to load test BTF: %ld\n", PTR_ERR(btf))) {
+	if (!ASSERT_OK_PTR(btf, "btf_parse_elf")) {
 		err = -PTR_ERR(btf);
 		btf = NULL;
 		goto done;
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c
index f36da15b134f..022c7d89d6f4 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_write.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c
@@ -4,8 +4,6 @@
 #include <bpf/btf.h>
 #include "btf_helpers.h"
 
-static int duration = 0;
-
 void test_btf_write() {
 	const struct btf_var_secinfo *vi;
 	const struct btf_type *t;
@@ -16,7 +14,7 @@ void test_btf_write() {
 	int id, err, str_off;
 
 	btf = btf__new_empty();
-	if (CHECK(IS_ERR(btf), "new_empty", "failed: %ld\n", PTR_ERR(btf)))
+	if (!ASSERT_OK_PTR(btf, "new_empty"))
 		return;
 
 	str_off = btf__find_str(btf, "int");
diff --git a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
index 643dfa35419c..876be0ecb654 100644
--- a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
@@ -102,8 +102,7 @@ static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd)
 	 */
 	parent_link = bpf_program__attach_cgroup(obj->progs.egress,
 						 parent_cgroup_fd);
-	if (CHECK(IS_ERR(parent_link), "parent-cg-attach",
-		  "err %ld", PTR_ERR(parent_link)))
+	if (!ASSERT_OK_PTR(parent_link, "parent-cg-attach"))
 		goto close_bpf_object;
 	err = connect_send(CHILD_CGROUP);
 	if (CHECK(err, "first-connect-send", "errno %d", errno))
@@ -126,8 +125,7 @@ static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd)
 	 */
 	child_link = bpf_program__attach_cgroup(obj->progs.egress,
 						child_cgroup_fd);
-	if (CHECK(IS_ERR(child_link), "child-cg-attach",
-		  "err %ld", PTR_ERR(child_link)))
+	if (!ASSERT_OK_PTR(child_link, "child-cg-attach"))
 		goto close_bpf_object;
 	err = connect_send(CHILD_CGROUP);
 	if (CHECK(err, "second-connect-send", "errno %d", errno))
@@ -147,10 +145,8 @@ static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd)
 		goto close_bpf_object;
 
 close_bpf_object:
-	if (!IS_ERR(parent_link))
-		bpf_link__destroy(parent_link);
-	if (!IS_ERR(child_link))
-		bpf_link__destroy(child_link);
+	bpf_link__destroy(parent_link);
+	bpf_link__destroy(child_link);
 
 	cg_storage_multi_egress_only__destroy(obj);
 }
@@ -176,18 +172,15 @@ static void test_isolated(int parent_cgroup_fd, int child_cgroup_fd)
 	 */
 	parent_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1,
 							 parent_cgroup_fd);
-	if (CHECK(IS_ERR(parent_egress1_link), "parent-egress1-cg-attach",
-		  "err %ld", PTR_ERR(parent_egress1_link)))
+	if (!ASSERT_OK_PTR(parent_egress1_link, "parent-egress1-cg-attach"))
 		goto close_bpf_object;
 	parent_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2,
 							 parent_cgroup_fd);
-	if (CHECK(IS_ERR(parent_egress2_link), "parent-egress2-cg-attach",
-		  "err %ld", PTR_ERR(parent_egress2_link)))
+	if (!ASSERT_OK_PTR(parent_egress2_link, "parent-egress2-cg-attach"))
 		goto close_bpf_object;
 	parent_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress,
 							 parent_cgroup_fd);
-	if (CHECK(IS_ERR(parent_ingress_link), "parent-ingress-cg-attach",
-		  "err %ld", PTR_ERR(parent_ingress_link)))
+	if (!ASSERT_OK_PTR(parent_ingress_link, "parent-ingress-cg-attach"))
 		goto close_bpf_object;
 	err = connect_send(CHILD_CGROUP);
 	if (CHECK(err, "first-connect-send", "errno %d", errno))
@@ -221,18 +214,15 @@ static void test_isolated(int parent_cgroup_fd, int child_cgroup_fd)
 	 */
 	child_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1,
 							child_cgroup_fd);
-	if (CHECK(IS_ERR(child_egress1_link), "child-egress1-cg-attach",
-		  "err %ld", PTR_ERR(child_egress1_link)))
+	if (!ASSERT_OK_PTR(child_egress1_link, "child-egress1-cg-attach"))
 		goto close_bpf_object;
 	child_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2,
 							child_cgroup_fd);
-	if (CHECK(IS_ERR(child_egress2_link), "child-egress2-cg-attach",
-		  "err %ld", PTR_ERR(child_egress2_link)))
+	if (!ASSERT_OK_PTR(child_egress2_link, "child-egress2-cg-attach"))
 		goto close_bpf_object;
 	child_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress,
 							child_cgroup_fd);
-	if (CHECK(IS_ERR(child_ingress_link), "child-ingress-cg-attach",
-		  "err %ld", PTR_ERR(child_ingress_link)))
+	if (!ASSERT_OK_PTR(child_ingress_link, "child-ingress-cg-attach"))
 		goto close_bpf_object;
 	err = connect_send(CHILD_CGROUP);
 	if (CHECK(err, "second-connect-send", "errno %d", errno))
@@ -264,18 +254,12 @@ static void test_isolated(int parent_cgroup_fd, int child_cgroup_fd)
 		goto close_bpf_object;
 
 close_bpf_object:
-	if (!IS_ERR(parent_egress1_link))
-		bpf_link__destroy(parent_egress1_link);
-	if (!IS_ERR(parent_egress2_link))
-		bpf_link__destroy(parent_egress2_link);
-	if (!IS_ERR(parent_ingress_link))
-		bpf_link__destroy(parent_ingress_link);
-	if (!IS_ERR(child_egress1_link))
-		bpf_link__destroy(child_egress1_link);
-	if (!IS_ERR(child_egress2_link))
-		bpf_link__destroy(child_egress2_link);
-	if (!IS_ERR(child_ingress_link))
-		bpf_link__destroy(child_ingress_link);
+	bpf_link__destroy(parent_egress1_link);
+	bpf_link__destroy(parent_egress2_link);
+	bpf_link__destroy(parent_ingress_link);
+	bpf_link__destroy(child_egress1_link);
+	bpf_link__destroy(child_egress2_link);
+	bpf_link__destroy(child_ingress_link);
 
 	cg_storage_multi_isolated__destroy(obj);
 }
@@ -301,18 +285,15 @@ static void test_shared(int parent_cgroup_fd, int child_cgroup_fd)
 	 */
 	parent_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1,
 							 parent_cgroup_fd);
-	if (CHECK(IS_ERR(parent_egress1_link), "parent-egress1-cg-attach",
-		  "err %ld", PTR_ERR(parent_egress1_link)))
+	if (!ASSERT_OK_PTR(parent_egress1_link, "parent-egress1-cg-attach"))
 		goto close_bpf_object;
 	parent_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2,
 							 parent_cgroup_fd);
-	if (CHECK(IS_ERR(parent_egress2_link), "parent-egress2-cg-attach",
-		  "err %ld", PTR_ERR(parent_egress2_link)))
+	if (!ASSERT_OK_PTR(parent_egress2_link, "parent-egress2-cg-attach"))
 		goto close_bpf_object;
 	parent_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress,
 							 parent_cgroup_fd);
-	if (CHECK(IS_ERR(parent_ingress_link), "parent-ingress-cg-attach",
-		  "err %ld", PTR_ERR(parent_ingress_link)))
+	if (!ASSERT_OK_PTR(parent_ingress_link, "parent-ingress-cg-attach"))
 		goto close_bpf_object;
 	err = connect_send(CHILD_CGROUP);
 	if (CHECK(err, "first-connect-send", "errno %d", errno))
@@ -338,18 +319,15 @@ static void test_shared(int parent_cgroup_fd, int child_cgroup_fd)
 	 */
 	child_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1,
 							child_cgroup_fd);
-	if (CHECK(IS_ERR(child_egress1_link), "child-egress1-cg-attach",
-		  "err %ld", PTR_ERR(child_egress1_link)))
+	if (!ASSERT_OK_PTR(child_egress1_link, "child-egress1-cg-attach"))
 		goto close_bpf_object;
 	child_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2,
 							child_cgroup_fd);
-	if (CHECK(IS_ERR(child_egress2_link), "child-egress2-cg-attach",
-		  "err %ld", PTR_ERR(child_egress2_link)))
+	if (!ASSERT_OK_PTR(child_egress2_link, "child-egress2-cg-attach"))
 		goto close_bpf_object;
 	child_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress,
 							child_cgroup_fd);
-	if (CHECK(IS_ERR(child_ingress_link), "child-ingress-cg-attach",
-		  "err %ld", PTR_ERR(child_ingress_link)))
+	if (!ASSERT_OK_PTR(child_ingress_link, "child-ingress-cg-attach"))
 		goto close_bpf_object;
 	err = connect_send(CHILD_CGROUP);
 	if (CHECK(err, "second-connect-send", "errno %d", errno))
@@ -375,18 +353,12 @@ static void test_shared(int parent_cgroup_fd, int child_cgroup_fd)
 		goto close_bpf_object;
 
 close_bpf_object:
-	if (!IS_ERR(parent_egress1_link))
-		bpf_link__destroy(parent_egress1_link);
-	if (!IS_ERR(parent_egress2_link))
-		bpf_link__destroy(parent_egress2_link);
-	if (!IS_ERR(parent_ingress_link))
-		bpf_link__destroy(parent_ingress_link);
-	if (!IS_ERR(child_egress1_link))
-		bpf_link__destroy(child_egress1_link);
-	if (!IS_ERR(child_egress2_link))
-		bpf_link__destroy(child_egress2_link);
-	if (!IS_ERR(child_ingress_link))
-		bpf_link__destroy(child_ingress_link);
+	bpf_link__destroy(parent_egress1_link);
+	bpf_link__destroy(parent_egress2_link);
+	bpf_link__destroy(parent_ingress_link);
+	bpf_link__destroy(child_egress1_link);
+	bpf_link__destroy(child_egress2_link);
+	bpf_link__destroy(child_ingress_link);
 
 	cg_storage_multi_shared__destroy(obj);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
index 0a1fc9816cef..20bb8831dda6 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
@@ -167,7 +167,7 @@ void test_cgroup_attach_multi(void)
 	prog_cnt = 2;
 	CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS,
 				  BPF_F_QUERY_EFFECTIVE, &attach_flags,
-				  prog_ids, &prog_cnt) != -1);
+				  prog_ids, &prog_cnt) >= 0);
 	CHECK_FAIL(errno != ENOSPC);
 	CHECK_FAIL(prog_cnt != 4);
 	/* check that prog_ids are returned even when buffer is too small */
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
index 736796e56ed1..9091524131d6 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
@@ -65,8 +65,7 @@ void test_cgroup_link(void)
 	for (i = 0; i < cg_nr; i++) {
 		links[i] = bpf_program__attach_cgroup(skel->progs.egress,
 						      cgs[i].fd);
-		if (CHECK(IS_ERR(links[i]), "cg_attach", "i: %d, err: %ld\n",
-				 i, PTR_ERR(links[i])))
+		if (!ASSERT_OK_PTR(links[i], "cg_attach"))
 			goto cleanup;
 	}
 
@@ -121,8 +120,7 @@ void test_cgroup_link(void)
 
 	links[last_cg] = bpf_program__attach_cgroup(skel->progs.egress,
 						    cgs[last_cg].fd);
-	if (CHECK(IS_ERR(links[last_cg]), "cg_attach", "err: %ld\n",
-		  PTR_ERR(links[last_cg])))
+	if (!ASSERT_OK_PTR(links[last_cg], "cg_attach"))
 		goto cleanup;
 
 	ping_and_check(cg_nr + 1, 0);
@@ -147,7 +145,7 @@ void test_cgroup_link(void)
 	/* attempt to mix in with multi-attach bpf_link */
 	tmp_link = bpf_program__attach_cgroup(skel->progs.egress,
 					      cgs[last_cg].fd);
-	if (CHECK(!IS_ERR(tmp_link), "cg_attach_fail", "unexpected success!\n")) {
+	if (!ASSERT_ERR_PTR(tmp_link, "cg_attach_fail")) {
 		bpf_link__destroy(tmp_link);
 		goto cleanup;
 	}
@@ -165,8 +163,7 @@ void test_cgroup_link(void)
 	/* attach back link-based one */
 	links[last_cg] = bpf_program__attach_cgroup(skel->progs.egress,
 						    cgs[last_cg].fd);
-	if (CHECK(IS_ERR(links[last_cg]), "cg_attach", "err: %ld\n",
-		  PTR_ERR(links[last_cg])))
+	if (!ASSERT_OK_PTR(links[last_cg], "cg_attach"))
 		goto cleanup;
 
 	ping_and_check(cg_nr, 0);
@@ -249,8 +246,7 @@ cleanup:
 				 BPF_CGROUP_INET_EGRESS);
 
 	for (i = 0; i < cg_nr; i++) {
-		if (!IS_ERR(links[i]))
-			bpf_link__destroy(links[i]);
+		bpf_link__destroy(links[i]);
 	}
 	test_cgroup_link__destroy(skel);
 
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c
index 464edc1c1708..b9dc4ec655b5 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c
@@ -60,7 +60,7 @@ static void run_cgroup_bpf_test(const char *cg_path, int out_sk)
 		goto cleanup;
 
 	link = bpf_program__attach_cgroup(skel->progs.ingress_lookup, cgfd);
-	if (CHECK(IS_ERR(link), "cgroup_attach", "err: %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "cgroup_attach"))
 		goto cleanup;
 
 	run_lookup_test(&skel->bss->g_serv_port, out_sk);
diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c
index b62a39315336..012068f33a0a 100644
--- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c
+++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c
@@ -53,7 +53,7 @@ static void test_check_mtu_xdp_attach(void)
 	prog = skel->progs.xdp_use_helper_basic;
 
 	link = bpf_program__attach_xdp(prog, IFINDEX_LO);
-	if (CHECK(IS_ERR(link), "link_attach", "failed: %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "link_attach"))
 		goto out;
 	skel->links.xdp_use_helper_basic = link;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 607710826dca..d02e064c535f 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -369,8 +369,7 @@ static int setup_type_id_case_local(struct core_reloc_test_case *test)
 	const char *name;
 	int i;
 
-	if (CHECK(IS_ERR(local_btf), "local_btf", "failed: %ld\n", PTR_ERR(local_btf)) ||
-	    CHECK(IS_ERR(targ_btf), "targ_btf", "failed: %ld\n", PTR_ERR(targ_btf))) {
+	if (!ASSERT_OK_PTR(local_btf, "local_btf") || !ASSERT_OK_PTR(targ_btf, "targ_btf")) {
 		btf__free(local_btf);
 		btf__free(targ_btf);
 		return -EINVAL;
@@ -848,8 +847,7 @@ void test_core_reloc(void)
 		}
 
 		obj = bpf_object__open_file(test_case->bpf_obj_file, NULL);
-		if (CHECK(IS_ERR(obj), "obj_open", "failed to open '%s': %ld\n",
-			  test_case->bpf_obj_file, PTR_ERR(obj)))
+		if (!ASSERT_OK_PTR(obj, "obj_open"))
 			continue;
 
 		probe_name = "raw_tracepoint/sys_enter";
@@ -899,8 +897,7 @@ void test_core_reloc(void)
 		data->my_pid_tgid = my_pid_tgid;
 
 		link = bpf_program__attach_raw_tracepoint(prog, tp_name);
-		if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n",
-			  PTR_ERR(link)))
+		if (!ASSERT_OK_PTR(link, "attach_raw_tp"))
 			goto cleanup;
 
 		/* trigger test run */
@@ -941,10 +938,8 @@ cleanup:
 			CHECK_FAIL(munmap(mmap_data, mmap_sz));
 			mmap_data = NULL;
 		}
-		if (!IS_ERR_OR_NULL(link)) {
-			bpf_link__destroy(link);
-			link = NULL;
-		}
+		bpf_link__destroy(link);
+		link = NULL;
 		bpf_object__close(obj);
 	}
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
index 109d0345a2be..91154c2ba256 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
@@ -1,8 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
-#include "fentry_test.skel.h"
-#include "fexit_test.skel.h"
+#include "fentry_test.lskel.h"
+#include "fexit_test.lskel.h"
 
 void test_fentry_fexit(void)
 {
@@ -26,7 +26,7 @@ void test_fentry_fexit(void)
 	if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
 		goto close_prog;
 
-	prog_fd = bpf_program__fd(fexit_skel->progs.test1);
+	prog_fd = fexit_skel->progs.test1.prog_fd;
 	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
 	CHECK(err || retval, "ipv6",
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
index 7cb111b11995..174c89e7456e 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
@@ -1,13 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
-#include "fentry_test.skel.h"
+#include "fentry_test.lskel.h"
 
 static int fentry_test(struct fentry_test *fentry_skel)
 {
 	int err, prog_fd, i;
 	__u32 duration = 0, retval;
-	struct bpf_link *link;
+	int link_fd;
 	__u64 *result;
 
 	err = fentry_test__attach(fentry_skel);
@@ -15,11 +15,11 @@ static int fentry_test(struct fentry_test *fentry_skel)
 		return err;
 
 	/* Check that already linked program can't be attached again. */
-	link = bpf_program__attach(fentry_skel->progs.test1);
-	if (!ASSERT_ERR_PTR(link, "fentry_attach_link"))
+	link_fd = fentry_test__test1__attach(fentry_skel);
+	if (!ASSERT_LT(link_fd, 0, "fentry_attach_link"))
 		return -1;
 
-	prog_fd = bpf_program__fd(fentry_skel->progs.test1);
+	prog_fd = fentry_skel->progs.test1.prog_fd;
 	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
 	ASSERT_OK(err, "test_run");
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index 63990842d20f..73b4c76e6b86 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -146,10 +146,8 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 
 close_prog:
 	for (i = 0; i < prog_cnt; i++)
-		if (!IS_ERR_OR_NULL(link[i]))
-			bpf_link__destroy(link[i]);
-	if (!IS_ERR_OR_NULL(obj))
-		bpf_object__close(obj);
+		bpf_link__destroy(link[i]);
+	bpf_object__close(obj);
 	bpf_object__close(tgt_obj);
 	free(link);
 	free(prog);
@@ -231,7 +229,7 @@ static int test_second_attach(struct bpf_object *obj)
 		return err;
 
 	link = bpf_program__attach_freplace(prog, tgt_fd, tgt_name);
-	if (CHECK(IS_ERR(link), "second_link", "failed to attach second link prog_fd %d tgt_fd %d\n", bpf_program__fd(prog), tgt_fd))
+	if (!ASSERT_OK_PTR(link, "second_link"))
 		goto out;
 
 	err = bpf_prog_test_run(tgt_fd, 1, &pkt_v6, sizeof(pkt_v6),
@@ -283,9 +281,7 @@ static void test_fmod_ret_freplace(void)
 	opts.attach_prog_fd = pkt_fd;
 
 	freplace_obj = bpf_object__open_file(freplace_name, &opts);
-	if (CHECK(IS_ERR_OR_NULL(freplace_obj), "freplace_obj_open",
-		  "failed to open %s: %ld\n", freplace_name,
-		  PTR_ERR(freplace_obj)))
+	if (!ASSERT_OK_PTR(freplace_obj, "freplace_obj_open"))
 		goto out;
 
 	err = bpf_object__load(freplace_obj);
@@ -294,14 +290,12 @@ static void test_fmod_ret_freplace(void)
 
 	prog = bpf_program__next(NULL, freplace_obj);
 	freplace_link = bpf_program__attach_trace(prog);
-	if (CHECK(IS_ERR(freplace_link), "freplace_attach_trace", "failed to link\n"))
+	if (!ASSERT_OK_PTR(freplace_link, "freplace_attach_trace"))
 		goto out;
 
 	opts.attach_prog_fd = bpf_program__fd(prog);
 	fmod_obj = bpf_object__open_file(fmod_ret_name, &opts);
-	if (CHECK(IS_ERR_OR_NULL(fmod_obj), "fmod_obj_open",
-		  "failed to open %s: %ld\n", fmod_ret_name,
-		  PTR_ERR(fmod_obj)))
+	if (!ASSERT_OK_PTR(fmod_obj, "fmod_obj_open"))
 		goto out;
 
 	err = bpf_object__load(fmod_obj);
@@ -350,9 +344,7 @@ static void test_obj_load_failure_common(const char *obj_file,
 			   );
 
 	obj = bpf_object__open_file(obj_file, &opts);
-	if (CHECK(IS_ERR_OR_NULL(obj), "obj_open",
-		  "failed to open %s: %ld\n", obj_file,
-		  PTR_ERR(obj)))
+	if (!ASSERT_OK_PTR(obj, "obj_open"))
 		goto close_prog;
 
 	/* It should fail to load the program */
@@ -361,8 +353,7 @@ static void test_obj_load_failure_common(const char *obj_file,
 		goto close_prog;
 
 close_prog:
-	if (!IS_ERR_OR_NULL(obj))
-		bpf_object__close(obj);
+	bpf_object__close(obj);
 	bpf_object__close(pkt_obj);
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
index ccc7e8a34ab6..4e7f4b42ea29 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
@@ -6,7 +6,7 @@
 #include <time.h>
 #include <sys/mman.h>
 #include <sys/syscall.h>
-#include "fexit_sleep.skel.h"
+#include "fexit_sleep.lskel.h"
 
 static int do_sleep(void *skel)
 {
@@ -58,8 +58,8 @@ void test_fexit_sleep(void)
 	 * waiting for percpu_ref_kill to confirm). The other one
 	 * will be freed quickly.
 	 */
-	close(bpf_program__fd(fexit_skel->progs.nanosleep_fentry));
-	close(bpf_program__fd(fexit_skel->progs.nanosleep_fexit));
+	close(fexit_skel->progs.nanosleep_fentry.prog_fd);
+	close(fexit_skel->progs.nanosleep_fexit.prog_fd);
 	fexit_sleep__detach(fexit_skel);
 
 	/* kill the thread to unwind sys_nanosleep stack through the trampoline */
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
index 6792e41f7f69..af3dba726701 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
@@ -1,13 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
-#include "fexit_test.skel.h"
+#include "fexit_test.lskel.h"
 
 static int fexit_test(struct fexit_test *fexit_skel)
 {
 	int err, prog_fd, i;
 	__u32 duration = 0, retval;
-	struct bpf_link *link;
+	int link_fd;
 	__u64 *result;
 
 	err = fexit_test__attach(fexit_skel);
@@ -15,11 +15,11 @@ static int fexit_test(struct fexit_test *fexit_skel)
 		return err;
 
 	/* Check that already linked program can't be attached again. */
-	link = bpf_program__attach(fexit_skel->progs.test1);
-	if (!ASSERT_ERR_PTR(link, "fexit_attach_link"))
+	link_fd = fexit_test__test1__attach(fexit_skel);
+	if (!ASSERT_LT(link_fd, 0, "fexit_attach_link"))
 		return -1;
 
-	prog_fd = bpf_program__fd(fexit_skel->progs.test1);
+	prog_fd = fexit_skel->progs.test1.prog_fd;
 	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
 	ASSERT_OK(err, "test_run");
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index cd6dc80edf18..225714f71ac6 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -541,7 +541,7 @@ static void test_skb_less_link_create(struct bpf_flow *skel, int tap_fd)
 		return;
 
 	link = bpf_program__attach_netns(skel->progs._dissect, net_fd);
-	if (CHECK(IS_ERR(link), "attach_netns", "err %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "attach_netns"))
 		goto out_close;
 
 	run_tests_skb_less(tap_fd, skel->maps.last_dissection);
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
index 172c586b6996..3931ede5c534 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
@@ -134,9 +134,9 @@ static void test_link_create_link_create(int netns, int prog1, int prog2)
 	/* Expect failure creating link when another link exists */
 	errno = 0;
 	link2 = bpf_link_create(prog2, netns, BPF_FLOW_DISSECTOR, &opts);
-	if (CHECK_FAIL(link2 != -1 || errno != E2BIG))
+	if (CHECK_FAIL(link2 >= 0 || errno != E2BIG))
 		perror("bpf_prog_attach(prog2) expected E2BIG");
-	if (link2 != -1)
+	if (link2 >= 0)
 		close(link2);
 	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
 
@@ -159,9 +159,9 @@ static void test_prog_attach_link_create(int netns, int prog1, int prog2)
 	/* Expect failure creating link when prog attached */
 	errno = 0;
 	link = bpf_link_create(prog2, netns, BPF_FLOW_DISSECTOR, &opts);
-	if (CHECK_FAIL(link != -1 || errno != EEXIST))
+	if (CHECK_FAIL(link >= 0 || errno != EEXIST))
 		perror("bpf_link_create(prog2) expected EEXIST");
-	if (link != -1)
+	if (link >= 0)
 		close(link);
 	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
 
@@ -623,7 +623,7 @@ static void run_tests(int netns)
 	}
 out_close:
 	for (i = 0; i < ARRAY_SIZE(progs); i++) {
-		if (progs[i] != -1)
+		if (progs[i] >= 0)
 			CHECK_FAIL(close(progs[i]));
 	}
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
index 925722217edf..522237aa4470 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
@@ -121,12 +121,12 @@ void test_get_stack_raw_tp(void)
 		goto close_prog;
 
 	link = bpf_program__attach_raw_tracepoint(prog, "sys_enter");
-	if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "attach_raw_tp"))
 		goto close_prog;
 
 	pb_opts.sample_cb = get_stack_print_output;
 	pb = perf_buffer__new(bpf_map__fd(map), 8, &pb_opts);
-	if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb)))
+	if (!ASSERT_OK_PTR(pb, "perf_buf__new"))
 		goto close_prog;
 
 	/* trigger some syscall action */
@@ -141,9 +141,7 @@ void test_get_stack_raw_tp(void)
 	}
 
 close_prog:
-	if (!IS_ERR_OR_NULL(link))
-		bpf_link__destroy(link);
-	if (!IS_ERR_OR_NULL(pb))
-		perf_buffer__free(pb);
+	bpf_link__destroy(link);
+	perf_buffer__free(pb);
 	bpf_object__close(obj);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c
index d884b2ed5bc5..8d5a6023a1bb 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c
@@ -48,8 +48,7 @@ void test_get_stackid_cannot_attach(void)
 
 	skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu,
 							   pmu_fd);
-	CHECK(!IS_ERR(skel->links.oncpu), "attach_perf_event_no_callchain",
-	      "should have failed\n");
+	ASSERT_ERR_PTR(skel->links.oncpu, "attach_perf_event_no_callchain");
 	close(pmu_fd);
 
 	/* add PERF_SAMPLE_CALLCHAIN, attach should succeed */
@@ -65,8 +64,7 @@ void test_get_stackid_cannot_attach(void)
 
 	skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu,
 							   pmu_fd);
-	CHECK(IS_ERR(skel->links.oncpu), "attach_perf_event_callchain",
-	      "err: %ld\n", PTR_ERR(skel->links.oncpu));
+	ASSERT_OK_PTR(skel->links.oncpu, "attach_perf_event_callchain");
 	close(pmu_fd);
 
 	/* add exclude_callchain_kernel, attach should fail */
@@ -82,8 +80,7 @@ void test_get_stackid_cannot_attach(void)
 
 	skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu,
 							   pmu_fd);
-	CHECK(!IS_ERR(skel->links.oncpu), "attach_perf_event_exclude_callchain_kernel",
-	      "should have failed\n");
+	ASSERT_ERR_PTR(skel->links.oncpu, "attach_perf_event_exclude_callchain_kernel");
 	close(pmu_fd);
 
 cleanup:
diff --git a/tools/testing/selftests/bpf/prog_tests/hashmap.c b/tools/testing/selftests/bpf/prog_tests/hashmap.c
index 428d488830c6..4747ab18f97f 100644
--- a/tools/testing/selftests/bpf/prog_tests/hashmap.c
+++ b/tools/testing/selftests/bpf/prog_tests/hashmap.c
@@ -48,8 +48,7 @@ static void test_hashmap_generic(void)
 	struct hashmap *map;
 
 	map = hashmap__new(hash_fn, equal_fn, NULL);
-	if (CHECK(IS_ERR(map), "hashmap__new",
-		  "failed to create map: %ld\n", PTR_ERR(map)))
+	if (!ASSERT_OK_PTR(map, "hashmap__new"))
 		return;
 
 	for (i = 0; i < ELEM_CNT; i++) {
@@ -267,8 +266,7 @@ static void test_hashmap_multimap(void)
 
 	/* force collisions */
 	map = hashmap__new(collision_hash_fn, equal_fn, NULL);
-	if (CHECK(IS_ERR(map), "hashmap__new",
-		  "failed to create map: %ld\n", PTR_ERR(map)))
+	if (!ASSERT_OK_PTR(map, "hashmap__new"))
 		return;
 
 	/* set up multimap:
@@ -339,8 +337,7 @@ static void test_hashmap_empty()
 
 	/* force collisions */
 	map = hashmap__new(hash_fn, equal_fn, NULL);
-	if (CHECK(IS_ERR(map), "hashmap__new",
-		  "failed to create map: %ld\n", PTR_ERR(map)))
+	if (!ASSERT_OK_PTR(map, "hashmap__new"))
 		goto cleanup;
 
 	if (CHECK(hashmap__size(map) != 0, "hashmap__size",
diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
index d65107919998..ddfb6bf97152 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
@@ -97,15 +97,13 @@ void test_kfree_skb(void)
 		goto close_prog;
 
 	link = bpf_program__attach_raw_tracepoint(prog, NULL);
-	if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "attach_raw_tp"))
 		goto close_prog;
 	link_fentry = bpf_program__attach_trace(fentry);
-	if (CHECK(IS_ERR(link_fentry), "attach fentry", "err %ld\n",
-		  PTR_ERR(link_fentry)))
+	if (!ASSERT_OK_PTR(link_fentry, "attach fentry"))
 		goto close_prog;
 	link_fexit = bpf_program__attach_trace(fexit);
-	if (CHECK(IS_ERR(link_fexit), "attach fexit", "err %ld\n",
-		  PTR_ERR(link_fexit)))
+	if (!ASSERT_OK_PTR(link_fexit, "attach fexit"))
 		goto close_prog;
 
 	perf_buf_map = bpf_object__find_map_by_name(obj2, "perf_buf_map");
@@ -116,7 +114,7 @@ void test_kfree_skb(void)
 	pb_opts.sample_cb = on_sample;
 	pb_opts.ctx = &passed;
 	pb = perf_buffer__new(bpf_map__fd(perf_buf_map), 1, &pb_opts);
-	if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb)))
+	if (!ASSERT_OK_PTR(pb, "perf_buf__new"))
 		goto close_prog;
 
 	memcpy(skb.cb, &cb, sizeof(cb));
@@ -144,12 +142,9 @@ void test_kfree_skb(void)
 	CHECK_FAIL(!test_ok[0] || !test_ok[1]);
 close_prog:
 	perf_buffer__free(pb);
-	if (!IS_ERR_OR_NULL(link))
-		bpf_link__destroy(link);
-	if (!IS_ERR_OR_NULL(link_fentry))
-		bpf_link__destroy(link_fentry);
-	if (!IS_ERR_OR_NULL(link_fexit))
-		bpf_link__destroy(link_fexit);
+	bpf_link__destroy(link);
+	bpf_link__destroy(link_fentry);
+	bpf_link__destroy(link_fexit);
 	bpf_object__close(obj);
 	bpf_object__close(obj2);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
index 7fc0951ee75f..30a7b9b837bf 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
@@ -2,7 +2,7 @@
 /* Copyright (c) 2021 Facebook */
 #include <test_progs.h>
 #include <network_helpers.h>
-#include "kfunc_call_test.skel.h"
+#include "kfunc_call_test.lskel.h"
 #include "kfunc_call_test_subprog.skel.h"
 
 static void test_main(void)
@@ -14,13 +14,13 @@ static void test_main(void)
 	if (!ASSERT_OK_PTR(skel, "skel"))
 		return;
 
-	prog_fd = bpf_program__fd(skel->progs.kfunc_call_test1);
+	prog_fd = skel->progs.kfunc_call_test1.prog_fd;
 	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
 				NULL, NULL, (__u32 *)&retval, NULL);
 	ASSERT_OK(err, "bpf_prog_test_run(test1)");
 	ASSERT_EQ(retval, 12, "test1-retval");
 
-	prog_fd = bpf_program__fd(skel->progs.kfunc_call_test2);
+	prog_fd = skel->progs.kfunc_call_test2.prog_fd;
 	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
 				NULL, NULL, (__u32 *)&retval, NULL);
 	ASSERT_OK(err, "bpf_prog_test_run(test2)");
diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
index b58b775d19f3..67bebd324147 100644
--- a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
@@ -87,8 +87,7 @@ void test_ksyms_btf(void)
 	struct btf *btf;
 
 	btf = libbpf_find_kernel_btf();
-	if (CHECK(IS_ERR(btf), "btf_exists", "failed to load kernel BTF: %ld\n",
-		  PTR_ERR(btf)))
+	if (!ASSERT_OK_PTR(btf, "btf_exists"))
 		return;
 
 	percpu_datasec = btf__find_by_name_kind(btf, ".data..percpu",
diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c
index 4c232b456479..2cd5cded543f 100644
--- a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c
+++ b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c
@@ -4,7 +4,7 @@
 #include <test_progs.h>
 #include <bpf/libbpf.h>
 #include <bpf/btf.h>
-#include "test_ksyms_module.skel.h"
+#include "test_ksyms_module.lskel.h"
 
 static int duration;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/link_pinning.c b/tools/testing/selftests/bpf/prog_tests/link_pinning.c
index a743288cf384..6fc97c45f71e 100644
--- a/tools/testing/selftests/bpf/prog_tests/link_pinning.c
+++ b/tools/testing/selftests/bpf/prog_tests/link_pinning.c
@@ -17,7 +17,7 @@ void test_link_pinning_subtest(struct bpf_program *prog,
 	int err, i;
 
 	link = bpf_program__attach(prog);
-	if (CHECK(IS_ERR(link), "link_attach", "err: %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "link_attach"))
 		goto cleanup;
 
 	bss->in = 1;
@@ -51,7 +51,7 @@ void test_link_pinning_subtest(struct bpf_program *prog,
 
 	/* re-open link from BPFFS */
 	link = bpf_link__open(link_pin_path);
-	if (CHECK(IS_ERR(link), "link_open", "err: %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "link_open"))
 		goto cleanup;
 
 	CHECK(strcmp(link_pin_path, bpf_link__pin_path(link)), "pin_path2",
@@ -84,8 +84,7 @@ void test_link_pinning_subtest(struct bpf_program *prog,
 	CHECK(i == 10000, "link_attached", "got to iteration #%d\n", i);
 
 cleanup:
-	if (!IS_ERR(link))
-		bpf_link__destroy(link);
+	bpf_link__destroy(link);
 }
 
 void test_link_pinning(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/lookup_and_delete.c b/tools/testing/selftests/bpf/prog_tests/lookup_and_delete.c
new file mode 100644
index 000000000000..beebfa9730e1
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/lookup_and_delete.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <test_progs.h>
+#include "test_lookup_and_delete.skel.h"
+
+#define START_VALUE 1234
+#define NEW_VALUE 4321
+#define MAX_ENTRIES 2
+
+static int duration;
+static int nr_cpus;
+
+static int fill_values(int map_fd)
+{
+	__u64 key, value = START_VALUE;
+	int err;
+
+	for (key = 1; key < MAX_ENTRIES + 1; key++) {
+		err = bpf_map_update_elem(map_fd, &key, &value, BPF_NOEXIST);
+		if (!ASSERT_OK(err, "bpf_map_update_elem"))
+			return -1;
+	}
+
+	return 0;
+}
+
+static int fill_values_percpu(int map_fd)
+{
+	__u64 key, value[nr_cpus];
+	int i, err;
+
+	for (i = 0; i < nr_cpus; i++)
+		value[i] = START_VALUE;
+
+	for (key = 1; key < MAX_ENTRIES + 1; key++) {
+		err = bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST);
+		if (!ASSERT_OK(err, "bpf_map_update_elem"))
+			return -1;
+	}
+
+	return 0;
+}
+
+static struct test_lookup_and_delete *setup_prog(enum bpf_map_type map_type,
+						 int *map_fd)
+{
+	struct test_lookup_and_delete *skel;
+	int err;
+
+	skel = test_lookup_and_delete__open();
+	if (!ASSERT_OK_PTR(skel, "test_lookup_and_delete__open"))
+		return NULL;
+
+	err = bpf_map__set_type(skel->maps.hash_map, map_type);
+	if (!ASSERT_OK(err, "bpf_map__set_type"))
+		goto cleanup;
+
+	err = bpf_map__set_max_entries(skel->maps.hash_map, MAX_ENTRIES);
+	if (!ASSERT_OK(err, "bpf_map__set_max_entries"))
+		goto cleanup;
+
+	err = test_lookup_and_delete__load(skel);
+	if (!ASSERT_OK(err, "test_lookup_and_delete__load"))
+		goto cleanup;
+
+	*map_fd = bpf_map__fd(skel->maps.hash_map);
+	if (!ASSERT_GE(*map_fd, 0, "bpf_map__fd"))
+		goto cleanup;
+
+	return skel;
+
+cleanup:
+	test_lookup_and_delete__destroy(skel);
+	return NULL;
+}
+
+/* Triggers BPF program that updates map with given key and value */
+static int trigger_tp(struct test_lookup_and_delete *skel, __u64 key,
+		      __u64 value)
+{
+	int err;
+
+	skel->bss->set_pid = getpid();
+	skel->bss->set_key = key;
+	skel->bss->set_value = value;
+
+	err = test_lookup_and_delete__attach(skel);
+	if (!ASSERT_OK(err, "test_lookup_and_delete__attach"))
+		return -1;
+
+	syscall(__NR_getpgid);
+
+	test_lookup_and_delete__detach(skel);
+
+	return 0;
+}
+
+static void test_lookup_and_delete_hash(void)
+{
+	struct test_lookup_and_delete *skel;
+	__u64 key, value;
+	int map_fd, err;
+
+	/* Setup program and fill the map. */
+	skel = setup_prog(BPF_MAP_TYPE_HASH, &map_fd);
+	if (!ASSERT_OK_PTR(skel, "setup_prog"))
+		return;
+
+	err = fill_values(map_fd);
+	if (!ASSERT_OK(err, "fill_values"))
+		goto cleanup;
+
+	/* Lookup and delete element. */
+	key = 1;
+	err = bpf_map_lookup_and_delete_elem(map_fd, &key, &value);
+	if (!ASSERT_OK(err, "bpf_map_lookup_and_delete_elem"))
+		goto cleanup;
+
+	/* Fetched value should match the initially set value. */
+	if (CHECK(value != START_VALUE, "bpf_map_lookup_and_delete_elem",
+		  "unexpected value=%lld\n", value))
+		goto cleanup;
+
+	/* Check that the entry is non existent. */
+	err = bpf_map_lookup_elem(map_fd, &key, &value);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem"))
+		goto cleanup;
+
+cleanup:
+	test_lookup_and_delete__destroy(skel);
+}
+
+static void test_lookup_and_delete_percpu_hash(void)
+{
+	struct test_lookup_and_delete *skel;
+	__u64 key, val, value[nr_cpus];
+	int map_fd, err, i;
+
+	/* Setup program and fill the map. */
+	skel = setup_prog(BPF_MAP_TYPE_PERCPU_HASH, &map_fd);
+	if (!ASSERT_OK_PTR(skel, "setup_prog"))
+		return;
+
+	err = fill_values_percpu(map_fd);
+	if (!ASSERT_OK(err, "fill_values_percpu"))
+		goto cleanup;
+
+	/* Lookup and delete element. */
+	key = 1;
+	err = bpf_map_lookup_and_delete_elem(map_fd, &key, value);
+	if (!ASSERT_OK(err, "bpf_map_lookup_and_delete_elem"))
+		goto cleanup;
+
+	for (i = 0; i < nr_cpus; i++) {
+		val = value[i];
+
+		/* Fetched value should match the initially set value. */
+		if (CHECK(val != START_VALUE, "map value",
+			  "unexpected for cpu %d: %lld\n", i, val))
+			goto cleanup;
+	}
+
+	/* Check that the entry is non existent. */
+	err = bpf_map_lookup_elem(map_fd, &key, value);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem"))
+		goto cleanup;
+
+cleanup:
+	test_lookup_and_delete__destroy(skel);
+}
+
+static void test_lookup_and_delete_lru_hash(void)
+{
+	struct test_lookup_and_delete *skel;
+	__u64 key, value;
+	int map_fd, err;
+
+	/* Setup program and fill the LRU map. */
+	skel = setup_prog(BPF_MAP_TYPE_LRU_HASH, &map_fd);
+	if (!ASSERT_OK_PTR(skel, "setup_prog"))
+		return;
+
+	err = fill_values(map_fd);
+	if (!ASSERT_OK(err, "fill_values"))
+		goto cleanup;
+
+	/* Insert new element at key=3, should reuse LRU element. */
+	key = 3;
+	err = trigger_tp(skel, key, NEW_VALUE);
+	if (!ASSERT_OK(err, "trigger_tp"))
+		goto cleanup;
+
+	/* Lookup and delete element 3. */
+	err = bpf_map_lookup_and_delete_elem(map_fd, &key, &value);
+	if (!ASSERT_OK(err, "bpf_map_lookup_and_delete_elem"))
+		goto cleanup;
+
+	/* Value should match the new value. */
+	if (CHECK(value != NEW_VALUE, "bpf_map_lookup_and_delete_elem",
+		  "unexpected value=%lld\n", value))
+		goto cleanup;
+
+	/* Check that entries 3 and 1 are non existent. */
+	err = bpf_map_lookup_elem(map_fd, &key, &value);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem"))
+		goto cleanup;
+
+	key = 1;
+	err = bpf_map_lookup_elem(map_fd, &key, &value);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem"))
+		goto cleanup;
+
+cleanup:
+	test_lookup_and_delete__destroy(skel);
+}
+
+static void test_lookup_and_delete_lru_percpu_hash(void)
+{
+	struct test_lookup_and_delete *skel;
+	__u64 key, val, value[nr_cpus];
+	int map_fd, err, i, cpucnt = 0;
+
+	/* Setup program and fill the LRU map. */
+	skel = setup_prog(BPF_MAP_TYPE_LRU_PERCPU_HASH, &map_fd);
+	if (!ASSERT_OK_PTR(skel, "setup_prog"))
+		return;
+
+	err = fill_values_percpu(map_fd);
+	if (!ASSERT_OK(err, "fill_values_percpu"))
+		goto cleanup;
+
+	/* Insert new element at key=3, should reuse LRU element 1. */
+	key = 3;
+	err = trigger_tp(skel, key, NEW_VALUE);
+	if (!ASSERT_OK(err, "trigger_tp"))
+		goto cleanup;
+
+	/* Clean value. */
+	for (i = 0; i < nr_cpus; i++)
+		value[i] = 0;
+
+	/* Lookup and delete element 3. */
+	err = bpf_map_lookup_and_delete_elem(map_fd, &key, value);
+	if (!ASSERT_OK(err, "bpf_map_lookup_and_delete_elem")) {
+		goto cleanup;
+	}
+
+	/* Check if only one CPU has set the value. */
+	for (i = 0; i < nr_cpus; i++) {
+		val = value[i];
+		if (val) {
+			if (CHECK(val != NEW_VALUE, "map value",
+				  "unexpected for cpu %d: %lld\n", i, val))
+				goto cleanup;
+			cpucnt++;
+		}
+	}
+	if (CHECK(cpucnt != 1, "map value", "set for %d CPUs instead of 1!\n",
+		  cpucnt))
+		goto cleanup;
+
+	/* Check that entries 3 and 1 are non existent. */
+	err = bpf_map_lookup_elem(map_fd, &key, &value);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem"))
+		goto cleanup;
+
+	key = 1;
+	err = bpf_map_lookup_elem(map_fd, &key, &value);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem"))
+		goto cleanup;
+
+cleanup:
+	test_lookup_and_delete__destroy(skel);
+}
+
+void test_lookup_and_delete(void)
+{
+	nr_cpus = bpf_num_possible_cpus();
+
+	if (test__start_subtest("lookup_and_delete"))
+		test_lookup_and_delete_hash();
+	if (test__start_subtest("lookup_and_delete_percpu"))
+		test_lookup_and_delete_percpu_hash();
+	if (test__start_subtest("lookup_and_delete_lru"))
+		test_lookup_and_delete_lru_hash();
+	if (test__start_subtest("lookup_and_delete_lru_percpu"))
+		test_lookup_and_delete_lru_percpu_hash();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c b/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c
new file mode 100644
index 000000000000..59adb4715394
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c
@@ -0,0 +1,559 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Check if we can migrate child sockets.
+ *
+ *   1. call listen() for 4 server sockets.
+ *   2. call connect() for 25 client sockets.
+ *   3. call listen() for 1 server socket. (migration target)
+ *   4. update a map to migrate all child sockets
+ *        to the last server socket (migrate_map[cookie] = 4)
+ *   5. call shutdown() for first 4 server sockets
+ *        and migrate the requests in the accept queue
+ *        to the last server socket.
+ *   6. call listen() for the second server socket.
+ *   7. call shutdown() for the last server
+ *        and migrate the requests in the accept queue
+ *        to the second server socket.
+ *   8. call listen() for the last server.
+ *   9. call shutdown() for the second server
+ *        and migrate the requests in the accept queue
+ *        to the last server socket.
+ *  10. call accept() for the last server socket.
+ *
+ * Author: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
+ */
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "test_progs.h"
+#include "test_migrate_reuseport.skel.h"
+#include "network_helpers.h"
+
+#ifndef TCP_FASTOPEN_CONNECT
+#define TCP_FASTOPEN_CONNECT 30
+#endif
+
+#define IFINDEX_LO 1
+
+#define NR_SERVERS 5
+#define NR_CLIENTS (NR_SERVERS * 5)
+#define MIGRATED_TO (NR_SERVERS - 1)
+
+/* fastopenq->max_qlen and sk->sk_max_ack_backlog */
+#define QLEN (NR_CLIENTS * 5)
+
+#define MSG "Hello World\0"
+#define MSGLEN 12
+
+static struct migrate_reuseport_test_case {
+	const char *name;
+	__s64 servers[NR_SERVERS];
+	__s64 clients[NR_CLIENTS];
+	struct sockaddr_storage addr;
+	socklen_t addrlen;
+	int family;
+	int state;
+	bool drop_ack;
+	bool expire_synack_timer;
+	bool fastopen;
+	struct bpf_link *link;
+} test_cases[] = {
+	{
+		.name = "IPv4 TCP_ESTABLISHED  inet_csk_listen_stop",
+		.family = AF_INET,
+		.state = BPF_TCP_ESTABLISHED,
+		.drop_ack = false,
+		.expire_synack_timer = false,
+		.fastopen = false,
+	},
+	{
+		.name = "IPv4 TCP_SYN_RECV     inet_csk_listen_stop",
+		.family = AF_INET,
+		.state = BPF_TCP_SYN_RECV,
+		.drop_ack = true,
+		.expire_synack_timer = false,
+		.fastopen = true,
+	},
+	{
+		.name = "IPv4 TCP_NEW_SYN_RECV reqsk_timer_handler",
+		.family = AF_INET,
+		.state = BPF_TCP_NEW_SYN_RECV,
+		.drop_ack = true,
+		.expire_synack_timer = true,
+		.fastopen = false,
+	},
+	{
+		.name = "IPv4 TCP_NEW_SYN_RECV inet_csk_complete_hashdance",
+		.family = AF_INET,
+		.state = BPF_TCP_NEW_SYN_RECV,
+		.drop_ack = true,
+		.expire_synack_timer = false,
+		.fastopen = false,
+	},
+	{
+		.name = "IPv6 TCP_ESTABLISHED  inet_csk_listen_stop",
+		.family = AF_INET6,
+		.state = BPF_TCP_ESTABLISHED,
+		.drop_ack = false,
+		.expire_synack_timer = false,
+		.fastopen = false,
+	},
+	{
+		.name = "IPv6 TCP_SYN_RECV     inet_csk_listen_stop",
+		.family = AF_INET6,
+		.state = BPF_TCP_SYN_RECV,
+		.drop_ack = true,
+		.expire_synack_timer = false,
+		.fastopen = true,
+	},
+	{
+		.name = "IPv6 TCP_NEW_SYN_RECV reqsk_timer_handler",
+		.family = AF_INET6,
+		.state = BPF_TCP_NEW_SYN_RECV,
+		.drop_ack = true,
+		.expire_synack_timer = true,
+		.fastopen = false,
+	},
+	{
+		.name = "IPv6 TCP_NEW_SYN_RECV inet_csk_complete_hashdance",
+		.family = AF_INET6,
+		.state = BPF_TCP_NEW_SYN_RECV,
+		.drop_ack = true,
+		.expire_synack_timer = false,
+		.fastopen = false,
+	}
+};
+
+static void init_fds(__s64 fds[], int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++)
+		fds[i] = -1;
+}
+
+static void close_fds(__s64 fds[], int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++) {
+		if (fds[i] != -1) {
+			close(fds[i]);
+			fds[i] = -1;
+		}
+	}
+}
+
+static int setup_fastopen(char *buf, int size, int *saved_len, bool restore)
+{
+	int err = 0, fd, len;
+
+	fd = open("/proc/sys/net/ipv4/tcp_fastopen", O_RDWR);
+	if (!ASSERT_NEQ(fd, -1, "open"))
+		return -1;
+
+	if (restore) {
+		len = write(fd, buf, *saved_len);
+		if (!ASSERT_EQ(len, *saved_len, "write - restore"))
+			err = -1;
+	} else {
+		*saved_len = read(fd, buf, size);
+		if (!ASSERT_GE(*saved_len, 1, "read")) {
+			err = -1;
+			goto close;
+		}
+
+		err = lseek(fd, 0, SEEK_SET);
+		if (!ASSERT_OK(err, "lseek"))
+			goto close;
+
+		/* (TFO_CLIENT_ENABLE | TFO_SERVER_ENABLE |
+		 *  TFO_CLIENT_NO_COOKIE | TFO_SERVER_COOKIE_NOT_REQD)
+		 */
+		len = write(fd, "519", 3);
+		if (!ASSERT_EQ(len, 3, "write - setup"))
+			err = -1;
+	}
+
+close:
+	close(fd);
+
+	return err;
+}
+
+static int drop_ack(struct migrate_reuseport_test_case *test_case,
+		    struct test_migrate_reuseport *skel)
+{
+	if (test_case->family == AF_INET)
+		skel->bss->server_port = ((struct sockaddr_in *)
+					  &test_case->addr)->sin_port;
+	else
+		skel->bss->server_port = ((struct sockaddr_in6 *)
+					  &test_case->addr)->sin6_port;
+
+	test_case->link = bpf_program__attach_xdp(skel->progs.drop_ack,
+						  IFINDEX_LO);
+	if (!ASSERT_OK_PTR(test_case->link, "bpf_program__attach_xdp"))
+		return -1;
+
+	return 0;
+}
+
+static int pass_ack(struct migrate_reuseport_test_case *test_case)
+{
+	int err;
+
+	err = bpf_link__detach(test_case->link);
+	if (!ASSERT_OK(err, "bpf_link__detach"))
+		return -1;
+
+	test_case->link = NULL;
+
+	return 0;
+}
+
+static int start_servers(struct migrate_reuseport_test_case *test_case,
+			 struct test_migrate_reuseport *skel)
+{
+	int i, err, prog_fd, reuseport = 1, qlen = QLEN;
+
+	prog_fd = bpf_program__fd(skel->progs.migrate_reuseport);
+
+	make_sockaddr(test_case->family,
+		      test_case->family == AF_INET ? "127.0.0.1" : "::1", 0,
+		      &test_case->addr, &test_case->addrlen);
+
+	for (i = 0; i < NR_SERVERS; i++) {
+		test_case->servers[i] = socket(test_case->family, SOCK_STREAM,
+					       IPPROTO_TCP);
+		if (!ASSERT_NEQ(test_case->servers[i], -1, "socket"))
+			return -1;
+
+		err = setsockopt(test_case->servers[i], SOL_SOCKET,
+				 SO_REUSEPORT, &reuseport, sizeof(reuseport));
+		if (!ASSERT_OK(err, "setsockopt - SO_REUSEPORT"))
+			return -1;
+
+		err = bind(test_case->servers[i],
+			   (struct sockaddr *)&test_case->addr,
+			   test_case->addrlen);
+		if (!ASSERT_OK(err, "bind"))
+			return -1;
+
+		if (i == 0) {
+			err = setsockopt(test_case->servers[i], SOL_SOCKET,
+					 SO_ATTACH_REUSEPORT_EBPF,
+					 &prog_fd, sizeof(prog_fd));
+			if (!ASSERT_OK(err,
+				       "setsockopt - SO_ATTACH_REUSEPORT_EBPF"))
+				return -1;
+
+			err = getsockname(test_case->servers[i],
+					  (struct sockaddr *)&test_case->addr,
+					  &test_case->addrlen);
+			if (!ASSERT_OK(err, "getsockname"))
+				return -1;
+		}
+
+		if (test_case->fastopen) {
+			err = setsockopt(test_case->servers[i],
+					 SOL_TCP, TCP_FASTOPEN,
+					 &qlen, sizeof(qlen));
+			if (!ASSERT_OK(err, "setsockopt - TCP_FASTOPEN"))
+				return -1;
+		}
+
+		/* All requests will be tied to the first four listeners */
+		if (i != MIGRATED_TO) {
+			err = listen(test_case->servers[i], qlen);
+			if (!ASSERT_OK(err, "listen"))
+				return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int start_clients(struct migrate_reuseport_test_case *test_case)
+{
+	char buf[MSGLEN] = MSG;
+	int i, err;
+
+	for (i = 0; i < NR_CLIENTS; i++) {
+		test_case->clients[i] = socket(test_case->family, SOCK_STREAM,
+					       IPPROTO_TCP);
+		if (!ASSERT_NEQ(test_case->clients[i], -1, "socket"))
+			return -1;
+
+		/* The attached XDP program drops only the final ACK, so
+		 * clients will transition to TCP_ESTABLISHED immediately.
+		 */
+		err = settimeo(test_case->clients[i], 100);
+		if (!ASSERT_OK(err, "settimeo"))
+			return -1;
+
+		if (test_case->fastopen) {
+			int fastopen = 1;
+
+			err = setsockopt(test_case->clients[i], IPPROTO_TCP,
+					 TCP_FASTOPEN_CONNECT, &fastopen,
+					 sizeof(fastopen));
+			if (!ASSERT_OK(err,
+				       "setsockopt - TCP_FASTOPEN_CONNECT"))
+				return -1;
+		}
+
+		err = connect(test_case->clients[i],
+			      (struct sockaddr *)&test_case->addr,
+			      test_case->addrlen);
+		if (!ASSERT_OK(err, "connect"))
+			return -1;
+
+		err = write(test_case->clients[i], buf, MSGLEN);
+		if (!ASSERT_EQ(err, MSGLEN, "write"))
+			return -1;
+	}
+
+	return 0;
+}
+
+static int update_maps(struct migrate_reuseport_test_case *test_case,
+		       struct test_migrate_reuseport *skel)
+{
+	int i, err, migrated_to = MIGRATED_TO;
+	int reuseport_map_fd, migrate_map_fd;
+	__u64 value;
+
+	reuseport_map_fd = bpf_map__fd(skel->maps.reuseport_map);
+	migrate_map_fd = bpf_map__fd(skel->maps.migrate_map);
+
+	for (i = 0; i < NR_SERVERS; i++) {
+		value = (__u64)test_case->servers[i];
+		err = bpf_map_update_elem(reuseport_map_fd, &i, &value,
+					  BPF_NOEXIST);
+		if (!ASSERT_OK(err, "bpf_map_update_elem - reuseport_map"))
+			return -1;
+
+		err = bpf_map_lookup_elem(reuseport_map_fd, &i, &value);
+		if (!ASSERT_OK(err, "bpf_map_lookup_elem - reuseport_map"))
+			return -1;
+
+		err = bpf_map_update_elem(migrate_map_fd, &value, &migrated_to,
+					  BPF_NOEXIST);
+		if (!ASSERT_OK(err, "bpf_map_update_elem - migrate_map"))
+			return -1;
+	}
+
+	return 0;
+}
+
+static int migrate_dance(struct migrate_reuseport_test_case *test_case)
+{
+	int i, err;
+
+	/* Migrate TCP_ESTABLISHED and TCP_SYN_RECV requests
+	 * to the last listener based on eBPF.
+	 */
+	for (i = 0; i < MIGRATED_TO; i++) {
+		err = shutdown(test_case->servers[i], SHUT_RDWR);
+		if (!ASSERT_OK(err, "shutdown"))
+			return -1;
+	}
+
+	/* No dance for TCP_NEW_SYN_RECV to migrate based on eBPF */
+	if (test_case->state == BPF_TCP_NEW_SYN_RECV)
+		return 0;
+
+	/* Note that we use the second listener instead of the
+	 * first one here.
+	 *
+	 * The fist listener is bind()ed with port 0 and,
+	 * SOCK_BINDPORT_LOCK is not set to sk_userlocks, so
+	 * calling listen() again will bind() the first listener
+	 * on a new ephemeral port and detach it from the existing
+	 * reuseport group.  (See: __inet_bind(), tcp_set_state())
+	 *
+	 * OTOH, the second one is bind()ed with a specific port,
+	 * and SOCK_BINDPORT_LOCK is set. Thus, re-listen() will
+	 * resurrect the listener on the existing reuseport group.
+	 */
+	err = listen(test_case->servers[1], QLEN);
+	if (!ASSERT_OK(err, "listen"))
+		return -1;
+
+	/* Migrate from the last listener to the second one.
+	 *
+	 * All listeners were detached out of the reuseport_map,
+	 * so migration will be done by kernel random pick from here.
+	 */
+	err = shutdown(test_case->servers[MIGRATED_TO], SHUT_RDWR);
+	if (!ASSERT_OK(err, "shutdown"))
+		return -1;
+
+	/* Back to the existing reuseport group */
+	err = listen(test_case->servers[MIGRATED_TO], QLEN);
+	if (!ASSERT_OK(err, "listen"))
+		return -1;
+
+	/* Migrate back to the last one from the second one */
+	err = shutdown(test_case->servers[1], SHUT_RDWR);
+	if (!ASSERT_OK(err, "shutdown"))
+		return -1;
+
+	return 0;
+}
+
+static void count_requests(struct migrate_reuseport_test_case *test_case,
+			   struct test_migrate_reuseport *skel)
+{
+	struct sockaddr_storage addr;
+	socklen_t len = sizeof(addr);
+	int err, cnt = 0, client;
+	char buf[MSGLEN];
+
+	err = settimeo(test_case->servers[MIGRATED_TO], 4000);
+	if (!ASSERT_OK(err, "settimeo"))
+		goto out;
+
+	for (; cnt < NR_CLIENTS; cnt++) {
+		client = accept(test_case->servers[MIGRATED_TO],
+				(struct sockaddr *)&addr, &len);
+		if (!ASSERT_NEQ(client, -1, "accept"))
+			goto out;
+
+		memset(buf, 0, MSGLEN);
+		read(client, &buf, MSGLEN);
+		close(client);
+
+		if (!ASSERT_STREQ(buf, MSG, "read"))
+			goto out;
+	}
+
+out:
+	ASSERT_EQ(cnt, NR_CLIENTS, "count in userspace");
+
+	switch (test_case->state) {
+	case BPF_TCP_ESTABLISHED:
+		cnt = skel->bss->migrated_at_close;
+		break;
+	case BPF_TCP_SYN_RECV:
+		cnt = skel->bss->migrated_at_close_fastopen;
+		break;
+	case BPF_TCP_NEW_SYN_RECV:
+		if (test_case->expire_synack_timer)
+			cnt = skel->bss->migrated_at_send_synack;
+		else
+			cnt = skel->bss->migrated_at_recv_ack;
+		break;
+	default:
+		cnt = 0;
+	}
+
+	ASSERT_EQ(cnt, NR_CLIENTS, "count in BPF prog");
+}
+
+static void run_test(struct migrate_reuseport_test_case *test_case,
+		     struct test_migrate_reuseport *skel)
+{
+	int err, saved_len;
+	char buf[16];
+
+	skel->bss->migrated_at_close = 0;
+	skel->bss->migrated_at_close_fastopen = 0;
+	skel->bss->migrated_at_send_synack = 0;
+	skel->bss->migrated_at_recv_ack = 0;
+
+	init_fds(test_case->servers, NR_SERVERS);
+	init_fds(test_case->clients, NR_CLIENTS);
+
+	if (test_case->fastopen) {
+		memset(buf, 0, sizeof(buf));
+
+		err = setup_fastopen(buf, sizeof(buf), &saved_len, false);
+		if (!ASSERT_OK(err, "setup_fastopen - setup"))
+			return;
+	}
+
+	err = start_servers(test_case, skel);
+	if (!ASSERT_OK(err, "start_servers"))
+		goto close_servers;
+
+	if (test_case->drop_ack) {
+		/* Drop the final ACK of the 3-way handshake and stick the
+		 * in-flight requests on TCP_SYN_RECV or TCP_NEW_SYN_RECV.
+		 */
+		err = drop_ack(test_case, skel);
+		if (!ASSERT_OK(err, "drop_ack"))
+			goto close_servers;
+	}
+
+	/* Tie requests to the first four listners */
+	err = start_clients(test_case);
+	if (!ASSERT_OK(err, "start_clients"))
+		goto close_clients;
+
+	err = listen(test_case->servers[MIGRATED_TO], QLEN);
+	if (!ASSERT_OK(err, "listen"))
+		goto close_clients;
+
+	err = update_maps(test_case, skel);
+	if (!ASSERT_OK(err, "fill_maps"))
+		goto close_clients;
+
+	/* Migrate the requests in the accept queue only.
+	 * TCP_NEW_SYN_RECV requests are not migrated at this point.
+	 */
+	err = migrate_dance(test_case);
+	if (!ASSERT_OK(err, "migrate_dance"))
+		goto close_clients;
+
+	if (test_case->expire_synack_timer) {
+		/* Wait for SYN+ACK timers to expire so that
+		 * reqsk_timer_handler() migrates TCP_NEW_SYN_RECV requests.
+		 */
+		sleep(1);
+	}
+
+	if (test_case->link) {
+		/* Resume 3WHS and migrate TCP_NEW_SYN_RECV requests */
+		err = pass_ack(test_case);
+		if (!ASSERT_OK(err, "pass_ack"))
+			goto close_clients;
+	}
+
+	count_requests(test_case, skel);
+
+close_clients:
+	close_fds(test_case->clients, NR_CLIENTS);
+
+	if (test_case->link) {
+		err = pass_ack(test_case);
+		ASSERT_OK(err, "pass_ack - clean up");
+	}
+
+close_servers:
+	close_fds(test_case->servers, NR_SERVERS);
+
+	if (test_case->fastopen) {
+		err = setup_fastopen(buf, sizeof(buf), &saved_len, true);
+		ASSERT_OK(err, "setup_fastopen - restore");
+	}
+}
+
+void test_migrate_reuseport(void)
+{
+	struct test_migrate_reuseport *skel;
+	int i;
+
+	skel = test_migrate_reuseport__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
+		test__start_subtest(test_cases[i].name);
+		run_test(&test_cases[i], skel);
+	}
+
+	test_migrate_reuseport__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/obj_name.c b/tools/testing/selftests/bpf/prog_tests/obj_name.c
index e178416bddad..6194b776a28b 100644
--- a/tools/testing/selftests/bpf/prog_tests/obj_name.c
+++ b/tools/testing/selftests/bpf/prog_tests/obj_name.c
@@ -38,13 +38,13 @@ void test_obj_name(void)
 
 		fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
 		CHECK((tests[i].success && fd < 0) ||
-		      (!tests[i].success && fd != -1) ||
+		      (!tests[i].success && fd >= 0) ||
 		      (!tests[i].success && errno != tests[i].expected_errno),
 		      "check-bpf-prog-name",
 		      "fd %d(%d) errno %d(%d)\n",
 		       fd, tests[i].success, errno, tests[i].expected_errno);
 
-		if (fd != -1)
+		if (fd >= 0)
 			close(fd);
 
 		/* test different attr.map_name during BPF_MAP_CREATE */
@@ -59,13 +59,13 @@ void test_obj_name(void)
 		memcpy(attr.map_name, tests[i].name, ncopy);
 		fd = syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr));
 		CHECK((tests[i].success && fd < 0) ||
-		      (!tests[i].success && fd != -1) ||
+		      (!tests[i].success && fd >= 0) ||
 		      (!tests[i].success && errno != tests[i].expected_errno),
 		      "check-bpf-map-name",
 		      "fd %d(%d) errno %d(%d)\n",
 		      fd, tests[i].success, errno, tests[i].expected_errno);
 
-		if (fd != -1)
+		if (fd >= 0)
 			close(fd);
 	}
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_branches.c b/tools/testing/selftests/bpf/prog_tests/perf_branches.c
index e35c444902a7..12c4f45cee1a 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_branches.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_branches.c
@@ -74,7 +74,7 @@ static void test_perf_branches_common(int perf_fd,
 
 	/* attach perf_event */
 	link = bpf_program__attach_perf_event(skel->progs.perf_branches, perf_fd);
-	if (CHECK(IS_ERR(link), "attach_perf_event", "err %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "attach_perf_event"))
 		goto out_destroy_skel;
 
 	/* generate some branches on cpu 0 */
@@ -119,7 +119,7 @@ static void test_perf_branches_hw(void)
 	 * Some setups don't support branch records (virtual machines, !x86),
 	 * so skip test in this case.
 	 */
-	if (pfd == -1) {
+	if (pfd < 0) {
 		if (errno == ENOENT || errno == EOPNOTSUPP) {
 			printf("%s:SKIP:no PERF_SAMPLE_BRANCH_STACK\n",
 			       __func__);
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
index ca9f0895ec84..6490e9673002 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@@ -80,7 +80,7 @@ void test_perf_buffer(void)
 	pb_opts.sample_cb = on_sample;
 	pb_opts.ctx = &cpu_seen;
 	pb = perf_buffer__new(bpf_map__fd(skel->maps.perf_buf_map), 1, &pb_opts);
-	if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb)))
+	if (!ASSERT_OK_PTR(pb, "perf_buf__new"))
 		goto out_close;
 
 	CHECK(perf_buffer__epoll_fd(pb) < 0, "epoll_fd",
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c b/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c
index 72c3690844fb..33144c9432ae 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c
@@ -97,8 +97,7 @@ void test_perf_event_stackmap(void)
 
 	skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu,
 							   pmu_fd);
-	if (CHECK(IS_ERR(skel->links.oncpu), "attach_perf_event",
-		  "err %ld\n", PTR_ERR(skel->links.oncpu))) {
+	if (!ASSERT_OK_PTR(skel->links.oncpu, "attach_perf_event")) {
 		close(pmu_fd);
 		goto cleanup;
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/probe_user.c b/tools/testing/selftests/bpf/prog_tests/probe_user.c
index 7aecfd9e87d1..95bd12097358 100644
--- a/tools/testing/selftests/bpf/prog_tests/probe_user.c
+++ b/tools/testing/selftests/bpf/prog_tests/probe_user.c
@@ -15,7 +15,7 @@ void test_probe_user(void)
 	static const int zero = 0;
 
 	obj = bpf_object__open_file(obj_file, &opts);
-	if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj)))
+	if (!ASSERT_OK_PTR(obj, "obj_open_file"))
 		return;
 
 	kprobe_prog = bpf_object__find_program_by_title(obj, prog_name);
@@ -33,11 +33,8 @@ void test_probe_user(void)
 		goto cleanup;
 
 	kprobe_link = bpf_program__attach(kprobe_prog);
-	if (CHECK(IS_ERR(kprobe_link), "attach_kprobe",
-		  "err %ld\n", PTR_ERR(kprobe_link))) {
-		kprobe_link = NULL;
+	if (!ASSERT_OK_PTR(kprobe_link, "attach_kprobe"))
 		goto cleanup;
-	}
 
 	memset(&curr, 0, sizeof(curr));
 	in->sin_family = AF_INET;
diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
index 131d7f7eeb42..89fc98faf19e 100644
--- a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
+++ b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
@@ -46,7 +46,7 @@ void test_prog_run_xattr(void)
 	tattr.prog_fd = bpf_program__fd(skel->progs.test_pkt_access);
 
 	err = bpf_prog_test_run_xattr(&tattr);
-	CHECK_ATTR(err != -1 || errno != ENOSPC || tattr.retval, "run",
+	CHECK_ATTR(err >= 0 || errno != ENOSPC || tattr.retval, "run",
 	      "err %d errno %d retval %d\n", err, errno, tattr.retval);
 
 	CHECK_ATTR(tattr.data_size_out != sizeof(pkt_v4), "data_size_out",
@@ -78,6 +78,6 @@ void test_prog_run_xattr(void)
 cleanup:
 	if (skel)
 		test_pkt_access__destroy(skel);
-	if (stats_fd != -1)
+	if (stats_fd >= 0)
 		close(stats_fd);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c
index c5fb191874ac..41720a62c4fa 100644
--- a/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c
+++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c
@@ -77,7 +77,7 @@ void test_raw_tp_test_run(void)
 	/* invalid cpu ID should fail with ENXIO */
 	opts.cpu = 0xffffffff;
 	err = bpf_prog_test_run_opts(prog_fd, &opts);
-	CHECK(err != -1 || errno != ENXIO,
+	CHECK(err >= 0 || errno != ENXIO,
 	      "test_run_opts_fail",
 	      "should failed with ENXIO\n");
 
@@ -85,7 +85,7 @@ void test_raw_tp_test_run(void)
 	opts.cpu = 1;
 	opts.flags = 0;
 	err = bpf_prog_test_run_opts(prog_fd, &opts);
-	CHECK(err != -1 || errno != EINVAL,
+	CHECK(err >= 0 || errno != EINVAL,
 	      "test_run_opts_fail",
 	      "should failed with EINVAL\n");
 
diff --git a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c
index 563e12120e77..5f9eaa3ab584 100644
--- a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c
+++ b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c
@@ -30,7 +30,7 @@ void test_rdonly_maps(void)
 	struct bss bss;
 
 	obj = bpf_object__open_file(file, NULL);
-	if (CHECK(IS_ERR(obj), "obj_open", "err %ld\n", PTR_ERR(obj)))
+	if (!ASSERT_OK_PTR(obj, "obj_open"))
 		return;
 
 	err = bpf_object__load(obj);
@@ -58,11 +58,8 @@ void test_rdonly_maps(void)
 			goto cleanup;
 
 		link = bpf_program__attach_raw_tracepoint(prog, "sys_enter");
-		if (CHECK(IS_ERR(link), "attach_prog", "prog '%s', err %ld\n",
-			  t->prog_name, PTR_ERR(link))) {
-			link = NULL;
+		if (!ASSERT_OK_PTR(link, "attach_prog"))
 			goto cleanup;
-		}
 
 		/* trigger probe */
 		usleep(1);
diff --git a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
index ac1ee10cffd8..de2688166696 100644
--- a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
+++ b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
@@ -15,7 +15,7 @@ void test_reference_tracking(void)
 	int err = 0;
 
 	obj = bpf_object__open_file(file, &open_opts);
-	if (CHECK_FAIL(IS_ERR(obj)))
+	if (!ASSERT_OK_PTR(obj, "obj_open_file"))
 		return;
 
 	if (CHECK(strcmp(bpf_object__name(obj), obj_name), "obj_name",
diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
index d3c2de2c24d1..f62361306f6d 100644
--- a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
+++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
@@ -76,7 +76,7 @@ __resolve_symbol(struct btf *btf, int type_id)
 	}
 
 	for (i = 0; i < ARRAY_SIZE(test_symbols); i++) {
-		if (test_symbols[i].id != -1)
+		if (test_symbols[i].id >= 0)
 			continue;
 
 		if (BTF_INFO_KIND(type->info) != test_symbols[i].type)
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index f9a8ae331963..a01788090c31 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -12,7 +12,7 @@
 #include <sys/sysinfo.h>
 #include <linux/perf_event.h>
 #include <linux/ring_buffer.h>
-#include "test_ringbuf.skel.h"
+#include "test_ringbuf.lskel.h"
 
 #define EDONE 7777
 
@@ -94,9 +94,7 @@ void test_ringbuf(void)
 	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
 		return;
 
-	err = bpf_map__set_max_entries(skel->maps.ringbuf, page_size);
-	if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n"))
-		goto cleanup;
+	skel->maps.ringbuf.max_entries = page_size;
 
 	err = test_ringbuf__load(skel);
 	if (CHECK(err != 0, "skel_load", "skeleton load failed\n"))
@@ -151,7 +149,7 @@ void test_ringbuf(void)
 	/* only trigger BPF program for current process */
 	skel->bss->pid = getpid();
 
-	ringbuf = ring_buffer__new(bpf_map__fd(skel->maps.ringbuf),
+	ringbuf = ring_buffer__new(skel->maps.ringbuf.map_fd,
 				   process_sample, NULL, NULL);
 	if (CHECK(!ringbuf, "ringbuf_create", "failed to create ringbuf\n"))
 		goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
index cef63e703924..167cd8a2edfd 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
@@ -63,7 +63,7 @@ void test_ringbuf_multi(void)
 		goto cleanup;
 
 	proto_fd = bpf_create_map(BPF_MAP_TYPE_RINGBUF, 0, 0, page_size, 0);
-	if (CHECK(proto_fd == -1, "bpf_create_map", "bpf_create_map failed\n"))
+	if (CHECK(proto_fd < 0, "bpf_create_map", "bpf_create_map failed\n"))
 		goto cleanup;
 
 	err = bpf_map__set_inner_map_fd(skel->maps.ringbuf_hash, proto_fd);
diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
index 821b4146b7b6..4efd337d6a3c 100644
--- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
+++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
@@ -78,7 +78,7 @@ static int create_maps(enum bpf_map_type inner_type)
 	attr.max_entries = REUSEPORT_ARRAY_SIZE;
 
 	reuseport_array = bpf_create_map_xattr(&attr);
-	RET_ERR(reuseport_array == -1, "creating reuseport_array",
+	RET_ERR(reuseport_array < 0, "creating reuseport_array",
 		"reuseport_array:%d errno:%d\n", reuseport_array, errno);
 
 	/* Creating outer_map */
@@ -89,7 +89,7 @@ static int create_maps(enum bpf_map_type inner_type)
 	attr.max_entries = 1;
 	attr.inner_map_fd = reuseport_array;
 	outer_map = bpf_create_map_xattr(&attr);
-	RET_ERR(outer_map == -1, "creating outer_map",
+	RET_ERR(outer_map < 0, "creating outer_map",
 		"outer_map:%d errno:%d\n", outer_map, errno);
 
 	return 0;
@@ -102,8 +102,9 @@ static int prepare_bpf_obj(void)
 	int err;
 
 	obj = bpf_object__open("test_select_reuseport_kern.o");
-	RET_ERR(IS_ERR_OR_NULL(obj), "open test_select_reuseport_kern.o",
-		"obj:%p PTR_ERR(obj):%ld\n", obj, PTR_ERR(obj));
+	err = libbpf_get_error(obj);
+	RET_ERR(err, "open test_select_reuseport_kern.o",
+		"obj:%p PTR_ERR(obj):%d\n", obj, err);
 
 	map = bpf_object__find_map_by_name(obj, "outer_map");
 	RET_ERR(!map, "find outer_map", "!map\n");
@@ -116,31 +117,31 @@ static int prepare_bpf_obj(void)
 	prog = bpf_program__next(NULL, obj);
 	RET_ERR(!prog, "get first bpf_program", "!prog\n");
 	select_by_skb_data_prog = bpf_program__fd(prog);
-	RET_ERR(select_by_skb_data_prog == -1, "get prog fd",
+	RET_ERR(select_by_skb_data_prog < 0, "get prog fd",
 		"select_by_skb_data_prog:%d\n", select_by_skb_data_prog);
 
 	map = bpf_object__find_map_by_name(obj, "result_map");
 	RET_ERR(!map, "find result_map", "!map\n");
 	result_map = bpf_map__fd(map);
-	RET_ERR(result_map == -1, "get result_map fd",
+	RET_ERR(result_map < 0, "get result_map fd",
 		"result_map:%d\n", result_map);
 
 	map = bpf_object__find_map_by_name(obj, "tmp_index_ovr_map");
 	RET_ERR(!map, "find tmp_index_ovr_map\n", "!map");
 	tmp_index_ovr_map = bpf_map__fd(map);
-	RET_ERR(tmp_index_ovr_map == -1, "get tmp_index_ovr_map fd",
+	RET_ERR(tmp_index_ovr_map < 0, "get tmp_index_ovr_map fd",
 		"tmp_index_ovr_map:%d\n", tmp_index_ovr_map);
 
 	map = bpf_object__find_map_by_name(obj, "linum_map");
 	RET_ERR(!map, "find linum_map", "!map\n");
 	linum_map = bpf_map__fd(map);
-	RET_ERR(linum_map == -1, "get linum_map fd",
+	RET_ERR(linum_map < 0, "get linum_map fd",
 		"linum_map:%d\n", linum_map);
 
 	map = bpf_object__find_map_by_name(obj, "data_check_map");
 	RET_ERR(!map, "find data_check_map", "!map\n");
 	data_check_map = bpf_map__fd(map);
-	RET_ERR(data_check_map == -1, "get data_check_map fd",
+	RET_ERR(data_check_map < 0, "get data_check_map fd",
 		"data_check_map:%d\n", data_check_map);
 
 	return 0;
@@ -237,7 +238,7 @@ static long get_linum(void)
 	int err;
 
 	err = bpf_map_lookup_elem(linum_map, &index_zero, &linum);
-	RET_ERR(err == -1, "lookup_elem(linum_map)", "err:%d errno:%d\n",
+	RET_ERR(err < 0, "lookup_elem(linum_map)", "err:%d errno:%d\n",
 		err, errno);
 
 	return linum;
@@ -254,11 +255,11 @@ static void check_data(int type, sa_family_t family, const struct cmd *cmd,
 	addrlen = sizeof(cli_sa);
 	err = getsockname(cli_fd, (struct sockaddr *)&cli_sa,
 			  &addrlen);
-	RET_IF(err == -1, "getsockname(cli_fd)", "err:%d errno:%d\n",
+	RET_IF(err < 0, "getsockname(cli_fd)", "err:%d errno:%d\n",
 	       err, errno);
 
 	err = bpf_map_lookup_elem(data_check_map, &index_zero, &result);
-	RET_IF(err == -1, "lookup_elem(data_check_map)", "err:%d errno:%d\n",
+	RET_IF(err < 0, "lookup_elem(data_check_map)", "err:%d errno:%d\n",
 	       err, errno);
 
 	if (type == SOCK_STREAM) {
@@ -347,7 +348,7 @@ static void check_results(void)
 
 	for (i = 0; i < NR_RESULTS; i++) {
 		err = bpf_map_lookup_elem(result_map, &i, &results[i]);
-		RET_IF(err == -1, "lookup_elem(result_map)",
+		RET_IF(err < 0, "lookup_elem(result_map)",
 		       "i:%u err:%d errno:%d\n", i, err, errno);
 	}
 
@@ -524,12 +525,12 @@ static void test_syncookie(int type, sa_family_t family)
 	 */
 	err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero,
 				  &tmp_index, BPF_ANY);
-	RET_IF(err == -1, "update_elem(tmp_index_ovr_map, 0, 1)",
+	RET_IF(err < 0, "update_elem(tmp_index_ovr_map, 0, 1)",
 	       "err:%d errno:%d\n", err, errno);
 	do_test(type, family, &cmd, PASS);
 	err = bpf_map_lookup_elem(tmp_index_ovr_map, &index_zero,
 				  &tmp_index);
-	RET_IF(err == -1 || tmp_index != -1,
+	RET_IF(err < 0 || tmp_index >= 0,
 	       "lookup_elem(tmp_index_ovr_map)",
 	       "err:%d errno:%d tmp_index:%d\n",
 	       err, errno, tmp_index);
@@ -569,7 +570,7 @@ static void test_detach_bpf(int type, sa_family_t family)
 
 	for (i = 0; i < NR_RESULTS; i++) {
 		err = bpf_map_lookup_elem(result_map, &i, &tmp);
-		RET_IF(err == -1, "lookup_elem(result_map)",
+		RET_IF(err < 0, "lookup_elem(result_map)",
 		       "i:%u err:%d errno:%d\n", i, err, errno);
 		nr_run_before += tmp;
 	}
@@ -584,7 +585,7 @@ static void test_detach_bpf(int type, sa_family_t family)
 
 	for (i = 0; i < NR_RESULTS; i++) {
 		err = bpf_map_lookup_elem(result_map, &i, &tmp);
-		RET_IF(err == -1, "lookup_elem(result_map)",
+		RET_IF(err < 0, "lookup_elem(result_map)",
 		       "i:%u err:%d errno:%d\n", i, err, errno);
 		nr_run_after += tmp;
 	}
@@ -632,24 +633,24 @@ static void prepare_sk_fds(int type, sa_family_t family, bool inany)
 					 SO_ATTACH_REUSEPORT_EBPF,
 					 &select_by_skb_data_prog,
 					 sizeof(select_by_skb_data_prog));
-			RET_IF(err == -1, "setsockopt(SO_ATTACH_REUEPORT_EBPF)",
+			RET_IF(err < 0, "setsockopt(SO_ATTACH_REUEPORT_EBPF)",
 			       "err:%d errno:%d\n", err, errno);
 		}
 
 		err = bind(sk_fds[i], (struct sockaddr *)&srv_sa, addrlen);
-		RET_IF(err == -1, "bind()", "sk_fds[%d] err:%d errno:%d\n",
+		RET_IF(err < 0, "bind()", "sk_fds[%d] err:%d errno:%d\n",
 		       i, err, errno);
 
 		if (type == SOCK_STREAM) {
 			err = listen(sk_fds[i], 10);
-			RET_IF(err == -1, "listen()",
+			RET_IF(err < 0, "listen()",
 			       "sk_fds[%d] err:%d errno:%d\n",
 			       i, err, errno);
 		}
 
 		err = bpf_map_update_elem(reuseport_array, &i, &sk_fds[i],
 					  BPF_NOEXIST);
-		RET_IF(err == -1, "update_elem(reuseport_array)",
+		RET_IF(err < 0, "update_elem(reuseport_array)",
 		       "sk_fds[%d] err:%d errno:%d\n", i, err, errno);
 
 		if (i == first) {
@@ -682,7 +683,7 @@ static void setup_per_test(int type, sa_family_t family, bool inany,
 	prepare_sk_fds(type, family, inany);
 	err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero, &ovr,
 				  BPF_ANY);
-	RET_IF(err == -1, "update_elem(tmp_index_ovr_map, 0, -1)",
+	RET_IF(err < 0, "update_elem(tmp_index_ovr_map, 0, -1)",
 	       "err:%d errno:%d\n", err, errno);
 
 	/* Install reuseport_array to outer_map? */
@@ -691,7 +692,7 @@ static void setup_per_test(int type, sa_family_t family, bool inany,
 
 	err = bpf_map_update_elem(outer_map, &index_zero, &reuseport_array,
 				  BPF_ANY);
-	RET_IF(err == -1, "update_elem(outer_map, 0, reuseport_array)",
+	RET_IF(err < 0, "update_elem(outer_map, 0, reuseport_array)",
 	       "err:%d errno:%d\n", err, errno);
 }
 
@@ -720,18 +721,18 @@ static void cleanup_per_test(bool no_inner_map)
 		return;
 
 	err = bpf_map_delete_elem(outer_map, &index_zero);
-	RET_IF(err == -1, "delete_elem(outer_map)",
+	RET_IF(err < 0, "delete_elem(outer_map)",
 	       "err:%d errno:%d\n", err, errno);
 }
 
 static void cleanup(void)
 {
-	if (outer_map != -1) {
+	if (outer_map >= 0) {
 		close(outer_map);
 		outer_map = -1;
 	}
 
-	if (reuseport_array != -1) {
+	if (reuseport_array >= 0) {
 		close(reuseport_array);
 		reuseport_array = -1;
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c
index 7043e6ded0e6..023cc532992d 100644
--- a/tools/testing/selftests/bpf/prog_tests/send_signal.c
+++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c
@@ -2,7 +2,7 @@
 #include <test_progs.h>
 #include "test_send_signal_kern.skel.h"
 
-static volatile int sigusr1_received = 0;
+int sigusr1_received = 0;
 
 static void sigusr1_handler(int signum)
 {
@@ -91,8 +91,7 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 
 		skel->links.send_signal_perf =
 			bpf_program__attach_perf_event(skel->progs.send_signal_perf, pmu_fd);
-		if (CHECK(IS_ERR(skel->links.send_signal_perf), "attach_perf_event",
-			  "err %ld\n", PTR_ERR(skel->links.send_signal_perf)))
+		if (!ASSERT_OK_PTR(skel->links.send_signal_perf, "attach_perf_event"))
 			goto disable_pmu;
 	}
 
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
index 45c82db3c58c..aee41547e7f4 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
@@ -480,7 +480,7 @@ static struct bpf_link *attach_lookup_prog(struct bpf_program *prog)
 	}
 
 	link = bpf_program__attach_netns(prog, net_fd);
-	if (CHECK(IS_ERR(link), "bpf_program__attach_netns", "failed\n")) {
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_netns")) {
 		errno = -PTR_ERR(link);
 		log_err("failed to attach program '%s' to netns",
 			bpf_program__name(prog));
diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c
index fe87b77af459..f6f130c99b8c 100644
--- a/tools/testing/selftests/bpf/prog_tests/skeleton.c
+++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c
@@ -82,10 +82,8 @@ void test_skeleton(void)
 	CHECK(data->out2 != 2, "res2", "got %lld != exp %d\n", data->out2, 2);
 	CHECK(bss->out3 != 3, "res3", "got %d != exp %d\n", (int)bss->out3, 3);
 	CHECK(bss->out4 != 4, "res4", "got %lld != exp %d\n", bss->out4, 4);
-	CHECK(bss->handler_out5.a != 5, "res5", "got %d != exp %d\n",
-	      bss->handler_out5.a, 5);
-	CHECK(bss->handler_out5.b != 6, "res6", "got %lld != exp %d\n",
-	      bss->handler_out5.b, 6);
+	CHECK(bss->out5.a != 5, "res5", "got %d != exp %d\n", bss->out5.a, 5);
+	CHECK(bss->out5.b != 6, "res6", "got %lld != exp %d\n", bss->out5.b, 6);
 	CHECK(bss->out6 != 14, "res7", "got %d != exp %d\n", bss->out6, 14);
 
 	CHECK(bss->bpf_syscall != kcfg->CONFIG_BPF_SYSCALL, "ext1",
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_fields.c b/tools/testing/selftests/bpf/prog_tests/sock_fields.c
index af87118e748e..577d619fb07e 100644
--- a/tools/testing/selftests/bpf/prog_tests/sock_fields.c
+++ b/tools/testing/selftests/bpf/prog_tests/sock_fields.c
@@ -97,12 +97,12 @@ static void check_result(void)
 
 	err = bpf_map_lookup_elem(linum_map_fd, &egress_linum_idx,
 				  &egress_linum);
-	CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)",
+	CHECK(err < 0, "bpf_map_lookup_elem(linum_map_fd)",
 	      "err:%d errno:%d\n", err, errno);
 
 	err = bpf_map_lookup_elem(linum_map_fd, &ingress_linum_idx,
 				  &ingress_linum);
-	CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)",
+	CHECK(err < 0, "bpf_map_lookup_elem(linum_map_fd)",
 	      "err:%d errno:%d\n", err, errno);
 
 	memcpy(&srv_sk, &skel->bss->srv_sk, sizeof(srv_sk));
@@ -355,14 +355,12 @@ void test_sock_fields(void)
 
 	egress_link = bpf_program__attach_cgroup(skel->progs.egress_read_sock_fields,
 						 child_cg_fd);
-	if (CHECK(IS_ERR(egress_link), "attach_cgroup(egress)", "err:%ld\n",
-		  PTR_ERR(egress_link)))
+	if (!ASSERT_OK_PTR(egress_link, "attach_cgroup(egress)"))
 		goto done;
 
 	ingress_link = bpf_program__attach_cgroup(skel->progs.ingress_read_sock_fields,
 						  child_cg_fd);
-	if (CHECK(IS_ERR(ingress_link), "attach_cgroup(ingress)", "err:%ld\n",
-		  PTR_ERR(ingress_link)))
+	if (!ASSERT_OK_PTR(ingress_link, "attach_cgroup(ingress)"))
 		goto done;
 
 	linum_map_fd = bpf_map__fd(skel->maps.linum_map);
@@ -375,8 +373,8 @@ done:
 	bpf_link__destroy(egress_link);
 	bpf_link__destroy(ingress_link);
 	test_sock_fields__destroy(skel);
-	if (child_cg_fd != -1)
+	if (child_cg_fd >= 0)
 		close(child_cg_fd);
-	if (parent_cg_fd != -1)
+	if (parent_cg_fd >= 0)
 		close(parent_cg_fd);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index ab77596b64e3..1352ec104149 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -88,11 +88,11 @@ static void test_sockmap_create_update_free(enum bpf_map_type map_type)
 	int s, map, err;
 
 	s = connected_socket_v4();
-	if (CHECK_FAIL(s == -1))
+	if (CHECK_FAIL(s < 0))
 		return;
 
 	map = bpf_create_map(map_type, sizeof(int), sizeof(int), 1, 0);
-	if (CHECK_FAIL(map == -1)) {
+	if (CHECK_FAIL(map < 0)) {
 		perror("bpf_create_map");
 		goto out;
 	}
@@ -245,7 +245,7 @@ static void test_sockmap_copy(enum bpf_map_type map_type)
 	opts.link_info = &linfo;
 	opts.link_info_len = sizeof(linfo);
 	link = bpf_program__attach_iter(skel->progs.copy, &opts);
-	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+	if (!ASSERT_OK_PTR(link, "attach_iter"))
 		goto out;
 
 	iter_fd = bpf_iter_create(bpf_link__fd(link));
@@ -304,7 +304,7 @@ static void test_sockmap_skb_verdict_attach(enum bpf_attach_type first,
 	}
 
 	err = bpf_prog_attach(verdict, map, second, 0);
-	assert(err == -1 && errno == EBUSY);
+	ASSERT_EQ(err, -EBUSY, "prog_attach_fail");
 
 	err = bpf_prog_detach2(verdict, map, first);
 	if (CHECK_FAIL(err)) {
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
index 06b86addc181..7a0d64fdc192 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
@@ -98,7 +98,7 @@ static void run_tests(int family, enum bpf_map_type map_type)
 	int map;
 
 	map = bpf_create_map(map_type, sizeof(int), sizeof(int), 1, 0);
-	if (CHECK_FAIL(map == -1)) {
+	if (CHECK_FAIL(map < 0)) {
 		perror("bpf_map_create");
 		return;
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 648d9ae898d2..0f066b89b4af 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -139,7 +139,7 @@
 #define xbpf_map_delete_elem(fd, key)                                          \
 	({                                                                     \
 		int __ret = bpf_map_delete_elem((fd), (key));                  \
-		if (__ret == -1)                                               \
+		if (__ret < 0)                                               \
 			FAIL_ERRNO("map_delete");                              \
 		__ret;                                                         \
 	})
@@ -147,7 +147,7 @@
 #define xbpf_map_lookup_elem(fd, key, val)                                     \
 	({                                                                     \
 		int __ret = bpf_map_lookup_elem((fd), (key), (val));           \
-		if (__ret == -1)                                               \
+		if (__ret < 0)                                               \
 			FAIL_ERRNO("map_lookup");                              \
 		__ret;                                                         \
 	})
@@ -155,7 +155,7 @@
 #define xbpf_map_update_elem(fd, key, val, flags)                              \
 	({                                                                     \
 		int __ret = bpf_map_update_elem((fd), (key), (val), (flags));  \
-		if (__ret == -1)                                               \
+		if (__ret < 0)                                               \
 			FAIL_ERRNO("map_update");                              \
 		__ret;                                                         \
 	})
@@ -164,7 +164,7 @@
 	({                                                                     \
 		int __ret =                                                    \
 			bpf_prog_attach((prog), (target), (type), (flags));    \
-		if (__ret == -1)                                               \
+		if (__ret < 0)                                               \
 			FAIL_ERRNO("prog_attach(" #type ")");                  \
 		__ret;                                                         \
 	})
@@ -172,7 +172,7 @@
 #define xbpf_prog_detach2(prog, target, type)                                  \
 	({                                                                     \
 		int __ret = bpf_prog_detach2((prog), (target), (type));        \
-		if (__ret == -1)                                               \
+		if (__ret < 0)                                               \
 			FAIL_ERRNO("prog_detach2(" #type ")");                 \
 		__ret;                                                         \
 	})
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
index 11a769e18f5d..0a91d8d9954b 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
@@ -62,8 +62,7 @@ retry:
 
 	skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu,
 							   pmu_fd);
-	if (CHECK(IS_ERR(skel->links.oncpu), "attach_perf_event",
-		  "err %ld\n", PTR_ERR(skel->links.oncpu))) {
+	if (!ASSERT_OK_PTR(skel->links.oncpu, "attach_perf_event")) {
 		close(pmu_fd);
 		goto cleanup;
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
index 37269d23df93..04b476bd62b9 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
@@ -21,7 +21,7 @@ void test_stacktrace_map(void)
 		goto close_prog;
 
 	link = bpf_program__attach_tracepoint(prog, "sched", "sched_switch");
-	if (CHECK(IS_ERR(link), "attach_tp", "err %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "attach_tp"))
 		goto close_prog;
 
 	/* find map fds */
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
index 404a5498e1a3..4fd30bb651ad 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
@@ -21,7 +21,7 @@ void test_stacktrace_map_raw_tp(void)
 		goto close_prog;
 
 	link = bpf_program__attach_raw_tracepoint(prog, "sched_switch");
-	if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "attach_raw_tp"))
 		goto close_prog;
 
 	/* find map fds */
@@ -59,7 +59,6 @@ void test_stacktrace_map_raw_tp(void)
 		goto close_prog;
 
 close_prog:
-	if (!IS_ERR_OR_NULL(link))
-		bpf_link__destroy(link);
+	bpf_link__destroy(link);
 	bpf_object__close(obj);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/static_linked.c b/tools/testing/selftests/bpf/prog_tests/static_linked.c
index 46556976dccc..5c4e3014e063 100644
--- a/tools/testing/selftests/bpf/prog_tests/static_linked.c
+++ b/tools/testing/selftests/bpf/prog_tests/static_linked.c
@@ -14,12 +14,7 @@ void test_static_linked(void)
 		return;
 
 	skel->rodata->rovar1 = 1;
-	skel->bss->static_var1 = 2;
-	skel->bss->static_var11 = 3;
-
 	skel->rodata->rovar2 = 4;
-	skel->bss->static_var2 = 5;
-	skel->bss->static_var22 = 6;
 
 	err = test_static_linked__load(skel);
 	if (!ASSERT_OK(err, "skel_load"))
@@ -32,8 +27,8 @@ void test_static_linked(void)
 	/* trigger */
 	usleep(1);
 
-	ASSERT_EQ(skel->bss->var1, 1 * 2 + 2 + 3, "var1");
-	ASSERT_EQ(skel->bss->var2, 4 * 3 + 5 + 6, "var2");
+	ASSERT_EQ(skel->data->var1, 1 * 2 + 2 + 3, "var1");
+	ASSERT_EQ(skel->data->var2, 4 * 3 + 5 + 6, "var2");
 
 cleanup:
 	test_static_linked__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/syscall.c b/tools/testing/selftests/bpf/prog_tests/syscall.c
new file mode 100644
index 000000000000..81e997a69f7a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/syscall.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <test_progs.h>
+#include "syscall.skel.h"
+
+struct args {
+	__u64 log_buf;
+	__u32 log_size;
+	int max_entries;
+	int map_fd;
+	int prog_fd;
+	int btf_fd;
+};
+
+void test_syscall(void)
+{
+	static char verifier_log[8192];
+	struct args ctx = {
+		.max_entries = 1024,
+		.log_buf = (uintptr_t) verifier_log,
+		.log_size = sizeof(verifier_log),
+	};
+	struct bpf_prog_test_run_attr tattr = {
+		.ctx_in = &ctx,
+		.ctx_size_in = sizeof(ctx),
+	};
+	struct syscall *skel = NULL;
+	__u64 key = 12, value = 0;
+	int err;
+
+	skel = syscall__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	tattr.prog_fd = bpf_program__fd(skel->progs.bpf_prog);
+	err = bpf_prog_test_run_xattr(&tattr);
+	ASSERT_EQ(err, 0, "err");
+	ASSERT_EQ(tattr.retval, 1, "retval");
+	ASSERT_GT(ctx.map_fd, 0, "ctx.map_fd");
+	ASSERT_GT(ctx.prog_fd, 0, "ctx.prog_fd");
+	ASSERT_OK(memcmp(verifier_log, "processed", sizeof("processed") - 1),
+		  "verifier_log");
+
+	err = bpf_map_lookup_elem(ctx.map_fd, &key, &value);
+	ASSERT_EQ(err, 0, "map_lookup");
+	ASSERT_EQ(value, 34, "map lookup value");
+cleanup:
+	syscall__destroy(skel);
+	if (ctx.prog_fd > 0)
+		close(ctx.prog_fd);
+	if (ctx.map_fd > 0)
+		close(ctx.map_fd);
+	if (ctx.btf_fd > 0)
+		close(ctx.btf_fd);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_bpf.c b/tools/testing/selftests/bpf/prog_tests/tc_bpf.c
new file mode 100644
index 000000000000..4a505a5adf4d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tc_bpf.c
@@ -0,0 +1,395 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include <linux/pkt_cls.h>
+
+#include "test_tc_bpf.skel.h"
+
+#define LO_IFINDEX 1
+
+#define TEST_DECLARE_OPTS(__fd)                                                                   \
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_h, .handle = 1);                                     \
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_p, .priority = 1);                                   \
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_f, .prog_fd = __fd);                                 \
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hp, .handle = 1, .priority = 1);                     \
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hf, .handle = 1, .prog_fd = __fd);                   \
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_pf, .priority = 1, .prog_fd = __fd);                 \
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hpf, .handle = 1, .priority = 1, .prog_fd = __fd);   \
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hpi, .handle = 1, .priority = 1, .prog_id = 42);     \
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hpr, .handle = 1, .priority = 1,                     \
+			    .flags = BPF_TC_F_REPLACE);                                            \
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hpfi, .handle = 1, .priority = 1, .prog_fd = __fd,   \
+			    .prog_id = 42);                                                        \
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_prio_max, .handle = 1, .priority = UINT16_MAX + 1);
+
+static int test_tc_bpf_basic(const struct bpf_tc_hook *hook, int fd)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts, .handle = 1, .priority = 1, .prog_fd = fd);
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	int ret;
+
+	ret = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+	if (!ASSERT_OK(ret, "bpf_obj_get_info_by_fd"))
+		return ret;
+
+	ret = bpf_tc_attach(hook, &opts);
+	if (!ASSERT_OK(ret, "bpf_tc_attach"))
+		return ret;
+
+	if (!ASSERT_EQ(opts.handle, 1, "handle set") ||
+	    !ASSERT_EQ(opts.priority, 1, "priority set") ||
+	    !ASSERT_EQ(opts.prog_id, info.id, "prog_id set"))
+		goto end;
+
+	opts.prog_id = 0;
+	opts.flags = BPF_TC_F_REPLACE;
+	ret = bpf_tc_attach(hook, &opts);
+	if (!ASSERT_OK(ret, "bpf_tc_attach replace mode"))
+		goto end;
+
+	opts.flags = opts.prog_fd = opts.prog_id = 0;
+	ret = bpf_tc_query(hook, &opts);
+	if (!ASSERT_OK(ret, "bpf_tc_query"))
+		goto end;
+
+	if (!ASSERT_EQ(opts.handle, 1, "handle set") ||
+	    !ASSERT_EQ(opts.priority, 1, "priority set") ||
+	    !ASSERT_EQ(opts.prog_id, info.id, "prog_id set"))
+		goto end;
+
+end:
+	opts.flags = opts.prog_fd = opts.prog_id = 0;
+	ret = bpf_tc_detach(hook, &opts);
+	ASSERT_OK(ret, "bpf_tc_detach");
+	return ret;
+}
+
+static int test_tc_bpf_api(struct bpf_tc_hook *hook, int fd)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, attach_opts, .handle = 1, .priority = 1, .prog_fd = fd);
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, inv_hook, .attach_point = BPF_TC_INGRESS);
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts, .handle = 1, .priority = 1);
+	int ret;
+
+	ret = bpf_tc_hook_create(NULL);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_create invalid hook = NULL"))
+		return -EINVAL;
+
+	/* hook ifindex = 0 */
+	ret = bpf_tc_hook_create(&inv_hook);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_create invalid hook ifindex == 0"))
+		return -EINVAL;
+
+	ret = bpf_tc_hook_destroy(&inv_hook);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_destroy invalid hook ifindex == 0"))
+		return -EINVAL;
+
+	ret = bpf_tc_attach(&inv_hook, &attach_opts);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook ifindex == 0"))
+		return -EINVAL;
+	attach_opts.prog_id = 0;
+
+	ret = bpf_tc_detach(&inv_hook, &opts);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook ifindex == 0"))
+		return -EINVAL;
+
+	ret = bpf_tc_query(&inv_hook, &opts);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook ifindex == 0"))
+		return -EINVAL;
+
+	/* hook ifindex < 0 */
+	inv_hook.ifindex = -1;
+
+	ret = bpf_tc_hook_create(&inv_hook);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_create invalid hook ifindex < 0"))
+		return -EINVAL;
+
+	ret = bpf_tc_hook_destroy(&inv_hook);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_destroy invalid hook ifindex < 0"))
+		return -EINVAL;
+
+	ret = bpf_tc_attach(&inv_hook, &attach_opts);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook ifindex < 0"))
+		return -EINVAL;
+	attach_opts.prog_id = 0;
+
+	ret = bpf_tc_detach(&inv_hook, &opts);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook ifindex < 0"))
+		return -EINVAL;
+
+	ret = bpf_tc_query(&inv_hook, &opts);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook ifindex < 0"))
+		return -EINVAL;
+
+	inv_hook.ifindex = LO_IFINDEX;
+
+	/* hook.attach_point invalid */
+	inv_hook.attach_point = 0xabcd;
+	ret = bpf_tc_hook_create(&inv_hook);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_create invalid hook.attach_point"))
+		return -EINVAL;
+
+	ret = bpf_tc_hook_destroy(&inv_hook);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_destroy invalid hook.attach_point"))
+		return -EINVAL;
+
+	ret = bpf_tc_attach(&inv_hook, &attach_opts);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook.attach_point"))
+		return -EINVAL;
+
+	ret = bpf_tc_detach(&inv_hook, &opts);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook.attach_point"))
+		return -EINVAL;
+
+	ret = bpf_tc_query(&inv_hook, &opts);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook.attach_point"))
+		return -EINVAL;
+
+	inv_hook.attach_point = BPF_TC_INGRESS;
+
+	/* hook.attach_point valid, but parent invalid */
+	inv_hook.parent = TC_H_MAKE(1UL << 16, 10);
+	ret = bpf_tc_hook_create(&inv_hook);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_create invalid hook parent"))
+		return -EINVAL;
+
+	ret = bpf_tc_hook_destroy(&inv_hook);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_destroy invalid hook parent"))
+		return -EINVAL;
+
+	ret = bpf_tc_attach(&inv_hook, &attach_opts);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook parent"))
+		return -EINVAL;
+
+	ret = bpf_tc_detach(&inv_hook, &opts);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook parent"))
+		return -EINVAL;
+
+	ret = bpf_tc_query(&inv_hook, &opts);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook parent"))
+		return -EINVAL;
+
+	inv_hook.attach_point = BPF_TC_CUSTOM;
+	inv_hook.parent = 0;
+	/* These return EOPNOTSUPP instead of EINVAL as parent is checked after
+	 * attach_point of the hook.
+	 */
+	ret = bpf_tc_hook_create(&inv_hook);
+	if (!ASSERT_EQ(ret, -EOPNOTSUPP, "bpf_tc_hook_create invalid hook parent"))
+		return -EINVAL;
+
+	ret = bpf_tc_hook_destroy(&inv_hook);
+	if (!ASSERT_EQ(ret, -EOPNOTSUPP, "bpf_tc_hook_destroy invalid hook parent"))
+		return -EINVAL;
+
+	ret = bpf_tc_attach(&inv_hook, &attach_opts);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook parent"))
+		return -EINVAL;
+
+	ret = bpf_tc_detach(&inv_hook, &opts);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook parent"))
+		return -EINVAL;
+
+	ret = bpf_tc_query(&inv_hook, &opts);
+	if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook parent"))
+		return -EINVAL;
+
+	inv_hook.attach_point = BPF_TC_INGRESS;
+
+	/* detach */
+	{
+		TEST_DECLARE_OPTS(fd);
+
+		ret = bpf_tc_detach(NULL, &opts_hp);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook = NULL"))
+			return -EINVAL;
+
+		ret = bpf_tc_detach(hook, NULL);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid opts = NULL"))
+			return -EINVAL;
+
+		ret = bpf_tc_detach(hook, &opts_hpr);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid flags set"))
+			return -EINVAL;
+
+		ret = bpf_tc_detach(hook, &opts_hpf);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid prog_fd set"))
+			return -EINVAL;
+
+		ret = bpf_tc_detach(hook, &opts_hpi);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid prog_id set"))
+			return -EINVAL;
+
+		ret = bpf_tc_detach(hook, &opts_p);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid handle unset"))
+			return -EINVAL;
+
+		ret = bpf_tc_detach(hook, &opts_h);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid priority unset"))
+			return -EINVAL;
+
+		ret = bpf_tc_detach(hook, &opts_prio_max);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid priority > UINT16_MAX"))
+			return -EINVAL;
+	}
+
+	/* query */
+	{
+		TEST_DECLARE_OPTS(fd);
+
+		ret = bpf_tc_query(NULL, &opts);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook = NULL"))
+			return -EINVAL;
+
+		ret = bpf_tc_query(hook, NULL);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid opts = NULL"))
+			return -EINVAL;
+
+		ret = bpf_tc_query(hook, &opts_hpr);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid flags set"))
+			return -EINVAL;
+
+		ret = bpf_tc_query(hook, &opts_hpf);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid prog_fd set"))
+			return -EINVAL;
+
+		ret = bpf_tc_query(hook, &opts_hpi);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid prog_id set"))
+			return -EINVAL;
+
+		ret = bpf_tc_query(hook, &opts_p);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid handle unset"))
+			return -EINVAL;
+
+		ret = bpf_tc_query(hook, &opts_h);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid priority unset"))
+			return -EINVAL;
+
+		ret = bpf_tc_query(hook, &opts_prio_max);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid priority > UINT16_MAX"))
+			return -EINVAL;
+
+		/* when chain is not present, kernel returns -EINVAL */
+		ret = bpf_tc_query(hook, &opts_hp);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query valid handle, priority set"))
+			return -EINVAL;
+	}
+
+	/* attach */
+	{
+		TEST_DECLARE_OPTS(fd);
+
+		ret = bpf_tc_attach(NULL, &opts_hp);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook = NULL"))
+			return -EINVAL;
+
+		ret = bpf_tc_attach(hook, NULL);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid opts = NULL"))
+			return -EINVAL;
+
+		opts_hp.flags = 42;
+		ret = bpf_tc_attach(hook, &opts_hp);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid flags"))
+			return -EINVAL;
+
+		ret = bpf_tc_attach(hook, NULL);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid prog_fd unset"))
+			return -EINVAL;
+
+		ret = bpf_tc_attach(hook, &opts_hpi);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid prog_id set"))
+			return -EINVAL;
+
+		ret = bpf_tc_attach(hook, &opts_pf);
+		if (!ASSERT_OK(ret, "bpf_tc_attach valid handle unset"))
+			return -EINVAL;
+		opts_pf.prog_fd = opts_pf.prog_id = 0;
+		ASSERT_OK(bpf_tc_detach(hook, &opts_pf), "bpf_tc_detach");
+
+		ret = bpf_tc_attach(hook, &opts_hf);
+		if (!ASSERT_OK(ret, "bpf_tc_attach valid priority unset"))
+			return -EINVAL;
+		opts_hf.prog_fd = opts_hf.prog_id = 0;
+		ASSERT_OK(bpf_tc_detach(hook, &opts_hf), "bpf_tc_detach");
+
+		ret = bpf_tc_attach(hook, &opts_prio_max);
+		if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid priority > UINT16_MAX"))
+			return -EINVAL;
+
+		ret = bpf_tc_attach(hook, &opts_f);
+		if (!ASSERT_OK(ret, "bpf_tc_attach valid both handle and priority unset"))
+			return -EINVAL;
+		opts_f.prog_fd = opts_f.prog_id = 0;
+		ASSERT_OK(bpf_tc_detach(hook, &opts_f), "bpf_tc_detach");
+	}
+
+	return 0;
+}
+
+void test_tc_bpf(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX,
+			    .attach_point = BPF_TC_INGRESS);
+	struct test_tc_bpf *skel = NULL;
+	bool hook_created = false;
+	int cls_fd, ret;
+
+	skel = test_tc_bpf__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tc_bpf__open_and_load"))
+		return;
+
+	cls_fd = bpf_program__fd(skel->progs.cls);
+
+	ret = bpf_tc_hook_create(&hook);
+	if (ret == 0)
+		hook_created = true;
+
+	ret = ret == -EEXIST ? 0 : ret;
+	if (!ASSERT_OK(ret, "bpf_tc_hook_create(BPF_TC_INGRESS)"))
+		goto end;
+
+	hook.attach_point = BPF_TC_CUSTOM;
+	hook.parent = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS);
+	ret = bpf_tc_hook_create(&hook);
+	if (!ASSERT_EQ(ret, -EOPNOTSUPP, "bpf_tc_hook_create invalid hook.attach_point"))
+		goto end;
+
+	ret = test_tc_bpf_basic(&hook, cls_fd);
+	if (!ASSERT_OK(ret, "test_tc_internal ingress"))
+		goto end;
+
+	ret = bpf_tc_hook_destroy(&hook);
+	if (!ASSERT_EQ(ret, -EOPNOTSUPP, "bpf_tc_hook_destroy invalid hook.attach_point"))
+		goto end;
+
+	hook.attach_point = BPF_TC_INGRESS;
+	hook.parent = 0;
+	bpf_tc_hook_destroy(&hook);
+
+	ret = test_tc_bpf_basic(&hook, cls_fd);
+	if (!ASSERT_OK(ret, "test_tc_internal ingress"))
+		goto end;
+
+	bpf_tc_hook_destroy(&hook);
+
+	hook.attach_point = BPF_TC_EGRESS;
+	ret = test_tc_bpf_basic(&hook, cls_fd);
+	if (!ASSERT_OK(ret, "test_tc_internal egress"))
+		goto end;
+
+	bpf_tc_hook_destroy(&hook);
+
+	ret = test_tc_bpf_api(&hook, cls_fd);
+	if (!ASSERT_OK(ret, "test_tc_bpf_api"))
+		goto end;
+
+	bpf_tc_hook_destroy(&hook);
+
+end:
+	if (hook_created) {
+		hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS;
+		bpf_tc_hook_destroy(&hook);
+	}
+	test_tc_bpf__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
index 08d19cafd5e8..1fa772079967 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
@@ -353,8 +353,7 @@ static void fastopen_estab(void)
 		return;
 
 	link = bpf_program__attach_cgroup(skel->progs.estab, cg_fd);
-	if (CHECK(IS_ERR(link), "attach_cgroup(estab)", "err: %ld\n",
-		  PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "attach_cgroup(estab)"))
 		return;
 
 	if (sk_fds_connect(&sk_fds, true)) {
@@ -398,8 +397,7 @@ static void syncookie_estab(void)
 		return;
 
 	link = bpf_program__attach_cgroup(skel->progs.estab, cg_fd);
-	if (CHECK(IS_ERR(link), "attach_cgroup(estab)", "err: %ld\n",
-		  PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "attach_cgroup(estab)"))
 		return;
 
 	if (sk_fds_connect(&sk_fds, false)) {
@@ -431,8 +429,7 @@ static void fin(void)
 		return;
 
 	link = bpf_program__attach_cgroup(skel->progs.estab, cg_fd);
-	if (CHECK(IS_ERR(link), "attach_cgroup(estab)", "err: %ld\n",
-		  PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "attach_cgroup(estab)"))
 		return;
 
 	if (sk_fds_connect(&sk_fds, false)) {
@@ -471,8 +468,7 @@ static void __simple_estab(bool exprm)
 		return;
 
 	link = bpf_program__attach_cgroup(skel->progs.estab, cg_fd);
-	if (CHECK(IS_ERR(link), "attach_cgroup(estab)", "err: %ld\n",
-		  PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "attach_cgroup(estab)"))
 		return;
 
 	if (sk_fds_connect(&sk_fds, false)) {
@@ -509,8 +505,7 @@ static void misc(void)
 		return;
 
 	link = bpf_program__attach_cgroup(misc_skel->progs.misc_estab, cg_fd);
-	if (CHECK(IS_ERR(link), "attach_cgroup(misc_estab)", "err: %ld\n",
-		  PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "attach_cgroup(misc_estab)"))
 		return;
 
 	if (sk_fds_connect(&sk_fds, false)) {
diff --git a/tools/testing/selftests/bpf/prog_tests/test_overhead.c b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
index 9966685866fd..123c68c1917d 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_overhead.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
@@ -73,7 +73,7 @@ void test_test_overhead(void)
 		return;
 
 	obj = bpf_object__open_file("./test_overhead.o", NULL);
-	if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj)))
+	if (!ASSERT_OK_PTR(obj, "obj_open_file"))
 		return;
 
 	kprobe_prog = bpf_object__find_program_by_title(obj, kprobe_name);
@@ -108,7 +108,7 @@ void test_test_overhead(void)
 	/* attach kprobe */
 	link = bpf_program__attach_kprobe(kprobe_prog, false /* retprobe */,
 					  kprobe_func);
-	if (CHECK(IS_ERR(link), "attach_kprobe", "err %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "attach_kprobe"))
 		goto cleanup;
 	test_run("kprobe");
 	bpf_link__destroy(link);
@@ -116,28 +116,28 @@ void test_test_overhead(void)
 	/* attach kretprobe */
 	link = bpf_program__attach_kprobe(kretprobe_prog, true /* retprobe */,
 					  kprobe_func);
-	if (CHECK(IS_ERR(link), "attach kretprobe", "err %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "attach_kretprobe"))
 		goto cleanup;
 	test_run("kretprobe");
 	bpf_link__destroy(link);
 
 	/* attach raw_tp */
 	link = bpf_program__attach_raw_tracepoint(raw_tp_prog, "task_rename");
-	if (CHECK(IS_ERR(link), "attach fentry", "err %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "attach_raw_tp"))
 		goto cleanup;
 	test_run("raw_tp");
 	bpf_link__destroy(link);
 
 	/* attach fentry */
 	link = bpf_program__attach_trace(fentry_prog);
-	if (CHECK(IS_ERR(link), "attach fentry", "err %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "attach_fentry"))
 		goto cleanup;
 	test_run("fentry");
 	bpf_link__destroy(link);
 
 	/* attach fexit */
 	link = bpf_program__attach_trace(fexit_prog);
-	if (CHECK(IS_ERR(link), "attach fexit", "err %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "attach_fexit"))
 		goto cleanup;
 	test_run("fexit");
 	bpf_link__destroy(link);
diff --git a/tools/testing/selftests/bpf/prog_tests/trace_printk.c b/tools/testing/selftests/bpf/prog_tests/trace_printk.c
index 39b0decb1bb2..d39bc00feb45 100644
--- a/tools/testing/selftests/bpf/prog_tests/trace_printk.c
+++ b/tools/testing/selftests/bpf/prog_tests/trace_printk.c
@@ -3,7 +3,7 @@
 
 #include <test_progs.h>
 
-#include "trace_printk.skel.h"
+#include "trace_printk.lskel.h"
 
 #define TRACEBUF	"/sys/kernel/debug/tracing/trace_pipe"
 #define SEARCHMSG	"testing,testing"
@@ -21,6 +21,9 @@ void test_trace_printk(void)
 	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
 		return;
 
+	ASSERT_EQ(skel->rodata->fmt[0], 'T', "invalid printk fmt string");
+	skel->rodata->fmt[0] = 't';
+
 	err = trace_printk__load(skel);
 	if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err))
 		goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
index f3022d934e2d..d7f5a931d7f3 100644
--- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
+++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
@@ -55,7 +55,7 @@ void test_trampoline_count(void)
 	/* attach 'allowed' trampoline programs */
 	for (i = 0; i < MAX_TRAMP_PROGS; i++) {
 		obj = bpf_object__open_file(object, NULL);
-		if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) {
+		if (!ASSERT_OK_PTR(obj, "obj_open_file")) {
 			obj = NULL;
 			goto cleanup;
 		}
@@ -68,14 +68,14 @@ void test_trampoline_count(void)
 
 		if (rand() % 2) {
 			link = load(inst[i].obj, fentry_name);
-			if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link))) {
+			if (!ASSERT_OK_PTR(link, "attach_prog")) {
 				link = NULL;
 				goto cleanup;
 			}
 			inst[i].link_fentry = link;
 		} else {
 			link = load(inst[i].obj, fexit_name);
-			if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link))) {
+			if (!ASSERT_OK_PTR(link, "attach_prog")) {
 				link = NULL;
 				goto cleanup;
 			}
@@ -85,7 +85,7 @@ void test_trampoline_count(void)
 
 	/* and try 1 extra.. */
 	obj = bpf_object__open_file(object, NULL);
-	if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) {
+	if (!ASSERT_OK_PTR(obj, "obj_open_file")) {
 		obj = NULL;
 		goto cleanup;
 	}
@@ -96,13 +96,15 @@ void test_trampoline_count(void)
 
 	/* ..that needs to fail */
 	link = load(obj, fentry_name);
-	if (CHECK(!IS_ERR(link), "cannot attach over the limit", "err %ld\n", PTR_ERR(link))) {
+	err = libbpf_get_error(link);
+	if (!ASSERT_ERR_PTR(link, "cannot attach over the limit")) {
 		bpf_link__destroy(link);
 		goto cleanup_extra;
 	}
 
 	/* with E2BIG error */
-	CHECK(PTR_ERR(link) != -E2BIG, "proper error check", "err %ld\n", PTR_ERR(link));
+	ASSERT_EQ(err, -E2BIG, "proper error check");
+	ASSERT_EQ(link, NULL, "ptr_is_null");
 
 	/* and finaly execute the probe */
 	if (CHECK_FAIL(prctl(PR_GET_NAME, comm, 0L, 0L, 0L)))
diff --git a/tools/testing/selftests/bpf/prog_tests/udp_limit.c b/tools/testing/selftests/bpf/prog_tests/udp_limit.c
index 2aba09d4d01b..56c9d6bd38a3 100644
--- a/tools/testing/selftests/bpf/prog_tests/udp_limit.c
+++ b/tools/testing/selftests/bpf/prog_tests/udp_limit.c
@@ -22,11 +22,10 @@ void test_udp_limit(void)
 		goto close_cgroup_fd;
 
 	skel->links.sock = bpf_program__attach_cgroup(skel->progs.sock, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.sock, "cg_attach_sock"))
+		goto close_skeleton;
 	skel->links.sock_release = bpf_program__attach_cgroup(skel->progs.sock_release, cgroup_fd);
-	if (CHECK(IS_ERR(skel->links.sock) || IS_ERR(skel->links.sock_release),
-		  "cg-attach", "sock %ld sock_release %ld",
-		  PTR_ERR(skel->links.sock),
-		  PTR_ERR(skel->links.sock_release)))
+	if (!ASSERT_OK_PTR(skel->links.sock_release, "cg_attach_sock_release"))
 		goto close_skeleton;
 
 	/* BPF program enforces a single UDP socket per cgroup,
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
index 2c6c570b21f8..3bd5904b4db5 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
@@ -90,7 +90,7 @@ void test_xdp_bpf2bpf(void)
 	pb_opts.ctx = &passed;
 	pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map),
 			      1, &pb_opts);
-	if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb)))
+	if (!ASSERT_OK_PTR(pb, "perf_buf__new"))
 		goto out;
 
 	/* Run test program */
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
index 6f814999b395..46eed0a33c23 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_link.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
@@ -51,7 +51,7 @@ void test_xdp_link(void)
 
 	/* BPF link is not allowed to replace prog attachment */
 	link = bpf_program__attach_xdp(skel1->progs.xdp_handler, IFINDEX_LO);
-	if (CHECK(!IS_ERR(link), "link_attach_fail", "unexpected success\n")) {
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
 		bpf_link__destroy(link);
 		/* best-effort detach prog */
 		opts.old_fd = prog_fd1;
@@ -67,7 +67,7 @@ void test_xdp_link(void)
 
 	/* now BPF link should attach successfully */
 	link = bpf_program__attach_xdp(skel1->progs.xdp_handler, IFINDEX_LO);
-	if (CHECK(IS_ERR(link), "link_attach", "failed: %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "link_attach"))
 		goto cleanup;
 	skel1->links.xdp_handler = link;
 
@@ -95,7 +95,7 @@ void test_xdp_link(void)
 
 	/* BPF link is not allowed to replace another BPF link */
 	link = bpf_program__attach_xdp(skel2->progs.xdp_handler, IFINDEX_LO);
-	if (CHECK(!IS_ERR(link), "link_attach_fail", "unexpected success\n")) {
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
 		bpf_link__destroy(link);
 		goto cleanup;
 	}
@@ -105,7 +105,7 @@ void test_xdp_link(void)
 
 	/* new link attach should succeed */
 	link = bpf_program__attach_xdp(skel2->progs.xdp_handler, IFINDEX_LO);
-	if (CHECK(IS_ERR(link), "link_attach", "failed: %ld\n", PTR_ERR(link)))
+	if (!ASSERT_OK_PTR(link, "link_attach"))
 		goto cleanup;
 	skel2->links.xdp_handler = link;
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
index 6dfce3fd68bc..0aa3cd34cbe3 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
@@ -2,7 +2,6 @@
 /* Copyright (c) 2020 Facebook */
 #include "bpf_iter.h"
 #include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
index b83b5d2e17dc..6c39e86b666f 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
@@ -2,7 +2,6 @@
 /* Copyright (c) 2020 Facebook */
 #include "bpf_iter.h"
 #include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c
index d58d9f1642b5..784a610ce039 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c
@@ -3,7 +3,6 @@
 #include "bpf_iter.h"
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c
index 95989f4c99b5..a28e51e2dcee 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c
@@ -3,7 +3,6 @@
 #include "bpf_iter.h"
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c
index b7f32c160f4e..c86b93f33b32 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task.c
@@ -2,7 +2,6 @@
 /* Copyright (c) 2020 Facebook */
 #include "bpf_iter.h"
 #include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c
index a1ddc36f13ec..bca8b889cb10 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c
@@ -2,7 +2,6 @@
 /* Copyright (c) 2020, Oracle and/or its affiliates. */
 #include "bpf_iter.h"
 #include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
 #include <bpf/bpf_core_read.h>
 
 #include <errno.h>
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c
index b2f7c7c5f952..6e7b400888fe 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c
@@ -2,7 +2,6 @@
 /* Copyright (c) 2020 Facebook */
 #include "bpf_iter.h"
 #include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c
index 43c36f5f7649..f2b8167b72a8 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c
@@ -2,7 +2,6 @@
 /* Copyright (c) 2020 Facebook */
 #include "bpf_iter.h"
 #include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c
index 11d1aa37cf11..4ea6a37d1345 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c
@@ -2,7 +2,6 @@
 /* Copyright (c) 2020 Facebook */
 #include "bpf_iter.h"
 #include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c
index 54380c5e1069..2e4775c35414 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c
@@ -3,7 +3,6 @@
 #include "bpf_iter.h"
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
 #include <bpf/bpf_endian.h>
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c
index b4fbddfa4e10..943f7bba180e 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c
@@ -3,7 +3,6 @@
 #include "bpf_iter.h"
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
 #include <bpf/bpf_endian.h>
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
index ee49493dc125..400fdf8d6233 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
@@ -9,8 +9,8 @@ __u32 map1_id = 0, map2_id = 0;
 __u32 map1_accessed = 0, map2_accessed = 0;
 __u64 map1_seqnum = 0, map2_seqnum1 = 0, map2_seqnum2 = 0;
 
-static volatile const __u32 print_len;
-static volatile const __u32 ret1;
+volatile const __u32 print_len;
+volatile const __u32 ret1;
 
 SEC("iter/bpf_map")
 int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c
index f258583afbbd..cf0c485b1ed7 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c
@@ -3,7 +3,6 @@
 #include "bpf_iter.h"
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
 #include <bpf/bpf_endian.h>
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c
index 65f93bb03f0f..5031e21c433f 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c
@@ -3,7 +3,6 @@
 #include "bpf_iter.h"
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
 #include <bpf/bpf_endian.h>
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c
index a46a264ce24e..55e283050cab 100644
--- a/tools/testing/selftests/bpf/progs/kfree_skb.c
+++ b/tools/testing/selftests/bpf/progs/kfree_skb.c
@@ -109,10 +109,10 @@ int BPF_PROG(trace_kfree_skb, struct sk_buff *skb, void *location)
 	return 0;
 }
 
-static volatile struct {
+struct {
 	bool fentry_test_ok;
 	bool fexit_test_ok;
-} result;
+} result = {};
 
 SEC("fentry/eth_type_trans")
 int BPF_PROG(fentry_eth_type_trans, struct sk_buff *skb, struct net_device *dev,
diff --git a/tools/testing/selftests/bpf/progs/linked_maps1.c b/tools/testing/selftests/bpf/progs/linked_maps1.c
index 52291515cc72..00bf1ca95986 100644
--- a/tools/testing/selftests/bpf/progs/linked_maps1.c
+++ b/tools/testing/selftests/bpf/progs/linked_maps1.c
@@ -75,7 +75,7 @@ int BPF_PROG(handler_exit1)
 	val = bpf_map_lookup_elem(&map_weak, &key);
 	if (val)
 		output_weak1 = *val;
-	
+
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/syscall.c b/tools/testing/selftests/bpf/progs/syscall.c
new file mode 100644
index 000000000000..e550f728962d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/syscall.c
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <linux/stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <../../../tools/include/linux/filter.h>
+#include <linux/btf.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct args {
+	__u64 log_buf;
+	__u32 log_size;
+	int max_entries;
+	int map_fd;
+	int prog_fd;
+	int btf_fd;
+};
+
+#define BTF_INFO_ENC(kind, kind_flag, vlen) \
+	((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
+#define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type)
+#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \
+	((encoding) << 24 | (bits_offset) << 16 | (nr_bits))
+#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \
+	BTF_INT_ENC(encoding, bits_offset, bits)
+
+static int btf_load(void)
+{
+	struct btf_blob {
+		struct btf_header btf_hdr;
+		__u32 types[8];
+		__u32 str;
+	} raw_btf = {
+		.btf_hdr = {
+			.magic = BTF_MAGIC,
+			.version = BTF_VERSION,
+			.hdr_len = sizeof(struct btf_header),
+			.type_len = sizeof(__u32) * 8,
+			.str_off = sizeof(__u32) * 8,
+			.str_len = sizeof(__u32),
+		},
+		.types = {
+			/* long */
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 64, 8),  /* [1] */
+			/* unsigned long */
+			BTF_TYPE_INT_ENC(0, 0, 0, 64, 8),  /* [2] */
+		},
+	};
+	static union bpf_attr btf_load_attr = {
+		.btf_size = sizeof(raw_btf),
+	};
+
+	btf_load_attr.btf = (long)&raw_btf;
+	return bpf_sys_bpf(BPF_BTF_LOAD, &btf_load_attr, sizeof(btf_load_attr));
+}
+
+SEC("syscall")
+int bpf_prog(struct args *ctx)
+{
+	static char license[] = "GPL";
+	static struct bpf_insn insns[] = {
+		BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+		BPF_LD_MAP_FD(BPF_REG_1, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	static union bpf_attr map_create_attr = {
+		.map_type = BPF_MAP_TYPE_HASH,
+		.key_size = 8,
+		.value_size = 8,
+		.btf_key_type_id = 1,
+		.btf_value_type_id = 2,
+	};
+	static union bpf_attr map_update_attr = { .map_fd = 1, };
+	static __u64 key = 12;
+	static __u64 value = 34;
+	static union bpf_attr prog_load_attr = {
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.insn_cnt = sizeof(insns) / sizeof(insns[0]),
+	};
+	int ret;
+
+	ret = btf_load();
+	if (ret <= 0)
+		return ret;
+
+	ctx->btf_fd = ret;
+	map_create_attr.max_entries = ctx->max_entries;
+	map_create_attr.btf_fd = ret;
+
+	prog_load_attr.license = (long) license;
+	prog_load_attr.insns = (long) insns;
+	prog_load_attr.log_buf = ctx->log_buf;
+	prog_load_attr.log_size = ctx->log_size;
+	prog_load_attr.log_level = 1;
+
+	ret = bpf_sys_bpf(BPF_MAP_CREATE, &map_create_attr, sizeof(map_create_attr));
+	if (ret <= 0)
+		return ret;
+	ctx->map_fd = ret;
+	insns[3].imm = ret;
+
+	map_update_attr.map_fd = ret;
+	map_update_attr.key = (long) &key;
+	map_update_attr.value = (long) &value;
+	ret = bpf_sys_bpf(BPF_MAP_UPDATE_ELEM, &map_update_attr, sizeof(map_update_attr));
+	if (ret < 0)
+		return ret;
+
+	ret = bpf_sys_bpf(BPF_PROG_LOAD, &prog_load_attr, sizeof(prog_load_attr));
+	if (ret <= 0)
+		return ret;
+	ctx->prog_fd = ret;
+	return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/tailcall3.c b/tools/testing/selftests/bpf/progs/tailcall3.c
index 739dc2a51e74..910858fe078a 100644
--- a/tools/testing/selftests/bpf/progs/tailcall3.c
+++ b/tools/testing/selftests/bpf/progs/tailcall3.c
@@ -10,7 +10,7 @@ struct {
 	__uint(value_size, sizeof(__u32));
 } jmp_table SEC(".maps");
 
-static volatile int count;
+int count = 0;
 
 SEC("classifier/0")
 int bpf_func_0(struct __sk_buff *skb)
diff --git a/tools/testing/selftests/bpf/progs/tailcall4.c b/tools/testing/selftests/bpf/progs/tailcall4.c
index f82075b47d7d..bd4be135c39d 100644
--- a/tools/testing/selftests/bpf/progs/tailcall4.c
+++ b/tools/testing/selftests/bpf/progs/tailcall4.c
@@ -10,7 +10,7 @@ struct {
 	__uint(value_size, sizeof(__u32));
 } jmp_table SEC(".maps");
 
-static volatile int selector;
+int selector = 0;
 
 #define TAIL_FUNC(x)				\
 	SEC("classifier/" #x)			\
diff --git a/tools/testing/selftests/bpf/progs/tailcall5.c b/tools/testing/selftests/bpf/progs/tailcall5.c
index ce5450744fd4..adf30a33064e 100644
--- a/tools/testing/selftests/bpf/progs/tailcall5.c
+++ b/tools/testing/selftests/bpf/progs/tailcall5.c
@@ -10,7 +10,7 @@ struct {
 	__uint(value_size, sizeof(__u32));
 } jmp_table SEC(".maps");
 
-static volatile int selector;
+int selector = 0;
 
 #define TAIL_FUNC(x)				\
 	SEC("classifier/" #x)			\
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c
index 7b1c04183824..3cc4c12817b5 100644
--- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c
@@ -20,7 +20,7 @@ int subprog_tail(struct __sk_buff *skb)
 	return 1;
 }
 
-static volatile int count;
+int count = 0;
 
 SEC("classifier/0")
 int bpf_func_0(struct __sk_buff *skb)
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c
index 9a1b166b7fbe..77df6d4db895 100644
--- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c
@@ -9,7 +9,7 @@ struct {
 	__uint(value_size, sizeof(__u32));
 } jmp_table SEC(".maps");
 
-static volatile int count;
+int count = 0;
 
 __noinline
 int subprog_tail_2(struct __sk_buff *skb)
diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c
index c4a9bae96e75..71184af57749 100644
--- a/tools/testing/selftests/bpf/progs/test_check_mtu.c
+++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c
@@ -11,8 +11,8 @@
 char _license[] SEC("license") = "GPL";
 
 /* Userspace will update with MTU it can see on device */
-static volatile const int GLOBAL_USER_MTU;
-static volatile const __u32 GLOBAL_USER_IFINDEX;
+volatile const int GLOBAL_USER_MTU;
+volatile const __u32 GLOBAL_USER_IFINDEX;
 
 /* BPF-prog will update these with MTU values it can see */
 __u32 global_bpf_mtu_xdp = 0;
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
index 3c1e042962e6..e2a5acc4785c 100644
--- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
@@ -39,8 +39,8 @@ char _license[] SEC("license") = "Dual BSD/GPL";
 /**
  * Destination port and IP used for UDP encapsulation.
  */
-static volatile const __be16 ENCAPSULATION_PORT;
-static volatile const __be32 ENCAPSULATION_IP;
+volatile const __be16 ENCAPSULATION_PORT;
+volatile const __be32 ENCAPSULATION_IP;
 
 typedef struct {
 	uint64_t processed_packets_total;
diff --git a/tools/testing/selftests/bpf/progs/test_global_func_args.c b/tools/testing/selftests/bpf/progs/test_global_func_args.c
index cae309538a9e..e712bf77daae 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func_args.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func_args.c
@@ -8,7 +8,7 @@ struct S {
 	int v;
 };
 
-static volatile struct S global_variable;
+struct S global_variable = {};
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/test_lookup_and_delete.c b/tools/testing/selftests/bpf/progs/test_lookup_and_delete.c
new file mode 100644
index 000000000000..3a193f42c7e7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_lookup_and_delete.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+__u32 set_pid = 0;
+__u64 set_key = 0;
+__u64 set_value = 0;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 2);
+	__type(key, __u64);
+	__type(value, __u64);
+} hash_map SEC(".maps");
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int bpf_lookup_and_delete_test(const void *ctx)
+{
+	if (set_pid == bpf_get_current_pid_tgid() >> 32)
+		bpf_map_update_elem(&hash_map, &set_key, &set_value, BPF_NOEXIST);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_migrate_reuseport.c b/tools/testing/selftests/bpf/progs/test_migrate_reuseport.c
new file mode 100644
index 000000000000..27df571abf5b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_migrate_reuseport.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Check if we can migrate child sockets.
+ *
+ *   1. If reuse_md->migrating_sk is NULL (SYN packet),
+ *        return SK_PASS without selecting a listener.
+ *   2. If reuse_md->migrating_sk is not NULL (socket migration),
+ *        select a listener (reuseport_map[migrate_map[cookie]])
+ *
+ * Author: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
+ */
+
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/in.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY);
+	__uint(max_entries, 256);
+	__type(key, int);
+	__type(value, __u64);
+} reuseport_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 256);
+	__type(key, __u64);
+	__type(value, int);
+} migrate_map SEC(".maps");
+
+int migrated_at_close = 0;
+int migrated_at_close_fastopen = 0;
+int migrated_at_send_synack = 0;
+int migrated_at_recv_ack = 0;
+__be16 server_port;
+
+SEC("xdp")
+int drop_ack(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct ethhdr *eth = data;
+	struct tcphdr *tcp = NULL;
+
+	if (eth + 1 > data_end)
+		goto pass;
+
+	switch (bpf_ntohs(eth->h_proto)) {
+	case ETH_P_IP: {
+		struct iphdr *ip = (struct iphdr *)(eth + 1);
+
+		if (ip + 1 > data_end)
+			goto pass;
+
+		if (ip->protocol != IPPROTO_TCP)
+			goto pass;
+
+		tcp = (struct tcphdr *)((void *)ip + ip->ihl * 4);
+		break;
+	}
+	case ETH_P_IPV6: {
+		struct ipv6hdr *ipv6 = (struct ipv6hdr *)(eth + 1);
+
+		if (ipv6 + 1 > data_end)
+			goto pass;
+
+		if (ipv6->nexthdr != IPPROTO_TCP)
+			goto pass;
+
+		tcp = (struct tcphdr *)(ipv6 + 1);
+		break;
+	}
+	default:
+		goto pass;
+	}
+
+	if (tcp + 1 > data_end)
+		goto pass;
+
+	if (tcp->dest != server_port)
+		goto pass;
+
+	if (!tcp->syn && tcp->ack)
+		return XDP_DROP;
+
+pass:
+	return XDP_PASS;
+}
+
+SEC("sk_reuseport/migrate")
+int migrate_reuseport(struct sk_reuseport_md *reuse_md)
+{
+	int *key, flags = 0, state, err;
+	__u64 cookie;
+
+	if (!reuse_md->migrating_sk)
+		return SK_PASS;
+
+	state = reuse_md->migrating_sk->state;
+	cookie = bpf_get_socket_cookie(reuse_md->sk);
+
+	key = bpf_map_lookup_elem(&migrate_map, &cookie);
+	if (!key)
+		return SK_DROP;
+
+	err = bpf_sk_select_reuseport(reuse_md, &reuseport_map, key, flags);
+	if (err)
+		return SK_PASS;
+
+	switch (state) {
+	case BPF_TCP_ESTABLISHED:
+		__sync_fetch_and_add(&migrated_at_close, 1);
+		break;
+	case BPF_TCP_SYN_RECV:
+		__sync_fetch_and_add(&migrated_at_close_fastopen, 1);
+		break;
+	case BPF_TCP_NEW_SYN_RECV:
+		if (!reuse_md->len)
+			__sync_fetch_and_add(&migrated_at_send_synack, 1);
+		else
+			__sync_fetch_and_add(&migrated_at_recv_ack, 1);
+		break;
+	}
+
+	return SK_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
index ecbeea2df259..fc8e8a34a3db 100644
--- a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
+++ b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
@@ -5,7 +5,7 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
-static volatile const struct {
+const struct {
 	unsigned a[4];
 	/*
 	 * if the struct's size is multiple of 16, compiler will put it into
@@ -15,11 +15,11 @@ static volatile const struct {
 	char _y;
 } rdonly_values = { .a = {2, 3, 4, 5} };
 
-static volatile struct {
+struct {
 	unsigned did_run;
 	unsigned iters;
 	unsigned sum;
-} res;
+} res = {};
 
 SEC("raw_tracepoint/sys_enter:skip_loop")
 int skip_loop(struct pt_regs *ctx)
diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf.c b/tools/testing/selftests/bpf/progs/test_ringbuf.c
index 6b3f288b7c63..eaa7d9dba0be 100644
--- a/tools/testing/selftests/bpf/progs/test_ringbuf.c
+++ b/tools/testing/selftests/bpf/progs/test_ringbuf.c
@@ -35,7 +35,7 @@ long prod_pos = 0;
 /* inner state */
 long seq = 0;
 
-SEC("tp/syscalls/sys_enter_getpgid")
+SEC("fentry/__x64_sys_getpgid")
 int test_ringbuf(void *ctx)
 {
 	int cur_pid = bpf_get_current_pid_tgid() >> 32;
@@ -48,7 +48,7 @@ int test_ringbuf(void *ctx)
 	sample = bpf_ringbuf_reserve(&ringbuf, sizeof(*sample), 0);
 	if (!sample) {
 		__sync_fetch_and_add(&dropped, 1);
-		return 1;
+		return 0;
 	}
 
 	sample->pid = pid;
diff --git a/tools/testing/selftests/bpf/progs/test_skeleton.c b/tools/testing/selftests/bpf/progs/test_skeleton.c
index 374ccef704e1..441fa1c552c8 100644
--- a/tools/testing/selftests/bpf/progs/test_skeleton.c
+++ b/tools/testing/selftests/bpf/progs/test_skeleton.c
@@ -38,11 +38,11 @@ extern int LINUX_KERNEL_VERSION __kconfig;
 bool bpf_syscall = 0;
 int kern_ver = 0;
 
+struct s out5 = {};
+
 SEC("raw_tp/sys_enter")
 int handler(const void *ctx)
 {
-	static volatile struct s out5;
-
 	out1 = in1;
 	out2 = in2;
 	out3 = in3;
diff --git a/tools/testing/selftests/bpf/progs/test_snprintf.c b/tools/testing/selftests/bpf/progs/test_snprintf.c
index e35129bea0a0..e2ad26150f9b 100644
--- a/tools/testing/selftests/bpf/progs/test_snprintf.c
+++ b/tools/testing/selftests/bpf/progs/test_snprintf.c
@@ -3,7 +3,6 @@
 
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
 
 __u32 pid = 0;
 
diff --git a/tools/testing/selftests/bpf/progs/test_snprintf_single.c b/tools/testing/selftests/bpf/progs/test_snprintf_single.c
index 402adaf344f9..3095837334d3 100644
--- a/tools/testing/selftests/bpf/progs/test_snprintf_single.c
+++ b/tools/testing/selftests/bpf/progs/test_snprintf_single.c
@@ -5,7 +5,7 @@
 #include <bpf/bpf_helpers.h>
 
 /* The format string is filled from the userspace such that loading fails */
-static const char fmt[10];
+const char fmt[10];
 
 SEC("raw_tp/sys_enter")
 int handler(const void *ctx)
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
index a39eba9f5201..a1cc58b10c7c 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
@@ -28,8 +28,8 @@ struct {
 	__type(value, unsigned int);
 } verdict_map SEC(".maps");
 
-static volatile bool test_sockmap; /* toggled by user-space */
-static volatile bool test_ingress; /* toggled by user-space */
+bool test_sockmap = false; /* toggled by user-space */
+bool test_ingress = false; /* toggled by user-space */
 
 SEC("sk_skb/stream_parser")
 int prog_stream_parser(struct __sk_buff *skb)
diff --git a/tools/testing/selftests/bpf/progs/test_static_linked1.c b/tools/testing/selftests/bpf/progs/test_static_linked1.c
index ea1a6c4c7172..4f0b612e1661 100644
--- a/tools/testing/selftests/bpf/progs/test_static_linked1.c
+++ b/tools/testing/selftests/bpf/progs/test_static_linked1.c
@@ -4,10 +4,10 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
-/* 8-byte aligned .bss */
-static volatile long static_var1;
-static volatile int static_var11;
-int var1 = 0;
+/* 8-byte aligned .data */
+static volatile long static_var1 = 2;
+static volatile int static_var2 = 3;
+int var1 = -1;
 /* 4-byte aligned .rodata */
 const volatile int rovar1;
 
@@ -21,7 +21,7 @@ static __noinline int subprog(int x)
 SEC("raw_tp/sys_enter")
 int handler1(const void *ctx)
 {
-	var1 = subprog(rovar1) + static_var1 + static_var11;
+	var1 = subprog(rovar1) + static_var1 + static_var2;
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_static_linked2.c b/tools/testing/selftests/bpf/progs/test_static_linked2.c
index 54d8d1ab577c..766ebd502a60 100644
--- a/tools/testing/selftests/bpf/progs/test_static_linked2.c
+++ b/tools/testing/selftests/bpf/progs/test_static_linked2.c
@@ -4,10 +4,10 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
-/* 4-byte aligned .bss */
-static volatile int static_var2;
-static volatile int static_var22;
-int var2 = 0;
+/* 4-byte aligned .data */
+static volatile int static_var1 = 5;
+static volatile int static_var2 = 6;
+int var2 = -1;
 /* 8-byte aligned .rodata */
 const volatile long rovar2;
 
@@ -21,7 +21,7 @@ static __noinline int subprog(int x)
 SEC("raw_tp/sys_enter")
 int handler2(const void *ctx)
 {
-	var2 = subprog(rovar2) + static_var2 + static_var22;
+	var2 = subprog(rovar2) + static_var1 + static_var2;
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_subprogs.c b/tools/testing/selftests/bpf/progs/test_subprogs.c
index d3c5673c0218..b7c37ca09544 100644
--- a/tools/testing/selftests/bpf/progs/test_subprogs.c
+++ b/tools/testing/selftests/bpf/progs/test_subprogs.c
@@ -4,8 +4,18 @@
 
 const char LICENSE[] SEC("license") = "GPL";
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} array SEC(".maps");
+
 __noinline int sub1(int x)
 {
+	int key = 0;
+
+	bpf_map_lookup_elem(&array, &key);
 	return x + 1;
 }
 
@@ -23,6 +33,9 @@ static __noinline int sub3(int z)
 
 static __noinline int sub4(int w)
 {
+	int key = 0;
+
+	bpf_map_lookup_elem(&array, &key);
 	return w + sub3(5) + sub1(6);
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_tc_bpf.c b/tools/testing/selftests/bpf/progs/test_tc_bpf.c
new file mode 100644
index 000000000000..18a3a7ed924a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_tc_bpf.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+/* Dummy prog to test TC-BPF API */
+
+SEC("classifier")
+int cls(struct __sk_buff *skb)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/trace_printk.c b/tools/testing/selftests/bpf/progs/trace_printk.c
index 8ca7f399b670..119582aa105a 100644
--- a/tools/testing/selftests/bpf/progs/trace_printk.c
+++ b/tools/testing/selftests/bpf/progs/trace_printk.c
@@ -10,11 +10,11 @@ char _license[] SEC("license") = "GPL";
 int trace_printk_ret = 0;
 int trace_printk_ran = 0;
 
-SEC("tp/raw_syscalls/sys_enter")
+const char fmt[] = "Testing,testing %d\n";
+
+SEC("fentry/__x64_sys_nanosleep")
 int sys_enter(void *ctx)
 {
-	static const char fmt[] = "testing,testing %d\n";
-
 	trace_printk_ret = bpf_trace_printk(fmt, sizeof(fmt),
 					    ++trace_printk_ran);
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
new file mode 100644
index 000000000000..880debcbcd65
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+#define KBUILD_MODNAME "foo"
+#include <string.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+/* One map use devmap, another one use devmap_hash for testing */
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+	__uint(max_entries, 1024);
+} map_all SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP_HASH);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(struct bpf_devmap_val));
+	__uint(max_entries, 128);
+} map_egress SEC(".maps");
+
+/* map to store egress interfaces mac addresses */
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __u32);
+	__type(value, __be64);
+	__uint(max_entries, 128);
+} mac_map SEC(".maps");
+
+SEC("xdp_redirect_map_multi")
+int xdp_redirect_map_multi_prog(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	int if_index = ctx->ingress_ifindex;
+	struct ethhdr *eth = data;
+	__u16 h_proto;
+	__u64 nh_off;
+
+	nh_off = sizeof(*eth);
+	if (data + nh_off > data_end)
+		return XDP_DROP;
+
+	h_proto = eth->h_proto;
+
+	/* Using IPv4 for (BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) testing */
+	if (h_proto == bpf_htons(ETH_P_IP))
+		return bpf_redirect_map(&map_all, 0,
+					BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
+	/* Using IPv6 for none flag testing */
+	else if (h_proto == bpf_htons(ETH_P_IPV6))
+		return bpf_redirect_map(&map_all, if_index, 0);
+	/* All others for BPF_F_BROADCAST testing */
+	else
+		return bpf_redirect_map(&map_all, 0, BPF_F_BROADCAST);
+}
+
+/* The following 2 progs are for 2nd devmap prog testing */
+SEC("xdp_redirect_map_ingress")
+int xdp_redirect_map_all_prog(struct xdp_md *ctx)
+{
+	return bpf_redirect_map(&map_egress, 0,
+				BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
+}
+
+SEC("xdp_devmap/map_prog")
+int xdp_devmap_prog(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	__u32 key = ctx->egress_ifindex;
+	struct ethhdr *eth = data;
+	__u64 nh_off;
+	__be64 *mac;
+
+	nh_off = sizeof(*eth);
+	if (data + nh_off > data_end)
+		return XDP_DROP;
+
+	mac = bpf_map_lookup_elem(&mac_map, &key);
+	if (mac)
+		__builtin_memcpy(eth->h_source, mac, ETH_ALEN);
+
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_doc_build.sh b/tools/testing/selftests/bpf/test_doc_build.sh
index 7eb940a7b2eb..ed12111cd2f0 100755
--- a/tools/testing/selftests/bpf/test_doc_build.sh
+++ b/tools/testing/selftests/bpf/test_doc_build.sh
@@ -1,5 +1,6 @@
 #!/bin/bash
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+set -e
 
 # Assume script is located under tools/testing/selftests/bpf/. We want to start
 # build attempts from the top of kernel repository.
diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
index 6a5349f9eb14..7e9049fa3edf 100644
--- a/tools/testing/selftests/bpf/test_lru_map.c
+++ b/tools/testing/selftests/bpf/test_lru_map.c
@@ -231,6 +231,14 @@ static void test_lru_sanity0(int map_type, int map_flags)
 	assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 &&
 	       errno == ENOENT);
 
+	/* lookup elem key=1 and delete it, then check it doesn't exist */
+	key = 1;
+	assert(!bpf_map_lookup_and_delete_elem(lru_map_fd, &key, &value));
+	assert(value[0] == 1234);
+
+	/* remove the same element from the expected map */
+	assert(!bpf_map_delete_elem(expected_map_fd, &key));
+
 	assert(map_equal(lru_map_fd, expected_map_fd));
 
 	close(expected_map_fd);
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 51adc42b2b40..30cbf5d98f7d 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -53,23 +53,30 @@ static void test_hashmap(unsigned int task, void *data)
 
 	value = 0;
 	/* BPF_NOEXIST means add new element if it doesn't exist. */
-	assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 &&
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) < 0 &&
 	       /* key=1 already exists. */
 	       errno == EEXIST);
 
 	/* -1 is an invalid flag. */
-	assert(bpf_map_update_elem(fd, &key, &value, -1) == -1 &&
+	assert(bpf_map_update_elem(fd, &key, &value, -1) < 0 &&
 	       errno == EINVAL);
 
 	/* Check that key=1 can be found. */
 	assert(bpf_map_lookup_elem(fd, &key, &value) == 0 && value == 1234);
 
 	key = 2;
+	value = 1234;
+	/* Insert key=2 element. */
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
+
+	/* Check that key=2 matches the value and delete it */
+	assert(bpf_map_lookup_and_delete_elem(fd, &key, &value) == 0 && value == 1234);
+
 	/* Check that key=2 is not found. */
-	assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT);
+	assert(bpf_map_lookup_elem(fd, &key, &value) < 0 && errno == ENOENT);
 
 	/* BPF_EXIST means update existing element. */
-	assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) == -1 &&
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) < 0 &&
 	       /* key=2 is not there. */
 	       errno == ENOENT);
 
@@ -80,7 +87,7 @@ static void test_hashmap(unsigned int task, void *data)
 	 * inserted due to max_entries limit.
 	 */
 	key = 0;
-	assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 &&
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) < 0 &&
 	       errno == E2BIG);
 
 	/* Update existing element, though the map is full. */
@@ -89,12 +96,12 @@ static void test_hashmap(unsigned int task, void *data)
 	key = 2;
 	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
 	key = 3;
-	assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 &&
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) < 0 &&
 	       errno == E2BIG);
 
 	/* Check that key = 0 doesn't exist. */
 	key = 0;
-	assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT);
+	assert(bpf_map_delete_elem(fd, &key) < 0 && errno == ENOENT);
 
 	/* Iterate over two elements. */
 	assert(bpf_map_get_next_key(fd, NULL, &first_key) == 0 &&
@@ -104,7 +111,7 @@ static void test_hashmap(unsigned int task, void *data)
 	assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 &&
 	       (next_key == 1 || next_key == 2) &&
 	       (next_key != first_key));
-	assert(bpf_map_get_next_key(fd, &next_key, &next_key) == -1 &&
+	assert(bpf_map_get_next_key(fd, &next_key, &next_key) < 0 &&
 	       errno == ENOENT);
 
 	/* Delete both elements. */
@@ -112,13 +119,13 @@ static void test_hashmap(unsigned int task, void *data)
 	assert(bpf_map_delete_elem(fd, &key) == 0);
 	key = 2;
 	assert(bpf_map_delete_elem(fd, &key) == 0);
-	assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT);
+	assert(bpf_map_delete_elem(fd, &key) < 0 && errno == ENOENT);
 
 	key = 0;
 	/* Check that map is empty. */
-	assert(bpf_map_get_next_key(fd, NULL, &next_key) == -1 &&
+	assert(bpf_map_get_next_key(fd, NULL, &next_key) < 0 &&
 	       errno == ENOENT);
-	assert(bpf_map_get_next_key(fd, &key, &next_key) == -1 &&
+	assert(bpf_map_get_next_key(fd, &key, &next_key) < 0 &&
 	       errno == ENOENT);
 
 	close(fd);
@@ -166,15 +173,25 @@ static void test_hashmap_percpu(unsigned int task, void *data)
 	/* Insert key=1 element. */
 	assert(!(expected_key_mask & key));
 	assert(bpf_map_update_elem(fd, &key, value, BPF_ANY) == 0);
+
+	/* Lookup and delete elem key=1 and check value. */
+	assert(bpf_map_lookup_and_delete_elem(fd, &key, value) == 0 &&
+	       bpf_percpu(value,0) == 100);
+
+	for (i = 0; i < nr_cpus; i++)
+		bpf_percpu(value,i) = i + 100;
+
+	/* Insert key=1 element which should not exist. */
+	assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) == 0);
 	expected_key_mask |= key;
 
 	/* BPF_NOEXIST means add new element if it doesn't exist. */
-	assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) == -1 &&
+	assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) < 0 &&
 	       /* key=1 already exists. */
 	       errno == EEXIST);
 
 	/* -1 is an invalid flag. */
-	assert(bpf_map_update_elem(fd, &key, value, -1) == -1 &&
+	assert(bpf_map_update_elem(fd, &key, value, -1) < 0 &&
 	       errno == EINVAL);
 
 	/* Check that key=1 can be found. Value could be 0 if the lookup
@@ -186,10 +203,10 @@ static void test_hashmap_percpu(unsigned int task, void *data)
 
 	key = 2;
 	/* Check that key=2 is not found. */
-	assert(bpf_map_lookup_elem(fd, &key, value) == -1 && errno == ENOENT);
+	assert(bpf_map_lookup_elem(fd, &key, value) < 0 && errno == ENOENT);
 
 	/* BPF_EXIST means update existing element. */
-	assert(bpf_map_update_elem(fd, &key, value, BPF_EXIST) == -1 &&
+	assert(bpf_map_update_elem(fd, &key, value, BPF_EXIST) < 0 &&
 	       /* key=2 is not there. */
 	       errno == ENOENT);
 
@@ -202,11 +219,11 @@ static void test_hashmap_percpu(unsigned int task, void *data)
 	 * inserted due to max_entries limit.
 	 */
 	key = 0;
-	assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) == -1 &&
+	assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) < 0 &&
 	       errno == E2BIG);
 
 	/* Check that key = 0 doesn't exist. */
-	assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT);
+	assert(bpf_map_delete_elem(fd, &key) < 0 && errno == ENOENT);
 
 	/* Iterate over two elements. */
 	assert(bpf_map_get_next_key(fd, NULL, &first_key) == 0 &&
@@ -237,13 +254,13 @@ static void test_hashmap_percpu(unsigned int task, void *data)
 	assert(bpf_map_delete_elem(fd, &key) == 0);
 	key = 2;
 	assert(bpf_map_delete_elem(fd, &key) == 0);
-	assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT);
+	assert(bpf_map_delete_elem(fd, &key) < 0 && errno == ENOENT);
 
 	key = 0;
 	/* Check that map is empty. */
-	assert(bpf_map_get_next_key(fd, NULL, &next_key) == -1 &&
+	assert(bpf_map_get_next_key(fd, NULL, &next_key) < 0 &&
 	       errno == ENOENT);
-	assert(bpf_map_get_next_key(fd, &key, &next_key) == -1 &&
+	assert(bpf_map_get_next_key(fd, &key, &next_key) < 0 &&
 	       errno == ENOENT);
 
 	close(fd);
@@ -360,7 +377,7 @@ static void test_arraymap(unsigned int task, void *data)
 	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
 
 	value = 0;
-	assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 &&
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) < 0 &&
 	       errno == EEXIST);
 
 	/* Check that key=1 can be found. */
@@ -374,11 +391,11 @@ static void test_arraymap(unsigned int task, void *data)
 	 * due to max_entries limit.
 	 */
 	key = 2;
-	assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) == -1 &&
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) < 0 &&
 	       errno == E2BIG);
 
 	/* Check that key = 2 doesn't exist. */
-	assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT);
+	assert(bpf_map_lookup_elem(fd, &key, &value) < 0 && errno == ENOENT);
 
 	/* Iterate over two elements. */
 	assert(bpf_map_get_next_key(fd, NULL, &next_key) == 0 &&
@@ -387,12 +404,12 @@ static void test_arraymap(unsigned int task, void *data)
 	       next_key == 0);
 	assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 &&
 	       next_key == 1);
-	assert(bpf_map_get_next_key(fd, &next_key, &next_key) == -1 &&
+	assert(bpf_map_get_next_key(fd, &next_key, &next_key) < 0 &&
 	       errno == ENOENT);
 
 	/* Delete shouldn't succeed. */
 	key = 1;
-	assert(bpf_map_delete_elem(fd, &key) == -1 && errno == EINVAL);
+	assert(bpf_map_delete_elem(fd, &key) < 0 && errno == EINVAL);
 
 	close(fd);
 }
@@ -418,7 +435,7 @@ static void test_arraymap_percpu(unsigned int task, void *data)
 	assert(bpf_map_update_elem(fd, &key, values, BPF_ANY) == 0);
 
 	bpf_percpu(values, 0) = 0;
-	assert(bpf_map_update_elem(fd, &key, values, BPF_NOEXIST) == -1 &&
+	assert(bpf_map_update_elem(fd, &key, values, BPF_NOEXIST) < 0 &&
 	       errno == EEXIST);
 
 	/* Check that key=1 can be found. */
@@ -433,11 +450,11 @@ static void test_arraymap_percpu(unsigned int task, void *data)
 
 	/* Check that key=2 cannot be inserted due to max_entries limit. */
 	key = 2;
-	assert(bpf_map_update_elem(fd, &key, values, BPF_EXIST) == -1 &&
+	assert(bpf_map_update_elem(fd, &key, values, BPF_EXIST) < 0 &&
 	       errno == E2BIG);
 
 	/* Check that key = 2 doesn't exist. */
-	assert(bpf_map_lookup_elem(fd, &key, values) == -1 && errno == ENOENT);
+	assert(bpf_map_lookup_elem(fd, &key, values) < 0 && errno == ENOENT);
 
 	/* Iterate over two elements. */
 	assert(bpf_map_get_next_key(fd, NULL, &next_key) == 0 &&
@@ -446,12 +463,12 @@ static void test_arraymap_percpu(unsigned int task, void *data)
 	       next_key == 0);
 	assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 &&
 	       next_key == 1);
-	assert(bpf_map_get_next_key(fd, &next_key, &next_key) == -1 &&
+	assert(bpf_map_get_next_key(fd, &next_key, &next_key) < 0 &&
 	       errno == ENOENT);
 
 	/* Delete shouldn't succeed. */
 	key = 1;
-	assert(bpf_map_delete_elem(fd, &key) == -1 && errno == EINVAL);
+	assert(bpf_map_delete_elem(fd, &key) < 0 && errno == EINVAL);
 
 	close(fd);
 }
@@ -555,7 +572,7 @@ static void test_queuemap(unsigned int task, void *data)
 		assert(bpf_map_update_elem(fd, NULL, &vals[i], 0) == 0);
 
 	/* Check that element cannot be pushed due to max_entries limit */
-	assert(bpf_map_update_elem(fd, NULL, &val, 0) == -1 &&
+	assert(bpf_map_update_elem(fd, NULL, &val, 0) < 0 &&
 	       errno == E2BIG);
 
 	/* Peek element */
@@ -571,12 +588,12 @@ static void test_queuemap(unsigned int task, void *data)
 		       val == vals[i]);
 
 	/* Check that there are not elements left */
-	assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == -1 &&
+	assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) < 0 &&
 	       errno == ENOENT);
 
 	/* Check that non supported functions set errno to EINVAL */
-	assert(bpf_map_delete_elem(fd, NULL) == -1 && errno == EINVAL);
-	assert(bpf_map_get_next_key(fd, NULL, NULL) == -1 && errno == EINVAL);
+	assert(bpf_map_delete_elem(fd, NULL) < 0 && errno == EINVAL);
+	assert(bpf_map_get_next_key(fd, NULL, NULL) < 0 && errno == EINVAL);
 
 	close(fd);
 }
@@ -613,7 +630,7 @@ static void test_stackmap(unsigned int task, void *data)
 		assert(bpf_map_update_elem(fd, NULL, &vals[i], 0) == 0);
 
 	/* Check that element cannot be pushed due to max_entries limit */
-	assert(bpf_map_update_elem(fd, NULL, &val, 0) == -1 &&
+	assert(bpf_map_update_elem(fd, NULL, &val, 0) < 0 &&
 	       errno == E2BIG);
 
 	/* Peek element */
@@ -629,12 +646,12 @@ static void test_stackmap(unsigned int task, void *data)
 		       val == vals[i]);
 
 	/* Check that there are not elements left */
-	assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == -1 &&
+	assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) < 0 &&
 	       errno == ENOENT);
 
 	/* Check that non supported functions set errno to EINVAL */
-	assert(bpf_map_delete_elem(fd, NULL) == -1 && errno == EINVAL);
-	assert(bpf_map_get_next_key(fd, NULL, NULL) == -1 && errno == EINVAL);
+	assert(bpf_map_delete_elem(fd, NULL) < 0 && errno == EINVAL);
+	assert(bpf_map_get_next_key(fd, NULL, NULL) < 0 && errno == EINVAL);
 
 	close(fd);
 }
@@ -835,7 +852,7 @@ static void test_sockmap(unsigned int tasks, void *data)
 	}
 
 	bpf_map_rx = bpf_object__find_map_by_name(obj, "sock_map_rx");
-	if (IS_ERR(bpf_map_rx)) {
+	if (!bpf_map_rx) {
 		printf("Failed to load map rx from verdict prog\n");
 		goto out_sockmap;
 	}
@@ -847,7 +864,7 @@ static void test_sockmap(unsigned int tasks, void *data)
 	}
 
 	bpf_map_tx = bpf_object__find_map_by_name(obj, "sock_map_tx");
-	if (IS_ERR(bpf_map_tx)) {
+	if (!bpf_map_tx) {
 		printf("Failed to load map tx from verdict prog\n");
 		goto out_sockmap;
 	}
@@ -859,7 +876,7 @@ static void test_sockmap(unsigned int tasks, void *data)
 	}
 
 	bpf_map_msg = bpf_object__find_map_by_name(obj, "sock_map_msg");
-	if (IS_ERR(bpf_map_msg)) {
+	if (!bpf_map_msg) {
 		printf("Failed to load map msg from msg_verdict prog\n");
 		goto out_sockmap;
 	}
@@ -871,7 +888,7 @@ static void test_sockmap(unsigned int tasks, void *data)
 	}
 
 	bpf_map_break = bpf_object__find_map_by_name(obj, "sock_map_break");
-	if (IS_ERR(bpf_map_break)) {
+	if (!bpf_map_break) {
 		printf("Failed to load map tx from verdict prog\n");
 		goto out_sockmap;
 	}
@@ -1153,7 +1170,7 @@ static void test_map_in_map(void)
 	}
 
 	map = bpf_object__find_map_by_name(obj, "mim_array");
-	if (IS_ERR(map)) {
+	if (!map) {
 		printf("Failed to load array of maps from test prog\n");
 		goto out_map_in_map;
 	}
@@ -1164,7 +1181,7 @@ static void test_map_in_map(void)
 	}
 
 	map = bpf_object__find_map_by_name(obj, "mim_hash");
-	if (IS_ERR(map)) {
+	if (!map) {
 		printf("Failed to load hash of maps from test prog\n");
 		goto out_map_in_map;
 	}
@@ -1177,7 +1194,7 @@ static void test_map_in_map(void)
 	bpf_object__load(obj);
 
 	map = bpf_object__find_map_by_name(obj, "mim_array");
-	if (IS_ERR(map)) {
+	if (!map) {
 		printf("Failed to load array of maps from test prog\n");
 		goto out_map_in_map;
 	}
@@ -1194,7 +1211,7 @@ static void test_map_in_map(void)
 	}
 
 	map = bpf_object__find_map_by_name(obj, "mim_hash");
-	if (IS_ERR(map)) {
+	if (!map) {
 		printf("Failed to load hash of maps from test prog\n");
 		goto out_map_in_map;
 	}
@@ -1246,7 +1263,7 @@ static void test_map_large(void)
 	}
 
 	key.c = -1;
-	assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 &&
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) < 0 &&
 	       errno == E2BIG);
 
 	/* Iterate through all elements. */
@@ -1254,12 +1271,12 @@ static void test_map_large(void)
 	key.c = -1;
 	for (i = 0; i < MAP_SIZE; i++)
 		assert(bpf_map_get_next_key(fd, &key, &key) == 0);
-	assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT);
+	assert(bpf_map_get_next_key(fd, &key, &key) < 0 && errno == ENOENT);
 
 	key.c = 0;
 	assert(bpf_map_lookup_elem(fd, &key, &value) == 0 && value == 0);
 	key.a = 1;
-	assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT);
+	assert(bpf_map_lookup_elem(fd, &key, &value) < 0 && errno == ENOENT);
 
 	close(fd);
 }
@@ -1391,7 +1408,7 @@ static void test_map_parallel(void)
 	run_parallel(TASKS, test_update_delete, data);
 
 	/* Check that key=0 is already there. */
-	assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 &&
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) < 0 &&
 	       errno == EEXIST);
 
 	/* Check that all elements were inserted. */
@@ -1399,7 +1416,7 @@ static void test_map_parallel(void)
 	key = -1;
 	for (i = 0; i < MAP_SIZE; i++)
 		assert(bpf_map_get_next_key(fd, &key, &key) == 0);
-	assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT);
+	assert(bpf_map_get_next_key(fd, &key, &key) < 0 && errno == ENOENT);
 
 	/* Another check for all elements */
 	for (i = 0; i < MAP_SIZE; i++) {
@@ -1415,8 +1432,8 @@ static void test_map_parallel(void)
 
 	/* Nothing should be left. */
 	key = -1;
-	assert(bpf_map_get_next_key(fd, NULL, &key) == -1 && errno == ENOENT);
-	assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT);
+	assert(bpf_map_get_next_key(fd, NULL, &key) < 0 && errno == ENOENT);
+	assert(bpf_map_get_next_key(fd, &key, &key) < 0 && errno == ENOENT);
 }
 
 static void test_map_rdonly(void)
@@ -1434,12 +1451,12 @@ static void test_map_rdonly(void)
 	key = 1;
 	value = 1234;
 	/* Try to insert key=1 element. */
-	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == -1 &&
+	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) < 0 &&
 	       errno == EPERM);
 
 	/* Check that key=1 is not found. */
-	assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT);
-	assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == ENOENT);
+	assert(bpf_map_lookup_elem(fd, &key, &value) < 0 && errno == ENOENT);
+	assert(bpf_map_get_next_key(fd, &key, &value) < 0 && errno == ENOENT);
 
 	close(fd);
 }
@@ -1462,8 +1479,8 @@ static void test_map_wronly_hash(void)
 	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
 
 	/* Check that reading elements and keys from the map is not allowed. */
-	assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == EPERM);
-	assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == EPERM);
+	assert(bpf_map_lookup_elem(fd, &key, &value) < 0 && errno == EPERM);
+	assert(bpf_map_get_next_key(fd, &key, &value) < 0 && errno == EPERM);
 
 	close(fd);
 }
@@ -1490,10 +1507,10 @@ static void test_map_wronly_stack_or_queue(enum bpf_map_type map_type)
 	assert(bpf_map_update_elem(fd, NULL, &value, BPF_ANY) == 0);
 
 	/* Peek element should fail */
-	assert(bpf_map_lookup_elem(fd, NULL, &value) == -1 && errno == EPERM);
+	assert(bpf_map_lookup_elem(fd, NULL, &value) < 0 && errno == EPERM);
 
 	/* Pop element should fail */
-	assert(bpf_map_lookup_and_delete_elem(fd, NULL, &value) == -1 &&
+	assert(bpf_map_lookup_and_delete_elem(fd, NULL, &value) < 0 &&
 	       errno == EPERM);
 
 	close(fd);
@@ -1547,7 +1564,7 @@ static void prepare_reuseport_grp(int type, int map_fd, size_t map_elem_size,
 			value = &fd32;
 		}
 		err = bpf_map_update_elem(map_fd, &index0, value, BPF_ANY);
-		CHECK(err != -1 || errno != EINVAL,
+		CHECK(err >= 0 || errno != EINVAL,
 		      "reuseport array update unbound sk",
 		      "sock_type:%d err:%d errno:%d\n",
 		      type, err, errno);
@@ -1576,7 +1593,7 @@ static void prepare_reuseport_grp(int type, int map_fd, size_t map_elem_size,
 			 */
 			err = bpf_map_update_elem(map_fd, &index0, value,
 						  BPF_ANY);
-			CHECK(err != -1 || errno != EINVAL,
+			CHECK(err >= 0 || errno != EINVAL,
 			      "reuseport array update non-listening sk",
 			      "sock_type:%d err:%d errno:%d\n",
 			      type, err, errno);
@@ -1606,31 +1623,31 @@ static void test_reuseport_array(void)
 
 	map_fd = bpf_create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
 				sizeof(__u32), sizeof(__u64), array_size, 0);
-	CHECK(map_fd == -1, "reuseport array create",
+	CHECK(map_fd < 0, "reuseport array create",
 	      "map_fd:%d, errno:%d\n", map_fd, errno);
 
 	/* Test lookup/update/delete with invalid index */
 	err = bpf_map_delete_elem(map_fd, &bad_index);
-	CHECK(err != -1 || errno != E2BIG, "reuseport array del >=max_entries",
+	CHECK(err >= 0 || errno != E2BIG, "reuseport array del >=max_entries",
 	      "err:%d errno:%d\n", err, errno);
 
 	err = bpf_map_update_elem(map_fd, &bad_index, &fd64, BPF_ANY);
-	CHECK(err != -1 || errno != E2BIG,
+	CHECK(err >= 0 || errno != E2BIG,
 	      "reuseport array update >=max_entries",
 	      "err:%d errno:%d\n", err, errno);
 
 	err = bpf_map_lookup_elem(map_fd, &bad_index, &map_cookie);
-	CHECK(err != -1 || errno != ENOENT,
+	CHECK(err >= 0 || errno != ENOENT,
 	      "reuseport array update >=max_entries",
 	      "err:%d errno:%d\n", err, errno);
 
 	/* Test lookup/delete non existence elem */
 	err = bpf_map_lookup_elem(map_fd, &index3, &map_cookie);
-	CHECK(err != -1 || errno != ENOENT,
+	CHECK(err >= 0 || errno != ENOENT,
 	      "reuseport array lookup not-exist elem",
 	      "err:%d errno:%d\n", err, errno);
 	err = bpf_map_delete_elem(map_fd, &index3);
-	CHECK(err != -1 || errno != ENOENT,
+	CHECK(err >= 0 || errno != ENOENT,
 	      "reuseport array del not-exist elem",
 	      "err:%d errno:%d\n", err, errno);
 
@@ -1644,7 +1661,7 @@ static void test_reuseport_array(void)
 		/* BPF_EXIST failure case */
 		err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx],
 					  BPF_EXIST);
-		CHECK(err != -1 || errno != ENOENT,
+		CHECK(err >= 0 || errno != ENOENT,
 		      "reuseport array update empty elem BPF_EXIST",
 		      "sock_type:%d err:%d errno:%d\n",
 		      type, err, errno);
@@ -1653,7 +1670,7 @@ static void test_reuseport_array(void)
 		/* BPF_NOEXIST success case */
 		err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx],
 					  BPF_NOEXIST);
-		CHECK(err == -1,
+		CHECK(err < 0,
 		      "reuseport array update empty elem BPF_NOEXIST",
 		      "sock_type:%d err:%d errno:%d\n",
 		      type, err, errno);
@@ -1662,7 +1679,7 @@ static void test_reuseport_array(void)
 		/* BPF_EXIST success case. */
 		err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx],
 					  BPF_EXIST);
-		CHECK(err == -1,
+		CHECK(err < 0,
 		      "reuseport array update same elem BPF_EXIST",
 		      "sock_type:%d err:%d errno:%d\n", type, err, errno);
 		fds_idx = REUSEPORT_FD_IDX(err, fds_idx);
@@ -1670,7 +1687,7 @@ static void test_reuseport_array(void)
 		/* BPF_NOEXIST failure case */
 		err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx],
 					  BPF_NOEXIST);
-		CHECK(err != -1 || errno != EEXIST,
+		CHECK(err >= 0 || errno != EEXIST,
 		      "reuseport array update non-empty elem BPF_NOEXIST",
 		      "sock_type:%d err:%d errno:%d\n",
 		      type, err, errno);
@@ -1679,7 +1696,7 @@ static void test_reuseport_array(void)
 		/* BPF_ANY case (always succeed) */
 		err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx],
 					  BPF_ANY);
-		CHECK(err == -1,
+		CHECK(err < 0,
 		      "reuseport array update same sk with BPF_ANY",
 		      "sock_type:%d err:%d errno:%d\n", type, err, errno);
 
@@ -1688,32 +1705,32 @@ static void test_reuseport_array(void)
 
 		/* The same sk cannot be added to reuseport_array twice */
 		err = bpf_map_update_elem(map_fd, &index3, &fd64, BPF_ANY);
-		CHECK(err != -1 || errno != EBUSY,
+		CHECK(err >= 0 || errno != EBUSY,
 		      "reuseport array update same sk with same index",
 		      "sock_type:%d err:%d errno:%d\n",
 		      type, err, errno);
 
 		err = bpf_map_update_elem(map_fd, &index0, &fd64, BPF_ANY);
-		CHECK(err != -1 || errno != EBUSY,
+		CHECK(err >= 0 || errno != EBUSY,
 		      "reuseport array update same sk with different index",
 		      "sock_type:%d err:%d errno:%d\n",
 		      type, err, errno);
 
 		/* Test delete elem */
 		err = bpf_map_delete_elem(map_fd, &index3);
-		CHECK(err == -1, "reuseport array delete sk",
+		CHECK(err < 0, "reuseport array delete sk",
 		      "sock_type:%d err:%d errno:%d\n",
 		      type, err, errno);
 
 		/* Add it back with BPF_NOEXIST */
 		err = bpf_map_update_elem(map_fd, &index3, &fd64, BPF_NOEXIST);
-		CHECK(err == -1,
+		CHECK(err < 0,
 		      "reuseport array re-add with BPF_NOEXIST after del",
 		      "sock_type:%d err:%d errno:%d\n", type, err, errno);
 
 		/* Test cookie */
 		err = bpf_map_lookup_elem(map_fd, &index3, &map_cookie);
-		CHECK(err == -1 || sk_cookie != map_cookie,
+		CHECK(err < 0 || sk_cookie != map_cookie,
 		      "reuseport array lookup re-added sk",
 		      "sock_type:%d err:%d errno:%d sk_cookie:0x%llx map_cookie:0x%llxn",
 		      type, err, errno, sk_cookie, map_cookie);
@@ -1722,7 +1739,7 @@ static void test_reuseport_array(void)
 		for (f = 0; f < ARRAY_SIZE(grpa_fds64); f++)
 			close(grpa_fds64[f]);
 		err = bpf_map_lookup_elem(map_fd, &index3, &map_cookie);
-		CHECK(err != -1 || errno != ENOENT,
+		CHECK(err >= 0 || errno != ENOENT,
 		      "reuseport array lookup after close()",
 		      "sock_type:%d err:%d errno:%d\n",
 		      type, err, errno);
@@ -1733,7 +1750,7 @@ static void test_reuseport_array(void)
 	CHECK(fd64 == -1, "socket(SOCK_RAW)", "err:%d errno:%d\n",
 	      err, errno);
 	err = bpf_map_update_elem(map_fd, &index3, &fd64, BPF_NOEXIST);
-	CHECK(err != -1 || errno != ENOTSUPP, "reuseport array update SOCK_RAW",
+	CHECK(err >= 0 || errno != ENOTSUPP, "reuseport array update SOCK_RAW",
 	      "err:%d errno:%d\n", err, errno);
 	close(fd64);
 
@@ -1743,16 +1760,16 @@ static void test_reuseport_array(void)
 	/* Test 32 bit fd */
 	map_fd = bpf_create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
 				sizeof(__u32), sizeof(__u32), array_size, 0);
-	CHECK(map_fd == -1, "reuseport array create",
+	CHECK(map_fd < 0, "reuseport array create",
 	      "map_fd:%d, errno:%d\n", map_fd, errno);
 	prepare_reuseport_grp(SOCK_STREAM, map_fd, sizeof(__u32), &fd64,
 			      &sk_cookie, 1);
 	fd = fd64;
 	err = bpf_map_update_elem(map_fd, &index3, &fd, BPF_NOEXIST);
-	CHECK(err == -1, "reuseport array update 32 bit fd",
+	CHECK(err < 0, "reuseport array update 32 bit fd",
 	      "err:%d errno:%d\n", err, errno);
 	err = bpf_map_lookup_elem(map_fd, &index3, &map_cookie);
-	CHECK(err != -1 || errno != ENOSPC,
+	CHECK(err >= 0 || errno != ENOSPC,
 	      "reuseport array lookup 32 bit fd",
 	      "err:%d errno:%d\n", err, errno);
 	close(fd);
@@ -1798,6 +1815,8 @@ int main(void)
 {
 	srand(time(NULL));
 
+	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+
 	map_flags = 0;
 	run_all_tests();
 
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 6396932b97e2..6f103106a39b 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -737,6 +737,9 @@ int main(int argc, char **argv)
 	if (err)
 		return err;
 
+	/* Use libbpf 1.0 API mode */
+	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+
 	libbpf_set_print(libbpf_print_fn);
 
 	srand(time(NULL));
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index dda52cb649dc..8ef7f334e715 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -249,16 +249,17 @@ extern int test__join_cgroup(const char *path);
 #define ASSERT_OK_PTR(ptr, name) ({					\
 	static int duration = 0;					\
 	const void *___res = (ptr);					\
-	bool ___ok = !IS_ERR_OR_NULL(___res);				\
-	CHECK(!___ok, (name),						\
-	      "unexpected error: %ld\n", PTR_ERR(___res));		\
+	int ___err = libbpf_get_error(___res);				\
+	bool ___ok = ___err == 0;					\
+	CHECK(!___ok, (name), "unexpected error: %d\n", ___err);	\
 	___ok;								\
 })
 
 #define ASSERT_ERR_PTR(ptr, name) ({					\
 	static int duration = 0;					\
 	const void *___res = (ptr);					\
-	bool ___ok = IS_ERR(___res);					\
+	int ___err = libbpf_get_error(___res);				\
+	bool ___ok = ___err != 0;					\
 	CHECK(!___ok, (name), "unexpected pointer: %p\n", ___res);	\
 	___ok;								\
 })
diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c
index 73da7fe8c152..4a39304cc5a6 100644
--- a/tools/testing/selftests/bpf/test_tcpnotify_user.c
+++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c
@@ -82,6 +82,8 @@ int main(int argc, char **argv)
 	cpu_set_t cpuset;
 	__u32 key = 0;
 
+	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+
 	CPU_ZERO(&cpuset);
 	CPU_SET(0, &cpuset);
 	pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset);
@@ -116,7 +118,7 @@ int main(int argc, char **argv)
 
 	pb_opts.sample_cb = dummyfn;
 	pb = perf_buffer__new(bpf_map__fd(perf_map), 8, &pb_opts);
-	if (IS_ERR(pb))
+	if (!pb)
 		goto err;
 
 	pthread_create(&tid, NULL, poller_thread, pb);
@@ -163,7 +165,6 @@ err:
 	bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
 	close(cg_fd);
 	cleanup_cgroup_environment();
-	if (!IS_ERR_OR_NULL(pb))
-		perf_buffer__free(pb);
+	perf_buffer__free(pb);
 	return error;
 }
diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
new file mode 100755
index 000000000000..1538373157e3
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
@@ -0,0 +1,204 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test topology:
+#     - - - - - - - - - - - - - - - - - - - - - - - - -
+#    | veth1         veth2         veth3 |  ... init net
+#     - -| - - - - - - | - - - - - - | - -
+#    ---------     ---------     ---------
+#    | veth0 |     | veth0 |     | veth0 |  ...
+#    ---------     ---------     ---------
+#       ns1           ns2           ns3
+#
+# Test modules:
+# XDP modes: generic, native, native + egress_prog
+#
+# Test cases:
+#   ARP: Testing BPF_F_BROADCAST, the ingress interface also should receive
+#   the redirects.
+#      ns1 -> gw: ns1, ns2, ns3, should receive the arp request
+#   IPv4: Testing BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, the ingress
+#   interface should not receive the redirects.
+#      ns1 -> gw: ns1 should not receive, ns2, ns3 should receive redirects.
+#   IPv6: Testing none flag, all the pkts should be redirected back
+#      ping test: ns1 -> ns2 (block), echo requests will be redirect back
+#   egress_prog:
+#      all src mac should be egress interface's mac
+
+# netns numbers
+NUM=3
+IFACES=""
+DRV_MODE="xdpgeneric xdpdrv xdpegress"
+PASS=0
+FAIL=0
+
+test_pass()
+{
+	echo "Pass: $@"
+	PASS=$((PASS + 1))
+}
+
+test_fail()
+{
+	echo "fail: $@"
+	FAIL=$((FAIL + 1))
+}
+
+clean_up()
+{
+	for i in $(seq $NUM); do
+		ip link del veth$i 2> /dev/null
+		ip netns del ns$i 2> /dev/null
+	done
+}
+
+# Kselftest framework requirement - SKIP code is 4.
+check_env()
+{
+	ip link set dev lo xdpgeneric off &>/dev/null
+	if [ $? -ne 0 ];then
+		echo "selftests: [SKIP] Could not run test without the ip xdpgeneric support"
+		exit 4
+	fi
+
+	which tcpdump &>/dev/null
+	if [ $? -ne 0 ];then
+		echo "selftests: [SKIP] Could not run test without tcpdump"
+		exit 4
+	fi
+}
+
+setup_ns()
+{
+	local mode=$1
+	IFACES=""
+
+	if [ "$mode" = "xdpegress" ]; then
+		mode="xdpdrv"
+	fi
+
+	for i in $(seq $NUM); do
+	        ip netns add ns$i
+	        ip link add veth$i type veth peer name veth0 netns ns$i
+		ip link set veth$i up
+		ip -n ns$i link set veth0 up
+
+		ip -n ns$i addr add 192.0.2.$i/24 dev veth0
+		ip -n ns$i addr add 2001:db8::$i/64 dev veth0
+		# Add a neigh entry for IPv4 ping test
+		ip -n ns$i neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0
+		ip -n ns$i link set veth0 $mode obj \
+			xdp_dummy.o sec xdp_dummy &> /dev/null || \
+			{ test_fail "Unable to load dummy xdp" && exit 1; }
+		IFACES="$IFACES veth$i"
+		veth_mac[$i]=$(ip link show veth$i | awk '/link\/ether/ {print $2}')
+	done
+}
+
+do_egress_tests()
+{
+	local mode=$1
+
+	# mac test
+	ip netns exec ns2 tcpdump -e -i veth0 -nn -l -e &> mac_ns1-2_${mode}.log &
+	ip netns exec ns3 tcpdump -e -i veth0 -nn -l -e &> mac_ns1-3_${mode}.log &
+	sleep 0.5
+	ip netns exec ns1 ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null
+	sleep 0.5
+	pkill -9 tcpdump
+
+	# mac check
+	grep -q "${veth_mac[2]} > ff:ff:ff:ff:ff:ff" mac_ns1-2_${mode}.log && \
+	       test_pass "$mode mac ns1-2" || test_fail "$mode mac ns1-2"
+	grep -q "${veth_mac[3]} > ff:ff:ff:ff:ff:ff" mac_ns1-3_${mode}.log && \
+		test_pass "$mode mac ns1-3" || test_fail "$mode mac ns1-3"
+}
+
+do_ping_tests()
+{
+	local mode=$1
+
+	# ping6 test: echo request should be redirect back to itself, not others
+	ip netns exec ns1 ip neigh add 2001:db8::2 dev veth0 lladdr 00:00:00:00:00:02
+
+	ip netns exec ns1 tcpdump -i veth0 -nn -l -e &> ns1-1_${mode}.log &
+	ip netns exec ns2 tcpdump -i veth0 -nn -l -e &> ns1-2_${mode}.log &
+	ip netns exec ns3 tcpdump -i veth0 -nn -l -e &> ns1-3_${mode}.log &
+	sleep 0.5
+	# ARP test
+	ip netns exec ns1 ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null
+	# IPv4 test
+	ip netns exec ns1 ping 192.0.2.253 -i 0.1 -c 4 &> /dev/null
+	# IPv6 test
+	ip netns exec ns1 ping6 2001:db8::2 -i 0.1 -c 2 &> /dev/null
+	sleep 0.5
+	pkill -9 tcpdump
+
+	# All netns should receive the redirect arp requests
+	[ $(grep -c "who-has 192.0.2.254" ns1-1_${mode}.log) -gt 4 ] && \
+		test_pass "$mode arp(F_BROADCAST) ns1-1" || \
+		test_fail "$mode arp(F_BROADCAST) ns1-1"
+	[ $(grep -c "who-has 192.0.2.254" ns1-2_${mode}.log) -le 4 ] && \
+		test_pass "$mode arp(F_BROADCAST) ns1-2" || \
+		test_fail "$mode arp(F_BROADCAST) ns1-2"
+	[ $(grep -c "who-has 192.0.2.254" ns1-3_${mode}.log) -le 4 ] && \
+		test_pass "$mode arp(F_BROADCAST) ns1-3" || \
+		test_fail "$mode arp(F_BROADCAST) ns1-3"
+
+	# ns1 should not receive the redirect echo request, others should
+	[ $(grep -c "ICMP echo request" ns1-1_${mode}.log) -eq 4 ] && \
+		test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1" || \
+		test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1"
+	[ $(grep -c "ICMP echo request" ns1-2_${mode}.log) -eq 4 ] && \
+		test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2" || \
+		test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2"
+	[ $(grep -c "ICMP echo request" ns1-3_${mode}.log) -eq 4 ] && \
+		test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3" || \
+		test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3"
+
+	# ns1 should receive the echo request, ns2 should not
+	[ $(grep -c "ICMP6, echo request" ns1-1_${mode}.log) -eq 4 ] && \
+		test_pass "$mode IPv6 (no flags) ns1-1" || \
+		test_fail "$mode IPv6 (no flags) ns1-1"
+	[ $(grep -c "ICMP6, echo request" ns1-2_${mode}.log) -eq 0 ] && \
+		test_pass "$mode IPv6 (no flags) ns1-2" || \
+		test_fail "$mode IPv6 (no flags) ns1-2"
+}
+
+do_tests()
+{
+	local mode=$1
+	local drv_p
+
+	case ${mode} in
+		xdpdrv)  drv_p="-N";;
+		xdpegress) drv_p="-X";;
+		xdpgeneric) drv_p="-S";;
+	esac
+
+	./xdp_redirect_multi $drv_p $IFACES &> xdp_redirect_${mode}.log &
+	xdp_pid=$!
+	sleep 1
+
+	if [ "$mode" = "xdpegress" ]; then
+		do_egress_tests $mode
+	else
+		do_ping_tests $mode
+	fi
+
+	kill $xdp_pid
+}
+
+trap clean_up 0 2 3 6 9
+
+check_env
+rm -f xdp_redirect_*.log ns*.log mac_ns*.log
+
+for mode in ${DRV_MODE}; do
+	setup_ns $mode
+	do_tests $mode
+	clean_up
+done
+
+echo "Summary: PASS $PASS, FAIL $FAIL"
+[ $FAIL -eq 0 ] && exit 0 || exit 1
diff --git a/tools/testing/selftests/bpf/xdp_redirect_multi.c b/tools/testing/selftests/bpf/xdp_redirect_multi.c
new file mode 100644
index 000000000000..3696a8f32c23
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_redirect_multi.c
@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/if_link.h>
+#include <assert.h>
+#include <errno.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <net/if.h>
+#include <unistd.h>
+#include <libgen.h>
+#include <sys/resource.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include "bpf_util.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#define MAX_IFACE_NUM 32
+#define MAX_INDEX_NUM 1024
+
+static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static int ifaces[MAX_IFACE_NUM] = {};
+
+static void int_exit(int sig)
+{
+	__u32 prog_id = 0;
+	int i;
+
+	for (i = 0; ifaces[i] > 0; i++) {
+		if (bpf_get_link_xdp_id(ifaces[i], &prog_id, xdp_flags)) {
+			printf("bpf_get_link_xdp_id failed\n");
+			exit(1);
+		}
+		if (prog_id)
+			bpf_set_link_xdp_fd(ifaces[i], -1, xdp_flags);
+	}
+
+	exit(0);
+}
+
+static int get_mac_addr(unsigned int ifindex, void *mac_addr)
+{
+	char ifname[IF_NAMESIZE];
+	struct ifreq ifr;
+	int fd, ret = -1;
+
+	fd = socket(AF_INET, SOCK_DGRAM, 0);
+	if (fd < 0)
+		return ret;
+
+	if (!if_indextoname(ifindex, ifname))
+		goto err_out;
+
+	strcpy(ifr.ifr_name, ifname);
+
+	if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
+		goto err_out;
+
+	memcpy(mac_addr, ifr.ifr_hwaddr.sa_data, 6 * sizeof(char));
+	ret = 0;
+
+err_out:
+	close(fd);
+	return ret;
+}
+
+static void usage(const char *prog)
+{
+	fprintf(stderr,
+		"usage: %s [OPTS] <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n"
+		"OPTS:\n"
+		"    -S    use skb-mode\n"
+		"    -N    enforce native mode\n"
+		"    -F    force loading prog\n"
+		"    -X    load xdp program on egress\n",
+		prog);
+}
+
+int main(int argc, char **argv)
+{
+	int prog_fd, group_all, mac_map;
+	struct bpf_program *ingress_prog, *egress_prog;
+	struct bpf_prog_load_attr prog_load_attr = {
+		.prog_type = BPF_PROG_TYPE_UNSPEC,
+	};
+	int i, ret, opt, egress_prog_fd = 0;
+	struct bpf_devmap_val devmap_val;
+	bool attach_egress_prog = false;
+	unsigned char mac_addr[6];
+	char ifname[IF_NAMESIZE];
+	struct bpf_object *obj;
+	unsigned int ifindex;
+	char filename[256];
+
+	while ((opt = getopt(argc, argv, "SNFX")) != -1) {
+		switch (opt) {
+		case 'S':
+			xdp_flags |= XDP_FLAGS_SKB_MODE;
+			break;
+		case 'N':
+			/* default, set below */
+			break;
+		case 'F':
+			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+			break;
+		case 'X':
+			attach_egress_prog = true;
+			break;
+		default:
+			usage(basename(argv[0]));
+			return 1;
+		}
+	}
+
+	if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) {
+		xdp_flags |= XDP_FLAGS_DRV_MODE;
+	} else if (attach_egress_prog) {
+		printf("Load xdp program on egress with SKB mode not supported yet\n");
+		goto err_out;
+	}
+
+	if (optind == argc) {
+		printf("usage: %s <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n", argv[0]);
+		goto err_out;
+	}
+
+	printf("Get interfaces");
+	for (i = 0; i < MAX_IFACE_NUM && argv[optind + i]; i++) {
+		ifaces[i] = if_nametoindex(argv[optind + i]);
+		if (!ifaces[i])
+			ifaces[i] = strtoul(argv[optind + i], NULL, 0);
+		if (!if_indextoname(ifaces[i], ifname)) {
+			perror("Invalid interface name or i");
+			goto err_out;
+		}
+		if (ifaces[i] > MAX_INDEX_NUM) {
+			printf("Interface index to large\n");
+			goto err_out;
+		}
+		printf(" %d", ifaces[i]);
+	}
+	printf("\n");
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	prog_load_attr.file = filename;
+
+	if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+		goto err_out;
+
+	if (attach_egress_prog)
+		group_all = bpf_object__find_map_fd_by_name(obj, "map_egress");
+	else
+		group_all = bpf_object__find_map_fd_by_name(obj, "map_all");
+	mac_map = bpf_object__find_map_fd_by_name(obj, "mac_map");
+
+	if (group_all < 0 || mac_map < 0) {
+		printf("bpf_object__find_map_fd_by_name failed\n");
+		goto err_out;
+	}
+
+	if (attach_egress_prog) {
+		/* Find ingress/egress prog for 2nd xdp prog */
+		ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_all_prog");
+		egress_prog = bpf_object__find_program_by_name(obj, "xdp_devmap_prog");
+		if (!ingress_prog || !egress_prog) {
+			printf("finding ingress/egress_prog in obj file failed\n");
+			goto err_out;
+		}
+		prog_fd = bpf_program__fd(ingress_prog);
+		egress_prog_fd = bpf_program__fd(egress_prog);
+		if (prog_fd < 0 || egress_prog_fd < 0) {
+			printf("find egress_prog fd failed\n");
+			goto err_out;
+		}
+	}
+
+	signal(SIGINT, int_exit);
+	signal(SIGTERM, int_exit);
+
+	/* Init forward multicast groups and exclude group */
+	for (i = 0; ifaces[i] > 0; i++) {
+		ifindex = ifaces[i];
+
+		if (attach_egress_prog) {
+			ret = get_mac_addr(ifindex, mac_addr);
+			if (ret < 0) {
+				printf("get interface %d mac failed\n", ifindex);
+				goto err_out;
+			}
+			ret = bpf_map_update_elem(mac_map, &ifindex, mac_addr, 0);
+			if (ret) {
+				perror("bpf_update_elem mac_map failed\n");
+				goto err_out;
+			}
+		}
+
+		/* Add all the interfaces to group all */
+		devmap_val.ifindex = ifindex;
+		devmap_val.bpf_prog.fd = egress_prog_fd;
+		ret = bpf_map_update_elem(group_all, &ifindex, &devmap_val, 0);
+		if (ret) {
+			perror("bpf_map_update_elem");
+			goto err_out;
+		}
+
+		/* bind prog_fd to each interface */
+		ret = bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags);
+		if (ret) {
+			printf("Set xdp fd failed on %d\n", ifindex);
+			goto err_out;
+		}
+	}
+
+	/* sleep some time for testing */
+	sleep(999);
+
+	return 0;
+
+err_out:
+	return 1;
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
index 4029833f7e27..160891dcb4bc 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
@@ -109,6 +109,9 @@ router_destroy()
 	__addr_add_del $rp1 del 192.0.2.2/24 2001:db8:1::2/64
 
 	tc qdisc del dev $rp2 clsact
+
+	ip link set dev $rp2 down
+	ip link set dev $rp1 down
 }
 
 setup_prepare()
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
index 42d44e27802c..190c1b6b5365 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
@@ -111,6 +111,9 @@ router_destroy()
 	__addr_add_del $rp1 del 192.0.2.2/24 2001:db8:1::2/64
 
 	tc qdisc del dev $rp2 clsact
+
+	ip link set dev $rp2 down
+	ip link set dev $rp1 down
 }
 
 setup_prepare()
diff --git a/tools/testing/selftests/drivers/net/mlxsw/port_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/port_scale.sh
index 65f43a7ce9c9..1e9a4aff76a2 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/port_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/port_scale.sh
@@ -7,6 +7,8 @@
 
 PORT_NUM_NETIFS=0
 
+declare -a unsplit
+
 port_setup_prepare()
 {
 	:
@@ -20,12 +22,12 @@ port_cleanup()
 		devlink port unsplit $port
 		check_err $? "Did not unsplit $netdev"
 	done
+	unsplit=()
 }
 
 split_all_ports()
 {
 	local should_fail=$1; shift
-	local -a unsplit
 
 	# Loop over the splittable netdevs and create tuples of netdev along
 	# with its width. For example:
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
index 5cbff8038f84..28a570006d4d 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
@@ -93,7 +93,9 @@ switch_destroy()
 	lldptool -T -i $swp1 -V APP -d $(dscp_map 10) >/dev/null
 	lldpad_app_wait_del
 
+	ip link set dev $swp2 down
 	ip link set dev $swp2 nomaster
+	ip link set dev $swp1 down
 	ip link set dev $swp1 nomaster
 	ip link del dev br1
 }
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh
index 27de3d9ed08e..f4493ef9cca1 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh
@@ -29,37 +29,38 @@ cleanup()
 
 get_prio_pg()
 {
-	__mlnx_qos -i $swp | sed -n '/^PFC/,/^[^[:space:]]/p' |
-		grep buffer | sed 's/ \+/ /g' | cut -d' ' -f 2-
+	# Produces a string of numbers "<B0> <B1> ... <B7> ", where BX is number
+	# of buffer that priority X is mapped to.
+	dcb -j buffer show dev $swp |
+		jq -r '[.prio_buffer | .[] | tostring + " "] | add'
 }
 
 get_prio_pfc()
 {
-	__mlnx_qos -i $swp | sed -n '/^PFC/,/^[^[:space:]]/p' |
-		grep enabled | sed 's/ \+/ /g' | cut -d' ' -f 2-
+	# Produces a string of numbers "<P0> <P1> ... <P7> ", where PX denotes
+	# whether priority X has PFC enabled (the value is 1) or disabled (0).
+	dcb -j pfc show dev $swp |
+		jq -r '[.prio_pfc | .[] | if . then "1 " else "0 " end] | add'
 }
 
 get_prio_tc()
 {
-	__mlnx_qos -i $swp | sed -n '/^tc/,$p' |
-		awk '/^tc/ { TC = $2 }
-		     /priority:/ { PRIO[$2]=TC }
-		     END {
-			for (i in PRIO)
-			    printf("%d ", PRIO[i])
-		     }'
+	# Produces a string of numbers "<T0> <T1> ... <T7> ", where TC is number
+	# of TC that priority X is mapped to.
+	dcb -j ets show dev $swp |
+		jq -r '[.prio_tc | .[] | tostring + " "] | add'
 }
 
 get_buf_size()
 {
 	local idx=$1; shift
 
-	__mlnx_qos -i $swp | grep Receive | sed 's/.*: //' | cut -d, -f $((idx + 1))
+	dcb -j buffer show dev $swp | jq ".buffer_size[$idx]"
 }
 
 get_tot_size()
 {
-	__mlnx_qos -i $swp | grep Receive | sed 's/.*total_size=//'
+	dcb -j buffer show dev $swp | jq '.total_size'
 }
 
 check_prio_pg()
@@ -121,18 +122,18 @@ test_dcb_ets()
 {
 	RET=0
 
-	__mlnx_qos -i $swp --prio_tc=0,2,4,6,1,3,5,7 > /dev/null
+	dcb ets set dev $swp prio-tc 0:0 1:2 2:4 3:6 4:1 5:3 6:5 7:7
 
 	check_prio_pg "0 2 4 6 1 3 5 7 "
 	check_prio_tc "0 2 4 6 1 3 5 7 "
 	check_prio_pfc "0 0 0 0 0 0 0 0 "
 
-	__mlnx_qos -i $swp --prio_tc=0,0,0,0,0,0,0,0 > /dev/null
+	dcb ets set dev $swp prio-tc all:0
 
 	check_prio_pg "0 0 0 0 0 0 0 0 "
 	check_prio_tc "0 0 0 0 0 0 0 0 "
 
-	__mlnx_qos -i $swp --prio2buffer=1,3,5,7,0,2,4,6 &> /dev/null
+	dcb buffer set dev $swp prio-buffer 0:1 1:3 2:5 3:7 4:0 5:2 6:4 7:6 2>/dev/null
 	check_fail $? "prio2buffer accepted in DCB mode"
 
 	log_test "Configuring headroom through ETS"
@@ -174,7 +175,7 @@ test_pfc()
 {
 	RET=0
 
-	__mlnx_qos -i $swp --prio_tc=0,0,0,0,0,1,2,3 > /dev/null
+	dcb ets set dev $swp prio-tc all:0 5:1 6:2 7:3
 
 	local buf0size=$(get_buf_size 0)
 	local buf1size=$(get_buf_size 1)
@@ -193,7 +194,7 @@ test_pfc()
 
 	RET=0
 
-	__mlnx_qos -i $swp --pfc=0,0,0,0,0,1,1,1 --cable_len=0 > /dev/null
+	dcb pfc set dev $swp prio-pfc all:off 5:on 6:on 7:on delay 0
 
 	check_prio_pg "0 0 0 0 0 1 2 3 "
 	check_prio_pfc "0 0 0 0 0 1 1 1 "
@@ -210,7 +211,7 @@ test_pfc()
 
 	RET=0
 
-	__mlnx_qos -i $swp --pfc=0,0,0,0,0,1,1,1 --cable_len=1000 > /dev/null
+	dcb pfc set dev $swp delay 1000
 
 	check_buf_size 0 "== $buf0size"
 	check_buf_size 1 "> $buf1size"
@@ -221,8 +222,8 @@ test_pfc()
 
 	RET=0
 
-	__mlnx_qos -i $swp --pfc=0,0,0,0,0,0,0,0 --cable_len=0 > /dev/null
-	__mlnx_qos -i $swp --prio_tc=0,0,0,0,0,0,0,0 > /dev/null
+	dcb pfc set dev $swp prio-pfc all:off delay 0
+	dcb ets set dev $swp prio-tc all:0
 
 	check_prio_pg "0 0 0 0 0 0 0 0 "
 	check_prio_tc "0 0 0 0 0 0 0 0 "
@@ -242,13 +243,13 @@ test_tc_priomap()
 {
 	RET=0
 
-	__mlnx_qos -i $swp --prio_tc=0,1,2,3,4,5,6,7 > /dev/null
+	dcb ets set dev $swp prio-tc 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
 	check_prio_pg "0 1 2 3 4 5 6 7 "
 
 	tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M
 	check_prio_pg "0 0 0 0 0 0 0 0 "
 
-	__mlnx_qos -i $swp --prio2buffer=1,3,5,7,0,2,4,6 > /dev/null
+	dcb buffer set dev $swp prio-buffer 0:1 1:3 2:5 3:7 4:0 5:2 6:4 7:6
 	check_prio_pg "1 3 5 7 0 2 4 6 "
 
 	tc qdisc delete dev $swp root
@@ -256,9 +257,9 @@ test_tc_priomap()
 
 	# Clean up.
 	tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M
-	__mlnx_qos -i $swp --prio2buffer=0,0,0,0,0,0,0,0 > /dev/null
+	dcb buffer set dev $swp prio-buffer all:0
 	tc qdisc delete dev $swp root
-	__mlnx_qos -i $swp --prio_tc=0,0,0,0,0,0,0,0 > /dev/null
+	dcb ets set dev $swp prio-tc all:0
 
 	log_test "TC: priomap"
 }
@@ -270,12 +271,12 @@ test_tc_sizes()
 
 	RET=0
 
-	__mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 &> /dev/null
+	dcb buffer set dev $swp buffer-size all:0 0:$size 2>/dev/null
 	check_fail $? "buffer_size should fail before qdisc is added"
 
 	tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M
 
-	__mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 > /dev/null
+	dcb buffer set dev $swp buffer-size all:0 0:$size
 	check_err $? "buffer_size should pass after qdisc is added"
 	check_buf_size 0 "== $size" "set size: "
 
@@ -283,26 +284,26 @@ test_tc_sizes()
 	check_buf_size 0 "== $size" "set MTU: "
 	mtu_restore $swp
 
-	__mlnx_qos -i $swp --buffer_size=0,0,0,0,0,0,0,0 > /dev/null
+	dcb buffer set dev $swp buffer-size all:0
 
 	# After replacing the qdisc for the same kind, buffer_size still has to
 	# work.
 	tc qdisc replace dev $swp root handle 1: bfifo limit 1M
 
-	__mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 > /dev/null
+	dcb buffer set dev $swp buffer-size all:0 0:$size
 	check_buf_size 0 "== $size" "post replace, set size: "
 
-	__mlnx_qos -i $swp --buffer_size=0,0,0,0,0,0,0,0 > /dev/null
+	dcb buffer set dev $swp buffer-size all:0
 
 	# Likewise after replacing for a different kind.
 	tc qdisc replace dev $swp root handle 2: prio bands 8
 
-	__mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 > /dev/null
+	dcb buffer set dev $swp buffer-size all:0 0:$size
 	check_buf_size 0 "== $size" "post replace different kind, set size: "
 
 	tc qdisc delete dev $swp root
 
-	__mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 &> /dev/null
+	dcb buffer set dev $swp buffer-size all:0 0:$size 2>/dev/null
 	check_fail $? "buffer_size should fail after qdisc is deleted"
 
 	log_test "TC: buffer size"
@@ -363,10 +364,10 @@ test_tc_int_buf()
 	tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M
 	test_int_buf "TC: "
 
-	__mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 > /dev/null
+	dcb buffer set dev $swp buffer-size all:0 0:$size
 	test_int_buf "TC+buffsize: "
 
-	__mlnx_qos -i $swp --buffer_size=0,0,0,0,0,0,0,0 > /dev/null
+	dcb buffer set dev $swp buffer-size all:0
 	tc qdisc delete dev $swp root
 }
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh
index 0bf76f13c030..faa51012cdac 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh
@@ -82,17 +82,3 @@ bail_on_lldpad()
 		fi
 	fi
 }
-
-__mlnx_qos()
-{
-	local err
-
-	mlnx_qos "$@" 2>/dev/null
-	err=$?
-
-	if ((err)); then
-		echo "Error ($err) in mlnx_qos $@" >/dev/stderr
-	fi
-
-	return $err
-}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
index 5c7700212f75..5d5622fc2758 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
@@ -171,7 +171,7 @@ switch_create()
 	# assignment.
 	tc qdisc replace dev $swp1 root handle 1: \
 	   ets bands 8 strict 8 priomap 7 6
-	__mlnx_qos -i $swp1 --prio2buffer=0,1,0,0,0,0,0,0 >/dev/null
+	dcb buffer set dev $swp1 prio-buffer all:0 1:1
 
 	# $swp2
 	# -----
@@ -209,8 +209,8 @@ switch_create()
 	# the lossless prio into a buffer of its own. Don't bother with buffer
 	# sizes though, there is not going to be any pressure in the "backward"
 	# direction.
-	__mlnx_qos -i $swp3 --prio2buffer=0,1,0,0,0,0,0,0 >/dev/null
-	__mlnx_qos -i $swp3 --pfc=0,1,0,0,0,0,0,0 >/dev/null
+	dcb buffer set dev $swp3 prio-buffer all:0 1:1
+	dcb pfc set dev $swp3 prio-pfc all:off 1:on
 
 	# $swp4
 	# -----
@@ -226,11 +226,11 @@ switch_create()
 	# Configure qdisc so that we can hand-tune headroom.
 	tc qdisc replace dev $swp4 root handle 1: \
 	   ets bands 8 strict 8 priomap 7 6
-	__mlnx_qos -i $swp4 --prio2buffer=0,1,0,0,0,0,0,0 >/dev/null
-	__mlnx_qos -i $swp4 --pfc=0,1,0,0,0,0,0,0 >/dev/null
+	dcb buffer set dev $swp4 prio-buffer all:0 1:1
+	dcb pfc set dev $swp4 prio-pfc all:off 1:on
 	# PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which
 	# is (-2*MTU) about 80K of delay provision.
-	__mlnx_qos -i $swp4 --buffer_size=0,$_100KB,0,0,0,0,0,0 >/dev/null
+	dcb buffer set dev $swp4 buffer-size all:0 1:$_100KB
 
 	# bridges
 	# -------
@@ -273,9 +273,9 @@ switch_destroy()
 	# $swp4
 	# -----
 
-	__mlnx_qos -i $swp4 --buffer_size=0,0,0,0,0,0,0,0 >/dev/null
-	__mlnx_qos -i $swp4 --pfc=0,0,0,0,0,0,0,0 >/dev/null
-	__mlnx_qos -i $swp4 --prio2buffer=0,0,0,0,0,0,0,0 >/dev/null
+	dcb buffer set dev $swp4 buffer-size all:0
+	dcb pfc set dev $swp4 prio-pfc all:off
+	dcb buffer set dev $swp4 prio-buffer all:0
 	tc qdisc del dev $swp4 root
 
 	devlink_tc_bind_pool_th_restore $swp4 1 ingress
@@ -288,8 +288,8 @@ switch_destroy()
 	# $swp3
 	# -----
 
-	__mlnx_qos -i $swp3 --pfc=0,0,0,0,0,0,0,0 >/dev/null
-	__mlnx_qos -i $swp3 --prio2buffer=0,0,0,0,0,0,0,0 >/dev/null
+	dcb pfc set dev $swp3 prio-pfc all:off
+	dcb buffer set dev $swp3 prio-buffer all:0
 	tc qdisc del dev $swp3 root
 
 	devlink_tc_bind_pool_th_restore $swp3 1 egress
@@ -315,7 +315,7 @@ switch_destroy()
 	# $swp1
 	# -----
 
-	__mlnx_qos -i $swp1 --prio2buffer=0,0,0,0,0,0,0,0 >/dev/null
+	dcb buffer set dev $swp1 prio-buffer all:0
 	tc qdisc del dev $swp1 root
 
 	devlink_tc_bind_pool_th_restore $swp1 1 ingress
diff --git a/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh
index e93878d42596..683759d29199 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh
@@ -68,7 +68,7 @@ wait_for_routes()
 	local t0=$1; shift
 	local route_count=$1; shift
 
-	local t1=$(ip route | grep -o 'offload' | wc -l)
+	local t1=$(ip route | grep 'offload' | grep -v 'offload_failed' | wc -l)
 	local delta=$((t1 - t0))
 	echo $delta
 	[[ $delta -ge $route_count ]]
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
index 093bed088ad0..373d5f2a846e 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
@@ -234,15 +234,15 @@ __tc_sample_rate_test()
 
 	psample_capture_start
 
-	ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \
+	ip vrf exec v$h1 $MZ $h1 -c 320000 -d 100usec -p 64 -A 192.0.2.1 \
 		-B $dip -t udp dp=52768,sp=42768 -q
 
 	psample_capture_stop
 
 	pkts=$(grep -e "group 1 " $CAPTURE_FILE | wc -l)
-	pct=$((100 * (pkts - 100) / 100))
+	pct=$((100 * (pkts - 10000) / 10000))
 	(( -25 <= pct && pct <= 25))
-	check_err $? "Expected 100 packets, got $pkts packets, which is $pct% off. Required accuracy is +-25%"
+	check_err $? "Expected 10000 packets, got $pkts packets, which is $pct% off. Required accuracy is +-25%"
 
 	log_test "tc sample rate ($desc)"
 
@@ -587,15 +587,15 @@ __tc_sample_acl_rate_test()
 
 	psample_capture_start
 
-	ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \
+	ip vrf exec v$h1 $MZ $h1 -c 320000 -d 100usec -p 64 -A 192.0.2.1 \
 		-B 198.51.100.1 -t udp dp=52768,sp=42768 -q
 
 	psample_capture_stop
 
 	pkts=$(grep -e "group 1 " $CAPTURE_FILE | wc -l)
-	pct=$((100 * (pkts - 100) / 100))
+	pct=$((100 * (pkts - 10000) / 10000))
 	(( -25 <= pct && pct <= 25))
-	check_err $? "Expected 100 packets, got $pkts packets, which is $pct% off. Required accuracy is +-25%"
+	check_err $? "Expected 10000 packets, got $pkts packets, which is $pct% off. Required accuracy is +-25%"
 
 	# Setup a filter that should not match any packet and make sure packets
 	# are not sampled.
diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
index 40909c254365..9de1d123f4f5 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
@@ -5,12 +5,13 @@ lib_dir=$(dirname $0)/../../../net/forwarding
 
 ALL_TESTS="fw_flash_test params_test regions_test reload_test \
 	   netns_reload_test resource_test dev_info_test \
-	   empty_reporter_test dummy_reporter_test"
+	   empty_reporter_test dummy_reporter_test rate_test"
 NUM_NETIFS=0
 source $lib_dir/lib.sh
 
 BUS_ADDR=10
 PORT_COUNT=4
+VF_COUNT=4
 DEV_NAME=netdevsim$BUS_ADDR
 SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV_NAME/net/
 DEBUGFS_DIR=/sys/kernel/debug/netdevsim/$DEV_NAME/
@@ -507,6 +508,170 @@ dummy_reporter_test()
 	log_test "dummy reporter test"
 }
 
+rate_leafs_get()
+{
+	local handle=$1
+
+	cmd_jq "devlink port function rate show -j" \
+	       '.[] | to_entries | .[] | select(.value.type == "leaf") | .key | select(contains("'$handle'"))'
+}
+
+rate_nodes_get()
+{
+	local handle=$1
+
+	cmd_jq "devlink port function rate show -j" \
+		'.[] | to_entries | .[] | select(.value.type == "node") | .key | select(contains("'$handle'"))'
+}
+
+rate_attr_set()
+{
+	local handle=$1
+	local name=$2
+	local value=$3
+	local units=$4
+
+	devlink port function rate set $handle $name $value$units
+}
+
+rate_attr_get()
+{
+	local handle=$1
+	local name=$2
+
+	cmd_jq "devlink port function rate show $handle -j" '.[][].'$name
+}
+
+rate_attr_tx_rate_check()
+{
+	local handle=$1
+	local name=$2
+	local rate=$3
+	local debug_file=$4
+
+	rate_attr_set $handle $name $rate mbit
+	check_err $? "Failed to set $name value"
+
+	local debug_value=$(cat $debug_file)
+	check_err $? "Failed to read $name value from debugfs"
+	[ "$debug_value" == "$rate" ]
+	check_err $? "Unexpected $name debug value $debug_value != $rate"
+
+	local api_value=$(( $(rate_attr_get $handle $name) * 8 / 1000000 ))
+	check_err $? "Failed to get $name attr value"
+	[ "$api_value" == "$rate" ]
+	check_err $? "Unexpected $name attr value $api_value != $rate"
+}
+
+rate_attr_parent_check()
+{
+	local handle=$1
+	local parent=$2
+	local debug_file=$3
+
+	rate_attr_set $handle parent $parent
+	check_err $? "Failed to set parent"
+
+	debug_value=$(cat $debug_file)
+	check_err $? "Failed to get parent debugfs value"
+	[ "$debug_value" == "$parent" ]
+	check_err $? "Unexpected parent debug value $debug_value != $parent"
+
+	api_value=$(rate_attr_get $r_obj parent)
+	check_err $? "Failed to get parent attr value"
+	[ "$api_value" == "$parent" ]
+	check_err $? "Unexpected parent attr value $api_value != $parent"
+}
+
+rate_node_add()
+{
+	local handle=$1
+
+	devlink port function rate add $handle
+}
+
+rate_node_del()
+{
+	local handle=$1
+
+	devlink port function rate del $handle
+}
+
+rate_test()
+{
+	RET=0
+
+	echo $VF_COUNT > /sys/bus/netdevsim/devices/$DEV_NAME/sriov_numvfs
+	devlink dev eswitch set $DL_HANDLE mode switchdev
+	local leafs=`rate_leafs_get $DL_HANDLE`
+	local num_leafs=`echo $leafs | wc -w`
+	[ "$num_leafs" == "$VF_COUNT" ]
+	check_err $? "Expected $VF_COUNT rate leafs but got $num_leafs"
+
+	rate=10
+	for r_obj in $leafs
+	do
+		rate_attr_tx_rate_check $r_obj tx_share $rate \
+			$DEBUGFS_DIR/ports/${r_obj##*/}/tx_share
+		rate=$(($rate+10))
+	done
+
+	rate=100
+	for r_obj in $leafs
+	do
+		rate_attr_tx_rate_check $r_obj tx_max $rate \
+			$DEBUGFS_DIR/ports/${r_obj##*/}/tx_max
+		rate=$(($rate+100))
+	done
+
+	local node1_name='group1'
+	local node1="$DL_HANDLE/$node1_name"
+	rate_node_add "$node1"
+	check_err $? "Failed to add node $node1"
+
+	local num_nodes=`rate_nodes_get $DL_HANDLE | wc -w`
+	[ $num_nodes == 1 ]
+	check_err $? "Expected 1 rate node in output but got $num_nodes"
+
+	local node_tx_share=10
+	rate_attr_tx_rate_check $node1 tx_share $node_tx_share \
+		$DEBUGFS_DIR/rate_nodes/${node1##*/}/tx_share
+
+	local node_tx_max=100
+	rate_attr_tx_rate_check $node1 tx_max $node_tx_max \
+		$DEBUGFS_DIR/rate_nodes/${node1##*/}/tx_max
+
+	rate_node_del "$node1"
+	check_err $? "Failed to delete node $node1"
+	local num_nodes=`rate_nodes_get $DL_HANDLE | wc -w`
+	[ $num_nodes == 0 ]
+	check_err $? "Expected 0 rate node but got $num_nodes"
+
+	local node1_name='group1'
+	local node1="$DL_HANDLE/$node1_name"
+	rate_node_add "$node1"
+	check_err $? "Failed to add node $node1"
+
+	rate_attr_parent_check $r_obj $node1_name \
+		$DEBUGFS_DIR/ports/${r_obj##*/}/rate_parent
+
+	local node2_name='group2'
+	local node2="$DL_HANDLE/$node2_name"
+	rate_node_add "$node2"
+	check_err $? "Failed to add node $node2"
+
+	rate_attr_parent_check $node2 $node1_name \
+		$DEBUGFS_DIR/rate_nodes/$node2_name/rate_parent
+	rate_node_del "$node2"
+	check_err $? "Failed to delete node $node2"
+	rate_attr_set "$r_obj" noparent
+	check_err $? "Failed to unset $r_obj parent node"
+	rate_node_del "$node1"
+	check_err $? "Failed to delete node $node1"
+
+	log_test "rate test"
+}
+
 setup_prepare()
 {
 	modprobe netdevsim
diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh
index da49ad2761b5..109900c817be 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh
@@ -24,13 +24,15 @@ ALL_TESTS="
 NETDEVSIM_PATH=/sys/bus/netdevsim/
 DEV_ADDR=1337
 DEV=netdevsim${DEV_ADDR}
-DEVLINK_DEV=netdevsim/${DEV}
 DEBUGFS_DIR=/sys/kernel/debug/netdevsim/$DEV/
 SLEEP_TIME=1
 NETDEV=""
 NUM_NETIFS=0
 source $lib_dir/lib.sh
+
+DEVLINK_DEV=
 source $lib_dir/devlink_lib.sh
+DEVLINK_DEV=netdevsim/${DEV}
 
 require_command udevadm
 
@@ -163,6 +165,16 @@ trap_stats_test()
 			devlink_trap_action_set $trap_name "drop"
 			devlink_trap_stats_idle_test $trap_name
 			check_err $? "Stats of trap $trap_name not idle when action is drop"
+
+			echo "y"> $DEBUGFS_DIR/fail_trap_drop_counter_get
+			devlink -s trap show $DEVLINK_DEV trap $trap_name &> /dev/null
+			check_fail $? "Managed to read trap (hard dropped) statistics when should not"
+			echo "n"> $DEBUGFS_DIR/fail_trap_drop_counter_get
+			devlink -s trap show $DEVLINK_DEV trap $trap_name &> /dev/null
+			check_err $? "Did not manage to read trap (hard dropped) statistics when should"
+
+			devlink_trap_drop_stats_idle_test $trap_name
+			check_fail $? "Drop stats of trap $trap_name idle when should not"
 		else
 			devlink_trap_stats_idle_test $trap_name
 			check_fail $? "Stats of non-drop trap $trap_name idle when should not"
diff --git a/tools/testing/selftests/drivers/net/netdevsim/fib.sh b/tools/testing/selftests/drivers/net/netdevsim/fib.sh
index 251f228ce63e..fc794cd30389 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/fib.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/fib.sh
@@ -33,13 +33,15 @@ ALL_TESTS="
 NETDEVSIM_PATH=/sys/bus/netdevsim/
 DEV_ADDR=1337
 DEV=netdevsim${DEV_ADDR}
-DEVLINK_DEV=netdevsim/${DEV}
 SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/
 NUM_NETIFS=0
 source $lib_dir/lib.sh
-source $lib_dir/devlink_lib.sh
 source $lib_dir/fib_offload_lib.sh
 
+DEVLINK_DEV=
+source $lib_dir/devlink_lib.sh
+DEVLINK_DEV=netdevsim/${DEV}
+
 ipv4_identical_routes()
 {
 	fib_ipv4_identical_routes_test "testns1"
diff --git a/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh b/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh
index ba75c81cda91..e8e0dc088d6a 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh
@@ -44,12 +44,14 @@ ALL_TESTS="
 NETDEVSIM_PATH=/sys/bus/netdevsim/
 DEV_ADDR=1337
 DEV=netdevsim${DEV_ADDR}
-DEVLINK_DEV=netdevsim/${DEV}
 SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/
 DEBUGFS_NET_DIR=/sys/kernel/debug/netdevsim/$DEV/
 NUM_NETIFS=0
 source $lib_dir/lib.sh
+
+DEVLINK_DEV=
 source $lib_dir/devlink_lib.sh
+DEVLINK_DEV=netdevsim/${DEV}
 
 nexthop_check()
 {
diff --git a/tools/testing/selftests/drivers/net/netdevsim/psample.sh b/tools/testing/selftests/drivers/net/netdevsim/psample.sh
index ee10b1a8933c..e689ff7a0b12 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/psample.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/psample.sh
@@ -14,13 +14,15 @@ ALL_TESTS="
 NETDEVSIM_PATH=/sys/bus/netdevsim/
 DEV_ADDR=1337
 DEV=netdevsim${DEV_ADDR}
-DEVLINK_DEV=netdevsim/${DEV}
 SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/
 PSAMPLE_DIR=/sys/kernel/debug/netdevsim/$DEV/psample/
 CAPTURE_FILE=$(mktemp)
 NUM_NETIFS=0
 source $lib_dir/lib.sh
+
+DEVLINK_DEV=
 source $lib_dir/devlink_lib.sh
+DEVLINK_DEV=netdevsim/${DEV}
 
 # Available at https://github.com/Mellanox/libpsample
 require_command psample
diff --git a/tools/testing/selftests/net/devlink_port_split.py b/tools/testing/selftests/net/devlink_port_split.py
index 834066d465fc..2b5d6ff87373 100755
--- a/tools/testing/selftests/net/devlink_port_split.py
+++ b/tools/testing/selftests/net/devlink_port_split.py
@@ -18,6 +18,8 @@ import sys
 #
 
 
+# Kselftest framework requirement - SKIP code is 4
+KSFT_SKIP=4
 Port = collections.namedtuple('Port', 'bus_info name')
 
 
@@ -239,7 +241,11 @@ def main(cmdline=None):
         assert stderr == ""
 
         devs = json.loads(stdout)['dev']
-        dev = list(devs.keys())[0]
+        if devs:
+            dev = list(devs.keys())[0]
+        else:
+            print("no devlink device was found, test skipped")
+            sys.exit(KSFT_SKIP)
 
     cmd = "devlink dev show %s" % dev
     stdout, stderr = run_command(cmd)
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 49774a8a7736..0d293391e9a4 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -925,6 +925,14 @@ ipv6_fcnal_runtime()
 	run_cmd "$IP nexthop add id 86 via 2001:db8:91::2 dev veth1"
 	run_cmd "$IP ro add 2001:db8:101::1/128 nhid 81"
 
+	# route can not use prefsrc with nexthops
+	run_cmd "$IP ro add 2001:db8:101::2/128 nhid 86 from 2001:db8:91::1"
+	log_test $? 2 "IPv6 route can not use src routing with external nexthop"
+
+	# check cleanup path on invalid metric
+	run_cmd "$IP ro add 2001:db8:101::2/128 nhid 86 congctl lock foo"
+	log_test $? 2 "IPv6 route with invalid metric"
+
 	# rpfilter and default route
 	$IP nexthop flush >/dev/null 2>&1
 	run_cmd "ip netns exec me ip6tables -t mangle -I PREROUTING 1 -m rpfilter --invert -j DROP"
@@ -1366,6 +1374,10 @@ ipv4_fcnal_runtime()
 	run_cmd "$IP nexthop replace id 22 via 172.16.2.2 dev veth3"
 	log_test $? 2 "Nexthop replace with invalid scope for existing route"
 
+	# check cleanup path on invalid metric
+	run_cmd "$IP ro add 172.16.101.2/32 nhid 22 congctl lock foo"
+	log_test $? 2 "IPv4 route with invalid metric"
+
 	#
 	# add route with nexthop and check traffic
 	#
diff --git a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh
new file mode 100755
index 000000000000..a15d21dc035a
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh
@@ -0,0 +1,364 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test traffic distribution between two paths when using custom hash policy.
+#
+# +--------------------------------+
+# | H1                             |
+# |                     $h1 +      |
+# |   198.51.100.{2-253}/24 |      |
+# |   2001:db8:1::{2-fd}/64 |      |
+# +-------------------------|------+
+#                           |
+# +-------------------------|-------------------------+
+# | SW1                     |                         |
+# |                    $rp1 +                         |
+# |         198.51.100.1/24                           |
+# |        2001:db8:1::1/64                           |
+# |                                                   |
+# |                                                   |
+# |            $rp11 +             + $rp12            |
+# |     192.0.2.1/28 |             | 192.0.2.17/28    |
+# | 2001:db8:2::1/64 |             | 2001:db8:3::1/64 |
+# +------------------|-------------|------------------+
+#                    |             |
+# +------------------|-------------|------------------+
+# | SW2              |             |                  |
+# |                  |             |                  |
+# |            $rp21 +             + $rp22            |
+# |     192.0.2.2/28                 192.0.2.18/28    |
+# | 2001:db8:2::2/64                 2001:db8:3::2/64 |
+# |                                                   |
+# |                                                   |
+# |                    $rp2 +                         |
+# |          203.0.113.1/24 |                         |
+# |        2001:db8:4::1/64 |                         |
+# +-------------------------|-------------------------+
+#                           |
+# +-------------------------|------+
+# | H2                      |      |
+# |                     $h2 +      |
+# |    203.0.113.{2-253}/24        |
+# |   2001:db8:4::{2-fd}/64        |
+# +--------------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	custom_hash
+"
+
+NUM_NETIFS=8
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 198.51.100.2/24 2001:db8:1::2/64
+	ip route add vrf v$h1 default via 198.51.100.1 dev $h1
+	ip -6 route add vrf v$h1 default via 2001:db8:1::1 dev $h1
+}
+
+h1_destroy()
+{
+	ip -6 route del vrf v$h1 default
+	ip route del vrf v$h1 default
+	simple_if_fini $h1 198.51.100.2/24 2001:db8:1::2/64
+}
+
+sw1_create()
+{
+	simple_if_init $rp1 198.51.100.1/24 2001:db8:1::1/64
+	__simple_if_init $rp11 v$rp1 192.0.2.1/28 2001:db8:2::1/64
+	__simple_if_init $rp12 v$rp1 192.0.2.17/28 2001:db8:3::1/64
+
+	ip route add vrf v$rp1 203.0.113.0/24 \
+		nexthop via 192.0.2.2 dev $rp11 \
+		nexthop via 192.0.2.18 dev $rp12
+
+	ip -6 route add vrf v$rp1 2001:db8:4::/64 \
+		nexthop via 2001:db8:2::2 dev $rp11 \
+		nexthop via 2001:db8:3::2 dev $rp12
+}
+
+sw1_destroy()
+{
+	ip -6 route del vrf v$rp1 2001:db8:4::/64
+
+	ip route del vrf v$rp1 203.0.113.0/24
+
+	__simple_if_fini $rp12 192.0.2.17/28 2001:db8:3::1/64
+	__simple_if_fini $rp11 192.0.2.1/28 2001:db8:2::1/64
+	simple_if_fini $rp1 198.51.100.1/24 2001:db8:1::1/64
+}
+
+sw2_create()
+{
+	simple_if_init $rp2 203.0.113.1/24 2001:db8:4::1/64
+	__simple_if_init $rp21 v$rp2 192.0.2.2/28 2001:db8:2::2/64
+	__simple_if_init $rp22 v$rp2 192.0.2.18/28 2001:db8:3::2/64
+
+	ip route add vrf v$rp2 198.51.100.0/24 \
+		nexthop via 192.0.2.1 dev $rp21 \
+		nexthop via 192.0.2.17 dev $rp22
+
+	ip -6 route add vrf v$rp2 2001:db8:1::/64 \
+		nexthop via 2001:db8:2::1 dev $rp21 \
+		nexthop via 2001:db8:3::1 dev $rp22
+}
+
+sw2_destroy()
+{
+	ip -6 route del vrf v$rp2 2001:db8:1::/64
+
+	ip route del vrf v$rp2 198.51.100.0/24
+
+	__simple_if_fini $rp22 192.0.2.18/28 2001:db8:3::2/64
+	__simple_if_fini $rp21 192.0.2.2/28 2001:db8:2::2/64
+	simple_if_fini $rp2 203.0.113.1/24 2001:db8:4::1/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 203.0.113.2/24 2001:db8:4::2/64
+	ip route add vrf v$h2 default via 203.0.113.1 dev $h2
+	ip -6 route add vrf v$h2 default via 2001:db8:4::1 dev $h2
+}
+
+h2_destroy()
+{
+	ip -6 route del vrf v$h2 default
+	ip route del vrf v$h2 default
+	simple_if_fini $h2 203.0.113.2/24 2001:db8:4::2/64
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+
+	rp1=${NETIFS[p2]}
+
+	rp11=${NETIFS[p3]}
+	rp21=${NETIFS[p4]}
+
+	rp12=${NETIFS[p5]}
+	rp22=${NETIFS[p6]}
+
+	rp2=${NETIFS[p7]}
+
+	h2=${NETIFS[p8]}
+
+	vrf_prepare
+	h1_create
+	sw1_create
+	sw2_create
+	h2_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	h2_destroy
+	sw2_destroy
+	sw1_destroy
+	h1_destroy
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1 203.0.113.2
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:4::2
+}
+
+send_src_ipv4()
+{
+	$MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \
+		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
+}
+
+send_dst_ipv4()
+{
+	$MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \
+		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
+}
+
+send_src_udp4()
+{
+	$MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+		-d 1msec -t udp "sp=0-32768,dp=30000"
+}
+
+send_dst_udp4()
+{
+	$MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+		-d 1msec -t udp "sp=20000,dp=0-32768"
+}
+
+send_src_ipv6()
+{
+	$MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:4::2 \
+		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
+}
+
+send_dst_ipv6()
+{
+	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:4::2-2001:db8:4::fd" \
+		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
+}
+
+send_flowlabel()
+{
+	# Generate 16384 echo requests, each with a random flow label.
+	for _ in $(seq 1 16384); do
+		ip vrf exec v$h1 \
+			$PING6 2001:db8:4::2 -F 0 -c 1 -q >/dev/null 2>&1
+	done
+}
+
+send_src_udp6()
+{
+	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:4::2 \
+		-d 1msec -t udp "sp=0-32768,dp=30000"
+}
+
+send_dst_udp6()
+{
+	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:4::2 \
+		-d 1msec -t udp "sp=20000,dp=0-32768"
+}
+
+custom_hash_test()
+{
+	local field="$1"; shift
+	local balanced="$1"; shift
+	local send_flows="$@"
+
+	RET=0
+
+	local t0_rp11=$(link_stats_tx_packets_get $rp11)
+	local t0_rp12=$(link_stats_tx_packets_get $rp12)
+
+	$send_flows
+
+	local t1_rp11=$(link_stats_tx_packets_get $rp11)
+	local t1_rp12=$(link_stats_tx_packets_get $rp12)
+
+	local d_rp11=$((t1_rp11 - t0_rp11))
+	local d_rp12=$((t1_rp12 - t0_rp12))
+
+	local diff=$((d_rp12 - d_rp11))
+	local sum=$((d_rp11 + d_rp12))
+
+	local pct=$(echo "$diff / $sum * 100" | bc -l)
+	local is_balanced=$(echo "-20 <= $pct && $pct <= 20" | bc)
+
+	[[ ( $is_balanced -eq 1 && $balanced == "balanced" ) ||
+	   ( $is_balanced -eq 0 && $balanced == "unbalanced" ) ]]
+	check_err $? "Expected traffic to be $balanced, but it is not"
+
+	log_test "Multipath hash field: $field ($balanced)"
+	log_info "Packets sent on path1 / path2: $d_rp11 / $d_rp12"
+}
+
+custom_hash_v4()
+{
+	log_info "Running IPv4 custom multipath hash tests"
+
+	sysctl_set net.ipv4.fib_multipath_hash_policy 3
+
+	# Prevent the neighbour table from overflowing, as different neighbour
+	# entries will be created on $ol4 when using different destination IPs.
+	sysctl_set net.ipv4.neigh.default.gc_thresh1 1024
+	sysctl_set net.ipv4.neigh.default.gc_thresh2 1024
+	sysctl_set net.ipv4.neigh.default.gc_thresh3 1024
+
+	sysctl_set net.ipv4.fib_multipath_hash_fields 0x0001
+	custom_hash_test "Source IP" "balanced" send_src_ipv4
+	custom_hash_test "Source IP" "unbalanced" send_dst_ipv4
+
+	sysctl_set net.ipv4.fib_multipath_hash_fields 0x0002
+	custom_hash_test "Destination IP" "balanced" send_dst_ipv4
+	custom_hash_test "Destination IP" "unbalanced" send_src_ipv4
+
+	sysctl_set net.ipv4.fib_multipath_hash_fields 0x0010
+	custom_hash_test "Source port" "balanced" send_src_udp4
+	custom_hash_test "Source port" "unbalanced" send_dst_udp4
+
+	sysctl_set net.ipv4.fib_multipath_hash_fields 0x0020
+	custom_hash_test "Destination port" "balanced" send_dst_udp4
+	custom_hash_test "Destination port" "unbalanced" send_src_udp4
+
+	sysctl_restore net.ipv4.neigh.default.gc_thresh3
+	sysctl_restore net.ipv4.neigh.default.gc_thresh2
+	sysctl_restore net.ipv4.neigh.default.gc_thresh1
+
+	sysctl_restore net.ipv4.fib_multipath_hash_policy
+}
+
+custom_hash_v6()
+{
+	log_info "Running IPv6 custom multipath hash tests"
+
+	sysctl_set net.ipv6.fib_multipath_hash_policy 3
+
+	# Prevent the neighbour table from overflowing, as different neighbour
+	# entries will be created on $ol4 when using different destination IPs.
+	sysctl_set net.ipv6.neigh.default.gc_thresh1 1024
+	sysctl_set net.ipv6.neigh.default.gc_thresh2 1024
+	sysctl_set net.ipv6.neigh.default.gc_thresh3 1024
+
+	sysctl_set net.ipv6.fib_multipath_hash_fields 0x0001
+	custom_hash_test "Source IP" "balanced" send_src_ipv6
+	custom_hash_test "Source IP" "unbalanced" send_dst_ipv6
+
+	sysctl_set net.ipv6.fib_multipath_hash_fields 0x0002
+	custom_hash_test "Destination IP" "balanced" send_dst_ipv6
+	custom_hash_test "Destination IP" "unbalanced" send_src_ipv6
+
+	sysctl_set net.ipv6.fib_multipath_hash_fields 0x0008
+	custom_hash_test "Flowlabel" "balanced" send_flowlabel
+	custom_hash_test "Flowlabel" "unbalanced" send_src_ipv6
+
+	sysctl_set net.ipv6.fib_multipath_hash_fields 0x0010
+	custom_hash_test "Source port" "balanced" send_src_udp6
+	custom_hash_test "Source port" "unbalanced" send_dst_udp6
+
+	sysctl_set net.ipv6.fib_multipath_hash_fields 0x0020
+	custom_hash_test "Destination port" "balanced" send_dst_udp6
+	custom_hash_test "Destination port" "unbalanced" send_src_udp6
+
+	sysctl_restore net.ipv6.neigh.default.gc_thresh3
+	sysctl_restore net.ipv6.neigh.default.gc_thresh2
+	sysctl_restore net.ipv6.neigh.default.gc_thresh1
+
+	sysctl_restore net.ipv6.fib_multipath_hash_policy
+}
+
+custom_hash()
+{
+	# Test that when the hash policy is set to custom, traffic is
+	# distributed only according to the fields set in the
+	# fib_multipath_hash_fields sysctl.
+	#
+	# Each time set a different field and make sure traffic is only
+	# distributed when the field is changed in the packet stream.
+	custom_hash_v4
+	custom_hash_v6
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh
index 9c12c4fd3afc..13d3d4428a32 100644
--- a/tools/testing/selftests/net/forwarding/devlink_lib.sh
+++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh
@@ -18,6 +18,12 @@ if [[ ! -v DEVLINK_DEV ]]; then
 
 	DEVLINK_VIDDID=$(lspci -s $(echo $DEVLINK_DEV | cut -d"/" -f2) \
 			 -n | cut -d" " -f3)
+elif [[ ! -z "$DEVLINK_DEV" ]]; then
+	devlink dev show $DEVLINK_DEV &> /dev/null
+	if [ $? -ne 0 ]; then
+		echo "SKIP: devlink device \"$DEVLINK_DEV\" not found"
+		exit 1
+	fi
 fi
 
 ##############################################################################
@@ -318,6 +324,14 @@ devlink_trap_rx_bytes_get()
 		| jq '.[][][]["stats"]["rx"]["bytes"]'
 }
 
+devlink_trap_drop_packets_get()
+{
+	local trap_name=$1; shift
+
+	devlink -js trap show $DEVLINK_DEV trap $trap_name \
+		| jq '.[][][]["stats"]["rx"]["dropped"]'
+}
+
 devlink_trap_stats_idle_test()
 {
 	local trap_name=$1; shift
@@ -339,6 +353,24 @@ devlink_trap_stats_idle_test()
 	fi
 }
 
+devlink_trap_drop_stats_idle_test()
+{
+	local trap_name=$1; shift
+	local t0_packets t0_bytes
+
+	t0_packets=$(devlink_trap_drop_packets_get $trap_name)
+
+	sleep 1
+
+	t1_packets=$(devlink_trap_drop_packets_get $trap_name)
+
+	if [[ $t0_packets -eq $t1_packets ]]; then
+		return 0
+	else
+		return 1
+	fi
+}
+
 devlink_traps_enable_all()
 {
 	local trap_name
diff --git a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh
new file mode 100755
index 000000000000..a73f52efcb6c
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh
@@ -0,0 +1,456 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test traffic distribution when there are multiple paths between an IPv4 GRE
+# tunnel. The tunnel carries IPv4 and IPv6 traffic between multiple hosts.
+# Multiple routes are in the underlay network. With the default multipath
+# policy, SW2 will only look at the outer IP addresses, hence only a single
+# route would be used.
+#
+# +--------------------------------+
+# | H1                             |
+# |                     $h1 +      |
+# |   198.51.100.{2-253}/24 |      |
+# |   2001:db8:1::{2-fd}/64 |      |
+# +-------------------------|------+
+#                           |
+# +-------------------------|------------------+
+# | SW1                     |                  |
+# |                    $ol1 +                  |
+# |         198.51.100.1/24                    |
+# |        2001:db8:1::1/64                    |
+# |                                            |
+# |   + g1 (gre)                               |
+# |     loc=192.0.2.1                          |
+# |     rem=192.0.2.2 --.                      |
+# |     tos=inherit     |                      |
+# |                     v                      |
+# |                     + $ul1                 |
+# |                     | 192.0.2.17/28        |
+# +---------------------|----------------------+
+#                       |
+# +---------------------|----------------------+
+# | SW2                 |                      |
+# |               $ul21 +                      |
+# |       192.0.2.18/28 |                      |
+# |                     |                      |
+# !   __________________+___                   |
+# |  /                      \                  |
+# |  |                      |                  |
+# |  + $ul22.111 (vlan)     + $ul22.222 (vlan) |
+# |  | 192.0.2.33/28        | 192.0.2.49/28    |
+# |  |                      |                  |
+# +--|----------------------|------------------+
+#    |                      |
+# +--|----------------------|------------------+
+# |  |                      |                  |
+# |  + $ul32.111 (vlan)     + $ul32.222 (vlan) |
+# |  | 192.0.2.34/28        | 192.0.2.50/28    |
+# |  |                      |                  |
+# |  \__________________+___/                  |
+# |                     |                      |
+# |                     |                      |
+# |               $ul31 +                      |
+# |       192.0.2.65/28 |                  SW3 |
+# +---------------------|----------------------+
+#                       |
+# +---------------------|----------------------+
+# |                     + $ul4                 |
+# |                     ^ 192.0.2.66/28        |
+# |                     |                      |
+# |   + g2 (gre)        |                      |
+# |     loc=192.0.2.2   |                      |
+# |     rem=192.0.2.1 --'                      |
+# |     tos=inherit                            |
+# |                                            |
+# |                    $ol4 +                  |
+# |          203.0.113.1/24 |                  |
+# |        2001:db8:2::1/64 |              SW4 |
+# +-------------------------|------------------+
+#                           |
+# +-------------------------|------+
+# |                         |      |
+# |                     $h2 +      |
+# |    203.0.113.{2-253}/24        |
+# |   2001:db8:2::{2-fd}/64     H2 |
+# +--------------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	custom_hash
+"
+
+NUM_NETIFS=10
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 198.51.100.2/24 2001:db8:1::2/64
+	ip route add vrf v$h1 default via 198.51.100.1 dev $h1
+	ip -6 route add vrf v$h1 default via 2001:db8:1::1 dev $h1
+}
+
+h1_destroy()
+{
+	ip -6 route del vrf v$h1 default
+	ip route del vrf v$h1 default
+	simple_if_fini $h1 198.51.100.2/24 2001:db8:1::2/64
+}
+
+sw1_create()
+{
+	simple_if_init $ol1 198.51.100.1/24 2001:db8:1::1/64
+	__simple_if_init $ul1 v$ol1 192.0.2.17/28
+
+	tunnel_create g1 gre 192.0.2.1 192.0.2.2 tos inherit dev v$ol1
+	__simple_if_init g1 v$ol1 192.0.2.1/32
+	ip route add vrf v$ol1 192.0.2.2/32 via 192.0.2.18
+
+	ip route add vrf v$ol1 203.0.113.0/24 dev g1
+	ip -6 route add vrf v$ol1 2001:db8:2::/64 dev g1
+}
+
+sw1_destroy()
+{
+	ip -6 route del vrf v$ol1 2001:db8:2::/64
+	ip route del vrf v$ol1 203.0.113.0/24
+
+	ip route del vrf v$ol1 192.0.2.2/32
+	__simple_if_fini g1 192.0.2.1/32
+	tunnel_destroy g1
+
+	__simple_if_fini $ul1 192.0.2.17/28
+	simple_if_fini $ol1 198.51.100.1/24 2001:db8:1::1/64
+}
+
+sw2_create()
+{
+	simple_if_init $ul21 192.0.2.18/28
+	__simple_if_init $ul22 v$ul21
+	vlan_create $ul22 111 v$ul21 192.0.2.33/28
+	vlan_create $ul22 222 v$ul21 192.0.2.49/28
+
+	ip route add vrf v$ul21 192.0.2.1/32 via 192.0.2.17
+	ip route add vrf v$ul21 192.0.2.2/32 \
+	   nexthop via 192.0.2.34 \
+	   nexthop via 192.0.2.50
+}
+
+sw2_destroy()
+{
+	ip route del vrf v$ul21 192.0.2.2/32
+	ip route del vrf v$ul21 192.0.2.1/32
+
+	vlan_destroy $ul22 222
+	vlan_destroy $ul22 111
+	__simple_if_fini $ul22
+	simple_if_fini $ul21 192.0.2.18/28
+}
+
+sw3_create()
+{
+	simple_if_init $ul31 192.0.2.65/28
+	__simple_if_init $ul32 v$ul31
+	vlan_create $ul32 111 v$ul31 192.0.2.34/28
+	vlan_create $ul32 222 v$ul31 192.0.2.50/28
+
+	ip route add vrf v$ul31 192.0.2.2/32 via 192.0.2.66
+	ip route add vrf v$ul31 192.0.2.1/32 \
+	   nexthop via 192.0.2.33 \
+	   nexthop via 192.0.2.49
+
+	tc qdisc add dev $ul32 clsact
+	tc filter add dev $ul32 ingress pref 111 prot 802.1Q \
+	   flower vlan_id 111 action pass
+	tc filter add dev $ul32 ingress pref 222 prot 802.1Q \
+	   flower vlan_id 222 action pass
+}
+
+sw3_destroy()
+{
+	tc qdisc del dev $ul32 clsact
+
+	ip route del vrf v$ul31 192.0.2.1/32
+	ip route del vrf v$ul31 192.0.2.2/32
+
+	vlan_destroy $ul32 222
+	vlan_destroy $ul32 111
+	__simple_if_fini $ul32
+	simple_if_fini $ul31 192.0.2.65/28
+}
+
+sw4_create()
+{
+	simple_if_init $ol4 203.0.113.1/24 2001:db8:2::1/64
+	__simple_if_init $ul4 v$ol4 192.0.2.66/28
+
+	tunnel_create g2 gre 192.0.2.2 192.0.2.1 tos inherit dev v$ol4
+	__simple_if_init g2 v$ol4 192.0.2.2/32
+	ip route add vrf v$ol4 192.0.2.1/32 via 192.0.2.65
+
+	ip route add vrf v$ol4 198.51.100.0/24 dev g2
+	ip -6 route add vrf v$ol4 2001:db8:1::/64 dev g2
+}
+
+sw4_destroy()
+{
+	ip -6 route del vrf v$ol4 2001:db8:1::/64
+	ip route del vrf v$ol4 198.51.100.0/24
+
+	ip route del vrf v$ol4 192.0.2.1/32
+	__simple_if_fini g2 192.0.2.2/32
+	tunnel_destroy g2
+
+	__simple_if_fini $ul4 192.0.2.66/28
+	simple_if_fini $ol4 203.0.113.1/24 2001:db8:2::1/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 203.0.113.2/24 2001:db8:2::2/64
+	ip route add vrf v$h2 default via 203.0.113.1 dev $h2
+	ip -6 route add vrf v$h2 default via 2001:db8:2::1 dev $h2
+}
+
+h2_destroy()
+{
+	ip -6 route del vrf v$h2 default
+	ip route del vrf v$h2 default
+	simple_if_fini $h2 203.0.113.2/24 2001:db8:2::2/64
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+
+	ol1=${NETIFS[p2]}
+	ul1=${NETIFS[p3]}
+
+	ul21=${NETIFS[p4]}
+	ul22=${NETIFS[p5]}
+
+	ul32=${NETIFS[p6]}
+	ul31=${NETIFS[p7]}
+
+	ul4=${NETIFS[p8]}
+	ol4=${NETIFS[p9]}
+
+	h2=${NETIFS[p10]}
+
+	vrf_prepare
+	h1_create
+	sw1_create
+	sw2_create
+	sw3_create
+	sw4_create
+	h2_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	h2_destroy
+	sw4_destroy
+	sw3_destroy
+	sw2_destroy
+	sw1_destroy
+	h1_destroy
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1 203.0.113.2
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::2
+}
+
+send_src_ipv4()
+{
+	$MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \
+		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
+}
+
+send_dst_ipv4()
+{
+	$MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \
+		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
+}
+
+send_src_udp4()
+{
+	$MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+		-d 1msec -t udp "sp=0-32768,dp=30000"
+}
+
+send_dst_udp4()
+{
+	$MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+		-d 1msec -t udp "sp=20000,dp=0-32768"
+}
+
+send_src_ipv6()
+{
+	$MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \
+		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
+}
+
+send_dst_ipv6()
+{
+	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \
+		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
+}
+
+send_flowlabel()
+{
+	# Generate 16384 echo requests, each with a random flow label.
+	for _ in $(seq 1 16384); do
+		ip vrf exec v$h1 \
+			$PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1
+	done
+}
+
+send_src_udp6()
+{
+	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
+		-d 1msec -t udp "sp=0-32768,dp=30000"
+}
+
+send_dst_udp6()
+{
+	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
+		-d 1msec -t udp "sp=20000,dp=0-32768"
+}
+
+custom_hash_test()
+{
+	local field="$1"; shift
+	local balanced="$1"; shift
+	local send_flows="$@"
+
+	RET=0
+
+	local t0_111=$(tc_rule_stats_get $ul32 111 ingress)
+	local t0_222=$(tc_rule_stats_get $ul32 222 ingress)
+
+	$send_flows
+
+	local t1_111=$(tc_rule_stats_get $ul32 111 ingress)
+	local t1_222=$(tc_rule_stats_get $ul32 222 ingress)
+
+	local d111=$((t1_111 - t0_111))
+	local d222=$((t1_222 - t0_222))
+
+	local diff=$((d222 - d111))
+	local sum=$((d111 + d222))
+
+	local pct=$(echo "$diff / $sum * 100" | bc -l)
+	local is_balanced=$(echo "-20 <= $pct && $pct <= 20" | bc)
+
+	[[ ( $is_balanced -eq 1 && $balanced == "balanced" ) ||
+	   ( $is_balanced -eq 0 && $balanced == "unbalanced" ) ]]
+	check_err $? "Expected traffic to be $balanced, but it is not"
+
+	log_test "Multipath hash field: $field ($balanced)"
+	log_info "Packets sent on path1 / path2: $d111 / $d222"
+}
+
+custom_hash_v4()
+{
+	log_info "Running IPv4 overlay custom multipath hash tests"
+
+	# Prevent the neighbour table from overflowing, as different neighbour
+	# entries will be created on $ol4 when using different destination IPs.
+	sysctl_set net.ipv4.neigh.default.gc_thresh1 1024
+	sysctl_set net.ipv4.neigh.default.gc_thresh2 1024
+	sysctl_set net.ipv4.neigh.default.gc_thresh3 1024
+
+	sysctl_set net.ipv4.fib_multipath_hash_fields 0x0040
+	custom_hash_test "Inner source IP" "balanced" send_src_ipv4
+	custom_hash_test "Inner source IP" "unbalanced" send_dst_ipv4
+
+	sysctl_set net.ipv4.fib_multipath_hash_fields 0x0080
+	custom_hash_test "Inner destination IP" "balanced" send_dst_ipv4
+	custom_hash_test "Inner destination IP" "unbalanced" send_src_ipv4
+
+	sysctl_set net.ipv4.fib_multipath_hash_fields 0x0400
+	custom_hash_test "Inner source port" "balanced" send_src_udp4
+	custom_hash_test "Inner source port" "unbalanced" send_dst_udp4
+
+	sysctl_set net.ipv4.fib_multipath_hash_fields 0x0800
+	custom_hash_test "Inner destination port" "balanced" send_dst_udp4
+	custom_hash_test "Inner destination port" "unbalanced" send_src_udp4
+
+	sysctl_restore net.ipv4.neigh.default.gc_thresh3
+	sysctl_restore net.ipv4.neigh.default.gc_thresh2
+	sysctl_restore net.ipv4.neigh.default.gc_thresh1
+}
+
+custom_hash_v6()
+{
+	log_info "Running IPv6 overlay custom multipath hash tests"
+
+	# Prevent the neighbour table from overflowing, as different neighbour
+	# entries will be created on $ol4 when using different destination IPs.
+	sysctl_set net.ipv6.neigh.default.gc_thresh1 1024
+	sysctl_set net.ipv6.neigh.default.gc_thresh2 1024
+	sysctl_set net.ipv6.neigh.default.gc_thresh3 1024
+
+	sysctl_set net.ipv4.fib_multipath_hash_fields 0x0040
+	custom_hash_test "Inner source IP" "balanced" send_src_ipv6
+	custom_hash_test "Inner source IP" "unbalanced" send_dst_ipv6
+
+	sysctl_set net.ipv4.fib_multipath_hash_fields 0x0080
+	custom_hash_test "Inner destination IP" "balanced" send_dst_ipv6
+	custom_hash_test "Inner destination IP" "unbalanced" send_src_ipv6
+
+	sysctl_set net.ipv4.fib_multipath_hash_fields 0x0200
+	custom_hash_test "Inner flowlabel" "balanced" send_flowlabel
+	custom_hash_test "Inner flowlabel" "unbalanced" send_src_ipv6
+
+	sysctl_set net.ipv4.fib_multipath_hash_fields 0x0400
+	custom_hash_test "Inner source port" "balanced" send_src_udp6
+	custom_hash_test "Inner source port" "unbalanced" send_dst_udp6
+
+	sysctl_set net.ipv4.fib_multipath_hash_fields 0x0800
+	custom_hash_test "Inner destination port" "balanced" send_dst_udp6
+	custom_hash_test "Inner destination port" "unbalanced" send_src_udp6
+
+	sysctl_restore net.ipv6.neigh.default.gc_thresh3
+	sysctl_restore net.ipv6.neigh.default.gc_thresh2
+	sysctl_restore net.ipv6.neigh.default.gc_thresh1
+}
+
+custom_hash()
+{
+	# Test that when the hash policy is set to custom, traffic is
+	# distributed only according to the fields set in the
+	# fib_multipath_hash_fields sysctl.
+	#
+	# Each time set a different field and make sure traffic is only
+	# distributed when the field is changed in the packet stream.
+
+	sysctl_set net.ipv4.fib_multipath_hash_policy 3
+
+	custom_hash_v4
+	custom_hash_v6
+
+	sysctl_restore net.ipv4.fib_multipath_hash_policy
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh
new file mode 100755
index 000000000000..8fea2c2e0b25
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh
@@ -0,0 +1,458 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test traffic distribution when there are multiple paths between an IPv6 GRE
+# tunnel. The tunnel carries IPv4 and IPv6 traffic between multiple hosts.
+# Multiple routes are in the underlay network. With the default multipath
+# policy, SW2 will only look at the outer IP addresses, hence only a single
+# route would be used.
+#
+# +--------------------------------+
+# | H1                             |
+# |                     $h1 +      |
+# |   198.51.100.{2-253}/24 |      |
+# |   2001:db8:1::{2-fd}/64 |      |
+# +-------------------------|------+
+#                           |
+# +-------------------------|-------------------+
+# | SW1                     |                   |
+# |                    $ol1 +                   |
+# |         198.51.100.1/24                     |
+# |        2001:db8:1::1/64                     |
+# |                                             |
+# |+ g1 (ip6gre)                                |
+# |  loc=2001:db8:3::1                          |
+# |  rem=2001:db8:3::2 -.                       |
+# |     tos=inherit     |                       |
+# |                     v                       |
+# |                     + $ul1                  |
+# |                     | 2001:db8:10::1/64     |
+# +---------------------|-----------------------+
+#                       |
+# +---------------------|-----------------------+
+# | SW2                 |                       |
+# |               $ul21 +                       |
+# |   2001:db8:10::2/64 |                       |
+# |                     |                       |
+# !   __________________+___                    |
+# |  /                      \                   |
+# |  |                      |                   |
+# |  + $ul22.111 (vlan)     + $ul22.222 (vlan)  |
+# |  | 2001:db8:11::1/64    | 2001:db8:12::1/64 |
+# |  |                      |                   |
+# +--|----------------------|-------------------+
+#    |                      |
+# +--|----------------------|-------------------+
+# |  |                      |                   |
+# |  + $ul32.111 (vlan)     + $ul32.222 (vlan)  |
+# |  | 2001:db8:11::2/64    | 2001:db8:12::2/64 |
+# |  |                      |                   |
+# |  \__________________+___/                   |
+# |                     |                       |
+# |                     |                       |
+# |               $ul31 +                       |
+# |   2001:db8:13::1/64 |                   SW3 |
+# +---------------------|-----------------------+
+#                       |
+# +---------------------|-----------------------+
+# |                     + $ul4                  |
+# |                     ^ 2001:db8:13::2/64     |
+# |                     |                       |
+# |+ g2 (ip6gre)        |                       |
+# |  loc=2001:db8:3::2  |                       |
+# |  rem=2001:db8:3::1 -'                       |
+# |  tos=inherit                                |
+# |                                             |
+# |                    $ol4 +                   |
+# |          203.0.113.1/24 |                   |
+# |        2001:db8:2::1/64 |               SW4 |
+# +-------------------------|-------------------+
+#                           |
+# +-------------------------|------+
+# |                         |      |
+# |                     $h2 +      |
+# |    203.0.113.{2-253}/24        |
+# |   2001:db8:2::{2-fd}/64     H2 |
+# +--------------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	custom_hash
+"
+
+NUM_NETIFS=10
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 198.51.100.2/24 2001:db8:1::2/64
+	ip route add vrf v$h1 default via 198.51.100.1 dev $h1
+	ip -6 route add vrf v$h1 default via 2001:db8:1::1 dev $h1
+}
+
+h1_destroy()
+{
+	ip -6 route del vrf v$h1 default
+	ip route del vrf v$h1 default
+	simple_if_fini $h1 198.51.100.2/24 2001:db8:1::2/64
+}
+
+sw1_create()
+{
+	simple_if_init $ol1 198.51.100.1/24 2001:db8:1::1/64
+	__simple_if_init $ul1 v$ol1 2001:db8:10::1/64
+
+	tunnel_create g1 ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \
+		dev v$ol1
+	__simple_if_init g1 v$ol1 2001:db8:3::1/128
+	ip route add vrf v$ol1 2001:db8:3::2/128 via 2001:db8:10::2
+
+	ip route add vrf v$ol1 203.0.113.0/24 dev g1
+	ip -6 route add vrf v$ol1 2001:db8:2::/64 dev g1
+}
+
+sw1_destroy()
+{
+	ip -6 route del vrf v$ol1 2001:db8:2::/64
+	ip route del vrf v$ol1 203.0.113.0/24
+
+	ip route del vrf v$ol1 2001:db8:3::2/128
+	__simple_if_fini g1 2001:db8:3::1/128
+	tunnel_destroy g1
+
+	__simple_if_fini $ul1 2001:db8:10::1/64
+	simple_if_fini $ol1 198.51.100.1/24 2001:db8:1::1/64
+}
+
+sw2_create()
+{
+	simple_if_init $ul21 2001:db8:10::2/64
+	__simple_if_init $ul22 v$ul21
+	vlan_create $ul22 111 v$ul21 2001:db8:11::1/64
+	vlan_create $ul22 222 v$ul21 2001:db8:12::1/64
+
+	ip -6 route add vrf v$ul21 2001:db8:3::1/128 via 2001:db8:10::1
+	ip -6 route add vrf v$ul21 2001:db8:3::2/128 \
+	   nexthop via 2001:db8:11::2 \
+	   nexthop via 2001:db8:12::2
+}
+
+sw2_destroy()
+{
+	ip -6 route del vrf v$ul21 2001:db8:3::2/128
+	ip -6 route del vrf v$ul21 2001:db8:3::1/128
+
+	vlan_destroy $ul22 222
+	vlan_destroy $ul22 111
+	__simple_if_fini $ul22
+	simple_if_fini $ul21 2001:db8:10::2/64
+}
+
+sw3_create()
+{
+	simple_if_init $ul31 2001:db8:13::1/64
+	__simple_if_init $ul32 v$ul31
+	vlan_create $ul32 111 v$ul31 2001:db8:11::2/64
+	vlan_create $ul32 222 v$ul31 2001:db8:12::2/64
+
+	ip -6 route add vrf v$ul31 2001:db8:3::2/128 via 2001:db8:13::2
+	ip -6 route add vrf v$ul31 2001:db8:3::1/128 \
+	   nexthop via 2001:db8:11::1 \
+	   nexthop via 2001:db8:12::1
+
+	tc qdisc add dev $ul32 clsact
+	tc filter add dev $ul32 ingress pref 111 prot 802.1Q \
+	   flower vlan_id 111 action pass
+	tc filter add dev $ul32 ingress pref 222 prot 802.1Q \
+	   flower vlan_id 222 action pass
+}
+
+sw3_destroy()
+{
+	tc qdisc del dev $ul32 clsact
+
+	ip -6 route del vrf v$ul31 2001:db8:3::1/128
+	ip -6 route del vrf v$ul31 2001:db8:3::2/128
+
+	vlan_destroy $ul32 222
+	vlan_destroy $ul32 111
+	__simple_if_fini $ul32
+	simple_if_fini $ul31 2001:db8:13::1/64
+}
+
+sw4_create()
+{
+	simple_if_init $ol4 203.0.113.1/24 2001:db8:2::1/64
+	__simple_if_init $ul4 v$ol4 2001:db8:13::2/64
+
+	tunnel_create g2 ip6gre 2001:db8:3::2 2001:db8:3::1 tos inherit \
+		dev v$ol4
+	__simple_if_init g2 v$ol4 2001:db8:3::2/128
+	ip -6 route add vrf v$ol4 2001:db8:3::1/128 via 2001:db8:13::1
+
+	ip route add vrf v$ol4 198.51.100.0/24 dev g2
+	ip -6 route add vrf v$ol4 2001:db8:1::/64 dev g2
+}
+
+sw4_destroy()
+{
+	ip -6 route del vrf v$ol4 2001:db8:1::/64
+	ip route del vrf v$ol4 198.51.100.0/24
+
+	ip -6 route del vrf v$ol4 2001:db8:3::1/128
+	__simple_if_fini g2 2001:db8:3::2/128
+	tunnel_destroy g2
+
+	__simple_if_fini $ul4 2001:db8:13::2/64
+	simple_if_fini $ol4 203.0.113.1/24 2001:db8:2::1/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 203.0.113.2/24 2001:db8:2::2/64
+	ip route add vrf v$h2 default via 203.0.113.1 dev $h2
+	ip -6 route add vrf v$h2 default via 2001:db8:2::1 dev $h2
+}
+
+h2_destroy()
+{
+	ip -6 route del vrf v$h2 default
+	ip route del vrf v$h2 default
+	simple_if_fini $h2 203.0.113.2/24 2001:db8:2::2/64
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+
+	ol1=${NETIFS[p2]}
+	ul1=${NETIFS[p3]}
+
+	ul21=${NETIFS[p4]}
+	ul22=${NETIFS[p5]}
+
+	ul32=${NETIFS[p6]}
+	ul31=${NETIFS[p7]}
+
+	ul4=${NETIFS[p8]}
+	ol4=${NETIFS[p9]}
+
+	h2=${NETIFS[p10]}
+
+	vrf_prepare
+	h1_create
+	sw1_create
+	sw2_create
+	sw3_create
+	sw4_create
+	h2_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	h2_destroy
+	sw4_destroy
+	sw3_destroy
+	sw2_destroy
+	sw1_destroy
+	h1_destroy
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1 203.0.113.2
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::2
+}
+
+send_src_ipv4()
+{
+	$MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \
+		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
+}
+
+send_dst_ipv4()
+{
+	$MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \
+		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
+}
+
+send_src_udp4()
+{
+	$MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+		-d 1msec -t udp "sp=0-32768,dp=30000"
+}
+
+send_dst_udp4()
+{
+	$MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+		-d 1msec -t udp "sp=20000,dp=0-32768"
+}
+
+send_src_ipv6()
+{
+	$MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \
+		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
+}
+
+send_dst_ipv6()
+{
+	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \
+		-d 1msec -c 50 -t udp "sp=20000,dp=30000"
+}
+
+send_flowlabel()
+{
+	# Generate 16384 echo requests, each with a random flow label.
+	for _ in $(seq 1 16384); do
+		ip vrf exec v$h1 \
+			$PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1
+	done
+}
+
+send_src_udp6()
+{
+	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
+		-d 1msec -t udp "sp=0-32768,dp=30000"
+}
+
+send_dst_udp6()
+{
+	$MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
+		-d 1msec -t udp "sp=20000,dp=0-32768"
+}
+
+custom_hash_test()
+{
+	local field="$1"; shift
+	local balanced="$1"; shift
+	local send_flows="$@"
+
+	RET=0
+
+	local t0_111=$(tc_rule_stats_get $ul32 111 ingress)
+	local t0_222=$(tc_rule_stats_get $ul32 222 ingress)
+
+	$send_flows
+
+	local t1_111=$(tc_rule_stats_get $ul32 111 ingress)
+	local t1_222=$(tc_rule_stats_get $ul32 222 ingress)
+
+	local d111=$((t1_111 - t0_111))
+	local d222=$((t1_222 - t0_222))
+
+	local diff=$((d222 - d111))
+	local sum=$((d111 + d222))
+
+	local pct=$(echo "$diff / $sum * 100" | bc -l)
+	local is_balanced=$(echo "-20 <= $pct && $pct <= 20" | bc)
+
+	[[ ( $is_balanced -eq 1 && $balanced == "balanced" ) ||
+	   ( $is_balanced -eq 0 && $balanced == "unbalanced" ) ]]
+	check_err $? "Expected traffic to be $balanced, but it is not"
+
+	log_test "Multipath hash field: $field ($balanced)"
+	log_info "Packets sent on path1 / path2: $d111 / $d222"
+}
+
+custom_hash_v4()
+{
+	log_info "Running IPv4 overlay custom multipath hash tests"
+
+	# Prevent the neighbour table from overflowing, as different neighbour
+	# entries will be created on $ol4 when using different destination IPs.
+	sysctl_set net.ipv4.neigh.default.gc_thresh1 1024
+	sysctl_set net.ipv4.neigh.default.gc_thresh2 1024
+	sysctl_set net.ipv4.neigh.default.gc_thresh3 1024
+
+	sysctl_set net.ipv6.fib_multipath_hash_fields 0x0040
+	custom_hash_test "Inner source IP" "balanced" send_src_ipv4
+	custom_hash_test "Inner source IP" "unbalanced" send_dst_ipv4
+
+	sysctl_set net.ipv6.fib_multipath_hash_fields 0x0080
+	custom_hash_test "Inner destination IP" "balanced" send_dst_ipv4
+	custom_hash_test "Inner destination IP" "unbalanced" send_src_ipv4
+
+	sysctl_set net.ipv6.fib_multipath_hash_fields 0x0400
+	custom_hash_test "Inner source port" "balanced" send_src_udp4
+	custom_hash_test "Inner source port" "unbalanced" send_dst_udp4
+
+	sysctl_set net.ipv6.fib_multipath_hash_fields 0x0800
+	custom_hash_test "Inner destination port" "balanced" send_dst_udp4
+	custom_hash_test "Inner destination port" "unbalanced" send_src_udp4
+
+	sysctl_restore net.ipv4.neigh.default.gc_thresh3
+	sysctl_restore net.ipv4.neigh.default.gc_thresh2
+	sysctl_restore net.ipv4.neigh.default.gc_thresh1
+}
+
+custom_hash_v6()
+{
+	log_info "Running IPv6 overlay custom multipath hash tests"
+
+	# Prevent the neighbour table from overflowing, as different neighbour
+	# entries will be created on $ol4 when using different destination IPs.
+	sysctl_set net.ipv6.neigh.default.gc_thresh1 1024
+	sysctl_set net.ipv6.neigh.default.gc_thresh2 1024
+	sysctl_set net.ipv6.neigh.default.gc_thresh3 1024
+
+	sysctl_set net.ipv6.fib_multipath_hash_fields 0x0040
+	custom_hash_test "Inner source IP" "balanced" send_src_ipv6
+	custom_hash_test "Inner source IP" "unbalanced" send_dst_ipv6
+
+	sysctl_set net.ipv6.fib_multipath_hash_fields 0x0080
+	custom_hash_test "Inner destination IP" "balanced" send_dst_ipv6
+	custom_hash_test "Inner destination IP" "unbalanced" send_src_ipv6
+
+	sysctl_set net.ipv6.fib_multipath_hash_fields 0x0200
+	custom_hash_test "Inner flowlabel" "balanced" send_flowlabel
+	custom_hash_test "Inner flowlabel" "unbalanced" send_src_ipv6
+
+	sysctl_set net.ipv6.fib_multipath_hash_fields 0x0400
+	custom_hash_test "Inner source port" "balanced" send_src_udp6
+	custom_hash_test "Inner source port" "unbalanced" send_dst_udp6
+
+	sysctl_set net.ipv6.fib_multipath_hash_fields 0x0800
+	custom_hash_test "Inner destination port" "balanced" send_dst_udp6
+	custom_hash_test "Inner destination port" "unbalanced" send_src_udp6
+
+	sysctl_restore net.ipv6.neigh.default.gc_thresh3
+	sysctl_restore net.ipv6.neigh.default.gc_thresh2
+	sysctl_restore net.ipv6.neigh.default.gc_thresh1
+}
+
+custom_hash()
+{
+	# Test that when the hash policy is set to custom, traffic is
+	# distributed only according to the fields set in the
+	# fib_multipath_hash_fields sysctl.
+	#
+	# Each time set a different field and make sure traffic is only
+	# distributed when the field is changed in the packet stream.
+
+	sysctl_set net.ipv6.fib_multipath_hash_policy 3
+
+	custom_hash_v4
+	custom_hash_v6
+
+	sysctl_restore net.ipv6.fib_multipath_hash_policy
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh
index 55eeacf59241..64fbd211d907 100755
--- a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh
+++ b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh
@@ -75,7 +75,9 @@ switch_destroy()
 	tc qdisc del dev $swp2 clsact
 	tc qdisc del dev $swp1 clsact
 
+	ip link set dev $swp2 down
 	ip link set dev $swp2 nomaster
+	ip link set dev $swp1 down
 	ip link set dev $swp1 nomaster
 	ip link del dev br1
 }
diff --git a/tools/testing/selftests/net/forwarding/pedit_l4port.sh b/tools/testing/selftests/net/forwarding/pedit_l4port.sh
index 5f20d289ee43..10e594c55117 100755
--- a/tools/testing/selftests/net/forwarding/pedit_l4port.sh
+++ b/tools/testing/selftests/net/forwarding/pedit_l4port.sh
@@ -71,7 +71,9 @@ switch_destroy()
 	tc qdisc del dev $swp2 clsact
 	tc qdisc del dev $swp1 clsact
 
+	ip link set dev $swp2 down
 	ip link set dev $swp2 nomaster
+	ip link set dev $swp1 down
 	ip link set dev $swp1 nomaster
 	ip link del dev br1
 }
diff --git a/tools/testing/selftests/net/forwarding/skbedit_priority.sh b/tools/testing/selftests/net/forwarding/skbedit_priority.sh
index e3bd8a6bb8b4..bde11dc27873 100755
--- a/tools/testing/selftests/net/forwarding/skbedit_priority.sh
+++ b/tools/testing/selftests/net/forwarding/skbedit_priority.sh
@@ -72,7 +72,9 @@ switch_destroy()
 	tc qdisc del dev $swp2 clsact
 	tc qdisc del dev $swp1 clsact
 
+	ip link set dev $swp2 down
 	ip link set dev $swp2 nomaster
+	ip link set dev $swp1 down
 	ip link set dev $swp1 nomaster
 	ip link del dev br1
 }
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index d88e1fdfb147..89c4753c2760 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -6,6 +6,7 @@
 #include <limits.h>
 #include <fcntl.h>
 #include <string.h>
+#include <stdarg.h>
 #include <stdbool.h>
 #include <stdint.h>
 #include <stdio.h>
@@ -25,6 +26,7 @@
 #include <netinet/in.h>
 
 #include <linux/tcp.h>
+#include <linux/time_types.h>
 
 extern int optind;
 
@@ -66,6 +68,13 @@ static unsigned int cfg_do_w;
 static int cfg_wait;
 static uint32_t cfg_mark;
 
+struct cfg_cmsg_types {
+	unsigned int cmsg_enabled:1;
+	unsigned int timestampns:1;
+};
+
+static struct cfg_cmsg_types cfg_cmsg_types;
+
 static void die_usage(void)
 {
 	fprintf(stderr, "Usage: mptcp_connect [-6] [-u] [-s MPTCP|TCP] [-p port] [-m mode]"
@@ -80,11 +89,22 @@ static void die_usage(void)
 	fprintf(stderr, "\t-M mark -- set socket packet mark\n");
 	fprintf(stderr, "\t-u -- check mptcp ulp\n");
 	fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n");
+	fprintf(stderr, "\t-c cmsg -- test cmsg type <cmsg>\n");
 	fprintf(stderr,
 		"\t-P [saveWithPeek|saveAfterPeek] -- save data with/after MSG_PEEK form tcp socket\n");
 	exit(1);
 }
 
+static void xerror(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+	exit(1);
+}
+
 static void handle_signal(int nr)
 {
 	quit = true;
@@ -338,6 +358,58 @@ static size_t do_write(const int fd, char *buf, const size_t len)
 	return offset;
 }
 
+static void process_cmsg(struct msghdr *msgh)
+{
+	struct __kernel_timespec ts;
+	bool ts_found = false;
+	struct cmsghdr *cmsg;
+
+	for (cmsg = CMSG_FIRSTHDR(msgh); cmsg ; cmsg = CMSG_NXTHDR(msgh, cmsg)) {
+		if (cmsg->cmsg_level == SOL_SOCKET && cmsg->cmsg_type == SO_TIMESTAMPNS_NEW) {
+			memcpy(&ts, CMSG_DATA(cmsg), sizeof(ts));
+			ts_found = true;
+			continue;
+		}
+	}
+
+	if (cfg_cmsg_types.timestampns) {
+		if (!ts_found)
+			xerror("TIMESTAMPNS not present\n");
+	}
+}
+
+static ssize_t do_recvmsg_cmsg(const int fd, char *buf, const size_t len)
+{
+	char msg_buf[8192];
+	struct iovec iov = {
+		.iov_base = buf,
+		.iov_len = len,
+	};
+	struct msghdr msg = {
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+		.msg_control = msg_buf,
+		.msg_controllen = sizeof(msg_buf),
+	};
+	int flags = 0;
+	int ret = recvmsg(fd, &msg, flags);
+
+	if (ret <= 0)
+		return ret;
+
+	if (msg.msg_controllen && !cfg_cmsg_types.cmsg_enabled)
+		xerror("got %lu bytes of cmsg data, expected 0\n",
+		       (unsigned long)msg.msg_controllen);
+
+	if (msg.msg_controllen == 0 && cfg_cmsg_types.cmsg_enabled)
+		xerror("%s\n", "got no cmsg data");
+
+	if (msg.msg_controllen)
+		process_cmsg(&msg);
+
+	return ret;
+}
+
 static ssize_t do_rnd_read(const int fd, char *buf, const size_t len)
 {
 	int ret = 0;
@@ -357,6 +429,8 @@ static ssize_t do_rnd_read(const int fd, char *buf, const size_t len)
 	} else if (cfg_peek == CFG_AFTER_PEEK) {
 		ret = recv(fd, buf, cap, MSG_PEEK);
 		ret = (ret < 0) ? ret : read(fd, buf, cap);
+	} else if (cfg_cmsg_types.cmsg_enabled) {
+		ret = do_recvmsg_cmsg(fd, buf, cap);
 	} else {
 		ret = read(fd, buf, cap);
 	}
@@ -786,6 +860,48 @@ static void init_rng(void)
 	srand(foo);
 }
 
+static void xsetsockopt(int fd, int level, int optname, const void *optval, socklen_t optlen)
+{
+	int err;
+
+	err = setsockopt(fd, level, optname, optval, optlen);
+	if (err) {
+		perror("setsockopt");
+		exit(1);
+	}
+}
+
+static void apply_cmsg_types(int fd, const struct cfg_cmsg_types *cmsg)
+{
+	static const unsigned int on = 1;
+
+	if (cmsg->timestampns)
+		xsetsockopt(fd, SOL_SOCKET, SO_TIMESTAMPNS_NEW, &on, sizeof(on));
+}
+
+static void parse_cmsg_types(const char *type)
+{
+	char *next = strchr(type, ',');
+	unsigned int len = 0;
+
+	cfg_cmsg_types.cmsg_enabled = 1;
+
+	if (next) {
+		parse_cmsg_types(next + 1);
+		len = next - type;
+	} else {
+		len = strlen(type);
+	}
+
+	if (strncmp(type, "TIMESTAMPNS", len) == 0) {
+		cfg_cmsg_types.timestampns = 1;
+		return;
+	}
+
+	fprintf(stderr, "Unrecognized cmsg option %s\n", type);
+	exit(1);
+}
+
 int main_loop(void)
 {
 	int fd;
@@ -801,6 +917,8 @@ int main_loop(void)
 		set_rcvbuf(fd, cfg_rcvbuf);
 	if (cfg_sndbuf)
 		set_sndbuf(fd, cfg_sndbuf);
+	if (cfg_cmsg_types.cmsg_enabled)
+		apply_cmsg_types(fd, &cfg_cmsg_types);
 
 	return copyfd_io(0, fd, 1);
 }
@@ -887,7 +1005,7 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:M:P:")) != -1) {
+	while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:M:P:c:")) != -1) {
 		switch (c) {
 		case 'j':
 			cfg_join = true;
@@ -943,6 +1061,9 @@ static void parse_opts(int argc, char **argv)
 		case 'P':
 			cfg_peek = parse_peek(optarg);
 			break;
+		case 'c':
+			parse_cmsg_types(optarg);
+			break;
 		}
 	}
 
@@ -976,6 +1097,8 @@ int main(int argc, char *argv[])
 			set_sndbuf(fd, cfg_sndbuf);
 		if (cfg_mark)
 			set_mark(fd, cfg_mark);
+		if (cfg_cmsg_types.cmsg_enabled)
+			apply_cmsg_types(fd, &cfg_cmsg_types);
 
 		return main_loop_s(fd);
 	}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 2b495dc8d78e..2484fb6a9a8d 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -3,7 +3,7 @@
 
 time_start=$(date +%s)
 
-optstring="S:R:d:e:l:r:h4cm:f:t"
+optstring="S:R:d:e:l:r:h4cm:f:tC"
 ret=0
 sin=""
 sout=""
@@ -22,6 +22,7 @@ sndbuf=0
 rcvbuf=0
 options_log=true
 do_tcp=0
+checksum=false
 filesize=0
 
 if [ $tc_loss -eq 100 ];then
@@ -47,6 +48,7 @@ usage() {
 	echo -e "\t-R: set rcvbuf value (default: use kernel default)"
 	echo -e "\t-m: test mode (poll, sendfile; default: poll)"
 	echo -e "\t-t: also run tests with TCP (use twice to non-fallback tcp)"
+	echo -e "\t-C: enable the MPTCP data checksum"
 }
 
 while getopts "$optstring" option;do
@@ -104,6 +106,9 @@ while getopts "$optstring" option;do
 	"t")
 		do_tcp=$((do_tcp+1))
 		;;
+	"C")
+		checksum=true
+		;;
 	"?")
 		usage $0
 		exit 1
@@ -197,6 +202,12 @@ ip -net "$ns4" link set ns4eth3 up
 ip -net "$ns4" route add default via 10.0.3.2
 ip -net "$ns4" route add default via dead:beef:3::2
 
+if $checksum; then
+	for i in "$ns1" "$ns2" "$ns3" "$ns4";do
+		ip netns exec $i sysctl -q net.mptcp.checksum_enabled=1
+	done
+fi
+
 set_ethtool_flags() {
 	local ns="$1"
 	local dev="$2"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index fd99485cf2a4..523c7797f30a 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -12,6 +12,7 @@ timeout_poll=30
 timeout_test=$((timeout_poll * 2 + 1))
 mptcp_connect=""
 capture=0
+checksum=0
 do_all_tests=1
 
 TEST_COUNT=0
@@ -49,6 +50,9 @@ init()
 		ip netns exec $netns sysctl -q net.mptcp.enabled=1
 		ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0
 		ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0
+		if [ $checksum -eq 1 ]; then
+			ip netns exec $netns sysctl -q net.mptcp.checksum_enabled=1
+		fi
 	done
 
 	#  ns1              ns2
@@ -124,6 +128,17 @@ reset_with_add_addr_timeout()
 		-j DROP
 }
 
+reset_with_checksum()
+{
+	local ns1_enable=$1
+	local ns2_enable=$2
+
+	reset
+
+	ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=$ns1_enable
+	ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=$ns2_enable
+}
+
 ip -Version > /dev/null 2>&1
 if [ $? -ne 0 ];then
 	echo "SKIP: Could not run test without ip tool"
@@ -476,6 +491,45 @@ run_tests()
 	fi
 }
 
+chk_csum_nr()
+{
+	local msg=${1:-""}
+	local count
+	local dump_stats
+
+	if [ ! -z "$msg" ]; then
+		printf "%02u" "$TEST_COUNT"
+	else
+		echo -n "  "
+	fi
+	printf " %-36s %s" "$msg" "sum"
+	count=`ip netns exec $ns1 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}'`
+	[ -z "$count" ] && count=0
+	if [ "$count" != 0 ]; then
+		echo "[fail] got $count data checksum error[s] expected 0"
+		ret=1
+		dump_stats=1
+	else
+		echo -n "[ ok ]"
+	fi
+	echo -n " - csum  "
+	count=`ip netns exec $ns2 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}'`
+	[ -z "$count" ] && count=0
+	if [ "$count" != 0 ]; then
+		echo "[fail] got $count data checksum error[s] expected 0"
+		ret=1
+		dump_stats=1
+	else
+		echo "[ ok ]"
+	fi
+	if [ "${dump_stats}" = 1 ]; then
+		echo Server ns stats
+		ip netns exec $ns1 nstat -as | grep MPTcp
+		echo Client ns stats
+		ip netns exec $ns2 nstat -as | grep MPTcp
+	fi
+}
+
 chk_join_nr()
 {
 	local msg="$1"
@@ -523,6 +577,9 @@ chk_join_nr()
 		echo Client ns stats
 		ip netns exec $ns2 nstat -as | grep MPTcp
 	fi
+	if [ $checksum -eq 1 ]; then
+		chk_csum_nr
+	fi
 }
 
 chk_add_nr()
@@ -1374,6 +1431,37 @@ syncookies_tests()
 	chk_add_nr 1 1
 }
 
+checksum_tests()
+{
+	# checksum test 0 0
+	reset_with_checksum 0 0
+	ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+	ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+	run_tests $ns1 $ns2 10.0.1.1
+	chk_csum_nr "checksum test 0 0"
+
+	# checksum test 1 1
+	reset_with_checksum 1 1
+	ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+	ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+	run_tests $ns1 $ns2 10.0.1.1
+	chk_csum_nr "checksum test 1 1"
+
+	# checksum test 0 1
+	reset_with_checksum 0 1
+	ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+	ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+	run_tests $ns1 $ns2 10.0.1.1
+	chk_csum_nr "checksum test 0 1"
+
+	# checksum test 1 0
+	reset_with_checksum 1 0
+	ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+	ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+	run_tests $ns1 $ns2 10.0.1.1
+	chk_csum_nr "checksum test 1 0"
+}
+
 all_tests()
 {
 	subflows_tests
@@ -1387,6 +1475,7 @@ all_tests()
 	backup_tests
 	add_addr_ports_tests
 	syncookies_tests
+	checksum_tests
 }
 
 usage()
@@ -1403,7 +1492,9 @@ usage()
 	echo "  -b backup_tests"
 	echo "  -p add_addr_ports_tests"
 	echo "  -k syncookies_tests"
+	echo "  -S checksum_tests"
 	echo "  -c capture pcap files"
+	echo "  -C enable data checksum"
 	echo "  -h help"
 }
 
@@ -1418,13 +1509,16 @@ make_file "$sin" "server" 1
 trap cleanup EXIT
 
 for arg in "$@"; do
-	# check for "capture" arg before launching tests
+	# check for "capture/checksum" args before launching tests
 	if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"c"[0-9a-zA-Z]*$ ]]; then
 		capture=1
 	fi
+	if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"C"[0-9a-zA-Z]*$ ]]; then
+		checksum=1
+	fi
 
-	# exception for the capture option, the rest means: a part of the tests
-	if [ "${arg}" != "-c" ]; then
+	# exception for the capture/checksum options, the rest means: a part of the tests
+	if [ "${arg}" != "-c" ] && [ "${arg}" != "-C" ]; then
 		do_all_tests=0
 	fi
 done
@@ -1434,7 +1528,7 @@ if [ $do_all_tests -eq 1 ]; then
 	exit $ret
 fi
 
-while getopts 'fsltra64bpkch' opt; do
+while getopts 'fsltra64bpkchCS' opt; do
 	case $opt in
 		f)
 			subflows_tests
@@ -1469,8 +1563,13 @@ while getopts 'fsltra64bpkch' opt; do
 		k)
 			syncookies_tests
 			;;
+		S)
+			checksum_tests
+			;;
 		c)
 			;;
+		C)
+			;;
 		h | *)
 			usage
 			;;
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
index 2fa13946ac04..1579e471a5e7 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
@@ -178,7 +178,7 @@ do_transfer()
 
 	timeout ${timeout_test} \
 		ip netns exec ${listener_ns} \
-			$mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} \
+			$mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c TIMESTAMPNS \
 				${local_addr} < "$sin" > "$sout" &
 	spid=$!
 
@@ -186,7 +186,7 @@ do_transfer()
 
 	timeout ${timeout_test} \
 		ip netns exec ${connector_ns} \
-			$mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} \
+			$mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c TIMESTAMPNS \
 				$connect_addr < "$cin" > "$cout" &
 
 	cpid=$!
diff --git a/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh
new file mode 100755
index 000000000000..75ada17ac061
--- /dev/null
+++ b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh
@@ -0,0 +1,573 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# author: Andrea Mayer <andrea.mayer@uniroma2.it>
+# author: Paolo Lungaroni <paolo.lungaroni@uniroma2.it>
+
+# This test is designed for evaluating the new SRv6 End.DT46 Behavior used for
+# implementing IPv4/IPv6 L3 VPN use cases.
+#
+# The current SRv6 code in the Linux kernel only implements SRv6 End.DT4 and
+# End.DT6 Behaviors which can be used respectively to support IPv4-in-IPv6 and
+# IPv6-in-IPv6 VPNs. With End.DT4 and End.DT6 it is not possible to create a
+# single SRv6 VPN tunnel to carry both IPv4 and IPv6 traffic.
+# The SRv6 End.DT46 Behavior implementation is meant to support the
+# decapsulation of IPv4 and IPv6 traffic coming from a single SRv6 tunnel.
+# Therefore, the SRv6 End.DT46 Behavior in the Linux kernel greatly simplifies
+# the setup and operations of SRv6 VPNs.
+#
+# Hereafter a network diagram is shown, where two different tenants (named 100
+# and 200) offer IPv4/IPv6 L3 VPN services allowing hosts to communicate with
+# each other across an IPv6 network.
+#
+# Only hosts belonging to the same tenant (and to the same VPN) can communicate
+# with each other. Instead, the communication among hosts of different tenants
+# is forbidden.
+# In other words, hosts hs-t100-1 and hs-t100-2 are connected through the
+# IPv4/IPv6 L3 VPN of tenant 100 while hs-t200-3 and hs-t200-4 are connected
+# using the IPv4/IPv6 L3 VPN of tenant 200. Cross connection between tenant 100
+# and tenant 200 is forbidden and thus, for example, hs-t100-1 cannot reach
+# hs-t200-3 and vice versa.
+#
+# Routers rt-1 and rt-2 implement IPv4/IPv6 L3 VPN services leveraging the SRv6
+# architecture. The key components for such VPNs are: a) SRv6 Encap behavior,
+# b) SRv6 End.DT46 Behavior and c) VRF.
+#
+# To explain how an IPv4/IPv6 L3 VPN based on SRv6 works, let us briefly
+# consider an example where, within the same domain of tenant 100, the host
+# hs-t100-1 pings the host hs-t100-2.
+#
+# First of all, L2 reachability of the host hs-t100-2 is taken into account by
+# the router rt-1 which acts as a arp/ndp proxy.
+#
+# When the host hs-t100-1 sends an IPv6 or IPv4 packet destined to hs-t100-2,
+# the router rt-1 receives the packet on the internal veth-t100 interface. Such
+# interface is enslaved to the VRF vrf-100 whose associated table contains the
+# SRv6 Encap route for encapsulating any IPv6 or IPv4 packet in a IPv6 plus the
+# Segment Routing Header (SRH) packet. This packet is sent through the (IPv6)
+# core network up to the router rt-2 that receives it on veth0 interface.
+#
+# The rt-2 router uses the 'localsid' routing table to process incoming
+# IPv6+SRH packets which belong to the VPN of the tenant 100. For each of these
+# packets, the SRv6 End.DT46 Behavior removes the outer IPv6+SRH headers and
+# performs the lookup on the vrf-100 table using the destination address of
+# the decapsulated IPv6 or IPv4 packet. Afterwards, the packet is sent to the
+# host hs-t100-2 through the veth-t100 interface.
+#
+# The ping response follows the same processing but this time the roles of rt-1
+# and rt-2 are swapped.
+#
+# Of course, the IPv4/IPv6 L3 VPN for tenant 200 works exactly as the IPv4/IPv6
+# L3 VPN for tenant 100. In this case, only hosts hs-t200-3 and hs-t200-4 are
+# able to connect with each other.
+#
+#
+# +-------------------+                                   +-------------------+
+# |                   |                                   |                   |
+# |  hs-t100-1 netns  |                                   |  hs-t100-2 netns  |
+# |                   |                                   |                   |
+# |  +-------------+  |                                   |  +-------------+  |
+# |  |    veth0    |  |                                   |  |    veth0    |  |
+# |  |  cafe::1/64 |  |                                   |  |  cafe::2/64 |  |
+# |  | 10.0.0.1/24 |  |                                   |  | 10.0.0.2/24 |  |
+# |  +-------------+  |                                   |  +-------------+  |
+# |        .          |                                   |         .         |
+# +-------------------+                                   +-------------------+
+#          .                                                        .
+#          .                                                        .
+#          .                                                        .
+# +-----------------------------------+   +-----------------------------------+
+# |        .                          |   |                         .         |
+# | +---------------+                 |   |                 +---------------- |
+# | |   veth-t100   |                 |   |                 |   veth-t100   | |
+# | |  cafe::254/64 |                 |   |                 |  cafe::254/64 | |
+# | | 10.0.0.254/24 |    +----------+ |   | +----------+    | 10.0.0.254/24 | |
+# | +-------+-------+    | localsid | |   | | localsid |    +-------+-------- |
+# |         |            |   table  | |   | |   table  |            |         |
+# |    +----+----+       +----------+ |   | +----------+       +----+----+    |
+# |    | vrf-100 |                    |   |                    | vrf-100 |    |
+# |    +---------+     +------------+ |   | +------------+     +---------+    |
+# |                    |   veth0    | |   | |   veth0    |                    |
+# |                    | fd00::1/64 |.|...|.| fd00::2/64 |                    |
+# |    +---------+     +------------+ |   | +------------+     +---------+    |
+# |    | vrf-200 |                    |   |                    | vrf-200 |    |
+# |    +----+----+                    |   |                    +----+----+    |
+# |         |                         |   |                         |         |
+# | +-------+-------+                 |   |                 +-------+-------- |
+# | |   veth-t200   |                 |   |                 |   veth-t200   | |
+# | |  cafe::254/64 |                 |   |                 |  cafe::254/64 | |
+# | | 10.0.0.254/24 |                 |   |                 | 10.0.0.254/24 | |
+# | +---------------+      rt-1 netns |   | rt-2 netns      +---------------- |
+# |        .                          |   |                          .        |
+# +-----------------------------------+   +-----------------------------------+
+#          .                                                         .
+#          .                                                         .
+#          .                                                         .
+#          .                                                         .
+# +-------------------+                                   +-------------------+
+# |        .          |                                   |          .        |
+# |  +-------------+  |                                   |  +-------------+  |
+# |  |    veth0    |  |                                   |  |    veth0    |  |
+# |  |  cafe::3/64 |  |                                   |  |  cafe::4/64 |  |
+# |  | 10.0.0.3/24 |  |                                   |  | 10.0.0.4/24 |  |
+# |  +-------------+  |                                   |  +-------------+  |
+# |                   |                                   |                   |
+# |  hs-t200-3 netns  |                                   |  hs-t200-4 netns  |
+# |                   |                                   |                   |
+# +-------------------+                                   +-------------------+
+#
+#
+# ~~~~~~~~~~~~~~~~~~~~~~~~~
+# | Network configuration |
+# ~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+# rt-1: localsid table (table 90)
+# +--------------------------------------------------+
+# |SID              |Action                          |
+# +--------------------------------------------------+
+# |fc00:21:100::6046|apply SRv6 End.DT46 vrftable 100|
+# +--------------------------------------------------+
+# |fc00:21:200::6046|apply SRv6 End.DT46 vrftable 200|
+# +--------------------------------------------------+
+#
+# rt-1: VRF tenant 100 (table 100)
+# +---------------------------------------------------+
+# |host       |Action                                 |
+# +---------------------------------------------------+
+# |cafe::2    |apply seg6 encap segs fc00:12:100::6046|
+# +---------------------------------------------------+
+# |cafe::/64  |forward to dev veth-t100               |
+# +---------------------------------------------------+
+# |10.0.0.2   |apply seg6 encap segs fc00:12:100::6046|
+# +---------------------------------------------------+
+# |10.0.0.0/24|forward to dev veth-t100               |
+# +---------------------------------------------------+
+#
+# rt-1: VRF tenant 200 (table 200)
+# +---------------------------------------------------+
+# |host       |Action                                 |
+# +---------------------------------------------------+
+# |cafe::4    |apply seg6 encap segs fc00:12:200::6046|
+# +---------------------------------------------------+
+# |cafe::/64  |forward to dev veth-t200               |
+# +---------------------------------------------------+
+# |10.0.0.4   |apply seg6 encap segs fc00:12:200::6046|
+# +---------------------------------------------------+
+# |10.0.0.0/24|forward to dev veth-t200               |
+# +---------------------------------------------------+
+#
+#
+# rt-2: localsid table (table 90)
+# +--------------------------------------------------+
+# |SID              |Action                          |
+# +--------------------------------------------------+
+# |fc00:12:100::6046|apply SRv6 End.DT46 vrftable 100|
+# +--------------------------------------------------+
+# |fc00:12:200::6046|apply SRv6 End.DT46 vrftable 200|
+# +--------------------------------------------------+
+#
+# rt-2: VRF tenant 100 (table 100)
+# +---------------------------------------------------+
+# |host       |Action                                 |
+# +---------------------------------------------------+
+# |cafe::1    |apply seg6 encap segs fc00:21:100::6046|
+# +---------------------------------------------------+
+# |cafe::/64  |forward to dev veth-t100               |
+# +---------------------------------------------------+
+# |10.0.0.1   |apply seg6 encap segs fc00:21:100::6046|
+# +---------------------------------------------------+
+# |10.0.0.0/24|forward to dev veth-t100               |
+# +---------------------------------------------------+
+#
+# rt-2: VRF tenant 200 (table 200)
+# +---------------------------------------------------+
+# |host       |Action                                 |
+# +---------------------------------------------------+
+# |cafe::3    |apply seg6 encap segs fc00:21:200::6046|
+# +---------------------------------------------------+
+# |cafe::/64  |forward to dev veth-t200               |
+# +---------------------------------------------------+
+# |10.0.0.3   |apply seg6 encap segs fc00:21:200::6046|
+# +---------------------------------------------------+
+# |10.0.0.0/24|forward to dev veth-t200               |
+# +---------------------------------------------------+
+#
+
+readonly LOCALSID_TABLE_ID=90
+readonly IPv6_RT_NETWORK=fd00
+readonly IPv6_HS_NETWORK=cafe
+readonly IPv4_HS_NETWORK=10.0.0
+readonly VPN_LOCATOR_SERVICE=fc00
+PING_TIMEOUT_SEC=4
+
+ret=0
+
+PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
+
+log_test()
+{
+	local rc=$1
+	local expected=$2
+	local msg="$3"
+
+	if [ ${rc} -eq ${expected} ]; then
+		nsuccess=$((nsuccess+1))
+		printf "\n    TEST: %-60s  [ OK ]\n" "${msg}"
+	else
+		ret=1
+		nfail=$((nfail+1))
+		printf "\n    TEST: %-60s  [FAIL]\n" "${msg}"
+		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+			echo
+			echo "hit enter to continue, 'q' to quit"
+			read a
+			[ "$a" = "q" ] && exit 1
+		fi
+	fi
+}
+
+print_log_test_results()
+{
+	if [ "$TESTS" != "none" ]; then
+		printf "\nTests passed: %3d\n" ${nsuccess}
+		printf "Tests failed: %3d\n"   ${nfail}
+	fi
+}
+
+log_section()
+{
+	echo
+	echo "################################################################################"
+	echo "TEST SECTION: $*"
+	echo "################################################################################"
+}
+
+cleanup()
+{
+	ip link del veth-rt-1 2>/dev/null || true
+	ip link del veth-rt-2 2>/dev/null || true
+
+	# destroy routers rt-* and hosts hs-*
+	for ns in $(ip netns show | grep -E 'rt-*|hs-*'); do
+		ip netns del ${ns} || true
+	done
+}
+
+# Setup the basic networking for the routers
+setup_rt_networking()
+{
+	local rt=$1
+	local nsname=rt-${rt}
+
+	ip netns add ${nsname}
+	ip link set veth-rt-${rt} netns ${nsname}
+	ip -netns ${nsname} link set veth-rt-${rt} name veth0
+
+	ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0
+	ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0
+
+	ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad
+	ip -netns ${nsname} link set veth0 up
+	ip -netns ${nsname} link set lo up
+
+	ip netns exec ${nsname} sysctl -wq net.ipv4.ip_forward=1
+	ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.forwarding=1
+}
+
+setup_hs()
+{
+	local hs=$1
+	local rt=$2
+	local tid=$3
+	local hsname=hs-t${tid}-${hs}
+	local rtname=rt-${rt}
+	local rtveth=veth-t${tid}
+
+	# set the networking for the host
+	ip netns add ${hsname}
+
+	ip netns exec ${hsname} sysctl -wq net.ipv6.conf.all.accept_dad=0
+	ip netns exec ${hsname} sysctl -wq net.ipv6.conf.default.accept_dad=0
+
+	ip -netns ${hsname} link add veth0 type veth peer name ${rtveth}
+	ip -netns ${hsname} link set ${rtveth} netns ${rtname}
+	ip -netns ${hsname} addr add ${IPv6_HS_NETWORK}::${hs}/64 dev veth0 nodad
+	ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hs}/24 dev veth0
+	ip -netns ${hsname} link set veth0 up
+	ip -netns ${hsname} link set lo up
+
+	# configure the VRF for the tenant X on the router which is directly
+	# connected to the source host.
+	ip -netns ${rtname} link add vrf-${tid} type vrf table ${tid}
+	ip -netns ${rtname} link set vrf-${tid} up
+
+	ip netns exec ${rtname} sysctl -wq net.ipv6.conf.all.accept_dad=0
+	ip netns exec ${rtname} sysctl -wq net.ipv6.conf.default.accept_dad=0
+
+	# enslave the veth-tX interface to the vrf-X in the access router
+	ip -netns ${rtname} link set ${rtveth} master vrf-${tid}
+	ip -netns ${rtname} addr add ${IPv6_HS_NETWORK}::254/64 dev ${rtveth} nodad
+	ip -netns ${rtname} addr add ${IPv4_HS_NETWORK}.254/24 dev ${rtveth}
+	ip -netns ${rtname} link set ${rtveth} up
+
+	ip netns exec ${rtname} sysctl -wq net.ipv6.conf.${rtveth}.proxy_ndp=1
+	ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.proxy_arp=1
+
+	# disable the rp_filter otherwise the kernel gets confused about how
+	# to route decap ipv4 packets.
+	ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0
+	ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.rp_filter=0
+
+	ip netns exec ${rtname} sh -c "echo 1 > /proc/sys/net/vrf/strict_mode"
+}
+
+setup_vpn_config()
+{
+	local hssrc=$1
+	local rtsrc=$2
+	local hsdst=$3
+	local rtdst=$4
+	local tid=$5
+
+	local hssrc_name=hs-t${tid}-${hssrc}
+	local hsdst_name=hs-t${tid}-${hsdst}
+	local rtsrc_name=rt-${rtsrc}
+	local rtdst_name=rt-${rtdst}
+	local rtveth=veth-t${tid}
+	local vpn_sid=${VPN_LOCATOR_SERVICE}:${hssrc}${hsdst}:${tid}::6046
+
+	ip -netns ${rtsrc_name} -6 neigh add proxy ${IPv6_HS_NETWORK}::${hsdst} dev ${rtveth}
+
+	# set the encap route for encapsulating packets which arrive from the
+	# host hssrc and destined to the access router rtsrc.
+	ip -netns ${rtsrc_name} -6 route add ${IPv6_HS_NETWORK}::${hsdst}/128 vrf vrf-${tid} \
+		encap seg6 mode encap segs ${vpn_sid} dev veth0
+	ip -netns ${rtsrc_name} -4 route add ${IPv4_HS_NETWORK}.${hsdst}/32 vrf vrf-${tid} \
+		encap seg6 mode encap segs ${vpn_sid} dev veth0
+	ip -netns ${rtsrc_name} -6 route add ${vpn_sid}/128 vrf vrf-${tid} \
+		via fd00::${rtdst} dev veth0
+
+	# set the decap route for decapsulating packets which arrive from
+	# the rtdst router and destined to the hsdst host.
+	ip -netns ${rtdst_name} -6 route add ${vpn_sid}/128 table ${LOCALSID_TABLE_ID} \
+		encap seg6local action End.DT46 vrftable ${tid} dev vrf-${tid}
+
+	# all sids for VPNs start with a common locator which is fc00::/16.
+	# Routes for handling the SRv6 End.DT46 behavior instances are grouped
+	# together in the 'localsid' table.
+	#
+	# NOTE: added only once
+	if [ -z "$(ip -netns ${rtdst_name} -6 rule show | \
+	    grep "to ${VPN_LOCATOR_SERVICE}::/16 lookup ${LOCALSID_TABLE_ID}")" ]; then
+		ip -netns ${rtdst_name} -6 rule add \
+			to ${VPN_LOCATOR_SERVICE}::/16 \
+			lookup ${LOCALSID_TABLE_ID} prio 999
+	fi
+
+	# set default routes to unreachable for both ipv4 and ipv6
+	ip -netns ${rtsrc_name} -6 route add unreachable default metric 4278198272 \
+		vrf vrf-${tid}
+
+	ip -netns ${rtsrc_name} -4 route add unreachable default metric 4278198272 \
+		vrf vrf-${tid}
+}
+
+setup()
+{
+	ip link add veth-rt-1 type veth peer name veth-rt-2
+	# setup the networking for router rt-1 and router rt-2
+	setup_rt_networking 1
+	setup_rt_networking 2
+
+	# setup two hosts for the tenant 100.
+	#  - host hs-1 is directly connected to the router rt-1;
+	#  - host hs-2 is directly connected to the router rt-2.
+	setup_hs 1 1 100  #args: host router tenant
+	setup_hs 2 2 100
+
+	# setup two hosts for the tenant 200
+	#  - host hs-3 is directly connected to the router rt-1;
+	#  - host hs-4 is directly connected to the router rt-2.
+	setup_hs 3 1 200
+	setup_hs 4 2 200
+
+	# setup the IPv4/IPv6 L3 VPN which connects the host hs-t100-1 and host
+	# hs-t100-2 within the same tenant 100.
+	setup_vpn_config 1 1 2 2 100  #args: src_host src_router dst_host dst_router tenant
+	setup_vpn_config 2 2 1 1 100
+
+	# setup the IPv4/IPv6 L3 VPN which connects the host hs-t200-3 and host
+	# hs-t200-4 within the same tenant 200.
+	setup_vpn_config 3 1 4 2 200
+	setup_vpn_config 4 2 3 1 200
+}
+
+check_rt_connectivity()
+{
+	local rtsrc=$1
+	local rtdst=$2
+
+	ip netns exec rt-${rtsrc} ping -c 1 -W 1 ${IPv6_RT_NETWORK}::${rtdst} \
+		>/dev/null 2>&1
+}
+
+check_and_log_rt_connectivity()
+{
+	local rtsrc=$1
+	local rtdst=$2
+
+	check_rt_connectivity ${rtsrc} ${rtdst}
+	log_test $? 0 "Routers connectivity: rt-${rtsrc} -> rt-${rtdst}"
+}
+
+check_hs_ipv6_connectivity()
+{
+	local hssrc=$1
+	local hsdst=$2
+	local tid=$3
+
+	ip netns exec hs-t${tid}-${hssrc} ping -c 1 -W ${PING_TIMEOUT_SEC} \
+		${IPv6_HS_NETWORK}::${hsdst} >/dev/null 2>&1
+}
+
+check_hs_ipv4_connectivity()
+{
+	local hssrc=$1
+	local hsdst=$2
+	local tid=$3
+
+	ip netns exec hs-t${tid}-${hssrc} ping -c 1 -W ${PING_TIMEOUT_SEC} \
+		${IPv4_HS_NETWORK}.${hsdst} >/dev/null 2>&1
+}
+
+check_and_log_hs_connectivity()
+{
+	local hssrc=$1
+	local hsdst=$2
+	local tid=$3
+
+	check_hs_ipv6_connectivity ${hssrc} ${hsdst} ${tid}
+	log_test $? 0 "IPv6 Hosts connectivity: hs-t${tid}-${hssrc} -> hs-t${tid}-${hsdst} (tenant ${tid})"
+
+	check_hs_ipv4_connectivity ${hssrc} ${hsdst} ${tid}
+	log_test $? 0 "IPv4 Hosts connectivity: hs-t${tid}-${hssrc} -> hs-t${tid}-${hsdst} (tenant ${tid})"
+
+}
+
+check_and_log_hs_isolation()
+{
+	local hssrc=$1
+	local tidsrc=$2
+	local hsdst=$3
+	local tiddst=$4
+
+	check_hs_ipv6_connectivity ${hssrc} ${hsdst} ${tidsrc}
+	# NOTE: ping should fail
+	log_test $? 1 "IPv6 Hosts isolation: hs-t${tidsrc}-${hssrc} -X-> hs-t${tiddst}-${hsdst}"
+
+	check_hs_ipv4_connectivity ${hssrc} ${hsdst} ${tidsrc}
+	# NOTE: ping should fail
+	log_test $? 1 "IPv4 Hosts isolation: hs-t${tidsrc}-${hssrc} -X-> hs-t${tiddst}-${hsdst}"
+
+}
+
+
+check_and_log_hs2gw_connectivity()
+{
+	local hssrc=$1
+	local tid=$2
+
+	check_hs_ipv6_connectivity ${hssrc} 254 ${tid}
+	log_test $? 0 "IPv6 Hosts connectivity: hs-t${tid}-${hssrc} -> gw (tenant ${tid})"
+
+	check_hs_ipv4_connectivity ${hssrc} 254 ${tid}
+	log_test $? 0 "IPv4 Hosts connectivity: hs-t${tid}-${hssrc} -> gw (tenant ${tid})"
+
+}
+
+router_tests()
+{
+	log_section "IPv6 routers connectivity test"
+
+	check_and_log_rt_connectivity 1 2
+	check_and_log_rt_connectivity 2 1
+}
+
+host2gateway_tests()
+{
+	log_section "IPv4/IPv6 connectivity test among hosts and gateway"
+
+	check_and_log_hs2gw_connectivity 1 100
+	check_and_log_hs2gw_connectivity 2 100
+
+	check_and_log_hs2gw_connectivity 3 200
+	check_and_log_hs2gw_connectivity 4 200
+}
+
+host_vpn_tests()
+{
+	log_section "SRv6 VPN connectivity test among hosts in the same tenant"
+
+	check_and_log_hs_connectivity 1 2 100
+	check_and_log_hs_connectivity 2 1 100
+
+	check_and_log_hs_connectivity 3 4 200
+	check_and_log_hs_connectivity 4 3 200
+}
+
+host_vpn_isolation_tests()
+{
+	local i
+	local j
+	local k
+	local tmp
+	local l1="1 2"
+	local l2="3 4"
+	local t1=100
+	local t2=200
+
+	log_section "SRv6 VPN isolation test among hosts in different tentants"
+
+	for k in 0 1; do
+		for i in ${l1}; do
+			for j in ${l2}; do
+				check_and_log_hs_isolation ${i} ${t1} ${j} ${t2}
+			done
+		done
+
+		# let us test the reverse path
+		tmp="${l1}"; l1="${l2}"; l2="${tmp}"
+		tmp=${t1}; t1=${t2}; t2=${tmp}
+	done
+}
+
+if [ "$(id -u)" -ne 0 ];then
+	echo "SKIP: Need root privileges"
+	exit 0
+fi
+
+if [ ! -x "$(command -v ip)" ]; then
+	echo "SKIP: Could not run test without ip tool"
+	exit 0
+fi
+
+modprobe vrf &>/dev/null
+if [ ! -e /proc/sys/net/vrf/strict_mode ]; then
+        echo "SKIP: vrf sysctl does not exist"
+        exit 0
+fi
+
+cleanup &>/dev/null
+
+setup
+
+router_tests
+host2gateway_tests
+host_vpn_tests
+host_vpn_isolation_tests
+
+print_log_test_results
+
+cleanup &>/dev/null
+
+exit ${ret}
diff --git a/tools/testing/selftests/net/unicast_extensions.sh b/tools/testing/selftests/net/unicast_extensions.sh
index dbf0421986df..66354cdd5ce4 100755
--- a/tools/testing/selftests/net/unicast_extensions.sh
+++ b/tools/testing/selftests/net/unicast_extensions.sh
@@ -189,6 +189,15 @@ segmenttest 255.255.255.1 255.255.255.254 24 "assign and ping inside 255.255.255
 route_test 240.5.6.7 240.5.6.1  255.1.2.1    255.1.2.3      24 "route between 240.5.6/24 and 255.1.2/24 (is allowed)"
 route_test 0.200.6.7 0.200.38.1 245.99.101.1 245.99.200.111 16 "route between 0.200/16 and 245.99/16 (is allowed)"
 #
+# Test support for lowest address ending in .0
+segmenttest 5.10.15.20 5.10.15.0 24 "assign and ping lowest address (/24)"
+#
+# Test support for lowest address not ending in .0
+segmenttest 192.168.101.192 192.168.101.193 26 "assign and ping lowest address (/26)"
+#
+# Routing using lowest address as a gateway/endpoint
+route_test 192.168.42.1 192.168.42.0 9.8.7.6 9.8.7.0 24 "routing using lowest address"
+#
 # ==============================================
 # ==== TESTS THAT CURRENTLY EXPECT FAILURE =====
 # ==============================================
@@ -202,14 +211,6 @@ segmenttest 255.255.255.1 255.255.255.255 16 "assigning 255.255.255.255 (is forb
 # Currently Linux does not allow this, so this should fail too
 segmenttest 127.99.4.5 127.99.4.6 16 "assign and ping inside 127/8 (is forbidden)"
 #
-# Test support for lowest address
-# Currently Linux does not allow this, so this should fail too
-segmenttest 5.10.15.20 5.10.15.0 24 "assign and ping lowest address (is forbidden)"
-#
-# Routing using lowest address as a gateway/endpoint
-# Currently Linux does not allow this, so this should fail too
-route_test 192.168.42.1 192.168.42.0 9.8.7.6 9.8.7.0 24 "routing using lowest address (is forbidden)"
-#
 # Test support for unicast use of class D
 # Currently Linux does not allow this, so this should fail too
 segmenttest 225.1.2.3 225.1.2.200 24 "assign and ping class D address (is forbidden)"
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
index 41d783254b08..2aad4caa8581 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
@@ -446,6 +446,30 @@
         "teardown": []
     },
     {
+        "id": "ba5b",
+        "name": "Add vlan modify action for protocol 802.1Q setting priority 0",
+        "category": [
+            "actions",
+            "vlan"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action vlan",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action vlan modify protocol 802.1Q id 5 priority 0 index 100",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action vlan index 100",
+        "matchPattern": "action order [0-9]+: vlan.*modify id 100 priority 0 protocol 802.1Q pipe.*index 100 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action vlan"
+        ]
+    },
+    {
         "id": "6812",
         "name": "Add vlan modify action for protocol 802.1Q",
         "category": [
@@ -463,7 +487,7 @@
         "cmdUnderTest": "$TC actions add action vlan modify protocol 802.1Q id 5 index 100",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action vlan index 100",
-        "matchPattern": "action order [0-9]+: vlan.*modify id 100 protocol 802.1Q priority 0 pipe.*index 100 ref",
+        "matchPattern": "action order [0-9]+: vlan.*modify id 100 protocol 802.1Q pipe.*index 100 ref",
         "matchCount": "0",
         "teardown": [
             "$TC actions flush action vlan"
@@ -487,7 +511,7 @@
         "cmdUnderTest": "$TC actions add action vlan modify protocol 802.1ad id 500 reclassify index 12",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action vlan index 12",
-        "matchPattern": "action order [0-9]+: vlan.*modify id 500 protocol 802.1ad priority 0 reclassify.*index 12 ref",
+        "matchPattern": "action order [0-9]+: vlan.*modify id 500 protocol 802.1ad reclassify.*index 12 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action vlan"
diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c
index 93cbd6f603f9..2acbb7703c6a 100644
--- a/tools/testing/vsock/util.c
+++ b/tools/testing/vsock/util.c
@@ -84,7 +84,7 @@ void vsock_wait_remote_close(int fd)
 }
 
 /* Connect to <cid, port> and return the file descriptor. */
-int vsock_stream_connect(unsigned int cid, unsigned int port)
+static int vsock_connect(unsigned int cid, unsigned int port, int type)
 {
 	union {
 		struct sockaddr sa;
@@ -101,7 +101,7 @@ int vsock_stream_connect(unsigned int cid, unsigned int port)
 
 	control_expectln("LISTENING");
 
-	fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+	fd = socket(AF_VSOCK, type, 0);
 
 	timeout_begin(TIMEOUT);
 	do {
@@ -120,11 +120,21 @@ int vsock_stream_connect(unsigned int cid, unsigned int port)
 	return fd;
 }
 
+int vsock_stream_connect(unsigned int cid, unsigned int port)
+{
+	return vsock_connect(cid, port, SOCK_STREAM);
+}
+
+int vsock_seqpacket_connect(unsigned int cid, unsigned int port)
+{
+	return vsock_connect(cid, port, SOCK_SEQPACKET);
+}
+
 /* Listen on <cid, port> and return the first incoming connection.  The remote
  * address is stored to clientaddrp.  clientaddrp may be NULL.
  */
-int vsock_stream_accept(unsigned int cid, unsigned int port,
-			struct sockaddr_vm *clientaddrp)
+static int vsock_accept(unsigned int cid, unsigned int port,
+			struct sockaddr_vm *clientaddrp, int type)
 {
 	union {
 		struct sockaddr sa;
@@ -145,7 +155,7 @@ int vsock_stream_accept(unsigned int cid, unsigned int port,
 	int client_fd;
 	int old_errno;
 
-	fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+	fd = socket(AF_VSOCK, type, 0);
 
 	if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
 		perror("bind");
@@ -189,6 +199,18 @@ int vsock_stream_accept(unsigned int cid, unsigned int port,
 	return client_fd;
 }
 
+int vsock_stream_accept(unsigned int cid, unsigned int port,
+			struct sockaddr_vm *clientaddrp)
+{
+	return vsock_accept(cid, port, clientaddrp, SOCK_STREAM);
+}
+
+int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
+			   struct sockaddr_vm *clientaddrp)
+{
+	return vsock_accept(cid, port, clientaddrp, SOCK_SEQPACKET);
+}
+
 /* Transmit one byte and check the return value.
  *
  * expected_ret:
diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h
index e53dd09d26d9..a3375ad2fb7f 100644
--- a/tools/testing/vsock/util.h
+++ b/tools/testing/vsock/util.h
@@ -36,8 +36,11 @@ struct test_case {
 void init_signals(void);
 unsigned int parse_cid(const char *str);
 int vsock_stream_connect(unsigned int cid, unsigned int port);
+int vsock_seqpacket_connect(unsigned int cid, unsigned int port);
 int vsock_stream_accept(unsigned int cid, unsigned int port,
 			struct sockaddr_vm *clientaddrp);
+int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
+			   struct sockaddr_vm *clientaddrp);
 void vsock_wait_remote_close(int fd);
 void send_byte(int fd, int expected_ret, int flags);
 void recv_byte(int fd, int expected_ret, int flags);
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index 5a4fb80fa832..67766bfe176f 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -14,6 +14,8 @@
 #include <errno.h>
 #include <unistd.h>
 #include <linux/kernel.h>
+#include <sys/types.h>
+#include <sys/socket.h>
 
 #include "timeout.h"
 #include "control.h"
@@ -279,6 +281,110 @@ static void test_stream_msg_peek_server(const struct test_opts *opts)
 	close(fd);
 }
 
+#define MESSAGES_CNT 7
+static void test_seqpacket_msg_bounds_client(const struct test_opts *opts)
+{
+	int fd;
+
+	fd = vsock_seqpacket_connect(opts->peer_cid, 1234);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	/* Send several messages, one with MSG_EOR flag */
+	for (int i = 0; i < MESSAGES_CNT; i++)
+		send_byte(fd, 1, 0);
+
+	control_writeln("SENDDONE");
+	close(fd);
+}
+
+static void test_seqpacket_msg_bounds_server(const struct test_opts *opts)
+{
+	int fd;
+	char buf[16];
+	struct msghdr msg = {0};
+	struct iovec iov = {0};
+
+	fd = vsock_seqpacket_accept(VMADDR_CID_ANY, 1234, NULL);
+	if (fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	control_expectln("SENDDONE");
+	iov.iov_base = buf;
+	iov.iov_len = sizeof(buf);
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+
+	for (int i = 0; i < MESSAGES_CNT; i++) {
+		if (recvmsg(fd, &msg, 0) != 1) {
+			perror("message bound violated");
+			exit(EXIT_FAILURE);
+		}
+	}
+
+	close(fd);
+}
+
+#define MESSAGE_TRUNC_SZ 32
+static void test_seqpacket_msg_trunc_client(const struct test_opts *opts)
+{
+	int fd;
+	char buf[MESSAGE_TRUNC_SZ];
+
+	fd = vsock_seqpacket_connect(opts->peer_cid, 1234);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	if (send(fd, buf, sizeof(buf), 0) != sizeof(buf)) {
+		perror("send failed");
+		exit(EXIT_FAILURE);
+	}
+
+	control_writeln("SENDDONE");
+	close(fd);
+}
+
+static void test_seqpacket_msg_trunc_server(const struct test_opts *opts)
+{
+	int fd;
+	char buf[MESSAGE_TRUNC_SZ / 2];
+	struct msghdr msg = {0};
+	struct iovec iov = {0};
+
+	fd = vsock_seqpacket_accept(VMADDR_CID_ANY, 1234, NULL);
+	if (fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	control_expectln("SENDDONE");
+	iov.iov_base = buf;
+	iov.iov_len = sizeof(buf);
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+
+	ssize_t ret = recvmsg(fd, &msg, MSG_TRUNC);
+
+	if (ret != MESSAGE_TRUNC_SZ) {
+		printf("%zi\n", ret);
+		perror("MSG_TRUNC doesn't work");
+		exit(EXIT_FAILURE);
+	}
+
+	if (!(msg.msg_flags & MSG_TRUNC)) {
+		fprintf(stderr, "MSG_TRUNC expected\n");
+		exit(EXIT_FAILURE);
+	}
+
+	close(fd);
+}
+
 static struct test_case test_cases[] = {
 	{
 		.name = "SOCK_STREAM connection reset",
@@ -309,6 +415,16 @@ static struct test_case test_cases[] = {
 		.run_client = test_stream_msg_peek_client,
 		.run_server = test_stream_msg_peek_server,
 	},
+	{
+		.name = "SOCK_SEQPACKET msg bounds",
+		.run_client = test_seqpacket_msg_bounds_client,
+		.run_server = test_seqpacket_msg_bounds_server,
+	},
+	{
+		.name = "SOCK_SEQPACKET MSG_TRUNC flag",
+		.run_client = test_seqpacket_msg_trunc_client,
+		.run_server = test_seqpacket_msg_trunc_server,
+	},
 	{},
 };